diff options
| author | Tony Lindgren <tony@atomide.com> | 2017-11-28 08:12:32 -0800 |
|---|---|---|
| committer | Tony Lindgren <tony@atomide.com> | 2017-11-28 08:12:32 -0800 |
| commit | bc686442f8a601bccac1f22506ecdb4b0d62cadd (patch) | |
| tree | b224ab4aa2350b233da640f5850f48bc6bfeb2d0 /arch/x86 | |
| parent | 60636a5d0fa2f8bc6d0c23c4027100ba20866f9b (diff) | |
| parent | ca41e244517d6d3f1600c229ff7ca615049c1e9c (diff) | |
| download | linux-stable-bc686442f8a601bccac1f22506ecdb4b0d62cadd.tar.gz linux-stable-bc686442f8a601bccac1f22506ecdb4b0d62cadd.tar.bz2 linux-stable-bc686442f8a601bccac1f22506ecdb4b0d62cadd.zip | |
Merge branch 'dts-fixes' into omap-for-v4.15/fixes-dt
Diffstat (limited to 'arch/x86')
896 files changed, 9430 insertions, 5949 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 971feac13506..8eed3f94bfc7 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # Select 32 or 64 bit config 64BIT bool "64-bit kernel" if ARCH = "x86" @@ -55,7 +56,7 @@ config X86 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_PMEM_API if X86_64 # Causing hangs/crashes, see the commit that added this change for details. - select ARCH_HAS_REFCOUNT if BROKEN + select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_SET_MEMORY select ARCH_HAS_SG_CHAIN @@ -92,8 +93,10 @@ config X86 select GENERIC_FIND_FIRST_BIT select GENERIC_IOMAP select GENERIC_IRQ_EFFECTIVE_AFF_MASK if SMP + select GENERIC_IRQ_MATRIX_ALLOCATOR if X86_LOCAL_APIC select GENERIC_IRQ_MIGRATION if SMP select GENERIC_IRQ_PROBE + select GENERIC_IRQ_RESERVATION_MODE select GENERIC_IRQ_SHOW select GENERIC_PENDING_IRQ if SMP select GENERIC_SMP_IDLE_THREAD @@ -107,9 +110,8 @@ config X86 select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE select HAVE_ARCH_JUMP_LABEL - select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP + select HAVE_ARCH_KASAN if X86_64 select HAVE_ARCH_KGDB - select HAVE_ARCH_KMEMCHECK select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT select HAVE_ARCH_COMPAT_MMAP_BASES if MMU && COMPAT @@ -170,7 +172,7 @@ config X86 select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_RELIABLE_STACKTRACE if X86_64 && FRAME_POINTER_UNWINDER && STACK_VALIDATION + select HAVE_RELIABLE_STACKTRACE if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION select HAVE_STACK_VALIDATION if X86_64 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UNSTABLE_SCHED_CLOCK @@ -302,7 +304,6 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC config KASAN_SHADOW_OFFSET hex depends on KASAN - default 0xdff8000000000000 if X86_5LEVEL default 0xdffffc0000000000 config HAVE_INTEL_TXT @@ -1428,7 +1429,7 @@ config ARCH_DMA_ADDR_T_64BIT config X86_DIRECT_GBPAGES def_bool y - depends on X86_64 && !DEBUG_PAGEALLOC && !KMEMCHECK + depends on X86_64 && !DEBUG_PAGEALLOC ---help--- Certain kernel features effectively disable kernel linear 1 GB mappings (even if the CPU otherwise @@ -1802,6 +1803,22 @@ config X86_SMAP If unsure, say Y. +config X86_INTEL_UMIP + def_bool y + depends on CPU_SUP_INTEL + prompt "Intel User Mode Instruction Prevention" if EXPERT + ---help--- + The User Mode Instruction Prevention (UMIP) is a security + feature in newer Intel processors. If enabled, a general + protection fault is issued if the SGDT, SLDT, SIDT, SMSW + or STR instructions are executed in user mode. These instructions + unnecessarily expose information about the hardware state. + + The vast majority of applications do not use these instructions. + For the very few that do, software emulation is provided in + specific cases in protected and virtual-8086 modes. Emulated + results are dummy. + config X86_INTEL_MPX prompt "Intel MPX (Memory Protection Extensions)" def_bool n diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 3ba5ff2f2d08..65a9a4716e34 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # Put here option for CPU selection and depending optimization choice prompt "Processor family" diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 71a48a30fc84..6293a8768a91 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 menu "Kernel hacking" config TRACE_IRQFLAGS_SUPPORT @@ -358,28 +359,14 @@ config PUNIT_ATOM_DEBUG choice prompt "Choose kernel unwinder" - default FRAME_POINTER_UNWINDER + default UNWINDER_ORC if X86_64 + default UNWINDER_FRAME_POINTER if X86_32 ---help--- This determines which method will be used for unwinding kernel stack traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack, livepatch, lockdep, and more. -config FRAME_POINTER_UNWINDER - bool "Frame pointer unwinder" - select FRAME_POINTER - ---help--- - This option enables the frame pointer unwinder for unwinding kernel - stack traces. - - The unwinder itself is fast and it uses less RAM than the ORC - unwinder, but the kernel text size will grow by ~3% and the kernel's - overall performance will degrade by roughly 5-10%. - - This option is recommended if you want to use the livepatch - consistency model, as this is currently the only way to get a - reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE). - -config ORC_UNWINDER +config UNWINDER_ORC bool "ORC unwinder" depends on X86_64 select STACK_VALIDATION @@ -395,7 +382,22 @@ config ORC_UNWINDER Enabling this option will increase the kernel's runtime memory usage by roughly 2-4MB, depending on your kernel config. -config GUESS_UNWINDER +config UNWINDER_FRAME_POINTER + bool "Frame pointer unwinder" + select FRAME_POINTER + ---help--- + This option enables the frame pointer unwinder for unwinding kernel + stack traces. + + The unwinder itself is fast and it uses less RAM than the ORC + unwinder, but the kernel text size will grow by ~3% and the kernel's + overall