diff options
Diffstat (limited to 'arch')
955 files changed, 36564 insertions, 15639 deletions
diff --git a/arch/alpha/include/asm/fcntl.h b/arch/alpha/include/asm/fcntl.h index 1b71ca70c9f6..6d9e805f18a7 100644 --- a/arch/alpha/include/asm/fcntl.h +++ b/arch/alpha/include/asm/fcntl.h @@ -51,8 +51,6 @@ #define F_EXLCK 16 /* or 3 */ #define F_SHLCK 32 /* or 4 */ -#define F_INPROGRESS 64 - #include <asm-generic/fcntl.h> #endif diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h index 4ac48a095f3a..2207fc61665d 100644 --- a/arch/alpha/include/asm/unistd.h +++ b/arch/alpha/include/asm/unistd.h @@ -457,10 +457,12 @@ #define __NR_clock_adjtime 499 #define __NR_syncfs 500 #define __NR_setns 501 +#define __NR_accept4 502 +#define __NR_sendmmsg 503 #ifdef __KERNEL__ -#define NR_SYSCALLS 502 +#define NR_SYSCALLS 504 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/alpha/kernel/srm_env.c b/arch/alpha/kernel/srm_env.c index f0df3fbd8402..b9fc6c309d2e 100644 --- a/arch/alpha/kernel/srm_env.c +++ b/arch/alpha/kernel/srm_env.c @@ -4,9 +4,8 @@ * * (C) 2001,2002,2006 by Jan-Benedict Glaw <jbglaw@lug-owl.de> * - * This driver is at all a modified version of Erik Mouw's - * Documentation/DocBook/procfs_example.c, so: thank - * you, Erik! He can be reached via email at + * This driver is a modified version of Erik Mouw's example proc + * interface, so: thank you, Erik! He can be reached via email at * <J.A.K.Mouw@its.tudelft.nl>. It is based on an idea * provided by DEC^WCompaq^WIntel's "Jumpstart" CD. They * included a patch like this as well. Thanks for idea! diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S index 6acea1f96de3..e534e1c5bc11 100644 --- a/arch/alpha/kernel/systbls.S +++ b/arch/alpha/kernel/systbls.S @@ -520,6 +520,8 @@ sys_call_table: .quad sys_clock_adjtime .quad sys_syncfs /* 500 */ .quad sys_setns + .quad sys_accept4 + .quad sys_sendmmsg .size sys_call_table, . - sys_call_table .type sys_call_table, @object diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 2d95b5b5cf49..1005367d0f9d 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -3,7 +3,7 @@ config ARM default y select HAVE_AOUT select HAVE_DMA_API_DEBUG - select HAVE_IDE + select HAVE_IDE if PCI || ISA || PCMCIA select HAVE_MEMBLOCK select RTC_LIB select SYS_SUPPORTS_APM_EMULATION @@ -29,6 +29,7 @@ config ARM select HAVE_GENERIC_HARDIRQS select HAVE_SPARSE_IRQ select GENERIC_IRQ_SHOW + select CPU_PM if (SUSPEND || CPU_IDLE) help The ARM series is a line of low-power-consumption RISC chip designs licensed by ARM Ltd and targeted at embedded applications and @@ -225,6 +226,10 @@ config PHYS_OFFSET Please provide the physical address corresponding to the location of main memory in your system. +config GENERIC_BUG + def_bool y + depends on BUG + source "init/Kconfig" source "kernel/Kconfig.freezer" @@ -358,7 +363,6 @@ config ARCH_GEMINI config ARCH_PRIMA2 bool "CSR SiRFSoC PRIMA2 ARM Cortex A9 Platform" select CPU_V7 - select GENERIC_TIME select NO_IOPORT select GENERIC_CLOCKEVENTS select CLKDEV_LOOKUP @@ -399,6 +403,7 @@ config ARCH_FOOTBRIDGE select CPU_SA110 select FOOTBRIDGE select GENERIC_CLOCKEVENTS + select HAVE_IDE select NEED_MACH_MEMORY_H help Support for systems based on the DC21285 companion chip @@ -537,7 +542,6 @@ config ARCH_LPC32XX select ARM_AMBA select USB_ARCH_HAS_OHCI select CLKDEV_LOOKUP - select GENERIC_TIME select GENERIC_CLOCKEVENTS help Support for the NXP LPC32XX family of processors @@ -617,7 +621,6 @@ config ARCH_TEGRA bool "NVIDIA Tegra" select CLKDEV_LOOKUP select CLKSRC_MMIO - select GENERIC_TIME select GENERIC_CLOCKEVENTS select GENERIC_GPIO select HAVE_CLK @@ -650,6 +653,8 @@ config ARCH_PXA select SPARSE_IRQ select AUTO_ZRELADDR select MULTI_IRQ_HANDLER + select ARM_CPU_SUSPEND if PM + select HAVE_IDE help Support for Intel/Marvell's PXA2xx/PXA3xx processor line. @@ -691,6 +696,7 @@ config ARCH_RPC select NO_IOPORT select ARCH_SPARSEMEM_ENABLE select ARCH_USES_GETTIMEOFFSET + select HAVE_IDE select NEED_MACH_MEMORY_H help On the Acorn Risc-PC, Linux can support the internal IDE disk and @@ -710,6 +716,7 @@ config ARCH_SA1100 select HAVE_SCHED_CLOCK select TICK_ONESHOT select ARCH_REQUIRE_GPIOLIB + select HAVE_IDE select NEED_MACH_MEMORY_H help Support for StrongARM 11x0 based boards. @@ -744,7 +751,6 @@ config ARCH_S3C64XX select ARCH_REQUIRE_GPIOLIB select SAMSUNG_CLKSRC select SAMSUNG_IRQ_VIC_TIMER - select SAMSUNG_IRQ_UART select S3C_GPIO_TRACK select S3C_GPIO_PULL_UPDOWN select S3C_GPIO_CFG_S3C24XX @@ -937,7 +943,6 @@ config ARCH_VT8500 config ARCH_ZYNQ bool "Xilinx Zynq ARM Cortex A9 Platform" select CPU_V7 - select GENERIC_TIME select GENERIC_CLOCKEVENTS select CLKDEV_LOOKUP select ARM_GIC @@ -1402,6 +1407,7 @@ config SMP MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || \ ARCH_EXYNOS4 || ARCH_TEGRA || ARCH_U8500 || ARCH_VEXPRESS_CA9X4 || \ ARCH_MSM_SCORPIONMP || ARCH_SHMOBILE + depends on MMU select USE_GENERIC_SMP_HELPERS select HAVE_ARM_SCU if !ARCH_MSM_SCORPIONMP help @@ -1415,7 +1421,7 @@ config SMP processor machines. On a single processor machine, the kernel will run faster if you say N here. - See also <file:Documentation/i386/IO-APIC.txt>, + See also <file:Documentation/x86/i386/IO-APIC.txt>, <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at <http://tldp.org/HOWTO/SMP-HOWTO.html>. @@ -1434,6 +1440,31 @@ config SMP_ON_UP If you don't know what to do here, say Y. +config ARM_CPU_TOPOLOGY + bool "Support cpu topology definition" + depends on SMP && CPU_V7 + default y + help + Support ARM cpu topology definition. The MPIDR register defines + affinity between processors which is then used to describe the cpu + topology of an ARM System. + +config SCHED_MC + bool "Multi-core scheduler support" + depends on ARM_CPU_TOPOLOGY + help + Multi-core scheduler support improves the CPU scheduler's decision + making when dealing with multi-core CPU chips at a cost of slightly + increased overhead in some places. If unsure say N here. + +config SCHED_SMT + bool "SMT scheduler support" + depends on ARM_CPU_TOPOLOGY + help + Improves the CPU scheduler's decision making when dealing with + MultiThreading at a cost of slightly increased overhead in some + places. If unsure say N here. + config HAVE_ARM_SCU bool help @@ -1509,6 +1540,7 @@ config THUMB2_KERNEL depends on CPU_V7 && !CPU_V6 && !CPU_V6K && EXPERIMENTAL select AEABI select ARM_ASM_UNIFIED + select ARM_UNWIND help By enabling this option, the kernel will be compiled in Thumb-2 mode. A compiler/assembler that understand the unified @@ -1834,6 +1866,38 @@ config ZBOOT_ROM_SH_MOBILE_SDHI endchoice +config ARM_APPENDED_DTB + bool "Use appended device tree blob to zImage (EXPERIMENTAL)" + depends on OF && !ZBOOT_ROM && EXPERIMENTAL + help + With this option, the boot code will look for a device tree binary + (DTB) appended to zImage + (e.g. cat zImage <filename>.dtb > zImage_w_dtb). + + This is meant as a backward compatibility convenience for those + systems with a bootloader that can't be upgraded to accommodate + the documented boot protocol using a device tree. + + Beware that there is very little in terms of protection against + this option being confused by leftover garbage in memory that might + look like a DTB header after a reboot if no actual DTB is appended + to zImage. Do not leave this option active in a production kernel + if you don't intend to always append a DTB. Proper passing of the + location into r2 of a bootloader provided DTB is always preferable + to this option. + +config ARM_ATAG_DTB_COMPAT + bool "Supplement the appended DTB with traditional ATAG information" + depends on ARM_APPENDED_DTB + help + Some old bootloaders can't be updated to a DTB capable one, yet + they provide ATAGs with memory configuration, the ramdisk address, + the kernel cmdline string, etc. Such information is dynamically + provided by the bootloader and can't always be stored in a static + DTB. To allow a device tree enabled kernel to be used with such + bootloaders, this option allows zImage to extract the information + from the ATAG list and store it at run time into the appended DTB. + config CMDLINE string "Default kernel command string" default "" @@ -2129,6 +2193,9 @@ config ARCH_SUSPEND_POSSIBLE CPU_V6 || CPU_V6K || CPU_V7 || CPU_XSC3 || CPU_XSCALE def_bool y +config ARM_CPU_SUSPEND + def_bool PM_SLEEP + endmenu source "net/Kconfig" diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 81cbe40c159c..f283938c2fc7 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -65,13 +65,71 @@ config DEBUG_USER # These options are only for real kernel hackers who want to get their hands dirty. config DEBUG_LL - bool "Kernel low-level debugging functions" + bool "Kernel low-level debugging functions (read help!)" depends on DEBUG_KERNEL help Say Y here to include definitions of printascii, printch, printhex in the kernel. This is helpful if you are debugging code that executes before the console is initialized. + Note that selecting this option will limit the kernel to a single + UART definition, as specified below. Attempting to boot the kernel + image on a different platform *will not work*, so this option should + not be enabled for kernels that are intended to be portable. + +choice + prompt "Kernel low-level debugging port" + depends on DEBUG_LL + + config DEBUG_LL_UART_NONE + bool "No low-level debugging UART" + help + Say Y here if your platform doesn't provide a UART option + below. This relies on your platform choosing the right UART + definition internally in order for low-level debugging to + work. + + config DEBUG_ICEDCC + bool "Kernel low-level debugging via EmbeddedICE DCC channel" + help + Say Y here if you want the debug print routines to direct + their output to the EmbeddedICE macrocell's DCC channel using + co-processor 14. This is known to work on the ARM9 style ICE + channel and on the XScale with the PEEDI. + + Note that the system will appear to hang during boot if there + is nothing connected to read from the DCC. + + config DEBUG_FOOTBRIDGE_COM1 + bool "Kernel low-level debugging messages via footbridge 8250 at PCI COM1" + depends on FOOTBRIDGE + help + Say Y here if you want the debug print routines to direct + their output to the 8250 at PCI COM1. + + config DEBUG_DC21285_PORT + bool "Kernel low-level debugging messages via footbridge serial port" + depends on FOOTBRIDGE + help + Say Y here if you want the debug print routines to direct + their output to the serial port in the DC21285 (Footbridge). + + config DEBUG_CLPS711X_UART1 + bool "Kernel low-level debugging messages via UART1" + depends on ARCH_CLPS711X + help + Say Y here if you want the debug print routines to direct + their output to the first serial port on these devices. + + config DEBUG_CLPS711X_UART2 + bool "Kernel low-level debugging messages via UART2" + depends on ARCH_CLPS711X + help + Say Y here if you want the debug print routines to direct + their output to the second serial port on these devices. + +endchoice + config EARLY_PRINTK bool "Early printk" depends on DEBUG_LL @@ -80,43 +138,14 @@ config EARLY_PRINTK kernel low-level debugging functions. Add earlyprintk to your kernel parameters to enable this console. -config DEBUG_ICEDCC - bool "Kernel low-level debugging via EmbeddedICE DCC channel" - depends on DEBUG_LL - help - Say Y here if you want the debug print routines to direct their - output to the EmbeddedICE macrocell's DCC channel using - co-processor 14. This is known to work on the ARM9 style ICE - channel and on the XScale with the PEEDI. - - It does include a timeout to ensure that the system does not - totally freeze when there is nothing connected to read. - config OC_ETM bool "On-chip ETM and ETB" - select ARM_AMBA + depends on ARM_AMBA help Enables the on-chip embedded trace macrocell and embedded trace buffer driver that will allow you to collect traces of the kernel code. -config DEBUG_DC21285_PORT - bool "Kernel low-level debugging messages via footbridge serial port" - depends on DEBUG_LL && FOOTBRIDGE - help - Say Y here if you want the debug print routines to direct their - output to the serial port in the DC21285 (Footbridge). Saying N - will cause the debug messages to appear on the first 16550 - serial port. - -config DEBUG_CLPS711X_UART2 - bool "Kernel low-level debugging messages via UART2" - depends on DEBUG_LL && ARCH_CLPS711X - help - Say Y here if you want the debug print routines to direct their - output to the second serial port on these devices. Saying N will - cause the debug messages to appear on the first serial port. - config DEBUG_S3C_UART depends on PLAT_SAMSUNG int "S3C UART to use for low-level debug" @@ -129,4 +158,10 @@ config DEBUG_S3C_UART The uncompressor code port configuration is now handled by CONFIG_S3C_LOWLEVEL_UART_PORT. +config ARM_KPROBES_TEST + tristate "Kprobes test module" + depends on KPROBES && MODULES + help + Perform tests of kprobes API and instruction set simulation. + endmenu diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile index a1edfd5a129a..176062ac7f07 100644 --- a/arch/arm/boot/Makefile +++ b/arch/arm/boot/Makefile @@ -78,7 +78,16 @@ endif $(obj)/uImage: STARTADDR=$(LOADADDR) +check_for_multiple_loadaddr = \ +if [ $(words $(LOADADDR)) -gt 1 ]; then \ + echo 'multiple load addresses: $(LOADADDR)'; \ + echo 'This is incompatible with uImages'; \ + echo 'Specify LOADADDR on the commandline to build an uImage'; \ + false; \ +fi + $(obj)/uImage: $(obj)/zImage FORCE + @$(check_for_multiple_loadaddr) $(call if_changed,uimage) @echo ' Image $@ is ready' diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore index c6028967d336..e0936a148516 100644 --- a/arch/arm/boot/compressed/.gitignore +++ b/arch/arm/boot/compressed/.gitignore @@ -5,3 +5,12 @@ piggy.lzo piggy.lzma vmlinux vmlinux.lds + +# borrowed libfdt files +fdt.c +fdt.h +fdt_ro.c +fdt_rw.c +fdt_wip.c +libfdt.h +libfdt_internal.h diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 0c74a6fab952..21f56ff32797 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -26,6 +26,10 @@ HEAD = head.o OBJS += misc.o decompress.o FONTC = $(srctree)/drivers/video/console/font_acorn_8x8.c +# string library code (-Os is enforced to keep it much smaller) +OBJS += string.o +CFLAGS_string.o := -Os + # # Architecture dependencies # @@ -89,21 +93,41 @@ suffix_$(CONFIG_KERNEL_GZIP) = gzip suffix_$(CONFIG_KERNEL_LZO) = lzo suffix_$(CONFIG_KERNEL_LZMA) = lzma +# Borrowed libfdt files for the ATAG compatibility mode + +libfdt := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c +libfdt_hdrs := fdt.h libfdt.h libfdt_internal.h + +libfdt_objs := $(addsuffix .o, $(basename $(libfdt))) + +$(addprefix $(obj)/,$(libfdt) $(libfdt_hdrs)): $(obj)/%: $(srctree)/scripts/dtc/libfdt/% + $(call cmd,shipped) + +$(addprefix $(obj)/,$(libfdt_objs) atags_to_fdt.o): \ + $(addprefix $(obj)/,$(libfdt_hdrs)) + +ifeq ($(CONFIG_ARM_ATAG_DTB_COMPAT),y) +OBJS += $(libfdt_objs) atags_to_fdt.o +endif + targets := vmlinux vmlinux.lds \ piggy.$(suffix_y) piggy.$(suffix_y).o \ - font.o font.c head.o misc.o $(OBJS) + lib1funcs.o lib1funcs.S font.o font.c head.o misc.o $(OBJS) # Make sure files are removed during clean -extra-y += piggy.gzip piggy.lzo piggy.lzma lib1funcs.S +extra-y += piggy.gzip piggy.lzo piggy.lzma lib1funcs.S $(libfdt) $(libfdt_hdrs) ifeq ($(CONFIG_FUNCTION_TRACER),y) ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS)) endif -ccflags-y := -fpic -fno-builtin +ccflags-y := -fpic -fno-builtin -I$(obj) asflags-y := -Wa,-march=all +# Supply kernel BSS size to the decompressor via a linker symbol. +KBSS_SZ = $(shell size $(obj)/../../../../vmlinux | awk 'END{print $$3}') +LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ) # Supply ZRELADDR to the decompressor via a linker symbol. ifneq ($(CONFIG_AUTO_ZRELADDR),y) LDFLAGS_vmlinux += --defsym zreladdr=$(ZRELADDR) @@ -123,7 +147,7 @@ LDFLAGS_vmlinux += -T # For __aeabi_uidivmod lib1funcs = $(obj)/lib1funcs.o -$(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S FORCE +$(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S $(call cmd,shipped) # We need to prevent any GOTOFF relocs being used with references @@ -139,8 +163,16 @@ bad_syms=$$($(CROSS_COMPILE)nm $@ | sed -n 's/^.\{8\} [bc] \(.*\)/\1/p') && \ ( echo "following symbols must have non local/private scope:" >&2; \ echo "$$bad_syms" >&2; rm -f $@; false ) +check_for_multiple_zreladdr = \ +if [ $(words $(ZRELADDR)) -gt 1 -a "$(CONFIG_AUTO_ZRELADDR)" = "" ]; then \ + echo 'multiple zreladdrs: $(ZRELADDR)'; \ + echo 'This needs CONFIG_AUTO_ZRELADDR to be set'; \ + false; \ +fi + $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \ $(addprefix $(obj)/, $(OBJS)) $(lib1funcs) FORCE + @$(check_for_multiple_zreladdr) $(call if_changed,ld) @$(check_for_bad_syms) diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c new file mode 100644 index 000000000000..6ce11c481178 --- /dev/null +++ b/arch/arm/boot/compressed/atags_to_fdt.c @@ -0,0 +1,97 @@ +#include <asm/setup.h> +#include <libfdt.h> + +static int node_offset(void *fdt, const char *node_path) +{ + int offset = fdt_path_offset(fdt, node_path); + if (offset == -FDT_ERR_NOTFOUND) + offset = fdt_add_subnode(fdt, 0, node_path); + return offset; +} + +static int setprop(void *fdt, const char *node_path, const char *property, + uint32_t *val_array, int size) +{ + int offset = node_offset(fdt, node_path); + if (offset < 0) + return offset; + return fdt_setprop(fdt, offset, property, val_array, size); +} + +static int setprop_string(void *fdt, const char *node_path, + const char *property, const char *string) +{ + int offset = node_offset(fdt, node_path); + if (offset < 0) + return offset; + return fdt_setprop_string(fdt, offset, property, string); +} + +static int setprop_cell(void *fdt, const char *node_path, + const char *property, uint32_t val) +{ + int offset = node_offset(fdt, node_path); + if (offset < 0) + return offset; + return fdt_setprop_cell(fdt, offset, property, val); +} + +/* + * Convert and fold provided ATAGs into the provided FDT. + * + * REturn values: + * = 0 -> pretend success + * = 1 -> bad ATAG (may retry with another possible ATAG pointer) + * < 0 -> error from libfdt + */ +int atags_to_fdt(void *atag_list, void *fdt, int total_space) +{ + struct tag *atag = atag_list; + uint32_t mem_reg_property[2 * NR_BANKS]; + int memcount = 0; + int ret; + + /* make sure we've got an aligned pointer */ + if ((u32)atag_list & 0x3) + return 1; + + /* if we get a DTB here we're done already */ + if (*(u32 *)atag_list == fdt32_to_cpu(FDT_MAGIC)) + return 0; + + /* validate the ATAG */ + if (atag->hdr.tag != ATAG_CORE || + (atag->hdr.size != tag_size(tag_core) && + atag->hdr.size != 2)) + return 1; + + /* let's give it all the room it could need */ + ret = fdt_open_into(fdt, fdt, total_space); + if (ret < 0) + return ret; + + for_each_tag(atag, atag_list) { + if (atag->hdr.tag == ATAG_CMDLINE) { + setprop_string(fdt, "/chosen", "bootargs", + atag->u.cmdline.cmdline); + } else if (atag->hdr.tag == ATAG_MEM) { + if (memcount >= sizeof(mem_reg_property)/4) + continue; + mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.start); + mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.size); + } else if (atag->hdr.tag == ATAG_INITRD2) { + uint32_t initrd_start, initrd_size; + initrd_start = atag->u.initrd.start; + initrd_size = atag->u.initrd.size; + setprop_cell(fdt, "/chosen", "linux,initrd-start", + initrd_start); + setprop_cell(fdt, "/chosen", "linux,initrd-end", + initrd_start + initrd_size); + } + } + + if (memcount) + setprop(fdt, "/memory", "reg", mem_reg_property, 4*memcount); + + return fdt_pack(fdt); +} diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index e95a5989602a..c2effc917254 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -216,6 +216,104 @@ restart: adr r0, LC0 mov r10, r6 #endif + mov r5, #0 @ init dtb size to 0 +#ifdef CONFIG_ARM_APPENDED_DTB +/* + * r0 = delta + * r2 = BSS start + * r3 = BSS end + * r4 = final kernel address + * r5 = appended dtb size (still unknown) + * r6 = _edata + * r7 = architecture ID + * r8 = atags/device tree pointer + * r9 = size of decompressed image + * r10 = end of this image, including bss/stack/malloc space if non XIP + * r11 = GOT start + * r12 = GOT end + * sp = stack pointer + * + * if there are device trees (dtb) appended to zImage, advance r10 so that the + * dtb data will get relocated along with the kernel if necessary. + */ + + ldr lr, [r6, #0] +#ifndef __ARMEB__ + ldr r1, =0xedfe0dd0 @ sig is 0xd00dfeed big endian +#else + ldr r1, =0xd00dfeed +#endif + cmp lr, r1 + bne dtb_check_done @ not found + +#ifdef CONFIG_ARM_ATAG_DTB_COMPAT + /* + * OK... Let's do some funky business here. + * If we do have a DTB appended to zImage, and we do have + * an ATAG list around, we want the later to be translated + * and folded into the former here. To be on the safe side, + * let's temporarily move the stack away into the malloc + * area. No GOT fixup has occurred yet, but none of the + * code we're about to call uses any global variable. + */ + add sp, sp, #0x10000 + stmfd sp!, {r0-r3, ip, lr} + mov r0, r8 + mov r1, r6 + sub r2, sp, r6 + bl atags_to_fdt + + /* + * If returned value is 1, there is no ATAG at the location + * pointed by r8. Try the typical 0x100 offset from start + * of RAM and hope for the best. + */ + cmp r0, #1 + sub r0, r4, #TEXT_OFFSET + add r0, r0, #0x100 + mov r1, r6 + sub r2, sp, r6 + blne atags_to_fdt + + ldmfd sp!, {r0-r3, ip, lr} + sub sp, sp, #0x10000 +#endif + + mov r8, r6 @ use the appended device tree + + /* + * Make sure that the DTB doesn't end up in the final + * kernel's .bss area. To do so, we adjust the decompressed + * kernel size to compensate if that .bss size is larger + * than the relocated code. + */ + ldr r5, =_kernel_bss_size + adr r1, wont_overwrite + sub r1, r6, r1 + subs r1, r5, r1 + addhi r9, r9, r1 + + /* Get the dtb's size */ + ldr r5, [r6, #4] +#ifndef __ARMEB__ + /* convert r5 (dtb size) to little endian */ + eor r1, r5, r5, ror #16 + bic r1, r1, #0x00ff0000 + mov r5, r5, ror #8 + eor r5, r5, r1, lsr #8 +#endif + + /* preserve 64-bit alignment */ + add r5, r5, #7 + bic r5, r5, #7 + + /* relocate some pointers past the appended dtb */ + add r6, r6, r5 + add r10, r10, r5 + add sp, sp, r5 +dtb_check_done: +#endif + /* * Check to see if we will overwrite ourselves. * r4 = final kernel address @@ -223,15 +321,14 @@ restart: adr r0, LC0 * r10 = end of this image, including bss/stack/malloc space if non XIP * We basically want: * r4 - 16k page directory >= r10 -> OK - * r4 + image length <= current position (pc) -> OK + * r4 + image length <= address of wont_overwrite -> OK */ add r10, r10, #16384 cmp r4, r10 bhs wont_overwrite add r10, r4, r9 - ARM( cmp r10, pc ) - THUMB( mov lr, pc ) - THUMB( cmp r10, lr ) + adr r9, wont_overwrite + cmp r10, r9 bls wont_overwrite /* @@ -285,14 +382,16 @@ wont_overwrite: * r2 = BSS start * r3 = BSS end * r4 = kernel execution address + * r5 = appended dtb size (0 if not present) * r7 = architecture ID * r8 = atags pointer * r11 = GOT start * r12 = GOT end * sp = stack pointer */ - teq r0, #0 + orrs r1, r0, r5 beq not_relocated + add r11, r11, r0 add r12, r12, r0 @@ -307,12 +406,21 @@ wont_overwrite: /* * Relocate all entries in the GOT table. + * Bump bss entries to _edata + dtb size */ 1: ldr r1, [r11, #0] @ relocate entries in the GOT - add r1, r1, r0 @ table. This fixes up the - str r1, [r11], #4 @ C references. + add r1, r1, r0 @ This fixes up C references + cmp r1, r2 @ if entry >= bss_start && + cmphs r3, r1 @ bss_end > entry + addhi r1, r1, r5 @ entry += dtb size + str r1, [r11], #4 @ next entry cmp r11, r12 blo 1b + + /* bump our bss pointers too */ + add r2, r2, r5 + add r3, r3, r5 + #else /* diff --git a/arch/arm/boot/compressed/libfdt_env.h b/arch/arm/boot/compressed/libfdt_env.h new file mode 100644 index 000000000000..1f4e71876b00 --- /dev/null +++ b/arch/arm/boot/compressed/libfdt_env.h @@ -0,0 +1,15 @@ +#ifndef _ARM_LIBFDT_ENV_H +#define _ARM_LIBFDT_ENV_H + +#include <linux/types.h> +#include <linux/string.h> +#include <asm/byteorder.h> + +#define fdt16_to_cpu(x) be16_to_cpu(x) +#define cpu_to_fdt16(x) cpu_to_be16(x) +#define fdt32_to_cpu(x) be32_to_cpu(x) +#define cpu_to_fdt32(x) cpu_to_be32(x) +#define fdt64_to_cpu(x) be64_to_cpu(x) +#define cpu_to_fdt64(x) cpu_to_be64(x) + +#endif diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c index 832d37236c59..8e2a8fca5ed2 100644 --- a/arch/arm/boot/compressed/misc.c +++ b/arch/arm/boot/compressed/misc.c @@ -18,14 +18,9 @@ unsigned int __machine_arch_type; -#define _LINUX_STRING_H_ - #include <linux/compiler.h> /* for inline */ -#include <linux/types.h> /* for size_t */ -#include <linux/stddef.h> /* for NULL */ +#include <linux/types.h> #include <linux/linkage.h> -#include <asm/string.h> - static void putstr(const char *ptr); extern void error(char *x); @@ -101,41 +96,6 @@ static void putstr(const char *ptr) flush(); } - -void *memcpy(void *__dest, __const void *__src, size_t __n) -{ - int i = 0; - unsigned char *d = (unsigned char *)__dest, *s = (unsigned char *)__src; - - for (i = __n >> 3; i > 0; i--) { - *d++ = *s++; - *d++ = *s++; - *d++ = *s++; - *d++ = *s++; - *d++ = *s++; - *d++ = *s++; - *d++ = *s++; - *d++ = *s++; - } - - if (__n & 1 << 2) { - *d++ = *s++; - *d++ = *s++; - *d++ = *s++; - *d++ = *s++; - } - - if (__n & 1 << 1) { - *d++ = *s++; - *d++ = *s++; - } - - if (__n & 1) - *d++ = *s++; - - return __dest; -} - /* * gzip declarations */ diff --git a/arch/arm/boot/compressed/string.c b/arch/arm/boot/compressed/string.c new file mode 100644 index 000000000000..36e53ef9200f --- /dev/null +++ b/arch/arm/boot/compressed/string.c @@ -0,0 +1,127 @@ +/* + * arch/arm/boot/compressed/string.c + * + * Small subset of simple string routines + */ + +#include <linux/string.h> + +void *memcpy(void *__dest, __const void *__src, size_t __n) +{ + int i = 0; + unsigned char *d = (unsigned char *)__dest, *s = (unsigned char *)__src; + + for (i = __n >> 3; i > 0; i--) { + *d++ = *s++; + *d++ = *s++; + *d++ = *s++; + *d++ = *s++; + *d++ = *s++; + *d++ = *s++; + *d++ = *s++; + *d++ = *s++; + } + + if (__n & 1 << 2) { + *d++ = *s++; + *d++ = *s++; + *d++ = *s++; + *d++ = *s++; + } + + if (__n & 1 << 1) { + *d++ = *s++; + *d++ = *s++; + } + + if (__n & 1) + *d++ = *s++; + + return __dest; +} + +void *memmove(void *__dest, __const void *__src, size_t count) +{ + unsigned char *d = __dest; + const unsigned char *s = __src; + + if (__dest == __src) + return __dest; + + if (__dest < __src) + return memcpy(__dest, __src, count); + + while (count--) + d[count] = s[count]; + return __dest; +} + +size_t strlen(const char *s) +{ + const char *sc = s; + + while (*sc != '\0') + sc++; + return sc - s; +} + +int memcmp(const void *cs, const void *ct, size_t count) +{ + const unsigned char *su1 = cs, *su2 = ct, *end = su1 + count; + int res = 0; + + while (su1 < end) { + res = *su1++ - *su2++; + if (res) + break; + } + return res; +} + +int strcmp(const char *cs, const char *ct) +{ + unsigned char c1, c2; + int res = 0; + + do { + c1 = *cs++; + c2 = *ct++; + res = c1 - c2; + if (res) + break; + } while (c1); + return res; +} + +void *memchr(const void *s, int c, size_t count) +{ + const unsigned char *p = s; + + while (count--) + if ((unsigned char)c == *p++) + return (void *)(p - 1); + return NULL; +} + +char *strchr(const char *s, int c) +{ + while (*s != (char)c) + if (*s++ == '\0') + return NULL; + return (char *)s; +} + +#undef memset + +void *memset(void *s, int c, size_t count) +{ + char *xs = s; + while (count--) + *xs++ = c; + return s; +} + +void __memzero(void *s, size_t count) +{ + memset(s, 0, count); +} diff --git a/arch/arm/boot/compressed/vmlinux.lds.in b/arch/arm/boot/compressed/vmlinux.lds.in index 4e728834a1b9..4919f2ac8b89 100644 --- a/arch/arm/boot/compressed/vmlinux.lds.in +++ b/arch/arm/boot/compressed/vmlinux.lds.in @@ -51,6 +51,10 @@ SECTIONS _got_start = .; .got : { *(.got) } _got_end = .; + + /* ensure the zImage file size is always a multiple of 64 bits */ + /* (without a dummy byte, ld just ignores the empty section) */ + .pad : { BYTE(0); . = ALIGN(8); } _edata = .; . = BSS_START; diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c index 3227ca952a12..a8fc6b237592 100644 --- a/arch/arm/common/gic.c +++ b/arch/arm/common/gic.c @@ -26,14 +26,18 @@ #include <linux/kernel.h> #include <linux/list.h> #include <linux/smp.h> +#include <linux/cpu_pm.h> #include <linux/cpumask.h> #include <linux/io.h> +#include <linux/interrupt.h> +#include <linux/percpu.h> +#include <linux/slab.h> #include <asm/irq.h> #include <asm/mach/irq.h> #include <asm/hardware/gic.h> -static DEFINE_SPINLOCK(irq_controller_lock); +static DEFINE_RAW_SPINLOCK(irq_controller_lock); /* Address of GIC 0 CPU interface */ void __iomem *gic_cpu_base_addr __read_mostly; @@ -82,30 +86,30 @@ static void gic_mask_irq(struct irq_data *d) { u32 mask = 1 << (d->irq % 32); - spin_lock(&irq_controller_lock); + raw_spin_lock(&irq_controller_lock); writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_CLEAR + (gic_irq(d) / 32) * 4); if (gic_arch_extn.irq_mask) gic_arch_extn.irq_mask(d); - spin_unlock(&irq_controller_lock); + raw_spin_unlock(&irq_controller_lock); } static void gic_unmask_irq(struct irq_data *d) { u32 mask = 1 << (d->irq % 32); - spin_lock(&irq_controller_lock); + raw_spin_lock(&irq_controller_lock); if (gic_arch_extn.irq_unmask) gic_arch_extn.irq_unmask(d); writel_relaxed(mask, gic_dist_base(d) + GIC_DIST_ENABLE_SET + (gic_irq(d) / 32) * 4); - spin_unlock(&irq_controller_lock); + raw_spin_unlock(&irq_controller_lock); } static void gic_eoi_irq(struct irq_data *d) { if (gic_arch_extn.irq_eoi) { - spin_lock(&irq_controller_lock); + raw_spin_lock(&irq_controller_lock); gic_arch_extn.irq_eoi(d); - spin_unlock(&irq_controller_lock); + raw_spin_unlock(&irq_controller_lock); } writel_relaxed(gic_irq(d), gic_cpu_base(d) + GIC_CPU_EOI); @@ -129,7 +133,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) if (type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING) return -EINVAL; - spin_lock(&irq_controller_lock); + raw_spin_lock(&irq_controller_lock); if (gic_arch_extn.irq_set_type) gic_arch_extn.irq_set_type(d, type); @@ -154,7 +158,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) if (enabled) writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff); - spin_unlock(&irq_controller_lock); + raw_spin_unlock(&irq_controller_lock); return 0; } @@ -180,12 +184,12 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, return -EINVAL; mask = 0xff << shift; - bit = 1 << (cpu + shift); + bit = 1 << (cpu_logical_map(cpu) + shift); - spin_lock(&irq_controller_lock); + raw_spin_lock(&irq_controller_lock); val = readl_relaxed(reg) & ~mask; writel_relaxed(val | bit, reg); - spin_unlock(&irq_controller_lock); + raw_spin_unlock(&irq_controller_lock); return IRQ_SET_MASK_OK; } @@ -215,9 +219,9 @@ static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc) chained_irq_enter(chip, desc); - spin_lock(&irq_controller_lock); + raw_spin_lock(&irq_controller_lock); status = readl_relaxed(chip_data->cpu_base + GIC_CPU_INTACK); - spin_unlock(&irq_controller_lock); + raw_spin_unlock(&irq_controller_lock); gic_irq = (status & 0x3ff); if (gic_irq == 1023) @@ -259,9 +263,16 @@ static void __init gic_dist_init(struct gic_chip_data *gic, unsigned int irq_start) { unsigned int gic_irqs, irq_limit, i; + u32 cpumask; void __iomem *base = gic->dist_base; - u32 cpumask = 1 << smp_processor_id(); + u32 cpu = 0; + u32 nrppis = 0, ppi_base = 0; +#ifdef CONFIG_SMP + cpu = cpu_logical_map(smp_processor_id()); +#endif + + cpumask = 1 << cpu; cpumask |= cpumask << 8; cpumask |= cpumask << 16; @@ -276,6 +287,25 @@ static void __init gic_dist_init(struct gic_chip_data *gic, if (gic_irqs > 1020) gic_irqs = 1020; + gic->gic_irqs = gic_irqs; + + /* + * Nobody would be insane enough to use PPIs on a secondary + * GIC, right? + */ + if (gic == &gic_data[0]) { + nrppis = (32 - irq_start) & 31; + + /* The GIC only supports up to 16 PPIs. */ + if (nrppis > 16) + BUG(); + + ppi_base = gic->irq_offset + 32 - nrppis; + } + + pr_info("Configuring GIC with %d sources (%d PPIs)\n", + gic_irqs, (gic == &gic_data[0]) ? nrppis : 0); + /* * Set all global interrupts to be level triggered, active low. */ @@ -311,7 +341,17 @@ static void __init gic_dist_init(struct gic_chip_data *gic, /* * Setup the Linux IRQ subsystem. */ - for (i = irq_start; i < irq_limit; i++) { + for (i = 0; i < nrppis; i++) { + int ppi = i + ppi_base; + + irq_set_percpu_devid(ppi); + irq_set_chip_and_handler(ppi, &gic_chip, + handle_percpu_devid_irq); + irq_set_chip_data(ppi, gic); + set_irq_flags(ppi, IRQF_VALID | IRQF_NOAUTOEN); + } + + for (i = irq_start + nrppis; i < irq_limit; i++) { irq_set_chip_and_handler(i, &gic_chip, handle_fasteoi_irq); irq_set_chip_data(i, gic); set_irq_flags(i, IRQF_VALID | IRQF_PROBE); @@ -343,6 +383,189 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic) writel_relaxed(1, base + GIC_CPU_CTRL); } +#ifdef CONFIG_CPU_PM +/* + * Saves the GIC distributor registers during suspend or idle. Must be called + * with interrupts disabled but before powering down the GIC. After calling + * this function, no interrupts will be delivered by the GIC, and another + * platform-specific wakeup source must be enabled. + */ +static void gic_dist_save(unsigned int gic_nr) +{ + unsigned int gic_irqs; + void __iomem *dist_base; + int i; + + if (gic_nr >= MAX_GIC_NR) + BUG(); + + gic_irqs = gic_data[gic_nr].gic_irqs; + dist_base = gic_data[gic_nr].dist_base; + + if (!dist_base) + return; + + for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++) + gic_data[gic_nr].saved_spi_conf[i] = + readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4); + + for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++) + gic_data[gic_nr].saved_spi_target[i] = + readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4); + + for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) + gic_data[gic_nr].saved_spi_enable[i] = + readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4); +} + +/* + * Restores the GIC distributor registers during resume or when coming out of + * idle. Must be called before enabling interrupts. If a level interrupt + * that occured while the GIC was suspended is still present, it will be + * handled normally, but any edge interrupts that occured will not be seen by + * the GIC and need to be handled by the platform-specific wakeup source. + */ +static void gic_dist_restore(unsigned int gic_nr) +{ + unsigned int gic_irqs; + unsigned int i; + void __iomem *dist_base; + + if (gic_nr >= MAX_GIC_NR) + BUG(); + + gic_irqs = gic_data[gic_nr].gic_irqs; + dist_base = gic_data[gic_nr].dist_base; + + if (!dist_base) + return; + + writel_relaxed(0, dist_base + GIC_DIST_CTRL); + + for (i = 0; i < DIV_ROUND_UP(gic_irqs, 16); i++) + writel_relaxed(gic_data[gic_nr].saved_spi_conf[i], + dist_base + GIC_DIST_CONFIG + i * 4); + + for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++) + writel_relaxed(0xa0a0a0a0, + dist_base + GIC_DIST_PRI + i * 4); + + for (i = 0; i < DIV_ROUND_UP(gic_irqs, 4); i++) + writel_relaxed(gic_data[gic_nr].saved_spi_target[i], + dist_base + GIC_DIST_TARGET + i * 4); + + for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) + writel_relaxed(gic_data[gic_nr].saved_spi_enable[i], + dist_base + GIC_DIST_ENABLE_SET + i * 4); + + writel_relaxed(1, dist_base + GIC_DIST_CTRL); +} + +static void gic_cpu_save(unsigned int gic_nr) +{ + int i; + u32 *ptr; + void __iomem *dist_base; + void __iomem *cpu_base; + + if (gic_nr >= MAX_GIC_NR) + BUG(); + + dist_base = gic_data[gic_nr].dist_base; + cpu_base = gic_data[gic_nr].cpu_base; + + if (!dist_base || !cpu_base) + return; + + ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable); + for (i = 0; i < DIV_ROUND_UP(32, 32); i++) + ptr[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4); + + ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf); + for (i = 0; i < DIV_ROUND_UP(32, 16); i++) + ptr[i] = readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4); + +} + +static void gic_cpu_restore(unsigned int gic_nr) +{ + int i; + u32 *ptr; + void __iomem *dist_base; + void __iomem *cpu_base; + + if (gic_nr >= MAX_GIC_NR) + BUG(); + + dist_base = gic_data[gic_nr].dist_base; + cpu_base = gic_data[gic_nr].cpu_base; + + if (!dist_base || !cpu_base) + return; + + ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_enable); + for (i = 0; i < DIV_ROUND_UP(32, 32); i++) + writel_relaxed(ptr[i], dist_base + GIC_DIST_ENABLE_SET + i * 4); + + ptr = __this_cpu_ptr(gic_data[gic_nr].saved_ppi_conf); + for (i = 0; i < DIV_ROUND_UP(32, 16); i++) + writel_relaxed(ptr[i], dist_base + GIC_DIST_CONFIG + i * 4); + + for (i = 0; i < DIV_ROUND_UP(32, 4); i++) + writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4); + + writel_relaxed(0xf0, cpu_base + GIC_CPU_PRIMASK); + writel_relaxed(1, cpu_base + GIC_CPU_CTRL); +} + +static int gic_notifier(struct notifier_block *self, unsigned long cmd, void *v) +{ + int i; + + for (i = 0; i < MAX_GIC_NR; i++) { + switch (cmd) { + case CPU_PM_ENTER: + gic_cpu_save(i); + break; + case CPU_PM_ENTER_FAILED: + case CPU_PM_EXIT: + gic_cpu_restore(i); + break; + case CPU_CLUSTER_PM_ENTER: + gic_dist_save(i); + break; + case CPU_CLUSTER_PM_ENTER_FAILED: + case CPU_CLUSTER_PM_EXIT: + gic_dist_restore(i); + break; + } + } + + return NOTIFY_OK; +} + +static struct notifier_block gic_notifier_block = { + .notifier_call = gic_notifier, +}; + +static void __init gic_pm_init(struct gic_chip_data *gic) +{ + gic->saved_ppi_enable = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4, + sizeof(u32)); + BUG_ON(!gic->saved_ppi_enable); + + gic->saved_ppi_conf = __alloc_percpu(DIV_ROUND_UP(32, 16) * 4, + sizeof(u32)); + BUG_ON(!gic->saved_ppi_conf); + + cpu_pm_register_notifier(&gic_notifier_block); +} +#else +static void __init gic_pm_init(struct gic_chip_data *gic) +{ +} +#endif + void __init gic_init(unsigned int gic_nr, unsigned int irq_start, void __iomem *dist_base, void __iomem *cpu_base) { @@ -358,8 +581,10 @@ void __init gic_init(unsigned int gic_nr, unsigned int irq_start, if (gic_nr == 0) gic_cpu_base_addr = cpu_base; + gic_chip.flags |= gic_arch_extn.flags; gic_dist_init(gic, irq_start); gic_cpu_init(gic); + gic_pm_init(gic); } void __cpuinit gic_secondary_init(unsigned int gic_nr) @@ -369,20 +594,15 @@ void __cpuinit gic_secondary_init(unsigned int gic_nr) gic_cpu_init(&gic_data[gic_nr]); } -void __cpuinit gic_enable_ppi(unsigned int irq) -{ - unsigned long flags; - - local_irq_save(flags); - irq_set_status_flags(irq, IRQ_NOPROBE); - gic_unmask_irq(irq_get_irq_data(irq)); - local_irq_restore(flags); -} - #ifdef CONFIG_SMP void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) { - unsigned long map = *cpus_addr(*mask); + int cpu; + unsigned long map = 0; + + /* Convert our logical CPU mask into a physical one. */ + for_each_cpu(cpu, mask) + map |= 1 << cpu_logical_map(cpu); /* * Ensure that stores to Normal memory are visible to the diff --git a/arch/arm/common/pl330.c b/arch/arm/common/pl330.c index 97912fa48782..7129cfbdacd6 100644 --- a/arch/arm/common/pl330.c +++ b/arch/arm/common/pl330.c @@ -1546,7 +1546,7 @@ int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op) /* Start the next */ case PL330_OP_START: - if (!_start(thrd)) + if (!_thrd_active(thrd) && !_start(thrd)) ret = -EIO; break; diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c index 0569de6acfba..61691cdbdcf2 100644 --- a/arch/arm/common/sa1111.c +++ b/arch/arm/common/sa1111.c @@ -718,6 +718,10 @@ __sa1111_probe(struct device *me, struct resource *mem, int irq) goto err_free; } + ret = clk_prepare(sachip->clk); + if (ret) + goto err_clkput; + spin_lock_init(&sachip->lock); sachip->dev = me; @@ -733,7 +737,7 @@ __sa1111_probe(struct device *me, struct resource *mem, int irq) sachip->base = ioremap(mem->start, PAGE_SIZE * 2); if (!sachip->base) { ret = -ENOMEM; - goto err_clkput; + goto err_clk_unprep; } /* @@ -809,6 +813,8 @@ __sa1111_probe(struct device *me, struct resource *mem, int irq) err_unmap: iounmap(sachip->base); + err_clk_unprep: + clk_unprepare(sachip->clk); err_clkput: clk_put(sachip->clk); err_free: @@ -835,6 +841,7 @@ static void __sa1111_remove(struct sa1111 *sachip) sa1111_writel(0, irqbase + SA1111_WAKEEN1); clk_disable(sachip->clk); + clk_unprepare(sachip->clk); if (sachip->irq != NO_IRQ) { irq_set_chained_handler(sachip->irq, NULL); diff --git a/arch/arm/common/timer-sp.c b/arch/arm/common/timer-sp.c index 41df47875122..2393b5bc96fa 100644 --- a/arch/arm/common/timer-sp.c +++ b/arch/arm/common/timer-sp.c @@ -41,9 +41,17 @@ static long __init sp804_get_clock_rate(const char *name) return PTR_ERR(clk); } + err = clk_prepare(clk); + if (err) { + pr_err("sp804: %s clock failed to prepare: %d\n", name, err); + clk_put(clk); + return err; + } + err = clk_enable(clk); if (err) { pr_err("sp804: %s clock failed to enable: %d\n", name, err); + clk_unprepare(clk); clk_put(clk); return err; } @@ -52,6 +60,7 @@ static long __init sp804_get_clock_rate(const char *name) if (rate < 0) { pr_err("sp804: %s clock failed to get rate: %ld\n", name, rate); clk_disable(clk); + clk_unprepare(clk); clk_put(clk); } diff --git a/arch/arm/common/vic.c b/arch/arm/common/vic.c index 7aa4262ada7a..01f18a421b17 100644 --- a/arch/arm/common/vic.c +++ b/arch/arm/common/vic.c @@ -259,7 +259,6 @@ static void __init vic_disable(void __iomem *base) writel(0, base + VIC_INT_SELECT); writel(0, base + VIC_INT_ENABLE); writel(~0, base + VIC_INT_ENABLE_CLEAR); - writel(0, base + VIC_IRQ_STATUS); writel(0, base + VIC_ITCR); writel(~0, base + VIC_INT_SOFT_CLEAR); } @@ -347,7 +346,8 @@ void __init vic_init(void __iomem *base, unsigned int irq_start, /* Identify which VIC cell this one is, by reading the ID */ for (i = 0; i < 4; i++) { - u32 addr = ((u32)base & PAGE_MASK) + 0xfe0 + (i * 4); + void __iomem *addr; + addr = (void __iomem *)((u32)base & PAGE_MASK) + 0xfe0 + (i * 4); cellid |= (readl(addr) & 0xff) << (8 * i); } vendor = (cellid >> 12) & 0xff; diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig index 7196ade07e27..1103f62a1964 100644 --- a/arch/arm/configs/integrator_defconfig +++ b/arch/arm/configs/integrator_defconfig @@ -1,5 +1,6 @@ CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y +CONFIG_TINY_RCU=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -8,20 +9,29 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_ARCH_INTEGRATOR=y CONFIG_ARCH_INTEGRATOR_AP=y +CONFIG_ARCH_INTEGRATOR_CP=y CONFIG_CPU_ARM720T=y CONFIG_CPU_ARM920T=y +CONFIG_CPU_ARM922T=y +CONFIG_CPU_ARM926T=y +CONFIG_CPU_ARM1020=y +CONFIG_CPU_ARM1022=y +CONFIG_CPU_ARM1026=y CONFIG_PCI=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_PREEMPT=y +CONFIG_AEABI=y CONFIG_LEDS=y CONFIG_LEDS_CPU=y CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="console=ttyAM0,38400n8 root=/dev/nfs ip=bootp mem=32M" +CONFIG_CMDLINE="console=ttyAM0,38400n8 root=/dev/nfs ip=bootp" CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_FPE_NWFPE=y -CONFIG_PM=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -32,7 +42,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y # CONFIG_IPV6 is not set CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_AFS_PARTS=y CONFIG_MTD_CHAR=y @@ -40,6 +49,7 @@ CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_ADV_OPTIONS=y CONFIG_MTD_CFI_INTELEXT=y +CONFIG_MTD_PHYSMAP=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 @@ -56,6 +66,8 @@ CONFIG_FB_MODE_HELPERS=y CONFIG_FB_MATROX=y CONFIG_FB_MATROX_MILLENIUM=y CONFIG_FB_MATROX_MYSTIQUE=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_PL030=y CONFIG_EXT2_FS=y CONFIG_TMPFS=y CONFIG_JFFS2_FS=y @@ -68,4 +80,3 @@ CONFIG_NFSD_V3=y CONFIG_PARTITION_ADVANCED=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_ERRORS=y diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index 6550db3aa5c7..960abceb8e14 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -1,3 +1,20 @@ include include/asm-generic/Kbuild.asm header-y += hwcap.h + +generic-y += auxvec.h +generic-y += bitsperlong.h +generic-y += cputime.h +generic-y += emergency-restart.h +generic-y += errno.h +generic-y += ioctl.h +generic-y += irq_regs.h +generic-y += kdebug.h +generic-y += local.h +generic-y += local64.h +generic-y += percpu.h +generic-y += poll.h +generic-y += resource.h +generic-y += sections.h +generic-y += siginfo.h +generic-y += sizes.h diff --git a/arch/arm/include/asm/auxvec.h b/arch/arm/include/asm/auxvec.h deleted file mode 100644 index c0536f6b29a7..000000000000 --- a/arch/arm/include/asm/auxvec.h +++ /dev/null @@ -1,4 +0,0 @@ -#ifndef __ASMARM_AUXVEC_H -#define __ASMARM_AUXVEC_H - -#endif diff --git a/arch/arm/include/asm/bitsperlong.h b/arch/arm/include/asm/bitsperlong.h deleted file mode 100644 index 6dc0bb0c13b2..000000000000 --- a/arch/arm/include/asm/bitsperlong.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/bitsperlong.h> diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h index 4d88425a4169..9abe7a07d5ac 100644 --- a/arch/arm/include/asm/bug.h +++ b/arch/arm/include/asm/bug.h @@ -3,21 +3,58 @@ #ifdef CONFIG_BUG -#ifdef CONFIG_DEBUG_BUGVERBOSE -extern void __bug(const char *file, int line) __attribute__((noreturn)); - -/* give file/line information */ -#define BUG() __bug(__FILE__, __LINE__) +/* + * Use a suitable undefined instruction to use for ARM/Thumb2 bug handling. + * We need to be careful not to conflict with those used by other modules and + * the register_undef_hook() system. + */ +#ifdef CONFIG_THUMB2_KERNEL +#define BUG_INSTR_VALUE 0xde02 +#define BUG_INSTR_TYPE ".hword " #else +#define BUG_INSTR_VALUE 0xe7f001f2 +#define BUG_INSTR_TYPE ".word " +#endif -/* this just causes an oops */ -#define BUG() do { *(int *)0 = 0; } while (1) -#endif +#define BUG() _BUG(__FILE__, __LINE__, BUG_INSTR_VALUE) +#define _BUG(file, line, value) __BUG(file, line, value) + +#ifdef CONFIG_DEBUG_BUGVERBOSE + +/* + * The extra indirection is to ensure that the __FILE__ string comes through + * OK. Many version of gcc do not support the asm %c parameter which would be + * preferable to this unpleasantness. We use mergeable string sections to + * avoid multiple copies of the string appearing in the kernel image. + */ + +#define __BUG(__file, __line, __value) \ +do { \ + BUILD_BUG_ON(sizeof(struct bug_entry) != 12); \ + asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n" \ + ".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \ + "2:\t.asciz " #__file "\n" \ + ".popsection\n" \ + ".pushsection __bug_table,\"a\"\n" \ + "3:\t.word 1b, 2b\n" \ + "\t.hword " #__line ", 0\n" \ + ".popsection"); \ + unreachable(); \ +} while (0) + +#else /* not CONFIG_DEBUG_BUGVERBOSE */ + +#define __BUG(__file, __line, __value) \ +do { \ + asm volatile(BUG_INSTR_TYPE #__value); \ + unreachable(); \ +} while (0) +#endif /* CONFIG_DEBUG_BUGVERBOSE */ #define HAVE_ARCH_BUG -#endif +#endif /* CONFIG_BUG */ #include <asm-generic/bug.h> diff --git a/arch/arm/include/asm/cachetype.h b/arch/arm/include/asm/cachetype.h index c023db09fcc1..7ea78144ae22 100644 --- a/arch/arm/include/asm/cachetype.h +++ b/arch/arm/include/asm/cachetype.h @@ -7,6 +7,7 @@ #define CACHEID_VIPT (CACHEID_VIPT_ALIASING|CACHEID_VIPT_NONALIASING) #define CACHEID_ASID_TAGGED (1 << 3) #define CACHEID_VIPT_I_ALIASING (1 << 4) +#define CACHEID_PIPT (1 << 5) extern unsigned int cacheid; @@ -16,6 +17,7 @@ extern unsigned int cacheid; #define cache_is_vipt_aliasing() cacheid_is(CACHEID_VIPT_ALIASING) #define icache_is_vivt_asid_tagged() cacheid_is(CACHEID_ASID_TAGGED) #define icache_is_vipt_aliasing() cacheid_is(CACHEID_VIPT_I_ALIASING) +#define icache_is_pipt() cacheid_is(CACHEID_PIPT) /* * __LINUX_ARM_ARCH__ is the minimum supported CPU architecture @@ -26,7 +28,8 @@ extern unsigned int cacheid; #if __LINUX_ARM_ARCH__ >= 7 #define __CACHEID_ARCH_MIN (CACHEID_VIPT_NONALIASING |\ CACHEID_ASID_TAGGED |\ - CACHEID_VIPT_I_ALIASING) + CACHEID_VIPT_I_ALIASING |\ + CACHEID_PIPT) #elif __LINUX_ARM_ARCH__ >= 6 #define __CACHEID_ARCH_MIN (~CACHEID_VIVT) #else diff --git a/arch/arm/include/asm/cputime.h b/arch/arm/include/asm/cputime.h deleted file mode 100644 index 3a8002a5fec7..000000000000 --- a/arch/arm/include/asm/cputime.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ARM_CPUTIME_H -#define __ARM_CPUTIME_H - -#include <asm-generic/cputime.h> - -#endif /* __ARM_CPUTIME_H */ diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index cd4458f64171..cb47d28cbe1f 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -8,6 +8,7 @@ #define CPUID_CACHETYPE 1 #define CPUID_TCM 2 #define CPUID_TLBTYPE 3 +#define CPUID_MPIDR 5 #define CPUID_EXT_PFR0 "c1, 0" #define CPUID_EXT_PFR1 "c1, 1" @@ -70,6 +71,11 @@ static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void) return read_cpuid(CPUID_TCM); } +static inline unsigned int __attribute_const__ read_cpuid_mpidr(void) +{ + return read_cpuid(CPUID_MPIDR); +} + /* * Intel's XScale3 core supports some v6 features (supersections, L2) * but advertises itself as v5 as it does not support the v6 ISA. For diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h index 9f390ce335cb..6615f03f56a5 100644 --- a/arch/arm/include/asm/device.h +++ b/arch/arm/include/asm/device.h @@ -10,6 +10,9 @@ struct dev_archdata { #ifdef CONFIG_DMABOUNCE struct dmabounce_device_info *dmabounce; #endif +#ifdef CONFIG_IOMMU_API + void *iommu; /* private IOMMU data */ +#endif }; struct pdev_archdata { diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 7f27fab9d404..cb3b7c981c4b 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -32,7 +32,7 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr) static inline void *dma_to_virt(struct device *dev, dma_addr_t addr) { - return (void *)__bus_to_virt(addr); + return (void *)__bus_to_virt((unsigned long)addr); } static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h index 628670e9d7c9..69a5b0b6455c 100644 --- a/arch/arm/include/asm/dma.h +++ b/arch/arm/include/asm/dma.h @@ -34,18 +34,18 @@ #define DMA_MODE_CASCADE 0xc0 #define DMA_AUTOINIT 0x10 -extern spinlock_t dma_spin_lock; +extern raw_spinlock_t dma_spin_lock; static inline unsigned long claim_dma_lock(void) { unsigned long flags; - spin_lock_irqsave(&dma_spin_lock, flags); + raw_spin_lock_irqsave(&dma_spin_lock, flags); return flags; } static inline void release_dma_lock(unsigned long flags) { - spin_unlock_irqrestore(&dma_spin_lock, flags); + raw_spin_unlock_irqrestore(&dma_spin_lock, flags); } /* Clear the 'DMA Pointer Flip Flop'. diff --git a/arch/arm/include/asm/ecard.h b/arch/arm/include/asm/ecard.h index 29f2610efc70..eaea14676d57 100644 --- a/arch/arm/include/asm/ecard.h +++ b/arch/arm/include/asm/ecard.h @@ -161,7 +161,6 @@ struct expansion_card { /* Private internal data */ const char *card_desc; /* Card description */ - CONST unsigned int podaddr; /* Base Linux address for card */ CONST loader_t loader; /* loader program */ u64 dma_mask; }; diff --git a/arch/arm/include/asm/emergency-restart.h b/arch/arm/include/asm/emergency-restart.h deleted file mode 100644 index 108d8c48e42e..000000000000 --- a/arch/arm/include/asm/emergency-restart.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_EMERGENCY_RESTART_H -#define _ASM_EMERGENCY_RESTART_H - -#include <asm-generic/emergency-restart.h> - -#endif /* _ASM_EMERGENCY_RESTART_H */ diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S index 2f1e2098dfe7..88d61815f0c0 100644 --- a/arch/arm/include/asm/entry-macro-multi.S +++ b/arch/arm/include/asm/entry-macro-multi.S @@ -25,13 +25,6 @@ movne r1, sp adrne lr, BSYM(1b) bne do_IPI - -#ifdef CONFIG_LOCAL_TIMERS - test_for_ltirq r0, r2, r6, lr - movne r0, sp - adrne lr, BSYM(1b) - bne do_local_timer -#endif #endif 9997: .endm diff --git a/arch/arm/include/asm/errno.h b/arch/arm/include/asm/errno.h deleted file mode 100644 index 6e60f0612bb6..000000000000 --- a/arch/arm/include/asm/errno.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ARM_ERRNO_H -#define _ARM_ERRNO_H - -#include <asm-generic/errno.h> - -#endif diff --git a/arch/arm/include/asm/exception.h b/arch/arm/include/asm/exception.h new file mode 100644 index 000000000000..5abaf5bbd985 --- /dev/null +++ b/arch/arm/include/asm/exception.h @@ -0,0 +1,19 @@ +/* + * Annotations for marking C functions as exception handlers. + * + * These should only be used for C functions that are called from the low + * level exception entry code and not any intervening C code. + */ +#ifndef __ASM_ARM_EXCEPTION_H +#define __ASM_ARM_EXCEPTION_H + +#include <linux/ftrace.h> + +#define __exception __attribute__((section(".exception.text"))) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#define __exception_irq_entry __irq_entry +#else +#define __exception_irq_entry __exception +#endif + +#endif /* __ASM_ARM_EXCEPTION_H */ diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h index 89ad1805e579..ddf07a92a6c8 100644 --- a/arch/arm/include/asm/hardirq.h +++ b/arch/arm/include/asm/hardirq.h @@ -9,9 +9,6 @@ typedef struct { unsigned int __softirq_pending; -#ifdef CONFIG_LOCAL_TIMERS - unsigned int local_timer_irqs; -#endif #ifdef CONFIG_SMP unsigned int ipi_irqs[NR_IPI]; #endif diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h index 99a6ed7e1bfd..434edccdf7f3 100644 --- a/arch/arm/include/asm/hardware/cache-l2x0.h +++ b/arch/arm/include/asm/hardware/cache-l2x0.h @@ -52,6 +52,8 @@ #define L2X0_LOCKDOWN_WAY_D_BASE 0x900 #define L2X0_LOCKDOWN_WAY_I_BASE 0x904 #define L2X0_LOCKDOWN_STRIDE 0x08 +#define L2X0_ADDR_FILTER_START 0xC00 +#define L2X0_ADDR_FILTER_END 0xC04 #define L2X0_TEST_OPERATION 0xF00 #define L2X0_LINE_DATA 0xF10 #define L2X0_LINE_TAG 0xF30 @@ -65,8 +67,23 @@ #define L2X0_CACHE_ID_PART_MASK (0xf << 6) #define L2X0_CACHE_ID_PART_L210 (1 << 6) #define L2X0_CACHE_ID_PART_L310 (3 << 6) +#define L2X0_CACHE_ID_RTL_MASK 0x3f +#define L2X0_CACHE_ID_RTL_R0P0 0x0 +#define L2X0_CACHE_ID_RTL_R1P0 0x2 +#define L2X0_CACHE_ID_RTL_R2P0 0x4 +#define L2X0_CACHE_ID_RTL_R3P0 0x5 +#define L2X0_CACHE_ID_RTL_R3P1 0x6 +#define L2X0_CACHE_ID_RTL_R3P2 0x8 #define L2X0_AUX_CTRL_MASK 0xc0000fff +#define L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT 0 +#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK 0x7 +#define L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT 3 +#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK (0x7 << 3) +#define L2X0_AUX_CTRL_TAG_LATENCY_SHIFT 6 +#define L2X0_AUX_CTRL_TAG_LATENCY_MASK (0x7 << 6) +#define L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT 9 +#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK (0x7 << 9) #define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT 16 #define L2X0_AUX_CTRL_WAY_SIZE_SHIFT 17 #define L2X0_AUX_CTRL_WAY_SIZE_MASK (0x7 << 17) @@ -77,8 +94,33 @@ #define L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT 29 #define L2X0_AUX_CTRL_EARLY_BRESP_SHIFT 30 +#define L2X0_LATENCY_CTRL_SETUP_SHIFT 0 +#define L2X0_LATENCY_CTRL_RD_SHIFT 4 +#define L2X0_LATENCY_CTRL_WR_SHIFT 8 + +#define L2X0_ADDR_FILTER_EN 1 + #ifndef __ASSEMBLY__ extern void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask); +extern int l2x0_of_init(__u32 aux_val, __u32 aux_mask); + +struct l2x0_regs { + unsigned long phy_base; + unsigned long aux_ctrl; + /* + * Whether the following registers need to be saved/restored + * depends on platform + */ + unsigned long tag_latency; + unsigned long data_latency; + unsigned long filter_start; + unsigned long filter_end; + unsigned long prefetch_ctrl; + unsigned long pwr_ctrl; +}; + +extern struct l2x0_regs l2x0_saved_regs; + #endif #endif diff --git a/arch/arm/include/asm/hardware/entry-macro-gic.S b/arch/arm/include/asm/hardware/entry-macro-gic.S index c115b82fe80a..74ebc803904d 100644 --- a/arch/arm/include/asm/hardware/entry-macro-gic.S +++ b/arch/arm/include/asm/hardware/entry-macro-gic.S @@ -22,15 +22,11 @@ * interrupt controller spec. To wit: * * Interrupts 0-15 are IPI - * 16-28 are reserved - * 29-31 are local. We allow 30 to be used for the watchdog. + * 16-31 are local. We allow 30 to be used for the watchdog. * 32-1020 are global * 1021-1022 are reserved * 1023 is "spurious" (no interrupt) * - * For now, we ignore all local interrupts so only return an interrupt if it's - * between 30 and 1020. The test_for_ipi routine below will pick up on IPIs. - * * A simple read from the controller will tell us the number of the highest * priority enabled interrupt. We then just need to check whether it is in the * valid range for an IRQ (30-1020 inclusive). @@ -43,7 +39,7 @@ ldr \tmp, =1021 bic \irqnr, \irqstat, #0x1c00 - cmp \irqnr, #29 + cmp \irqnr, #15 cmpcc \irqnr, \irqnr cmpne \irqnr, \tmp cmpcs \irqnr, \irqnr @@ -62,14 +58,3 @@ strcc \irqstat, [\base, #GIC_CPU_EOI] cmpcs \irqnr, \irqnr .endm - -/* As above, this assumes that irqstat and base are preserved.. */ - - .macro test_for_ltirq, irqnr, irqstat, base, tmp - bic \irqnr, \irqstat, #0x1c00 - mov \tmp, #0 - cmp \irqnr, #29 - moveq \tmp, #1 - streq \irqstat, [\base, #GIC_CPU_EOI] - cmp \tmp, #0 - .endm diff --git a/arch/arm/include/asm/hardware/gic.h b/arch/arm/include/asm/hardware/gic.h index 435d3f86c708..14867e12f205 100644 --- a/arch/arm/include/asm/hardware/gic.h +++ b/arch/arm/include/asm/hardware/gic.h @@ -40,12 +40,19 @@ void gic_init(unsigned int, unsigned int, void __iomem *, void __iomem *); void gic_secondary_init(unsigned int); void gic_cascade_irq(unsigned int gic_nr, unsigned int irq); void gic_raise_softirq(const struct cpumask *mask, unsigned int irq); -void gic_enable_ppi(unsigned int); struct gic_chip_data { unsigned int irq_offset; void __iomem *dist_base; void __iomem *cpu_base; +#ifdef CONFIG_CPU_PM + u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)]; + u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)]; + u32 saved_spi_target[DIV_ROUND_UP(1020, 4)]; + u32 __percpu *saved_ppi_enable; + u32 __percpu *saved_ppi_conf; +#endif + unsigned int gic_irqs; }; #endif diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h index f389b2704d82..c190bc992f0e 100644 --- a/arch/arm/include/asm/hw_breakpoint.h +++ b/arch/arm/include/asm/hw_breakpoint.h @@ -50,6 +50,7 @@ static inline void decode_ctrl_reg(u32 reg, #define ARM_DEBUG_ARCH_V6_1 2 #define ARM_DEBUG_ARCH_V7_ECP14 3 #define ARM_DEBUG_ARCH_V7_MM 4 +#define ARM_DEBUG_ARCH_V7_1 5 /* Breakpoint */ #define ARM_BREAKPOINT_EXECUTE 0 @@ -57,6 +58,7 @@ static inline void decode_ctrl_reg(u32 reg, /* Watchpoints */ #define ARM_BREAKPOINT_LOAD 1 #define ARM_BREAKPOINT_STORE 2 +#define ARM_FSR_ACCESS_MASK (1 << 11) /* Privilege Levels */ #define ARM_BREAKPOINT_PRIV 1 diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index d66605dea55a..065d100fa63e 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -80,6 +80,7 @@ extern void __iomem *__arm_ioremap_caller(unsigned long, size_t, unsigned int, extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int); extern void __iomem *__arm_ioremap(unsigned long, size_t, unsigned int); +extern void __iomem *__arm_ioremap_exec(unsigned long, size_t, bool cached); extern void __iounmap(volatile void __iomem *addr); /* @@ -110,6 +111,27 @@ static inline void __iomem *__typesafe_io(unsigned long addr) #include <mach/io.h> /* + * This is the limit of PC card/PCI/ISA IO space, which is by default + * 64K if we have PC card, PCI or ISA support. Otherwise, default to + * zero to prevent ISA/PCI drivers claiming IO space (and potentially + * oopsing.) + * + * Only set this larger if you really need inb() et.al. to operate over + * a larger address space. Note that SOC_COMMON ioremaps each sockets + * IO space area, and so inb() et.al. must be defined to operate as per + * readb() et.al. on such platforms. + */ +#ifndef IO_SPACE_LIMIT +#if defined(CONFIG_PCMCIA_SOC_COMMON) || defined(CONFIG_PCMCIA_SOC_COMMON_MODULE) +#define IO_SPACE_LIMIT ((resource_size_t)0xffffffff) +#elif defined(CONFIG_PCI) || defined(CONFIG_ISA) || defined(CONFIG_PCCARD) +#define IO_SPACE_LIMIT ((resource_size_t)0xffff) +#else +#define IO_SPACE_LIMIT ((resource_size_t)0) +#endif +#endif + +/* * IO port access primitives * ------------------------- * @@ -189,11 +211,11 @@ extern void _memset_io(volatile void __iomem *, int, size_t); * IO port primitives for more information. */ #ifdef __mem_pci -#define readb_relaxed(c) ({ u8 __v = __raw_readb(__mem_pci(c)); __v; }) -#define readw_relaxed(c) ({ u16 __v = le16_to_cpu((__force __le16) \ - __raw_readw(__mem_pci(c))); __v; }) -#define readl_relaxed(c) ({ u32 __v = le32_to_cpu((__force __le32) \ - __raw_readl(__mem_pci(c))); __v; }) +#define readb_relaxed(c) ({ u8 __r = __raw_readb(__mem_pci(c)); __r; }) +#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \ + __raw_readw(__mem_pci(c))); __r; }) +#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \ + __raw_readl(__mem_pci(c))); __r; }) #define writeb_relaxed(v,c) ((void)__raw_writeb(v,__mem_pci(c))) #define writew_relaxed(v,c) ((void)__raw_writew((__force u16) \ @@ -238,7 +260,7 @@ extern void _memset_io(volatile void __iomem *, int, size_t); * ioremap and friends. * * ioremap takes a PCI memory address, as specified in - * Documentation/IO-mapping.txt. + * Documentation/io-mapping.txt. * */ #ifndef __arch_ioremap @@ -260,10 +282,16 @@ extern void _memset_io(volatile void __iomem *, int, size_t); #define ioread16(p) ({ unsigned int __v = le16_to_cpu((__force __le16)__raw_readw(p)); __iormb(); __v; }) #define ioread32(p) ({ unsigned int __v = le32_to_cpu((__force __le32)__raw_readl(p)); __iormb(); __v; }) +#define ioread16be(p) ({ unsigned int __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; }) +#define ioread32be(p) ({ unsigned int __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; }) + #define iowrite8(v,p) ({ __iowmb(); (void)__raw_writeb(v, p); }) #define iowrite16(v,p) ({ __iowmb(); (void)__raw_writew((__force __u16)cpu_to_le16(v), p); }) #define iowrite32(v,p) ({ __iowmb(); (void)__raw_writel((__force __u32)cpu_to_le32(v), p); }) +#define iowrite16be(v,p) ({ __iowmb(); (void)__raw_writew((__force __u16)cpu_to_be16(v), p); }) +#define iowrite32be(v,p) ({ __iowmb(); (void)__raw_writel((__force __u32)cpu_to_be32(v), p); }) + #define ioread8_rep(p,d,c) __raw_readsb(p,d,c) #define ioread16_rep(p,d,c) __raw_readsw(p,d,c) #define ioread32_rep(p,d,c) __raw_readsl(p,d,c) diff --git a/arch/arm/include/asm/ioctl.h b/arch/arm/include/asm/ioctl.h deleted file mode 100644 index b279fe06dfe5..000000000000 --- a/arch/arm/include/asm/ioctl.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/ioctl.h> diff --git a/arch/arm/include/asm/irq_regs.h b/arch/arm/include/asm/irq_regs.h deleted file mode 100644 index 3dd9c0b70270..000000000000 --- a/arch/arm/include/asm/irq_regs.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/irq_regs.h> diff --git a/arch/arm/include/asm/kdebug.h b/arch/arm/include/asm/kdebug.h deleted file mode 100644 index 6ece1b037665..000000000000 --- a/arch/arm/include/asm/kdebug.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/kdebug.h> diff --git a/arch/arm/include/asm/local.h b/arch/arm/include/asm/local.h deleted file mode 100644 index c11c530f74d0..000000000000 --- a/arch/arm/include/asm/local.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local.h> diff --git a/arch/arm/include/asm/local64.h b/arch/arm/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/arm/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/arm/include/asm/localtimer.h b/arch/arm/include/asm/localtimer.h index 080d74f8128d..c6a18424888e 100644 --- a/arch/arm/include/asm/localtimer.h +++ b/arch/arm/include/asm/localtimer.h @@ -10,6 +10,9 @@ #ifndef __ASM_ARM_LOCALTIMER_H #define __ASM_ARM_LOCALTIMER_H +#include <linux/errno.h> +#include <linux/interrupt.h> + struct clock_event_device; /* @@ -17,27 +20,20 @@ struct clock_event_device; */ void percpu_timer_setup(void); -/* - * Called from assembly, this is the local timer IRQ handler - */ -asmlinkage void do_local_timer(struct pt_regs *); - - #ifdef CONFIG_LOCAL_TIMERS #ifdef CONFIG_HAVE_ARM_TWD #include "smp_twd.h" -#define local_timer_ack() twd_timer_ack() +#define local_timer_stop(c) twd_timer_stop((c)) #else /* - * Platform provides this to acknowledge a local timer IRQ. - * Returns true if the local timer IRQ is to be processed. + * Stop the local timer */ -int local_timer_ack(void); +void local_timer_stop(struct clock_event_device *); #endif @@ -52,6 +48,10 @@ static inline int local_timer_setup(struct clock_event_device *evt) { return -ENXIO; } + +static inline void local_timer_stop(struct clock_event_device *evt) +{ +} #endif #endif diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 727da118bcc1..7d19425dd496 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -34,8 +34,7 @@ struct machine_desc { unsigned int reserve_lp1 :1; /* never has lp1 */ unsigned int reserve_lp2 :1; /* never has lp2 */ unsigned int soft_reboot :1; /* soft reboot */ - void (*fixup)(struct machine_desc *, - struct tag *, char **, + void (*fixup)(struct tag *, char **, struct meminfo *); void (*reserve)(void);/* reserve mem blocks */ void (*map_io)(void);/* IO mapping function */ diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h index d2fedb5aeb1f..b36f3654bf54 100644 --- a/arch/arm/include/asm/mach/map.h +++ b/arch/arm/include/asm/mach/map.h @@ -29,6 +29,7 @@ struct map_desc { #define MT_MEMORY_NONCACHED 11 #define MT_MEMORY_DTCM 12 #define MT_MEMORY_ITCM 13 +#define MT_MEMORY_SO 14 #ifdef CONFIG_MMU extern void iotable_init(struct map_desc *, int); diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h index b4ffe9d5b526..14965658a923 100644 --- a/arch/arm/include/asm/mmu.h +++ b/arch/arm/include/asm/mmu.h @@ -6,7 +6,7 @@ typedef struct { #ifdef CONFIG_CPU_HAS_ASID unsigned int id; - spinlock_t id_lock; + raw_spinlock_t id_lock; #endif unsigned int kvm_seq; } mm_context_t; @@ -16,7 +16,7 @@ typedef struct { /* init_mm.context.id_lock should be initialized. */ #define INIT_MM_CONTEXT(name) \ - .context.id_lock = __SPIN_LOCK_UNLOCKED(name.context.id_lock), + .context.id_lock = __RAW_SPIN_LOCK_UNLOCKED(name.context.id_lock), #else #define ASID(mm) (0) #endif diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h index d8387437ec5a..53426c66352a 100644 --- a/arch/arm/include/asm/outercache.h +++ b/arch/arm/include/asm/outercache.h @@ -34,6 +34,7 @@ struct outer_cache_fns { void (*sync)(void); #endif void (*set_debug)(unsigned long); + void (*resume)(void); }; #ifdef CONFIG_OUTER_CACHE @@ -74,6 +75,12 @@ static inline void outer_disable(void) outer_cache.disable(); } +static inline void outer_resume(void) +{ + if (outer_cache.resume) + outer_cache.resume(); +} + #else static inline void outer_inv_range(phys_addr_t start, phys_addr_t end) diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h index ac75d0848889..ca94653f1ecb 100644 --- a/arch/arm/include/asm/page.h +++ b/arch/arm/include/asm/page.h @@ -151,47 +151,7 @@ extern void __cpu_copy_user_highpage(struct page *to, struct page *from, #define clear_page(page) memset((void *)(page), 0, PAGE_SIZE) extern void copy_page(void *to, const void *from); -typedef unsigned long pteval_t; - -#undef STRICT_MM_TYPECHECKS - -#ifdef STRICT_MM_TYPECHECKS -/* - * These are used to make use of C type-checking.. - */ -typedef struct { pteval_t pte; } pte_t; -typedef struct { unsigned long pmd; } pmd_t; -typedef struct { unsigned long pgd[2]; } pgd_t; -typedef struct { unsigned long pgprot; } pgprot_t; - -#define pte_val(x) ((x).pte) -#define pmd_val(x) ((x).pmd) -#define pgd_val(x) ((x).pgd[0]) -#define pgprot_val(x) ((x).pgprot) - -#define __pte(x) ((pte_t) { (x) } ) -#define __pmd(x) ((pmd_t) { (x) } ) -#define __pgprot(x) ((pgprot_t) { (x) } ) - -#else -/* - * .. while these make it easier on the compiler - */ -typedef pteval_t pte_t; -typedef unsigned long pmd_t; -typedef unsigned long pgd_t[2]; -typedef unsigned long pgprot_t; - -#define pte_val(x) (x) -#define pmd_val(x) (x) -#define pgd_val(x) ((x)[0]) -#define pgprot_val(x) (x) - -#define __pte(x) (x) -#define __pmd(x) (x) -#define __pgprot(x) (x) - -#endif /* STRICT_MM_TYPECHECKS */ +#include <asm/pgtable-2level-types.h> #endif /* CONFIG_MMU */ diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h deleted file mode 100644 index b4e32d8ec072..000000000000 --- a/arch/arm/include/asm/percpu.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ARM_PERCPU -#define __ARM_PERCPU - -#include <asm-generic/percpu.h> - -#endif diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 22de005f159c..3e08fd3fbb6b 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -105,9 +105,9 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pte) } static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte, - unsigned long prot) + pmdval_t prot) { - unsigned long pmdval = (pte + PTE_HWTABLE_OFF) | prot; + pmdval_t pmdval = (pte + PTE_HWTABLE_OFF) | prot; pmdp[0] = __pmd(pmdval); pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t)); flush_pmd_entry(pmdp); diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h new file mode 100644 index 000000000000..5cfba15cb401 --- /dev/null +++ b/arch/arm/include/asm/pgtable-2level-hwdef.h @@ -0,0 +1,93 @@ +/* + * arch/arm/include/asm/pgtable-2level-hwdef.h + * + * Copyright (C) 1995-2002 Russell King + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _ASM_PGTABLE_2LEVEL_HWDEF_H +#define _ASM_PGTABLE_2LEVEL_HWDEF_H + +/* + * Hardware page table definitions. + * + * + Level 1 descriptor (PMD) + * - common + */ +#define PMD_TYPE_MASK (_AT(pmdval_t, 3) << 0) +#define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0) +#define PMD_TYPE_TABLE (_AT(pmdval_t, 1) << 0) +#define PMD_TYPE_SECT (_AT(pmdval_t, 2) << 0) +#define PMD_BIT4 (_AT(pmdval_t, 1) << 4) +#define PMD_DOMAIN(x) (_AT(pmdval_t, (x)) << 5) +#define PMD_PROTECTION (_AT(pmdval_t, 1) << 9) /* v5 */ +/* + * - section + */ +#define PMD_SECT_BUFFERABLE (_AT(pmdval_t, 1) << 2) +#define PMD_SECT_CACHEABLE (_AT(pmdval_t, 1) << 3) +#define PMD_SECT_XN (_AT(pmdval_t, 1) << 4) /* v6 */ +#define PMD_SECT_AP_WRITE (_AT(pmdval_t, 1) << 10) +#define PMD_SECT_AP_READ (_AT(pmdval_t, 1) << 11) +#define PMD_SECT_TEX(x) (_AT(pmdval_t, (x)) << 12) /* v5 */ +#define PMD_SECT_APX (_AT(pmdval_t, 1) << 15) /* v6 */ +#define PMD_SECT_S (_AT(pmdval_t, 1) << 16) /* v6 */ +#define PMD_SECT_nG (_AT(pmdval_t, 1) << 17) /* v6 */ +#define PMD_SECT_SUPER (_AT(pmdval_t, 1) << 18) /* v6 */ +#define PMD_SECT_AF (_AT(pmdval_t, 0)) + +#define PMD_SECT_UNCACHED (_AT(pmdval_t, 0)) +#define PMD_SECT_BUFFERED (PMD_SECT_BUFFERABLE) +#define PMD_SECT_WT (PMD_SECT_CACHEABLE) +#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) +#define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE) +#define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) +#define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2)) + +/* + * - coarse table (not used) + */ + +/* + * + Level 2 descriptor (PTE) + * - common + */ +#define PTE_TYPE_MASK (_AT(pteval_t, 3) << 0) +#define PTE_TYPE_FAULT (_AT(pteval_t, 0) << 0) +#define PTE_TYPE_LARGE (_AT(pteval_t, 1) << 0) +#define PTE_TYPE_SMALL (_AT(pteval_t, 2) << 0) +#define PTE_TYPE_EXT (_AT(pteval_t, 3) << 0) /* v5 */ +#define PTE_BUFFERABLE (_AT(pteval_t, 1) << 2) +#define PTE_CACHEABLE (_AT(pteval_t, 1) << 3) + +/* + * - extended small page/tiny page + */ +#define PTE_EXT_XN (_AT(pteval_t, 1) << 0) /* v6 */ +#define PTE_EXT_AP_MASK (_AT(pteval_t, 3) << 4) +#define PTE_EXT_AP0 (_AT(pteval_t, 1) << 4) +#define PTE_EXT_AP1 (_AT(pteval_t, 2) << 4) +#define PTE_EXT_AP_UNO_SRO (_AT(pteval_t, 0) << 4) +#define PTE_EXT_AP_UNO_SRW (PTE_EXT_AP0) +#define PTE_EXT_AP_URO_SRW (PTE_EXT_AP1) +#define PTE_EXT_AP_URW_SRW (PTE_EXT_AP1|PTE_EXT_AP0) +#define PTE_EXT_TEX(x) (_AT(pteval_t, (x)) << 6) /* v5 */ +#define PTE_EXT_APX (_AT(pteval_t, 1) << 9) /* v6 */ +#define PTE_EXT_COHERENT (_AT(pteval_t, 1) << 9) /* XScale3 */ +#define PTE_EXT_SHARED (_AT(pteval_t, 1) << 10) /* v6 */ +#define PTE_EXT_NG (_AT(pteval_t, 1) << 11) /* v6 */ + +/* + * - small page + */ +#define PTE_SMALL_AP_MASK (_AT(pteval_t, 0xff) << 4) +#define PTE_SMALL_AP_UNO_SRO (_AT(pteval_t, 0x00) << 4) +#define PTE_SMALL_AP_UNO_SRW (_AT(pteval_t, 0x55) << 4) +#define PTE_SMALL_AP_URO_SRW (_AT(pteval_t, 0xaa) << 4) +#define PTE_SMALL_AP_URW_SRW (_AT(pteval_t, 0xff) << 4) + +#define PHYS_MASK (~0UL) + +#endif diff --git a/arch/arm/include/asm/pgtable-2level-types.h b/arch/arm/include/asm/pgtable-2level-types.h new file mode 100644 index 000000000000..66cb5b0e89c5 --- /dev/null +++ b/arch/arm/include/asm/pgtable-2level-types.h @@ -0,0 +1,67 @@ +/* + * arch/arm/include/asm/pgtable-2level-types.h + * + * Copyright (C) 1995-2003 Russell King + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#ifndef _ASM_PGTABLE_2LEVEL_TYPES_H +#define _ASM_PGTABLE_2LEVEL_TYPES_H + +#include <asm/types.h> + +typedef u32 pteval_t; +typedef u32 pmdval_t; + +#undef STRICT_MM_TYPECHECKS + +#ifdef STRICT_MM_TYPECHECKS +/* + * These are used to make use of C type-checking.. + */ +typedef struct { pteval_t pte; } pte_t; +typedef struct { pmdval_t pmd; } pmd_t; +typedef struct { pmdval_t pgd[2]; } pgd_t; +typedef struct { pteval_t pgprot; } pgprot_t; + +#define pte_val(x) ((x).pte) +#define pmd_val(x) ((x).pmd) +#define pgd_val(x) ((x).pgd[0]) +#define pgprot_val(x) ((x).pgprot) + +#define __pte(x) ((pte_t) { (x) } ) +#define __pmd(x) ((pmd_t) { (x) } ) +#define __pgprot(x) ((pgprot_t) { (x) } ) + +#else +/* + * .. while these make it easier on the compiler + */ +typedef pteval_t pte_t; +typedef pmdval_t pmd_t; +typedef pmdval_t pgd_t[2]; +typedef pteval_t pgprot_t; + +#define pte_val(x) (x) +#define pmd_val(x) (x) +#define pgd_val(x) ((x)[0]) +#define pgprot_val(x) (x) + +#define __pte(x) (x) +#define __pmd(x) (x) +#define __pgprot(x) (x) + +#endif /* STRICT_MM_TYPECHECKS */ + +#endif /* _ASM_PGTABLE_2LEVEL_TYPES_H */ diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h new file mode 100644 index 000000000000..470457e1cfc5 --- /dev/null +++ b/arch/arm/include/asm/pgtable-2level.h @@ -0,0 +1,143 @@ +/* + * arch/arm/include/asm/pgtable-2level.h + * + * Copyright (C) 1995-2002 Russell King + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _ASM_PGTABLE_2LEVEL_H +#define _ASM_PGTABLE_2LEVEL_H + +/* + * Hardware-wise, we have a two level page table structure, where the first + * level has 4096 entries, and the second level has 256 entries. Each entry + * is one 32-bit word. Most of the bits in the second level entry are used + * by hardware, and there aren't any "accessed" and "dirty" bits. + * + * Linux on the other hand has a three level page table structure, which can + * be wrapped to fit a two level page table structure easily - using the PGD + * and PTE only. However, Linux also expects one "PTE" table per page, and + * at least a "dirty" bit. + * + * Therefore, we tweak the implementation slightly - we tell Linux that we + * have 2048 entries in the first level, each of which is 8 bytes (iow, two + * hardware pointers to the second level.) The second level contains two + * hardware PTE tables arranged contiguously, preceded by Linux versions + * which contain the state information Linux needs. We, therefore, end up + * with 512 entries in the "PTE" level. + * + * This leads to the page tables having the following layout: + * + * pgd pte + * | | + * +--------+ + * | | +------------+ +0 + * +- - - - + | Linux pt 0 | + * | | +------------+ +1024 + * +--------+ +0 | Linux pt 1 | + * | |-----> +------------+ +2048 + * +- - - - + +4 | h/w pt 0 | + * | |-----> +------------+ +3072 + * +--------+ +8 | h/w pt 1 | + * | | +------------+ +4096 + * + * See L_PTE_xxx below for definitions of bits in the "Linux pt", and + * PTE_xxx for definitions of bits appearing in the "h/w pt". + * + * PMD_xxx definitions refer to bits in the first level page table. + * + * The "dirty" bit is emulated by only granting hardware write permission + * iff the page is marked "writable" and "dirty" in the Linux PTE. This + * means that a write to a clean page will cause a permission fault, and + * the Linux MM layer will mark the page dirty via handle_pte_fault(). + * For the hardware to notice the permission change, the TLB entry must + * be flushed, and ptep_set_access_flags() does that for us. + * + * The "accessed" or "young" bit is emulated by a similar method; we only + * allow accesses to the page if the "young" bit is set. Accesses to the + * page will cause a fault, and handle_pte_fault() will set the young bit + * for us as long as the page is marked present in the corresponding Linux + * PTE entry. Again, ptep_set_access_flags() will ensure that the TLB is + * up to date. + * + * However, when the "young" bit is cleared, we deny access to the page + * by clearing the hardware PTE. Currently Linux does not flush the TLB + * for us in this case, which means the TLB will retain the transation + * until either the TLB entry is evicted under pressure, or a context + * switch which changes the user space mapping occurs. + */ +#define PTRS_PER_PTE 512 +#define PTRS_PER_PMD 1 +#define PTRS_PER_PGD 2048 + +#define PTE_HWTABLE_PTRS (PTRS_PER_PTE) +#define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t)) +#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32)) + +/* + * PMD_SHIFT determines the size of the area a second-level page table can map + * PGDIR_SHIFT determines what a third-level page table entry can map + */ +#define PMD_SHIFT 21 +#define PGDIR_SHIFT 21 + +#define PMD_SIZE (1UL << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE-1)) +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +/* + * section address mask and size definitions. + */ +#define SECTION_SHIFT 20 +#define SECTION_SIZE (1UL << SECTION_SHIFT) +#define SECTION_MASK (~(SECTION_SIZE-1)) + +/* + * ARMv6 supersection address mask and size definitions. + */ +#define SUPERSECTION_SHIFT 24 +#define SUPERSECTION_SIZE (1UL << SUPERSECTION_SHIFT) +#define SUPERSECTION_MASK (~(SUPERSECTION_SIZE-1)) + +#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) + +/* + * "Linux" PTE definitions. + * + * We keep two sets of PTEs - the hardware and the linux version. + * This allows greater flexibility in the way we map the Linux bits + * onto the hardware tables, and allows us to have YOUNG and DIRTY + * bits. + * + * The PTE table pointer refers to the hardware entries; the "Linux" + * entries are stored 1024 bytes below. + */ +#define L_PTE_PRESENT (_AT(pteval_t, 1) << 0) +#define L_PTE_YOUNG (_AT(pteval_t, 1) << 1) +#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */ +#define L_PTE_DIRTY (_AT(pteval_t, 1) << 6) +#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7) +#define L_PTE_USER (_AT(pteval_t, 1) << 8) +#define L_PTE_XN (_AT(pteval_t, 1) << 9) +#define L_PTE_SHARED (_AT(pteval_t, 1) << 10) /* shared(v6), coherent(xsc3) */ + +/* + * These are the memory types, defined to be compatible with + * pre-ARMv6 CPUs cacheable and bufferable bits: XXCB + */ +#define L_PTE_MT_UNCACHED (_AT(pteval_t, 0x00) << 2) /* 0000 */ +#define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */ +#define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */ +#define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */ +#define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */ +#define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */ +#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ +#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ +#define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ +#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ +#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) + +#endif /* _ASM_PGTABLE_2LEVEL_H */ diff --git a/arch/arm/include/asm/pgtable-hwdef.h b/arch/arm/include/asm/pgtable-hwdef.h index fd1521d5cb9d..183111164ce9 100644 --- a/arch/arm/include/asm/pgtable-hwdef.h +++ b/arch/arm/include/asm/pgtable-hwdef.h @@ -10,81 +10,6 @@ #ifndef _ASMARM_PGTABLE_HWDEF_H #define _ASMARM_PGTABLE_HWDEF_H -/* - * Hardware page table definitions. - * - * + Level 1 descriptor (PMD) - * - common - */ -#define PMD_TYPE_MASK (3 << 0) -#define PMD_TYPE_FAULT (0 << 0) -#define PMD_TYPE_TABLE (1 << 0) -#define PMD_TYPE_SECT (2 << 0) -#define PMD_BIT4 (1 << 4) -#define PMD_DOMAIN(x) ((x) << 5) -#define PMD_PROTECTION (1 << 9) /* v5 */ -/* - * - section - */ -#define PMD_SECT_BUFFERABLE (1 << 2) -#define PMD_SECT_CACHEABLE (1 << 3) -#define PMD_SECT_XN (1 << 4) /* v6 */ -#define PMD_SECT_AP_WRITE (1 << 10) -#define PMD_SECT_AP_READ (1 << 11) -#define PMD_SECT_TEX(x) ((x) << 12) /* v5 */ -#define PMD_SECT_APX (1 << 15) /* v6 */ -#define PMD_SECT_S (1 << 16) /* v6 */ -#define PMD_SECT_nG (1 << 17) /* v6 */ -#define PMD_SECT_SUPER (1 << 18) /* v6 */ - -#define PMD_SECT_UNCACHED (0) -#define PMD_SECT_BUFFERED (PMD_SECT_BUFFERABLE) -#define PMD_SECT_WT (PMD_SECT_CACHEABLE) -#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) -#define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE) -#define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE) -#define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2)) - -/* - * - coarse table (not used) - */ - -/* - * + Level 2 descriptor (PTE) - * - common - */ -#define PTE_TYPE_MASK (3 << 0) -#define PTE_TYPE_FAULT (0 << 0) -#define PTE_TYPE_LARGE (1 << 0) -#define PTE_TYPE_SMALL (2 << 0) -#define PTE_TYPE_EXT (3 << 0) /* v5 */ -#define PTE_BUFFERABLE (1 << 2) -#define PTE_CACHEABLE (1 << 3) - -/* - * - extended small page/tiny page - */ -#define PTE_EXT_XN (1 << 0) /* v6 */ -#define PTE_EXT_AP_MASK (3 << 4) -#define PTE_EXT_AP0 (1 << 4) -#define PTE_EXT_AP1 (2 << 4) -#define PTE_EXT_AP_UNO_SRO (0 << 4) -#define PTE_EXT_AP_UNO_SRW (PTE_EXT_AP0) -#define PTE_EXT_AP_URO_SRW (PTE_EXT_AP1) -#define PTE_EXT_AP_URW_SRW (PTE_EXT_AP1|PTE_EXT_AP0) -#define PTE_EXT_TEX(x) ((x) << 6) /* v5 */ -#define PTE_EXT_APX (1 << 9) /* v6 */ -#define PTE_EXT_COHERENT (1 << 9) /* XScale3 */ -#define PTE_EXT_SHARED (1 << 10) /* v6 */ -#define PTE_EXT_NG (1 << 11) /* v6 */ - -/* - * - small page - */ -#define PTE_SMALL_AP_MASK (0xff << 4) -#define PTE_SMALL_AP_UNO_SRO (0x00 << 4) -#define PTE_SMALL_AP_UNO_SRW (0x55 << 4) -#define PTE_SMALL_AP_URO_SRW (0xaa << 4) -#define PTE_SMALL_AP_URW_SRW (0xff << 4) +#include <asm/pgtable-2level-hwdef.h> #endif diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 5750704e0271..9451dce3a553 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -24,6 +24,8 @@ #include <mach/vmalloc.h> #include <asm/pgtable-hwdef.h> +#include <asm/pgtable-2level.h> + /* * Just any arbitrary offset to the start of the vmalloc VM area: the * current 8MB value just means that there will be a 8MB "hole" after the @@ -41,79 +43,6 @@ #define VMALLOC_START (((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)) #endif -/* - * Hardware-wise, we have a two level page table structure, where the first - * level has 4096 entries, and the second level has 256 entries. Each entry - * is one 32-bit word. Most of the bits in the second level entry are used - * by hardware, and there aren't any "accessed" and "dirty" bits. - * - * Linux on the other hand has a three level page table structure, which can - * be wrapped to fit a two level page table structure easily - using the PGD - * and PTE only. However, Linux also expects one "PTE" table per page, and - * at least a "dirty" bit. - * - * Therefore, we tweak the implementation slightly - we tell Linux that we - * have 2048 entries in the first level, each of which is 8 bytes (iow, two - * hardware pointers to the second level.) The second level contains two - * hardware PTE tables arranged contiguously, preceded by Linux versions - * which contain the state information Linux needs. We, therefore, end up - * with 512 entries in the "PTE" level. - * - * This leads to the page tables having the following layout: - * - * pgd pte - * | | - * +--------+ - * | | +------------+ +0 - * +- - - - + | Linux pt 0 | - * | | +------------+ +1024 - * +--------+ +0 | Linux pt 1 | - * | |-----> +------------+ +2048 - * +- - - - + +4 | h/w pt 0 | - * | |-----> +------------+ +3072 - * +--------+ +8 | h/w pt 1 | - * | | +------------+ +4096 - * - * See L_PTE_xxx below for definitions of bits in the "Linux pt", and - * PTE_xxx for definitions of bits appearing in the "h/w pt". - * - * PMD_xxx definitions refer to bits in the first level page table. - * - * The "dirty" bit is emulated by only granting hardware write permission - * iff the page is marked "writable" and "dirty" in the Linux PTE. This - * means that a write to a clean page will cause a permission fault, and - * the Linux MM layer will mark the page dirty via handle_pte_fault(). - * For the hardware to notice the permission change, the TLB entry must - * be flushed, and ptep_set_access_flags() does that for us. - * - * The "accessed" or "young" bit is emulated by a similar method; we only - * allow accesses to the page if the "young" bit is set. Accesses to the - * page will cause a fault, and handle_pte_fault() will set the young bit - * for us as long as the page is marked present in the corresponding Linux - * PTE entry. Again, ptep_set_access_flags() will ensure that the TLB is - * up to date. - * - * However, when the "young" bit is cleared, we deny access to the page - * by clearing the hardware PTE. Currently Linux does not flush the TLB - * for us in this case, which means the TLB will retain the transation - * until either the TLB entry is evicted under pressure, or a context - * switch which changes the user space mapping occurs. - */ -#define PTRS_PER_PTE 512 -#define PTRS_PER_PMD 1 -#define PTRS_PER_PGD 2048 - -#define PTE_HWTABLE_PTRS (PTRS_PER_PTE) -#define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t)) -#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32)) - -/* - * PMD_SHIFT determines the size of the area a second-level page table can map - * PGDIR_SHIFT determines what a third-level page table entry can map - */ -#define PMD_SHIFT 21 -#define PGDIR_SHIFT 21 - #define LIBRARY_TEXT_START 0x0c000000 #ifndef __ASSEMBLY__ @@ -124,12 +53,6 @@ extern void __pgd_error(const char *file, int line, pgd_t); #define pte_ERROR(pte) __pte_error(__FILE__, __LINE__, pte) #define pmd_ERROR(pmd) __pmd_error(__FILE__, __LINE__, pmd) #define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd) -#endif /* !__ASSEMBLY__ */ - -#define PMD_SIZE (1UL << PMD_SHIFT) -#define PMD_MASK (~(PMD_SIZE-1)) -#define PGDIR_SIZE (1UL << PGDIR_SHIFT) -#define PGDIR_MASK (~(PGDIR_SIZE-1)) /* * This is the lowest virtual address we can permit any user space @@ -138,60 +61,6 @@ extern void __pgd_error(const char *file, int line, pgd_t); */ #define FIRST_USER_ADDRESS PAGE_SIZE -#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) - -/* - * section address mask and size definitions. - */ -#define SECTION_SHIFT 20 -#define SECTION_SIZE (1UL << SECTION_SHIFT) -#define SECTION_MASK (~(SECTION_SIZE-1)) - -/* - * ARMv6 supersection address mask and size definitions. - */ -#define SUPERSECTION_SHIFT 24 -#define SUPERSECTION_SIZE (1UL << SUPERSECTION_SHIFT) -#define SUPERSECTION_MASK (~(SUPERSECTION_SIZE-1)) - -/* - * "Linux" PTE definitions. - * - * We keep two sets of PTEs - the hardware and the linux version. - * This allows greater flexibility in the way we map the Linux bits - * onto the hardware tables, and allows us to have YOUNG and DIRTY - * bits. - * - * The PTE table pointer refers to the hardware entries; the "Linux" - * entries are stored 1024 bytes below. - */ -#define L_PTE_PRESENT (_AT(pteval_t, 1) << 0) -#define L_PTE_YOUNG (_AT(pteval_t, 1) << 1) -#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */ -#define L_PTE_DIRTY (_AT(pteval_t, 1) << 6) -#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7) -#define L_PTE_USER (_AT(pteval_t, 1) << 8) -#define L_PTE_XN (_AT(pteval_t, 1) << 9) -#define L_PTE_SHARED (_AT(pteval_t, 1) << 10) /* shared(v6), coherent(xsc3) */ - -/* - * These are the memory types, defined to be compatible with - * pre-ARMv6 CPUs cacheable and bufferable bits: XXCB - */ -#define L_PTE_MT_UNCACHED (_AT(pteval_t, 0x00) << 2) /* 0000 */ -#define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */ -#define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */ -#define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */ -#define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */ -#define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */ -#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */ -#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */ -#define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */ -#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */ -#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2) - -#ifndef __ASSEMBLY__ - /* * The pgprot_* and protection_map entries will be fixed up in runtime * to include the cachable and bufferable bits based on memory policy, @@ -232,6 +101,9 @@ extern pgprot_t pgprot_kernel; #define pgprot_writecombine(prot) \ __pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE) +#define pgprot_stronglyordered(prot) \ + __pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED) + #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE #define pgprot_dmacoherent(prot) \ __pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE | L_PTE_XN) @@ -327,10 +199,10 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; static inline pte_t *pmd_page_vaddr(pmd_t pmd) { - return __va(pmd_val(pmd) & PAGE_MASK); + return __va(pmd_val(pmd) & PHYS_MASK & (s32)PAGE_MASK); } -#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd))) +#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK)) /* we don't need complex calculations here as the pmd is folded into the pgd */ #define pmd_addr_end(addr,end) (end) @@ -351,7 +223,7 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd) #define pte_offset_map(pmd,addr) (__pte_map(pmd) + pte_index(addr)) #define pte_unmap(pte) __pte_unmap(pte) -#define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) +#define pte_pfn(pte) ((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT) #define pfn_pte(pfn,prot) __pte(__pfn_to_phys(pfn) | pgprot_val(prot)) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h index b7e82c4aced6..71d99b83cdb9 100644 --- a/arch/arm/include/asm/pmu.h +++ b/arch/arm/include/asm/pmu.h @@ -13,7 +13,12 @@ #define __ARM_PMU_H__ #include <linux/interrupt.h> +#include <linux/perf_event.h> +/* + * Types of PMUs that can be accessed directly and require mutual + * exclusion between profiling tools. + */ enum arm_pmu_type { ARM_PMU_DEVICE_CPU = 0, ARM_NUM_PMU_DEVICES, @@ -37,21 +42,17 @@ struct arm_pmu_platdata { * reserve_pmu() - reserve the hardware performance counters * * Reserve the hardware performance counters in the system for exclusive use. - * The platform_device for the system is returned on success, ERR_PTR() - * encoded error on failure. + * Returns 0 on success or -EBUSY if the lock is already held. */ -extern struct platform_device * +extern int reserve_pmu(enum arm_pmu_type type); /** * release_pmu() - Relinquish control of the performance counters * * Release the performance counters and allow someone else to use them. - * Callers must have disabled the counters and released IRQs before calling - * this. The platform_device returned from reserve_pmu() must be passed as - * a cookie. */ -extern int +extern void release_pmu(enum arm_pmu_type type); /** @@ -68,24 +69,78 @@ init_pmu(enum arm_pmu_type type); #include <linux/err.h> -static inline struct platform_device * -reserve_pmu(enum arm_pmu_type type) -{ - return ERR_PTR(-ENODEV); -} - static inline int -release_pmu(enum arm_pmu_type type) +reserve_pmu(enum arm_pmu_type type) { return -ENODEV; } -static inline int -init_pmu(enum arm_pmu_type type) -{ - return -ENODEV; -} +static inline void +release_pmu(enum arm_pmu_type type) { } #endif /* CONFIG_CPU_HAS_PMU */ +#ifdef CONFIG_HW_PERF_EVENTS + +/* The events for a given PMU register set. */ +struct pmu_hw_events { + /* + * The events that are active on the PMU for the given index. + */ + struct perf_event **events; + + /* + * A 1 bit for an index indicates that the counter is being used for + * an event. A 0 means that the counter can be used. + */ + unsigned long *used_mask; + + /* + * Hardware lock to serialize accesses to PMU registers. Needed for the + * read/modify/write sequences. + */ + raw_spinlock_t pmu_lock; +}; + +struct arm_pmu { + struct pmu pmu; + enum arm_perf_pmu_ids id; + enum arm_pmu_type type; + cpumask_t active_irqs; + const char *name; + irqreturn_t (*handle_irq)(int irq_num, void *dev); + void (*enable)(struct hw_perf_event *evt, int idx); + void (*disable)(struct hw_perf_event *evt, int idx); + int (*get_event_idx)(struct pmu_hw_events *hw_events, + struct hw_perf_event *hwc); + int (*set_event_filter)(struct hw_perf_event *evt, + struct perf_event_attr *attr); + u32 (*read_counter)(int idx); + void (*write_counter)(int idx, u32 val); + void (*start)(void); + void (*stop)(void); + void (*reset)(void *); + int (*map_event)(struct perf_event *event); + int num_events; + atomic_t active_events; + struct mutex reserve_mutex; + u64 max_period; + struct platform_device *plat_device; + struct pmu_hw_events *(*get_hw_events)(void); +}; + +#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) + +int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type); + +u64 armpmu_event_update(struct perf_event *event, + struct hw_perf_event *hwc, + int idx, int overflow); + +int armpmu_event_set_period(struct perf_event *event, + struct hw_perf_event *hwc, + int idx); + +#endif /* CONFIG_HW_PERF_EVENTS */ + #endif /* __ARM_PMU_H__ */ diff --git a/arch/arm/include/asm/poll.h b/arch/arm/include/asm/poll.h deleted file mode 100644 index c98509d3149e..000000000000 --- a/arch/arm/include/asm/poll.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/poll.h> diff --git a/arch/arm/include/asm/proc-fns.h b/arch/arm/include/asm/proc-fns.h index 633d1cb84d87..9e92cb205e65 100644 --- a/arch/arm/include/asm/proc-fns.h +++ b/arch/arm/include/asm/proc-fns.h @@ -81,6 +81,10 @@ extern void cpu_dcache_clean_area(void *, int); extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm); extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext); extern void cpu_reset(unsigned long addr) __attribute__((noreturn)); + +/* These three are private to arch/arm/kernel/suspend.c */ +extern void cpu_do_suspend(void *); +extern void cpu_do_resume(void *); #else #define cpu_proc_init processor._proc_init #define cpu_proc_fin processor._proc_fin @@ -89,6 +93,10 @@ extern void cpu_reset(unsigned long addr) __attribute__((noreturn)); #define cpu_dcache_clean_area processor.dcache_clean_area #define cpu_set_pte_ext processor.set_pte_ext #define cpu_do_switch_mm processor.switch_mm + +/* These three are private to arch/arm/kernel/suspend.c */ +#define cpu_do_suspend processor.do_suspend +#define cpu_do_resume processor.do_resume #endif extern void cpu_resume(void); diff --git a/arch/arm/include/asm/resource.h b/arch/arm/include/asm/resource.h deleted file mode 100644 index 734b581b5b6a..000000000000 --- a/arch/arm/include/asm/resource.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ARM_RESOURCE_H -#define _ARM_RESOURCE_H - -#include <asm-generic/resource.h> - -#endif diff --git a/arch/arm/include/asm/sections.h b/arch/arm/include/asm/sections.h deleted file mode 100644 index 2b8c5160388f..000000000000 --- a/arch/arm/include/asm/sections.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/sections.h> diff --git a/arch/arm/include/asm/siginfo.h b/arch/arm/include/asm/siginfo.h deleted file mode 100644 index 5e21852e6039..000000000000 --- a/arch/arm/include/asm/siginfo.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASMARM_SIGINFO_H -#define _ASMARM_SIGINFO_H - -#include <asm-generic/siginfo.h> - -#endif diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index e42d96a45d3e..1e5717afc4ac 100644 --- a/arch/arm/include/asm/smp.h +++ b/arch/arm/include/asm/smp.h @@ -33,6 +33,11 @@ extern void show_ipi_list(struct seq_file *, int); asmlinkage void do_IPI(int ipinr, struct pt_regs *regs); /* + * Called from C code, this handles an IPI. + */ +void handle_IPI(int ipinr, struct pt_regs *regs); + +/* * Setup the set of possible CPUs (via set_cpu_possible) */ extern void smp_init_cpus(void); @@ -66,6 +71,12 @@ extern void platform_secondary_init(unsigned int cpu); extern void platform_smp_prepare_cpus(unsigned int); /* + * Logical CPU mapping. + */ +extern int __cpu_logical_map[NR_CPUS]; +#define cpu_logical_map(cpu) __cpu_logical_map[cpu] + +/* * Initial data for bringing up a secondary CPU. */ struct secondary_data { @@ -88,9 +99,4 @@ extern void platform_cpu_enable(unsigned int cpu); extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); -/* - * show local interrupt info - */ -extern void show_local_irqs(struct seq_file *, int); - #endif /* ifndef __ASM_ARM_SMP_H */ diff --git a/arch/arm/include/asm/smp_twd.h b/arch/arm/include/asm/smp_twd.h index fed9981fba08..ef9ffba97ad8 100644 --- a/arch/arm/include/asm/smp_twd.h +++ b/arch/arm/include/asm/smp_twd.h @@ -22,7 +22,7 @@ struct clock_event_device; extern void __iomem *twd_base; -int twd_timer_ack(void); void twd_timer_setup(struct clock_event_device *); +void twd_timer_stop(struct clock_event_device *); #endif diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h index b0e4e1a02318..1c0a551ae375 100644 --- a/arch/arm/include/asm/suspend.h +++ b/arch/arm/include/asm/suspend.h @@ -1,22 +1,7 @@ #ifndef __ASM_ARM_SUSPEND_H #define __ASM_ARM_SUSPEND_H -#include <asm/memory.h> -#include <asm/tlbflush.h> - extern void cpu_resume(void); - -/* - * Hide the first two arguments to __cpu_suspend - these are an implementation - * detail which platform code shouldn't have to know about. - */ -static inline int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) -{ - extern int __cpu_suspend(int, long, unsigned long, - int (*)(unsigned long)); - int ret = __cpu_suspend(0, PHYS_OFFSET - PAGE_OFFSET, arg, fn); - flush_tlb_all(); - return ret; -} +extern int cpu_suspend(unsigned long, int (*)(unsigned long)); #endif diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h index 832888d0c20c..984014b92647 100644 --- a/arch/arm/include/asm/system.h +++ b/arch/arm/include/asm/system.h @@ -57,18 +57,12 @@ #ifndef __ASSEMBLY__ +#include <linux/compiler.h> #include <linux/linkage.h> #include <linux/irqflags.h> #include <asm/outercache.h> -#define __exception __attribute__((section(".exception.text"))) -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -#define __exception_irq_entry __irq_entry -#else -#define __exception_irq_entry __exception -#endif - struct thread_info; struct task_struct; @@ -97,14 +91,13 @@ void hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, #define xchg(ptr,x) \ ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)))) -extern asmlinkage void __backtrace(void); extern asmlinkage void c_backtrace(unsigned long fp, int pmode); struct mm_struct; extern void show_pte(struct mm_struct *mm, unsigned long addr); extern void __show_regs(struct pt_regs *); -extern int cpu_architecture(void); +extern int __pure cpu_architecture(void); extern void cpu_init(void); void arm_machine_restart(char mode, const char *cmd); diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 8077145698ff..02b2f8203982 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -471,7 +471,7 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr) * these operations. This is typically used when we are removing * PMD entries. */ -static inline void flush_pmd_entry(pmd_t *pmd) +static inline void flush_pmd_entry(void *pmd) { const unsigned int __tlb_flag = __cpu_tlb_flags; @@ -487,7 +487,7 @@ static inline void flush_pmd_entry(pmd_t *pmd) dsb(); } -static inline void clean_pmd_entry(pmd_t *pmd) +static inline void clean_pmd_entry(void *pmd) { const unsigned int __tlb_flag = __cpu_tlb_flags; diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index accbd7cad9b5..a7e457ed27c3 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -1,6 +1,39 @@ #ifndef _ASM_ARM_TOPOLOGY_H #define _ASM_ARM_TOPOLOGY_H +#ifdef CONFIG_ARM_CPU_TOPOLOGY + +#include <linux/cpumask.h> + +struct cputopo_arm { + int thread_id; + int core_id; + int socket_id; + cpumask_t thread_sibling; + cpumask_t core_sibling; +}; + +extern struct cputopo_arm cpu_topology[NR_CPUS]; + +#define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id) +#define topology_core_id(cpu) (cpu_topology[cpu].core_id) +#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) +#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) + +#define mc_capable() (cpu_topology[0].socket_id != -1) +#define smt_capable() (cpu_topology[0].thread_id != -1) + +void init_cpu_topology(void); +void store_cpu_topology(unsigned int cpuid); +const struct cpumask *cpu_coregroup_mask(unsigned int cpu); + +#else + +static inline void init_cpu_topology(void) { } +static inline void store_cpu_topology(unsigned int cpuid) { } + +#endif + #include <asm-generic/topology.h> #endif /* _ASM_ARM_TOPOLOGY_H */ diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index f7887dc53c1f..16eed6aebfa4 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -29,7 +29,7 @@ obj-$(CONFIG_MODULES) += armksyms.o module.o obj-$(CONFIG_ARTHUR) += arthur.o obj-$(CONFIG_ISA_DMA) += dma-isa.o obj-$(CONFIG_PCI) += bios32.o isa.o -obj-$(CONFIG_PM_SLEEP) += sleep.o +obj-$(CONFIG_ARM_CPU_SUSPEND) += sleep.o suspend.o obj-$(CONFIG_HAVE_SCHED_CLOCK) += sched_clock.o obj-$(CONFIG_SMP) += smp.o smp_tlb.o obj-$(CONFIG_HAVE_ARM_SCU) += smp_scu.o @@ -43,6 +43,13 @@ obj-$(CONFIG_KPROBES) += kprobes-thumb.o else obj-$(CONFIG_KPROBES) += kprobes-arm.o endif +obj-$(CONFIG_ARM_KPROBES_TEST) += test-kprobes.o +test-kprobes-objs := kprobes-test.o +ifdef CONFIG_THUMB2_KERNEL +test-kprobes-objs += kprobes-test-thumb.o +else +test-kprobes-objs += kprobes-test-arm.o +endif obj-$(CONFIG_ATAGS_PROC) += atags.o obj-$(CONFIG_OABI_COMPAT) += sys_oabi-compat.o obj-$(CONFIG_ARM_THUMBEE) += thumbee.o @@ -66,6 +73,7 @@ obj-$(CONFIG_IWMMXT) += iwmmxt.o obj-$(CONFIG_CPU_HAS_PMU) += pmu.o obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt +obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o ifneq ($(CONFIG_ARCH_EBSA110),y) obj-y += io.o diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index aeef960ff795..8e3c6f11b0a1 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -49,9 +49,6 @@ extern void __aeabi_ulcmp(void); extern void fpundefinstr(void); - -EXPORT_SYMBOL(__backtrace); - /* platform dependent support */ EXPORT_SYMBOL(__udelay); EXPORT_SYMBOL(__const_udelay); diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 16baba2e4369..1429d8989fb9 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -20,6 +20,7 @@ #include <asm/thread_info.h> #include <asm/memory.h> #include <asm/procinfo.h> +#include <asm/hardware/cache-l2x0.h> #include <linux/kbuild.h> /* @@ -92,6 +93,17 @@ int main(void) DEFINE(S_OLD_R0, offsetof(struct pt_regs, ARM_ORIG_r0)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); BLANK(); +#ifdef CONFIG_CACHE_L2X0 + DEFINE(L2X0_R_PHY_BASE, offsetof(struct l2x0_regs, phy_base)); + DEFINE(L2X0_R_AUX_CTRL, offsetof(struct l2x0_regs, aux_ctrl)); + DEFINE(L2X0_R_TAG_LATENCY, offsetof(struct l2x0_regs, tag_latency)); + DEFINE(L2X0_R_DATA_LATENCY, offsetof(struct l2x0_regs, data_latency)); + DEFINE(L2X0_R_FILTER_START, offsetof(struct l2x0_regs, filter_start)); + DEFINE(L2X0_R_FILTER_END, offsetof(struct l2x0_regs, filter_end)); + DEFINE(L2X0_R_PREFETCH_CTRL, offsetof(struct l2x0_regs, prefetch_ctrl)); + DEFINE(L2X0_R_PWR_CTRL, offsetof(struct l2x0_regs, pwr_ctrl)); + BLANK(); +#endif #ifdef CONFIG_CPU_HAS_ASID DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id)); BLANK(); diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index d6df359408f0..c0d9203fc75e 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -412,6 +412,9 @@ void pcibios_fixup_bus(struct pci_bus *bus) printk(KERN_INFO "PCI: bus%d: Fast back to back transfers %sabled\n", bus->number, (features & PCI_COMMAND_FAST_BACK) ? "en" : "dis"); } +#ifdef CONFIG_HOTPLUG +EXPORT_SYMBOL(pcibios_fixup_bus); +#endif /* * Convert from Linux-centric to bus-centric addresses for bridge devices. @@ -431,6 +434,7 @@ pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, region->start = res->start - offset; region->end = res->end - offset; } +EXPORT_SYMBOL(pcibios_resource_to_bus); void __devinit pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, @@ -447,12 +451,7 @@ pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, res->start = region->start + offset; res->end = region->end + offset; } - -#ifdef CONFIG_HOTPLUG -EXPORT_SYMBOL(pcibios_fixup_bus); -EXPORT_SYMBOL(pcibios_resource_to_bus); EXPORT_SYMBOL(pcibios_bus_to_resource); -#endif /* * Swizzle the device pin each time we cross a bridge. diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S index b7685f1bb04a..204e2160cfcc 100644 --- a/arch/arm/kernel/debug.S +++ b/arch/arm/kernel/debug.S @@ -151,6 +151,8 @@ printhex: adr r2, hexbuf b printascii ENDPROC(printhex2) +hexbuf: .space 16 + .ltorg ENTRY(printascii) @@ -175,5 +177,3 @@ ENTRY(printch) mov r0, #0 b 1b ENDPROC(printch) - -hexbuf: .space 16 diff --git a/arch/arm/kernel/dma.c b/arch/arm/kernel/dma.c index 2c4a185f92cd..7b829d9663b1 100644 --- a/arch/arm/kernel/dma.c +++ b/arch/arm/kernel/dma.c @@ -23,7 +23,7 @@ #include <asm/mach/dma.h> -DEFINE_SPINLOCK(dma_spin_lock); +DEFINE_RAW_SPINLOCK(dma_spin_lock); EXPORT_SYMBOL(dma_spin_lock); static dma_t *dma_chan[MAX_DMA_CHANNELS]; diff --git a/arch/arm/kernel/ecard.c b/arch/arm/kernel/ecard.c index d16500110ee9..4dd0edab6a65 100644 --- a/arch/arm/kernel/ecard.c +++ b/arch/arm/kernel/ecard.c @@ -237,7 +237,7 @@ static void ecard_init_pgtables(struct mm_struct *mm) memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (IO_SIZE / PGDIR_SIZE)); - src_pgd = pgd_offset(mm, EASI_BASE); + src_pgd = pgd_offset(mm, (unsigned long)EASI_BASE); dst_pgd = pgd_offset(mm, EASI_START); memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE)); @@ -674,44 +674,37 @@ static int __init ecard_probeirqhw(void) #define ecard_probeirqhw() (0) #endif -#ifndef IO_EC_MEMC8_BASE -#define IO_EC_MEMC8_BASE 0 -#endif - -static unsigned int __ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed) +static void __iomem *__ecard_address(ecard_t *ec, card_type_t type, card_speed_t speed) { - unsigned long address = 0; + void __iomem *address = NULL; int slot = ec->slot_no; if (ec->slot_no == 8) - return IO_EC_MEMC8_BASE; + return ECARD_MEMC8_BASE; ectcr &= ~(1 << slot); switch (type) { case ECARD_MEMC: if (slot < 4) - address = IO_EC_MEMC_BASE + (slot << 12); + address = ECARD_MEMC_BASE + (slot << 14); break; case ECARD_IOC: if (slot < 4) - address = IO_EC_IOC_BASE + (slot << 12); -#ifdef IO_EC_IOC4_BASE + address = ECARD_IOC_BASE + (slot << 14); else - address = IO_EC_IOC4_BASE + ((slot - 4) << 12); -#endif + address = ECARD_IOC4_BASE + ((slot - 4) << 14); if (address) - address += speed << 17; + address += speed << 19; break; -#ifdef IO_EC_EASI_BASE case ECARD_EASI: - address = IO_EC_EASI_BASE + (slot << 22); + address = ECARD_EASI_BASE + (slot << 24); if (speed == ECARD_FAST) ectcr |= 1 << slot; break; -#endif + default: break; } @@ -990,6 +983,7 @@ ecard_probe(int slot, card_type_t type) ecard_t **ecp; ecard_t *ec; struct ex_ecid cid; + void __iomem *addr; int i, rc; ec = ecard_alloc_card(type, slot); @@ -999,7 +993,7 @@ ecard_probe(int slot, card_type_t type) } rc = -ENODEV; - if ((ec->podaddr = __ecard_address(ec, type, ECARD_SYNC)) == 0) + if ((addr = __ecard_address(ec, type, ECARD_SYNC)) == NULL) goto nodev; cid.r_zero = 1; @@ -1019,7 +1013,7 @@ ecard_probe(int slot, card_type_t type) ec->cid.fiqmask = cid.r_fiqmask; ec->cid.fiqoff = ecard_gets24(cid.r_fiqoff); ec->fiqaddr = - ec->irqaddr = (void __iomem *)ioaddr(ec->podaddr); + ec->irqaddr = addr; if (ec->cid.is) { ec->irqmask = ec->cid.irqmask; @@ -1048,10 +1042,8 @@ ecard_probe(int slot, card_type_t type) set_irq_flags(ec->irq, IRQF_VALID); } -#ifdef IO_EC_MEMC8_BASE if (slot == 8) ec->irq = 11; -#endif #ifdef CONFIG_ARCH_RPC /* On RiscPC, only first two slots have DMA capability */ if (slot < 2) @@ -1097,9 +1089,7 @@ static int __init ecard_init(void) ecard_probe(slot, ECARD_IOC); } -#ifdef IO_EC_MEMC8_BASE ecard_probe(8, ECARD_IOC); -#endif irqhw = ecard_probeirqhw(); diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index a87cbf889ff4..9ad50c4208ae 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -24,6 +24,7 @@ #include <asm/unwind.h> #include <asm/unistd.h> #include <asm/tls.h> +#include <asm/system.h> #include "entry-header.S" #include <asm/entry-macro-multi.S> @@ -262,8 +263,7 @@ __und_svc: ldr r0, [r4, #-4] #else ldrh r0, [r4, #-2] @ Thumb instruction at LR - 2 - and r9, r0, #0xf800 - cmp r9, #0xe800 @ 32-bit instruction if xx >= 0 + cmp r0, #0xe800 @ 32-bit instruction if xx >= 0 ldrhhs r9, [r4] @ bottom 16 bits orrhs r0, r9, r0, lsl #16 #endif @@ -440,18 +440,46 @@ __und_usr: #endif beq call_fpe @ Thumb instruction -#if __LINUX_ARM_ARCH__ >= 7 +#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7 +/* + * Thumb-2 instruction handling. Note that because pre-v6 and >= v6 platforms + * can never be supported in a single kernel, this code is not applicable at + * all when __LINUX_ARM_ARCH__ < 6. This allows simplifying assumptions to be + * made about .arch directives. + */ +#if __LINUX_ARM_ARCH__ < 7 +/* If the target CPU may not be Thumb-2-capable, a run-time check is needed: */ +#define NEED_CPU_ARCHITECTURE + ldr r5, .LCcpu_architecture + ldr r5, [r5] + cmp r5, #CPU_ARCH_ARMv7 + blo __und_usr_unknown +/* + * The following code won't get run unless the running CPU really is v7, so + * coding round the lack of ldrht on older arches is pointless. Temporarily + * override the assembler target arch with the minimum required instead: + */ + .arch armv6t2 +#endif 2: ARM( ldrht r5, [r4], #2 ) THUMB( ldrht r5, [r4] ) THUMB( add r4, r4, #2 ) - and r0, r5, #0xf800 @ mask bits 111x x... .... .... - cmp r0, #0xe800 @ 32bit instruction if xx != 0 + cmp r5, #0xe800 @ 32bit instruction if xx != 0 blo __und_usr_unknown 3: ldrht r0, [r4] add r2, r2, #2 @ r2 is PC + 2, make it PC + 4 orr r0, r0, r5, lsl #16 + +#if __LINUX_ARM_ARCH__ < 7 +/* If the target arch was overridden, change it back: */ +#ifdef CONFIG_CPU_32v6K + .arch armv6k #else + .arch armv6 +#endif +#endif /* __LINUX_ARM_ARCH__ < 7 */ +#else /* !(CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7) */ b __und_usr_unknown #endif UNWIND(.fnend ) @@ -578,6 +606,12 @@ call_fpe: movw_pc lr @ CP#14 (Debug) movw_pc lr @ CP#15 (Control) +#ifdef NEED_CPU_ARCHITECTURE + .align 2 +.LCcpu_architecture: + .word __cpu_architecture +#endif + #ifdef CONFIG_NEON .align 6 diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 673c806cc106..566c54c2a1fe 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -21,6 +21,7 @@ #include <asm/memory.h> #include <asm/thread_info.h> #include <asm/system.h> +#include <asm/pgtable.h> #ifdef CONFIG_DEBUG_LL #include <mach/debug-macro.S> @@ -38,11 +39,14 @@ #error KERNEL_RAM_VADDR must start at 0xXXXX8000 #endif +#define PG_DIR_SIZE 0x4000 +#define PMD_ORDER 2 + .globl swapper_pg_dir - .equ swapper_pg_dir, KERNEL_RAM_VADDR - 0x4000 + .equ swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE .macro pgtbl, rd, phys - add \rd, \phys, #TEXT_OFFSET - 0x4000 + add \rd, \phys, #TEXT_OFFSET - PG_DIR_SIZE .endm #ifdef CONFIG_XIP_KERNEL @@ -148,11 +152,11 @@ __create_page_tables: pgtbl r4, r8 @ page table address /* - * Clear the 16K level 1 swapper page table + * Clear the swapper page table */ mov r0, r4 mov r3, #0 - add r6, r0, #0x4000 + add r6, r0, #PG_DIR_SIZE 1: str r3, [r0], #4 str r3, [r0], #4 str r3, [r0], #4 @@ -171,30 +175,30 @@ __create_page_tables: sub r0, r0, r3 @ virt->phys offset add r5, r5, r0 @ phys __enable_mmu add r6, r6, r0 @ phys __enable_mmu_end - mov r5, r5, lsr #20 - mov r6, r6, lsr #20 + mov r5, r5, lsr #SECTION_SHIFT + mov r6, r6, lsr #SECTION_SHIFT -1: orr r3, r7, r5, lsl #20 @ flags + kernel base - str r3, [r4, r5, lsl #2] @ identity mapping - teq r5, r6 - addne r5, r5, #1 @ next section - bne 1b +1: orr r3, r7, r5, lsl #SECTION_SHIFT @ flags + kernel base + str r3, [r4, r5, lsl #PMD_ORDER] @ identity mapping + cmp r5, r6 + addlo r5, r5, #1 @ next section + blo 1b /* * Now setup the pagetables for our kernel direct * mapped region. */ mov r3, pc - mov r3, r3, lsr #20 - orr r3, r7, r3, lsl #20 - add r0, r4, #(KERNEL_START & 0xff000000) >> 18 - str r3, [r0, #(KERNEL_START & 0x00f00000) >> 18]! + mov r3, r3, lsr #SECTION_SHIFT + orr r3, r7, r3, lsl #SECTION_SHIFT + add r0, r4, #(KERNEL_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER) + str r3, [r0, #((KERNEL_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ORDER]! ldr r6, =(KERNEL_END - 1) - add r0, r0, #4 - add r6, r4, r6, lsr #18 + add r0, r0, #1 << PMD_ORDER + add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER) 1: cmp r0, r6 - add r3, r3, #1 << 20 - strls r3, [r0], #4 + add r3, r3, #1 << SECTION_SHIFT + strls r3, [r0], #1 << PMD_ORDER bls 1b #ifdef CONFIG_XIP_KERNEL @@ -203,11 +207,11 @@ __create_page_tables: */ add r3, r8, #TEXT_OFFSET orr r3, r3, r7 - add r0, r4, #(KERNEL_RAM_VADDR & 0xff000000) >> 18 - str r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> 18]! + add r0, r4, #(KERNEL_RAM_VADDR & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER) + str r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> (SECTION_SHIFT - PMD_ORDER)]! ldr r6, =(_end - 1) add r0, r0, #4 - add r6, r4, r6, lsr #18 + add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER) 1: cmp r0, r6 add r3, r3, #1 << 20 strls r3, [r0], #4 @@ -218,12 +222,12 @@ __create_page_tables: * Then map boot params address in r2 or * the first 1MB of ram if boot params address is not specified. */ - mov r0, r2, lsr #20 - movs r0, r0, lsl #20 + mov r0, r2, lsr #SECTION_SHIFT + movs r0, r0, lsl #SECTION_SHIFT moveq r0, r8 sub r3, r0, r8 add r3, r3, #PAGE_OFFSET - add r3, r4, r3, lsr #18 + add r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER) orr r6, r7, r0 str r6, [r3] @@ -236,21 +240,21 @@ __create_page_tables: */ addruart r7, r3, r0 - mov r3, r3, lsr #20 - mov r3, r3, lsl #2 + mov r3, r3, lsr #SECTION_SHIFT + mov r3, r3, lsl #PMD_ORDER add r0, r4, r3 rsb r3, r3, #0x4000 @ PTRS_PER_PGD*sizeof(long) cmp r3, #0x0800 @ limit to 512MB movhi r3, #0x0800 add r6, r0, r3 - mov r3, r7, lsr #20 + mov r3, r7, lsr #SECTION_SHIFT ldr r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags - orr r3, r7, r3, lsl #20 + orr r3, r7, r3, lsl #SECTION_SHIFT 1: str r3, [r0], #4 - add r3, r3, #1 << 20 - teq r0, r6 - bne 1b + add r3, r3, #1 << SECTION_SHIFT + cmp r0, r6 + blo 1b #else /* CONFIG_DEBUG_ICEDCC */ /* we don't need any serial debugging mappings for ICEDCC */ @@ -262,7 +266,7 @@ __create_page_tables: * If we're using the NetWinder or CATS, we also need to map * in the 16550-type serial port for the debug messages */ - add r0, r4, #0xff000000 >> 18 + add r0, r4, #0xff000000 >> (SECTION_SHIFT - PMD_ORDER) orr r3, r7, #0x7c000000 str r3, [r0] #endif @@ -272,10 +276,10 @@ __create_page_tables: * Similar reasons here - for debug. This is * only for Acorn RiscPC architectures. */ - add r0, r4, #0x02000000 >> 18 + add r0, r4, #0x02000000 >> (SECTION_SHIFT - PMD_ORDER) orr r3, r7, #0x02000000 str r3, [r0] - add r0, r4, #0xd8000000 >> 18 + add r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ORDER) str r3, [r0] #endif #endif diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index a927ca1f5566..814a52a9dc39 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -45,7 +45,6 @@ static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[ARM_MAX_WRP]); /* Number of BRP/WRP registers on this CPU. */ static int core_num_brps; -static int core_num_reserved_brps; static int core_num_wrps; /* Debug architecture version. */ @@ -137,10 +136,11 @@ static u8 get_debug_arch(void) u32 didr; /* Do we implement the extended CPUID interface? */ - if (WARN_ONCE((((read_cpuid_id() >> 16) & 0xf) != 0xf), - "CPUID feature registers not supported. " - "Assuming v6 debug is present.\n")) + if (((read_cpuid_id() >> 16) & 0xf) != 0xf) { + pr_warning("CPUID feature registers not supported. " + "Assuming v6 debug is present.\n"); return ARM_DEBUG_ARCH_V6; + } ARM_DBG_READ(c0, 0, didr); return (didr >> 16) & 0xf; @@ -154,10 +154,21 @@ u8 arch_get_debug_arch(void) static int debug_arch_supported(void) { u8 arch = get_debug_arch(); - return arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14; + + /* We don't support the memory-mapped interface. */ + return (arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14) || + arch >= ARM_DEBUG_ARCH_V7_1; +} + +/* Determine number of WRP registers available. */ +static int get_num_wrp_resources(void) +{ + u32 didr; + ARM_DBG_READ(c0, 0, didr); + return ((didr >> 28) & 0xf) + 1; } -/* Determine number of BRP register available. */ +/* Determine number of BRP registers available. */ static int get_num_brp_resources(void) { u32 didr; @@ -176,9 +187,10 @@ static int core_has_mismatch_brps(void) static int get_num_wrps(void) { /* - * FIXME: When a watchpoint fires, the only way to work out which - * watchpoint it was is by disassembling the faulting instruction - * and working out the address of the memory access. + * On debug architectures prior to 7.1, when a watchpoint fires, the + * only way to work out which watchpoint it was is by disassembling + * the faulting instruction and working out the address of the memory + * access. * * Furthermore, we can only do this if the watchpoint was precise * since imprecise watchpoints prevent us from calculating register @@ -192,36 +204,17 @@ static int get_num_wrps(void) * [the ARM ARM states that the DFAR is UNKNOWN, but experience shows * that it is set on some implementations]. */ + if (get_debug_arch() < ARM_DEBUG_ARCH_V7_1) + return 1; -#if 0 - int wrps; - u32 didr; - ARM_DBG_READ(c0, 0, didr); - wrps = ((didr >> 28) & 0xf) + 1; -#endif - int wrps = 1; - - if (core_has_mismatch_brps() && wrps >= get_num_brp_resources()) - wrps = get_num_brp_resources() - 1; - - return wrps; -} - -/* We reserve one breakpoint for each watchpoint. */ -static int get_num_reserved_brps(void) -{ - if (core_has_mismatch_brps()) - return get_num_wrps(); - return 0; + return get_num_wrp_resources(); } /* Determine number of usable BRPs available. */ static int get_num_brps(void) { int brps = get_num_brp_resources(); - if (core_has_mismatch_brps()) - brps -= get_num_reserved_brps(); - return brps; + return core_has_mismatch_brps() ? brps - 1 : brps; } /* @@ -239,7 +232,7 @@ static int enable_monitor_mode(void) /* Ensure that halting mode is disabled. */ if (WARN_ONCE(dscr & ARM_DSCR_HDBGEN, - "halting debug mode enabled. Unable to access hardware resources.\n")) { + "halting debug mode enabled. Unable to access hardware resources.\n")) { ret = -EPERM; goto out; } @@ -255,6 +248,7 @@ static int enable_monitor_mode(void) ARM_DBG_WRITE(c1, 0, (dscr | ARM_DSCR_MDBGEN)); break; case ARM_DEBUG_ARCH_V7_ECP14: + case ARM_DEBUG_ARCH_V7_1: ARM_DBG_WRITE(c2, 2, (dscr | ARM_DSCR_MDBGEN)); break; default: @@ -346,24 +340,10 @@ int arch_install_hw_breakpoint(struct perf_event *bp) val_base = ARM_BASE_BVR; slots = (struct perf_event **)__get_cpu_var(bp_on_reg); max_slots = core_num_brps; - if (info->step_ctrl.enabled) { - /* Override the breakpoint data with the step data. */ - addr = info->trigger & ~0x3; - ctrl = encode_ctrl_reg(info->step_ctrl); - } } else { /* Watchpoint */ - if (info->step_ctrl.enabled) { - /* Install into the reserved breakpoint region. */ - ctrl_base = ARM_BASE_BCR + core_num_brps; - val_base = ARM_BASE_BVR + core_num_brps; - /* Override the watchpoint data with the step data. */ - addr = info->trigger & ~0x3; - ctrl = encode_ctrl_reg(info->step_ctrl); - } else { - ctrl_base = ARM_BASE_WCR; - val_base = ARM_BASE_WVR; - } + ctrl_base = ARM_BASE_WCR; + val_base = ARM_BASE_WVR; slots = (struct perf_event **)__get_cpu_var(wp_on_reg); max_slots = core_num_wrps; } @@ -382,6 +362,17 @@ int arch_install_hw_breakpoint(struct perf_event *bp) goto out; } + /* Override the breakpoint data with the step data. */ + if (info->step_ctrl.enabled) { + addr = info->trigger & ~0x3; + ctrl = encode_ctrl_reg(info->step_ctrl); + if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE) { + i = 0; + ctrl_base = ARM_BASE_BCR + core_num_brps; + val_base = ARM_BASE_BVR + core_num_brps; + } + } + /* Setup the address register. */ write_wb_reg(val_base + i, addr); @@ -405,10 +396,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) max_slots = core_num_brps; } else { /* Watchpoint */ - if (info->step_ctrl.enabled) - base = ARM_BASE_BCR + core_num_brps; - else - base = ARM_BASE_WCR; + base = ARM_BASE_WCR; slots = (struct perf_event **)__get_cpu_var(wp_on_reg); max_slots = core_num_wrps; } @@ -426,6 +414,13 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot\n")) return; + /* Ensure that we disable the mismatch breakpoint. */ + if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE && + info->step_ctrl.enabled) { + i = 0; + base = ARM_BASE_BCR + core_num_brps; + } + /* Reset the control register. */ write_wb_reg(base + i, 0); } @@ -632,10 +627,9 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * we can use the mismatch feature as a poor-man's hardware * single-step, but this only works for per-task breakpoints. */ - if (WARN_ONCE(!bp->overflow_handler && - (arch_check_bp_in_kernelspace(bp) || !core_has_mismatch_brps() - || !bp->hw.bp_target), - "overflow handler required but none found\n")) { + if (!bp->overflow_handler && (arch_check_bp_in_kernelspace(bp) || + !core_has_mismatch_brps() || !bp->hw.bp_target)) { + pr_warning("overflow handler required but none found\n"); ret = -EINVAL; } out: @@ -666,34 +660,62 @@ static void disable_single_step(struct perf_event *bp) arch_install_hw_breakpoint(bp); } -static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs) +static void watchpoint_handler(unsigned long addr, unsigned int fsr, + struct pt_regs *regs) { - int i; + int i, access; + u32 val, ctrl_reg, alignment_mask; struct perf_event *wp, **slots; struct arch_hw_breakpoint *info; + struct arch_hw_breakpoint_ctrl ctrl; slots = (struct perf_event **)__get_cpu_var(wp_on_reg); - /* Without a disassembler, we can only handle 1 watchpoint. */ - BUG_ON(core_num_wrps > 1); - for (i = 0; i < core_num_wrps; ++i) { rcu_read_lock(); wp = slots[i]; - if (wp == NULL) { - rcu_read_unlock(); - continue; - } + if (wp == NULL) + goto unlock; + info = counter_arch_bp(wp); /* - * The DFAR is an unknown value. Since we only allow a - * single watchpoint, we can set the trigger to the lowest - * possible faulting address. + * The DFAR is an unknown value on debug architectures prior + * to 7.1. Since we only allow a single watchpoint on these + * older CPUs, we can set the trigger to the lowest possible + * faulting address. */ - info = counter_arch_bp(wp); - info->trigger = wp->attr.bp_addr; + if (debug_arch < ARM_DEBUG_ARCH_V7_1) { + BUG_ON(i > 0); + info->trigger = wp->attr.bp_addr; + } else { + if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) + alignment_mask = 0x7; + else + alignment_mask = 0x3; + + /* Check if the watchpoint value matches. */ + val = read_wb_reg(ARM_BASE_WVR + i); + if (val != (addr & ~alignment_mask)) + goto unlock; + + /* Possible match, check the byte address select. */ + ctrl_reg = read_wb_reg(ARM_BASE_WCR + i); + decode_ctrl_reg(ctrl_reg, &ctrl); + if (!((1 << (addr & alignment_mask)) & ctrl.len)) + goto unlock; + + /* Check that the access type matches. */ + access = (fsr & ARM_FSR_ACCESS_MASK) ? HW_BREAKPOINT_W : + HW_BREAKPOINT_R; + if (!(access & hw_breakpoint_type(wp))) + goto unlock; + + /* We have a winner. */ + info->trigger = addr; + } + pr_debug("watchpoint fired: address = 0x%x\n", info->trigger); perf_bp_event(wp, regs); @@ -705,6 +727,7 @@ static void watchpoint_handler(unsigned long unknown, struct pt_regs *regs) if (!wp->overflow_handler) enable_single_step(wp, instruction_pointer(regs)); +unlock: rcu_read_unlock(); } } @@ -717,7 +740,7 @@ static void watchpoint_single_step_handler(unsigned long pc) slots = (struct perf_event **)__get_cpu_var(wp_on_reg); - for (i = 0; i < core_num_reserved_brps; ++i) { + for (i = 0; i < core_num_wrps; ++i) { rcu_read_lock(); wp = slots[i]; @@ -820,7 +843,7 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr, case ARM_ENTRY_ASYNC_WATCHPOINT: WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n"); case ARM_ENTRY_SYNC_WATCHPOINT: - watchpoint_handler(addr, regs); + watchpoint_handler(addr, fsr, regs); break; default: ret = 1; /* Unhandled fault. */ @@ -834,11 +857,31 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr, /* * One-time initialisation. */ -static void reset_ctrl_regs(void *info) +static cpumask_t debug_err_mask; + +static int debug_reg_trap(struct pt_regs *regs, unsigned int instr) { - int i, cpu = smp_processor_id(); + int cpu = smp_processor_id(); + + pr_warning("Debug register access (0x%x) caused undefined instruction on CPU %d\n", + instr, cpu); + + /* Set the error flag for this CPU and skip the faulting instruction. */ + cpumask_set_cpu(cpu, &debug_err_mask); + instruction_pointer(regs) += 4; + return 0; +} + +static struct undef_hook debug_reg_hook = { + .instr_mask = 0x0fe80f10, + .instr_val = 0x0e000e10, + .fn = debug_reg_trap, +}; + +static void reset_ctrl_regs(void *unused) +{ + int i, raw_num_brps, err = 0, cpu = smp_processor_id(); u32 dbg_power; - cpumask_t *cpumask = info; /* * v7 debug contains save and restore registers so that debug state @@ -848,38 +891,57 @@ static void reset_ctrl_regs(void *info) * Access Register to avoid taking undefined instruction exceptions * later on. */ - if (debug_arch >= ARM_DEBUG_ARCH_V7_ECP14) { + switch (debug_arch) { + case ARM_DEBUG_ARCH_V6: + case ARM_DEBUG_ARCH_V6_1: + /* ARMv6 cores just need to reset the registers. */ + goto reset_regs; + case ARM_DEBUG_ARCH_V7_ECP14: /* * Ensure sticky power-down is clear (i.e. debug logic is * powered up). */ asm volatile("mrc p14, 0, %0, c1, c5, 4" : "=r" (dbg_power)); - if ((dbg_power & 0x1) == 0) { - pr_warning("CPU %d debug is powered down!\n", cpu); - cpumask_or(cpumask, cpumask, cpumask_of(cpu)); - return; - } - + if ((dbg_power & 0x1) == 0) + err = -EPERM; + break; + case ARM_DEBUG_ARCH_V7_1: /* - * Unconditionally clear the lock by writing a value - * other than 0xC5ACCE55 to the access register. + * Ensure the OS double lock is clear. */ - asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0)); - isb(); + asm volatile("mrc p14, 0, %0, c1, c3, 4" : "=r" (dbg_power)); + if ((dbg_power & 0x1) == 1) + err = -EPERM; + break; + } - /* - * Clear any configured vector-catch events before - * enabling monitor mode. - */ - asm volatile("mcr p14, 0, %0, c0, c7, 0" : : "r" (0)); - isb(); + if (err) { + pr_warning("CPU %d debug is powered down!\n", cpu); + cpumask_or(&debug_err_mask, &debug_err_mask, cpumask_of(cpu)); + return; } + /* + * Unconditionally clear the lock by writing a value + * other than 0xC5ACCE55 to the access register. + */ + asm volatile("mcr p14, 0, %0, c1, c0, 4" : : "r" (0)); + isb(); + + /* + * Clear any configured vector-catch events before + * enabling monitor mode. + */ + asm volatile("mcr p14, 0, %0, c0, c7, 0" : : "r" (0)); + isb(); + +reset_regs: if (enable_monitor_mode()) return; /* We must also reset any reserved registers. */ - for (i = 0; i < core_num_brps + core_num_reserved_brps; ++i) { + raw_num_brps = get_num_brp_resources(); + for (i = 0; i < raw_num_brps; ++i) { write_wb_reg(ARM_BASE_BCR + i, 0UL); write_wb_reg(ARM_BASE_BVR + i, 0UL); } @@ -895,6 +957,7 @@ static int __cpuinit dbg_reset_notify(struct notifier_block *self, { if (action == CPU_ONLINE) smp_call_function_single((int)cpu, reset_ctrl_regs, NULL, 1); + return NOTIFY_OK; } @@ -905,7 +968,6 @@ static struct notifier_block __cpuinitdata dbg_reset_nb = { static int __init arch_hw_breakpoint_init(void) { u32 dscr; - cpumask_t cpumask = { CPU_BITS_NONE }; debug_arch = get_debug_arch(); @@ -916,28 +978,31 @@ static int __init arch_hw_breakpoint_init(void) /* Determine how many BRPs/WRPs are available. */ core_num_brps = get_num_brps(); - core_num_reserved_brps = get_num_reserved_brps(); core_num_wrps = get_num_wrps(); - pr_info("found %d breakpoint and %d watchpoint registers.\n", - core_num_brps + core_num_reserved_brps, core_num_wrps); - - if (core_num_reserved_brps) - pr_info("%d breakpoint(s) reserved for watchpoint " - "single-step.\n", core_num_reserved_brps); + /* + * We need to tread carefully here because DBGSWENABLE may be + * driven low on this core and there isn't an architected way to + * determine that. + */ + register_undef_hook(&debug_reg_hook); /* * Reset the breakpoint resources. We assume that a halting * debugger will leave the world in a nice state for us. */ - on_each_cpu(reset_ctrl_regs, &cpumask, 1); - if (!cpumask_empty(&cpumask)) { + on_each_cpu(reset_ctrl_regs, NULL, 1); + unregister_undef_hook(&debug_reg_hook); + if (!cpumask_empty(&debug_err_mask)) { core_num_brps = 0; - core_num_reserved_brps = 0; core_num_wrps = 0; return 0; } + pr_info("found %d " "%s" "breakpoint and %d watchpoint registers.\n", + core_num_brps, core_has_mismatch_brps() ? "(+1 reserved) " : + "", core_num_wrps); + ARM_DBG_READ(c1, 0, dscr); if (dscr & ARM_DSCR_HDBGEN) { max_watchpoint_len = 4; diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index de3dcab8610b..7cb29261249a 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -35,8 +35,8 @@ #include <linux/list.h> #include <linux/kallsyms.h> #include <linux/proc_fs.h> -#include <linux/ftrace.h> +#include <asm/exception.h> #include <asm/system.h> #include <asm/mach/arch.h> #include <asm/mach/irq.h> @@ -59,9 +59,6 @@ int arch_show_interrupts(struct seq_file *p, int prec) #ifdef CONFIG_SMP show_ipi_list(p, prec); #endif -#ifdef CONFIG_LOCAL_TIMERS - show_local_irqs(p, prec); -#endif seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count); return 0; } diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 79203ee1d039..9fe8910308af 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -60,6 +60,7 @@ #include <linux/kernel.h> #include <linux/kprobes.h> +#include <linux/module.h> #include "kprobes.h" @@ -971,6 +972,9 @@ const union decode_item kprobe_decode_arm_table[] = { DECODE_END }; +#ifdef CONFIG_ARM_KPROBES_TEST_MODULE +EXPORT_SYMBOL_GPL(kprobe_decode_arm_table); +#endif static void __kprobes arm_singlestep(struct kprobe *p, struct pt_regs *regs) { diff --git a/arch/arm/kernel/kprobes-test-arm.c b/arch/arm/kernel/kprobes-test-arm.c new file mode 100644 index 000000000000..fc82de8bdcce --- /dev/null +++ b/arch/arm/kernel/kprobes-test-arm.c @@ -0,0 +1,1323 @@ +/* + * arch/arm/kernel/kprobes-test-arm.c + * + * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/module.h> + +#include "kprobes-test.h" + + +#define TEST_ISA "32" + +#define TEST_ARM_TO_THUMB_INTERWORK_R(code1, reg, val, code2) \ + TESTCASE_START(code1 #reg code2) \ + TEST_ARG_REG(reg, val) \ + TEST_ARG_REG(14, 99f) \ + TEST_ARG_END("") \ + "50: nop \n\t" \ + "1: "code1 #reg code2" \n\t" \ + " bx lr \n\t" \ + ".thumb \n\t" \ + "3: adr lr, 2f \n\t" \ + " bx lr \n\t" \ + ".arm \n\t" \ + "2: nop \n\t" \ + TESTCASE_END + +#define TEST_ARM_TO_THUMB_INTERWORK_P(code1, reg, val, code2) \ + TESTCASE_START(code1 #reg code2) \ + TEST_ARG_PTR(reg, val) \ + TEST_ARG_REG(14, 99f) \ + TEST_ARG_MEM(15, 3f+1) \ + TEST_ARG_END("") \ + "50: nop \n\t" \ + "1: "code1 #reg code2" \n\t" \ + " bx lr \n\t" \ + ".thumb \n\t" \ + "3: adr lr, 2f \n\t" \ + " bx lr \n\t" \ + ".arm \n\t" \ + "2: nop \n\t" \ + TESTCASE_END + + +void kprobe_arm_test_cases(void) +{ + kprobe_test_flags = 0; + + TEST_GROUP("Data-processing (register), (register-shifted register), (immediate)") + +#define _DATA_PROCESSING_DNM(op,s,val) \ + TEST_RR( op "eq" s " r0, r",1, VAL1,", r",2, val, "") \ + TEST_RR( op "ne" s " r1, r",1, VAL1,", r",2, val, ", lsl #3") \ + TEST_RR( op "cs" s " r2, r",3, VAL1,", r",2, val, ", lsr #4") \ + TEST_RR( op "cc" s " r3, r",3, VAL1,", r",2, val, ", asr #5") \ + TEST_RR( op "mi" s " r4, r",5, VAL1,", r",2, N(val),", asr #6") \ + TEST_RR( op "pl" s " r5, r",5, VAL1,", r",2, val, ", ror #7") \ + TEST_RR( op "vs" s " r6, r",7, VAL1,", r",2, val, ", rrx") \ + TEST_R( op "vc" s " r6, r",7, VAL1,", pc, lsl #3") \ + TEST_R( op "vc" s " r6, r",7, VAL1,", sp, lsr #4") \ + TEST_R( op "vc" s " r6, pc, r",7, VAL1,", asr #5") \ + TEST_R( op "vc" s " r6, sp, r",7, VAL1,", ror #6") \ + TEST_RRR( op "hi" s " r8, r",9, VAL1,", r",14,val, ", lsl r",0, 3,"")\ + TEST_RRR( op "ls" s " r9, r",9, VAL1,", r",14,val, ", lsr r",7, 4,"")\ + TEST_RRR( op "ge" s " r10, r",11,VAL1,", r",14,val, ", asr r",7, 5,"")\ + TEST_RRR( op "lt" s " r11, r",11,VAL1,", r",14,N(val),", asr r",7, 6,"")\ + TEST_RR( op "gt" s " r12, r13" ", r",14,val, ", ror r",14,7,"")\ + TEST_RR( op "le" s " r14, r",0, val, ", r13" ", lsl r",14,8,"")\ + TEST_RR( op s " r12, pc" ", r",14,val, ", ror r",14,7,"")\ + TEST_RR( op s " r14, r",0, val, ", pc" ", lsl r",14,8,"")\ + TEST_R( op "eq" s " r0, r",11,VAL1,", #0xf5") \ + TEST_R( op "ne" s " r11, r",0, VAL1,", #0xf5000000") \ + TEST_R( op s " r7, r",8, VAL2,", #0x000af000") \ + TEST( op s " r4, pc" ", #0x00005a00") + +#define DATA_PROCESSING_DNM(op,val) \ + _DATA_PROCESSING_DNM(op,"",val) \ + _DATA_PROCESSING_DNM(op,"s",val) + +#define DATA_PROCESSING_NM(op,val) \ + TEST_RR( op "ne r",1, VAL1,", r",2, val, "") \ + TEST_RR( op "eq r",1, VAL1,", r",2, val, ", lsl #3") \ + TEST_RR( op "cc r",3, VAL1,", r",2, val, ", lsr #4") \ + TEST_RR( op "cs r",3, VAL1,", r",2, val, ", asr #5") \ + TEST_RR( op "pl r",5, VAL1,", r",2, N(val),", asr #6") \ + TEST_RR( op "mi r",5, VAL1,", r",2, val, ", ror #7") \ + TEST_RR( op "vc r",7, VAL1,", r",2, val, ", rrx") \ + TEST_R ( op "vs r",7, VAL1,", pc, lsl #3") \ + TEST_R ( op "vs r",7, VAL1,", sp, lsr #4") \ + TEST_R( op "vs pc, r",7, VAL1,", asr #5") \ + TEST_R( op "vs sp, r",7, VAL1,", ror #6") \ + TEST_RRR( op "ls r",9, VAL1,", r",14,val, ", lsl r",0, 3,"") \ + TEST_RRR( op "hi r",9, VAL1,", r",14,val, ", lsr r",7, 4,"") \ + TEST_RRR( op "lt r",11,VAL1,", r",14,val, ", asr r",7, 5,"") \ + TEST_RRR( op "ge r",11,VAL1,", r",14,N(val),", asr r",7, 6,"") \ + TEST_RR( op "le r13" ", r",14,val, ", ror r",14,7,"") \ + TEST_RR( op "gt r",0, val, ", r13" ", lsl r",14,8,"") \ + TEST_RR( op " pc" ", r",14,val, ", ror r",14,7,"") \ + TEST_RR( op " r",0, val, ", pc" ", lsl r",14,8,"") \ + TEST_R( op "eq r",11,VAL1,", #0xf5") \ + TEST_R( op "ne r",0, VAL1,", #0xf5000000") \ + TEST_R( op " r",8, VAL2,", #0x000af000") + +#define _DATA_PROCESSING_DM(op,s,val) \ + TEST_R( op "eq" s " r0, r",1, val, "") \ + TEST_R( op "ne" s " r1, r",1, val, ", lsl #3") \ + TEST_R( op "cs" s " r2, r",3, val, ", lsr #4") \ + TEST_R( op "cc" s " r3, r",3, val, ", asr #5") \ + TEST_R( op "mi" s " r4, r",5, N(val),", asr #6") \ + TEST_R( op "pl" s " r5, r",5, val, ", ror #7") \ + TEST_R( op "vs" s " r6, r",10,val, ", rrx") \ + TEST( op "vs" s " r7, pc, lsl #3") \ + TEST( op "vs" s " r7, sp, lsr #4") \ + TEST_RR( op "vc" s " r8, r",7, val, ", lsl r",0, 3,"") \ + TEST_RR( op "hi" s " r9, r",9, val, ", lsr r",7, 4,"") \ + TEST_RR( op "ls" s " r10, r",9, val, ", asr r",7, 5,"") \ + TEST_RR( op "ge" s " r11, r",11,N(val),", asr r",7, 6,"") \ + TEST_RR( op "lt" s " r12, r",11,val, ", ror r",14,7,"") \ + TEST_R( op "gt" s " r14, r13" ", lsl r",14,8,"") \ + TEST_R( op "le" s " r14, pc" ", lsl r",14,8,"") \ + TEST( op "eq" s " r0, #0xf5") \ + TEST( op "ne" s " r11, #0xf5000000") \ + TEST( op s " r7, #0x000af000") \ + TEST( op s " r4, #0x00005a00") + +#define DATA_PROCESSING_DM(op,val) \ + _DATA_PROCESSING_DM(op,"",val) \ + _DATA_PROCESSING_DM(op,"s",val) + + DATA_PROCESSING_DNM("and",0xf00f00ff) + DATA_PROCESSING_DNM("eor",0xf00f00ff) + DATA_PROCESSING_DNM("sub",VAL2) + DATA_PROCESSING_DNM("rsb",VAL2) + DATA_PROCESSING_DNM("add",VAL2) + DATA_PROCESSING_DNM("adc",VAL2) + DATA_PROCESSING_DNM("sbc",VAL2) + DATA_PROCESSING_DNM("rsc",VAL2) + DATA_PROCESSING_NM("tst",0xf00f00ff) + DATA_PROCESSING_NM("teq",0xf00f00ff) + DATA_PROCESSING_NM("cmp",VAL2) + DATA_PROCESSING_NM("cmn",VAL2) + DATA_PROCESSING_DNM("orr",0xf00f00ff) + DATA_PROCESSING_DM("mov",VAL2) + DATA_PROCESSING_DNM("bic",0xf00f00ff) + DATA_PROCESSING_DM("mvn",VAL2) + + TEST("mov ip, sp") /* This has special case emulation code */ + + TEST_SUPPORTED("mov pc, #0x1000"); + TEST_SUPPORTED("mov sp, #0x1000"); + TEST_SUPPORTED("cmp pc, #0x1000"); + TEST_SUPPORTED("cmp sp, #0x1000"); + + /* Data-processing with PC as shift*/ + TEST_UNSUPPORTED(".word 0xe15c0f1e @ cmp r12, r14, asl pc") + TEST_UNSUPPORTED(".word 0xe1a0cf1e @ mov r12, r14, asl pc") + TEST_UNSUPPORTED(".word 0xe08caf1e @ add r10, r12, r14, asl pc") + + /* Data-processing with PC as shift*/ + TEST_UNSUPPORTED("movs pc, r1") + TEST_UNSUPPORTED("movs pc, r1, lsl r2") + TEST_UNSUPPORTED("movs pc, #0x10000") + TEST_UNSUPPORTED("adds pc, lr, r1") + TEST_UNSUPPORTED("adds pc, lr, r1, lsl r2") + TEST_UNSUPPORTED("adds pc, lr, #4") + + /* Data-processing with SP as target */ + TEST("add sp, sp, #16") + TEST("sub sp, sp, #8") + TEST("bic sp, sp, #0x20") + TEST("orr sp, sp, #0x20") + TEST_PR( "add sp, r",10,0,", r",11,4,"") + TEST_PRR("add sp, r",10,0,", r",11,4,", asl r",12,1,"") + TEST_P( "mov sp, r",10,0,"") + TEST_PR( "mov sp, r",10,0,", asl r",12,0,"") + + /* Data-processing with PC as target */ + TEST_BF( "add pc, pc, #2f-1b-8") + TEST_BF_R ("add pc, pc, r",14,2f-1f-8,"") + TEST_BF_R ("add pc, r",14,2f-1f-8,", pc") + TEST_BF_R ("mov pc, r",0,2f,"") + TEST_BF_RR("mov pc, r",0,2f,", asl r",1,0,"") + TEST_BB( "sub pc, pc, #1b-2b+8") +#if __LINUX_ARM_ARCH__ >= 6 + TEST_BB( "sub pc, pc, #1b-2b+8-2") /* UNPREDICTABLE before ARMv6 */ +#endif + TEST_BB_R( "sub pc, pc, r",14, 1f-2f+8,"") + TEST_BB_R( "rsb pc, r",14,1f-2f+8,", pc") + TEST_RR( "add pc, pc, r",10,-2,", asl r",11,1,"") +#ifdef CONFIG_THUMB2_KERNEL + TEST_ARM_TO_THUMB_INTERWORK_R("add pc, pc, r",0,3f-1f-8+1,"") + TEST_ARM_TO_THUMB_INTERWORK_R("sub pc, r",0,3f+8+1,", #8") +#endif + TEST_GROUP("Miscellaneous instructions") + + TEST("mrs r0, cpsr") + TEST("mrspl r7, cpsr") + TEST("mrs r14, cpsr") + TEST_UNSUPPORTED(".word 0xe10ff000 @ mrs r15, cpsr") + TEST_UNSUPPORTED("mrs r0, spsr") + TEST_UNSUPPORTED("mrs lr, spsr") + + TEST_UNSUPPORTED("msr cpsr, r0") + TEST_UNSUPPORTED("msr cpsr_f, lr") + TEST_UNSUPPORTED("msr spsr, r0") + + TEST_BF_R("bx r",0,2f,"") + TEST_BB_R("bx r",7,2f,"") + TEST_BF_R("bxeq r",14,2f,"") + + TEST_R("clz r0, r",0, 0x0,"") + TEST_R("clzeq r7, r",14,0x1,"") + TEST_R("clz lr, r",7, 0xffffffff,"") + TEST( "clz r4, sp") + TEST_UNSUPPORTED(".word 0x016fff10 @ clz pc, r0") + TEST_UNSUPPORTED(".word 0x016f0f1f @ clz r0, pc") + +#if __LINUX_ARM_ARCH__ >= 6 + TEST_UNSUPPORTED("bxj r0") +#endif + + TEST_BF_R("blx r",0,2f,"") + TEST_BB_R("blx r",7,2f,"") + TEST_BF_R("blxeq r",14,2f,"") + TEST_UNSUPPORTED(".word 0x0120003f @ blx pc") + + TEST_RR( "qadd r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "qaddvs lr, r",9, VAL2,", r",8, VAL1,"") + TEST_R( "qadd lr, r",9, VAL2,", r13") + TEST_RR( "qsub r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "qsubvs lr, r",9, VAL2,", r",8, VAL1,"") + TEST_R( "qsub lr, r",9, VAL2,", r13") + TEST_RR( "qdadd r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "qdaddvs lr, r",9, VAL2,", r",8, VAL1,"") + TEST_R( "qdadd lr, r",9, VAL2,", r13") + TEST_RR( "qdsub r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "qdsubvs lr, r",9, VAL2,", r",8, VAL1,"") + TEST_R( "qdsub lr, r",9, VAL2,", r13") + TEST_UNSUPPORTED(".word 0xe101f050 @ qadd pc, r0, r1") + TEST_UNSUPPORTED(".word 0xe121f050 @ qsub pc, r0, r1") + TEST_UNSUPPORTED(".word 0xe141f050 @ qdadd pc, r0, r1") + TEST_UNSUPPORTED(".word 0xe161f050 @ qdsub pc, r0, r1") + TEST_UNSUPPORTED(".word 0xe16f2050 @ qdsub r2, r0, pc") + TEST_UNSUPPORTED(".word 0xe161205f @ qdsub r2, pc, r1") + + TEST_UNSUPPORTED("bkpt 0xffff") + TEST_UNSUPPORTED("bkpt 0x0000") + + TEST_UNSUPPORTED(".word 0xe1600070 @ smc #0") + + TEST_GROUP("Halfword multiply and multiply-accumulate") + + TEST_RRR( "smlabb r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlabbge r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RR( "smlabb lr, r",1, VAL2,", r",2, VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe10f3281 @ smlabb pc, r1, r2, r3") + TEST_RRR( "smlatb r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlatbge r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RR( "smlatb lr, r",1, VAL2,", r",2, VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe10f32a1 @ smlatb pc, r1, r2, r3") + TEST_RRR( "smlabt r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlabtge r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RR( "smlabt lr, r",1, VAL2,", r",2, VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe10f32c1 @ smlabt pc, r1, r2, r3") + TEST_RRR( "smlatt r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlattge r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RR( "smlatt lr, r",1, VAL2,", r",2, VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe10f32e1 @ smlatt pc, r1, r2, r3") + + TEST_RRR( "smlawb r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlawbge r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RR( "smlawb lr, r",1, VAL2,", r",2, VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe12f3281 @ smlawb pc, r1, r2, r3") + TEST_RRR( "smlawt r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlawtge r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RR( "smlawt lr, r",1, VAL2,", r",2, VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe12f32c1 @ smlawt pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe12032cf @ smlawt r0, pc, r2, r3") + TEST_UNSUPPORTED(".word 0xe1203fc1 @ smlawt r0, r1, pc, r3") + TEST_UNSUPPORTED(".word 0xe120f2c1 @ smlawt r0, r1, r2, pc") + + TEST_RR( "smulwb r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smulwbge r7, r",8, VAL3,", r",9, VAL1,"") + TEST_R( "smulwb lr, r",1, VAL2,", r13") + TEST_UNSUPPORTED(".word 0xe12f02a1 @ smulwb pc, r1, r2") + TEST_RR( "smulwt r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smulwtge r7, r",8, VAL3,", r",9, VAL1,"") + TEST_R( "smulwt lr, r",1, VAL2,", r13") + TEST_UNSUPPORTED(".word 0xe12f02e1 @ smulwt pc, r1, r2") + + TEST_RRRR( "smlalbb r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "smlalbble r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRR( "smlalbb r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13") + TEST_UNSUPPORTED(".word 0xe14f1382 @ smlalbb pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe141f382 @ smlalbb r1, pc, r2, r3") + TEST_RRRR( "smlaltb r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "smlaltble r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRR( "smlaltb r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13") + TEST_UNSUPPORTED(".word 0xe14f13a2 @ smlaltb pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe141f3a2 @ smlaltb r1, pc, r2, r3") + TEST_RRRR( "smlalbt r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "smlalbtle r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRR( "smlalbt r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13") + TEST_UNSUPPORTED(".word 0xe14f13c2 @ smlalbt pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe141f3c2 @ smlalbt r1, pc, r2, r3") + TEST_RRRR( "smlaltt r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "smlalttle r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRR( "smlaltt r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13") + TEST_UNSUPPORTED(".word 0xe14f13e2 @ smlalbb pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe140f3e2 @ smlalbb r0, pc, r2, r3") + TEST_UNSUPPORTED(".word 0xe14013ef @ smlalbb r0, r1, pc, r3") + TEST_UNSUPPORTED(".word 0xe1401fe2 @ smlalbb r0, r1, r2, pc") + + TEST_RR( "smulbb r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smulbbge r7, r",8, VAL3,", r",9, VAL1,"") + TEST_R( "smulbb lr, r",1, VAL2,", r13") + TEST_UNSUPPORTED(".word 0xe16f0281 @ smulbb pc, r1, r2") + TEST_RR( "smultb r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smultbge r7, r",8, VAL3,", r",9, VAL1,"") + TEST_R( "smultb lr, r",1, VAL2,", r13") + TEST_UNSUPPORTED(".word 0xe16f02a1 @ smultb pc, r1, r2") + TEST_RR( "smulbt r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smulbtge r7, r",8, VAL3,", r",9, VAL1,"") + TEST_R( "smulbt lr, r",1, VAL2,", r13") + TEST_UNSUPPORTED(".word 0xe16f02c1 @ smultb pc, r1, r2") + TEST_RR( "smultt r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smulttge r7, r",8, VAL3,", r",9, VAL1,"") + TEST_R( "smultt lr, r",1, VAL2,", r13") + TEST_UNSUPPORTED(".word 0xe16f02e1 @ smultt pc, r1, r2") + TEST_UNSUPPORTED(".word 0xe16002ef @ smultt r0, pc, r2") + TEST_UNSUPPORTED(".word 0xe1600fe1 @ smultt r0, r1, pc") + + TEST_GROUP("Multiply and multiply-accumulate") + + TEST_RR( "mul r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "mulls r7, r",8, VAL2,", r",9, VAL2,"") + TEST_R( "mul lr, r",4, VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe00f0291 @ mul pc, r1, r2") + TEST_UNSUPPORTED(".word 0xe000029f @ mul r0, pc, r2") + TEST_UNSUPPORTED(".word 0xe0000f91 @ mul r0, r1, pc") + TEST_RR( "muls r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "mullss r7, r",8, VAL2,", r",9, VAL2,"") + TEST_R( "muls lr, r",4, VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe01f0291 @ muls pc, r1, r2") + + TEST_RRR( "mla r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "mlahi r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RR( "mla lr, r",1, VAL2,", r",2, VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe02f3291 @ mla pc, r1, r2, r3") + TEST_RRR( "mlas r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "mlahis r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RR( "mlas lr, r",1, VAL2,", r",2, VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe03f3291 @ mlas pc, r1, r2, r3") + +#if __LINUX_ARM_ARCH__ >= 6 + TEST_RR( "umaal r0, r1, r",2, VAL1,", r",3, VAL2,"") + TEST_RR( "umaalls r7, r8, r",9, VAL2,", r",10, VAL1,"") + TEST_R( "umaal lr, r12, r",11,VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe041f392 @ umaal pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe04f0392 @ umaal r0, pc, r2, r3") + TEST_UNSUPPORTED(".word 0xe0500090 @ undef") + TEST_UNSUPPORTED(".word 0xe05fff9f @ undef") + + TEST_RRR( "mls r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "mlshi r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RR( "mls lr, r",1, VAL2,", r",2, VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe06f3291 @ mls pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe060329f @ mls r0, pc, r2, r3") + TEST_UNSUPPORTED(".word 0xe0603f91 @ mls r0, r1, pc, r3") + TEST_UNSUPPORTED(".word 0xe060f291 @ mls r0, r1, r2, pc") +#endif + + TEST_UNSUPPORTED(".word 0xe0700090 @ undef") + TEST_UNSUPPORTED(".word 0xe07fff9f @ undef") + + TEST_RR( "umull r0, r1, r",2, VAL1,", r",3, VAL2,"") + TEST_RR( "umullls r7, r8, r",9, VAL2,", r",10, VAL1,"") + TEST_R( "umull lr, r12, r",11,VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe081f392 @ umull pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe08f1392 @ umull r1, pc, r2, r3") + TEST_RR( "umulls r0, r1, r",2, VAL1,", r",3, VAL2,"") + TEST_RR( "umulllss r7, r8, r",9, VAL2,", r",10, VAL1,"") + TEST_R( "umulls lr, r12, r",11,VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe091f392 @ umulls pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe09f1392 @ umulls r1, pc, r2, r3") + + TEST_RRRR( "umlal r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "umlalle r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRR( "umlal r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13") + TEST_UNSUPPORTED(".word 0xe0af1392 @ umlal pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe0a1f392 @ umlal r1, pc, r2, r3") + TEST_RRRR( "umlals r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "umlalles r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRR( "umlals r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13") + TEST_UNSUPPORTED(".word 0xe0bf1392 @ umlals pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe0b1f392 @ umlals r1, pc, r2, r3") + + TEST_RR( "smull r0, r1, r",2, VAL1,", r",3, VAL2,"") + TEST_RR( "smullls r7, r8, r",9, VAL2,", r",10, VAL1,"") + TEST_R( "smull lr, r12, r",11,VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe0c1f392 @ smull pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe0cf1392 @ smull r1, pc, r2, r3") + TEST_RR( "smulls r0, r1, r",2, VAL1,", r",3, VAL2,"") + TEST_RR( "smulllss r7, r8, r",9, VAL2,", r",10, VAL1,"") + TEST_R( "smulls lr, r12, r",11,VAL3,", r13") + TEST_UNSUPPORTED(".word 0xe0d1f392 @ smulls pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe0df1392 @ smulls r1, pc, r2, r3") + + TEST_RRRR( "smlal r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "smlalle r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRR( "smlal r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13") + TEST_UNSUPPORTED(".word 0xe0ef1392 @ smlal pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe0e1f392 @ smlal r1, pc, r2, r3") + TEST_RRRR( "smlals r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "smlalles r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRR( "smlals r",14,VAL3,", r",7, VAL4,", r",5, VAL1,", r13") + TEST_UNSUPPORTED(".word 0xe0ff1392 @ smlals pc, r1, r2, r3") + TEST_UNSUPPORTED(".word 0xe0f0f392 @ smlals r0, pc, r2, r3") + TEST_UNSUPPORTED(".word 0xe0f0139f @ smlals r0, r1, pc, r3") + TEST_UNSUPPORTED(".word 0xe0f01f92 @ smlals r0, r1, r2, pc") + + TEST_GROUP("Synchronization primitives") + + /* + * Use hard coded constants for SWP instructions to avoid warnings + * about deprecated instructions. + */ + TEST_RP( ".word 0xe108e097 @ swp lr, r",7,VAL2,", [r",8,0,"]") + TEST_R( ".word 0x610d0091 @ swpvs r0, r",1,VAL1,", [sp]") + TEST_RP( ".word 0xe10cd09e @ swp sp, r",14,VAL2,", [r",12,13*4,"]") + TEST_UNSUPPORTED(".word 0xe102f091 @ swp pc, r1, [r2]") + TEST_UNSUPPORTED(".word 0xe102009f @ swp r0, pc, [r2]") + TEST_UNSUPPORTED(".word 0xe10f0091 @ swp r0, r1, [pc]") + TEST_RP( ".word 0xe148e097 @ swpb lr, r",7,VAL2,", [r",8,0,"]") + TEST_R( ".word 0x614d0091 @ swpvsb r0, r",1,VAL1,", [sp]") + TEST_UNSUPPORTED(".word 0xe142f091 @ swpb pc, r1, [r2]") + + TEST_UNSUPPORTED(".word 0xe1100090") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe1200090") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe1300090") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe1500090") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe1600090") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe1700090") /* Unallocated space */ +#if __LINUX_ARM_ARCH__ >= 6 + TEST_UNSUPPORTED("ldrex r2, [sp]") + TEST_UNSUPPORTED("strexd r0, r2, r3, [sp]") + TEST_UNSUPPORTED("ldrexd r2, r3, [sp]") + TEST_UNSUPPORTED("strexb r0, r2, [sp]") + TEST_UNSUPPORTED("ldrexb r2, [sp]") + TEST_UNSUPPORTED("strexh r0, r2, [sp]") + TEST_UNSUPPORTED("ldrexh r2, [sp]") +#endif + TEST_GROUP("Extra load/store instructions") + + TEST_RPR( "strh r",0, VAL1,", [r",1, 48,", -r",2, 24,"]") + TEST_RPR( "streqh r",14,VAL2,", [r",13,0, ", r",12, 48,"]") + TEST_RPR( "strh r",1, VAL1,", [r",2, 24,", r",3, 48,"]!") + TEST_RPR( "strneh r",12,VAL2,", [r",11,48,", -r",10,24,"]!") + TEST_RPR( "strh r",2, VAL1,", [r",3, 24,"], r",4, 48,"") + TEST_RPR( "strh r",10,VAL2,", [r",9, 48,"], -r",11,24,"") + TEST_UNSUPPORTED(".word 0xe1afc0ba @ strh r12, [pc, r10]!") + TEST_UNSUPPORTED(".word 0xe089f0bb @ strh pc, [r9], r11") + TEST_UNSUPPORTED(".word 0xe089a0bf @ strh r10, [r9], pc") + + TEST_PR( "ldrh r0, [r",0, 48,", -r",2, 24,"]") + TEST_PR( "ldrcsh r14, [r",13,0, ", r",12, 48,"]") + TEST_PR( "ldrh r1, [r",2, 24,", r",3, 48,"]!") + TEST_PR( "ldrcch r12, [r",11,48,", -r",10,24,"]!") + TEST_PR( "ldrh r2, [r",3, 24,"], r",4, 48,"") + TEST_PR( "ldrh r10, [r",9, 48,"], -r",11,24,"") + TEST_UNSUPPORTED(".word 0xe1bfc0ba @ ldrh r12, [pc, r10]!") + TEST_UNSUPPORTED(".word 0xe099f0bb @ ldrh pc, [r9], r11") + TEST_UNSUPPORTED(".word 0xe099a0bf @ ldrh r10, [r9], pc") + + TEST_RP( "strh r",0, VAL1,", [r",1, 24,", #-2]") + TEST_RP( "strmih r",14,VAL2,", [r",13,0, ", #2]") + TEST_RP( "strh r",1, VAL1,", [r",2, 24,", #4]!") + TEST_RP( "strplh r",12,VAL2,", [r",11,24,", #-4]!") + TEST_RP( "strh r",2, VAL1,", [r",3, 24,"], #48") + TEST_RP( "strh r",10,VAL2,", [r",9, 64,"], #-48") + TEST_UNSUPPORTED(".word 0xe1efc3b0 @ strh r12, [pc, #48]!") + TEST_UNSUPPORTED(".word 0xe0c9f3b0 @ strh pc, [r9], #48") + + TEST_P( "ldrh r0, [r",0, 24,", #-2]") + TEST_P( "ldrvsh r14, [r",13,0, ", #2]") + TEST_P( "ldrh r1, [r",2, 24,", #4]!") + TEST_P( "ldrvch r12, [r",11,24,", #-4]!") + TEST_P( "ldrh r2, [r",3, 24,"], #48") + TEST_P( "ldrh r10, [r",9, 64,"], #-48") + TEST( "ldrh r0, [pc, #0]") + TEST_UNSUPPORTED(".word 0xe1ffc3b0 @ ldrh r12, [pc, #48]!") + TEST_UNSUPPORTED(".word 0xe0d9f3b0 @ ldrh pc, [r9], #48") + + TEST_PR( "ldrsb r0, [r",0, 48,", -r",2, 24,"]") + TEST_PR( "ldrhisb r14, [r",13,0,", r",12, 48,"]") + TEST_PR( "ldrsb r1, [r",2, 24,", r",3, 48,"]!") + TEST_PR( "ldrlssb r12, [r",11,48,", -r",10,24,"]!") + TEST_PR( "ldrsb r2, [r",3, 24,"], r",4, 48,"") + TEST_PR( "ldrsb r10, [r",9, 48,"], -r",11,24,"") + TEST_UNSUPPORTED(".word 0xe1bfc0da @ ldrsb r12, [pc, r10]!") + TEST_UNSUPPORTED(".word 0xe099f0db @ ldrsb pc, [r9], r11") + + TEST_P( "ldrsb r0, [r",0, 24,", #-1]") + TEST_P( "ldrgesb r14, [r",13,0, ", #1]") + TEST_P( "ldrsb r1, [r",2, 24,", #4]!") + TEST_P( "ldrltsb r12, [r",11,24,", #-4]!") + TEST_P( "ldrsb r2, [r",3, 24,"], #48") + TEST_P( "ldrsb r10, [r",9, 64,"], #-48") + TEST( "ldrsb r0, [pc, #0]") + TEST_UNSUPPORTED(".word 0xe1ffc3d0 @ ldrsb r12, [pc, #48]!") + TEST_UNSUPPORTED(".word 0xe0d9f3d0 @ ldrsb pc, [r9], #48") + + TEST_PR( "ldrsh r0, [r",0, 48,", -r",2, 24,"]") + TEST_PR( "ldrgtsh r14, [r",13,0, ", r",12, 48,"]") + TEST_PR( "ldrsh r1, [r",2, 24,", r",3, 48,"]!") + TEST_PR( "ldrlesh r12, [r",11,48,", -r",10,24,"]!") + TEST_PR( "ldrsh r2, [r",3, 24,"], r",4, 48,"") + TEST_PR( "ldrsh r10, [r",9, 48,"], -r",11,24,"") + TEST_UNSUPPORTED(".word 0xe1bfc0fa @ ldrsh r12, [pc, r10]!") + TEST_UNSUPPORTED(".word 0xe099f0fb @ ldrsh pc, [r9], r11") + + TEST_P( "ldrsh r0, [r",0, 24,", #-1]") + TEST_P( "ldreqsh r14, [r",13,0 ,", #1]") + TEST_P( "ldrsh r1, [r",2, 24,", #4]!") + TEST_P( "ldrnesh r12, [r",11,24,", #-4]!") + TEST_P( "ldrsh r2, [r",3, 24,"], #48") + TEST_P( "ldrsh r10, [r",9, 64,"], #-48") + TEST( "ldrsh r0, [pc, #0]") + TEST_UNSUPPORTED(".word 0xe1ffc3f0 @ ldrsh r12, [pc, #48]!") + TEST_UNSUPPORTED(".word 0xe0d9f3f0 @ ldrsh pc, [r9], #48") + +#if __LINUX_ARM_ARCH__ >= 7 + TEST_UNSUPPORTED("strht r1, [r2], r3") + TEST_UNSUPPORTED("ldrht r1, [r2], r3") + TEST_UNSUPPORTED("strht r1, [r2], #48") + TEST_UNSUPPORTED("ldrht r1, [r2], #48") + TEST_UNSUPPORTED("ldrsbt r1, [r2], r3") + TEST_UNSUPPORTED("ldrsbt r1, [r2], #48") + TEST_UNSUPPORTED("ldrsht r1, [r2], r3") + TEST_UNSUPPORTED("ldrsht r1, [r2], #48") +#endif + + TEST_RPR( "strd r",0, VAL1,", [r",1, 48,", -r",2,24,"]") + TEST_RPR( "strccd r",8, VAL2,", [r",13,0, ", r",12,48,"]") + TEST_RPR( "strd r",4, VAL1,", [r",2, 24,", r",3, 48,"]!") + TEST_RPR( "strcsd r",12,VAL2,", [r",11,48,", -r",10,24,"]!") + TEST_RPR( "strd r",2, VAL1,", [r",3, 24,"], r",4,48,"") + TEST_RPR( "strd r",10,VAL2,", [r",9, 48,"], -r",7,24,"") + TEST_UNSUPPORTED(".word 0xe1afc0fa @ strd r12, [pc, r10]!") + + TEST_PR( "ldrd r0, [r",0, 48,", -r",2,24,"]") + TEST_PR( "ldrmid r8, [r",13,0, ", r",12,48,"]") + TEST_PR( "ldrd r4, [r",2, 24,", r",3, 48,"]!") + TEST_PR( "ldrpld r6, [r",11,48,", -r",10,24,"]!") + TEST_PR( "ldrd r2, [r",5, 24,"], r",4,48,"") + TEST_PR( "ldrd r10, [r",9,48,"], -r",7,24,"") + TEST_UNSUPPORTED(".word 0xe1afc0da @ ldrd r12, [pc, r10]!") + TEST_UNSUPPORTED(".word 0xe089f0db @ ldrd pc, [r9], r11") + TEST_UNSUPPORTED(".word 0xe089e0db @ ldrd lr, [r9], r11") + TEST_UNSUPPORTED(".word 0xe089c0df @ ldrd r12, [r9], pc") + + TEST_RP( "strd r",0, VAL1,", [r",1, 24,", #-8]") + TEST_RP( "strvsd r",8, VAL2,", [r",13,0, ", #8]") + TEST_RP( "strd r",4, VAL1,", [r",2, 24,", #16]!") + TEST_RP( "strvcd r",12,VAL2,", [r",11,24,", #-16]!") + TEST_RP( "strd r",2, VAL1,", [r",4, 24,"], #48") + TEST_RP( "strd r",10,VAL2,", [r",9, 64,"], #-48") + TEST_UNSUPPORTED(".word 0xe1efc3f0 @ strd r12, [pc, #48]!") + + TEST_P( "ldrd r0, [r",0, 24,", #-8]") + TEST_P( "ldrhid r8, [r",13,0, ", #8]") + TEST_P( "ldrd r4, [r",2, 24,", #16]!") + TEST_P( "ldrlsd r6, [r",11,24,", #-16]!") + TEST_P( "ldrd r2, [r",5, 24,"], #48") + TEST_P( "ldrd r10, [r",9,6,"], #-48") + TEST_UNSUPPORTED(".word 0xe1efc3d0 @ ldrd r12, [pc, #48]!") + TEST_UNSUPPORTED(".word 0xe0c9f3d0 @ ldrd pc, [r9], #48") + TEST_UNSUPPORTED(".word 0xe0c9e3d0 @ ldrd lr, [r9], #48") + + TEST_GROUP("Miscellaneous") + +#if __LINUX_ARM_ARCH__ >= 7 + TEST("movw r0, #0") + TEST("movw r0, #0xffff") + TEST("movw lr, #0xffff") + TEST_UNSUPPORTED(".word 0xe300f000 @ movw pc, #0") + TEST_R("movt r",0, VAL1,", #0") + TEST_R("movt r",0, VAL2,", #0xffff") + TEST_R("movt r",14,VAL1,", #0xffff") + TEST_UNSUPPORTED(".word 0xe340f000 @ movt pc, #0") +#endif + + TEST_UNSUPPORTED("msr cpsr, 0x13") + TEST_UNSUPPORTED("msr cpsr_f, 0xf0000000") + TEST_UNSUPPORTED("msr spsr, 0x13") + +#if __LINUX_ARM_ARCH__ >= 7 + TEST_SUPPORTED("yield") + TEST("sev") + TEST("nop") + TEST("wfi") + TEST_SUPPORTED("wfe") + TEST_UNSUPPORTED("dbg #0") +#endif + + TEST_GROUP("Load/store word and unsigned byte") + +#define LOAD_STORE(byte) \ + TEST_RP( "str"byte" r",0, VAL1,", [r",1, 24,", #-2]") \ + TEST_RP( "str"byte" r",14,VAL2,", [r",13,0, ", #2]") \ + TEST_RP( "str"byte" r",1, VAL1,", [r",2, 24,", #4]!") \ + TEST_RP( "str"byte" r",12,VAL2,", [r",11,24,", #-4]!") \ + TEST_RP( "str"byte" r",2, VAL1,", [r",3, 24,"], #48") \ + TEST_RP( "str"byte" r",10,VAL2,", [r",9, 64,"], #-48") \ + TEST_RPR("str"byte" r",0, VAL1,", [r",1, 48,", -r",2, 24,"]") \ + TEST_RPR("str"byte" r",14,VAL2,", [r",13,0, ", r",12, 48,"]") \ + TEST_RPR("str"byte" r",1, VAL1,", [r",2, 24,", r",3, 48,"]!") \ + TEST_RPR("str"byte" r",12,VAL2,", [r",11,48,", -r",10,24,"]!") \ + TEST_RPR("str"byte" r",2, VAL1,", [r",3, 24,"], r",4, 48,"") \ + TEST_RPR("str"byte" r",10,VAL2,", [r",9, 48,"], -r",11,24,"") \ + TEST_RPR("str"byte" r",0, VAL1,", [r",1, 24,", r",2, 32,", asl #1]")\ + TEST_RPR("str"byte" r",14,VAL2,", [r",13,0, ", r",12, 32,", lsr #2]")\ + TEST_RPR("str"byte" r",1, VAL1,", [r",2, 24,", r",3, 32,", asr #3]!")\ + TEST_RPR("str"byte" r",12,VAL2,", [r",11,24,", r",10, 4,", ror #31]!")\ + TEST_P( "ldr"byte" r0, [r",0, 24,", #-2]") \ + TEST_P( "ldr"byte" r14, [r",13,0, ", #2]") \ + TEST_P( "ldr"byte" r1, [r",2, 24,", #4]!") \ + TEST_P( "ldr"byte" r12, [r",11,24,", #-4]!") \ + TEST_P( "ldr"byte" r2, [r",3, 24,"], #48") \ + TEST_P( "ldr"byte" r10, [r",9, 64,"], #-48") \ + TEST_PR( "ldr"byte" r0, [r",0, 48,", -r",2, 24,"]") \ + TEST_PR( "ldr"byte" r14, [r",13,0, ", r",12, 48,"]") \ + TEST_PR( "ldr"byte" r1, [r",2, 24,", r",3, 48,"]!") \ + TEST_PR( "ldr"byte" r12, [r",11,48,", -r",10,24,"]!") \ + TEST_PR( "ldr"byte" r2, [r",3, 24,"], r",4, 48,"") \ + TEST_PR( "ldr"byte" r10, [r",9, 48,"], -r",11,24,"") \ + TEST_PR( "ldr"byte" r0, [r",0, 24,", r",2, 32,", asl #1]") \ + TEST_PR( "ldr"byte" r14, [r",13,0, ", r",12, 32,", lsr #2]") \ + TEST_PR( "ldr"byte" r1, [r",2, 24,", r",3, 32,", asr #3]!") \ + TEST_PR( "ldr"byte" r12, [r",11,24,", r",10, 4,", ror #31]!") \ + TEST( "ldr"byte" r0, [pc, #0]") \ + TEST_R( "ldr"byte" r12, [pc, r",14,0,"]") + + LOAD_STORE("") + TEST_P( "str pc, [r",0,0,", #15*4]") + TEST_R( "str pc, [sp, r",2,15*4,"]") + TEST_BF( "ldr pc, [sp, #15*4]") + TEST_BF_R("ldr pc, [sp, r",2,15*4,"]") + + TEST_P( "str sp, [r",0,0,", #13*4]") + TEST_R( "str sp, [sp, r",2,13*4,"]") + TEST_BF( "ldr sp, [sp, #13*4]") + TEST_BF_R("ldr sp, [sp, r",2,13*4,"]") + +#ifdef CONFIG_THUMB2_KERNEL + TEST_ARM_TO_THUMB_INTERWORK_P("ldr pc, [r",0,0,", #15*4]") +#endif + TEST_UNSUPPORTED(".word 0xe5af6008 @ str r6, [pc, #8]!") + TEST_UNSUPPORTED(".word 0xe7af6008 @ str r6, [pc, r8]!") + TEST_UNSUPPORTED(".word 0xe5bf6008 @ ldr r6, [pc, #8]!") + TEST_UNSUPPORTED(".word 0xe7bf6008 @ ldr r6, [pc, r8]!") + TEST_UNSUPPORTED(".word 0xe788600f @ str r6, [r8, pc]") + TEST_UNSUPPORTED(".word 0xe798600f @ ldr r6, [r8, pc]") + + LOAD_STORE("b") + TEST_UNSUPPORTED(".word 0xe5f7f008 @ ldrb pc, [r7, #8]!") + TEST_UNSUPPORTED(".word 0xe7f7f008 @ ldrb pc, [r7, r8]!") + TEST_UNSUPPORTED(".word 0xe5ef6008 @ strb r6, [pc, #8]!") + TEST_UNSUPPORTED(".word 0xe7ef6008 @ strb r6, [pc, r3]!") + TEST_UNSUPPORTED(".word 0xe5ff6008 @ ldrb r6, [pc, #8]!") + TEST_UNSUPPORTED(".word 0xe7ff6008 @ ldrb r6, [pc, r3]!") + + TEST_UNSUPPORTED("ldrt r0, [r1], #4") + TEST_UNSUPPORTED("ldrt r1, [r2], r3") + TEST_UNSUPPORTED("strt r2, [r3], #4") + TEST_UNSUPPORTED("strt r3, [r4], r5") + TEST_UNSUPPORTED("ldrbt r4, [r5], #4") + TEST_UNSUPPORTED("ldrbt r5, [r6], r7") + TEST_UNSUPPORTED("strbt r6, [r7], #4") + TEST_UNSUPPORTED("strbt r7, [r8], r9") + +#if __LINUX_ARM_ARCH__ >= 7 + TEST_GROUP("Parallel addition and subtraction, signed") + + TEST_UNSUPPORTED(".word 0xe6000010") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe60fffff") /* Unallocated space */ + + TEST_RR( "sadd16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "sadd16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe61cff1a @ sadd16 pc, r12, r10") + TEST_RR( "sasx r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "sasx r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe61cff3a @ sasx pc, r12, r10") + TEST_RR( "ssax r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "ssax r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe61cff5a @ ssax pc, r12, r10") + TEST_RR( "ssub16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "ssub16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe61cff7a @ ssub16 pc, r12, r10") + TEST_RR( "sadd8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "sadd8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe61cff9a @ sadd8 pc, r12, r10") + TEST_UNSUPPORTED(".word 0xe61000b0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe61fffbf") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe61000d0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe61fffdf") /* Unallocated space */ + TEST_RR( "ssub8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "ssub8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe61cfffa @ ssub8 pc, r12, r10") + + TEST_RR( "qadd16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "qadd16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe62cff1a @ qadd16 pc, r12, r10") + TEST_RR( "qasx r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "qasx r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe62cff3a @ qasx pc, r12, r10") + TEST_RR( "qsax r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "qsax r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe62cff5a @ qsax pc, r12, r10") + TEST_RR( "qsub16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "qsub16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe62cff7a @ qsub16 pc, r12, r10") + TEST_RR( "qadd8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "qadd8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe62cff9a @ qadd8 pc, r12, r10") + TEST_UNSUPPORTED(".word 0xe62000b0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe62fffbf") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe62000d0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe62fffdf") /* Unallocated space */ + TEST_RR( "qsub8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "qsub8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe62cfffa @ qsub8 pc, r12, r10") + + TEST_RR( "shadd16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "shadd16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe63cff1a @ shadd16 pc, r12, r10") + TEST_RR( "shasx r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "shasx r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe63cff3a @ shasx pc, r12, r10") + TEST_RR( "shsax r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "shsax r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe63cff5a @ shsax pc, r12, r10") + TEST_RR( "shsub16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "shsub16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe63cff7a @ shsub16 pc, r12, r10") + TEST_RR( "shadd8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "shadd8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe63cff9a @ shadd8 pc, r12, r10") + TEST_UNSUPPORTED(".word 0xe63000b0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe63fffbf") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe63000d0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe63fffdf") /* Unallocated space */ + TEST_RR( "shsub8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "shsub8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe63cfffa @ shsub8 pc, r12, r10") + + TEST_GROUP("Parallel addition and subtraction, unsigned") + + TEST_UNSUPPORTED(".word 0xe6400010") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe64fffff") /* Unallocated space */ + + TEST_RR( "uadd16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uadd16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe65cff1a @ uadd16 pc, r12, r10") + TEST_RR( "uasx r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uasx r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe65cff3a @ uasx pc, r12, r10") + TEST_RR( "usax r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "usax r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe65cff5a @ usax pc, r12, r10") + TEST_RR( "usub16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "usub16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe65cff7a @ usub16 pc, r12, r10") + TEST_RR( "uadd8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uadd8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe65cff9a @ uadd8 pc, r12, r10") + TEST_UNSUPPORTED(".word 0xe65000b0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe65fffbf") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe65000d0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe65fffdf") /* Unallocated space */ + TEST_RR( "usub8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "usub8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe65cfffa @ usub8 pc, r12, r10") + + TEST_RR( "uqadd16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uqadd16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe66cff1a @ uqadd16 pc, r12, r10") + TEST_RR( "uqasx r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uqasx r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe66cff3a @ uqasx pc, r12, r10") + TEST_RR( "uqsax r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uqsax r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe66cff5a @ uqsax pc, r12, r10") + TEST_RR( "uqsub16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uqsub16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe66cff7a @ uqsub16 pc, r12, r10") + TEST_RR( "uqadd8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uqadd8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe66cff9a @ uqadd8 pc, r12, r10") + TEST_UNSUPPORTED(".word 0xe66000b0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe66fffbf") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe66000d0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe66fffdf") /* Unallocated space */ + TEST_RR( "uqsub8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uqsub8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe66cfffa @ uqsub8 pc, r12, r10") + + TEST_RR( "uhadd16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uhadd16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe67cff1a @ uhadd16 pc, r12, r10") + TEST_RR( "uhasx r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uhasx r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe67cff3a @ uhasx pc, r12, r10") + TEST_RR( "uhsax r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uhsax r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe67cff5a @ uhsax pc, r12, r10") + TEST_RR( "uhsub16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uhsub16 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe67cff7a @ uhsub16 pc, r12, r10") + TEST_RR( "uhadd8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uhadd8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe67cff9a @ uhadd8 pc, r12, r10") + TEST_UNSUPPORTED(".word 0xe67000b0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe67fffbf") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe67000d0") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe67fffdf") /* Unallocated space */ + TEST_RR( "uhsub8 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uhsub8 r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe67cfffa @ uhsub8 pc, r12, r10") + TEST_UNSUPPORTED(".word 0xe67feffa @ uhsub8 r14, pc, r10") + TEST_UNSUPPORTED(".word 0xe67cefff @ uhsub8 r14, r12, pc") +#endif /* __LINUX_ARM_ARCH__ >= 7 */ + +#if __LINUX_ARM_ARCH__ >= 6 + TEST_GROUP("Packing, unpacking, saturation, and reversal") + + TEST_RR( "pkhbt r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "pkhbt r14,r",12, HH1,", r",10,HH2,", lsl #2") + TEST_UNSUPPORTED(".word 0xe68cf11a @ pkhbt pc, r12, r10, lsl #2") + TEST_RR( "pkhtb r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "pkhtb r14,r",12, HH1,", r",10,HH2,", asr #2") + TEST_UNSUPPORTED(".word 0xe68cf15a @ pkhtb pc, r12, r10, asr #2") + TEST_UNSUPPORTED(".word 0xe68fe15a @ pkhtb r14, pc, r10, asr #2") + TEST_UNSUPPORTED(".word 0xe68ce15f @ pkhtb r14, r12, pc, asr #2") + TEST_UNSUPPORTED(".word 0xe6900010") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe69fffdf") /* Unallocated space */ + + TEST_R( "ssat r0, #24, r",0, VAL1,"") + TEST_R( "ssat r14, #24, r",12, VAL2,"") + TEST_R( "ssat r0, #24, r",0, VAL1,", lsl #8") + TEST_R( "ssat r14, #24, r",12, VAL2,", asr #8") + TEST_UNSUPPORTED(".word 0xe6b7f01c @ ssat pc, #24, r12") + + TEST_R( "usat r0, #24, r",0, VAL1,"") + TEST_R( "usat r14, #24, r",12, VAL2,"") + TEST_R( "usat r0, #24, r",0, VAL1,", lsl #8") + TEST_R( "usat r14, #24, r",12, VAL2,", asr #8") + TEST_UNSUPPORTED(".word 0xe6f7f01c @ usat pc, #24, r12") + + TEST_RR( "sxtab16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "sxtab16 r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "sxtb16 r8, r",7, HH1,"") + TEST_UNSUPPORTED(".word 0xe68cf47a @ sxtab16 pc,r12, r10, ror #8") + + TEST_RR( "sel r0, r",0, VAL1,", r",1, VAL2,"") + TEST_RR( "sel r14, r",12,VAL1,", r",10, VAL2,"") + TEST_UNSUPPORTED(".word 0xe68cffba @ sel pc, r12, r10") + TEST_UNSUPPORTED(".word 0xe68fefba @ sel r14, pc, r10") + TEST_UNSUPPORTED(".word 0xe68cefbf @ sel r14, r12, pc") + + TEST_R( "ssat16 r0, #12, r",0, HH1,"") + TEST_R( "ssat16 r14, #12, r",12, HH2,"") + TEST_UNSUPPORTED(".word 0xe6abff3c @ ssat16 pc, #12, r12") + + TEST_RR( "sxtab r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "sxtab r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "sxtb r8, r",7, HH1,"") + TEST_UNSUPPORTED(".word 0xe6acf47a @ sxtab pc,r12, r10, ror #8") + + TEST_R( "rev r0, r",0, VAL1,"") + TEST_R( "rev r14, r",12, VAL2,"") + TEST_UNSUPPORTED(".word 0xe6bfff3c @ rev pc, r12") + + TEST_RR( "sxtah r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "sxtah r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "sxth r8, r",7, HH1,"") + TEST_UNSUPPORTED(".word 0xe6bcf47a @ sxtah pc,r12, r10, ror #8") + + TEST_R( "rev16 r0, r",0, VAL1,"") + TEST_R( "rev16 r14, r",12, VAL2,"") + TEST_UNSUPPORTED(".word 0xe6bfffbc @ rev16 pc, r12") + + TEST_RR( "uxtab16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uxtab16 r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "uxtb16 r8, r",7, HH1,"") + TEST_UNSUPPORTED(".word 0xe6ccf47a @ uxtab16 pc,r12, r10, ror #8") + + TEST_R( "usat16 r0, #12, r",0, HH1,"") + TEST_R( "usat16 r14, #12, r",12, HH2,"") + TEST_UNSUPPORTED(".word 0xe6ecff3c @ usat16 pc, #12, r12") + TEST_UNSUPPORTED(".word 0xe6ecef3f @ usat16 r14, #12, pc") + + TEST_RR( "uxtab r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uxtab r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "uxtb r8, r",7, HH1,"") + TEST_UNSUPPORTED(".word 0xe6ecf47a @ uxtab pc,r12, r10, ror #8") + +#if __LINUX_ARM_ARCH__ >= 7 + TEST_R( "rbit r0, r",0, VAL1,"") + TEST_R( "rbit r14, r",12, VAL2,"") + TEST_UNSUPPORTED(".word 0xe6ffff3c @ rbit pc, r12") +#endif + + TEST_RR( "uxtah r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uxtah r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "uxth r8, r",7, HH1,"") + TEST_UNSUPPORTED(".word 0xe6fff077 @ uxth pc, r7") + TEST_UNSUPPORTED(".word 0xe6ff807f @ uxth r8, pc") + TEST_UNSUPPORTED(".word 0xe6fcf47a @ uxtah pc, r12, r10, ror #8") + TEST_UNSUPPORTED(".word 0xe6fce47f @ uxtah r14, r12, pc, ror #8") + + TEST_R( "revsh r0, r",0, VAL1,"") + TEST_R( "revsh r14, r",12, VAL2,"") + TEST_UNSUPPORTED(".word 0xe6ffff3c @ revsh pc, r12") + TEST_UNSUPPORTED(".word 0xe6ffef3f @ revsh r14, pc") + + TEST_UNSUPPORTED(".word 0xe6900070") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe69fff7f") /* Unallocated space */ + + TEST_UNSUPPORTED(".word 0xe6d00070") /* Unallocated space */ + TEST_UNSUPPORTED(".word 0xe6dfff7f") /* Unallocated space */ +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + +#if __LINUX_ARM_ARCH__ >= 6 + TEST_GROUP("Signed multiplies") + + TEST_RRR( "smlad r0, r",0, HH1,", r",1, HH2,", r",2, VAL1,"") + TEST_RRR( "smlad r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"") + TEST_UNSUPPORTED(".word 0xe70f8a1c @ smlad pc, r12, r10, r8") + TEST_RRR( "smladx r0, r",0, HH1,", r",1, HH2,", r",2, VAL1,"") + TEST_RRR( "smladx r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"") + TEST_UNSUPPORTED(".word 0xe70f8a3c @ smladx pc, r12, r10, r8") + + TEST_RR( "smuad r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "smuad r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe70ffa1c @ smuad pc, r12, r10") + TEST_RR( "smuadx r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "smuadx r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe70ffa3c @ smuadx pc, r12, r10") + + TEST_RRR( "smlsd r0, r",0, HH1,", r",1, HH2,", r",2, VAL1,"") + TEST_RRR( "smlsd r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"") + TEST_UNSUPPORTED(".word 0xe70f8a5c @ smlsd pc, r12, r10, r8") + TEST_RRR( "smlsdx r0, r",0, HH1,", r",1, HH2,", r",2, VAL1,"") + TEST_RRR( "smlsdx r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"") + TEST_UNSUPPORTED(".word 0xe70f8a7c @ smlsdx pc, r12, r10, r8") + + TEST_RR( "smusd r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "smusd r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe70ffa5c @ smusd pc, r12, r10") + TEST_RR( "smusdx r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "smusdx r14, r",12,HH2,", r",10,HH1,"") + TEST_UNSUPPORTED(".word 0xe70ffa7c @ smusdx pc, r12, r10") + + TEST_RRRR( "smlald r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2) + TEST_RRRR( "smlald r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1) + TEST_UNSUPPORTED(".word 0xe74af819 @ smlald pc, r10, r9, r8") + TEST_UNSUPPORTED(".word 0xe74fb819 @ smlald r11, pc, r9, r8") + TEST_UNSUPPORTED(".word 0xe74ab81f @ smlald r11, r10, pc, r8") + TEST_UNSUPPORTED(".word 0xe74abf19 @ smlald r11, r10, r9, pc") + + TEST_RRRR( "smlaldx r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2) + TEST_RRRR( "smlaldx r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1) + TEST_UNSUPPORTED(".word 0xe74af839 @ smlaldx pc, r10, r9, r8") + TEST_UNSUPPORTED(".word 0xe74fb839 @ smlaldx r11, pc, r9, r8") + + TEST_RRR( "smmla r0, r",0, VAL1,", r",1, VAL2,", r",2, VAL1,"") + TEST_RRR( "smmla r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"") + TEST_UNSUPPORTED(".word 0xe75f8a1c @ smmla pc, r12, r10, r8") + TEST_RRR( "smmlar r0, r",0, VAL1,", r",1, VAL2,", r",2, VAL1,"") + TEST_RRR( "smmlar r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"") + TEST_UNSUPPORTED(".word 0xe75f8a3c @ smmlar pc, r12, r10, r8") + + TEST_RR( "smmul r0, r",0, VAL1,", r",1, VAL2,"") + TEST_RR( "smmul r14, r",12,VAL2,", r",10,VAL1,"") + TEST_UNSUPPORTED(".word 0xe75ffa1c @ smmul pc, r12, r10") + TEST_RR( "smmulr r0, r",0, VAL1,", r",1, VAL2,"") + TEST_RR( "smmulr r14, r",12,VAL2,", r",10,VAL1,"") + TEST_UNSUPPORTED(".word 0xe75ffa3c @ smmulr pc, r12, r10") + + TEST_RRR( "smmls r0, r",0, VAL1,", r",1, VAL2,", r",2, VAL1,"") + TEST_RRR( "smmls r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"") + TEST_UNSUPPORTED(".word 0xe75f8adc @ smmls pc, r12, r10, r8") + TEST_RRR( "smmlsr r0, r",0, VAL1,", r",1, VAL2,", r",2, VAL1,"") + TEST_RRR( "smmlsr r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"") + TEST_UNSUPPORTED(".word 0xe75f8afc @ smmlsr pc, r12, r10, r8") + TEST_UNSUPPORTED(".word 0xe75e8aff @ smmlsr r14, pc, r10, r8") + TEST_UNSUPPORTED(".word 0xe75e8ffc @ smmlsr r14, r12, pc, r8") + TEST_UNSUPPORTED(".word 0xe75efafc @ smmlsr r14, r12, r10, pc") + + TEST_RR( "usad8 r0, r",0, VAL1,", r",1, VAL2,"") + TEST_RR( "usad8 r14, r",12,VAL2,", r",10,VAL1,"") + TEST_UNSUPPORTED(".word 0xe75ffa1c @ usad8 pc, r12, r10") + TEST_UNSUPPORTED(".word 0xe75efa1f @ usad8 r14, pc, r10") + TEST_UNSUPPORTED(".word 0xe75eff1c @ usad8 r14, r12, pc") + + TEST_RRR( "usada8 r0, r",0, VAL1,", r",1, VAL2,", r",2, VAL3,"") + TEST_RRR( "usada8 r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL3,"") + TEST_UNSUPPORTED(".word 0xe78f8a1c @ usada8 pc, r12, r10, r8") + TEST_UNSUPPORTED(".word 0xe78e8a1f @ usada8 r14, pc, r10, r8") + TEST_UNSUPPORTED(".word 0xe78e8f1c @ usada8 r14, r12, pc, r8") +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + +#if __LINUX_ARM_ARCH__ >= 7 + TEST_GROUP("Bit Field") + + TEST_R( "sbfx r0, r",0 , VAL1,", #0, #31") + TEST_R( "sbfxeq r14, r",12, VAL2,", #8, #16") + TEST_R( "sbfx r4, r",10, VAL1,", #16, #15") + TEST_UNSUPPORTED(".word 0xe7aff45c @ sbfx pc, r12, #8, #16") + + TEST_R( "ubfx r0, r",0 , VAL1,", #0, #31") + TEST_R( "ubfxcs r14, r",12, VAL2,", #8, #16") + TEST_R( "ubfx r4, r",10, VAL1,", #16, #15") + TEST_UNSUPPORTED(".word 0xe7eff45c @ ubfx pc, r12, #8, #16") + TEST_UNSUPPORTED(".word 0xe7efc45f @ ubfx r12, pc, #8, #16") + + TEST_R( "bfc r",0, VAL1,", #4, #20") + TEST_R( "bfcvs r",14,VAL2,", #4, #20") + TEST_R( "bfc r",7, VAL1,", #0, #31") + TEST_R( "bfc r",8, VAL2,", #0, #31") + TEST_UNSUPPORTED(".word 0xe7def01f @ bfc pc, #0, #31"); + + TEST_RR( "bfi r",0, VAL1,", r",0 , VAL2,", #0, #31") + TEST_RR( "bfipl r",12,VAL1,", r",14 , VAL2,", #4, #20") + TEST_UNSUPPORTED(".word 0xe7d7f21e @ bfi pc, r14, #4, #20") + + TEST_UNSUPPORTED(".word 0x07f000f0") /* Permanently UNDEFINED */ + TEST_UNSUPPORTED(".word 0x07ffffff") /* Permanently UNDEFINED */ +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + + TEST_GROUP("Branch, branch with link, and block data transfer") + + TEST_P( "stmda r",0, 16*4,", {r0}") + TEST_P( "stmeqda r",4, 16*4,", {r0-r15}") + TEST_P( "stmneda r",8, 16*4,"!, {r8-r15}") + TEST_P( "stmda r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + TEST_P( "stmda r",13,0, "!, {pc}") + + TEST_P( "ldmda r",0, 16*4,", {r0}") + TEST_BF_P("ldmcsda r",4, 15*4,", {r0-r15}") + TEST_BF_P("ldmccda r",7, 15*4,"!, {r8-r15}") + TEST_P( "ldmda r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + TEST_BF_P("ldmda r",14,15*4,"!, {pc}") + + TEST_P( "stmia r",0, 16*4,", {r0}") + TEST_P( "stmmiia r",4, 16*4,", {r0-r15}") + TEST_P( "stmplia r",8, 16*4,"!, {r8-r15}") + TEST_P( "stmia r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + TEST_P( "stmia r",14,0, "!, {pc}") + + TEST_P( "ldmia r",0, 16*4,", {r0}") + TEST_BF_P("ldmvsia r",4, 0, ", {r0-r15}") + TEST_BF_P("ldmvcia r",7, 8*4, "!, {r8-r15}") + TEST_P( "ldmia r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + TEST_BF_P("ldmia r",14,15*4,"!, {pc}") + + TEST_P( "stmdb r",0, 16*4,", {r0}") + TEST_P( "stmhidb r",4, 16*4,", {r0-r15}") + TEST_P( "stmlsdb r",8, 16*4,"!, {r8-r15}") + TEST_P( "stmdb r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + TEST_P( "stmdb r",13,4, "!, {pc}") + + TEST_P( "ldmdb r",0, 16*4,", {r0}") + TEST_BF_P("ldmgedb r",4, 16*4,", {r0-r15}") + TEST_BF_P("ldmltdb r",7, 16*4,"!, {r8-r15}") + TEST_P( "ldmdb r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + TEST_BF_P("ldmdb r",14,16*4,"!, {pc}") + + TEST_P( "stmib r",0, 16*4,", {r0}") + TEST_P( "stmgtib r",4, 16*4,", {r0-r15}") + TEST_P( "stmleib r",8, 16*4,"!, {r8-r15}") + TEST_P( "stmib r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + TEST_P( "stmib r",13,-4, "!, {pc}") + + TEST_P( "ldmib r",0, 16*4,", {r0}") + TEST_BF_P("ldmeqib r",4, -4,", {r0-r15}") + TEST_BF_P("ldmneib r",7, 7*4,"!, {r8-r15}") + TEST_P( "ldmib r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + TEST_BF_P("ldmib r",14,14*4,"!, {pc}") + + TEST_P( "stmdb r",13,16*4,"!, {r3-r12,lr}") + TEST_P( "stmeqdb r",13,16*4,"!, {r3-r12}") + TEST_P( "stmnedb r",2, 16*4,", {r3-r12,lr}") + TEST_P( "stmdb r",13,16*4,"!, {r2-r12,lr}") + TEST_P( "stmdb r",0, 16*4,", {r0-r12}") + TEST_P( "stmdb r",0, 16*4,", {r0-r12,lr}") + + TEST_BF_P("ldmia r",13,5*4, "!, {r3-r12,pc}") + TEST_P( "ldmccia r",13,5*4, "!, {r3-r12}") + TEST_BF_P("ldmcsia r",2, 5*4, "!, {r3-r12,pc}") + TEST_BF_P("ldmia r",13,4*4, "!, {r2-r12,pc}") + TEST_P( "ldmia r",0, 16*4,", {r0-r12}") + TEST_P( "ldmia r",0, 16*4,", {r0-r12,lr}") + +#ifdef CONFIG_THUMB2_KERNEL + TEST_ARM_TO_THUMB_INTERWORK_P("ldmplia r",0,15*4,", {pc}") + TEST_ARM_TO_THUMB_INTERWORK_P("ldmmiia r",13,0,", {r0-r15}") +#endif + TEST_BF("b 2f") + TEST_BF("bl 2f") + TEST_BB("b 2b") + TEST_BB("bl 2b") + + TEST_BF("beq 2f") + TEST_BF("bleq 2f") + TEST_BB("bne 2b") + TEST_BB("blne 2b") + + TEST_BF("bgt 2f") + TEST_BF("blgt 2f") + TEST_BB("blt 2b") + TEST_BB("bllt 2b") + + TEST_GROUP("Supervisor Call, and coprocessor instructions") + + /* + * We can't really test these by executing them, so all + * we can do is check that probes are, or are not allowed. + * At the moment none are allowed... + */ +#define TEST_COPROCESSOR(code) TEST_UNSUPPORTED(code) + +#define COPROCESSOR_INSTRUCTIONS_ST_LD(two,cc) \ + TEST_COPROCESSOR("stc"two" 0, cr0, [r13, #4]") \ + TEST_COPROCESSOR("stc"two" 0, cr0, [r13, #-4]") \ + TEST_COPROCESSOR("stc"two" 0, cr0, [r13, #4]!") \ + TEST_COPROCESSOR("stc"two" 0, cr0, [r13, #-4]!") \ + TEST_COPROCESSOR("stc"two" 0, cr0, [r13], #4") \ + TEST_COPROCESSOR("stc"two" 0, cr0, [r13], #-4") \ + TEST_COPROCESSOR("stc"two" 0, cr0, [r13], {1}") \ + TEST_COPROCESSOR("stc"two"l 0, cr0, [r13, #4]") \ + TEST_COPROCESSOR("stc"two"l 0, cr0, [r13, #-4]") \ + TEST_COPROCESSOR("stc"two"l 0, cr0, [r13, #4]!") \ + TEST_COPROCESSOR("stc"two"l 0, cr0, [r13, #-4]!") \ + TEST_COPROCESSOR("stc"two"l 0, cr0, [r13], #4") \ + TEST_COPROCESSOR("stc"two"l 0, cr0, [r13], #-4") \ + TEST_COPROCESSOR("stc"two"l 0, cr0, [r13], {1}") \ + TEST_COPROCESSOR("ldc"two" 0, cr0, [r13, #4]") \ + TEST_COPROCESSOR("ldc"two" 0, cr0, [r13, #-4]") \ + TEST_COPROCESSOR("ldc"two" 0, cr0, [r13, #4]!") \ + TEST_COPROCESSOR("ldc"two" 0, cr0, [r13, #-4]!") \ + TEST_COPROCESSOR("ldc"two" 0, cr0, [r13], #4") \ + TEST_COPROCESSOR("ldc"two" 0, cr0, [r13], #-4") \ + TEST_COPROCESSOR("ldc"two" 0, cr0, [r13], {1}") \ + TEST_COPROCESSOR("ldc"two"l 0, cr0, [r13, #4]") \ + TEST_COPROCESSOR("ldc"two"l 0, cr0, [r13, #-4]") \ + TEST_COPROCESSOR("ldc"two"l 0, cr0, [r13, #4]!") \ + TEST_COPROCESSOR("ldc"two"l 0, cr0, [r13, #-4]!") \ + TEST_COPROCESSOR("ldc"two"l 0, cr0, [r13], #4") \ + TEST_COPROCESSOR("ldc"two"l 0, cr0, [r13], #-4") \ + TEST_COPROCESSOR("ldc"two"l 0, cr0, [r13], {1}") \ + \ + TEST_COPROCESSOR( "stc"two" 0, cr0, [r15, #4]") \ + TEST_COPROCESSOR( "stc"two" 0, cr0, [r15, #-4]") \ + TEST_UNSUPPORTED(".word 0x"cc"daf0001 @ stc"two" 0, cr0, [r15, #4]!") \ + TEST_UNSUPPORTED(".word 0x"cc"d2f0001 @ stc"two" 0, cr0, [r15, #-4]!") \ + TEST_UNSUPPORTED(".word 0x"cc"caf0001 @ stc"two" 0, cr0, [r15], #4") \ + TEST_UNSUPPORTED(".word 0x"cc"c2f0001 @ stc"two" 0, cr0, [r15], #-4") \ + TEST_COPROCESSOR( "stc"two" 0, cr0, [r15], {1}") \ + TEST_COPROCESSOR( "stc"two"l 0, cr0, [r15, #4]") \ + TEST_COPROCESSOR( "stc"two"l 0, cr0, [r15, #-4]") \ + TEST_UNSUPPORTED(".word 0x"cc"def0001 @ stc"two"l 0, cr0, [r15, #4]!") \ + TEST_UNSUPPORTED(".word 0x"cc"d6f0001 @ stc"two"l 0, cr0, [r15, #-4]!") \ + TEST_UNSUPPORTED(".word 0x"cc"cef0001 @ stc"two"l 0, cr0, [r15], #4") \ + TEST_UNSUPPORTED(".word 0x"cc"c6f0001 @ stc"two"l 0, cr0, [r15], #-4") \ + TEST_COPROCESSOR( "stc"two"l 0, cr0, [r15], {1}") \ + TEST_COPROCESSOR( "ldc"two" 0, cr0, [r15, #4]") \ + TEST_COPROCESSOR( "ldc"two" 0, cr0, [r15, #-4]") \ + TEST_UNSUPPORTED(".word 0x"cc"dbf0001 @ ldc"two" 0, cr0, [r15, #4]!") \ + TEST_UNSUPPORTED(".word 0x"cc"d3f0001 @ ldc"two" 0, cr0, [r15, #-4]!") \ + TEST_UNSUPPORTED(".word 0x"cc"cbf0001 @ ldc"two" 0, cr0, [r15], #4") \ + TEST_UNSUPPORTED(".word 0x"cc"c3f0001 @ ldc"two" 0, cr0, [r15], #-4") \ + TEST_COPROCESSOR( "ldc"two" 0, cr0, [r15], {1}") \ + TEST_COPROCESSOR( "ldc"two"l 0, cr0, [r15, #4]") \ + TEST_COPROCESSOR( "ldc"two"l 0, cr0, [r15, #-4]") \ + TEST_UNSUPPORTED(".word 0x"cc"dff0001 @ ldc"two"l 0, cr0, [r15, #4]!") \ + TEST_UNSUPPORTED(".word 0x"cc"d7f0001 @ ldc"two"l 0, cr0, [r15, #-4]!") \ + TEST_UNSUPPORTED(".word 0x"cc"cff0001 @ ldc"two"l 0, cr0, [r15], #4") \ + TEST_UNSUPPORTED(".word 0x"cc"c7f0001 @ ldc"two"l 0, cr0, [r15], #-4") \ + TEST_COPROCESSOR( "ldc"two"l 0, cr0, [r15], {1}") + +#define COPROCESSOR_INSTRUCTIONS_MC_MR(two,cc) \ + \ + TEST_COPROCESSOR( "mcrr"two" 0, 15, r0, r14, cr0") \ + TEST_COPROCESSOR( "mcrr"two" 15, 0, r14, r0, cr15") \ + TEST_UNSUPPORTED(".word 0x"cc"c4f00f0 @ mcrr"two" 0, 15, r0, r15, cr0") \ + TEST_UNSUPPORTED(".word 0x"cc"c40ff0f @ mcrr"two" 15, 0, r15, r0, cr15") \ + TEST_COPROCESSOR( "mrrc"two" 0, 15, r0, r14, cr0") \ + TEST_COPROCESSOR( "mrrc"two" 15, 0, r14, r0, cr15") \ + TEST_UNSUPPORTED(".word 0x"cc"c5f00f0 @ mrrc"two" 0, 15, r0, r15, cr0") \ + TEST_UNSUPPORTED(".word 0x"cc"c50ff0f @ mrrc"two" 15, 0, r15, r0, cr15") \ + TEST_COPROCESSOR( "cdp"two" 15, 15, cr15, cr15, cr15, 7") \ + TEST_COPROCESSOR( "cdp"two" 0, 0, cr0, cr0, cr0, 0") \ + TEST_COPROCESSOR( "mcr"two" 15, 7, r15, cr15, cr15, 7") \ + TEST_COPROCESSOR( "mcr"two" 0, 0, r0, cr0, cr0, 0") \ + TEST_COPROCESSOR( "mrc"two" 15, 7, r15, cr15, cr15, 7") \ + TEST_COPROCESSOR( "mrc"two" 0, 0, r0, cr0, cr0, 0") + + COPROCESSOR_INSTRUCTIONS_ST_LD("","e") + COPROCESSOR_INSTRUCTIONS_MC_MR("","e") + TEST_UNSUPPORTED("svc 0") + TEST_UNSUPPORTED("svc 0xffffff") + + TEST_UNSUPPORTED("svc 0") + + TEST_GROUP("Unconditional instruction") + +#if __LINUX_ARM_ARCH__ >= 6 + TEST_UNSUPPORTED("srsda sp, 0x13") + TEST_UNSUPPORTED("srsdb sp, 0x13") + TEST_UNSUPPORTED("srsia sp, 0x13") + TEST_UNSUPPORTED("srsib sp, 0x13") + TEST_UNSUPPORTED("srsda sp!, 0x13") + TEST_UNSUPPORTED("srsdb sp!, 0x13") + TEST_UNSUPPORTED("srsia sp!, 0x13") + TEST_UNSUPPORTED("srsib sp!, 0x13") + + TEST_UNSUPPORTED("rfeda sp") + TEST_UNSUPPORTED("rfedb sp") + TEST_UNSUPPORTED("rfeia sp") + TEST_UNSUPPORTED("rfeib sp") + TEST_UNSUPPORTED("rfeda sp!") + TEST_UNSUPPORTED("rfedb sp!") + TEST_UNSUPPORTED("rfeia sp!") + TEST_UNSUPPORTED("rfeib sp!") + TEST_UNSUPPORTED(".word 0xf81d0a00 @ rfeda pc") + TEST_UNSUPPORTED(".word 0xf91d0a00 @ rfedb pc") + TEST_UNSUPPORTED(".word 0xf89d0a00 @ rfeia pc") + TEST_UNSUPPORTED(".word 0xf99d0a00 @ rfeib pc") + TEST_UNSUPPORTED(".word 0xf83d0a00 @ rfeda pc!") + TEST_UNSUPPORTED(".word 0xf93d0a00 @ rfedb pc!") + TEST_UNSUPPORTED(".word 0xf8bd0a00 @ rfeia pc!") + TEST_UNSUPPORTED(".word 0xf9bd0a00 @ rfeib pc!") +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + +#if __LINUX_ARM_ARCH__ >= 6 + TEST_X( "blx __dummy_thumb_subroutine_even", + ".thumb \n\t" + ".space 4 \n\t" + ".type __dummy_thumb_subroutine_even, %%function \n\t" + "__dummy_thumb_subroutine_even: \n\t" + "mov r0, pc \n\t" + "bx lr \n\t" + ".arm \n\t" + ) + TEST( "blx __dummy_thumb_subroutine_even") + + TEST_X( "blx __dummy_thumb_subroutine_odd", + ".thumb \n\t" + ".space 2 \n\t" + ".type __dummy_thumb_subroutine_odd, %%function \n\t" + "__dummy_thumb_subroutine_odd: \n\t" + "mov r0, pc \n\t" + "bx lr \n\t" + ".arm \n\t" + ) + TEST( "blx __dummy_thumb_subroutine_odd") +#endif /* __LINUX_ARM_ARCH__ >= 6 */ + + COPROCESSOR_INSTRUCTIONS_ST_LD("2","f") +#if __LINUX_ARM_ARCH__ >= 6 + COPROCESSOR_INSTRUCTIONS_MC_MR("2","f") +#endif + + TEST_GROUP("Miscellaneous instructions, memory hints, and Advanced SIMD instructions") + +#if __LINUX_ARM_ARCH__ >= 6 + TEST_UNSUPPORTED("cps 0x13") + TEST_UNSUPPORTED("cpsie i") + TEST_UNSUPPORTED("cpsid i") + TEST_UNSUPPORTED("cpsie i,0x13") + TEST_UNSUPPORTED("cpsid i,0x13") + TEST_UNSUPPORTED("setend le") + TEST_UNSUPPORTED("setend be") +#endif + +#if __LINUX_ARM_ARCH__ >= 7 + TEST_P("pli [r",0,0b,", #16]") + TEST( "pli [pc, #0]") + TEST_RR("pli [r",12,0b,", r",0, 16,"]") + TEST_RR("pli [r",0, 0b,", -r",12,16,", lsl #4]") +#endif + +#if __LINUX_ARM_ARCH__ >= 5 + TEST_P("pld [r",0,32,", #-16]") + TEST( "pld [pc, #0]") + TEST_PR("pld [r",7, 24, ", r",0, 16,"]") + TEST_PR("pld [r",8, 24, ", -r",12,16,", lsl #4]") +#endif + +#if __LINUX_ARM_ARCH__ >= 7 + TEST_SUPPORTED( ".word 0xf590f000 @ pldw [r0, #0]") + TEST_SUPPORTED( ".word 0xf797f000 @ pldw [r7, r0]") + TEST_SUPPORTED( ".word 0xf798f18c @ pldw [r8, r12, lsl #3]"); +#endif + +#if __LINUX_ARM_ARCH__ >= 7 + TEST_UNSUPPORTED("clrex") + TEST_UNSUPPORTED("dsb") + TEST_UNSUPPORTED("dmb") + TEST_UNSUPPORTED("isb") +#endif + + verbose("\n"); +} + diff --git a/arch/arm/kernel/kprobes-test-thumb.c b/arch/arm/kernel/kprobes-test-thumb.c new file mode 100644 index 000000000000..5e726c31c45a --- /dev/null +++ b/arch/arm/kernel/kprobes-test-thumb.c @@ -0,0 +1,1187 @@ +/* + * arch/arm/kernel/kprobes-test-thumb.c + * + * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/module.h> + +#include "kprobes-test.h" + + +#define TEST_ISA "16" + +#define DONT_TEST_IN_ITBLOCK(tests) \ + kprobe_test_flags |= TEST_FLAG_NO_ITBLOCK; \ + tests \ + kprobe_test_flags &= ~TEST_FLAG_NO_ITBLOCK; + +#define CONDITION_INSTRUCTIONS(cc_pos, tests) \ + kprobe_test_cc_position = cc_pos; \ + DONT_TEST_IN_ITBLOCK(tests) \ + kprobe_test_cc_position = 0; + +#define TEST_ITBLOCK(code) \ + kprobe_test_flags |= TEST_FLAG_FULL_ITBLOCK; \ + TESTCASE_START(code) \ + TEST_ARG_END("") \ + "50: nop \n\t" \ + "1: "code" \n\t" \ + " mov r1, #0x11 \n\t" \ + " mov r2, #0x22 \n\t" \ + " mov r3, #0x33 \n\t" \ + "2: nop \n\t" \ + TESTCASE_END \ + kprobe_test_flags &= ~TEST_FLAG_FULL_ITBLOCK; + +#define TEST_THUMB_TO_ARM_INTERWORK_P(code1, reg, val, code2) \ + TESTCASE_START(code1 #reg code2) \ + TEST_ARG_PTR(reg, val) \ + TEST_ARG_REG(14, 99f+1) \ + TEST_ARG_MEM(15, 3f) \ + TEST_ARG_END("") \ + " nop \n\t" /* To align 1f */ \ + "50: nop \n\t" \ + "1: "code1 #reg code2" \n\t" \ + " bx lr \n\t" \ + ".arm \n\t" \ + "3: adr lr, 2f+1 \n\t" \ + " bx lr \n\t" \ + ".thumb \n\t" \ + "2: nop \n\t" \ + TESTCASE_END + + +void kprobe_thumb16_test_cases(void) +{ + kprobe_test_flags = TEST_FLAG_NARROW_INSTR; + + TEST_GROUP("Shift (immediate), add, subtract, move, and compare") + + TEST_R( "lsls r7, r",0,VAL1,", #5") + TEST_R( "lsls r0, r",7,VAL2,", #11") + TEST_R( "lsrs r7, r",0,VAL1,", #5") + TEST_R( "lsrs r0, r",7,VAL2,", #11") + TEST_R( "asrs r7, r",0,VAL1,", #5") + TEST_R( "asrs r0, r",7,VAL2,", #11") + TEST_RR( "adds r2, r",0,VAL1,", r",7,VAL2,"") + TEST_RR( "adds r5, r",7,VAL2,", r",0,VAL2,"") + TEST_RR( "subs r2, r",0,VAL1,", r",7,VAL2,"") + TEST_RR( "subs r5, r",7,VAL2,", r",0,VAL2,"") + TEST_R( "adds r7, r",0,VAL1,", #5") + TEST_R( "adds r0, r",7,VAL2,", #2") + TEST_R( "subs r7, r",0,VAL1,", #5") + TEST_R( "subs r0, r",7,VAL2,", #2") + TEST( "movs.n r0, #0x5f") + TEST( "movs.n r7, #0xa0") + TEST_R( "cmp.n r",0,0x5e, ", #0x5f") + TEST_R( "cmp.n r",5,0x15f,", #0x5f") + TEST_R( "cmp.n r",7,0xa0, ", #0xa0") + TEST_R( "adds.n r",0,VAL1,", #0x5f") + TEST_R( "adds.n r",7,VAL2,", #0xa0") + TEST_R( "subs.n r",0,VAL1,", #0x5f") + TEST_R( "subs.n r",7,VAL2,", #0xa0") + + TEST_GROUP("16-bit Thumb data-processing instructions") + +#define DATA_PROCESSING16(op,val) \ + TEST_RR( op" r",0,VAL1,", r",7,val,"") \ + TEST_RR( op" r",7,VAL2,", r",0,val,"") + + DATA_PROCESSING16("ands",0xf00f00ff) + DATA_PROCESSING16("eors",0xf00f00ff) + DATA_PROCESSING16("lsls",11) + DATA_PROCESSING16("lsrs",11) + DATA_PROCESSING16("asrs",11) + DATA_PROCESSING16("adcs",VAL2) + DATA_PROCESSING16("sbcs",VAL2) + DATA_PROCESSING16("rors",11) + DATA_PROCESSING16("tst",0xf00f00ff) + TEST_R("rsbs r",0,VAL1,", #0") + TEST_R("rsbs r",7,VAL2,", #0") + DATA_PROCESSING16("cmp",0xf00f00ff) + DATA_PROCESSING16("cmn",0xf00f00ff) + DATA_PROCESSING16("orrs",0xf00f00ff) + DATA_PROCESSING16("muls",VAL2) + DATA_PROCESSING16("bics",0xf00f00ff) + DATA_PROCESSING16("mvns",VAL2) + + TEST_GROUP("Special data instructions and branch and exchange") + + TEST_RR( "add r",0, VAL1,", r",7,VAL2,"") + TEST_RR( "add r",3, VAL2,", r",8,VAL3,"") + TEST_RR( "add r",8, VAL3,", r",0,VAL1,"") + TEST_R( "add sp" ", r",8,-8, "") + TEST_R( "add r",14,VAL1,", pc") + TEST_BF_R("add pc" ", r",0,2f-1f-8,"") + TEST_UNSUPPORTED(".short 0x44ff @ add pc, pc") + + TEST_RR( "cmp r",3,VAL1,", r",8,VAL2,"") + TEST_RR( "cmp r",8,VAL2,", r",0,VAL1,"") + TEST_R( "cmp sp" ", r",8,-8, "") + + TEST_R( "mov r0, r",7,VAL2,"") + TEST_R( "mov r3, r",8,VAL3,"") + TEST_R( "mov r8, r",0,VAL1,"") + TEST_P( "mov sp, r",8,-8, "") + TEST( "mov lr, pc") + TEST_BF_R("mov pc, r",0,2f, "") + + TEST_BF_R("bx r",0, 2f+1,"") + TEST_BF_R("bx r",14,2f+1,"") + TESTCASE_START("bx pc") + TEST_ARG_REG(14, 99f+1) + TEST_ARG_END("") + " nop \n\t" /* To align the bx pc*/ + "50: nop \n\t" + "1: bx pc \n\t" + " bx lr \n\t" + ".arm \n\t" + " adr lr, 2f+1 \n\t" + " bx lr \n\t" + ".thumb \n\t" + "2: nop \n\t" + TESTCASE_END + + TEST_BF_R("blx r",0, 2f+1,"") + TEST_BB_R("blx r",14,2f+1,"") + TEST_UNSUPPORTED(".short 0x47f8 @ blx pc") + + TEST_GROUP("Load from Literal Pool") + + TEST_X( "ldr r0, 3f", + ".align \n\t" + "3: .word "__stringify(VAL1)) + TEST_X( "ldr r7, 3f", + ".space 128 \n\t" + ".align \n\t" + "3: .word "__stringify(VAL2)) + + TEST_GROUP("16-bit Thumb Load/store instructions") + + TEST_RPR("str r",0, VAL1,", [r",1, 24,", r",2, 48,"]") + TEST_RPR("str r",7, VAL2,", [r",6, 24,", r",5, 48,"]") + TEST_RPR("strh r",0, VAL1,", [r",1, 24,", r",2, 48,"]") + TEST_RPR("strh r",7, VAL2,", [r",6, 24,", r",5, 48,"]") + TEST_RPR("strb r",0, VAL1,", [r",1, 24,", r",2, 48,"]") + TEST_RPR("strb r",7, VAL2,", [r",6, 24,", r",5, 48,"]") + TEST_PR( "ldrsb r0, [r",1, 24,", r",2, 48,"]") + TEST_PR( "ldrsb r7, [r",6, 24,", r",5, 50,"]") + TEST_PR( "ldr r0, [r",1, 24,", r",2, 48,"]") + TEST_PR( "ldr r7, [r",6, 24,", r",5, 48,"]") + TEST_PR( "ldrh r0, [r",1, 24,", r",2, 48,"]") + TEST_PR( "ldrh r7, [r",6, 24,", r",5, 50,"]") + TEST_PR( "ldrb r0, [r",1, 24,", r",2, 48,"]") + TEST_PR( "ldrb r7, [r",6, 24,", r",5, 50,"]") + TEST_PR( "ldrsh r0, [r",1, 24,", r",2, 48,"]") + TEST_PR( "ldrsh r7, [r",6, 24,", r",5, 50,"]") + + TEST_RP("str r",0, VAL1,", [r",1, 24,", #120]") + TEST_RP("str r",7, VAL2,", [r",6, 24,", #120]") + TEST_P( "ldr r0, [r",1, 24,", #120]") + TEST_P( "ldr r7, [r",6, 24,", #120]") + TEST_RP("strb r",0, VAL1,", [r",1, 24,", #30]") + TEST_RP("strb r",7, VAL2,", [r",6, 24,", #30]") + TEST_P( "ldrb r0, [r",1, 24,", #30]") + TEST_P( "ldrb r7, [r",6, 24,", #30]") + TEST_RP("strh r",0, VAL1,", [r",1, 24,", #60]") + TEST_RP("strh r",7, VAL2,", [r",6, 24,", #60]") + TEST_P( "ldrh r0, [r",1, 24,", #60]") + TEST_P( "ldrh r7, [r",6, 24,", #60]") + + TEST_R( "str r",0, VAL1,", [sp, #0]") + TEST_R( "str r",7, VAL2,", [sp, #160]") + TEST( "ldr r0, [sp, #0]") + TEST( "ldr r7, [sp, #160]") + + TEST_RP("str r",0, VAL1,", [r",0, 24,"]") + TEST_P( "ldr r0, [r",0, 24,"]") + + TEST_GROUP("Generate PC-/SP-relative address") + + TEST("add r0, pc, #4") + TEST("add r7, pc, #1020") + TEST("add r0, sp, #4") + TEST("add r7, sp, #1020") + + TEST_GROUP("Miscellaneous 16-bit instructions") + + TEST_UNSUPPORTED( "cpsie i") + TEST_UNSUPPORTED( "cpsid i") + TEST_UNSUPPORTED( "setend le") + TEST_UNSUPPORTED( "setend be") + + TEST("add sp, #"__stringify(TEST_MEMORY_SIZE)) /* Assumes TEST_MEMORY_SIZE < 0x400 */ + TEST("sub sp, #0x7f*4") + +DONT_TEST_IN_ITBLOCK( + TEST_BF_R( "cbnz r",0,0, ", 2f") + TEST_BF_R( "cbz r",2,-1,", 2f") + TEST_BF_RX( "cbnz r",4,1, ", 2f",0x20) + TEST_BF_RX( "cbz r",7,0, ", 2f",0x40) +) + TEST_R("sxth r0, r",7, HH1,"") + TEST_R("sxth r7, r",0, HH2,"") + TEST_R("sxtb r0, r",7, HH1,"") + TEST_R("sxtb r7, r",0, HH2,"") + TEST_R("uxth r0, r",7, HH1,"") + TEST_R("uxth r7, r",0, HH2,"") + TEST_R("uxtb r0, r",7, HH1,"") + TEST_R("uxtb r7, r",0, HH2,"") + TEST_R("rev r0, r",7, VAL1,"") + TEST_R("rev r7, r",0, VAL2,"") + TEST_R("rev16 r0, r",7, VAL1,"") + TEST_R("rev16 r7, r",0, VAL2,"") + TEST_UNSUPPORTED(".short 0xba80") + TEST_UNSUPPORTED(".short 0xbabf") + TEST_R("revsh r0, r",7, VAL1,"") + TEST_R("revsh r7, r",0, VAL2,"") + +#define TEST_POPPC(code, offset) \ + TESTCASE_START(code) \ + TEST_ARG_PTR(13, offset) \ + TEST_ARG_END("") \ + TEST_BRANCH_F(code,0) \ + TESTCASE_END + + TEST("push {r0}") + TEST("push {r7}") + TEST("push {r14}") + TEST("push {r0-r7,r14}") + TEST("push {r0,r2,r4,r6,r14}") + TEST("push {r1,r3,r5,r7}") + TEST("pop {r0}") + TEST("pop {r7}") + TEST("pop {r0,r2,r4,r6}") + TEST_POPPC("pop {pc}",15*4) + TEST_POPPC("pop {r0-r7,pc}",7*4) + TEST_POPPC("pop {r1,r3,r5,r7,pc}",11*4) + TEST_THUMB_TO_ARM_INTERWORK_P("pop {pc} @ ",13,15*4,"") + TEST_THUMB_TO_ARM_INTERWORK_P("pop {r0-r7,pc} @ ",13,7*4,"") + + TEST_UNSUPPORTED("bkpt.n 0") + TEST_UNSUPPORTED("bkpt.n 255") + + TEST_SUPPORTED("yield") + TEST("sev") + TEST("nop") + TEST("wfi") + TEST_SUPPORTED("wfe") + TEST_UNSUPPORTED(".short 0xbf50") /* Unassigned hints */ + TEST_UNSUPPORTED(".short 0xbff0") /* Unassigned hints */ + +#define TEST_IT(code, code2) \ + TESTCASE_START(code) \ + TEST_ARG_END("") \ + "50: nop \n\t" \ + "1: "code" \n\t" \ + " "code2" \n\t" \ + "2: nop \n\t" \ + TESTCASE_END + +DONT_TEST_IN_ITBLOCK( + TEST_IT("it eq","moveq r0,#0") + TEST_IT("it vc","movvc r0,#0") + TEST_IT("it le","movle r0,#0") + TEST_IT("ite eq","moveq r0,#0\n\t movne r1,#1") + TEST_IT("itet vc","movvc r0,#0\n\t movvs r1,#1\n\t movvc r2,#2") + TEST_IT("itete le","movle r0,#0\n\t movgt r1,#1\n\t movle r2,#2\n\t movgt r3,#3") + TEST_IT("itttt le","movle r0,#0\n\t movle r1,#1\n\t movle r2,#2\n\t movle r3,#3") + TEST_IT("iteee le","movle r0,#0\n\t movgt r1,#1\n\t movgt r2,#2\n\t movgt r3,#3") +) + + TEST_GROUP("Load and store multiple") + + TEST_P("ldmia r",4, 16*4,"!, {r0,r7}") + TEST_P("ldmia r",7, 16*4,"!, {r0-r6}") + TEST_P("stmia r",4, 16*4,"!, {r0,r7}") + TEST_P("stmia r",0, 16*4,"!, {r0-r7}") + + TEST_GROUP("Conditional branch and Supervisor Call instructions") + +CONDITION_INSTRUCTIONS(8, + TEST_BF("beq 2f") + TEST_BB("bne 2b") + TEST_BF("bgt 2f") + TEST_BB("blt 2b") +) + TEST_UNSUPPORTED(".short 0xde00") + TEST_UNSUPPORTED(".short 0xdeff") + TEST_UNSUPPORTED("svc #0x00") + TEST_UNSUPPORTED("svc #0xff") + + TEST_GROUP("Unconditional branch") + + TEST_BF( "b 2f") + TEST_BB( "b 2b") + TEST_BF_X("b 2f", 0x400) + TEST_BB_X("b 2b", 0x400) + + TEST_GROUP("Testing instructions in IT blocks") + + TEST_ITBLOCK("subs.n r0, r0") + + verbose("\n"); +} + + +void kprobe_thumb32_test_cases(void) +{ + kprobe_test_flags = 0; + + TEST_GROUP("Load/store multiple") + + TEST_UNSUPPORTED("rfedb sp") + TEST_UNSUPPORTED("rfeia sp") + TEST_UNSUPPORTED("rfedb sp!") + TEST_UNSUPPORTED("rfeia sp!") + + TEST_P( "stmia r",0, 16*4,", {r0,r8}") + TEST_P( "stmia r",4, 16*4,", {r0-r12,r14}") + TEST_P( "stmia r",7, 16*4,"!, {r8-r12,r14}") + TEST_P( "stmia r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + + TEST_P( "ldmia r",0, 16*4,", {r0,r8}") + TEST_P( "ldmia r",4, 0, ", {r0-r12,r14}") + TEST_BF_P("ldmia r",5, 8*4, "!, {r6-r12,r15}") + TEST_P( "ldmia r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + TEST_BF_P("ldmia r",14,14*4,"!, {r4,pc}") + + TEST_P( "stmdb r",0, 16*4,", {r0,r8}") + TEST_P( "stmdb r",4, 16*4,", {r0-r12,r14}") + TEST_P( "stmdb r",5, 16*4,"!, {r8-r12,r14}") + TEST_P( "stmdb r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + + TEST_P( "ldmdb r",0, 16*4,", {r0,r8}") + TEST_P( "ldmdb r",4, 16*4,", {r0-r12,r14}") + TEST_BF_P("ldmdb r",5, 16*4,"!, {r6-r12,r15}") + TEST_P( "ldmdb r",12,16*4,"!, {r1,r3,r5,r7,r8-r11,r14}") + TEST_BF_P("ldmdb r",14,16*4,"!, {r4,pc}") + + TEST_P( "stmdb r",13,16*4,"!, {r3-r12,lr}") + TEST_P( "stmdb r",13,16*4,"!, {r3-r12}") + TEST_P( "stmdb r",2, 16*4,", {r3-r12,lr}") + TEST_P( "stmdb r",13,16*4,"!, {r2-r12,lr}") + TEST_P( "stmdb r",0, 16*4,", {r0-r12}") + TEST_P( "stmdb r",0, 16*4,", {r0-r12,lr}") + + TEST_BF_P("ldmia r",13,5*4, "!, {r3-r12,pc}") + TEST_P( "ldmia r",13,5*4, "!, {r3-r12}") + TEST_BF_P("ldmia r",2, 5*4, "!, {r3-r12,pc}") + TEST_BF_P("ldmia r",13,4*4, "!, {r2-r12,pc}") + TEST_P( "ldmia r",0, 16*4,", {r0-r12}") + TEST_P( "ldmia r",0, 16*4,", {r0-r12,lr}") + + TEST_THUMB_TO_ARM_INTERWORK_P("ldmia r",0,14*4,", {r12,pc}") + TEST_THUMB_TO_ARM_INTERWORK_P("ldmia r",13,2*4,", {r0-r12,pc}") + + TEST_UNSUPPORTED(".short 0xe88f,0x0101 @ stmia pc, {r0,r8}") + TEST_UNSUPPORTED(".short 0xe92f,0x5f00 @ stmdb pc!, {r8-r12,r14}") + TEST_UNSUPPORTED(".short 0xe8bd,0xc000 @ ldmia r13!, {r14,pc}") + TEST_UNSUPPORTED(".short 0xe93e,0xc000 @ ldmdb r14!, {r14,pc}") + TEST_UNSUPPORTED(".short 0xe8a7,0x3f00 @ stmia r7!, {r8-r12,sp}") + TEST_UNSUPPORTED(".short 0xe8a7,0x9f00 @ stmia r7!, {r8-r12,pc}") + TEST_UNSUPPORTED(".short 0xe93e,0x2010 @ ldmdb r14!, {r4,sp}") + + TEST_GROUP("Load/store double or exclusive, table branch") + + TEST_P( "ldrd r0, r1, [r",1, 24,", #-16]") + TEST( "ldrd r12, r14, [sp, #16]") + TEST_P( "ldrd r1, r0, [r",7, 24,", #-16]!") + TEST( "ldrd r14, r12, [sp, #16]!") + TEST_P( "ldrd r1, r0, [r",7, 24,"], #16") + TEST( "ldrd r7, r8, [sp], #-16") + + TEST_X( "ldrd r12, r14, 3f", + ".align 3 \n\t" + "3: .word "__stringify(VAL1)" \n\t" + " .word "__stringify(VAL2)) + + TEST_UNSUPPORTED(".short 0xe9ff,0xec04 @ ldrd r14, r12, [pc, #16]!") + TEST_UNSUPPORTED(".short 0xe8ff,0xec04 @ ldrd r14, r12, [pc], #16") + TEST_UNSUPPORTED(".short 0xe9d4,0xd800 @ ldrd sp, r8, [r4]") + TEST_UNSUPPORTED(".short 0xe9d4,0xf800 @ ldrd pc, r8, [r4]") + TEST_UNSUPPORTED(".short 0xe9d4,0x7d00 @ ldrd r7, sp, [r4]") + TEST_UNSUPPORTED(".short 0xe9d4,0x7f00 @ ldrd r7, pc, [r4]") + + TEST_RRP("strd r",0, VAL1,", r",1, VAL2,", [r",1, 24,", #-16]") + TEST_RR( "strd r",12,VAL2,", r",14,VAL1,", [sp, #16]") + TEST_RRP("strd r",1, VAL1,", r",0, VAL2,", [r",7, 24,", #-16]!") + TEST_RR( "strd r",14,VAL2,", r",12,VAL1,", [sp, #16]!") + TEST_RRP("strd r",1, VAL1,", r",0, VAL2,", [r",7, 24,"], #16") + TEST_RR( "strd r",7, VAL2,", r",8, VAL1,", [sp], #-16") + TEST_UNSUPPORTED(".short 0xe9ef,0xec04 @ strd r14, r12, [pc, #16]!") + TEST_UNSUPPORTED(".short 0xe8ef,0xec04 @ strd r14, r12, [pc], #16") + + TEST_RX("tbb [pc, r",0, (9f-(1f+4)),"]", + "9: \n\t" + ".byte (2f-1b-4)>>1 \n\t" + ".byte (3f-1b-4)>>1 \n\t" + "3: mvn r0, r0 \n\t" + "2: nop \n\t") + + TEST_RX("tbb [pc, r",4, (9f-(1f+4)+1),"]", + "9: \n\t" + ".byte (2f-1b-4)>>1 \n\t" + ".byte (3f-1b-4)>>1 \n\t" + "3: mvn r0, r0 \n\t" + "2: nop \n\t") + + TEST_RRX("tbb [r",1,9f,", r",2,0,"]", + "9: \n\t" + ".byte (2f-1b-4)>>1 \n\t" + ".byte (3f-1b-4)>>1 \n\t" + "3: mvn r0, r0 \n\t" + "2: nop \n\t") + + TEST_RX("tbh [pc, r",7, (9f-(1f+4))>>1,"]", + "9: \n\t" + ".short (2f-1b-4)>>1 \n\t" + ".short (3f-1b-4)>>1 \n\t" + "3: mvn r0, r0 \n\t" + "2: nop \n\t") + + TEST_RX("tbh [pc, r",12, ((9f-(1f+4))>>1)+1,"]", + "9: \n\t" + ".short (2f-1b-4)>>1 \n\t" + ".short (3f-1b-4)>>1 \n\t" + "3: mvn r0, r0 \n\t" + "2: nop \n\t") + + TEST_RRX("tbh [r",1,9f, ", r",14,1,"]", + "9: \n\t" + ".short (2f-1b-4)>>1 \n\t" + ".short (3f-1b-4)>>1 \n\t" + "3: mvn r0, r0 \n\t" + "2: nop \n\t") + + TEST_UNSUPPORTED(".short 0xe8d1,0xf01f @ tbh [r1, pc]") + TEST_UNSUPPORTED(".short 0xe8d1,0xf01d @ tbh [r1, sp]") + TEST_UNSUPPORTED(".short 0xe8dd,0xf012 @ tbh [sp, r2]") + + TEST_UNSUPPORTED("strexb r0, r1, [r2]") + TEST_UNSUPPORTED("strexh r0, r1, [r2]") + TEST_UNSUPPORTED("strexd r0, r1, [r2]") + TEST_UNSUPPORTED("ldrexb r0, [r1]") + TEST_UNSUPPORTED("ldrexh r0, [r1]") + TEST_UNSUPPORTED("ldrexd r0, [r1]") + + TEST_GROUP("Data-processing (shifted register) and (modified immediate)") + +#define _DATA_PROCESSING32_DNM(op,s,val) \ + TEST_RR(op s".w r0, r",1, VAL1,", r",2, val, "") \ + TEST_RR(op s" r1, r",1, VAL1,", r",2, val, ", lsl #3") \ + TEST_RR(op s" r2, r",3, VAL1,", r",2, val, ", lsr #4") \ + TEST_RR(op s" r3, r",3, VAL1,", r",2, val, ", asr #5") \ + TEST_RR(op s" r4, r",5, VAL1,", r",2, N(val),", asr #6") \ + TEST_RR(op s" r5, r",5, VAL1,", r",2, val, ", ror #7") \ + TEST_RR(op s" r8, r",9, VAL1,", r",10,val, ", rrx") \ + TEST_R( op s" r0, r",11,VAL1,", #0x00010001") \ + TEST_R( op s" r11, r",0, VAL1,", #0xf5000000") \ + TEST_R( op s" r7, r",8, VAL2,", #0x000af000") + +#define DATA_PROCESSING32_DNM(op,val) \ + _DATA_PROCESSING32_DNM(op,"",val) \ + _DATA_PROCESSING32_DNM(op,"s",val) + +#define DATA_PROCESSING32_NM(op,val) \ + TEST_RR(op".w r",1, VAL1,", r",2, val, "") \ + TEST_RR(op" r",1, VAL1,", r",2, val, ", lsl #3") \ + TEST_RR(op" r",3, VAL1,", r",2, val, ", lsr #4") \ + TEST_RR(op" r",3, VAL1,", r",2, val, ", asr #5") \ + TEST_RR(op" r",5, VAL1,", r",2, N(val),", asr #6") \ + TEST_RR(op" r",5, VAL1,", r",2, val, ", ror #7") \ + TEST_RR(op" r",9, VAL1,", r",10,val, ", rrx") \ + TEST_R( op" r",11,VAL1,", #0x00010001") \ + TEST_R( op" r",0, VAL1,", #0xf5000000") \ + TEST_R( op" r",8, VAL2,", #0x000af000") + +#define _DATA_PROCESSING32_DM(op,s,val) \ + TEST_R( op s".w r0, r",14, val, "") \ + TEST_R( op s" r1, r",12, val, ", lsl #3") \ + TEST_R( op s" r2, r",11, val, ", lsr #4") \ + TEST_R( op s" r3, r",10, val, ", asr #5") \ + TEST_R( op s" r4, r",9, N(val),", asr #6") \ + TEST_R( op s" r5, r",8, val, ", ror #7") \ + TEST_R( op s" r8, r",7,val, ", rrx") \ + TEST( op s" r0, #0x00010001") \ + TEST( op s" r11, #0xf5000000") \ + TEST( op s" r7, #0x000af000") \ + TEST( op s" r4, #0x00005a00") + +#define DATA_PROCESSING32_DM(op,val) \ + _DATA_PROCESSING32_DM(op,"",val) \ + _DATA_PROCESSING32_DM(op,"s",val) + + DATA_PROCESSING32_DNM("and",0xf00f00ff) + DATA_PROCESSING32_NM("tst",0xf00f00ff) + DATA_PROCESSING32_DNM("bic",0xf00f00ff) + DATA_PROCESSING32_DNM("orr",0xf00f00ff) + DATA_PROCESSING32_DM("mov",VAL2) + DATA_PROCESSING32_DNM("orn",0xf00f00ff) + DATA_PROCESSING32_DM("mvn",VAL2) + DATA_PROCESSING32_DNM("eor",0xf00f00ff) + DATA_PROCESSING32_NM("teq",0xf00f00ff) + DATA_PROCESSING32_DNM("add",VAL2) + DATA_PROCESSING32_NM("cmn",VAL2) + DATA_PROCESSING32_DNM("adc",VAL2) + DATA_PROCESSING32_DNM("sbc",VAL2) + DATA_PROCESSING32_DNM("sub",VAL2) + DATA_PROCESSING32_NM("cmp",VAL2) + DATA_PROCESSING32_DNM("rsb",VAL2) + + TEST_RR("pkhbt r0, r",0, HH1,", r",1, HH2,"") + TEST_RR("pkhbt r14,r",12, HH1,", r",10,HH2,", lsl #2") + TEST_RR("pkhtb r0, r",0, HH1,", r",1, HH2,"") + TEST_RR("pkhtb r14,r",12, HH1,", r",10,HH2,", asr #2") + + TEST_UNSUPPORTED(".short 0xea17,0x0f0d @ tst.w r7, sp") + TEST_UNSUPPORTED(".short 0xea17,0x0f0f @ tst.w r7, pc") + TEST_UNSUPPORTED(".short 0xea1d,0x0f07 @ tst.w sp, r7") + TEST_UNSUPPORTED(".short 0xea1f,0x0f07 @ tst.w pc, r7") + TEST_UNSUPPORTED(".short 0xf01d,0x1f08 @ tst sp, #0x00080008") + TEST_UNSUPPORTED(".short 0xf01f,0x1f08 @ tst pc, #0x00080008") + + TEST_UNSUPPORTED(".short 0xea97,0x0f0d @ teq.w r7, sp") + TEST_UNSUPPORTED(".short 0xea97,0x0f0f @ teq.w r7, pc") + TEST_UNSUPPORTED(".short 0xea9d,0x0f07 @ teq.w sp, r7") + TEST_UNSUPPORTED(".short 0xea9f,0x0f07 @ teq.w pc, r7") + TEST_UNSUPPORTED(".short 0xf09d,0x1f08 @ tst sp, #0x00080008") + TEST_UNSUPPORTED(".short 0xf09f,0x1f08 @ tst pc, #0x00080008") + + TEST_UNSUPPORTED(".short 0xeb17,0x0f0d @ cmn.w r7, sp") + TEST_UNSUPPORTED(".short 0xeb17,0x0f0f @ cmn.w r7, pc") + TEST_P("cmn.w sp, r",7,0,"") + TEST_UNSUPPORTED(".short 0xeb1f,0x0f07 @ cmn.w pc, r7") + TEST( "cmn sp, #0x00080008") + TEST_UNSUPPORTED(".short 0xf11f,0x1f08 @ cmn pc, #0x00080008") + + TEST_UNSUPPORTED(".short 0xebb7,0x0f0d @ cmp.w r7, sp") + TEST_UNSUPPORTED(".short 0xebb7,0x0f0f @ cmp.w r7, pc") + TEST_P("cmp.w sp, r",7,0,"") + TEST_UNSUPPORTED(".short 0xebbf,0x0f07 @ cmp.w pc, r7") + TEST( "cmp sp, #0x00080008") + TEST_UNSUPPORTED(".short 0xf1bf,0x1f08 @ cmp pc, #0x00080008") + + TEST_UNSUPPORTED(".short 0xea5f,0x070d @ movs.w r7, sp") + TEST_UNSUPPORTED(".short 0xea5f,0x070f @ movs.w r7, pc") + TEST_UNSUPPORTED(".short 0xea5f,0x0d07 @ movs.w sp, r7") + TEST_UNSUPPORTED(".short 0xea4f,0x0f07 @ mov.w pc, r7") + TEST_UNSUPPORTED(".short 0xf04f,0x1d08 @ mov sp, #0x00080008") + TEST_UNSUPPORTED(".short 0xf04f,0x1f08 @ mov pc, #0x00080008") + + TEST_R("add.w r0, sp, r",1, 4,"") + TEST_R("adds r0, sp, r",1, 4,", asl #3") + TEST_R("add r0, sp, r",1, 4,", asl #4") + TEST_R("add r0, sp, r",1, 16,", ror #1") + TEST_R("add.w sp, sp, r",1, 4,"") + TEST_R("add sp, sp, r",1, 4,", asl #3") + TEST_UNSUPPORTED(".short 0xeb0d,0x1d01 @ add sp, sp, r1, asl #4") + TEST_UNSUPPORTED(".short 0xeb0d,0x0d71 @ add sp, sp, r1, ror #1") + TEST( "add.w r0, sp, #24") + TEST( "add.w sp, sp, #24") + TEST_UNSUPPORTED(".short 0xeb0d,0x0f01 @ add pc, sp, r1") + TEST_UNSUPPORTED(".short 0xeb0d,0x000f @ add r0, sp, pc") + TEST_UNSUPPORTED(".short 0xeb0d,0x000d @ add r0, sp, sp") + TEST_UNSUPPORTED(".short 0xeb0d,0x0d0f @ add sp, sp, pc") + TEST_UNSUPPORTED(".short 0xeb0d,0x0d0d @ add sp, sp, sp") + + TEST_R("sub.w r0, sp, r",1, 4,"") + TEST_R("subs r0, sp, r",1, 4,", asl #3") + TEST_R("sub r0, sp, r",1, 4,", asl #4") + TEST_R("sub r0, sp, r",1, 16,", ror #1") + TEST_R("sub.w sp, sp, r",1, 4,"") + TEST_R("sub sp, sp, r",1, 4,", asl #3") + TEST_UNSUPPORTED(".short 0xebad,0x1d01 @ sub sp, sp, r1, asl #4") + TEST_UNSUPPORTED(".short 0xebad,0x0d71 @ sub sp, sp, r1, ror #1") + TEST_UNSUPPORTED(".short 0xebad,0x0f01 @ sub pc, sp, r1") + TEST( "sub.w r0, sp, #24") + TEST( "sub.w sp, sp, #24") + + TEST_UNSUPPORTED(".short 0xea02,0x010f @ and r1, r2, pc") + TEST_UNSUPPORTED(".short 0xea0f,0x0103 @ and r1, pc, r3") + TEST_UNSUPPORTED(".short 0xea02,0x0f03 @ and pc, r2, r3") + TEST_UNSUPPORTED(".short 0xea02,0x010d @ and r1, r2, sp") + TEST_UNSUPPORTED(".short 0xea0d,0x0103 @ and r1, sp, r3") + TEST_UNSUPPORTED(".short 0xea02,0x0d03 @ and sp, r2, r3") + TEST_UNSUPPORTED(".short 0xf00d,0x1108 @ and r1, sp, #0x00080008") + TEST_UNSUPPORTED(".short 0xf00f,0x1108 @ and r1, pc, #0x00080008") + TEST_UNSUPPORTED(".short 0xf002,0x1d08 @ and sp, r8, #0x00080008") + TEST_UNSUPPORTED(".short 0xf002,0x1f08 @ and pc, r8, #0x00080008") + + TEST_UNSUPPORTED(".short 0xeb02,0x010f @ add r1, r2, pc") + TEST_UNSUPPORTED(".short 0xeb0f,0x0103 @ add r1, pc, r3") + TEST_UNSUPPORTED(".short 0xeb02,0x0f03 @ add pc, r2, r3") + TEST_UNSUPPORTED(".short 0xeb02,0x010d @ add r1, r2, sp") + TEST_SUPPORTED( ".short 0xeb0d,0x0103 @ add r1, sp, r3") + TEST_UNSUPPORTED(".short 0xeb02,0x0d03 @ add sp, r2, r3") + TEST_SUPPORTED( ".short 0xf10d,0x1108 @ add r1, sp, #0x00080008") + TEST_UNSUPPORTED(".short 0xf10d,0x1f08 @ add pc, sp, #0x00080008") + TEST_UNSUPPORTED(".short 0xf10f,0x1108 @ add r1, pc, #0x00080008") + TEST_UNSUPPORTED(".short 0xf102,0x1d08 @ add sp, r8, #0x00080008") + TEST_UNSUPPORTED(".short 0xf102,0x1f08 @ add pc, r8, #0x00080008") + + TEST_UNSUPPORTED(".short 0xeaa0,0x0000") + TEST_UNSUPPORTED(".short 0xeaf0,0x0000") + TEST_UNSUPPORTED(".short 0xeb20,0x0000") + TEST_UNSUPPORTED(".short 0xeb80,0x0000") + TEST_UNSUPPORTED(".short 0xebe0,0x0000") + + TEST_UNSUPPORTED(".short 0xf0a0,0x0000") + TEST_UNSUPPORTED(".short 0xf0c0,0x0000") + TEST_UNSUPPORTED(".short 0xf0f0,0x0000") + TEST_UNSUPPORTED(".short 0xf120,0x0000") + TEST_UNSUPPORTED(".short 0xf180,0x0000") + TEST_UNSUPPORTED(".short 0xf1e0,0x0000") + + TEST_GROUP("Coprocessor instructions") + + TEST_UNSUPPORTED(".short 0xec00,0x0000") + TEST_UNSUPPORTED(".short 0xeff0,0x0000") + TEST_UNSUPPORTED(".short 0xfc00,0x0000") + TEST_UNSUPPORTED(".short 0xfff0,0x0000") + + TEST_GROUP("Data-processing (plain binary immediate)") + + TEST_R("addw r0, r",1, VAL1,", #0x123") + TEST( "addw r14, sp, #0xf5a") + TEST( "addw sp, sp, #0x20") + TEST( "addw r7, pc, #0x888") + TEST_UNSUPPORTED(".short 0xf20f,0x1f20 @ addw pc, pc, #0x120") + TEST_UNSUPPORTED(".short 0xf20d,0x1f20 @ addw pc, sp, #0x120") + TEST_UNSUPPORTED(".short 0xf20f,0x1d20 @ addw sp, pc, #0x120") + TEST_UNSUPPORTED(".short 0xf200,0x1d20 @ addw sp, r0, #0x120") + + TEST_R("subw r0, r",1, VAL1,", #0x123") + TEST( "subw r14, sp, #0xf5a") + TEST( "subw sp, sp, #0x20") + TEST( "subw r7, pc, #0x888") + TEST_UNSUPPORTED(".short 0xf2af,0x1f20 @ subw pc, pc, #0x120") + TEST_UNSUPPORTED(".short 0xf2ad,0x1f20 @ subw pc, sp, #0x120") + TEST_UNSUPPORTED(".short 0xf2af,0x1d20 @ subw sp, pc, #0x120") + TEST_UNSUPPORTED(".short 0xf2a0,0x1d20 @ subw sp, r0, #0x120") + + TEST("movw r0, #0") + TEST("movw r0, #0xffff") + TEST("movw lr, #0xffff") + TEST_UNSUPPORTED(".short 0xf240,0x0d00 @ movw sp, #0") + TEST_UNSUPPORTED(".short 0xf240,0x0f00 @ movw pc, #0") + + TEST_R("movt r",0, VAL1,", #0") + TEST_R("movt r",0, VAL2,", #0xffff") + TEST_R("movt r",14,VAL1,", #0xffff") + TEST_UNSUPPORTED(".short 0xf2c0,0x0d00 @ movt sp, #0") + TEST_UNSUPPORTED(".short 0xf2c0,0x0f00 @ movt pc, #0") + + TEST_R( "ssat r0, #24, r",0, VAL1,"") + TEST_R( "ssat r14, #24, r",12, VAL2,"") + TEST_R( "ssat r0, #24, r",0, VAL1,", lsl #8") + TEST_R( "ssat r14, #24, r",12, VAL2,", asr #8") + TEST_UNSUPPORTED(".short 0xf30c,0x0d17 @ ssat sp, #24, r12") + TEST_UNSUPPORTED(".short 0xf30c,0x0f17 @ ssat pc, #24, r12") + TEST_UNSUPPORTED(".short 0xf30d,0x0c17 @ ssat r12, #24, sp") + TEST_UNSUPPORTED(".short 0xf30f,0x0c17 @ ssat r12, #24, pc") + + TEST_R( "usat r0, #24, r",0, VAL1,"") + TEST_R( "usat r14, #24, r",12, VAL2,"") + TEST_R( "usat r0, #24, r",0, VAL1,", lsl #8") + TEST_R( "usat r14, #24, r",12, VAL2,", asr #8") + TEST_UNSUPPORTED(".short 0xf38c,0x0d17 @ usat sp, #24, r12") + TEST_UNSUPPORTED(".short 0xf38c,0x0f17 @ usat pc, #24, r12") + TEST_UNSUPPORTED(".short 0xf38d,0x0c17 @ usat r12, #24, sp") + TEST_UNSUPPORTED(".short 0xf38f,0x0c17 @ usat r12, #24, pc") + + TEST_R( "ssat16 r0, #12, r",0, HH1,"") + TEST_R( "ssat16 r14, #12, r",12, HH2,"") + TEST_UNSUPPORTED(".short 0xf32c,0x0d0b @ ssat16 sp, #12, r12") + TEST_UNSUPPORTED(".short 0xf32c,0x0f0b @ ssat16 pc, #12, r12") + TEST_UNSUPPORTED(".short 0xf32d,0x0c0b @ ssat16 r12, #12, sp") + TEST_UNSUPPORTED(".short 0xf32f,0x0c0b @ ssat16 r12, #12, pc") + + TEST_R( "usat16 r0, #12, r",0, HH1,"") + TEST_R( "usat16 r14, #12, r",12, HH2,"") + TEST_UNSUPPORTED(".short 0xf3ac,0x0d0b @ usat16 sp, #12, r12") + TEST_UNSUPPORTED(".short 0xf3ac,0x0f0b @ usat16 pc, #12, r12") + TEST_UNSUPPORTED(".short 0xf3ad,0x0c0b @ usat16 r12, #12, sp") + TEST_UNSUPPORTED(".short 0xf3af,0x0c0b @ usat16 r12, #12, pc") + + TEST_R( "sbfx r0, r",0 , VAL1,", #0, #31") + TEST_R( "sbfx r14, r",12, VAL2,", #8, #16") + TEST_R( "sbfx r4, r",10, VAL1,", #16, #15") + TEST_UNSUPPORTED(".short 0xf34c,0x2d0f @ sbfx sp, r12, #8, #16") + TEST_UNSUPPORTED(".short 0xf34c,0x2f0f @ sbfx pc, r12, #8, #16") + TEST_UNSUPPORTED(".short 0xf34d,0x2c0f @ sbfx r12, sp, #8, #16") + TEST_UNSUPPORTED(".short 0xf34f,0x2c0f @ sbfx r12, pc, #8, #16") + + TEST_R( "ubfx r0, r",0 , VAL1,", #0, #31") + TEST_R( "ubfx r14, r",12, VAL2,", #8, #16") + TEST_R( "ubfx r4, r",10, VAL1,", #16, #15") + TEST_UNSUPPORTED(".short 0xf3cc,0x2d0f @ ubfx sp, r12, #8, #16") + TEST_UNSUPPORTED(".short 0xf3cc,0x2f0f @ ubfx pc, r12, #8, #16") + TEST_UNSUPPORTED(".short 0xf3cd,0x2c0f @ ubfx r12, sp, #8, #16") + TEST_UNSUPPORTED(".short 0xf3cf,0x2c0f @ ubfx r12, pc, #8, #16") + + TEST_R( "bfc r",0, VAL1,", #4, #20") + TEST_R( "bfc r",14,VAL2,", #4, #20") + TEST_R( "bfc r",7, VAL1,", #0, #31") + TEST_R( "bfc r",8, VAL2,", #0, #31") + TEST_UNSUPPORTED(".short 0xf36f,0x0d1e @ bfc sp, #0, #31") + TEST_UNSUPPORTED(".short 0xf36f,0x0f1e @ bfc pc, #0, #31") + + TEST_RR( "bfi r",0, VAL1,", r",0 , VAL2,", #0, #31") + TEST_RR( "bfi r",12,VAL1,", r",14 , VAL2,", #4, #20") + TEST_UNSUPPORTED(".short 0xf36e,0x1d17 @ bfi sp, r14, #4, #20") + TEST_UNSUPPORTED(".short 0xf36e,0x1f17 @ bfi pc, r14, #4, #20") + TEST_UNSUPPORTED(".short 0xf36d,0x1e17 @ bfi r14, sp, #4, #20") + + TEST_GROUP("Branches and miscellaneous control") + +CONDITION_INSTRUCTIONS(22, + TEST_BF("beq.w 2f") + TEST_BB("bne.w 2b") + TEST_BF("bgt.w 2f") + TEST_BB("blt.w 2b") + TEST_BF_X("bpl.w 2f",0x1000) +) + + TEST_UNSUPPORTED("msr cpsr, r0") + TEST_UNSUPPORTED("msr cpsr_f, r1") + TEST_UNSUPPORTED("msr spsr, r2") + + TEST_UNSUPPORTED("cpsie.w i") + TEST_UNSUPPORTED("cpsid.w i") + TEST_UNSUPPORTED("cps 0x13") + + TEST_SUPPORTED("yield.w") + TEST("sev.w") + TEST("nop.w") + TEST("wfi.w") + TEST_SUPPORTED("wfe.w") + TEST_UNSUPPORTED("dbg.w #0") + + TEST_UNSUPPORTED("clrex") + TEST_UNSUPPORTED("dsb") + TEST_UNSUPPORTED("dmb") + TEST_UNSUPPORTED("isb") + + TEST_UNSUPPORTED("bxj r0") + + TEST_UNSUPPORTED("subs pc, lr, #4") + + TEST("mrs r0, cpsr") + TEST("mrs r14, cpsr") + TEST_UNSUPPORTED(".short 0xf3ef,0x8d00 @ mrs sp, spsr") + TEST_UNSUPPORTED(".short 0xf3ef,0x8f00 @ mrs pc, spsr") + TEST_UNSUPPORTED("mrs r0, spsr") + TEST_UNSUPPORTED("mrs lr, spsr") + + TEST_UNSUPPORTED(".short 0xf7f0,0x8000 @ smc #0") + + TEST_UNSUPPORTED(".short 0xf7f0,0xa000 @ undefeined") + + TEST_BF( "b.w 2f") + TEST_BB( "b.w 2b") + TEST_BF_X("b.w 2f", 0x1000) + + TEST_BF( "bl.w 2f") + TEST_BB( "bl.w 2b") + TEST_BB_X("bl.w 2b", 0x1000) + + TEST_X( "blx __dummy_arm_subroutine", + ".arm \n\t" + ".align \n\t" + ".type __dummy_arm_subroutine, %%function \n\t" + "__dummy_arm_subroutine: \n\t" + "mov r0, pc \n\t" + "bx lr \n\t" + ".thumb \n\t" + ) + TEST( "blx __dummy_arm_subroutine") + + TEST_GROUP("Store single data item") + +#define SINGLE_STORE(size) \ + TEST_RP( "str"size" r",0, VAL1,", [r",11,-1024,", #1024]") \ + TEST_RP( "str"size" r",14,VAL2,", [r",1, -1024,", #1080]") \ + TEST_RP( "str"size" r",0, VAL1,", [r",11,256, ", #-120]") \ + TEST_RP( "str"size" r",14,VAL2,", [r",1, 256, ", #-128]") \ + TEST_RP( "str"size" r",0, VAL1,", [r",11,24, "], #120") \ + TEST_RP( "str"size" r",14,VAL2,", [r",1, 24, "], #128") \ + TEST_RP( "str"size" r",0, VAL1,", [r",11,24, "], #-120") \ + TEST_RP( "str"size" r",14,VAL2,", [r",1, 24, "], #-128") \ + TEST_RP( "str"size" r",0, VAL1,", [r",11,24, ", #120]!") \ + TEST_RP( "str"size" r",14,VAL2,", [r",1, 24, ", #128]!") \ + TEST_RP( "str"size" r",0, VAL1,", [r",11,256, ", #-120]!") \ + TEST_RP( "str"size" r",14,VAL2,", [r",1, 256, ", #-128]!") \ + TEST_RPR("str"size".w r",0, VAL1,", [r",1, 0,", r",2, 4,"]") \ + TEST_RPR("str"size" r",14,VAL2,", [r",10,0,", r",11,4,", lsl #1]") \ + TEST_R( "str"size".w r",7, VAL1,", [sp, #24]") \ + TEST_RP( "str"size".w r",0, VAL2,", [r",0,0, "]") \ + TEST_UNSUPPORTED("str"size"t r0, [r1, #4]") + + SINGLE_STORE("b") + SINGLE_STORE("h") + SINGLE_STORE("") + + TEST("str sp, [sp]") + TEST_UNSUPPORTED(".short 0xf8cf,0xe000 @ str r14, [pc]") + TEST_UNSUPPORTED(".short 0xf8ce,0xf000 @ str pc, [r14]") + + TEST_GROUP("Advanced SIMD element or structure load/store instructions") + + TEST_UNSUPPORTED(".short 0xf900,0x0000") + TEST_UNSUPPORTED(".short 0xf92f,0xffff") + TEST_UNSUPPORTED(".short 0xf980,0x0000") + TEST_UNSUPPORTED(".short 0xf9ef,0xffff") + + TEST_GROUP("Load single data item and memory hints") + +#define SINGLE_LOAD(size) \ + TEST_P( "ldr"size" r0, [r",11,-1024, ", #1024]") \ + TEST_P( "ldr"size" r14, [r",1, -1024,", #1080]") \ + TEST_P( "ldr"size" r0, [r",11,256, ", #-120]") \ + TEST_P( "ldr"size" r14, [r",1, 256, ", #-128]") \ + TEST_P( "ldr"size" r0, [r",11,24, "], #120") \ + TEST_P( "ldr"size" r14, [r",1, 24, "], #128") \ + TEST_P( "ldr"size" r0, [r",11,24, "], #-120") \ + TEST_P( "ldr"size" r14, [r",1,24, "], #-128") \ + TEST_P( "ldr"size" r0, [r",11,24, ", #120]!") \ + TEST_P( "ldr"size" r14, [r",1, 24, ", #128]!") \ + TEST_P( "ldr"size" r0, [r",11,256, ", #-120]!") \ + TEST_P( "ldr"size" r14, [r",1, 256, ", #-128]!") \ + TEST_PR("ldr"size".w r0, [r",1, 0,", r",2, 4,"]") \ + TEST_PR("ldr"size" r14, [r",10,0,", r",11,4,", lsl #1]") \ + TEST_X( "ldr"size".w r0, 3f", \ + ".align 3 \n\t" \ + "3: .word "__stringify(VAL1)) \ + TEST_X( "ldr"size".w r14, 3f", \ + ".align 3 \n\t" \ + "3: .word "__stringify(VAL2)) \ + TEST( "ldr"size".w r7, 3b") \ + TEST( "ldr"size".w r7, [sp, #24]") \ + TEST_P( "ldr"size".w r0, [r",0,0, "]") \ + TEST_UNSUPPORTED("ldr"size"t r0, [r1, #4]") + + SINGLE_LOAD("b") + SINGLE_LOAD("sb") + SINGLE_LOAD("h") + SINGLE_LOAD("sh") + SINGLE_LOAD("") + + TEST_BF_P("ldr pc, [r",14, 15*4,"]") + TEST_P( "ldr sp, [r",14, 13*4,"]") + TEST_BF_R("ldr pc, [sp, r",14, 15*4,"]") + TEST_R( "ldr sp, [sp, r",14, 13*4,"]") + TEST_THUMB_TO_ARM_INTERWORK_P("ldr pc, [r",0,0,", #15*4]") + TEST_SUPPORTED("ldr sp, 99f") + TEST_SUPPORTED("ldr pc, 99f") + + TEST_UNSUPPORTED(".short 0xf854,0x700d @ ldr r7, [r4, sp]") + TEST_UNSUPPORTED(".short 0xf854,0x700f @ ldr r7, [r4, pc]") + TEST_UNSUPPORTED(".short 0xf814,0x700d @ ldrb r7, [r4, sp]") + TEST_UNSUPPORTED(".short 0xf814,0x700f @ ldrb r7, [r4, pc]") + TEST_UNSUPPORTED(".short 0xf89f,0xd004 @ ldrb sp, 99f") + TEST_UNSUPPORTED(".short 0xf814,0xd008 @ ldrb sp, [r4, r8]") + TEST_UNSUPPORTED(".short 0xf894,0xd000 @ ldrb sp, [r4]") + + TEST_UNSUPPORTED(".short 0xf860,0x0000") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xf9ff,0xffff") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xf950,0x0000") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xf95f,0xffff") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xf800,0x0800") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xf97f,0xfaff") /* Unallocated space */ + + TEST( "pli [pc, #4]") + TEST( "pli [pc, #-4]") + TEST( "pld [pc, #4]") + TEST( "pld [pc, #-4]") + + TEST_P( "pld [r",0,-1024,", #1024]") + TEST( ".short 0xf8b0,0xf400 @ pldw [r0, #1024]") + TEST_P( "pli [r",4, 0b,", #1024]") + TEST_P( "pld [r",7, 120,", #-120]") + TEST( ".short 0xf837,0xfc78 @ pldw [r7, #-120]") + TEST_P( "pli [r",11,120,", #-120]") + TEST( "pld [sp, #0]") + + TEST_PR("pld [r",7, 24, ", r",0, 16,"]") + TEST_PR("pld [r",8, 24, ", r",12,16,", lsl #3]") + TEST_SUPPORTED(".short 0xf837,0xf000 @ pldw [r7, r0]") + TEST_SUPPORTED(".short 0xf838,0xf03c @ pldw [r8, r12, lsl #3]"); + TEST_RR("pli [r",12,0b,", r",0, 16,"]") + TEST_RR("pli [r",0, 0b,", r",12,16,", lsl #3]") + TEST_R( "pld [sp, r",1, 16,"]") + TEST_UNSUPPORTED(".short 0xf817,0xf00d @pld [r7, sp]") + TEST_UNSUPPORTED(".short 0xf817,0xf00f @pld [r7, pc]") + + TEST_GROUP("Data-processing (register)") + +#define SHIFTS32(op) \ + TEST_RR(op" r0, r",1, VAL1,", r",2, 3, "") \ + TEST_RR(op" r14, r",12,VAL2,", r",11,10,"") + + SHIFTS32("lsl") + SHIFTS32("lsls") + SHIFTS32("lsr") + SHIFTS32("lsrs") + SHIFTS32("asr") + SHIFTS32("asrs") + SHIFTS32("ror") + SHIFTS32("rors") + + TEST_UNSUPPORTED(".short 0xfa01,0xff02 @ lsl pc, r1, r2") + TEST_UNSUPPORTED(".short 0xfa01,0xfd02 @ lsl sp, r1, r2") + TEST_UNSUPPORTED(".short 0xfa0f,0xf002 @ lsl r0, pc, r2") + TEST_UNSUPPORTED(".short 0xfa0d,0xf002 @ lsl r0, sp, r2") + TEST_UNSUPPORTED(".short 0xfa01,0xf00f @ lsl r0, r1, pc") + TEST_UNSUPPORTED(".short 0xfa01,0xf00d @ lsl r0, r1, sp") + + TEST_RR( "sxtah r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "sxtah r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "sxth r8, r",7, HH1,"") + + TEST_UNSUPPORTED(".short 0xfa0f,0xff87 @ sxth pc, r7"); + TEST_UNSUPPORTED(".short 0xfa0f,0xfd87 @ sxth sp, r7"); + TEST_UNSUPPORTED(".short 0xfa0f,0xf88f @ sxth r8, pc"); + TEST_UNSUPPORTED(".short 0xfa0f,0xf88d @ sxth r8, sp"); + + TEST_RR( "uxtah r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uxtah r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "uxth r8, r",7, HH1,"") + + TEST_RR( "sxtab16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "sxtab16 r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "sxtb16 r8, r",7, HH1,"") + + TEST_RR( "uxtab16 r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uxtab16 r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "uxtb16 r8, r",7, HH1,"") + + TEST_RR( "sxtab r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "sxtab r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "sxtb r8, r",7, HH1,"") + + TEST_RR( "uxtab r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "uxtab r14,r",12, HH2,", r",10,HH1,", ror #8") + TEST_R( "uxtb r8, r",7, HH1,"") + + TEST_UNSUPPORTED(".short 0xfa60,0x00f0") + TEST_UNSUPPORTED(".short 0xfa7f,0xffff") + +#define PARALLEL_ADD_SUB(op) \ + TEST_RR( op"add16 r0, r",0, HH1,", r",1, HH2,"") \ + TEST_RR( op"add16 r14, r",12,HH2,", r",10,HH1,"") \ + TEST_RR( op"asx r0, r",0, HH1,", r",1, HH2,"") \ + TEST_RR( op"asx r14, r",12,HH2,", r",10,HH1,"") \ + TEST_RR( op"sax r0, r",0, HH1,", r",1, HH2,"") \ + TEST_RR( op"sax r14, r",12,HH2,", r",10,HH1,"") \ + TEST_RR( op"sub16 r0, r",0, HH1,", r",1, HH2,"") \ + TEST_RR( op"sub16 r14, r",12,HH2,", r",10,HH1,"") \ + TEST_RR( op"add8 r0, r",0, HH1,", r",1, HH2,"") \ + TEST_RR( op"add8 r14, r",12,HH2,", r",10,HH1,"") \ + TEST_RR( op"sub8 r0, r",0, HH1,", r",1, HH2,"") \ + TEST_RR( op"sub8 r14, r",12,HH2,", r",10,HH1,"") + + TEST_GROUP("Parallel addition and subtraction, signed") + + PARALLEL_ADD_SUB("s") + PARALLEL_ADD_SUB("q") + PARALLEL_ADD_SUB("sh") + + TEST_GROUP("Parallel addition and subtraction, unsigned") + + PARALLEL_ADD_SUB("u") + PARALLEL_ADD_SUB("uq") + PARALLEL_ADD_SUB("uh") + + TEST_GROUP("Miscellaneous operations") + + TEST_RR("qadd r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR("qadd lr, r",9, VAL2,", r",8, VAL1,"") + TEST_RR("qsub r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR("qsub lr, r",9, VAL2,", r",8, VAL1,"") + TEST_RR("qdadd r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR("qdadd lr, r",9, VAL2,", r",8, VAL1,"") + TEST_RR("qdsub r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR("qdsub lr, r",9, VAL2,", r",8, VAL1,"") + + TEST_R("rev.w r0, r",0, VAL1,"") + TEST_R("rev r14, r",12, VAL2,"") + TEST_R("rev16.w r0, r",0, VAL1,"") + TEST_R("rev16 r14, r",12, VAL2,"") + TEST_R("rbit r0, r",0, VAL1,"") + TEST_R("rbit r14, r",12, VAL2,"") + TEST_R("revsh.w r0, r",0, VAL1,"") + TEST_R("revsh r14, r",12, VAL2,"") + + TEST_UNSUPPORTED(".short 0xfa9c,0xff8c @ rev pc, r12"); + TEST_UNSUPPORTED(".short 0xfa9c,0xfd8c @ rev sp, r12"); + TEST_UNSUPPORTED(".short 0xfa9f,0xfe8f @ rev r14, pc"); + TEST_UNSUPPORTED(".short 0xfa9d,0xfe8d @ rev r14, sp"); + + TEST_RR("sel r0, r",0, VAL1,", r",1, VAL2,"") + TEST_RR("sel r14, r",12,VAL1,", r",10, VAL2,"") + + TEST_R("clz r0, r",0, 0x0,"") + TEST_R("clz r7, r",14,0x1,"") + TEST_R("clz lr, r",7, 0xffffffff,"") + + TEST_UNSUPPORTED(".short 0xfa80,0xf030") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xfaff,0xff7f") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xfab0,0xf000") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xfaff,0xff7f") /* Unallocated space */ + + TEST_GROUP("Multiply, multiply accumulate, and absolute difference operations") + + TEST_RR( "mul r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "mul r7, r",8, VAL2,", r",9, VAL2,"") + TEST_UNSUPPORTED(".short 0xfb08,0xff09 @ mul pc, r8, r9") + TEST_UNSUPPORTED(".short 0xfb08,0xfd09 @ mul sp, r8, r9") + TEST_UNSUPPORTED(".short 0xfb0f,0xf709 @ mul r7, pc, r9") + TEST_UNSUPPORTED(".short 0xfb0d,0xf709 @ mul r7, sp, r9") + TEST_UNSUPPORTED(".short 0xfb08,0xf70f @ mul r7, r8, pc") + TEST_UNSUPPORTED(".short 0xfb08,0xf70d @ mul r7, r8, sp") + + TEST_RRR( "mla r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "mla r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_UNSUPPORTED(".short 0xfb08,0xaf09 @ mla pc, r8, r9, r10"); + TEST_UNSUPPORTED(".short 0xfb08,0xad09 @ mla sp, r8, r9, r10"); + TEST_UNSUPPORTED(".short 0xfb0f,0xa709 @ mla r7, pc, r9, r10"); + TEST_UNSUPPORTED(".short 0xfb0d,0xa709 @ mla r7, sp, r9, r10"); + TEST_UNSUPPORTED(".short 0xfb08,0xa70f @ mla r7, r8, pc, r10"); + TEST_UNSUPPORTED(".short 0xfb08,0xa70d @ mla r7, r8, sp, r10"); + TEST_UNSUPPORTED(".short 0xfb08,0xd709 @ mla r7, r8, r9, sp"); + + TEST_RRR( "mls r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "mls r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + + TEST_RRR( "smlabb r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlabb r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RRR( "smlatb r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlatb r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RRR( "smlabt r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlabt r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RRR( "smlatt r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlatt r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RR( "smulbb r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smulbb r7, r",8, VAL3,", r",9, VAL1,"") + TEST_RR( "smultb r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smultb r7, r",8, VAL3,", r",9, VAL1,"") + TEST_RR( "smulbt r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smulbt r7, r",8, VAL3,", r",9, VAL1,"") + TEST_RR( "smultt r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smultt r7, r",8, VAL3,", r",9, VAL1,"") + + TEST_RRR( "smlad r0, r",0, HH1,", r",1, HH2,", r",2, VAL1,"") + TEST_RRR( "smlad r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"") + TEST_RRR( "smladx r0, r",0, HH1,", r",1, HH2,", r",2, VAL1,"") + TEST_RRR( "smladx r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"") + TEST_RR( "smuad r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "smuad r14, r",12,HH2,", r",10,HH1,"") + TEST_RR( "smuadx r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "smuadx r14, r",12,HH2,", r",10,HH1,"") + + TEST_RRR( "smlawb r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlawb r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RRR( "smlawt r0, r",1, VAL1,", r",2, VAL2,", r",3, VAL3,"") + TEST_RRR( "smlawt r7, r",8, VAL3,", r",9, VAL1,", r",10, VAL2,"") + TEST_RR( "smulwb r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smulwb r7, r",8, VAL3,", r",9, VAL1,"") + TEST_RR( "smulwt r0, r",1, VAL1,", r",2, VAL2,"") + TEST_RR( "smulwt r7, r",8, VAL3,", r",9, VAL1,"") + + TEST_RRR( "smlsd r0, r",0, HH1,", r",1, HH2,", r",2, VAL1,"") + TEST_RRR( "smlsd r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"") + TEST_RRR( "smlsdx r0, r",0, HH1,", r",1, HH2,", r",2, VAL1,"") + TEST_RRR( "smlsdx r14, r",12,HH2,", r",10,HH1,", r",8, VAL2,"") + TEST_RR( "smusd r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "smusd r14, r",12,HH2,", r",10,HH1,"") + TEST_RR( "smusdx r0, r",0, HH1,", r",1, HH2,"") + TEST_RR( "smusdx r14, r",12,HH2,", r",10,HH1,"") + + TEST_RRR( "smmla r0, r",0, VAL1,", r",1, VAL2,", r",2, VAL1,"") + TEST_RRR( "smmla r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"") + TEST_RRR( "smmlar r0, r",0, VAL1,", r",1, VAL2,", r",2, VAL1,"") + TEST_RRR( "smmlar r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"") + TEST_RR( "smmul r0, r",0, VAL1,", r",1, VAL2,"") + TEST_RR( "smmul r14, r",12,VAL2,", r",10,VAL1,"") + TEST_RR( "smmulr r0, r",0, VAL1,", r",1, VAL2,"") + TEST_RR( "smmulr r14, r",12,VAL2,", r",10,VAL1,"") + + TEST_RRR( "smmls r0, r",0, VAL1,", r",1, VAL2,", r",2, VAL1,"") + TEST_RRR( "smmls r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"") + TEST_RRR( "smmlsr r0, r",0, VAL1,", r",1, VAL2,", r",2, VAL1,"") + TEST_RRR( "smmlsr r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL2,"") + + TEST_RRR( "usada8 r0, r",0, VAL1,", r",1, VAL2,", r",2, VAL3,"") + TEST_RRR( "usada8 r14, r",12,VAL2,", r",10,VAL1,", r",8, VAL3,"") + TEST_RR( "usad8 r0, r",0, VAL1,", r",1, VAL2,"") + TEST_RR( "usad8 r14, r",12,VAL2,", r",10,VAL1,"") + + TEST_UNSUPPORTED(".short 0xfb00,0xf010") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xfb0f,0xff1f") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xfb70,0xf010") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xfb7f,0xff1f") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xfb70,0x0010") /* Unallocated space */ + TEST_UNSUPPORTED(".short 0xfb7f,0xff1f") /* Unallocated space */ + + TEST_GROUP("Long multiply, long multiply accumulate, and divide") + + TEST_RR( "smull r0, r1, r",2, VAL1,", r",3, VAL2,"") + TEST_RR( "smull r7, r8, r",9, VAL2,", r",10, VAL1,"") + TEST_UNSUPPORTED(".short 0xfb89,0xf80a @ smull pc, r8, r9, r10"); + TEST_UNSUPPORTED(".short 0xfb89,0xd80a @ smull sp, r8, r9, r10"); + TEST_UNSUPPORTED(".short 0xfb89,0x7f0a @ smull r7, pc, r9, r10"); + TEST_UNSUPPORTED(".short 0xfb89,0x7d0a @ smull r7, sp, r9, r10"); + TEST_UNSUPPORTED(".short 0xfb8f,0x780a @ smull r7, r8, pc, r10"); + TEST_UNSUPPORTED(".short 0xfb8d,0x780a @ smull r7, r8, sp, r10"); + TEST_UNSUPPORTED(".short 0xfb89,0x780f @ smull r7, r8, r9, pc"); + TEST_UNSUPPORTED(".short 0xfb89,0x780d @ smull r7, r8, r9, sp"); + + TEST_RR( "umull r0, r1, r",2, VAL1,", r",3, VAL2,"") + TEST_RR( "umull r7, r8, r",9, VAL2,", r",10, VAL1,"") + + TEST_RRRR( "smlal r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "smlal r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + + TEST_RRRR( "smlalbb r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "smlalbb r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRRR( "smlalbt r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "smlalbt r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRRR( "smlaltb r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "smlaltb r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRRR( "smlaltt r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "smlaltt r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + + TEST_RRRR( "smlald r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2) + TEST_RRRR( "smlald r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1) + TEST_RRRR( "smlaldx r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2) + TEST_RRRR( "smlaldx r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1) + + TEST_RRRR( "smlsld r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2) + TEST_RRRR( "smlsld r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1) + TEST_RRRR( "smlsldx r",0, VAL1,", r",1, VAL2, ", r",0, HH1,", r",1, HH2) + TEST_RRRR( "smlsldx r",11,VAL2,", r",10,VAL1, ", r",9, HH2,", r",8, HH1) + + TEST_RRRR( "umlal r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "umlal r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + TEST_RRRR( "umaal r",0, VAL1,", r",1, VAL2,", r",2, VAL3,", r",3, VAL4) + TEST_RRRR( "umaal r",8, VAL4,", r",9, VAL1,", r",10,VAL2,", r",11,VAL3) + + TEST_GROUP("Coprocessor instructions") + + TEST_UNSUPPORTED(".short 0xfc00,0x0000") + TEST_UNSUPPORTED(".short 0xffff,0xffff") + + TEST_GROUP("Testing instructions in IT blocks") + + TEST_ITBLOCK("sub.w r0, r0") + + verbose("\n"); +} + diff --git a/arch/arm/kernel/kprobes-test.c b/arch/arm/kernel/kprobes-test.c new file mode 100644 index 000000000000..e17cdd6d90d8 --- /dev/null +++ b/arch/arm/kernel/kprobes-test.c @@ -0,0 +1,1748 @@ +/* + * arch/arm/kernel/kprobes-test.c + * + * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * This file contains test code for ARM kprobes. + * + * The top level function run_all_tests() executes tests for all of the + * supported instruction sets: ARM, 16-bit Thumb, and 32-bit Thumb. These tests + * fall into two categories; run_api_tests() checks basic functionality of the + * kprobes API, and run_test_cases() is a comprehensive test for kprobes + * instruction decoding and simulation. + * + * run_test_cases() first checks the kprobes decoding table for self consistency + * (using table_test()) then executes a series of test cases for each of the CPU + * instruction forms. coverage_start() and coverage_end() are used to verify + * that these test cases cover all of the possible combinations of instructions + * described by the kprobes decoding tables. + * + * The individual test cases are in kprobes-test-arm.c and kprobes-test-thumb.c + * which use the macros defined in kprobes-test.h. The rest of this + * documentation will describe the operation of the framework used by these + * test cases. + */ + +/* + * TESTING METHODOLOGY + * ------------------- + * + * The methodology used to test an ARM instruction 'test_insn' is to use + * inline assembler like: + * + * test_before: nop + * test_case: test_insn + * test_after: nop + * + * When the test case is run a kprobe is placed of each nop. The + * post-handler of the test_before probe is used to modify the saved CPU + * register context to that which we require for the test case. The + * pre-handler of the of the test_after probe saves a copy of the CPU + * register context. In this way we can execute test_insn with a specific + * register context and see the results afterwards. + * + * To actually test the kprobes instruction emulation we perform the above + * step a second time but with an additional kprobe on the test_case + * instruction itself. If the emulation is accurate then the results seen + * by the test_after probe will be identical to the first run which didn't + * have a probe on test_case. + * + * Each test case is run several times with a variety of variations in the + * flags value of stored in CPSR, and for Thumb code, different ITState. + * + * For instructions which can modify PC, a second test_after probe is used + * like this: + * + * test_before: nop + * test_case: test_insn + * test_after: nop + * b test_done + * test_after2: nop + * test_done: + * + * The test case is constructed such that test_insn branches to + * test_after2, or, if testing a conditional instruction, it may just + * continue to test_after. The probes inserted at both locations let us + * determine which happened. A similar approach is used for testing + * backwards branches... + * + * b test_before + * b test_done @ helps to cope with off by 1 branches + * test_after2: nop + * b test_done + * test_before: nop + * test_case: test_insn + * test_after: nop + * test_done: + * + * The macros used to generate the assembler instructions describe above + * are TEST_INSTRUCTION, TEST_BRANCH_F (branch forwards) and TEST_BRANCH_B + * (branch backwards). In these, the local variables numbered 1, 50, 2 and + * 99 represent: test_before, test_case, test_after2 and test_done. + * + * FRAMEWORK + * --------- + * + * Each test case is wrapped between the pair of macros TESTCASE_START and + * TESTCASE_END. As well as performing the inline assembler boilerplate, + * these call out to the kprobes_test_case_start() and + * kprobes_test_case_end() functions which drive the execution of the test + * case. The specific arguments to use for each test case are stored as + * inline data constructed using the various TEST_ARG_* macros. Putting + * this all together, a simple test case may look like: + * + * TESTCASE_START("Testing mov r0, r7") + * TEST_ARG_REG(7, 0x12345678) // Set r7=0x12345678 + * TEST_ARG_END("") + * TEST_INSTRUCTION("mov r0, r7") + * TESTCASE_END + * + * Note, in practice the single convenience macro TEST_R would be used for this + * instead. + * + * The above would expand to assembler looking something like: + * + * @ TESTCASE_START + * bl __kprobes_test_case_start + * @ start of inline data... + * .ascii "mov r0, r7" @ text title for test case + * .byte 0 + * .align 2 + * + * @ TEST_ARG_REG + * .byte ARG_TYPE_REG + * .byte 7 + * .short 0 + * .word 0x1234567 + * + * @ TEST_ARG_END + * .byte ARG_TYPE_END + * .byte TEST_ISA @ flags, including ISA being tested + * .short 50f-0f @ offset of 'test_before' + * .short 2f-0f @ offset of 'test_after2' (if relevent) + * .short 99f-0f @ offset of 'test_done' + * @ start of test case code... + * 0: + * .code TEST_ISA @ switch to ISA being tested + * + * @ TEST_INSTRUCTION + * 50: nop @ location for 'test_before' probe + * 1: mov r0, r7 @ the test case instruction 'test_insn' + * nop @ location for 'test_after' probe + * + * // TESTCASE_END + * 2: + * 99: bl __kprobes_test_case_end_##TEST_ISA + * .code NONMAL_ISA + * + * When the above is execute the following happens... + * + * __kprobes_test_case_start() is an assembler wrapper which sets up space + * for a stack buffer and calls the C function kprobes_test_case_start(). + * This C function will do some initial processing of the inline data and + * setup some global state. It then inserts the test_before and test_after + * kprobes and returns a value which causes the assembler wrapper to jump + * to the start of the test case code, (local label '0'). + * + * When the test case code executes, the test_before probe will be hit and + * test_before_post_handler will call setup_test_context(). This fills the + * stack buffer and CPU registers with a test pattern and then processes + * the test case arguments. In our example there is one TEST_ARG_REG which + * indicates that R7 should be loaded with the value 0x12345678. + * + * When the test_before probe ends, the test case continues and executes + * the "mov r0, r7" instruction. It then hits the test_after probe and the + * pre-handler for this (test_after_pre_handler) will save a copy of the + * CPU register context. This should now have R0 holding the same value as + * R7. + * + * Finally we get to the call to __kprobes_test_case_end_{32,16}. This is + * an assembler wrapper which switches back to the ISA used by the test + * code and calls the C function kprobes_test_case_end(). + * + * For each run through the test case, test_case_run_count is incremented + * by one. For even runs, kprobes_test_case_end() saves a copy of the + * register and stack buffer contents from the test case just run. It then + * inserts a kprobe on the test case instruction 'test_insn' and returns a + * value to cause the test case code to be re-run. + * + * For odd numbered runs, kprobes_test_case_end() compares the register and + * stack buffer contents to those that were saved on the previous even + * numbered run (the one without the kprobe on test_insn). These should be + * the same if the kprobe instruction simulation routine is correct. + * + * The pair of test case runs is repeated with different combinations of + * flag values in CPSR and, for Thumb, different ITState. This is + * controlled by test_context_cpsr(). + * + * BUILDING TEST CASES + * ------------------- + * + * + * As an aid to building test cases, the stack buffer is initialised with + * some special values: + * + * [SP+13*4] Contains SP+120. This can be used to test instructions + * which load a value into SP. + * + * [SP+15*4] When testing branching instructions using TEST_BRANCH_{F,B}, + * this holds the target address of the branch, 'test_after2'. + * This can be used to test instructions which load a PC value + * from memory. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/kprobes.h> + +#include "kprobes.h" +#include "kprobes-test.h" + + +#define BENCHMARKING 1 + + +/* + * Test basic API + */ + +static bool test_regs_ok; +static int test_func_instance; +static int pre_handler_called; +static int post_handler_called; +static int jprobe_func_called; +static int kretprobe_handler_called; + +#define FUNC_ARG1 0x12345678 +#define FUNC_ARG2 0xabcdef + + +#ifndef CONFIG_THUMB2_KERNEL + +long arm_func(long r0, long r1); + +static void __used __naked __arm_kprobes_test_func(void) +{ + __asm__ __volatile__ ( + ".arm \n\t" + ".type arm_func, %%function \n\t" + "arm_func: \n\t" + "adds r0, r0, r1 \n\t" + "bx lr \n\t" + ".code "NORMAL_ISA /* Back to Thumb if necessary */ + : : : "r0", "r1", "cc" + ); +} + +#else /* CONFIG_THUMB2_KERNEL */ + +long thumb16_func(long r0, long r1); +long thumb32even_func(long r0, long r1); +long thumb32odd_func(long r0, long r1); + +static void __used __naked __thumb_kprobes_test_funcs(void) +{ + __asm__ __volatile__ ( + ".type thumb16_func, %%function \n\t" + "thumb16_func: \n\t" + "adds.n r0, r0, r1 \n\t" + "bx lr \n\t" + + ".align \n\t" + ".type thumb32even_func, %%function \n\t" + "thumb32even_func: \n\t" + "adds.w r0, r0, r1 \n\t" + "bx lr \n\t" + + ".align \n\t" + "nop.n \n\t" + ".type thumb32odd_func, %%function \n\t" + "thumb32odd_func: \n\t" + "adds.w r0, r0, r1 \n\t" + "bx lr \n\t" + + : : : "r0", "r1", "cc" + ); +} + +#endif /* CONFIG_THUMB2_KERNEL */ + + +static int call_test_func(long (*func)(long, long), bool check_test_regs) +{ + long ret; + + ++test_func_instance; + test_regs_ok = false; + + ret = (*func)(FUNC_ARG1, FUNC_ARG2); + if (ret != FUNC_ARG1 + FUNC_ARG2) { + pr_err("FAIL: call_test_func: func returned %lx\n", ret); + return false; + } + + if (check_test_regs && !test_regs_ok) { + pr_err("FAIL: test regs not OK\n"); + return false; + } + + return true; +} + +static int __kprobes pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + pre_handler_called = test_func_instance; + if (regs->ARM_r0 == FUNC_ARG1 && regs->ARM_r1 == FUNC_ARG2) + test_regs_ok = true; + return 0; +} + +static void __kprobes post_handler(struct kprobe *p, struct pt_regs *regs, + unsigned long flags) +{ + post_handler_called = test_func_instance; + if (regs->ARM_r0 != FUNC_ARG1 + FUNC_ARG2 || regs->ARM_r1 != FUNC_ARG2) + test_regs_ok = false; +} + +static struct kprobe the_kprobe = { + .addr = 0, + .pre_handler = pre_handler, + .post_handler = post_handler +}; + +static int test_kprobe(long (*func)(long, long)) +{ + int ret; + + the_kprobe.addr = (kprobe_opcode_t *)func; + ret = register_kprobe(&the_kprobe); + if (ret < 0) { + pr_err("FAIL: register_kprobe failed with %d\n", ret); + return ret; + } + + ret = call_test_func(func, true); + + unregister_kprobe(&the_kprobe); + the_kprobe.flags = 0; /* Clear disable flag to allow reuse */ + + if (!ret) + return -EINVAL; + if (pre_handler_called != test_func_instance) { + pr_err("FAIL: kprobe pre_handler not called\n"); + return -EINVAL; + } + if (post_handler_called != test_func_instance) { + pr_err("FAIL: kprobe post_handler not called\n"); + return -EINVAL; + } + if (!call_test_func(func, false)) + return -EINVAL; + if (pre_handler_called == test_func_instance || + post_handler_called == test_func_instance) { + pr_err("FAIL: probe called after unregistering\n"); + return -EINVAL; + } + + return 0; +} + +static void __kprobes jprobe_func(long r0, long r1) +{ + jprobe_func_called = test_func_instance; + if (r0 == FUNC_ARG1 && r1 == FUNC_ARG2) + test_regs_ok = true; + jprobe_return(); +} + +static struct jprobe the_jprobe = { + .entry = jprobe_func, +}; + +static int test_jprobe(long (*func)(long, long)) +{ + int ret; + + the_jprobe.kp.addr = (kprobe_opcode_t *)func; + ret = register_jprobe(&the_jprobe); + if (ret < 0) { + pr_err("FAIL: register_jprobe failed with %d\n", ret); + return ret; + } + + ret = call_test_func(func, true); + + unregister_jprobe(&the_jprobe); + the_jprobe.kp.flags = 0; /* Clear disable flag to allow reuse */ + + if (!ret) + return -EINVAL; + if (jprobe_func_called != test_func_instance) { + pr_err("FAIL: jprobe handler function not called\n"); + return -EINVAL; + } + if (!call_test_func(func, false)) + return -EINVAL; + if (jprobe_func_called == test_func_instance) { + pr_err("FAIL: probe called after unregistering\n"); + return -EINVAL; + } + + return 0; +} + +static int __kprobes +kretprobe_handler(struct kretprobe_instance *ri, struct pt_regs *regs) +{ + kretprobe_handler_called = test_func_instance; + if (regs_return_value(regs) == FUNC_ARG1 + FUNC_ARG2) + test_regs_ok = true; + return 0; +} + +static struct kretprobe the_kretprobe = { + .handler = kretprobe_handler, +}; + +static int test_kretprobe(long (*func)(long, long)) +{ + int ret; + + the_kretprobe.kp.addr = (kprobe_opcode_t *)func; + ret = register_kretprobe(&the_kretprobe); + if (ret < 0) { + pr_err("FAIL: register_kretprobe failed with %d\n", ret); + return ret; + } + + ret = call_test_func(func, true); + + unregister_kretprobe(&the_kretprobe); + the_kretprobe.kp.flags = 0; /* Clear disable flag to allow reuse */ + + if (!ret) + return -EINVAL; + if (kretprobe_handler_called != test_func_instance) { + pr_err("FAIL: kretprobe handler not called\n"); + return -EINVAL; + } + if (!call_test_func(func, false)) + return -EINVAL; + if (jprobe_func_called == test_func_instance) { + pr_err("FAIL: kretprobe called after unregistering\n"); + return -EINVAL; + } + + return 0; +} + +static int run_api_tests(long (*func)(long, long)) +{ + int ret; + + pr_info(" kprobe\n"); + ret = test_kprobe(func); + if (ret < 0) + return ret; + + pr_info(" jprobe\n"); + ret = test_jprobe(func); + if (ret < 0) + return ret; + + pr_info(" kretprobe\n"); + ret = test_kretprobe(func); + if (ret < 0) + return ret; + + return 0; +} + + +/* + * Benchmarking + */ + +#if BENCHMARKING + +static void __naked benchmark_nop(void) +{ + __asm__ __volatile__ ( + "nop \n\t" + "bx lr" + ); +} + +#ifdef CONFIG_THUMB2_KERNEL +#define wide ".w" +#else +#define wide +#endif + +static void __naked benchmark_pushpop1(void) +{ + __asm__ __volatile__ ( + "stmdb"wide" sp!, {r3-r11,lr} \n\t" + "ldmia"wide" sp!, {r3-r11,pc}" + ); +} + +static void __naked benchmark_pushpop2(void) +{ + __asm__ __volatile__ ( + "stmdb"wide" sp!, {r0-r8,lr} \n\t" + "ldmia"wide" sp!, {r0-r8,pc}" + ); +} + +static void __naked benchmark_pushpop3(void) +{ + __asm__ __volatile__ ( + "stmdb"wide" sp!, {r4,lr} \n\t" + "ldmia"wide" sp!, {r4,pc}" + ); +} + +static void __naked benchmark_pushpop4(void) +{ + __asm__ __volatile__ ( + "stmdb"wide" sp!, {r0,lr} \n\t" + "ldmia"wide" sp!, {r0,pc}" + ); +} + + +#ifdef CONFIG_THUMB2_KERNEL + +static void __naked benchmark_pushpop_thumb(void) +{ + __asm__ __volatile__ ( + "push.n {r0-r7,lr} \n\t" + "pop.n {r0-r7,pc}" + ); +} + +#endif + +static int __kprobes +benchmark_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + return 0; +} + +static int benchmark(void(*fn)(void)) +{ + unsigned n, i, t, t0; + + for (n = 1000; ; n *= 2) { + t0 = sched_clock(); + for (i = n; i > 0; --i) + fn(); + t = sched_clock() - t0; + if (t >= 250000000) + break; /* Stop once we took more than 0.25 seconds */ + } + return t / n; /* Time for one iteration in nanoseconds */ +}; + +static int kprobe_benchmark(void(*fn)(void), unsigned offset) +{ + struct kprobe k = { + .addr = (kprobe_opcode_t *)((uintptr_t)fn + offset), + .pre_handler = benchmark_pre_handler, + }; + + int ret = register_kprobe(&k); + if (ret < 0) { + pr_err("FAIL: register_kprobe failed with %d\n", ret); + return ret; + } + + ret = benchmark(fn); + + unregister_kprobe(&k); + return ret; +}; + +struct benchmarks { + void (*fn)(void); + unsigned offset; + const char *title; +}; + +static int run_benchmarks(void) +{ + int ret; + struct benchmarks list[] = { + {&benchmark_nop, 0, "nop"}, + /* + * benchmark_pushpop{1,3} will have the optimised + * instruction emulation, whilst benchmark_pushpop{2,4} will + * be the equivalent unoptimised instructions. + */ + {&benchmark_pushpop1, 0, "stmdb sp!, {r3-r11,lr}"}, + {&benchmark_pushpop1, 4, "ldmia sp!, {r3-r11,pc}"}, + {&benchmark_pushpop2, 0, "stmdb sp!, {r0-r8,lr}"}, + {&benchmark_pushpop2, 4, "ldmia sp!, {r0-r8,pc}"}, + {&benchmark_pushpop3, 0, "stmdb sp!, {r4,lr}"}, + {&benchmark_pushpop3, 4, "ldmia sp!, {r4,pc}"}, + {&benchmark_pushpop4, 0, "stmdb sp!, {r0,lr}"}, + {&benchmark_pushpop4, 4, "ldmia sp!, {r0,pc}"}, +#ifdef CONFIG_THUMB2_KERNEL + {&benchmark_pushpop_thumb, 0, "push.n {r0-r7,lr}"}, + {&benchmark_pushpop_thumb, 2, "pop.n {r0-r7,pc}"}, +#endif + {0} + }; + + struct benchmarks *b; + for (b = list; b->fn; ++b) { + ret = kprobe_benchmark(b->fn, b->offset); + if (ret < 0) + return ret; + pr_info(" %dns for kprobe %s\n", ret, b->title); + } + + pr_info("\n"); + return 0; +} + +#endif /* BENCHMARKING */ + + +/* + * Decoding table self-consistency tests + */ + +static const int decode_struct_sizes[NUM_DECODE_TYPES] = { + [DECODE_TYPE_TABLE] = sizeof(struct decode_table), + [DECODE_TYPE_CUSTOM] = sizeof(struct decode_custom), + [DECODE_TYPE_SIMULATE] = sizeof(struct decode_simulate), + [DECODE_TYPE_EMULATE] = sizeof(struct decode_emulate), + [DECODE_TYPE_OR] = sizeof(struct decode_or), + [DECODE_TYPE_REJECT] = sizeof(struct decode_reject) +}; + +static int table_iter(const union decode_item *table, + int (*fn)(const struct decode_header *, void *), + void *args) +{ + const struct decode_header *h = (struct decode_header *)table; + int result; + + for (;;) { + enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK; + + if (type == DECODE_TYPE_END) + return 0; + + result = fn(h, args); + if (result) + return result; + + h = (struct decode_header *) + ((uintptr_t)h + decode_struct_sizes[type]); + + } +} + +static int table_test_fail(const struct decode_header *h, const char* message) +{ + + pr_err("FAIL: kprobes test failure \"%s\" (mask %08x, value %08x)\n", + message, h->mask.bits, h->value.bits); + return -EINVAL; +} + +struct table_test_args { + const union decode_item *root_table; + u32 parent_mask; + u32 parent_value; +}; + +static int table_test_fn(const struct decode_header *h, void *args) +{ + struct table_test_args *a = (struct table_test_args *)args; + enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK; + + if (h->value.bits & ~h->mask.bits) + return table_test_fail(h, "Match value has bits not in mask"); + + if ((h->mask.bits & a->parent_mask) != a->parent_mask) + return table_test_fail(h, "Mask has bits not in parent mask"); + + if ((h->value.bits ^ a->parent_value) & a->parent_mask) + return table_test_fail(h, "Value is inconsistent with parent"); + + if (type == DECODE_TYPE_TABLE) { + struct decode_table *d = (struct decode_table *)h; + struct table_test_args args2 = *a; + args2.parent_mask = h->mask.bits; + args2.parent_value = h->value.bits; + return table_iter(d->table.table, table_test_fn, &args2); + } + + return 0; +} + +static int table_test(const union decode_item *table) +{ + struct table_test_args args = { + .root_table = table, + .parent_mask = 0, + .parent_value = 0 + }; + return table_iter(args.root_table, table_test_fn, &args); +} + + +/* + * Decoding table test coverage analysis + * + * coverage_start() builds a coverage_table which contains a list of + * coverage_entry's to match each entry in the specified kprobes instruction + * decoding table. + * + * When test cases are run, coverage_add() is called to process each case. + * This looks up the corresponding entry in the coverage_table and sets it as + * being matched, as well as clearing the regs flag appropriate for the test. + * + * After all test cases have been run, coverage_end() is called to check that + * all entries in coverage_table have been matched and that all regs flags are + * cleared. I.e. that all possible combinations of instructions described by + * the kprobes decoding tables have had a test case executed for them. + */ + +bool coverage_fail; + +#define MAX_COVERAGE_ENTRIES 256 + +struct coverage_entry { + const struct decode_header *header; + unsigned regs; + unsigned nesting; + char matched; +}; + +struct coverage_table { + struct coverage_entry *base; + unsigned num_entries; + unsigned nesting; +}; + +struct coverage_table coverage; + +#define COVERAGE_ANY_REG (1<<0) +#define COVERAGE_SP (1<<1) +#define COVERAGE_PC (1<<2) +#define COVERAGE_PCWB (1<<3) + +static const char coverage_register_lookup[16] = { + [REG_TYPE_ANY] = COVERAGE_ANY_REG | COVERAGE_SP | COVERAGE_PC, + [REG_TYPE_SAMEAS16] = COVERAGE_ANY_REG, + [REG_TYPE_SP] = COVERAGE_SP, + [REG_TYPE_PC] = COVERAGE_PC, + [REG_TYPE_NOSP] = COVERAGE_ANY_REG | COVERAGE_SP, + [REG_TYPE_NOSPPC] = COVERAGE_ANY_REG | COVERAGE_SP | COVERAGE_PC, + [REG_TYPE_NOPC] = COVERAGE_ANY_REG | COVERAGE_PC, + [REG_TYPE_NOPCWB] = COVERAGE_ANY_REG | COVERAGE_PC | COVERAGE_PCWB, + [REG_TYPE_NOPCX] = COVERAGE_ANY_REG, + [REG_TYPE_NOSPPCX] = COVERAGE_ANY_REG | COVERAGE_SP, +}; + +unsigned coverage_start_registers(const struct decode_header *h) +{ + unsigned regs = 0; + int i; + for (i = 0; i < 20; i += 4) { + int r = (h->type_regs.bits >> (DECODE_TYPE_BITS + i)) & 0xf; + regs |= coverage_register_lookup[r] << i; + } + return regs; +} + +static int coverage_start_fn(const struct decode_header *h, void *args) +{ + struct coverage_table *coverage = (struct coverage_table *)args; + enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK; + struct coverage_entry *entry = coverage->base + coverage->num_entries; + + if (coverage->num_entries == MAX_COVERAGE_ENTRIES - 1) { + pr_err("FAIL: Out of space for test coverage data"); + return -ENOMEM; + } + + ++coverage->num_entries; + + entry->header = h; + entry->regs = coverage_start_registers(h); + entry->nesting = coverage->nesting; + entry->matched = false; + + if (type == DECODE_TYPE_TABLE) { + struct decode_table *d = (struct decode_table *)h; + int ret; + ++coverage->nesting; + ret = table_iter(d->table.table, coverage_start_fn, coverage); + --coverage->nesting; + return ret; + } + + return 0; +} + +static int coverage_start(const union decode_item *table) +{ + coverage.base = kmalloc(MAX_COVERAGE_ENTRIES * + sizeof(struct coverage_entry), GFP_KERNEL); + coverage.num_entries = 0; + coverage.nesting = 0; + return table_iter(table, coverage_start_fn, &coverage); +} + +static void +coverage_add_registers(struct coverage_entry *entry, kprobe_opcode_t insn) +{ + int regs = entry->header->type_regs.bits >> DECODE_TYPE_BITS; + int i; + for (i = 0; i < 20; i += 4) { + enum decode_reg_type reg_type = (regs >> i) & 0xf; + int reg = (insn >> i) & 0xf; + int flag; + + if (!reg_type) + continue; + + if (reg == 13) + flag = COVERAGE_SP; + else if (reg == 15) + flag = COVERAGE_PC; + else + flag = COVERAGE_ANY_REG; + entry->regs &= ~(flag << i); + + switch (reg_type) { + + case REG_TYPE_NONE: + case REG_TYPE_ANY: + case REG_TYPE_SAMEAS16: + break; + + case REG_TYPE_SP: + if (reg != 13) + return; + break; + + case REG_TYPE_PC: + if (reg != 15) + return; + break; + + case REG_TYPE_NOSP: + if (reg == 13) + return; + break; + + case REG_TYPE_NOSPPC: + case REG_TYPE_NOSPPCX: + if (reg == 13 || reg == 15) + return; + break; + + case REG_TYPE_NOPCWB: + if (!is_writeback(insn)) + break; + if (reg == 15) { + entry->regs &= ~(COVERAGE_PCWB << i); + return; + } + break; + + case REG_TYPE_NOPC: + case REG_TYPE_NOPCX: + if (reg == 15) + return; + break; + } + + } +} + +static void coverage_add(kprobe_opcode_t insn) +{ + struct coverage_entry *entry = coverage.base; + struct coverage_entry *end = coverage.base + coverage.num_entries; + bool matched = false; + unsigned nesting = 0; + + for (; entry < end; ++entry) { + const struct decode_header *h = entry->header; + enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK; + + if (entry->nesting > nesting) + continue; /* Skip sub-table we didn't match */ + + if (entry->nesting < nesting) + break; /* End of sub-table we were scanning */ + + if (!matched) { + if ((insn & h->mask.bits) != h->value.bits) + continue; + entry->matched = true; + } + + switch (type) { + + case DECODE_TYPE_TABLE: + ++nesting; + break; + + case DECODE_TYPE_CUSTOM: + case DECODE_TYPE_SIMULATE: + case DECODE_TYPE_EMULATE: + coverage_add_registers(entry, insn); + return; + + case DECODE_TYPE_OR: + matched = true; + break; + + case DECODE_TYPE_REJECT: + default: + return; + } + + } +} + +static void coverage_end(void) +{ + struct coverage_entry *entry = coverage.base; + struct coverage_entry *end = coverage.base + coverage.num_entries; + + for (; entry < end; ++entry) { + u32 mask = entry->header->mask.bits; + u32 value = entry->header->value.bits; + + if (entry->regs) { + pr_err("FAIL: Register test coverage missing for %08x %08x (%05x)\n", + mask, value, entry->regs); + coverage_fail = true; + } + if (!entry->matched) { + pr_err("FAIL: Test coverage entry missing for %08x %08x\n", + mask, value); + coverage_fail = true; + } + } + + kfree(coverage.base); +} + + +/* + * Framework for instruction set test cases + */ + +void __naked __kprobes_test_case_start(void) +{ + __asm__ __volatile__ ( + "stmdb sp!, {r4-r11} \n\t" + "sub sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t" + "bic r0, lr, #1 @ r0 = inline title string \n\t" + "mov r1, sp \n\t" + "bl kprobes_test_case_start \n\t" + "bx r0 \n\t" + ); +} + +#ifndef CONFIG_THUMB2_KERNEL + +void __naked __kprobes_test_case_end_32(void) +{ + __asm__ __volatile__ ( + "mov r4, lr \n\t" + "bl kprobes_test_case_end \n\t" + "cmp r0, #0 \n\t" + "movne pc, r0 \n\t" + "mov r0, r4 \n\t" + "add sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t" + "ldmia sp!, {r4-r11} \n\t" + "mov pc, r0 \n\t" + ); +} + +#else /* CONFIG_THUMB2_KERNEL */ + +void __naked __kprobes_test_case_end_16(void) +{ + __asm__ __volatile__ ( + "mov r4, lr \n\t" + "bl kprobes_test_case_end \n\t" + "cmp r0, #0 \n\t" + "bxne r0 \n\t" + "mov r0, r4 \n\t" + "add sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t" + "ldmia sp!, {r4-r11} \n\t" + "bx r0 \n\t" + ); +} + +void __naked __kprobes_test_case_end_32(void) +{ + __asm__ __volatile__ ( + ".arm \n\t" + "orr lr, lr, #1 @ will return to Thumb code \n\t" + "ldr pc, 1f \n\t" + "1: \n\t" + ".word __kprobes_test_case_end_16 \n\t" + ); +} + +#endif + + +int kprobe_test_flags; +int kprobe_test_cc_position; + +static int test_try_count; +static int test_pass_count; +static int test_fail_count; + +static struct pt_regs initial_regs; +static struct pt_regs expected_regs; +static struct pt_regs result_regs; + +static u32 expected_memory[TEST_MEMORY_SIZE/sizeof(u32)]; + +static const char *current_title; +static struct test_arg *current_args; +static u32 *current_stack; +static uintptr_t current_branch_target; + +static uintptr_t current_code_start; +static kprobe_opcode_t current_instruction; + + +#define TEST_CASE_PASSED -1 +#define TEST_CASE_FAILED -2 + +static int test_case_run_count; +static bool test_case_is_thumb; +static int test_instance; + +/* + * We ignore the state of the imprecise abort disable flag (CPSR.A) because this + * can change randomly as the kernel doesn't take care to preserve or initialise + * this across context switches. Also, with Security Extentions, the flag may + * not be under control of the kernel; for this reason we ignore the state of + * the FIQ disable flag CPSR.F as well. + */ +#define PSR_IGNORE_BITS (PSR_A_BIT | PSR_F_BIT) + +static unsigned long test_check_cc(int cc, unsigned long cpsr) +{ + unsigned long temp; + + switch (cc) { + case 0x0: /* eq */ + return cpsr & PSR_Z_BIT; + + case 0x1: /* ne */ + return (~cpsr) & PSR_Z_BIT; + + case 0x2: /* cs */ + return cpsr & PSR_C_BIT; + + case 0x3: /* cc */ + return (~cpsr) & PSR_C_BIT; + + case 0x4: /* mi */ + return cpsr & PSR_N_BIT; + + case 0x5: /* pl */ + return (~cpsr) & PSR_N_BIT; + + case 0x6: /* vs */ + return cpsr & PSR_V_BIT; + + case 0x7: /* vc */ + return (~cpsr) & PSR_V_BIT; + + case 0x8: /* hi */ + cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ + return cpsr & PSR_C_BIT; + + case 0x9: /* ls */ + cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ + return (~cpsr) & PSR_C_BIT; + + case 0xa: /* ge */ + cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + return (~cpsr) & PSR_N_BIT; + + case 0xb: /* lt */ + cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + return cpsr & PSR_N_BIT; + + case 0xc: /* gt */ + temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + temp |= (cpsr << 1); /* PSR_N_BIT |= PSR_Z_BIT */ + return (~temp) & PSR_N_BIT; + + case 0xd: /* le */ + temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + temp |= (cpsr << 1); /* PSR_N_BIT |= PSR_Z_BIT */ + return temp & PSR_N_BIT; + + case 0xe: /* al */ + case 0xf: /* unconditional */ + return true; + } + BUG(); + return false; +} + +static int is_last_scenario; +static int probe_should_run; /* 0 = no, 1 = yes, -1 = unknown */ +static int memory_needs_checking; + +static unsigned long test_context_cpsr(int scenario) +{ + unsigned long cpsr; + + probe_should_run = 1; + + /* Default case is that we cycle through 16 combinations of flags */ + cpsr = (scenario & 0xf) << 28; /* N,Z,C,V flags */ + cpsr |= (scenario & 0xf) << 16; /* GE flags */ + cpsr |= (scenario & 0x1) << 27; /* Toggle Q flag */ + + if (!test_case_is_thumb) { + /* Testing ARM code */ + probe_should_run = test_check_cc(current_instruction >> 28, cpsr) != 0; + if (scenario == 15) + is_last_scenario = true; + + } else if (kprobe_test_flags & TEST_FLAG_NO_ITBLOCK) { + /* Testing Thumb code without setting ITSTATE */ + if (kprobe_test_cc_position) { + int cc = (current_instruction >> kprobe_test_cc_position) & 0xf; + probe_should_run = test_check_cc(cc, cpsr) != 0; + } + + if (scenario == 15) + is_last_scenario = true; + + } else if (kprobe_test_flags & TEST_FLAG_FULL_ITBLOCK) { + /* Testing Thumb code with all combinations of ITSTATE */ + unsigned x = (scenario >> 4); + unsigned cond_base = x % 7; /* ITSTATE<7:5> */ + unsigned mask = x / 7 + 2; /* ITSTATE<4:0>, bits reversed */ + + if (mask > 0x1f) { + /* Finish by testing state from instruction 'itt al' */ + cond_base = 7; + mask = 0x4; + if ((scenario & 0xf) == 0xf) + is_last_scenario = true; + } + + cpsr |= cond_base << 13; /* ITSTATE<7:5> */ + cpsr |= (mask & 0x1) << 12; /* ITSTATE<4> */ + cpsr |= (mask & 0x2) << 10; /* ITSTATE<3> */ + cpsr |= (mask & 0x4) << 8; /* ITSTATE<2> */ + cpsr |= (mask & 0x8) << 23; /* ITSTATE<1> */ + cpsr |= (mask & 0x10) << 21; /* ITSTATE<0> */ + + probe_should_run = test_check_cc((cpsr >> 12) & 0xf, cpsr) != 0; + + } else { + /* Testing Thumb code with several combinations of ITSTATE */ + switch (scenario) { + case 16: /* Clear NZCV flags and 'it eq' state (false as Z=0) */ + cpsr = 0x00000800; + probe_should_run = 0; + break; + case 17: /* Set NZCV flags and 'it vc' state (false as V=1) */ + cpsr = 0xf0007800; + probe_should_run = 0; + break; + case 18: /* Clear NZCV flags and 'it ls' state (true as C=0) */ + cpsr = 0x00009800; + break; + case 19: /* Set NZCV flags and 'it cs' state (true as C=1) */ + cpsr = 0xf0002800; + is_last_scenario = true; + break; + } + } + + return cpsr; +} + +static void setup_test_context(struct pt_regs *regs) +{ + int scenario = test_case_run_count>>1; + unsigned long val; + struct test_arg *args; + int i; + + is_last_scenario = false; + memory_needs_checking = false; + + /* Initialise test memory on stack */ + val = (scenario & 1) ? VALM : ~VALM; + for (i = 0; i < TEST_MEMORY_SIZE / sizeof(current_stack[0]); ++i) + current_stack[i] = val + (i << 8); + /* Put target of branch on stack for tests which load PC from memory */ + if (current_branch_target) + current_stack[15] = current_branch_target; + /* Put a value for SP on stack for tests which load SP from memory */ + current_stack[13] = (u32)current_stack + 120; + + /* Initialise register values to their default state */ + val = (scenario & 2) ? VALR : ~VALR; + for (i = 0; i < 13; ++i) + regs->uregs[i] = val ^ (i << 8); + regs->ARM_lr = val ^ (14 << 8); + regs->ARM_cpsr &= ~(APSR_MASK | PSR_IT_MASK); + regs->ARM_cpsr |= test_context_cpsr(scenario); + + /* Perform testcase specific register setup */ + args = current_args; + for (; args[0].type != ARG_TYPE_END; ++args) + switch (args[0].type) { + case ARG_TYPE_REG: { + struct test_arg_regptr *arg = + (struct test_arg_regptr *)args; + regs->uregs[arg->reg] = arg->val; + break; + } + case ARG_TYPE_PTR: { + struct test_arg_regptr *arg = + (struct test_arg_regptr *)args; + regs->uregs[arg->reg] = + (unsigned long)current_stack + arg->val; + memory_needs_checking = true; + break; + } + case ARG_TYPE_MEM: { + struct test_arg_mem *arg = (struct test_arg_mem *)args; + current_stack[arg->index] = arg->val; + break; + } + default: + break; + } +} + +struct test_probe { + struct kprobe kprobe; + bool registered; + int hit; +}; + +static void unregister_test_probe(struct test_probe *probe) +{ + if (probe->registered) { + unregister_kprobe(&probe->kprobe); + probe->kprobe.flags = 0; /* Clear disable flag to allow reuse */ + } + probe->registered = false; +} + +static int register_test_probe(struct test_probe *probe) +{ + int ret; + + if (probe->registered) + BUG(); + + ret = register_kprobe(&probe->kprobe); + if (ret >= 0) { + probe->registered = true; + probe->hit = -1; + } + return ret; +} + +static int __kprobes +test_before_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + container_of(p, struct test_probe, kprobe)->hit = test_instance; + return 0; +} + +static void __kprobes +test_before_post_handler(struct kprobe *p, struct pt_regs *regs, + unsigned long flags) +{ + setup_test_context(regs); + initial_regs = *regs; + initial_regs.ARM_cpsr &= ~PSR_IGNORE_BITS; +} + +static int __kprobes +test_case_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + container_of(p, struct test_probe, kprobe)->hit = test_instance; + return 0; +} + +static int __kprobes +test_after_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + if (container_of(p, struct test_probe, kprobe)->hit == test_instance) + return 0; /* Already run for this test instance */ + + result_regs = *regs; + result_regs.ARM_cpsr &= ~PSR_IGNORE_BITS; + + /* Undo any changes done to SP by the test case */ + regs->ARM_sp = (unsigned long)current_stack; + + container_of(p, struct test_probe, kprobe)->hit = test_instance; + return 0; +} + +static struct test_probe test_before_probe = { + .kprobe.pre_handler = test_before_pre_handler, + .kprobe.post_handler = test_before_post_handler, +}; + +static struct test_probe test_case_probe = { + .kprobe.pre_handler = test_case_pre_handler, +}; + +static struct test_probe test_after_probe = { + .kprobe.pre_handler = test_after_pre_handler, +}; + +static struct test_probe test_after2_probe = { + .kprobe.pre_handler = test_after_pre_handler, +}; + +static void test_case_cleanup(void) +{ + unregister_test_probe(&test_before_probe); + unregister_test_probe(&test_case_probe); + unregister_test_probe(&test_after_probe); + unregister_test_probe(&test_after2_probe); +} + +static void print_registers(struct pt_regs *regs) +{ + pr_err("r0 %08lx | r1 %08lx | r2 %08lx | r3 %08lx\n", + regs->ARM_r0, regs->ARM_r1, regs->ARM_r2, regs->ARM_r3); + pr_err("r4 %08lx | r5 %08lx | r6 %08lx | r7 %08lx\n", + regs->ARM_r4, regs->ARM_r5, regs->ARM_r6, regs->ARM_r7); + pr_err("r8 %08lx | r9 %08lx | r10 %08lx | r11 %08lx\n", + regs->ARM_r8, regs->ARM_r9, regs->ARM_r10, regs->ARM_fp); + pr_err("r12 %08lx | sp %08lx | lr %08lx | pc %08lx\n", + regs->ARM_ip, regs->ARM_sp, regs->ARM_lr, regs->ARM_pc); + pr_err("cpsr %08lx\n", regs->ARM_cpsr); +} + +static void print_memory(u32 *mem, size_t size) +{ + int i; + for (i = 0; i < size / sizeof(u32); i += 4) + pr_err("%08x %08x %08x %08x\n", mem[i], mem[i+1], + mem[i+2], mem[i+3]); +} + +static size_t expected_memory_size(u32 *sp) +{ + size_t size = sizeof(expected_memory); + int offset = (uintptr_t)sp - (uintptr_t)current_stack; + if (offset > 0) + size -= offset; + return size; +} + +static void test_case_failed(const char *message) +{ + test_case_cleanup(); + + pr_err("FAIL: %s\n", message); + pr_err("FAIL: Test %s\n", current_title); + pr_err("FAIL: Scenario %d\n", test_case_run_count >> 1); +} + +static unsigned long next_instruction(unsigned long pc) +{ +#ifdef CONFIG_THUMB2_KERNEL + if ((pc & 1) && !is_wide_instruction(*(u16 *)(pc - 1))) + return pc + 2; + else +#endif + return pc + 4; +} + +static uintptr_t __used kprobes_test_case_start(const char *title, void *stack) +{ + struct test_arg *args; + struct test_arg_end *end_arg; + unsigned long test_code; + + args = (struct test_arg *)PTR_ALIGN(title + strlen(title) + 1, 4); + + current_title = title; + current_args = args; + current_stack = stack; + + ++test_try_count; + + while (args->type != ARG_TYPE_END) + ++args; + end_arg = (struct test_arg_end *)args; + + test_code = (unsigned long)(args + 1); /* Code starts after args */ + + test_case_is_thumb = end_arg->flags & ARG_FLAG_THUMB; + if (test_case_is_thumb) + test_code |= 1; + + current_code_start = test_code; + + current_branch_target = 0; + if (end_arg->branch_offset != end_arg->end_offset) + current_branch_target = test_code + end_arg->branch_offset; + + test_code += end_arg->code_offset; + test_before_probe.kprobe.addr = (kprobe_opcode_t *)test_code; + + test_code = next_instruction(test_code); + test_case_probe.kprobe.addr = (kprobe_opcode_t *)test_code; + + if (test_case_is_thumb) { + u16 *p = (u16 *)(test_code & ~1); + current_instruction = p[0]; + if (is_wide_instruction(current_instruction)) { + current_instruction <<= 16; + current_instruction |= p[1]; + } + } else { + current_instruction = *(u32 *)test_code; + } + + if (current_title[0] == '.') + verbose("%s\n", current_title); + else + verbose("%s\t@ %0*x\n", current_title, + test_case_is_thumb ? 4 : 8, + current_instruction); + + test_code = next_instruction(test_code); + test_after_probe.kprobe.addr = (kprobe_opcode_t *)test_code; + + if (kprobe_test_flags & TEST_FLAG_NARROW_INSTR) { + if (!test_case_is_thumb || + is_wide_instruction(current_instruction)) { + test_case_failed("expected 16-bit instruction"); + goto fail; + } + } else { + if (test_case_is_thumb && + !is_wide_instruction(current_instruction)) { + test_case_failed("expected 32-bit instruction"); + goto fail; + } + } + + coverage_add(current_instruction); + + if (end_arg->flags & ARG_FLAG_UNSUPPORTED) { + if (register_test_probe(&test_case_probe) < 0) + goto pass; + test_case_failed("registered probe for unsupported instruction"); + goto fail; + } + + if (end_arg->flags & ARG_FLAG_SUPPORTED) { + if (register_test_probe(&test_case_probe) >= 0) + goto pass; + test_case_failed("couldn't register probe for supported instruction"); + goto fail; + } + + if (register_test_probe(&test_before_probe) < 0) { + test_case_failed("register test_before_probe failed"); + goto fail; + } + if (register_test_probe(&test_after_probe) < 0) { + test_case_failed("register test_after_probe failed"); + goto fail; + } + if (current_branch_target) { + test_after2_probe.kprobe.addr = + (kprobe_opcode_t *)current_branch_target; + if (register_test_probe(&test_after2_probe) < 0) { + test_case_failed("register test_after2_probe failed"); + goto fail; + } + } + + /* Start first run of test case */ + test_case_run_count = 0; + ++test_instance; + return current_code_start; +pass: + test_case_run_count = TEST_CASE_PASSED; + return (uintptr_t)test_after_probe.kprobe.addr; +fail: + test_case_run_count = TEST_CASE_FAILED; + return (uintptr_t)test_after_probe.kprobe.addr; +} + +static bool check_test_results(void) +{ + size_t mem_size = 0; + u32 *mem = 0; + + if (memcmp(&expected_regs, &result_regs, sizeof(expected_regs))) { + test_case_failed("registers differ"); + goto fail; + } + + if (memory_needs_checking) { + mem = (u32 *)result_regs.ARM_sp; + mem_size = expected_memory_size(mem); + if (memcmp(expected_memory, mem, mem_size)) { + test_case_failed("test memory differs"); + goto fail; + } + } + + return true; + +fail: + pr_err("initial_regs:\n"); + print_registers(&initial_regs); + pr_err("expected_regs:\n"); + print_registers(&expected_regs); + pr_err("result_regs:\n"); + print_registers(&result_regs); + + if (mem) { + pr_err("current_stack=%p\n", current_stack); + pr_err("expected_memory:\n"); + print_memory(expected_memory, mem_size); + pr_err("result_memory:\n"); + print_memory(mem, mem_size); + } + + return false; +} + +static uintptr_t __used kprobes_test_case_end(void) +{ + if (test_case_run_count < 0) { + if (test_case_run_count == TEST_CASE_PASSED) + /* kprobes_test_case_start did all the needed testing */ + goto pass; + else + /* kprobes_test_case_start failed */ + goto fail; + } + + if (test_before_probe.hit != test_instance) { + test_case_failed("test_before_handler not run"); + goto fail; + } + + if (test_after_probe.hit != test_instance && + test_after2_probe.hit != test_instance) { + test_case_failed("test_after_handler not run"); + goto fail; + } + + /* + * Even numbered test runs ran without a probe on the test case so + * we can gather reference results. The subsequent odd numbered run + * will have the probe inserted. + */ + if ((test_case_run_count & 1) == 0) { + /* Save results from run without probe */ + u32 *mem = (u32 *)result_regs.ARM_sp; + expected_regs = result_regs; + memcpy(expected_memory, mem, expected_memory_size(mem)); + + /* Insert probe onto test case instruction */ + if (register_test_probe(&test_case_probe) < 0) { + test_case_failed("register test_case_probe failed"); + goto fail; + } + } else { + /* Check probe ran as expected */ + if (probe_should_run == 1) { + if (test_case_probe.hit != test_instance) { + test_case_failed("test_case_handler not run"); + goto fail; + } + } else if (probe_should_run == 0) { + if (test_case_probe.hit == test_instance) { + test_case_failed("test_case_handler ran"); + goto fail; + } + } + + /* Remove probe for any subsequent reference run */ + unregister_test_probe(&test_case_probe); + + if (!check_test_results()) + goto fail; + + if (is_last_scenario) + goto pass; + } + + /* Do next test run */ + ++test_case_run_count; + ++test_instance; + return current_code_start; +fail: + ++test_fail_count; + goto end; +pass: + ++test_pass_count; +end: + test_case_cleanup(); + return 0; +} + + +/* + * Top level test functions + */ + +static int run_test_cases(void (*tests)(void), const union decode_item *table) +{ + int ret; + + pr_info(" Check decoding tables\n"); + ret = table_test(table); + if (ret) + return ret; + + pr_info(" Run test cases\n"); + ret = coverage_start(table); + if (ret) + return ret; + + tests(); + + coverage_end(); + return 0; +} + + +static int __init run_all_tests(void) +{ + int ret = 0; + + pr_info("Begining kprobe tests...\n"); + +#ifndef CONFIG_THUMB2_KERNEL + + pr_info("Probe ARM code\n"); + ret = run_api_tests(arm_func); + if (ret) + goto out; + + pr_info("ARM instruction simulation\n"); + ret = run_test_cases(kprobe_arm_test_cases, kprobe_decode_arm_table); + if (ret) + goto out; + +#else /* CONFIG_THUMB2_KERNEL */ + + pr_info("Probe 16-bit Thumb code\n"); + ret = run_api_tests(thumb16_func); + if (ret) + goto out; + + pr_info("Probe 32-bit Thumb code, even halfword\n"); + ret = run_api_tests(thumb32even_func); + if (ret) + goto out; + + pr_info("Probe 32-bit Thumb code, odd halfword\n"); + ret = run_api_tests(thumb32odd_func); + if (ret) + goto out; + + pr_info("16-bit Thumb instruction simulation\n"); + ret = run_test_cases(kprobe_thumb16_test_cases, + kprobe_decode_thumb16_table); + if (ret) + goto out; + + pr_info("32-bit Thumb instruction simulation\n"); + ret = run_test_cases(kprobe_thumb32_test_cases, + kprobe_decode_thumb32_table); + if (ret) + goto out; +#endif + + pr_info("Total instruction simulation tests=%d, pass=%d fail=%d\n", + test_try_count, test_pass_count, test_fail_count); + if (test_fail_count) { + ret = -EINVAL; + goto out; + } + +#if BENCHMARKING + pr_info("Benchmarks\n"); + ret = run_benchmarks(); + if (ret) + goto out; +#endif + +#if __LINUX_ARM_ARCH__ >= 7 + /* We are able to run all test cases so coverage should be complete */ + if (coverage_fail) { + pr_err("FAIL: Test coverage checks failed\n"); + ret = -EINVAL; + goto out; + } +#endif + +out: + if (ret == 0) + pr_info("Finished kprobe tests OK\n"); + else + pr_err("kprobe tests failed\n"); + + return ret; +} + + +/* + * Module setup + */ + +#ifdef MODULE + +static void __exit kprobe_test_exit(void) +{ +} + +module_init(run_all_tests) +module_exit(kprobe_test_exit) +MODULE_LICENSE("GPL"); + +#else /* !MODULE */ + +late_initcall(run_all_tests); + +#endif diff --git a/arch/arm/kernel/kprobes-test.h b/arch/arm/kernel/kprobes-test.h new file mode 100644 index 000000000000..0dc5d77b9356 --- /dev/null +++ b/arch/arm/kernel/kprobes-test.h @@ -0,0 +1,392 @@ +/* + * arch/arm/kernel/kprobes-test.h + * + * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define VERBOSE 0 /* Set to '1' for more logging of test cases */ + +#ifdef CONFIG_THUMB2_KERNEL +#define NORMAL_ISA "16" +#else +#define NORMAL_ISA "32" +#endif + + +/* Flags used in kprobe_test_flags */ +#define TEST_FLAG_NO_ITBLOCK (1<<0) +#define TEST_FLAG_FULL_ITBLOCK (1<<1) +#define TEST_FLAG_NARROW_INSTR (1<<2) + +extern int kprobe_test_flags; +extern int kprobe_test_cc_position; + + +#define TEST_MEMORY_SIZE 256 + + +/* + * Test case structures. + * + * The arguments given to test cases can be one of three types. + * + * ARG_TYPE_REG + * Load a register with the given value. + * + * ARG_TYPE_PTR + * Load a register with a pointer into the stack buffer (SP + given value). + * + * ARG_TYPE_MEM + * Store the given value into the stack buffer at [SP+index]. + * + */ + +#define ARG_TYPE_END 0 +#define ARG_TYPE_REG 1 +#define ARG_TYPE_PTR 2 +#define ARG_TYPE_MEM 3 + +#define ARG_FLAG_UNSUPPORTED 0x01 +#define ARG_FLAG_SUPPORTED 0x02 +#define ARG_FLAG_THUMB 0x10 /* Must be 16 so TEST_ISA can be used */ +#define ARG_FLAG_ARM 0x20 /* Must be 32 so TEST_ISA can be used */ + +struct test_arg { + u8 type; /* ARG_TYPE_x */ + u8 _padding[7]; +}; + +struct test_arg_regptr { + u8 type; /* ARG_TYPE_REG or ARG_TYPE_PTR */ + u8 reg; + u8 _padding[2]; + u32 val; +}; + +struct test_arg_mem { + u8 type; /* ARG_TYPE_MEM */ + u8 index; + u8 _padding[2]; + u32 val; +}; + +struct test_arg_end { + u8 type; /* ARG_TYPE_END */ + u8 flags; /* ARG_FLAG_x */ + u16 code_offset; + u16 branch_offset; + u16 end_offset; +}; + + +/* + * Building blocks for test cases. + * + * Each test case is wrapped between TESTCASE_START and TESTCASE_END. + * + * To specify arguments for a test case the TEST_ARG_{REG,PTR,MEM} macros are + * used followed by a terminating TEST_ARG_END. + * + * After this, the instruction to be tested is defined with TEST_INSTRUCTION. + * Or for branches, TEST_BRANCH_B and TEST_BRANCH_F (branch forwards/backwards). + * + * Some specific test cases may make use of other custom constructs. + */ + +#if VERBOSE +#define verbose(fmt, ...) pr_info(fmt, ##__VA_ARGS__) +#else +#define verbose(fmt, ...) +#endif + +#define TEST_GROUP(title) \ + verbose("\n"); \ + verbose(title"\n"); \ + verbose("---------------------------------------------------------\n"); + +#define TESTCASE_START(title) \ + __asm__ __volatile__ ( \ + "bl __kprobes_test_case_start \n\t" \ + /* don't use .asciz here as 'title' may be */ \ + /* multiple strings to be concatenated. */ \ + ".ascii "#title" \n\t" \ + ".byte 0 \n\t" \ + ".align 2 \n\t" + +#define TEST_ARG_REG(reg, val) \ + ".byte "__stringify(ARG_TYPE_REG)" \n\t" \ + ".byte "#reg" \n\t" \ + ".short 0 \n\t" \ + ".word "#val" \n\t" + +#define TEST_ARG_PTR(reg, val) \ + ".byte "__stringify(ARG_TYPE_PTR)" \n\t" \ + ".byte "#reg" \n\t" \ + ".short 0 \n\t" \ + ".word "#val" \n\t" + +#define TEST_ARG_MEM(index, val) \ + ".byte "__stringify(ARG_TYPE_MEM)" \n\t" \ + ".byte "#index" \n\t" \ + ".short 0 \n\t" \ + ".word "#val" \n\t" + +#define TEST_ARG_END(flags) \ + ".byte "__stringify(ARG_TYPE_END)" \n\t" \ + ".byte "TEST_ISA flags" \n\t" \ + ".short 50f-0f \n\t" \ + ".short 2f-0f \n\t" \ + ".short 99f-0f \n\t" \ + ".code "TEST_ISA" \n\t" \ + "0: \n\t" + +#define TEST_INSTRUCTION(instruction) \ + "50: nop \n\t" \ + "1: "instruction" \n\t" \ + " nop \n\t" + +#define TEST_BRANCH_F(instruction, xtra_dist) \ + TEST_INSTRUCTION(instruction) \ + ".if "#xtra_dist" \n\t" \ + " b 99f \n\t" \ + ".space "#xtra_dist" \n\t" \ + ".endif \n\t" \ + " b 99f \n\t" \ + "2: nop \n\t" + +#define TEST_BRANCH_B(instruction, xtra_dist) \ + " b 50f \n\t" \ + " b 99f \n\t" \ + "2: nop \n\t" \ + " b 99f \n\t" \ + ".if "#xtra_dist" \n\t" \ + ".space "#xtra_dist" \n\t" \ + ".endif \n\t" \ + TEST_INSTRUCTION(instruction) + +#define TESTCASE_END \ + "2: \n\t" \ + "99: \n\t" \ + " bl __kprobes_test_case_end_"TEST_ISA" \n\t" \ + ".code "NORMAL_ISA" \n\t" \ + : : \ + : "r0", "r1", "r2", "r3", "ip", "lr", "memory", "cc" \ + ); + + +/* + * Macros to define test cases. + * + * Those of the form TEST_{R,P,M}* can be used to define test cases + * which take combinations of the three basic types of arguments. E.g. + * + * TEST_R One register argument + * TEST_RR Two register arguments + * TEST_RPR A register, a pointer, then a register argument + * + * For testing instructions which may branch, there are macros TEST_BF_* + * and TEST_BB_* for branching forwards and backwards. + * + * TEST_SUPPORTED and TEST_UNSUPPORTED don't cause the code to be executed, + * the just verify that a kprobe is or is not allowed on the given instruction. + */ + +#define TEST(code) \ + TESTCASE_START(code) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code) \ + TESTCASE_END + +#define TEST_UNSUPPORTED(code) \ + TESTCASE_START(code) \ + TEST_ARG_END("|"__stringify(ARG_FLAG_UNSUPPORTED)) \ + TEST_INSTRUCTION(code) \ + TESTCASE_END + +#define TEST_SUPPORTED(code) \ + TESTCASE_START(code) \ + TEST_ARG_END("|"__stringify(ARG_FLAG_SUPPORTED)) \ + TEST_INSTRUCTION(code) \ + TESTCASE_END + +#define TEST_R(code1, reg, val, code2) \ + TESTCASE_START(code1 #reg code2) \ + TEST_ARG_REG(reg, val) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 #reg code2) \ + TESTCASE_END + +#define TEST_RR(code1, reg1, val1, code2, reg2, val2, code3) \ + TESTCASE_START(code1 #reg1 code2 #reg2 code3) \ + TEST_ARG_REG(reg1, val1) \ + TEST_ARG_REG(reg2, val2) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3) \ + TESTCASE_END + +#define TEST_RRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\ + TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4) \ + TEST_ARG_REG(reg1, val1) \ + TEST_ARG_REG(reg2, val2) \ + TEST_ARG_REG(reg3, val3) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4) \ + TESTCASE_END + +#define TEST_RRRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4, reg4, val4) \ + TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4 #reg4) \ + TEST_ARG_REG(reg1, val1) \ + TEST_ARG_REG(reg2, val2) \ + TEST_ARG_REG(reg3, val3) \ + TEST_ARG_REG(reg4, val4) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4 #reg4) \ + TESTCASE_END + +#define TEST_P(code1, reg1, val1, code2) \ + TESTCASE_START(code1 #reg1 code2) \ + TEST_ARG_PTR(reg1, val1) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 #reg1 code2) \ + TESTCASE_END + +#define TEST_PR(code1, reg1, val1, code2, reg2, val2, code3) \ + TESTCASE_START(code1 #reg1 code2 #reg2 code3) \ + TEST_ARG_PTR(reg1, val1) \ + TEST_ARG_REG(reg2, val2) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3) \ + TESTCASE_END + +#define TEST_RP(code1, reg1, val1, code2, reg2, val2, code3) \ + TESTCASE_START(code1 #reg1 code2 #reg2 code3) \ + TEST_ARG_REG(reg1, val1) \ + TEST_ARG_PTR(reg2, val2) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3) \ + TESTCASE_END + +#define TEST_PRR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\ + TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4) \ + TEST_ARG_PTR(reg1, val1) \ + TEST_ARG_REG(reg2, val2) \ + TEST_ARG_REG(reg3, val3) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4) \ + TESTCASE_END + +#define TEST_RPR(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\ + TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4) \ + TEST_ARG_REG(reg1, val1) \ + TEST_ARG_PTR(reg2, val2) \ + TEST_ARG_REG(reg3, val3) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4) \ + TESTCASE_END + +#define TEST_RRP(code1, reg1, val1, code2, reg2, val2, code3, reg3, val3, code4)\ + TESTCASE_START(code1 #reg1 code2 #reg2 code3 #reg3 code4) \ + TEST_ARG_REG(reg1, val1) \ + TEST_ARG_REG(reg2, val2) \ + TEST_ARG_PTR(reg3, val3) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 #reg1 code2 #reg2 code3 #reg3 code4) \ + TESTCASE_END + +#define TEST_BF_P(code1, reg1, val1, code2) \ + TESTCASE_START(code1 #reg1 code2) \ + TEST_ARG_PTR(reg1, val1) \ + TEST_ARG_END("") \ + TEST_BRANCH_F(code1 #reg1 code2, 0) \ + TESTCASE_END + +#define TEST_BF_X(code, xtra_dist) \ + TESTCASE_START(code) \ + TEST_ARG_END("") \ + TEST_BRANCH_F(code, xtra_dist) \ + TESTCASE_END + +#define TEST_BB_X(code, xtra_dist) \ + TESTCASE_START(code) \ + TEST_ARG_END("") \ + TEST_BRANCH_B(code, xtra_dist) \ + TESTCASE_END + +#define TEST_BF_RX(code1, reg, val, code2, xtra_dist) \ + TESTCASE_START(code1 #reg code2) \ + TEST_ARG_REG(reg, val) \ + TEST_ARG_END("") \ + TEST_BRANCH_F(code1 #reg code2, xtra_dist) \ + TESTCASE_END + +#define TEST_BB_RX(code1, reg, val, code2, xtra_dist) \ + TESTCASE_START(code1 #reg code2) \ + TEST_ARG_REG(reg, val) \ + TEST_ARG_END("") \ + TEST_BRANCH_B(code1 #reg code2, xtra_dist) \ + TESTCASE_END + +#define TEST_BF(code) TEST_BF_X(code, 0) +#define TEST_BB(code) TEST_BB_X(code, 0) + +#define TEST_BF_R(code1, reg, val, code2) TEST_BF_RX(code1, reg, val, code2, 0) +#define TEST_BB_R(code1, reg, val, code2) TEST_BB_RX(code1, reg, val, code2, 0) + +#define TEST_BF_RR(code1, reg1, val1, code2, reg2, val2, code3) \ + TESTCASE_START(code1 #reg1 code2 #reg2 code3) \ + TEST_ARG_REG(reg1, val1) \ + TEST_ARG_REG(reg2, val2) \ + TEST_ARG_END("") \ + TEST_BRANCH_F(code1 #reg1 code2 #reg2 code3, 0) \ + TESTCASE_END + +#define TEST_X(code, codex) \ + TESTCASE_START(code) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code) \ + " b 99f \n\t" \ + " "codex" \n\t" \ + TESTCASE_END + +#define TEST_RX(code1, reg, val, code2, codex) \ + TESTCASE_START(code1 #reg code2) \ + TEST_ARG_REG(reg, val) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 __stringify(reg) code2) \ + " b 99f \n\t" \ + " "codex" \n\t" \ + TESTCASE_END + +#define TEST_RRX(code1, reg1, val1, code2, reg2, val2, code3, codex) \ + TESTCASE_START(code1 #reg1 code2 #reg2 code3) \ + TEST_ARG_REG(reg1, val1) \ + TEST_ARG_REG(reg2, val2) \ + TEST_ARG_END("") \ + TEST_INSTRUCTION(code1 __stringify(reg1) code2 __stringify(reg2) code3) \ + " b 99f \n\t" \ + " "codex" \n\t" \ + TESTCASE_END + + +/* Various values used in test cases... */ +#define N(val) (val ^ 0xffffffff) +#define VAL1 0x12345678 +#define VAL2 N(VAL1) +#define VAL3 0xa5f801 +#define VAL4 N(VAL3) +#define VALM 0x456789ab +#define VALR 0xdeaddead +#define HH1 0x0123fecb +#define HH2 0xa9874567 + + +#ifdef CONFIG_THUMB2_KERNEL +void kprobe_thumb16_test_cases(void); +void kprobe_thumb32_test_cases(void); +#else +void kprobe_arm_test_cases(void); +#endif diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c index 902ca59e8b11..8f96ec778e8d 100644 --- a/arch/arm/kernel/kprobes-thumb.c +++ b/arch/arm/kernel/kprobes-thumb.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/kprobes.h> +#include <linux/module.h> #include "kprobes.h" @@ -943,6 +944,9 @@ const union decode_item kprobe_decode_thumb32_table[] = { */ DECODE_END }; +#ifdef CONFIG_ARM_KPROBES_TEST_MODULE +EXPORT_SYMBOL_GPL(kprobe_decode_thumb32_table); +#endif static void __kprobes t16_simulate_bxblx(struct kprobe *p, struct pt_regs *regs) @@ -1423,6 +1427,9 @@ const union decode_item kprobe_decode_thumb16_table[] = { DECODE_END }; +#ifdef CONFIG_ARM_KPROBES_TEST_MODULE +EXPORT_SYMBOL_GPL(kprobe_decode_thumb16_table); +#endif static unsigned long __kprobes thumb_check_cc(unsigned long cpsr) { diff --git a/arch/arm/kernel/kprobes.h b/arch/arm/kernel/kprobes.h index a6aeda0a6c7f..38945f78f9f1 100644 --- a/arch/arm/kernel/kprobes.h +++ b/arch/arm/kernel/kprobes.h @@ -413,6 +413,14 @@ struct decode_reject { DECODE_HEADER(DECODE_TYPE_REJECT, _mask, _value, 0) +#ifdef CONFIG_THUMB2_KERNEL +extern const union decode_item kprobe_decode_thumb16_table[]; +extern const union decode_item kprobe_decode_thumb32_table[]; +#else +extern const union decode_item kprobe_decode_arm_table[]; +#endif + + int kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi, const union decode_item *table, bool thumb16); diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index e59bbd496c39..c1b4463dcc83 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -32,6 +32,24 @@ static atomic_t waiting_for_crash_ipi; int machine_kexec_prepare(struct kimage *image) { + unsigned long page_list; + void *reboot_code_buffer; + page_list = image->head & PAGE_MASK; + + reboot_code_buffer = page_address(image->control_code_page); + + /* Prepare parameters for reboot_code_buffer*/ + kexec_start_address = image->start; + kexec_indirection_page = page_list; + kexec_mach_type = machine_arch_type; + kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET; + + /* copy our kernel relocation code to the control code page */ + memcpy(reboot_code_buffer, + relocate_new_kernel, relocate_new_kernel_size); + + flush_icache_range((unsigned long) reboot_code_buffer, + (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE); return 0; } @@ -82,31 +100,14 @@ void (*kexec_reinit)(void); void machine_kexec(struct kimage *image) { - unsigned long page_list; unsigned long reboot_code_buffer_phys; void *reboot_code_buffer; - - page_list = image->head & PAGE_MASK; - /* we need both effective and real address here */ reboot_code_buffer_phys = page_to_pfn(image->control_code_page) << PAGE_SHIFT; reboot_code_buffer = page_address(image->control_code_page); - /* Prepare parameters for reboot_code_buffer*/ - kexec_start_address = image->start; - kexec_indirection_page = page_list; - kexec_mach_type = machine_arch_type; - kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET; - - /* copy our kernel relocation code to the control code page */ - memcpy(reboot_code_buffer, - relocate_new_kernel, relocate_new_kernel_size); - - - flush_icache_range((unsigned long) reboot_code_buffer, - (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE); printk(KERN_INFO "Bye!\n"); if (kexec_reinit) diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index cc2020c2c709..1e9be5d25e56 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -33,7 +33,7 @@ * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off. */ #undef MODULES_VADDR -#define MODULES_VADDR (((unsigned long)_etext + ~PGDIR_MASK) & PGDIR_MASK) +#define MODULES_VADDR (((unsigned long)_etext + ~PMD_MASK) & PMD_MASK) #endif #ifdef CONFIG_MMU diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 53c9c2610cbc..e6e5d7c84f1a 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -12,6 +12,7 @@ */ #define pr_fmt(fmt) "hw perfevents: " fmt +#include <linux/bitmap.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/module.h> @@ -26,16 +27,8 @@ #include <asm/pmu.h> #include <asm/stacktrace.h> -static struct platform_device *pmu_device; - -/* - * Hardware lock to serialize accesses to PMU registers. Needed for the - * read/modify/write sequences. - */ -static DEFINE_RAW_SPINLOCK(pmu_lock); - /* - * ARMv6 supports a maximum of 3 events, starting from index 1. If we add + * ARMv6 supports a maximum of 3 events, starting from index 0. If we add * another platform that supports more, we need to increase this to be the * largest of all platforms. * @@ -43,62 +36,24 @@ static DEFINE_RAW_SPINLOCK(pmu_lock); * cycle counter CCNT + 31 events counters CNT0..30. * Cortex-A8 has 1+4 counters, Cortex-A9 has 1+6 counters. */ -#define ARMPMU_MAX_HWEVENTS 33 +#define ARMPMU_MAX_HWEVENTS 32 -/* The events for a given CPU. */ -struct cpu_hw_events { - /* - * The events that are active on the CPU for the given index. Index 0 - * is reserved. - */ - struct perf_event *events[ARMPMU_MAX_HWEVENTS]; - - /* - * A 1 bit for an index indicates that the counter is being used for - * an event. A 0 means that the counter can be used. - */ - unsigned long used_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)]; +static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events); +static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask); +static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events); - /* - * A 1 bit for an index indicates that the counter is actively being - * used. - */ - unsigned long active_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)]; -}; -static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events); - -struct arm_pmu { - enum arm_perf_pmu_ids id; - const char *name; - irqreturn_t (*handle_irq)(int irq_num, void *dev); - void (*enable)(struct hw_perf_event *evt, int idx); - void (*disable)(struct hw_perf_event *evt, int idx); - int (*get_event_idx)(struct cpu_hw_events *cpuc, - struct hw_perf_event *hwc); - u32 (*read_counter)(int idx); - void (*write_counter)(int idx, u32 val); - void (*start)(void); - void (*stop)(void); - void (*reset)(void *); - const unsigned (*cache_map)[PERF_COUNT_HW_CACHE_MAX] - [PERF_COUNT_HW_CACHE_OP_MAX] - [PERF_COUNT_HW_CACHE_RESULT_MAX]; - const unsigned (*event_map)[PERF_COUNT_HW_MAX]; - u32 raw_event_mask; - int num_events; - u64 max_period; -}; +#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) /* Set at runtime when we know what CPU type we are. */ -static const struct arm_pmu *armpmu; +static struct arm_pmu *cpu_pmu; enum arm_perf_pmu_ids armpmu_get_pmu_id(void) { int id = -ENODEV; - if (armpmu != NULL) - id = armpmu->id; + if (cpu_pmu != NULL) + id = cpu_pmu->id; return id; } @@ -109,8 +64,8 @@ armpmu_get_max_events(void) { int max_events = 0; - if (armpmu != NULL) - max_events = armpmu->num_events; + if (cpu_pmu != NULL) + max_events = cpu_pmu->num_events; return max_events; } @@ -130,7 +85,11 @@ EXPORT_SYMBOL_GPL(perf_num_counters); #define CACHE_OP_UNSUPPORTED 0xFFFF static int -armpmu_map_cache_event(u64 config) +armpmu_map_cache_event(const unsigned (*cache_map) + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX], + u64 config) { unsigned int cache_type, cache_op, cache_result, ret; @@ -146,7 +105,7 @@ armpmu_map_cache_event(u64 config) if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) return -EINVAL; - ret = (int)(*armpmu->cache_map)[cache_type][cache_op][cache_result]; + ret = (int)(*cache_map)[cache_type][cache_op][cache_result]; if (ret == CACHE_OP_UNSUPPORTED) return -ENOENT; @@ -155,23 +114,46 @@ armpmu_map_cache_event(u64 config) } static int -armpmu_map_event(u64 config) +armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config) { - int mapping = (*armpmu->event_map)[config]; - return mapping == HW_OP_UNSUPPORTED ? -EOPNOTSUPP : mapping; + int mapping = (*event_map)[config]; + return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping; } static int -armpmu_map_raw_event(u64 config) +armpmu_map_raw_event(u32 raw_event_mask, u64 config) { - return (int)(config & armpmu->raw_event_mask); + return (int)(config & raw_event_mask); } -static int +static int map_cpu_event(struct perf_event *event, + const unsigned (*event_map)[PERF_COUNT_HW_MAX], + const unsigned (*cache_map) + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX], + u32 raw_event_mask) +{ + u64 config = event->attr.config; + + switch (event->attr.type) { + case PERF_TYPE_HARDWARE: + return armpmu_map_event(event_map, config); + case PERF_TYPE_HW_CACHE: + return armpmu_map_cache_event(cache_map, config); + case PERF_TYPE_RAW: + return armpmu_map_raw_event(raw_event_mask, config); + } + + return -ENOENT; +} + +int armpmu_event_set_period(struct perf_event *event, struct hw_perf_event *hwc, int idx) { + struct arm_pmu *armpmu = to_arm_pmu(event->pmu); s64 left = local64_read(&hwc->period_left); s64 period = hwc->sample_period; int ret = 0; @@ -202,11 +184,12 @@ armpmu_event_set_period(struct perf_event *event, return ret; } -static u64 +u64 armpmu_event_update(struct perf_event *event, struct hw_perf_event *hwc, int idx, int overflow) { + struct arm_pmu *armpmu = to_arm_pmu(event->pmu); u64 delta, prev_raw_count, new_raw_count; again: @@ -246,11 +229,9 @@ armpmu_read(struct perf_event *event) static void armpmu_stop(struct perf_event *event, int flags) { + struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - if (!armpmu) - return; - /* * ARM pmu always has to update the counter, so ignore * PERF_EF_UPDATE, see comments in armpmu_start(). @@ -266,11 +247,9 @@ armpmu_stop(struct perf_event *event, int flags) static void armpmu_start(struct perf_event *event, int flags) { + struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - if (!armpmu) - return; - /* * ARM pmu always has to reprogram the period, so ignore * PERF_EF_RELOAD, see the comment below. @@ -293,16 +272,16 @@ armpmu_start(struct perf_event *event, int flags) static void armpmu_del(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct arm_pmu *armpmu = to_arm_pmu(event->pmu); + struct pmu_hw_events *hw_events = armpmu->get_hw_events(); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; WARN_ON(idx < 0); - clear_bit(idx, cpuc->active_mask); armpmu_stop(event, PERF_EF_UPDATE); - cpuc->events[idx] = NULL; - clear_bit(idx, cpuc->used_mask); + hw_events->events[idx] = NULL; + clear_bit(idx, hw_events->used_mask); perf_event_update_userpage(event); } @@ -310,7 +289,8 @@ armpmu_del(struct perf_event *event, int flags) static int armpmu_add(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct arm_pmu *armpmu = to_arm_pmu(event->pmu); + struct pmu_hw_events *hw_events = armpmu->get_hw_events(); struct hw_perf_event *hwc = &event->hw; int idx; int err = 0; @@ -318,7 +298,7 @@ armpmu_add(struct perf_event *event, int flags) perf_pmu_disable(event->pmu); /* If we don't have a space for the counter then finish early. */ - idx = armpmu->get_event_idx(cpuc, hwc); + idx = armpmu->get_event_idx(hw_events, hwc); if (idx < 0) { err = idx; goto out; @@ -330,8 +310,7 @@ armpmu_add(struct perf_event *event, int flags) */ event->hw.idx = idx; armpmu->disable(hwc, idx); - cpuc->events[idx] = event; - set_bit(idx, cpuc->active_mask); + hw_events->events[idx] = event; hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; if (flags & PERF_EF_START) @@ -345,25 +324,25 @@ out: return err; } -static struct pmu pmu; - static int -validate_event(struct cpu_hw_events *cpuc, +validate_event(struct pmu_hw_events *hw_events, struct perf_event *event) { + struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event fake_event = event->hw; + struct pmu *leader_pmu = event->group_leader->pmu; - if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF) + if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF) return 1; - return armpmu->get_event_idx(cpuc, &fake_event) >= 0; + return armpmu->get_event_idx(hw_events, &fake_event) >= 0; } static int validate_group(struct perf_event *event) { struct perf_event *sibling, *leader = event->group_leader; - struct cpu_hw_events fake_pmu; + struct pmu_hw_events fake_pmu; memset(&fake_pmu, 0, sizeof(fake_pmu)); @@ -383,110 +362,119 @@ validate_group(struct perf_event *event) static irqreturn_t armpmu_platform_irq(int irq, void *dev) { - struct arm_pmu_platdata *plat = dev_get_platdata(&pmu_device->dev); + struct arm_pmu *armpmu = (struct arm_pmu *) dev; + struct platform_device *plat_device = armpmu->plat_device; + struct arm_pmu_platdata *plat = dev_get_platdata(&plat_device->dev); return plat->handle_irq(irq, dev, armpmu->handle_irq); } +static void +armpmu_release_hardware(struct arm_pmu *armpmu) +{ + int i, irq, irqs; + struct platform_device *pmu_device = armpmu->plat_device; + + irqs = min(pmu_device->num_resources, num_possible_cpus()); + + for (i = 0; i < irqs; ++i) { + if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs)) + continue; + irq = platform_get_irq(pmu_device, i); + if (irq >= 0) + free_irq(irq, armpmu); + } + + release_pmu(armpmu->type); +} + static int -armpmu_reserve_hardware(void) +armpmu_reserve_hardware(struct arm_pmu *armpmu) { struct arm_pmu_platdata *plat; irq_handler_t handle_irq; - int i, err = -ENODEV, irq; + int i, err, irq, irqs; + struct platform_device *pmu_device = armpmu->plat_device; - pmu_device = reserve_pmu(ARM_PMU_DEVICE_CPU); - if (IS_ERR(pmu_device)) { + err = reserve_pmu(armpmu->type); + if (err) { pr_warning("unable to reserve pmu\n"); - return PTR_ERR(pmu_device); + return err; } - init_pmu(ARM_PMU_DEVICE_CPU); - plat = dev_get_platdata(&pmu_device->dev); if (plat && plat->handle_irq) handle_irq = armpmu_platform_irq; else handle_irq = armpmu->handle_irq; - if (pmu_device->num_resources < 1) { + irqs = min(pmu_device->num_resources, num_possible_cpus()); + if (irqs < 1) { pr_err("no irqs for PMUs defined\n"); return -ENODEV; } - for (i = 0; i < pmu_device->num_resources; ++i) { + for (i = 0; i < irqs; ++i) { + err = 0; irq = platform_get_irq(pmu_device, i); if (irq < 0) continue; + /* + * If we have a single PMU interrupt that we can't shift, + * assume that we're running on a uniprocessor machine and + * continue. Otherwise, continue without this interrupt. + */ + if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) { + pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n", + irq, i); + continue; + } + err = request_irq(irq, handle_irq, IRQF_DISABLED | IRQF_NOBALANCING, - "armpmu", NULL); + "arm-pmu", armpmu); if (err) { - pr_warning("unable to request IRQ%d for ARM perf " - "counters\n", irq); - break; + pr_err("unable to request IRQ%d for ARM PMU counters\n", + irq); + armpmu_release_hardware(armpmu); + return err; } - } - if (err) { - for (i = i - 1; i >= 0; --i) { - irq = platform_get_irq(pmu_device, i); - if (irq >= 0) - free_irq(irq, NULL); - } - release_pmu(ARM_PMU_DEVICE_CPU); - pmu_device = NULL; + cpumask_set_cpu(i, &armpmu->active_irqs); } - return err; + return 0; } static void -armpmu_release_hardware(void) +hw_perf_event_destroy(struct perf_event *event) { - int i, irq; + struct arm_pmu *armpmu = to_arm_pmu(event->pmu); + atomic_t *active_events = &armpmu->active_events; + struct mutex *pmu_reserve_mutex = &armpmu->reserve_mutex; - for (i = pmu_device->num_resources - 1; i >= 0; --i) { - irq = platform_get_irq(pmu_device, i); - if (irq >= 0) - free_irq(irq, NULL); + if (atomic_dec_and_mutex_lock(active_events, pmu_reserve_mutex)) { + armpmu_release_hardware(armpmu); + mutex_unlock(pmu_reserve_mutex); } - armpmu->stop(); - - release_pmu(ARM_PMU_DEVICE_CPU); - pmu_device = NULL; } -static atomic_t active_events = ATOMIC_INIT(0); -static DEFINE_MUTEX(pmu_reserve_mutex); - -static void -hw_perf_event_destroy(struct perf_event *event) +static int +event_requires_mode_exclusion(struct perf_event_attr *attr) { - if (atomic_dec_and_mutex_lock(&active_events, &pmu_reserve_mutex)) { - armpmu_release_hardware(); - mutex_unlock(&pmu_reserve_mutex); - } + return attr->exclude_idle || attr->exclude_user || + attr->exclude_kernel || attr->exclude_hv; } static int __hw_perf_event_init(struct perf_event *event) { + struct arm_pmu *armpmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; int mapping, err; - /* Decode the generic type into an ARM event identifier. */ - if (PERF_TYPE_HARDWARE == event->attr.type) { - mapping = armpmu_map_event(event->attr.config); - } else if (PERF_TYPE_HW_CACHE == event->attr.type) { - mapping = armpmu_map_cache_event(event->attr.config); - } else if (PERF_TYPE_RAW == event->attr.type) { - mapping = armpmu_map_raw_event(event->attr.config); - } else { - pr_debug("event type %x not supported\n", event->attr.type); - return -EOPNOTSUPP; - } + mapping = armpmu->map_event(event); if (mapping < 0) { pr_debug("event %x:%llx not supported\n", event->attr.type, @@ -495,34 +483,31 @@ __hw_perf_event_init(struct perf_event *event) } /* + * We don't assign an index until we actually place the event onto + * hardware. Use -1 to signify that we haven't decided where to put it + * yet. For SMP systems, each core has it's own PMU so we can't do any + * clever allocation or constraints checking at this point. + */ + hwc->idx = -1; + hwc->config_base = 0; + hwc->config = 0; + hwc->event_base = 0; + + /* * Check whether we need to exclude the counter from certain modes. - * The ARM performance counters are on all of the time so if someone - * has asked us for some excludes then we have to fail. */ - if (event->attr.exclude_kernel || event->attr.exclude_user || - event->attr.exclude_hv || event->attr.exclude_idle) { + if ((!armpmu->set_event_filter || + armpmu->set_event_filter(hwc, &event->attr)) && + event_requires_mode_exclusion(&event->attr)) { pr_debug("ARM performance counters do not support " "mode exclusion\n"); return -EPERM; } /* - * We don't assign an index until we actually place the event onto - * hardware. Use -1 to signify that we haven't decided where to put it - * yet. For SMP systems, each core has it's own PMU so we can't do any - * clever allocation or constraints checking at this point. + * Store the event encoding into the config_base field. */ - hwc->idx = -1; - - /* - * Store the event encoding into the config_base field. config and - * event_base are unused as the only 2 things we need to know are - * the event mapping and the counter to use. The counter to use is - * also the indx and the config_base is the event type. - */ - hwc->config_base = (unsigned long)mapping; - hwc->config = 0; - hwc->event_base = 0; + hwc->config_base |= (unsigned long)mapping; if (!hwc->sample_period) { hwc->sample_period = armpmu->max_period; @@ -542,32 +527,23 @@ __hw_perf_event_init(struct perf_event *event) static int armpmu_event_init(struct perf_event *event) { + struct arm_pmu *armpmu = to_arm_pmu(event->pmu); int err = 0; + atomic_t *active_events = &armpmu->active_events; - switch (event->attr.type) { - case PERF_TYPE_RAW: - case PERF_TYPE_HARDWARE: - case PERF_TYPE_HW_CACHE: - break; - - default: + if (armpmu->map_event(event) == -ENOENT) return -ENOENT; - } - - if (!armpmu) - return -ENODEV; event->destroy = hw_perf_event_destroy; - if (!atomic_inc_not_zero(&active_events)) { - mutex_lock(&pmu_reserve_mutex); - if (atomic_read(&active_events) == 0) { - err = armpmu_reserve_hardware(); - } + if (!atomic_inc_not_zero(active_events)) { + mutex_lock(&armpmu->reserve_mutex); + if (atomic_read(active_events) == 0) + err = armpmu_reserve_hardware(armpmu); if (!err) - atomic_inc(&active_events); - mutex_unlock(&pmu_reserve_mutex); + atomic_inc(active_events); + mutex_unlock(&armpmu->reserve_mutex); } if (err) @@ -582,22 +558,9 @@ static int armpmu_event_init(struct perf_event *event) static void armpmu_enable(struct pmu *pmu) { - /* Enable all of the perf events on hardware. */ - int idx, enabled = 0; - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - - if (!armpmu) - return; - - for (idx = 0; idx <= armpmu->num_events; ++idx) { - struct perf_event *event = cpuc->events[idx]; - - if (!event) - continue; - - armpmu->enable(&event->hw, idx); - enabled = 1; - } + struct arm_pmu *armpmu = to_arm_pmu(pmu); + struct pmu_hw_events *hw_events = armpmu->get_hw_events(); + int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events); if (enabled) armpmu->start(); @@ -605,20 +568,32 @@ static void armpmu_enable(struct pmu *pmu) static void armpmu_disable(struct pmu *pmu) { - if (armpmu) - armpmu->stop(); + struct arm_pmu *armpmu = to_arm_pmu(pmu); + armpmu->stop(); } -static struct pmu pmu = { - .pmu_enable = armpmu_enable, - .pmu_disable = armpmu_disable, - .event_init = armpmu_event_init, - .add = armpmu_add, - .del = armpmu_del, - .start = armpmu_start, - .stop = armpmu_stop, - .read = armpmu_read, -}; +static void __init armpmu_init(struct arm_pmu *armpmu) +{ + atomic_set(&armpmu->active_events, 0); + mutex_init(&armpmu->reserve_mutex); + + armpmu->pmu = (struct pmu) { + .pmu_enable = armpmu_enable, + .pmu_disable = armpmu_disable, + .event_init = armpmu_event_init, + .add = armpmu_add, + .del = armpmu_del, + .start = armpmu_start, + .stop = armpmu_stop, + .read = armpmu_read, + }; +} + +int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type) +{ + armpmu_init(armpmu); + return perf_pmu_register(&armpmu->pmu, name, type); +} /* Include the PMU-specific implementations. */ #include "perf_event_xscale.c" @@ -630,14 +605,72 @@ static struct pmu pmu = { * This requires SMP to be available, so exists as a separate initcall. */ static int __init -armpmu_reset(void) +cpu_pmu_reset(void) +{ + if (cpu_pmu && cpu_pmu->reset) + return on_each_cpu(cpu_pmu->reset, NULL, 1); + return 0; +} +arch_initcall(cpu_pmu_reset); + +/* + * PMU platform driver and devicetree bindings. + */ +static struct of_device_id armpmu_of_device_ids[] = { + {.compatible = "arm,cortex-a9-pmu"}, + {.compatible = "arm,cortex-a8-pmu"}, + {.compatible = "arm,arm1136-pmu"}, + {.compatible = "arm,arm1176-pmu"}, + {}, +}; + +static struct platform_device_id armpmu_plat_device_ids[] = { + {.name = "arm-pmu"}, + {}, +}; + +static int __devinit armpmu_device_probe(struct platform_device *pdev) { - if (armpmu && armpmu->reset) - return on_each_cpu(armpmu->reset, NULL, 1); + cpu_pmu->plat_device = pdev; return 0; } -arch_initcall(armpmu_reset); +static struct platform_driver armpmu_driver = { + .driver = { + .name = "arm-pmu", + .of_match_table = armpmu_of_device_ids, + }, + .probe = armpmu_device_probe, + .id_table = armpmu_plat_device_ids, +}; + +static int __init register_pmu_driver(void) +{ + return platform_driver_register(&armpmu_driver); +} +device_initcall(register_pmu_driver); + +static struct pmu_hw_events *armpmu_get_cpu_events(void) +{ + return &__get_cpu_var(cpu_hw_events); +} + +static void __init cpu_pmu_init(struct arm_pmu *armpmu) +{ + int cpu; + for_each_possible_cpu(cpu) { + struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu); + events->events = per_cpu(hw_events, cpu); + events->used_mask = per_cpu(used_mask, cpu); + raw_spin_lock_init(&events->pmu_lock); + } + armpmu->get_hw_events = armpmu_get_cpu_events; + armpmu->type = ARM_PMU_DEVICE_CPU; +} + +/* + * CPU PMU identification and registration. + */ static int __init init_hw_perf_events(void) { @@ -651,22 +684,22 @@ init_hw_perf_events(void) case 0xB360: /* ARM1136 */ case 0xB560: /* ARM1156 */ case 0xB760: /* ARM1176 */ - armpmu = armv6pmu_init(); + cpu_pmu = armv6pmu_init(); break; case 0xB020: /* ARM11mpcore */ - armpmu = armv6mpcore_pmu_init(); + cpu_pmu = armv6mpcore_pmu_init(); break; case 0xC080: /* Cortex-A8 */ - armpmu = armv7_a8_pmu_init(); + cpu_pmu = armv7_a8_pmu_init(); break; case 0xC090: /* Cortex-A9 */ - armpmu = armv7_a9_pmu_init(); + cpu_pmu = armv7_a9_pmu_init(); break; case 0xC050: /* Cortex-A5 */ - armpmu = armv7_a5_pmu_init(); + cpu_pmu = armv7_a5_pmu_init(); break; case 0xC0F0: /* Cortex-A15 */ - armpmu = armv7_a15_pmu_init(); + cpu_pmu = armv7_a15_pmu_init(); break; } /* Intel CPUs [xscale]. */ @@ -674,23 +707,23 @@ init_hw_perf_events(void) part_number = (cpuid >> 13) & 0x7; switch (part_number) { case 1: - armpmu = xscale1pmu_init(); + cpu_pmu = xscale1pmu_init(); break; case 2: - armpmu = xscale2pmu_init(); + cpu_pmu = xscale2pmu_init(); break; } } - if (armpmu) { + if (cpu_pmu) { pr_info("enabled with %s PMU driver, %d counters available\n", - armpmu->name, armpmu->num_events); + cpu_pmu->name, cpu_pmu->num_events); + cpu_pmu_init(cpu_pmu); + armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW); } else { pr_info("no hardware support available\n"); } - perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); - return 0; } early_initcall(init_hw_perf_events); diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c index dd7f3b9f4cb3..e63d8115c01b 100644 --- a/arch/arm/kernel/perf_event_v6.c +++ b/arch/arm/kernel/perf_event_v6.c @@ -54,7 +54,7 @@ enum armv6_perf_types { }; enum armv6_counters { - ARMV6_CYCLE_COUNTER = 1, + ARMV6_CYCLE_COUNTER = 0, ARMV6_COUNTER0, ARMV6_COUNTER1, }; @@ -433,6 +433,7 @@ armv6pmu_enable_event(struct hw_perf_event *hwc, int idx) { unsigned long val, mask, evt, flags; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); if (ARMV6_CYCLE_COUNTER == idx) { mask = 0; @@ -454,12 +455,29 @@ armv6pmu_enable_event(struct hw_perf_event *hwc, * Mask out the current event and set the counter to count the event * that we're interested in. */ - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); val = armv6_pmcr_read(); val &= ~mask; val |= evt; armv6_pmcr_write(val); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static int counter_is_active(unsigned long pmcr, int idx) +{ + unsigned long mask = 0; + if (idx == ARMV6_CYCLE_COUNTER) + mask = ARMV6_PMCR_CCOUNT_IEN; + else if (idx == ARMV6_COUNTER0) + mask = ARMV6_PMCR_COUNT0_IEN; + else if (idx == ARMV6_COUNTER1) + mask = ARMV6_PMCR_COUNT1_IEN; + + if (mask) + return pmcr & mask; + + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return 0; } static irqreturn_t @@ -468,7 +486,7 @@ armv6pmu_handle_irq(int irq_num, { unsigned long pmcr = armv6_pmcr_read(); struct perf_sample_data data; - struct cpu_hw_events *cpuc; + struct pmu_hw_events *cpuc; struct pt_regs *regs; int idx; @@ -487,11 +505,11 @@ armv6pmu_handle_irq(int irq_num, perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); - for (idx = 0; idx <= armpmu->num_events; ++idx) { + for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; - if (!test_bit(idx, cpuc->active_mask)) + if (!counter_is_active(pmcr, idx)) continue; /* @@ -508,7 +526,7 @@ armv6pmu_handle_irq(int irq_num, continue; if (perf_event_overflow(event, &data, regs)) - armpmu->disable(hwc, idx); + cpu_pmu->disable(hwc, idx); } /* @@ -527,28 +545,30 @@ static void armv6pmu_start(void) { unsigned long flags, val; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); val = armv6_pmcr_read(); val |= ARMV6_PMCR_ENABLE; armv6_pmcr_write(val); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static void armv6pmu_stop(void) { unsigned long flags, val; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); val = armv6_pmcr_read(); val &= ~ARMV6_PMCR_ENABLE; armv6_pmcr_write(val); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static int -armv6pmu_get_event_idx(struct cpu_hw_events *cpuc, +armv6pmu_get_event_idx(struct pmu_hw_events *cpuc, struct hw_perf_event *event) { /* Always place a cycle counter into the cycle counter. */ @@ -578,6 +598,7 @@ armv6pmu_disable_event(struct hw_perf_event *hwc, int idx) { unsigned long val, mask, evt, flags; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); if (ARMV6_CYCLE_COUNTER == idx) { mask = ARMV6_PMCR_CCOUNT_IEN; @@ -598,12 +619,12 @@ armv6pmu_disable_event(struct hw_perf_event *hwc, * of ETM bus signal assertion cycles. The external reporting should * be disabled and so this should never increment. */ - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); val = armv6_pmcr_read(); val &= ~mask; val |= evt; armv6_pmcr_write(val); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static void @@ -611,6 +632,7 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc, int idx) { unsigned long val, mask, flags, evt = 0; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); if (ARMV6_CYCLE_COUNTER == idx) { mask = ARMV6_PMCR_CCOUNT_IEN; @@ -627,15 +649,21 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc, * Unlike UP ARMv6, we don't have a way of stopping the counters. We * simply disable the interrupt reporting. */ - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); val = armv6_pmcr_read(); val &= ~mask; val |= evt; armv6_pmcr_write(val); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static int armv6_map_event(struct perf_event *event) +{ + return map_cpu_event(event, &armv6_perf_map, + &armv6_perf_cache_map, 0xFF); } -static const struct arm_pmu armv6pmu = { +static struct arm_pmu armv6pmu = { .id = ARM_PERF_PMU_ID_V6, .name = "v6", .handle_irq = armv6pmu_handle_irq, @@ -646,14 +674,12 @@ static const struct arm_pmu armv6pmu = { .get_event_idx = armv6pmu_get_event_idx, .start = armv6pmu_start, .stop = armv6pmu_stop, - .cache_map = &armv6_perf_cache_map, - .event_map = &armv6_perf_map, - .raw_event_mask = 0xFF, + .map_event = armv6_map_event, .num_events = 3, .max_period = (1LLU << 32) - 1, }; -static const struct arm_pmu *__init armv6pmu_init(void) +static struct arm_pmu *__init armv6pmu_init(void) { return &armv6pmu; } @@ -665,7 +691,14 @@ static const struct arm_pmu *__init armv6pmu_init(void) * disable the interrupt reporting and update the event. When unthrottling we * reset the period and enable the interrupt reporting. */ -static const struct arm_pmu armv6mpcore_pmu = { + +static int armv6mpcore_map_event(struct perf_event *event) +{ + return map_cpu_event(event, &armv6mpcore_perf_map, + &armv6mpcore_perf_cache_map, 0xFF); +} + +static struct arm_pmu armv6mpcore_pmu = { .id = ARM_PERF_PMU_ID_V6MP, .name = "v6mpcore", .handle_irq = armv6pmu_handle_irq, @@ -676,24 +709,22 @@ static const struct arm_pmu armv6mpcore_pmu = { .get_event_idx = armv6pmu_get_event_idx, .start = armv6pmu_start, .stop = armv6pmu_stop, - .cache_map = &armv6mpcore_perf_cache_map, - .event_map = &armv6mpcore_perf_map, - .raw_event_mask = 0xFF, + .map_event = armv6mpcore_map_event, .num_events = 3, .max_period = (1LLU << 32) - 1, }; -static const struct arm_pmu *__init armv6mpcore_pmu_init(void) +static struct arm_pmu *__init armv6mpcore_pmu_init(void) { return &armv6mpcore_pmu; } #else -static const struct arm_pmu *__init armv6pmu_init(void) +static struct arm_pmu *__init armv6pmu_init(void) { return NULL; } -static const struct arm_pmu *__init armv6mpcore_pmu_init(void) +static struct arm_pmu *__init armv6mpcore_pmu_init(void) { return NULL; } diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 4c851834f68e..1ef6d0034b85 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -17,6 +17,9 @@ */ #ifdef CONFIG_CPU_V7 + +static struct arm_pmu armv7pmu; + /* * Common ARMv7 event types * @@ -321,8 +324,8 @@ static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE, - [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_COHERENT_LINE_HIT, - [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_COHERENT_LINE_MISS, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_DCACHE_ACCESS, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_DCACHE_REFILL, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES, @@ -676,23 +679,24 @@ static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] }; /* - * Perf Events counters + * Perf Events' indices */ -enum armv7_counters { - ARMV7_CYCLE_COUNTER = 1, /* Cycle counter */ - ARMV7_COUNTER0 = 2, /* First event counter */ -}; +#define ARMV7_IDX_CYCLE_COUNTER 0 +#define ARMV7_IDX_COUNTER0 1 +#define ARMV7_IDX_COUNTER_LAST (ARMV7_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1) + +#define ARMV7_MAX_COUNTERS 32 +#define ARMV7_COUNTER_MASK (ARMV7_MAX_COUNTERS - 1) /* - * The cycle counter is ARMV7_CYCLE_COUNTER. - * The first event counter is ARMV7_COUNTER0. - * The last event counter is (ARMV7_COUNTER0 + armpmu->num_events - 1). + * ARMv7 low level PMNC access */ -#define ARMV7_COUNTER_LAST (ARMV7_COUNTER0 + armpmu->num_events - 1) /* - * ARMv7 low level PMNC access + * Perf Event to low level counters mapping */ +#define ARMV7_IDX_TO_COUNTER(x) \ + (((x) - ARMV7_IDX_COUNTER0) & ARMV7_COUNTER_MASK) /* * Per-CPU PMNC: config reg @@ -708,103 +712,76 @@ enum armv7_counters { #define ARMV7_PMNC_MASK 0x3f /* Mask for writable bits */ /* - * Available counters - */ -#define ARMV7_CNT0 0 /* First event counter */ -#define ARMV7_CCNT 31 /* Cycle counter */ - -/* Perf Event to low level counters mapping */ -#define ARMV7_EVENT_CNT_TO_CNTx (ARMV7_COUNTER0 - ARMV7_CNT0) - -/* - * CNTENS: counters enable reg - */ -#define ARMV7_CNTENS_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx)) -#define ARMV7_CNTENS_C (1 << ARMV7_CCNT) - -/* - * CNTENC: counters disable reg - */ -#define ARMV7_CNTENC_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx)) -#define ARMV7_CNTENC_C (1 << ARMV7_CCNT) - -/* - * INTENS: counters overflow interrupt enable reg - */ -#define ARMV7_INTENS_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx)) -#define ARMV7_INTENS_C (1 << ARMV7_CCNT) - -/* - * INTENC: counters overflow interrupt disable reg - */ -#define ARMV7_INTENC_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx)) -#define ARMV7_INTENC_C (1 << ARMV7_CCNT) - -/* - * EVTSEL: Event selection reg + * FLAG: counters overflow flag status reg */ -#define ARMV7_EVTSEL_MASK 0xff /* Mask for writable bits */ +#define ARMV7_FLAG_MASK 0xffffffff /* Mask for writable bits */ +#define ARMV7_OVERFLOWED_MASK ARMV7_FLAG_MASK /* - * SELECT: Counter selection reg + * PMXEVTYPER: Event selection reg */ -#define ARMV7_SELECT_MASK 0x1f /* Mask for writable bits */ +#define ARMV7_EVTYPE_MASK 0xc00000ff /* Mask for writable bits */ +#define ARMV7_EVTYPE_EVENT 0xff /* Mask for EVENT bits */ /* - * FLAG: counters overflow flag status reg + * Event filters for PMUv2 */ -#define ARMV7_FLAG_P(idx) (1 << (idx - ARMV7_EVENT_CNT_TO_CNTx)) -#define ARMV7_FLAG_C (1 << ARMV7_CCNT) -#define ARMV7_FLAG_MASK 0xffffffff /* Mask for writable bits */ -#define ARMV7_OVERFLOWED_MASK ARMV7_FLAG_MASK +#define ARMV7_EXCLUDE_PL1 (1 << 31) +#define ARMV7_EXCLUDE_USER (1 << 30) +#define ARMV7_INCLUDE_HYP (1 << 27) -static inline unsigned long armv7_pmnc_read(void) +static inline u32 armv7_pmnc_read(void) { u32 val; asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val)); return val; } -static inline void armv7_pmnc_write(unsigned long val) +static inline void armv7_pmnc_write(u32 val) { val &= ARMV7_PMNC_MASK; isb(); asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val)); } -static inline int armv7_pmnc_has_overflowed(unsigned long pmnc) +static inline int armv7_pmnc_has_overflowed(u32 pmnc) { return pmnc & ARMV7_OVERFLOWED_MASK; } -static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc, - enum armv7_counters counter) +static inline int armv7_pmnc_counter_valid(int idx) +{ + return idx >= ARMV7_IDX_CYCLE_COUNTER && idx <= ARMV7_IDX_COUNTER_LAST; +} + +static inline int armv7_pmnc_counter_has_overflowed(u32 pmnc, int idx) { int ret = 0; + u32 counter; - if (counter == ARMV7_CYCLE_COUNTER) - ret = pmnc & ARMV7_FLAG_C; - else if ((counter >= ARMV7_COUNTER0) && (counter <= ARMV7_COUNTER_LAST)) - ret = pmnc & ARMV7_FLAG_P(counter); - else + if (!armv7_pmnc_counter_valid(idx)) { pr_err("CPU%u checking wrong counter %d overflow status\n", - smp_processor_id(), counter); + smp_processor_id(), idx); + } else { + counter = ARMV7_IDX_TO_COUNTER(idx); + ret = pmnc & BIT(counter); + } return ret; } -static inline int armv7_pmnc_select_counter(unsigned int idx) +static inline int armv7_pmnc_select_counter(int idx) { - u32 val; + u32 counter; - if ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST)) { - pr_err("CPU%u selecting wrong PMNC counter" - " %d\n", smp_processor_id(), idx); - return -1; + if (!armv7_pmnc_counter_valid(idx)) { + pr_err("CPU%u selecting wrong PMNC counter %d\n", + smp_processor_id(), idx); + return -EINVAL; } - val = (idx - ARMV7_EVENT_CNT_TO_CNTx) & ARMV7_SELECT_MASK; - asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val)); + counter = ARMV7_IDX_TO_COUNTER(idx); + asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (counter)); isb(); return idx; @@ -812,124 +789,95 @@ static inline int armv7_pmnc_select_counter(unsigned int idx) static inline u32 armv7pmu_read_counter(int idx) { - unsigned long value = 0; + u32 value = 0; - if (idx == ARMV7_CYCLE_COUNTER) - asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value)); - else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) { - if (armv7_pmnc_select_counter(idx) == idx) - asm volatile("mrc p15, 0, %0, c9, c13, 2" - : "=r" (value)); - } else + if (!armv7_pmnc_counter_valid(idx)) pr_err("CPU%u reading wrong counter %d\n", smp_processor_id(), idx); + else if (idx == ARMV7_IDX_CYCLE_COUNTER) + asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value)); + else if (armv7_pmnc_select_counter(idx) == idx) + asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (value)); return value; } static inline void armv7pmu_write_counter(int idx, u32 value) { - if (idx == ARMV7_CYCLE_COUNTER) - asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value)); - else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) { - if (armv7_pmnc_select_counter(idx) == idx) - asm volatile("mcr p15, 0, %0, c9, c13, 2" - : : "r" (value)); - } else + if (!armv7_pmnc_counter_valid(idx)) pr_err("CPU%u writing wrong counter %d\n", smp_processor_id(), idx); + else if (idx == ARMV7_IDX_CYCLE_COUNTER) + asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value)); + else if (armv7_pmnc_select_counter(idx) == idx) + asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (value)); } -static inline void armv7_pmnc_write_evtsel(unsigned int idx, u32 val) +static inline void armv7_pmnc_write_evtsel(int idx, u32 val) { if (armv7_pmnc_select_counter(idx) == idx) { - val &= ARMV7_EVTSEL_MASK; + val &= ARMV7_EVTYPE_MASK; asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val)); } } -static inline u32 armv7_pmnc_enable_counter(unsigned int idx) +static inline int armv7_pmnc_enable_counter(int idx) { - u32 val; + u32 counter; - if ((idx != ARMV7_CYCLE_COUNTER) && - ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) { - pr_err("CPU%u enabling wrong PMNC counter" - " %d\n", smp_processor_id(), idx); - return -1; + if (!armv7_pmnc_counter_valid(idx)) { + pr_err("CPU%u enabling wrong PMNC counter %d\n", + smp_processor_id(), idx); + return -EINVAL; } - if (idx == ARMV7_CYCLE_COUNTER) - val = ARMV7_CNTENS_C; - else - val = ARMV7_CNTENS_P(idx); - - asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val)); - + counter = ARMV7_IDX_TO_COUNTER(idx); + asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(counter))); return idx; } -static inline u32 armv7_pmnc_disable_counter(unsigned int idx) +static inline int armv7_pmnc_disable_counter(int idx) { - u32 val; - + u32 counter; - if ((idx != ARMV7_CYCLE_COUNTER) && - ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) { - pr_err("CPU%u disabling wrong PMNC counter" - " %d\n", smp_processor_id(), idx); - return -1; + if (!armv7_pmnc_counter_valid(idx)) { + pr_err("CPU%u disabling wrong PMNC counter %d\n", + smp_processor_id(), idx); + return -EINVAL; } - if (idx == ARMV7_CYCLE_COUNTER) - val = ARMV7_CNTENC_C; - else - val = ARMV7_CNTENC_P(idx); - - asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val)); - + counter = ARMV7_IDX_TO_COUNTER(idx); + asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(counter))); return idx; } -static inline u32 armv7_pmnc_enable_intens(unsigned int idx) +static inline int armv7_pmnc_enable_intens(int idx) { - u32 val; + u32 counter; - if ((idx != ARMV7_CYCLE_COUNTER) && - ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) { - pr_err("CPU%u enabling wrong PMNC counter" - " interrupt enable %d\n", smp_processor_id(), idx); - return -1; + if (!armv7_pmnc_counter_valid(idx)) { + pr_err("CPU%u enabling wrong PMNC counter IRQ enable %d\n", + smp_processor_id(), idx); + return -EINVAL; } - if (idx == ARMV7_CYCLE_COUNTER) - val = ARMV7_INTENS_C; - else - val = ARMV7_INTENS_P(idx); - - asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val)); - + counter = ARMV7_IDX_TO_COUNTER(idx); + asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(counter))); return idx; } -static inline u32 armv7_pmnc_disable_intens(unsigned int idx) +static inline int armv7_pmnc_disable_intens(int idx) { - u32 val; + u32 counter; - if ((idx != ARMV7_CYCLE_COUNTER) && - ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) { - pr_err("CPU%u disabling wrong PMNC counter" - " interrupt enable %d\n", smp_processor_id(), idx); - return -1; + if (!armv7_pmnc_counter_valid(idx)) { + pr_err("CPU%u disabling wrong PMNC counter IRQ enable %d\n", + smp_processor_id(), idx); + return -EINVAL; } - if (idx == ARMV7_CYCLE_COUNTER) - val = ARMV7_INTENC_C; - else - val = ARMV7_INTENC_P(idx); - - asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val)); - + counter = ARMV7_IDX_TO_COUNTER(idx); + asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter))); return idx; } @@ -973,14 +921,14 @@ static void armv7_pmnc_dump_regs(void) asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val)); printk(KERN_INFO "CCNT =0x%08x\n", val); - for (cnt = ARMV7_COUNTER0; cnt < ARMV7_COUNTER_LAST; cnt++) { + for (cnt = ARMV7_IDX_COUNTER0; cnt <= ARMV7_IDX_COUNTER_LAST; cnt++) { armv7_pmnc_select_counter(cnt); asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val)); printk(KERN_INFO "CNT[%d] count =0x%08x\n", - cnt-ARMV7_EVENT_CNT_TO_CNTx, val); + ARMV7_IDX_TO_COUNTER(cnt), val); asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val)); printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n", - cnt-ARMV7_EVENT_CNT_TO_CNTx, val); + ARMV7_IDX_TO_COUNTER(cnt), val); } } #endif @@ -988,12 +936,13 @@ static void armv7_pmnc_dump_regs(void) static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx) { unsigned long flags; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); /* * Enable counter and interrupt, and set the counter to count * the event that we're interested in. */ - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); /* * Disable counter @@ -1002,9 +951,10 @@ static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx) /* * Set event (if destined for PMNx counters) - * We don't need to set the event if it's a cycle count + * We only need to set the event for the cycle counter if we + * have the ability to perform event filtering. */ - if (idx != ARMV7_CYCLE_COUNTER) + if (armv7pmu.set_event_filter || idx != ARMV7_IDX_CYCLE_COUNTER) armv7_pmnc_write_evtsel(idx, hwc->config_base); /* @@ -1017,17 +967,18 @@ static void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx) */ armv7_pmnc_enable_counter(idx); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx) { unsigned long flags; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); /* * Disable counter and interrupt */ - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); /* * Disable counter @@ -1039,14 +990,14 @@ static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx) */ armv7_pmnc_disable_intens(idx); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) { - unsigned long pmnc; + u32 pmnc; struct perf_sample_data data; - struct cpu_hw_events *cpuc; + struct pmu_hw_events *cpuc; struct pt_regs *regs; int idx; @@ -1069,13 +1020,10 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); - for (idx = 0; idx <= armpmu->num_events; ++idx) { + for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; - if (!test_bit(idx, cpuc->active_mask)) - continue; - /* * We have a single interrupt for all counters. Check that * each counter has overflowed before we process it. @@ -1090,7 +1038,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) continue; if (perf_event_overflow(event, &data, regs)) - armpmu->disable(hwc, idx); + cpu_pmu->disable(hwc, idx); } /* @@ -1108,61 +1056,114 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) static void armv7pmu_start(void) { unsigned long flags; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); /* Enable all counters */ armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static void armv7pmu_stop(void) { unsigned long flags; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); /* Disable all counters */ armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } -static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc, +static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc, struct hw_perf_event *event) { int idx; + unsigned long evtype = event->config_base & ARMV7_EVTYPE_EVENT; /* Always place a cycle counter into the cycle counter. */ - if (event->config_base == ARMV7_PERFCTR_CPU_CYCLES) { - if (test_and_set_bit(ARMV7_CYCLE_COUNTER, cpuc->used_mask)) + if (evtype == ARMV7_PERFCTR_CPU_CYCLES) { + if (test_and_set_bit(ARMV7_IDX_CYCLE_COUNTER, cpuc->used_mask)) return -EAGAIN; - return ARMV7_CYCLE_COUNTER; - } else { - /* - * For anything other than a cycle counter, try and use - * the events counters - */ - for (idx = ARMV7_COUNTER0; idx <= armpmu->num_events; ++idx) { - if (!test_and_set_bit(idx, cpuc->used_mask)) - return idx; - } + return ARMV7_IDX_CYCLE_COUNTER; + } - /* The counters are all in use. */ - return -EAGAIN; + /* + * For anything other than a cycle counter, try and use + * the events counters + */ + for (idx = ARMV7_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) { + if (!test_and_set_bit(idx, cpuc->used_mask)) + return idx; } + + /* The counters are all in use. */ + return -EAGAIN; +} + +/* + * Add an event filter to a given event. This will only work for PMUv2 PMUs. + */ +static int armv7pmu_set_event_filter(struct hw_perf_event *event, + struct perf_event_attr *attr) +{ + unsigned long config_base = 0; + + if (attr->exclude_idle) + return -EPERM; + if (attr->exclude_user) + config_base |= ARMV7_EXCLUDE_USER; + if (attr->exclude_kernel) + config_base |= ARMV7_EXCLUDE_PL1; + if (!attr->exclude_hv) + config_base |= ARMV7_INCLUDE_HYP; + + /* + * Install the filter into config_base as this is used to + * construct the event type. + */ + event->config_base = config_base; + + return 0; } static void armv7pmu_reset(void *info) { - u32 idx, nb_cnt = armpmu->num_events; + u32 idx, nb_cnt = cpu_pmu->num_events; /* The counter and interrupt enable registers are unknown at reset. */ - for (idx = 1; idx < nb_cnt; ++idx) + for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) armv7pmu_disable_event(NULL, idx); /* Initialize & Reset PMNC: C and P bits */ armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C); } +static int armv7_a8_map_event(struct perf_event *event) +{ + return map_cpu_event(event, &armv7_a8_perf_map, + &armv7_a8_perf_cache_map, 0xFF); +} + +static int armv7_a9_map_event(struct perf_event *event) +{ + return map_cpu_event(event, &armv7_a9_perf_map, + &armv7_a9_perf_cache_map, 0xFF); +} + +static int armv7_a5_map_event(struct perf_event *event) +{ + return map_cpu_event(event, &armv7_a5_perf_map, + &armv7_a5_perf_cache_map, 0xFF); +} + +static int armv7_a15_map_event(struct perf_event *event) +{ + return map_cpu_event(event, &armv7_a15_perf_map, + &armv7_a15_perf_cache_map, 0xFF); +} + static struct arm_pmu armv7pmu = { .handle_irq = armv7pmu_handle_irq, .enable = armv7pmu_enable_event, @@ -1173,7 +1174,6 @@ static struct arm_pmu armv7pmu = { .start = armv7pmu_start, .stop = armv7pmu_stop, .reset = armv7pmu_reset, - .raw_event_mask = 0xFF, .max_period = (1LLU << 32) - 1, }; @@ -1188,62 +1188,59 @@ static u32 __init armv7_read_num_pmnc_events(void) return nb_cnt + 1; } -static const struct arm_pmu *__init armv7_a8_pmu_init(void) +static struct arm_pmu *__init armv7_a8_pmu_init(void) { armv7pmu.id = ARM_PERF_PMU_ID_CA8; armv7pmu.name = "ARMv7 Cortex-A8"; - armv7pmu.cache_map = &armv7_a8_perf_cache_map; - armv7pmu.event_map = &armv7_a8_perf_map; + armv7pmu.map_event = armv7_a8_map_event; armv7pmu.num_events = armv7_read_num_pmnc_events(); return &armv7pmu; } -static const struct arm_pmu *__init armv7_a9_pmu_init(void) +static struct arm_pmu *__init armv7_a9_pmu_init(void) { armv7pmu.id = ARM_PERF_PMU_ID_CA9; armv7pmu.name = "ARMv7 Cortex-A9"; - armv7pmu.cache_map = &armv7_a9_perf_cache_map; - armv7pmu.event_map = &armv7_a9_perf_map; + armv7pmu.map_event = armv7_a9_map_event; armv7pmu.num_events = armv7_read_num_pmnc_events(); return &armv7pmu; } -static const struct arm_pmu *__init armv7_a5_pmu_init(void) +static struct arm_pmu *__init armv7_a5_pmu_init(void) { armv7pmu.id = ARM_PERF_PMU_ID_CA5; armv7pmu.name = "ARMv7 Cortex-A5"; - armv7pmu.cache_map = &armv7_a5_perf_cache_map; - armv7pmu.event_map = &armv7_a5_perf_map; + armv7pmu.map_event = armv7_a5_map_event; armv7pmu.num_events = armv7_read_num_pmnc_events(); return &armv7pmu; } -static const struct arm_pmu *__init armv7_a15_pmu_init(void) +static struct arm_pmu *__init armv7_a15_pmu_init(void) { armv7pmu.id = ARM_PERF_PMU_ID_CA15; armv7pmu.name = "ARMv7 Cortex-A15"; - armv7pmu.cache_map = &armv7_a15_perf_cache_map; - armv7pmu.event_map = &armv7_a15_perf_map; + armv7pmu.map_event = armv7_a15_map_event; armv7pmu.num_events = armv7_read_num_pmnc_events(); + armv7pmu.set_event_filter = armv7pmu_set_event_filter; return &armv7pmu; } #else -static const struct arm_pmu *__init armv7_a8_pmu_init(void) +static struct arm_pmu *__init armv7_a8_pmu_init(void) { return NULL; } -static const struct arm_pmu *__init armv7_a9_pmu_init(void) +static struct arm_pmu *__init armv7_a9_pmu_init(void) { return NULL; } -static const struct arm_pmu *__init armv7_a5_pmu_init(void) +static struct arm_pmu *__init armv7_a5_pmu_init(void) { return NULL; } -static const struct arm_pmu *__init armv7_a15_pmu_init(void) +static struct arm_pmu *__init armv7_a15_pmu_init(void) { return NULL; } diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c index 3c4397491d08..e0cca10a8411 100644 --- a/arch/arm/kernel/perf_event_xscale.c +++ b/arch/arm/kernel/perf_event_xscale.c @@ -40,7 +40,7 @@ enum xscale_perf_types { }; enum xscale_counters { - XSCALE_CYCLE_COUNTER = 1, + XSCALE_CYCLE_COUNTER = 0, XSCALE_COUNTER0, XSCALE_COUNTER1, XSCALE_COUNTER2, @@ -222,7 +222,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev) { unsigned long pmnc; struct perf_sample_data data; - struct cpu_hw_events *cpuc; + struct pmu_hw_events *cpuc; struct pt_regs *regs; int idx; @@ -249,13 +249,10 @@ xscale1pmu_handle_irq(int irq_num, void *dev) perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); - for (idx = 0; idx <= armpmu->num_events; ++idx) { + for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; - if (!test_bit(idx, cpuc->active_mask)) - continue; - if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx)) continue; @@ -266,7 +263,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev) continue; if (perf_event_overflow(event, &data, regs)) - armpmu->disable(hwc, idx); + cpu_pmu->disable(hwc, idx); } irq_work_run(); @@ -284,6 +281,7 @@ static void xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx) { unsigned long val, mask, evt, flags; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); switch (idx) { case XSCALE_CYCLE_COUNTER: @@ -305,18 +303,19 @@ xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx) return; } - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); val = xscale1pmu_read_pmnc(); val &= ~mask; val |= evt; xscale1pmu_write_pmnc(val); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static void xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx) { unsigned long val, mask, evt, flags; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); switch (idx) { case XSCALE_CYCLE_COUNTER: @@ -336,16 +335,16 @@ xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx) return; } - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); val = xscale1pmu_read_pmnc(); val &= ~mask; val |= evt; xscale1pmu_write_pmnc(val); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static int -xscale1pmu_get_event_idx(struct cpu_hw_events *cpuc, +xscale1pmu_get_event_idx(struct pmu_hw_events *cpuc, struct hw_perf_event *event) { if (XSCALE_PERFCTR_CCNT == event->config_base) { @@ -368,24 +367,26 @@ static void xscale1pmu_start(void) { unsigned long flags, val; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); val = xscale1pmu_read_pmnc(); val |= XSCALE_PMU_ENABLE; xscale1pmu_write_pmnc(val); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static void xscale1pmu_stop(void) { unsigned long flags, val; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); val = xscale1pmu_read_pmnc(); val &= ~XSCALE_PMU_ENABLE; xscale1pmu_write_pmnc(val); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static inline u32 @@ -424,7 +425,13 @@ xscale1pmu_write_counter(int counter, u32 val) } } -static const struct arm_pmu xscale1pmu = { +static int xscale_map_event(struct perf_event *event) +{ + return map_cpu_event(event, &xscale_perf_map, + &xscale_perf_cache_map, 0xFF); +} + +static struct arm_pmu xscale1pmu = { .id = ARM_PERF_PMU_ID_XSCALE1, .name = "xscale1", .handle_irq = xscale1pmu_handle_irq, @@ -435,14 +442,12 @@ static const struct arm_pmu xscale1pmu = { .get_event_idx = xscale1pmu_get_event_idx, .start = xscale1pmu_start, .stop = xscale1pmu_stop, - .cache_map = &xscale_perf_cache_map, - .event_map = &xscale_perf_map, - .raw_event_mask = 0xFF, + .map_event = xscale_map_event, .num_events = 3, .max_period = (1LLU << 32) - 1, }; -static const struct arm_pmu *__init xscale1pmu_init(void) +static struct arm_pmu *__init xscale1pmu_init(void) { return &xscale1pmu; } @@ -560,7 +565,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev) { unsigned long pmnc, of_flags; struct perf_sample_data data; - struct cpu_hw_events *cpuc; + struct pmu_hw_events *cpuc; struct pt_regs *regs; int idx; @@ -581,13 +586,10 @@ xscale2pmu_handle_irq(int irq_num, void *dev) perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); - for (idx = 0; idx <= armpmu->num_events; ++idx) { + for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; - if (!test_bit(idx, cpuc->active_mask)) - continue; - if (!xscale2_pmnc_counter_has_overflowed(pmnc, idx)) continue; @@ -598,7 +600,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev) continue; if (perf_event_overflow(event, &data, regs)) - armpmu->disable(hwc, idx); + cpu_pmu->disable(hwc, idx); } irq_work_run(); @@ -616,6 +618,7 @@ static void xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx) { unsigned long flags, ien, evtsel; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); ien = xscale2pmu_read_int_enable(); evtsel = xscale2pmu_read_event_select(); @@ -649,16 +652,17 @@ xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx) return; } - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); xscale2pmu_write_event_select(evtsel); xscale2pmu_write_int_enable(ien); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static void xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx) { unsigned long flags, ien, evtsel; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); ien = xscale2pmu_read_int_enable(); evtsel = xscale2pmu_read_event_select(); @@ -692,14 +696,14 @@ xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx) return; } - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); xscale2pmu_write_event_select(evtsel); xscale2pmu_write_int_enable(ien); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static int -xscale2pmu_get_event_idx(struct cpu_hw_events *cpuc, +xscale2pmu_get_event_idx(struct pmu_hw_events *cpuc, struct hw_perf_event *event) { int idx = xscale1pmu_get_event_idx(cpuc, event); @@ -718,24 +722,26 @@ static void xscale2pmu_start(void) { unsigned long flags, val; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64; val |= XSCALE_PMU_ENABLE; xscale2pmu_write_pmnc(val); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static void xscale2pmu_stop(void) { unsigned long flags, val; + struct pmu_hw_events *events = cpu_pmu->get_hw_events(); - raw_spin_lock_irqsave(&pmu_lock, flags); + raw_spin_lock_irqsave(&events->pmu_lock, flags); val = xscale2pmu_read_pmnc(); val &= ~XSCALE_PMU_ENABLE; xscale2pmu_write_pmnc(val); - raw_spin_unlock_irqrestore(&pmu_lock, flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } static inline u32 @@ -786,7 +792,7 @@ xscale2pmu_write_counter(int counter, u32 val) } } -static const struct arm_pmu xscale2pmu = { +static struct arm_pmu xscale2pmu = { .id = ARM_PERF_PMU_ID_XSCALE2, .name = "xscale2", .handle_irq = xscale2pmu_handle_irq, @@ -797,24 +803,22 @@ static const struct arm_pmu xscale2pmu = { .get_event_idx = xscale2pmu_get_event_idx, .start = xscale2pmu_start, .stop = xscale2pmu_stop, - .cache_map = &xscale_perf_cache_map, - .event_map = &xscale_perf_map, - .raw_event_mask = 0xFF, + .map_event = xscale_map_event, .num_events = 5, .max_period = (1LLU << 32) - 1, }; -static const struct arm_pmu *__init xscale2pmu_init(void) +static struct arm_pmu *__init xscale2pmu_init(void) { return &xscale2pmu; } #else -static const struct arm_pmu *__init xscale1pmu_init(void) +static struct arm_pmu *__init xscale1pmu_init(void) { return NULL; } -static const struct arm_pmu *__init xscale2pmu_init(void) +static struct arm_pmu *__init xscale2pmu_init(void) { return NULL; } diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c index c53474fe84df..2c3407ee8576 100644 --- a/arch/arm/kernel/pmu.c +++ b/arch/arm/kernel/pmu.c @@ -10,192 +10,26 @@ * */ -#define pr_fmt(fmt) "PMU: " fmt - -#include <linux/cpumask.h> #include <linux/err.h> -#include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/of_device.h> -#include <linux/platform_device.h> #include <asm/pmu.h> -static volatile long pmu_lock; - -static struct platform_device *pmu_devices[ARM_NUM_PMU_DEVICES]; - -static int __devinit pmu_register(struct platform_device *pdev, - enum arm_pmu_type type) -{ - if (type < 0 || type >= ARM_NUM_PMU_DEVICES) { - pr_warning("received registration request for unknown " - "PMU device type %d\n", type); - return -EINVAL; - } - - if (pmu_devices[type]) { - pr_warning("rejecting duplicate registration of PMU device " - "type %d.", type); - return -ENOSPC; - } - - pr_info("registered new PMU device of type %d\n", type); - pmu_devices[type] = pdev; - return 0; -} - -#define OF_MATCH_PMU(_name, _type) { \ - .compatible = _name, \ - .data = (void *)_type, \ -} - -#define OF_MATCH_CPU(name) OF_MATCH_PMU(name, ARM_PMU_DEVICE_CPU) - -static struct of_device_id armpmu_of_device_ids[] = { - OF_MATCH_CPU("arm,cortex-a9-pmu"), - OF_MATCH_CPU("arm,cortex-a8-pmu"), - OF_MATCH_CPU("arm,arm1136-pmu"), - OF_MATCH_CPU("arm,arm1176-pmu"), - {}, -}; - -#define PLAT_MATCH_PMU(_name, _type) { \ - .name = _name, \ - .driver_data = _type, \ -} - -#define PLAT_MATCH_CPU(_name) PLAT_MATCH_PMU(_name, ARM_PMU_DEVICE_CPU) - -static struct platform_device_id armpmu_plat_device_ids[] = { - PLAT_MATCH_CPU("arm-pmu"), - {}, -}; - -enum arm_pmu_type armpmu_device_type(struct platform_device *pdev) -{ - const struct of_device_id *of_id; - const struct platform_device_id *pdev_id; - - /* provided by of_device_id table */ - if (pdev->dev.of_node) { - of_id = of_match_device(armpmu_of_device_ids, &pdev->dev); - BUG_ON(!of_id); - return (enum arm_pmu_type)of_id->data; - } - - /* Provided by platform_device_id table */ - pdev_id = platform_get_device_id(pdev); - BUG_ON(!pdev_id); - return pdev_id->driver_data; -} - -static int __devinit armpmu_device_probe(struct platform_device *pdev) -{ - return pmu_register(pdev, armpmu_device_type(pdev)); -} - -static struct platform_driver armpmu_driver = { - .driver = { - .name = "arm-pmu", - .of_match_table = armpmu_of_device_ids, - }, - .probe = armpmu_device_probe, - .id_table = armpmu_plat_device_ids, -}; - -static int __init register_pmu_driver(void) -{ - return platform_driver_register(&armpmu_driver); -} -device_initcall(register_pmu_driver); +/* + * PMU locking to ensure mutual exclusion between different subsystems. + */ +static unsigned long pmu_lock[BITS_TO_LONGS(ARM_NUM_PMU_DEVICES)]; -struct platform_device * +int reserve_pmu(enum arm_pmu_type type) { - struct platform_device *pdev; - - if (test_and_set_bit_lock(type, &pmu_lock)) { - pdev = ERR_PTR(-EBUSY); - } else if (pmu_devices[type] == NULL) { - clear_bit_unlock(type, &pmu_lock); - pdev = ERR_PTR(-ENODEV); - } else { - pdev = pmu_devices[type]; - } - - return pdev; + return test_and_set_bit_lock(type, pmu_lock) ? -EBUSY : 0; } EXPORT_SYMBOL_GPL(reserve_pmu); -int +void release_pmu(enum arm_pmu_type type) { - if (WARN_ON(!pmu_devices[type])) - return -EINVAL; - clear_bit_unlock(type, &pmu_lock); - return 0; -} -EXPORT_SYMBOL_GPL(release_pmu); - -static int -set_irq_affinity(int irq, - unsigned int cpu) -{ -#ifdef CONFIG_SMP - int err = irq_set_affinity(irq, cpumask_of(cpu)); - if (err) - pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n", - irq, cpu); - return err; -#else - return -EINVAL; -#endif -} - -static int -init_cpu_pmu(void) -{ - int i, irqs, err = 0; - struct platform_device *pdev = pmu_devices[ARM_PMU_DEVICE_CPU]; - - if (!pdev) - return -ENODEV; - - irqs = pdev->num_resources; - - /* - * If we have a single PMU interrupt that we can't shift, assume that - * we're running on a uniprocessor machine and continue. - */ - if (irqs == 1 && !irq_can_set_affinity(platform_get_irq(pdev, 0))) - return 0; - - for (i = 0; i < irqs; ++i) { - err = set_irq_affinity(platform_get_irq(pdev, i), i); - if (err) - break; - } - - return err; -} - -int -init_pmu(enum arm_pmu_type type) -{ - int err = 0; - - switch (type) { - case ARM_PMU_DEVICE_CPU: - err = init_cpu_pmu(); - break; - default: - pr_warning("attempt to initialise PMU of unknown " - "type %d\n", type); - err = -EINVAL; - } - - return err; + clear_bit_unlock(type, pmu_lock); } -EXPORT_SYMBOL_GPL(init_pmu); diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 1a347f481e5e..fd0814076ff6 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -319,7 +319,7 @@ void show_regs(struct pt_regs * regs) printk("\n"); printk("Pid: %d, comm: %20s\n", task_pid_nr(current), current->comm); __show_regs(regs); - __backtrace(); + dump_stack(); } ATOMIC_NOTIFIER_HEAD(thread_notify_head); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 6136144f8f8d..bda0a218f4a5 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -29,6 +29,8 @@ #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/memblock.h> +#include <linux/bug.h> +#include <linux/compiler.h> #include <asm/unified.h> #include <asm/cpu.h> @@ -42,6 +44,7 @@ #include <asm/cacheflush.h> #include <asm/cachetype.h> #include <asm/tlbflush.h> +#include <asm/system.h> #include <asm/prom.h> #include <asm/mach/arch.h> @@ -115,6 +118,13 @@ struct outer_cache_fns outer_cache __read_mostly; EXPORT_SYMBOL(outer_cache); #endif +/* + * Cached cpu_architecture() result for use by assembler code. + * C code should use the cpu_architecture() function instead of accessing this + * variable directly. + */ +int __cpu_architecture __read_mostly = CPU_ARCH_UNKNOWN; + struct stack { u32 irq[3]; u32 abt[3]; @@ -210,7 +220,7 @@ static const char *proc_arch[] = { "?(17)", }; -int cpu_architecture(void) +static int __get_cpu_architecture(void) { int cpu_arch; @@ -243,11 +253,22 @@ int cpu_architecture(void) return cpu_arch; } +int __pure cpu_architecture(void) +{ + BUG_ON(__cpu_architecture == CPU_ARCH_UNKNOWN); + + return __cpu_architecture; +} + static int cpu_has_aliasing_icache(unsigned int arch) { int aliasing_icache; unsigned int id_reg, num_sets, line_size; + /* PIPT caches never alias. */ + if (icache_is_pipt()) + return 0; + /* arch specifies the register format */ switch (arch) { case CPU_ARCH_ARMv7: @@ -282,8 +303,14 @@ static void __init cacheid_init(void) /* ARMv7 register format */ arch = CPU_ARCH_ARMv7; cacheid = CACHEID_VIPT_NONALIASING; - if ((cachetype & (3 << 14)) == 1 << 14) + switch (cachetype & (3 << 14)) { + case (1 << 14): cacheid |= CACHEID_ASID_TAGGED; + break; + case (3 << 14): + cacheid |= CACHEID_PIPT; + break; + } } else { arch = CPU_ARCH_ARMv6; if (cachetype & (1 << 23)) @@ -300,10 +327,11 @@ static void __init cacheid_init(void) printk("CPU: %s data cache, %s instruction cache\n", cache_is_vivt() ? "VIVT" : cache_is_vipt_aliasing() ? "VIPT aliasing" : - cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown", + cache_is_vipt_nonaliasing() ? "PIPT / VIPT nonaliasing" : "unknown", cache_is_vivt() ? "VIVT" : icache_is_vivt_asid_tagged() ? "VIVT ASID tagged" : icache_is_vipt_aliasing() ? "VIPT aliasing" : + icache_is_pipt() ? "PIPT" : cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown"); } @@ -414,6 +442,7 @@ static void __init setup_processor(void) } cpu_name = list->cpu_name; + __cpu_architecture = __get_cpu_architecture(); #ifdef MULTI_CPU processor = *list->proc; @@ -844,7 +873,7 @@ static struct machine_desc * __init setup_machine_tags(unsigned int nr) } if (mdesc->fixup) - mdesc->fixup(mdesc, tags, &from, &meminfo); + mdesc->fixup(tags, &from, &meminfo); if (tags->hdr.tag == ATAG_CORE) { if (meminfo.nr_banks != 0) diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index dc902f2c6845..020e99c845e7 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -8,92 +8,61 @@ .text /* - * Save CPU state for a suspend - * r1 = v:p offset - * r2 = suspend function arg0 - * r3 = suspend function + * Save CPU state for a suspend. This saves the CPU general purpose + * registers, and allocates space on the kernel stack to save the CPU + * specific registers and some other data for resume. + * r0 = suspend function arg0 + * r1 = suspend function */ ENTRY(__cpu_suspend) stmfd sp!, {r4 - r11, lr} #ifdef MULTI_CPU ldr r10, =processor - ldr r5, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state - ldr ip, [r10, #CPU_DO_RESUME] @ virtual resume function + ldr r4, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state #else - ldr r5, =cpu_suspend_size - ldr ip, =cpu_do_resume + ldr r4, =cpu_suspend_size #endif - mov r6, sp @ current virtual SP - sub sp, sp, r5 @ allocate CPU state on stack - mov r0, sp @ save pointer to CPU save block - add ip, ip, r1 @ convert resume fn to phys - stmfd sp!, {r1, r6, ip} @ save v:p, virt SP, phys resume fn - ldr r5, =sleep_save_sp - add r6, sp, r1 @ convert SP to phys - stmfd sp!, {r2, r3} @ save suspend func arg and pointer + mov r5, sp @ current virtual SP + add r4, r4, #12 @ Space for pgd, virt sp, phys resume fn + sub sp, sp, r4 @ allocate CPU state on stack + stmfd sp!, {r0, r1} @ save suspend func arg and pointer + add r0, sp, #8 @ save pointer to save block + mov r1, r4 @ size of save block + mov r2, r5 @ virtual SP + ldr r3, =sleep_save_sp #ifdef CONFIG_SMP ALT_SMP(mrc p15, 0, lr, c0, c0, 5) ALT_UP(mov lr, #0) and lr, lr, #15 - str r6, [r5, lr, lsl #2] @ save phys SP -#else - str r6, [r5] @ save phys SP -#endif -#ifdef MULTI_CPU - mov lr, pc - ldr pc, [r10, #CPU_DO_SUSPEND] @ save CPU state -#else - bl cpu_do_suspend -#endif - - @ flush data cache -#ifdef MULTI_CACHE - ldr r10, =cpu_cache - mov lr, pc - ldr pc, [r10, #CACHE_FLUSH_KERN_ALL] -#else - bl __cpuc_flush_kern_all + add r3, r3, lr, lsl #2 #endif + bl __cpu_suspend_save adr lr, BSYM(cpu_suspend_abort) ldmfd sp!, {r0, pc} @ call suspend fn ENDPROC(__cpu_suspend) .ltorg cpu_suspend_abort: - ldmia sp!, {r1 - r3} @ pop v:p, virt SP, phys resume fn + ldmia sp!, {r1 - r3} @ pop phys pgd, virt SP, phys resume fn + teq r0, #0 + moveq r0, #1 @ force non-zero value mov sp, r2 ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_suspend_abort) /* * r0 = control register value - * r1 = v:p offset (preserved by cpu_do_resume) - * r2 = phys page table base - * r3 = L1 section flags */ + .align 5 ENTRY(cpu_resume_mmu) - adr r4, cpu_resume_turn_mmu_on - mov r4, r4, lsr #20 - orr r3, r3, r4, lsl #20 - ldr r5, [r2, r4, lsl #2] @ save old mapping - str r3, [r2, r4, lsl #2] @ setup 1:1 mapping for mmu code - sub r2, r2, r1 ldr r3, =cpu_resume_after_mmu - bic r1, r0, #CR_C @ ensure D-cache is disabled - b cpu_resume_turn_mmu_on -ENDPROC(cpu_resume_mmu) - .ltorg - .align 5 -cpu_resume_turn_mmu_on: - mcr p15, 0, r1, c1, c0, 0 @ turn on MMU, I-cache, etc - mrc p15, 0, r1, c0, c0, 0 @ read id reg - mov r1, r1 - mov r1, r1 + mcr p15, 0, r0, c1, c0, 0 @ turn on MMU, I-cache, etc + mrc p15, 0, r0, c0, c0, 0 @ read id reg + mov r0, r0 + mov r0, r0 mov pc, r3 @ jump to virtual address -ENDPROC(cpu_resume_turn_mmu_on) +ENDPROC(cpu_resume_mmu) cpu_resume_after_mmu: - str r5, [r2, r4, lsl #2] @ restore old mapping - mcr p15, 0, r0, c1, c0, 0 @ turn on D-cache bl cpu_init @ restore the und/abt/irq banked regs mov r0, #0 @ return zero on success ldmfd sp!, {r4 - r11, pc} @@ -119,7 +88,7 @@ ENTRY(cpu_resume) ldr r0, sleep_save_sp @ stack phys addr #endif setmode PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1 @ set SVC, irqs off - @ load v:p, stack, resume fn + @ load phys pgd, stack, resume fn ARM( ldmia r0!, {r1, sp, pc} ) THUMB( ldmia r0!, {r1, r2, r3} ) THUMB( mov sp, r2 ) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index d88ff0230e82..ef5640b9e218 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -16,7 +16,6 @@ #include <linux/cache.h> #include <linux/profile.h> #include <linux/errno.h> -#include <linux/ftrace.h> #include <linux/mm.h> #include <linux/err.h> #include <linux/cpu.h> @@ -31,6 +30,8 @@ #include <asm/cacheflush.h> #include <asm/cpu.h> #include <asm/cputype.h> +#include <asm/exception.h> +#include <asm/topology.h> #include <asm/mmu_context.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -39,6 +40,7 @@ #include <asm/tlbflush.h> #include <asm/ptrace.h> #include <asm/localtimer.h> +#include <asm/smp_plat.h> /* * as from 2.5, kernels no longer have an init_tasks structure @@ -259,6 +261,20 @@ void __ref cpu_die(void) } #endif /* CONFIG_HOTPLUG_CPU */ +int __cpu_logical_map[NR_CPUS]; + +void __init smp_setup_processor_id(void) +{ + int i; + u32 cpu = is_smp() ? read_cpuid_mpidr() & 0xff : 0; + + cpu_logical_map(0) = cpu; + for (i = 1; i < NR_CPUS; ++i) + cpu_logical_map(i) = i == cpu ? 0 : i; + + printk(KERN_INFO "Booting Linux on physical CPU %d\n", cpu); +} + /* * Called by both boot and secondaries to move global data into * per-processor storage. @@ -268,6 +284,8 @@ static void __cpuinit smp_store_cpu_info(unsigned int cpuid) struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid); cpu_info->loops_per_jiffy = loops_per_jiffy; + + store_cpu_topology(cpuid); } /* @@ -301,17 +319,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void) */ platform_secondary_init(cpu); - /* - * Enable local interrupts. - */ notify_cpu_starting(cpu); - local_irq_enable(); - local_fiq_enable(); - - /* - * Setup the percpu timer for this CPU. - */ - percpu_timer_setup(); calibrate_delay(); @@ -323,10 +331,23 @@ asmlinkage void __cpuinit secondary_start_kernel(void) * before we continue. */ set_cpu_online(cpu, true); + + /* + * Setup the percpu timer for this CPU. + */ + percpu_timer_setup(); + while (!cpu_active(cpu)) cpu_relax(); /* + * cpu_active bit is set, so it's safe to enalbe interrupts + * now. + */ + local_irq_enable(); + local_fiq_enable(); + + /* * OK, it's off to the idle thread for us */ cpu_idle(); @@ -358,6 +379,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) { unsigned int ncores = num_possible_cpus(); + init_cpu_topology(); + smp_store_cpu_info(smp_processor_id()); /* @@ -437,10 +460,6 @@ u64 smp_irq_stat_cpu(unsigned int cpu) for (i = 0; i < NR_IPI; i++) sum += __get_irq_stat(cpu, ipi_irqs[i]); -#ifdef CONFIG_LOCAL_TIMERS - sum += __get_irq_stat(cpu, local_timer_irqs); -#endif - return sum; } @@ -457,33 +476,6 @@ static void ipi_timer(void) irq_exit(); } -#ifdef CONFIG_LOCAL_TIMERS -asmlinkage void __exception_irq_entry do_local_timer(struct pt_regs *regs) -{ - struct pt_regs *old_regs = set_irq_regs(regs); - int cpu = smp_processor_id(); - - if (local_timer_ack()) { - __inc_irq_stat(cpu, local_timer_irqs); - ipi_timer(); - } - - set_irq_regs(old_regs); -} - -void show_local_irqs(struct seq_file *p, int prec) -{ - unsigned int cpu; - - seq_printf(p, "%*s: ", prec, "LOC"); - - for_each_present_cpu(cpu) - seq_printf(p, "%10u ", __get_irq_stat(cpu, local_timer_irqs)); - - seq_printf(p, " Local timer interrupts\n"); -} -#endif - #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST static void smp_timer_broadcast(const struct cpumask *mask) { @@ -534,11 +526,11 @@ static void percpu_timer_stop(void) unsigned int cpu = smp_processor_id(); struct clock_event_device *evt = &per_cpu(percpu_clockevent, cpu); - evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt); + local_timer_stop(evt); } #endif -static DEFINE_SPINLOCK(stop_lock); +static DEFINE_RAW_SPINLOCK(stop_lock); /* * ipi_cpu_stop - handle IPI from smp_send_stop() @@ -547,10 +539,10 @@ static void ipi_cpu_stop(unsigned int cpu) { if (system_state == SYSTEM_BOOTING || system_state == SYSTEM_RUNNING) { - spin_lock(&stop_lock); + raw_spin_lock(&stop_lock); printk(KERN_CRIT "CPU%u: stopping\n", cpu); dump_stack(); - spin_unlock(&stop_lock); + raw_spin_unlock(&stop_lock); } set_cpu_online(cpu, false); @@ -567,6 +559,11 @@ static void ipi_cpu_stop(unsigned int cpu) */ asmlinkage void __exception_irq_entry do_IPI(int ipinr, struct pt_regs *regs) { + handle_IPI(ipinr, regs); +} + +void handle_IPI(int ipinr, struct pt_regs *regs) +{ unsigned int cpu = smp_processor_id(); struct pt_regs *old_regs = set_irq_regs(regs); diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index 7fcddb75c877..8f5dd7963356 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -34,7 +34,7 @@ unsigned int __init scu_get_core_count(void __iomem *scu_base) /* * Enable the SCU */ -void __init scu_enable(void __iomem *scu_base) +void scu_enable(void __iomem *scu_base) { u32 scu_ctrl; diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index 01c186222f3b..a8a6682d6b52 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -19,6 +19,7 @@ #include <linux/io.h> #include <asm/smp_twd.h> +#include <asm/localtimer.h> #include <asm/hardware/gic.h> /* set up by the platform code */ @@ -26,6 +27,8 @@ void __iomem *twd_base; static unsigned long twd_timer_rate; +static struct clock_event_device __percpu **twd_evt; + static void twd_set_mode(enum clock_event_mode mode, struct clock_event_device *clk) { @@ -80,6 +83,12 @@ int twd_timer_ack(void) return 0; } +void twd_timer_stop(struct clock_event_device *clk) +{ + twd_set_mode(CLOCK_EVT_MODE_UNUSED, clk); + disable_percpu_irq(clk->irq); +} + static void __cpuinit twd_calibrate_rate(void) { unsigned long count; @@ -119,11 +128,43 @@ static void __cpuinit twd_calibrate_rate(void) } } +static irqreturn_t twd_handler(int irq, void *dev_id) +{ + struct clock_event_device *evt = *(struct clock_event_device **)dev_id; + + if (twd_timer_ack()) { + evt->event_handler(evt); + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + /* * Setup the local clock events for a CPU. */ void __cpuinit twd_timer_setup(struct clock_event_device *clk) { + struct clock_event_device **this_cpu_clk; + + if (!twd_evt) { + int err; + + twd_evt = alloc_percpu(struct clock_event_device *); + if (!twd_evt) { + pr_err("twd: can't allocate memory\n"); + return; + } + + err = request_percpu_irq(clk->irq, twd_handler, + "twd", twd_evt); + if (err) { + pr_err("twd: can't register interrupt %d (%d)\n", + clk->irq, err); + return; + } + } + twd_calibrate_rate(); clk->name = "local_timer"; @@ -137,8 +178,10 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk) clk->max_delta_ns = clockevent_delta2ns(0xffffffff, clk); clk->min_delta_ns = clockevent_delta2ns(0xf, clk); + this_cpu_clk = __this_cpu_ptr(twd_evt); + *this_cpu_clk = clk; + clockevents_register_device(clk); - /* Make sure our local interrupt controller has this enabled */ - gic_enable_ppi(clk->irq); + enable_percpu_irq(clk->irq, 0); } diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c new file mode 100644 index 000000000000..93a22d282c16 --- /dev/null +++ b/arch/arm/kernel/suspend.c @@ -0,0 +1,72 @@ +#include <linux/init.h> + +#include <asm/pgalloc.h> +#include <asm/pgtable.h> +#include <asm/memory.h> +#include <asm/suspend.h> +#include <asm/tlbflush.h> + +static pgd_t *suspend_pgd; + +extern int __cpu_suspend(unsigned long, int (*)(unsigned long)); +extern void cpu_resume_mmu(void); + +/* + * This is called by __cpu_suspend() to save the state, and do whatever + * flushing is required to ensure that when the CPU goes to sleep we have + * the necessary data available when the caches are not searched. + */ +void __cpu_suspend_save(u32 *ptr, u32 ptrsz, u32 sp, u32 *save_ptr) +{ + *save_ptr = virt_to_phys(ptr); + + /* This must correspond to the LDM in cpu_resume() assembly */ + *ptr++ = virt_to_phys(suspend_pgd); + *ptr++ = sp; + *ptr++ = virt_to_phys(cpu_do_resume); + + cpu_do_suspend(ptr); + + flush_cache_all(); + outer_clean_range(*save_ptr, *save_ptr + ptrsz); + outer_clean_range(virt_to_phys(save_ptr), + virt_to_phys(save_ptr) + sizeof(*save_ptr)); +} + +/* + * Hide the first two arguments to __cpu_suspend - these are an implementation + * detail which platform code shouldn't have to know about. + */ +int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) +{ + struct mm_struct *mm = current->active_mm; + int ret; + + if (!suspend_pgd) + return -EINVAL; + + /* + * Provide a temporary page table with an identity mapping for + * the MMU-enable code, required for resuming. On successful + * resume (indicated by a zero return code), we need to switch + * back to the correct page tables. + */ + ret = __cpu_suspend(arg, fn); + if (ret == 0) { + cpu_switch_mm(mm->pgd, mm); + local_flush_tlb_all(); + } + + return ret; +} + +static int __init cpu_suspend_init(void) +{ + suspend_pgd = pgd_alloc(&init_mm); + if (suspend_pgd) { + unsigned long addr = virt_to_phys(cpu_resume_mmu); + identity_mapping_add(suspend_pgd, addr, addr + SECTION_SIZE); + } + return suspend_pgd ? 0 : -ENOMEM; +} +core_initcall(cpu_suspend_init); diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c index cb634c3e28e9..5a54b95d6bd2 100644 --- a/arch/arm/kernel/time.c +++ b/arch/arm/kernel/time.c @@ -39,13 +39,11 @@ */ static struct sys_timer *system_timer; -#if defined(CONFIG_RTC_DRV_CMOS) || defined(CONFIG_RTC_DRV_CMOS_MODULE) +#if defined(CONFIG_RTC_DRV_CMOS) || defined(CONFIG_RTC_DRV_CMOS_MODULE) || \ + defined(CONFIG_NVRAM) || defined(CONFIG_NVRAM_MODULE) /* this needs a better home */ DEFINE_SPINLOCK(rtc_lock); - -#ifdef CONFIG_RTC_DRV_CMOS_MODULE EXPORT_SYMBOL(rtc_lock); -#endif #endif /* pc-style 'CMOS' RTC support */ /* change this if you have some constant time drift */ diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c new file mode 100644 index 000000000000..1040c00405d0 --- /dev/null +++ b/arch/arm/kernel/topology.c @@ -0,0 +1,148 @@ +/* + * arch/arm/kernel/topology.c + * + * Copyright (C) 2011 Linaro Limited. + * Written by: Vincent Guittot + * + * based on arch/sh/kernel/topology.c + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ + +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/init.h> +#include <linux/percpu.h> +#include <linux/node.h> +#include <linux/nodemask.h> +#include <linux/sched.h> + +#include <asm/cputype.h> +#include <asm/topology.h> + +#define MPIDR_SMP_BITMASK (0x3 << 30) +#define MPIDR_SMP_VALUE (0x2 << 30) + +#define MPIDR_MT_BITMASK (0x1 << 24) + +/* + * These masks reflect the current use of the affinity levels. + * The affinity level can be up to 16 bits according to ARM ARM + */ + +#define MPIDR_LEVEL0_MASK 0x3 +#define MPIDR_LEVEL0_SHIFT 0 + +#define MPIDR_LEVEL1_MASK 0xF +#define MPIDR_LEVEL1_SHIFT 8 + +#define MPIDR_LEVEL2_MASK 0xFF +#define MPIDR_LEVEL2_SHIFT 16 + +struct cputopo_arm cpu_topology[NR_CPUS]; + +const struct cpumask *cpu_coregroup_mask(unsigned int cpu) +{ + return &cpu_topology[cpu].core_sibling; +} + +/* + * store_cpu_topology is called at boot when only one cpu is running + * and with the mutex cpu_hotplug.lock locked, when several cpus have booted, + * which prevents simultaneous write access to cpu_topology array + */ +void store_cpu_topology(unsigned int cpuid) +{ + struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid]; + unsigned int mpidr; + unsigned int cpu; + + /* If the cpu topology has been already set, just return */ + if (cpuid_topo->core_id != -1) + return; + + mpidr = read_cpuid_mpidr(); + + /* create cpu topology mapping */ + if ((mpidr & MPIDR_SMP_BITMASK) == MPIDR_SMP_VALUE) { + /* + * This is a multiprocessor system + * multiprocessor format & multiprocessor mode field are set + */ + + if (mpidr & MPIDR_MT_BITMASK) { + /* core performance interdependency */ + cpuid_topo->thread_id = (mpidr >> MPIDR_LEVEL0_SHIFT) + & MPIDR_LEVEL0_MASK; + cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL1_SHIFT) + & MPIDR_LEVEL1_MASK; + cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL2_SHIFT) + & MPIDR_LEVEL2_MASK; + } else { + /* largely independent cores */ + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL0_SHIFT) + & MPIDR_LEVEL0_MASK; + cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL1_SHIFT) + & MPIDR_LEVEL1_MASK; + } + } else { + /* + * This is an uniprocessor system + * we are in multiprocessor format but uniprocessor system + * or in the old uniprocessor format + */ + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = 0; + cpuid_topo->socket_id = -1; + } + + /* update core and thread sibling masks */ + for_each_possible_cpu(cpu) { + struct cputopo_arm *cpu_topo = &cpu_topology[cpu]; + + if (cpuid_topo->socket_id == cpu_topo->socket_id) { + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, + &cpuid_topo->core_sibling); + + if (cpuid_topo->core_id == cpu_topo->core_id) { + cpumask_set_cpu(cpuid, + &cpu_topo->thread_sibling); + if (cpu != cpuid) + cpumask_set_cpu(cpu, + &cpuid_topo->thread_sibling); + } + } + } + smp_wmb(); + + printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", + cpuid, cpu_topology[cpuid].thread_id, + cpu_topology[cpuid].core_id, + cpu_topology[cpuid].socket_id, mpidr); +} + +/* + * init_cpu_topology is called at boot when only one cpu is running + * which prevent simultaneous write access to cpu_topology array + */ +void init_cpu_topology(void) +{ + unsigned int cpu; + + /* init core mask */ + for_each_possible_cpu(cpu) { + struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]); + + cpu_topo->thread_id = -1; + cpu_topo->core_id = -1; + cpu_topo->socket_id = -1; + cpumask_clear(&cpu_topo->core_sibling); + cpumask_clear(&cpu_topo->thread_sibling); + } + smp_wmb(); +} diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index bc9f9da782cb..99a572702509 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -21,12 +21,14 @@ #include <linux/kdebug.h> #include <linux/module.h> #include <linux/kexec.h> +#include <linux/bug.h> #include <linux/delay.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/atomic.h> #include <asm/cacheflush.h> +#include <asm/exception.h> #include <asm/system.h> #include <asm/unistd.h> #include <asm/traps.h> @@ -255,7 +257,7 @@ static int __die(const char *str, int err, struct thread_info *thread, struct pt return ret; } -static DEFINE_SPINLOCK(die_lock); +static DEFINE_RAW_SPINLOCK(die_lock); /* * This function is protected against re-entrancy. @@ -267,9 +269,11 @@ void die(const char *str, struct pt_regs *regs, int err) oops_enter(); - spin_lock_irq(&die_lock); + raw_spin_lock_irq(&die_lock); console_verbose(); bust_spinlocks(1); + if (!user_mode(regs)) + report_bug(regs->ARM_pc, regs); ret = __die(str, err, thread, regs); if (regs && kexec_should_crash(thread->task)) @@ -277,7 +281,7 @@ void die(const char *str, struct pt_regs *regs, int err) bust_spinlocks(0); add_taint(TAINT_DIE); - spin_unlock_irq(&die_lock); + raw_spin_unlock_irq(&die_lock); oops_exit(); if (in_interrupt()) @@ -301,25 +305,43 @@ void arm_notify_die(const char *str, struct pt_regs *regs, } } +#ifdef CONFIG_GENERIC_BUG + +int is_valid_bugaddr(unsigned long pc) +{ +#ifdef CONFIG_THUMB2_KERNEL + unsigned short bkpt; +#else + unsigned long bkpt; +#endif + + if (probe_kernel_address((unsigned *)pc, bkpt)) + return 0; + + return bkpt == BUG_INSTR_VALUE; +} + +#endif + static LIST_HEAD(undef_hook); -static DEFINE_SPINLOCK(undef_lock); +static DEFINE_RAW_SPINLOCK(undef_lock); void register_undef_hook(struct undef_hook *hook) { unsigned long flags; - spin_lock_irqsave(&undef_lock, flags); + raw_spin_lock_irqsave(&undef_lock, flags); list_add(&hook->node, &undef_hook); - spin_unlock_irqrestore(&undef_lock, flags); + raw_spin_unlock_irqrestore(&undef_lock, flags); } void unregister_undef_hook(struct undef_hook *hook) { unsigned long flags; - spin_lock_irqsave(&undef_lock, flags); + raw_spin_lock_irqsave(&undef_lock, flags); list_del(&hook->node); - spin_unlock_irqrestore(&undef_lock, flags); + raw_spin_unlock_irqrestore(&undef_lock, flags); } static int call_undef_hook(struct pt_regs *regs, unsigned int instr) @@ -328,12 +350,12 @@ static int call_undef_hook(struct pt_regs *regs, unsigned int instr) unsigned long flags; int (*fn)(struct pt_regs *regs, unsigned int instr) = NULL; - spin_lock_irqsave(&undef_lock, flags); + raw_spin_lock_irqsave(&undef_lock, flags); list_for_each_entry(hook, &undef_hook, node) if ((instr & hook->instr_mask) == hook->instr_val && (regs->ARM_cpsr & hook->cpsr_mask) == hook->cpsr_val) fn = hook->fn; - spin_unlock_irqrestore(&undef_lock, flags); + raw_spin_unlock_irqrestore(&undef_lock, flags); return fn ? fn(regs, instr) : 1; } @@ -706,16 +728,6 @@ baddataabort(int code, unsigned long instr, struct pt_regs *regs) arm_notify_die("unknown data abort code", regs, &info, instr, 0); } -void __attribute__((noreturn)) __bug(const char *file, int line) -{ - printk(KERN_CRIT"kernel BUG at %s:%d!\n", file, line); - *(int *)0 = 0; - - /* Avoid "noreturn function does return" */ - for (;;); -} -EXPORT_SYMBOL(__bug); - void __readwrite_bug(const char *fn) { printk("%s called, but not implemented\n", fn); diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 4e66f62b8d41..20b3041e0860 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -21,7 +21,8 @@ #define ARM_CPU_KEEP(x) #endif -#if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK) +#if (defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)) || \ + defined(CONFIG_GENERIC_BUG) #define ARM_EXIT_KEEP(x) x #define ARM_EXIT_DISCARD(x) #else diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S index a673297b0cf1..cd07b5814c23 100644 --- a/arch/arm/lib/backtrace.S +++ b/arch/arm/lib/backtrace.S @@ -22,15 +22,10 @@ #define mask r7 #define offset r8 -ENTRY(__backtrace) - mov r1, #0x10 - mov r0, fp - ENTRY(c_backtrace) #if !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK) mov pc, lr -ENDPROC(__backtrace) ENDPROC(c_backtrace) #else stmfd sp!, {r4 - r8, lr} @ Save an extra register so we have a location... @@ -107,7 +102,6 @@ for_each_frame: tst frame, mask @ Check for address exceptions mov r1, frame bl printk no_frame: ldmfd sp!, {r4 - r8, pc} -ENDPROC(__backtrace) ENDPROC(c_backtrace) .pushsection __ex_table,"a" diff --git a/arch/arm/lib/div64.S b/arch/arm/lib/div64.S index faa7748142da..e55c4842c290 100644 --- a/arch/arm/lib/div64.S +++ b/arch/arm/lib/div64.S @@ -13,6 +13,7 @@ */ #include <linux/linkage.h> +#include <asm/unwind.h> #ifdef __ARMEB__ #define xh r0 @@ -44,6 +45,7 @@ */ ENTRY(__do_div64) +UNWIND(.fnstart) @ Test for easy paths first. subs ip, r4, #1 @@ -189,7 +191,12 @@ ENTRY(__do_div64) moveq yh, xh moveq xh, #0 moveq pc, lr +UNWIND(.fnend) +UNWIND(.fnstart) +UNWIND(.pad #4) +UNWIND(.save {lr}) +Ldiv0_64: @ Division by 0: str lr, [sp, #-8]! bl __div0 @@ -200,4 +207,5 @@ ENTRY(__do_div64) mov xh, #0 ldr pc, [sp], #8 +UNWIND(.fnend) ENDPROC(__do_div64) diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index 8b9b13649f81..025f742dd4df 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -17,6 +17,7 @@ #include <linux/sched.h> #include <linux/hardirq.h> /* for in_atomic() */ #include <linux/gfp.h> +#include <linux/highmem.h> #include <asm/current.h> #include <asm/page.h> diff --git a/arch/arm/mach-at91/Makefile.boot b/arch/arm/mach-at91/Makefile.boot index 3462b815054a..9ab5a3e5f4f1 100644 --- a/arch/arm/mach-at91/Makefile.boot +++ b/arch/arm/mach-at91/Makefile.boot @@ -4,15 +4,15 @@ # INITRD_PHYS must be in RAM ifeq ($(CONFIG_ARCH_AT91CAP9),y) - zreladdr-y := 0x70008000 + zreladdr-y += 0x70008000 params_phys-y := 0x70000100 initrd_phys-y := 0x70410000 else ifeq ($(CONFIG_ARCH_AT91SAM9G45),y) - zreladdr-y := 0x70008000 + zreladdr-y += 0x70008000 params_phys-y := 0x70000100 initrd_phys-y := 0x70410000 else - zreladdr-y := 0x20008000 + zreladdr-y += 0x20008000 params_phys-y := 0x20000100 initrd_phys-y := 0x20410000 endif diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c index a53b3de9daa2..3c2b580b9d75 100644 --- a/arch/arm/mach-at91/at91sam9260_devices.c +++ b/arch/arm/mach-at91/at91sam9260_devices.c @@ -319,7 +319,7 @@ void __init at91_add_device_mci(short mmc_id, struct mci_platform_data *data) if (!data) return; - for (i = 0; i < ATMEL_MCI_MAX_NR_SLOTS; i++) { + for (i = 0; i < ATMCI_MAX_NR_SLOTS; i++) { if (data->slot[i].bus_width) { /* input/irq */ if (data->slot[i].detect_pin) { diff --git a/arch/arm/mach-bcmring/Kconfig b/arch/arm/mach-bcmring/Kconfig index 457b4384913e..9170d16dca50 100644 --- a/arch/arm/mach-bcmring/Kconfig +++ b/arch/arm/mach-bcmring/Kconfig @@ -17,5 +17,3 @@ config BCM_ZRELADDR hex "Compressed ZREL ADDR" endmenu - -# source "drivers/char/bcmring/Kconfig" diff --git a/arch/arm/mach-bcmring/Makefile.boot b/arch/arm/mach-bcmring/Makefile.boot index fb53b283bebb..aef2467757fa 100644 --- a/arch/arm/mach-bcmring/Makefile.boot +++ b/arch/arm/mach-bcmring/Makefile.boot @@ -1,6 +1,6 @@ # Address where decompressor will be written and eventually executed. # # default to SDRAM -zreladdr-y := $(CONFIG_BCM_ZRELADDR) +zreladdr-y += $(CONFIG_BCM_ZRELADDR) params_phys-y := 0x00000800 diff --git a/arch/arm/mach-bcmring/arch.c b/arch/arm/mach-bcmring/arch.c index a604b9ebb501..31a143592c81 100644 --- a/arch/arm/mach-bcmring/arch.c +++ b/arch/arm/mach-bcmring/arch.c @@ -136,8 +136,8 @@ static void __init bcmring_init_machine(void) * *****************************************************************************/ -static void __init bcmring_fixup(struct machine_desc *desc, - struct tag *t, char **cmdline, struct meminfo *mi) { +static void __init bcmring_fixup(struct tag *t, char **cmdline, + struct meminfo *mi) { #ifdef CONFIG_BLK_DEV_INITRD printk(KERN_NOTICE "bcmring_fixup\n"); t->hdr.tag = ATAG_CORE; diff --git a/arch/arm/mach-bcmring/irq.c b/arch/arm/mach-bcmring/irq.c index c48feaf4e8e9..437fa683bcb2 100644 --- a/arch/arm/mach-bcmring/irq.c +++ b/arch/arm/mach-bcmring/irq.c @@ -20,7 +20,6 @@ #include <linux/stddef.h> #include <linux/list.h> #include <linux/timer.h> -#include <linux/version.h> #include <linux/io.h> #include <mach/hardware.h> diff --git a/arch/arm/mach-bcmring/timer.c b/arch/arm/mach-bcmring/timer.c index 2d415d2a8e68..af9c3d7e2a0c 100644 --- a/arch/arm/mach-bcmring/timer.c +++ b/arch/arm/mach-bcmring/timer.c @@ -12,7 +12,6 @@ * consent. *****************************************************************************/ -#include <linux/version.h> #include <linux/types.h> #include <linux/module.h> #include <csp/tmrHw.h> diff --git a/arch/arm/mach-clps711x/Makefile.boot b/arch/arm/mach-clps711x/Makefile.boot index a51fcef64fe0..9398e859b5af 100644 --- a/arch/arm/mach-clps711x/Makefile.boot +++ b/arch/arm/mach-clps711x/Makefile.boot @@ -1,5 +1,5 @@ # The standard locations for stuff on CLPS711x type processors - zreladdr-y := 0xc0028000 + zreladdr-y += 0xc0028000 params_phys-y := 0xc0000100 # Should probably have some agreement on these... initrd_phys-$(CONFIG_ARCH_P720T) := 0xc0400000 diff --git a/arch/arm/mach-clps711x/clep7312.c b/arch/arm/mach-clps711x/clep7312.c index 06c8abd9371f..80496c09ac59 100644 --- a/arch/arm/mach-clps711x/clep7312.c +++ b/arch/arm/mach-clps711x/clep7312.c @@ -26,8 +26,7 @@ #include "common.h" static void __init -fixup_clep7312(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fixup_clep7312(struct tag *tags, char **cmdline, struct meminfo *mi) { mi->nr_banks=1; mi->bank[0].start = 0xc0000000; diff --git a/arch/arm/mach-clps711x/edb7211-arch.c b/arch/arm/mach-clps711x/edb7211-arch.c index abf522d1ec9b..9721f6111dc0 100644 --- a/arch/arm/mach-clps711x/edb7211-arch.c +++ b/arch/arm/mach-clps711x/edb7211-arch.c @@ -37,8 +37,7 @@ static void __init edb7211_reserve(void) } static void __init -fixup_edb7211(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fixup_edb7211(struct tag *tags, char **cmdline, struct meminfo *mi) { /* * Bank start addresses are not present in the information diff --git a/arch/arm/mach-clps711x/fortunet.c b/arch/arm/mach-clps711x/fortunet.c index b6f7d86bb1c9..d99256687298 100644 --- a/arch/arm/mach-clps711x/fortunet.c +++ b/arch/arm/mach-clps711x/fortunet.c @@ -57,8 +57,7 @@ typedef struct tag_IMAGE_PARAMS #define IMAGE_PARAMS_PHYS 0xC01F0000 static void __init -fortunet_fixup(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fortunet_fixup(struct tag *tags, char **cmdline, struct meminfo *mi) { IMAGE_PARAMS *ip = phys_to_virt(IMAGE_PARAMS_PHYS); *cmdline = phys_to_virt(ip->command_line); diff --git a/arch/arm/mach-clps711x/p720t.c b/arch/arm/mach-clps711x/p720t.c index e7f75aeb1e5b..6ecea95f38b2 100644 --- a/arch/arm/mach-clps711x/p720t.c +++ b/arch/arm/mach-clps711x/p720t.c @@ -56,8 +56,7 @@ static struct map_desc p720t_io_desc[] __initdata = { }; static void __init -fixup_p720t(struct machine_desc *desc, struct tag *tag, - char **cmdline, struct meminfo *mi) +fixup_p720t(struct tag *tag, char **cmdline, struct meminfo *mi) { /* * Our bootloader doesn't setup any tags (yet). diff --git a/arch/arm/mach-cns3xxx/Makefile.boot b/arch/arm/mach-cns3xxx/Makefile.boot index 777012865220..d079de0b6e3b 100644 --- a/arch/arm/mach-cns3xxx/Makefile.boot +++ b/arch/arm/mach-cns3xxx/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00C00000 diff --git a/arch/arm/mach-davinci/Makefile.boot b/arch/arm/mach-davinci/Makefile.boot index db97ef2c6477..04a6c4e67b14 100644 --- a/arch/arm/mach-davinci/Makefile.boot +++ b/arch/arm/mach-davinci/Makefile.boot @@ -2,12 +2,12 @@ ifeq ($(CONFIG_ARCH_DAVINCI_DA8XX),y) ifeq ($(CONFIG_ARCH_DAVINCI_DMx),y) $(error Cannot enable DaVinci and DA8XX platforms concurrently) else - zreladdr-y := 0xc0008000 + zreladdr-y += 0xc0008000 params_phys-y := 0xc0000100 initrd_phys-y := 0xc0800000 endif else - zreladdr-y := 0x80008000 + zreladdr-y += 0x80008000 params_phys-y := 0x80000100 initrd_phys-y := 0x80800000 endif diff --git a/arch/arm/mach-dove/Makefile.boot b/arch/arm/mach-dove/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-dove/Makefile.boot +++ b/arch/arm/mach-dove/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-ebsa110/Makefile.boot b/arch/arm/mach-ebsa110/Makefile.boot index 232126044935..83cf07c38ada 100644 --- a/arch/arm/mach-ebsa110/Makefile.boot +++ b/arch/arm/mach-ebsa110/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000400 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-ebsa110/include/mach/io.h b/arch/arm/mach-ebsa110/include/mach/io.h index f68daa632af0..44679db672fb 100644 --- a/arch/arm/mach-ebsa110/include/mach/io.h +++ b/arch/arm/mach-ebsa110/include/mach/io.h @@ -13,8 +13,6 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H -#define IO_SPACE_LIMIT 0xffff - u8 __inb8(unsigned int port); void __outb8(u8 val, unsigned int port); diff --git a/arch/arm/mach-ep93xx/Makefile.boot b/arch/arm/mach-ep93xx/Makefile.boot index 0ad33f15c622..d3113a71cb40 100644 --- a/arch/arm/mach-ep93xx/Makefile.boot +++ b/arch/arm/mach-ep93xx/Makefile.boot @@ -1,14 +1,14 @@ - zreladdr-$(CONFIG_EP93XX_SDCE3_SYNC_PHYS_OFFSET) := 0x00008000 + zreladdr-$(CONFIG_EP93XX_SDCE3_SYNC_PHYS_OFFSET) += 0x00008000 params_phys-$(CONFIG_EP93XX_SDCE3_SYNC_PHYS_OFFSET) := 0x00000100 - zreladdr-$(CONFIG_EP93XX_SDCE0_PHYS_OFFSET) := 0xc0008000 + zreladdr-$(CONFIG_EP93XX_SDCE0_PHYS_OFFSET) += 0xc0008000 params_phys-$(CONFIG_EP93XX_SDCE0_PHYS_OFFSET) := 0xc0000100 - zreladdr-$(CONFIG_EP93XX_SDCE1_PHYS_OFFSET) := 0xd0008000 + zreladdr-$(CONFIG_EP93XX_SDCE1_PHYS_OFFSET) += 0xd0008000 params_phys-$(CONFIG_EP93XX_SDCE1_PHYS_OFFSET) := 0xd0000100 - zreladdr-$(CONFIG_EP93XX_SDCE2_PHYS_OFFSET) := 0xe0008000 + zreladdr-$(CONFIG_EP93XX_SDCE2_PHYS_OFFSET) += 0xe0008000 params_phys-$(CONFIG_EP93XX_SDCE2_PHYS_OFFSET) := 0xe0000100 - zreladdr-$(CONFIG_EP93XX_SDCE3_ASYNC_PHYS_OFFSET) := 0xf0008000 + zreladdr-$(CONFIG_EP93XX_SDCE3_ASYNC_PHYS_OFFSET) += 0xf0008000 params_phys-$(CONFIG_EP93XX_SDCE3_ASYNC_PHYS_OFFSET) := 0xf0000100 diff --git a/arch/arm/mach-ep93xx/edb93xx.c b/arch/arm/mach-ep93xx/edb93xx.c index c63a5ec1a8e3..70ef8c527d27 100644 --- a/arch/arm/mach-ep93xx/edb93xx.c +++ b/arch/arm/mach-ep93xx/edb93xx.c @@ -160,6 +160,11 @@ static void __init edb93xx_register_spi(void) /************************************************************************* * EDB93xx I2S *************************************************************************/ +static struct platform_device edb93xx_audio_device = { + .name = "edb93xx-audio", + .id = -1, +}; + static int __init edb93xx_has_audio(void) { return (machine_is_edb9301() || machine_is_edb9302() || @@ -171,6 +176,7 @@ static void __init edb93xx_register_i2s(void) { if (edb93xx_has_audio()) { ep93xx_register_i2s(); + platform_device_register(&edb93xx_audio_device); } } diff --git a/arch/arm/mach-ep93xx/include/mach/gpio.h b/arch/arm/mach-ep93xx/include/mach/gpio.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/arch/arm/mach-ep93xx/include/mach/gpio.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/arm/mach-ep93xx/simone.c b/arch/arm/mach-ep93xx/simone.c index d6f286b4db9c..52e090dc9d27 100644 --- a/arch/arm/mach-ep93xx/simone.c +++ b/arch/arm/mach-ep93xx/simone.c @@ -53,6 +53,17 @@ static struct i2c_board_info __initdata simone_i2c_board_info[] = { }, }; +static struct platform_device simone_audio_device = { + .name = "simone-audio", + .id = -1, +}; + +static void __init simone_register_audio(void) +{ + ep93xx_register_ac97(); + platform_device_register(&simone_audio_device); +} + static void __init simone_init_machine(void) { ep93xx_init_devices(); @@ -61,7 +72,7 @@ static void __init simone_init_machine(void) ep93xx_register_fb(&simone_fb_info); ep93xx_register_i2c(&simone_i2c_gpio_data, simone_i2c_board_info, ARRAY_SIZE(simone_i2c_board_info)); - ep93xx_register_ac97(); + simone_register_audio(); } MACHINE_START(SIM_ONE, "Simplemachines Sim.One Board") diff --git a/arch/arm/mach-ep93xx/snappercl15.c b/arch/arm/mach-ep93xx/snappercl15.c index 2b4d4b0201df..8121e3aedc0a 100644 --- a/arch/arm/mach-ep93xx/snappercl15.c +++ b/arch/arm/mach-ep93xx/snappercl15.c @@ -150,6 +150,17 @@ static struct ep93xxfb_mach_info __initdata snappercl15_fb_info = { .bpp = 16, }; +static struct platform_device snappercl15_audio_device = { + .name = "snappercl15-audio", + .id = -1, +}; + +static void __init snappercl15_register_audio(void) +{ + ep93xx_register_i2s(); + platform_device_register(&snappercl15_audio_device); +} + static void __init snappercl15_init_machine(void) { ep93xx_init_devices(); @@ -157,7 +168,7 @@ static void __init snappercl15_init_machine(void) ep93xx_register_i2c(&snappercl15_i2c_gpio_data, snappercl15_i2c_data, ARRAY_SIZE(snappercl15_i2c_data)); ep93xx_register_fb(&snappercl15_fb_info); - ep93xx_register_i2s(); + snappercl15_register_audio(); platform_device_register(&snappercl15_nand_device); } diff --git a/arch/arm/mach-exynos4/Kconfig b/arch/arm/mach-exynos4/Kconfig index 0c77ab99fa16..fc1f92dfbea8 100644 --- a/arch/arm/mach-exynos4/Kconfig +++ b/arch/arm/mach-exynos4/Kconfig @@ -12,6 +12,7 @@ if ARCH_EXYNOS4 config CPU_EXYNOS4210 bool select S3C_PL330_DMA + select ARM_CPU_SUSPEND if PM help Enable EXYNOS4210 CPU support diff --git a/arch/arm/mach-exynos4/Makefile.boot b/arch/arm/mach-exynos4/Makefile.boot index d65956ffb43d..b9862e22bf10 100644 --- a/arch/arm/mach-exynos4/Makefile.boot +++ b/arch/arm/mach-exynos4/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x40008000 + zreladdr-y += 0x40008000 params_phys-y := 0x40000100 diff --git a/arch/arm/mach-exynos4/include/mach/entry-macro.S b/arch/arm/mach-exynos4/include/mach/entry-macro.S index d7a1e281ce7a..006a4f4c65c6 100644 --- a/arch/arm/mach-exynos4/include/mach/entry-macro.S +++ b/arch/arm/mach-exynos4/include/mach/entry-macro.S @@ -55,7 +55,7 @@ bic \irqnr, \irqstat, #0x1c00 - cmp \irqnr, #29 + cmp \irqnr, #15 cmpcc \irqnr, \irqnr cmpne \irqnr, \tmp cmpcs \irqnr, \irqnr @@ -76,8 +76,3 @@ strcc \irqstat, [\base, #GIC_CPU_EOI] cmpcs \irqnr, \irqnr .endm - - /* As above, this assumes that irqstat and base are preserved.. */ - - .macro test_for_ltirq, irqnr, irqstat, base, tmp - .endm diff --git a/arch/arm/mach-exynos4/mct.c b/arch/arm/mach-exynos4/mct.c index ddd86864fb83..582b874aab0e 100644 --- a/arch/arm/mach-exynos4/mct.c +++ b/arch/arm/mach-exynos4/mct.c @@ -386,9 +386,11 @@ static void exynos4_mct_tick_init(struct clock_event_device *evt) if (cpu == 0) { mct_tick0_event_irq.dev_id = &mct_tick[cpu]; + evt->irq = IRQ_MCT_L0; setup_irq(IRQ_MCT_L0, &mct_tick0_event_irq); } else { mct_tick1_event_irq.dev_id = &mct_tick[cpu]; + evt->irq = IRQ_MCT_L1; setup_irq(IRQ_MCT_L1, &mct_tick1_event_irq); irq_set_affinity(IRQ_MCT_L1, cpumask_of(1)); } @@ -402,9 +404,10 @@ int __cpuinit local_timer_setup(struct clock_event_device *evt) return 0; } -int local_timer_ack(void) +void local_timer_stop(struct clock_event_device *evt) { - return 0; + evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt); + disable_irq(evt->irq); } #endif /* CONFIG_LOCAL_TIMERS */ diff --git a/arch/arm/mach-exynos4/platsmp.c b/arch/arm/mach-exynos4/platsmp.c index df6ef1b2f98b..0c90896ad9a0 100644 --- a/arch/arm/mach-exynos4/platsmp.c +++ b/arch/arm/mach-exynos4/platsmp.c @@ -193,12 +193,10 @@ void __init smp_init_cpus(void) ncores = scu_base ? scu_get_core_count(scu_base) : 1; /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "EXYNOS4: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-footbridge/Kconfig b/arch/arm/mach-footbridge/Kconfig index c8e7afcf14ec..f643ef819da6 100644 --- a/arch/arm/mach-footbridge/Kconfig +++ b/arch/arm/mach-footbridge/Kconfig @@ -4,8 +4,8 @@ menu "Footbridge Implementations" config ARCH_CATS bool "CATS" - select CLKSRC_I8253 select CLKEVT_I8253 + select CLKSRC_I8253 select FOOTBRIDGE_HOST select ISA select ISA_DMA @@ -61,8 +61,8 @@ config ARCH_EBSA285_HOST config ARCH_NETWINDER bool "NetWinder" - select CLKSRC_I8253 select CLKEVT_I8253 + select CLKSRC_I8253 select FOOTBRIDGE_HOST select ISA select ISA_DMA diff --git a/arch/arm/mach-footbridge/Makefile.boot b/arch/arm/mach-footbridge/Makefile.boot index c7e75acfe6c9..ff0a4b5b0a82 100644 --- a/arch/arm/mach-footbridge/Makefile.boot +++ b/arch/arm/mach-footbridge/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-footbridge/cats-hw.c b/arch/arm/mach-footbridge/cats-hw.c index a3da5d1106c2..d5f178540928 100644 --- a/arch/arm/mach-footbridge/cats-hw.c +++ b/arch/arm/mach-footbridge/cats-hw.c @@ -76,8 +76,7 @@ __initcall(cats_hw_init); * hard reboots fail on early boards. */ static void __init -fixup_cats(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fixup_cats(struct tag *tags, char **cmdline, struct meminfo *mi) { screen_info.orig_video_lines = 25; screen_info.orig_video_points = 16; diff --git a/arch/arm/mach-footbridge/include/mach/hardware.h b/arch/arm/mach-footbridge/include/mach/hardware.h index 15d54981674c..e3d6ccac2162 100644 --- a/arch/arm/mach-footbridge/include/mach/hardware.h +++ b/arch/arm/mach-footbridge/include/mach/hardware.h @@ -93,7 +93,7 @@ #define CPLD_FLASH_WR_ENABLE 1 #ifndef __ASSEMBLY__ -extern spinlock_t nw_gpio_lock; +extern raw_spinlock_t nw_gpio_lock; extern void nw_gpio_modify_op(unsigned int mask, unsigned int set); extern void nw_gpio_modify_io(unsigned int mask, unsigned int in); extern unsigned int nw_gpio_read(void); diff --git a/arch/arm/mach-footbridge/include/mach/io.h b/arch/arm/mach-footbridge/include/mach/io.h index 32e4cc397c28..15a70396c27d 100644 --- a/arch/arm/mach-footbridge/include/mach/io.h +++ b/arch/arm/mach-footbridge/include/mach/io.h @@ -23,8 +23,6 @@ #define PCIO_SIZE 0x00100000 #define PCIO_BASE MMU_IO(0xff000000, 0x7c000000) -#define IO_SPACE_LIMIT 0xffff - /* * Translation of various region addresses to virtual addresses */ diff --git a/arch/arm/mach-footbridge/netwinder-hw.c b/arch/arm/mach-footbridge/netwinder-hw.c index d8c1c922e24c..0d3846f3b60d 100644 --- a/arch/arm/mach-footbridge/netwinder-hw.c +++ b/arch/arm/mach-footbridge/netwinder-hw.c @@ -68,7 +68,7 @@ static inline void wb977_ww(int reg, int val) /* * This is a lock for accessing ports GP1_IO_BASE and GP2_IO_BASE */ -DEFINE_SPINLOCK(nw_gpio_lock); +DEFINE_RAW_SPINLOCK(nw_gpio_lock); EXPORT_SYMBOL(nw_gpio_lock); static unsigned int current_gpio_op; @@ -327,9 +327,9 @@ static inline void wb977_init_gpio(void) /* * Set Group1/Group2 outputs */ - spin_lock_irqsave(&nw_gpio_lock, flags); + raw_spin_lock_irqsave(&nw_gpio_lock, flags); nw_gpio_modify_op(-1, GPIO_RED_LED | GPIO_FAN); - spin_unlock_irqrestore(&nw_gpio_lock, flags); + raw_spin_unlock_irqrestore(&nw_gpio_lock, flags); } /* @@ -390,9 +390,9 @@ static void __init cpld_init(void) { unsigned long flags; - spin_lock_irqsave(&nw_gpio_lock, flags); + raw_spin_lock_irqsave(&nw_gpio_lock, flags); nw_cpld_modify(-1, CPLD_UNMUTE | CPLD_7111_DISABLE); - spin_unlock_irqrestore(&nw_gpio_lock, flags); + raw_spin_unlock_irqrestore(&nw_gpio_lock, flags); } static unsigned char rwa_unlock[] __initdata = @@ -616,9 +616,9 @@ static int __init nw_hw_init(void) cpld_init(); rwa010_init(); - spin_lock_irqsave(&nw_gpio_lock, flags); + raw_spin_lock_irqsave(&nw_gpio_lock, flags); nw_gpio_modify_op(GPIO_RED_LED|GPIO_GREEN_LED, DEFAULT_LEDS); - spin_unlock_irqrestore(&nw_gpio_lock, flags); + raw_spin_unlock_irqrestore(&nw_gpio_lock, flags); } return 0; } @@ -631,8 +631,7 @@ __initcall(nw_hw_init); * the parameter page. */ static void __init -fixup_netwinder(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fixup_netwinder(struct tag *tags, char **cmdline, struct meminfo *mi) { #ifdef CONFIG_ISAPNP extern int isapnp_disable; diff --git a/arch/arm/mach-footbridge/netwinder-leds.c b/arch/arm/mach-footbridge/netwinder-leds.c index 00269fe0be8a..e57102e871fc 100644 --- a/arch/arm/mach-footbridge/netwinder-leds.c +++ b/arch/arm/mach-footbridge/netwinder-leds.c @@ -31,13 +31,13 @@ static char led_state; static char hw_led_state; -static DEFINE_SPINLOCK(leds_lock); +static DEFINE_RAW_SPINLOCK(leds_lock); static void netwinder_leds_event(led_event_t evt) { unsigned long flags; - spin_lock_irqsave(&leds_lock, flags); + raw_spin_lock_irqsave(&leds_lock, flags); switch (evt) { case led_start: @@ -117,12 +117,12 @@ static void netwinder_leds_event(led_event_t evt) break; } - spin_unlock_irqrestore(&leds_lock, flags); + raw_spin_unlock_irqrestore(&leds_lock, flags); if (led_state & LED_STATE_ENABLED) { - spin_lock_irqsave(&nw_gpio_lock, flags); + raw_spin_lock_irqsave(&nw_gpio_lock, flags); nw_gpio_modify_op(GPIO_RED_LED | GPIO_GREEN_LED, hw_led_state); - spin_unlock_irqrestore(&nw_gpio_lock, flags); + raw_spin_unlock_irqrestore(&nw_gpio_lock, flags); } } diff --git a/arch/arm/mach-gemini/Makefile.boot b/arch/arm/mach-gemini/Makefile.boot index 22a52c228d93..683f52b20e3d 100644 --- a/arch/arm/mach-gemini/Makefile.boot +++ b/arch/arm/mach-gemini/Makefile.boot @@ -1,9 +1,9 @@ ifeq ($(CONFIG_GEMINI_MEM_SWAP),y) - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 else - zreladdr-y := 0x10008000 + zreladdr-y += 0x10008000 params_phys-y := 0x10000100 initrd_phys-y := 0x10800000 endif diff --git a/arch/arm/mach-h720x/Makefile.boot b/arch/arm/mach-h720x/Makefile.boot index 52984017bd91..d875a7094dfe 100644 --- a/arch/arm/mach-h720x/Makefile.boot +++ b/arch/arm/mach-h720x/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-$(CONFIG_ARCH_H720X) := 0x40008000 + zreladdr-$(CONFIG_ARCH_H720X) += 0x40008000 diff --git a/arch/arm/mach-imx/Makefile.boot b/arch/arm/mach-imx/Makefile.boot index ebee18b3884c..dbe61201bcd8 100644 --- a/arch/arm/mach-imx/Makefile.boot +++ b/arch/arm/mach-imx/Makefile.boot @@ -1,19 +1,19 @@ -zreladdr-$(CONFIG_ARCH_MX1) := 0x08008000 +zreladdr-$(CONFIG_ARCH_MX1) += 0x08008000 params_phys-$(CONFIG_ARCH_MX1) := 0x08000100 initrd_phys-$(CONFIG_ARCH_MX1) := 0x08800000 -zreladdr-$(CONFIG_MACH_MX21) := 0xC0008000 +zreladdr-$(CONFIG_MACH_MX21) += 0xC0008000 params_phys-$(CONFIG_MACH_MX21) := 0xC0000100 initrd_phys-$(CONFIG_MACH_MX21) := 0xC0800000 -zreladdr-$(CONFIG_ARCH_MX25) := 0x80008000 +zreladdr-$(CONFIG_ARCH_MX25) += 0x80008000 params_phys-$(CONFIG_ARCH_MX25) := 0x80000100 initrd_phys-$(CONFIG_ARCH_MX25) := 0x80800000 -zreladdr-$(CONFIG_MACH_MX27) := 0xA0008000 +zreladdr-$(CONFIG_MACH_MX27) += 0xA0008000 params_phys-$(CONFIG_MACH_MX27) := 0xA0000100 initrd_phys-$(CONFIG_MACH_MX27) := 0xA0800000 -zreladdr-$(CONFIG_ARCH_MX3) := 0x80008000 +zreladdr-$(CONFIG_ARCH_MX3) += 0x80008000 params_phys-$(CONFIG_ARCH_MX3) := 0x80000100 initrd_phys-$(CONFIG_ARCH_MX3) := 0x80800000 diff --git a/arch/arm/mach-imx/mach-mx27_3ds.c b/arch/arm/mach-imx/mach-mx27_3ds.c index 2eafbac2c763..377230497dcc 100644 --- a/arch/arm/mach-imx/mach-mx27_3ds.c +++ b/arch/arm/mach-imx/mach-mx27_3ds.c @@ -241,7 +241,7 @@ static struct regulator_init_data gpo_init = { }; static struct regulator_consumer_supply vmmc1_consumers[] = { - REGULATOR_SUPPLY("lcd_2v8", NULL), + REGULATOR_SUPPLY("vcore", "spi0.0"), }; static struct regulator_init_data vmmc1_init = { @@ -257,7 +257,7 @@ static struct regulator_init_data vmmc1_init = { }; static struct regulator_consumer_supply vgen_consumers[] = { - REGULATOR_SUPPLY("vdd_lcdio", NULL), + REGULATOR_SUPPLY("vdd", "spi0.0"), }; static struct regulator_init_data vgen_init = { @@ -348,8 +348,6 @@ static const struct imx_fb_platform_data mx27_3ds_fb_data __initconst = { static struct l4f00242t03_pdata mx27_3ds_lcd_pdata = { .reset_gpio = LCD_RESET, .data_enable_gpio = LCD_ENABLE, - .core_supply = "lcd_2v8", - .io_supply = "vdd_lcdio", }; static struct spi_board_info mx27_3ds_spi_devs[] __initdata = { diff --git a/arch/arm/mach-imx/mach-mx31_3ds.c b/arch/arm/mach-imx/mach-mx31_3ds.c index 712a7fb1cf01..0de4d1835ea4 100644 --- a/arch/arm/mach-imx/mach-mx31_3ds.c +++ b/arch/arm/mach-imx/mach-mx31_3ds.c @@ -285,8 +285,6 @@ static struct mx3fb_platform_data mx3fb_pdata __initdata = { static struct l4f00242t03_pdata mx31_3ds_l4f00242t03_pdata = { .reset_gpio = IOMUX_TO_GPIO(MX31_PIN_LCS1), .data_enable_gpio = IOMUX_TO_GPIO(MX31_PIN_SER_RS), - .core_supply = "lcd_2v8", - .io_supply = "vdd_lcdio", }; /* @@ -411,7 +409,7 @@ static struct regulator_init_data vmmc2_init = { }; static struct regulator_consumer_supply vmmc1_consumers[] = { - REGULATOR_SUPPLY("lcd_2v8", NULL), + REGULATOR_SUPPLY("vcore", "spi0.0"), REGULATOR_SUPPLY("cmos_2v8", "soc-camera-pdrv.0"), }; @@ -428,7 +426,7 @@ static struct regulator_init_data vmmc1_init = { }; static struct regulator_consumer_supply vgen_consumers[] = { - REGULATOR_SUPPLY("vdd_lcdio", NULL), + REGULATOR_SUPPLY("vdd", "spi0.0"), }; static struct regulator_init_data vgen_init = { diff --git a/arch/arm/mach-integrator/Makefile.boot b/arch/arm/mach-integrator/Makefile.boot index c7e75acfe6c9..ff0a4b5b0a82 100644 --- a/arch/arm/mach-integrator/Makefile.boot +++ b/arch/arm/mach-integrator/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-integrator/core.c b/arch/arm/mach-integrator/core.c index 77315b995681..4b38e13667ac 100644 --- a/arch/arm/mach-integrator/core.c +++ b/arch/arm/mach-integrator/core.c @@ -126,6 +126,10 @@ static struct clk_lookup lookups[] = { { /* Bus clock */ .con_id = "apb_pclk", .clk = &dummy_apb_pclk, + }, { + /* Integrator/AP timer frequency */ + .dev_id = "ap_timer", + .clk = &clk24mhz, }, { /* UART0 */ .dev_id = "mb:16", .clk = &uartclk, @@ -205,7 +209,7 @@ static struct amba_pl010_data integrator_uart_data = { #define CM_CTRL IO_ADDRESS(INTEGRATOR_HDR_CTRL) -static DEFINE_SPINLOCK(cm_lock); +static DEFINE_RAW_SPINLOCK(cm_lock); /** * cm_control - update the CM_CTRL register. @@ -217,10 +221,10 @@ void cm_control(u32 mask, u32 set) unsigned long flags; u32 val; - spin_lock_irqsave(&cm_lock, flags); + raw_spin_lock_irqsave(&cm_lock, flags); val = readl(CM_CTRL) & ~mask; writel(val | set, CM_CTRL); - spin_unlock_irqrestore(&cm_lock, flags); + raw_spin_unlock_irqrestore(&cm_lock, flags); } EXPORT_SYMBOL(cm_control); diff --git a/arch/arm/mach-integrator/include/mach/io.h b/arch/arm/mach-integrator/include/mach/io.h index f21bb5493dd9..37beed3fa3ed 100644 --- a/arch/arm/mach-integrator/include/mach/io.h +++ b/arch/arm/mach-integrator/include/mach/io.h @@ -20,8 +20,6 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H -#define IO_SPACE_LIMIT 0xffff - /* * WARNING: this has to mirror definitions in platform.h */ diff --git a/arch/arm/mach-integrator/include/mach/platform.h b/arch/arm/mach-integrator/include/mach/platform.h index 5e6ea5cfea6e..ec467baade09 100644 --- a/arch/arm/mach-integrator/include/mach/platform.h +++ b/arch/arm/mach-integrator/include/mach/platform.h @@ -13,9 +13,6 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -/* DO NOT EDIT!! - this file automatically generated - * from .s file by awk -f s2h.awk - */ /************************************************************************** * * Copyright © ARM Limited 1998. All rights reserved. * ***********************************************************************/ @@ -399,15 +396,6 @@ #define INTEGRATOR_TIMER1_BASE (INTEGRATOR_CT_BASE + 0x100) #define INTEGRATOR_TIMER2_BASE (INTEGRATOR_CT_BASE + 0x200) -#define TICKS_PER_uSEC 24 - -/* - * These are useconds NOT ticks. - * - */ -#define mSEC_1 1000 -#define mSEC_10 (mSEC_1 * 10) - #define INTEGRATOR_CSR_BASE 0x10000000 #define INTEGRATOR_CSR_SIZE 0x10000000 diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c index a20fb3f2bc45..a1769f35a86e 100644 --- a/arch/arm/mach-integrator/integrator_ap.c +++ b/arch/arm/mach-integrator/integrator_ap.c @@ -32,6 +32,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/mtd/physmap.h> +#include <linux/clk.h> #include <video/vga.h> #include <mach/hardware.h> @@ -322,27 +323,16 @@ static void __init ap_init(void) #define TIMER1_VA_BASE IO_ADDRESS(INTEGRATOR_TIMER1_BASE) #define TIMER2_VA_BASE IO_ADDRESS(INTEGRATOR_TIMER2_BASE) -/* - * How long is the timer interval? - */ -#define TIMER_INTERVAL (TICKS_PER_uSEC * mSEC_10) -#if TIMER_INTERVAL >= 0x100000 -#define TICKS2USECS(x) (256 * (x) / TICKS_PER_uSEC) -#elif TIMER_INTERVAL >= 0x10000 -#define TICKS2USECS(x) (16 * (x) / TICKS_PER_uSEC) -#else -#define TICKS2USECS(x) ((x) / TICKS_PER_uSEC) -#endif - static unsigned long timer_reload; -static void integrator_clocksource_init(u32 khz) +static void integrator_clocksource_init(unsigned long inrate) { void __iomem *base = (void __iomem *)TIMER2_VA_BASE; u32 ctrl = TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC; + unsigned long rate = inrate; - if (khz >= 1500) { - khz /= 16; + if (rate >= 1500000) { + rate /= 16; ctrl |= TIMER_CTRL_DIV16; } @@ -350,7 +340,7 @@ static void integrator_clocksource_init(u32 khz) writel(ctrl, base + TIMER_CTRL); clocksource_mmio_init(base + TIMER_VALUE, "timer2", - khz * 1000, 200, 16, clocksource_mmio_readl_down); + rate, 200, 16, clocksource_mmio_readl_down); } static void __iomem * const clkevt_base = (void __iomem *)TIMER1_VA_BASE; @@ -374,15 +364,29 @@ static void clkevt_set_mode(enum clock_event_mode mode, struct clock_event_devic { u32 ctrl = readl(clkevt_base + TIMER_CTRL) & ~TIMER_CTRL_ENABLE; - BUG_ON(mode == CLOCK_EVT_MODE_ONESHOT); + /* Disable timer */ + writel(ctrl, clkevt_base + TIMER_CTRL); - if (mode == CLOCK_EVT_MODE_PERIODIC) { - writel(ctrl, clkevt_base + TIMER_CTRL); + switch (mode) { + case CLOCK_EVT_MODE_PERIODIC: + /* Enable the timer and start the periodic tick */ writel(timer_reload, clkevt_base + TIMER_LOAD); ctrl |= TIMER_CTRL_PERIODIC | TIMER_CTRL_ENABLE; + writel(ctrl, clkevt_base + TIMER_CTRL); + break; + case CLOCK_EVT_MODE_ONESHOT: + /* Leave the timer disabled, .set_next_event will enable it */ + ctrl &= ~TIMER_CTRL_PERIODIC; + writel(ctrl, clkevt_base + TIMER_CTRL); + break; + case CLOCK_EVT_MODE_UNUSED: + case CLOCK_EVT_MODE_SHUTDOWN: + case CLOCK_EVT_MODE_RESUME: + default: + /* Just leave in disabled state */ + break; } - writel(ctrl, clkevt_base + TIMER_CTRL); } static int clkevt_set_next_event(unsigned long next, struct clock_event_device *evt) @@ -398,12 +402,10 @@ static int clkevt_set_next_event(unsigned long next, struct clock_event_device * static struct clock_event_device integrator_clockevent = { .name = "timer1", - .shift = 34, - .features = CLOCK_EVT_FEAT_PERIODIC, + .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, .set_mode = clkevt_set_mode, .set_next_event = clkevt_set_next_event, .rating = 300, - .cpumask = cpu_all_mask, }; static struct irqaction integrator_timer_irq = { @@ -413,29 +415,27 @@ static struct irqaction integrator_timer_irq = { .dev_id = &integrator_clockevent, }; -static void integrator_clockevent_init(u32 khz) +static void integrator_clockevent_init(unsigned long inrate) { - struct clock_event_device *evt = &integrator_clockevent; + unsigned long rate = inrate; unsigned int ctrl = 0; - if (khz * 1000 > 0x100000 * HZ) { - khz /= 256; + /* Calculate and program a divisor */ + if (rate > 0x100000 * HZ) { + rate /= 256; ctrl |= TIMER_CTRL_DIV256; - } else if (khz * 1000 > 0x10000 * HZ) { - khz /= 16; + } else if (rate > 0x10000 * HZ) { + rate /= 16; ctrl |= TIMER_CTRL_DIV16; } - - timer_reload = khz * 1000 / HZ; + timer_reload = rate / HZ; writel(ctrl, clkevt_base + TIMER_CTRL); - evt->irq = IRQ_TIMERINT1; - evt->mult = div_sc(khz, NSEC_PER_MSEC, evt->shift); - evt->max_delta_ns = clockevent_delta2ns(0xffff, evt); - evt->min_delta_ns = clockevent_delta2ns(0xf, evt); - setup_irq(IRQ_TIMERINT1, &integrator_timer_irq); - clockevents_register_device(evt); + clockevents_config_and_register(&integrator_clockevent, + rate, + 1, + 0xffffU); } /* @@ -443,14 +443,20 @@ static void integrator_clockevent_init(u32 khz) */ static void __init ap_init_timer(void) { - u32 khz = TICKS_PER_uSEC * 1000; + struct clk *clk; + unsigned long rate; + + clk = clk_get_sys("ap_timer", NULL); + BUG_ON(IS_ERR(clk)); + clk_enable(clk); + rate = clk_get_rate(clk); writel(0, TIMER0_VA_BASE + TIMER_CTRL); writel(0, TIMER1_VA_BASE + TIMER_CTRL); writel(0, TIMER2_VA_BASE + TIMER_CTRL); - integrator_clocksource_init(khz); - integrator_clockevent_init(khz); + integrator_clocksource_init(rate); + integrator_clockevent_init(rate); } static struct sys_timer ap_timer = { diff --git a/arch/arm/mach-integrator/pci_v3.c b/arch/arm/mach-integrator/pci_v3.c index 11b86e5b71c2..b4d8f8b8a085 100644 --- a/arch/arm/mach-integrator/pci_v3.c +++ b/arch/arm/mach-integrator/pci_v3.c @@ -163,7 +163,7 @@ * 7:2 register number * */ -static DEFINE_SPINLOCK(v3_lock); +static DEFINE_RAW_SPINLOCK(v3_lock); #define PCI_BUS_NONMEM_START 0x00000000 #define PCI_BUS_NONMEM_SIZE SZ_256M @@ -284,7 +284,7 @@ static int v3_read_config(struct pci_bus *bus, unsigned int devfn, int where, unsigned long flags; u32 v; - spin_lock_irqsave(&v3_lock, flags); + raw_spin_lock_irqsave(&v3_lock, flags); addr = v3_open_config_window(bus, devfn, where); switch (size) { @@ -302,7 +302,7 @@ static int v3_read_config(struct pci_bus *bus, unsigned int devfn, int where, } v3_close_config_window(); - spin_unlock_irqrestore(&v3_lock, flags); + raw_spin_unlock_irqrestore(&v3_lock, flags); *val = v; return PCIBIOS_SUCCESSFUL; @@ -314,7 +314,7 @@ static int v3_write_config(struct pci_bus *bus, unsigned int devfn, int where, unsigned long addr; unsigned long flags; - spin_lock_irqsave(&v3_lock, flags); + raw_spin_lock_irqsave(&v3_lock, flags); addr = v3_open_config_window(bus, devfn, where); switch (size) { @@ -335,7 +335,7 @@ static int v3_write_config(struct pci_bus *bus, unsigned int devfn, int where, } v3_close_config_window(); - spin_unlock_irqrestore(&v3_lock, flags); + raw_spin_unlock_irqrestore(&v3_lock, flags); return PCIBIOS_SUCCESSFUL; } @@ -513,7 +513,7 @@ void __init pci_v3_preinit(void) hook_fault_code(8, v3_pci_fault, SIGBUS, 0, "external abort on non-linefetch"); hook_fault_code(10, v3_pci_fault, SIGBUS, 0, "external abort on non-linefetch"); - spin_lock_irqsave(&v3_lock, flags); + raw_spin_lock_irqsave(&v3_lock, flags); /* * Unlock V3 registers, but only if they were previously locked. @@ -586,7 +586,7 @@ void __init pci_v3_preinit(void) printk(KERN_ERR "PCI: unable to grab PCI error " "interrupt: %d\n", ret); - spin_unlock_irqrestore(&v3_lock, flags); + raw_spin_unlock_irqrestore(&v3_lock, flags); } void __init pci_v3_postinit(void) diff --git a/arch/arm/mach-iop13xx/Makefile.boot b/arch/arm/mach-iop13xx/Makefile.boot index 0b0e19fdfe6c..3a8c38c3189c 100644 --- a/arch/arm/mach-iop13xx/Makefile.boot +++ b/arch/arm/mach-iop13xx/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-iop32x/Makefile.boot b/arch/arm/mach-iop32x/Makefile.boot index 47000dccd61f..0a833b11e38c 100644 --- a/arch/arm/mach-iop32x/Makefile.boot +++ b/arch/arm/mach-iop32x/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0xa0008000 + zreladdr-y += 0xa0008000 params_phys-y := 0xa0000100 initrd_phys-y := 0xa0800000 diff --git a/arch/arm/mach-iop33x/Makefile.boot b/arch/arm/mach-iop33x/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-iop33x/Makefile.boot +++ b/arch/arm/mach-iop33x/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-ixp2000/Makefile.boot b/arch/arm/mach-ixp2000/Makefile.boot index d84c5807a43d..9c7af91d93da 100644 --- a/arch/arm/mach-ixp2000/Makefile.boot +++ b/arch/arm/mach-ixp2000/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 diff --git a/arch/arm/mach-ixp23xx/Makefile.boot b/arch/arm/mach-ixp23xx/Makefile.boot index d5561ad15bad..44fb4a717c3f 100644 --- a/arch/arm/mach-ixp23xx/Makefile.boot +++ b/arch/arm/mach-ixp23xx/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 diff --git a/arch/arm/mach-ixp4xx/Makefile.boot b/arch/arm/mach-ixp4xx/Makefile.boot index d84c5807a43d..9c7af91d93da 100644 --- a/arch/arm/mach-ixp4xx/Makefile.boot +++ b/arch/arm/mach-ixp4xx/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c index 2131832ee6ba..f72a3a893c47 100644 --- a/arch/arm/mach-ixp4xx/common-pci.c +++ b/arch/arm/mach-ixp4xx/common-pci.c @@ -54,7 +54,7 @@ unsigned long ixp4xx_pci_reg_base = 0; * these transactions are atomic or we will end up * with corrupt data on the bus or in a driver. */ -static DEFINE_SPINLOCK(ixp4xx_pci_lock); +static DEFINE_RAW_SPINLOCK(ixp4xx_pci_lock); /* * Read from PCI config space @@ -62,10 +62,10 @@ static DEFINE_SPINLOCK(ixp4xx_pci_lock); static void crp_read(u32 ad_cbe, u32 *data) { unsigned long flags; - spin_lock_irqsave(&ixp4xx_pci_lock, flags); + raw_spin_lock_irqsave(&ixp4xx_pci_lock, flags); *PCI_CRP_AD_CBE = ad_cbe; *data = *PCI_CRP_RDATA; - spin_unlock_irqrestore(&ixp4xx_pci_lock, flags); + raw_spin_unlock_irqrestore(&ixp4xx_pci_lock, flags); } /* @@ -74,10 +74,10 @@ static void crp_read(u32 ad_cbe, u32 *data) static void crp_write(u32 ad_cbe, u32 data) { unsigned long flags; - spin_lock_irqsave(&ixp4xx_pci_lock, flags); + raw_spin_lock_irqsave(&ixp4xx_pci_lock, flags); *PCI_CRP_AD_CBE = CRP_AD_CBE_WRITE | ad_cbe; *PCI_CRP_WDATA = data; - spin_unlock_irqrestore(&ixp4xx_pci_lock, flags); + raw_spin_unlock_irqrestore(&ixp4xx_pci_lock, flags); } static inline int check_master_abort(void) @@ -101,7 +101,7 @@ int ixp4xx_pci_read_errata(u32 addr, u32 cmd, u32* data) int retval = 0; int i; - spin_lock_irqsave(&ixp4xx_pci_lock, flags); + raw_spin_lock_irqsave(&ixp4xx_pci_lock, flags); *PCI_NP_AD = addr; @@ -118,7 +118,7 @@ int ixp4xx_pci_read_errata(u32 addr, u32 cmd, u32* data) if(check_master_abort()) retval = 1; - spin_unlock_irqrestore(&ixp4xx_pci_lock, flags); + raw_spin_unlock_irqrestore(&ixp4xx_pci_lock, flags); return retval; } @@ -127,7 +127,7 @@ int ixp4xx_pci_read_no_errata(u32 addr, u32 cmd, u32* data) unsigned long flags; int retval = 0; - spin_lock_irqsave(&ixp4xx_pci_lock, flags); + raw_spin_lock_irqsave(&ixp4xx_pci_lock, flags); *PCI_NP_AD = addr; @@ -140,7 +140,7 @@ int ixp4xx_pci_read_no_errata(u32 addr, u32 cmd, u32* data) if(check_master_abort()) retval = 1; - spin_unlock_irqrestore(&ixp4xx_pci_lock, flags); + raw_spin_unlock_irqrestore(&ixp4xx_pci_lock, flags); return retval; } @@ -149,7 +149,7 @@ int ixp4xx_pci_write(u32 addr, u32 cmd, u32 data) unsigned long flags; int retval = 0; - spin_lock_irqsave(&ixp4xx_pci_lock, flags); + raw_spin_lock_irqsave(&ixp4xx_pci_lock, flags); *PCI_NP_AD = addr; @@ -162,7 +162,7 @@ int ixp4xx_pci_write(u32 addr, u32 cmd, u32 data) if(check_master_abort()) retval = 1; - spin_unlock_irqrestore(&ixp4xx_pci_lock, flags); + raw_spin_unlock_irqrestore(&ixp4xx_pci_lock, flags); return retval; } @@ -397,7 +397,8 @@ void __init ixp4xx_pci_preinit(void) local_write_config(PCI_BASE_ADDRESS_0, 4, PHYS_OFFSET); local_write_config(PCI_BASE_ADDRESS_1, 4, PHYS_OFFSET + SZ_16M); local_write_config(PCI_BASE_ADDRESS_2, 4, PHYS_OFFSET + SZ_32M); - local_write_config(PCI_BASE_ADDRESS_3, 4, PHYS_OFFSET + SZ_48M); + local_write_config(PCI_BASE_ADDRESS_3, 4, + PHYS_OFFSET + SZ_32M + SZ_16M); /* * Enable CSR window at 64 MiB to allow PCI masters diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h index 57b5410c31f4..ffb9d6afb89f 100644 --- a/arch/arm/mach-ixp4xx/include/mach/io.h +++ b/arch/arm/mach-ixp4xx/include/mach/io.h @@ -17,8 +17,6 @@ #include <mach/hardware.h> -#define IO_SPACE_LIMIT 0x0000ffff - extern int (*ixp4xx_pci_read)(u32 addr, u32 cmd, u32* data); extern int ixp4xx_pci_write(u32 addr, u32 cmd, u32 data); diff --git a/arch/arm/mach-kirkwood/Makefile.boot b/arch/arm/mach-kirkwood/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-kirkwood/Makefile.boot +++ b/arch/arm/mach-kirkwood/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-ks8695/Makefile.boot b/arch/arm/mach-ks8695/Makefile.boot index 48eb2cb3ac77..c9b0bebcf237 100644 --- a/arch/arm/mach-ks8695/Makefile.boot +++ b/arch/arm/mach-ks8695/Makefile.boot @@ -3,6 +3,6 @@ # PARAMS_PHYS must be within 4MB of ZRELADDR # INITRD_PHYS must be in RAM - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-lpc32xx/Makefile.boot b/arch/arm/mach-lpc32xx/Makefile.boot index b796b41ebf8f..2cfe0ee635c5 100644 --- a/arch/arm/mach-lpc32xx/Makefile.boot +++ b/arch/arm/mach-lpc32xx/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x80008000 + zreladdr-y += 0x80008000 params_phys-y := 0x80000100 initrd_phys-y := 0x82000000 diff --git a/arch/arm/mach-lpc32xx/include/mach/gpio.h b/arch/arm/mach-lpc32xx/include/mach/gpio.h index e69de29bb2d1..40a8c178f10d 100644 --- a/arch/arm/mach-lpc32xx/include/mach/gpio.h +++ b/arch/arm/mach-lpc32xx/include/mach/gpio.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/arm/mach-mmp/Makefile.boot b/arch/arm/mach-mmp/Makefile.boot index 574a4aa8321a..5edf03e2beed 100644 --- a/arch/arm/mach-mmp/Makefile.boot +++ b/arch/arm/mach-mmp/Makefile.boot @@ -1 +1 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 diff --git a/arch/arm/mach-mmp/aspenite.c b/arch/arm/mach-mmp/aspenite.c index 833c3a2784aa..06b5ad774604 100644 --- a/arch/arm/mach-mmp/aspenite.c +++ b/arch/arm/mach-mmp/aspenite.c @@ -160,7 +160,7 @@ static struct mtd_partition aspenite_nand_partitions[] = { }, { .name = "filesystem", .offset = MTDPART_OFS_APPEND, - .size = SZ_48M, + .size = SZ_32M + SZ_16M, .mask_flags = 0, } }; diff --git a/arch/arm/mach-mmp/include/mach/pxa168.h b/arch/arm/mach-mmp/include/mach/pxa168.h index 7f005843a707..7fb568d2845b 100644 --- a/arch/arm/mach-mmp/include/mach/pxa168.h +++ b/arch/arm/mach-mmp/include/mach/pxa168.h @@ -35,6 +35,13 @@ extern struct pxa_device_desc pxa168_device_fb; extern struct pxa_device_desc pxa168_device_keypad; extern struct pxa_device_desc pxa168_device_eth; +struct pxa168_usb_pdata { + /* If NULL, default phy init routine for PXA168 would be called */ + int (*phy_init)(void __iomem *usb_phy_reg_base); +}; +/* pdata can be NULL */ +int __init pxa168_add_usb_host(struct pxa168_usb_pdata *pdata); + static inline int pxa168_add_uart(int id) { struct pxa_device_desc *d = NULL; diff --git a/arch/arm/mach-mmp/pxa168.c b/arch/arm/mach-mmp/pxa168.c index 50c1763911ff..76ca15c00e45 100644 --- a/arch/arm/mach-mmp/pxa168.c +++ b/arch/arm/mach-mmp/pxa168.c @@ -24,6 +24,9 @@ #include <mach/dma.h> #include <mach/devices.h> #include <mach/mfp.h> +#include <linux/platform_device.h> +#include <linux/dma-mapping.h> +#include <mach/pxa168.h> #include "common.h" #include "clock.h" @@ -82,6 +85,7 @@ static APBC_CLK(keypad, PXA168_KPC, 0, 32000); static APMU_CLK(nand, NAND, 0x19b, 156000000); static APMU_CLK(lcd, LCD, 0x7f, 312000000); static APMU_CLK(eth, ETH, 0x09, 0); +static APMU_CLK(usb, USB, 0x12, 0); /* device and clock bindings */ static struct clk_lookup pxa168_clkregs[] = { @@ -103,6 +107,7 @@ static struct clk_lookup pxa168_clkregs[] = { INIT_CLKREG(&clk_lcd, "pxa168-fb", NULL), INIT_CLKREG(&clk_keypad, "pxa27x-keypad", NULL), INIT_CLKREG(&clk_eth, "pxa168-eth", "MFUCLK"), + INIT_CLKREG(&clk_usb, "pxa168-ehci", "PXA168-USBCLK"), }; static int __init pxa168_init(void) @@ -168,3 +173,44 @@ PXA168_DEVICE(ssp5, "pxa168-ssp", 4, SSP5, 0xd4021000, 0x40, 60, 61); PXA168_DEVICE(fb, "pxa168-fb", -1, LCD, 0xd420b000, 0x1c8); PXA168_DEVICE(keypad, "pxa27x-keypad", -1, KEYPAD, 0xd4012000, 0x4c); PXA168_DEVICE(eth, "pxa168-eth", -1, MFU, 0xc0800000, 0x0fff); + +struct resource pxa168_usb_host_resources[] = { + /* USB Host conroller register base */ + [0] = { + .start = 0xd4209000, + .end = 0xd4209000 + 0x200, + .flags = IORESOURCE_MEM, + .name = "pxa168-usb-host", + }, + /* USB PHY register base */ + [1] = { + .start = 0xd4206000, + .end = 0xd4206000 + 0xff, + .flags = IORESOURCE_MEM, + .name = "pxa168-usb-phy", + }, + [2] = { + .start = IRQ_PXA168_USB2, + .end = IRQ_PXA168_USB2, + .flags = IORESOURCE_IRQ, + }, +}; + +static u64 pxa168_usb_host_dmamask = DMA_BIT_MASK(32); +struct platform_device pxa168_device_usb_host = { + .name = "pxa168-ehci", + .id = -1, + .dev = { + .dma_mask = &pxa168_usb_host_dmamask, + .coherent_dma_mask = DMA_BIT_MASK(32), + }, + + .num_resources = ARRAY_SIZE(pxa168_usb_host_resources), + .resource = pxa168_usb_host_resources, +}; + +int __init pxa168_add_usb_host(struct pxa168_usb_pdata *pdata) +{ + pxa168_device_usb_host.dev.platform_data = pdata; + return platform_device_register(&pxa168_device_usb_host); +} diff --git a/arch/arm/mach-mmp/ttc_dkb.c b/arch/arm/mach-mmp/ttc_dkb.c index 6bd37a27e5fc..176515a76989 100644 --- a/arch/arm/mach-mmp/ttc_dkb.c +++ b/arch/arm/mach-mmp/ttc_dkb.c @@ -93,7 +93,7 @@ static struct mtd_partition ttc_dkb_onenand_partitions[] = { }, { .name = "filesystem", .offset = MTDPART_OFS_APPEND, - .size = SZ_48M, + .size = SZ_32M + SZ_16M, .mask_flags = 0, } }; diff --git a/arch/arm/mach-msm/Makefile.boot b/arch/arm/mach-msm/Makefile.boot index 24dfbf8c07c4..9b803a578b4d 100644 --- a/arch/arm/mach-msm/Makefile.boot +++ b/arch/arm/mach-msm/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x10008000 + zreladdr-y += 0x10008000 params_phys-y := 0x10000100 initrd_phys-y := 0x10800000 diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c index 16c86f8b4f3f..a60ab6d04ec5 100644 --- a/arch/arm/mach-msm/board-halibut.c +++ b/arch/arm/mach-msm/board-halibut.c @@ -78,8 +78,8 @@ static void __init halibut_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init halibut_fixup(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +static void __init halibut_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks=1; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-msm/board-mahimahi.c b/arch/arm/mach-msm/board-mahimahi.c index 8a1672ee4e4a..5a4882fc6f7a 100644 --- a/arch/arm/mach-msm/board-mahimahi.c +++ b/arch/arm/mach-msm/board-mahimahi.c @@ -53,8 +53,8 @@ static void __init mahimahi_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init mahimahi_fixup(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +static void __init mahimahi_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks = 2; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-msm/board-msm8x60.c b/arch/arm/mach-msm/board-msm8x60.c index 9221f54778be..106170fb1844 100644 --- a/arch/arm/mach-msm/board-msm8x60.c +++ b/arch/arm/mach-msm/board-msm8x60.c @@ -53,8 +53,6 @@ static void __init msm8x60_map_io(void) static void __init msm8x60_init_irq(void) { - unsigned int i; - gic_init(0, GIC_PPI_START, MSM_QGIC_DIST_BASE, (void *)MSM_QGIC_CPU_BASE); @@ -66,15 +64,6 @@ static void __init msm8x60_init_irq(void) */ if (!machine_is_msm8x60_sim()) writel(0x0000FFFF, MSM_QGIC_DIST_BASE + GIC_DIST_ENABLE_SET); - - /* FIXME: Not installing AVS_SVICINT and AVS_SVICINTSWDONE yet - * as they are configured as level, which does not play nice with - * handle_percpu_irq. - */ - for (i = GIC_PPI_START; i < GIC_SPI_START; i++) { - if (i != AVS_SVICINT && i != AVS_SVICINTSWDONE) - irq_set_handler(i, handle_percpu_irq); - } } static void __init msm8x60_init(void) diff --git a/arch/arm/mach-msm/board-sapphire.c b/arch/arm/mach-msm/board-sapphire.c index afa9293d5800..32b465763dbd 100644 --- a/arch/arm/mach-msm/board-sapphire.c +++ b/arch/arm/mach-msm/board-sapphire.c @@ -76,8 +76,8 @@ static struct map_desc sapphire_io_desc[] __initdata = { } }; -static void __init sapphire_fixup(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +static void __init sapphire_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { int smi_sz = parse_tag_smi((const struct tag *)tags); diff --git a/arch/arm/mach-msm/board-trout.c b/arch/arm/mach-msm/board-trout.c index 22d5694f5fea..6b9b227c87c5 100644 --- a/arch/arm/mach-msm/board-trout.c +++ b/arch/arm/mach-msm/board-trout.c @@ -48,8 +48,8 @@ static void __init trout_init_irq(void) msm_init_irq(); } -static void __init trout_fixup(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +static void __init trout_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks = 1; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-msm/clock.c b/arch/arm/mach-msm/clock.c index 22a537669624..d9145dfc2a3b 100644 --- a/arch/arm/mach-msm/clock.c +++ b/arch/arm/mach-msm/clock.c @@ -18,7 +18,7 @@ #include <linux/list.h> #include <linux/err.h> #include <linux/spinlock.h> -#include <linux/pm_qos_params.h> +#include <linux/pm_qos.h> #include <linux/mutex.h> #include <linux/clk.h> #include <linux/string.h> diff --git a/arch/arm/mach-msm/devices-msm7x00.c b/arch/arm/mach-msm/devices-msm7x00.c index c4f5e26feb4d..993780f490ad 100644 --- a/arch/arm/mach-msm/devices-msm7x00.c +++ b/arch/arm/mach-msm/devices-msm7x00.c @@ -176,12 +176,6 @@ static struct resource resources_sdc1[] = { .name = "cmd_irq", }, { - .start = INT_SDC1_1, - .end = INT_SDC1_1, - .flags = IORESOURCE_IRQ, - .name = "pio_irq", - }, - { .flags = IORESOURCE_IRQ | IORESOURCE_DISABLED, .name = "status_irq" }, @@ -204,12 +198,6 @@ static struct resource resources_sdc2[] = { .flags = IORESOURCE_IRQ, .name = "cmd_irq", }, - { - .start = INT_SDC2_1, - .end = INT_SDC2_1, - .flags = IORESOURCE_IRQ, - .name = "pio_irq", - }, { .flags = IORESOURCE_IRQ | IORESOURCE_DISABLED, .name = "status_irq" @@ -233,12 +221,6 @@ static struct resource resources_sdc3[] = { .flags = IORESOURCE_IRQ, .name = "cmd_irq", }, - { - .start = INT_SDC3_1, - .end = INT_SDC3_1, - .flags = IORESOURCE_IRQ, - .name = "pio_irq", - }, { .flags = IORESOURCE_IRQ | IORESOURCE_DISABLED, .name = "status_irq" @@ -262,12 +244,6 @@ static struct resource resources_sdc4[] = { .flags = IORESOURCE_IRQ, .name = "cmd_irq", }, - { - .start = INT_SDC4_1, - .end = INT_SDC4_1, - .flags = IORESOURCE_IRQ, - .name = "pio_irq", - }, { .flags = IORESOURCE_IRQ | IORESOURCE_DISABLED, .name = "status_irq" diff --git a/arch/arm/mach-msm/devices-qsd8x50.c b/arch/arm/mach-msm/devices-qsd8x50.c index 12d8deb78d9c..131633b12a34 100644 --- a/arch/arm/mach-msm/devices-qsd8x50.c +++ b/arch/arm/mach-msm/devices-qsd8x50.c @@ -140,12 +140,6 @@ static struct resource resources_sdc1[] = { .name = "cmd_irq", }, { - .start = INT_SDC1_1, - .end = INT_SDC1_1, - .flags = IORESOURCE_IRQ, - .name = "pio_irq", - }, - { .flags = IORESOURCE_IRQ | IORESOURCE_DISABLED, .name = "status_irq" }, @@ -168,12 +162,6 @@ static struct resource resources_sdc2[] = { .flags = IORESOURCE_IRQ, .name = "cmd_irq", }, - { - .start = INT_SDC2_1, - .end = INT_SDC2_1, - .flags = IORESOURCE_IRQ, - .name = "pio_irq", - }, { .flags = IORESOURCE_IRQ | IORESOURCE_DISABLED, .name = "status_irq" @@ -197,12 +185,6 @@ static struct resource resources_sdc3[] = { .flags = IORESOURCE_IRQ, .name = "cmd_irq", }, - { - .start = INT_SDC3_1, - .end = INT_SDC3_1, - .flags = IORESOURCE_IRQ, - .name = "pio_irq", - }, { .flags = IORESOURCE_IRQ | IORESOURCE_DISABLED, .name = "status_irq" @@ -226,12 +208,6 @@ static struct resource resources_sdc4[] = { .flags = IORESOURCE_IRQ, .name = "cmd_irq", }, - { - .start = INT_SDC4_1, - .end = INT_SDC4_1, - .flags = IORESOURCE_IRQ, - .name = "pio_irq", - }, { .flags = IORESOURCE_IRQ | IORESOURCE_DISABLED, .name = "status_irq" diff --git a/arch/arm/mach-msm/include/mach/entry-macro-qgic.S b/arch/arm/mach-msm/include/mach/entry-macro-qgic.S index 12467157afb9..717076f3ca73 100644 --- a/arch/arm/mach-msm/include/mach/entry-macro-qgic.S +++ b/arch/arm/mach-msm/include/mach/entry-macro-qgic.S @@ -8,81 +8,10 @@ * warranty of any kind, whether express or implied. */ -#include <mach/hardware.h> -#include <asm/hardware/gic.h> +#include <asm/hardware/entry-macro-gic.S> .macro disable_fiq .endm - .macro get_irqnr_preamble, base, tmp - ldr \base, =gic_cpu_base_addr - ldr \base, [\base] - .endm - .macro arch_ret_to_user, tmp1, tmp2 .endm - - /* - * The interrupt numbering scheme is defined in the - * interrupt controller spec. To wit: - * - * Migrated the code from ARM MP port to be more consistent - * with interrupt processing , the following still holds true - * however, all interrupts are treated the same regardless of - * if they are local IPI or PPI - * - * Interrupts 0-15 are IPI - * 16-31 are PPI - * (16-18 are the timers) - * 32-1020 are global - * 1021-1022 are reserved - * 1023 is "spurious" (no interrupt) - * - * A simple read from the controller will tell us the number of the - * highest priority enabled interrupt. We then just need to check - * whether it is in the valid range for an IRQ (0-1020 inclusive). - * - * Base ARM code assumes that the local (private) peripheral interrupts - * are not valid, we treat them differently, in that the privates are - * handled like normal shared interrupts with the exception that only - * one processor can register the interrupt and the handler must be - * the same for all processors. - */ - - .macro get_irqnr_and_base, irqnr, irqstat, base, tmp - - ldr \irqstat, [\base, #GIC_CPU_INTACK] /* bits 12-10 =srcCPU, - 9-0 =int # */ - - bic \irqnr, \irqstat, #0x1c00 @mask src - cmp \irqnr, #15 - ldr \tmp, =1021 - cmpcc \irqnr, \irqnr - cmpne \irqnr, \tmp - cmpcs \irqnr, \irqnr - - .endm - - /* We assume that irqstat (the raw value of the IRQ acknowledge - * register) is preserved from the macro above. - * If there is an IPI, we immediately signal end of interrupt on the - * controller, since this requires the original irqstat value which - * we won't easily be able to recreate later. - */ - .macro test_for_ipi, irqnr, irqstat, base, tmp - bic \irqnr, \irqstat, #0x1c00 - cmp \irqnr, #16 - strcc \irqstat, [\base, #GIC_CPU_EOI] - cmpcs \irqnr, \irqnr - .endm - - /* As above, this assumes that irqstat and base are preserved.. */ - - .macro test_for_ltirq, irqnr, irqstat, base, tmp - bic \irqnr, \irqstat, #0x1c00 - mov \tmp, #0 - cmp \irqnr, #16 - moveq \tmp, #1 - streq \irqstat, [\base, #GIC_CPU_EOI] - cmp \tmp, #0 - .endm diff --git a/arch/arm/mach-msm/include/mach/mmc.h b/arch/arm/mach-msm/include/mach/mmc.h index 5631b51cec46..ffcd9e3a6a7e 100644 --- a/arch/arm/mach-msm/include/mach/mmc.h +++ b/arch/arm/mach-msm/include/mach/mmc.h @@ -8,13 +8,6 @@ #include <linux/mmc/card.h> #include <linux/mmc/sdio_func.h> -struct embedded_sdio_data { - struct sdio_cis cis; - struct sdio_cccr cccr; - struct sdio_embedded_func *funcs; - int num_funcs; -}; - struct msm_mmc_gpio { unsigned no; const char *name; @@ -29,9 +22,9 @@ struct msm_mmc_platform_data { unsigned int ocr_mask; /* available voltages */ u32 (*translate_vdd)(struct device *, unsigned int); unsigned int (*status)(struct device *); - struct embedded_sdio_data *embedded_sdio; int (*register_status_notify)(void (*callback)(int card_present, void *dev_id), void *dev_id); struct msm_mmc_gpio_data *gpio_data; + void (*init_card)(struct mmc_card *card); }; #endif diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c index 1a1af9e56250..727659520912 100644 --- a/arch/arm/mach-msm/platsmp.c +++ b/arch/arm/mach-msm/platsmp.c @@ -156,6 +156,12 @@ void __init smp_init_cpus(void) { unsigned int i, ncores = get_core_count(); + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; + } + for (i = 0; i < ncores; i++) set_cpu_possible(i, true); diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c index 63621f152c98..afeeca52fc66 100644 --- a/arch/arm/mach-msm/timer.c +++ b/arch/arm/mach-msm/timer.c @@ -71,12 +71,16 @@ enum timer_location { struct msm_clock { struct clock_event_device clockevent; struct clocksource clocksource; - struct irqaction irq; + unsigned int irq; void __iomem *regbase; uint32_t freq; uint32_t shift; void __iomem *global_counter; void __iomem *local_counter; + union { + struct clock_event_device *evt; + struct clock_event_device __percpu **percpu_evt; + }; }; enum { @@ -87,13 +91,10 @@ enum { static struct msm_clock msm_clocks[]; -static struct clock_event_device *local_clock_event; static irqreturn_t msm_timer_interrupt(int irq, void *dev_id) { - struct clock_event_device *evt = dev_id; - if (smp_processor_id() != 0) - evt = local_clock_event; + struct clock_event_device *evt = *(struct clock_event_device **)dev_id; if (evt->event_handler == NULL) return IRQ_HANDLED; evt->event_handler(evt); @@ -171,13 +172,7 @@ static struct msm_clock msm_clocks[] = { .mask = CLOCKSOURCE_MASK(32), .flags = CLOCK_SOURCE_IS_CONTINUOUS, }, - .irq = { - .name = "gp_timer", - .flags = IRQF_DISABLED | IRQF_TIMER | IRQF_TRIGGER_RISING, - .handler = msm_timer_interrupt, - .dev_id = &msm_clocks[0].clockevent, - .irq = INT_GP_TIMER_EXP - }, + .irq = INT_GP_TIMER_EXP, .freq = GPT_HZ, }, [MSM_CLOCK_DGT] = { @@ -196,13 +191,7 @@ static struct msm_clock msm_clocks[] = { .mask = CLOCKSOURCE_MASK((32 - MSM_DGT_SHIFT)), .flags = CLOCK_SOURCE_IS_CONTINUOUS, }, - .irq = { - .name = "dg_timer", - .flags = IRQF_DISABLED | IRQF_TIMER | IRQF_TRIGGER_RISING, - .handler = msm_timer_interrupt, - .dev_id = &msm_clocks[1].clockevent, - .irq = INT_DEBUG_TIMER_EXP - }, + .irq = INT_DEBUG_TIMER_EXP, .freq = DGT_HZ >> MSM_DGT_SHIFT, .shift = MSM_DGT_SHIFT, } @@ -261,10 +250,30 @@ static void __init msm_timer_init(void) printk(KERN_ERR "msm_timer_init: clocksource_register " "failed for %s\n", cs->name); - res = setup_irq(clock->irq.irq, &clock->irq); + ce->irq = clock->irq; + if (cpu_is_msm8x60() || cpu_is_msm8960()) { + clock->percpu_evt = alloc_percpu(struct clock_event_device *); + if (!clock->percpu_evt) { + pr_err("msm_timer_init: memory allocation " + "failed for %s\n", ce->name); + continue; + } + + *__this_cpu_ptr(clock->percpu_evt) = ce; + res = request_percpu_irq(ce->irq, msm_timer_interrupt, + ce->name, clock->percpu_evt); + if (!res) + enable_percpu_irq(ce->irq, 0); + } else { + clock->evt = ce; + res = request_irq(ce->irq, msm_timer_interrupt, + IRQF_TIMER | IRQF_NOBALANCING | IRQF_TRIGGER_RISING, + ce->name, &clock->evt); + } + if (res) - printk(KERN_ERR "msm_timer_init: setup_irq " - "failed for %s\n", cs->name); + pr_err("msm_timer_init: request_irq failed for %s\n", + ce->name); clockevents_register_device(ce); } @@ -273,6 +282,7 @@ static void __init msm_timer_init(void) #ifdef CONFIG_SMP int __cpuinit local_timer_setup(struct clock_event_device *evt) { + static bool local_timer_inited; struct msm_clock *clock = &msm_clocks[MSM_GLOBAL_TIMER]; /* Use existing clock_event for cpu 0 */ @@ -281,12 +291,13 @@ int __cpuinit local_timer_setup(struct clock_event_device *evt) writel(DGT_CLK_CTL_DIV_4, MSM_TMR_BASE + DGT_CLK_CTL); - if (!local_clock_event) { + if (!local_timer_inited) { writel(0, clock->regbase + TIMER_ENABLE); writel(0, clock->regbase + TIMER_CLEAR); writel(~0, clock->regbase + TIMER_MATCH_VAL); + local_timer_inited = true; } - evt->irq = clock->irq.irq; + evt->irq = clock->irq; evt->name = "local_timer"; evt->features = CLOCK_EVT_FEAT_ONESHOT; evt->rating = clock->clockevent.rating; @@ -298,17 +309,17 @@ int __cpuinit local_timer_setup(struct clock_event_device *evt) clockevent_delta2ns(0xf0000000 >> clock->shift, evt); evt->min_delta_ns = clockevent_delta2ns(4, evt); - local_clock_event = evt; - - gic_enable_ppi(clock->irq.irq); + *__this_cpu_ptr(clock->percpu_evt) = evt; + enable_percpu_irq(evt->irq, 0); clockevents_register_device(evt); return 0; } -inline int local_timer_ack(void) +void local_timer_stop(struct clock_event_device *evt) { - return 1; + evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt); + disable_percpu_irq(evt->irq); } #endif diff --git a/arch/arm/mach-mv78xx0/Makefile.boot b/arch/arm/mach-mv78xx0/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-mv78xx0/Makefile.boot +++ b/arch/arm/mach-mv78xx0/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-mx5/Makefile.boot b/arch/arm/mach-mx5/Makefile.boot index e928be1b6757..ca207ca305ec 100644 --- a/arch/arm/mach-mx5/Makefile.boot +++ b/arch/arm/mach-mx5/Makefile.boot @@ -1,9 +1,9 @@ - zreladdr-$(CONFIG_ARCH_MX50) := 0x70008000 + zreladdr-$(CONFIG_ARCH_MX50) += 0x70008000 params_phys-$(CONFIG_ARCH_MX50) := 0x70000100 initrd_phys-$(CONFIG_ARCH_MX50) := 0x70800000 - zreladdr-$(CONFIG_ARCH_MX51) := 0x90008000 + zreladdr-$(CONFIG_ARCH_MX51) += 0x90008000 params_phys-$(CONFIG_ARCH_MX51) := 0x90000100 initrd_phys-$(CONFIG_ARCH_MX51) := 0x90800000 - zreladdr-$(CONFIG_ARCH_MX53) := 0x70008000 + zreladdr-$(CONFIG_ARCH_MX53) += 0x70008000 params_phys-$(CONFIG_ARCH_MX53) := 0x70000100 initrd_phys-$(CONFIG_ARCH_MX53) := 0x70800000 diff --git a/arch/arm/mach-mxs/Makefile.boot b/arch/arm/mach-mxs/Makefile.boot index eb541e0291da..07b11fe6453f 100644 --- a/arch/arm/mach-mxs/Makefile.boot +++ b/arch/arm/mach-mxs/Makefile.boot @@ -1 +1 @@ -zreladdr-y := 0x40008000 +zreladdr-y += 0x40008000 diff --git a/arch/arm/mach-netx/Makefile.boot b/arch/arm/mach-netx/Makefile.boot index b81cf6aff0ac..534a4d27055e 100644 --- a/arch/arm/mach-netx/Makefile.boot +++ b/arch/arm/mach-netx/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x80008000 + zreladdr-y += 0x80008000 diff --git a/arch/arm/mach-nomadik/Makefile.boot b/arch/arm/mach-nomadik/Makefile.boot index c7e75acfe6c9..ff0a4b5b0a82 100644 --- a/arch/arm/mach-nomadik/Makefile.boot +++ b/arch/arm/mach-nomadik/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-nuc93x/Makefile.boot b/arch/arm/mach-nuc93x/Makefile.boot index a057b546b6e5..6c3d421c2d11 100644 --- a/arch/arm/mach-nuc93x/Makefile.boot +++ b/arch/arm/mach-nuc93x/Makefile.boot @@ -1,3 +1,3 @@ -zreladdr-y := 0x00008000 +zreladdr-y += 0x00008000 params_phys-y := 0x00000100 diff --git a/arch/arm/mach-nuc93x/time.c b/arch/arm/mach-nuc93x/time.c index 2f90f9dc6e30..f9807c029ec5 100644 --- a/arch/arm/mach-nuc93x/time.c +++ b/arch/arm/mach-nuc93x/time.c @@ -82,7 +82,7 @@ static void nuc93x_timer_setup(void) timer0_load = (rate / TICKS_PER_SEC); __raw_writel(timer0_load, REG_TICR0); - val |= (PERIOD | COUNTEN | INTEN | PRESCALE);; + val |= (PERIOD | COUNTEN | INTEN | PRESCALE); __raw_writel(val, REG_TCSR0); } diff --git a/arch/arm/mach-omap1/Makefile.boot b/arch/arm/mach-omap1/Makefile.boot index 292d56c5a888..13bda8dbd604 100644 --- a/arch/arm/mach-omap1/Makefile.boot +++ b/arch/arm/mach-omap1/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x10008000 + zreladdr-y += 0x10008000 params_phys-y := 0x10000100 initrd_phys-y := 0x10800000 diff --git a/arch/arm/mach-omap1/pm_bus.c b/arch/arm/mach-omap1/pm_bus.c index 943072d5a1d5..7868e75ad077 100644 --- a/arch/arm/mach-omap1/pm_bus.c +++ b/arch/arm/mach-omap1/pm_bus.c @@ -13,6 +13,7 @@ #include <linux/kernel.h> #include <linux/io.h> #include <linux/pm_runtime.h> +#include <linux/pm_clock.h> #include <linux/platform_device.h> #include <linux/mutex.h> #include <linux/clk.h> diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 57b66d590c52..89bfb49389f2 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -36,6 +36,7 @@ config ARCH_OMAP3 select ARM_L1_CACHE_SHIFT_6 if !ARCH_OMAP4 select ARCH_HAS_OPP select PM_OPP if PM + select ARM_CPU_SUSPEND if PM config ARCH_OMAP4 bool "TI OMAP4" @@ -50,6 +51,7 @@ config ARCH_OMAP4 select ARCH_HAS_OPP select PM_OPP if PM select USB_ARCH_HAS_EHCI + select ARM_CPU_SUSPEND if PM comment "OMAP Core Type" depends on ARCH_OMAP2 diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index f34336560437..7317a2b39dd1 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -242,14 +242,11 @@ obj-$(CONFIG_MACH_IGEP0020) += board-igep0020.o \ obj-$(CONFIG_MACH_OMAP3_TOUCHBOOK) += board-omap3touchbook.o \ hsmmc.o obj-$(CONFIG_MACH_OMAP_4430SDP) += board-4430sdp.o \ - hsmmc.o \ - omap_phy_internal.o + hsmmc.o obj-$(CONFIG_MACH_OMAP4_PANDA) += board-omap4panda.o \ - hsmmc.o \ - omap_phy_internal.o + hsmmc.o -obj-$(CONFIG_MACH_OMAP3517EVM) += board-am3517evm.o \ - omap_phy_internal.o \ +obj-$(CONFIG_MACH_OMAP3517EVM) += board-am3517evm.o obj-$(CONFIG_MACH_CRANEBOARD) += board-am3517crane.o @@ -260,6 +257,8 @@ obj-$(CONFIG_MACH_TI8168EVM) += board-ti8168evm.o usbfs-$(CONFIG_ARCH_OMAP_OTG) := usb-fs.o obj-y += $(usbfs-m) $(usbfs-y) obj-y += usb-musb.o +obj-y += omap_phy_internal.o + obj-$(CONFIG_MACH_OMAP2_TUSB6010) += usb-tusb6010.o obj-y += usb-host.o diff --git a/arch/arm/mach-omap2/Makefile.boot b/arch/arm/mach-omap2/Makefile.boot index 565aff7f37a9..b03e562acc60 100644 --- a/arch/arm/mach-omap2/Makefile.boot +++ b/arch/arm/mach-omap2/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x80008000 + zreladdr-y += 0x80008000 params_phys-y := 0x80000100 initrd_phys-y := 0x80800000 diff --git a/arch/arm/mach-omap2/board-2430sdp.c b/arch/arm/mach-omap2/board-2430sdp.c index 87f43ade4405..f8ce84b69eb1 100644 --- a/arch/arm/mach-omap2/board-2430sdp.c +++ b/arch/arm/mach-omap2/board-2430sdp.c @@ -39,6 +39,9 @@ #include <plat/usb.h> #include <plat/gpmc-smc91x.h> +#include <video/omapdss.h> +#include <video/omap-panel-generic-dpi.h> + #include "mux.h" #include "hsmmc.h" #include "common-board-devices.h" @@ -99,20 +102,72 @@ static struct platform_device sdp2430_flash_device = { .resource = &sdp2430_flash_resource, }; -static struct platform_device sdp2430_lcd_device = { - .name = "sdp2430_lcd", - .id = -1, -}; - static struct platform_device *sdp2430_devices[] __initdata = { &sdp2430_flash_device, +}; + +/* LCD */ +#define SDP2430_LCD_PANEL_BACKLIGHT_GPIO 91 +#define SDP2430_LCD_PANEL_ENABLE_GPIO 154 + +static int sdp2430_panel_enable_lcd(struct omap_dss_device *dssdev) +{ + gpio_direction_output(SDP2430_LCD_PANEL_ENABLE_GPIO, 1); + gpio_direction_output(SDP2430_LCD_PANEL_BACKLIGHT_GPIO, 1); + + return 0; +} + +static void sdp2430_panel_disable_lcd(struct omap_dss_device *dssdev) +{ + gpio_direction_output(SDP2430_LCD_PANEL_ENABLE_GPIO, 0); + gpio_direction_output(SDP2430_LCD_PANEL_BACKLIGHT_GPIO, 0); +} + +static struct panel_generic_dpi_data sdp2430_panel_data = { + .name = "nec_nl2432dr22-11b", + .platform_enable = sdp2430_panel_enable_lcd, + .platform_disable = sdp2430_panel_disable_lcd, +}; + +static struct omap_dss_device sdp2430_lcd_device = { + .name = "lcd", + .driver_name = "generic_dpi_panel", + .type = OMAP_DISPLAY_TYPE_DPI, + .phy.dpi.data_lines = 16, + .data = &sdp2430_panel_data, +}; + +static struct omap_dss_device *sdp2430_dss_devices[] = { &sdp2430_lcd_device, }; -static struct omap_lcd_config sdp2430_lcd_config __initdata = { - .ctrl_name = "internal", +static struct omap_dss_board_info sdp2430_dss_data = { + .num_devices = ARRAY_SIZE(sdp2430_dss_devices), + .devices = sdp2430_dss_devices, + .default_device = &sdp2430_lcd_device, }; +static void __init sdp2430_display_init(void) +{ + int r; + + static struct gpio gpios[] __initdata = { + { SDP2430_LCD_PANEL_ENABLE_GPIO, GPIOF_OUT_INIT_LOW, + "LCD reset" }, + { SDP2430_LCD_PANEL_BACKLIGHT_GPIO, GPIOF_OUT_INIT_LOW, + "LCD Backlight" }, + }; + + r = gpio_request_array(gpios, ARRAY_SIZE(gpios)); + if (r) { + pr_err("Cannot request LCD GPIOs, error %d\n", r); + return; + } + + omap_display_init(&sdp2430_dss_data); +} + #if defined(CONFIG_SMC91X) || defined(CONFIG_SMC91x_MODULE) static struct omap_smc91x_platform_data board_smc91x_data = { @@ -137,10 +192,6 @@ static inline void board_smc91x_init(void) #endif -static struct omap_board_config_kernel sdp2430_config[] __initdata = { - {OMAP_TAG_LCD, &sdp2430_lcd_config}, -}; - static void __init omap_2430sdp_init_early(void) { omap2_init_common_infrastructure(); @@ -229,9 +280,6 @@ static void __init omap_2430sdp_init(void) { omap2430_mux_init(board_mux, OMAP_PACKAGE_ZAC); - omap_board_config = sdp2430_config; - omap_board_config_size = ARRAY_SIZE(sdp2430_config); - omap2430_i2c_init(); platform_add_devices(sdp2430_devices, ARRAY_SIZE(sdp2430_devices)); @@ -247,6 +295,8 @@ static void __init omap_2430sdp_init(void) /* Turn off secondary LCD backlight */ gpio_request_one(SECONDARY_LCD_GPIO, GPIOF_OUT_INIT_LOW, "Secondary LCD backlight"); + + sdp2430_display_init(); } static void __init omap_2430sdp_map_io(void) diff --git a/arch/arm/mach-omap2/board-3430sdp.c b/arch/arm/mach-omap2/board-3430sdp.c index 2430531b2239..204beddcb949 100644 --- a/arch/arm/mach-omap2/board-3430sdp.c +++ b/arch/arm/mach-omap2/board-3430sdp.c @@ -37,7 +37,7 @@ #include <plat/dma.h> #include <plat/gpmc.h> #include <video/omapdss.h> -#include <video/omap-panel-generic-dpi.h> +#include <video/omap-panel-dvi.h> #include <plat/gpmc-smc91x.h> @@ -186,8 +186,7 @@ static struct omap_dss_device sdp3430_lcd_device = { .platform_disable = sdp3430_panel_disable_lcd, }; -static struct panel_generic_dpi_data dvi_panel = { - .name = "generic", +static struct panel_dvi_platform_data dvi_panel = { .platform_enable = sdp3430_panel_enable_dvi, .platform_disable = sdp3430_panel_disable_dvi, }; @@ -195,7 +194,7 @@ static struct panel_generic_dpi_data dvi_panel = { static struct omap_dss_device sdp3430_dvi_device = { .name = "dvi", .type = OMAP_DISPLAY_TYPE_DPI, - .driver_name = "generic_dpi_panel", + .driver_name = "dvi", .data = &dvi_panel, .phy.dpi.data_lines = 24, }; diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c index e749c950d1bc..a3e37ff3ad18 100644 --- a/arch/arm/mach-omap2/board-4430sdp.c +++ b/arch/arm/mach-omap2/board-4430sdp.c @@ -38,6 +38,8 @@ #include <plat/mmc.h> #include <plat/omap4-keypad.h> #include <video/omapdss.h> +#include <video/omap-panel-nokia-dsi.h> +#include <video/omap-panel-picodlp.h> #include <linux/wl12xx.h> #include "mux.h" @@ -52,6 +54,8 @@ #define OMAP4_SFH7741_ENABLE_GPIO 188 #define HDMI_GPIO_HPD 60 /* Hot plug pin for HDMI */ #define HDMI_GPIO_LS_OE 41 /* Level shifter for HDMI */ +#define DISPLAY_SEL_GPIO 59 /* LCD2/PicoDLP switch */ +#define DLP_POWER_ON_GPIO 40 #define GPIO_WIFI_PMENA 54 #define GPIO_WIFI_IRQ 53 @@ -340,11 +344,6 @@ static int __init omap_ethernet_init(void) return status; } -static struct platform_device sdp4430_lcd_device = { - .name = "sdp4430_lcd", - .id = -1, -}; - static struct regulator_consumer_supply sdp4430_vbat_supply[] = { REGULATOR_SUPPLY("vddvibl", "twl6040-vibra"), REGULATOR_SUPPLY("vddvibr", "twl6040-vibra"), @@ -374,21 +373,12 @@ static struct platform_device sdp4430_vbat = { }; static struct platform_device *sdp4430_devices[] __initdata = { - &sdp4430_lcd_device, &sdp4430_gpio_keys_device, &sdp4430_leds_gpio, &sdp4430_leds_pwm, &sdp4430_vbat, }; -static struct omap_lcd_config sdp4430_lcd_config __initdata = { - .ctrl_name = "internal", -}; - -static struct omap_board_config_kernel sdp4430_config[] __initdata = { - { OMAP_TAG_LCD, &sdp4430_lcd_config }, -}; - static void __init omap_4430sdp_init_early(void) { omap2_init_common_infrastructure(); @@ -648,37 +638,202 @@ static void sdp4430_panel_disable_hdmi(struct omap_dss_device *dssdev) gpio_free(HDMI_GPIO_HPD); } -static struct omap_dss_device sdp4430_hdmi_device = { - .name = "hdmi", - .driver_name = "hdmi_panel", - .type = OMAP_DISPLAY_TYPE_HDMI, - .clocks = { - .dispc = { +static struct nokia_dsi_panel_data dsi1_panel = { + .name = "taal", + .reset_gpio = 102, + .use_ext_te = false, + .ext_te_gpio = 101, + .esd_interval = 0, +}; + +static struct omap_dss_device sdp4430_lcd_device = { + .name = "lcd", + .driver_name = "taal", + .type = OMAP_DISPLAY_TYPE_DSI, + .data = &dsi1_panel, + .phy.dsi = { + .clk_lane = 1, + .clk_pol = 0, + .data1_lane = 2, + .data1_pol = 0, + .data2_lane = 3, + .data2_pol = 0, + + .module = 0, + }, + + .clocks = { + .dispc = { + .channel = { + /* Logic Clock = 172.8 MHz */ + .lck_div = 1, + /* Pixel Clock = 34.56 MHz */ + .pck_div = 5, + .lcd_clk_src = OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DISPC, + }, .dispc_fclk_src = OMAP_DSS_CLK_SRC_FCK, }, - .hdmi = { - .regn = 15, - .regm2 = 1, + + .dsi = { + .regn = 16, /* Fint = 2.4 MHz */ + .regm = 180, /* DDR Clock = 216 MHz */ + .regm_dispc = 5, /* PLL1_CLK1 = 172.8 MHz */ + .regm_dsi = 5, /* PLL1_CLK2 = 172.8 MHz */ + + .lp_clk_div = 10, /* LP Clock = 8.64 MHz */ + .dsi_fclk_src = OMAP_DSS_CLK_SRC_DSI_PLL_HSDIV_DSI, + }, + }, + .channel = OMAP_DSS_CHANNEL_LCD, +}; + +static struct nokia_dsi_panel_data dsi2_panel = { + .name = "taal", + .reset_gpio = 104, + .use_ext_te = false, + .ext_te_gpio = 103, + .esd_interval = 0, +}; + +static struct omap_dss_device sdp4430_lcd2_device = { + .name = "lcd2", + .driver_name = "taal", + .type = OMAP_DISPLAY_TYPE_DSI, + .data = &dsi2_panel, + .phy.dsi = { + .clk_lane = 1, + .clk_pol = 0, + .data1_lane = 2, + .data1_pol = 0, + .data2_lane = 3, + .data2_pol = 0, + + .module = 1, + }, + + .clocks = { + .dispc = { + .channel = { + /* Logic Clock = 172.8 MHz */ + .lck_div = 1, + /* Pixel Clock = 34.56 MHz */ + .pck_div = 5, + .lcd_clk_src = OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DISPC, + }, + .dispc_fclk_src = OMAP_DSS_CLK_SRC_FCK, + }, + + .dsi = { + .regn = 16, /* Fint = 2.4 MHz */ + .regm = 180, /* DDR Clock = 216 MHz */ + .regm_dispc = 5, /* PLL1_CLK1 = 172.8 MHz */ + .regm_dsi = 5, /* PLL1_CLK2 = 172.8 MHz */ + + .lp_clk_div = 10, /* LP Clock = 8.64 MHz */ + .dsi_fclk_src = OMAP_DSS_CLK_SRC_DSI2_PLL_HSDIV_DSI, }, }, + .channel = OMAP_DSS_CHANNEL_LCD2, +}; + +static void sdp4430_lcd_init(void) +{ + int r; + + r = gpio_request_one(dsi1_panel.reset_gpio, GPIOF_DIR_OUT, + "lcd1_reset_gpio"); + if (r) + pr_err("%s: Could not get lcd1_reset_gpio\n", __func__); + + r = gpio_request_one(dsi2_panel.reset_gpio, GPIOF_DIR_OUT, + "lcd2_reset_gpio"); + if (r) + pr_err("%s: Could not get lcd2_reset_gpio\n", __func__); +} + +static struct omap_dss_device sdp4430_hdmi_device = { + .name = "hdmi", + .driver_name = "hdmi_panel", + .type = OMAP_DISPLAY_TYPE_HDMI, .platform_enable = sdp4430_panel_enable_hdmi, .platform_disable = sdp4430_panel_disable_hdmi, .channel = OMAP_DSS_CHANNEL_DIGIT, }; +static struct picodlp_panel_data sdp4430_picodlp_pdata = { + .picodlp_adapter_id = 2, + .emu_done_gpio = 44, + .pwrgood_gpio = 45, +}; + +static void sdp4430_picodlp_init(void) +{ + int r; + const struct gpio picodlp_gpios[] = { + {DLP_POWER_ON_GPIO, GPIOF_OUT_INIT_LOW, + "DLP POWER ON"}, + {sdp4430_picodlp_pdata.emu_done_gpio, GPIOF_IN, + "DLP EMU DONE"}, + {sdp4430_picodlp_pdata.pwrgood_gpio, GPIOF_OUT_INIT_LOW, + "DLP PWRGOOD"}, + }; + + r = gpio_request_array(picodlp_gpios, ARRAY_SIZE(picodlp_gpios)); + if (r) + pr_err("Cannot request PicoDLP GPIOs, error %d\n", r); +} + +static int sdp4430_panel_enable_picodlp(struct omap_dss_device *dssdev) +{ + gpio_set_value(DISPLAY_SEL_GPIO, 0); + gpio_set_value(DLP_POWER_ON_GPIO, 1); + + return 0; +} + +static void sdp4430_panel_disable_picodlp(struct omap_dss_device *dssdev) +{ + gpio_set_value(DLP_POWER_ON_GPIO, 0); + gpio_set_value(DISPLAY_SEL_GPIO, 1); +} + +static struct omap_dss_device sdp4430_picodlp_device = { + .name = "picodlp", + .driver_name = "picodlp_panel", + .type = OMAP_DISPLAY_TYPE_DPI, + .phy.dpi.data_lines = 24, + .channel = OMAP_DSS_CHANNEL_LCD2, + .platform_enable = sdp4430_panel_enable_picodlp, + .platform_disable = sdp4430_panel_disable_picodlp, + .data = &sdp4430_picodlp_pdata, +}; + static struct omap_dss_device *sdp4430_dss_devices[] = { + &sdp4430_lcd_device, + &sdp4430_lcd2_device, &sdp4430_hdmi_device, + &sdp4430_picodlp_device, }; static struct omap_dss_board_info sdp4430_dss_data = { .num_devices = ARRAY_SIZE(sdp4430_dss_devices), .devices = sdp4430_dss_devices, - .default_device = &sdp4430_hdmi_device, + .default_device = &sdp4430_lcd_device, }; -void omap_4430sdp_display_init(void) +static void omap_4430sdp_display_init(void) { + int r; + + /* Enable LCD2 by default (instead of Pico DLP) */ + r = gpio_request_one(DISPLAY_SEL_GPIO, GPIOF_OUT_INIT_HIGH, + "display_sel"); + if (r) + pr_err("%s: Could not get display_sel GPIO\n", __func__); + + sdp4430_lcd_init(); sdp4430_hdmi_mux_init(); + sdp4430_picodlp_init(); omap_display_init(&sdp4430_dss_data); } @@ -802,9 +957,6 @@ static void __init omap_4430sdp_init(void) package = OMAP_PACKAGE_CBL; omap4_mux_init(board_mux, NULL, package); - omap_board_config = sdp4430_config; - omap_board_config_size = ARRAY_SIZE(sdp4430_config); - omap4_i2c_init(); omap_sfh7741prox_init(); platform_add_devices(sdp4430_devices, ARRAY_SIZE(sdp4430_devices)); diff --git a/arch/arm/mach-omap2/board-am3517evm.c b/arch/arm/mach-omap2/board-am3517evm.c index 1325085e453d..ab10f75984d8 100644 --- a/arch/arm/mach-omap2/board-am3517evm.c +++ b/arch/arm/mach-omap2/board-am3517evm.c @@ -36,6 +36,7 @@ #include <plat/usb.h> #include <video/omapdss.h> #include <video/omap-panel-generic-dpi.h> +#include <video/omap-panel-dvi.h> #include "mux.h" #include "control.h" @@ -333,8 +334,7 @@ static void am3517_evm_panel_disable_dvi(struct omap_dss_device *dssdev) dvi_enabled = 0; } -static struct panel_generic_dpi_data dvi_panel = { - .name = "generic", +static struct panel_dvi_platform_data dvi_panel = { .platform_enable = am3517_evm_panel_enable_dvi, .platform_disable = am3517_evm_panel_disable_dvi, }; @@ -342,7 +342,7 @@ static struct panel_generic_dpi_data dvi_panel = { static struct omap_dss_device am3517_evm_dvi_device = { .type = OMAP_DISPLAY_TYPE_DPI, .name = "dvi", - .driver_name = "generic_dpi_panel", + .driver_name = "dvi", .data = &dvi_panel, .phy.dpi.data_lines = 24, }; diff --git a/arch/arm/mach-omap2/board-apollon.c b/arch/arm/mach-omap2/board-apollon.c index 67800e647d7a..ad55351e0cab 100644 --- a/arch/arm/mach-omap2/board-apollon.c +++ b/arch/arm/mach-omap2/board-apollon.c @@ -40,6 +40,9 @@ #include <plat/common.h> #include <plat/gpmc.h> +#include <video/omapdss.h> +#include <video/omap-panel-generic-dpi.h> + #include "mux.h" #include "control.h" @@ -149,11 +152,6 @@ static struct platform_device apollon_smc91x_device = { .resource = apollon_smc91x_resources, }; -static struct platform_device apollon_lcd_device = { - .name = "apollon_lcd", - .id = -1, -}; - static struct omap_led_config apollon_led_config[] = { { .cdev = { @@ -191,7 +189,6 @@ static struct platform_device apollon_led_device = { static struct platform_device *apollon_devices[] __initdata = { &apollon_onenand_device, &apollon_smc91x_device, - &apollon_lcd_device, &apollon_led_device, }; @@ -265,12 +262,26 @@ static struct omap_usb_config apollon_usb_config __initdata = { .pins[0] = 6, }; -static struct omap_lcd_config apollon_lcd_config __initdata = { - .ctrl_name = "internal", +static struct panel_generic_dpi_data apollon_panel_data = { + .name = "apollon", }; -static struct omap_board_config_kernel apollon_config[] __initdata = { - { OMAP_TAG_LCD, &apollon_lcd_config }, +static struct omap_dss_device apollon_lcd_device = { + .name = "lcd", + .driver_name = "generic_dpi_panel", + .type = OMAP_DISPLAY_TYPE_DPI, + .phy.dpi.data_lines = 18, + .data = &apollon_panel_data, +}; + +static struct omap_dss_device *apollon_dss_devices[] = { + &apollon_lcd_device, +}; + +static struct omap_dss_board_info apollon_dss_data = { + .num_devices = ARRAY_SIZE(apollon_dss_devices), + .devices = apollon_dss_devices, + .default_device = &apollon_lcd_device, }; static void __init omap_apollon_init_early(void) @@ -314,8 +325,6 @@ static void __init omap_apollon_init(void) u32 v; omap2420_mux_init(board_mux, OMAP_PACKAGE_ZAC); - omap_board_config = apollon_config; - omap_board_config_size = ARRAY_SIZE(apollon_config); apollon_init_smc91x(); apollon_led_init(); @@ -340,6 +349,8 @@ static void __init omap_apollon_init(void) */ platform_add_devices(apollon_devices, ARRAY_SIZE(apollon_devices)); omap_serial_init(); + + omap_display_init(&apollon_dss_data); } static void __init omap_apollon_map_io(void) diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c index 38179c175503..6e0f0d2e39bc 100644 --- a/arch/arm/mach-omap2/board-cm-t35.c +++ b/arch/arm/mach-omap2/board-cm-t35.c @@ -43,6 +43,7 @@ #include <plat/usb.h> #include <video/omapdss.h> #include <video/omap-panel-generic-dpi.h> +#include <video/omap-panel-dvi.h> #include <plat/mcspi.h> #include <mach/hardware.h> @@ -242,8 +243,7 @@ static struct omap_dss_device cm_t35_lcd_device = { .phy.dpi.data_lines = 18, }; -static struct panel_generic_dpi_data dvi_panel = { - .name = "generic", +static struct panel_dvi_platform_data dvi_panel = { .platform_enable = cm_t35_panel_enable_dvi, .platform_disable = cm_t35_panel_disable_dvi, }; @@ -251,7 +251,7 @@ static struct panel_generic_dpi_data dvi_panel = { static struct omap_dss_device cm_t35_dvi_device = { .name = "dvi", .type = OMAP_DISPLAY_TYPE_DPI, - .driver_name = "generic_dpi_panel", + .driver_name = "dvi", .data = &dvi_panel, .phy.dpi.data_lines = 24, }; diff --git a/arch/arm/mach-omap2/board-devkit8000.c b/arch/arm/mach-omap2/board-devkit8000.c index 99a42432ac93..d9bfe54917e4 100644 --- a/arch/arm/mach-omap2/board-devkit8000.c +++ b/arch/arm/mach-omap2/board-devkit8000.c @@ -47,6 +47,7 @@ #include <plat/usb.h> #include <video/omapdss.h> #include <video/omap-panel-generic-dpi.h> +#include <video/omap-panel-dvi.h> #include <plat/mcspi.h> #include <linux/input/matrix_keypad.h> @@ -139,7 +140,7 @@ static struct regulator_consumer_supply devkit8000_vio_supply[] = { }; static struct panel_generic_dpi_data lcd_panel = { - .name = "generic", + .name = "innolux_at070tn83", .platform_enable = devkit8000_panel_enable_lcd, .platform_disable = devkit8000_panel_disable_lcd, }; @@ -152,8 +153,7 @@ static struct omap_dss_device devkit8000_lcd_device = { .phy.dpi.data_lines = 24, }; -static struct panel_generic_dpi_data dvi_panel = { - .name = "generic", +static struct panel_dvi_platform_data dvi_panel = { .platform_enable = devkit8000_panel_enable_dvi, .platform_disable = devkit8000_panel_disable_dvi, }; @@ -161,7 +161,7 @@ static struct panel_generic_dpi_data dvi_panel = { static struct omap_dss_device devkit8000_dvi_device = { .name = "dvi", .type = OMAP_DISPLAY_TYPE_DPI, - .driver_name = "generic_dpi_panel", + .driver_name = "dvi", .data = &dvi_panel, .phy.dpi.data_lines = 24, }; @@ -267,7 +267,7 @@ static struct twl4030_gpio_platform_data devkit8000_gpio_data = { static struct regulator_consumer_supply devkit8000_vpll1_supplies[] = { REGULATOR_SUPPLY("vdds_dsi", "omapdss"), - REGULATOR_SUPPLY("vdds_dsi", "omapdss_dsi1"), + REGULATOR_SUPPLY("vdds_dsi", "omapdss_dsi.0"), }; /* VMMC1 for MMC1 pins CMD, CLK, DAT0..DAT3 (20 mA, plus card == max 220 mA) */ diff --git a/arch/arm/mach-omap2/board-h4.c b/arch/arm/mach-omap2/board-h4.c index 82421a4cfa92..8fcf79628ca1 100644 --- a/arch/arm/mach-omap2/board-h4.c +++ b/arch/arm/mach-omap2/board-h4.c @@ -39,6 +39,9 @@ #include <plat/dma.h> #include <plat/gpmc.h> +#include <video/omapdss.h> +#include <video/omap-panel-generic-dpi.h> + #include "mux.h" #include "control.h" @@ -156,17 +159,33 @@ static struct platform_device h4_kp_device = { }, }; -static struct platform_device h4_lcd_device = { - .name = "lcd_h4", - .id = -1, -}; - static struct platform_device *h4_devices[] __initdata = { &h4_flash_device, &h4_kp_device, +}; + +static struct panel_generic_dpi_data h4_panel_data = { + .name = "h4", +}; + +static struct omap_dss_device h4_lcd_device = { + .name = "lcd", + .driver_name = "generic_dpi_panel", + .type = OMAP_DISPLAY_TYPE_DPI, + .phy.dpi.data_lines = 16, + .data = &h4_panel_data, +}; + +static struct omap_dss_device *h4_dss_devices[] = { &h4_lcd_device, }; +static struct omap_dss_board_info h4_dss_data = { + .num_devices = ARRAY_SIZE(h4_dss_devices), + .devices = h4_dss_devices, + .default_device = &h4_lcd_device, +}; + /* 2420 Sysboot setup (2430 is different) */ static u32 get_sysboot_value(void) { @@ -270,10 +289,6 @@ static void __init h4_init_flash(void) h4_flash_resource.end = base + SZ_64M - 1; } -static struct omap_lcd_config h4_lcd_config __initdata = { - .ctrl_name = "internal", -}; - static struct omap_usb_config h4_usb_config __initdata = { /* S1.10 OFF -- usb "download port" * usb0 switched to Mini-B port and isp1105 transceiver; @@ -285,10 +300,6 @@ static struct omap_usb_config h4_usb_config __initdata = { .hmc_mode = 0x00, /* 0:dev|otg 1:disable 2:disable */ }; -static struct omap_board_config_kernel h4_config[] __initdata = { - { OMAP_TAG_LCD, &h4_lcd_config }, -}; - static void __init omap_h4_init_early(void) { omap2_init_common_infrastructure(); @@ -330,9 +341,6 @@ static void __init omap_h4_init(void) { omap2420_mux_init(board_mux, OMAP_PACKAGE_ZAF); - omap_board_config = h4_config; - omap_board_config_size = ARRAY_SIZE(h4_config); - /* * Make sure the serial ports are muxed on at this point. * You have to mux them off in device drivers later on @@ -371,6 +379,8 @@ static void __init omap_h4_init(void) omap2_usbfs_init(&h4_usb_config); omap_serial_init(); h4_init_flash(); + + omap_display_init(&h4_dss_data); } static void __init omap_h4_map_io(void) diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c index 7040352b16b4..96f9ef34d2fb 100644 --- a/arch/arm/mach-omap2/board-igep0020.c +++ b/arch/arm/mach-omap2/board-igep0020.c @@ -32,7 +32,7 @@ #include <plat/gpmc.h> #include <plat/usb.h> #include <video/omapdss.h> -#include <video/omap-panel-generic-dpi.h> +#include <video/omap-panel-dvi.h> #include <plat/onenand.h> #include "mux.h" @@ -455,16 +455,16 @@ static void igep2_disable_dvi(struct omap_dss_device *dssdev) gpio_direction_output(IGEP2_GPIO_DVI_PUP, 0); } -static struct panel_generic_dpi_data dvi_panel = { - .name = "generic", +static struct panel_dvi_platform_data dvi_panel = { .platform_enable = igep2_enable_dvi, .platform_disable = igep2_disable_dvi, + .i2c_bus_num = 3, }; static struct omap_dss_device igep2_dvi_device = { .type = OMAP_DISPLAY_TYPE_DPI, .name = "dvi", - .driver_name = "generic_dpi_panel", + .driver_name = "dvi", .data = &dvi_panel, .phy.dpi.data_lines = 24, }; diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c index abe8c7e496a2..f8f8a68a4899 100644 --- a/arch/arm/mach-omap2/board-ldp.c +++ b/arch/arm/mach-omap2/board-ldp.c @@ -27,6 +27,7 @@ #include <linux/io.h> #include <linux/smsc911x.h> #include <linux/mmc/host.h> +#include <linux/gpio.h> #include <mach/hardware.h> #include <asm/mach-types.h> @@ -43,6 +44,9 @@ #include <plat/usb.h> #include <plat/gpmc-smsc911x.h> +#include <video/omapdss.h> +#include <video/omap-panel-generic-dpi.h> + #include "board-flash.h" #include "mux.h" #include "hsmmc.h" @@ -179,29 +183,108 @@ static inline void __init ldp_init_smsc911x(void) gpmc_smsc911x_init(&smsc911x_cfg); } -static struct platform_device ldp_lcd_device = { - .name = "ldp_lcd", - .id = -1, +/* LCD */ + +static int ldp_backlight_gpio; +static int ldp_lcd_enable_gpio; + +#define LCD_PANEL_RESET_GPIO 55 +#define LCD_PANEL_QVGA_GPIO 56 + +static int ldp_panel_enable_lcd(struct omap_dss_device *dssdev) +{ + if (gpio_is_valid(ldp_lcd_enable_gpio)) + gpio_direction_output(ldp_lcd_enable_gpio, 1); + if (gpio_is_valid(ldp_backlight_gpio)) + gpio_direction_output(ldp_backlight_gpio, 1); + + return 0; +} + +static void ldp_panel_disable_lcd(struct omap_dss_device *dssdev) +{ + if (gpio_is_valid(ldp_lcd_enable_gpio)) + gpio_direction_output(ldp_lcd_enable_gpio, 0); + if (gpio_is_valid(ldp_backlight_gpio)) + gpio_direction_output(ldp_backlight_gpio, 0); +} + +static struct panel_generic_dpi_data ldp_panel_data = { + .name = "nec_nl2432dr22-11b", + .platform_enable = ldp_panel_enable_lcd, + .platform_disable = ldp_panel_disable_lcd, }; -static struct omap_lcd_config ldp_lcd_config __initdata = { - .ctrl_name = "internal", +static struct omap_dss_device ldp_lcd_device = { + .name = "lcd", + .driver_name = "generic_dpi_panel", + .type = OMAP_DISPLAY_TYPE_DPI, + .phy.dpi.data_lines = 18, + .data = &ldp_panel_data, +}; + +static struct omap_dss_device *ldp_dss_devices[] = { + &ldp_lcd_device, }; -static struct omap_board_config_kernel ldp_config[] __initdata = { - { OMAP_TAG_LCD, &ldp_lcd_config }, +static struct omap_dss_board_info ldp_dss_data = { + .num_devices = ARRAY_SIZE(ldp_dss_devices), + .devices = ldp_dss_devices, + .default_device = &ldp_lcd_device, }; +static void __init ldp_display_init(void) +{ + int r; + + static struct gpio gpios[] __initdata = { + {LCD_PANEL_RESET_GPIO, GPIOF_OUT_INIT_HIGH, "LCD RESET"}, + {LCD_PANEL_QVGA_GPIO, GPIOF_OUT_INIT_HIGH, "LCD QVGA"}, + }; + + r = gpio_request_array(gpios, ARRAY_SIZE(gpios)); + if (r) { + pr_err("Cannot request LCD GPIOs, error %d\n", r); + return; + } + + omap_display_init(&ldp_dss_data); +} + static void __init omap_ldp_init_early(void) { omap2_init_common_infrastructure(); omap2_init_common_devices(NULL, NULL); } +static int ldp_twl_gpio_setup(struct device *dev, unsigned gpio, unsigned ngpio) +{ + int r; + + struct gpio gpios[] = { + {gpio + 7 , GPIOF_OUT_INIT_LOW, "LCD ENABLE"}, + {gpio + 15, GPIOF_OUT_INIT_LOW, "LCD BACKLIGHT"}, + }; + + r = gpio_request_array(gpios, ARRAY_SIZE(gpios)); + if (r) { + pr_err("Cannot request LCD GPIOs, error %d\n", r); + ldp_backlight_gpio = -EINVAL; + ldp_lcd_enable_gpio = -EINVAL; + return r; + } + + ldp_backlight_gpio = gpio + 15; + ldp_lcd_enable_gpio = gpio + 7; + + return 0; +} + static struct twl4030_gpio_platform_data ldp_gpio_data = { .gpio_base = OMAP_MAX_GPIO_LINES, .irq_base = TWL4030_GPIO_IRQ_BASE, .irq_end = TWL4030_GPIO_IRQ_END, + .setup = ldp_twl_gpio_setup, }; static struct regulator_consumer_supply ldp_vmmc1_supply[] = { @@ -243,10 +326,31 @@ static struct regulator_init_data ldp_vaux1 = { .consumer_supplies = ldp_vaux1_supplies, }; +static struct regulator_consumer_supply ldp_vpll2_supplies[] = { + REGULATOR_SUPPLY("vdds_dsi", "omapdss"), + REGULATOR_SUPPLY("vdds_dsi", "omapdss_dsi1"), +}; + +static struct regulator_init_data ldp_vpll2 = { + .constraints = { + .name = "VDVI", + .min_uV = 1800000, + .max_uV = 1800000, + .apply_uV = true, + .valid_modes_mask = REGULATOR_MODE_NORMAL + | REGULATOR_MODE_STANDBY, + .valid_ops_mask = REGULATOR_CHANGE_MODE + | REGULATOR_CHANGE_STATUS, + }, + .num_consumer_supplies = ARRAY_SIZE(ldp_vpll2_supplies), + .consumer_supplies = ldp_vpll2_supplies, +}; + static struct twl4030_platform_data ldp_twldata = { /* platform_data for children goes here */ .vmmc1 = &ldp_vmmc1, .vaux1 = &ldp_vaux1, + .vpll2 = &ldp_vpll2, .gpio = &ldp_gpio_data, .keypad = &ldp_kp_twl4030_data, }; @@ -272,7 +376,6 @@ static struct omap2_hsmmc_info mmc[] __initdata = { }; static struct platform_device *ldp_devices[] __initdata = { - &ldp_lcd_device, &ldp_gpio_keys_device, }; @@ -317,8 +420,6 @@ static struct mtd_partition ldp_nand_partitions[] = { static void __init omap_ldp_init(void) { omap3_mux_init(board_mux, OMAP_PACKAGE_CBB); - omap_board_config = ldp_config; - omap_board_config_size = ARRAY_SIZE(ldp_config); ldp_init_smsc911x(); omap_i2c_init(); platform_add_devices(ldp_devices, ARRAY_SIZE(ldp_devices)); @@ -329,6 +430,7 @@ static void __init omap_ldp_init(void) ARRAY_SIZE(ldp_nand_partitions), ZOOM_NAND_CS, 0); omap2_hsmmc_init(mmc); + ldp_display_init(); } MACHINE_START(OMAP_LDP, "OMAP LDP board") diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c index 1fde8a0474bb..928933ba28ce 100644 --- a/arch/arm/mach-omap2/board-omap3beagle.c +++ b/arch/arm/mach-omap2/board-omap3beagle.c @@ -42,7 +42,7 @@ #include <plat/board.h> #include <plat/common.h> #include <video/omapdss.h> -#include <video/omap-panel-generic-dpi.h> +#include <video/omap-panel-dvi.h> #include <plat/gpmc.h> #include <plat/nand.h> #include <plat/usb.h> @@ -203,16 +203,16 @@ static void beagle_disable_dvi(struct omap_dss_device *dssdev) gpio_set_value(dssdev->reset_gpio, 0); } -static struct panel_generic_dpi_data dvi_panel = { - .name = "generic", +static struct panel_dvi_platform_data dvi_panel = { .platform_enable = beagle_enable_dvi, .platform_disable = beagle_disable_dvi, + .i2c_bus_num = 3, }; static struct omap_dss_device beagle_dvi_device = { .type = OMAP_DISPLAY_TYPE_DPI, .name = "dvi", - .driver_name = "generic_dpi_panel", + .driver_name = "dvi", .data = &dvi_panel, .phy.dpi.data_lines = 24, .reset_gpio = -EINVAL, diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c index 15c69a0c1ce5..0d5a9e46a6af 100644 --- a/arch/arm/mach-omap2/board-omap3evm.c +++ b/arch/arm/mach-omap2/board-omap3evm.c @@ -45,7 +45,7 @@ #include <plat/common.h> #include <plat/mcspi.h> #include <video/omapdss.h> -#include <video/omap-panel-generic-dpi.h> +#include <video/omap-panel-dvi.h> #include "mux.h" #include "sdram-micron-mt46h32m32lf-6.h" @@ -247,8 +247,7 @@ static void omap3_evm_disable_dvi(struct omap_dss_device *dssdev) dvi_enabled = 0; } -static struct panel_generic_dpi_data dvi_panel = { - .name = "generic", +static struct panel_dvi_platform_data dvi_panel = { .platform_enable = omap3_evm_enable_dvi, .platform_disable = omap3_evm_disable_dvi, }; @@ -256,7 +255,7 @@ static struct panel_generic_dpi_data dvi_panel = { static struct omap_dss_device omap3_evm_dvi_device = { .name = "dvi", .type = OMAP_DISPLAY_TYPE_DPI, - .driver_name = "generic_dpi_panel", + .driver_name = "dvi", .data = &dvi_panel, .phy.dpi.data_lines = 24, }; diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c index ace56938dd3b..cca523eb73b4 100644 --- a/arch/arm/mach-omap2/board-omap3pandora.c +++ b/arch/arm/mach-omap2/board-omap3pandora.c @@ -335,7 +335,7 @@ static struct regulator_consumer_supply pandora_vmmc3_supply[] = { static struct regulator_consumer_supply pandora_vdds_supplies[] = { REGULATOR_SUPPLY("vdds_sdi", "omapdss"), REGULATOR_SUPPLY("vdds_dsi", "omapdss"), - REGULATOR_SUPPLY("vdds_dsi", "omapdss_dsi1"), + REGULATOR_SUPPLY("vdds_dsi", "omapdss_dsi.0"), }; static struct regulator_consumer_supply pandora_vcc_lcd_supply[] = { diff --git a/arch/arm/mach-omap2/board-omap3stalker.c b/arch/arm/mach-omap2/board-omap3stalker.c index ba13e1d5d0ab..4732589ad97e 100644 --- a/arch/arm/mach-omap2/board-omap3stalker.c +++ b/arch/arm/mach-omap2/board-omap3stalker.c @@ -41,6 +41,7 @@ #include <plat/usb.h> #include <video/omapdss.h> #include <video/omap-panel-generic-dpi.h> +#include <video/omap-panel-dvi.h> #include <plat/mcspi.h> #include <linux/input/matrix_keypad.h> @@ -107,39 +108,6 @@ static void __init omap3_stalker_display_init(void) return; } -static int omap3_stalker_enable_lcd(struct omap_dss_device *dssdev) -{ - if (dvi_enabled) { - printk(KERN_ERR "cannot enable LCD, DVI is enabled\n"); - return -EINVAL; - } - gpio_set_value(DSS_ENABLE_GPIO, 1); - gpio_set_value(LCD_PANEL_BKLIGHT_GPIO, 1); - lcd_enabled = 1; - return 0; -} - -static void omap3_stalker_disable_lcd(struct omap_dss_device *dssdev) -{ - gpio_set_value(DSS_ENABLE_GPIO, 0); - gpio_set_value(LCD_PANEL_BKLIGHT_GPIO, 0); - lcd_enabled = 0; -} - -static struct panel_generic_dpi_data lcd_panel = { - .name = "generic", - .platform_enable = omap3_stalker_enable_lcd, - .platform_disable = omap3_stalker_disable_lcd, -}; - -static struct omap_dss_device omap3_stalker_lcd_device = { - .name = "lcd", - .driver_name = "generic_dpi_panel", - .data = &lcd_panel, - .phy.dpi.data_lines = 24, - .type = OMAP_DISPLAY_TYPE_DPI, -}; - static int omap3_stalker_enable_tv(struct omap_dss_device *dssdev) { return 0; @@ -179,8 +147,7 @@ static void omap3_stalker_disable_dvi(struct omap_dss_device *dssdev) dvi_enabled = 0; } -static struct panel_generic_dpi_data dvi_panel = { - .name = "generic", +static struct panel_dvi_platform_data dvi_panel = { .platform_enable = omap3_stalker_enable_dvi, .platform_disable = omap3_stalker_disable_dvi, }; @@ -188,13 +155,12 @@ static struct panel_generic_dpi_data dvi_panel = { static struct omap_dss_device omap3_stalker_dvi_device = { .name = "dvi", .type = OMAP_DISPLAY_TYPE_DPI, - .driver_name = "generic_dpi_panel", + .driver_name = "dvi", .data = &dvi_panel, .phy.dpi.data_lines = 24, }; static struct omap_dss_device *omap3_stalker_dss_devices[] = { - &omap3_stalker_lcd_device, &omap3_stalker_tv_device, &omap3_stalker_dvi_device, }; diff --git a/arch/arm/mach-omap2/board-omap3touchbook.c b/arch/arm/mach-omap2/board-omap3touchbook.c index 49e4bd207cb6..abb68913e047 100644 --- a/arch/arm/mach-omap2/board-omap3touchbook.c +++ b/arch/arm/mach-omap2/board-omap3touchbook.c @@ -104,15 +104,6 @@ static struct omap2_hsmmc_info mmc[] = { {} /* Terminator */ }; -static struct platform_device omap3_touchbook_lcd_device = { - .name = "omap3touchbook_lcd", - .id = -1, -}; - -static struct omap_lcd_config omap3_touchbook_lcd_config __initdata = { - .ctrl_name = "internal", -}; - static struct regulator_consumer_supply touchbook_vmmc1_supply[] = { REGULATOR_SUPPLY("vmmc", "omap_hsmmc.0"), }; @@ -165,14 +156,12 @@ static struct twl4030_gpio_platform_data touchbook_gpio_data = { static struct regulator_consumer_supply touchbook_vdac_supply[] = { { .supply = "vdac", - .dev = &omap3_touchbook_lcd_device.dev, }, }; static struct regulator_consumer_supply touchbook_vdvi_supply[] = { { .supply = "vdvi", - .dev = &omap3_touchbook_lcd_device.dev, }, }; @@ -316,10 +305,6 @@ static struct platform_device keys_gpio = { }, }; -static struct omap_board_config_kernel omap3_touchbook_config[] __initdata = { - { OMAP_TAG_LCD, &omap3_touchbook_lcd_config }, -}; - #ifdef CONFIG_OMAP_MUX static struct omap_board_mux board_mux[] __initdata = { { .reg_offset = OMAP_MUX_TERMINATOR }, @@ -339,7 +324,6 @@ static void __init omap3_touchbook_init_irq(void) } static struct platform_device *omap3_touchbook_devices[] __initdata = { - &omap3_touchbook_lcd_device, &leds_gpio, &keys_gpio, }; @@ -376,8 +360,6 @@ early_param("tbr", early_touchbook_revision); static void __init omap3_touchbook_init(void) { omap3_mux_init(board_mux, OMAP_PACKAGE_CBB); - omap_board_config = omap3_touchbook_config; - omap_board_config_size = ARRAY_SIZE(omap3_touchbook_config); pm_power_off = omap3_touchbook_poweroff; diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c index 683bede73d54..ed38d8fd090f 100644 --- a/arch/arm/mach-omap2/board-omap4panda.c +++ b/arch/arm/mach-omap2/board-omap4panda.c @@ -40,7 +40,7 @@ #include <plat/common.h> #include <plat/usb.h> #include <plat/mmc.h> -#include <video/omap-panel-generic-dpi.h> +#include <video/omap-panel-dvi.h> #include "hsmmc.h" #include "control.h" @@ -455,16 +455,16 @@ static void omap4_panda_disable_dvi(struct omap_dss_device *dssdev) } /* Using generic display panel */ -static struct panel_generic_dpi_data omap4_dvi_panel = { - .name = "generic", +static struct panel_dvi_platform_data omap4_dvi_panel = { .platform_enable = omap4_panda_enable_dvi, .platform_disable = omap4_panda_disable_dvi, + .i2c_bus_num = 3, }; struct omap_dss_device omap4_panda_dvi_device = { .type = OMAP_DISPLAY_TYPE_DPI, .name = "dvi", - .driver_name = "generic_dpi_panel", + .driver_name = "dvi", .data = &omap4_dvi_panel, .phy.dpi.data_lines = 24, .reset_gpio = PANDA_DVI_TFP410_POWER_DOWN_GPIO, diff --git a/arch/arm/mach-omap2/board-overo.c b/arch/arm/mach-omap2/board-overo.c index e592fb134c4e..ec0f60c1cb7c 100644 --- a/arch/arm/mach-omap2/board-overo.c +++ b/arch/arm/mach-omap2/board-overo.c @@ -46,6 +46,7 @@ #include <plat/common.h> #include <video/omapdss.h> #include <video/omap-panel-generic-dpi.h> +#include <video/omap-panel-dvi.h> #include <plat/gpmc.h> #include <mach/hardware.h> #include <plat/nand.h> @@ -182,16 +183,16 @@ static void overo_panel_disable_dvi(struct omap_dss_device *dssdev) dvi_enabled = 0; } -static struct panel_generic_dpi_data dvi_panel = { - .name = "generic", +static struct panel_dvi_platform_data dvi_panel = { .platform_enable = overo_panel_enable_dvi, .platform_disable = overo_panel_disable_dvi, + .i2c_bus_num = 3, }; static struct omap_dss_device overo_dvi_device = { .name = "dvi", .type = OMAP_DISPLAY_TYPE_DPI, - .driver_name = "generic_dpi_panel", + .driver_name = "dvi", .data = &dvi_panel, .phy.dpi.data_lines = 24, }; diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c index 5a886cd2c598..ba1aa07bdb29 100644 --- a/arch/arm/mach-omap2/board-rx51-peripherals.c +++ b/arch/arm/mach-omap2/board-rx51-peripherals.c @@ -900,7 +900,6 @@ static struct twl4030_platform_data rx51_twldata __initdata = { }; static struct tpa6130a2_platform_data rx51_tpa6130a2_data __initdata_or_module = { - .id = TPA6130A2, .power_gpio = 98, }; diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c index a6c473bbb3d6..faa2a8e28de5 100644 --- a/arch/arm/mach-omap2/board-rx51.c +++ b/arch/arm/mach-omap2/board-rx51.c @@ -79,29 +79,6 @@ static struct cpuidle_params rx51_cpuidle_params[] = { {7505 + 15274, 484329, 1}, }; -static struct omap_lcd_config rx51_lcd_config = { - .ctrl_name = "internal", -}; - -static struct omap_fbmem_config rx51_fbmem0_config = { - .size = 752 * 1024, -}; - -static struct omap_fbmem_config rx51_fbmem1_config = { - .size = 752 * 1024, -}; - -static struct omap_fbmem_config rx51_fbmem2_config = { - .size = 752 * 1024, -}; - -static struct omap_board_config_kernel rx51_config[] = { - { OMAP_TAG_FBMEM, &rx51_fbmem0_config }, - { OMAP_TAG_FBMEM, &rx51_fbmem1_config }, - { OMAP_TAG_FBMEM, &rx51_fbmem2_config }, - { OMAP_TAG_LCD, &rx51_lcd_config }, -}; - static void __init rx51_init_early(void) { struct omap_sdrc_params *sdrc_params; @@ -128,8 +105,6 @@ static struct omap_musb_board_data musb_board_data = { static void __init rx51_init(void) { omap3_mux_init(board_mux, OMAP_PACKAGE_CBB); - omap_board_config = rx51_config; - omap_board_config_size = ARRAY_SIZE(rx51_config); omap3_pm_init_cpuidle(rx51_cpuidle_params); omap_serial_init(); usb_musb_init(&musb_board_data); diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c index 5391079c8689..ae8ea5b3b1a0 100644 --- a/arch/arm/mach-omap2/devices.c +++ b/arch/arm/mach-omap2/devices.c @@ -329,6 +329,38 @@ static void omap_init_audio(void) static inline void omap_init_audio(void) {} #endif +#if defined(CONFIG_SND_OMAP_SOC_MCPDM) || \ + defined(CONFIG_SND_OMAP_SOC_MCPDM_MODULE) + +static struct omap_device_pm_latency omap_mcpdm_latency[] = { + { + .deactivate_func = omap_device_idle_hwmods, + .activate_func = omap_device_enable_hwmods, + .flags = OMAP_DEVICE_LATENCY_AUTO_ADJUST, + }, +}; + +static void omap_init_mcpdm(void) +{ + struct omap_hwmod *oh; + struct omap_device *od; + + oh = omap_hwmod_lookup("mcpdm"); + if (!oh) { + printk(KERN_ERR "Could not look up mcpdm hw_mod\n"); + return; + } + + od = omap_device_build("omap-mcpdm", -1, oh, NULL, 0, + omap_mcpdm_latency, + ARRAY_SIZE(omap_mcpdm_latency), 0); + if (IS_ERR(od)) + printk(KERN_ERR "Could not build omap_device for omap-mcpdm-dai\n"); +} +#else +static inline void omap_init_mcpdm(void) {} +#endif + #if defined(CONFIG_SPI_OMAP24XX) || defined(CONFIG_SPI_OMAP24XX_MODULE) #include <plat/mcspi.h> @@ -682,6 +714,7 @@ static int __init omap2_init_devices(void) * in alphabetical order so they're easier to sort through. */ omap_init_audio(); + omap_init_mcpdm(); omap_init_camera(); omap_init_mbox(); omap_init_mcspi(); diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c index a5b7a236aa5b..62510ec863c6 100644 --- a/arch/arm/mach-omap2/display.c +++ b/arch/arm/mach-omap2/display.c @@ -27,6 +27,8 @@ #include <plat/omap_device.h> #include <plat/omap-pm.h> +#include "control.h" + static struct platform_device omap_display_device = { .name = "omapdss", .id = -1, @@ -61,7 +63,7 @@ static const struct omap_dss_hwmod_data omap3_dss_hwmod_data[] __initdata = { { "dss_dispc", "omapdss_dispc", -1 }, { "dss_rfbi", "omapdss_rfbi", -1 }, { "dss_venc", "omapdss_venc", -1 }, - { "dss_dsi1", "omapdss_dsi1", -1 }, + { "dss_dsi1", "omapdss_dsi", 0 }, }; static const struct omap_dss_hwmod_data omap4_dss_hwmod_data[] __initdata = { @@ -69,11 +71,58 @@ static const struct omap_dss_hwmod_data omap4_dss_hwmod_data[] __initdata = { { "dss_dispc", "omapdss_dispc", -1 }, { "dss_rfbi", "omapdss_rfbi", -1 }, { "dss_venc", "omapdss_venc", -1 }, - { "dss_dsi1", "omapdss_dsi1", -1 }, - { "dss_dsi2", "omapdss_dsi2", -1 }, + { "dss_dsi1", "omapdss_dsi", 0 }, + { "dss_dsi2", "omapdss_dsi", 1 }, { "dss_hdmi", "omapdss_hdmi", -1 }, }; +static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes) +{ + u32 enable_mask, enable_shift; + u32 pipd_mask, pipd_shift; + u32 reg; + + if (dsi_id == 0) { + enable_mask = OMAP4_DSI1_LANEENABLE_MASK; + enable_shift = OMAP4_DSI1_LANEENABLE_SHIFT; + pipd_mask = OMAP4_DSI1_PIPD_MASK; + pipd_shift = OMAP4_DSI1_PIPD_SHIFT; + } else if (dsi_id == 1) { + enable_mask = OMAP4_DSI2_LANEENABLE_MASK; + enable_shift = OMAP4_DSI2_LANEENABLE_SHIFT; + pipd_mask = OMAP4_DSI2_PIPD_MASK; + pipd_shift = OMAP4_DSI2_PIPD_SHIFT; + } else { + return -ENODEV; + } + + reg = omap4_ctrl_pad_readl(OMAP4_CTRL_MODULE_PAD_CORE_CONTROL_DSIPHY); + + reg &= ~enable_mask; + reg &= ~pipd_mask; + + reg |= (lanes << enable_shift) & enable_mask; + reg |= (lanes << pipd_shift) & pipd_mask; + + omap4_ctrl_pad_writel(reg, OMAP4_CTRL_MODULE_PAD_CORE_CONTROL_DSIPHY); + + return 0; +} + +static int omap_dsi_enable_pads(int dsi_id, unsigned lane_mask) +{ + if (cpu_is_omap44xx()) + return omap4_dsi_mux_pads(dsi_id, lane_mask); + + return 0; +} + +static void omap_dsi_disable_pads(int dsi_id, unsigned lane_mask) +{ + if (cpu_is_omap44xx()) + omap4_dsi_mux_pads(dsi_id, 0); +} + int __init omap_display_init(struct omap_dss_board_info *board_data) { int r = 0; @@ -96,6 +145,11 @@ int __init omap_display_init(struct omap_dss_board_info *board_data) oh_count = ARRAY_SIZE(omap4_dss_hwmod_data); } + if (board_data->dsi_enable_pads == NULL) + board_data->dsi_enable_pads = omap_dsi_enable_pads; + if (board_data->dsi_disable_pads == NULL) + board_data->dsi_disable_pads = omap_dsi_disable_pads; + pdata.board_data = board_data; pdata.board_data->get_context_loss_count = omap_pm_get_dev_context_loss_count; diff --git a/arch/arm/mach-omap2/include/mach/entry-macro.S b/arch/arm/mach-omap2/include/mach/entry-macro.S index ceb8b7e593d7..feb90a10945a 100644 --- a/arch/arm/mach-omap2/include/mach/entry-macro.S +++ b/arch/arm/mach-omap2/include/mach/entry-macro.S @@ -78,7 +78,7 @@ 4401: ldr \irqstat, [\base, #GIC_CPU_INTACK] ldr \tmp, =1021 bic \irqnr, \irqstat, #0x1c00 - cmp \irqnr, #29 + cmp \irqnr, #15 cmpcc \irqnr, \irqnr cmpne \irqnr, \tmp cmpcs \irqnr, \irqnr @@ -101,18 +101,6 @@ it cs cmpcs \irqnr, \irqnr .endm - - /* As above, this assumes that irqstat and base are preserved */ - - .macro test_for_ltirq, irqnr, irqstat, base, tmp - bic \irqnr, \irqstat, #0x1c00 - mov \tmp, #0 - cmp \irqnr, #29 - itt eq - moveq \tmp, #1 - streq \irqstat, [\base, #GIC_CPU_EOI] - cmp \tmp, #0 - .endm #endif /* CONFIG_SMP */ #else /* MULTI_OMAP2 */ diff --git a/arch/arm/mach-omap2/iommu2.c b/arch/arm/mach-omap2/iommu2.c index f286012783c6..eefc37912ef3 100644 --- a/arch/arm/mach-omap2/iommu2.c +++ b/arch/arm/mach-omap2/iommu2.c @@ -66,7 +66,7 @@ ((pgsz) == MMU_CAM_PGSZ_4K) ? 0xfffff000 : 0) -static void __iommu_set_twl(struct iommu *obj, bool on) +static void __iommu_set_twl(struct omap_iommu *obj, bool on) { u32 l = iommu_read_reg(obj, MMU_CNTL); @@ -85,7 +85,7 @@ static void __iommu_set_twl(struct iommu *obj, bool on) } -static int omap2_iommu_enable(struct iommu *obj) +static int omap2_iommu_enable(struct omap_iommu *obj) { u32 l, pa; unsigned long timeout; @@ -127,7 +127,7 @@ static int omap2_iommu_enable(struct iommu *obj) return 0; } -static void omap2_iommu_disable(struct iommu *obj) +static void omap2_iommu_disable(struct omap_iommu *obj) { u32 l = iommu_read_reg(obj, MMU_CNTL); @@ -138,12 +138,12 @@ static void omap2_iommu_disable(struct iommu *obj) dev_dbg(obj->dev, "%s is shutting down\n", obj->name); } -static void omap2_iommu_set_twl(struct iommu *obj, bool on) +static void omap2_iommu_set_twl(struct omap_iommu *obj, bool on) { __iommu_set_twl(obj, false); } -static u32 omap2_iommu_fault_isr(struct iommu *obj, u32 *ra) +static u32 omap2_iommu_fault_isr(struct omap_iommu *obj, u32 *ra) { u32 stat, da; u32 errs = 0; @@ -173,13 +173,13 @@ static u32 omap2_iommu_fault_isr(struct iommu *obj, u32 *ra) return errs; } -static void omap2_tlb_read_cr(struct iommu *obj, struct cr_regs *cr) +static void omap2_tlb_read_cr(struct omap_iommu *obj, struct cr_regs *cr) { cr->cam = iommu_read_reg(obj, MMU_READ_CAM); cr->ram = iommu_read_reg(obj, MMU_READ_RAM); } -static void omap2_tlb_load_cr(struct iommu *obj, struct cr_regs *cr) +static void omap2_tlb_load_cr(struct omap_iommu *obj, struct cr_regs *cr) { iommu_write_reg(obj, cr->cam | MMU_CAM_V, MMU_CAM); iommu_write_reg(obj, cr->ram, MMU_RAM); @@ -193,7 +193,8 @@ static u32 omap2_cr_to_virt(struct cr_regs *cr) return cr->cam & mask; } -static struct cr_regs *omap2_alloc_cr(struct iommu *obj, struct iotlb_entry *e) +static struct cr_regs *omap2_alloc_cr(struct omap_iommu *obj, + struct iotlb_entry *e) { struct cr_regs *cr; @@ -230,7 +231,8 @@ static u32 omap2_get_pte_attr(struct iotlb_entry *e) return attr; } -static ssize_t omap2_dump_cr(struct iommu *obj, struct cr_regs *cr, char *buf) +static ssize_t +omap2_dump_cr(struct omap_iommu *obj, struct cr_regs *cr, char *buf) { char *p = buf; @@ -254,7 +256,8 @@ static ssize_t omap2_dump_cr(struct iommu *obj, struct cr_regs *cr, char *buf) goto out; \ } while (0) -static ssize_t omap2_iommu_dump_ctx(struct iommu *obj, char *buf, ssize_t len) +static ssize_t +omap2_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t len) { char *p = buf; @@ -280,7 +283,7 @@ out: return p - buf; } -static void omap2_iommu_save_ctx(struct iommu *obj) +static void omap2_iommu_save_ctx(struct omap_iommu *obj) { int i; u32 *p = obj->ctx; @@ -293,7 +296,7 @@ static void omap2_iommu_save_ctx(struct iommu *obj) BUG_ON(p[0] != IOMMU_ARCH_VERSION); } -static void omap2_iommu_restore_ctx(struct iommu *obj) +static void omap2_iommu_restore_ctx(struct omap_iommu *obj) { int i; u32 *p = obj->ctx; @@ -343,13 +346,13 @@ static const struct iommu_functions omap2_iommu_ops = { static int __init omap2_iommu_init(void) { - return install_iommu_arch(&omap2_iommu_ops); + return omap_install_iommu_arch(&omap2_iommu_ops); } module_init(omap2_iommu_init); static void __exit omap2_iommu_exit(void) { - uninstall_iommu_arch(&omap2_iommu_ops); + omap_uninstall_iommu_arch(&omap2_iommu_ops); } module_exit(omap2_iommu_exit); diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index ce65e9329c7b..889464dc7b2d 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -109,12 +109,10 @@ void __init smp_init_cpus(void) ncores = scu_get_core_count(scu_base); /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "OMAP4: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c index 6201422c0606..79325c65c23c 100644 --- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c @@ -5430,7 +5430,7 @@ static __initdata struct omap_hwmod *omap44xx_hwmods[] = { &omap44xx_mcbsp4_hwmod, /* mcpdm class */ -/* &omap44xx_mcpdm_hwmod, */ + &omap44xx_mcpdm_hwmod, /* mcspi class */ &omap44xx_mcspi1_hwmod, diff --git a/arch/arm/mach-omap2/smartreflex.c b/arch/arm/mach-omap2/smartreflex.c index 34c01a7de810..f49804f181d4 100644 --- a/arch/arm/mach-omap2/smartreflex.c +++ b/arch/arm/mach-omap2/smartreflex.c @@ -247,7 +247,7 @@ static void sr_stop_vddautocomp(struct omap_sr *sr) * driver register and sr device intializtion API's. Only one call * will ultimately succeed. * - * Currently this function registers interrrupt handler for a particular SR + * Currently this function registers interrupt handler for a particular SR * if smartreflex class driver is already registered and has * requested for interrupts and the SR interrupt line in present. */ diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c index daa056ed8738..522435772168 100644 --- a/arch/arm/mach-omap2/twl-common.c +++ b/arch/arm/mach-omap2/twl-common.c @@ -99,7 +99,7 @@ static struct regulator_init_data omap3_vdac_idata = { static struct regulator_consumer_supply omap3_vpll2_supplies[] = { REGULATOR_SUPPLY("vdds_dsi", "omapdss"), - REGULATOR_SUPPLY("vdds_dsi", "omapdss_dsi1"), + REGULATOR_SUPPLY("vdds_dsi", "omapdss_dsi.0"), }; static struct regulator_init_data omap3_vpll2_idata = { @@ -235,6 +235,12 @@ static struct regulator_init_data omap4_vana_idata = { }, }; +static struct regulator_consumer_supply omap4_vcxio_supply[] = { + REGULATOR_SUPPLY("vdds_dsi", "omapdss_dss"), + REGULATOR_SUPPLY("vdds_dsi", "omapdss_dsi.0"), + REGULATOR_SUPPLY("vdds_dsi", "omapdss_dsi.1"), +}; + static struct regulator_init_data omap4_vcxio_idata = { .constraints = { .min_uV = 1800000, @@ -243,7 +249,10 @@ static struct regulator_init_data omap4_vcxio_idata = { | REGULATOR_MODE_STANDBY, .valid_ops_mask = REGULATOR_CHANGE_MODE | REGULATOR_CHANGE_STATUS, + .always_on = true, }, + .num_consumer_supplies = ARRAY_SIZE(omap4_vcxio_supply), + .consumer_supplies = omap4_vcxio_supply, }; static struct regulator_init_data omap4_vusb_idata = { diff --git a/arch/arm/mach-orion5x/Makefile.boot b/arch/arm/mach-orion5x/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-orion5x/Makefile.boot +++ b/arch/arm/mach-orion5x/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c index 0ab531d047fc..22ace0bf2f92 100644 --- a/arch/arm/mach-orion5x/common.c +++ b/arch/arm/mach-orion5x/common.c @@ -308,8 +308,8 @@ void __init orion5x_init(void) * Many orion-based systems have buggy bootloader implementations. * This is a common fixup for bogus memory tags. */ -void __init tag_fixup_mem32(struct machine_desc *mdesc, struct tag *t, - char **from, struct meminfo *meminfo) +void __init tag_fixup_mem32(struct tag *t, char **from, + struct meminfo *meminfo) { for (; t->hdr.size; t = tag_next(t)) if (t->hdr.tag == ATAG_MEM && diff --git a/arch/arm/mach-orion5x/common.h b/arch/arm/mach-orion5x/common.h index 3e5499dda49a..909489f4d23e 100644 --- a/arch/arm/mach-orion5x/common.h +++ b/arch/arm/mach-orion5x/common.h @@ -53,11 +53,9 @@ int orion5x_pci_sys_setup(int nr, struct pci_sys_data *sys); struct pci_bus *orion5x_pci_sys_scan_bus(int nr, struct pci_sys_data *sys); int orion5x_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin); -struct machine_desc; struct meminfo; struct tag; -extern void __init tag_fixup_mem32(struct machine_desc *, struct tag *, - char **, struct meminfo *); +extern void __init tag_fixup_mem32(struct tag *, char **, struct meminfo *); #endif diff --git a/arch/arm/mach-pnx4008/Makefile.boot b/arch/arm/mach-pnx4008/Makefile.boot index 44c7117e20dd..9fa19baa7f2e 100644 --- a/arch/arm/mach-pnx4008/Makefile.boot +++ b/arch/arm/mach-pnx4008/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x80008000 + zreladdr-y += 0x80008000 params_phys-y := 0x80000100 initrd_phys-y := 0x80800000 diff --git a/arch/arm/mach-prima2/Makefile.boot b/arch/arm/mach-prima2/Makefile.boot index d023db3ae4ff..c77a4883a4ee 100644 --- a/arch/arm/mach-prima2/Makefile.boot +++ b/arch/arm/mach-prima2/Makefile.boot @@ -1,3 +1,3 @@ -zreladdr-y := 0x00008000 +zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-pxa/Makefile.boot b/arch/arm/mach-pxa/Makefile.boot index 1ead67178eca..2c1ae92f2106 100644 --- a/arch/arm/mach-pxa/Makefile.boot +++ b/arch/arm/mach-pxa/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0xa0008000 + zreladdr-y += 0xa0008000 diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c index e40dc47cf2f1..3a7387f93c38 100644 --- a/arch/arm/mach-pxa/cm-x300.c +++ b/arch/arm/mach-pxa/cm-x300.c @@ -837,8 +837,8 @@ static void __init cm_x300_init(void) cm_x300_init_bl(); } -static void __init cm_x300_fixup(struct machine_desc *mdesc, struct tag *tags, - char **cmdline, struct meminfo *mi) +static void __init cm_x300_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { /* Make sure that mi->bank[0].start = PHYS_ADDR */ for (; tags->hdr.size; tags = tag_next(tags)) diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c index 185a37cad254..3e9483b06053 100644 --- a/arch/arm/mach-pxa/corgi.c +++ b/arch/arm/mach-pxa/corgi.c @@ -705,8 +705,8 @@ static void __init corgi_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init fixup_corgi(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init fixup_corgi(struct tag *tags, char **cmdline, + struct meminfo *mi) { sharpsl_save_param(); mi->nr_banks=1; diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c index e823c54057f3..8e697dd8accd 100644 --- a/arch/arm/mach-pxa/eseries.c +++ b/arch/arm/mach-pxa/eseries.c @@ -41,8 +41,7 @@ #include "clock.h" /* Only e800 has 128MB RAM */ -void __init eseries_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +void __init eseries_fixup(struct tag *tags, char **cmdline, struct meminfo *mi) { mi->nr_banks=1; mi->bank[0].start = 0xa0000000; diff --git a/arch/arm/mach-pxa/eseries.h b/arch/arm/mach-pxa/eseries.h index 5930f5e2a123..be921965e91a 100644 --- a/arch/arm/mach-pxa/eseries.h +++ b/arch/arm/mach-pxa/eseries.h @@ -1,5 +1,4 @@ -void __init eseries_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi); +void __init eseries_fixup(struct tag *tags, char **cmdline, struct meminfo *mi); extern struct pxa2xx_udc_mach_info e7xx_udc_mach_info; extern struct pxaficp_platform_data e7xx_ficp_platform_data; diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c index 25f29adf5114..532c5d3a97d2 100644 --- a/arch/arm/mach-pxa/irq.c +++ b/arch/arm/mach-pxa/irq.c @@ -18,6 +18,8 @@ #include <linux/io.h> #include <linux/irq.h> +#include <asm/exception.h> + #include <mach/hardware.h> #include <mach/irqs.h> #include <mach/gpio-pxa.h> diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c index a113ea9ab4ab..948ce3e729fa 100644 --- a/arch/arm/mach-pxa/poodle.c +++ b/arch/arm/mach-pxa/poodle.c @@ -454,8 +454,8 @@ static void __init poodle_init(void) poodle_init_spi(); } -static void __init fixup_poodle(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init fixup_poodle(struct tag *tags, char **cmdline, + struct meminfo *mi) { sharpsl_save_param(); mi->nr_banks=1; diff --git a/arch/arm/mach-pxa/saar.c b/arch/arm/mach-pxa/saar.c index 602d70b50f81..fc2c1e05af9c 100644 --- a/arch/arm/mach-pxa/saar.c +++ b/arch/arm/mach-pxa/saar.c @@ -540,7 +540,7 @@ static struct mtd_partition saar_onenand_partitions[] = { }, { .name = "filesystem", .offset = MTDPART_OFS_APPEND, - .size = SZ_48M, + .size = SZ_32M + SZ_16M, .mask_flags = 0, } }; diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 438c7b5e451f..d8dec9113aad 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -970,8 +970,8 @@ static void __init spitz_init(void) spitz_i2c_init(); } -static void __init spitz_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init spitz_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { sharpsl_save_param(); mi->nr_banks = 1; diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c index 9f69a2682693..402b0c96613b 100644 --- a/arch/arm/mach-pxa/tosa.c +++ b/arch/arm/mach-pxa/tosa.c @@ -960,8 +960,8 @@ static void __init tosa_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); } -static void __init fixup_tosa(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init fixup_tosa(struct tag *tags, char **cmdline, + struct meminfo *mi) { sharpsl_save_param(); mi->nr_banks=1; diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c index 54930cccbe54..70e1730ef282 100644 --- a/arch/arm/mach-pxa/xcep.c +++ b/arch/arm/mach-pxa/xcep.c @@ -142,8 +142,7 @@ static struct platform_device *devices[] __initdata = { /* We have to state that there are HWMON devices on the I2C bus on XCEP. * Drivers for HWMON verify capabilities of the adapter when loading and - * refuse to attach if the adapter doesn't support HWMON class of devices. - * See also Documentation/i2c/porting-clients. */ + * refuse to attach if the adapter doesn't support HWMON class of devices. */ static struct i2c_pxa_platform_data xcep_i2c_platform_data = { .class = I2C_CLASS_HWMON }; diff --git a/arch/arm/mach-realview/Makefile.boot b/arch/arm/mach-realview/Makefile.boot index d97e003d3df4..d2c3d788f688 100644 --- a/arch/arm/mach-realview/Makefile.boot +++ b/arch/arm/mach-realview/Makefile.boot @@ -1,9 +1,9 @@ ifeq ($(CONFIG_REALVIEW_HIGH_PHYS_OFFSET),y) - zreladdr-y := 0x70008000 + zreladdr-y += 0x70008000 params_phys-y := 0x70000100 initrd_phys-y := 0x70800000 else - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 endif diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c index 5c23450d2d1d..d5ed5d4f77d6 100644 --- a/arch/arm/mach-realview/core.c +++ b/arch/arm/mach-realview/core.c @@ -517,8 +517,7 @@ void __init realview_timer_init(unsigned int timer_irq) /* * Setup the memory banks. */ -void realview_fixup(struct machine_desc *mdesc, struct tag *tags, char **from, - struct meminfo *meminfo) +void realview_fixup(struct tag *tags, char **from, struct meminfo *meminfo) { /* * Most RealView platforms have 512MB contiguous RAM at 0x70000000. diff --git a/arch/arm/mach-realview/core.h b/arch/arm/mach-realview/core.h index 5c83d1e87a03..47259c89a75e 100644 --- a/arch/arm/mach-realview/core.h +++ b/arch/arm/mach-realview/core.h @@ -63,8 +63,8 @@ extern int realview_flash_register(struct resource *res, u32 num); extern int realview_eth_register(const char *name, struct resource *res); extern int realview_usb_register(struct resource *res); extern void realview_init_early(void); -extern void realview_fixup(struct machine_desc *mdesc, struct tag *tags, - char **from, struct meminfo *meminfo); +extern void realview_fixup(struct tag *tags, char **from, + struct meminfo *meminfo); extern void (*realview_reset)(char); #endif diff --git a/arch/arm/mach-realview/include/mach/board-pb1176.h b/arch/arm/mach-realview/include/mach/board-pb1176.h index 002ab5d8c11c..2a15fef94730 100644 --- a/arch/arm/mach-realview/include/mach/board-pb1176.h +++ b/arch/arm/mach-realview/include/mach/board-pb1176.h @@ -70,6 +70,7 @@ #define REALVIEW_DC1176_GIC_CPU_BASE 0x10120000 /* GIC CPU interface, on devchip */ #define REALVIEW_DC1176_GIC_DIST_BASE 0x10121000 /* GIC distributor, on devchip */ +#define REALVIEW_DC1176_ROM_BASE 0x10200000 /* 16KiB NRAM preudo-ROM, on devchip */ #define REALVIEW_PB1176_GIC_CPU_BASE 0x10040000 /* GIC CPU interface, on FPGA */ #define REALVIEW_PB1176_GIC_DIST_BASE 0x10041000 /* GIC distributor, on FPGA */ #define REALVIEW_PB1176_L220_BASE 0x10110000 /* L220 registers */ diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c index 4ae943bafa92..e83c654a58d0 100644 --- a/arch/arm/mach-realview/platsmp.c +++ b/arch/arm/mach-realview/platsmp.c @@ -52,12 +52,10 @@ void __init smp_init_cpus(void) ncores = scu_base ? scu_get_core_count(scu_base) : 1; /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "Realview: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-realview/realview_pb1176.c b/arch/arm/mach-realview/realview_pb1176.c index 7263dea77779..c057540ec776 100644 --- a/arch/arm/mach-realview/realview_pb1176.c +++ b/arch/arm/mach-realview/realview_pb1176.c @@ -26,6 +26,8 @@ #include <linux/amba/pl061.h> #include <linux/amba/mmci.h> #include <linux/amba/pl022.h> +#include <linux/mtd/physmap.h> +#include <linux/mtd/partitions.h> #include <linux/io.h> #include <mach/hardware.h> @@ -204,22 +206,48 @@ static struct amba_device *amba_devs[] __initdata = { * RealView PB1176 platform devices */ static struct resource realview_pb1176_flash_resources[] = { - [0] = { + { .start = REALVIEW_PB1176_FLASH_BASE, .end = REALVIEW_PB1176_FLASH_BASE + REALVIEW_PB1176_FLASH_SIZE - 1, .flags = IORESOURCE_MEM, }, - [1] = { +#ifdef CONFIG_REALVIEW_PB1176_SECURE_FLASH + { .start = REALVIEW_PB1176_SEC_FLASH_BASE, .end = REALVIEW_PB1176_SEC_FLASH_BASE + REALVIEW_PB1176_SEC_FLASH_SIZE - 1, .flags = IORESOURCE_MEM, }, -}; -#ifdef CONFIG_REALVIEW_PB1176_SECURE_FLASH -#define PB1176_FLASH_BLOCKS 2 -#else -#define PB1176_FLASH_BLOCKS 1 #endif +}; + +static struct physmap_flash_data pb1176_rom_pdata = { + .probe_type = "map_rom", + .width = 4, + .nr_parts = 0, +}; + +static struct resource pb1176_rom_resources[] = { + /* + * This exposes the PB1176 DevChip ROM as an MTD ROM mapping. + * The reference manual states that this is actually a pseudo-ROM + * programmed in NVRAM. + */ + { + .start = REALVIEW_DC1176_ROM_BASE, + .end = REALVIEW_DC1176_ROM_BASE + SZ_16K - 1, + .flags = IORESOURCE_MEM, + } +}; + +static struct platform_device pb1176_rom_device = { + .name = "physmap-flash", + .id = -1, + .num_resources = ARRAY_SIZE(pb1176_rom_resources), + .resource = pb1176_rom_resources, + .dev = { + .platform_data = &pb1176_rom_pdata, + }, +}; static struct resource realview_pb1176_smsc911x_resources[] = { [0] = { @@ -316,8 +344,7 @@ static void realview_pb1176_reset(char mode) __raw_writel(REALVIEW_PB1176_SYS_SOFT_RESET, reset_ctrl); } -static void realview_pb1176_fixup(struct machine_desc *mdesc, - struct tag *tags, char **from, +static void realview_pb1176_fixup(struct tag *tags, char **from, struct meminfo *meminfo) { /* @@ -338,7 +365,8 @@ static void __init realview_pb1176_init(void) #endif realview_flash_register(realview_pb1176_flash_resources, - PB1176_FLASH_BLOCKS); + ARRAY_SIZE(realview_pb1176_flash_resources)); + platform_device_register(&pb1176_rom_device); realview_eth_register(NULL, realview_pb1176_smsc911x_resources); platform_device_register(&realview_i2c_device); realview_usb_register(realview_pb1176_isp1761_resources); diff --git a/arch/arm/mach-realview/realview_pbx.c b/arch/arm/mach-realview/realview_pbx.c index 8ec7e52618b4..63c4114afae9 100644 --- a/arch/arm/mach-realview/realview_pbx.c +++ b/arch/arm/mach-realview/realview_pbx.c @@ -319,8 +319,8 @@ static struct sys_timer realview_pbx_timer = { .init = realview_pbx_timer_init, }; -static void realview_pbx_fixup(struct machine_desc *mdesc, struct tag *tags, - char **from, struct meminfo *meminfo) +static void realview_pbx_fixup(struct tag *tags, char **from, + struct meminfo *meminfo) { #ifdef CONFIG_SPARSEMEM /* @@ -335,7 +335,7 @@ static void realview_pbx_fixup(struct machine_desc *mdesc, struct tag *tags, meminfo->bank[2].size = SZ_256M; meminfo->nr_banks = 3; #else - realview_fixup(mdesc, tags, from, meminfo); + realview_fixup(tags, from, meminfo); #endif } diff --git a/arch/arm/mach-rpc/Makefile.boot b/arch/arm/mach-rpc/Makefile.boot index 9c9e7685ec7c..ae2df0d7d037 100644 --- a/arch/arm/mach-rpc/Makefile.boot +++ b/arch/arm/mach-rpc/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x10008000 + zreladdr-y += 0x10008000 params_phys-y := 0x10000100 initrd_phys-y := 0x18000000 diff --git a/arch/arm/mach-rpc/include/mach/hardware.h b/arch/arm/mach-rpc/include/mach/hardware.h index dde6b3c0e299..050d63c74cc1 100644 --- a/arch/arm/mach-rpc/include/mach/hardware.h +++ b/arch/arm/mach-rpc/include/mach/hardware.h @@ -36,7 +36,7 @@ #define EASI_SIZE 0x08000000 /* EASI I/O */ #define EASI_START 0x08000000 -#define EASI_BASE 0xe5000000 +#define EASI_BASE IOMEM(0xe5000000) #define IO_START 0x03000000 /* I/O */ #define IO_SIZE 0x01000000 @@ -51,21 +51,20 @@ /* * IO Addresses */ -#define VIDC_BASE IOMEM(0xe0400000) -#define EXPMASK_BASE 0xe0360000 -#define IOMD_BASE IOMEM(0xe0200000) -#define IOC_BASE IOMEM(0xe0200000) -#define PCIO_BASE IOMEM(0xe0010000) -#define FLOPPYDMA_BASE IOMEM(0xe002a000) +#define ECARD_EASI_BASE (EASI_BASE) +#define VIDC_BASE (IO_BASE + 0x00400000) +#define EXPMASK_BASE (IO_BASE + 0x00360000) +#define ECARD_IOC4_BASE (IO_BASE + 0x00270000) +#define ECARD_IOC_BASE (IO_BASE + 0x00240000) +#define IOMD_BASE (IO_BASE + 0x00200000) +#define IOC_BASE (IO_BASE + 0x00200000) +#define ECARD_MEMC8_BASE (IO_BASE + 0x0002b000) +#define FLOPPYDMA_BASE (IO_BASE + 0x0002a000) +#define PCIO_BASE (IO_BASE + 0x00010000) +#define ECARD_MEMC_BASE (IO_BASE + 0x00000000) #define vidc_writel(val) __raw_writel(val, VIDC_BASE) -#define IO_EC_EASI_BASE 0x81400000 -#define IO_EC_IOC4_BASE 0x8009c000 -#define IO_EC_IOC_BASE 0x80090000 -#define IO_EC_MEMC8_BASE 0x8000ac00 -#define IO_EC_MEMC_BASE 0x80000000 - #define NETSLOT_BASE 0x0302b000 #define NETSLOT_SIZE 0x00001000 diff --git a/arch/arm/mach-rpc/include/mach/io.h b/arch/arm/mach-rpc/include/mach/io.h index 20da7f486e51..695f4ed2e11b 100644 --- a/arch/arm/mach-rpc/include/mach/io.h +++ b/arch/arm/mach-rpc/include/mach/io.h @@ -15,195 +15,18 @@ #include <mach/hardware.h> -#define IO_SPACE_LIMIT 0xffffffff +#define IO_SPACE_LIMIT 0xffff /* - * We use two different types of addressing - PC style addresses, and ARM - * addresses. PC style accesses the PC hardware with the normal PC IO - * addresses, eg 0x3f8 for serial#1. ARM addresses are 0x80000000+ - * and are translated to the start of IO. Note that all addresses are - * shifted left! - */ -#define __PORT_PCIO(x) (!