performance will degrade by roughly 5-10%. + + This option is recommended if you want to use the livepatch + consistency model, as this is currently the only way to get a + reliable stack trace (CONFIG_HAVE_RELIABLE_STACKTRACE). + +config UNWINDER_GUESS bool "Guess unwinder" depends on EXPERT ---help--- @@ -410,7 +412,7 @@ config GUESS_UNWINDER endchoice config FRAME_POINTER - depends on !ORC_UNWINDER && !GUESS_UNWINDER + depends on !UNWINDER_ORC && !UNWINDER_GUESS bool endmenu diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 6276572259c8..3e73bc255e4e 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # Unified Makefile for i386 and x86_64 # select defconfig based on actual architecture @@ -157,11 +158,6 @@ ifdef CONFIG_X86_X32 endif export CONFIG_X86_X32_ABI -# Don't unroll struct assignments with kmemcheck enabled -ifeq ($(CONFIG_KMEMCHECK),y) - KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy) -endif - # # If the function graph tracer is used with mcount instead of fentry, # '-maccumulate-outgoing-args' is needed to prevent a GCC bug diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index 5b7e898ffd9a..45af19921ebd 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 core-y += arch/x86/crypto/ ifeq ($(CONFIG_X86_32),y) diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index f3717d36718a..1f5faf8606b4 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # CPU tuning section - shared with UML. # Must change only cflags-y (or [yn]), not CFLAGS! That makes a difference for UML. diff --git a/arch/x86/boot/.gitignore b/arch/x86/boot/.gitignore index e3cf9f682be5..09d25dd09307 100644 --- a/arch/x86/boot/.gitignore +++ b/arch/x86/boot/.gitignore @@ -7,3 +7,6 @@ zoffset.h setup setup.bin setup.elf +fdimage +mtools.conf +image.iso diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index d88a2fddba8c..9b5adae9cc40 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -123,63 +123,26 @@ image_cmdline = default linux $(FDARGS) $(if $(FDINITRD),initrd=initrd.img,) $(obj)/mtools.conf: $(src)/mtools.conf.in sed -e 's|@OBJ@|$(obj)|g' < $< > $@ +quiet_cmd_genimage = GENIMAGE $3 +cmd_genimage = sh $(srctree)/$(src)/genimage.sh $2 $3 $(obj)/bzImage \ + $(obj)/mtools.conf '$(image_cmdline)' $(FDINITRD) + # This requires write access to /dev/fd0 bzdisk: $(obj)/bzImage $(obj)/mtools.conf - MTOOLSRC=$(obj)/mtools.conf mformat a: ; sync - syslinux /dev/fd0 ; sync - echo '$(image_cmdline)' | \ - MTOOLSRC=$(src)/mtools.conf mcopy - a:syslinux.cfg - if [ -f '$(FDINITRD)' ] ; then \ - MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' a:initrd.img ; \ - fi - MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage a:linux ; sync + $(call cmd,genimage,bzdisk,/dev/fd0) # These require being root or having syslinux 2.02 or higher installed fdimage fdimage144: $(obj)/bzImage $(obj)/mtools.conf - dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=1440 - MTOOLSRC=$(obj)/mtools.conf mformat v: ; sync - syslinux $(obj)/fdimage ; sync - echo '$(image_cmdline)' | \ - MTOOLSRC=$(obj)/mtools.conf mcopy - v:syslinux.cfg - if [ -f '$(FDINITRD)' ] ; then \ - MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' v:initrd.img ; \ - fi - MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage v:linux ; sync + $(call cmd,genimage,fdimage144,$(obj)/fdimage) + @$(kecho) 'Kernel: $(obj)/fdimage is ready' fdimage288: $(obj)/bzImage $(obj)/mtools.conf - dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=2880 - MTOOLSRC=$(obj)/mtools.conf mformat w: ; sync - syslinux $(obj)/fdimage ; sync - echo '$(image_cmdline)' | \ - MTOOLSRC=$(obj)/mtools.conf mcopy - w:syslinux.cfg - if [ -f '$(FDINITRD)' ] ; then \ - MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' w:initrd.img ; \ - fi - MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage w:linux ; sync + $(call cmd,genimage,fdimage288,$(obj)/fdimage) + @$(kecho) 'Kernel: $(obj)/fdimage is ready' isoimage: $(obj)/bzImage - -rm -rf $(obj)/isoimage - mkdir $(obj)/isoimage - for i in lib lib64 share end ; do \ - if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \ - cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \ - if [ -f /usr/$$i/syslinux/ldlinux.c32 ]; then \ - cp /usr/$$i/syslinux/ldlinux.c32 $(obj)/isoimage ; \ - fi ; \ - break ; \ - fi ; \ - if [ $$i = end ] ; then exit 1 ; fi ; \ - done - cp $(obj)/bzImage $(obj)/isoimage/linux - echo '$(image_cmdline)' > $(obj)/isoimage/isolinux.cfg - if [ -f '$(FDINITRD)' ] ; then \ - cp '$(FDINITRD)' $(obj)/isoimage/initrd.img ; \ - fi - mkisofs -J -r -o $(obj)/image.iso -b isolinux.bin -c boot.cat \ - -no-emul-boot -boot-load-size 4 -boot-info-table \ - $(obj)/isoimage - isohybrid $(obj)/image.iso 2>/dev/null || true - rm -rf $(obj)/isoimage + $(call cmd,genimage,isoimage,$(obj)/image.iso) + @$(kecho) 'Kernel: $(obj)/image.iso is ready' bzlilo: $(obj)/bzImage if [ -f $(INSTALL_PATH)/vmlinuz ]; then mv $(INSTALL_PATH)/vmlinuz $(INSTALL_PATH)/vmlinuz.old; fi diff --git a/arch/x86/boot/code16gcc.h b/arch/x86/boot/code16gcc.h index 5ff426535397..e19fd7536307 100644 --- a/arch/x86/boot/code16gcc.h +++ b/arch/x86/boot/code16gcc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ # # code16gcc.h # diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 8a958274b54c..1e9c322e973a 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # linux/arch/x86/boot/compressed/Makefile # @@ -35,6 +36,7 @@ KBUILD_CFLAGS += -mno-mmx -mno-sse KBUILD_CFLAGS += $(call cc-option,-ffreestanding) KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector) KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) +KBUILD_CFLAGS += $(call cc-disable-warning, gnu) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n @@ -77,6 +79,7 @@ vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o + vmlinux-objs-y += $(obj)/mem_encrypt.o endif $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index 9dc1ce6ba3c0..0cb325734cfb 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "misc.h" #if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE diff --git a/arch/x86/boot/compressed/cpuflags.c b/arch/x86/boot/compressed/cpuflags.c index aa313466118b..6448a8196d32 100644 --- a/arch/x86/boot/compressed/cpuflags.c +++ b/arch/x86/boot/compressed/cpuflags.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #ifdef CONFIG_RANDOMIZE_BASE #include "../cpuflags.c" diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index c0223f1a89d7..e799dc5c6448 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef BOOT_COMPRESSED_EBOOT_H #define BOOT_COMPRESSED_EBOOT_H diff --git a/arch/x86/boot/compressed/efi_stub_32.S b/arch/x86/boot/compressed/efi_stub_32.S index a53440e81d52..257e341fd2c8 100644 --- a/arch/x86/boot/compressed/efi_stub_32.S +++ b/arch/x86/boot/compressed/efi_stub_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * EFI call stub for IA32. * diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S index 630384a4c14a..bff9ab7c6317 100644 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ b/arch/x86/boot/compressed/efi_thunk_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming * diff --git a/arch/x86/boot/compressed/error.c b/arch/x86/boot/compressed/error.c index 31922023de49..c881878e56d3 100644 --- a/arch/x86/boot/compressed/error.c +++ b/arch/x86/boot/compressed/error.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Callers outside of misc.c need access to the error reporting routines, * but the *_putstr() functions need to stay in misc.c because of how diff --git a/arch/x86/boot/compressed/error.h b/arch/x86/boot/compressed/error.h index d732e608e3af..1de5821184f1 100644 --- a/arch/x86/boot/compressed/error.h +++ b/arch/x86/boot/compressed/error.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef BOOT_COMPRESSED_ERROR_H #define BOOT_COMPRESSED_ERROR_H diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 11c68cf53d4e..37380c0d5999 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * linux/boot/head.S * diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index b4a5d284391c..20919b4f3133 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * linux/boot/head.S * @@ -130,6 +131,19 @@ ENTRY(startup_32) /* * Build early 4G boot pagetable */ + /* + * If SEV is active then set the encryption mask in the page tables. + * This will insure that when the kernel is copied and decompressed + * it will be done so encrypted. + */ + call get_sev_encryption_bit + xorl %edx, %edx + testl %eax, %eax + jz 1f + subl $32, %eax /* Encryption bit is always above bit 31 */ + bts %eax, %edx /* Set encryption mask for page tables */ +1: + /* Initialize Page tables to 0 */ leal pgtable(%ebx), %edi xorl %eax, %eax @@ -140,12 +154,14 @@ ENTRY(startup_32) leal pgtable + 0(%ebx), %edi leal 0x1007 (%edi), %eax movl %eax, 0(%edi) + addl %edx, 4(%edi) /* Build Level 3 */ leal pgtable + 0x1000(%ebx), %edi leal 0x1007(%edi), %eax movl $4, %ecx 1: movl %eax, 0x00(%edi) + addl %edx, 0x04(%edi) addl $0x00001000, %eax addl $8, %edi decl %ecx @@ -156,6 +172,7 @@ ENTRY(startup_32) movl $0x00000183, %eax movl $2048, %ecx 1: movl %eax, 0(%edi) + addl %edx, 4(%edi) addl $0x00200000, %eax addl $8, %edi decl %ecx diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 17818ba6906f..8199a6187251 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kaslr.c * @@ -170,7 +171,6 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size) static void mem_avoid_memmap(char *str) { static int i; - int rc; if (i >= MAX_MEMMAP_REGIONS) return; @@ -218,7 +218,7 @@ static int handle_mem_memmap(void) return 0; tmp_cmdline = malloc(len + 1); - if (!tmp_cmdline ) + if (!tmp_cmdline) error("Failed to allocate space for tmp_cmdline"); memcpy(tmp_cmdline, args, len); @@ -362,7 +362,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, cmd_line |= boot_params->hdr.cmd_line_ptr; /* Calculate size of cmd_line. */ ptr = (char *)(unsigned long)cmd_line; - for (cmd_line_size = 0; ptr[cmd_line_size++]; ) + for (cmd_line_size = 0; ptr[cmd_line_size++];) ; mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line; mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size; diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S new file mode 100644 index 000000000000..54f5f6625a73 --- /dev/null +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -0,0 +1,120 @@ +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2017 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.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/linkage.h> + +#include <asm/processor-flags.h> +#include <asm/msr.h> +#include <asm/asm-offsets.h> + + .text + .code32 +ENTRY(get_sev_encryption_bit) + xor %eax, %eax + +#ifdef CONFIG_AMD_MEM_ENCRYPT + push %ebx + push %ecx + push %edx + push %edi + + /* + * RIP-relative addressing is needed to access the encryption bit + * variable. Since we are running in 32-bit mode we need this call/pop + * sequence to get the proper relative addressing. + */ + call 1f +1: popl %edi + subl $1b, %edi + + movl enc_bit(%edi), %eax + cmpl $0, %eax + jge .Lsev_exit + + /* Check if running under a hypervisor */ + movl $1, %eax + cpuid + bt $31, %ecx /* Check the hypervisor bit */ + jnc .Lno_sev + + movl $0x80000000, %eax /* CPUID to check the highest leaf */ + cpuid + cmpl $0x8000001f, %eax /* See if 0x8000001f is available */ + jb .Lno_sev + + /* + * Check for the SEV feature: + * CPUID Fn8000_001F[EAX] - Bit 