((x) & 0x80000000)) - -/* - * Dynamic IO functions. - */ -static inline void __outb (unsigned int value, unsigned int port) -{ - unsigned long temp; - __asm__ __volatile__( - "tst %2, #0x80000000\n\t" - "mov %0, %4\n\t" - "addeq %0, %0, %3\n\t" - "strb %1, [%0, %2, lsl #2] @ outb" - : "=&r" (temp) - : "r" (value), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE) - : "cc"); -} - -static inline void __outw (unsigned int value, unsigned int port) -{ - unsigned long temp; - __asm__ __volatile__( - "tst %2, #0x80000000\n\t" - "mov %0, %4\n\t" - "addeq %0, %0, %3\n\t" - "str %1, [%0, %2, lsl #2] @ outw" - : "=&r" (temp) - : "r" (value|value<<16), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE) - : "cc"); -} - -static inline void __outl (unsigned int value, unsigned int port) -{ - unsigned long temp; - __asm__ __volatile__( - "tst %2, #0x80000000\n\t" - "mov %0, %4\n\t" - "addeq %0, %0, %3\n\t" - "str %1, [%0, %2, lsl #2] @ outl" - : "=&r" (temp) - : "r" (value), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE) - : "cc"); -} - -#define DECLARE_DYN_IN(sz,fnsuffix,instr) \ -static inline unsigned sz __in##fnsuffix (unsigned int port) \ -{ \ - unsigned long temp, value; \ - __asm__ __volatile__( \ - "tst %2, #0x80000000\n\t" \ - "mov %0, %4\n\t" \ - "addeq %0, %0, %3\n\t" \ - "ldr" instr " %1, [%0, %2, lsl #2] @ in" #fnsuffix \ - : "=&r" (temp), "=r" (value) \ - : "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE) \ - : "cc"); \ - return (unsigned sz)value; \ -} - -static inline void __iomem *__deprecated __ioaddr(unsigned int port) -{ - void __iomem *ret; - if (__PORT_PCIO(port)) - ret = PCIO_BASE; - else - ret = IO_BASE; - return ret + (port << 2); -} - -#define DECLARE_IO(sz,fnsuffix,instr) \ - DECLARE_DYN_IN(sz,fnsuffix,instr) - -DECLARE_IO(char,b,"b") -DECLARE_IO(short,w,"") -DECLARE_IO(int,l,"") - -#undef DECLARE_IO -#undef DECLARE_DYN_IN - -/* - * Constant address IO functions + * We need PC style IO addressing for: + * - floppy (at 0x3f2,0x3f4,0x3f5,0x3f7) + * - parport (at 0x278-0x27a, 0x27b-0x27f, 0x778-0x77a) + * - 8250 serial (only for compile) * - * These have to be macros for the 'J' constraint to work - - * +/-4096 immediate operand. + * These peripherals are found in an area of MMIO which looks very much + * like an ISA bus, but with registers at the low byte of each word. */ -#define __outbc(value,port) \ -({ \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "strb %0, [%1, %2] @ outbc" \ - : : "r" (value), "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "strb %0, [%1, %2] @ outbc" \ - : : "r" (value), "r" (IO_BASE), "r" ((port) << 2)); \ -}) - -#define __inbc(port) \ -({ \ - unsigned char result; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "ldrb %0, [%1, %2] @ inbc" \ - : "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "ldrb %0, [%1, %2] @ inbc" \ - : "=r" (result) : "r" (IO_BASE), "r" ((port) << 2)); \ - result; \ -}) - -#define __outwc(value,port) \ -({ \ - unsigned long __v = value; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "str %0, [%1, %2] @ outwc" \ - : : "r" (__v|__v<<16), "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "str %0, [%1, %2] @ outwc" \ - : : "r" (__v|__v<<16), "r" (IO_BASE), "r" ((port) << 2)); \ -}) - -#define __inwc(port) \ -({ \ - unsigned short result; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "ldr %0, [%1, %2] @ inwc" \ - : "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "ldr %0, [%1, %2] @ inwc" \ - : "=r" (result) : "r" (IO_BASE), "r" ((port) << 2)); \ - result & 0xffff; \ -}) - -#define __outlc(value,port) \ -({ \ - unsigned long __v = value; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "str %0, [%1, %2] @ outlc" \ - : : "r" (__v), "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "str %0, [%1, %2] @ outlc" \ - : : "r" (__v), "r" (IO_BASE), "r" ((port) << 2)); \ -}) - -#define __inlc(port) \ -({ \ - unsigned long result; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "ldr %0, [%1, %2] @ inlc" \ - : "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2)); \ - else \ - __asm__ __volatile__( \ - "ldr %0, [%1, %2] @ inlc" \ - : "=r" (result) : "r" (IO_BASE), "r" ((port) << 2)); \ - result; \ -}) - -#define inb(p) (__builtin_constant_p((p)) ? __inbc(p) : __inb(p)) -#define inw(p) (__builtin_constant_p((p)) ? __inwc(p) : __inw(p)) -#define inl(p) (__builtin_constant_p((p)) ? __inlc(p) : __inl(p)) -#define outb(v,p) (__builtin_constant_p((p)) ? __outbc(v,p) : __outb(v,p)) -#define outw(v,p) (__builtin_constant_p((p)) ? __outwc(v,p) : __outw(v,p)) -#define outl(v,p) (__builtin_constant_p((p)) ? __outlc(v,p) : __outl(v,p)) - -/* the following macro is deprecated */ -#define ioaddr(port) ((unsigned long)__ioaddr((port))) - -#define insb(p,d,l) __raw_readsb(__ioaddr(p),d,l) -#define insw(p,d,l) __raw_readsw(__ioaddr(p),d,l) - -#define outsb(p,d,l) __raw_writesb(__ioaddr(p),d,l) -#define outsw(p,d,l) __raw_writesw(__ioaddr(p),d,l) +#define __io(a) (PCIO_BASE + ((a) << 2)) /* * 1:1 mapping for ioremapped regions. diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c index a9241eb87724..8559598ab767 100644 --- a/arch/arm/mach-rpc/riscpc.c +++ b/arch/arm/mach-rpc/riscpc.c @@ -74,7 +74,7 @@ static struct map_desc rpc_io_desc[] __initdata = { .length = IO_SIZE , .type = MT_DEVICE }, { /* EASI space */ - .virtual = EASI_BASE, + .virtual = (unsigned long)EASI_BASE, .pfn = __phys_to_pfn(EASI_START), .length = EASI_SIZE, .type = MT_DEVICE diff --git a/arch/arm/mach-s3c2410/Makefile.boot b/arch/arm/mach-s3c2410/Makefile.boot index 58c1dd7f8e1d..4457605ba04a 100644 --- a/arch/arm/mach-s3c2410/Makefile.boot +++ b/arch/arm/mach-s3c2410/Makefile.boot @@ -1,7 +1,7 @@ ifeq ($(CONFIG_PM_H1940),y) - zreladdr-y := 0x30108000 + zreladdr-y += 0x30108000 params_phys-y := 0x30100100 else - zreladdr-y := 0x30008000 + zreladdr-y += 0x30008000 params_phys-y := 0x30000100 endif diff --git a/arch/arm/mach-s3c2410/include/mach/io.h b/arch/arm/mach-s3c2410/include/mach/io.h index 9813dbf2ae4f..118749f37c4c 100644 --- a/arch/arm/mach-s3c2410/include/mach/io.h +++ b/arch/arm/mach-s3c2410/include/mach/io.h @@ -199,8 +199,6 @@ DECLARE_IO(int,l,"") #define outw(v,p) (__builtin_constant_p((p)) ? __outwc(v,p) : __outw(v,p)) #define outl(v,p) (__builtin_constant_p((p)) ? __outlc(v,p) : __outl(v,p)) #define __ioaddr(p) (__builtin_constant_p((p)) ? __ioaddr(p) : __ioaddrc(p)) -/* the following macro is deprecated */ -#define ioaddr(port) __ioaddr((port)) #define insb(p,d,l) __raw_readsb(__ioaddr(p),d,l) #define insw(p,d,l) __raw_readsw(__ioaddr(p),d,l) diff --git a/arch/arm/mach-s3c2410/s3c2410.c b/arch/arm/mach-s3c2410/s3c2410.c index f1d3bd8f6f17..343a540d86a9 100644 --- a/arch/arm/mach-s3c2410/s3c2410.c +++ b/arch/arm/mach-s3c2410/s3c2410.c @@ -170,7 +170,9 @@ int __init s3c2410_init(void) { printk("S3C2410: Initialising architecture\n"); +#ifdef CONFIG_PM register_syscore_ops(&s3c2410_pm_syscore_ops); +#endif register_syscore_ops(&s3c24xx_irq_syscore_ops); return sysdev_register(&s3c2410_sysdev); diff --git a/arch/arm/mach-s3c2412/mach-smdk2413.c b/arch/arm/mach-s3c2412/mach-smdk2413.c index d6325ede9f29..f1eec1b54932 100644 --- a/arch/arm/mach-s3c2412/mach-smdk2413.c +++ b/arch/arm/mach-s3c2412/mach-smdk2413.c @@ -92,8 +92,7 @@ static struct platform_device *smdk2413_devices[] __initdata = { &s3c_device_usbgadget, }; -static void __init smdk2413_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, +static void __init smdk2413_fixup(struct tag *tags, char **cmdline, struct meminfo *mi) { if (tags != phys_to_virt(S3C2410_SDRAM_PA + 0x100)) { diff --git a/arch/arm/mach-s3c2412/mach-vstms.c b/arch/arm/mach-s3c2412/mach-vstms.c index 5955c15018b4..1bbb1ef5f4ff 100644 --- a/arch/arm/mach-s3c2412/mach-vstms.c +++ b/arch/arm/mach-s3c2412/mach-vstms.c @@ -129,9 +129,8 @@ static struct platform_device *vstms_devices[] __initdata = { &s3c_device_nand, }; -static void __init vstms_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, - struct meminfo *mi) +static void __init vstms_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { if (tags != phys_to_virt(S3C2410_SDRAM_PA + 0x100)) { mi->nr_banks=1; diff --git a/arch/arm/mach-s3c2412/s3c2412.c b/arch/arm/mach-s3c2412/s3c2412.c index ef0958d3e5c6..57a1e01e4e50 100644 --- a/arch/arm/mach-s3c2412/s3c2412.c +++ b/arch/arm/mach-s3c2412/s3c2412.c @@ -245,7 +245,9 @@ int __init s3c2412_init(void) { printk("S3C2412: Initialising architecture\n"); +#ifdef CONFIG_PM register_syscore_ops(&s3c2412_pm_syscore_ops); +#endif register_syscore_ops(&s3c24xx_irq_syscore_ops); return sysdev_register(&s3c2412_sysdev); diff --git a/arch/arm/mach-s3c2416/s3c2416.c b/arch/arm/mach-s3c2416/s3c2416.c index 494ce913dc95..20b3fdfb3051 100644 --- a/arch/arm/mach-s3c2416/s3c2416.c +++ b/arch/arm/mach-s3c2416/s3c2416.c @@ -97,7 +97,9 @@ int __init s3c2416_init(void) s3c_fb_setname("s3c2443-fb"); +#ifdef CONFIG_PM register_syscore_ops(&s3c2416_pm_syscore_ops); +#endif register_syscore_ops(&s3c24xx_irq_syscore_ops); return sysdev_register(&s3c2416_sysdev); diff --git a/arch/arm/mach-s3c2440/s3c2440.c b/arch/arm/mach-s3c2440/s3c2440.c index ce99ff72838d..2270d3360216 100644 --- a/arch/arm/mach-s3c2440/s3c2440.c +++ b/arch/arm/mach-s3c2440/s3c2440.c @@ -55,7 +55,9 @@ int __init s3c2440_init(void) /* register suspend/resume handlers */ +#ifdef CONFIG_PM register_syscore_ops(&s3c2410_pm_syscore_ops); +#endif register_syscore_ops(&s3c244x_pm_syscore_ops); register_syscore_ops(&s3c24xx_irq_syscore_ops); diff --git a/arch/arm/mach-s3c2440/s3c2442.c b/arch/arm/mach-s3c2440/s3c2442.c index 9ad99f8016a1..6f2b65e6e068 100644 --- a/arch/arm/mach-s3c2440/s3c2442.c +++ b/arch/arm/mach-s3c2440/s3c2442.c @@ -169,7 +169,9 @@ int __init s3c2442_init(void) { printk("S3C2442: Initialising architecture\n"); +#ifdef CONFIG_PM register_syscore_ops(&s3c2410_pm_syscore_ops); +#endif register_syscore_ops(&s3c244x_pm_syscore_ops); register_syscore_ops(&s3c24xx_irq_syscore_ops); diff --git a/arch/arm/mach-s3c64xx/Makefile.boot b/arch/arm/mach-s3c64xx/Makefile.boot index ba41fdc0a586..c642333af3ed 100644 --- a/arch/arm/mach-s3c64xx/Makefile.boot +++ b/arch/arm/mach-s3c64xx/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x50008000 + zreladdr-y += 0x50008000 params_phys-y := 0x50000100 diff --git a/arch/arm/mach-s3c64xx/dev-uart.c b/arch/arm/mach-s3c64xx/dev-uart.c index f797f748b999..c681b99eda08 100644 --- a/arch/arm/mach-s3c64xx/dev-uart.c +++ b/arch/arm/mach-s3c64xx/dev-uart.c @@ -37,21 +37,10 @@ static struct resource s3c64xx_uart0_resource[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = IRQ_S3CUART_RX0, - .end = IRQ_S3CUART_RX0, + .start = IRQ_UART0, + .end = IRQ_UART0, .flags = IORESOURCE_IRQ, }, - [2] = { - .start = IRQ_S3CUART_TX0, - .end = IRQ_S3CUART_TX0, - .flags = IORESOURCE_IRQ, - - }, - [3] = { - .start = IRQ_S3CUART_ERR0, - .end = IRQ_S3CUART_ERR0, - .flags = IORESOURCE_IRQ, - } }; static struct resource s3c64xx_uart1_resource[] = { @@ -61,19 +50,8 @@ static struct resource s3c64xx_uart1_resource[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = IRQ_S3CUART_RX1, - .end = IRQ_S3CUART_RX1, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = IRQ_S3CUART_TX1, - .end = IRQ_S3CUART_TX1, - .flags = IORESOURCE_IRQ, - - }, - [3] = { - .start = IRQ_S3CUART_ERR1, - .end = IRQ_S3CUART_ERR1, + .start = IRQ_UART1, + .end = IRQ_UART1, .flags = IORESOURCE_IRQ, }, }; @@ -85,19 +63,8 @@ static struct resource s3c6xx_uart2_resource[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = IRQ_S3CUART_RX2, - .end = IRQ_S3CUART_RX2, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = IRQ_S3CUART_TX2, - .end = IRQ_S3CUART_TX2, - .flags = IORESOURCE_IRQ, - - }, - [3] = { - .start = IRQ_S3CUART_ERR2, - .end = IRQ_S3CUART_ERR2, + .start = IRQ_UART2, + .end = IRQ_UART2, .flags = IORESOURCE_IRQ, }, }; @@ -109,19 +76,8 @@ static struct resource s3c64xx_uart3_resource[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = IRQ_S3CUART_RX3, - .end = IRQ_S3CUART_RX3, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = IRQ_S3CUART_TX3, - .end = IRQ_S3CUART_TX3, - .flags = IORESOURCE_IRQ, - - }, - [3] = { - .start = IRQ_S3CUART_ERR3, - .end = IRQ_S3CUART_ERR3, + .start = IRQ_UART3, + .end = IRQ_UART3, .flags = IORESOURCE_IRQ, }, }; diff --git a/arch/arm/mach-s3c64xx/include/mach/irqs.h b/arch/arm/mach-s3c64xx/include/mach/irqs.h index c026f67a80de..443f85b3c203 100644 --- a/arch/arm/mach-s3c64xx/include/mach/irqs.h +++ b/arch/arm/mach-s3c64xx/include/mach/irqs.h @@ -27,36 +27,6 @@ #define IRQ_VIC0_BASE S3C_IRQ(0) #define IRQ_VIC1_BASE S3C_IRQ(32) -/* UART interrupts, each UART has 4 intterupts per channel so - * use the space between the ISA and S3C main interrupts. Note, these - * are not in the same order as the S3C24XX series! */ - -#define IRQ_S3CUART_BASE0 (16) -#define IRQ_S3CUART_BASE1 (20) -#define IRQ_S3CUART_BASE2 (24) -#define IRQ_S3CUART_BASE3 (28) - -#define UART_IRQ_RXD (0) -#define UART_IRQ_ERR (1) -#define UART_IRQ_TXD (2) -#define UART_IRQ_MODEM (3) - -#define IRQ_S3CUART_RX0 (IRQ_S3CUART_BASE0 + UART_IRQ_RXD) -#define IRQ_S3CUART_TX0 (IRQ_S3CUART_BASE0 + UART_IRQ_TXD) -#define IRQ_S3CUART_ERR0 (IRQ_S3CUART_BASE0 + UART_IRQ_ERR) - -#define IRQ_S3CUART_RX1 (IRQ_S3CUART_BASE1 + UART_IRQ_RXD) -#define IRQ_S3CUART_TX1 (IRQ_S3CUART_BASE1 + UART_IRQ_TXD) -#define IRQ_S3CUART_ERR1 (IRQ_S3CUART_BASE1 + UART_IRQ_ERR) - -#define IRQ_S3CUART_RX2 (IRQ_S3CUART_BASE2 + UART_IRQ_RXD) -#define IRQ_S3CUART_TX2 (IRQ_S3CUART_BASE2 + UART_IRQ_TXD) -#define IRQ_S3CUART_ERR2 (IRQ_S3CUART_BASE2 + UART_IRQ_ERR) - -#define IRQ_S3CUART_RX3 (IRQ_S3CUART_BASE3 + UART_IRQ_RXD) -#define IRQ_S3CUART_TX3 (IRQ_S3CUART_BASE3 + UART_IRQ_TXD) -#define IRQ_S3CUART_ERR3 (IRQ_S3CUART_BASE3 + UART_IRQ_ERR) - /* VIC based IRQs */ #define S3C64XX_IRQ_VIC0(x) (IRQ_VIC0_BASE + (x)) diff --git a/arch/arm/mach-s3c64xx/irq.c b/arch/arm/mach-s3c64xx/irq.c index 75d9a0e49193..b07357e94958 100644 --- a/arch/arm/mach-s3c64xx/irq.c +++ b/arch/arm/mach-s3c64xx/irq.c @@ -25,29 +25,6 @@ #include <plat/irq-uart.h> #include <plat/cpu.h> -static struct s3c_uart_irq uart_irqs[] = { - [0] = { - .regs = S3C_VA_UART0, - .base_irq = IRQ_S3CUART_BASE0, - .parent_irq = IRQ_UART0, - }, - [1] = { - .regs = S3C_VA_UART1, - .base_irq = IRQ_S3CUART_BASE1, - .parent_irq = IRQ_UART1, - }, - [2] = { - .regs = S3C_VA_UART2, - .base_irq = IRQ_S3CUART_BASE2, - .parent_irq = IRQ_UART2, - }, - [3] = { - .regs = S3C_VA_UART3, - .base_irq = IRQ_S3CUART_BASE3, - .parent_irq = IRQ_UART3, - }, -}; - /* setup the sources the vic should advertise resume for, even though it * is not doing the wake (set_irq_wake needs to be valid) */ #define IRQ_VIC0_RESUME (1 << (IRQ_RTC_TIC - IRQ_VIC0_BASE)) @@ -67,6 +44,4 @@ void __init s3c64xx_init_irq(u32 vic0_valid, u32 vic1_valid) /* add the timer sub-irqs */ s3c_init_vic_timer_irq(5, IRQ_TIMER0); - - s3c_init_uart_irqs(uart_irqs, ARRAY_SIZE(uart_irqs)); } diff --git a/arch/arm/mach-s5p64x0/Makefile.boot b/arch/arm/mach-s5p64x0/Makefile.boot index ff90aa13bd67..79ece4055b02 100644 --- a/arch/arm/mach-s5p64x0/Makefile.boot +++ b/arch/arm/mach-s5p64x0/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x20008000 + zreladdr-y += 0x20008000 params_phys-y := 0x20000100 diff --git a/arch/arm/mach-s5pc100/Makefile.boot b/arch/arm/mach-s5pc100/Makefile.boot index ff90aa13bd67..79ece4055b02 100644 --- a/arch/arm/mach-s5pc100/Makefile.boot +++ b/arch/arm/mach-s5pc100/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x20008000 + zreladdr-y += 0x20008000 params_phys-y := 0x20000100 diff --git a/arch/arm/mach-s5pv210/Makefile.boot b/arch/arm/mach-s5pv210/Makefile.boot index ff90aa13bd67..79ece4055b02 100644 --- a/arch/arm/mach-s5pv210/Makefile.boot +++ b/arch/arm/mach-s5pv210/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x20008000 + zreladdr-y += 0x20008000 params_phys-y := 0x20000100 diff --git a/arch/arm/mach-sa1100/Makefile b/arch/arm/mach-sa1100/Makefile index 73a5c6431792..ed7408d3216c 100644 --- a/arch/arm/mach-sa1100/Makefile +++ b/arch/arm/mach-sa1100/Makefile @@ -45,7 +45,6 @@ obj-$(CONFIG_SA1100_PLEB) += pleb.o obj-$(CONFIG_SA1100_SHANNON) += shannon.o obj-$(CONFIG_SA1100_SIMPAD) += simpad.o -led-$(CONFIG_SA1100_SIMPAD) += leds-simpad.o # LEDs support obj-$(CONFIG_LEDS) += $(led-y) diff --git a/arch/arm/mach-sa1100/Makefile.boot b/arch/arm/mach-sa1100/Makefile.boot index a56ad0417cf2..5a616f6e5612 100644 --- a/arch/arm/mach-sa1100/Makefile.boot +++ b/arch/arm/mach-sa1100/Makefile.boot @@ -1,6 +1,7 @@ - zreladdr-y := 0xc0008000 ifeq ($(CONFIG_ARCH_SA1100),y) - zreladdr-$(CONFIG_SA1111) := 0xc0208000 + zreladdr-$(CONFIG_SA1111) += 0xc0208000 +else + zreladdr-y += 0xc0008000 endif params_phys-y := 0xc0000100 initrd_phys-y := 0xc0800000 diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c index d40da5f1f37b..3dd133f18415 100644 --- a/arch/arm/mach-sa1100/assabet.c +++ b/arch/arm/mach-sa1100/assabet.c @@ -301,8 +301,7 @@ static void __init get_assabet_scr(void) } static void __init -fixup_assabet(struct machine_desc *desc, struct tag *tags, - char **cmdline, struct meminfo *mi) +fixup_assabet(struct tag *tags, char **cmdline, struct meminfo *mi) { /* This must be done before any call to machine_has_neponset() */ map_sa1100_gpio_regs(); diff --git a/arch/arm/mach-sa1100/include/mach/io.h b/arch/arm/mach-sa1100/include/mach/io.h index d8b43f3dcd2d..dfc27ff08344 100644 --- a/arch/arm/mach-sa1100/include/mach/io.h +++ b/arch/arm/mach-sa1100/include/mach/io.h @@ -10,11 +10,9 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H -#define IO_SPACE_LIMIT 0xffffffff - /* - * We don't actually have real ISA nor PCI buses, but there is so many - * drivers out there that might just work if we fake them... + * __io() is required to be an equivalent mapping to __mem_pci() for + * SOC_COMMON to work. */ #define __io(a) __typesafe_io(a) #define __mem_pci(a) (a) diff --git a/arch/arm/mach-sa1100/include/mach/simpad.h b/arch/arm/mach-sa1100/include/mach/simpad.h index 9296c4513ce1..db28118103eb 100644 --- a/arch/arm/mach-sa1100/include/mach/simpad.h +++ b/arch/arm/mach-sa1100/include/mach/simpad.h @@ -48,32 +48,80 @@ #define GPIO_SMART_CARD GPIO_GPIO10 #define IRQ_GPIO_SMARD_CARD IRQ_GPIO10 -// CS3 Latch is write only, a shadow is necessary +/*--- ucb1x00 GPIO ---*/ +#define SIMPAD_UCB1X00_GPIO_BASE (GPIO_MAX + 1) +#define SIMPAD_UCB1X00_GPIO_PROG1 (SIMPAD_UCB1X00_GPIO_BASE) +#define SIMPAD_UCB1X00_GPIO_PROG2 (SIMPAD_UCB1X00_GPIO_BASE + 1) +#define SIMPAD_UCB1X00_GPIO_UP (SIMPAD_UCB1X00_GPIO_BASE + 2) +#define SIMPAD_UCB1X00_GPIO_DOWN (SIMPAD_UCB1X00_GPIO_BASE + 3) +#define SIMPAD_UCB1X00_GPIO_LEFT (SIMPAD_UCB1X00_GPIO_BASE + 4) +#define SIMPAD_UCB1X00_GPIO_RIGHT (SIMPAD_UCB1X00_GPIO_BASE + 5) +#define SIMPAD_UCB1X00_GPIO_6 (SIMPAD_UCB1X00_GPIO_BASE + 6) +#define SIMPAD_UCB1X00_GPIO_7 (SIMPAD_UCB1X00_GPIO_BASE + 7) +#define SIMPAD_UCB1X00_GPIO_HEADSET (SIMPAD_UCB1X00_GPIO_BASE + 8) +#define SIMPAD_UCB1X00_GPIO_SPEAKER (SIMPAD_UCB1X00_GPIO_BASE + 9) + +/*--- CS3 Latch ---*/ +#define SIMPAD_CS3_GPIO_BASE (GPIO_MAX + 11) +#define SIMPAD_CS3_VCC_5V_EN (SIMPAD_CS3_GPIO_BASE) +#define SIMPAD_CS3_VCC_3V_EN (SIMPAD_CS3_GPIO_BASE + 1) +#define SIMPAD_CS3_EN1 (SIMPAD_CS3_GPIO_BASE + 2) +#define SIMPAD_CS3_EN0 (SIMPAD_CS3_GPIO_BASE + 3) +#define SIMPAD_CS3_DISPLAY_ON (SIMPAD_CS3_GPIO_BASE + 4) +#define SIMPAD_CS3_PCMCIA_BUFF_DIS (SIMPAD_CS3_GPIO_BASE + 5) +#define SIMPAD_CS3_MQ_RESET (SIMPAD_CS3_GPIO_BASE + 6) +#define SIMPAD_CS3_PCMCIA_RESET (SIMPAD_CS3_GPIO_BASE + 7) +#define SIMPAD_CS3_DECT_POWER_ON (SIMPAD_CS3_GPIO_BASE + 8) +#define SIMPAD_CS3_IRDA_SD (SIMPAD_CS3_GPIO_BASE + 9) +#define SIMPAD_CS3_RS232_ON (SIMPAD_CS3_GPIO_BASE + 10) +#define SIMPAD_CS3_SD_MEDIAQ (SIMPAD_CS3_GPIO_BASE + 11) +#define SIMPAD_CS3_LED2_ON (SIMPAD_CS3_GPIO_BASE + 12) +#define SIMPAD_CS3_IRDA_MODE (SIMPAD_CS3_GPIO_BASE + 13) +#define SIMPAD_CS3_ENABLE_5V (SIMPAD_CS3_GPIO_BASE + 14) +#define SIMPAD_CS3_RESET_SIMCARD (SIMPAD_CS3_GPIO_BASE + 15) + +#define SIMPAD_CS3_PCMCIA_BVD1 (SIMPAD_CS3_GPIO_BASE + 16) +#define SIMPAD_CS3_PCMCIA_BVD2 (SIMPAD_CS3_GPIO_BASE + 17) +#define SIMPAD_CS3_PCMCIA_VS1 (SIMPAD_CS3_GPIO_BASE + 18) +#define SIMPAD_CS3_PCMCIA_VS2 (SIMPAD_CS3_GPIO_BASE + 19) +#define SIMPAD_CS3_LOCK_IND (SIMPAD_CS3_GPIO_BASE + 20) +#define SIMPAD_CS3_CHARGING_STATE (SIMPAD_CS3_GPIO_BASE + 21) +#define SIMPAD_CS3_PCMCIA_SHORT (SIMPAD_CS3_GPIO_BASE + 22) +#define SIMPAD_CS3_GPIO_23 (SIMPAD_CS3_GPIO_BASE + 23) -#define CS3BUSTYPE unsigned volatile long #define CS3_BASE 0xf1000000 -#define VCC_5V_EN 0x0001 // For 5V PCMCIA -#define VCC_3V_EN 0x0002 // FOR 3.3V PCMCIA -#define EN1 0x0004 // This is only for EPROM's -#define EN0 0x0008 // Both should be enable for 3.3V or 5V -#define DISPLAY_ON 0x0010 -#define PCMCIA_BUFF_DIS 0x0020 -#define MQ_RESET 0x0040 -#define PCMCIA_RESET 0x0080 -#define DECT_POWER_ON 0x0100 -#define IRDA_SD 0x0200 // Shutdown for powersave -#define RS232_ON 0x0400 -#define SD_MEDIAQ 0x0800 // Shutdown for powersave -#define LED2_ON 0x1000 -#define IRDA_MODE 0x2000 // Fast/Slow IrDA mode -#define ENABLE_5V 0x4000 // Enable 5V circuit -#define RESET_SIMCARD 0x8000 - -#define RS232_ENABLE 0x0440 -#define PCMCIAMASK 0x402f - - +long simpad_get_cs3_ro(void); +long simpad_get_cs3_shadow(void); +void simpad_set_cs3_bit(int value); +void simpad_clear_cs3_bit(int value); + +#define VCC_5V_EN 0x0001 /* For 5V PCMCIA */ +#define VCC_3V_EN 0x0002 /* FOR 3.3V PCMCIA */ +#define EN1 0x0004 /* This is only for EPROM's */ +#define EN0 0x0008 /* Both should be enable for 3.3V or 5V */ +#define DISPLAY_ON 0x0010 +#define PCMCIA_BUFF_DIS 0x0020 +#define MQ_RESET 0x0040 +#define PCMCIA_RESET 0x0080 +#define DECT_POWER_ON 0x0100 +#define IRDA_SD 0x0200 /* Shutdown for powersave */ +#define RS232_ON 0x0400 +#define SD_MEDIAQ 0x0800 /* Shutdown for powersave */ +#define LED2_ON 0x1000 +#define IRDA_MODE 0x2000 /* Fast/Slow IrDA mode */ +#define ENABLE_5V 0x4000 /* Enable 5V circuit */ +#define RESET_SIMCARD 0x8000 + +#define PCMCIA_BVD1 0x01 +#define PCMCIA_BVD2 0x02 +#define PCMCIA_VS1 0x04 +#define PCMCIA_VS2 0x08 +#define LOCK_IND 0x10 +#define CHARGING_STATE 0x20 +#define PCMCIA_SHORT 0x40 + +/*--- Battery ---*/ struct simpad_battery { unsigned char ac_status; /* line connected yes/no */ unsigned char status; /* battery loading yes/no */ diff --git a/arch/arm/mach-sa1100/leds-simpad.c b/arch/arm/mach-sa1100/leds-simpad.c deleted file mode 100644 index d50f4eeaa12e..000000000000 --- a/arch/arm/mach-sa1100/leds-simpad.c +++ /dev/null @@ -1,100 +0,0 @@ -/* - * linux/arch/arm/mach-sa1100/leds-simpad.c - * - * Author: Juergen Messerer <juergen.messerer@siemens.ch> - */ -#include <linux/init.h> - -#include <mach/hardware.h> -#include <asm/leds.h> -#include <asm/system.h> -#include <mach/simpad.h> - -#include "leds.h" - - -#define LED_STATE_ENABLED 1 -#define LED_STATE_CLAIMED 2 - -static unsigned int led_state; -static unsigned int hw_led_state; - -#define LED_GREEN (1) -#define LED_MASK (1) - -extern void set_cs3_bit(int value); -extern void clear_cs3_bit(int value); - -void simpad_leds_event(led_event_t evt) -{ - switch (evt) - { - case led_start: - hw_led_state = LED_GREEN; - led_state = LED_STATE_ENABLED; - break; - - case led_stop: - led_state &= ~LED_STATE_ENABLED; - break; - - case led_claim: - led_state |= LED_STATE_CLAIMED; - hw_led_state = LED_GREEN; - break; - - case led_release: - led_state &= ~LED_STATE_CLAIMED; - hw_led_state = LED_GREEN; - break; - -#ifdef CONFIG_LEDS_TIMER - case led_timer: - if (!(led_state & LED_STATE_CLAIMED)) - hw_led_state ^= LED_GREEN; - break; -#endif - -#ifdef CONFIG_LEDS_CPU - case led_idle_start: - break; - - case led_idle_end: - break; -#endif - - case led_halted: - break; - - case led_green_on: - if (led_state & LED_STATE_CLAIMED) - hw_led_state |= LED_GREEN; - break; - - case led_green_off: - if (led_state & LED_STATE_CLAIMED) - hw_led_state &= ~LED_GREEN; - break; - - case led_amber_on: - break; - - case led_amber_off: - break; - - case led_red_on: - break; - - case led_red_off: - break; - - default: - break; - } - - if (led_state & LED_STATE_ENABLED) - set_cs3_bit(LED2_ON); - else - clear_cs3_bit(LED2_ON); -} - diff --git a/arch/arm/mach-sa1100/leds.c b/arch/arm/mach-sa1100/leds.c index bbfe197fb4d6..5fe71a0f1053 100644 --- a/arch/arm/mach-sa1100/leds.c +++ b/arch/arm/mach-sa1100/leds.c @@ -42,8 +42,6 @@ sa1100_leds_init(void) leds_event = adsbitsy_leds_event; if (machine_is_pt_system3()) leds_event = system3_leds_event; - if (machine_is_simpad()) - leds_event = simpad_leds_event; /* what about machine registry? including led, apm... -zecke */ leds_event(led_start); return 0; diff --git a/arch/arm/mach-sa1100/leds.h b/arch/arm/mach-sa1100/leds.h index 68cc9f773d6d..776b6020f550 100644 --- a/arch/arm/mach-sa1100/leds.h +++ b/arch/arm/mach-sa1100/leds.h @@ -11,4 +11,3 @@ extern void pfs168_leds_event(led_event_t evt); extern void graphicsmaster_leds_event(led_event_t evt); extern void adsbitsy_leds_event(led_event_t evt); extern void system3_leds_event(led_event_t evt); -extern void simpad_leds_event(led_event_t evt); diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c index a1c2427655da..4790f3f3d008 100644 --- a/arch/arm/mach-sa1100/simpad.c +++ b/arch/arm/mach-sa1100/simpad.c @@ -13,6 +13,7 @@ #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> #include <linux/io.h> +#include <linux/gpio.h> #include <asm/irq.h> #include <mach/hardware.h> @@ -28,35 +29,92 @@ #include <linux/serial_core.h> #include <linux/ioport.h> +#include <linux/input.h> +#include <linux/gpio_keys.h> +#include <linux/leds.h> +#include <linux/i2c-gpio.h> #include "generic.h" -long cs3_shadow; +/* + * CS3 support + */ -long get_cs3_shadow(void) +static long cs3_shadow; +static spinlock_t cs3_lock; +static struct gpio_chip cs3_gpio; + +long simpad_get_cs3_ro(void) +{ + return readl(CS3_BASE); +} +EXPORT_SYMBOL(simpad_get_cs3_ro); + +long simpad_get_cs3_shadow(void) { return cs3_shadow; } +EXPORT_SYMBOL(simpad_get_cs3_shadow); -void set_cs3(long value) +static void __simpad_write_cs3(void) { - *(CS3BUSTYPE *)(CS3_BASE) = cs3_shadow = value; + writel(cs3_shadow, CS3_BASE); } -void set_cs3_bit(int value) +void simpad_set_cs3_bit(int value) { + unsigned long flags; + + spin_lock_irqsave(&cs3_lock, flags); cs3_shadow |= value; - *(CS3BUSTYPE *)(CS3_BASE) = cs3_shadow; + __simpad_write_cs3(); + spin_unlock_irqrestore(&cs3_lock, flags); } +EXPORT_SYMBOL(simpad_set_cs3_bit); -void clear_cs3_bit(int value) +void simpad_clear_cs3_bit(int value) { + unsigned long flags; + + spin_lock_irqsave(&cs3_lock, flags); cs3_shadow &= ~value; - *(CS3BUSTYPE *)(CS3_BASE) = cs3_shadow; + __simpad_write_cs3(); + spin_unlock_irqrestore(&cs3_lock, flags); } +EXPORT_SYMBOL(simpad_clear_cs3_bit); + +static void cs3_gpio_set(struct gpio_chip *chip, unsigned offset, int value) +{ + if (offset > 15) + return; + if (value) + simpad_set_cs3_bit(1 << offset); + else + simpad_clear_cs3_bit(1 << offset); +}; + +static int cs3_gpio_get(struct gpio_chip *chip, unsigned offset) +{ + if (offset > 15) + return simpad_get_cs3_ro() & (1 << (offset - 16)); + return simpad_get_cs3_shadow() & (1 << offset); +}; -EXPORT_SYMBOL(set_cs3_bit); -EXPORT_SYMBOL(clear_cs3_bit); +static int cs3_gpio_direction_input(struct gpio_chip *chip, unsigned offset) +{ + if (offset > 15) + return 0; + return -EINVAL; +}; + +static int cs3_gpio_direction_output(struct gpio_chip *chip, unsigned offset, + int value) +{ + if (offset > 15) + return -EINVAL; + cs3_gpio_set(chip, offset, value); + return 0; +}; static struct map_desc simpad_io_desc[] __initdata = { { /* MQ200 */ @@ -64,9 +122,9 @@ static struct map_desc simpad_io_desc[] __initdata = { .pfn = __phys_to_pfn(0x4b800000), .length = 0x00800000, .type = MT_DEVICE - }, { /* Paules CS3, write only */ - .virtual = 0xf1000000, - .pfn = __phys_to_pfn(0x18000000), + }, { /* Simpad CS3 */ + .virtual = CS3_BASE, + .pfn = __phys_to_pfn(SA1100_CS3_PHYS), .length = 0x00100000, .type = MT_DEVICE }, @@ -78,12 +136,12 @@ static void simpad_uart_pm(struct uart_port *port, u_int state, u_int oldstate) if (port->mapbase == (u_int)&Ser1UTCR0) { if (state) { - clear_cs3_bit(RS232_ON); - clear_cs3_bit(DECT_POWER_ON); + simpad_clear_cs3_bit(RS232_ON); + simpad_clear_cs3_bit(DECT_POWER_ON); }else { - set_cs3_bit(RS232_ON); - set_cs3_bit(DECT_POWER_ON); + simpad_set_cs3_bit(RS232_ON); + simpad_set_cs3_bit(DECT_POWER_ON); } } } @@ -132,6 +190,7 @@ static struct resource simpad_flash_resources [] = { static struct mcp_plat_data simpad_mcp_data = { .mccr0 = MCCR0_ADM, .sclk_rate = 11981000, + .gpio_base = SIMPAD_UCB1X00_GPIO_BASE, }; @@ -142,9 +201,10 @@ static void __init simpad_map_io(void) iotable_init(simpad_io_desc, ARRAY_SIZE(simpad_io_desc)); - set_cs3_bit (EN1 | EN0 | LED2_ON | DISPLAY_ON | RS232_ON | - ENABLE_5V | RESET_SIMCARD | DECT_POWER_ON); - + /* Initialize CS3 */ + cs3_shadow = (EN1 | EN0 | LED2_ON | DISPLAY_ON | + RS232_ON | ENABLE_5V | RESET_SIMCARD | DECT_POWER_ON); + __simpad_write_cs3(); /* Spinlocks not yet initialized */ sa1100_register_uart_fns(&simpad_port_fns); sa1100_register_uart(0, 3); /* serial interface */ @@ -170,13 +230,14 @@ static void __init simpad_map_io(void) static void simpad_power_off(void) { - local_irq_disable(); // was cli - set_cs3(0x800); /* only SD_MEDIAQ */ + local_irq_disable(); + cs3_shadow = SD_MEDIAQ; + __simpad_write_cs3(); /* Bypass spinlock here */ /* disable internal oscillator, float CS lines */ PCFR = (PCFR_OPDE | PCFR_FP | PCFR_FS); - /* enable wake-up on GPIO0 (Assabet...) */ - PWER = GFER = GRER = 1; + /* enable wake-up on GPIO0 */ + PWER = GFER = GRER = PWER_GPIO0; /* * set scratchpad to zero, just in case it is used as a * restart address by the bootloader. @@ -192,6 +253,91 @@ static void simpad_power_off(void) } +/* + * gpio_keys +*/ + +static struct gpio_keys_button simpad_button_table[] = { + { KEY_POWER, IRQ_GPIO_POWER_BUTTON, 1, "power button" }, +}; + +static struct gpio_keys_platform_data simpad_keys_data = { + .buttons = simpad_button_table, + .nbuttons = ARRAY_SIZE(simpad_button_table), +}; + +static struct platform_device simpad_keys = { + .name = "gpio-keys", + .dev = { + .platform_data = &simpad_keys_data, + }, +}; + +static struct gpio_keys_button simpad_polled_button_table[] = { + { KEY_PROG1, SIMPAD_UCB1X00_GPIO_PROG1, 1, "prog1 button" }, + { KEY_PROG2, SIMPAD_UCB1X00_GPIO_PROG2, 1, "prog2 button" }, + { KEY_UP, SIMPAD_UCB1X00_GPIO_UP, 1, "up button" }, + { KEY_DOWN, SIMPAD_UCB1X00_GPIO_DOWN, 1, "down button" }, + { KEY_LEFT, SIMPAD_UCB1X00_GPIO_LEFT, 1, "left button" }, + { KEY_RIGHT, SIMPAD_UCB1X00_GPIO_RIGHT, 1, "right button" }, +}; + +static struct gpio_keys_platform_data simpad_polled_keys_data = { + .buttons = simpad_polled_button_table, + .nbuttons = ARRAY_SIZE(simpad_polled_button_table), + .poll_interval = 50, +}; + +static struct platform_device simpad_polled_keys = { + .name = "gpio-keys-polled", + .dev = { + .platform_data = &simpad_polled_keys_data, + }, +}; + +/* + * GPIO LEDs + */ + +static struct gpio_led simpad_leds[] = { + { + .name = "simpad:power", + .gpio = SIMPAD_CS3_LED2_ON, + .active_low = 0, + .default_trigger = "default-on", + }, +}; + +static struct gpio_led_platform_data simpad_led_data = { + .num_leds = ARRAY_SIZE(simpad_leds), + .leds = simpad_leds, +}; + +static struct platform_device simpad_gpio_leds = { + .name = "leds-gpio", + .id = 0, + .dev = { + .platform_data = &simpad_led_data, + }, +}; + +/* + * i2c + */ +static struct i2c_gpio_platform_data simpad_i2c_data = { + .sda_pin = GPIO_GPIO21, + .scl_pin = GPIO_GPIO25, + .udelay = 10, + .timeout = HZ, +}; + +static struct platform_device simpad_i2c = { + .name = "i2c-gpio", + .id = 0, + .dev = { + .platform_data = &simpad_i2c_data, + }, +}; /* * MediaQ Video Device @@ -202,7 +348,11 @@ static struct platform_device simpad_mq200fb = { }; static struct platform_device *devices[] __initdata = { - &simpad_mq200fb + &simpad_keys, + &simpad_polled_keys, + &simpad_mq200fb, + &simpad_gpio_leds, + &simpad_i2c, }; @@ -211,6 +361,19 @@ static int __init simpad_init(void) { int ret; + spin_lock_init(&cs3_lock); + + cs3_gpio.label = "simpad_cs3"; + cs3_gpio.base = SIMPAD_CS3_GPIO_BASE; + cs3_gpio.ngpio = 24; + cs3_gpio.set = cs3_gpio_set; + cs3_gpio.get = cs3_gpio_get; + cs3_gpio.direction_input = cs3_gpio_direction_input; + cs3_gpio.direction_output = cs3_gpio_direction_output; + ret = gpiochip_add(&cs3_gpio); + if (ret) + printk(KERN_WARNING "simpad: Unable to register cs3 GPIO device"); + pm_power_off = simpad_power_off; sa11x0_register_mtd(&simpad_flash_data, simpad_flash_resources, diff --git a/arch/arm/mach-shark/Makefile.boot b/arch/arm/mach-shark/Makefile.boot index 4320f8b92771..e40e24e4ca34 100644 --- a/arch/arm/mach-shark/Makefile.boot +++ b/arch/arm/mach-shark/Makefile.boot @@ -1,2 +1,2 @@ - zreladdr-y := 0x08008000 + zreladdr-y += 0x08008000 diff --git a/arch/arm/mach-shark/leds.c b/arch/arm/mach-shark/leds.c index c9e32de4adf9..ccd49189bbd0 100644 --- a/arch/arm/mach-shark/leds.c +++ b/arch/arm/mach-shark/leds.c @@ -36,7 +36,7 @@ static char led_state; static short hw_led_state; static short saved_state; -static DEFINE_SPINLOCK(leds_lock); +static DEFINE_RAW_SPINLOCK(leds_lock); short sequoia_read(int addr) { outw(addr,0x24); @@ -52,7 +52,7 @@ static void sequoia_leds_event(led_event_t evt) { unsigned long flags; - spin_lock_irqsave(&leds_lock, flags); + raw_spin_lock_irqsave(&leds_lock, flags); hw_led_state = sequoia_read(0x09); @@ -144,7 +144,7 @@ static void sequoia_leds_event(led_event_t evt) if (led_state & LED_STATE_ENABLED) sequoia_write(hw_led_state,0x09); - spin_unlock_irqrestore(&leds_lock, flags); + raw_spin_unlock_irqrestore(&leds_lock, flags); } static int __init leds_init(void) diff --git a/arch/arm/mach-shmobile/Makefile.boot b/arch/arm/mach-shmobile/Makefile.boot index 1c08ee9de86a..498efd99338d 100644 --- a/arch/arm/mach-shmobile/Makefile.boot +++ b/arch/arm/mach-shmobile/Makefile.boot @@ -1,7 +1,7 @@ __ZRELADDR := $(shell /bin/bash -c 'printf "0x%08x" \ $$[$(CONFIG_MEMORY_START) + 0x8000]') - zreladdr-y := $(__ZRELADDR) + zreladdr-y += $(__ZRELADDR) # Unsupported legacy stuff # diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c index 5fde49da399a..475342bcc95c 100644 --- a/arch/arm/mach-shmobile/board-ag5evm.c +++ b/arch/arm/mach-shmobile/board-ag5evm.c @@ -355,14 +355,17 @@ static struct resource sdhi0_resources[] = { .flags = IORESOURCE_MEM, }, [1] = { + .name = SH_MOBILE_SDHI_IRQ_CARD_DETECT, .start = gic_spi(83), .flags = IORESOURCE_IRQ, }, [2] = { + .name = SH_MOBILE_SDHI_IRQ_SDCARD, .start = gic_spi(84), .flags = IORESOURCE_IRQ, }, [3] = { + .name = SH_MOBILE_SDHI_IRQ_SDIO, .start = gic_spi(85), .flags = IORESOURCE_IRQ, }, @@ -398,14 +401,17 @@ static struct resource sdhi1_resources[] = { .flags = IORESOURCE_MEM, }, [1] = { + .name = SH_MOBILE_SDHI_IRQ_CARD_DETECT, .start = gic_spi(87), .flags = IORESOURCE_IRQ, }, [2] = { + .name = SH_MOBILE_SDHI_IRQ_SDCARD, .start = gic_spi(88), .flags = IORESOURCE_IRQ, }, [3] = { + .name = SH_MOBILE_SDHI_IRQ_SDIO, .start = gic_spi(89), .flags = IORESOURCE_IRQ, }, diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c index b622d8d3ab72..5b7edadf4647 100644 --- a/arch/arm/mach-shmobile/board-ap4evb.c +++ b/arch/arm/mach-shmobile/board-ap4evb.c @@ -42,6 +42,7 @@ #include <linux/leds.h> #include <linux/input/sh_keysc.h> #include <linux/usb/r8a66597.h> +#include <linux/pm_clock.h> #include <linux/dma-mapping.h> #include <media/sh_mobile_ceu.h> @@ -1411,6 +1412,11 @@ static void __init ap4evb_init(void) sh7372_add_device_to_domain(&sh7372_a4lc, &lcdc_device); sh7372_add_device_to_domain(&sh7372_a4mp, &fsi_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &sh_mmcif_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi0_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi1_device); + sh7372_add_device_to_domain(&sh7372_a4r, &ceu_device); + hdmi_init_pm_clock(); fsi_init_pm_clock(); sh7372_pm_init(); diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c index de2253d7f157..3689ad2e9156 100644 --- a/arch/arm/mach-shmobile/board-mackerel.c +++ b/arch/arm/mach-shmobile/board-mackerel.c @@ -39,7 +39,7 @@ #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> #include <linux/mtd/physmap.h> -#include <linux/pm_runtime.h> +#include <linux/pm_clock.h> #include <linux/smsc911x.h> #include <linux/sh_intc.h> #include <linux/tca6416_keypad.h> @@ -811,6 +811,7 @@ static struct usbhs_private usbhs1_private = { }, .driver_param = { .buswait_bwait = 4, + .has_otg = 1, .pipe_type = usbhs1_pipe_cfg, .pipe_size = ARRAY_SIZE(usbhs1_pipe_cfg), .d0_tx_id = SHDMA_SLAVE_USB1_TX, @@ -1071,14 +1072,17 @@ static struct resource sdhi1_resources[] = { .flags = IORESOURCE_MEM, }, [1] = { + .name = SH_MOBILE_SDHI_IRQ_CARD_DETECT, .start = evt2irq(0x0e80), /* SDHI1_SDHI1I0 */ .flags = IORESOURCE_IRQ, }, [2] = { + .name = SH_MOBILE_SDHI_IRQ_SDCARD, .start = evt2irq(0x0ea0), /* SDHI1_SDHI1I1 */ .flags = IORESOURCE_IRQ, }, [3] = { + .name = SH_MOBILE_SDHI_IRQ_SDIO, .start = evt2irq(0x0ec0), /* SDHI1_SDHI1I2 */ .flags = IORESOURCE_IRQ, }, @@ -1122,14 +1126,17 @@ static struct resource sdhi2_resources[] = { .flags = IORESOURCE_MEM, }, [1] = { + .name = SH_MOBILE_SDHI_IRQ_CARD_DETECT, .start = evt2irq(0x1200), /* SDHI2_SDHI2I0 */ .flags = IORESOURCE_IRQ, }, [2] = { + .name = SH_MOBILE_SDHI_IRQ_SDCARD, .start = evt2irq(0x1220), /* SDHI2_SDHI2I1 */ .flags = IORESOURCE_IRQ, }, [3] = { + .name = SH_MOBILE_SDHI_IRQ_SDIO, .start = evt2irq(0x1240), /* SDHI2_SDHI2I2 */ .flags = IORESOURCE_IRQ, }, @@ -1590,7 +1597,17 @@ static void __init mackerel_init(void) sh7372_add_device_to_domain(&sh7372_a4lc, &lcdc_device); sh7372_add_device_to_domain(&sh7372_a4lc, &hdmi_lcdc_device); + sh7372_add_device_to_domain(&sh7372_a4lc, &meram_device); sh7372_add_device_to_domain(&sh7372_a4mp, &fsi_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &usbhs0_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &usbhs1_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &sh_mmcif_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi0_device); +#if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE) + sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi1_device); +#endif + sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi2_device); + sh7372_add_device_to_domain(&sh7372_a4r, &ceu_device); hdmi_init_pm_clock(); sh7372_pm_init(); diff --git a/arch/arm/mach-shmobile/entry-intc.S b/arch/arm/mach-shmobile/entry-intc.S index cac0a7ae2084..1a1c00ca39a2 100644 --- a/arch/arm/mach-shmobile/entry-intc.S +++ b/arch/arm/mach-shmobile/entry-intc.S @@ -51,7 +51,4 @@ .macro test_for_ipi, irqnr, irqstat, base, tmp .endm - .macro test_for_ltirq, irqnr, irqstat, base, tmp - .endm - arch_irq_handler shmobile_handle_irq_intc diff --git a/arch/arm/mach-shmobile/include/mach/common.h b/arch/arm/mach-shmobile/include/mach/common.h index 06aecb31d9c7..c0cdbf997c91 100644 --- a/arch/arm/mach-shmobile/include/mach/common.h +++ b/arch/arm/mach-shmobile/include/mach/common.h @@ -35,8 +35,8 @@ extern void sh7372_add_standard_devices(void); extern void sh7372_clock_init(void); extern void sh7372_pinmux_init(void); extern void sh7372_pm_init(void); -extern void sh7372_cpu_suspend(void); -extern void sh7372_cpu_resume(void); +extern void sh7372_resume_core_standby_a3sm(void); +extern int sh7372_do_idle_a3sm(unsigned long unused); extern struct clk sh7372_extal1_clk; extern struct clk sh7372_extal2_clk; diff --git a/arch/arm/mach-shmobile/include/mach/entry-macro.S b/arch/arm/mach-shmobile/include/mach/entry-macro.S index d791f10eeac7..8d4a416d4285 100644 --- a/arch/arm/mach-shmobile/include/mach/entry-macro.S +++ b/arch/arm/mach-shmobile/include/mach/entry-macro.S @@ -27,8 +27,5 @@ .macro test_for_ipi, irqnr, irqstat, base, tmp .endm - .macro test_for_ltirq, irqnr, irqstat, base, tmp - .endm - .macro arch_ret_to_user, tmp1, tmp2 .endm diff --git a/arch/arm/mach-shmobile/include/mach/sh7372.h b/arch/arm/mach-shmobile/include/mach/sh7372.h index 24e63a85e669..84532f9629b2 100644 --- a/arch/arm/mach-shmobile/include/mach/sh7372.h +++ b/arch/arm/mach-shmobile/include/mach/sh7372.h @@ -479,7 +479,12 @@ struct platform_device; struct sh7372_pm_domain { struct generic_pm_domain genpd; + struct dev_power_governor *gov; + void (*suspend)(void); + void (*resume)(void); unsigned int bit_shift; + bool no_debug; + bool stay_on; }; static inline struct sh7372_pm_domain *to_sh7372_pd(struct generic_pm_domain *d) @@ -491,16 +496,24 @@ static inline struct sh7372_pm_domain *to_sh7372_pd(struct generic_pm_domain *d) extern struct sh7372_pm_domain sh7372_a4lc; extern struct sh7372_pm_domain sh7372_a4mp; extern struct sh7372_pm_domain sh7372_d4; +extern struct sh7372_pm_domain sh7372_a4r; extern struct sh7372_pm_domain sh7372_a3rv; extern struct sh7372_pm_domain sh7372_a3ri; +extern struct sh7372_pm_domain sh7372_a3sp; extern struct sh7372_pm_domain sh7372_a3sg; extern void sh7372_init_pm_domain(struct sh7372_pm_domain *sh7372_pd); extern void sh7372_add_device_to_domain(struct sh7372_pm_domain *sh7372_pd, struct platform_device *pdev); +extern void sh7372_pm_add_subdomain(struct sh7372_pm_domain *sh7372_pd, + struct sh7372_pm_domain *sh7372_sd); #else #define sh7372_init_pm_domain(pd) do { } while(0) #define sh7372_add_device_to_domain(pd, pdev) do { } while(0) +#define sh7372_pm_add_subdomain(pd, sd) do { } while(0) #endif /* CONFIG_PM */ +extern void sh7372_intcs_suspend(void); +extern void sh7372_intcs_resume(void); + #endif /* __ASM_SH7372_H__ */ diff --git a/arch/arm/mach-shmobile/intc-sh7372.c b/arch/arm/mach-shmobile/intc-sh7372.c index 739315e30eb9..29cdc0522d9c 100644 --- a/arch/arm/mach-shmobile/intc-sh7372.c +++ b/arch/arm/mach-shmobile/intc-sh7372.c @@ -606,9 +606,16 @@ static void intcs_demux(unsigned int irq, struct irq_desc *desc) generic_handle_irq(intcs_evt2irq(evtcodeas)); } +static void __iomem *intcs_ffd2; +static void __iomem *intcs_ffd5; + void __init sh7372_init_irq(void) { - void __iomem *intevtsa = ioremap_nocache(0xffd20100, PAGE_SIZE); + void __iomem *intevtsa; + + intcs_ffd2 = ioremap_nocache(0xffd20000, PAGE_SIZE); + intevtsa = intcs_ffd2 + 0x100; + intcs_ffd5 = ioremap_nocache(0xffd50000, PAGE_SIZE); register_intc_controller(&intca_desc); register_intc_controller(&intcs_desc); @@ -617,3 +624,46 @@ void __init sh7372_init_irq(void) irq_set_handler_data(evt2irq(0xf80), (void *)intevtsa); irq_set_chained_handler(evt2irq(0xf80), intcs_demux); } + +static unsigned short ffd2[0x200]; +static unsigned short ffd5[0x100]; + +void sh7372_intcs_suspend(void) +{ + int k; + + for (k = 0x00; k <= 0x30; k += 4) + ffd2[k] = __raw_readw(intcs_ffd2 + k); + + for (k = 0x80; k <= 0xb0; k += 4) + ffd2[k] = __raw_readb(intcs_ffd2 + k); + + for (k = 0x180; k <= 0x188; k += 4) + ffd2[k] = __raw_readb(intcs_ffd2 + k); + + for (k = 0x00; k <= 0x3c; k += 4) + ffd5[k] = __raw_readw(intcs_ffd5 + k); + + for (k = 0x80; k <= 0x9c; k += 4) + ffd5[k] = __raw_readb(intcs_ffd5 + k); +} + +void sh7372_intcs_resume(void) +{ + int k; + + for (k = 0x00; k <= 0x30; k += 4) + __raw_writew(ffd2[k], intcs_ffd2 + k); + + for (k = 0x80; k <= 0xb0; k += 4) + __raw_writeb(ffd2[k], intcs_ffd2 + k); + + for (k = 0x180; k <= 0x188; k += 4) + __raw_writeb(ffd2[k], intcs_ffd2 + k); + + for (k = 0x00; k <= 0x3c; k += 4) + __raw_writew(ffd5[k], intcs_ffd5 + k); + + for (k = 0x80; k <= 0x9c; k += 4) + __raw_writeb(ffd5[k], intcs_ffd5 + k); +} diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c index 66f980625a33..e4e485fa2532 100644 --- a/arch/arm/mach-shmobile/platsmp.c +++ b/arch/arm/mach-shmobile/platsmp.c @@ -56,6 +56,12 @@ void __init smp_init_cpus(void) unsigned int ncores = shmobile_smp_get_core_count(); unsigned int i; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; + } + for (i = 0; i < ncores; i++) set_cpu_possible(i, true); diff --git a/arch/arm/mach-shmobile/pm-sh7372.c b/arch/arm/mach-shmobile/pm-sh7372.c index 933fb411be0f..79612737c5b2 100644 --- a/arch/arm/mach-shmobile/pm-sh7372.c +++ b/arch/arm/mach-shmobile/pm-sh7372.c @@ -15,23 +15,61 @@ #include <linux/list.h> #include <linux/err.h> #include <linux/slab.h> -#include <linux/pm_runtime.h> +#include <linux/pm_clock.h> #include <linux/platform_device.h> #include <linux/delay.h> +#include <linux/irq.h> +#include <linux/bitrev.h> #include <asm/system.h> #include <asm/io.h> #include <asm/tlbflush.h> +#include <asm/suspend.h> #include <mach/common.h> #include <mach/sh7372.h> -#define SMFRAM 0xe6a70000 -#define SYSTBCR 0xe6150024 -#define SBAR 0xe6180020 -#define APARMBAREA 0xe6f10020 +/* DBG */ +#define DBGREG1 0xe6100020 +#define DBGREG9 0xe6100040 +/* CPGA */ +#define SYSTBCR 0xe6150024 +#define MSTPSR0 0xe6150030 +#define MSTPSR1 0xe6150038 +#define MSTPSR2 0xe6150040 +#define MSTPSR3 0xe6150048 +#define MSTPSR4 0xe615004c +#define PLLC01STPCR 0xe61500c8 + +/* SYSC */ #define SPDCR 0xe6180008 #define SWUCR 0xe6180014 +#define SBAR 0xe6180020 +#define WUPRMSK 0xe6180028 +#define WUPSMSK 0xe618002c +#define WUPSMSK2 0xe6180048 #define PSTR 0xe6180080 +#define WUPSFAC 0xe6180098 +#define IRQCR 0xe618022c +#define IRQCR2 0xe6180238 +#define IRQCR3 0xe6180244 +#define IRQCR4 0xe6180248 +#define PDNSEL 0xe6180254 + +/* INTC */ +#define ICR1A 0xe6900000 +#define ICR2A 0xe6900004 +#define ICR3A 0xe6900008 +#define ICR4A 0xe690000c +#define INTMSK00A 0xe6900040 +#define INTMSK10A 0xe6900044 +#define INTMSK20A 0xe6900048 +#define INTMSK30A 0xe690004c + +/* MFIS */ +#define SMFRAM 0xe6a70000 + +/* AP-System Core */ +#define APARMBAREA 0xe6f10020 #define PSTR_RETRIES 100 #define PSTR_DELAY_US 10 @@ -43,6 +81,12 @@ static int pd_power_down(struct generic_pm_domain *genpd) struct sh7372_pm_domain *sh7372_pd = to_sh7372_pd(genpd); unsigned int mask = 1 << sh7372_pd->bit_shift; + if (sh7372_pd->suspend) + sh7372_pd->suspend(); + + if (sh7372_pd->stay_on) + return 0; + if (__raw_readl(PSTR) & mask) { unsigned int retry_count; @@ -55,8 +99,9 @@ static int pd_power_down(struct generic_pm_domain *genpd) } } - pr_debug("sh7372 power domain down 0x%08x -> PSTR = 0x%08x\n", - mask, __raw_readl(PSTR)); + if (!sh7372_pd->no_debug) + pr_debug("sh7372 power domain down 0x%08x -> PSTR = 0x%08x\n", + mask, __raw_readl(PSTR)); return 0; } @@ -68,6 +113,9 @@ static int pd_power_up(struct generic_pm_domain *genpd) unsigned int retry_count; int ret = 0; + if (sh7372_pd->stay_on) + goto out; + if (__raw_readl(PSTR) & mask) goto out; @@ -84,66 +132,48 @@ static int pd_power_up(struct generic_pm_domain *genpd) if (__raw_readl(SWUCR) & mask) ret = -EIO; + if (!sh7372_pd->no_debug) + pr_debug("sh7372 power domain up 0x%08x -> PSTR = 0x%08x\n", + mask, __raw_readl(PSTR)); + out: - pr_debug("sh7372 power domain up 0x%08x -> PSTR = 0x%08x\n", - mask, __raw_readl(PSTR)); + if (ret == 0 && sh7372_pd->resume) + sh7372_pd->resume(); return ret; } -static int pd_power_up_a3rv(struct generic_pm_domain *genpd) +static void sh7372_a4r_suspend(void) { - int ret = pd_power_up(genpd); - - /* force A4LC on after A3RV has been requested on */ - pm_genpd_poweron(&sh7372_a4lc.genpd); - - return ret; + sh7372_intcs_suspend(); + __raw_writel(0x300fffff, WUPRMSK); /* avoid wakeup */ } -static int pd_power_down_a3rv(struct generic_pm_domain *genpd) +static bool pd_active_wakeup(struct device *dev) { - int ret = pd_power_down(genpd); - - /* try to power down A4LC after A3RV is requested off */ - genpd_queue_power_off_work(&sh7372_a4lc.genpd); - - return ret; + return true; } -static int pd_power_down_a4lc(struct generic_pm_domain *genpd) +static bool sh7372_power_down_forbidden(struct dev_pm_domain *domain) { - /* only power down A4LC if A3RV is off */ - if (!(__raw_readl(PSTR) & (1 << sh7372_a3rv.bit_shift))) - return pd_power_down(genpd); - - return -EBUSY; + return false; } -static bool pd_active_wakeup(struct device *dev) -{ - return true; -} +struct dev_power_governor sh7372_always_on_gov = { + .power_down_ok = sh7372_power_down_forbidden, +}; void sh7372_init_pm_domain(struct sh7372_pm_domain *sh7372_pd) { struct generic_pm_domain *genpd = &sh7372_pd->genpd; - pm_genpd_init(genpd, NULL, false); + pm_genpd_init(genpd, sh7372_pd->gov, false); genpd->stop_device = pm_clk_suspend; genpd->start_device = pm_clk_resume; + genpd->dev_irq_safe = true; genpd->active_wakeup = pd_active_wakeup; - - if (sh7372_pd == &sh7372_a4lc) { - genpd->power_off = pd_power_down_a4lc; - genpd->power_on = pd_power_up; - } else if (sh7372_pd == &sh7372_a3rv) { - genpd->power_off = pd_power_down_a3rv; - genpd->power_on = pd_power_up_a3rv; - } else { - genpd->power_off = pd_power_down; - genpd->power_on = pd_power_up; - } + genpd->power_off = pd_power_down; + genpd->power_on = pd_power_up; genpd->power_on(&sh7372_pd->genpd); } @@ -152,11 +182,15 @@ void sh7372_add_device_to_domain(struct sh7372_pm_domain *sh7372_pd, { struct device *dev = &pdev->dev; - if (!dev->power.subsys_data) { - pm_clk_init(dev); - pm_clk_add(dev, NULL); - } pm_genpd_add_device(&sh7372_pd->genpd, dev); + if (pm_clk_no_clocks(dev)) + pm_clk_add(dev, NULL); +} + +void sh7372_pm_add_subdomain(struct sh7372_pm_domain *sh7372_pd, + struct sh7372_pm_domain *sh7372_sd) +{ + pm_genpd_add_subdomain(&sh7372_pd->genpd, &sh7372_sd->genpd); } struct sh7372_pm_domain sh7372_a4lc = { @@ -171,6 +205,14 @@ struct sh7372_pm_domain sh7372_d4 = { .bit_shift = 3, }; +struct sh7372_pm_domain sh7372_a4r = { + .bit_shift = 5, + .gov = &sh7372_always_on_gov, + .suspend = sh7372_a4r_suspend, + .resume = sh7372_intcs_resume, + .stay_on = true, +}; + struct sh7372_pm_domain sh7372_a3rv = { .bit_shift = 6, }; @@ -179,39 +221,187 @@ struct sh7372_pm_domain sh7372_a3ri = { .bit_shift = 8, }; +struct sh7372_pm_domain sh7372_a3sp = { + .bit_shift = 11, + .gov = &sh7372_always_on_gov, + .no_debug = true, +}; + struct sh7372_pm_domain sh7372_a3sg = { .bit_shift = 13, }; #endif /* CONFIG_PM */ +#if defined(CONFIG_SUSPEND) || defined(CONFIG_CPU_IDLE) +static int sh7372_do_idle_core_standby(unsigned long unused) +{ + cpu_do_idle(); /* WFI when SYSTBCR == 0x10 -> Core Standby */ + return 0; +} + static void sh7372_enter_core_standby(void) { - void __iomem *smfram = (void __iomem *)SMFRAM; + /* set reset vector, translate 4k */ + __raw_writel(__pa(sh7372_resume_core_standby_a3sm), SBAR); + __raw_writel(0, APARMBAREA); - __raw_writel(0, APARMBAREA); /* translate 4k */ - __raw_writel(__pa(sh7372_cpu_resume), SBAR); /* set reset vector */ - __raw_writel(0x10, SYSTBCR); /* enable core standby */ + /* enter sleep mode with SYSTBCR to 0x10 */ + __raw_writel(0x10, SYSTBCR); + cpu_suspend(0, sh7372_do_idle_core_standby); + __raw_writel(0, SYSTBCR); - __raw_writel(0, smfram + 0x3c); /* clear page table address */ + /* disable reset vector translation */ + __raw_writel(0, SBAR); +} +#endif + +#ifdef CONFIG_SUSPEND +static void sh7372_enter_a3sm_common(int pllc0_on) +{ + /* set reset vector, translate 4k */ + __raw_writel(__pa(sh7372_resume_core_standby_a3sm), SBAR); + __raw_writel(0, APARMBAREA); + + if (pllc0_on) + __raw_writel(0, PLLC01STPCR); + else + __raw_writel(1 << 28, PLLC01STPCR); + + __raw_writel(0, PDNSEL); /* power-down A3SM only, not A4S */ + __raw_readl(WUPSFAC); /* read wakeup int. factor before sleep */ + cpu_suspend(0, sh7372_do_idle_a3sm); + __raw_readl(WUPSFAC); /* read wakeup int. factor after wakeup */ + + /* disable reset vector translation */ + __raw_writel(0, SBAR); +} + +static int sh7372_a3sm_valid(unsigned long *mskp, unsigned long *msk2p) +{ + unsigned long mstpsr0, mstpsr1, mstpsr2, mstpsr3, mstpsr4; + unsigned long msk, msk2; + + /* check active clocks to determine potential wakeup sources */ + + mstpsr0 = __raw_readl(MSTPSR0); + if ((mstpsr0 & 0x00000003) != 0x00000003) { + pr_debug("sh7372 mstpsr0 0x%08lx\n", mstpsr0); + return 0; + } + + mstpsr1 = __raw_readl(MSTPSR1); + if ((mstpsr1 & 0xff079b7f) != 0xff079b7f) { + pr_debug("sh7372 mstpsr1 0x%08lx\n", mstpsr1); + return 0; + } - sh7372_cpu_suspend(); - cpu_init(); + mstpsr2 = __raw_readl(MSTPSR2); + if ((mstpsr2 & 0x000741ff) != 0x000741ff) { + pr_debug("sh7372 mstpsr2 0x%08lx\n", mstpsr2); + return 0; + } - /* if page table address is non-NULL then we have been powered down */ - if (__raw_readl(smfram + 0x3c)) { - __raw_writel(__raw_readl(smfram + 0x40), - __va(__raw_readl(smfram + 0x3c))); + mstpsr3 = __raw_readl(MSTPSR3); + if ((mstpsr3 & 0x1a60f010) != 0x1a60f010) { + pr_debug("sh7372 mstpsr3 0x%08lx\n", mstpsr3); + return 0; + } - flush_tlb_all(); - set_cr(__raw_readl(smfram + 0x38)); + mstpsr4 = __raw_readl(MSTPSR4); + if ((mstpsr4 & 0x00008cf0) != 0x00008cf0) { + pr_debug("sh7372 mstpsr4 0x%08lx\n", mstpsr4); + return 0; } - __raw_writel(0, SYSTBCR); /* disable core standby */ - __raw_writel(0, SBAR); /* disable reset vector translation */ + msk = 0; + msk2 = 0; + + /* make bitmaps of limited number of wakeup sources */ + + if ((mstpsr2 & (1 << 23)) == 0) /* SPU2 */ + msk |= 1 << 31; + + if ((mstpsr2 & (1 << 12)) == 0) /* MFI_MFIM */ + msk |= 1 << 21; + + if ((mstpsr4 & (1 << 3)) == 0) /* KEYSC */ + msk |= 1 << 2; + + if ((mstpsr1 & (1 << 24)) == 0) /* CMT0 */ + msk |= 1 << 1; + + if ((mstpsr3 & (1 << 29)) == 0) /* CMT1 */ + msk |= 1 << 1; + + if ((mstpsr4 & (1 << 0)) == 0) /* CMT2 */ + msk |= 1 << 1; + + if ((mstpsr2 & (1 << 13)) == 0) /* MFI_MFIS */ + msk2 |= 1 << 17; + + *mskp = msk; + *msk2p = msk2; + + return 1; +} + +static void sh7372_icr_to_irqcr(unsigned long icr, u16 *irqcr1p, u16 *irqcr2p) +{ + u16 tmp, irqcr1, irqcr2; + int k; + + irqcr1 = 0; + irqcr2 = 0; + + /* convert INTCA ICR register layout to SYSC IRQCR+IRQCR2 */ + for (k = 0; k <= 7; k++) { + tmp = (icr >> ((7 - k) * 4)) & 0xf; + irqcr1 |= (tmp & 0x03) << (k * 2); + irqcr2 |= (tmp >> 2) << (k * 2); + } + + *irqcr1p = irqcr1; + *irqcr2p = irqcr2; +} + +static void sh7372_setup_a3sm(unsigned long msk, unsigned long msk2) +{ + u16 irqcrx_low, irqcrx_high, irqcry_low, irqcry_high; + unsigned long tmp; + + /* read IRQ0A -> IRQ15A mask */ + tmp = bitrev8(__raw_readb(INTMSK00A)); + tmp |= bitrev8(__raw_readb(INTMSK10A)) << 8; + + /* setup WUPSMSK from clocks and external IRQ mask */ + msk = (~msk & 0xc030000f) | (tmp << 4); + __raw_writel(msk, WUPSMSK); + + /* propage level/edge trigger for external IRQ 0->15 */ + sh7372_icr_to_irqcr(__raw_readl(ICR1A), &irqcrx_low, &irqcry_low); + sh7372_icr_to_irqcr(__raw_readl(ICR2A), &irqcrx_high, &irqcry_high); + __raw_writel((irqcrx_high << 16) | irqcrx_low, IRQCR); + __raw_writel((irqcry_high << 16) | irqcry_low, IRQCR2); + + /* read IRQ16A -> IRQ31A mask */ + tmp = bitrev8(__raw_readb(INTMSK20A)); + tmp |= bitrev8(__raw_readb(INTMSK30A)) << 8; + + /* setup WUPSMSK2 from clocks and external IRQ mask */ + msk2 = (~msk2 & 0x00030000) | tmp; + __raw_writel(msk2, WUPSMSK2); + + /* propage level/edge trigger for external IRQ 16->31 */ + sh7372_icr_to_irqcr(__raw_readl(ICR3A), &irqcrx_low, &irqcry_low); + sh7372_icr_to_irqcr(__raw_readl(ICR4A), &irqcrx_high, &irqcry_high); + __raw_writel((irqcrx_high << 16) | irqcrx_low, IRQCR3); + __raw_writel((irqcry_high << 16) | irqcry_low, IRQCR4); } +#endif #ifdef CONFIG_CPU_IDLE + static void sh7372_cpuidle_setup(struct cpuidle_device *dev) { struct cpuidle_state *state; @@ -239,9 +429,25 @@ static void sh7372_cpuidle_init(void) {} #endif #ifdef CONFIG_SUSPEND + static int sh7372_enter_suspend(suspend_state_t suspend_state) { - sh7372_enter_core_standby(); + unsigned long msk, msk2; + + /* check active clocks to determine potential wakeup sources */ + if (sh7372_a3sm_valid(&msk, &msk2)) { + + /* convert INTC mask and sense to SYSC mask and sense */ + sh7372_setup_a3sm(msk, msk2); + + /* enter A3SM sleep with PLLC0 off */ + pr_debug("entering A3SM\n"); + sh7372_enter_a3sm_common(0); + } else { + /* default to Core Standby that supports all wakeup sources */ + pr_debug("entering Core Standby\n"); + sh7372_enter_core_standby(); + } return 0; } @@ -253,9 +459,6 @@ static void sh7372_suspend_init(void) static void sh7372_suspend_init(void) {} #endif -#define DBGREG1 0xe6100020 -#define DBGREG9 0xe6100040 - void __init sh7372_pm_init(void) { /* enable DBG hardware block to kick SYSC */ @@ -263,6 +466,9 @@ void __init sh7372_pm_init(void) __raw_writel(0x0000a501, DBGREG9); __raw_writel(0x00000000, DBGREG1); + /* do not convert A3SM, A3SP, A3SG, A4R power down into A4S */ + __raw_writel(0, PDNSEL); + sh7372_suspend_init(); sh7372_cpuidle_init(); } diff --git a/arch/arm/mach-shmobile/pm_runtime.c b/arch/arm/mach-shmobile/pm_runtime.c index 6ec454e1e063..bd5c6a3b8c55 100644 --- a/arch/arm/mach-shmobile/pm_runtime.c +++ b/arch/arm/mach-shmobile/pm_runtime.c @@ -15,6 +15,7 @@ #include <linux/io.h> #include <linux/pm_runtime.h> #include <linux/pm_domain.h> +#include <linux/pm_clock.h> #include <linux/platform_device.h> #include <linux/clk.h> #include <linux/sh_clk.h> diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c index 2d9b1b1a2538..2380389e6ac5 100644 --- a/arch/arm/mach-shmobile/setup-sh7372.c +++ b/arch/arm/mach-shmobile/setup-sh7372.c @@ -30,6 +30,7 @@ #include <linux/sh_dma.h> #include <linux/sh_intc.h> #include <linux/sh_timer.h> +#include <linux/pm_domain.h> #include <mach/hardware.h> #include <mach/sh7372.h> #include <asm/mach-types.h> @@ -990,9 +991,14 @@ void __init sh7372_add_standard_devices(void) sh7372_init_pm_domain(&sh7372_a4lc); sh7372_init_pm_domain(&sh7372_a4mp); sh7372_init_pm_domain(&sh7372_d4); + sh7372_init_pm_domain(&sh7372_a4r); sh7372_init_pm_domain(&sh7372_a3rv); sh7372_init_pm_domain(&sh7372_a3ri); sh7372_init_pm_domain(&sh7372_a3sg); + sh7372_init_pm_domain(&sh7372_a3sp); + + sh7372_pm_add_subdomain(&sh7372_a4lc, &sh7372_a3rv); + sh7372_pm_add_subdomain(&sh7372_a4r, &sh7372_a4lc); platform_add_devices(sh7372_early_devices, ARRAY_SIZE(sh7372_early_devices)); @@ -1003,6 +1009,25 @@ void __init sh7372_add_standard_devices(void) sh7372_add_device_to_domain(&sh7372_a3rv, &vpu_device); sh7372_add_device_to_domain(&sh7372_a4mp, &spu0_device); sh7372_add_device_to_domain(&sh7372_a4mp, &spu1_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &scif0_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &scif1_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &scif2_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &scif3_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &scif4_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &scif5_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &scif6_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &iic1_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &dma0_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &dma1_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &dma2_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &usb_dma0_device); + sh7372_add_device_to_domain(&sh7372_a3sp, &usb_dma1_device); + sh7372_add_device_to_domain(&sh7372_a4r, &iic0_device); + sh7372_add_device_to_domain(&sh7372_a4r, &veu0_device); + sh7372_add_device_to_domain(&sh7372_a4r, &veu1_device); + sh7372_add_device_to_domain(&sh7372_a4r, &veu2_device); + sh7372_add_device_to_domain(&sh7372_a4r, &veu3_device); + sh7372_add_device_to_domain(&sh7372_a4r, &jpu_device); } void __init sh7372_add_early_devices(void) diff --git a/arch/arm/mach-shmobile/sleep-sh7372.S b/arch/arm/mach-shmobile/sleep-sh7372.S index d37d3ca4d18f..f3ab3c5810ea 100644 --- a/arch/arm/mach-shmobile/sleep-sh7372.S +++ b/arch/arm/mach-shmobile/sleep-sh7372.S @@ -30,58 +30,20 @@ */ #include <linux/linkage.h> +#include <linux/init.h> +#include <asm/memory.h> #include <asm/assembler.h> -#define SMFRAM 0xe6a70000 - - .align -kernel_flush: - .word v7_flush_dcache_all - - .align 3 -ENTRY(sh7372_cpu_suspend) - stmfd sp!, {r0-r12, lr} @ save registers on stack - - ldr r8, =SMFRAM - - mov r4, sp @ Store sp - mrs r5, spsr @ Store spsr - mov r6, lr @ Store lr - stmia r8!, {r4-r6} - - mrc p15, 0, r4, c1, c0, 2 @ Coprocessor access control register - mrc p15, 0, r5, c2, c0, 0 @ TTBR0 - mrc p15, 0, r6, c2, c0, 1 @ TTBR1 - mrc p15, 0, r7, c2, c0, 2 @ TTBCR - stmia r8!, {r4-r7} - - mrc p15, 0, r4, c3, c0, 0 @ Domain access Control Register - mrc p15, 0, r5, c10, c2, 0 @ PRRR - mrc p15, 0, r6, c10, c2, 1 @ NMRR - stmia r8!,{r4-r6} - - mrc p15, 0, r4, c13, c0, 1 @ Context ID - mrc p15, 0, r5, c13, c0, 2 @ User r/w thread and process ID - mrc p15, 0, r6, c12, c0, 0 @ Secure or NS vector base address - mrs r7, cpsr @ Store current cpsr - stmia r8!, {r4-r7} - - mrc p15, 0, r4, c1, c0, 0 @ save control register - stmia r8!, {r4} - - /* - * jump out to kernel flush routine - * - reuse that code is better - * - it executes in a cached space so is faster than refetch per-block - * - should be faster and will change with kernel - * - 'might' have to copy address, load and jump to it - * Flush all data from the L1 data cache before disabling - * SCTLR.C bit. - */ - ldr r1, kernel_flush - mov lr, pc - bx r1 +#if defined(CONFIG_SUSPEND) || defined(CONFIG_CPU_IDLE) + .align 12 + .text + .global sh7372_resume_core_standby_a3sm +sh7372_resume_core_standby_a3sm: + ldr pc, 1f +1: .long cpu_resume - PAGE_OFFSET + PLAT_PHYS_OFFSET + .global sh7372_do_idle_a3sm +sh7372_do_idle_a3sm: /* * Clear the SCTLR.C bit to prevent further data cache * allocation. Clearing SCTLR.C would make all the data accesses @@ -92,10 +54,13 @@ ENTRY(sh7372_cpu_suspend) mcr p15, 0, r0, c1, c0, 0 isb + /* disable L2 cache in the aux control register */ + mrc p15, 0, r10, c1, c0, 1 + bic r10, r10, #2 + mcr p15, 0, r10, c1, c0, 1 + /* - * Invalidate L1 data cache. Even though only invalidate is - * necessary exported flush API is used here. Doing clean - * on already clean cache would be almost NOP. + * Invalidate data cache again. */ ldr r1, kernel_flush blx r1 @@ -115,146 +80,16 @@ ENTRY(sh7372_cpu_suspend) dsb dmb -/* - * =================================== - * == WFI instruction => Enter idle == - * =================================== - */ - wfi @ wait for interrupt - -/* - * =================================== - * == Resume path for non-OFF modes == - * =================================== - */ - mrc p15, 0, r0, c1, c0, 0 - tst r0, #(1 << 2) @ Check C bit enabled? - orreq r0, r0, #(1 << 2) @ Enable the C bit if cleared - mcreq p15, 0, r0, c1, c0, 0 - isb - -/* - * =================================== - * == Exit point from non-OFF modes == - * =================================== - */ - ldmfd sp!, {r0-r12, pc} @ restore regs and return +#define SPDCR 0xe6180008 +#define A3SM (1 << 12) - .pool + /* A3SM power down */ + ldr r0, =SPDCR + ldr r1, =A3SM + str r1, [r0] +1: + b 1b - .align 12 - .text - .global sh7372_cpu_resume -sh7372_cpu_resume: - - mov r1, #0 - /* - * Invalidate all instruction caches to PoU - * and flush branch target cache - */ - mcr p15, 0, r1, c7, c5, 0 - - ldr r3, =SMFRAM - - ldmia r3!, {r4-r6} - mov sp, r4 @ Restore sp - msr spsr_cxsf, r5 @ Restore spsr - mov lr, r6 @ Restore lr - - ldmia r3!, {r4-r7} - mcr p15, 0, r4, c1, c0, 2 @ Coprocessor access Control Register - mcr p15, 0, r5, c2, c0, 0 @ TTBR0 - mcr p15, 0, r6, c2, c0, 1 @ TTBR1 - mcr p15, 0, r7, c2, c0, 2 @ TTBCR - - ldmia r3!,{r4-r6} - mcr p15, 0, r4, c3, c0, 0 @ Domain access Control Register - mcr p15, 0, r5, c10, c2, 0 @ PRRR - mcr p15, 0, r6, c10, c2, 1 @ NMRR - - ldmia r3!,{r4-r7} - mcr p15, 0, r4, c13, c0, 1 @ Context ID - mcr p15, 0, r5, c13, c0, 2 @ User r/w thread and process ID - mrc p15, 0, r6, c12, c0, 0 @ Secure or NS vector base address - msr cpsr, r7 @ store cpsr - - /* Starting to enable MMU here */ - mrc p15, 0, r7, c2, c0, 2 @ Read TTBRControl - /* Extract N (0:2) bits and decide whether to use TTBR0 or TTBR1 */ - and r7, #0x7 - cmp r7, #0x0 - beq usettbr0 -ttbr_error: - /* - * More work needs to be done to support N[0:2] value other than 0 - * So looping here so that the error can be detected - */ - b ttbr_error - - .align -cache_pred_disable_mask: - .word 0xFFFFE7FB -ttbrbit_mask: - .word 0xFFFFC000 -table_index_mask: - .word 0xFFF00000 -table_entry: - .word 0x00000C02 -usettbr0: - - mrc p15, 0, r2, c2, c0, 0 - ldr r5, ttbrbit_mask - and r2, r5 - mov r4, pc - ldr r5, table_index_mask - and r4, r5 @ r4 = 31 to 20 bits of pc - /* Extract the value to be written to table entry */ - ldr r6, table_entry - /* r6 has the value to be written to table entry */ - add r6, r6, r4 - /* Getting the address of table entry to modify */ - lsr r4, #18 - /* r2 has the location which needs to be modified */ - add r2, r4 - ldr r4, [r2] - str r6, [r2] /* modify the table entry */ - - mov r7, r6 - mov r5, r2 - mov r6, r4 - /* r5 = original page table address */ - /* r6 = original page table data */ - - mov r0, #0 - mcr p15, 0, r0, c7, c5, 4 @ Flush prefetch buffer - mcr p15, 0, r0, c7, c5, 6 @ Invalidate branch predictor array - mcr p15, 0, r0, c8, c5, 0 @ Invalidate instruction TLB - mcr p15, 0, r0, c8, c6, 0 @ Invalidate data TLB - - /* - * Restore control register. This enables the MMU. - * The caches and prediction are not enabled here, they - * will be enabled after restoring the MMU table entry. - */ - ldmia r3!, {r4} - stmia r3!, {r5} /* save original page table address */ - stmia r3!, {r6} /* save original page table data */ - stmia r3!, {r7} /* save modified page table data */ - - ldr r2, cache_pred_disable_mask - and r4, r2 - mcr p15, 0, r4, c1, c0, 0 - dsb - isb - - ldr r0, =restoremmu_on - bx r0 - -/* - * ============================== - * == Exit point from OFF mode == - * ============================== - */ -restoremmu_on: - - ldmfd sp!, {r0-r12, pc} @ restore regs and return +kernel_flush: + .word v7_flush_dcache_all +#endif diff --git a/arch/arm/mach-spear3xx/Makefile.boot b/arch/arm/mach-spear3xx/Makefile.boot index 7a1f3c0eadb8..4674a4c221db 100644 --- a/arch/arm/mach-spear3xx/Makefile.boot +++ b/arch/arm/mach-spear3xx/Makefile.boot @@ -1,3 +1,3 @@ -zreladdr-y := 0x00008000 +zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-spear6xx/Makefile.boot b/arch/arm/mach-spear6xx/Makefile.boot index 7a1f3c0eadb8..4674a4c221db 100644 --- a/arch/arm/mach-spear6xx/Makefile.boot +++ b/arch/arm/mach-spear6xx/Makefile.boot @@ -1,3 +1,3 @@ -zreladdr-y := 0x00008000 +zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-tcc8k/Makefile.boot b/arch/arm/mach-tcc8k/Makefile.boot index f135c9deae10..5e02d4156b04 100644 --- a/arch/arm/mach-tcc8k/Makefile.boot +++ b/arch/arm/mach-tcc8k/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x20008000 + zreladdr-y += 0x20008000 params_phys-y := 0x20000100 initrd_phys-y := 0x20800000 diff --git a/arch/arm/mach-tegra/Makefile.boot b/arch/arm/mach-tegra/Makefile.boot index 428ad122be03..5e870d29eca1 100644 --- a/arch/arm/mach-tegra/Makefile.boot +++ b/arch/arm/mach-tegra/Makefile.boot @@ -1,4 +1,4 @@ -zreladdr-$(CONFIG_ARCH_TEGRA_2x_SOC) := 0x00008000 +zreladdr-$(CONFIG_ARCH_TEGRA_2x_SOC) += 0x00008000 params_phys-$(CONFIG_ARCH_TEGRA_2x_SOC) := 0x00000100 initrd_phys-$(CONFIG_ARCH_TEGRA_2x_SOC) := 0x00800000 diff --git a/arch/arm/mach-tegra/board-harmony.c b/arch/arm/mach-tegra/board-harmony.c index a4d1980e697a..93c793f48caf 100644 --- a/arch/arm/mach-tegra/board-harmony.c +++ b/arch/arm/mach-tegra/board-harmony.c @@ -123,8 +123,8 @@ static struct platform_device *harmony_devices[] __initdata = { &harmony_audio_device, }; -static void __init tegra_harmony_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init tegra_harmony_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks = 2; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-tegra/board-paz00.c b/arch/arm/mach-tegra/board-paz00.c index 3197c4cbaa71..fbc9e0ed926e 100644 --- a/arch/arm/mach-tegra/board-paz00.c +++ b/arch/arm/mach-tegra/board-paz00.c @@ -84,8 +84,8 @@ static void paz00_usb_init(void) platform_device_register(&tegra_ehci3_device); } -static void __init tegra_paz00_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init tegra_paz00_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks = 1; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-tegra/board-trimslice.c b/arch/arm/mach-tegra/board-trimslice.c index 8489aa8f5154..e3d9ec2f0fe1 100644 --- a/arch/arm/mach-tegra/board-trimslice.c +++ b/arch/arm/mach-tegra/board-trimslice.c @@ -126,8 +126,8 @@ static void trimslice_usb_init(void) platform_device_register(&tegra_ehci1_device); } -static void __init tegra_trimslice_fixup(struct machine_desc *desc, - struct tag *tags, char **cmdline, struct meminfo *mi) +static void __init tegra_trimslice_fixup(struct tag *tags, char **cmdline, + struct meminfo *mi) { mi->nr_banks = 2; mi->bank[0].start = PHYS_OFFSET; diff --git a/arch/arm/mach-tegra/cpu-tegra.c b/arch/arm/mach-tegra/cpu-tegra.c index 0e1016a827ac..0e0fd4d889bd 100644 --- a/arch/arm/mach-tegra/cpu-tegra.c +++ b/arch/arm/mach-tegra/cpu-tegra.c @@ -32,7 +32,6 @@ #include <asm/system.h> -#include <mach/hardware.h> #include <mach/clk.h> /* Frequency table index must be sequential starting at 0 */ diff --git a/arch/arm/mach-tegra/include/mach/gpio.h b/arch/arm/mach-tegra/include/mach/gpio.h index e69de29bb2d1..40a8c178f10d 100644 --- a/arch/arm/mach-tegra/include/mach/gpio.h +++ b/arch/arm/mach-tegra/include/mach/gpio.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/arm/mach-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c index 0886cbccddee..7d2b5d03c1df 100644 --- a/arch/arm/mach-tegra/platsmp.c +++ b/arch/arm/mach-tegra/platsmp.c @@ -114,10 +114,10 @@ void __init smp_init_cpus(void) { unsigned int i, ncores = scu_get_core_count(scu_base); - if (ncores > NR_CPUS) { - printk(KERN_ERR "Tegra: no. of cores (%u) greater than configured (%u), clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-u300/Kconfig b/arch/arm/mach-u300/Kconfig index 7b5c229dc7ea..d6e5d306557b 100644 --- a/arch/arm/mach-u300/Kconfig +++ b/arch/arm/mach-u300/Kconfig @@ -6,6 +6,8 @@ comment "ST-Ericsson Mobile Platform Products" config MACH_U300 bool "U300" + select PINCTRL + select PINMUX_U300 select GPIO_U300 comment "ST-Ericsson U300/U330/U335/U365 Feature Selections" diff --git a/arch/arm/mach-u300/Makefile b/arch/arm/mach-u300/Makefile index 8fd354aaf0a7..285538124e5e 100644 --- a/arch/arm/mach-u300/Makefile +++ b/arch/arm/mach-u300/Makefile @@ -2,7 +2,7 @@ # Makefile for the linux kernel, U300 machine. # -obj-y := core.o clock.o timer.o padmux.o +obj-y := core.o clock.o timer.o obj-m := obj-n := obj- := diff --git a/arch/arm/mach-u300/Makefile.boot b/arch/arm/mach-u300/Makefile.boot index 6fbfc6ea2d35..69357affbd77 100644 --- a/arch/arm/mach-u300/Makefile.boot +++ b/arch/arm/mach-u300/Makefile.boot @@ -4,10 +4,10 @@ # INITRD_PHYS must be in RAM ifdef CONFIG_MACH_U300_SINGLE_RAM - zreladdr-y := 0x28E08000 + zreladdr-y += 0x28E08000 params_phys-y := 0x28E00100 else - zreladdr-y := 0x48008000 + zreladdr-y += 0x48008000 params_phys-y := 0x48000100 endif diff --git a/arch/arm/mach-u300/core.c b/arch/arm/mach-u300/core.c index 22c5ab79a74c..f4ad6d2e26f3 100644 --- a/arch/arm/mach-u300/core.c +++ b/arch/arm/mach-u300/core.c @@ -25,6 +25,8 @@ #include <linux/err.h> #include <linux/mtd/nand.h> #include <linux/mtd/fsmc.h> +#include <linux/pinctrl/machine.h> +#include <linux/pinctrl/pinmux.h> #include <linux/dma-mapping.h> #include <asm/types.h> @@ -1539,6 +1541,14 @@ static struct coh901318_platform coh901318_platform = { .max_channels = U300_DMA_CHANNELS, }; +static struct resource pinmux_resources[] = { + { + .start = U300_SYSCON_BASE, + .end = U300_SYSCON_BASE + SZ_4K - 1, + .flags = IORESOURCE_MEM, + }, +}; + static struct platform_device wdog_device = { .name = "coh901327_wdog", .id = -1, @@ -1658,6 +1668,72 @@ static struct platform_device dma_device = { }, }; +static struct platform_device pinmux_device = { + .name = "pinmux-u300", + .id = -1, + .num_resources = ARRAY_SIZE(pinmux_resources), + .resource = pinmux_resources, +}; + +/* Pinmux settings */ +static struct pinmux_map u300_pinmux_map[] = { + /* anonymous maps for chip power and EMIFs */ + PINMUX_MAP_PRIMARY_SYS_HOG("POWER", "power"), + PINMUX_MAP_PRIMARY_SYS_HOG("EMIF0", "emif0"), + PINMUX_MAP_PRIMARY_SYS_HOG("EMIF1", "emif1"), + /* per-device maps for MMC/SD, SPI and UART */ + PINMUX_MAP_PRIMARY("MMCSD", "mmc0", "mmci"), + PINMUX_MAP_PRIMARY("SPI", "spi0", "pl022"), + PINMUX_MAP_PRIMARY("UART0", "uart0", "uart0"), +}; + +struct u300_mux_hog { + const char *name; + struct device *dev; + struct pinmux *pmx; +}; + +static struct u300_mux_hog u300_mux_hogs[] = { + { + .name = "uart0", + .dev = &uart0_device.dev, + }, + { + .name = "spi0", + .dev = &pl022_device.dev, + }, + { + .name = "mmc0", + .dev = &mmcsd_device.dev, + }, +}; + +static int __init u300_pinmux_fetch(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(u300_mux_hogs); i++) { + struct pinmux *pmx; + int ret; + + pmx = pinmux_get(u300_mux_hogs[i].dev, NULL); + if (IS_ERR(pmx)) { + pr_err("u300: could not get pinmux hog %s\n", + u300_mux_hogs[i].name); + continue; + } + ret = pinmux_enable(pmx); + if (ret) { + pr_err("u300: could enable pinmux hog %s\n", + u300_mux_hogs[i].name); + continue; + } + u300_mux_hogs[i].pmx = pmx; + } + return 0; +} +subsys_initcall(u300_pinmux_fetch); + /* * Notice that AMBA devices are initialized before platform devices. * @@ -1671,10 +1747,10 @@ static struct platform_device *platform_devs[] __initdata = { &gpio_device, &nand_device, &wdog_device, - &ave_device + &ave_device, + &pinmux_device, }; - /* * Interrupts: the U300 platforms have two pl190 ARM PrimeCells connected * together so some interrupts are connected to the first one and some @@ -1856,6 +1932,10 @@ void __init u300_init_devices(void) u300_assign_physmem(); + /* Initialize pinmuxing */ + pinmux_register_mappings(u300_pinmux_map, + ARRAY_SIZE(u300_pinmux_map)); + /* Register subdevices on the I2C buses */ u300_i2c_register_board_devices(); diff --git a/arch/arm/mach-u300/include/mach/gpio.h b/arch/arm/mach-u300/include/mach/gpio.h index e69de29bb2d1..40a8c178f10d 100644 --- a/arch/arm/mach-u300/include/mach/gpio.h +++ b/arch/arm/mach-u300/include/mach/gpio.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/arm/mach-u300/include/mach/syscon.h b/arch/arm/mach-u300/include/mach/syscon.h index 7444f5c7da97..6e84f07a7c6f 100644 --- a/arch/arm/mach-u300/include/mach/syscon.h +++ b/arch/arm/mach-u300/include/mach/syscon.h @@ -234,91 +234,6 @@ #define U300_SYSCON_ECCR_EMIF_1_RET_OUT_CLK_EN_N_DISABLE (0x0004) #define U300_SYSCON_ECCR_EMIF_MEMCLK_RET_EN_N_DISABLE (0x0002) #define U300_SYSCON_ECCR_EMIF_SDRCLK_RET_EN_N_DISABLE (0x0001) -/* PAD MUX Control register 1 (LOW) 16bit (R/W) */ -#define U300_SYSCON_PMC1LR (0x007C) -#define U300_SYSCON_PMC1LR_MASK (0xFFFF) -#define U300_SYSCON_PMC1LR_CDI_MASK (0xC000) -#define U300_SYSCON_PMC1LR_CDI_CDI (0x0000) -#define U300_SYSCON_PMC1LR_CDI_EMIF (0x4000) -#ifdef CONFIG_MACH_U300_BS335 -#define U300_SYSCON_PMC1LR_CDI_CDI2 (0x8000) -#define U300_SYSCON_PMC1LR_CDI_WCDMA_APP_GPIO (0xC000) -#elif CONFIG_MACH_U300_BS365 -#define U300_SYSCON_PMC1LR_CDI_GPIO (0x8000) -#define U300_SYSCON_PMC1LR_CDI_WCDMA (0xC000) -#endif -#define U300_SYSCON_PMC1LR_PDI_MASK (0x3000) -#define U300_SYSCON_PMC1LR_PDI_PDI (0x0000) -#define U300_SYSCON_PMC1LR_PDI_EGG (0x1000) -#define U300_SYSCON_PMC1LR_PDI_WCDMA (0x3000) -#define U300_SYSCON_PMC1LR_MMCSD_MASK (0x0C00) -#define U300_SYSCON_PMC1LR_MMCSD_MMCSD (0x0000) -#define U300_SYSCON_PMC1LR_MMCSD_MSPRO (0x0400) -#define U300_SYSCON_PMC1LR_MMCSD_DSP (0x0800) -#define U300_SYSCON_PMC1LR_MMCSD_WCDMA (0x0C00) -#define U300_SYSCON_PMC1LR_ETM_MASK (0x0300) -#define U300_SYSCON_PMC1LR_ETM_ACC (0x0000) -#define U300_SYSCON_PMC1LR_ETM_APP (0x0100) -#define U300_SYSCON_PMC1LR_EMIF_1_CS2_MASK (0x00C0) -#define U300_SYSCON_PMC1LR_EMIF_1_CS2_STATIC (0x0000) -#define U300_SYSCON_PMC1LR_EMIF_1_CS2_NFIF (0x0040) -#define U300_SYSCON_PMC1LR_EMIF_1_CS2_SDRAM (0x0080) -#define U300_SYSCON_PMC1LR_EMIF_1_CS2_STATIC_2GB (0x00C0) -#define U300_SYSCON_PMC1LR_EMIF_1_CS1_MASK (0x0030) -#define U300_SYSCON_PMC1LR_EMIF_1_CS1_STATIC (0x0000) -#define U300_SYSCON_PMC1LR_EMIF_1_CS1_NFIF (0x0010) -#define U300_SYSCON_PMC1LR_EMIF_1_CS1_SDRAM (0x0020) -#define U300_SYSCON_PMC1LR_EMIF_1_CS1_SEMI (0x0030) -#define U300_SYSCON_PMC1LR_EMIF_1_CS0_MASK (0x000C) -#define U300_SYSCON_PMC1LR_EMIF_1_CS0_STATIC (0x0000) -#define U300_SYSCON_PMC1LR_EMIF_1_CS0_NFIF (0x0004) -#define U300_SYSCON_PMC1LR_EMIF_1_CS0_SDRAM (0x0008) -#define U300_SYSCON_PMC1LR_EMIF_1_CS0_SEMI (0x000C) -#define U300_SYSCON_PMC1LR_EMIF_1_MASK (0x0003) -#define U300_SYSCON_PMC1LR_EMIF_1_STATIC (0x0000) -#define U300_SYSCON_PMC1LR_EMIF_1_SDRAM0 (0x0001) -#define U300_SYSCON_PMC1LR_EMIF_1_SDRAM1 (0x0002) -#define U300_SYSCON_PMC1LR_EMIF_1 (0x0003) -/* PAD MUX Control register 2 (HIGH) 16bit (R/W) */ -#define U300_SYSCON_PMC1HR (0x007E) -#define U300_SYSCON_PMC1HR_MASK (0xFFFF) -#define U300_SYSCON_PMC1HR_MISC_2_MASK (0xC000) -#define U300_SYSCON_PMC1HR_MISC_2_APP_GPIO (0x0000) -#define U300_SYSCON_PMC1HR_MISC_2_MSPRO (0x4000) -#define U300_SYSCON_PMC1HR_MISC_2_DSP (0x8000) -#define U300_SYSCON_PMC1HR_MISC_2_AAIF (0xC000) -#define U300_SYSCON_PMC1HR_APP_GPIO_2_MASK (0x3000) -#define U300_SYSCON_PMC1HR_APP_GPIO_2_APP_GPIO (0x0000) -#define U300_SYSCON_PMC1HR_APP_GPIO_2_NFIF (0x1000) -#define U300_SYSCON_PMC1HR_APP_GPIO_2_DSP (0x2000) -#define U300_SYSCON_PMC1HR_APP_GPIO_2_AAIF (0x3000) -#define U300_SYSCON_PMC1HR_APP_GPIO_1_MASK (0x0C00) -#define U300_SYSCON_PMC1HR_APP_GPIO_1_APP_GPIO (0x0000) -#define U300_SYSCON_PMC1HR_APP_GPIO_1_MMC (0x0400) -#define U300_SYSCON_PMC1HR_APP_GPIO_1_DSP (0x0800) -#define U300_SYSCON_PMC1HR_APP_GPIO_1_AAIF (0x0C00) -#define U300_SYSCON_PMC1HR_APP_SPI_CS_2_MASK (0x0300) -#define U300_SYSCON_PMC1HR_APP_SPI_CS_2_APP_GPIO (0x0000) -#define U300_SYSCON_PMC1HR_APP_SPI_CS_2_SPI (0x0100) -#define U300_SYSCON_PMC1HR_APP_SPI_CS_2_AAIF (0x0300) -#define U300_SYSCON_PMC1HR_APP_SPI_CS_1_MASK (0x00C0) -#define U300_SYSCON_PMC1HR_APP_SPI_CS_1_APP_GPIO (0x0000) -#define U300_SYSCON_PMC1HR_APP_SPI_CS_1_SPI (0x0040) -#define U300_SYSCON_PMC1HR_APP_SPI_CS_1_AAIF (0x00C0) -#define U300_SYSCON_PMC1HR_APP_SPI_2_MASK (0x0030) -#define U300_SYSCON_PMC1HR_APP_SPI_2_APP_GPIO (0x0000) -#define U300_SYSCON_PMC1HR_APP_SPI_2_SPI (0x0010) -#define U300_SYSCON_PMC1HR_APP_SPI_2_DSP (0x0020) -#define U300_SYSCON_PMC1HR_APP_SPI_2_AAIF (0x0030) -#define U300_SYSCON_PMC1HR_APP_UART0_2_MASK (0x000C) -#define U300_SYSCON_PMC1HR_APP_UART0_2_APP_GPIO (0x0000) -#define U300_SYSCON_PMC1HR_APP_UART0_2_UART0 (0x0004) -#define U300_SYSCON_PMC1HR_APP_UART0_2_NFIF_CS (0x0008) -#define U300_SYSCON_PMC1HR_APP_UART0_2_AAIF (0x000C) -#define U300_SYSCON_PMC1HR_APP_UART0_1_MASK (0x0003) -#define U300_SYSCON_PMC1HR_APP_UART0_1_APP_GPIO (0x0000) -#define U300_SYSCON_PMC1HR_APP_UART0_1_UART0 (0x0001) -#define U300_SYSCON_PMC1HR_APP_UART0_1_AAIF (0x0003) /* Step one for killing the applications system 16bit (-/W) */ #define U300_SYSCON_KA1R (0x0080) #define U300_SYSCON_KA1R_MASK (0xFFFF) @@ -357,57 +272,6 @@ #define U300_SYSCON_PUCR_EMIF_1_16BIT_PU_ENABLE (0x0080) #define U300_SYSCON_PUCR_EMIF_1_8BIT_PU_ENABLE (0x0040) #define U300_SYSCON_PUCR_KEY_IN_PU_EN_MASK (0x003F) -/* Padmux 2 control */ -#define U300_SYSCON_PMC2R (0x100) -#define U300_SYSCON_PMC2R_APP_MISC_0_MASK (0x00C0) -#define U300_SYSCON_PMC2R_APP_MISC_0_APP_GPIO (0x0000) -#define U300_SYSCON_PMC2R_APP_MISC_0_EMIF_SDRAM (0x0040) -#define U300_SYSCON_PMC2R_APP_MISC_0_MMC (0x0080) -#define U300_SYSCON_PMC2R_APP_MISC_0_CDI2 (0x00C0) -#define U300_SYSCON_PMC2R_APP_MISC_1_MASK (0x0300) -#define U300_SYSCON_PMC2R_APP_MISC_1_APP_GPIO (0x0000) -#define U300_SYSCON_PMC2R_APP_MISC_1_EMIF_SDRAM (0x0100) -#define U300_SYSCON_PMC2R_APP_MISC_1_MMC (0x0200) -#define U300_SYSCON_PMC2R_APP_MISC_1_CDI2 (0x0300) -#define U300_SYSCON_PMC2R_APP_MISC_2_MASK (0x0C00) -#define U300_SYSCON_PMC2R_APP_MISC_2_APP_GPIO (0x0000) -#define U300_SYSCON_PMC2R_APP_MISC_2_EMIF_SDRAM (0x0400) -#define U300_SYSCON_PMC2R_APP_MISC_2_MMC (0x0800) -#define U300_SYSCON_PMC2R_APP_MISC_2_CDI2 (0x0C00) -#define U300_SYSCON_PMC2R_APP_MISC_3_MASK (0x3000) -#define U300_SYSCON_PMC2R_APP_MISC_3_APP_GPIO (0x0000) -#define U300_SYSCON_PMC2R_APP_MISC_3_EMIF_SDRAM (0x1000) -#define U300_SYSCON_PMC2R_APP_MISC_3_MMC (0x2000) -#define U300_SYSCON_PMC2R_APP_MISC_3_CDI2 (0x3000) -#define U300_SYSCON_PMC2R_APP_MISC_4_MASK (0xC000) -#define U300_SYSCON_PMC2R_APP_MISC_4_APP_GPIO (0x0000) -#define U300_SYSCON_PMC2R_APP_MISC_4_EMIF_SDRAM (0x4000) -#define U300_SYSCON_PMC2R_APP_MISC_4_MMC (0x8000) -#define U300_SYSCON_PMC2R_APP_MISC_4_ACC_GPIO (0xC000) -/* TODO: More SYSCON registers missing */ -#define U300_SYSCON_PMC3R (0x10c) -#define U300_SYSCON_PMC3R_APP_MISC_11_MASK (0xc000) -#define U300_SYSCON_PMC3R_APP_MISC_11_SPI (0x4000) -#define U300_SYSCON_PMC3R_APP_MISC_10_MASK (0x3000) -#define U300_SYSCON_PMC3R_APP_MISC_10_SPI (0x1000) -/* TODO: Missing other configs */ -#define U300_SYSCON_PMC4R (0x168) -#define U300_SYSCON_PMC4R_APP_MISC_12_MASK (0x0003) -#define U300_SYSCON_PMC4R_APP_MISC_12_APP_GPIO (0x0000) -#define U300_SYSCON_PMC4R_APP_MISC_13_MASK (0x000C) -#define U300_SYSCON_PMC4R_APP_MISC_13_CDI (0x0000) -#define U300_SYSCON_PMC4R_APP_MISC_13_SMIA (0x0004) -#define U300_SYSCON_PMC4R_APP_MISC_13_SMIA2 (0x0008) -#define U300_SYSCON_PMC4R_APP_MISC_13_APP_GPIO (0x000C) -#define U300_SYSCON_PMC4R_APP_MISC_14_MASK (0x0030) -#define U300_SYSCON_PMC4R_APP_MISC_14_CDI (0x0000) -#define U300_SYSCON_PMC4R_APP_MISC_14_SMIA (0x0010) -#define U300_SYSCON_PMC4R_APP_MISC_14_CDI2 (0x0020) -#define U300_SYSCON_PMC4R_APP_MISC_14_APP_GPIO (0x0030) -#define U300_SYSCON_PMC4R_APP_MISC_16_MASK (0x0300) -#define U300_SYSCON_PMC4R_APP_MISC_16_APP_GPIO_13 (0x0000) -#define U300_SYSCON_PMC4R_APP_MISC_16_APP_UART1_CTS (0x0100) -#define U300_SYSCON_PMC4R_APP_MISC_16_EMIF_1_STATIC_CS5_N (0x0200) /* SYS_0_CLK_CONTROL first clock control 16bit (R/W) */ #define U300_SYSCON_S0CCR (0x120) #define U300_SYSCON_S0CCR_FIELD_MASK (0x43FF) diff --git a/arch/arm/mach-u300/mmc.c b/arch/arm/mach-u300/mmc.c index d9a5c92db74a..4d482aacc272 100644 --- a/arch/arm/mach-u300/mmc.c +++ b/arch/arm/mach-u300/mmc.c @@ -21,7 +21,6 @@ #include <mach/gpio-u300.h> #include "mmc.h" -#include "padmux.h" static struct mmci_platform_data mmc0_plat_data = { /* @@ -45,24 +44,9 @@ static struct mmci_platform_data mmc0_plat_data = { int __devinit mmc_init(struct amba_device *adev) { struct device *mmcsd_device = &adev->dev; - struct pmx *pmx; int ret = 0; mmcsd_device->platform_data = &mmc0_plat_data; - /* - * Setup padmuxing for MMC. Since this must always be - * compiled into the kernel, pmx is never released. - */ - pmx = pmx_get(mmcsd_device, U300_APP_PMX_MMC_SETTING); - - if (IS_ERR(pmx)) - pr_warning("Could not get padmux handle\n"); - else { - ret = pmx_activate(mmcsd_device, pmx); - if (IS_ERR_VALUE(ret)) - pr_warning("Could not activate padmuxing\n"); - } - return ret; } diff --git a/arch/arm/mach-u300/padmux.c b/arch/arm/mach-u300/padmux.c deleted file mode 100644 index 4c93c6cefd37..000000000000 --- a/arch/arm/mach-u300/padmux.c +++ /dev/null @@ -1,367 +0,0 @@ -/* - * - * arch/arm/mach-u300/padmux.c - * - * - * Copyright (C) 2009 ST-Ericsson AB - * License terms: GNU General Public License (GPL) version 2 - * U300 PADMUX functions - * Author: Martin Persson <martin.persson@stericsson.com> - */ - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/device.h> -#include <linux/err.h> -#include <linux/errno.h> -#include <linux/io.h> -#include <linux/mutex.h> -#include <linux/string.h> -#include <linux/bug.h> -#include <linux/debugfs.h> -#include <linux/seq_file.h> -#include <mach/u300-regs.h> -#include <mach/syscon.h> -#include "padmux.h" - -static DEFINE_MUTEX(pmx_mutex); - -const u32 pmx_registers[] = { - (U300_SYSCON_VBASE + U300_SYSCON_PMC1LR), - (U300_SYSCON_VBASE + U300_SYSCON_PMC1HR), - (U300_SYSCON_VBASE + U300_SYSCON_PMC2R), - (U300_SYSCON_VBASE + U300_SYSCON_PMC3R), - (U300_SYSCON_VBASE + U300_SYSCON_PMC4R) -}; - -/* High level functionality */ - -/* Lazy dog: - * onmask = { - * {"PMC1LR" mask, "PMC1LR" value}, - * {"PMC1HR" mask, "PMC1HR" value}, - * {"PMC2R" mask, "PMC2R" value}, - * {"PMC3R" mask, "PMC3R" value}, - * {"PMC4R" mask, "PMC4R" value} - * } - */ -static struct pmx mmc_setting = { - .setting = U300_APP_PMX_MMC_SETTING, - .default_on = false, - .activated = false, - .name = "MMC", - .onmask = { - {U300_SYSCON_PMC1LR_MMCSD_MASK, - U300_SYSCON_PMC1LR_MMCSD_MMCSD}, - {0, 0}, - {0, 0}, - {0, 0}, - {U300_SYSCON_PMC4R_APP_MISC_12_MASK, - U300_SYSCON_PMC4R_APP_MISC_12_APP_GPIO} - }, -}; - -static struct pmx spi_setting = { - .setting = U300_APP_PMX_SPI_SETTING, - .default_on = false, - .activated = false, - .name = "SPI", - .onmask = {{0, 0}, - {U300_SYSCON_PMC1HR_APP_SPI_2_MASK | - U300_SYSCON_PMC1HR_APP_SPI_CS_1_MASK | - U300_SYSCON_PMC1HR_APP_SPI_CS_2_MASK, - U300_SYSCON_PMC1HR_APP_SPI_2_SPI | - U300_SYSCON_PMC1HR_APP_SPI_CS_1_SPI | - U300_SYSCON_PMC1HR_APP_SPI_CS_2_SPI}, - {0, 0}, - {0, 0}, - {0, 0} - }, -}; - -/* Available padmux settings */ -static struct pmx *pmx_settings[] = { - &mmc_setting, - &spi_setting, -}; - -static void update_registers(struct pmx *pmx, bool activate) -{ - u16 regval, val, mask; - int i; - - for (i = 0; i < ARRAY_SIZE(pmx_registers); i++) { - if (activate) - val = pmx->onmask[i].val; - else - val = 0; - - mask = pmx->onmask[i].mask; - if (mask != 0) { - regval = readw(pmx_registers[i]); - regval &= ~mask; - regval |= val; - writew(regval, pmx_registers[i]); - } - } -} - -struct pmx *pmx_get(struct device *dev, enum pmx_settings setting) -{ - int i; - struct pmx *pmx = ERR_PTR(-ENOENT); - - if (dev == NULL) - return ERR_PTR(-EINVAL); - - mutex_lock(&pmx_mutex); - for (i = 0; i < ARRAY_SIZE(pmx_settings); i++) { - - if (setting == pmx_settings[i]->setting) { - - if (pmx_settings[i]->dev != NULL) { - WARN(1, "padmux: required setting " - "in use by another consumer\n"); - } else { - pmx = pmx_settings[i]; - pmx->dev = dev; - dev_dbg(dev, "padmux: setting nr %d is now " - "bound to %s and ready to use\n", - setting, dev_name(dev)); - break; - } - } - } - mutex_unlock(&pmx_mutex); - - return pmx; -} -EXPORT_SYMBOL(pmx_get); - -int pmx_put(struct device *dev, struct pmx *pmx) -{ - int i; - int ret = -ENOENT; - - if (pmx == NULL || dev == NULL) - return -EINVAL; - - mutex_lock(&pmx_mutex); - for (i = 0; i < ARRAY_SIZE(pmx_settings); i++) { - - if (pmx->setting == pmx_settings[i]->setting) { - - if (dev != pmx->dev) { - WARN(1, "padmux: cannot release handle as " - "it is bound to another consumer\n"); - ret = -EINVAL; - break; - } else { - pmx_settings[i]->dev = NULL; - ret = 0; - break; - } - } - } - mutex_unlock(&pmx_mutex); - - return ret; -} -EXPORT_SYMBOL(pmx_put); - -int pmx_activate(struct device *dev, struct pmx *pmx) -{ - int i, j, ret; - ret = 0; - - if (pmx == NULL || dev == NULL) - return -EINVAL; - - mutex_lock(&pmx_mutex); - - /* Make sure the required bits are not used */ - for (i = 0; i < ARRAY_SIZE(pmx_settings); i++) { - - if (pmx_settings[i]->dev == NULL || pmx_settings[i] == pmx) - continue; - - for (j = 0; j < ARRAY_SIZE(pmx_registers); j++) { - - if (pmx_settings[i]->onmask[j].mask & pmx-> - onmask[j].mask) { - /* More than one entry on the same bits */ - WARN(1, "padmux: cannot activate " - "setting. Bit conflict with " - "an active setting\n"); - - ret = -EUSERS; - goto exit; - } - } - } - update_registers(pmx, true); - pmx->activated = true; - dev_dbg(dev, "padmux: setting nr %d is activated\n", - pmx->setting); - -exit: - mutex_unlock(&pmx_mutex); - return ret; -} -EXPORT_SYMBOL(pmx_activate); - -int pmx_deactivate(struct device *dev, struct pmx *pmx) -{ - int i; - int ret = -ENOENT; - - if (pmx == NULL || dev == NULL) - return -EINVAL; - - mutex_lock(&pmx_mutex); - for (i = 0; i < ARRAY_SIZE(pmx_settings); i++) { - - if (pmx_settings[i]->dev == NULL) - continue; - - if (pmx->setting == pmx_settings[i]->setting) { - - if (dev != pmx->dev) { - WARN(1, "padmux: cannot deactivate " - "pmx setting as it was activated " - "by another consumer\n"); - - ret = -EBUSY; - continue; - } else { - update_registers(pmx, false); - pmx_settings[i]->dev = NULL; - pmx->activated = false; - ret = 0; - dev_dbg(dev, "padmux: setting nr %d is deactivated", - pmx->setting); - break; - } - } - } - mutex_unlock(&pmx_mutex); - - return ret; -} -EXPORT_SYMBOL(pmx_deactivate); - -/* - * For internal use only. If it is to be exported, - * it should be reentrant. Notice that pmx_activate - * (i.e. runtime settings) always override default settings. - */ -static int pmx_set_default(void) -{ - /* Used to identify several entries on the same bits */ - u16 modbits[ARRAY_SIZE(pmx_registers)]; - - int i, j; - - memset(modbits, 0, ARRAY_SIZE(pmx_registers) * sizeof(u16)); - - for (i = 0; i < ARRAY_SIZE(pmx_settings); i++) { - - if (!pmx_settings[i]->default_on) - continue; - - for (j = 0; j < ARRAY_SIZE(pmx_registers); j++) { - - /* Make sure there is only one entry on the same bits */ - if (modbits[j] & pmx_settings[i]->onmask[j].mask) { - BUG(); - return -EUSERS; - } - modbits[j] |= pmx_settings[i]->onmask[j].mask; - } - update_registers(pmx_settings[i], true); - } - return 0; -} - -#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_U300_DEBUG)) -static int pmx_show(struct seq_file *s, void *data) -{ - int i; - seq_printf(s, "-------------------------------------------------\n"); - seq_printf(s, "SETTING BOUND TO DEVICE STATE\n"); - seq_printf(s, "-------------------------------------------------\n"); - mutex_lock(&pmx_mutex); - for (i = 0; i < ARRAY_SIZE(pmx_settings); i++) { - /* Format pmx and device name nicely */ - char cdp[33]; - int chars; - - chars = snprintf(&cdp[0], 17, "%s", pmx_settings[i]->name); - while (chars < 16) { - cdp[chars] = ' '; - chars++; - } - chars = snprintf(&cdp[16], 17, "%s", pmx_settings[i]->dev ? - dev_name(pmx_settings[i]->dev) : "N/A"); - while (chars < 16) { - cdp[chars+16] = ' '; - chars++; - } - cdp[32] = '\0'; - - seq_printf(s, - "%s\t%s\n", - &cdp[0], - pmx_settings[i]->activated ? - "ACTIVATED" : "DEACTIVATED" - ); - - } - mutex_unlock(&pmx_mutex); - return 0; -} - -static int pmx_open(struct inode *inode, struct file *file) -{ - return single_open(file, pmx_show, NULL); -} - -static const struct file_operations pmx_operations = { - .owner = THIS_MODULE, - .open = pmx_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int __init init_pmx_read_debugfs(void) -{ - /* Expose a simple debugfs interface to view pmx settings */ - (void) debugfs_create_file("padmux", S_IFREG | S_IRUGO, - NULL, NULL, - &pmx_operations); - return 0; -} - -/* - * This needs to come in after the core_initcall(), - * because debugfs is not available until - * the subsystems come up. - */ -module_init(init_pmx_read_debugfs); -#endif - -static int __init pmx_init(void) -{ - int ret; - - ret = pmx_set_default(); - - if (IS_ERR_VALUE(ret)) - pr_crit("padmux: default settings could not be set\n"); - - return 0; -} - -/* Should be initialized before consumers */ -core_initcall(pmx_init); diff --git a/arch/arm/mach-u300/padmux.h b/arch/arm/mach-u300/padmux.h deleted file mode 100644 index 6e8b86064097..000000000000 --- a/arch/arm/mach-u300/padmux.h +++ /dev/null @@ -1,39 +0,0 @@ -/* - * - * arch/arm/mach-u300/padmux.h - * - * - * Copyright (C) 2009 ST-Ericsson AB - * License terms: GNU General Public License (GPL) version 2 - * U300 PADMUX API - * Author: Martin Persson <martin.persson@stericsson.com> - */ - -#ifndef __MACH_U300_PADMUX_H -#define __MACH_U300_PADMUX_H - -enum pmx_settings { - U300_APP_PMX_MMC_SETTING, - U300_APP_PMX_SPI_SETTING -}; - -struct pmx_onmask { - u16 mask; /* Mask bits */ - u16 val; /* Value when active */ -}; - -struct pmx { - struct device *dev; - enum pmx_settings setting; - char *name; - bool activated; - bool default_on; - struct pmx_onmask onmask[]; -}; - -struct pmx *pmx_get(struct device *dev, enum pmx_settings setting); -int pmx_put(struct device *dev, struct pmx *pmx); -int pmx_activate(struct device *dev, struct pmx *pmx); -int pmx_deactivate(struct device *dev, struct pmx *pmx); - -#endif diff --git a/arch/arm/mach-u300/spi.c b/arch/arm/mach-u300/spi.c index 7b597e2b19e2..a1affacfa59c 100644 --- a/arch/arm/mach-u300/spi.c +++ b/arch/arm/mach-u300/spi.c @@ -14,8 +14,6 @@ #include <mach/coh901318.h> #include <mach/dma_channels.h> -#include "padmux.h" - /* * The following is for the actual devices on the SSP/SPI bus */ @@ -95,25 +93,7 @@ static struct pl022_ssp_controller ssp_platform_data = { void __init u300_spi_init(struct amba_device *adev) { - struct pmx *pmx; - adev->dev.platform_data = &ssp_platform_data; - /* - * Setup padmuxing for SPI. Since this must always be - * compiled into the kernel, pmx is never released. - */ - pmx = pmx_get(&adev->dev, U300_APP_PMX_SPI_SETTING); - - if (IS_ERR(pmx)) - dev_warn(&adev->dev, "Could not get padmux handle\n"); - else { - int ret; - - ret = pmx_activate(&adev->dev, pmx); - if (IS_ERR_VALUE(ret)) - dev_warn(&adev->dev, "Could not activate padmuxing\n"); - } - } void __init u300_spi_register_board_devices(void) diff --git a/arch/arm/mach-ux500/Makefile.boot b/arch/arm/mach-ux500/Makefile.boot index c7e75acfe6c9..ff0a4b5b0a82 100644 --- a/arch/arm/mach-ux500/Makefile.boot +++ b/arch/arm/mach-ux500/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c index a33df5f4c27a..eb5199102cfa 100644 --- a/arch/arm/mach-ux500/platsmp.c +++ b/arch/arm/mach-ux500/platsmp.c @@ -156,12 +156,10 @@ void __init smp_init_cpus(void) ncores = scu_base ? scu_get_core_count(scu_base) : 1; /* sanity check */ - if (ncores > NR_CPUS) { - printk(KERN_WARNING - "U8500: no. of cores (%d) greater than configured " - "maximum of %d - clipping\n", - ncores, NR_CPUS); - ncores = NR_CPUS; + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; } for (i = 0; i < ncores; i++) diff --git a/arch/arm/mach-versatile/Makefile.boot b/arch/arm/mach-versatile/Makefile.boot index c7e75acfe6c9..ff0a4b5b0a82 100644 --- a/arch/arm/mach-versatile/Makefile.boot +++ b/arch/arm/mach-versatile/Makefile.boot @@ -1,4 +1,4 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mach-vexpress/Makefile.boot b/arch/arm/mach-vexpress/Makefile.boot index 07c2d9c457ec..8630b3d10a4d 100644 --- a/arch/arm/mach-vexpress/Makefile.boot +++ b/arch/arm/mach-vexpress/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x60008000 + zreladdr-y += 0x60008000 params_phys-y := 0x60000100 initrd_phys-y := 0x60800000 diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c index bfd32f52c2db..2b1e836a76ed 100644 --- a/arch/arm/mach-vexpress/ct-ca9x4.c +++ b/arch/arm/mach-vexpress/ct-ca9x4.c @@ -221,6 +221,12 @@ static void ct_ca9x4_init_cpu_map(void) { int i, ncores = scu_get_core_count(MMIO_P2V(A9_MPCORE_SCU)); + if (ncores > nr_cpu_ids) { + pr_warn("SMP: %u cores greater than maximum (%u), clipping\n", + ncores, nr_cpu_ids); + ncores = nr_cpu_ids; + } + for (i = 0; i < ncores; ++i) set_cpu_possible(i, true); diff --git a/arch/arm/mach-vexpress/hotplug.c b/arch/arm/mach-vexpress/hotplug.c index ea4cbfb90a66..3668cf91d2de 100644 --- a/arch/arm/mach-vexpress/hotplug.c +++ b/arch/arm/mach-vexpress/hotplug.c @@ -13,6 +13,7 @@ #include <linux/smp.h> #include <asm/cacheflush.h> +#include <asm/system.h> extern volatile int pen_release; @@ -62,13 +63,7 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious) * code will have already disabled interrupts */ for (;;) { - /* - * here's the WFI - */ - asm(".word 0xe320f003\n" - : - : - : "memory", "cc"); + wfi(); if (pen_release == cpu) { /* diff --git a/arch/arm/mach-vexpress/include/mach/gpio.h b/arch/arm/mach-vexpress/include/mach/gpio.h new file mode 100644 index 000000000000..40a8c178f10d --- /dev/null +++ b/arch/arm/mach-vexpress/include/mach/gpio.h @@ -0,0 +1 @@ +/* empty */ diff --git a/arch/arm/mach-vexpress/include/mach/io.h b/arch/arm/mach-vexpress/include/mach/io.h index 748bb524ee71..13522d86685e 100644 --- a/arch/arm/mach-vexpress/include/mach/io.h +++ b/arch/arm/mach-vexpress/include/mach/io.h @@ -20,8 +20,6 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H -#define IO_SPACE_LIMIT 0xffffffff - #define __io(a) __typesafe_io(a) #define __mem_pci(a) (a) diff --git a/arch/arm/mach-vt8500/Makefile.boot b/arch/arm/mach-vt8500/Makefile.boot index a8acc4e24902..b79c41cdfdff 100644 --- a/arch/arm/mach-vt8500/Makefile.boot +++ b/arch/arm/mach-vt8500/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x01000000 diff --git a/arch/arm/mach-vt8500/include/mach/io.h b/arch/arm/mach-vt8500/include/mach/io.h index 9077239f78c9..46181eecf273 100644 --- a/arch/arm/mach-vt8500/include/mach/io.h +++ b/arch/arm/mach-vt8500/include/mach/io.h @@ -20,8 +20,6 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H -#define IO_SPACE_LIMIT 0xffff - #define __io(a) __typesafe_io((a) + 0xf0000000) #define __mem_pci(a) (a) diff --git a/arch/arm/mach-w90x900/Makefile.boot b/arch/arm/mach-w90x900/Makefile.boot index a057b546b6e5..6c3d421c2d11 100644 --- a/arch/arm/mach-w90x900/Makefile.boot +++ b/arch/arm/mach-w90x900/Makefile.boot @@ -1,3 +1,3 @@ -zreladdr-y := 0x00008000 +zreladdr-y += 0x00008000 params_phys-y := 0x00000100 diff --git a/arch/arm/mach-w90x900/cpu.c b/arch/arm/mach-w90x900/cpu.c index 83c56324a472..0a235e502330 100644 --- a/arch/arm/mach-w90x900/cpu.c +++ b/arch/arm/mach-w90x900/cpu.c @@ -60,7 +60,7 @@ static DEFINE_CLK(emc, 7); static DEFINE_SUBCLK(rmii, 2); static DEFINE_CLK(usbd, 8); static DEFINE_CLK(usbh, 9); -static DEFINE_CLK(g2d, 10);; +static DEFINE_CLK(g2d, 10); static DEFINE_CLK(pwm, 18); static DEFINE_CLK(ps2, 24); static DEFINE_CLK(kpi, 25); diff --git a/arch/arm/mach-zynq/Makefile.boot b/arch/arm/mach-zynq/Makefile.boot index 67039c3e0c48..760a0efe7580 100644 --- a/arch/arm/mach-zynq/Makefile.boot +++ b/arch/arm/mach-zynq/Makefile.boot @@ -1,3 +1,3 @@ - zreladdr-y := 0x00008000 + zreladdr-y += 0x00008000 params_phys-y := 0x00000100 initrd_phys-y := 0x00800000 diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index cfbcf8b95599..c335c76e0d88 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -86,16 +86,6 @@ core_param(alignment, ai_usermode, int, 0600); #define UM_FIXUP (1 << 1) #define UM_SIGNAL (1 << 2) -#ifdef CONFIG_PROC_FS -static const char *usermode_action[] = { - "ignored", - "warn", - "fixup", - "fixup+warn", - "signal", - "signal+warn" -}; - /* Return true if and only if the ARMv6 unaligned access model is in use. */ static bool cpu_is_v6_unaligned(void) { @@ -123,6 +113,16 @@ static int safe_usermode(int new_usermode, bool warn) return new_usermode; } +#ifdef CONFIG_PROC_FS +static const char *usermode_action[] = { + "ignored", + "warn", + "fixup", + "fixup+warn", + "signal", + "signal+warn" +}; + static int alignment_proc_show(struct seq_file *m, void *v) { seq_printf(m, "User:\t\t%lu\n", ai_user); diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 9ecfdb511951..8ac9e9f84790 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -16,9 +16,12 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/err.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/io.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <asm/cacheflush.h> #include <asm/hardware/cache-l2x0.h> @@ -26,15 +29,23 @@ #define CACHE_LINE_SIZE 32 static void __iomem *l2x0_base; -static DEFINE_SPINLOCK(l2x0_lock); +static DEFINE_RAW_SPINLOCK(l2x0_lock); static uint32_t l2x0_way_mask; /* Bitmask of active ways */ static uint32_t l2x0_size; +struct l2x0_regs l2x0_saved_regs; + +struct l2x0_of_data { + void (*setup)(const struct device_node *, __u32 *, __u32 *); + void (*save)(void); + void (*resume)(void); +}; + static inline void cache_wait_way(void __iomem *reg, unsigned long mask) { /* wait for cache operation by line or way to complete */ while (readl_relaxed(reg) & mask) - ; + cpu_relax(); } #ifdef CONFIG_CACHE_PL310 @@ -115,9 +126,9 @@ static void l2x0_cache_sync(void) { unsigned long flags; - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); cache_sync(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void __l2x0_flush_all(void) @@ -134,9 +145,9 @@ static void l2x0_flush_all(void) unsigned long flags; /* clean all ways */ - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); __l2x0_flush_all(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_clean_all(void) @@ -144,11 +155,11 @@ static void l2x0_clean_all(void) unsigned long flags; /* clean all ways */ - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_WAY); cache_wait_way(l2x0_base + L2X0_CLEAN_WAY, l2x0_way_mask); cache_sync(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_inv_all(void) @@ -156,13 +167,13 @@ static void l2x0_inv_all(void) unsigned long flags; /* invalidate all ways */ - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); /* Invalidating when L2 is enabled is a nono */ BUG_ON(readl(l2x0_base + L2X0_CTRL) & 1); writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY); cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask); cache_sync(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_inv_range(unsigned long start, unsigned long end) @@ -170,7 +181,7 @@ static void l2x0_inv_range(unsigned long start, unsigned long end) void __iomem *base = l2x0_base; unsigned long flags; - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); if (start & (CACHE_LINE_SIZE - 1)) { start &= ~(CACHE_LINE_SIZE - 1); debug_writel(0x03); @@ -195,13 +206,13 @@ static void l2x0_inv_range(unsigned long start, unsigned long end) } if (blk_end < end) { - spin_unlock_irqrestore(&l2x0_lock, flags); - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); } } cache_wait(base + L2X0_INV_LINE_PA, 1); cache_sync(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_clean_range(unsigned long start, unsigned long end) @@ -214,7 +225,7 @@ static void l2x0_clean_range(unsigned long start, unsigned long end) return; } - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); @@ -225,13 +236,13 @@ static void l2x0_clean_range(unsigned long start, unsigned long end) } if (blk_end < end) { - spin_unlock_irqrestore(&l2x0_lock, flags); - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); } } cache_wait(base + L2X0_CLEAN_LINE_PA, 1); cache_sync(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_flush_range(unsigned long start, unsigned long end) @@ -244,7 +255,7 @@ static void l2x0_flush_range(unsigned long start, unsigned long end) return; } - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); @@ -257,27 +268,27 @@ static void l2x0_flush_range(unsigned long start, unsigned long end) debug_writel(0x00); if (blk_end < end) { - spin_unlock_irqrestore(&l2x0_lock, flags); - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); } } cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1); cache_sync(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_disable(void) { unsigned long flags; - spin_lock_irqsave(&l2x0_lock, flags); + raw_spin_lock_irqsave(&l2x0_lock, flags); __l2x0_flush_all(); writel_relaxed(0, l2x0_base + L2X0_CTRL); dsb(); - spin_unlock_irqrestore(&l2x0_lock, flags); + raw_spin_unlock_irqrestore(&l2x0_lock, flags); } -static void __init l2x0_unlock(__u32 cache_id) +static void l2x0_unlock(__u32 cache_id) { int lockregs; int i; @@ -353,6 +364,8 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) /* l2x0 controller is disabled */ writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL); + l2x0_saved_regs.aux_ctrl = aux; + l2x0_inv_all(); /* enable L2X0 */ @@ -372,3 +385,202 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask) printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n", ways, cache_id, aux, l2x0_size); } + +#ifdef CONFIG_OF +static void __init l2x0_of_setup(const struct device_node *np, + __u32 *aux_val, __u32 *aux_mask) +{ + u32 data[2] = { 0, 0 }; + u32 tag = 0; + u32 dirty = 0; + u32 val = 0, mask = 0; + + of_property_read_u32(np, "arm,tag-latency", &tag); + if (tag) { + mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK; + val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT; + } + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1]) { + mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK | + L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK; + val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) | + ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT); + } + + of_property_read_u32(np, "arm,dirty-latency", &dirty); + if (dirty) { + mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK; + val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT; + } + + *aux_val &= ~mask; + *aux_val |= val; + *aux_mask &= ~mask; +} + +static void __init pl310_of_setup(const struct device_node *np, + __u32 *aux_val, __u32 *aux_mask) +{ + u32 data[3] = { 0, 0, 0 }; + u32 tag[3] = { 0, 0, 0 }; + u32 filter[2] = { 0, 0 }; + + of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag)); + if (tag[0] && tag[1] && tag[2]) + writel_relaxed( + ((tag[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | + ((tag[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | + ((tag[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), + l2x0_base + L2X0_TAG_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,data-latency", + data, ARRAY_SIZE(data)); + if (data[0] && data[1] && data[2]) + writel_relaxed( + ((data[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) | + ((data[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) | + ((data[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT), + l2x0_base + L2X0_DATA_LATENCY_CTRL); + + of_property_read_u32_array(np, "arm,filter-ranges", + filter, ARRAY_SIZE(filter)); + if (filter[1]) { + writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M), + l2x0_base + L2X0_ADDR_FILTER_END); + writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L2X0_ADDR_FILTER_EN, + l2x0_base + L2X0_ADDR_FILTER_START); + } +} + +static void __init pl310_save(void) +{ + u32 l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + l2x0_saved_regs.tag_latency = readl_relaxed(l2x0_base + + L2X0_TAG_LATENCY_CTRL); + l2x0_saved_regs.data_latency = readl_relaxed(l2x0_base + + L2X0_DATA_LATENCY_CTRL); + l2x0_saved_regs.filter_end = readl_relaxed(l2x0_base + + L2X0_ADDR_FILTER_END); + l2x0_saved_regs.filter_start = readl_relaxed(l2x0_base + + L2X0_ADDR_FILTER_START); + + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { + /* + * From r2p0, there is Prefetch offset/control register + */ + l2x0_saved_regs.prefetch_ctrl = readl_relaxed(l2x0_base + + L2X0_PREFETCH_CTRL); + /* + * From r3p0, there is Power control register + */ + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) + l2x0_saved_regs.pwr_ctrl = readl_relaxed(l2x0_base + + L2X0_POWER_CTRL); + } +} + +static void l2x0_resume(void) +{ + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + /* restore aux ctrl and enable l2 */ + l2x0_unlock(readl_relaxed(l2x0_base + L2X0_CACHE_ID)); + + writel_relaxed(l2x0_saved_regs.aux_ctrl, l2x0_base + + L2X0_AUX_CTRL); + + l2x0_inv_all(); + + writel_relaxed(1, l2x0_base + L2X0_CTRL); + } +} + +static void pl310_resume(void) +{ + u32 l2x0_revision; + + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + /* restore pl310 setup */ + writel_relaxed(l2x0_saved_regs.tag_latency, + l2x0_base + L2X0_TAG_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.data_latency, + l2x0_base + L2X0_DATA_LATENCY_CTRL); + writel_relaxed(l2x0_saved_regs.filter_end, + l2x0_base + L2X0_ADDR_FILTER_END); + writel_relaxed(l2x0_saved_regs.filter_start, + l2x0_base + L2X0_ADDR_FILTER_START); + + l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & + L2X0_CACHE_ID_RTL_MASK; + + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) { + writel_relaxed(l2x0_saved_regs.prefetch_ctrl, + l2x0_base + L2X0_PREFETCH_CTRL); + if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0) + writel_relaxed(l2x0_saved_regs.pwr_ctrl, + l2x0_base + L2X0_POWER_CTRL); + } + } + + l2x0_resume(); +} + +static const struct l2x0_of_data pl310_data = { + pl310_of_setup, + pl310_save, + pl310_resume, +}; + +static const struct l2x0_of_data l2x0_data = { + l2x0_of_setup, + NULL, + l2x0_resume, +}; + +static const struct of_device_id l2x0_ids[] __initconst = { + { .compatible = "arm,pl310-cache", .data = (void *)&pl310_data }, + { .compatible = "arm,l220-cache", .data = (void *)&l2x0_data }, + { .compatible = "arm,l210-cache", .data = (void *)&l2x0_data }, + {} +}; + +int __init l2x0_of_init(__u32 aux_val, __u32 aux_mask) +{ + struct device_node *np; + struct l2x0_of_data *data; + struct resource res; + + np = of_find_matching_node(NULL, l2x0_ids); + if (!np) + return -ENODEV; + + if (of_address_to_resource(np, 0, &res)) + return -ENODEV; + + l2x0_base = ioremap(res.start, resource_size(&res)); + if (!l2x0_base) + return -ENOMEM; + + l2x0_saved_regs.phy_base = res.start; + + data = of_match_node(l2x0_ids, np)->data; + + /* L2 configuration can only be changed if the cache is disabled */ + if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & 1)) { + if (data->setup) + data->setup(np, &aux_val, &aux_mask); + } + + if (data->save) + data->save(); + + l2x0_init(l2x0_base, aux_val, aux_mask); + + outer_cache.resume = data->resume; + return 0; +} +#endif diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c index b0ee9ba3cfab..93aac068da94 100644 --- a/arch/arm/mm/context.c +++ b/arch/arm/mm/context.c @@ -16,7 +16,7 @@ #include <asm/mmu_context.h> #include <asm/tlbflush.h> -static DEFINE_SPINLOCK(cpu_asid_lock); +static DEFINE_RAW_SPINLOCK(cpu_asid_lock); unsigned int cpu_last_asid = ASID_FIRST_VERSION; #ifdef CONFIG_SMP DEFINE_PER_CPU(struct mm_struct *, current_mm); @@ -31,7 +31,7 @@ DEFINE_PER_CPU(struct mm_struct *, current_mm); void __init_new_context(struct task_struct *tsk, struct mm_struct *mm) { mm->context.id = 0; - spin_lock_init(&mm->context.id_lock); + raw_spin_lock_init(&mm->context.id_lock); } static void flush_context(void) @@ -58,7 +58,7 @@ static void set_mm_context(struct mm_struct *mm, unsigned int asid) * the broadcast. This function is also called via IPI so the * mm->context.id_lock has to be IRQ-safe. */ - spin_lock_irqsave(&mm->context.id_lock, flags); + raw_spin_lock_irqsave(&mm->context.id_lock, flags); if (likely((mm->context.id ^ cpu_last_asid) >> ASID_BITS)) { /* * Old version of ASID found. Set the new one and @@ -67,7 +67,7 @@ static void set_mm_context(struct mm_struct *mm, unsigned int asid) mm->context.id = asid; cpumask_clear(mm_cpumask(mm)); } - spin_unlock_irqrestore(&mm->context.id_lock, flags); + raw_spin_unlock_irqrestore(&mm->context.id_lock, flags); /* * Set the mm_cpumask(mm) bit for the current CPU. @@ -117,7 +117,7 @@ void __new_context(struct mm_struct *mm) { unsigned int asid; - spin_lock(&cpu_asid_lock); + raw_spin_lock(&cpu_asid_lock); #ifdef CONFIG_SMP /* * Check the ASID again, in case the change was broadcast from @@ -125,7 +125,7 @@ void __new_context(struct mm_struct *mm) */ if (unlikely(((mm->context.id ^ cpu_last_asid) >> ASID_BITS) == 0)) { cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); - spin_unlock(&cpu_asid_lock); + raw_spin_unlock(&cpu_asid_lock); return; } #endif @@ -153,5 +153,5 @@ void __new_context(struct mm_struct *mm) } set_mm_context(mm, asid); - spin_unlock(&cpu_asid_lock); + raw_spin_unlock(&cpu_asid_lock); } diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c index b8061519ce77..7d0a8c230342 100644 --- a/arch/arm/mm/copypage-v4mc.c +++ b/arch/arm/mm/copypage-v4mc.c @@ -30,7 +30,7 @@ #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \ L_PTE_MT_MINICACHE) -static DEFINE_SPINLOCK(minicache_lock); +static DEFINE_RAW_SPINLOCK(minicache_lock); /* * ARMv4 mini-dcache optimised copy_user_highpage @@ -76,14 +76,14 @@ void v4_mc_copy_user_highpage(struct page *to, struct page *from, if (!test_and_set_bit(PG_dcache_clean, &from->flags)) __flush_dcache_page(page_mapping(from), from); - spin_lock(&minicache_lock); + raw_spin_lock(&minicache_lock); set_pte_ext(TOP_PTE(0xffff8000), pfn_pte(page_to_pfn(from), minicache_pgprot), 0); flush_tlb_kernel_page(0xffff8000); mc_copy_user_page((void *)0xffff8000, kto); - spin_unlock(&minicache_lock); + raw_spin_unlock(&minicache_lock); kunmap_atomic(kto, KM_USER1); } diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c index 63cca0097130..3d9a1552cef6 100644 --- a/arch/arm/mm/copypage-v6.c +++ b/arch/arm/mm/copypage-v6.c @@ -27,7 +27,7 @@ #define from_address (0xffff8000) #define to_address (0xffffc000) -static DEFINE_SPINLOCK(v6_lock); +static DEFINE_RAW_SPINLOCK(v6_lock); /* * Copy the user page. No aliasing to deal with so we can just @@ -88,7 +88,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to, * Now copy the page using the same cache colour as the * pages ultimate destination. */ - spin_lock(&v6_lock); + raw_spin_lock(&v6_lock); set_pte_ext(TOP_PTE(from_address) + offset, pfn_pte(page_to_pfn(from), PAGE_KERNEL), 0); set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(to), PAGE_KERNEL), 0); @@ -101,7 +101,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to, copy_page((void *)kto, (void *)kfrom); - spin_unlock(&v6_lock); + raw_spin_unlock(&v6_lock); } /* @@ -121,13 +121,13 @@ static void v6_clear_user_highpage_aliasing(struct page *page, unsigned long vad * Now clear the page using the same cache colour as * the pages ultimate destination. */ - spin_lock(&v6_lock); + raw_spin_lock(&v6_lock); set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(page), PAGE_KERNEL), 0); flush_tlb_kernel_page(to); clear_page((void *)to); - spin_unlock(&v6_lock); + raw_spin_unlock(&v6_lock); } struct cpu_user_fns v6_user_fns __initdata = { diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c index 649bbcd325bf..610c24ced310 100644 --- a/arch/arm/mm/copypage-xscale.c +++ b/arch/arm/mm/copypage-xscale.c @@ -32,7 +32,7 @@ #define minicache_pgprot __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | \ L_PTE_MT_MINICACHE) -static DEFINE_SPINLOCK(minicache_lock); +static DEFINE_RAW_SPINLOCK(minicache_lock); /* * XScale mini-dcache optimised copy_user_highpage @@ -98,14 +98,14 @@ void xscale_mc_copy_user_highpage(struct page *to, struct page *from, if (!test_and_set_bit(PG_dcache_clean, &from->flags)) __flush_dcache_page(page_mapping(from), from); - spin_lock(&minicache_lock); + raw_spin_lock(&minicache_lock); set_pte_ext(TOP_PTE(COPYPAGE_MINICACHE), pfn_pte(page_to_pfn(from), minicache_pgprot), 0); flush_tlb_kernel_page(COPYPAGE_MINICACHE); mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto); - spin_unlock(&minicache_lock); + raw_spin_unlock(&minicache_lock); kunmap_atomic(kto, KM_USER1); } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 01f5987eb1ad..e4e7f6cba1ab 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -120,9 +120,8 @@ static void __dma_free_buffer(struct page *page, size_t size) #ifdef CONFIG_MMU - #define CONSISTENT_OFFSET(x) (((unsigned long)(x) - consistent_base) >> PAGE_SHIFT) -#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - consistent_base) >> PGDIR_SHIFT) +#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - consistent_base) >> PMD_SHIFT) /* * These are the page tables (2MB each) covering uncached, DMA consistent allocations @@ -206,7 +205,7 @@ static int __init consistent_init(void) } consistent_pte[i++] = pte; - base += (1 << PGDIR_SHIFT); + base += PMD_SIZE; } while (base < CONSISTENT_END); return ret; diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 3b5ea68acbb8..aa33949fef60 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -20,6 +20,7 @@ #include <linux/highmem.h> #include <linux/perf_event.h> +#include <asm/exception.h> #include <asm/system.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 34409a08ba0d..04e9a92bb47a 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -496,6 +496,13 @@ static void __init free_unused_memmap(struct meminfo *mi) */ bank_start = min(bank_start, ALIGN(prev_bank_end, PAGES_PER_SECTION)); +#else + /* + * Align down here since the VM subsystem insists that the + * memmap entries are valid from the bank start aligned to + * MAX_ORDER_NR_PAGES. + */ + bank_start = round_down(bank_start, MAX_ORDER_NR_PAGES); #endif /* * If we had a previous bank, and there is a space diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index ab506272b2d3..bdb248c4f55c 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -289,6 +289,27 @@ __arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype) } EXPORT_SYMBOL(__arm_ioremap); +/* + * Remap an arbitrary physical address space into the kernel virtual + * address space as memory. Needed when the kernel wants to execute + * code in external memory. This is needed for reprogramming source + * clocks that would affect normal memory for example. Please see + * CONFIG_GENERIC_ALLOCATOR for allocating external memory. + */ +void __iomem * +__arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached) +{ + unsigned int mtype; + + if (cached) + mtype = MT_MEMORY; + else + mtype = MT_MEMORY_NONCACHED; + + return __arm_ioremap_caller(phys_addr, size, mtype, + __builtin_return_address(0)); +} + void __iounmap(volatile void __iomem *io_addr) { void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr); diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index 010566799c80..ad7cce3bc431 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -12,8 +12,8 @@ static inline pmd_t *pmd_off_k(unsigned long virt) struct mem_type { pteval_t prot_pte; - unsigned int prot_l1; - unsigned int prot_sect; + pmdval_t prot_l1; + pmdval_t prot_sect; unsigned int domain; }; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 594d677b92c8..dc8c550e6cbd 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -60,7 +60,7 @@ EXPORT_SYMBOL(pgprot_kernel); struct cachepolicy { const char policy[16]; unsigned int cr_mask; - unsigned int pmd; + pmdval_t pmd; pteval_t pte; }; @@ -273,6 +273,14 @@ static struct mem_type mem_types[] = { .prot_l1 = PMD_TYPE_TABLE, .domain = DOMAIN_KERNEL, }, + [MT_MEMORY_SO] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_MT_UNCACHED, + .prot_l1 = PMD_TYPE_TABLE, + .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_S | + PMD_SECT_UNCACHED | PMD_SECT_XN, + .domain = DOMAIN_KERNEL, + }, }; const struct mem_type *get_mem_type(unsigned int type) @@ -288,7 +296,7 @@ static void __init build_mem_type_table(void) { struct cachepolicy *cp; unsigned int cr = get_cr(); - unsigned int user_pgprot, kern_pgprot, vecs_pgprot; + pteval_t user_pgprot, kern_pgprot, vecs_pgprot; int cpu_arch = cpu_architecture(); int i; @@ -863,14 +871,14 @@ static inline void prepare_page_table(void) /* * Clear out all the mappings below the kernel image. */ - for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE) + for (addr = 0; addr < MODULES_VADDR; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); #ifdef CONFIG_XIP_KERNEL /* The XIP kernel is mapped in the module area -- skip over it */ - addr = ((unsigned long)_etext + PGDIR_SIZE - 1) & PGDIR_MASK; + addr = ((unsigned long)_etext + PMD_SIZE - 1) & PMD_MASK; #endif - for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE) + for ( ; addr < PAGE_OFFSET; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); /* @@ -885,10 +893,12 @@ static inline void prepare_page_table(void) * memory bank, up to the end of the vmalloc region. */ for (addr = __phys_to_virt(end); - addr < VMALLOC_END; addr += PGDIR_SIZE) + addr < VMALLOC_END; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); } +#define SWAPPER_PG_DIR_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) + /* * Reserve the special regions of memory */ @@ -898,7 +908,7 @@ void __init arm_mm_memblock_reserve(void) * Reserve the page tables. These are already in use, * and can only be in node 0. */ - memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t)); + memblock_reserve(__pa(swapper_pg_dir), SWAPPER_PG_DIR_SIZE); #ifdef CONFIG_SA1111 /* @@ -926,7 +936,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc) */ vectors_page = early_alloc(PAGE_SIZE); - for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE) + for (addr = VMALLOC_END; addr; addr += PMD_SIZE) pmd_clear(pmd_off_k(addr)); /* diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S index 2e6849b41f66..88fb3d9e0640 100644 --- a/arch/arm/mm/proc-arm920.S +++ b/arch/arm/mm/proc-arm920.S @@ -379,31 +379,26 @@ ENTRY(cpu_arm920_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm920_suspend_size -.equ cpu_arm920_suspend_size, 4 * 4 +.equ cpu_arm920_suspend_size, 4 * 3 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_arm920_do_suspend) - stmfd sp!, {r4 - r7, lr} + stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID mrc p15, 0, r5, c3, c0, 0 @ Domain ID - mrc p15, 0, r6, c2, c0, 0 @ TTB address - mrc p15, 0, r7, c1, c0, 0 @ Control register - stmia r0, {r4 - r7} - ldmfd sp!, {r4 - r7, pc} + mrc p15, 0, r6, c1, c0, 0 @ Control register + stmia r0, {r4 - r6} + ldmfd sp!, {r4 - r6, pc} ENDPROC(cpu_arm920_do_suspend) ENTRY(cpu_arm920_do_resume) mov ip, #0 mcr p15, 0, ip, c8, c7, 0 @ invalidate I+D TLBs mcr p15, 0, ip, c7, c7, 0 @ invalidate I+D caches - ldmia r0, {r4 - r7} + ldmia r0, {r4 - r6} mcr p15, 0, r4, c13, c0, 0 @ PID mcr p15, 0, r5, c3, c0, 0 @ Domain ID - mcr p15, 0, r6, c2, c0, 0 @ TTB address - mov r0, r7 @ control register - mov r2, r6, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE + mcr p15, 0, r1, c2, c0, 0 @ TTB address + mov r0, r6 @ control register b cpu_resume_mmu ENDPROC(cpu_arm920_do_resume) #endif diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S index cd8f79c3a282..9f8fd91f918a 100644 --- a/arch/arm/mm/proc-arm926.S +++ b/arch/arm/mm/proc-arm926.S @@ -394,31 +394,26 @@ ENTRY(cpu_arm926_set_pte_ext) /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */ .globl cpu_arm926_suspend_size -.equ cpu_arm926_suspend_size, 4 * 4 +.equ cpu_arm926_suspend_size, 4 * 3 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_arm926_do_suspend) - stmfd sp!, {r4 - r7, lr} + stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c13, c0, 0 @ PID mrc p15, 0, r5, c3, c0, 0 @ Domain ID - mrc p15, 0, r6, c2, c0, 0 @ TTB address - mrc p15, 0, r7, c1, c0, 0 @ Control register - stmia r0, {r4 - r7} - ldmfd sp!, {r4 - r7, pc} + mrc p15, 0, r6, c1, c0, 0 @ Control register + stmia r0, {r4 - r6} + ldmfd sp!, {r4 - r6, pc} ENDPROC(cpu_arm926_do_suspend) ENTRY(cpu_arm926_do_resume) mov ip, #0 mcr p15, 0, ip, c8, c7, 0 @ invalidate I+D TLBs mcr p15, 0, ip, c7, c7, 0 @ invalidate I+D caches - ldmia r0, {r4 - r7} + ldmia r0, {r4 - r6} mcr p15, 0, r4, c13, c0, 0 @ PID mcr p15, 0, r5, c3, c0, 0 @ Domain ID - mcr p15, 0, r6, c2, c0, 0 @ TTB address - mov r0, r7 @ control register - mov r2, r6, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | PMD_BIT4 | PMD_SECT_AP_WRITE + mcr p15, 0, r1, c2, c0, 0 @ TTB address + mov r0, r6 @ control register b cpu_resume_mmu ENDPROC(cpu_arm926_do_resume) #endif diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S index 69e7f2ef7384..7d91545d089b 100644 --- a/arch/arm/mm/proc-sa1100.S +++ b/arch/arm/mm/proc-sa1100.S @@ -168,20 +168,19 @@ ENTRY(cpu_sa1100_set_pte_ext) mov pc, lr .globl cpu_sa1100_suspend_size -.equ cpu_sa1100_suspend_size, 4*4 +.equ cpu_sa1100_suspend_size, 4 * 3 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_sa1100_do_suspend) - stmfd sp!, {r4 - r7, lr} + stmfd sp!, {r4 - r6, lr} mrc p15, 0, r4, c3, c0, 0 @ domain ID - mrc p15, 0, r5, c2, c0, 0 @ translation table base addr - mrc p15, 0, r6, c13, c0, 0 @ PID - mrc p15, 0, r7, c1, c0, 0 @ control reg - stmia r0, {r4 - r7} @ store cp regs - ldmfd sp!, {r4 - r7, pc} + mrc p15, 0, r5, c13, c0, 0 @ PID + mrc p15, 0, r6, c1, c0, 0 @ control reg + stmia r0, {r4 - r6} @ store cp regs + ldmfd sp!, {r4 - r6, pc} ENDPROC(cpu_sa1100_do_suspend) ENTRY(cpu_sa1100_do_resume) - ldmia r0, {r4 - r7} @ load cp regs + ldmia r0, {r4 - r6} @ load cp regs mov ip, #0 mcr p15, 0, ip, c8, c7, 0 @ flush I+D TLBs mcr p15, 0, ip, c7, c7, 0 @ flush I&D cache @@ -189,13 +188,9 @@ ENTRY(cpu_sa1100_do_resume) mcr p15, 0, ip, c9, c0, 5 @ allow user space to use RB mcr p15, 0, r4, c3, c0, 0 @ domain ID - mcr p15, 0, r5, c2, c0, 0 @ translation table base addr - mcr p15, 0, r6, c13, c0, 0 @ PID - mov r0, r7 @ control register - mov r2, r5, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE + mcr p15, 0, r1, c2, c0, 0 @ translation table base addr + mcr p15, 0, r5, c13, c0, 0 @ PID + mov r0, r6 @ control register b cpu_resume_mmu ENDPROC(cpu_sa1100_do_resume) #endif diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index a923aa0fd00d..d061d2fa5506 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -128,20 +128,18 @@ ENTRY(cpu_v6_set_pte_ext) /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */ .globl cpu_v6_suspend_size -.equ cpu_v6_suspend_size, 4 * 8 +.equ cpu_v6_suspend_size, 4 * 6 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_v6_do_suspend) - stmfd sp!, {r4 - r11, lr} + stmfd sp!, {r4 - r9, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID - mrc p15, 0, r5, c13, c0, 1 @ Context ID - mrc p15, 0, r6, c3, c0, 0 @ Domain ID - mrc p15, 0, r7, c2, c0, 0 @ Translation table base 0 - mrc p15, 0, r8, c2, c0, 1 @ Translation table base 1 - mrc p15, 0, r9, c1, c0, 1 @ auxiliary control register - mrc p15, 0, r10, c1, c0, 2 @ co-processor access control - mrc p15, 0, r11, c1, c0, 0 @ control register - stmia r0, {r4 - r11} - ldmfd sp!, {r4- r11, pc} + mrc p15, 0, r5, c3, c0, 0 @ Domain ID + mrc p15, 0, r6, c2, c0, 1 @ Translation table base 1 + mrc p15, 0, r7, c1, c0, 1 @ auxiliary control register + mrc p15, 0, r8, c1, c0, 2 @ co-processor access control + mrc p15, 0, r9, c1, c0, 0 @ control register + stmia r0, {r4 - r9} + ldmfd sp!, {r4- r9, pc} ENDPROC(cpu_v6_do_suspend) ENTRY(cpu_v6_do_resume) @@ -150,25 +148,21 @@ ENTRY(cpu_v6_do_resume) mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache mcr p15, 0, ip, c7, c15, 0 @ clean+invalidate cache mcr p15, 0, ip, c7, c10, 4 @ drain write buffer - ldmia r0, {r4 - r11} + mcr p15, 0, ip, c13, c0, 1 @ set reserved context ID + ldmia r0, {r4 - r9} mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID - mcr p15, 0, r5, c13, c0, 1 @ Context ID - mcr p15, 0, r6, c3, c0, 0 @ Domain ID - mcr p15, 0, r7, c2, c0, 0 @ Translation table base 0 - mcr p15, 0, r8, c2, c0, 1 @ Translation table base 1 - mcr p15, 0, r9, c1, c0, 1 @ auxiliary control register - mcr p15, 0, r10, c1, c0, 2 @ co-processor access control + mcr p15, 0, r5, c3, c0, 0 @ Domain ID + ALT_SMP(orr r1, r1, #TTB_FLAGS_SMP) + ALT_UP(orr r1, r1, #TTB_FLAGS_UP) + mcr p15, 0, r1, c2, c0, 0 @ Translation table base 0 + mcr p15, 0, r6, c2, c0, 1 @ Translation table base 1 + mcr p15, 0, r7, c1, c0, 1 @ auxiliary control register + mcr p15, 0, r8, c1, c0, 2 @ co-processor access control mcr p15, 0, ip, c2, c0, 2 @ TTB control register mcr p15, 0, ip, c7, c5, 4 @ ISB - mov r0, r11 @ control register - mov r2, r7, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, cpu_resume_l1_flags + mov r0, r9 @ control register b cpu_resume_mmu ENDPROC(cpu_v6_do_resume) -cpu_resume_l1_flags: - ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP) - ALT_UP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP) #endif string cpu_v6_name, "ARMv6-compatible processor" diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 9049c0764db2..2c559ac38142 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -217,56 +217,50 @@ ENDPROC(cpu_v7_set_pte_ext) /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */ .globl cpu_v7_suspend_size -.equ cpu_v7_suspend_size, 4 * 9 -#ifdef CONFIG_PM_SLEEP +.equ cpu_v7_suspend_size, 4 * 7 +#ifdef CONFIG_ARM_CPU_SUSPEND ENTRY(cpu_v7_do_suspend) - stmfd sp!, {r4 - r11, lr} + stmfd sp!, {r4 - r10, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID - mrc p15, 0, r5, c13, c0, 1 @ Context ID - mrc p15, 0, r6, c13, c0, 3 @ User r/o thread ID - stmia r0!, {r4 - r6} + mrc p15, 0, r5, c13, c0, 3 @ User r/o thread ID + stmia r0!, {r4 - r5} mrc p15, 0, r6, c3, c0, 0 @ Domain ID - mrc p15, 0, r7, c2, c0, 0 @ TTB 0 - mrc p15, 0, r8, c2, c0, 1 @ TTB 1 - mrc p15, 0, r9, c1, c0, 0 @ Control register - mrc p15, 0, r10, c1, c0, 1 @ Auxiliary control register - mrc p15, 0, r11, c1, c0, 2 @ Co-processor access control - stmia r0, {r6 - r11} - ldmfd sp!, {r4 - r11, pc} + mrc p15, 0, r7, c2, c0, 1 @ TTB 1 + mrc p15, 0, r8, c1, c0, 0 @ Control register + mrc p15, 0, r9, c1, c0, 1 @ Auxiliary control register + mrc p15, 0, r10, c1, c0, 2 @ Co-processor access control + stmia r0, {r6 - r10} + ldmfd sp!, {r4 - r10, pc} ENDPROC(cpu_v7_do_suspend) ENTRY(cpu_v7_do_resume) mov ip, #0 mcr p15, 0, ip, c8, c7, 0 @ invalidate TLBs mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache - ldmia r0!, {r4 - r6} + mcr p15, 0, ip, c13, c0, 1 @ set reserved context ID + ldmia r0!, {r4 - r5} mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID - mcr p15, 0, r5, c13, c0, 1 @ Context ID - mcr p15, 0, r6, c13, c0, 3 @ User r/o thread ID - ldmia r0, {r6 - r11} + mcr p15, 0, r5, c13, c0, 3 @ User r/o thread ID + ldmia r0, {r6 - r10} mcr p15, 0, r6, c3, c0, 0 @ Domain ID - mcr p15, 0, r7, c2, c0, 0 @ TTB 0 - mcr p15, 0, r8, c2, c0, 1 @ TTB 1 + ALT_SMP(orr r1, r1, #TTB_FLAGS_SMP) + ALT_UP(orr r1, r1, #TTB_FLAGS_UP) + mcr p15, 0, r1, c2, c0, 0 @ TTB 0 + mcr p15, 0, r7, c2, c0, 1 @ TTB 1 mcr p15, 0, ip, c2, c0, 2 @ TTB control register mrc p15, 0, r4, c1, c0, 1 @ Read Auxiliary control register - teq r4, r10 @ Is it already set? - mcrne p15, 0, r10, c1, c0, 1 @ No, so write it - mcr p15, 0, r11, c1, c0, 2 @ Co-processor access control + teq r4, r9 @ Is it already set? + mcrne p15, 0, r9, c1, c0, 1 @ No, so write it + mcr p15, 0, r10, c1, c0, 2 @ Co-processor access control ldr r4, =PRRR @ PRRR ldr r5, =NMRR @ NMRR mcr p15, 0, r4, c10, c2, 0 @ write PRRR mcr p15, 0, r5, c10, c2, 1 @ write NMRR isb dsb - mov r0, r9 @ control register - mov r2, r7, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, cpu_resume_l1_flags + mov r0, r8 @ control register b cpu_resume_mmu ENDPROC(cpu_v7_do_resume) -cpu_resume_l1_flags: - ALT_SMP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_SMP) - ALT_UP(.long PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_FLAGS_UP) #endif __CPUINIT diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S index 755e1bf22681..abf0507a08ae 100644 --- a/arch/arm/mm/proc-xsc3.S +++ b/arch/arm/mm/proc-xsc3.S @@ -406,24 +406,23 @@ ENTRY(cpu_xsc3_set_pte_ext) .align .globl cpu_xsc3_suspend_size -.equ cpu_xsc3_suspend_size, 4 * 7 +.equ cpu_xsc3_suspend_size, 4 * 6 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_xsc3_do_suspend) - stmfd sp!, {r4 - r10, lr} + stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode mrc p15, 0, r5, c15, c1, 0 @ CP access reg mrc p15, 0, r6, c13, c0, 0 @ PID mrc p15, 0, r7, c3, c0, 0 @ domain ID - mrc p15, 0, r8, c2, c0, 0 @ translation table base addr - mrc p15, 0, r9, c1, c0, 1 @ auxiliary control reg - mrc p15, 0, r10, c1, c0, 0 @ control reg + mrc p15, 0, r8, c1, c0, 1 @ auxiliary control reg + mrc p15, 0, r9, c1, c0, 0 @ control reg bic r4, r4, #2 @ clear frequency change bit - stmia r0, {r4 - r10} @ store cp regs - ldmia sp!, {r4 - r10, pc} + stmia r0, {r4 - r9} @ store cp regs + ldmia sp!, {r4 - r9, pc} ENDPROC(cpu_xsc3_do_suspend) ENTRY(cpu_xsc3_do_resume) - ldmia r0, {r4 - r10} @ load cp regs + ldmia r0, {r4 - r9} @ load cp regs mov ip, #0 mcr p15, 0, ip, c7, c7, 0 @ invalidate I & D caches, BTB mcr p15, 0, ip, c7, c10, 4 @ drain write (&fill) buffer @@ -433,15 +432,10 @@ ENTRY(cpu_xsc3_do_resume) mcr p15, 0, r5, c15, c1, 0 @ CP access reg mcr p15, 0, r6, c13, c0, 0 @ PID mcr p15, 0, r7, c3, c0, 0 @ domain ID - mcr p15, 0, r8, c2, c0, 0 @ translation table base addr - mcr p15, 0, r9, c1, c0, 1 @ auxiliary control reg - - @ temporarily map resume_turn_on_mmu into the page table, - @ otherwise prefetch abort occurs after MMU is turned on - mov r0, r10 @ control register - mov r2, r8, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, =0x542e @ section flags + orr r1, r1, #0x18 @ cache the page table in L2 + mcr p15, 0, r1, c2, c0, 0 @ translation table base addr + mcr p15, 0, r8, c1, c0, 1 @ auxiliary control reg + mov r0, r9 @ control register b cpu_resume_mmu ENDPROC(cpu_xsc3_do_resume) #endif diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S index fbc06e55b87a..3277904bebaf 100644 --- a/arch/arm/mm/proc-xscale.S +++ b/arch/arm/mm/proc-xscale.S @@ -520,24 +520,23 @@ ENTRY(cpu_xscale_set_pte_ext) .align .globl cpu_xscale_suspend_size -.equ cpu_xscale_suspend_size, 4 * 7 +.equ cpu_xscale_suspend_size, 4 * 6 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_xscale_do_suspend) - stmfd sp!, {r4 - r10, lr} + stmfd sp!, {r4 - r9, lr} mrc p14, 0, r4, c6, c0, 0 @ clock configuration, for turbo mode mrc p15, 0, r5, c15, c1, 0 @ CP access reg mrc p15, 0, r6, c13, c0, 0 @ PID mrc p15, 0, r7, c3, c0, 0 @ domain ID - mrc p15, 0, r8, c2, c0, 0 @ translation table base addr - mrc p15, 0, r9, c1, c1, 0 @ auxiliary control reg - mrc p15, 0, r10, c1, c0, 0 @ control reg + mrc p15, 0, r8, c1, c1, 0 @ auxiliary control reg + mrc p15, 0, r9, c1, c0, 0 @ control reg bic r4, r4, #2 @ clear frequency change bit - stmia r0, {r4 - r10} @ store cp regs - ldmfd sp!, {r4 - r10, pc} + stmia r0, {r4 - r9} @ store cp regs + ldmfd sp!, {r4 - r9, pc} ENDPROC(cpu_xscale_do_suspend) ENTRY(cpu_xscale_do_resume) - ldmia r0, {r4 - r10} @ load cp regs + ldmia r0, {r4 - r9} @ load cp regs mov ip, #0 mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs mcr p15, 0, ip, c7, c7, 0 @ invalidate I & D caches, BTB @@ -545,13 +544,9 @@ ENTRY(cpu_xscale_do_resume) mcr p15, 0, r5, c15, c1, 0 @ CP access reg mcr p15, 0, r6, c13, c0, 0 @ PID mcr p15, 0, r7, c3, c0, 0 @ domain ID - mcr p15, 0, r8, c2, c0, 0 @ translation table base addr - mcr p15, 0, r9, c1, c1, 0 @ auxiliary control reg - mov r0, r10 @ control register - mov r2, r8, lsr #14 @ get TTB0 base - mov r2, r2, lsl #14 - ldr r3, =PMD_TYPE_SECT | PMD_SECT_BUFFERABLE | \ - PMD_SECT_CACHEABLE | PMD_SECT_AP_WRITE + mcr p15, 0, r1, c2, c0, 0 @ translation table base addr + mcr p15, 0, r8, c1, c1, 0 @ auxiliary control reg + mov r0, r9 @ control register b cpu_resume_mmu ENDPROC(cpu_xscale_do_resume) #endif diff --git a/arch/arm/plat-mxc/Kconfig b/arch/arm/plat-mxc/Kconfig index a5353fc0793f..4c8fdbcc9467 100644 --- a/arch/arm/plat-mxc/Kconfig +++ b/arch/arm/plat-mxc/Kconfig @@ -39,7 +39,7 @@ config ARCH_MX503 select ARCH_MX50_SUPPORTED select ARCH_MX53_SUPPORTED help - This enables support for machines using Freescale's i.MX50 and i.MX51 + This enables support for machines using Freescale's i.MX50 and i.MX53 processors. config ARCH_MX51 diff --git a/arch/arm/plat-mxc/devices.c b/arch/arm/plat-mxc/devices.c index 0d6ed31bdbf2..a34b2ae895f2 100644 --- a/arch/arm/plat-mxc/devices.c +++ b/arch/arm/plat-mxc/devices.c @@ -37,59 +37,6 @@ int __init mxc_register_device(struct platform_device *pdev, void *data) return ret; } -struct platform_device *__init imx_add_platform_device_dmamask( - const char *name, int id, - const struct resource *res, unsigned int num_resources, - const void *data, size_t size_data, u64 dmamask) -{ - int ret = -ENOMEM; - struct platform_device *pdev; - - pdev = platform_device_alloc(name, id); - if (!pdev) - goto err; - - if (dmamask) { - /* - * This memory isn't freed when the device is put, - * I don't have a nice idea for that though. Conceptually - * dma_mask in struct device should not be a pointer. - * See http://thread.gmane.org/gmane.linux.kernel.pci/9081 - */ - pdev->dev.dma_mask = - kmalloc(sizeof(*pdev->dev.dma_mask), GFP_KERNEL); - if (!pdev->dev.dma_mask) - /* ret is still -ENOMEM; */ - goto err; - - *pdev->dev.dma_mask = dmamask; - pdev->dev.coherent_dma_mask = dmamask; - } - - if (res) { - ret = platform_device_add_resources(pdev, res, num_resources); - if (ret) - goto err; - } - - if (data) { - ret = platform_device_add_data(pdev, data, size_data); - if (ret) - goto err; - } - - ret = platform_device_add(pdev); - if (ret) { -err: - if (dmamask) - kfree(pdev->dev.dma_mask); - platform_device_put(pdev); - return ERR_PTR(ret); - } - - return pdev; -} - struct device mxc_aips_bus = { .init_name = "mxc_aips", .parent = &platform_bus, diff --git a/arch/arm/plat-mxc/include/mach/devices-common.h b/arch/arm/plat-mxc/include/mach/devices-common.h index 524538aabc4b..543525d76a60 100644 --- a/arch/arm/plat-mxc/include/mach/devices-common.h +++ b/arch/arm/plat-mxc/include/mach/devices-common.h @@ -14,10 +14,22 @@ extern struct device mxc_aips_bus; extern struct device mxc_ahb_bus; -struct platform_device *imx_add_platform_device_dmamask( +static inline struct platform_device *imx_add_platform_device_dmamask( const char *name, int id, const struct resource *res, unsigned int num_resources, - const void *data, size_t size_data, u64 dmamask); + const void *data, size_t size_data, u64 dmamask) +{ + struct platform_device_info pdevinfo = { + .name = name, + .id = id, + .res = res, + .num_res = num_resources, + .data = data, + .size_data = size_data, + .dma_mask = dmamask, + }; + return platform_device_register_full(&pdevinfo); +} static inline struct platform_device *imx_add_platform_device( const char *name, int id, diff --git a/arch/arm/plat-mxc/include/mach/i2c.h b/arch/arm/plat-mxc/include/mach/i2c.h index 4a5dc5c6d8e8..375cdd0cf876 100644 --- a/arch/arm/plat-mxc/include/mach/i2c.h +++ b/arch/arm/plat-mxc/include/mach/i2c.h @@ -11,14 +11,10 @@ /** * struct imxi2c_platform_data - structure of platform data for MXC I2C driver - * @init: Initialise gpio's and other board specific things - * @exit: Free everything initialised by @init * @bitrate: Bus speed measured in Hz * **/ struct imxi2c_platform_data { - int (*init)(struct device *dev); - void (*exit)(struct device *dev); int bitrate; }; diff --git a/arch/arm/plat-nomadik/include/plat/gpio-nomadik.h b/arch/arm/plat-nomadik/include/plat/gpio-nomadik.h index 3ba4d8f8073b..9605bf227df9 100644 --- a/arch/arm/plat-nomadik/include/plat/gpio-nomadik.h +++ b/arch/arm/plat-nomadik/include/plat/gpio-nomadik.h @@ -67,6 +67,9 @@ extern int nmk_gpio_get_mode(int gpio); extern void nmk_gpio_wakeups_suspend(void); extern void nmk_gpio_wakeups_resume(void); +extern void nmk_gpio_clocks_enable(void); +extern void nmk_gpio_clocks_disable(void); + extern void nmk_gpio_read_pull(int gpio_bank, u32 *pull_up); /* diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig index 95732af7b208..aa59f4247dc5 100644 --- a/arch/arm/plat-omap/Kconfig +++ b/arch/arm/plat-omap/Kconfig @@ -14,6 +14,7 @@ config ARCH_OMAP1 select CLKDEV_LOOKUP select CLKSRC_MMIO select GENERIC_IRQ_CHIP + select HAVE_IDE select NEED_MACH_MEMORY_H help "Systems based on omap7xx, omap15xx or omap16xx" @@ -133,18 +134,6 @@ config OMAP_MBOX_KFIFO_SIZE This can also be changed at runtime (via the mbox_kfifo_size module parameter). -config OMAP_IOMMU - tristate - -config OMAP_IOMMU_DEBUG - tristate "Export OMAP IOMMU internals in DebugFS" - depends on OMAP_IOMMU && DEBUG_FS - help - Select this to see extensive information about - the internal state of OMAP IOMMU in debugfs. - - Say N unless you know you need this. - config OMAP_IOMMU_IVA2 bool diff --git a/arch/arm/plat-omap/Makefile b/arch/arm/plat-omap/Makefile index f0233e6abcdf..985262242f25 100644 --- a/arch/arm/plat-omap/Makefile +++ b/arch/arm/plat-omap/Makefile @@ -18,8 +18,6 @@ obj-$(CONFIG_ARCH_OMAP3) += omap_device.o obj-$(CONFIG_ARCH_OMAP4) += omap_device.o obj-$(CONFIG_OMAP_MCBSP) += mcbsp.o -obj-$(CONFIG_OMAP_IOMMU) += iommu.o iovmm.o -obj-$(CONFIG_OMAP_IOMMU_DEBUG) += iommu-debug.o obj-$(CONFIG_CPU_FREQ) += cpu-omap.o obj-$(CONFIG_OMAP_DM_TIMER) += dmtimer.o diff --git a/arch/arm/plat-omap/devices.c b/arch/arm/plat-omap/devices.c index 64c3bd4aa54e..c46c47afa090 100644 --- a/arch/arm/plat-omap/devices.c +++ b/arch/arm/plat-omap/devices.c @@ -73,41 +73,6 @@ void omap_mcbsp_register_board_cfg(struct resource *res, int res_count, /*-------------------------------------------------------------------------*/ -#if defined(CONFIG_SND_OMAP_SOC_MCPDM) || \ - defined(CONFIG_SND_OMAP_SOC_MCPDM_MODULE) - -static struct resource mcpdm_resources[] = { - { - .name = "mcpdm_mem", - .start = OMAP44XX_MCPDM_BASE, - .end = OMAP44XX_MCPDM_BASE + SZ_4K, - .flags = IORESOURCE_MEM, - }, - { - .name = "mcpdm_irq", - .start = OMAP44XX_IRQ_MCPDM, - .end = OMAP44XX_IRQ_MCPDM, - .flags = IORESOURCE_IRQ, - }, -}; - -static struct platform_device omap_mcpdm_device = { - .name = "omap-mcpdm", - .id = -1, - .num_resources = ARRAY_SIZE(mcpdm_resources), - .resource = mcpdm_resources, -}; - -static void omap_init_mcpdm(void) -{ - (void) platform_device_register(&omap_mcpdm_device); -} -#else -static inline void omap_init_mcpdm(void) {} -#endif - -/*-------------------------------------------------------------------------*/ - #if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) || \ defined(CONFIG_MMC_OMAP_HS) || defined(CONFIG_MMC_OMAP_HS_MODULE) @@ -290,7 +255,6 @@ static int __init omap_init_devices(void) * in alphabetical order so they're easier to sort through. */ omap_init_rng(); - omap_init_mcpdm(); omap_init_uwire(); return 0; } diff --git a/arch/arm/plat-omap/i2c.c b/arch/arm/plat-omap/i2c.c index 3341ca4703e9..2388b8eebaaa 100644 --- a/arch/arm/plat-omap/i2c.c +++ b/arch/arm/plat-omap/i2c.c @@ -108,6 +108,22 @@ static inline int omap1_i2c_add_bus(int bus_id) res[1].start = INT_I2C; pdata = &i2c_pdata[bus_id - 1]; + /* all OMAP1 have IP version 1 register set */ + pdata->rev = OMAP_I2C_IP_VERSION_1; + + /* all OMAP1 I2C are implemented like this */ + pdata->flags = OMAP_I2C_FLAG_NO_FIFO | + OMAP_I2C_FLAG_SIMPLE_CLOCK | + OMAP_I2C_FLAG_16BIT_DATA_REG | + OMAP_I2C_FLAG_ALWAYS_ARMXOR_CLK; + + /* how the cpu bus is wired up differs for 7xx only */ + + if (cpu_is_omap7xx()) + pdata->flags |= OMAP_I2C_FLAG_BUS_SHIFT_1; + else + pdata->flags |= OMAP_I2C_FLAG_BUS_SHIFT_2; + return platform_device_register(pdev); } @@ -138,6 +154,7 @@ static inline int omap2_i2c_add_bus(int bus_id) struct omap_device *od; char oh_name[MAX_OMAP_I2C_HWMOD_NAME_LEN]; struct omap_i2c_bus_platform_data *pdata; + struct omap_i2c_dev_attr *dev_attr; omap2_i2c_mux_pins(bus_id); @@ -152,6 +169,16 @@ static inline int omap2_i2c_add_bus(int bus_id) pdata = &i2c_pdata[bus_id - 1]; /* + * pass the hwmod class's CPU-specific knowledge of I2C IP revision in + * use, and functionality implementation flags, up to the OMAP I2C + * driver via platform data + */ + pdata->rev = oh->class->rev; + + dev_attr = (struct omap_i2c_dev_attr *)oh->dev_attr; + pdata->flags = dev_attr->flags; + + /* * When waiting for completion of a i2c transfer, we need to * set a wake up latency constraint for the MPU. This is to * ensure quick enough wakeup from idle, when transfer diff --git a/arch/arm/plat-omap/include/plat/iommu.h b/arch/arm/plat-omap/include/plat/iommu.h index 174f1b9c8c03..a1d79ee19250 100644 --- a/arch/arm/plat-omap/include/plat/iommu.h +++ b/arch/arm/plat-omap/include/plat/iommu.h @@ -25,16 +25,17 @@ struct iotlb_entry { }; }; -struct iommu { +struct omap_iommu { const char *name; struct module *owner; struct clk *clk; void __iomem *regbase; struct device *dev; void *isr_priv; + struct iommu_domain *domain; unsigned int refcount; - struct mutex iommu_lock; /* global for this whole object */ + spinlock_t iommu_lock; /* global for this whole object */ /* * We don't change iopgd for a situation like pgd for a task, @@ -48,8 +49,6 @@ struct iommu { struct list_head mmap; struct mutex mmap_lock; /* protect mmap */ - int (*isr)(struct iommu *obj, u32 da, u32 iommu_errs, void *priv); - void *ctx; /* iommu context: registres saved area */ u32 da_start; u32 da_end; @@ -81,25 +80,27 @@ struct iotlb_lock { struct iommu_functions { unsigned long version; - int (*enable)(struct iommu *obj); - void (*disable)(struct iommu *obj); - void (*set_twl)(struct iommu *obj, bool on); - u32 (*fault_isr)(struct iommu *obj, u32 *ra); + int (*enable)(struct omap_iommu *obj); + void (*disable)(struct omap_iommu *obj); + void (*set_twl)(struct omap_iommu *obj, bool on); + u32 (*fault_isr)(struct omap_iommu *obj, u32 *ra); - void (*tlb_read_cr)(struct iommu *obj, struct cr_regs *cr); - void (*tlb_load_cr)(struct iommu *obj, struct cr_regs *cr); + void (*tlb_read_cr)(struct omap_iommu *obj, struct cr_regs *cr); + void (*tlb_load_cr)(struct omap_iommu *obj, struct cr_regs *cr); - struct cr_regs *(*alloc_cr)(struct iommu *obj, struct iotlb_entry *e); + struct cr_regs *(*alloc_cr)(struct omap_iommu *obj, + struct iotlb_entry *e); int (*cr_valid)(struct cr_regs *cr); u32 (*cr_to_virt)(struct cr_regs *cr); void (*cr_to_e)(struct cr_regs *cr, struct iotlb_entry *e); - ssize_t (*dump_cr)(struct iommu *obj, struct cr_regs *cr, char *buf); + ssize_t (*dump_cr)(struct omap_iommu *obj, struct cr_regs *cr, + char *buf); u32 (*get_pte_attr)(struct iotlb_entry *e); - void (*save_ctx)(struct iommu *obj); - void (*restore_ctx)(struct iommu *obj); - ssize_t (*dump_ctx)(struct iommu *obj, char *buf, ssize_t len); + void (*save_ctx)(struct omap_iommu *obj); + void (*restore_ctx)(struct omap_iommu *obj); + ssize_t (*dump_ctx)(struct omap_iommu *obj, char *buf, ssize_t len); }; struct iommu_platform_data { @@ -150,40 +151,31 @@ struct iommu_platform_data { /* * global functions */ -extern u32 iommu_arch_version(void); - -extern void iotlb_cr_to_e(struct cr_regs *cr, struct iotlb_entry *e); -extern u32 iotlb_cr_to_virt(struct cr_regs *cr); - -extern int load_iotlb_entry(struct iommu *obj, struct iotlb_entry *e); -extern void iommu_set_twl(struct iommu *obj, bool on); -extern void flush_iotlb_page(struct iommu *obj, u32 da); -extern void flush_iotlb_range(struct iommu *obj, u32 start, u32 end); -extern void flush_iotlb_all(struct iommu *obj); - -extern int iopgtable_store_entry(struct iommu *obj, struct iotlb_entry *e); -extern void iopgtable_lookup_entry(struct iommu *obj, u32 da, u32 **ppgd, - u32 **ppte); -extern size_t iopgtable_clear_entry(struct iommu *obj, u32 iova); - -extern int iommu_set_da_range(struct iommu *obj, u32 start, u32 end); -extern struct iommu *iommu_get(const char *name); -extern void iommu_put(struct iommu *obj); -extern int iommu_set_isr(const char *name, - int (*isr)(struct iommu *obj, u32 da, u32 iommu_errs, +extern u32 omap_iommu_arch_version(void); + +extern void omap_iotlb_cr_to_e(struct cr_regs *cr, struct iotlb_entry *e); + +extern int +omap_iopgtable_store_entry(struct omap_iommu *obj, struct iotlb_entry *e); + +extern int omap_iommu_set_isr(const char *name, + int (*isr)(struct omap_iommu *obj, u32 da, u32 iommu_errs, void *priv), void *isr_priv); -extern void iommu_save_ctx(struct iommu *obj); -extern void iommu_restore_ctx(struct iommu *obj); +extern void omap_iommu_save_ctx(struct omap_iommu *obj); +extern void omap_iommu_restore_ctx(struct omap_iommu *obj); -extern int install_iommu_arch(const struct iommu_functions *ops); -extern void uninstall_iommu_arch(const struct iommu_functions *ops); +extern int omap_install_iommu_arch(const struct iommu_functions *ops); +extern void omap_uninstall_iommu_arch(const struct iommu_functions *ops); -extern int foreach_iommu_device(void *data, +extern int omap_foreach_iommu_device(void *data, int (*fn)(struct device *, void *)); -extern ssize_t iommu_dump_ctx(struct iommu *obj, char *buf, ssize_t len); -extern size_t dump_tlb_entries(struct iommu *obj, char *buf, ssize_t len); +extern ssize_t +omap_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t len); +extern size_t +omap_dump_tlb_entries(struct omap_iommu *obj, char *buf, ssize_t len); +struct device *omap_find_iommu_device(const char *name); #endif /* __MACH_IOMMU_H */ diff --git a/arch/arm/plat-omap/include/plat/iommu2.h b/arch/arm/plat-omap/include/plat/iommu2.h index 10ad05f410e9..d4116b595e40 100644 --- a/arch/arm/plat-omap/include/plat/iommu2.h +++ b/arch/arm/plat-omap/include/plat/iommu2.h @@ -83,12 +83,12 @@ /* * register accessors */ -static inline u32 iommu_read_reg(struct iommu *obj, size_t offs) +static inline u32 iommu_read_reg(struct omap_iommu *obj, size_t offs) { return __raw_readl(obj->regbase + offs); } -static inline void iommu_write_reg(struct iommu *obj, u32 val, size_t offs) +static inline void iommu_write_reg(struct omap_iommu *obj, u32 val, size_t offs) { __raw_writel(val, obj->regbase + offs); } diff --git a/arch/arm/plat-omap/iopgtable.h b/arch/arm/plat-omap/include/plat/iopgtable.h index c3e93bb0911f..66a813977d52 100644 --- a/arch/arm/plat-omap/iopgtable.h +++ b/arch/arm/plat-omap/include/plat/iopgtable.h @@ -56,6 +56,19 @@ #define IOPAGE_MASK IOPTE_MASK +/** + * omap_iommu_translate() - va to pa translation + * @d: omap iommu descriptor + * @va: virtual address + * @mask: omap iommu descriptor mask + * + * va to pa translation + */ +static inline phys_addr_t omap_iommu_translate(u32 d, u32 va, u32 mask) +{ + return (d & mask) | (va & (~mask)); +} + /* * some descriptor attributes. */ @@ -64,10 +77,15 @@ #define IOPGD_SUPER (1 << 18 | 2 << 0) #define iopgd_is_table(x) (((x) & 3) == IOPGD_TABLE) +#define iopgd_is_section(x) (((x) & (1 << 18 | 3)) == IOPGD_SECTION) +#define iopgd_is_super(x) (((x) & (1 << 18 | 3)) == IOPGD_SUPER) #define IOPTE_SMALL (2 << 0) #define IOPTE_LARGE (1 << 0) +#define iopte_is_small(x) (((x) & 2) == IOPTE_SMALL) +#define iopte_is_large(x) (((x) & 3) == IOPTE_LARGE) + /* to find an entry in a page-table-directory */ #define iopgd_index(da) (((da) >> IOPGD_SHIFT) & (PTRS_PER_IOPGD - 1)) #define iopgd_offset(obj, da) ((obj)->iopgd + iopgd_index(da)) @@ -97,6 +115,6 @@ static inline u32 iotlb_init_entry(struct iotlb_entry *e, u32 da, u32 pa, } #define to_iommu(dev) \ - (struct iommu *)platform_get_drvdata(to_platform_device(dev)) + (struct omap_iommu *)platform_get_drvdata(to_platform_device(dev)) #endif /* __PLAT_OMAP_IOMMU_H */ diff --git a/arch/arm/plat-omap/include/plat/iovmm.h b/arch/arm/plat-omap/include/plat/iovmm.h index e992b9655fbc..6af1a91c0f36 100644 --- a/arch/arm/plat-omap/include/plat/iovmm.h +++ b/arch/arm/plat-omap/include/plat/iovmm.h @@ -13,8 +13,10 @@ #ifndef __IOMMU_MMAP_H #define __IOMMU_MMAP_H +#include <linux/iommu.h> + struct iovm_struct { - struct iommu *iommu; /* iommu object which this belongs to */ + struct omap_iommu *iommu; /* iommu object which this belongs to */ u32 da_start; /* area definition */ u32 da_end; u32 flags; /* IOVMF_: see below */ @@ -70,20 +72,18 @@ struct iovm_struct { #define IOVMF_DA_FIXED (1 << (4 + IOVMF_SW_SHIFT)) -extern struct iovm_struct *find_iovm_area(struct iommu *obj, u32 da); -extern u32 iommu_vmap(struct iommu *obj, u32 da, +extern struct iovm_struct *omap_find_iovm_area(struct omap_iommu *obj, u32 da); +extern u32 +omap_iommu_vmap(struct iommu_domain *domain, struct omap_iommu *obj, u32 da, const struct sg_table *sgt, u32 flags); -extern struct sg_table *iommu_vunmap(struct iommu *obj, u32 da); -extern u32 iommu_vmalloc(struct iommu *obj, u32 da, size_t bytes, - u32 flags); -extern void iommu_vfree(struct iommu *obj, const u32 da); -extern u32 iommu_kmap(struct iommu *obj, u32 da, u32 pa, size_t bytes, - u32 flags); -extern void iommu_kunmap(struct iommu *obj, u32 da); -extern u32 iommu_kmalloc(struct iommu *obj, u32 da, size_t bytes, - u32 flags); -extern void iommu_kfree(struct iommu *obj, u32 da); - -extern void *da_to_va(struct iommu *obj, u32 da); +extern struct sg_table *omap_iommu_vunmap(struct iommu_domain *domain, + struct omap_iommu *obj, u32 da); +extern u32 +omap_iommu_vmalloc(struct iommu_domain *domain, struct omap_iommu *obj, + u32 da, size_t bytes, u32 flags); +extern void +omap_iommu_vfree(struct iommu_domain *domain, struct omap_iommu *obj, + const u32 da); +extern void *omap_da_to_va(struct omap_iommu *obj, u32 da); #endif /* __IOMMU_MMAP_H */ diff --git a/arch/arm/plat-omap/include/plat/mmc.h b/arch/arm/plat-omap/include/plat/mmc.h index c7b874186c27..94cf70afb236 100644 --- a/arch/arm/plat-omap/include/plat/mmc.h +++ b/arch/arm/plat-omap/include/plat/mmc.h @@ -31,7 +31,24 @@ #define OMAP_MMC_MAX_SLOTS 2 -#define OMAP_HSMMC_SUPPORTS_DUAL_VOLT BIT(1) +/* + * struct omap_mmc_dev_attr.flags possibilities + * + * OMAP_HSMMC_SUPPORTS_DUAL_VOLT: Some HSMMC controller instances can + * operate with either 1.8Vdc or 3.0Vdc card voltages; this flag + * should be set if this is the case. See for example Section 22.5.3 + * "MMC/SD/SDIO1 Bus Voltage Selection" of the OMAP34xx Multimedia + * Device Silicon Revision 3.1.x Revision ZR (July 2011) (SWPU223R). + * + * OMAP_HSMMC_BROKEN_MULTIBLOCK_READ: Multiple-block read transfers + * don't work correctly on some MMC controller instances on some + * OMAP3 SoCs; this flag should be set if this is the case. See + * for example Advisory 2.1.1.128 "MMC: Multiple Block Read + * Operation Issue" in _OMAP3530/3525/3515/3503 Silicon Errata_ + * Revision F (October 2010) (SPRZ278F). + */ +#define OMAP_HSMMC_SUPPORTS_DUAL_VOLT BIT(0) +#define OMAP_HSMMC_BROKEN_MULTIBLOCK_READ BIT(1) struct omap_mmc_dev_attr { u8 flags; diff --git a/arch/arm/plat-omap/iommu-debug.c b/arch/arm/plat-omap/iommu-debug.c deleted file mode 100644 index f07cf2f08e09..000000000000 --- a/arch/arm/plat-omap/iommu-debug.c +++ /dev/null @@ -1,418 +0,0 @@ -/* - * omap iommu: debugfs interface - * - * Copyright (C) 2008-2009 Nokia Corporation - * - * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/err.h> -#include <linux/clk.h> -#include <linux/io.h> -#include <linux/slab.h> -#include <linux/uaccess.h> -#include <linux/platform_device.h> -#include <linux/debugfs.h> - -#include <plat/iommu.h> -#include <plat/iovmm.h> - -#include "iopgtable.h" - -#define MAXCOLUMN 100 /* for short messages */ - -static DEFINE_MUTEX(iommu_debug_lock); - -static struct dentry *iommu_debug_root; - -static ssize_t debug_read_ver(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) -{ - u32 ver = iommu_arch_version(); - char buf[MAXCOLUMN], *p = buf; - - p += sprintf(p, "H/W version: %d.%d\n", (ver >> 4) & 0xf , ver & 0xf); - - return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); -} - -static ssize_t debug_read_regs(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct iommu *obj = file->private_data; - char *p, *buf; - ssize_t bytes; - - buf = kmalloc(count, GFP_KERNEL); - if (!buf) - return -ENOMEM; - p = buf; - - mutex_lock(&iommu_debug_lock); - - bytes = iommu_dump_ctx(obj, p, count); - bytes = simple_read_from_buffer(userbuf, count, ppos, buf, bytes); - - mutex_unlock(&iommu_debug_lock); - kfree(buf); - - return bytes; -} - -static ssize_t debug_read_tlb(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct iommu *obj = file->private_data; - char *p, *buf; - ssize_t bytes, rest; - - buf = kmalloc(count, GFP_KERNEL); - if (!buf) - return -ENOMEM; - p = buf; - - mutex_lock(&iommu_debug_lock); - - p += sprintf(p, "%8s %8s\n", "cam:", "ram:"); - p += sprintf(p, "-----------------------------------------\n"); - rest = count - (p - buf); - p += dump_tlb_entries(obj, p, rest); - - bytes = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); - - mutex_unlock(&iommu_debug_lock); - kfree(buf); - - return bytes; -} - -static ssize_t debug_write_pagetable(struct file *file, - const char __user *userbuf, size_t count, loff_t *ppos) -{ - struct iotlb_entry e; - struct cr_regs cr; - int err; - struct iommu *obj = file->private_data; - char buf[MAXCOLUMN], *p = buf; - - count = min(count, sizeof(buf)); - - mutex_lock(&iommu_debug_lock); - if (copy_from_user(p, userbuf, count)) { - mutex_unlock(&iommu_debug_lock); - return -EFAULT; - } - - sscanf(p, "%x %x", &cr.cam, &cr.ram); - if (!cr.cam || !cr.ram) { - mutex_unlock(&iommu_debug_lock); - return -EINVAL; - } - - iotlb_cr_to_e(&cr, &e); - err = iopgtable_store_entry(obj, &e); - if (err) - dev_err(obj->dev, "%s: fail to store cr\n", __func__); - - mutex_unlock(&iommu_debug_lock); - return count; -} - -#define dump_ioptable_entry_one(lv, da, val) \ - ({ \ - int __err = 0; \ - ssize_t bytes; \ - const int maxcol = 22; \ - const char *str = "%d: %08x %08x\n"; \ - bytes = snprintf(p, maxcol, str, lv, da, val); \ - p += bytes; \ - len -= bytes; \ - if (len < maxcol) \ - __err = -ENOMEM; \ - __err; \ - }) - -static ssize_t dump_ioptable(struct iommu *obj, char *buf, ssize_t len) -{ - int i; - u32 *iopgd; - char *p = buf; - - spin_lock(&obj->page_table_lock); - - iopgd = iopgd_offset(obj, 0); - for (i = 0; i < PTRS_PER_IOPGD; i++, iopgd++) { - int j, err; - u32 *iopte; - u32 da; - - if (!*iopgd) - continue; - - if (!(*iopgd & IOPGD_TABLE)) { - da = i << IOPGD_SHIFT; - - err = dump_ioptable_entry_one(1, da, *iopgd); - if (err) - goto out; - continue; - } - - iopte = iopte_offset(iopgd, 0); - - for (j = 0; j < PTRS_PER_IOPTE; j++, iopte++) { - if (!*iopte) - continue; - - da = (i << IOPGD_SHIFT) + (j << IOPTE_SHIFT); - err = dump_ioptable_entry_one(2, da, *iopgd); - if (err) - goto out; - } - } -out: - spin_unlock(&obj->page_table_lock); - - return p - buf; -} - -static ssize_t debug_read_pagetable(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct iommu *obj = file->private_data; - char *p, *buf; - size_t bytes; - - buf = (char *)__get_free_page(GFP_KERNEL); - if (!buf) - return -ENOMEM; - p = buf; - - p += sprintf(p, "L: %8s %8s\n", "da:", "pa:"); - p += sprintf(p, "-----------------------------------------\n"); - - mutex_lock(&iommu_debug_lock); - - bytes = PAGE_SIZE - (p - buf); - p += dump_ioptable(obj, p, bytes); - - bytes = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); - - mutex_unlock(&iommu_debug_lock); - free_page((unsigned long)buf); - - return bytes; -} - -static ssize_t debug_read_mmap(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct iommu *obj = file->private_data; - char *p, *buf; - struct iovm_struct *tmp; - int uninitialized_var(i); - ssize_t bytes; - - buf = (char *)__get_free_page(GFP_KERNEL); - if (!buf) - return -ENOMEM; - p = buf; - - p += sprintf(p, "%-3s %-8s %-8s %6s %8s\n", - "No", "start", "end", "size", "flags"); - p += sprintf(p, "-------------------------------------------------\n"); - - mutex_lock(&iommu_debug_lock); - - list_for_each_entry(tmp, &obj->mmap, list) { - size_t len; - const char *str = "%3d %08x-%08x %6x %8x\n"; - const int maxcol = 39; - - len = tmp->da_end - tmp->da_start; - p += snprintf(p, maxcol, str, - i, tmp->da_start, tmp->da_end, len, tmp->flags); - - if (PAGE_SIZE - (p - buf) < maxcol) - break; - i++; - } - - bytes = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); - - mutex_unlock(&iommu_debug_lock); - free_page((unsigned long)buf); - - return bytes; -} - -static ssize_t debug_read_mem(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct iommu *obj = file->private_data; - char *p, *buf; - struct iovm_struct *area; - ssize_t bytes; - - count = min_t(ssize_t, count, PAGE_SIZE); - - buf = (char *)__get_free_page(GFP_KERNEL); - if (!buf) - return -ENOMEM; - p = buf; - - mutex_lock(&iommu_debug_lock); - - area = find_iovm_area(obj, (u32)ppos); - if (IS_ERR(area)) { - bytes = -EINVAL; - goto err_out; - } - memcpy(p, area->va, count); - p += count; - - bytes = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); -err_out: - mutex_unlock(&iommu_debug_lock); - free_page((unsigned long)buf); - - return bytes; -} - -static ssize_t debug_write_mem(struct file *file, const char __user *userbuf, - size_t count, loff_t *ppos) -{ - struct iommu *obj = file->private_data; - struct iovm_struct *area; - char *p, *buf; - - count = min_t(size_t, count, PAGE_SIZE); - - buf = (char *)__get_free_page(GFP_KERNEL); - if (!buf) - return -ENOMEM; - p = buf; - - mutex_lock(&iommu_debug_lock); - - if (copy_from_user(p, userbuf, count)) { - count = -EFAULT; - goto err_out; - } - - area = find_iovm_area(obj, (u32)ppos); - if (IS_ERR(area)) { - count = -EINVAL; - goto err_out; - } - memcpy(area->va, p, count); -err_out: - mutex_unlock(&iommu_debug_lock); - free_page((unsigned long)buf); - - return count; -} - -static int debug_open_generic(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return 0; -} - -#define DEBUG_FOPS(name) \ - static const struct file_operations debug_##name##_fops = { \ - .open = debug_open_generic, \ - .read = debug_read_##name, \ - .write = debug_write_##name, \ - .llseek = generic_file_llseek, \ - }; - -#define DEBUG_FOPS_RO(name) \ - static const struct file_operations debug_##name##_fops = { \ - .open = debug_open_generic, \ - .read = debug_read_##name, \ - .llseek = generic_file_llseek, \ - }; - -DEBUG_FOPS_RO(ver); -DEBUG_FOPS_RO(regs); -DEBUG_FOPS_RO(tlb); -DEBUG_FOPS(pagetable); -DEBUG_FOPS_RO(mmap); -DEBUG_FOPS(mem); - -#define __DEBUG_ADD_FILE(attr, mode) \ - { \ - struct dentry *dent; \ - dent = debugfs_create_file(#attr, mode, parent, \ - obj, &debug_##attr##_fops); \ - if (!dent) \ - return -ENOMEM; \ - } - -#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 600) -#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 400) - -static int iommu_debug_register(struct device *dev, void *data) -{ - struct platform_device *pdev = to_platform_device(dev); - struct iommu *obj = platform_get_drvdata(pdev); - struct dentry *d, *parent; - - if (!obj || !obj->dev) - return -EINVAL; - - d = debugfs_create_dir(obj->name, iommu_debug_root); - if (!d) - return -ENOMEM; - parent = d; - - d = debugfs_create_u8("nr_tlb_entries", 400, parent, - (u8 *)&obj->nr_tlb_entries); - if (!d) - return -ENOMEM; - - DEBUG_ADD_FILE_RO(ver); - DEBUG_ADD_FILE_RO(regs); - DEBUG_ADD_FILE_RO(tlb); - DEBUG_ADD_FILE(pagetable); - DEBUG_ADD_FILE_RO(mmap); - DEBUG_ADD_FILE(mem); - - return 0; -} - -static int __init iommu_debug_init(void) -{ - struct dentry *d; - int err; - - d = debugfs_create_dir("iommu", NULL); - if (!d) - return -ENOMEM; - iommu_debug_root = d; - - err = foreach_iommu_device(d, iommu_debug_register); - if (err) - goto err_out; - return 0; - -err_out: - debugfs_remove_recursive(iommu_debug_root); - return err; -} -module_init(iommu_debug_init) - -static void __exit iommu_debugfs_exit(void) -{ - debugfs_remove_recursive(iommu_debug_root); -} -module_exit(iommu_debugfs_exit) - -MODULE_DESCRIPTION("omap iommu: debugfs interface"); -MODULE_AUTHOR("Hiroshi DOYU <Hiroshi.DOYU@nokia.com>"); -MODULE_LICENSE("GPL v2"); diff --git a/arch/arm/plat-omap/iommu.c b/arch/arm/plat-omap/iommu.c deleted file mode 100644 index 34fc31ee9081..000000000000 --- a/arch/arm/plat-omap/iommu.c +++ /dev/null @@ -1,1102 +0,0 @@ -/* - * omap iommu: tlb and pagetable primitives - * - * Copyright (C) 2008-2010 Nokia Corporation - * - * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>, - * Paul Mundt and Toshihiro Kobayashi - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/err.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/interrupt.h> -#include <linux/ioport.h> -#include <linux/clk.h> -#include <linux/platform_device.h> - -#include <asm/cacheflush.h> - -#include <plat/iommu.h> - -#include "iopgtable.h" - -#define for_each_iotlb_cr(obj, n, __i, cr) \ - for (__i = 0; \ - (__i < (n)) && (cr = __iotlb_read_cr((obj), __i), true); \ - __i++) - -/* accommodate the difference between omap1 and omap2/3 */ -static const struct iommu_functions *arch_iommu; - -static struct platform_driver omap_iommu_driver; -static struct kmem_cache *iopte_cachep; - -/** - * install_iommu_arch - Install archtecure specific iommu functions - * @ops: a pointer to architecture specific iommu functions - * - * There are several kind of iommu algorithm(tlb, pagetable) among - * omap series. This interface installs such an iommu algorighm. - **/ -int install_iommu_arch(const struct iommu_functions *ops) -{ - if (arch_iommu) - return -EBUSY; - - arch_iommu = ops; - return 0; -} -EXPORT_SYMBOL_GPL(install_iommu_arch); - -/** - * uninstall_iommu_arch - Uninstall archtecure specific iommu functions - * @ops: a pointer to architecture specific iommu functions - * - * This interface uninstalls the iommu algorighm installed previously. - **/ -void uninstall_iommu_arch(const struct iommu_functions *ops) -{ - if (arch_iommu != ops) - pr_err("%s: not your arch\n", __func__); - - arch_iommu = NULL; -} -EXPORT_SYMBOL_GPL(uninstall_iommu_arch); - -/** - * iommu_save_ctx - Save registers for pm off-mode support - * @obj: target iommu - **/ -void iommu_save_ctx(struct iommu *obj) -{ - arch_iommu->save_ctx(obj); -} -EXPORT_SYMBOL_GPL(iommu_save_ctx); - -/** - * iommu_restore_ctx - Restore registers for pm off-mode support - * @obj: target iommu - **/ -void iommu_restore_ctx(struct iommu *obj) -{ - arch_iommu->restore_ctx(obj); -} -EXPORT_SYMBOL_GPL(iommu_restore_ctx); - -/** - * iommu_arch_version - Return running iommu arch version - **/ -u32 iommu_arch_version(void) -{ - return arch_iommu->version; -} -EXPORT_SYMBOL_GPL(iommu_arch_version); - -static int iommu_enable(struct iommu *obj) -{ - int err; - - if (!obj) - return -EINVAL; - - if (!arch_iommu) - return -ENODEV; - - clk_enable(obj->clk); - - err = arch_iommu->enable(obj); - - clk_disable(obj->clk); - return err; -} - -static void iommu_disable(struct iommu *obj) -{ - if (!obj) - return; - - clk_enable(obj->clk); - - arch_iommu->disable(obj); - - clk_disable(obj->clk); -} - -/* - * TLB operations - */ -void iotlb_cr_to_e(struct cr_regs *cr, struct iotlb_entry *e) -{ - BUG_ON(!cr || !e); - - arch_iommu->cr_to_e(cr, e); -} -EXPORT_SYMBOL_GPL(iotlb_cr_to_e); - -static inline int iotlb_cr_valid(struct cr_regs *cr) -{ - if (!cr) - return -EINVAL; - - return arch_iommu->cr_valid(cr); -} - -static inline struct cr_regs *iotlb_alloc_cr(struct iommu *obj, - struct iotlb_entry *e) -{ - if (!e) - return NULL; - - return arch_iommu->alloc_cr(obj, e); -} - -u32 iotlb_cr_to_virt(struct cr_regs *cr) -{ - return arch_iommu->cr_to_virt(cr); -} -EXPORT_SYMBOL_GPL(iotlb_cr_to_virt); - -static u32 get_iopte_attr(struct iotlb_entry *e) -{ - return arch_iommu->get_pte_attr(e); -} - -static u32 iommu_report_fault(struct iommu *obj, u32 *da) -{ - return arch_iommu->fault_isr(obj, da); -} - -static void iotlb_lock_get(struct iommu *obj, struct iotlb_lock *l) -{ - u32 val; - - val = iommu_read_reg(obj, MMU_LOCK); - - l->base = MMU_LOCK_BASE(val); - l->vict = MMU_LOCK_VICT(val); - -} - -static void iotlb_lock_set(struct iommu *obj, struct iotlb_lock *l) -{ - u32 val; - - val = (l->base << MMU_LOCK_BASE_SHIFT); - val |= (l->vict << MMU_LOCK_VICT_SHIFT); - - iommu_write_reg(obj, val, MMU_LOCK); -} - -static void iotlb_read_cr(struct iommu *obj, struct cr_regs *cr) -{ - arch_iommu->tlb_read_cr(obj, cr); -} - -static void iotlb_load_cr(struct iommu *obj, struct cr_regs *cr) -{ - arch_iommu->tlb_load_cr(obj, cr); - - iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY); - iommu_write_reg(obj, 1, MMU_LD_TLB); -} - -/** - * iotlb_dump_cr - Dump an iommu tlb entry into buf - * @obj: target iommu - * @cr: contents of cam and ram register - * @buf: output buffer - **/ -static inline ssize_t iotlb_dump_cr(struct iommu *obj, struct cr_regs *cr, - char *buf) -{ - BUG_ON(!cr || !buf); - - return arch_iommu->dump_cr(obj, cr, buf); -} - -/* only used in iotlb iteration for-loop */ -static struct cr_regs __iotlb_read_cr(struct iommu *obj, int n) -{ - struct cr_regs cr; - struct iotlb_lock l; - - iotlb_lock_get(obj, &l); - l.vict = n; - iotlb_lock_set(obj, &l); - iotlb_read_cr(obj, &cr); - - return cr; -} - -/** - * load_iotlb_entry - Set an iommu tlb entry - * @obj: target iommu - * @e: an iommu tlb entry info - **/ -int load_iotlb_entry(struct iommu *obj, struct iotlb_entry *e) -{ - int err = 0; - struct iotlb_lock l; - struct cr_regs *cr; - - if (!obj || !obj->nr_tlb_entries || !e) - return -EINVAL; - - clk_enable(obj->clk); - - iotlb_lock_get(obj, &l); - if (l.base == obj->nr_tlb_entries) { - dev_warn(obj->dev, "%s: preserve entries full\n", __func__); - err = -EBUSY; - goto out; - } - if (!e->prsvd) { - int i; - struct cr_regs tmp; - - for_each_iotlb_cr(obj, obj->nr_tlb_entries, i, tmp) - if (!iotlb_cr_valid(&tmp)) - break; - - if (i == obj->nr_tlb_entries) { - dev_dbg(obj->dev, "%s: full: no entry\n", __func__); - err = -EBUSY; - goto out; - } - - iotlb_lock_get(obj, &l); - } else { - l.vict = l.base; - iotlb_lock_set(obj, &l); - } - - cr = iotlb_alloc_cr(obj, e); - if (IS_ERR(cr)) { - clk_disable(obj->clk); - return PTR_ERR(cr); - } - - iotlb_load_cr(obj, cr); - kfree(cr); - - if (e->prsvd) - l.base++; - /* increment victim for next tlb load */ - if (++l.vict == obj->nr_tlb_entries) - l.vict = l.base; - iotlb_lock_set(obj, &l); -out: - clk_disable(obj->clk); - return err; -} -EXPORT_SYMBOL_GPL(load_iotlb_entry); - -/** - * flush_iotlb_page - Clear an iommu tlb entry - * @obj: target iommu - * @da: iommu device virtual address - * - * Clear an iommu tlb entry which includes 'da' address. - **/ -void flush_iotlb_page(struct iommu *obj, u32 da) -{ - int i; - struct cr_regs cr; - - clk_enable(obj->clk); - - for_each_iotlb_cr(obj, obj->nr_tlb_entries, i, cr) { - u32 start; - size_t bytes; - - if (!iotlb_cr_valid(&cr)) - continue; - - start = iotlb_cr_to_virt(&cr); - bytes = iopgsz_to_bytes(cr.cam & 3); - - if ((start <= da) && (da < start + bytes)) { - dev_dbg(obj->dev, "%s: %08x<=%08x(%x)\n", - __func__, start, da, bytes); - iotlb_load_cr(obj, &cr); - iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY); - } - } - clk_disable(obj->clk); - - if (i == obj->nr_tlb_entries) - dev_dbg(obj->dev, "%s: no page for %08x\n", __func__, da); -} -EXPORT_SYMBOL_GPL(flush_iotlb_page); - -/** - * flush_iotlb_range - Clear an iommu tlb entries - * @obj: target iommu - * @start: iommu device virtual address(start) - * @end: iommu device virtual address(end) - * - * Clear an iommu tlb entry which includes 'da' address. - **/ -void flush_iotlb_range(struct iommu *obj, u32 start, u32 end) -{ - u32 da = start; - - while (da < end) { - flush_iotlb_page(obj, da); - /* FIXME: Optimize for multiple page size */ - da += IOPTE_SIZE; - } -} -EXPORT_SYMBOL_GPL(flush_iotlb_range); - -/** - * flush_iotlb_all - Clear all iommu tlb entries - * @obj: target iommu - **/ -void flush_iotlb_all(struct iommu *obj) -{ - struct iotlb_lock l; - - clk_enable(obj->clk); - - l.base = 0; - l.vict = 0; - iotlb_lock_set(obj, &l); - - iommu_write_reg(obj, 1, MMU_GFLUSH); - - clk_disable(obj->clk); -} -EXPORT_SYMBOL_GPL(flush_iotlb_all); - -/** - * iommu_set_twl - enable/disable table walking logic - * @obj: target iommu - * @on: enable/disable - * - * Function used to enable/disable TWL. If one wants to work - * exclusively with locked TLB entries and receive notifications - * for TLB miss then call this function to disable TWL. - */ -void iommu_set_twl(struct iommu *obj, bool on) -{ - clk_enable(obj->clk); - arch_iommu->set_twl(obj, on); - clk_disable(obj->clk); -} -EXPORT_SYMBOL_GPL(iommu_set_twl); - -#if defined(CONFIG_OMAP_IOMMU_DEBUG_MODULE) - -ssize_t iommu_dump_ctx(struct iommu *obj, char *buf, ssize_t bytes) -{ - if (!obj || !buf) - return -EINVAL; - - clk_enable(obj->clk); - - bytes = arch_iommu->dump_ctx(obj, buf, bytes); - - clk_disable(obj->clk); - - return bytes; -} -EXPORT_SYMBOL_GPL(iommu_dump_ctx); - -static int __dump_tlb_entries(struct iommu *obj, struct cr_regs *crs, int num) -{ - int i; - struct iotlb_lock saved; - struct cr_regs tmp; - struct cr_regs *p = crs; - - clk_enable(obj->clk); - iotlb_lock_get(obj, &saved); - - for_each_iotlb_cr(obj, num, i, tmp) { - if (!iotlb_cr_valid(&tmp)) - continue; - *p++ = tmp; - } - - iotlb_lock_set(obj, &saved); - clk_disable(obj->clk); - - return p - crs; -} - -/** - * dump_tlb_entries - dump cr arrays to given buffer - * @obj: target iommu - * @buf: output buffer - **/ -size_t dump_tlb_entries(struct iommu *obj, char *buf, ssize_t bytes) -{ - int i, num; - struct cr_regs *cr; - char *p = buf; - - num = bytes / sizeof(*cr); - num = min(obj->nr_tlb_entries, num); - - cr = kcalloc(num, sizeof(*cr), GFP_KERNEL); - if (!cr) - return 0; - - num = __dump_tlb_entries(obj, cr, num); - for (i = 0; i < num; i++) - p += iotlb_dump_cr(obj, cr + i, p); - kfree(cr); - - return p - buf; -} -EXPORT_SYMBOL_GPL(dump_tlb_entries); - -int foreach_iommu_device(void *data, int (*fn)(struct device *, void *)) -{ - return driver_for_each_device(&omap_iommu_driver.driver, - NULL, data, fn); -} -EXPORT_SYMBOL_GPL(foreach_iommu_device); - -#endif /* CONFIG_OMAP_IOMMU_DEBUG_MODULE */ - -/* - * H/W pagetable operations - */ -static void flush_iopgd_range(u32 *first, u32 *last) -{ - /* FIXME: L2 cache should be taken care of if it exists */ - do { - asm("mcr p15, 0, %0, c7, c10, 1 @ flush_pgd" - : : "r" (first)); - first += L1_CACHE_BYTES / sizeof(*first); - } while (first <= last); -} - -static void flush_iopte_range(u32 *first, u32 *last) -{ - /* FIXME: L2 cache should be taken care of if it exists */ - do { - asm("mcr p15, 0, %0, c7, c10, 1 @ flush_pte" - : : "r" (first)); - first += L1_CACHE_BYTES / sizeof(*first); - } while (first <= last); -} - -static void iopte_free(u32 *iopte) -{ - /* Note: freed iopte's must be clean ready for re-use */ - kmem_cache_free(iopte_cachep, iopte); -} - -static u32 *iopte_alloc(struct iommu *obj, u32 *iopgd, u32 da) -{ - u32 *iopte; - - /* a table has already existed */ - if (*iopgd) - goto pte_ready; - - /* - * do the allocation outside the page table lock - */ - spin_unlock(&obj->page_table_lock); - iopte = kmem_cache_zalloc(iopte_cachep, GFP_KERNEL); - spin_lock(&obj->page_table_lock); - - if (!*iopgd) { - if (!iopte) - return ERR_PTR(-ENOMEM); - - *iopgd = virt_to_phys(iopte) | IOPGD_TABLE; - flush_iopgd_range(iopgd, iopgd); - - dev_vdbg(obj->dev, "%s: a new pte:%p\n", __func__, iopte); - } else { - /* We raced, free the reduniovant table */ - iopte_free(iopte); - } - -pte_ready: - iopte = iopte_offset(iopgd, da); - - dev_vdbg(obj->dev, - "%s: da:%08x pgd:%p *pgd:%08x pte:%p *pte:%08x\n", - __func__, da, iopgd, *iopgd, iopte, *iopte); - - return iopte; -} - -static int iopgd_alloc_section(struct iommu *obj, u32 da, u32 pa, u32 prot) -{ - u32 *iopgd = iopgd_offset(obj, da); - - if ((da | pa) & ~IOSECTION_MASK) { - dev_err(obj->dev, "%s: %08x:%08x should aligned on %08lx\n", - __func__, da, pa, IOSECTION_SIZE); - return -EINVAL; - } - - *iopgd = (pa & IOSECTION_MASK) | prot | IOPGD_SECTION; - flush_iopgd_range(iopgd, iopgd); - return 0; -} - -static int iopgd_alloc_super(struct iommu *obj, u32 da, u32 pa, u32 prot) -{ - u32 *iopgd = iopgd_offset(obj, da); - int i; - - if ((da | pa) & ~IOSUPER_MASK) { - dev_err(obj->dev, "%s: %08x:%08x should aligned on %08lx\n", - __func__, da, pa, IOSUPER_SIZE); - return -EINVAL; - } - - for (i = 0; i < 16; i++) - *(iopgd + i) = (pa & IOSUPER_MASK) | prot | IOPGD_SUPER; - flush_iopgd_range(iopgd, iopgd + 15); - return 0; -} - -static int iopte_alloc_page(struct iommu *obj, u32 da, u32 pa, u32 prot) -{ - u32 *iopgd = iopgd_offset(obj, da); - u32 *iopte = iopte_alloc(obj, iopgd, da); - - if (IS_ERR(iopte)) - return PTR_ERR(iopte); - - *iopte = (pa & IOPAGE_MASK) | prot | IOPTE_SMALL; - flush_iopte_range(iopte, iopte); - - dev_vdbg(obj->dev, "%s: da:%08x pa:%08x pte:%p *pte:%08x\n", - __func__, da, pa, iopte, *iopte); - - return 0; -} - -static int iopte_alloc_large(struct iommu *obj, u32 da, u32 pa, u32 prot) -{ - u32 *iopgd = iopgd_offset(obj, da); - u32 *iopte = iopte_alloc(obj, iopgd, da); - int i; - - if ((da | pa) & ~IOLARGE_MASK) { - dev_err(obj->dev, "%s: %08x:%08x should aligned on %08lx\n", - __func__, da, pa, IOLARGE_SIZE); - return -EINVAL; - } - - if (IS_ERR(iopte)) - return PTR_ERR(iopte); - - for (i = 0; i < 16; i++) - *(iopte + i) = (pa & IOLARGE_MASK) | prot | IOPTE_LARGE; - flush_iopte_range(iopte, iopte + 15); - return 0; -} - -static int iopgtable_store_entry_core(struct iommu *obj, struct iotlb_entry *e) -{ - int (*fn)(struct iommu *, u32, u32, u32); - u32 prot; - int err; - - if (!obj || !e) - return -EINVAL; - - switch (e->pgsz) { - case MMU_CAM_PGSZ_16M: - fn = iopgd_alloc_super; - break; - case MMU_CAM_PGSZ_1M: - fn = iopgd_alloc_section; - break; - case MMU_CAM_PGSZ_64K: - fn = iopte_alloc_large; - break; - case MMU_CAM_PGSZ_4K: - fn = iopte_alloc_page; - break; - default: - fn = NULL; - BUG(); - break; - } - - prot = get_iopte_attr(e); - - spin_lock(&obj->page_table_lock); - err = fn(obj, e->da, e->pa, prot); - spin_unlock(&obj->page_table_lock); - - return err; -} - -/** - * iopgtable_store_entry - Make an iommu pte entry - * @obj: target iommu - * @e: an iommu tlb entry info - **/ -int iopgtable_store_entry(struct iommu *obj, struct iotlb_entry *e) -{ - int err; - - flush_iotlb_page(obj, e->da); - err = iopgtable_store_entry_core(obj, e); -#ifdef PREFETCH_IOTLB - if (!err) - load_iotlb_entry(obj, e); -#endif - return err; -} -EXPORT_SYMBOL_GPL(iopgtable_store_entry); - -/** - * iopgtable_lookup_entry - Lookup an iommu pte entry - * @obj: target iommu - * @da: iommu device virtual address - * @ppgd: iommu pgd entry pointer to be returned - * @ppte: iommu pte entry pointer to be returned - **/ -void iopgtable_lookup_entry(struct iommu *obj, u32 da, u32 **ppgd, u32 **ppte) -{ - u32 *iopgd, *iopte = NULL; - - iopgd = iopgd_offset(obj, da); - if (!*iopgd) - goto out; - - if (iopgd_is_table(*iopgd)) - iopte = iopte_offset(iopgd, da); -out: - *ppgd = iopgd; - *ppte = iopte; -} -EXPORT_SYMBOL_GPL(iopgtable_lookup_entry); - -static size_t iopgtable_clear_entry_core(struct iommu *obj, u32 da) -{ - size_t bytes; - u32 *iopgd = iopgd_offset(obj, da); - int nent = 1; - - if (!*iopgd) - return 0; - - if (iopgd_is_table(*iopgd)) { - int i; - u32 *iopte = iopte_offset(iopgd, da); - - bytes = IOPTE_SIZE; - if (*iopte & IOPTE_LARGE) { - nent *= 16; - /* rewind to the 1st entry */ - iopte = iopte_offset(iopgd, (da & IOLARGE_MASK)); - } - bytes *= nent; - memset(iopte, 0, nent * sizeof(*iopte)); - flush_iopte_range(iopte, iopte + (nent - 1) * sizeof(*iopte)); - - /* - * do table walk to check if this table is necessary or not - */ - iopte = iopte_offset(iopgd, 0); - for (i = 0; i < PTRS_PER_IOPTE; i++) - if (iopte[i]) - goto out; - - iopte_free(iopte); - nent = 1; /* for the next L1 entry */ - } else { - bytes = IOPGD_SIZE; - if ((*iopgd & IOPGD_SUPER) == IOPGD_SUPER) { - nent *= 16; - /* rewind to the 1st entry */ - iopgd = iopgd_offset(obj, (da & IOSUPER_MASK)); - } - bytes *= nent; - } - memset(iopgd, 0, nent * sizeof(*iopgd)); - flush_iopgd_range(iopgd, iopgd + (nent - 1) * sizeof(*iopgd)); -out: - return bytes; -} - -/** - * iopgtable_clear_entry - Remove an iommu pte entry - * @obj: target iommu - * @da: iommu device virtual address - **/ -size_t iopgtable_clear_entry(struct iommu *obj, u32 da) -{ - size_t bytes; - - spin_lock(&obj->page_table_lock); - - bytes = iopgtable_clear_entry_core(obj, da); - flush_iotlb_page(obj, da); - - spin_unlock(&obj->page_table_lock); - - return bytes; -} -EXPORT_SYMBOL_GPL(iopgtable_clear_entry); - -static void iopgtable_clear_entry_all(struct iommu *obj) -{ - int i; - - spin_lock(&obj->page_table_lock); - - for (i = 0; i < PTRS_PER_IOPGD; i++) { - u32 da; - u32 *iopgd; - - da = i << IOPGD_SHIFT; - iopgd = iopgd_offset(obj, da); - - if (!*iopgd) - continue; - - if (iopgd_is_table(*iopgd)) - iopte_free(iopte_offset(iopgd, 0)); - - *iopgd = 0; - flush_iopgd_range(iopgd, iopgd); - } - - flush_iotlb_all(obj); - - spin_unlock(&obj->page_table_lock); -} - -/* - * Device IOMMU generic operations - */ -static irqreturn_t iommu_fault_handler(int irq, void *data) -{ - u32 da, errs; - u32 *iopgd, *iopte; - struct iommu *obj = data; - - if (!obj->refcount) - return IRQ_NONE; - - clk_enable(obj->clk); - errs = iommu_report_fault(obj, &da); - clk_disable(obj->clk); - if (errs == 0) - return IRQ_HANDLED; - - /* Fault callback or TLB/PTE Dynamic loading */ - if (obj->isr && !obj->isr(obj, da, errs, obj->isr_priv)) - return IRQ_HANDLED; - - iommu_disable(obj); - - iopgd = iopgd_offset(obj, da); - - if (!iopgd_is_table(*iopgd)) { - dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p " - "*pgd:px%08x\n", obj->name, errs, da, iopgd, *iopgd); - return IRQ_NONE; - } - - iopte = iopte_offset(iopgd, da); - - dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p *pgd:0x%08x " - "pte:0x%p *pte:0x%08x\n", obj->name, errs, da, iopgd, *iopgd, - iopte, *iopte); - - return IRQ_NONE; -} - -static int device_match_by_alias(struct device *dev, void *data) -{ - struct iommu *obj = to_iommu(dev); - const char *name = data; - - pr_debug("%s: %s %s\n", __func__, obj->name, name); - - return strcmp(obj->name, name) == 0; -} - -/** - * iommu_set_da_range - Set a valid device address range - * @obj: target iommu - * @start Start of valid range - * @end End of valid range - **/ -int iommu_set_da_range(struct iommu *obj, u32 start, u32 end) -{ - - if (!obj) - return -EFAULT; - - if (end < start || !PAGE_ALIGN(start | end)) - return -EINVAL; - - obj->da_start = start; - obj->da_end = end; - - return 0; -} -EXPORT_SYMBOL_GPL(iommu_set_da_range); - -/** - * iommu_get - Get iommu handler - * @name: target iommu name - **/ -struct iommu *iommu_get(const char *name) -{ - int err = -ENOMEM; - struct device *dev; - struct iommu *obj; - - dev = driver_find_device(&omap_iommu_driver.driver, NULL, (void *)name, - device_match_by_alias); - if (!dev) - return ERR_PTR(-ENODEV); - - obj = to_iommu(dev); - - mutex_lock(&obj->iommu_lock); - - if (obj->refcount++ == 0) { - err = iommu_enable(obj); - if (err) - goto err_enable; - flush_iotlb_all(obj); - } - - if (!try_module_get(obj->owner)) - goto err_module; - - mutex_unlock(&obj->iommu_lock); - - dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name); - return obj; - -err_module: - if (obj->refcount == 1) - iommu_disable(obj); -err_enable: - obj->refcount--; - mutex_unlock(&obj->iommu_lock); - return ERR_PTR(err); -} -EXPORT_SYMBOL_GPL(iommu_get); - -/** - * iommu_put - Put back iommu handler - * @obj: target iommu - **/ -void iommu_put(struct iommu *obj) -{ - if (!obj || IS_ERR(obj)) - return; - - mutex_lock(&obj->iommu_lock); - - if (--obj->refcount == 0) - iommu_disable(obj); - - module_put(obj->owner); - - mutex_unlock(&obj->iommu_lock); - - dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name); -} -EXPORT_SYMBOL_GPL(iommu_put); - -int iommu_set_isr(const char *name, - int (*isr)(struct iommu *obj, u32 da, u32 iommu_errs, - void *priv), - void *isr_priv) -{ - struct device *dev; - struct iommu *obj; - - dev = driver_find_device(&omap_iommu_driver.driver, NULL, (void *)name, - device_match_by_alias); - if (!dev) - return -ENODEV; - - obj = to_iommu(dev); - mutex_lock(&obj->iommu_lock); - if (obj->refcount != 0) { - mutex_unlock(&obj->iommu_lock); - return -EBUSY; - } - obj->isr = isr; - obj->isr_priv = isr_priv; - mutex_unlock(&obj->iommu_lock); - - return 0; -} -EXPORT_SYMBOL_GPL(iommu_set_isr); - -/* - * OMAP Device MMU(IOMMU) detection - */ -static int __devinit omap_iommu_probe(struct platform_device *pdev) -{ - int err = -ENODEV; - void *p; - int irq; - struct iommu *obj; - struct resource *res; - struct iommu_platform_data *pdata = pdev->dev.platform_data; - - if (pdev->num_resources != 2) - return -EINVAL; - - obj = kzalloc(sizeof(*obj) + MMU_REG_SIZE, GFP_KERNEL); - if (!obj) - return -ENOMEM; - - obj->clk = clk_get(&pdev->dev, pdata->clk_name); - if (IS_ERR(obj->clk)) - goto err_clk; - - obj->nr_tlb_entries = pdata->nr_tlb_entries; - obj->name = pdata->name; - obj->dev = &pdev->dev; - obj->ctx = (void *)obj + sizeof(*obj); - obj->da_start = pdata->da_start; - obj->da_end = pdata->da_end; - - mutex_init(&obj->iommu_lock); - mutex_init(&obj->mmap_lock); - spin_lock_init(&obj->page_table_lock); - INIT_LIST_HEAD(&obj->mmap); - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - err = -ENODEV; - goto err_mem; - } - - res = request_mem_region(res->start, resource_size(res), - dev_name(&pdev->dev)); - if (!res) { - err = -EIO; - goto err_mem; - } - - obj->regbase = ioremap(res->start, resource_size(res)); - if (!obj->regbase) { - err = -ENOMEM; - goto err_ioremap; - } - - irq = platform_get_irq(pdev, 0); - if (irq < 0) { - err = -ENODEV; - goto err_irq; - } - err = request_irq(irq, iommu_fault_handler, IRQF_SHARED, - dev_name(&pdev->dev), obj); - if (err < 0) - goto err_irq; - platform_set_drvdata(pdev, obj); - - p = (void *)__get_free_pages(GFP_KERNEL, get_order(IOPGD_TABLE_SIZE)); - if (!p) { - err = -ENOMEM; - goto err_pgd; - } - memset(p, 0, IOPGD_TABLE_SIZE); - clean_dcache_area(p, IOPGD_TABLE_SIZE); - obj->iopgd = p; - - BUG_ON(!IS_ALIGNED((unsigned long)obj->iopgd, IOPGD_TABLE_SIZE)); - - dev_info(&pdev->dev, "%s registered\n", obj->name); - return 0; - -err_pgd: - free_irq(irq, obj); -err_irq: - iounmap(obj->regbase); -err_ioremap: - release_mem_region(res->start, resource_size(res)); -err_mem: - clk_put(obj->clk); -err_clk: - kfree(obj); - return err; -} - -static int __devexit omap_iommu_remove(struct platform_device *pdev) -{ - int irq; - struct resource *res; - struct iommu *obj = platform_get_drvdata(pdev); - - platform_set_drvdata(pdev, NULL); - - iopgtable_clear_entry_all(obj); - free_pages((unsigned long)obj->iopgd, get_order(IOPGD_TABLE_SIZE)); - - irq = platform_get_irq(pdev, 0); - free_irq(irq, obj); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(res->start, resource_size(res)); - iounmap(obj->regbase); - - clk_put(obj->clk); - dev_info(&pdev->dev, "%s removed\n", obj->name); - kfree(obj); - return 0; -} - -static struct platform_driver omap_iommu_driver = { - .probe = omap_iommu_probe, - .remove = __devexit_p(omap_iommu_remove), - .driver = { - .name = "omap-iommu", - }, -}; - -static void iopte_cachep_ctor(void *iopte) -{ - clean_dcache_area(iopte, IOPTE_TABLE_SIZE); -} - -static int __init omap_iommu_init(void) -{ - struct kmem_cache *p; - const unsigned long flags = SLAB_HWCACHE_ALIGN; - size_t align = 1 << 10; /* L2 pagetable alignement */ - - p = kmem_cache_create("iopte_cache", IOPTE_TABLE_SIZE, align, flags, - iopte_cachep_ctor); - if (!p) - return -ENOMEM; - iopte_cachep = p; - - return platform_driver_register(&omap_iommu_driver); -} -module_init(omap_iommu_init); - -static void __exit omap_iommu_exit(void) -{ - kmem_cache_destroy(iopte_cachep); - - platform_driver_unregister(&omap_iommu_driver); -} -module_exit(omap_iommu_exit); - -MODULE_DESCRIPTION("omap iommu: tlb and pagetable primitives"); -MODULE_ALIAS("platform:omap-iommu"); -MODULE_AUTHOR("Hiroshi DOYU, Paul Mundt and Toshihiro Kobayashi"); -MODULE_LICENSE("GPL v2"); diff --git a/arch/arm/plat-omap/iovmm.c b/arch/arm/plat-omap/iovmm.c deleted file mode 100644 index 79e7fedb8602..000000000000 --- a/arch/arm/plat-omap/iovmm.c +++ /dev/null @@ -1,904 +0,0 @@ -/* - * omap iommu: simple virtual address space management - * - * Copyright (C) 2008-2009 Nokia Corporation - * - * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/err.h> -#include <linux/slab.h> -#include <linux/vmalloc.h> -#include <linux/device.h> -#include <linux/scatterlist.h> - -#include <asm/cacheflush.h> -#include <asm/mach/map.h> - -#include <plat/iommu.h> -#include <plat/iovmm.h> - -#include "iopgtable.h" - -/* - * A device driver needs to create address mappings between: - * - * - iommu/device address - * - physical address - * - mpu virtual address - * - * There are 4 possible patterns for them: - * - * |iova/ mapping iommu_ page - * | da pa va (d)-(p)-(v) function type - * --------------------------------------------------------------------------- - * 1 | c c c 1 - 1 - 1 _kmap() / _kunmap() s - * 2 | c c,a c 1 - 1 - 1 _kmalloc()/ _kfree() s - * 3 | c d c 1 - n - 1 _vmap() / _vunmap() s - * 4 | c d,a c 1 - n - 1 _vmalloc()/ _vfree() n* - * - * - * 'iova': device iommu virtual address - * 'da': alias of 'iova' - * 'pa': physical address - * 'va': mpu virtual address - * - * 'c': contiguous memory area - * 'd': discontiguous memory area - * 'a': anonymous memory allocation - * '()': optional feature - * - * 'n': a normal page(4KB) size is used. - * 's': multiple iommu superpage(16MB, 1MB, 64KB, 4KB) size is used. - * - * '*': not yet, but feasible. - */ - -static struct kmem_cache *iovm_area_cachep; - -/* return total bytes of sg buffers */ -static size_t sgtable_len(const struct sg_table *sgt) -{ - unsigned int i, total = 0; - struct scatterlist *sg; - - if (!sgt) - return 0; - - for_each_sg(sgt->sgl, sg, sgt->nents, i) { - size_t bytes; - - bytes = sg->length; - - if (!iopgsz_ok(bytes)) { - pr_err("%s: sg[%d] not iommu pagesize(%x)\n", - __func__, i, bytes); - return 0; - } - - total += bytes; - } - - return total; -} -#define sgtable_ok(x) (!!sgtable_len(x)) - -static unsigned max_alignment(u32 addr) -{ - int i; - unsigned pagesize[] = { SZ_16M, SZ_1M, SZ_64K, SZ_4K, }; - for (i = 0; i < ARRAY_SIZE(pagesize) && addr & (pagesize[i] - 1); i++) - ; - return (i < ARRAY_SIZE(pagesize)) ? pagesize[i] : 0; -} - -/* - * calculate the optimal number sg elements from total bytes based on - * iommu superpages - */ -static unsigned sgtable_nents(size_t bytes, u32 da, u32 pa) -{ - unsigned nr_entries = 0, ent_sz; - - if (!IS_ALIGNED(bytes, PAGE_SIZE)) { - pr_err("%s: wrong size %08x\n", __func__, bytes); - return 0; - } - - while (bytes) { - ent_sz = max_alignment(da | pa); - ent_sz = min_t(unsigned, ent_sz, iopgsz_max(bytes)); - nr_entries++; - da += ent_sz; - pa += ent_sz; - bytes -= ent_sz; - } - - return nr_entries; -} - -/* allocate and initialize sg_table header(a kind of 'superblock') */ -static struct sg_table *sgtable_alloc(const size_t bytes, u32 flags, - u32 da, u32 pa) -{ - unsigned int nr_entries; - int err; - struct sg_table *sgt; - - if (!bytes) - return ERR_PTR(-EINVAL); - - if (!IS_ALIGNED(bytes, PAGE_SIZE)) - return ERR_PTR(-EINVAL); - - if (flags & IOVMF_LINEAR) { - nr_entries = sgtable_nents(bytes, da, pa); - if (!nr_entries) - return ERR_PTR(-EINVAL); - } else - nr_entries = bytes / PAGE_SIZE; - - sgt = kzalloc(sizeof(*sgt), GFP_KERNEL); - if (!sgt) - return ERR_PTR(-ENOMEM); - - err = sg_alloc_table(sgt, nr_entries, GFP_KERNEL); - if (err) { - kfree(sgt); - return ERR_PTR(err); - } - - pr_debug("%s: sgt:%p(%d entries)\n", __func__, sgt, nr_entries); - - return sgt; -} - -/* free sg_table header(a kind of superblock) */ -static void sgtable_free(struct sg_table *sgt) -{ - if (!sgt) - return; - - sg_free_table(sgt); - kfree(sgt); - - pr_debug("%s: sgt:%p\n", __func__, sgt); -} - -/* map 'sglist' to a contiguous mpu virtual area and return 'va' */ -static void *vmap_sg(const struct sg_table *sgt) -{ - u32 va; - size_t total; - unsigned int i; - struct scatterlist *sg; - struct vm_struct *new; - const struct mem_type *mtype; - - mtype = get_mem_type(MT_DEVICE); - if (!mtype) - return ERR_PTR(-EINVAL); - - total = sgtable_len(sgt); - if (!total) - return ERR_PTR(-EINVAL); - - new = __get_vm_area(total, VM_IOREMAP, VMALLOC_START, VMALLOC_END); - if (!new) - return ERR_PTR(-ENOMEM); - va = (u32)new->addr; - - for_each_sg(sgt->sgl, sg, sgt->nents, i) { - size_t bytes; - u32 pa; - int err; - - pa = sg_phys(sg); - bytes = sg->length; - - BUG_ON(bytes != PAGE_SIZE); - - err = ioremap_page(va, pa, mtype); - if (err) - goto err_out; - - va += bytes; - } - - flush_cache_vmap((unsigned long)new->addr, - (unsigned long)(new->addr + total)); - return new->addr; - -err_out: - WARN_ON(1); /* FIXME: cleanup some mpu mappings */ - vunmap(new->addr); - return ERR_PTR(-EAGAIN); -} - -static inline void vunmap_sg(const void *va) -{ - vunmap(va); -} - -static struct iovm_struct *__find_iovm_area(struct iommu *obj, const u32 da) -{ - struct iovm_struct *tmp; - - list_for_each_entry(tmp, &obj->mmap, list) { - if ((da >= tmp->da_start) && (da < tmp->da_end)) { - size_t len; - - len = tmp->da_end - tmp->da_start; - - dev_dbg(obj->dev, "%s: %08x-%08x-%08x(%x) %08x\n", - __func__, tmp->da_start, da, tmp->da_end, len, - tmp->flags); - - return tmp; - } - } - - return NULL; -} - -/** - * find_iovm_area - find iovma which includes @da - * @da: iommu device virtual address - * - * Find the existing iovma starting at @da - */ -struct iovm_struct *find_iovm_area(struct iommu *obj, u32 da) -{ - struct iovm_struct *area; - - mutex_lock(&obj->mmap_lock); - area = __find_iovm_area(obj, da); - mutex_unlock(&obj->mmap_lock); - - return area; -} -EXPORT_SYMBOL_GPL(find_iovm_area); - -/* - * This finds the hole(area) which fits the requested address and len - * in iovmas mmap, and returns the new allocated iovma. - */ -static struct iovm_struct *alloc_iovm_area(struct iommu *obj, u32 da, - size_t bytes, u32 flags) -{ - struct iovm_struct *new, *tmp; - u32 start, prev_end, alignment; - - if (!obj || !bytes) - return ERR_PTR(-EINVAL); - - start = da; - alignment = PAGE_SIZE; - - if (~flags & IOVMF_DA_FIXED) { - /* Don't map address 0 */ - start = obj->da_start ? obj->da_start : alignment; - - if (flags & IOVMF_LINEAR) - alignment = iopgsz_max(bytes); - start = roundup(start, alignment); - } else if (start < obj->da_start || start > obj->da_end || - obj->da_end - start < bytes) { - return ERR_PTR(-EINVAL); - } - - tmp = NULL; - if (list_empty(&obj->mmap)) - goto found; - - prev_end = 0; - list_for_each_entry(tmp, &obj->mmap, list) { - - if (prev_end > start) - break; - - if (tmp->da_start > start && (tmp->da_start - start) >= bytes) - goto found; - - if (tmp->da_end >= start && ~flags & IOVMF_DA_FIXED) - start = roundup(tmp->da_end + 1, alignment); - - prev_end = tmp->da_end; - } - - if ((start >= prev_end) && (obj->da_end - start >= bytes)) - goto found; - - dev_dbg(obj->dev, "%s: no space to fit %08x(%x) flags: %08x\n", - __func__, da, bytes, flags); - - return ERR_PTR(-EINVAL); - -found: - new = kmem_cache_zalloc(iovm_area_cachep, GFP_KERNEL); - if (!new) - return ERR_PTR(-ENOMEM); - - new->iommu = obj; - new->da_start = start; - new->da_end = start + bytes; - new->flags = flags; - - /* - * keep ascending order of iovmas - */ - if (tmp) - list_add_tail(&new->list, &tmp->list); - else - list_add(&new->list, &obj->mmap); - - dev_dbg(obj->dev, "%s: found %08x-%08x-%08x(%x) %08x\n", - __func__, new->da_start, start, new->da_end, bytes, flags); - - return new; -} - -static void free_iovm_area(struct iommu *obj, struct iovm_struct *area) -{ - size_t bytes; - - BUG_ON(!obj || !area); - - bytes = area->da_end - area->da_start; - - dev_dbg(obj->dev, "%s: %08x-%08x(%x) %08x\n", - __func__, area->da_start, area->da_end, bytes, area->flags); - - list_del(&area->list); - kmem_cache_free(iovm_area_cachep, area); -} - -/** - * da_to_va - convert (d) to (v) - * @obj: objective iommu - * @da: iommu device virtual address - * @va: mpu virtual address - * - * Returns mpu virtual addr which corresponds to a given device virtual addr - */ -void *da_to_va(struct iommu *obj, u32 da) -{ - void *va = NULL; - struct iovm_struct *area; - - mutex_lock(&obj->mmap_lock); - - area = __find_iovm_area(obj, da); - if (!area) { - dev_dbg(obj->dev, "%s: no da area(%08x)\n", __func__, da); - goto out; - } - va = area->va; -out: - mutex_unlock(&obj->mmap_lock); - - return va; -} -EXPORT_SYMBOL_GPL(da_to_va); - -static void sgtable_fill_vmalloc(struct sg_table *sgt, void *_va) -{ - unsigned int i; - struct scatterlist *sg; - void *va = _va; - void *va_end; - - for_each_sg(sgt->sgl, sg, sgt->nents, i) { - struct page *pg; - const size_t bytes = PAGE_SIZE; - - /* - * iommu 'superpage' isn't supported with 'iommu_vmalloc()' - */ - pg = vmalloc_to_page(va); - BUG_ON(!pg); - sg_set_page(sg, pg, bytes, 0); - - va += bytes; - } - - va_end = _va + PAGE_SIZE * i; -} - -static inline void sgtable_drain_vmalloc(struct sg_table *sgt) -{ - /* - * Actually this is not necessary at all, just exists for - * consistency of the code readability. - */ - BUG_ON(!sgt); -} - -static void sgtable_fill_kmalloc(struct sg_table *sgt, u32 pa, u32 da, - size_t len) -{ - unsigned int i; - struct scatterlist *sg; - - for_each_sg(sgt->sgl, sg, sgt->nents, i) { - unsigned bytes; - - bytes = max_alignment(da | pa); - bytes = min_t(unsigned, bytes, iopgsz_max(len)); - - BUG_ON(!iopgsz_ok(bytes)); - - sg_set_buf(sg, phys_to_virt(pa), bytes); - /* - * 'pa' is cotinuous(linear). - */ - pa += bytes; - da += bytes; - len -= bytes; - } - BUG_ON(len); -} - -static inline void sgtable_drain_kmalloc(struct sg_table *sgt) -{ - /* - * Actually this is not necessary at all, just exists for - * consistency of the code readability - */ - BUG_ON(!sgt); -} - -/* create 'da' <-> 'pa' mapping from 'sgt' */ -static int map_iovm_area(struct iommu *obj, struct iovm_struct *new, - const struct sg_table *sgt, u32 flags) -{ - int err; - unsigned int i, j; - struct scatterlist *sg; - u32 da = new->da_start; - - if (!obj || !sgt) - return -EINVAL; - - BUG_ON(!sgtable_ok(sgt)); - - for_each_sg(sgt->sgl, sg, sgt->nents, i) { - u32 pa; - int pgsz; - size_t bytes; - struct iotlb_entry e; - - pa = sg_phys(sg); - bytes = sg->length; - - flags &= ~IOVMF_PGSZ_MASK; - pgsz = bytes_to_iopgsz(bytes); - if (pgsz < 0) - goto err_out; - flags |= pgsz; - - pr_debug("%s: [%d] %08x %08x(%x)\n", __func__, - i, da, pa, bytes); - - iotlb_init_entry(&e, da, pa, flags); - err = iopgtable_store_entry(obj, &e); - if (err) - goto err_out; - - da += bytes; - } - return 0; - -err_out: - da = new->da_start; - - for_each_sg(sgt->sgl, sg, i, j) { - size_t bytes; - - bytes = iopgtable_clear_entry(obj, da); - - BUG_ON(!iopgsz_ok(bytes)); - - da += bytes; - } - return err; -} - -/* release 'da' <-> 'pa' mapping */ -static void unmap_iovm_area(struct iommu *obj, struct iovm_struct *area) -{ - u32 start; - size_t total = area->da_end - area->da_start; - - BUG_ON((!total) || !IS_ALIGNED(total, PAGE_SIZE)); - - start = area->da_start; - while (total > 0) { - size_t bytes; - - bytes = iopgtable_clear_entry(obj, start); - if (bytes == 0) - bytes = PAGE_SIZE; - else - dev_dbg(obj->dev, "%s: unmap %08x(%x) %08x\n", - __func__, start, bytes, area->flags); - - BUG_ON(!IS_ALIGNED(bytes, PAGE_SIZE)); - - total -= bytes; - start += bytes; - } - BUG_ON(total); -} - -/* template function for all unmapping */ -static struct sg_table *unmap_vm_area(struct iommu *obj, const u32 da, - void (*fn)(const void *), u32 flags) -{ - struct sg_table *sgt = NULL; - struct iovm_struct *area; - - if (!IS_ALIGNED(da, PAGE_SIZE)) { - dev_err(obj->dev, "%s: alignment err(%08x)\n", __func__, da); - return NULL; - } - - mutex_lock(&obj->mmap_lock); - - area = __find_iovm_area(obj, da); - if (!area) { - dev_dbg(obj->dev, "%s: no da area(%08x)\n", __func__, da); - goto out; - } - - if ((area->flags & flags) != flags) { - dev_err(obj->dev, "%s: wrong flags(%08x)\n", __func__, - area->flags); - goto out; - } - sgt = (struct sg_table *)area->sgt; - - unmap_iovm_area(obj, area); - - fn(area->va); - - dev_dbg(obj->dev, "%s: %08x-%08x-%08x(%x) %08x\n", __func__, - area->da_start, da, area->da_end, - area->da_end - area->da_start, area->flags); - - free_iovm_area(obj, area); -out: - mutex_unlock(&obj->mmap_lock); - - return sgt; -} - -static u32 map_iommu_region(struct iommu *obj, u32 da, - const struct sg_table *sgt, void *va, size_t bytes, u32 flags) -{ - int err = -ENOMEM; - struct iovm_struct *new; - - mutex_lock(&obj->mmap_lock); - - new = alloc_iovm_area(obj, da, bytes, flags); - if (IS_ERR(new)) { - err = PTR_ERR(new); - goto err_alloc_iovma; - } - new->va = va; - new->sgt = sgt; - - if (map_iovm_area(obj, new, sgt, new->flags)) - goto err_map; - - mutex_unlock(&obj->mmap_lock); - - dev_dbg(obj->dev, "%s: da:%08x(%x) flags:%08x va:%p\n", - __func__, new->da_start, bytes, new->flags, va); - - return new->da_start; - -err_map: - free_iovm_area(obj, new); -err_alloc_iovma: - mutex_unlock(&obj->mmap_lock); - return err; -} - -static inline u32 __iommu_vmap(struct iommu *obj, u32 da, - const struct sg_table *sgt, void *va, size_t bytes, u32 flags) -{ - return map_iommu_region(obj, da, sgt, va, bytes, flags); -} - -/** - * iommu_vmap - (d)-(p)-(v) address mapper - * @obj: objective iommu - * @sgt: address of scatter gather table - * @flags: iovma and page property - * - * Creates 1-n-1 mapping with given @sgt and returns @da. - * All @sgt element must be io page size aligned. - */ -u32 iommu_vmap(struct iommu *obj, u32 da, const struct sg_table *sgt, - u32 flags) -{ - size_t bytes; - void *va = NULL; - - if (!obj || !obj->dev || !sgt) - return -EINVAL; - - bytes = sgtable_len(sgt); - if (!bytes) - return -EINVAL; - bytes = PAGE_ALIGN(bytes); - - if (flags & IOVMF_MMIO) { - va = vmap_sg(sgt); - if (IS_ERR(va)) - return PTR_ERR(va); - } - - flags |= IOVMF_DISCONT; - flags |= IOVMF_MMIO; - - da = __iommu_vmap(obj, da, sgt, va, bytes, flags); - if (IS_ERR_VALUE(da)) - vunmap_sg(va); - - return da; -} -EXPORT_SYMBOL_GPL(iommu_vmap); - -/** - * iommu_vunmap - release virtual mapping obtained by 'iommu_vmap()' - * @obj: objective iommu - * @da: iommu device virtual address - * - * Free the iommu virtually contiguous memory area starting at - * @da, which was returned by 'iommu_vmap()'. - */ -struct sg_table *iommu_vunmap(struct iommu *obj, u32 da) -{ - struct sg_table *sgt; - /* - * 'sgt' is allocated before 'iommu_vmalloc()' is called. - * Just returns 'sgt' to the caller to free - */ - sgt = unmap_vm_area(obj, da, vunmap_sg, IOVMF_DISCONT | IOVMF_MMIO); - if (!sgt) - dev_dbg(obj->dev, "%s: No sgt\n", __func__); - return sgt; -} -EXPORT_SYMBOL_GPL(iommu_vunmap); - -/** - * iommu_vmalloc - (d)-(p)-(v) address allocator and mapper - * @obj: objective iommu - * @da: contiguous iommu virtual memory - * @bytes: allocation size - * @flags: iovma and page property - * - * Allocate @bytes linearly and creates 1-n-1 mapping and returns - * @da again, which might be adjusted if 'IOVMF_DA_FIXED' is not set. - */ -u32 iommu_vmalloc(struct iommu *obj, u32 da, size_t bytes, u32 flags) -{ - void *va; - struct sg_table *sgt; - - if (!obj || !obj->dev || !bytes) - return -EINVAL; - - bytes = PAGE_ALIGN(bytes); - - va = vmalloc(bytes); - if (!va) - return -ENOMEM; - - flags |= IOVMF_DISCONT; - flags |= IOVMF_ALLOC; - - sgt = sgtable_alloc(bytes, flags, da, 0); - if (IS_ERR(sgt)) { - da = PTR_ERR(sgt); - goto err_sgt_alloc; - } - sgtable_fill_vmalloc(sgt, va); - - da = __iommu_vmap(obj, da, sgt, va, bytes, flags); - if (IS_ERR_VALUE(da)) - goto err_iommu_vmap; - - return da; - -err_iommu_vmap: - sgtable_drain_vmalloc(sgt); - sgtable_free(sgt); -err_sgt_alloc: - vfree(va); - return da; -} -EXPORT_SYMBOL_GPL(iommu_vmalloc); - -/** - * iommu_vfree - release memory allocated by 'iommu_vmalloc()' - * @obj: objective iommu - * @da: iommu device virtual address - * - * Frees the iommu virtually continuous memory area starting at - * @da, as obtained from 'iommu_vmalloc()'. - */ -void iommu_vfree(struct iommu *obj, const u32 da) -{ - struct sg_table *sgt; - - sgt = unmap_vm_area(obj, da, vfree, IOVMF_DISCONT | IOVMF_ALLOC); - if (!sgt) - dev_dbg(obj->dev, "%s: No sgt\n", __func__); - sgtable_free(sgt); -} -EXPORT_SYMBOL_GPL(iommu_vfree); - -static u32 __iommu_kmap(struct iommu *obj, u32 da, u32 pa, void *va, - size_t bytes, u32 flags) -{ - struct sg_table *sgt; - - sgt = sgtable_alloc(bytes, flags, da, pa); - if (IS_ERR(sgt)) - return PTR_ERR(sgt); - - sgtable_fill_kmalloc(sgt, pa, da, bytes); - - da = map_iommu_region(obj, da, sgt, va, bytes, flags); - if (IS_ERR_VALUE(da)) { - sgtable_drain_kmalloc(sgt); - sgtable_free(sgt); - } - - return da; -} - -/** - * iommu_kmap - (d)-(p)-(v) address mapper - * @obj: objective iommu - * @da: contiguous iommu virtual memory - * @pa: contiguous physical memory - * @flags: iovma and page property - * - * Creates 1-1-1 mapping and returns @da again, which can be - * adjusted if 'IOVMF_DA_FIXED' is not set. - */ -u32 iommu_kmap(struct iommu *obj, u32 da, u32 pa, size_t bytes, - u32 flags) -{ - void *va; - - if (!obj || !obj->dev || !bytes) - return -EINVAL; - - bytes = PAGE_ALIGN(bytes); - - va = ioremap(pa, bytes); - if (!va) - return -ENOMEM; - - flags |= IOVMF_LINEAR; - flags |= IOVMF_MMIO; - - da = __iommu_kmap(obj, da, pa, va, bytes, flags); - if (IS_ERR_VALUE(da)) - iounmap(va); - - return da; -} -EXPORT_SYMBOL_GPL(iommu_kmap); - -/** - * iommu_kunmap - release virtual mapping obtained by 'iommu_kmap()' - * @obj: objective iommu - * @da: iommu device virtual address - * - * Frees the iommu virtually contiguous memory area starting at - * @da, which was passed to and was returned by'iommu_kmap()'. - */ -void iommu_kunmap(struct iommu *obj, u32 da) -{ - struct sg_table *sgt; - typedef void (*func_t)(const void *); - - sgt = unmap_vm_area(obj, da, (func_t)iounmap, - IOVMF_LINEAR | IOVMF_MMIO); - if (!sgt) - dev_dbg(obj->dev, "%s: No sgt\n", __func__); - sgtable_free(sgt); -} -EXPORT_SYMBOL_GPL(iommu_kunmap); - -/** - * iommu_kmalloc - (d)-(p)-(v) address allocator and mapper - * @obj: objective iommu - * @da: contiguous iommu virtual memory - * @bytes: bytes for allocation - * @flags: iovma and page property - * - * Allocate @bytes linearly and creates 1-1-1 mapping and returns - * @da again, which might be adjusted if 'IOVMF_DA_FIXED' is not set. - */ -u32 iommu_kmalloc(struct iommu *obj, u32 da, size_t bytes, u32 flags) -{ - void *va; - u32 pa; - - if (!obj || !obj->dev || !bytes) - return -EINVAL; - - bytes = PAGE_ALIGN(bytes); - - va = kmalloc(bytes, GFP_KERNEL | GFP_DMA); - if (!va) - return -ENOMEM; - pa = virt_to_phys(va); - - flags |= IOVMF_LINEAR; - flags |= IOVMF_ALLOC; - - da = __iommu_kmap(obj, da, pa, va, bytes, flags); - if (IS_ERR_VALUE(da)) - kfree(va); - - return da; -} -EXPORT_SYMBOL_GPL(iommu_kmalloc); - -/** - * iommu_kfree - release virtual mapping obtained by 'iommu_kmalloc()' - * @obj: objective iommu - * @da: iommu device virtual address - * - * Frees the iommu virtually contiguous memory area starting at - * @da, which was passed to and was returned by'iommu_kmalloc()'. - */ -void iommu_kfree(struct iommu *obj, u32 da) -{ - struct sg_table *sgt; - - sgt = unmap_vm_area(obj, da, kfree, IOVMF_LINEAR | IOVMF_ALLOC); - if (!sgt) - dev_dbg(obj->dev, "%s: No sgt\n", __func__); - sgtable_free(sgt); -} -EXPORT_SYMBOL_GPL(iommu_kfree); - - -static int __init iovmm_init(void) -{ - const unsigned long flags = SLAB_HWCACHE_ALIGN; - struct kmem_cache *p; - - p = kmem_cache_create("iovm_area_cache", sizeof(struct iovm_struct), 0, - flags, NULL); - if (!p) - return -ENOMEM; - iovm_area_cachep = p; - - return 0; -} -module_init(iovmm_init); - -static void __exit iovmm_exit(void) -{ - kmem_cache_destroy(iovm_area_cachep); -} -module_exit(iovmm_exit); - -MODULE_DESCRIPTION("omap iommu: simple virtual address space management"); -MODULE_AUTHOR("Hiroshi DOYU <Hiroshi.DOYU@nokia.com>"); -MODULE_LICENSE("GPL v2"); diff --git a/arch/arm/plat-s5p/Kconfig b/arch/arm/plat-s5p/Kconfig index 9843c954c042..9a197e55f669 100644 --- a/arch/arm/plat-s5p/Kconfig +++ b/arch/arm/plat-s5p/Kconfig @@ -22,7 +22,6 @@ config PLAT_S5P select PLAT_SAMSUNG select SAMSUNG_CLKSRC select SAMSUNG_IRQ_VIC_TIMER - select SAMSUNG_IRQ_UART help Base platform code for Samsung's S5P series SoC. diff --git a/arch/arm/plat-s5p/dev-uart.c b/arch/arm/plat-s5p/dev-uart.c index afaf87fdb93e..c9308db36183 100644 --- a/arch/arm/plat-s5p/dev-uart.c +++ b/arch/arm/plat-s5p/dev-uart.c @@ -32,20 +32,10 @@ static struct resource s5p_uart0_resource[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = IRQ_S5P_UART_RX0, - .end = IRQ_S5P_UART_RX0, + .start = IRQ_UART0, + .end = IRQ_UART0, .flags = IORESOURCE_IRQ, }, - [2] = { - .start = IRQ_S5P_UART_TX0, - .end = IRQ_S5P_UART_TX0, - .flags = IORESOURCE_IRQ, - }, - [3] = { - .start = IRQ_S5P_UART_ERR0, - .end = IRQ_S5P_UART_ERR0, - .flags = IORESOURCE_IRQ, - } }; static struct resource s5p_uart1_resource[] = { @@ -55,18 +45,8 @@ static struct resource s5p_uart1_resource[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = IRQ_S5P_UART_RX1, - .end = IRQ_S5P_UART_RX1, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = IRQ_S5P_UART_TX1, - .end = IRQ_S5P_UART_TX1, - .flags = IORESOURCE_IRQ, - }, - [3] = { - .start = IRQ_S5P_UART_ERR1, - .end = IRQ_S5P_UART_ERR1, + .start = IRQ_UART1, + .end = IRQ_UART1, .flags = IORESOURCE_IRQ, }, }; @@ -78,18 +58,8 @@ static struct resource s5p_uart2_resource[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = IRQ_S5P_UART_RX2, - .end = IRQ_S5P_UART_RX2, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = IRQ_S5P_UART_TX2, - .end = IRQ_S5P_UART_TX2, - .flags = IORESOURCE_IRQ, - }, - [3] = { - .start = IRQ_S5P_UART_ERR2, - .end = IRQ_S5P_UART_ERR2, + .start = IRQ_UART2, + .end = IRQ_UART2, .flags = IORESOURCE_IRQ, }, }; @@ -102,18 +72,8 @@ static struct resource s5p_uart3_resource[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = IRQ_S5P_UART_RX3, - .end = IRQ_S5P_UART_RX3, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = IRQ_S5P_UART_TX3, - .end = IRQ_S5P_UART_TX3, - .flags = IORESOURCE_IRQ, - }, - [3] = { - .start = IRQ_S5P_UART_ERR3, - .end = IRQ_S5P_UART_ERR3, + .start = IRQ_UART3, + .end = IRQ_UART3, .flags = IORESOURCE_IRQ, }, #endif @@ -127,18 +87,8 @@ static struct resource s5p_uart4_resource[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = IRQ_S5P_UART_RX4, - .end = IRQ_S5P_UART_RX4, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = IRQ_S5P_UART_TX4, - .end = IRQ_S5P_UART_TX4, - .flags = IORESOURCE_IRQ, - }, - [3] = { - .start = IRQ_S5P_UART_ERR4, - .end = IRQ_S5P_UART_ERR4, + .start = IRQ_UART4, + .end = IRQ_UART4, .flags = IORESOURCE_IRQ, }, #endif @@ -152,18 +102,8 @@ static struct resource s5p_uart5_resource[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = IRQ_S5P_UART_RX5, - .end = IRQ_S5P_UART_RX5, - .flags = IORESOURCE_IRQ, - }, - [2] = { - .start = IRQ_S5P_UART_TX5, - .end = IRQ_S5P_UART_TX5, - .flags = IORESOURCE_IRQ, - }, - [3] = { - .start = IRQ_S5P_UART_ERR5, - .end = IRQ_S5P_UART_ERR5, + .start = IRQ_UART5, + .end = IRQ_UART5, .flags = IORESOURCE_IRQ, }, #endif diff --git a/arch/arm/plat-s5p/include/plat/irqs.h b/arch/arm/plat-s5p/include/plat/irqs.h index ba9121c60a2a..144dbfc6506d 100644 --- a/arch/arm/plat-s5p/include/plat/irqs.h +++ b/arch/arm/plat-s5p/include/plat/irqs.h @@ -37,41 +37,6 @@ #define IRQ_VIC1_BASE S5P_VIC1_BASE #define IRQ_VIC2_BASE S5P_VIC2_BASE -/* UART interrupts, each UART has 4 intterupts per channel so - * use the space between the ISA and S3C main interrupts. Note, these - * are not in the same order as the S3C24XX series! */ - -#define IRQ_S5P_UART_BASE0 (16) -#define IRQ_S5P_UART_BASE1 (20) -#define IRQ_S5P_UART_BASE2 (24) -#define IRQ_S5P_UART_BASE3 (28) - -#define UART_IRQ_RXD (0) -#define UART_IRQ_ERR (1) -#define UART_IRQ_TXD (2) - -#define IRQ_S5P_UART_RX0 (IRQ_S5P_UART_BASE0 + UART_IRQ_RXD) -#define IRQ_S5P_UART_TX0 (IRQ_S5P_UART_BASE0 + UART_IRQ_TXD) -#define IRQ_S5P_UART_ERR0 (IRQ_S5P_UART_BASE0 + UART_IRQ_ERR) - -#define IRQ_S5P_UART_RX1 (IRQ_S5P_UART_BASE1 + UART_IRQ_RXD) -#define IRQ_S5P_UART_TX1 (IRQ_S5P_UART_BASE1 + UART_IRQ_TXD) -#define IRQ_S5P_UART_ERR1 (IRQ_S5P_UART_BASE1 + UART_IRQ_ERR) - -#define IRQ_S5P_UART_RX2 (IRQ_S5P_UART_BASE2 + UART_IRQ_RXD) -#define IRQ_S5P_UART_TX2 (IRQ_S5P_UART_BASE2 + UART_IRQ_TXD) -#define IRQ_S5P_UART_ERR2 (IRQ_S5P_UART_BASE2 + UART_IRQ_ERR) - -#define IRQ_S5P_UART_RX3 (IRQ_S5P_UART_BASE3 + UART_IRQ_RXD) -#define IRQ_S5P_UART_TX3 (IRQ_S5P_UART_BASE3 + UART_IRQ_TXD) -#define IRQ_S5P_UART_ERR3 (IRQ_S5P_UART_BASE3 + UART_IRQ_ERR) - -/* S3C compatibilty defines */ -#define IRQ_S3CUART_RX0 IRQ_S5P_UART_RX0 -#define IRQ_S3CUART_RX1 IRQ_S5P_UART_RX1 -#define IRQ_S3CUART_RX2 IRQ_S5P_UART_RX2 -#define IRQ_S3CUART_RX3 IRQ_S5P_UART_RX3 - /* VIC based IRQs */ #define S5P_IRQ_VIC0(x) (S5P_VIC0_BASE + (x)) diff --git a/arch/arm/plat-s5p/irq-gpioint.c b/arch/arm/plat-s5p/irq-gpioint.c index f88216d23991..c65eb791d1bb 100644 --- a/arch/arm/plat-s5p/irq-gpioint.c +++ b/arch/arm/plat-s5p/irq-gpioint.c @@ -163,9 +163,9 @@ static __init int s5p_gpioint_add(struct s3c_gpio_chip *chip) ct->chip.irq_mask = irq_gc_mask_set_bit; ct->chip.irq_unmask = irq_gc_mask_clr_bit; ct->chip.irq_set_type = s5p_gpioint_set_type, - ct->regs.ack = PEND_OFFSET + REG_OFFSET(chip->group); - ct->regs.mask = MASK_OFFSET + REG_OFFSET(chip->group); - ct->regs.type = CON_OFFSET + REG_OFFSET(chip->group); + ct->regs.ack = PEND_OFFSET + REG_OFFSET(group - bank->start); + ct->regs.mask = MASK_OFFSET + REG_OFFSET(group - bank->start); + ct->regs.type = CON_OFFSET + REG_OFFSET(group - bank->start); irq_setup_generic_chip(gc, IRQ_MSK(chip->chip.ngpio), IRQ_GC_INIT_MASK_CACHE, IRQ_NOREQUEST | IRQ_NOPROBE, 0); diff --git a/arch/arm/plat-s5p/irq.c b/arch/arm/plat-s5p/irq.c index a97c08957f49..afdaa1082b9f 100644 --- a/arch/arm/plat-s5p/irq.c +++ b/arch/arm/plat-s5p/irq.c @@ -17,42 +17,10 @@ #include <asm/hardware/vic.h> -#include <linux/serial_core.h> #include <mach/map.h> #include <plat/regs-timer.h> -#include <plat/regs-serial.h> #include <plat/cpu.h> #include <plat/irq-vic-timer.h> -#include <plat/irq-uart.h> - -/* - * Note, we make use of the fact that the parent IRQs, IRQ_UART[0..3] - * are consecutive when looking up the interrupt in the demux routines. - */ -static struct s3c_uart_irq uart_irqs[] = { - [0] = { - .regs = S5P_VA_UART0, - .base_irq = IRQ_S5P_UART_BASE0, - .parent_irq = IRQ_UART0, - }, - [1] = { - .regs = S5P_VA_UART1, - .base_irq = IRQ_S5P_UART_BASE1, - .parent_irq = IRQ_UART1, - }, - [2] = { - .regs = S5P_VA_UART2, - .base_irq = IRQ_S5P_UART_BASE2, - .parent_irq = IRQ_UART2, - }, -#if CONFIG_SERIAL_SAMSUNG_UARTS > 3 - [3] = { - .regs = S5P_VA_UART3, - .base_irq = IRQ_S5P_UART_BASE3, - .parent_irq = IRQ_UART3, - }, -#endif -}; void __init s5p_init_irq(u32 *vic, u32 num_vic) { @@ -65,6 +33,4 @@ void __init s5p_init_irq(u32 *vic, u32 num_vic) #endif s3c_init_vic_timer_irq(5, IRQ_TIMER0); - - s3c_init_uart_irqs(uart_irqs, ARRAY_SIZE(uart_irqs)); } diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig index b3e10659e4b8..dffa37bc4a0b 100644 --- a/arch/arm/plat-samsung/Kconfig +++ b/arch/arm/plat-samsung/Kconfig @@ -65,11 +65,6 @@ config SAMSUNG_IRQ_VIC_TIMER help Internal configuration to build the VIC timer interrupt code. -config SAMSUNG_IRQ_UART - bool - help - Internal configuration to build the IRQ UART demux code. - # options for gpio configuration support config SAMSUNG_GPIOLIB_4BIT diff --git a/arch/arm/plat-samsung/Makefile b/arch/arm/plat-samsung/Makefile index 853764ba8cc5..1105922342fe 100644 --- a/arch/arm/plat-samsung/Makefile +++ b/arch/arm/plat-samsung/Makefile @@ -21,7 +21,6 @@ obj-y += dev-asocdma.o obj-$(CONFIG_SAMSUNG_CLKSRC) += clock-clksrc.o -obj-$(CONFIG_SAMSUNG_IRQ_UART) += irq-uart.o obj-$(CONFIG_SAMSUNG_IRQ_VIC_TIMER) += irq-vic-timer.o # ADC diff --git a/arch/arm/plat-samsung/include/plat/regs-serial.h b/arch/arm/plat-samsung/include/plat/regs-serial.h index bac36fa3becb..720734847027 100644 --- a/arch/arm/plat-samsung/include/plat/regs-serial.h +++ b/arch/arm/plat-samsung/include/plat/regs-serial.h @@ -186,6 +186,11 @@ #define S3C64XX_UINTSP 0x34 #define S3C64XX_UINTM 0x38 +#define S3C64XX_UINTM_RXD (0) +#define S3C64XX_UINTM_TXD (2) +#define S3C64XX_UINTM_RXD_MSK (1 << S3C64XX_UINTM_RXD) +#define S3C64XX_UINTM_TXD_MSK (1 << S3C64XX_UINTM_TXD) + /* Following are specific to S5PV210 */ #define S5PV210_UCON_CLKMASK (1<<10) #define S5PV210_UCON_PCLK (0<<10) diff --git a/arch/arm/plat-samsung/irq-uart.c b/arch/arm/plat-samsung/irq-uart.c deleted file mode 100644 index 3014c7226bd1..000000000000 --- a/arch/arm/plat-samsung/irq-uart.c +++ /dev/null @@ -1,96 +0,0 @@ -/* arch/arm/plat-samsung/irq-uart.c - * originally part of arch/arm/plat-s3c64xx/irq.c - * - * Copyright 2008 Openmoko, Inc. - * Copyright 2008 Simtec Electronics - * Ben Dooks <ben@simtec.co.uk> - * http://armlinux.simtec.co.uk/ - * - * Samsung- UART Interrupt handling - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/serial_core.h> -#include <linux/irq.h> -#include <linux/io.h> - -#include <asm/mach/irq.h> - -#include <mach/map.h> -#include <plat/irq-uart.h> -#include <plat/regs-serial.h> -#include <plat/cpu.h> - -/* Note, we make use of the fact that the parent IRQs, IRQ_UART[0..3] - * are consecutive when looking up the interrupt in the demux routines. - */ -static void s3c_irq_demux_uart(unsigned int irq, struct irq_desc *desc) -{ - struct s3c_uart_irq *uirq = desc->irq_data.handler_data; - struct irq_chip *chip = irq_get_chip(irq); - u32 pend = __raw_readl(uirq->regs + S3C64XX_UINTP); - int base = uirq->base_irq; - - chained_irq_enter(chip, desc); - - if (pend & (1 << 0)) - generic_handle_irq(base); - if (pend & (1 << 1)) - generic_handle_irq(base + 1); - if (pend & (1 << 2)) - generic_handle_irq(base + 2); - if (pend & (1 << 3)) - generic_handle_irq(base + 3); - - chained_irq_exit(chip, desc); -} - -static void __init s3c_init_uart_irq(struct s3c_uart_irq *uirq) -{ - void __iomem *reg_base = uirq->regs; - struct irq_chip_generic *gc; - struct irq_chip_type *ct; - - /* mask all interrupts at the start. */ - __raw_writel(0xf, reg_base + S3C64XX_UINTM); - - gc = irq_alloc_generic_chip("s3c-uart", 1, uirq->base_irq, reg_base, - handle_level_irq); - - if (!gc) { - pr_err("%s: irq_alloc_generic_chip for IRQ %u failed\n", - __func__, uirq->base_irq); - return; - } - - ct = gc->chip_types; - ct->chip.irq_ack = irq_gc_ack_set_bit; - ct->chip.irq_mask = irq_gc_mask_set_bit; - ct->chip.irq_unmask = irq_gc_mask_clr_bit; - ct->regs.ack = S3C64XX_UINTP; - ct->regs.mask = S3C64XX_UINTM; - irq_setup_generic_chip(gc, IRQ_MSK(4), IRQ_GC_INIT_MASK_CACHE, - IRQ_NOREQUEST | IRQ_NOPROBE, 0); - - irq_set_handler_data(uirq->parent_irq, uirq); - irq_set_chained_handler(uirq->parent_irq, s3c_irq_demux_uart); -} - -/** - * s3c_init_uart_irqs() - initialise UART IRQs and the necessary demuxing - * @irq: The interrupt data for registering - * @nr_irqs: The number of interrupt descriptions in @irq. - * - * Register the UART interrupts specified by @irq including the demuxing - * routines. This supports the S3C6400 and newer style of devices. - */ -void __init s3c_init_uart_irqs(struct s3c_uart_irq *irq, unsigned int nr_irqs) -{ - for (; nr_irqs > 0; nr_irqs--, irq++) - s3c_init_uart_irq(irq); -} diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types index 62cc8f981171..5bdeef969847 100644 --- a/arch/arm/tools/mach-types +++ b/arch/arm/tools/mach-types @@ -12,10 +12,9 @@ # # http://www.arm.linux.org.uk/developer/machines/?action=new # -# XXX: This is a cut-down version of the file; it contains only machines that -# XXX: are in mainline or have been submitted to the machine database within -# XXX: the last 12 months. If your entry is missing please email rmk at -# XXX: <linux@arm.linux.org.uk> +# This is a cut-down version of the file; it contains only machines that +# are merged into mainline or have been edited in the machine database +# within the last 12 months. References to machine_is_NAME() do not count! # # Last update: Sat May 7 08:48:24 2011 # @@ -65,6 +64,7 @@ h7201 ARCH_H7201 H7201 161 h7202 ARCH_H7202 H7202 162 iq80321 ARCH_IQ80321 IQ80321 169 ks8695 ARCH_KS8695 KS8695 180 +karo ARCH_KARO KARO 190 smdk2410 ARCH_SMDK2410 SMDK2410 193 ceiva ARCH_CEIVA CEIVA 200 voiceblue MACH_VOICEBLUE VOICEBLUE 218 @@ -188,6 +188,7 @@ omap_2430sdp MACH_OMAP_2430SDP OMAP_2430SDP 900 davinci_evm MACH_DAVINCI_EVM DAVINCI_EVM 901 palmz72 MACH_PALMZ72 PALMZ72 904 nxdb500 MACH_NXDB500 NXDB500 905 +apf9328 MACH_APF9328 APF9328 906 palmt5 MACH_PALMT5 PALMT5 917 palmtc MACH_PALMTC PALMTC 918 omap_apollon MACH_OMAP_APOLLON OMAP_APOLLON 919 @@ -271,10 +272,12 @@ pcm038 MACH_PCM038 PCM038 1551 ts_x09 MACH_TS209 TS209 1565 at91cap9adk MACH_AT91CAP9ADK AT91CAP9ADK 1566 mx31moboard MACH_MX31MOBOARD MX31MOBOARD 1574 +vision_ep9307 MACH_VISION_EP9307 VISION_EP9307 1578 terastation_pro2 MACH_TERASTATION_PRO2 TERASTATION_PRO2 1584 linkstation_pro MACH_LINKSTATION_PRO LINKSTATION_PRO 1585 e350 MACH_E350 E350 1596 ts409 MACH_TS409 TS409 1601 +rsi_ews MACH_RSI_EWS RSI_EWS 1609 cm_x300 MACH_CM_X300 CM_X300 1616 at91sam9g20ek MACH_AT91SAM9G20EK AT91SAM9G20EK 1624 smdk6410 MACH_SMDK6410 SMDK6410 1626 @@ -331,6 +334,7 @@ smdkc100 MACH_SMDKC100 SMDKC100 1826 tavorevb MACH_TAVOREVB TAVOREVB 1827 saar MACH_SAAR SAAR 1828 at91sam9m10g45ek MACH_AT91SAM9M10G45EK AT91SAM9M10G45EK 1830 +usb_a9g20 MACH_USB_A9G20 USB_A9G20 1841 mxlads MACH_MXLADS MXLADS 1851 linkstation_mini MACH_LINKSTATION_MINI LINKSTATION_MINI 1858 afeb9260 MACH_AFEB9260 AFEB9260 1859 @@ -369,6 +373,7 @@ pcm043 MACH_PCM043 PCM043 2072 sheevaplug MACH_SHEEVAPLUG SHEEVAPLUG 2097 avengers_lite MACH_AVENGERS_LITE AVENGERS_LITE 2104 mx51_babbage MACH_MX51_BABBAGE MX51_BABBAGE 2125 +tx37 MACH_TX37 TX37 2127 rd78x00_masa MACH_RD78X00_MASA RD78X00_MASA 2135 dm355_leopard MACH_DM355_LEOPARD DM355_LEOPARD 2138 ts219 MACH_TS219 TS219 2139 @@ -379,6 +384,7 @@ omap_4430sdp MACH_OMAP_4430SDP OMAP_4430SDP 2160 magx_zn5 MACH_MAGX_ZN5 MAGX_ZN5 2162 btmavb101 MACH_BTMAVB101 BTMAVB101 2172 btmawb101 MACH_BTMAWB101 BTMAWB101 2173 +tx25 MACH_TX25 TX25 2177 omap3_torpedo MACH_OMAP3_TORPEDO OMAP3_TORPEDO 2178 anw6410 MACH_ANW6410 ANW6410 2183 imx27_visstrim_m10 MACH_IMX27_VISSTRIM_M10 IMX27_VISSTRIM_M10 2187 @@ -423,6 +429,7 @@ raumfeld_rc MACH_RAUMFELD_RC RAUMFELD_RC 2413 raumfeld_connector MACH_RAUMFELD_CONNECTOR RAUMFELD_CONNECTOR 2414 raumfeld_speaker MACH_RAUMFELD_SPEAKER RAUMFELD_SPEAKER 2415 tnetv107x MACH_TNETV107X TNETV107X 2418 +mx51_m2id MACH_MX51_M2ID MX51_M2ID 2428 smdkv210 MACH_SMDKV210 SMDKV210 2456 omap_zoom3 MACH_OMAP_ZOOM3 OMAP_ZOOM3 2464 omap_3630sdp MACH_OMAP_3630SDP OMAP_3630SDP 2465 @@ -433,14 +440,17 @@ omapl138_hawkboard MACH_OMAPL138_HAWKBOARD OMAPL138_HAWKBOARD 2495 ts41x MACH_TS41X TS41X 2502 phy3250 MACH_PHY3250 PHY3250 2511 mini6410 MACH_MINI6410 MINI6410 2520 +tx51 MACH_TX51 TX51 2529 mx28evk MACH_MX28EVK MX28EVK 2531 smartq5 MACH_SMARTQ5 SMARTQ5 2534 davinci_dm6467tevm MACH_DAVINCI_DM6467TEVM DAVINCI_DM6467TEVM 2548 mxt_td60 MACH_MXT_TD60 MXT_TD60 2550 riot_bei2 MACH_RIOT_BEI2 RIOT_BEI2 2576 riot_x37 MACH_RIOT_X37 RIOT_X37 2578 +pca101 MACH_PCA101 PCA101 2595 capc7117 MACH_CAPC7117 CAPC7117 2612 icontrol MACH_ICONTROL ICONTROL 2624 +gplugd MACH_GPLUGD GPLUGD 2625 qsd8x50a_st1_5 MACH_QSD8X50A_ST1_5 QSD8X50A_ST1_5 2627 mx23evk MACH_MX23EVK MX23EVK 2629 ap4evb MACH_AP4EVB AP4EVB 2630 @@ -1113,3 +1123,5 @@ blissc MACH_BLISSC BLISSC 3491 thales_adc MACH_THALES_ADC THALES_ADC 3492 ubisys_p9d_evp MACH_UBISYS_P9D_EVP UBISYS_P9D_EVP 3493 atdgp318 MACH_ATDGP318 ATDGP318 3494 +smdk4212 MACH_SMDK4212 SMDK4212 3638 +smdk4412 MACH_SMDK4412 SMDK4412 3765 diff --git a/arch/arm/vfp/Makefile b/arch/arm/vfp/Makefile index 6de73aab0195..a81404c09d5d 100644 --- a/arch/arm/vfp/Makefile +++ b/arch/arm/vfp/Makefile @@ -7,7 +7,7 @@ # ccflags-y := -DDEBUG # asflags-y := -DDEBUG -KBUILD_AFLAGS :=$(KBUILD_AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp) +KBUILD_AFLAGS :=$(KBUILD_AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp -mfloat-abi=soft) LDFLAGS +=--no-warn-mismatch obj-y += vfp.o diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 79bcb4316930..0cbd5a0a9332 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/cpu.h> +#include <linux/cpu_pm.h> #include <linux/kernel.h> #include <linux/notifier.h> #include <linux/signal.h> @@ -68,7 +69,7 @@ static bool vfp_state_in_hw(unsigned int cpu, struct thread_info *thread) /* * Force a reload of the VFP context from the thread structure. We do * this by ensuring that access to the VFP hardware is disabled, and - * clear last_VFP_context. Must be called from non-preemptible context. + * clear vfp_current_hw_state. Must be called from non-preemptible context. */ static void vfp_force_reload(unsigned int cpu, struct thread_info *thread) { @@ -436,9 +437,7 @@ static void vfp_enable(void *unused) set_copro_access(access | CPACC_FULL(10) | CPACC_FULL(11)); } -#ifdef CONFIG_PM -#include <linux/syscore_ops.h> - +#ifdef CONFIG_CPU_PM static int vfp_pm_suspend(void) { struct thread_info *ti = current_thread_info(); @@ -468,19 +467,33 @@ static void vfp_pm_resume(void) fmxr(FPEXC, fmrx(FPEXC) & ~FPEXC_EN); } -static struct syscore_ops vfp_pm_syscore_ops = { - .suspend = vfp_pm_suspend, - .resume = vfp_pm_resume, +static int vfp_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, + void *v) +{ + switch (cmd) { + case CPU_PM_ENTER: + vfp_pm_suspend(); + break; + case CPU_PM_ENTER_FAILED: + case CPU_PM_EXIT: + vfp_pm_resume(); + break; + } + return NOTIFY_OK; +} + +static struct notifier_block vfp_cpu_pm_notifier_block = { + .notifier_call = vfp_cpu_pm_notifier, }; static void vfp_pm_init(void) { - register_syscore_ops(&vfp_pm_syscore_ops); + cpu_pm_register_notifier(&vfp_cpu_pm_notifier_block); } #else static inline void vfp_pm_init(void) { } -#endif /* CONFIG_PM */ +#endif /* CONFIG_CPU_PM */ /* * Ensure that the VFP state stored in 'thread->vfpstate' is up to date diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index c7476295de80..abe5a9e85148 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -248,10 +248,6 @@ config HOTPLUG_CPU depends on SMP && HOTPLUG default y -config HAVE_LEGACY_PER_CPU_AREA - def_bool y - depends on SMP - config BF_REV_MIN int default 0 if (BF51x || BF52x || (BF54x && !BF54xM)) diff --git a/arch/blackfin/configs/BF548-EZKIT_defconfig b/arch/blackfin/configs/BF548-EZKIT_defconfig index 56151b5dbc44..0e6d841b5d01 100644 --- a/arch/blackfin/configs/BF548-EZKIT_defconfig +++ b/arch/blackfin/configs/BF548-EZKIT_defconfig @@ -4,7 +4,6 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y -# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set CONFIG_EXPERT=y # CONFIG_SYSCTL_SYSCALL is not set # CONFIG_ELF_CORE is not set @@ -40,7 +39,6 @@ CONFIG_EBIU_MODEVAL=0x1 CONFIG_EBIU_FCTLVAL=0x6 CONFIG_BINFMT_FLAT=y CONFIG_BINFMT_ZFLAT=y -CONFIG_PM=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -55,7 +53,6 @@ CONFIG_IP_PNP=y CONFIG_CAN=m CONFIG_CAN_RAW=m CONFIG_CAN_BCM=m -CONFIG_CAN_DEV=m CONFIG_CAN_BFIN=m CONFIG_IRDA=m CONFIG_IRLAN=m @@ -67,7 +64,6 @@ CONFIG_BFIN_SIR3=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_FW_LOADER=m CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y @@ -105,12 +101,12 @@ CONFIG_INPUT_TOUCHSCREEN=y CONFIG_TOUCHSCREEN_AD7877=m CONFIG_INPUT_MISC=y # CONFIG_SERIO is not set -# CONFIG_DEVKMEM is not set +# CONFIG_LEGACY_PTYS is not set CONFIG_BFIN_JTAG_COMM=m +# CONFIG_DEVKMEM is not set CONFIG_SERIAL_BFIN=y CONFIG_SERIAL_BFIN_CONSOLE=y CONFIG_SERIAL_BFIN_UART1=y -# CONFIG_LEGACY_PTYS is not set # CONFIG_HW_RANDOM is not set CONFIG_I2C=y CONFIG_I2C_CHARDEV=y @@ -163,6 +159,7 @@ CONFIG_USB_DEVICEFS=y CONFIG_USB_OTG_BLACKLIST_HUB=y CONFIG_USB_MON=y CONFIG_USB_MUSB_HDRC=y +CONFIG_USB_MUSB_BLACKFIN=y CONFIG_USB_STORAGE=y CONFIG_MMC=y CONFIG_MMC_BLOCK=m @@ -185,8 +182,6 @@ CONFIG_NFS_FS=m CONFIG_NFS_V3=y CONFIG_NFSD=m CONFIG_NFSD_V3=y -CONFIG_SMB_FS=m -CONFIG_SMB_NLS_DEFAULT=y CONFIG_CIFS=y CONFIG_NLS_CODEPAGE_437=m CONFIG_NLS_CODEPAGE_936=m @@ -196,7 +191,6 @@ CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_SHIRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_INFO=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set # CONFIG_FTRACE is not set CONFIG_DEBUG_MMRS=y CONFIG_DEBUG_HWERR=y @@ -206,5 +200,4 @@ CONFIG_DEBUG_BFIN_HWTRACE_COMPRESSION_ONE=y CONFIG_EARLY_PRINTK=y CONFIG_CPLB_INFO=y CONFIG_BFIN_PSEUDODBG_INSNS=y -CONFIG_CRYPTO=y # CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild index 7a075eaf6041..5a0625aad6a0 100644 --- a/arch/blackfin/include/asm/Kbuild +++ b/arch/blackfin/include/asm/Kbuild @@ -21,6 +21,7 @@ generic-y += local64.h generic-y += local.h generic-y += mman.h generic-y += msgbuf.h +generic-y += mutex.h generic-y += param.h generic-y += percpu.h generic-y += pgalloc.h diff --git a/arch/blackfin/include/asm/atomic.h b/arch/blackfin/include/asm/atomic.h index 135225696fd2..54c6e2887e9f 100644 --- a/arch/blackfin/include/asm/atomic.h +++ b/arch/blackfin/include/asm/atomic.h @@ -1,5 +1,5 @@ /* - * Copyright 2004-2009 Analog Devices Inc. + * Copyright 2004-2011 Analog Devices Inc. * * Licensed under the GPL-2 or later. */ @@ -7,111 +7,27 @@ #ifndef __ARCH_BLACKFIN_ATOMIC__ #define __ARCH_BLACKFIN_ATOMIC__ -#ifndef CONFIG_SMP -# include <asm-generic/atomic.h> -#else +#ifdef CONFIG_SMP -#include <linux/types.h> -#include <asm/system.h> /* local_irq_XXX() */ - -/* - * Atomic operations that C can't guarantee us. Useful for - * resource counting etc.. - */ - -#define ATOMIC_INIT(i) { (i) } -#define atomic_set(v, i) (((v)->counter) = i) - -#define atomic_read(v) __raw_uncached_fetch_asm(&(v)->counter) +#include <linux/linkage.h> asmlinkage int __raw_uncached_fetch_asm(const volatile int *ptr); - asmlinkage int __raw_atomic_update_asm(volatile int *ptr, int value); - asmlinkage int __raw_atomic_clear_asm(volatile int *ptr, int value); - asmlinkage int __raw_atomic_set_asm(volatile int *ptr, int value); - asmlinkage int __raw_atomic_xor_asm(volatile int *ptr, int value); - asmlinkage int __raw_atomic_test_asm(const volatile int *ptr, int value); -static inline void atomic_add(int i, atomic_t *v) -{ - __raw_atomic_update_asm(&v->counter, i); -} - -static inline void atomic_sub(int i, atomic_t *v) -{ - __raw_atomic_update_asm(&v->counter, -i); -} - -static inline int atomic_add_return(int i, atomic_t *v) -{ - return __raw_atomic_update_asm(&v->counter, i); -} - -static inline int atomic_sub_return(int i, atomic_t *v) -{ - return __raw_atomic_update_asm(&v->counter, -i); -} +#define atomic_read(v) __raw_uncached_fetch_asm(&(v)->counter) -static inline void atomic_inc(volatile atomic_t *v) -{ - __raw_atomic_update_asm(&v->counter, 1); -} - -static inline void atomic_dec(volatile atomic_t *v) -{ - __raw_atomic_update_asm(&v->counter, -1); -} - -static inline void atomic_clear_mask(int mask, atomic_t *v) -{ - __raw_atomic_clear_asm(&v->counter, mask); -} - -static inline void atomic_set_mask(int mask, atomic_t *v) -{ - __raw_atomic_set_asm(&v->counter, mask); -} - -/* Atomic operations are already serializing */ -#define smp_mb__before_atomic_dec() barrier() -#define smp_mb__after_atomic_dec() barrier() -#define smp_mb__before_atomic_inc() barrier() -#define smp_mb__after_atomic_inc() barrier() - -#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) -#define atomic_dec_return(v) atomic_sub_return(1,(v)) -#define atomic_inc_return(v) atomic_add_return(1,(v)) - -#define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n))) -#define atomic_xchg(v, new) (xchg(&((v)->counter), new)) - -#define __atomic_add_unless(v, a, u) \ -({ \ - int c, old; \ - c = atomic_read(v); \ - while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \ - c = old; \ - c; \ -}) - -/* - * atomic_inc_and_test - increment and test - * @v: pointer of type atomic_t - * - * Atomically increments @v by 1 - * and returns true if the result is zero, or false for all - * other cases. - */ -#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) - -#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) +#define atomic_add_return(i, v) __raw_atomic_update_asm(&(v)->counter, i) +#define atomic_sub_return(i, v) __raw_atomic_update_asm(&(v)->counter, -(i)) +#define atomic_clear_mask(m, v) __raw_atomic_clear_asm(&(v)->counter, m) +#define atomic_set_mask(m, v) __raw_atomic_set_asm(&(v)->counter, m) #endif +#include <asm-generic/atomic.h> + #endif diff --git a/arch/blackfin/include/asm/mutex.h b/arch/blackfin/include/asm/mutex.h deleted file mode 100644 index ff6101aa2c71..000000000000 --- a/arch/blackfin/include/asm/mutex.