1 + * CPUID Fn8000_001F[EBX] - Bits 5:0 + * Pagetable bit position used to indicate encryption + */ + movl $0x8000001f, %eax + cpuid + bt $1, %eax /* Check if SEV is available */ + jnc .Lno_sev + + movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */ + rdmsr + bt $MSR_AMD64_SEV_ENABLED_BIT, %eax /* Check if SEV is active */ + jnc .Lno_sev + + movl %ebx, %eax + andl $0x3f, %eax /* Return the encryption bit location */ + movl %eax, enc_bit(%edi) + jmp .Lsev_exit + +.Lno_sev: + xor %eax, %eax + movl %eax, enc_bit(%edi) + +.Lsev_exit: + pop %edi + pop %edx + pop %ecx + pop %ebx + +#endif /* CONFIG_AMD_MEM_ENCRYPT */ + + ret +ENDPROC(get_sev_encryption_bit) + + .code64 +ENTRY(get_sev_encryption_mask) + xor %rax, %rax + +#ifdef CONFIG_AMD_MEM_ENCRYPT + push %rbp + push %rdx + + movq %rsp, %rbp /* Save current stack pointer */ + + call get_sev_encryption_bit /* Get the encryption bit position */ + testl %eax, %eax + jz .Lno_sev_mask + + xor %rdx, %rdx + bts %rax, %rdx /* Create the encryption mask */ + mov %rdx, %rax /* ... and return it */ + +.Lno_sev_mask: + movq %rbp, %rsp /* Restore original stack pointer */ + + pop %rdx + pop %rbp +#endif + + ret +ENDPROC(get_sev_encryption_mask) + + .data +enc_bit: + .int 0xffffffff diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index c14217cd0155..b50c42455e25 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * misc.c * diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 766a5211f827..9d323dc6b159 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef BOOT_COMPRESSED_MISC_H #define BOOT_COMPRESSED_MISC_H @@ -108,4 +109,6 @@ static inline void console_init(void) { } #endif +unsigned long get_sev_encryption_mask(void); + #endif diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c index f1aa43854bed..d5364ca2e3f9 100644 --- a/arch/x86/boot/compressed/pagetable.c +++ b/arch/x86/boot/compressed/pagetable.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This code is used on x86_64 to create page table identity mappings on * demand by building up a new set of page tables (or appending to the @@ -76,16 +77,18 @@ static unsigned long top_level_pgt; * Mapping information structure passed to kernel_ident_mapping_init(). * Due to relocation, pointers must be assigned at run time not build time. */ -static struct x86_mapping_info mapping_info = { - .page_flag = __PAGE_KERNEL_LARGE_EXEC, -}; +static struct x86_mapping_info mapping_info; /* Locates and clears a region for a new top level page table. */ void initialize_identity_maps(void) { + unsigned long sev_me_mask = get_sev_encryption_mask(); + /* Init mapping_info with run-time function/buffer pointers. */ mapping_info.alloc_pgt_page = alloc_pgt_page; mapping_info.context = &pgt_data; + mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sev_me_mask; + mapping_info.kernpg_flag = _KERNPG_TABLE | sev_me_mask; /* * It should be impossible for this not to already be true, diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c index cea140ce6b42..19dbbcdd1a53 100644 --- a/arch/x86/boot/compressed/string.c +++ b/arch/x86/boot/compressed/string.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This provides an optimized implementation of memcpy, and a simplified * implementation of memset and memmove. These are used here because the diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index e24e0a0c90c9..f491bbde8493 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <asm-generic/vmlinux.lds.h> OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT) diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index 9e77c23c2422..a0b75f73dc63 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include "bitops.h" diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h index 15ad56a3f905..2e20814d3ce3 100644 --- a/arch/x86/boot/cpuflags.h +++ b/arch/x86/boot/cpuflags.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef BOOT_CPUFLAGS_H #define BOOT_CPUFLAGS_H diff --git a/arch/x86/boot/ctype.h b/arch/x86/boot/ctype.h index 020f137df7a2..8f5ef2994b5e 100644 --- a/arch/x86/boot/ctype.h +++ b/arch/x86/boot/ctype.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef BOOT_CTYPE_H #define BOOT_CTYPE_H diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c index f0b8d6d93164..b25c53527a94 100644 --- a/arch/x86/boot/early_serial_console.c +++ b/arch/x86/boot/early_serial_console.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Serial port routines for use during early boot reporting. This code is * included from both the compressed kernel and the regular kernel. diff --git a/arch/x86/boot/genimage.sh b/arch/x86/boot/genimage.sh new file mode 100644 index 000000000000..49f4970f693b --- /dev/null +++ b/arch/x86/boot/genimage.sh @@ -0,0 +1,124 @@ +#!/bin/sh +# +# 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) 2017 by Changbin Du <changbin.du@intel.com> +# +# Adapted from code in arch/x86/boot/Makefile by H. Peter Anvin and others +# +# "make fdimage/fdimage144/fdimage288/isoimage" script for x86 architecture +# +# Arguments: +# $1 - fdimage format +# $2 - target image file +# $3 - kernel bzImage file +# $4 - mtool configuration file +# $5 - kernel cmdline +# $6 - inird image file +# + +# Use "make V=1" to debug this script +case "${KBUILD_VERBOSE}" in +*1*) + set -x + ;; +esac + +verify () { + if [ ! -f "$1" ]; then + echo "" 1>&2 + echo " *** Missing file: $1" 1>&2 + echo "" 1>&2 + exit 1 + fi +} + + +export MTOOLSRC=$4 +FIMAGE=$2 +FBZIMAGE=$3 +KCMDLINE=$5 +FDINITRD=$6 + +# Make sure the files actually exist +verify "$FBZIMAGE" +verify "$MTOOLSRC" + +genbzdisk() { + mformat a: + syslinux $FIMAGE + echo "$KCMDLINE" | mcopy - a:syslinux.cfg + if [ -f "$FDINITRD" ] ; then + mcopy "$FDINITRD" a:initrd.img + fi + mcopy $FBZIMAGE a:linux +} + +genfdimage144() { + dd if=/dev/zero of=$FIMAGE bs=1024 count=1440 2> /dev/null + mformat v: + syslinux $FIMAGE + echo "$KCMDLINE" | mcopy - v:syslinux.cfg + if [ -f "$FDINITRD" ] ; then + mcopy "$FDINITRD" v:initrd.img + fi + mcopy $FBZIMAGE v:linux +} + +genfdimage288() { + dd if=/dev/zero of=$FIMAGE bs=1024 count=2880 2> /dev/null + mformat w: + syslinux $FIMAGE + echo "$KCMDLINE" | mcopy - W:syslinux.cfg + if [ -f "$FDINITRD" ] ; then + mcopy "$FDINITRD" w:initrd.img + fi + mcopy $FBZIMAGE w:linux +} + +genisoimage() { + tmp_dir=`dirname $FIMAGE`/isoimage + rm -rf $tmp_dir + mkdir $tmp_dir + for i in lib lib64 share end ; do + for j in syslinux ISOLINUX ; do + if [ -f /usr/$i/$j/isolinux.bin ] ; then + isolinux=/usr/$i/$j/isolinux.bin + cp $isolinux $tmp_dir + fi + done + for j in syslinux syslinux/modules/bios ; do + if [ -f /usr/$i/$j/ldlinux.c32 ]; then + ldlinux=/usr/$i/$j/ldlinux.c32 + cp $ldlinux $tmp_dir + fi + done + if [ -n "$isolinux" -a -n "$ldlinux" ] ; then + break + fi + if [ $i = end -a -z "$isolinux" ] ; then + echo 'Need an isolinux.bin file, please install syslinux/isolinux.' + exit 1 + fi + done + cp $FBZIMAGE $tmp_dir/linux + echo "$KCMDLINE" > $tmp_dir/isolinux.cfg + if [ -f "$FDINITRD" ] ; then + cp "$FDINITRD" $tmp_dir/initrd.img + fi + mkisofs -J -r -input-charset=utf-8 -quiet -o $FIMAGE -b isolinux.bin \ + -c boot.cat -no-emul-boot -boot-load-size 4 -boot-info-table \ + $tmp_dir + isohybrid $FIMAGE 2>/dev/null || true + rm -rf $tmp_dir +} + +case $1 in + bzdisk) genbzdisk;; + fdimage144) genfdimage144;; + fdimage288) genfdimage288;; + isoimage) genisoimage;; + *) echo 'Unknown image format'; exit 1; +esac diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 1bb08ecffd24..850b8762e889 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * header.S * @@ -16,7 +17,6 @@ */ #include <asm/segment.h> -#include <generated/utsrelease.h> #include <asm/boot.h> #include <asm/page_types.h> #include <asm/setup.h> diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index f274a50db5fa..3d78e27077f4 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef BOOT_STRING_H #define BOOT_STRING_H diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 0702d2531bc7..d4e6cd4577e5 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1997 Martin Mares diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c index 45bc9402aa49..a14c5178d4ba 100644 --- a/arch/x86/boot/video-vga.c +++ b/arch/x86/boot/video-vga.c @@ -241,9 +241,9 @@ static int vga_probe(void) vga_modes, }; static int mode_count[] = { - sizeof(cga_modes)/sizeof(struct mode_info), - sizeof(ega_modes)/sizeof(struct mode_info), - sizeof(vga_modes)/sizeof(struct mode_info), + ARRAY_SIZE(cga_modes), + ARRAY_SIZE(ega_modes), + ARRAY_SIZE(vga_modes), }; struct biosregs ireg, oreg; diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config index 550cd5012b73..66c9e2aab16c 100644 --- a/arch/x86/configs/tiny.config +++ b/arch/x86/configs/tiny.config @@ -1,5 +1,5 @@ CONFIG_NOHIGHMEM=y # CONFIG_HIGHMEM4G is not set # CONFIG_HIGHMEM64G is not set -CONFIG_GUESS_UNWINDER=y -# CONFIG_FRAME_POINTER_UNWINDER is not set +CONFIG_UNWINDER_GUESS=y +# CONFIG_UNWINDER_FRAME_POINTER is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 4a4b16e56d35..e32fc1f274d8 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -299,6 +299,7 @@ CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_DEBUG_RODATA_TEST is not set CONFIG_DEBUG_BOOT_PARAMS=y CONFIG_OPTIMIZE_INLINING=y +CONFIG_UNWINDER_ORC=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 9e32d40d71bd..5f07333bb224 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Arch-specific CryptoAPI modules. # diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 5c15d6b57329..3bf3dcf29825 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -28,6 +28,7 @@ #include <crypto/cryptd.h> #include <crypto/ctr.h> #include <crypto/b128ops.h> +#include <crypto/gcm.h> #include <crypto/xts.h> #include <asm/cpu_device_id.h> #include <asm/fpu/api.h> @@ -1067,9 +1068,10 @@ static struct skcipher_alg aesni_skciphers[] = { } }; +static struct simd_skcipher_alg *aesni_simd_skciphers[ARRAY_SIZE(aesni_skciphers)]; -struct { +static struct { const char *algname; const char *drvname; const char *basename; @@ -1131,7 +1133,7 @@ static struct aead_alg aesni_aead_algs[] = { { .setauthsize = common_rfc4106_set_authsize, .encrypt = helper_rfc4106_encrypt, .decrypt = helper_rfc4106_decrypt, - .ivsize = 8, + .ivsize = GCM_RFC4106_IV_SIZE, .maxauthsize = 16, .base = { .cra_name = "__gcm-aes-aesni", @@ -1149,7 +1151,7 @@ static struct aead_alg aesni_aead_algs[] = { { .setauthsize = rfc4106_set_authsize, .encrypt = rfc4106_encrypt, .decrypt = rfc4106_decrypt, - .ivsize = 8, + .ivsize = GCM_RFC4106_IV_SIZE, .maxauthsize = 16, .base = { .cra_name = "rfc4106(gcm(aes))", @@ -1165,7 +1167,7 @@ static struct aead_alg aesni_aead_algs[] = { { .setauthsize = generic_gcmaes_set_authsize, .encrypt = generic_gcmaes_encrypt, .decrypt = generic_gcmaes_decrypt, - .ivsize = 12, + .ivsize = GCM_AES_IV_SIZE, .maxauthsize = 16, .base = { .cra_name = "gcm(aes)", diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S index 246c67006ed0..8c1fcb6bad21 100644 --- a/arch/x86/crypto/blowfish-x86_64-asm_64.S +++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S @@ -33,7 +33,7 @@ #define s3 ((16 + 2 + (3 * 256)) * 4) /* register macros */ -#define CTX %rdi +#define CTX %r12 #define RIO %rsi #define RX0 %rax @@ -56,12 +56,12 @@ #define RX2bh %ch #define RX3bh %dh -#define RT0 %rbp +#define RT0 %rdi #define RT1 %rsi #define RT2 %r8 #define RT3 %r9 -#define