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/mutex-dec.h> diff --git a/arch/blackfin/include/asm/uaccess.h b/arch/blackfin/include/asm/uaccess.h index 1c0d190adaef..5cc111502822 100644 --- a/arch/blackfin/include/asm/uaccess.h +++ b/arch/blackfin/include/asm/uaccess.h @@ -195,17 +195,17 @@ static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (access_ok(VERIFY_READ, from, n)) - memcpy(to, from, n); + memcpy(to, (const void __force *)from, n); else return n; return 0; } static inline unsigned long __must_check -copy_to_user(void *to, const void __user *from, unsigned long n) +copy_to_user(void __user *to, const void *from, unsigned long n) { if (access_ok(VERIFY_WRITE, to, n)) - memcpy(to, from, n); + memcpy((void __force *)to, from, n); else return n; return 0; diff --git a/arch/blackfin/kernel/Makefile b/arch/blackfin/kernel/Makefile index b7bdc42fe1a3..1f88edd4572a 100644 --- a/arch/blackfin/kernel/Makefile +++ b/arch/blackfin/kernel/Makefile @@ -38,6 +38,6 @@ obj-$(CONFIG_PERF_EVENTS) += perf_event.o # the kgdb test puts code into L2 and without linker # relaxation, we need to force long calls to/from it -CFLAGS_kgdb_test.o := -mlong-calls -O0 +CFLAGS_kgdb_test.o := -mlong-calls obj-$(CONFIG_DEBUG_MMRS) += debug-mmrs.o diff --git a/arch/blackfin/kernel/kgdb_test.c b/arch/blackfin/kernel/kgdb_test.c index 2a6e9dbb62a5..4a7dcfea98af 100644 --- a/arch/blackfin/kernel/kgdb_test.c +++ b/arch/blackfin/kernel/kgdb_test.c @@ -50,8 +50,7 @@ void kgdb_l2_test(void) #endif - -int kgdb_test(char *name, int len, int count, int z) +noinline int kgdb_test(char *name, int len, int count, int z) { pr_alert("kgdb name(%d): %s, %d, %d\n", len, name, count, z); count = z; diff --git a/arch/blackfin/kernel/time-ts.c b/arch/blackfin/kernel/time-ts.c index 9e9b60d969dc..1bcf3a3c57d8 100644 --- a/arch/blackfin/kernel/time-ts.c +++ b/arch/blackfin/kernel/time-ts.c @@ -188,8 +188,7 @@ irqreturn_t bfin_gptmr0_interrupt(int irq, void *dev_id) static struct irqaction gptmr0_irq = { .name = "Blackfin GPTimer0", - .flags = IRQF_DISABLED | IRQF_TIMER | \ - IRQF_IRQPOLL | IRQF_PERCPU, + .flags = IRQF_TIMER | IRQF_IRQPOLL | IRQF_PERCPU, .handler = bfin_gptmr0_interrupt, }; @@ -297,8 +296,7 @@ irqreturn_t bfin_coretmr_interrupt(int irq, void *dev_id) static struct irqaction coretmr_irq = { .name = "Blackfin CoreTimer", - .flags = IRQF_DISABLED | IRQF_TIMER | \ - IRQF_IRQPOLL | IRQF_PERCPU, + .flags = IRQF_TIMER | IRQF_IRQPOLL | IRQF_PERCPU, .handler = bfin_coretmr_interrupt, }; diff --git a/arch/blackfin/kernel/time.c b/arch/blackfin/kernel/time.c index ceb2bf63dfe2..2310b249675f 100644 --- a/arch/blackfin/kernel/time.c +++ b/arch/blackfin/kernel/time.c @@ -25,7 +25,6 @@ static struct irqaction bfin_timer_irq = { .name = "Blackfin Timer Tick", - .flags = IRQF_DISABLED }; #if defined(CONFIG_IPIPE) diff --git a/arch/blackfin/mach-bf533/boards/H8606.c b/arch/blackfin/mach-bf533/boards/H8606.c index eb325ed6607e..5da5787fc4ef 100644 --- a/arch/blackfin/mach-bf533/boards/H8606.c +++ b/arch/blackfin/mach-bf533/boards/H8606.c @@ -54,7 +54,8 @@ static struct resource dm9000_resources[] = { [2] = { .start = IRQ_PF10, .end = IRQ_PF10, - .flags = (IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE | IRQF_SHARED | IRQF_TRIGGER_HIGH), + .flags = (IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE | + IORESOURCE_IRQ_SHAREABLE), }, }; diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537e.c b/arch/blackfin/mach-bf537/boards/cm_bf537e.c index 44fd8409db10..9fb20d6d8f91 100644 --- a/arch/blackfin/mach-bf537/boards/cm_bf537e.c +++ b/arch/blackfin/mach-bf537/boards/cm_bf537e.c @@ -605,7 +605,7 @@ static struct platform_device bfin_mac_device = { static struct pata_platform_info bfin_pata_platform_data = { .ioport_shift = 2, - .irq_type = IRQF_TRIGGER_HIGH | IRQF_DISABLED, + .irq_type = IRQF_TRIGGER_HIGH, }; static struct resource bfin_pata_resources[] = { diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537u.c b/arch/blackfin/mach-bf537/boards/cm_bf537u.c index 1b4ac5c64aae..5ba389fc61ae 100644 --- a/arch/blackfin/mach-bf537/boards/cm_bf537u.c +++ b/arch/blackfin/mach-bf537/boards/cm_bf537u.c @@ -570,7 +570,7 @@ static struct platform_device bfin_mac_device = { static struct pata_platform_info bfin_pata_platform_data = { .ioport_shift = 2, - .irq_type = IRQF_TRIGGER_HIGH | IRQF_DISABLED, + .irq_type = IRQF_TRIGGER_HIGH, }; static struct resource bfin_pata_resources[] = { diff --git a/arch/blackfin/mach-bf537/boards/stamp.c b/arch/blackfin/mach-bf537/boards/stamp.c index b52e6728f64f..6c916a67ef68 100644 --- a/arch/blackfin/mach-bf537/boards/stamp.c +++ b/arch/blackfin/mach-bf537/boards/stamp.c @@ -962,10 +962,10 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SND_BF5XX_SOC_AD183X) \ - || defined(CONFIG_SND_BF5XX_SOC_AD183X_MODULE) +#if defined(CONFIG_SND_BF5XX_SOC_AD1836) \ + || defined(CONFIG_SND_BF5XX_SOC_AD1836_MODULE) { - .modalias = "ad183x", + .modalias = "ad1836", .max_speed_hz = 3125000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, .chip_select = 4, @@ -984,9 +984,9 @@ static struct spi_board_info bfin_spi_board_info[] __initdata = { }, #endif -#if defined(CONFIG_SND_BF5XX_SOC_ADAV80X) || defined(CONFIG_SND_BF5XX_SOC_ADAV80X_MODULE) +#if defined(CONFIG_SND_SOC_ADAV80X) || defined(CONFIG_SND_SOC_ADV80X_MODULE) { - .modalias = "adav80x", + .modalias = "adav801", .max_speed_hz = 3125000, /* max spi clock (SCK) speed in HZ */ .bus_num = 0, .chip_select = 1, @@ -2101,7 +2101,7 @@ static struct i2c_board_info __initdata bfin_i2c_board_info[] = { }, #endif -#if defined(CONFIG_SND_BF5XX_SOC_ADAV80X) || defined(CONFIG_SND_BF5XX_SOC_ADAV80X_MODULE) +#if defined(CONFIG_SND_SOC_ADAV80X) || defined(CONFIG_SND_SOC_ADAV80X_MODULE) { I2C_BOARD_INFO("adav803", 0x10), }, @@ -2134,23 +2134,6 @@ static struct i2c_board_info __initdata bfin_i2c_board_info[] = { }, #endif -#if defined(CONFIG_AD7414) || defined(CONFIG_AD7414_MODULE) - { - I2C_BOARD_INFO("ad7414", 0x9), - .irq = IRQ_PG5, - .irq_flags = IRQF_TRIGGER_LOW, - }, -#endif - -#if defined(CONFIG_AD7416) || defined(CONFIG_AD7416_MODULE) - { - I2C_BOARD_INFO("ad7417", 0xb), - .irq = IRQ_PG5, - .irq_flags = IRQF_TRIGGER_LOW, - .platform_data = (void *)GPIO_PF4, - }, -#endif - #if defined(CONFIG_ADE7854_I2C) || defined(CONFIG_ADE7854_I2C_MODULE) { I2C_BOARD_INFO("ade7854", 0x38), @@ -2161,15 +2144,6 @@ static struct i2c_board_info __initdata bfin_i2c_board_info[] = { { I2C_BOARD_INFO("adt75", 0x9), .irq = IRQ_PG5, - .irq_flags = IRQF_TRIGGER_LOW, - }, -#endif - -#if defined(CONFIG_ADT7408) || defined(CONFIG_ADT7408_MODULE) - { - I2C_BOARD_INFO("adt7408", 0x18), - .irq = IRQ_PG5, - .irq_flags = IRQF_TRIGGER_LOW, }, #endif @@ -2178,7 +2152,6 @@ static struct i2c_board_info __initdata bfin_i2c_board_info[] = { I2C_BOARD_INFO("adt7410", 0x48), /* CT critical temperature event. line 0 */ .irq = IRQ_PG5, - .irq_flags = IRQF_TRIGGER_LOW, .platform_data = (void *)&adt7410_platform_data, }, #endif @@ -2187,7 +2160,6 @@ static struct i2c_board_info __initdata bfin_i2c_board_info[] = { { I2C_BOARD_INFO("ad7291", 0x20), .irq = IRQ_PG5, - .irq_flags = IRQF_TRIGGER_LOW, }, #endif @@ -2275,6 +2247,11 @@ static struct i2c_board_info __initdata bfin_i2c_board_info[] = { I2C_BOARD_INFO("adau1361", 0x38), }, #endif +#if defined(CONFIG_SND_SOC_ADAU1701) || defined(CONFIG_SND_SOC_ADAU1701_MODULE) + { + I2C_BOARD_INFO("adau1701", 0x34), + }, +#endif #if defined(CONFIG_AD525X_DPOT) || defined(CONFIG_AD525X_DPOT_MODULE) { I2C_BOARD_INFO("ad5258", 0x18), @@ -2388,7 +2365,7 @@ static struct platform_device bfin_sport1_uart_device = { #define PATA_INT IRQ_PF5 static struct pata_platform_info bfin_pata_platform_data = { .ioport_shift = 1, - .irq_flags = IRQF_TRIGGER_HIGH | IRQF_DISABLED, + .irq_flags = IRQF_TRIGGER_HIGH, }; static struct resource bfin_pata_resources[] = { @@ -2540,13 +2517,21 @@ static struct platform_device bfin_ac97_pcm = { }; #endif -#if defined(CONFIG_SND_BF5XX_SOC_AD73311) || defined(CONFIG_SND_BF5XX_SOC_AD73311_MODULE) +#if defined(CONFIG_SND_SOC_AD73311) || defined(CONFIG_SND_SOC_AD73311_MODULE) static struct platform_device bfin_ad73311_codec_device = { .name = "ad73311", .id = -1, }; #endif +#if defined(CONFIG_SND_SOC_BFIN_EVAL_ADAV80X) || \ + defined(CONFIG_SND_SOC_BFIN_EVAL_ADAV80X_MODULE) +static struct platform_device bfin_eval_adav801_device = { + .name = "bfin-eval-adav801", + .id = -1, +}; +#endif + #if defined(CONFIG_SND_BF5XX_SOC_I2S) || defined(CONFIG_SND_BF5XX_SOC_I2S_MODULE) static struct platform_device bfin_i2s = { .name = "bfin-i2s", @@ -2661,6 +2646,20 @@ static struct platform_device iio_gpio_trigger = { }; #endif +#if defined(CONFIG_SND_SOC_BFIN_EVAL_ADAU1373) || \ + defined(CONFIG_SND_SOC_BFIN_EVAL_ADAU1373_MODULE) +static struct platform_device bf5xx_adau1373_device = { + .name = "bfin-eval-adau1373", +}; +#endif + +#if defined(CONFIG_SND_SOC_BFIN_EVAL_ADAU1701) || \ + defined(CONFIG_SND_SOC_BFIN_EVAL_ADAU1701_MODULE) +static struct platform_device bf5xx_adau1701_device = { + .name = "bfin-eval-adau1701", +}; +#endif + static struct platform_device *stamp_devices[] __initdata = { &bfin_dpmc, @@ -2782,7 +2781,7 @@ static struct platform_device *stamp_devices[] __initdata = { &bfin_ac97_pcm, #endif -#if defined(CONFIG_SND_BF5XX_SOC_AD73311) || defined(CONFIG_SND_BF5XX_SOC_AD73311_MODULE) +#if defined(CONFIG_SND_SOC_AD73311) || defined(CONFIG_SND_SOC_AD73311_MODULE) &bfin_ad73311_codec_device, #endif @@ -2821,6 +2820,21 @@ static struct platform_device *stamp_devices[] __initdata = { defined(CONFIG_IIO_GPIO_TRIGGER_MODULE) &iio_gpio_trigger, #endif + +#if defined(CONFIG_SND_SOC_BFIN_EVAL_ADAU1373) || \ + defined(CONFIG_SND_SOC_BFIN_EVAL_ADAU1373_MODULE) + &bf5xx_adau1373_device, +#endif + +#if defined(CONFIG_SND_SOC_BFIN_EVAL_ADAU1701) || \ + defined(CONFIG_SND_SOC_BFIN_EVAL_ADAU1701_MODULE) + &bf5xx_adau1701_device, +#endif + +#if defined(CONFIG_SND_SOC_BFIN_EVAL_ADAV80X) || \ + defined(CONFIG_SND_SOC_BFIN_EVAL_ADAV80X_MODULE) + &bfin_eval_adav801_device, +#endif }; static int __init net2272_init(void) diff --git a/arch/blackfin/mach-bf537/boards/tcm_bf537.c b/arch/blackfin/mach-bf537/boards/tcm_bf537.c index 9b7287abdfa1..2da0316d890e 100644 --- a/arch/blackfin/mach-bf537/boards/tcm_bf537.c +++ b/arch/blackfin/mach-bf537/boards/tcm_bf537.c @@ -572,7 +572,7 @@ static struct platform_device bfin_mac_device = { static struct pata_platform_info bfin_pata_platform_data = { .ioport_shift = 2, - .irq_type = IRQF_TRIGGER_HIGH | IRQF_DISABLED, + .irq_type = IRQF_TRIGGER_HIGH, }; static struct resource bfin_pata_resources[] = { diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c index e4f397d1d65b..c1b72f2d6354 100644 --- a/arch/blackfin/mach-bf561/boards/cm_bf561.c +++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c @@ -348,7 +348,7 @@ static struct platform_device bfin_sir0_device = { static struct pata_platform_info bfin_pata_platform_data = { .ioport_shift = 2, - .irq_type = IRQF_TRIGGER_HIGH | IRQF_DISABLED, + .irq_type = IRQF_TRIGGER_HIGH, }; static struct resource bfin_pata_resources[] = { diff --git a/arch/blackfin/mach-bf561/smp.c b/arch/blackfin/mach-bf561/smp.c index 85abd8be1343..db22401e7605 100644 --- a/arch/blackfin/mach-bf561/smp.c +++ b/arch/blackfin/mach-bf561/smp.c @@ -114,7 +114,7 @@ void __init platform_request_ipi(int irq, void *handler) int ret; const char *name = (irq == IRQ_SUPPLE_0) ? supple0 : supple1; - ret = request_irq(irq, handler, IRQF_DISABLED | IRQF_PERCPU, name, handler); + ret = request_irq(irq, handler, IRQF_PERCPU, name, handler); if (ret) panic("Cannot request %s for IPI service", name); } diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index 107622aacf6b..0784a52389c8 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -295,10 +295,15 @@ EXPORT_SYMBOL_GPL(smp_call_function_single); void smp_send_reschedule(int cpu) { + cpumask_t callmap; /* simply trigger an ipi */ if (cpu_is_offline(cpu)) return; - platform_send_ipi_cpu(cpu, IRQ_SUPPLE_0); + + cpumask_clear(&callmap); + cpumask_set_cpu(cpu, &callmap); + + smp_send_message(callmap, BFIN_IPI_RESCHEDULE, NULL, NULL, 0); return; } diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig index 17addacb169e..408b055c585f 100644 --- a/arch/cris/Kconfig +++ b/arch/cris/Kconfig @@ -282,8 +282,8 @@ config ETRAX_RTC Enables drivers for the Real-Time Clock battery-backed chips on some products. The kernel reads the time when booting, and the date can be set using ioctl(fd, RTC_SET_TIME, &rt) with rt a - rtc_time struct (see <file:include/asm-cris/rtc.h>) on the /dev/rtc - device. You can check the time with cat /proc/rtc, but + rtc_time struct (see <file:arch/cris/include/asm/rtc.h>) on the + /dev/rtc device. You can check the time with cat /proc/rtc, but normal time reading should be done using libc function time and friends. diff --git a/arch/cris/arch-v10/Kconfig b/arch/cris/arch-v10/Kconfig index adc164e99339..df9a38b4f18f 100644 --- a/arch/cris/arch-v10/Kconfig +++ b/arch/cris/arch-v10/Kconfig @@ -24,8 +24,8 @@ config ETRAX_PA_LEDS help The ETRAX network driver is responsible for flashing LED's when packets arrive and are sent. It uses macros defined in - <file:include/asm-cris/io.h>, and those macros are defined after what - YOU choose in this option. The actual bits used are configured + <file:arch/cris/include/asm/io.h>, and those macros are defined after + what YOU choose in this option. The actual bits used are configured separately. Select this if the LEDs are on port PA. Some products put the leds on PB or a memory-mapped latch (CSP0) instead. @@ -34,8 +34,8 @@ config ETRAX_PB_LEDS help The ETRAX network driver is responsible for flashing LED's when packets arrive and are sent. It uses macros defined in - <file:include/asm-cris/io.h>, and those macros are defined after what - YOU choose in this option. The actual bits used are configured + <file:arch/cris/include/asm/io.h>, and those macros are defined after + what YOU choose in this option. The actual bits used are configured separately. Select this if the LEDs are on port PB. Some products put the leds on PA or a memory-mapped latch (CSP0) instead. @@ -44,8 +44,8 @@ config ETRAX_CSP0_LEDS help The ETRAX network driver is responsible for flashing LED's when packets arrive and are sent. It uses macros defined in - <file:include/asm-cris/io.h>, and those macros are defined after what - YOU choose in this option. The actual bits used are configured + <file:arch/cris/include/asm/io.h>, and those macros are defined after + what YOU choose in this option. The actual bits used are configured separately. Select this if the LEDs are on a memory-mapped latch using chip select CSP0, this is mapped at 0x90000000. Some products put the leds on PA or PB instead. diff --git a/arch/cris/arch-v10/drivers/Kconfig b/arch/cris/arch-v10/drivers/Kconfig index 0d7221779923..32d90867a984 100644 --- a/arch/cris/arch-v10/drivers/Kconfig +++ b/arch/cris/arch-v10/drivers/Kconfig @@ -4,6 +4,7 @@ config ETRAX_ETHERNET bool "Ethernet support" depends on ETRAX_ARCH_V10 select NET_ETHERNET + select NET_CORE select MII help This option enables the ETRAX 100LX built-in 10/100Mbit Ethernet diff --git a/arch/cris/arch-v10/kernel/kgdb.c b/arch/cris/arch-v10/kernel/kgdb.c index b9f9c8ce2169..b579dd02e098 100644 --- a/arch/cris/arch-v10/kernel/kgdb.c +++ b/arch/cris/arch-v10/kernel/kgdb.c @@ -694,7 +694,7 @@ mem2hex(char *buf, unsigned char *mem, int count) /* Valid mem address. */ for (i = 0; i < count; i++) { ch = *mem++; - buf = pack_hex_byte(buf, ch); + buf = hex_byte_pack(buf, ch); } } @@ -868,7 +868,7 @@ stub_is_stopped(int sigval) /* Send trap type (converted to signal) */ *ptr++ = 'T'; - ptr = pack_hex_byte(ptr, sigval); + ptr = hex_byte_pack(ptr, sigval); /* Send register contents. We probably only need to send the * PC, frame pointer and stack pointer here. Other registers will be @@ -881,7 +881,7 @@ stub_is_stopped(int sigval) status = read_register (regno, ®_cont); if (status == SUCCESS) { - ptr = pack_hex_byte(ptr, regno); + ptr = hex_byte_pack(ptr, regno); *ptr++ = ':'; ptr = mem2hex(ptr, (unsigned char *)®_cont, diff --git a/arch/cris/arch-v32/drivers/Kconfig b/arch/cris/arch-v32/drivers/Kconfig index 41a2732e8b9c..e47e9c3401b0 100644 --- a/arch/cris/arch-v32/drivers/Kconfig +++ b/arch/cris/arch-v32/drivers/Kconfig @@ -4,6 +4,7 @@ config ETRAX_ETHERNET bool "Ethernet support" depends on ETRAX_ARCH_V32 select NET_ETHERNET + select NET_CORE select MII help This option enables the ETRAX FS built-in 10/100Mbit Ethernet diff --git a/arch/cris/arch-v32/kernel/kgdb.c b/arch/cris/arch-v32/kernel/kgdb.c index c0343c3ea7f8..8c1d35cdf00a 100644 --- a/arch/cris/arch-v32/kernel/kgdb.c +++ b/arch/cris/arch-v32/kernel/kgdb.c @@ -677,7 +677,7 @@ mem2hex(char *buf, unsigned char *mem, int count) /* Valid mem address. */ for (i = 0; i < count; i++) { ch = *mem++; - buf = pack_hex_byte(buf, ch); + buf = hex_byte_pack(buf, ch); } } /* Terminate properly. */ @@ -695,7 +695,7 @@ mem2hex_nbo(char *buf, unsigned char *mem, int count) mem += count - 1; for (i = 0; i < count; i++) { ch = *mem--; - buf = pack_hex_byte(buf, ch); + buf = hex_byte_pack(buf, ch); } /* Terminate properly. */ @@ -880,7 +880,7 @@ stub_is_stopped(int sigval) /* Send trap type (converted to signal) */ *ptr++ = 'T'; - ptr = pack_hex_byte(ptr, sigval); + ptr = hex_byte_pack(ptr, sigval); if (((reg.exs & 0xff00) >> 8) == 0xc) { @@ -988,26 +988,26 @@ stub_is_stopped(int sigval) } /* Only send PC, frame and stack pointer. */ read_register(PC, ®_cont); - ptr = pack_hex_byte(ptr, PC); + ptr = hex_byte_pack(ptr, PC); *ptr++ = ':'; ptr = mem2hex(ptr, (unsigned char *)®_cont, register_size[PC]); *ptr++ = ';'; read_register(R8, ®_cont); - ptr = pack_hex_byte(ptr, R8); + ptr = hex_byte_pack(ptr, R8); *ptr++ = ':'; ptr = mem2hex(ptr, (unsigned char *)®_cont, register_size[R8]); *ptr++ = ';'; read_register(SP, ®_cont); - ptr = pack_hex_byte(ptr, SP); + ptr = hex_byte_pack(ptr, SP); *ptr++ = ':'; ptr = mem2hex(ptr, (unsigned char *)®_cont, register_size[SP]); *ptr++ = ';'; /* Send ERP as well; this will save us an entire register fetch in some cases. */ read_register(ERP, ®_cont); - ptr = pack_hex_byte(ptr, ERP); + ptr = hex_byte_pack(ptr, ERP); *ptr++ = ':'; ptr = mem2hex(ptr, (unsigned char *)®_cont, register_size[ERP]); *ptr++ = ';'; diff --git a/arch/cris/arch-v32/lib/nand_init.S b/arch/cris/arch-v32/lib/nand_init.S deleted file mode 100644 index d671fed451c9..000000000000 --- a/arch/cris/arch-v32/lib/nand_init.S +++ /dev/null @@ -1,178 +0,0 @@ -##============================================================================= -## -## nand_init.S -## -## The bootrom copies data from the NAND flash to the internal RAM but -## due to a bug/feature we can only trust the 256 first bytes. So this -## code copies more data from NAND flash to internal RAM. Obvioulsy this -## code must fit in the first 256 bytes so alter with care. -## -## Some notes about the bug/feature for future reference: -## The bootrom copies the first 127 KB from NAND flash to internal -## memory. The problem is that it does a bytewise copy. NAND flashes -## does autoincrement on the address so for a 16-bite device each -## read/write increases the address by two. So the copy loop in the -## bootrom will discard every second byte. This is solved by inserting -## zeroes in every second byte in the first erase block. -## -## The bootrom also incorrectly assumes that it can read the flash -## linear with only one read command but the flash will actually -## switch between normal area and spare area if you do that so we -## can't trust more than the first 256 bytes. -## -##============================================================================= - -#include <arch/hwregs/asm/reg_map_asm.h> -#include <arch/hwregs/asm/gio_defs_asm.h> -#include <arch/hwregs/asm/pinmux_defs_asm.h> -#include <arch/hwregs/asm/bif_core_defs_asm.h> -#include <arch/hwregs/asm/config_defs_asm.h> - -;; There are 8-bit NAND flashes and 16-bit NAND flashes. -;; We need to treat them slightly different. -#if CONFIG_ETRAX_FLASH_BUSWIDTH==2 -#define PAGE_SIZE 256 -#else -#error 2 -#define PAGE_SIZE 512 -#endif -#define ERASE_BLOCK 16384 - -;; GPIO pins connected to NAND flash -#define CE 4 -#define CLE 5 -#define ALE 6 -#define BY 7 - -;; Address space for NAND flash -#define NAND_RD_ADDR 0x90000000 -#define NAND_WR_ADDR 0x94000000 - -#define READ_CMD 0x00 - -;; Readability macros -#define CSP_MASK \ - REG_MASK(bif_core, rw_grp3_cfg, gated_csp0) | \ - REG_MASK(bif_core, rw_grp3_cfg, gated_csp1) -#define CSP_VAL \ - REG_STATE(bif_core, rw_grp3_cfg, gated_csp0, rd) | \ - REG_STATE(bif_core, rw_grp3_cfg, gated_csp1, wr) - -;;---------------------------------------------------------------------------- -;; Macros to set/clear GPIO bits - -.macro SET x - or.b (1<<\x),$r9 - move.d $r9, [$r2] -.endm - -.macro CLR x - and.b ~(1<<\x),$r9 - move.d $r9, [$r2] -.endm - -;;---------------------------------------------------------------------------- - -nand_boot: - ;; Check if nand boot was selected - move.d REG_ADDR(config, regi_config, r_bootsel), $r0 - move.d [$r0], $r0 - and.d REG_MASK(config, r_bootsel, boot_mode), $r0 - cmp.d REG_STATE(config, r_bootsel, boot_mode, nand), $r0 - bne normal_boot ; No NAND boot - nop - -copy_nand_to_ram: - ;; copy_nand_to_ram - ;; Arguments - ;; r10 - destination - ;; r11 - source offset - ;; r12 - size - ;; r13 - Address to jump to after completion - ;; Note : r10-r12 are clobbered on return - ;; Registers used: - ;; r0 - NAND_RD_ADDR - ;; r1 - NAND_WR_ADDR - ;; r2 - reg_gio_rw_pa_dout - ;; r3 - reg_gio_r_pa_din - ;; r4 - tmp - ;; r5 - byte counter within a page - ;; r6 - reg_pinmux_rw_pa - ;; r7 - reg_gio_rw_pa_oe - ;; r8 - reg_bif_core_rw_grp3_cfg - ;; r9 - reg_gio_rw_pa_dout shadow - move.d 0x90000000, $r0 - move.d 0x94000000, $r1 - move.d REG_ADDR(gio, regi_gio, rw_pa_dout), $r2 - move.d REG_ADDR(gio, regi_gio, r_pa_din), $r3 - move.d REG_ADDR(pinmux, regi_pinmux, rw_pa), $r6 - move.d REG_ADDR(gio, regi_gio, rw_pa_oe), $r7 - move.d REG_ADDR(bif_core, regi_bif_core, rw_grp3_cfg), $r8 - -#if CONFIG_ETRAX_FLASH_BUSWIDTH==2 - lsrq 1, $r11 -#endif - ;; Set up GPIO - move.d [$r2], $r9 - move.d [$r7], $r4 - or.b (1<<ALE) | (1 << CLE) | (1<<CE), $r4 - move.d $r4, [$r7] - - ;; Set up bif - move.d [$r8], $r4 - and.d CSP_MASK, $r4 - or.d CSP_VAL, $r4 - move.d $r4, [$r8] - -1: ;; Copy one page - CLR CE - SET CLE - moveq READ_CMD, $r4 - move.b $r4, [$r1] - moveq 20, $r4 -2: bne 2b - subq 1, $r4 - CLR CLE - SET ALE - clear.w [$r1] ; Column address = 0 - move.d $r11, $r4 - lsrq 8, $r4 - move.b $r4, [$r1] ; Row address - lsrq 8, $r4 - move.b $r4, [$r1] ; Row address - moveq 20, $r4 -2: bne 2b - subq 1, $r4 - CLR ALE -2: move.d [$r3], $r4 - and.d 1 << BY, $r4 - beq 2b - movu.w PAGE_SIZE, $r5 -2: ; Copy one byte/word -#if CONFIG_ETRAX_FLASH_BUSWIDTH==2 - move.w [$r0], $r4 -#else - move.b [$r0], $r4 -#endif - subq 1, $r5 - bne 2b -#if CONFIG_ETRAX_FLASH_BUSWIDTH==2 - move.w $r4, [$r10+] - subu.w PAGE_SIZE*2, $r12 -#else - move.b $r4, [$r10+] - subu.w PAGE_SIZE, $r12 -#endif - bpl 1b - addu.w PAGE_SIZE, $r11 - - ;; End of copy - jump $r13 - nop - - ;; This will warn if the code above is too large. If you consider - ;; to remove this you don't understand the bug/feature. - .org 256 - .org ERASE_BLOCK - -normal_boot: diff --git a/arch/frv/kernel/gdb-stub.c b/arch/frv/kernel/gdb-stub.c index a4dba6b20bd0..a6d5381c94fe 100644 --- a/arch/frv/kernel/gdb-stub.c +++ b/arch/frv/kernel/gdb-stub.c @@ -672,7 +672,7 @@ static unsigned char *mem2hex(const void *_mem, char *buf, int count, int may_fa if ((uint32_t)mem&1 && count>=1) { if (!gdbstub_read_byte(mem,ch)) return NULL; - buf = pack_hex_byte(buf, ch[0]); + buf = hex_byte_pack(buf, ch[0]); mem++; count--; } @@ -680,8 +680,8 @@ static unsigned char *mem2hex(const void *_mem, char *buf, int count, int may_fa if ((uint32_t)mem&3 && count>=2) { if (!gdbstub_read_word(mem,(uint16_t *)ch)) return NULL; - buf = pack_hex_byte(buf, ch[0]); - buf = pack_hex_byte(buf, ch[1]); + buf = hex_byte_pack(buf, ch[0]); + buf = hex_byte_pack(buf, ch[1]); mem += 2; count -= 2; } @@ -689,10 +689,10 @@ static unsigned char *mem2hex(const void *_mem, char *buf, int count, int may_fa while (count>=4) { if (!gdbstub_read_dword(mem,(uint32_t *)ch)) return NULL; - buf = pack_hex_byte(buf, ch[0]); - buf = pack_hex_byte(buf, ch[1]); - buf = pack_hex_byte(buf, ch[2]); - buf = pack_hex_byte(buf, ch[3]); + buf = hex_byte_pack(buf, ch[0]); + buf = hex_byte_pack(buf, ch[1]); + buf = hex_byte_pack(buf, ch[2]); + buf = hex_byte_pack(buf, ch[3]); mem += 4; count -= 4; } @@ -700,8 +700,8 @@ static unsigned char *mem2hex(const void *_mem, char *buf, int count, int may_fa if (count>=2) { if (!gdbstub_read_word(mem,(uint16_t *)ch)) return NULL; - buf = pack_hex_byte(buf, ch[0]); - buf = pack_hex_byte(buf, ch[1]); + buf = hex_byte_pack(buf, ch[0]); + buf = hex_byte_pack(buf, ch[1]); mem += 2; count -= 2; } @@ -709,7 +709,7 @@ static unsigned char *mem2hex(const void *_mem, char *buf, int count, int may_fa if (count>=1) { if (!gdbstub_read_byte(mem,ch)) return NULL; - buf = pack_hex_byte(buf, ch[0]); + buf = hex_byte_pack(buf, ch[0]); } *buf = 0; @@ -1498,21 +1498,21 @@ void gdbstub(int sigval) ptr = mem2hex(title, ptr, sizeof(title) - 1,0); hx = hex_asc_hi(brr >> 24); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_lo(brr >> 24); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_hi(brr >> 16); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_lo(brr >> 16); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_hi(brr >> 8); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_lo(brr >> 8); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_hi(brr); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_lo(brr); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); ptr = mem2hex(crlf, ptr, sizeof(crlf) - 1, 0); *ptr = 0; @@ -1526,10 +1526,10 @@ void gdbstub(int sigval) /* Send trap type (converted to signal) */ *ptr++ = 'T'; - ptr = pack_hex_byte(ptr, sigval); + ptr = hex_byte_pack(ptr, sigval); /* Send Error PC */ - ptr = pack_hex_byte(ptr, GDB_REG_PC); + ptr = hex_byte_pack(ptr, GDB_REG_PC); *ptr++ = ':'; ptr = mem2hex(&__debug_frame->pc, ptr, 4, 0); *ptr++ = ';'; @@ -1537,7 +1537,7 @@ void gdbstub(int sigval) /* * Send frame pointer */ - ptr = pack_hex_byte(ptr, GDB_REG_FP); + ptr = hex_byte_pack(ptr, GDB_REG_FP); *ptr++ = ':'; ptr = mem2hex(&__debug_frame->fp, ptr, 4, 0); *ptr++ = ';'; @@ -1545,7 +1545,7 @@ void gdbstub(int sigval) /* * Send stack pointer */ - ptr = pack_hex_byte(ptr, GDB_REG_SP); + ptr = hex_byte_pack(ptr, GDB_REG_SP); *ptr++ = ':'; ptr = mem2hex(&__debug_frame->sp, ptr, 4, 0); *ptr++ = ';'; diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index 091ed6192ae8..d1f377f5d3b6 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -160,7 +160,7 @@ config VT_CONSOLE config HW_CONSOLE bool - depends on VT && !S390 && !UM + depends on VT default y comment "Unix98 PTY support" @@ -195,7 +195,7 @@ config UNIX98_PTYS source "drivers/char/pcmcia/Kconfig" -source "drivers/serial/Kconfig" +source "drivers/tty/serial/Kconfig" source "drivers/i2c/Kconfig" diff --git a/arch/h8300/include/asm/gpio.h b/arch/h8300/include/asm/gpio-internal.h index a714f0c0efbc..a714f0c0efbc 100644 --- a/arch/h8300/include/asm/gpio.h +++ b/arch/h8300/include/asm/gpio-internal.h diff --git a/arch/h8300/platform/h8300h/irq.c b/arch/h8300/platform/h8300h/irq.c index e977345105d7..bc4f51bceef5 100644 --- a/arch/h8300/platform/h8300h/irq.c +++ b/arch/h8300/platform/h8300h/irq.c @@ -11,7 +11,7 @@ #include <asm/traps.h> #include <asm/irq.h> #include <asm/io.h> -#include <asm/gpio.h> +#include <asm/gpio-internal.h> #include <asm/regs306x.h> const int __initdata h8300_saved_vectors[] = { diff --git a/arch/h8300/platform/h8s/irq.c b/arch/h8300/platform/h8s/irq.c index 8182f041f829..7b5f29febc07 100644 --- a/arch/h8300/platform/h8s/irq.c +++ b/arch/h8300/platform/h8s/irq.c @@ -14,7 +14,7 @@ #include <asm/traps.h> #include <asm/irq.h> #include <asm/io.h> -#include <asm/gpio.h> +#include <asm/gpio-internal.h> #include <asm/regs267x.h> /* saved vector list */ diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig new file mode 100644 index 000000000000..02513c2dd5ec --- /dev/null +++ b/arch/hexagon/Kconfig @@ -0,0 +1,220 @@ +# Hexagon configuration +comment "Linux Kernel Configuration for Hexagon" + +config HEXAGON + def_bool y + select HAVE_OPROFILE + select USE_GENERIC_SMP_HELPERS if SMP + # Other pending projects/to-do items. + # select HAVE_REGS_AND_STACK_ACCESS_API + # select HAVE_HW_BREAKPOINT if PERF_EVENTS + # select ARCH_HAS_CPU_IDLE_WAIT + # select ARCH_WANT_OPTIONAL_GPIOLIB + # select ARCH_REQUIRE_GPIOLIB + # select HAVE_CLK + # select IRQ_PER_CPU + select HAVE_IRQ_WORK + # select GENERIC_PENDING_IRQ if SMP + select GENERIC_ATOMIC64 + select HAVE_PERF_EVENTS + select HAVE_GENERIC_HARDIRQS + select GENERIC_HARDIRQS_NO__DO_IRQ + select GENERIC_HARDIRQS_NO_DEPRECATED + # GENERIC_ALLOCATOR is used by dma_alloc_coherent() + select GENERIC_ALLOCATOR + select GENERIC_IRQ_SHOW + select HAVE_ARCH_KGDB + select HAVE_ARCH_TRACEHOOK + select NO_IOPORT + # mostly generic routines, with some accelerated ones + ---help--- + Qualcomm Hexagon is a processor architecture designed for high + performance and low power across a wide variety of applications. + +config HEXAGON_ARCH_V1 + bool + +config HEXAGON_ARCH_V2 + bool + +config HEXAGON_ARCH_V3 + bool + +config HEXAGON_ARCH_V4 + bool + +config FRAME_POINTER + def_bool y + +config LOCKDEP_SUPPORT + def_bool y + +config PCI + def_bool n + +config EARLY_PRINTK + def_bool y + +config KTIME_SCALAR + def_bool y + +config MMU + def_bool y + +config TRACE_IRQFLAGS_SUPPORT + def_bool y + +config GENERIC_CSUM + def_bool y + +# +# Use the generic interrupt handling code in kernel/irq/: +# +config GENERIC_IRQ_PROBE + def_bool y + +config GENERIC_IOMAP + def_bool y + +#config ZONE_DMA +# bool +# default y + +config HAS_DMA + bool + select HAVE_DMA_ATTRS + default y + +config NEED_SG_DMA_LENGTH + def_bool y + +config RWSEM_GENERIC_SPINLOCK + def_bool n + +config RWSEM_XCHGADD_ALGORITHM + def_bool y + +config GENERIC_FIND_NEXT_BIT + def_bool y + +config GENERIC_HWEIGHT + def_bool y + +config GENERIC_TIME + def_bool y + +config GENERIC_CLOCKEVENTS + def_bool y + +config GENERIC_CLOCKEVENTS_BROADCAST + def_bool y + +config STACKTRACE_SUPPORT + def_bool y + select STACKTRACE + +config GENERIC_BUG + def_bool y + depends on BUG + +config BUG + def_bool y + +menu "Machine selection" + +choice + prompt "System type" + default HEXAGON_ARCH_V2 + +config HEXAGON_COMET + bool "Comet Board" + select HEXAGON_ARCH_V2 + ---help--- + Support for the Comet platform. + +endchoice + +config HEXAGON_VM + def_bool y + +config CMDLINE + string "Default kernel command string" + default "" + help + On some platforms, there is currently no way for the boot loader + to pass arguments to the kernel. For these, you should supply some + command-line options at build time by entering them here. At a + minimum, you should specify the memory size and the root device + (e.g., mem=64M root=/dev/nfs). + +config HEXAGON_ANGEL_TRAPS + bool "Use Angel Traps" + default n + ---help--- + Enable angel debug traps (for printk's). + +config SMP + bool "Multi-Processing support" + ---help--- + Enables SMP support in the kernel. If unsure, say "Y" + +config NR_CPUS + int "Maximum number of CPUs" if SMP + range 2 6 if SMP + default "1" if !SMP + default "6" if SMP + ---help--- + This allows you to specify the maximum number of CPUs which this + kernel will support. The maximum supported value is 6 and the + minimum value which makes sense is 2. + + This is purely to save memory - each supported CPU adds + approximately eight kilobytes to the kernel image. + +choice + prompt "Kernel page size" + default PAGE_SIZE_4KB + ---help--- + Changes the default page size; use with caution. + +config PAGE_SIZE_4KB + bool "4KB" + +config PAGE_SIZE_16KB + bool "16KB" + +config PAGE_SIZE_64KB + bool "64KB" + +config PAGE_SIZE_256KB + bool "256KB" + +endchoice + +source "mm/Kconfig" + +source "kernel/Kconfig.hz" +source "kernel/time/Kconfig" + +config GENERIC_GPIO + bool "Generic GPIO support" + default n + +endmenu + +source "init/Kconfig" +source "drivers/Kconfig" +source "fs/Kconfig" + +menu "Executable File Formats" +source "fs/Kconfig.binfmt" +endmenu + +source "net/Kconfig" +source "security/Kconfig" +source "crypto/Kconfig" +source "lib/Kconfig" + +menu "Kernel hacking" +source "lib/Kconfig.debug" +endmenu diff --git a/arch/hexagon/Makefile b/arch/hexagon/Makefile new file mode 100644 index 000000000000..0c4de8790fd5 --- /dev/null +++ b/arch/hexagon/Makefile @@ -0,0 +1,58 @@ +# Makefile for the Hexagon arch + +KBUILD_DEFCONFIG = comet_defconfig + +# Do not use GP-relative jumps +KBUILD_CFLAGS += -G0 +LDFLAGS_vmlinux += -G0 + +# Do not use single-byte enums; these will overflow. +KBUILD_CFLAGS += -fno-short-enums + +# Modules must use either long-calls, or use pic/plt. +# Use long-calls for now, it's easier. And faster. +# CFLAGS_MODULE += -fPIC +# LDFLAGS_MODULE += -shared +CFLAGS_MODULE += -mlong-calls + +cflags-$(CONFIG_HEXAGON_ARCH_V1) += $(call cc-option,-mv1) +cflags-$(CONFIG_HEXAGON_ARCH_V2) += $(call cc-option,-mv2) +cflags-$(CONFIG_HEXAGON_ARCH_V3) += $(call cc-option,-mv3) +cflags-$(CONFIG_HEXAGON_ARCH_V4) += $(call cc-option,-mv4) + +aflags-$(CONFIG_HEXAGON_ARCH_V1) += $(call cc-option,-mv1) +aflags-$(CONFIG_HEXAGON_ARCH_V2) += $(call cc-option,-mv2) +aflags-$(CONFIG_HEXAGON_ARCH_V3) += $(call cc-option,-mv3) +aflags-$(CONFIG_HEXAGON_ARCH_V4) += $(call cc-option,-mv4) + +ldflags-$(CONFIG_HEXAGON_ARCH_V1) += $(call cc-option,-mv1) +ldflags-$(CONFIG_HEXAGON_ARCH_V2) += $(call cc-option,-mv2) +ldflags-$(CONFIG_HEXAGON_ARCH_V3) += $(call cc-option,-mv3) +ldflags-$(CONFIG_HEXAGON_ARCH_V4) += $(call cc-option,-mv4) + +KBUILD_CFLAGS += $(cflags-y) +KBUILD_AFLAGS += $(aflags-y) + +# no KBUILD_LDFLAGS? +LDFLAGS += $(ldflags-y) + +# Thread-info register will be r19. This value is not configureable; +# it is hard-coded in several files. +TIR_NAME := r19 +KBUILD_CFLAGS += -ffixed-$(TIR_NAME) -DTHREADINFO_REG=$(TIR_NAME) -D__linux__ +KBUILD_AFLAGS += -DTHREADINFO_REG=$(TIR_NAME) + +LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name) +libs-y += $(LIBGCC) + +head-y := arch/hexagon/kernel/head.o \ + arch/hexagon/kernel/init_task.o + +core-y += arch/hexagon/kernel/ \ + arch/hexagon/mm/ \ + arch/hexagon/lib/ + +# arch/hexagon/platform/common/ +# +#core-$(CONFIG_HEXAGON_COMET) += arch/hexagon/platform/comet/ +#machine-$(CONFIG_HEXAGON_COMET) := comet diff --git a/arch/hexagon/configs/comet_defconfig b/arch/hexagon/configs/comet_defconfig new file mode 100644 index 000000000000..e324f65f41e7 --- /dev/null +++ b/arch/hexagon/configs/comet_defconfig @@ -0,0 +1,85 @@ +CONFIG_SMP=y +CONFIG_DEFAULT_MMAP_MIN_ADDR=0 +CONFIG_HZ_100=y +CONFIG_EXPERIMENTAL=y +CONFIG_CROSS_COMPILE="hexagon-" +CONFIG_LOCALVERSION="-smp" +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_BSD_PROCESS_ACCT_V3=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=18 +CONFIG_BLK_DEV_INITRD=y +CONFIG_EMBEDDED=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_BLK_DEV_BSG is not set +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +# CONFIG_STANDALONE is not set +CONFIG_CONNECTOR=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_NBD=y +CONFIG_NETDEVICES=y +CONFIG_MII=y +CONFIG_PHYLIB=y +CONFIG_NET_ETHERNET=y +# CONFIG_NETDEV_1000 is not set +# CONFIG_NETDEV_10000 is not set +# CONFIG_INPUT_MOUSEDEV is not set +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +# CONFIG_CONSOLE_TRANSLATIONS is not set +CONFIG_LEGACY_PTY_COUNT=64 +# CONFIG_DEVKMEM is not set +# CONFIG_HW_RANDOM is not set +CONFIG_SPI=y +CONFIG_SPI_DEBUG=y +CONFIG_SPI_BITBANG=y +# CONFIG_HWMON is not set +# CONFIG_VGA_CONSOLE is not set +# CONFIG_HID_SUPPORT is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT2_FS_POSIX_ACL=y +CONFIG_EXT2_FS_SECURITY=y +CONFIG_EXT3_FS=y +# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set +CONFIG_EXT3_FS_POSIX_ACL=y +CONFIG_EXT3_FS_SECURITY=y +CONFIG_QUOTA=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +CONFIG_NFS_V3=y +CONFIG_NFS_V3_ACL=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +# CONFIG_INET_DIAG is not set +# CONFIG_IPV6 is not set +CONFIG_CRYPTO_MD5=y +# CONFIG_CRYPTO_ANSI_CPRNG is not set +# CONFIG_CRYPTO_HW is not set +CONFIG_CRC_CCITT=y +CONFIG_CRC16=y +CONFIG_CRC_T10DIF=y +CONFIG_LIBCRC32C=y +CONFIG_FRAME_WARN=0 +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_FS=y +# CONFIG_SCHED_DEBUG is not set +CONFIG_DEBUG_INFO=y diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild new file mode 100644 index 000000000000..9aa17f1917ea --- /dev/null +++ b/arch/hexagon/include/asm/Kbuild @@ -0,0 +1,58 @@ +include include/asm-generic/Kbuild.asm + +header-y += registers.h +header-y += ucontext.h +header-y += user.h + +generic-y += auxvec.h +generic-y += bug.h +generic-y += bugs.h +generic-y += cpumask.h +generic-y += cputime.h +generic-y += current.h +generic-y += device.h +generic-y += div64.h +generic-y += emergency-restart.h +generic-y += errno.h +generic-y += fb.h +generic-y += fcntl.h +generic-y += ftrace.h +generic-y += hardirq.h +generic-y += hw_irq.h +generic-y += ioctl.h +generic-y += ioctls.h +generic-y += iomap.h +generic-y += ipcbuf.h +generic-y += ipc.h +generic-y += irq_regs.h +generic-y += kdebug.h +generic-y += kmap_types.h +generic-y += local64.h +generic-y += local.h +generic-y += local.h +generic-y += mman.h +generic-y += msgbuf.h +generic-y += pci.h +generic-y += percpu.h +generic-y += poll.h +generic-y += posix_types.h +generic-y += resource.h +generic-y += rwsem.h +generic-y += scatterlist.h +generic-y += sections.h +generic-y += segment.h +generic-y += sembuf.h +generic-y += shmbuf.h +generic-y += shmparam.h +generic-y += siginfo.h +generic-y += socket.h +generic-y += sockios.h +generic-y += statfs.h +generic-y += stat.h +generic-y += termbits.h +generic-y += termios.h +generic-y += topology.h +generic-y += types.h +generic-y += ucontext.h +generic-y += unaligned.h +generic-y += xor.h diff --git a/arch/hexagon/include/asm/asm-offsets.h b/arch/hexagon/include/asm/asm-offsets.h new file mode 100644 index 000000000000..d370ee36a182 --- /dev/null +++ b/arch/hexagon/include/asm/asm-offsets.h @@ -0,0 +1 @@ +#include <generated/asm-offsets.h> diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h new file mode 100644 index 000000000000..e220f9053035 --- /dev/null +++ b/arch/hexagon/include/asm/atomic.h @@ -0,0 +1,164 @@ +/* + * Atomic operations for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_ATOMIC_H +#define _ASM_ATOMIC_H + +#include <linux/types.h> + +#define ATOMIC_INIT(i) { (i) } +#define atomic_set(v, i) ((v)->counter = (i)) + +/** + * atomic_read - reads a word, atomically + * @v: pointer to atomic value + * + * Assumes all word reads on our architecture are atomic. + */ +#define atomic_read(v) ((v)->counter) + +/** + * atomic_xchg - atomic + * @v: pointer to memory to change + * @new: new value (technically passed in a register -- see xchg) + */ +#define atomic_xchg(v, new) (xchg(&((v)->counter), (new))) + + +/** + * atomic_cmpxchg - atomic compare-and-exchange values + * @v: pointer to value to change + * @old: desired old value to match + * @new: new value to put in + * + * Parameters are then pointer, value-in-register, value-in-register, + * and the output is the old value. + * + * Apparently this is complicated for archs that don't support + * the memw_locked like we do (or it's broken or whatever). + * + * Kind of the lynchpin of the rest of the generically defined routines. + * Remember V2 had that bug with dotnew predicate set by memw_locked. + * + * "old" is "expected" old val, __oldval is actual old value + */ +static inline int atomic_cmpxchg(atomic_t *v, int old, int new) +{ + int __oldval; + + asm volatile( + "1: %0 = memw_locked(%1);\n" + " { P0 = cmp.eq(%0,%2);\n" + " if (!P0.new) jump:nt 2f; }\n" + " memw_locked(%1,P0) = %3;\n" + " if (!P0) jump 1b;\n" + "2:\n" + : "=&r" (__oldval) + : "r" (&v->counter), "r" (old), "r" (new) + : "memory", "p0" + ); + + return __oldval; +} + +static inline int atomic_add_return(int i, atomic_t *v) +{ + int output; + + __asm__ __volatile__ ( + "1: %0 = memw_locked(%1);\n" + " %0 = add(%0,%2);\n" + " memw_locked(%1,P3)=%0;\n" + " if !P3 jump 1b;\n" + : "=&r" (output) + : "r" (&v->counter), "r" (i) + : "memory", "p3" + ); + return output; + +} + +#define atomic_add(i, v) atomic_add_return(i, (v)) + +static inline int atomic_sub_return(int i, atomic_t *v) +{ + int output; + __asm__ __volatile__ ( + "1: %0 = memw_locked(%1);\n" + " %0 = sub(%0,%2);\n" + " memw_locked(%1,P3)=%0\n" + " if !P3 jump 1b;\n" + : "=&r" (output) + : "r" (&v->counter), "r" (i) + : "memory", "p3" + ); + return output; +} + +#define atomic_sub(i, v) atomic_sub_return(i, (v)) + +/** + * atomic_add_unless - add unless the number is a given value + * @v: pointer to value + * @a: amount to add + * @u: unless value is equal to u + * + * Returns 1 if the add happened, 0 if it didn't. + */ +static inline int __atomic_add_unless(atomic_t *v, int a, int u) +{ + int output, __oldval; + asm volatile( + "1: %0 = memw_locked(%2);" + " {" + " p3 = cmp.eq(%0, %4);" + " if (p3.new) jump:nt 2f;" + " %0 = add(%0, %3);" + " %1 = #0;" + " }" + " memw_locked(%2, p3) = %0;" + " {" + " if !p3 jump 1b;" + " %1 = #1;" + " }" + "2:" + : "=&r" (__oldval), "=&r" (output) + : "r" (v), "r" (a), "r" (u) + : "memory", "p3" + ); + return output; +} + +#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) + +#define atomic_inc(v) atomic_add(1, (v)) +#define atomic_dec(v) atomic_sub(1, (v)) + +#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) +#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) +#define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0) +#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0) + + +#define atomic_inc_return(v) (atomic_add_return(1, v)) +#define atomic_dec_return(v) (atomic_sub_return(1, v)) + +#endif diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h new file mode 100644 index 000000000000..d23461e080ff --- /dev/null +++ b/arch/hexagon/include/asm/bitops.h @@ -0,0 +1,301 @@ +/* + * Bit operations for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_BITOPS_H +#define _ASM_BITOPS_H + +#include <linux/compiler.h> +#include <asm/byteorder.h> +#include <asm/system.h> +#include <asm/atomic.h> + +#ifdef __KERNEL__ + +#define smp_mb__before_clear_bit() barrier() +#define smp_mb__after_clear_bit() barrier() + +/* + * The offset calculations for these are based on BITS_PER_LONG == 32 + * (i.e. I get to shift by #5-2 (32 bits per long, 4 bytes per access), + * mask by 0x0000001F) + * + * Typically, R10 is clobbered for address, R11 bit nr, and R12 is temp + */ + +/** + * test_and_clear_bit - clear a bit and return its old value + * @nr: bit number to clear + * @addr: pointer to memory + */ +static inline int test_and_clear_bit(int nr, volatile void *addr) +{ + int oldval; + + __asm__ __volatile__ ( + " {R10 = %1; R11 = asr(%2,#5); }\n" + " {R10 += asl(R11,#2); R11 = and(%2,#0x1f)}\n" + "1: R12 = memw_locked(R10);\n" + " { P0 = tstbit(R12,R11); R12 = clrbit(R12,R11); }\n" + " memw_locked(R10,P1) = R12;\n" + " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n" + : "=&r" (oldval) + : "r" (addr), "r" (nr) + : "r10", "r11", "r12", "p0", "p1", "memory" + ); + + return oldval; +} + +/** + * test_and_set_bit - set a bit and return its old value + * @nr: bit number to set + * @addr: pointer to memory + */ +static inline int test_and_set_bit(int nr, volatile void *addr) +{ + int oldval; + + __asm__ __volatile__ ( + " {R10 = %1; R11 = asr(%2,#5); }\n" + " {R10 += asl(R11,#2); R11 = and(%2,#0x1f)}\n" + "1: R12 = memw_locked(R10);\n" + " { P0 = tstbit(R12,R11); R12 = setbit(R12,R11); }\n" + " memw_locked(R10,P1) = R12;\n" + " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n" + : "=&r" (oldval) + : "r" (addr), "r" (nr) + : "r10", "r11", "r12", "p0", "p1", "memory" + ); + + + return oldval; + +} + +/** + * test_and_change_bit - toggle a bit and return its old value + * @nr: bit number to set + * @addr: pointer to memory + */ +static inline int test_and_change_bit(int nr, volatile void *addr) +{ + int oldval; + + __asm__ __volatile__ ( + " {R10 = %1; R11 = asr(%2,#5); }\n" + " {R10 += asl(R11,#2); R11 = and(%2,#0x1f)}\n" + "1: R12 = memw_locked(R10);\n" + " { P0 = tstbit(R12,R11); R12 = togglebit(R12,R11); }\n" + " memw_locked(R10,P1) = R12;\n" + " {if !P1 jump 1b; %0 = mux(P0,#1,#0);}\n" + : "=&r" (oldval) + : "r" (addr), "r" (nr) + : "r10", "r11", "r12", "p0", "p1", "memory" + ); + + return oldval; + +} + +/* + * Atomic, but doesn't care about the return value. + * Rewrite later to save a cycle or two. + */ + +static inline void clear_bit(int nr, volatile void *addr) +{ + test_and_clear_bit(nr, addr); +} + +static inline void set_bit(int nr, volatile void *addr) +{ + test_and_set_bit(nr, addr); +} + +static inline void change_bit(int nr, volatile void *addr) +{ + test_and_change_bit(nr, addr); +} + + +/* + * These are allowed to be non-atomic. In fact the generic flavors are + * in non-atomic.h. Would it be better to use intrinsics for this? + * + * OK, writes in our architecture do not invalidate LL/SC, so this has to + * be atomic, particularly for things like slab_lock and slab_unlock. + * + */ +static inline void __clear_bit(int nr, volatile unsigned long *addr) +{ + test_and_clear_bit(nr, addr); +} + +static inline void __set_bit(int nr, volatile unsigned long *addr) +{ + test_and_set_bit(nr, addr); +} + +static inline void __change_bit(int nr, volatile unsigned long *addr) +{ + test_and_change_bit(nr, addr); +} + +/* Apparently, at least some of these are allowed to be non-atomic */ +static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) +{ + return test_and_clear_bit(nr, addr); +} + +static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) +{ + return test_and_set_bit(nr, addr); +} + +static inline int __test_and_change_bit(int nr, volatile unsigned long *addr) +{ + return test_and_change_bit(nr, addr); +} + +static inline int __test_bit(int nr, const volatile unsigned long *addr) +{ + int retval; + + asm volatile( + "{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n" + : "=&r" (retval) + : "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG) + : "p0" + ); + + return retval; +} + +#define test_bit(nr, addr) __test_bit(nr, addr) + +/* + * ffz - find first zero in word. + * @word: The word to search + * + * Undefined if no zero exists, so code should check against ~0UL first. + */ +static inline long ffz(int x) +{ + int r; + + asm("%0 = ct1(%1);\n" + : "=&r" (r) + : "r" (x)); + return r; +} + +/* + * fls - find last (most-significant) bit set + * @x: the word to search + * + * This is defined the same way as ffs. + * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. + */ +static inline long fls(int x) +{ + int r; + + asm("{ %0 = cl0(%1);}\n" + "%0 = sub(#32,%0);\n" + : "=&r" (r) + : "r" (x) + : "p0"); + + return r; +} + +/* + * ffs - find first bit set + * @x: the word to search + * + * This is defined the same way as + * the libc and compiler builtin ffs routines, therefore + * differs in spirit from the above ffz (man ffs). + */ +static inline long ffs(int x) +{ + int r; + + asm("{ P0 = cmp.eq(%1,#0); %0 = ct0(%1);}\n" + "{ if P0 %0 = #0; if !P0 %0 = add(%0,#1);}\n" + : "=&r" (r) + : "r" (x) + : "p0"); + + return r; +} + +/* + * __ffs - find first bit in word. + * @word: The word to search + * + * Undefined if no bit exists, so code should check against 0 first. + * + * bits_per_long assumed to be 32 + * numbering starts at 0 I think (instead of 1 like ffs) + */ +static inline unsigned long __ffs(unsigned long word) +{ + int num; + + asm("%0 = ct0(%1);\n" + : "=&r" (num) + : "r" (word)); + + return num; +} + +/* + * __fls - find last (most-significant) set bit in a long word + * @word: the word to search + * + * Undefined if no set bit exists, so code should check against 0 first. + * bits_per_long assumed to be 32 + */ +static inline unsigned long __fls(unsigned long word) +{ + int num; + + asm("%0 = cl0(%1);\n" + "%0 = sub(#31,%0);\n" + : "=&r" (num) + : "r" (word)); + + return num; +} + +#include <asm-generic/bitops/lock.h> +#include <asm-generic/bitops/find.h> + +#include <asm-generic/bitops/fls64.h> +#include <asm-generic/bitops/sched.h> +#include <asm-generic/bitops/hweight.h> + +#include <asm-generic/bitops/le.h> +#include <asm-generic/bitops/ext2-atomic.h> + +#endif /* __KERNEL__ */ +#endif diff --git a/arch/hexagon/include/asm/bitsperlong.h b/arch/hexagon/include/asm/bitsperlong.h new file mode 100644 index 000000000000..2701cae3426e --- /dev/null +++ b/arch/hexagon/include/asm/bitsperlong.h @@ -0,0 +1,26 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef __ASM_HEXAGON_BITSPERLONG_H +#define __ASM_HEXAGON_BITSPERLONG_H + +#define __BITS_PER_LONG 32 + +#include <asm-generic/bitsperlong.h> + +#endif diff --git a/arch/hexagon/include/asm/byteorder.h b/arch/hexagon/include/asm/byteorder.h new file mode 100644 index 000000000000..0e19b9fe4ca6 --- /dev/null +++ b/arch/hexagon/include/asm/byteorder.h @@ -0,0 +1,28 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_BYTEORDER_H +#define _ASM_BYTEORDER_H + +#if defined(__GNUC__) && !defined(__STRICT_ANSI__) || defined(__KERNEL__) +# define __BYTEORDER_HAS_U64__ +#endif + +#include <linux/byteorder/little_endian.h> + +#endif /* _ASM_BYTEORDER_H */ diff --git a/arch/hexagon/include/asm/cache.h b/arch/hexagon/include/asm/cache.h new file mode 100644 index 000000000000..0f01de2eb4ab --- /dev/null +++ b/arch/hexagon/include/asm/cache.h @@ -0,0 +1,34 @@ +/* + * Cache definitions for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef __ASM_CACHE_H +#define __ASM_CACHE_H + +/* Bytes per L1 cache line */ +#define L1_CACHE_SHIFT (5) +#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) + +#define __cacheline_aligned __aligned(L1_CACHE_BYTES) +#define ____cacheline_aligned __aligned(L1_CACHE_BYTES) + +/* See http://kerneltrap.org/node/15100 */ +#define __read_mostly + +#endif diff --git a/arch/hexagon/include/asm/cacheflush.h b/arch/hexagon/include/asm/cacheflush.h new file mode 100644 index 000000000000..6865c1be927a --- /dev/null +++ b/arch/hexagon/include/asm/cacheflush.h @@ -0,0 +1,99 @@ +/* + * Cache flush operations for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_CACHEFLUSH_H +#define _ASM_CACHEFLUSH_H + +#include <linux/cache.h> +#include <linux/mm.h> +#include <asm/string.h> +#include <asm-generic/cacheflush.h> + +/* Cache flushing: + * + * - flush_cache_all() flushes entire cache + * - flush_cache_mm(mm) flushes the specified mm context's cache lines + * - flush_cache_page(mm, vmaddr, pfn) flushes a single page + * - flush_cache_range(vma, start, end) flushes a range of pages + * - flush_icache_range(start, end) flush a range of instructions + * - flush_dcache_page(pg) flushes(wback&invalidates) a page for dcache + * - flush_icache_page(vma, pg) flushes(invalidates) a page for icache + * + * Need to doublecheck which one is really needed for ptrace stuff to work. + */ +#define LINESIZE 32 +#define LINEBITS 5 + +/* + * Flush Dcache range through current map. + */ +extern void flush_dcache_range(unsigned long start, unsigned long end); + +/* + * Flush Icache range through current map. + */ +#undef flush_icache_range +extern void flush_icache_range(unsigned long start, unsigned long end); + +/* + * Memory-management related flushes are there to ensure in non-physically + * indexed cache schemes that stale lines belonging to a given ASID aren't + * in the cache to confuse things. The prototype Hexagon Virtual Machine + * only uses a single ASID for all user-mode maps, which should + * mean that they aren't necessary. A brute-force, flush-everything + * implementation, with the name xxxxx_hexagon() is present in + * arch/hexagon/mm/cache.c, but let's not wire it up until we know + * it is needed. + */ +extern void flush_cache_all_hexagon(void); + +/* + * This may or may not ever have to be non-null, depending on the + * virtual machine MMU. For a native kernel, it's definitiely a no-op + * + * This is also the place where deferred cache coherency stuff seems + * to happen, classically... but instead we do it like ia64 and + * clean the cache when the PTE is set. + * + */ +static inline void update_mmu_cache(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + /* generic_ptrace_pokedata doesn't wind up here, does it? */ +} + +#undef copy_to_user_page +static inline void copy_to_user_page(struct vm_area_struct *vma, + struct page *page, + unsigned long vaddr, + void *dst, void *src, int len) +{ + memcpy(dst, src, len); + if (vma->vm_flags & VM_EXEC) { + flush_icache_range((unsigned long) dst, + (unsigned long) dst + len); + } +} + + +extern void hexagon_inv_dcache_range(unsigned long start, unsigned long end); +extern void hexagon_clean_dcache_range(unsigned long start, unsigned long end); + +#endif diff --git a/arch/hexagon/include/asm/checksum.h b/arch/hexagon/include/asm/checksum.h new file mode 100644 index 000000000000..3ce4ecd44f82 --- /dev/null +++ b/arch/hexagon/include/asm/checksum.h @@ -0,0 +1,50 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_CHECKSUM_H +#define _ASM_CHECKSUM_H + +#define do_csum do_csum +unsigned int do_csum(const void *voidptr, int len); + +/* + * the same as csum_partial, but copies from src while it + * checksums + * + * here even more important to align src and dst on a 32-bit (or even + * better 64-bit) boundary + */ +#define csum_partial_copy_nocheck csum_partial_copy_nocheck +__wsum csum_partial_copy_nocheck(const void *src, void *dst, + int len, __wsum sum); + +/* + * computes the checksum of the TCP/UDP pseudo-header + * returns a 16-bit checksum, already complemented + */ +#define csum_tcpudp_nofold csum_tcpudp_nofold +__wsum csum_tcpudp_nofold(unsigned long saddr, unsigned long daddr, + unsigned short len, unsigned short proto, __wsum sum); + +#define csum_tcpudp_magic csum_tcpudp_magic +__sum16 csum_tcpudp_magic(unsigned long saddr, unsigned long daddr, + unsigned short len, unsigned short proto, __wsum sum); + +#include <asm-generic/checksum.h> + +#endif diff --git a/arch/hexagon/include/asm/delay.h b/arch/hexagon/include/asm/delay.h new file mode 100644 index 000000000000..9ab12e9a872b --- /dev/null +++ b/arch/hexagon/include/asm/delay.h @@ -0,0 +1,28 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_DELAY_H +#define _ASM_DELAY_H + +#include <asm/param.h> + +extern void __udelay(unsigned long usecs); + +#define udelay(usecs) __udelay((usecs)) + +#endif /* _ASM_DELAY_H */ diff --git a/arch/hexagon/include/asm/dma-mapping.h b/arch/hexagon/include/asm/dma-mapping.h new file mode 100644 index 000000000000..448b224ba4ef --- /dev/null +++ b/arch/hexagon/include/asm/dma-mapping.h @@ -0,0 +1,101 @@ +/* + * DMA operations for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_DMA_MAPPING_H +#define _ASM_DMA_MAPPING_H + +#include <linux/types.h> +#include <linux/cache.h> +#include <linux/mm.h> +#include <linux/scatterlist.h> +#include <linux/dma-mapping.h> +#include <linux/dma-debug.h> +#include <linux/dma-attrs.h> +#include <asm/io.h> + +struct device; +extern int bad_dma_address; + +extern struct dma_map_ops *dma_ops; + +#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) +#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) + +static inline struct dma_map_ops *get_dma_ops(struct device *dev) +{ + if (unlikely(dev == NULL)) + return NULL; + + return dma_ops; +} + +extern int dma_supported(struct device *dev, u64 mask); +extern int dma_set_mask(struct device *dev, u64 mask); +extern int dma_is_consistent(struct device *dev, dma_addr_t dma_handle); +extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size, + enum dma_data_direction direction); + +#include <asm-generic/dma-mapping-common.h> + +static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) +{ + if (!dev->dma_mask) + return 0; + return addr + size - 1 <= *dev->dma_mask; +} + +static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + struct dma_map_ops *dma_ops = get_dma_ops(dev); + + if (dma_ops->mapping_error) + return dma_ops->mapping_error(dev, dma_addr); + + return (dma_addr == bad_dma_address); +} + +static inline void *dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag) +{ + void *ret; + struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!dma_ops); + + ret = ops->alloc_coherent(dev, size, dma_handle, flag); + + debug_dma_alloc_coherent(dev, size, *dma_handle, ret); + + return ret; +} + +static inline void dma_free_coherent(struct device *dev, size_t size, + void *cpu_addr, dma_addr_t dma_handle) +{ + struct dma_map_ops *dma_ops = get_dma_ops(dev); + + BUG_ON(!dma_ops); + + dma_ops->free_coherent(dev, size, cpu_addr, dma_handle); + + debug_dma_free_coherent(dev, size, cpu_addr, dma_handle); +} + +#endif diff --git a/arch/hexagon/include/asm/dma.h b/arch/hexagon/include/asm/dma.h new file mode 100644 index 000000000000..da6d2f61a93a --- /dev/null +++ b/arch/hexagon/include/asm/dma.h @@ -0,0 +1,29 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_DMA_H +#define _ASM_DMA_H + +#include <asm/io.h> + +#define MAX_DMA_CHANNELS 1 +#define MAX_DMA_ADDRESS (PAGE_OFFSET) + +extern size_t hexagon_coherent_pool_size; + +#endif diff --git a/arch/hexagon/include/asm/elf.h b/arch/hexagon/include/asm/elf.h new file mode 100644 index 000000000000..37976a0d3650 --- /dev/null +++ b/arch/hexagon/include/asm/elf.h @@ -0,0 +1,229 @@ +/* + * ELF definitions for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef __ASM_ELF_H +#define __ASM_ELF_H + +#include <asm/ptrace.h> +#include <asm/user.h> + +/* + * This should really be in linux/elf-em.h. + */ +#define EM_HEXAGON 164 /* QUALCOMM Hexagon */ + +struct elf32_hdr; + +/* + * ELF header e_flags defines. + */ + +/* should have stuff like "CPU type" and maybe "ABI version", etc */ + +/* Hexagon relocations */ + /* V2 */ +#define R_HEXAGON_NONE 0 +#define R_HEXAGON_B22_PCREL 1 +#define R_HEXAGON_B15_PCREL 2 +#define R_HEXAGON_B7_PCREL 3 +#define R_HEXAGON_LO16 4 +#define R_HEXAGON_HI16 5 +#define R_HEXAGON_32 6 +#define R_HEXAGON_16 7 +#define R_HEXAGON_8 8 +#define R_HEXAGON_GPREL16_0 9 +#define R_HEXAGON_GPREL16_1 10 +#define R_HEXAGON_GPREL16_2 11 +#define R_HEXAGON_GPREL16_3 12 +#define R_HEXAGON_HL16 13 + /* V3 */ +#define R_HEXAGON_B13_PCREL 14 + /* V4 */ +#define R_HEXAGON_B9_PCREL 15 + /* V4 (extenders) */ +#define R_HEXAGON_B32_PCREL_X 16 +#define R_HEXAGON_32_6_X 17 + /* V4 (extended) */ +#define R_HEXAGON_B22_PCREL_X 18 +#define R_HEXAGON_B15_PCREL_X 19 +#define R_HEXAGON_B13_PCREL_X 20 +#define R_HEXAGON_B9_PCREL_X 21 +#define R_HEXAGON_B7_PCREL_X 22 +#define R_HEXAGON_16_X 23 +#define R_HEXAGON_12_X 24 +#define R_HEXAGON_11_X 25 +#define R_HEXAGON_10_X 26 +#define R_HEXAGON_9_X 27 +#define R_HEXAGON_8_X 28 +#define R_HEXAGON_7_X 29 +#define R_HEXAGON_6_X 30 + /* V2 PIC */ +#define R_HEXAGON_32_PCREL 31 +#define R_HEXAGON_COPY 32 +#define R_HEXAGON_GLOB_DAT 33 +#define R_HEXAGON_JMP_SLOT 34 +#define R_HEXAGON_RELATIVE 35 +#define R_HEXAGON_PLT_B22_PCREL 36 +#define R_HEXAGON_GOTOFF_LO16 37 +#define R_HEXAGON_GOTOFF_HI16 38 +#define R_HEXAGON_GOTOFF_32 39 +#define R_HEXAGON_GOT_LO16 40 +#define R_HEXAGON_GOT_HI16 41 +#define R_HEXAGON_GOT_32 42 +#define R_HEXAGON_GOT_16 43 + +/* + * ELF register definitions.. + */ +typedef unsigned long elf_greg_t; + +typedef struct user_regs_struct elf_gregset_t; +#define ELF_NGREG (sizeof(elf_gregset_t)/sizeof(unsigned long)) + +/* Placeholder */ +typedef unsigned long elf_fpregset_t; + +/* + * Bypass the whole "regsets" thing for now and use the define. + */ + +#define ELF_CORE_COPY_REGS(DEST, REGS) \ +do { \ + DEST.r0 = REGS->r00; \ + DEST.r1 = REGS->r01; \ + DEST.r2 = REGS->r02; \ + DEST.r3 = REGS->r03; \ + DEST.r4 = REGS->r04; \ + DEST.r5 = REGS->r05; \ + DEST.r6 = REGS->r06; \ + DEST.r7 = REGS->r07; \ + DEST.r8 = REGS->r08; \ + DEST.r9 = REGS->r09; \ + DEST.r10 = REGS->r10; \ + DEST.r11 = REGS->r11; \ + DEST.r12 = REGS->r12; \ + DEST.r13 = REGS->r13; \ + DEST.r14 = REGS->r14; \ + DEST.r15 = REGS->r15; \ + DEST.r16 = REGS->r16; \ + DEST.r17 = REGS->r17; \ + DEST.r18 = REGS->r18; \ + DEST.r19 = REGS->r19; \ + DEST.r20 = REGS->r20; \ + DEST.r21 = REGS->r21; \ + DEST.r22 = REGS->r22; \ + DEST.r23 = REGS->r23; \ + DEST.r24 = REGS->r24; \ + DEST.r25 = REGS->r25; \ + DEST.r26 = REGS->r26; \ + DEST.r27 = REGS->r27; \ + DEST.r28 = REGS->r28; \ + DEST.r29 = pt_psp(REGS); \ + DEST.r30 = REGS->r30; \ + DEST.r31 = REGS->r31; \ + DEST.sa0 = REGS->sa0; \ + DEST.lc0 = REGS->lc0; \ + DEST.sa1 = REGS->sa1; \ + DEST.lc1 = REGS->lc1; \ + DEST.m0 = REGS->m0; \ + DEST.m1 = REGS->m1; \ + DEST.usr = REGS->usr; \ + DEST.p3_0 = REGS->preds; \ + DEST.gp = REGS->gp; \ + DEST.ugp = REGS->ugp; \ + DEST.pc = pt_elr(REGS); \ + DEST.cause = pt_cause(REGS); \ + DEST.badva = pt_badva(REGS); \ +} while (0); + + + +/* + * This is used to ensure we don't load something for the wrong architecture. + * Checks the machine and ABI type. + */ +#define elf_check_arch(hdr) ((hdr)->e_machine == EM_HEXAGON) + +/* + * These are used to set parameters in the core dumps. + */ +#define ELF_CLASS ELFCLASS32 +#define ELF_DATA ELFDATA2LSB +#define ELF_ARCH EM_HEXAGON + +#ifdef CONFIG_HEXAGON_ARCH_V2 +#define ELF_CORE_EFLAGS 0x1 +#endif + +#ifdef CONFIG_HEXAGON_ARCH_V3 +#define ELF_CORE_EFLAGS 0x2 +#endif + +#ifdef CONFIG_HEXAGON_ARCH_V4 +#define ELF_CORE_EFLAGS 0x3 +#endif + +/* + * Some architectures have ld.so set up a pointer to a function + * to be registered using atexit, to facilitate cleanup. So that + * static executables will be well-behaved, we would null the register + * in question here, in the pt_regs structure passed. For now, + * leave it a null macro. + */ +#define ELF_PLAT_INIT(regs, load_addr) do { } while (0) + +#define USE_ELF_CORE_DUMP +#define CORE_DUMP_USE_REGSET + +/* Hrm is this going to cause problems for changing PAGE_SIZE? */ +#define ELF_EXEC_PAGESIZE 4096 + +/* + * This is the location that an ET_DYN program is loaded if exec'ed. Typical + * use of this is to invoke "./ld.so someprog" to test out a new version of + * the loader. We need to make sure that it is out of the way of the program + * that it will "exec", and that there is sufficient room for the brk. + */ +#define ELF_ET_DYN_BASE 0x08000000UL + +/* + * This yields a mask that user programs can use to figure out what + * instruction set this cpu supports. + */ +#define ELF_HWCAP (0) + +/* + * This yields a string that ld.so will use to load implementation + * specific libraries for optimization. This is more specific in + * intent than poking at uname or /proc/cpuinfo. + */ +#define ELF_PLATFORM (NULL) + +#ifdef __KERNEL__ +#define SET_PERSONALITY(ex) set_personality(PER_LINUX) +#endif + +#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 +struct linux_binprm; +extern int arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp); + + +#endif diff --git a/arch/hexagon/include/asm/fixmap.h b/arch/hexagon/include/asm/fixmap.h new file mode 100644 index 000000000000..b27f4941645b --- /dev/null +++ b/arch/hexagon/include/asm/fixmap.h @@ -0,0 +1,73 @@ +/* + * Fixmap support for Hexagon - enough to support highmem features + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_FIXMAP_H +#define _ASM_FIXMAP_H + +/* + * A lot of the fixmap info is already in mem-layout.h + */ +#include <asm/mem-layout.h> + +/* + * Full fixmap support involves set_fixmap() functions, but + * these may not be needed if all we're after is an area for + * highmem kernel mappings. + */ +#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT)) +#define __virt_to_fix(x) ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT) + +extern void __this_fixmap_does_not_exist(void); + +/** + * fix_to_virt -- "index to address" translation. + * + * If anyone tries to use the idx directly without translation, + * we catch the bug with a NULL-deference kernel oops. Illegal + * ranges of incoming indices are caught too. + */ +static inline unsigned long fix_to_virt(const unsigned int idx) +{ + /* + * This branch gets completely eliminated after inlining, + * except when someone tries to use fixaddr indices in an + * illegal way. (such as mixing up address types or using + * out-of-range indices). + * + * If it doesn't get removed, the linker will complain + * loudly with a reasonably clear error message.. + */ + if (idx >= __end_of_fixed_addresses) + __this_fixmap_does_not_exist(); + + return __fix_to_virt(idx); +} + +static inline unsigned long virt_to_fix(const unsigned long vaddr) +{ + BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START); + return __virt_to_fix(vaddr); +} + +#define kmap_get_fixmap_pte(vaddr) \ + pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), \ + (vaddr)), (vaddr)), (vaddr)) + +#endif diff --git a/arch/hexagon/include/asm/fpu.h b/arch/hexagon/include/asm/fpu.h new file mode 100644 index 000000000000..0e135ea8c45b --- /dev/null +++ b/arch/hexagon/include/asm/fpu.h @@ -0,0 +1,4 @@ +/* + * If the FPU is used inside the kernel, + * kernel_fpu_end() will be defined here. + */ diff --git a/arch/hexagon/include/asm/futex.h b/arch/hexagon/include/asm/futex.h new file mode 100644 index 000000000000..7e597f8434da --- /dev/null +++ b/arch/hexagon/include/asm/futex.h @@ -0,0 +1,137 @@ +#ifndef _ASM_HEXAGON_FUTEX_H +#define _ASM_HEXAGON_FUTEX_H + +#ifdef __KERNEL__ + +#include <linux/futex.h> +#include <linux/uaccess.h> +#include <asm/errno.h> + +/* XXX TODO-- need to add sync barriers! */ + +#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ + __asm__ __volatile( \ + "1: %0 = memw_locked(%3);\n" \ + /* For example: %1 = %4 */ \ + insn \ + "2: memw_locked(%3,p2) = %1;\n" \ + " if !p2 jump 1b;\n" \ + " %1 = #0;\n" \ + "3:\n" \ + ".section .fixup,\"ax\"\n" \ + "4: %1 = #%5;\n" \ + " jump 3b\n" \ + ".previous\n" \ + ".section __ex_table,\"a\"\n" \ + ".long 1b,4b,2b,4b\n" \ + ".previous\n" \ + : "=&r" (oldval), "=&r" (ret), "+m" (*uaddr) \ + : "r" (uaddr), "r" (oparg), "i" (-EFAULT) \ + : "p2", "memory") + + +static inline int +futex_atomic_op_inuser(int encoded_op, int __user *uaddr) +{ + int op = (encoded_op >> 28) & 7; + int cmp = (encoded_op >> 24) & 15; + int oparg = (encoded_op << 8) >> 20; + int cmparg = (encoded_op << 20) >> 20; + int oldval = 0, ret; + if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) + oparg = 1 << oparg; + + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + return -EFAULT; + + pagefault_disable(); + + switch (op) { + case FUTEX_OP_SET: + __futex_atomic_op("%1 = %4\n", ret, oldval, uaddr, oparg); + break; + case FUTEX_OP_ADD: + __futex_atomic_op("%1 = add(%0,%4)\n", ret, oldval, uaddr, + oparg); + break; + case FUTEX_OP_OR: + __futex_atomic_op("%1 = or(%0,%4)\n", ret, oldval, uaddr, + oparg); + break; + case FUTEX_OP_ANDN: + __futex_atomic_op("%1 = not(%4); %1 = and(%0,%1)\n", ret, + oldval, uaddr, oparg); + break; + case FUTEX_OP_XOR: + __futex_atomic_op("%1 = xor(%0,%4)\n", ret, oldval, uaddr, + oparg); + break; + default: + ret = -ENOSYS; + } + + pagefault_enable(); + + if (!ret) { + switch (cmp) { + case FUTEX_OP_CMP_EQ: + ret = (oldval == cmparg); + break; + case FUTEX_OP_CMP_NE: + ret = (oldval != cmparg); + break; + case FUTEX_OP_CMP_LT: + ret = (oldval < cmparg); + break; + case FUTEX_OP_CMP_GE: + ret = (oldval >= cmparg); + break; + case FUTEX_OP_CMP_LE: + ret = (oldval <= cmparg); + break; + case FUTEX_OP_CMP_GT: + ret = (oldval > cmparg); + break; + default: + ret = -ENOSYS; + } + } + return ret; +} + +static inline int +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, + u32 newval) +{ + int prev; + int ret; + + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + + __asm__ __volatile__ ( + "1: %1 = memw_locked(%3)\n" + " {\n" + " p2 = cmp.eq(%1,%4)\n" + " if !p2.new jump:NT 3f\n" + " }\n" + "2: memw_locked(%3,p2) = %5\n" + " if !p2 jump 1b\n" + "3:\n" + ".section .fixup,\"ax\"\n" + "4: %0 = #%6\n" + " jump 3b\n" + ".previous\n" + ".section __ex_table,\"a\"\n" + ".long 1b,4b,2b,4b\n" + ".previous\n" + : "+r" (ret), "=&r" (prev), "+m" (*uaddr) + : "r" (uaddr), "r" (oldval), "r" (newval), "i"(-EFAULT) + : "p2", "memory"); + + *uval = prev; + return ret; +} + +#endif /* __KERNEL__ */ +#endif /* _ASM_HEXAGON_FUTEX_H */ diff --git a/arch/hexagon/include/asm/hexagon_vm.h b/arch/hexagon/include/asm/hexagon_vm.h new file mode 100644 index 000000000000..182cb9d54769 --- /dev/null +++ b/arch/hexagon/include/asm/hexagon_vm.h @@ -0,0 +1,281 @@ +/* + * Declarations for to Hexagon Virtal Machine. + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef ASM_HEXAGON_VM_H +#define ASM_HEXAGON_VM_H + +/* + * In principle, a Linux kernel for the VM could + * selectively define the virtual instructions + * as inline assembler macros, but for a first pass, + * we'll use subroutines for both the VM and the native + * kernels. It's costing a subroutine call/return, + * but it makes for a single set of entry points + * for tracing/debugging. + */ + +/* + * Lets make this stuff visible only if configured, + * so we can unconditionally include the file. + */ + +#ifndef __ASSEMBLY__ + +enum VM_CACHE_OPS { + ickill, + dckill, + l2kill, + dccleaninva, + icinva, + idsync, + fetch_cfg +}; + +enum VM_INT_OPS { + nop, + globen, + globdis, + locen, + locdis, + affinity, + get, + peek, + status, + post, + clear +}; + +extern void _K_VM_event_vector(void); + +void __vmrte(void); +long __vmsetvec(void *); +long __vmsetie(long); +long __vmgetie(void); +long __vmintop(enum VM_INT_OPS, long, long, long, long); +long __vmclrmap(void *, unsigned long); +long __vmnewmap(void *); +long __vmcache(enum VM_CACHE_OPS op, unsigned long addr, unsigned long len); +unsigned long long __vmgettime(void); +long __vmsettime(unsigned long long); +long __vmstart(void *, void *); +void __vmstop(void); +long __vmwait(void); +void __vmyield(void); +long __vmvpid(void); + +static inline long __vmcache_ickill(void) +{ + return __vmcache(ickill, 0, 0); +} + +static inline long __vmcache_dckill(void) +{ + return __vmcache(dckill, 0, 0); +} + +static inline long __vmcache_l2kill(void) +{ + return __vmcache(l2kill, 0, 0); +} + +static inline long __vmcache_dccleaninva(unsigned long addr, unsigned long len) +{ + return __vmcache(dccleaninva, addr, len); +} + +static inline long __vmcache_icinva(unsigned long addr, unsigned long len) +{ + return __vmcache(icinva, addr, len); +} + +static inline long __vmcache_idsync(unsigned long addr, + unsigned long len) +{ + return __vmcache(idsync, addr, len); +} + +static inline long __vmcache_fetch_cfg(unsigned long val) +{ + return __vmcache(fetch_cfg, val, 0); +} + +/* interrupt operations */ + +static inline long __vmintop_nop(void) +{ + return __vmintop(nop, 0, 0, 0, 0); +} + +static inline long __vmintop_globen(long i) +{ + return __vmintop(globen, i, 0, 0, 0); +} + +static inline long __vmintop_globdis(long i) +{ + return __vmintop(globdis, i, 0, 0, 0); +} + +static inline long __vmintop_locen(long i) +{ + return __vmintop(locen, i, 0, 0, 0); +} + +static inline long __vmintop_locdis(long i) +{ + return __vmintop(locdis, i, 0, 0, 0); +} + +static inline long __vmintop_affinity(long i, long cpu) +{ + return __vmintop(locdis, i, cpu, 0, 0); +} + +static inline long __vmintop_get(void) +{ + return __vmintop(get, 0, 0, 0, 0); +} + +static inline long __vmintop_peek(void) +{ + return __vmintop(peek, 0, 0, 0, 0); +} + +static inline long __vmintop_status(long i) +{ + return __vmintop(status, i, 0, 0, 0); +} + +static inline long __vmintop_post(long i) +{ + return __vmintop(post, i, 0, 0, 0); +} + +static inline long __vmintop_clear(long i) +{ + return __vmintop(clear, i, 0, 0, 0); +} + +#else /* Only assembly code should reference these */ + +#define HVM_TRAP1_VMRTE 1 +#define HVM_TRAP1_VMSETVEC 2 +#define HVM_TRAP1_VMSETIE 3 +#define HVM_TRAP1_VMGETIE 4 +#define HVM_TRAP1_VMINTOP 5 +#define HVM_TRAP1_VMCLRMAP 10 +#define HVM_TRAP1_VMNEWMAP 11 +#define HVM_TRAP1_FORMERLY_VMWIRE 12 +#define HVM_TRAP1_VMCACHE 13 +#define HVM_TRAP1_VMGETTIME 14 +#define HVM_TRAP1_VMSETTIME 15 +#define HVM_TRAP1_VMWAIT 16 +#define HVM_TRAP1_VMYIELD 17 +#define HVM_TRAP1_VMSTART 18 +#define HVM_TRAP1_VMSTOP 19 +#define HVM_TRAP1_VMVPID 20 +#define HVM_TRAP1_VMSETREGS 21 +#define HVM_TRAP1_VMGETREGS 22 + +#endif /* __ASSEMBLY__ */ + +/* + * Constants for virtual instruction parameters and return values + */ + +/* vmsetie arguments */ + +#define VM_INT_DISABLE 0 +#define VM_INT_ENABLE 1 + +/* vmsetimask arguments */ + +#define VM_INT_UNMASK 0 +#define VM_INT_MASK 1 + +#define VM_NEWMAP_TYPE_LINEAR 0 +#define VM_NEWMAP_TYPE_PGTABLES 1 + + +/* + * Event Record definitions useful to both C and Assembler + */ + +/* VMEST Layout */ + +#define HVM_VMEST_UM_SFT 31 +#define HVM_VMEST_UM_MSK 1 +#define HVM_VMEST_IE_SFT 30 +#define HVM_VMEST_IE_MSK 1 +#define HVM_VMEST_EVENTNUM_SFT 16 +#define HVM_VMEST_EVENTNUM_MSK 0xff +#define HVM_VMEST_CAUSE_SFT 0 +#define HVM_VMEST_CAUSE_MSK 0xffff + +/* + * The initial program gets to find a system environment descriptor + * on its stack when it begins exection. The first word is a version + * code to indicate what is there. Zero means nothing more. + */ + +#define HEXAGON_VM_SED_NULL 0 + +/* + * Event numbers for vector binding + */ + +#define HVM_EV_RESET 0 +#define HVM_EV_MACHCHECK 1 +#define HVM_EV_GENEX 2 +#define HVM_EV_TRAP 8 +#define HVM_EV_INTR 15 +/* These shoud be nuked as soon as we know the VM is up to spec v0.1.1 */ +#define HVM_EV_INTR_0 16 +#define HVM_MAX_INTR 240 + +/* + * Cause values for General Exception + */ + +#define HVM_GE_C_BUS 0x01 +#define HVM_GE_C_XPROT 0x11 +#define HVM_GE_C_XUSER 0x14 +#define HVM_GE_C_INVI 0x15 +#define HVM_GE_C_PRIVI 0x1B +#define HVM_GE_C_XMAL 0x1C +#define HVM_GE_C_RMAL 0x20 +#define HVM_GE_C_WMAL 0x21 +#define HVM_GE_C_RPROT 0x22 +#define HVM_GE_C_WPROT 0x23 +#define HVM_GE_C_RUSER 0x24 +#define HVM_GE_C_WUSER 0x25 +#define HVM_GE_C_CACHE 0x28 + +/* + * Cause codes for Machine Check + */ + +#define HVM_MCHK_C_DOWN 0x00 +#define HVM_MCHK_C_BADSP 0x01 +#define HVM_MCHK_C_BADEX 0x02 +#define HVM_MCHK_C_BADPT 0x03 +#define HVM_MCHK_C_REGWR 0x29 + +#endif diff --git a/arch/hexagon/include/asm/intrinsics.h b/arch/hexagon/include/asm/intrinsics.h new file mode 100644 index 000000000000..1c02186d2e9a --- /dev/null +++ b/arch/hexagon/include/asm/intrinsics.h @@ -0,0 +1,26 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_HEXAGON_INTRINSICS_H +#define _ASM_HEXAGON_INTRINSICS_H + +#define HEXAGON_P_vrmpyhacc_PP __builtin_HEXAGON_M2_vrmac_s0 +#define HEXAGON_P_vrmpyh_PP __builtin_HEXAGON_M2_vrmpy_s0 +#define HEXAGON_R_cl0_R __builtin_HEXAGON_S2_cl0 + +#endif diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h new file mode 100644 index 000000000000..b3acc2cc71bf --- /dev/null +++ b/arch/hexagon/include/asm/io.h @@ -0,0 +1,326 @@ +/* + * IO definitions for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_IO_H +#define _ASM_IO_H + +#ifdef __KERNEL__ + +#include <linux/types.h> +#include <linux/delay.h> +#include <linux/vmalloc.h> +#include <asm/string.h> +#include <asm/mem-layout.h> +#include <asm/iomap.h> +#include <asm/page.h> +#include <asm/cacheflush.h> +#include <asm/tlbflush.h> + +/* + * We don't have PCI yet. + * _IO_BASE is pointing at what should be unused virtual space. + */ +#define IO_SPACE_LIMIT 0xffff +#define _IO_BASE ((void __iomem *)0xfe000000) + +extern int remap_area_pages(unsigned long start, unsigned long phys_addr, + unsigned long end, unsigned long flags); + +extern void __iounmap(const volatile void __iomem *addr); + +/* Defined in lib/io.c, needed for smc91x driver. */ +extern void __raw_readsw(const void __iomem *addr, void *data, int wordlen); +extern void __raw_writesw(void __iomem *addr, const void *data, int wordlen); + +extern void __raw_readsl(const void __iomem *addr, void *data, int wordlen); +extern void __raw_writesl(void __iomem *addr, const void *data, int wordlen); + +#define readsw(p, d, l) __raw_readsw(p, d, l) +#define writesw(p, d, l) __raw_writesw(p, d, l) + +#define readsl(p, d, l) __raw_readsl(p, d, l) +#define writesl(p, d, l) __raw_writesl(p, d, l) + +/* + * virt_to_phys - map virtual address to physical + * @address: address to map + */ +static inline unsigned long virt_to_phys(volatile void *address) +{ + return __pa(address); +} + +/* + * phys_to_virt - map physical address to virtual + * @address: address to map + */ +static inline void *phys_to_virt(unsigned long address) +{ + return __va(address); +} + +/* + * convert a physical pointer to a virtual kernel pointer for + * /dev/mem access. + */ +#define xlate_dev_kmem_ptr(p) __va(p) +#define xlate_dev_mem_ptr(p) __va(p) + +/* + * IO port access primitives. Hexagon doesn't have special IO access + * instructions; all I/O is memory mapped. + * + * in/out are used for "ports", but we don't have "port instructions", + * so these are really just memory mapped too. + */ + +/* + * readb - read byte from memory mapped device + * @addr: pointer to memory + * + * Operates on "I/O bus memory space" + */ +static inline u8 readb(const volatile void __iomem *addr) +{ + u8 val; + asm volatile( + "%0 = memb(%1);" + : "=&r" (val) + : "r" (addr) + ); + return val; +} + +static inline u16 readw(const volatile void __iomem *addr) +{ + u16 val; + asm volatile( + "%0 = memh(%1);" + : "=&r" (val) + : "r" (addr) + ); + return val; +} + +static inline u32 readl(const volatile void __iomem *addr) +{ + u32 val; + asm volatile( + "%0 = memw(%1);" + : "=&r" (val) + : "r" (addr) + ); + return val; +} + +/* + * writeb - write a byte to a memory location + * @data: data to write to + * @addr: pointer to memory + * + */ +static inline void writeb(u8 data, volatile void __iomem *addr) +{ + asm volatile( + "memb(%0) = %1;" + : + : "r" (addr), "r" (data) + : "memory" + ); +} + +static inline void writew(u16 data, volatile void __iomem *addr) +{ + asm volatile( + "memh(%0) = %1;" + : + : "r" (addr), "r" (data) + : "memory" + ); + +} + +static inline void writel(u32 data, volatile void __iomem *addr) +{ + asm volatile( + "memw(%0) = %1;" + : + : "r" (addr), "r" (data) + : "memory" + ); +} + +#define __raw_writeb writeb +#define __raw_writew writew +#define __raw_writel writel + +#define __raw_readb readb +#define __raw_readw readw +#define __raw_readl readl + +/* + * Need an mtype somewhere in here, for cache type deals? + * This is probably too long for an inline. + */ +void __iomem *ioremap_nocache(unsigned long phys_addr, unsigned long size); + +static inline void __iomem *ioremap(unsigned long phys_addr, unsigned long size) +{ + return ioremap_nocache(phys_addr, size); +} + +static inline void iounmap(volatile void __iomem *addr) +{ + __iounmap(addr); +} + +#define __raw_writel writel + +static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, + int count) +{ + memcpy(dst, (void *) src, count); +} + +static inline void memcpy_toio(volatile void __iomem *dst, const void *src, + int count) +{ + memcpy((void *) dst, src, count); +} + +#define PCI_IO_ADDR (volatile void __iomem *) + +/* + * inb - read byte from I/O port or something + * @port: address in I/O space + * + * Operates on "I/O bus I/O space" + */ +static inline u8 inb(unsigned long port) +{ + return readb(_IO_BASE + (port & IO_SPACE_LIMIT)); +} + +static inline u16 inw(unsigned long port) +{ + return readw(_IO_BASE + (port & IO_SPACE_LIMIT)); +} + +static inline u32 inl(unsigned long port) +{ + return readl(_IO_BASE + (port & IO_SPACE_LIMIT)); +} + +/* + * outb - write a byte to a memory location + * @data: data to write to + * @addr: address in I/O space + */ +static inline void outb(u8 data, unsigned long port) +{ + writeb(data, _IO_BASE + (port & IO_SPACE_LIMIT)); +} + +static inline void outw(u16 data, unsigned long port) +{ + writew(data, _IO_BASE + (port & IO_SPACE_LIMIT)); +} + +static inline void outl(u32 data, unsigned long port) +{ + writel(data, _IO_BASE + (port & IO_SPACE_LIMIT)); +} + +#define outb_p outb +#define outw_p outw +#define outl_p outl + +#define inb_p inb +#define inw_p inw +#define inl_p inl + +static inline void insb(unsigned long port, void *buffer, int count) +{ + if (count) { + u8 *buf = buffer; + do { + u8 x = inb(port); + *buf++ = x; + } while (--count); + } +} + +static inline void insw(unsigned long port, void *buffer, int count) +{ + if (count) { + u16 *buf = buffer; + do { + u16 x = inw(port); + *buf++ = x; + } while (--count); + } +} + +static inline void insl(unsigned long port, void *buffer, int count) +{ + if (count) { + u32 *buf = buffer; + do { + u32 x = inw(port); + *buf++ = x; + } while (--count); + } +} + +static inline void outsb(unsigned long port, const void *buffer, int count) +{ + if (count) { + const u8 *buf = buffer; + do { + outb(*buf++, port); + } while (--count); + } +} + +static inline void outsw(unsigned long port, const void *buffer, int count) +{ + if (count) { + const u16 *buf = buffer; + do { + outw(*buf++, port); + } while (--count); + } +} + +static inline void outsl(unsigned long port, const void *buffer, int count) +{ + if (count) { + const u32 *buf = buffer; + do { + outl(*buf++, port); + } while (--count); + } +} + +#define flush_write_buffers() do { } while (0) + +#endif /* __KERNEL__ */ + +#endif diff --git a/arch/hexagon/include/asm/irq.h b/arch/hexagon/include/asm/irq.h new file mode 100644 index 000000000000..ded8c15cf3e5 --- /dev/null +++ b/arch/hexagon/include/asm/irq.h @@ -0,0 +1,36 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_IRQ_H_ +#define _ASM_IRQ_H_ + +/* Number of first-level interrupts associated with the CPU core. */ +#define HEXAGON_CPUINTS 32 + +/* + * Must define NR_IRQS before including <asm-generic/irq.h> + * 64 == the two SIRC's, 176 == the two gpio's + * + * IRQ configuration is still in flux; defining this to a comfortably + * large number. + */ +#define NR_IRQS 512 + +#include <asm-generic/irq.h> + +#endif diff --git a/arch/hexagon/include/asm/irqflags.h b/arch/hexagon/include/asm/irqflags.h new file mode 100644 index 000000000000..ec1523655416 --- /dev/null +++ b/arch/hexagon/include/asm/irqflags.h @@ -0,0 +1,62 @@ +/* + * IRQ support for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_IRQFLAGS_H +#define _ASM_IRQFLAGS_H + +#include <asm/hexagon_vm.h> +#include <linux/types.h> + +static inline unsigned long arch_local_save_flags(void) +{ + return __vmgetie(); +} + +static inline unsigned long arch_local_irq_save(void) +{ + return __vmsetie(VM_INT_DISABLE); +} + +static inline bool arch_irqs_disabled_flags(unsigned long flags) +{ + return !flags; +} + +static inline bool arch_irqs_disabled(void) +{ + return !__vmgetie(); +} + +static inline void arch_local_irq_enable(void) +{ + __vmsetie(VM_INT_ENABLE); +} + +static inline void arch_local_irq_disable(void) +{ + __vmsetie(VM_INT_DISABLE); +} + +static inline void arch_local_irq_restore(unsigned long flags) +{ + __vmsetie(flags); +} + +#endif diff --git a/arch/hexagon/include/asm/kgdb.h b/arch/hexagon/include/asm/kgdb.h new file mode 100644 index 000000000000..9e8779702f10 --- /dev/null +++ b/arch/hexagon/include/asm/kgdb.h @@ -0,0 +1,43 @@ +/* + * arch/hexagon/include/asm/kgdb.h - Hexagon KGDB Support + * + * Copyright (c) 2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef __HEXAGON_KGDB_H__ +#define __HEXAGON_KGDB_H__ + +#define BREAK_INSTR_SIZE 4 +#define CACHE_FLUSH_IS_SAFE 1 +#define BUFMAX ((NUMREGBYTES * 2) + 512) + +static inline void arch_kgdb_breakpoint(void) +{ + asm("trap0(#0xDB)"); +} + +/* Registers: + * 32 gpr + sa0/1 + lc0/1 + m0/1 + gp + ugp + pred + pc = 42 total. + * vm regs = psp+elr+est+badva = 4 + * syscall+restart = 2 more + * so 48 = 42 +4 + 2 + */ +#define DBG_USER_REGS 42 +#define DBG_MAX_REG_NUM (DBG_USER_REGS + 6) +#define NUMREGBYTES (DBG_MAX_REG_NUM*4) + +#endif /* __HEXAGON_KGDB_H__ */ diff --git a/arch/hexagon/include/asm/linkage.h b/arch/hexagon/include/asm/linkage.h new file mode 100644 index 000000000000..a00b85f680b8 --- /dev/null +++ b/arch/hexagon/include/asm/linkage.h @@ -0,0 +1,25 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef __ASM_LINKAGE_H +#define __ASM_LINKAGE_H + +#define __ALIGN .align 4 +#define __ALIGN_STR ".align 4" + +#endif diff --git a/arch/hexagon/include/asm/mem-layout.h b/arch/hexagon/include/asm/mem-layout.h new file mode 100644 index 000000000000..72e5dcda79f5 --- /dev/null +++ b/arch/hexagon/include/asm/mem-layout.h @@ -0,0 +1,112 @@ +/* + * Memory layout definitions for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_HEXAGON_MEM_LAYOUT_H +#define _ASM_HEXAGON_MEM_LAYOUT_H + +#include <linux/const.h> + +/* + * Have to do this for ginormous numbers, else they get printed as + * negative numbers, which the linker no likey when you try to + * assign it to the location counter. + */ + +#define PAGE_OFFSET _AC(0xc0000000, UL) + +/* + * LOAD_ADDRESS is the physical/linear address of where in memory + * the kernel gets loaded. The 12 least significant bits must be zero (0) + * due to limitations on setting the EVB + * + */ + +#ifndef LOAD_ADDRESS +#define LOAD_ADDRESS 0x00000000 +#endif + +#define TASK_SIZE (PAGE_OFFSET) + +/* not sure how these are used yet */ +#define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX TASK_SIZE + +#ifndef __ASSEMBLY__ +enum fixed_addresses { + FIX_KMAP_BEGIN, + FIX_KMAP_END, /* check for per-cpuism */ + __end_of_fixed_addresses +}; + +#define MIN_KERNEL_SEG 0x300 /* From 0xc0000000 */ +extern int max_kernel_seg; + +/* + * Start of vmalloc virtual address space for kernel; + * supposed to be based on the amount of physical memory available + */ + +#define VMALLOC_START (PAGE_OFFSET + VMALLOC_OFFSET + \ + (unsigned long)high_memory) + +/* Gap between physical ram and vmalloc space for guard purposes. */ +#define VMALLOC_OFFSET PAGE_SIZE + +/* + * Create the space between VMALLOC_START and FIXADDR_TOP backwards + * from the ... "top". + * + * Permanent IO mappings will live at 0xfexx_xxxx + * Hypervisor occupies the last 16MB page at 0xffxxxxxx + */ + +#define FIXADDR_TOP 0xfe000000 +#define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) + +/* + * "permanent kernel mappings", defined as long-lasting mappings of + * high-memory page frames into the kernel address space. + */ + +#define LAST_PKMAP PTRS_PER_PTE +#define LAST_PKMAP_MASK (LAST_PKMAP - 1) +#define PKMAP_NR(virt) ((virt - PKMAP_BASE) >> PAGE_SHIFT) +#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT)) + +/* + * To the "left" of the fixed map space is the kmap space + * + * "Permanent Kernel Mappings"; fancy (or less fancy) PTE table + * that looks like it's actually walked. + * Need to check the alignment/shift usage; some archs use + * PMD_MASK on this value + */ +#define PKMAP_BASE (FIXADDR_START-PAGE_SIZE*LAST_PKMAP) + +/* + * 2 pages of guard gap between where vmalloc area ends + * and pkmap_base begins. + */ +#define VMALLOC_END (PKMAP_BASE-PAGE_SIZE*2) +#endif /* !__ASSEMBLY__ */ + + +#endif /* _ASM_HEXAGON_MEM_LAYOUT_H */ diff --git a/arch/hexagon/include/asm/mmu.h b/arch/hexagon/include/asm/mmu.h new file mode 100644 index 000000000000..30a5d8d2659d --- /dev/null +++ b/arch/hexagon/include/asm/mmu.h @@ -0,0 +1,37 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_MMU_H +#define _ASM_MMU_H + +#include <asm/vdso.h> + +/* + * Architecture-specific state for a mm_struct. + * For the Hexagon Virtual Machine, it can be a copy + * of the pointer to the page table base. + */ +struct mm_context { + unsigned long long generation; + unsigned long ptbase; + struct hexagon_vdso *vdso; +}; + +typedef struct mm_context mm_context_t; + +#endif diff --git a/arch/hexagon/include/asm/mmu_context.h b/arch/hexagon/include/asm/mmu_context.h new file mode 100644 index 000000000000..b4fe5a5411b6 --- /dev/null +++ b/arch/hexagon/include/asm/mmu_context.h @@ -0,0 +1,100 @@ +/* + * MM context support for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_MMU_CONTEXT_H +#define _ASM_MMU_CONTEXT_H + +#include <asm/setup.h> +#include <asm/page.h> +#include <asm/pgalloc.h> +#include <asm/mem-layout.h> + +static inline void destroy_context(struct mm_struct *mm) +{ +} + +/* + * VM port hides all TLB management, so "lazy TLB" isn't very + * meaningful. Even for ports to architectures with visble TLBs, + * this is almost invariably a null function. + */ +static inline void enter_lazy_tlb(struct mm_struct *mm, + struct task_struct *tsk) +{ +} + +/* + * Architecture-specific actions, if any, for memory map deactivation. + */ +static inline void deactivate_mm(struct task_struct *tsk, + struct mm_struct *mm) +{ +} + +/** + * init_new_context - initialize context related info for new mm_struct instance + * @tsk: pointer to a task struct + * @mm: pointer to a new mm struct + */ +static inline int init_new_context(struct task_struct *tsk, + struct mm_struct *mm) +{ + /* mm->context is set up by pgd_alloc */ + return 0; +} + +/* + * Switch active mm context + */ +static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk) +{ + int l1; + + /* + * For virtual machine, we have to update system map if it's been + * touched. + */ + if (next->context.generation < prev->context.generation) { + for (l1 = MIN_KERNEL_SEG; l1 <= max_kernel_seg; l1++) + next->pgd[l1] = init_mm.pgd[l1]; + + next->context.generation = prev->context.generation; + } + + __vmnewmap((void *)next->context.ptbase); +} + +/* + * Activate new memory map for task + */ +static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) +{ + unsigned long flags; + + local_irq_save(flags); + switch_mm(prev, next, current_thread_info()->task); + local_irq_restore(flags); +} + +/* Generic hooks for arch_dup_mmap and arch_exit_mmap */ +#include <asm-generic/mm_hooks.h> + +#endif diff --git a/arch/hexagon/include/asm/module.h b/arch/hexagon/include/asm/module.h new file mode 100644 index 000000000000..72ba494e6d7d --- /dev/null +++ b/arch/hexagon/include/asm/module.h @@ -0,0 +1,26 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_MODULE_H +#define _ASM_MODULE_H + +#include <asm-generic/module.h> + +#define MODULE_ARCH_VERMAGIC __stringify(PROCESSOR_MODEL_NAME) " " + +#endif diff --git a/arch/hexagon/include/asm/mutex.h b/arch/hexagon/include/asm/mutex.h new file mode 100644 index 000000000000..58b52de1bc22 --- /dev/null +++ b/arch/hexagon/include/asm/mutex.h @@ -0,0 +1,8 @@ +/* + * Pull in the generic implementation for the mutex fastpath. + * + * TODO: implement optimized primitives instead, or leave the generic + * implementation in place, or pick the atomic_xchg() based generic + * implementation. (see asm-generic/mutex-xchg.h for details) + */ +#include <asm-generic/mutex-xchg.h> diff --git a/arch/hexagon/include/asm/page.h b/arch/hexagon/include/asm/page.h new file mode 100644 index 000000000000..edd97626c482 --- /dev/null +++ b/arch/hexagon/include/asm/page.h @@ -0,0 +1,157 @@ +/* + * Page management definitions for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_PAGE_H +#define _ASM_PAGE_H + +#include <linux/const.h> + +/* This is probably not the most graceful way to handle this. */ + +#ifdef CONFIG_PAGE_SIZE_4KB +#define PAGE_SHIFT 12 +#define HEXAGON_L1_PTE_SIZE __HVM_PDE_S_4KB +#endif + +#ifdef CONFIG_PAGE_SIZE_16KB +#define PAGE_SHIFT 14 +#define HEXAGON_L1_PTE_SIZE __HVM_PDE_S_16KB +#endif + +#ifdef CONFIG_PAGE_SIZE_64KB +#define PAGE_SHIFT 16 +#define HEXAGON_L1_PTE_SIZE __HVM_PDE_S_64KB +#endif + +#ifdef CONFIG_PAGE_SIZE_256KB +#define PAGE_SHIFT 18 +#define HEXAGON_L1_PTE_SIZE __HVM_PDE_S_256KB +#endif + +#ifdef CONFIG_PAGE_SIZE_1MB +#define PAGE_SHIFT 20 +#define HEXAGON_L1_PTE_SIZE __HVM_PDE_S_1MB +#endif + +/* + * These should be defined in hugetlb.h, but apparently not. + * "Huge" for us should be 4MB or 16MB, which are both represented + * in L1 PTE's. Right now, it's set up for 4MB. + */ +#ifdef CONFIG_HUGETLB_PAGE +#define HPAGE_SHIFT 22 +#define HPAGE_SIZE (1UL << HPAGE_SHIFT) +#define HPAGE_MASK (~(HPAGE_SIZE-1)) +#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT-PAGE_SHIFT) +#define HVM_HUGEPAGE_SIZE 0x5 +#endif + +#define PAGE_SIZE (1UL << PAGE_SHIFT) +#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1)) + +#ifdef __KERNEL__ +#ifndef __ASSEMBLY__ + +/* + * This is for PFN_DOWN, which mm.h needs. Seems the right place to pull it in. + */ +#include <linux/pfn.h> + +/* + * We implement a two-level architecture-specific page table structure. + * Null intermediate page table level (pmd, pud) definitions will come from + * asm-generic/pagetable-nopmd.h and asm-generic/pagetable-nopud.h + */ +typedef struct { unsigned long pte; } pte_t; +typedef struct { unsigned long pgd; } pgd_t; +typedef struct { unsigned long pgprot; } pgprot_t; +typedef struct page *pgtable_t; + +#define pte_val(x) ((x).pte) +#define pgd_val(x) ((x).pgd) +#define pgprot_val(x) ((x).pgprot) +#define __pte(x) ((pte_t) { (x) }) +#define __pgd(x) ((pgd_t) { (x) }) +#define __pgprot(x) ((pgprot_t) { (x) }) + +/* + * We need a __pa and a __va routine for kernel space. + * MIPS says they're only used during mem_init. + * also, check if we need a PHYS_OFFSET. + */ +#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET) +#define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET)) + +/* The "page frame" descriptor is defined in linux/mm.h */ +struct page; + +/* Returns page frame descriptor for virtual address. */ +#define virt_to_page(kaddr) pfn_to_page(PFN_DOWN(__pa(kaddr))) + +/* Default vm area behavior is non-executable. */ +#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) + +#define pfn_valid(pfn) ((pfn) < max_mapnr) +#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) + +/* Need to not use a define for linesize; may move this to another file. */ +static inline void clear_page(void *page) +{ + /* This can only be done on pages with L1 WB cache */ + asm volatile( + " loop0(1f,%1);\n" + "1: { dczeroa(%0);\n" + " %0 = add(%0,#32); }:endloop0\n" + : "+r" (page) + : "r" (PAGE_SIZE/32) + : "lc0", "sa0", "memory" + ); +} + +#define copy_page(to, from) memcpy((to), (from), PAGE_SIZE) + +/* + * Under assumption that kernel always "sees" user map... + */ +#define clear_user_page(page, vaddr, pg) clear_page(page) +#define copy_user_page(to, from, vaddr, pg) copy_page(to, from) + +/* + * page_to_phys - convert page to physical address + * @page - pointer to page entry in mem_map + */ +#define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) + +/* + * For port to Hexagon Virtual Machine, MAYBE we check for attempts + * to reference reserved HVM space, but in any case, the VM will be + * protected. + */ +#define kern_addr_valid(addr) (1) + +#include <asm-generic/memory_model.h> +/* XXX Todo: implement assembly-optimized version of getorder. */ +#include <asm-generic/getorder.h> + +#endif /* ifdef __ASSEMBLY__ */ +#endif /* ifdef __KERNEL__ */ + +#endif diff --git a/arch/arm/include/asm/sizes.h b/arch/hexagon/include/asm/param.h index 154b89b81d3e..285344bbd036 100644 --- a/arch/arm/include/asm/sizes.h +++ b/arch/hexagon/include/asm/param.h @@ -1,8 +1,9 @@ /* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of @@ -11,11 +12,15 @@ * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -/* Size definitions - * Copyright (C) ARM Limited 1998. All rights reserved. + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. */ -#include <asm-generic/sizes.h> -#define SZ_48M (SZ_32M + SZ_16M) +#ifndef _ASM_PARAM_H +#define _ASM_PARAM_H + +#define EXEC_PAGESIZE 16384 + +#include <asm-generic/param.h> + +#endif diff --git a/arch/hexagon/include/asm/perf_event.h b/arch/hexagon/include/asm/perf_event.h new file mode 100644 index 000000000000..6c2910f91180 --- /dev/null +++ b/arch/hexagon/include/asm/perf_event.h @@ -0,0 +1,24 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_PERF_EVENT_H +#define _ASM_PERF_EVENT_H + +#define PERF_EVENT_INDEX_OFFSET 0 + +#endif /* _ASM_PERF_EVENT_H */ diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h new file mode 100644 index 000000000000..13443c775131 --- /dev/null +++ b/arch/hexagon/include/asm/pgalloc.h @@ -0,0 +1,146 @@ +/* + * Page table support for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_PGALLOC_H +#define _ASM_PGALLOC_H + +#include <asm/mem-layout.h> +#include <asm/atomic.h> + +#define check_pgt_cache() do {} while (0) + +extern unsigned long long kmap_generation; + +/* + * Page table creation interface + */ +static inline pgd_t *pgd_alloc(struct mm_struct *mm) +{ + pgd_t *pgd; + + pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + + /* + * There may be better ways to do this, but to ensure + * that new address spaces always contain the kernel + * base mapping, and to ensure that the user area is + * initially marked invalid, initialize the new map + * map with a copy of the kernel's persistent map. + */ + + memcpy(pgd, swapper_pg_dir, PTRS_PER_PGD*sizeof(pgd_t *)); + mm->context.generation = kmap_generation; + + /* Physical version is what is passed to virtual machine on switch */ + mm->context.ptbase = __pa(pgd); + + return pgd; +} + +static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + free_page((unsigned long) pgd); +} + +static inline struct page *pte_alloc_one(struct mm_struct *mm, + unsigned long address) +{ + struct page *pte; + + pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); + + if (pte) + pgtable_page_ctor(pte); + + return pte; +} + +/* _kernel variant gets to use a different allocator */ +static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, + unsigned long address) +{ + gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO; + return (pte_t *) __get_free_page(flags); +} + +static inline void pte_free(struct mm_struct *mm, struct page *pte) +{ + pgtable_page_dtor(pte); + __free_page(pte); +} + +static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) +{ + free_page((unsigned long)pte); +} + +static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, + pgtable_t pte) +{ + /* + * Conveniently, zero in 3 LSB means indirect 4K page table. + * Not so convenient when you're trying to vary the page size. + */ + set_pmd(pmd, __pmd(((unsigned long)page_to_pfn(pte) << PAGE_SHIFT) | + HEXAGON_L1_PTE_SIZE)); +} + +/* + * Other architectures seem to have ways of making all processes + * share the same pmd's for their kernel mappings, but the v0.3 + * Hexagon VM spec has a "monolithic" L1 table for user and kernel + * segments. We track "generations" of the kernel map to minimize + * overhead, and update the "slave" copies of the kernel mappings + * as part of switch_mm. However, we still need to update the + * kernel map of the active thread who's calling pmd_populate_kernel... + */ +static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, + pte_t *pte) +{ + extern spinlock_t kmap_gen_lock; + pmd_t *ppmd; + int pmdindex; + + spin_lock(&kmap_gen_lock); + kmap_generation++; + mm->context.generation = kmap_generation; + current->active_mm->context.generation = kmap_generation; + spin_unlock(&kmap_gen_lock); + + set_pmd(pmd, __pmd(((unsigned long)__pa(pte)) | HEXAGON_L1_PTE_SIZE)); + + /* + * Now the "slave" copy of the current thread. + * This is pointer arithmetic, not byte addresses! + */ + pmdindex = (pgd_t *)pmd - mm->pgd; + ppmd = (pmd_t *)current->active_mm->pgd + pmdindex; + set_pmd(ppmd, __pmd(((unsigned long)__pa(pte)) | HEXAGON_L1_PTE_SIZE)); + if (pmdindex > max_kernel_seg) + max_kernel_seg = pmdindex; +} + +#define __pte_free_tlb(tlb, pte, addr) \ +do { \ + pgtable_page_dtor((pte)); \ + tlb_remove_page((tlb), (pte)); \ +} while (0) + +#endif diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h new file mode 100644 index 000000000000..ca619bf225ef --- /dev/null +++ b/arch/hexagon/include/asm/pgtable.h @@ -0,0 +1,518 @@ +/* + * Page table support for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_PGTABLE_H +#define _ASM_PGTABLE_H + +/* + * Page table definitions for Qualcomm Hexagon processor. + */ +#include <linux/swap.h> +#include <asm/page.h> +#include <asm-generic/pgtable-nopmd.h> + +/* A handy thing to have if one has the RAM. Declared in head.S */ +extern unsigned long empty_zero_page; +extern unsigned long zero_page_mask; + +/* + * The PTE model described here is that of the Hexagon Virtual Machine, + * which autonomously walks 2-level page tables. At a lower level, we + * also describe the RISCish software-loaded TLB entry structure of + * the underlying Hexagon processor. A kernel built to run on the + * virtual machine has no need to know about the underlying hardware. + */ +#include <asm/vm_mmu.h> + +/* + * To maximize the comfort level for the PTE manipulation macros, + * define the "well known" architecture-specific bits. + */ +#define _PAGE_READ __HVM_PTE_R +#define _PAGE_WRITE __HVM_PTE_W +#define _PAGE_EXECUTE __HVM_PTE_X +#define _PAGE_USER __HVM_PTE_U + +/* + * We have a total of 4 "soft" bits available in the abstract PTE. + * The two mandatory software bits are Dirty and Accessed. + * To make nonlinear swap work according to the more recent + * model, we want a low order "Present" bit to indicate whether + * the PTE describes MMU programming or swap space. + */ +#define _PAGE_PRESENT (1<<0) +#define _PAGE_DIRTY (1<<1) +#define _PAGE_ACCESSED (1<<2) + +/* + * _PAGE_FILE is only meaningful if _PAGE_PRESENT is false, while + * _PAGE_DIRTY is only meaningful if _PAGE_PRESENT is true. + * So we can overload the bit... + */ +#define _PAGE_FILE _PAGE_DIRTY /* set: pagecache, unset = swap */ + +/* + * For now, let's say that Valid and Present are the same thing. + * Alternatively, we could say that it's the "or" of R, W, and X + * permissions. + */ +#define _PAGE_VALID _PAGE_PRESENT + +/* + * We're not defining _PAGE_GLOBAL here, since there's no concept + * of global pages or ASIDs exposed to the Hexagon Virtual Machine, + * and we want to use the same page table structures and macros in + * the native kernel as we do in the virtual machine kernel. + * So we'll put up with a bit of inefficiency for now... + */ + +/* + * Top "FOURTH" level (pgd), which for the Hexagon VM is really + * only the second from the bottom, pgd and pud both being collapsed. + * Each entry represents 4MB of virtual address space, 4K of table + * thus maps the full 4GB. + */ +#define PGDIR_SHIFT 22 +#define PTRS_PER_PGD 1024 + +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +#ifdef CONFIG_PAGE_SIZE_4KB +#define PTRS_PER_PTE 1024 +#endif + +#ifdef CONFIG_PAGE_SIZE_16KB +#define PTRS_PER_PTE 256 +#endif + +#ifdef CONFIG_PAGE_SIZE_64KB +#define PTRS_PER_PTE 64 +#endif + +#ifdef CONFIG_PAGE_SIZE_256KB +#define PTRS_PER_PTE 16 +#endif + +#ifdef CONFIG_PAGE_SIZE_1MB +#define PTRS_PER_PTE 4 +#endif + +/* Any bigger and the PTE disappears. */ +#define pgd_ERROR(e) \ + printk(KERN_ERR "%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__,\ + pgd_val(e)) + +/* + * Page Protection Constants. Includes (in this variant) cache attributes. + */ +extern unsigned long _dflt_cache_att; + +#define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_USER | \ + _dflt_cache_att) +#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | \ + _PAGE_READ | _PAGE_EXECUTE | _dflt_cache_att) +#define PAGE_COPY PAGE_READONLY +#define PAGE_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | \ + _PAGE_READ | _PAGE_EXECUTE | _dflt_cache_att) +#define PAGE_COPY_EXEC PAGE_EXEC +#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | \ + _PAGE_EXECUTE | _PAGE_WRITE | _dflt_cache_att) +#define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_READ | \ + _PAGE_WRITE | _PAGE_EXECUTE | _dflt_cache_att) + + +/* + * Aliases for mapping mmap() protection bits to page protections. + * These get used for static initialization, so using the _dflt_cache_att + * variable for the default cache attribute isn't workable. If the + * default gets changed at boot time, the boot option code has to + * update data structures like the protaction_map[] array. + */ +#define CACHEDEF (CACHE_DEFAULT << 6) + +/* Private (copy-on-write) page protections. */ +#define __P000 __pgprot(_PAGE_PRESENT | _PAGE_USER | CACHEDEF) +#define __P001 __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | CACHEDEF) +#define __P010 __P000 /* Write-only copy-on-write */ +#define __P011 __P001 /* Read/Write copy-on-write */ +#define __P100 __pgprot(_PAGE_PRESENT | _PAGE_USER | \ + _PAGE_EXECUTE | CACHEDEF) +#define __P101 __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_EXECUTE | \ + _PAGE_READ | CACHEDEF) +#define __P110 __P100 /* Write/execute copy-on-write */ +#define __P111 __P101 /* Read/Write/Execute, copy-on-write */ + +/* Shared page protections. */ +#define __S000 __P000 +#define __S001 __P001 +#define __S010 __pgprot(_PAGE_PRESENT | _PAGE_USER | \ + _PAGE_WRITE | CACHEDEF) +#define __S011 __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | \ + _PAGE_WRITE | CACHEDEF) +#define __S100 __pgprot(_PAGE_PRESENT | _PAGE_USER | \ + _PAGE_EXECUTE | CACHEDEF) +#define __S101 __P101 +#define __S110 __pgprot(_PAGE_PRESENT | _PAGE_USER | \ + _PAGE_EXECUTE | _PAGE_WRITE | CACHEDEF) +#define __S111 __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | \ + _PAGE_EXECUTE | _PAGE_WRITE | CACHEDEF) + +extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; /* located in head.S */ + +/* Seems to be zero even in architectures where the zero page is firewalled? */ +#define FIRST_USER_ADDRESS 0 +#define pte_special(pte) 0 +#define pte_mkspecial(pte) (pte) + +/* HUGETLB not working currently */ +#ifdef CONFIG_HUGETLB_PAGE +#define pte_mkhuge(pte) __pte((pte_val(pte) & ~0x3) | HVM_HUGEPAGE_SIZE) +#endif + +/* + * For now, assume that higher-level code will do TLB/MMU invalidations + * and don't insert that overhead into this low-level function. + */ +extern void sync_icache_dcache(pte_t pte); + +#define pte_present_exec_user(pte) \ + ((pte_val(pte) & (_PAGE_EXECUTE | _PAGE_USER)) == \ + (_PAGE_EXECUTE | _PAGE_USER)) + +static inline void set_pte(pte_t *ptep, pte_t pteval) +{ + /* should really be using pte_exec, if it weren't declared later. */ + if (pte_present_exec_user(pteval)) + sync_icache_dcache(pteval); + + *ptep = pteval; +} + +/* + * For the Hexagon Virtual Machine MMU (or its emulation), a null/invalid + * L1 PTE (PMD/PGD) has 7 in the least significant bits. For the L2 PTE + * (Linux PTE), the key is to have bits 11..9 all zero. We'd use 0x7 + * as a universal null entry, but some of those least significant bits + * are interpreted by software. + */ +#define _NULL_PMD 0x7 +#define _NULL_PTE 0x0 + +static inline void pmd_clear(pmd_t *pmd_entry_ptr) +{ + pmd_val(*pmd_entry_ptr) = _NULL_PMD; +} + +/* + * Conveniently, a null PTE value is invalid. + */ +static inline void pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_val(*ptep) = _NULL_PTE; +} + +#ifdef NEED_PMD_INDEX_DESPITE_BEING_2_LEVEL +/** + * pmd_index - returns the index of the entry in the PMD page + * which would control the given virtual address + */ +#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) + +#endif + +/** + * pgd_index - returns the index of the entry in the PGD page + * which would control the given virtual address + * + * This returns the *index* for the address in the pgd_t + */ +#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1)) + +/* + * pgd_offset - find an offset in a page-table-directory + */ +#define pgd_offset(mm, addr) ((mm)->pgd + pgd_index(addr)) + +/* + * pgd_offset_k - get kernel (init_mm) pgd entry pointer for addr + */ +#define pgd_offset_k(address) pgd_offset(&init_mm, address) + +/** + * pmd_none - check if pmd_entry is mapped + * @pmd_entry: pmd entry + * + * MIPS checks it against that "invalid pte table" thing. + */ +static inline int pmd_none(pmd_t pmd) +{ + return pmd_val(pmd) == _NULL_PMD; +} + +/** + * pmd_present - is there a page table behind this? + * Essentially the inverse of pmd_none. We maybe + * save an inline instruction by defining it this + * way, instead of simply "!pmd_none". + */ +static inline int pmd_present(pmd_t pmd) +{ + return pmd_val(pmd) != (unsigned long)_NULL_PMD; +} + +/** + * pmd_bad - check if a PMD entry is "bad". That might mean swapped out. + * As we have no known cause of badness, it's null, as it is for many + * architectures. + */ +static inline int pmd_bad(pmd_t pmd) +{ + return 0; +} + +/* + * pmd_page - converts a PMD entry to a page pointer + */ +#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)) +#define pmd_pgtable(pmd) pmd_page(pmd) + +/** + * pte_none - check if pte is mapped + * @pte: pte_t entry + */ +static inline int pte_none(pte_t pte) +{ + return pte_val(pte) == _NULL_PTE; +}; + +/* + * pte_present - check if page is present + */ +static inline int pte_present(pte_t pte) +{ + return pte_val(pte) & _PAGE_PRESENT; +} + +/* mk_pte - make a PTE out of a page pointer and protection bits */ +#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) + +/* pte_page - returns a page (frame pointer/descriptor?) based on a PTE */ +#define pte_page(x) pfn_to_page(pte_pfn(x)) + +/* pte_mkold - mark PTE as not recently accessed */ +static inline pte_t pte_mkold(pte_t pte) +{ + pte_val(pte) &= ~_PAGE_ACCESSED; + return pte; +} + +/* pte_mkyoung - mark PTE as recently accessed */ +static inline pte_t pte_mkyoung(pte_t pte) +{ + pte_val(pte) |= _PAGE_ACCESSED; + return pte; +} + +/* pte_mkclean - mark page as in sync with backing store */ +static inline pte_t pte_mkclean(pte_t pte) +{ + pte_val(pte) &= ~_PAGE_DIRTY; + return pte; +} + +/* pte_mkdirty - mark page as modified */ +static inline pte_t pte_mkdirty(pte_t pte) +{ + pte_val(pte) |= _PAGE_DIRTY; + return pte; +} + +/* pte_young - "is PTE marked as accessed"? */ +static inline int pte_young(pte_t pte) +{ + return pte_val(pte) & _PAGE_ACCESSED; +} + +/* pte_dirty - "is PTE dirty?" */ +static inline int pte_dirty(pte_t pte) +{ + return pte_val(pte) & _PAGE_DIRTY; +} + +/* pte_modify - set protection bits on PTE */ +static inline pte_t pte_modify(pte_t pte, pgprot_t prot) +{ + pte_val(pte) &= PAGE_MASK; + pte_val(pte) |= pgprot_val(prot); + return pte; +} + +/* pte_wrprotect - mark page as not writable */ +static inline pte_t pte_wrprotect(pte_t pte) +{ + pte_val(pte) &= ~_PAGE_WRITE; + return pte; +} + +/* pte_mkwrite - mark page as writable */ +static inline pte_t pte_mkwrite(pte_t pte) +{ + pte_val(pte) |= _PAGE_WRITE; + return pte; +} + +/* pte_mkexec - mark PTE as executable */ +static inline pte_t pte_mkexec(pte_t pte) +{ + pte_val(pte) |= _PAGE_EXECUTE; + return pte; +} + +/* pte_read - "is PTE marked as readable?" */ +static inline int pte_read(pte_t pte) +{ + return pte_val(pte) & _PAGE_READ; +} + +/* pte_write - "is PTE marked as writable?" */ +static inline int pte_write(pte_t pte) +{ + return pte_val(pte) & _PAGE_WRITE; +} + + +/* pte_exec - "is PTE marked as executable?" */ +static inline int pte_exec(pte_t pte) +{ + return pte_val(pte) & _PAGE_EXECUTE; +} + +/* __pte_to_swp_entry - extract swap entry from PTE */ +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) + +/* __swp_entry_to_pte - extract PTE from swap entry */ +#define __swp_entry_to_pte(x) ((pte_t) { (x).val }) + +/* pfn_pte - convert page number and protection value to page table entry */ +#define pfn_pte(pfn, pgprot) __pte((pfn << PAGE_SHIFT) | pgprot_val(pgprot)) + +/* pte_pfn - convert pte to page frame number */ +#define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) +#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval)) + +/* + * set_pte_at - update page table and do whatever magic may be + * necessary to make the underlying hardware/firmware take note. + * + * VM may require a virtual instruction to alert the MMU. + */ +#define set_pte_at(mm, addr, ptep, pte) set_pte(ptep, pte) + +/* + * May need to invoke the virtual machine as well... + */ +#define pte_unmap(pte) do { } while (0) +#define pte_unmap_nested(pte) do { } while (0) + +/* + * pte_offset_map - returns the linear address of the page table entry + * corresponding to an address + */ +#define pte_offset_map(dir, address) \ + ((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset(address)) + +#define pte_offset_map_nested(pmd, addr) pte_offset_map(pmd, addr) + +/* pte_offset_kernel - kernel version of pte_offset */ +#define pte_offset_kernel(dir, address) \ + ((pte_t *) (unsigned long) __va(pmd_val(*dir) & PAGE_MASK) \ + + __pte_offset(address)) + +/* ZERO_PAGE - returns the globally shared zero page */ +#define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page)) + +#define __pte_offset(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + +/* Nothing special about IO remapping at this point */ +#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ + remap_pfn_range(vma, vaddr, pfn, size, prot) + +/* I think this is in case we have page table caches; needed by init/main.c */ +#define pgtable_cache_init() do { } while (0) + +/* + * Swap/file PTE definitions. If _PAGE_PRESENT is zero, the rest of the + * PTE is interpreted as swap information. Depending on the _PAGE_FILE + * bit, the remaining free bits are eitehr interpreted as a file offset + * or a swap type/offset tuple. Rather than have the TLB fill handler + * test _PAGE_PRESENT, we're going to reserve the permissions bits + * and set them to all zeros for swap entries, which speeds up the + * miss handler at the cost of 3 bits of offset. That trade-off can + * be revisited if necessary, but Hexagon processor architecture and + * target applications suggest a lot of TLB misses and not much swap space. + * + * Format of swap PTE: + * bit 0: Present (zero) + * bit 1: _PAGE_FILE (zero) + * bits 2-6: swap type (arch independent layer uses 5 bits max) + * bits 7-9: bits 2:0 of offset + * bits 10-12: effectively _PAGE_PROTNONE (all zero) + * bits 13-31: bits 21:3 of swap offset + * + * Format of file PTE: + * bit 0: Present (zero) + * bit 1: _PAGE_FILE (zero) + * bits 2-9: bits 7:0 of offset + * bits 10-12: effectively _PAGE_PROTNONE (all zero) + * bits 13-31: bits 26:8 of swap offset + * + * The split offset makes some of the following macros a little gnarly, + * but there's plenty of precedent for this sort of thing. + */ +#define PTE_FILE_MAX_BITS 27 + +/* Used for swap PTEs */ +#define __swp_type(swp_pte) (((swp_pte).val >> 2) & 0x1f) + +#define __swp_offset(swp_pte) \ + ((((swp_pte).val >> 7) & 0x7) | (((swp_pte).val >> 10) & 0x003ffff8)) + +#define __swp_entry(type, offset) \ + ((swp_entry_t) { \ + ((type << 2) | \ + ((offset & 0x3ffff8) << 10) | ((offset & 0x7) << 7)) }) + +/* Used for file PTEs */ +#define pte_file(pte) \ + ((pte_val(pte) & (_PAGE_FILE | _PAGE_PRESENT)) == _PAGE_FILE) + +#define pte_to_pgoff(pte) \ + (((pte_val(pte) >> 2) & 0xff) | ((pte_val(pte) >> 5) & 0x07ffff00)) + +#define pgoff_to_pte(off) \ + ((pte_t) { ((((off) & 0x7ffff00) << 5) | (((off) & 0xff) << 2)\ + | _PAGE_FILE) }) + +/* Oh boy. There are a lot of possible arch overrides found in this file. */ +#include <asm-generic/pgtable.h> + +#endif diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h new file mode 100644 index 000000000000..20c5ddabbd8b --- /dev/null +++ b/arch/hexagon/include/asm/processor.h @@ -0,0 +1,123 @@ +/* + * Process/processor support for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_PROCESSOR_H +#define _ASM_PROCESSOR_H + +#ifndef __ASSEMBLY__ + +#include <asm/mem-layout.h> +#include <asm/registers.h> +#include <asm/hexagon_vm.h> + +/* must be a macro */ +#define current_text_addr() ({ __label__ _l; _l: &&_l; }) + +/* task_struct, defined elsewhere, is the "process descriptor" */ +struct task_struct; + +/* this is defined in arch/process.c */ +extern pid_t kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); +extern unsigned long thread_saved_pc(struct task_struct *tsk); + +extern void start_thread(struct pt_regs *, unsigned long, unsigned long); + +/* + * thread_struct is supposed to be for context switch data. + * Specifically, to hold the state necessary to perform switch_to... + */ +struct thread_struct { + void *switch_sp; +}; + +/* + * initializes thread_struct + * The only thing we have in there is switch_sp + * which doesn't really need to be initialized. + */ + +#define INIT_THREAD { \ +} + +#define cpu_relax() __vmyield() + +/* + * "Unlazying all lazy status" occurs here. + */ +static inline void prepare_to_copy(struct task_struct *tsk) +{ +} + +/* + * Decides where the kernel will search for a free chunk of vm space during + * mmaps. + * See also arch_get_unmapped_area. + * Doesn't affect if you have MAX_FIXED in the page flags set though... + * + * Apparently the convention is that ld.so will ask for "unmapped" private + * memory to be allocated SOMEWHERE, but it also asks for memory explicitly + * via MAP_FIXED at the lower * addresses starting at VA=0x0. + * + * If the two requests collide, you get authentic segfaulting action, so + * you have to kick the "unmapped" base requests higher up. + */ +#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE/3)) + + +#define task_pt_regs(task) \ + ((struct pt_regs *)(task_stack_page(task) + THREAD_SIZE) - 1) + +#define KSTK_EIP(tsk) (pt_elr(task_pt_regs(tsk))) +#define KSTK_ESP(tsk) (pt_psp(task_pt_regs(tsk))) + +/* Free all resources held by a thread; defined in process.c */ +extern void release_thread(struct task_struct *dead_task); + +/* Get wait channel for task P. */ +extern unsigned long get_wchan(struct task_struct *p); + +/* The following stuff is pretty HEXAGON specific. */ + +/* This is really just here for __switch_to. + Offsets are pulled via asm-offsets.c */ + +/* + * No real reason why VM and native switch stacks should be different. + * Ultimately this should merge. Note that Rev C. ABI called out only + * R24-27 as callee saved GPRs needing explicit attention (R29-31 being + * dealt with automagically by allocframe), but the current ABI has + * more, R16-R27. By saving more, the worst case is that we waste some + * cycles if building with the old compilers. + */ + +struct hexagon_switch_stack { + unsigned long long r1716; + unsigned long long r1918; + unsigned long long r2120; + unsigned long long r2322; + unsigned long long r2524; + unsigned long long r2726; + unsigned long fp; + unsigned long lr; +}; + +#endif /* !__ASSEMBLY__ */ + +#endif diff --git a/arch/hexagon/include/asm/ptrace.h b/arch/hexagon/include/asm/ptrace.h new file mode 100644 index 000000000000..3d2f607cd63c --- /dev/null +++ b/arch/hexagon/include/asm/ptrace.h @@ -0,0 +1,35 @@ +/* + * Ptrace definitions for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_PTRACE_H +#define _ASM_PTRACE_H + +#include <asm/registers.h> + +#define instruction_pointer(regs) pt_elr(regs) +#define user_stack_pointer(regs) ((regs)->r29) + +#define profile_pc(regs) instruction_pointer(regs) + +/* kprobe-based event tracer support */ +extern int regs_query_register_offset(const char *name); +extern const char *regs_query_register_name(unsigned int offset); + +#endif diff --git a/arch/hexagon/include/asm/registers.h b/arch/hexagon/include/asm/registers.h new file mode 100644 index 000000000000..4dd741be855d --- /dev/null +++ b/arch/hexagon/include/asm/registers.h @@ -0,0 +1,236 @@ +/* + * Register definitions for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_REGISTERS_H +#define _ASM_REGISTERS_H + +#define SP r29 + +#ifndef __ASSEMBLY__ + +/* See kernel/entry.S for further documentation. */ + +/* + * Entry code copies the event record out of guest registers into + * this structure (which is on the stack). + */ + +struct hvm_event_record { + unsigned long vmel; /* Event Linkage (return address) */ + unsigned long vmest; /* Event context - pre-event SSR values */ + unsigned long vmpsp; /* Previous stack pointer */ + unsigned long vmbadva; /* Bad virtual address for addressing events */ +}; + +struct pt_regs { + long restart_r0; /* R0 checkpoint for syscall restart */ + long syscall_nr; /* Only used in system calls */ + union { + struct { + unsigned long usr; + unsigned long preds; + }; + long long int predsusr; + }; + union { + struct { + unsigned long m0; + unsigned long m1; + }; + long long int m1m0; + }; + union { + struct { + unsigned long sa1; + unsigned long lc1; + }; + long long int lc1sa1; + }; + union { + struct { + unsigned long sa0; + unsigned long lc0; + }; + long long int lc0sa0; + }; + union { + struct { + unsigned long gp; + unsigned long ugp; + }; + long long int ugpgp; + }; + /* + * Be extremely careful with rearranging these, if at all. Some code + * assumes the 32 registers exist exactly like this in memory; + * e.g. kernel/ptrace.c + * e.g. kernel/signal.c (restore_sigcontext) + */ + union { + struct { + unsigned long r00; + unsigned long r01; + }; + long long int r0100; + }; + union { + struct { + unsigned long r02; + unsigned long r03; + }; + long long int r0302; + }; + union { + struct { + unsigned long r04; + unsigned long r05; + }; + long long int r0504; + }; + union { + struct { + unsigned long r06; + unsigned long r07; + }; + long long int r0706; + }; + union { + struct { + unsigned long r08; + unsigned long r09; + }; + long long int r0908; + }; + union { + struct { + unsigned long r10; + unsigned long r11; + }; + long long int r1110; + }; + union { + struct { + unsigned long r12; + unsigned long r13; + }; + long long int r1312; + }; + union { + struct { + unsigned long r14; + unsigned long r15; + }; + long long int r1514; + }; + union { + struct { + unsigned long r16; + unsigned long r17; + }; + long long int r1716; + }; + union { + struct { + unsigned long r18; + unsigned long r19; + }; + long long int r1918; + }; + union { + struct { + unsigned long r20; + unsigned long r21; + }; + long long int r2120; + }; + union { + struct { + unsigned long r22; + unsigned long r23; + }; + long long int r2322; + }; + union { + struct { + unsigned long r24; + unsigned long r25; + }; + long long int r2524; + }; + union { + struct { + unsigned long r26; + unsigned long r27; + }; + long long int r2726; + }; + union { + struct { + unsigned long r28; + unsigned long r29; + }; + long long int r2928; + }; + union { + struct { + unsigned long r30; + unsigned long r31; + }; + long long int r3130; + }; + /* VM dispatch pushes event record onto stack - we can build on it */ + struct hvm_event_record hvmer; +}; + +/* Defines to conveniently access the values */ + +/* + * As of the VM spec 0.5, these registers are now set/retrieved via a + * VM call. On the in-bound side, we just fetch the values + * at the entry points and stuff them into the old record in pt_regs. + * However, on the outbound side, probably at VM rte, we set the + * registers back. + */ + +#define pt_elr(regs) ((regs)->hvmer.vmel) +#define pt_set_elr(regs, val) ((regs)->hvmer.vmel = (val)) +#define pt_cause(regs) ((regs)->hvmer.vmest & (HVM_VMEST_CAUSE_MSK)) +#define user_mode(regs) \ + (((regs)->hvmer.vmest & (HVM_VMEST_UM_MSK << HVM_VMEST_UM_SFT)) != 0) +#define ints_enabled(regs) \ + (((regs)->hvmer.vmest & (HVM_VMEST_IE_MSK << HVM_VMEST_IE_SFT)) != 0) +#define pt_psp(regs) ((regs)->hvmer.vmpsp) +#define pt_badva(regs) ((regs)->hvmer.vmbadva) + +#define pt_set_rte_sp(regs, sp) do {\ + pt_psp(regs) = (sp);\ + (regs)->SP = (unsigned long) &((regs)->hvmer);\ + } while (0) + +#define pt_set_kmode(regs) \ + (regs)->hvmer.vmest = (HVM_VMEST_IE_MSK << HVM_VMEST_IE_SFT) + +#define pt_set_usermode(regs) \ + (regs)->hvmer.vmest = (HVM_VMEST_UM_MSK << HVM_VMEST_UM_SFT) \ + | (HVM_VMEST_IE_MSK << HVM_VMEST_IE_SFT) + +#endif /* ifndef __ASSEMBLY */ + +#endif diff --git a/arch/hexagon/include/asm/setup.h b/arch/hexagon/include/asm/setup.h new file mode 100644 index 000000000000..3b754c50bc0a --- /dev/null +++ b/arch/hexagon/include/asm/setup.h @@ -0,0 +1,29 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_SETUP_H +#define _ASM_SETUP_H + +#include <linux/init.h> +#include <asm-generic/setup.h> + +extern char external_cmdline_buffer; + +void __init setup_arch_memory(void); + +#endif diff --git a/arch/hexagon/include/asm/sigcontext.h b/arch/hexagon/include/asm/sigcontext.h new file mode 100644 index 000000000000..ce6dcd995220 --- /dev/null +++ b/arch/hexagon/include/asm/sigcontext.h @@ -0,0 +1,33 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_SIGCONTEXT_H +#define _ASM_SIGCONTEXT_H + +#include <asm/user.h> + +/* + * Signal context structure - contains all info to do with the state + * before the signal handler was invoked. Note: only add new entries + * to the end of the structure. + */ +struct sigcontext { + struct user_regs_struct sc_regs; +} __aligned(8); + +#endif diff --git a/arch/hexagon/include/asm/signal.h b/arch/hexagon/include/asm/signal.h new file mode 100644 index 000000000000..471c0562e17b --- /dev/null +++ b/arch/hexagon/include/asm/signal.h @@ -0,0 +1,26 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_SIGNAL_H +#define _ASM_SIGNAL_H + +extern unsigned long __rt_sigtramp_template[2]; + +#include <asm-generic/signal.h> + +#endif diff --git a/arch/hexagon/include/asm/smp.h b/arch/hexagon/include/asm/smp.h new file mode 100644 index 000000000000..87c869a6a897 --- /dev/null +++ b/arch/hexagon/include/asm/smp.h @@ -0,0 +1,44 @@ +/* + * SMP definitions for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef __ASM_SMP_H +#define __ASM_SMP_H + +#include <linux/cpumask.h> + +#define raw_smp_processor_id() (current_thread_info()->cpu) + +enum ipi_message_type { + IPI_NOP = 0, + IPI_RESCHEDULE = 1, + IPI_CALL_FUNC, + IPI_CALL_FUNC_SINGLE, + IPI_CPU_STOP, + IPI_TIMER, +}; + +extern void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg); +extern void smp_start_cpus(void); +extern void arch_send_call_function_single_ipi(int cpu); +extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); + +extern void smp_vm_unmask_irq(void *info); + +#endif diff --git a/arch/hexagon/include/asm/spinlock.h b/arch/hexagon/include/asm/spinlock.h new file mode 100644 index 000000000000..168a920485a8 --- /dev/null +++ b/arch/hexagon/include/asm/spinlock.h @@ -0,0 +1,186 @@ +/* + * Spinlock support for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_SPINLOCK_H +#define _ASM_SPINLOCK_H + +#include <asm/irqflags.h> + +/* + * This file is pulled in for SMP builds. + * Really need to check all the barrier stuff for "true" SMP + */ + +/* + * Read locks: + * - load the lock value + * - increment it + * - if the lock value is still negative, go back and try again. + * - unsuccessful store is unsuccessful. Go back and try again. Loser. + * - successful store new lock value if positive -> lock acquired + */ +static inline void arch_read_lock(arch_rwlock_t *lock) +{ + __asm__ __volatile__( + "1: R6 = memw_locked(%0);\n" + " { P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n" + " { if !P3 jump 1b; }\n" + " memw_locked(%0,P3) = R6;\n" + " { if !P3 jump 1b; }\n" + : + : "r" (&lock->lock) + : "memory", "r6", "p3" + ); + +} + +static inline void arch_read_unlock(arch_rwlock_t *lock) +{ + __asm__ __volatile__( + "1: R6 = memw_locked(%0);\n" + " R6 = add(R6,#-1);\n" + " memw_locked(%0,P3) = R6\n" + " if !P3 jump 1b;\n" + : + : "r" (&lock->lock) + : "memory", "r6", "p3" + ); + +} + +/* I think this returns 0 on fail, 1 on success. */ +static inline int arch_read_trylock(arch_rwlock_t *lock) +{ + int temp; + __asm__ __volatile__( + " R6 = memw_locked(%1);\n" + " { %0 = #0; P3 = cmp.ge(R6,#0); R6 = add(R6,#1);}\n" + " { if !P3 jump 1f; }\n" + " memw_locked(%1,P3) = R6;\n" + " { %0 = P3 }\n" + "1:\n" + : "=&r" (temp) + : "r" (&lock->lock) + : "memory", "r6", "p3" + ); + return temp; +} + +static inline int arch_read_can_lock(arch_rwlock_t *rwlock) +{ + return rwlock->lock == 0; +} + +static inline int arch_write_can_lock(arch_rwlock_t *rwlock) +{ + return rwlock->lock == 0; +} + +/* Stuffs a -1 in the lock value? */ +static inline void arch_write_lock(arch_rwlock_t *lock) +{ + __asm__ __volatile__( + "1: R6 = memw_locked(%0)\n" + " { P3 = cmp.eq(R6,#0); R6 = #-1;}\n" + " { if !P3 jump 1b; }\n" + " memw_locked(%0,P3) = R6;\n" + " { if !P3 jump 1b; }\n" + : + : "r" (&lock->lock) + : "memory", "r6", "p3" + ); +} + + +static inline int arch_write_trylock(arch_rwlock_t *lock) +{ + int temp; + __asm__ __volatile__( + " R6 = memw_locked(%1)\n" + " { %0 = #0; P3 = cmp.eq(R6,#0); R6 = #-1;}\n" + " { if !P3 jump 1f; }\n" + " memw_locked(%1,P3) = R6;\n" + " %0 = P3;\n" + "1:\n" + : "=&r" (temp) + : "r" (&lock->lock) + : "memory", "r6", "p3" + ); + return temp; + +} + +static inline void arch_write_unlock(arch_rwlock_t *lock) +{ + smp_mb(); + lock->lock = 0; +} + +static inline void arch_spin_lock(arch_spinlock_t *lock) +{ + __asm__ __volatile__( + "1: R6 = memw_locked(%0);\n" + " P3 = cmp.eq(R6,#0);\n" + " { if !P3 jump 1b; R6 = #1; }\n" + " memw_locked(%0,P3) = R6;\n" + " { if !P3 jump 1b; }\n" + : + : "r" (&lock->lock) + : "memory", "r6", "p3" + ); + +} + +static inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + smp_mb(); + lock->lock = 0; +} + +static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock) +{ + int temp; + __asm__ __volatile__( + " R6 = memw_locked(%1);\n" + " P3 = cmp.eq(R6,#0);\n" + " { if !P3 jump 1f; R6 = #1; %0 = #0; }\n" + " memw_locked(%1,P3) = R6;\n" + " %0 = P3;\n" + "1:\n" + : "=&r" (temp) + : "r" (&lock->lock) + : "memory", "r6", "p3" + ); + return temp; +} + +/* + * SMP spinlocks are intended to allow only a single CPU at the lock + */ +#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) +#define arch_spin_unlock_wait(lock) \ + do {while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) +#define arch_spin_is_locked(x) ((x)->lock != 0) + +#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) +#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) + +#endif diff --git a/arch/hexagon/include/asm/spinlock_types.h b/arch/hexagon/include/asm/spinlock_types.h new file mode 100644 index 000000000000..5e937af1c4ad --- /dev/null +++ b/arch/hexagon/include/asm/spinlock_types.h @@ -0,0 +1,42 @@ +/* + * Spinlock support for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_SPINLOCK_TYPES_H +#define _ASM_SPINLOCK_TYPES_H + +#include <linux/version.h> + +#ifndef __LINUX_SPINLOCK_TYPES_H +# error "please don't include this file directly" +#endif + +typedef struct { + volatile unsigned int lock; +} arch_spinlock_t; + +#define __ARCH_SPIN_LOCK_UNLOCKED { 0 } + +typedef struct { + volatile unsigned int lock; +} arch_rwlock_t; + +#define __ARCH_RW_LOCK_UNLOCKED { 0 } + +#endif diff --git a/arch/hexagon/include/asm/string.h b/arch/hexagon/include/asm/string.h new file mode 100644 index 000000000000..f4489c15942c --- /dev/null +++ b/arch/hexagon/include/asm/string.h @@ -0,0 +1,32 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_STRING_H_ +#define _ASM_STRING_H_ + +#ifdef __KERNEL__ +#define __HAVE_ARCH_MEMCPY +extern void *memcpy(void *__to, __const__ void *__from, size_t __n); + +/* ToDo: use dczeroa, accelerate the compiler-constant zero case */ +#define __HAVE_ARCH_MEMSET +extern void *memset(void *__to, int c, size_t __n); +#endif + + +#endif /* _ASM_STRING_H_ */ diff --git a/arch/hexagon/include/asm/suspend.h b/arch/hexagon/include/asm/suspend.h new file mode 100644 index 000000000000..089dd8268791 --- /dev/null +++ b/arch/hexagon/include/asm/suspend.h @@ -0,0 +1,27 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_SUSPEND_H +#define _ASM_SUSPEND_H + +static inline int arch_prepare_suspend(void) +{ + return 0; +} + +#endif diff --git a/arch/hexagon/include/asm/swab.h b/arch/hexagon/include/asm/swab.h new file mode 100644 index 000000000000..99cf0be3fb83 --- /dev/null +++ b/arch/hexagon/include/asm/swab.h @@ -0,0 +1,24 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_SWAB_H +#define _ASM_SWAB_H + +#define __SWAB_64_THRU_32__ + +#endif diff --git a/arch/hexagon/include/asm/syscall.h b/arch/hexagon/include/asm/syscall.h new file mode 100644 index 000000000000..3e7d61d38d97 --- /dev/null +++ b/arch/hexagon/include/asm/syscall.h @@ -0,0 +1,54 @@ +/* + * Syscall support for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_HEXAGON_SYSCALL_H +#define _ASM_HEXAGON_SYSCALL_H + +typedef long (*syscall_fn)(unsigned long, unsigned long, + unsigned long, unsigned long, + unsigned long, unsigned long); + +asmlinkage int sys_execve(char __user *ufilename, char __user * __user *argv, + char __user * __user *envp); +asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp, + unsigned long parent_tidp, unsigned long child_tidp); + +#define sys_execve sys_execve +#define sys_clone sys_clone + +#include <asm-generic/syscalls.h> + +extern void *sys_call_table[]; + +static inline long syscall_get_nr(struct task_struct *task, + struct pt_regs *regs) +{ + return regs->r06; +} + +static inline void syscall_get_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned int i, unsigned int n, + unsigned long *args) +{ + BUG_ON(i + n > 6); + memcpy(args, &(®s->r00)[i], n * sizeof(args[0])); +} +#endif diff --git a/arch/hexagon/include/asm/system.h b/arch/hexagon/include/asm/system.h new file mode 100644 index 000000000000..323ed1dd65e2 --- /dev/null +++ b/arch/hexagon/include/asm/system.h @@ -0,0 +1,126 @@ +/* + * System level definitions for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_SYSTEM_H +#define _ASM_SYSTEM_H + +#include <linux/linkage.h> +#include <linux/irqflags.h> +#include <asm/atomic.h> +#include <asm/hexagon_vm.h> + +struct thread_struct; + +extern struct task_struct *__switch_to(struct task_struct *, + struct task_struct *, + struct task_struct *); + +#define switch_to(p, n, r) do {\ + r = __switch_to((p), (n), (r));\ +} while (0) + + +#define rmb() barrier() +#define read_barrier_depends() barrier() +#define wmb() barrier() +#define mb() barrier() +#define smp_rmb() barrier() +#define smp_read_barrier_depends() barrier() +#define smp_wmb() barrier() +#define smp_mb() barrier() +#define smp_mb__before_atomic_dec() barrier() +#define smp_mb__after_atomic_dec() barrier() +#define smp_mb__before_atomic_inc() barrier() +#define smp_mb__after_atomic_inc() barrier() + +/* + * __xchg - atomically exchange a register and a memory location + * @x: value to swap + * @ptr: pointer to memory + * @size: size of the value + * + * Only 4 bytes supported currently. + * + * Note: there was an errata for V2 about .new's and memw_locked. + * + */ +static inline unsigned long __xchg(unsigned long x, volatile void *ptr, + int size) +{ + unsigned long retval; + + /* Can't seem to use printk or panic here, so just stop */ + if (size != 4) do { asm volatile("brkpt;\n"); } while (1); + + __asm__ __volatile__ ( + "1: %0 = memw_locked(%1);\n" /* load into retval */ + " memw_locked(%1,P0) = %2;\n" /* store into memory */ + " if !P0 jump 1b;\n" + : "=&r" (retval) + : "r" (ptr), "r" (x) + : "memory", "p0" + ); + return retval; +} + +/* + * Atomically swap the contents of a register with memory. Should be atomic + * between multiple CPU's and within interrupts on the same CPU. + */ +#define xchg(ptr, v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v), (ptr), \ + sizeof(*(ptr)))) + +/* Set a value and use a memory barrier. Used by the scheduler somewhere. */ +#define set_mb(var, value) \ + do { var = value; mb(); } while (0) + +/* + * see rt-mutex-design.txt; cmpxchg supposedly checks if *ptr == A and swaps. + * looks just like atomic_cmpxchg on our arch currently with a bunch of + * variable casting. + */ +#define __HAVE_ARCH_CMPXCHG 1 + +#define cmpxchg(ptr, old, new) \ +({ \ + __typeof__(ptr) __ptr = (ptr); \ + __typeof__(*(ptr)) __old = (old); \ + __typeof__(*(ptr)) __new = (new); \ + __typeof__(*(ptr)) __oldval = 0; \ + \ + asm volatile( \ + "1: %0 = memw_locked(%1);\n" \ + " { P0 = cmp.eq(%0,%2);\n" \ + " if (!P0.new) jump:nt 2f; }\n" \ + " memw_locked(%1,p0) = %3;\n" \ + " if (!P0) jump 1b;\n" \ + "2:\n" \ + : "=&r" (__oldval) \ + : "r" (__ptr), "r" (__old), "r" (__new) \ + : "memory", "p0" \ + ); \ + __oldval; \ +}) + +/* Should probably shoot for an 8-byte aligned stack pointer */ +#define STACK_MASK (~7) +#define arch_align_stack(x) (x & STACK_MASK) + +#endif diff --git a/arch/hexagon/include/asm/thread_info.h b/arch/hexagon/include/asm/thread_info.h new file mode 100644 index 000000000000..9c2934ff5756 --- /dev/null +++ b/arch/hexagon/include/asm/thread_info.h @@ -0,0 +1,154 @@ +/* + * Thread support for the Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_THREAD_INFO_H +#define _ASM_THREAD_INFO_H + +#ifdef __KERNEL__ + +#ifndef __ASSEMBLY__ +#include <asm/processor.h> +#include <asm/registers.h> +#include <asm/page.h> +#endif + +#define THREAD_SHIFT 12 +#define THREAD_SIZE (1<<THREAD_SHIFT) + +#if THREAD_SHIFT >= PAGE_SHIFT +#define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT) +#else /* don't use standard allocator */ +#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR +extern struct thread_info *alloc_thread_info_node(struct task_struct *tsk, int node); +extern void free_thread_info(struct thread_info *ti); +#endif + + +#ifndef __ASSEMBLY__ + +typedef struct { + unsigned long seg; +} mm_segment_t; + +/* + * This is union'd with the "bottom" of the kernel stack. + * It keeps track of thread info which is handy for routines + * to access quickly. + */ + +struct thread_info { + struct task_struct *task; /* main task structure */ + struct exec_domain *exec_domain; /* execution domain */ + unsigned long flags; /* low level flags */ + __u32 cpu; /* current cpu */ + int preempt_count; /* 0=>preemptible,<0=>BUG */ + mm_segment_t addr_limit; /* segmentation sux */ + /* + * used for syscalls somehow; + * seems to have a function pointer and four arguments + */ + struct restart_block restart_block; + /* Points to the current pt_regs frame */ + struct pt_regs *regs; + /* + * saved kernel sp at switch_to time; + * not sure if this is used (it's not in the VM model it seems; + * see thread_struct) + */ + unsigned long sp; +}; + +#else /* !__ASSEMBLY__ */ + +#include <asm/asm-offsets.h> + +#endif /* __ASSEMBLY__ */ + +/* looks like "linux/hardirq.h" uses this. */ + +#define PREEMPT_ACTIVE 0x10000000 + +#ifndef __ASSEMBLY__ + +#define INIT_THREAD_INFO(tsk) \ +{ \ + .task = &tsk, \ + .exec_domain = &default_exec_domain, \ + .flags = 0, \ + .cpu = 0, \ + .preempt_count = 1, \ + .addr_limit = KERNEL_DS, \ + .restart_block = { \ + .fn = do_no_restart_syscall, \ + }, \ + .sp = 0, \ + .regs = NULL, \ +} + +#define init_thread_info (init_thread_union.thread_info) +#define init_stack (init_thread_union.stack) + +/* Tacky preprocessor trickery */ +#define qqstr(s) qstr(s) +#define qstr(s) #s +#define QUOTED_THREADINFO_REG qqstr(THREADINFO_REG) + +register struct thread_info *__current_thread_info asm(QUOTED_THREADINFO_REG); +#define current_thread_info() __current_thread_info + +#endif /* __ASSEMBLY__ */ + +/* + * thread information flags + * - these are process state flags that various assembly files + * may need to access + * - pending work-to-be-done flags are in LSW + * - other flags in MSW + */ + +#define TIF_SYSCALL_TRACE 0 /* syscall trace active */ +#define TIF_NOTIFY_RESUME 1 /* resumption notification requested */ +#define TIF_SIGPENDING 2 /* signal pending */ +#define TIF_NEED_RESCHED 3 /* rescheduling necessary */ +#define TIF_SINGLESTEP 4 /* restore ss @ return to usr mode */ +#define TIF_IRET 5 /* return with iret */ +#define TIF_RESTORE_SIGMASK 6 /* restore sig mask in do_signal() */ +/* true if poll_idle() is polling TIF_NEED_RESCHED */ +#define TIF_POLLING_NRFLAG 16 +#define TIF_MEMDIE 17 /* OOM killer killed process */ + +#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) +#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) +#define _TIF_SIGPENDING (1 << TIF_SIGPENDING) +#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) +#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_IRET (1 << TIF_IRET) +#define _TIF_RESTORE_SIGMASK (1 << TIF_RESTORE_SIGMASK) +#define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) + +/* work to do on interrupt/exception return - All but TIF_SYSCALL_TRACE */ +#define _TIF_WORK_MASK (0x0000FFFF & ~_TIF_SYSCALL_TRACE) + +/* work to do on any return to u-space */ +#define _TIF_ALLWORK_MASK 0x0000FFFF + +#endif /* __KERNEL__ */ + +#endif diff --git a/arch/hexagon/include/asm/time.h b/arch/hexagon/include/asm/time.h new file mode 100644 index 000000000000..081b82cac9a9 --- /dev/null +++ b/arch/hexagon/include/asm/time.h @@ -0,0 +1,29 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef ASM_TIME_H +#define ASM_TIME_H + +extern cycles_t pcycle_freq_mhz; +extern cycles_t thread_freq_mhz; +extern cycles_t sleep_clk_freq; + +void setup_percpu_clockdev(void); +void ipi_timer(void); + +#endif diff --git a/arch/hexagon/include/asm/timer-regs.h b/arch/hexagon/include/asm/timer-regs.h new file mode 100644 index 000000000000..d80db239a7b6 --- /dev/null +++ b/arch/hexagon/include/asm/timer-regs.h @@ -0,0 +1,39 @@ +/* + * Timer support for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_TIMER_REGS_H +#define _ASM_TIMER_REGS_H + +/* This stuff should go into a platform specific file */ +#define TCX0_CLK_RATE 19200 +#define TIMER_ENABLE 0 +#define TIMER_CLR_ON_MATCH 1 + +/* + * 8x50 HDD Specs 5-8. Simulator co-sim not fixed until + * release 1.1, and then it's "adjustable" and probably not defaulted. + */ +#define RTOS_TIMER_INT 3 +#ifdef CONFIG_HEXAGON_COMET +#define RTOS_TIMER_REGS_ADDR 0xAB000000UL +#endif +#define SLEEP_CLK_RATE 32000 + +#endif diff --git a/arch/hexagon/include/asm/timex.h b/arch/hexagon/include/asm/timex.h new file mode 100644 index 000000000000..b11c62b23f31 --- /dev/null +++ b/arch/hexagon/include/asm/timex.h @@ -0,0 +1,36 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_TIMEX_H +#define _ASM_TIMEX_H + +#include <asm-generic/timex.h> +#include <asm/timer-regs.h> + +/* Using TCX0 as our clock. CLOCK_TICK_RATE scheduled to be removed. */ +#define CLOCK_TICK_RATE TCX0_CLK_RATE + +#define ARCH_HAS_READ_CURRENT_TIMER + +static inline int read_current_timer(unsigned long *timer_val) +{ + *timer_val = (unsigned long) __vmgettime(); + return 0; +} + +#endif diff --git a/arch/hexagon/include/asm/tlb.h b/arch/hexagon/include/asm/tlb.h new file mode 100644 index 000000000000..473abde01d62 --- /dev/null +++ b/arch/hexagon/include/asm/tlb.h @@ -0,0 +1,39 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_TLB_H +#define _ASM_TLB_H + +#include <linux/pagemap.h> +#include <asm/tlbflush.h> + +/* + * We don't need any special per-pte or per-vma handling... + */ +#define tlb_start_vma(tlb, vma) do { } while (0) +#define tlb_end_vma(tlb, vma) do { } while (0) +#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) + +/* + * .. because we flush the whole mm when it fills up + */ +#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm) + +#include <asm-generic/tlb.h> + +#endif diff --git a/arch/hexagon/include/asm/tlbflush.h b/arch/hexagon/include/asm/tlbflush.h new file mode 100644 index 000000000000..b89a90251225 --- /dev/null +++ b/arch/hexagon/include/asm/tlbflush.h @@ -0,0 +1,58 @@ +/* + * TLB flush support for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_TLBFLUSH_H +#define _ASM_TLBFLUSH_H + +#include <linux/mm.h> +#include <asm/processor.h> + +/* + * TLB flushing -- in "SMP", these routines get defined to be the + * ones from smp.c, else they are some local flavors. + */ + +/* + * These functions are commonly macros, but in the interests of + * VM vs. native implementation and code size, we simply declare + * the function prototypes here. + */ +extern void tlb_flush_all(void); +extern void flush_tlb_mm(struct mm_struct *mm); +extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr); +extern void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end); +extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void flush_tlb_one(unsigned long); + +/* + * "This is called in munmap when we have freed up some page-table pages. + * We don't need to do anything here..." + * + * The VM kernel doesn't walk page tables, and they are passed to the VMM + * by logical address. There doesn't seem to be any possibility that they + * could be referenced by the VM kernel based on a stale mapping, since + * they would only be located by consulting the mm structure, and they + * will have been purged from that structure by the munmap. Seems like + * a noop on HVM as well. + */ +#define flush_tlb_pgtables(mm, start, end) + +#endif diff --git a/arch/hexagon/include/asm/traps.h b/arch/hexagon/include/asm/traps.h new file mode 100644 index 000000000000..6a407f6e5e24 --- /dev/null +++ b/arch/hexagon/include/asm/traps.h @@ -0,0 +1,29 @@ +/* + * Trap support for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_HEXAGON_TRAPS_H +#define _ASM_HEXAGON_TRAPS_H + +#include <asm/registers.h> + +extern int die(const char *str, struct pt_regs *regs, long err); +extern int die_if_kernel(char *str, struct pt_regs *regs, long err); + +#endif /* _ASM_HEXAGON_TRAPS_H */ diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h new file mode 100644 index 000000000000..7e706eadbf0a --- /dev/null +++ b/arch/hexagon/include/asm/uaccess.h @@ -0,0 +1,116 @@ +/* + * User memory access support for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_UACCESS_H +#define _ASM_UACCESS_H +/* + * User space memory access functions + */ +#include <linux/sched.h> +#include <linux/mm.h> +#include <asm/segment.h> +#include <asm/sections.h> + +/* + * access_ok: - Checks if a user space pointer is valid + * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE. Note that + * %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe + * to write to a block, it is always safe to read from it. + * @addr: User space pointer to start of block to check + * @size: Size of block to check + * + * Context: User context only. This function may sleep. + * + * Checks if a pointer to a block of memory in user space is valid. + * + * Returns true (nonzero) if the memory block *may* be valid, false (zero) + * if it is definitely invalid. + * + * User address space in Hexagon, like x86, goes to 0xbfffffff, so the + * simple MSB-based tests used by MIPS won't work. Some further + * optimization is probably possible here, but for now, keep it + * reasonably simple and not *too* slow. After all, we've got the + * MMU for backup. + */ +#define VERIFY_READ 0 +#define VERIFY_WRITE 1 + +#define __access_ok(addr, size) \ + ((get_fs().seg == KERNEL_DS.seg) || \ + (((unsigned long)addr < get_fs().seg) && \ + (unsigned long)size < (get_fs().seg - (unsigned long)addr))) + +/* + * When a kernel-mode page fault is taken, the faulting instruction + * address is checked against a table of exception_table_entries. + * Each entry is a tuple of the address of an instruction that may + * be authorized to fault, and the address at which execution should + * be resumed instead of the faulting instruction, so as to effect + * a workaround. + */ + +/* Assembly somewhat optimized copy routines */ +unsigned long __copy_from_user_hexagon(void *to, const void __user *from, + unsigned long n); +unsigned long __copy_to_user_hexagon(void __user *to, const void *from, + unsigned long n); + +#define __copy_from_user(to, from, n) __copy_from_user_hexagon(to, from, n) +#define __copy_to_user(to, from, n) __copy_to_user_hexagon(to, from, n) + +/* + * XXX todo: some additonal performance gain is possible by + * implementing __copy_to/from_user_inatomic, which is much + * like __copy_to/from_user, but performs slightly less checking. + */ + +__kernel_size_t __clear_user_hexagon(void __user *dest, unsigned long count); +#define __clear_user(a, s) __clear_user_hexagon((a), (s)) + +#define __strncpy_from_user(dst, src, n) hexagon_strncpy_from_user(dst, src, n) + +/* get around the ifndef in asm-generic/uaccess.h */ +#define __strnlen_user __strnlen_user + +extern long __strnlen_user(const char __user *src, long n); + +static inline long hexagon_strncpy_from_user(char *dst, const char __user *src, + long n); + +#include <asm-generic/uaccess.h> + +/* Todo: an actual accelerated version of this. */ +static inline long hexagon_strncpy_from_user(char *dst, const char __user *src, + long n) +{ + long res = __strnlen_user(src, n); + + /* return from strnlen can't be zero -- that would be rubbish. */ + + if (res > n) { + copy_from_user(dst, src, n); + return n; + } else { + copy_from_user(dst, src, res); + return res-1; + } +} + +#endif diff --git a/arch/hexagon/include/asm/unistd.h b/arch/hexagon/include/asm/unistd.h new file mode 100644 index 000000000000..4d0ecde3665f --- /dev/null +++ b/arch/hexagon/include/asm/unistd.h @@ -0,0 +1,36 @@ +/* + * Syscall support for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#if !defined(_ASM_HEXAGON_UNISTD_H) || defined(__SYSCALL) +#define _ASM_HEXAGON_UNISTD_H + +/* + * The kernel pulls this unistd.h in three different ways: + * 1. the "normal" way which gets all the __NR defines + * 2. with __SYSCALL defined to produce function declarations + * 3. with __SYSCALL defined to produce syscall table initialization + * See also: syscalltab.c + */ + +#define sys_mmap2 sys_mmap_pgoff + +#include <asm-generic/unistd.h> + +#endif diff --git a/arch/hexagon/include/asm/user.h b/arch/hexagon/include/asm/user.h new file mode 100644 index 000000000000..3a55078543d1 --- /dev/null +++ b/arch/hexagon/include/asm/user.h @@ -0,0 +1,81 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef HEXAGON_ASM_USER_H +#define HEXAGON_ASM_USER_H + +/* + * Layout for registers passed in elf core dumps to userspace. + * + * Basically a rearranged subset of "pt_regs". + * + * Interested parties: libc, gdb... + */ + +struct user_regs_struct { + unsigned long r0; + unsigned long r1; + unsigned long r2; + unsigned long r3; + unsigned long r4; + unsigned long r5; + unsigned long r6; + unsigned long r7; + unsigned long r8; + unsigned long r9; + unsigned long r10; + unsigned long r11; + unsigned long r12; + unsigned long r13; + unsigned long r14; + unsigned long r15; + unsigned long r16; + unsigned long r17; + unsigned long r18; + unsigned long r19; + unsigned long r20; + unsigned long r21; + unsigned long r22; + unsigned long r23; + unsigned long r24; + unsigned long r25; + unsigned long r26; + unsigned long r27; + unsigned long r28; + unsigned long r29; + unsigned long r30; + unsigned long r31; + unsigned long sa0; + unsigned long lc0; + unsigned long sa1; + unsigned long lc1; + unsigned long m0; + unsigned long m1; + unsigned long usr; + unsigned long p3_0; + unsigned long gp; + unsigned long ugp; + unsigned long pc; + unsigned long cause; + unsigned long badva; + unsigned long pad1; /* pad out to 48 words total */ + unsigned long pad2; /* pad out to 48 words total */ + unsigned long pad3; /* pad out to 48 words total */ +}; + +#endif diff --git a/arch/hexagon/include/asm/vdso.h b/arch/hexagon/include/asm/vdso.h new file mode 100644 index 000000000000..2d95cbba3572 --- /dev/null +++ b/arch/hexagon/include/asm/vdso.h @@ -0,0 +1,30 @@ +/* + * vDSO implementation for Hexagon + * + * Copyright (c) 2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef __ASM_VDSO_H +#define __ASM_VDSO_H + +#include <linux/types.h> + +struct hexagon_vdso { + u32 rt_signal_trampoline[2]; +}; + +#endif /* __ASM_VDSO_H */ diff --git a/arch/hexagon/include/asm/vm_fault.h b/arch/hexagon/include/asm/vm_fault.h new file mode 100644 index 000000000000..cacda36ef5d5 --- /dev/null +++ b/arch/hexagon/include/asm/vm_fault.h @@ -0,0 +1,26 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_HEXAGON_VM_FAULT_H +#define _ASM_HEXAGON_VM_FAULT_H + +extern void execute_protection_fault(struct pt_regs *); +extern void write_protection_fault(struct pt_regs *); +extern void read_protection_fault(struct pt_regs *); + +#endif diff --git a/arch/hexagon/include/asm/vm_mmu.h b/arch/hexagon/include/asm/vm_mmu.h new file mode 100644 index 000000000000..580462de5cca --- /dev/null +++ b/arch/hexagon/include/asm/vm_mmu.h @@ -0,0 +1,111 @@ +/* + * Hexagon VM page table entry definitions + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef _ASM_VM_MMU_H +#define _ASM_VM_MMU_H + +/* + * Shift, mask, and other constants for the Hexagon Virtual Machine + * page tables. + * + * Virtual machine MMU allows first-level entries to either be + * single-level lookup PTEs for very large pages, or PDEs pointing + * to second-level PTEs for smaller pages. If PTE is single-level, + * the least significant bits cannot be used as software bits to encode + * virtual memory subsystem information about the page, and that state + * must be maintained in some parallel data structure. + */ + +/* S or Page Size field in PDE */ +#define __HVM_PDE_S (0x7 << 0) +#define __HVM_PDE_S_4KB 0 +#define __HVM_PDE_S_16KB 1 +#define __HVM_PDE_S_64KB 2 +#define __HVM_PDE_S_256KB 3 +#define __HVM_PDE_S_1MB 4 +#define __HVM_PDE_S_4MB 5 +#define __HVM_PDE_S_16MB 6 +#define __HVM_PDE_S_INVALID 7 + +/* Masks for L2 page table pointer, as function of page size */ +#define __HVM_PDE_PTMASK_4KB 0xfffff000 +#define __HVM_PDE_PTMASK_16KB 0xfffffc00 +#define __HVM_PDE_PTMASK_64KB 0xffffff00 +#define __HVM_PDE_PTMASK_256KB 0xffffffc0 +#define __HVM_PDE_PTMASK_1MB 0xfffffff0 + +/* + * Virtual Machine PTE Bits/Fields + */ +#define __HVM_PTE_T (1<<4) +#define __HVM_PTE_U (1<<5) +#define __HVM_PTE_C (0x7<<6) +#define __HVM_PTE_CVAL(pte) (((pte) & __HVM_PTE_C) >> 6) +#define __HVM_PTE_R (1<<9) +#define __HVM_PTE_W (1<<10) +#define __HVM_PTE_X (1<<11) + +/* + * Cache Attributes, to be shifted as necessary for virtual/physical PTEs + */ + +#define __HEXAGON_C_WB 0x0 /* Write-back, no L2 */ +#define __HEXAGON_C_WT 0x1 /* Write-through, no L2 */ +#define __HEXAGON_C_DEV 0x4 /* Device register space */ +#define __HEXAGON_C_WT_L2 0x5 /* Write-through, with L2 */ +/* this really should be #if CONFIG_HEXAGON_ARCH = 2 but that's not defined */ +#if defined(CONFIG_HEXAGON_COMET) || defined(CONFIG_QDSP6_ST1) +#define __HEXAGON_C_UNC __HEXAGON_C_DEV +#else +#define __HEXAGON_C_UNC 0x6 /* Uncached memory */ +#endif +#define __HEXAGON_C_WB_L2 0x7 /* Write-back, with L2 */ + +/* + * This can be overriden, but we're defaulting to the most aggressive + * cache policy, the better to find bugs sooner. + */ + +#define CACHE_DEFAULT __HEXAGON_C_WB_L2 + +/* Masks for physical page address, as a function of page size */ + +#define __HVM_PTE_PGMASK_4KB 0xfffff000 +#define __HVM_PTE_PGMASK_16KB 0xffffc000 +#define __HVM_PTE_PGMASK_64KB 0xffff0000 +#define __HVM_PTE_PGMASK_256KB 0xfffc0000 +#define __HVM_PTE_PGMASK_1MB 0xfff00000 + +/* Masks for single-level large page lookups */ + +#define __HVM_PTE_PGMASK_4MB 0xffc00000 +#define __HVM_PTE_PGMASK_16MB 0xff000000 + +/* + * "Big kernel page mappings" (see vm_init_segtable.S) + * are currently 16MB + */ + +#define BIG_KERNEL_PAGE_SHIFT 24 +#define BIG_KERNEL_PAGE_SIZE (1 << BIG_KERNEL_PAGE_SHIFT) + + + +#endif /* _ASM_VM_MMU_H */ diff --git a/arch/hexagon/kernel/Makefile b/arch/hexagon/kernel/Makefile new file mode 100644 index 000000000000..3689f3754d09 --- /dev/null +++ b/arch/hexagon/kernel/Makefile @@ -0,0 +1,18 @@ +extra-y := head.o vmlinux.lds init_task.o + +obj-$(CONFIG_SMP) += smp.o topology.o + +obj-y += setup.o irq_cpu.o traps.o syscalltab.o signal.o time.o +obj-y += process.o syscall.o trampoline.o reset.o ptrace.o +obj-y += vdso.o + +obj-$(CONFIG_KGDB) += kgdb.o +obj-$(CONFIG_MODULES) += module.o hexagon_ksyms.o + +# Modules required to work with the Hexagon Virtual Machine +obj-y += vm_entry.o vm_events.o vm_switch.o vm_ops.o vm_init_segtable.o +obj-y += vm_vectors.o + +obj-$(CONFIG_HAS_DMA) += dma.o + +obj-$(CONFIG_STACKTRACE) += stacktrace.o diff --git a/arch/hexagon/kernel/asm-offsets.c b/arch/hexagon/kernel/asm-offsets.c new file mode 100644 index 000000000000..89ffa514611f --- /dev/null +++ b/arch/hexagon/kernel/asm-offsets.c @@ -0,0 +1,104 @@ +/* + * Copyright (C) 1996 David S. Miller + * Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003 Ralf Baechle + * Copyright (C) 1999, 2000 Silicon Graphics, Inc. + * Kevin Kissell, kevink@mips.com and Carsten Langgaard, carstenl@mips.com + * Copyright (C) 2000 MIPS Technologies, Inc. + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/compat.h> +#include <linux/types.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/interrupt.h> +#include <linux/kbuild.h> +#include <asm/ptrace.h> +#include <asm/processor.h> + +/* This file is used to produce asm/linkerscript constants from header + files typically used in c. Specifically, it generates asm-offsets.h */ + +int main(void) +{ + COMMENT("This is a comment."); + /* might get these from somewhere else. */ + DEFINE(_PAGE_SIZE, PAGE_SIZE); + DEFINE(_PAGE_SHIFT, PAGE_SHIFT); + BLANK(); + + COMMENT("Hexagon pt_regs definitions"); + OFFSET(_PT_SYSCALL_NR, pt_regs, syscall_nr); + OFFSET(_PT_UGPGP, pt_regs, ugpgp); + OFFSET(_PT_R3130, pt_regs, r3130); + OFFSET(_PT_R2928, pt_regs, r2928); + OFFSET(_PT_R2726, pt_regs, r2726); + OFFSET(_PT_R2524, pt_regs, r2524); + OFFSET(_PT_R2322, pt_regs, r2322); + OFFSET(_PT_R2120, pt_regs, r2120); + OFFSET(_PT_R1918, pt_regs, r1918); + OFFSET(_PT_R1716, pt_regs, r1716); + OFFSET(_PT_R1514, pt_regs, r1514); + OFFSET(_PT_R1312, pt_regs, r1312); + OFFSET(_PT_R1110, pt_regs, r1110); + OFFSET(_PT_R0908, pt_regs, r0908); + OFFSET(_PT_R0706, pt_regs, r0706); + OFFSET(_PT_R0504, pt_regs, r0504); + OFFSET(_PT_R0302, pt_regs, r0302); + OFFSET(_PT_R0100, pt_regs, r0100); + OFFSET(_PT_LC0SA0, pt_regs, lc0sa0); + OFFSET(_PT_LC1SA1, pt_regs, lc1sa1); + OFFSET(_PT_M1M0, pt_regs, m1m0); + OFFSET(_PT_PREDSUSR, pt_regs, predsusr); + OFFSET(_PT_EVREC, pt_regs, hvmer); + OFFSET(_PT_ER_VMEL, pt_regs, hvmer.vmel); + OFFSET(_PT_ER_VMEST, pt_regs, hvmer.vmest); + OFFSET(_PT_ER_VMPSP, pt_regs, hvmer.vmpsp); + OFFSET(_PT_ER_VMBADVA, pt_regs, hvmer.vmbadva); + DEFINE(_PT_REGS_SIZE, sizeof(struct pt_regs)); + BLANK(); + + COMMENT("Hexagon thread_info definitions"); + OFFSET(_THREAD_INFO_FLAGS, thread_info, flags); + OFFSET(_THREAD_INFO_PT_REGS, thread_info, regs); + OFFSET(_THREAD_INFO_SP, thread_info, sp); + DEFINE(_THREAD_SIZE, THREAD_SIZE); + BLANK(); + + COMMENT("Hexagon hexagon_switch_stack definitions"); + OFFSET(_SWITCH_R1716, hexagon_switch_stack, r1716); + OFFSET(_SWITCH_R1918, hexagon_switch_stack, r1918); + OFFSET(_SWITCH_R2120, hexagon_switch_stack, r2120); + OFFSET(_SWITCH_R2322, hexagon_switch_stack, r2322); + + OFFSET(_SWITCH_R2524, hexagon_switch_stack, r2524); + OFFSET(_SWITCH_R2726, hexagon_switch_stack, r2726); + OFFSET(_SWITCH_FP, hexagon_switch_stack, fp); + OFFSET(_SWITCH_LR, hexagon_switch_stack, lr); + DEFINE(_SWITCH_STACK_SIZE, sizeof(struct hexagon_switch_stack)); + BLANK(); + + COMMENT("Hexagon task_struct definitions"); + OFFSET(_TASK_THREAD_INFO, task_struct, stack); + OFFSET(_TASK_STRUCT_THREAD, task_struct, thread); + + COMMENT("Hexagon thread_struct definitions"); + OFFSET(_THREAD_STRUCT_SWITCH_SP, thread_struct, switch_sp); + + return 0; +} diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c new file mode 100644 index 000000000000..e711ace62fdf --- /dev/null +++ b/arch/hexagon/kernel/dma.c @@ -0,0 +1,220 @@ +/* + * DMA implementation for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/dma-mapping.h> +#include <linux/bootmem.h> +#include <linux/genalloc.h> +#include <asm/dma-mapping.h> + +struct dma_map_ops *dma_ops; +EXPORT_SYMBOL(dma_ops); + +int bad_dma_address; /* globals are automatically initialized to zero */ + +int dma_supported(struct device *dev, u64 mask) +{ + if (mask == DMA_BIT_MASK(32)) + return 1; + else + return 0; +} +EXPORT_SYMBOL(dma_supported); + +int dma_set_mask(struct device *dev, u64 mask) +{ + if (!dev->dma_mask || !dma_supported(dev, mask)) + return -EIO; + + *dev->dma_mask = mask; + + return 0; +} +EXPORT_SYMBOL(dma_set_mask); + +static struct gen_pool *coherent_pool; + + +/* Allocates from a pool of uncached memory that was reserved at boot time */ + +void *hexagon_dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_addr, gfp_t flag) +{ + void *ret; + + if (coherent_pool == NULL) { + coherent_pool = gen_pool_create(PAGE_SHIFT, -1); + + if (coherent_pool == NULL) + panic("Can't create %s() memory pool!", __func__); + else + gen_pool_add(coherent_pool, + (PAGE_OFFSET + (max_low_pfn << PAGE_SHIFT)), + hexagon_coherent_pool_size, -1); + } + + ret = (void *) gen_pool_alloc(coherent_pool, size); + + if (ret) { + memset(ret, 0, size); + *dma_addr = (dma_addr_t) (ret - PAGE_OFFSET); + } else + *dma_addr = ~0; + + return ret; +} + +static void hexagon_free_coherent(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_addr) +{ + gen_pool_free(coherent_pool, (unsigned long) vaddr, size); +} + +static int check_addr(const char *name, struct device *hwdev, + dma_addr_t bus, size_t size) +{ + if (hwdev && hwdev->dma_mask && !dma_capable(hwdev, bus, size)) { + if (*hwdev->dma_mask >= DMA_BIT_MASK(32)) + printk(KERN_ERR + "%s: overflow %Lx+%zu of device mask %Lx\n", + name, (long long)bus, size, + (long long)*hwdev->dma_mask); + return 0; + } + return 1; +} + +static int hexagon_map_sg(struct device *hwdev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + struct scatterlist *s; + int i; + + WARN_ON(nents == 0 || sg[0].length == 0); + + for_each_sg(sg, s, nents, i) { + s->dma_address = sg_phys(s); + if (!check_addr("map_sg", hwdev, s->dma_address, s->length)) + return 0; + + s->dma_length = s->length; + + flush_dcache_range(PAGE_OFFSET + s->dma_address, + PAGE_OFFSET + s->dma_address + s->length); + } + + return nents; +} + +/* + * address is virtual + */ +static inline void dma_sync(void *addr, size_t size, + enum dma_data_direction dir) +{ + switch (dir) { + case DMA_TO_DEVICE: + hexagon_clean_dcache_range((unsigned long) addr, + (unsigned long) addr + size); + break; + case DMA_FROM_DEVICE: + hexagon_inv_dcache_range((unsigned long) addr, + (unsigned long) addr + size); + break; + case DMA_BIDIRECTIONAL: + flush_dcache_range((unsigned long) addr, + (unsigned long) addr + size); + break; + default: + BUG(); + } +} + +static inline void *dma_addr_to_virt(dma_addr_t dma_addr) +{ + return phys_to_virt((unsigned long) dma_addr); +} + +/** + * hexagon_map_page() - maps an address for device DMA + * @dev: pointer to DMA device + * @page: pointer to page struct of DMA memory + * @offset: offset within page + * @size: size of memory to map + * @dir: transfer direction + * @attrs: pointer to DMA attrs (not used) + * + * Called to map a memory address to a DMA address prior + * to accesses to/from device. + * + * We don't particularly have many hoops to jump through + * so far. Straight translation between phys and virtual. + * + * DMA is not cache coherent so sync is necessary; this + * seems to be a convenient place to do it. + * + */ +static dma_addr_t hexagon_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + dma_addr_t bus = page_to_phys(page) + offset; + WARN_ON(size == 0); + + if (!check_addr("map_single", dev, bus, size)) + return bad_dma_address; + + dma_sync(dma_addr_to_virt(bus), size, dir); + + return bus; +} + +static void hexagon_sync_single_for_cpu(struct device *dev, + dma_addr_t dma_handle, size_t size, + enum dma_data_direction dir) +{ + dma_sync(dma_addr_to_virt(dma_handle), size, dir); +} + +static void hexagon_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, size_t size, + enum dma_data_direction dir) +{ + dma_sync(dma_addr_to_virt(dma_handle), size, dir); +} + +struct dma_map_ops hexagon_dma_ops = { + .alloc_coherent = hexagon_dma_alloc_coherent, + .free_coherent = hexagon_free_coherent, + .map_sg = hexagon_map_sg, + .map_page = hexagon_map_page, + .sync_single_for_cpu = hexagon_sync_single_for_cpu, + .sync_single_for_device = hexagon_sync_single_for_device, + .is_phys = 1, +}; + +void __init hexagon_dma_init(void) +{ + if (dma_ops) + return; + + dma_ops = &hexagon_dma_ops; +} diff --git a/arch/hexagon/kernel/head.S b/arch/hexagon/kernel/head.S new file mode 100644 index 000000000000..8e6b819125a3 --- /dev/null +++ b/arch/hexagon/kernel/head.S @@ -0,0 +1,162 @@ +/* + * Early kernel startup code for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/linkage.h> +#include <linux/init.h> +#include <asm/asm-offsets.h> +#include <asm/mem-layout.h> +#include <asm/vm_mmu.h> +#include <asm/page.h> + + __INIT +ENTRY(stext) + /* + * VMM will already have set up true vector page, MMU, etc. + * To set up initial kernel identity map, we have to pass + * the VMM a pointer to some canonical page tables. In + * this implementation, we're assuming that we've got + * them precompiled. Generate value in R24, as we'll need + * it again shortly. + */ + r24.L = #LO(swapper_pg_dir) + r24.H = #HI(swapper_pg_dir) + + /* + * Symbol is kernel segment address, but we need + * the logical/physical address. + */ + r24 = asl(r24, #2) + r24 = lsr(r24, #2) + + r0 = r24 + + /* + * Initialize a 16MB PTE to make the virtual and physical + * addresses where the kernel was loaded be identical. + */ +#define PTE_BITS ( __HVM_PTE_R | __HVM_PTE_W | __HVM_PTE_X \ + | __HEXAGON_C_WB_L2 << 6 \ + | __HVM_PDE_S_4MB) + + r1 = pc + r2.H = #0xffc0 + r2.L = #0x0000 + r1 = and(r1,r2) /* round PC to 4MB boundary */ + r2 = lsr(r1, #22) /* 4MB page number */ + r2 = asl(r2, #2) /* times sizeof(PTE) (4bytes) */ + r0 = add(r0,r2) /* r0 = address of correct PTE */ + r2 = #PTE_BITS + r1 = add(r1,r2) /* r1 = 4MB PTE for the first entry */ + r2.h = #0x0040 + r2.l = #0x0000 /* 4MB */ + memw(r0 ++ #4) = r1 + r1 = add(r1, r2) + memw(r0 ++ #4) = r1 + + r0 = r24 + + /* + * The subroutine wrapper around the virtual instruction touches + * no memory, so we should be able to use it even here. + */ + call __vmnewmap; + + /* Jump into virtual address range. */ + + r31.h = #hi(__head_s_vaddr_target) + r31.l = #lo(__head_s_vaddr_target) + jumpr r31 + + /* Insert trippy space effects. */ + +__head_s_vaddr_target: + /* + * Tear down VA=PA translation now that we are running + * in the desgnated kernel segments. + */ + r0 = #__HVM_PDE_S_INVALID + r1 = r24 + loop0(1f,#0x100) +1: + { + memw(R1 ++ #4) = R0 + }:endloop0 + + r0 = r24 + call __vmnewmap + + /* Go ahead and install the trap0 return so angel calls work */ + r0.h = #hi(_K_provisional_vec) + r0.l = #lo(_K_provisional_vec) + call __vmsetvec + + /* + * OK, at this point we should start to be much more careful, + * we're going to enter C code and start touching memory + * in all sorts of places. + * This means: + * SGP needs to be OK + * Need to lock shared resources + * A bunch of other things that will cause + * all kinds of painful bugs + */ + + /* + * Stack pointer should be pointed at the init task's + * thread stack, which should have been declared in arch/init_task.c. + * So uhhhhh... + * It's accessible via the init_thread_union, which is a union + * of a thread_info struct and a stack; of course, the top + * of the stack is not for you. The end of the stack + * is simply init_thread_union + THREAD_SIZE. + */ + + {r29.H = #HI(init_thread_union); r0.H = #HI(_THREAD_SIZE); } + {r29.L = #LO(init_thread_union); r0.L = #LO(_THREAD_SIZE); } + + /* initialize the register used to point to current_thread_info */ + /* Fixme: THREADINFO_REG can't be R2 because of that memset thing. */ + {r29 = add(r29,r0); THREADINFO_REG = r29; } + + /* Hack: zero bss; */ + { r0.L = #LO(__bss_start); r1 = #0; r2.l = #LO(__bss_stop); } + { r0.H = #HI(__bss_start); r2.h = #HI(__bss_stop); } + + r2 = sub(r2,r0); + call memset; + + /* Time to make the doughnuts. */ + call start_kernel + + /* + * Should not reach here. + */ +1: + jump 1b + +.p2align PAGE_SHIFT +ENTRY(external_cmdline_buffer) + .fill _PAGE_SIZE,1,0 + +.data +.p2align PAGE_SHIFT +ENTRY(empty_zero_page) + .fill _PAGE_SIZE,1,0 diff --git a/arch/hexagon/kernel/hexagon_ksyms.c b/arch/hexagon/kernel/hexagon_ksyms.c new file mode 100644 index 000000000000..7f1892471805 --- /dev/null +++ b/arch/hexagon/kernel/hexagon_ksyms.c @@ -0,0 +1,40 @@ +/* + * Export of symbols defined in assembly files and/or libgcc. + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <asm/hexagon_vm.h> +#include <asm/uaccess.h> + +EXPORT_SYMBOL(__copy_from_user_hexagon); +EXPORT_SYMBOL(__copy_to_user_hexagon); +EXPORT_SYMBOL(__vmgetie); +EXPORT_SYMBOL(__vmsetie); +EXPORT_SYMBOL(memcpy); +EXPORT_SYMBOL(memset); + +#define DECLARE_EXPORT(name) \ + extern void name(void); EXPORT_SYMBOL(name) + +/* Symbols found in libgcc that assorted kernel modules need */ +DECLARE_EXPORT(__hexagon_memcpy_likely_aligned_min32bytes_mult8bytes); + +DECLARE_EXPORT(__hexagon_divsi3); +DECLARE_EXPORT(__hexagon_modsi3); +DECLARE_EXPORT(__hexagon_udivsi3); +DECLARE_EXPORT(__hexagon_umodsi3); diff --git a/arch/hexagon/kernel/init_task.c b/arch/hexagon/kernel/init_task.c new file mode 100644 index 000000000000..73283d3edf09 --- /dev/null +++ b/arch/hexagon/kernel/init_task.c @@ -0,0 +1,54 @@ +/* + * Init task definition + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/init_task.h> +#include <linux/fs.h> +#include <linux/mqueue.h> +#include <asm/thread_info.h> +#include <asm/uaccess.h> +#include <asm/pgtable.h> + +static struct signal_struct init_signals = INIT_SIGNALS(init_signals); +static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); + +/* + * Initial thread structure. + * + * We need to make sure that this is 8192-byte aligned due to the + * way process stacks are handled. This is done by making sure + * the linker maps this in the .text segment right after head.S, + * and making head.S ensure the proper alignment. + */ +union thread_union init_thread_union + __attribute__((__section__(".data.init_task"), + __aligned__(THREAD_SIZE))) = { + INIT_THREAD_INFO(init_task) + }; + +/* + * Initial task structure. + * + * All other task structs will be allocated on slabs in fork.c + */ +struct task_struct init_task = INIT_TASK(init_task); +EXPORT_SYMBOL(init_task); diff --git a/arch/hexagon/kernel/irq_cpu.c b/arch/hexagon/kernel/irq_cpu.c new file mode 100644 index 000000000000..d4416a1a431e --- /dev/null +++ b/arch/hexagon/kernel/irq_cpu.c @@ -0,0 +1,90 @@ +/* + * First-level interrupt controller model for Hexagon. + * + * Copyright (c) 2010-2011 Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/interrupt.h> +#include <asm/irq.h> +#include <asm/hexagon_vm.h> + +static void mask_irq(struct irq_data *data) +{ + __vmintop_locdis((long) data->irq); +} + +static void mask_irq_num(unsigned int irq) +{ + __vmintop_locdis((long) irq); +} + +static void unmask_irq(struct irq_data *data) +{ + __vmintop_locen((long) data->irq); +} + +/* This is actually all we need for handle_fasteoi_irq */ +static void eoi_irq(struct irq_data *data) +{ + __vmintop_globen((long) data->irq); +} + +/* Power mamangement wake call. We don't need this, however, + * if this is absent, then an -ENXIO error is returned to the + * msm_serial driver, and it fails to correctly initialize. + * This is a bug in the msm_serial driver, but, for now, we + * work around it here, by providing this bogus handler. + * XXX FIXME!!! remove this when msm_serial is fixed. + */ +static int set_wake(struct irq_data *data, unsigned int on) +{ + return 0; +} + +static struct irq_chip hexagon_irq_chip = { + .name = "HEXAGON", + .irq_mask = mask_irq, + .irq_unmask = unmask_irq, + .irq_set_wake = set_wake, + .irq_eoi = eoi_irq +}; + +/** + * The hexagon core comes with a first-level interrupt controller + * with 32 total possible interrupts. When the core is embedded + * into different systems/platforms, it is typically wrapped by + * macro cells that provide one or more second-level interrupt + * controllers that are cascaded into one or more of the first-level + * interrupts handled here. The precise wiring of these other + * irqs varies from platform to platform, and are set up & configured + * in the platform-specific files. + * + * The first-level interrupt controller is wrapped by the VM, which + * virtualizes the interrupt controller for us. It provides a very + * simple, fast & efficient API, and so the fasteoi handler is + * appropriate for this case. + */ +void __init init_IRQ(void) +{ + int irq; + + for (irq = 0; irq < HEXAGON_CPUINTS; irq++) { + mask_irq_num(irq); + irq_set_chip_and_handler(irq, &hexagon_irq_chip, + handle_fasteoi_irq); + } +} diff --git a/arch/hexagon/kernel/kgdb.c b/arch/hexagon/kernel/kgdb.c new file mode 100644 index 000000000000..fe4aa1bcca50 --- /dev/null +++ b/arch/hexagon/kernel/kgdb.c @@ -0,0 +1,254 @@ +/* + * arch/hexagon/kernel/kgdb.c - Hexagon KGDB Support + * + * Copyright (c) 2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/kdebug.h> +#include <linux/kgdb.h> + +/* All registers are 4 bytes, for now */ +#define GDB_SIZEOF_REG 4 + +/* The register names are used during printing of the regs; + * Keep these at three letters to pretty-print. */ +struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { + { " r0", GDB_SIZEOF_REG, offsetof(struct pt_regs, r00)}, + { " r1", GDB_SIZEOF_REG, offsetof(struct pt_regs, r01)}, + { " r2", GDB_SIZEOF_REG, offsetof(struct pt_regs, r02)}, + { " r3", GDB_SIZEOF_REG, offsetof(struct pt_regs, r03)}, + { " r4", GDB_SIZEOF_REG, offsetof(struct pt_regs, r04)}, + { " r5", GDB_SIZEOF_REG, offsetof(struct pt_regs, r05)}, + { " r6", GDB_SIZEOF_REG, offsetof(struct pt_regs, r06)}, + { " r7", GDB_SIZEOF_REG, offsetof(struct pt_regs, r07)}, + { " r8", GDB_SIZEOF_REG, offsetof(struct pt_regs, r08)}, + { " r9", GDB_SIZEOF_REG, offsetof(struct pt_regs, r09)}, + { "r10", GDB_SIZEOF_REG, offsetof(struct pt_regs, r10)}, + { "r11", GDB_SIZEOF_REG, offsetof(struct pt_regs, r11)}, + { "r12", GDB_SIZEOF_REG, offsetof(struct pt_regs, r12)}, + { "r13", GDB_SIZEOF_REG, offsetof(struct pt_regs, r13)}, + { "r14", GDB_SIZEOF_REG, offsetof(struct pt_regs, r14)}, + { "r15", GDB_SIZEOF_REG, offsetof(struct pt_regs, r15)}, + { "r16", GDB_SIZEOF_REG, offsetof(struct pt_regs, r16)}, + { "r17", GDB_SIZEOF_REG, offsetof(struct pt_regs, r17)}, + { "r18", GDB_SIZEOF_REG, offsetof(struct pt_regs, r18)}, + { "r19", GDB_SIZEOF_REG, offsetof(struct pt_regs, r19)}, + { "r20", GDB_SIZEOF_REG, offsetof(struct pt_regs, r20)}, + { "r21", GDB_SIZEOF_REG, offsetof(struct pt_regs, r21)}, + { "r22", GDB_SIZEOF_REG, offsetof(struct pt_regs, r22)}, + { "r23", GDB_SIZEOF_REG, offsetof(struct pt_regs, r23)}, + { "r24", GDB_SIZEOF_REG, offsetof(struct pt_regs, r24)}, + { "r25", GDB_SIZEOF_REG, offsetof(struct pt_regs, r25)}, + { "r26", GDB_SIZEOF_REG, offsetof(struct pt_regs, r26)}, + { "r27", GDB_SIZEOF_REG, offsetof(struct pt_regs, r27)}, + { "r28", GDB_SIZEOF_REG, offsetof(struct pt_regs, r28)}, + { "r29", GDB_SIZEOF_REG, offsetof(struct pt_regs, r29)}, + { "r30", GDB_SIZEOF_REG, offsetof(struct pt_regs, r30)}, + { "r31", GDB_SIZEOF_REG, offsetof(struct pt_regs, r31)}, + + { "usr", GDB_SIZEOF_REG, offsetof(struct pt_regs, usr)}, + { "preds", GDB_SIZEOF_REG, offsetof(struct pt_regs, preds)}, + { " m0", GDB_SIZEOF_REG, offsetof(struct pt_regs, m0)}, + { " m1", GDB_SIZEOF_REG, offsetof(struct pt_regs, m1)}, + { "sa0", GDB_SIZEOF_REG, offsetof(struct pt_regs, sa0)}, + { "sa1", GDB_SIZEOF_REG, offsetof(struct pt_regs, sa1)}, + { "lc0", GDB_SIZEOF_REG, offsetof(struct pt_regs, lc0)}, + { "lc1", GDB_SIZEOF_REG, offsetof(struct pt_regs, lc1)}, + { " gp", GDB_SIZEOF_REG, offsetof(struct pt_regs, gp)}, + { "ugp", GDB_SIZEOF_REG, offsetof(struct pt_regs, ugp)}, + { "psp", GDB_SIZEOF_REG, offsetof(struct pt_regs, hvmer.vmpsp)}, + { "elr", GDB_SIZEOF_REG, offsetof(struct pt_regs, hvmer.vmel)}, + { "est", GDB_SIZEOF_REG, offsetof(struct pt_regs, hvmer.vmest)}, + { "badva", GDB_SIZEOF_REG, offsetof(struct pt_regs, hvmer.vmbadva)}, + { "restart_r0", GDB_SIZEOF_REG, offsetof(struct pt_regs, restart_r0)}, + { "syscall_nr", GDB_SIZEOF_REG, offsetof(struct pt_regs, syscall_nr)}, +}; + +struct kgdb_arch arch_kgdb_ops = { + /* trap0(#0xDB) 0x0cdb0054 */ + .gdb_bpt_instr = {0x54, 0x00, 0xdb, 0x0c}, +}; + +char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return NULL; + + *((unsigned long *) mem) = *((unsigned long *) ((void *)regs + + dbg_reg_def[regno].offset)); + + return dbg_reg_def[regno].name; +} + +int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return -EINVAL; + + *((unsigned long *) ((void *)regs + dbg_reg_def[regno].offset)) = + *((unsigned long *) mem); + + return 0; +} + +void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) +{ + instruction_pointer(regs) = pc; +} + +#ifdef CONFIG_SMP + +/** + * kgdb_roundup_cpus - Get other CPUs into a holding pattern + * @flags: Current IRQ state + * + * On SMP systems, we need to get the attention of the other CPUs + * and get them be in a known state. This should do what is needed + * to get the other CPUs to call kgdb_wait(). Note that on some arches, + * the NMI approach is not used for rounding up all the CPUs. For example, + * in case of MIPS, smp_call_function() is used to roundup CPUs. In + * this case, we have to make sure that interrupts are enabled before + * calling smp_call_function(). The argument to this function is + * the flags that will be used when restoring the interrupts. There is + * local_irq_save() call before kgdb_roundup_cpus(). + * + * On non-SMP systems, this is not called. + */ + +static void hexagon_kgdb_nmi_hook(void *ignored) +{ + kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs()); +} + +void kgdb_roundup_cpus(unsigned long flags) +{ + local_irq_enable(); + smp_call_function(hexagon_kgdb_nmi_hook, NULL, 0); + local_irq_disable(); +} +#endif + + +/* Not yet working */ +void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, + struct task_struct *task) +{ + struct pt_regs *thread_regs; + + if (task == NULL) + return; + + /* Initialize to zero */ + memset(gdb_regs, 0, NUMREGBYTES); + + /* Otherwise, we have only some registers from switch_to() */ + thread_regs = task_pt_regs(task); + gdb_regs[0] = thread_regs->r00; +} + +/** + * kgdb_arch_handle_exception - Handle architecture specific GDB packets. + * @vector: The error vector of the exception that happened. + * @signo: The signal number of the exception that happened. + * @err_code: The error code of the exception that happened. + * @remcom_in_buffer: The buffer of the packet we have read. + * @remcom_out_buffer: The buffer of %BUFMAX bytes to write a packet into. + * @regs: The &struct pt_regs of the current process. + * + * This function MUST handle the 'c' and 's' command packets, + * as well packets to set / remove a hardware breakpoint, if used. + * If there are additional packets which the hardware needs to handle, + * they are handled here. The code should return -1 if it wants to + * process more packets, and a %0 or %1 if it wants to exit from the + * kgdb callback. + * + * Not yet working. + */ +int kgdb_arch_handle_exception(int vector, int signo, int err_code, + char *remcom_in_buffer, char *remcom_out_buffer, + struct pt_regs *linux_regs) +{ + switch (remcom_in_buffer[0]) { + case 's': + case 'c': + return 0; + } + /* Stay in the debugger. */ + return -1; +} + +static int __kgdb_notify(struct die_args *args, unsigned long cmd) +{ + /* cpu roundup */ + if (atomic_read(&kgdb_active) != -1) { + kgdb_nmicallback(smp_processor_id(), args->regs); + return NOTIFY_STOP; + } + + if (user_mode(args->regs)) + return NOTIFY_DONE; + + if (kgdb_handle_exception(args->trapnr & 0xff, args->signr, args->err, + args->regs)) + return NOTIFY_DONE; + + return NOTIFY_STOP; +} + +static int +kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr) +{ + unsigned long flags; + int ret; + + local_irq_save(flags); + ret = __kgdb_notify(ptr, cmd); + local_irq_restore(flags); + + return ret; +} + +static struct notifier_block kgdb_notifier = { + .notifier_call = kgdb_notify, + + /* + * Lowest-prio notifier priority, we want to be notified last: + */ + .priority = -INT_MAX, +}; + +/** + * kgdb_arch_init - Perform any architecture specific initalization. + * + * This function will handle the initalization of any architecture + * specific callbacks. + */ +int kgdb_arch_init(void) +{ + return register_die_notifier(&kgdb_notifier); +} + +/** + * kgdb_arch_exit - Perform any architecture specific uninitalization. + * + * This function will handle the uninitalization of any architecture + * specific callbacks, for dynamic registration and unregistration. + */ +void kgdb_arch_exit(void) +{ + unregister_die_notifier(&kgdb_notifier); +} diff --git a/arch/hexagon/kernel/module.c b/arch/hexagon/kernel/module.c new file mode 100644 index 000000000000..61a76bae3668 --- /dev/null +++ b/arch/hexagon/kernel/module.c @@ -0,0 +1,162 @@ +/* + * Kernel module loader for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <asm/module.h> +#include <linux/elf.h> +#include <linux/module.h> +#include <linux/moduleloader.h> +#include <linux/vmalloc.h> + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(fmt , ...) +#endif + +/* + * module_frob_arch_sections - tweak got/plt sections. + * @hdr - pointer to elf header + * @sechdrs - pointer to elf load section headers + * @secstrings - symbol names + * @mod - pointer to module + */ +int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, + char *secstrings, + struct module *mod) +{ + unsigned int i; + int found = 0; + + /* Look for .plt and/or .got.plt and/or .init.plt sections */ + for (i = 0; i < hdr->e_shnum; i++) { + DEBUGP("Section %d is %s\n", i, + secstrings + sechdrs[i].sh_name); + if (strcmp(secstrings + sechdrs[i].sh_name, ".plt") == 0) + found = i+1; + if (strcmp(secstrings + sechdrs[i].sh_name, ".got.plt") == 0) + found = i+1; + if (strcmp(secstrings + sechdrs[i].sh_name, ".rela.plt") == 0) + found = i+1; + } + + /* At this time, we don't support modules comiled with -shared */ + if (found) { + printk(KERN_WARNING + "Module '%s' contains unexpected .plt/.got sections.\n", + mod->name); + /* return -ENOEXEC; */ + } + + return 0; +} + +/* + * apply_relocate_add - perform rela relocations. + * @sechdrs - pointer to section headers + * @strtab - some sort of start address? + * @symindex - symbol index offset or something? + * @relsec - address to relocate to? + * @module - pointer to module + * + * Perform rela relocations. + */ +int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, + unsigned int symindex, unsigned int relsec, + struct module *module) +{ + unsigned int i; + Elf32_Sym *sym; + uint32_t *location; + uint32_t value; + unsigned int nrelocs = sechdrs[relsec].sh_size / sizeof(Elf32_Rela); + Elf32_Rela *rela = (void *)sechdrs[relsec].sh_addr; + Elf32_Word sym_info = sechdrs[relsec].sh_info; + Elf32_Sym *sym_base = (Elf32_Sym *) sechdrs[symindex].sh_addr; + void *loc_base = (void *) sechdrs[sym_info].sh_addr; + + DEBUGP("Applying relocations in section %u to section %u base=%p\n", + relsec, sym_info, loc_base); + + for (i = 0; i < nrelocs; i++) { + + /* Symbol to relocate */ + sym = sym_base + ELF32_R_SYM(rela[i].r_info); + + /* Where to make the change */ + location = loc_base + rela[i].r_offset; + + /* `Everything is relative'. */ + value = sym->st_value + rela[i].r_addend; + + DEBUGP("%d: value=%08x loc=%p reloc=%d symbol=%s\n", + i, value, location, ELF32_R_TYPE(rela[i].r_info), + sym->st_name ? + &strtab[sym->st_name] : "(anonymous)"); + + switch (ELF32_R_TYPE(rela[i].r_info)) { + case R_HEXAGON_B22_PCREL: { + int dist = (int)(value - (uint32_t)location); + if ((dist < -0x00800000) || + (dist >= 0x00800000)) { + printk(KERN_ERR + "%s: %s: %08x=%08x-%08x %s\n", + module->name, + "R_HEXAGON_B22_PCREL reloc out of range", + dist, value, (uint32_t)location, + sym->st_name ? + &strtab[sym->st_name] : "(anonymous)"); + return -ENOEXEC; + } + DEBUGP("B22_PCREL contents: %08X.\n", *location); + *location &= ~0x01ff3fff; + *location |= 0x00003fff & dist; + *location |= 0x01ff0000 & (dist<<2); + DEBUGP("Contents after reloc: %08x\n", *location); + break; + } + case R_HEXAGON_HI16: + value = (value>>16) & 0xffff; + /* fallthrough */ + case R_HEXAGON_LO16: + *location &= ~0x00c03fff; + *location |= value & 0x3fff; + *location |= (value & 0xc000) << 8; + break; + case R_HEXAGON_32: + *location = value; + break; + case R_HEXAGON_32_PCREL: + *location = value - (uint32_t)location; + break; + case R_HEXAGON_PLT_B22_PCREL: + case R_HEXAGON_GOTOFF_LO16: + case R_HEXAGON_GOTOFF_HI16: + printk(KERN_ERR "%s: GOT/PLT relocations unsupported\n", + module->name); + return -ENOEXEC; + default: + printk(KERN_ERR "%s: unknown relocation: %u\n", + module->name, + ELF32_R_TYPE(rela[i].r_info)); + return -ENOEXEC; + } + } + return 0; +} diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c new file mode 100644 index 000000000000..18c4f0b0f4ba --- /dev/null +++ b/arch/hexagon/kernel/process.c @@ -0,0 +1,279 @@ +/* + * Process creation support for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/sched.h> +#include <linux/types.h> +#include <linux/module.h> +#include <linux/tick.h> +#include <linux/uaccess.h> +#include <linux/slab.h> + +/* + * Kernel thread creation. The desired kernel function is "wrapped" + * in the kernel_thread_helper function, which does cleanup + * afterwards. + */ +static void __noreturn kernel_thread_helper(void *arg, int (*fn)(void *)) +{ + do_exit(fn(arg)); +} + +int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) +{ + struct pt_regs regs; + + memset(®s, 0, sizeof(regs)); + /* + * Yes, we're exploting illicit knowledge of the ABI here. + */ + regs.r00 = (unsigned long) arg; + regs.r01 = (unsigned long) fn; + pt_set_elr(®s, (unsigned long)kernel_thread_helper); + pt_set_kmode(®s); + + return do_fork(flags|CLONE_VM|CLONE_UNTRACED, 0, ®s, 0, NULL, NULL); +} +EXPORT_SYMBOL(kernel_thread); + +/* + * Program thread launch. Often defined as a macro in processor.h, + * but we're shooting for a small footprint and it's not an inner-loop + * performance-critical operation. + * + * The Hexagon ABI specifies that R28 is zero'ed before program launch, + * so that gets automatically done here. If we ever stop doing that here, + * we'll probably want to define the ELF_PLAT_INIT macro. + */ +void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) +{ + /* Set to run with user-mode data segmentation */ + set_fs(USER_DS); + /* We want to zero all data-containing registers. Is this overkill? */ + memset(regs, 0, sizeof(*regs)); + /* We might want to also zero all Processor registers here */ + pt_set_usermode(regs); + pt_set_elr(regs, pc); + pt_set_rte_sp(regs, sp); +} + +/* + * Spin, or better still, do a hardware or VM wait instruction + * If hardware or VM offer wait termination even though interrupts + * are disabled. + */ +static void default_idle(void) +{ + __vmwait(); +} + +void (*idle_sleep)(void) = default_idle; + +void cpu_idle(void) +{ + while (1) { + tick_nohz_stop_sched_tick(1); + local_irq_disable(); + while (!need_resched()) { + idle_sleep(); + /* interrupts wake us up, but aren't serviced */ + local_irq_enable(); /* service interrupt */ + local_irq_disable(); + } + local_irq_enable(); + tick_nohz_restart_sched_tick(); + schedule(); + } +} + +/* + * Return saved PC of a blocked thread + */ +unsigned long thread_saved_pc(struct task_struct *tsk) +{ + return 0; +} + +/* + * Copy architecture-specific thread state + */ +int copy_thread(unsigned long clone_flags, unsigned long usp, + unsigned long unused, struct task_struct *p, + struct pt_regs *regs) +{ + struct thread_info *ti = task_thread_info(p); + struct hexagon_switch_stack *ss; + struct pt_regs *childregs; + asmlinkage void ret_from_fork(void); + + childregs = (struct pt_regs *) (((unsigned long) ti + THREAD_SIZE) - + sizeof(*childregs)); + + memcpy(childregs, regs, sizeof(*childregs)); + ti->regs = childregs; + + /* + * Establish kernel stack pointer and initial PC for new thread + */ + ss = (struct hexagon_switch_stack *) ((unsigned long) childregs - + sizeof(*ss)); + ss->lr = (unsigned long)ret_from_fork; + p->thread.switch_sp = ss; + + /* If User mode thread, set pt_reg stack pointer as per parameter */ + if (user_mode(childregs)) { + pt_set_rte_sp(childregs, usp); + + /* Child sees zero return value */ + childregs->r00 = 0; + + /* + * The clone syscall has the C signature: + * int [r0] clone(int flags [r0], + * void *child_frame [r1], + * void *parent_tid [r2], + * void *child_tid [r3], + * void *thread_control_block [r4]); + * ugp is used to provide TLS support. + */ + if (clone_flags & CLONE_SETTLS) + childregs->ugp = childregs->r04; + + /* + * Parent sees new pid -- not necessary, not even possible at + * this point in the fork process + * Might also want to set things like ti->addr_limit + */ + } else { + /* + * If kernel thread, resume stack is kernel stack base. + * Note that this is pointer arithmetic on pt_regs * + */ + pt_set_rte_sp(childregs, (unsigned long)(childregs + 1)); + /* + * We need the current thread_info fast path pointer + * set up in pt_regs. The register to be used is + * parametric for assembler code, but the mechanism + * doesn't drop neatly into C. Needs to be fixed. + */ + childregs->THREADINFO_REG = (unsigned long) ti; + } + + /* + * thread_info pointer is pulled out of task_struct "stack" + * field on switch_to. + */ + p->stack = (void *)ti; + + return 0; +} + +/* + * Release any architecture-specific resources locked by thread + */ +void release_thread(struct task_struct *dead_task) +{ +} + +/* + * Free any architecture-specific thread data structures, etc. + */ +void exit_thread(void) +{ +} + +/* + * Some archs flush debug and FPU info here + */ +void flush_thread(void) +{ +} + +/* + * The "wait channel" terminology is archaic, but what we want + * is an identification of the point at which the scheduler + * was invoked by a blocked thread. + */ +unsigned long get_wchan(struct task_struct *p) +{ + unsigned long fp, pc; + unsigned long stack_page; + int count = 0; + if (!p || p == current || p->state == TASK_RUNNING) + return 0; + + stack_page = (unsigned long)task_stack_page(p); + fp = ((struct hexagon_switch_stack *)p->thread.switch_sp)->fp; + do { + if (fp < (stack_page + sizeof(struct thread_info)) || + fp >= (THREAD_SIZE - 8 + stack_page)) + return 0; + pc = ((unsigned long *)fp)[1]; + if (!in_sched_functions(pc)) + return pc; + fp = *(unsigned long *) fp; + } while (count++ < 16); + + return 0; +} + +/* + * Borrowed from PowerPC -- basically allow smaller kernel stacks if we + * go crazy with the page sizes. + */ +#if THREAD_SHIFT < PAGE_SHIFT + +static struct kmem_cache *thread_info_cache; + +struct thread_info *alloc_thread_info_node(struct task_struct *tsk, int node) +{ + struct thread_info *ti; + + ti = kmem_cache_alloc_node(thread_info_cache, GFP_KERNEL, node); + if (unlikely(ti == NULL)) + return NULL; +#ifdef CONFIG_DEBUG_STACK_USAGE + memset(ti, 0, THREAD_SIZE); +#endif + return ti; +} + +void free_thread_info(struct thread_info *ti) +{ + kmem_cache_free(thread_info_cache, ti); +} + +/* Weak symbol; called by init/main.c */ + +void thread_info_cache_init(void) +{ + thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE, + THREAD_SIZE, 0, NULL); + BUG_ON(thread_info_cache == NULL); +} + +#endif /* THREAD_SHIFT < PAGE_SHIFT */ + +/* + * Required placeholder. + */ +int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) +{ + return 0; +} diff --git a/arch/hexagon/kernel/ptrace.c b/arch/hexagon/kernel/ptrace.c new file mode 100644 index 000000000000..bea3f08470fd --- /dev/null +++ b/arch/hexagon/kernel/ptrace.c @@ -0,0 +1,180 @@ +/* + * Ptrace support for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <generated/compile.h> + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/errno.h> +#include <linux/ptrace.h> +#include <linux/regset.h> +#include <linux/user.h> + +#include <asm/system.h> +#include <asm/user.h> + +static int genregs_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + unsigned int dummy; + struct pt_regs *regs = task_pt_regs(target); + + + if (!regs) + return -EIO; + + /* The general idea here is that the copyout must happen in + * exactly the same order in which the userspace expects these + * regs. Now, the sequence in userspace does not match the + * sequence in the kernel, so everything past the 32 gprs + * happens one at a time. + */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + ®s->r00, 0, 32*sizeof(unsigned long)); + +#define ONEXT(KPT_REG, USR_REG) \ + if (!ret) \ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, \ + KPT_REG, offsetof(struct user_regs_struct, USR_REG), \ + offsetof(struct user_regs_struct, USR_REG) + \ + sizeof(unsigned long)); + + /* Must be exactly same sequence as struct user_regs_struct */ + ONEXT(®s->sa0, sa0); + ONEXT(®s->lc0, lc0); + ONEXT(®s->sa1, sa1); + ONEXT(®s->lc1, lc1); + ONEXT(®s->m0, m0); + ONEXT(®s->m1, m1); + ONEXT(®s->usr, usr); + ONEXT(®s->preds, p3_0); + ONEXT(®s->gp, gp); + ONEXT(®s->ugp, ugp); + ONEXT(&pt_elr(regs), pc); + dummy = pt_cause(regs); + ONEXT(&dummy, cause); + ONEXT(&pt_badva(regs), badva); + + /* Pad the rest with zeros, if needed */ + if (!ret) + ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, + offsetof(struct user_regs_struct, pad1), -1); + return ret; +} + +static int genregs_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + unsigned long bucket; + struct pt_regs *regs = task_pt_regs(target); + + if (!regs) + return -EIO; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + ®s->r00, 0, 32*sizeof(unsigned long)); + +#define INEXT(KPT_REG, USR_REG) \ + if (!ret) \ + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, \ + KPT_REG, offsetof(struct user_regs_struct, USR_REG), \ + offsetof(struct user_regs_struct, USR_REG) + \ + sizeof(unsigned long)); + + /* Must be exactly same sequence as struct user_regs_struct */ + INEXT(®s->sa0, sa0); + INEXT(®s->lc0, lc0); + INEXT(®s->sa1, sa1); + INEXT(®s->lc1, lc1); + INEXT(®s->m0, m0); + INEXT(®s->m1, m1); + INEXT(®s->usr, usr); + INEXT(®s->preds, p3_0); + INEXT(®s->gp, gp); + INEXT(®s->ugp, ugp); + INEXT(&pt_elr(regs), pc); + + /* CAUSE and BADVA aren't writeable. */ + INEXT(&bucket, cause); + INEXT(&bucket, badva); + + /* Ignore the rest, if needed */ + if (!ret) + ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, + offsetof(struct user_regs_struct, pad1), -1); + + if (ret) + return ret; + + /* + * This is special; SP is actually restored by the VM via the + * special event record which is set by the special trap. + */ + regs->hvmer.vmpsp = regs->r29; + return 0; +} + +enum hexagon_regset { + REGSET_GENERAL, +}; + +static const struct user_regset hexagon_regsets[] = { + [REGSET_GENERAL] = { + .core_note_type = NT_PRSTATUS, + .n = ELF_NGREG, + .size = sizeof(unsigned long), + .align = sizeof(unsigned long), + .get = genregs_get, + .set = genregs_set, + }, +}; + +static const struct user_regset_view hexagon_user_view = { + .name = UTS_MACHINE, + .e_machine = ELF_ARCH, + .ei_osabi = ELF_OSABI, + .regsets = hexagon_regsets, + .n = ARRAY_SIZE(hexagon_regsets) +}; + +const struct user_regset_view *task_user_regset_view(struct task_struct *task) +{ + return &hexagon_user_view; +} + +void ptrace_disable(struct task_struct *child) +{ + /* Boilerplate - resolves to null inline if no HW single-step */ + user_disable_single_step(child); +} + +long arch_ptrace(struct task_struct *child, long request, + unsigned long addr, unsigned long data) +{ + return ptrace_request(child, request, addr, data); +} diff --git a/arch/hexagon/kernel/reset.c b/arch/hexagon/kernel/reset.c new file mode 100644 index 000000000000..4d72fc58e9b1 --- /dev/null +++ b/arch/hexagon/kernel/reset.c @@ -0,0 +1,38 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/smp.h> +#include <asm/hexagon_vm.h> + +void machine_power_off(void) +{ + smp_send_stop(); + __vmstop(); +} + +void machine_halt(void) +{ +} + +void machine_restart(char *cmd) +{ +} + +void pm_power_off(void) +{ +} diff --git a/arch/hexagon/kernel/setup.c b/arch/hexagon/kernel/setup.c new file mode 100644 index 000000000000..1202f78d25cb --- /dev/null +++ b/arch/hexagon/kernel/setup.c @@ -0,0 +1,145 @@ +/* + * Arch related setup for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/init.h> +#include <linux/bootmem.h> +#include <linux/mmzone.h> +#include <linux/mm.h> +#include <linux/seq_file.h> +#include <linux/console.h> +#include <linux/of_fdt.h> +#include <asm/io.h> +#include <asm/sections.h> +#include <asm/setup.h> +#include <asm/processor.h> +#include <asm/hexagon_vm.h> +#include <asm/vm_mmu.h> +#include <asm/time.h> +#ifdef CONFIG_OF +#include <asm/prom.h> +#endif + +char cmd_line[COMMAND_LINE_SIZE]; +static char default_command_line[COMMAND_LINE_SIZE] __initdata = CONFIG_CMDLINE; + +int on_simulator; + +void __cpuinit calibrate_delay(void) +{ + loops_per_jiffy = thread_freq_mhz * 1000000 / HZ; +} + +/* + * setup_arch - high level architectural setup routine + * @cmdline_p: pointer to pointer to command-line arguments + */ + +void __init setup_arch(char **cmdline_p) +{ + char *p = &external_cmdline_buffer; + + /* + * These will eventually be pulled in via either some hypervisor + * or devicetree description. Hardwiring for now. + */ + pcycle_freq_mhz = 600; + thread_freq_mhz = 100; + sleep_clk_freq = 32000; + + /* + * Set up event bindings to handle exceptions and interrupts. + */ + __vmsetvec(_K_VM_event_vector); + + /* + * Simulator has a few differences from the hardware. + * For now, check uninitialized-but-mapped memory + * prior to invoking setup_arch_memory(). + */ + if (*(int *)((unsigned long)_end + 8) == 0x1f1f1f1f) + on_simulator = 1; + else + on_simulator = 0; + + if (p[0] != '\0') + strlcpy(boot_command_line, p, COMMAND_LINE_SIZE); + else + strlcpy(boot_command_line, default_command_line, + COMMAND_LINE_SIZE); + + /* + * boot_command_line and the value set up by setup_arch + * are both picked up by the init code. If no reason to + * make them different, pass the same pointer back. + */ + strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE); + *cmdline_p = cmd_line; + + parse_early_param(); + + setup_arch_memory(); + +#ifdef CONFIG_SMP + smp_start_cpus(); +#endif +} + +/* + * Functions for dumping CPU info via /proc + * Probably should move to kernel/proc.c or something. + */ +static void *c_start(struct seq_file *m, loff_t *pos) +{ + return *pos < nr_cpu_ids ? (void *)((unsigned long) *pos + 1) : NULL; +} + +static void *c_next(struct seq_file *m, void *v, loff_t *pos) +{ + ++*pos; + return c_start(m, pos); +} + +static void c_stop(struct seq_file *m, void *v) +{ +} + +/* + * Eventually this will dump information about + * CPU properties like ISA level, TLB size, etc. + */ +static int show_cpuinfo(struct seq_file *m, void *v) +{ + int cpu = (unsigned long) v - 1; + + seq_printf(m, "processor\t: %d\n", cpu); + seq_printf(m, "model name\t: Hexagon Virtual Machine\n"); + seq_printf(m, "BogoMips\t: %lu.%02lu\n", + (loops_per_jiffy * HZ) / 500000, + ((loops_per_jiffy * HZ) / 5000) % 100); + seq_printf(m, "\n"); + return 0; +} + +const struct seq_operations cpuinfo_op = { + .start = &c_start, + .next = &c_next, + .stop = &c_stop, + .show = &show_cpuinfo, +}; diff --git a/arch/hexagon/kernel/signal.c b/arch/hexagon/kernel/signal.c new file mode 100644 index 000000000000..b45be3181193 --- /dev/null +++ b/arch/hexagon/kernel/signal.c @@ -0,0 +1,345 @@ +/* + * Signal support for Hexagon processor + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/linkage.h> +#include <linux/syscalls.h> +#include <linux/freezer.h> +#include <linux/tracehook.h> +#include <asm/registers.h> +#include <asm/thread_info.h> +#include <asm/unistd.h> +#include <asm/uaccess.h> +#include <asm/ucontext.h> +#include <asm/cacheflush.h> +#include <asm/signal.h> +#include <asm/vdso.h> + +#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) + +struct rt_sigframe { + unsigned long tramp[2]; + struct siginfo info; + struct ucontext uc; +}; + +static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, + size_t frame_size) +{ + unsigned long sp = regs->r29; + + /* Switch to signal stack if appropriate */ + if ((ka->sa.sa_flags & SA_ONSTACK) && (sas_ss_flags(sp) == 0)) + sp = current->sas_ss_sp + current->sas_ss_size; + + return (void __user *)((sp - frame_size) & ~(sizeof(long long) - 1)); +} + +static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) +{ + unsigned long tmp; + int err = 0; + + err |= copy_to_user(&sc->sc_regs.r0, ®s->r00, + 32*sizeof(unsigned long)); + + err |= __put_user(regs->sa0, &sc->sc_regs.sa0); + err |= __put_user(regs->lc0, &sc->sc_regs.lc0); + err |= __put_user(regs->sa1, &sc->sc_regs.sa1); + err |= __put_user(regs->lc1, &sc->sc_regs.lc1); + err |= __put_user(regs->m0, &sc->sc_regs.m0); + err |= __put_user(regs->m1, &sc->sc_regs.m1); + err |= __put_user(regs->usr, &sc->sc_regs.usr); + err |= __put_user(regs->preds, &sc->sc_regs.p3_0); + err |= __put_user(regs->gp, &sc->sc_regs.gp); + err |= __put_user(regs->ugp, &sc->sc_regs.ugp); + + tmp = pt_elr(regs); err |= __put_user(tmp, &sc->sc_regs.pc); + tmp = pt_cause(regs); err |= __put_user(tmp, &sc->sc_regs.cause); + tmp = pt_badva(regs); err |= __put_user(tmp, &sc->sc_regs.badva); + + return err; +} + +static int restore_sigcontext(struct pt_regs *regs, + struct sigcontext __user *sc) +{ + unsigned long tmp; + int err = 0; + + err |= copy_from_user(®s->r00, &sc->sc_regs.r0, + 32 * sizeof(unsigned long)); + + err |= __get_user(regs->sa0, &sc->sc_regs.sa0); + err |= __get_user(regs->lc0, &sc->sc_regs.lc0); + err |= __get_user(regs->sa1, &sc->sc_regs.sa1); + err |= __get_user(regs->lc1, &sc->sc_regs.lc1); + err |= __get_user(regs->m0, &sc->sc_regs.m0); + err |= __get_user(regs->m1, &sc->sc_regs.m1); + err |= __get_user(regs->usr, &sc->sc_regs.usr); + err |= __get_user(regs->preds, &sc->sc_regs.p3_0); + err |= __get_user(regs->gp, &sc->sc_regs.gp); + err |= __get_user(regs->ugp, &sc->sc_regs.ugp); + + err |= __get_user(tmp, &sc->sc_regs.pc); pt_set_elr(regs, tmp); + + return err; +} + +/* + * Setup signal stack frame with siginfo structure + */ +static int setup_rt_frame(int signr, struct k_sigaction *ka, siginfo_t *info, + sigset_t *set, struct pt_regs *regs) +{ + int err = 0; + struct rt_sigframe __user *frame; + struct hexagon_vdso *vdso = current->mm->context.vdso; + + frame = get_sigframe(ka, regs, sizeof(struct rt_sigframe)); + + if (!access_ok(VERIFY_WRITE, frame, sizeof(struct rt_sigframe))) + goto sigsegv; + + if (copy_siginfo_to_user(&frame->info, info)) + goto sigsegv; + + /* The on-stack signal trampoline is no longer executed; + * however, the libgcc signal frame unwinding code checks for + * the presence of these two numeric magic values. + */ + err |= __put_user(0x7800d166, &frame->tramp[0]); + err |= __put_user(0x5400c004, &frame->tramp[1]); + err |= setup_sigcontext(regs, &frame->uc.uc_mcontext); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) + goto sigsegv; + + /* Load r0/r1 pair with signumber/siginfo pointer... */ + regs->r0100 = ((unsigned long long)((unsigned long)&frame->info) << 32) + | (unsigned long long)signr; + regs->r02 = (unsigned long) &frame->uc; + regs->r31 = (unsigned long) vdso->rt_signal_trampoline; + pt_psp(regs) = (unsigned long) frame; + pt_set_elr(regs, (unsigned long)ka->sa.sa_handler); + + return 0; + +sigsegv: + force_sigsegv(signr, current); + return -EFAULT; +} + +/* + * Setup invocation of signal handler + */ +static int handle_signal(int sig, siginfo_t *info, struct k_sigaction *ka, + sigset_t *oldset, struct pt_regs *regs) +{ + int rc; + + /* + * If we're handling a signal that aborted a system call, + * set up the error return value before adding the signal + * frame to the stack. + */ + + if (regs->syscall_nr >= 0) { + switch (regs->r00) { + case -ERESTART_RESTARTBLOCK: + case -ERESTARTNOHAND: + regs->r00 = -EINTR; + break; + case -ERESTARTSYS: + if (!(ka->sa.sa_flags & SA_RESTART)) { + regs->r00 = -EINTR; + break; + } + /* Fall through */ + case -ERESTARTNOINTR: + regs->r06 = regs->syscall_nr; + pt_set_elr(regs, pt_elr(regs) - 4); + regs->r00 = regs->restart_r0; + break; + default: + break; + } + } + + /* + * Set up the stack frame; not doing the SA_SIGINFO thing. We + * only set up the rt_frame flavor. + */ + rc = setup_rt_frame(sig, ka, info, oldset, regs); + + /* If there was an error on setup, no signal was delivered. */ + if (rc) + return rc; + + spin_lock_irq(¤t->sighand->siglock); + sigorsets(¤t->blocked, ¤t->blocked, &ka->sa.sa_mask); + if (!(ka->sa.sa_flags & SA_NODEFER)) + sigaddset(¤t->blocked, sig); + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + + return 0; +} + +/* + * Called from return-from-event code. + */ +static void do_signal(struct pt_regs *regs) +{ + struct k_sigaction sigact; + siginfo_t info; + int signo; + + if (!user_mode(regs)) + return; + + if (try_to_freeze()) + goto no_signal; + + signo = get_signal_to_deliver(&info, &sigact, regs, NULL); + + if (signo > 0) { + sigset_t *oldset; + + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + oldset = ¤t->saved_sigmask; + else + oldset = ¤t->blocked; + + if (handle_signal(signo, &info, &sigact, oldset, regs) == 0) { + /* + * Successful delivery case. The saved sigmask is + * stored in the signal frame, and will be restored + * by sigreturn. We can clear the TIF flag. + */ + clear_thread_flag(TIF_RESTORE_SIGMASK); + + tracehook_signal_handler(signo, &info, &sigact, regs, + test_thread_flag(TIF_SINGLESTEP)); + } + return; + } + +no_signal: + /* + * If we came from a system call, handle the restart. + */ + if (regs->syscall_nr >= 0) { + switch (regs->r00) { + case -ERESTARTNOHAND: + case -ERESTARTSYS: + case -ERESTARTNOINTR: + regs->r06 = regs->syscall_nr; + break; + case -ERESTART_RESTARTBLOCK: + regs->r06 = __NR_restart_syscall; + break; + default: + goto no_restart; + } + pt_set_elr(regs, pt_elr(regs) - 4); + regs->r00 = regs->restart_r0; + } + +no_restart: + /* If there's no signal to deliver, put the saved sigmask back */ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) { + clear_thread_flag(TIF_RESTORE_SIGMASK); + sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + } +} + +void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) +{ + if (thread_info_flags & _TIF_SIGPENDING) + do_signal(regs); + + if (thread_info_flags & _TIF_NOTIFY_RESUME) { + clear_thread_flag(TIF_NOTIFY_RESUME); + if (current->replacement_session_keyring) + key_replace_session_keyring(); + } +} + +/* + * Architecture-specific wrappers for signal-related system calls + */ +asmlinkage int sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss) +{ + struct pt_regs *regs = current_thread_info()->regs; + + return do_sigaltstack(uss, uoss, regs->r29); +} + +asmlinkage int sys_rt_sigreturn(void) +{ + struct pt_regs *regs = current_thread_info()->regs; + struct rt_sigframe __user *frame; + sigset_t blocked; + + frame = (struct rt_sigframe __user *)pt_psp(regs); + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_from_user(&blocked, &frame->uc.uc_sigmask, sizeof(blocked))) + goto badframe; + + sigdelsetmask(&blocked, ~_BLOCKABLE); + spin_lock_irq(¤t->sighand->siglock); + current->blocked = blocked; + recalc_sigpending(); + spin_unlock_irq(¤t->sighand->siglock); + + if (restore_sigcontext(regs, &frame->uc.uc_mcontext)) + goto badframe; + + /* Restore the user's stack as well */ + pt_psp(regs) = regs->r29; + + /* + * Leave a trace in the stack frame that this was a sigreturn. + * If the system call is to replay, we've already restored the + * number in the GPR slot and it will be regenerated on the + * new system call trap entry. Note that if restore_sigcontext() + * did something other than a bulk copy of the pt_regs struct, + * we could avoid this assignment by simply not overwriting + * regs->syscall_nr. + */ + regs->syscall_nr = __NR_rt_sigreturn; + + /* + * If we were meticulous, we'd only call this if we knew that + * we were actually going to use an alternate stack, and we'd + * consider any error to be fatal. What we do here, in common + * with many other architectures, is call it blindly and only + * consider the -EFAULT return case to be proof of a problem. + */ + if (do_sigaltstack(&frame->uc.uc_stack, NULL, pt_psp(regs)) == -EFAULT) + goto badframe; + + return 0; + +badframe: + force_sig(SIGSEGV, current); + return 0; +} diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c new file mode 100644 index 000000000000..c871a2cffaef --- /dev/null +++ b/arch/hexagon/kernel/smp.c @@ -0,0 +1,276 @@ +/* + * SMP support for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/sched.h> +#include <linux/smp.h> +#include <linux/spinlock.h> + +#include <asm/system.h> /* xchg */ +#include <asm/time.h> /* timer_interrupt */ +#include <asm/hexagon_vm.h> + +#define BASE_IPI_IRQ 26 + +/* + * cpu_possible_map needs to be filled out prior to setup_per_cpu_areas + * (which is prior to any of our smp_prepare_cpu crap), in order to set + * up the... per_cpu areas. + */ + +struct ipi_data { + unsigned long bits; +}; + +static DEFINE_PER_CPU(struct ipi_data, ipi_data); + +static inline void __handle_ipi(unsigned long *ops, struct ipi_data *ipi, + int cpu) +{ + unsigned long msg = 0; + do { + msg = find_next_bit(ops, BITS_PER_LONG, msg+1); + + switch (msg) { + + case IPI_TIMER: + ipi_timer(); + break; + + case IPI_CALL_FUNC: + generic_smp_call_function_interrupt(); + break; + + case IPI_CALL_FUNC_SINGLE: + generic_smp_call_function_single_interrupt(); + break; + + case IPI_CPU_STOP: + /* + * call vmstop() + */ + __vmstop(); + break; + + case IPI_RESCHEDULE: + scheduler_ipi(); + break; + } + } while (msg < BITS_PER_LONG); +} + +/* Used for IPI call from other CPU's to unmask int */ +void smp_vm_unmask_irq(void *info) +{ + __vmintop_locen((long) info); +} + + +/* + * This is based on Alpha's IPI stuff. + * Supposed to take (int, void*) as args now. + * Specifically, first arg is irq, second is the irq_desc. + */ + +irqreturn_t handle_ipi(int irq, void *desc) +{ + int cpu = smp_processor_id(); + struct ipi_data *ipi = &per_cpu(ipi_data, cpu); + unsigned long ops; + + while ((ops = xchg(&ipi->bits, 0)) != 0) + __handle_ipi(&ops, ipi, cpu); + return IRQ_HANDLED; +} + +void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg) +{ + unsigned long flags; + unsigned long cpu; + unsigned long retval; + + local_irq_save(flags); + + for_each_cpu(cpu, cpumask) { + struct ipi_data *ipi = &per_cpu(ipi_data, cpu); + + set_bit(msg, &ipi->bits); + /* Possible barrier here */ + retval = __vmintop_post(BASE_IPI_IRQ+cpu); + + if (retval != 0) { + printk(KERN_ERR "interrupt %ld not configured?\n", + BASE_IPI_IRQ+cpu); + } + } + + local_irq_restore(flags); +} + +static struct irqaction ipi_intdesc = { + .handler = handle_ipi, + .flags = IRQF_TRIGGER_RISING, + .name = "ipi_handler" +}; + +void __init smp_prepare_boot_cpu(void) +{ +} + +/* + * interrupts should already be disabled from the VM + * SP should already be correct; need to set THREADINFO_REG + * to point to current thread info + */ + +void __cpuinit start_secondary(void) +{ + unsigned int cpu; + unsigned long thread_ptr; + + /* Calculate thread_info pointer from stack pointer */ + __asm__ __volatile__( + "%0 = SP;\n" + : "=r" (thread_ptr) + ); + + thread_ptr = thread_ptr & ~(THREAD_SIZE-1); + + __asm__ __volatile__( + QUOTED_THREADINFO_REG " = %0;\n" + : + : "r" (thread_ptr) + ); + + /* Set the memory struct */ + atomic_inc(&init_mm.mm_count); + current->active_mm = &init_mm; + + cpu = smp_processor_id(); + + setup_irq(BASE_IPI_IRQ + cpu, &ipi_intdesc); + + /* Register the clock_event dummy */ + setup_percpu_clockdev(); + + printk(KERN_INFO "%s cpu %d\n", __func__, current_thread_info()->cpu); + + set_cpu_online(cpu, true); + while (!cpumask_test_cpu(cpu, cpu_active_mask)) + cpu_relax(); + local_irq_enable(); + + cpu_idle(); +} + + +/* + * called once for each present cpu + * apparently starts up the CPU and then + * maintains control until "cpu_online(cpu)" is set. + */ + +int __cpuinit __cpu_up(unsigned int cpu) +{ + struct task_struct *idle; + struct thread_info *thread; + void *stack_start; + + /* Create new init task for the CPU */ + idle = fork_idle(cpu); + if (IS_ERR(idle)) + panic(KERN_ERR "fork_idle failed\n"); + + thread = (struct thread_info *)idle->stack; + thread->cpu = cpu; + + /* Boot to the head. */ + stack_start = ((void *) thread) + THREAD_SIZE; + __vmstart(start_secondary, stack_start); + + while (!cpu_isset(cpu, cpu_online_map)) + barrier(); + + return 0; +} + +void __init smp_cpus_done(unsigned int max_cpus) +{ +} + +void __init smp_prepare_cpus(unsigned int max_cpus) +{ + int i; + + /* + * should eventually have some sort of machine + * descriptor that has this stuff + */ + + /* Right now, let's just fake it. */ + for (i = 0; i < max_cpus; i++) + cpu_set(i, cpu_present_map); + + /* Also need to register the interrupts for IPI */ + if (max_cpus > 1) + setup_irq(BASE_IPI_IRQ, &ipi_intdesc); +} + +void smp_send_reschedule(int cpu) +{ + send_ipi(cpumask_of(cpu), IPI_RESCHEDULE); +} + +void smp_send_stop(void) +{ + struct cpumask targets; + cpumask_copy(&targets, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &targets); + send_ipi(&targets, IPI_CPU_STOP); +} + +void arch_send_call_function_single_ipi(int cpu) +{ + send_ipi(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE); +} + +void arch_send_call_function_ipi_mask(const struct cpumask *mask) +{ + send_ipi(mask, IPI_CALL_FUNC); +} + +int setup_profiling_timer(unsigned int multiplier) +{ + return -EINVAL; +} + +void smp_start_cpus(void) +{ + int i; + + for (i = 0; i < NR_CPUS; i++) + cpu_set(i, cpu_possible_map); +} diff --git a/arch/hexagon/kernel/stacktrace.c b/arch/hexagon/kernel/stacktrace.c new file mode 100644 index 000000000000..11c597b2ac59 --- /dev/null +++ b/arch/hexagon/kernel/stacktrace.c @@ -0,0 +1,66 @@ +/* + * Stacktrace support for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/sched.h> +#include <linux/stacktrace.h> +#include <linux/thread_info.h> +#include <linux/module.h> + +register unsigned long current_frame_pointer asm("r30"); + +struct stackframe { + unsigned long fp; + unsigned long rets; +}; + +/* + * Save stack-backtrace addresses into a stack_trace buffer. + */ +void save_stack_trace(struct stack_trace *trace) +{ + unsigned long low, high; + unsigned long fp; + struct stackframe *frame; + int skip = trace->skip; + + low = (unsigned long)task_stack_page(current); + high = low + THREAD_SIZE; + fp = current_frame_pointer; + + while (fp >= low && fp <= (high - sizeof(*frame))) { + frame = (struct stackframe *)fp; + + if (skip) { + skip--; + } else { + trace->entries[trace->nr_entries++] = frame->rets; + if (trace->nr_entries >= trace->max_entries) + break; + } + + /* + * The next frame must be at a higher address than the + * current frame. + */ + low = fp + sizeof(*frame); + fp = frame->fp; + } +} +EXPORT_SYMBOL_GPL(save_stack_trace); diff --git a/arch/hexagon/kernel/syscall.c b/arch/hexagon/kernel/syscall.c new file mode 100644 index 000000000000..620dd18197a0 --- /dev/null +++ b/arch/hexagon/kernel/syscall.c @@ -0,0 +1,90 @@ +/* + * Hexagon system calls + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/linkage.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/syscalls.h> +#include <linux/unistd.h> +#include <asm/mman.h> +#include <asm/registers.h> + +/* + * System calls with architecture-specific wrappers. + * See signal.c for signal-related system call wrappers. + */ + +asmlinkage int sys_execve(char __user *ufilename, + const char __user *const __user *argv, + const char __user *const __user *envp) +{ + struct pt_regs *pregs = current_thread_info()->regs; + char *filename; + int retval; + + filename = getname(ufilename); + retval = PTR_ERR(filename); + if (IS_ERR(filename)) + return retval; + + retval = do_execve(filename, argv, envp, pregs); + putname(filename); + + return retval; +} + +asmlinkage int sys_clone(unsigned long clone_flags, unsigned long newsp, + unsigned long parent_tidp, unsigned long child_tidp) +{ + struct pt_regs *pregs = current_thread_info()->regs; + + if (!newsp) + newsp = pregs->SP; + return do_fork(clone_flags, newsp, pregs, 0, (int __user *)parent_tidp, + (int __user *)child_tidp); +} + +/* + * Do a system call from the kernel, so as to have a proper pt_regs + * and recycle the sys_execvpe infrustructure. + */ +int kernel_execve(const char *filename, + const char *const argv[], const char *const envp[]) +{ + register unsigned long __a0 asm("r0") = (unsigned long) filename; + register unsigned long __a1 asm("r1") = (unsigned long) argv; + register unsigned long __a2 asm("r2") = (unsigned long) envp; + int retval; + + __asm__ volatile( + " R6 = #%4;\n" + " trap0(#1);\n" + " %0 = R0;\n" + : "=r" (retval) + : "r" (__a0), "r" (__a1), "r" (__a2), "i" (__NR_execve) + ); + + return retval; +} +EXPORT_SYMBOL(kernel_execve); diff --git a/arch/hexagon/kernel/syscalltab.c b/arch/hexagon/kernel/syscalltab.c new file mode 100644 index 000000000000..c550f4177ab8 --- /dev/null +++ b/arch/hexagon/kernel/syscalltab.c @@ -0,0 +1,32 @@ +/* + * System call table for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/syscalls.h> +#include <linux/signal.h> +#include <linux/unistd.h> + +#include <asm/syscall.h> + +#undef __SYSCALL +#define __SYSCALL(nr, call) [nr] = (call), + +void *sys_call_table[__NR_syscalls] = { +#include <asm/unistd.h> +}; diff --git a/arch/hexagon/kernel/time.c b/arch/hexagon/kernel/time.c new file mode 100644 index 000000000000..6bee15c9c113 --- /dev/null +++ b/arch/hexagon/kernel/time.c @@ -0,0 +1,250 @@ +/* + * Time related functions for Hexagon architecture + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/init.h> +#include <linux/clockchips.h> +#include <linux/clocksource.h> +#include <linux/interrupt.h> +#include <linux/err.h> +#include <linux/platform_device.h> +#include <linux/ioport.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> + +#include <asm/timer-regs.h> +#include <asm/hexagon_vm.h> + +/* + * For the clocksource we need: + * pcycle frequency (600MHz) + * For the loops_per_jiffy we need: + * thread/cpu frequency (100MHz) + * And for the timer, we need: + * sleep clock rate + */ + +cycles_t pcycle_freq_mhz; +cycles_t thread_freq_mhz; +cycles_t sleep_clk_freq; + +static struct resource rtos_timer_resources[] = { + { + .start = RTOS_TIMER_REGS_ADDR, + .end = RTOS_TIMER_REGS_ADDR+PAGE_SIZE-1, + .flags = IORESOURCE_MEM, + }, +}; + +static struct platform_device rtos_timer_device = { + .name = "rtos_timer", + .id = -1, + .num_resources = ARRAY_SIZE(rtos_timer_resources), + .resource = rtos_timer_resources, +}; + +/* A lot of this stuff should move into a platform specific section. */ +struct adsp_hw_timer_struct { + u32 match; /* Match value */ + u32 count; + u32 enable; /* [1] - CLR_ON_MATCH_EN, [0] - EN */ + u32 clear; /* one-shot register that clears the count */ +}; + +/* Look for "TCX0" for related constants. */ +static __iomem struct adsp_hw_timer_struct *rtos_timer; + +static cycle_t timer_get_cycles(struct clocksource *cs) +{ + return (cycle_t) __vmgettime(); +} + +static struct clocksource hexagon_clocksource = { + .name = "pcycles", + .rating = 250, + .read = timer_get_cycles, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +static int set_next_event(unsigned long delta, struct clock_event_device *evt) +{ + /* Assuming the timer will be disabled when we enter here. */ + + iowrite32(1, &rtos_timer->clear); + iowrite32(0, &rtos_timer->clear); + + iowrite32(delta, &rtos_timer->match); + iowrite32(1 << TIMER_ENABLE, &rtos_timer->enable); + return 0; +} + +/* + * Sets the mode (periodic, shutdown, oneshot, etc) of a timer. + */ +static void set_mode(enum clock_event_mode mode, + struct clock_event_device *evt) +{ + switch (mode) { + case CLOCK_EVT_MODE_SHUTDOWN: + /* XXX implement me */ + default: + break; + } +} + +#ifdef CONFIG_SMP +/* Broadcast mechanism */ +static void broadcast(const struct cpumask *mask) +{ + send_ipi(mask, IPI_TIMER); +} +#endif + +static struct clock_event_device hexagon_clockevent_dev = { + .name = "clockevent", + .features = CLOCK_EVT_FEAT_ONESHOT, + .rating = 400, + .irq = RTOS_TIMER_INT, + .set_next_event = set_next_event, + .set_mode = set_mode, +#ifdef CONFIG_SMP + .broadcast = broadcast, +#endif +}; + +#ifdef CONFIG_SMP +static DEFINE_PER_CPU(struct clock_event_device, clock_events); + +void setup_percpu_clockdev(void) +{ + int cpu = smp_processor_id(); + struct clock_event_device *ce_dev = &hexagon_clockevent_dev; + struct clock_event_device *dummy_clock_dev = + &per_cpu(clock_events, cpu); + + memcpy(dummy_clock_dev, ce_dev, sizeof(*dummy_clock_dev)); + INIT_LIST_HEAD(&dummy_clock_dev->list); + + dummy_clock_dev->features = CLOCK_EVT_FEAT_DUMMY; + dummy_clock_dev->cpumask = cpumask_of(cpu); + dummy_clock_dev->mode = CLOCK_EVT_MODE_UNUSED; + + clockevents_register_device(dummy_clock_dev); +} + +/* Called from smp.c for each CPU's timer ipi call */ +void ipi_timer(void) +{ + int cpu = smp_processor_id(); + struct clock_event_device *ce_dev = &per_cpu(clock_events, cpu); + + ce_dev->event_handler(ce_dev); +} +#endif /* CONFIG_SMP */ + +static irqreturn_t timer_interrupt(int irq, void *devid) +{ + struct clock_event_device *ce_dev = &hexagon_clockevent_dev; + + iowrite32(0, &rtos_timer->enable); + ce_dev->event_handler(ce_dev); + + return IRQ_HANDLED; +} + +/* This should also be pulled from devtree */ +static struct irqaction rtos_timer_intdesc = { + .handler = timer_interrupt, + .flags = IRQF_TIMER | IRQF_TRIGGER_RISING, + .name = "rtos_timer" +}; + +/* + * time_init_deferred - called by start_kernel to set up timer/clock source + * + * Install the IRQ handler for the clock, setup timers. + * This is done late, as that way, we can use ioremap(). + * + * This runs just before the delay loop is calibrated, and + * is used for delay calibration. + */ +void __init time_init_deferred(void) +{ + struct resource *resource = NULL; + struct clock_event_device *ce_dev = &hexagon_clockevent_dev; + struct device_node *dn; + struct resource r; + int err; + + ce_dev->cpumask = cpu_all_mask; + + if (!resource) + resource = rtos_timer_device.resource; + + /* ioremap here means this has to run later, after paging init */ + rtos_timer = ioremap(resource->start, resource->end + - resource->start + 1); + + if (!rtos_timer) { + release_mem_region(resource->start, resource->end + - resource->start + 1); + } + clocksource_register_khz(&hexagon_clocksource, pcycle_freq_mhz * 1000); + + /* Note: the sim generic RTOS clock is apparently really 18750Hz */ + + /* + * Last arg is some guaranteed seconds for which the conversion will + * work without overflow. + */ + clockevents_calc_mult_shift(ce_dev, sleep_clk_freq, 4); + + ce_dev->max_delta_ns = clockevent_delta2ns(0x7fffffff, ce_dev); + ce_dev->min_delta_ns = clockevent_delta2ns(0xf, ce_dev); + +#ifdef CONFIG_SMP + setup_percpu_clockdev(); +#endif + + clockevents_register_device(ce_dev); + setup_irq(ce_dev->irq, &rtos_timer_intdesc); +} + +void __init time_init(void) +{ + late_time_init = time_init_deferred; +} + +/* + * This could become parametric or perhaps even computed at run-time, + * but for now we take the observed simulator jitter. + */ +static long long fudgefactor = 350; /* Maybe lower if kernel optimized. */ + +void __udelay(unsigned long usecs) +{ + unsigned long long start = __vmgettime(); + unsigned long long finish = (pcycle_freq_mhz * usecs) - fudgefactor; + + while ((__vmgettime() - start) < finish) + cpu_relax(); /* not sure how this improves readability */ +} +EXPORT_SYMBOL(__udelay); diff --git a/arch/hexagon/kernel/topology.c b/arch/hexagon/kernel/topology.c new file mode 100644 index 000000000000..ba4475184432 --- /dev/null +++ b/arch/hexagon/kernel/topology.c @@ -0,0 +1,52 @@ +/* + * CPU topology for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/init.h> +#include <linux/node.h> +#include <linux/nodemask.h> +#include <linux/percpu.h> + +/* Swiped from MIPS. */ + +static DEFINE_PER_CPU(struct cpu, cpu_devices); + +static int __init topology_init(void) +{ + int i, ret; + + for_each_present_cpu(i) { + + /* + * register_cpu takes a per_cpu pointer and + * just points it at another per_cpu struct... + */ + + ret = register_cpu(&per_cpu(cpu_devices, i), i); + if (ret) + printk(KERN_WARNING "topology_init: register_cpu %d " + "failed (%d)\n", i, ret); + } + + return 0; +} + +subsys_initcall(topology_init); diff --git a/arch/hexagon/kernel/trampoline.S b/arch/hexagon/kernel/trampoline.S new file mode 100644 index 000000000000..06c36c036b98 --- /dev/null +++ b/arch/hexagon/kernel/trampoline.S @@ -0,0 +1,35 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +/* + * Trampoline sequences to be copied onto user stack. + * This consumes a little more space than hand-assembling + * immediate constants for use in C, but is more portable + * to future tweaks to the Hexagon instruction set. + */ + +#include <asm/unistd.h> + +/* Sig trampolines - call sys_sigreturn or sys_rt_sigreturn as appropriate */ + +/* plain sigreturn is gone. */ + + .globl __rt_sigtramp_template +__rt_sigtramp_template: + r6 = #__NR_rt_sigreturn; + trap0(#1); diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c new file mode 100644 index 000000000000..f08857d0715b --- /dev/null +++ b/arch/hexagon/kernel/traps.c @@ -0,0 +1,454 @@ +/* + * Kernel traps/events for Hexagon processor + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/kdebug.h> +#include <linux/syscalls.h> +#include <linux/signal.h> +#include <linux/tracehook.h> +#include <asm/traps.h> +#include <asm/vm_fault.h> +#include <asm/syscall.h> +#include <asm/registers.h> +#include <asm/unistd.h> +#include <asm/sections.h> +#ifdef CONFIG_KGDB +# include <linux/kgdb.h> +#endif + +#define TRAP_SYSCALL 1 +#define TRAP_DEBUG 0xdb + +void __init trap_init(void) +{ +} + +#ifdef CONFIG_GENERIC_BUG +/* Maybe should resemble arch/sh/kernel/traps.c ?? */ +int is_valid_bugaddr(unsigned long addr) +{ + return 1; +} +#endif /* CONFIG_GENERIC_BUG */ + +static const char *ex_name(int ex) +{ + switch (ex) { + case HVM_GE_C_XPROT: + case HVM_GE_C_XUSER: + return "Execute protection fault"; + case HVM_GE_C_RPROT: + case HVM_GE_C_RUSER: + return "Read protection fault"; + case HVM_GE_C_WPROT: + case HVM_GE_C_WUSER: + return "Write protection fault"; + case HVM_GE_C_XMAL: + return "Misaligned instruction"; + case HVM_GE_C_RMAL: + return "Misaligned data load"; + case HVM_GE_C_WMAL: + return "Misaligned data store"; + case HVM_GE_C_INVI: + case HVM_GE_C_PRIVI: + return "Illegal instruction"; + case HVM_GE_C_BUS: + return "Precise bus error"; + case HVM_GE_C_CACHE: + return "Cache error"; + + case 0xdb: + return "Debugger trap"; + + default: + return "Unrecognized exception"; + } +} + +static void do_show_stack(struct task_struct *task, unsigned long *fp, + unsigned long ip) +{ + int kstack_depth_to_print = 24; + unsigned long offset, size; + const char *name = NULL; + unsigned long *newfp; + unsigned long low, high; + char tmpstr[128]; + char *modname; + int i; + + if (task == NULL) + task = current; + + printk(KERN_INFO "CPU#%d, %s/%d, Call Trace:\n", + raw_smp_processor_id(), task->comm, + task_pid_nr(task)); + + if (fp == NULL) { + if (task == current) { + asm("%0 = r30" : "=r" (fp)); + } else { + fp = (unsigned long *) + ((struct hexagon_switch_stack *) + task->thread.switch_sp)->fp; + } + } + + if ((((unsigned long) fp) & 0x3) || ((unsigned long) fp < 0x1000)) { + printk(KERN_INFO "-- Corrupt frame pointer %p\n", fp); + return; + } + + /* Saved link reg is one word above FP */ + if (!ip) + ip = *(fp+1); + + /* Expect kernel stack to be in-bounds */ + low = (unsigned long)task_stack_page(task); + high = low + THREAD_SIZE - 8; + low += sizeof(struct thread_info); + + for (i = 0; i < kstack_depth_to_print; i++) { + + name = kallsyms_lookup(ip, &size, &offset, &modname, tmpstr); + + printk(KERN_INFO "[%p] 0x%lx: %s + 0x%lx", fp, ip, name, + offset); + if (((unsigned long) fp < low) || (high < (unsigned long) fp)) + printk(KERN_CONT " (FP out of bounds!)"); + if (modname) + printk(KERN_CONT " [%s] ", modname); + printk(KERN_CONT "\n"); + + newfp = (unsigned long *) *fp; + + if (((unsigned long) newfp) & 0x3) { + printk(KERN_INFO "-- Corrupt frame pointer %p\n", + newfp); + break; + } + + /* Attempt to continue past exception. */ + if (0 == newfp) { + struct pt_regs *regs = (struct pt_regs *) (((void *)fp) + + 8); + + if (regs->syscall_nr != -1) { + printk(KERN_INFO "-- trap0 -- syscall_nr: %ld", + regs->syscall_nr); + printk(KERN_CONT " psp: %lx elr: %lx\n", + pt_psp(regs), pt_elr(regs)); + break; + } else { + /* really want to see more ... */ + kstack_depth_to_print += 6; + printk(KERN_INFO "-- %s (0x%lx) badva: %lx\n", + ex_name(pt_cause(regs)), pt_cause(regs), + pt_badva(regs)); + } + + newfp = (unsigned long *) regs->r30; + ip = pt_elr(regs); + } else { + ip = *(newfp + 1); + } + + /* If link reg is null, we are done. */ + if (ip == 0x0) + break; + + /* If newfp isn't larger, we're tracing garbage. */ + if (newfp > fp) + fp = newfp; + else + break; + } +} + +void show_stack(struct task_struct *task, unsigned long *fp) +{ + /* Saved link reg is one word above FP */ + do_show_stack(task, fp, 0); +} + +void dump_stack(void) +{ + unsigned long *fp; + asm("%0 = r30" : "=r" (fp)); + show_stack(current, fp); +} +EXPORT_SYMBOL(dump_stack); + +int die(const char *str, struct pt_regs *regs, long err) +{ + static struct { + spinlock_t lock; + int counter; + } die = { + .lock = __SPIN_LOCK_UNLOCKED(die.lock), + .counter = 0 + }; + + console_verbose(); + oops_enter(); + + spin_lock_irq(&die.lock); + bust_spinlocks(1); + printk(KERN_EMERG "Oops: %s[#%d]:\n", str, ++die.counter); + + if (notify_die(DIE_OOPS, str, regs, err, pt_cause(regs), SIGSEGV) == + NOTIFY_STOP) + return 1; + + print_modules(); + show_regs(regs); + do_show_stack(current, ®s->r30, pt_elr(regs)); + + bust_spinlocks(0); + add_taint(TAINT_DIE); + + spin_unlock_irq(&die.lock); + + if (in_interrupt()) + panic("Fatal exception in interrupt"); + + if (panic_on_oops) + panic("Fatal exception"); + + oops_exit(); + do_exit(err); + return 0; +} + +int die_if_kernel(char *str, struct pt_regs *regs, long err) +{ + if (!user_mode(regs)) + return die(str, regs, err); + else + return 0; +} + +/* + * It's not clear that misaligned fetches are ever recoverable. + */ +static void misaligned_instruction(struct pt_regs *regs) +{ + die_if_kernel("Misaligned Instruction", regs, 0); + force_sig(SIGBUS, current); +} + +/* + * Misaligned loads and stores, on the other hand, can be + * emulated, and probably should be, some day. But for now + * they will be considered fatal. + */ +static void misaligned_data_load(struct pt_regs *regs) +{ + die_if_kernel("Misaligned Data Load", regs, 0); + force_sig(SIGBUS, current); +} + +static void misaligned_data_store(struct pt_regs *regs) +{ + die_if_kernel("Misaligned Data Store", regs, 0); + force_sig(SIGBUS, current); +} + +static void illegal_instruction(struct pt_regs *regs) +{ + die_if_kernel("Illegal Instruction", regs, 0); + force_sig(SIGILL, current); +} + +/* + * Precise bus errors may be recoverable with a a retry, + * but for now, treat them as irrecoverable. + */ +static void precise_bus_error(struct pt_regs *regs) +{ + die_if_kernel("Precise Bus Error", regs, 0); + force_sig(SIGBUS, current); +} + +/* + * If anything is to be done here other than panic, + * it will probably be complex and migrate to another + * source module. For now, just die. + */ +static void cache_error(struct pt_regs *regs) +{ + die("Cache Error", regs, 0); +} + +/* + * General exception handler + */ +void do_genex(struct pt_regs *regs) +{ + /* + * Decode Cause and Dispatch + */ + switch (pt_cause(regs)) { + case HVM_GE_C_XPROT: + case HVM_GE_C_XUSER: + execute_protection_fault(regs); + break; + case HVM_GE_C_RPROT: + case HVM_GE_C_RUSER: + read_protection_fault(regs); + break; + case HVM_GE_C_WPROT: + case HVM_GE_C_WUSER: + write_protection_fault(regs); + break; + case HVM_GE_C_XMAL: + misaligned_instruction(regs); + break; + case HVM_GE_C_RMAL: + misaligned_data_load(regs); + break; + case HVM_GE_C_WMAL: + misaligned_data_store(regs); + break; + case HVM_GE_C_INVI: + case HVM_GE_C_PRIVI: + illegal_instruction(regs); + break; + case HVM_GE_C_BUS: + precise_bus_error(regs); + break; + case HVM_GE_C_CACHE: + cache_error(regs); + break; + default: + /* Halt and catch fire */ + panic("Unrecognized exception 0x%lx\n", pt_cause(regs)); + break; + } +} + +/* Indirect system call dispatch */ +long sys_syscall(void) +{ + printk(KERN_ERR "sys_syscall invoked!\n"); + return -ENOSYS; +} + +void do_trap0(struct pt_regs *regs) +{ + unsigned long syscallret = 0; + syscall_fn syscall; + + switch (pt_cause(regs)) { + case TRAP_SYSCALL: + /* System call is trap0 #1 */ + + /* allow strace to catch syscall args */ + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACE) && + tracehook_report_syscall_entry(regs))) + return; /* return -ENOSYS somewhere? */ + + /* Interrupts should be re-enabled for syscall processing */ + __vmsetie(VM_INT_ENABLE); + + /* + * System call number is in r6, arguments in r0..r5. + * Fortunately, no Linux syscall has more than 6 arguments, + * and Hexagon ABI passes first 6 arguments in registers. + * 64-bit arguments are passed in odd/even register pairs. + * Fortunately, we have no system calls that take more + * than three arguments with more than one 64-bit value. + * Should that change, we'd need to redesign to copy + * between user and kernel stacks. + */ + regs->syscall_nr = regs->r06; + + /* + * GPR R0 carries the first parameter, and is also used + * to report the return value. We need a backup of + * the user's value in case we need to do a late restart + * of the system call. + */ + regs->restart_r0 = regs->r00; + + if ((unsigned long) regs->syscall_nr >= __NR_syscalls) { + regs->r00 = -1; + } else { + syscall = (syscall_fn) + (sys_call_table[regs->syscall_nr]); + syscallret = syscall(regs->r00, regs->r01, + regs->r02, regs->r03, + regs->r04, regs->r05); + } + + /* + * If it was a sigreturn system call, don't overwrite + * r0 value in stack frame with return value. + * + * __NR_sigreturn doesn't seem to exist in new unistd.h + */ + + if (regs->syscall_nr != __NR_rt_sigreturn) + regs->r00 = syscallret; + + /* allow strace to get the syscall return state */ + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACE))) + tracehook_report_syscall_exit(regs, 0); + + break; + case TRAP_DEBUG: + /* Trap0 0xdb is debug breakpoint */ + if (user_mode(regs)) { + struct siginfo info; + + info.si_signo = SIGTRAP; + info.si_errno = 0; + /* + * Some architecures add some per-thread state + * to distinguish between breakpoint traps and + * trace traps. We may want to do that, and + * set the si_code value appropriately, or we + * may want to use a different trap0 flavor. + */ + info.si_code = TRAP_BRKPT; + info.si_addr = (void __user *) pt_elr(regs); + send_sig_info(SIGTRAP, &info, current); + } else { +#ifdef CONFIG_KGDB + kgdb_handle_exception(pt_cause(regs), SIGTRAP, + TRAP_BRKPT, regs); +#endif + } + break; + } + /* Ignore other trap0 codes for now, especially 0 (Angel calls) */ +} + +/* + * Machine check exception handler + */ +void do_machcheck(struct pt_regs *regs) +{ + /* Halt and catch fire */ + __vmstop(); +} diff --git a/arch/hexagon/kernel/vdso.c b/arch/hexagon/kernel/vdso.c new file mode 100644 index 000000000000..16277c33308a --- /dev/null +++ b/arch/hexagon/kernel/vdso.c @@ -0,0 +1,100 @@ +/* + * vDSO implementation for Hexagon + * + * Copyright (c) 2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/err.h> +#include <linux/mm.h> +#include <linux/vmalloc.h> + +#include <asm/vdso.h> + +static struct page *vdso_page; + +/* Create a vDSO page holding the signal trampoline. + * We want this for a non-executable stack. + */ +static int __init vdso_init(void) +{ + struct hexagon_vdso *vdso; + + vdso_page = alloc_page(GFP_KERNEL); + if (!vdso_page) + panic("Cannot allocate vdso"); + + vdso = vmap(&vdso_page, 1, 0, PAGE_KERNEL); + if (!vdso) + panic("Cannot map vdso"); + clear_page(vdso); + + /* Install the signal trampoline; currently looks like this: + * r6 = #__NR_rt_sigreturn; + * trap0(#1); + */ + vdso->rt_signal_trampoline[0] = __rt_sigtramp_template[0]; + vdso->rt_signal_trampoline[1] = __rt_sigtramp_template[1]; + + vunmap(vdso); + + return 0; +} +arch_initcall(vdso_init); + +/* + * Called from binfmt_elf. Create a VMA for the vDSO page. + */ +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + int ret; + unsigned long vdso_base; + struct mm_struct *mm = current->mm; + + down_write(&mm->mmap_sem); + + /* Try to get it loaded right near ld.so/glibc. */ + vdso_base = STACK_TOP; + + vdso_base = get_unmapped_area(NULL, vdso_base, PAGE_SIZE, 0, 0); + if (IS_ERR_VALUE(vdso_base)) { + ret = vdso_base; + goto up_fail; + } + + /* MAYWRITE to allow gdb to COW and set breakpoints. */ + ret = install_special_mapping(mm, vdso_base, PAGE_SIZE, + VM_READ|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC| + VM_ALWAYSDUMP, + &vdso_page); + + if (ret) + goto up_fail; + + mm->context.vdso = (void *)vdso_base; + +up_fail: + up_write(&mm->mmap_sem); + return ret; +} + +const char *arch_vma_name(struct vm_area_struct *vma) +{ + if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso) + return "[vdso]"; + return NULL; +} diff --git a/arch/hexagon/kernel/vm_entry.S b/arch/hexagon/kernel/vm_entry.S new file mode 100644 index 000000000000..5b99066cbc8d --- /dev/null +++ b/arch/hexagon/kernel/vm_entry.S @@ -0,0 +1,269 @@ +/* + * Event entry/exit for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <asm/asm-offsets.h> /* assembly-safer versions of C defines */ +#include <asm/mem-layout.h> /* sigh, except for page_offset */ +#include <asm/hexagon_vm.h> +#include <asm/thread_info.h> + +/* + * Entry into guest-mode Linux under Hexagon Virtual Machine. + * Stack pointer points to event record - build pt_regs on top of it, + * set up a plausible C stack frame, and dispatch to the C handler. + * On return, do vmrte virtual instruction with SP where we started. + * + * VM Spec 0.5 uses a trap to fetch HVM record now. + */ + +/* + * Save full register state, while setting up thread_info struct + * pointer derived from kernel stack pointer in THREADINFO_REG + * register, putting prior thread_info.regs pointer in a callee-save + * register (R24, which had better not ever be assigned to THREADINFO_REG), + * and updating thread_info.regs to point to current stack frame, + * so as to support nested events in kernel mode. + * + * As this is common code, we set the pt_regs system call number + * to -1 for all events. It will be replaced with the system call + * number in the case where we decode a system call (trap0(#1)). + */ + +#define save_pt_regs()\ + memd(R0 + #_PT_R3130) = R31:30; \ + { memw(R0 + #_PT_R2928) = R28; \ + R31 = memw(R0 + #_PT_ER_VMPSP); }\ + { memw(R0 + #(_PT_R2928 + 4)) = R31; \ + R31 = ugp; } \ + { memd(R0 + #_PT_R2726) = R27:26; \ + R30 = gp ; } \ + memd(R0 + #_PT_R2524) = R25:24; \ + memd(R0 + #_PT_R2322) = R23:22; \ + memd(R0 + #_PT_R2120) = R21:20; \ + memd(R0 + #_PT_R1918) = R19:18; \ + memd(R0 + #_PT_R1716) = R17:16; \ + memd(R0 + #_PT_R1514) = R15:14; \ + memd(R0 + #_PT_R1312) = R13:12; \ + { memd(R0 + #_PT_R1110) = R11:10; \ + R15 = lc0; } \ + { memd(R0 + #_PT_R0908) = R9:8; \ + R14 = sa0; } \ + { memd(R0 + #_PT_R0706) = R7:6; \ + R13 = lc1; } \ + { memd(R0 + #_PT_R0504) = R5:4; \ + R12 = sa1; } \ + { memd(R0 + #_PT_UGPGP) = R31:30; \ + R11 = m1; \ + R2.H = #HI(_THREAD_SIZE); } \ + { memd(R0 + #_PT_LC0SA0) = R15:14; \ + R10 = m0; \ + R2.L = #LO(_THREAD_SIZE); } \ + { memd(R0 + #_PT_LC1SA1) = R13:12; \ + R15 = p3:0; \ + R2 = neg(R2); } \ + { memd(R0 + #_PT_M1M0) = R11:10; \ + R14 = usr; \ + R2 = and(R0,R2); } \ + { memd(R0 + #_PT_PREDSUSR) = R15:14; \ + THREADINFO_REG = R2; } \ + { r24 = memw(THREADINFO_REG + #_THREAD_INFO_PT_REGS); \ + memw(THREADINFO_REG + #_THREAD_INFO_PT_REGS) = R0; \ + R2 = #-1; } \ + { memw(R0 + #_PT_SYSCALL_NR) = R2; \ + R30 = #0; } + +/* + * Restore registers and thread_info.regs state. THREADINFO_REG + * is assumed to still be sane, and R24 to have been correctly + * preserved. Don't restore R29 (SP) until later. + */ + +#define restore_pt_regs() \ + { memw(THREADINFO_REG + #_THREAD_INFO_PT_REGS) = R24; \ + R15:14 = memd(R0 + #_PT_PREDSUSR); } \ + { R11:10 = memd(R0 + #_PT_M1M0); \ + p3:0 = R15; } \ + { R13:12 = memd(R0 + #_PT_LC1SA1); \ + usr = R14; } \ + { R15:14 = memd(R0 + #_PT_LC0SA0); \ + m1 = R11; } \ + { R3:2 = memd(R0 + #_PT_R0302); \ + m0 = R10; } \ + { R5:4 = memd(R0 + #_PT_R0504); \ + lc1 = R13; } \ + { R7:6 = memd(R0 + #_PT_R0706); \ + sa1 = R12; } \ + { R9:8 = memd(R0 + #_PT_R0908); \ + lc0 = R15; } \ + { R11:10 = memd(R0 + #_PT_R1110); \ + sa0 = R14; } \ + { R13:12 = memd(R0 + #_PT_R1312); \ + R15:14 = memd(R0 + #_PT_R1514); } \ + { R17:16 = memd(R0 + #_PT_R1716); \ + R19:18 = memd(R0 + #_PT_R1918); } \ + { R21:20 = memd(R0 + #_PT_R2120); \ + R23:22 = memd(R0 + #_PT_R2322); } \ + { R25:24 = memd(R0 + #_PT_R2524); \ + R27:26 = memd(R0 + #_PT_R2726); } \ + R31:30 = memd(R0 + #_PT_UGPGP); \ + { R28 = memw(R0 + #_PT_R2928); \ + ugp = R31; } \ + { R31:30 = memd(R0 + #_PT_R3130); \ + gp = R30; } + + /* + * Clears off enough space for the rest of pt_regs; evrec is a part + * of pt_regs in HVM mode. Save R0/R1, set handler's address in R1. + * R0 is the address of pt_regs and is the parameter to save_pt_regs. + */ + +/* + * Since the HVM isn't automagically pushing the EVREC onto the stack anymore, + * we'll subract the entire size out and then fill it in ourselves. + * Need to save off R0, R1, R2, R3 immediately. + */ + +#define vm_event_entry(CHandler) \ + { \ + R29 = add(R29, #-(_PT_REGS_SIZE)); \ + memd(R29 + #(_PT_R0100 + -_PT_REGS_SIZE)) = R1:0; \ + } \ + { \ + memd(R29 +#_PT_R0302) = R3:2; \ + } \ + trap1(#HVM_TRAP1_VMGETREGS); \ + { \ + memd(R29 + #_PT_ER_VMEL) = R1:0; \ + R0 = R29; \ + R1.L = #LO(CHandler); \ + } \ + { \ + memd(R29 + #_PT_ER_VMPSP) = R3:2; \ + R1.H = #HI(CHandler); \ + jump event_dispatch; \ + } + +.text + /* + * Do bulk save/restore in one place. + * Adds a jump to dispatch latency, but + * saves hundreds of bytes. + */ + +event_dispatch: + save_pt_regs() + callr r1 + + /* + * If we were in kernel mode, we don't need to check scheduler + * or signals if CONFIG_PREEMPT is not set. If set, then it has + * to jump to a need_resched kind of block. + * BTW, CONFIG_PREEMPT is not supported yet. + */ + +#ifdef CONFIG_PREEMPT + R0 = #VM_INT_DISABLE + trap1(#HVM_TRAP1_VMSETIE) +#endif + + /* "Nested control path" -- if the previous mode was kernel */ + R0 = memw(R29 + #_PT_ER_VMEST); + P0 = tstbit(R0, #HVM_VMEST_UM_SFT); + if !P0 jump restore_all; + /* + * Returning from system call, normally coming back from user mode + */ +return_from_syscall: + /* Disable interrupts while checking TIF */ + R0 = #VM_INT_DISABLE + trap1(#HVM_TRAP1_VMSETIE) + + /* + * Coming back from the C-world, our thread info pointer + * should be in the designated register (usually R19) + */ + R1.L = #LO(_TIF_ALLWORK_MASK) + { + R1.H = #HI(_TIF_ALLWORK_MASK); + R0 = memw(THREADINFO_REG + #_THREAD_INFO_FLAGS); + } + + /* + * Compare against the "return to userspace" _TIF_WORK_MASK + */ + R1 = and(R1,R0); + { P0 = cmp.eq(R1,#0); if (!P0.new) jump:t work_pending;} + jump restore_all; /* we're outta here! */ + +work_pending: + { + P0 = tstbit(R1, #TIF_NEED_RESCHED); + if (!P0.new) jump:nt work_notifysig; + } + call schedule + jump return_from_syscall; /* check for more work */ + +work_notifysig: + /* this is the part that's kind of fuzzy. */ + R1 = and(R0, #(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME)); + P0 = cmp.eq(R1, #0); + if P0 jump restore_all + R1 = R0; /* unsigned long thread_info_flags */ + R0 = R29; /* regs should still be at top of stack */ + call do_notify_resume + +restore_all: + /* Disable interrupts, if they weren't already, before reg restore. */ + R0 = #VM_INT_DISABLE + trap1(#HVM_TRAP1_VMSETIE) + + /* do the setregs here for VM 0.5 */ + /* R29 here should already be pointing at pt_regs */ + R1:0 = memd(R29 + #_PT_ER_VMEL); + R3:2 = memd(R29 + #_PT_ER_VMPSP); + trap1(#HVM_TRAP1_VMSETREGS); + + R0 = R29 + restore_pt_regs() + R1:0 = memd(R29 + #_PT_R0100); + R29 = add(R29, #_PT_REGS_SIZE); + trap1(#HVM_TRAP1_VMRTE) + /* Notreached */ + + .globl _K_enter_genex +_K_enter_genex: + vm_event_entry(do_genex) + + .globl _K_enter_interrupt +_K_enter_interrupt: + vm_event_entry(arch_do_IRQ) + + .globl _K_enter_trap0 +_K_enter_trap0: + vm_event_entry(do_trap0) + + .globl _K_enter_machcheck +_K_enter_machcheck: + vm_event_entry(do_machcheck) + + + .globl ret_from_fork +ret_from_fork: + call schedule_tail + jump return_from_syscall diff --git a/arch/hexagon/kernel/vm_events.c b/arch/hexagon/kernel/vm_events.c new file mode 100644 index 000000000000..986a081e32ec --- /dev/null +++ b/arch/hexagon/kernel/vm_events.c @@ -0,0 +1,101 @@ +/* + * Mostly IRQ support for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/kernel.h> +#include <asm/registers.h> +#include <linux/irq.h> +#include <linux/hardirq.h> +#include <asm/system.h> + +/* + * show_regs - print pt_regs structure + * @regs: pointer to pt_regs + * + * To-do: add all the accessor definitions to registers.h + * + * Will make this routine a lot easier to write. + */ +void show_regs(struct pt_regs *regs) +{ + printk(KERN_EMERG "restart_r0: \t0x%08lx syscall_nr: %ld\n", + regs->restart_r0, regs->syscall_nr); + printk(KERN_EMERG "preds: \t\t0x%08lx\n", regs->preds); + printk(KERN_EMERG "lc0: \t0x%08lx sa0: 0x%08lx m0: 0x%08lx\n", + regs->lc0, regs->sa0, regs->m0); + printk(KERN_EMERG "lc1: \t0x%08lx sa1: 0x%08lx m1: 0x%08lx\n", + regs->lc1, regs->sa1, regs->m1); + printk(KERN_EMERG "gp: \t0x%08lx ugp: 0x%08lx usr: 0x%08lx\n", + regs->gp, regs->ugp, regs->usr); + printk(KERN_EMERG "r0: \t0x%08lx %08lx %08lx %08lx\n", regs->r00, + regs->r01, + regs->r02, + regs->r03); + printk(KERN_EMERG "r4: \t0x%08lx %08lx %08lx %08lx\n", regs->r04, + regs->r05, + regs->r06, + regs->r07); + printk(KERN_EMERG "r8: \t0x%08lx %08lx %08lx %08lx\n", regs->r08, + regs->r09, + regs->r10, + regs->r11); + printk(KERN_EMERG "r12: \t0x%08lx %08lx %08lx %08lx\n", regs->r12, + regs->r13, + regs->r14, + regs->r15); + printk(KERN_EMERG "r16: \t0x%08lx %08lx %08lx %08lx\n", regs->r16, + regs->r17, + regs->r18, + regs->r19); + printk(KERN_EMERG "r20: \t0x%08lx %08lx %08lx %08lx\n", regs->r20, + regs->r21, + regs->r22, + regs->r23); + printk(KERN_EMERG "r24: \t0x%08lx %08lx %08lx %08lx\n", regs->r24, + regs->r25, + regs->r26, + regs->r27); + printk(KERN_EMERG "r28: \t0x%08lx %08lx %08lx %08lx\n", regs->r28, + regs->r29, + regs->r30, + regs->r31); + + printk(KERN_EMERG "elr: \t0x%08lx cause: 0x%08lx user_mode: %d\n", + pt_elr(regs), pt_cause(regs), user_mode(regs)); + printk(KERN_EMERG "psp: \t0x%08lx badva: 0x%08lx int_enabled: %d\n", + pt_psp(regs), pt_badva(regs), ints_enabled(regs)); +} + +void dummy_handler(struct pt_regs *regs) +{ + unsigned int elr = pt_elr(regs); + printk(KERN_ERR "Unimplemented handler; ELR=0x%08x\n", elr); +} + + +void arch_do_IRQ(struct pt_regs *regs) +{ + int irq = pt_cause(regs); + struct pt_regs *old_regs = set_irq_regs(regs); + + irq_enter(); + generic_handle_irq(irq); + irq_exit(); + set_irq_regs(old_regs); +} diff --git a/arch/hexagon/kernel/vm_init_segtable.S b/arch/hexagon/kernel/vm_init_segtable.S new file mode 100644 index 000000000000..aebb35b6465e --- /dev/null +++ b/arch/hexagon/kernel/vm_init_segtable.S @@ -0,0 +1,442 @@ +/* + * Initial page table for Linux kernel under Hexagon VM, + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +/* + * These tables are pre-computed and linked into kernel. + */ + +#include <asm/vm_mmu.h> +/* #include <asm/iomap.h> */ + +/* + * Start with mapping PA=0 to both VA=0x0 and VA=0xc000000 as 16MB large pages. + * No user mode access, RWX, write-back cache. The entry needs + * to be replicated for all 4 virtual segments mapping to the page. + */ + +/* "Big Kernel Page" */ +#define BKP(pa) (((pa) & __HVM_PTE_PGMASK_4MB) \ + | __HVM_PTE_R | __HVM_PTE_W | __HVM_PTE_X \ + | __HEXAGON_C_WB_L2 << 6 \ + | __HVM_PDE_S_16MB) + +/* No cache version */ + +#define BKPG_IO(pa) (((pa) & __HVM_PTE_PGMASK_16MB) \ + | __HVM_PTE_R | __HVM_PTE_W | __HVM_PTE_X \ + | __HVM_PDE_S_16MB | __HEXAGON_C_DEV << 6 ) + +#define FOURK_IO(pa) (((pa) & __HVM_PTE_PGMASK_4KB) \ + | __HVM_PTE_R | __HVM_PTE_W | __HVM_PTE_X \ + | __HEXAGON_C_DEV << 6 ) + +#define L2_PTR(pa) (((pa) & __HVM_PTE_PGMASK_4KB) \ + | __HVM_PDE_S_4KB ) + +#define X __HVM_PDE_S_INVALID + + .p2align 12 + .globl swapper_pg_dir + .globl _K_init_segtable +swapper_pg_dir: +/* VA 0x00000000 */ + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X +/* VA 0x40000000 */ + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X +/* VA 0x80000000 */ + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X +/*0xa8*/.word X,X,X,X +#ifdef CONFIG_COMET_EARLY_UART_DEBUG +UART_PTE_ENTRY: +/*0xa9*/.word BKPG_IO(0xa9000000),BKPG_IO(0xa9000000),BKPG_IO(0xa9000000),BKPG_IO(0xa9000000) +#else +/*0xa9*/.word X,X,X,X +#endif +/*0xaa*/.word X,X,X,X +/*0xab*/.word X,X,X,X +/*0xac*/.word X,X,X,X +/*0xad*/.word X,X,X,X +/*0xae*/.word X,X,X,X +/*0xaf*/.word X,X,X,X +/*0xb0*/.word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X + .word X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X,X +_K_init_segtable: +/* VA 0xC0000000 */ + .word BKP(0x00000000), BKP(0x00400000), BKP(0x00800000), BKP(0x00c00000) + .word BKP(0x01000000), BKP(0x01400000), BKP(0x01800000), BKP(0x01c00000) + .word BKP(0x02000000), BKP(0x02400000), BKP(0x02800000), BKP(0x02c00000) + .word BKP(0x03000000), BKP(0x03400000), BKP(0x03800000), BKP(0x03c00000) + .word BKP(0x04000000), BKP(0x04400000), BKP(0x04800000), BKP(0x04c00000) + .word BKP(0x05000000), BKP(0x05400000), BKP(0x05800000), BKP(0x05c00000) + .word BKP(0x06000000), BKP(0x06400000), BKP(0x06800000), BKP(0x06c00000) + .word BKP(0x07000000), BKP(0x07400000), BKP(0x07800000), BKP(0x07c00000) + + .word BKP(0x08000000), BKP(0x08400000), BKP(0x08800000), BKP(0x08c00000) + .word BKP(0x09000000), BKP(0x09400000), BKP(0x09800000), BKP(0x09c00000) + .word BKP(0x0a000000), BKP(0x0a400000), BKP(0x0a800000), BKP(0x0ac00000) + .word BKP(0x0b000000), BKP(0x0b400000), BKP(0x0b800000), BKP(0x0bc00000) + .word BKP(0x0c000000), BKP(0x0c400000), BKP(0x0c800000), BKP(0x0cc00000) + .word BKP(0x0d000000), BKP(0x0d400000), BKP(0x0d800000), BKP(0x0dc00000) + .word BKP(0x0e000000), BKP(0x0e400000), BKP(0x0e800000), BKP(0x0ec00000) + .word BKP(0x0f000000), BKP(0x0f400000), BKP(0x0f800000), BKP(0x0fc00000) + + .word BKP(0x10000000), BKP(0x10400000), BKP(0x10800000), BKP(0x10c00000) + .word BKP(0x11000000), BKP(0x11400000), BKP(0x11800000), BKP(0x11c00000) + .word BKP(0x12000000), BKP(0x12400000), BKP(0x12800000), BKP(0x12c00000) + .word BKP(0x13000000), BKP(0x13400000), BKP(0x13800000), BKP(0x13c00000) + .word BKP(0x14000000), BKP(0x14400000), BKP(0x14800000), BKP(0x14c00000) + .word BKP(0x15000000), BKP(0x15400000), BKP(0x15800000), BKP(0x15c00000) + .word BKP(0x16000000), BKP(0x16400000), BKP(0x16800000), BKP(0x16c00000) + .word BKP(0x17000000), BKP(0x17400000), BKP(0x17800000), BKP(0x17c00000) + + .word BKP(0x18000000), BKP(0x18400000), BKP(0x18800000), BKP(0x18c00000) + .word BKP(0x19000000), BKP(0x19400000), BKP(0x19800000), BKP(0x19c00000) + .word BKP(0x1a000000), BKP(0x1a400000), BKP(0x1a800000), BKP(0x1ac00000) + .word BKP(0x1b000000), BKP(0x1b400000), BKP(0x1b800000), BKP(0x1bc00000) + .word BKP(0x1c000000), BKP(0x1c400000), BKP(0x1c800000), BKP(0x1cc00000) + .word BKP(0x1d000000), BKP(0x1d400000), BKP(0x1d800000), BKP(0x1dc00000) + .word BKP(0x1e000000), BKP(0x1e400000), BKP(0x1e800000), BKP(0x1ec00000) + .word BKP(0x1f000000), BKP(0x1f400000), BKP(0x1f800000), BKP(0x1fc00000) + + .word BKP(0x20000000), BKP(0x20400000), BKP(0x20800000), BKP(0x20c00000) + .word BKP(0x21000000), BKP(0x21400000), BKP(0x21800000), BKP(0x21c00000) + .word BKP(0x22000000), BKP(0x22400000), BKP(0x22800000), BKP(0x22c00000) + .word BKP(0x23000000), BKP(0x23400000), BKP(0x23800000), BKP(0x23c00000) + .word BKP(0x24000000), BKP(0x24400000), BKP(0x24800000), BKP(0x24c00000) + .word BKP(0x25000000), BKP(0x25400000), BKP(0x25800000), BKP(0x25c00000) + .word BKP(0x26000000), BKP(0x26400000), BKP(0x26800000), BKP(0x26c00000) + .word BKP(0x27000000), BKP(0x27400000), BKP(0x27800000), BKP(0x27c00000) + + .word BKP(0x28000000), BKP(0x28400000), BKP(0x28800000), BKP(0x28c00000) + .word BKP(0x29000000), BKP(0x29400000), BKP(0x29800000), BKP(0x29c00000) + .word BKP(0x2a000000), BKP(0x2a400000), BKP(0x2a800000), BKP(0x2ac00000) + .word BKP(0x2b000000), BKP(0x2b400000), BKP(0x2b800000), BKP(0x2bc00000) + .word BKP(0x2c000000), BKP(0x2c400000), BKP(0x2c800000), BKP(0x2cc00000) + .word BKP(0x2d000000), BKP(0x2d400000), BKP(0x2d800000), BKP(0x2dc00000) + .word BKP(0x2e000000), BKP(0x2e400000), BKP(0x2e800000), BKP(0x2ec00000) + .word BKP(0x2f000000), BKP(0x2f400000), BKP(0x2f800000), BKP(0x2fc00000) + + .word BKP(0x30000000), BKP(0x30400000), BKP(0x30800000), BKP(0x30c00000) + .word BKP(0x31000000), BKP(0x31400000), BKP(0x31800000), BKP(0x31c00000) + .word BKP(0x32000000), BKP(0x32400000), BKP(0x32800000), BKP(0x32c00000) + .word BKP(0x33000000), BKP(0x33400000), BKP(0x33800000), BKP(0x33c00000) + .word BKP(0x34000000), BKP(0x34400000), BKP(0x34800000), BKP(0x34c00000) + .word BKP(0x35000000), BKP(0x35400000), BKP(0x35800000), BKP(0x35c00000) + .word BKP(0x36000000), BKP(0x36400000), BKP(0x36800000), BKP(0x36c00000) + .word BKP(0x37000000), BKP(0x37400000), BKP(0x37800000), BKP(0x37c00000) + + .word BKP(0x38000000), BKP(0x38400000), BKP(0x38800000), BKP(0x38c00000) + .word BKP(0x39000000), BKP(0x39400000), BKP(0x39800000), BKP(0x39c00000) + .word BKP(0x3a000000), BKP(0x3a400000), BKP(0x3a800000), BKP(0x3ac00000) + .word BKP(0x3b000000), BKP(0x3b400000), BKP(0x3b800000), BKP(0x3bc00000) + .word BKP(0x3c000000), BKP(0x3c400000), BKP(0x3c800000), BKP(0x3cc00000) + .word BKP(0x3d000000), BKP(0x3d400000), BKP(0x3d800000), BKP(0x3dc00000) +_K_io_map: + .word X,X,X,X /* 0x3e000000 - device IO early remap */ + .word X,X,X,X /* 0x3f000000 - hypervisor space*/ + +#if 0 +/* + * This is in here as an example for devices which need to be mapped really + * early. + */ + .p2align 12 + .globl _K_io_kmap + .globl _K_init_devicetable +_K_init_devicetable: /* Should be 4MB worth of entries */ + .word FOURK_IO(MSM_GPIO1_PHYS),FOURK_IO(MSM_GPIO2_PHYS),FOURK_IO(MSM_SIRC_PHYS),X + .word FOURK_IO(TLMM_GPIO1_PHYS),X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X + .word X,X,X,X +#endif diff --git a/arch/hexagon/kernel/vm_ops.S b/arch/hexagon/kernel/vm_ops.S new file mode 100644 index 000000000000..24d7fcac4ff2 --- /dev/null +++ b/arch/hexagon/kernel/vm_ops.S @@ -0,0 +1,102 @@ +/* + * Hexagon VM instruction support + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/linkage.h> +#include <asm/hexagon_vm.h> + +/* + * C wrappers for virtual machine "instructions". These + * could be, and perhaps some day will be, handled as in-line + * macros, but for tracing/debugging it's handy to have + * a single point of invocation for each of them. + * Conveniently, they take paramters and return values + * consistent with the ABI calling convention. + */ + +ENTRY(__vmrte) + trap1(#HVM_TRAP1_VMRTE); + jumpr R31; + +ENTRY(__vmsetvec) + trap1(#HVM_TRAP1_VMSETVEC); + jumpr R31; + +ENTRY(__vmsetie) + trap1(#HVM_TRAP1_VMSETIE); + jumpr R31; + +ENTRY(__vmgetie) + trap1(#HVM_TRAP1_VMGETIE); + jumpr R31; + +ENTRY(__vmintop) + trap1(#HVM_TRAP1_VMINTOP); + jumpr R31; + +ENTRY(__vmclrmap) + trap1(#HVM_TRAP1_VMCLRMAP); + jumpr R31; + +ENTRY(__vmnewmap) + r1 = #VM_NEWMAP_TYPE_PGTABLES; + trap1(#HVM_TRAP1_VMNEWMAP); + jumpr R31; + +ENTRY(__vmcache) + trap1(#HVM_TRAP1_VMCACHE); + jumpr R31; + +ENTRY(__vmgettime) + trap1(#HVM_TRAP1_VMGETTIME); + jumpr R31; + +ENTRY(__vmsettime) + trap1(#HVM_TRAP1_VMSETTIME); + jumpr R31; + +ENTRY(__vmwait) + trap1(#HVM_TRAP1_VMWAIT); + jumpr R31; + +ENTRY(__vmyield) + trap1(#HVM_TRAP1_VMYIELD); + jumpr R31; + +ENTRY(__vmstart) + trap1(#HVM_TRAP1_VMSTART); + jumpr R31; + +ENTRY(__vmstop) + trap1(#HVM_TRAP1_VMSTOP); + jumpr R31; + +ENTRY(__vmvpid) + trap1(#HVM_TRAP1_VMVPID); + jumpr R31; + +/* Probably not actually going to use these; see vm_entry.S */ + +ENTRY(__vmsetregs) + trap1(#HVM_TRAP1_VMSETREGS); + jumpr R31; + +ENTRY(__vmgetregs) + trap1(#HVM_TRAP1_VMGETREGS); + jumpr R31; diff --git a/arch/hexagon/kernel/vm_switch.S b/arch/hexagon/kernel/vm_switch.S new file mode 100644 index 000000000000..0decf2f58e32 --- /dev/null +++ b/arch/hexagon/kernel/vm_switch.S @@ -0,0 +1,95 @@ +/* + * Context switch support for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <asm/asm-offsets.h> + +.text + +/* + * The register used as a fast-path thread information pointer + * is determined as a kernel configuration option. If it happens + * to be a callee-save register, we're going to be saving and + * restoring it twice here. + * + * This code anticipates a revised ABI where R20-23 are added + * to the set of callee-save registers, but this should be + * backward compatible to legacy tools. + */ + + +/* + * void switch_to(struct task_struct *prev, + * struct task_struct *next, struct task_struct *last); + */ + .p2align 2 + .globl __switch_to + .type __switch_to, @function + +/* + * When we exit the wormhole, we need to store the previous task + * in the new R0's pointer. Technically it should be R2, but they should + * be the same; seems like a legacy thing. In short, don't butcher + * R0, let it go back out unmolested. + */ + +__switch_to: + /* + * Push callee-saves onto "prev" stack. + * Here, we're sneaky because the LR and FP + * storage of the thread_stack structure + * is automagically allocated by allocframe, + * so we pass struct size less 8. + */ + allocframe(#(_SWITCH_STACK_SIZE - 8)); + memd(R29+#(_SWITCH_R2726))=R27:26; + memd(R29+#(_SWITCH_R2524))=R25:24; + memd(R29+#(_SWITCH_R2322))=R23:22; + memd(R29+#(_SWITCH_R2120))=R21:20; + memd(R29+#(_SWITCH_R1918))=R19:18; + memd(R29+#(_SWITCH_R1716))=R17:16; + /* Stash thread_info pointer in task_struct */ + memw(R0+#_TASK_THREAD_INFO) = THREADINFO_REG; + memw(R0 +#(_TASK_STRUCT_THREAD + _THREAD_STRUCT_SWITCH_SP)) = R29; + /* Switch to "next" stack and restore callee saves from there */ + R29 = memw(R1 + #(_TASK_STRUCT_THREAD + _THREAD_STRUCT_SWITCH_SP)); + { + R27:26 = memd(R29+#(_SWITCH_R2726)); + R25:24 = memd(R29+#(_SWITCH_R2524)); + } + { + R23:22 = memd(R29+#(_SWITCH_R2322)); + R21:20 = memd(R29+#(_SWITCH_R2120)); + } + { + R19:18 = memd(R29+#(_SWITCH_R1918)); + R17:16 = memd(R29+#(_SWITCH_R1716)); + } + { + /* THREADINFO_REG is currently one of the callee-saved regs + * above, and so be sure to re-load it last. + */ + THREADINFO_REG = memw(R1 + #_TASK_THREAD_INFO); + R31:30 = memd(R29+#_SWITCH_FP); + } + { + R29 = add(R29,#_SWITCH_STACK_SIZE); + jumpr R31; + } + .size __switch_to, .-__switch_to diff --git a/arch/hexagon/kernel/vm_vectors.S b/arch/hexagon/kernel/vm_vectors.S new file mode 100644 index 000000000000..97a4b50b00df --- /dev/null +++ b/arch/hexagon/kernel/vm_vectors.S @@ -0,0 +1,48 @@ +/* + * Event jump tables + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <asm/hexagon_vm.h> + +.text + +/* This is registered early on to allow angel */ +.global _K_provisional_vec +_K_provisional_vec: + jump 1f; + jump 1f; + jump 1f; + jump 1f; + jump 1f; + trap1(#HVM_TRAP1_VMRTE) + jump 1f; + jump 1f; + + +.global _K_VM_event_vector +_K_VM_event_vector: +1: + jump 1b; /* Reset */ + jump _K_enter_machcheck; + jump _K_enter_genex; + jump 1b; /* 3 Rsvd */ + jump 1b; /* 4 Rsvd */ + jump _K_enter_trap0; + jump 1b; /* 6 Rsvd */ + jump _K_enter_interrupt; diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S new file mode 100644 index 000000000000..071d3c30edfb --- /dev/null +++ b/arch/hexagon/kernel/vmlinux.lds.S @@ -0,0 +1,88 @@ +/* + * Linker script for Hexagon kernel + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#define LOAD_OFFSET PAGE_OFFSET + +#include <asm-generic/vmlinux.lds.h> +#include <asm/asm-offsets.h> /* Most of the kernel defines are here */ +#include <asm/mem-layout.h> /* except for page_offset */ +#include <asm/cache.h> /* and now we're pulling cache line size */ +OUTPUT_ARCH(hexagon) +ENTRY(stext) + +jiffies = jiffies_64; + +/* +See asm-generic/vmlinux.lds.h for expansion of some of these macros. +See asm-generic/sections.h for seemingly required labels. +*/ + +#define PAGE_SIZE _PAGE_SIZE + +/* This LOAD_OFFSET is temporary for debugging on the simulator; it may change + for hypervisor pseudo-physical memory. */ + + +SECTIONS +{ + . = PAGE_OFFSET + LOAD_ADDRESS; + + __init_begin = .; + HEAD_TEXT_SECTION + INIT_TEXT_SECTION(PAGE_SIZE) + PERCPU_SECTION(L1_CACHE_BYTES) + __init_end = .; + + . = ALIGN(_PAGE_SIZE); + _stext = .; + .text : AT(ADDR(.text) - LOAD_OFFSET) { + _text = .; + TEXT_TEXT + SCHED_TEXT + LOCK_TEXT + KPROBES_TEXT + *(.fixup) + } + _etext = .; + + INIT_DATA_SECTION(PAGE_SIZE) + + _sdata = .; + RW_DATA_SECTION(32,PAGE_SIZE,PAGE_SIZE) + RO_DATA_SECTION(PAGE_SIZE) + _edata = .; + + EXCEPTION_TABLE(16) + NOTES + + BSS_SECTION(_PAGE_SIZE, _PAGE_SIZE, _PAGE_SIZE) + + _end = .; + + /DISCARD/ : { + EXIT_TEXT + EXIT_DATA + EXIT_CALL + } + + STABS_DEBUG + DWARF_DEBUG + +} diff --git a/arch/hexagon/lib/Makefile b/arch/hexagon/lib/Makefile new file mode 100644 index 000000000000..874655e85671 --- /dev/null +++ b/arch/hexagon/lib/Makefile @@ -0,0 +1,4 @@ +# +# Makefile for hexagon-specific library files. +# +obj-y = checksum.o io.o memcpy.o memset.o diff --git a/arch/hexagon/lib/checksum.c b/arch/hexagon/lib/checksum.c new file mode 100644 index 000000000000..93005522d52b --- /dev/null +++ b/arch/hexagon/lib/checksum.c @@ -0,0 +1,203 @@ +/* + * Checksum functions for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +/* This was derived from arch/alpha/lib/checksum.c */ + + +#include <linux/module.h> +#include <linux/string.h> + +#include <asm/byteorder.h> +#include <net/checksum.h> +#include <linux/uaccess.h> +#include <asm/intrinsics.h> + + +/* Vector value operations */ +#define SIGN(x, y) ((0x8000ULL*x)<<y) +#define CARRY(x, y) ((0x0002ULL*x)<<y) +#define SELECT(x, y) ((0x0001ULL*x)<<y) + +#define VR_NEGATE(a, b, c, d) (SIGN(a, 48) + SIGN(b, 32) + SIGN(c, 16) \ + + SIGN(d, 0)) +#define VR_CARRY(a, b, c, d) (CARRY(a, 48) + CARRY(b, 32) + CARRY(c, 16) \ + + CARRY(d, 0)) +#define VR_SELECT(a, b, c, d) (SELECT(a, 48) + SELECT(b, 32) + SELECT(c, 16) \ + + SELECT(d, 0)) + + +/* optimized HEXAGON V3 intrinsic version */ +static inline unsigned short from64to16(u64 x) +{ + u64 sum; + + sum = HEXAGON_P_vrmpyh_PP(x^VR_NEGATE(1, 1, 1, 1), + VR_SELECT(1, 1, 1, 1)); + sum += VR_CARRY(0, 0, 1, 0); + sum = HEXAGON_P_vrmpyh_PP(sum, VR_SELECT(0, 0, 1, 1)); + + return 0xFFFF & sum; +} + +/* + * computes the checksum of the TCP/UDP pseudo-header + * returns a 16-bit checksum, already complemented. + */ +__sum16 csum_tcpudp_magic(unsigned long saddr, unsigned long daddr, + unsigned short len, unsigned short proto, + __wsum sum) +{ + return (__force __sum16)~from64to16( + (__force u64)saddr + (__force u64)daddr + + (__force u64)sum + ((len + proto) << 8)); +} + +__wsum csum_tcpudp_nofold(unsigned long saddr, unsigned long daddr, + unsigned short len, unsigned short proto, + __wsum sum) +{ + u64 result; + + result = (__force u64)saddr + (__force u64)daddr + + (__force u64)sum + ((len + proto) << 8); + + /* Fold down to 32-bits so we don't lose in the typedef-less + network stack. */ + /* 64 to 33 */ + result = (result & 0xffffffffUL) + (result >> 32); + /* 33 to 32 */ + result = (result & 0xffffffffUL) + (result >> 32); + return (__force __wsum)result; +} +EXPORT_SYMBOL(csum_tcpudp_nofold); + +/* + * Do a 64-bit checksum on an arbitrary memory area.. + * + * This isn't a great routine, but it's not _horrible_ either. The + * inner loop could be unrolled a bit further, and there are better + * ways to do the carry, but this is reasonable. + */ + +/* optimized HEXAGON intrinsic version, with over read fixed */ +unsigned int do_csum(const void *voidptr, int len) +{ + u64 sum0, sum1, x0, x1, *ptr8_o, *ptr8_e, *ptr8; + int i, start, mid, end, mask; + const char *ptr = voidptr; + unsigned short *ptr2; + unsigned int *ptr4; + + if (len <= 0) + return 0; + + start = 0xF & (16-(((int) ptr) & 0xF)) ; + mask = 0x7fffffffUL >> HEXAGON_R_cl0_R(len); + start = start & mask ; + + mid = len - start; + end = mid & 0xF; + mid = mid>>4; + sum0 = mid << 18; + sum1 = 0; + + if (start & 1) + sum0 += (u64) (ptr[0] << 8); + ptr2 = (unsigned short *) &ptr[start & 1]; + if (start & 2) + sum1 += (u64) ptr2[0]; + ptr4 = (unsigned int *) &ptr[start & 3]; + if (start & 4) { + sum0 = HEXAGON_P_vrmpyhacc_PP(sum0, + VR_NEGATE(0, 0, 1, 1)^((u64)ptr4[0]), + VR_SELECT(0, 0, 1, 1)); + sum0 += VR_SELECT(0, 0, 1, 0); + } + ptr8 = (u64 *) &ptr[start & 7]; + if (start & 8) { + sum1 = HEXAGON_P_vrmpyhacc_PP(sum1, + VR_NEGATE(1, 1, 1, 1)^(ptr8[0]), + VR_SELECT(1, 1, 1, 1)); + sum1 += VR_CARRY(0, 0, 1, 0); + } + ptr8_o = (u64 *) (ptr + start); + ptr8_e = (u64 *) (ptr + start + 8); + + if (mid) { + x0 = *ptr8_e; ptr8_e += 2; + x1 = *ptr8_o; ptr8_o += 2; + if (mid > 1) + for (i = 0; i < mid-1; i++) { + sum0 = HEXAGON_P_vrmpyhacc_PP(sum0, + x0^VR_NEGATE(1, 1, 1, 1), + VR_SELECT(1, 1, 1, 1)); + sum1 = HEXAGON_P_vrmpyhacc_PP(sum1, + x1^VR_NEGATE(1, 1, 1, 1), + VR_SELECT(1, 1, 1, 1)); + x0 = *ptr8_e; ptr8_e += 2; + x1 = *ptr8_o; ptr8_o += 2; + } + sum0 = HEXAGON_P_vrmpyhacc_PP(sum0, x0^VR_NEGATE(1, 1, 1, 1), + VR_SELECT(1, 1, 1, 1)); + sum1 = HEXAGON_P_vrmpyhacc_PP(sum1, x1^VR_NEGATE(1, 1, 1, 1), + VR_SELECT(1, 1, 1, 1)); + } + + ptr4 = (unsigned int *) &ptr[start + (mid * 16) + (end & 8)]; + if (end & 4) { + sum1 = HEXAGON_P_vrmpyhacc_PP(sum1, + VR_NEGATE(0, 0, 1, 1)^((u64)ptr4[0]), + VR_SELECT(0, 0, 1, 1)); + sum1 += VR_SELECT(0, 0, 1, 0); + } + ptr2 = (unsigned short *) &ptr[start + (mid * 16) + (end & 12)]; + if (end & 2) + sum0 += (u64) ptr2[0]; + + if (end & 1) + sum1 += (u64) ptr[start + (mid * 16) + (end & 14)]; + + ptr8 = (u64 *) &ptr[start + (mid * 16)]; + if (end & 8) { + sum0 = HEXAGON_P_vrmpyhacc_PP(sum0, + VR_NEGATE(1, 1, 1, 1)^(ptr8[0]), + VR_SELECT(1, 1, 1, 1)); + sum0 += VR_CARRY(0, 0, 1, 0); + } + sum0 = HEXAGON_P_vrmpyh_PP((sum0+sum1)^VR_NEGATE(0, 0, 0, 1), + VR_SELECT(0, 0, 1, 1)); + sum0 += VR_NEGATE(0, 0, 0, 1); + sum0 = HEXAGON_P_vrmpyh_PP(sum0, VR_SELECT(0, 0, 1, 1)); + + if (start & 1) + sum0 = (sum0 << 8) | (0xFF & (sum0 >> 8)); + + return 0xFFFF & sum0; +} + +/* + * copy from ds while checksumming, otherwise like csum_partial + */ +__wsum +csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum) +{ + memcpy(dst, src, len); + return csum_partial(dst, len, sum); +} diff --git a/arch/hexagon/lib/io.c b/arch/hexagon/lib/io.c new file mode 100644 index 000000000000..8ae47ba0e705 --- /dev/null +++ b/arch/hexagon/lib/io.c @@ -0,0 +1,91 @@ +/* + * I/O access functions for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <asm/io.h> + +/* These are all FIFO routines! */ + +/* + * __raw_readsw - read words a short at a time + * @addr: source address + * @data: data address + * @len: number of shorts to read + */ +void __raw_readsw(const void __iomem *addr, void *data, int len) +{ + const volatile short int *src = (short int *) addr; + short int *dst = (short int *) data; + + if ((u32)data & 0x1) + panic("unaligned pointer to readsw"); + + while (len-- > 0) + *dst++ = *src; + +} + +/* + * __raw_writesw - read words a short at a time + * @addr: source address + * @data: data address + * @len: number of shorts to read + */ +void __raw_writesw(void __iomem *addr, const void *data, int len) +{ + const short int *src = (short int *)data; + volatile short int *dst = (short int *)addr; + + if ((u32)data & 0x1) + panic("unaligned pointer to writesw"); + + while (len-- > 0) + *dst = *src++; + + +} + +/* Pretty sure len is pre-adjusted for the length of the access already */ +void __raw_readsl(const void __iomem *addr, void *data, int len) +{ + const volatile long *src = (long *) addr; + long *dst = (long *) data; + + if ((u32)data & 0x3) + panic("unaligned pointer to readsl"); + + while (len-- > 0) + *dst++ = *src; + + +} + +void __raw_writesl(void __iomem *addr, const void *data, int len) +{ + const long *src = (long *)data; + volatile long *dst = (long *)addr; + + if ((u32)data & 0x3) + panic("unaligned pointer to writesl"); + + while (len-- > 0) + *dst = *src++; + + +} diff --git a/arch/hexagon/lib/memcpy.S b/arch/hexagon/lib/memcpy.S new file mode 100644 index 000000000000..2101c3395665 --- /dev/null +++ b/arch/hexagon/lib/memcpy.S @@ -0,0 +1,543 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +/* + * Description + * + * library function for memcpy where length bytes are copied from + * ptr_in to ptr_out. ptr_out is returned unchanged. + * Allows any combination of alignment on input and output pointers + * and length from 0 to 2^32-1 + * + * Restrictions + * The arrays should not overlap, the program will produce undefined output + * if they do. + * For blocks less than 16 bytes a byte by byte copy is performed. For + * 8byte alignments, and length multiples, a dword copy is performed up to + * 96bytes + * History + * + * DJH 5/15/09 Initial version 1.0 + * DJH 6/ 1/09 Version 1.1 modified ABI to inlcude R16-R19 + * DJH 7/12/09 Version 1.2 optimized codesize down to 760 was 840 + * DJH 10/14/09 Version 1.3 added special loop for aligned case, was + * overreading bloated codesize back up to 892 + * DJH 4/20/10 Version 1.4 fixed Ldword_loop_epilog loop to prevent loads + * occuring if only 1 left outstanding, fixes bug + * # 3888, corrected for all alignments. Peeled off + * 1 32byte chunk from kernel loop and extended 8byte + * loop at end to solve all combinations and prevent + * over read. Fixed Ldword_loop_prolog to prevent + * overread for blocks less than 48bytes. Reduced + * codesize to 752 bytes + * DJH 4/21/10 version 1.5 1.4 fix broke code for input block ends not + * aligned to dword boundaries,underwriting by 1 + * byte, added detection for this and fixed. A + * little bloat. + * DJH 4/23/10 version 1.6 corrected stack error, R20 was not being restored + * always, fixed the error of R20 being modified + * before it was being saved + * Natural c model + * =============== + * void * memcpy(char * ptr_out, char * ptr_in, int length) { + * int i; + * if(length) for(i=0; i < length; i++) { ptr_out[i] = ptr_in[i]; } + * return(ptr_out); + * } + * + * Optimized memcpy function + * ========================= + * void * memcpy(char * ptr_out, char * ptr_in, int len) { + * int i, prolog, kernel, epilog, mask; + * u8 offset; + * s64 data0, dataF8, data70; + * + * s64 * ptr8_in; + * s64 * ptr8_out; + * s32 * ptr4; + * s16 * ptr2; + * + * offset = ((int) ptr_in) & 7; + * ptr8_in = (s64 *) &ptr_in[-offset]; //read in the aligned pointers + * + * data70 = *ptr8_in++; + * dataF8 = *ptr8_in++; + * + * data0 = HEXAGON_P_valignb_PPp(dataF8, data70, offset); + * + * prolog = 32 - ((int) ptr_out); + * mask = 0x7fffffff >> HEXAGON_R_cl0_R(len); + * prolog = prolog & mask; + * kernel = len - prolog; + * epilog = kernel & 0x1F; + * kernel = kernel>>5; + * + * if (prolog & 1) { ptr_out[0] = (u8) data0; data0 >>= 8; ptr_out += 1;} + * ptr2 = (s16 *) &ptr_out[0]; + * if (prolog & 2) { ptr2[0] = (u16) data0; data0 >>= 16; ptr_out += 2;} + * ptr4 = (s32 *) &ptr_out[0]; + * if (prolog & 4) { ptr4[0] = (u32) data0; data0 >>= 32; ptr_out += 4;} + * + * offset = offset + (prolog & 7); + * if (offset >= 8) { + * data70 = dataF8; + * dataF8 = *ptr8_in++; + * } + * offset = offset & 0x7; + * + * prolog = prolog >> 3; + * if (prolog) for (i=0; i < prolog; i++) { + * data0 = HEXAGON_P_valignb_PPp(dataF8, data70, offset); + * ptr8_out = (s64 *) &ptr_out[0]; *ptr8_out = data0; ptr_out += 8; + * data70 = dataF8; + * dataF8 = *ptr8_in++; + * } + * if(kernel) { kernel -= 1; epilog += 32; } + * if(kernel) for(i=0; i < kernel; i++) { + * data0 = HEXAGON_P_valignb_PPp(dataF8, data70, offset); + * ptr8_out = (s64 *) &ptr_out[0]; *ptr8_out = data0; ptr_out += 8; + * data70 = *ptr8_in++; + * + * data0 = HEXAGON_P_valignb_PPp(data70, dataF8, offset); + * ptr8_out = (s64 *) &ptr_out[0]; *ptr8_out = data0; ptr_out += 8; + * dataF8 = *ptr8_in++; + * + * data0 = HEXAGON_P_valignb_PPp(dataF8, data70, offset); + * ptr8_out = (s64 *) &ptr_out[0]; *ptr8_out = data0; ptr_out += 8; + * data70 = *ptr8_in++; + * + * data0 = HEXAGON_P_valignb_PPp(data70, dataF8, offset); + * ptr8_out = (s64 *) &ptr_out[0]; *ptr8_out = data0; ptr_out += 8; + * dataF8 = *ptr8_in++; + * } + * epilogdws = epilog >> 3; + * if (epilogdws) for (i=0; i < epilogdws; i++) { + * data0 = HEXAGON_P_valignb_PPp(dataF8, data70, offset); + * ptr8_out = (s64 *) &ptr_out[0]; *ptr8_out = data0; ptr_out += 8; + * data70 = dataF8; + * dataF8 = *ptr8_in++; + * } + * data0 = HEXAGON_P_valignb_PPp(dataF8, data70, offset); + * + * ptr4 = (s32 *) &ptr_out[0]; + * if (epilog & 4) { ptr4[0] = (u32) data0; data0 >>= 32; ptr_out += 4;} + * ptr2 = (s16 *) &ptr_out[0]; + * if (epilog & 2) { ptr2[0] = (u16) data0; data0 >>= 16; ptr_out += 2;} + * if (epilog & 1) { *ptr_out++ = (u8) data0; } + * + * return(ptr_out - length); + * } + * + * Codesize : 784 bytes + */ + + +#define ptr_out R0 /* destination pounter */ +#define ptr_in R1 /* source pointer */ +#define len R2 /* length of copy in bytes */ + +#define data70 R13:12 /* lo 8 bytes of non-aligned transfer */ +#define dataF8 R11:10 /* hi 8 bytes of non-aligned transfer */ +#define ldata0 R7:6 /* even 8 bytes chunks */ +#define ldata1 R25:24 /* odd 8 bytes chunks */ +#define data1 R7 /* lower 8 bytes of ldata1 */ +#define data0 R6 /* lower 8 bytes of ldata0 */ + +#define ifbyte p0 /* if transfer has bytes in epilog/prolog */ +#define ifhword p0 /* if transfer has shorts in epilog/prolog */ +#define ifword p0 /* if transfer has words in epilog/prolog */ +#define noprolog p0 /* no prolog, xfer starts at 32byte */ +#define nokernel p1 /* no 32byte multiple block in the transfer */ +#define noepilog p0 /* no epilog, xfer ends on 32byte boundary */ +#define align p2 /* alignment of input rel to 8byte boundary */ +#define kernel1 p0 /* kernel count == 1 */ + +#define dalign R25 /* rel alignment of input to output data */ +#define star3 R16 /* number bytes in prolog - dwords */ +#define rest R8 /* length - prolog bytes */ +#define back R7 /* nr bytes > dword boundary in src block */ +#define epilog R3 /* bytes in epilog */ +#define inc R15:14 /* inc kernel by -1 and defetch ptr by 32 */ +#define kernel R4 /* number of 32byte chunks in kernel */ +#define ptr_in_p_128 R5 /* pointer for prefetch of input data */ +#define mask R8 /* mask used to determine prolog size */ +#define shift R8 /* used to work a shifter to extract bytes */ +#define shift2 R5 /* in epilog to workshifter to extract bytes */ +#define prolog R15 /* bytes in prolog */ +#define epilogdws R15 /* number dwords in epilog */ +#define shiftb R14 /* used to extract bytes */ +#define offset R9 /* same as align in reg */ +#define ptr_out_p_32 R17 /* pointer to output dczero */ +#define align888 R14 /* if simple dword loop can be used */ +#define len8 R9 /* number of dwords in length */ +#define over R20 /* nr of bytes > last inp buf dword boundary */ + +#define ptr_in_p_128kernel R5:4 /* packed fetch pointer & kernel cnt */ + + .section .text + .p2align 4 + .global memcpy + .type memcpy, @function +memcpy: +{ + p2 = cmp.eq(len, #0); /* =0 */ + align888 = or(ptr_in, ptr_out); /* %8 < 97 */ + p0 = cmp.gtu(len, #23); /* %1, <24 */ + p1 = cmp.eq(ptr_in, ptr_out); /* attempt to overwrite self */ +} +{ + p1 = or(p2, p1); + p3 = cmp.gtu(len, #95); /* %8 < 97 */ + align888 = or(align888, len); /* %8 < 97 */ + len8 = lsr(len, #3); /* %8 < 97 */ +} +{ + dcfetch(ptr_in); /* zero/ptrin=ptrout causes fetch */ + p2 = bitsclr(align888, #7); /* %8 < 97 */ + if(p1) jumpr r31; /* =0 */ +} +{ + p2 = and(p2,!p3); /* %8 < 97 */ + if (p2.new) len = add(len, #-8); /* %8 < 97 */ + if (p2.new) jump:NT .Ldwordaligned; /* %8 < 97 */ +} +{ + if(!p0) jump .Lbytes23orless; /* %1, <24 */ + mask.l = #LO(0x7fffffff); + /* all bytes before line multiples of data */ + prolog = sub(#0, ptr_out); +} +{ + /* save r31 on stack, decrement sp by 16 */ + allocframe(#24); + mask.h = #HI(0x7fffffff); + ptr_in_p_128 = add(ptr_in, #32); + back = cl0(len); +} +{ + memd(sp+#0) = R17:16; /* save r16,r17 on stack6 */ + r31.l = #LO(.Lmemcpy_return); /* set up final return pointer */ + prolog &= lsr(mask, back); + offset = and(ptr_in, #7); +} +{ + memd(sp+#8) = R25:24; /* save r25,r24 on stack */ + dalign = sub(ptr_out, ptr_in); + r31.h = #HI(.Lmemcpy_return); /* set up final return pointer */ +} +{ + /* see if there if input buffer end if aligned */ + over = add(len, ptr_in); + back = add(len, offset); + memd(sp+#16) = R21:20; /* save r20,r21 on stack */ +} +{ + noprolog = bitsclr(prolog, #7); + prolog = and(prolog, #31); + dcfetch(ptr_in_p_128); + ptr_in_p_128 = add(ptr_in_p_128, #32); +} +{ + kernel = sub(len, prolog); + shift = asl(prolog, #3); + star3 = and(prolog, #7); + ptr_in = and(ptr_in, #-8); +} +{ + prolog = lsr(prolog, #3); + epilog = and(kernel, #31); + ptr_out_p_32 = add(ptr_out, prolog); + over = and(over, #7); +} +{ + p3 = cmp.gtu(back, #8); + kernel = lsr(kernel, #5); + dcfetch(ptr_in_p_128); + ptr_in_p_128 = add(ptr_in_p_128, #32); +} +{ + p1 = cmp.eq(prolog, #0); + if(!p1.new) prolog = add(prolog, #1); + dcfetch(ptr_in_p_128); /* reserve the line 64bytes on */ + ptr_in_p_128 = add(ptr_in_p_128, #32); +} +{ + nokernel = cmp.eq(kernel,#0); + dcfetch(ptr_in_p_128); /* reserve the line 64bytes on */ + ptr_in_p_128 = add(ptr_in_p_128, #32); + shiftb = and(shift, #8); +} +{ + dcfetch(ptr_in_p_128); /* reserve the line 64bytes on */ + ptr_in_p_128 = add(ptr_in_p_128, #32); + if(nokernel) jump .Lskip64; + p2 = cmp.eq(kernel, #1); /* skip ovr if kernel == 0 */ +} +{ + dczeroa(ptr_out_p_32); + /* don't advance pointer */ + if(!p2) ptr_out_p_32 = add(ptr_out_p_32, #32); +} +{ + dalign = and(dalign, #31); + dczeroa(ptr_out_p_32); +} +.Lskip64: +{ + data70 = memd(ptr_in++#16); + if(p3) dataF8 = memd(ptr_in+#8); + if(noprolog) jump .Lnoprolog32; + align = offset; +} +/* upto initial 7 bytes */ +{ + ldata0 = valignb(dataF8, data70, align); + ifbyte = tstbit(shift,#3); + offset = add(offset, star3); +} +{ + if(ifbyte) memb(ptr_out++#1) = data0; + ldata0 = lsr(ldata0, shiftb); + shiftb = and(shift, #16); + ifhword = tstbit(shift,#4); +} +{ + if(ifhword) memh(ptr_out++#2) = data0; + ldata0 = lsr(ldata0, shiftb); + ifword = tstbit(shift,#5); + p2 = cmp.gtu(offset, #7); +} +{ + if(ifword) memw(ptr_out++#4) = data0; + if(p2) data70 = dataF8; + if(p2) dataF8 = memd(ptr_in++#8); /* another 8 bytes */ + align = offset; +} +.Lnoprolog32: +{ + p3 = sp1loop0(.Ldword_loop_prolog, prolog) + rest = sub(len, star3); /* whats left after the loop */ + p0 = cmp.gt(over, #0); +} + if(p0) rest = add(rest, #16); +.Ldword_loop_prolog: +{ + if(p3) memd(ptr_out++#8) = ldata0; + ldata0 = valignb(dataF8, data70, align); + p0 = cmp.gt(rest, #16); +} +{ + data70 = dataF8; + if(p0) dataF8 = memd(ptr_in++#8); + rest = add(rest, #-8); +}:endloop0 +.Lkernel: +{ + /* kernel is at least 32bytes */ + p3 = cmp.gtu(kernel, #0); + /* last itn. remove edge effects */ + if(p3.new) kernel = add(kernel, #-1); + /* dealt with in last dword loop */ + if(p3.new) epilog = add(epilog, #32); +} +{ + nokernel = cmp.eq(kernel, #0); /* after adjustment, recheck */ + if(nokernel.new) jump:NT .Lepilog; /* likely not taken */ + inc = combine(#32, #-1); + p3 = cmp.gtu(dalign, #24); +} +{ + if(p3) jump .Lodd_alignment; +} +{ + loop0(.Loword_loop_25to31, kernel); + kernel1 = cmp.gtu(kernel, #1); + rest = kernel; +} + .falign +.Loword_loop_25to31: +{ + dcfetch(ptr_in_p_128); /* prefetch 4 lines ahead */ + if(kernel1) ptr_out_p_32 = add(ptr_out_p_32, #32); +} +{ + dczeroa(ptr_out_p_32); /* reserve the next 32bytes in cache */ + p3 = cmp.eq(kernel, rest); +} +{ + /* kernel -= 1 */ + ptr_in_p_128kernel = vaddw(ptr_in_p_128kernel, inc); + /* kill write on first iteration */ + if(!p3) memd(ptr_out++#8) = ldata1; + ldata1 = valignb(dataF8, data70, align); + data70 = memd(ptr_in++#8); +} +{ + memd(ptr_out++#8) = ldata0; + ldata0 = valignb(data70, dataF8, align); + dataF8 = memd(ptr_in++#8); +} +{ + memd(ptr_out++#8) = ldata1; + ldata1 = valignb(dataF8, data70, align); + data70 = memd(ptr_in++#8); +} +{ + memd(ptr_out++#8) = ldata0; + ldata0 = valignb(data70, dataF8, align); + dataF8 = memd(ptr_in++#8); + kernel1 = cmp.gtu(kernel, #1); +}:endloop0 +{ + memd(ptr_out++#8) = ldata1; + jump .Lepilog; +} +.Lodd_alignment: +{ + loop0(.Loword_loop_00to24, kernel); + kernel1 = cmp.gtu(kernel, #1); + rest = add(kernel, #-1); +} + .falign +.Loword_loop_00to24: +{ + dcfetch(ptr_in_p_128); /* prefetch 4 lines ahead */ + ptr_in_p_128kernel = vaddw(ptr_in_p_128kernel, inc); + if(kernel1) ptr_out_p_32 = add(ptr_out_p_32, #32); +} +{ + dczeroa(ptr_out_p_32); /* reserve the next 32bytes in cache */ +} +{ + memd(ptr_out++#8) = ldata0; + ldata0 = valignb(dataF8, data70, align); + data70 = memd(ptr_in++#8); +} +{ + memd(ptr_out++#8) = ldata0; + ldata0 = valignb(data70, dataF8, align); + dataF8 = memd(ptr_in++#8); +} +{ + memd(ptr_out++#8) = ldata0; + ldata0 = valignb(dataF8, data70, align); + data70 = memd(ptr_in++#8); +} +{ + memd(ptr_out++#8) = ldata0; + ldata0 = valignb(data70, dataF8, align); + dataF8 = memd(ptr_in++#8); + kernel1 = cmp.gtu(kernel, #1); +}:endloop0 +.Lepilog: +{ + noepilog = cmp.eq(epilog,#0); + epilogdws = lsr(epilog, #3); + kernel = and(epilog, #7); +} +{ + if(noepilog) jumpr r31; + if(noepilog) ptr_out = sub(ptr_out, len); + p3 = cmp.eq(epilogdws, #0); + shift2 = asl(epilog, #3); +} +{ + shiftb = and(shift2, #32); + ifword = tstbit(epilog,#2); + if(p3) jump .Lepilog60; + if(!p3) epilog = add(epilog, #-16); +} +{ + loop0(.Ldword_loop_epilog, epilogdws); + /* stop criteria is lsbs unless = 0 then its 8 */ + p3 = cmp.eq(kernel, #0); + if(p3.new) kernel= #8; + p1 = cmp.gt(over, #0); +} + /* if not aligned to end of buffer execute 1 more iteration */ + if(p1) kernel= #0; +.Ldword_loop_epilog: +{ + memd(ptr_out++#8) = ldata0; + ldata0 = valignb(dataF8, data70, align); + p3 = cmp.gt(epilog, kernel); +} +{ + data70 = dataF8; + if(p3) dataF8 = memd(ptr_in++#8); + epilog = add(epilog, #-8); +}:endloop0 +/* copy last 7 bytes */ +.Lepilog60: +{ + if(ifword) memw(ptr_out++#4) = data0; + ldata0 = lsr(ldata0, shiftb); + ifhword = tstbit(epilog,#1); + shiftb = and(shift2, #16); +} +{ + if(ifhword) memh(ptr_out++#2) = data0; + ldata0 = lsr(ldata0, shiftb); + ifbyte = tstbit(epilog,#0); + if(ifbyte.new) len = add(len, #-1); +} +{ + if(ifbyte) memb(ptr_out) = data0; + ptr_out = sub(ptr_out, len); /* return dest pointer */ + jumpr r31; +} +/* do byte copy for small n */ +.Lbytes23orless: +{ + p3 = sp1loop0(.Lbyte_copy, len); + len = add(len, #-1); +} +.Lbyte_copy: +{ + data0 = memb(ptr_in++#1); + if(p3) memb(ptr_out++#1) = data0; +}:endloop0 +{ + memb(ptr_out) = data0; + ptr_out = sub(ptr_out, len); + jumpr r31; +} +/* do dword copies for aligned in, out and length */ +.Ldwordaligned: +{ + p3 = sp1loop0(.Ldword_copy, len8); +} +.Ldword_copy: +{ + if(p3) memd(ptr_out++#8) = ldata0; + ldata0 = memd(ptr_in++#8); +}:endloop0 +{ + memd(ptr_out) = ldata0; + ptr_out = sub(ptr_out, len); + jumpr r31; /* return to function caller */ +} +.Lmemcpy_return: + r21:20 = memd(sp+#16); /* restore r20+r21 */ +{ + r25:24 = memd(sp+#8); /* restore r24+r25 */ + r17:16 = memd(sp+#0); /* restore r16+r17 */ +} + deallocframe; /* restore r31 and incrment stack by 16 */ + jumpr r31 diff --git a/arch/hexagon/lib/memset.S b/arch/hexagon/lib/memset.S new file mode 100644 index 000000000000..26d961439ab0 --- /dev/null +++ b/arch/hexagon/lib/memset.S @@ -0,0 +1,315 @@ +/* + * Copyright (c) 2011 Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + + +/* HEXAGON assembly optimized memset */ +/* Replaces the standard library function memset */ + + + .macro HEXAGON_OPT_FUNC_BEGIN name + .text + .p2align 4 + .globl \name + .type \name, @function +\name: + .endm + + .macro HEXAGON_OPT_FUNC_FINISH name + .size \name, . - \name + .endm + +/* FUNCTION: memset (v2 version) */ +#if __HEXAGON_ARCH__ < 3 +HEXAGON_OPT_FUNC_BEGIN memset + { + r6 = #8 + r7 = extractu(r0, #3 , #0) + p0 = cmp.eq(r2, #0) + p1 = cmp.gtu(r2, #7) + } + { + r4 = vsplatb(r1) + r8 = r0 /* leave r0 intact for return val */ + r9 = sub(r6, r7) /* bytes until double alignment */ + if p0 jumpr r31 /* count == 0, so return */ + } + { + r3 = #0 + r7 = #0 + p0 = tstbit(r9, #0) + if p1 jump 2f /* skip byte loop */ + } + +/* less than 8 bytes to set, so just set a byte at a time and return */ + + loop0(1f, r2) /* byte loop */ + .falign +1: /* byte loop */ + { + memb(r8++#1) = r4 + }:endloop0 + jumpr r31 + .falign +2: /* skip byte loop */ + { + r6 = #1 + p0 = tstbit(r9, #1) + p1 = cmp.eq(r2, #1) + if !p0 jump 3f /* skip initial byte store */ + } + { + memb(r8++#1) = r4 + r3:2 = sub(r3:2, r7:6) + if p1 jumpr r31 + } + .falign +3: /* skip initial byte store */ + { + r6 = #2 + p0 = tstbit(r9, #2) + p1 = cmp.eq(r2, #2) + if !p0 jump 4f /* skip initial half store */ + } + { + memh(r8++#2) = r4 + r3:2 = sub(r3:2, r7:6) + if p1 jumpr r31 + } + .falign +4: /* skip initial half store */ + { + r6 = #4 + p0 = cmp.gtu(r2, #7) + p1 = cmp.eq(r2, #4) + if !p0 jump 5f /* skip initial word store */ + } + { + memw(r8++#4) = r4 + r3:2 = sub(r3:2, r7:6) + p0 = cmp.gtu(r2, #11) + if p1 jumpr r31 + } + .falign +5: /* skip initial word store */ + { + r10 = lsr(r2, #3) + p1 = cmp.eq(r3, #1) + if !p0 jump 7f /* skip double loop */ + } + { + r5 = r4 + r6 = #8 + loop0(6f, r10) /* double loop */ + } + +/* set bytes a double word at a time */ + + .falign +6: /* double loop */ + { + memd(r8++#8) = r5:4 + r3:2 = sub(r3:2, r7:6) + p1 = cmp.eq(r2, #8) + }:endloop0 + .falign +7: /* skip double loop */ + { + p0 = tstbit(r2, #2) + if p1 jumpr r31 + } + { + r6 = #4 + p0 = tstbit(r2, #1) + p1 = cmp.eq(r2, #4) + if !p0 jump 8f /* skip final word store */ + } + { + memw(r8++#4) = r4 + r3:2 = sub(r3:2, r7:6) + if p1 jumpr r31 + } + .falign +8: /* skip final word store */ + { + p1 = cmp.eq(r2, #2) + if !p0 jump 9f /* skip final half store */ + } + { + memh(r8++#2) = r4 + if p1 jumpr r31 + } + .falign +9: /* skip final half store */ + { + memb(r8++#1) = r4 + jumpr r31 + } +HEXAGON_OPT_FUNC_FINISH memset +#endif + + +/* FUNCTION: memset (v3 and higher version) */ +#if __HEXAGON_ARCH__ >= 3 +HEXAGON_OPT_FUNC_BEGIN memset + { + r7=vsplatb(r1) + r6 = r0 + if (r2==#0) jump:nt .L1 + } + { + r5:4=combine(r7,r7) + p0 = cmp.gtu(r2,#8) + if (p0.new) jump:nt .L3 + } + { + r3 = r0 + loop0(.L47,r2) + } + .falign +.L47: + { + memb(r3++#1) = r1 + }:endloop0 /* start=.L47 */ + jumpr r31 +.L3: + { + p0 = tstbit(r0,#0) + if (!p0.new) jump:nt .L8 + p1 = cmp.eq(r2, #1) + } + { + r6 = add(r0, #1) + r2 = add(r2,#-1) + memb(r0) = r1 + if (p1) jump .L1 + } +.L8: + { + p0 = tstbit(r6,#1) + if (!p0.new) jump:nt .L10 + } + { + r2 = add(r2,#-2) + memh(r6++#2) = r7 + p0 = cmp.eq(r2, #2) + if (p0.new) jump:nt .L1 + } +.L10: + { + p0 = tstbit(r6,#2) + if (!p0.new) jump:nt .L12 + } + { + r2 = add(r2,#-4) + memw(r6++#4) = r7 + p0 = cmp.eq(r2, #4) + if (p0.new) jump:nt .L1 + } +.L12: + { + p0 = cmp.gtu(r2,#127) + if (!p0.new) jump:nt .L14 + } + r3 = and(r6,#31) + if (r3==#0) jump:nt .L17 + { + memd(r6++#8) = r5:4 + r2 = add(r2,#-8) + } + r3 = and(r6,#31) + if (r3==#0) jump:nt .L17 + { + memd(r6++#8) = r5:4 + r2 = add(r2,#-8) + } + r3 = and(r6,#31) + if (r3==#0) jump:nt .L17 + { + memd(r6++#8) = r5:4 + r2 = add(r2,#-8) + } +.L17: + { + r3 = lsr(r2,#5) + if (r1!=#0) jump:nt .L18 + } + { + r8 = r3 + r3 = r6 + loop0(.L46,r3) + } + .falign +.L46: + { + dczeroa(r6) + r6 = add(r6,#32) + r2 = add(r2,#-32) + }:endloop0 /* start=.L46 */ +.L14: + { + p0 = cmp.gtu(r2,#7) + if (!p0.new) jump:nt .L28 + r8 = lsr(r2,#3) + } + loop0(.L44,r8) + .falign +.L44: + { + memd(r6++#8) = r5:4 + r2 = add(r2,#-8) + }:endloop0 /* start=.L44 */ +.L28: + { + p0 = tstbit(r2,#2) + if (!p0.new) jump:nt .L33 + } + { + r2 = add(r2,#-4) + memw(r6++#4) = r7 + } +.L33: + { + p0 = tstbit(r2,#1) + if (!p0.new) jump:nt .L35 + } + { + r2 = add(r2,#-2) + memh(r6++#2) = r7 + } +.L35: + p0 = cmp.eq(r2,#1) + if (p0) memb(r6) = r1 +.L1: + jumpr r31 +.L18: + loop0(.L45,r3) + .falign +.L45: + dczeroa(r6) + { + memd(r6++#8) = r5:4 + r2 = add(r2,#-32) + } + memd(r6++#8) = r5:4 + memd(r6++#8) = r5:4 + { + memd(r6++#8) = r5:4 + }:endloop0 /* start=.L45 */ + jump .L14 +HEXAGON_OPT_FUNC_FINISH memset +#endif diff --git a/arch/hexagon/mm/Makefile b/arch/hexagon/mm/Makefile new file mode 100644 index 000000000000..1a0be4d576e1 --- /dev/null +++ b/arch/hexagon/mm/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for Hexagon memory management subsystem +# + +obj-y := init.o pgalloc.o ioremap.o uaccess.o vm_fault.o cache.o +obj-y += copy_to_user.o copy_from_user.o strnlen_user.o vm_tlb.o diff --git a/arch/hexagon/mm/cache.c b/arch/hexagon/mm/cache.c new file mode 100644 index 000000000000..c5cf6ee27587 --- /dev/null +++ b/arch/hexagon/mm/cache.c @@ -0,0 +1,128 @@ +/* + * Cache management functions for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/mm.h> +#include <asm/cacheflush.h> +#include <asm/hexagon_vm.h> + +#define spanlines(start, end) \ + (((end - (start & ~(LINESIZE - 1))) >> LINEBITS) + 1) + +void flush_dcache_range(unsigned long start, unsigned long end) +{ + unsigned long lines = spanlines(start, end-1); + unsigned long i, flags; + + start &= ~(LINESIZE - 1); + + local_irq_save(flags); + + for (i = 0; i < lines; i++) { + __asm__ __volatile__ ( + " dccleaninva(%0); " + : + : "r" (start) + ); + start += LINESIZE; + } + local_irq_restore(flags); +} + +void flush_icache_range(unsigned long start, unsigned long end) +{ + unsigned long lines = spanlines(start, end-1); + unsigned long i, flags; + + start &= ~(LINESIZE - 1); + + local_irq_save(flags); + + for (i = 0; i < lines; i++) { + __asm__ __volatile__ ( + " dccleana(%0); " + " icinva(%0); " + : + : "r" (start) + ); + start += LINESIZE; + } + __asm__ __volatile__ ( + "isync" + ); + local_irq_restore(flags); +} + +void hexagon_clean_dcache_range(unsigned long start, unsigned long end) +{ + unsigned long lines = spanlines(start, end-1); + unsigned long i, flags; + + start &= ~(LINESIZE - 1); + + local_irq_save(flags); + + for (i = 0; i < lines; i++) { + __asm__ __volatile__ ( + " dccleana(%0); " + : + : "r" (start) + ); + start += LINESIZE; + } + local_irq_restore(flags); +} + +void hexagon_inv_dcache_range(unsigned long start, unsigned long end) +{ + unsigned long lines = spanlines(start, end-1); + unsigned long i, flags; + + start &= ~(LINESIZE - 1); + + local_irq_save(flags); + + for (i = 0; i < lines; i++) { + __asm__ __volatile__ ( + " dcinva(%0); " + : + : "r" (start) + ); + start += LINESIZE; + } + local_irq_restore(flags); +} + + + + +/* + * This is just really brutal and shouldn't be used anyways, + * especially on V2. Left here just in case. + */ +void flush_cache_all_hexagon(void) +{ + unsigned long flags; + local_irq_save(flags); + __vmcache_ickill(); + __vmcache_dckill(); + __vmcache_l2kill(); + local_irq_restore(flags); + mb(); +} diff --git a/arch/hexagon/mm/copy_from_user.S b/arch/hexagon/mm/copy_from_user.S new file mode 100644 index 000000000000..8eb1d4d61a3d --- /dev/null +++ b/arch/hexagon/mm/copy_from_user.S @@ -0,0 +1,114 @@ +/* + * User memory copy functions for kernel + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +/* + * The right way to do this involves valignb + * The easy way to do this is only speed up src/dest similar alignment. + */ + +/* + * Copy to/from user are the same, except that for packets with a load and + * a store, I don't know how to tell which kind of exception we got. + * Therefore, we duplicate the function, and handle faulting addresses + * differently for each function + */ + +/* + * copy from user: loads can fault + */ +#define src_sav r13 +#define dst_sav r12 +#define src_dst_sav r13:12 +#define d_dbuf r15:14 +#define w_dbuf r15 + +#define dst r0 +#define src r1 +#define bytes r2 +#define loopcount r5 + +#define FUNCNAME __copy_from_user_hexagon +#include "copy_user_template.S" + + /* LOAD FAULTS from COPY_FROM_USER */ + + /* Alignment loop. r2 has been updated. Return it. */ + .falign +1009: +2009: +4009: + { + r0 = r2 + jumpr r31 + } + /* Normal copy loops. Do epilog. Use src-src_sav to compute distance */ + /* X - (A - B) == X + B - A */ + .falign +8089: + { + memd(dst) = d_dbuf + r2 += sub(src_sav,src) + } + { + r0 = r2 + jumpr r31 + } + .falign +4089: + { + memw(dst) = w_dbuf + r2 += sub(src_sav,src) + } + { + r0 = r2 + jumpr r31 + } + .falign +2089: + { + memh(dst) = w_dbuf + r2 += sub(src_sav,src) + } + { + r0 = r2 + jumpr r31 + } + .falign +1089: + { + memb(dst) = w_dbuf + r2 += sub(src_sav,src) + } + { + r0 = r2 + jumpr r31 + } + + /* COPY FROM USER: only loads can fail */ + + .section __ex_table,"a" + .long 1000b,1009b + .long 2000b,2009b + .long 4000b,4009b + .long 8080b,8089b + .long 4080b,4089b + .long 2080b,2089b + .long 1080b,1089b + .previous diff --git a/arch/hexagon/mm/copy_to_user.S b/arch/hexagon/mm/copy_to_user.S new file mode 100644 index 000000000000..cb9740ed9e7d --- /dev/null +++ b/arch/hexagon/mm/copy_to_user.S @@ -0,0 +1,92 @@ +/* + * User memory copying routines for the Hexagon Kernel + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +/* The right way to do this involves valignb + * The easy way to do this is only speed up src/dest similar alignment. + */ + +/* + * Copy to/from user are the same, except that for packets with a load and + * a store, I don't know how to tell which kind of exception we got. + * Therefore, we duplicate the function, and handle faulting addresses + * differently for each function + */ + +/* + * copy to user: stores can fault + */ +#define src_sav r13 +#define dst_sav r12 +#define src_dst_sav r13:12 +#define d_dbuf r15:14 +#define w_dbuf r15 + +#define dst r0 +#define src r1 +#define bytes r2 +#define loopcount r5 + +#define FUNCNAME __copy_to_user_hexagon +#include "copy_user_template.S" + + /* STORE FAULTS from COPY_TO_USER */ + .falign +1109: +2109: +4109: + /* Alignment loop. r2 has been updated. Return it. */ + { + r0 = r2 + jumpr r31 + } + /* Normal copy loops. Use dst-dst_sav to compute distance */ + /* dst holds best write, no need to unwind any loops */ + /* X - (A - B) == X + B - A */ + .falign +8189: +8199: +4189: +4199: +2189: +2199: +1189: +1199: + { + r2 += sub(dst_sav,dst) + } + { + r0 = r2 + jumpr r31 + } + + /* COPY TO USER: only stores can fail */ + .section __ex_table,"a" + .long 1100b,1109b + .long 2100b,2109b + .long 4100b,4109b + .long 8180b,8189b + .long 8190b,8199b + .long 4180b,4189b + .long 4190b,4199b + .long 2180b,2189b + .long 2190b,2199b + .long 1180b,1189b + .long 1190b,1199b + .previous diff --git a/arch/hexagon/mm/copy_user_template.S b/arch/hexagon/mm/copy_user_template.S new file mode 100644 index 000000000000..08d7d7b23daa --- /dev/null +++ b/arch/hexagon/mm/copy_user_template.S @@ -0,0 +1,185 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +/* Numerology: + * WXYZ + * W: width in bytes + * X: Load=0, Store=1 + * Y: Location 0=preamble,8=loop,9=epilog + * Z: Location=0,handler=9 + */ + .text + .global FUNCNAME + .type FUNCNAME, @function + .p2align 5 +FUNCNAME: + { + p0 = cmp.gtu(bytes,#0) + if (!p0.new) jump:nt .Ldone + r3 = or(dst,src) + r4 = xor(dst,src) + } + { + p1 = cmp.gtu(bytes,#15) + p0 = bitsclr(r3,#7) + if (!p0.new) jump:nt .Loop_not_aligned_8 + src_dst_sav = combine(src,dst) + } + + { + loopcount = lsr(bytes,#3) + if (!p1) jump .Lsmall + } + p3=sp1loop0(.Loop8,loopcount) +.Loop8: +8080: +8180: + { + if (p3) memd(dst++#8) = d_dbuf + d_dbuf = memd(src++#8) + }:endloop0 +8190: + { + memd(dst++#8) = d_dbuf + bytes -= asl(loopcount,#3) + jump .Lsmall + } + +.Loop_not_aligned_8: + { + p0 = bitsclr(r4,#7) + if (p0.new) jump:nt .Lalign + } + { + p0 = bitsclr(r3,#3) + if (!p0.new) jump:nt .Loop_not_aligned_4 + p1 = cmp.gtu(bytes,#7) + } + + { + if (!p1) jump .Lsmall + loopcount = lsr(bytes,#2) + } + p3=sp1loop0(.Loop4,loopcount) +.Loop4: +4080: +4180: + { + if (p3) memw(dst++#4) = w_dbuf + w_dbuf = memw(src++#4) + }:endloop0 +4190: + { + memw(dst++#4) = w_dbuf + bytes -= asl(loopcount,#2) + jump .Lsmall + } + +.Loop_not_aligned_4: + { + p0 = bitsclr(r3,#1) + if (!p0.new) jump:nt .Loop_not_aligned + p1 = cmp.gtu(bytes,#3) + } + + { + if (!p1) jump .Lsmall + loopcount = lsr(bytes,#1) + } + p3=sp1loop0(.Loop2,loopcount) +.Loop2: +2080: +2180: + { + if (p3) memh(dst++#2) = w_dbuf + w_dbuf = memuh(src++#2) + }:endloop0 +2190: + { + memh(dst++#2) = w_dbuf + bytes -= asl(loopcount,#1) + jump .Lsmall + } + +.Loop_not_aligned: /* Works for as small as one byte */ + p3=sp1loop0(.Loop1,bytes) +.Loop1: +1080: +1180: + { + if (p3) memb(dst++#1) = w_dbuf + w_dbuf = memub(src++#1) + }:endloop0 + /* Done */ +1190: + { + memb(dst) = w_dbuf + jumpr r31 + r0 = #0 + } + +.Lsmall: + { + p0 = cmp.gtu(bytes,#0) + if (p0.new) jump:nt .Loop_not_aligned + } +.Ldone: + { + r0 = #0 + jumpr r31 + } + .falign +.Lalign: +1000: + { + if (p0.new) w_dbuf = memub(src) + p0 = tstbit(src,#0) + if (!p1) jump .Lsmall + } +1100: + { + if (p0) memb(dst++#1) = w_dbuf + if (p0) bytes = add(bytes,#-1) + if (p0) src = add(src,#1) + } +2000: + { + if (p0.new) w_dbuf = memuh(src) + p0 = tstbit(src,#1) + if (!p1) jump .Lsmall + } +2100: + { + if (p0) memh(dst++#2) = w_dbuf + if (p0) bytes = add(bytes,#-2) + if (p0) src = add(src,#2) + } +4000: + { + if (p0.new) w_dbuf = memw(src) + p0 = tstbit(src,#2) + if (!p1) jump .Lsmall + } +4100: + { + if (p0) memw(dst++#4) = w_dbuf + if (p0) bytes = add(bytes,#-4) + if (p0) src = add(src,#4) + jump FUNCNAME + } + .size FUNCNAME,.-FUNCNAME diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c new file mode 100644 index 000000000000..b57d741750b2 --- /dev/null +++ b/arch/hexagon/mm/init.c @@ -0,0 +1,276 @@ +/* + * Memory subsystem initialization for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/bootmem.h> +#include <asm/atomic.h> +#include <linux/highmem.h> +#include <asm/tlb.h> +#include <asm/sections.h> +#include <asm/vm_mmu.h> + +/* + * Define a startpg just past the end of the kernel image and a lastpg + * that corresponds to the end of real or simulated platform memory. + */ +#define bootmem_startpg (PFN_UP(((unsigned long) _end) - PAGE_OFFSET)) + +unsigned long bootmem_lastpg; /* Should be set by platform code */ + +/* Set as variable to limit PMD copies */ +int max_kernel_seg = 0x303; + +/* think this should be (page_size-1) the way it's used...*/ +unsigned long zero_page_mask; + +/* indicate pfn's of high memory */ +unsigned long highstart_pfn, highend_pfn; + +/* struct mmu_gather defined in asm-generic.h; */ +DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); + +/* Default cache attribute for newly created page tables */ +unsigned long _dflt_cache_att = CACHEDEF; + +/* + * The current "generation" of kernel map, which should not roll + * over until Hell freezes over. Actual bound in years needs to be + * calculated to confirm. + */ +DEFINE_SPINLOCK(kmap_gen_lock); + +/* checkpatch says don't init this to 0. */ +unsigned long long kmap_generation; + +/* + * mem_init - initializes memory + * + * Frees up bootmem + * Fixes up more stuff for HIGHMEM + * Calculates and displays memory available/used + */ +void __init mem_init(void) +{ + /* No idea where this is actually declared. Seems to evade LXR. */ + totalram_pages += free_all_bootmem(); + num_physpages = bootmem_lastpg; /* seriously, what? */ + + printk(KERN_INFO "totalram_pages = %ld\n", totalram_pages); + + /* + * To-Do: someone somewhere should wipe out the bootmem map + * after we're done? + */ + + /* + * This can be moved to some more virtual-memory-specific + * initialization hook at some point. Set the init_mm + * descriptors "context" value to point to the initial + * kernel segment table's physical address. + */ + init_mm.context.ptbase = __pa(init_mm.pgd); +} + +/* + * free_initmem - frees memory used by stuff declared with __init + * + * Todo: free pages between __init_begin and __init_end; possibly + * some devtree related stuff as well. + */ +void __init_refok free_initmem(void) +{ +} + +/* + * free_initrd_mem - frees... initrd memory. + * @start - start of init memory + * @end - end of init memory + * + * Apparently has to be passed the address of the initrd memory. + * + * Wrapped by #ifdef CONFIG_BLKDEV_INITRD + */ +void free_initrd_mem(unsigned long start, unsigned long end) +{ +} + +void sync_icache_dcache(pte_t pte) +{ + unsigned long addr; + struct page *page; + + page = pte_page(pte); + addr = (unsigned long) page_address(page); + + __vmcache_idsync(addr, PAGE_SIZE); +} + +/* + * In order to set up page allocator "nodes", + * somebody has to call free_area_init() for UMA. + * + * In this mode, we only have one pg_data_t + * structure: contig_mem_data. + */ +void __init paging_init(void) +{ + unsigned long zones_sizes[MAX_NR_ZONES] = {0, }; + + /* + * This is not particularly well documented anywhere, but + * give ZONE_NORMAL all the memory, including the big holes + * left by the kernel+bootmem_map which are already left as reserved + * in the bootmem_map; free_area_init should see those bits and + * adjust accordingly. + */ + + zones_sizes[ZONE_NORMAL] = max_low_pfn; + + free_area_init(zones_sizes); /* sets up the zonelists and mem_map */ + + /* + * Start of high memory area. Will probably need something more + * fancy if we... get more fancy. + */ + high_memory = (void *)((bootmem_lastpg + 1) << PAGE_SHIFT); +} + +#ifndef DMA_RESERVE +#define DMA_RESERVE (4) +#endif + +#define DMA_CHUNKSIZE (1<<22) +#define DMA_RESERVED_BYTES (DMA_RESERVE * DMA_CHUNKSIZE) + +/* + * Pick out the memory size. We look for mem=size, + * where size is "size[KkMm]" + */ +static int __init early_mem(char *p) +{ + unsigned long size; + char *endp; + + size = memparse(p, &endp); + + bootmem_lastpg = PFN_DOWN(size); + + return 0; +} +early_param("mem", early_mem); + +size_t hexagon_coherent_pool_size = (size_t) (DMA_RESERVE << 22); + +void __init setup_arch_memory(void) +{ + int bootmap_size; + /* XXX Todo: this probably should be cleaned up */ + u32 *segtable = (u32 *) &swapper_pg_dir[0]; + u32 *segtable_end; + + /* + * Set up boot memory allocator + * + * The Gorman book also talks about these functions. + * This needs to change for highmem setups. + */ + + /* Memory size needs to be a multiple of 16M */ + bootmem_lastpg = PFN_DOWN((bootmem_lastpg << PAGE_SHIFT) & + ~((BIG_KERNEL_PAGE_SIZE) - 1)); + + /* + * Reserve the top DMA_RESERVE bytes of RAM for DMA (uncached) + * memory allocation + */ + bootmap_size = init_bootmem(bootmem_startpg, bootmem_lastpg - + PFN_DOWN(DMA_RESERVED_BYTES)); + + printk(KERN_INFO "bootmem_startpg: 0x%08lx\n", bootmem_startpg); + printk(KERN_INFO "bootmem_lastpg: 0x%08lx\n", bootmem_lastpg); + printk(KERN_INFO "bootmap_size: %d\n", bootmap_size); + printk(KERN_INFO "max_low_pfn: 0x%08lx\n", max_low_pfn); + + /* + * The default VM page tables (will be) populated with + * VA=PA+PAGE_OFFSET mapping. We go in and invalidate entries + * higher than what we have memory for. + */ + + /* this is pointer arithmetic; each entry covers 4MB */ + segtable = segtable + (PAGE_OFFSET >> 22); + + /* this actually only goes to the end of the first gig */ + segtable_end = segtable + (1<<(30-22)); + + /* Move forward to the start of empty pages */ + segtable += bootmem_lastpg >> (22-PAGE_SHIFT); + + { + int i; + + for (i = 1 ; i <= DMA_RESERVE ; i++) + segtable[-i] = ((segtable[-i] & __HVM_PTE_PGMASK_4MB) + | __HVM_PTE_R | __HVM_PTE_W | __HVM_PTE_X + | __HEXAGON_C_UNC << 6 + | __HVM_PDE_S_4MB); + } + + printk(KERN_INFO "clearing segtable from %p to %p\n", segtable, + segtable_end); + while (segtable < (segtable_end-8)) + *(segtable++) = __HVM_PDE_S_INVALID; + /* stop the pointer at the device I/O 4MB page */ + + printk(KERN_INFO "segtable = %p (should be equal to _K_io_map)\n", + segtable); + +#if 0 + /* Other half of the early device table from vm_init_segtable. */ + printk(KERN_INFO "&_K_init_devicetable = 0x%08x\n", + (unsigned long) _K_init_devicetable-PAGE_OFFSET); + *segtable = ((u32) (unsigned long) _K_init_devicetable-PAGE_OFFSET) | + __HVM_PDE_S_4KB; + printk(KERN_INFO "*segtable = 0x%08x\n", *segtable); +#endif + + /* + * Free all the memory that wasn't taken up by the bootmap, the DMA + * reserve, or kernel itself. + */ + free_bootmem(PFN_PHYS(bootmem_startpg)+bootmap_size, + PFN_PHYS(bootmem_lastpg - bootmem_startpg) - bootmap_size - + DMA_RESERVED_BYTES); + + /* + * The bootmem allocator seemingly just lives to feed memory + * to the paging system + */ + printk(KERN_INFO "PAGE_SIZE=%lu\n", PAGE_SIZE); + paging_init(); /* See Gorman Book, 2.3 */ + + /* + * At this point, the page allocator is kind of initialized, but + * apparently no pages are available (just like with the bootmem + * allocator), and need to be freed themselves via mem_init(), + * which is called by start_kernel() later on in the process + */ +} diff --git a/arch/hexagon/mm/ioremap.c b/arch/hexagon/mm/ioremap.c new file mode 100644 index 000000000000..3a37bc3b0116 --- /dev/null +++ b/arch/hexagon/mm/ioremap.c @@ -0,0 +1,56 @@ +/* + * I/O remap functions for Hexagon + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/io.h> +#include <linux/vmalloc.h> + +void __iomem *ioremap_nocache(unsigned long phys_addr, unsigned long size) +{ + unsigned long last_addr, addr; + unsigned long offset = phys_addr & ~PAGE_MASK; + struct vm_struct *area; + + pgprot_t prot = __pgprot(_PAGE_PRESENT|_PAGE_READ|_PAGE_WRITE + |(__HEXAGON_C_DEV << 6)); + + last_addr = phys_addr + size - 1; + + /* Wrapping not allowed */ + if (!size || (last_addr < phys_addr)) + return NULL; + + /* Rounds up to next page size, including whole-page offset */ + size = PAGE_ALIGN(offset + size); + + area = get_vm_area(size, VM_IOREMAP); + addr = (unsigned long)area->addr; + + if (ioremap_page_range(addr, addr+size, phys_addr, prot)) { + vunmap((void *)addr); + return NULL; + } + + return (void __iomem *) (offset + addr); +} + +void __iounmap(const volatile void __iomem *addr) +{ + vunmap((void *) ((unsigned long) addr & PAGE_MASK)); +} diff --git a/arch/hexagon/mm/pgalloc.c b/arch/hexagon/mm/pgalloc.c new file mode 100644 index 000000000000..b175e2d42b89 --- /dev/null +++ b/arch/hexagon/mm/pgalloc.c @@ -0,0 +1,23 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#include <linux/init.h> + +void __init pgtable_cache_init(void) +{ +} diff --git a/arch/hexagon/mm/strnlen_user.S b/arch/hexagon/mm/strnlen_user.S new file mode 100644 index 000000000000..5c6a16c7c72a --- /dev/null +++ b/arch/hexagon/mm/strnlen_user.S @@ -0,0 +1,139 @@ +/* + * User string length functions for kernel + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#define isrc r0 +#define max r1 /* Do not change! */ + +#define end r2 +#define tmp1 r3 + +#define obo r6 /* off-by-one */ +#define start r7 +#define mod8 r8 +#define dbuf r15:14 +#define dcmp r13:12 + +/* + * The vector mask version of this turned out *really* badly. + * The hardware loop version also turned out *really* badly. + * Seems straight pointer arithmetic basically wins here. + */ + +#define fname __strnlen_user + + .text + .global fname + .type fname, @function + .p2align 5 /* why? */ +fname: + { + mod8 = and(isrc,#7); + end = add(isrc,max); + start = isrc; + } + { + P0 = cmp.eq(mod8,#0); + mod8 = and(end,#7); + dcmp = #0; + if (P0.new) jump:t dw_loop; /* fire up the oven */ + } + +alignment_loop: +fail_1: { + tmp1 = memb(start++#1); + } + { + P0 = cmp.eq(tmp1,#0); + if (P0.new) jump:nt exit_found; + P1 = cmp.gtu(end,start); + mod8 = and(start,#7); + } + { + if (!P1) jump exit_error; /* hit the end */ + P0 = cmp.eq(mod8,#0); + } + { + if (!P0) jump alignment_loop; + } + + + +dw_loop: +fail_2: { + dbuf = memd(start); + obo = add(start,#1); + } + { + P0 = vcmpb.eq(dbuf,dcmp); + } + { + tmp1 = P0; + P0 = cmp.gtu(end,start); + } + { + tmp1 = ct0(tmp1); + mod8 = and(end,#7); + if (!P0) jump end_check; + } + { + P0 = cmp.eq(tmp1,#32); + if (!P0.new) jump:nt exit_found; + if (!P0.new) start = add(obo,tmp1); + } + { + start = add(start,#8); + jump dw_loop; + } /* might be nice to combine these jumps... */ + + +end_check: + { + P0 = cmp.gt(tmp1,mod8); + if (P0.new) jump:nt exit_error; /* neverfound! */ + start = add(obo,tmp1); + } + +exit_found: + { + R0 = sub(start,isrc); + jumpr R31; + } + +exit_error: + { + R0 = add(max,#1); + jumpr R31; + } + + /* Uh, what does the "fixup" return here? */ + .falign +fix_1: + { + R0 = #0; + jumpr R31; + } + + .size fname,.-fname + + +.section __ex_table,"a" +.long fail_1,fix_1 +.long fail_2,fix_1 +.previous diff --git a/arch/hexagon/mm/uaccess.c b/arch/hexagon/mm/uaccess.c new file mode 100644 index 000000000000..e748108b47a7 --- /dev/null +++ b/arch/hexagon/mm/uaccess.c @@ -0,0 +1,59 @@ +/* + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +/* + * Support for user memory access from kernel. This will + * probably be inlined for performance at some point, but + * for ease of debug, and to a lesser degree for code size, + * we implement here as subroutines. + */ +#include <linux/types.h> +#include <asm/uaccess.h> +#include <asm/pgtable.h> + +/* + * For clear_user(), exploit previously defined copy_to_user function + * and the fact that we've got a handy zero page defined in kernel/head.S + * + * dczero here would be even faster. + */ +__kernel_size_t __clear_user_hexagon(void __user *dest, unsigned long count) +{ + long uncleared; + + while (count > PAGE_SIZE) { + uncleared = __copy_to_user_hexagon(dest, &empty_zero_page, + PAGE_SIZE); + if (uncleared) + return count - (PAGE_SIZE - uncleared); + count -= PAGE_SIZE; + dest += PAGE_SIZE; + } + if (count) + count = __copy_to_user_hexagon(dest, &empty_zero_page, count); + + return count; +} + +unsigned long clear_user_hexagon(void __user *dest, unsigned long count) +{ + if (!access_ok(VERIFY_WRITE, dest, count)) + return count; + else + return __clear_user_hexagon(dest, count); +} diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c new file mode 100644 index 000000000000..c10b76ff9d65 --- /dev/null +++ b/arch/hexagon/mm/vm_fault.c @@ -0,0 +1,187 @@ +/* + * Memory fault handling for Hexagon + * + * Copyright (c) 2010-2011 Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +/* + * Page fault handling for the Hexagon Virtual Machine. + * Can also be called by a native port emulating the HVM + * execptions. + */ + +#include <asm/pgtable.h> +#include <asm/traps.h> +#include <asm/uaccess.h> +#include <linux/mm.h> +#include <linux/signal.h> +#include <linux/module.h> +#include <linux/hardirq.h> + +/* + * Decode of hardware exception sends us to one of several + * entry points. At each, we generate canonical arguments + * for handling by the abstract memory management code. + */ +#define FLT_IFETCH -1 +#define FLT_LOAD 0 +#define FLT_STORE 1 + + +/* + * Canonical page fault handler + */ +void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) +{ + struct vm_area_struct *vma; + struct mm_struct *mm = current->mm; + siginfo_t info; + int si_code = SEGV_MAPERR; + int fault; + const struct exception_table_entry *fixup; + + /* + * If we're in an interrupt or have no user context, + * then must not take the fault. + */ + if (unlikely(in_interrupt() || !mm)) + goto no_context; + + local_irq_enable(); + + down_read(&mm->mmap_sem); + vma = find_vma(mm, address); + if (!vma) + goto bad_area; + + if (vma->vm_start <= address) + goto good_area; + + if (!(vma->vm_flags & VM_GROWSDOWN)) + goto bad_area; + + if (expand_stack(vma, address)) + goto bad_area; + +good_area: + /* Address space is OK. Now check access rights. */ + si_code = SEGV_ACCERR; + + switch (cause) { + case FLT_IFETCH: + if (!(vma->vm_flags & VM_EXEC)) + goto bad_area; + break; + case FLT_LOAD: + if (!(vma->vm_flags & VM_READ)) + goto bad_area; + break; + case FLT_STORE: + if (!(vma->vm_flags & VM_WRITE)) + goto bad_area; + break; + } + + fault = handle_mm_fault(mm, vma, address, (cause > 0)); + + /* The most common case -- we are done. */ + if (likely(!(fault & VM_FAULT_ERROR))) { + if (fault & VM_FAULT_MAJOR) + current->maj_flt++; + else + current->min_flt++; + + up_read(&mm->mmap_sem); + return; + } + + up_read(&mm->mmap_sem); + + /* Handle copyin/out exception cases */ + if (!user_mode(regs)) + goto no_context; + + if (fault & VM_FAULT_OOM) { + pagefault_out_of_memory(); + return; + } + + /* User-mode address is in the memory map, but we are + * unable to fix up the page fault. + */ + if (fault & VM_FAULT_SIGBUS) { + info.si_signo = SIGBUS; + info.si_code = BUS_ADRERR; + } + /* Address is not in the memory map */ + else { + info.si_signo = SIGSEGV; + info.si_code = SEGV_ACCERR; + } + info.si_errno = 0; + info.si_addr = (void __user *)address; + force_sig_info(info.si_code, &info, current); + return; + +bad_area: + up_read(&mm->mmap_sem); + + if (user_mode(regs)) { + info.si_signo = SIGSEGV; + info.si_errno = 0; + info.si_code = si_code; + info.si_addr = (void *)address; + force_sig_info(SIGSEGV, &info, current); + return; + } + /* Kernel-mode fault falls through */ + +no_context: + fixup = search_exception_tables(pt_elr(regs)); + if (fixup) { + pt_set_elr(regs, fixup->fixup); + return; + } + + /* Things are looking very, very bad now */ + bust_spinlocks(1); + printk(KERN_EMERG "Unable to handle kernel paging request at " + "virtual address 0x%08lx, regs %p\n", address, regs); + die("Bad Kernel VA", regs, SIGKILL); +} + + +void read_protection_fault(struct pt_regs *regs) +{ + unsigned long badvadr = pt_badva(regs); + + do_page_fault(badvadr, FLT_LOAD, regs); +} + +void write_protection_fault(struct pt_regs *regs) +{ + unsigned long badvadr = pt_badva(regs); + + do_page_fault(badvadr, FLT_STORE, regs); +} + +void execute_protection_fault(struct pt_regs *regs) +{ + unsigned long badvadr = pt_badva(regs); + + do_page_fault(badvadr, FLT_IFETCH, regs); +} diff --git a/arch/hexagon/mm/vm_tlb.c b/arch/hexagon/mm/vm_tlb.c new file mode 100644 index 000000000000..c6ff41575461 --- /dev/null +++ b/arch/hexagon/mm/vm_tlb.c @@ -0,0 +1,93 @@ +/* + * Hexagon Virtual Machine TLB functions + * + * Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +/* + * The Hexagon Virtual Machine conceals the real workings of + * the TLB, but there are one or two functions that need to + * be instantiated for it, differently from a native build. + */ +#include <linux/mm.h> +#include <asm/page.h> +#include <asm/hexagon_vm.h> + +/* + * Initial VM implementation has only one map active at a time, with + * TLB purgings on changes. So either we're nuking the current map, + * or it's a no-op. This operation is messy on true SMPs where other + * processors must be induced to flush the copies in their local TLBs, + * but Hexagon thread-based virtual processors share the same MMU. + */ +void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + struct mm_struct *mm = vma->vm_mm; + + if (mm->context.ptbase == current->active_mm->context.ptbase) + __vmclrmap((void *)start, end - start); +} + +/* + * Flush a page from the kernel virtual map - used by highmem + */ +void flush_tlb_one(unsigned long vaddr) +{ + __vmclrmap((void *)vaddr, PAGE_SIZE); +} + +/* + * Flush all TLBs across all CPUs, virtual or real. + * A single Hexagon core has 6 thread contexts but + * only one TLB. + */ +void tlb_flush_all(void) +{ + /* should probably use that fixaddr end or whateve label */ + __vmclrmap(0, 0xffff0000); +} + +/* + * Flush TLB entries associated with a given mm_struct mapping. + */ +void flush_tlb_mm(struct mm_struct *mm) +{ + /* Current Virtual Machine has only one map active at a time */ + if (current->active_mm->context.ptbase == mm->context.ptbase) + tlb_flush_all(); +} + +/* + * Flush TLB state associated with a page of a vma. + */ +void flush_tlb_page(struct vm_area_struct *vma, unsigned long vaddr) +{ + struct mm_struct *mm = vma->vm_mm; + + if (mm->context.ptbase == current->active_mm->context.ptbase) + __vmclrmap((void *)vaddr, PAGE_SIZE); +} + +/* + * Flush TLB entries associated with a kernel address range. + * Like flush range, but without the check on the vma->vm_mm. + */ +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + __vmclrmap((void *)start, end - start); +} diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig index 0e5cd1405e0e..43ab1cd097a5 100644 --- a/arch/ia64/configs/generic_defconfig +++ b/arch/ia64/configs/generic_defconfig @@ -234,4 +234,4 @@ CONFIG_CRYPTO_MD5=y # CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRC_T10DIF=y CONFIG_MISC_DEVICES=y -CONFIG_DMAR=y +CONFIG_INTEL_IOMMU=y diff --git a/arch/ia64/dig/Makefile b/arch/ia64/dig/Makefile index 2f7caddf093e..ae16ec4f6308 100644 --- a/arch/ia64/dig/Makefile +++ b/arch/ia64/dig/Makefile @@ -6,7 +6,7 @@ # obj-y := setup.o -ifeq ($(CONFIG_DMAR), y) +ifeq ($(CONFIG_INTEL_IOMMU), y) obj-$(CONFIG_IA64_GENERIC) += machvec.o machvec_vtd.o else obj-$(CONFIG_IA64_GENERIC) += machvec.o diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index 80241fe03f50..f5f4ef149aac 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -915,7 +915,7 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt) * @dir: R/W or both. * @attrs: optional dma attributes * - * See Documentation/PCI/PCI-DMA-mapping.txt + * See Documentation/DMA-API-HOWTO.txt */ static dma_addr_t sba_map_page(struct device *dev, struct page *page, unsigned long poff, size_t size, @@ -1044,7 +1044,7 @@ sba_mark_clean(struct ioc *ioc, dma_addr_t iova, size_t size) * @dir: R/W or both. * @attrs: optional dma attributes * - * See Documentation/PCI/PCI-DMA-mapping.txt + * See Documentation/DMA-API-HOWTO.txt */ static void sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) @@ -1127,7 +1127,7 @@ void sba_unmap_single_attrs(struct device *dev, dma_addr_t iova, size_t size, * @size: number of bytes mapped in driver buffer. * @dma_handle: IOVA of new buffer. * - * See Documentation/PCI/PCI-DMA-mapping.txt + * See Documentation/DMA-API-HOWTO.txt */ static void * sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flags) @@ -1190,7 +1190,7 @@ sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp * @vaddr: virtual address IOVA of "consistent" buffer. * @dma_handler: IO virtual address of "consistent" buffer. * - * See Documentation/PCI/PCI-DMA-mapping.txt + * See Documentation/DMA-API-HOWTO.txt */ static void sba_free_coherent (struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle) @@ -1453,7 +1453,7 @@ static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, * @dir: R/W or both. * @attrs: optional dma attributes * - * See Documentation/PCI/PCI-DMA-mapping.txt + * See Documentation/DMA-API-HOWTO.txt */ static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction dir, @@ -1549,7 +1549,7 @@ static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist, * @dir: R/W or both. * @attrs: optional dma attributes * - * See Documentation/PCI/PCI-DMA-mapping.txt + * See Documentation/DMA-API-HOWTO.txt */ static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction dir, diff --git a/arch/ia64/hp/sim/simeth.c b/arch/ia64/hp/sim/simeth.c index 7e81966ce481..47afcc61f6e5 100644 --- a/arch/ia64/hp/sim/simeth.c +++ b/arch/ia64/hp/sim/simeth.c @@ -172,7 +172,7 @@ static const struct net_device_ops simeth_netdev_ops = { .ndo_stop = simeth_close, .ndo_start_xmit = simeth_tx, .ndo_get_stats = simeth_get_stats, - .ndo_set_multicast_list = set_multicast_list, /* not yet used */ + .ndo_set_rx_mode = set_multicast_list, /* not yet used */ }; diff --git a/arch/ia64/include/asm/device.h b/arch/ia64/include/asm/device.h index d66d446b127c..d05e78f6db94 100644 --- a/arch/ia64/include/asm/device.h +++ b/arch/ia64/include/asm/device.h @@ -10,7 +10,7 @@ struct dev_archdata { #ifdef CONFIG_ACPI void *acpi_handle; #endif -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU void *iommu; /* hook for IOMMU specific extension */ #endif }; diff --git a/arch/ia64/include/asm/iommu.h b/arch/ia64/include/asm/iommu.h index 745e095fe82e..105c93b00b1b 100644 --- a/arch/ia64/include/asm/iommu.h +++ b/arch/ia64/include/asm/iommu.h @@ -7,12 +7,14 @@ extern void pci_iommu_shutdown(void); extern void no_iommu_init(void); +#ifdef CONFIG_INTEL_IOMMU extern int force_iommu, no_iommu; -extern int iommu_detected; -#ifdef CONFIG_DMAR extern int iommu_pass_through; +extern int iommu_detected; #else #define iommu_pass_through (0) +#define no_iommu (1) +#define iommu_detected (0) #endif extern void iommu_dma_init(void); extern void machvec_init(const char *name); diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h index 73b5f785e70c..127dd7be346a 100644 --- a/arch/ia64/include/asm/pci.h +++ b/arch/ia64/include/asm/pci.h @@ -139,7 +139,7 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) return channel ? isa_irq_to_vector(15) : isa_irq_to_vector(14); } -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU extern void pci_iommu_alloc(void); #endif #endif /* _ASM_IA64_PCI_H */ diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index 395c2f216dd8..d959c84904be 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -43,7 +43,7 @@ obj-$(CONFIG_IA64_ESI) += esi.o ifneq ($(CONFIG_IA64_ESI),) obj-y += esi_stub.o # must be in kernel proper endif -obj-$(CONFIG_DMAR) += pci-dma.o +obj-$(CONFIG_INTEL_IOMMU) += pci-dma.o obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_BINFMT_ELF) += elfcore.o diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 3be485a300b1..bfb4d01e0e51 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -88,7 +88,7 @@ acpi_get_sysname(void) struct acpi_table_rsdp *rsdp; struct acpi_table_xsdt *xsdt; struct acpi_table_header *hdr; -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU u64 i, nentries; #endif @@ -125,7 +125,7 @@ acpi_get_sysname(void) return "xen"; } -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU /* Look for Intel IOMMU */ nentries = (hdr->length - sizeof(*hdr)) / sizeof(xsdt->table_offset_entry[0]); diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c index 009df5434a7a..94e0db72d4a6 100644 --- a/arch/ia64/kernel/msi_ia64.c +++ b/arch/ia64/kernel/msi_ia64.c @@ -131,7 +131,7 @@ void arch_teardown_msi_irq(unsigned int irq) return ia64_teardown_msi_irq(irq); } -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU #ifdef CONFIG_SMP static int dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) @@ -210,5 +210,5 @@ int arch_setup_dmar_msi(unsigned int irq) "edge"); return 0; } -#endif /* CONFIG_DMAR */ +#endif /* CONFIG_INTEL_IOMMU */ diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c index f6b1ff0aea76..c16162c70860 100644 --- a/arch/ia64/kernel/pci-dma.c +++ b/arch/ia64/kernel/pci-dma.c @@ -14,7 +14,7 @@ #include <asm/system.h> -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU #include <linux/kernel.h> diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 8213efe1998c..43f4c92816ef 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -33,6 +33,7 @@ #include <linux/uaccess.h> #include <linux/iommu.h> #include <linux/intel-iommu.h> +#include <linux/pci.h> #include <asm/pgtable.h> #include <asm/gcc_intrin.h> @@ -204,7 +205,7 @@ int kvm_dev_ioctl_check_extension(long ext) r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; case KVM_CAP_IOMMU: - r = iommu_found(); + r = iommu_present(&pci_bus_type); break; default: r = 0; diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig index b92b9445255d..6c4e9aaa70c1 100644 --- a/arch/m32r/Kconfig +++ b/arch/m32r/Kconfig @@ -10,6 +10,7 @@ config M32R select HAVE_GENERIC_HARDIRQS select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW + select GENERIC_ATOMIC64 config SBUS bool diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 9e8ee9d2b8ca..6c28582fb98f 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -21,6 +21,15 @@ config ARCH_HAS_ILOG2_U32 config ARCH_HAS_ILOG2_U64 bool +config GENERIC_CLOCKEVENTS + bool + +config GENERIC_CMOS_UPDATE + def_bool !MMU + +config GENERIC_GPIO + bool + config GENERIC_HWEIGHT bool default y @@ -29,10 +38,16 @@ config GENERIC_CALIBRATE_DELAY bool default y +config GENERIC_IOMAP + def_bool MMU + config TIME_LOW_RES bool default y +config ARCH_USES_GETTIMEOFFSET + def_bool MMU + config NO_IOPORT def_bool y @@ -62,13 +77,31 @@ config MMU Select if you want MMU-based virtualised addressing space support by paged memory management. If unsure, say 'Y'. -menu "Platform dependent setup" +config MMU_MOTOROLA + bool + +config MMU_SUN3 + bool + depends on MMU && !MMU_MOTOROLA + +menu "Platform setup" + +source arch/m68k/Kconfig.cpu + +source arch/m68k/Kconfig.machine + +source arch/m68k/Kconfig.bus + +endmenu + +menu "Kernel Features" -if MMU -source arch/m68k/Kconfig.mmu +if COLDFIRE +source "kernel/Kconfig.preempt" endif -if !MMU -source arch/m68k/Kconfig.nommu + +if !MMU || COLDFIRE +source "kernel/time/Kconfig" endif source "mm/Kconfig" @@ -85,9 +118,9 @@ if !MMU menu "Power management options" config PM - bool "Power Management support" - help - Support processor power management modes + bool "Power Management support" + help + Support processor power management modes endmenu endif @@ -96,151 +129,7 @@ source "net/Kconfig" source "drivers/Kconfig" -if MMU - -menu "Character devices" - -config ATARI_MFPSER - tristate "Atari MFP serial support" - depends on ATARI - ---help--- - If you like to use the MFP serial ports ("Modem1", "Serial1") under - Linux, say Y. The driver equally supports all kinds of MFP serial - ports and automatically detects whether Serial1 is available. - - To compile this driver as a module, choose M here. - - Note for Falcon users: You also have an MFP port, it's just not - wired to the outside... But you could use the port under Linux. - -config ATARI_MIDI - tristate "Atari MIDI serial support" - depends on ATARI - help - If you want to use your Atari's MIDI port in Linux, say Y. - - To compile this driver as a module, choose M here. - -config ATARI_DSP56K - tristate "Atari DSP56k support (EXPERIMENTAL)" - depends on ATARI && EXPERIMENTAL - help - If you want to be able to use the DSP56001 in Falcons, say Y. This - driver is still experimental, and if you don't know what it is, or - if you don't have this processor, just say N. - - To compile this driver as a module, choose M here. - -config AMIGA_BUILTIN_SERIAL - tristate "Amiga builtin serial support" - depends on AMIGA - help - If you want to use your Amiga's built-in serial port in Linux, - answer Y. - - To compile this driver as a module, choose M here. - -config MULTIFACE_III_TTY - tristate "Multiface Card III serial support" - depends on AMIGA - help - If you want to use a Multiface III card's serial port in Linux, - answer Y. - - To compile this driver as a module, choose M here. - -config GVPIOEXT - tristate "GVP IO-Extender support" - depends on PARPORT=n && ZORRO - help - If you want to use a GVP IO-Extender serial card in Linux, say Y. - Otherwise, say N. - -config GVPIOEXT_LP - tristate "GVP IO-Extender parallel printer support" - depends on GVPIOEXT - help - Say Y to enable driving a printer from the parallel port on your - GVP IO-Extender card, N otherwise. - -config GVPIOEXT_PLIP - tristate "GVP IO-Extender PLIP support" - depends on GVPIOEXT - help - Say Y to enable doing IP over the parallel port on your GVP - IO-Extender card, N otherwise. - -config MAC_HID - bool - depends on INPUT_ADBHID - default y - -config HPDCA - tristate "HP DCA serial support" - depends on DIO && SERIAL_8250 - help - If you want to use the internal "DCA" serial ports on an HP300 - machine, say Y here. - -config HPAPCI - tristate "HP APCI serial support" - depends on HP300 && SERIAL_8250 && EXPERIMENTAL - help - If you want to use the internal "APCI" serial ports on an HP400 - machine, say Y here. - -config MVME147_SCC - bool "SCC support for MVME147 serial ports" - depends on MVME147 && BROKEN - help - This is the driver for the serial ports on the Motorola MVME147 - boards. Everyone using one of these boards should say Y here. - -config MVME162_SCC - bool "SCC support for MVME162 serial ports" - depends on MVME16x && BROKEN - help - This is the driver for the serial ports on the Motorola MVME162 and - 172 boards. Everyone using one of these boards should say Y here. - -config BVME6000_SCC - bool "SCC support for BVME6000 serial ports" - depends on BVME6000 && BROKEN - help - This is the driver for the serial ports on the BVME4000 and BVME6000 - boards from BVM Ltd. Everyone using one of these boards should say - Y here. - -config DN_SERIAL - bool "Support for DN serial port (dummy)" - depends on APOLLO - -config SERIAL_CONSOLE - bool "Support for serial port console" - depends on (AMIGA || ATARI || SUN3 || SUN3X || VME || APOLLO) && (ATARI_MFPSER=y || ATARI_MIDI=y || AMIGA_BUILTIN_SERIAL=y || GVPIOEXT=y || MULTIFACE_III_TTY=y || SERIAL=y || MVME147_SCC || SERIAL167 || MVME162_SCC || BVME6000_SCC || DN_SERIAL) - ---help--- - If you say Y here, it will be possible to use a serial port as the - system console (the system console is the device which receives all - kernel messages and warnings and which allows logins in single user - mode). This could be useful if some terminal or printer is connected - to that serial port. - - Even if you say Y here, the currently visible virtual console - (/dev/tty0) will still be used as the system console by default, but - you can alter that using a kernel command line option such as - "console=ttyS1". (Try "man bootparam" or see the documentation of - your boot loader (lilo or loadlin) about how to pass options to the - kernel at boot time.) - - If you don't have a VGA card installed and you say Y here, the - kernel will automatically use the first serial line, /dev/ttyS0, as - system console. - - If unsure, say N. - -endmenu - -endif +source "arch/m68k/Kconfig.devices" source "fs/Kconfig" diff --git a/arch/m68k/Kconfig.bus b/arch/m68k/Kconfig.bus new file mode 100644 index 000000000000..8294f0c1785e --- /dev/null +++ b/arch/m68k/Kconfig.bus @@ -0,0 +1,55 @@ +if MMU + +comment "Bus Support" + +config NUBUS + bool + depends on MAC + default y + +config ZORRO + bool "Amiga Zorro (AutoConfig) bus support" + depends on AMIGA + help + This enables support for the Zorro bus in the Amiga. If you have + expansion cards in your Amiga that conform to the Amiga + AutoConfig(tm) specification, say Y, otherwise N. Note that even + expansion cards that do not fit in the Zorro slots but fit in e.g. + the CPU slot may fall in this category, so you have to say Y to let + Linux use these. + +config AMIGA_PCMCIA + bool "Amiga 1200/600 PCMCIA support (EXPERIMENTAL)" + depends on AMIGA && EXPERIMENTAL + help + Include support in the kernel for pcmcia on Amiga 1200 and Amiga + 600. If you intend to use pcmcia cards say Y; otherwise say N. + +config ISA + bool + depends on Q40 || AMIGA_PCMCIA + default y + help + Find out whether you have ISA slots on your motherboard. ISA is the + name of a bus system, i.e. the way the CPU talks to the other stuff + inside your box. Other bus systems are PCI, EISA, MicroChannel + (MCA) or VESA. ISA is an older system, now being displaced by PCI; + newer boards don't support it. If you have ISA, say Y, otherwise N. + +config GENERIC_ISA_DMA + def_bool ISA + +source "drivers/pci/Kconfig" + +source "drivers/zorro/Kconfig" + +endif + +if !MMU + +config ISA_DMA_API + def_bool !M5272 + +source "drivers/pcmcia/Kconfig" + +endif diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu new file mode 100644 index 000000000000..e632b2d12106 --- /dev/null +++ b/arch/m68k/Kconfig.cpu @@ -0,0 +1,429 @@ +comment "Processor Type" + +config M68000 + bool + select CPU_HAS_NO_BITFIELDS + help + The Freescale (was Motorola) 68000 CPU is the first generation of + the well known M68K family of processors. The CPU core as well as + being available as a stand alone CPU was also used in many + System-On-Chip devices (eg 68328, 68302, etc). It does not contain + a paging MMU. + +config MCPU32 + bool + select CPU_HAS_NO_BITFIELDS + help + The Freescale (was then Motorola) CPU32 is a CPU core that is + based on the 68020 processor. For the most part it is used in + System-On-Chip parts, and does not contain a paging MMU. + +config COLDFIRE + bool + select GENERIC_GPIO + select ARCH_REQUIRE_GPIOLIB + select CPU_HAS_NO_BITFIELDS + help + The Freescale ColdFire family of processors is a modern derivitive + of the 68000 processor family. They are mainly targeted at embedded + applications, and are all System-On-Chip (SOC) devices, as opposed + to stand alone CPUs. They implement a subset of the original 68000 + processor instruction set. + +config M68020 + bool "68020 support" + depends on MMU + help + If you anticipate running this kernel on a computer with a MC68020 + processor, say Y. Otherwise, say N. Note that the 68020 requires a + 68851 MMU (Memory Management Unit) to run Linux/m68k, except on the + Sun 3, which provides its own version. + +config M68030 + bool "68030 support" + depends on MMU && !MMU_SUN3 + help + If you anticipate running this kernel on a computer with a MC68030 + processor, say Y. Otherwise, say N. Note that a MC68EC030 will not + work, as it does not include an MMU (Memory Management Unit). + +config M68040 + bool "68040 support" + depends on MMU && !MMU_SUN3 + help + If you anticipate running this kernel on a computer with a MC68LC040 + or MC68040 processor, say Y. Otherwise, say N. Note that an + MC68EC040 will not work, as it does not include an MMU (Memory + Management Unit). + +config M68060 + bool "68060 support" + depends on MMU && !MMU_SUN3 + help + If you anticipate running this kernel on a computer with a MC68060 + processor, say Y. Otherwise, say N. + +config M68328 + bool "MC68328" + depends on !MMU + select M68000 + help + Motorola 68328 processor support. + +config M68EZ328 + bool "MC68EZ328" + depends on !MMU + select M68000 + help + Motorola 68EX328 processor support. + +config M68VZ328 + bool "MC68VZ328" + depends on !MMU + select M68000 + help + Motorola 68VZ328 processor support. + +config M68360 + bool "MC68360" + depends on !MMU + select MCPU32 + help + Motorola 68360 processor support. + +config M5206 + bool "MCF5206" + depends on !MMU + select COLDFIRE + select COLDFIRE_SW_A7 + select HAVE_MBAR + help + Motorola ColdFire 5206 processor support. + +config M5206e + bool "MCF5206e" + depends on !MMU + select COLDFIRE + select COLDFIRE_SW_A7 + select HAVE_MBAR + help + Motorola ColdFire 5206e processor support. + +config M520x + bool "MCF520x" + depends on !MMU + select COLDFIRE + select GENERIC_CLOCKEVENTS + select HAVE_CACHE_SPLIT + help + Freescale Coldfire 5207/5208 processor support. + +config M523x + bool "MCF523x" + depends on !MMU + select COLDFIRE + select GENERIC_CLOCKEVENTS + select HAVE_CACHE_SPLIT + select HAVE_IPSBAR + help + Freescale Coldfire 5230/1/2/4/5 processor support + +config M5249 + bool "MCF5249" + depends on !MMU + select COLDFIRE + select COLDFIRE_SW_A7 + select HAVE_MBAR + help + Motorola ColdFire 5249 processor support. + +config M527x + bool + +config M5271 + bool "MCF5271" + depends on !MMU + select COLDFIRE + select M527x + select HAVE_CACHE_SPLIT + select HAVE_IPSBAR + select GENERIC_CLOCKEVENTS + help + Freescale (Motorola) ColdFire 5270/5271 processor support. + +config M5272 + bool "MCF5272" + depends on !MMU + select COLDFIRE + select COLDFIRE_SW_A7 + select HAVE_MBAR + help + Motorola ColdFire 5272 processor support. + +config M5275 + bool "MCF5275" + depends on !MMU + select COLDFIRE + select M527x + select HAVE_CACHE_SPLIT + select HAVE_IPSBAR + select GENERIC_CLOCKEVENTS + help + Freescale (Motorola) ColdFire 5274/5275 processor support. + +config M528x + bool "MCF528x" + depends on !MMU + select COLDFIRE + select GENERIC_CLOCKEVENTS + select HAVE_CACHE_SPLIT + select HAVE_IPSBAR + help + Motorola ColdFire 5280/5282 processor support. + +config M5307 + bool "MCF5307" + depends on !MMU + select COLDFIRE + select COLDFIRE_SW_A7 + select HAVE_CACHE_CB + select HAVE_MBAR + help + Motorola ColdFire 5307 processor support. + +config M532x + bool "MCF532x" + depends on !MMU + select COLDFIRE + select HAVE_CACHE_CB + help + Freescale (Motorola) ColdFire 532x processor support. + +config M5407 + bool "MCF5407" + depends on !MMU + select COLDFIRE + select COLDFIRE_SW_A7 + select HAVE_CACHE_CB + select HAVE_MBAR + help + Motorola ColdFire 5407 processor support. + +config M54xx + bool + +config M547x + bool "MCF547x" + depends on !MMU + select COLDFIRE + select M54xx + select HAVE_CACHE_CB + select HAVE_MBAR + help + Freescale ColdFire 5470/5471/5472/5473/5474/5475 processor support. + +config M548x + bool "MCF548x" + depends on !MMU + select COLDFIRE + select M54xx + select HAVE_CACHE_CB + select HAVE_MBAR + help + Freescale ColdFire 5480/5481/5482/5483/5484/5485 processor support. + + +comment "Processor Specific Options" + +config M68KFPU_EMU + bool "Math emulation support (EXPERIMENTAL)" + depends on MMU + depends on EXPERIMENTAL + help + At some point in the future, this will cause floating-point math + instructions to be emulated by the kernel on machines that lack a + floating-point math coprocessor. Thrill-seekers and chronically + sleep-deprived psychotic hacker types can say Y now, everyone else + should probably wait a while. + +config M68KFPU_EMU_EXTRAPREC + bool "Math emulation extra precision" + depends on M68KFPU_EMU + help + The fpu uses normally a few bit more during calculations for + correct rounding, the emulator can (often) do the same but this + extra calculation can cost quite some time, so you can disable + it here. The emulator will then "only" calculate with a 64 bit + mantissa and round slightly incorrect, what is more than enough + for normal usage. + +config M68KFPU_EMU_ONLY + bool "Math emulation only kernel" + depends on M68KFPU_EMU + help + This option prevents any floating-point instructions from being + compiled into the kernel, thereby the kernel doesn't save any + floating point context anymore during task switches, so this + kernel will only be usable on machines without a floating-point + math coprocessor. This makes the kernel a bit faster as no tests + needs to be executed whether a floating-point instruction in the + kernel should be executed or not. + +config ADVANCED + bool "Advanced configuration options" + depends on MMU + ---help--- + This gives you access to some advanced options for the CPU. The + defaults should be fine for most users, but these options may make + it possible for you to improve performance somewhat if you know what + you are doing. + + Note that the answer to this question won't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about these options. + + Most users should say N to this question. + +config RMW_INSNS + bool "Use read-modify-write instructions" + depends on ADVANCED + ---help--- + This allows to use certain instructions that work with indivisible + read-modify-write bus cycles. While this is faster than the + workaround of disabling interrupts, it can conflict with DMA + ( = direct memory access) on many Amiga systems, and it is also said + to destabilize other machines. It is very likely that this will + cause serious problems on any Amiga or Atari Medusa if set. The only + configuration where it should work are 68030-based Ataris, where it + apparently improves performance. But you've been warned! Unless you + really know what you are doing, say N. Try Y only if you're quite + adventurous. + +config SINGLE_MEMORY_CHUNK + bool "Use one physical chunk of memory only" if ADVANCED && !SUN3 + depends on MMU + default y if SUN3 + select NEED_MULTIPLE_NODES + help + Ignore all but the first contiguous chunk of physical memory for VM + purposes. This will save a few bytes kernel size and may speed up + some operations. Say N if not sure. + +config ARCH_DISCONTIGMEM_ENABLE + def_bool MMU && !SINGLE_MEMORY_CHUNK + +config 060_WRITETHROUGH + bool "Use write-through caching for 68060 supervisor accesses" + depends on ADVANCED && M68060 + ---help--- + The 68060 generally uses copyback caching of recently accessed data. + Copyback caching means that memory writes will be held in an on-chip + cache and only written back to memory some time later. Saying Y + here will force supervisor (kernel) accesses to use writethrough + caching. Writethrough caching means that data is written to memory + straight away, so that cache and memory data always agree. + Writethrough caching is less efficient, but is needed for some + drivers on 68060 based systems where the 68060 bus snooping signal + is hardwired on. The 53c710 SCSI driver is known to suffer from + this problem. + +config M68K_L2_CACHE + bool + depends on MAC + default y + +config NODES_SHIFT + int + default "3" + depends on !SINGLE_MEMORY_CHUNK + +config FPU + bool + +config COLDFIRE_SW_A7 + bool + +config HAVE_CACHE_SPLIT + bool + +config HAVE_CACHE_CB + bool + +config HAVE_MBAR + bool + +config HAVE_IPSBAR + bool + +config CLOCK_SET + bool "Enable setting the CPU clock frequency" + depends on COLDFIRE + default n + help + On some CPU's you do not need to know what the core CPU clock + frequency is. On these you can disable clock setting. On some + traditional 68K parts, and on all ColdFire parts you need to set + the appropriate CPU clock frequency. On these devices many of the + onboard peripherals derive their timing from the master CPU clock + frequency. + +config CLOCK_FREQ + int "Set the core clock frequency" + default "66666666" + depends on CLOCK_SET + help + Define the CPU clock frequency in use. This is the core clock + frequency, it may or may not be the same as the external clock + crystal fitted to your board. Some processors have an internal + PLL and can have their frequency programmed at run time, others + use internal dividers. In general the kernel won't setup a PLL + if it is fitted (there are some exceptions). This value will be + specific to the exact CPU that you are using. + +config OLDMASK + bool "Old mask 5307 (1H55J) silicon" + depends on M5307 + help + Build support for the older revision ColdFire 5307 silicon. + Specifically this is the 1H55J mask revision. + +if HAVE_CACHE_SPLIT +choice + prompt "Split Cache Configuration" + default CACHE_I + +config CACHE_I + bool "Instruction" + help + Use all of the ColdFire CPU cache memory as an instruction cache. + +config CACHE_D + bool "Data" + help + Use all of the ColdFire CPU cache memory as a data cache. + +config CACHE_BOTH + bool "Both" + help + Split the ColdFire CPU cache, and use half as an instruction cache + and half as a data cache. +endchoice +endif + +if HAVE_CACHE_CB +choice + prompt "Data cache mode" + default CACHE_WRITETHRU + +config CACHE_WRITETHRU + bool "Write-through" + help + The ColdFire CPU cache is set into Write-through mode. + +config CACHE_COPYBACK + bool "Copy-back" + help + The ColdFire CPU cache is set into Copy-back mode. +endchoice +endif + diff --git a/arch/m68k/Kconfig.devices b/arch/m68k/Kconfig.devices new file mode 100644 index 000000000000..d214034be6a6 --- /dev/null +++ b/arch/m68k/Kconfig.devices @@ -0,0 +1,123 @@ +if MMU + +config ARCH_MAY_HAVE_PC_FDC + bool + depends on BROKEN && (Q40 || SUN3X) + default y + +menu "Platform devices" + +config HEARTBEAT + bool "Use power LED as a heartbeat" if AMIGA || APOLLO || ATARI || MAC ||Q40 + default y if !AMIGA && !APOLLO && !ATARI && !MAC && !Q40 && HP300 + help + Use the power-on LED on your machine as a load meter. The exact + behavior is platform-dependent, but normally the flash frequency is + a hyperbolic function of the 5-minute load average. + +# We have a dedicated heartbeat LED. :-) +config PROC_HARDWARE + bool "/proc/hardware support" + help + Say Y here to support the /proc/hardware file, which gives you + access to information about the machine you're running on, + including the model, CPU, MMU, clock speed, BogoMIPS rating, + and memory size. + +endmenu + +menu "Character devices" + +config ATARI_MFPSER + tristate "Atari MFP serial support" + depends on ATARI + ---help--- + If you like to use the MFP serial ports ("Modem1", "Serial1") under + Linux, say Y. The driver equally supports all kinds of MFP serial + ports and automatically detects whether Serial1 is available. + + To compile this driver as a module, choose M here. + + Note for Falcon users: You also have an MFP port, it's just not + wired to the outside... But you could use the port under Linux. + +config ATARI_MIDI + tristate "Atari MIDI serial support" + depends on ATARI + help + If you want to use your Atari's MIDI port in Linux, say Y. + + To compile this driver as a module, choose M here. + +config ATARI_DSP56K + tristate "Atari DSP56k support (EXPERIMENTAL)" + depends on ATARI && EXPERIMENTAL + help + If you want to be able to use the DSP56001 in Falcons, say Y. This + driver is still experimental, and if you don't know what it is, or + if you don't have this processor, just say N. + + To compile this driver as a module, choose M here. + +config AMIGA_BUILTIN_SERIAL + tristate "Amiga builtin serial support" + depends on AMIGA + help + If you want to use your Amiga's built-in serial port in Linux, + answer Y. + + To compile this driver as a module, choose M here. + +config MULTIFACE_III_TTY + tristate "Multiface Card III serial support" + depends on AMIGA + help + If you want to use a Multiface III card's serial port in Linux, + answer Y. + + To compile this driver as a module, choose M here. + +config HPDCA + tristate "HP DCA serial support" + depends on DIO && SERIAL_8250 + help + If you want to use the internal "DCA" serial ports on an HP300 + machine, say Y here. + +config HPAPCI + tristate "HP APCI serial support" + depends on HP300 && SERIAL_8250 && EXPERIMENTAL + help + If you want to use the internal "APCI" serial ports on an HP400 + machine, say Y here. + +config DN_SERIAL + bool "Support for DN serial port (dummy)" + depends on APOLLO + +config SERIAL_CONSOLE + bool "Support for serial port console" + depends on (AMIGA || ATARI || SUN3 || SUN3X || VME || APOLLO) && (ATARI_MFPSER=y || ATARI_MIDI=y || AMIGA_BUILTIN_SERIAL=y || MULTIFACE_III_TTY=y || SERIAL=y || SERIAL167 || DN_SERIAL) + ---help--- + If you say Y here, it will be possible to use a serial port as the + system console (the system console is the device which receives all + kernel messages and warnings and which allows logins in single user + mode). This could be useful if some terminal or printer is connected + to that serial port. + + Even if you say Y here, the currently visible virtual console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttyS1". (Try "man bootparam" or see the documentation of + your boot loader (lilo or loadlin) about how to pass options to the + kernel at boot time.) + + If you don't have a VGA card installed and you say Y here, the + kernel will automatically use the first serial line, /dev/ttyS0, as + system console. + + If unsure, say N. + +endmenu + +endif diff --git a/arch/m68k/Kconfig.nommu b/arch/m68k/Kconfig.machine index ff46383112a4..ef4a26aff780 100644 --- a/arch/m68k/Kconfig.nommu +++ b/arch/m68k/Kconfig.machine @@ -1,297 +1,142 @@ -config FPU - bool - default n - -config GENERIC_GPIO - bool - default n - -config GENERIC_CMOS_UPDATE - bool - default y - -config GENERIC_CLOCKEVENTS - bool - default n - -config M68000 - bool - select CPU_HAS_NO_BITFIELDS - help - The Freescale (was Motorola) 68000 CPU is the first generation of - the well known M68K family of processors. The CPU core as well as - being available as a stand alone CPU was also used in many - System-On-Chip devices (eg 68328, 68302, etc). It does not contain - a paging MMU. - -config MCPU32 - bool - select CPU_HAS_NO_BITFIELDS - help - The Freescale (was then Motorola) CPU32 is a CPU core that is - based on the 68020 processor. For the most part it is used in - System-On-Chip parts, and does not contain a paging MMU. - -config COLDFIRE - bool - select GENERIC_GPIO - select ARCH_REQUIRE_GPIOLIB - select CPU_HAS_NO_BITFIELDS - help - The Freescale ColdFire family of processors is a modern derivitive - of the 68000 processor family. They are mainly targeted at embedded - applications, and are all System-On-Chip (SOC) devices, as opposed - to stand alone CPUs. They implement a subset of the original 68000 - processor instruction set. - -config COLDFIRE_SW_A7 - bool - default n - -config HAVE_CACHE_SPLIT - bool - -config HAVE_CACHE_CB - bool - -config HAVE_MBAR - bool - -config HAVE_IPSBAR - bool - -choice - prompt "CPU" - default M68EZ328 - -config M68328 - bool "MC68328" - select M68000 - help - Motorola 68328 processor support. - -config M68EZ328 - bool "MC68EZ328" - select M68000 - help - Motorola 68EX328 processor support. - -config M68VZ328 - bool "MC68VZ328" - select M68000 - help - Motorola 68VZ328 processor support. - -config M68360 - bool "MC68360" - select MCPU32 - help - Motorola 68360 processor support. - -config M5206 - bool "MCF5206" - select COLDFIRE - select COLDFIRE_SW_A7 - select HAVE_MBAR - help - Motorola ColdFire 5206 processor support. +comment "Machine Types" + +config AMIGA + bool "Amiga support" + depends on MMU + select MMU_MOTOROLA if MMU + help + This option enables support for the Amiga series of computers. If + you plan to use this kernel on an Amiga, say Y here and browse the + material available in <file:Documentation/m68k>; otherwise say N. + +config ATARI + bool "Atari support" + depends on MMU + select MMU_MOTOROLA if MMU + help + This option enables support for the 68000-based Atari series of + computers (including the TT, Falcon and Medusa). If you plan to use + this kernel on an Atari, say Y here and browse the material + available in <file:Documentation/m68k>; otherwise say N. + +config MAC + bool "Macintosh support" + depends on MMU + select MMU_MOTOROLA if MMU + help + This option enables support for the Apple Macintosh series of + computers (yes, there is experimental support now, at least for part + of the series). + + Say N unless you're willing to code the remaining necessary support. + ;) + +config APOLLO + bool "Apollo support" + depends on MMU + select MMU_MOTOROLA if MMU + help + Say Y here if you want to run Linux on an MC680x0-based Apollo + Domain workstation such as the DN3500. + +config VME + bool "VME (Motorola and BVM) support" + depends on MMU + select MMU_MOTOROLA if MMU + help + Say Y here if you want to build a kernel for a 680x0 based VME + board. Boards currently supported include Motorola boards MVME147, + MVME162, MVME166, MVME167, MVME172, and MVME177. BVME4000 and + BVME6000 boards from BVM Ltd are also supported. + +config MVME147 + bool "MVME147 support" + depends on MMU + depends on VME + help + Say Y to include support for early Motorola VME boards. This will + build a kernel which can run on MVME147 single-board computers. If + you select this option you will have to select the appropriate + drivers for SCSI, Ethernet and serial ports later on. + +config MVME16x + bool "MVME162, 166 and 167 support" + depends on MMU + depends on VME + help + Say Y to include support for Motorola VME boards. This will build a + kernel which can run on MVME162, MVME166, MVME167, MVME172, and + MVME177 boards. If you select this option you will have to select + the appropriate drivers for SCSI, Ethernet and serial ports later + on. + +config BVME6000 + bool "BVME4000 and BVME6000 support" + depends on MMU + depends on VME + help + Say Y to include support for VME boards from BVM Ltd. This will + build a kernel which can run on BVME4000 and BVME6000 boards. If + you select this option you will have to select the appropriate + drivers for SCSI, Ethernet and serial ports later on. + +config HP300 + bool "HP9000/300 and HP9000/400 support" + depends on MMU + select MMU_MOTOROLA if MMU + help + This option enables support for the HP9000/300 and HP9000/400 series + of workstations. Support for these machines is still somewhat + experimental. If you plan to try to use the kernel on such a machine + say Y here. + Everybody else says N. + +config SUN3X + bool "Sun3x support" + depends on MMU + select MMU_MOTOROLA if MMU + select M68030 + help + This option enables support for the Sun 3x series of workstations. + Be warned that this support is very experimental. + Note that Sun 3x kernels are not compatible with Sun 3 hardware. + General Linux information on the Sun 3x series (now discontinued) + is at <http://www.angelfire.com/ca2/tech68k/sun3.html>. + + If you don't want to compile a kernel for a Sun 3x, say N. + +config Q40 + bool "Q40/Q60 support" + depends on MMU + select MMU_MOTOROLA if MMU + help + The Q40 is a Motorola 68040-based successor to the Sinclair QL + manufactured in Germany. There is an official Q40 home page at + <http://www.q40.de/>. This option enables support for the Q40 and + Q60. Select your CPU below. For 68LC060 don't forget to enable FPU + emulation. + +config SUN3 + bool "Sun3 support" + depends on MMU + depends on !MMU_MOTOROLA + select MMU_SUN3 if MMU + select M68020 + help + This option enables support for the Sun 3 series of workstations + (3/50, 3/60, 3/1xx, 3/2xx systems). Enabling this option requires + that all other hardware types must be disabled, as Sun 3 kernels + are incompatible with all other m68k targets (including Sun 3x!). + + If you don't want to compile a kernel exclusively for a Sun 3, say N. -config M5206e - bool "MCF5206e" - select COLDFIRE - select COLDFIRE_SW_A7 - select HAVE_MBAR - help - Motorola ColdFire 5206e processor support. - -config M520x - bool "MCF520x" - select COLDFIRE - select GENERIC_CLOCKEVENTS - select HAVE_CACHE_SPLIT - help - Freescale Coldfire 5207/5208 processor support. - -config M523x - bool "MCF523x" - select COLDFIRE - select GENERIC_CLOCKEVENTS - select HAVE_CACHE_SPLIT - select HAVE_IPSBAR - help - Freescale Coldfire 5230/1/2/4/5 processor support - -config M5249 - bool "MCF5249" - select COLDFIRE - select COLDFIRE_SW_A7 - select HAVE_MBAR - help - Motorola ColdFire 5249 processor support. - -config M5271 - bool "MCF5271" - select COLDFIRE - select HAVE_CACHE_SPLIT - select HAVE_IPSBAR - help - Freescale (Motorola) ColdFire 5270/5271 processor support. - -config M5272 - bool "MCF5272" - select COLDFIRE - select COLDFIRE_SW_A7 - select HAVE_MBAR - help - Motorola ColdFire 5272 processor support. - -config M5275 - bool "MCF5275" - select COLDFIRE - select HAVE_CACHE_SPLIT - select HAVE_IPSBAR - help - Freescale (Motorola) ColdFire 5274/5275 processor support. - -config M528x - bool "MCF528x" - select COLDFIRE - select GENERIC_CLOCKEVENTS - select HAVE_CACHE_SPLIT - select HAVE_IPSBAR - help - Motorola ColdFire 5280/5282 processor support. - -config M5307 - bool "MCF5307" - select COLDFIRE - select COLDFIRE_SW_A7 - select HAVE_CACHE_CB - select HAVE_MBAR - help - Motorola ColdFire 5307 processor support. - -config M532x - bool "MCF532x" - select COLDFIRE - select HAVE_CACHE_CB - help - Freescale (Motorola) ColdFire 532x processor support. - -config M5407 - bool "MCF5407" - select COLDFIRE - select COLDFIRE_SW_A7 - select HAVE_CACHE_CB - select HAVE_MBAR - help - Motorola ColdFire 5407 processor support. - -config M547x - bool "MCF547x" - select COLDFIRE - select HAVE_CACHE_CB - select HAVE_MBAR - help - Freescale ColdFire 5470/5471/5472/5473/5474/5475 processor support. - -config M548x - bool "MCF548x" - select COLDFIRE - select HAVE_CACHE_CB - select HAVE_MBAR - help - Freescale ColdFire 5480/5481/5482/5483/5484/5485 processor support. - -endchoice - -config M527x - bool - depends on (M5271 || M5275) - select GENERIC_CLOCKEVENTS - default y - -config M54xx +config PILOT bool - depends on (M548x || M547x) - default y - -config CLOCK_SET - bool "Enable setting the CPU clock frequency" - default n - help - On some CPU's you do not need to know what the core CPU clock - frequency is. On these you can disable clock setting. On some - traditional 68K parts, and on all ColdFire parts you need to set - the appropriate CPU clock frequency. On these devices many of the - onboard peripherals derive their timing from the master CPU clock - frequency. - -config CLOCK_FREQ - int "Set the core clock frequency" - default "66666666" - depends on CLOCK_SET - help - Define the CPU clock frequency in use. This is the core clock - frequency, it may or may not be the same as the external clock - crystal fitted to your board. Some processors have an internal - PLL and can have their frequency programmed at run time, others - use internal dividers. In general the kernel won't setup a PLL - if it is fitted (there are some exceptions). This value will be - specific to the exact CPU that you are using. - -config OLDMASK - bool "Old mask 5307 (1H55J) silicon" - depends on M5307 - help - Build support for the older revision ColdFire 5307 silicon. - Specifically this is the 1H55J mask revision. - -if HAVE_CACHE_SPLIT -choice - prompt "Split Cache Configuration" - default CACHE_I - -config CACHE_I - bool "Instruction" - help - Use all of the ColdFire CPU cache memory as an instruction cache. - -config CACHE_D - bool "Data" - help - Use all of the ColdFire CPU cache memory as a data cache. - -config CACHE_BOTH - bool "Both" - help - Split the ColdFire CPU cache, and use half as an instruction cache - and half as a data cache. -endchoice -endif - -if HAVE_CACHE_CB -choice - prompt "Data cache mode" - default CACHE_WRITETHRU - -config CACHE_WRITETHRU - bool "Write-through" - help - The ColdFire CPU cache is set into Write-through mode. - -config CACHE_COPYBACK - bool "Copy-back" - help - The ColdFire CPU cache is set into Copy-back mode. -endchoice -endif - -comment "Platform" config PILOT3 bool "Pilot 1000/5000, PalmPilot Personal/Pro, or PalmIII support" depends on M68328 + select PILOT help Support for the Palm Pilot 1000/5000, Personal/Pro and PalmIII. @@ -302,7 +147,7 @@ config XCOPILOT_BUGS Support the bugs of Xcopilot. config UC5272 - bool 'Arcturus Networks uC5272 dimm board support' + bool "Arcturus Networks uC5272 dimm board support" depends on M5272 help Support for the Arcturus Networks uC5272 dimm board. @@ -356,15 +201,23 @@ config UCQUICC help Support for the Lineo uCquicc board. +config ARNEWSH + bool + config ARN5206 bool "Arnewsh 5206 board support" depends on M5206 + select ARNEWSH help Support for the Arnewsh 5206 board. +config FREESCALE + bool + config M5206eC3 bool "Motorola M5206eC3 board support" depends on M5206e + select FREESCALE help Support for the Motorola M5206eC3 board. @@ -377,75 +230,92 @@ config ELITE config M5208EVB bool "Freescale M5208EVB board support" depends on M520x + select FREESCALE help Support for the Freescale Coldfire M5208EVB. config M5235EVB bool "Freescale M5235EVB support" depends on M523x + select FREESCALE help Support for the Freescale M5235EVB board. config M5249C3 bool "Motorola M5249C3 board support" depends on M5249 + select FREESCALE help Support for the Motorola M5249C3 board. config M5271EVB bool "Freescale (Motorola) M5271EVB board support" depends on M5271 + select FREESCALE help Support for the Freescale (Motorola) M5271EVB board. config M5275EVB bool "Freescale (Motorola) M5275EVB board support" depends on M5275 + select FREESCALE help Support for the Freescale (Motorola) M5275EVB board. config M5272C3 bool "Motorola M5272C3 board support" depends on M5272 + select FREESCALE help Support for the Motorola M5272C3 board. +config senTec + bool + config COBRA5272 bool "senTec COBRA5272 board support" depends on M5272 + select senTec help Support for the senTec COBRA5272 board. +config AVNET + bool + config AVNET5282 bool "Avnet 5282 board support" depends on M528x + select AVNET help - Support for the Avnet 5282 board. - + Support for the Avnet 5282 board. + config M5282EVB bool "Motorola M5282EVB board support" depends on M528x + select FREESCALE help Support for the Motorola M5282EVB board. config COBRA5282 bool "senTec COBRA5282 board support" depends on M528x + select senTec help Support for the senTec COBRA5282 board. - + config SOM5282EM bool "EMAC.Inc SOM5282EM board support" depends on M528x + select EMAC_INC help - Support for the EMAC.Inc SOM5282EM module. - + Support for the EMAC.Inc SOM5282EM module. + config WILDFIRE bool "Intec Automation Inc. WildFire board support" depends on M528x help Support for the Intec Automation Inc. WildFire. - + config WILDFIREMOD bool "Intec Automation Inc. WildFire module support" depends on M528x @@ -455,12 +325,14 @@ config WILDFIREMOD config ARN5307 bool "Arnewsh 5307 board support" depends on M5307 + select ARNEWSH help Support for the Arnewsh 5307 board. config M5307C3 bool "Motorola M5307C3 board support" depends on M5307 + select FREESCALE help Support for the Motorola M5307C3 board. @@ -473,6 +345,7 @@ config SECUREEDGEMP3 config M5329EVB bool "Freescale (Motorola) M5329EVB board support" depends on M532x + select FREESCALE help Support for the Freescale (Motorola) M5329EVB board. @@ -485,6 +358,7 @@ config COBRA5329 config M5407C3 bool "Motorola M5407C3 board support" depends on M5407 + select FREESCALE help Support for the Motorola M5407C3 board. @@ -524,9 +398,13 @@ config SNAPGEAR help Special additional support for SnapGear router boards. +config SNEHA + bool + config CPU16B bool "Sneha Technologies S.L. Sarasvati board support" depends on M5272 + select SNEHA help Support for the SNEHA CPU16B board. @@ -536,63 +414,20 @@ config MOD5272 help Support for the Netburner MOD-5272 board. +config SAVANT + bool + config SAVANTrosie1 bool "Savant Rosie1 board support" depends on M523x + select SAVANT help Support for the Savant Rosie1 board. -config ROMFS_FROM_ROM - bool "ROMFS image not RAM resident" - depends on (NETtel || SNAPGEAR) - help - The ROMfs filesystem will stay resident in the FLASH/ROM, not be - moved into RAM. - -config PILOT - bool - default y - depends on (PILOT3 || PILOT5) - -config ARNEWSH - bool - default y - depends on (ARN5206 || ARN5307) - -config FREESCALE - bool - default y - depends on (M5206eC3 || M5208EVB || M5235EVB || M5249C3 || M5271EVB || M5272C3 || M5275EVB || M5282EVB || M5307C3 || M5329EVB || M5407C3) - -config HW_FEITH - bool - default y - depends on (CLEOPATRA || CANCam || SCALES) - -config senTec - bool - default y - depends on (COBRA5272 || COBRA5282) - -config EMAC_INC - bool - default y - depends on (SOM5282EM) -config SNEHA - bool - default y - depends on CPU16B +if !MMU || COLDFIRE -config SAVANT - bool - default y - depends on SAVANTrosie1 - -config AVNET - bool - default y - depends on (AVNET5282) +comment "Machine Options" config UBOOT bool "Support for U-Boot command line parameters" @@ -673,33 +508,6 @@ config KERNELBASE a system with the RAM based at address 0, and leaving enough room for the theoretical maximum number of 256 vectors. -choice - prompt "RAM bus width" - default RAMAUTOBIT - -config RAMAUTOBIT - bool "AUTO" - help - Select the physical RAM data bus size. Not needed on most platforms, - so you can generally choose AUTO. - -config RAM8BIT - bool "8bit" - help - Configure RAM bus to be 8 bits wide. - -config RAM16BIT - bool "16bit" - help - Configure RAM bus to be 16 bits wide. - -config RAM32BIT - bool "32bit" - help - Configure RAM bus to be 32 bits wide. - -endchoice - comment "ROM configuration" config ROM @@ -772,16 +580,4 @@ config ROMKERNEL endchoice -if COLDFIRE -source "kernel/Kconfig.preempt" endif - -source "kernel/time/Kconfig" - -config ISA_DMA_API - bool - depends on !M5272 - default y - -source "drivers/pcmcia/Kconfig" - diff --git a/arch/m68k/Kconfig.mmu b/arch/m68k/Kconfig.mmu deleted file mode 100644 index 13e20bbc4079..000000000000 --- a/arch/m68k/Kconfig.mmu +++ /dev/null @@ -1,411 +0,0 @@ -config GENERIC_IOMAP - bool - default y - -config ARCH_MAY_HAVE_PC_FDC - bool - depends on BROKEN && (Q40 || SUN3X) - default y - -config ARCH_USES_GETTIMEOFFSET - def_bool y - -config EISA - bool - ---help--- - The Extended Industry Standard Architecture (EISA) bus was - developed as an open alternative to the IBM MicroChannel bus. - - The EISA bus provided some of the features of the IBM MicroChannel - bus while maintaining backward compatibility with cards made for - the older ISA bus. The EISA bus saw limited use between 1988 and - 1995 when it was made obsolete by the PCI bus. - - Say Y here if you are building a kernel for an EISA-based machine. - - Otherwise, say N. - -config MCA - bool - help - MicroChannel Architecture is found in some IBM PS/2 machines and - laptops. It is a bus system similar to PCI or ISA. See - <file:Documentation/mca.txt> (and especially the web page given - there) before attempting to build an MCA bus kernel. - -config PCMCIA - tristate - ---help--- - Say Y here if you want to attach PCMCIA- or PC-cards to your Linux - computer. These are credit-card size devices such as network cards, - modems or hard drives often used with laptops computers. There are - actually two varieties of these cards: the older 16 bit PCMCIA cards - and the newer 32 bit CardBus cards. If you want to use CardBus - cards, you need to say Y here and also to "CardBus support" below. - - To use your PC-cards, you will need supporting software from David - Hinds' pcmcia-cs package (see the file <file:Documentation/Changes> - for location). Please also read the PCMCIA-HOWTO, available from - <http://www.tldp.org/docs.html#howto>. - - To compile this driver as modules, choose M here: the - modules will be called pcmcia_core and ds. - -config AMIGA - bool "Amiga support" - select MMU_MOTOROLA if MMU - help - This option enables support for the Amiga series of computers. If - you plan to use this kernel on an Amiga, say Y here and browse the - material available in <file:Documentation/m68k>; otherwise say N. - -config ATARI - bool "Atari support" - select MMU_MOTOROLA if MMU - help - This option enables support for the 68000-based Atari series of - computers (including the TT, Falcon and Medusa). If you plan to use - this kernel on an Atari, say Y here and browse the material - available in <file:Documentation/m68k>; otherwise say N. - -config MAC - bool "Macintosh support" - select MMU_MOTOROLA if MMU - help - This option enables support for the Apple Macintosh series of - computers (yes, there is experimental support now, at least for part - of the series). - - Say N unless you're willing to code the remaining necessary support. - ;) - -config NUBUS - bool - depends on MAC - default y - -config M68K_L2_CACHE - bool - depends on MAC - default y - -config APOLLO - bool "Apollo support" - select MMU_MOTOROLA if MMU - help - Say Y here if you want to run Linux on an MC680x0-based Apollo - Domain workstation such as the DN3500. - -config VME - bool "VME (Motorola and BVM) support" - select MMU_MOTOROLA if MMU - help - Say Y here if you want to build a kernel for a 680x0 based VME - board. Boards currently supported include Motorola boards MVME147, - MVME162, MVME166, MVME167, MVME172, and MVME177. BVME4000 and - BVME6000 boards from BVM Ltd are also supported. - -config MVME147 - bool "MVME147 support" - depends on VME - help - Say Y to include support for early Motorola VME boards. This will - build a kernel which can run on MVME147 single-board computers. If - you select this option you will have to select the appropriate - drivers for SCSI, Ethernet and serial ports later on. - -config MVME16x - bool "MVME162, 166 and 167 support" - depends on VME - help - Say Y to include support for Motorola VME boards. This will build a - kernel which can run on MVME162, MVME166, MVME167, MVME172, and - MVME177 boards. If you select this option you will have to select - the appropriate drivers for SCSI, Ethernet and serial ports later - on. - -config BVME6000 - bool "BVME4000 and BVME6000 support" - depends on VME - help - Say Y to include support for VME boards from BVM Ltd. This will - build a kernel which can run on BVME4000 and BVME6000 boards. If - you select this option you will have to select the appropriate - drivers for SCSI, Ethernet and serial ports later on. - -config HP300 - bool "HP9000/300 and HP9000/400 support" - select MMU_MOTOROLA if MMU - help - This option enables support for the HP9000/300 and HP9000/400 series - of workstations. Support for these machines is still somewhat - experimental. If you plan to try to use the kernel on such a machine - say Y here. - Everybody else says N. - -config DIO - bool "DIO bus support" - depends on HP300 - default y - help - Say Y here to enable support for the "DIO" expansion bus used in - HP300 machines. If you are using such a system you almost certainly - want this. - -config SUN3X - bool "Sun3x support" - select MMU_MOTOROLA if MMU - select M68030 - help - This option enables support for the Sun 3x series of workstations. - Be warned that this support is very experimental. - Note that Sun 3x kernels are not compatible with Sun 3 hardware. - General Linux information on the Sun 3x series (now discontinued) - is at <http://www.angelfire.com/ca2/tech68k/sun3.html>. - - If you don't want to compile a kernel for a Sun 3x, say N. - -config Q40 - bool "Q40/Q60 support" - select MMU_MOTOROLA if MMU - help - The Q40 is a Motorola 68040-based successor to the Sinclair QL - manufactured in Germany. There is an official Q40 home page at - <http://www.q40.de/>. This option enables support for the Q40 and - Q60. Select your CPU below. For 68LC060 don't forget to enable FPU - emulation. - -config SUN3 - bool "Sun3 support" - depends on !MMU_MOTOROLA - select MMU_SUN3 if MMU - select M68020 - help - This option enables support for the Sun 3 series of workstations - (3/50, 3/60, 3/1xx, 3/2xx systems). Enabling this option requires - that all other hardware types must be disabled, as Sun 3 kernels - are incompatible with all other m68k targets (including Sun 3x!). - - If you don't want to compile a kernel exclusively for a Sun 3, say N. - -config NATFEAT - bool "ARAnyM emulator support" - depends on ATARI - help - This option enables support for ARAnyM native features, such as - access to a disk image as /dev/hda. - -config NFBLOCK - tristate "NatFeat block device support" - depends on BLOCK && NATFEAT - help - Say Y to include support for the ARAnyM NatFeat block device - which allows direct access to the hard drives without using - the hardware emulation. - -config NFCON - tristate "NatFeat console driver" - depends on NATFEAT - help - Say Y to include support for the ARAnyM NatFeat console driver - which allows the console output to be redirected to the stderr - output of ARAnyM. - -config NFETH - tristate "NatFeat Ethernet support" - depends on NET_ETHERNET && NATFEAT - help - Say Y to include support for the ARAnyM NatFeat network device - which will emulate a regular ethernet device while presenting an - ethertap device to the host system. - -comment "Processor type" - -config M68020 - bool "68020 support" - help - If you anticipate running this kernel on a computer with a MC68020 - processor, say Y. Otherwise, say N. Note that the 68020 requires a - 68851 MMU (Memory Management Unit) to run Linux/m68k, except on the - Sun 3, which provides its own version. - -config M68030 - bool "68030 support" - depends on !MMU_SUN3 - help - If you anticipate running this kernel on a computer with a MC68030 - processor, say Y. Otherwise, say N. Note that a MC68EC030 will not - work, as it does not include an MMU (Memory Management Unit). - -config M68040 - bool "68040 support" - depends on !MMU_SUN3 - help - If you anticipate running this kernel on a computer with a MC68LC040 - or MC68040 processor, say Y. Otherwise, say N. Note that an - MC68EC040 will not work, as it does not include an MMU (Memory - Management Unit). - -config M68060 - bool "68060 support" - depends on !MMU_SUN3 - help - If you anticipate running this kernel on a computer with a MC68060 - processor, say Y. Otherwise, say N. - -config MMU_MOTOROLA - bool - -config MMU_SUN3 - bool - depends on MMU && !MMU_MOTOROLA - -config M68KFPU_EMU - bool "Math emulation support (EXPERIMENTAL)" - depends on EXPERIMENTAL - help - At some point in the future, this will cause floating-point math - instructions to be emulated by the kernel on machines that lack a - floating-point math coprocessor. Thrill-seekers and chronically - sleep-deprived psychotic hacker types can say Y now, everyone else - should probably wait a while. - -config M68KFPU_EMU_EXTRAPREC - bool "Math emulation extra precision" - depends on M68KFPU_EMU - help - The fpu uses normally a few bit more during calculations for - correct rounding, the emulator can (often) do the same but this - extra calculation can cost quite some time, so you can disable - it here. The emulator will then "only" calculate with a 64 bit - mantissa and round slightly incorrect, what is more than enough - for normal usage. - -config M68KFPU_EMU_ONLY - bool "Math emulation only kernel" - depends on M68KFPU_EMU - help - This option prevents any floating-point instructions from being - compiled into the kernel, thereby the kernel doesn't save any - floating point context anymore during task switches, so this - kernel will only be usable on machines without a floating-point - math coprocessor. This makes the kernel a bit faster as no tests - needs to be executed whether a floating-point instruction in the - kernel should be executed or not. - -config ADVANCED - bool "Advanced configuration options" - ---help--- - This gives you access to some advanced options for the CPU. The - defaults should be fine for most users, but these options may make - it possible for you to improve performance somewhat if you know what - you are doing. - - Note that the answer to this question won't directly affect the - kernel: saying N will just cause the configurator to skip all - the questions about these options. - - Most users should say N to this question. - -config RMW_INSNS - bool "Use read-modify-write instructions" - depends on ADVANCED - ---help--- - This allows to use certain instructions that work with indivisible - read-modify-write bus cycles. While this is faster than the - workaround of disabling interrupts, it can conflict with DMA - ( = direct memory access) on many Amiga systems, and it is also said - to destabilize other machines. It is very likely that this will - cause serious problems on any Amiga or Atari Medusa if set. The only - configuration where it should work are 68030-based Ataris, where it - apparently improves performance. But you've been warned! Unless you - really know what you are doing, say N. Try Y only if you're quite - adventurous. - -config SINGLE_MEMORY_CHUNK - bool "Use one physical chunk of memory only" if ADVANCED && !SUN3 - default y if SUN3 - select NEED_MULTIPLE_NODES - help - Ignore all but the first contiguous chunk of physical memory for VM - purposes. This will save a few bytes kernel size and may speed up - some operations. Say N if not sure. - -config 060_WRITETHROUGH - bool "Use write-through caching for 68060 supervisor accesses" - depends on ADVANCED && M68060 - ---help--- - The 68060 generally uses copyback caching of recently accessed data. - Copyback caching means that memory writes will be held in an on-chip - cache and only written back to memory some time later. Saying Y - here will force supervisor (kernel) accesses to use writethrough - caching. Writethrough caching means that data is written to memory - straight away, so that cache and memory data always agree. - Writethrough caching is less efficient, but is needed for some - drivers on 68060 based systems where the 68060 bus snooping signal - is hardwired on. The 53c710 SCSI driver is known to suffer from - this problem. - -config ARCH_DISCONTIGMEM_ENABLE - def_bool !SINGLE_MEMORY_CHUNK - -config NODES_SHIFT - int - default "3" - depends on !SINGLE_MEMORY_CHUNK - -config ZORRO - bool "Amiga Zorro (AutoConfig) bus support" - depends on AMIGA - help - This enables support for the Zorro bus in the Amiga. If you have - expansion cards in your Amiga that conform to the Amiga - AutoConfig(tm) specification, say Y, otherwise N. Note that even - expansion cards that do not fit in the Zorro slots but fit in e.g. - the CPU slot may fall in this category, so you have to say Y to let - Linux use these. - -config AMIGA_PCMCIA - bool "Amiga 1200/600 PCMCIA support (EXPERIMENTAL)" - depends on AMIGA && EXPERIMENTAL - help - Include support in the kernel for pcmcia on Amiga 1200 and Amiga - 600. If you intend to use pcmcia cards say Y; otherwise say N. - -config HEARTBEAT - bool "Use power LED as a heartbeat" if AMIGA || APOLLO || ATARI || MAC ||Q40 - default y if !AMIGA && !APOLLO && !ATARI && !MAC && !Q40 && HP300 - help - Use the power-on LED on your machine as a load meter. The exact - behavior is platform-dependent, but normally the flash frequency is - a hyperbolic function of the 5-minute load average. - -# We have a dedicated heartbeat LED. :-) -config PROC_HARDWARE - bool "/proc/hardware support" - help - Say Y here to support the /proc/hardware file, which gives you - access to information about the machine you're running on, - including the model, CPU, MMU, clock speed, BogoMIPS rating, - and memory size. - -config ISA - bool - depends on Q40 || AMIGA_PCMCIA - default y - help - Find out whether you have ISA slots on your motherboard. ISA is the - name of a bus system, i.e. the way the CPU talks to the other stuff - inside your box. Other bus systems are PCI, EISA, MicroChannel - (MCA) or VESA. ISA is an older system, now being displaced by PCI; - newer boards don't support it. If you have ISA, say Y, otherwise N. - -config GENERIC_ISA_DMA - bool - depends on Q40 || AMIGA_PCMCIA - default y - -source "drivers/pci/Kconfig" - -source "drivers/zorro/Kconfig" - diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile index be46cadd4017..cf318f20c64d 100644 --- a/arch/m68k/Makefile +++ b/arch/m68k/Makefile @@ -1,7 +1,171 @@ +# +# m68k/Makefile +# +# This file is included by the global makefile so that you can add your own +# architecture-specific flags and dependencies. Remember to do have actions +# for "archclean" and "archdep" for cleaning up and making dependencies for +# this architecture +# +# This file is subject to the terms and conditions of the GNU General Public +# License. See the file "COPYING" in the main directory of this archive +# for more details. +# +# Copyright (C) 1994 by Hamish Macdonald +# Copyright (C) 2002,2011 Greg Ungerer <gerg@snapgear.com> +# + KBUILD_DEFCONFIG := multi_defconfig +# +# Enable processor type. Ordering of these is important - we want to +# use the minimum processor type of the range we support. The logic +# for 680x0 will only allow use of the -m68060 or -m68040 if no other +# 680x0 type is specified - and no option is specified for 68030 or +# 68020. The other m68k/ColdFire types always specify some type of +# compiler cpu type flag. +# +ifndef CONFIG_M68040 +cpuflags-$(CONFIG_M68060) := -m68060 +endif +ifndef CONFIG_M68060 +cpuflags-$(CONFIG_M68040) := -m68040 +endif +cpuflags-$(CONFIG_M68030) := +cpuflags-$(CONFIG_M68020) := +cpuflags-$(CONFIG_M68360) := -m68332 +cpuflags-$(CONFIG_M68000) := -m68000 +cpuflags-$(CONFIG_M54xx) := $(call cc-option,-mcpu=5475,-m5200) +cpuflags-$(CONFIG_M5407) := $(call cc-option,-mcpu=5407,-m5200) +cpuflags-$(CONFIG_M532x) := $(call cc-option,-mcpu=532x,-m5307) +cpuflags-$(CONFIG_M5307) := $(call cc-option,-mcpu=5307,-m5200) +cpuflags-$(CONFIG_M528x) := $(call cc-option,-mcpu=528x,-m5307) +cpuflags-$(CONFIG_M5275) := $(call cc-option,-mcpu=5275,-m5307) +cpuflags-$(CONFIG_M5272) := $(call cc-option,-mcpu=5272,-m5307) +cpuflags-$(CONFIG_M5271) := $(call cc-option,-mcpu=5271,-m5307) +cpuflags-$(CONFIG_M523x) := $(call cc-option,-mcpu=523x,-m5307) +cpuflags-$(CONFIG_M5249) := $(call cc-option,-mcpu=5249,-m5200) +cpuflags-$(CONFIG_M520x) := $(call cc-option,-mcpu=5208,-m5200) +cpuflags-$(CONFIG_M5206e) := $(call cc-option,-mcpu=5206e,-m5200) +cpuflags-$(CONFIG_M5206) := $(call cc-option,-mcpu=5206,-m5200) + +KBUILD_AFLAGS += $(cpuflags-y) +KBUILD_CFLAGS += $(cpuflags-y) -pipe ifdef CONFIG_MMU -include $(srctree)/arch/m68k/Makefile_mm +# without -fno-strength-reduce the 53c7xx.c driver fails ;-( +KBUILD_CFLAGS += -fno-strength-reduce -ffixed-a2 +else +# we can use a m68k-linux-gcc toolchain with these in place +KBUILD_CFLAGS += -DUTS_SYSNAME=\"uClinux\" +KBUILD_CFLAGS += -D__uClinux__ +KBUILD_AFLAGS += -D__uClinux__ +endif + +LDFLAGS := -m m68kelf +KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/m68k/kernel/module.lds +ifneq ($(SUBARCH),$(ARCH)) + ifeq ($(CROSS_COMPILE),) + CROSS_COMPILE := $(call cc-cross-prefix, \ + m68k-linux-gnu- m68k-linux- m68k-unknown-linux-gnu-) + endif +endif + +ifdef CONFIG_SUN3 +LDFLAGS_vmlinux = -N +endif + +CHECKFLAGS += -D__mc68000__ + + +ifdef CONFIG_KGDB +# If configured for kgdb support, include debugging infos and keep the +# frame pointer +KBUILD_CFLAGS := $(subst -fomit-frame-pointer,,$(KBUILD_CFLAGS)) -g +endif + +# +# Select the assembler head startup code. Order is important. The default +# head code is first, processor specific selections can override it after. +# +head-y := arch/m68k/kernel/head.o +head-$(CONFIG_SUN3) := arch/m68k/kernel/sun3-head.o +head-$(CONFIG_M68360) := arch/m68k/platform/68360/head.o +head-$(CONFIG_M68000) := arch/m68k/platform/68328/head.o +head-$(CONFIG_COLDFIRE) := arch/m68k/platform/coldfire/head.o + +core-y += arch/m68k/kernel/ arch/m68k/mm/ +libs-y += arch/m68k/lib/ + +core-$(CONFIG_Q40) += arch/m68k/q40/ +core-$(CONFIG_AMIGA) += arch/m68k/amiga/ +core-$(CONFIG_ATARI) += arch/m68k/atari/ +core-$(CONFIG_MAC) += arch/m68k/mac/ +core-$(CONFIG_HP300) += arch/m68k/hp300/ +core-$(CONFIG_APOLLO) += arch/m68k/apollo/ +core-$(CONFIG_MVME147) += arch/m68k/mvme147/ +core-$(CONFIG_MVME16x) += arch/m68k/mvme16x/ +core-$(CONFIG_BVME6000) += arch/m68k/bvme6000/ +core-$(CONFIG_SUN3X) += arch/m68k/sun3x/ arch/m68k/sun3/ +core-$(CONFIG_SUN3) += arch/m68k/sun3/ arch/m68k/sun3/prom/ +core-$(CONFIG_NATFEAT) += arch/m68k/emu/ +core-$(CONFIG_M68040) += arch/m68k/fpsp040/ +core-$(CONFIG_M68060) += arch/m68k/ifpsp060/ +core-$(CONFIG_M68KFPU_EMU) += arch/m68k/math-emu/ +core-$(CONFIG_M68360) += arch/m68k/platform/68360/ +core-$(CONFIG_M68000) += arch/m68k/platform/68328/ +core-$(CONFIG_M68EZ328) += arch/m68k/platform/68EZ328/ +core-$(CONFIG_M68VZ328) += arch/m68k/platform/68VZ328/ +core-$(CONFIG_COLDFIRE) += arch/m68k/platform/coldfire/ +core-$(CONFIG_M5206) += arch/m68k/platform/5206/ +core-$(CONFIG_M5206e) += arch/m68k/platform/5206/ +core-$(CONFIG_M520x) += arch/m68k/platform/520x/ +core-$(CONFIG_M523x) += arch/m68k/platform/523x/ +core-$(CONFIG_M5249) += arch/m68k/platform/5249/ +core-$(CONFIG_M527x) += arch/m68k/platform/527x/ +core-$(CONFIG_M5272) += arch/m68k/platform/5272/ +core-$(CONFIG_M528x) += arch/m68k/platform/528x/ +core-$(CONFIG_M5307) += arch/m68k/platform/5307/ +core-$(CONFIG_M532x) += arch/m68k/platform/532x/ +core-$(CONFIG_M5407) += arch/m68k/platform/5407/ +core-$(CONFIG_M54xx) += arch/m68k/platform/54xx/ + + +all: zImage + +lilo: vmlinux + if [ -f $(INSTALL_PATH)/vmlinux ]; then mv -f $(INSTALL_PATH)/vmlinux $(INSTALL_PATH)/vmlinux.old; fi + if [ -f $(INSTALL_PATH)/System.map ]; then mv -f $(INSTALL_PATH)/System.map $(INSTALL_PATH)/System.old; fi + cat vmlinux > $(INSTALL_PATH)/vmlinux + cp System.map $(INSTALL_PATH)/System.map + if [ -x /sbin/lilo ]; then /sbin/lilo; else /etc/lilo/install; fi + +zImage compressed: vmlinux.gz + +vmlinux.gz: vmlinux + +ifndef CONFIG_KGDB + cp vmlinux vmlinux.tmp + $(STRIP) vmlinux.tmp + gzip -9c vmlinux.tmp >vmlinux.gz + rm vmlinux.tmp else -include $(srctree)/arch/m68k/Makefile_no + gzip -9c vmlinux >vmlinux.gz endif + +bzImage: vmlinux.bz2 + +vmlinux.bz2: vmlinux + +ifndef CONFIG_KGDB + cp vmlinux vmlinux.tmp + $(STRIP) vmlinux.tmp + bzip2 -1c vmlinux.tmp >vmlinux.bz2 + rm vmlinux.tmp +else + bzip2 -1c vmlinux >vmlinux.bz2 +endif + +archclean: + rm -f vmlinux.gz vmlinux.bz2 + +install: + sh $(srctree)/arch/m68k/install.sh $(KERNELRELEASE) vmlinux.gz System.map "$(INSTALL_PATH)" diff --git a/arch/m68k/Makefile_mm b/arch/m68k/Makefile_mm deleted file mode 100644 index d449b6d5aecf..000000000000 --- a/arch/m68k/Makefile_mm +++ /dev/null @@ -1,121 +0,0 @@ -# -# m68k/Makefile -# -# This file is included by the global makefile so that you can add your own -# architecture-specific flags and dependencies. Remember to do have actions -# for "archclean" and "archdep" for cleaning up and making dependencies for -# this architecture -# -# This file is subject to the terms and conditions of the GNU General Public -# License. See the file "COPYING" in the main directory of this archive -# for more details. -# -# Copyright (C) 1994 by Hamish Macdonald -# - -# override top level makefile -AS += -m68020 -LDFLAGS := -m m68kelf -KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/m68k/kernel/module.lds -ifneq ($(SUBARCH),$(ARCH)) - ifeq ($(CROSS_COMPILE),) - CROSS_COMPILE := $(call cc-cross-prefix, \ - m68k-linux-gnu- m68k-linux- m68k-unknown-linux-gnu-) - endif -endif - -ifdef CONFIG_SUN3 -LDFLAGS_vmlinux = -N -endif - -CHECKFLAGS += -D__mc68000__ - -# without -fno-strength-reduce the 53c7xx.c driver fails ;-( -KBUILD_CFLAGS += -pipe -fno-strength-reduce -ffixed-a2 - -# enable processor switch if compiled only for a single cpu -ifndef CONFIG_M68020 -ifndef CONFIG_M68030 - -ifndef CONFIG_M68060 -KBUILD_CFLAGS += -m68040 -endif - -ifndef CONFIG_M68040 -KBUILD_CFLAGS += -m68060 -endif - -endif -endif - -ifdef CONFIG_KGDB -# If configured for kgdb support, include debugging infos and keep the -# frame pointer -KBUILD_CFLAGS := $(subst -fomit-frame-pointer,,$(KBUILD_CFLAGS)) -g -endif - -ifndef CONFIG_SUN3 -head-y := arch/m68k/kernel/head.o -else -head-y := arch/m68k/kernel/sun3-head.o -endif - -core-y += arch/m68k/kernel/ arch/m68k/mm/ -libs-y += arch/m68k/lib/ - -core-$(CONFIG_Q40) += arch/m68k/q40/ -core-$(CONFIG_AMIGA) += arch/m68k/amiga/ -core-$(CONFIG_ATARI) += arch/m68k/atari/ -core-$(CONFIG_MAC) += arch/m68k/mac/ -core-$(CONFIG_HP300) += arch/m68k/hp300/ -core-$(CONFIG_APOLLO) += arch/m68k/apollo/ -core-$(CONFIG_MVME147) += arch/m68k/mvme147/ -core-$(CONFIG_MVME16x) += arch/m68k/mvme16x/ -core-$(CONFIG_BVME6000) += arch/m68k/bvme6000/ -core-$(CONFIG_SUN3X) += arch/m68k/sun3x/ arch/m68k/sun3/ -core-$(CONFIG_SUN3) += arch/m68k/sun3/ arch/m68k/sun3/prom/ -core-$(CONFIG_NATFEAT) += arch/m68k/emu/ -core-$(CONFIG_M68040) += arch/m68k/fpsp040/ -core-$(CONFIG_M68060) += arch/m68k/ifpsp060/ -core-$(CONFIG_M68KFPU_EMU) += arch/m68k/math-emu/ - -all: zImage - -lilo: vmlinux - if [ -f $(INSTALL_PATH)/vmlinux ]; then mv -f $(INSTALL_PATH)/vmlinux $(INSTALL_PATH)/vmlinux.old; fi - if [ -f $(INSTALL_PATH)/System.map ]; then mv -f $(INSTALL_PATH)/System.map $(INSTALL_PATH)/System.old; fi - cat vmlinux > $(INSTALL_PATH)/vmlinux - cp System.map $(INSTALL_PATH)/System.map - if [ -x /sbin/lilo ]; then /sbin/lilo; else /etc/lilo/install; fi - -zImage compressed: vmlinux.gz - -vmlinux.gz: vmlinux - -ifndef CONFIG_KGDB - cp vmlinux vmlinux.tmp - $(STRIP) vmlinux.tmp - gzip -9c vmlinux.tmp >vmlinux.gz - rm vmlinux.tmp -else - gzip -9c vmlinux >vmlinux.gz -endif - -bzImage: vmlinux.bz2 - -vmlinux.bz2: vmlinux - -ifndef CONFIG_KGDB - cp vmlinux vmlinux.tmp - $(STRIP) vmlinux.tmp - bzip2 -1c vmlinux.tmp >vmlinux.bz2 - rm vmlinux.tmp -else - bzip2 -1c vmlinux >vmlinux.bz2 -endif - -archclean: - rm -f vmlinux.gz vmlinux.bz2 - -install: - sh $(srctree)/arch/m68k/install.sh $(KERNELRELEASE) vmlinux.gz System.map "$(INSTALL_PATH)" diff --git a/arch/m68k/Makefile_no b/arch/m68k/Makefile_no deleted file mode 100644 index 844d3f172264..000000000000 --- a/arch/m68k/Makefile_no +++ /dev/null @@ -1,124 +0,0 @@ -# -# arch/m68k/Makefile -# -# This file is subject to the terms and conditions of the GNU General Public -# License. See the file "COPYING" in the main directory of this archive -# for more details. -# -# (C) Copyright 2002, Greg Ungerer <gerg@snapgear.com> -# - -platform-$(CONFIG_M68328) := 68328 -platform-$(CONFIG_M68EZ328) := 68EZ328 -platform-$(CONFIG_M68VZ328) := 68VZ328 -platform-$(CONFIG_M68360) := 68360 -platform-$(CONFIG_M5206) := 5206 -platform-$(CONFIG_M5206e) := 5206 -platform-$(CONFIG_M520x) := 520x -platform-$(CONFIG_M523x) := 523x -platform-$(CONFIG_M5249) := 5249 -platform-$(CONFIG_M527x) := 527x -platform-$(CONFIG_M5272) := 5272 -platform-$(CONFIG_M528x) := 528x -platform-$(CONFIG_M5307) := 5307 -platform-$(CONFIG_M532x) := 532x -platform-$(CONFIG_M5407) := 5407 -platform-$(CONFIG_M54xx) := 54xx -PLATFORM := $(platform-y) - -board-$(CONFIG_PILOT) := pilot -board-$(CONFIG_UC5272) := UC5272 -board-$(CONFIG_UC5282) := UC5282 -board-$(CONFIG_UCSIMM) := ucsimm -board-$(CONFIG_UCDIMM) := ucdimm -board-$(CONFIG_UCQUICC) := uCquicc -board-$(CONFIG_DRAGEN2) := de2 -board-$(CONFIG_ARNEWSH) := ARNEWSH -board-$(CONFIG_FREESCALE) := FREESCALE -board-$(CONFIG_M5235EVB) := M5235EVB -board-$(CONFIG_M5271EVB) := M5271EVB -board-$(CONFIG_M5275EVB) := M5275EVB -board-$(CONFIG_M5282EVB) := M5282EVB -board-$(CONFIG_ELITE) := eLITE -board-$(CONFIG_NETtel) := NETtel -board-$(CONFIG_SECUREEDGEMP3) := MP3 -board-$(CONFIG_CLEOPATRA) := CLEOPATRA -board-$(CONFIG_senTec) := senTec -board-$(CONFIG_SNEHA) := SNEHA -board-$(CONFIG_M5208EVB) := M5208EVB -board-$(CONFIG_MOD5272) := MOD5272 -board-$(CONFIG_AVNET) := AVNET -board-$(CONFIG_SAVANT) := SAVANT -BOARD := $(board-y) - -model-$(CONFIG_RAMKERNEL) := ram -model-$(CONFIG_ROMKERNEL) := rom -MODEL := $(model-y) - -# -# Some code support is grouped together for a common cpu-subclass (for -# example all ColdFire cpu's are very similar). Determine the sub-class -# for the selected cpu. ONLY need to define this for the non-base member -# of the family. -# -cpuclass-$(CONFIG_M5206) := coldfire -cpuclass-$(CONFIG_M5206e) := coldfire -cpuclass-$(CONFIG_M520x) := coldfire -cpuclass-$(CONFIG_M523x) := coldfire -cpuclass-$(CONFIG_M5249) := coldfire -cpuclass-$(CONFIG_M527x) := coldfire -cpuclass-$(CONFIG_M5272) := coldfire -cpuclass-$(CONFIG_M528x) := coldfire -cpuclass-$(CONFIG_M5307) := coldfire -cpuclass-$(CONFIG_M532x) := coldfire -cpuclass-$(CONFIG_M5407) := coldfire -cpuclass-$(CONFIG_M54xx) := coldfire -cpuclass-$(CONFIG_M68328) := 68328 -cpuclass-$(CONFIG_M68EZ328) := 68328 -cpuclass-$(CONFIG_M68VZ328) := 68328 -cpuclass-$(CONFIG_M68360) := 68360 -CPUCLASS := $(cpuclass-y) - -ifneq ($(CPUCLASS),$(PLATFORM)) -CLASSDIR := arch/m68k/platform/$(cpuclass-y)/ -endif - -export PLATFORM BOARD MODEL CPUCLASS - -# -# Some CFLAG additions based on specific CPU type. -# -cflags-$(CONFIG_M5206) := $(call cc-option,-mcpu=5206,-m5200) -cflags-$(CONFIG_M5206e) := $(call cc-option,-mcpu=5206e,-m5200) -cflags-$(CONFIG_M520x) := $(call cc-option,-mcpu=5208,-m5200) -cflags-$(CONFIG_M523x) := $(call cc-option,-mcpu=523x,-m5307) -cflags-$(CONFIG_M5249) := $(call cc-option,-mcpu=5249,-m5200) -cflags-$(CONFIG_M5271) := $(call cc-option,-mcpu=5271,-m5307) -cflags-$(CONFIG_M5272) := $(call cc-option,-mcpu=5272,-m5307) -cflags-$(CONFIG_M5275) := $(call cc-option,-mcpu=5275,-m5307) -cflags-$(CONFIG_M528x) := $(call cc-option,-mcpu=528x,-m5307) -cflags-$(CONFIG_M5307) := $(call cc-option,-mcpu=5307,-m5200) -cflags-$(CONFIG_M532x) := $(call cc-option,-mcpu=532x,-m5307) -cflags-$(CONFIG_M5407) := $(call cc-option,-mcpu=5407,-m5200) -cflags-$(CONFIG_M54xx) := $(call cc-option,-mcpu=5475,-m5200) -cflags-$(CONFIG_M68328) := -m68000 -cflags-$(CONFIG_M68EZ328) := -m68000 -cflags-$(CONFIG_M68VZ328) := -m68000 -cflags-$(CONFIG_M68360) := -m68332 - -KBUILD_AFLAGS += $(cflags-y) - -KBUILD_CFLAGS += $(cflags-y) -KBUILD_CFLAGS += -D__linux__ -KBUILD_CFLAGS += -DUTS_SYSNAME=\"uClinux\" - -head-y := arch/m68k/platform/$(cpuclass-y)/head.o - -core-y += arch/m68k/kernel/ \ - arch/m68k/mm/ \ - $(CLASSDIR) \ - arch/m68k/platform/$(PLATFORM)/ -libs-y += arch/m68k/lib/ - -archclean: - diff --git a/arch/m68k/include/asm/entry.h b/arch/m68k/include/asm/entry.h index 876eec6f2b52..c3c5a8643e15 100644 --- a/arch/m68k/include/asm/entry.h +++ b/arch/m68k/include/asm/entry.h @@ -1,5 +1,254 @@ -#ifdef __uClinux__ -#include "entry_no.h" +#ifndef __M68K_ENTRY_H +#define __M68K_ENTRY_H + +#include <asm/setup.h> +#include <asm/page.h> +#ifdef __ASSEMBLY__ +#include <asm/thread_info.h> +#endif + +/* + * Stack layout in 'ret_from_exception': + * + * This allows access to the syscall arguments in registers d1-d5 + * + * 0(sp) - d1 + * 4(sp) - d2 + * 8(sp) - d3 + * C(sp) - d4 + * 10(sp) - d5 + * 14(sp) - a0 + * 18(sp) - a1 + * 1C(sp) - a2 + * 20(sp) - d0 + * 24(sp) - orig_d0 + * 28(sp) - stack adjustment + * 2C(sp) - [ sr ] [ format & vector ] + * 2E(sp) - [ pc-hiword ] [ sr ] + * 30(sp) - [ pc-loword ] [ pc-hiword ] + * 32(sp) - [ format & vector ] [ pc-loword ] + * ^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^ + * M68K COLDFIRE + */ + +/* the following macro is used when enabling interrupts */ +#if defined(MACH_ATARI_ONLY) + /* block out HSYNC on the atari */ +#define ALLOWINT (~0x400) +#define MAX_NOINT_IPL 3 #else -#include "entry_mm.h" + /* portable version */ +#define ALLOWINT (~0x700) +#define MAX_NOINT_IPL 0 +#endif /* machine compilation types */ + +#ifdef __ASSEMBLY__ +/* + * This defines the normal kernel pt-regs layout. + * + * regs a3-a6 and d6-d7 are preserved by C code + * the kernel doesn't mess with usp unless it needs to + */ +#define SWITCH_STACK_SIZE (6*4+4) /* includes return address */ + +#ifdef CONFIG_COLDFIRE +#ifdef CONFIG_COLDFIRE_SW_A7 +/* + * This is made a little more tricky on older ColdFires. There is no + * separate supervisor and user stack pointers. Need to artificially + * construct a usp in software... When doing this we need to disable + * interrupts, otherwise bad things will happen. + */ +.globl sw_usp +.globl sw_ksp + +.macro SAVE_ALL_SYS + move #0x2700,%sr /* disable intrs */ + btst #5,%sp@(2) /* from user? */ + bnes 6f /* no, skip */ + movel %sp,sw_usp /* save user sp */ + addql #8,sw_usp /* remove exception */ + movel sw_ksp,%sp /* kernel sp */ + subql #8,%sp /* room for exception */ + clrl %sp@- /* stkadj */ + movel %d0,%sp@- /* orig d0 */ + movel %d0,%sp@- /* d0 */ + lea %sp@(-32),%sp /* space for 8 regs */ + moveml %d1-%d5/%a0-%a2,%sp@ + movel sw_usp,%a0 /* get usp */ + movel %a0@-,%sp@(PT_OFF_PC) /* copy exception program counter */ + movel %a0@-,%sp@(PT_OFF_FORMATVEC)/*copy exception format/vector/sr */ + bra 7f + 6: + clrl %sp@- /* stkadj */ + movel %d0,%sp@- /* orig d0 */ + movel %d0,%sp@- /* d0 */ + lea %sp@(-32),%sp /* space for 8 regs */ + moveml %d1-%d5/%a0-%a2,%sp@ + 7: +.endm + +.macro SAVE_ALL_INT + SAVE_ALL_SYS + moveq #-1,%d0 /* not system call entry */ + movel %d0,%sp@(PT_OFF_ORIG_D0) +.endm + +.macro RESTORE_USER + move #0x2700,%sr /* disable intrs */ + movel sw_usp,%a0 /* get usp */ + movel %sp@(PT_OFF_PC),%a0@- /* copy exception program counter */ + movel %sp@(PT_OFF_FORMATVEC),%a0@-/*copy exception format/vector/sr */ + moveml %sp@,%d1-%d5/%a0-%a2 + lea %sp@(32),%sp /* space for 8 regs */ + movel %sp@+,%d0 + addql #4,%sp /* orig d0 */ + addl %sp@+,%sp /* stkadj */ + addql #8,%sp /* remove exception */ + movel %sp,sw_ksp /* save ksp */ + subql #8,sw_usp /* set exception */ + movel sw_usp,%sp /* restore usp */ + rte +.endm + +.macro RDUSP + movel sw_usp,%a3 +.endm + +.macro WRUSP + movel %a3,sw_usp +.endm + +#else /* !CONFIG_COLDFIRE_SW_A7 */ +/* + * Modern ColdFire parts have separate supervisor and user stack + * pointers. Simple load and restore macros for this case. + */ +.macro SAVE_ALL_SYS + move #0x2700,%sr /* disable intrs */ + clrl %sp@- /* stkadj */ + movel %d0,%sp@- /* orig d0 */ + movel %d0,%sp@- /* d0 */ + lea %sp@(-32),%sp /* space for 8 regs */ + moveml %d1-%d5/%a0-%a2,%sp@ +.endm + +.macro SAVE_ALL_INT + move #0x2700,%sr /* disable intrs */ + clrl %sp@- /* stkadj */ + pea -1:w /* orig d0 */ + movel %d0,%sp@- /* d0 */ + lea %sp@(-32),%sp /* space for 8 regs */ + moveml %d1-%d5/%a0-%a2,%sp@ +.endm + +.macro RESTORE_USER + moveml %sp@,%d1-%d5/%a0-%a2 + lea %sp@(32),%sp /* space for 8 regs */ + movel %sp@+,%d0 + addql #4,%sp /* orig d0 */ + addl %sp@+,%sp /* stkadj */ + rte +.endm + +.macro RDUSP + /*move %usp,%a3*/ + .word 0x4e6b +.endm + +.macro WRUSP + /*move %a3,%usp*/ + .word 0x4e63 +.endm + +#endif /* !CONFIG_COLDFIRE_SW_A7 */ + +.macro SAVE_SWITCH_STACK + lea %sp@(-24),%sp /* 6 regs */ + moveml %a3-%a6/%d6-%d7,%sp@ +.endm + +.macro RESTORE_SWITCH_STACK + moveml %sp@,%a3-%a6/%d6-%d7 + lea %sp@(24),%sp /* 6 regs */ +.endm + +#else /* !CONFIG_COLDFIRE */ + +/* + * All other types of m68k parts (68000, 680x0, CPU32) have the same + * entry and exit code. + */ + +/* + * a -1 in the orig_d0 field signifies + * that the stack frame is NOT for syscall + */ +.macro SAVE_ALL_INT + clrl %sp@- /* stk_adj */ + pea -1:w /* orig d0 */ + movel %d0,%sp@- /* d0 */ + moveml %d1-%d5/%a0-%a2,%sp@- +.endm + +.macro SAVE_ALL_SYS + clrl %sp@- /* stk_adj */ + movel %d0,%sp@- /* orig d0 */ + movel %d0,%sp@- /* d0 */ + moveml %d1-%d5/%a0-%a2,%sp@- +.endm + +.macro RESTORE_ALL + moveml %sp@+,%a0-%a2/%d1-%d5 + movel %sp@+,%d0 + addql #4,%sp /* orig d0 */ + addl %sp@+,%sp /* stk adj */ + rte +.endm + + +.macro SAVE_SWITCH_STACK + moveml %a3-%a6/%d6-%d7,%sp@- +.endm + +.macro RESTORE_SWITCH_STACK + moveml %sp@+,%a3-%a6/%d6-%d7 +.endm + +#endif /* !CONFIG_COLDFIRE */ + +/* + * Register %a2 is reserved and set to current task on MMU enabled systems. + * Non-MMU systems do not reserve %a2 in this way, and this definition is + * not used for them. + */ +#define curptr a2 + +#define GET_CURRENT(tmp) get_current tmp +.macro get_current reg=%d0 + movel %sp,\reg + andw #-THREAD_SIZE,\reg + movel \reg,%curptr + movel %curptr@,%curptr +.endm + +#else /* C source */ + +#define STR(X) STR1(X) +#define STR1(X) #X + +#define SAVE_ALL_INT \ + "clrl %%sp@-;" /* stk_adj */ \ + "pea -1:w;" /* orig d0 = -1 */ \ + "movel %%d0,%%sp@-;" /* d0 */ \ + "moveml %%d1-%%d5/%%a0-%%a2,%%sp@-" + +#define GET_CURRENT(tmp) \ + "movel %%sp,"#tmp"\n\t" \ + "andw #-"STR(THREAD_SIZE)","#tmp"\n\t" \ + "movel "#tmp",%%a2\n\t" \ + "movel %%a2@,%%a2" + #endif + +#endif /* __M68K_ENTRY_H */ diff --git a/arch/m68k/include/asm/entry_mm.h b/arch/m68k/include/asm/entry_mm.h deleted file mode 100644 index 73b8c8fbed9c..000000000000 --- a/arch/m68k/include/asm/entry_mm.h +++ /dev/null @@ -1,128 +0,0 @@ -#ifndef __M68K_ENTRY_H -#define __M68K_ENTRY_H - -#include <asm/setup.h> -#include <asm/page.h> -#ifdef __ASSEMBLY__ -#include <asm/thread_info.h> -#endif - -/* - * Stack layout in 'ret_from_exception': - * - * This allows access to the syscall arguments in registers d1-d5 - * - * 0(sp) - d1 - * 4(sp) - d2 - * 8(sp) - d3 - * C(sp) - d4 - * 10(sp) - d5 - * 14(sp) - a0 - * 18(sp) - a1 - * 1C(sp) - a2 - * 20(sp) - d0 - * 24(sp) - orig_d0 - * 28(sp) - stack adjustment - * 2C(sp) - sr - * 2E(sp) - pc - * 32(sp) - format & vector - */ - -/* - * 97/05/14 Andreas: Register %a2 is now set to the current task throughout - * the whole kernel. - */ - -/* the following macro is used when enabling interrupts */ -#if defined(MACH_ATARI_ONLY) - /* block out HSYNC on the atari */ -#define ALLOWINT (~0x400) -#define MAX_NOINT_IPL 3 -#else - /* portable version */ -#define ALLOWINT (~0x700) -#define MAX_NOINT_IPL 0 -#endif /* machine compilation types */ - -#ifdef __ASSEMBLY__ - -#define curptr a2 - -LFLUSH_I_AND_D = 0x00000808 - -#define SAVE_ALL_INT save_all_int -#define SAVE_ALL_SYS save_all_sys -#define RESTORE_ALL restore_all -/* - * This defines the normal kernel pt-regs layout. - * - * regs a3-a6 and d6-d7 are preserved by C code - * the kernel doesn't mess with usp unless it needs to - */ - -/* - * a -1 in the orig_d0 field signifies - * that the stack frame is NOT for syscall - */ -.macro save_all_int - clrl %sp@- | stk_adj - pea -1:w | orig d0 - movel %d0,%sp@- | d0 - moveml %d1-%d5/%a0-%a1/%curptr,%sp@- -.endm - -.macro save_all_sys - clrl %sp@- | stk_adj - movel %d0,%sp@- | orig d0 - movel %d0,%sp@- | d0 - moveml %d1-%d5/%a0-%a1/%curptr,%sp@- -.endm - -.macro restore_all - moveml %sp@+,%a0-%a1/%curptr/%d1-%d5 - movel %sp@+,%d0 - addql #4,%sp | orig d0 - addl %sp@+,%sp | stk adj - rte -.endm - -#define SWITCH_STACK_SIZE (6*4+4) /* includes return address */ - -#define SAVE_SWITCH_STACK save_switch_stack -#define RESTORE_SWITCH_STACK restore_switch_stack -#define GET_CURRENT(tmp) get_current tmp - -.macro save_switch_stack - moveml %a3-%a6/%d6-%d7,%sp@- -.endm - -.macro restore_switch_stack - moveml %sp@+,%a3-%a6/%d6-%d7 -.endm - -.macro get_current reg=%d0 - movel %sp,\reg - andw #-THREAD_SIZE,\reg - movel \reg,%curptr - movel %curptr@,%curptr -.endm - -#else /* C source */ - -#define STR(X) STR1(X) -#define STR1(X) #X - -#define SAVE_ALL_INT \ - "clrl %%sp@-;" /* stk_adj */ \ - "pea -1:w;" /* orig d0 = -1 */ \ - "movel %%d0,%%sp@-;" /* d0 */ \ - "moveml %%d1-%%d5/%%a0-%%a2,%%sp@-" -#define GET_CURRENT(tmp) \ - "movel %%sp,"#tmp"\n\t" \ - "andw #-"STR(THREAD_SIZE)","#tmp"\n\t" \ - "movel "#tmp",%%a2\n\t" \ - "movel %%a2@,%%a2" - -#endif - -#endif /* __M68K_ENTRY_H */ diff --git a/arch/m68k/include/asm/entry_no.h b/arch/m68k/include/asm/entry_no.h deleted file mode 100644 index 68611e3dbb1d..000000000000 --- a/arch/m68k/include/asm/entry_no.h +++ /dev/null @@ -1,181 +0,0 @@ -#ifndef __M68KNOMMU_ENTRY_H -#define __M68KNOMMU_ENTRY_H - -#include <asm/setup.h> -#include <asm/page.h> - -/* - * Stack layout in 'ret_from_exception': - * - * This allows access to the syscall arguments in registers d1-d5 - * - * 0(sp) - d1 - * 4(sp) - d2 - * 8(sp) - d3 - * C(sp) - d4 - * 10(sp) - d5 - * 14(sp) - a0 - * 18(sp) - a1 - * 1C(sp) - a2 - * 20(sp) - d0 - * 24(sp) - orig_d0 - * 28(sp) - stack adjustment - * 2C(sp) - [ sr ] [ format & vector ] - * 2E(sp) - [ pc-hiword ] [ sr ] - * 30(sp) - [ pc-loword ] [ pc-hiword ] - * 32(sp) - [ format & vector ] [ pc-loword ] - * ^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^ - * M68K COLDFIRE - */ - -#define ALLOWINT (~0x700) - -#ifdef __ASSEMBLY__ - -#define SWITCH_STACK_SIZE (6*4+4) /* Includes return address */ - -/* - * This defines the normal kernel pt-regs layout. - * - * regs are a2-a6 and d6-d7 preserved by C code - * the kernel doesn't mess with usp unless it needs to - */ - -#ifdef CONFIG_COLDFIRE -#ifdef CONFIG_COLDFIRE_SW_A7 -/* - * This is made a little more tricky on older ColdFires. There is no - * separate supervisor and user stack pointers. Need to artificially - * construct a usp in software... When doing this we need to disable - * interrupts, otherwise bad things will happen. - */ -.globl sw_usp -.globl sw_ksp - -.macro SAVE_ALL - move #0x2700,%sr /* disable intrs */ - btst #5,%sp@(2) /* from user? */ - bnes 6f /* no, skip */ - movel %sp,sw_usp /* save user sp */ - addql #8,sw_usp /* remove exception */ - movel sw_ksp,%sp /* kernel sp */ - subql #8,%sp /* room for exception */ - clrl %sp@- /* stkadj */ - movel %d0,%sp@- /* orig d0 */ - movel %d0,%sp@- /* d0 */ - lea %sp@(-32),%sp /* space for 8 regs */ - moveml %d1-%d5/%a0-%a2,%sp@ - movel sw_usp,%a0 /* get usp */ - movel %a0@-,%sp@(PT_OFF_PC) /* copy exception program counter */ - movel %a0@-,%sp@(PT_OFF_FORMATVEC)/*copy exception format/vector/sr */ - bra 7f - 6: - clrl %sp@- /* stkadj */ - movel %d0,%sp@- /* orig d0 */ - movel %d0,%sp@- /* d0 */ - lea %sp@(-32),%sp /* space for 8 regs */ - moveml %d1-%d5/%a0-%a2,%sp@ - 7: -.endm - -.macro RESTORE_USER - move #0x2700,%sr /* disable intrs */ - movel sw_usp,%a0 /* get usp */ - movel %sp@(PT_OFF_PC),%a0@- /* copy exception program counter */ - movel %sp@(PT_OFF_FORMATVEC),%a0@-/*copy exception format/vector/sr */ - moveml %sp@,%d1-%d5/%a0-%a2 - lea %sp@(32),%sp /* space for 8 regs */ - movel %sp@+,%d0 - addql #4,%sp /* orig d0 */ - addl %sp@+,%sp /* stkadj */ - addql #8,%sp /* remove exception */ - movel %sp,sw_ksp /* save ksp */ - subql #8,sw_usp /* set exception */ - movel sw_usp,%sp /* restore usp */ - rte -.endm - -.macro RDUSP - movel sw_usp,%a3 -.endm - -.macro WRUSP - movel %a3,sw_usp -.endm - -#else /* !CONFIG_COLDFIRE_SW_A7 */ -/* - * Modern ColdFire parts have separate supervisor and user stack - * pointers. Simple load and restore macros for this case. - */ -.macro SAVE_ALL - move #0x2700,%sr /* disable intrs */ - clrl %sp@- /* stkadj */ - movel %d0,%sp@- /* orig d0 */ - movel %d0,%sp@- /* d0 */ - lea %sp@(-32),%sp /* space for 8 regs */ - moveml %d1-%d5/%a0-%a2,%sp@ -.endm - -.macro RESTORE_USER - moveml %sp@,%d1-%d5/%a0-%a2 - lea %sp@(32),%sp /* space for 8 regs */ - movel %sp@+,%d0 - addql #4,%sp /* orig d0 */ - addl %sp@+,%sp /* stkadj */ - rte -.endm - -.macro RDUSP - /*move %usp,%a3*/ - .word 0x4e6b -.endm - -.macro WRUSP - /*move %a3,%usp*/ - .word 0x4e63 -.endm - -#endif /* !CONFIG_COLDFIRE_SW_A7 */ - -.macro SAVE_SWITCH_STACK - lea %sp@(-24),%sp /* 6 regs */ - moveml %a3-%a6/%d6-%d7,%sp@ -.endm - -.macro RESTORE_SWITCH_STACK - moveml %sp@,%a3-%a6/%d6-%d7 - lea %sp@(24),%sp /* 6 regs */ -.endm - -#else /* !CONFIG_COLDFIRE */ - -/* - * Standard 68k interrupt entry and exit macros. - */ -.macro SAVE_ALL - clrl %sp@- /* stkadj */ - movel %d0,%sp@- /* orig d0 */ - movel %d0,%sp@- /* d0 */ - moveml %d1-%d5/%a0-%a2,%sp@- -.endm - -.macro RESTORE_ALL - moveml %sp@+,%a0-%a2/%d1-%d5 - movel %sp@+,%d0 - addql #4,%sp /* orig d0 */ - addl %sp@+,%sp /* stkadj */ - rte -.endm - -.macro SAVE_SWITCH_STACK - moveml %a3-%a6/%d6-%d7,%sp@- -.endm - -.macro RESTORE_SWITCH_STACK - moveml %sp@+,%a3-%a6/%d6-%d7 -.endm - -#endif /* !COLDFIRE_SW_A7 */ -#endif /* __ASSEMBLY__ */ -#endif /* __M68KNOMMU_ENTRY_H */ diff --git a/arch/m68k/include/asm/m520xsim.h b/arch/m68k/include/asm/m520xsim.h index b6bf2c518bac..eda62de7e607 100644 --- a/arch/m68k/include/asm/m520xsim.h +++ b/arch/m68k/include/asm/m520xsim.h @@ -90,15 +90,13 @@ #define MCFGPIO_PDDR_FECH 0xFC0A4013 #define MCFGPIO_PDDR_FECL 0xFC0A4014 -#define MCFGPIO_PPDSDR_BUSCTL 0xFC0A401A -#define MCFGPIO_PPDSDR_BE 0xFC0A401B -#define MCFGPIO_PPDSDR_CS 0xFC0A401C -#define MCFGPIO_PPDSDR_FECI2C 0xFC0A401D -#define MCFGPIO_PPDSDR_QSPI 0xFC0A401E -#define MCFGPIO_PPDSDR_TIMER 0xFC0A401F -#define MCFGPIO_PPDSDR_UART 0xFC0A4021 -#define MCFGPIO_PPDSDR_FECH 0xFC0A4021 -#define MCFGPIO_PPDSDR_FECL 0xFC0A4022 +#define MCFGPIO_PPDSDR_CS 0xFC0A401A +#define MCFGPIO_PPDSDR_FECI2C 0xFC0A401B +#define MCFGPIO_PPDSDR_QSPI 0xFC0A401C +#define MCFGPIO_PPDSDR_TIMER 0xFC0A401D +#define MCFGPIO_PPDSDR_UART 0xFC0A401E +#define MCFGPIO_PPDSDR_FECH 0xFC0A401F +#define MCFGPIO_PPDSDR_FECL 0xFC0A4020 #define MCFGPIO_PCLRR_BUSCTL 0xFC0A4024 #define MCFGPIO_PCLRR_BE 0xFC0A4025 @@ -113,11 +111,11 @@ /* * Generic GPIO support */ -#define MCFGPIO_PODR MCFGPIO_PODR_BUSCTL -#define MCFGPIO_PDDR MCFGPIO_PDDR_BUSCTL -#define MCFGPIO_PPDR MCFGPIO_PPDSDR_BUSCTL -#define MCFGPIO_SETR MCFGPIO_PPDSDR_BUSCTL -#define MCFGPIO_CLRR MCFGPIO_PCLRR_BUSCTL +#define MCFGPIO_PODR MCFGPIO_PODR_CS +#define MCFGPIO_PDDR MCFGPIO_PDDR_CS +#define MCFGPIO_PPDR MCFGPIO_PPDSDR_CS +#define MCFGPIO_SETR MCFGPIO_PPDSDR_CS +#define MCFGPIO_CLRR MCFGPIO_PCLRR_CS #define MCFGPIO_PIN_MAX 80 #define MCFGPIO_IRQ_MAX 8 diff --git a/arch/m68k/include/asm/mcfqspi.h b/arch/m68k/include/asm/mcfqspi.h index 39d90d51111d..7fe631972f1f 100644 --- a/arch/m68k/include/asm/mcfqspi.h +++ b/arch/m68k/include/asm/mcfqspi.h @@ -24,9 +24,11 @@ #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) #define MCFQSPI_IOBASE (MCF_IPSBAR + 0x340) #elif defined(CONFIG_M5249) -#define MCFQSPI_IOBASE (MCF_MBAR + 0x300) -#elif defined(CONFIG_M520x) || defined(CONFIG_M532x) -#define MCFQSPI_IOBASE 0xFC058000 +#define MCFQSPI_IOBASE (MCF_MBAR + 0x300) +#elif defined(CONFIG_M520x) +#define MCFQSPI_IOBASE 0xFC05C000 +#elif defined(CONFIG_M532x) +#define MCFQSPI_IOBASE 0xFC058000 #endif #define MCFQSPI_IOSIZE 0x40 diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h index 90595721185f..a8d1c60eb9ce 100644 --- a/arch/m68k/include/asm/page_no.h +++ b/arch/m68k/include/asm/page_no.h @@ -5,6 +5,9 @@ extern unsigned long memory_start; extern unsigned long memory_end; +extern unsigned long _rambase; +extern unsigned long _ramstart; +extern unsigned long _ramend; #define get_user_page(vaddr) __get_free_page(GFP_KERNEL) #define free_user_page(page, addr) free_page(addr) diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index d8ef53ac03f9..568facf30276 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -135,6 +135,12 @@ do { \ wrusp(_usp); \ } while(0) +static inline int handle_kernel_fault(struct pt_regs *regs) +{ + /* Any fault in kernel is fatal on non-mmu */ + return 0; +} + #endif /* Forward declaration, a strange C thing */ diff --git a/arch/m68k/include/asm/sections.h b/arch/m68k/include/asm/sections.h index d64967ecfec6..5277e52715ec 100644 --- a/arch/m68k/include/asm/sections.h +++ b/arch/m68k/include/asm/sections.h @@ -3,4 +3,6 @@ #include <asm-generic/sections.h> +extern char _sbss[], _ebss[]; + #endif /* _ASM_M68K_SECTIONS_H */ diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile index c482ebc9dd54..e7f0f2e5ad44 100644 --- a/arch/m68k/kernel/Makefile +++ b/arch/m68k/kernel/Makefile @@ -1,5 +1,21 @@ -ifdef CONFIG_MMU -include arch/m68k/kernel/Makefile_mm -else -include arch/m68k/kernel/Makefile_no +# +# Makefile for the linux kernel. +# + +extra-$(CONFIG_MMU) := head.o +extra-$(CONFIG_SUN3) := sun3-head.o +extra-y += vmlinux.lds + +obj-y := entry.o m68k_ksyms.o module.o process.o ptrace.o setup.o signal.o \ + sys_m68k.o syscalltable.o time.o traps.o + +obj-$(CONFIG_MMU) += ints.o devres.o vectors.o +devres-$(CONFIG_MMU) = ../../../kernel/irq/devres.o + +ifndef CONFIG_MMU_SUN3 +obj-y += dma.o endif +ifndef CONFIG_MMU +obj-y += init_task.o irq.o +endif + diff --git a/arch/m68k/kernel/Makefile_mm b/arch/m68k/kernel/Makefile_mm deleted file mode 100644 index aced67804579..000000000000 --- a/arch/m68k/kernel/Makefile_mm +++ /dev/null @@ -1,17 +0,0 @@ -# -# Makefile for the linux kernel. -# - -ifndef CONFIG_SUN3 - extra-y := head.o -else - extra-y := sun3-head.o -endif -extra-y += vmlinux.lds - -obj-y := entry.o process.o traps.o ints.o signal.o ptrace.o module.o \ - sys_m68k.o time.o setup.o m68k_ksyms.o devres.o syscalltable.o - -devres-y = ../../../kernel/irq/devres.o - -obj-y$(CONFIG_MMU_SUN3) += dma.o # no, it's not a typo diff --git a/arch/m68k/kernel/Makefile_no b/arch/m68k/kernel/Makefile_no deleted file mode 100644 index 37c3fc074c0a..000000000000 --- a/arch/m68k/kernel/Makefile_no +++ /dev/null @@ -1,10 +0,0 @@ -# -# Makefile for arch/m68knommu/kernel. -# - -extra-y := vmlinux.lds - -obj-y += dma.o entry.o init_task.o irq.o m68k_ksyms.o process.o ptrace.o \ - setup.o signal.o syscalltable.o sys_m68k.o time.o traps.o - -obj-$(CONFIG_MODULES) += module.o diff --git a/arch/m68k/kernel/entry_no.S b/arch/m68k/kernel/entry_no.S index 5f0f6b598b5a..1b4289061a64 100644 --- a/arch/m68k/kernel/entry_no.S +++ b/arch/m68k/kernel/entry_no.S @@ -43,7 +43,7 @@ .globl sys_vfork ENTRY(buserr) - SAVE_ALL + SAVE_ALL_INT moveq #-1,%d0 movel %d0,%sp@(PT_OFF_ORIG_D0) movel %sp,%sp@- /* stack frame pointer argument */ @@ -52,7 +52,7 @@ ENTRY(buserr) jra ret_from_exception ENTRY(trap) - SAVE_ALL + SAVE_ALL_INT moveq #-1,%d0 movel %d0,%sp@(PT_OFF_ORIG_D0) movel %sp,%sp@- /* stack frame pointer argument */ @@ -64,7 +64,7 @@ ENTRY(trap) .globl dbginterrupt ENTRY(dbginterrupt) - SAVE_ALL + SAVE_ALL_INT moveq #-1,%d0 movel %d0,%sp@(PT_OFF_ORIG_D0) movel %sp,%sp@- /* stack frame pointer argument */ diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index 16b2de7f5101..2ed8c0fb1517 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -36,6 +36,7 @@ #include <asm/irq.h> #include <asm/machdep.h> #include <asm/pgtable.h> +#include <asm/sections.h> unsigned long memory_start; unsigned long memory_end; @@ -80,9 +81,6 @@ void (*mach_power_off)(void); #define CPU_INSTR_PER_JIFFY 16 #endif -extern int _stext, _etext, _sdata, _edata, _sbss, _ebss, _end; -extern int _ramstart, _ramend; - #if defined(CONFIG_UBOOT) /* * parse_uboot_commandline diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index c98add3f5f0f..89362f2bb56a 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -1,5 +1,1107 @@ -#ifdef CONFIG_MMU -#include "traps_mm.c" +/* + * linux/arch/m68k/kernel/traps.c + * + * Copyright (C) 1993, 1994 by Hamish Macdonald + * + * 68040 fixes by Michael Rausch + * 68040 fixes by Martin Apel + * 68040 fixes and writeback by Richard Zidlicky + * 68060 fixes by Roman Hodek + * 68060 fixes by Jesper Skov + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ + +/* + * Sets up all exception vectors + */ + +#include <linux/sched.h> +#include <linux/signal.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/user.h> +#include <linux/string.h> +#include <linux/linkage.h> +#include <linux/init.h> +#include <linux/ptrace.h> +#include <linux/kallsyms.h> + +#include <asm/setup.h> +#include <asm/fpu.h> +#include <asm/system.h> +#include <asm/uaccess.h> +#include <asm/traps.h> +#include <asm/pgalloc.h> +#include <asm/machdep.h> +#include <asm/siginfo.h> + + +static const char *vec_names[] = { + [VEC_RESETSP] = "RESET SP", + [VEC_RESETPC] = "RESET PC", + [VEC_BUSERR] = "BUS ERROR", + [VEC_ADDRERR] = "ADDRESS ERROR", + [VEC_ILLEGAL] = "ILLEGAL INSTRUCTION", + [VEC_ZERODIV] = "ZERO DIVIDE", + [VEC_CHK] = "CHK", + [VEC_TRAP] = "TRAPcc", + [VEC_PRIV] = "PRIVILEGE VIOLATION", + [VEC_TRACE] = "TRACE", + [VEC_LINE10] = "LINE 1010", + [VEC_LINE11] = "LINE 1111", + [VEC_RESV12] = "UNASSIGNED RESERVED 12", + [VEC_COPROC] = "COPROCESSOR PROTOCOL VIOLATION", + [VEC_FORMAT] = "FORMAT ERROR", + [VEC_UNINT] = "UNINITIALIZED INTERRUPT", + [VEC_RESV16] = "UNASSIGNED RESERVED 16", + [VEC_RESV17] = "UNASSIGNED RESERVED 17", + [VEC_RESV18] = "UNASSIGNED RESERVED 18", + [VEC_RESV19] = "UNASSIGNED RESERVED 19", + [VEC_RESV20] = "UNASSIGNED RESERVED 20", + [VEC_RESV21] = "UNASSIGNED RESERVED 21", + [VEC_RESV22] = "UNASSIGNED RESERVED 22", + [VEC_RESV23] = "UNASSIGNED RESERVED 23", + [VEC_SPUR] = "SPURIOUS INTERRUPT", + [VEC_INT1] = "LEVEL 1 INT", + [VEC_INT2] = "LEVEL 2 INT", + [VEC_INT3] = "LEVEL 3 INT", + [VEC_INT4] = "LEVEL 4 INT", + [VEC_INT5] = "LEVEL 5 INT", + [VEC_INT6] = "LEVEL 6 INT", + [VEC_INT7] = "LEVEL 7 INT", + [VEC_SYS] = "SYSCALL", + [VEC_TRAP1] = "TRAP #1", + [VEC_TRAP2] = "TRAP #2", + [VEC_TRAP3] = "TRAP #3", + [VEC_TRAP4] = "TRAP #4", + [VEC_TRAP5] = "TRAP #5", + [VEC_TRAP6] = "TRAP #6", + [VEC_TRAP7] = "TRAP #7", + [VEC_TRAP8] = "TRAP #8", + [VEC_TRAP9] = "TRAP #9", + [VEC_TRAP10] = "TRAP #10", + [VEC_TRAP11] = "TRAP #11", + [VEC_TRAP12] = "TRAP #12", + [VEC_TRAP13] = "TRAP #13", + [VEC_TRAP14] = "TRAP #14", + [VEC_TRAP15] = "TRAP #15", + [VEC_FPBRUC] = "FPCP BSUN", + [VEC_FPIR] = "FPCP INEXACT", + [VEC_FPDIVZ] = "FPCP DIV BY 0", + [VEC_FPUNDER] = "FPCP UNDERFLOW", + [VEC_FPOE] = "FPCP OPERAND ERROR", + [VEC_FPOVER] = "FPCP OVERFLOW", + [VEC_FPNAN] = "FPCP SNAN", + [VEC_FPUNSUP] = "FPCP UNSUPPORTED OPERATION", + [VEC_MMUCFG] = "MMU CONFIGURATION ERROR", + [VEC_MMUILL] = "MMU ILLEGAL OPERATION ERROR", + [VEC_MMUACC] = "MMU ACCESS LEVEL VIOLATION ERROR", + [VEC_RESV59] = "UNASSIGNED RESERVED 59", + [VEC_UNIMPEA] = "UNASSIGNED RESERVED 60", + [VEC_UNIMPII] = "UNASSIGNED RESERVED 61", + [VEC_RESV62] = "UNASSIGNED RESERVED 62", + [VEC_RESV63] = "UNASSIGNED RESERVED 63", +}; + +static const char *space_names[] = { + [0] = "Space 0", + [USER_DATA] = "User Data", + [USER_PROGRAM] = "User Program", +#ifndef CONFIG_SUN3 + [3] = "Space 3", #else -#include "traps_no.c" + [FC_CONTROL] = "Control", +#endif + [4] = "Space 4", + [SUPER_DATA] = "Super Data", + [SUPER_PROGRAM] = "Super Program", + [CPU_SPACE] = "CPU" +}; + +void die_if_kernel(char *,struct pt_regs *,int); +asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address, + unsigned long error_code); +int send_fault_sig(struct pt_regs *regs); + +asmlinkage void trap_c(struct frame *fp); + +#if defined (CONFIG_M68060) +static inline void access_error060 (struct frame *fp) +{ + unsigned long fslw = fp->un.fmt4.pc; /* is really FSLW for access error */ + +#ifdef DEBUG + printk("fslw=%#lx, fa=%#lx\n", fslw, fp->un.fmt4.effaddr); +#endif + + if (fslw & MMU060_BPE) { + /* branch prediction error -> clear branch cache */ + __asm__ __volatile__ ("movec %/cacr,%/d0\n\t" + "orl #0x00400000,%/d0\n\t" + "movec %/d0,%/cacr" + : : : "d0" ); + /* return if there's no other error */ + if (!(fslw & MMU060_ERR_BITS) && !(fslw & MMU060_SEE)) + return; + } + + if (fslw & (MMU060_DESC_ERR | MMU060_WP | MMU060_SP)) { + unsigned long errorcode; + unsigned long addr = fp->un.fmt4.effaddr; + + if (fslw & MMU060_MA) + addr = (addr + PAGE_SIZE - 1) & PAGE_MASK; + + errorcode = 1; + if (fslw & MMU060_DESC_ERR) { + __flush_tlb040_one(addr); + errorcode = 0; + } + if (fslw & MMU060_W) + errorcode |= 2; +#ifdef DEBUG + printk("errorcode = %d\n", errorcode ); +#endif + do_page_fault(&fp->ptregs, addr, errorcode); + } else if (fslw & (MMU060_SEE)){ + /* Software Emulation Error. + * fault during mem_read/mem_write in ifpsp060/os.S + */ + send_fault_sig(&fp->ptregs); + } else if (!(fslw & (MMU060_RE|MMU060_WE)) || + send_fault_sig(&fp->ptregs) > 0) { + printk("pc=%#lx, fa=%#lx\n", fp->ptregs.pc, fp->un.fmt4.effaddr); + printk( "68060 access error, fslw=%lx\n", fslw ); + trap_c( fp ); + } +} +#endif /* CONFIG_M68060 */ + +#if defined (CONFIG_M68040) +static inline unsigned long probe040(int iswrite, unsigned long addr, int wbs) +{ + unsigned long mmusr; + mm_segment_t old_fs = get_fs(); + + set_fs(MAKE_MM_SEG(wbs)); + + if (iswrite) + asm volatile (".chip 68040; ptestw (%0); .chip 68k" : : "a" (addr)); + else + asm volatile (".chip 68040; ptestr (%0); .chip 68k" : : "a" (addr)); + + asm volatile (".chip 68040; movec %%mmusr,%0; .chip 68k" : "=r" (mmusr)); + + set_fs(old_fs); + + return mmusr; +} + +static inline int do_040writeback1(unsigned short wbs, unsigned long wba, + unsigned long wbd) +{ + int res = 0; + mm_segment_t old_fs = get_fs(); + + /* set_fs can not be moved, otherwise put_user() may oops */ + set_fs(MAKE_MM_SEG(wbs)); + + switch (wbs & WBSIZ_040) { + case BA_SIZE_BYTE: + res = put_user(wbd & 0xff, (char __user *)wba); + break; + case BA_SIZE_WORD: + res = put_user(wbd & 0xffff, (short __user *)wba); + break; + case BA_SIZE_LONG: + res = put_user(wbd, (int __user *)wba); + break; + } + + /* set_fs can not be moved, otherwise put_user() may oops */ + set_fs(old_fs); + + +#ifdef DEBUG + printk("do_040writeback1, res=%d\n",res); +#endif + + return res; +} + +/* after an exception in a writeback the stack frame corresponding + * to that exception is discarded, set a few bits in the old frame + * to simulate what it should look like + */ +static inline void fix_xframe040(struct frame *fp, unsigned long wba, unsigned short wbs) +{ + fp->un.fmt7.faddr = wba; + fp->un.fmt7.ssw = wbs & 0xff; + if (wba != current->thread.faddr) + fp->un.fmt7.ssw |= MA_040; +} + +static inline void do_040writebacks(struct frame *fp) +{ + int res = 0; +#if 0 + if (fp->un.fmt7.wb1s & WBV_040) + printk("access_error040: cannot handle 1st writeback. oops.\n"); +#endif + + if ((fp->un.fmt7.wb2s & WBV_040) && + !(fp->un.fmt7.wb2s & WBTT_040)) { + res = do_040writeback1(fp->un.fmt7.wb2s, fp->un.fmt7.wb2a, + fp->un.fmt7.wb2d); + if (res) + fix_xframe040(fp, fp->un.fmt7.wb2a, fp->un.fmt7.wb2s); + else + fp->un.fmt7.wb2s = 0; + } + + /* do the 2nd wb only if the first one was successful (except for a kernel wb) */ + if (fp->un.fmt7.wb3s & WBV_040 && (!res || fp->un.fmt7.wb3s & 4)) { + res = do_040writeback1(fp->un.fmt7.wb3s, fp->un.fmt7.wb3a, + fp->un.fmt7.wb3d); + if (res) + { + fix_xframe040(fp, fp->un.fmt7.wb3a, fp->un.fmt7.wb3s); + + fp->un.fmt7.wb2s = fp->un.fmt7.wb3s; + fp->un.fmt7.wb3s &= (~WBV_040); + fp->un.fmt7.wb2a = fp->un.fmt7.wb3a; + fp->un.fmt7.wb2d = fp->un.fmt7.wb3d; + } + else + fp->un.fmt7.wb3s = 0; + } + + if (res) + send_fault_sig(&fp->ptregs); +} + +/* + * called from sigreturn(), must ensure userspace code didn't + * manipulate exception frame to circumvent protection, then complete + * pending writebacks + * we just clear TM2 to turn it into a userspace access + */ +asmlinkage void berr_040cleanup(struct frame *fp) +{ + fp->un.fmt7.wb2s &= ~4; + fp->un.fmt7.wb3s &= ~4; + + do_040writebacks(fp); +} + +static inline void access_error040(struct frame *fp) +{ + unsigned short ssw = fp->un.fmt7.ssw; + unsigned long mmusr; + +#ifdef DEBUG + printk("ssw=%#x, fa=%#lx\n", ssw, fp->un.fmt7.faddr); + printk("wb1s=%#x, wb2s=%#x, wb3s=%#x\n", fp->un.fmt7.wb1s, + fp->un.fmt7.wb2s, fp->un.fmt7.wb3s); + printk ("wb2a=%lx, wb3a=%lx, wb2d=%lx, wb3d=%lx\n", + fp->un.fmt7.wb2a, fp->un.fmt7.wb3a, + fp->un.fmt7.wb2d, fp->un.fmt7.wb3d); +#endif + + if (ssw & ATC_040) { + unsigned long addr = fp->un.fmt7.faddr; + unsigned long errorcode; + + /* + * The MMU status has to be determined AFTER the address + * has been corrected if there was a misaligned access (MA). + */ + if (ssw & MA_040) + addr = (addr + 7) & -8; + + /* MMU error, get the MMUSR info for this access */ + mmusr = probe040(!(ssw & RW_040), addr, ssw); +#ifdef DEBUG + printk("mmusr = %lx\n", mmusr); +#endif + errorcode = 1; + if (!(mmusr & MMU_R_040)) { + /* clear the invalid atc entry */ + __flush_tlb040_one(addr); + errorcode = 0; + } + + /* despite what documentation seems to say, RMW + * accesses have always both the LK and RW bits set */ + if (!(ssw & RW_040) || (ssw & LK_040)) + errorcode |= 2; + + if (do_page_fault(&fp->ptregs, addr, errorcode)) { +#ifdef DEBUG + printk("do_page_fault() !=0\n"); +#endif + if (user_mode(&fp->ptregs)){ + /* delay writebacks after signal delivery */ +#ifdef DEBUG + printk(".. was usermode - return\n"); +#endif + return; + } + /* disable writeback into user space from kernel + * (if do_page_fault didn't fix the mapping, + * the writeback won't do good) + */ +disable_wb: +#ifdef DEBUG + printk(".. disabling wb2\n"); +#endif + if (fp->un.fmt7.wb2a == fp->un.fmt7.faddr) + fp->un.fmt7.wb2s &= ~WBV_040; + if (fp->un.fmt7.wb3a == fp->un.fmt7.faddr) + fp->un.fmt7.wb3s &= ~WBV_040; + } + } else { + /* In case of a bus error we either kill the process or expect + * the kernel to catch the fault, which then is also responsible + * for cleaning up the mess. + */ + current->thread.signo = SIGBUS; + current->thread.faddr = fp->un.fmt7.faddr; + if (send_fault_sig(&fp->ptregs) >= 0) + printk("68040 bus error (ssw=%x, faddr=%lx)\n", ssw, + fp->un.fmt7.faddr); + goto disable_wb; + } + + do_040writebacks(fp); +} +#endif /* CONFIG_M68040 */ + +#if defined(CONFIG_SUN3) +#include <asm/sun3mmu.h> + +extern int mmu_emu_handle_fault (unsigned long, int, int); + +/* sun3 version of bus_error030 */ + +static inline void bus_error030 (struct frame *fp) +{ + unsigned char buserr_type = sun3_get_buserr (); + unsigned long addr, errorcode; + unsigned short ssw = fp->un.fmtb.ssw; + extern unsigned long _sun3_map_test_start, _sun3_map_test_end; + +#ifdef DEBUG + if (ssw & (FC | FB)) + printk ("Instruction fault at %#010lx\n", + ssw & FC ? + fp->ptregs.format == 0xa ? fp->ptregs.pc + 2 : fp->un.fmtb.baddr - 2 + : + fp->ptregs.format == 0xa ? fp->ptregs.pc + 4 : fp->un.fmtb.baddr); + if (ssw & DF) + printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n", + ssw & RW ? "read" : "write", + fp->un.fmtb.daddr, + space_names[ssw & DFC], fp->ptregs.pc); +#endif + + /* + * Check if this page should be demand-mapped. This needs to go before + * the testing for a bad kernel-space access (demand-mapping applies + * to kernel accesses too). + */ + + if ((ssw & DF) + && (buserr_type & (SUN3_BUSERR_PROTERR | SUN3_BUSERR_INVALID))) { + if (mmu_emu_handle_fault (fp->un.fmtb.daddr, ssw & RW, 0)) + return; + } + + /* Check for kernel-space pagefault (BAD). */ + if (fp->ptregs.sr & PS_S) { + /* kernel fault must be a data fault to user space */ + if (! ((ssw & DF) && ((ssw & DFC) == USER_DATA))) { + // try checking the kernel mappings before surrender + if (mmu_emu_handle_fault (fp->un.fmtb.daddr, ssw & RW, 1)) + return; + /* instruction fault or kernel data fault! */ + if (ssw & (FC | FB)) + printk ("Instruction fault at %#010lx\n", + fp->ptregs.pc); + if (ssw & DF) { + /* was this fault incurred testing bus mappings? */ + if((fp->ptregs.pc >= (unsigned long)&_sun3_map_test_start) && + (fp->ptregs.pc <= (unsigned long)&_sun3_map_test_end)) { + send_fault_sig(&fp->ptregs); + return; + } + + printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n", + ssw & RW ? "read" : "write", + fp->un.fmtb.daddr, + space_names[ssw & DFC], fp->ptregs.pc); + } + printk ("BAD KERNEL BUSERR\n"); + + die_if_kernel("Oops", &fp->ptregs,0); + force_sig(SIGKILL, current); + return; + } + } else { + /* user fault */ + if (!(ssw & (FC | FB)) && !(ssw & DF)) + /* not an instruction fault or data fault! BAD */ + panic ("USER BUSERR w/o instruction or data fault"); + } + + + /* First handle the data fault, if any. */ + if (ssw & DF) { + addr = fp->un.fmtb.daddr; + +// errorcode bit 0: 0 -> no page 1 -> protection fault +// errorcode bit 1: 0 -> read fault 1 -> write fault + +// (buserr_type & SUN3_BUSERR_PROTERR) -> protection fault +// (buserr_type & SUN3_BUSERR_INVALID) -> invalid page fault + + if (buserr_type & SUN3_BUSERR_PROTERR) + errorcode = 0x01; + else if (buserr_type & SUN3_BUSERR_INVALID) + errorcode = 0x00; + else { +#ifdef DEBUG + printk ("*** unexpected busfault type=%#04x\n", buserr_type); + printk ("invalid %s access at %#lx from pc %#lx\n", + !(ssw & RW) ? "write" : "read", addr, + fp->ptregs.pc); +#endif + die_if_kernel ("Oops", &fp->ptregs, buserr_type); + force_sig (SIGBUS, current); + return; + } + +//todo: wtf is RM bit? --m + if (!(ssw & RW) || ssw & RM) + errorcode |= 0x02; + + /* Handle page fault. */ + do_page_fault (&fp->ptregs, addr, errorcode); + + /* Retry the data fault now. */ + return; + } + + /* Now handle the instruction fault. */ + + /* Get the fault address. */ + if (fp->ptregs.format == 0xA) + addr = fp->ptregs.pc + 4; + else + addr = fp->un.fmtb.baddr; + if (ssw & FC) + addr -= 2; + + if (buserr_type & SUN3_BUSERR_INVALID) { + if (!mmu_emu_handle_fault (fp->un.fmtb.daddr, 1, 0)) + do_page_fault (&fp->ptregs, addr, 0); + } else { +#ifdef DEBUG + printk ("protection fault on insn access (segv).\n"); +#endif + force_sig (SIGSEGV, current); + } +} +#else +#if defined(CPU_M68020_OR_M68030) +static inline void bus_error030 (struct frame *fp) +{ + volatile unsigned short temp; + unsigned short mmusr; + unsigned long addr, errorcode; + unsigned short ssw = fp->un.fmtb.ssw; +#ifdef DEBUG + unsigned long desc; + + printk ("pid = %x ", current->pid); + printk ("SSW=%#06x ", ssw); + + if (ssw & (FC | FB)) + printk ("Instruction fault at %#010lx\n", + ssw & FC ? + fp->ptregs.format == 0xa ? fp->ptregs.pc + 2 : fp->un.fmtb.baddr - 2 + : + fp->ptregs.format == 0xa ? fp->ptregs.pc + 4 : fp->un.fmtb.baddr); + if (ssw & DF) + printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n", + ssw & RW ? "read" : "write", + fp->un.fmtb.daddr, + space_names[ssw & DFC], fp->ptregs.pc); +#endif + + /* ++andreas: If a data fault and an instruction fault happen + at the same time map in both pages. */ + + /* First handle the data fault, if any. */ + if (ssw & DF) { + addr = fp->un.fmtb.daddr; + +#ifdef DEBUG + asm volatile ("ptestr %3,%2@,#7,%0\n\t" + "pmove %%psr,%1@" + : "=a&" (desc) + : "a" (&temp), "a" (addr), "d" (ssw)); +#else + asm volatile ("ptestr %2,%1@,#7\n\t" + "pmove %%psr,%0@" + : : "a" (&temp), "a" (addr), "d" (ssw)); +#endif + mmusr = temp; + +#ifdef DEBUG + printk("mmusr is %#x for addr %#lx in task %p\n", + mmusr, addr, current); + printk("descriptor address is %#lx, contents %#lx\n", + __va(desc), *(unsigned long *)__va(desc)); +#endif + + errorcode = (mmusr & MMU_I) ? 0 : 1; + if (!(ssw & RW) || (ssw & RM)) + errorcode |= 2; + + if (mmusr & (MMU_I | MMU_WP)) { + if (ssw & 4) { + printk("Data %s fault at %#010lx in %s (pc=%#lx)\n", + ssw & RW ? "read" : "write", + fp->un.fmtb.daddr, + space_names[ssw & DFC], fp->ptregs.pc); + goto buserr; + } + /* Don't try to do anything further if an exception was + handled. */ + if (do_page_fault (&fp->ptregs, addr, errorcode) < 0) + return; + } else if (!(mmusr & MMU_I)) { + /* probably a 020 cas fault */ + if (!(ssw & RM) && send_fault_sig(&fp->ptregs) > 0) + printk("unexpected bus error (%#x,%#x)\n", ssw, mmusr); + } else if (mmusr & (MMU_B|MMU_L|MMU_S)) { + printk("invalid %s access at %#lx from pc %#lx\n", + !(ssw & RW) ? "write" : "read", addr, + fp->ptregs.pc); + die_if_kernel("Oops",&fp->ptregs,mmusr); + force_sig(SIGSEGV, current); + return; + } else { +#if 0 + static volatile long tlong; +#endif + + printk("weird %s access at %#lx from pc %#lx (ssw is %#x)\n", + !(ssw & RW) ? "write" : "read", addr, + fp->ptregs.pc, ssw); + asm volatile ("ptestr #1,%1@,#0\n\t" + "pmove %%psr,%0@" + : /* no outputs */ + : "a" (&temp), "a" (addr)); + mmusr = temp; + + printk ("level 0 mmusr is %#x\n", mmusr); +#if 0 + asm volatile ("pmove %%tt0,%0@" + : /* no outputs */ + : "a" (&tlong)); + printk("tt0 is %#lx, ", tlong); + asm volatile ("pmove %%tt1,%0@" + : /* no outputs */ + : "a" (&tlong)); + printk("tt1 is %#lx\n", tlong); +#endif +#ifdef DEBUG + printk("Unknown SIGSEGV - 1\n"); +#endif + die_if_kernel("Oops",&fp->ptregs,mmusr); + force_sig(SIGSEGV, current); + return; + } + + /* setup an ATC entry for the access about to be retried */ + if (!(ssw & RW) || (ssw & RM)) + asm volatile ("ploadw %1,%0@" : /* no outputs */ + : "a" (addr), "d" (ssw)); + else + asm volatile ("ploadr %1,%0@" : /* no outputs */ + : "a" (addr), "d" (ssw)); + } + + /* Now handle the instruction fault. */ + + if (!(ssw & (FC|FB))) + return; + + if (fp->ptregs.sr & PS_S) { + printk("Instruction fault at %#010lx\n", + fp->ptregs.pc); + buserr: + printk ("BAD KERNEL BUSERR\n"); + die_if_kernel("Oops",&fp->ptregs,0); + force_sig(SIGKILL, current); + return; + } + + /* get the fault address */ + if (fp->ptregs.format == 10) + addr = fp->ptregs.pc + 4; + else + addr = fp->un.fmtb.baddr; + if (ssw & FC) + addr -= 2; + + if ((ssw & DF) && ((addr ^ fp->un.fmtb.daddr) & PAGE_MASK) == 0) + /* Insn fault on same page as data fault. But we + should still create the ATC entry. */ + goto create_atc_entry; + +#ifdef DEBUG + asm volatile ("ptestr #1,%2@,#7,%0\n\t" + "pmove %%psr,%1@" + : "=a&" (desc) + : "a" (&temp), "a" (addr)); +#else + asm volatile ("ptestr #1,%1@,#7\n\t" + "pmove %%psr,%0@" + : : "a" (&temp), "a" (addr)); +#endif + mmusr = temp; + +#ifdef DEBUG + printk ("mmusr is %#x for addr %#lx in task %p\n", + mmusr, addr, current); + printk ("descriptor address is %#lx, contents %#lx\n", + __va(desc), *(unsigned long *)__va(desc)); +#endif + + if (mmusr & MMU_I) + do_page_fault (&fp->ptregs, addr, 0); + else if (mmusr & (MMU_B|MMU_L|MMU_S)) { + printk ("invalid insn access at %#lx from pc %#lx\n", + addr, fp->ptregs.pc); +#ifdef DEBUG + printk("Unknown SIGSEGV - 2\n"); +#endif + die_if_kernel("Oops",&fp->ptregs,mmusr); + force_sig(SIGSEGV, current); + return; + } + +create_atc_entry: + /* setup an ATC entry for the access about to be retried */ + asm volatile ("ploadr #2,%0@" : /* no outputs */ + : "a" (addr)); +} +#endif /* CPU_M68020_OR_M68030 */ +#endif /* !CONFIG_SUN3 */ + +asmlinkage void buserr_c(struct frame *fp) +{ + /* Only set esp0 if coming from user mode */ + if (user_mode(&fp->ptregs)) + current->thread.esp0 = (unsigned long) fp; + +#ifdef DEBUG + printk ("*** Bus Error *** Format is %x\n", fp->ptregs.format); +#endif + + switch (fp->ptregs.format) { +#if defined (CONFIG_M68060) + case 4: /* 68060 access error */ + access_error060 (fp); + break; +#endif +#if defined (CONFIG_M68040) + case 0x7: /* 68040 access error */ + access_error040 (fp); + break; +#endif +#if defined (CPU_M68020_OR_M68030) + case 0xa: + case 0xb: + bus_error030 (fp); + break; +#endif + default: + die_if_kernel("bad frame format",&fp->ptregs,0); +#ifdef DEBUG + printk("Unknown SIGSEGV - 4\n"); +#endif + force_sig(SIGSEGV, current); + } +} + + +static int kstack_depth_to_print = 48; + +void show_trace(unsigned long *stack) +{ + unsigned long *endstack; + unsigned long addr; + int i; + + printk("Call Trace:"); + addr = (unsigned long)stack + THREAD_SIZE - 1; + endstack = (unsigned long *)(addr & -THREAD_SIZE); + i = 0; + while (stack + 1 <= endstack) { + addr = *stack++; + /* + * If the address is either in the text segment of the + * kernel, or in the region which contains vmalloc'ed + * memory, it *may* be the address of a calling + * routine; if so, print it so that someone tracing + * down the cause of the crash will be able to figure + * out the call path that was taken. + */ + if (__kernel_text_address(addr)) { +#ifndef CONFIG_KALLSYMS + if (i % 5 == 0) + printk("\n "); +#endif + printk(" [<%08lx>] %pS\n", addr, (void *)addr); + i++; + } + } + printk("\n"); +} + +void show_registers(struct pt_regs *regs) +{ + struct frame *fp = (struct frame *)regs; + mm_segment_t old_fs = get_fs(); + u16 c, *cp; + unsigned long addr; + int i; + + print_modules(); + printk("PC: [<%08lx>] %pS\n", regs->pc, (void *)regs->pc); + printk("SR: %04x SP: %p a2: %08lx\n", regs->sr, regs, regs->a2); + printk("d0: %08lx d1: %08lx d2: %08lx d3: %08lx\n", + regs->d0, regs->d1, regs->d2, regs->d3); + printk("d4: %08lx d5: %08lx a0: %08lx a1: %08lx\n", + regs->d4, regs->d5, regs->a0, regs->a1); + + printk("Process %s (pid: %d, task=%p)\n", + current->comm, task_pid_nr(current), current); + addr = (unsigned long)&fp->un; + printk("Frame format=%X ", regs->format); + switch (regs->format) { + case 0x2: + printk("instr addr=%08lx\n", fp->un.fmt2.iaddr); + addr += sizeof(fp->un.fmt2); + break; + case 0x3: + printk("eff addr=%08lx\n", fp->un.fmt3.effaddr); + addr += sizeof(fp->un.fmt3); + break; + case 0x4: + printk((CPU_IS_060 ? "fault addr=%08lx fslw=%08lx\n" + : "eff addr=%08lx pc=%08lx\n"), + fp->un.fmt4.effaddr, fp->un.fmt4.pc); + addr += sizeof(fp->un.fmt4); + break; + case 0x7: + printk("eff addr=%08lx ssw=%04x faddr=%08lx\n", + fp->un.fmt7.effaddr, fp->un.fmt7.ssw, fp->un.fmt7.faddr); + printk("wb 1 stat/addr/data: %04x %08lx %08lx\n", + fp->un.fmt7.wb1s, fp->un.fmt7.wb1a, fp->un.fmt7.wb1dpd0); + printk("wb 2 stat/addr/data: %04x %08lx %08lx\n", + fp->un.fmt7.wb2s, fp->un.fmt7.wb2a, fp->un.fmt7.wb2d); + printk("wb 3 stat/addr/data: %04x %08lx %08lx\n", + fp->un.fmt7.wb3s, fp->un.fmt7.wb3a, fp->un.fmt7.wb3d); + printk("push data: %08lx %08lx %08lx %08lx\n", + fp->un.fmt7.wb1dpd0, fp->un.fmt7.pd1, fp->un.fmt7.pd2, + fp->un.fmt7.pd3); + addr += sizeof(fp->un.fmt7); + break; + case 0x9: + printk("instr addr=%08lx\n", fp->un.fmt9.iaddr); + addr += sizeof(fp->un.fmt9); + break; + case 0xa: + printk("ssw=%04x isc=%04x isb=%04x daddr=%08lx dobuf=%08lx\n", + fp->un.fmta.ssw, fp->un.fmta.isc, fp->un.fmta.isb, + fp->un.fmta.daddr, fp->un.fmta.dobuf); + addr += sizeof(fp->un.fmta); + break; + case 0xb: + printk("ssw=%04x isc=%04x isb=%04x daddr=%08lx dobuf=%08lx\n", + fp->un.fmtb.ssw, fp->un.fmtb.isc, fp->un.fmtb.isb, + fp->un.fmtb.daddr, fp->un.fmtb.dobuf); + printk("baddr=%08lx dibuf=%08lx ver=%x\n", + fp->un.fmtb.baddr, fp->un.fmtb.dibuf, fp->un.fmtb.ver); + addr += sizeof(fp->un.fmtb); + break; + default: + printk("\n"); + } + show_stack(NULL, (unsigned long *)addr); + + printk("Code:"); + set_fs(KERNEL_DS); + cp = (u16 *)regs->pc; + for (i = -8; i < 16; i++) { + if (get_user(c, cp + i) && i >= 0) { + printk(" Bad PC value."); + break; + } + printk(i ? " %04x" : " <%04x>", c); + } + set_fs(old_fs); + printk ("\n"); +} + +void show_stack(struct task_struct *task, unsigned long *stack) +{ + unsigned long *p; + unsigned long *endstack; + int i; + + if (!stack) { + if (task) + stack = (unsigned long *)task->thread.esp0; + else + stack = (unsigned long *)&stack; + } + endstack = (unsigned long *)(((unsigned long)stack + THREAD_SIZE - 1) & -THREAD_SIZE); + + printk("Stack from %08lx:", (unsigned long)stack); + p = stack; + for (i = 0; i < kstack_depth_to_print; i++) { + if (p + 1 > endstack) + break; + if (i % 8 == 0) + printk("\n "); + printk(" %08lx", *p++); + } + printk("\n"); + show_trace(stack); +} + +/* + * The architecture-independent backtrace generator + */ +void dump_stack(void) +{ + unsigned long stack; + + show_trace(&stack); +} + +EXPORT_SYMBOL(dump_stack); + +/* + * The vector number returned in the frame pointer may also contain + * the "fs" (Fault Status) bits on ColdFire. These are in the bottom + * 2 bits, and upper 2 bits. So we need to mask out the real vector + * number before using it in comparisons. You don't need to do this on + * real 68k parts, but it won't hurt either. + */ + +void bad_super_trap (struct frame *fp) +{ + int vector = (fp->ptregs.vector >> 2) & 0xff; + + console_verbose(); + if (vector < ARRAY_SIZE(vec_names)) + printk ("*** %s *** FORMAT=%X\n", + vec_names[vector], + fp->ptregs.format); + else + printk ("*** Exception %d *** FORMAT=%X\n", + vector, fp->ptregs.format); + if (vector == VEC_ADDRERR && CPU_IS_020_OR_030) { + unsigned short ssw = fp->un.fmtb.ssw; + + printk ("SSW=%#06x ", ssw); + + if (ssw & RC) + printk ("Pipe stage C instruction fault at %#010lx\n", + (fp->ptregs.format) == 0xA ? + fp->ptregs.pc + 2 : fp->un.fmtb.baddr - 2); + if (ssw & RB) + printk ("Pipe stage B instruction fault at %#010lx\n", + (fp->ptregs.format) == 0xA ? + fp->ptregs.pc + 4 : fp->un.fmtb.baddr); + if (ssw & DF) + printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n", + ssw & RW ? "read" : "write", + fp->un.fmtb.daddr, space_names[ssw & DFC], + fp->ptregs.pc); + } + printk ("Current process id is %d\n", task_pid_nr(current)); + die_if_kernel("BAD KERNEL TRAP", &fp->ptregs, 0); +} + +asmlinkage void trap_c(struct frame *fp) +{ + int sig; + int vector = (fp->ptregs.vector >> 2) & 0xff; + siginfo_t info; + + if (fp->ptregs.sr & PS_S) { + if (vector == VEC_TRACE) { + /* traced a trapping instruction on a 68020/30, + * real exception will be executed afterwards. + */ + } else if (!handle_kernel_fault(&fp->ptregs)) + bad_super_trap(fp); + return; + } + + /* send the appropriate signal to the user program */ + switch (vector) { + case VEC_ADDRERR: + info.si_code = BUS_ADRALN; + sig = SIGBUS; + break; + case VEC_ILLEGAL: + case VEC_LINE10: + case VEC_LINE11: + info.si_code = ILL_ILLOPC; + sig = SIGILL; + break; + case VEC_PRIV: + info.si_code = ILL_PRVOPC; + sig = SIGILL; + break; + case VEC_COPROC: + info.si_code = ILL_COPROC; + sig = SIGILL; + break; + case VEC_TRAP1: + case VEC_TRAP2: + case VEC_TRAP3: + case VEC_TRAP4: + case VEC_TRAP5: + case VEC_TRAP6: + case VEC_TRAP7: + case VEC_TRAP8: + case VEC_TRAP9: + case VEC_TRAP10: + case VEC_TRAP11: + case VEC_TRAP12: + case VEC_TRAP13: + case VEC_TRAP14: + info.si_code = ILL_ILLTRP; + sig = SIGILL; + break; + case VEC_FPBRUC: + case VEC_FPOE: + case VEC_FPNAN: + info.si_code = FPE_FLTINV; + sig = SIGFPE; + break; + case VEC_FPIR: + info.si_code = FPE_FLTRES; + sig = SIGFPE; + break; + case VEC_FPDIVZ: + info.si_code = FPE_FLTDIV; + sig = SIGFPE; + break; + case VEC_FPUNDER: + info.si_code = FPE_FLTUND; + sig = SIGFPE; + break; + case VEC_FPOVER: + info.si_code = FPE_FLTOVF; + sig = SIGFPE; + break; + case VEC_ZERODIV: + info.si_code = FPE_INTDIV; + sig = SIGFPE; + break; + case VEC_CHK: + case VEC_TRAP: + info.si_code = FPE_INTOVF; + sig = SIGFPE; + break; + case VEC_TRACE: /* ptrace single step */ + info.si_code = TRAP_TRACE; + sig = SIGTRAP; + break; + case VEC_TRAP15: /* breakpoint */ + info.si_code = TRAP_BRKPT; + sig = SIGTRAP; + break; + default: + info.si_code = ILL_ILLOPC; + sig = SIGILL; + break; + } + info.si_signo = sig; + info.si_errno = 0; + switch (fp->ptregs.format) { + default: + info.si_addr = (void *) fp->ptregs.pc; + break; + case 2: + info.si_addr = (void *) fp->un.fmt2.iaddr; + break; + case 7: + info.si_addr = (void *) fp->un.fmt7.effaddr; + break; + case 9: + info.si_addr = (void *) fp->un.fmt9.iaddr; + break; + case 10: + info.si_addr = (void *) fp->un.fmta.daddr; + break; + case 11: + info.si_addr = (void *) fp->un.fmtb.daddr; + break; + } + force_sig_info (sig, &info, current); +} + +void die_if_kernel (char *str, struct pt_regs *fp, int nr) +{ + if (!(fp->sr & PS_S)) + return; + + console_verbose(); + printk("%s: %08x\n",str,nr); + show_registers(fp); + add_taint(TAINT_DIE); + do_exit(SIGSEGV); +} + +asmlinkage void set_esp0(unsigned long ssp) +{ + current->thread.esp0 = ssp; +} + +/* + * This function is called if an error occur while accessing + * user-space from the fpsp040 code. + */ +asmlinkage void fpsp040_die(void) +{ + do_exit(SIGSEGV); +} + +#ifdef CONFIG_M68KFPU_EMU +asmlinkage void fpemu_signal(int signal, int code, void *addr) +{ + siginfo_t info; + + info.si_signo = signal; + info.si_errno = 0; + info.si_code = code; + info.si_addr = addr; + force_sig_info(signal, &info, current); +} #endif diff --git a/arch/m68k/kernel/traps_mm.c b/arch/m68k/kernel/traps_mm.c deleted file mode 100644 index 4022bbc28878..000000000000 --- a/arch/m68k/kernel/traps_mm.c +++ /dev/null @@ -1,1207 +0,0 @@ -/* - * linux/arch/m68k/kernel/traps.c - * - * Copyright (C) 1993, 1994 by Hamish Macdonald - * - * 68040 fixes by Michael Rausch - * 68040 fixes by Martin Apel - * 68040 fixes and writeback by Richard Zidlicky - * 68060 fixes by Roman Hodek - * 68060 fixes by Jesper Skov - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive - * for more details. - */ - -/* - * Sets up all exception vectors - */ - -#include <linux/sched.h> -#include <linux/signal.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/module.h> -#include <linux/user.h> -#include <linux/string.h> -#include <linux/linkage.h> -#include <linux/init.h> -#include <linux/ptrace.h> -#include <linux/kallsyms.h> - -#include <asm/setup.h> -#include <asm/fpu.h> -#include <asm/system.h> -#include <asm/uaccess.h> -#include <asm/traps.h> -#include <asm/pgalloc.h> -#include <asm/machdep.h> -#include <asm/siginfo.h> - -/* assembler routines */ -asmlinkage void system_call(void); -asmlinkage void buserr(void); -asmlinkage void trap(void); -asmlinkage void nmihandler(void); -#ifdef CONFIG_M68KFPU_EMU -asmlinkage void fpu_emu(void); -#endif - -e_vector vectors[256]; - -/* nmi handler for the Amiga */ -asm(".text\n" - __ALIGN_STR "\n" - "nmihandler: rte"); - -/* - * this must be called very early as the kernel might - * use some instruction that are emulated on the 060 - * and so we're prepared for early probe attempts (e.g. nf_init). - */ -void __init base_trap_init(void) -{ - if (MACH_IS_SUN3X) { - extern e_vector *sun3x_prom_vbr; - - __asm__ volatile ("movec %%vbr, %0" : "=r" (sun3x_prom_vbr)); - } - - /* setup the exception vector table */ - __asm__ volatile ("movec %0,%%vbr" : : "r" ((void*)vectors)); - - if (CPU_IS_060) { - /* set up ISP entry points */ - asmlinkage void unimp_vec(void) asm ("_060_isp_unimp"); - - vectors[VEC_UNIMPII] = unimp_vec; - } - - vectors[VEC_BUSERR] = buserr; - vectors[VEC_ILLEGAL] = trap; - vectors[VEC_SYS] = system_call; -} - -void __init trap_init (void) -{ - int i; - - for (i = VEC_SPUR; i <= VEC_INT7; i++) - vectors[i] = bad_inthandler; - - for (i = 0; i < VEC_USER; i++) - if (!vectors[i]) - vectors[i] = trap; - - for (i = VEC_USER; i < 256; i++) - vectors[i] = bad_inthandler; - -#ifdef CONFIG_M68KFPU_EMU - if (FPU_IS_EMU) - vectors[VEC_LINE11] = fpu_emu; -#endif - - if (CPU_IS_040 && !FPU_IS_EMU) { - /* set up FPSP entry points */ - asmlinkage void dz_vec(void) asm ("dz"); - asmlinkage void inex_vec(void) asm ("inex"); - asmlinkage void ovfl_vec(void) asm ("ovfl"); - asmlinkage void unfl_vec(void) asm ("unfl"); - asmlinkage void snan_vec(void) asm ("snan"); - asmlinkage void operr_vec(void) asm ("operr"); - asmlinkage void bsun_vec(void) asm ("bsun"); - asmlinkage void fline_vec(void) asm ("fline"); - asmlinkage void unsupp_vec(void) asm ("unsupp"); - - vectors[VEC_FPDIVZ] = dz_vec; - vectors[VEC_FPIR] = inex_vec; - vectors[VEC_FPOVER] = ovfl_vec; - vectors[VEC_FPUNDER] = unfl_vec; - vectors[VEC_FPNAN] = snan_vec; - vectors[VEC_FPOE] = operr_vec; - vectors[VEC_FPBRUC] = bsun_vec; - vectors[VEC_LINE11] = fline_vec; - vectors[VEC_FPUNSUP] = unsupp_vec; - } - - if (CPU_IS_060 && !FPU_IS_EMU) { - /* set up IFPSP entry points */ - asmlinkage void snan_vec6(void) asm ("_060_fpsp_snan"); - asmlinkage void operr_vec6(void) asm ("_060_fpsp_operr"); - asmlinkage void ovfl_vec6(void) asm ("_060_fpsp_ovfl"); - asmlinkage void unfl_vec6(void) asm ("_060_fpsp_unfl"); - asmlinkage void dz_vec6(void) asm ("_060_fpsp_dz"); - asmlinkage void inex_vec6(void) asm ("_060_fpsp_inex"); - asmlinkage void fline_vec6(void) asm ("_060_fpsp_fline"); - asmlinkage void unsupp_vec6(void) asm ("_060_fpsp_unsupp"); - asmlinkage void effadd_vec6(void) asm ("_060_fpsp_effadd"); - - vectors[VEC_FPNAN] = snan_vec6; - vectors[VEC_FPOE] = operr_vec6; - vectors[VEC_FPOVER] = ovfl_vec6; - vectors[VEC_FPUNDER] = unfl_vec6; - vectors[VEC_FPDIVZ] = dz_vec6; - vectors[VEC_FPIR] = inex_vec6; - vectors[VEC_LINE11] = fline_vec6; - vectors[VEC_FPUNSUP] = unsupp_vec6; - vectors[VEC_UNIMPEA] = effadd_vec6; - } - - /* if running on an amiga, make the NMI interrupt do nothing */ - if (MACH_IS_AMIGA) { - vectors[VEC_INT7] = nmihandler; - } -} - - -static const char *vec_names[] = { - [VEC_RESETSP] = "RESET SP", - [VEC_RESETPC] = "RESET PC", - [VEC_BUSERR] = "BUS ERROR", - [VEC_ADDRERR] = "ADDRESS ERROR", - [VEC_ILLEGAL] = "ILLEGAL INSTRUCTION", - [VEC_ZERODIV] = "ZERO DIVIDE", - [VEC_CHK] = "CHK", - [VEC_TRAP] = "TRAPcc", - [VEC_PRIV] = "PRIVILEGE VIOLATION", - [VEC_TRACE] = "TRACE", - [VEC_LINE10] = "LINE 1010", - [VEC_LINE11] = "LINE 1111", - [VEC_RESV12] = "UNASSIGNED RESERVED 12", - [VEC_COPROC] = "COPROCESSOR PROTOCOL VIOLATION", - [VEC_FORMAT] = "FORMAT ERROR", - [VEC_UNINT] = "UNINITIALIZED INTERRUPT", - [VEC_RESV16] = "UNASSIGNED RESERVED 16", - [VEC_RESV17] = "UNASSIGNED RESERVED 17", - [VEC_RESV18] = "UNASSIGNED RESERVED 18", - [VEC_RESV19] = "UNASSIGNED RESERVED 19", - [VEC_RESV20] = "UNASSIGNED RESERVED 20", - [VEC_RESV21] = "UNASSIGNED RESERVED 21", - [VEC_RESV22] = "UNASSIGNED RESERVED 22", - [VEC_RESV23] = "UNASSIGNED RESERVED 23", - [VEC_SPUR] = "SPURIOUS INTERRUPT", - [VEC_INT1] = "LEVEL 1 INT", - [VEC_INT2] = "LEVEL 2 INT", - [VEC_INT3] = "LEVEL 3 INT", - [VEC_INT4] = "LEVEL 4 INT", - [VEC_INT5] = "LEVEL 5 INT", - [VEC_INT6] = "LEVEL 6 INT", - [VEC_INT7] = "LEVEL 7 INT", - [VEC_SYS] = "SYSCALL", - [VEC_TRAP1] = "TRAP #1", - [VEC_TRAP2] = "TRAP #2", - [VEC_TRAP3] = "TRAP #3", - [VEC_TRAP4] = "TRAP #4", - [VEC_TRAP5] = "TRAP #5", - [VEC_TRAP6] = "TRAP #6", - [VEC_TRAP7] = "TRAP #7", - [VEC_TRAP8] = "TRAP #8", - [VEC_TRAP9] = "TRAP #9", - [VEC_TRAP10] = "TRAP #10", - [VEC_TRAP11] = "TRAP #11", - [VEC_TRAP12] = "TRAP #12", - [VEC_TRAP13] = "TRAP #13", - [VEC_TRAP14] = "TRAP #14", - [VEC_TRAP15] = "TRAP #15", - [VEC_FPBRUC] = "FPCP BSUN", - [VEC_FPIR] = "FPCP INEXACT", - [VEC_FPDIVZ] = "FPCP DIV BY 0", - [VEC_FPUNDER] = "FPCP UNDERFLOW", - [VEC_FPOE] = "FPCP OPERAND ERROR", - [VEC_FPOVER] = "FPCP OVERFLOW", - [VEC_FPNAN] = "FPCP SNAN", - [VEC_FPUNSUP] = "FPCP UNSUPPORTED OPERATION", - [VEC_MMUCFG] = "MMU CONFIGURATION ERROR", - [VEC_MMUILL] = "MMU ILLEGAL OPERATION ERROR", - [VEC_MMUACC] = "MMU ACCESS LEVEL VIOLATION ERROR", - [VEC_RESV59] = "UNASSIGNED RESERVED 59", - [VEC_UNIMPEA] = "UNASSIGNED RESERVED 60", - [VEC_UNIMPII] = "UNASSIGNED RESERVED 61", - [VEC_RESV62] = "UNASSIGNED RESERVED 62", - [VEC_RESV63] = "UNASSIGNED RESERVED 63", -}; - -static const char *space_names[] = { - [0] = "Space 0", - [USER_DATA] = "User Data", - [USER_PROGRAM] = "User Program", -#ifndef CONFIG_SUN3 - [3] = "Space 3", -#else - [FC_CONTROL] = "Control", -#endif - [4] = "Space 4", - [SUPER_DATA] = "Super Data", - [SUPER_PROGRAM] = "Super Program", - [CPU_SPACE] = "CPU" -}; - -void die_if_kernel(char *,struct pt_regs *,int); -asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address, - unsigned long error_code); -int send_fault_sig(struct pt_regs *regs); - -asmlinkage void trap_c(struct frame *fp); - -#if defined (CONFIG_M68060) -static inline void access_error060 (struct frame *fp) -{ - unsigned long fslw = fp->un.fmt4.pc; /* is really FSLW for access error */ - -#ifdef DEBUG - printk("fslw=%#lx, fa=%#lx\n", fslw, fp->un.fmt4.effaddr); -#endif - - if (fslw & MMU060_BPE) { - /* branch prediction error -> clear branch cache */ - __asm__ __volatile__ ("movec %/cacr,%/d0\n\t" - "orl #0x00400000,%/d0\n\t" - "movec %/d0,%/cacr" - : : : "d0" ); - /* return if there's no other error */ - if (!(fslw & MMU060_ERR_BITS) && !(fslw & MMU060_SEE)) - return; - } - - if (fslw & (MMU060_DESC_ERR | MMU060_WP | MMU060_SP)) { - unsigned long errorcode; - unsigned long addr = fp->un.fmt4.effaddr; - - if (fslw & MMU060_MA) - addr = (addr + PAGE_SIZE - 1) & PAGE_MASK; - - errorcode = 1; - if (fslw & MMU060_DESC_ERR) { - __flush_tlb040_one(addr); - errorcode = 0; - } - if (fslw & MMU060_W) - errorcode |= 2; -#ifdef DEBUG - printk("errorcode = %d\n", errorcode ); -#endif - do_page_fault(&fp->ptregs, addr, errorcode); - } else if (fslw & (MMU060_SEE)){ - /* Software Emulation Error. - * fault during mem_read/mem_write in ifpsp060/os.S - */ - send_fault_sig(&fp->ptregs); - } else if (!(fslw & (MMU060_RE|MMU060_WE)) || - send_fault_sig(&fp->ptregs) > 0) { - printk("pc=%#lx, fa=%#lx\n", fp->ptregs.pc, fp->un.fmt4.effaddr); - printk( "68060 access error, fslw=%lx\n", fslw ); - trap_c( fp ); - } -} -#endif /* CONFIG_M68060 */ - -#if defined (CONFIG_M68040) -static inline unsigned long probe040(int iswrite, unsigned long addr, int wbs) -{ - unsigned long mmusr; - mm_segment_t old_fs = get_fs(); - - set_fs(MAKE_MM_SEG(wbs)); - - if (iswrite) - asm volatile (".chip 68040; ptestw (%0); .chip 68k" : : "a" (addr)); - else - asm volatile (".chip 68040; ptestr (%0); .chip 68k" : : "a" (addr)); - - asm volatile (".chip 68040; movec %%mmusr,%0; .chip 68k" : "=r" (mmusr)); - - set_fs(old_fs); - - return mmusr; -} - -static inline int do_040writeback1(unsigned short wbs, unsigned long wba, - unsigned long wbd) -{ - int res = 0; - mm_segment_t old_fs = get_fs(); - - /* set_fs can not be moved, otherwise put_user() may oops */ - set_fs(MAKE_MM_SEG(wbs)); - - switch (wbs & WBSIZ_040) { - case BA_SIZE_BYTE: - res = put_user(wbd & 0xff, (char __user *)wba); - break; - case BA_SIZE_WORD: - res = put_user(wbd & 0xffff, (short __user *)wba); - break; - case BA_SIZE_LONG: - res = put_user(wbd, (int __user *)wba); - break; - } - - /* set_fs can not be moved, otherwise put_user() may oops */ - set_fs(old_fs); - - -#ifdef DEBUG - printk("do_040writeback1, res=%d\n",res); -#endif - - return res; -} - -/* after an exception in a writeback the stack frame corresponding - * to that exception is discarded, set a few bits in the old frame - * to simulate what it should look like - */ -static inline void fix_xframe040(struct frame *fp, unsigned long wba, unsigned short wbs) -{ - fp->un.fmt7.faddr = wba; - fp->un.fmt7.ssw = wbs & 0xff; - if (wba != current->thread.faddr) - fp->un.fmt7.ssw |= MA_040; -} - -static inline void do_040writebacks(struct frame *fp) -{ - int res = 0; -#if 0 - if (fp->un.fmt7.wb1s & WBV_040) - printk("access_error040: cannot handle 1st writeback. oops.\n"); -#endif - - if ((fp->un.fmt7.wb2s & WBV_040) && - !(fp->un.fmt7.wb2s & WBTT_040)) { - res = do_040writeback1(fp->un.fmt7.wb2s, fp->un.fmt7.wb2a, - fp->un.fmt7.wb2d); - if (res) - fix_xframe040(fp, fp->un.fmt7.wb2a, fp->un.fmt7.wb2s); - else - fp->un.fmt7.wb2s = 0; - } - - /* do the 2nd wb only if the first one was successful (except for a kernel wb) */ - if (fp->un.fmt7.wb3s & WBV_040 && (!res || fp->un.fmt7.wb3s & 4)) { - res = do_040writeback1(fp->un.fmt7.wb3s, fp->un.fmt7.wb3a, - fp->un.fmt7.wb3d); - if (res) - { - fix_xframe040(fp, fp->un.fmt7.wb3a, fp->un.fmt7.wb3s); - - fp->un.fmt7.wb2s = fp->un.fmt7.wb3s; - fp->un.fmt7.wb3s &= (~WBV_040); - fp->un.fmt7.wb2a = fp->un.fmt7.wb3a; - fp->un.fmt7.wb2d = fp->un.fmt7.wb3d; - } - else - fp->un.fmt7.wb3s = 0; - } - - if (res) - send_fault_sig(&fp->ptregs); -} - -/* - * called from sigreturn(), must ensure userspace code didn't - * manipulate exception frame to circumvent protection, then complete - * pending writebacks - * we just clear TM2 to turn it into a userspace access - */ -asmlinkage void berr_040cleanup(struct frame *fp) -{ - fp->un.fmt7.wb2s &= ~4; - fp->un.fmt7.wb3s &= ~4; - - do_040writebacks(fp); -} - -static inline void access_error040(struct frame *fp) -{ - unsigned short ssw = fp->un.fmt7.ssw; - unsigned long mmusr; - -#ifdef DEBUG - printk("ssw=%#x, fa=%#lx\n", ssw, fp->un.fmt7.faddr); - printk("wb1s=%#x, wb2s=%#x, wb3s=%#x\n", fp->un.fmt7.wb1s, - fp->un.fmt7.wb2s, fp->un.fmt7.wb3s); - printk ("wb2a=%lx, wb3a=%lx, wb2d=%lx, wb3d=%lx\n", - fp->un.fmt7.wb2a, fp->un.fmt7.wb3a, - fp->un.fmt7.wb2d, fp->un.fmt7.wb3d); -#endif - - if (ssw & ATC_040) { - unsigned long addr = fp->un.fmt7.faddr; - unsigned long errorcode; - - /* - * The MMU status has to be determined AFTER the address - * has been corrected if there was a misaligned access (MA). - */ - if (ssw & MA_040) - addr = (addr + 7) & -8; - - /* MMU error, get the MMUSR info for this access */ - mmusr = probe040(!(ssw & RW_040), addr, ssw); -#ifdef DEBUG - printk("mmusr = %lx\n", mmusr); -#endif - errorcode = 1; - if (!(mmusr & MMU_R_040)) { - /* clear the invalid atc entry */ - __flush_tlb040_one(addr); - errorcode = 0; - } - - /* despite what documentation seems to say, RMW - * accesses have always both the LK and RW bits set */ - if (!(ssw & RW_040) || (ssw & LK_040)) - errorcode |= 2; - - if (do_page_fault(&fp->ptregs, addr, errorcode)) { -#ifdef DEBUG - printk("do_page_fault() !=0\n"); -#endif - if (user_mode(&fp->ptregs)){ - /* delay writebacks after signal delivery */ -#ifdef DEBUG - printk(".. was usermode - return\n"); -#endif - return; - } - /* disable writeback into user space from kernel - * (if do_page_fault didn't fix the mapping, - * the writeback won't do good) - */ -disable_wb: -#ifdef DEBUG - printk(".. disabling wb2\n"); -#endif - if (fp->un.fmt7.wb2a == fp->un.fmt7.faddr) - fp->un.fmt7.wb2s &= ~WBV_040; - if (fp->un.fmt7.wb3a == fp->un.fmt7.faddr) - fp->un.fmt7.wb3s &= ~WBV_040; - } - } else { - /* In case of a bus error we either kill the process or expect - * the kernel to catch the fault, which then is also responsible - * for cleaning up the mess. - */ - current->thread.signo = SIGBUS; - current->thread.faddr = fp->un.fmt7.faddr; - if (send_fault_sig(&fp->ptregs) >= 0) - printk("68040 bus error (ssw=%x, faddr=%lx)\n", ssw, - fp->un.fmt7.faddr); - goto disable_wb; - } - - do_040writebacks(fp); -} -#endif /* CONFIG_M68040 */ - -#if defined(CONFIG_SUN3) -#include <asm/sun3mmu.h> - -extern int mmu_emu_handle_fault (unsigned long, int, int); - -/* sun3 version of bus_error030 */ - -static inline void bus_error030 (struct frame *fp) -{ - unsigned char buserr_type = sun3_get_buserr (); - unsigned long addr, errorcode; - unsigned short ssw = fp->un.fmtb.ssw; - extern unsigned long _sun3_map_test_start, _sun3_map_test_end; - -#ifdef DEBUG - if (ssw & (FC | FB)) - printk ("Instruction fault at %#010lx\n", - ssw & FC ? - fp->ptregs.format == 0xa ? fp->ptregs.pc + 2 : fp->un.fmtb.baddr - 2 - : - fp->ptregs.format == 0xa ? fp->ptregs.pc + 4 : fp->un.fmtb.baddr); - if (ssw & DF) - printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n", - ssw & RW ? "read" : "write", - fp->un.fmtb.daddr, - space_names[ssw & DFC], fp->ptregs.pc); -#endif - - /* - * Check if this page should be demand-mapped. This needs to go before - * the testing for a bad kernel-space access (demand-mapping applies - * to kernel accesses too). - */ - - if ((ssw & DF) - && (buserr_type & (SUN3_BUSERR_PROTERR | SUN3_BUSERR_INVALID))) { - if (mmu_emu_handle_fault (fp->un.fmtb.daddr, ssw & RW, 0)) - return; - } - - /* Check for kernel-space pagefault (BAD). */ - if (fp->ptregs.sr & PS_S) { - /* kernel fault must be a data fault to user space */ - if (! ((ssw & DF) && ((ssw & DFC) == USER_DATA))) { - // try checking the kernel mappings before surrender - if (mmu_emu_handle_fault (fp->un.fmtb.daddr, ssw & RW, 1)) - return; - /* instruction fault or kernel data fault! */ - if (ssw & (FC | FB)) - printk ("Instruction fault at %#010lx\n", - fp->ptregs.pc); - if (ssw & DF) { - /* was this fault incurred testing bus mappings? */ - if((fp->ptregs.pc >= (unsigned long)&_sun3_map_test_start) && - (fp->ptregs.pc <= (unsigned long)&_sun3_map_test_end)) { - send_fault_sig(&fp->ptregs); - return; - } - - printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n", - ssw & RW ? "read" : "write", - fp->un.fmtb.daddr, - space_names[ssw & DFC], fp->ptregs.pc); - } - printk ("BAD KERNEL BUSERR\n"); - - die_if_kernel("Oops", &fp->ptregs,0); - force_sig(SIGKILL, current); - return; - } - } else { - /* user fault */ - if (!(ssw & (FC | FB)) && !(ssw & DF)) - /* not an instruction fault or data fault! BAD */ - panic ("USER BUSERR w/o instruction or data fault"); - } - - - /* First handle the data fault, if any. */ - if (ssw & DF) { - addr = fp->un.fmtb.daddr; - -// errorcode bit 0: 0 -> no page 1 -> protection fault -// errorcode bit 1: 0 -> read fault 1 -> write fault - -// (buserr_type & SUN3_BUSERR_PROTERR) -> protection fault -// (buserr_type & SUN3_BUSERR_INVALID) -> invalid page fault - - if (buserr_type & SUN3_BUSERR_PROTERR) - errorcode = 0x01; - else if (buserr_type & SUN3_BUSERR_INVALID) - errorcode = 0x00; - else { -#ifdef DEBUG - printk ("*** unexpected busfault type=%#04x\n", buserr_type); - printk ("invalid %s access at %#lx from pc %#lx\n", - !(ssw & RW) ? "write" : "read", addr, - fp->ptregs.pc); -#endif - die_if_kernel ("Oops", &fp->ptregs, buserr_type); - force_sig (SIGBUS, current); - return; - } - -//todo: wtf is RM bit? --m - if (!(ssw & RW) || ssw & RM) - errorcode |= 0x02; - - /* Handle page fault. */ - do_page_fault (&fp->ptregs, addr, errorcode); - - /* Retry the data fault now. */ - return; - } - - /* Now handle the instruction fault. */ - - /* Get the fault address. */ - if (fp->ptregs.format == 0xA) - addr = fp->ptregs.pc + 4; - else - addr = fp->un.fmtb.baddr; - if (ssw & FC) - addr -= 2; - - if (buserr_type & SUN3_BUSERR_INVALID) { - if (!mmu_emu_handle_fault (fp->un.fmtb.daddr, 1, 0)) - do_page_fault (&fp->ptregs, addr, 0); - } else { -#ifdef DEBUG - printk ("protection fault on insn access (segv).\n"); -#endif - force_sig (SIGSEGV, current); - } -} -#else -#if defined(CPU_M68020_OR_M68030) -static inline void bus_error030 (struct frame *fp) -{ - volatile unsigned short temp; - unsigned short mmusr; - unsigned long addr, errorcode; - unsigned short ssw = fp->un.fmtb.ssw; -#ifdef DEBUG - unsigned long desc; - - printk ("pid = %x ", current->pid); - printk ("SSW=%#06x ", ssw); - - if (ssw & (FC | FB)) - printk ("Instruction fault at %#010lx\n", - ssw & FC ? - fp->ptregs.format == 0xa ? fp->ptregs.pc + 2 : fp->un.fmtb.baddr - 2 - : - fp->ptregs.format == 0xa ? fp->ptregs.pc + 4 : fp->un.fmtb.baddr); - if (ssw & DF) - printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n", - ssw & RW ? "read" : "write", - fp->un.fmtb.daddr, - space_names[ssw & DFC], fp->ptregs.pc); -#endif - - /* ++andreas: If a data fault and an instruction fault happen - at the same time map in both pages. */ - - /* First handle the data fault, if any. */ - if (ssw & DF) { - addr = fp->un.fmtb.daddr; - -#ifdef DEBUG - asm volatile ("ptestr %3,%2@,#7,%0\n\t" - "pmove %%psr,%1@" - : "=a&" (desc) - : "a" (&temp), "a" (addr), "d" (ssw)); -#else - asm volatile ("ptestr %2,%1@,#7\n\t" - "pmove %%psr,%0@" - : : "a" (&temp), "a" (addr), "d" (ssw)); -#endif - mmusr = temp; - -#ifdef DEBUG - printk("mmusr is %#x for addr %#lx in task %p\n", - mmusr, addr, current); - printk("descriptor address is %#lx, contents %#lx\n", - __va(desc), *(unsigned long *)__va(desc)); -#endif - - errorcode = (mmusr & MMU_I) ? 0 : 1; - if (!(ssw & RW) || (ssw & RM)) - errorcode |= 2; - - if (mmusr & (MMU_I | MMU_WP)) { - if (ssw & 4) { - printk("Data %s fault at %#010lx in %s (pc=%#lx)\n", - ssw & RW ? "read" : "write", - fp->un.fmtb.daddr, - space_names[ssw & DFC], fp->ptregs.pc); - goto buserr; - } - /* Don't try to do anything further if an exception was - handled. */ - if (do_page_fault (&fp->ptregs, addr, errorcode) < 0) - return; - } else if (!(mmusr & MMU_I)) { - /* probably a 020 cas fault */ - if (!(ssw & RM) && send_fault_sig(&fp->ptregs) > 0) - printk("unexpected bus error (%#x,%#x)\n", ssw, mmusr); - } else if (mmusr & (MMU_B|MMU_L|MMU_S)) { - printk("invalid %s access at %#lx from pc %#lx\n", - !(ssw & RW) ? "write" : "read", addr, - fp->ptregs.pc); - die_if_kernel("Oops",&fp->ptregs,mmusr); - force_sig(SIGSEGV, current); - return; - } else { -#if 0 - static volatile long tlong; -#endif - - printk("weird %s access at %#lx from pc %#lx (ssw is %#x)\n", - !(ssw & RW) ? "write" : "read", addr, - fp->ptregs.pc, ssw); - asm volatile ("ptestr #1,%1@,#0\n\t" - "pmove %%psr,%0@" - : /* no outputs */ - : "a" (&temp), "a" (addr)); - mmusr = temp; - - printk ("level 0 mmusr is %#x\n", mmusr); -#if 0 - asm volatile ("pmove %%tt0,%0@" - : /* no outputs */ - : "a" (&tlong)); - printk("tt0 is %#lx, ", tlong); - asm volatile ("pmove %%tt1,%0@" - : /* no outputs */ - : "a" (&tlong)); - printk("tt1 is %#lx\n", tlong); -#endif -#ifdef DEBUG - printk("Unknown SIGSEGV - 1\n"); -#endif - die_if_kernel("Oops",&fp->ptregs,mmusr); - force_sig(SIGSEGV, current); - return; - } - - /* setup an ATC entry for the access about to be retried */ - if (!(ssw & RW) || (ssw & RM)) - asm volatile ("ploadw %1,%0@" : /* no outputs */ - : "a" (addr), "d" (ssw)); - else - asm volatile ("ploadr %1,%0@" : /* no outputs */ - : "a" (addr), "d" (ssw)); - } - - /* Now handle the instruction fault. */ - - if (!(ssw & (FC|FB))) - return; - - if (fp->ptregs.sr & PS_S) { - printk("Instruction fault at %#010lx\n", - fp->ptregs.pc); - buserr: - printk ("BAD KERNEL BUSERR\n"); - die_if_kernel("Oops",&fp->ptregs,0); - force_sig(SIGKILL, current); - return; - } - - /* get the fault address */ - if (fp->ptregs.format == 10) - addr = fp->ptregs.pc + 4; - else - addr = fp->un.fmtb.baddr; - if (ssw & FC) - addr -= 2; - - if ((ssw & DF) && ((addr ^ fp->un.fmtb.daddr) & PAGE_MASK) == 0) - /* Insn fault on same page as data fault. But we - should still create the ATC entry. */ - goto create_atc_entry; - -#ifdef DEBUG - asm volatile ("ptestr #1,%2@,#7,%0\n\t" - "pmove %%psr,%1@" - : "=a&" (desc) - : "a" (&temp), "a" (addr)); -#else - asm volatile ("ptestr #1,%1@,#7\n\t" - "pmove %%psr,%0@" - : : "a" (&temp), "a" (addr)); -#endif - mmusr = temp; - -#ifdef DEBUG - printk ("mmusr is %#x for addr %#lx in task %p\n", - mmusr, addr, current); - printk ("descriptor address is %#lx, contents %#lx\n", - __va(desc), *(unsigned long *)__va(desc)); -#endif - - if (mmusr & MMU_I) - do_page_fault (&fp->ptregs, addr, 0); - else if (mmusr & (MMU_B|MMU_L|MMU_S)) { - printk ("invalid insn access at %#lx from pc %#lx\n", - addr, fp->ptregs.pc); -#ifdef DEBUG - printk("Unknown SIGSEGV - 2\n"); -#endif - die_if_kernel("Oops",&fp->ptregs,mmusr); - force_sig(SIGSEGV, current); - return; - } - -create_atc_entry: - /* setup an ATC entry for the access about to be retried */ - asm volatile ("ploadr #2,%0@" : /* no outputs */ - : "a" (addr)); -} -#endif /* CPU_M68020_OR_M68030 */ -#endif /* !CONFIG_SUN3 */ - -asmlinkage void buserr_c(struct frame *fp) -{ - /* Only set esp0 if coming from user mode */ - if (user_mode(&fp->ptregs)) - current->thread.esp0 = (unsigned long) fp; - -#ifdef DEBUG - printk ("*** Bus Error *** Format is %x\n", fp->ptregs.format); -#endif - - switch (fp->ptregs.format) { -#if defined (CONFIG_M68060) - case 4: /* 68060 access error */ - access_error060 (fp); - break; -#endif -#if defined (CONFIG_M68040) - case 0x7: /* 68040 access error */ - access_error040 (fp); - break; -#endif -#if defined (CPU_M68020_OR_M68030) - case 0xa: - case 0xb: - bus_error030 (fp); - break; -#endif - default: - die_if_kernel("bad frame format",&fp->ptregs,0); -#ifdef DEBUG - printk("Unknown SIGSEGV - 4\n"); -#endif - force_sig(SIGSEGV, current); - } -} - - -static int kstack_depth_to_print = 48; - -void show_trace(unsigned long *stack) -{ - unsigned long *endstack; - unsigned long addr; - int i; - - printk("Call Trace:"); - addr = (unsigned long)stack + THREAD_SIZE - 1; - endstack = (unsigned long *)(addr & -THREAD_SIZE); - i = 0; - while (stack + 1 <= endstack) { - addr = *stack++; - /* - * If the address is either in the text segment of the - * kernel, or in the region which contains vmalloc'ed - * memory, it *may* be the address of a calling - * routine; if so, print it so that someone tracing - * down the cause of the crash will be able to figure - * out the call path that was taken. - */ - if (__kernel_text_address(addr)) { -#ifndef CONFIG_KALLSYMS - if (i % 5 == 0) - printk("\n "); -#endif - printk(" [<%08lx>] %pS\n", addr, (void *)addr); - i++; - } - } - printk("\n"); -} - -void show_registers(struct pt_regs *regs) -{ - struct frame *fp = (struct frame *)regs; - mm_segment_t old_fs = get_fs(); - u16 c, *cp; - unsigned long addr; - int i; - - print_modules(); - printk("PC: [<%08lx>] %pS\n", regs->pc, (void *)regs->pc); - printk("SR: %04x SP: %p a2: %08lx\n", regs->sr, regs, regs->a2); - printk("d0: %08lx d1: %08lx d2: %08lx d3: %08lx\n", - regs->d0, regs->d1, regs->d2, regs->d3); - printk("d4: %08lx d5: %08lx a0: %08lx a1: %08lx\n", - regs->d4, regs->d5, regs->a0, regs->a1); - - printk("Process %s (pid: %d, task=%p)\n", - current->comm, task_pid_nr(current), current); - addr = (unsigned long)&fp->un; - printk("Frame format=%X ", regs->format); - switch (regs->format) { - case 0x2: - printk("instr addr=%08lx\n", fp->un.fmt2.iaddr); - addr += sizeof(fp->un.fmt2); - break; - case 0x3: - printk("eff addr=%08lx\n", fp->un.fmt3.effaddr); - addr += sizeof(fp->un.fmt3); - break; - case 0x4: - printk((CPU_IS_060 ? "fault addr=%08lx fslw=%08lx\n" - : "eff addr=%08lx pc=%08lx\n"), - fp->un.fmt4.effaddr, fp->un.fmt4.pc); - addr += sizeof(fp->un.fmt4); - break; - case 0x7: - printk("eff addr=%08lx ssw=%04x faddr=%08lx\n", - fp->un.fmt7.effaddr, fp->un.fmt7.ssw, fp->un.fmt7.faddr); - printk("wb 1 stat/addr/data: %04x %08lx %08lx\n", - fp->un.fmt7.wb1s, fp->un.fmt7.wb1a, fp->un.fmt7.wb1dpd0); - printk("wb 2 stat/addr/data: %04x %08lx %08lx\n", - fp->un.fmt7.wb2s, fp->un.fmt7.wb2a, fp->un.fmt7.wb2d); - printk("wb 3 stat/addr/data: %04x %08lx %08lx\n", - fp->un.fmt7.wb3s, fp->un.fmt7.wb3a, fp->un.fmt7.wb3d); - printk("push data: %08lx %08lx %08lx %08lx\n", - fp->un.fmt7.wb1dpd0, fp->un.fmt7.pd1, fp->un.fmt7.pd2, - fp->un.fmt7.pd3); - addr += sizeof(fp->un.fmt7); - break; - case 0x9: - printk("instr addr=%08lx\n", fp->un.fmt9.iaddr); - addr += sizeof(fp->un.fmt9); - break; - case 0xa: - printk("ssw=%04x isc=%04x isb=%04x daddr=%08lx dobuf=%08lx\n", - fp->un.fmta.ssw, fp->un.fmta.isc, fp->un.fmta.isb, - fp->un.fmta.daddr, fp->un.fmta.dobuf); - addr += sizeof(fp->un.fmta); - break; - case 0xb: - printk("ssw=%04x isc=%04x isb=%04x daddr=%08lx dobuf=%08lx\n", - fp->un.fmtb.ssw, fp->un.fmtb.isc, fp->un.fmtb.isb, - fp->un.fmtb.daddr, fp->un.fmtb.dobuf); - printk("baddr=%08lx dibuf=%08lx ver=%x\n", - fp->un.fmtb.baddr, fp->un.fmtb.dibuf, fp->un.fmtb.ver); - addr += sizeof(fp->un.fmtb); - break; - default: - printk("\n"); - } - show_stack(NULL, (unsigned long *)addr); - - printk("Code:"); - set_fs(KERNEL_DS); - cp = (u16 *)regs->pc; - for (i = -8; i < 16; i++) { - if (get_user(c, cp + i) && i >= 0) { - printk(" Bad PC value."); - break; - } - printk(i ? " %04x" : " <%04x>", c); - } - set_fs(old_fs); - printk ("\n"); -} - -void show_stack(struct task_struct *task, unsigned long *stack) -{ - unsigned long *p; - unsigned long *endstack; - int i; - - if (!stack) { - if (task) - stack = (unsigned long *)task->thread.esp0; - else - stack = (unsigned long *)&stack; - } - endstack = (unsigned long *)(((unsigned long)stack + THREAD_SIZE - 1) & -THREAD_SIZE); - - printk("Stack from %08lx:", (unsigned long)stack); - p = stack; - for (i = 0; i < kstack_depth_to_print; i++) { - if (p + 1 > endstack) - break; - if (i % 8 == 0) - printk("\n "); - printk(" %08lx", *p++); - } - printk("\n"); - show_trace(stack); -} - -/* - * The architecture-independent backtrace generator - */ -void dump_stack(void) -{ - unsigned long stack; - - show_trace(&stack); -} - -EXPORT_SYMBOL(dump_stack); - -void bad_super_trap (struct frame *fp) -{ - console_verbose(); - if (fp->ptregs.vector < 4 * ARRAY_SIZE(vec_names)) - printk ("*** %s *** FORMAT=%X\n", - vec_names[(fp->ptregs.vector) >> 2], - fp->ptregs.format); - else - printk ("*** Exception %d *** FORMAT=%X\n", - (fp->ptregs.vector) >> 2, - fp->ptregs.format); - if (fp->ptregs.vector >> 2 == VEC_ADDRERR && CPU_IS_020_OR_030) { - unsigned short ssw = fp->un.fmtb.ssw; - - printk ("SSW=%#06x ", ssw); - - if (ssw & RC) - printk ("Pipe stage C instruction fault at %#010lx\n", - (fp->ptregs.format) == 0xA ? - fp->ptregs.pc + 2 : fp->un.fmtb.baddr - 2); - if (ssw & RB) - printk ("Pipe stage B instruction fault at %#010lx\n", - (fp->ptregs.format) == 0xA ? - fp->ptregs.pc + 4 : fp->un.fmtb.baddr); - if (ssw & DF) - printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n", - ssw & RW ? "read" : "write", - fp->un.fmtb.daddr, space_names[ssw & DFC], - fp->ptregs.pc); - } - printk ("Current process id is %d\n", task_pid_nr(current)); - die_if_kernel("BAD KERNEL TRAP", &fp->ptregs, 0); -} - -asmlinkage void trap_c(struct frame *fp) -{ - int sig; - siginfo_t info; - - if (fp->ptregs.sr & PS_S) { - if (fp->ptregs.vector == VEC_TRACE << 2) { - /* traced a trapping instruction on a 68020/30, - * real exception will be executed afterwards. - */ - } else if (!handle_kernel_fault(&fp->ptregs)) - bad_super_trap(fp); - return; - } - - /* send the appropriate signal to the user program */ - switch ((fp->ptregs.vector) >> 2) { - case VEC_ADDRERR: - info.si_code = BUS_ADRALN; - sig = SIGBUS; - break; - case VEC_ILLEGAL: - case VEC_LINE10: - case VEC_LINE11: - info.si_code = ILL_ILLOPC; - sig = SIGILL; - break; - case VEC_PRIV: - info.si_code = ILL_PRVOPC; - sig = SIGILL; - break; - case VEC_COPROC: - info.si_code = ILL_COPROC; - sig = SIGILL; - break; - case VEC_TRAP1: - case VEC_TRAP2: - case VEC_TRAP3: - case VEC_TRAP4: - case VEC_TRAP5: - case VEC_TRAP6: - case VEC_TRAP7: - case VEC_TRAP8: - case VEC_TRAP9: - case VEC_TRAP10: - case VEC_TRAP11: - case VEC_TRAP12: - case VEC_TRAP13: - case VEC_TRAP14: - info.si_code = ILL_ILLTRP; - sig = SIGILL; - break; - case VEC_FPBRUC: - case VEC_FPOE: - case VEC_FPNAN: - info.si_code = FPE_FLTINV; - sig = SIGFPE; - break; - case VEC_FPIR: - info.si_code = FPE_FLTRES; - sig = SIGFPE; - break; - case VEC_FPDIVZ: - info.si_code = FPE_FLTDIV; - sig = SIGFPE; - break; - case VEC_FPUNDER: - info.si_code = FPE_FLTUND; - sig = SIGFPE; - break; - case VEC_FPOVER: - info.si_code = FPE_FLTOVF; - sig = SIGFPE; - break; - case VEC_ZERODIV: - info.si_code = FPE_INTDIV; - sig = SIGFPE; - break; - case VEC_CHK: - case VEC_TRAP: - info.si_code = FPE_INTOVF; - sig = SIGFPE; - break; - case VEC_TRACE: /* ptrace single step */ - info.si_code = TRAP_TRACE; - sig = SIGTRAP; - break; - case VEC_TRAP15: /* breakpoint */ - info.si_code = TRAP_BRKPT; - sig = SIGTRAP; - break; - default: - info.si_code = ILL_ILLOPC; - sig = SIGILL; - break; - } - info.si_signo = sig; - info.si_errno = 0; - switch (fp->ptregs.format) { - default: - info.si_addr = (void *) fp->ptregs.pc; - break; - case 2: - info.si_addr = (void *) fp->un.fmt2.iaddr; - break; - case 7: - info.si_addr = (void *) fp->un.fmt7.effaddr; - break; - case 9: - info.si_addr = (void *) fp->un.fmt9.iaddr; - break; - case 10: - info.si_addr = (void *) fp->un.fmta.daddr; - break; - case 11: - info.si_addr = (void *) fp->un.fmtb.daddr; - break; - } - force_sig_info (sig, &info, current); -} - -void die_if_kernel (char *str, struct pt_regs *fp, int nr) -{ - if (!(fp->sr & PS_S)) - return; - - console_verbose(); - printk("%s: %08x\n",str,nr); - show_registers(fp); - add_taint(TAINT_DIE); - do_exit(SIGSEGV); -} - -/* - * This function is called if an error occur while accessing - * user-space from the fpsp040 code. - */ -asmlinkage void fpsp040_die(void) -{ - do_exit(SIGSEGV); -} - -#ifdef CONFIG_M68KFPU_EMU -asmlinkage void fpemu_signal(int signal, int code, void *addr) -{ - siginfo_t info; - - info.si_signo = signal; - info.si_errno = 0; - info.si_code = code; - info.si_addr = addr; - force_sig_info(signal, &info, current); -} -#endif diff --git a/arch/m68k/kernel/traps_no.c b/arch/m68k/kernel/traps_no.c deleted file mode 100644 index e67b8c806959..000000000000 --- a/arch/m68k/kernel/traps_no.c +++ /dev/null @@ -1,361 +0,0 @@ -/* - * linux/arch/m68knommu/kernel/traps.c - * - * Copyright (C) 1993, 1994 by Hamish Macdonald - * - * 68040 fixes by Michael Rausch - * 68040 fixes by Martin Apel - * 68060 fixes by Roman Hodek - * 68060 fixes by Jesper Skov - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive - * for more details. - */ - -/* - * Sets up all exception vectors - */ -#include <linux/sched.h> -#include <linux/signal.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/module.h> -#include <linux/types.h> -#include <linux/user.h> -#include <linux/string.h> -#include <linux/linkage.h> -#include <linux/init.h> -#include <linux/ptrace.h> -#include <linux/kallsyms.h> - -#include <asm/setup.h> -#include <asm/fpu.h> -#include <asm/system.h> -#include <asm/uaccess.h> -#include <asm/traps.h> -#include <asm/pgtable.h> -#include <asm/machdep.h> -#include <asm/siginfo.h> - -static char const * const vec_names[] = { - "RESET SP", "RESET PC", "BUS ERROR", "ADDRESS ERROR", - "ILLEGAL INSTRUCTION", "ZERO DIVIDE", "CHK", "TRAPcc", - "PRIVILEGE VIOLATION", "TRACE", "LINE 1010", "LINE 1111", - "UNASSIGNED RESERVED 12", "COPROCESSOR PROTOCOL VIOLATION", - "FORMAT ERROR", "UNINITIALIZED INTERRUPT", - "UNASSIGNED RESERVED 16", "UNASSIGNED RESERVED 17", - "UNASSIGNED RESERVED 18", "UNASSIGNED RESERVED 19", - "UNASSIGNED RESERVED 20", "UNASSIGNED RESERVED 21", - "UNASSIGNED RESERVED 22", "UNASSIGNED RESERVED 23", - "SPURIOUS INTERRUPT", "LEVEL 1 INT", "LEVEL 2 INT", "LEVEL 3 INT", - "LEVEL 4 INT", "LEVEL 5 INT", "LEVEL 6 INT", "LEVEL 7 INT", - "SYSCALL", "TRAP #1", "TRAP #2", "TRAP #3", - "TRAP #4", "TRAP #5", "TRAP #6", "TRAP #7", - "TRAP #8", "TRAP #9", "TRAP #10", "TRAP #11", - "TRAP #12", "TRAP #13", "TRAP #14", "TRAP #15", - "FPCP BSUN", "FPCP INEXACT", "FPCP DIV BY 0", "FPCP UNDERFLOW", - "FPCP OPERAND ERROR", "FPCP OVERFLOW", "FPCP SNAN", - "FPCP UNSUPPORTED OPERATION", - "MMU CONFIGURATION ERROR" -}; - -void die_if_kernel(char *str, struct pt_regs *fp, int nr) -{ - if (!(fp->sr & PS_S)) - return; - - console_verbose(); - printk(KERN_EMERG "%s: %08x\n",str,nr); - printk(KERN_EMERG "PC: [<%08lx>]\nSR: %04x SP: %p a2: %08lx\n", - fp->pc, fp->sr, fp, fp->a2); - printk(KERN_EMERG "d0: %08lx d1: %08lx d2: %08lx d3: %08lx\n", - fp->d0, fp->d1, fp->d2, fp->d3); - printk(KERN_EMERG "d4: %08lx d5: %08lx a0: %08lx a1: %08lx\n", - fp->d4, fp->d5, fp->a0, fp->a1); - - printk(KERN_EMERG "Process %s (pid: %d, stackpage=%08lx)\n", - current->comm, current->pid, PAGE_SIZE+(unsigned long)current); - show_stack(NULL, (unsigned long *)(fp + 1)); - add_taint(TAINT_DIE); - do_exit(SIGSEGV); -} - -asmlinkage void buserr_c(struct frame *fp) -{ - /* Only set esp0 if coming from user mode */ - if (user_mode(&fp->ptregs)) - current->thread.esp0 = (unsigned long) fp; - -#if defined(DEBUG) - printk (KERN_DEBUG "*** Bus Error *** Format is %x\n", fp->ptregs.format); -#endif - - die_if_kernel("bad frame format",&fp->ptregs,0); -#if defined(DEBUG) - printk(KERN_DEBUG "Unknown SIGSEGV - 4\n"); -#endif - force_sig(SIGSEGV, current); -} - -static void print_this_address(unsigned long addr, int i) -{ -#ifdef CONFIG_KALLSYMS - printk(KERN_EMERG " [%08lx] ", addr); - print_symbol(KERN_CONT "%s\n", addr); -#else - if (i % 5) - printk(KERN_CONT " [%08lx] ", addr); - else - printk(KERN_EMERG " [%08lx] ", addr); - i++; -#endif -} - -int kstack_depth_to_print = 48; - -static void __show_stack(struct task_struct *task, unsigned long *stack) -{ - unsigned long *endstack, addr; -#ifdef CONFIG_FRAME_POINTER - unsigned long *last_stack; -#endif - int i; - - if (!stack) - stack = (unsigned long *)task->thread.ksp; - - addr = (unsigned long) stack; - endstack = (unsigned long *) PAGE_ALIGN(addr); - - printk(KERN_EMERG "Stack from %08lx:", (unsigned long)stack); - for (i = 0; i < kstack_depth_to_print; i++) { - if (stack + 1 + i > endstack) - break; - if (i % 8 == 0) - printk(KERN_EMERG " "); - printk(KERN_CONT " %08lx", *(stack + i)); - } - printk("\n"); - i = 0; - -#ifdef CONFIG_FRAME_POINTER - printk(KERN_EMERG "Call Trace:\n"); - - last_stack = stack - 1; - while (stack <= endstack && stack > last_stack) { - - addr = *(stack + 1); - print_this_address(addr, i); - i++; - - last_stack = stack; - stack = (unsigned long *)*stack; - } - printk("\n"); -#else - printk(KERN_EMERG "Call Trace with CONFIG_FRAME_POINTER disabled:\n"); - while (stack <= endstack) { - addr = *stack++; - /* - * If the address is either in the text segment of the kernel, - * or in a region which is occupied by a module then it *may* - * be the address of a calling routine; if so, print it so that - * someone tracing down the cause of the crash will be able to - * figure out the call path that was taken. - */ - if (__kernel_text_address(addr)) { - print_this_address(addr, i); - i++; - } - } - printk(KERN_CONT "\n"); -#endif -} - -void bad_super_trap(struct frame *fp) -{ - int vector = (fp->ptregs.vector >> 2) & 0xff; - - console_verbose(); - if (vector < ARRAY_SIZE(vec_names)) - printk (KERN_WARNING "*** %s *** FORMAT=%X\n", - vec_names[vector], - fp->ptregs.format); - else - printk (KERN_WARNING "*** Exception %d *** FORMAT=%X\n", - vector, - fp->ptregs.format); - printk (KERN_WARNING "Current process id is %d\n", current->pid); - die_if_kernel("BAD KERNEL TRAP", &fp->ptregs, 0); -} - -asmlinkage void trap_c(struct frame *fp) -{ - int sig; - int vector = (fp->ptregs.vector >> 2) & 0xff; - siginfo_t info; - - if (fp->ptregs.sr & PS_S) { - if (vector == VEC_TRACE) { - /* traced a trapping instruction */ - } else - bad_super_trap(fp); - return; - } - - /* send the appropriate signal to the user program */ - switch (vector) { - case VEC_ADDRERR: - info.si_code = BUS_ADRALN; - sig = SIGBUS; - break; - case VEC_ILLEGAL: - case VEC_LINE10: - case VEC_LINE11: - info.si_code = ILL_ILLOPC; - sig = SIGILL; - break; - case VEC_PRIV: - info.si_code = ILL_PRVOPC; - sig = SIGILL; - break; - case VEC_COPROC: - info.si_code = ILL_COPROC; - sig = SIGILL; - break; - case VEC_TRAP1: /* gdbserver breakpoint */ - fp->ptregs.pc -= 2; - info.si_code = TRAP_TRACE; - sig = SIGTRAP; - break; - case VEC_TRAP2: - case VEC_TRAP3: - case VEC_TRAP4: - case VEC_TRAP5: - case VEC_TRAP6: - case VEC_TRAP7: - case VEC_TRAP8: - case VEC_TRAP9: - case VEC_TRAP10: - case VEC_TRAP11: - case VEC_TRAP12: - case VEC_TRAP13: - case VEC_TRAP14: - info.si_code = ILL_ILLTRP; - sig = SIGILL; - break; - case VEC_FPBRUC: - case VEC_FPOE: - case VEC_FPNAN: - info.si_code = FPE_FLTINV; - sig = SIGFPE; - break; - case VEC_FPIR: - info.si_code = FPE_FLTRES; - sig = SIGFPE; - break; - case VEC_FPDIVZ: - info.si_code = FPE_FLTDIV; - sig = SIGFPE; - break; - case VEC_FPUNDER: - info.si_code = FPE_FLTUND; - sig = SIGFPE; - break; - case VEC_FPOVER: - info.si_code = FPE_FLTOVF; - sig = SIGFPE; - break; - case VEC_ZERODIV: - info.si_code = FPE_INTDIV; - sig = SIGFPE; - break; - case VEC_CHK: - case VEC_TRAP: - info.si_code = FPE_INTOVF; - sig = SIGFPE; - break; - case VEC_TRACE: /* ptrace single step */ - info.si_code = TRAP_TRACE; - sig = SIGTRAP; - break; - case VEC_TRAP15: /* breakpoint */ - info.si_code = TRAP_BRKPT; - sig = SIGTRAP; - break; - default: - info.si_code = ILL_ILLOPC; - sig = SIGILL; - break; - } - info.si_signo = sig; - info.si_errno = 0; - switch (fp->ptregs.format) { - default: - info.si_addr = (void *) fp->ptregs.pc; - break; - case 2: - info.si_addr = (void *) fp->un.fmt2.iaddr; - break; - case 7: - info.si_addr = (void *) fp->un.fmt7.effaddr; - break; - case 9: - info.si_addr = (void *) fp->un.fmt9.iaddr; - break; - case 10: - info.si_addr = (void *) fp->un.fmta.daddr; - break; - case 11: - info.si_addr = (void *) fp->un.fmtb.daddr; - break; - } - force_sig_info (sig, &info, current); -} - -asmlinkage void set_esp0(unsigned long ssp) -{ - current->thread.esp0 = ssp; -} - -/* - * The architecture-independent backtrace generator - */ -void dump_stack(void) -{ - /* - * We need frame pointers for this little trick, which works as follows: - * - * +------------+ 0x00 - * | Next SP | -> 0x0c - * +------------+ 0x04 - * | Caller | - * +------------+ 0x08 - * | Local vars | -> our stack var - * +------------+ 0x0c - * | Next SP | -> 0x18, that is what we pass to show_stack() - * +------------+ 0x10 - * | Caller | - * +------------+ 0x14 - * | Local vars | - * +------------+ 0x18 - * | ... | - * +------------+ - */ - - unsigned long *stack; - - stack = (unsigned long *)&stack; - stack++; - __show_stack(current, stack); -} -EXPORT_SYMBOL(dump_stack); - -void show_stack(struct task_struct *task, unsigned long *stack) -{ - if (!stack && !task) - dump_stack(); - else - __show_stack(task, stack); -} diff --git a/arch/m68k/kernel/vectors.c b/arch/m68k/kernel/vectors.c new file mode 100644 index 000000000000..147b03fbc71e --- /dev/null +++ b/arch/m68k/kernel/vectors.c @@ -0,0 +1,145 @@ +/* + * vectors.c + * + * Copyright (C) 1993, 1994 by Hamish Macdonald + * + * 68040 fixes by Michael Rausch + * 68040 fixes by Martin Apel + * 68040 fixes and writeback by Richard Zidlicky + * 68060 fixes by Roman Hodek + * 68060 fixes by Jesper Skov + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ + +/* + * Sets up all exception vectors + */ +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/linkage.h> +#include <linux/init.h> +#include <linux/kallsyms.h> + +#include <asm/setup.h> +#include <asm/fpu.h> +#include <asm/system.h> +#include <asm/traps.h> + +/* assembler routines */ +asmlinkage void system_call(void); +asmlinkage void buserr(void); +asmlinkage void trap(void); +asmlinkage void nmihandler(void); +#ifdef CONFIG_M68KFPU_EMU +asmlinkage void fpu_emu(void); +#endif + +e_vector vectors[256]; + +/* nmi handler for the Amiga */ +asm(".text\n" + __ALIGN_STR "\n" + "nmihandler: rte"); + +/* + * this must be called very early as the kernel might + * use some instruction that are emulated on the 060 + * and so we're prepared for early probe attempts (e.g. nf_init). + */ +void __init base_trap_init(void) +{ + if (MACH_IS_SUN3X) { + extern e_vector *sun3x_prom_vbr; + + __asm__ volatile ("movec %%vbr, %0" : "=r" (sun3x_prom_vbr)); + } + + /* setup the exception vector table */ + __asm__ volatile ("movec %0,%%vbr" : : "r" ((void*)vectors)); + + if (CPU_IS_060) { + /* set up ISP entry points */ + asmlinkage void unimp_vec(void) asm ("_060_isp_unimp"); + + vectors[VEC_UNIMPII] = unimp_vec; + } + + vectors[VEC_BUSERR] = buserr; + vectors[VEC_ILLEGAL] = trap; + vectors[VEC_SYS] = system_call; +} + +void __init trap_init (void) +{ + int i; + + for (i = VEC_SPUR; i <= VEC_INT7; i++) + vectors[i] = bad_inthandler; + + for (i = 0; i < VEC_USER; i++) + if (!vectors[i]) + vectors[i] = trap; + + for (i = VEC_USER; i < 256; i++) + vectors[i] = bad_inthandler; + +#ifdef CONFIG_M68KFPU_EMU + if (FPU_IS_EMU) + vectors[VEC_LINE11] = fpu_emu; +#endif + + if (CPU_IS_040 && !FPU_IS_EMU) { + /* set up FPSP entry points */ + asmlinkage void dz_vec(void) asm ("dz"); + asmlinkage void inex_vec(void) asm ("inex"); + asmlinkage void ovfl_vec(void) asm ("ovfl"); + asmlinkage void unfl_vec(void) asm ("unfl"); + asmlinkage void snan_vec(void) asm ("snan"); + asmlinkage void operr_vec(void) asm ("operr"); + asmlinkage void bsun_vec(void) asm ("bsun"); + asmlinkage void fline_vec(void) asm ("fline"); + asmlinkage void unsupp_vec(void) asm ("unsupp"); + + vectors[VEC_FPDIVZ] = dz_vec; + vectors[VEC_FPIR] = inex_vec; + vectors[VEC_FPOVER] = ovfl_vec; + vectors[VEC_FPUNDER] = unfl_vec; + vectors[VEC_FPNAN] = snan_vec; + vectors[VEC_FPOE] = operr_vec; + vectors[VEC_FPBRUC] = bsun_vec; + vectors[VEC_LINE11] = fline_vec; + vectors[VEC_FPUNSUP] = unsupp_vec; + } + + if (CPU_IS_060 && !FPU_IS_EMU) { + /* set up IFPSP entry points */ + asmlinkage void snan_vec6(void) asm ("_060_fpsp_snan"); + asmlinkage void operr_vec6(void) asm ("_060_fpsp_operr"); + asmlinkage void ovfl_vec6(void) asm ("_060_fpsp_ovfl"); + asmlinkage void unfl_vec6(void) asm ("_060_fpsp_unfl"); + asmlinkage void dz_vec6(void) asm ("_060_fpsp_dz"); + asmlinkage void inex_vec6(void) asm ("_060_fpsp_inex"); + asmlinkage void fline_vec6(void) asm ("_060_fpsp_fline"); + asmlinkage void unsupp_vec6(void) asm ("_060_fpsp_unsupp"); + asmlinkage void effadd_vec6(void) asm ("_060_fpsp_effadd"); + + vectors[VEC_FPNAN] = snan_vec6; + vectors[VEC_FPOE] = operr_vec6; + vectors[VEC_FPOVER] = ovfl_vec6; + vectors[VEC_FPUNDER] = unfl_vec6; + vectors[VEC_FPDIVZ] = dz_vec6; + vectors[VEC_FPIR] = inex_vec6; + vectors[VEC_LINE11] = fline_vec6; + vectors[VEC_FPUNSUP] = unsupp_vec6; + vectors[VEC_UNIMPEA] = effadd_vec6; + } + + /* if running on an amiga, make the NMI interrupt do nothing */ + if (MACH_IS_AMIGA) { + vectors[VEC_INT7] = nmihandler; + } +} + diff --git a/arch/m68k/kernel/vmlinux.lds_no.S b/arch/m68k/kernel/vmlinux.lds_no.S index 7dc4087a9545..4e2389340837 100644 --- a/arch/m68k/kernel/vmlinux.lds_no.S +++ b/arch/m68k/kernel/vmlinux.lds_no.S @@ -77,7 +77,6 @@ SECTIONS { *(.rodata) *(.rodata.*) *(__vermagic) /* Kernel version magic */ - *(__markers_strings) *(.rodata1) *(.rodata.str1.1) diff --git a/arch/m68k/lib/memcpy.c b/arch/m68k/lib/memcpy.c index 064889316974..10ca051d56b8 100644 --- a/arch/m68k/lib/memcpy.c +++ b/arch/m68k/lib/memcpy.c @@ -22,6 +22,15 @@ void *memcpy(void *to, const void *from, size_t n) from = cfrom; n--; } +#if defined(CONFIG_M68000) + if ((long)from & 1) { + char *cto = to; + const char *cfrom = from; + for (; n; n--) + *cto++ = *cfrom++; + return xto; + } +#endif if (n > 2 && (long)to & 2) { short *sto = to; const short *sfrom = from; diff --git a/arch/m68k/mac/macints.c b/arch/m68k/mac/macints.c index 900d899f3323..f92190c159b4 100644 --- a/arch/m68k/mac/macints.c +++ b/arch/m68k/mac/macints.c @@ -370,7 +370,7 @@ int mac_irq_pending(unsigned int irq) break; case 4: if (psc_present) - psc_irq_pending(irq); + return psc_irq_pending(irq); break; } return 0; diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index e023fc6b37e5..eb915551de69 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -304,35 +304,41 @@ static void via_write_pram(int offset, __u8 data) static long via_read_time(void) { union { - __u8 cdata[4]; - long idata; + __u8 cdata[4]; + long idata; } result, last_result; - int ct; + int count = 1; + + via_pram_command(0x81, &last_result.cdata[3]); + via_pram_command(0x85, &last_result.cdata[2]); + via_pram_command(0x89, &last_result.cdata[1]); + via_pram_command(0x8D, &last_result.cdata[0]); /* * The NetBSD guys say to loop until you get the same reading * twice in a row. */ - ct = 0; - do { - if (++ct > 10) { - printk("via_read_time: couldn't get valid time, " - "last read = 0x%08lx and 0x%08lx\n", - last_result.idata, result.idata); - break; - } - - last_result.idata = result.idata; - result.idata = 0; - + while (1) { via_pram_command(0x81, &result.cdata[3]); via_pram_command(0x85, &result.cdata[2]); via_pram_command(0x89, &result.cdata[1]); via_pram_command(0x8D, &result.cdata[0]); - } while (result.idata != last_result.idata); - return result.idata - RTC_OFFSET; + if (result.idata == last_result.idata) + return result.idata - RTC_OFFSET; + + if (++count > 10) + break; + + last_result.idata = result.idata; + } + + pr_err("via_read_time: failed to read a stable value; " + "got 0x%08lx then 0x%08lx\n", + last_result.idata, result.idata); + + return 0; } /* diff --git a/arch/m68k/mm/init_no.c b/arch/m68k/mm/init_no.c index 50cd12cf28d9..1e33d39ca9a0 100644 --- a/arch/m68k/mm/init_no.c +++ b/arch/m68k/mm/init_no.c @@ -32,6 +32,7 @@ #include <linux/gfp.h> #include <asm/setup.h> +#include <asm/sections.h> #include <asm/segment.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -44,9 +45,6 @@ */ void *empty_zero_page; -extern unsigned long memory_start; -extern unsigned long memory_end; - /* * paging_init() continues the virtual memory environment setup which * was begun by the code in arch/head.S. @@ -78,8 +76,6 @@ void __init mem_init(void) { int codek = 0, datak = 0, initk = 0; unsigned long tmp; - extern char _etext, _stext, _sdata, _ebss, __init_begin, __init_end; - extern unsigned int _ramend, _rambase; unsigned long len = _ramend - _rambase; unsigned long start_mem = memory_start; /* DAVIDM - these must start at end of kernel */ unsigned long end_mem = memory_end; /* DAVIDM - this must not include kernel stack at top */ @@ -95,9 +91,9 @@ void __init mem_init(void) /* this will put all memory onto the freelists */ totalram_pages = free_all_bootmem(); - codek = (&_etext - &_stext) >> 10; - datak = (&_ebss - &_sdata) >> 10; - initk = (&__init_begin - &__init_end) >> 10; + codek = (_etext - _stext) >> 10; + datak = (_ebss - _sdata) >> 10; + initk = (__init_begin - __init_end) >> 10; tmp = nr_free_pages() << PAGE_SHIFT; printk(KERN_INFO "Memory available: %luk/%luk RAM, (%dk kernel code, %dk data)\n", @@ -129,22 +125,21 @@ void free_initmem(void) { #ifdef CONFIG_RAMKERNEL unsigned long addr; - extern char __init_begin, __init_end; /* * The following code should be cool even if these sections * are not page aligned. */ - addr = PAGE_ALIGN((unsigned long)(&__init_begin)); + addr = PAGE_ALIGN((unsigned long) __init_begin); /* next to check that the page we free is not a partial page */ - for (; addr + PAGE_SIZE < (unsigned long)(&__init_end); addr +=PAGE_SIZE) { + for (; addr + PAGE_SIZE < ((unsigned long) __init_end); addr += PAGE_SIZE) { ClearPageReserved(virt_to_page(addr)); init_page_count(virt_to_page(addr)); free_page(addr); totalram_pages++; } pr_notice("Freeing unused kernel memory: %luk freed (0x%x - 0x%x)\n", - (addr - PAGE_ALIGN((long) &__init_begin)) >> 10, - (int)(PAGE_ALIGN((unsigned long)(&__init_begin))), + (addr - PAGE_ALIGN((unsigned long) __init_begin)) >> 10, + (int)(PAGE_ALIGN((unsigned long) __init_begin)), (int)(addr - PAGE_SIZE)); #endif } diff --git a/arch/m68k/platform/520x/config.c b/arch/m68k/platform/520x/config.c index 621238f1a219..8a98683f1b15 100644 --- a/arch/m68k/platform/520x/config.c +++ b/arch/m68k/platform/520x/config.c @@ -91,9 +91,9 @@ static struct resource m520x_qspi_resources[] = { }, }; -#define MCFQSPI_CS0 62 -#define MCFQSPI_CS1 63 -#define MCFQSPI_CS2 44 +#define MCFQSPI_CS0 46 +#define MCFQSPI_CS1 47 +#define MCFQSPI_CS2 27 static int m520x_cs_setup(struct mcfqspi_cs_control *cs_control) { diff --git a/arch/m68k/platform/520x/gpio.c b/arch/m68k/platform/520x/gpio.c index d757328563d1..9bcc3e4b60c5 100644 --- a/arch/m68k/platform/520x/gpio.c +++ b/arch/m68k/platform/520x/gpio.c @@ -38,42 +38,6 @@ static struct mcf_gpio_chip mcf_gpio_chips[] = { }, { .gpio_chip = { - .label = "BUSCTL", - .request = mcf_gpio_request, - .free = mcf_gpio_free, - .direction_input = mcf_gpio_direction_input, - .direction_output = mcf_gpio_direction_output, - .get = mcf_gpio_get_value, - .set = mcf_gpio_set_value_fast, - .base = 8, - .ngpio = 4, - }, - .pddr = (void __iomem *) MCFGPIO_PDDR_BUSCTL, - .podr = (void __iomem *) MCFGPIO_PODR_BUSCTL, - .ppdr = (void __iomem *) MCFGPIO_PPDSDR_BUSCTL, - .setr = (void __iomem *) MCFGPIO_PPDSDR_BUSCTL, - .clrr = (void __iomem *) MCFGPIO_PCLRR_BUSCTL, - }, - { - .gpio_chip = { - .label = "BE", - .request = mcf_gpio_request, - .free = mcf_gpio_free, - .direction_input = mcf_gpio_direction_input, - .direction_output = mcf_gpio_direction_output, - .get = mcf_gpio_get_value, - .set = mcf_gpio_set_value_fast, - .base = 16, - .ngpio = 4, - }, - .pddr = (void __iomem *) MCFGPIO_PDDR_BE, - .podr = (void __iomem *) MCFGPIO_PODR_BE, - .ppdr = (void __iomem *) MCFGPIO_PPDSDR_BE, - .setr = (void __iomem *) MCFGPIO_PPDSDR_BE, - .clrr = (void __iomem *) MCFGPIO_PCLRR_BE, - }, - { - .gpio_chip = { .label = "CS", .request = mcf_gpio_request, .free = mcf_gpio_free, @@ -81,7 +45,7 @@ static struct mcf_gpio_chip mcf_gpio_chips[] = { .direction_output = mcf_gpio_direction_output, .get = mcf_gpio_get_value, .set = mcf_gpio_set_value_fast, - .base = 25, + .base = 9, .ngpio = 3, }, .pddr = (void __iomem *) MCFGPIO_PDDR_CS, @@ -99,7 +63,7 @@ static struct mcf_gpio_chip mcf_gpio_chips[] = { .direction_output = mcf_gpio_direction_output, .get = mcf_gpio_get_value, .set = mcf_gpio_set_value_fast, - .base = 32, + .base = 16, .ngpio = 4, }, .pddr = (void __iomem *) MCFGPIO_PDDR_FECI2C, @@ -117,7 +81,7 @@ static struct mcf_gpio_chip mcf_gpio_chips[] = { .direction_output = mcf_gpio_direction_output, .get = mcf_gpio_get_value, .set = mcf_gpio_set_value_fast, - .base = 40, + .base = 24, .ngpio = 4, }, .pddr = (void __iomem *) MCFGPIO_PDDR_QSPI, @@ -135,7 +99,7 @@ static struct mcf_gpio_chip mcf_gpio_chips[] = { .direction_output = mcf_gpio_direction_output, .get = mcf_gpio_get_value, .set = mcf_gpio_set_value_fast, - .base = 48, + .base = 32, .ngpio = 4, }, .pddr = (void __iomem *) MCFGPIO_PDDR_TIMER, @@ -153,7 +117,7 @@ static struct mcf_gpio_chip mcf_gpio_chips[] = { .direction_output = mcf_gpio_direction_output, .get = mcf_gpio_get_value, .set = mcf_gpio_set_value_fast, - .base = 56, + .base = 40, .ngpio = 8, }, .pddr = (void __iomem *) MCFGPIO_PDDR_UART, @@ -171,7 +135,7 @@ static struct mcf_gpio_chip mcf_gpio_chips[] = { .direction_output = mcf_gpio_direction_output, .get = mcf_gpio_get_value, .set = mcf_gpio_set_value_fast, - .base = 64, + .base = 48, .ngpio = 8, }, .pddr = (void __iomem *) MCFGPIO_PDDR_FECH, @@ -189,7 +153,7 @@ static struct mcf_gpio_chip mcf_gpio_chips[] = { .direction_output = mcf_gpio_direction_output, .get = mcf_gpio_get_value, .set = mcf_gpio_set_value_fast, - .base = 72, + .base = 56, .ngpio = 8, }, .pddr = (void __iomem *) MCFGPIO_PDDR_FECL, diff --git a/arch/m68k/platform/68328/Makefile b/arch/m68k/platform/68328/Makefile index 5e5435552d56..e4dfd8fde068 100644 --- a/arch/m68k/platform/68328/Makefile +++ b/arch/m68k/platform/68328/Makefile @@ -2,7 +2,10 @@ # Makefile for arch/m68knommu/platform/68328. # -head-y = head-$(MODEL).o +model-y := ram +model-$(CONFIG_ROMKERNEL) := rom + +head-y = head-$(model-y).o head-$(CONFIG_PILOT) = head-pilot.o head-$(CONFIG_DRAGEN2) = head-de2.o diff --git a/arch/m68k/platform/68328/entry.S b/arch/m68k/platform/68328/entry.S index 293e1eba9acc..5c39b80ed7de 100644 --- a/arch/m68k/platform/68328/entry.S +++ b/arch/m68k/platform/68328/entry.S @@ -67,7 +67,7 @@ ret_from_signal: jra ret_from_exception ENTRY(system_call) - SAVE_ALL + SAVE_ALL_SYS /* save top of frame*/ pea %sp@ @@ -129,7 +129,7 @@ Lsignal_return: * This is the main interrupt handler, responsible for calling process_int() */ inthandler1: - SAVE_ALL + SAVE_ALL_INT movew %sp@(PT_OFF_FORMATVEC), %d0 and #0x3ff, %d0 @@ -140,7 +140,7 @@ inthandler1: bra ret_from_interrupt inthandler2: - SAVE_ALL + SAVE_ALL_INT movew %sp@(PT_OFF_FORMATVEC), %d0 and #0x3ff, %d0 @@ -151,7 +151,7 @@ inthandler2: bra ret_from_interrupt inthandler3: - SAVE_ALL + SAVE_ALL_INT movew %sp@(PT_OFF_FORMATVEC), %d0 and #0x3ff, %d0 @@ -162,7 +162,7 @@ inthandler3: bra ret_from_interrupt inthandler4: - SAVE_ALL + SAVE_ALL_INT movew %sp@(PT_OFF_FORMATVEC), %d0 and #0x3ff, %d0 @@ -173,7 +173,7 @@ inthandler4: bra ret_from_interrupt inthandler5: - SAVE_ALL + SAVE_ALL_INT movew %sp@(PT_OFF_FORMATVEC), %d0 and #0x3ff, %d0 @@ -184,7 +184,7 @@ inthandler5: bra ret_from_interrupt inthandler6: - SAVE_ALL + SAVE_ALL_INT movew %sp@(PT_OFF_FORMATVEC), %d0 and #0x3ff, %d0 @@ -195,7 +195,7 @@ inthandler6: bra ret_from_interrupt inthandler7: - SAVE_ALL + SAVE_ALL_INT movew %sp@(PT_OFF_FORMATVEC), %d0 and #0x3ff, %d0 @@ -206,7 +206,7 @@ inthandler7: bra ret_from_interrupt inthandler: - SAVE_ALL + SAVE_ALL_INT movew %sp@(PT_OFF_FORMATVEC), %d0 and #0x3ff, %d0 diff --git a/arch/m68k/platform/68360/Makefile b/arch/m68k/platform/68360/Makefile index cf5af73a5789..f6f434383049 100644 --- a/arch/m68k/platform/68360/Makefile +++ b/arch/m68k/platform/68360/Makefile @@ -1,10 +1,12 @@ # # Makefile for arch/m68knommu/platform/68360. # +model-y := ram +model-$(CONFIG_ROMKERNEL) := rom obj-y := config.o commproc.o entry.o ints.o extra-y := head.o -$(obj)/head.o: $(obj)/head-$(MODEL).o - ln -sf head-$(MODEL).o $(obj)/head.o +$(obj)/head.o: $(obj)/head-$(model-y).o + ln -sf head-$(model-y).o $(obj)/head.o diff --git a/arch/m68k/platform/68360/entry.S b/arch/m68k/platform/68360/entry.S index abbb89672ea0..aa47d1d49929 100644 --- a/arch/m68k/platform/68360/entry.S +++ b/arch/m68k/platform/68360/entry.S @@ -63,7 +63,7 @@ ret_from_signal: jra ret_from_exception ENTRY(system_call) - SAVE_ALL + SAVE_ALL_SYS /* save top of frame*/ pea %sp@ @@ -125,7 +125,7 @@ Lsignal_return: * This is the main interrupt handler, responsible for calling do_IRQ() */ inthandler: - SAVE_ALL + SAVE_ALL_INT movew %sp@(PT_OFF_FORMATVEC), %d0 and.l #0x3ff, %d0 lsr.l #0x02, %d0 diff --git a/arch/m68k/platform/coldfire/entry.S b/arch/m68k/platform/coldfire/entry.S index bd27242c2f43..3157461a8d1d 100644 --- a/arch/m68k/platform/coldfire/entry.S +++ b/arch/m68k/platform/coldfire/entry.S @@ -61,7 +61,7 @@ enosys: bra 1f ENTRY(system_call) - SAVE_ALL + SAVE_ALL_SYS move #0x2000,%sr /* enable intrs again */ cmpl #NR_syscalls,%d0 @@ -165,9 +165,7 @@ Lsignal_return: * sources). Calls up to high level code to do all the work. */ ENTRY(inthandler) - SAVE_ALL - moveq #-1,%d0 - movel %d0,%sp@(PT_OFF_ORIG_D0) + SAVE_ALL_INT movew %sp@(PT_OFF_FORMATVEC),%d0 /* put exception # in d0 */ andl #0x03fc,%d0 /* mask out vector only */ diff --git a/arch/m68k/q40/README b/arch/m68k/q40/README index b26d5f55e91d..93f4c4cd3c45 100644 --- a/arch/m68k/q40/README +++ b/arch/m68k/q40/README @@ -31,7 +31,7 @@ drivers used by the Q40, apart from the very obvious (console etc.): char/joystick/* # most of this should work, not # in default config.in block/q40ide.c # startup for ide - ide* # see Documentation/ide.txt + ide* # see Documentation/ide/ide.txt floppy.c # normal PC driver, DMA emu in asm/floppy.h # and arch/m68k/kernel/entry.S # see drivers/block/README.fd diff --git a/arch/microblaze/include/asm/dma-mapping.h b/arch/microblaze/include/asm/dma-mapping.h index 8fbb0ec10233..3a3e5b886854 100644 --- a/arch/microblaze/include/asm/dma-mapping.h +++ b/arch/microblaze/include/asm/dma-mapping.h @@ -16,7 +16,7 @@ #define _ASM_MICROBLAZE_DMA_MAPPING_H /* - * See Documentation/PCI/PCI-DMA-mapping.txt and + * See Documentation/DMA-API-HOWTO.txt and * Documentation/DMA-API.txt for documentation. */ @@ -28,12 +28,12 @@ #include <linux/dma-attrs.h> #include <asm/io.h> #include <asm-generic/dma-coherent.h> +#include <asm/cacheflush.h> #define DMA_ERROR_CODE (~(dma_addr_t)0x0) #define __dma_alloc_coherent(dev, gfp, size, handle) NULL #define __dma_free_coherent(size, addr) ((void)0) -#define __dma_sync(addr, size, rw) ((void)0) static inline unsigned long device_to_mask(struct device *dev) { @@ -95,6 +95,22 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask) #include <asm-generic/dma-mapping-common.h> +static inline void __dma_sync(unsigned long paddr, + size_t size, enum dma_data_direction direction) +{ + switch (direction) { + case DMA_TO_DEVICE: + case DMA_BIDIRECTIONAL: + flush_dcache_range(paddr, paddr + size); + break; + case DMA_FROM_DEVICE: + invalidate_dcache_range(paddr, paddr + size); + break; + default: + BUG(); + } +} + static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { struct dma_map_ops *ops = get_dma_ops(dev); @@ -135,7 +151,7 @@ static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size, enum dma_data_direction direction) { BUG_ON(direction == DMA_NONE); - __dma_sync(vaddr, size, (int)direction); + __dma_sync(virt_to_phys(vaddr), size, (int)direction); } #endif /* _ASM_MICROBLAZE_DMA_MAPPING_H */ diff --git a/arch/microblaze/include/asm/elf.h b/arch/microblaze/include/asm/elf.h index 098dfdde4b06..834849f59ae8 100644 --- a/arch/microblaze/include/asm/elf.h +++ b/arch/microblaze/include/asm/elf.h @@ -16,13 +16,15 @@ * I've snaffled the value from the microblaze binutils source code * /binutils/microblaze/include/elf/microblaze.h */ -#define EM_XILINX_MICROBLAZE 0xbaab -#define ELF_ARCH EM_XILINX_MICROBLAZE +#define EM_MICROBLAZE 189 +#define EM_MICROBLAZE_OLD 0xbaab +#define ELF_ARCH EM_MICROBLAZE /* * This is used to ensure we don't load something for the wrong architecture. */ -#define elf_check_arch(x) ((x)->e_machine == EM_XILINX_MICROBLAZE) +#define elf_check_arch(x) ((x)->e_machine == EM_MICROBLAZE \ + || (x)->e_machine == EM_MICROBLAZE_OLD) /* * These are used to set parameters in the core dumps. diff --git a/arch/microblaze/include/asm/system.h b/arch/microblaze/include/asm/system.h index e6a2284571dc..5a433cbaafb3 100644 --- a/arch/microblaze/include/asm/system.h +++ b/arch/microblaze/include/asm/system.h @@ -17,8 +17,6 @@ #include <asm-generic/cmpxchg.h> #include <asm-generic/cmpxchg-local.h> -#define __ARCH_WANT_INTERRUPTS_ON_CTXSW - struct task_struct; struct thread_info; @@ -96,11 +94,4 @@ extern struct dentry *of_debugfs_root; #define arch_align_stack(x) (x) -/* - * MicroBlaze doesn't handle unaligned accesses in hardware. - * - * Based on this we force the IP header alignment in network drivers. - */ -#define NET_IP_ALIGN 2 - #endif /* _ASM_MICROBLAZE_SYSTEM_H */ diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h index 5bb95a11880d..072b0077abf9 100644 --- a/arch/microblaze/include/asm/uaccess.h +++ b/arch/microblaze/include/asm/uaccess.h @@ -95,7 +95,7 @@ static inline int ___range_ok(unsigned long addr, unsigned long size) * - "addr", "addr + size" and "size" are all below the limit */ #define access_ok(type, addr, size) \ - (get_fs().seg > (((unsigned long)(addr)) | \ + (get_fs().seg >= (((unsigned long)(addr)) | \ (size) | ((unsigned long)(addr) + (size)))) /* || printk("access_ok failed for %s at 0x%08lx (size %d), seg 0x%08x\n", diff --git a/arch/microblaze/kernel/cpu/cpuinfo.c b/arch/microblaze/kernel/cpu/cpuinfo.c index 44394d80a683..54194b28574a 100644 --- a/arch/microblaze/kernel/cpu/cpuinfo.c +++ b/arch/microblaze/kernel/cpu/cpuinfo.c @@ -34,6 +34,7 @@ const struct cpu_ver_key cpu_ver_lookup[] = { {"8.00.a", 0x12}, {"8.00.b", 0x13}, {"8.10.a", 0x14}, + {"8.20.a", 0x15}, {NULL, 0}, }; diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index 393e6b2db688..dc6416d265d6 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -11,7 +11,6 @@ #include <linux/gfp.h> #include <linux/dma-debug.h> #include <asm/bug.h> -#include <asm/cacheflush.h> /* * Generic direct DMA implementation @@ -21,21 +20,6 @@ * can set archdata.dma_data to an unsigned long holding the offset. By * default the offset is PCI_DRAM_OFFSET. */ -static inline void __dma_sync_page(unsigned long paddr, unsigned long offset, - size_t size, enum dma_data_direction direction) -{ - switch (direction) { - case DMA_TO_DEVICE: - case DMA_BIDIRECTIONAL: - flush_dcache_range(paddr + offset, paddr + offset + size); - break; - case DMA_FROM_DEVICE: - invalidate_dcache_range(paddr + offset, paddr + offset + size); - break; - default: - BUG(); - } -} static unsigned long get_dma_direct_offset(struct device *dev) { @@ -91,7 +75,7 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, /* FIXME this part of code is untested */ for_each_sg(sgl, sg, nents, i) { sg->dma_address = sg_phys(sg) + get_dma_direct_offset(dev); - __dma_sync_page(page_to_phys(sg_page(sg)), sg->offset, + __dma_sync(page_to_phys(sg_page(sg)) + sg->offset, sg->length, direction); } @@ -116,7 +100,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev, enum dma_data_direction direction, struct dma_attrs *attrs) { - __dma_sync_page(page_to_phys(page), offset, size, direction); + __dma_sync(page_to_phys(page) + offset, size, direction); return page_to_phys(page) + offset + get_dma_direct_offset(dev); } @@ -131,7 +115,63 @@ static inline void dma_direct_unmap_page(struct device *dev, * phys_to_virt is here because in __dma_sync_page is __virt_to_phys and * dma_address is physical address */ - __dma_sync_page(dma_address, 0 , size, direction); + __dma_sync(dma_address, size, direction); +} + +static inline void +dma_direct_sync_single_for_cpu(struct device *dev, + dma_addr_t dma_handle, size_t size, + enum dma_data_direction direction) +{ + /* + * It's pointless to flush the cache as the memory segment + * is given to the CPU + */ + + if (direction == DMA_FROM_DEVICE) + __dma_sync(dma_handle, size, direction); +} + +static inline void +dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t dma_handle, size_t size, + enum dma_data_direction direction) +{ + /* + * It's pointless to invalidate the cache if the device isn't + * supposed to write to the relevant region + */ + + if (direction == DMA_TO_DEVICE) + __dma_sync(dma_handle, size, direction); +} + +static inline void +dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, + enum dma_data_direction direction) +{ + struct scatterlist *sg; + int i; + + /* FIXME this part of code is untested */ + if (direction == DMA_FROM_DEVICE) + for_each_sg(sgl, sg, nents, i) + __dma_sync(sg->dma_address, sg->length, direction); +} + +static inline void +dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, + enum dma_data_direction direction) +{ + struct scatterlist *sg; + int i; + + /* FIXME this part of code is untested */ + if (direction == DMA_TO_DEVICE) + for_each_sg(sgl, sg, nents, i) + __dma_sync(sg->dma_address, sg->length, direction); } struct dma_map_ops dma_direct_ops = { @@ -142,6 +182,10 @@ struct dma_map_ops dma_direct_ops = { .dma_supported = dma_direct_dma_supported, .map_page = dma_direct_map_page, .unmap_page = dma_direct_unmap_page, + .sync_single_for_cpu = dma_direct_sync_single_for_cpu, + .sync_single_for_device = dma_direct_sync_single_for_device, + .sync_sg_for_cpu = dma_direct_sync_sg_for_cpu, + .sync_sg_for_device = dma_direct_sync_sg_for_device, }; EXPORT_SYMBOL(dma_direct_ops); diff --git a/arch/microblaze/kernel/exceptions.c b/arch/microblaze/kernel/exceptions.c index 66fad2301221..6348dc82f428 100644 --- a/arch/microblaze/kernel/exceptions.c +++ b/arch/microblaze/kernel/exceptions.c @@ -119,7 +119,7 @@ asmlinkage void full_exception(struct pt_regs *regs, unsigned int type, case MICROBLAZE_DIV_ZERO_EXCEPTION: if (user_mode(regs)) { pr_debug("Divide by zero exception in user mode\n"); - _exception(SIGILL, regs, FPE_INTDIV, addr); + _exception(SIGFPE, regs, FPE_INTDIV, addr); return; } printk(KERN_WARNING "Divide by zero exception " \ diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index dbb812421d8a..95cc295976a7 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -179,6 +179,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, ti->cpu_context.msr = (childregs->msr|MSR_VM); ti->cpu_context.msr &= ~MSR_UMS; /* switch_to to kernel mode */ + ti->cpu_context.msr &= ~MSR_IE; #endif ti->cpu_context.r15 = (unsigned long)ret_from_fork - 8; diff --git a/arch/microblaze/kernel/ptrace.c b/arch/microblaze/kernel/ptrace.c index 6a8e0cc5c57d..043cb58f9c44 100644 --- a/arch/microblaze/kernel/ptrace.c +++ b/arch/microblaze/kernel/ptrace.c @@ -148,7 +148,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) ret = -1L; if (unlikely(current->audit_context)) - audit_syscall_entry(EM_XILINX_MICROBLAZE, regs->r12, + audit_syscall_entry(EM_MICROBLAZE, regs->r12, regs->r5, regs->r6, regs->r7, regs->r8); diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c index e5550ce4e0eb..af74b1113aab 100644 --- a/arch/microblaze/kernel/timer.c +++ b/arch/microblaze/kernel/timer.c @@ -308,7 +308,8 @@ unsigned long long notrace sched_clock(void) { if (timer_initialized) { struct clocksource *cs = &clocksource_microblaze; - cycle_t cyc = cnt32_to_63(cs->read(NULL)); + + cycle_t cyc = cnt32_to_63(cs->read(NULL)) & LLONG_MAX; return clocksource_cyc2ns(cyc, cs->mult, cs->shift); } return 0; diff --git a/arch/microblaze/lib/Makefile b/arch/microblaze/lib/Makefile index 10c320aa908b..c13067b243c3 100644 --- a/arch/microblaze/lib/Makefile +++ b/arch/microblaze/lib/Makefile @@ -25,5 +25,6 @@ lib-y += lshrdi3.o lib-y += modsi3.o lib-y += muldi3.o lib-y += mulsi3.o +lib-y += ucmpdi2.o lib-y += udivsi3.o lib-y += umodsi3.o diff --git a/arch/microblaze/lib/uaccess_old.S b/arch/microblaze/lib/uaccess_old.S index 5810cec54a7a..f037266cdaf3 100644 --- a/arch/microblaze/lib/uaccess_old.S +++ b/arch/microblaze/lib/uaccess_old.S @@ -10,6 +10,7 @@ #include <linux/errno.h> #include <linux/linkage.h> +#include <asm/page.h> /* * int __strncpy_user(char *to, char *from, int len); @@ -33,8 +34,8 @@ __strncpy_user: * r3 - temp count * r4 - temp val */ + beqid r7,3f addik r3,r7,0 /* temp_count = len */ - beqi r3,3f 1: lbu r4,r6,r0 sb r4,r5,r0 @@ -76,8 +77,8 @@ __strncpy_user: .type __strnlen_user, @function .align 4; __strnlen_user: + beqid r6,3f addik r3,r6,0 - beqi r3,3f 1: lbu r4,r5,r0 beqid r4,2f /* break on NUL */ @@ -102,6 +103,49 @@ __strnlen_user: .section __ex_table,"a" .word 1b,4b +/* Loop unrolling for __copy_tofrom_user */ +#define COPY(offset) \ +1: lwi r4 , r6, 0x0000 + offset; \ +2: lwi r19, r6, 0x0004 + offset; \ +3: lwi r20, r6, 0x0008 + offset; \ +4: lwi r21, r6, 0x000C + offset; \ +5: lwi r22, r6, 0x0010 + offset; \ +6: lwi r23, r6, 0x0014 + offset; \ +7: lwi r24, r6, 0x0018 + offset; \ +8: lwi r25, r6, 0x001C + offset; \ +9: swi r4 , r5, 0x0000 + offset; \ +10: swi r19, r5, 0x0004 + offset; \ +11: swi r20, r5, 0x0008 + offset; \ +12: swi r21, r5, 0x000C + offset; \ +13: swi r22, r5, 0x0010 + offset; \ +14: swi r23, r5, 0x0014 + offset; \ +15: swi r24, r5, 0x0018 + offset; \ +16: swi r25, r5, 0x001C + offset; \ + .section __ex_table,"a"; \ + .word 1b, 0f; \ + .word 2b, 0f; \ + .word 3b, 0f; \ + .word 4b, 0f; \ + .word 5b, 0f; \ + .word 6b, 0f; \ + .word 7b, 0f; \ + .word 8b, 0f; \ + .word 9b, 0f; \ + .word 10b, 0f; \ + .word 11b, 0f; \ + .word 12b, 0f; \ + .word 13b, 0f; \ + .word 14b, 0f; \ + .word 15b, 0f; \ + .word 16b, 0f; \ + .text + +#define COPY_80(offset) \ + COPY(0x00 + offset);\ + COPY(0x20 + offset);\ + COPY(0x40 + offset);\ + COPY(0x60 + offset); + /* * int __copy_tofrom_user(char *to, char *from, int len) * Return: @@ -119,34 +163,79 @@ __copy_tofrom_user: * r7, r3 - count * r4 - tempval */ - beqid r7, 3f /* zero size is not likely */ - andi r3, r7, 0x3 /* filter add count */ - bneid r3, 4f /* if is odd value then byte copying */ + beqid r7, 0f /* zero size is not likely */ or r3, r5, r6 /* find if is any to/from unaligned */ - andi r3, r3, 0x3 /* mask unaligned */ - bneid r3, 1f /* it is unaligned -> then jump */ + or r3, r3, r7 /* find if count is unaligned */ + andi r3, r3, 0x3 /* mask last 3 bits */ + bneid r3, bu1 /* if r3 is not zero then byte copying */ + or r3, r0, r0 + + rsubi r3, r7, PAGE_SIZE /* detect PAGE_SIZE */ + beqid r3, page; or r3, r0, r0 -/* at least one 4 byte copy */ -5: lw r4, r6, r3 -6: sw r4, r5, r3 +w1: lw r4, r6, r3 /* at least one 4 byte copy */ +w2: sw r4, r5, r3 addik r7, r7, -4 - bneid r7, 5b + bneid r7, w1 addik r3, r3, 4 addik r3, r7, 0 rtsd r15, 8 nop -4: or r3, r0, r0 -1: lbu r4,r6,r3 -2: sb r4,r5,r3 + + .section __ex_table,"a" + .word w1, 0f; + .word w2, 0f; + .text + +.align 4 /* Alignment is important to keep icache happy */ +page: /* Create room on stack and save registers for storign values */ + addik r1, r1, -32 + swi r19, r1, 4 + swi r20, r1, 8 + swi r21, r1, 12 + swi r22, r1, 16 + swi r23, r1, 20 + swi r24, r1, 24 + swi r25, r1, 28 +loop: /* r4, r19, r20, r21, r22, r23, r24, r25 are used for storing values */ + /* Loop unrolling to get performance boost */ + COPY_80(0x000); + COPY_80(0x080); + COPY_80(0x100); + COPY_80(0x180); + /* copy loop */ + addik r6, r6, 0x200 + addik r7, r7, -0x200 + bneid r7, loop + addik r5, r5, 0x200 + /* Restore register content */ + lwi r19, r1, 4 + lwi r20, r1, 8 + lwi r21, r1, 12 + lwi r22, r1, 16 + lwi r23, r1, 20 + lwi r24, r1, 24 + lwi r25, r1, 28 + addik r1, r1, 32 + /* return back */ + addik r3, r7, 0 + rtsd r15, 8 + nop + +.align 4 /* Alignment is important to keep icache happy */ +bu1: lbu r4,r6,r3 +bu2: sb r4,r5,r3 addik r7,r7,-1 - bneid r7,1b + bneid r7,bu1 addik r3,r3,1 /* delay slot */ -3: +0: addik r3,r7,0 rtsd r15,8 nop .size __copy_tofrom_user, . - __copy_tofrom_user .section __ex_table,"a" - .word 1b,3b,2b,3b,5b,3b,6b,3b + .word bu1, 0b; + .word bu2, 0b; + .text diff --git a/arch/microblaze/lib/ucmpdi2.c b/arch/microblaze/lib/ucmpdi2.c new file mode 100644 index 000000000000..63ca105b6713 --- /dev/null +++ b/arch/microblaze/lib/ucmpdi2.c @@ -0,0 +1,20 @@ +#include <linux/module.h> + +#include "libgcc.h" + +word_type __ucmpdi2(unsigned long long a, unsigned long long b) +{ + const DWunion au = {.ll = a}; + const DWunion bu = {.ll = b}; + + if ((unsigned int) au.s.high < (unsigned int) bu.s.high) + return 0; + else if ((unsigned int) au.s.high > (unsigned int) bu.s.high) + return 2; + if ((unsigned int) au.s.low < (unsigned int) bu.s.low) + return 0; + else if ((unsigned int) au.s.low > (unsigned int) bu.s.low) + return 2; + return 1; +} +EXPORT_SYMBOL(__ucmpdi2); diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 213f2d671669..36a133e5ee35 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -304,11 +304,11 @@ asmlinkage void __init mmu_init(void) /* Map in all of RAM starting at CONFIG_KERNEL_START */ mapin_ram(); -#ifdef HIGHMEM_START_BOOL - ioremap_base = HIGHMEM_START; +#ifdef CONFIG_HIGHMEM_START_BOOL + ioremap_base = CONFIG_HIGHMEM_START; #else ioremap_base = 0xfe000000UL; /* for now, could be 0xfffff000 */ -#endif /* CONFIG_HIGHMEM */ +#endif /* CONFIG_HIGHMEM_START_BOOL */ ioremap_bot = ioremap_base; /* Initialize the context management stuff */ diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 177cdaf83564..4cbc6d8de210 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -24,6 +24,7 @@ config MIPS select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select HAVE_ARCH_JUMP_LABEL + select IRQ_FORCED_THREADING menu "Machine selection" @@ -91,15 +92,8 @@ config BCM47XX select DMA_NONCOHERENT select HW_HAS_PCI select IRQ_CPU - select SYS_HAS_CPU_MIPS32_R1 select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN - select SSB - select SSB_DRIVER_MIPS - select SSB_DRIVER_EXTIF - select SSB_EMBEDDED - select SSB_B43_PCI_BRIDGE if PCI - select SSB_PCICORE_HOSTMODE if PCI select GENERIC_GPIO select SYS_HAS_EARLY_PRINTK select CFE @@ -722,6 +716,7 @@ config CAVIUM_OCTEON_SIMULATOR select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_HOTPLUG_CPU select SYS_HAS_CPU_CAVIUM_OCTEON + select HOLES_IN_ZONE help The Octeon simulator is software performance model of the Cavium Octeon Processor. It supports simulating Octeon processors on x86 @@ -744,6 +739,7 @@ config CAVIUM_OCTEON_REFERENCE_BOARD select ZONE_DMA32 select USB_ARCH_HAS_OHCI select USB_ARCH_HAS_EHCI + select HOLES_IN_ZONE help This option supports all of the Octeon reference boards from Cavium Networks. It builds a kernel that dynamically determines the Octeon @@ -788,6 +784,7 @@ endchoice source "arch/mips/alchemy/Kconfig" source "arch/mips/ath79/Kconfig" +source "arch/mips/bcm47xx/Kconfig" source "arch/mips/bcm63xx/Kconfig" source "arch/mips/jazz/Kconfig" source "arch/mips/jz4740/Kconfig" @@ -973,6 +970,9 @@ config ISA_DMA_API config GENERIC_GPIO bool +config HOLES_IN_ZONE + bool + # # Endianess selection. Sufficiently obscure so many users don't know what to # answer,so we try hard to limit the available choices. Also the use of a diff --git a/arch/mips/alchemy/common/platform.c b/arch/mips/alchemy/common/platform.c index 3b2c18b14341..f72c48d4804c 100644 --- a/arch/mips/alchemy/common/platform.c +++ b/arch/mips/alchemy/common/platform.c @@ -492,7 +492,7 @@ static void __init alchemy_setup_macs(int ctype) memcpy(au1xxx_eth0_platform_data.mac, ethaddr, 6); ret = platform_device_register(&au1xxx_eth0_device); - if (!ret) + if (ret) printk(KERN_INFO "Alchemy: failed to register MAC0\n"); diff --git a/arch/mips/alchemy/common/power.c b/arch/mips/alchemy/common/power.c index 647e518c90bc..b86324a42601 100644 --- a/arch/mips/alchemy/common/power.c +++ b/arch/mips/alchemy/common/power.c @@ -158,15 +158,21 @@ static void restore_core_regs(void) void au_sleep(void) { - int cpuid = alchemy_get_cputype(); - if (cpuid != ALCHEMY_CPU_UNKNOWN) { - save_core_regs(); - if (cpuid <= ALCHEMY_CPU_AU1500) - alchemy_sleep_au1000(); - else if (cpuid <= ALCHEMY_CPU_AU1200) - alchemy_sleep_au1550(); - restore_core_regs(); + save_core_regs(); + + switch (alchemy_get_cputype()) { + case ALCHEMY_CPU_AU1000: + case ALCHEMY_CPU_AU1500: + case ALCHEMY_CPU_AU1100: + alchemy_sleep_au1000(); + break; + case ALCHEMY_CPU_AU1550: + case ALCHEMY_CPU_AU1200: + alchemy_sleep_au1550(); + break; } + + restore_core_regs(); } #endif /* CONFIG_PM */ diff --git a/arch/mips/alchemy/devboards/bcsr.c b/arch/mips/alchemy/devboards/bcsr.c index 596ad00e7f05..463d2c4d9441 100644 --- a/arch/mips/alchemy/devboards/bcsr.c +++ b/arch/mips/alchemy/devboards/bcsr.c @@ -89,8 +89,12 @@ static void bcsr_csc_handler(unsigned int irq, struct irq_desc *d) { unsigned short bisr = __raw_readw(bcsr_virt + BCSR_REG_INTSTAT); + disable_irq_nosync(irq); + for ( ; bisr; bisr &= bisr - 1) generic_handle_irq(bcsr_csc_base + __ffs(bisr)); + + enable_irq(irq); } /* NOTE: both the enable and mask bits must be cleared, otherwise the diff --git a/arch/mips/alchemy/devboards/db1200/platform.c b/arch/mips/alchemy/devboards/db1200/platform.c index fbb55935b99e..dda090bf74e6 100644 --- a/arch/mips/alchemy/devboards/db1200/platform.c +++ b/arch/mips/alchemy/devboards/db1200/platform.c @@ -422,6 +422,7 @@ static struct resource au1200_psc1_res[] = { }, }; +/* AC97 or I2S device */ static struct platform_device db1200_audio_dev = { /* name assigned later based on switch setting */ .id = 1, /* PSC ID */ @@ -429,19 +430,32 @@ static struct platform_device db1200_audio_dev = { .resource = au1200_psc1_res, }; +/* DB1200 ASoC card device */ +static struct platform_device db1200_sound_dev = { + /* name assigned later based on switch setting */ + .id = 1, /* PSC ID */ +}; + static struct platform_device db1200_stac_dev = { .name = "ac97-codec", .id = 1, /* on PSC1 */ }; +static struct platform_device db1200_audiodma_dev = { + .name = "au1xpsc-pcm", + .id = 1, /* PSC ID */ +}; + static struct platform_device *db1200_devs[] __initdata = { NULL, /* PSC0, selected by S6.8 */ &db1200_ide_dev, &db1200_eth_dev, &db1200_rtc_dev, &db1200_nand_dev, + &db1200_audiodma_dev, &db1200_audio_dev, &db1200_stac_dev, + &db1200_sound_dev, }; static int __init db1200_dev_init(void) @@ -501,10 +515,12 @@ static int __init db1200_dev_init(void) if (sw == BCSR_SWITCHES_DIP_8) { bcsr_mod(BCSR_RESETS, 0, BCSR_RESETS_PSC1MUX); db1200_audio_dev.name = "au1xpsc_i2s"; + db1200_sound_dev.name = "db1200-i2s"; printk(KERN_INFO " S6.7 ON : PSC1 mode I2S\n"); } else { bcsr_mod(BCSR_RESETS, BCSR_RESETS_PSC1MUX, 0); db1200_audio_dev.name = "au1xpsc_ac97"; + db1200_sound_dev.name = "db1200-ac97"; printk(KERN_INFO " S6.7 OFF: PSC1 mode AC97\n"); } diff --git a/arch/mips/alchemy/devboards/db1200/setup.c b/arch/mips/alchemy/devboards/db1200/setup.c index 1dac4f27d334..4a8980027ecf 100644 --- a/arch/mips/alchemy/devboards/db1200/setup.c +++ b/arch/mips/alchemy/devboards/db1200/setup.c @@ -23,13 +23,6 @@ void __init board_setup(void) unsigned long freq0, clksrc, div, pfc; unsigned short whoami; - /* Set Config[OD] (disable overlapping bus transaction): - * This gets rid of a _lot_ of spurious interrupts (especially - * wrt. IDE); but incurs ~10% performance hit in some - * cpu-bound applications. - */ - set_c0_config(1 << 19); - bcsr_init(DB1200_BCSR_PHYS_ADDR, DB1200_BCSR_PHYS_ADDR + DB1200_BCSR_HEXLED_OFS); diff --git a/arch/mips/alchemy/devboards/db1x00/platform.c b/arch/mips/alchemy/devboards/db1x00/platform.c index 978d5ab3d678..7057d28f7301 100644 --- a/arch/mips/alchemy/devboards/db1x00/platform.c +++ b/arch/mips/alchemy/devboards/db1x00/platform.c @@ -19,8 +19,11 @@ */ #include <linux/init.h> +#include <linux/interrupt.h> #include <linux/platform_device.h> +#include <asm/mach-au1x00/au1000.h> +#include <asm/mach-au1x00/au1000_dma.h> #include <asm/mach-au1x00/au1xxx.h> #include <asm/mach-db1x00/bcsr.h> #include "../platform.h" @@ -85,6 +88,45 @@ #endif #endif +static struct resource alchemy_ac97c_res[] = { + [0] = { + .start = AU1000_AC97_PHYS_ADDR, + .end = AU1000_AC97_PHYS_ADDR + 0xfff, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = DMA_ID_AC97C_TX, + .end = DMA_ID_AC97C_TX, + .flags = IORESOURCE_DMA, + }, + [2] = { + .start = DMA_ID_AC97C_RX, + .end = DMA_ID_AC97C_RX, + .flags = IORESOURCE_DMA, + }, +}; + +static struct platform_device alchemy_ac97c_dev = { + .name = "alchemy-ac97c", + .id = -1, + .resource = alchemy_ac97c_res, + .num_resources = ARRAY_SIZE(alchemy_ac97c_res), +}; + +static struct platform_device alchemy_ac97c_dma_dev = { + .name = "alchemy-pcm-dma", + .id = 0, +}; + +static struct platform_device db1x00_codec_dev = { + .name = "ac97-codec", + .id = -1, +}; + +static struct platform_device db1x00_audio_dev = { + .name = "db1000-audio", +}; + static int __init db1xxx_dev_init(void) { #ifdef DB1XXX_HAS_PCMCIA @@ -113,6 +155,12 @@ static int __init db1xxx_dev_init(void) 1); #endif db1x_register_norflash(BOARD_FLASH_SIZE, BOARD_FLASH_WIDTH, F_SWAPPED); + + platform_device_register(&db1x00_codec_dev); + platform_device_register(&alchemy_ac97c_dma_dev); + platform_device_register(&alchemy_ac97c_dev); + platform_device_register(&db1x00_audio_dev); + return 0; } device_initcall(db1xxx_dev_init); diff --git a/arch/mips/ar7/irq.c b/arch/mips/ar7/irq.c index 03db3daadbd8..88c4babfdb5d 100644 --- a/arch/mips/ar7/irq.c +++ b/arch/mips/ar7/irq.c @@ -98,7 +98,8 @@ static struct irq_chip ar7_sec_irq_type = { static struct irqaction ar7_cascade_action = { .handler = no_action, - .name = "AR7 cascade interrupt" + .name = "AR7 cascade interrupt", + .flags = IRQF_NO_THREAD, }; static void __init ar7_irq_init(int base) diff --git a/arch/mips/bcm47xx/Kconfig b/arch/mips/bcm47xx/Kconfig new file mode 100644 index 000000000000..6210b8d84109 --- /dev/null +++ b/arch/mips/bcm47xx/Kconfig @@ -0,0 +1,31 @@ +if BCM47XX + +config BCM47XX_SSB + bool "SSB Support for Broadcom BCM47XX" + select SYS_HAS_CPU_MIPS32_R1 + select SSB + select SSB_DRIVER_MIPS + select SSB_DRIVER_EXTIF + select SSB_EMBEDDED + select SSB_B43_PCI_BRIDGE if PCI + select SSB_PCICORE_HOSTMODE if PCI + default y + help + Add support for old Broadcom BCM47xx boards with Sonics Silicon Backplane support. + + This will generate an image with support for SSB and MIPS32 R1 instruction set. + +config BCM47XX_BCMA + bool "BCMA Support for Broadcom BCM47XX" + select SYS_HAS_CPU_MIPS32_R2 + select BCMA + select BCMA_HOST_SOC + select BCMA_DRIVER_MIPS + select BCMA_DRIVER_PCI_HOSTMODE if PCI + default y + help + Add support for new Broadcom BCM47xx boards with Broadcom specific Advanced Microcontroller Bus. + + This will generate an image with support for BCMA and MIPS32 R2 instruction set. + +endif diff --git a/arch/mips/bcm47xx/Makefile b/arch/mips/bcm47xx/Makefile index 7465e8a72d9a..4add17349ff9 100644 --- a/arch/mips/bcm47xx/Makefile +++ b/arch/mips/bcm47xx/Makefile @@ -3,4 +3,5 @@ # under Linux. # -obj-y := gpio.o irq.o nvram.o prom.o serial.o setup.o time.o wgt634u.o +obj-y += gpio.o irq.o nvram.o prom.o serial.o setup.o time.o +obj-$(CONFIG_BCM47XX_SSB) += wgt634u.o diff --git a/arch/mips/bcm47xx/gpio.c b/arch/mips/bcm47xx/gpio.c index e4a5ee9c9721..57b425fd4d41 100644 --- a/arch/mips/bcm47xx/gpio.c +++ b/arch/mips/bcm47xx/gpio.c @@ -20,42 +20,82 @@ static DECLARE_BITMAP(gpio_in_use, BCM47XX_EXTIF_GPIO_LINES); int gpio_request(unsigned gpio, const char *tag) { - if (ssb_chipco_available(&ssb_bcm47xx.chipco) && - ((unsigned)gpio >= BCM47XX_CHIPCO_GPIO_LINES)) - return -EINVAL; + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + if (ssb_chipco_available(&bcm47xx_bus.ssb.chipco) && + ((unsigned)gpio >= BCM47XX_CHIPCO_GPIO_LINES)) + return -EINVAL; - if (ssb_extif_available(&ssb_bcm47xx.extif) && - ((unsigned)gpio >= BCM47XX_EXTIF_GPIO_LINES)) - return -EINVAL; + if (ssb_extif_available(&bcm47xx_bus.ssb.extif) && + ((unsigned)gpio >= BCM47XX_EXTIF_GPIO_LINES)) + return -EINVAL; - if (test_and_set_bit(gpio, gpio_in_use)) - return -EBUSY; + if (test_and_set_bit(gpio, gpio_in_use)) + return -EBUSY; - return 0; + return 0; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + if (gpio >= BCM47XX_CHIPCO_GPIO_LINES) + return -EINVAL; + + if (test_and_set_bit(gpio, gpio_in_use)) + return -EBUSY; + + return 0; +#endif + } + return -EINVAL; } EXPORT_SYMBOL(gpio_request); void gpio_free(unsigned gpio) { - if (ssb_chipco_available(&ssb_bcm47xx.chipco) && - ((unsigned)gpio >= BCM47XX_CHIPCO_GPIO_LINES)) - return; + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + if (ssb_chipco_available(&bcm47xx_bus.ssb.chipco) && + ((unsigned)gpio >= BCM47XX_CHIPCO_GPIO_LINES)) + return; + + if (ssb_extif_available(&bcm47xx_bus.ssb.extif) && + ((unsigned)gpio >= BCM47XX_EXTIF_GPIO_LINES)) + return; - if (ssb_extif_available(&ssb_bcm47xx.extif) && - ((unsigned)gpio >= BCM47XX_EXTIF_GPIO_LINES)) + clear_bit(gpio, gpio_in_use); return; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + if (gpio >= BCM47XX_CHIPCO_GPIO_LINES) + return; - clear_bit(gpio, gpio_in_use); + clear_bit(gpio, gpio_in_use); + return; +#endif + } } EXPORT_SYMBOL(gpio_free); int gpio_to_irq(unsigned gpio) { - if (ssb_chipco_available(&ssb_bcm47xx.chipco)) - return ssb_mips_irq(ssb_bcm47xx.chipco.dev) + 2; - else if (ssb_extif_available(&ssb_bcm47xx.extif)) - return ssb_mips_irq(ssb_bcm47xx.extif.dev) + 2; - else - return -EINVAL; + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + if (ssb_chipco_available(&bcm47xx_bus.ssb.chipco)) + return ssb_mips_irq(bcm47xx_bus.ssb.chipco.dev) + 2; + else if (ssb_extif_available(&bcm47xx_bus.ssb.extif)) + return ssb_mips_irq(bcm47xx_bus.ssb.extif.dev) + 2; + else + return -EINVAL; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + return bcma_core_mips_irq(bcm47xx_bus.bcma.bus.drv_cc.core) + 2; +#endif + } + return -EINVAL; } EXPORT_SYMBOL_GPL(gpio_to_irq); diff --git a/arch/mips/bcm47xx/irq.c b/arch/mips/bcm47xx/irq.c index 325757acd020..8cf3833b2d29 100644 --- a/arch/mips/bcm47xx/irq.c +++ b/arch/mips/bcm47xx/irq.c @@ -26,6 +26,7 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <asm/irq_cpu.h> +#include <bcm47xx.h> void plat_irq_dispatch(void) { @@ -51,5 +52,16 @@ void plat_irq_dispatch(void) void __init arch_init_irq(void) { +#ifdef CONFIG_BCM47XX_BCMA + if (bcm47xx_bus_type == BCM47XX_BUS_TYPE_BCMA) { + bcma_write32(bcm47xx_bus.bcma.bus.drv_mips.core, + BCMA_MIPS_MIPS74K_INTMASK(5), 1 << 31); + /* + * the kernel reads the timer irq from some register and thinks + * it's #5, but we offset it by 2 and route to #7 + */ + cp0_compare_irq = 7; + } +#endif mips_cpu_irq_init(); } diff --git a/arch/mips/bcm47xx/nvram.c b/arch/mips/bcm47xx/nvram.c index 54db815bc86c..a84e3bb7387f 100644 --- a/arch/mips/bcm47xx/nvram.c +++ b/arch/mips/bcm47xx/nvram.c @@ -26,14 +26,35 @@ static char nvram_buf[NVRAM_SPACE]; /* Probe for NVRAM header */ static void early_nvram_init(void) { - struct ssb_mipscore *mcore = &ssb_bcm47xx.mipscore; +#ifdef CONFIG_BCM47XX_SSB + struct ssb_mipscore *mcore_ssb; +#endif +#ifdef CONFIG_BCM47XX_BCMA + struct bcma_drv_cc *bcma_cc; +#endif struct nvram_header *header; int i; - u32 base, lim, off; + u32 base = 0; + u32 lim = 0; + u32 off; u32 *src, *dst; - base = mcore->flash_window; - lim = mcore->flash_window_size; + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + mcore_ssb = &bcm47xx_bus.ssb.mipscore; + base = mcore_ssb->flash_window; + lim = mcore_ssb->flash_window_size; + break; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + bcma_cc = &bcm47xx_bus.bcma.bus.drv_cc; + base = bcma_cc->pflash.window; + lim = bcma_cc->pflash.window_size; + break; +#endif + } off = FLASH_MIN; while (off <= lim) { diff --git a/arch/mips/bcm47xx/serial.c b/arch/mips/bcm47xx/serial.c index 59c11afdb2ab..57981e4fe2bc 100644 --- a/arch/mips/bcm47xx/serial.c +++ b/arch/mips/bcm47xx/serial.c @@ -23,10 +23,11 @@ static struct platform_device uart8250_device = { }, }; -static int __init uart8250_init(void) +#ifdef CONFIG_BCM47XX_SSB +static int __init uart8250_init_ssb(void) { int i; - struct ssb_mipscore *mcore = &(ssb_bcm47xx.mipscore); + struct ssb_mipscore *mcore = &(bcm47xx_bus.ssb.mipscore); memset(&uart8250_data, 0, sizeof(uart8250_data)); @@ -44,6 +45,47 @@ static int __init uart8250_init(void) } return platform_device_register(&uart8250_device); } +#endif + +#ifdef CONFIG_BCM47XX_BCMA +static int __init uart8250_init_bcma(void) +{ + int i; + struct bcma_drv_cc *cc = &(bcm47xx_bus.bcma.bus.drv_cc); + + memset(&uart8250_data, 0, sizeof(uart8250_data)); + + for (i = 0; i < cc->nr_serial_ports; i++) { + struct plat_serial8250_port *p = &(uart8250_data[i]); + struct bcma_serial_port *bcma_port; + bcma_port = &(cc->serial_ports[i]); + + p->mapbase = (unsigned int) bcma_port->regs; + p->membase = (void *) bcma_port->regs; + p->irq = bcma_port->irq + 2; + p->uartclk = bcma_port->baud_base; + p->regshift = bcma_port->reg_shift; + p->iotype = UPIO_MEM; + p->flags = UPF_BOOT_AUTOCONF | UPF_SHARE_IRQ; + } + return platform_device_register(&uart8250_device); +} +#endif + +static int __init uart8250_init(void) +{ + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + return uart8250_init_ssb(); +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + return uart8250_init_bcma(); +#endif + } + return -EINVAL; +} module_init(uart8250_init); diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index cfae81571ded..17c3d14d7c49 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -29,21 +29,36 @@ #include <linux/types.h> #include <linux/ssb/ssb.h> #include <linux/ssb/ssb_embedded.h> +#include <linux/bcma/bcma_soc.h> #include <asm/bootinfo.h> #include <asm/reboot.h> #include <asm/time.h> #include <bcm47xx.h> #include <asm/mach-bcm47xx/nvram.h> -struct ssb_bus ssb_bcm47xx; -EXPORT_SYMBOL(ssb_bcm47xx); +union bcm47xx_bus bcm47xx_bus; +EXPORT_SYMBOL(bcm47xx_bus); + +enum bcm47xx_bus_type bcm47xx_bus_type; +EXPORT_SYMBOL(bcm47xx_bus_type); static void bcm47xx_machine_restart(char *command) { printk(KERN_ALERT "Please stand by while rebooting the system...