RT0d %ebp +#define RT0d %edi #define RT1d %esi #define RT2d %r8d #define RT3d %r9d @@ -120,13 +120,14 @@ ENTRY(__blowfish_enc_blk) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src * %rcx: bool, if true: xor output */ - movq %rbp, %r11; + movq %r12, %r11; + movq %rdi, CTX; movq %rsi, %r10; movq %rdx, RIO; @@ -142,7 +143,7 @@ ENTRY(__blowfish_enc_blk) round_enc(14); add_roundkey_enc(16); - movq %r11, %rbp; + movq %r11, %r12; movq %r10, RIO; test %cl, %cl; @@ -157,12 +158,13 @@ ENDPROC(__blowfish_enc_blk) ENTRY(blowfish_dec_blk) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ - movq %rbp, %r11; + movq %r12, %r11; + movq %rdi, CTX; movq %rsi, %r10; movq %rdx, RIO; @@ -181,7 +183,7 @@ ENTRY(blowfish_dec_blk) movq %r10, RIO; write_block(); - movq %r11, %rbp; + movq %r11, %r12; ret; ENDPROC(blowfish_dec_blk) @@ -298,20 +300,21 @@ ENDPROC(blowfish_dec_blk) ENTRY(__blowfish_enc_blk_4way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src * %rcx: bool, if true: xor output */ - pushq %rbp; + pushq %r12; pushq %rbx; pushq %rcx; - preload_roundkey_enc(0); - + movq %rdi, CTX movq %rsi, %r11; movq %rdx, RIO; + preload_roundkey_enc(0); + read_block4(); round_enc4(0); @@ -324,39 +327,40 @@ ENTRY(__blowfish_enc_blk_4way) round_enc4(14); add_preloaded_roundkey4(); - popq %rbp; + popq %r12; movq %r11, RIO; - test %bpl, %bpl; + test %r12b, %r12b; jnz .L__enc_xor4; write_block4(); popq %rbx; - popq %rbp; + popq %r12; ret; .L__enc_xor4: xor_block4(); popq %rbx; - popq %rbp; + popq %r12; ret; ENDPROC(__blowfish_enc_blk_4way) ENTRY(blowfish_dec_blk_4way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ - pushq %rbp; + pushq %r12; pushq %rbx; - preload_roundkey_dec(17); - movq %rsi, %r11; + movq %rdi, CTX; + movq %rsi, %r11 movq %rdx, RIO; + preload_roundkey_dec(17); read_block4(); round_dec4(17); @@ -373,7 +377,7 @@ ENTRY(blowfish_dec_blk_4way) write_block4(); popq %rbx; - popq %rbp; + popq %r12; ret; ENDPROC(blowfish_dec_blk_4way) diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S index 310319c601ed..95ba6956a7f6 100644 --- a/arch/x86/crypto/camellia-x86_64-asm_64.S +++ b/arch/x86/crypto/camellia-x86_64-asm_64.S @@ -75,17 +75,17 @@ #define RCD1bh %dh #define RT0 %rsi -#define RT1 %rbp +#define RT1 %r12 #define RT2 %r8 #define RT0d %esi -#define RT1d %ebp +#define RT1d %r12d #define RT2d %r8d #define RT2bl %r8b #define RXOR %r9 -#define RRBP %r10 +#define RR12 %r10 #define RDST %r11 #define RXORd %r9d @@ -197,7 +197,7 @@ ENTRY(__camellia_enc_blk) * %rdx: src * %rcx: bool xor */ - movq %rbp, RRBP; + movq %r12, RR12; movq %rcx, RXOR; movq %rsi, RDST; @@ -227,13 +227,13 @@ ENTRY(__camellia_enc_blk) enc_outunpack(mov, RT1); - movq RRBP, %rbp; + movq RR12, %r12; ret; .L__enc_xor: enc_outunpack(xor, RT1); - movq RRBP, %rbp; + movq RR12, %r12; ret; ENDPROC(__camellia_enc_blk) @@ -248,7 +248,7 @@ ENTRY(camellia_dec_blk) movl $24, RXORd; cmovel RXORd, RT2d; /* max */ - movq %rbp, RRBP; + movq %r12, RR12; movq %rsi, RDST; movq %rdx, RIO; @@ -271,7 +271,7 @@ ENTRY(camellia_dec_blk) dec_outunpack(); - movq RRBP, %rbp; + movq RR12, %r12; ret; ENDPROC(camellia_dec_blk) @@ -433,7 +433,7 @@ ENTRY(__camellia_enc_blk_2way) */ pushq %rbx; - movq %rbp, RRBP; + movq %r12, RR12; movq %rcx, RXOR; movq %rsi, RDST; movq %rdx, RIO; @@ -461,14 +461,14 @@ ENTRY(__camellia_enc_blk_2way) enc_outunpack2(mov, RT2); - movq RRBP, %rbp; + movq RR12, %r12; popq %rbx; ret; .L__enc2_xor: enc_outunpack2(xor, RT2); - movq RRBP, %rbp; + movq RR12, %r12; popq %rbx; ret; ENDPROC(__camellia_enc_blk_2way) @@ -485,7 +485,7 @@ ENTRY(camellia_dec_blk_2way) cmovel RXORd, RT2d; /* max */ movq %rbx, RXOR; - movq %rbp, RRBP; + movq %r12, RR12; movq %rsi, RDST; movq %rdx, RIO; @@ -508,7 +508,7 @@ ENTRY(camellia_dec_blk_2way) dec_outunpack2(); - movq RRBP, %rbp; + movq RR12, %r12; movq RXOR, %rbx; ret; ENDPROC(camellia_dec_blk_2way) diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S index b4a8806234ea..86107c961bb4 100644 --- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S @@ -47,7 +47,7 @@ /********************************************************************** 16-way AVX cast5 **********************************************************************/ -#define CTX %rdi +#define CTX %r15 #define RL1 %xmm0 #define RR1 %xmm1 @@ -70,8 +70,8 @@ #define RTMP %xmm15 -#define RID1 %rbp -#define RID1d %ebp +#define RID1 %rdi +#define RID1d %edi #define RID2 %rsi #define RID2d %esi @@ -226,7 +226,7 @@ .align 16 __cast5_enc_blk16: /* input: - * %rdi: ctx, CTX + * %rdi: ctx * RL1: blocks 1 and 2 * RR1: blocks 3 and 4 * RL2: blocks 5 and 6 @@ -246,9 +246,11 @@ __cast5_enc_blk16: * RR4: encrypted blocks 15 and 16 */ - pushq %rbp; + pushq %r15; pushq %rbx; + movq %rdi, CTX; + vmovdqa .Lbswap_mask, RKM; vmovd .Lfirst_mask, R1ST; vmovd .L32_mask, R32; @@ -283,7 +285,7 @@ __cast5_enc_blk16: .L__skip_enc: popq %rbx; - popq %rbp; + popq %r15; vmovdqa .Lbswap_mask, RKM; @@ -298,7 +300,7 @@ ENDPROC(__cast5_enc_blk16) .align 16 __cast5_dec_blk16: /* input: - * %rdi: ctx, CTX + * %rdi: ctx * RL1: encrypted blocks 1 and 2 * RR1: encrypted blocks 3 and 4 * RL2: encrypted blocks 5 and 6 @@ -318,9 +320,11 @@ __cast5_dec_blk16: * RR4: decrypted blocks 15 and 16 */ - pushq %rbp; + pushq %r15; pushq %rbx; + movq %rdi, CTX; + vmovdqa .Lbswap_mask, RKM; vmovd .Lfirst_mask, R1ST; vmovd .L32_mask, R32; @@ -356,7 +360,7 @@ __cast5_dec_blk16: vmovdqa .Lbswap_mask, RKM; popq %rbx; - popq %rbp; + popq %r15; outunpack_blocks(RR1, RL1, RTMP, RX, RKM); outunpack_blocks(RR2, RL2, RTMP, RX, RKM); @@ -372,12 +376,14 @@ ENDPROC(__cast5_dec_blk16) ENTRY(cast5_ecb_enc_16way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; vmovdqu (0*4*4)(%rdx), RL1; @@ -400,18 +406,22 @@ ENTRY(cast5_ecb_enc_16way) vmovdqu RR4, (6*4*4)(%r11); vmovdqu RL4, (7*4*4)(%r11); + popq %r15; FRAME_END ret; ENDPROC(cast5_ecb_enc_16way) ENTRY(cast5_ecb_dec_16way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN + pushq %r15; + + movq %rdi, CTX; movq %rsi, %r11; vmovdqu (0*4*4)(%rdx), RL1; @@ -434,20 +444,22 @@ ENTRY(cast5_ecb_dec_16way) vmovdqu RR4, (6*4*4)(%r11); vmovdqu RL4, (7*4*4)(%r11); + popq %r15; FRAME_END ret; ENDPROC(cast5_ecb_dec_16way) ENTRY(cast5_cbc_dec_16way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN - pushq %r12; + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; movq %rdx, %r12; @@ -483,23 +495,24 @@ ENTRY(cast5_cbc_dec_16way) vmovdqu RR4, (6*16)(%r11); vmovdqu RL4, (7*16)(%r11); + popq %r15; popq %r12; - FRAME_END ret; ENDPROC(cast5_cbc_dec_16way) ENTRY(cast5_ctr_16way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src * %rcx: iv (big endian, 64bit) */ FRAME_BEGIN - pushq %r12; + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; movq %rdx, %r12; @@ -558,8 +571,8 @@ ENTRY(cast5_ctr_16way) vmovdqu RR4, (6*16)(%r11); vmovdqu RL4, (7*16)(%r11); + popq %r15; popq %r12; - FRAME_END ret; ENDPROC(cast5_ctr_16way) diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S index 952d3156a933..7f30b6f0d72c 100644 --- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S @@ -47,7 +47,7 @@ /********************************************************************** 8-way AVX cast6 **********************************************************************/ -#define CTX %rdi +#define CTX %r15 #define RA1 %xmm0 #define RB1 %xmm1 @@ -70,8 +70,8 @@ #define RTMP %xmm15 -#define RID1 %rbp -#define RID1d %ebp +#define RID1 %rdi +#define RID1d %edi #define RID2 %rsi #define RID2d %esi @@ -264,15 +264,17 @@ .align 8 __cast6_enc_blk8: /* input: - * %rdi: ctx, CTX + * %rdi: ctx * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks * output: * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks */ - pushq %rbp; + pushq %r15; pushq %rbx; + movq %rdi, CTX; + vmovdqa .Lbswap_mask, RKM; vmovd .Lfirst_mask, R1ST; vmovd .L32_mask, R32; @@ -297,7 +299,7 @@ __cast6_enc_blk8: QBAR(11); popq %rbx; - popq %rbp; + popq %r15; vmovdqa .Lbswap_mask, RKM; @@ -310,15 +312,17 @@ ENDPROC(__cast6_enc_blk8) .align 8 __cast6_dec_blk8: /* input: - * %rdi: ctx, CTX + * %rdi: ctx * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks * output: * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: decrypted blocks */ - pushq %rbp; + pushq %r15; pushq %rbx; + movq %rdi, CTX; + vmovdqa .Lbswap_mask, RKM; vmovd .Lfirst_mask, R1ST; vmovd .L32_mask, R32; @@ -343,7 +347,7 @@ __cast6_dec_blk8: QBAR(0); popq %rbx; - popq %rbp; + popq %r15; vmovdqa .Lbswap_mask, RKM; outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM); @@ -354,12 +358,14 @@ ENDPROC(__cast6_dec_blk8) ENTRY(cast6_ecb_enc_8way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); @@ -368,18 +374,21 @@ ENTRY(cast6_ecb_enc_8way) store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; FRAME_END ret; ENDPROC(cast6_ecb_enc_8way) ENTRY(cast6_ecb_dec_8way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); @@ -388,20 +397,22 @@ ENTRY(cast6_ecb_dec_8way) store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; FRAME_END ret; ENDPROC(cast6_ecb_dec_8way) ENTRY(cast6_cbc_dec_8way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN - pushq %r12; + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; movq %rdx, %r12; @@ -411,8 +422,8 @@ ENTRY(cast6_cbc_dec_8way) store_cbc_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; popq %r12; - FRAME_END ret; ENDPROC(cast6_cbc_dec_8way) @@ -425,9 +436,10 @@ ENTRY(cast6_ctr_8way) * %rcx: iv (little endian, 128bit) */ FRAME_BEGIN - pushq %r12; + pushq %r15 + movq %rdi, CTX; movq %rsi, %r11; movq %rdx, %r12; @@ -438,8 +450,8 @@ ENTRY(cast6_ctr_8way) store_ctr_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; popq %r12; - FRAME_END ret; ENDPROC(cast6_ctr_8way) @@ -452,7 +464,9 @@ ENTRY(cast6_xts_enc_8way) * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) */ FRAME_BEGIN + pushq %r15; + movq %rdi, CTX movq %rsi, %r11; /* regs <= src, dst <= IVs, regs <= regs xor IVs */ @@ -464,6 +478,7 @@ ENTRY(cast6_xts_enc_8way) /* dst <= regs xor IVs(in dst) */ store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; FRAME_END ret; ENDPROC(cast6_xts_enc_8way) @@ -476,7 +491,9 @@ ENTRY(cast6_xts_dec_8way) * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) */ FRAME_BEGIN + pushq %r15; + movq %rdi, CTX movq %rsi, %r11; /* regs <= src, dst <= IVs, regs <= regs xor IVs */ @@ -488,6 +505,7 @@ ENTRY(cast6_xts_dec_8way) /* dst <= regs xor IVs(in dst) */ store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; FRAME_END ret; ENDPROC(cast6_xts_dec_8way) diff --git a/arch/x86/crypto/chacha20-avx2-x86_64.S b/arch/x86/crypto/chacha20-avx2-x86_64.S index 3a2dc3dc6cac..f3cd26f48332 100644 --- a/arch/x86/crypto/chacha20-avx2-x86_64.S +++ b/arch/x86/crypto/chacha20-avx2-x86_64.S @@ -45,7 +45,7 @@ ENTRY(chacha20_8block_xor_avx2) vzeroupper # 4 * 32 byte stack, 32-byte aligned - mov %rsp, %r8 + lea 8(%rsp),%r10 and $~31, %rsp sub $0x80, %rsp @@ -443,6 +443,6 @@ ENTRY(chacha20_8block_xor_avx2) vmovdqu %ymm15,0x01e0(%rsi) vzeroupper - mov %r8,%rsp + lea -8(%r10),%rsp ret ENDPROC(chacha20_8block_xor_avx2) diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S index 3f511a7d73b8..512a2b500fd1 100644 --- a/arch/x86/crypto/chacha20-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -160,7 +160,7 @@ ENTRY(chacha20_4block_xor_ssse3) # done with the slightly better performing SSSE3 byte shuffling, # 7/12-bit word rotation uses traditional shift+OR. - mov %rsp,%r11 + lea 