\n"); local_irq_disable(); /* Set the watchdog timer to reset immediately */ - ssb_watchdog_timer_set(&ssb_bcm47xx, 1); + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + ssb_watchdog_timer_set(&bcm47xx_bus.ssb, 1); + break; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + bcma_chipco_watchdog_timer_set(&bcm47xx_bus.bcma.bus.drv_cc, 1); + break; +#endif + } while (1) cpu_relax(); } @@ -52,11 +67,23 @@ static void bcm47xx_machine_halt(void) { /* Disable interrupts and watchdog and spin forever */ local_irq_disable(); - ssb_watchdog_timer_set(&ssb_bcm47xx, 0); + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + ssb_watchdog_timer_set(&bcm47xx_bus.ssb, 0); + break; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + bcma_chipco_watchdog_timer_set(&bcm47xx_bus.bcma.bus.drv_cc, 0); + break; +#endif + } while (1) cpu_relax(); } +#ifdef CONFIG_BCM47XX_SSB #define READ_FROM_NVRAM(_outvar, name, buf) \ if (nvram_getprefix(prefix, name, buf, sizeof(buf)) >= 0)\ sprom->_outvar = simple_strtoul(buf, NULL, 0); @@ -247,7 +274,7 @@ static int bcm47xx_get_invariants(struct ssb_bus *bus, return 0; } -void __init plat_mem_setup(void) +static void __init bcm47xx_register_ssb(void) { int err; char buf[100]; @@ -258,12 +285,12 @@ void __init plat_mem_setup(void) printk(KERN_WARNING "bcm47xx: someone else already registered" " a ssb SPROM callback handler (err %d)\n", err); - err = ssb_bus_ssbbus_register(&ssb_bcm47xx, SSB_ENUM_BASE, + err = ssb_bus_ssbbus_register(&(bcm47xx_bus.ssb), SSB_ENUM_BASE, bcm47xx_get_invariants); if (err) panic("Failed to initialize SSB bus (err %d)\n", err); - mcore = &ssb_bcm47xx.mipscore; + mcore = &bcm47xx_bus.ssb.mipscore; if (nvram_getenv("kernel_args", buf, sizeof(buf)) >= 0) { if (strstr(buf, "console=ttyS1")) { struct ssb_serial_port port; @@ -276,8 +303,57 @@ void __init plat_mem_setup(void) memcpy(&mcore->serial_ports[1], &port, sizeof(port)); } } +} +#endif + +#ifdef CONFIG_BCM47XX_BCMA +static void __init bcm47xx_register_bcma(void) +{ + int err; + + err = bcma_host_soc_register(&bcm47xx_bus.bcma); + if (err) + panic("Failed to initialize BCMA bus (err %d)\n", err); +} +#endif + +void __init plat_mem_setup(void) +{ + struct cpuinfo_mips *c = ¤t_cpu_data; + + if (c->cputype == CPU_74K) { + printk(KERN_INFO "bcm47xx: using bcma bus\n"); +#ifdef CONFIG_BCM47XX_BCMA + bcm47xx_bus_type = BCM47XX_BUS_TYPE_BCMA; + bcm47xx_register_bcma(); +#endif + } else { + printk(KERN_INFO "bcm47xx: using ssb bus\n"); +#ifdef CONFIG_BCM47XX_SSB + bcm47xx_bus_type = BCM47XX_BUS_TYPE_SSB; + bcm47xx_register_ssb(); +#endif + } _machine_restart = bcm47xx_machine_restart; _machine_halt = bcm47xx_machine_halt; pm_power_off = bcm47xx_machine_halt; } + +static int __init bcm47xx_register_bus_complete(void) +{ + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + /* Nothing to do */ + break; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + bcma_bus_register(&bcm47xx_bus.bcma.bus); + break; +#endif + } + return 0; +} +device_initcall(bcm47xx_register_bus_complete); diff --git a/arch/mips/bcm47xx/time.c b/arch/mips/bcm47xx/time.c index 0c6f47b3fd94..536374dcba78 100644 --- a/arch/mips/bcm47xx/time.c +++ b/arch/mips/bcm47xx/time.c @@ -30,7 +30,7 @@ void __init plat_time_init(void) { - unsigned long hz; + unsigned long hz = 0; /* * Use deterministic values for initial counter interrupt @@ -39,7 +39,19 @@ void __init plat_time_init(void) write_c0_count(0); write_c0_compare(0xffff); - hz = ssb_cpu_clock(&ssb_bcm47xx.mipscore) / 2; + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + hz = ssb_cpu_clock(&bcm47xx_bus.ssb.mipscore) / 2; + break; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + hz = bcma_cpu_clock(&bcm47xx_bus.bcma.bus.drv_mips) / 2; + break; +#endif + } + if (!hz) hz = 100000000; diff --git a/arch/mips/bcm47xx/wgt634u.c b/arch/mips/bcm47xx/wgt634u.c index 74d06965326f..e9f9ec8d443b 100644 --- a/arch/mips/bcm47xx/wgt634u.c +++ b/arch/mips/bcm47xx/wgt634u.c @@ -108,7 +108,7 @@ static irqreturn_t gpio_interrupt(int irq, void *ignored) /* Interrupts are shared, check if the current one is a GPIO interrupt. */ - if (!ssb_chipco_irq_status(&ssb_bcm47xx.chipco, + if (!ssb_chipco_irq_status(&bcm47xx_bus.ssb.chipco, SSB_CHIPCO_IRQ_GPIO)) return IRQ_NONE; @@ -132,22 +132,26 @@ static int __init wgt634u_init(void) * machine. Use the MAC address as an heuristic. Netgear Inc. has * been allocated ranges 00:09:5b:xx:xx:xx and 00:0f:b5:xx:xx:xx. */ + u8 *et0mac; - u8 *et0mac = ssb_bcm47xx.sprom.et0mac; + if (bcm47xx_bus_type != BCM47XX_BUS_TYPE_SSB) + return -ENODEV; + + et0mac = bcm47xx_bus.ssb.sprom.et0mac; if (et0mac[0] == 0x00 && ((et0mac[1] == 0x09 && et0mac[2] == 0x5b) || (et0mac[1] == 0x0f && et0mac[2] == 0xb5))) { - struct ssb_mipscore *mcore = &ssb_bcm47xx.mipscore; + struct ssb_mipscore *mcore = &bcm47xx_bus.ssb.mipscore; printk(KERN_INFO "WGT634U machine detected.\n"); if (!request_irq(gpio_to_irq(WGT634U_GPIO_RESET), gpio_interrupt, IRQF_SHARED, - "WGT634U GPIO", &ssb_bcm47xx.chipco)) { + "WGT634U GPIO", &bcm47xx_bus.ssb.chipco)) { gpio_direction_input(WGT634U_GPIO_RESET); gpio_intmask(WGT634U_GPIO_RESET, 1); - ssb_chipco_irq_mask(&ssb_bcm47xx.chipco, + ssb_chipco_irq_mask(&bcm47xx_bus.ssb.chipco, SSB_CHIPCO_IRQ_GPIO, SSB_CHIPCO_IRQ_GPIO); } diff --git a/arch/mips/bcm63xx/irq.c b/arch/mips/bcm63xx/irq.c index cea6021cb8d7..162e11b4ed75 100644 --- a/arch/mips/bcm63xx/irq.c +++ b/arch/mips/bcm63xx/irq.c @@ -222,6 +222,7 @@ static struct irq_chip bcm63xx_external_irq_chip = { static struct irqaction cpu_ip2_cascade_action = { .handler = no_action, .name = "cascade_ip2", + .flags = IRQF_NO_THREAD, }; void __init arch_init_irq(void) diff --git a/arch/mips/cobalt/irq.c b/arch/mips/cobalt/irq.c index cb9bf820fe53..965c777d3561 100644 --- a/arch/mips/cobalt/irq.c +++ b/arch/mips/cobalt/irq.c @@ -48,6 +48,7 @@ asmlinkage void plat_irq_dispatch(void) static struct irqaction cascade = { .handler = no_action, .name = "cascade", + .flags = IRQF_NO_THREAD, }; void __init arch_init_irq(void) diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c index fa45e924be05..f7b7ba6d5c45 100644 --- a/arch/mips/dec/setup.c +++ b/arch/mips/dec/setup.c @@ -101,20 +101,24 @@ int cpu_fpu_mask = DEC_CPU_IRQ_MASK(DEC_CPU_INR_FPU); static struct irqaction ioirq = { .handler = no_action, .name = "cascade", + .flags = IRQF_NO_THREAD, }; static struct irqaction fpuirq = { .handler = no_action, .name = "fpu", + .flags = IRQF_NO_THREAD, }; static struct irqaction busirq = { .flags = IRQF_DISABLED, .name = "bus error", + .flags = IRQF_NO_THREAD, }; static struct irqaction haltirq = { .handler = dec_intr_halt, .name = "halt", + .flags = IRQF_NO_THREAD, }; diff --git a/arch/mips/emma/markeins/irq.c b/arch/mips/emma/markeins/irq.c index 3dbd7a5a6ad3..7798887a1288 100644 --- a/arch/mips/emma/markeins/irq.c +++ b/arch/mips/emma/markeins/irq.c @@ -169,7 +169,7 @@ void emma2rh_gpio_irq_init(void) static struct irqaction irq_cascade = { .handler = no_action, - .flags = 0, + .flags = IRQF_NO_THREAD, .name = "cascade", .dev_id = NULL, .next = NULL, diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index dbc51065df5b..b77df0366ee6 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -111,7 +111,8 @@ struct compat_statfs { int f_bavail; compat_fsid_t f_fsid; int f_namelen; - int f_spare[6]; + int f_flags; + int f_spare[5]; }; #define COMPAT_RLIM_INFINITY 0x7fffffffUL diff --git a/arch/mips/include/asm/lasat/lasat.h b/arch/mips/include/asm/lasat/lasat.h index a1ada1c27c16..e8ff70f80e13 100644 --- a/arch/mips/include/asm/lasat/lasat.h +++ b/arch/mips/include/asm/lasat/lasat.h @@ -41,10 +41,8 @@ enum lasat_mtdparts { /* * The format of the data record in the EEPROM. - * See Documentation/LASAT/eeprom.txt for a detailed description - * of the fields in this struct, and the LASAT Hardware Configuration - * field specification for a detailed description of the config - * field. + * See the LASAT Hardware Configuration field specification for a detailed + * description of the config field. */ #include <linux/types.h> diff --git a/arch/mips/include/asm/mach-au1x00/au1xxx_psc.h b/arch/mips/include/asm/mach-au1x00/au1xxx_psc.h index 892b7f168eb4..5a5cb7386427 100644 --- a/arch/mips/include/asm/mach-au1x00/au1xxx_psc.h +++ b/arch/mips/include/asm/mach-au1x00/au1xxx_psc.h @@ -394,19 +394,6 @@ typedef struct psc_spi { #define PSC_SPITXRX_LC (1 << 29) #define PSC_SPITXRX_SR (1 << 28) -/* PSC in SMBus (I2C) Mode. */ -typedef struct psc_smb { - u32 psc_sel; - u32 psc_ctrl; - u32 psc_smbcfg; - u32 psc_smbmsk; - u32 psc_smbpcr; - u32 psc_smbstat; - u32 psc_smbevnt; - u32 psc_smbtxrx; - u32 psc_smbtmr; -} psc_smb_t; - /* SMBus Config Register. */ #define PSC_SMBCFG_RT_MASK (3 << 30) #define PSC_SMBCFG_RT_FIFO1 (0 << 30) diff --git a/arch/mips/include/asm/mach-bcm47xx/bcm47xx.h b/arch/mips/include/asm/mach-bcm47xx/bcm47xx.h index d008f47a28bd..de95e0723e2b 100644 --- a/arch/mips/include/asm/mach-bcm47xx/bcm47xx.h +++ b/arch/mips/include/asm/mach-bcm47xx/bcm47xx.h @@ -19,7 +19,29 @@ #ifndef __ASM_BCM47XX_H #define __ASM_BCM47XX_H -/* SSB bus */ -extern struct ssb_bus ssb_bcm47xx; +#include <linux/ssb/ssb.h> +#include <linux/bcma/bcma.h> +#include <linux/bcma/bcma_soc.h> + +enum bcm47xx_bus_type { +#ifdef CONFIG_BCM47XX_SSB + BCM47XX_BUS_TYPE_SSB, +#endif +#ifdef CONFIG_BCM47XX_BCMA + BCM47XX_BUS_TYPE_BCMA, +#endif +}; + +union bcm47xx_bus { +#ifdef CONFIG_BCM47XX_SSB + struct ssb_bus ssb; +#endif +#ifdef CONFIG_BCM47XX_BCMA + struct bcma_soc bcma; +#endif +}; + +extern union bcm47xx_bus bcm47xx_bus; +extern enum bcm47xx_bus_type bcm47xx_bus_type; #endif /* __ASM_BCM47XX_H */ diff --git a/arch/mips/include/asm/mach-bcm47xx/gpio.h b/arch/mips/include/asm/mach-bcm47xx/gpio.h index 98504142124e..76961cabeedf 100644 --- a/arch/mips/include/asm/mach-bcm47xx/gpio.h +++ b/arch/mips/include/asm/mach-bcm47xx/gpio.h @@ -10,6 +10,7 @@ #define __BCM47XX_GPIO_H #include <linux/ssb/ssb_embedded.h> +#include <linux/bcma/bcma.h> #include <asm/mach-bcm47xx/bcm47xx.h> #define BCM47XX_EXTIF_GPIO_LINES 5 @@ -21,41 +22,118 @@ extern int gpio_to_irq(unsigned gpio); static inline int gpio_get_value(unsigned gpio) { - return ssb_gpio_in(&ssb_bcm47xx, 1 << gpio); + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + return ssb_gpio_in(&bcm47xx_bus.ssb, 1 << gpio); +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + return bcma_chipco_gpio_in(&bcm47xx_bus.bcma.bus.drv_cc, + 1 << gpio); +#endif + } + return -EINVAL; } static inline void gpio_set_value(unsigned gpio, int value) { - ssb_gpio_out(&ssb_bcm47xx, 1 << gpio, value ? 1 << gpio : 0); + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + ssb_gpio_out(&bcm47xx_bus.ssb, 1 << gpio, + value ? 1 << gpio : 0); + return; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + bcma_chipco_gpio_out(&bcm47xx_bus.bcma.bus.drv_cc, 1 << gpio, + value ? 1 << gpio : 0); + return; +#endif + } } static inline int gpio_direction_input(unsigned gpio) { - ssb_gpio_outen(&ssb_bcm47xx, 1 << gpio, 0); - return 0; + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + ssb_gpio_outen(&bcm47xx_bus.ssb, 1 << gpio, 0); + return 0; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + bcma_chipco_gpio_outen(&bcm47xx_bus.bcma.bus.drv_cc, 1 << gpio, + 0); + return 0; +#endif + } + return -EINVAL; } static inline int gpio_direction_output(unsigned gpio, int value) { - /* first set the gpio out value */ - ssb_gpio_out(&ssb_bcm47xx, 1 << gpio, value ? 1 << gpio : 0); - /* then set the gpio mode */ - ssb_gpio_outen(&ssb_bcm47xx, 1 << gpio, 1 << gpio); - return 0; + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + /* first set the gpio out value */ + ssb_gpio_out(&bcm47xx_bus.ssb, 1 << gpio, + value ? 1 << gpio : 0); + /* then set the gpio mode */ + ssb_gpio_outen(&bcm47xx_bus.ssb, 1 << gpio, 1 << gpio); + return 0; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + /* first set the gpio out value */ + bcma_chipco_gpio_out(&bcm47xx_bus.bcma.bus.drv_cc, 1 << gpio, + value ? 1 << gpio : 0); + /* then set the gpio mode */ + bcma_chipco_gpio_outen(&bcm47xx_bus.bcma.bus.drv_cc, 1 << gpio, + 1 << gpio); + return 0; +#endif + } + return -EINVAL; } static inline int gpio_intmask(unsigned gpio, int value) { - ssb_gpio_intmask(&ssb_bcm47xx, 1 << gpio, - value ? 1 << gpio : 0); - return 0; + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + ssb_gpio_intmask(&bcm47xx_bus.ssb, 1 << gpio, + value ? 1 << gpio : 0); + return 0; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + bcma_chipco_gpio_intmask(&bcm47xx_bus.bcma.bus.drv_cc, + 1 << gpio, value ? 1 << gpio : 0); + return 0; +#endif + } + return -EINVAL; } static inline int gpio_polarity(unsigned gpio, int value) { - ssb_gpio_polarity(&ssb_bcm47xx, 1 << gpio, - value ? 1 << gpio : 0); - return 0; + switch (bcm47xx_bus_type) { +#ifdef CONFIG_BCM47XX_SSB + case BCM47XX_BUS_TYPE_SSB: + ssb_gpio_polarity(&bcm47xx_bus.ssb, 1 << gpio, + value ? 1 << gpio : 0); + return 0; +#endif +#ifdef CONFIG_BCM47XX_BCMA + case BCM47XX_BUS_TYPE_BCMA: + bcma_chipco_gpio_polarity(&bcm47xx_bus.bcma.bus.drv_cc, + 1 << gpio, value ? 1 << gpio : 0); + return 0; +#endif + } + return -EINVAL; } diff --git a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h index 0d5a42b5f47a..a58addb98cfd 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h @@ -54,7 +54,6 @@ #define cpu_has_mips_r2_exec_hazard 0 #define cpu_has_dsp 0 #define cpu_has_mipsmt 0 -#define cpu_has_userlocal 0 #define cpu_has_vint 0 #define cpu_has_veic 0 #define cpu_hwrena_impl_bits 0xc0000000 diff --git a/arch/mips/include/asm/mach-powertv/dma-coherence.h b/arch/mips/include/asm/mach-powertv/dma-coherence.h index 62c094085947..35371641575d 100644 --- a/arch/mips/include/asm/mach-powertv/dma-coherence.h +++ b/arch/mips/include/asm/mach-powertv/dma-coherence.h @@ -13,7 +13,6 @@ #define __ASM_MACH_POWERTV_DMA_COHERENCE_H #include <linux/sched.h> -#include <linux/version.h> #include <linux/device.h> #include <asm/mach-powertv/asic.h> diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h index b4ba2449444b..cb41af5f3406 100644 --- a/arch/mips/include/asm/stackframe.h +++ b/arch/mips/include/asm/stackframe.h @@ -195,9 +195,9 @@ * to cover the pipeline delay. */ .set mips32 - mfc0 v1, CP0_TCSTATUS + mfc0 k0, CP0_TCSTATUS .set mips0 - LONG_S v1, PT_TCSTATUS(sp) + LONG_S k0, PT_TCSTATUS(sp) #endif /* CONFIG_MIPS_MT_SMTC */ LONG_S $4, PT_R4(sp) LONG_S $5, PT_R5(sp) diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c index 73031f7fc827..4397972949fa 100644 --- a/arch/mips/jz4740/gpio.c +++ b/arch/mips/jz4740/gpio.c @@ -18,7 +18,7 @@ #include <linux/init.h> #include <linux/spinlock.h> -#include <linux/sysdev.h> +#include <linux/syscore_ops.h> #include <linux/io.h> #include <linux/gpio.h> #include <linux/delay.h> @@ -86,7 +86,6 @@ struct jz_gpio_chip { spinlock_t lock; struct gpio_chip gpio_chip; - struct sys_device sysdev; }; static struct jz_gpio_chip jz4740_gpio_chips[]; @@ -459,49 +458,47 @@ static struct jz_gpio_chip jz4740_gpio_chips[] = { JZ4740_GPIO_CHIP(D), }; -static inline struct jz_gpio_chip *sysdev_to_chip(struct sys_device *dev) +static void jz4740_gpio_suspend_chip(struct jz_gpio_chip *chip) { - return container_of(dev, struct jz_gpio_chip, sysdev); + chip->suspend_mask = readl(chip->base + JZ_REG_GPIO_MASK); + writel(~(chip->wakeup), chip->base + JZ_REG_GPIO_MASK_SET); + writel(chip->wakeup, chip->base + JZ_REG_GPIO_MASK_CLEAR); } -static int jz4740_gpio_suspend(struct sys_device *dev, pm_message_t state) +static int jz4740_gpio_suspend(void) { - struct jz_gpio_chip *chip = sysdev_to_chip(dev); + int i; - chip->suspend_mask = readl(chip->base + JZ_REG_GPIO_MASK); - writel(~(chip->wakeup), chip->base + JZ_REG_GPIO_MASK_SET); - writel(chip->wakeup, chip->base + JZ_REG_GPIO_MASK_CLEAR); + for (i = 0; i < ARRAY_SIZE(jz4740_gpio_chips); i++) + jz4740_gpio_suspend_chip(&jz4740_gpio_chips[i]); return 0; } -static int jz4740_gpio_resume(struct sys_device *dev) +static void jz4740_gpio_resume_chip(struct jz_gpio_chip *chip) { - struct jz_gpio_chip *chip = sysdev_to_chip(dev); uint32_t mask = chip->suspend_mask; writel(~mask, chip->base + JZ_REG_GPIO_MASK_CLEAR); writel(mask, chip->base + JZ_REG_GPIO_MASK_SET); +} - return 0; +static void jz4740_gpio_resume(void) +{ + int i; + + for (i = ARRAY_SIZE(jz4740_gpio_chips) - 1; i >= 0 ; i--) + jz4740_gpio_resume_chip(&jz4740_gpio_chips[i]); } -static struct sysdev_class jz4740_gpio_sysdev_class = { - .name = "gpio", +static struct syscore_ops jz4740_gpio_syscore_ops = { .suspend = jz4740_gpio_suspend, .resume = jz4740_gpio_resume, }; -static int jz4740_gpio_chip_init(struct jz_gpio_chip *chip, unsigned int id) +static void jz4740_gpio_chip_init(struct jz_gpio_chip *chip, unsigned int id) { - int ret, irq; - - chip->sysdev.id = id; - chip->sysdev.cls = &jz4740_gpio_sysdev_class; - ret = sysdev_register(&chip->sysdev); - - if (ret) - return ret; + int irq; spin_lock_init(&chip->lock); @@ -519,22 +516,17 @@ static int jz4740_gpio_chip_init(struct jz_gpio_chip *chip, unsigned int id) irq_set_chip_and_handler(irq, &jz_gpio_irq_chip, handle_level_irq); } - - return 0; } static int __init jz4740_gpio_init(void) { unsigned int i; - int ret; - - ret = sysdev_class_register(&jz4740_gpio_sysdev_class); - if (ret) - return ret; for (i = 0; i < ARRAY_SIZE(jz4740_gpio_chips); ++i) jz4740_gpio_chip_init(&jz4740_gpio_chips[i], i); + register_syscore_ops(&jz4740_gpio_syscore_ops); + printk(KERN_INFO "JZ4740 GPIO initialized\n"); return 0; diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index feb8021a305f..6a2d758dd8e9 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -19,6 +19,26 @@ #include <asm-generic/sections.h> +#if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT) +#define MCOUNT_OFFSET_INSNS 5 +#else +#define MCOUNT_OFFSET_INSNS 4 +#endif + +/* + * Check if the address is in kernel space + * + * Clone core_kernel_text() from kernel/extable.c, but doesn't call + * init_kernel_text() for Ftrace doesn't trace functions in init sections. + */ +static inline int in_kernel_space(unsigned long ip) +{ + if (ip >= (unsigned long)_stext && + ip <= (unsigned long)_etext) + return 1; + return 0; +} + #ifdef CONFIG_DYNAMIC_FTRACE #define JAL 0x0c000000 /* jump & link: ip --> ra, jump to target */ @@ -54,20 +74,6 @@ static inline void ftrace_dyn_arch_init_insns(void) #endif } -/* - * Check if the address is in kernel space - * - * Clone core_kernel_text() from kernel/extable.c, but doesn't call - * init_kernel_text() for Ftrace doesn't trace functions in init sections. - */ -static inline int in_kernel_space(unsigned long ip) -{ - if (ip >= (unsigned long)_stext && - ip <= (unsigned long)_etext) - return 1; - return 0; -} - static int ftrace_modify_code(unsigned long ip, unsigned int new_code) { int faulted; @@ -112,11 +118,6 @@ static int ftrace_modify_code(unsigned long ip, unsigned int new_code) * 1: offset = 4 instructions */ -#if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT) -#define MCOUNT_OFFSET_INSNS 5 -#else -#define MCOUNT_OFFSET_INSNS 4 -#endif #define INSN_B_1F (0x10000000 | MCOUNT_OFFSET_INSNS) int ftrace_make_nop(struct module *mod, diff --git a/arch/mips/kernel/i8259.c b/arch/mips/kernel/i8259.c index 5c74eb797f08..32b397b646ee 100644 --- a/arch/mips/kernel/i8259.c +++ b/arch/mips/kernel/i8259.c @@ -229,7 +229,7 @@ static void i8259A_shutdown(void) */ if (i8259A_auto_eoi >= 0) { outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ - outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */ + outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ } } @@ -295,6 +295,7 @@ static void init_8259A(int auto_eoi) static struct irqaction irq2 = { .handler = no_action, .name = "cascade", + .flags = IRQF_NO_THREAD, }; static struct resource pic1_io_resource = { diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 876a75cc376f..922a554cd108 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -349,3 +349,10 @@ SYSCALL_DEFINE6(32_fanotify_mark, int, fanotify_fd, unsigned int, flags, return sys_fanotify_mark(fanotify_fd, flags, merge_64(a3, a4), dfd, pathname); } + +SYSCALL_DEFINE6(32_futex, u32 __user *, uaddr, int, op, u32, val, + struct compat_timespec __user *, utime, u32 __user *, uaddr2, + u32, val3) +{ + return compat_sys_futex(uaddr, op, val, utime, uaddr2, val3); +} diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index f9296e894e46..6de1f598346e 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -315,7 +315,7 @@ EXPORT(sysn32_call_table) PTR sys_fremovexattr PTR sys_tkill PTR sys_ni_syscall - PTR compat_sys_futex + PTR sys_32_futex PTR compat_sys_sched_setaffinity /* 6195 */ PTR compat_sys_sched_getaffinity PTR sys_cacheflush diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 4d7c9827706f..1d813169e453 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -441,7 +441,7 @@ sys_call_table: PTR sys_fremovexattr /* 4235 */ PTR sys_tkill PTR sys_sendfile64 - PTR compat_sys_futex + PTR sys_32_futex PTR compat_sys_sched_setaffinity PTR compat_sys_sched_getaffinity /* 4240 */ PTR compat_sys_io_setup diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index dbbe0ce48d89..f8524003676a 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -8,6 +8,7 @@ * Copyright (C) 1999, 2000 Silicon Graphics, Inc. */ #include <linux/cache.h> +#include <linux/irqflags.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/personality.h> @@ -658,6 +659,8 @@ static void do_signal(struct pt_regs *regs) asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { + local_irq_enable(); + /* deal with pending signal delivery */ if (thread_info_flags & (_TIF_SIGPENDING | _TIF_RESTORE_SIGMASK)) do_signal(regs); diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index b7517e3abc85..cbea618af0b4 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -14,6 +14,7 @@ #include <linux/bug.h> #include <linux/compiler.h> #include <linux/init.h> +#include <linux/kernel.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/sched.h> @@ -364,21 +365,26 @@ static int regs_to_trapnr(struct pt_regs *regs) return (regs->cp0_cause >> 2) & 0x1f; } -static DEFINE_SPINLOCK(die_lock); +static DEFINE_RAW_SPINLOCK(die_lock); void __noreturn die(const char *str, struct pt_regs *regs) { static int die_counter; int sig = SIGSEGV; #ifdef CONFIG_MIPS_MT_SMTC - unsigned long dvpret = dvpe(); + unsigned long dvpret; #endif /* CONFIG_MIPS_MT_SMTC */ + oops_enter(); + if (notify_die(DIE_OOPS, str, regs, 0, regs_to_trapnr(regs), SIGSEGV) == NOTIFY_STOP) sig = 0; console_verbose(); - spin_lock_irq(&die_lock); + raw_spin_lock_irq(&die_lock); +#ifdef CONFIG_MIPS_MT_SMTC + dvpret = dvpe(); +#endif /* CONFIG_MIPS_MT_SMTC */ bust_spinlocks(1); #ifdef CONFIG_MIPS_MT_SMTC mips_mt_regdump(dvpret); @@ -387,7 +393,9 @@ void __noreturn die(const char *str, struct pt_regs *regs) printk("%s[#%d]:\n", str, ++die_counter); show_registers(regs); add_taint(TAINT_DIE); - spin_unlock_irq(&die_lock); + raw_spin_unlock_irq(&die_lock); + + oops_exit(); if (in_interrupt()) panic("Fatal exception in interrupt"); diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 2cd50ad0d5c6..3efcb065f78a 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -192,7 +192,7 @@ static struct tc *get_tc(int index) } spin_unlock(&vpecontrol.tc_list_lock); - return NULL; + return res; } /* allocate a vpe and associate it with this minor (or index) */ diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c index fc89795cafdb..f9737bb3c5ab 100644 --- a/arch/mips/lantiq/irq.c +++ b/arch/mips/lantiq/irq.c @@ -123,11 +123,10 @@ void ltq_enable_irq(struct irq_data *d) static unsigned int ltq_startup_eiu_irq(struct irq_data *d) { int i; - int irq_nr = d->irq - INT_NUM_IRQ0; ltq_enable_irq(d); for (i = 0; i < MAX_EIU; i++) { - if (irq_nr == ltq_eiu_irq[i]) { + if (d->irq == ltq_eiu_irq[i]) { /* low level - we should really handle set_type */ ltq_eiu_w32(ltq_eiu_r32(LTQ_EIU_EXIN_C) | (0x6 << (i * 4)), LTQ_EIU_EXIN_C); @@ -147,11 +146,10 @@ static unsigned int ltq_startup_eiu_irq(struct irq_data *d) static void ltq_shutdown_eiu_irq(struct irq_data *d) { int i; - int irq_nr = d->irq - INT_NUM_IRQ0; ltq_disable_irq(d); for (i = 0; i < MAX_EIU; i++) { - if (irq_nr == ltq_eiu_irq[i]) { + if (d->irq == ltq_eiu_irq[i]) { /* disable */ ltq_eiu_w32(ltq_eiu_r32(LTQ_EIU_EXIN_INEN) & ~(1 << i), LTQ_EIU_EXIN_INEN); diff --git a/arch/mips/lantiq/xway/ebu.c b/arch/mips/lantiq/xway/ebu.c index 66eb52fa50a1..033b3184c7a7 100644 --- a/arch/mips/lantiq/xway/ebu.c +++ b/arch/mips/lantiq/xway/ebu.c @@ -10,7 +10,6 @@ #include <linux/kernel.h> #include <linux/module.h> -#include <linux/version.h> #include <linux/ioport.h> #include <lantiq_soc.h> diff --git a/arch/mips/lantiq/xway/pmu.c b/arch/mips/lantiq/xway/pmu.c index 9d69f01e352b..39f0d2641cbf 100644 --- a/arch/mips/lantiq/xway/pmu.c +++ b/arch/mips/lantiq/xway/pmu.c @@ -8,7 +8,6 @@ #include <linux/kernel.h> #include <linux/module.h> -#include <linux/version.h> #include <linux/ioport.h> #include <lantiq_soc.h> diff --git a/arch/mips/lasat/interrupt.c b/arch/mips/lasat/interrupt.c index de4c165515d7..d608b6ef0edd 100644 --- a/arch/mips/lasat/interrupt.c +++ b/arch/mips/lasat/interrupt.c @@ -105,6 +105,7 @@ asmlinkage void plat_irq_dispatch(void) static struct irqaction cascade = { .handler = no_action, .name = "cascade", + .flags = IRQF_NO_THREAD, }; void __init arch_init_irq(void) diff --git a/arch/mips/loongson/fuloong-2e/irq.c b/arch/mips/loongson/fuloong-2e/irq.c index d61a04222b87..3cf1fef29f0e 100644 --- a/arch/mips/loongson/fuloong-2e/irq.c +++ b/arch/mips/loongson/fuloong-2e/irq.c @@ -42,6 +42,7 @@ asmlinkage void mach_irq_dispatch(unsigned int pending) static struct irqaction cascade_irqaction = { .handler = no_action, .name = "cascade", + .flags = IRQF_NO_THREAD, }; void __init mach_init_irq(void) diff --git a/arch/mips/loongson/lemote-2f/irq.c b/arch/mips/loongson/lemote-2f/irq.c index 081db102bb98..14b081841b6b 100644 --- a/arch/mips/loongson/lemote-2f/irq.c +++ b/arch/mips/loongson/lemote-2f/irq.c @@ -96,12 +96,13 @@ static irqreturn_t ip6_action(int cpl, void *dev_id) struct irqaction ip6_irqaction = { .handler = ip6_action, .name = "cascade", - .flags = IRQF_SHARED, + .flags = IRQF_SHARED | IRQF_NO_THREAD, }; struct irqaction cascade_irqaction = { .handler = no_action, .name = "cascade", + .flags = IRQF_NO_THREAD, }; void __init mach_init_irq(void) diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 9ff5d0fac556..302d779d5b0d 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -6,6 +6,7 @@ * Copyright (C) 2011 Wind River Systems, * written by Ralf Baechle <ralf@linux-mips.org> */ +#include <linux/compiler.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/mman.h> @@ -15,12 +16,11 @@ #include <linux/sched.h> unsigned long shm_align_mask = PAGE_SIZE - 1; /* Sane caches */ - EXPORT_SYMBOL(shm_align_mask); /* gap between mmap and stack */ #define MIN_GAP (128*1024*1024UL) -#define MAX_GAP ((TASK_SIZE)/6*5) +#define MAX_GAP ((TASK_SIZE)/6*5) static int mmap_is_legacy(void) { @@ -57,13 +57,13 @@ static inline unsigned long COLOUR_ALIGN_DOWN(unsigned long addr, return base - off; } -#define COLOUR_ALIGN(addr,pgoff) \ +#define COLOUR_ALIGN(addr, pgoff) \ ((((addr) + shm_align_mask) & ~shm_align_mask) + \ (((pgoff) << PAGE_SHIFT) & shm_align_mask)) enum mmap_allocation_direction {UP, DOWN}; -static unsigned long arch_get_unmapped_area_foo(struct file *filp, +static unsigned long arch_get_unmapped_area_common(struct file *filp, unsigned long addr0, unsigned long len, unsigned long pgoff, unsigned long flags, enum mmap_allocation_direction dir) { @@ -103,16 +103,16 @@ static unsigned long arch_get_unmapped_area_foo(struct file *filp, vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vma->vm_start)) return addr; } if (dir == UP) { addr = mm->mmap_base; - if (do_color_align) - addr = COLOUR_ALIGN(addr, pgoff); - else - addr = PAGE_ALIGN(addr); + if (do_color_align) + addr = COLOUR_ALIGN(addr, pgoff); + else + addr = PAGE_ALIGN(addr); for (vma = find_vma(current->mm, addr); ; vma = vma->vm_next) { /* At this point: (!vma || addr < vma->vm_end). */ @@ -131,28 +131,30 @@ static unsigned long arch_get_unmapped_area_foo(struct file *filp, mm->free_area_cache = mm->mmap_base; } - /* either no address requested or can't fit in requested address hole */ + /* + * either no address requested, or the mapping can't fit into + * the requested address hole + */ addr = mm->free_area_cache; - if (do_color_align) { - unsigned long base = - COLOUR_ALIGN_DOWN(addr - len, pgoff); - + if (do_color_align) { + unsigned long base = + COLOUR_ALIGN_DOWN(addr - len, pgoff); addr = base + len; - } + } /* make sure it can fit in the remaining address space */ if (likely(addr > len)) { vma = find_vma(mm, addr - len); if (!vma || addr <= vma->vm_start) { - /* remember the address as a hint for next time */ - return mm->free_area_cache = addr-len; + /* cache the address as a hint for next time */ + return mm->free_area_cache = addr - len; } } if (unlikely(mm->mmap_base < len)) goto bottomup; - addr = mm->mmap_base-len; + addr = mm->mmap_base - len; if (do_color_align) addr = COLOUR_ALIGN_DOWN(addr, pgoff); @@ -163,8 +165,8 @@ static unsigned long arch_get_unmapped_area_foo(struct file *filp, * return with success: */ vma = find_vma(mm, addr); - if (likely(!vma || addr+len <= vma->vm_start)) { - /* remember the address as a hint for next time */ + if (likely(!vma || addr + len <= vma->vm_start)) { + /* cache the address as a hint for next time */ return mm->free_area_cache = addr; } @@ -173,7 +175,7 @@ static unsigned long arch_get_unmapped_area_foo(struct file *filp, mm->cached_hole_size = vma->vm_start - addr; /* try just below the current vma->vm_start */ - addr = vma->vm_start-len; + addr = vma->vm_start - len; if (do_color_align) addr = COLOUR_ALIGN_DOWN(addr, pgoff); } while (likely(len < vma->vm_start)); @@ -201,7 +203,7 @@ bottomup: unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr0, unsigned long len, unsigned long pgoff, unsigned long flags) { - return arch_get_unmapped_area_foo(filp, + return arch_get_unmapped_area_common(filp, addr0, len, pgoff, flags, UP); } @@ -213,7 +215,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr0, unsigned long len, unsigned long pgoff, unsigned long flags) { - return arch_get_unmapped_area_foo(filp, + return arch_get_unmapped_area_common(filp, addr0, len, pgoff, flags, DOWN); } diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index b6e1cff50667..e06370f58ef3 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -1759,14 +1759,13 @@ static void __cpuinit build_r3000_tlb_modify_handler(void) u32 *p = handle_tlbm; struct uasm_label *l = labels; struct uasm_reloc *r = relocs; - struct work_registers wr; memset(handle_tlbm, 0, sizeof(handle_tlbm)); memset(labels, 0, sizeof(labels)); memset(relocs, 0, sizeof(relocs)); build_r3000_tlbchange_handler_head(&p, K0, K1); - build_pte_modifiable(&p, &r, wr.r1, wr.r2, wr.r3, label_nopage_tlbm); + build_pte_modifiable(&p, &r, K0, K1, -1, label_nopage_tlbm); uasm_i_nop(&p); /* load delay */ build_make_write(&p, &r, K0, K1); build_r3000_pte_reload_tlbwi(&p, K0, K1); @@ -1963,7 +1962,8 @@ static void __cpuinit build_r4000_tlb_load_handler(void) uasm_i_andi(&p, wr.r3, wr.r3, 2); uasm_il_beqz(&p, &r, wr.r3, label_tlbl_goaround2); } - + if (PM_DEFAULT_MASK == 0) + uasm_i_nop(&p); /* * We clobbered C0_PAGEMASK, restore it. On the other branch * it is restored in build_huge_tlb_write_entry. diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index 1d36c511a7a5..d53ff91b277c 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -350,12 +350,14 @@ unsigned int plat_ipi_resched_int_xlate(unsigned int cpu) static struct irqaction i8259irq = { .handler = no_action, - .name = "XT-PIC cascade" + .name = "XT-PIC cascade", + .flags = IRQF_NO_THREAD, }; static struct irqaction corehi_irqaction = { .handler = no_action, - .name = "CoreHi" + .name = "CoreHi", + .flags = IRQF_NO_THREAD, }; static msc_irqmap_t __initdata msc_irqmap[] = { diff --git a/arch/mips/netlogic/xlr/Makefile b/arch/mips/netlogic/xlr/Makefile index 9bd3f731f62e..2dca585dd2f7 100644 --- a/arch/mips/netlogic/xlr/Makefile +++ b/arch/mips/netlogic/xlr/Makefile @@ -2,4 +2,4 @@ obj-y += setup.o platform.o irq.o setup.o time.o obj-$(CONFIG_SMP) += smp.o smpboot.o obj-$(CONFIG_EARLY_PRINTK) += xlr_console.o -EXTRA_CFLAGS += -Werror +ccflags-y += -Werror diff --git a/arch/mips/pci/pci-bcm47xx.c b/arch/mips/pci/pci-bcm47xx.c index 455f8e50a007..400535a955d0 100644 --- a/arch/mips/pci/pci-bcm47xx.c +++ b/arch/mips/pci/pci-bcm47xx.c @@ -25,6 +25,7 @@ #include <linux/types.h> #include <linux/pci.h> #include <linux/ssb/ssb.h> +#include <bcm47xx.h> int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { @@ -33,9 +34,13 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) int pcibios_plat_dev_init(struct pci_dev *dev) { +#ifdef CONFIG_BCM47XX_SSB int res; u8 slot, pin; + if (bcm47xx_bus_type != BCM47XX_BUS_TYPE_SSB) + return 0; + res = ssb_pcibios_plat_dev_init(dev); if (res < 0) { printk(KERN_ALERT "PCI: Failed to init device %s\n", @@ -55,5 +60,6 @@ int pcibios_plat_dev_init(struct pci_dev *dev) } dev->irq = res; +#endif return 0; } diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c index 603d7493e966..8656388b34bd 100644 --- a/arch/mips/pci/pci-lantiq.c +++ b/arch/mips/pci/pci-lantiq.c @@ -171,8 +171,13 @@ static int __devinit ltq_pci_startup(struct ltq_pci_data *conf) u32 temp_buffer; /* set clock to 33Mhz */ - ltq_cgu_w32(ltq_cgu_r32(LTQ_CGU_IFCCR) & ~0xf00000, LTQ_CGU_IFCCR); - ltq_cgu_w32(ltq_cgu_r32(LTQ_CGU_IFCCR) | 0x800000, LTQ_CGU_IFCCR); + if (ltq_is_ar9()) { + ltq_cgu_w32(ltq_cgu_r32(LTQ_CGU_IFCCR) & ~0x1f00000, LTQ_CGU_IFCCR); + ltq_cgu_w32(ltq_cgu_r32(LTQ_CGU_IFCCR) | 0xe00000, LTQ_CGU_IFCCR); + } else { + ltq_cgu_w32(ltq_cgu_r32(LTQ_CGU_IFCCR) & ~0xf00000, LTQ_CGU_IFCCR); + ltq_cgu_w32(ltq_cgu_r32(LTQ_CGU_IFCCR) | 0x800000, LTQ_CGU_IFCCR); + } /* external or internal clock ? */ if (conf->clock) { diff --git a/arch/mips/pci/pci-rc32434.c b/arch/mips/pci/pci-rc32434.c index 764362ce5e40..5f3a69cebad1 100644 --- a/arch/mips/pci/pci-rc32434.c +++ b/arch/mips/pci/pci-rc32434.c @@ -215,7 +215,7 @@ static int __init rc32434_pci_init(void) rc32434_pcibridge_init(); io_map_base = ioremap(rc32434_res_pci_io1.start, - resource_size(&rcrc32434_res_pci_io1)); + resource_size(&rc32434_res_pci_io1)); if (!io_map_base) return -ENOMEM; diff --git a/arch/mips/pmc-sierra/msp71xx/msp_irq.c b/arch/mips/pmc-sierra/msp71xx/msp_irq.c index 4531c4a514bc..d3c3d81757a5 100644 --- a/arch/mips/pmc-sierra/msp71xx/msp_irq.c +++ b/arch/mips/pmc-sierra/msp71xx/msp_irq.c @@ -108,12 +108,14 @@ asmlinkage void plat_irq_dispatch(struct pt_regs *regs) static struct irqaction cic_cascade_msp = { .handler = no_action, - .name = "MSP CIC cascade" + .name = "MSP CIC cascade", + .flags = IRQF_NO_THREAD, }; static struct irqaction per_cascade_msp = { .handler = no_action, - .name = "MSP PER cascade" + .name = "MSP PER cascade", + .flags = IRQF_NO_THREAD, }; void __init arch_init_irq(void) diff --git a/arch/mips/pmc-sierra/msp71xx/msp_serial.c b/arch/mips/pmc-sierra/msp71xx/msp_serial.c index f7261628d8a6..a1c7c7da2336 100644 --- a/arch/mips/pmc-sierra/msp71xx/msp_serial.c +++ b/arch/mips/pmc-sierra/msp71xx/msp_serial.c @@ -27,6 +27,7 @@ #include <linux/serial.h> #include <linux/serial_core.h> #include <linux/serial_reg.h> +#include <linux/slab.h> #include <asm/bootinfo.h> #include <asm/io.h> @@ -38,6 +39,55 @@ #include <msp_int.h> #include <msp_regs.h> +struct msp_uart_data { + int last_lcr; +}; + +static void msp_serial_out(struct uart_port *p, int offset, int value) +{ + struct msp_uart_data *d = p->private_data; + + if (offset == UART_LCR) + d->last_lcr = value; + + offset <<= p->regshift; + writeb(value, p->membase + offset); +} + +static unsigned int msp_serial_in(struct uart_port *p, int offset) +{ + offset <<= p->regshift; + + return readb(p->membase + offset); +} + +static int msp_serial_handle_irq(struct uart_port *p) +{ + struct msp_uart_data *d = p->private_data; + unsigned int iir = readb(p->membase + (UART_IIR << p->regshift)); + + if (serial8250_handle_irq(p, iir)) { + return 1; + } else if ((iir & UART_IIR_BUSY) == UART_IIR_BUSY) { + /* + * The DesignWare APB UART has an Busy Detect (0x07) interrupt + * meaning an LCR write attempt occurred while the UART was + * busy. The interrupt must be cleared by reading the UART + * status register (USR) and the LCR re-written. + * + * Note: MSP reserves 0x20 bytes of address space for the UART + * and the USR is mapped in a separate block at an offset of + * 0xc0 from the start of the UART. + */ + (void)readb(p->membase + 0xc0); + writeb(d->last_lcr, p->membase + (UART_LCR << p->regshift)); + + return 1; + } + + return 0; +} + void __init msp_serial_setup(void) { char *s; @@ -59,13 +109,22 @@ void __init msp_serial_setup(void) up.irq = MSP_INT_UART0; up.uartclk = uartclk; up.regshift = 2; - up.iotype = UPIO_DWAPB; /* UPIO_MEM like */ + up.iotype = UPIO_MEM; up.flags = ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST; up.type = PORT_16550A; up.line = 0; - up.private_data = (void*)UART0_STATUS_REG; - if (early_serial_setup(&up)) - printk(KERN_ERR "Early serial init of port 0 failed\n"); + up.serial_out = msp_serial_out; + up.serial_in = msp_serial_in; + up.handle_irq = msp_serial_handle_irq; + up.private_data = kzalloc(sizeof(struct msp_uart_data), GFP_KERNEL); + if (!up.private_data) { + pr_err("failed to allocate uart private data\n"); + return; + } + if (early_serial_setup(&up)) { + kfree(up.private_data); + pr_err("Early serial init of port 0 failed\n"); + } /* Initialize the second serial port, if one exists */ switch (mips_machtype) { @@ -88,6 +147,8 @@ void __init msp_serial_setup(void) up.irq = MSP_INT_UART1; up.line = 1; up.private_data = (void*)UART1_STATUS_REG; - if (early_serial_setup(&up)) - printk(KERN_ERR "Early serial init of port 1 failed\n"); + if (early_serial_setup(&up)) { + kfree(up.private_data); + pr_err("Early serial init of port 1 failed\n"); + } } diff --git a/arch/mips/pnx8550/common/int.c b/arch/mips/pnx8550/common/int.c index 6b93c81779c1..1ebe22bdadc8 100644 --- a/arch/mips/pnx8550/common/int.c +++ b/arch/mips/pnx8550/common/int.c @@ -167,7 +167,7 @@ static struct irq_chip level_irq_type = { static struct irqaction gic_action = { .handler = no_action, - .flags = IRQF_DISABLED, + .flags = IRQF_DISABLED | IRQF_NO_THREAD, .name = "GIC", }; diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c index b4d08e4d2ea9..f72c336ea27b 100644 --- a/arch/mips/sgi-ip22/ip22-int.c +++ b/arch/mips/sgi-ip22/ip22-int.c @@ -155,32 +155,32 @@ static void __irq_entry indy_buserror_irq(void) static struct irqaction local0_cascade = { .handler = no_action, - .flags = IRQF_DISABLED, + .flags = IRQF_DISABLED | IRQF_NO_THREAD, .name = "local0 cascade", }; static struct irqaction local1_cascade = { .handler = no_action, - .flags = IRQF_DISABLED, + .flags = IRQF_DISABLED | IRQF_NO_THREAD, .name = "local1 cascade", }; static struct irqaction buserr = { .handler = no_action, - .flags = IRQF_DISABLED, + .flags = IRQF_DISABLED | IRQF_NO_THREAD, .name = "Bus Error", }; static struct irqaction map0_cascade = { .handler = no_action, - .flags = IRQF_DISABLED, + .flags = IRQF_DISABLED | IRQF_NO_THREAD, .name = "mapable0 cascade", }; #ifdef USE_LIO3_IRQ static struct irqaction map1_cascade = { .handler = no_action, - .flags = IRQF_DISABLED, + .flags = IRQF_DISABLED | IRQF_NO_THREAD, .name = "mapable1 cascade", }; #define SGI_INTERRUPTS SGINT_END diff --git a/arch/mips/sni/rm200.c b/arch/mips/sni/rm200.c index a7e5a6d917b1..3ab5b5d25b0a 100644 --- a/arch/mips/sni/rm200.c +++ b/arch/mips/sni/rm200.c @@ -359,6 +359,7 @@ void sni_rm200_init_8259A(void) static struct irqaction sni_rm200_irq2 = { .handler = no_action, .name = "cascade", + .flags = IRQF_NO_THREAD, }; static struct resource sni_rm200_pic1_resource = { diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c index e9f95dcde379..ba3cec3155df 100644 --- a/arch/mips/txx9/generic/setup_tx4939.c +++ b/arch/mips/txx9/generic/setup_tx4939.c @@ -321,7 +321,7 @@ void __init tx4939_sio_init(unsigned int sclk, unsigned int cts_mask) static u32 tx4939_get_eth_speed(struct net_device *dev) { struct ethtool_cmd cmd; - if (dev_ethtool_get_settings(dev, &cmd)) + if (__ethtool_get_settings(dev, &cmd)) return 100; /* default 100Mbps */ return ethtool_cmd_speed(&cmd); diff --git a/arch/mips/vr41xx/common/irq.c b/arch/mips/vr41xx/common/irq.c index 70a3b85f3757..fad2bef432cd 100644 --- a/arch/mips/vr41xx/common/irq.c +++ b/arch/mips/vr41xx/common/irq.c @@ -34,6 +34,7 @@ static irq_cascade_t irq_cascade[NR_IRQS] __cacheline_aligned; static struct irqaction cascade_irqaction = { .handler = no_action, .name = "cascade", + .flags = IRQF_NO_THREAD, }; int cascade_irq(unsigned int irq, int (*get_irq)(unsigned int)) diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig index 1f870340ebdd..438db84a1f7c 100644 --- a/arch/mn10300/Kconfig +++ b/arch/mn10300/Kconfig @@ -47,9 +47,6 @@ config GENERIC_CMOS_UPDATE config GENERIC_HWEIGHT def_bool y -config GENERIC_TIME - def_bool y - config GENERIC_CLOCKEVENTS def_bool y @@ -195,7 +192,7 @@ config SMP singleprocessor machines. On a singleprocessor machine, the kernel will run faster if you say N here. - See also <file:Documentation/i386/IO-APIC.txt>, + See also <file:Documentation/x86/i386/IO-APIC.txt>, <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at <http://www.tldp.org/docs.html#howto>. diff --git a/arch/mn10300/kernel/gdb-stub.c b/arch/mn10300/kernel/gdb-stub.c index 538266b2c9bc..522eb8a9b60d 100644 --- a/arch/mn10300/kernel/gdb-stub.c +++ b/arch/mn10300/kernel/gdb-stub.c @@ -798,7 +798,7 @@ unsigned char *mem2hex(const void *_mem, char *buf, int count, int may_fault) if ((u32) mem & 1 && count >= 1) { if (gdbstub_read_byte(mem, ch) != 0) return 0; - buf = pack_hex_byte(buf, ch[0]); + buf = hex_byte_pack(buf, ch[0]); mem++; count--; } @@ -806,8 +806,8 @@ unsigned char *mem2hex(const void *_mem, char *buf, int count, int may_fault) if ((u32) mem & 3 && count >= 2) { if (gdbstub_read_word(mem, ch) != 0) return 0; - buf = pack_hex_byte(buf, ch[0]); - buf = pack_hex_byte(buf, ch[1]); + buf = hex_byte_pack(buf, ch[0]); + buf = hex_byte_pack(buf, ch[1]); mem += 2; count -= 2; } @@ -815,10 +815,10 @@ unsigned char *mem2hex(const void *_mem, char *buf, int count, int may_fault) while (count >= 4) { if (gdbstub_read_dword(mem, ch) != 0) return 0; - buf = pack_hex_byte(buf, ch[0]); - buf = pack_hex_byte(buf, ch[1]); - buf = pack_hex_byte(buf, ch[2]); - buf = pack_hex_byte(buf, ch[3]); + buf = hex_byte_pack(buf, ch[0]); + buf = hex_byte_pack(buf, ch[1]); + buf = hex_byte_pack(buf, ch[2]); + buf = hex_byte_pack(buf, ch[3]); mem += 4; count -= 4; } @@ -826,8 +826,8 @@ unsigned char *mem2hex(const void *_mem, char *buf, int count, int may_fault) if (count >= 2) { if (gdbstub_read_word(mem, ch) != 0) return 0; - buf = pack_hex_byte(buf, ch[0]); - buf = pack_hex_byte(buf, ch[1]); + buf = hex_byte_pack(buf, ch[0]); + buf = hex_byte_pack(buf, ch[1]); mem += 2; count -= 2; } @@ -835,7 +835,7 @@ unsigned char *mem2hex(const void *_mem, char *buf, int count, int may_fault) if (count >= 1) { if (gdbstub_read_byte(mem, ch) != 0) return 0; - buf = pack_hex_byte(buf, ch[0]); + buf = hex_byte_pack(buf, ch[0]); } *buf = 0; @@ -1273,13 +1273,13 @@ static int gdbstub(struct pt_regs *regs, enum exception_code excep) ptr = mem2hex(title, ptr, sizeof(title) - 1, 0); hx = hex_asc_hi(excep >> 8); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_lo(excep >> 8); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_hi(excep); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_lo(excep); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); ptr = mem2hex(crlf, ptr, sizeof(crlf) - 1, 0); *ptr = 0; @@ -1291,21 +1291,21 @@ static int gdbstub(struct pt_regs *regs, enum exception_code excep) ptr = mem2hex(tbcberr, ptr, sizeof(tbcberr) - 1, 0); hx = hex_asc_hi(bcberr >> 24); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_lo(bcberr >> 24); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_hi(bcberr >> 16); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_lo(bcberr >> 16); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_hi(bcberr >> 8); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_lo(bcberr >> 8); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_hi(bcberr); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); hx = hex_asc_lo(bcberr); - ptr = pack_hex_byte(ptr, hx); + ptr = hex_byte_pack(ptr, hx); ptr = mem2hex(crlf, ptr, sizeof(crlf) - 1, 0); *ptr = 0; @@ -1321,12 +1321,12 @@ static int gdbstub(struct pt_regs *regs, enum exception_code excep) * Send trap type (converted to signal) */ *ptr++ = 'T'; - ptr = pack_hex_byte(ptr, sigval); + ptr = hex_byte_pack(ptr, sigval); /* * Send Error PC */ - ptr = pack_hex_byte(ptr, GDB_REGID_PC); + ptr = hex_byte_pack(ptr, GDB_REGID_PC); *ptr++ = ':'; ptr = mem2hex(®s->pc, ptr, 4, 0); *ptr++ = ';'; @@ -1334,7 +1334,7 @@ static int gdbstub(struct pt_regs *regs, enum exception_code excep) /* * Send frame pointer */ - ptr = pack_hex_byte(ptr, GDB_REGID_FP); + ptr = hex_byte_pack(ptr, GDB_REGID_FP); *ptr++ = ':'; ptr = mem2hex(®s->a3, ptr, 4, 0); *ptr++ = ';'; @@ -1343,7 +1343,7 @@ static int gdbstub(struct pt_regs *regs, enum exception_code excep) * Send stack pointer */ ssp = (unsigned long) (regs + 1); - ptr = pack_hex_byte(ptr, GDB_REGID_SP); + ptr = hex_byte_pack(ptr, GDB_REGID_SP); *ptr++ = ':'; ptr = mem2hex(&ssp, ptr, 4, 0); *ptr++ = ';'; diff --git a/arch/mn10300/kernel/irq.c b/arch/mn10300/kernel/irq.c index 2623d19f4f4c..2381df83bd00 100644 --- a/arch/mn10300/kernel/irq.c +++ b/arch/mn10300/kernel/irq.c @@ -260,7 +260,6 @@ void set_intr_level(int irq, u16 level) /* * mark an interrupt to be ACK'd after interrupt handlers have been run rather * than before - * - see Documentation/mn10300/features.txt */ void mn10300_set_lateack_irq_type(int irq) { diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index 4558bafbd1a2..9460e1c266dd 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -1,6 +1,6 @@ # # For a description of the syntax of this configuration file, -# see Documentation/kbuild/config-language.txt. +# see Documentation/kbuild/kconfig-language.txt. # config OPENRISC diff --git a/arch/openrisc/include/asm/dma-mapping.h b/arch/openrisc/include/asm/dma-mapping.h index 60b472233900..b206ba4608b2 100644 --- a/arch/openrisc/include/asm/dma-mapping.h +++ b/arch/openrisc/include/asm/dma-mapping.h @@ -18,7 +18,7 @@ #define __ASM_OPENRISC_DMA_MAPPING_H /* - * See Documentation/PCI/PCI-DMA-mapping.txt and + * See Documentation/DMA-API-HOWTO.txt and * Documentation/DMA-API.txt for documentation. * * This file is written with the intention of eventually moving over diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index e077b0bf56ca..fdfd8be29e95 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -169,9 +169,7 @@ config 64BIT choice prompt "Kernel page size" - default PARISC_PAGE_SIZE_4KB if !64BIT - default PARISC_PAGE_SIZE_4KB if 64BIT -# default PARISC_PAGE_SIZE_16KB if 64BIT + default PARISC_PAGE_SIZE_4KB config PARISC_PAGE_SIZE_4KB bool "4KB" diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index efa0b60c63fe..760f331d4fa3 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -105,7 +105,8 @@ struct compat_statfs { __kernel_fsid_t f_fsid; s32 f_namelen; s32 f_frsize; - s32 f_spare[5]; + s32 f_flags; + s32 f_spare[4]; }; struct compat_sigcontext { diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h index 890531e32fe8..467bbd510eac 100644 --- a/arch/parisc/include/asm/dma-mapping.h +++ b/arch/parisc/include/asm/dma-mapping.h @@ -5,7 +5,7 @@ #include <asm/cacheflush.h> #include <asm/scatterlist.h> -/* See Documentation/PCI/PCI-DMA-mapping.txt */ +/* See Documentation/DMA-API-HOWTO.txt */ struct hppa_dma_ops { int (*dma_supported)(struct device *dev, u64 mask); void *(*alloc_consistent)(struct device *dev, size_t size, dma_addr_t *iova, gfp_t flag); diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index a029f74a3c5c..d047edea2504 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -2,7 +2,7 @@ ** PARISC 1.1 Dynamic DMA mapping support. ** This implementation is for PA-RISC platforms that do not support ** I/O TLBs (aka DMA address translation hardware). -** See Documentation/PCI/PCI-DMA-mapping.txt for interface definitions. +** See Documentation/DMA-API-HOWTO.txt for interface definitions. ** ** (c) Copyright 1999,2000 Hewlett-Packard Company ** (c) Copyright 2000 Grant Grundler diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 6926b61acfea..47682b67fd36 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -656,6 +656,8 @@ config SBUS config FSL_SOC bool + select HAVE_CAN_FLEXCAN if NET && CAN + select PPC_CLOCK if CAN_FLEXCAN config FSL_PCI bool diff --git a/arch/powerpc/boot/dts/p1010rdb.dts b/arch/powerpc/boot/dts/p1010rdb.dts index 6b33b73a5ba0..d6c669c888e9 100644 --- a/arch/powerpc/boot/dts/p1010rdb.dts +++ b/arch/powerpc/boot/dts/p1010rdb.dts @@ -23,6 +23,8 @@ ethernet2 = &enet2; pci0 = &pci0; pci1 = &pci1; + can0 = &can0; + can1 = &can1; }; memory { @@ -169,14 +171,6 @@ }; }; - can0@1c000 { - fsl,flexcan-clock-source = "platform"; - }; - - can1@1d000 { - fsl,flexcan-clock-source = "platform"; - }; - usb@22000 { phy_type = "utmi"; }; diff --git a/arch/powerpc/boot/dts/p1010si.dtsi b/arch/powerpc/boot/dts/p1010si.dtsi index 7f51104f2e36..cabe0a453ae6 100644 --- a/arch/powerpc/boot/dts/p1010si.dtsi +++ b/arch/powerpc/boot/dts/p1010si.dtsi @@ -140,20 +140,18 @@ interrupt-parent = <&mpic>; }; - can0@1c000 { - compatible = "fsl,flexcan-v1.0"; + can0: can@1c000 { + compatible = "fsl,p1010-flexcan"; reg = <0x1c000 0x1000>; interrupts = <48 0x2>; interrupt-parent = <&mpic>; - fsl,flexcan-clock-divider = <2>; }; - can1@1d000 { - compatible = "fsl,flexcan-v1.0"; + can1: can@1d000 { + compatible = "fsl,p1010-flexcan"; reg = <0x1d000 0x1000>; interrupts = <61 0x2>; interrupt-parent = <&mpic>; - fsl,flexcan-clock-divider = <2>; }; L2: l2-cache-controller@20000 { diff --git a/arch/powerpc/configs/40x/acadia_defconfig b/arch/powerpc/configs/40x/acadia_defconfig index 4182c772340b..ed3bab72a834 100644 --- a/arch/powerpc/configs/40x/acadia_defconfig +++ b/arch/powerpc/configs/40x/acadia_defconfig @@ -44,12 +44,13 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 # CONFIG_MISC_DEVICES is not set CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y CONFIG_MII=y -CONFIG_IBM_NEW_EMAC=y -CONFIG_IBM_NEW_EMAC_RXB=256 -CONFIG_IBM_NEW_EMAC_TXB=256 -CONFIG_IBM_NEW_EMAC_DEBUG=y +CONFIG_IBM_EMAC=y +CONFIG_IBM_EMAC_RXB=256 +CONFIG_IBM_EMAC_TXB=256 +CONFIG_IBM_EMAC_DEBUG=y # CONFIG_NETDEV_1000 is not set # CONFIG_NETDEV_10000 is not set # CONFIG_INPUT is not set diff --git a/arch/powerpc/configs/40x/ep405_defconfig b/arch/powerpc/configs/40x/ep405_defconfig index 2dbb293163f5..17582a3420fb 100644 --- a/arch/powerpc/configs/40x/ep405_defconfig +++ b/arch/powerpc/configs/40x/ep405_defconfig @@ -42,8 +42,9 @@ CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/powerpc/configs/40x/hcu4_defconfig b/arch/powerpc/configs/40x/hcu4_defconfig index ebeb4accad65..dba263c1d3a2 100644 --- a/arch/powerpc/configs/40x/hcu4_defconfig +++ b/arch/powerpc/configs/40x/hcu4_defconfig @@ -43,8 +43,9 @@ CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/powerpc/configs/40x/kilauea_defconfig b/arch/powerpc/configs/40x/kilauea_defconfig index 532ea9d93a15..f2d4be936e08 100644 --- a/arch/powerpc/configs/40x/kilauea_defconfig +++ b/arch/powerpc/configs/40x/kilauea_defconfig @@ -51,10 +51,11 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 # CONFIG_MISC_DEVICES is not set CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y -CONFIG_IBM_NEW_EMAC_RXB=256 -CONFIG_IBM_NEW_EMAC_TXB=256 +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y +CONFIG_IBM_EMAC_RXB=256 +CONFIG_IBM_EMAC_TXB=256 # CONFIG_NETDEV_1000 is not set # CONFIG_NETDEV_10000 is not set # CONFIG_INPUT is not set diff --git a/arch/powerpc/configs/40x/makalu_defconfig b/arch/powerpc/configs/40x/makalu_defconfig index 3c142ac1b344..42b979355f9b 100644 --- a/arch/powerpc/configs/40x/makalu_defconfig +++ b/arch/powerpc/configs/40x/makalu_defconfig @@ -43,10 +43,11 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 # CONFIG_MISC_DEVICES is not set CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y -CONFIG_IBM_NEW_EMAC_RXB=256 -CONFIG_IBM_NEW_EMAC_TXB=256 +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y +CONFIG_IBM_EMAC_RXB=256 +CONFIG_IBM_EMAC_TXB=256 # CONFIG_NETDEV_1000 is not set # CONFIG_NETDEV_10000 is not set # CONFIG_INPUT is not set diff --git a/arch/powerpc/configs/40x/walnut_defconfig b/arch/powerpc/configs/40x/walnut_defconfig index ff57d4828ffc..aa1a4cac3708 100644 --- a/arch/powerpc/configs/40x/walnut_defconfig +++ b/arch/powerpc/configs/40x/walnut_defconfig @@ -40,8 +40,9 @@ CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/powerpc/configs/44x/arches_defconfig b/arch/powerpc/configs/44x/arches_defconfig index 3ed16d5c909d..329f9a3b892e 100644 --- a/arch/powerpc/configs/44x/arches_defconfig +++ b/arch/powerpc/configs/44x/arches_defconfig @@ -44,10 +44,11 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 # CONFIG_MISC_DEVICES is not set CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y -CONFIG_IBM_NEW_EMAC_RXB=256 -CONFIG_IBM_NEW_EMAC_TXB=256 +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y +CONFIG_IBM_EMAC_RXB=256 +CONFIG_IBM_EMAC_TXB=256 # CONFIG_NETDEV_1000 is not set # CONFIG_NETDEV_10000 is not set # CONFIG_INPUT is not set diff --git a/arch/powerpc/configs/44x/bamboo_defconfig b/arch/powerpc/configs/44x/bamboo_defconfig index b1b7d2c5c059..cef7d62560c4 100644 --- a/arch/powerpc/configs/44x/bamboo_defconfig +++ b/arch/powerpc/configs/44x/bamboo_defconfig @@ -32,8 +32,9 @@ CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/powerpc/configs/44x/bluestone_defconfig b/arch/powerpc/configs/44x/bluestone_defconfig index 30a0a8e08fdd..20c8d26d7fc0 100644 --- a/arch/powerpc/configs/44x/bluestone_defconfig +++ b/arch/powerpc/configs/44x/bluestone_defconfig @@ -38,10 +38,11 @@ CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y -CONFIG_IBM_NEW_EMAC_RXB=256 -CONFIG_IBM_NEW_EMAC_TXB=256 +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y +CONFIG_IBM_EMAC_RXB=256 +CONFIG_IBM_EMAC_TXB=256 CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=2 diff --git a/arch/powerpc/configs/44x/canyonlands_defconfig b/arch/powerpc/configs/44x/canyonlands_defconfig index a46942aac695..d5be93e6e92d 100644 --- a/arch/powerpc/configs/44x/canyonlands_defconfig +++ b/arch/powerpc/configs/44x/canyonlands_defconfig @@ -49,10 +49,11 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 # CONFIG_MISC_DEVICES is not set CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y -CONFIG_IBM_NEW_EMAC_RXB=256 -CONFIG_IBM_NEW_EMAC_TXB=256 +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y +CONFIG_IBM_EMAC_RXB=256 +CONFIG_IBM_EMAC_TXB=256 # CONFIG_NETDEV_1000 is not set # CONFIG_NETDEV_10000 is not set # CONFIG_INPUT is not set diff --git a/arch/powerpc/configs/44x/ebony_defconfig b/arch/powerpc/configs/44x/ebony_defconfig index 07d77e51f1ba..f9269fc4ffcc 100644 --- a/arch/powerpc/configs/44x/ebony_defconfig +++ b/arch/powerpc/configs/44x/ebony_defconfig @@ -40,8 +40,9 @@ CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/powerpc/configs/44x/eiger_defconfig b/arch/powerpc/configs/44x/eiger_defconfig index 2ce7e9aff09e..9be089038fd7 100644 --- a/arch/powerpc/configs/44x/eiger_defconfig +++ b/arch/powerpc/configs/44x/eiger_defconfig @@ -55,10 +55,11 @@ CONFIG_FUSION=y CONFIG_FUSION_SAS=y CONFIG_I2O=y CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y -CONFIG_IBM_NEW_EMAC_RXB=256 -CONFIG_IBM_NEW_EMAC_TXB=256 +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y +CONFIG_IBM_EMAC_RXB=256 +CONFIG_IBM_EMAC_TXB=256 CONFIG_E1000E=y # CONFIG_NETDEV_10000 is not set # CONFIG_INPUT is not set diff --git a/arch/powerpc/configs/44x/icon_defconfig b/arch/powerpc/configs/44x/icon_defconfig index 18730ff9de7c..82f73035a7ce 100644 --- a/arch/powerpc/configs/44x/icon_defconfig +++ b/arch/powerpc/configs/44x/icon_defconfig @@ -56,8 +56,9 @@ CONFIG_FUSION_SAS=y CONFIG_FUSION_CTL=y CONFIG_FUSION_LOGGING=y CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_NETDEV_1000 is not set # CONFIG_NETDEV_10000 is not set # CONFIG_WLAN is not set diff --git a/arch/powerpc/configs/44x/katmai_defconfig b/arch/powerpc/configs/44x/katmai_defconfig index 34c09144a699..109562c3c6be 100644 --- a/arch/powerpc/configs/44x/katmai_defconfig +++ b/arch/powerpc/configs/44x/katmai_defconfig @@ -42,8 +42,9 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 CONFIG_MACINTOSH_DRIVERS=y CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/powerpc/configs/44x/redwood_defconfig b/arch/powerpc/configs/44x/redwood_defconfig index 01cc2b1a7f9a..48802811da76 100644 --- a/arch/powerpc/configs/44x/redwood_defconfig +++ b/arch/powerpc/configs/44x/redwood_defconfig @@ -53,11 +53,12 @@ CONFIG_FUSION=y CONFIG_FUSION_SAS=y CONFIG_I2O=y CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y -CONFIG_IBM_NEW_EMAC_RXB=256 -CONFIG_IBM_NEW_EMAC_TXB=256 -CONFIG_IBM_NEW_EMAC_DEBUG=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y +CONFIG_IBM_EMAC_RXB=256 +CONFIG_IBM_EMAC_TXB=256 +CONFIG_IBM_EMAC_DEBUG=y CONFIG_E1000E=y # CONFIG_NETDEV_10000 is not set # CONFIG_INPUT is not set diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig index dfcffede16ad..ca088cd581af 100644 --- a/arch/powerpc/configs/44x/sam440ep_defconfig +++ b/arch/powerpc/configs/44x/sam440ep_defconfig @@ -44,8 +44,9 @@ CONFIG_ATA=y # CONFIG_SATA_PMP is not set CONFIG_SATA_SIL=y CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_NETDEV_1000 is not set # CONFIG_NETDEV_10000 is not set CONFIG_INPUT_FF_MEMLESS=m diff --git a/arch/powerpc/configs/44x/sequoia_defconfig b/arch/powerpc/configs/44x/sequoia_defconfig index 47e399f2892f..b7a653b626db 100644 --- a/arch/powerpc/configs/44x/sequoia_defconfig +++ b/arch/powerpc/configs/44x/sequoia_defconfig @@ -46,8 +46,9 @@ CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/powerpc/configs/44x/taishan_defconfig b/arch/powerpc/configs/44x/taishan_defconfig index a6a002ed5681..30de97f158a4 100644 --- a/arch/powerpc/configs/44x/taishan_defconfig +++ b/arch/powerpc/configs/44x/taishan_defconfig @@ -40,8 +40,9 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 CONFIG_MACINTOSH_DRIVERS=y CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig index abf74dc1f79c..105bc56f4b2b 100644 --- a/arch/powerpc/configs/44x/warp_defconfig +++ b/arch/powerpc/configs/44x/warp_defconfig @@ -54,9 +54,10 @@ CONFIG_BLK_DEV_SD=y CONFIG_SCSI_SPI_ATTRS=y # CONFIG_SCSI_LOWLEVEL is not set CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y CONFIG_MII=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_IBM_EMAC=y # CONFIG_NETDEV_1000 is not set # CONFIG_NETDEV_10000 is not set # CONFIG_INPUT is not set diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig index bfd634b5ada7..7cb703b948b1 100644 --- a/arch/powerpc/configs/ppc40x_defconfig +++ b/arch/powerpc/configs/ppc40x_defconfig @@ -50,8 +50,9 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=35000 CONFIG_XILINX_SYSACE=m CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_INPUT is not set CONFIG_SERIO=m # CONFIG_SERIO_I8042 is not set diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig index 47133202a625..6cdf1c0d2c8a 100644 --- a/arch/powerpc/configs/ppc44x_defconfig +++ b/arch/powerpc/configs/ppc44x_defconfig @@ -63,8 +63,9 @@ CONFIG_BLK_DEV_SD=m # CONFIG_SCSI_LOWLEVEL is not set CONFIG_NETDEVICES=y CONFIG_TUN=m -CONFIG_NET_ETHERNET=y -CONFIG_IBM_NEW_EMAC=y +CONFIG_ETHERNET=y +CONFIG_NET_VENDOR_IBM=y +CONFIG_IBM_EMAC=y # CONFIG_INPUT is not set CONFIG_SERIO=m # CONFIG_SERIO_I8042 is not set diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 91010e8f8479..88e602f6430d 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -100,7 +100,8 @@ struct compat_statfs { compat_fsid_t f_fsid; int f_namelen; /* SunOS ignores this field. */ int f_frsize; - int f_spare[5]; + int f_flags; + int f_spare[4]; }; #define COMPAT_RLIM_OLD_INFINITY 0x7fffffff diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h index a4f6c85431f8..08fe69edcd10 100644 --- a/arch/powerpc/include/asm/kvm.h +++ b/arch/powerpc/include/asm/kvm.h @@ -149,6 +149,12 @@ struct kvm_regs { #define KVM_SREGS_E_UPDATE_DBSR (1 << 3) /* + * Book3S special bits to indicate contents in the struct by maintaining + * backwards compatibility with older structs. If adding a new field, + * please make sure to add a flag for that new field */ +#define KVM_SREGS_S_HIOR (1 << 0) + +/* * In KVM_SET_SREGS, reserved/pad fields must be left untouched from a * previous KVM_GET_REGS. * @@ -173,6 +179,8 @@ struct kvm_sregs { __u64 ibat[8]; __u64 dbat[8]; } ppc32; + __u64 flags; /* KVM_SREGS_S_ */ + __u64 hior; } s; struct { union { @@ -276,6 +284,11 @@ struct kvm_guest_debug_arch { #define KVM_INTERRUPT_UNSET -2U #define KVM_INTERRUPT_SET_LEVEL -3U +#define KVM_CPU_440 1 +#define KVM_CPU_E500V2 2 +#define KVM_CPU_3S_32 3 +#define KVM_CPU_3S_64 4 + /* for KVM_CAP_SPAPR_TCE */ struct kvm_create_spapr_tce { __u64 liobn; diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 98da010252a3..a384ffdf33de 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -90,6 +90,8 @@ struct kvmppc_vcpu_book3s { #endif int context_id[SID_CONTEXTS]; + bool hior_sregs; /* HIOR is set by SREGS, not PVR */ + struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE]; struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG]; struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE]; @@ -139,15 +141,14 @@ extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu); extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); -extern void kvmppc_handler_lowmem_trampoline(void); -extern void kvmppc_handler_trampoline_enter(void); -extern void kvmppc_rmcall(ulong srr0, ulong srr1); +extern void kvmppc_entry_trampoline(void); extern void kvmppc_hv_entry_trampoline(void); extern void kvmppc_load_up_fpu(void); extern void kvmppc_load_up_altivec(void); extern void kvmppc_load_up_vsx(void); extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst); extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst); +extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd); static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) { @@ -382,6 +383,39 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu) } #endif +static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, + unsigned long pte_index) +{ + unsigned long rb, va_low; + + rb = (v & ~0x7fUL) << 16; /* AVA field */ + va_low = pte_index >> 3; + if (v & HPTE_V_SECONDARY) + va_low = ~va_low; + /* xor vsid from AVA */ + if (!(v & HPTE_V_1TB_SEG)) + va_low ^= v >> 12; + else + va_low ^= v >> 24; + va_low &= 0x7ff; + if (v & HPTE_V_LARGE) { + rb |= 1; /* L field */ + if (cpu_has_feature(CPU_FTR_ARCH_206) && + (r & 0xff000)) { + /* non-16MB large page, must be 64k */ + /* (masks depend on page size) */ + rb |= 0x1000; /* page encoding in LP field */ + rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */ + rb |= (va_low & 0xfe); /* AVAL field (P7 doesn't seem to care) */ + } + } else { + /* 4kB page */ + rb |= (va_low & 0x7ff) << 12; /* remaining 11b of VA */ + } + rb |= (v >> 54) & 0x300; /* B field */ + return rb; +} + /* Magic register values loaded into r3 and r4 before the 'sc' assembly * instruction for the OSI hypercalls */ #define OSI_SC_MAGIC_R3 0x113724FA diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index ef7b3688c3b6..1f2f5b6156bd 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -75,6 +75,8 @@ struct kvmppc_host_state { ulong scratch0; ulong scratch1; u8 in_guest; + u8 restore_hid5; + u8 napping; #ifdef CONFIG_KVM_BOOK3S_64_HV struct kvm_vcpu *kvm_vcpu; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index cc22b282d755..bf8af5d5d5dc 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -198,21 +198,29 @@ struct kvm_arch { */ struct kvmppc_vcore { int n_runnable; - int n_blocked; + int n_busy; int num_threads; int entry_exit_count; int n_woken; int nap_count; + int napping_threads; u16 pcpu; - u8 vcore_running; + u8 vcore_state; u8 in_guest; struct list_head runnable_threads; spinlock_t lock; + wait_queue_head_t wq; }; #define VCORE_ENTRY_COUNT(vc) ((vc)->entry_exit_count & 0xff) #define VCORE_EXIT_COUNT(vc) ((vc)->entry_exit_count >> 8) +/* Values for vcore_state */ +#define VCORE_INACTIVE 0 +#define VCORE_RUNNING 1 +#define VCORE_EXITING 2 +#define VCORE_SLEEPING 3 + struct kvmppc_pte { ulong eaddr; u64 vpage; @@ -258,14 +266,6 @@ struct kvm_vcpu_arch { ulong host_stack; u32 host_pid; #ifdef CONFIG_PPC_BOOK3S - ulong host_msr; - ulong host_r2; - void *host_retip; - ulong trampoline_lowmem; - ulong trampoline_enter; - ulong highmem_handler; - ulong rmcall; - ulong host_paca_phys; struct kvmppc_slb slb[64]; int slb_max; /* 1 + index of last valid entry in slb[] */ int slb_nr; /* total number of entries in SLB */ @@ -389,6 +389,9 @@ struct kvm_vcpu_arch { u8 dcr_is_write; u8 osi_needed; u8 osi_enabled; + u8 papr_enabled; + u8 sane; + u8 cpu_type; u8 hcall_needed; u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */ @@ -408,11 +411,13 @@ struct kvm_vcpu_arch { struct dtl *dtl; struct dtl *dtl_end; + wait_queue_head_t *wqp; struct kvmppc_vcore *vcore; int ret; int trap; int state; int ptid; + bool timer_running; wait_queue_head_t cpu_run; struct kvm_vcpu_arch_shared *shared; @@ -428,8 +433,9 @@ struct kvm_vcpu_arch { #endif }; -#define KVMPPC_VCPU_BUSY_IN_HOST 0 -#define KVMPPC_VCPU_BLOCKED 1 +/* Values for vcpu->arch.state */ +#define KVMPPC_VCPU_STOPPED 0 +#define KVMPPC_VCPU_BUSY_IN_HOST 1 #define KVMPPC_VCPU_RUNNABLE 2 #endif /* __POWERPC_KVM_HOST_H__ */ diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index d121f49d62b8..46efd1a265c9 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -66,6 +66,7 @@ extern int kvmppc_emulate_instruction(struct kvm_run *run, extern int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu); extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu); extern u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb); +extern int kvmppc_sanity_check(struct kvm_vcpu *vcpu); /* Core-specific hooks */ diff --git a/arch/powerpc/include/asm/qe.h b/arch/powerpc/include/asm/qe.h index 0947b36e534c..5e0b6d511e14 100644 --- a/arch/powerpc/include/asm/qe.h +++ b/arch/powerpc/include/asm/qe.h @@ -196,7 +196,7 @@ static inline int qe_alive_during_sleep(void) /* Structure that defines QE firmware binary files. * - * See Documentation/powerpc/qe-firmware.txt for a description of these + * See Documentation/powerpc/qe_firmware.txt for a description of these * fields. */ struct qe_firmware { diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index fa0d27a400de..559ae1ee6706 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -354,3 +354,5 @@ COMPAT_SYS_SPU(clock_adjtime) SYSCALL_SPU(syncfs) COMPAT_SYS_SPU(sendmmsg) SYSCALL_SPU(setns) +COMPAT_SYS(process_vm_readv) +COMPAT_SYS(process_vm_writev) diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h index 93e05d1b34b2..5354ae91bdde 100644 --- a/arch/powerpc/include/asm/udbg.h +++ b/arch/powerpc/include/asm/udbg.h @@ -54,6 +54,7 @@ extern void __init udbg_init_40x_realmode(void); extern void __init udbg_init_cpm(void); extern void __init udbg_init_usbgecko(void); extern void __init udbg_init_wsp(void); +extern void __init udbg_init_ehv_bc(void); #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_UDBG_H */ diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index b8b3f599362b..d3d1b5efd7eb 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -373,10 +373,12 @@ #define __NR_syncfs 348 #define __NR_sendmmsg 349 #define __NR_setns 350 +#define __NR_process_vm_readv 351 +#define __NR_process_vm_writev 352 #ifdef __KERNEL__ -#define __NR_syscalls 351 +#define __NR_syscalls 353 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 5f078bc2063e..69f7ffe7f674 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -44,6 +44,7 @@ #include <asm/compat.h> #include <asm/mmu.h> #include <asm/hvcall.h> +#include <asm/xics.h> #endif #ifdef CONFIG_PPC_ISERIES #include <asm/iseries/alpaca.h> @@ -449,8 +450,6 @@ int main(void) #ifdef CONFIG_PPC_BOOK3S DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm)); DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id)); - DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip)); - DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr)); DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr)); DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr)); DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr)); @@ -458,14 +457,12 @@ int main(void) DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor)); DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl)); DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr)); - DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem)); - DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter)); - DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler)); - DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall)); DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags)); DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec)); DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires)); DEFINE(VCPU_PENDING_EXC, offsetof(struct kvm_vcpu, arch.pending_exceptions)); + DEFINE(VCPU_CEDED, offsetof(struct kvm_vcpu, arch.ceded)); + DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded)); DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa)); DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr)); DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc)); @@ -481,6 +478,7 @@ int main(void) DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count)); DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count)); DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest)); + DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads)); DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) - offsetof(struct kvmppc_vcpu_book3s, vcpu)); DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige)); @@ -537,6 +535,8 @@ int main(void) HSTATE_FIELD(HSTATE_SCRATCH0, scratch0); HSTATE_FIELD(HSTATE_SCRATCH1, scratch1); HSTATE_FIELD(HSTATE_IN_GUEST, in_guest); + HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5); + HSTATE_FIELD(HSTATE_NAPPING, napping); #ifdef CONFIG_KVM_BOOK3S_64_HV HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu); @@ -549,6 +549,7 @@ int main(void) HSTATE_FIELD(HSTATE_DSCR, host_dscr); HSTATE_FIELD(HSTATE_DABR, dabr); HSTATE_FIELD(HSTATE_DECEXP, dec_expires); + DEFINE(IPI_PRIORITY, IPI_PRIORITY); #endif /* CONFIG_KVM_BOOK3S_64_HV */ #else /* CONFIG_PPC_BOOK3S */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 41b02c792aa3..29ddd8b1c274 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -427,16 +427,6 @@ slb_miss_user_pseries: b . /* prevent spec. execution */ #endif /* __DISABLED__ */ -/* KVM's trampoline code needs to be close to the interrupt handlers */ - -#ifdef CONFIG_KVM_BOOK3S_64_HANDLER -#ifdef CONFIG_KVM_BOOK3S_PR -#include "../kvm/book3s_rmhandlers.S" -#else -#include "../kvm/book3s_hv_rmhandlers.S" -#endif -#endif - .align 7 .globl __end_interrupts __end_interrupts: diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index faa82c1f3f68..b4607a91d1f4 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -67,6 +67,8 @@ void __init udbg_early_init(void) udbg_init_usbgecko(); #elif defined(CONFIG_PPC_EARLY_DEBUG_WSP) udbg_init_wsp(); +#elif defined(CONFIG_PPC_EARLY_DEBUG_EHV_BC) + udbg_init_ehv_bc(); #endif #ifdef CONFIG_PPC_EARLY_DEBUG diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c index da3a1225c0ac..ca1f88b3dc59 100644 --- a/arch/powerpc/kvm/44x.c +++ b/arch/powerpc/kvm/44x.c @@ -78,6 +78,8 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu) for (i = 0; i < ARRAY_SIZE(vcpu_44x->shadow_refs); i++) vcpu_44x->shadow_refs[i].gtlb_index = -1; + vcpu->arch.cpu_type = KVM_CPU_440; + return 0; } diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 08428e2c188d..3688aeecc4b2 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -43,18 +43,22 @@ kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \ fpu.o \ book3s_paired_singles.o \ book3s_pr.o \ + book3s_pr_papr.o \ book3s_emulate.o \ book3s_interrupts.o \ book3s_mmu_hpte.o \ book3s_64_mmu_host.o \ book3s_64_mmu.o \ book3s_32_mmu.o +kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \ + book3s_rmhandlers.o kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \ book3s_hv.o \ book3s_hv_interrupts.o \ book3s_64_mmu_hv.o kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \ + book3s_hv_rmhandlers.o \ book3s_hv_rm_mmu.o \ book3s_64_vio_hv.o \ book3s_hv_builtin.o diff --git a/arch/powerpc/kvm/book3s_32_sr.S b/arch/powerpc/kvm/book3s_32_sr.S index 3608471ad2d8..7e06a6fc8d07 100644 --- a/arch/powerpc/kvm/book3s_32_sr.S +++ b/arch/powerpc/kvm/book3s_32_sr.S @@ -31,7 +31,7 @@ * R1 = host R1 * R2 = host R2 * R3 = shadow vcpu - * all other volatile GPRS = free + * all other volatile GPRS = free except R4, R6 * SVCPU[CR] = guest CR * SVCPU[XER] = guest XER * SVCPU[CTR] = guest CTR diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index c6d3e194b6b4..b871721c0050 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -128,7 +128,13 @@ static hva_t kvmppc_mmu_book3s_64_get_pteg( dprintk("MMU: page=0x%x sdr1=0x%llx pteg=0x%llx vsid=0x%llx\n", page, vcpu_book3s->sdr1, pteg, slbe->vsid); - r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT); + /* When running a PAPR guest, SDR1 contains a HVA address instead + of a GPA */ + if (vcpu_book3s->vcpu.arch.papr_enabled) + r = pteg; + else + r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT); + if (kvm_is_error_hva(r)) return r; return r | (pteg & ~PAGE_MASK); diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S index 04e7d3bbfe8b..f2e6e48ea463 100644 --- a/arch/powerpc/kvm/book3s_64_slb.S +++ b/arch/powerpc/kvm/book3s_64_slb.S @@ -53,7 +53,7 @@ slb_exit_skip_ ## num: * R1 = host R1 * R2 = host R2 * R3 = shadow vcpu - * all other volatile GPRS = free + * all other volatile GPRS = free except R4, R6 * SVCPU[CR] = guest CR * SVCPU[XER] = guest XER * SVCPU[CTR] = guest CTR diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 466846557089..0c9dc62532d0 100644 --- a/arch/powerpc/kvm/book3s_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -63,6 +63,25 @@ * function pointers, so let's just disable the define. */ #undef mfsrin +enum priv_level { + PRIV_PROBLEM = 0, + PRIV_SUPER = 1, + PRIV_HYPER = 2, +}; + +static bool spr_allowed(struct kvm_vcpu *vcpu, enum priv_level level) +{ + /* PAPR VMs only access supervisor SPRs */ + if (vcpu->arch.papr_enabled && (level > PRIV_SUPER)) + return false; + + /* Limit user space to its own small SPR set */ + if ((vcpu->arch.shared->msr & MSR_PR) && level > PRIV_PROBLEM) + return false; + + return true; +} + int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int inst, int *advance) { @@ -296,6 +315,8 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) switch (sprn) { case SPRN_SDR1: + if (!spr_allowed(vcpu, PRIV_HYPER)) + goto unprivileged; to_book3s(vcpu)->sdr1 = spr_val; break; case SPRN_DSISR: @@ -390,6 +411,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) case SPRN_PMC4_GEKKO: case SPRN_WPAR_GEKKO: break; +unprivileged: default: printk(KERN_INFO "KVM: invalid SPR write: %d\n", sprn); #ifndef DEBUG_SPR @@ -421,6 +443,8 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) break; } case SPRN_SDR1: + if (!spr_allowed(vcpu, PRIV_HYPER)) + goto unprivileged; kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1); break; case SPRN_DSISR: @@ -449,6 +473,10 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) case SPRN_HID5: kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[5]); break; + case SPRN_CFAR: + case SPRN_PURR: + kvmppc_set_gpr(vcpu, rt, 0); + break; case SPRN_GQR0: case SPRN_GQR1: case SPRN_GQR2: @@ -476,6 +504,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) kvmppc_set_gpr(vcpu, rt, 0); break; default: +unprivileged: printk(KERN_INFO "KVM: invalid SPR read: %d\n", sprn); #ifndef DEBUG_SPR emulated = EMULATE_FAIL; diff --git a/arch/powerpc/kvm/book3s_exports.c b/arch/powerpc/kvm/book3s_exports.c index 88c8f26add02..f7f63a00ab1f 100644 --- a/arch/powerpc/kvm/book3s_exports.c +++ b/arch/powerpc/kvm/book3s_exports.c @@ -23,9 +23,7 @@ #ifdef CONFIG_KVM_BOOK3S_64_HV EXPORT_SYMBOL_GPL(kvmppc_hv_entry_trampoline); #else -EXPORT_SYMBOL_GPL(kvmppc_handler_trampoline_enter); -EXPORT_SYMBOL_GPL(kvmppc_handler_lowmem_trampoline); -EXPORT_SYMBOL_GPL(kvmppc_rmcall); +EXPORT_SYMBOL_GPL(kvmppc_entry_trampoline); EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu); #ifdef CONFIG_ALTIVEC EXPORT_SYMBOL_GPL(kvmppc_load_up_altivec); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index cc0d7f1b19ab..4644c7986d80 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -62,6 +62,8 @@ /* #define EXIT_DEBUG_SIMPLE */ /* #define EXIT_DEBUG_INT */ +static void kvmppc_end_cede(struct kvm_vcpu *vcpu); + void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { local_paca->kvm_hstate.kvm_vcpu = vcpu; @@ -72,40 +74,10 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu) { } -static void kvmppc_vcpu_blocked(struct kvm_vcpu *vcpu); -static void kvmppc_vcpu_unblocked(struct kvm_vcpu *vcpu); - -void kvmppc_vcpu_block(struct kvm_vcpu *vcpu) -{ - u64 now; - unsigned long dec_nsec; - - now = get_tb(); - if (now >= vcpu->arch.dec_expires && !kvmppc_core_pending_dec(vcpu)) - kvmppc_core_queue_dec(vcpu); - if (vcpu->arch.pending_exceptions) - return; - if (vcpu->arch.dec_expires != ~(u64)0) { - dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC / - tb_ticks_per_sec; - hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec), - HRTIMER_MODE_REL); - } - - kvmppc_vcpu_blocked(vcpu); - - kvm_vcpu_block(vcpu); - vcpu->stat.halt_wakeup++; - - if (vcpu->arch.dec_expires != ~(u64)0) - hrtimer_try_to_cancel(&vcpu->arch.dec_timer); - - kvmppc_vcpu_unblocked(vcpu); -} - void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr) { vcpu->arch.shregs.msr = msr; + kvmppc_end_cede(vcpu); } void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) @@ -257,15 +229,6 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) switch (req) { case H_CEDE: - vcpu->arch.shregs.msr |= MSR_EE; - vcpu->arch.ceded = 1; - smp_mb(); - if (!vcpu->arch.prodded) - kvmppc_vcpu_block(vcpu); - else - vcpu->arch.prodded = 0; - smp_mb(); - vcpu->arch.ceded = 0; break; case H_PROD: target = kvmppc_get_gpr(vcpu, 4); @@ -388,20 +351,6 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, break; } - - if (!(r & RESUME_HOST)) { - /* To avoid clobbering exit_reason, only check for signals if - * we aren't already exiting to userspace for some other - * reason. */ - if (signal_pending(tsk)) { - vcpu->stat.signal_exits++; - run->exit_reason = KVM_EXIT_INTR; - r = -EINTR; - } else { - kvmppc_core_deliver_interrupts(vcpu); - } - } - return r; } @@ -479,13 +428,9 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) kvmppc_mmu_book3s_hv_init(vcpu); /* - * Some vcpus may start out in stopped state. If we initialize - * them to busy-in-host state they will stop other vcpus in the - * vcore from running. Instead we initialize them to blocked - * state, effectively considering them to be stopped until we - * see the first run ioctl for them. + * We consider the vcpu stopped until we see the first run ioctl for it. */ - vcpu->arch.state = KVMPPC_VCPU_BLOCKED; + vcpu->arch.state = KVMPPC_VCPU_STOPPED; init_waitqueue_head(&vcpu->arch.cpu_run); @@ -496,6 +441,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) if (vcore) { INIT_LIST_HEAD(&vcore->runnable_threads); spin_lock_init(&vcore->lock); + init_waitqueue_head(&vcore->wq); } kvm->arch.vcores[core] = vcore; } @@ -506,10 +452,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) spin_lock(&vcore->lock); ++vcore->num_threads; - ++vcore->n_blocked; spin_unlock(&vcore->lock); vcpu->arch.vcore = vcore; + vcpu->arch.cpu_type = KVM_CPU_3S_64; + kvmppc_sanity_check(vcpu); + return vcpu; free_vcpu: @@ -524,30 +472,31 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu) kfree(vcpu); } -static void kvmppc_vcpu_blocked(struct kvm_vcpu *vcpu) +static void kvmppc_set_timer(struct kvm_vcpu *vcpu) { - struct kvmppc_vcore *vc = vcpu->arch.vcore; + unsigned long dec_nsec, now; - spin_lock(&vc->lock); - vcpu->arch.state = KVMPPC_VCPU_BLOCKED; - ++vc->n_blocked; - if (vc->n_runnable > 0 && - vc->n_runnable + vc->n_blocked == vc->num_threads) { - vcpu = list_first_entry(&vc->runnable_threads, struct kvm_vcpu, - arch.run_list); - wake_up(&vcpu->arch.cpu_run); + now = get_tb(); + if (now > vcpu->arch.dec_expires) { + /* decrementer has already gone negative */ + kvmppc_core_queue_dec(vcpu); + kvmppc_core_deliver_interrupts(vcpu); + return; } - spin_unlock(&vc->lock); + dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC + / tb_ticks_per_sec; + hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec), + HRTIMER_MODE_REL); + vcpu->arch.timer_running = 1; } -static void kvmppc_vcpu_unblocked(struct kvm_vcpu *vcpu) +static void kvmppc_end_cede(struct kvm_vcpu *vcpu) { - struct kvmppc_vcore *vc = vcpu->arch.vcore; - - spin_lock(&vc->lock); - vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; - --vc->n_blocked; - spin_unlock(&vc->lock); + vcpu->arch.ceded = 0; + if (vcpu->arch.timer_running) { + hrtimer_try_to_cancel(&vcpu->arch.dec_timer); + vcpu->arch.timer_running = 0; + } } extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu); @@ -562,6 +511,7 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, return; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; --vc->n_runnable; + ++vc->n_busy; /* decrement the physical thread id of each following vcpu */ v = vcpu; list_for_each_entry_continue(v, &vc->runnable_threads, arch.run_list) @@ -575,15 +525,20 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu) struct paca_struct *tpaca; struct kvmppc_vcore *vc = vcpu->arch.vcore; + if (vcpu->arch.timer_running) { + hrtimer_try_to_cancel(&vcpu->arch.dec_timer); + vcpu->arch.timer_running = 0; + } cpu = vc->pcpu + vcpu->arch.ptid; tpaca = &paca[cpu]; tpaca->kvm_hstate.kvm_vcpu = vcpu; tpaca->kvm_hstate.kvm_vcore = vc; + tpaca->kvm_hstate.napping = 0; + vcpu->cpu = vc->pcpu; smp_wmb(); #ifdef CONFIG_PPC_ICP_NATIVE if (vcpu->arch.ptid) { tpaca->cpu_start = 0x80; - tpaca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST; wmb(); xics_wake_cpu(cpu); ++vc->n_woken; @@ -631,9 +586,10 @@ static int on_primary_thread(void) */ static int kvmppc_run_core(struct kvmppc_vcore *vc) { - struct kvm_vcpu *vcpu, *vnext; + struct kvm_vcpu *vcpu, *vcpu0, *vnext; long ret; u64 now; + int ptid; /* don't start if any threads have a signal pending */ list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) @@ -652,29 +608,50 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) goto out; } + /* + * Assign physical thread IDs, first to non-ceded vcpus + * and then to ceded ones. + */ + ptid = 0; + vcpu0 = NULL; + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { + if (!vcpu->arch.ceded) { + if (!ptid) + vcpu0 = vcpu; + vcpu->arch.ptid = ptid++; + } + } + if (!vcpu0) + return 0; /* nothing to run */ + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) + if (vcpu->arch.ceded) + vcpu->arch.ptid = ptid++; + vc->n_woken = 0; vc->nap_count = 0; vc->entry_exit_count = 0; - vc->vcore_running = 1; + vc->vcore_state = VCORE_RUNNING; vc->in_guest = 0; vc->pcpu = smp_processor_id(); + vc->napping_threads = 0; list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) kvmppc_start_thread(vcpu); - vcpu = list_first_entry(&vc->runnable_threads, struct kvm_vcpu, - arch.run_list); + preempt_disable(); spin_unlock(&vc->lock); - preempt_disable(); kvm_guest_enter(); - __kvmppc_vcore_entry(NULL, vcpu); + __kvmppc_vcore_entry(NULL, vcpu0); - /* wait for secondary threads to finish writing their state to memory */ spin_lock(&vc->lock); + /* disable sending of IPIs on virtual external irqs */ + list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) + vcpu->cpu = -1; + /* wait for secondary threads to finish writing their state to memory */ if (vc->nap_count < vc->n_woken) kvmppc_wait_for_nap(vc); /* prevent other vcpu threads from doing kvmppc_start_thread() now */ - vc->vcore_running = 2; + vc->vcore_state = VCORE_EXITING; spin_unlock(&vc->lock); /* make sure updates to secondary vcpu structs are visible now */ @@ -690,22 +667,26 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) if (now < vcpu->arch.dec_expires && kvmppc_core_pending_dec(vcpu)) kvmppc_core_dequeue_dec(vcpu); - if (!vcpu->arch.trap) { - if (signal_pending(vcpu->arch.run_task)) { - vcpu->arch.kvm_run->exit_reason = KVM_EXIT_INTR; - vcpu->arch.ret = -EINTR; - } - continue; /* didn't get to run */ - } - ret = kvmppc_handle_exit(vcpu->arch.kvm_run, vcpu, - vcpu->arch.run_task); + + ret = RESUME_GUEST; + if (vcpu->arch.trap) + ret = kvmppc_handle_exit(vcpu->arch.kvm_run, vcpu, + vcpu->arch.run_task); + vcpu->arch.ret = ret; vcpu->arch.trap = 0; + + if (vcpu->arch.ceded) { + if (ret != RESUME_GUEST) + kvmppc_end_cede(vcpu); + else + kvmppc_set_timer(vcpu); + } } spin_lock(&vc->lock); out: - vc->vcore_running = 0; + vc->vcore_state = VCORE_INACTIVE; list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads, arch.run_list) { if (vcpu->arch.ret != RESUME_GUEST) { @@ -717,82 +698,130 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc) return 1; } -static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +/* + * Wait for some other vcpu thread to execute us, and + * wake us up when we need to handle something in the host. + */ +static void kvmppc_wait_for_exec(struct kvm_vcpu *vcpu, int wait_state) { - int ptid; - int wait_state; - struct kvmppc_vcore *vc; DEFINE_WAIT(wait); - /* No need to go into the guest when all we do is going out */ - if (signal_pending(current)) { - kvm_run->exit_reason = KVM_EXIT_INTR; - return -EINTR; + prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state); + if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) + schedule(); + finish_wait(&vcpu->arch.cpu_run, &wait); +} + +/* + * All the vcpus in this vcore are idle, so wait for a decrementer + * or external interrupt to one of the vcpus. vc->lock is held. + */ +static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) +{ + DEFINE_WAIT(wait); + struct kvm_vcpu *v; + int all_idle = 1; + + prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + vc->vcore_state = VCORE_SLEEPING; + spin_unlock(&vc->lock); + list_for_each_entry(v, &vc->runnable_threads, arch.run_list) { + if (!v->arch.ceded || v->arch.pending_exceptions) { + all_idle = 0; + break; + } } + if (all_idle) + schedule(); + finish_wait(&vc->wq, &wait); + spin_lock(&vc->lock); + vc->vcore_state = VCORE_INACTIVE; +} - /* On PPC970, check that we have an RMA region */ - if (!vcpu->kvm->arch.rma && cpu_has_feature(CPU_FTR_ARCH_201)) - return -EPERM; +static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +{ + int n_ceded; + int prev_state; + struct kvmppc_vcore *vc; + struct kvm_vcpu *v, *vn; kvm_run->exit_reason = 0; vcpu->arch.ret = RESUME_GUEST; vcpu->arch.trap = 0; - flush_fp_to_thread(current); - flush_altivec_to_thread(current); - flush_vsx_to_thread(current); - /* * Synchronize with other threads in this virtual core */ vc = vcpu->arch.vcore; spin_lock(&vc->lock); - /* This happens the first time this is called for a vcpu */ - if (vcpu->arch.state == KVMPPC_VCPU_BLOCKED) - --vc->n_blocked; - vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; - ptid = vc->n_runnable; + vcpu->arch.ceded = 0; vcpu->arch.run_task = current; vcpu->arch.kvm_run = kvm_run; - vcpu->arch.ptid = ptid; + prev_state = vcpu->arch.state; + vcpu->arch.state = KVMPPC_VCPU_RUNNABLE; list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads); ++vc->n_runnable; - wait_state = TASK_INTERRUPTIBLE; - while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) { - if (signal_pending(current)) { - if (!vc->vcore_running) { - kvm_run->exit_reason = KVM_EXIT_INTR; - vcpu->arch.ret = -EINTR; - break; - } - /* have to wait for vcore to stop executing guest */ - wait_state = TASK_UNINTERRUPTIBLE; - smp_send_reschedule(vc->pcpu); + /* + * This happens the first time this is called for a vcpu. + * If the vcore is already running, we may be able to start + * this thread straight away and have it join in. + */ + if (prev_state == KVMPPC_VCPU_STOPPED) { + if (vc->vcore_state == VCORE_RUNNING && + VCORE_EXIT_COUNT(vc) == 0) { + vcpu->arch.ptid = vc->n_runnable - 1; + kvmppc_start_thread(vcpu); } - if (!vc->vcore_running && - vc->n_runnable + vc->n_blocked == vc->num_threads) { - /* we can run now */ - if (kvmppc_run_core(vc)) - continue; - } + } else if (prev_state == KVMPPC_VCPU_BUSY_IN_HOST) + --vc->n_busy; - if (vc->vcore_running == 1 && VCORE_EXIT_COUNT(vc) == 0) - kvmppc_start_thread(vcpu); + while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE && + !signal_pending(current)) { + if (vc->n_busy || vc->vcore_state != VCORE_INACTIVE) { + spin_unlock(&vc->lock); + kvmppc_wait_for_exec(vcpu, TASK_INTERRUPTIBLE); + spin_lock(&vc->lock); + continue; + } + n_ceded = 0; + list_for_each_entry(v, &vc->runnable_threads, arch.run_list) + n_ceded += v->arch.ceded; + if (n_ceded == vc->n_runnable) + kvmppc_vcore_blocked(vc); + else + kvmppc_run_core(vc); + + list_for_each_entry_safe(v, vn, &vc->runnable_threads, + arch.run_list) { + kvmppc_core_deliver_interrupts(v); + if (signal_pending(v->arch.run_task)) { + kvmppc_remove_runnable(vc, v); + v->stat.signal_exits++; + v->arch.kvm_run->exit_reason = KVM_EXIT_INTR; + v->arch.ret = -EINTR; + wake_up(&v->arch.cpu_run); + } + } + } - /* wait for other threads to come in, or wait for vcore */ - prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state); - spin_unlock(&vc->lock); - schedule(); - finish_wait(&vcpu->arch.cpu_run, &wait); - spin_lock(&vc->lock); + if (signal_pending(current)) { + if (vc->vcore_state == VCORE_RUNNING || + vc->vcore_state == VCORE_EXITING) { + spin_unlock(&vc->lock); + kvmppc_wait_for_exec(vcpu, TASK_UNINTERRUPTIBLE); + spin_lock(&vc->lock); + } + if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) { + kvmppc_remove_runnable(vc, vcpu); + vcpu->stat.signal_exits++; + kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->arch.ret = -EINTR; + } } - if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) - kvmppc_remove_runnable(vc, vcpu); spin_unlock(&vc->lock); - return vcpu->arch.ret; } @@ -800,6 +829,26 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu) { int r; + if (!vcpu->arch.sane) { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + return -EINVAL; + } + + /* No need to go into the guest when all we'll do is come back out */ + if (signal_pending(current)) { + run->exit_reason = KVM_EXIT_INTR; + return -EINTR; + } + + /* On PPC970, check that we have an RMA region */ + if (!vcpu->kvm->arch.rma && cpu_has_feature(CPU_FTR_ARCH_201)) + return -EPERM; + + flush_fp_to_thread(current); + flush_altivec_to_thread(current); + flush_vsx_to_thread(current); + vcpu->arch.wqp = &vcpu->arch.vcore->wq; + do { r = kvmppc_run_vcpu(run, vcpu); diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index fcfe6b055558..bacb0cfa3602 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -110,39 +110,6 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags, return H_SUCCESS; } -static unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, - unsigned long pte_index) -{ - unsigned long rb, va_low; - - rb = (v & ~0x7fUL) << 16; /* AVA field */ - va_low = pte_index >> 3; - if (v & HPTE_V_SECONDARY) - va_low = ~va_low; - /* xor vsid from AVA */ - if (!(v & HPTE_V_1TB_SEG)) - va_low ^= v >> 12; - else - va_low ^= v >> 24; - va_low &= 0x7ff; - if (v & HPTE_V_LARGE) { - rb |= 1; /* L field */ - if (cpu_has_feature(CPU_FTR_ARCH_206) && - (r & 0xff000)) { - /* non-16MB large page, must be 64k */ - /* (masks depend on page size) */ - rb |= 0x1000; /* page encoding in LP field */ - rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */ - rb |= (va_low & 0xfe); /* AVAL field (P7 doesn't seem to care) */ - } - } else { - /* 4kB page */ - rb |= (va_low & 0x7ff) << 12; /* remaining 11b of VA */ - } - rb |= (v >> 54) & 0x300; /* B field */ - return rb; -} - #define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token)) static inline int try_lock_tlbie(unsigned int *lock) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index de2950135e6e..f422231d9235 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -20,7 +20,10 @@ #include <asm/ppc_asm.h> #include <asm/kvm_asm.h> #include <asm/reg.h> +#include <asm/mmu.h> #include <asm/page.h> +#include <asm/ptrace.h> +#include <asm/hvcall.h> #include <asm/asm-offsets.h> #include <asm/exception-64s.h> @@ -49,7 +52,7 @@ kvmppc_skip_Hinterrupt: b . /* - * Call kvmppc_handler_trampoline_enter in real mode. + * Call kvmppc_hv_entry in real mode. * Must be called with interrupts hard-disabled. * * Input Registers: @@ -89,6 +92,12 @@ _GLOBAL(kvmppc_hv_entry_trampoline) kvm_start_guest: ld r1,PACAEMERGSP(r13) subi r1,r1,STACK_FRAME_OVERHEAD + ld r2,PACATOC(r13) + + /* were we napping due to cede? */ + lbz r0,HSTATE_NAPPING(r13) + cmpwi r0,0 + bne kvm_end_cede /* get vcpu pointer */ ld r4, HSTATE_KVM_VCPU(r13) @@ -276,15 +285,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) cmpwi r0,0 beq 20b - /* Set LPCR. Set the MER bit if there is a pending external irq. */ + /* Set LPCR and RMOR. */ 10: ld r8,KVM_LPCR(r9) - ld r0,VCPU_PENDING_EXC(r4) - li r7,(1 << BOOK3S_IRQPRIO_EXTERNAL) - oris r7,r7,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h - and. r0,r0,r7 - beq 11f - ori r8,r8,LPCR_MER -11: mtspr SPRN_LPCR,r8 + mtspr SPRN_LPCR,r8 ld r8,KVM_RMOR(r9) mtspr SPRN_RMOR,r8 isync @@ -448,19 +451,50 @@ toc_tlbie_lock: mtctr r6 mtxer r7 - /* Move SRR0 and SRR1 into the respective regs */ +kvmppc_cede_reentry: /* r4 = vcpu, r13 = paca */ ld r6, VCPU_SRR0(r4) ld r7, VCPU_SRR1(r4) - mtspr SPRN_SRR0, r6 - mtspr SPRN_SRR1, r7 - ld r10, VCPU_PC(r4) + ld r11, VCPU_MSR(r4) /* r11 = vcpu->arch.msr & ~MSR_HV */ - ld r11, VCPU_MSR(r4) /* r10 = vcpu->arch.msr & ~MSR_HV */ rldicl r11, r11, 63 - MSR_HV_LG, 1 rotldi r11, r11, 1 + MSR_HV_LG ori r11, r11, MSR_ME + /* Check if we can deliver an external or decrementer interrupt now */ + ld r0,VCPU_PENDING_EXC(r4) + li r8,(1 << BOOK3S_IRQPRIO_EXTERNAL) + oris r8,r8,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h + and r0,r0,r8 + cmpdi cr1,r0,0 + andi. r0,r11,MSR_EE + beq cr1,11f +BEGIN_FTR_SECTION + mfspr r8,SPRN_LPCR + ori r8,r8,LPCR_MER + mtspr SPRN_LPCR,r8 + isync +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) + beq 5f + li r0,BOOK3S_INTERRUPT_EXTERNAL +12: mr r6,r10 + mr r10,r0 + mr r7,r11 + li r11,(MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */ + rotldi r11,r11,63 + b 5f +11: beq 5f + mfspr r0,SPRN_DEC + cmpwi r0,0 + li r0,BOOK3S_INTERRUPT_DECREMENTER + blt 12b + + /* Move SRR0 and SRR1 into the respective regs */ +5: mtspr SPRN_SRR0, r6 + mtspr SPRN_SRR1, r7 + li r0,0 + stb r0,VCPU_CEDED(r4) /* cancel cede */ + fast_guest_return: mtspr SPRN_HSRR0,r10 mtspr SPRN_HSRR1,r11 @@ -574,21 +608,20 @@ kvmppc_interrupt: /* See if this is something we can handle in real mode */ cmpwi r12,BOOK3S_INTERRUPT_SYSCALL beq hcall_try_real_mode -hcall_real_cont: /* Check for mediated interrupts (could be done earlier really ...) */ BEGIN_FTR_SECTION cmpwi r12,BOOK3S_INTERRUPT_EXTERNAL bne+ 1f - ld r5,VCPU_KVM(r9) - ld r5,KVM_LPCR(r5) andi. r0,r11,MSR_EE beq 1f + mfspr r5,SPRN_LPCR andi. r0,r5,LPCR_MER bne bounce_ext_interrupt 1: END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) +hcall_real_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ /* Save DEC */ mfspr r5,SPRN_DEC mftb r6 @@ -682,7 +715,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201) slbia ptesync -hdec_soon: +hdec_soon: /* r9 = vcpu, r12 = trap, r13 = paca */ BEGIN_FTR_SECTION b 32f END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) @@ -700,6 +733,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) addi r0,r3,0x100 stwcx. r0,0,r6 bne 41b + lwsync /* * At this point we have an interrupt that we have to pass @@ -713,18 +747,39 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) * interrupt, since the other threads will already be on their * way here in that case. */ + cmpwi r3,0x100 /* Are we the first here? */ + bge 43f + cmpwi r3,1 /* Are any other threads in the guest? */ + ble 43f cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER beq 40f - cmpwi r3,0x100 /* Are we the first here? */ - bge 40f - cmpwi r3,1 - ble 40f li r0,0 mtspr SPRN_HDEC,r0 40: + /* + * Send an IPI to any napping threads, since an HDEC interrupt + * doesn't wake CPUs up from nap. + */ + lwz r3,VCORE_NAPPING_THREADS(r5) + lwz r4,VCPU_PTID(r9) + li r0,1 + sldi r0,r0,r4 + andc. r3,r3,r0 /* no sense IPI'ing ourselves */ + beq 43f + mulli r4,r4,PACA_SIZE /* get paca for thread 0 */ + subf r6,r4,r13 +42: andi. r0,r3,1 + beq 44f + ld r8,HSTATE_XICS_PHYS(r6) /* get thread's XICS reg addr */ + li r0,IPI_PRIORITY + li r7,XICS_QIRR + stbcix r0,r7,r8 /* trigger the IPI */ +44: srdi. r3,r3,1 + addi r6,r6,PACA_SIZE + bne 42b /* Secondary threads wait for primary to do partition switch */ - ld r4,VCPU_KVM(r9) /* pointer to struct kvm */ +43: ld r4,VCPU_KVM(r9) /* pointer to struct kvm */ ld r5,HSTATE_KVM_VCORE(r13) lwz r3,VCPU_PTID(r9) cmpwi r3,0 @@ -1077,7 +1132,6 @@ hcall_try_real_mode: hcall_real_fallback: li r12,BOOK3S_INTERRUPT_SYSCALL ld r9, HSTATE_KVM_VCPU(r13) - ld r11, VCPU_MSR(r9) b hcall_real_cont @@ -1139,7 +1193,7 @@ hcall_real_table: .long 0 /* 0xd4 */ .long 0 /* 0xd8 */ .long 0 /* 0xdc */ - .long 0 /* 0xe0 */ + .long .kvmppc_h_cede - hcall_real_table .long 0 /* 0xe4 */ .long 0 /* 0xe8 */ .long 0 /* 0xec */ @@ -1168,7 +1222,8 @@ bounce_ext_interrupt: mtspr SPRN_SRR0,r10 mtspr SPRN_SRR1,r11 li r10,BOOK3S_INTERRUPT_EXTERNAL - LOAD_REG_IMMEDIATE(r11,MSR_SF | MSR_ME); + li r11,(MSR_ME << 1) | 1 /* synthesize MSR_SF | MSR_ME */ + rotldi r11,r11,63 b fast_guest_return _GLOBAL(kvmppc_h_set_dabr) @@ -1177,6 +1232,178 @@ _GLOBAL(kvmppc_h_set_dabr) li r3,0 blr +_GLOBAL(kvmppc_h_cede) + ori r11,r11,MSR_EE + std r11,VCPU_MSR(r3) + li r0,1 + stb r0,VCPU_CEDED(r3) + sync /* order setting ceded vs. testing prodded */ + lbz r5,VCPU_PRODDED(r3) + cmpwi r5,0 + bne 1f + li r0,0 /* set trap to 0 to say hcall is handled */ + stw r0,VCPU_TRAP(r3) + li r0,H_SUCCESS + std r0,VCPU_GPR(r3)(r3) +BEGIN_FTR_SECTION + b 2f /* just send it up to host on 970 */ +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) + + /* + * Set our bit in the bitmask of napping threads unless all the + * other threads are already napping, in which case we send this + * up to the host. + */ + ld r5,HSTATE_KVM_VCORE(r13) + lwz r6,VCPU_PTID(r3) + lwz r8,VCORE_ENTRY_EXIT(r5) + clrldi r8,r8,56 + li r0,1 + sld r0,r0,r6 + addi r6,r5,VCORE_NAPPING_THREADS +31: lwarx r4,0,r6 + or r4,r4,r0 + popcntw r7,r4 + cmpw r7,r8 + bge 2f + stwcx. r4,0,r6 + bne 31b + li r0,1 + stb r0,HSTATE_NAPPING(r13) + /* order napping_threads update vs testing entry_exit_count */ + lwsync + mr r4,r3 + lwz r7,VCORE_ENTRY_EXIT(r5) + cmpwi r7,0x100 + bge 33f /* another thread already exiting */ + +/* + * Although not specifically required by the architecture, POWER7 + * preserves the following registers in nap mode, even if an SMT mode + * switch occurs: SLB entries, PURR, SPURR, AMOR, UAMOR, AMR, SPRG0-3, + * DAR, DSISR, DABR, DABRX, DSCR, PMCx, MMCRx, SIAR, SDAR. + */ + /* Save non-volatile GPRs */ + std r14, VCPU_GPR(r14)(r3) + std r15, VCPU_GPR(r15)(r3) + std r16, VCPU_GPR(r16)(r3) + std r17, VCPU_GPR(r17)(r3) + std r18, VCPU_GPR(r18)(r3) + std r19, VCPU_GPR(r19)(r3) + std r20, VCPU_GPR(r20)(r3) + std r21, VCPU_GPR(r21)(r3) + std r22, VCPU_GPR(r22)(r3) + std r23, VCPU_GPR(r23)(r3) + std r24, VCPU_GPR(r24)(r3) + std r25, VCPU_GPR(r25)(r3) + std r26, VCPU_GPR(r26)(r3) + std r27, VCPU_GPR(r27)(r3) + std r28, VCPU_GPR(r28)(r3) + std r29, VCPU_GPR(r29)(r3) + std r30, VCPU_GPR(r30)(r3) + std r31, VCPU_GPR(r31)(r3) + + /* save FP state */ + bl .kvmppc_save_fp + + /* + * Take a nap until a decrementer or external interrupt occurs, + * with PECE1 (wake on decr) and PECE0 (wake on external) set in LPCR + */ + li r0,0x80 + stb r0,PACAPROCSTART(r13) + mfspr r5,SPRN_LPCR + ori r5,r5,LPCR_PECE0 | LPCR_PECE1 + mtspr SPRN_LPCR,r5 + isync + li r0, 0 + std r0, HSTATE_SCRATCH0(r13) + ptesync + ld r0, HSTATE_SCRATCH0(r13) +1: cmpd r0, r0 + bne 1b + nap + b . + +kvm_end_cede: + /* Woken by external or decrementer interrupt */ + ld r1, HSTATE_HOST_R1(r13) + ld r2, PACATOC(r13) + + /* If we're a secondary thread and we got here by an IPI, ack it */ + ld r4,HSTATE_KVM_VCPU(r13) + lwz r3,VCPU_PTID(r4) + cmpwi r3,0 + beq 27f + mfspr r3,SPRN_SRR1 + rlwinm r3,r3,44-31,0x7 /* extract wake reason field */ + cmpwi r3,4 /* was it an external interrupt? */ + bne 27f + ld r5, HSTATE_XICS_PHYS(r13) + li r0,0xff + li r6,XICS_QIRR + li r7,XICS_XIRR + lwzcix r8,r5,r7 /* ack the interrupt */ + sync + stbcix r0,r5,r6 /* clear it */ + stwcix r8,r5,r7 /* EOI it */ +27: + /* load up FP state */ + bl kvmppc_load_fp + + /* Load NV GPRS */ + ld r14, VCPU_GPR(r14)(r4) + ld r15, VCPU_GPR(r15)(r4) + ld r16, VCPU_GPR(r16)(r4) + ld r17, VCPU_GPR(r17)(r4) + ld r18, VCPU_GPR(r18)(r4) + ld r19, VCPU_GPR(r19)(r4) + ld r20, VCPU_GPR(r20)(r4) + ld r21, VCPU_GPR(r21)(r4) + ld r22, VCPU_GPR(r22)(r4) + ld r23, VCPU_GPR(r23)(r4) + ld r24, VCPU_GPR(r24)(r4) + ld r25, VCPU_GPR(r25)(r4) + ld r26, VCPU_GPR(r26)(r4) + ld r27, VCPU_GPR(r27)(r4) + ld r28, VCPU_GPR(r28)(r4) + ld r29, VCPU_GPR(r29)(r4) + ld r30, VCPU_GPR(r30)(r4) + ld r31, VCPU_GPR(r31)(r4) + + /* clear our bit in vcore->napping_threads */ +33: ld r5,HSTATE_KVM_VCORE(r13) + lwz r3,VCPU_PTID(r4) + li r0,1 + sld r0,r0,r3 + addi r6,r5,VCORE_NAPPING_THREADS +32: lwarx r7,0,r6 + andc r7,r7,r0 + stwcx. r7,0,r6 + bne 32b + li r0,0 + stb r0,HSTATE_NAPPING(r13) + + /* see if any other thread is already exiting */ + lwz r0,VCORE_ENTRY_EXIT(r5) + cmpwi r0,0x100 + blt kvmppc_cede_reentry /* if not go back to guest */ + + /* some threads are exiting, so go to the guest exit path */ + b hcall_real_fallback + + /* cede when already previously prodded case */ +1: li r0,0 + stb r0,VCPU_PRODDED(r3) + sync /* order testing prodded vs. clearing ceded */ + stb r0,VCPU_CEDED(r3) + li r3,H_SUCCESS + blr + + /* we've ceded but we want to give control to the host */ +2: li r3,H_TOO_HARD + blr + secondary_too_late: ld r5,HSTATE_KVM_VCORE(r13) HMT_LOW @@ -1194,14 +1421,20 @@ secondary_too_late: slbmte r6,r5 1: addi r11,r11,16 .endr - b 50f secondary_nap: - /* Clear any pending IPI */ -50: ld r5, HSTATE_XICS_PHYS(r13) + /* Clear any pending IPI - assume we're a secondary thread */ + ld r5, HSTATE_XICS_PHYS(r13) + li r7, XICS_XIRR + lwzcix r3, r5, r7 /* ack any pending interrupt */ + rlwinm. r0, r3, 0, 0xffffff /* any pending? */ + beq 37f + sync li r0, 0xff li r6, XICS_QIRR - stbcix r0, r5, r6 + stbcix r0, r5, r6 /* clear the IPI */ + stwcix r3, r5, r7 /* EOI it */ +37: sync /* increment the nap count and then go to nap mode */ ld r4, HSTATE_KVM_VCORE(r13) @@ -1211,13 +1444,12 @@ secondary_nap: addi r3, r3, 1 stwcx. r3, 0, r4 bne 51b - isync + li r3, LPCR_PECE0 mfspr r4, SPRN_LPCR - li r0, LPCR_PECE - andc r4, r4, r0 - ori r4, r4, LPCR_PECE0 /* exit nap on interrupt */ + rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1 mtspr SPRN_LPCR, r4 + isync li r0, 0 std r0, HSTATE_SCRATCH0(r13) ptesync diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index c54b0e30cf3f..0a8515a5c042 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -29,27 +29,11 @@ #define ULONG_SIZE 8 #define FUNC(name) GLUE(.,name) -#define GET_SHADOW_VCPU_R13 - -#define DISABLE_INTERRUPTS \ - mfmsr r0; \ - rldicl r0,r0,48,1; \ - rotldi r0,r0,16; \ - mtmsrd r0,1; \ - #elif defined(CONFIG_PPC_BOOK3S_32) #define ULONG_SIZE 4 #define FUNC(name) name -#define GET_SHADOW_VCPU_R13 \ - lwz r13, (THREAD + THREAD_KVM_SVCPU)(r2) - -#define DISABLE_INTERRUPTS \ - mfmsr r0; \ - rlwinm r0,r0,0,17,15; \ - mtmsr r0; \ - #endif /* CONFIG_PPC_BOOK3S_XX */ @@ -108,44 +92,17 @@ kvm_start_entry: kvm_start_lightweight: - GET_SHADOW_VCPU_R13 - PPC_LL r3, VCPU_HIGHMEM_HANDLER(r4) - PPC_STL r3, HSTATE_VMHANDLER(r13) - - PPC_LL r10, VCPU_SHADOW_MSR(r4) /* r10 = vcpu->arch.shadow_msr */ - - DISABLE_INTERRUPTS - #ifdef CONFIG_PPC_BOOK3S_64 - /* Some guests may need to have dcbz set to 32 byte length. - * - * Usually we ensure that by patching the guest's instructions - * to trap on dcbz and emulate it in the hypervisor. - * - * If we can, we should tell the CPU to use 32 byte dcbz though, - * because that's a lot faster. - */ - PPC_LL r3, VCPU_HFLAGS(r4) - rldicl. r3, r3, 0, 63 /* CR = ((r3 & 1) == 0) */ - beq no_dcbz32_on - - mfspr r3,SPRN_HID5 - ori r3, r3, 0x80 /* XXX HID5_dcbz32 = 0x80 */ - mtspr SPRN_HID5,r3 - -no_dcbz32_on: - + rldicl r3, r3, 0, 63 /* r3 &= 1 */ + stb r3, HSTATE_RESTORE_HID5(r13) #endif /* CONFIG_PPC_BOOK3S_64 */ - PPC_LL r6, VCPU_RMCALL(r4) - mtctr r6 - - PPC_LL r3, VCPU_TRAMPOLINE_ENTER(r4) - LOAD_REG_IMMEDIATE(r4, MSR_KERNEL & ~(MSR_IR | MSR_DR)) + PPC_LL r4, VCPU_SHADOW_MSR(r4) /* get shadow_msr */ /* Jump to segment patching handler and into our guest */ - bctr + bl FUNC(kvmppc_entry_trampoline) + nop /* * This is the handler in module memory. It gets jumped at from the @@ -170,21 +127,6 @@ kvmppc_handler_highmem: /* R7 = vcpu */ PPC_LL r7, GPR4(r1) -#ifdef CONFIG_PPC_BOOK3S_64 - - PPC_LL r5, VCPU_HFLAGS(r7) - rldicl. r5, r5, 0, 63 /* CR = ((r5 & 1) == 0) */ - beq no_dcbz32_off - - li r4, 0 - mfspr r5,SPRN_HID5 - rldimi r5,r4,6,56 - mtspr SPRN_HID5,r5 - -no_dcbz32_off: - -#endif /* CONFIG_PPC_BOOK3S_64 */ - PPC_STL r14, VCPU_GPR(r14)(r7) PPC_STL r15, VCPU_GPR(r15)(r7) PPC_STL r16, VCPU_GPR(r16)(r7) @@ -204,67 +146,6 @@ no_dcbz32_off: PPC_STL r30, VCPU_GPR(r30)(r7) PPC_STL r31, VCPU_GPR(r31)(r7) - /* Restore host msr -> SRR1 */ - PPC_LL r6, VCPU_HOST_MSR(r7) - - /* - * For some interrupts, we need to call the real Linux - * handler, so it can do work for us. This has to happen - * as if the interrupt arrived from the kernel though, - * so let's fake it here where most state is restored. - * - * Call Linux for hardware interrupts/decrementer - * r3 = address of interrupt handler (exit reason) - */ - - cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL - beq call_linux_handler - cmpwi r12, BOOK3S_INTERRUPT_DECREMENTER - beq call_linux_handler - cmpwi r12, BOOK3S_INTERRUPT_PERFMON - beq call_linux_handler - - /* Back to EE=1 */ - mtmsr r6 - sync - b kvm_return_point - -call_linux_handler: - - /* - * If we land here we need to jump back to the handler we - * came from. - * - * We have a page that we can access from real mode, so let's - * jump back to that and use it as a trampoline to get back into the - * interrupt handler! - * - * R3 still contains the exit code, - * R5 VCPU_HOST_RETIP and - * R6 VCPU_HOST_MSR - */ - - /* Restore host IP -> SRR0 */ - PPC_LL r5, VCPU_HOST_RETIP(r7) - - /* XXX Better move to a safe function? - * What if we get an HTAB flush in between mtsrr0 and mtsrr1? */ - - mtlr r12 - - PPC_LL r4, VCPU_TRAMPOLINE_LOWMEM(r7) - mtsrr0 r4 - LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)) - mtsrr1 r3 - - RFI - -.global kvm_return_point -kvm_return_point: - - /* Jump back to lightweight entry if we're supposed to */ - /* go back into the guest */ - /* Pass the exit number as 3rd argument to kvmppc_handle_exit */ mr r5, r12 diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 0c0d3f274437..d417511abfb1 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -150,16 +150,22 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) #ifdef CONFIG_PPC_BOOK3S_64 if ((pvr >= 0x330000) && (pvr < 0x70330000)) { kvmppc_mmu_book3s_64_init(vcpu); - to_book3s(vcpu)->hior = 0xfff00000; + if (!to_book3s(vcpu)->hior_sregs) + to_book3s(vcpu)->hior = 0xfff00000; to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL; + vcpu->arch.cpu_type = KVM_CPU_3S_64; } else #endif { kvmppc_mmu_book3s_32_init(vcpu); - to_book3s(vcpu)->hior = 0; + if (!to_book3s(vcpu)->hior_sregs) + to_book3s(vcpu)->hior = 0; to_book3s(vcpu)->msr_mask = 0xffffffffULL; + vcpu->arch.cpu_type = KVM_CPU_3S_32; } + kvmppc_sanity_check(vcpu); + /* If we are in hypervisor level on 970, we can tell the CPU to * treat DCBZ as 32 bytes store */ vcpu->arch.hflags &= ~BOOK3S_HFLAG_DCBZ32; @@ -646,7 +652,27 @@ program_interrupt: break; } case BOOK3S_INTERRUPT_SYSCALL: - if (vcpu->arch.osi_enabled && + if (vcpu->arch.papr_enabled && + (kvmppc_get_last_inst(vcpu) == 0x44000022) && + !(vcpu->arch.shared->msr & MSR_PR)) { + /* SC 1 papr hypercalls */ + ulong cmd = kvmppc_get_gpr(vcpu, 3); + int i; + + if (kvmppc_h_pr(vcpu, cmd) == EMULATE_DONE) { + r = RESUME_GUEST; + break; + } + + run->papr_hcall.nr = cmd; + for (i = 0; i < 9; ++i) { + ulong gpr = kvmppc_get_gpr(vcpu, 4 + i); + run->papr_hcall.args[i] = gpr; + } + run->exit_reason = KVM_EXIT_PAPR_HCALL; + vcpu->arch.hcall_needed = 1; + r = RESUME_HOST; + } else if (vcpu->arch.osi_enabled && (((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) && (((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) { /* MOL hypercalls */ @@ -770,6 +796,9 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, } } + if (sregs->u.s.flags & KVM_SREGS_S_HIOR) + sregs->u.s.hior = to_book3s(vcpu)->hior; + return 0; } @@ -806,6 +835,11 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, /* Flush the MMU after messing with the segments */ kvmppc_mmu_pte_flush(vcpu, 0, 0); + if (sregs->u.s.flags & KVM_SREGS_S_HIOR) { + to_book3s(vcpu)->hior_sregs = true; + to_book3s(vcpu)->hior = sregs->u.s.hior; + } + return 0; } @@ -841,8 +875,6 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) if (!p) goto uninit_vcpu; - vcpu->arch.host_retip = kvm_return_point; - vcpu->arch.host_msr = mfmsr(); #ifdef CONFIG_PPC_BOOK3S_64 /* default to book3s_64 (970fx) */ vcpu->arch.pvr = 0x3C0301; @@ -853,16 +885,6 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id) kvmppc_set_pvr(vcpu, vcpu->arch.pvr); vcpu->arch.slb_nr = 64; - /* remember where some real-mode handlers are */ - vcpu->arch.trampoline_lowmem = __pa(kvmppc_handler_lowmem_trampoline); - vcpu->arch.trampoline_enter = __pa(kvmppc_handler_trampoline_enter); - vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem; -#ifdef CONFIG_PPC_BOOK3S_64 - vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall; -#else - vcpu->arch.rmcall = (ulong)kvmppc_rmcall; -#endif - vcpu->arch.shadow_msr = MSR_USER64; err = kvmppc_mmu_init(vcpu); @@ -908,6 +930,12 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) #endif ulong ext_msr; + /* Check if we can run the vcpu at all */ + if (!vcpu->arch.sane) { + kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + return -EINVAL; + } + /* No need to go into the guest when all we do is going out */ if (signal_pending(current)) { kvm_run->exit_reason = KVM_EXIT_INTR; diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c new file mode 100644 index 000000000000..b9589324797b --- /dev/null +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -0,0 +1,158 @@ +/* + * Copyright (C) 2011. Freescale Inc. All rights reserved. + * + * Authors: + * Alexander Graf <agraf@suse.de> + * Paul Mackerras <paulus@samba.org> + * + * Description: + * + * Hypercall handling for running PAPR guests in PR KVM on Book 3S + * processors. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + */ + +#include <asm/uaccess.h> +#include <asm/kvm_ppc.h> +#include <asm/kvm_book3s.h> + +static unsigned long get_pteg_addr(struct kvm_vcpu *vcpu, long pte_index) +{ + struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); + unsigned long pteg_addr; + + pte_index <<= 4; + pte_index &= ((1 << ((vcpu_book3s->sdr1 & 0x1f) + 11)) - 1) << 7 | 0x70; + pteg_addr = vcpu_book3s->sdr1 & 0xfffffffffffc0000ULL; + pteg_addr |= pte_index; + + return pteg_addr; +} + +static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu) +{ + long flags = kvmppc_get_gpr(vcpu, 4); + long pte_index = kvmppc_get_gpr(vcpu, 5); + unsigned long pteg[2 * 8]; + unsigned long pteg_addr, i, *hpte; + + pte_index &= ~7UL; + pteg_addr = get_pteg_addr(vcpu, pte_index); + + copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg)); + hpte = pteg; + + if (likely((flags & H_EXACT) == 0)) { + pte_index &= ~7UL; + for (i = 0; ; ++i) { + if (i == 8) + return H_PTEG_FULL; + if ((*hpte & HPTE_V_VALID) == 0) + break; + hpte += 2; + } + } else { + i = kvmppc_get_gpr(vcpu, 5) & 7UL; + hpte += i * 2; + } + + hpte[0] = kvmppc_get_gpr(vcpu, 6); + hpte[1] = kvmppc_get_gpr(vcpu, 7); + copy_to_user((void __user *)pteg_addr, pteg, sizeof(pteg)); + kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + kvmppc_set_gpr(vcpu, 4, pte_index | i); + + return EMULATE_DONE; +} + +static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu) +{ + unsigned long flags= kvmppc_get_gpr(vcpu, 4); + unsigned long pte_index = kvmppc_get_gpr(vcpu, 5); + unsigned long avpn = kvmppc_get_gpr(vcpu, 6); + unsigned long v = 0, pteg, rb; + unsigned long pte[2]; + + pteg = get_pteg_addr(vcpu, pte_index); + copy_from_user(pte, (void __user *)pteg, sizeof(pte)); + + if ((pte[0] & HPTE_V_VALID) == 0 || + ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn) || + ((flags & H_ANDCOND) && (pte[0] & avpn) != 0)) { + kvmppc_set_gpr(vcpu, 3, H_NOT_FOUND); + return EMULATE_DONE; + } + + copy_to_user((void __user *)pteg, &v, sizeof(v)); + + rb = compute_tlbie_rb(pte[0], pte[1], pte_index); + vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false); + + kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + kvmppc_set_gpr(vcpu, 4, pte[0]); + kvmppc_set_gpr(vcpu, 5, pte[1]); + + return EMULATE_DONE; +} + +static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu) +{ + unsigned long flags = kvmppc_get_gpr(vcpu, 4); + unsigned long pte_index = kvmppc_get_gpr(vcpu, 5); + unsigned long avpn = kvmppc_get_gpr(vcpu, 6); + unsigned long rb, pteg, r, v; + unsigned long pte[2]; + + pteg = get_pteg_addr(vcpu, pte_index); + copy_from_user(pte, (void __user *)pteg, sizeof(pte)); + + if ((pte[0] & HPTE_V_VALID) == 0 || + ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn)) { + kvmppc_set_gpr(vcpu, 3, H_NOT_FOUND); + return EMULATE_DONE; + } + + v = pte[0]; + r = pte[1]; + r &= ~(HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_HI | + HPTE_R_KEY_LO); + r |= (flags << 55) & HPTE_R_PP0; + r |= (flags << 48) & HPTE_R_KEY_HI; + r |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO); + + pte[1] = r; + + rb = compute_tlbie_rb(v, r, pte_index); + vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false); + copy_to_user((void __user *)pteg, pte, sizeof(pte)); + + kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + + return EMULATE_DONE; +} + +int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) +{ + switch (cmd) { + case H_ENTER: + return kvmppc_h_pr_enter(vcpu); + case H_REMOVE: + return kvmppc_h_pr_remove(vcpu); + case H_PROTECT: + return kvmppc_h_pr_protect(vcpu); + case H_BULK_REMOVE: + /* We just flush all PTEs, so user space can + handle the HPT modifications */ + kvmppc_mmu_pte_flush(vcpu, 0, 0); + break; + case H_CEDE: + kvm_vcpu_block(vcpu); + vcpu->stat.halt_wakeup++; + return EMULATE_DONE; + } + + return EMULATE_FAIL; +} diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index c1f877c4a884..34187585c507 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -20,6 +20,7 @@ #include <asm/ppc_asm.h> #include <asm/kvm_asm.h> #include <asm/reg.h> +#include <asm/mmu.h> #include <asm/page.h> #include <asm/asm-offsets.h> @@ -35,10 +36,10 @@ #if defined(CONFIG_PPC_BOOK3S_64) -#define LOAD_SHADOW_VCPU(reg) GET_PACA(reg) -#define MSR_NOIRQ MSR_KERNEL & ~(MSR_IR | MSR_DR) #define FUNC(name) GLUE(.,name) +#define MTMSR_EERI(reg) mtmsrd (reg),1 + .globl kvmppc_skip_interrupt kvmppc_skip_interrupt: /* * Here all GPRs are unchanged from when the interrupt happened @@ -51,6 +52,7 @@ kvmppc_skip_interrupt: rfid b . + .globl kvmppc_skip_Hinterrupt kvmppc_skip_Hinterrupt: /* * Here all GPRs are unchanged from when the interrupt happened @@ -65,8 +67,8 @@ kvmppc_skip_Hinterrupt: #elif defined(CONFIG_PPC_BOOK3S_32) -#define MSR_NOIRQ MSR_KERNEL #define FUNC(name) name +#define MTMSR_EERI(reg) mtmsr (reg) .macro INTERRUPT_TRAMPOLINE intno @@ -167,40 +169,24 @@ kvmppc_handler_skip_ins: #endif /* - * This trampoline brings us back to a real mode handler - * - * Input Registers: - * - * R5 = SRR0 - * R6 = SRR1 - * LR = real-mode IP + * Call kvmppc_handler_trampoline_enter in real mode * + * On entry, r4 contains the guest shadow MSR */ -.global kvmppc_handler_lowmem_trampoline -kvmppc_handler_lowmem_trampoline: - - mtsrr0 r5 +_GLOBAL(kvmppc_entry_trampoline) + mfmsr r5 + LOAD_REG_ADDR(r7, kvmppc_handler_trampoline_enter) + toreal(r7) + + li r9, MSR_RI + ori r9, r9, MSR_EE + andc r9, r5, r9 /* Clear EE and RI in MSR value */ + li r6, MSR_IR | MSR_DR + ori r6, r6, MSR_EE + andc r6, r5, r6 /* Clear EE, DR and IR in MSR value */ + MTMSR_EERI(r9) /* Clear EE and RI in MSR */ + mtsrr0 r7 /* before we set srr0/1 */ mtsrr1 r6 - blr -kvmppc_handler_lowmem_trampoline_end: - -/* - * Call a function in real mode - * - * Input Registers: - * - * R3 = function - * R4 = MSR - * R5 = scratch register - * - */ -_GLOBAL(kvmppc_rmcall) - LOAD_REG_IMMEDIATE(r5, MSR_NOIRQ) - mtmsr r5 /* Disable relocation and interrupts, so mtsrr - doesn't get interrupted */ - sync - mtsrr0 r3 - mtsrr1 r4 RFI #if defined(CONFIG_PPC_BOOK3S_32) diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index aed32e517212..0676ae249b9f 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -23,6 +23,7 @@ #define GET_SHADOW_VCPU(reg) \ mr reg, r13 +#define MTMSR_EERI(reg) mtmsrd (reg),1 #elif defined(CONFIG_PPC_BOOK3S_32) @@ -30,6 +31,7 @@ tophys(reg, r2); \ lwz reg, (THREAD + THREAD_KVM_SVCPU)(reg); \ tophys(reg, reg) +#define MTMSR_EERI(reg) mtmsr (reg) #endif @@ -57,10 +59,12 @@ kvmppc_handler_trampoline_enter: /* Required state: * * MSR = ~IR|DR - * R13 = PACA * R1 = host R1 * R2 = host R2 - * R10 = guest MSR + * R4 = guest shadow MSR + * R5 = normal host MSR + * R6 = current host MSR (EE, IR, DR off) + * LR = highmem guest exit code * all other volatile GPRS = free * SVCPU[CR] = guest CR * SVCPU[XER] = guest XER @@ -71,15 +75,15 @@ kvmppc_handler_trampoline_enter: /* r3 = shadow vcpu */ GET_SHADOW_VCPU(r3) + /* Save guest exit handler address and MSR */ + mflr r0 + PPC_STL r0, HSTATE_VMHANDLER(r3) + PPC_STL r5, HSTATE_HOST_MSR(r3) + /* Save R1/R2 in the PACA (64-bit) or shadow_vcpu (32-bit) */ PPC_STL r1, HSTATE_HOST_R1(r3) PPC_STL r2, HSTATE_HOST_R2(r3) - /* Move SRR0 and SRR1 into the respective regs */ - PPC_LL r9, SVCPU_PC(r3) - mtsrr0 r9 - mtsrr1 r10 - /* Activate guest mode, so faults get handled by KVM */ li r11, KVM_GUEST_MODE_GUEST stb r11, HSTATE_IN_GUEST(r3) @@ -87,17 +91,46 @@ kvmppc_handler_trampoline_enter: /* Switch to guest segment. This is subarch specific. */ LOAD_GUEST_SEGMENTS +#ifdef CONFIG_PPC_BOOK3S_64 + /* Some guests may need to have dcbz set to 32 byte length. + * + * Usually we ensure that by patching the guest's instructions + * to trap on dcbz and emulate it in the hypervisor. + * + * If we can, we should tell the CPU to use 32 byte dcbz though, + * because that's a lot faster. + */ + lbz r0, HSTATE_RESTORE_HID5(r3) + cmpwi r0, 0 + beq no_dcbz32_on + + mfspr r0,SPRN_HID5 + ori r0, r0, 0x80 /* XXX HID5_dcbz32 = 0x80 */ + mtspr SPRN_HID5,r0 +no_dcbz32_on: + +#endif /* CONFIG_PPC_BOOK3S_64 */ + /* Enter guest */ - PPC_LL r4, SVCPU_CTR(r3) - PPC_LL r5, SVCPU_LR(r3) - lwz r6, SVCPU_CR(r3) - lwz r7, SVCPU_XER(r3) + PPC_LL r8, SVCPU_CTR(r3) + PPC_LL r9, SVCPU_LR(r3) + lwz r10, SVCPU_CR(r3) + lwz r11, SVCPU_XER(r3) + + mtctr r8 + mtlr r9 + mtcr r10 + mtxer r11 - mtctr r4 - mtlr r5 - mtcr r6 - mtxer r7 + /* Move SRR0 and SRR1 into the respective regs */ + PPC_LL r9, SVCPU_PC(r3) + /* First clear RI in our current MSR value */ + li r0, MSR_RI + andc r6, r6, r0 + MTMSR_EERI(r6) + mtsrr0 r9 + mtsrr1 r4 PPC_LL r0, SVCPU_R0(r3) PPC_LL r1, SVCPU_R1(r3) @@ -213,11 +246,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) beq ld_last_inst cmpwi r12, BOOK3S_INTERRUPT_PROGRAM beq ld_last_inst + cmpwi r12, BOOK3S_INTERRUPT_SYSCALL + beq ld_last_prev_inst cmpwi r12, BOOK3S_INTERRUPT_ALIGNMENT beq- ld_last_inst b no_ld_last_inst +ld_last_prev_inst: + addi r3, r3, -4 + ld_last_inst: /* Save off the guest instruction we're at */ @@ -254,6 +292,43 @@ no_ld_last_inst: /* Switch back to host MMU */ LOAD_HOST_SEGMENTS +#ifdef CONFIG_PPC_BOOK3S_64 + + lbz r5, HSTATE_RESTORE_HID5(r13) + cmpwi r5, 0 + beq no_dcbz32_off + + li r4, 0 + mfspr r5,SPRN_HID5 + rldimi r5,r4,6,56 + mtspr SPRN_HID5,r5 + +no_dcbz32_off: + +#endif /* CONFIG_PPC_BOOK3S_64 */ + + /* + * For some interrupts, we need to call the real Linux + * handler, so it can do work for us. This has to happen + * as if the interrupt arrived from the kernel though, + * so let's fake it here where most state is restored. + * + * Having set up SRR0/1 with the address where we want + * to continue with relocation on (potentially in module + * space), we either just go straight there with rfi[d], + * or we jump to an interrupt handler with bctr if there + * is an interrupt to be handled first. In the latter + * case, the rfi[d] at the end of the interrupt handler + * will get us back to where we want to continue. + */ + + cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL + beq 1f + cmpwi r12, BOOK3S_INTERRUPT_DECREMENTER + beq 1f + cmpwi r12, BOOK3S_INTERRUPT_PERFMON +1: mtctr r12 + /* Register usage at this point: * * R1 = host R1 @@ -264,13 +339,15 @@ no_ld_last_inst: * */ - /* RFI into the highmem handler */ - mfmsr r7 - ori r7, r7, MSR_IR|MSR_DR|MSR_RI|MSR_ME /* Enable paging */ - mtsrr1 r7 - /* Load highmem handler address */ + PPC_LL r6, HSTATE_HOST_MSR(r13) PPC_LL r8, HSTATE_VMHANDLER(r13) + + /* Restore host msr -> SRR1 */ + mtsrr1 r6 + /* Load highmem handler address */ mtsrr0 r8 + /* RFI into the highmem handler, or jump to interrupt handler */ + beqctr RFI kvmppc_handler_trampoline_exit_end: diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index ee45fa01220e..bb6c988f010a 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -316,6 +316,11 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) { int ret; + if (!vcpu->arch.sane) { + kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + return -EINVAL; + } + local_irq_disable(); kvm_guest_enter(); ret = __kvmppc_vcpu_run(kvm_run, vcpu); @@ -618,6 +623,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { int i; + int r; vcpu->arch.pc = 0; vcpu->arch.shared->msr = 0; @@ -634,7 +640,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) kvmppc_init_timing_stats(vcpu); - return kvmppc_core_vcpu_setup(vcpu); + r = kvmppc_core_vcpu_setup(vcpu); + kvmppc_sanity_check(vcpu); + return r; } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 797a7447c268..26d20903f2bc 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -73,6 +73,8 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu) /* Since booke kvm only support one core, update all vcpus' PIR to 0 */ vcpu->vcpu_id = 0; + vcpu->arch.cpu_type = KVM_CPU_E500V2; + return 0; } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index a107c9be0fb1..0d843c6ba315 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -39,12 +39,8 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { -#ifndef CONFIG_KVM_BOOK3S_64_HV return !(v->arch.shared->msr & MSR_WE) || !!(v->arch.pending_exceptions); -#else - return !(v->arch.ceded) || !!(v->arch.pending_exceptions); -#endif } int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) @@ -95,6 +91,31 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) return r; } +int kvmppc_sanity_check(struct kvm_vcpu *vcpu) +{ + int r = false; + + /* We have to know what CPU to virtualize */ + if (!vcpu->arch.pvr) + goto out; + + /* PAPR only works with book3s_64 */ + if ((vcpu->arch.cpu_type != KVM_CPU_3S_64) && vcpu->arch.papr_enabled) + goto out; + +#ifdef CONFIG_KVM_BOOK3S_64_HV + /* HV KVM can only do PAPR mode for now */ + if (!vcpu->arch.papr_enabled) + goto out; +#endif + + r = true; + +out: + vcpu->arch.sane = r; + return r ? 0 : -EINVAL; +} + int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu) { enum emulation_result er; @@ -188,6 +209,8 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_PPC_BOOKE_SREGS: #else case KVM_CAP_PPC_SEGSTATE: + case KVM_CAP_PPC_HIOR: + case KVM_CAP_PPC_PAPR: #endif case KVM_CAP_PPC_UNSET_IRQ: case KVM_CAP_PPC_IRQ_LEVEL: @@ -258,6 +281,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) { struct kvm_vcpu *vcpu; vcpu = kvmppc_core_vcpu_create(kvm, id); + vcpu->arch.wqp = &vcpu->wq; if (!IS_ERR(vcpu)) kvmppc_create_vcpu_debugfs(vcpu, id); return vcpu; @@ -289,8 +313,8 @@ static void kvmppc_decrementer_func(unsigned long data) kvmppc_core_queue_dec(vcpu); - if (waitqueue_active(&vcpu->wq)) { - wake_up_interruptible(&vcpu->wq); + if (waitqueue_active(vcpu->arch.wqp)) { + wake_up_interruptible(vcpu->arch.wqp); vcpu->stat.halt_wakeup++; } } @@ -543,13 +567,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { - if (irq->irq == KVM_INTERRUPT_UNSET) + if (irq->irq == KVM_INTERRUPT_UNSET) { kvmppc_core_dequeue_external(vcpu, irq); - else - kvmppc_core_queue_external(vcpu, irq); + return 0; + } + + kvmppc_core_queue_external(vcpu, irq); - if (waitqueue_active(&vcpu->wq)) { - wake_up_interruptible(&vcpu->wq); + if (waitqueue_active(vcpu->arch.wqp)) { + wake_up_interruptible(vcpu->arch.wqp); vcpu->stat.halt_wakeup++; } else if (vcpu->cpu != -1) { smp_send_reschedule(vcpu->cpu); @@ -571,11 +597,18 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, r = 0; vcpu->arch.osi_enabled = true; break; + case KVM_CAP_PPC_PAPR: + r = 0; + vcpu->arch.papr_enabled = true; + break; default: r = -EINVAL; break; } + if (!r) + r = kvmppc_sanity_check(vcpu); + return r; } diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig index d733d7ca939c..b5d87067a58b 100644 --- a/arch/powerpc/platforms/40x/Kconfig +++ b/arch/powerpc/platforms/40x/Kconfig @@ -130,21 +130,21 @@ config 405GP bool select IBM405_ERR77 select IBM405_ERR51 - select IBM_NEW_EMAC_ZMII + select IBM_EMAC_ZMII config 405EP bool config 405EX bool - select IBM_NEW_EMAC_EMAC4 - select IBM_NEW_EMAC_RGMII + select IBM_EMAC_EMAC4 + select IBM_EMAC_RGMII config 405EZ bool - select IBM_NEW_EMAC_NO_FLOW_CTRL - select IBM_NEW_EMAC_MAL_CLR_ICINTSTAT - select IBM_NEW_EMAC_MAL_COMMON_ERR + select IBM_EMAC_NO_FLOW_CTRL + select IBM_EMAC_MAL_CLR_ICINTSTAT + select IBM_EMAC_MAL_COMMON_ERR config 405GPR bool diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index e958b6f48ec2..762322ce24a9 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -23,7 +23,7 @@ config BLUESTONE default n select PPC44x_SIMPLE select APM821xx - select IBM_NEW_EMAC_RGMII + select IBM_EMAC_RGMII help This option enables support for the APM APM821xx Evaluation board. @@ -122,8 +122,8 @@ config CANYONLANDS select PPC4xx_PCI_EXPRESS select PCI_MSI select PPC4xx_MSI - select IBM_NEW_EMAC_RGMII - select IBM_NEW_EMAC_ZMII + select IBM_EMAC_RGMII + select IBM_EMAC_ZMII help This option enables support for the AMCC PPC460EX evaluation board. @@ -135,8 +135,8 @@ config GLACIER select 460EX # Odd since it uses 460GT but the effects are the same select PCI select PPC4xx_PCI_EXPRESS - select IBM_NEW_EMAC_RGMII - select IBM_NEW_EMAC_ZMII + select IBM_EMAC_RGMII + select IBM_EMAC_ZMII help This option enables support for the AMCC PPC460GT evaluation board. @@ -161,7 +161,7 @@ config EIGER select 460SX select PCI select PPC4xx_PCI_EXPRESS - select IBM_NEW_EMAC_RGMII + select IBM_EMAC_RGMII help This option enables support for the AMCC PPC460SX evaluation board. @@ -260,59 +260,59 @@ config 440EP bool select PPC_FPU select IBM440EP_ERR42 - select IBM_NEW_EMAC_ZMII + select IBM_EMAC_ZMII select USB_ARCH_HAS_OHCI config 440EPX bool select PPC_FPU - select IBM_NEW_EMAC_EMAC4 - select IBM_NEW_EMAC_RGMII - select IBM_NEW_EMAC_ZMII + select IBM_EMAC_EMAC4 + select IBM_EMAC_RGMII + select IBM_EMAC_ZMII config 440GRX bool - select IBM_NEW_EMAC_EMAC4 - select IBM_NEW_EMAC_RGMII - select IBM_NEW_EMAC_ZMII + select IBM_EMAC_EMAC4 + select IBM_EMAC_RGMII + select IBM_EMAC_ZMII config 440GP bool - select IBM_NEW_EMAC_ZMII + select IBM_EMAC_ZMII config 440GX bool - select IBM_NEW_EMAC_EMAC4 - select IBM_NEW_EMAC_RGMII - select IBM_NEW_EMAC_ZMII #test only - select IBM_NEW_EMAC_TAH #test only + select IBM_EMAC_EMAC4 + select IBM_EMAC_RGMII + select IBM_EMAC_ZMII #test only + select IBM_EMAC_TAH #test only config 440SP bool config 440SPe bool - select IBM_NEW_EMAC_EMAC4 + select IBM_EMAC_EMAC4 config 460EX bool select PPC_FPU - select IBM_NEW_EMAC_EMAC4 - select IBM_NEW_EMAC_TAH + select IBM_EMAC_EMAC4 + select IBM_EMAC_TAH config 460SX bool select PPC_FPU - select IBM_NEW_EMAC_EMAC4 - select IBM_NEW_EMAC_RGMII - select IBM_NEW_EMAC_ZMII - select IBM_NEW_EMAC_TAH + select IBM_EMAC_EMAC4 + select IBM_EMAC_RGMII + select IBM_EMAC_ZMII + select IBM_EMAC_TAH config APM821xx bool select PPC_FPU - select IBM_NEW_EMAC_EMAC4 - select IBM_NEW_EMAC_TAH + select IBM_EMAC_EMAC4 + select IBM_EMAC_TAH # 44x errata/workaround config symbols, selected by the CPU models above config IBM440EP_ERR42 diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c index e41ebbdb3e12..cfe958e94e1e 100644 --- a/arch/powerpc/platforms/512x/mpc512x_shared.c +++ b/arch/powerpc/platforms/512x/mpc512x_shared.c @@ -66,8 +66,8 @@ struct fsl_diu_shared_fb { bool in_use; }; -unsigned int mpc512x_get_pixel_format(unsigned int bits_per_pixel, - int monitor_port) +u32 mpc512x_get_pixel_format(enum fsl_diu_monitor_port port, + unsigned int bits_per_pixel) { switch (bits_per_pixel) { case 32: @@ -80,11 +80,12 @@ unsigned int mpc512x_get_pixel_format(unsigned int bits_per_pixel, return 0x00000400; } -void mpc512x_set_gamma_table(int monitor_port, char *gamma_table_base) +void mpc512x_set_gamma_table(enum fsl_diu_monitor_port port, + char *gamma_table_base) { } -void mpc512x_set_monitor_port(int monitor_port) +void mpc512x_set_monitor_port(enum fsl_diu_monitor_port port) { } @@ -182,14 +183,10 @@ void mpc512x_set_pixel_clock(unsigned int pixclock) iounmap(ccm); } -ssize_t mpc512x_show_monitor_port(int monitor_port, char *buf) +enum fsl_diu_monitor_port +mpc512x_valid_monitor_port(enum fsl_diu_monitor_port port) { - return sprintf(buf, "0 - 5121 LCD\n"); -} - -int mpc512x_set_sysfs_monitor_port(int val) -{ - return 0; + return FSL_DIU_PORT_DVI; } static struct fsl_diu_shared_fb __attribute__ ((__aligned__(8))) diu_shared_fb; @@ -256,7 +253,7 @@ void __init mpc512x_init_diu(void) } mode = in_be32(&diu_reg->diu_mode); - if (mode != MFB_MODE1) { + if (mode == MFB_MODE0) { pr_info("%s: DIU OFF\n", __func__); goto out; } @@ -332,8 +329,7 @@ void __init mpc512x_setup_diu(void) diu_ops.set_gamma_table = mpc512x_set_gamma_table; diu_ops.set_monitor_port = mpc512x_set_monitor_port; diu_ops.set_pixel_clock = mpc512x_set_pixel_clock; - diu_ops.show_monitor_port = mpc512x_show_monitor_port; - diu_ops.set_sysfs_monitor_port = mpc512x_set_sysfs_monitor_port; + diu_ops.valid_monitor_port = mpc512x_valid_monitor_port; diu_ops.release_bootmem = mpc512x_release_bootmem; #endif } diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index 498534cd5265..12f5932dadc9 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -80,7 +80,7 @@ config P1010_RDB config P1022_DS bool "Freescale P1022 DS" select DEFAULT_UIMAGE - select CONFIG_PHYS_64BIT # The DTS has 36-bit addresses + select PHYS_64BIT # The DTS has 36-bit addresses select SWIOTLB help This option enables support for the Freescale P1022DS reference board. diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c index 266b3aadfe5e..c01c7277888c 100644 --- a/arch/powerpc/platforms/85xx/p1022_ds.c +++ b/arch/powerpc/platforms/85xx/p1022_ds.c @@ -93,8 +93,8 @@ * The Area Descriptor is a 32-bit value that determine which bits in each * pixel are to be used for each color. */ -static unsigned int p1022ds_get_pixel_format(unsigned int bits_per_pixel, - int monitor_port) +static u32 p1022ds_get_pixel_format(enum fsl_diu_monitor_port port, + unsigned int bits_per_pixel) { switch (bits_per_pixel) { case 32: @@ -118,7 +118,8 @@ static unsigned int p1022ds_get_pixel_format(unsigned int bits_per_pixel, * On some boards, the gamma table for some ports may need to be modified. * This is not the case on the P1022DS, so we do nothing. */ -static void p1022ds_set_gamma_table(int monitor_port, char *gamma_table_base) +static void p1022ds_set_gamma_table(enum fsl_diu_monitor_port port, + char *gamma_table_base) { } @@ -126,7 +127,7 @@ static void p1022ds_set_gamma_table(int monitor_port, char *gamma_table_base) * p1022ds_set_monitor_port: switch the output to a different monitor port * */ -static void p1022ds_set_monitor_port(int monitor_port) +static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port) { struct device_node *pixis_node; void __iomem *pixis; @@ -145,19 +146,21 @@ static void p1022ds_set_monitor_port(int monitor_port) } brdcfg1 = pixis + 9; /* BRDCFG1 is at offset 9 in the ngPIXIS */ - switch (monitor_port) { - case 0: /* DVI */ + switch (port) { + case FSL_DIU_PORT_DVI: + printk(KERN_INFO "%s:%u\n", __func__, __LINE__); /* Enable the DVI port, disable the DFP and the backlight */ clrsetbits_8(brdcfg1, PX_BRDCFG1_DFPEN | PX_BRDCFG1_BACKLIGHT, PX_BRDCFG1_DVIEN); break; - case 1: /* Single link LVDS */ + case FSL_DIU_PORT_LVDS: + printk(KERN_INFO "%s:%u\n", __func__, __LINE__); /* Enable the DFP port, disable the DVI and the backlight */ clrsetbits_8(brdcfg1, PX_BRDCFG1_DVIEN | PX_BRDCFG1_BACKLIGHT, PX_BRDCFG1_DFPEN); break; default: - pr_err("p1022ds: unsupported monitor port %i\n", monitor_port); + pr_err("p1022ds: unsupported monitor port %i\n", port); } iounmap(pixis); @@ -214,23 +217,18 @@ void p1022ds_set_pixel_clock(unsigned int pixclock) } /** - * p1022ds_show_monitor_port: show the current monitor - * - * This function returns a string indicating whether the current monitor is - * set to DVI or LVDS. - */ -ssize_t p1022ds_show_monitor_port(int monitor_port, char *buf) -{ - return sprintf(buf, "%c0 - DVI\n%c1 - Single link LVDS\n", - monitor_port == 0 ? '*' : ' ', monitor_port == 1 ? '*' : ' '); -} - -/** - * p1022ds_set_sysfs_monitor_port: set the monitor port for sysfs + * p1022ds_valid_monitor_port: set the monitor port for sysfs */ -int p1022ds_set_sysfs_monitor_port(int val) +enum fsl_diu_monitor_port +p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port) { - return val < 2 ? val : 0; + switch (port) { + case FSL_DIU_PORT_DVI: + case FSL_DIU_PORT_LVDS: + return port; + default: + return FSL_DIU_PORT_DVI; /* Dual-link LVDS is not supported */ + } } #endif @@ -305,8 +303,7 @@ static void __init p1022_ds_setup_arch(void) diu_ops.set_gamma_table = p1022ds_set_gamma_table; diu_ops.set_monitor_port = p1022ds_set_monitor_port; diu_ops.set_pixel_clock = p1022ds_set_pixel_clock; - diu_ops.show_monitor_port = p1022ds_show_monitor_port; - diu_ops.set_sysfs_monitor_port = p1022ds_set_sysfs_monitor_port; + diu_ops.valid_monitor_port = p1022ds_valid_monitor_port; #endif #ifdef CONFIG_SMP diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c index 74e018ef724b..13fa9a6403e6 100644 --- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c +++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c @@ -152,10 +152,10 @@ machine_device_initcall(mpc86xx_hpcd, mpc8610_declare_of_platform_devices); (c2 << AD_COMP_2_SHIFT) | (c1 << AD_COMP_1_SHIFT) | \ (c0 << AD_COMP_0_SHIFT) | (size << AD_PIXEL_S_SHIFT)) -unsigned int mpc8610hpcd_get_pixel_format(unsigned int bits_per_pixel, - int monitor_port) +u32 mpc8610hpcd_get_pixel_format(enum fsl_diu_monitor_port port, + unsigned int bits_per_pixel) { - static const unsigned long pixelformat[][3] = { + static const u32 pixelformat[][3] = { { MAKE_AD(3, 0, 2, 1, 3, 8, 8, 8, 8), MAKE_AD(4, 2, 0, 1, 2, 8, 8, 8, 0), @@ -170,7 +170,8 @@ unsigned int mpc8610hpcd_get_pixel_format(unsigned int bits_per_pixel, unsigned int arch_monitor; /* The DVI port is mis-wired on revision 1 of this board. */ - arch_monitor = ((*pixis_arch == 0x01) && (monitor_port == 0))? 0 : 1; + arch_monitor = + ((*pixis_arch == 0x01) && (port == FSL_DIU_PORT_DVI)) ? 0 : 1; switch (bits_per_pixel) { case 32: @@ -185,10 +186,11 @@ unsigned int mpc8610hpcd_get_pixel_format(unsigned int bits_per_pixel, } } -void mpc8610hpcd_set_gamma_table(int monitor_port, char *gamma_table_base) +void mpc8610hpcd_set_gamma_table(enum fsl_diu_monitor_port port, + char *gamma_table_base) { int i; - if (monitor_port == 2) { /* dual link LVDS */ + if (port == FSL_DIU_PORT_DLVDS) { for (i = 0; i < 256*3; i++) gamma_table_base[i] = (gamma_table_base[i] << 2) | ((gamma_table_base[i] >> 6) & 0x03); @@ -199,17 +201,21 @@ void mpc8610hpcd_set_gamma_table(int monitor_port, char *gamma_table_base) #define PX_BRDCFG0_DLINK (1 << 4) #define PX_BRDCFG0_DIU_MASK (PX_BRDCFG0_DVISEL | PX_BRDCFG0_DLINK) -void mpc8610hpcd_set_monitor_port(int monitor_port) +void mpc8610hpcd_set_monitor_port(enum fsl_diu_monitor_port port) { - static const u8 bdcfg[] = { - PX_BRDCFG0_DVISEL | PX_BRDCFG0_DLINK, - PX_BRDCFG0_DLINK, - 0, - }; - - if (monitor_port < 3) + switch (port) { + case FSL_DIU_PORT_DVI: clrsetbits_8(pixis_bdcfg0, PX_BRDCFG0_DIU_MASK, - bdcfg[monitor_port]); + PX_BRDCFG0_DVISEL | PX_BRDCFG0_DLINK); + break; + case FSL_DIU_PORT_LVDS: + clrsetbits_8(pixis_bdcfg0, PX_BRDCFG0_DIU_MASK, + PX_BRDCFG0_DLINK); + break; + case FSL_DIU_PORT_DLVDS: + clrbits8(pixis_bdcfg0, PX_BRDCFG0_DIU_MASK); + break; + } } /** @@ -262,20 +268,10 @@ void mpc8610hpcd_set_pixel_clock(unsigned int pixclock) iounmap(guts); } -ssize_t mpc8610hpcd_show_monitor_port(int monitor_port, char *buf) -{ - return snprintf(buf, PAGE_SIZE, - "%c0 - DVI\n" - "%c1 - Single link LVDS\n" - "%c2 - Dual link LVDS\n", - monitor_port == 0 ? '*' : ' ', - monitor_port == 1 ? '*' : ' ', - monitor_port == 2 ? '*' : ' '); -} - -int mpc8610hpcd_set_sysfs_monitor_port(int val) +enum fsl_diu_monitor_port +mpc8610hpcd_valid_monitor_port(enum fsl_diu_monitor_port port) { - return val < 3 ? val : 0; + return port; } #endif @@ -307,8 +303,7 @@ static void __init mpc86xx_hpcd_setup_arch(void) diu_ops.set_gamma_table = mpc8610hpcd_set_gamma_table; diu_ops.set_monitor_port = mpc8610hpcd_set_monitor_port; diu_ops.set_pixel_clock = mpc8610hpcd_set_pixel_clock; - diu_ops.show_monitor_port = mpc8610hpcd_show_monitor_port; - diu_ops.set_sysfs_monitor_port = mpc8610hpcd_set_sysfs_monitor_port; + diu_ops.valid_monitor_port = mpc8610hpcd_valid_monitor_port; #endif pixis_node = of_find_compatible_node(NULL, NULL, "fsl,fpga-pixis"); diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 67d5009b4e86..2e7ff0c5cf42 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -17,10 +17,10 @@ config PPC_CELL_NATIVE select PPC_CELL_COMMON select MPIC select PPC_IO_WORKAROUNDS - select IBM_NEW_EMAC_EMAC4 - select IBM_NEW_EMAC_RGMII - select IBM_NEW_EMAC_ZMII #test only - select IBM_NEW_EMAC_TAH #test only + select IBM_EMAC_EMAC4 + select IBM_EMAC_RGMII + select IBM_EMAC_ZMII #test only + select IBM_EMAC_TAH #test only default n config PPC_IBM_CELL_BLADE diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c b/arch/powerpc/platforms/embedded6xx/storcenter.c index 613070e9ddbe..f1eebcae9bf0 100644 --- a/arch/powerpc/platforms/embedded6xx/storcenter.c +++ b/arch/powerpc/platforms/embedded6xx/storcenter.c @@ -77,7 +77,7 @@ static void __init storcenter_setup_arch(void) } /* - * Interrupt setup and service. Interrrupts on the turbostation come + * Interrupt setup and service. Interrupts on the turbostation come * from the four PCI slots plus onboard 8241 devices: I2C, DUART. */ static void __init storcenter_init_IRQ(void) diff --git a/arch/powerpc/sysdev/fsl_soc.h b/arch/powerpc/sysdev/fsl_soc.h index 2ece02beb8ff..c6d00736f07f 100644 --- a/arch/powerpc/sysdev/fsl_soc.h +++ b/arch/powerpc/sysdev/fsl_soc.h @@ -22,15 +22,24 @@ struct device_node; extern void fsl_rstcr_restart(char *cmd); #if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE) + +/* The different ports that the DIU can be connected to */ +enum fsl_diu_monitor_port { + FSL_DIU_PORT_DVI, /* DVI */ + FSL_DIU_PORT_LVDS, /* Single-link LVDS */ + FSL_DIU_PORT_DLVDS /* Dual-link LVDS */ +}; + struct platform_diu_data_ops { - unsigned int (*get_pixel_format) (unsigned int bits_per_pixel, - int monitor_port); - void (*set_gamma_table) (int monitor_port, char *gamma_table_base); - void (*set_monitor_port) (int monitor_port); - void (*set_pixel_clock) (unsigned int pixclock); - ssize_t (*show_monitor_port) (int monitor_port, char *buf); - int (*set_sysfs_monitor_port) (int val); - void (*release_bootmem) (void); + u32 (*get_pixel_format)(enum fsl_diu_monitor_port port, + unsigned int bpp); + void (*set_gamma_table)(enum fsl_diu_monitor_port port, + char *gamma_table_base); + void (*set_monitor_port)(enum fsl_diu_monitor_port port); + void (*set_pixel_clock)(unsigned int pixclock); + enum fsl_diu_monitor_port (*valid_monitor_port) + (enum fsl_diu_monitor_port port); + void (*release_bootmem)(void); }; extern struct platform_diu_data_ops diu_ops; diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c index 904c6cbaf45b..3363fbc964f8 100644 --- a/arch/powerpc/sysdev/qe_lib/qe.c +++ b/arch/powerpc/sysdev/qe_lib/qe.c @@ -382,7 +382,7 @@ static void qe_upload_microcode(const void *base, /* * Upload a microcode to the I-RAM at a specific address. * - * See Documentation/powerpc/qe-firmware.txt for information on QE microcode + * See Documentation/powerpc/qe_firmware.txt for information on QE microcode * uploading. * * Currently, only version 1 is supported, so the 'version' field must be diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c index 984cd2029158..3330feca7502 100644 --- a/arch/powerpc/sysdev/uic.c +++ b/arch/powerpc/sysdev/uic.c @@ -47,7 +47,7 @@ struct uic { int index; int dcrbase; - spinlock_t lock; + raw_spinlock_t lock; /* The remapper for this UIC */ struct irq_host *irqhost; @@ -61,14 +61,14 @@ static void uic_unmask_irq(struct irq_data *d) u32 er, sr; sr = 1 << (31-src); - spin_lock_irqsave(&uic->lock, flags); + raw_spin_lock_irqsave(&uic->lock, flags); /* ack level-triggered interrupts here */ if (irqd_is_level_type(d)) mtdcr(uic->dcrbase + UIC_SR, sr); er = mfdcr(uic->dcrbase + UIC_ER); er |= sr; mtdcr(uic->dcrbase + UIC_ER, er); - spin_unlock_irqrestore(&uic->lock, flags); + raw_spin_unlock_irqrestore(&uic->lock, flags); } static void uic_mask_irq(struct irq_data *d) @@ -78,11 +78,11 @@ static void uic_mask_irq(struct irq_data *d) unsigned long flags; u32 er; - spin_lock_irqsave(&uic->lock, flags); + raw_spin_lock_irqsave(&uic->lock, flags); er = mfdcr(uic->dcrbase + UIC_ER); er &= ~(1 << (31 - src)); mtdcr(uic->dcrbase + UIC_ER, er); - spin_unlock_irqrestore(&uic->lock, flags); + raw_spin_unlock_irqrestore(&uic->lock, flags); } static void uic_ack_irq(struct irq_data *d) @@ -91,9 +91,9 @@ static void uic_ack_irq(struct irq_data *d) unsigned int src = irqd_to_hwirq(d); unsigned long flags; - spin_lock_irqsave(&uic->lock, flags); + raw_spin_lock_irqsave(&uic->lock, flags); mtdcr(uic->dcrbase + UIC_SR, 1 << (31-src)); - spin_unlock_irqrestore(&uic->lock, flags); + raw_spin_unlock_irqrestore(&uic->lock, flags); } static void uic_mask_ack_irq(struct irq_data *d) @@ -104,7 +104,7 @@ static void uic_mask_ack_irq(struct irq_data *d) u32 er, sr; sr = 1 << (31-src); - spin_lock_irqsave(&uic->lock, flags); + raw_spin_lock_irqsave(&uic->lock, flags); er = mfdcr(uic->dcrbase + UIC_ER); er &= ~sr; mtdcr(uic->dcrbase + UIC_ER, er); @@ -118,7 +118,7 @@ static void uic_mask_ack_irq(struct irq_data *d) */ if (!irqd_is_level_type(d)) mtdcr(uic->dcrbase + UIC_SR, sr); - spin_unlock_irqrestore(&uic->lock, flags); + raw_spin_unlock_irqrestore(&uic->lock, flags); } static int uic_set_irq_type(struct irq_data *d, unsigned int flow_type) @@ -152,7 +152,7 @@ static int uic_set_irq_type(struct irq_data *d, unsigned int flow_type) mask = ~(1 << (31 - src)); - spin_lock_irqsave(&uic->lock, flags); + raw_spin_lock_irqsave(&uic->lock, flags); tr = mfdcr(uic->dcrbase + UIC_TR); pr = mfdcr(uic->dcrbase + UIC_PR); tr = (tr & mask) | (trigger << (31-src)); @@ -161,7 +161,7 @@ static int uic_set_irq_type(struct irq_data *d, unsigned int flow_type) mtdcr(uic->dcrbase + UIC_PR, pr); mtdcr(uic->dcrbase + UIC_TR, tr); - spin_unlock_irqrestore(&uic->lock, flags); + raw_spin_unlock_irqrestore(&uic->lock, flags); return 0; } @@ -254,7 +254,7 @@ static struct uic * __init uic_init_one(struct device_node *node) if (! uic) return NULL; /* FIXME: panic? */ - spin_lock_init(&uic->lock); + raw_spin_lock_init(&uic->lock); indexp = of_get_property(node, "cell-index", &len); if (!indexp || (len != sizeof(u32))) { printk(KERN_ERR "uic: Device node %s has missing or invalid " diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index ed5cb5af5281..a9fbd43395f7 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -91,6 +91,7 @@ config S390 select HAVE_ARCH_MUTEX_CPU_RELAX select HAVE_ARCH_JUMP_LABEL if !MARCH_G5 select HAVE_RCU_TABLE_FREE if SMP + select ARCH_SAVE_PAGE_KEYS if HIBERNATION select ARCH_INLINE_SPIN_TRYLOCK select ARCH_INLINE_SPIN_TRYLOCK_BH select ARCH_INLINE_SPIN_LOCK @@ -568,6 +569,16 @@ config KEXEC current kernel, and to start another kernel. It is like a reboot but is independent of hardware/microcode support. +config CRASH_DUMP + bool "kernel crash dumps" + depends on 64BIT + help + Generate crash dump after being started by kexec. + Crash dump kernels are loaded in the main kernel with kexec-tools + into a specially reserved region and then later executed after + a crash by kdump/kexec. + For more details see Documentation/kdump/kdump.txt + config ZFCPDUMP def_bool n prompt "zfcpdump support" diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c index 028f23ea81d1..465eca756feb 100644 --- a/arch/s390/boot/compressed/misc.c +++ b/arch/s390/boot/compressed/misc.c @@ -61,7 +61,7 @@ static unsigned long free_mem_end_ptr; extern _sclp_print_early(const char *); -int puts(const char *s) +static int puts(const char *s) { _sclp_print_early(s); return 0; diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 29c82c640a88..6cf8e26b3137 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -68,7 +68,7 @@ CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_POLICE=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" -# CONFIG_FIRMWARE_IN_KERNEL is not set +CONFIG_DEVTMPFS=y CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c index 6023c6dc1fb7..74c8f5e76ce4 100644 --- a/arch/s390/hypfs/hypfs_diag.c +++ b/arch/s390/hypfs/hypfs_diag.c @@ -562,10 +562,9 @@ static int dbfs_d204_create(void **data, void **data_free_ptr, size_t *size) void *base; buf_size = PAGE_SIZE * (diag204_buf_pages + 1) + sizeof(d204->hdr); - base = vmalloc(buf_size); + base = vzalloc(buf_size); if (!base) return -ENOMEM; - memset(base, 0, buf_size); d204 = page_align_ptr(base + sizeof(d204->hdr)) - sizeof(d204->hdr); rc = diag204_do_store(d204->buf, diag204_buf_pages); if (rc) { diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h index 623f2fb71774..9381c92cc779 100644 --- a/arch/s390/include/asm/ccwdev.h +++ b/arch/s390/include/asm/ccwdev.h @@ -11,6 +11,7 @@ #include <linux/device.h> #include <linux/mod_devicetable.h> #include <asm/fcx.h> +#include <asm/irq.h> /* structs from asm/cio.h */ struct irb; @@ -127,6 +128,7 @@ enum uc_todo { * @restore: callback for restoring after hibernation * @uc_handler: callback for unit check handler * @driver: embedded device driver structure + * @int_class: interruption class to use for accounting interrupts */ struct ccw_driver { struct ccw_device_id *ids; @@ -144,6 +146,7 @@ struct ccw_driver { int (*restore)(struct ccw_device *); enum uc_todo (*uc_handler) (struct ccw_device *, struct irb *); struct device_driver driver; + enum interruption_class int_class; }; extern struct ccw_device *get_ccwdev_by_busid(struct ccw_driver *cdrv, diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index da359ca6fe55..2e49748b27da 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -12,6 +12,7 @@ #define PSW32_MASK_IO 0x02000000UL #define PSW32_MASK_EXT 0x01000000UL #define PSW32_MASK_KEY 0x00F00000UL +#define PSW32_MASK_BASE 0x00080000UL /* Always one */ #define PSW32_MASK_MCHECK 0x00040000UL #define PSW32_MASK_WAIT 0x00020000UL #define PSW32_MASK_PSTATE 0x00010000UL @@ -19,21 +20,19 @@ #define PSW32_MASK_CC 0x00003000UL #define PSW32_MASK_PM 0x00000f00UL -#define PSW32_ADDR_AMODE31 0x80000000UL +#define PSW32_MASK_USER 0x00003F00UL + +#define PSW32_ADDR_AMODE 0x80000000UL #define PSW32_ADDR_INSN 0x7FFFFFFFUL -#define PSW32_BASE_BITS 0x00080000UL +#define PSW32_DEFAULT_KEY (((u32) PAGE_DEFAULT_ACC) << 20) #define PSW32_ASC_PRIMARY 0x00000000UL #define PSW32_ASC_ACCREG 0x00004000UL #define PSW32_ASC_SECONDARY 0x00008000UL #define PSW32_ASC_HOME 0x0000C000UL -#define PSW32_MASK_MERGE(CURRENT,NEW) \ - (((CURRENT) & ~(PSW32_MASK_CC|PSW32_MASK_PM)) | \ - ((NEW) & (PSW32_MASK_CC|PSW32_MASK_PM))) - -extern long psw32_user_bits; +extern u32 psw32_user_bits; #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "s390\0\0\0\0" @@ -131,7 +130,8 @@ struct compat_statfs { compat_fsid_t f_fsid; s32 f_namelen; s32 f_frsize; - s32 f_spare[6]; + s32 f_flags; + s32 f_spare[5]; }; #define COMPAT_RLIM_OLD_INFINITY 0x7fffffff diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h index 97cc4403fabf..6940abfbe1d9 100644 --- a/arch/s390/include/asm/ipl.h +++ b/arch/s390/include/asm/ipl.h @@ -168,5 +168,6 @@ enum diag308_rc { extern int diag308(unsigned long subcode, void *addr); extern void diag308_reset(void); +extern void store_status(void); #endif /* _ASM_S390_IPL_H */ diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h index ba7b01c726a3..ba6d85f88d50 100644 --- a/arch/s390/include/asm/irq.h +++ b/arch/s390/include/asm/irq.h @@ -8,7 +8,8 @@ enum interruption_class { EXTERNAL_INTERRUPT, IO_INTERRUPT, EXTINT_CLK, - EXTINT_IPI, + EXTINT_EXC, + EXTINT_EMS, EXTINT_TMR, EXTINT_TLA, EXTINT_PFL, @@ -17,8 +18,8 @@ enum interruption_class { EXTINT_SCP, EXTINT_IUC, EXTINT_CPM, + IOINT_CIO, IOINT_QAI, - IOINT_QDI, IOINT_DAS, IOINT_C15, IOINT_C70, @@ -28,6 +29,7 @@ enum interruption_class { IOINT_CLW, IOINT_CTC, IOINT_APB, + IOINT_CSC, NMI_NMI, NR_IRQS, }; diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h index bb729b84a21e..cf4e47b0948c 100644 --- a/arch/s390/include/asm/kexec.h +++ b/arch/s390/include/asm/kexec.h @@ -30,9 +30,15 @@ /* Not more than 2GB */ #define KEXEC_CONTROL_MEMORY_LIMIT (1UL<<31) +/* Maximum address we can use for the crash control pages */ +#define KEXEC_CRASH_CONTROL_MEMORY_LIMIT (-1UL) + /* Allocate one page for the pdp and the second for the code */ #define KEXEC_CONTROL_PAGE_SIZE 4096 +/* Alignment of crashkernel memory */ +#define KEXEC_CRASH_MEM_ALIGN HPAGE_SIZE + /* The native architecture */ #define KEXEC_ARCH KEXEC_ARCH_S390 diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 00ff00dfb24c..24e18473d926 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -119,6 +119,7 @@ struct kvm_vcpu_stat { u32 instruction_lctlg; u32 exit_program_interruption; u32 exit_instr_and_program; + u32 deliver_external_call; u32 deliver_emergency_signal; u32 deliver_service_signal; u32 deliver_virtio_interrupt; @@ -138,11 +139,13 @@ struct kvm_vcpu_stat { u32 instruction_stfl; u32 instruction_tprot; u32 instruction_sigp_sense; + u32 instruction_sigp_external_call; u32 instruction_sigp_emergency; u32 instruction_sigp_stop; u32 instruction_sigp_arch; u32 instruction_sigp_prefix; u32 instruction_sigp_restart; + u32 diagnose_10; u32 diagnose_44; }; @@ -174,6 +177,10 @@ struct kvm_s390_prefix_info { __u32 address; }; +struct kvm_s390_extcall_info { + __u16 code; +}; + struct kvm_s390_emerg_info { __u16 code; }; @@ -186,6 +193,7 @@ struct kvm_s390_interrupt_info { struct kvm_s390_ext_info ext; struct kvm_s390_pgm_info pgm; struct kvm_s390_emerg_info emerg; + struct kvm_s390_extcall_info extcall; struct kvm_s390_prefix_info prefix; }; }; diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index e85c911aabf0..9e13c7d56cc1 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -151,10 +151,8 @@ struct _lowcore { */ __u32 ipib; /* 0x0e00 */ __u32 ipib_checksum; /* 0x0e04 */ - - /* 64 bit save area */ - __u64 save_area_64; /* 0x0e08 */ - __u8 pad_0x0e10[0x0f00-0x0e10]; /* 0x0e10 */ + __u32 vmcore_info; /* 0x0e08 */ + __u8 pad_0x0e0c[0x0f00-0x0e0c]; /* 0x0e0c */ /* Extended facility list */ __u64 stfle_fac_list[32]; /* 0x0f00 */ @@ -290,9 +288,7 @@ struct _lowcore { */ __u64 ipib; /* 0x0e00 */ __u32 ipib_checksum; /* 0x0e08 */ - - /* 64 bit save area */ - __u64 save_area_64; /* 0x0e0c */ + __u64 vmcore_info; /* 0x0e0c */ __u8 pad_0x0e14[0x0f00-0x0e14]; /* 0x0e14 */ /* Extended facility list */ diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index accb372ddc7e..f7ec548c2b9d 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -177,6 +177,7 @@ static inline int page_test_and_clear_young(unsigned long pfn) struct page; void arch_free_page(struct page *page, int order); void arch_alloc_page(struct page *page, int order); +void arch_set_page_states(int make_stable); static inline int devmem_is_allowed(unsigned long pfn) { diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index c0cb794bb365..34ede0ea85a9 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -696,7 +696,9 @@ void gmap_disable(struct gmap *gmap); int gmap_map_segment(struct gmap *gmap, unsigned long from, unsigned long to, unsigned long length); int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len); +unsigned long __gmap_fault(unsigned long address, struct gmap *); unsigned long gmap_fault(unsigned long address, struct gmap *); +void gmap_discard(unsigned long from, unsigned long to, struct gmap *); /* * Certain architectures need to do special things when PTEs diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index a4b6229e5d4b..5f33d37d032c 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -33,6 +33,8 @@ static inline void get_cpu_id(struct cpuid *ptr) extern void s390_adjust_jiffies(void); extern int get_cpu_capability(unsigned int *); +extern const struct seq_operations cpuinfo_op; +extern int sysctl_ieee_emulation_warnings; /* * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit. @@ -118,17 +120,17 @@ struct stack_frame { /* * Do necessary setup to start up a new thread. */ -#define start_thread(regs, new_psw, new_stackp) do { \ - regs->psw.mask = psw_user_bits; \ - regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ - regs->gprs[15] = new_stackp; \ +#define start_thread(regs, new_psw, new_stackp) do { \ + regs->psw.mask = psw_user_bits | PSW_MASK_EA | PSW_MASK_BA; \ + regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ + regs->gprs[15] = new_stackp; \ } while (0) -#define start_thread31(regs, new_psw, new_stackp) do { \ - regs->psw.mask = psw_user32_bits; \ - regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ - regs->gprs[15] = new_stackp; \ - crst_table_downgrade(current->mm, 1UL << 31); \ +#define start_thread31(regs, new_psw, new_stackp) do { \ + regs->psw.mask = psw_user_bits | PSW_MASK_BA; \ + regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ + regs->gprs[15] = new_stackp; \ + crst_table_downgrade(current->mm, 1UL << 31); \ } while (0) /* Forward declaration, a strange C thing */ @@ -187,7 +189,6 @@ static inline void __load_psw(psw_t psw) * Set PSW mask to specified value, while leaving the * PSW addr pointing to the next instruction. */ - static inline void __load_psw_mask (unsigned long mask) { unsigned long addr; @@ -212,26 +213,37 @@ static inline void __load_psw_mask (unsigned long mask) : "=&d" (addr), "=Q" (psw) : "Q" (psw) : "memory", "cc"); #endif /* __s390x__ */ } - + /* - * Function to stop a processor until an interruption occurred + * Rewind PSW instruction address by specified number of bytes. */ -static inline void enabled_wait(void) +static inline unsigned long __rewind_psw(psw_t psw, unsigned long ilc) { - __load_psw_mask(PSW_BASE_BITS | PSW_MASK_IO | PSW_MASK_EXT | - PSW_MASK_MCHECK | PSW_MASK_WAIT | PSW_DEFAULT_KEY); -} +#ifndef __s390x__ + if (psw.addr & PSW_ADDR_AMODE) + /* 31 bit mode */ + return (psw.addr - ilc) | PSW_ADDR_AMODE; + /* 24 bit mode */ + return (psw.addr - ilc) & ((1UL << 24) - 1); +#else + unsigned long mask; + mask = (psw.mask & PSW_MASK_EA) ? -1UL : + (psw.mask & PSW_MASK_BA) ? (1UL << 31) - 1 : + (1UL << 24) - 1; + return (psw.addr - ilc) & mask; +#endif +} + /* * Function to drop a processor into disabled wait state */ - static inline void ATTRIB_NORET disabled_wait(unsigned long code) { unsigned long ctl_buf; psw_t dw_psw; - dw_psw.mask = PSW_BASE_BITS | PSW_MASK_WAIT; + dw_psw.mask = PSW_MASK_BASE | PSW_MASK_WAIT | PSW_MASK_BA | PSW_MASK_EA; dw_psw.addr = code; /* * Store status and then load disabled wait psw, diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 62fd80c9e98c..a65846340d51 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -230,17 +230,21 @@ typedef struct #define PSW_MASK_IO 0x02000000UL #define PSW_MASK_EXT 0x01000000UL #define PSW_MASK_KEY 0x00F00000UL +#define PSW_MASK_BASE 0x00080000UL /* always one */ #define PSW_MASK_MCHECK 0x00040000UL #define PSW_MASK_WAIT 0x00020000UL #define PSW_MASK_PSTATE 0x00010000UL #define PSW_MASK_ASC 0x0000C000UL #define PSW_MASK_CC 0x00003000UL #define PSW_MASK_PM 0x00000F00UL +#define PSW_MASK_EA 0x00000000UL +#define PSW_MASK_BA 0x00000000UL + +#define PSW_MASK_USER 0x00003F00UL #define PSW_ADDR_AMODE 0x80000000UL #define PSW_ADDR_INSN 0x7FFFFFFFUL -#define PSW_BASE_BITS 0x00080000UL #define PSW_DEFAULT_KEY (((unsigned long) PAGE_DEFAULT_ACC) << 20) #define PSW_ASC_PRIMARY 0x00000000UL @@ -254,6 +258,7 @@ typedef struct #define PSW_MASK_DAT 0x0400000000000000UL #define PSW_MASK_IO 0x0200000000000000UL #define PSW_MASK_EXT 0x0100000000000000UL +#define PSW_MASK_BASE 0x0000000000000000UL #define PSW_MASK_KEY 0x00F0000000000000UL #define PSW_MASK_MCHECK 0x0004000000000000UL #define PSW_MASK_WAIT 0x0002000000000000UL @@ -261,12 +266,14 @@ typedef struct #define PSW_MASK_ASC 0x0000C00000000000UL #define PSW_MASK_CC 0x0000300000000000UL #define PSW_MASK_PM 0x00000F0000000000UL +#define PSW_MASK_EA 0x0000000100000000UL +#define PSW_MASK_BA 0x0000000080000000UL + +#define PSW_MASK_USER 0x00003F0180000000UL #define PSW_ADDR_AMODE 0x0000000000000000UL #define PSW_ADDR_INSN 0xFFFFFFFFFFFFFFFFUL -#define PSW_BASE_BITS 0x0000000180000000UL -#define PSW_BASE32_BITS 0x0000000080000000UL #define PSW_DEFAULT_KEY (((unsigned long) PAGE_DEFAULT_ACC) << 52) #define PSW_ASC_PRIMARY 0x0000000000000000UL @@ -279,18 +286,7 @@ typedef struct #ifdef __KERNEL__ extern long psw_kernel_bits; extern long psw_user_bits; -#ifdef CONFIG_64BIT -extern long psw_user32_bits; #endif -#endif - -/* This macro merges a NEW PSW mask specified by the user into - the currently active PSW mask CURRENT, modifying only those - bits in CURRENT that the user may be allowed to change: this - is the condition code and the program mask bits. */ -#define PSW_MASK_MERGE(CURRENT,NEW) \ - (((CURRENT) & ~(PSW_MASK_CC|PSW_MASK_PM)) | \ - ((NEW) & (PSW_MASK_CC|PSW_MASK_PM))) /* * The s390_regs structure is used to define the elf_gregset_t. @@ -328,8 +324,7 @@ struct pt_regs psw_t psw; unsigned long gprs[NUM_GPRS]; unsigned long orig_gpr2; - unsigned short ilc; - unsigned short svcnr; + unsigned int svc_code; }; /* @@ -487,6 +482,8 @@ typedef struct #define PTRACE_POKETEXT_AREA 0x5004 #define PTRACE_POKEDATA_AREA 0x5005 #define PTRACE_GET_LAST_BREAK 0x5006 +#define PTRACE_PEEK_SYSTEM_CALL 0x5007 +#define PTRACE_POKE_SYSTEM_CALL 0x5008 /* * PT_PROT definition is loosely based on hppa bsd definition in diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 15c97625df8d..e63d13dd3bf5 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -46,6 +46,8 @@ struct qdesfmt0 { u32 : 16; } __attribute__ ((packed)); +#define QDR_AC_MULTI_BUFFER_ENABLE 0x01 + /** * struct qdr - queue description record (QDR) * @qfmt: queue format @@ -123,6 +125,40 @@ struct slibe { }; /** + * struct qaob - queue asynchronous operation block + * @res0: reserved parameters + * @res1: reserved parameter + * @res2: reserved parameter + * @res3: reserved parameter + * @aorc: asynchronous operation return code + * @flags: internal flags + * @cbtbs: control block type + * @sb_count: number of storage blocks + * @sba: storage block element addresses + * @dcount: size of storage block elements + * @user0: user defineable value + * @res4: reserved paramater + * @user1: user defineable value + * @user2: user defineable value + */ +struct qaob { + u64 res0[6]; + u8 res1; + u8 res2; + u8 res3; + u8 aorc; + u8 flags; + u16 cbtbs; + u8 sb_count; + u64 sba[QDIO_MAX_ELEMENTS_PER_BUFFER]; + u16 dcount[QDIO_MAX_ELEMENTS_PER_BUFFER]; + u64 user0; + u64 res4[2]; + u64 user1; + u64 user2; +} __attribute__ ((packed, aligned(256))); + +/** * struct slib - storage list information block (SLIB) * @nsliba: next SLIB address (if any) * @sla: SL address @@ -222,9 +258,46 @@ struct slsb { u8 val[QDIO_MAX_BUFFERS_PER_Q]; } __attribute__ ((packed, aligned(256))); +#define CHSC_AC2_MULTI_BUFFER_AVAILABLE 0x0080 +#define CHSC_AC2_MULTI_BUFFER_ENABLED 0x0040 #define CHSC_AC2_DATA_DIV_AVAILABLE 0x0010 #define CHSC_AC2_DATA_DIV_ENABLED 0x0002 +/** + * struct qdio_outbuf_state - SBAL related asynchronous operation information + * (for communication with upper layer programs) + * (only required for use with completion queues) + * @flags: flags indicating state of buffer + * @aob: pointer to QAOB used for the particular SBAL + * @user: pointer to upper layer program's state information related to SBAL + * (stored in user1 data of QAOB) + */ +struct qdio_outbuf_state { + u8 flags; + struct qaob *aob; + void *user; +}; + +#define QDIO_OUTBUF_STATE_FLAG_NONE 0x00 +#define QDIO_OUTBUF_STATE_FLAG_PENDING 0x01 + +#define CHSC_AC1_INITIATE_INPUTQ 0x80 + + +/* qdio adapter-characteristics-1 flag */ +#define AC1_SIGA_INPUT_NEEDED 0x40 /* process input queues */ +#define AC1_SIGA_OUTPUT_NEEDED 0x20 /* process output queues */ +#define AC1_SIGA_SYNC_NEEDED 0x10 /* ask hypervisor to sync */ +#define AC1_AUTOMATIC_SYNC_ON_THININT 0x08 /* set by hypervisor */ +#define AC1_AUTOMATIC_SYNC_ON_OUT_PCI 0x04 /* set by hypervisor */ +#define AC1_SC_QEBSM_AVAILABLE 0x02 /* available for subchannel */ +#define AC1_SC_QEBSM_ENABLED 0x01 /* enabled for subchannel */ + +#define CHSC_AC2_DATA_DIV_AVAILABLE 0x0010 +#define CHSC_AC2_DATA_DIV_ENABLED 0x0002 + +#define CHSC_AC3_FORMAT2_CQ_AVAILABLE 0x8000 + struct qdio_ssqd_desc { u8 flags; u8:8; @@ -243,8 +316,7 @@ struct qdio_ssqd_desc { u64 sch_token; u8 mro; u8 mri; - u8:8; - u8 sbalic; + u16 qdioac3; u16:16; u8:8; u8 mmwc; @@ -280,13 +352,16 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int, * @no_output_qs: number of output queues * @input_handler: handler to be called for input queues * @output_handler: handler to be called for output queues + * @queue_start_poll: polling handlers (one per input queue or NULL) * @int_parm: interruption parameter * @input_sbal_addr_array: address of no_input_qs * 128 pointers * @output_sbal_addr_array: address of no_output_qs * 128 pointers + * @output_sbal_state_array: no_output_qs * 128 state info (for CQ or NULL) */ struct qdio_initialize { struct ccw_device *cdev; unsigned char q_format; + unsigned char qdr_ac; unsigned char adapter_name[8]; unsigned int qib_param_field_format; unsigned char *qib_param_field; @@ -297,11 +372,12 @@ struct qdio_initialize { unsigned int no_output_qs; qdio_handler_t *input_handler; qdio_handler_t *output_handler; - void (*queue_start_poll) (struct ccw_device *, int, unsigned long); + void (**queue_start_poll) (struct ccw_device *, int, unsigned long); int scan_threshold; unsigned long int_parm; void **input_sbal_addr_array; void **output_sbal_addr_array; + struct qdio_outbuf_state *output_sbal_state_array; }; #define QDIO_STATE_INACTIVE 0x00000002 /* after qdio_cleanup */ @@ -316,6 +392,7 @@ struct qdio_initialize { extern int qdio_allocate(struct qdio_initialize *); extern int qdio_establish(struct qdio_initialize *); extern int qdio_activate(struct ccw_device *); +extern void qdio_release_aob(struct qaob *); extern int do_QDIO(struct ccw_device *, unsigned int, int, unsigned int, unsigned int); extern int qdio_start_irq(struct ccw_device *, int); diff --git a/arch/s390/include/asm/reset.h b/arch/s390/include/asm/reset.h index f584f4a52581..3d6ad4ad2a3f 100644 --- a/arch/s390/include/asm/reset.h +++ b/arch/s390/include/asm/reset.h @@ -17,5 +17,5 @@ struct reset_call { extern void register_reset_call(struct reset_call *reset); extern void unregister_reset_call(struct reset_call *reset); -extern void s390_reset_system(void); +extern void s390_reset_system(void (*func)(void *), void *data); #endif /* _ASM_S390_RESET_H */ diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index d5e2ef10537d..5a099714df04 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -26,15 +26,21 @@ #define IPL_DEVICE (*(unsigned long *) (0x10404)) #define INITRD_START (*(unsigned long *) (0x1040C)) #define INITRD_SIZE (*(unsigned long *) (0x10414)) +#define OLDMEM_BASE (*(unsigned long *) (0x1041C)) +#define OLDMEM_SIZE (*(unsigned long *) (0x10424)) #else /* __s390x__ */ #define IPL_DEVICE (*(unsigned long *) (0x10400)) #define INITRD_START (*(unsigned long *) (0x10408)) #define INITRD_SIZE (*(unsigned long *) (0x10410)) +#define OLDMEM_BASE (*(unsigned long *) (0x10418)) +#define OLDMEM_SIZE (*(unsigned long *) (0x10420)) #endif /* __s390x__ */ #define COMMAND_LINE ((char *) (0x10480)) #define CHUNK_READ_WRITE 0 #define CHUNK_READ_ONLY 1 +#define CHUNK_OLDMEM 4 +#define CHUNK_CRASHK 5 struct mem_chunk { unsigned long addr; @@ -48,6 +54,8 @@ extern int memory_end_set; extern unsigned long memory_end; void detect_memory_layout(struct mem_chunk chunk[]); +void create_mem_hole(struct mem_chunk memory_chunk[], unsigned long addr, + unsigned long size, int type); #define PRIMARY_SPACE_MODE 0 #define ACCESS_REGISTER_MODE 1 @@ -106,6 +114,7 @@ extern unsigned int user_mode; #endif /* __s390x__ */ #define ZFCPDUMP_HSA_SIZE (32UL<<20) +#define ZFCPDUMP_HSA_SIZE_MAX (64UL<<20) /* * Console mode. Override with conmode= @@ -134,10 +143,14 @@ extern char kernel_nss_name[]; #define IPL_DEVICE 0x10404 #define INITRD_START 0x1040C #define INITRD_SIZE 0x10414 +#define OLDMEM_BASE 0x1041C +#define OLDMEM_SIZE 0x10424 #else /* __s390x__ */ #define IPL_DEVICE 0x10400 #define INITRD_START 0x10408 #define INITRD_SIZE 0x10410 +#define OLDMEM_BASE 0x10418 +#define OLDMEM_SIZE 0x10420 #endif /* __s390x__ */ #define COMMAND_LINE 0x10480 diff --git a/arch/s390/include/asm/sfp-util.h b/arch/s390/include/asm/sfp-util.h index 0addc6466d95..ca3f8814e361 100644 --- a/arch/s390/include/asm/sfp-util.h +++ b/arch/s390/include/asm/sfp-util.h @@ -72,6 +72,6 @@ extern unsigned long __udiv_qrnnd (unsigned int *, unsigned int, #define UDIV_NEEDS_NORMALIZATION 0 -#define abort() return 0 +#define abort() BUG() #define __BYTE_ORDER __BIG_ENDIAN diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index 045e009fc164..ab47a69fdf07 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -33,6 +33,7 @@ extern struct save_area *zfcpdump_save_areas[NR_CPUS + 1]; extern void smp_switch_to_ipl_cpu(void (*func)(void *), void *); extern void smp_switch_to_cpu(void (*)(void *), void *, unsigned long sp, int from, int to); +extern void smp_restart_with_online_cpu(void); extern void smp_restart_cpu(void); /* @@ -64,6 +65,10 @@ static inline void smp_switch_to_ipl_cpu(void (*func)(void *), void *data) func(data); } +static inline void smp_restart_with_online_cpu(void) +{ +} + #define smp_vcpu_scheduled (1) #endif /* CONFIG_SMP */ diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 56612fc8186e..fd94dfec8d08 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -13,6 +13,8 @@ #include <linux/smp.h> +extern int spin_retry; + static inline int _raw_compare_and_swap(volatile unsigned int *lock, unsigned int old, unsigned int new) diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index 5c0246b955d8..b239ff53b189 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -13,6 +13,7 @@ #define _ASM_SYSCALL_H 1 #include <linux/sched.h> +#include <linux/err.h> #include <asm/ptrace.h> /* @@ -25,7 +26,8 @@ extern const unsigned int sys_call_table[]; static inline long syscall_get_nr(struct task_struct *task, struct pt_regs *regs) { - return regs->svcnr ? regs->svcnr : -1; + return test_tsk_thread_flag(task, TIF_SYSCALL) ? + (regs->svc_code & 0xffff) : -1; } static inline void syscall_rollback(struct task_struct *task, @@ -37,7 +39,7 @@ static inline void syscall_rollback(struct task_struct *task, static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { - return (regs->gprs[2] >= -4096UL) ? -regs->gprs[2] : 0; + return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0; } static inline long syscall_get_return_value(struct task_struct *task, diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h index 6582f69f2389..ef573c1d71a7 100644 --- a/arch/s390/include/asm/system.h +++ b/arch/s390/include/asm/system.h @@ -20,6 +20,8 @@ struct task_struct; +extern int sysctl_userprocess_debug; + extern struct task_struct *__switch_to(void *, void *); extern void update_per_regs(struct task_struct *task); @@ -114,6 +116,8 @@ extern void pfault_fini(void); extern void cmma_init(void); extern int memcpy_real(void *, void *, size_t); extern void copy_to_absolute_zero(void *dest, void *src, size_t count); +extern int copy_to_user_real(void __user *dest, void *src, size_t count); +extern int copy_from_user_real(void *dest, void __user *src, size_t count); #define finish_arch_switch(prev) do { \ set_fs(current->thread.mm_segment); \ @@ -210,8 +214,10 @@ __set_psw_mask(unsigned long mask) __load_psw_mask(mask | (arch_local_save_flags() & ~(-1UL >> 8))); } -#define local_mcck_enable() __set_psw_mask(psw_kernel_bits) -#define local_mcck_disable() __set_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK) +#define local_mcck_enable() \ + __set_psw_mask(psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK) +#define local_mcck_disable() \ + __set_psw_mask(psw_kernel_bits | PSW_MASK_DAT) #ifdef CONFIG_SMP diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 1a5dbb6f1495..a23183423b14 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -48,6 +48,7 @@ struct thread_info { unsigned int cpu; /* current CPU */ int preempt_count; /* 0 => preemptable, <0 => BUG */ struct restart_block restart_block; + unsigned int system_call; __u64 user_timer; __u64 system_timer; unsigned long last_break; /* last breaking-event-address. */ @@ -84,10 +85,10 @@ static inline struct thread_info *current_thread_info(void) /* * thread information flags bit numbers */ +#define TIF_SYSCALL 0 /* inside a system call */ #define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ -#define TIF_RESTART_SVC 4 /* restart svc with new svc number */ #define TIF_PER_TRAP 6 /* deliver sigtrap on return to user */ #define TIF_MCCK_PENDING 7 /* machine check handling is pending */ #define TIF_SYSCALL_TRACE 8 /* syscall trace active */ @@ -103,11 +104,11 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SINGLE_STEP 20 /* This task is single stepped */ #define TIF_FREEZE 21 /* thread is freezing for suspend */ +#define _TIF_SYSCALL (1<<TIF_SYSCALL) #define _TIF_NOTIFY_RESUME (1<<TIF_NOTIFY_RESUME) #define _TIF_RESTORE_SIGMASK (1<<TIF_RESTORE_SIGMASK) #define _TIF_SIGPENDING (1<<TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED) -#define _TIF_RESTART_SVC (1<<TIF_RESTART_SVC) #define _TIF_PER_TRAP (1<<TIF_PER_TRAP) #define _TIF_MCCK_PENDING (1<<TIF_MCCK_PENDING) #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) @@ -117,7 +118,7 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_SIE (1<<TIF_SIE) #define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG) #define _TIF_31BIT (1<<TIF_31BIT) -#define _TIF_SINGLE_STEP (1<<TIF_FREEZE) +#define _TIF_SINGLE_STEP (1<<TIF_SINGLE_STEP) #define _TIF_FREEZE (1<<TIF_FREEZE) #ifdef CONFIG_64BIT diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 88829a40af6f..d610bef9c5e9 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -86,6 +86,17 @@ static inline void get_clock_ext(char *clk) asm volatile("stcke %0" : "=Q" (*clk) : : "cc"); } +static inline unsigned long long get_clock_fast(void) +{ + unsigned long long clk; + + if (test_facility(25)) + asm volatile(".insn s,0xb27c0000,%0" : "=Q" (clk) : : "cc"); + else + clk = get_clock(); + return clk; +} + static inline unsigned long long get_clock_xt(void) { unsigned char clk[16]; diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index 304445382382..1d8648cf2fea 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -59,6 +59,7 @@ static inline void __tlb_flush_full(struct mm_struct *mm) } #else #define __tlb_flush_full(mm) __tlb_flush_local() +#define __tlb_flush_global() __tlb_flush_local() #endif /* diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index df3732249baa..dd4f07640919 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -48,6 +48,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += $(if $(CONFIG_64BIT),mcount64.o,mcount.o) obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o +obj-$(CONFIG_CRASH_DUMP) += crash_dump.o # Kexec part S390_KEXEC_OBJS := machine_kexec.o crash.o diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 2b45591e1582..751318765e2e 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -45,8 +45,7 @@ int main(void) DEFINE(__PT_PSW, offsetof(struct pt_regs, psw)); DEFINE(__PT_GPRS, offsetof(struct pt_regs, gprs)); DEFINE(__PT_ORIG_GPR2, offsetof(struct pt_regs, orig_gpr2)); - DEFINE(__PT_ILC, offsetof(struct pt_regs, ilc)); - DEFINE(__PT_SVCNR, offsetof(struct pt_regs, svcnr)); + DEFINE(__PT_SVC_CODE, offsetof(struct pt_regs, svc_code)); DEFINE(__PT_SIZE, sizeof(struct pt_regs)); BLANK(); DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain)); @@ -141,7 +140,6 @@ int main(void) DEFINE(__LC_FPREGS_SAVE_AREA, offsetof(struct _lowcore, floating_pt_save_area)); DEFINE(__LC_GPREGS_SAVE_AREA, offsetof(struct _lowcore, gpregs_save_area)); DEFINE(__LC_CREGS_SAVE_AREA, offsetof(struct _lowcore, cregs_save_area)); - DEFINE(__LC_SAVE_AREA_64, offsetof(struct _lowcore, save_area_64)); #ifdef CONFIG_32BIT DEFINE(SAVE_AREA_BASE, offsetof(struct _lowcore, extended_save_area_addr)); #else /* CONFIG_32BIT */ diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S index 255435663bf8..f8828d38fa6e 100644 --- a/arch/s390/kernel/base.S +++ b/arch/s390/kernel/base.S @@ -86,6 +86,8 @@ s390_base_pgm_handler_fn: ENTRY(diag308_reset) larl %r4,.Lctlregs # Save control registers stctg %c0,%c15,0(%r4) + larl %r4,.Lfpctl # Floating point control register + stfpc 0(%r4) larl %r4,.Lrestart_psw # Setup restart PSW at absolute 0 lghi %r3,0 lg %r4,0(%r4) # Save PSW @@ -99,6 +101,8 @@ ENTRY(diag308_reset) sam64 # Switch to 64 bit addressing mode larl %r4,.Lctlregs # Restore control registers lctlg %c0,%c15,0(%r4) + larl %r4,.Lfpctl # Restore floating point ctl register + lfpc 0(%r4) br %r14 .align 16 .Lrestart_psw: @@ -110,6 +114,8 @@ ENTRY(diag308_reset) .rept 16 .quad 0 .endr +.Lfpctl: + .long 0 .previous #else /* CONFIG_64BIT */ diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 53acaa86dd94..84a982898448 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -60,12 +60,9 @@ #include "compat_linux.h" -long psw_user32_bits = (PSW_BASE32_BITS | PSW_MASK_DAT | PSW_ASC_HOME | - PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK | - PSW_MASK_PSTATE | PSW_DEFAULT_KEY); -long psw32_user_bits = (PSW32_BASE_BITS | PSW32_MASK_DAT | PSW32_ASC_HOME | - PSW32_MASK_IO | PSW32_MASK_EXT | PSW32_MASK_MCHECK | - PSW32_MASK_PSTATE); +u32 psw32_user_bits = PSW32_MASK_DAT | PSW32_MASK_IO | PSW32_MASK_EXT | + PSW32_DEFAULT_KEY | PSW32_MASK_BASE | PSW32_MASK_MCHECK | + PSW32_MASK_PSTATE | PSW32_ASC_HOME; /* For this source file, we want overflow handling. */ @@ -365,12 +362,7 @@ asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, if (set) { if (copy_from_user (&s32, set, sizeof(compat_sigset_t))) return -EFAULT; - switch (_NSIG_WORDS) { - case 4: s.sig[3] = s32.sig[6] | (((long)s32.sig[7]) << 32); - case 3: s.sig[2] = s32.sig[4] | (((long)s32.sig[5]) << 32); - case 2: s.sig[1] = s32.sig[2] | (((long)s32.sig[3]) << 32); - case 1: s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32); - } + s.sig[0] = s32.sig[0] | (((long)s32.sig[1]) << 32); } set_fs (KERNEL_DS); ret = sys_rt_sigprocmask(how, @@ -380,12 +372,8 @@ asmlinkage long sys32_rt_sigprocmask(int how, compat_sigset_t __user *set, set_fs (old_fs); if (ret) return ret; if (oset) { - switch (_NSIG_WORDS) { - case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3]; - case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2]; - case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1]; - case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0]; - } + s32.sig[1] = (s.sig[0] >> 32); + s32.sig[0] = s.sig[0]; if (copy_to_user (oset, &s32, sizeof(compat_sigset_t))) return -EFAULT; } @@ -404,12 +392,8 @@ asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *set, ret = sys_rt_sigpending((sigset_t __force __user *) &s, sigsetsize); set_fs (old_fs); if (!ret) { - switch (_NSIG_WORDS) { - case 4: s32.sig[7] = (s.sig[3] >> 32); s32.sig[6] = s.sig[3]; - case 3: s32.sig[5] = (s.sig[2] >> 32); s32.sig[4] = s.sig[2]; - case 2: s32.sig[3] = (s.sig[1] >> 32); s32.sig[2] = s.sig[1]; - case 1: s32.sig[1] = (s.sig[0] >> 32); s32.sig[0] = s.sig[0]; - } + s32.sig[1] = (s.sig[0] >> 32); + s32.sig[0] = s.sig[0]; if (copy_to_user (set, &s32, sizeof(compat_sigset_t))) return -EFAULT; } diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index a9a285b8c4ad..4f68c81d3ffa 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -141,7 +141,8 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) break; case __SI_FAULT >> 16: err |= __get_user(tmp, &from->si_addr); - to->si_addr = (void __user *)(u64) (tmp & PSW32_ADDR_INSN); + to->si_addr = (void __force __user *) + (u64) (tmp & PSW32_ADDR_INSN); break; case __SI_POLL >> 16: err |= __get_user(to->si_band, &from->si_band); @@ -213,16 +214,8 @@ sys32_rt_sigaction(int sig, const struct sigaction32 __user *act, ret = get_user(sa_handler, &act->sa_handler); ret |= __copy_from_user(&set32, &act->sa_mask, sizeof(compat_sigset_t)); - switch (_NSIG_WORDS) { - case 4: new_ka.sa.sa_mask.sig[3] = set32.sig[6] - | (((long)set32.sig[7]) << 32); - case 3: new_ka.sa.sa_mask.sig[2] = set32.sig[4] - | (((long)set32.sig[5]) << 32); - case 2: new_ka.sa.sa_mask.sig[1] = set32.sig[2] - | (((long)set32.sig[3]) << 32); - case 1: new_ka.sa.sa_mask.sig[0] = set32.sig[0] - | (((long)set32.sig[1]) << 32); - } + new_ka.sa.sa_mask.sig[0] = + set32.sig[0] | (((long)set32.sig[1]) << 32); ret |= __get_user(new_ka.sa.sa_flags, &act->sa_flags); if (ret) @@ -233,20 +226,8 @@ sys32_rt_sigaction(int sig, const struct sigaction32 __user *act, ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); if (!ret && oact) { - switch (_NSIG_WORDS) { - case 4: - set32.sig[7] = (old_ka.sa.sa_mask.sig[3] >> 32); - set32.sig[6] = old_ka.sa.sa_mask.sig[3]; - case 3: - set32.sig[5] = (old_ka.sa.sa_mask.sig[2] >> 32); - set32.sig[4] = old_ka.sa.sa_mask.sig[2]; - case 2: - set32.sig[3] = (old_ka.sa.sa_mask.sig[1] >> 32); - set32.sig[2] = old_ka.sa.sa_mask.sig[1]; - case 1: - set32.sig[1] = (old_ka.sa.sa_mask.sig[0] >> 32); - set32.sig[0] = old_ka.sa.sa_mask.sig[0]; - } + set32.sig[1] = (old_ka.sa.sa_mask.sig[0] >> 32); + set32.sig[0] = old_ka.sa.sa_mask.sig[0]; ret = put_user((unsigned long)old_ka.sa.sa_handler, &oact->sa_handler); ret |= __copy_to_user(&oact->sa_mask, &set32, sizeof(compat_sigset_t)); @@ -300,9 +281,10 @@ static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs) _s390_regs_common32 regs32; int err, i; - regs32.psw.mask = PSW32_MASK_MERGE(psw32_user_bits, - (__u32)(regs->psw.mask >> 32)); - regs32.psw.addr = PSW32_ADDR_AMODE31 | (__u32) regs->psw.addr; + regs32.psw.mask = psw32_user_bits | + ((__u32)(regs->psw.mask >> 32) & PSW32_MASK_USER); + regs32.psw.addr = (__u32) regs->psw.addr | + (__u32)(regs->psw.mask & PSW_MASK_BA); for (i = 0; i < NUM_GPRS; i++) regs32.gprs[i] = (__u32) regs->gprs[i]; save_access_regs(current->thread.acrs); @@ -327,8 +309,9 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) err = __copy_from_user(®s32, &sregs->regs, sizeof(regs32)); if (err) return err; - regs->psw.mask = PSW_MASK_MERGE(regs->psw.mask, - (__u64)regs32.psw.mask << 32); + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | + (__u64)(regs32.psw.mask & PSW32_MASK_USER) << 32 | + (__u64)(regs32.psw.addr & PSW32_ADDR_AMODE); regs->psw.addr = (__u64)(regs32.psw.addr & PSW32_ADDR_INSN); for (i = 0; i < NUM_GPRS; i++) regs->gprs[i] = (__u64) regs32.gprs[i]; @@ -342,7 +325,7 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) return err; restore_fp_regs(¤t->thread.fp_regs); - regs->svcnr = 0; /* disable syscall checks */ + clear_thread_flag(TIF_SYSCALL); /* No longer in a system call */ return 0; } @@ -496,11 +479,11 @@ static int setup_frame32(int sig, struct k_sigaction *ka, /* Set up to return from userspace. If provided, use a stub already in userspace. */ if (ka->sa.sa_flags & SA_RESTORER) { - regs->gprs[14] = (__u64) ka->sa.sa_restorer; + regs->gprs[14] = (__u64) ka->sa.sa_restorer | PSW32_ADDR_AMODE; } else { - regs->gprs[14] = (__u64) frame->retcode; + regs->gprs[14] = (__u64) frame->retcode | PSW32_ADDR_AMODE; if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, - (u16 __user *)(frame->retcode))) + (u16 __force __user *)(frame->retcode))) goto give_sigsegv; } @@ -509,11 +492,12 @@ static int setup_frame32(int sig, struct k_sigaction *ka, goto give_sigsegv; /* Set up registers for signal handler */ - regs->gprs[15] = (__u64) frame; - regs->psw.addr = (__u64) ka->sa.sa_handler; + regs->gprs[15] = (__force __u64) frame; + regs->psw.mask |= PSW_MASK_BA; /* force amode 31 */ + regs->psw.addr = (__force __u64) ka->sa.sa_handler; regs->gprs[2] = map_signal(sig); - regs->gprs[3] = (__u64) &frame->sc; + regs->gprs[3] = (__force __u64) &frame->sc; /* We forgot to include these in the sigcontext. To avoid breaking binary compatibility, they are passed as args. */ @@ -521,7 +505,7 @@ static int setup_frame32(int sig, struct k_sigaction *ka, regs->gprs[5] = current->thread.prot_addr; /* Place signal number on stack to allow backtrace from handler. */ - if (__put_user(regs->gprs[2], (int __user *) &frame->signo)) + if (__put_user(regs->gprs[2], (int __force __user *) &frame->signo)) goto give_sigsegv; return 0; @@ -564,20 +548,21 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info, } else { regs->gprs[14] = (__u64) frame->retcode; err |= __put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, - (u16 __user *)(frame->retcode)); + (u16 __force __user *)(frame->retcode)); } /* Set up backchain. */ - if (__put_user(regs->gprs[15], (unsigned int __user *) frame)) + if (__put_user(regs->gprs[15], (unsigned int __force __user *) frame)) goto give_sigsegv; /* Set up registers for signal handler */ - regs->gprs[15] = (__u64) frame; + regs->gprs[15] = (__force __u64) frame; + regs->psw.mask |= PSW_MASK_BA; /* force amode 31 */ regs->psw.addr = (__u64) ka->sa.sa_handler; regs->gprs[2] = map_signal(sig); - regs->gprs[3] = (__u64) &frame->info; - regs->gprs[4] = (__u64) &frame->uc; + regs->gprs[3] = (__force __u64) &frame->info; + regs->gprs[4] = (__force __u64) &frame->uc; return 0; give_sigsegv: diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 7526db6bf501..5006a1d9f5d0 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -1623,8 +1623,7 @@ ENTRY(sys_syncfs_wrapper) lgfr %r2,%r2 # int jg sys_syncfs - .globl sys_setns_wrapper -sys_setns_wrapper: +ENTRY(sys_setns_wrapper) lgfr %r2,%r2 # int lgfr %r3,%r3 # int jg sys_setns diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c new file mode 100644 index 000000000000..39f8fd4438fc --- /dev/null +++ b/arch/s390/kernel/crash_dump.c @@ -0,0 +1,426 @@ +/* + * S390 kdump implementation + * + * Copyright IBM Corp. 2011 + * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#include <linux/crash_dump.h> +#include <asm/lowcore.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/gfp.h> +#include <linux/slab.h> +#include <linux/crash_dump.h> +#include <linux/bootmem.h> +#include <linux/elf.h> +#include <asm/ipl.h> + +#define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y))) +#define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y))) +#define PTR_DIFF(x, y) ((unsigned long)(((char *) (x)) - ((unsigned long) (y)))) + +/* + * Copy one page from "oldmem" + * + * For the kdump reserved memory this functions performs a swap operation: + * - [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] is mapped to [0 - OLDMEM_SIZE]. + * - [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] + */ +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, + size_t csize, unsigned long offset, int userbuf) +{ + unsigned long src; + + if (!csize) + return 0; + + src = (pfn << PAGE_SHIFT) + offset; + if (src < OLDMEM_SIZE) + src += OLDMEM_BASE; + else if (src > OLDMEM_BASE && + src < OLDMEM_BASE + OLDMEM_SIZE) + src -= OLDMEM_BASE; + if (userbuf) + copy_to_user_real((void __force __user *) buf, (void *) src, + csize); + else + memcpy_real(buf, (void *) src, csize); + return csize; +} + +/* + * Copy memory from old kernel + */ +static int copy_from_oldmem(void *dest, void *src, size_t count) +{ + unsigned long copied = 0; + int rc; + + if ((unsigned long) src < OLDMEM_SIZE) { + copied = min(count, OLDMEM_SIZE - (unsigned long) src); + rc = memcpy_real(dest, src + OLDMEM_BASE, copied); + if (rc) + return rc; + } + return memcpy_real(dest + copied, src + copied, count - copied); +} + +/* + * Alloc memory and panic in case of ENOMEM + */ +static void *kzalloc_panic(int len) +{ + void *rc; + + rc = kzalloc(len, GFP_KERNEL); + if (!rc) + panic("s390 kdump kzalloc (%d) failed", len); + return rc; +} + +/* + * Get memory layout and create hole for oldmem + */ +static struct mem_chunk *get_memory_layout(void) +{ + struct mem_chunk *chunk_array; + + chunk_array = kzalloc_panic(MEMORY_CHUNKS * sizeof(struct mem_chunk)); + detect_memory_layout(chunk_array); + create_mem_hole(chunk_array, OLDMEM_BASE, OLDMEM_SIZE, CHUNK_CRASHK); + return chunk_array; +} + +/* + * Initialize ELF note + */ +static void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len, + const char *name) +{ + Elf64_Nhdr *note; + u64 len; + + note = (Elf64_Nhdr *)buf; + note->n_namesz = strlen(name) + 1; + note->n_descsz = d_len; + note->n_type = type; + len = sizeof(Elf64_Nhdr); + + memcpy(buf + len, name, note->n_namesz); + len = roundup(len + note->n_namesz, 4); + + memcpy(buf + len, desc, note->n_descsz); + len = roundup(len + note->n_descsz, 4); + + return PTR_ADD(buf, len); +} + +/* + * Initialize prstatus note + */ +static void *nt_prstatus(void *ptr, struct save_area *sa) +{ + struct elf_prstatus nt_prstatus; + static int cpu_nr = 1; + + memset(&nt_prstatus, 0, sizeof(nt_prstatus)); + memcpy(&nt_prstatus.pr_reg.gprs, sa->gp_regs, sizeof(sa->gp_regs)); + memcpy(&nt_prstatus.pr_reg.psw, sa->psw, sizeof(sa->psw)); + memcpy(&nt_prstatus.pr_reg.acrs, sa->acc_regs, sizeof(sa->acc_regs)); + nt_prstatus.pr_pid = cpu_nr; + cpu_nr++; + + return nt_init(ptr, NT_PRSTATUS, &nt_prstatus, sizeof(nt_prstatus), + "CORE"); +} + +/* + * Initialize fpregset (floating point) note + */ +static void *nt_fpregset(void *ptr, struct save_area *sa) +{ + elf_fpregset_t nt_fpregset; + + memset(&nt_fpregset, 0, sizeof(nt_fpregset)); + memcpy(&nt_fpregset.fpc, &sa->fp_ctrl_reg, sizeof(sa->fp_ctrl_reg)); + memcpy(&nt_fpregset.fprs, &sa->fp_regs, sizeof(sa->fp_regs)); + + return nt_init(ptr, NT_PRFPREG, &nt_fpregset, sizeof(nt_fpregset), + "CORE"); +} + +/* + * Initialize timer note + */ +static void *nt_s390_timer(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer), + KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize TOD clock comparator note + */ +static void *nt_s390_tod_cmp(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_TODCMP, &sa->clk_cmp, + sizeof(sa->clk_cmp), KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize TOD programmable register note + */ +static void *nt_s390_tod_preg(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_TODPREG, &sa->tod_reg, + sizeof(sa->tod_reg), KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize control register note + */ +static void *nt_s390_ctrs(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_CTRS, &sa->ctrl_regs, + sizeof(sa->ctrl_regs), KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize prefix register note + */ +static void *nt_s390_prefix(void *ptr, struct save_area *sa) +{ + return nt_init(ptr, NT_S390_PREFIX, &sa->pref_reg, + sizeof(sa->pref_reg), KEXEC_CORE_NOTE_NAME); +} + +/* + * Fill ELF notes for one CPU with save area registers + */ +void *fill_cpu_elf_notes(void *ptr, struct save_area *sa) +{ + ptr = nt_prstatus(ptr, sa); + ptr = nt_fpregset(ptr, sa); + ptr = nt_s390_timer(ptr, sa); + ptr = nt_s390_tod_cmp(ptr, sa); + ptr = nt_s390_tod_preg(ptr, sa); + ptr = nt_s390_ctrs(ptr, sa); + ptr = nt_s390_prefix(ptr, sa); + return ptr; +} + +/* + * Initialize prpsinfo note (new kernel) + */ +static void *nt_prpsinfo(void *ptr) +{ + struct elf_prpsinfo prpsinfo; + + memset(&prpsinfo, 0, sizeof(prpsinfo)); + prpsinfo.pr_sname = 'R'; + strcpy(prpsinfo.pr_fname, "vmlinux"); + return nt_init(ptr, NT_PRPSINFO, &prpsinfo, sizeof(prpsinfo), + KEXEC_CORE_NOTE_NAME); +} + +/* + * Initialize vmcoreinfo note (new kernel) + */ +static void *nt_vmcoreinfo(void *ptr) +{ + char nt_name[11], *vmcoreinfo; + Elf64_Nhdr note; + void *addr; + + if (copy_from_oldmem(&addr, &S390_lowcore.vmcore_info, sizeof(addr))) + return ptr; + memset(nt_name, 0, sizeof(nt_name)); + if (copy_from_oldmem(¬e, addr, sizeof(note))) + return ptr; + if (copy_from_oldmem(nt_name, addr + sizeof(note), sizeof(nt_name) - 1)) + return ptr; + if (strcmp(nt_name, "VMCOREINFO") != 0) + return ptr; + vmcoreinfo = kzalloc_panic(note.n_descsz + 1); + if (copy_from_oldmem(vmcoreinfo, addr + 24, note.n_descsz)) + return ptr; + vmcoreinfo[note.n_descsz + 1] = 0; + return nt_init(ptr, 0, vmcoreinfo, note.n_descsz, "VMCOREINFO"); +} + +/* + * Initialize ELF header (new kernel) + */ +static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt) +{ + memset(ehdr, 0, sizeof(*ehdr)); + memcpy(ehdr->e_ident, ELFMAG, SELFMAG); + ehdr->e_ident[EI_CLASS] = ELFCLASS64; + ehdr->e_ident[EI_DATA] = ELFDATA2MSB; + ehdr->e_ident[EI_VERSION] = EV_CURRENT; + memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD); + ehdr->e_type = ET_CORE; + ehdr->e_machine = EM_S390; + ehdr->e_version = EV_CURRENT; + ehdr->e_phoff = sizeof(Elf64_Ehdr); + ehdr->e_ehsize = sizeof(Elf64_Ehdr); + ehdr->e_phentsize = sizeof(Elf64_Phdr); + ehdr->e_phnum = mem_chunk_cnt + 1; + return ehdr + 1; +} + +/* + * Return CPU count for ELF header (new kernel) + */ +static int get_cpu_cnt(void) +{ + int i, cpus = 0; + + for (i = 0; zfcpdump_save_areas[i]; i++) { + if (zfcpdump_save_areas[i]->pref_reg == 0) + continue; + cpus++; + } + return cpus; +} + +/* + * Return memory chunk count for ELF header (new kernel) + */ +static int get_mem_chunk_cnt(void) +{ + struct mem_chunk *chunk_array, *mem_chunk; + int i, cnt = 0; + + chunk_array = get_memory_layout(); + for (i = 0; i < MEMORY_CHUNKS; i++) { + mem_chunk = &chunk_array[i]; + if (chunk_array[i].type != CHUNK_READ_WRITE && + chunk_array[i].type != CHUNK_READ_ONLY) + continue; + if (mem_chunk->size == 0) + continue; + cnt++; + } + kfree(chunk_array); + return cnt; +} + +/* + * Relocate pointer in order to allow vmcore code access the data + */ +static inline unsigned long relocate(unsigned long addr) +{ + return OLDMEM_BASE + addr; +} + +/* + * Initialize ELF loads (new kernel) + */ +static int loads_init(Elf64_Phdr *phdr, u64 loads_offset) +{ + struct mem_chunk *chunk_array, *mem_chunk; + int i; + + chunk_array = get_memory_layout(); + for (i = 0; i < MEMORY_CHUNKS; i++) { + mem_chunk = &chunk_array[i]; + if (mem_chunk->size == 0) + break; + if (chunk_array[i].type != CHUNK_READ_WRITE && + chunk_array[i].type != CHUNK_READ_ONLY) + continue; + else + phdr->p_filesz = mem_chunk->size; + phdr->p_type = PT_LOAD; + phdr->p_offset = mem_chunk->addr; + phdr->p_vaddr = mem_chunk->addr; + phdr->p_paddr = mem_chunk->addr; + phdr->p_memsz = mem_chunk->size; + phdr->p_flags = PF_R | PF_W | PF_X; + phdr->p_align = PAGE_SIZE; + phdr++; + } + kfree(chunk_array); + return i; +} + +/* + * Initialize notes (new kernel) + */ +static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset) +{ + struct save_area *sa; + void *ptr_start = ptr; + int i; + + ptr = nt_prpsinfo(ptr); + + for (i = 0; zfcpdump_save_areas[i]; i++) { + sa = zfcpdump_save_areas[i]; + if (sa->pref_reg == 0) + continue; + ptr = fill_cpu_elf_notes(ptr, sa); + } + ptr = nt_vmcoreinfo(ptr); + memset(phdr, 0, sizeof(*phdr)); + phdr->p_type = PT_NOTE; + phdr->p_offset = relocate(notes_offset); + phdr->p_filesz = (unsigned long) PTR_SUB(ptr, ptr_start); + phdr->p_memsz = phdr->p_filesz; + return ptr; +} + +/* + * Create ELF core header (new kernel) + */ +static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz) +{ + Elf64_Phdr *phdr_notes, *phdr_loads; + int mem_chunk_cnt; + void *ptr, *hdr; + u32 alloc_size; + u64 hdr_off; + + mem_chunk_cnt = get_mem_chunk_cnt(); + + alloc_size = 0x1000 + get_cpu_cnt() * 0x300 + + mem_chunk_cnt * sizeof(Elf64_Phdr); + hdr = kzalloc_panic(alloc_size); + /* Init elf header */ + ptr = ehdr_init(hdr, mem_chunk_cnt); + /* Init program headers */ + phdr_notes = ptr; + ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr)); + phdr_loads = ptr; + ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr) * mem_chunk_cnt); + /* Init notes */ + hdr_off = PTR_DIFF(ptr, hdr); + ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off); + /* Init loads */ + hdr_off = PTR_DIFF(ptr, hdr); + loads_init(phdr_loads, ((unsigned long) hdr) + hdr_off); + *elfcorebuf_sz = hdr_off; + *elfcorebuf = (void *) relocate((unsigned long) hdr); + BUG_ON(*elfcorebuf_sz > alloc_size); +} + +/* + * Create kdump ELF core header in new kernel, if it has not been passed via + * the "elfcorehdr" kernel parameter + */ +static int setup_kdump_elfcorehdr(void) +{ + size_t elfcorebuf_sz; + char *elfcorebuf; + + if (!OLDMEM_BASE || is_kdump_kernel()) + return -EINVAL; + s390_elf_corehdr_create(&elfcorebuf, &elfcorebuf_sz); + elfcorehdr_addr = (unsigned long long) elfcorebuf; + elfcorehdr_size = elfcorebuf_sz; + return 0; +} + +subsys_initcall(setup_kdump_elfcorehdr); diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index f297456dba7a..37394b3413e2 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -252,7 +252,7 @@ static noinline __init void setup_lowcore_early(void) { psw_t psw; - psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY; + psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA; psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_ext_handler; S390_lowcore.external_new_psw = psw; psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 02ec8fe7d03f..b13157057e02 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -43,16 +43,15 @@ SP_R13 = STACK_FRAME_OVERHEAD + __PT_GPRS + 52 SP_R14 = STACK_FRAME_OVERHEAD + __PT_GPRS + 56 SP_R15 = STACK_FRAME_OVERHEAD + __PT_GPRS + 60 SP_ORIG_R2 = STACK_FRAME_OVERHEAD + __PT_ORIG_GPR2 -SP_ILC = STACK_FRAME_OVERHEAD + __PT_ILC -SP_SVCNR = STACK_FRAME_OVERHEAD + __PT_SVCNR +SP_SVC_CODE = STACK_FRAME_OVERHEAD + __PT_SVC_CODE SP_SIZE = STACK_FRAME_OVERHEAD + __PT_SIZE _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ - _TIF_MCCK_PENDING | _TIF_RESTART_SVC | _TIF_PER_TRAP ) + _TIF_MCCK_PENDING | _TIF_PER_TRAP ) _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) -_TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \ - _TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8) +_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT) STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT @@ -228,9 +227,10 @@ ENTRY(system_call) sysc_saveall: SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC l %r12,__LC_THREAD_INFO # load pointer to thread_info struct + mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+3(%r12),_TIF_SYSCALL sysc_vtime: UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER sysc_stime: @@ -239,17 +239,17 @@ sysc_update: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER sysc_do_svc: xr %r7,%r7 - icm %r7,3,SP_SVCNR(%r15) # load svc number and test for svc 0 + icm %r7,3,SP_SVC_CODE+2(%r15)# load svc number and test for svc 0 bnz BASED(sysc_nr_ok) # svc number > 0 # svc 0: system call number in %r1 cl %r1,BASED(.Lnr_syscalls) bnl BASED(sysc_nr_ok) - sth %r1,SP_SVCNR(%r15) + sth %r1,SP_SVC_CODE+2(%r15) lr %r7,%r1 # copy svc number to %r7 sysc_nr_ok: sll %r7,2 # svc number *4 l %r10,BASED(.Lsysc_table) - tm __TI_flags+2(%r12),_TIF_SYSCALL + tm __TI_flags+2(%r12),_TIF_TRACE >> 8 mvc SP_ARGS(4,%r15),SP_R7(%r15) l %r8,0(%r7,%r10) # get system call addr. bnz BASED(sysc_tracesys) @@ -259,23 +259,19 @@ sysc_nr_ok: sysc_return: LOCKDEP_SYS_EXIT sysc_tif: + tm SP_PSW+1(%r15),0x01 # returning to user ? + bno BASED(sysc_restore) tm __TI_flags+3(%r12),_TIF_WORK_SVC bnz BASED(sysc_work) # there is work to do (signals etc.) + ni __TI_flags+3(%r12),255-_TIF_SYSCALL sysc_restore: RESTORE_ALL __LC_RETURN_PSW,1 sysc_done: # -# There is work to do, but first we need to check if we return to userspace. -# -sysc_work: - tm SP_PSW+1(%r15),0x01 # returning to user ? - bno BASED(sysc_restore) - -# # One of the work bits is on. Find out which one. # -sysc_work_tif: +sysc_work: tm __TI_flags+3(%r12),_TIF_MCCK_PENDING bo BASED(sysc_mcck_pending) tm __TI_flags+3(%r12),_TIF_NEED_RESCHED @@ -284,8 +280,6 @@ sysc_work_tif: bo BASED(sysc_sigpending) tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME bo BASED(sysc_notify_resume) - tm __TI_flags+3(%r12),_TIF_RESTART_SVC - bo BASED(sysc_restart) tm __TI_flags+3(%r12),_TIF_PER_TRAP bo BASED(sysc_singlestep) b BASED(sysc_return) # beware of critical section cleanup @@ -314,11 +308,14 @@ sysc_sigpending: la %r2,SP_PTREGS(%r15) # load pt_regs l %r1,BASED(.Ldo_signal) basr %r14,%r1 # call do_signal - tm __TI_flags+3(%r12),_TIF_RESTART_SVC - bo BASED(sysc_restart) - tm __TI_flags+3(%r12),_TIF_PER_TRAP - bo BASED(sysc_singlestep) - b BASED(sysc_return) + tm __TI_flags+3(%r12),_TIF_SYSCALL + bno BASED(sysc_return) + lm %r2,%r6,SP_R2(%r15) # load svc arguments + xr %r7,%r7 # svc 0 returns -ENOSYS + clc SP_SVC_CODE+2(2,%r15),BASED(.Lnr_syscalls+2) + bnl BASED(sysc_nr_ok) # invalid svc number -> do svc 0 + icm %r7,3,SP_SVC_CODE+2(%r15)# load new svc number + b BASED(sysc_nr_ok) # restart svc # # _TIF_NOTIFY_RESUME is set, call do_notify_resume @@ -329,24 +326,11 @@ sysc_notify_resume: la %r14,BASED(sysc_return) br %r1 # call do_notify_resume - -# -# _TIF_RESTART_SVC is set, set up registers and restart svc -# -sysc_restart: - ni __TI_flags+3(%r12),255-_TIF_RESTART_SVC # clear TIF_RESTART_SVC - l %r7,SP_R2(%r15) # load new svc number - mvc SP_R2(4,%r15),SP_ORIG_R2(%r15) # restore first argument - lm %r2,%r6,SP_R2(%r15) # load svc arguments - sth %r7,SP_SVCNR(%r15) - b BASED(sysc_nr_ok) # restart svc - # # _TIF_PER_TRAP is set, call do_per_trap # sysc_singlestep: - ni __TI_flags+3(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP - xc SP_SVCNR(2,%r15),SP_SVCNR(%r15) # clear svc number + ni __TI_flags+3(%r12),255-(_TIF_SYSCALL | _TIF_PER_TRAP) la %r2,SP_PTREGS(%r15) # address of register-save area l %r1,BASED(.Lhandle_per) # load adr. of per handler la %r14,BASED(sysc_return) # load adr. of system return @@ -361,7 +345,7 @@ sysc_tracesys: la %r2,SP_PTREGS(%r15) # load pt_regs la %r3,0 xr %r0,%r0 - icm %r0,3,SP_SVCNR(%r15) + icm %r0,3,SP_SVC_CODE(%r15) st %r0,SP_R2(%r15) basr %r14,%r1 cl %r2,BASED(.Lnr_syscalls) @@ -376,7 +360,7 @@ sysc_tracego: basr %r14,%r8 # call sys_xxx st %r2,SP_R2(%r15) # store return value sysc_tracenogo: - tm __TI_flags+2(%r12),_TIF_SYSCALL + tm __TI_flags+2(%r12),_TIF_TRACE >> 8 bz BASED(sysc_return) l %r1,BASED(.Ltrace_exit) la %r2,SP_PTREGS(%r15) # load pt_regs @@ -454,7 +438,6 @@ ENTRY(pgm_check_handler) bnz BASED(pgm_per) # got per exception -> special case SAVE_ALL_PGM __LC_PGM_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - xc SP_ILC(4,%r15),SP_ILC(%r15) mvc SP_PSW(8,%r15),__LC_PGM_OLD_PSW l %r12,__LC_THREAD_INFO # load pointer to thread_info struct tm SP_PSW+1(%r15),0x01 # interrupting from user ? @@ -530,9 +513,10 @@ pgm_exit2: pgm_svcper: SAVE_ALL_PGM __LC_SVC_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC l %r12,__LC_THREAD_INFO # load pointer to thread_info struct + mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+3(%r12),(_TIF_SYSCALL | _TIF_PER_TRAP) UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER @@ -540,7 +524,6 @@ pgm_svcper: mvc __THREAD_per_cause(2,%r8),__LC_PER_CAUSE mvc __THREAD_per_address(4,%r8),__LC_PER_ADDRESS mvc __THREAD_per_paid(1,%r8),__LC_PER_PAID - oi __TI_flags+3(%r12),_TIF_PER_TRAP # set TIF_PER_TRAP stosm __SF_EMPTY(%r15),0x03 # reenable interrupts lm %r2,%r6,SP_R2(%r15) # load svc arguments b BASED(sysc_do_svc) @@ -550,7 +533,6 @@ pgm_svcper: # kernel_per: REENABLE_IRQS - xc SP_SVCNR(2,%r15),SP_SVCNR(%r15) la %r2,SP_PTREGS(%r15) # address of register-save area l %r1,BASED(.Lhandle_per) # load adr. of per handler basr %r14,%r1 # branch to do_single_step @@ -853,13 +835,13 @@ restart_go: # PSW restart interrupt handler # ENTRY(psw_restart_int_handler) - st %r15,__LC_SAVE_AREA_64(%r0) # save r15 + st %r15,__LC_SAVE_AREA+48(%r0) # save r15 basr %r15,0 0: l %r15,.Lrestart_stack-0b(%r15) # load restart stack l %r15,0(%r15) ahi %r15,-SP_SIZE # make room for pt_regs stm %r0,%r14,SP_R0(%r15) # store gprs %r0-%r14 to stack - mvc SP_R15(4,%r15),__LC_SAVE_AREA_64(%r0)# store saved %r15 to stack + mvc SP_R15(4,%r15),__LC_SAVE_AREA+48(%r0)# store saved %r15 to stack mvc SP_PSW(8,%r15),__LC_RST_OLD_PSW(%r0) # store restart old psw xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) # set backchain to 0 basr %r14,0 @@ -965,9 +947,11 @@ cleanup_system_call: s %r15,BASED(.Lc_spsize) # make room for registers & psw st %r15,12(%r12) CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC mvc 0(4,%r12),__LC_THREAD_INFO + l %r12,__LC_THREAD_INFO + mvc SP_PSW(8,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+3(%r12),_TIF_SYSCALL cleanup_vtime: clc __LC_RETURN_PSW+4(4),BASED(cleanup_system_call_insn+12) bhe BASED(cleanup_stime) diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 66729eb7bbc5..ef8fb1d6e8d7 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -5,24 +5,33 @@ #include <linux/signal.h> #include <asm/ptrace.h> + +extern void (*pgm_check_table[128])(struct pt_regs *, long, unsigned long); +extern void *restart_stack; + +asmlinkage long do_syscall_trace_enter(struct pt_regs *regs); +asmlinkage void do_syscall_trace_exit(struct pt_regs *regs); + void do_protection_exception(struct pt_regs *, long, unsigned long); void do_dat_exception(struct pt_regs *, long, unsigned long); void do_asce_exception(struct pt_regs *, long, unsigned long); -extern int sysctl_userprocess_debug; - void do_per_trap(struct pt_regs *regs); void syscall_trace(struct pt_regs *regs, int entryexit); void kernel_stack_overflow(struct pt_regs * regs); void do_signal(struct pt_regs *regs); int handle_signal32(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs); +void do_notify_resume(struct pt_regs *regs); void do_extint(struct pt_regs *regs, unsigned int, unsigned int, unsigned long); +void do_restart(void); int __cpuinit start_secondary(void *cpuvoid); void __init startup_init(void); void die(const char * str, struct pt_regs * regs, long err); +void __init time_init(void); + struct s390_mmap_arg_struct; struct fadvise64_64_args; struct old_sigaction; diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 713da0760538..83a93747e2fd 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -43,19 +43,18 @@ SP_R13 = STACK_FRAME_OVERHEAD + __PT_GPRS + 104 SP_R14 = STACK_FRAME_OVERHEAD + __PT_GPRS + 112 SP_R15 = STACK_FRAME_OVERHEAD + __PT_GPRS + 120 SP_ORIG_R2 = STACK_FRAME_OVERHEAD + __PT_ORIG_GPR2 -SP_ILC = STACK_FRAME_OVERHEAD + __PT_ILC -SP_SVCNR = STACK_FRAME_OVERHEAD + __PT_SVCNR +SP_SVC_CODE = STACK_FRAME_OVERHEAD + __PT_SVC_CODE SP_SIZE = STACK_FRAME_OVERHEAD + __PT_SIZE STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER STACK_SIZE = 1 << STACK_SHIFT _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ - _TIF_MCCK_PENDING | _TIF_RESTART_SVC | _TIF_PER_TRAP ) + _TIF_MCCK_PENDING | _TIF_PER_TRAP ) _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_MCCK_PENDING) -_TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \ - _TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8) +_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ + _TIF_SYSCALL_TRACEPOINT) _TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING) #define BASED(name) name-system_call(%r13) @@ -249,9 +248,10 @@ ENTRY(system_call) sysc_saveall: SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC lg %r12,__LC_THREAD_INFO # load pointer to thread_info struct + mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+7(%r12),_TIF_SYSCALL sysc_vtime: UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER sysc_stime: @@ -260,14 +260,14 @@ sysc_update: mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER LAST_BREAK sysc_do_svc: - llgh %r7,SP_SVCNR(%r15) + llgh %r7,SP_SVC_CODE+2(%r15) slag %r7,%r7,2 # shift and test for svc 0 jnz sysc_nr_ok # svc 0: system call number in %r1 llgfr %r1,%r1 # clear high word in r1 cghi %r1,NR_syscalls jnl sysc_nr_ok - sth %r1,SP_SVCNR(%r15) + sth %r1,SP_SVC_CODE+2(%r15) slag %r7,%r1,2 # shift and test for svc 0 sysc_nr_ok: larl %r10,sys_call_table @@ -277,7 +277,7 @@ sysc_nr_ok: larl %r10,sys_call_table_emu # use 31 bit emulation system calls sysc_noemu: #endif - tm __TI_flags+6(%r12),_TIF_SYSCALL + tm __TI_flags+6(%r12),_TIF_TRACE >> 8 mvc SP_ARGS(8,%r15),SP_R7(%r15) lgf %r8,0(%r7,%r10) # load address of system call routine jnz sysc_tracesys @@ -287,23 +287,19 @@ sysc_noemu: sysc_return: LOCKDEP_SYS_EXIT sysc_tif: + tm SP_PSW+1(%r15),0x01 # returning to user ? + jno sysc_restore tm __TI_flags+7(%r12),_TIF_WORK_SVC jnz sysc_work # there is work to do (signals etc.) + ni __TI_flags+7(%r12),255-_TIF_SYSCALL sysc_restore: RESTORE_ALL __LC_RETURN_PSW,1 sysc_done: # -# There is work to do, but first we need to check if we return to userspace. -# -sysc_work: - tm SP_PSW+1(%r15),0x01 # returning to user ? - jno sysc_restore - -# # One of the work bits is on. Find out which one. # -sysc_work_tif: +sysc_work: tm __TI_flags+7(%r12),_TIF_MCCK_PENDING jo sysc_mcck_pending tm __TI_flags+7(%r12),_TIF_NEED_RESCHED @@ -312,8 +308,6 @@ sysc_work_tif: jo sysc_sigpending tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME jo sysc_notify_resume - tm __TI_flags+7(%r12),_TIF_RESTART_SVC - jo sysc_restart tm __TI_flags+7(%r12),_TIF_PER_TRAP jo sysc_singlestep j sysc_return # beware of critical section cleanup @@ -339,11 +333,15 @@ sysc_sigpending: ni __TI_flags+7(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP la %r2,SP_PTREGS(%r15) # load pt_regs brasl %r14,do_signal # call do_signal - tm __TI_flags+7(%r12),_TIF_RESTART_SVC - jo sysc_restart - tm __TI_flags+7(%r12),_TIF_PER_TRAP - jo sysc_singlestep - j sysc_return + tm __TI_flags+7(%r12),_TIF_SYSCALL + jno sysc_return + lmg %r2,%r6,SP_R2(%r15) # load svc arguments + lghi %r7,0 # svc 0 returns -ENOSYS + lh %r1,SP_SVC_CODE+2(%r15) # load new svc number + cghi %r1,NR_syscalls + jnl sysc_nr_ok # invalid svc number -> do svc 0 + slag %r7,%r1,2 + j sysc_nr_ok # restart svc # # _TIF_NOTIFY_RESUME is set, call do_notify_resume @@ -354,23 +352,10 @@ sysc_notify_resume: jg do_notify_resume # call do_notify_resume # -# _TIF_RESTART_SVC is set, set up registers and restart svc -# -sysc_restart: - ni __TI_flags+7(%r12),255-_TIF_RESTART_SVC # clear TIF_RESTART_SVC - lg %r7,SP_R2(%r15) # load new svc number - mvc SP_R2(8,%r15),SP_ORIG_R2(%r15) # restore first argument - lmg %r2,%r6,SP_R2(%r15) # load svc arguments - sth %r7,SP_SVCNR(%r15) - slag %r7,%r7,2 - j sysc_nr_ok # restart svc - -# # _TIF_PER_TRAP is set, call do_per_trap # sysc_singlestep: - ni __TI_flags+7(%r12),255-_TIF_PER_TRAP # clear TIF_PER_TRAP - xc SP_SVCNR(2,%r15),SP_SVCNR(%r15) # clear svc number + ni __TI_flags+7(%r12),255-(_TIF_SYSCALL | _TIF_PER_TRAP) la %r2,SP_PTREGS(%r15) # address of register-save area larl %r14,sysc_return # load adr. of system return jg do_per_trap @@ -382,7 +367,7 @@ sysc_singlestep: sysc_tracesys: la %r2,SP_PTREGS(%r15) # load pt_regs la %r3,0 - llgh %r0,SP_SVCNR(%r15) + llgh %r0,SP_SVC_CODE+2(%r15) stg %r0,SP_R2(%r15) brasl %r14,do_syscall_trace_enter lghi %r0,NR_syscalls @@ -397,7 +382,7 @@ sysc_tracego: basr %r14,%r8 # call sys_xxx stg %r2,SP_R2(%r15) # store return value sysc_tracenogo: - tm __TI_flags+6(%r12),_TIF_SYSCALL + tm __TI_flags+6(%r12),_TIF_TRACE >> 8 jz sysc_return la %r2,SP_PTREGS(%r15) # load pt_regs larl %r14,sysc_return # return point is sysc_return @@ -470,7 +455,6 @@ ENTRY(pgm_check_handler) jnz pgm_per # got per exception -> special case SAVE_ALL_PGM __LC_PGM_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - xc SP_ILC(4,%r15),SP_ILC(%r15) mvc SP_PSW(16,%r15),__LC_PGM_OLD_PSW lg %r12,__LC_THREAD_INFO # load pointer to thread_info struct HANDLE_SIE_INTERCEPT @@ -550,9 +534,10 @@ pgm_exit2: pgm_svcper: SAVE_ALL_PGM __LC_SVC_OLD_PSW,__LC_SAVE_AREA CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC lg %r12,__LC_THREAD_INFO # load pointer to thread_info struct + mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+7(%r12),(_TIF_SYSCALL | _TIF_PER_TRAP) UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER UPDATE_VTIME __LC_LAST_UPDATE_TIMER,__LC_EXIT_TIMER,__LC_SYSTEM_TIMER mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER @@ -561,7 +546,6 @@ pgm_svcper: mvc __THREAD_per_cause(2,%r8),__LC_PER_CAUSE mvc __THREAD_per_address(8,%r8),__LC_PER_ADDRESS mvc __THREAD_per_paid(1,%r8),__LC_PER_PAID - oi __TI_flags+7(%r12),_TIF_PER_TRAP # set TIF_PER_TRAP stosm __SF_EMPTY(%r15),0x03 # reenable interrupts lmg %r2,%r6,SP_R2(%r15) # load svc arguments j sysc_do_svc @@ -571,7 +555,6 @@ pgm_svcper: # kernel_per: REENABLE_IRQS - xc SP_SVCNR(2,%r15),SP_SVCNR(%r15) # clear svc number la %r2,SP_PTREGS(%r15) # address of register-save area brasl %r14,do_per_trap j pgm_exit @@ -869,12 +852,12 @@ restart_go: # PSW restart interrupt handler # ENTRY(psw_restart_int_handler) - stg %r15,__LC_SAVE_AREA_64(%r0) # save r15 + stg %r15,__LC_SAVE_AREA+120(%r0) # save r15 larl %r15,restart_stack # load restart stack lg %r15,0(%r15) aghi %r15,-SP_SIZE # make room for pt_regs stmg %r0,%r14,SP_R0(%r15) # store gprs %r0-%r14 to stack - mvc SP_R15(8,%r15),__LC_SAVE_AREA_64(%r0)# store saved %r15 to stack + mvc SP_R15(8,%r15),__LC_SAVE_AREA+120(%r0)# store saved %r15 to stack mvc SP_PSW(16,%r15),__LC_RST_OLD_PSW(%r0)# store restart old psw xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) # set backchain to 0 brasl %r14,do_restart @@ -972,9 +955,11 @@ cleanup_system_call: stg %r15,32(%r12) stg %r11,0(%r12) CREATE_STACK_FRAME __LC_SAVE_AREA - mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW - mvc SP_ILC(4,%r15),__LC_SVC_ILC mvc 8(8,%r12),__LC_THREAD_INFO + lg %r12,__LC_THREAD_INFO + mvc SP_PSW(16,%r15),__LC_SVC_OLD_PSW + mvc SP_SVC_CODE(4,%r15),__LC_SVC_ILC + oi __TI_flags+7(%r12),_TIF_SYSCALL cleanup_vtime: clc __LC_RETURN_PSW+8(8),BASED(cleanup_system_call_insn+24) jhe cleanup_stime @@ -1096,6 +1081,7 @@ sie_exit: lghi %r2,0 br %r14 sie_fault: + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce lg %r14,__LC_THREAD_INFO # pointer thread_info struct ni __TI_flags+6(%r14),255-(_TIF_SIE>>8) lg %r14,__SF_EMPTY+8(%r15) # load guest register save area diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index 2d781bab37bb..900068d2bf92 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -449,10 +449,28 @@ ENTRY(start) # .org 0x10000 ENTRY(startup) + j .Lep_startup_normal + .org 0x10008 +# +# This is a list of s390 kernel entry points. At address 0x1000f the number of +# valid entry points is stored. +# +# IMPORTANT: Do not change this table, it is s390 kernel ABI! +# + .ascii "S390EP" + .byte 0x00,0x01 +# +# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode +# + .org 0x10010 +ENTRY(startup_kdump) + j .Lep_startup_kdump +.Lep_startup_normal: basr %r13,0 # get base .LPG0: xc 0x200(256),0x200 # partially clear lowcore xc 0x300(256),0x300 + xc 0xe00(256),0xe00 stck __LC_LAST_UPDATE_CLOCK spt 5f-.LPG0(%r13) mvc __LC_LAST_UPDATE_TIMER(8),5f-.LPG0(%r13) @@ -534,6 +552,8 @@ ENTRY(startup) .align 8 5: .long 0x7fffffff,0xffffffff +#include "head_kdump.S" + # # params at 10400 (setup.h) # @@ -541,6 +561,8 @@ ENTRY(startup) .long 0,0 # IPL_DEVICE .long 0,0 # INITRD_START .long 0,0 # INITRD_SIZE + .long 0,0 # OLDMEM_BASE + .long 0,0 # OLDMEM_SIZE .org COMMAND_LINE .byte "root=/dev/ram0 ro" diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S index f21954b44dc1..d3f1ab7d90ad 100644 --- a/arch/s390/kernel/head31.S +++ b/arch/s390/kernel/head31.S @@ -92,7 +92,7 @@ ENTRY(_stext) .LPG3: # check control registers stctl %c0,%c15,0(%r15) - oi 2(%r15),0x40 # enable sigp emergency signal + oi 2(%r15),0x60 # enable sigp emergency & external call oi 0(%r15),0x10 # switch on low address protection lctl %c0,%c15,0(%r15) diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index ae5d492b069e..99348c0eaa41 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -90,7 +90,7 @@ ENTRY(_stext) .LPG3: # check control registers stctg %c0,%c15,0(%r15) - oi 6(%r15),0x40 # enable sigp emergency signal + oi 6(%r15),0x60 # enable sigp emergency & external call oi 4(%r15),0x10 # switch on low address proctection lctlg %c0,%c15,0(%r15) diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/kernel/head_kdump.S new file mode 100644 index 000000000000..e1ac3893e972 --- /dev/null +++ b/arch/s390/kernel/head_kdump.S @@ -0,0 +1,119 @@ +/* + * S390 kdump lowlevel functions (new kernel) + * + * Copyright IBM Corp. 2011 + * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com> + */ + +#define DATAMOVER_ADDR 0x4000 +#define COPY_PAGE_ADDR 0x6000 + +#ifdef CONFIG_CRASH_DUMP + +# +# kdump entry (new kernel - not yet relocated) +# +# Note: This code has to be position independent +# + +.align 2 +.Lep_startup_kdump: + lhi %r1,2 # mode 2 = esame (dump) + sigp %r1,%r0,0x12 # Switch to esame mode + sam64 # Switch to 64 bit addressing + basr %r13,0 +.Lbase: + larl %r2,.Lbase_addr # Check, if we have been + lg %r2,0(%r2) # already relocated: + clgr %r2,%r13 # + jne .Lrelocate # No : Start data mover + lghi %r2,0 # Yes: Start kdump kernel + brasl %r14,startup_kdump_relocated + +.Lrelocate: + larl %r4,startup + lg %r2,0x418(%r4) # Get kdump base + lg %r3,0x420(%r4) # Get kdump size + + larl %r10,.Lcopy_start # Source of data mover + lghi %r8,DATAMOVER_ADDR # Target of data mover + mvc 0(256,%r8),0(%r10) # Copy data mover code + + agr %r8,%r2 # Copy data mover to + mvc 0(256,%r8),0(%r10) # reserved mem + + lghi %r14,DATAMOVER_ADDR # Jump to copied data mover + basr %r14,%r14 +.Lbase_addr: + .quad .Lbase + +# +# kdump data mover code (runs at address DATAMOVER_ADDR) +# +# r2: kdump base address +# r3: kdump size +# +.Lcopy_start: + basr %r13,0 # Base +0: + lgr %r11,%r2 # Save kdump base address + lgr %r12,%r2 + agr %r12,%r3 # Compute kdump end address + + lghi %r5,0 + lghi %r10,COPY_PAGE_ADDR # Load copy page address +1: + mvc 0(256,%r10),0(%r5) # Copy old kernel to tmp + mvc 0(256,%r5),0(%r11) # Copy new kernel to old + mvc 0(256,%r11),0(%r10) # Copy tmp to new + aghi %r11,256 + aghi %r5,256 + clgr %r11,%r12 + jl 1b + + lg %r14,.Lstartup_kdump-0b(%r13) + basr %r14,%r14 # Start relocated kernel +.Lstartup_kdump: + .long 0x00000000,0x00000000 + startup_kdump_relocated +.Lcopy_end: + +# +# Startup of kdump (relocated new kernel) +# +.align 2 +startup_kdump_relocated: + basr %r13,0 +0: + mvc 0(8,%r0),.Lrestart_psw-0b(%r13) # Setup restart PSW + mvc 464(16,%r0),.Lpgm_psw-0b(%r13) # Setup pgm check PSW + lhi %r1,1 # Start new kernel + diag %r1,%r1,0x308 # with diag 308 + +.Lno_diag308: # No diag 308 + sam31 # Switch to 31 bit addr mode + sr %r1,%r1 # Erase register r1 + sr %r2,%r2 # Erase register r2 + sigp %r1,%r2,0x12 # Switch to 31 bit arch mode + lpsw 0 # Start new kernel... +.align 8 +.Lrestart_psw: + .long 0x00080000,0x80000000 + startup +.Lpgm_psw: + .quad 0x0000000180000000,0x0000000000000000 + .Lno_diag308 +#else +.align 2 +.Lep_startup_kdump: +#ifdef CONFIG_64BIT + larl %r13,startup_kdump_crash + lpswe 0(%r13) +.align 8 +startup_kdump_crash: + .quad 0x0002000080000000,0x0000000000000000 + startup_kdump_crash +#else + basr %r13,0 +0: lpsw startup_kdump_crash-0b(%r13) +.align 8 +startup_kdump_crash: + .long 0x000a0000,0x00000000 + startup_kdump_crash +#endif /* CONFIG_64BIT */ +#endif /* CONFIG_CRASH_DUMP */ diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 48c710206366..affa8e68124a 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -16,6 +16,7 @@ #include <linux/ctype.h> #include <linux/fs.h> #include <linux/gfp.h> +#include <linux/crash_dump.h> #include <asm/ipl.h> #include <asm/smp.h> #include <asm/setup.h> @@ -26,6 +27,7 @@ #include <asm/sclp.h> #include <asm/sigp.h> #include <asm/checksum.h> +#include "entry.h" #define IPL_PARM_BLOCK_VERSION 0 @@ -275,8 +277,8 @@ static ssize_t ipl_type_show(struct kobject *kobj, struct kobj_attribute *attr, static struct kobj_attribute sys_ipl_type_attr = __ATTR_RO(ipl_type); /* VM IPL PARM routines */ -size_t reipl_get_ascii_vmparm(char *dest, size_t size, - const struct ipl_parameter_block *ipb) +static size_t reipl_get_ascii_vmparm(char *dest, size_t size, + const struct ipl_parameter_block *ipb) { int i; size_t len; @@ -338,8 +340,8 @@ static size_t scpdata_length(const char* buf, size_t count) return count; } -size_t reipl_append_ascii_scpdata(char *dest, size_t size, - const struct ipl_parameter_block *ipb) +static size_t reipl_append_ascii_scpdata(char *dest, size_t size, + const struct ipl_parameter_block *ipb) { size_t count; size_t i; @@ -1738,7 +1740,11 @@ static struct kobj_attribute on_restart_attr = void do_restart(void) { + smp_restart_with_online_cpu(); smp_send_stop(); +#ifdef CONFIG_CRASH_DUMP + crash_kexec(NULL); +#endif on_restart_trigger.action->fn(&on_restart_trigger); stop_run(&on_restart_trigger); } @@ -2009,7 +2015,7 @@ static void do_reset_calls(void) u32 dump_prefix_page; -void s390_reset_system(void) +void s390_reset_system(void (*func)(void *), void *data) { struct _lowcore *lc; @@ -2028,15 +2034,19 @@ void s390_reset_system(void) __ctl_clear_bit(0,28); /* Set new machine check handler */ - S390_lowcore.mcck_new_psw.mask = psw_kernel_bits & ~PSW_MASK_MCHECK; + S390_lowcore.mcck_new_psw.mask = psw_kernel_bits | PSW_MASK_DAT; S390_lowcore.mcck_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_mcck_handler; /* Set new program check handler */ - S390_lowcore.program_new_psw.mask = psw_kernel_bits & ~PSW_MASK_MCHECK; + S390_lowcore.program_new_psw.mask = psw_kernel_bits | PSW_MASK_DAT; S390_lowcore.program_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; + /* Store status at absolute zero */ + store_status(); + do_reset_calls(); + if (func) + func(data); } - diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 1f4050d45f78..b9a7fdd9c814 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -33,7 +33,8 @@ static const struct irq_class intrclass_names[] = { {.name = "EXT" }, {.name = "I/O" }, {.name = "CLK", .desc = "[EXT] Clock Comparator" }, - {.name = "IPI", .desc = "[EXT] Signal Processor" }, + {.name = "EXC", .desc = "[EXT] External Call" }, + {.name = "EMS", .desc = "[EXT] Emergency Signal" }, {.name = "TMR", .desc = "[EXT] CPU Timer" }, {.name = "TAL", .desc = "[EXT] Timing Alert" }, {.name = "PFL", .desc = "[EXT] Pseudo Page Fault" }, @@ -42,8 +43,8 @@ static const struct irq_class intrclass_names[] = { {.name = "SCP", .desc = "[EXT] Service Call" }, {.name = "IUC", .desc = "[EXT] IUCV" }, {.name = "CPM", .desc = "[EXT] CPU Measurement" }, + {.name = "CIO", .desc = "[I/O] Common I/O Layer Interrupt" }, {.name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt" }, - {.name = "QDI", .desc = "[I/O] QDIO Interrupt" }, {.name = "DAS", .desc = "[I/O] DASD" }, {.name = "C15", .desc = "[I/O] 3215" }, {.name = "C70", .desc = "[I/O] 3270" }, @@ -53,6 +54,7 @@ static const struct irq_class intrclass_names[] = { {.name = "CLW", .desc = "[I/O] CLAW" }, {.name = "CTC", .desc = "[I/O] CTC" }, {.name = "APB", .desc = "[I/O] AP Bus" }, + {.name = "CSC", .desc = "[I/O] CHSC Subchannel" }, {.name = "NMI", .desc = "[NMI] Machine Check" }, }; diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 1d05d669107c..64b761aef004 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -635,7 +635,7 @@ void __kprobes jprobe_return(void) asm volatile(".word 0x0002"); } -void __kprobes jprobe_return_end(void) +static void __used __kprobes jprobe_return_end(void) { asm volatile("bcr 0,0"); } diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index b09b9c62573e..3cd0f25ab015 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -1,10 +1,11 @@ /* * arch/s390/kernel/machine_kexec.c * - * Copyright IBM Corp. 2005,2006 + * Copyright IBM Corp. 2005,2011 * * Author(s): Rolf Adelsberger, * Heiko Carstens <heiko.carstens@de.ibm.com> + * Michael Holzheu <holzheu@linux.vnet.ibm.com> */ #include <linux/device.h> @@ -21,12 +22,162 @@ #include <asm/smp.h> #include <asm/reset.h> #include <asm/ipl.h> +#include <asm/diag.h> +#include <asm/asm-offsets.h> typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long); extern const unsigned char relocate_kernel[]; extern const unsigned long long relocate_kernel_len; +#ifdef CONFIG_CRASH_DUMP + +void *fill_cpu_elf_notes(void *ptr, struct save_area *sa); + +/* + * Create ELF notes for one CPU + */ +static void add_elf_notes(int cpu) +{ + struct save_area *sa = (void *) 4608 + store_prefix(); + void *ptr; + + memcpy((void *) (4608UL + sa->pref_reg), sa, sizeof(*sa)); + ptr = (u64 *) per_cpu_ptr(crash_notes, cpu); + ptr = fill_cpu_elf_notes(ptr, sa); + memset(ptr, 0, sizeof(struct elf_note)); +} + +/* + * Store status of next available physical CPU + */ +static int store_status_next(int start_cpu, int this_cpu) +{ + struct save_area *sa = (void *) 4608 + store_prefix(); + int cpu, rc; + + for (cpu = start_cpu; cpu < 65536; cpu++) { + if (cpu == this_cpu) + continue; + do { + rc = raw_sigp(cpu, sigp_stop_and_store_status); + } while (rc == sigp_busy); + if (rc != sigp_order_code_accepted) + continue; + if (sa->pref_reg) + return cpu; + } + return -1; +} + +/* + * Initialize CPU ELF notes + */ +void setup_regs(void) +{ + unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE; + int cpu, this_cpu, phys_cpu = 0, first = 1; + + this_cpu = stap(); + + if (!S390_lowcore.prefixreg_save_area) + first = 0; + for_each_online_cpu(cpu) { + if (first) { + add_elf_notes(cpu); + first = 0; + continue; + } + phys_cpu = store_status_next(phys_cpu, this_cpu); + if (phys_cpu == -1) + break; + add_elf_notes(cpu); + phys_cpu++; + } + /* Copy dump CPU store status info to absolute zero */ + memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area)); +} + +#endif + +/* + * Start kdump: We expect here that a store status has been done on our CPU + */ +static void __do_machine_kdump(void *image) +{ +#ifdef CONFIG_CRASH_DUMP + int (*start_kdump)(int) = (void *)((struct kimage *) image)->start; + + __load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA); + setup_regs(); + start_kdump(1); +#endif +} + +/* + * Check if kdump checksums are valid: We call purgatory with parameter "0" + */ +static int kdump_csum_valid(struct kimage *image) +{ +#ifdef CONFIG_CRASH_DUMP + int (*start_kdump)(int) = (void *)image->start; + int rc; + + __arch_local_irq_stnsm(0xfb); /* disable DAT */ + rc = start_kdump(0); + __arch_local_irq_stosm(0x04); /* enable DAT */ + return rc ? 0 : -EINVAL; +#else + return -EINVAL; +#endif +} + +/* + * Map or unmap crashkernel memory + */ +static void crash_map_pages(int enable) +{ + unsigned long size = resource_size(&crashk_res); + + BUG_ON(crashk_res.start % KEXEC_CRASH_MEM_ALIGN || + size % KEXEC_CRASH_MEM_ALIGN); + if (enable) + vmem_add_mapping(crashk_res.start, size); + else + vmem_remove_mapping(crashk_res.start, size); +} + +/* + * Map crashkernel memory + */ +void crash_map_reserved_pages(void) +{ + crash_map_pages(1); +} + +/* + * Unmap crashkernel memory + */ +void crash_unmap_reserved_pages(void) +{ + crash_map_pages(0); +} + +/* + * Give back memory to hypervisor before new kdump is loaded + */ +static int machine_kexec_prepare_kdump(void) +{ +#ifdef CONFIG_CRASH_DUMP + if (MACHINE_IS_VM) + diag10_range(PFN_DOWN(crashk_res.start), + PFN_DOWN(crashk_res.end - crashk_res.start + 1)); + return 0; +#else + return -EINVAL; +#endif +} + int machine_kexec_prepare(struct kimage *image) { void *reboot_code_buffer; @@ -35,6 +186,9 @@ int machine_kexec_prepare(struct kimage *image) if (ipl_flags & IPL_NSS_VALID) return -ENOSYS; + if (image->type == KEXEC_TYPE_CRASH) + return machine_kexec_prepare_kdump(); + /* We don't support anything but the default image type for now. */ if (image->type != KEXEC_TYPE_DEFAULT) return -EINVAL; @@ -51,27 +205,53 @@ void machine_kexec_cleanup(struct kimage *image) { } +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_SYMBOL(lowcore_ptr); + VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS); +} + void machine_shutdown(void) { } -static void __machine_kexec(void *data) +/* + * Do normal kexec + */ +static void __do_machine_kexec(void *data) { relocate_kernel_t data_mover; struct kimage *image = data; - pfault_fini(); - s390_reset_system(); - data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page); /* Call the moving routine */ (*data_mover)(&image->head, image->start); - for (;;); } +/* + * Reset system and call either kdump or normal kexec + */ +static void __machine_kexec(void *data) +{ + struct kimage *image = data; + + pfault_fini(); + if (image->type == KEXEC_TYPE_CRASH) + s390_reset_system(__do_machine_kdump, data); + else + s390_reset_system(__do_machine_kexec, data); + disabled_wait((unsigned long) __builtin_return_address(0)); +} + +/* + * Do either kdump or normal kexec. In case of kdump we first ask + * purgatory, if kdump checksums are valid. + */ void machine_kexec(struct kimage *image) { + if (image->type == KEXEC_TYPE_CRASH && !kdump_csum_valid(image)) + return; tracer_disable(); smp_send_stop(); smp_switch_to_ipl_cpu(__machine_kexec, image); diff --git a/arch/s390/kernel/mem_detect.c b/arch/s390/kernel/mem_detect.c index 0fbe4e32f7ba..19b4568f4cee 100644 --- a/arch/s390/kernel/mem_detect.c +++ b/arch/s390/kernel/mem_detect.c @@ -62,3 +62,72 @@ void detect_memory_layout(struct mem_chunk chunk[]) arch_local_irq_restore(flags); } EXPORT_SYMBOL(detect_memory_layout); + +/* + * Create memory hole with given address, size, and type + */ +void create_mem_hole(struct mem_chunk chunks[], unsigned long addr, + unsigned long size, int type) +{ + unsigned long start, end, new_size; + int i; + + for (i = 0; i < MEMORY_CHUNKS; i++) { + if (chunks[i].size == 0) + continue; + if (addr + size < chunks[i].addr) + continue; + if (addr >= chunks[i].addr + chunks[i].size) + continue; + start = max(addr, chunks[i].addr); + end = min(addr + size, chunks[i].addr + chunks[i].size); + new_size = end - start; + if (new_size == 0) + continue; + if (start == chunks[i].addr && + end == chunks[i].addr + chunks[i].size) { + /* Remove chunk */ + chunks[i].type = type; + } else if (start == chunks[i].addr) { + /* Make chunk smaller at start */ + if (i >= MEMORY_CHUNKS - 1) + panic("Unable to create memory hole"); + memmove(&chunks[i + 1], &chunks[i], + sizeof(struct mem_chunk) * + (MEMORY_CHUNKS - (i + 1))); + chunks[i + 1].addr = chunks[i].addr + new_size; + chunks[i + 1].size = chunks[i].size - new_size; + chunks[i].size = new_size; + chunks[i].type = type; + i += 1; + } else if (end == chunks[i].addr + chunks[i].size) { + /* Make chunk smaller at end */ + if (i >= MEMORY_CHUNKS - 1) + panic("Unable to create memory hole"); + memmove(&chunks[i + 1], &chunks[i], + sizeof(struct mem_chunk) * + (MEMORY_CHUNKS - (i + 1))); + chunks[i + 1].addr = start; + chunks[i + 1].size = new_size; + chunks[i + 1].type = type; + chunks[i].size -= new_size; + i += 1; + } else { + /* Create memory hole */ + if (i >= MEMORY_CHUNKS - 2) + panic("Unable to create memory hole"); + memmove(&chunks[i + 2], &chunks[i], + sizeof(struct mem_chunk) * + (MEMORY_CHUNKS - (i + 2))); + chunks[i + 1].addr = addr; + chunks[i + 1].size = size; + chunks[i + 1].type = type; + chunks[i + 2].addr = addr + size; + chunks[i + 2].size = + chunks[i].addr + chunks[i].size - (addr + size); + chunks[i + 2].type = chunks[i].type; + chunks[i].size = addr - chunks[i].addr; + i += 2; + } + } +} diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 541a7509faeb..9451b210a1b4 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -12,6 +12,7 @@ #include <linux/sched.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/elfcore.h> #include <linux/smp.h> #include <linux/slab.h> #include <linux/interrupt.h> @@ -117,7 +118,8 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) struct pt_regs regs; memset(®s, 0, sizeof(regs)); - regs.psw.mask = psw_kernel_bits | PSW_MASK_IO | PSW_MASK_EXT; + regs.psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; regs.psw.addr = (unsigned long) kernel_thread_starter | PSW_ADDR_AMODE; regs.gprs[9] = (unsigned long) fn; regs.gprs[10] = (unsigned long) arg; diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 311e9d712888..6e0073e43f54 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -74,7 +74,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { - return *pos < NR_CPUS ? (void *)((unsigned long) *pos + 1) : NULL; + return *pos < nr_cpu_ids ? (void *)((unsigned long) *pos + 1) : NULL; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index ef86ad243986..450931a45b68 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -42,34 +42,37 @@ enum s390_regset { REGSET_GENERAL, REGSET_FP, REGSET_LAST_BREAK, + REGSET_SYSTEM_CALL, REGSET_GENERAL_EXTENDED, }; void update_per_regs(struct task_struct *task) { - static const struct per_regs per_single_step = { - .control = PER_EVENT_IFETCH, - .start = 0, - .end = PSW_ADDR_INSN, - }; struct pt_regs *regs = task_pt_regs(task); struct thread_struct *thread = &task->thread; - const struct per_regs *new; - struct per_regs old; - - /* TIF_SINGLE_STEP overrides the user specified PER registers. */ - new = test_tsk_thread_flag(task, TIF_SINGLE_STEP) ? - &per_single_step : &thread->per_user; + struct per_regs old, new; + + /* Copy user specified PER registers */ + new.control = thread->per_user.control; + new.start = thread->per_user.start; + new.end = thread->per_user.end; + + /* merge TIF_SINGLE_STEP into user specified PER registers. */ + if (test_tsk_thread_flag(task, TIF_SINGLE_STEP)) { + new.control |= PER_EVENT_IFETCH; + new.start = 0; + new.end = PSW_ADDR_INSN; + } /* Take care of the PER enablement bit in the PSW. */ - if (!(new->control & PER_EVENT_MASK)) { + if (!(new.control & PER_EVENT_MASK)) { regs->psw.mask &= ~PSW_MASK_PER; return; } regs->psw.mask |= PSW_MASK_PER; __ctl_store(old, 9, 11); - if (memcmp(new, &old, sizeof(struct per_regs)) != 0) - __ctl_load(*new, 9, 11); + if (memcmp(&new, &old, sizeof(struct per_regs)) != 0) + __ctl_load(new, 9, 11); } void user_enable_single_step(struct task_struct *task) @@ -166,8 +169,8 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr) */ tmp = *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr); if (addr == (addr_t) &dummy->regs.psw.mask) - /* Remove per bit from user psw. */ - tmp &= ~PSW_MASK_PER; + /* Return a clean psw mask. */ + tmp = psw_user_bits | (tmp & PSW_MASK_USER); } else if (addr < (addr_t) &dummy->regs.orig_gpr2) { /* @@ -289,18 +292,17 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) * psw and gprs are stored on the stack */ if (addr == (addr_t) &dummy->regs.psw.mask && -#ifdef CONFIG_COMPAT - data != PSW_MASK_MERGE(psw_user32_bits, data) && -#endif - data != PSW_MASK_MERGE(psw_user_bits, data)) + ((data & ~PSW_MASK_USER) != psw_user_bits || + ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA)))) /* Invalid psw mask. */ return -EINVAL; -#ifndef CONFIG_64BIT if (addr == (addr_t) &dummy->regs.psw.addr) - /* I'd like to reject addresses without the - high order bit but older gdb's rely on it */ - data |= PSW_ADDR_AMODE; -#endif + /* + * The debugger changed the instruction address, + * reset system call restart, see signal.c:do_signal + */ + task_thread_info(child)->system_call = 0; + *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data; } else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) { @@ -495,21 +497,21 @@ static u32 __peek_user_compat(struct task_struct *child, addr_t addr) __u32 tmp; if (addr < (addr_t) &dummy32->regs.acrs) { + struct pt_regs *regs = task_pt_regs(child); /* * psw and gprs are stored on the stack */ if (addr == (addr_t) &dummy32->regs.psw.mask) { /* Fake a 31 bit psw mask. */ - tmp = (__u32)(task_pt_regs(child)->psw.mask >> 32); - tmp = PSW32_MASK_MERGE(psw32_user_bits, tmp); + tmp = (__u32)(regs->psw.mask >> 32); + tmp = psw32_user_bits | (tmp & PSW32_MASK_USER); } else if (addr == (addr_t) &dummy32->regs.psw.addr) { /* Fake a 31 bit psw address. */ - tmp = (__u32) task_pt_regs(child)->psw.addr | - PSW32_ADDR_AMODE31; + tmp = (__u32) regs->psw.addr | + (__u32)(regs->psw.mask & PSW_MASK_BA); } else { /* gpr 0-15 */ - tmp = *(__u32 *)((addr_t) &task_pt_regs(child)->psw + - addr*2 + 4); + tmp = *(__u32 *)((addr_t) ®s->psw + addr*2 + 4); } } else if (addr < (addr_t) (&dummy32->regs.orig_gpr2)) { /* @@ -594,24 +596,32 @@ static int __poke_user_compat(struct task_struct *child, addr_t offset; if (addr < (addr_t) &dummy32->regs.acrs) { + struct pt_regs *regs = task_pt_regs(child); /* * psw, gprs, acrs and orig_gpr2 are stored on the stack */ if (addr == (addr_t) &dummy32->regs.psw.mask) { /* Build a 64 bit psw mask from 31 bit mask. */ - if (tmp != PSW32_MASK_MERGE(psw32_user_bits, tmp)) + if ((tmp & ~PSW32_MASK_USER) != psw32_user_bits) /* Invalid psw mask. */ return -EINVAL; - task_pt_regs(child)->psw.mask = - PSW_MASK_MERGE(psw_user32_bits, (__u64) tmp << 32); + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | + (regs->psw.mask & PSW_MASK_BA) | + (__u64)(tmp & PSW32_MASK_USER) << 32; } else if (addr == (addr_t) &dummy32->regs.psw.addr) { /* Build a 64 bit psw address from 31 bit address. */ - task_pt_regs(child)->psw.addr = - (__u64) tmp & PSW32_ADDR_INSN; + regs->psw.addr = (__u64) tmp & PSW32_ADDR_INSN; + /* Transfer 31 bit amode bit to psw mask. */ + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) | + (__u64)(tmp & PSW32_ADDR_AMODE); + /* + * The debugger changed the instruction address, + * reset system call restart, see signal.c:do_signal + */ + task_thread_info(child)->system_call = 0; } else { /* gpr 0-15 */ - *(__u32*)((addr_t) &task_pt_regs(child)->psw - + addr*2 + 4) = tmp; + *(__u32*)((addr_t) ®s->psw + addr*2 + 4) = tmp; } } else if (addr < (addr_t) (&dummy32->regs.orig_gpr2)) { /* @@ -735,7 +745,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) * debugger stored an invalid system call number. Skip * the system call and the system call restart handling. */ - regs->svcnr = 0; + clear_thread_flag(TIF_SYSCALL); ret = -1; } @@ -897,6 +907,26 @@ static int s390_last_break_get(struct task_struct *target, #endif +static int s390_system_call_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + unsigned int *data = &task_thread_info(target)->system_call; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + data, 0, sizeof(unsigned int)); +} + +static int s390_system_call_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + unsigned int *data = &task_thread_info(target)->system_call; + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + data, 0, sizeof(unsigned int)); +} + static const struct user_regset s390_regsets[] = { [REGSET_GENERAL] = { .core_note_type = NT_PRSTATUS, @@ -923,6 +953,14 @@ static const struct user_regset s390_regsets[] = { .get = s390_last_break_get, }, #endif + [REGSET_SYSTEM_CALL] = { + .core_note_type = NT_S390_SYSTEM_CALL, + .n = 1, + .size = sizeof(unsigned int), + .align = sizeof(unsigned int), + .get = s390_system_call_get, + .set = s390_system_call_set, + }, }; static const struct user_regset_view user_s390_view = { @@ -1102,6 +1140,14 @@ static const struct user_regset s390_compat_regsets[] = { .align = sizeof(long), .get = s390_compat_last_break_get, }, + [REGSET_SYSTEM_CALL] = { + .core_note_type = NT_S390_SYSTEM_CALL, + .n = 1, + .size = sizeof(compat_uint_t), + .align = sizeof(compat_uint_t), + .get = s390_system_call_get, + .set = s390_system_call_set, + }, [REGSET_GENERAL_EXTENDED] = { .core_note_type = NT_S390_HIGH_GPRS, .n = sizeof(s390_compat_regs_high) / sizeof(compat_long_t), diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S index 303d961c3bb5..ad67c214be04 100644 --- a/arch/s390/kernel/reipl.S +++ b/arch/s390/kernel/reipl.S @@ -10,6 +10,12 @@ #include <asm/asm-offsets.h> # +# store_status: Empty implementation until kdump is supported on 31 bit +# +ENTRY(store_status) + br %r14 + +# # do_reipl_asm # Parameter: r2 = schid of reipl device # diff --git a/arch/s390/kernel/reipl64.S b/arch/s390/kernel/reipl64.S index e690975403f4..732a793ec53a 100644 --- a/arch/s390/kernel/reipl64.S +++ b/arch/s390/kernel/reipl64.S @@ -17,11 +17,11 @@ # ENTRY(store_status) /* Save register one and load save area base */ - stg %r1,__LC_SAVE_AREA_64(%r0) + stg %r1,__LC_SAVE_AREA+120(%r0) lghi %r1,SAVE_AREA_BASE /* General purpose registers */ stmg %r0,%r15,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) - lg %r2,__LC_SAVE_AREA_64(%r0) + lg %r2,__LC_SAVE_AREA+120(%r0) stg %r2,__LC_GPREGS_SAVE_AREA-SAVE_AREA_BASE+8(%r1) /* Control registers */ stctg %c0,%c15,__LC_CREGS_SAVE_AREA-SAVE_AREA_BASE(%r1) @@ -62,8 +62,11 @@ ENTRY(store_status) larl %r2,store_status stg %r2,__LC_PSW_SAVE_AREA-SAVE_AREA_BASE + 8(%r1) br %r14 -.align 8 + + .section .bss + .align 8 .Lclkcmp: .quad 0x0000000000000000 + .previous # # do_reipl_asm diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 7b371c37061d..8ac6bfa2786c 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -42,6 +42,9 @@ #include <linux/reboot.h> #include <linux/topology.h> #include <linux/ftrace.h> +#include <linux/kexec.h> +#include <linux/crash_dump.h> +#include <linux/memory.h> #include <asm/ipl.h> #include <asm/uaccess.h> @@ -57,12 +60,13 @@ #include <asm/ebcdic.h> #include <asm/compat.h> #include <asm/kvm_virtio.h> +#include <asm/diag.h> -long psw_kernel_bits = (PSW_BASE_BITS | PSW_MASK_DAT | PSW_ASC_PRIMARY | - PSW_MASK_MCHECK | PSW_DEFAULT_KEY); -long psw_user_bits = (PSW_BASE_BITS | PSW_MASK_DAT | PSW_ASC_HOME | - PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK | - PSW_MASK_PSTATE | PSW_DEFAULT_KEY); +long psw_kernel_bits = PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_ASC_PRIMARY | + PSW_MASK_EA | PSW_MASK_BA; +long psw_user_bits = PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | + PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_MCHECK | + PSW_MASK_PSTATE | PSW_ASC_HOME; /* * User copy operations. @@ -274,22 +278,14 @@ early_param("mem", early_parse_mem); unsigned int user_mode = HOME_SPACE_MODE; EXPORT_SYMBOL_GPL(user_mode); -static int set_amode_and_uaccess(unsigned long user_amode, - unsigned long user32_amode) +static int set_amode_primary(void) { - psw_user_bits = PSW_BASE_BITS | PSW_MASK_DAT | user_amode | - PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK | - PSW_MASK_PSTATE | PSW_DEFAULT_KEY; + psw_kernel_bits = (psw_kernel_bits & ~PSW_MASK_ASC) | PSW_ASC_HOME; + psw_user_bits = (psw_user_bits & ~PSW_MASK_ASC) | PSW_ASC_PRIMARY; #ifdef CONFIG_COMPAT - psw_user32_bits = PSW_BASE32_BITS | PSW_MASK_DAT | user_amode | - PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK | - PSW_MASK_PSTATE | PSW_DEFAULT_KEY; - psw32_user_bits = PSW32_BASE_BITS | PSW32_MASK_DAT | user32_amode | - PSW32_MASK_IO | PSW32_MASK_EXT | PSW32_MASK_MCHECK | - PSW32_MASK_PSTATE; + psw32_user_bits = + (psw32_user_bits & ~PSW32_MASK_ASC) | PSW32_ASC_PRIMARY; #endif - psw_kernel_bits = PSW_BASE_BITS | PSW_MASK_DAT | PSW_ASC_HOME | - PSW_MASK_MCHECK | PSW_DEFAULT_KEY; if (MACHINE_HAS_MVCOS) { memcpy(&uaccess, &uaccess_mvcos_switch, sizeof(uaccess)); @@ -325,7 +321,7 @@ early_param("user_mode", early_parse_user_mode); static void setup_addressing_mode(void) { if (user_mode == PRIMARY_SPACE_MODE) { - if (set_amode_and_uaccess(PSW_ASC_PRIMARY, PSW32_ASC_PRIMARY)) + if (set_amode_primary()) pr_info("Address spaces switched, " "mvcos available\n"); else @@ -344,24 +340,25 @@ setup_lowcore(void) */ BUILD_BUG_ON(sizeof(struct _lowcore) != LC_PAGES * 4096); lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0); - lc->restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY; + lc->restart_psw.mask = psw_kernel_bits; lc->restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler; - if (user_mode != HOME_SPACE_MODE) - lc->restart_psw.mask |= PSW_ASC_HOME; - lc->external_new_psw.mask = psw_kernel_bits; + lc->external_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_MCHECK; lc->external_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) ext_int_handler; - lc->svc_new_psw.mask = psw_kernel_bits | PSW_MASK_IO | PSW_MASK_EXT; + lc->svc_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; lc->svc_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) system_call; - lc->program_new_psw.mask = psw_kernel_bits; + lc->program_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_MCHECK; lc->program_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long)pgm_check_handler; - lc->mcck_new_psw.mask = - psw_kernel_bits & ~PSW_MASK_MCHECK & ~PSW_MASK_DAT; + PSW_ADDR_AMODE | (unsigned long) pgm_check_handler; + lc->mcck_new_psw.mask = psw_kernel_bits; lc->mcck_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) mcck_int_handler; - lc->io_new_psw.mask = psw_kernel_bits; + lc->io_new_psw.mask = psw_kernel_bits | + PSW_MASK_DAT | PSW_MASK_MCHECK; lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler; lc->clock_comparator = -1ULL; lc->kernel_stack = ((unsigned long) &init_thread_union) + THREAD_SIZE; @@ -435,10 +432,14 @@ static void __init setup_resources(void) for (i = 0; i < MEMORY_CHUNKS; i++) { if (!memory_chunk[i].size) continue; + if (memory_chunk[i].type == CHUNK_OLDMEM || + memory_chunk[i].type == CHUNK_CRASHK) + continue; res = alloc_bootmem_low(sizeof(*res)); res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; switch (memory_chunk[i].type) { case CHUNK_READ_WRITE: + case CHUNK_CRASHK: res->name = "System RAM"; break; case CHUNK_READ_ONLY: @@ -479,6 +480,7 @@ static void __init setup_memory_end(void) unsigned long max_mem; int i; + #ifdef CONFIG_ZFCPDUMP if (ipl_info.type == IPL_TYPE_FCP_DUMP) { memory_end = ZFCPDUMP_HSA_SIZE; @@ -545,11 +547,201 @@ static void __init setup_restart_psw(void) * Setup restart PSW for absolute zero lowcore. This is necesary * if PSW restart is done on an offline CPU that has lowcore zero */ - psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY; + psw.mask = PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA; psw.addr = PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler; copy_to_absolute_zero(&S390_lowcore.restart_psw, &psw, sizeof(psw)); } +static void __init setup_vmcoreinfo(void) +{ +#ifdef CONFIG_KEXEC + unsigned long ptr = paddr_vmcoreinfo_note(); + + copy_to_absolute_zero(&S390_lowcore.vmcore_info, &ptr, sizeof(ptr)); +#endif +} + +#ifdef CONFIG_CRASH_DUMP + +/* + * Find suitable location for crashkernel memory + */ +static unsigned long __init find_crash_base(unsigned long crash_size, + char **msg) +{ + unsigned long crash_base; + struct mem_chunk *chunk; + int i; + + if (memory_chunk[0].size < crash_size) { + *msg = "first memory chunk must be at least crashkernel size"; + return 0; + } + if (is_kdump_kernel() && (crash_size == OLDMEM_SIZE)) + return OLDMEM_BASE; + + for (i = MEMORY_CHUNKS - 1; i >= 0; i--) { + chunk = &memory_chunk[i]; + if (chunk->size == 0) + continue; + if (chunk->type != CHUNK_READ_WRITE) + continue; + if (chunk->size < crash_size) + continue; + crash_base = (chunk->addr + chunk->size) - crash_size; + if (crash_base < crash_size) + continue; + if (crash_base < ZFCPDUMP_HSA_SIZE_MAX) + continue; + if (crash_base < (unsigned long) INITRD_START + INITRD_SIZE) + continue; + return crash_base; + } + *msg = "no suitable area found"; + return 0; +} + +/* + * Check if crash_base and crash_size is valid + */ +static int __init verify_crash_base(unsigned long crash_base, + unsigned long crash_size, + char **msg) +{ + struct mem_chunk *chunk; + int i; + + /* + * Because we do the swap to zero, we must have at least 'crash_size' + * bytes free space before crash_base + */ + if (crash_size > crash_base) { + *msg = "crashkernel offset must be greater than size"; + return -EINVAL; + } + + /* First memory chunk must be at least crash_size */ + if (memory_chunk[0].size < crash_size) { + *msg = "first memory chunk must be at least crashkernel size"; + return -EINVAL; + } + /* Check if we fit into the respective memory chunk */ + for (i = 0; i < MEMORY_CHUNKS; i++) { + chunk = &memory_chunk[i]; + if (chunk->size == 0) + continue; + if (crash_base < chunk->addr) + continue; + if (crash_base >= chunk->addr + chunk->size) + continue; + /* we have found the memory chunk */ + if (crash_base + crash_size > chunk->addr + chunk->size) { + *msg = "selected memory chunk is too small for " + "crashkernel memory"; + return -EINVAL; + } + return 0; + } + *msg = "invalid memory range specified"; + return -EINVAL; +} + +/* + * Reserve kdump memory by creating a memory hole in the mem_chunk array + */ +static void __init reserve_kdump_bootmem(unsigned long addr, unsigned long size, + int type) +{ + + create_mem_hole(memory_chunk, addr, size, type); +} + +/* + * When kdump is enabled, we have to ensure that no memory from + * the area [0 - crashkernel memory size] and + * [crashk_res.start - crashk_res.end] is set offline. + */ +static int kdump_mem_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct memory_notify *arg = data; + + if (arg->start_pfn < PFN_DOWN(resource_size(&crashk_res))) + return NOTIFY_BAD; + if (arg->start_pfn > PFN_DOWN(crashk_res.end)) + return NOTIFY_OK; + if (arg->start_pfn + arg->nr_pages - 1 < PFN_DOWN(crashk_res.start)) + return NOTIFY_OK; + return NOTIFY_BAD; +} + +static struct notifier_block kdump_mem_nb = { + .notifier_call = kdump_mem_notifier, +}; + +#endif + +/* + * Make sure that oldmem, where the dump is stored, is protected + */ +static void reserve_oldmem(void) +{ +#ifdef CONFIG_CRASH_DUMP + if (!OLDMEM_BASE) + return; + + reserve_kdump_bootmem(OLDMEM_BASE, OLDMEM_SIZE, CHUNK_OLDMEM); + reserve_kdump_bootmem(OLDMEM_SIZE, memory_end - OLDMEM_SIZE, + CHUNK_OLDMEM); + if (OLDMEM_BASE + OLDMEM_SIZE == real_memory_size) + saved_max_pfn = PFN_DOWN(OLDMEM_BASE) - 1; + else + saved_max_pfn = PFN_DOWN(real_memory_size) - 1; +#endif +} + +/* + * Reserve memory for kdump kernel to be loaded with kexec + */ +static void __init reserve_crashkernel(void) +{ +#ifdef CONFIG_CRASH_DUMP + unsigned long long crash_base, crash_size; + char *msg; + int rc; + + rc = parse_crashkernel(boot_command_line, memory_end, &crash_size, + &crash_base); + if (rc || crash_size == 0) + return; + crash_base = ALIGN(crash_base, KEXEC_CRASH_MEM_ALIGN); + crash_size = ALIGN(crash_size, KEXEC_CRASH_MEM_ALIGN); + if (register_memory_notifier(&kdump_mem_nb)) + return; + if (!crash_base) + crash_base = find_crash_base(crash_size, &msg); + if (!crash_base) { + pr_info("crashkernel reservation failed: %s\n", msg); + unregister_memory_notifier(&kdump_mem_nb); + return; + } + if (verify_crash_base(crash_base, crash_size, &msg)) { + pr_info("crashkernel reservation failed: %s\n", msg); + unregister_memory_notifier(&kdump_mem_nb); + return; + } + if (!OLDMEM_BASE && MACHINE_IS_VM) + diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size)); + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; + insert_resource(&iomem_resource, &crashk_res); + reserve_kdump_bootmem(crash_base, crash_size, CHUNK_CRASHK); + pr_info("Reserving %lluMB of memory at %lluMB " + "for crashkernel (System RAM: %luMB)\n", + crash_size >> 20, crash_base >> 20, memory_end >> 20); +#endif +} + static void __init setup_memory(void) { @@ -580,6 +772,14 @@ setup_memory(void) if (PFN_PHYS(start_pfn) + bmap_size > INITRD_START) { start = PFN_PHYS(start_pfn) + bmap_size + PAGE_SIZE; +#ifdef CONFIG_CRASH_DUMP + if (OLDMEM_BASE) { + /* Move initrd behind kdump oldmem */ + if (start + INITRD_SIZE > OLDMEM_BASE && + start < OLDMEM_BASE + OLDMEM_SIZE) + start = OLDMEM_BASE + OLDMEM_SIZE; + } +#endif if (start + INITRD_SIZE > memory_end) { pr_err("initrd extends beyond end of " "memory (0x%08lx > 0x%08lx) " @@ -610,7 +810,8 @@ setup_memory(void) for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) { unsigned long start_chunk, end_chunk, pfn; - if (memory_chunk[i].type != CHUNK_READ_WRITE) + if (memory_chunk[i].type != CHUNK_READ_WRITE && + memory_chunk[i].type != CHUNK_CRASHK) continue; start_chunk = PFN_DOWN(memory_chunk[i].addr); end_chunk = start_chunk + PFN_DOWN(memory_chunk[i].size); @@ -644,6 +845,15 @@ setup_memory(void) reserve_bootmem(start_pfn << PAGE_SHIFT, bootmap_size, BOOTMEM_DEFAULT); +#ifdef CONFIG_CRASH_DUMP + if (crashk_res.start) + reserve_bootmem(crashk_res.start, + crashk_res.end - crashk_res.start + 1, + BOOTMEM_DEFAULT); + if (is_kdump_kernel()) + reserve_bootmem(elfcorehdr_addr - OLDMEM_BASE, + PAGE_ALIGN(elfcorehdr_size), BOOTMEM_DEFAULT); +#endif #ifdef CONFIG_BLK_DEV_INITRD if (INITRD_START && INITRD_SIZE) { if (INITRD_START + INITRD_SIZE <= memory_end) { @@ -812,8 +1022,11 @@ setup_arch(char **cmdline_p) setup_ipl(); setup_memory_end(); setup_addressing_mode(); + reserve_oldmem(); + reserve_crashkernel(); setup_memory(); setup_resources(); + setup_vmcoreinfo(); setup_restart_psw(); setup_lowcore(); diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 9a40e1cc5ec3..05a85bc14c98 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -30,6 +30,7 @@ #include <asm/ucontext.h> #include <asm/uaccess.h> #include <asm/lowcore.h> +#include <asm/compat.h> #include "entry.h" #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) @@ -116,7 +117,8 @@ static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs) /* Copy a 'clean' PSW mask to the user to avoid leaking information about whether PER is currently on. */ - user_sregs.regs.psw.mask = PSW_MASK_MERGE(psw_user_bits, regs->psw.mask); + user_sregs.regs.psw.mask = psw_user_bits | + (regs->psw.mask & PSW_MASK_USER); user_sregs.regs.psw.addr = regs->psw.addr; memcpy(&user_sregs.regs.gprs, ®s->gprs, sizeof(sregs->regs.gprs)); memcpy(&user_sregs.regs.acrs, current->thread.acrs, @@ -143,9 +145,13 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs) err = __copy_from_user(&user_sregs, sregs, sizeof(_sigregs)); if (err) return err; - regs->psw.mask = PSW_MASK_MERGE(regs->psw.mask, - user_sregs.regs.psw.mask); - regs->psw.addr = PSW_ADDR_AMODE | user_sregs.regs.psw.addr; + /* Use regs->psw.mask instead of psw_user_bits to preserve PER bit. */ + regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) | + (user_sregs.regs.psw.mask & PSW_MASK_USER); + /* Check for invalid amode */ + if (regs->psw.mask & PSW_MASK_EA) + regs->psw.mask |= PSW_MASK_BA; + regs->psw.addr = user_sregs.regs.psw.addr; memcpy(®s->gprs, &user_sregs.regs.gprs, sizeof(sregs->regs.gprs)); memcpy(¤t->thread.acrs, &user_sregs.regs.acrs, sizeof(sregs->regs.acrs)); @@ -156,7 +162,7 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs) current->thread.fp_regs.fpc &= FPC_VALID_MASK; restore_fp_regs(¤t->thread.fp_regs); - regs->svcnr = 0; /* disable syscall checks */ + clear_thread_flag(TIF_SYSCALL); /* No longer in a system call */ return 0; } @@ -288,6 +294,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, /* Set up registers for signal handler */ regs->gprs[15] = (unsigned long) frame; + regs->psw.mask |= PSW_MASK_EA | PSW_MASK_BA; /* 64 bit amode */ regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; regs->gprs[2] = map_signal(sig); @@ -356,6 +363,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, /* Set up registers for signal handler */ regs->gprs[15] = (unsigned long) frame; + regs->psw.mask |= PSW_MASK_EA | PSW_MASK_BA; /* 64 bit amode */ regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; regs->gprs[2] = map_signal(sig); @@ -401,7 +409,6 @@ static int handle_signal(unsigned long sig, struct k_sigaction *ka, */ void do_signal(struct pt_regs *regs) { - unsigned long retval = 0, continue_addr = 0, restart_addr = 0; siginfo_t info; int signr; struct k_sigaction ka; @@ -421,54 +428,45 @@ void do_signal(struct pt_regs *regs) else oldset = ¤t->blocked; - /* Are we from a system call? */ - if (regs->svcnr) { - continue_addr = regs->psw.addr; - restart_addr = continue_addr - regs->ilc; - retval = regs->gprs[2]; - - /* Prepare for system call restart. We do this here so that a - debugger will see the already changed PSW. */ - switch (retval) { - case -ERESTARTNOHAND: - case -ERESTARTSYS: - case -ERESTARTNOINTR: - regs->gprs[2] = regs->orig_gpr2; - regs->psw.addr = restart_addr; - break; - case -ERESTART_RESTARTBLOCK: - regs->gprs[2] = -EINTR; - } - regs->svcnr = 0; /* Don't deal with this again. */ - } - - /* Get signal to deliver. When running under ptrace, at this point - the debugger may change all our registers ... */ + /* + * Get signal to deliver. When running under ptrace, at this point + * the debugger may change all our registers, including the system + * call information. + */ + current_thread_info()->system_call = + test_thread_flag(TIF_SYSCALL) ? regs->svc_code : 0; signr = get_signal_to_deliver(&info, &ka, regs, NULL); - /* Depending on the signal settings we may need to revert the - decision to restart the system call. */ - if (signr > 0 && regs->psw.addr == restart_addr) { - if (retval == -ERESTARTNOHAND - || (retval == -ERESTARTSYS - && !(current->sighand->action[signr-1].sa.sa_flags - & SA_RESTART))) { - regs->gprs[2] = -EINTR; - regs->psw.addr = continue_addr; - } - } - if (signr > 0) { /* Whee! Actually deliver the signal. */ - int ret; -#ifdef CONFIG_COMPAT - if (is_compat_task()) { - ret = handle_signal32(signr, &ka, &info, oldset, regs); - } - else -#endif - ret = handle_signal(signr, &ka, &info, oldset, regs); - if (!ret) { + if (current_thread_info()->system_call) { + regs->svc_code = current_thread_info()->system_call; + /* Check for system call restarting. */ + switch (regs->gprs[2]) { + case -ERESTART_RESTARTBLOCK: + case -ERESTARTNOHAND: + regs->gprs[2] = -EINTR; + break; + case -ERESTARTSYS: + if (!(ka.sa.sa_flags & SA_RESTART)) { + regs->gprs[2] = -EINTR; + break; + } + /* fallthrough */ + case -ERESTARTNOINTR: + regs->gprs[2] = regs->orig_gpr2; + regs->psw.addr = + __rewind_psw(regs->psw, + regs->svc_code >> 16); + break; + } + /* No longer in a system call */ + clear_thread_flag(TIF_SYSCALL); + } + + if ((is_compat_task() ? + handle_signal32(signr, &ka, &info, oldset, regs) : + handle_signal(signr, &ka, &info, oldset, regs)) == 0) { /* * A signal was successfully delivered; the saved * sigmask will have been stored in the signal frame, @@ -482,11 +480,32 @@ void do_signal(struct pt_regs *regs) * Let tracing know that we've done the handler setup. */ tracehook_signal_handler(signr, &info, &ka, regs, - test_thread_flag(TIF_SINGLE_STEP)); + test_thread_flag(TIF_SINGLE_STEP)); } return; } + /* No handlers present - check for system call restart */ + if (current_thread_info()->system_call) { + regs->svc_code = current_thread_info()->system_call; + switch (regs->gprs[2]) { + case -ERESTART_RESTARTBLOCK: + /* Restart with sys_restart_syscall */ + regs->svc_code = __NR_restart_syscall; + /* fallthrough */ + case -ERESTARTNOHAND: + case -ERESTARTSYS: + case -ERESTARTNOINTR: + /* Restart system call with magic TIF bit. */ + regs->gprs[2] = regs->orig_gpr2; + set_thread_flag(TIF_SYSCALL); + break; + default: + clear_thread_flag(TIF_SYSCALL); + break; + } + } + /* * If there's no signal to deliver, we just put the saved sigmask back. */ @@ -494,13 +513,6 @@ void do_signal(struct pt_regs *regs) clear_thread_flag(TIF_RESTORE_SIGMASK); sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); } - - /* Restart a different system call. */ - if (retval == -ERESTART_RESTARTBLOCK - && regs->psw.addr == continue_addr) { - regs->gprs[2] = __NR_restart_syscall; - set_thread_flag(TIF_RESTART_SVC); - } } void do_notify_resume(struct pt_regs *regs) diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 6ab16ac64d29..3ea872890da2 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -38,6 +38,7 @@ #include <linux/timex.h> #include <linux/bootmem.h> #include <linux/slab.h> +#include <linux/crash_dump.h> #include <asm/asm-offsets.h> #include <asm/ipl.h> #include <asm/setup.h> @@ -97,6 +98,29 @@ static inline int cpu_stopped(int cpu) return raw_cpu_stopped(cpu_logical_map(cpu)); } +/* + * Ensure that PSW restart is done on an online CPU + */ +void smp_restart_with_online_cpu(void) +{ + int cpu; + + for_each_online_cpu(cpu) { + if (stap() == __cpu_logical_map[cpu]) { + /* We are online: Enable DAT again and return */ + __load_psw_mask(psw_kernel_bits | PSW_MASK_DAT); + return; + } + } + /* We are not online: Do PSW restart on an online CPU */ + while (sigp(cpu, sigp_restart) == sigp_busy) + cpu_relax(); + /* And stop ourself */ + while (raw_sigp(stap(), sigp_stop) == sigp_busy) + cpu_relax(); + for (;;); +} + void smp_switch_to_ipl_cpu(void (*func)(void *), void *data) { struct _lowcore *lc, *current_lc; @@ -106,14 +130,16 @@ void smp_switch_to_ipl_cpu(void (*func)(void *), void *data) if (smp_processor_id() == 0) func(data); - __load_psw_mask(PSW_BASE_BITS | PSW_DEFAULT_KEY); + __load_psw_mask(PSW_DEFAULT_KEY | PSW_MASK_BASE | + PSW_MASK_EA | PSW_MASK_BA); /* Disable lowcore protection */ __ctl_clear_bit(0, 28); current_lc = lowcore_ptr[smp_processor_id()]; lc = lowcore_ptr[0]; if (!lc) lc = current_lc; - lc->restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY; + lc->restart_psw.mask = + PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA; lc->restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) smp_restart_cpu; if (!cpu_online(0)) smp_switch_to_cpu(func, data, 0, stap(), __cpu_logical_map[0]); @@ -135,7 +161,7 @@ void smp_send_stop(void) int cpu, rc; /* Disable all interrupts/machine checks */ - __load_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK); + __load_psw_mask(psw_kernel_bits | PSW_MASK_DAT); trace_hardirqs_off(); /* stop all processors */ @@ -161,7 +187,10 @@ static void do_ext_call_interrupt(unsigned int ext_int_code, { unsigned long bits; - kstat_cpu(smp_processor_id()).irqs[EXTINT_IPI]++; + if (ext_int_code == 0x1202) + kstat_cpu(smp_processor_id()).irqs[EXTINT_EXC]++; + else + kstat_cpu(smp_processor_id()).irqs[EXTINT_EMS]++; /* * handle bit signal external calls */ @@ -183,12 +212,19 @@ static void do_ext_call_interrupt(unsigned int ext_int_code, */ static void smp_ext_bitcall(int cpu, int sig) { + int order; + /* * Set signaling bit in lowcore of target cpu and kick it */ set_bit(sig, (unsigned long *) &lowcore_ptr[cpu]->ext_call_fast); - while (sigp(cpu, sigp_emergency_signal) == sigp_busy) + while (1) { + order = smp_vcpu_scheduled(cpu) ? + sigp_external_call : sigp_emergency_signal; + if (sigp(cpu, order) != sigp_busy) + break; udelay(10); + } } void arch_send_call_function_ipi_mask(const struct cpumask *mask) @@ -281,11 +317,13 @@ void smp_ctl_clear_bit(int cr, int bit) } EXPORT_SYMBOL(smp_ctl_clear_bit); -#ifdef CONFIG_ZFCPDUMP +#if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_CRASH_DUMP) static void __init smp_get_save_area(unsigned int cpu, unsigned int phy_cpu) { - if (ipl_info.type != IPL_TYPE_FCP_DUMP) + if (ipl_info.type != IPL_TYPE_FCP_DUMP && !OLDMEM_BASE) + return; + if (is_kdump_kernel()) return; if (cpu >= NR_CPUS) { pr_warning("CPU %i exceeds the maximum %i and is excluded from " @@ -403,6 +441,18 @@ static void __init smp_detect_cpus(void) info = kmalloc(sizeof(*info), GFP_KERNEL); if (!info) panic("smp_detect_cpus failed to allocate memory\n"); +#ifdef CONFIG_CRASH_DUMP + if (OLDMEM_BASE && !is_kdump_kernel()) { + struct save_area *save_area; + + save_area = kmalloc(sizeof(*save_area), GFP_KERNEL); + if (!save_area) + panic("could not allocate memory for save area\n"); + copy_oldmem_page(1, (void *) save_area, sizeof(*save_area), + 0x200, 0); + zfcpdump_save_areas[0] = save_area; + } +#endif /* Use sigp detection algorithm if sclp doesn't work. */ if (sclp_get_cpu_info(info)) { smp_use_sigp_detection = 1; @@ -463,7 +513,8 @@ int __cpuinit start_secondary(void *cpuvoid) set_cpu_online(smp_processor_id(), true); ipi_call_unlock(); __ctl_clear_bit(0, 28); /* Disable lowcore protection */ - S390_lowcore.restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY; + S390_lowcore.restart_psw.mask = + PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA; S390_lowcore.restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler; __ctl_set_bit(0, 28); /* Enable lowcore protection */ @@ -511,7 +562,8 @@ static int __cpuinit smp_alloc_lowcore(int cpu) memset((char *)lowcore + 512, 0, sizeof(*lowcore) - 512); lowcore->async_stack = async_stack + ASYNC_SIZE; lowcore->panic_stack = panic_stack + PAGE_SIZE; - lowcore->restart_psw.mask = PSW_BASE_BITS | PSW_DEFAULT_KEY; + lowcore->restart_psw.mask = + PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_EA | PSW_MASK_BA; lowcore->restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) restart_int_handler; if (user_mode != HOME_SPACE_MODE) @@ -712,6 +764,9 @@ void __init smp_prepare_cpus(unsigned int max_cpus) /* request the 0x1201 emergency signal external interrupt */ if (register_external_interrupt(0x1201, do_ext_call_interrupt) != 0) panic("Couldn't request external interrupt 0x1201"); + /* request the 0x1202 external call external interrupt */ + if (register_external_interrupt(0x1202, do_ext_call_interrupt) != 0) + panic("Couldn't request external interrupt 0x1202"); /* Reallocate current lowcore, but keep its contents. */ lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, LC_ORDER); diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c index cf9e5c6d5527..47df775c844d 100644 --- a/arch/s390/kernel/suspend.c +++ b/arch/s390/kernel/suspend.c @@ -7,6 +7,8 @@ */ #include <linux/pfn.h> +#include <linux/suspend.h> +#include <linux/mm.h> #include <asm/system.h> /* @@ -14,6 +16,123 @@ */ extern const void __nosave_begin, __nosave_end; +/* + * The restore of the saved pages in an hibernation image will set + * the change and referenced bits in the storage key for each page. + * Overindication of the referenced bits after an hibernation cycle + * does not cause any harm but the overindication of the change bits + * would cause trouble. + * Use the ARCH_SAVE_PAGE_KEYS hooks to save the storage key of each + * page to the most significant byte of the associated page frame + * number in the hibernation image. + */ + +/* + * Key storage is allocated as a linked list of pages. + * The size of the keys array is (PAGE_SIZE - sizeof(long)) + */ +struct page_key_data { + struct page_key_data *next; + unsigned char data[]; +}; + +#define PAGE_KEY_DATA_SIZE (PAGE_SIZE - sizeof(struct page_key_data *)) + +static struct page_key_data *page_key_data; +static struct page_key_data *page_key_rp, *page_key_wp; +static unsigned long page_key_rx, page_key_wx; + +/* + * For each page in the hibernation image one additional byte is + * stored in the most significant byte of the page frame number. + * On suspend no additional memory is required but on resume the + * keys need to be memorized until the page data has been restored. + * Only then can the storage keys be set to their old state. + */ +unsigned long page_key_additional_pages(unsigned long pages) +{ + return DIV_ROUND_UP(pages, PAGE_KEY_DATA_SIZE); +} + +/* + * Free page_key_data list of arrays. + */ +void page_key_free(void) +{ + struct page_key_data *pkd; + + while (page_key_data) { + pkd = page_key_data; + page_key_data = pkd->next; + free_page((unsigned long) pkd); + } +} + +/* + * Allocate page_key_data list of arrays with enough room to store + * one byte for each page in the hibernation image. + */ +int page_key_alloc(unsigned long pages) +{ + struct page_key_data *pk; + unsigned long size; + + size = DIV_ROUND_UP(pages, PAGE_KEY_DATA_SIZE); + while (size--) { + pk = (struct page_key_data *) get_zeroed_page(GFP_KERNEL); + if (!pk) { + page_key_free(); + return -ENOMEM; + } + pk->next = page_key_data; + page_key_data = pk; + } + page_key_rp = page_key_wp = page_key_data; + page_key_rx = page_key_wx = 0; + return 0; +} + +/* + * Save the storage key into the upper 8 bits of the page frame number. + */ +void page_key_read(unsigned long *pfn) +{ + unsigned long addr; + + addr = (unsigned long) page_address(pfn_to_page(*pfn)); + *(unsigned char *) pfn = (unsigned char) page_get_storage_key(addr); +} + +/* + * Extract the storage key from the upper 8 bits of the page frame number + * and store it in the page_key_data list of arrays. + */ +void page_key_memorize(unsigned long *pfn) +{ + page_key_wp->data[page_key_wx] = *(unsigned char *) pfn; + *(unsigned char *) pfn = 0; + if (++page_key_wx < PAGE_KEY_DATA_SIZE) + return; + page_key_wp = page_key_wp->next; + page_key_wx = 0; +} + +/* + * Get the next key from the page_key_data list of arrays and set the + * storage key of the page referred by @address. If @address refers to + * a "safe" page the swsusp_arch_resume code will transfer the storage + * key from the buffer page to the original page. + */ +void page_key_write(void *address) +{ + page_set_storage_key((unsigned long) address, + page_key_rp->data[page_key_rx], 0); + if (++page_key_rx >= PAGE_KEY_DATA_SIZE) + return; + page_key_rp = page_key_rp->next; + page_key_rx = 0; +} + int pfn_is_nosave(unsigned long pfn) { unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin)); diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index 51bcdb50a230..acb78cdee896 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -136,11 +136,14 @@ ENTRY(swsusp_arch_resume) 0: lg %r2,8(%r1) lg %r4,0(%r1) + iske %r0,%r4 lghi %r3,PAGE_SIZE lghi %r5,PAGE_SIZE 1: mvcle %r2,%r4,0 jo 1b + lg %r2,8(%r1) + sske %r0,%r2 lg %r1,16(%r1) ltgr %r1,%r1 jnz 0b diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index 5c9e439bf3f6..2a94b774695c 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -442,7 +442,7 @@ void s390_adjust_jiffies(void) */ FP_UNPACK_SP(SA, &fmil); if ((info->capability >> 23) == 0) - FP_FROM_INT_S(SB, info->capability, 32, int); + FP_FROM_INT_S(SB, (long) info->capability, 64, long); else FP_UNPACK_SP(SB, &info->capability); FP_DIV_S(SR, SA, SB); diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index dff933065ab6..ebbfab3c6e5a 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -48,6 +48,7 @@ #include <asm/timer.h> #include <asm/etr.h> #include <asm/cio.h> +#include "entry.h" /* change this if you have some constant time drift */ #define USECS_PER_JIFFY ((unsigned long) 1000000/HZ) @@ -109,10 +110,14 @@ static void fixup_clock_comparator(unsigned long long delta) set_clock_comparator(S390_lowcore.clock_comparator); } -static int s390_next_event(unsigned long delta, +static int s390_next_ktime(ktime_t expires, struct clock_event_device *evt) { - S390_lowcore.clock_comparator = get_clock() + delta; + u64 nsecs; + + nsecs = ktime_to_ns(ktime_sub(expires, ktime_get_monotonic_offset())); + do_div(nsecs, 125); + S390_lowcore.clock_comparator = TOD_UNIX_EPOCH + (nsecs << 9); set_clock_comparator(S390_lowcore.clock_comparator); return 0; } @@ -137,14 +142,15 @@ void init_cpu_timer(void) cpu = smp_processor_id(); cd = &per_cpu(comparators, cpu); cd->name = "comparator"; - cd->features = CLOCK_EVT_FEAT_ONESHOT; + cd->features = CLOCK_EVT_FEAT_ONESHOT | + CLOCK_EVT_FEAT_KTIME; cd->mult = 16777; cd->shift = 12; cd->min_delta_ns = 1; cd->max_delta_ns = LONG_MAX; cd->rating = 400; cd->cpumask = cpumask_of(cpu); - cd->set_next_event = s390_next_event; + cd->set_next_ktime = s390_next_ktime; cd->set_mode = s390_set_mode; clockevents_register_device(cd); diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 0cd340b72632..77b8942b9a15 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -299,8 +299,8 @@ out: } __initcall(init_topology_update); -static void alloc_masks(struct sysinfo_15_1_x *info, struct mask_info *mask, - int offset) +static void __init alloc_masks(struct sysinfo_15_1_x *info, + struct mask_info *mask, int offset) { int i, nr_masks; diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index ffabcd9d3363..a9807dd86276 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -200,7 +200,7 @@ void show_registers(struct pt_regs *regs) mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC), mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM)); #ifdef CONFIG_64BIT - printk(" EA:%x", mask_bits(regs, PSW_BASE_BITS)); + printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA)); #endif printk("\n%s GPRS: " FOURLONG, mode, regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); @@ -334,7 +334,8 @@ void __kprobes do_per_trap(struct pt_regs *regs) info.si_signo = SIGTRAP; info.si_errno = 0; info.si_code = TRAP_HWBKPT; - info.si_addr = (void *) current->thread.per_event.address; + info.si_addr = + (void __force __user *) current->thread.per_event.address; force_sig_info(SIGTRAP, &info, current); } diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 2d6228f60cd6..bb48977f5469 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -170,7 +170,8 @@ void __kprobes vtime_stop_cpu(void) psw_t psw; /* Wait for external, I/O or machine check interrupt. */ - psw.mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_IO | PSW_MASK_EXT; + psw.mask = psw_kernel_bits | PSW_MASK_WAIT | + PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; idle->nohz_delay = 0; @@ -183,7 +184,8 @@ void __kprobes vtime_stop_cpu(void) * set_cpu_timer(VTIMER_MAX_SLICE); * idle->idle_enter = get_clock(); * __load_psw_mask(psw_kernel_bits | PSW_MASK_WAIT | - * PSW_MASK_IO | PSW_MASK_EXT); + * PSW_MASK_DAT | PSW_MASK_IO | + * PSW_MASK_EXT | PSW_MASK_MCHECK); * The difference is that the inline assembly makes sure that * the last three instruction are stpt, stck and lpsw in that * order. This is done to increase the precision. @@ -216,7 +218,8 @@ void __kprobes vtime_stop_cpu(void) * vq->idle = get_cpu_timer(); * idle->idle_enter = get_clock(); * __load_psw_mask(psw_kernel_bits | PSW_MASK_WAIT | - * PSW_MASK_IO | PSW_MASK_EXT); + * PSW_MASK_DAT | PSW_MASK_IO | + * PSW_MASK_EXT | PSW_MASK_MCHECK); * The difference is that the inline assembly makes sure that * the last three instruction are stpt, stck and lpsw in that * order. This is done to increase the precision. @@ -458,7 +461,7 @@ void add_virt_timer_periodic(void *new) } EXPORT_SYMBOL(add_virt_timer_periodic); -int __mod_vtimer(struct vtimer_list *timer, __u64 expires, int periodic) +static int __mod_vtimer(struct vtimer_list *timer, __u64 expires, int periodic) { struct vtimer_queue *vq; unsigned long flags; diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 9e4c84187cf5..87cedd61be04 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -1,7 +1,7 @@ /* * diag.c - handling diagnose instructions * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008,2011 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License (version 2 only) @@ -15,6 +15,34 @@ #include <linux/kvm_host.h> #include "kvm-s390.h" +static int diag_release_pages(struct kvm_vcpu *vcpu) +{ + unsigned long start, end; + unsigned long prefix = vcpu->arch.sie_block->prefix; + + start = vcpu->arch.guest_gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; + end = vcpu->arch.guest_gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096; + + if (start & ~PAGE_MASK || end & ~PAGE_MASK || start > end + || start < 2 * PAGE_SIZE) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + + VCPU_EVENT(vcpu, 5, "diag release pages %lX %lX", start, end); + vcpu->stat.diagnose_10++; + + /* we checked for start > end above */ + if (end < prefix || start >= prefix + 2 * PAGE_SIZE) { + gmap_discard(start, end, vcpu->arch.gmap); + } else { + if (start < prefix) + gmap_discard(start, prefix, vcpu->arch.gmap); + if (end >= prefix) + gmap_discard(prefix + 2 * PAGE_SIZE, + end, vcpu->arch.gmap); + } + return 0; +} + static int __diag_time_slice_end(struct kvm_vcpu *vcpu) { VCPU_EVENT(vcpu, 5, "%s", "diag time slice end"); @@ -57,6 +85,8 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16; switch (code) { + case 0x10: + return diag_release_pages(vcpu); case 0x44: return __diag_time_slice_end(vcpu); case 0x308: diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c9aeb4b4d0b8..87c16705b381 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -38,6 +38,11 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu, struct kvm_s390_interrupt_info *inti) { switch (inti->type) { + case KVM_S390_INT_EXTERNAL_CALL: + if (psw_extint_disabled(vcpu)) + return 0; + if (vcpu->arch.sie_block->gcr[0] & 0x2000ul) + return 1; case KVM_S390_INT_EMERGENCY: if (psw_extint_disabled(vcpu)) return 0; @@ -98,6 +103,7 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu, struct kvm_s390_interrupt_info *inti) { switch (inti->type) { + case KVM_S390_INT_EXTERNAL_CALL: case KVM_S390_INT_EMERGENCY: case KVM_S390_INT_SERVICE: case KVM_S390_INT_VIRTIO: @@ -143,6 +149,28 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu, exception = 1; break; + case KVM_S390_INT_EXTERNAL_CALL: + VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call"); + vcpu->stat.deliver_external_call++; + rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1202); + if (rc == -EFAULT) + exception = 1; + + rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, inti->extcall.code); + if (rc == -EFAULT) + exception = 1; + + rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + + rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw, + __LC_EXT_NEW_PSW, sizeof(psw_t)); + if (rc == -EFAULT) + exception = 1; + break; + case KVM_S390_INT_SERVICE: VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x", inti->ext.ext_params); @@ -522,6 +550,7 @@ int kvm_s390_inject_vm(struct kvm *kvm, break; case KVM_S390_PROGRAM_INT: case KVM_S390_SIGP_STOP: + case KVM_S390_INT_EXTERNAL_CALL: case KVM_S390_INT_EMERGENCY: default: kfree(inti); @@ -581,6 +610,7 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, break; case KVM_S390_SIGP_STOP: case KVM_S390_RESTART: + case KVM_S390_INT_EXTERNAL_CALL: case KVM_S390_INT_EMERGENCY: VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type); inti->type = s390int->type; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index dc2b580e27bc..0bd3bea1e4cd 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -46,6 +46,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_lctlg", VCPU_STAT(instruction_lctlg) }, { "instruction_lctl", VCPU_STAT(instruction_lctl) }, { "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) }, + { "deliver_external_call", VCPU_STAT(deliver_external_call) }, { "deliver_service_signal", VCPU_STAT(deliver_service_signal) }, { "deliver_virtio_interrupt", VCPU_STAT(deliver_virtio_interrupt) }, { "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) }, @@ -64,11 +65,13 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_stfl", VCPU_STAT(instruction_stfl) }, { "instruction_tprot", VCPU_STAT(instruction_tprot) }, { "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) }, + { "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) }, { "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) }, { "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) }, { "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) }, { "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) }, { "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) }, + { "diagnose_10", VCPU_STAT(diagnose_10) }, { "diagnose_44", VCPU_STAT(diagnose_44) }, { NULL } }; @@ -175,6 +178,8 @@ int kvm_arch_init_vm(struct kvm *kvm) if (rc) goto out_err; + rc = -ENOMEM; + kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL); if (!kvm->arch.sca) goto out_err; @@ -312,11 +317,17 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) { - struct kvm_vcpu *vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL); - int rc = -ENOMEM; + struct kvm_vcpu *vcpu; + int rc = -EINVAL; + + if (id >= KVM_MAX_VCPUS) + goto out; + rc = -ENOMEM; + + vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL); if (!vcpu) - goto out_nomem; + goto out; vcpu->arch.sie_block = (struct kvm_s390_sie_block *) get_zeroed_page(GFP_KERNEL); @@ -352,7 +363,7 @@ out_free_sie_block: free_page((unsigned long)(vcpu->arch.sie_block)); out_free_cpu: kfree(vcpu); -out_nomem: +out: return ERR_PTR(rc); } @@ -386,6 +397,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, { memcpy(&vcpu->arch.guest_acrs, &sregs->acrs, sizeof(sregs->acrs)); memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs)); + restore_access_regs(vcpu->arch.guest_acrs); return 0; } @@ -401,6 +413,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs)); vcpu->arch.guest_fpregs.fpc = fpu->fpc; + restore_fp_regs(&vcpu->arch.guest_fpregs); return 0; } diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index d6a50c1fb2e6..f815118835f3 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -87,6 +87,7 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) return -ENOMEM; inti->type = KVM_S390_INT_EMERGENCY; + inti->emerg.code = vcpu->vcpu_id; spin_lock(&fi->lock); li = fi->local_int[cpu_addr]; @@ -103,9 +104,47 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) wake_up_interruptible(&li->wq); spin_unlock_bh(&li->lock); rc = 0; /* order accepted */ + VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); +unlock: + spin_unlock(&fi->lock); + return rc; +} + +static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) +{ + struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; + struct kvm_s390_local_interrupt *li; + struct kvm_s390_interrupt_info *inti; + int rc; + + if (cpu_addr >= KVM_MAX_VCPUS) + return 3; /* not operational */ + + inti = kzalloc(sizeof(*inti), GFP_KERNEL); + if (!inti) + return -ENOMEM; + + inti->type = KVM_S390_INT_EXTERNAL_CALL; + inti->extcall.code = vcpu->vcpu_id; + + spin_lock(&fi->lock); + li = fi->local_int[cpu_addr]; + if (li == NULL) { + rc = 3; /* not operational */ + kfree(inti); + goto unlock; + } + spin_lock_bh(&li->lock); + list_add_tail(&inti->list, &li->list); + atomic_set(&li->active, 1); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + if (waitqueue_active(&li->wq)) + wake_up_interruptible(&li->wq); + spin_unlock_bh(&li->lock); + rc = 0; /* order accepted */ + VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr); unlock: spin_unlock(&fi->lock); - VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); return rc; } @@ -267,6 +306,10 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) rc = __sigp_sense(vcpu, cpu_addr, &vcpu->arch.guest_gprs[r1]); break; + case SIGP_EXTERNAL_CALL: + vcpu->stat.instruction_sigp_external_call++; + rc = __sigp_external_call(vcpu, cpu_addr); + break; case SIGP_EMERGENCY: vcpu->stat.instruction_sigp_emergency++; rc = __sigp_emergency(vcpu, cpu_addr); diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index a65229d91c92..db92f044024c 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -32,7 +32,8 @@ static void __udelay_disabled(unsigned long long usecs) u64 clock_saved; u64 end; - mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT; + mask = psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_WAIT | + PSW_MASK_EXT | PSW_MASK_MCHECK; end = get_clock() + (usecs << 12); clock_saved = local_tick_disable(); __ctl_store(cr0_saved, 0, 0); diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index 74833831417f..342ae35a5ba9 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -342,7 +342,8 @@ int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old) if (segment_eq(get_fs(), KERNEL_DS)) return __futex_atomic_op_pt(op, uaddr, oparg, old); spin_lock(¤t->mm->page_table_lock); - uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr); + uaddr = (u32 __force __user *) + __dat_user_addr((__force unsigned long) uaddr); if (!uaddr) { spin_unlock(¤t->mm->page_table_lock); return -EFAULT; @@ -378,7 +379,8 @@ int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr, if (segment_eq(get_fs(), KERNEL_DS)) return __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval); spin_lock(¤t->mm->page_table_lock); - uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr); + uaddr = (u32 __force __user *) + __dat_user_addr((__force unsigned long) uaddr); if (!uaddr) { spin_unlock(¤t->mm->page_table_lock); return -EFAULT; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 9564fc779b27..1766def5bc3f 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -307,7 +307,7 @@ static inline int do_exception(struct pt_regs *regs, int access, #ifdef CONFIG_PGSTE if (test_tsk_thread_flag(current, TIF_SIE) && S390_lowcore.gmap) { - address = gmap_fault(address, + address = __gmap_fault(address, (struct gmap *) S390_lowcore.gmap); if (address == -EFAULT) { fault = VM_FAULT_BADMAP; @@ -393,7 +393,7 @@ void __kprobes do_protection_exception(struct pt_regs *regs, long pgm_int_code, int fault; /* Protection exception is suppressing, decrement psw address. */ - regs->psw.addr -= (pgm_int_code >> 16); + regs->psw.addr = __rewind_psw(regs->psw, pgm_int_code >> 16); /* * Check for low-address protection. This needs to be treated * as a special case because the translation exception code @@ -454,7 +454,7 @@ int __handle_fault(unsigned long uaddr, unsigned long pgm_int_code, int write) struct pt_regs regs; int access, fault; - regs.psw.mask = psw_kernel_bits; + regs.psw.mask = psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK; if (!irqs_disabled()) regs.psw.mask |= PSW_MASK_IO | PSW_MASK_EXT; regs.psw.addr = (unsigned long) __builtin_return_address(0); diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 5dbbaa6e594c..1cb8427bedfb 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/errno.h> +#include <linux/gfp.h> #include <asm/system.h> /* @@ -60,6 +61,9 @@ long probe_kernel_write(void *dst, const void *src, size_t size) return copied < 0 ? -EFAULT : 0; } +/* + * Copy memory in real mode (kernel to kernel) + */ int memcpy_real(void *dest, void *src, size_t count) { register unsigned long _dest asm("2") = (unsigned long) dest; @@ -101,3 +105,55 @@ void copy_to_absolute_zero(void *dest, void *src, size_t count) __ctl_load(cr0, 0, 0); preempt_enable(); } + +/* + * Copy memory from kernel (real) to user (virtual) + */ +int copy_to_user_real(void __user *dest, void *src, size_t count) +{ + int offs = 0, size, rc; + char *buf; + + buf = (char *) __get_free_page(GFP_KERNEL); + if (!buf) + return -ENOMEM; + rc = -EFAULT; + while (offs < count) { + size = min(PAGE_SIZE, count - offs); + if (memcpy_real(buf, src + offs, size)) + goto out; + if (copy_to_user(dest + offs, buf, size)) + goto out; + offs += size; + } + rc = 0; +out: + free_page((unsigned long) buf); + return rc; +} + +/* + * Copy memory from user (virtual) to kernel (real) + */ +int copy_from_user_real(void *dest, void __user *src, size_t count) +{ + int offs = 0, size, rc; + char *buf; + + buf = (char *) __get_free_page(GFP_KERNEL); + if (!buf) + return -ENOMEM; + rc = -EFAULT; + while (offs < count) { + size = min(PAGE_SIZE, count - offs); + if (copy_from_user(buf, src + offs, size)) + goto out; + if (memcpy_real(dest + offs, buf, size)) + goto out; + offs += size; + } + rc = 0; +out: + free_page((unsigned long) buf); + return rc; +} diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index c9a9f7f18188..f09c74881b7e 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -26,6 +26,7 @@ #include <linux/personality.h> #include <linux/mm.h> +#include <linux/mman.h> #include <linux/module.h> #include <linux/random.h> #include <asm/pgalloc.h> diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index d013ed39743b..b36537a5f43e 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -5,6 +5,7 @@ #include <linux/module.h> #include <linux/mm.h> #include <linux/hugetlb.h> +#include <asm/cacheflush.h> #include <asm/pgtable.h> static void change_page_attr(unsigned long addr, int numpages, diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 5d56c2b95b14..301c84d3b542 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -1,5 +1,5 @@ /* - * Copyright IBM Corp. 2007,2009 + * Copyright IBM Corp. 2007,2011 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ @@ -222,6 +222,7 @@ void gmap_free(struct gmap *gmap) /* Free all segment & region tables. */ down_read(&gmap->mm->mmap_sem); + spin_lock(&gmap->mm->page_table_lock); list_for_each_entry_safe(page, next, &gmap->crst_list, lru) { table = (unsigned long *) page_to_phys(page); if ((*table & _REGION_ENTRY_TYPE_MASK) == 0) @@ -230,6 +231,7 @@ void gmap_free(struct gmap *gmap) gmap_unlink_segment(gmap, table); __free_pages(page, ALLOC_ORDER); } + spin_unlock(&gmap->mm->page_table_lock); up_read(&gmap->mm->mmap_sem); list_del(&gmap->list); kfree(gmap); @@ -256,6 +258,9 @@ void gmap_disable(struct gmap *gmap) } EXPORT_SYMBOL_GPL(gmap_disable); +/* + * gmap_alloc_table is assumed to be called with mmap_sem held + */ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, unsigned long init) { @@ -267,14 +272,12 @@ static int gmap_alloc_table(struct gmap *gmap, return -ENOMEM; new = (unsigned long *) page_to_phys(page); crst_table_init(new, init); - down_read(&gmap->mm->mmap_sem); if (*table & _REGION_ENTRY_INV) { list_add(&page->lru, &gmap->crst_list); *table = (unsigned long) new | _REGION_ENTRY_LENGTH | (*table & _REGION_ENTRY_TYPE_MASK); } else __free_pages(page, ALLOC_ORDER); - up_read(&gmap->mm->mmap_sem); return 0; } @@ -299,6 +302,7 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len) flush = 0; down_read(&gmap->mm->mmap_sem); + spin_lock(&gmap->mm->page_table_lock); for (off = 0; off < len; off += PMD_SIZE) { /* Walk the guest addr space page table */ table = gmap->table + (((to + off) >> 53) & 0x7ff); @@ -320,6 +324,7 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len) *table = _SEGMENT_ENTRY_INV; } out: + spin_unlock(&gmap->mm->page_table_lock); up_read(&gmap->mm->mmap_sem); if (flush) gmap_flush_tlb(gmap); @@ -350,6 +355,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from, flush = 0; down_read(&gmap->mm->mmap_sem); + spin_lock(&gmap->mm->page_table_lock); for (off = 0; off < len; off += PMD_SIZE) { /* Walk the gmap address space page table */ table = gmap->table + (((to + off) >> 53) & 0x7ff); @@ -373,19 +379,24 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from, flush |= gmap_unlink_segment(gmap, table); *table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | (from + off); } + spin_unlock(&gmap->mm->page_table_lock); up_read(&gmap->mm->mmap_sem); if (flush) gmap_flush_tlb(gmap); return 0; out_unmap: + spin_unlock(&gmap->mm->page_table_lock); up_read(&gmap->mm->mmap_sem); gmap_unmap_segment(gmap, to, len); return -ENOMEM; } EXPORT_SYMBOL_GPL(gmap_map_segment); -unsigned long gmap_fault(unsigned long address, struct gmap *gmap) +/* + * this function is assumed to be called with mmap_sem held + */ +unsigned long __gmap_fault(unsigned long address, struct gmap *gmap) { unsigned long *table, vmaddr, segment; struct mm_struct *mm; @@ -445,16 +456,75 @@ unsigned long gmap_fault(unsigned long address, struct gmap *gmap) page = pmd_page(*pmd); mp = (struct gmap_pgtable *) page->index; rmap->entry = table; + spin_lock(&mm->page_table_lock); list_add(&rmap->list, &mp->mapper); + spin_unlock(&mm->page_table_lock); /* Set gmap segment table entry to page table. */ *table = pmd_val(*pmd) & PAGE_MASK; return vmaddr | (address & ~PMD_MASK); } return -EFAULT; +} +unsigned long gmap_fault(unsigned long address, struct gmap *gmap) +{ + unsigned long rc; + + down_read(&gmap->mm->mmap_sem); + rc = __gmap_fault(address, gmap); + up_read(&gmap->mm->mmap_sem); + + return rc; } EXPORT_SYMBOL_GPL(gmap_fault); +void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap) +{ + + unsigned long *table, address, size; + struct vm_area_struct *vma; + struct gmap_pgtable *mp; + struct page *page; + + down_read(&gmap->mm->mmap_sem); + address = from; + while (address < to) { + /* Walk the gmap address space page table */ + table = gmap->table + ((address >> 53) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) { + address = (address + PMD_SIZE) & PMD_MASK; + continue; + } + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + ((address >> 42) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) { + address = (address + PMD_SIZE) & PMD_MASK; + continue; + } + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + ((address >> 31) & 0x7ff); + if (unlikely(*table & _REGION_ENTRY_INV)) { + address = (address + PMD_SIZE) & PMD_MASK; + continue; + } + table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); + table = table + ((address >> 20) & 0x7ff); + if (unlikely(*table & _SEGMENT_ENTRY_INV)) { + address = (address + PMD_SIZE) & PMD_MASK; + continue; + } + page = pfn_to_page(*table >> PAGE_SHIFT); + mp = (struct gmap_pgtable *) page->index; + vma = find_vma(gmap->mm, mp->vmaddr); + size = min(to - address, PMD_SIZE - (address & ~PMD_MASK)); + zap_page_range(vma, mp->vmaddr | (address & ~PMD_MASK), + size, NULL); + address = (address + PMD_SIZE) & PMD_MASK; + } + up_read(&gmap->mm->mmap_sem); +} +EXPORT_SYMBOL_GPL(gmap_discard); + void gmap_unmap_notifier(struct mm_struct *mm, unsigned long *table) { struct gmap_rmap *rmap, *next; @@ -662,8 +732,9 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table) void __tlb_remove_table(void *_table) { - void *table = (void *)((unsigned long) _table & PAGE_MASK); - unsigned type = (unsigned long) _table & ~PAGE_MASK; + const unsigned long mask = (FRAG_MASK << 4) | FRAG_MASK; + void *table = (void *)((unsigned long) _table & ~mask); + unsigned type = (unsigned long) _table & mask; if (type) __page_table_free_rcu(table, type); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 781ff5169560..4799383e2df9 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -335,6 +335,9 @@ void __init vmem_map_init(void) ro_start = ((unsigned long)&_stext) & PAGE_MASK; ro_end = PFN_ALIGN((unsigned long)&_eshared); for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) { + if (memory_chunk[i].type == CHUNK_CRASHK || + memory_chunk[i].type == CHUNK_OLDMEM) + continue; start = memory_chunk[i].addr; end = memory_chunk[i].addr + memory_chunk[i].size; if (start >= ro_end || end <= ro_start) @@ -368,6 +371,9 @@ static int __init vmem_convert_memory_chunk(void) for (i = 0; i < MEMORY_CHUNKS; i++) { if (!memory_chunk[i].size) continue; + if (memory_chunk[i].type == CHUNK_CRASHK || + memory_chunk[i].type == CHUNK_OLDMEM) + continue; seg = kzalloc(sizeof(*seg), GFP_KERNEL); if (!seg) panic("Out of memory...\n"); diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c index 4552ce40c81a..f43c0e4282af 100644 --- a/arch/s390/oprofile/hwsampler.c +++ b/arch/s390/oprofile/hwsampler.c @@ -994,7 +994,7 @@ allocate_error: * * Returns 0 on success, !0 on failure. */ -int hwsampler_deallocate() +int hwsampler_deallocate(void) { int rc; @@ -1035,7 +1035,7 @@ unsigned long hwsampler_get_sample_overflow_count(unsigned int cpu) return cb->sample_overflow; } -int hwsampler_setup() +int hwsampler_setup(void) { int rc; int cpu; @@ -1102,7 +1102,7 @@ setup_exit: return rc; } -int hwsampler_shutdown() +int hwsampler_shutdown(void) { int rc; @@ -1203,7 +1203,7 @@ start_all_exit: * * Returns 0 on success, !0 on failure. */ -int hwsampler_stop_all() +int hwsampler_stop_all(void) { int tmp_rc, rc, cpu; struct hws_cpu_buffer *cb; diff --git a/arch/sh/include/asm/sh_eth.h b/arch/sh/include/asm/sh_eth.h deleted file mode 100644 index 0f325da0f923..000000000000 --- a/arch/sh/include/asm/sh_eth.h +++ /dev/null @@ -1,25 +0,0 @@ -#ifndef __ASM_SH_ETH_H__ -#define __ASM_SH_ETH_H__ - -#include <linux/phy.h> - -enum {EDMAC_LITTLE_ENDIAN, EDMAC_BIG_ENDIAN}; -enum { - SH_ETH_REG_GIGABIT, - SH_ETH_REG_FAST_SH4, - SH_ETH_REG_FAST_SH3_SH2 -}; - -struct sh_eth_plat_data { - int phy; - int edmac_endian; - int register_type; - phy_interface_t phy_interface; - void (*set_mdio_gate)(unsigned long addr); - - unsigned char mac_addr[6]; - unsigned no_ether_link:1; - unsigned ether_link_active_low:1; -}; - -#endif diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index 6f57325bb883..b8be20d42a0a 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -134,7 +134,8 @@ struct compat_statfs { compat_fsid_t f_fsid; int f_namelen; /* SunOS ignores this field. */ int f_frsize; - int f_spare[5]; + int f_flags; + int f_spare[4]; }; #define COMPAT_RLIM_INFINITY 0x7fffffff diff --git a/arch/sparc/include/asm/pgtsrmmu.h b/arch/sparc/include/asm/pgtsrmmu.h index 1407c07bdade..f6ae2b2b6870 100644 --- a/arch/sparc/include/asm/pgtsrmmu.h +++ b/arch/sparc/include/asm/pgtsrmmu.h @@ -280,7 +280,7 @@ static inline unsigned long srmmu_hwprobe(unsigned long vaddr) return retval; } #else -#define srmmu_hwprobe(addr) (srmmu_swprobe(addr, 0) & SRMMU_PTE_PMASK) +#define srmmu_hwprobe(addr) srmmu_swprobe(addr, 0) #endif static inline int diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 1e94f946570e..8aa0d4408586 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -230,7 +230,8 @@ static void pci_parse_of_addrs(struct platform_device *op, res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2]; } else if (i == dev->rom_base_reg) { res = &dev->resource[PCI_ROM_RESOURCE]; - flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE; + flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE + | IORESOURCE_SIZEALIGN; } else { printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i); continue; diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index 1ba95aff5d59..2caa556db86d 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -273,10 +273,7 @@ void do_sigreturn32(struct pt_regs *regs) case 1: set.sig[0] = seta[0] + (((long)seta[1]) << 32); } sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: @@ -377,10 +374,7 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) case 1: set.sig[0] = seta.sig[0] + (((long)seta.sig[1]) << 32); } sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: force_sig(SIGSEGV, current); @@ -782,6 +776,7 @@ static inline int handle_signal32(unsigned long signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + sigset_t blocked; int err; if (ka->sa.sa_flags & SA_SIGINFO) @@ -792,12 +787,10 @@ static inline int handle_signal32(unsigned long signr, struct k_sigaction *ka, if (err) return err; - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NOMASK)) - sigaddset(¤t->blocked,signr); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + sigaddset(&blocked, signr); + set_current_blocked(&blocked); tracehook_signal_handler(signr, info, ka, regs, 0); @@ -881,7 +874,7 @@ void do_signal32(sigset_t *oldset, struct pt_regs * regs, */ if (current_thread_info()->status & TS_RESTORE_SIGMASK) { current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + set_current_blocked(¤t->saved_sigmask); } } diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 04ede8f04add..8ce247ac04cc 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -62,12 +62,13 @@ struct rt_signal_frame { static int _sigpause_common(old_sigset_t set) { - set &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); + sigset_t blocked; + current->saved_sigmask = current->blocked; - siginitset(¤t->blocked, set); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + + set &= _BLOCKABLE; + siginitset(&blocked, set); + set_current_blocked(&blocked); current->state = TASK_INTERRUPTIBLE; schedule(); @@ -139,10 +140,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) goto segv_and_exit; sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv_and_exit: @@ -209,10 +207,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) } sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: force_sig(SIGSEGV, current); @@ -470,6 +465,7 @@ static inline int handle_signal(unsigned long signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + sigset_t blocked; int err; if (ka->sa.sa_flags & SA_SIGINFO) @@ -480,12 +476,10 @@ handle_signal(unsigned long signr, struct k_sigaction *ka, if (err) return err; - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NOMASK)) - sigaddset(¤t->blocked, signr); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + sigaddset(&blocked, signr); + set_current_blocked(&blocked); tracehook_signal_handler(signr, info, ka, regs, 0); @@ -581,7 +575,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) */ if (test_thread_flag(TIF_RESTORE_SIGMASK)) { clear_thread_flag(TIF_RESTORE_SIGMASK); - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + set_current_blocked(¤t->saved_sigmask); } } diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 47509df3b893..a2b81598d905 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -70,10 +70,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs) goto do_sigsegv; } sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); } if (test_thread_flag(TIF_32BIT)) { pc &= 0xffffffff; @@ -242,12 +239,13 @@ struct rt_signal_frame { static long _sigpause_common(old_sigset_t set) { - set &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); + sigset_t blocked; + current->saved_sigmask = current->blocked; - siginitset(¤t->blocked, set); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + + set &= _BLOCKABLE; + siginitset(&blocked, set); + set_current_blocked(&blocked); current->state = TASK_INTERRUPTIBLE; schedule(); @@ -327,10 +325,7 @@ void do_rt_sigreturn(struct pt_regs *regs) pt_regs_clear_syscall(regs); sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: force_sig(SIGSEGV, current); @@ -484,18 +479,17 @@ static inline int handle_signal(unsigned long signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + sigset_t blocked; int err; err = setup_rt_frame(ka, regs, signr, oldset, (ka->sa.sa_flags & SA_SIGINFO) ? info : NULL); if (err) return err; - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NOMASK)) - sigaddset(¤t->blocked,signr); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + sigaddset(&blocked, signr); + set_current_blocked(&blocked); tracehook_signal_handler(signr, info, ka, regs, 0); @@ -601,7 +595,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) */ if (current_thread_info()->status & TS_RESTORE_SIGMASK) { current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + set_current_blocked(¤t->saved_sigmask); } } diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c index 32b626c9d815..73370674ccff 100644 --- a/arch/sparc/kernel/visemul.c +++ b/arch/sparc/kernel/visemul.c @@ -713,17 +713,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a > b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPGT32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a > b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; @@ -733,17 +733,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a <= b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPLE32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a <= b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; @@ -753,17 +753,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a != b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPNE32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a != b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; @@ -773,17 +773,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a == b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPEQ32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a == b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; } diff --git a/arch/sparc/lib/memcpy.S b/arch/sparc/lib/memcpy.S index 34fe65751737..4d8c497517bd 100644 --- a/arch/sparc/lib/memcpy.S +++ b/arch/sparc/lib/memcpy.S @@ -7,40 +7,12 @@ * Copyright (C) 1996 Jakub Jelinek (jj@sunsite.mff.cuni.cz) */ -#ifdef __KERNEL__ - -#define FUNC(x) \ +#define FUNC(x) \ .globl x; \ .type x,@function; \ - .align 4; \ + .align 4; \ x: -#undef FASTER_REVERSE -#undef FASTER_NONALIGNED -#define FASTER_ALIGNED - -/* In kernel these functions don't return a value. - * One should use macros in asm/string.h for that purpose. - * We return 0, so that bugs are more apparent. - */ -#define SETUP_RETL -#define RETL_INSN clr %o0 - -#else - -/* libc */ - -#include "DEFS.h" - -#define FASTER_REVERSE -#define FASTER_NONALIGNED -#define FASTER_ALIGNED - -#define SETUP_RETL mov %o0, %g6 -#define RETL_INSN mov %g6, %o0 - -#endif - /* Both these macros have to start with exactly the same insn */ #define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \ ldd [%src + (offset) + 0x00], %t0; \ @@ -164,30 +136,6 @@ x: .text .align 4 -#ifdef FASTER_REVERSE - -70: /* rdword_align */ - - andcc %o1, 1, %g0 - be 4f - andcc %o1, 2, %g0 - - ldub [%o1 - 1], %g2 - sub %o1, 1, %o1 - stb %g2, [%o0 - 1] - sub %o2, 1, %o2 - be 3f - sub %o0, 1, %o0 -4: - lduh [%o1 - 2], %g2 - sub %o1, 2, %o1 - sth %g2, [%o0 - 2] - sub %o2, 2, %o2 - b 3f - sub %o0, 2, %o0 - -#endif /* FASTER_REVERSE */ - 0: retl nop ! Only bcopy returns here and it retuns void... @@ -198,7 +146,7 @@ FUNC(__memmove) #endif FUNC(memmove) cmp %o0, %o1 - SETUP_RETL + mov %o0, %g7 bleu 9f sub %o0, %o1, %o4 @@ -207,8 +155,6 @@ FUNC(memmove) bleu 0f andcc %o4, 3, %o5 -#ifndef FASTER_REVERSE - add %o1, %o2, %o1 add %o0, %o2, %o0 sub %o1, 1, %o1 @@ -224,295 +170,7 @@ FUNC(memmove) sub %o0, 1, %o0 retl - RETL_INSN - -#else /* FASTER_REVERSE */ - - add %o1, %o2, %o1 - add %o0, %o2, %o0 - bne 77f - cmp %o2, 15 - bleu 91f - andcc %o1, 3, %g0 - bne 70b -3: - andcc %o1, 4, %g0 - - be 2f - mov %o2, %g1 - - ld [%o1 - 4], %o4 - sub %g1, 4, %g1 - st %o4, [%o0 - 4] - sub %o1, 4, %o1 - sub %o0, 4, %o0 -2: - andcc %g1, 0xffffff80, %g7 - be 3f - andcc %o0, 4, %g0 - - be 74f + 4 -5: - RMOVE_BIGCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 - sub %o1, 128, %o1 - bne 5b - sub %o0, 128, %o0 -3: - andcc %g1, 0x70, %g7 - be 72f - andcc %g1, 8, %g0 - - sethi %hi(72f), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - sub %o1, %g7, %o1 - sub %o5, %o4, %o5 - jmpl %o5 + %lo(72f), %g0 - sub %o0, %g7, %o0 - -71: /* rmemcpy_table */ - RMOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x30, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x20, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g4, g5) - -72: /* rmemcpy_table_end */ - - be 73f - andcc %g1, 4, %g0 - - ldd [%o1 - 0x08], %g2 - sub %o0, 8, %o0 - sub %o1, 8, %o1 - st %g2, [%o0] - st %g3, [%o0 + 0x04] - -73: /* rmemcpy_last7 */ - - be 1f - andcc %g1, 2, %g0 - - ld [%o1 - 4], %g2 - sub %o1, 4, %o1 - st %g2, [%o0 - 4] - sub %o0, 4, %o0 -1: - be 1f - andcc %g1, 1, %g0 - - lduh [%o1 - 2], %g2 - sub %o1, 2, %o1 - sth %g2, [%o0 - 2] - sub %o0, 2, %o0 -1: - be 1f - nop - - ldub [%o1 - 1], %g2 - stb %g2, [%o0 - 1] -1: - retl - RETL_INSN - -74: /* rldd_std */ - RMOVE_BIGALIGNCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 - sub %o1, 128, %o1 - bne 74b - sub %o0, 128, %o0 - - andcc %g1, 0x70, %g7 - be 72b - andcc %g1, 8, %g0 - - sethi %hi(72b), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - sub %o1, %g7, %o1 - sub %o5, %o4, %o5 - jmpl %o5 + %lo(72b), %g0 - sub %o0, %g7, %o0 - -75: /* rshort_end */ - - and %o2, 0xe, %o3 -2: - sethi %hi(76f), %o5 - sll %o3, 3, %o4 - sub %o0, %o3, %o0 - sub %o5, %o4, %o5 - sub %o1, %o3, %o1 - jmpl %o5 + %lo(76f), %g0 - andcc %o2, 1, %g0 - - RMOVE_SHORTCHUNK(o1, o0, 0x0c, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x0a, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x08, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x06, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x04, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x02, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x00, g2, g3) - -76: /* rshort_table_end */ - - be 1f - nop - ldub [%o1 - 1], %g2 - stb %g2, [%o0 - 1] -1: - retl - RETL_INSN - -91: /* rshort_aligned_end */ - - bne 75b - andcc %o2, 8, %g0 - - be 1f - andcc %o2, 4, %g0 - - ld [%o1 - 0x08], %g2 - ld [%o1 - 0x04], %g3 - sub %o1, 8, %o1 - st %g2, [%o0 - 0x08] - st %g3, [%o0 - 0x04] - sub %o0, 8, %o0 -1: - b 73b - mov %o2, %g1 - -77: /* rnon_aligned */ - cmp %o2, 15 - bleu 75b - andcc %o0, 3, %g0 - be 64f - andcc %o0, 1, %g0 - be 63f - andcc %o0, 2, %g0 - ldub [%o1 - 1], %g5 - sub %o1, 1, %o1 - stb %g5, [%o0 - 1] - sub %o0, 1, %o0 - be 64f - sub %o2, 1, %o2 -63: - ldub [%o1 - 1], %g5 - sub %o1, 2, %o1 - stb %g5, [%o0 - 1] - sub %o0, 2, %o0 - ldub [%o1], %g5 - sub %o2, 2, %o2 - stb %g5, [%o0] -64: - and %o1, 3, %g2 - and %o1, -4, %o1 - and %o2, 0xc, %g3 - add %o1, 4, %o1 - cmp %g3, 4 - sll %g2, 3, %g4 - mov 32, %g2 - be 4f - sub %g2, %g4, %g7 - - blu 3f - cmp %g3, 8 - - be 2f - srl %o2, 2, %g3 - - ld [%o1 - 4], %o3 - add %o0, -8, %o0 - ld [%o1 - 8], %o4 - add %o1, -16, %o1 - b 7f - add %g3, 1, %g3 -2: - ld [%o1 - 4], %o4 - add %o0, -4, %o0 - ld [%o1 - 8], %g1 - add %o1, -12, %o1 - b 8f - add %g3, 2, %g3 -3: - ld [%o1 - 4], %o5 - add %o0, -12, %o0 - ld [%o1 - 8], %o3 - add %o1, -20, %o1 - b 6f - srl %o2, 2, %g3 -4: - ld [%o1 - 4], %g1 - srl %o2, 2, %g3 - ld [%o1 - 8], %o5 - add %o1, -24, %o1 - add %o0, -16, %o0 - add %g3, -1, %g3 - - ld [%o1 + 12], %o3 -5: - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 - or %g2, %g5, %g2 - st %g2, [%o0 + 12] -6: - ld [%o1 + 8], %o4 - sll %o3, %g4, %g2 - srl %o5, %g7, %g5 - or %g2, %g5, %g2 - st %g2, [%o0 + 8] -7: - ld [%o1 + 4], %g1 - sll %o4, %g4, %g2 - srl %o3, %g7, %g5 - or %g2, %g5, %g2 - st %g2, [%o0 + 4] -8: - ld [%o1], %o5 - sll %g1, %g4, %g2 - srl %o4, %g7, %g5 - addcc %g3, -4, %g3 - or %g2, %g5, %g2 - add %o1, -16, %o1 - st %g2, [%o0] - add %o0, -16, %o0 - bne,a 5b - ld [%o1 + 12], %o3 - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 - srl %g4, 3, %g3 - or %g2, %g5, %g2 - add %o1, %g3, %o1 - andcc %o2, 2, %g0 - st %g2, [%o0 + 12] - be 1f - andcc %o2, 1, %g0 - - ldub [%o1 + 15], %g5 - add %o1, -2, %o1 - stb %g5, [%o0 + 11] - add %o0, -2, %o0 - ldub [%o1 + 16], %g5 - stb %g5, [%o0 + 12] -1: - be 1f - nop - ldub [%o1 + 15], %g5 - stb %g5, [%o0 + 11] -1: - retl - RETL_INSN - -#endif /* FASTER_REVERSE */ + mov %g7, %o0 /* NOTE: This code is executed just for the cases, where %src (=%o1) & 3 is != 0. @@ -546,7 +204,7 @@ FUNC(memmove) FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ sub %o0, %o1, %o4 - SETUP_RETL + mov %o0, %g7 9: andcc %o4, 3, %o5 0: @@ -569,7 +227,7 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ add %o1, 4, %o1 add %o0, 4, %o0 2: - andcc %g1, 0xffffff80, %g7 + andcc %g1, 0xffffff80, %g0 be 3f andcc %o0, 4, %g0 @@ -579,22 +237,23 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ MOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 + sub %g1, 128, %g1 add %o1, 128, %o1 - bne 5b + cmp %g1, 128 + bge 5b add %o0, 128, %o0 3: - andcc %g1, 0x70, %g7 + andcc %g1, 0x70, %g4 be 80f andcc %g1, 8, %g0 sethi %hi(80f), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - add %o1, %g7, %o1 + srl %g4, 1, %o4 + add %g4, %o4, %o4 + add %o1, %g4, %o1 sub %o5, %o4, %o5 jmpl %o5 + %lo(80f), %g0 - add %o0, %g7, %o0 + add %o0, %g4, %o0 79: /* memcpy_table */ @@ -641,43 +300,28 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ stb %g2, [%o0] 1: retl - RETL_INSN + mov %g7, %o0 82: /* ldd_std */ MOVE_BIGALIGNCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 + subcc %g1, 128, %g1 add %o1, 128, %o1 - bne 82b + cmp %g1, 128 + bge 82b add %o0, 128, %o0 -#ifndef FASTER_ALIGNED - - andcc %g1, 0x70, %g7 - be 80b - andcc %g1, 8, %g0 - - sethi %hi(80b), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - add %o1, %g7, %o1 - sub %o5, %o4, %o5 - jmpl %o5 + %lo(80b), %g0 - add %o0, %g7, %o0 - -#else /* FASTER_ALIGNED */ - - andcc %g1, 0x70, %g7 + andcc %g1, 0x70, %g4 be 84f andcc %g1, 8, %g0 sethi %hi(84f), %o5 - add %o1, %g7, %o1 - sub %o5, %g7, %o5 + add %o1, %g4, %o1 + sub %o5, %g4, %o5 jmpl %o5 + %lo(84f), %g0 - add %o0, %g7, %o0 + add %o0, %g4, %o0 83: /* amemcpy_table */ @@ -721,382 +365,132 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ stb %g2, [%o0] 1: retl - RETL_INSN - -#endif /* FASTER_ALIGNED */ + mov %g7, %o0 86: /* non_aligned */ cmp %o2, 6 bleu 88f + nop -#ifdef FASTER_NONALIGNED - - cmp %o2, 256 - bcc 87f - -#endif /* FASTER_NONALIGNED */ - - andcc %o0, 3, %g0 + save %sp, -96, %sp + andcc %i0, 3, %g0 be 61f - andcc %o0, 1, %g0 + andcc %i0, 1, %g0 be 60f - andcc %o0, 2, %g0 + andcc %i0, 2, %g0 - ldub [%o1], %g5 - add %o1, 1, %o1 - stb %g5, [%o0] - sub %o2, 1, %o2 + ldub [%i1], %g5 + add %i1, 1, %i1 + stb %g5, [%i0] + sub %i2, 1, %i2 bne 61f - add %o0, 1, %o0 + add %i0, 1, %i0 60: - ldub [%o1], %g3 - add %o1, 2, %o1 - stb %g3, [%o0] - sub %o2, 2, %o2 - ldub [%o1 - 1], %g3 - add %o0, 2, %o0 - stb %g3, [%o0 - 1] + ldub [%i1], %g3 + add %i1, 2, %i1 + stb %g3, [%i0] + sub %i2, 2, %i2 + ldub [%i1 - 1], %g3 + add %i0, 2, %i0 + stb %g3, [%i0 - 1] 61: - and %o1, 3, %g2 - and %o2, 0xc, %g3 - and %o1, -4, %o1 + and %i1, 3, %g2 + and %i2, 0xc, %g3 + and %i1, -4, %i1 cmp %g3, 4 sll %g2, 3, %g4 mov 32, %g2 be 4f - sub %g2, %g4, %g7 + sub %g2, %g4, %l0 blu 3f cmp %g3, 0x8 be 2f - srl %o2, 2, %g3 + srl %i2, 2, %g3 - ld [%o1], %o3 - add %o0, -8, %o0 - ld [%o1 + 4], %o4 + ld [%i1], %i3 + add %i0, -8, %i0 + ld [%i1 + 4], %i4 b 8f add %g3, 1, %g3 2: - ld [%o1], %o4 - add %o0, -12, %o0 - ld [%o1 + 4], %o5 + ld [%i1], %i4 + add %i0, -12, %i0 + ld [%i1 + 4], %i5 add %g3, 2, %g3 b 9f - add %o1, -4, %o1 + add %i1, -4, %i1 3: - ld [%o1], %g1 - add %o0, -4, %o0 - ld [%o1 + 4], %o3 - srl %o2, 2, %g3 + ld [%i1], %g1 + add %i0, -4, %i0 + ld [%i1 + 4], %i3 + srl %i2, 2, %g3 b 7f - add %o1, 4, %o1 + add %i1, 4, %i1 4: - ld [%o1], %o5 - cmp %o2, 7 - ld [%o1 + 4], %g1 - srl %o2, 2, %g3 + ld [%i1], %i5 + cmp %i2, 7 + ld [%i1 + 4], %g1 + srl %i2, 2, %g3 bleu 10f - add %o1, 8, %o1 + add %i1, 8, %i1 - ld [%o1], %o3 + ld [%i1], %i3 add %g3, -1, %g3 5: - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 + sll %i5, %g4, %g2 + srl %g1, %l0, %g5 or %g2, %g5, %g2 - st %g2, [%o0] + st %g2, [%i0] 7: - ld [%o1 + 4], %o4 + ld [%i1 + 4], %i4 sll %g1, %g4, %g2 - srl %o3, %g7, %g5 + srl %i3, %l0, %g5 or %g2, %g5, %g2 - st %g2, [%o0 + 4] + st %g2, [%i0 + 4] 8: - ld [%o1 + 8], %o5 - sll %o3, %g4, %g2 - srl %o4, %g7, %g5 + ld [%i1 + 8], %i5 + sll %i3, %g4, %g2 + srl %i4, %l0, %g5 or %g2, %g5, %g2 - st %g2, [%o0 + 8] + st %g2, [%i0 + 8] 9: - ld [%o1 + 12], %g1 - sll %o4, %g4, %g2 - srl %o5, %g7, %g5 + ld [%i1 + 12], %g1 + sll %i4, %g4, %g2 + srl %i5, %l0, %g5 addcc %g3, -4, %g3 or %g2, %g5, %g2 - add %o1, 16, %o1 - st %g2, [%o0 + 12] - add %o0, 16, %o0 + add %i1, 16, %i1 + st %g2, [%i0 + 12] + add %i0, 16, %i0 bne,a 5b - ld [%o1], %o3 + ld [%i1], %i3 10: - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 - srl %g7, 3, %g3 + sll %i5, %g4, %g2 + srl %g1, %l0, %g5 + srl %l0, 3, %g3 or %g2, %g5, %g2 - sub %o1, %g3, %o1 - andcc %o2, 2, %g0 - st %g2, [%o0] + sub %i1, %g3, %i1 + andcc %i2, 2, %g0 + st %g2, [%i0] be 1f - andcc %o2, 1, %g0 - - ldub [%o1], %g2 - add %o1, 2, %o1 - stb %g2, [%o0 + 4] - add %o0, 2, %o0 - ldub [%o1 - 1], %g2 - stb %g2, [%o0 + 3] + andcc %i2, 1, %g0 + + ldub [%i1], %g2 + add %i1, 2, %i1 + stb %g2, [%i0 + 4] + add %i0, 2, %i0 + ldub [%i1 - 1], %g2 + stb %g2, [%i0 + 3] 1: be 1f nop - ldub [%o1], %g2 - stb %g2, [%o0 + 4] -1: - retl - RETL_INSN - -#ifdef FASTER_NONALIGNED - -87: /* faster_nonaligned */ - - andcc %o1, 3, %g0 - be 3f - andcc %o1, 1, %g0 - - be 4f - andcc %o1, 2, %g0 - - ldub [%o1], %g2 - add %o1, 1, %o1 - stb %g2, [%o0] - sub %o2, 1, %o2 - bne 3f - add %o0, 1, %o0 -4: - lduh [%o1], %g2 - add %o1, 2, %o1 - srl %g2, 8, %g3 - sub %o2, 2, %o2 - stb %g3, [%o0] - add %o0, 2, %o0 - stb %g2, [%o0 - 1] -3: - andcc %o1, 4, %g0 - - bne 2f - cmp %o5, 1 - - ld [%o1], %o4 - srl %o4, 24, %g2 - stb %g2, [%o0] - srl %o4, 16, %g3 - stb %g3, [%o0 + 1] - srl %o4, 8, %g2 - stb %g2, [%o0 + 2] - sub %o2, 4, %o2 - stb %o4, [%o0 + 3] - add %o1, 4, %o1 - add %o0, 4, %o0 -2: - be 33f - cmp %o5, 2 - be 32f - sub %o2, 4, %o2 -31: - ld [%o1], %g2 - add %o1, 4, %o1 - srl %g2, 24, %g3 - and %o0, 7, %g5 - stb %g3, [%o0] - cmp %g5, 7 - sll %g2, 8, %g1 - add %o0, 4, %o0 - be 41f - and %o2, 0xffffffc0, %o3 - ld [%o0 - 7], %o4 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 4b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 -1: - st %o4, [%o0 - 7] - sth %g2, [%o0 - 3] - srl %g1, 8, %g4 - b 88f - stb %g4, [%o0 - 1] -32: - ld [%o1], %g2 - add %o1, 4, %o1 - srl %g2, 16, %g3 - and %o0, 7, %g5 - sth %g3, [%o0] - cmp %g5, 6 - sll %g2, 16, %g1 - add %o0, 4, %o0 - be 42f - and %o2, 0xffffffc0, %o3 - ld [%o0 - 6], %o4 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 4b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 -1: - st %o4, [%o0 - 6] - b 88f - sth %g2, [%o0 - 2] -33: - ld [%o1], %g2 - sub %o2, 4, %o2 - srl %g2, 24, %g3 - and %o0, 7, %g5 - stb %g3, [%o0] - cmp %g5, 5 - srl %g2, 8, %g4 - sll %g2, 24, %g1 - sth %g4, [%o0 + 1] - add %o1, 4, %o1 - be 43f - and %o2, 0xffffffc0, %o3 - - ld [%o0 - 1], %o4 - add %o0, 4, %o0 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 4b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 24, %g2 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 24, %g2 -1: - st %o4, [%o0 - 5] - b 88f - stb %g2, [%o0 - 1] -41: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 41b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 + ldub [%i1], %g2 + stb %g2, [%i0 + 4] 1: - sth %g2, [%o0 - 3] - srl %g1, 8, %g4 - b 88f - stb %g4, [%o0 - 1] -43: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 43b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 24, %g2 -4: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 24, %g2 -1: - stb %g2, [%o0 + 3] - b 88f - add %o0, 4, %o0 -42: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 42b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 -1: - sth %g2, [%o0 - 2] - - /* Fall through */ - -#endif /* FASTER_NONALIGNED */ + ret + restore %g7, %g0, %o0 88: /* short_end */ @@ -1127,7 +521,7 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ stb %g2, [%o0] 1: retl - RETL_INSN + mov %g7, %o0 90: /* short_aligned_end */ bne 88b diff --git a/arch/sparc/mm/leon_mm.c b/arch/sparc/mm/leon_mm.c index e485a6804998..13c2169822a8 100644 --- a/arch/sparc/mm/leon_mm.c +++ b/arch/sparc/mm/leon_mm.c @@ -162,7 +162,7 @@ ready: printk(KERN_INFO "swprobe: padde %x\n", paddr_calc); if (paddr) *paddr = paddr_calc; - return paddrbase; + return pte; } void leon_flush_icache_all(void) diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index b30f71ac0d06..70a0de46cd1b 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -46,9 +46,6 @@ config NEED_PER_CPU_PAGE_FIRST_CHUNK config SYS_SUPPORTS_HUGETLBFS def_bool y -config GENERIC_TIME - def_bool y - config GENERIC_CLOCKEVENTS def_bool y diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig index 2ad73fb707b9..dafdbbae1124 100644 --- a/arch/tile/configs/tilegx_defconfig +++ b/arch/tile/configs/tilegx_defconfig @@ -11,7 +11,6 @@ CONFIG_HAVE_ARCH_ALLOC_REMAP=y CONFIG_HAVE_SETUP_PER_CPU_AREA=y CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y CONFIG_SYS_SUPPORTS_HUGETLBFS=y -CONFIG_GENERIC_TIME=y CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_RWSEM_GENERIC_SPINLOCK=y CONFIG_DEFAULT_MIGRATION_COST=10000000 diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig index f58dc362b944..6f05f969b564 100644 --- a/arch/tile/configs/tilepro_defconfig +++ b/arch/tile/configs/tilepro_defconfig @@ -11,7 +11,6 @@ CONFIG_HAVE_ARCH_ALLOC_REMAP=y CONFIG_HAVE_SETUP_PER_CPU_AREA=y CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y CONFIG_SYS_SUPPORTS_HUGETLBFS=y -CONFIG_GENERIC_TIME=y CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_RWSEM_GENERIC_SPINLOCK=y CONFIG_DEFAULT_MIGRATION_COST=10000000 diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S index fc94607f0bd5..aecc8ed5f39b 100644 --- a/arch/tile/kernel/intvec_32.S +++ b/arch/tile/kernel/intvec_32.S @@ -21,7 +21,7 @@ #include <asm/ptrace.h> #include <asm/thread_info.h> #include <asm/irqflags.h> -#include <linux/atomic.h> +#include <asm/atomic_32.h> #include <asm/asm-offsets.h> #include <hv/hypervisor.h> #include <arch/abi.h> diff --git a/arch/tile/lib/atomic_asm_32.S b/arch/tile/lib/atomic_asm_32.S index 1f75a2a56101..30638042691d 100644 --- a/arch/tile/lib/atomic_asm_32.S +++ b/arch/tile/lib/atomic_asm_32.S @@ -70,7 +70,7 @@ */ #include <linux/linkage.h> -#include <linux/atomic.h> +#include <asm/atomic_32.h> #include <asm/page.h> #include <asm/processor.h> diff --git a/arch/um/defconfig b/arch/um/defconfig index 9f7634f08cf3..761f5e1a657e 100644 --- a/arch/um/defconfig +++ b/arch/um/defconfig @@ -13,7 +13,6 @@ CONFIG_LOCKDEP_SUPPORT=y # CONFIG_STACKTRACE_SUPPORT is not set CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_GENERIC_BUG=y -CONFIG_GENERIC_TIME=y CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_IRQ_RELEASE_METHOD=y CONFIG_HZ=100 diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 22745b47c829..a492e59883a3 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -368,7 +368,7 @@ static const struct net_device_ops uml_netdev_ops = { .ndo_open = uml_net_open, .ndo_stop = uml_net_close, .ndo_start_xmit = uml_net_start_xmit, - .ndo_set_multicast_list = uml_net_set_multicast_list, + .ndo_set_rx_mode = uml_net_set_multicast_list, .ndo_tx_timeout = uml_net_tx_timeout, .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = uml_net_change_mtu, diff --git a/arch/unicore32/include/asm/io.h b/arch/unicore32/include/asm/io.h index 4bd87f3d13d4..1a5c5a5eb39c 100644 --- a/arch/unicore32/include/asm/io.h +++ b/arch/unicore32/include/asm/io.h @@ -32,7 +32,7 @@ extern void __uc32_iounmap(volatile void __iomem *addr); * ioremap and friends. * * ioremap takes a PCI memory address, as specified in - * Documentation/IO-mapping.txt. + * Documentation/io-mapping.txt. * */ #define ioremap(cookie, size) __uc32_ioremap(cookie, size) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6a47bb22657f..77f7a384c0b5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -64,10 +64,12 @@ config X86 select HAVE_TEXT_POKE_SMP select HAVE_GENERIC_HARDIRQS select HAVE_SPARSE_IRQ + select SPARSE_IRQ select GENERIC_FIND_FIRST_BIT select GENERIC_IRQ_PROBE select GENERIC_PENDING_IRQ if SMP select GENERIC_IRQ_SHOW + select GENERIC_CLOCKEVENTS_MIN_ADJUST select IRQ_FORCED_THREADING select USE_GENERIC_SMP_HELPERS if SMP select HAVE_BPF_JIT if (X86_64 && NET) @@ -130,7 +132,7 @@ config SBUS bool config NEED_DMA_MAP_STATE - def_bool (X86_64 || DMAR || DMA_API_DEBUG) + def_bool (X86_64 || INTEL_IOMMU || DMA_API_DEBUG) config NEED_SG_DMA_LENGTH def_bool y @@ -220,7 +222,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC config HAVE_INTEL_TXT def_bool y - depends on EXPERIMENTAL && DMAR && ACPI + depends on EXPERIMENTAL && INTEL_IOMMU && ACPI config X86_32_SMP def_bool y @@ -279,7 +281,7 @@ config SMP Y to "Enhanced Real Time Clock Support", below. The "Advanced Power Management" code will be disabled if you say Y here. - See also <file:Documentation/i386/IO-APIC.txt>, + See also <file:Documentation/x86/i386/IO-APIC.txt>, <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at <http://www.tldp.org/docs.html#howto>. @@ -287,7 +289,7 @@ config SMP config X86_X2APIC bool "Support x2apic" - depends on X86_LOCAL_APIC && X86_64 && INTR_REMAP + depends on X86_LOCAL_APIC && X86_64 && IRQ_REMAP ---help--- This enables x2apic support on CPUs that have this feature. @@ -1452,6 +1454,15 @@ config ARCH_USES_PG_UNCACHED def_bool y depends on X86_PAT +config ARCH_RANDOM + def_bool y + prompt "x86 architectural random number generator" if EXPERT + ---help--- + Enable the x86 architectural RDRAND instruction + (Intel Bull Mountain technology) to generate random numbers. + If supported, this is a high bandwidth, cryptographically + secure hardware random number generator. + config EFI bool "EFI runtime service support" depends on ACPI @@ -2064,6 +2075,20 @@ config OLPC_XO15_SCI - AC adapter status updates - Battery status updates +config ALIX + bool "PCEngines ALIX System Support (LED setup)" + select GPIOLIB + ---help--- + This option enables system support for the PCEngines ALIX. + At present this just sets up LEDs for GPIO control on + ALIX2/3/6 boards. However, other system specific setup should + get added here. + + Note: You must still enable the drivers for GPIO and LED support + (GPIO_CS5535 & LEDS_GPIO) to actually use the LEDs + + Note: You have to set alix.force=1 for boards with Award BIOS. + endif # X86_32 config AMD_NB diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index c0f8a5c88910..bf56e1793272 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -139,7 +139,7 @@ config IOMMU_DEBUG code. When you use it make sure you have a big enough IOMMU/AGP aperture. Most of the options enabled by this can be set more finegrained using the iommu= command line - options. See Documentation/x86_64/boot-options.txt for more + options. See Documentation/x86/x86_64/boot-options.txt for more details. config IOMMU_STRESS diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 93e689f4bd86..bdb4d458ec8c 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -129,7 +129,7 @@ start_sys_seg: .word SYSSEG # obsolete and meaningless, but just type_of_loader: .byte 0 # 0 means ancient bootloader, newer # bootloaders know to change this. - # See Documentation/i386/boot.txt for + # See Documentation/x86/boot.txt for # assigned ids # flags, unused bits must be zero (RFU) bit within loadflags diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 22a0dc8e51dd..058a35b8286c 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -67,8 +67,8 @@ CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_X86_ACPI_CPUFREQ=y CONFIG_PCI_MMCONFIG=y -CONFIG_DMAR=y -# CONFIG_DMAR_DEFAULT_ON is not set +CONFIG_INTEL_IOMMU=y +# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set CONFIG_PCIEPORTBUS=y CONFIG_PCCARD=y CONFIG_YENTA=y diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index c04f1b7a9139..3537d4b91f74 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -7,21 +7,33 @@ obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o +obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o +obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o +obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o aes-i586-y := aes-i586-asm_32.o aes_glue.o twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o +blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o +twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o + +# enable AVX support only when $(AS) can actually assemble the instructions +ifeq ($(call as-instr,vpxor %xmm0$(comma)%xmm1$(comma)%xmm2,yes,no),yes) +AFLAGS_sha1_ssse3_asm.o += -DSHA1_ENABLE_AVX_SUPPORT +CFLAGS_sha1_ssse3_glue.o += -DSHA1_ENABLE_AVX_SUPPORT +endif +sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c index 49ae9fe32b22..b0b6950cc8c8 100644 --- a/arch/x86/crypto/aes_glue.c +++ b/arch/x86/crypto/aes_glue.c @@ -4,6 +4,7 @@ */ #include <crypto/aes.h> +#include <asm/aes.h> asmlinkage void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in); asmlinkage void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in); diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S new file mode 100644 index 000000000000..391d245dc086 --- /dev/null +++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S @@ -0,0 +1,390 @@ +/* + * Blowfish Cipher Algorithm (x86_64) + * + * Copyright (C) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 + * USA + * + */ + +.file "blowfish-x86_64-asm.S" +.text + +/* structure of crypto context */ +#define p 0 +#define s0 ((16 + 2) * 4) +#define s1 ((16 + 2 + (1 * 256)) * 4) +#define s2 ((16 + 2 + (2 * 256)) * 4) +#define s3 ((16 + 2 + (3 * 256)) * 4) + +/* register macros */ +#define CTX %rdi +#define RIO %rsi + +#define RX0 %rax +#define RX1 %rbx +#define RX2 %rcx +#define RX3 %rdx + +#define RX0d %eax +#define RX1d %ebx +#define RX2d %ecx +#define RX3d %edx + +#define RX0bl %al +#define RX1bl %bl +#define RX2bl %cl +#define RX3bl %dl + +#define RX0bh %ah +#define RX1bh %bh +#define RX2bh %ch +#define RX3bh %dh + +#define RT0 %rbp +#define RT1 %rsi +#define RT2 %r8 +#define RT3 %r9 + +#define RT0d %ebp +#define RT1d %esi +#define RT2d %r8d +#define RT3d %r9d + +#define RKEY %r10 + +/*********************************************************************** + * 1-way blowfish + ***********************************************************************/ +#define F() \ + rorq $16, RX0; \ + movzbl RX0bh, RT0d; \ + movzbl RX0bl, RT1d; \ + rolq $16, RX0; \ + movl s0(CTX,RT0,4), RT0d; \ + addl s1(CTX,RT1,4), RT0d; \ + movzbl RX0bh, RT1d; \ + movzbl RX0bl, RT2d; \ + rolq $32, RX0; \ + xorl s2(CTX,RT1,4), RT0d; \ + addl s3(CTX,RT2,4), RT0d; \ + xorq RT0, RX0; + +#define add_roundkey_enc(n) \ + xorq p+4*(n)(CTX), RX0; + +#define round_enc(n) \ + add_roundkey_enc(n); \ + \ + F(); \ + F(); + +#define add_roundkey_dec(n) \ + movq p+4*(n-1)(CTX), RT0; \ + rorq $32, RT0; \ + xorq RT0, RX0; + +#define round_dec(n) \ + add_roundkey_dec(n); \ + \ + F(); \ + F(); \ + +#define read_block() \ + movq (RIO), RX0; \ + rorq $32, RX0; \ + bswapq RX0; + +#define write_block() \ + bswapq RX0; \ + movq RX0, (RIO); + +#define xor_block() \ + bswapq RX0; \ + xorq RX0, (RIO); + +.align 8 +.global __blowfish_enc_blk +.type __blowfish_enc_blk,@function; + +__blowfish_enc_blk: + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + * %rcx: bool, if true: xor output + */ + movq %rbp, %r11; + + movq %rsi, %r10; + movq %rdx, RIO; + + read_block(); + + round_enc(0); + round_enc(2); + round_enc(4); + round_enc(6); + round_enc(8); + round_enc(10); + round_enc(12); + round_enc(14); + add_roundkey_enc(16); + + movq %r11, %rbp; + + movq %r10, RIO; + test %cl, %cl; + jnz __enc_xor; + + write_block(); + ret; +__enc_xor: + xor_block(); + ret; + +.align 8 +.global blowfish_dec_blk +.type blowfish_dec_blk,@function; + +blowfish_dec_blk: + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + movq %rbp, %r11; + + movq %rsi, %r10; + movq %rdx, RIO; + + read_block(); + + round_dec(17); + round_dec(15); + round_dec(13); + round_dec(11); + round_dec(9); + round_dec(7); + round_dec(5); + round_dec(3); + add_roundkey_dec(1); + + movq %r10, RIO; + write_block(); + + movq %r11, %rbp; + + ret; + +/********************************************************************** + 4-way blowfish, four blocks parallel + **********************************************************************/ + +/* F() for 4-way. Slower when used alone/1-way, but faster when used + * parallel/4-way (tested on AMD Phenom II & Intel Xeon E7330). + */ +#define F4(x) \ + movzbl x ## bh, RT1d; \ + movzbl x ## bl, RT3d; \ + rorq $16, x; \ + movzbl x ## bh, RT0d; \ + movzbl x ## bl, RT2d; \ + rorq $16, x; \ + movl s0(CTX,RT0,4), RT0d; \ + addl s1(CTX,RT2,4), RT0d; \ + xorl s2(CTX,RT1,4), RT0d; \ + addl s3(CTX,RT3,4), RT0d; \ + xorq RT0, x; + +#define add_preloaded_roundkey4() \ + xorq RKEY, RX0; \ + xorq RKEY, RX1; \ + xorq RKEY, RX2; \ + xorq RKEY, RX3; + +#define preload_roundkey_enc(n) \ + movq p+4*(n)(CTX), RKEY; + +#define add_roundkey_enc4(n) \ + add_preloaded_roundkey4(); \ + preload_roundkey_enc(n + 2); + +#define round_enc4(n) \ + add_roundkey_enc4(n); \ + \ + F4(RX0); \ + F4(RX1); \ + F4(RX2); \ + F4(RX3); \ + \ + F4(RX0); \ + F4(RX1); \ + F4(RX2); \ + F4(RX3); + +#define preload_roundkey_dec(n) \ + movq p+4*((n)-1)(CTX), RKEY; \ + rorq $32, RKEY; + +#define add_roundkey_dec4(n) \ + add_preloaded_roundkey4(); \ + preload_roundkey_dec(n - 2); + +#define round_dec4(n) \ + add_roundkey_dec4(n); \ + \ + F4(RX0); \ + F4(RX1); \ + F4(RX2); \ + F4(RX3); \ + \ + F4(RX0); \ + F4(RX1); \ + F4(RX2); \ + F4(RX3); + +#define read_block4() \ + movq (RIO), RX0; \ + rorq $32, RX0; \ + bswapq RX0; \ + \ + movq 8(RIO), RX1; \ + rorq $32, RX1; \ + bswapq RX1; \ + \ + movq 16(RIO), RX2; \ + rorq $32, RX2; \ + bswapq RX2; \ + \ + movq 24(RIO), RX3; \ + rorq $32, RX3; \ + bswapq RX3; + +#define write_block4() \ + bswapq RX0; \ + movq RX0, (RIO); \ + \ + bswapq RX1; \ + movq RX1, 8(RIO); \ + \ + bswapq RX2; \ + movq RX2, 16(RIO); \ + \ + bswapq RX3; \ + movq RX3, 24(RIO); + +#define xor_block4() \ + bswapq RX0; \ + xorq RX0, (RIO); \ + \ + bswapq RX1; \ + xorq RX1, 8(RIO); \ + \ + bswapq RX2; \ + xorq RX2, 16(RIO); \ + \ + bswapq RX3; \ + xorq RX3, 24(RIO); + +.align 8 +.global __blowfish_enc_blk_4way +.type __blowfish_enc_blk_4way,@function; + +__blowfish_enc_blk_4way: + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + * %rcx: bool, if true: xor output + */ + pushq %rbp; + pushq %rbx; + pushq %rcx; + + preload_roundkey_enc(0); + + movq %rsi, %r11; + movq %rdx, RIO; + + read_block4(); + + round_enc4(0); + round_enc4(2); + round_enc4(4); + round_enc4(6); + round_enc4(8); + round_enc4(10); + round_enc4(12); + round_enc4(14); + add_preloaded_roundkey4(); + + popq %rbp; + movq %r11, RIO; + + test %bpl, %bpl; + jnz __enc_xor4; + + write_block4(); + + popq %rbx; + popq %rbp; + ret; + +__enc_xor4: + xor_block4(); + + popq %rbx; + popq %rbp; + ret; + +.align 8 +.global blowfish_dec_blk_4way +.type blowfish_dec_blk_4way,@function; + +blowfish_dec_blk_4way: + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src + */ + pushq %rbp; + pushq %rbx; + preload_roundkey_dec(17); + + movq %rsi, %r11; + movq %rdx, RIO; + + read_block4(); + + round_dec4(17); + round_dec4(15); + round_dec4(13); + round_dec4(11); + round_dec4(9); + round_dec4(7); + round_dec4(5); + round_dec4(3); + add_preloaded_roundkey4(); + + movq %r11, RIO; + write_block4(); + + popq %rbx; + popq %rbp; + + ret; + diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c new file mode 100644 index 000000000000..b05aa163d55a --- /dev/null +++ b/arch/x86/crypto/blowfish_glue.c @@ -0,0 +1,492 @@ +/* + * Glue Code for assembler optimized version of Blowfish + * + * Copyright (c) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> + * + * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by: + * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> + * CTR part based on code (crypto/ctr.c) by: + * (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 + * USA + * + */ + +#include <crypto/blowfish.h> +#include <linux/crypto.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/types.h> +#include <crypto/algapi.h> + +/* regular block cipher functions */ +asmlinkage void __blowfish_enc_blk(struct bf_ctx *ctx, u8 *dst, const u8 *src, + bool xor); +asmlinkage void blowfish_dec_blk(struct bf_ctx *ctx, u8 *dst, const u8 *src); + +/* 4-way parallel cipher functions */ +asmlinkage void __blowfish_enc_blk_4way(struct bf_ctx *ctx, u8 *dst, + const u8 *src, bool xor); +asmlinkage void blowfish_dec_blk_4way(struct bf_ctx *ctx, u8 *dst, + const u8 *src); + +static inline void blowfish_enc_blk(struct bf_ctx *ctx, u8 *dst, const u8 *src) +{ + __blowfish_enc_blk(ctx, dst, src, false); +} + +static inline void blowfish_enc_blk_xor(struct bf_ctx *ctx, u8 *dst, + const u8 *src) +{ + __blowfish_enc_blk(ctx, dst, src, true); +} + +static inline void blowfish_enc_blk_4way(struct bf_ctx *ctx, u8 *dst, + const u8 *src) +{ + __blowfish_enc_blk_4way(ctx, dst, src, false); +} + +static inline void blowfish_enc_blk_xor_4way(struct bf_ctx *ctx, u8 *dst, + const u8 *src) +{ + __blowfish_enc_blk_4way(ctx, dst, src, true); +} + +static void blowfish_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + blowfish_enc_blk(crypto_tfm_ctx(tfm), dst, src); +} + +static void blowfish_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + blowfish_dec_blk(crypto_tfm_ctx(tfm), dst, src); +} + +static struct crypto_alg bf_alg = { + .cra_name = "blowfish", + .cra_driver_name = "blowfish-asm", + .cra_priority = 200, + .cra_flags = CRYPTO_ALG_TYPE_CIPHER, + .cra_blocksize = BF_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct bf_ctx), + .cra_alignmask = 3, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(bf_alg.cra_list), + .cra_u = { + .cipher = { + .cia_min_keysize = BF_MIN_KEY_SIZE, + .cia_max_keysize = BF_MAX_KEY_SIZE, + .cia_setkey = blowfish_setkey, + .cia_encrypt = blowfish_encrypt, + .cia_decrypt = blowfish_decrypt, + } + } +}; + +static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk, + void (*fn)(struct bf_ctx *, u8 *, const u8 *), + void (*fn_4way)(struct bf_ctx *, u8 *, const u8 *)) +{ + struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = BF_BLOCK_SIZE; + unsigned int nbytes; + int err; + + err = blkcipher_walk_virt(desc, walk); + + while ((nbytes = walk->nbytes)) { + u8 *wsrc = walk->src.virt.addr; + u8 *wdst = walk->dst.virt.addr; + + /* Process four block batch */ + if (nbytes >= bsize * 4) { + do { + fn_4way(ctx, wdst, wsrc); + + wsrc += bsize * 4; + wdst += bsize * 4; + nbytes -= bsize * 4; + } while (nbytes >= bsize * 4); + + if (nbytes < bsize) + goto done; + } + + /* Handle leftovers */ + do { + fn(ctx, wdst, wsrc); + + wsrc += bsize; + wdst += bsize; + nbytes -= bsize; + } while (nbytes >= bsize); + +done: + err = blkcipher_walk_done(desc, walk, nbytes); + } + + return err; +} + +static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + + blkcipher_walk_init(&walk, dst, src, nbytes); + return ecb_crypt(desc, &walk, blowfish_enc_blk, blowfish_enc_blk_4way); +} + +static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + + blkcipher_walk_init(&walk, dst, src, nbytes); + return ecb_crypt(desc, &walk, blowfish_dec_blk, blowfish_dec_blk_4way); +} + +static struct crypto_alg blk_ecb_alg = { + .cra_name = "ecb(blowfish)", + .cra_driver_name = "ecb-blowfish-asm", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = BF_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct bf_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_ecb_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = BF_MIN_KEY_SIZE, + .max_keysize = BF_MAX_KEY_SIZE, + .setkey = blowfish_setkey, + .encrypt = ecb_encrypt, + .decrypt = ecb_decrypt, + }, + }, +}; + +static unsigned int __cbc_encrypt(struct blkcipher_desc *desc, + struct blkcipher_walk *walk) +{ + struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = BF_BLOCK_SIZE; + unsigned int nbytes = walk->nbytes; + u64 *src = (u64 *)walk->src.virt.addr; + u64 *dst = (u64 *)walk->dst.virt.addr; + u64 *iv = (u64 *)walk->iv; + + do { + *dst = *src ^ *iv; + blowfish_enc_blk(ctx, (u8 *)dst, (u8 *)dst); + iv = dst; + + src += 1; + dst += 1; + nbytes -= bsize; + } while (nbytes >= bsize); + + *(u64 *)walk->iv = *iv; + return nbytes; +} + +static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + while ((nbytes = walk.nbytes)) { + nbytes = __cbc_encrypt(desc, &walk); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + + return err; +} + +static unsigned int __cbc_decrypt(struct blkcipher_desc *desc, + struct blkcipher_walk *walk) +{ + struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = BF_BLOCK_SIZE; + unsigned int nbytes = walk->nbytes; + u64 *src = (u64 *)walk->src.virt.addr; + u64 *dst = (u64 *)walk->dst.virt.addr; + u64 ivs[4 - 1]; + u64 last_iv; + + /* Start of the last block. */ + src += nbytes / bsize - 1; + dst += nbytes / bsize - 1; + + last_iv = *src; + + /* Process four block batch */ + if (nbytes >= bsize * 4) { + do { + nbytes -= bsize * 4 - bsize; + src -= 4 - 1; + dst -= 4 - 1; + + ivs[0] = src[0]; + ivs[1] = src[1]; + ivs[2] = src[2]; + + blowfish_dec_blk_4way(ctx, (u8 *)dst, (u8 *)src); + + dst[1] ^= ivs[0]; + dst[2] ^= ivs[1]; + dst[3] ^= ivs[2]; + + nbytes -= bsize; + if (nbytes < bsize) + goto done; + + *dst ^= *(src - 1); + src -= 1; + dst -= 1; + } while (nbytes >= bsize * 4); + + if (nbytes < bsize) + goto done; + } + + /* Handle leftovers */ + for (;;) { + blowfish_dec_blk(ctx, (u8 *)dst, (u8 *)src); + + nbytes -= bsize; + if (nbytes < bsize) + break; + + *dst ^= *(src - 1); + src -= 1; + dst -= 1; + } + +done: + *dst ^= *(u64 *)walk->iv; + *(u64 *)walk->iv = last_iv; + + return nbytes; +} + +static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + while ((nbytes = walk.nbytes)) { + nbytes = __cbc_decrypt(desc, &walk); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + + return err; +} + +static struct crypto_alg blk_cbc_alg = { + .cra_name = "cbc(blowfish)", + .cra_driver_name = "cbc-blowfish-asm", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = BF_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct bf_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_cbc_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = BF_MIN_KEY_SIZE, + .max_keysize = BF_MAX_KEY_SIZE, + .ivsize = BF_BLOCK_SIZE, + .setkey = blowfish_setkey, + .encrypt = cbc_encrypt, + .decrypt = cbc_decrypt, + }, + }, +}; + +static void ctr_crypt_final(struct bf_ctx *ctx, struct blkcipher_walk *walk) +{ + u8 *ctrblk = walk->iv; + u8 keystream[BF_BLOCK_SIZE]; + u8 *src = walk->src.virt.addr; + u8 *dst = walk->dst.virt.addr; + unsigned int nbytes = walk->nbytes; + + blowfish_enc_blk(ctx, keystream, ctrblk); + crypto_xor(keystream, src, nbytes); + memcpy(dst, keystream, nbytes); + + crypto_inc(ctrblk, BF_BLOCK_SIZE); +} + +static unsigned int __ctr_crypt(struct blkcipher_desc *desc, + struct blkcipher_walk *walk) +{ + struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = BF_BLOCK_SIZE; + unsigned int nbytes = walk->nbytes; + u64 *src = (u64 *)walk->src.virt.addr; + u64 *dst = (u64 *)walk->dst.virt.addr; + u64 ctrblk = be64_to_cpu(*(__be64 *)walk->iv); + __be64 ctrblocks[4]; + + /* Process four block batch */ + if (nbytes >= bsize * 4) { + do { + if (dst != src) { + dst[0] = src[0]; + dst[1] = src[1]; + dst[2] = src[2]; + dst[3] = src[3]; + } + + /* create ctrblks for parallel encrypt */ + ctrblocks[0] = cpu_to_be64(ctrblk++); + ctrblocks[1] = cpu_to_be64(ctrblk++); + ctrblocks[2] = cpu_to_be64(ctrblk++); + ctrblocks[3] = cpu_to_be64(ctrblk++); + + blowfish_enc_blk_xor_4way(ctx, (u8 *)dst, + (u8 *)ctrblocks); + + src += 4; + dst += 4; + } while ((nbytes -= bsize * 4) >= bsize * 4); + + if (nbytes < bsize) + goto done; + } + + /* Handle leftovers */ + do { + if (dst != src) + *dst = *src; + + ctrblocks[0] = cpu_to_be64(ctrblk++); + + blowfish_enc_blk_xor(ctx, (u8 *)dst, (u8 *)ctrblocks); + + src += 1; + dst += 1; + } while ((nbytes -= bsize) >= bsize); + +done: + *(__be64 *)walk->iv = cpu_to_be64(ctrblk); + return nbytes; +} + +static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt_block(desc, &walk, BF_BLOCK_SIZE); + + while ((nbytes = walk.nbytes) >= BF_BLOCK_SIZE) { + nbytes = __ctr_crypt(desc, &walk); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + + if (walk.nbytes) { + ctr_crypt_final(crypto_blkcipher_ctx(desc->tfm), &walk); + err = blkcipher_walk_done(desc, &walk, 0); + } + + return err; +} + +static struct crypto_alg blk_ctr_alg = { + .cra_name = "ctr(blowfish)", + .cra_driver_name = "ctr-blowfish-asm", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct bf_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_ctr_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = BF_MIN_KEY_SIZE, + .max_keysize = BF_MAX_KEY_SIZE, + .ivsize = BF_BLOCK_SIZE, + .setkey = blowfish_setkey, + .encrypt = ctr_crypt, + .decrypt = ctr_crypt, + }, + }, +}; + +static int __init init(void) +{ + int err; + + err = crypto_register_alg(&bf_alg); + if (err) + goto bf_err; + err = crypto_register_alg(&blk_ecb_alg); + if (err) + goto ecb_err; + err = crypto_register_alg(&blk_cbc_alg); + if (err) + goto cbc_err; + err = crypto_register_alg(&blk_ctr_alg); + if (err) + goto ctr_err; + + return 0; + +ctr_err: + crypto_unregister_alg(&blk_cbc_alg); +cbc_err: + crypto_unregister_alg(&blk_ecb_alg); +ecb_err: + crypto_unregister_alg(&bf_alg); +bf_err: + return err; +} + +static void __exit fini(void) +{ + crypto_unregister_alg(&blk_ctr_alg); + crypto_unregister_alg(&blk_cbc_alg); + crypto_unregister_alg(&blk_ecb_alg); + crypto_unregister_alg(&bf_alg); +} + +module_init(init); +module_exit(fini); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Blowfish Cipher Algorithm, asm optimized"); +MODULE_ALIAS("blowfish"); +MODULE_ALIAS("blowfish-asm"); diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S new file mode 100644 index 000000000000..b2c2f57d70e8 --- /dev/null +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -0,0 +1,558 @@ +/* + * This is a SIMD SHA-1 implementation. It requires the Intel(R) Supplemental + * SSE3 instruction set extensions introduced in Intel Core Microarchitecture + * processors. CPUs supporting Intel(R) AVX extensions will get an additional + * boost. + * + * This work was inspired by the vectorized implementation of Dean Gaudet. + * Additional information on it can be found at: + * http://www.arctic.org/~dean/crypto/sha1.html + * + * It was improved upon with more efficient vectorization of the message + * scheduling. This implementation has also been optimized for all current and + * several future generations of Intel CPUs. + * + * See this article for more information about the implementation details: + * http://software.intel.com/en-us/articles/improving-the-performance-of-the-secure-hash-algorithm-1/ + * + * Copyright (C) 2010, Intel Corp. + * Authors: Maxim Locktyukhin <maxim.locktyukhin@intel.com> + * Ronen Zohar <ronen.zohar@intel.com> + * + * Converted to AT&T syntax and adapted for inclusion in the Linux kernel: + * Author: Mathias Krause <minipli@googlemail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#define CTX %rdi // arg1 +#define BUF %rsi // arg2 +#define CNT %rdx // arg3 + +#define REG_A %ecx +#define REG_B %esi +#define REG_C %edi +#define REG_D %ebp +#define REG_E %edx + +#define REG_T1 %eax +#define REG_T2 %ebx + +#define K_BASE %r8 +#define HASH_PTR %r9 +#define BUFFER_PTR %r10 +#define BUFFER_END %r11 + +#define W_TMP1 %xmm0 +#define W_TMP2 %xmm9 + +#define W0 %xmm1 +#define W4 %xmm2 +#define W8 %xmm3 +#define W12 %xmm4 +#define W16 %xmm5 +#define W20 %xmm6 +#define W24 %xmm7 +#define W28 %xmm8 + +#define XMM_SHUFB_BSWAP %xmm10 + +/* we keep window of 64 w[i]+K pre-calculated values in a circular buffer */ +#define WK(t) (((t) & 15) * 4)(%rsp) +#define W_PRECALC_AHEAD 16 + +/* + * This macro implements the SHA-1 function's body for single 64-byte block + * param: function's name + */ +.macro SHA1_VECTOR_ASM name + .global \name + .type \name, @function + .align 32 +\name: + push %rbx + push %rbp + push %r12 + + mov %rsp, %r12 + sub $64, %rsp # allocate workspace + and $~15, %rsp # align stack + + mov CTX, HASH_PTR + mov BUF, BUFFER_PTR + + shl $6, CNT # multiply by 64 + add BUF, CNT + mov CNT, BUFFER_END + + lea K_XMM_AR(%rip), K_BASE + xmm_mov BSWAP_SHUFB_CTL(%rip), XMM_SHUFB_BSWAP + + SHA1_PIPELINED_MAIN_BODY + + # cleanup workspace + mov $8, %ecx + mov %rsp, %rdi + xor %rax, %rax + rep stosq + + mov %r12, %rsp # deallocate workspace + + pop %r12 + pop %rbp + pop %rbx + ret + + .size \name, .-\name +.endm + +/* + * This macro implements 80 rounds of SHA-1 for one 64-byte block + */ +.macro SHA1_PIPELINED_MAIN_BODY + INIT_REGALLOC + + mov (HASH_PTR), A + mov 4(HASH_PTR), B + mov 8(HASH_PTR), C + mov 12(HASH_PTR), D + mov 16(HASH_PTR), E + + .set i, 0 + .rept W_PRECALC_AHEAD + W_PRECALC i + .set i, (i+1) + .endr + +.align 4 +1: + RR F1,A,B,C,D,E,0 + RR F1,D,E,A,B,C,2 + RR F1,B,C,D,E,A,4 + RR F1,E,A,B,C,D,6 + RR F1,C,D,E,A,B,8 + + RR F1,A,B,C,D,E,10 + RR F1,D,E,A,B,C,12 + RR F1,B,C,D,E,A,14 + RR F1,E,A,B,C,D,16 + RR F1,C,D,E,A,B,18 + + RR F2,A,B,C,D,E,20 + RR F2,D,E,A,B,C,22 + RR F2,B,C,D,E,A,24 + RR F2,E,A,B,C,D,26 + RR F2,C,D,E,A,B,28 + + RR F2,A,B,C,D,E,30 + RR F2,D,E,A,B,C,32 + RR F2,B,C,D,E,A,34 + RR F2,E,A,B,C,D,36 + RR F2,C,D,E,A,B,38 + + RR F3,A,B,C,D,E,40 + RR F3,D,E,A,B,C,42 + RR F3,B,C,D,E,A,44 + RR F3,E,A,B,C,D,46 + RR F3,C,D,E,A,B,48 + + RR F3,A,B,C,D,E,50 + RR F3,D,E,A,B,C,52 + RR F3,B,C,D,E,A,54 + RR F3,E,A,B,C,D,56 + RR F3,C,D,E,A,B,58 + + add $64, BUFFER_PTR # move to the next 64-byte block + cmp BUFFER_END, BUFFER_PTR # if the current is the last one use + cmovae K_BASE, BUFFER_PTR # dummy source to avoid buffer overrun + + RR F4,A,B,C,D,E,60 + RR F4,D,E,A,B,C,62 + RR F4,B,C,D,E,A,64 + RR F4,E,A,B,C,D,66 + RR F4,C,D,E,A,B,68 + + RR F4,A,B,C,D,E,70 + RR F4,D,E,A,B,C,72 + RR F4,B,C,D,E,A,74 + RR F4,E,A,B,C,D,76 + RR F4,C,D,E,A,B,78 + + UPDATE_HASH (HASH_PTR), A + UPDATE_HASH 4(HASH_PTR), B + UPDATE_HASH 8(HASH_PTR), C + UPDATE_HASH 12(HASH_PTR), D + UPDATE_HASH 16(HASH_PTR), E + + RESTORE_RENAMED_REGS + cmp K_BASE, BUFFER_PTR # K_BASE means, we reached the end + jne 1b +.endm + +.macro INIT_REGALLOC + .set A, REG_A + .set B, REG_B + .set C, REG_C + .set D, REG_D + .set E, REG_E + .set T1, REG_T1 + .set T2, REG_T2 +.endm + +.macro RESTORE_RENAMED_REGS + # order is important (REG_C is where it should be) + mov B, REG_B + mov D, REG_D + mov A, REG_A + mov E, REG_E +.endm + +.macro SWAP_REG_NAMES a, b + .set _T, \a + .set \a, \b + .set \b, _T +.endm + +.macro F1 b, c, d + mov \c, T1 + SWAP_REG_NAMES \c, T1 + xor \d, T1 + and \b, T1 + xor \d, T1 +.endm + +.macro F2 b, c, d + mov \d, T1 + SWAP_REG_NAMES \d, T1 + xor \c, T1 + xor \b, T1 +.endm + +.macro F3 b, c ,d + mov \c, T1 + SWAP_REG_NAMES \c, T1 + mov \b, T2 + or \b, T1 + and \c, T2 + and \d, T1 + or T2, T1 +.endm + +.macro F4 b, c, d + F2 \b, \c, \d +.endm + +.macro UPDATE_HASH hash, val + add \hash, \val + mov \val, \hash +.endm + +/* + * RR does two rounds of SHA-1 back to back with W[] pre-calc + * t1 = F(b, c, d); e += w(i) + * e += t1; b <<= 30; d += w(i+1); + * t1 = F(a, b, c); + * d += t1; a <<= 5; + * e += a; + * t1 = e; a >>= 7; + * t1 <<= 5; + * d += t1; + */ +.macro RR F, a, b, c, d, e, round + add WK(\round), \e + \F \b, \c, \d # t1 = F(b, c, d); + W_PRECALC (\round + W_PRECALC_AHEAD) + rol $30, \b + add T1, \e + add WK(\round + 1), \d + + \F \a, \b, \c + W_PRECALC (\round + W_PRECALC_AHEAD + 1) + rol $5, \a + add \a, \e + add T1, \d + ror $7, \a # (a <<r 5) >>r 7) => a <<r 30) + + mov \e, T1 + SWAP_REG_NAMES \e, T1 + + rol $5, T1 + add T1, \d + + # write: \a, \b + # rotate: \a<=\d, \b<=\e, \c<=\a, \d<=\b, \e<=\c +.endm + +.macro W_PRECALC r + .set i, \r + + .if (i < 20) + .set K_XMM, 0 + .elseif (i < 40) + .set K_XMM, 16 + .elseif (i < 60) + .set K_XMM, 32 + .elseif (i < 80) + .set K_XMM, 48 + .endif + + .if ((i < 16) || ((i >= 80) && (i < (80 + W_PRECALC_AHEAD)))) + .set i, ((\r) % 80) # pre-compute for the next iteration + .if (i == 0) + W_PRECALC_RESET + .endif + W_PRECALC_00_15 + .elseif (i<32) + W_PRECALC_16_31 + .elseif (i < 80) // rounds 32-79 + W_PRECALC_32_79 + .endif +.endm + +.macro W_PRECALC_RESET + .set W, W0 + .set W_minus_04, W4 + .set W_minus_08, W8 + .set W_minus_12, W12 + .set W_minus_16, W16 + .set W_minus_20, W20 + .set W_minus_24, W24 + .set W_minus_28, W28 + .set W_minus_32, W +.endm + +.macro W_PRECALC_ROTATE + .set W_minus_32, W_minus_28 + .set W_minus_28, W_minus_24 + .set W_minus_24, W_minus_20 + .set W_minus_20, W_minus_16 + .set W_minus_16, W_minus_12 + .set W_minus_12, W_minus_08 + .set W_minus_08, W_minus_04 + .set W_minus_04, W + .set W, W_minus_32 +.endm + +.macro W_PRECALC_SSSE3 + +.macro W_PRECALC_00_15 + W_PRECALC_00_15_SSSE3 +.endm +.macro W_PRECALC_16_31 + W_PRECALC_16_31_SSSE3 +.endm +.macro W_PRECALC_32_79 + W_PRECALC_32_79_SSSE3 +.endm + +/* message scheduling pre-compute for rounds 0-15 */ +.macro W_PRECALC_00_15_SSSE3 + .if ((i & 3) == 0) + movdqu (i*4)(BUFFER_PTR), W_TMP1 + .elseif ((i & 3) == 1) + pshufb XMM_SHUFB_BSWAP, W_TMP1 + movdqa W_TMP1, W + .elseif ((i & 3) == 2) + paddd (K_BASE), W_TMP1 + .elseif ((i & 3) == 3) + movdqa W_TMP1, WK(i&~3) + W_PRECALC_ROTATE + .endif +.endm + +/* message scheduling pre-compute for rounds 16-31 + * + * - calculating last 32 w[i] values in 8 XMM registers + * - pre-calculate K+w[i] values and store to mem, for later load by ALU add + * instruction + * + * some "heavy-lifting" vectorization for rounds 16-31 due to w[i]->w[i-3] + * dependency, but improves for 32-79 + */ +.macro W_PRECALC_16_31_SSSE3 + # blended scheduling of vector and scalar instruction streams, one 4-wide + # vector iteration / 4 scalar rounds + .if ((i & 3) == 0) + movdqa W_minus_12, W + palignr $8, W_minus_16, W # w[i-14] + movdqa W_minus_04, W_TMP1 + psrldq $4, W_TMP1 # w[i-3] + pxor W_minus_08, W + .elseif ((i & 3) == 1) + pxor W_minus_16, W_TMP1 + pxor W_TMP1, W + movdqa W, W_TMP2 + movdqa W, W_TMP1 + pslldq $12, W_TMP2 + .elseif ((i & 3) == 2) + psrld $31, W + pslld $1, W_TMP1 + por W, W_TMP1 + movdqa W_TMP2, W + psrld $30, W_TMP2 + pslld $2, W + .elseif ((i & 3) == 3) + pxor W, W_TMP1 + pxor W_TMP2, W_TMP1 + movdqa W_TMP1, W + paddd K_XMM(K_BASE), W_TMP1 + movdqa W_TMP1, WK(i&~3) + W_PRECALC_ROTATE + .endif +.endm + +/* message scheduling pre-compute for rounds 32-79 + * + * in SHA-1 specification: w[i] = (w[i-3] ^ w[i-8] ^ w[i-14] ^ w[i-16]) rol 1 + * instead we do equal: w[i] = (w[i-6] ^ w[i-16] ^ w[i-28] ^ w[i-32]) rol 2 + * allows more efficient vectorization since w[i]=>w[i-3] dependency is broken + */ +.macro W_PRECALC_32_79_SSSE3 + .if ((i & 3) == 0) + movdqa W_minus_04, W_TMP1 + pxor W_minus_28, W # W is W_minus_32 before xor + palignr $8, W_minus_08, W_TMP1 + .elseif ((i & 3) == 1) + pxor W_minus_16, W + pxor W_TMP1, W + movdqa W, W_TMP1 + .elseif ((i & 3) == 2) + psrld $30, W + pslld $2, W_TMP1 + por W, W_TMP1 + .elseif ((i & 3) == 3) + movdqa W_TMP1, W + paddd K_XMM(K_BASE), W_TMP1 + movdqa W_TMP1, WK(i&~3) + W_PRECALC_ROTATE + .endif +.endm + +.endm // W_PRECALC_SSSE3 + + +#define K1 0x5a827999 +#define K2 0x6ed9eba1 +#define K3 0x8f1bbcdc +#define K4 0xca62c1d6 + +.section .rodata +.align 16 + +K_XMM_AR: + .long K1, K1, K1, K1 + .long K2, K2, K2, K2 + .long K3, K3, K3, K3 + .long K4, K4, K4, K4 + +BSWAP_SHUFB_CTL: + .long 0x00010203 + .long 0x04050607 + .long 0x08090a0b + .long 0x0c0d0e0f + + +.section .text + +W_PRECALC_SSSE3 +.macro xmm_mov a, b + movdqu \a,\b +.endm + +/* SSSE3 optimized implementation: + * extern "C" void sha1_transform_ssse3(u32 *digest, const char *data, u32 *ws, + * unsigned int rounds); + */ +SHA1_VECTOR_ASM sha1_transform_ssse3 + +#ifdef SHA1_ENABLE_AVX_SUPPORT + +.macro W_PRECALC_AVX + +.purgem W_PRECALC_00_15 +.macro W_PRECALC_00_15 + W_PRECALC_00_15_AVX +.endm +.purgem W_PRECALC_16_31 +.macro W_PRECALC_16_31 + W_PRECALC_16_31_AVX +.endm +.purgem W_PRECALC_32_79 +.macro W_PRECALC_32_79 + W_PRECALC_32_79_AVX +.endm + +.macro W_PRECALC_00_15_AVX + .if ((i & 3) == 0) + vmovdqu (i*4)(BUFFER_PTR), W_TMP1 + .elseif ((i & 3) == 1) + vpshufb XMM_SHUFB_BSWAP, W_TMP1, W + .elseif ((i & 3) == 2) + vpaddd (K_BASE), W, W_TMP1 + .elseif ((i & 3) == 3) + vmovdqa W_TMP1, WK(i&~3) + W_PRECALC_ROTATE + .endif +.endm + +.macro W_PRECALC_16_31_AVX + .if ((i & 3) == 0) + vpalignr $8, W_minus_16, W_minus_12, W # w[i-14] + vpsrldq $4, W_minus_04, W_TMP1 # w[i-3] + vpxor W_minus_08, W, W + vpxor W_minus_16, W_TMP1, W_TMP1 + .elseif ((i & 3) == 1) + vpxor W_TMP1, W, W + vpslldq $12, W, W_TMP2 + vpslld $1, W, W_TMP1 + .elseif ((i & 3) == 2) + vpsrld $31, W, W + vpor W, W_TMP1, W_TMP1 + vpslld $2, W_TMP2, W + vpsrld $30, W_TMP2, W_TMP2 + .elseif ((i & 3) == 3) + vpxor W, W_TMP1, W_TMP1 + vpxor W_TMP2, W_TMP1, W + vpaddd K_XMM(K_BASE), W, W_TMP1 + vmovdqu W_TMP1, WK(i&~3) + W_PRECALC_ROTATE + .endif +.endm + +.macro W_PRECALC_32_79_AVX + .if ((i & 3) == 0) + vpalignr $8, W_minus_08, W_minus_04, W_TMP1 + vpxor W_minus_28, W, W # W is W_minus_32 before xor + .elseif ((i & 3) == 1) + vpxor W_minus_16, W_TMP1, W_TMP1 + vpxor W_TMP1, W, W + .elseif ((i & 3) == 2) + vpslld $2, W, W_TMP1 + vpsrld $30, W, W + vpor W, W_TMP1, W + .elseif ((i & 3) == 3) + vpaddd K_XMM(K_BASE), W, W_TMP1 + vmovdqu W_TMP1, WK(i&~3) + W_PRECALC_ROTATE + .endif +.endm + +.endm // W_PRECALC_AVX + +W_PRECALC_AVX +.purgem xmm_mov +.macro xmm_mov a, b + vmovdqu \a,\b +.endm + + +/* AVX optimized implementation: + * extern "C" void sha1_transform_avx(u32 *digest, const char *data, u32 *ws, + * unsigned int rounds); + */ +SHA1_VECTOR_ASM sha1_transform_avx + +#endif diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c new file mode 100644 index 000000000000..f916499d0abe --- /dev/null +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -0,0 +1,240 @@ +/* + * Cryptographic API. + * + * Glue code for the SHA1 Secure Hash Algorithm assembler implementation using + * Supplemental SSE3 instructions. + * + * This file is based on sha1_generic.c + * + * Copyright (c) Alan Smithee. + * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk> + * Copyright (c) Jean-Francois Dive <jef@linuxbe.org> + * Copyright (c) Mathias Krause <minipli@googlemail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <crypto/internal/hash.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/cryptohash.h> +#include <linux/types.h> +#include <crypto/sha.h> +#include <asm/byteorder.h> +#include <asm/i387.h> +#include <asm/xcr.h> +#include <asm/xsave.h> + + +asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data, + unsigned int rounds); +#ifdef SHA1_ENABLE_AVX_SUPPORT +asmlinkage void sha1_transform_avx(u32 *digest, const char *data, + unsigned int rounds); +#endif + +static asmlinkage void (*sha1_transform_asm)(u32 *, const char *, unsigned int); + + +static int sha1_ssse3_init(struct shash_desc *desc) +{ + struct sha1_state *sctx = shash_desc_ctx(desc); + + *sctx = (struct sha1_state){ + .state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 }, + }; + + return 0; +} + +static int __sha1_ssse3_update(struct shash_desc *desc, const u8 *data, + unsigned int len, unsigned int partial) +{ + struct sha1_state *sctx = shash_desc_ctx(desc); + unsigned int done = 0; + + sctx->count += len; + + if (partial) { + done = SHA1_BLOCK_SIZE - partial; + memcpy(sctx->buffer + partial, data, done); + sha1_transform_asm(sctx->state, sctx->buffer, 1); + } + + if (len - done >= SHA1_BLOCK_SIZE) { + const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE; + + sha1_transform_asm(sctx->state, data + done, rounds); + done += rounds * SHA1_BLOCK_SIZE; + } + + memcpy(sctx->buffer, data + done, len - done); + + return 0; +} + +static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + struct sha1_state *sctx = shash_desc_ctx(desc); + unsigned int partial = sctx->count % SHA1_BLOCK_SIZE; + int res; + + /* Handle the fast case right here */ + if (partial + len < SHA1_BLOCK_SIZE) { + sctx->count += len; + memcpy(sctx->buffer + partial, data, len); + + return 0; + } + + if (!irq_fpu_usable()) { + res = crypto_sha1_update(desc, data, len); + } else { + kernel_fpu_begin(); + res = __sha1_ssse3_update(desc, data, len, partial); + kernel_fpu_end(); + } + + return res; +} + + +/* Add padding and return the message digest. */ +static int sha1_ssse3_final(struct shash_desc *desc, u8 *out) +{ + struct sha1_state *sctx = shash_desc_ctx(desc); + unsigned int i, index, padlen; + __be32 *dst = (__be32 *)out; + __be64 bits; + static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, }; + + bits = cpu_to_be64(sctx->count << 3); + + /* Pad out to 56 mod 64 and append length */ + index = sctx->count % SHA1_BLOCK_SIZE; + padlen = (index < 56) ? (56 - index) : ((SHA1_BLOCK_SIZE+56) - index); + if (!irq_fpu_usable()) { + crypto_sha1_update(desc, padding, padlen); + crypto_sha1_update(desc, (const u8 *)&bits, sizeof(bits)); + } else { + kernel_fpu_begin(); + /* We need to fill a whole block for __sha1_ssse3_update() */ + if (padlen <= 56) { + sctx->count += padlen; + memcpy(sctx->buffer + index, padding, padlen); + } else { + __sha1_ssse3_update(desc, padding, padlen, index); + } + __sha1_ssse3_update(desc, (const u8 *)&bits, sizeof(bits), 56); + kernel_fpu_end(); + } + + /* Store state in digest */ + for (i = 0; i < 5; i++) + dst[i] = cpu_to_be32(sctx->state[i]); + + /* Wipe context */ + memset(sctx, 0, sizeof(*sctx)); + + return 0; +} + +static int sha1_ssse3_export(struct shash_desc *desc, void *out) +{ + struct sha1_state *sctx = shash_desc_ctx(desc); + + memcpy(out, sctx, sizeof(*sctx)); + + return 0; +} + +static int sha1_ssse3_import(struct shash_desc *desc, const void *in) +{ + struct sha1_state *sctx = shash_desc_ctx(desc); + + memcpy(sctx, in, sizeof(*sctx)); + + return 0; +} + +static struct shash_alg alg = { + .digestsize = SHA1_DIGEST_SIZE, + .init = sha1_ssse3_init, + .update = sha1_ssse3_update, + .final = sha1_ssse3_final, + .export = sha1_ssse3_export, + .import = sha1_ssse3_import, + .descsize = sizeof(struct sha1_state), + .statesize = sizeof(struct sha1_state), + .base = { + .cra_name = "sha1", + .cra_driver_name= "sha1-ssse3", + .cra_priority = 150, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; + +#ifdef SHA1_ENABLE_AVX_SUPPORT +static bool __init avx_usable(void) +{ + u64 xcr0; + + if (!cpu_has_avx || !cpu_has_osxsave) + return false; + + xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { + pr_info("AVX detected but unusable.\n"); + + return false; + } + + return true; +} +#endif + +static int __init sha1_ssse3_mod_init(void) +{ + /* test for SSSE3 first */ + if (cpu_has_ssse3) + sha1_transform_asm = sha1_transform_ssse3; + +#ifdef SHA1_ENABLE_AVX_SUPPORT + /* allow AVX to override SSSE3, it's a little faster */ + if (avx_usable()) + sha1_transform_asm = sha1_transform_avx; +#endif + + if (sha1_transform_asm) { + pr_info("Using %s optimized SHA-1 implementation\n", + sha1_transform_asm == sha1_transform_ssse3 ? "SSSE3" + : "AVX"); + return crypto_register_shash(&alg); + } + pr_info("Neither AVX nor SSSE3 is available/usable.\n"); + + return -ENODEV; +} + +static void __exit sha1_ssse3_mod_fini(void) +{ + crypto_unregister_shash(&alg); +} + +module_init(sha1_ssse3_mod_init); +module_exit(sha1_ssse3_mod_fini); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated"); + +MODULE_ALIAS("sha1"); diff --git a/arch/x86/crypto/twofish-i586-asm_32.S b/arch/x86/crypto/twofish-i586-asm_32.S index 575331cb2a8a..658af4bb35c9 100644 --- a/arch/x86/crypto/twofish-i586-asm_32.S +++ b/arch/x86/crypto/twofish-i586-asm_32.S @@ -26,7 +26,7 @@ #define in_blk 12 /* input byte array address parameter*/ #define out_blk 8 /* output byte array address parameter*/ -#define tfm 4 /* Twofish context structure */ +#define ctx 4 /* Twofish context structure */ #define a_offset 0 #define b_offset 4 @@ -229,8 +229,8 @@ twofish_enc_blk: push %esi push %edi - mov tfm + 16(%esp), %ebp /* abuse the base pointer: set new base bointer to the crypto tfm */ - add $crypto_tfm_ctx_offset, %ebp /* ctx address */ + mov ctx + 16(%esp), %ebp /* abuse the base pointer: set new base + * pointer to the ctx address */ mov in_blk+16(%esp),%edi /* input address in edi */ mov (%edi), %eax @@ -285,8 +285,8 @@ twofish_dec_blk: push %edi - mov tfm + 16(%esp), %ebp /* abuse the base pointer: set new base bointer to the crypto tfm */ - add $crypto_tfm_ctx_offset, %ebp /* ctx address */ + mov ctx + 16(%esp), %ebp /* abuse the base pointer: set new base + * pointer to the ctx address */ mov in_blk+16(%esp),%edi /* input address in edi */ mov (%edi), %eax diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S new file mode 100644 index 000000000000..5b012a2c5119 --- /dev/null +++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S @@ -0,0 +1,316 @@ +/* + * Twofish Cipher 3-way parallel algorithm (x86_64) + * + * Copyright (C) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 + * USA + * + */ + +.file "twofish-x86_64-asm-3way.S" +.text + +/* structure of crypto context */ +#define s0 0 +#define s1 1024 +#define s2 2048 +#define s3 3072 +#define w 4096 +#define k 4128 + +/********************************************************************** + 3-way twofish + **********************************************************************/ +#define CTX %rdi +#define RIO %rdx + +#define RAB0 %rax +#define RAB1 %rbx +#define RAB2 %rcx + +#define RAB0d %eax +#define RAB1d %ebx +#define RAB2d %ecx + +#define RAB0bh %ah +#define RAB1bh %bh +#define RAB2bh %ch + +#define RAB0bl %al +#define RAB1bl %bl +#define RAB2bl %cl + +#define RCD0 %r8 +#define RCD1 %r9 +#define RCD2 %r10 + +#define RCD0d %r8d +#define RCD1d %r9d +#define RCD2d %r10d + +#define RX0 %rbp +#define RX1 %r11 +#define RX2 %r12 + +#define RX0d %ebp +#define RX1d %r11d +#define RX2d %r12d + +#define RY0 %r13 +#define RY1 %r14 +#define RY2 %r15 + +#define RY0d %r13d +#define RY1d %r14d +#define RY2d %r15d + +#define RT0 %rdx +#define RT1 %rsi + +#define RT0d %edx +#define RT1d %esi + +#define do16bit_ror(rot, op1, op2, T0, T1, tmp1, tmp2, ab, dst) \ + movzbl ab ## bl, tmp2 ## d; \ + movzbl ab ## bh, tmp1 ## d; \ + rorq $(rot), ab; \ + op1##l T0(CTX, tmp2, 4), dst ## d; \ + op2##l T1(CTX, tmp1, 4), dst ## d; + +/* + * Combined G1 & G2 function. Reordered with help of rotates to have moves + * at begining. + */ +#define g1g2_3(ab, cd, Tx0, Tx1, Tx2, Tx3, Ty0, Ty1, Ty2, Ty3, x, y) \ + /* G1,1 && G2,1 */ \ + do16bit_ror(32, mov, xor, Tx0, Tx1, RT0, x ## 0, ab ## 0, x ## 0); \ + do16bit_ror(48, mov, xor, Ty1, Ty2, RT0, y ## 0, ab ## 0, y ## 0); \ + \ + do16bit_ror(32, mov, xor, Tx0, Tx1, RT0, x ## 1, ab ## 1, x ## 1); \ + do16bit_ror(48, mov, xor, Ty1, Ty2, RT0, y ## 1, ab ## 1, y ## 1); \ + \ + do16bit_ror(32, mov, xor, Tx0, Tx1, RT0, x ## 2, ab ## 2, x ## 2); \ + do16bit_ror(48, mov, xor, Ty1, Ty2, RT0, y ## 2, ab ## 2, y ## 2); \ + \ + /* G1,2 && G2,2 */ \ + do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 0, x ## 0); \ + do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 0, y ## 0); \ + xchgq cd ## 0, ab ## 0; \ + \ + do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 1, x ## 1); \ + do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 1, y ## 1); \ + xchgq cd ## 1, ab ## 1; \ + \ + do16bit_ror(32, xor, xor, Tx2, Tx3, RT0, RT1, ab ## 2, x ## 2); \ + do16bit_ror(16, xor, xor, Ty3, Ty0, RT0, RT1, ab ## 2, y ## 2); \ + xchgq cd ## 2, ab ## 2; + +#define enc_round_end(ab, x, y, n) \ + addl y ## d, x ## d; \ + addl x ## d, y ## d; \ + addl k+4*(2*(n))(CTX), x ## d; \ + xorl ab ## d, x ## d; \ + addl k+4*(2*(n)+1)(CTX), y ## d; \ + shrq $32, ab; \ + roll $1, ab ## d; \ + xorl y ## d, ab ## d; \ + shlq $32, ab; \ + rorl $1, x ## d; \ + orq x, ab; + +#define dec_round_end(ba, x, y, n) \ + addl y ## d, x ## d; \ + addl x ## d, y ## d; \ + addl k+4*(2*(n))(CTX), x ## d; \ + addl k+4*(2*(n)+1)(CTX), y ## d; \ + xorl ba ## d, y ## d; \ + shrq $32, ba; \ + roll $1, ba ## d; \ + xorl x ## d, ba ## d; \ + shlq $32, ba; \ + rorl $1, y ## d; \ + orq y, ba; + +#define encrypt_round3(ab, cd, n) \ + g1g2_3(ab, cd, s0, s1, s2, s3, s0, s1, s2, s3, RX, RY); \ + \ + enc_round_end(ab ## 0, RX0, RY0, n); \ + enc_round_end(ab ## 1, RX1, RY1, n); \ + enc_round_end(ab ## 2, RX2, RY2, n); + +#define decrypt_round3(ba, dc, n) \ + g1g2_3(ba, dc, s1, s2, s3, s0, s3, s0, s1, s2, RY, RX); \ + \ + dec_round_end(ba ## 0, RX0, RY0, n); \ + dec_round_end(ba ## 1, RX1, RY1, n); \ + dec_round_end(ba ## 2, RX2, RY2, n); + +#define encrypt_cycle3(ab, cd, n) \ + encrypt_round3(ab, cd, n*2); \ + encrypt_round3(ab, cd, (n*2)+1); + +#define decrypt_cycle3(ba, dc, n) \ + decrypt_round3(ba, dc, (n*2)+1); \ + decrypt_round3(ba, dc, (n*2)); + +#define inpack3(in, n, xy, m) \ + movq 4*(n)(in), xy ## 0; \ + xorq w+4*m(CTX), xy ## 0; \ + \ + movq 4*(4+(n))(in), xy ## 1; \ + xorq w+4*m(CTX), xy ## 1; \ + \ + movq 4*(8+(n))(in), xy ## 2; \ + xorq w+4*m(CTX), xy ## 2; + +#define outunpack3(op, out, n, xy, m) \ + xorq w+4*m(CTX), xy ## 0; \ + op ## q xy ## 0, 4*(n)(out); \ + \ + xorq w+4*m(CTX), xy ## 1; \ + op ## q xy ## 1, 4*(4+(n))(out); \ + \ + xorq w+4*m(CTX), xy ## 2; \ + op ## q xy ## 2, 4*(8+(n))(out); + +#define inpack_enc3() \ + inpack3(RIO, 0, RAB, 0); \ + inpack3(RIO, 2, RCD, 2); + +#define outunpack_enc3(op) \ + outunpack3(op, RIO, 2, RAB, 6); \ + outunpack3(op, RIO, 0, RCD, 4); + +#define inpack_dec3() \ + inpack3(RIO, 0, RAB, 4); \ + rorq $32, RAB0; \ + rorq $32, RAB1; \ + rorq $32, RAB2; \ + inpack3(RIO, 2, RCD, 6); \ + rorq $32, RCD0; \ + rorq $32, RCD1; \ + rorq $32, RCD2; + +#define outunpack_dec3() \ + rorq $32, RCD0; \ + rorq $32, RCD1; \ + rorq $32, RCD2; \ + outunpack3(mov, RIO, 0, RCD, 0); \ + rorq $32, RAB0; \ + rorq $32, RAB1; \ + rorq $32, RAB2; \ + outunpack3(mov, RIO, 2, RAB, 2); + +.align 8 +.global __twofish_enc_blk_3way +.type __twofish_enc_blk_3way,@function; + +__twofish_enc_blk_3way: + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src, RIO + * %rcx: bool, if true: xor output + */ + pushq %r15; + pushq %r14; + pushq %r13; + pushq %r12; + pushq %rbp; + pushq %rbx; + + pushq %rcx; /* bool xor */ + pushq %rsi; /* dst */ + + inpack_enc3(); + + encrypt_cycle3(RAB, RCD, 0); + encrypt_cycle3(RAB, RCD, 1); + encrypt_cycle3(RAB, RCD, 2); + encrypt_cycle3(RAB, RCD, 3); + encrypt_cycle3(RAB, RCD, 4); + encrypt_cycle3(RAB, RCD, 5); + encrypt_cycle3(RAB, RCD, 6); + encrypt_cycle3(RAB, RCD, 7); + + popq RIO; /* dst */ + popq %rbp; /* bool xor */ + + testb %bpl, %bpl; + jnz __enc_xor3; + + outunpack_enc3(mov); + + popq %rbx; + popq %rbp; + popq %r12; + popq %r13; + popq %r14; + popq %r15; + ret; + +__enc_xor3: + outunpack_enc3(xor); + + popq %rbx; + popq %rbp; + popq %r12; + popq %r13; + popq %r14; + popq %r15; + ret; + +.global twofish_dec_blk_3way +.type twofish_dec_blk_3way,@function; + +twofish_dec_blk_3way: + /* input: + * %rdi: ctx, CTX + * %rsi: dst + * %rdx: src, RIO + */ + pushq %r15; + pushq %r14; + pushq %r13; + pushq %r12; + pushq %rbp; + pushq %rbx; + + pushq %rsi; /* dst */ + + inpack_dec3(); + + decrypt_cycle3(RAB, RCD, 7); + decrypt_cycle3(RAB, RCD, 6); + decrypt_cycle3(RAB, RCD, 5); + decrypt_cycle3(RAB, RCD, 4); + decrypt_cycle3(RAB, RCD, 3); + decrypt_cycle3(RAB, RCD, 2); + decrypt_cycle3(RAB, RCD, 1); + decrypt_cycle3(RAB, RCD, 0); + + popq RIO; /* dst */ + + outunpack_dec3(); + + popq %rbx; + popq %rbp; + popq %r12; + popq %r13; + popq %r14; + popq %r15; + ret; + diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S index 573aa102542e..7bcf3fcc3668 100644 --- a/arch/x86/crypto/twofish-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-x86_64-asm_64.S @@ -221,10 +221,9 @@ twofish_enc_blk: pushq R1 - /* %rdi contains the crypto tfm address */ + /* %rdi contains the ctx address */ /* %rsi contains the output address */ /* %rdx contains the input address */ - add $crypto_tfm_ctx_offset, %rdi /* set ctx address */ /* ctx address is moved to free one non-rex register as target for the 8bit high operations */ mov %rdi, %r11 @@ -274,10 +273,9 @@ twofish_enc_blk: twofish_dec_blk: pushq R1 - /* %rdi contains the crypto tfm address */ + /* %rdi contains the ctx address */ /* %rsi contains the output address */ /* %rdx contains the input address */ - add $crypto_tfm_ctx_offset, %rdi /* set ctx address */ /* ctx address is moved to free one non-rex register as target for the 8bit high operations */ mov %rdi, %r11 diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c index cefaf8b9aa18..dc6b3fb817fc 100644 --- a/arch/x86/crypto/twofish_glue.c +++ b/arch/x86/crypto/twofish_glue.c @@ -44,17 +44,21 @@ #include <linux/module.h> #include <linux/types.h> -asmlinkage void twofish_enc_blk(struct crypto_tfm *tfm, u8 *dst, const u8 *src); -asmlinkage void twofish_dec_blk(struct crypto_tfm *tfm, u8 *dst, const u8 *src); +asmlinkage void twofish_enc_blk(struct twofish_ctx *ctx, u8 *dst, + const u8 *src); +EXPORT_SYMBOL_GPL(twofish_enc_blk); +asmlinkage void twofish_dec_blk(struct twofish_ctx *ctx, u8 *dst, + const u8 *src); +EXPORT_SYMBOL_GPL(twofish_dec_blk); static void twofish_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { - twofish_enc_blk(tfm, dst, src); + twofish_enc_blk(crypto_tfm_ctx(tfm), dst, src); } static void twofish_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { - twofish_dec_blk(tfm, dst, src); + twofish_dec_blk(crypto_tfm_ctx(tfm), dst, src); } static struct crypto_alg alg = { diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c new file mode 100644 index 000000000000..5ede9c444c3e --- /dev/null +++ b/arch/x86/crypto/twofish_glue_3way.c @@ -0,0 +1,472 @@ +/* + * Glue Code for 3-way parallel assembler optimized version of Twofish + * + * Copyright (c) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> + * + * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by: + * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> + * CTR part based on code (crypto/ctr.c) by: + * (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 + * USA + * + */ + +#include <linux/crypto.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/types.h> +#include <crypto/algapi.h> +#include <crypto/twofish.h> +#include <crypto/b128ops.h> + +/* regular block cipher functions from twofish_x86_64 module */ +asmlinkage void twofish_enc_blk(struct twofish_ctx *ctx, u8 *dst, + const u8 *src); +asmlinkage void twofish_dec_blk(struct twofish_ctx *ctx, u8 *dst, + const u8 *src); + +/* 3-way parallel cipher functions */ +asmlinkage void __twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst, + const u8 *src, bool xor); +asmlinkage void twofish_dec_blk_3way(struct twofish_ctx *ctx, u8 *dst, + const u8 *src); + +static inline void twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst, + const u8 *src) +{ + __twofish_enc_blk_3way(ctx, dst, src, false); +} + +static inline void twofish_enc_blk_xor_3way(struct twofish_ctx *ctx, u8 *dst, + const u8 *src) +{ + __twofish_enc_blk_3way(ctx, dst, src, true); +} + +static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk, + void (*fn)(struct twofish_ctx *, u8 *, const u8 *), + void (*fn_3way)(struct twofish_ctx *, u8 *, const u8 *)) +{ + struct twofish_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = TF_BLOCK_SIZE; + unsigned int nbytes; + int err; + + err = blkcipher_walk_virt(desc, walk); + + while ((nbytes = walk->nbytes)) { + u8 *wsrc = walk->src.virt.addr; + u8 *wdst = walk->dst.virt.addr; + + /* Process three block batch */ + if (nbytes >= bsize * 3) { + do { + fn_3way(ctx, wdst, wsrc); + + wsrc += bsize * 3; + wdst += bsize * 3; + nbytes -= bsize * 3; + } while (nbytes >= bsize * 3); + + if (nbytes < bsize) + goto done; + } + + /* Handle leftovers */ + do { + fn(ctx, wdst, wsrc); + + wsrc += bsize; + wdst += bsize; + nbytes -= bsize; + } while (nbytes >= bsize); + +done: + err = blkcipher_walk_done(desc, walk, nbytes); + } + + return err; +} + +static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + + blkcipher_walk_init(&walk, dst, src, nbytes); + return ecb_crypt(desc, &walk, twofish_enc_blk, twofish_enc_blk_3way); +} + +static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + + blkcipher_walk_init(&walk, dst, src, nbytes); + return ecb_crypt(desc, &walk, twofish_dec_blk, twofish_dec_blk_3way); +} + +static struct crypto_alg blk_ecb_alg = { + .cra_name = "ecb(twofish)", + .cra_driver_name = "ecb-twofish-3way", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = TF_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct twofish_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_ecb_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = TF_MIN_KEY_SIZE, + .max_keysize = TF_MAX_KEY_SIZE, + .setkey = twofish_setkey, + .encrypt = ecb_encrypt, + .decrypt = ecb_decrypt, + }, + }, +}; + +static unsigned int __cbc_encrypt(struct blkcipher_desc *desc, + struct blkcipher_walk *walk) +{ + struct twofish_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = TF_BLOCK_SIZE; + unsigned int nbytes = walk->nbytes; + u128 *src = (u128 *)walk->src.virt.addr; + u128 *dst = (u128 *)walk->dst.virt.addr; + u128 *iv = (u128 *)walk->iv; + + do { + u128_xor(dst, src, iv); + twofish_enc_blk(ctx, (u8 *)dst, (u8 *)dst); + iv = dst; + + src += 1; + dst += 1; + nbytes -= bsize; + } while (nbytes >= bsize); + + u128_xor((u128 *)walk->iv, (u128 *)walk->iv, iv); + return nbytes; +} + +static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + while ((nbytes = walk.nbytes)) { + nbytes = __cbc_encrypt(desc, &walk); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + + return err; +} + +static unsigned int __cbc_decrypt(struct blkcipher_desc *desc, + struct blkcipher_walk *walk) +{ + struct twofish_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = TF_BLOCK_SIZE; + unsigned int nbytes = walk->nbytes; + u128 *src = (u128 *)walk->src.virt.addr; + u128 *dst = (u128 *)walk->dst.virt.addr; + u128 ivs[3 - 1]; + u128 last_iv; + + /* Start of the last block. */ + src += nbytes / bsize - 1; + dst += nbytes / bsize - 1; + + last_iv = *src; + + /* Process three block batch */ + if (nbytes >= bsize * 3) { + do { + nbytes -= bsize * (3 - 1); + src -= 3 - 1; + dst -= 3 - 1; + + ivs[0] = src[0]; + ivs[1] = src[1]; + + twofish_dec_blk_3way(ctx, (u8 *)dst, (u8 *)src); + + u128_xor(dst + 1, dst + 1, ivs + 0); + u128_xor(dst + 2, dst + 2, ivs + 1); + + nbytes -= bsize; + if (nbytes < bsize) + goto done; + + u128_xor(dst, dst, src - 1); + src -= 1; + dst -= 1; + } while (nbytes >= bsize * 3); + + if (nbytes < bsize) + goto done; + } + + /* Handle leftovers */ + for (;;) { + twofish_dec_blk(ctx, (u8 *)dst, (u8 *)src); + + nbytes -= bsize; + if (nbytes < bsize) + break; + + u128_xor(dst, dst, src - 1); + src -= 1; + dst -= 1; + } + +done: + u128_xor(dst, dst, (u128 *)walk->iv); + *(u128 *)walk->iv = last_iv; + + return nbytes; +} + +static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + while ((nbytes = walk.nbytes)) { + nbytes = __cbc_decrypt(desc, &walk); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + + return err; +} + +static struct crypto_alg blk_cbc_alg = { + .cra_name = "cbc(twofish)", + .cra_driver_name = "cbc-twofish-3way", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = TF_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct twofish_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_cbc_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = TF_MIN_KEY_SIZE, + .max_keysize = TF_MAX_KEY_SIZE, + .ivsize = TF_BLOCK_SIZE, + .setkey = twofish_setkey, + .encrypt = cbc_encrypt, + .decrypt = cbc_decrypt, + }, + }, +}; + +static inline void u128_to_be128(be128 *dst, const u128 *src) +{ + dst->a = cpu_to_be64(src->a); + dst->b = cpu_to_be64(src->b); +} + +static inline void be128_to_u128(u128 *dst, const be128 *src) +{ + dst->a = be64_to_cpu(src->a); + dst->b = be64_to_cpu(src->b); +} + +static inline void u128_inc(u128 *i) +{ + i->b++; + if (!i->b) + i->a++; +} + +static void ctr_crypt_final(struct blkcipher_desc *desc, + struct blkcipher_walk *walk) +{ + struct twofish_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + u8 *ctrblk = walk->iv; + u8 keystream[TF_BLOCK_SIZE]; + u8 *src = walk->src.virt.addr; + u8 *dst = walk->dst.virt.addr; + unsigned int nbytes = walk->nbytes; + + twofish_enc_blk(ctx, keystream, ctrblk); + crypto_xor(keystream, src, nbytes); + memcpy(dst, keystream, nbytes); + + crypto_inc(ctrblk, TF_BLOCK_SIZE); +} + +static unsigned int __ctr_crypt(struct blkcipher_desc *desc, + struct blkcipher_walk *walk) +{ + struct twofish_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + unsigned int bsize = TF_BLOCK_SIZE; + unsigned int nbytes = walk->nbytes; + u128 *src = (u128 *)walk->src.virt.addr; + u128 *dst = (u128 *)walk->dst.virt.addr; + u128 ctrblk; + be128 ctrblocks[3]; + + be128_to_u128(&ctrblk, (be128 *)walk->iv); + + /* Process three block batch */ + if (nbytes >= bsize * 3) { + do { + if (dst != src) { + dst[0] = src[0]; + dst[1] = src[1]; + dst[2] = src[2]; + } + + /* create ctrblks for parallel encrypt */ + u128_to_be128(&ctrblocks[0], &ctrblk); + u128_inc(&ctrblk); + u128_to_be128(&ctrblocks[1], &ctrblk); + u128_inc(&ctrblk); + u128_to_be128(&ctrblocks[2], &ctrblk); + u128_inc(&ctrblk); + + twofish_enc_blk_xor_3way(ctx, (u8 *)dst, + (u8 *)ctrblocks); + + src += 3; + dst += 3; + nbytes -= bsize * 3; + } while (nbytes >= bsize * 3); + + if (nbytes < bsize) + goto done; + } + + /* Handle leftovers */ + do { + if (dst != src) + *dst = *src; + + u128_to_be128(&ctrblocks[0], &ctrblk); + u128_inc(&ctrblk); + + twofish_enc_blk(ctx, (u8 *)ctrblocks, (u8 *)ctrblocks); + u128_xor(dst, dst, (u128 *)ctrblocks); + + src += 1; + dst += 1; + nbytes -= bsize; + } while (nbytes >= bsize); + +done: + u128_to_be128((be128 *)walk->iv, &ctrblk); + return nbytes; +} + +static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt_block(desc, &walk, TF_BLOCK_SIZE); + + while ((nbytes = walk.nbytes) >= TF_BLOCK_SIZE) { + nbytes = __ctr_crypt(desc, &walk); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + + if (walk.nbytes) { + ctr_crypt_final(desc, &walk); + err = blkcipher_walk_done(desc, &walk, 0); + } + + return err; +} + +static struct crypto_alg blk_ctr_alg = { + .cra_name = "ctr(twofish)", + .cra_driver_name = "ctr-twofish-3way", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct twofish_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_ctr_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = TF_MIN_KEY_SIZE, + .max_keysize = TF_MAX_KEY_SIZE, + .ivsize = TF_BLOCK_SIZE, + .setkey = twofish_setkey, + .encrypt = ctr_crypt, + .decrypt = ctr_crypt, + }, + }, +}; + +int __init init(void) +{ + int err; + + err = crypto_register_alg(&blk_ecb_alg); + if (err) + goto ecb_err; + err = crypto_register_alg(&blk_cbc_alg); + if (err) + goto cbc_err; + err = crypto_register_alg(&blk_ctr_alg); + if (err) + goto ctr_err; + + return 0; + +ctr_err: + crypto_unregister_alg(&blk_cbc_alg); +cbc_err: + crypto_unregister_alg(&blk_ecb_alg); +ecb_err: + return err; +} + +void __exit fini(void) +{ + crypto_unregister_alg(&blk_ctr_alg); + crypto_unregister_alg(&blk_cbc_alg); + crypto_unregister_alg(&blk_ecb_alg); +} + +module_init(init); +module_exit(fini); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Twofish Cipher Algorithm, 3-way parallel asm optimized"); +MODULE_ALIAS("twofish"); +MODULE_ALIAS("twofish-asm"); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 54edb207ff3a..a6253ec1b284 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -850,4 +850,6 @@ ia32_sys_call_table: .quad sys_syncfs .quad compat_sys_sendmmsg /* 345 */ .quad sys_setns + .quad compat_sys_process_vm_readv + .quad compat_sys_process_vm_writev ia32_syscall_end: diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 67f87f257611..8e41071704a5 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -19,9 +19,15 @@ extern int amd_numa_init(void); extern int amd_get_subcaches(int); extern int amd_set_subcaches(int, int); +struct amd_l3_cache { + unsigned indices; + u8 subcaches[4]; +}; + struct amd_northbridge { struct pci_dev *misc; struct pci_dev *link; + struct amd_l3_cache l3_cache; }; struct amd_northbridge_info { diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 7b3ca8324b69..9b7273cb2193 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -495,7 +495,7 @@ static inline void default_wait_for_init_deassert(atomic_t *deassert) return; } -extern struct apic *generic_bigsmp_probe(void); +extern void generic_bigsmp_probe(void); #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 34595d5e1038..3925d8007864 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -100,7 +100,9 @@ #define APIC_TIMER_BASE_CLKIN 0x0 #define APIC_TIMER_BASE_TMBASE 0x1 #define APIC_TIMER_BASE_DIV 0x2 +#define APIC_LVT_TIMER_ONESHOT (0 << 17) #define APIC_LVT_TIMER_PERIODIC (1 << 17) +#define APIC_LVT_TIMER_TSCDEADLINE (2 << 17) #define APIC_LVT_MASKED (1 << 16) #define APIC_LVT_LEVEL_TRIGGER (1 << 15) #define APIC_LVT_REMOTE_IRR (1 << 14) diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h new file mode 100644 index 000000000000..0d9ec770f2f8 --- /dev/null +++ b/arch/x86/include/asm/archrandom.h @@ -0,0 +1,75 @@ +/* + * This file is part of the Linux kernel. + * + * Copyright (c) 2011, Intel Corporation + * Authors: Fenghua Yu <fenghua.yu@intel.com>, + * H. Peter Anvin <hpa@linux.intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * + */ + +#ifndef ASM_X86_ARCHRANDOM_H +#define ASM_X86_ARCHRANDOM_H + +#include <asm/processor.h> +#include <asm/cpufeature.h> +#include <asm/alternative.h> +#include <asm/nops.h> + +#define RDRAND_RETRY_LOOPS 10 + +#define RDRAND_INT ".byte 0x0f,0xc7,0xf0" +#ifdef CONFIG_X86_64 +# define RDRAND_LONG ".byte 0x48,0x0f,0xc7,0xf0" +#else +# define RDRAND_LONG RDRAND_INT +#endif + +#ifdef CONFIG_ARCH_RANDOM + +#define GET_RANDOM(name, type, rdrand, nop) \ +static inline int name(type *v) \ +{ \ + int ok; \ + alternative_io("movl $0, %0\n\t" \ + nop, \ + "\n1: " rdrand "\n\t" \ + "jc 2f\n\t" \ + "decl %0\n\t" \ + "jnz 1b\n\t" \ + "2:", \ + X86_FEATURE_RDRAND, \ + ASM_OUTPUT2("=r" (ok), "=a" (*v)), \ + "0" (RDRAND_RETRY_LOOPS)); \ + return ok; \ +} + +#ifdef CONFIG_X86_64 + +GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP5); +GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP4); + +#else + +GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP3); +GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP3); + +#endif /* CONFIG_X86_64 */ + +#endif /* CONFIG_ARCH_RANDOM */ + +extern void x86_init_rdrand(struct cpuinfo_x86 *c); + +#endif /* ASM_X86_ARCHRANDOM_H */ diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 10572e309ab2..58cb6d4085f7 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -172,18 +172,14 @@ static inline int atomic_add_negative(int i, atomic_t *v) */ static inline int atomic_add_return(int i, atomic_t *v) { - int __i; #ifdef CONFIG_M386 + int __i; unsigned long flags; if (unlikely(boot_cpu_data.x86 <= 3)) goto no_xadd; #endif /* Modern 486+ processor */ - __i = i; - asm volatile(LOCK_PREFIX "xaddl %0, %1" - : "+r" (i), "+m" (v->counter) - : : "memory"); - return i + __i; + return i + xadd(&v->counter, i); #ifdef CONFIG_M386 no_xadd: /* Legacy 386 processor */ diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 017594d403f6..0e1cbfc8ee06 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -170,11 +170,7 @@ static inline int atomic64_add_negative(long i, atomic64_t *v) */ static inline long atomic64_add_return(long i, atomic64_t *v) { - long __i = i; - asm volatile(LOCK_PREFIX "xaddq %0, %1;" - : "+r" (i), "+m" (v->counter) - : : "memory"); - return i + __i; + return i + xadd(&v->counter, i); } static inline long atomic64_sub_return(long i, atomic64_t *v) diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index a460fa088d4c..5d3acdf5a7a6 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -1,5 +1,210 @@ +#ifndef ASM_X86_CMPXCHG_H +#define ASM_X86_CMPXCHG_H + +#include <linux/compiler.h> +#include <asm/alternative.h> /* Provides LOCK_PREFIX */ + +/* + * Non-existant functions to indicate usage errors at link time + * (or compile-time if the compiler implements __compiletime_error(). + */ +extern void __xchg_wrong_size(void) + __compiletime_error("Bad argument size for xchg"); +extern void __cmpxchg_wrong_size(void) + __compiletime_error("Bad argument size for cmpxchg"); +extern void __xadd_wrong_size(void) + __compiletime_error("Bad argument size for xadd"); + +/* + * Constants for operation sizes. On 32-bit, the 64-bit size it set to + * -1 because sizeof will never return -1, thereby making those switch + * case statements guaranteeed dead code which the compiler will + * eliminate, and allowing the "missing symbol in the default case" to + * indicate a usage error. + */ +#define __X86_CASE_B 1 +#define __X86_CASE_W 2 +#define __X86_CASE_L 4 +#ifdef CONFIG_64BIT +#define __X86_CASE_Q 8 +#else +#define __X86_CASE_Q -1 /* sizeof will never return -1 */ +#endif + +/* + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. + * Since this is generally used to protect other memory information, we + * use "asm volatile" and "memory" clobbers to prevent gcc from moving + * information around. + */ +#define __xchg(x, ptr, size) \ +({ \ + __typeof(*(ptr)) __x = (x); \ + switch (size) { \ + case __X86_CASE_B: \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile("xchgb %0,%1" \ + : "=q" (__x), "+m" (*__ptr) \ + : "0" (__x) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_W: \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile("xchgw %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_L: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile("xchgl %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_Q: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ + asm volatile("xchgq %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ + : "memory"); \ + break; \ + } \ + default: \ + __xchg_wrong_size(); \ + } \ + __x; \ +}) + +#define xchg(ptr, v) \ + __xchg((v), (ptr), sizeof(*ptr)) + +/* + * Atomic compare and exchange. Compare OLD with MEM, if identical, + * store NEW in MEM. Return the initial value in MEM. Success is + * indicated by comparing RETURN with OLD. + */ +#define __raw_cmpxchg(ptr, old, new, size, lock) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (old); \ + __typeof__(*(ptr)) __new = (new); \ + switch (size) { \ + case __X86_CASE_B: \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile(lock "cmpxchgb %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_W: \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile(lock "cmpxchgw %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_L: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile(lock "cmpxchgl %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_Q: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ + asm volatile(lock "cmpxchgq %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + __ret; \ +}) + +#define __cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX) + +#define __sync_cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "lock; ") + +#define __cmpxchg_local(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "") + #ifdef CONFIG_X86_32 # include "cmpxchg_32.h" #else # include "cmpxchg_64.h" #endif + +#ifdef __HAVE_ARCH_CMPXCHG +#define cmpxchg(ptr, old, new) \ + __cmpxchg((ptr), (old), (new), sizeof(*ptr)) + +#define sync_cmpxchg(ptr, old, new) \ + __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr)) + +#define cmpxchg_local(ptr, old, new) \ + __cmpxchg_local((ptr), (old), (new), sizeof(*ptr)) +#endif + +#define __xadd(ptr, inc, lock) \ + ({ \ + __typeof__ (*(ptr)) __ret = (inc); \ + switch (sizeof(*(ptr))) { \ + case __X86_CASE_B: \ + asm volatile (lock "xaddb %b0, %1\n" \ + : "+r" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + case __X86_CASE_W: \ + asm volatile (lock "xaddw %w0, %1\n" \ + : "+r" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + case __X86_CASE_L: \ + asm volatile (lock "xaddl %0, %1\n" \ + : "+r" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + case __X86_CASE_Q: \ + asm volatile (lock "xaddq %q0, %1\n" \ + : "+r" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + default: \ + __xadd_wrong_size(); \ + } \ + __ret; \ + }) + +/* + * xadd() adds "inc" to "*ptr" and atomically returns the previous + * value of "*ptr". + * + * xadd() is locked when multiple CPUs are online + * xadd_sync() is always locked + * xadd_local() is never locked + */ +#define xadd(ptr, inc) __xadd((ptr), (inc), LOCK_PREFIX) +#define xadd_sync(ptr, inc) __xadd((ptr), (inc), "lock; ") +#define xadd_local(ptr, inc) __xadd((ptr), (inc), "") + +#endif /* ASM_X86_CMPXCHG_H */ diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index 3deb7250624c..fbebb07dd80b 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -1,61 +1,11 @@ #ifndef _ASM_X86_CMPXCHG_32_H #define _ASM_X86_CMPXCHG_32_H -#include <linux/bitops.h> /* for LOCK_PREFIX */ - /* * Note: if you use set64_bit(), __cmpxchg64(), or their variants, you * you need to test for the feature in boot_cpu_data. */ -extern void __xchg_wrong_size(void); - -/* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. - * Since this is generally used to protect other memory information, we - * use "asm volatile" and "memory" clobbers to prevent gcc from moving - * information around. - */ -#define __xchg(x, ptr, size) \ -({ \ - __typeof(*(ptr)) __x = (x); \ - switch (size) { \ - case 1: \ - { \ - volatile u8 *__ptr = (volatile u8 *)(ptr); \ - asm volatile("xchgb %0,%1" \ - : "=q" (__x), "+m" (*__ptr) \ - : "0" (__x) \ - : "memory"); \ - break; \ - } \ - case 2: \ - { \ - volatile u16 *__ptr = (volatile u16 *)(ptr); \ - asm volatile("xchgw %0,%1" \ - : "=r" (__x), "+m" (*__ptr) \ - : "0" (__x) \ - : "memory"); \ - break; \ - } \ - case 4: \ - { \ - volatile u32 *__ptr = (volatile u32 *)(ptr); \ - asm volatile("xchgl %0,%1" \ - : "=r" (__x), "+m" (*__ptr) \ - : "0" (__x) \ - : "memory"); \ - break; \ - } \ - default: \ - __xchg_wrong_size(); \ - } \ - __x; \ -}) - -#define xchg(ptr, v) \ - __xchg((v), (ptr), sizeof(*ptr)) - /* * CMPXCHG8B only writes to the target if we had the previous * value in registers, otherwise it acts as a read and gives us the @@ -84,72 +34,8 @@ static inline void set_64bit(volatile u64 *ptr, u64 value) : "memory"); } -extern void __cmpxchg_wrong_size(void); - -/* - * Atomic compare and exchange. Compare OLD with MEM, if identical, - * store NEW in MEM. Return the initial value in MEM. Success is - * indicated by comparing RETURN with OLD. - */ -#define __raw_cmpxchg(ptr, old, new, size, lock) \ -({ \ - __typeof__(*(ptr)) __ret; \ - __typeof__(*(ptr)) __old = (old); \ - __typeof__(*(ptr)) __new = (new); \ - switch (size) { \ - case 1: \ - { \ - volatile u8 *__ptr = (volatile u8 *)(ptr); \ - asm volatile(lock "cmpxchgb %2,%1" \ - : "=a" (__ret), "+m" (*__ptr) \ - : "q" (__new), "0" (__old) \ - : "memory"); \ - break; \ - } \ - case 2: \ - { \ - volatile u16 *__ptr = (volatile u16 *)(ptr); \ - asm volatile(lock "cmpxchgw %2,%1" \ - : "=a" (__ret), "+m" (*__ptr) \ - : "r" (__new), "0" (__old) \ - : "memory"); \ - break; \ - } \ - case 4: \ - { \ - volatile u32 *__ptr = (volatile u32 *)(ptr); \ - asm volatile(lock "cmpxchgl %2,%1" \ - : "=a" (__ret), "+m" (*__ptr) \ - : "r" (__new), "0" (__old) \ - : "memory"); \ - break; \ - } \ - default: \ - __cmpxchg_wrong_size(); \ - } \ - __ret; \ -}) - -#define __cmpxchg(ptr, old, new, size) \ - __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX) - -#define __sync_cmpxchg(ptr, old, new, size) \ - __raw_cmpxchg((ptr), (old), (new), (size), "lock; ") - -#define __cmpxchg_local(ptr, old, new, size) \ - __raw_cmpxchg((ptr), (old), (new), (size), "") - #ifdef CONFIG_X86_CMPXCHG #define __HAVE_ARCH_CMPXCHG 1 - -#define cmpxchg(ptr, old, new) \ - __cmpxchg((ptr), (old), (new), sizeof(*ptr)) - -#define sync_cmpxchg(ptr, old, new) \ - __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr)) - -#define cmpxchg_local(ptr, old, new) \ - __cmpxchg_local((ptr), (old), (new), sizeof(*ptr)) #endif #ifdef CONFIG_X86_CMPXCHG64 diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 7cf5c0a24434..285da02c38fa 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -1,144 +1,13 @@ #ifndef _ASM_X86_CMPXCHG_64_H #define _ASM_X86_CMPXCHG_64_H -#include <asm/alternative.h> /* Provides LOCK_PREFIX */ - static inline void set_64bit(volatile u64 *ptr, u64 val) { *ptr = val; } -extern void __xchg_wrong_size(void); -extern void __cmpxchg_wrong_size(void); - -/* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. - * Since this is generally used to protect other memory information, we - * use "asm volatile" and "memory" clobbers to prevent gcc from moving - * information around. - */ -#define __xchg(x, ptr, size) \ -({ \ - __typeof(*(ptr)) __x = (x); \ - switch (size) { \ - case 1: \ - { \ - volatile u8 *__ptr = (volatile u8 *)(ptr); \ - asm volatile("xchgb %0,%1" \ - : "=q" (__x), "+m" (*__ptr) \ - : "0" (__x) \ - : "memory"); \ - break; \ - } \ - case 2: \ - { \ - volatile u16 *__ptr = (volatile u16 *)(ptr); \ - asm volatile("xchgw %0,%1" \ - : "=r" (__x), "+m" (*__ptr) \ - : "0" (__x) \ - : "memory"); \ - break; \ - } \ - case 4: \ - { \ - volatile u32 *__ptr = (volatile u32 *)(ptr); \ - asm volatile("xchgl %0,%1" \ - : "=r" (__x), "+m" (*__ptr) \ - : "0" (__x) \ - : "memory"); \ - break; \ - } \ - case 8: \ - { \ - volatile u64 *__ptr = (volatile u64 *)(ptr); \ - asm volatile("xchgq %0,%1" \ - : "=r" (__x), "+m" (*__ptr) \ - : "0" (__x) \ - : "memory"); \ - break; \ - } \ - default: \ - __xchg_wrong_size(); \ - } \ - __x; \ -}) - -#define xchg(ptr, v) \ - __xchg((v), (ptr), sizeof(*ptr)) - #define __HAVE_ARCH_CMPXCHG 1 -/* - * Atomic compare and exchange. Compare OLD with MEM, if identical, - * store NEW in MEM. Return the initial value in MEM. Success is - * indicated by comparing RETURN with OLD. - */ -#define __raw_cmpxchg(ptr, old, new, size, lock) \ -({ \ - __typeof__(*(ptr)) __ret; \ - __typeof__(*(ptr)) __old = (old); \ - __typeof__(*(ptr)) __new = (new); \ - switch (size) { \ - case 1: \ - { \ - volatile u8 *__ptr = (volatile u8 *)(ptr); \ - asm volatile(lock "cmpxchgb %2,%1" \ - : "=a" (__ret), "+m" (*__ptr) \ - : "q" (__new), "0" (__old) \ - : "memory"); \ - break; \ - } \ - case 2: \ - { \ - volatile u16 *__ptr = (volatile u16 *)(ptr); \ - asm volatile(lock "cmpxchgw %2,%1" \ - : "=a" (__ret), "+m" (*__ptr) \ - : "r" (__new), "0" (__old) \ - : "memory"); \ - break; \ - } \ - case 4: \ - { \ - volatile u32 *__ptr = (volatile u32 *)(ptr); \ - asm volatile(lock "cmpxchgl %2,%1" \ - : "=a" (__ret), "+m" (*__ptr) \ - : "r" (__new), "0" (__old) \ - : "memory"); \ - break; \ - } \ - case 8: \ - { \ - volatile u64 *__ptr = (volatile u64 *)(ptr); \ - asm volatile(lock "cmpxchgq %2,%1" \ - : "=a" (__ret), "+m" (*__ptr) \ - : "r" (__new), "0" (__old) \ - : "memory"); \ - break; \ - } \ - default: \ - __cmpxchg_wrong_size(); \ - } \ - __ret; \ -}) - -#define __cmpxchg(ptr, old, new, size) \ - __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX) - -#define __sync_cmpxchg(ptr, old, new, size) \ - __raw_cmpxchg((ptr), (old), (new), (size), "lock; ") - -#define __cmpxchg_local(ptr, old, new, size) \ - __raw_cmpxchg((ptr), (old), (new), (size), "") - -#define cmpxchg(ptr, old, new) \ - __cmpxchg((ptr), (old), (new), sizeof(*ptr)) - -#define sync_cmpxchg(ptr, old, new) \ - __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr)) - -#define cmpxchg_local(ptr, old, new) \ - __cmpxchg_local((ptr), (old), (new), sizeof(*ptr)) - #define cmpxchg64(ptr, o, n) \ ({ \ BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 1d9cd27c2920..30d737ef2a42 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -108,7 +108,8 @@ struct compat_statfs { compat_fsid_t f_fsid; int f_namelen; /* SunOS ignores this field. */ int f_frsize; - int f_spare[5]; + int f_flags; + int f_spare[4]; }; #define COMPAT_RLIM_OLD_INFINITY 0x7fffffff diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 88b23a43f340..f3444f700f36 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -114,12 +114,14 @@ #define X86_FEATURE_CX16 (4*32+13) /* CMPXCHG16B */ #define X86_FEATURE_XTPR (4*32+14) /* Send Task Priority Messages */ #define X86_FEATURE_PDCM (4*32+15) /* Performance Capabilities */ +#define X86_FEATURE_PCID (4*32+17) /* Process Context Identifiers */ #define X86_FEATURE_DCA (4*32+18) /* Direct Cache Access */ #define X86_FEATURE_XMM4_1 (4*32+19) /* "sse4_1" SSE-4.1 */ #define X86_FEATURE_XMM4_2 (4*32+20) /* "sse4_2" SSE-4.2 */ #define X86_FEATURE_X2APIC (4*32+21) /* x2APIC */ #define X86_FEATURE_MOVBE (4*32+22) /* MOVBE instruction */ #define X86_FEATURE_POPCNT (4*32+23) /* POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER (4*32+24) /* Tsc deadline timer */ #define X86_FEATURE_AES (4*32+25) /* AES instructions */ #define X86_FEATURE_XSAVE (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ #define X86_FEATURE_OSXSAVE (4*32+27) /* "" XSAVE enabled in the OS */ @@ -257,7 +259,9 @@ extern const char * const x86_power_flags[32]; #define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM) #define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2) #define cpu_has_xmm3 boot_cpu_has(X86_FEATURE_XMM3) +#define cpu_has_ssse3 boot_cpu_has(X86_FEATURE_SSSE3) #define cpu_has_aes boot_cpu_has(X86_FEATURE_AES) +#define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX) #define cpu_has_ht boot_cpu_has(X86_FEATURE_HT) #define cpu_has_mp boot_cpu_has(X86_FEATURE_MP) #define cpu_has_nx boot_cpu_has(X86_FEATURE_NX) @@ -285,6 +289,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_xmm4_2 boot_cpu_has(X86_FEATURE_XMM4_2) #define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC) #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) +#define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) #define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) #define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index 029f230ab637..63a2a03d7d51 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -8,7 +8,7 @@ struct dev_archdata { #ifdef CONFIG_X86_64 struct dma_map_ops *dma_ops; #endif -#if defined(CONFIG_DMAR) || defined(CONFIG_AMD_IOMMU) +#if defined(CONFIG_INTEL_IOMMU) || defined(CONFIG_AMD_IOMMU) void *iommu; /* hook for IOMMU specific extension */ #endif }; diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index d4c419f883a0..ed3065fd6314 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -2,7 +2,7 @@ #define _ASM_X86_DMA_MAPPING_H /* - * IOMMU interface. See Documentation/PCI/PCI-DMA-mapping.txt and + * IOMMU interface. See Documentation/DMA-API-HOWTO.txt and * Documentation/DMA-API.txt for documentation. */ diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h index 326099199318..f6f15986df6c 100644 --- a/arch/x86/include/asm/dwarf2.h +++ b/arch/x86/include/asm/dwarf2.h @@ -27,6 +27,7 @@ #define CFI_REMEMBER_STATE .cfi_remember_state #define CFI_RESTORE_STATE .cfi_restore_state #define CFI_UNDEFINED .cfi_undefined +#define CFI_ESCAPE .cfi_escape #ifdef CONFIG_AS_CFI_SIGNAL_FRAME #define CFI_SIGNAL_FRAME .cfi_signal_frame @@ -68,6 +69,7 @@ #define CFI_REMEMBER_STATE cfi_ignore #define CFI_RESTORE_STATE cfi_ignore #define CFI_UNDEFINED cfi_ignore +#define CFI_ESCAPE cfi_ignore #define CFI_SIGNAL_FRAME cfi_ignore #endif diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index f2ad2163109d..5f962df30d0f 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -4,6 +4,7 @@ /* * ELF register definitions.. */ +#include <linux/thread_info.h> #include <asm/ptrace.h> #include <asm/user.h> @@ -320,4 +321,34 @@ extern int syscall32_setup_pages(struct linux_binprm *, int exstack); extern unsigned long arch_randomize_brk(struct mm_struct *mm); #define arch_randomize_brk arch_randomize_brk +/* + * True on X86_32 or when emulating IA32 on X86_64 + */ +static inline int mmap_is_ia32(void) +{ +#ifdef CONFIG_X86_32 + return 1; +#endif +#ifdef CONFIG_IA32_EMULATION + if (test_thread_flag(TIF_IA32)) + return 1; +#endif + return 0; +} + +/* The first two values are special, do not change. See align_addr() */ +enum align_flags { + ALIGN_VA_32 = BIT(0), + ALIGN_VA_64 = BIT(1), + ALIGN_VDSO = BIT(2), + ALIGN_TOPDOWN = BIT(3), +}; + +struct va_alignment { + int flags; + unsigned long mask; +} ____cacheline_aligned; + +extern struct va_alignment va_align; +extern unsigned long align_addr(unsigned long, struct file *, enum align_flags); #endif /* _ASM_X86_ELF_H */ diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 09199052060f..eb92a6ed2be7 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -119,7 +119,7 @@ struct irq_cfg { cpumask_var_t old_domain; u8 vector; u8 move_in_progress : 1; -#ifdef CONFIG_INTR_REMAP +#ifdef CONFIG_IRQ_REMAP struct irq_2_iommu irq_2_iommu; #endif }; diff --git a/arch/x86/include/asm/hyperv.h b/arch/x86/include/asm/hyperv.h index 5df477ac3af7..b80420bcd09d 100644 --- a/arch/x86/include/asm/hyperv.h +++ b/arch/x86/include/asm/hyperv.h @@ -189,5 +189,6 @@ #define HV_STATUS_INVALID_HYPERCALL_CODE 2 #define HV_STATUS_INVALID_HYPERCALL_INPUT 3 #define HV_STATUS_INVALID_ALIGNMENT 4 +#define HV_STATUS_INSUFFICIENT_BUFFERS 19 #endif diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 1c23360fb2d8..47d99934580f 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -3,7 +3,8 @@ #define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8) -#ifdef CONFIG_INTR_REMAP +#ifdef CONFIG_IRQ_REMAP +static void irq_remap_modify_chip_defaults(struct irq_chip *chip); static inline void prepare_irte(struct irte *irte, int vector, unsigned int dest) { @@ -36,6 +37,9 @@ static inline bool irq_remapped(struct irq_cfg *cfg) { return false; } +static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip) +{ +} #endif #endif /* _ASM_X86_IRQ_REMAPPING_H */ diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 7e50f06393aa..4b4448761e88 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -160,19 +160,11 @@ static inline int invalid_vm86_irq(int irq) #define IO_APIC_VECTOR_LIMIT ( 32 * MAX_IO_APICS ) #ifdef CONFIG_X86_IO_APIC -# ifdef CONFIG_SPARSE_IRQ -# define CPU_VECTOR_LIMIT (64 * NR_CPUS) -# define NR_IRQS \ +# define CPU_VECTOR_LIMIT (64 * NR_CPUS) +# define NR_IRQS \ (CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ? \ (NR_VECTORS + CPU_VECTOR_LIMIT) : \ (NR_VECTORS + IO_APIC_VECTOR_LIMIT)) -# else -# define CPU_VECTOR_LIMIT (32 * NR_CPUS) -# define NR_IRQS \ - (CPU_VECTOR_LIMIT < IO_APIC_VECTOR_LIMIT ? \ - (NR_VECTORS + CPU_VECTOR_LIMIT) : \ - (NR_VECTORS + IO_APIC_VECTOR_LIMIT)) -# endif #else /* !CONFIG_X86_IO_APIC: */ # define NR_IRQS NR_IRQS_LEGACY #endif diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 6040d115ef51..a026507893e9 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -262,7 +262,7 @@ struct x86_emulate_ctxt { struct operand dst; bool has_seg_override; u8 seg_override; - unsigned int d; + u64 d; int (*execute)(struct x86_emulate_ctxt *ctxt); int (*check_perm)(struct x86_emulate_ctxt *ctxt); /* modrm */ @@ -275,6 +275,8 @@ struct x86_emulate_ctxt { unsigned long _eip; /* Fields above regs are cleared together. */ unsigned long regs[NR_VCPU_REGS]; + struct operand memop; + struct operand *memopp; struct fetch_cache fetch; struct read_cache io_read; struct read_cache mem_read; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index dd51c83aa5de..b4973f4dab98 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -26,7 +26,8 @@ #include <asm/mtrr.h> #include <asm/msr-index.h> -#define KVM_MAX_VCPUS 64 +#define KVM_MAX_VCPUS 254 +#define KVM_SOFT_MAX_VCPUS 64 #define KVM_MEMORY_SLOTS 32 /* memory slots that does not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 4 @@ -264,6 +265,7 @@ struct kvm_mmu { void (*new_cr3)(struct kvm_vcpu *vcpu); void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root); unsigned long (*get_cr3)(struct kvm_vcpu *vcpu); + u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err, bool prefault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, @@ -411,8 +413,9 @@ struct kvm_vcpu_arch { u32 tsc_catchup_mult; s8 tsc_catchup_shift; - bool nmi_pending; - bool nmi_injected; + atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ + unsigned nmi_pending; /* NMI queued after currently running handler */ + bool nmi_injected; /* Trying to inject an NMI this entry */ struct mtrr_state_type mtrr_state; u32 pat; @@ -628,14 +631,13 @@ struct kvm_x86_ops { void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc); + u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage); - - const struct trace_print_flags *exit_reasons_str; }; struct kvm_arch_async_pf { @@ -672,6 +674,8 @@ u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); extern bool tdp_enabled; +u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); + /* control of guest tsc rate supported? */ extern bool kvm_has_tsc_control; /* minimum supported tsc_khz for guests */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d52609aeeab8..a6962d9161a0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -229,6 +229,8 @@ #define MSR_IA32_APICBASE_ENABLE (1<<11) #define MSR_IA32_APICBASE_BASE (0xfffff<<12) +#define MSR_IA32_TSCDEADLINE 0x000006e0 + #define MSR_IA32_UCODE_WRITE 0x00000079 #define MSR_IA32_UCODE_REV 0x0000008b diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 4886a68f267e..fd3f9f18cf3f 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -22,27 +22,26 @@ void arch_trigger_all_cpu_backtrace(void); #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace #endif -/* - * Define some priorities for the nmi notifier call chain. - * - * Create a local nmi bit that has a higher priority than - * external nmis, because the local ones are more frequent. - * - * Also setup some default high/normal/low settings for - * subsystems to registers with. Using 4 bits to separate - * the priorities. This can go a lot higher if needed be. - */ - -#define NMI_LOCAL_SHIFT 16 /* randomly picked */ -#define NMI_LOCAL_BIT (1ULL << NMI_LOCAL_SHIFT) -#define NMI_HIGH_PRIOR (1ULL << 8) -#define NMI_NORMAL_PRIOR (1ULL << 4) -#define NMI_LOW_PRIOR (1ULL << 0) -#define NMI_LOCAL_HIGH_PRIOR (NMI_LOCAL_BIT | NMI_HIGH_PRIOR) -#define NMI_LOCAL_NORMAL_PRIOR (NMI_LOCAL_BIT | NMI_NORMAL_PRIOR) -#define NMI_LOCAL_LOW_PRIOR (NMI_LOCAL_BIT | NMI_LOW_PRIOR) +#define NMI_FLAG_FIRST 1 + +enum { + NMI_LOCAL=0, + NMI_UNKNOWN, + NMI_MAX +}; + +#define NMI_DONE 0 +#define NMI_HANDLED 1 + +typedef int (*nmi_handler_t)(unsigned int, struct pt_regs *); + +int register_nmi_handler(unsigned int, nmi_handler_t, unsigned long, + const char *); + +void unregister_nmi_handler(unsigned int, const char *); void stop_nmi(void); void restart_nmi(void); +void local_touch_nmi(void); #endif /* _ASM_X86_NMI_H */ diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 704526734bef..e38197806853 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -99,10 +99,10 @@ struct pci_raw_ops { int reg, int len, u32 val); }; -extern struct pci_raw_ops *raw_pci_ops; -extern struct pci_raw_ops *raw_pci_ext_ops; +extern const struct pci_raw_ops *raw_pci_ops; +extern const struct pci_raw_ops *raw_pci_ext_ops; -extern struct pci_raw_ops pci_direct_conf1; +extern const struct pci_raw_ops pci_direct_conf1; extern bool port_cf9_safe; /* arch_initcall level */ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 094fb30817ab..f61c62f7d5d8 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -29,6 +29,9 @@ #define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23) #define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL +#define AMD_PERFMON_EVENTSEL_GUESTONLY (1ULL << 40) +#define AMD_PERFMON_EVENTSEL_HOSTONLY (1ULL << 41) + #define AMD64_EVENTSEL_EVENT \ (ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32)) #define INTEL_ARCH_EVENT_MASK \ @@ -43,14 +46,17 @@ #define AMD64_RAW_EVENT_MASK \ (X86_RAW_EVENT_MASK | \ AMD64_EVENTSEL_EVENT) +#define AMD64_NUM_COUNTERS 4 +#define AMD64_NUM_COUNTERS_F15H 6 +#define AMD64_NUM_COUNTERS_MAX AMD64_NUM_COUNTERS_F15H -#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c +#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) -#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 0 +#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 0 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \ (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX)) -#define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6 +#define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6 /* * Intel "Architectural Performance Monitoring" CPUID @@ -110,6 +116,35 @@ union cpuid10_edx { */ #define X86_PMC_IDX_FIXED_BTS (X86_PMC_IDX_FIXED + 16) +/* + * IBS cpuid feature detection + */ + +#define IBS_CPUID_FEATURES 0x8000001b + +/* + * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but + * bit 0 is used to indicate the existence of IBS. + */ +#define IBS_CAPS_AVAIL (1U<<0) +#define IBS_CAPS_FETCHSAM (1U<<1) +#define IBS_CAPS_OPSAM (1U<<2) +#define IBS_CAPS_RDWROPCNT (1U<<3) +#define IBS_CAPS_OPCNT (1U<<4) +#define IBS_CAPS_BRNTRGT (1U<<5) +#define IBS_CAPS_OPCNTEXT (1U<<6) + +#define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \ + | IBS_CAPS_FETCHSAM \ + | IBS_CAPS_OPSAM) + +/* + * IBS APIC setup + */ +#define IBSCTL 0x1cc +#define IBSCTL_LVT_OFFSET_VALID (1ULL<<8) +#define IBSCTL_LVT_OFFSET_MASK 0x0F + /* IbsFetchCtl bits/masks */ #define IBS_FETCH_RAND_EN (1ULL<<57) #define IBS_FETCH_VAL (1ULL<<49) @@ -124,6 +159,8 @@ union cpuid10_edx { #define IBS_OP_MAX_CNT 0x0000FFFFULL #define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */ +extern u32 get_ibs_caps(void); + #ifdef CONFIG_PERF_EVENTS extern void perf_events_lapic_init(void); @@ -159,7 +196,19 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); ); \ } +struct perf_guest_switch_msr { + unsigned msr; + u64 host, guest; +}; + +extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr); #else +static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr) +{ + *nr = 0; + return NULL; +} + static inline void perf_events_lapic_init(void) { } #endif diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 0d1171c97729..b650435ffb53 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -111,6 +111,7 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; #endif + u32 microcode; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define X86_VENDOR_INTEL 0 @@ -179,7 +180,8 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx, "=b" (*ebx), "=c" (*ecx), "=d" (*edx) - : "0" (*eax), "2" (*ecx)); + : "0" (*eax), "2" (*ecx) + : "memory"); } static inline void load_cr3(pgd_t *pgdir) diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 3250e3d605d9..92f297069e87 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -23,7 +23,7 @@ void machine_real_restart(unsigned int type); #define MRR_BIOS 0 #define MRR_APM 1 -typedef void (*nmi_shootdown_cb)(int, struct die_args*); +typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); void nmi_shootdown_cpus(nmi_shootdown_cb callback); #endif /* _ASM_X86_REBOOT_H */ diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index df4cd32b4cc6..2dbe4a721ce5 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -204,13 +204,7 @@ static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem) */ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) { - long tmp = delta; - - asm volatile(LOCK_PREFIX "xadd %0,%1" - : "+r" (tmp), "+m" (sem->count) - : : "memory"); - - return tmp + delta; + return delta + xadd(&sem->count, delta); } #endif /* __KERNEL__ */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index ee67edf86fdd..972c260919a3 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -49,109 +49,49 @@ * issues and should be optimal for the uncontended case. Note the tail must be * in the high part, because a wide xadd increment of the low part would carry * up and contaminate the high part. - * - * With fewer than 2^8 possible CPUs, we can use x86's partial registers to - * save some instructions and make the code more elegant. There really isn't - * much between them in performance though, especially as locks are out of line. */ -#if (NR_CPUS < 256) -#define TICKET_SHIFT 8 - static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock) { - short inc = 0x0100; - - asm volatile ( - LOCK_PREFIX "xaddw %w0, %1\n" - "1:\t" - "cmpb %h0, %b0\n\t" - "je 2f\n\t" - "rep ; nop\n\t" - "movb %1, %b0\n\t" - /* don't need lfence here, because loads are in-order */ - "jmp 1b\n" - "2:" - : "+Q" (inc), "+m" (lock->slock) - : - : "memory", "cc"); + register struct __raw_tickets inc = { .tail = 1 }; + + inc = xadd(&lock->tickets, inc); + + for (;;) { + if (inc.head == inc.tail) + break; + cpu_relax(); + inc.head = ACCESS_ONCE(lock->tickets.head); + } + barrier(); /* make sure nothing creeps before the lock is taken */ } static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) { - int tmp, new; - - asm volatile("movzwl %2, %0\n\t" - "cmpb %h0,%b0\n\t" - "leal 0x100(%" REG_PTR_MODE "0), %1\n\t" - "jne 1f\n\t" - LOCK_PREFIX "cmpxchgw %w1,%2\n\t" - "1:" - "sete %b1\n\t" - "movzbl %b1,%0\n\t" - : "=&a" (tmp), "=&q" (new), "+m" (lock->slock) - : - : "memory", "cc"); + arch_spinlock_t old, new; + + old.tickets = ACCESS_ONCE(lock->tickets); + if (old.tickets.head != old.tickets.tail) + return 0; + + new.head_tail = old.head_tail + (1 << TICKET_SHIFT); - return tmp; + /* cmpxchg is a full barrier, so nothing can move before it */ + return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail; } +#if (NR_CPUS < 256) static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) { asm volatile(UNLOCK_LOCK_PREFIX "incb %0" - : "+m" (lock->slock) + : "+m" (lock->head_tail) : : "memory", "cc"); } #else -#define TICKET_SHIFT 16 - -static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock) -{ - int inc = 0x00010000; - int tmp; - - asm volatile(LOCK_PREFIX "xaddl %0, %1\n" - "movzwl %w0, %2\n\t" - "shrl $16, %0\n\t" - "1:\t" - "cmpl %0, %2\n\t" - "je 2f\n\t" - "rep ; nop\n\t" - "movzwl %1, %2\n\t" - /* don't need lfence here, because loads are in-order */ - "jmp 1b\n" - "2:" - : "+r" (inc), "+m" (lock->slock), "=&r" (tmp) - : - : "memory", "cc"); -} - -static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) -{ - int tmp; - int new; - - asm volatile("movl %2,%0\n\t" - "movl %0,%1\n\t" - "roll $16, %0\n\t" - "cmpl %0,%1\n\t" - "leal 0x00010000(%" REG_PTR_MODE "0), %1\n\t" - "jne 1f\n\t" - LOCK_PREFIX "cmpxchgl %1,%2\n\t" - "1:" - "sete %b1\n\t" - "movzbl %b1,%0\n\t" - : "=&a" (tmp), "=&q" (new), "+m" (lock->slock) - : - : "memory", "cc"); - - return tmp; -} - static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) { asm volatile(UNLOCK_LOCK_PREFIX "incw %0" - : "+m" (lock->slock) + : "+m" (lock->head_tail) : : "memory", "cc"); } @@ -159,16 +99,16 @@ static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) { - int tmp = ACCESS_ONCE(lock->slock); + struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); - return !!(((tmp >> TICKET_SHIFT) ^ tmp) & ((1 << TICKET_SHIFT) - 1)); + return !!(tmp.tail ^ tmp.head); } static inline int __ticket_spin_is_contended(arch_spinlock_t *lock) { - int tmp = ACCESS_ONCE(lock->slock); + struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); - return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1; + return ((tmp.tail - tmp.head) & TICKET_MASK) > 1; } #ifndef CONFIG_PARAVIRT_SPINLOCKS diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index 7c7a486fcb68..8ebd5df7451e 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -5,11 +5,29 @@ # error "please don't include this file directly" #endif +#include <linux/types.h> + +#if (CONFIG_NR_CPUS < 256) +typedef u8 __ticket_t; +typedef u16 __ticketpair_t; +#else +typedef u16 __ticket_t; +typedef u32 __ticketpair_t; +#endif + +#define TICKET_SHIFT (sizeof(__ticket_t) * 8) +#define TICKET_MASK ((__ticket_t)((1 << TICKET_SHIFT) - 1)) + typedef struct arch_spinlock { - unsigned int slock; + union { + __ticketpair_t head_tail; + struct __raw_tickets { + __ticket_t head, tail; + } tickets; + }; } arch_spinlock_t; -#define __ARCH_SPIN_LOCK_UNLOCKED { 0 } +#define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } } #include <asm/rwlock.h> diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index 593485b38ab3..599c77d38f33 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -352,10 +352,12 @@ #define __NR_syncfs 344 #define __NR_sendmmsg 345 #define __NR_setns 346 +#define __NR_process_vm_readv 347 +#define __NR_process_vm_writev 348 #ifdef __KERNEL__ -#define NR_syscalls 347 +#define NR_syscalls 349 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 201040573444..0431f193c3f2 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -624,7 +624,6 @@ __SYSCALL(__NR_vmsplice, sys_vmsplice) __SYSCALL(__NR_move_pages, sys_move_pages) #define __NR_utimensat 280 __SYSCALL(__NR_utimensat, sys_utimensat) -#define __IGNORE_getcpu /* implemented as a vsyscall */ #define __NR_epoll_pwait 281 __SYSCALL(__NR_epoll_pwait, sys_epoll_pwait) #define __NR_signalfd 282 @@ -683,6 +682,10 @@ __SYSCALL(__NR_sendmmsg, sys_sendmmsg) __SYSCALL(__NR_setns, sys_setns) #define __NR_getcpu 309 __SYSCALL(__NR_getcpu, sys_getcpu) +#define __NR_process_vm_readv 310 +__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv) +#define __NR_process_vm_writev 311 +__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 37d369859c8e..8e862aaf0d90 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -55,6 +55,7 @@ #define UV_BAU_TUNABLES_DIR "sgi_uv" #define UV_BAU_TUNABLES_FILE "bau_tunables" #define WHITESPACE " \t\n" +#define uv_mmask ((1UL << uv_hub_info->m_val) - 1) #define uv_physnodeaddr(x) ((__pa((unsigned long)(x)) & uv_mmask)) #define cpubit_isset(cpu, bau_local_cpumask) \ test_bit((cpu), (bau_local_cpumask).bits) @@ -656,11 +657,7 @@ static inline int atomic_read_short(const struct atomic_short *v) */ static inline int atom_asr(short i, struct atomic_short *v) { - short __i = i; - asm volatile(LOCK_PREFIX "xaddw %0, %1" - : "+r" (i), "+m" (v->counter) - : : "memory"); - return i + __i; + return i + xadd(&v->counter, i); } /* diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index f26544a15214..54a13aaebc40 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -46,6 +46,13 @@ * PNODE - the low N bits of the GNODE. The PNODE is the most useful variant * of the nasid for socket usage. * + * GPA - (global physical address) a socket physical address converted + * so that it can be used by the GRU as a global address. Socket + * physical addresses 1) need additional NASID (node) bits added + * to the high end of the address, and 2) unaliased if the + * partition does not have a physical address 0. In addition, on + * UV2 rev 1, GPAs need the gnode left shifted to bits 39 or 40. + * * * NumaLink Global Physical Address Format: * +--------------------------------+---------------------+ @@ -141,6 +148,8 @@ struct uv_hub_info_s { unsigned int gnode_extra; unsigned char hub_revision; unsigned char apic_pnode_shift; + unsigned char m_shift; + unsigned char n_lshift; unsigned long gnode_upper; unsigned long lowmem_remap_top; unsigned long lowmem_remap_base; @@ -177,6 +186,16 @@ static inline int is_uv2_hub(void) return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE; } +static inline int is_uv2_1_hub(void) +{ + return uv_hub_info->hub_revision == UV2_HUB_REVISION_BASE; +} + +static inline int is_uv2_2_hub(void) +{ + return uv_hub_info->hub_revision == UV2_HUB_REVISION_BASE + 1; +} + union uvh_apicid { unsigned long v; struct uvh_apicid_s { @@ -276,7 +295,10 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr) { if (paddr < uv_hub_info->lowmem_remap_top) paddr |= uv_hub_info->lowmem_remap_base; - return paddr | uv_hub_info->gnode_upper; + paddr |= uv_hub_info->gnode_upper; + paddr = ((paddr << uv_hub_info->m_shift) >> uv_hub_info->m_shift) | + ((paddr >> uv_hub_info->m_val) << uv_hub_info->n_lshift); + return paddr; } @@ -300,16 +322,19 @@ static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa) unsigned long remap_base = uv_hub_info->lowmem_remap_base; unsigned long remap_top = uv_hub_info->lowmem_remap_top; + gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) | + ((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val); + gpa = gpa & uv_hub_info->gpa_mask; if (paddr >= remap_base && paddr < remap_base + remap_top) paddr -= remap_base; return paddr; } -/* gnode -> pnode */ +/* gpa -> pnode */ static inline unsigned long uv_gpa_to_gnode(unsigned long gpa) { - return gpa >> uv_hub_info->m_val; + return gpa >> uv_hub_info->n_lshift; } /* gpa -> pnode */ @@ -320,6 +345,12 @@ static inline int uv_gpa_to_pnode(unsigned long gpa) return uv_gpa_to_gnode(gpa) & n_mask; } +/* gpa -> node offset*/ +static inline unsigned long uv_gpa_to_offset(unsigned long gpa) +{ + return (gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift; +} + /* pnode, offset --> socket virtual */ static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset) { diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2caf290e9895..31f180c21ce9 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -350,6 +350,18 @@ enum vmcs_field { #define DEBUG_REG_ACCESS_REG(eq) (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */ +/* + * Exit Qualifications for APIC-Access + */ +#define APIC_ACCESS_OFFSET 0xfff /* 11:0, offset within the APIC page */ +#define APIC_ACCESS_TYPE 0xf000 /* 15:12, access type */ +#define TYPE_LINEAR_APIC_INST_READ (0 << 12) +#define TYPE_LINEAR_APIC_INST_WRITE (1 << 12) +#define TYPE_LINEAR_APIC_INST_FETCH (2 << 12) +#define TYPE_LINEAR_APIC_EVENT (3 << 12) +#define TYPE_PHYSICAL_APIC_EVENT (10 << 12) +#define TYPE_PHYSICAL_APIC_INST (15 << 12) + /* segment AR */ #define SEGMENT_AR_L_MASK (1 << 13) diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 7ff4669580cf..c34f96c2f7a0 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -12,6 +12,7 @@ #include <asm/pgtable.h> #include <xen/interface/xen.h> +#include <xen/grant_table.h> #include <xen/features.h> /* Xen machine address */ @@ -48,14 +49,11 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s, unsigned long pfn_e); extern int m2p_add_override(unsigned long mfn, struct page *page, - bool clear_pte); + struct gnttab_map_grant_ref *kmap_op); extern int m2p_remove_override(struct page *page, bool clear_pte); extern struct page *m2p_find_override(unsigned long mfn); extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); -#ifdef CONFIG_XEN_DEBUG_FS -extern int p2m_dump_show(struct seq_file *m, void *v); -#endif static inline unsigned long pfn_to_mfn(unsigned long pfn) { unsigned long mfn; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 82f2912155a5..8baca3c4871c 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -19,7 +19,7 @@ endif obj-y := process_$(BITS).o signal.o entry_$(BITS).o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o -obj-y += time.o ioport.o ldt.o dumpstack.o +obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 8a439d364b94..b1e7c7f7a0af 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -5,7 +5,7 @@ * This allows to use PCI devices that only support 32bit addresses on systems * with more than 4GB. * - * See Documentation/PCI/PCI-DMA-mapping.txt for the interface specification. + * See Documentation/DMA-API-HOWTO.txt for the interface specification. * * Copyright 2002 Andi Kleen, SuSE Labs. * Subject to the GNU General Public License v2 only. diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 52fa56399a50..a2fd72e0ab35 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1437,27 +1437,21 @@ void enable_x2apic(void) int __init enable_IR(void) { -#ifdef CONFIG_INTR_REMAP +#ifdef CONFIG_IRQ_REMAP if (!intr_remapping_supported()) { pr_debug("intr-remapping not supported\n"); - return 0; + return -1; } if (!x2apic_preenabled && skip_ioapic_setup) { pr_info("Skipped enabling intr-remap because of skipping " "io-apic setup\n"); - return 0; + return -1; } - if (enable_intr_remapping(x2apic_supported())) - return 0; - - pr_info("Enabled Interrupt-remapping\n"); - - return 1; - + return enable_intr_remapping(); #endif - return 0; + return -1; } void __init enable_IR_x2apic(void) @@ -1481,11 +1475,11 @@ void __init enable_IR_x2apic(void) mask_ioapic_entries(); if (dmar_table_init_ret) - ret = 0; + ret = -1; else ret = enable_IR(); - if (!ret) { + if (ret < 0) { /* IR is required if there is APIC ID > 255 even when running * under KVM */ @@ -1499,6 +1493,9 @@ void __init enable_IR_x2apic(void) x2apic_force_phys(); } + if (ret == IRQ_REMAP_XAPIC_MODE) + goto nox2apic; + x2apic_enabled = 1; if (x2apic_supported() && !x2apic_mode) { @@ -1508,19 +1505,21 @@ void __init enable_IR_x2apic(void) } nox2apic: - if (!ret) /* IR enabling failed */ + if (ret < 0) /* IR enabling failed */ restore_ioapic_entries(); legacy_pic->restore_mask(); local_irq_restore(flags); out: - if (x2apic_enabled) + if (x2apic_enabled || !x2apic_supported()) return; if (x2apic_preenabled) panic("x2apic: enabled by BIOS but kernel init failed."); - else if (cpu_has_x2apic) - pr_info("Not enabling x2apic, Intr-remapping init failed.\n"); + else if (ret == IRQ_REMAP_XAPIC_MODE) + pr_info("x2apic not enabled, IRQ remapping is in xapic mode\n"); + else if (ret < 0) + pr_info("x2apic not enabled, IRQ remapping init failed\n"); } #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index efd737e827f4..521bead01137 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -255,12 +255,24 @@ static struct apic apic_bigsmp = { .x86_32_early_logical_apicid = bigsmp_early_logical_apicid, }; -struct apic * __init generic_bigsmp_probe(void) +void __init generic_bigsmp_probe(void) { - if (probe_bigsmp()) - return &apic_bigsmp; + unsigned int cpu; - return NULL; + if (!probe_bigsmp()) + return; + + apic = &apic_bigsmp; + + for_each_possible_cpu(cpu) { + if (early_per_cpu(x86_cpu_to_logical_apicid, + cpu) == BAD_APICID) + continue; + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = + bigsmp_early_logical_apicid(cpu); + } + + pr_info("Overriding APIC driver with %s\n", apic_bigsmp.name); } apic_driver(apic_bigsmp); diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index d5e57db0f7be..31cb9ae992b7 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -60,22 +60,10 @@ void arch_trigger_all_cpu_backtrace(void) } static int __kprobes -arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self, - unsigned long cmd, void *__args) +arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) { - struct die_args *args = __args; - struct pt_regs *regs; int cpu; - switch (cmd) { - case DIE_NMI: - break; - - default: - return NOTIFY_DONE; - } - - regs = args->regs; cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { @@ -86,21 +74,16 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self, show_regs(regs); arch_spin_unlock(&lock); cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); - return NOTIFY_STOP; + return NMI_HANDLED; } - return NOTIFY_DONE; + return NMI_DONE; } -static __read_mostly struct notifier_block backtrace_notifier = { - .notifier_call = arch_trigger_all_cpu_backtrace_handler, - .next = NULL, - .priority = NMI_LOCAL_LOW_PRIOR, -}; - static int __init register_trigger_all_cpu_backtrace(void) { - register_die_notifier(&backtrace_notifier); + register_nmi_handler(NMI_LOCAL, arch_trigger_all_cpu_backtrace_handler, + 0, "arch_bt"); return 0; } early_initcall(register_trigger_all_cpu_backtrace); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 8eb863e27ea6..3c31fa98af6d 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -92,21 +92,21 @@ static struct ioapic { DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1); } ioapics[MAX_IO_APICS]; -#define mpc_ioapic_ver(id) ioapics[id].mp_config.apicver +#define mpc_ioapic_ver(ioapic_idx) ioapics[ioapic_idx].mp_config.apicver -int mpc_ioapic_id(int id) +int mpc_ioapic_id(int ioapic_idx) { - return ioapics[id].mp_config.apicid; + return ioapics[ioapic_idx].mp_config.apicid; } -unsigned int mpc_ioapic_addr(int id) +unsigned int mpc_ioapic_addr(int ioapic_idx) { - return ioapics[id].mp_config.apicaddr; + return ioapics[ioapic_idx].mp_config.apicaddr; } -struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int id) +struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx) { - return &ioapics[id].gsi_config; + return &ioapics[ioapic_idx].gsi_config; } int nr_ioapics; @@ -186,11 +186,7 @@ static struct irq_pin_list *alloc_irq_pin_list(int node) /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */ -#ifdef CONFIG_SPARSE_IRQ static struct irq_cfg irq_cfgx[NR_IRQS_LEGACY]; -#else -static struct irq_cfg irq_cfgx[NR_IRQS]; -#endif int __init arch_early_irq_init(void) { @@ -234,7 +230,6 @@ int __init arch_early_irq_init(void) return 0; } -#ifdef CONFIG_SPARSE_IRQ static struct irq_cfg *irq_cfg(unsigned int irq) { return irq_get_chip_data(irq); @@ -269,22 +264,6 @@ static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) kfree(cfg); } -#else - -struct irq_cfg *irq_cfg(unsigned int irq) -{ - return irq < nr_irqs ? irq_cfgx + irq : NULL; -} - -static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node) -{ - return irq_cfgx + irq; -} - -static inline void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) { } - -#endif - static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) { int res = irq_alloc_desc_at(at, node); @@ -394,13 +373,21 @@ union entry_union { struct IO_APIC_route_entry entry; }; +static struct IO_APIC_route_entry __ioapic_read_entry(int apic, int pin) +{ + union entry_union eu; + + eu.w1 = io_apic_read(apic, 0x10 + 2 * pin); + eu.w2 = io_apic_read(apic, 0x11 + 2 * pin); + return eu.entry; +} + static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin) { union entry_union eu; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - eu.w1 = io_apic_read(apic, 0x10 + 2 * pin); - eu.w2 = io_apic_read(apic, 0x11 + 2 * pin); + eu.entry = __ioapic_read_entry(apic, pin); raw_spin_unlock_irqrestore(&ioapic_lock, flags); return eu.entry; } @@ -529,18 +516,6 @@ static void io_apic_modify_irq(struct irq_cfg *cfg, __io_apic_modify_irq(entry, mask_and, mask_or, final); } -static void __mask_and_edge_IO_APIC_irq(struct irq_pin_list *entry) -{ - __io_apic_modify_irq(entry, ~IO_APIC_REDIR_LEVEL_TRIGGER, - IO_APIC_REDIR_MASKED, NULL); -} - -static void __unmask_and_level_IO_APIC_irq(struct irq_pin_list *entry) -{ - __io_apic_modify_irq(entry, ~IO_APIC_REDIR_MASKED, - IO_APIC_REDIR_LEVEL_TRIGGER, NULL); -} - static void io_apic_sync(struct irq_pin_list *entry) { /* @@ -585,6 +560,66 @@ static void unmask_ioapic_irq(struct irq_data *data) unmask_ioapic(data->chip_data); } +/* + * IO-APIC versions below 0x20 don't support EOI register. + * For the record, here is the information about various versions: + * 0Xh 82489DX + * 1Xh I/OAPIC or I/O(x)APIC which are not PCI 2.2 Compliant + * 2Xh I/O(x)APIC which is PCI 2.2 Compliant + * 30h-FFh Reserved + * + * Some of the Intel ICH Specs (ICH2 to ICH5) documents the io-apic + * version as 0x2. This is an error with documentation and these ICH chips + * use io-apic's of version 0x20. + * + * For IO-APIC's with EOI register, we use that to do an explicit EOI. + * Otherwise, we simulate the EOI message manually by changing the trigger + * mode to edge and then back to level, with RTE being masked during this. + */ +static void __eoi_ioapic_pin(int apic, int pin, int vector, struct irq_cfg *cfg) +{ + if (mpc_ioapic_ver(apic) >= 0x20) { + /* + * Intr-remapping uses pin number as the virtual vector + * in the RTE. Actual vector is programmed in + * intr-remapping table entry. Hence for the io-apic + * EOI we use the pin number. + */ + if (cfg && irq_remapped(cfg)) + io_apic_eoi(apic, pin); + else + io_apic_eoi(apic, vector); + } else { + struct IO_APIC_route_entry entry, entry1; + + entry = entry1 = __ioapic_read_entry(apic, pin); + + /* + * Mask the entry and change the trigger mode to edge. + */ + entry1.mask = 1; + entry1.trigger = IOAPIC_EDGE; + + __ioapic_write_entry(apic, pin, entry1); + + /* + * Restore the previous level triggered entry. + */ + __ioapic_write_entry(apic, pin, entry); + } +} + +static void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) +{ + struct irq_pin_list *entry; + unsigned long flags; + + raw_spin_lock_irqsave(&ioapic_lock, flags); + for_each_irq_pin(entry, cfg->irq_2_pin) + __eoi_ioapic_pin(entry->apic, entry->pin, cfg->vector, cfg); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); +} + static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) { struct IO_APIC_route_entry entry; @@ -593,10 +628,44 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) entry = ioapic_read_entry(apic, pin); if (entry.delivery_mode == dest_SMI) return; + + /* + * Make sure the entry is masked and re-read the contents to check + * if it is a level triggered pin and if the remote-IRR is set. + */ + if (!entry.mask) { + entry.mask = 1; + ioapic_write_entry(apic, pin, entry); + entry = ioapic_read_entry(apic, pin); + } + + if (entry.irr) { + unsigned long flags; + + /* + * Make sure the trigger mode is set to level. Explicit EOI + * doesn't clear the remote-IRR if the trigger mode is not + * set to level. + */ + if (!entry.trigger) { + entry.trigger = IOAPIC_LEVEL; + ioapic_write_entry(apic, pin, entry); + } + + raw_spin_lock_irqsave(&ioapic_lock, flags); + __eoi_ioapic_pin(apic, pin, entry.vector, NULL); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); + } + /* - * Disable it in the IO-APIC irq-routing table: + * Clear the rest of the bits in the IO-APIC RTE except for the mask + * bit. */ ioapic_mask_entry(apic, pin); + entry = ioapic_read_entry(apic, pin); + if (entry.irr) + printk(KERN_ERR "Unable to reset IRR for apic: %d, pin :%d\n", + mpc_ioapic_id(apic), pin); } static void clear_IO_APIC (void) @@ -712,13 +781,13 @@ int restore_ioapic_entries(void) /* * Find the IRQ entry number of a certain pin. */ -static int find_irq_entry(int apic, int pin, int type) +static int find_irq_entry(int ioapic_idx, int pin, int type) { int i; for (i = 0; i < mp_irq_entries; i++) if (mp_irqs[i].irqtype == type && - (mp_irqs[i].dstapic == mpc_ioapic_id(apic) || + (mp_irqs[i].dstapic == mpc_ioapic_id(ioapic_idx) || mp_irqs[i].dstapic == MP_APIC_ALL) && mp_irqs[i].dstirq == pin) return i; @@ -757,12 +826,13 @@ static int __init find_isa_irq_apic(int irq, int type) (mp_irqs[i].srcbusirq == irq)) break; } + if (i < mp_irq_entries) { - int apic; - for(apic = 0; apic < nr_ioapics; apic++) { - if (mpc_ioapic_id(apic) == mp_irqs[i].dstapic) - return apic; - } + int ioapic_idx; + + for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) + if (mpc_ioapic_id(ioapic_idx) == mp_irqs[i].dstapic) + return ioapic_idx; } return -1; @@ -977,7 +1047,7 @@ static int pin_2_irq(int idx, int apic, int pin) int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin, struct io_apic_irq_attr *irq_attr) { - int apic, i, best_guess = -1; + int ioapic_idx, i, best_guess = -1; apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n", @@ -990,8 +1060,8 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin, for (i = 0; i < mp_irq_entries; i++) { int lbus = mp_irqs[i].srcbus; - for (apic = 0; apic < nr_ioapics; apic++) - if (mpc_ioapic_id(apic) == mp_irqs[i].dstapic || + for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) + if (mpc_ioapic_id(ioapic_idx) == mp_irqs[i].dstapic || mp_irqs[i].dstapic == MP_APIC_ALL) break; @@ -999,13 +1069,13 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin, !mp_irqs[i].irqtype && (bus == lbus) && (slot == ((mp_irqs[i].srcbusirq >> 2) & 0x1f))) { - int irq = pin_2_irq(i, apic, mp_irqs[i].dstirq); + int irq = pin_2_irq(i, ioapic_idx, mp_irqs[i].dstirq); - if (!(apic || IO_APIC_IRQ(irq))) + if (!(ioapic_idx || IO_APIC_IRQ(irq))) continue; if (pin == (mp_irqs[i].srcbusirq & 3)) { - set_io_apic_irq_attr(irq_attr, apic, + set_io_apic_irq_attr(irq_attr, ioapic_idx, mp_irqs[i].dstirq, irq_trigger(i), irq_polarity(i)); @@ -1016,7 +1086,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin, * best-guess fuzzy result for broken mptables. */ if (best_guess < 0) { - set_io_apic_irq_attr(irq_attr, apic, + set_io_apic_irq_attr(irq_attr, ioapic_idx, mp_irqs[i].dstirq, irq_trigger(i), irq_polarity(i)); @@ -1202,7 +1272,6 @@ void __setup_vector_irq(int cpu) } static struct irq_chip ioapic_chip; -static struct irq_chip ir_ioapic_chip; #ifdef CONFIG_X86_32 static inline int IO_APIC_irq_trigger(int irq) @@ -1246,7 +1315,7 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg, if (irq_remapped(cfg)) { irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - chip = &ir_ioapic_chip; + irq_remap_modify_chip_defaults(chip); fasteoi = trigger != 0; } @@ -1255,77 +1324,100 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg, fasteoi ? "fasteoi" : "edge"); } -static int setup_ioapic_entry(int apic_id, int irq, - struct IO_APIC_route_entry *entry, - unsigned int destination, int trigger, - int polarity, int vector, int pin) + +static int setup_ir_ioapic_entry(int irq, + struct IR_IO_APIC_route_entry *entry, + unsigned int destination, int vector, + struct io_apic_irq_attr *attr) { - /* - * add it to the IO-APIC irq-routing table: - */ - memset(entry,0,sizeof(*entry)); + int index; + struct irte irte; + int ioapic_id = mpc_ioapic_id(attr->ioapic); + struct intel_iommu *iommu = map_ioapic_to_ir(ioapic_id); - if (intr_remapping_enabled) { - struct intel_iommu *iommu = map_ioapic_to_ir(apic_id); - struct irte irte; - struct IR_IO_APIC_route_entry *ir_entry = - (struct IR_IO_APIC_route_entry *) entry; - int index; + if (!iommu) { + pr_warn("No mapping iommu for ioapic %d\n", ioapic_id); + return -ENODEV; + } - if (!iommu) - panic("No mapping iommu for ioapic %d\n", apic_id); + index = alloc_irte(iommu, irq, 1); + if (index < 0) { + pr_warn("Failed to allocate IRTE for ioapic %d\n", ioapic_id); + return -ENOMEM; + } - index = alloc_irte(iommu, irq, 1); - if (index < 0) - panic("Failed to allocate IRTE for ioapic %d\n", apic_id); + prepare_irte(&irte, vector, destination); - prepare_irte(&irte, vector, destination); + /* Set source-id of interrupt request */ + set_ioapic_sid(&irte, ioapic_id); - /* Set source-id of interrupt request */ - set_ioapic_sid(&irte, apic_id); + modify_irte(irq, &irte); - modify_irte(irq, &irte); + apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: " + "Set IRTE entry (P:%d FPD:%d Dst_Mode:%d " + "Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X " + "Avail:%X Vector:%02X Dest:%08X " + "SID:%04X SQ:%X SVT:%X)\n", + attr->ioapic, irte.present, irte.fpd, irte.dst_mode, + irte.redir_hint, irte.trigger_mode, irte.dlvry_mode, + irte.avail, irte.vector, irte.dest_id, + irte.sid, irte.sq, irte.svt); + + memset(entry, 0, sizeof(*entry)); + + entry->index2 = (index >> 15) & 0x1; + entry->zero = 0; + entry->format = 1; + entry->index = (index & 0x7fff); + /* + * IO-APIC RTE will be configured with virtual vector. + * irq handler will do the explicit EOI to the io-apic. + */ + entry->vector = attr->ioapic_pin; + entry->mask = 0; /* enable IRQ */ + entry->trigger = attr->trigger; + entry->polarity = attr->polarity; - ir_entry->index2 = (index >> 15) & 0x1; - ir_entry->zero = 0; - ir_entry->format = 1; - ir_entry->index = (index & 0x7fff); - /* - * IO-APIC RTE will be configured with virtual vector. - * irq handler will do the explicit EOI to the io-apic. - */ - ir_entry->vector = pin; - - apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: " - "Set IRTE entry (P:%d FPD:%d Dst_Mode:%d " - "Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X " - "Avail:%X Vector:%02X Dest:%08X " - "SID:%04X SQ:%X SVT:%X)\n", - apic_id, irte.present, irte.fpd, irte.dst_mode, - irte.redir_hint, irte.trigger_mode, irte.dlvry_mode, - irte.avail, irte.vector, irte.dest_id, - irte.sid, irte.sq, irte.svt); - } else { - entry->delivery_mode = apic->irq_delivery_mode; - entry->dest_mode = apic->irq_dest_mode; - entry->dest = destination; - entry->vector = vector; - } + /* Mask level triggered irqs. + * Use IRQ_DELAYED_DISABLE for edge triggered irqs. + */ + if (attr->trigger) + entry->mask = 1; - entry->mask = 0; /* enable IRQ */ - entry->trigger = trigger; - entry->polarity = polarity; + return 0; +} - /* Mask level triggered irqs. +static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry, + unsigned int destination, int vector, + struct io_apic_irq_attr *attr) +{ + if (intr_remapping_enabled) + return setup_ir_ioapic_entry(irq, + (struct IR_IO_APIC_route_entry *)entry, + destination, vector, attr); + + memset(entry, 0, sizeof(*entry)); + + entry->delivery_mode = apic->irq_delivery_mode; + entry->dest_mode = apic->irq_dest_mode; + entry->dest = destination; + entry->vector = vector; + entry->mask = 0; /* enable IRQ */ + entry->trigger = attr->trigger; + entry->polarity = attr->polarity; + + /* + * Mask level triggered irqs. * Use IRQ_DELAYED_DISABLE for edge triggered irqs. */ - if (trigger) + if (attr->trigger) entry->mask = 1; + return 0; } -static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq, - struct irq_cfg *cfg, int trigger, int polarity) +static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, + struct io_apic_irq_attr *attr) { struct IO_APIC_route_entry entry; unsigned int dest; @@ -1348,49 +1440,48 @@ static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq, apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " "IRQ %d Mode:%i Active:%i Dest:%d)\n", - apic_id, mpc_ioapic_id(apic_id), pin, cfg->vector, - irq, trigger, polarity, dest); - + attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin, + cfg->vector, irq, attr->trigger, attr->polarity, dest); - if (setup_ioapic_entry(mpc_ioapic_id(apic_id), irq, &entry, - dest, trigger, polarity, cfg->vector, pin)) { - printk("Failed to setup ioapic entry for ioapic %d, pin %d\n", - mpc_ioapic_id(apic_id), pin); + if (setup_ioapic_entry(irq, &entry, dest, cfg->vector, attr)) { + pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", + mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); __clear_irq_vector(irq, cfg); + return; } - ioapic_register_intr(irq, cfg, trigger); + ioapic_register_intr(irq, cfg, attr->trigger); if (irq < legacy_pic->nr_legacy_irqs) legacy_pic->mask(irq); - ioapic_write_entry(apic_id, pin, entry); + ioapic_write_entry(attr->ioapic, attr->ioapic_pin, entry); } -static bool __init io_apic_pin_not_connected(int idx, int apic_id, int pin) +static bool __init io_apic_pin_not_connected(int idx, int ioapic_idx, int pin) { if (idx != -1) return false; apic_printk(APIC_VERBOSE, KERN_DEBUG " apic %d pin %d not connected\n", - mpc_ioapic_id(apic_id), pin); + mpc_ioapic_id(ioapic_idx), pin); return true; } -static void __init __io_apic_setup_irqs(unsigned int apic_id) +static void __init __io_apic_setup_irqs(unsigned int ioapic_idx) { int idx, node = cpu_to_node(0); struct io_apic_irq_attr attr; unsigned int pin, irq; - for (pin = 0; pin < ioapics[apic_id].nr_registers; pin++) { - idx = find_irq_entry(apic_id, pin, mp_INT); - if (io_apic_pin_not_connected(idx, apic_id, pin)) + for (pin = 0; pin < ioapics[ioapic_idx].nr_registers; pin++) { + idx = find_irq_entry(ioapic_idx, pin, mp_INT); + if (io_apic_pin_not_connected(idx, ioapic_idx, pin)) continue; - irq = pin_2_irq(idx, apic_id, pin); + irq = pin_2_irq(idx, ioapic_idx, pin); - if ((apic_id > 0) && (irq > 16)) + if ((ioapic_idx > 0) && (irq > 16)) continue; /* @@ -1398,10 +1489,10 @@ static void __init __io_apic_setup_irqs(unsigned int apic_id) * installed and if it returns 1: */ if (apic->multi_timer_check && - apic->multi_timer_check(apic_id, irq)) + apic->multi_timer_check(ioapic_idx, irq)) continue; - set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx), + set_io_apic_irq_attr(&attr, ioapic_idx, pin, irq_trigger(idx), irq_polarity(idx)); io_apic_setup_irq_pin(irq, node, &attr); @@ -1410,12 +1501,12 @@ static void __init __io_apic_setup_irqs(unsigned int apic_id) static void __init setup_IO_APIC_irqs(void) { - unsigned int apic_id; + unsigned int ioapic_idx; apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); - for (apic_id = 0; apic_id < nr_ioapics; apic_id++) - __io_apic_setup_irqs(apic_id); + for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) + __io_apic_setup_irqs(ioapic_idx); } /* @@ -1425,28 +1516,28 @@ static void __init setup_IO_APIC_irqs(void) */ void setup_IO_APIC_irq_extra(u32 gsi) { - int apic_id = 0, pin, idx, irq, node = cpu_to_node(0); + int ioapic_idx = 0, pin, idx, irq, node = cpu_to_node(0); struct io_apic_irq_attr attr; /* * Convert 'gsi' to 'ioapic.pin'. */ - apic_id = mp_find_ioapic(gsi); - if (apic_id < 0) + ioapic_idx = mp_find_ioapic(gsi); + if (ioapic_idx < 0) return; - pin = mp_find_ioapic_pin(apic_id, gsi); - idx = find_irq_entry(apic_id, pin, mp_INT); + pin = mp_find_ioapic_pin(ioapic_idx, gsi); + idx = find_irq_entry(ioapic_idx, pin, mp_INT); if (idx == -1) return; - irq = pin_2_irq(idx, apic_id, pin); + irq = pin_2_irq(idx, ioapic_idx, pin); /* Only handle the non legacy irqs on secondary ioapics */ - if (apic_id == 0 || irq < NR_IRQS_LEGACY) + if (ioapic_idx == 0 || irq < NR_IRQS_LEGACY) return; - set_io_apic_irq_attr(&attr, apic_id, pin, irq_trigger(idx), + set_io_apic_irq_attr(&attr, ioapic_idx, pin, irq_trigger(idx), irq_polarity(idx)); io_apic_setup_irq_pin_once(irq, node, &attr); @@ -1455,8 +1546,8 @@ void setup_IO_APIC_irq_extra(u32 gsi) /* * Set up the timer pin, possibly with the 8259A-master behind. */ -static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin, - int vector) +static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, + unsigned int pin, int vector) { struct IO_APIC_route_entry entry; @@ -1487,45 +1578,29 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic_id, unsigned int pin, /* * Add it to the IO-APIC irq-routing table: */ - ioapic_write_entry(apic_id, pin, entry); + ioapic_write_entry(ioapic_idx, pin, entry); } - -__apicdebuginit(void) print_IO_APIC(void) +__apicdebuginit(void) print_IO_APIC(int ioapic_idx) { - int apic, i; + int i; union IO_APIC_reg_00 reg_00; union IO_APIC_reg_01 reg_01; union IO_APIC_reg_02 reg_02; union IO_APIC_reg_03 reg_03; unsigned long flags; - struct irq_cfg *cfg; - unsigned int irq; - - printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); - for (i = 0; i < nr_ioapics; i++) - printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n", - mpc_ioapic_id(i), ioapics[i].nr_registers); - - /* - * We are a bit conservative about what we expect. We have to - * know about every hardware change ASAP. - */ - printk(KERN_INFO "testing the IO APIC.......................\n"); - - for (apic = 0; apic < nr_ioapics; apic++) { raw_spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic, 0); - reg_01.raw = io_apic_read(apic, 1); + reg_00.raw = io_apic_read(ioapic_idx, 0); + reg_01.raw = io_apic_read(ioapic_idx, 1); if (reg_01.bits.version >= 0x10) - reg_02.raw = io_apic_read(apic, 2); + reg_02.raw = io_apic_read(ioapic_idx, 2); if (reg_01.bits.version >= 0x20) - reg_03.raw = io_apic_read(apic, 3); + reg_03.raw = io_apic_read(ioapic_idx, 3); raw_spin_unlock_irqrestore(&ioapic_lock, flags); printk("\n"); - printk(KERN_DEBUG "IO APIC #%d......\n", mpc_ioapic_id(apic)); + printk(KERN_DEBUG "IO APIC #%d......\n", mpc_ioapic_id(ioapic_idx)); printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw); printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID); printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type); @@ -1575,7 +1650,7 @@ __apicdebuginit(void) print_IO_APIC(void) struct IO_APIC_route_entry entry; struct IR_IO_APIC_route_entry *ir_entry; - entry = ioapic_read_entry(apic, i); + entry = ioapic_read_entry(ioapic_idx, i); ir_entry = (struct IR_IO_APIC_route_entry *) &entry; printk(KERN_DEBUG " %02x %04X ", i, @@ -1596,7 +1671,7 @@ __apicdebuginit(void) print_IO_APIC(void) } else { struct IO_APIC_route_entry entry; - entry = ioapic_read_entry(apic, i); + entry = ioapic_read_entry(ioapic_idx, i); printk(KERN_DEBUG " %02x %02X ", i, entry.dest @@ -1614,7 +1689,28 @@ __apicdebuginit(void) print_IO_APIC(void) ); } } - } +} + +__apicdebuginit(void) print_IO_APICs(void) +{ + int ioapic_idx; + struct irq_cfg *cfg; + unsigned int irq; + + printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); + for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) + printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n", + mpc_ioapic_id(ioapic_idx), + ioapics[ioapic_idx].nr_registers); + + /* + * We are a bit conservative about what we expect. We have to + * know about every hardware change ASAP. + */ + printk(KERN_INFO "testing the IO APIC.......................\n"); + + for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) + print_IO_APIC(ioapic_idx); printk(KERN_DEBUG "IRQ to pin mappings:\n"); for_each_active_irq(irq) { @@ -1633,8 +1729,6 @@ __apicdebuginit(void) print_IO_APIC(void) } printk(KERN_INFO ".................................... done.\n"); - - return; } __apicdebuginit(void) print_APIC_field(int base) @@ -1828,7 +1922,7 @@ __apicdebuginit(int) print_ICs(void) return 0; print_local_APICs(show_lapic); - print_IO_APIC(); + print_IO_APICs(); return 0; } @@ -1953,7 +2047,7 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) { union IO_APIC_reg_00 reg_00; physid_mask_t phys_id_present_map; - int apic_id; + int ioapic_idx; int i; unsigned char old_id; unsigned long flags; @@ -1967,21 +2061,20 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) /* * Set the IOAPIC ID to the value stored in the MPC table. */ - for (apic_id = 0; apic_id < nr_ioapics; apic_id++) { - + for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) { /* Read the register 0 value */ raw_spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic_id, 0); + reg_00.raw = io_apic_read(ioapic_idx, 0); raw_spin_unlock_irqrestore(&ioapic_lock, flags); - old_id = mpc_ioapic_id(apic_id); + old_id = mpc_ioapic_id(ioapic_idx); - if (mpc_ioapic_id(apic_id) >= get_physical_broadcast()) { + if (mpc_ioapic_id(ioapic_idx) >= get_physical_broadcast()) { printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n", - apic_id, mpc_ioapic_id(apic_id)); + ioapic_idx, mpc_ioapic_id(ioapic_idx)); printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", reg_00.bits.ID); - ioapics[apic_id].mp_config.apicid = reg_00.bits.ID; + ioapics[ioapic_idx].mp_config.apicid = reg_00.bits.ID; } /* @@ -1990,9 +2083,9 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) * 'stuck on smp_invalidate_needed IPI wait' messages. */ if (apic->check_apicid_used(&phys_id_present_map, - mpc_ioapic_id(apic_id))) { + mpc_ioapic_id(ioapic_idx))) { printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n", - apic_id, mpc_ioapic_id(apic_id)); + ioapic_idx, mpc_ioapic_id(ioapic_idx)); for (i = 0; i < get_physical_broadcast(); i++) if (!physid_isset(i, phys_id_present_map)) break; @@ -2001,14 +2094,14 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", i); physid_set(i, phys_id_present_map); - ioapics[apic_id].mp_config.apicid = i; + ioapics[ioapic_idx].mp_config.apicid = i; } else { physid_mask_t tmp; - apic->apicid_to_cpu_present(mpc_ioapic_id(apic_id), + apic->apicid_to_cpu_present(mpc_ioapic_id(ioapic_idx), &tmp); apic_printk(APIC_VERBOSE, "Setting %d in the " "phys_id_present_map\n", - mpc_ioapic_id(apic_id)); + mpc_ioapic_id(ioapic_idx)); physids_or(phys_id_present_map, phys_id_present_map, tmp); } @@ -2016,35 +2109,35 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) * We need to adjust the IRQ routing table * if the ID changed. */ - if (old_id != mpc_ioapic_id(apic_id)) + if (old_id != mpc_ioapic_id(ioapic_idx)) for (i = 0; i < mp_irq_entries; i++) if (mp_irqs[i].dstapic == old_id) mp_irqs[i].dstapic - = mpc_ioapic_id(apic_id); + = mpc_ioapic_id(ioapic_idx); /* * Update the ID register according to the right value * from the MPC table if they are different. */ - if (mpc_ioapic_id(apic_id) == reg_00.bits.ID) + if (mpc_ioapic_id(ioapic_idx) == reg_00.bits.ID) continue; apic_printk(APIC_VERBOSE, KERN_INFO "...changing IO-APIC physical APIC ID to %d ...", - mpc_ioapic_id(apic_id)); + mpc_ioapic_id(ioapic_idx)); - reg_00.bits.ID = mpc_ioapic_id(apic_id); + reg_00.bits.ID = mpc_ioapic_id(ioapic_idx); raw_spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic_id, 0, reg_00.raw); + io_apic_write(ioapic_idx, 0, reg_00.raw); raw_spin_unlock_irqrestore(&ioapic_lock, flags); /* * Sanity check */ raw_spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic_id, 0); + reg_00.raw = io_apic_read(ioapic_idx, 0); raw_spin_unlock_irqrestore(&ioapic_lock, flags); - if (reg_00.bits.ID != mpc_ioapic_id(apic_id)) + if (reg_00.bits.ID != mpc_ioapic_id(ioapic_idx)) printk("could not set ID!\n"); else apic_printk(APIC_VERBOSE, " ok.\n"); @@ -2255,7 +2348,7 @@ ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, return ret; } -#ifdef CONFIG_INTR_REMAP +#ifdef CONFIG_IRQ_REMAP /* * Migrate the IO-APIC irq in the presence of intr-remapping. @@ -2267,6 +2360,9 @@ ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, * updated vector information), by using a virtual vector (io-apic pin number). * Real vector that is used for interrupting cpu will be coming from * the interrupt-remapping table entry. + * + * As the migration is a simple atomic update of IRTE, the same mechanism + * is used to migrate MSI irq's in the presence of interrupt-remapping. */ static int ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, @@ -2291,10 +2387,16 @@ ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, irte.dest_id = IRTE_DEST(dest); /* - * Modified the IRTE and flushes the Interrupt entry cache. + * Atomically updates the IRTE with the new destination, vector + * and flushes the interrupt entry cache. */ modify_irte(irq, &irte); + /* + * After this point, all the interrupts will start arriving + * at the new destination. So, time to cleanup the previous + * vector allocation. + */ if (cfg->move_in_progress) send_cleanup_vector(cfg); @@ -2407,48 +2509,6 @@ static void ack_apic_edge(struct irq_data *data) atomic_t irq_mis_count; -/* - * IO-APIC versions below 0x20 don't support EOI register. - * For the record, here is the information about various versions: - * 0Xh 82489DX - * 1Xh I/OAPIC or I/O(x)APIC which are not PCI 2.2 Compliant - * 2Xh I/O(x)APIC which is PCI 2.2 Compliant - * 30h-FFh Reserved - * - * Some of the Intel ICH Specs (ICH2 to ICH5) documents the io-apic - * version as 0x2. This is an error with documentation and these ICH chips - * use io-apic's of version 0x20. - * - * For IO-APIC's with EOI register, we use that to do an explicit EOI. - * Otherwise, we simulate the EOI message manually by changing the trigger - * mode to edge and then back to level, with RTE being masked during this. -*/ -static void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) -{ - struct irq_pin_list *entry; - unsigned long flags; - - raw_spin_lock_irqsave(&ioapic_lock, flags); - for_each_irq_pin(entry, cfg->irq_2_pin) { - if (mpc_ioapic_ver(entry->apic) >= 0x20) { - /* - * Intr-remapping uses pin number as the virtual vector - * in the RTE. Actual vector is programmed in - * intr-remapping table entry. Hence for the io-apic - * EOI we use the pin number. - */ - if (irq_remapped(cfg)) - io_apic_eoi(entry->apic, entry->pin); - else - io_apic_eoi(entry->apic, cfg->vector); - } else { - __mask_and_edge_IO_APIC_irq(entry); - __unmask_and_level_IO_APIC_irq(entry); - } - } - raw_spin_unlock_irqrestore(&ioapic_lock, flags); -} - static void ack_apic_level(struct irq_data *data) { struct irq_cfg *cfg = data->chip_data; @@ -2552,7 +2612,7 @@ static void ack_apic_level(struct irq_data *data) } } -#ifdef CONFIG_INTR_REMAP +#ifdef CONFIG_IRQ_REMAP static void ir_ack_apic_edge(struct irq_data *data) { ack_APIC_irq(); @@ -2563,7 +2623,23 @@ static void ir_ack_apic_level(struct irq_data *data) ack_APIC_irq(); eoi_ioapic_irq(data->irq, data->chip_data); } -#endif /* CONFIG_INTR_REMAP */ + +static void ir_print_prefix(struct irq_data *data, struct seq_file *p) +{ + seq_printf(p, " IR-%s", data->chip->name); +} + +static void irq_remap_modify_chip_defaults(struct irq_chip *chip) +{ + chip->irq_print_chip = ir_print_prefix; + chip->irq_ack = ir_ack_apic_edge; + chip->irq_eoi = ir_ack_apic_level; + +#ifdef CONFIG_SMP + chip->irq_set_affinity = ir_ioapic_set_affinity; +#endif +} +#endif /* CONFIG_IRQ_REMAP */ static struct irq_chip ioapic_chip __read_mostly = { .name = "IO-APIC", @@ -2578,21 +2654,6 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_retrigger = ioapic_retrigger_irq, }; -static struct irq_chip ir_ioapic_chip __read_mostly = { - .name = "IR-IO-APIC", - .irq_startup = startup_ioapic_irq, - .irq_mask = mask_ioapic_irq, - .irq_unmask = unmask_ioapic_irq, -#ifdef CONFIG_INTR_REMAP - .irq_ack = ir_ack_apic_edge, - .irq_eoi = ir_ack_apic_level, -#ifdef CONFIG_SMP - .irq_set_affinity = ir_ioapic_set_affinity, -#endif -#endif - .irq_retrigger = ioapic_retrigger_irq, -}; - static inline void init_IO_APIC_traps(void) { struct irq_cfg *cfg; @@ -2944,27 +3005,26 @@ static int __init io_apic_bug_finalize(void) late_initcall(io_apic_bug_finalize); -static void resume_ioapic_id(int ioapic_id) +static void resume_ioapic_id(int ioapic_idx) { unsigned long flags; union IO_APIC_reg_00 reg_00; - raw_spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(ioapic_id, 0); - if (reg_00.bits.ID != mpc_ioapic_id(ioapic_id)) { - reg_00.bits.ID = mpc_ioapic_id(ioapic_id); - io_apic_write(ioapic_id, 0, reg_00.raw); + reg_00.raw = io_apic_read(ioapic_idx, 0); + if (reg_00.bits.ID != mpc_ioapic_id(ioapic_idx)) { + reg_00.bits.ID = mpc_ioapic_id(ioapic_idx); + io_apic_write(ioapic_idx, 0, reg_00.raw); } raw_spin_unlock_irqrestore(&ioapic_lock, flags); } static void ioapic_resume(void) { - int ioapic_id; + int ioapic_idx; - for (ioapic_id = nr_ioapics - 1; ioapic_id >= 0; ioapic_id--) - resume_ioapic_id(ioapic_id); + for (ioapic_idx = nr_ioapics - 1; ioapic_idx >= 0; ioapic_idx--) + resume_ioapic_id(ioapic_idx); restore_ioapic_entries(); } @@ -3144,45 +3204,6 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) return 0; } -#ifdef CONFIG_INTR_REMAP -/* - * Migrate the MSI irq to another cpumask. This migration is - * done in the process context using interrupt-remapping hardware. - */ -static int -ir_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) -{ - struct irq_cfg *cfg = data->chip_data; - unsigned int dest, irq = data->irq; - struct irte irte; - - if (get_irte(irq, &irte)) - return -1; - - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; - - irte.vector = cfg->vector; - irte.dest_id = IRTE_DEST(dest); - - /* - * atomically update the IRTE with the new destination and vector. - */ - modify_irte(irq, &irte); - - /* - * After this point, all the interrupts will start arriving - * at the new destination. So, time to cleanup the previous - * vector allocation. - */ - if (cfg->move_in_progress) - send_cleanup_vector(cfg); - - return 0; -} - -#endif #endif /* CONFIG_SMP */ /* @@ -3200,19 +3221,6 @@ static struct irq_chip msi_chip = { .irq_retrigger = ioapic_retrigger_irq, }; -static struct irq_chip msi_ir_chip = { - .name = "IR-PCI-MSI", - .irq_unmask = unmask_msi_irq, - .irq_mask = mask_msi_irq, -#ifdef CONFIG_INTR_REMAP - .irq_ack = ir_ack_apic_edge, -#ifdef CONFIG_SMP - .irq_set_affinity = ir_msi_set_affinity, -#endif -#endif - .irq_retrigger = ioapic_retrigger_irq, -}; - /* * Map the PCI dev to the corresponding remapping hardware unit * and allocate 'nvec' consecutive interrupt-remapping table entries @@ -3255,7 +3263,7 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) if (irq_remapped(irq_get_chip_data(irq))) { irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - chip = &msi_ir_chip; + irq_remap_modify_chip_defaults(chip); } irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); @@ -3328,7 +3336,7 @@ void native_teardown_msi_irq(unsigned int irq) destroy_irq(irq); } -#if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP) +#ifdef CONFIG_DMAR_TABLE #ifdef CONFIG_SMP static int dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, @@ -3409,19 +3417,6 @@ static int hpet_msi_set_affinity(struct irq_data *data, #endif /* CONFIG_SMP */ -static struct irq_chip ir_hpet_msi_type = { - .name = "IR-HPET_MSI", - .irq_unmask = hpet_msi_unmask, - .irq_mask = hpet_msi_mask, -#ifdef CONFIG_INTR_REMAP - .irq_ack = ir_ack_apic_edge, -#ifdef CONFIG_SMP - .irq_set_affinity = ir_msi_set_affinity, -#endif -#endif - .irq_retrigger = ioapic_retrigger_irq, -}; - static struct irq_chip hpet_msi_type = { .name = "HPET_MSI", .irq_unmask = hpet_msi_unmask, @@ -3458,7 +3453,7 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id) hpet_msi_write(irq_get_handler_data(irq), &msg); irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); if (irq_remapped(irq_get_chip_data(irq))) - chip = &ir_hpet_msi_type; + irq_remap_modify_chip_defaults(chip); irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); return 0; @@ -3566,26 +3561,25 @@ io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr) return -EINVAL; ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin); if (!ret) - setup_ioapic_irq(attr->ioapic, attr->ioapic_pin, irq, cfg, - attr->trigger, attr->polarity); + setup_ioapic_irq(irq, cfg, attr); return ret; } int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr) { - unsigned int id = attr->ioapic, pin = attr->ioapic_pin; + unsigned int ioapic_idx = attr->ioapic, pin = attr->ioapic_pin; int ret; /* Avoid redundant programming */ - if (test_bit(pin, ioapics[id].pin_programmed)) { + if (test_bit(pin, ioapics[ioapic_idx].pin_programmed)) { pr_debug("Pin %d-%d already programmed\n", - mpc_ioapic_id(id), pin); + mpc_ioapic_id(ioapic_idx), pin); return 0; } ret = io_apic_setup_irq_pin(irq, node, attr); if (!ret) - set_bit(pin, ioapics[id].pin_programmed); + set_bit(pin, ioapics[ioapic_idx].pin_programmed); return ret; } @@ -3621,7 +3615,6 @@ int get_nr_irqs_gsi(void) return nr_irqs_gsi; } -#ifdef CONFIG_SPARSE_IRQ int __init arch_probe_nr_irqs(void) { int nr; @@ -3641,7 +3634,6 @@ int __init arch_probe_nr_irqs(void) return NR_IRQS_LEGACY; } -#endif int io_apic_set_pci_routing(struct device *dev, int irq, struct io_apic_irq_attr *irq_attr) diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index b5254ad044ab..0787bb3412f4 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -200,14 +200,8 @@ void __init default_setup_apic_routing(void) * - we find more than 8 CPUs in acpi LAPIC listing with xAPIC support */ - if (!cmdline_apic && apic == &apic_default) { - struct apic *bigsmp = generic_bigsmp_probe(); - if (bigsmp) { - apic = bigsmp; - printk(KERN_INFO "Overriding APIC driver with %s\n", - apic->name); - } - } + if (!cmdline_apic && apic == &apic_default) + generic_bigsmp_probe(); #endif if (apic->setup_apic_routing) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 34b18594e724..62ae3001ae02 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -672,18 +672,11 @@ void __cpuinit uv_cpu_init(void) /* * When NMI is received, print a stack trace. */ -int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data) +int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) { unsigned long real_uv_nmi; int bid; - if (reason != DIE_NMIUNKNOWN) - return NOTIFY_OK; - - if (in_crash_kexec) - /* do nothing if entering the crash kernel */ - return NOTIFY_OK; - /* * Each blade has an MMR that indicates when an NMI has been sent * to cpus on the blade. If an NMI is detected, atomically @@ -704,7 +697,7 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data) } if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count)) - return NOTIFY_DONE; + return NMI_DONE; __get_cpu_var(cpu_last_nmi_count) = uv_blade_info[bid].nmi_count; @@ -717,17 +710,12 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data) dump_stack(); spin_unlock(&uv_nmi_lock); - return NOTIFY_STOP; + return NMI_HANDLED; } -static struct notifier_block uv_dump_stack_nmi_nb = { - .notifier_call = uv_handle_nmi, - .priority = NMI_LOCAL_LOW_PRIOR - 1, -}; - void uv_register_nmi_notifier(void) { - if (register_die_notifier(&uv_dump_stack_nmi_nb)) + if (register_nmi_handler(NMI_UNKNOWN, uv_handle_nmi, 0, "uv")) printk(KERN_WARNING "UV NMI handler failed to register\n"); } @@ -832,6 +820,10 @@ void __init uv_system_init(void) uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift; uv_cpu_hub_info(cpu)->hub_revision = uv_hub_info->hub_revision; + uv_cpu_hub_info(cpu)->m_shift = 64 - m_val; + uv_cpu_hub_info(cpu)->n_lshift = is_uv2_1_hub() ? + (m_val == 40 ? 40 : 39) : m_val; + pnode = uv_apicid_to_pnode(apicid); blade = boot_pnode_to_blade(pnode); lcpu = uv_blade_info[blade].nr_possible_cpus; @@ -862,8 +854,7 @@ void __init uv_system_init(void) if (uv_node_to_blade[nid] >= 0) continue; paddr = node_start_pfn(nid) << PAGE_SHIFT; - paddr = uv_soc_phys_ram_to_gpa(paddr); - pnode = (paddr >> m_val) & pnode_mask; + pnode = uv_gpa_to_pnode(uv_soc_phys_ram_to_gpa(paddr)); blade = boot_pnode_to_blade(pnode); uv_node_to_blade[nid] = blade; } diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 0371c484bb8a..a46bd383953c 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -249,8 +249,6 @@ extern int (*console_blank_hook)(int); #define APM_MINOR_DEV 134 /* - * See Documentation/Config.help for the configuration options. - * * Various options can be changed at boot time as follows: * (We allow underscores for compatibility with the modules code) * apm=on/off enable/disable APM diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 6042981d0309..25f24dccdcfa 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -15,6 +15,7 @@ CFLAGS_common.o := $(nostackp) obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += proc.o capflags.o powerflags.o common.o obj-y += vmware.o hypervisor.o sched.o mshyperv.o +obj-y += rdrand.o obj-$(CONFIG_X86_32) += bugs.o obj-$(CONFIG_X86_64) += bugs_64.o @@ -28,10 +29,15 @@ obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o +ifdef CONFIG_PERF_EVENTS +obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o +endif + obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ -obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o +obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o perf_event_amd_ibs.o quiet_cmd_mkcapflags = MKCAP $@ cmd_mkcapflags = $(PERL) $(srctree)/$(src)/mkcapflags.pl $< $@ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index b13ed393dfce..46ae4f65fc7f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1,5 +1,6 @@ #include <linux/init.h> #include <linux/bitops.h> +#include <linux/elf.h> #include <linux/mm.h> #include <linux/io.h> @@ -410,8 +411,38 @@ static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c) #endif } +static void __cpuinit bsp_init_amd(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { + + if (c->x86 > 0x10 || + (c->x86 == 0x10 && c->x86_model >= 0x2)) { + u64 val; + + rdmsrl(MSR_K7_HWCR, val); + if (!(val & BIT(24))) + printk(KERN_WARNING FW_BUG "TSC doesn't count " + "with P0 frequency!\n"); + } + } + + if (c->x86 == 0x15) { + unsigned long upperbit; + u32 cpuid, assoc; + + cpuid = cpuid_edx(0x80000005); + assoc = cpuid >> 16 & 0xff; + upperbit = ((cpuid >> 24) << 10) / assoc; + + va_align.mask = (upperbit - 1) & PAGE_MASK; + va_align.flags = ALIGN_VA_32 | ALIGN_VA_64; + } +} + static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) { + u32 dummy; + early_init_amd_mc(c); /* @@ -442,22 +473,7 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) } #endif - /* We need to do the following only once */ - if (c != &boot_cpu_data) - return; - - if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { - - if (c->x86 > 0x10 || - (c->x86 == 0x10 && c->x86_model >= 0x2)) { - u64 val; - - rdmsrl(MSR_K7_HWCR, val); - if (!(val & BIT(24))) - printk(KERN_WARNING FW_BUG "TSC doesn't count " - "with P0 frequency!\n"); - } - } + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); } static void __cpuinit init_amd(struct cpuinfo_x86 *c) @@ -679,6 +695,7 @@ static const struct cpu_dev __cpuinitconst amd_cpu_dev = { .c_size_cache = amd_size_cache, #endif .c_early_init = early_init_amd, + .c_bsp_init = bsp_init_amd, .c_init = init_amd, .c_x86_vendor = X86_VENDOR_AMD, }; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 62184390a601..aa003b13a831 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -15,6 +15,7 @@ #include <asm/stackprotector.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> +#include <asm/archrandom.h> #include <asm/hypervisor.h> #include <asm/processor.h> #include <asm/sections.h> @@ -681,6 +682,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) filter_cpuid_features(c, false); setup_smep(c); + + if (this_cpu->c_bsp_init) + this_cpu->c_bsp_init(c); } void __init early_cpu_init(void) @@ -857,6 +861,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) #endif init_hypervisor(c); + x86_init_rdrand(c); /* * Clear/Set all flags overriden by options, need do it diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index e765633f210e..1b22dcc51af4 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -18,6 +18,7 @@ struct cpu_dev { struct cpu_model_info c_models[4]; void (*c_early_init)(struct cpuinfo_x86 *); + void (*c_bsp_init)(struct cpuinfo_x86 *); void (*c_init)(struct cpuinfo_x86 *); void (*c_identify)(struct cpuinfo_x86 *); unsigned int (*c_size_cache)(struct cpuinfo_x86 *, unsigned int); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index ed6086eedf1d..523131213f08 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -47,6 +47,15 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) (c->x86 == 0x6 && c->x86_model >= 0x0e)) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) { + unsigned lower_word; + + wrmsr(MSR_IA32_UCODE_REV, 0, 0); + /* Required by the SDM */ + sync_core(); + rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode); + } + /* * Atom erratum AAE44/AAF40/AAG38/AAH41: * @@ -55,17 +64,10 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) * need the microcode to have already been loaded... so if it is * not, recommend a BIOS update and disable large pages. */ - if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2) { - u32 ucode, junk; - - wrmsr(MSR_IA32_UCODE_REV, 0, 0); - sync_core(); - rdmsr(MSR_IA32_UCODE_REV, junk, ucode); - - if (ucode < 0x20e) { - printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n"); - clear_cpu_cap(c, X86_FEATURE_PSE); - } + if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 && + c->microcode < 0x20e) { + printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n"); + clear_cpu_cap(c, X86_FEATURE_PSE); } #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index c105c533ed94..a3b0811693c9 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -151,28 +151,17 @@ union _cpuid4_leaf_ecx { u32 full; }; -struct amd_l3_cache { - struct amd_northbridge *nb; - unsigned indices; - u8 subcaches[4]; -}; - -struct _cpuid4_info { +struct _cpuid4_info_regs { union _cpuid4_leaf_eax eax; union _cpuid4_leaf_ebx ebx; union _cpuid4_leaf_ecx ecx; unsigned long size; - struct amd_l3_cache *l3; - DECLARE_BITMAP(shared_cpu_map, NR_CPUS); + struct amd_northbridge *nb; }; -/* subset of above _cpuid4_info w/o shared_cpu_map */ -struct _cpuid4_info_regs { - union _cpuid4_leaf_eax eax; - union _cpuid4_leaf_ebx ebx; - union _cpuid4_leaf_ecx ecx; - unsigned long size; - struct amd_l3_cache *l3; +struct _cpuid4_info { + struct _cpuid4_info_regs base; + DECLARE_BITMAP(shared_cpu_map, NR_CPUS); }; unsigned short num_cache_leaves; @@ -314,16 +303,23 @@ struct _cache_attr { /* * L3 cache descriptors */ -static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3) +static void __cpuinit amd_calc_l3_indices(struct amd_northbridge *nb) { + struct amd_l3_cache *l3 = &nb->l3_cache; unsigned int sc0, sc1, sc2, sc3; u32 val = 0; - pci_read_config_dword(l3->nb->misc, 0x1C4, &val); + pci_read_config_dword(nb->misc, 0x1C4, &val); /* calculate subcache sizes */ l3->subcaches[0] = sc0 = !(val & BIT(0)); l3->subcaches[1] = sc1 = !(val & BIT(4)); + + if (boot_cpu_data.x86 == 0x15) { + l3->subcaches[0] = sc0 += !(val & BIT(1)); + l3->subcaches[1] = sc1 += !(val & BIT(5)); + } + l3->subcaches[2] = sc2 = !(val & BIT(8)) + !(val & BIT(9)); l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13)); @@ -333,33 +329,16 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3) static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) { - static struct amd_l3_cache *__cpuinitdata l3_caches; int node; /* only for L3, and not in virtualized environments */ - if (index < 3 || amd_nb_num() == 0) + if (index < 3) return; - /* - * Strictly speaking, the amount in @size below is leaked since it is - * never freed but this is done only on shutdown so it doesn't matter. - */ - if (!l3_caches) { - int size = amd_nb_num() * sizeof(struct amd_l3_cache); - - l3_caches = kzalloc(size, GFP_ATOMIC); - if (!l3_caches) - return; - } - node = amd_get_nb_id(smp_processor_id()); - - if (!l3_caches[node].nb) { - l3_caches[node].nb = node_to_amd_nb(node); - amd_calc_l3_indices(&l3_caches[node]); - } - - this_leaf->l3 = &l3_caches[node]; + this_leaf->nb = node_to_amd_nb(node); + if (this_leaf->nb && !this_leaf->nb->l3_cache.indices) + amd_calc_l3_indices(this_leaf->nb); } /* @@ -369,11 +348,11 @@ static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, * * @returns: the disabled index if used or negative value if slot free. */ -int amd_get_l3_disable_slot(struct amd_l3_cache *l3, unsigned slot) +int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot) { unsigned int reg = 0; - pci_read_config_dword(l3->nb->misc, 0x1BC + slot * 4, ®); + pci_read_config_dword(nb->misc, 0x1BC + slot * 4, ®); /* check whether this slot is activated already */ if (reg & (3UL << 30)) @@ -387,11 +366,10 @@ static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, { int index; - if (!this_leaf->l3 || - !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) + if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) return -EINVAL; - index = amd_get_l3_disable_slot(this_leaf->l3, slot); + index = amd_get_l3_disable_slot(this_leaf->base.nb, slot); if (index >= 0) return sprintf(buf, "%d\n", index); @@ -408,7 +386,7 @@ show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf, \ SHOW_CACHE_DISABLE(0) SHOW_CACHE_DISABLE(1) -static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu, +static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu, unsigned slot, unsigned long idx) { int i; @@ -421,10 +399,10 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu, for (i = 0; i < 4; i++) { u32 reg = idx | (i << 20); - if (!l3->subcaches[i]) + if (!nb->l3_cache.subcaches[i]) continue; - pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg); + pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg); /* * We need to WBINVD on a core on the node containing the L3 @@ -434,7 +412,7 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu, wbinvd_on_cpu(cpu); reg |= BIT(31); - pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg); + pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg); } } @@ -448,24 +426,24 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu, * * @return: 0 on success, error status on failure */ -int amd_set_l3_disable_slot(struct amd_l3_cache *l3, int cpu, unsigned slot, +int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot, unsigned long index) { int ret = 0; /* check if @slot is already used or the index is already disabled */ - ret = amd_get_l3_disable_slot(l3, slot); + ret = amd_get_l3_disable_slot(nb, slot); if (ret >= 0) return -EINVAL; - if (index > l3->indices) + if (index > nb->l3_cache.indices) return -EINVAL; /* check whether the other slot has disabled the same index already */ - if (index == amd_get_l3_disable_slot(l3, !slot)) + if (index == amd_get_l3_disable_slot(nb, !slot)) return -EINVAL; - amd_l3_disable_index(l3, cpu, slot, index); + amd_l3_disable_index(nb, cpu, slot, index); return 0; } @@ -480,8 +458,7 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!this_leaf->l3 || - !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) + if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) return -EINVAL; cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); @@ -489,7 +466,7 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, if (strict_strtoul(buf, 10, &val) < 0) return -EINVAL; - err = amd_set_l3_disable_slot(this_leaf->l3, cpu, slot, val); + err = amd_set_l3_disable_slot(this_leaf->base.nb, cpu, slot, val); if (err) { if (err == -EEXIST) printk(KERN_WARNING "L3 disable slot %d in use!\n", @@ -518,7 +495,7 @@ static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644, static ssize_t show_subcaches(struct _cpuid4_info *this_leaf, char *buf, unsigned int cpu) { - if (!this_leaf->l3 || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) + if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) return -EINVAL; return sprintf(buf, "%x\n", amd_get_subcaches(cpu)); @@ -533,7 +510,7 @@ store_subcaches(struct _cpuid4_info *this_leaf, const char *buf, size_t count, if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!this_leaf->l3 || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) + if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) return -EINVAL; if (strict_strtoul(buf, 16, &val) < 0) @@ -769,7 +746,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) return; } this_leaf = CPUID4_INFO_IDX(cpu, index); - num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing; + num_threads_sharing = 1 + this_leaf->base.eax.split.num_threads_sharing; if (num_threads_sharing == 1) cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map)); @@ -820,29 +797,19 @@ static void __cpuinit free_cache_attributes(unsigned int cpu) for (i = 0; i < num_cache_leaves; i++) cache_remove_shared_cpu_map(cpu, i); - kfree(per_cpu(ici_cpuid4_info, cpu)->l3); kfree(per_cpu(ici_cpuid4_info, cpu)); per_cpu(ici_cpuid4_info, cpu) = NULL; } -static int -__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf) -{ - struct _cpuid4_info_regs *leaf_regs = - (struct _cpuid4_info_regs *)this_leaf; - - return cpuid4_cache_lookup_regs(index, leaf_regs); -} - static void __cpuinit get_cpu_leaves(void *_retval) { int j, *retval = _retval, cpu = smp_processor_id(); /* Do cpuid and store the results */ for (j = 0; j < num_cache_leaves; j++) { - struct _cpuid4_info *this_leaf; - this_leaf = CPUID4_INFO_IDX(cpu, j); - *retval = cpuid4_cache_lookup(j, this_leaf); + struct _cpuid4_info *this_leaf = CPUID4_INFO_IDX(cpu, j); + + *retval = cpuid4_cache_lookup_regs(j, &this_leaf->base); if (unlikely(*retval < 0)) { int i; @@ -900,16 +867,16 @@ static ssize_t show_##file_name(struct _cpuid4_info *this_leaf, char *buf, \ return sprintf(buf, "%lu\n", (unsigned long)this_leaf->object + val); \ } -show_one_plus(level, eax.split.level, 0); -show_one_plus(coherency_line_size, ebx.split.coherency_line_size, 1); -show_one_plus(physical_line_partition, ebx.split.physical_line_partition, 1); -show_one_plus(ways_of_associativity, ebx.split.ways_of_associativity, 1); -show_one_plus(number_of_sets, ecx.split.number_of_sets, 1); +show_one_plus(level, base.eax.split.level, 0); +show_one_plus(coherency_line_size, base.ebx.split.coherency_line_size, 1); +show_one_plus(physical_line_partition, base.ebx.split.physical_line_partition, 1); +show_one_plus(ways_of_associativity, base.ebx.split.ways_of_associativity, 1); +show_one_plus(number_of_sets, base.ecx.split.number_of_sets, 1); static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf, unsigned int cpu) { - return sprintf(buf, "%luK\n", this_leaf->size / 1024); + return sprintf(buf, "%luK\n", this_leaf->base.size / 1024); } static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf, @@ -946,7 +913,7 @@ static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf, static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf, unsigned int cpu) { - switch (this_leaf->eax.split.type) { + switch (this_leaf->base.eax.split.type) { case CACHE_TYPE_DATA: return sprintf(buf, "Data\n"); case CACHE_TYPE_INST: @@ -1135,7 +1102,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) ktype_cache.default_attrs = default_attrs; #ifdef CONFIG_AMD_NB - if (this_leaf->l3) + if (this_leaf->base.nb) ktype_cache.default_attrs = amd_l3_attrs(); #endif retval = kobject_init_and_add(&(this_object->kobj), diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 0ed633c5048b..6199232161cf 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -78,27 +78,20 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs) static cpumask_var_t mce_inject_cpumask; -static int mce_raise_notify(struct notifier_block *self, - unsigned long val, void *data) +static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs) { - struct die_args *args = (struct die_args *)data; int cpu = smp_processor_id(); struct mce *m = &__get_cpu_var(injectm); - if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask)) - return NOTIFY_DONE; + if (!cpumask_test_cpu(cpu, mce_inject_cpumask)) + return NMI_DONE; cpumask_clear_cpu(cpu, mce_inject_cpumask); if (m->inject_flags & MCJ_EXCEPTION) - raise_exception(m, args->regs); + raise_exception(m, regs); else if (m->status) raise_poll(m); - return NOTIFY_STOP; + return NMI_HANDLED; } -static struct notifier_block mce_raise_nb = { - .notifier_call = mce_raise_notify, - .priority = NMI_LOCAL_NORMAL_PRIOR, -}; - /* Inject mce on current CPU */ static int raise_local(void) { @@ -216,7 +209,8 @@ static int inject_init(void) return -ENOMEM; printk(KERN_INFO "Machine check injector initialized\n"); mce_chrdev_ops.write = mce_write; - register_die_notifier(&mce_raise_nb); + register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, + "mce_notify"); return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 08363b042122..7b5063a6ad42 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -217,8 +217,13 @@ static void print_mce(struct mce *m) pr_cont("MISC %llx ", m->misc); pr_cont("\n"); - pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n", - m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid); + /* + * Note this output is parsed by external tools and old fields + * should not be changed. + */ + pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n", + m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid, + cpu_data(m->extcpu).microcode); /* * Print out human-readable details about the MCE error, @@ -908,9 +913,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) percpu_inc(mce_exception_count); - if (notify_die(DIE_NMI, "machine check", regs, error_code, - 18, SIGKILL) == NOTIFY_STOP) - goto out; if (!banks) goto out; @@ -1140,6 +1142,15 @@ static void mce_start_timer(unsigned long data) add_timer_on(t, smp_processor_id()); } +/* Must not be called in IRQ context where del_timer_sync() can deadlock */ +static void mce_timer_delete_all(void) +{ + int cpu; + + for_each_online_cpu(cpu) + del_timer_sync(&per_cpu(mce_timer, cpu)); +} + static void mce_do_trigger(struct work_struct *work) { call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT); @@ -1750,7 +1761,6 @@ static struct syscore_ops mce_syscore_ops = { static void mce_cpu_restart(void *data) { - del_timer_sync(&__get_cpu_var(mce_timer)); if (!mce_available(__this_cpu_ptr(&cpu_info))) return; __mcheck_cpu_init_generic(); @@ -1760,16 +1770,15 @@ static void mce_cpu_restart(void *data) /* Reinit MCEs after user configuration changes */ static void mce_restart(void) { + mce_timer_delete_all(); on_each_cpu(mce_cpu_restart, NULL, 1); } /* Toggle features for corrected errors */ -static void mce_disable_ce(void *all) +static void mce_disable_cmci(void *data) { if (!mce_available(__this_cpu_ptr(&cpu_info))) return; - if (all) - del_timer_sync(&__get_cpu_var(mce_timer)); cmci_clear(); } @@ -1852,7 +1861,8 @@ static ssize_t set_ignore_ce(struct sys_device *s, if (mce_ignore_ce ^ !!new) { if (new) { /* disable ce features */ - on_each_cpu(mce_disable_ce, (void *)1, 1); + mce_timer_delete_all(); + on_each_cpu(mce_disable_cmci, NULL, 1); mce_ignore_ce = 1; } else { /* enable ce features */ @@ -1875,7 +1885,7 @@ static ssize_t set_cmci_disabled(struct sys_device *s, if (mce_cmci_disabled ^ !!new) { if (new) { /* disable cmci */ - on_each_cpu(mce_disable_ce, NULL, 1); + on_each_cpu(mce_disable_cmci, NULL, 1); mce_cmci_disabled = 1; } else { /* enable cmci */ diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 8694ef56459d..38e49bc95ffc 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -28,7 +28,7 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); * cmci_discover_lock protects against parallel discovery attempts * which could race against each other. */ -static DEFINE_SPINLOCK(cmci_discover_lock); +static DEFINE_RAW_SPINLOCK(cmci_discover_lock); #define CMCI_THRESHOLD 1 @@ -85,7 +85,7 @@ static void cmci_discover(int banks, int boot) int hdr = 0; int i; - spin_lock_irqsave(&cmci_discover_lock, flags); + raw_spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; @@ -116,7 +116,7 @@ static void cmci_discover(int banks, int boot) WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); } } - spin_unlock_irqrestore(&cmci_discover_lock, flags); + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); if (hdr) printk(KERN_CONT "\n"); } @@ -150,7 +150,7 @@ void cmci_clear(void) if (!cmci_supported(&banks)) return; - spin_lock_irqsave(&cmci_discover_lock, flags); + raw_spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { if (!test_bit(i, __get_cpu_var(mce_banks_owned))) continue; @@ -160,7 +160,7 @@ void cmci_clear(void) wrmsrl(MSR_IA32_MCx_CTL2(i), val); __clear_bit(i, __get_cpu_var(mce_banks_owned)); } - spin_unlock_irqrestore(&cmci_discover_lock, flags); + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } /* diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d944bf6c50e9..0a630dd4b620 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -11,6 +11,8 @@ */ #include <linux/types.h> +#include <linux/time.h> +#include <linux/clocksource.h> #include <linux/module.h> #include <asm/processor.h> #include <asm/hypervisor.h> @@ -36,6 +38,25 @@ static bool __init ms_hyperv_platform(void) !memcmp("Microsoft Hv", hyp_signature, 12); } +static cycle_t read_hv_clock(struct clocksource *arg) +{ + cycle_t current_tick; + /* + * Read the partition counter to get the current tick count. This count + * is set to 0 when the partition is created and is incremented in + * 100 nanosecond units. + */ + rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick); + return current_tick; +} + +static struct clocksource hyperv_cs = { + .name = "hyperv_clocksource", + .rating = 400, /* use this when running on Hyperv*/ + .read = read_hv_clock, + .mask = CLOCKSOURCE_MASK(64), +}; + static void __init ms_hyperv_init_platform(void) { /* @@ -46,6 +67,8 @@ static void __init ms_hyperv_init_platform(void) printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n", ms_hyperv.features, ms_hyperv.hints); + + clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index cfa62ec090ec..640891014b2a 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -32,6 +32,8 @@ #include <asm/smp.h> #include <asm/alternative.h> +#include "perf_event.h" + #if 0 #undef wrmsrl #define wrmsrl(msr, val) \ @@ -43,283 +45,17 @@ do { \ } while (0) #endif -/* - * | NHM/WSM | SNB | - * register ------------------------------- - * | HT | no HT | HT | no HT | - *----------------------------------------- - * offcore | core | core | cpu | core | - * lbr_sel | core | core | cpu | core | - * ld_lat | cpu | core | cpu | core | - *----------------------------------------- - * - * Given that there is a small number of shared regs, - * we can pre-allocate their slot in the per-cpu - * per-core reg tables. - */ -enum extra_reg_type { - EXTRA_REG_NONE = -1, /* not used */ - - EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ - EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ - - EXTRA_REG_MAX /* number of entries needed */ -}; - -struct event_constraint { - union { - unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - u64 idxmsk64; - }; - u64 code; - u64 cmask; - int weight; -}; - -struct amd_nb { - int nb_id; /* NorthBridge id */ - int refcnt; /* reference count */ - struct perf_event *owners[X86_PMC_IDX_MAX]; - struct event_constraint event_constraints[X86_PMC_IDX_MAX]; -}; - -struct intel_percore; - -#define MAX_LBR_ENTRIES 16 - -struct cpu_hw_events { - /* - * Generic x86 PMC bits - */ - struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ - unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; - int enabled; - - int n_events; - int n_added; - int n_txn; - int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ - u64 tags[X86_PMC_IDX_MAX]; - struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ - - unsigned int group_flag; - - /* - * Intel DebugStore bits - */ - struct debug_store *ds; - u64 pebs_enabled; - - /* - * Intel LBR bits - */ - int lbr_users; - void *lbr_context; - struct perf_branch_stack lbr_stack; - struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; - - /* - * manage shared (per-core, per-cpu) registers - * used on Intel NHM/WSM/SNB - */ - struct intel_shared_regs *shared_regs; - - /* - * AMD specific bits - */ - struct amd_nb *amd_nb; -}; - -#define __EVENT_CONSTRAINT(c, n, m, w) {\ - { .idxmsk64 = (n) }, \ - .code = (c), \ - .cmask = (m), \ - .weight = (w), \ -} - -#define EVENT_CONSTRAINT(c, n, m) \ - __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n)) - -/* - * Constraint on the Event code. - */ -#define INTEL_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) - -/* - * Constraint on the Event code + UMask + fixed-mask - * - * filter mask to validate fixed counter events. - * the following filters disqualify for fixed counters: - * - inv - * - edge - * - cnt-mask - * The other filters are supported by fixed counters. - * The any-thread option is supported starting with v3. - */ -#define FIXED_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK) - -/* - * Constraint on the Event code + UMask - */ -#define INTEL_UEVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) - -#define EVENT_CONSTRAINT_END \ - EVENT_CONSTRAINT(0, 0, 0) - -#define for_each_event_constraint(e, c) \ - for ((e) = (c); (e)->weight; (e)++) - -/* - * Per register state. - */ -struct er_account { - raw_spinlock_t lock; /* per-core: protect structure */ - u64 config; /* extra MSR config */ - u64 reg; /* extra MSR number */ - atomic_t ref; /* reference count */ -}; - -/* - * Extra registers for specific events. - * - * Some events need large masks and require external MSRs. - * Those extra MSRs end up being shared for all events on - * a PMU and sometimes between PMU of sibling HT threads. - * In either case, the kernel needs to handle conflicting - * accesses to those extra, shared, regs. The data structure - * to manage those registers is stored in cpu_hw_event. - */ -struct extra_reg { - unsigned int event; - unsigned int msr; - u64 config_mask; - u64 valid_mask; - int idx; /* per_xxx->regs[] reg index */ -}; - -#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ - .event = (e), \ - .msr = (ms), \ - .config_mask = (m), \ - .valid_mask = (vm), \ - .idx = EXTRA_REG_##i \ - } - -#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ - EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx) - -#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0) - -union perf_capabilities { - struct { - u64 lbr_format : 6; - u64 pebs_trap : 1; - u64 pebs_arch_reg : 1; - u64 pebs_format : 4; - u64 smm_freeze : 1; - }; - u64 capabilities; -}; - -/* - * struct x86_pmu - generic x86 pmu - */ -struct x86_pmu { - /* - * Generic x86 PMC bits - */ - const char *name; - int version; - int (*handle_irq)(struct pt_regs *); - void (*disable_all)(void); - void (*enable_all)(int added); - void (*enable)(struct perf_event *); - void (*disable)(struct perf_event *); - int (*hw_config)(struct perf_event *event); - int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); - unsigned eventsel; - unsigned perfctr; - u64 (*event_map)(int); - int max_events; - int num_counters; - int num_counters_fixed; - int cntval_bits; - u64 cntval_mask; - int apic; - u64 max_period; - struct event_constraint * - (*get_event_constraints)(struct cpu_hw_events *cpuc, - struct perf_event *event); - - void (*put_event_constraints)(struct cpu_hw_events *cpuc, - struct perf_event *event); - struct event_constraint *event_constraints; - void (*quirks)(void); - int perfctr_second_write; - - int (*cpu_prepare)(int cpu); - void (*cpu_starting)(int cpu); - void (*cpu_dying)(int cpu); - void (*cpu_dead)(int cpu); - - /* - * Intel Arch Perfmon v2+ - */ - u64 intel_ctrl; - union perf_capabilities intel_cap; +struct x86_pmu x86_pmu __read_mostly; - /* - * Intel DebugStore bits - */ - int bts, pebs; - int bts_active, pebs_active; - int pebs_record_size; - void (*drain_pebs)(struct pt_regs *regs); - struct event_constraint *pebs_constraints; - - /* - * Intel LBR - */ - unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ - int lbr_nr; /* hardware stack size */ - - /* - * Extra registers for events - */ - struct extra_reg *extra_regs; - unsigned int er_flags; -}; - -#define ERF_NO_HT_SHARING 1 -#define ERF_HAS_RSP_1 2 - -static struct x86_pmu x86_pmu __read_mostly; - -static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { +DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, }; -static int x86_perf_event_set_period(struct perf_event *event); - -/* - * Generalized hw caching related hw_event table, filled - * in on a per model basis. A value of 0 means - * 'not supported', -1 means 'hw_event makes no sense on - * this CPU', any other value means the raw hw_event - * ID. - */ - -#define C(x) PERF_COUNT_HW_CACHE_##x - -static u64 __read_mostly hw_cache_event_ids +u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; -static u64 __read_mostly hw_cache_extra_regs +u64 __read_mostly hw_cache_extra_regs [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; @@ -329,8 +65,7 @@ static u64 __read_mostly hw_cache_extra_regs * Can only be executed on the CPU where the event is active. * Returns the delta events processed. */ -static u64 -x86_perf_event_update(struct perf_event *event) +u64 x86_perf_event_update(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int shift = 64 - x86_pmu.cntval_bits; @@ -373,30 +108,6 @@ again: return new_raw_count; } -static inline int x86_pmu_addr_offset(int index) -{ - int offset; - - /* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */ - alternative_io(ASM_NOP2, - "shll $1, %%eax", - X86_FEATURE_PERFCTR_CORE, - "=a" (offset), - "a" (index)); - - return offset; -} - -static inline unsigned int x86_pmu_config_addr(int index) -{ - return x86_pmu.eventsel + x86_pmu_addr_offset(index); -} - -static inline unsigned int x86_pmu_event_addr(int index) -{ - return x86_pmu.perfctr + x86_pmu_addr_offset(index); -} - /* * Find and validate any extra registers to set up. */ @@ -532,9 +243,6 @@ msr_fail: return false; } -static void reserve_ds_buffers(void); -static void release_ds_buffers(void); - static void hw_perf_event_destroy(struct perf_event *event) { if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) { @@ -583,7 +291,7 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) return x86_pmu_extra_regs(val, event); } -static int x86_setup_perfctr(struct perf_event *event) +int x86_setup_perfctr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; @@ -647,7 +355,7 @@ static int x86_setup_perfctr(struct perf_event *event) return 0; } -static int x86_pmu_hw_config(struct perf_event *event) +int x86_pmu_hw_config(struct perf_event *event) { if (event->attr.precise_ip) { int precise = 0; @@ -723,7 +431,7 @@ static int __x86_pmu_event_init(struct perf_event *event) return x86_pmu.hw_config(event); } -static void x86_pmu_disable_all(void) +void x86_pmu_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; @@ -758,15 +466,7 @@ static void x86_pmu_disable(struct pmu *pmu) x86_pmu.disable_all(); } -static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, - u64 enable_mask) -{ - if (hwc->extra_reg.reg) - wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); - wrmsrl(hwc->config_base, hwc->config | enable_mask); -} - -static void x86_pmu_enable_all(int added) +void x86_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; @@ -788,7 +488,7 @@ static inline int is_x86_event(struct perf_event *event) return event->pmu == &pmu; } -static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) +int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { struct event_constraint *c, *constraints[X86_PMC_IDX_MAX]; unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; @@ -959,7 +659,6 @@ static inline int match_prev_assignment(struct hw_perf_event *hwc, } static void x86_pmu_start(struct perf_event *event, int flags); -static void x86_pmu_stop(struct perf_event *event, int flags); static void x86_pmu_enable(struct pmu *pmu) { @@ -1031,21 +730,13 @@ static void x86_pmu_enable(struct pmu *pmu) x86_pmu.enable_all(added); } -static inline void x86_pmu_disable_event(struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - wrmsrl(hwc->config_base, hwc->config); -} - static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); /* * Set the next IRQ period, based on the hwc->period_left value. * To be called with the event disabled in hw: */ -static int -x86_perf_event_set_period(struct perf_event *event) +int x86_perf_event_set_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; s64 left = local64_read(&hwc->period_left); @@ -1105,7 +796,7 @@ x86_perf_event_set_period(struct perf_event *event) return ret; } -static void x86_pmu_enable_event(struct perf_event *event) +void x86_pmu_enable_event(struct perf_event *event) { if (__this_cpu_read(cpu_hw_events.enabled)) __x86_pmu_enable_event(&event->hw, @@ -1244,7 +935,7 @@ void perf_event_print_debug(void) local_irq_restore(flags); } -static void x86_pmu_stop(struct perf_event *event, int flags) +void x86_pmu_stop(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; @@ -1297,7 +988,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) perf_event_update_userpage(event); } -static int x86_pmu_handle_irq(struct pt_regs *regs) +int x86_pmu_handle_irq(struct pt_regs *regs) { struct perf_sample_data data; struct cpu_hw_events *cpuc; @@ -1367,109 +1058,28 @@ void perf_events_lapic_init(void) apic_write(APIC_LVTPC, APIC_DM_NMI); } -struct pmu_nmi_state { - unsigned int marked; - int handled; -}; - -static DEFINE_PER_CPU(struct pmu_nmi_state, pmu_nmi); - static int __kprobes -perf_event_nmi_handler(struct notifier_block *self, - unsigned long cmd, void *__args) +perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { - struct die_args *args = __args; - unsigned int this_nmi; - int handled; - if (!atomic_read(&active_events)) - return NOTIFY_DONE; - - switch (cmd) { - case DIE_NMI: - break; - case DIE_NMIUNKNOWN: - this_nmi = percpu_read(irq_stat.__nmi_count); - if (this_nmi != __this_cpu_read(pmu_nmi.marked)) - /* let the kernel handle the unknown nmi */ - return NOTIFY_DONE; - /* - * This one is a PMU back-to-back nmi. Two events - * trigger 'simultaneously' raising two back-to-back - * NMIs. If the first NMI handles both, the latter - * will be empty and daze the CPU. So, we drop it to - * avoid false-positive 'unknown nmi' messages. - */ - return NOTIFY_STOP; - default: - return NOTIFY_DONE; - } - - handled = x86_pmu.handle_irq(args->regs); - if (!handled) - return NOTIFY_DONE; - - this_nmi = percpu_read(irq_stat.__nmi_count); - if ((handled > 1) || - /* the next nmi could be a back-to-back nmi */ - ((__this_cpu_read(pmu_nmi.marked) == this_nmi) && - (__this_cpu_read(pmu_nmi.handled) > 1))) { - /* - * We could have two subsequent back-to-back nmis: The - * first handles more than one counter, the 2nd - * handles only one counter and the 3rd handles no - * counter. - * - * This is the 2nd nmi because the previous was - * handling more than one counter. We will mark the - * next (3rd) and then drop it if unhandled. - */ - __this_cpu_write(pmu_nmi.marked, this_nmi + 1); - __this_cpu_write(pmu_nmi.handled, handled); - } + return NMI_DONE; - return NOTIFY_STOP; + return x86_pmu.handle_irq(regs); } -static __read_mostly struct notifier_block perf_event_nmi_notifier = { - .notifier_call = perf_event_nmi_handler, - .next = NULL, - .priority = NMI_LOCAL_LOW_PRIOR, -}; - -static struct event_constraint unconstrained; -static struct event_constraint emptyconstraint; - -static struct event_constraint * -x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) -{ - struct event_constraint *c; - - if (x86_pmu.event_constraints) { - for_each_event_constraint(c, x86_pmu.event_constraints) { - if ((event->hw.config & c->cmask) == c->code) - return c; - } - } - - return &unconstrained; -} - -#include "perf_event_amd.c" -#include "perf_event_p6.c" -#include "perf_event_p4.c" -#include "perf_event_intel_lbr.c" -#include "perf_event_intel_ds.c" -#include "perf_event_intel.c" +struct event_constraint emptyconstraint; +struct event_constraint unconstrained; static int __cpuinit x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); int ret = NOTIFY_OK; switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: + cpuc->kfree_on_online = NULL; if (x86_pmu.cpu_prepare) ret = x86_pmu.cpu_prepare(cpu); break; @@ -1479,6 +1089,10 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) x86_pmu.cpu_starting(cpu); break; + case CPU_ONLINE: + kfree(cpuc->kfree_on_online); + break; + case CPU_DYING: if (x86_pmu.cpu_dying) x86_pmu.cpu_dying(cpu); @@ -1557,7 +1171,7 @@ static int __init init_hw_perf_events(void) ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED; perf_events_lapic_init(); - register_die_notifier(&perf_event_nmi_notifier); + register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI"); unconstrained = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h new file mode 100644 index 000000000000..b9698d40ac4b --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event.h @@ -0,0 +1,505 @@ +/* + * Performance events x86 architecture header + * + * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2009 Jaswinder Singh Rajput + * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> + * Copyright (C) 2009 Google, Inc., Stephane Eranian + * + * For licencing details see kernel-base/COPYING + */ + +#include <linux/perf_event.h> + +/* + * | NHM/WSM | SNB | + * register ------------------------------- + * | HT | no HT | HT | no HT | + *----------------------------------------- + * offcore | core | core | cpu | core | + * lbr_sel | core | core | cpu | core | + * ld_lat | cpu | core | cpu | core | + *----------------------------------------- + * + * Given that there is a small number of shared regs, + * we can pre-allocate their slot in the per-cpu + * per-core reg tables. + */ +enum extra_reg_type { + EXTRA_REG_NONE = -1, /* not used */ + + EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ + EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ + + EXTRA_REG_MAX /* number of entries needed */ +}; + +struct event_constraint { + union { + unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + u64 idxmsk64; + }; + u64 code; + u64 cmask; + int weight; +}; + +struct amd_nb { + int nb_id; /* NorthBridge id */ + int refcnt; /* reference count */ + struct perf_event *owners[X86_PMC_IDX_MAX]; + struct event_constraint event_constraints[X86_PMC_IDX_MAX]; +}; + +/* The maximal number of PEBS events: */ +#define MAX_PEBS_EVENTS 4 + +/* + * A debug store configuration. + * + * We only support architectures that use 64bit fields. + */ +struct debug_store { + u64 bts_buffer_base; + u64 bts_index; + u64 bts_absolute_maximum; + u64 bts_interrupt_threshold; + u64 pebs_buffer_base; + u64 pebs_index; + u64 pebs_absolute_maximum; + u64 pebs_interrupt_threshold; + u64 pebs_event_reset[MAX_PEBS_EVENTS]; +}; + +/* + * Per register state. + */ +struct er_account { + raw_spinlock_t lock; /* per-core: protect structure */ + u64 config; /* extra MSR config */ + u64 reg; /* extra MSR number */ + atomic_t ref; /* reference count */ +}; + +/* + * Per core/cpu state + * + * Used to coordinate shared registers between HT threads or + * among events on a single PMU. + */ +struct intel_shared_regs { + struct er_account regs[EXTRA_REG_MAX]; + int refcnt; /* per-core: #HT threads */ + unsigned core_id; /* per-core: core id */ +}; + +#define MAX_LBR_ENTRIES 16 + +struct cpu_hw_events { + /* + * Generic x86 PMC bits + */ + struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ + unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + int enabled; + + int n_events; + int n_added; + int n_txn; + int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ + u64 tags[X86_PMC_IDX_MAX]; + struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ + + unsigned int group_flag; + + /* + * Intel DebugStore bits + */ + struct debug_store *ds; + u64 pebs_enabled; + + /* + * Intel LBR bits + */ + int lbr_users; + void *lbr_context; + struct perf_branch_stack lbr_stack; + struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; + + /* + * Intel host/guest exclude bits + */ + u64 intel_ctrl_guest_mask; + u64 intel_ctrl_host_mask; + struct perf_guest_switch_msr guest_switch_msrs[X86_PMC_IDX_MAX]; + + /* + * manage shared (per-core, per-cpu) registers + * used on Intel NHM/WSM/SNB + */ + struct intel_shared_regs *shared_regs; + + /* + * AMD specific bits + */ + struct amd_nb *amd_nb; + + void *kfree_on_online; +}; + +#define __EVENT_CONSTRAINT(c, n, m, w) {\ + { .idxmsk64 = (n) }, \ + .code = (c), \ + .cmask = (m), \ + .weight = (w), \ +} + +#define EVENT_CONSTRAINT(c, n, m) \ + __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n)) + +/* + * Constraint on the Event code. + */ +#define INTEL_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) + +/* + * Constraint on the Event code + UMask + fixed-mask + * + * filter mask to validate fixed counter events. + * the following filters disqualify for fixed counters: + * - inv + * - edge + * - cnt-mask + * The other filters are supported by fixed counters. + * The any-thread option is supported starting with v3. + */ +#define FIXED_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK) + +/* + * Constraint on the Event code + UMask + */ +#define INTEL_UEVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) + +#define EVENT_CONSTRAINT_END \ + EVENT_CONSTRAINT(0, 0, 0) + +#define for_each_event_constraint(e, c) \ + for ((e) = (c); (e)->weight; (e)++) + +/* + * Extra registers for specific events. + * + * Some events need large masks and require external MSRs. + * Those extra MSRs end up being shared for all events on + * a PMU and sometimes between PMU of sibling HT threads. + * In either case, the kernel needs to handle conflicting + * accesses to those extra, shared, regs. The data structure + * to manage those registers is stored in cpu_hw_event. + */ +struct extra_reg { + unsigned int event; + unsigned int msr; + u64 config_mask; + u64 valid_mask; + int idx; /* per_xxx->regs[] reg index */ +}; + +#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ + .event = (e), \ + .msr = (ms), \ + .config_mask = (m), \ + .valid_mask = (vm), \ + .idx = EXTRA_REG_##i \ + } + +#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ + EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx) + +#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0) + +union perf_capabilities { + struct { + u64 lbr_format:6; + u64 pebs_trap:1; + u64 pebs_arch_reg:1; + u64 pebs_format:4; + u64 smm_freeze:1; + }; + u64 capabilities; +}; + +/* + * struct x86_pmu - generic x86 pmu + */ +struct x86_pmu { + /* + * Generic x86 PMC bits + */ + const char *name; + int version; + int (*handle_irq)(struct pt_regs *); + void (*disable_all)(void); + void (*enable_all)(int added); + void (*enable)(struct perf_event *); + void (*disable)(struct perf_event *); + int (*hw_config)(struct perf_event *event); + int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); + unsigned eventsel; + unsigned perfctr; + u64 (*event_map)(int); + int max_events; + int num_counters; + int num_counters_fixed; + int cntval_bits; + u64 cntval_mask; + int apic; + u64 max_period; + struct event_constraint * + (*get_event_constraints)(struct cpu_hw_events *cpuc, + struct perf_event *event); + + void (*put_event_constraints)(struct cpu_hw_events *cpuc, + struct perf_event *event); + struct event_constraint *event_constraints; + void (*quirks)(void); + int perfctr_second_write; + + int (*cpu_prepare)(int cpu); + void (*cpu_starting)(int cpu); + void (*cpu_dying)(int cpu); + void (*cpu_dead)(int cpu); + + /* + * Intel Arch Perfmon v2+ + */ + u64 intel_ctrl; + union perf_capabilities intel_cap; + + /* + * Intel DebugStore bits + */ + int bts, pebs; + int bts_active, pebs_active; + int pebs_record_size; + void (*drain_pebs)(struct pt_regs *regs); + struct event_constraint *pebs_constraints; + + /* + * Intel LBR + */ + unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ + int lbr_nr; /* hardware stack size */ + + /* + * Extra registers for events + */ + struct extra_reg *extra_regs; + unsigned int er_flags; + + /* + * Intel host/guest support (KVM) + */ + struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr); +}; + +#define ERF_NO_HT_SHARING 1 +#define ERF_HAS_RSP_1 2 + +extern struct x86_pmu x86_pmu __read_mostly; + +DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events); + +int x86_perf_event_set_period(struct perf_event *event); + +/* + * Generalized hw caching related hw_event table, filled + * in on a per model basis. A value of 0 means + * 'not supported', -1 means 'hw_event makes no sense on + * this CPU', any other value means the raw hw_event + * ID. + */ + +#define C(x) PERF_COUNT_HW_CACHE_##x + +extern u64 __read_mostly hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; +extern u64 __read_mostly hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; + +u64 x86_perf_event_update(struct perf_event *event); + +static inline int x86_pmu_addr_offset(int index) +{ + int offset; + + /* offset = X86_FEATURE_PERFCTR_CORE ? index << 1 : index */ + alternative_io(ASM_NOP2, + "shll $1, %%eax", + X86_FEATURE_PERFCTR_CORE, + "=a" (offset), + "a" (index)); + + return offset; +} + +static inline unsigned int x86_pmu_config_addr(int index) +{ + return x86_pmu.eventsel + x86_pmu_addr_offset(index); +} + +static inline unsigned int x86_pmu_event_addr(int index) +{ + return x86_pmu.perfctr + x86_pmu_addr_offset(index); +} + +int x86_setup_perfctr(struct perf_event *event); + +int x86_pmu_hw_config(struct perf_event *event); + +void x86_pmu_disable_all(void); + +static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, + u64 enable_mask) +{ + if (hwc->extra_reg.reg) + wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); + wrmsrl(hwc->config_base, hwc->config | enable_mask); +} + +void x86_pmu_enable_all(int added); + +int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign); + +void x86_pmu_stop(struct perf_event *event, int flags); + +static inline void x86_pmu_disable_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + wrmsrl(hwc->config_base, hwc->config); +} + +void x86_pmu_enable_event(struct perf_event *event); + +int x86_pmu_handle_irq(struct pt_regs *regs); + +extern struct event_constraint emptyconstraint; + +extern struct event_constraint unconstrained; + +#ifdef CONFIG_CPU_SUP_AMD + +int amd_pmu_init(void); + +#else /* CONFIG_CPU_SUP_AMD */ + +static inline int amd_pmu_init(void) +{ + return 0; +} + +#endif /* CONFIG_CPU_SUP_AMD */ + +#ifdef CONFIG_CPU_SUP_INTEL + +int intel_pmu_save_and_restart(struct perf_event *event); + +struct event_constraint * +x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event); + +struct intel_shared_regs *allocate_shared_regs(int cpu); + +int intel_pmu_init(void); + +void init_debug_store_on_cpu(int cpu); + +void fini_debug_store_on_cpu(int cpu); + +void release_ds_buffers(void); + +void reserve_ds_buffers(void); + +extern struct event_constraint bts_constraint; + +void intel_pmu_enable_bts(u64 config); + +void intel_pmu_disable_bts(void); + +int intel_pmu_drain_bts_buffer(void); + +extern struct event_constraint intel_core2_pebs_event_constraints[]; + +extern struct event_constraint intel_atom_pebs_event_constraints[]; + +extern struct event_constraint intel_nehalem_pebs_event_constraints[]; + +extern struct event_constraint intel_westmere_pebs_event_constraints[]; + +extern struct event_constraint intel_snb_pebs_event_constraints[]; + +struct event_constraint *intel_pebs_constraints(struct perf_event *event); + +void intel_pmu_pebs_enable(struct perf_event *event); + +void intel_pmu_pebs_disable(struct perf_event *event); + +void intel_pmu_pebs_enable_all(void); + +void intel_pmu_pebs_disable_all(void); + +void intel_ds_init(void); + +void intel_pmu_lbr_reset(void); + +void intel_pmu_lbr_enable(struct perf_event *event); + +void intel_pmu_lbr_disable(struct perf_event *event); + +void intel_pmu_lbr_enable_all(void); + +void intel_pmu_lbr_disable_all(void); + +void intel_pmu_lbr_read(void); + +void intel_pmu_lbr_init_core(void); + +void intel_pmu_lbr_init_nhm(void); + +void intel_pmu_lbr_init_atom(void); + +int p4_pmu_init(void); + +int p6_pmu_init(void); + +#else /* CONFIG_CPU_SUP_INTEL */ + +static inline void reserve_ds_buffers(void) +{ +} + +static inline void release_ds_buffers(void) +{ +} + +static inline int intel_pmu_init(void) +{ + return 0; +} + +static inline struct intel_shared_regs *allocate_shared_regs(int cpu) +{ + return NULL; +} + +#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 941caa2e449b..aeefd45697a2 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -1,4 +1,10 @@ -#ifdef CONFIG_CPU_SUP_AMD +#include <linux/perf_event.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <asm/apicdef.h> + +#include "perf_event.h" static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] @@ -132,6 +138,19 @@ static int amd_pmu_hw_config(struct perf_event *event) if (ret) return ret; + if (event->attr.exclude_host && event->attr.exclude_guest) + /* + * When HO == GO == 1 the hardware treats that as GO == HO == 0 + * and will count in both modes. We don't want to count in that + * case so we emulate no-counting by setting US = OS = 0. + */ + event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR | + ARCH_PERFMON_EVENTSEL_OS); + else if (event->attr.exclude_host) + event->hw.config |= AMD_PERFMON_EVENTSEL_GUESTONLY; + else if (event->attr.exclude_guest) + event->hw.config |= AMD_PERFMON_EVENTSEL_HOSTONLY; + if (event->attr.type != PERF_TYPE_RAW) return 0; @@ -350,7 +369,7 @@ static void amd_pmu_cpu_starting(int cpu) continue; if (nb->nb_id == nb_id) { - kfree(cpuc->amd_nb); + cpuc->kfree_on_online = cpuc->amd_nb; cpuc->amd_nb = nb; break; } @@ -392,7 +411,7 @@ static __initconst const struct x86_pmu amd_pmu = { .perfctr = MSR_K7_PERFCTR0, .event_map = amd_pmu_event_map, .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_counters = 4, + .num_counters = AMD64_NUM_COUNTERS, .cntval_bits = 48, .cntval_mask = (1ULL << 48) - 1, .apic = 1, @@ -556,7 +575,7 @@ static __initconst const struct x86_pmu amd_pmu_f15h = { .perfctr = MSR_F15H_PERF_CTR, .event_map = amd_pmu_event_map, .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_counters = 6, + .num_counters = AMD64_NUM_COUNTERS_F15H, .cntval_bits = 48, .cntval_mask = (1ULL << 48) - 1, .apic = 1, @@ -573,7 +592,7 @@ static __initconst const struct x86_pmu amd_pmu_f15h = { #endif }; -static __init int amd_pmu_init(void) +__init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ if (boot_cpu_data.x86 < 6) @@ -602,12 +621,3 @@ static __init int amd_pmu_init(void) return 0; } - -#else /* CONFIG_CPU_SUP_AMD */ - -static int amd_pmu_init(void) -{ - return 0; -} - -#endif diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c new file mode 100644 index 000000000000..ab6343d21825 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -0,0 +1,294 @@ +/* + * Performance events - AMD IBS + * + * Copyright (C) 2011 Advanced Micro Devices, Inc., Robert Richter + * + * For licencing details see kernel-base/COPYING + */ + +#include <linux/perf_event.h> +#include <linux/module.h> +#include <linux/pci.h> + +#include <asm/apic.h> + +static u32 ibs_caps; + +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) + +static struct pmu perf_ibs; + +static int perf_ibs_init(struct perf_event *event) +{ + if (perf_ibs.type != event->attr.type) + return -ENOENT; + return 0; +} + +static int perf_ibs_add(struct perf_event *event, int flags) +{ + return 0; +} + +static void perf_ibs_del(struct perf_event *event, int flags) +{ +} + +static struct pmu perf_ibs = { + .event_init= perf_ibs_init, + .add= perf_ibs_add, + .del= perf_ibs_del, +}; + +static __init int perf_event_ibs_init(void) +{ + if (!ibs_caps) + return -ENODEV; /* ibs not supported by the cpu */ + + perf_pmu_register(&perf_ibs, "ibs", -1); + printk(KERN_INFO "perf: AMD IBS detected (0x%08x)\n", ibs_caps); + + return 0; +} + +#else /* defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) */ + +static __init int perf_event_ibs_init(void) { return 0; } + +#endif + +/* IBS - apic initialization, for perf and oprofile */ + +static __init u32 __get_ibs_caps(void) +{ + u32 caps; + unsigned int max_level; + + if (!boot_cpu_has(X86_FEATURE_IBS)) + return 0; + + /* check IBS cpuid feature flags */ + max_level = cpuid_eax(0x80000000); + if (max_level < IBS_CPUID_FEATURES) + return IBS_CAPS_DEFAULT; + + caps = cpuid_eax(IBS_CPUID_FEATURES); + if (!(caps & IBS_CAPS_AVAIL)) + /* cpuid flags not valid */ + return IBS_CAPS_DEFAULT; + + return caps; +} + +u32 get_ibs_caps(void) +{ + return ibs_caps; +} + +EXPORT_SYMBOL(get_ibs_caps); + +static inline int get_eilvt(int offset) +{ + return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1); +} + +static inline int put_eilvt(int offset) +{ + return !setup_APIC_eilvt(offset, 0, 0, 1); +} + +/* + * Check and reserve APIC extended interrupt LVT offset for IBS if available. + */ +static inline int ibs_eilvt_valid(void) +{ + int offset; + u64 val; + int valid = 0; + + preempt_disable(); + + rdmsrl(MSR_AMD64_IBSCTL, val); + offset = val & IBSCTL_LVT_OFFSET_MASK; + + if (!(val & IBSCTL_LVT_OFFSET_VALID)) { + pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n", + smp_processor_id(), offset, MSR_AMD64_IBSCTL, val); + goto out; + } + + if (!get_eilvt(offset)) { + pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n", + smp_processor_id(), offset, MSR_AMD64_IBSCTL, val); + goto out; + } + + valid = 1; +out: + preempt_enable(); + + return valid; +} + +static int setup_ibs_ctl(int ibs_eilvt_off) +{ + struct pci_dev *cpu_cfg; + int nodes; + u32 value = 0; + + nodes = 0; + cpu_cfg = NULL; + do { + cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD, + PCI_DEVICE_ID_AMD_10H_NB_MISC, + cpu_cfg); + if (!cpu_cfg) + break; + ++nodes; + pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off + | IBSCTL_LVT_OFFSET_VALID); + pci_read_config_dword(cpu_cfg, IBSCTL, &value); + if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) { + pci_dev_put(cpu_cfg); + printk(KERN_DEBUG "Failed to setup IBS LVT offset, " + "IBSCTL = 0x%08x\n", value); + return -EINVAL; + } + } while (1); + + if (!nodes) { + printk(KERN_DEBUG "No CPU node configured for IBS\n"); + return -ENODEV; + } + + return 0; +} + +/* + * This runs only on the current cpu. We try to find an LVT offset and + * setup the local APIC. For this we must disable preemption. On + * success we initialize all nodes with this offset. This updates then + * the offset in the IBS_CTL per-node msr. The per-core APIC setup of + * the IBS interrupt vector is handled by perf_ibs_cpu_notifier that + * is using the new offset. + */ +static int force_ibs_eilvt_setup(void) +{ + int offset; + int ret; + + preempt_disable(); + /* find the next free available EILVT entry, skip offset 0 */ + for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) { + if (get_eilvt(offset)) + break; + } + preempt_enable(); + + if (offset == APIC_EILVT_NR_MAX) { + printk(KERN_DEBUG "No EILVT entry available\n"); + return -EBUSY; + } + + ret = setup_ibs_ctl(offset); + if (ret) + goto out; + + if (!ibs_eilvt_valid()) { + ret = -EFAULT; + goto out; + } + + pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset); + pr_err(FW_BUG "workaround enabled for IBS LVT offset\n"); + + return 0; +out: + preempt_disable(); + put_eilvt(offset); + preempt_enable(); + return ret; +} + +static inline int get_ibs_lvt_offset(void) +{ + u64 val; + + rdmsrl(MSR_AMD64_IBSCTL, val); + if (!(val & IBSCTL_LVT_OFFSET_VALID)) + return -EINVAL; + + return val & IBSCTL_LVT_OFFSET_MASK; +} + +static void setup_APIC_ibs(void *dummy) +{ + int offset; + + offset = get_ibs_lvt_offset(); + if (offset < 0) + goto failed; + + if (!setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 0)) + return; +failed: + pr_warn("perf: IBS APIC setup failed on cpu #%d\n", + smp_processor_id()); +} + +static void clear_APIC_ibs(void *dummy) +{ + int offset; + + offset = get_ibs_lvt_offset(); + if (offset >= 0) + setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1); +} + +static int __cpuinit +perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_STARTING: + setup_APIC_ibs(NULL); + break; + case CPU_DYING: + clear_APIC_ibs(NULL); + break; + default: + break; + } + + return NOTIFY_OK; +} + +static __init int amd_ibs_init(void) +{ + u32 caps; + int ret; + + caps = __get_ibs_caps(); + if (!caps) + return -ENODEV; /* ibs not supported by the cpu */ + + if (!ibs_eilvt_valid()) { + ret = force_ibs_eilvt_setup(); + if (ret) { + pr_err("Failed to setup IBS, %d\n", ret); + return ret; + } + } + + get_online_cpus(); + ibs_caps = caps; + /* make ibs_caps visible to other cpus: */ + smp_mb(); + perf_cpu_notifier(perf_ibs_cpu_notifier); + smp_call_function(setup_APIC_ibs, NULL, 1); + put_online_cpus(); + + return perf_event_ibs_init(); +} + +/* Since we need the pci subsystem to init ibs we can't do this earlier: */ +device_initcall(amd_ibs_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index f88af2c2a561..e09ca20e86ee 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1,16 +1,19 @@ -#ifdef CONFIG_CPU_SUP_INTEL - /* * Per core/cpu state * * Used to coordinate shared registers between HT threads or * among events on a single PMU. */ -struct intel_shared_regs { - struct er_account regs[EXTRA_REG_MAX]; - int refcnt; /* per-core: #HT threads */ - unsigned core_id; /* per-core: core id */ -}; + +#include <linux/stddef.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/slab.h> + +#include <asm/hardirq.h> +#include <asm/apic.h> + +#include "perf_event.h" /* * Intel PerfMon, used on Core and later. @@ -746,7 +749,8 @@ static void intel_pmu_enable_all(int added) intel_pmu_pebs_enable_all(); intel_pmu_lbr_enable_all(); - wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl); + wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, + x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask); if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) { struct perf_event *event = @@ -869,6 +873,7 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc) static void intel_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) { intel_pmu_disable_bts(); @@ -876,6 +881,9 @@ static void intel_pmu_disable_event(struct perf_event *event) return; } + cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx); + cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_disable_fixed(hwc); return; @@ -921,6 +929,7 @@ static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) static void intel_pmu_enable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) { if (!__this_cpu_read(cpu_hw_events.enabled)) @@ -930,6 +939,11 @@ static void intel_pmu_enable_event(struct perf_event *event) return; } + if (event->attr.exclude_host) + cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx); + if (event->attr.exclude_guest) + cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx); + if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { intel_pmu_enable_fixed(hwc); return; @@ -945,7 +959,7 @@ static void intel_pmu_enable_event(struct perf_event *event) * Save and restart an expired event. Called by NMI contexts, * so it has to be careful about preempting normal event ops: */ -static int intel_pmu_save_and_restart(struct perf_event *event) +int intel_pmu_save_and_restart(struct perf_event *event) { x86_perf_event_update(event); return x86_perf_event_set_period(event); @@ -1197,6 +1211,21 @@ intel_shared_regs_constraints(struct cpu_hw_events *cpuc, return c; } +struct event_constraint * +x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct event_constraint *c; + + if (x86_pmu.event_constraints) { + for_each_event_constraint(c, x86_pmu.event_constraints) { + if ((event->hw.config & c->cmask) == c->code) + return c; + } + } + + return &unconstrained; +} + static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { @@ -1284,12 +1313,84 @@ static int intel_pmu_hw_config(struct perf_event *event) return 0; } +struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr) +{ + if (x86_pmu.guest_get_msrs) + return x86_pmu.guest_get_msrs(nr); + *nr = 0; + return NULL; +} +EXPORT_SYMBOL_GPL(perf_guest_get_msrs); + +static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs; + + arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL; + arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask; + arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask; + + *nr = 1; + return arr; +} + +static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs; + int idx; + + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + struct perf_event *event = cpuc->events[idx]; + + arr[idx].msr = x86_pmu_config_addr(idx); + arr[idx].host = arr[idx].guest = 0; + + if (!test_bit(idx, cpuc->active_mask)) + continue; + + arr[idx].host = arr[idx].guest = + event->hw.config | ARCH_PERFMON_EVENTSEL_ENABLE; + + if (event->attr.exclude_host) + arr[idx].host &= ~ARCH_PERFMON_EVENTSEL_ENABLE; + else if (event->attr.exclude_guest) + arr[idx].guest &= ~ARCH_PERFMON_EVENTSEL_ENABLE; + } + + *nr = x86_pmu.num_counters; + return arr; +} + +static void core_pmu_enable_event(struct perf_event *event) +{ + if (!event->attr.exclude_host) + x86_pmu_enable_event(event); +} + +static void core_pmu_enable_all(int added) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int idx; + + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + struct hw_perf_event *hwc = &cpuc->events[idx]->hw; + + if (!test_bit(idx, cpuc->active_mask) || + cpuc->events[idx]->attr.exclude_host) + continue; + + __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); + } +} + static __initconst const struct x86_pmu core_pmu = { .name = "core", .handle_irq = x86_pmu_handle_irq, .disable_all = x86_pmu_disable_all, - .enable_all = x86_pmu_enable_all, - .enable = x86_pmu_enable_event, + .enable_all = core_pmu_enable_all, + .enable = core_pmu_enable_event, .disable = x86_pmu_disable_event, .hw_config = x86_pmu_hw_config, .schedule_events = x86_schedule_events, @@ -1307,9 +1408,10 @@ static __initconst const struct x86_pmu core_pmu = { .get_event_constraints = intel_get_event_constraints, .put_event_constraints = intel_put_event_constraints, .event_constraints = intel_core_event_constraints, + .guest_get_msrs = core_guest_get_msrs, }; -static struct intel_shared_regs *allocate_shared_regs(int cpu) +struct intel_shared_regs *allocate_shared_regs(int cpu) { struct intel_shared_regs *regs; int i; @@ -1362,7 +1464,7 @@ static void intel_pmu_cpu_starting(int cpu) pc = per_cpu(cpu_hw_events, i).shared_regs; if (pc && pc->core_id == core_id) { - kfree(cpuc->shared_regs); + cpuc->kfree_on_online = cpuc->shared_regs; cpuc->shared_regs = pc; break; } @@ -1413,6 +1515,7 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, + .guest_get_msrs = intel_guest_get_msrs, }; static void intel_clovertown_quirks(void) @@ -1441,7 +1544,7 @@ static void intel_clovertown_quirks(void) x86_pmu.pebs_constraints = NULL; } -static __init int intel_pmu_init(void) +__init int intel_pmu_init(void) { union cpuid10_edx edx; union cpuid10_eax eax; @@ -1597,7 +1700,7 @@ static __init int intel_pmu_init(void) intel_pmu_lbr_init_nhm(); x86_pmu.event_constraints = intel_snb_event_constraints; - x86_pmu.pebs_constraints = intel_snb_pebs_events; + x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; @@ -1628,16 +1731,3 @@ static __init int intel_pmu_init(void) } return 0; } - -#else /* CONFIG_CPU_SUP_INTEL */ - -static int intel_pmu_init(void) -{ - return 0; -} - -static struct intel_shared_regs *allocate_shared_regs(int cpu) -{ - return NULL; -} -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 1b1ef3addcfd..c0d238f49db8 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -1,7 +1,10 @@ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/bitops.h> +#include <linux/types.h> +#include <linux/slab.h> -/* The maximal number of PEBS events: */ -#define MAX_PEBS_EVENTS 4 +#include <asm/perf_event.h> + +#include "perf_event.h" /* The size of a BTS record in bytes: */ #define BTS_RECORD_SIZE 24 @@ -37,24 +40,7 @@ struct pebs_record_nhm { u64 status, dla, dse, lat; }; -/* - * A debug store configuration. - * - * We only support architectures that use 64bit fields. - */ -struct debug_store { - u64 bts_buffer_base; - u64 bts_index; - u64 bts_absolute_maximum; - u64 bts_interrupt_threshold; - u64 pebs_buffer_base; - u64 pebs_index; - u64 pebs_absolute_maximum; - u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; -}; - -static void init_debug_store_on_cpu(int cpu) +void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -66,7 +52,7 @@ static void init_debug_store_on_cpu(int cpu) (u32)((u64)(unsigned long)ds >> 32)); } -static void fini_debug_store_on_cpu(int cpu) +void fini_debug_store_on_cpu(int cpu) { if (!per_cpu(cpu_hw_events, cpu).ds) return; @@ -175,7 +161,7 @@ static void release_ds_buffer(int cpu) kfree(ds); } -static void release_ds_buffers(void) +void release_ds_buffers(void) { int cpu; @@ -194,7 +180,7 @@ static void release_ds_buffers(void) put_online_cpus(); } -static void reserve_ds_buffers(void) +void reserve_ds_buffers(void) { int bts_err = 0, pebs_err = 0; int cpu; @@ -260,10 +246,10 @@ static void reserve_ds_buffers(void) * BTS */ -static struct event_constraint bts_constraint = +struct event_constraint bts_constraint = EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0); -static void intel_pmu_enable_bts(u64 config) +void intel_pmu_enable_bts(u64 config) { unsigned long debugctlmsr; @@ -282,7 +268,7 @@ static void intel_pmu_enable_bts(u64 config) update_debugctlmsr(debugctlmsr); } -static void intel_pmu_disable_bts(void) +void intel_pmu_disable_bts(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); unsigned long debugctlmsr; @@ -299,7 +285,7 @@ static void intel_pmu_disable_bts(void) update_debugctlmsr(debugctlmsr); } -static int intel_pmu_drain_bts_buffer(void) +int intel_pmu_drain_bts_buffer(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -361,7 +347,7 @@ static int intel_pmu_drain_bts_buffer(void) /* * PEBS */ -static struct event_constraint intel_core2_pebs_event_constraints[] = { +struct event_constraint intel_core2_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ @@ -370,14 +356,14 @@ static struct event_constraint intel_core2_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint intel_atom_pebs_event_constraints[] = { +struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ EVENT_CONSTRAINT_END }; -static struct event_constraint intel_nehalem_pebs_event_constraints[] = { +struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ @@ -392,7 +378,7 @@ static struct event_constraint intel_nehalem_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint intel_westmere_pebs_event_constraints[] = { +struct event_constraint intel_westmere_pebs_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ @@ -407,7 +393,7 @@ static struct event_constraint intel_westmere_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint intel_snb_pebs_events[] = { +struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ @@ -428,8 +414,7 @@ static struct event_constraint intel_snb_pebs_events[] = { EVENT_CONSTRAINT_END }; -static struct event_constraint * -intel_pebs_constraints(struct perf_event *event) +struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -446,7 +431,7 @@ intel_pebs_constraints(struct perf_event *event) return &emptyconstraint; } -static void intel_pmu_pebs_enable(struct perf_event *event) +void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; @@ -460,7 +445,7 @@ static void intel_pmu_pebs_enable(struct perf_event *event) intel_pmu_lbr_enable(event); } -static void intel_pmu_pebs_disable(struct perf_event *event) +void intel_pmu_pebs_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; @@ -475,7 +460,7 @@ static void intel_pmu_pebs_disable(struct perf_event *event) intel_pmu_lbr_disable(event); } -static void intel_pmu_pebs_enable_all(void) +void intel_pmu_pebs_enable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -483,7 +468,7 @@ static void intel_pmu_pebs_enable_all(void) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); } -static void intel_pmu_pebs_disable_all(void) +void intel_pmu_pebs_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -576,8 +561,6 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 0; } -static int intel_pmu_save_and_restart(struct perf_event *event); - static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *__pebs) { @@ -716,7 +699,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * BTS, PEBS probe and setup */ -static void intel_ds_init(void) +void intel_ds_init(void) { /* * No support for 32bit formats @@ -749,15 +732,3 @@ static void intel_ds_init(void) } } } - -#else /* CONFIG_CPU_SUP_INTEL */ - -static void reserve_ds_buffers(void) -{ -} - -static void release_ds_buffers(void) -{ -} - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index d202c1bece1a..3fab3de3ce96 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -1,4 +1,10 @@ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/perf_event.h> +#include <linux/types.h> + +#include <asm/perf_event.h> +#include <asm/msr.h> + +#include "perf_event.h" enum { LBR_FORMAT_32 = 0x00, @@ -48,7 +54,7 @@ static void intel_pmu_lbr_reset_64(void) } } -static void intel_pmu_lbr_reset(void) +void intel_pmu_lbr_reset(void) { if (!x86_pmu.lbr_nr) return; @@ -59,7 +65,7 @@ static void intel_pmu_lbr_reset(void) intel_pmu_lbr_reset_64(); } -static void intel_pmu_lbr_enable(struct perf_event *event) +void intel_pmu_lbr_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -81,7 +87,7 @@ static void intel_pmu_lbr_enable(struct perf_event *event) cpuc->lbr_users++; } -static void intel_pmu_lbr_disable(struct perf_event *event) +void intel_pmu_lbr_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -95,7 +101,7 @@ static void intel_pmu_lbr_disable(struct perf_event *event) __intel_pmu_lbr_disable(); } -static void intel_pmu_lbr_enable_all(void) +void intel_pmu_lbr_enable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -103,7 +109,7 @@ static void intel_pmu_lbr_enable_all(void) __intel_pmu_lbr_enable(); } -static void intel_pmu_lbr_disable_all(void) +void intel_pmu_lbr_disable_all(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -178,7 +184,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) cpuc->lbr_stack.nr = i; } -static void intel_pmu_lbr_read(void) +void intel_pmu_lbr_read(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -191,7 +197,7 @@ static void intel_pmu_lbr_read(void) intel_pmu_lbr_read_64(cpuc); } -static void intel_pmu_lbr_init_core(void) +void intel_pmu_lbr_init_core(void) { x86_pmu.lbr_nr = 4; x86_pmu.lbr_tos = 0x01c9; @@ -199,7 +205,7 @@ static void intel_pmu_lbr_init_core(void) x86_pmu.lbr_to = 0x60; } -static void intel_pmu_lbr_init_nhm(void) +void intel_pmu_lbr_init_nhm(void) { x86_pmu.lbr_nr = 16; x86_pmu.lbr_tos = 0x01c9; @@ -207,12 +213,10 @@ static void intel_pmu_lbr_init_nhm(void) x86_pmu.lbr_to = 0x6c0; } -static void intel_pmu_lbr_init_atom(void) +void intel_pmu_lbr_init_atom(void) { x86_pmu.lbr_nr = 8; x86_pmu.lbr_tos = 0x01c9; x86_pmu.lbr_from = 0x40; x86_pmu.lbr_to = 0x60; } - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 7809d2bcb209..492bf1358a7c 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -7,9 +7,13 @@ * For licencing details see kernel-base/COPYING */ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/perf_event.h> #include <asm/perf_event_p4.h> +#include <asm/hardirq.h> +#include <asm/apic.h> + +#include "perf_event.h" #define P4_CNTR_LIMIT 3 /* @@ -1303,7 +1307,7 @@ static __initconst const struct x86_pmu p4_pmu = { .perfctr_second_write = 1, }; -static __init int p4_pmu_init(void) +__init int p4_pmu_init(void) { unsigned int low, high; @@ -1326,5 +1330,3 @@ static __init int p4_pmu_init(void) return 0; } - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index 20c097e33860..c7181befecde 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -1,4 +1,7 @@ -#ifdef CONFIG_CPU_SUP_INTEL +#include <linux/perf_event.h> +#include <linux/types.h> + +#include "perf_event.h" /* * Not sure about some of these @@ -114,7 +117,7 @@ static __initconst const struct x86_pmu p6_pmu = { .event_constraints = p6_event_constraints, }; -static __init int p6_pmu_init(void) +__init int p6_pmu_init(void) { switch (boot_cpu_data.x86_model) { case 1: @@ -138,5 +141,3 @@ static __init int p6_pmu_init(void) return 0; } - -#endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 62ac8cb6ba27..14b23140e81f 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -85,6 +85,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "stepping\t: %d\n", c->x86_mask); else seq_printf(m, "stepping\t: unknown\n"); + if (c->microcode) + seq_printf(m, "microcode\t: 0x%x\n", c->microcode); if (cpu_has(c, X86_FEATURE_TSC)) { unsigned int freq = cpufreq_quick_get(cpu); diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c new file mode 100644 index 000000000000..feca286c2bb4 --- /dev/null +++ b/arch/x86/kernel/cpu/rdrand.c @@ -0,0 +1,73 @@ +/* + * This file is part of the Linux kernel. + * + * Copyright (c) 2011, Intel Corporation + * Authors: Fenghua Yu <fenghua.yu@intel.com>, + * H. Peter Anvin <hpa@linux.intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * + */ + +#include <asm/processor.h> +#include <asm/archrandom.h> +#include <asm/sections.h> + +static int __init x86_rdrand_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_RDRAND); + return 1; +} +__setup("nordrand", x86_rdrand_setup); + +/* We can't use arch_get_random_long() here since alternatives haven't run */ +static inline int rdrand_long(unsigned long *v) +{ + int ok; + asm volatile("1: " RDRAND_LONG "\n\t" + "jc 2f\n\t" + "decl %0\n\t" + "jnz 1b\n\t" + "2:" + : "=r" (ok), "=a" (*v) + : "0" (RDRAND_RETRY_LOOPS)); + return ok; +} + +/* + * Force a reseed cycle; we are architecturally guaranteed a reseed + * after no more than 512 128-bit chunks of random data. This also + * acts as a test of the CPU capability. + */ +#define RESEED_LOOP ((512*128)/sizeof(unsigned long)) + +void __cpuinit x86_init_rdrand(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_ARCH_RANDOM + unsigned long tmp; + int i, count, ok; + + if (!cpu_has(c, X86_FEATURE_RDRAND)) + return; /* Nothing to do */ + + for (count = i = 0; i < RESEED_LOOP; i++) { + ok = rdrand_long(&tmp); + if (ok) + count++; + } + + if (count != RESEED_LOOP) + clear_cpu_cap(c, X86_FEATURE_RDRAND); +#endif +} diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 764c7c2b1811..13ad89971d47 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -32,15 +32,12 @@ int in_crash_kexec; #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) -static void kdump_nmi_callback(int cpu, struct die_args *args) +static void kdump_nmi_callback(int cpu, struct pt_regs *regs) { - struct pt_regs *regs; #ifdef CONFIG_X86_32 struct pt_regs fixed_regs; #endif - regs = args->regs; - #ifdef CONFIG_X86_32 if (!user_mode_vm(regs)) { crash_fixup_ss_esp(&fixed_regs, regs); diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 6419bb05ecd5..faf8d5e74b0b 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -331,10 +331,15 @@ ENDPROC(native_usergs_sysret64) 1: incl PER_CPU_VAR(irq_count) jne 2f mov PER_CPU_VAR(irq_stack_ptr),%rsp - EMPTY_FRAME 0 + CFI_DEF_CFA_REGISTER rsi 2: /* Store previous stack value */ pushq %rsi + CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \ + 0x77 /* DW_OP_breg7 */, 0, \ + 0x06 /* DW_OP_deref */, \ + 0x08 /* DW_OP_const1u */, SS+8-RBP, \ + 0x22 /* DW_OP_plus */ /* We entered an interrupt context - irqs are off: */ TRACE_IRQS_OFF .endm @@ -788,7 +793,6 @@ END(interrupt) subq $ORIG_RAX-RBP, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP SAVE_ARGS_IRQ - PARTIAL_FRAME 0 call \func .endm @@ -813,10 +817,10 @@ ret_from_intr: /* Restore saved previous stack */ popq %rsi - leaq 16(%rsi), %rsp - + CFI_DEF_CFA_REGISTER rsi + leaq ARGOFFSET-RBP(%rsi), %rsp CFI_DEF_CFA_REGISTER rsp - CFI_ADJUST_CFA_OFFSET -16 + CFI_ADJUST_CFA_OFFSET RBP-ARGOFFSET exit_intr: GET_THREAD_INFO(%rcx) diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 3fee346ef545..cacdd46d184d 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -42,7 +42,7 @@ void arch_jump_label_transform(struct jump_entry *entry, put_online_cpus(); } -void arch_jump_label_text_poke_early(jump_label_t addr) +void __init_or_module arch_jump_label_text_poke_early(jump_label_t addr) { text_poke_early((void *)addr, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE); diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 00354d4919a9..faba5771acad 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -511,28 +511,37 @@ single_step_cont(struct pt_regs *regs, struct die_args *args) static int was_in_debug_nmi[NR_CPUS]; -static int __kgdb_notify(struct die_args *args, unsigned long cmd) +static int kgdb_nmi_handler(unsigned int cmd, struct pt_regs *regs) { - struct pt_regs *regs = args->regs; - switch (cmd) { - case DIE_NMI: + case NMI_LOCAL: if (atomic_read(&kgdb_active) != -1) { /* KGDB CPU roundup */ kgdb_nmicallback(raw_smp_processor_id(), regs); was_in_debug_nmi[raw_smp_processor_id()] = 1; touch_nmi_watchdog(); - return NOTIFY_STOP; + return NMI_HANDLED; } - return NOTIFY_DONE; + break; - case DIE_NMIUNKNOWN: + case NMI_UNKNOWN: if (was_in_debug_nmi[raw_smp_processor_id()]) { was_in_debug_nmi[raw_smp_processor_id()] = 0; - return NOTIFY_STOP; + return NMI_HANDLED; } - return NOTIFY_DONE; + break; + default: + /* do nothing */ + break; + } + return NMI_DONE; +} + +static int __kgdb_notify(struct die_args *args, unsigned long cmd) +{ + struct pt_regs *regs = args->regs; + switch (cmd) { case DIE_DEBUG: if (atomic_read(&kgdb_cpu_doing_single_step) != -1) { if (user_mode(regs)) @@ -590,11 +599,6 @@ kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr) static struct notifier_block kgdb_notifier = { .notifier_call = kgdb_notify, - - /* - * Lowest-prio notifier priority, we want to be notified last: - */ - .priority = NMI_LOCAL_LOW_PRIOR, }; /** @@ -605,7 +609,31 @@ static struct notifier_block kgdb_notifier = { */ int kgdb_arch_init(void) { - return register_die_notifier(&kgdb_notifier); + int retval; + + retval = register_die_notifier(&kgdb_notifier); + if (retval) + goto out; + + retval = register_nmi_handler(NMI_LOCAL, kgdb_nmi_handler, + 0, "kgdb"); + if (retval) + goto out1; + + retval = register_nmi_handler(NMI_UNKNOWN, kgdb_nmi_handler, + 0, "kgdb"); + + if (retval) + goto out2; + + return retval; + +out2: + unregister_nmi_handler(NMI_LOCAL, "kgdb"); +out1: + unregister_die_notifier(&kgdb_notifier); +out: + return retval; } static void kgdb_hw_overflow_handler(struct perf_event *event, @@ -673,6 +701,8 @@ void kgdb_arch_exit(void) breakinfo[i].pev = NULL; } } + unregister_nmi_handler(NMI_UNKNOWN, "kgdb"); + unregister_nmi_handler(NMI_LOCAL, "kgdb"); unregister_die_notifier(&kgdb_notifier); } diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index f1a6244d7d93..7da647d8b64c 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -75,8 +75,11 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); /* * Undefined/reserved opcodes, conditional jump, Opcode Extension * Groups, and some special opcodes can not boost. + * This is non-const and volatile to keep gcc from statically + * optimizing it out, as variable_test_bit makes gcc think only + * *(unsigned long*) is used. */ -static const u32 twobyte_is_boostable[256 / 32] = { +static volatile u32 twobyte_is_boostable[256 / 32] = { /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ /* ---------------------------------------------- */ W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */ diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 591be0ee1934..d494799aafcd 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -74,14 +74,13 @@ static struct equiv_cpu_entry *equiv_cpu_table; static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) { struct cpuinfo_x86 *c = &cpu_data(cpu); - u32 dummy; if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) { pr_warning("CPU%d: family %d not supported\n", cpu, c->x86); return -1; } - rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy); + csig->rev = c->microcode; pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev); return 0; @@ -130,6 +129,7 @@ static int apply_microcode_amd(int cpu) int cpu_num = raw_smp_processor_id(); struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; struct microcode_amd *mc_amd = uci->mc; + struct cpuinfo_x86 *c = &cpu_data(cpu); /* We should bind the task to the CPU */ BUG_ON(cpu_num != cpu); @@ -150,6 +150,7 @@ static int apply_microcode_amd(int cpu) pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev); uci->cpu_sig.rev = rev; + c->microcode = rev; return 0; } diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index f9242800bc84..f2d2a664e797 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -483,7 +483,13 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) sysfs_remove_group(&sys_dev->kobj, &mc_attr_group); pr_debug("CPU%d removed\n", cpu); break; - case CPU_DEAD: + + /* + * When a CPU goes offline, don't free up or invalidate the copy of + * the microcode in kernel memory, so that we can reuse it when the + * CPU comes back online without unnecessarily requesting the userspace + * for it again. + */ case CPU_UP_CANCELED_FROZEN: /* The CPU refused to come up during a system resume */ microcode_fini_cpu(cpu); diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 1a1b606d3e92..3ca42d0e43a2 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -161,12 +161,7 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) csig->pf = 1 << ((val[1] >> 18) & 7); } - wrmsr(MSR_IA32_UCODE_REV, 0, 0); - /* see notes above for revision 1.07. Apparent chip bug */ - sync_core(); - /* get the current revision from MSR 0x8B */ - rdmsr(MSR_IA32_UCODE_REV, val[0], csig->rev); - + csig->rev = c->microcode; pr_info("CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n", cpu_num, csig->sig, csig->pf, csig->rev); @@ -299,9 +294,9 @@ static int apply_microcode(int cpu) struct microcode_intel *mc_intel; struct ucode_cpu_info *uci; unsigned int val[2]; - int cpu_num; + int cpu_num = raw_smp_processor_id(); + struct cpuinfo_x86 *c = &cpu_data(cpu_num); - cpu_num = raw_smp_processor_id(); uci = ucode_cpu_info + cpu; mc_intel = uci->mc; @@ -317,7 +312,7 @@ static int apply_microcode(int cpu) (unsigned long) mc_intel->bits >> 16 >> 16); wrmsr(MSR_IA32_UCODE_REV, 0, 0); - /* see notes above for revision 1.07. Apparent chip bug */ + /* As documented in the SDM: Do a CPUID 1 here */ sync_core(); /* get the current revision from MSR 0x8B */ @@ -335,6 +330,7 @@ static int apply_microcode(int cpu) (mc_intel->hdr.date >> 16) & 0xff); uci->cpu_sig.rev = val[1]; + c->microcode = val[1]; return 0; } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c new file mode 100644 index 000000000000..7ec5bd140b87 --- /dev/null +++ b/arch/x86/kernel/nmi.c @@ -0,0 +1,433 @@ +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + * Copyright (C) 2011 Don Zickus Red Hat, Inc. + * + * Pentium III FXSR, SSE support + * Gareth Hughes <gareth@valinux.com>, May 2000 + */ + +/* + * Handle hardware traps and faults. + */ +#include <linux/spinlock.h> +#include <linux/kprobes.h> +#include <linux/kdebug.h> +#include <linux/nmi.h> +#include <linux/delay.h> +#include <linux/hardirq.h> +#include <linux/slab.h> + +#include <linux/mca.h> + +#if defined(CONFIG_EDAC) +#include <linux/edac.h> +#endif + +#include <linux/atomic.h> +#include <asm/traps.h> +#include <asm/mach_traps.h> +#include <asm/nmi.h> + +#define NMI_MAX_NAMELEN 16 +struct nmiaction { + struct list_head list; + nmi_handler_t handler; + unsigned int flags; + char *name; +}; + +struct nmi_desc { + spinlock_t lock; + struct list_head head; +}; + +static struct nmi_desc nmi_desc[NMI_MAX] = +{ + { + .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock), + .head = LIST_HEAD_INIT(nmi_desc[0].head), + }, + { + .lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock), + .head = LIST_HEAD_INIT(nmi_desc[1].head), + }, + +}; + +struct nmi_stats { + unsigned int normal; + unsigned int unknown; + unsigned int external; + unsigned int swallow; +}; + +static DEFINE_PER_CPU(struct nmi_stats, nmi_stats); + +static int ignore_nmis; + +int unknown_nmi_panic; +/* + * Prevent NMI reason port (0x61) being accessed simultaneously, can + * only be used in NMI handler. + */ +static DEFINE_RAW_SPINLOCK(nmi_reason_lock); + +static int __init setup_unknown_nmi_panic(char *str) +{ + unknown_nmi_panic = 1; + return 1; +} +__setup("unknown_nmi_panic", setup_unknown_nmi_panic); + +#define nmi_to_desc(type) (&nmi_desc[type]) + +static int notrace __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) +{ + struct nmi_desc *desc = nmi_to_desc(type); + struct nmiaction *a; + int handled=0; + + rcu_read_lock(); + + /* + * NMIs are edge-triggered, which means if you have enough + * of them concurrently, you can lose some because only one + * can be latched at any given time. Walk the whole list + * to handle those situations. + */ + list_for_each_entry_rcu(a, &desc->head, list) + handled += a->handler(type, regs); + + rcu_read_unlock(); + + /* return total number of NMI events handled */ + return handled; +} + +static int __setup_nmi(unsigned int type, struct nmiaction *action) +{ + struct nmi_desc *desc = nmi_to_desc(type); + unsigned long flags; + + spin_lock_irqsave(&desc->lock, flags); + + /* + * most handlers of type NMI_UNKNOWN never return because + * they just assume the NMI is theirs. Just a sanity check + * to manage expectations + */ + WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head)); + + /* + * some handlers need to be executed first otherwise a fake + * event confuses some handlers (kdump uses this flag) + */ + if (action->flags & NMI_FLAG_FIRST) + list_add_rcu(&action->list, &desc->head); + else + list_add_tail_rcu(&action->list, &desc->head); + + spin_unlock_irqrestore(&desc->lock, flags); + return 0; +} + +static struct nmiaction *__free_nmi(unsigned int type, const char *name) +{ + struct nmi_desc *desc = nmi_to_desc(type); + struct nmiaction *n; + unsigned long flags; + + spin_lock_irqsave(&desc->lock, flags); + + list_for_each_entry_rcu(n, &desc->head, list) { + /* + * the name passed in to describe the nmi handler + * is used as the lookup key + */ + if (!strcmp(n->name, name)) { + WARN(in_nmi(), + "Trying to free NMI (%s) from NMI context!\n", n->name); + list_del_rcu(&n->list); + break; + } + } + + spin_unlock_irqrestore(&desc->lock, flags); + synchronize_rcu(); + return (n); +} + +int register_nmi_handler(unsigned int type, nmi_handler_t handler, + unsigned long nmiflags, const char *devname) +{ + struct nmiaction *action; + int retval = -ENOMEM; + + if (!handler) + return -EINVAL; + + action = kzalloc(sizeof(struct nmiaction), GFP_KERNEL); + if (!action) + goto fail_action; + + action->handler = handler; + action->flags = nmiflags; + action->name = kstrndup(devname, NMI_MAX_NAMELEN, GFP_KERNEL); + if (!action->name) + goto fail_action_name; + + retval = __setup_nmi(type, action); + + if (retval) + goto fail_setup_nmi; + + return retval; + +fail_setup_nmi: + kfree(action->name); +fail_action_name: + kfree(action); +fail_action: + + return retval; +} +EXPORT_SYMBOL_GPL(register_nmi_handler); + +void unregister_nmi_handler(unsigned int type, const char *name) +{ + struct nmiaction *a; + + a = __free_nmi(type, name); + if (a) { + kfree(a->name); + kfree(a); + } +} + +EXPORT_SYMBOL_GPL(unregister_nmi_handler); + +static notrace __kprobes void +pci_serr_error(unsigned char reason, struct pt_regs *regs) +{ + pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n", + reason, smp_processor_id()); + + /* + * On some machines, PCI SERR line is used to report memory + * errors. EDAC makes use of it. + */ +#if defined(CONFIG_EDAC) + if (edac_handler_set()) { + edac_atomic_assert_error(); + return; + } +#endif + + if (panic_on_unrecovered_nmi) + panic("NMI: Not continuing"); + + pr_emerg("Dazed and confused, but trying to continue\n"); + + /* Clear and disable the PCI SERR error line. */ + reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR; + outb(reason, NMI_REASON_PORT); +} + +static notrace __kprobes void +io_check_error(unsigned char reason, struct pt_regs *regs) +{ + unsigned long i; + + pr_emerg( + "NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n", + reason, smp_processor_id()); + show_registers(regs); + + if (panic_on_io_nmi) + panic("NMI IOCK error: Not continuing"); + + /* Re-enable the IOCK line, wait for a few seconds */ + reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK; + outb(reason, NMI_REASON_PORT); + + i = 20000; + while (--i) { + touch_nmi_watchdog(); + udelay(100); + } + + reason &= ~NMI_REASON_CLEAR_IOCHK; + outb(reason, NMI_REASON_PORT); +} + +static notrace __kprobes void +unknown_nmi_error(unsigned char reason, struct pt_regs *regs) +{ + int handled; + + /* + * Use 'false' as back-to-back NMIs are dealt with one level up. + * Of course this makes having multiple 'unknown' handlers useless + * as only the first one is ever run (unless it can actually determine + * if it caused the NMI) + */ + handled = nmi_handle(NMI_UNKNOWN, regs, false); + if (handled) { + __this_cpu_add(nmi_stats.unknown, handled); + return; + } + + __this_cpu_add(nmi_stats.unknown, 1); + +#ifdef CONFIG_MCA + /* + * Might actually be able to figure out what the guilty party + * is: + */ + if (MCA_bus) { + mca_handle_nmi(); + return; + } +#endif + pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", + reason, smp_processor_id()); + + pr_emerg("Do you have a strange power saving mode enabled?\n"); + if (unknown_nmi_panic || panic_on_unrecovered_nmi) + panic("NMI: Not continuing"); + + pr_emerg("Dazed and confused, but trying to continue\n"); +} + +static DEFINE_PER_CPU(bool, swallow_nmi); +static DEFINE_PER_CPU(unsigned long, last_nmi_rip); + +static notrace __kprobes void default_do_nmi(struct pt_regs *regs) +{ + unsigned char reason = 0; + int handled; + bool b2b = false; + + /* + * CPU-specific NMI must be processed before non-CPU-specific + * NMI, otherwise we may lose it, because the CPU-specific + * NMI can not be detected/processed on other CPUs. + */ + + /* + * Back-to-back NMIs are interesting because they can either + * be two NMI or more than two NMIs (any thing over two is dropped + * due to NMI being edge-triggered). If this is the second half + * of the back-to-back NMI, assume we dropped things and process + * more handlers. Otherwise reset the 'swallow' NMI behaviour + */ + if (regs->ip == __this_cpu_read(last_nmi_rip)) + b2b = true; + else + __this_cpu_write(swallow_nmi, false); + + __this_cpu_write(last_nmi_rip, regs->ip); + + handled = nmi_handle(NMI_LOCAL, regs, b2b); + __this_cpu_add(nmi_stats.normal, handled); + if (handled) { + /* + * There are cases when a NMI handler handles multiple + * events in the current NMI. One of these events may + * be queued for in the next NMI. Because the event is + * already handled, the next NMI will result in an unknown + * NMI. Instead lets flag this for a potential NMI to + * swallow. + */ + if (handled > 1) + __this_cpu_write(swallow_nmi, true); + return; + } + + /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */ + raw_spin_lock(&nmi_reason_lock); + reason = get_nmi_reason(); + + if (reason & NMI_REASON_MASK) { + if (reason & NMI_REASON_SERR) + pci_serr_error(reason, regs); + else if (reason & NMI_REASON_IOCHK) + io_check_error(reason, regs); +#ifdef CONFIG_X86_32 + /* + * Reassert NMI in case it became active + * meanwhile as it's edge-triggered: + */ + reassert_nmi(); +#endif + __this_cpu_add(nmi_stats.external, 1); + raw_spin_unlock(&nmi_reason_lock); + return; + } + raw_spin_unlock(&nmi_reason_lock); + + /* + * Only one NMI can be latched at a time. To handle + * this we may process multiple nmi handlers at once to + * cover the case where an NMI is dropped. The downside + * to this approach is we may process an NMI prematurely, + * while its real NMI is sitting latched. This will cause + * an unknown NMI on the next run of the NMI processing. + * + * We tried to flag that condition above, by setting the + * swallow_nmi flag when we process more than one event. + * This condition is also only present on the second half + * of a back-to-back NMI, so we flag that condition too. + * + * If both are true, we assume we already processed this + * NMI previously and we swallow it. Otherwise we reset + * the logic. + * + * There are scenarios where we may accidentally swallow + * a 'real' unknown NMI. For example, while processing + * a perf NMI another perf NMI comes in along with a + * 'real' unknown NMI. These two NMIs get combined into + * one (as descibed above). When the next NMI gets + * processed, it will be flagged by perf as handled, but + * noone will know that there was a 'real' unknown NMI sent + * also. As a result it gets swallowed. Or if the first + * perf NMI returns two events handled then the second + * NMI will get eaten by the logic below, again losing a + * 'real' unknown NMI. But this is the best we can do + * for now. + */ + if (b2b && __this_cpu_read(swallow_nmi)) + __this_cpu_add(nmi_stats.swallow, 1); + else + unknown_nmi_error(reason, regs); +} + +dotraplinkage notrace __kprobes void +do_nmi(struct pt_regs *regs, long error_code) +{ + nmi_enter(); + + inc_irq_stat(__nmi_count); + + if (!ignore_nmis) + default_do_nmi(regs); + + nmi_exit(); +} + +void stop_nmi(void) +{ + ignore_nmis++; +} + +void restart_nmi(void) +{ + ignore_nmis--; +} + +/* reset the back-to-back NMI logic */ +void local_touch_nmi(void) +{ + __this_cpu_write(last_nmi_rip, 0); +} diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index b49d00da2aed..622872054fbe 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -117,8 +117,8 @@ again: } /* - * See <Documentation/x86_64/boot-options.txt> for the iommu kernel parameter - * documentation. + * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel + * parameter documentation. */ static __init int iommu_setup(char *p) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e7e3b019c439..b9b3b1a51643 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -49,7 +49,7 @@ void free_thread_xstate(struct task_struct *tsk) void free_thread_info(struct thread_info *ti) { free_thread_xstate(ti->task); - free_pages((unsigned long)ti, get_order(THREAD_SIZE)); + free_pages((unsigned long)ti, THREAD_ORDER); } void arch_task_cache_init(void) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 7a3b65107a27..795b79f984c2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -57,6 +57,7 @@ #include <asm/idle.h> #include <asm/syscalls.h> #include <asm/debugreg.h> +#include <asm/nmi.h> asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); @@ -107,6 +108,7 @@ void cpu_idle(void) if (cpu_is_offline(cpu)) play_dead(); + local_touch_nmi(); local_irq_disable(); /* Don't trace irqs off for idle */ stop_critical_timings(); @@ -262,7 +264,7 @@ EXPORT_SYMBOL_GPL(start_thread); /* - * switch_to(x,yn) should switch tasks from x to y. + * switch_to(x,y) should switch tasks from x to y. * * We fsave/fwait so that an exception goes off at the right time * (as a call from the fsave or fwait in effect) rather than to diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index f693e44e1bf6..3bd7e6eebf31 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -51,6 +51,7 @@ #include <asm/idle.h> #include <asm/syscalls.h> #include <asm/debugreg.h> +#include <asm/nmi.h> asmlinkage extern void ret_from_fork(void); @@ -133,6 +134,7 @@ void cpu_idle(void) * from here on, until they go to idle. * Otherwise, idle callbacks can misfire. */ + local_touch_nmi(); local_irq_disable(); enter_idle(); /* Don't trace irqs off for idle */ diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 9242436e9937..e334be1182b9 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -464,7 +464,7 @@ static inline void kb_wait(void) } } -static void vmxoff_nmi(int cpu, struct die_args *args) +static void vmxoff_nmi(int cpu, struct pt_regs *regs) { cpu_emergency_vmxoff(); } @@ -736,14 +736,10 @@ static nmi_shootdown_cb shootdown_callback; static atomic_t waiting_for_crash_ipi; -static int crash_nmi_callback(struct notifier_block *self, - unsigned long val, void *data) +static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) { int cpu; - if (val != DIE_NMI) - return NOTIFY_OK; - cpu = raw_smp_processor_id(); /* Don't do anything if this handler is invoked on crashing cpu. @@ -751,10 +747,10 @@ static int crash_nmi_callback(struct notifier_block *self, * an NMI if system was initially booted with nmi_watchdog parameter. */ if (cpu == crashing_cpu) - return NOTIFY_STOP; + return NMI_HANDLED; local_irq_disable(); - shootdown_callback(cpu, (struct die_args *)data); + shootdown_callback(cpu, regs); atomic_dec(&waiting_for_crash_ipi); /* Assume hlt works */ @@ -762,7 +758,7 @@ static int crash_nmi_callback(struct notifier_block *self, for (;;) cpu_relax(); - return 1; + return NMI_HANDLED; } static void smp_send_nmi_allbutself(void) @@ -770,12 +766,6 @@ static void smp_send_nmi_allbutself(void) apic->send_IPI_allbutself(NMI_VECTOR); } -static struct notifier_block crash_nmi_nb = { - .notifier_call = crash_nmi_callback, - /* we want to be the first one called */ - .priority = NMI_LOCAL_HIGH_PRIOR+1, -}; - /* Halt all other CPUs, calling the specified function on each of them * * This function can be used to halt all other CPUs on crash @@ -794,7 +784,8 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); /* Would it be better to replace the trap vector here? */ - if (register_die_notifier(&crash_nmi_nb)) + if (register_nmi_handler(NMI_LOCAL, crash_nmi_callback, + NMI_FLAG_FIRST, "crash")) return; /* return what? */ /* Ensure the new callback function is set before sending * out the NMI diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index ff14a5044ce6..051489082d59 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -14,10 +14,73 @@ #include <linux/personality.h> #include <linux/random.h> #include <linux/uaccess.h> +#include <linux/elf.h> #include <asm/ia32.h> #include <asm/syscalls.h> +/* + * Align a virtual address to avoid aliasing in the I$ on AMD F15h. + * + * @flags denotes the allocation direction - bottomup or topdown - + * or vDSO; see call sites below. + */ +unsigned long align_addr(unsigned long addr, struct file *filp, + enum align_flags flags) +{ + unsigned long tmp_addr; + + /* handle 32- and 64-bit case with a single conditional */ + if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32()))) + return addr; + + if (!(current->flags & PF_RANDOMIZE)) + return addr; + + if (!((flags & ALIGN_VDSO) || filp)) + return addr; + + tmp_addr = addr; + + /* + * We need an address which is <= than the original + * one only when in topdown direction. + */ + if (!(flags & ALIGN_TOPDOWN)) + tmp_addr += va_align.mask; + + tmp_addr &= ~va_align.mask; + + return tmp_addr; +} + +static int __init control_va_addr_alignment(char *str) +{ + /* guard against enabling this on other CPU families */ + if (va_align.flags < 0) + return 1; + + if (*str == 0) + return 1; + + if (*str == '=') + str++; + + if (!strcmp(str, "32")) + va_align.flags = ALIGN_VA_32; + else if (!strcmp(str, "64")) + va_align.flags = ALIGN_VA_64; + else if (!strcmp(str, "off")) + va_align.flags = 0; + else if (!strcmp(str, "on")) + va_align.flags = ALIGN_VA_32 | ALIGN_VA_64; + else + return 0; + + return 1; +} +__setup("align_va_addr", control_va_addr_alignment); + SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, off) @@ -92,6 +155,9 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, start_addr = addr; full_search: + + addr = align_addr(addr, filp, 0); + for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { /* At this point: (!vma || addr < vma->vm_end). */ if (end - len < addr) { @@ -117,6 +183,7 @@ full_search: mm->cached_hole_size = vma->vm_start - addr; addr = vma->vm_end; + addr = align_addr(addr, filp, 0); } } @@ -161,10 +228,13 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, /* make sure it can fit in the remaining address space */ if (addr > len) { - vma = find_vma(mm, addr-len); - if (!vma || addr <= vma->vm_start) + unsigned long tmp_addr = align_addr(addr - len, filp, + ALIGN_TOPDOWN); + + vma = find_vma(mm, tmp_addr); + if (!vma || tmp_addr + len <= vma->vm_start) /* remember the address as a hint for next time */ - return mm->free_area_cache = addr-len; + return mm->free_area_cache = tmp_addr; } if (mm->mmap_base < len) @@ -173,6 +243,8 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = mm->mmap_base-len; do { + addr = align_addr(addr, filp, ALIGN_TOPDOWN); + /* * Lookup failure means no vma is above this address, * else if new region fits below vma->vm_start, diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index bc19be332bc9..9a0e31293920 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -346,3 +346,5 @@ ENTRY(sys_call_table) .long sys_syncfs .long sys_sendmmsg /* 345 */ .long sys_setns + .long sys_process_vm_readv + .long sys_process_vm_writev diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 6913369c234c..a8e3eb83466c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -81,15 +81,6 @@ gate_desc idt_table[NR_VECTORS] __page_aligned_data = { { { { 0, 0 } } }, }; DECLARE_BITMAP(used_vectors, NR_VECTORS); EXPORT_SYMBOL_GPL(used_vectors); -static int ignore_nmis; - -int unknown_nmi_panic; -/* - * Prevent NMI reason port (0x61) being accessed simultaneously, can - * only be used in NMI handler. - */ -static DEFINE_RAW_SPINLOCK(nmi_reason_lock); - static inline void conditional_sti(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) @@ -307,152 +298,6 @@ gp_in_kernel: die("general protection fault", regs, error_code); } -static int __init setup_unknown_nmi_panic(char *str) -{ - unknown_nmi_panic = 1; - return 1; -} -__setup("unknown_nmi_panic", setup_unknown_nmi_panic); - -static notrace __kprobes void -pci_serr_error(unsigned char reason, struct pt_regs *regs) -{ - pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n", - reason, smp_processor_id()); - - /* - * On some machines, PCI SERR line is used to report memory - * errors. EDAC makes use of it. - */ -#if defined(CONFIG_EDAC) - if (edac_handler_set()) { - edac_atomic_assert_error(); - return; - } -#endif - - if (panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); - - pr_emerg("Dazed and confused, but trying to continue\n"); - - /* Clear and disable the PCI SERR error line. */ - reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR; - outb(reason, NMI_REASON_PORT); -} - -static notrace __kprobes void -io_check_error(unsigned char reason, struct pt_regs *regs) -{ - unsigned long i; - - pr_emerg( - "NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n", - reason, smp_processor_id()); - show_registers(regs); - - if (panic_on_io_nmi) - panic("NMI IOCK error: Not continuing"); - - /* Re-enable the IOCK line, wait for a few seconds */ - reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK; - outb(reason, NMI_REASON_PORT); - - i = 20000; - while (--i) { - touch_nmi_watchdog(); - udelay(100); - } - - reason &= ~NMI_REASON_CLEAR_IOCHK; - outb(reason, NMI_REASON_PORT); -} - -static notrace __kprobes void -unknown_nmi_error(unsigned char reason, struct pt_regs *regs) -{ - if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) == - NOTIFY_STOP) - return; -#ifdef CONFIG_MCA - /* - * Might actually be able to figure out what the guilty party - * is: - */ - if (MCA_bus) { - mca_handle_nmi(); - return; - } -#endif - pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", - reason, smp_processor_id()); - - pr_emerg("Do you have a strange power saving mode enabled?\n"); - if (unknown_nmi_panic || panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); - - pr_emerg("Dazed and confused, but trying to continue\n"); -} - -static notrace __kprobes void default_do_nmi(struct pt_regs *regs) -{ - unsigned char reason = 0; - - /* - * CPU-specific NMI must be processed before non-CPU-specific - * NMI, otherwise we may lose it, because the CPU-specific - * NMI can not be detected/processed on other CPUs. - */ - if (notify_die(DIE_NMI, "nmi", regs, 0, 2, SIGINT) == NOTIFY_STOP) - return; - - /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */ - raw_spin_lock(&nmi_reason_lock); - reason = get_nmi_reason(); - - if (reason & NMI_REASON_MASK) { - if (reason & NMI_REASON_SERR) - pci_serr_error(reason, regs); - else if (reason & NMI_REASON_IOCHK) - io_check_error(reason, regs); -#ifdef CONFIG_X86_32 - /* - * Reassert NMI in case it became active - * meanwhile as it's edge-triggered: - */ - reassert_nmi(); -#endif - raw_spin_unlock(&nmi_reason_lock); - return; - } - raw_spin_unlock(&nmi_reason_lock); - - unknown_nmi_error(reason, regs); -} - -dotraplinkage notrace __kprobes void -do_nmi(struct pt_regs *regs, long error_code) -{ - nmi_enter(); - - inc_irq_stat(__nmi_count); - - if (!ignore_nmis) - default_do_nmi(regs); - - nmi_exit(); -} - -void stop_nmi(void) -{ - ignore_nmis++; -} - -void restart_nmi(void) -{ - ignore_nmis--; -} - /* May run on IST stack. */ dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) { diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 18ae83dd1cd7..b56c65de384d 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -56,7 +56,7 @@ DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) = .lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock), }; -static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; +static enum { EMULATE, NATIVE, NONE } vsyscall_mode = NATIVE; static int __init vsyscall_setup(char *str) { diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 8b4cc5f067de..f1e3be18a08f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -29,6 +29,39 @@ #include "tss.h" /* + * Operand types + */ +#define OpNone 0ull +#define OpImplicit 1ull /* No generic decode */ +#define OpReg 2ull /* Register */ +#define OpMem 3ull /* Memory */ +#define OpAcc 4ull /* Accumulator: AL/AX/EAX/RAX */ +#define OpDI 5ull /* ES:DI/EDI/RDI */ +#define OpMem64 6ull /* Memory, 64-bit */ +#define OpImmUByte 7ull /* Zero-extended 8-bit immediate */ +#define OpDX 8ull /* DX register */ +#define OpCL 9ull /* CL register (for shifts) */ +#define OpImmByte 10ull /* 8-bit sign extended immediate */ +#define OpOne 11ull /* Implied 1 */ +#define OpImm 12ull /* Sign extended immediate */ +#define OpMem16 13ull /* Memory operand (16-bit). */ +#define OpMem32 14ull /* Memory operand (32-bit). */ +#define OpImmU 15ull /* Immediate operand, zero extended */ +#define OpSI 16ull /* SI/ESI/RSI */ +#define OpImmFAddr 17ull /* Immediate far address */ +#define OpMemFAddr 18ull /* Far address in memory */ +#define OpImmU16 19ull /* Immediate operand, 16 bits, zero extended */ +#define OpES 20ull /* ES */ +#define OpCS 21ull /* CS */ +#define OpSS 22ull /* SS */ +#define OpDS 23ull /* DS */ +#define OpFS 24ull /* FS */ +#define OpGS 25ull /* GS */ + +#define OpBits 5 /* Width of operand field */ +#define OpMask ((1ull << OpBits) - 1) + +/* * Opcode effective-address decode tables. * Note that we only emulate instructions that have at least one memory * operand (excluding implicit stack references). We assume that stack @@ -40,37 +73,35 @@ /* Operand sizes: 8-bit operands or specified/overridden size. */ #define ByteOp (1<<0) /* 8-bit operands. */ /* Destination operand type. */ -#define ImplicitOps (1<<1) /* Implicit in opcode. No generic decode. */ -#define DstReg (2<<1) /* Register operand. */ -#define DstMem (3<<1) /* Memory operand. */ -#define DstAcc (4<<1) /* Destination Accumulator */ -#define DstDI (5<<1) /* Destination is in ES:(E)DI */ -#define DstMem64 (6<<1) /* 64bit memory operand */ -#define DstImmUByte (7<<1) /* 8-bit unsigned immediate operand */ -#define DstDX (8<<1) /* Destination is in DX register */ -#define DstMask (0xf<<1) +#define DstShift 1 +#define ImplicitOps (OpImplicit << DstShift) +#define DstReg (OpReg << DstShift) +#define DstMem (OpMem << DstShift) +#define DstAcc (OpAcc << DstShift) +#define DstDI (OpDI << DstShift) +#define DstMem64 (OpMem64 << DstShift) +#define DstImmUByte (OpImmUByte << DstShift) +#define DstDX (OpDX << DstShift) +#define DstMask (OpMask << DstShift) /* Source operand type. */ -#define SrcNone (0<<5) /* No source operand. */ -#define SrcReg (1<<5) /* Register operand. */ -#define SrcMem (2<<5) /* Memory operand. */ -#define SrcMem16 (3<<5) /* Memory operand (16-bit). */ -#define SrcMem32 (4<<5) /* Memory operand (32-bit). */ -#define SrcImm (5<<5) /* Immediate operand. */ -#define SrcImmByte (6<<5) /* 8-bit sign-extended immediate operand. */ -#define SrcOne (7<<5) /* Implied '1' */ -#define SrcImmUByte (8<<5) /* 8-bit unsigned immediate operand. */ -#define SrcImmU (9<<5) /* Immediate operand, unsigned */ -#define SrcSI (0xa<<5) /* Source is in the DS:RSI */ -#define SrcImmFAddr (0xb<<5) /* Source is immediate far address */ -#define SrcMemFAddr (0xc<<5) /* Source is far address in memory */ -#define SrcAcc (0xd<<5) /* Source Accumulator */ -#define SrcImmU16 (0xe<<5) /* Immediate operand, unsigned, 16 bits */ -#define SrcDX (0xf<<5) /* Source is in DX register */ -#define SrcMask (0xf<<5) -/* Generic ModRM decode. */ -#define ModRM (1<<9) -/* Destination is only written; never read. */ -#define Mov (1<<10) +#define SrcShift 6 +#define SrcNone (OpNone << SrcShift) +#define SrcReg (OpReg << SrcShift) +#define SrcMem (OpMem << SrcShift) +#define SrcMem16 (OpMem16 << SrcShift) +#define SrcMem32 (OpMem32 << SrcShift) +#define SrcImm (OpImm << SrcShift) +#define SrcImmByte (OpImmByte << SrcShift) +#define SrcOne (OpOne << SrcShift) +#define SrcImmUByte (OpImmUByte << SrcShift) +#define SrcImmU (OpImmU << SrcShift) +#define SrcSI (OpSI << SrcShift) +#define SrcImmFAddr (OpImmFAddr << SrcShift) +#define SrcMemFAddr (OpMemFAddr << SrcShift) +#define SrcAcc (OpAcc << SrcShift) +#define SrcImmU16 (OpImmU16 << SrcShift) +#define SrcDX (OpDX << SrcShift) +#define SrcMask (OpMask << SrcShift) #define BitOp (1<<11) #define MemAbs (1<<12) /* Memory operand is absolute displacement */ #define String (1<<13) /* String instruction (rep capable) */ @@ -81,6 +112,10 @@ #define Prefix (3<<15) /* Instruction varies with 66/f2/f3 prefix */ #define RMExt (4<<15) /* Opcode extension in ModRM r/m if mod == 3 */ #define Sse (1<<18) /* SSE Vector instruction */ +/* Generic ModRM decode. */ +#define ModRM (1<<19) +/* Destination is only written; never read. */ +#define Mov (1<<20) /* Misc flags */ #define Prot (1<<21) /* instruction generates #UD if not in prot-mode */ #define VendorSpecific (1<<22) /* Vendor specific instruction */ @@ -91,12 +126,19 @@ #define Priv (1<<27) /* instruction generates #GP if current CPL != 0 */ #define No64 (1<<28) /* Source 2 operand type */ -#define Src2None (0<<29) -#define Src2CL (1<<29) -#define Src2ImmByte (2<<29) -#define Src2One (3<<29) -#define Src2Imm (4<<29) -#define Src2Mask (7<<29) +#define Src2Shift (29) +#define Src2None (OpNone << Src2Shift) +#define Src2CL (OpCL << Src2Shift) +#define Src2ImmByte (OpImmByte << Src2Shift) +#define Src2One (OpOne << Src2Shift) +#define Src2Imm (OpImm << Src2Shift) +#define Src2ES (OpES << Src2Shift) +#define Src2CS (OpCS << Src2Shift) +#define Src2SS (OpSS << Src2Shift) +#define Src2DS (OpDS << Src2Shift) +#define Src2FS (OpFS << Src2Shift) +#define Src2GS (OpGS << Src2Shift) +#define Src2Mask (OpMask << Src2Shift) #define X2(x...) x, x #define X3(x...) X2(x), x @@ -108,8 +150,8 @@ #define X16(x...) X8(x), X8(x) struct opcode { - u32 flags; - u8 intercept; + u64 flags : 56; + u64 intercept : 8; union { int (*execute)(struct x86_emulate_ctxt *ctxt); struct opcode *group; @@ -205,105 +247,100 @@ struct gprefix { #define ON64(x) #endif -#define ____emulate_2op(_op, _src, _dst, _eflags, _x, _y, _suffix, _dsttype) \ +#define ____emulate_2op(ctxt, _op, _x, _y, _suffix, _dsttype) \ do { \ __asm__ __volatile__ ( \ _PRE_EFLAGS("0", "4", "2") \ _op _suffix " %"_x"3,%1; " \ _POST_EFLAGS("0", "4", "2") \ - : "=m" (_eflags), "+q" (*(_dsttype*)&(_dst).val),\ + : "=m" ((ctxt)->eflags), \ + "+q" (*(_dsttype*)&(ctxt)->dst.val), \ "=&r" (_tmp) \ - : _y ((_src).val), "i" (EFLAGS_MASK)); \ + : _y ((ctxt)->src.val), "i" (EFLAGS_MASK)); \ } while (0) /* Raw emulation: instruction has two explicit operands. */ -#define __emulate_2op_nobyte(_op,_src,_dst,_eflags,_wx,_wy,_lx,_ly,_qx,_qy) \ +#define __emulate_2op_nobyte(ctxt,_op,_wx,_wy,_lx,_ly,_qx,_qy) \ do { \ unsigned long _tmp; \ \ - switch ((_dst).bytes) { \ + switch ((ctxt)->dst.bytes) { \ case 2: \ - ____emulate_2op(_op,_src,_dst,_eflags,_wx,_wy,"w",u16);\ + ____emulate_2op(ctxt,_op,_wx,_wy,"w",u16); \ break; \ case 4: \ - ____emulate_2op(_op,_src,_dst,_eflags,_lx,_ly,"l",u32);\ + ____emulate_2op(ctxt,_op,_lx,_ly,"l",u32); \ break; \ case 8: \ - ON64(____emulate_2op(_op,_src,_dst,_eflags,_qx,_qy,"q",u64)); \ + ON64(____emulate_2op(ctxt,_op,_qx,_qy,"q",u64)); \ break; \ } \ } while (0) -#define __emulate_2op(_op,_src,_dst,_eflags,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \ +#define __emulate_2op(ctxt,_op,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \ do { \ unsigned long _tmp; \ - switch ((_dst).bytes) { \ + switch ((ctxt)->dst.bytes) { \ case 1: \ - ____emulate_2op(_op,_src,_dst,_eflags,_bx,_by,"b",u8); \ + ____emulate_2op(ctxt,_op,_bx,_by,"b",u8); \ break; \ default: \ - __emulate_2op_nobyte(_op, _src, _dst, _eflags, \ + __emulate_2op_nobyte(ctxt, _op, \ _wx, _wy, _lx, _ly, _qx, _qy); \ break; \ } \ } while (0) /* Source operand is byte-sized and may be restricted to just %cl. */ -#define emulate_2op_SrcB(_op, _src, _dst, _eflags) \ - __emulate_2op(_op, _src, _dst, _eflags, \ - "b", "c", "b", "c", "b", "c", "b", "c") +#define emulate_2op_SrcB(ctxt, _op) \ + __emulate_2op(ctxt, _op, "b", "c", "b", "c", "b", "c", "b", "c") /* Source operand is byte, word, long or quad sized. */ -#define emulate_2op_SrcV(_op, _src, _dst, _eflags) \ - __emulate_2op(_op, _src, _dst, _eflags, \ - "b", "q", "w", "r", _LO32, "r", "", "r") +#define emulate_2op_SrcV(ctxt, _op) \ + __emulate_2op(ctxt, _op, "b", "q", "w", "r", _LO32, "r", "", "r") /* Source operand is word, long or quad sized. */ -#define emulate_2op_SrcV_nobyte(_op, _src, _dst, _eflags) \ - __emulate_2op_nobyte(_op, _src, _dst, _eflags, \ - "w", "r", _LO32, "r", "", "r") +#define emulate_2op_SrcV_nobyte(ctxt, _op) \ + __emulate_2op_nobyte(ctxt, _op, "w", "r", _LO32, "r", "", "r") /* Instruction has three operands and one operand is stored in ECX register */ -#define __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, _suffix, _type) \ +#define __emulate_2op_cl(ctxt, _op, _suffix, _type) \ do { \ unsigned long _tmp; \ - _type _clv = (_cl).val; \ - _type _srcv = (_src).val; \ - _type _dstv = (_dst).val; \ + _type _clv = (ctxt)->src2.val; \ + _type _srcv = (ctxt)->src.val; \ + _type _dstv = (ctxt)->dst.val; \ \ __asm__ __volatile__ ( \ _PRE_EFLAGS("0", "5", "2") \ _op _suffix " %4,%1 \n" \ _POST_EFLAGS("0", "5", "2") \ - : "=m" (_eflags), "+r" (_dstv), "=&r" (_tmp) \ + : "=m" ((ctxt)->eflags), "+r" (_dstv), "=&r" (_tmp) \ : "c" (_clv) , "r" (_srcv), "i" (EFLAGS_MASK) \ ); \ \ - (_cl).val = (unsigned long) _clv; \ - (_src).val = (unsigned long) _srcv; \ - (_dst).val = (unsigned long) _dstv; \ + (ctxt)->src2.val = (unsigned long) _clv; \ + (ctxt)->src2.val = (unsigned long) _srcv; \ + (ctxt)->dst.val = (unsigned long) _dstv; \ } while (0) -#define emulate_2op_cl(_op, _cl, _src, _dst, _eflags) \ +#define emulate_2op_cl(ctxt, _op) \ do { \ - switch ((_dst).bytes) { \ + switch ((ctxt)->dst.bytes) { \ case 2: \ - __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "w", unsigned short); \ + __emulate_2op_cl(ctxt, _op, "w", u16); \ break; \ case 4: \ - __emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "l", unsigned int); \ + __emulate_2op_cl(ctxt, _op, "l", u32); \ break; \ case 8: \ - ON64(__emulate_2op_cl(_op, _cl, _src, _dst, _eflags, \ - "q", unsigned long)); \ + ON64(__emulate_2op_cl(ctxt, _op, "q", ulong)); \ break; \ } \ } while (0) -#define __emulate_1op(_op, _dst, _eflags, _suffix) \ +#define __emulate_1op(ctxt, _op, _suffix) \ do { \ unsigned long _tmp; \ \ @@ -311,39 +348,27 @@ struct gprefix { _PRE_EFLAGS("0", "3", "2") \ _op _suffix " %1; " \ _POST_EFLAGS("0", "3", "2") \ - : "=m" (_eflags), "+m" ((_dst).val), \ + : "=m" ((ctxt)->eflags), "+m" ((ctxt)->dst.val), \ "=&r" (_tmp) \ : "i" (EFLAGS_MASK)); \ } while (0) /* Instruction has only one explicit operand (no source operand). */ -#define emulate_1op(_op, _dst, _eflags) \ +#define emulate_1op(ctxt, _op) \ do { \ - switch ((_dst).bytes) { \ - case 1: __emulate_1op(_op, _dst, _eflags, "b"); break; \ - case 2: __emulate_1op(_op, _dst, _eflags, "w"); break; \ - case 4: __emulate_1op(_op, _dst, _eflags, "l"); break; \ - case 8: ON64(__emulate_1op(_op, _dst, _eflags, "q")); break; \ + switch ((ctxt)->dst.bytes) { \ + case 1: __emulate_1op(ctxt, _op, "b"); break; \ + case 2: __emulate_1op(ctxt, _op, "w"); break; \ + case 4: __emulate_1op(ctxt, _op, "l"); break; \ + case 8: ON64(__emulate_1op(ctxt, _op, "q")); break; \ } \ } while (0) -#define __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags, _suffix) \ - do { \ - unsigned long _tmp; \ - \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0", "4", "1") \ - _op _suffix " %5; " \ - _POST_EFLAGS("0", "4", "1") \ - : "=m" (_eflags), "=&r" (_tmp), \ - "+a" (_rax), "+d" (_rdx) \ - : "i" (EFLAGS_MASK), "m" ((_src).val), \ - "a" (_rax), "d" (_rdx)); \ - } while (0) - -#define __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, _eflags, _suffix, _ex) \ +#define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex) \ do { \ unsigned long _tmp; \ + ulong *rax = &(ctxt)->regs[VCPU_REGS_RAX]; \ + ulong *rdx = &(ctxt)->regs[VCPU_REGS_RDX]; \ \ __asm__ __volatile__ ( \ _PRE_EFLAGS("0", "5", "1") \ @@ -356,53 +381,27 @@ struct gprefix { "jmp 2b \n\t" \ ".popsection \n\t" \ _ASM_EXTABLE(1b, 3b) \ - : "=m" (_eflags), "=&r" (_tmp), \ - "+a" (_rax), "+d" (_rdx), "+qm"(_ex) \ - : "i" (EFLAGS_MASK), "m" ((_src).val), \ - "a" (_rax), "d" (_rdx)); \ + : "=m" ((ctxt)->eflags), "=&r" (_tmp), \ + "+a" (*rax), "+d" (*rdx), "+qm"(_ex) \ + : "i" (EFLAGS_MASK), "m" ((ctxt)->src.val), \ + "a" (*rax), "d" (*rdx)); \ } while (0) /* instruction has only one source operand, destination is implicit (e.g. mul, div, imul, idiv) */ -#define emulate_1op_rax_rdx(_op, _src, _rax, _rdx, _eflags) \ +#define emulate_1op_rax_rdx(ctxt, _op, _ex) \ do { \ - switch((_src).bytes) { \ + switch((ctxt)->src.bytes) { \ case 1: \ - __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "b"); \ + __emulate_1op_rax_rdx(ctxt, _op, "b", _ex); \ break; \ case 2: \ - __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "w"); \ + __emulate_1op_rax_rdx(ctxt, _op, "w", _ex); \ break; \ case 4: \ - __emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "l"); \ - break; \ - case 8: \ - ON64(__emulate_1op_rax_rdx(_op, _src, _rax, _rdx, \ - _eflags, "q")); \ - break; \ - } \ - } while (0) - -#define emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, _eflags, _ex) \ - do { \ - switch((_src).bytes) { \ - case 1: \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "b", _ex); \ - break; \ - case 2: \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "w", _ex); \ - break; \ - case 4: \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "l", _ex); \ + __emulate_1op_rax_rdx(ctxt, _op, "l", _ex); \ break; \ case 8: ON64( \ - __emulate_1op_rax_rdx_ex(_op, _src, _rax, _rdx, \ - _eflags, "q", _ex)); \ + __emulate_1op_rax_rdx(ctxt, _op, "q", _ex)); \ break; \ } \ } while (0) @@ -651,41 +650,50 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt, return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception); } -static int do_insn_fetch_byte(struct x86_emulate_ctxt *ctxt, - unsigned long eip, u8 *dest) +/* + * Fetch the next byte of the instruction being emulated which is pointed to + * by ctxt->_eip, then increment ctxt->_eip. + * + * Also prefetch the remaining bytes of the instruction without crossing page + * boundary if they are not in fetch_cache yet. + */ +static int do_insn_fetch_byte(struct x86_emulate_ctxt *ctxt, u8 *dest) { struct fetch_cache *fc = &ctxt->fetch; int rc; int size, cur_size; - if (eip == fc->end) { + if (ctxt->_eip == fc->end) { unsigned long linear; - struct segmented_address addr = { .seg=VCPU_SREG_CS, .ea=eip}; + struct segmented_address addr = { .seg = VCPU_SREG_CS, + .ea = ctxt->_eip }; cur_size = fc->end - fc->start; - size = min(15UL - cur_size, PAGE_SIZE - offset_in_page(eip)); + size = min(15UL - cur_size, + PAGE_SIZE - offset_in_page(ctxt->_eip)); rc = __linearize(ctxt, addr, size, false, true, &linear); - if (rc != X86EMUL_CONTINUE) + if (unlikely(rc != X86EMUL_CONTINUE)) return rc; rc = ctxt->ops->fetch(ctxt, linear, fc->data + cur_size, size, &ctxt->exception); - if (rc != X86EMUL_CONTINUE) + if (unlikely(rc != X86EMUL_CONTINUE)) return rc; fc->end += size; } - *dest = fc->data[eip - fc->start]; + *dest = fc->data[ctxt->_eip - fc->start]; + ctxt->_eip++; return X86EMUL_CONTINUE; } static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, - unsigned long eip, void *dest, unsigned size) + void *dest, unsigned size) { int rc; /* x86 instructions are limited to 15 bytes. */ - if (eip + size - ctxt->eip > 15) + if (unlikely(ctxt->_eip + size - ctxt->eip > 15)) return X86EMUL_UNHANDLEABLE; while (size--) { - rc = do_insn_fetch_byte(ctxt, eip++, dest++); + rc = do_insn_fetch_byte(ctxt, dest++); if (rc != X86EMUL_CONTINUE) return rc; } @@ -693,20 +701,18 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, } /* Fetch next part of the instruction being emulated. */ -#define insn_fetch(_type, _size, _eip) \ +#define insn_fetch(_type, _ctxt) \ ({ unsigned long _x; \ - rc = do_insn_fetch(ctxt, (_eip), &_x, (_size)); \ + rc = do_insn_fetch(_ctxt, &_x, sizeof(_type)); \ if (rc != X86EMUL_CONTINUE) \ goto done; \ - (_eip) += (_size); \ (_type)_x; \ }) -#define insn_fetch_arr(_arr, _size, _eip) \ -({ rc = do_insn_fetch(ctxt, (_eip), _arr, (_size)); \ +#define insn_fetch_arr(_arr, _size, _ctxt) \ +({ rc = do_insn_fetch(_ctxt, _arr, (_size)); \ if (rc != X86EMUL_CONTINUE) \ goto done; \ - (_eip) += (_size); \ }) /* @@ -894,7 +900,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, ctxt->modrm_rm = base_reg = (ctxt->rex_prefix & 1) << 3; /* REG.B */ } - ctxt->modrm = insn_fetch(u8, 1, ctxt->_eip); + ctxt->modrm = insn_fetch(u8, ctxt); ctxt->modrm_mod |= (ctxt->modrm & 0xc0) >> 6; ctxt->modrm_reg |= (ctxt->modrm & 0x38) >> 3; ctxt->modrm_rm |= (ctxt->modrm & 0x07); @@ -928,13 +934,13 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, switch (ctxt->modrm_mod) { case 0: if (ctxt->modrm_rm == 6) - modrm_ea += insn_fetch(u16, 2, ctxt->_eip); + modrm_ea += insn_fetch(u16, ctxt); break; case 1: - modrm_ea += insn_fetch(s8, 1, ctxt->_eip); + modrm_ea += insn_fetch(s8, ctxt); break; case 2: - modrm_ea += insn_fetch(u16, 2, ctxt->_eip); + modrm_ea += insn_fetch(u16, ctxt); break; } switch (ctxt->modrm_rm) { @@ -971,13 +977,13 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, } else { /* 32/64-bit ModR/M decode. */ if ((ctxt->modrm_rm & 7) == 4) { - sib = insn_fetch(u8, 1, ctxt->_eip); + sib = insn_fetch(u8, ctxt); index_reg |= (sib >> 3) & 7; base_reg |= sib & 7; scale = sib >> 6; if ((base_reg & 7) == 5 && ctxt->modrm_mod == 0) - modrm_ea += insn_fetch(s32, 4, ctxt->_eip); + modrm_ea += insn_fetch(s32, ctxt); else modrm_ea += ctxt->regs[base_reg]; if (index_reg != 4) @@ -990,13 +996,13 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, switch (ctxt->modrm_mod) { case 0: if (ctxt->modrm_rm == 5) - modrm_ea += insn_fetch(s32, 4, ctxt->_eip); + modrm_ea += insn_fetch(s32, ctxt); break; case 1: - modrm_ea += insn_fetch(s8, 1, ctxt->_eip); + modrm_ea += insn_fetch(s8, ctxt); break; case 2: - modrm_ea += insn_fetch(s32, 4, ctxt->_eip); + modrm_ea += insn_fetch(s32, ctxt); break; } } @@ -1013,13 +1019,13 @@ static int decode_abs(struct x86_emulate_ctxt *ctxt, op->type = OP_MEM; switch (ctxt->ad_bytes) { case 2: - op->addr.mem.ea = insn_fetch(u16, 2, ctxt->_eip); + op->addr.mem.ea = insn_fetch(u16, ctxt); break; case 4: - op->addr.mem.ea = insn_fetch(u32, 4, ctxt->_eip); + op->addr.mem.ea = insn_fetch(u32, ctxt); break; case 8: - op->addr.mem.ea = insn_fetch(u64, 8, ctxt->_eip); + op->addr.mem.ea = insn_fetch(u64, ctxt); break; } done: @@ -1452,15 +1458,18 @@ static int em_popf(struct x86_emulate_ctxt *ctxt) return emulate_popf(ctxt, &ctxt->dst.val, ctxt->op_bytes); } -static int emulate_push_sreg(struct x86_emulate_ctxt *ctxt, int seg) +static int em_push_sreg(struct x86_emulate_ctxt *ctxt) { + int seg = ctxt->src2.val; + ctxt->src.val = get_segment_selector(ctxt, seg); return em_push(ctxt); } -static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, int seg) +static int em_pop_sreg(struct x86_emulate_ctxt *ctxt) { + int seg = ctxt->src2.val; unsigned long selector; int rc; @@ -1674,64 +1683,74 @@ static int em_grp2(struct x86_emulate_ctxt *ctxt) { switch (ctxt->modrm_reg) { case 0: /* rol */ - emulate_2op_SrcB("rol", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "rol"); break; case 1: /* ror */ - emulate_2op_SrcB("ror", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "ror"); break; case 2: /* rcl */ - emulate_2op_SrcB("rcl", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "rcl"); break; case 3: /* rcr */ - emulate_2op_SrcB("rcr", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "rcr"); break; case 4: /* sal/shl */ case 6: /* sal/shl */ - emulate_2op_SrcB("sal", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "sal"); break; case 5: /* shr */ - emulate_2op_SrcB("shr", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "shr"); break; case 7: /* sar */ - emulate_2op_SrcB("sar", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcB(ctxt, "sar"); break; } return X86EMUL_CONTINUE; } -static int em_grp3(struct x86_emulate_ctxt *ctxt) +static int em_not(struct x86_emulate_ctxt *ctxt) +{ + ctxt->dst.val = ~ctxt->dst.val; + return X86EMUL_CONTINUE; +} + +static int em_neg(struct x86_emulate_ctxt *ctxt) +{ + emulate_1op(ctxt, "neg"); + return X86EMUL_CONTINUE; +} + +static int em_mul_ex(struct x86_emulate_ctxt *ctxt) +{ + u8 ex = 0; + + emulate_1op_rax_rdx(ctxt, "mul", ex); + return X86EMUL_CONTINUE; +} + +static int em_imul_ex(struct x86_emulate_ctxt *ctxt) +{ + u8 ex = 0; + + emulate_1op_rax_rdx(ctxt, "imul", ex); + return X86EMUL_CONTINUE; +} + +static int em_div_ex(struct x86_emulate_ctxt *ctxt) { - unsigned long *rax = &ctxt->regs[VCPU_REGS_RAX]; - unsigned long *rdx = &ctxt->regs[VCPU_REGS_RDX]; u8 de = 0; - switch (ctxt->modrm_reg) { - case 0 ... 1: /* test */ - emulate_2op_SrcV("test", ctxt->src, ctxt->dst, ctxt->eflags); - break; - case 2: /* not */ - ctxt->dst.val = ~ctxt->dst.val; - break; - case 3: /* neg */ - emulate_1op("neg", ctxt->dst, ctxt->eflags); - break; - case 4: /* mul */ - emulate_1op_rax_rdx("mul", ctxt->src, *rax, *rdx, ctxt->eflags); - break; - case 5: /* imul */ - emulate_1op_rax_rdx("imul", ctxt->src, *rax, *rdx, ctxt->eflags); - break; - case 6: /* div */ - emulate_1op_rax_rdx_ex("div", ctxt->src, *rax, *rdx, - ctxt->eflags, de); - break; - case 7: /* idiv */ - emulate_1op_rax_rdx_ex("idiv", ctxt->src, *rax, *rdx, - ctxt->eflags, de); - break; - default: - return X86EMUL_UNHANDLEABLE; - } + emulate_1op_rax_rdx(ctxt, "div", de); + if (de) + return emulate_de(ctxt); + return X86EMUL_CONTINUE; +} + +static int em_idiv_ex(struct x86_emulate_ctxt *ctxt) +{ + u8 de = 0; + + emulate_1op_rax_rdx(ctxt, "idiv", de); if (de) return emulate_de(ctxt); return X86EMUL_CONTINUE; @@ -1743,10 +1762,10 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt) switch (ctxt->modrm_reg) { case 0: /* inc */ - emulate_1op("inc", ctxt->dst, ctxt->eflags); + emulate_1op(ctxt, "inc"); break; case 1: /* dec */ - emulate_1op("dec", ctxt->dst, ctxt->eflags); + emulate_1op(ctxt, "dec"); break; case 2: /* call near abs */ { long int old_eip; @@ -1812,8 +1831,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) return rc; } -static int emulate_load_segment(struct x86_emulate_ctxt *ctxt, int seg) +static int em_lseg(struct x86_emulate_ctxt *ctxt) { + int seg = ctxt->src2.val; unsigned short sel; int rc; @@ -2452,7 +2472,7 @@ static int em_das(struct x86_emulate_ctxt *ctxt) ctxt->src.type = OP_IMM; ctxt->src.val = 0; ctxt->src.bytes = 1; - emulate_2op_SrcV("or", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "or"); ctxt->eflags &= ~(X86_EFLAGS_AF | X86_EFLAGS_CF); if (cf) ctxt->eflags |= X86_EFLAGS_CF; @@ -2502,49 +2522,49 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) static int em_add(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("add", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "add"); return X86EMUL_CONTINUE; } static int em_or(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("or", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "or"); return X86EMUL_CONTINUE; } static int em_adc(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("adc", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "adc"); return X86EMUL_CONTINUE; } static int em_sbb(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("sbb", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "sbb"); return X86EMUL_CONTINUE; } static int em_and(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("and", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "and"); return X86EMUL_CONTINUE; } static int em_sub(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("sub", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "sub"); return X86EMUL_CONTINUE; } static int em_xor(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("xor", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "xor"); return X86EMUL_CONTINUE; } static int em_cmp(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("cmp", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "cmp"); /* Disable writeback. */ ctxt->dst.type = OP_NONE; return X86EMUL_CONTINUE; @@ -2552,7 +2572,9 @@ static int em_cmp(struct x86_emulate_ctxt *ctxt) static int em_test(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV("test", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "test"); + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; return X86EMUL_CONTINUE; } @@ -2570,7 +2592,7 @@ static int em_xchg(struct x86_emulate_ctxt *ctxt) static int em_imul(struct x86_emulate_ctxt *ctxt) { - emulate_2op_SrcV_nobyte("imul", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV_nobyte(ctxt, "imul"); return X86EMUL_CONTINUE; } @@ -3025,9 +3047,14 @@ static struct opcode group1A[] = { }; static struct opcode group3[] = { - D(DstMem | SrcImm | ModRM), D(DstMem | SrcImm | ModRM), - D(DstMem | SrcNone | ModRM | Lock), D(DstMem | SrcNone | ModRM | Lock), - X4(D(SrcMem | ModRM)), + I(DstMem | SrcImm | ModRM, em_test), + I(DstMem | SrcImm | ModRM, em_test), + I(DstMem | SrcNone | ModRM | Lock, em_not), + I(DstMem | SrcNone | ModRM | Lock, em_neg), + I(SrcMem | ModRM, em_mul_ex), + I(SrcMem | ModRM, em_imul_ex), + I(SrcMem | ModRM, em_div_ex), + I(SrcMem | ModRM, em_idiv_ex), }; static struct opcode group4[] = { @@ -3090,16 +3117,20 @@ static struct gprefix pfx_0f_6f_0f_7f = { static struct opcode opcode_table[256] = { /* 0x00 - 0x07 */ I6ALU(Lock, em_add), - D(ImplicitOps | Stack | No64), D(ImplicitOps | Stack | No64), + I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg), + I(ImplicitOps | Stack | No64 | Src2ES, em_pop_sreg), /* 0x08 - 0x0F */ I6ALU(Lock, em_or), - D(ImplicitOps | Stack | No64), N, + I(ImplicitOps | Stack | No64 | Src2CS, em_push_sreg), + N, /* 0x10 - 0x17 */ I6ALU(Lock, em_adc), - D(ImplicitOps | Stack | No64), D(ImplicitOps | Stack | No64), + I(ImplicitOps | Stack | No64 | Src2SS, em_push_sreg), + I(ImplicitOps | Stack | No64 | Src2SS, em_pop_sreg), /* 0x18 - 0x1F */ I6ALU(Lock, em_sbb), - D(ImplicitOps | Stack | No64), D(ImplicitOps | Stack | No64), + I(ImplicitOps | Stack | No64 | Src2DS, em_push_sreg), + I(ImplicitOps | Stack | No64 | Src2DS, em_pop_sreg), /* 0x20 - 0x27 */ I6ALU(Lock, em_and), N, N, /* 0x28 - 0x2F */ @@ -3167,7 +3198,8 @@ static struct opcode opcode_table[256] = { D2bv(DstMem | SrcImmByte | ModRM), I(ImplicitOps | Stack | SrcImmU16, em_ret_near_imm), I(ImplicitOps | Stack, em_ret), - D(DstReg | SrcMemFAddr | ModRM | No64), D(DstReg | SrcMemFAddr | ModRM | No64), + I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg), + I(DstReg | SrcMemFAddr | ModRM | No64 | Src2DS, em_lseg), G(ByteOp, group11), G(0, group11), /* 0xC8 - 0xCF */ N, N, N, I(ImplicitOps | Stack, em_ret_far), @@ -3242,20 +3274,22 @@ static struct opcode twobyte_table[256] = { /* 0x90 - 0x9F */ X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)), /* 0xA0 - 0xA7 */ - D(ImplicitOps | Stack), D(ImplicitOps | Stack), + I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg), DI(ImplicitOps, cpuid), D(DstMem | SrcReg | ModRM | BitOp), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), N, N, /* 0xA8 - 0xAF */ - D(ImplicitOps | Stack), D(ImplicitOps | Stack), + I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg), DI(ImplicitOps, rsm), D(DstMem | SrcReg | ModRM | BitOp | Lock), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), D(ModRM), I(DstReg | SrcMem | ModRM, em_imul), /* 0xB0 - 0xB7 */ D2bv(DstMem | SrcReg | ModRM | Lock), - D(DstReg | SrcMemFAddr | ModRM), D(DstMem | SrcReg | ModRM | BitOp | Lock), - D(DstReg | SrcMemFAddr | ModRM), D(DstReg | SrcMemFAddr | ModRM), + I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg), + D(DstMem | SrcReg | ModRM | BitOp | Lock), + I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg), + I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg), D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xB8 - 0xBF */ N, N, @@ -3309,13 +3343,13 @@ static int decode_imm(struct x86_emulate_ctxt *ctxt, struct operand *op, /* NB. Immediates are sign-extended as necessary. */ switch (op->bytes) { case 1: - op->val = insn_fetch(s8, 1, ctxt->_eip); + op->val = insn_fetch(s8, ctxt); break; case 2: - op->val = insn_fetch(s16, 2, ctxt->_eip); + op->val = insn_fetch(s16, ctxt); break; case 4: - op->val = insn_fetch(s32, 4, ctxt->_eip); + op->val = insn_fetch(s32, ctxt); break; } if (!sign_extension) { @@ -3335,6 +3369,125 @@ done: return rc; } +static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, + unsigned d) +{ + int rc = X86EMUL_CONTINUE; + + switch (d) { + case OpReg: + decode_register_operand(ctxt, op, + op == &ctxt->dst && + ctxt->twobyte && (ctxt->b == 0xb6 || ctxt->b == 0xb7)); + break; + case OpImmUByte: + rc = decode_imm(ctxt, op, 1, false); + break; + case OpMem: + ctxt->memop.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; + mem_common: + *op = ctxt->memop; + ctxt->memopp = op; + if ((ctxt->d & BitOp) && op == &ctxt->dst) + fetch_bit_operand(ctxt); + op->orig_val = op->val; + break; + case OpMem64: + ctxt->memop.bytes = 8; + goto mem_common; + case OpAcc: + op->type = OP_REG; + op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; + op->addr.reg = &ctxt->regs[VCPU_REGS_RAX]; + fetch_register_operand(op); + op->orig_val = op->val; + break; + case OpDI: + op->type = OP_MEM; + op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; + op->addr.mem.ea = + register_address(ctxt, ctxt->regs[VCPU_REGS_RDI]); + op->addr.mem.seg = VCPU_SREG_ES; + op->val = 0; + break; + case OpDX: + op->type = OP_REG; + op->bytes = 2; + op->addr.reg = &ctxt->regs[VCPU_REGS_RDX]; + fetch_register_operand(op); + break; + case OpCL: + op->bytes = 1; + op->val = ctxt->regs[VCPU_REGS_RCX] & 0xff; + break; + case OpImmByte: + rc = decode_imm(ctxt, op, 1, true); + break; + case OpOne: + op->bytes = 1; + op->val = 1; + break; + case OpImm: + rc = decode_imm(ctxt, op, imm_size(ctxt), true); + break; + case OpMem16: + ctxt->memop.bytes = 2; + goto mem_common; + case OpMem32: + ctxt->memop.bytes = 4; + goto mem_common; + case OpImmU16: + rc = decode_imm(ctxt, op, 2, false); + break; + case OpImmU: + rc = decode_imm(ctxt, op, imm_size(ctxt), false); + break; + case OpSI: + op->type = OP_MEM; + op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; + op->addr.mem.ea = + register_address(ctxt, ctxt->regs[VCPU_REGS_RSI]); + op->addr.mem.seg = seg_override(ctxt); + op->val = 0; + break; + case OpImmFAddr: + op->type = OP_IMM; + op->addr.mem.ea = ctxt->_eip; + op->bytes = ctxt->op_bytes + 2; + insn_fetch_arr(op->valptr, op->bytes, ctxt); + break; + case OpMemFAddr: + ctxt->memop.bytes = ctxt->op_bytes + 2; + goto mem_common; + case OpES: + op->val = VCPU_SREG_ES; + break; + case OpCS: + op->val = VCPU_SREG_CS; + break; + case OpSS: + op->val = VCPU_SREG_SS; + break; + case OpDS: + op->val = VCPU_SREG_DS; + break; + case OpFS: + op->val = VCPU_SREG_FS; + break; + case OpGS: + op->val = VCPU_SREG_GS; + break; + case OpImplicit: + /* Special instructions do their own operand decoding. */ + default: + op->type = OP_NONE; /* Disable writeback. */ + break; + } + +done: + return rc; +} + int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) { int rc = X86EMUL_CONTINUE; @@ -3342,8 +3495,9 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) int def_op_bytes, def_ad_bytes, goffset, simd_prefix; bool op_prefix = false; struct opcode opcode; - struct operand memop = { .type = OP_NONE }, *memopp = NULL; + ctxt->memop.type = OP_NONE; + ctxt->memopp = NULL; ctxt->_eip = ctxt->eip; ctxt->fetch.start = ctxt->_eip; ctxt->fetch.end = ctxt->fetch.start + insn_len; @@ -3366,7 +3520,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) break; #endif default: - return -1; + return EMULATION_FAILED; } ctxt->op_bytes = def_op_bytes; @@ -3374,7 +3528,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) /* Legacy prefixes. */ for (;;) { - switch (ctxt->b = insn_fetch(u8, 1, ctxt->_eip)) { + switch (ctxt->b = insn_fetch(u8, ctxt)) { case 0x66: /* operand-size override */ op_prefix = true; /* switch between 2/4 bytes */ @@ -3430,7 +3584,7 @@ done_prefixes: /* Two-byte opcode? */ if (ctxt->b == 0x0f) { ctxt->twobyte = 1; - ctxt->b = insn_fetch(u8, 1, ctxt->_eip); + ctxt->b = insn_fetch(u8, ctxt); opcode = twobyte_table[ctxt->b]; } ctxt->d = opcode.flags; @@ -3438,13 +3592,13 @@ done_prefixes: while (ctxt->d & GroupMask) { switch (ctxt->d & GroupMask) { case Group: - ctxt->modrm = insn_fetch(u8, 1, ctxt->_eip); + ctxt->modrm = insn_fetch(u8, ctxt); --ctxt->_eip; goffset = (ctxt->modrm >> 3) & 7; opcode = opcode.u.group[goffset]; break; case GroupDual: - ctxt->modrm = insn_fetch(u8, 1, ctxt->_eip); + ctxt->modrm = insn_fetch(u8, ctxt); --ctxt->_eip; goffset = (ctxt->modrm >> 3) & 7; if ((ctxt->modrm >> 6) == 3) @@ -3458,7 +3612,7 @@ done_prefixes: break; case Prefix: if (ctxt->rep_prefix && op_prefix) - return X86EMUL_UNHANDLEABLE; + return EMULATION_FAILED; simd_prefix = op_prefix ? 0x66 : ctxt->rep_prefix; switch (simd_prefix) { case 0x00: opcode = opcode.u.gprefix->pfx_no; break; @@ -3468,10 +3622,10 @@ done_prefixes: } break; default: - return X86EMUL_UNHANDLEABLE; + return EMULATION_FAILED; } - ctxt->d &= ~GroupMask; + ctxt->d &= ~(u64)GroupMask; ctxt->d |= opcode.flags; } @@ -3481,10 +3635,10 @@ done_prefixes: /* Unrecognised? */ if (ctxt->d == 0 || (ctxt->d & Undefined)) - return -1; + return EMULATION_FAILED; if (!(ctxt->d & VendorSpecific) && ctxt->only_vendor_specific_insn) - return -1; + return EMULATION_FAILED; if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack)) ctxt->op_bytes = 8; @@ -3501,96 +3655,27 @@ done_prefixes: /* ModRM and SIB bytes. */ if (ctxt->d & ModRM) { - rc = decode_modrm(ctxt, &memop); + rc = decode_modrm(ctxt, &ctxt->memop); if (!ctxt->has_seg_override) set_seg_override(ctxt, ctxt->modrm_seg); } else if (ctxt->d & MemAbs) - rc = decode_abs(ctxt, &memop); + rc = decode_abs(ctxt, &ctxt->memop); if (rc != X86EMUL_CONTINUE) goto done; if (!ctxt->has_seg_override) set_seg_override(ctxt, VCPU_SREG_DS); - memop.addr.mem.seg = seg_override(ctxt); + ctxt->memop.addr.mem.seg = seg_override(ctxt); - if (memop.type == OP_MEM && ctxt->ad_bytes != 8) - memop.addr.mem.ea = (u32)memop.addr.mem.ea; + if (ctxt->memop.type == OP_MEM && ctxt->ad_bytes != 8) + ctxt->memop.addr.mem.ea = (u32)ctxt->memop.addr.mem.ea; /* * Decode and fetch the source operand: register, memory * or immediate. */ - switch (ctxt->d & SrcMask) { - case SrcNone: - break; - case SrcReg: - decode_register_operand(ctxt, &ctxt->src, 0); - break; - case SrcMem16: - memop.bytes = 2; - goto srcmem_common; - case SrcMem32: - memop.bytes = 4; - goto srcmem_common; - case SrcMem: - memop.bytes = (ctxt->d & ByteOp) ? 1 : - ctxt->op_bytes; - srcmem_common: - ctxt->src = memop; - memopp = &ctxt->src; - break; - case SrcImmU16: - rc = decode_imm(ctxt, &ctxt->src, 2, false); - break; - case SrcImm: - rc = decode_imm(ctxt, &ctxt->src, imm_size(ctxt), true); - break; - case SrcImmU: - rc = decode_imm(ctxt, &ctxt->src, imm_size(ctxt), false); - break; - case SrcImmByte: - rc = decode_imm(ctxt, &ctxt->src, 1, true); - break; - case SrcImmUByte: - rc = decode_imm(ctxt, &ctxt->src, 1, false); - break; - case SrcAcc: - ctxt->src.type = OP_REG; - ctxt->src.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - ctxt->src.addr.reg = &ctxt->regs[VCPU_REGS_RAX]; - fetch_register_operand(&ctxt->src); - break; - case SrcOne: - ctxt->src.bytes = 1; - ctxt->src.val = 1; - break; - case SrcSI: - ctxt->src.type = OP_MEM; - ctxt->src.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - ctxt->src.addr.mem.ea = - register_address(ctxt, ctxt->regs[VCPU_REGS_RSI]); - ctxt->src.addr.mem.seg = seg_override(ctxt); - ctxt->src.val = 0; - break; - case SrcImmFAddr: - ctxt->src.type = OP_IMM; - ctxt->src.addr.mem.ea = ctxt->_eip; - ctxt->src.bytes = ctxt->op_bytes + 2; - insn_fetch_arr(ctxt->src.valptr, ctxt->src.bytes, ctxt->_eip); - break; - case SrcMemFAddr: - memop.bytes = ctxt->op_bytes + 2; - goto srcmem_common; - break; - case SrcDX: - ctxt->src.type = OP_REG; - ctxt->src.bytes = 2; - ctxt->src.addr.reg = &ctxt->regs[VCPU_REGS_RDX]; - fetch_register_operand(&ctxt->src); - break; - } - + rc = decode_operand(ctxt, &ctxt->src, (ctxt->d >> SrcShift) & OpMask); if (rc != X86EMUL_CONTINUE) goto done; @@ -3598,85 +3683,18 @@ done_prefixes: * Decode and fetch the second source operand: register, memory * or immediate. */ - switch (ctxt->d & Src2Mask) { - case Src2None: - break; - case Src2CL: - ctxt->src2.bytes = 1; - ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0xff; - break; - case Src2ImmByte: - rc = decode_imm(ctxt, &ctxt->src2, 1, true); - break; - case Src2One: - ctxt->src2.bytes = 1; - ctxt->src2.val = 1; - break; - case Src2Imm: - rc = decode_imm(ctxt, &ctxt->src2, imm_size(ctxt), true); - break; - } - + rc = decode_operand(ctxt, &ctxt->src2, (ctxt->d >> Src2Shift) & OpMask); if (rc != X86EMUL_CONTINUE) goto done; /* Decode and fetch the destination operand: register or memory. */ - switch (ctxt->d & DstMask) { - case DstReg: - decode_register_operand(ctxt, &ctxt->dst, - ctxt->twobyte && (ctxt->b == 0xb6 || ctxt->b == 0xb7)); - break; - case DstImmUByte: - ctxt->dst.type = OP_IMM; - ctxt->dst.addr.mem.ea = ctxt->_eip; - ctxt->dst.bytes = 1; - ctxt->dst.val = insn_fetch(u8, 1, ctxt->_eip); - break; - case DstMem: - case DstMem64: - ctxt->dst = memop; - memopp = &ctxt->dst; - if ((ctxt->d & DstMask) == DstMem64) - ctxt->dst.bytes = 8; - else - ctxt->dst.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - if (ctxt->d & BitOp) - fetch_bit_operand(ctxt); - ctxt->dst.orig_val = ctxt->dst.val; - break; - case DstAcc: - ctxt->dst.type = OP_REG; - ctxt->dst.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - ctxt->dst.addr.reg = &ctxt->regs[VCPU_REGS_RAX]; - fetch_register_operand(&ctxt->dst); - ctxt->dst.orig_val = ctxt->dst.val; - break; - case DstDI: - ctxt->dst.type = OP_MEM; - ctxt->dst.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - ctxt->dst.addr.mem.ea = - register_address(ctxt, ctxt->regs[VCPU_REGS_RDI]); - ctxt->dst.addr.mem.seg = VCPU_SREG_ES; - ctxt->dst.val = 0; - break; - case DstDX: - ctxt->dst.type = OP_REG; - ctxt->dst.bytes = 2; - ctxt->dst.addr.reg = &ctxt->regs[VCPU_REGS_RDX]; - fetch_register_operand(&ctxt->dst); - break; - case ImplicitOps: - /* Special instructions do their own operand decoding. */ - default: - ctxt->dst.type = OP_NONE; /* Disable writeback. */ - break; - } + rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask); done: - if (memopp && memopp->type == OP_MEM && ctxt->rip_relative) - memopp->addr.mem.ea += ctxt->_eip; + if (ctxt->memopp && ctxt->memopp->type == OP_MEM && ctxt->rip_relative) + ctxt->memopp->addr.mem.ea += ctxt->_eip; - return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK; + return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK; } static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) @@ -3825,32 +3843,11 @@ special_insn: goto twobyte_insn; switch (ctxt->b) { - case 0x06: /* push es */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_ES); - break; - case 0x07: /* pop es */ - rc = emulate_pop_sreg(ctxt, VCPU_SREG_ES); - break; - case 0x0e: /* push cs */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_CS); - break; - case 0x16: /* push ss */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_SS); - break; - case 0x17: /* pop ss */ - rc = emulate_pop_sreg(ctxt, VCPU_SREG_SS); - break; - case 0x1e: /* push ds */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_DS); - break; - case 0x1f: /* pop ds */ - rc = emulate_pop_sreg(ctxt, VCPU_SREG_DS); - break; case 0x40 ... 0x47: /* inc r16/r32 */ - emulate_1op("inc", ctxt->dst, ctxt->eflags); + emulate_1op(ctxt, "inc"); break; case 0x48 ... 0x4f: /* dec r16/r32 */ - emulate_1op("dec", ctxt->dst, ctxt->eflags); + emulate_1op(ctxt, "dec"); break; case 0x63: /* movsxd */ if (ctxt->mode != X86EMUL_MODE_PROT64) @@ -3891,12 +3888,6 @@ special_insn: case 0xc0 ... 0xc1: rc = em_grp2(ctxt); break; - case 0xc4: /* les */ - rc = emulate_load_segment(ctxt, VCPU_SREG_ES); - break; - case 0xc5: /* lds */ - rc = emulate_load_segment(ctxt, VCPU_SREG_DS); - break; case 0xcc: /* int3 */ rc = emulate_int(ctxt, 3); break; @@ -3953,9 +3944,6 @@ special_insn: /* complement carry flag from eflags reg */ ctxt->eflags ^= EFLG_CF; break; - case 0xf6 ... 0xf7: /* Grp3 */ - rc = em_grp3(ctxt); - break; case 0xf8: /* clc */ ctxt->eflags &= ~EFLG_CF; break; @@ -4103,36 +4091,24 @@ twobyte_insn: case 0x90 ... 0x9f: /* setcc r/m8 */ ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags); break; - case 0xa0: /* push fs */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_FS); - break; - case 0xa1: /* pop fs */ - rc = emulate_pop_sreg(ctxt, VCPU_SREG_FS); - break; case 0xa3: bt: /* bt */ ctxt->dst.type = OP_NONE; /* only subword offset */ ctxt->src.val &= (ctxt->dst.bytes << 3) - 1; - emulate_2op_SrcV_nobyte("bt", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV_nobyte(ctxt, "bt"); break; case 0xa4: /* shld imm8, r, r/m */ case 0xa5: /* shld cl, r, r/m */ - emulate_2op_cl("shld", ctxt->src2, ctxt->src, ctxt->dst, ctxt->eflags); - break; - case 0xa8: /* push gs */ - rc = emulate_push_sreg(ctxt, VCPU_SREG_GS); - break; - case 0xa9: /* pop gs */ - rc = emulate_pop_sreg(ctxt, VCPU_SREG_GS); + emulate_2op_cl(ctxt, "shld"); break; case 0xab: bts: /* bts */ - emulate_2op_SrcV_nobyte("bts", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV_nobyte(ctxt, "bts"); break; case 0xac: /* shrd imm8, r, r/m */ case 0xad: /* shrd cl, r, r/m */ - emulate_2op_cl("shrd", ctxt->src2, ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_cl(ctxt, "shrd"); break; case 0xae: /* clflush */ break; @@ -4143,7 +4119,7 @@ twobyte_insn: */ ctxt->src.orig_val = ctxt->src.val; ctxt->src.val = ctxt->regs[VCPU_REGS_RAX]; - emulate_2op_SrcV("cmp", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "cmp"); if (ctxt->eflags & EFLG_ZF) { /* Success: write back to memory. */ ctxt->dst.val = ctxt->src.orig_val; @@ -4153,18 +4129,9 @@ twobyte_insn: ctxt->dst.addr.reg = (unsigned long *)&ctxt->regs[VCPU_REGS_RAX]; } break; - case 0xb2: /* lss */ - rc = emulate_load_segment(ctxt, VCPU_SREG_SS); - break; case 0xb3: btr: /* btr */ - emulate_2op_SrcV_nobyte("btr", ctxt->src, ctxt->dst, ctxt->eflags); - break; - case 0xb4: /* lfs */ - rc = emulate_load_segment(ctxt, VCPU_SREG_FS); - break; - case 0xb5: /* lgs */ - rc = emulate_load_segment(ctxt, VCPU_SREG_GS); + emulate_2op_SrcV_nobyte(ctxt, "btr"); break; case 0xb6 ... 0xb7: /* movzx */ ctxt->dst.bytes = ctxt->op_bytes; @@ -4185,7 +4152,7 @@ twobyte_insn: break; case 0xbb: btc: /* btc */ - emulate_2op_SrcV_nobyte("btc", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV_nobyte(ctxt, "btc"); break; case 0xbc: { /* bsf */ u8 zf; @@ -4217,7 +4184,7 @@ twobyte_insn: (s16) ctxt->src.val; break; case 0xc0 ... 0xc1: /* xadd */ - emulate_2op_SrcV("add", ctxt->src, ctxt->dst, ctxt->eflags); + emulate_2op_SrcV(ctxt, "add"); /* Write back the register source. */ ctxt->src.val = ctxt->dst.orig_val; write_register_operand(&ctxt->src); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index efad72385058..76e3f1cd0369 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -713,14 +713,16 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier); kvm_iodevice_init(&pit->dev, &pit_dev_ops); - ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &pit->dev); + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, KVM_PIT_BASE_ADDRESS, + KVM_PIT_MEM_LENGTH, &pit->dev); if (ret < 0) goto fail; if (flags & KVM_PIT_SPEAKER_DUMMY) { kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops); ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, - &pit->speaker_dev); + KVM_SPEAKER_BASE_ADDRESS, 4, + &pit->speaker_dev); if (ret < 0) goto fail_unregister; } diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 19fe855e7953..cac4746d7ffb 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -34,6 +34,9 @@ #include <linux/kvm_host.h> #include "trace.h" +#define pr_pic_unimpl(fmt, ...) \ + pr_err_ratelimited("kvm: pic: " fmt, ## __VA_ARGS__) + static void pic_irq_request(struct kvm *kvm, int level); static void pic_lock(struct kvm_pic *s) @@ -306,10 +309,10 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) } s->init_state = 1; if (val & 0x02) - printk(KERN_ERR "single mode not supported"); + pr_pic_unimpl("single mode not supported"); if (val & 0x08) - printk(KERN_ERR - "level sensitive irq not supported"); + pr_pic_unimpl( + "level sensitive irq not supported"); } else if (val & 0x08) { if (val & 0x04) s->poll = 1; @@ -459,22 +462,15 @@ static int picdev_in_range(gpa_t addr) } } -static inline struct kvm_pic *to_pic(struct kvm_io_device *dev) -{ - return container_of(dev, struct kvm_pic, dev); -} - -static int picdev_write(struct kvm_io_device *this, +static int picdev_write(struct kvm_pic *s, gpa_t addr, int len, const void *val) { - struct kvm_pic *s = to_pic(this); unsigned char data = *(unsigned char *)val; if (!picdev_in_range(addr)) return -EOPNOTSUPP; if (len != 1) { - if (printk_ratelimit()) - printk(KERN_ERR "PIC: non byte write\n"); + pr_pic_unimpl("non byte write\n"); return 0; } pic_lock(s); @@ -494,17 +490,15 @@ static int picdev_write(struct kvm_io_device *this, return 0; } -static int picdev_read(struct kvm_io_device *this, +static int picdev_read(struct kvm_pic *s, gpa_t addr, int len, void *val) { - struct kvm_pic *s = to_pic(this); unsigned char data = 0; if (!picdev_in_range(addr)) return -EOPNOTSUPP; if (len != 1) { - if (printk_ratelimit()) - printk(KERN_ERR "PIC: non byte read\n"); + pr_pic_unimpl("non byte read\n"); return 0; } pic_lock(s); @@ -525,6 +519,48 @@ static int picdev_read(struct kvm_io_device *this, return 0; } +static int picdev_master_write(struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + return picdev_write(container_of(dev, struct kvm_pic, dev_master), + addr, len, val); +} + +static int picdev_master_read(struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + return picdev_read(container_of(dev, struct kvm_pic, dev_master), + addr, len, val); +} + +static int picdev_slave_write(struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + return picdev_write(container_of(dev, struct kvm_pic, dev_slave), + addr, len, val); +} + +static int picdev_slave_read(struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + return picdev_read(container_of(dev, struct kvm_pic, dev_slave), + addr, len, val); +} + +static int picdev_eclr_write(struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + return picdev_write(container_of(dev, struct kvm_pic, dev_eclr), + addr, len, val); +} + +static int picdev_eclr_read(struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + return picdev_read(container_of(dev, struct kvm_pic, dev_eclr), + addr, len, val); +} + /* * callback when PIC0 irq status changed */ @@ -537,9 +573,19 @@ static void pic_irq_request(struct kvm *kvm, int level) s->output = level; } -static const struct kvm_io_device_ops picdev_ops = { - .read = picdev_read, - .write = picdev_write, +static const struct kvm_io_device_ops picdev_master_ops = { + .read = picdev_master_read, + .write = picdev_master_write, +}; + +static const struct kvm_io_device_ops picdev_slave_ops = { + .read = picdev_slave_read, + .write = picdev_slave_write, +}; + +static const struct kvm_io_device_ops picdev_eclr_ops = { + .read = picdev_eclr_read, + .write = picdev_eclr_write, }; struct kvm_pic *kvm_create_pic(struct kvm *kvm) @@ -560,16 +606,39 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm) /* * Initialize PIO device */ - kvm_iodevice_init(&s->dev, &picdev_ops); + kvm_iodevice_init(&s->dev_master, &picdev_master_ops); + kvm_iodevice_init(&s->dev_slave, &picdev_slave_ops); + kvm_iodevice_init(&s->dev_eclr, &picdev_eclr_ops); mutex_lock(&kvm->slots_lock); - ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &s->dev); + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0x20, 2, + &s->dev_master); + if (ret < 0) + goto fail_unlock; + + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0xa0, 2, &s->dev_slave); + if (ret < 0) + goto fail_unreg_2; + + ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, 0x4d0, 2, &s->dev_eclr); + if (ret < 0) + goto fail_unreg_1; + mutex_unlock(&kvm->slots_lock); - if (ret < 0) { - kfree(s); - return NULL; - } return s; + +fail_unreg_1: + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &s->dev_slave); + +fail_unreg_2: + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &s->dev_master); + +fail_unlock: + mutex_unlock(&kvm->slots_lock); + + kfree(s); + + return NULL; } void kvm_destroy_pic(struct kvm *kvm) @@ -577,7 +646,9 @@ void kvm_destroy_pic(struct kvm *kvm) struct kvm_pic *vpic = kvm->arch.vpic; if (vpic) { - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_master); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_slave); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_eclr); kvm->arch.vpic = NULL; kfree(vpic); } diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 53e2d084bffb..2086f2bfba33 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -66,7 +66,9 @@ struct kvm_pic { struct kvm *kvm; struct kvm_kpic_state pics[2]; /* 0 is master pic, 1 is slave pic */ int output; /* intr from master PIC */ - struct kvm_io_device dev; + struct kvm_io_device dev_master; + struct kvm_io_device dev_slave; + struct kvm_io_device dev_eclr; void (*ack_notifier)(void *opaque, int irq); unsigned long irq_states[16]; }; diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 3377d53fcd36..544076c4f44b 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -45,13 +45,6 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index) return vcpu->arch.walk_mmu->pdptrs[index]; } -static inline u64 kvm_pdptr_read_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, int index) -{ - load_pdptrs(vcpu, mmu, mmu->get_cr3(vcpu)); - - return mmu->pdptrs[index]; -} - static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) { ulong tmask = mask & KVM_POSSIBLE_CR0_GUEST_BITS; diff --git a/arch/x86/kvm/kvm_timer.h b/arch/x86/kvm/kvm_timer.h index 64bc6ea78d90..497dbaa366d4 100644 --- a/arch/x86/kvm/kvm_timer.h +++ b/arch/x86/kvm/kvm_timer.h @@ -2,6 +2,8 @@ struct kvm_timer { struct hrtimer timer; s64 period; /* unit: ns */ + u32 timer_mode_mask; + u64 tscdeadline; atomic_t pending; /* accumulated triggered timers */ bool reinject; struct kvm_timer_ops *t_ops; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 57dcbd4308fa..54abb40199d6 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -68,6 +68,9 @@ #define VEC_POS(v) ((v) & (32 - 1)) #define REG_POS(v) (((v) >> 5) << 4) +static unsigned int min_timer_period_us = 500; +module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); + static inline u32 apic_get_reg(struct kvm_lapic *apic, int reg_off) { return *((u32 *) (apic->regs + reg_off)); @@ -135,9 +138,23 @@ static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type) return apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK; } +static inline int apic_lvtt_oneshot(struct kvm_lapic *apic) +{ + return ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_ONESHOT); +} + static inline int apic_lvtt_period(struct kvm_lapic *apic) { - return apic_get_reg(apic, APIC_LVTT) & APIC_LVT_TIMER_PERIODIC; + return ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_PERIODIC); +} + +static inline int apic_lvtt_tscdeadline(struct kvm_lapic *apic) +{ + return ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) == + APIC_LVT_TIMER_TSCDEADLINE); } static inline int apic_lvt_nmi_mode(u32 lvt_val) @@ -166,7 +183,7 @@ static inline int apic_x2apic_mode(struct kvm_lapic *apic) } static unsigned int apic_lvt_mask[APIC_LVT_NUM] = { - LVT_MASK | APIC_LVT_TIMER_PERIODIC, /* LVTT */ + LVT_MASK , /* part LVTT mask, timer mode mask added at runtime */ LVT_MASK | APIC_MODE_MASK, /* LVTTHMR */ LVT_MASK | APIC_MODE_MASK, /* LVTPC */ LINT_MASK, LINT_MASK, /* LVT0-1 */ @@ -316,8 +333,8 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda) result = 1; break; default: - printk(KERN_WARNING "Bad DFR vcpu %d: %08x\n", - apic->vcpu->vcpu_id, apic_get_reg(apic, APIC_DFR)); + apic_debug("Bad DFR vcpu %d: %08x\n", + apic->vcpu->vcpu_id, apic_get_reg(apic, APIC_DFR)); break; } @@ -354,8 +371,8 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, result = (target != source); break; default: - printk(KERN_WARNING "Bad dest shorthand value %x\n", - short_hand); + apic_debug("kvm: apic: Bad dest shorthand value %x\n", + short_hand); break; } @@ -401,11 +418,11 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, break; case APIC_DM_REMRD: - printk(KERN_DEBUG "Ignoring delivery mode 3\n"); + apic_debug("Ignoring delivery mode 3\n"); break; case APIC_DM_SMI: - printk(KERN_DEBUG "Ignoring guest SMI\n"); + apic_debug("Ignoring guest SMI\n"); break; case APIC_DM_NMI: @@ -565,11 +582,13 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) val = kvm_apic_id(apic) << 24; break; case APIC_ARBPRI: - printk(KERN_WARNING "Access APIC ARBPRI register " - "which is for P6\n"); + apic_debug("Access APIC ARBPRI register which is for P6\n"); break; case APIC_TMCCT: /* Timer CCR */ + if (apic_lvtt_tscdeadline(apic)) + return 0; + val = apic_get_tmcct(apic); break; @@ -664,29 +683,40 @@ static void update_divide_count(struct kvm_lapic *apic) static void start_apic_timer(struct kvm_lapic *apic) { - ktime_t now = apic->lapic_timer.timer.base->get_time(); - - apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT) * - APIC_BUS_CYCLE_NS * apic->divide_count; + ktime_t now; atomic_set(&apic->lapic_timer.pending, 0); - if (!apic->lapic_timer.period) - return; - /* - * Do not allow the guest to program periodic timers with small - * interval, since the hrtimers are not throttled by the host - * scheduler. - */ - if (apic_lvtt_period(apic)) { - if (apic->lapic_timer.period < NSEC_PER_MSEC/2) - apic->lapic_timer.period = NSEC_PER_MSEC/2; - } + if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) { + /* lapic timer in oneshot or peroidic mode */ + now = apic->lapic_timer.timer.base->get_time(); + apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT) + * APIC_BUS_CYCLE_NS * apic->divide_count; + + if (!apic->lapic_timer.period) + return; + /* + * Do not allow the guest to program periodic timers with small + * interval, since the hrtimers are not throttled by the host + * scheduler. + */ + if (apic_lvtt_period(apic)) { + s64 min_period = min_timer_period_us * 1000LL; + + if (apic->lapic_timer.period < min_period) { + pr_info_ratelimited( + "kvm: vcpu %i: requested %lld ns " + "lapic timer period limited to %lld ns\n", + apic->vcpu->vcpu_id, + apic->lapic_timer.period, min_period); + apic->lapic_timer.period = min_period; + } + } - hrtimer_start(&apic->lapic_timer.timer, - ktime_add_ns(now, apic->lapic_timer.period), - HRTIMER_MODE_ABS); + hrtimer_start(&apic->lapic_timer.timer, + ktime_add_ns(now, apic->lapic_timer.period), + HRTIMER_MODE_ABS); - apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" + apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" PRIx64 ", " "timer initial count 0x%x, period %lldns, " "expire @ 0x%016" PRIx64 ".\n", __func__, @@ -695,6 +725,30 @@ static void start_apic_timer(struct kvm_lapic *apic) apic->lapic_timer.period, ktime_to_ns(ktime_add_ns(now, apic->lapic_timer.period))); + } else if (apic_lvtt_tscdeadline(apic)) { + /* lapic timer in tsc deadline mode */ + u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; + u64 ns = 0; + struct kvm_vcpu *vcpu = apic->vcpu; + unsigned long this_tsc_khz = vcpu_tsc_khz(vcpu); + unsigned long flags; + + if (unlikely(!tscdeadline || !this_tsc_khz)) + return; + + local_irq_save(flags); + + now = apic->lapic_timer.timer.base->get_time(); + guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); + if (likely(tscdeadline > guest_tsc)) { + ns = (tscdeadline - guest_tsc) * 1000000ULL; + do_div(ns, this_tsc_khz); + } + hrtimer_start(&apic->lapic_timer.timer, + ktime_add_ns(now, ns), HRTIMER_MODE_ABS); + + local_irq_restore(flags); + } } static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) @@ -782,7 +836,6 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVT0: apic_manage_nmi_watchdog(apic, val); - case APIC_LVTT: case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: @@ -796,7 +849,22 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) break; + case APIC_LVTT: + if ((apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask) != + (val & apic->lapic_timer.timer_mode_mask)) + hrtimer_cancel(&apic->lapic_timer.timer); + + if (!apic_sw_enabled(apic)) + val |= APIC_LVT_MASKED; + val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask); + apic_set_reg(apic, APIC_LVTT, val); + break; + case APIC_TMICT: + if (apic_lvtt_tscdeadline(apic)) + break; + hrtimer_cancel(&apic->lapic_timer.timer); apic_set_reg(apic, APIC_TMICT, val); start_apic_timer(apic); @@ -804,14 +872,14 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_TDCR: if (val & 4) - printk(KERN_ERR "KVM_WRITE:TDCR %x\n", val); + apic_debug("KVM_WRITE:TDCR %x\n", val); apic_set_reg(apic, APIC_TDCR, val); update_divide_count(apic); break; case APIC_ESR: if (apic_x2apic_mode(apic) && val != 0) { - printk(KERN_ERR "KVM_WRITE:ESR not zero %x\n", val); + apic_debug("KVM_WRITE:ESR not zero %x\n", val); ret = 1; } break; @@ -864,6 +932,15 @@ static int apic_mmio_write(struct kvm_io_device *this, return 0; } +void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (apic) + apic_reg_write(vcpu->arch.apic, APIC_EOI, 0); +} +EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); + void kvm_free_lapic(struct kvm_vcpu *vcpu) { if (!vcpu->arch.apic) @@ -883,6 +960,32 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu) *---------------------------------------------------------------------- */ +u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + if (!apic) + return 0; + + if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) + return 0; + + return apic->lapic_timer.tscdeadline; +} + +void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + if (!apic) + return; + + if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic)) + return; + + hrtimer_cancel(&apic->lapic_timer.timer); + apic->lapic_timer.tscdeadline = data; + start_apic_timer(apic); +} + void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) { struct kvm_lapic *apic = vcpu->arch.apic; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 52c9e6b9e725..138e8cc6fea6 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -26,6 +26,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); void kvm_lapic_reset(struct kvm_vcpu *vcpu); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); +void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); void kvm_apic_set_version(struct kvm_vcpu *vcpu); @@ -41,6 +42,9 @@ int kvm_lapic_enabled(struct kvm_vcpu *vcpu); bool kvm_apic_present(struct kvm_vcpu *vcpu); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); +u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); +void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data); + void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu); void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8e8da7960dbe..f1b36cf3e3d0 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2770,7 +2770,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) { - pdptr = kvm_pdptr_read_mmu(vcpu, &vcpu->arch.mmu, i); + pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i); if (!is_present_gpte(pdptr)) { vcpu->arch.mmu.pae_root[i] = 0; continue; @@ -3318,6 +3318,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->direct_map = true; context->set_cr3 = kvm_x86_ops->set_tdp_cr3; context->get_cr3 = get_cr3; + context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; context->nx = is_nx(vcpu); @@ -3376,6 +3377,7 @@ static int init_kvm_softmmu(struct kvm_vcpu *vcpu) vcpu->arch.walk_mmu->set_cr3 = kvm_x86_ops->set_cr3; vcpu->arch.walk_mmu->get_cr3 = get_cr3; + vcpu->arch.walk_mmu->get_pdptr = kvm_pdptr_read; vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault; return r; @@ -3386,6 +3388,7 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) struct kvm_mmu *g_context = &vcpu->arch.nested_mmu; g_context->get_cr3 = get_cr3; + g_context->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault; /* diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 2460a265be23..746ec259d024 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -121,16 +121,16 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) { + static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); unsigned long *rmapp; struct kvm_mmu_page *rev_sp; gfn_t gfn; - rev_sp = page_header(__pa(sptep)); gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt); if (!gfn_to_memslot(kvm, gfn)) { - if (!printk_ratelimit()) + if (!__ratelimit(&ratelimit_state)) return; audit_printk(kvm, "no memslot for gfn %llx\n", gfn); audit_printk(kvm, "index %ld of sp (gfn=%llx)\n", @@ -141,7 +141,7 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level); if (!*rmapp) { - if (!printk_ratelimit()) + if (!__ratelimit(&ratelimit_state)) return; audit_printk(kvm, "no rmap for writable spte %llx\n", *sptep); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 507e2b844cfa..92994100638b 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -147,7 +147,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, gfn_t table_gfn; unsigned index, pt_access, uninitialized_var(pte_access); gpa_t pte_gpa; - bool eperm; + bool eperm, last_gpte; int offset; const int write_fault = access & PFERR_WRITE_MASK; const int user_fault = access & PFERR_USER_MASK; @@ -163,7 +163,7 @@ retry_walk: #if PTTYPE == 64 if (walker->level == PT32E_ROOT_LEVEL) { - pte = kvm_pdptr_read_mmu(vcpu, mmu, (addr >> 30) & 3); + pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3); trace_kvm_mmu_paging_element(pte, walker->level); if (!is_present_gpte(pte)) goto error; @@ -221,6 +221,17 @@ retry_walk: eperm = true; #endif + last_gpte = FNAME(is_last_gpte)(walker, vcpu, mmu, pte); + if (last_gpte) { + pte_access = pt_access & + FNAME(gpte_access)(vcpu, pte, true); + /* check if the kernel is fetching from user page */ + if (unlikely(pte_access & PT_USER_MASK) && + kvm_read_cr4_bits(vcpu, X86_CR4_SMEP)) + if (fetch_fault && !user_fault) + eperm = true; + } + if (!eperm && unlikely(!(pte & PT_ACCESSED_MASK))) { int ret; trace_kvm_mmu_set_accessed_bit(table_gfn, index, @@ -238,18 +249,12 @@ retry_walk: walker->ptes[walker->level - 1] = pte; - if (FNAME(is_last_gpte)(walker, vcpu, mmu, pte)) { + if (last_gpte) { int lvl = walker->level; gpa_t real_gpa; gfn_t gfn; u32 ac; - /* check if the kernel is fetching from user page */ - if (unlikely(pte_access & PT_USER_MASK) && - kvm_read_cr4_bits(vcpu, X86_CR4_SMEP)) - if (fetch_fault && !user_fault) - eperm = true; - gfn = gpte_to_gfn_lvl(pte, lvl); gfn += (addr & PT_LVL_OFFSET_MASK(lvl)) >> PAGE_SHIFT; @@ -295,7 +300,6 @@ retry_walk: walker->ptes[walker->level - 1] = pte; } - pte_access = pt_access & FNAME(gpte_access)(vcpu, pte, true); walker->pt_access = pt_access; walker->pte_access = pte_access; pgprintk("%s: pte %llx pte_access %x pt_access %x\n", diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 475d1c948501..e32243eac2f4 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1084,7 +1084,6 @@ static void init_vmcb(struct vcpu_svm *svm) if (npt_enabled) { /* Setup VMCB for Nested Paging */ control->nested_ctl = 1; - clr_intercept(svm, INTERCEPT_TASK_SWITCH); clr_intercept(svm, INTERCEPT_INVLPG); clr_exception_intercept(svm, PF_VECTOR); clr_cr_intercept(svm, INTERCEPT_CR3_READ); @@ -1844,6 +1843,20 @@ static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu) return svm->nested.nested_cr3; } +static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 cr3 = svm->nested.nested_cr3; + u64 pdpte; + int ret; + + ret = kvm_read_guest_page(vcpu->kvm, gpa_to_gfn(cr3), &pdpte, + offset_in_page(cr3) + index * 8, 8); + if (ret) + return 0; + return pdpte; +} + static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) { @@ -1875,6 +1888,7 @@ static int nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu.set_cr3 = nested_svm_set_tdp_cr3; vcpu->arch.mmu.get_cr3 = nested_svm_get_tdp_cr3; + vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr; vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit; vcpu->arch.mmu.shadow_root_level = get_npt_level(); vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; @@ -2182,7 +2196,8 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) vmcb->control.exit_info_1, vmcb->control.exit_info_2, vmcb->control.exit_int_info, - vmcb->control.exit_int_info_err); + vmcb->control.exit_int_info_err, + KVM_ISA_SVM); nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page); if (!nested_vmcb) @@ -2894,15 +2909,20 @@ static int cr8_write_interception(struct vcpu_svm *svm) return 0; } +u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu) +{ + struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu)); + return vmcb->control.tsc_offset + + svm_scale_tsc(vcpu, native_read_tsc()); +} + static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) { struct vcpu_svm *svm = to_svm(vcpu); switch (ecx) { case MSR_IA32_TSC: { - struct vmcb *vmcb = get_host_vmcb(svm); - - *data = vmcb->control.tsc_offset + + *data = svm->vmcb->control.tsc_offset + svm_scale_tsc(vcpu, native_read_tsc()); break; @@ -3314,8 +3334,6 @@ static int handle_exit(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; - trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); - if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE)) vcpu->arch.cr0 = svm->vmcb->save.cr0; if (npt_enabled) @@ -3335,7 +3353,8 @@ static int handle_exit(struct kvm_vcpu *vcpu) svm->vmcb->control.exit_info_1, svm->vmcb->control.exit_info_2, svm->vmcb->control.exit_int_info, - svm->vmcb->control.exit_int_info_err); + svm->vmcb->control.exit_int_info_err, + KVM_ISA_SVM); vmexit = nested_svm_exit_special(svm); @@ -3768,6 +3787,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; + trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM); + if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_handle_nmi(&svm->vcpu); @@ -3897,60 +3918,6 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) } } -static const struct trace_print_flags svm_exit_reasons_str[] = { - { SVM_EXIT_READ_CR0, "read_cr0" }, - { SVM_EXIT_READ_CR3, "read_cr3" }, - { SVM_EXIT_READ_CR4, "read_cr4" }, - { SVM_EXIT_READ_CR8, "read_cr8" }, - { SVM_EXIT_WRITE_CR0, "write_cr0" }, - { SVM_EXIT_WRITE_CR3, "write_cr3" }, - { SVM_EXIT_WRITE_CR4, "write_cr4" }, - { SVM_EXIT_WRITE_CR8, "write_cr8" }, - { SVM_EXIT_READ_DR0, "read_dr0" }, - { SVM_EXIT_READ_DR1, "read_dr1" }, - { SVM_EXIT_READ_DR2, "read_dr2" }, - { SVM_EXIT_READ_DR3, "read_dr3" }, - { SVM_EXIT_WRITE_DR0, "write_dr0" }, - { SVM_EXIT_WRITE_DR1, "write_dr1" }, - { SVM_EXIT_WRITE_DR2, "write_dr2" }, - { SVM_EXIT_WRITE_DR3, "write_dr3" }, - { SVM_EXIT_WRITE_DR5, "write_dr5" }, - { SVM_EXIT_WRITE_DR7, "write_dr7" }, - { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, - { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, - { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, - { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, - { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, - { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, - { SVM_EXIT_INTR, "interrupt" }, - { SVM_EXIT_NMI, "nmi" }, - { SVM_EXIT_SMI, "smi" }, - { SVM_EXIT_INIT, "init" }, - { SVM_EXIT_VINTR, "vintr" }, - { SVM_EXIT_CPUID, "cpuid" }, - { SVM_EXIT_INVD, "invd" }, - { SVM_EXIT_HLT, "hlt" }, - { SVM_EXIT_INVLPG, "invlpg" }, - { SVM_EXIT_INVLPGA, "invlpga" }, - { SVM_EXIT_IOIO, "io" }, - { SVM_EXIT_MSR, "msr" }, - { SVM_EXIT_TASK_SWITCH, "task_switch" }, - { SVM_EXIT_SHUTDOWN, "shutdown" }, - { SVM_EXIT_VMRUN, "vmrun" }, - { SVM_EXIT_VMMCALL, "hypercall" }, - { SVM_EXIT_VMLOAD, "vmload" }, - { SVM_EXIT_VMSAVE, "vmsave" }, - { SVM_EXIT_STGI, "stgi" }, - { SVM_EXIT_CLGI, "clgi" }, - { SVM_EXIT_SKINIT, "skinit" }, - { SVM_EXIT_WBINVD, "wbinvd" }, - { SVM_EXIT_MONITOR, "monitor" }, - { SVM_EXIT_MWAIT, "mwait" }, - { SVM_EXIT_XSETBV, "xsetbv" }, - { SVM_EXIT_NPF, "npf" }, - { -1, NULL } -}; - static int svm_get_lpage_level(void) { return PT_PDPE_LEVEL; @@ -4223,7 +4190,6 @@ static struct kvm_x86_ops svm_x86_ops = { .get_mt_mask = svm_get_mt_mask, .get_exit_info = svm_get_exit_info, - .exit_reasons_str = svm_exit_reasons_str, .get_lpage_level = svm_get_lpage_level, @@ -4239,6 +4205,7 @@ static struct kvm_x86_ops svm_x86_ops = { .write_tsc_offset = svm_write_tsc_offset, .adjust_tsc_offset = svm_adjust_tsc_offset, .compute_tsc_offset = svm_compute_tsc_offset, + .read_l1_tsc = svm_read_l1_tsc, .set_tdp_cr3 = set_tdp_cr3, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 3ff898c104f7..911d2641f14c 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -2,6 +2,8 @@ #define _TRACE_KVM_H #include <linux/tracepoint.h> +#include <asm/vmx.h> +#include <asm/svm.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm @@ -181,6 +183,95 @@ TRACE_EVENT(kvm_apic, #define KVM_ISA_VMX 1 #define KVM_ISA_SVM 2 +#define VMX_EXIT_REASONS \ + { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ + { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ + { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ + { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ + { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ + { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ + { EXIT_REASON_CPUID, "CPUID" }, \ + { EXIT_REASON_HLT, "HLT" }, \ + { EXIT_REASON_INVLPG, "INVLPG" }, \ + { EXIT_REASON_RDPMC, "RDPMC" }, \ + { EXIT_REASON_RDTSC, "RDTSC" }, \ + { EXIT_REASON_VMCALL, "VMCALL" }, \ + { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \ + { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \ + { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \ + { EXIT_REASON_VMPTRST, "VMPTRST" }, \ + { EXIT_REASON_VMREAD, "VMREAD" }, \ + { EXIT_REASON_VMRESUME, "VMRESUME" }, \ + { EXIT_REASON_VMWRITE, "VMWRITE" }, \ + { EXIT_REASON_VMOFF, "VMOFF" }, \ + { EXIT_REASON_VMON, "VMON" }, \ + { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \ + { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \ + { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \ + { EXIT_REASON_MSR_READ, "MSR_READ" }, \ + { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ + { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ + { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ + { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ + { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ + { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ + { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ + { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ + { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ + { EXIT_REASON_WBINVD, "WBINVD" } + +#define SVM_EXIT_REASONS \ + { SVM_EXIT_READ_CR0, "read_cr0" }, \ + { SVM_EXIT_READ_CR3, "read_cr3" }, \ + { SVM_EXIT_READ_CR4, "read_cr4" }, \ + { SVM_EXIT_READ_CR8, "read_cr8" }, \ + { SVM_EXIT_WRITE_CR0, "write_cr0" }, \ + { SVM_EXIT_WRITE_CR3, "write_cr3" }, \ + { SVM_EXIT_WRITE_CR4, "write_cr4" }, \ + { SVM_EXIT_WRITE_CR8, "write_cr8" }, \ + { SVM_EXIT_READ_DR0, "read_dr0" }, \ + { SVM_EXIT_READ_DR1, "read_dr1" }, \ + { SVM_EXIT_READ_DR2, "read_dr2" }, \ + { SVM_EXIT_READ_DR3, "read_dr3" }, \ + { SVM_EXIT_WRITE_DR0, "write_dr0" }, \ + { SVM_EXIT_WRITE_DR1, "write_dr1" }, \ + { SVM_EXIT_WRITE_DR2, "write_dr2" }, \ + { SVM_EXIT_WRITE_DR3, "write_dr3" }, \ + { SVM_EXIT_WRITE_DR5, "write_dr5" }, \ + { SVM_EXIT_WRITE_DR7, "write_dr7" }, \ + { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \ + { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \ + { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ + { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ + { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ + { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ + { SVM_EXIT_INTR, "interrupt" }, \ + { SVM_EXIT_NMI, "nmi" }, \ + { SVM_EXIT_SMI, "smi" }, \ + { SVM_EXIT_INIT, "init" }, \ + { SVM_EXIT_VINTR, "vintr" }, \ + { SVM_EXIT_CPUID, "cpuid" }, \ + { SVM_EXIT_INVD, "invd" }, \ + { SVM_EXIT_HLT, "hlt" }, \ + { SVM_EXIT_INVLPG, "invlpg" }, \ + { SVM_EXIT_INVLPGA, "invlpga" }, \ + { SVM_EXIT_IOIO, "io" }, \ + { SVM_EXIT_MSR, "msr" }, \ + { SVM_EXIT_TASK_SWITCH, "task_switch" }, \ + { SVM_EXIT_SHUTDOWN, "shutdown" }, \ + { SVM_EXIT_VMRUN, "vmrun" }, \ + { SVM_EXIT_VMMCALL, "hypercall" }, \ + { SVM_EXIT_VMLOAD, "vmload" }, \ + { SVM_EXIT_VMSAVE, "vmsave" }, \ + { SVM_EXIT_STGI, "stgi" }, \ + { SVM_EXIT_CLGI, "clgi" }, \ + { SVM_EXIT_SKINIT, "skinit" }, \ + { SVM_EXIT_WBINVD, "wbinvd" }, \ + { SVM_EXIT_MONITOR, "monitor" }, \ + { SVM_EXIT_MWAIT, "mwait" }, \ + { SVM_EXIT_XSETBV, "xsetbv" }, \ + { SVM_EXIT_NPF, "npf" } + /* * Tracepoint for kvm guest exit: */ @@ -205,8 +296,9 @@ TRACE_EVENT(kvm_exit, ), TP_printk("reason %s rip 0x%lx info %llx %llx", - ftrace_print_symbols_seq(p, __entry->exit_reason, - kvm_x86_ops->exit_reasons_str), + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_reason, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_reason, SVM_EXIT_REASONS), __entry->guest_rip, __entry->info1, __entry->info2) ); @@ -486,9 +578,9 @@ TRACE_EVENT(kvm_nested_intercepts, TRACE_EVENT(kvm_nested_vmexit, TP_PROTO(__u64 rip, __u32 exit_code, __u64 exit_info1, __u64 exit_info2, - __u32 exit_int_info, __u32 exit_int_info_err), + __u32 exit_int_info, __u32 exit_int_info_err, __u32 isa), TP_ARGS(rip, exit_code, exit_info1, exit_info2, - exit_int_info, exit_int_info_err), + exit_int_info, exit_int_info_err, isa), TP_STRUCT__entry( __field( __u64, rip ) @@ -497,6 +589,7 @@ TRACE_EVENT(kvm_nested_vmexit, __field( __u64, exit_info2 ) __field( __u32, exit_int_info ) __field( __u32, exit_int_info_err ) + __field( __u32, isa ) ), TP_fast_assign( @@ -506,12 +599,14 @@ TRACE_EVENT(kvm_nested_vmexit, __entry->exit_info2 = exit_info2; __entry->exit_int_info = exit_int_info; __entry->exit_int_info_err = exit_int_info_err; + __entry->isa = isa; ), TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx " "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", __entry->rip, - ftrace_print_symbols_seq(p, __entry->exit_code, - kvm_x86_ops->exit_reasons_str), + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_code, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_code, SVM_EXIT_REASONS), __entry->exit_info1, __entry->exit_info2, __entry->exit_int_info, __entry->exit_int_info_err) ); @@ -522,9 +617,9 @@ TRACE_EVENT(kvm_nested_vmexit, TRACE_EVENT(kvm_nested_vmexit_inject, TP_PROTO(__u32 exit_code, __u64 exit_info1, __u64 exit_info2, - __u32 exit_int_info, __u32 exit_int_info_err), + __u32 exit_int_info, __u32 exit_int_info_err, __u32 isa), TP_ARGS(exit_code, exit_info1, exit_info2, - exit_int_info, exit_int_info_err), + exit_int_info, exit_int_info_err, isa), TP_STRUCT__entry( __field( __u32, exit_code ) @@ -532,6 +627,7 @@ TRACE_EVENT(kvm_nested_vmexit_inject, __field( __u64, exit_info2 ) __field( __u32, exit_int_info ) __field( __u32, exit_int_info_err ) + __field( __u32, isa ) ), TP_fast_assign( @@ -540,12 +636,14 @@ TRACE_EVENT(kvm_nested_vmexit_inject, __entry->exit_info2 = exit_info2; __entry->exit_int_info = exit_int_info; __entry->exit_int_info_err = exit_int_info_err; + __entry->isa = isa; ), TP_printk("reason: %s ext_inf1: 0x%016llx " "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x", - ftrace_print_symbols_seq(p, __entry->exit_code, - kvm_x86_ops->exit_reasons_str), + (__entry->isa == KVM_ISA_VMX) ? + __print_symbolic(__entry->exit_code, VMX_EXIT_REASONS) : + __print_symbolic(__entry->exit_code, SVM_EXIT_REASONS), __entry->exit_info1, __entry->exit_info2, __entry->exit_int_info, __entry->exit_int_info_err) ); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e65a158dee64..a0d6bd9ad442 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -71,6 +71,9 @@ module_param(vmm_exclusive, bool, S_IRUGO); static int __read_mostly yield_on_hlt = 1; module_param(yield_on_hlt, bool, S_IRUGO); +static int __read_mostly fasteoi = 1; +module_param(fasteoi, bool, S_IRUGO); + /* * If nested=1, nested virtualization is supported, i.e., guests may use * VMX and be a hypervisor for its own guests. If nested=0, guests may not @@ -1748,6 +1751,21 @@ static u64 guest_read_tsc(void) } /* + * Like guest_read_tsc, but always returns L1's notion of the timestamp + * counter, even if a nested guest (L2) is currently running. + */ +u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu) +{ + u64 host_tsc, tsc_offset; + + rdtscll(host_tsc); + tsc_offset = is_guest_mode(vcpu) ? + to_vmx(vcpu)->nested.vmcs01_tsc_offset : + vmcs_read64(TSC_OFFSET); + return host_tsc + tsc_offset; +} + +/* * Empty call-back. Needs to be implemented when VMX enables the SET_TSC_KHZ * ioctl. In this case the call-back should update internal vmx state to make * the changes effective. @@ -1762,15 +1780,23 @@ static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) */ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { - vmcs_write64(TSC_OFFSET, offset); - if (is_guest_mode(vcpu)) + if (is_guest_mode(vcpu)) { /* - * We're here if L1 chose not to trap the TSC MSR. Since - * prepare_vmcs12() does not copy tsc_offset, we need to also - * set the vmcs12 field here. + * We're here if L1 chose not to trap WRMSR to TSC. According + * to the spec, this should set L1's TSC; The offset that L1 + * set for L2 remains unchanged, and still needs to be added + * to the newly set TSC to get L2's TSC. */ - get_vmcs12(vcpu)->tsc_offset = offset - - to_vmx(vcpu)->nested.vmcs01_tsc_offset; + struct vmcs12 *vmcs12; + to_vmx(vcpu)->nested.vmcs01_tsc_offset = offset; + /* recalculate vmcs02.TSC_OFFSET: */ + vmcs12 = get_vmcs12(vcpu); + vmcs_write64(TSC_OFFSET, offset + + (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING) ? + vmcs12->tsc_offset : 0)); + } else { + vmcs_write64(TSC_OFFSET, offset); + } } static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment) @@ -2736,8 +2762,8 @@ static void enter_lmode(struct kvm_vcpu *vcpu) guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) { - printk(KERN_DEBUG "%s: tss fixup for long mode. \n", - __func__); + pr_debug_ratelimited("%s: tss fixup for long mode. \n", + __func__); vmcs_write32(GUEST_TR_AR_BYTES, (guest_tr_ar & ~AR_TYPE_MASK) | AR_TYPE_BUSY_64_TSS); @@ -4115,8 +4141,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); if (is_page_fault(intr_info)) { /* EPT won't cause page fault directly */ - if (enable_ept) - BUG(); + BUG_ON(enable_ept); cr2 = vmcs_readl(EXIT_QUALIFICATION); trace_kvm_page_fault(cr2, error_code); @@ -4518,6 +4543,24 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu) static int handle_apic_access(struct kvm_vcpu *vcpu) { + if (likely(fasteoi)) { + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + int access_type, offset; + + access_type = exit_qualification & APIC_ACCESS_TYPE; + offset = exit_qualification & APIC_ACCESS_OFFSET; + /* + * Sane guest uses MOV to write EOI, with written value + * not cared. So make a short-circuit here by avoiding + * heavy instruction emulation. + */ + if ((access_type == TYPE_LINEAR_APIC_INST_WRITE) && + (offset == APIC_EOI)) { + kvm_lapic_set_eoi(vcpu); + skip_emulated_instruction(vcpu); + return 1; + } + } return emulate_instruction(vcpu, 0) == EMULATE_DONE; } @@ -5591,8 +5634,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return 0; if (unlikely(vmx->fail)) { - printk(KERN_INFO "%s failed vm entry %x\n", - __func__, vmcs_read32(VM_INSTRUCTION_ERROR)); + pr_info_ratelimited("%s failed vm entry %x\n", __func__, + vmcs_read32(VM_INSTRUCTION_ERROR)); return 1; } @@ -5696,8 +5739,6 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; - trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); - /* If guest state is invalid, start emulating */ if (vmx->emulation_required && emulate_invalid_guest_state) return handle_invalid_guest_state(vcpu); @@ -6101,6 +6142,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); + trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); vmx_complete_atomic_exit(vmx); vmx_recover_nmi_blocking(vmx); @@ -6241,49 +6283,6 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) return ret; } -#define _ER(x) { EXIT_REASON_##x, #x } - -static const struct trace_print_flags vmx_exit_reasons_str[] = { - _ER(EXCEPTION_NMI), - _ER(EXTERNAL_INTERRUPT), - _ER(TRIPLE_FAULT), - _ER(PENDING_INTERRUPT), - _ER(NMI_WINDOW), - _ER(TASK_SWITCH), - _ER(CPUID), - _ER(HLT), - _ER(INVLPG), - _ER(RDPMC), - _ER(RDTSC), - _ER(VMCALL), - _ER(VMCLEAR), - _ER(VMLAUNCH), - _ER(VMPTRLD), - _ER(VMPTRST), - _ER(VMREAD), - _ER(VMRESUME), - _ER(VMWRITE), - _ER(VMOFF), - _ER(VMON), - _ER(CR_ACCESS), - _ER(DR_ACCESS), - _ER(IO_INSTRUCTION), - _ER(MSR_READ), - _ER(MSR_WRITE), - _ER(MWAIT_INSTRUCTION), - _ER(MONITOR_INSTRUCTION), - _ER(PAUSE_INSTRUCTION), - _ER(MCE_DURING_VMENTRY), - _ER(TPR_BELOW_THRESHOLD), - _ER(APIC_ACCESS), - _ER(EPT_VIOLATION), - _ER(EPT_MISCONFIG), - _ER(WBINVD), - { -1, NULL } -}; - -#undef _ER - static int vmx_get_lpage_level(void) { if (enable_ept && !cpu_has_vmx_ept_1g_page()) @@ -6514,8 +6513,11 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) set_cr4_guest_host_mask(vmx); - vmcs_write64(TSC_OFFSET, - vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset); + if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) + vmcs_write64(TSC_OFFSET, + vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset); + else + vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); if (enable_vpid) { /* @@ -6610,9 +6612,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (vmcs12->vm_entry_msr_load_count > 0 || vmcs12->vm_exit_msr_load_count > 0 || vmcs12->vm_exit_msr_store_count > 0) { - if (printk_ratelimit()) - printk(KERN_WARNING - "%s: VMCS MSR_{LOAD,STORE} unsupported\n", __func__); + pr_warn_ratelimited("%s: VMCS MSR_{LOAD,STORE} unsupported\n", + __func__); nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; } @@ -6922,7 +6923,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu) load_vmcs12_host_state(vcpu, vmcs12); - /* Update TSC_OFFSET if vmx_adjust_tsc_offset() was used while L2 ran */ + /* Update TSC_OFFSET if TSC was changed while L2 ran */ vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); /* This is needed for same reason as it was needed in prepare_vmcs02 */ @@ -7039,7 +7040,6 @@ static struct kvm_x86_ops vmx_x86_ops = { .get_mt_mask = vmx_get_mt_mask, .get_exit_info = vmx_get_exit_info, - .exit_reasons_str = vmx_exit_reasons_str, .get_lpage_level = vmx_get_lpage_level, @@ -7055,6 +7055,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .write_tsc_offset = vmx_write_tsc_offset, .adjust_tsc_offset = vmx_adjust_tsc_offset, .compute_tsc_offset = vmx_compute_tsc_offset, + .read_l1_tsc = vmx_read_l1_tsc, .set_tdp_cr3 = vmx_set_cr3, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 84a28ea45fa4..c38efd7b792e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -44,6 +44,7 @@ #include <linux/perf_event.h> #include <linux/uaccess.h> #include <linux/hash.h> +#include <linux/pci.h> #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS @@ -83,6 +84,7 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); static void update_cr8_intercept(struct kvm_vcpu *vcpu); static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); +static void process_nmi(struct kvm_vcpu *vcpu); struct kvm_x86_ops *kvm_x86_ops; EXPORT_SYMBOL_GPL(kvm_x86_ops); @@ -359,8 +361,8 @@ void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) void kvm_inject_nmi(struct kvm_vcpu *vcpu) { - kvm_make_request(KVM_REQ_EVENT, vcpu); - vcpu->arch.nmi_pending = 1; + atomic_inc(&vcpu->arch.nmi_queued); + kvm_make_request(KVM_REQ_NMI, vcpu); } EXPORT_SYMBOL_GPL(kvm_inject_nmi); @@ -599,6 +601,8 @@ static bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) static void update_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; + struct kvm_lapic *apic = vcpu->arch.apic; + u32 timer_mode_mask; best = kvm_find_cpuid_entry(vcpu, 1, 0); if (!best) @@ -610,6 +614,16 @@ static void update_cpuid(struct kvm_vcpu *vcpu) if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) best->ecx |= bit(X86_FEATURE_OSXSAVE); } + + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && + best->function == 0x1) { + best->ecx |= bit(X86_FEATURE_TSC_DEADLINE_TIMER); + timer_mode_mask = 3 << 17; + } else + timer_mode_mask = 1 << 17; + + if (apic) + apic->lapic_timer.timer_mode_mask = timer_mode_mask; } int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -825,6 +839,7 @@ static u32 msrs_to_save[] = { static unsigned num_msrs_to_save; static u32 emulated_msrs[] = { + MSR_IA32_TSCDEADLINE, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, @@ -1000,7 +1015,7 @@ static inline int kvm_tsc_changes_freq(void) return ret; } -static u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu) +u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu) { if (vcpu->arch.virtual_tsc_khz) return vcpu->arch.virtual_tsc_khz; @@ -1098,7 +1113,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); - kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp); + tsc_timestamp = kvm_x86_ops->read_l1_tsc(v); kernel_ns = get_kernel_ns(); this_tsc_khz = vcpu_tsc_khz(v); if (unlikely(this_tsc_khz == 0)) { @@ -1564,6 +1579,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: return kvm_x2apic_msr_write(vcpu, msr, data); + case MSR_IA32_TSCDEADLINE: + kvm_set_lapic_tscdeadline_msr(vcpu, data); + break; case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; @@ -1825,6 +1843,9 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); case HV_X64_MSR_TPR: return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); + case HV_X64_MSR_APIC_ASSIST_PAGE: + data = vcpu->arch.hv_vapic; + break; default: pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; @@ -1839,7 +1860,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) switch (msr) { case MSR_IA32_PLATFORM_ID: - case MSR_IA32_UCODE_REV: case MSR_IA32_EBL_CR_POWERON: case MSR_IA32_DEBUGCTLMSR: case MSR_IA32_LASTBRANCHFROMIP: @@ -1860,6 +1880,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_FAM10H_MMIO_CONF_BASE: data = 0; break; + case MSR_IA32_UCODE_REV: + data = 0x100000000ULL; + break; case MSR_MTRRcap: data = 0x500 | KVM_NR_VAR_MTRR; break; @@ -1888,6 +1911,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: return kvm_x2apic_msr_read(vcpu, msr, pdata); break; + case MSR_IA32_TSCDEADLINE: + data = kvm_get_lapic_tscdeadline_msr(vcpu); + break; case MSR_IA32_MISC_ENABLE: data = vcpu->arch.ia32_misc_enable_msr; break; @@ -2086,6 +2112,9 @@ int kvm_dev_ioctl_check_extension(long ext) r = !kvm_x86_ops->cpu_has_accelerated_tpr(); break; case KVM_CAP_NR_VCPUS: + r = KVM_SOFT_MAX_VCPUS; + break; + case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; break; case KVM_CAP_NR_MEMSLOTS: @@ -2095,7 +2124,7 @@ int kvm_dev_ioctl_check_extension(long ext) r = 0; break; case KVM_CAP_IOMMU: - r = iommu_found(); + r = iommu_present(&pci_bus_type); break; case KVM_CAP_MCE: r = KVM_MAX_MCE_BANKS; @@ -2210,7 +2239,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) s64 tsc_delta; u64 tsc; - kvm_get_msr(vcpu, MSR_IA32_TSC, &tsc); + tsc = kvm_x86_ops->read_l1_tsc(vcpu); tsc_delta = !vcpu->arch.last_guest_tsc ? 0 : tsc - vcpu->arch.last_guest_tsc; @@ -2234,7 +2263,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); - kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc); + vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); } static int is_efer_nx(void) @@ -2819,6 +2848,7 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { + process_nmi(vcpu); events->exception.injected = vcpu->arch.exception.pending && !kvm_exception_is_soft(vcpu->arch.exception.nr); @@ -2836,7 +2866,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI); events->nmi.injected = vcpu->arch.nmi_injected; - events->nmi.pending = vcpu->arch.nmi_pending; + events->nmi.pending = vcpu->arch.nmi_pending != 0; events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); events->nmi.pad = 0; @@ -2856,6 +2886,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, | KVM_VCPUEVENT_VALID_SHADOW)) return -EINVAL; + process_nmi(vcpu); vcpu->arch.exception.pending = events->exception.injected; vcpu->arch.exception.nr = events->exception.nr; vcpu->arch.exception.has_error_code = events->exception.has_error_code; @@ -3556,7 +3587,11 @@ long kvm_arch_vm_ioctl(struct file *filp, if (r) { mutex_lock(&kvm->slots_lock); kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev); + &vpic->dev_master); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_slave); + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev_eclr); mutex_unlock(&kvm->slots_lock); kfree(vpic); goto create_irqchip_unlock; @@ -4045,84 +4080,105 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, return 0; } -static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, - unsigned long addr, - void *val, - unsigned int bytes, - struct x86_exception *exception) +int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, + const void *val, int bytes) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - gpa_t gpa; - int handled, ret; + int ret; + ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); + if (ret < 0) + return 0; + kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1); + return 1; +} + +struct read_write_emulator_ops { + int (*read_write_prepare)(struct kvm_vcpu *vcpu, void *val, + int bytes); + int (*read_write_emulate)(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes); + int (*read_write_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, + int bytes, void *val); + int (*read_write_exit_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes); + bool write; +}; + +static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) +{ if (vcpu->mmio_read_completed) { memcpy(val, vcpu->mmio_data, bytes); trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, vcpu->mmio_phys_addr, *(u64 *)val); vcpu->mmio_read_completed = 0; - return X86EMUL_CONTINUE; + return 1; } - ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, false); - - if (ret < 0) - return X86EMUL_PROPAGATE_FAULT; - - if (ret) - goto mmio; - - if (kvm_read_guest_virt(ctxt, addr, val, bytes, exception) - == X86EMUL_CONTINUE) - return X86EMUL_CONTINUE; + return 0; +} -mmio: - /* - * Is this MMIO handled locally? - */ - handled = vcpu_mmio_read(vcpu, gpa, bytes, val); +static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + return !kvm_read_guest(vcpu->kvm, gpa, val, bytes); +} - if (handled == bytes) - return X86EMUL_CONTINUE; +static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ + return emulator_write_phys(vcpu, gpa, val, bytes); +} - gpa += handled; - bytes -= handled; - val += handled; +static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val) +{ + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); + return vcpu_mmio_write(vcpu, gpa, bytes, val); +} +static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) +{ trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); - - vcpu->mmio_needed = 1; - vcpu->run->exit_reason = KVM_EXIT_MMIO; - vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->run->mmio.len = min(vcpu->mmio_size, 8); - vcpu->run->mmio.is_write = vcpu->mmio_is_write = 0; - vcpu->mmio_index = 0; - return X86EMUL_IO_NEEDED; } -int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, - const void *val, int bytes) +static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, + void *val, int bytes) { - int ret; - - ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); - if (ret < 0) - return 0; - kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1); - return 1; + memcpy(vcpu->mmio_data, val, bytes); + memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8); + return X86EMUL_CONTINUE; } -static int emulator_write_emulated_onepage(unsigned long addr, - const void *val, - unsigned int bytes, - struct x86_exception *exception, - struct kvm_vcpu *vcpu) +static struct read_write_emulator_ops read_emultor = { + .read_write_prepare = read_prepare, + .read_write_emulate = read_emulate, + .read_write_mmio = vcpu_mmio_read, + .read_write_exit_mmio = read_exit_mmio, +}; + +static struct read_write_emulator_ops write_emultor = { + .read_write_emulate = write_emulate, + .read_write_mmio = write_mmio, + .read_write_exit_mmio = write_exit_mmio, + .write = true, +}; + +static int emulator_read_write_onepage(unsigned long addr, void *val, + unsigned int bytes, + struct x86_exception *exception, + struct kvm_vcpu *vcpu, + struct read_write_emulator_ops *ops) { gpa_t gpa; int handled, ret; + bool write = ops->write; - ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, true); + if (ops->read_write_prepare && + ops->read_write_prepare(vcpu, val, bytes)) + return X86EMUL_CONTINUE; + + ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); if (ret < 0) return X86EMUL_PROPAGATE_FAULT; @@ -4131,15 +4187,14 @@ static int emulator_write_emulated_onepage(unsigned long addr, if (ret) goto mmio; - if (emulator_write_phys(vcpu, gpa, val, bytes)) + if (ops->read_write_emulate(vcpu, gpa, val, bytes)) return X86EMUL_CONTINUE; mmio: - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); /* * Is this MMIO handled locally? */ - handled = vcpu_mmio_write(vcpu, gpa, bytes, val); + handled = ops->read_write_mmio(vcpu, gpa, bytes, val); if (handled == bytes) return X86EMUL_CONTINUE; @@ -4148,23 +4203,20 @@ mmio: val += handled; vcpu->mmio_needed = 1; - memcpy(vcpu->mmio_data, val, bytes); vcpu->run->exit_reason = KVM_EXIT_MMIO; vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa; vcpu->mmio_size = bytes; vcpu->run->mmio.len = min(vcpu->mmio_size, 8); - vcpu->run->mmio.is_write = vcpu->mmio_is_write = 1; - memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8); + vcpu->run->mmio.is_write = vcpu->mmio_is_write = write; vcpu->mmio_index = 0; - return X86EMUL_CONTINUE; + return ops->read_write_exit_mmio(vcpu, gpa, val, bytes); } -int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, - unsigned long addr, - const void *val, - unsigned int bytes, - struct x86_exception *exception) +int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, + void *val, unsigned int bytes, + struct x86_exception *exception, + struct read_write_emulator_ops *ops) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); @@ -4173,16 +4225,38 @@ int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, int rc, now; now = -addr & ~PAGE_MASK; - rc = emulator_write_emulated_onepage(addr, val, now, exception, - vcpu); + rc = emulator_read_write_onepage(addr, val, now, exception, + vcpu, ops); + if (rc != X86EMUL_CONTINUE) return rc; addr += now; val += now; bytes -= now; } - return emulator_write_emulated_onepage(addr, val, bytes, exception, - vcpu); + + return emulator_read_write_onepage(addr, val, bytes, exception, + vcpu, ops); +} + +static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, + void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + return emulator_read_write(ctxt, addr, val, bytes, + exception, &read_emultor); +} + +int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, + unsigned long addr, + const void *val, + unsigned int bytes, + struct x86_exception *exception) +{ + return emulator_read_write(ctxt, addr, (void *)val, bytes, + exception, &write_emultor); } #define CMPXCHG_TYPE(t, ptr, old, new) \ @@ -4712,7 +4786,7 @@ int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) kvm_set_rflags(vcpu, ctxt->eflags); if (irq == NMI_VECTOR) - vcpu->arch.nmi_pending = false; + vcpu->arch.nmi_pending = 0; else vcpu->arch.interrupt.pending = false; @@ -4788,7 +4862,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, trace_kvm_emulate_insn_start(vcpu); ++vcpu->stat.insn_emulation; - if (r) { + if (r != EMULATION_OK) { if (emulation_type & EMULTYPE_TRAP_UD) return EMULATE_FAIL; if (reexecute_instruction(vcpu, cr2)) @@ -5521,7 +5595,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu) /* try to inject new event if pending */ if (vcpu->arch.nmi_pending) { if (kvm_x86_ops->nmi_allowed(vcpu)) { - vcpu->arch.nmi_pending = false; + --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; kvm_x86_ops->set_nmi(vcpu); } @@ -5553,10 +5627,26 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) } } +static void process_nmi(struct kvm_vcpu *vcpu) +{ + unsigned limit = 2; + + /* + * x86 is limited to one NMI running, and one NMI pending after it. + * If an NMI is already in progress, limit further NMIs to just one. + * Otherwise, allow two (and we'll inject the first one immediately). + */ + if (kvm_x86_ops->get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) + limit = 1; + + vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); + kvm_make_request(KVM_REQ_EVENT, vcpu); +} + static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; - bool nmi_pending; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && vcpu->run->request_interrupt_window; @@ -5596,6 +5686,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_NMI, vcpu)) + process_nmi(vcpu); } @@ -5603,19 +5695,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (unlikely(r)) goto out; - /* - * An NMI can be injected between local nmi_pending read and - * vcpu->arch.nmi_pending read inside inject_pending_event(). - * But in that case, KVM_REQ_EVENT will be set, which makes - * the race described above benign. - */ - nmi_pending = ACCESS_ONCE(vcpu->arch.nmi_pending); - if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { inject_pending_event(vcpu); /* enable NMI/IRQ window open exits if needed */ - if (nmi_pending) + if (vcpu->arch.nmi_pending) kvm_x86_ops->enable_nmi_window(vcpu); else if (kvm_cpu_has_interrupt(vcpu) || req_int_win) kvm_x86_ops->enable_irq_window(vcpu); @@ -5678,7 +5762,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (hw_breakpoint_active()) hw_breakpoint_restore(); - kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc); + vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); @@ -6323,7 +6407,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) { - vcpu->arch.nmi_pending = false; + atomic_set(&vcpu->arch.nmi_queued, 0); + vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; vcpu->arch.switch_db_regs = 0; @@ -6598,7 +6683,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) !vcpu->arch.apf.halted) || !list_empty_careful(&vcpu->async_pf.done) || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED - || vcpu->arch.nmi_pending || + || atomic_read(&vcpu->arch.nmi_queued) || (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)); } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 13ee258442ae..f63da5ef217c 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -70,6 +70,7 @@ #include <asm/i387.h> #include <asm/stackprotector.h> #include <asm/reboot.h> /* for struct machine_ops */ +#include <asm/kvm_para.h> /*G:010 * Welcome to the Guest! @@ -455,6 +456,15 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, *ax &= 0xFFFFF0FF; *ax |= 0x00000500; break; + + /* + * This is used to detect if we're running under KVM. We might be, + * but that's a Host matter, not us. So say we're not. + */ + case KVM_CPUID_SIGNATURE: + *bx = *cx = *dx = 0; + break; + /* * 0x80000000 returns the highest Extended Function, so we futureproof * like we do above by limiting it to known fields. diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 9f33b984d0ef..374562ed6704 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -22,14 +22,23 @@ #include <asm/inat.h> #include <asm/insn.h> -#define get_next(t, insn) \ - ({t r; r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; }) +/* Verify next sizeof(t) bytes can be on the same instruction */ +#define validate_next(t, insn, n) \ + ((insn)->next_byte + sizeof(t) + n - (insn)->kaddr <= MAX_INSN_SIZE) + +#define __get_next(t, insn) \ + ({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; }) + +#define __peek_nbyte_next(t, insn, n) \ + ({ t r = *(t*)((insn)->next_byte + n); r; }) -#define peek_next(t, insn) \ - ({t r; r = *(t*)insn->next_byte; r; }) +#define get_next(t, insn) \ + ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); }) #define peek_nbyte_next(t, insn, n) \ - ({t r; r = *(t*)((insn)->next_byte + n); r; }) + ({ if (unlikely(!validate_next(t, insn, n))) goto err_out; __peek_nbyte_next(t, insn, n); }) + +#define peek_next(t, insn) peek_nbyte_next(t, insn, 0) /** * insn_init() - initialize struct insn @@ -158,6 +167,8 @@ vex_end: insn->vex_prefix.got = 1; prefixes->got = 1; + +err_out: return; } @@ -208,6 +219,9 @@ void insn_get_opcode(struct insn *insn) insn->attr = 0; /* This instruction is bad */ end: opcode->got = 1; + +err_out: + return; } /** @@ -241,6 +255,9 @@ void insn_get_modrm(struct insn *insn) if (insn->x86_64 && inat_is_force64(insn->attr)) insn->opnd_bytes = 8; modrm->got = 1; + +err_out: + return; } @@ -290,6 +307,9 @@ void insn_get_sib(struct insn *insn) } } insn->sib.got = 1; + +err_out: + return; } @@ -351,6 +371,9 @@ void insn_get_displacement(struct insn *insn) } out: insn->displacement.got = 1; + +err_out: + return; } /* Decode moffset16/32/64 */ @@ -373,6 +396,9 @@ static void __get_moffset(struct insn *insn) break; } insn->moffset1.got = insn->moffset2.got = 1; + +err_out: + return; } /* Decode imm v32(Iz) */ @@ -389,6 +415,9 @@ static void __get_immv32(struct insn *insn) insn->immediate.nbytes = 4; break; } + +err_out: + return; } /* Decode imm v64(Iv/Ov) */ @@ -411,6 +440,9 @@ static void __get_immv(struct insn *insn) break; } insn->immediate1.got = insn->immediate2.got = 1; + +err_out: + return; } /* Decode ptr16:16/32(Ap) */ @@ -432,6 +464,9 @@ static void __get_immptr(struct insn *insn) insn->immediate2.value = get_next(unsigned short, insn); insn->immediate2.nbytes = 2; insn->immediate1.got = insn->immediate2.got = 1; + +err_out: + return; } /** @@ -496,6 +531,9 @@ void insn_get_immediate(struct insn *insn) } done: insn->immediate.got = 1; + +err_out: + return; } /** diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 0d17c8c50acd..5db0490deb07 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -17,7 +17,7 @@ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/pgalloc.h> /* pgd_*(), ... */ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ -#include <asm/vsyscall.h> +#include <asm/fixmap.h> /* VSYSCALL_START */ /* * Page fault error code bits: @@ -420,12 +420,14 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) return 0; } +#ifdef CONFIG_CPU_SUP_AMD static const char errata93_warning[] = KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n" "******* Working around it, but it may cause SEGVs or burn power.\n" "******* Please consider a BIOS update.\n" "******* Disabling USB legacy in the BIOS may also help.\n"; +#endif /* * No vm86 mode in 64-bit mode: @@ -505,7 +507,11 @@ bad: */ static int is_errata93(struct pt_regs *regs, unsigned long address) { -#ifdef CONFIG_X86_64 +#if defined(CONFIG_X86_64) && defined(CONFIG_CPU_SUP_AMD) + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD + || boot_cpu_data.x86 != 0xf) + return 0; + if (address != regs->ip) return 0; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 30326443ab81..87488b93a65c 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -63,9 +63,8 @@ static void __init find_early_table_space(unsigned long end, int use_pse, #ifdef CONFIG_X86_32 /* for fixmap */ tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE); - - good_end = max_pfn_mapped << PAGE_SHIFT; #endif + good_end = max_pfn_mapped << PAGE_SHIFT; base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE); if (base == MEMBLOCK_ERROR) diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 1dab5194fd9d..4b5ba85eb5c9 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -31,6 +31,10 @@ #include <linux/sched.h> #include <asm/elf.h> +struct __read_mostly va_alignment va_align = { + .flags = -1, +}; + static unsigned int stack_maxrandom_size(void) { unsigned int max = 0; @@ -42,7 +46,6 @@ static unsigned int stack_maxrandom_size(void) return max; } - /* * Top of mmap area (just below the process stack). * @@ -51,21 +54,6 @@ static unsigned int stack_maxrandom_size(void) #define MIN_GAP (128*1024*1024UL + stack_maxrandom_size()) #define MAX_GAP (TASK_SIZE/6*5) -/* - * True on X86_32 or when emulating IA32 on X86_64 - */ -static int mmap_is_ia32(void) -{ -#ifdef CONFIG_X86_32 - return 1; -#endif -#ifdef CONFIG_IA32_EMULATION - if (test_thread_flag(TIF_IA32)) - return 1; -#endif - return 0; -} - static int mmap_is_legacy(void) { if (current->personality & ADDR_COMPAT_LAYOUT) diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 67421f38a215..de54b9b278a7 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -29,7 +29,6 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/io.h> -#include <linux/version.h> #include <linux/kallsyms.h> #include <asm/pgtable.h> #include <linux/mmiotrace.h> diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 68894fdc034b..75f9528e0372 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -61,26 +61,15 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model, } -static int profile_exceptions_notify(struct notifier_block *self, - unsigned long val, void *data) +static int profile_exceptions_notify(unsigned int val, struct pt_regs *regs) { - struct die_args *args = (struct die_args *)data; - int ret = NOTIFY_DONE; - - switch (val) { - case DIE_NMI: - if (ctr_running) - model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs)); - else if (!nmi_enabled) - break; - else - model->stop(&__get_cpu_var(cpu_msrs)); - ret = NOTIFY_STOP; - break; - default: - break; - } - return ret; + if (ctr_running) + model->check_ctrs(regs, &__get_cpu_var(cpu_msrs)); + else if (!nmi_enabled) + return NMI_DONE; + else + model->stop(&__get_cpu_var(cpu_msrs)); + return NMI_HANDLED; } static void nmi_cpu_save_registers(struct op_msrs *msrs) @@ -355,20 +344,14 @@ static void nmi_cpu_setup(void *dummy) int cpu = smp_processor_id(); struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu); nmi_cpu_save_registers(msrs); - spin_lock(&oprofilefs_lock); + raw_spin_lock(&oprofilefs_lock); model->setup_ctrs(model, msrs); nmi_cpu_setup_mux(cpu, msrs); - spin_unlock(&oprofilefs_lock); + raw_spin_unlock(&oprofilefs_lock); per_cpu(saved_lvtpc, cpu) = apic_read(APIC_LVTPC); apic_write(APIC_LVTPC, APIC_DM_NMI); } -static struct notifier_block profile_exceptions_nb = { - .notifier_call = profile_exceptions_notify, - .next = NULL, - .priority = NMI_LOCAL_LOW_PRIOR, -}; - static void nmi_cpu_restore_registers(struct op_msrs *msrs) { struct op_msr *counters = msrs->counters; @@ -402,8 +385,6 @@ static void nmi_cpu_shutdown(void *dummy) apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu)); apic_write(APIC_LVTERR, v); nmi_cpu_restore_registers(msrs); - if (model->cpu_down) - model->cpu_down(); } static void nmi_cpu_up(void *dummy) @@ -508,7 +489,8 @@ static int nmi_setup(void) ctr_running = 0; /* make variables visible to the nmi handler: */ smp_mb(); - err = register_die_notifier(&profile_exceptions_nb); + err = register_nmi_handler(NMI_LOCAL, profile_exceptions_notify, + 0, "oprofile"); if (err) goto fail; @@ -538,7 +520,7 @@ static void nmi_shutdown(void) put_online_cpus(); /* make variables visible to the nmi handler: */ smp_mb(); - unregister_die_notifier(&profile_exceptions_nb); + unregister_nmi_handler(NMI_LOCAL, "oprofile"); msrs = &get_cpu_var(cpu_msrs); model->shutdown(msrs); free_msrs(); diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c index 720bf5a53c51..7f8052cd6620 100644 --- a/arch/x86/oprofile/nmi_timer_int.c +++ b/arch/x86/oprofile/nmi_timer_int.c @@ -18,32 +18,16 @@ #include <asm/apic.h> #include <asm/ptrace.h> -static int profile_timer_exceptions_notify(struct notifier_block *self, - unsigned long val, void *data) +static int profile_timer_exceptions_notify(unsigned int val, struct pt_regs *regs) { - struct die_args *args = (struct die_args *)data; - int ret = NOTIFY_DONE; - - switch (val) { - case DIE_NMI: - oprofile_add_sample(args->regs, 0); - ret = NOTIFY_STOP; - break; - default: - break; - } - return ret; + oprofile_add_sample(regs, 0); + return NMI_HANDLED; } -static struct notifier_block profile_timer_exceptions_nb = { - .notifier_call = profile_timer_exceptions_notify, - .next = NULL, - .priority = NMI_LOW_PRIOR, -}; - static int timer_start(void) { - if (register_die_notifier(&profile_timer_exceptions_nb)) + if (register_nmi_handler(NMI_LOCAL, profile_timer_exceptions_notify, + 0, "oprofile-timer")) return 1; return 0; } @@ -51,7 +35,7 @@ static int timer_start(void) static void timer_stop(void) { - unregister_die_notifier(&profile_timer_exceptions_nb); + unregister_nmi_handler(NMI_LOCAL, "oprofile-timer"); synchronize_sched(); /* Allow already-started NMIs to complete. */ } diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index 9cbb710dc94b..303f08637826 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -29,8 +29,6 @@ #include "op_x86_model.h" #include "op_counter.h" -#define NUM_COUNTERS 4 -#define NUM_COUNTERS_F15H 6 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX #define NUM_VIRT_COUNTERS 32 #else @@ -70,62 +68,12 @@ static struct ibs_config ibs_config; static struct ibs_state ibs_state; /* - * IBS cpuid feature detection - */ - -#define IBS_CPUID_FEATURES 0x8000001b - -/* - * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but - * bit 0 is used to indicate the existence of IBS. - */ -#define IBS_CAPS_AVAIL (1U<<0) -#define IBS_CAPS_FETCHSAM (1U<<1) -#define IBS_CAPS_OPSAM (1U<<2) -#define IBS_CAPS_RDWROPCNT (1U<<3) -#define IBS_CAPS_OPCNT (1U<<4) -#define IBS_CAPS_BRNTRGT (1U<<5) -#define IBS_CAPS_OPCNTEXT (1U<<6) - -#define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \ - | IBS_CAPS_FETCHSAM \ - | IBS_CAPS_OPSAM) - -/* - * IBS APIC setup - */ -#define IBSCTL 0x1cc -#define IBSCTL_LVT_OFFSET_VALID (1ULL<<8) -#define IBSCTL_LVT_OFFSET_MASK 0x0F - -/* * IBS randomization macros */ #define IBS_RANDOM_BITS 12 #define IBS_RANDOM_MASK ((1ULL << IBS_RANDOM_BITS) - 1) #define IBS_RANDOM_MAXCNT_OFFSET (1ULL << (IBS_RANDOM_BITS - 5)) -static u32 get_ibs_caps(void) -{ - u32 ibs_caps; - unsigned int max_level; - - if (!boot_cpu_has(X86_FEATURE_IBS)) - return 0; - - /* check IBS cpuid feature flags */ - max_level = cpuid_eax(0x80000000); - if (max_level < IBS_CPUID_FEATURES) - return IBS_CAPS_DEFAULT; - - ibs_caps = cpuid_eax(IBS_CPUID_FEATURES); - if (!(ibs_caps & IBS_CAPS_AVAIL)) - /* cpuid flags not valid */ - return IBS_CAPS_DEFAULT; - - return ibs_caps; -} - /* * 16-bit Linear Feedback Shift Register (LFSR) * @@ -316,81 +264,6 @@ static void op_amd_stop_ibs(void) wrmsrl(MSR_AMD64_IBSOPCTL, 0); } -static inline int get_eilvt(int offset) -{ - return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1); -} - -static inline int put_eilvt(int offset) -{ - return !setup_APIC_eilvt(offset, 0, 0, 1); -} - -static inline int ibs_eilvt_valid(void) -{ - int offset; - u64 val; - int valid = 0; - - preempt_disable(); - - rdmsrl(MSR_AMD64_IBSCTL, val); - offset = val & IBSCTL_LVT_OFFSET_MASK; - - if (!(val & IBSCTL_LVT_OFFSET_VALID)) { - pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n", - smp_processor_id(), offset, MSR_AMD64_IBSCTL, val); - goto out; - } - - if (!get_eilvt(offset)) { - pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n", - smp_processor_id(), offset, MSR_AMD64_IBSCTL, val); - goto out; - } - - valid = 1; -out: - preempt_enable(); - - return valid; -} - -static inline int get_ibs_offset(void) -{ - u64 val; - - rdmsrl(MSR_AMD64_IBSCTL, val); - if (!(val & IBSCTL_LVT_OFFSET_VALID)) - return -EINVAL; - - return val & IBSCTL_LVT_OFFSET_MASK; -} - -static void setup_APIC_ibs(void) -{ - int offset; - - offset = get_ibs_offset(); - if (offset < 0) - goto failed; - - if (!setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 0)) - return; -failed: - pr_warn("oprofile: IBS APIC setup failed on cpu #%d\n", - smp_processor_id()); -} - -static void clear_APIC_ibs(void) -{ - int offset; - - offset = get_ibs_offset(); - if (offset >= 0) - setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1); -} - #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX static void op_mux_switch_ctrl(struct op_x86_model_spec const *model, @@ -439,7 +312,7 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs) goto fail; } /* both registers must be reserved */ - if (num_counters == NUM_COUNTERS_F15H) { + if (num_counters == AMD64_NUM_COUNTERS_F15H) { msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1); msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1); } else { @@ -504,15 +377,6 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model, val |= op_x86_get_ctrl(model, &counter_config[virt]); wrmsrl(msrs->controls[i].addr, val); } - - if (ibs_caps) - setup_APIC_ibs(); -} - -static void op_amd_cpu_shutdown(void) -{ - if (ibs_caps) - clear_APIC_ibs(); } static int op_amd_check_ctrs(struct pt_regs * const regs, @@ -575,86 +439,6 @@ static void op_amd_stop(struct op_msrs const * const msrs) op_amd_stop_ibs(); } -static int setup_ibs_ctl(int ibs_eilvt_off) -{ - struct pci_dev *cpu_cfg; - int nodes; - u32 value = 0; - - nodes = 0; - cpu_cfg = NULL; - do { - cpu_cfg = pci_get_device(PCI_VENDOR_ID_AMD, - PCI_DEVICE_ID_AMD_10H_NB_MISC, - cpu_cfg); - if (!cpu_cfg) - break; - ++nodes; - pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off - | IBSCTL_LVT_OFFSET_VALID); - pci_read_config_dword(cpu_cfg, IBSCTL, &value); - if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) { - pci_dev_put(cpu_cfg); - printk(KERN_DEBUG "Failed to setup IBS LVT offset, " - "IBSCTL = 0x%08x\n", value); - return -EINVAL; - } - } while (1); - - if (!nodes) { - printk(KERN_DEBUG "No CPU node configured for IBS\n"); - return -ENODEV; - } - - return 0; -} - -/* - * This runs only on the current cpu. We try to find an LVT offset and - * setup the local APIC. For this we must disable preemption. On - * success we initialize all nodes with this offset. This updates then - * the offset in the IBS_CTL per-node msr. The per-core APIC setup of - * the IBS interrupt vector is called from op_amd_setup_ctrs()/op_- - * amd_cpu_shutdown() using the new offset. - */ -static int force_ibs_eilvt_setup(void) -{ - int offset; - int ret; - - preempt_disable(); - /* find the next free available EILVT entry, skip offset 0 */ - for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) { - if (get_eilvt(offset)) - break; - } - preempt_enable(); - - if (offset == APIC_EILVT_NR_MAX) { - printk(KERN_DEBUG "No EILVT entry available\n"); - return -EBUSY; - } - - ret = setup_ibs_ctl(offset); - if (ret) - goto out; - - if (!ibs_eilvt_valid()) { - ret = -EFAULT; - goto out; - } - - pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset); - pr_err(FW_BUG "workaround enabled for IBS LVT offset\n"); - - return 0; -out: - preempt_disable(); - put_eilvt(offset); - preempt_enable(); - return ret; -} - /* * check and reserve APIC extended interrupt LVT offset for IBS if * available @@ -667,17 +451,6 @@ static void init_ibs(void) if (!ibs_caps) return; - if (ibs_eilvt_valid()) - goto out; - - if (!force_ibs_eilvt_setup()) - goto out; - - /* Failed to setup ibs */ - ibs_caps = 0; - return; - -out: printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps); } @@ -741,9 +514,9 @@ static int op_amd_init(struct oprofile_operations *ops) ops->create_files = setup_ibs_files; if (boot_cpu_data.x86 == 0x15) { - num_counters = NUM_COUNTERS_F15H; + num_counters = AMD64_NUM_COUNTERS_F15H; } else { - num_counters = NUM_COUNTERS; + num_counters = AMD64_NUM_COUNTERS; } op_amd_spec.num_counters = num_counters; @@ -760,7 +533,6 @@ struct op_x86_model_spec op_amd_spec = { .init = op_amd_init, .fill_in_addresses = &op_amd_fill_in_addresses, .setup_ctrs = &op_amd_setup_ctrs, - .cpu_down = &op_amd_cpu_shutdown, .check_ctrs = &op_amd_check_ctrs, .start = &op_amd_start, .stop = &op_amd_stop, diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index 94b745045e45..d90528ea5412 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -28,7 +28,7 @@ static int counter_width = 32; #define MSR_PPRO_EVENTSEL_RESERVED ((0xFFFFFFFFULL<<32)|(1ULL<<21)) -static u64 *reset_value; +static u64 reset_value[OP_MAX_COUNTER]; static void ppro_shutdown(struct op_msrs const * const msrs) { @@ -40,10 +40,6 @@ static void ppro_shutdown(struct op_msrs const * const msrs) release_perfctr_nmi(MSR_P6_PERFCTR0 + i); release_evntsel_nmi(MSR_P6_EVNTSEL0 + i); } - if (reset_value) { - kfree(reset_value); - reset_value = NULL; - } } static int ppro_fill_in_addresses(struct op_msrs * const msrs) @@ -79,13 +75,6 @@ static void ppro_setup_ctrs(struct op_x86_model_spec const *model, u64 val; int i; - if (!reset_value) { - reset_value = kzalloc(sizeof(reset_value[0]) * num_counters, - GFP_ATOMIC); - if (!reset_value) - return; - } - if (cpu_has_arch_perfmon) { union cpuid10_eax eax; eax.full = cpuid_eax(0xa); @@ -141,13 +130,6 @@ static int ppro_check_ctrs(struct pt_regs * const regs, u64 val; int i; - /* - * This can happen if perf counters are in use when - * we steal the die notifier NMI. - */ - if (unlikely(!reset_value)) - goto out; - for (i = 0; i < num_counters; ++i) { if (!reset_value[i]) continue; @@ -158,7 +140,6 @@ static int ppro_check_ctrs(struct pt_regs * const regs, wrmsrl(msrs->counters[i].addr, -reset_value[i]); } -out: /* Only P6 based Pentium M need to re-unmask the apic vector but it * doesn't hurt other P6 variant */ apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED); @@ -179,8 +160,6 @@ static void ppro_start(struct op_msrs const * const msrs) u64 val; int i; - if (!reset_value) - return; for (i = 0; i < num_counters; ++i) { if (reset_value[i]) { rdmsrl(msrs->controls[i].addr, val); @@ -196,8 +175,6 @@ static void ppro_stop(struct op_msrs const * const msrs) u64 val; int i; - if (!reset_value) - return; for (i = 0; i < num_counters; ++i) { if (!reset_value[i]) continue; @@ -242,7 +219,7 @@ static void arch_perfmon_setup_counters(void) eax.split.bit_width = 40; } - num_counters = eax.split.num_counters; + num_counters = min((int)eax.split.num_counters, OP_MAX_COUNTER); op_arch_perfmon_spec.num_counters = num_counters; op_arch_perfmon_spec.num_controls = num_counters; diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h index 89017fa1fd63..71e8a67337e2 100644 --- a/arch/x86/oprofile/op_x86_model.h +++ b/arch/x86/oprofile/op_x86_model.h @@ -43,7 +43,6 @@ struct op_x86_model_spec { int (*fill_in_addresses)(struct op_msrs * const msrs); void (*setup_ctrs)(struct op_x86_model_spec const *model, struct op_msrs const * const msrs); - void (*cpu_down)(void); int (*check_ctrs)(struct pt_regs * const regs, struct op_msrs const * const msrs); void (*start)(struct op_msrs const * const msrs); diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 039d91315bc5..404f21a3ff9e 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -43,6 +43,17 @@ static const struct dmi_system_id pci_use_crs_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "ALiveSATA2-GLAN"), }, }, + /* https://bugzilla.kernel.org/show_bug.cgi?id=30552 */ + /* 2006 AMD HT/VIA system with two host bridges */ + { + .callback = set_use_crs, + .ident = "ASUS M2V-MX SE", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."), + DMI_MATCH(DMI_BOARD_NAME, "M2V-MX SE"), + DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."), + }, + }, {} }; diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c index 99176094500b..41bd2a2d2c50 100644 --- a/arch/x86/pci/ce4100.c +++ b/arch/x86/pci/ce4100.c @@ -304,7 +304,7 @@ static int ce4100_conf_write(unsigned int seg, unsigned int bus, return pci_direct_conf1.write(seg, bus, devfn, reg, len, value); } -struct pci_raw_ops ce4100_pci_conf = { +static const struct pci_raw_ops ce4100_pci_conf = { .read = ce4100_conf_read, .write = ce4100_conf_write, }; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 92df322e0b57..7962ccb4d9b2 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -33,8 +33,8 @@ int noioapicreroute = 1; int pcibios_last_bus = -1; unsigned long pirq_table_addr; struct pci_bus *pci_root_bus; -struct pci_raw_ops *raw_pci_ops; -struct pci_raw_ops *raw_pci_ext_ops; +const struct pci_raw_ops *__read_mostly raw_pci_ops; +const struct pci_raw_ops *__read_mostly raw_pci_ext_ops; int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val) diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c index 4f2c70439d7f..15460590b8c5 100644 --- a/arch/x86/pci/direct.c +++ b/arch/x86/pci/direct.c @@ -79,7 +79,7 @@ static int pci_conf1_write(unsigned int seg, unsigned int bus, #undef PCI_CONF1_ADDRESS -struct pci_raw_ops pci_direct_conf1 = { +const struct pci_raw_ops pci_direct_conf1 = { .read = pci_conf1_read, .write = pci_conf1_write, }; @@ -175,7 +175,7 @@ static int pci_conf2_write(unsigned int seg, unsigned int bus, #undef PCI_CONF2_ADDRESS -struct pci_raw_ops pci_direct_conf2 = { +static const struct pci_raw_ops pci_direct_conf2 = { .read = pci_conf2_read, .write = pci_conf2_write, }; @@ -191,7 +191,7 @@ struct pci_raw_ops pci_direct_conf2 = { * This should be close to trivial, but it isn't, because there are buggy * chipsets (yes, you guessed it, by Intel and Compaq) that have no class ID. */ -static int __init pci_sanity_check(struct pci_raw_ops *o) +static int __init pci_sanity_check(const struct pci_raw_ops *o) { u32 x = 0; int year, devfn; diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c index a3d9c54792ae..5372e86834c0 100644 --- a/arch/x86/pci/mmconfig_32.c +++ b/arch/x86/pci/mmconfig_32.c @@ -117,7 +117,7 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus, return 0; } -static struct pci_raw_ops pci_mmcfg = { +static const struct pci_raw_ops pci_mmcfg = { .read = pci_mmcfg_read, .write = pci_mmcfg_write, }; diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index e783841bd1d7..915a493502cb 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -81,7 +81,7 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus, return 0; } -static struct pci_raw_ops pci_mmcfg = { +static const struct pci_raw_ops pci_mmcfg = { .read = pci_mmcfg_read, .write = pci_mmcfg_write, }; diff --git a/arch/x86/pci/numaq_32.c b/arch/x86/pci/numaq_32.c index 512a88c41501..51abf02f9226 100644 --- a/arch/x86/pci/numaq_32.c +++ b/arch/x86/pci/numaq_32.c @@ -110,7 +110,7 @@ static int pci_conf1_mq_write(unsigned int seg, unsigned int bus, #undef PCI_CONF1_MQ_ADDRESS -static struct pci_raw_ops pci_direct_conf1_mq = { +static const struct pci_raw_ops pci_direct_conf1_mq = { .read = pci_conf1_mq_read, .write = pci_conf1_mq_write }; diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c index 5262603b04d9..7043a4f0e98a 100644 --- a/arch/x86/pci/olpc.c +++ b/arch/x86/pci/olpc.c @@ -301,7 +301,7 @@ static int pci_olpc_write(unsigned int seg, unsigned int bus, return 0; } -static struct pci_raw_ops pci_olpc_conf = { +static const struct pci_raw_ops pci_olpc_conf = { .read = pci_olpc_read, .write = pci_olpc_write, }; diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index f68553551467..db0e9a51e611 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -303,7 +303,7 @@ static int pci_bios_write(unsigned int seg, unsigned int bus, * Function table for BIOS32 access */ -static struct pci_raw_ops pci_bios_access = { +static const struct pci_raw_ops pci_bios_access = { .read = pci_bios_read, .write = pci_bios_write }; @@ -312,7 +312,7 @@ static struct pci_raw_ops pci_bios_access = { * Try to find PCI BIOS. */ -static struct pci_raw_ops * __devinit pci_find_bios(void) +static const struct pci_raw_ops * __devinit pci_find_bios(void) { union bios32 *check; unsigned char sum; diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 1017c7bee388..492ade8c978e 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -175,8 +175,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) "pcifront-msi-x" : "pcifront-msi", DOMID_SELF); - if (irq < 0) + if (irq < 0) { + ret = irq; goto free; + } i++; } kfree(v); @@ -221,8 +223,10 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (msg.data != XEN_PIRQ_MSI_DATA || xen_irq_from_pirq(pirq) < 0) { pirq = xen_allocate_pirq_msi(dev, msidesc); - if (pirq < 0) + if (pirq < 0) { + irq = -ENODEV; goto error; + } xen_msi_compose_msg(dev, pirq, &msg); __write_msi_msg(msidesc, &msg); dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq); @@ -244,10 +248,12 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) error: dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); - return -ENODEV; + return irq; } #ifdef CONFIG_XEN_DOM0 +static bool __read_mostly pci_seg_supported = true; + static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { int ret = 0; @@ -265,10 +271,11 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) memset(&map_irq, 0, sizeof(map_irq)); map_irq.domid = domid; - map_irq.type = MAP_PIRQ_TYPE_MSI; + map_irq.type = MAP_PIRQ_TYPE_MSI_SEG; map_irq.index = -1; map_irq.pirq = -1; - map_irq.bus = dev->bus->number; + map_irq.bus = dev->bus->number | + (pci_domain_nr(dev->bus) << 16); map_irq.devfn = dev->devfn; if (type == PCI_CAP_ID_MSIX) { @@ -285,7 +292,20 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) map_irq.entry_nr = msidesc->msi_attrib.entry_nr; } - ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); + ret = -EINVAL; + if (pci_seg_supported) + ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, + &map_irq); + if (ret == -EINVAL && !pci_domain_nr(dev->bus)) { + map_irq.type = MAP_PIRQ_TYPE_MSI; + map_irq.index = -1; + map_irq.pirq = -1; + map_irq.bus = dev->bus->number; + ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, + &map_irq); + if (ret != -EINVAL) + pci_seg_supported = false; + } if (ret) { dev_warn(&dev->dev, "xen map irq failed %d for %d domain\n", ret, domid); diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile index 021eee91c056..8d874396cb29 100644 --- a/arch/x86/platform/Makefile +++ b/arch/x86/platform/Makefile @@ -1,6 +1,7 @@ # Platform specific code goes here obj-y += ce4100/ obj-y += efi/ +obj-y += geode/ obj-y += iris/ obj-y += mrst/ obj-y += olpc/ diff --git a/arch/x86/platform/geode/Makefile b/arch/x86/platform/geode/Makefile new file mode 100644 index 000000000000..07c9cd05021a --- /dev/null +++ b/arch/x86/platform/geode/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_ALIX) += alix.o diff --git a/arch/x86/platform/geode/alix.c b/arch/x86/platform/geode/alix.c new file mode 100644 index 000000000000..ca1973699d3d --- /dev/null +++ b/arch/x86/platform/geode/alix.c @@ -0,0 +1,142 @@ +/* + * System Specific setup for PCEngines ALIX. + * At the moment this means setup of GPIO control of LEDs + * on Alix.2/3/6 boards. + * + * + * Copyright (C) 2008 Constantin Baranov <const@mimas.ru> + * Copyright (C) 2011 Ed Wildgoose <kernel@wildgooses.com> + * + * TODO: There are large similarities with leds-net5501.c + * by Alessandro Zummo <a.zummo@towertech.it> + * In the future leds-net5501.c should be migrated over to platform + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/string.h> +#include <linux/module.h> +#include <linux/leds.h> +#include <linux/platform_device.h> +#include <linux/gpio.h> + +#include <asm/geode.h> + +static int force = 0; +module_param(force, bool, 0444); +/* FIXME: Award bios is not automatically detected as Alix platform */ +MODULE_PARM_DESC(force, "Force detection as ALIX.2/ALIX.3 platform"); + +static struct gpio_led alix_leds[] = { + { + .name = "alix:1", + .gpio = 6, + .default_trigger = "default-on", + .active_low = 1, + }, + { + .name = "alix:2", + .gpio = 25, + .default_trigger = "default-off", + .active_low = 1, + }, + { + .name = "alix:3", + .gpio = 27, + .default_trigger = "default-off", + .active_low = 1, + }, +}; + +static struct gpio_led_platform_data alix_leds_data = { + .num_leds = ARRAY_SIZE(alix_leds), + .leds = alix_leds, +}; + +static struct platform_device alix_leds_dev = { + .name = "leds-gpio", + .id = -1, + .dev.platform_data = &alix_leds_data, +}; + +static void __init register_alix(void) +{ + /* Setup LED control through leds-gpio driver */ + platform_device_register(&alix_leds_dev); +} + +static int __init alix_present(unsigned long bios_phys, + const char *alix_sig, + size_t alix_sig_len) +{ + const size_t bios_len = 0x00010000; + const char *bios_virt; + const char *scan_end; + const char *p; + char name[64]; + + if (force) { + printk(KERN_NOTICE "%s: forced to skip BIOS test, " + "assume system is ALIX.2/ALIX.3\n", + KBUILD_MODNAME); + return 1; + } + + bios_virt = phys_to_virt(bios_phys); + scan_end = bios_virt + bios_len - (alix_sig_len + 2); + for (p = bios_virt; p < scan_end; p++) { + const char *tail; + char *a; + + if (memcmp(p, alix_sig, alix_sig_len) != 0) + continue; + + memcpy(name, p, sizeof(name)); + + /* remove the first \0 character from string */ + a = strchr(name, '\0'); + if (a) + *a = ' '; + + /* cut the string at a newline */ + a = strchr(name, '\r'); + if (a) + *a = '\0'; + + tail = p + alix_sig_len; + if ((tail[0] == '2' || tail[0] == '3')) { + printk(KERN_INFO + "%s: system is recognized as \"%s\"\n", + KBUILD_MODNAME, name); + return 1; + } + } + + return 0; +} + +static int __init alix_init(void) +{ + const char tinybios_sig[] = "PC Engines ALIX."; + const char coreboot_sig[] = "PC Engines\0ALIX."; + + if (!is_geode()) + return 0; + + if (alix_present(0xf0000, tinybios_sig, sizeof(tinybios_sig) - 1) || + alix_present(0x500, coreboot_sig, sizeof(coreboot_sig) - 1)) + register_alix(); + + return 0; +} + +module_init(alix_init); + +MODULE_AUTHOR("Ed Wildgoose <kernel@wildgooses.com>"); +MODULE_DESCRIPTION("PCEngines ALIX System Setup"); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index 58425adc22c6..e6379526675b 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -14,6 +14,8 @@ #include <linux/init.h> #include <linux/kernel.h> +#include <linux/interrupt.h> +#include <linux/scatterlist.h> #include <linux/sfi.h> #include <linux/intel_pmic_gpio.h> #include <linux/spi/spi.h> @@ -392,6 +394,7 @@ static void __init *max3111_platform_data(void *info) struct spi_board_info *spi_info = info; int intr = get_gpio_by_name("max3111_int"); + spi_info->mode = SPI_MODE_0; if (intr == -1) return NULL; spi_info->irq = intr + MRST_IRQ_OFFSET; @@ -678,38 +681,40 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) pentry = (struct sfi_device_table_entry *)sb->pentry; for (i = 0; i < num; i++, pentry++) { - if (pentry->irq != (u8)0xff) { /* native RTE case */ + int irq = pentry->irq; + + if (irq != (u8)0xff) { /* native RTE case */ /* these SPI2 devices are not exposed to system as PCI * devices, but they have separate RTE entry in IOAPIC * so we have to enable them one by one here */ - ioapic = mp_find_ioapic(pentry->irq); + ioapic = mp_find_ioapic(irq); irq_attr.ioapic = ioapic; - irq_attr.ioapic_pin = pentry->irq; + irq_attr.ioapic_pin = irq; irq_attr.trigger = 1; irq_attr.polarity = 1; - io_apic_set_pci_routing(NULL, pentry->irq, &irq_attr); + io_apic_set_pci_routing(NULL, irq, &irq_attr); } else - pentry->irq = 0; /* No irq */ + irq = 0; /* No irq */ switch (pentry->type) { case SFI_DEV_TYPE_IPC: /* ID as IRQ is a hack that will go away */ - pdev = platform_device_alloc(pentry->name, pentry->irq); + pdev = platform_device_alloc(pentry->name, irq); if (pdev == NULL) { pr_err("out of memory for SFI platform device '%s'.\n", pentry->name); continue; } - install_irq_resource(pdev, pentry->irq); + install_irq_resource(pdev, irq); pr_debug("info[%2d]: IPC bus, name = %16.16s, " - "irq = 0x%2x\n", i, pentry->name, pentry->irq); + "irq = 0x%2x\n", i, pentry->name, irq); sfi_handle_ipc_dev(pdev); break; case SFI_DEV_TYPE_SPI: memset(&spi_info, 0, sizeof(spi_info)); strncpy(spi_info.modalias, pentry->name, SFI_NAME_LEN); - spi_info.irq = pentry->irq; + spi_info.irq = irq; spi_info.bus_num = pentry->host_num; spi_info.chip_select = pentry->addr; spi_info.max_speed_hz = pentry->max_freq; @@ -726,7 +731,7 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) memset(&i2c_info, 0, sizeof(i2c_info)); bus = pentry->host_num; strncpy(i2c_info.type, pentry->name, SFI_NAME_LEN); - i2c_info.irq = pentry->irq; + i2c_info.irq = irq; i2c_info.addr = pentry->addr; pr_debug("info[%2d]: I2C bus = %d, name = %16.16s, " "irq = 0x%2x, addr = 0x%x\n", i, bus, diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index db8b915f54bc..5b552198f774 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -115,9 +115,6 @@ early_param("nobau", setup_nobau); /* base pnode in this partition */ static int uv_base_pnode __read_mostly; -/* position of pnode (which is nasid>>1): */ -static int uv_nshift __read_mostly; -static unsigned long uv_mmask __read_mostly; static DEFINE_PER_CPU(struct ptc_stats, ptcstats); static DEFINE_PER_CPU(struct bau_control, bau_control); @@ -1435,7 +1432,7 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) { int i; int cpu; - unsigned long pa; + unsigned long gpa; unsigned long m; unsigned long n; size_t dsize; @@ -1451,9 +1448,9 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) bau_desc = kmalloc_node(dsize, GFP_KERNEL, node); BUG_ON(!bau_desc); - pa = uv_gpa(bau_desc); /* need the real nasid*/ - n = pa >> uv_nshift; - m = pa & uv_mmask; + gpa = uv_gpa(bau_desc); + n = uv_gpa_to_gnode(gpa); + m = uv_gpa_to_offset(gpa); /* the 14-bit pnode */ write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m)); @@ -1525,9 +1522,9 @@ static void pq_init(int node, int pnode) bcp->queue_last = pqp + (DEST_Q_SIZE - 1); } /* - * need the pnode of where the memory was really allocated + * need the gnode of where the memory was really allocated */ - pn = uv_gpa(pqp) >> uv_nshift; + pn = uv_gpa_to_gnode(uv_gpa(pqp)); first = uv_physnodeaddr(pqp); pn_first = ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | first; last = uv_physnodeaddr(pqp + (DEST_Q_SIZE - 1)); @@ -1837,8 +1834,6 @@ static int __init uv_bau_init(void) zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu)); } - uv_nshift = uv_hub_info->m_val; - uv_mmask = (1UL << uv_hub_info->m_val) - 1; nuvhubs = uv_num_possible_blades(); spin_lock_init(&disable_lock); congested_cycles = usec_2_cycles(congested_respns_us); diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 316fbca3490e..153407c35b75 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -89,6 +89,15 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) addr = start + (offset << PAGE_SHIFT); if (addr >= end) addr = end; + + /* + * page-align it here so that get_unmapped_area doesn't + * align it wrongfully again to the next page. addr can come in 4K + * unaligned here as a result of stack start randomization. + */ + addr = PAGE_ALIGN(addr); + addr = align_addr(addr, NULL, ALIGN_VDSO); + return addr; } diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 5cc821cb2e09..26c731a106af 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -25,8 +25,7 @@ config XEN_PRIVILEGED_GUEST config XEN_PVHVM def_bool y - depends on XEN - depends on X86_LOCAL_APIC + depends on XEN && PCI && X86_LOCAL_APIC config XEN_MAX_DOMAIN_MEMORY int @@ -49,11 +48,3 @@ config XEN_DEBUG_FS help Enable statistics output and various tuning options in debugfs. Enabling this option may incur a significant performance overhead. - -config XEN_DEBUG - bool "Enable Xen debug checks" - depends on XEN - default n - help - Enable various WARN_ON checks in the Xen MMU code. - Enabling this option WILL incur a significant performance overhead. diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 2d69617950f7..da8afd576a6b 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -251,6 +251,7 @@ static void __init xen_init_cpuid_mask(void) ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ (1 << X86_FEATURE_ACPI)); /* disable ACPI */ ax = 1; + cx = 0; xen_cpuid(&ax, &bx, &cx, &dx); xsave_mask = diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3dd53f997b11..87f6673b1207 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -495,41 +495,6 @@ static pte_t xen_make_pte(pteval_t pte) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte); -#ifdef CONFIG_XEN_DEBUG -pte_t xen_make_pte_debug(pteval_t pte) -{ - phys_addr_t addr = (pte & PTE_PFN_MASK); - phys_addr_t other_addr; - bool io_page = false; - pte_t _pte; - - if (pte & _PAGE_IOMAP) - io_page = true; - - _pte = xen_make_pte(pte); - - if (!addr) - return _pte; - - if (io_page && - (xen_initial_domain() || addr >= ISA_END_ADDRESS)) { - other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT; - WARN_ONCE(addr != other_addr, - "0x%lx is using VM_IO, but it is 0x%lx!\n", - (unsigned long)addr, (unsigned long)other_addr); - } else { - pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP; - other_addr = (_pte.pte & PTE_PFN_MASK); - WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set), - "0x%lx is missing VM_IO (and wasn't fixed)!\n", - (unsigned long)addr); - } - - return _pte; -} -PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug); -#endif - static pgd_t xen_make_pgd(pgdval_t pgd) { pgd = pte_pfn_to_mfn(pgd); @@ -1992,9 +1957,6 @@ void __init xen_ident_map_ISA(void) static void __init xen_post_allocator_init(void) { -#ifdef CONFIG_XEN_DEBUG - pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug); -#endif pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; pv_mmu_ops.set_pud = xen_set_pud; @@ -2404,17 +2366,3 @@ out: return err; } EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range); - -#ifdef CONFIG_XEN_DEBUG_FS -static int p2m_dump_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, p2m_dump_show, NULL); -} - -static const struct file_operations p2m_dump_fops = { - .open = p2m_dump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; -#endif /* CONFIG_XEN_DEBUG_FS */ diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 58efeb9d5440..1b267e75158d 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -161,7 +161,9 @@ #include <asm/xen/page.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> +#include <xen/grant_table.h> +#include "multicalls.h" #include "xen-ops.h" static void __init m2p_override_init(void); @@ -676,7 +678,8 @@ static unsigned long mfn_hash(unsigned long mfn) } /* Add an MFN override for a particular page */ -int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte) +int m2p_add_override(unsigned long mfn, struct page *page, + struct gnttab_map_grant_ref *kmap_op) { unsigned long flags; unsigned long pfn; @@ -692,16 +695,28 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte) "m2p_add_override: pfn %lx not mapped", pfn)) return -EINVAL; } - - page->private = mfn; + WARN_ON(PagePrivate(page)); + SetPagePrivate(page); + set_page_private(page, mfn); page->index = pfn_to_mfn(pfn); if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) return -ENOMEM; - if (clear_pte && !PageHighMem(page)) - /* Just zap old mapping for now */ - pte_clear(&init_mm, address, ptep); + if (kmap_op != NULL) { + if (!PageHighMem(page)) { + struct multicall_space mcs = + xen_mc_entry(sizeof(*kmap_op)); + + MULTI_grant_table_op(mcs.mc, + GNTTABOP_map_grant_ref, kmap_op, 1); + + xen_mc_issue(PARAVIRT_LAZY_MMU); + } + /* let's use dev_bus_addr to record the old mfn instead */ + kmap_op->dev_bus_addr = page->index; + page->index = (unsigned long) kmap_op; + } spin_lock_irqsave(&m2p_override_lock, flags); list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]); spin_unlock_irqrestore(&m2p_override_lock, flags); @@ -735,13 +750,56 @@ int m2p_remove_override(struct page *page, bool clear_pte) spin_lock_irqsave(&m2p_override_lock, flags); list_del(&page->lru); spin_unlock_irqrestore(&m2p_override_lock, flags); - set_phys_to_machine(pfn, page->index); + WARN_ON(!PagePrivate(page)); + ClearPagePrivate(page); - if (clear_pte && !PageHighMem(page)) - set_pte_at(&init_mm, address, ptep, - pfn_pte(pfn, PAGE_KERNEL)); - /* No tlb flush necessary because the caller already - * left the pte unmapped. */ + if (clear_pte) { + struct gnttab_map_grant_ref *map_op = + (struct gnttab_map_grant_ref *) page->index; + set_phys_to_machine(pfn, map_op->dev_bus_addr); + if (!PageHighMem(page)) { + struct multicall_space mcs; + struct gnttab_unmap_grant_ref *unmap_op; + + /* + * It might be that we queued all the m2p grant table + * hypercalls in a multicall, then m2p_remove_override + * get called before the multicall has actually been + * issued. In this case handle is going to -1 because + * it hasn't been modified yet. + */ + if (map_op->handle == -1) + xen_mc_flush(); + /* + * Now if map_op->handle is negative it means that the + * hypercall actually returned an error. + */ + if (map_op->handle == GNTST_general_error) { + printk(KERN_WARNING "m2p_remove_override: " + "pfn %lx mfn %lx, failed to modify kernel mappings", + pfn, mfn); + return -1; + } + + mcs = xen_mc_entry( + sizeof(struct gnttab_unmap_grant_ref)); + unmap_op = mcs.args; + unmap_op->host_addr = map_op->host_addr; + unmap_op->handle = map_op->handle; + unmap_op->dev_bus_addr = 0; + + MULTI_grant_table_op(mcs.mc, + GNTTABOP_unmap_grant_ref, unmap_op, 1); + + xen_mc_issue(PARAVIRT_LAZY_MMU); + + set_pte_at(&init_mm, address, ptep, + pfn_pte(pfn, PAGE_KERNEL)); + __flush_tlb_single(address); + map_op->host_addr = 0; + } + } else + set_phys_to_machine(pfn, page->index); return 0; } @@ -758,7 +816,7 @@ struct page *m2p_find_override(unsigned long mfn) spin_lock_irqsave(&m2p_override_lock, flags); list_for_each_entry(p, bucket, lru) { - if (p->private == mfn) { + if (page_private(p) == mfn) { ret = p; break; } @@ -782,17 +840,21 @@ unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn) EXPORT_SYMBOL_GPL(m2p_find_override_pfn); #ifdef CONFIG_XEN_DEBUG_FS - -int p2m_dump_show(struct seq_file *m, void *v) +#include <linux/debugfs.h> +#include "debugfs.h" +static int p2m_dump_show(struct seq_file *m, void *v) { static const char * const level_name[] = { "top", "middle", - "entry", "abnormal" }; - static const char * const type_name[] = { "identity", "missing", - "pfn", "abnormal"}; + "entry", "abnormal", "error"}; #define TYPE_IDENTITY 0 #define TYPE_MISSING 1 #define TYPE_PFN 2 #define TYPE_UNKNOWN 3 + static const char * const type_name[] = { + [TYPE_IDENTITY] = "identity", + [TYPE_MISSING] = "missing", + [TYPE_PFN] = "pfn", + [TYPE_UNKNOWN] = "abnormal"}; unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0; unsigned int uninitialized_var(prev_level); unsigned int uninitialized_var(prev_type); @@ -856,4 +918,32 @@ int p2m_dump_show(struct seq_file *m, void *v) #undef TYPE_PFN #undef TYPE_UNKNOWN } -#endif + +static int p2m_dump_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, p2m_dump_show, NULL); +} + +static const struct file_operations p2m_dump_fops = { + .open = p2m_dump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *d_mmu_debug; + +static int __init xen_p2m_debugfs(void) +{ + struct dentry *d_xen = xen_init_debugfs(); + + if (d_xen == NULL) + return -ENOMEM; + + d_mmu_debug = debugfs_create_dir("mmu", d_xen); + + debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops); + return 0; +} +fs_initcall(xen_p2m_debugfs); +#endif /* CONFIG_XEN_DEBUG_FS */ diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 46d6d21dbdbe..38d0af4fefec 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -37,7 +37,10 @@ extern void xen_syscall_target(void); extern void xen_syscall32_target(void); /* Amount of extra memory space we add to the e820 ranges */ -phys_addr_t xen_extra_mem_start, xen_extra_mem_size; +struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; + +/* Number of pages released from the initial allocation. */ +unsigned long xen_released_pages; /* * The maximum amount of extra memory compared to the base size. The @@ -51,48 +54,47 @@ phys_addr_t xen_extra_mem_start, xen_extra_mem_size; */ #define EXTRA_MEM_RATIO (10) -static void __init xen_add_extra_mem(unsigned long pages) +static void __init xen_add_extra_mem(u64 start, u64 size) { unsigned long pfn; + int i; - u64 size = (u64)pages * PAGE_SIZE; - u64 extra_start = xen_extra_mem_start + xen_extra_mem_size; - - if (!pages) - return; - - e820_add_region(extra_start, size, E820_RAM); - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); - - memblock_x86_reserve_range(extra_start, extra_start + size, "XEN EXTRA"); + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + /* Add new region. */ + if (xen_extra_mem[i].size == 0) { + xen_extra_mem[i].start = start; + xen_extra_mem[i].size = size; + break; + } + /* Append to existing region. */ + if (xen_extra_mem[i].start + xen_extra_mem[i].size == start) { + xen_extra_mem[i].size += size; + break; + } + } + if (i == XEN_EXTRA_MEM_MAX_REGIONS) + printk(KERN_WARNING "Warning: not enough extra memory regions\n"); - xen_extra_mem_size += size; + memblock_x86_reserve_range(start, start + size, "XEN EXTRA"); - xen_max_p2m_pfn = PFN_DOWN(extra_start + size); + xen_max_p2m_pfn = PFN_DOWN(start + size); - for (pfn = PFN_DOWN(extra_start); pfn <= xen_max_p2m_pfn; pfn++) + for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++) __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } -static unsigned long __init xen_release_chunk(phys_addr_t start_addr, - phys_addr_t end_addr) +static unsigned long __init xen_release_chunk(unsigned long start, + unsigned long end) { struct xen_memory_reservation reservation = { .address_bits = 0, .extent_order = 0, .domid = DOMID_SELF }; - unsigned long start, end; unsigned long len = 0; unsigned long pfn; int ret; - start = PFN_UP(start_addr); - end = PFN_DOWN(end_addr); - - if (end <= start) - return 0; - for(pfn = start; pfn < end; pfn++) { unsigned long mfn = pfn_to_mfn(pfn); @@ -117,72 +119,52 @@ static unsigned long __init xen_release_chunk(phys_addr_t start_addr, return len; } -static unsigned long __init xen_return_unused_memory(unsigned long max_pfn, - const struct e820map *e820) +static unsigned long __init xen_set_identity_and_release( + const struct e820entry *list, size_t map_size, unsigned long nr_pages) { - phys_addr_t max_addr = PFN_PHYS(max_pfn); - phys_addr_t last_end = ISA_END_ADDRESS; + phys_addr_t start = 0; unsigned long released = 0; - int i; - - /* Free any unused memory above the low 1Mbyte. */ - for (i = 0; i < e820->nr_map && last_end < max_addr; i++) { - phys_addr_t end = e820->map[i].addr; - end = min(max_addr, end); - - if (last_end < end) - released += xen_release_chunk(last_end, end); - last_end = max(last_end, e820->map[i].addr + e820->map[i].size); - } - - if (last_end < max_addr) - released += xen_release_chunk(last_end, max_addr); - - printk(KERN_INFO "released %lu pages of unused memory\n", released); - return released; -} - -static unsigned long __init xen_set_identity(const struct e820entry *list, - ssize_t map_size) -{ - phys_addr_t last = xen_initial_domain() ? 0 : ISA_END_ADDRESS; - phys_addr_t start_pci = last; - const struct e820entry *entry; unsigned long identity = 0; + const struct e820entry *entry; int i; + /* + * Combine non-RAM regions and gaps until a RAM region (or the + * end of the map) is reached, then set the 1:1 map and + * release the pages (if available) in those non-RAM regions. + * + * The combined non-RAM regions are rounded to a whole number + * of pages so any partial pages are accessible via the 1:1 + * mapping. This is needed for some BIOSes that put (for + * example) the DMI tables in a reserved region that begins on + * a non-page boundary. + */ for (i = 0, entry = list; i < map_size; i++, entry++) { - phys_addr_t start = entry->addr; - phys_addr_t end = start + entry->size; + phys_addr_t end = entry->addr + entry->size; - if (start < last) - start = last; + if (entry->type == E820_RAM || i == map_size - 1) { + unsigned long start_pfn = PFN_DOWN(start); + unsigned long end_pfn = PFN_UP(end); - if (end <= start) - continue; + if (entry->type == E820_RAM) + end_pfn = PFN_UP(entry->addr); - /* Skip over the 1MB region. */ - if (last > end) - continue; + if (start_pfn < end_pfn) { + if (start_pfn < nr_pages) + released += xen_release_chunk( + start_pfn, min(end_pfn, nr_pages)); - if ((entry->type == E820_RAM) || (entry->type == E820_UNUSABLE)) { - if (start > start_pci) identity += set_phys_range_identity( - PFN_UP(start_pci), PFN_DOWN(start)); - - /* Without saving 'last' we would gooble RAM too - * at the end of the loop. */ - last = end; - start_pci = end; - continue; + start_pfn, end_pfn); + } + start = end; } - start_pci = min(start, start_pci); - last = end; } - if (last > start_pci) - identity += set_phys_range_identity( - PFN_UP(start_pci), PFN_DOWN(last)); - return identity; + + printk(KERN_INFO "Released %lu pages of unused memory\n", released); + printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity); + + return released; } static unsigned long __init xen_get_max_pages(void) @@ -197,21 +179,32 @@ static unsigned long __init xen_get_max_pages(void) return min(max_pages, MAX_DOMAIN_PAGES); } +static void xen_align_and_add_e820_region(u64 start, u64 size, int type) +{ + u64 end = start + size; + + /* Align RAM regions to page boundaries. */ + if (type == E820_RAM) { + start = PAGE_ALIGN(start); + end &= ~((u64)PAGE_SIZE - 1); + } + + e820_add_region(start, end - start, type); +} + /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ char * __init xen_memory_setup(void) { static struct e820entry map[E820MAX] __initdata; - static struct e820entry map_raw[E820MAX] __initdata; unsigned long max_pfn = xen_start_info->nr_pages; unsigned long long mem_end; int rc; struct xen_memory_map memmap; + unsigned long max_pages; unsigned long extra_pages = 0; - unsigned long extra_limit; - unsigned long identity_pages = 0; int i; int op; @@ -237,58 +230,65 @@ char * __init xen_memory_setup(void) } BUG_ON(rc); - memcpy(map_raw, map, sizeof(map)); - e820.nr_map = 0; - xen_extra_mem_start = mem_end; - for (i = 0; i < memmap.nr_entries; i++) { - unsigned long long end; - - /* Guard against non-page aligned E820 entries. */ - if (map[i].type == E820_RAM) - map[i].size -= (map[i].size + map[i].addr) % PAGE_SIZE; - - end = map[i].addr + map[i].size; - if (map[i].type == E820_RAM && end > mem_end) { - /* RAM off the end - may be partially included */ - u64 delta = min(map[i].size, end - mem_end); - - map[i].size -= delta; - end -= delta; - - extra_pages += PFN_DOWN(delta); - /* - * Set RAM below 4GB that is not for us to be unusable. - * This prevents "System RAM" address space from being - * used as potential resource for I/O address (happens - * when 'allocate_resource' is called). - */ - if (delta && - (xen_initial_domain() && end < 0x100000000ULL)) - e820_add_region(end, delta, E820_UNUSABLE); + /* Make sure the Xen-supplied memory map is well-ordered. */ + sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries); + + max_pages = xen_get_max_pages(); + if (max_pages > max_pfn) + extra_pages += max_pages - max_pfn; + + /* + * Set P2M for all non-RAM pages and E820 gaps to be identity + * type PFNs. Any RAM pages that would be made inaccesible by + * this are first released. + */ + xen_released_pages = xen_set_identity_and_release( + map, memmap.nr_entries, max_pfn); + extra_pages += xen_released_pages; + + /* + * Clamp the amount of extra memory to a EXTRA_MEM_RATIO + * factor the base size. On non-highmem systems, the base + * size is the full initial memory allocation; on highmem it + * is limited to the max size of lowmem, so that it doesn't + * get completely filled. + * + * In principle there could be a problem in lowmem systems if + * the initial memory is also very large with respect to + * lowmem, but we won't try to deal with that here. + */ + extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), + extra_pages); + + i = 0; + while (i < memmap.nr_entries) { + u64 addr = map[i].addr; + u64 size = map[i].size; + u32 type = map[i].type; + + if (type == E820_RAM) { + if (addr < mem_end) { + size = min(size, mem_end - addr); + } else if (extra_pages) { + size = min(size, (u64)extra_pages * PAGE_SIZE); + extra_pages -= size / PAGE_SIZE; + xen_add_extra_mem(addr, size); + } else + type = E820_UNUSABLE; } - if (map[i].size > 0 && end > xen_extra_mem_start) - xen_extra_mem_start = end; + xen_align_and_add_e820_region(addr, size, type); - /* Add region if any remains */ - if (map[i].size > 0) - e820_add_region(map[i].addr, map[i].size, map[i].type); + map[i].addr += size; + map[i].size -= size; + if (map[i].size == 0) + i++; } - /* Align the balloon area so that max_low_pfn does not get set - * to be at the _end_ of the PCI gap at the far end (fee01000). - * Note that xen_extra_mem_start gets set in the loop above to be - * past the last E820 region. */ - if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32))) - xen_extra_mem_start = (1ULL<<32); /* * In domU, the ISA region is normal, usable memory, but we * reserve ISA memory anyway because too many things poke * about in there. - * - * In Dom0, the host E820 information can leave gaps in the - * ISA range, which would cause us to release those pages. To - * avoid this, we unconditionally reserve them here. */ e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, E820_RESERVED); @@ -305,44 +305,6 @@ char * __init xen_memory_setup(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); - extra_limit = xen_get_max_pages(); - if (max_pfn + extra_pages > extra_limit) { - if (extra_limit > max_pfn) - extra_pages = extra_limit - max_pfn; - else - extra_pages = 0; - } - - extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820); - - /* - * Clamp the amount of extra memory to a EXTRA_MEM_RATIO - * factor the base size. On non-highmem systems, the base - * size is the full initial memory allocation; on highmem it - * is limited to the max size of lowmem, so that it doesn't - * get completely filled. - * - * In principle there could be a problem in lowmem systems if - * the initial memory is also very large with respect to - * lowmem, but we won't try to deal with that here. - */ - extra_limit = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), - max_pfn + extra_pages); - - if (extra_limit >= max_pfn) - extra_pages = extra_limit - max_pfn; - else - extra_pages = 0; - - xen_add_extra_mem(extra_pages); - - /* - * Set P2M for all non-RAM pages and E820 gaps to be identity - * type PFNs. We supply it with the non-sanitized version - * of the E820. - */ - identity_pages = xen_set_identity(map_raw, memmap.nr_entries); - printk(KERN_INFO "Set %ld page(s) to 1-1 mapping.\n", identity_pages); return "Xen"; } diff --git a/arch/xtensa/configs/iss_defconfig b/arch/xtensa/configs/iss_defconfig index 0234cd198c54..f932b30b47fb 100644 --- a/arch/xtensa/configs/iss_defconfig +++ b/arch/xtensa/configs/iss_defconfig @@ -15,7 +15,6 @@ CONFIG_GENERIC_GPIO=y # CONFIG_ARCH_HAS_ILOG2_U64 is not set CONFIG_NO_IOPORT=y CONFIG_HZ=100 -CONFIG_GENERIC_TIME=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" CONFIG_CONSTRUCTORS=y diff --git a/arch/xtensa/configs/s6105_defconfig b/arch/xtensa/configs/s6105_defconfig index 4891abbf16bc..550e8ed5b5c6 100644 --- a/arch/xtensa/configs/s6105_defconfig +++ b/arch/xtensa/configs/s6105_defconfig @@ -15,7 +15,6 @@ CONFIG_GENERIC_GPIO=y # CONFIG_ARCH_HAS_ILOG2_U64 is not set CONFIG_NO_IOPORT=y CONFIG_HZ=100 -CONFIG_GENERIC_TIME=y CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index f717e20d961b..7dde24456427 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -633,7 +633,7 @@ static const struct net_device_ops iss_netdev_ops = { .ndo_set_mac_address = iss_net_set_mac, //.ndo_do_ioctl = iss_net_ioctl, .ndo_tx_timeout = iss_net_tx_timeout, - .ndo_set_multicast_list = iss_net_set_multicast_list, + .ndo_set_rx_mode = iss_net_set_multicast_list, }; static int iss_net_configure(int index, char *init) |