8(%rsp),%r10 sub $0x80,%rsp and $~63,%rsp @@ -625,6 +625,6 @@ ENTRY(chacha20_4block_xor_ssse3) pxor %xmm1,%xmm15 movdqu %xmm15,0xf0(%rsi) - mov %r11,%rsp + lea -8(%r10),%rsp ret ENDPROC(chacha20_4block_xor_ssse3) diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S index f247304299a2..1c099dc08cc3 100644 --- a/arch/x86/crypto/crc32-pclmul_asm.S +++ b/arch/x86/crypto/crc32-pclmul_asm.S @@ -41,6 +41,7 @@ #include <asm/inst.h> +.section .rodata .align 16 /* * [x4*128+32 mod P(x) << 32)]' << 1 = 0x154442bd4 @@ -111,19 +112,13 @@ ENTRY(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligned */ pxor CONSTANT, %xmm1 sub $0x40, LEN add $0x40, BUF -#ifndef __x86_64__ - /* This is for position independent code(-fPIC) support for 32bit */ - call delta -delta: - pop %ecx -#endif cmp $0x40, LEN jb less_64 #ifdef __x86_64__ movdqa .Lconstant_R2R1(%rip), CONSTANT #else - movdqa .Lconstant_R2R1 - delta(%ecx), CONSTANT + movdqa .Lconstant_R2R1, CONSTANT #endif loop_64:/* 64 bytes Full cache line folding */ @@ -172,7 +167,7 @@ less_64:/* Folding cache line into 128bit */ #ifdef __x86_64__ movdqa .Lconstant_R4R3(%rip), CONSTANT #else - movdqa .Lconstant_R4R3 - delta(%ecx), CONSTANT + movdqa .Lconstant_R4R3, CONSTANT #endif prefetchnta (BUF) @@ -220,8 +215,8 @@ fold_64: movdqa .Lconstant_R5(%rip), CONSTANT movdqa .Lconstant_mask32(%rip), %xmm3 #else - movdqa .Lconstant_R5 - delta(%ecx), CONSTANT - movdqa .Lconstant_mask32 - delta(%ecx), %xmm3 + movdqa .Lconstant_R5, CONSTANT + movdqa .Lconstant_mask32, %xmm3 #endif psrldq $0x04, %xmm2 pand %xmm3, %xmm1 @@ -232,7 +227,7 @@ fold_64: #ifdef __x86_64__ movdqa .Lconstant_RUpoly(%rip), CONSTANT #else - movdqa .Lconstant_RUpoly - delta(%ecx), CONSTANT + movdqa .Lconstant_RUpoly, CONSTANT #endif movdqa %xmm1, %xmm2 pand %xmm3, %xmm1 diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S index f3e91647ca27..8e49ce117494 100644 --- a/arch/x86/crypto/des3_ede-asm_64.S +++ b/arch/x86/crypto/des3_ede-asm_64.S @@ -64,12 +64,12 @@ #define RW2bh %ch #define RT0 %r15 -#define RT1 %rbp +#define RT1 %rsi #define RT2 %r14 #define RT3 %rdx #define RT0d %r15d -#define RT1d %ebp +#define RT1d %esi #define RT2d %r14d #define RT3d %edx @@ -177,13 +177,14 @@ ENTRY(des3_ede_x86_64_crypt_blk) * %rsi: dst * %rdx: src */ - pushq %rbp; pushq %rbx; pushq %r12; pushq %r13; pushq %r14; pushq %r15; + pushq %rsi; /* dst */ + read_block(%rdx, RL0, RR0); initial_permutation(RL0, RR0); @@ -241,6 +242,8 @@ ENTRY(des3_ede_x86_64_crypt_blk) round1(32+15, RL0, RR0, dummy2); final_permutation(RR0, RL0); + + popq %rsi /* dst */ write_block(%rsi, RR0, RL0); popq %r15; @@ -248,7 +251,6 @@ ENTRY(des3_ede_x86_64_crypt_blk) popq %r13; popq %r12; popq %rbx; - popq %rbp; ret; ENDPROC(des3_ede_x86_64_crypt_blk) @@ -432,13 +434,14 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way) * %rdx: src (3 blocks) */ - pushq %rbp; pushq %rbx; pushq %r12; pushq %r13; pushq %r14; pushq %r15; + pushq %rsi /* dst */ + /* load input */ movl 0 * 4(%rdx), RL0d; movl 1 * 4(%rdx), RR0d; @@ -520,6 +523,7 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way) bswapl RR2d; bswapl RL2d; + popq %rsi /* dst */ movl RR0d, 0 * 4(%rsi); movl RL0d, 1 * 4(%rsi); movl RR1d, 2 * 4(%rsi); @@ -532,7 +536,6 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way) popq %r13; popq %r12; popq %rbx; - popq %rbp; ret; ENDPROC(des3_ede_x86_64_crypt_blk_3way) diff --git a/arch/x86/crypto/salsa20-x86_64-asm_64.S b/arch/x86/crypto/salsa20-x86_64-asm_64.S index 9279e0b2d60e..10db30d58006 100644 --- a/arch/x86/crypto/salsa20-x86_64-asm_64.S +++ b/arch/x86/crypto/salsa20-x86_64-asm_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> # enter salsa20_encrypt_bytes diff --git a/arch/x86/crypto/sha1-mb/Makefile b/arch/x86/crypto/sha1-mb/Makefile index 2e14acc3da25..815ded3ba90e 100644 --- a/arch/x86/crypto/sha1-mb/Makefile +++ b/arch/x86/crypto/sha1-mb/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Arch-specific CryptoAPI modules. # diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S index 93b945597ecf..7cfba738f104 100644 --- a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S +++ b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S @@ -157,8 +157,8 @@ LABEL skip_ %I .endr # Find min length - vmovdqa _lens+0*16(state), %xmm0 - vmovdqa _lens+1*16(state), %xmm1 + vmovdqu _lens+0*16(state), %xmm0 + vmovdqu _lens+1*16(state), %xmm1 vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A} vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C} @@ -178,8 +178,8 @@ LABEL skip_ %I vpsubd %xmm2, %xmm0, %xmm0 vpsubd %xmm2, %xmm1, %xmm1 - vmovdqa %xmm0, _lens+0*16(state) - vmovdqa %xmm1, _lens+1*16(state) + vmovdqu %xmm0, _lens+0*16(state) + vmovdqu %xmm1, _lens+1*16(state) # "state" and "args" are the same address, arg1 # len is arg2 @@ -235,8 +235,8 @@ ENTRY(sha1_mb_mgr_get_comp_job_avx2) jc .return_null # Find min length - vmovdqa _lens(state), %xmm0 - vmovdqa _lens+1*16(state), %xmm1 + vmovdqu _lens(state), %xmm0 + vmovdqu _lens+1*16(state), %xmm1 vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A} vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C} diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S index 1eab79c9ac48..9f712a7dfd79 100644 --- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S +++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S @@ -89,7 +89,7 @@ #define REG_RE %rdx #define REG_RTA %r12 #define REG_RTB %rbx -#define REG_T1 %ebp +#define REG_T1 %r11d #define xmm_mov vmovups #define avx2_zeroupper vzeroupper #define RND_F1 1 @@ -637,7 +637,6 @@ _loop3: ENTRY(\name) push %rbx - push %rbp push %r12 push %r13 push %r14 @@ -673,7 +672,6 @@ _loop3: pop %r14 pop %r13 pop %r12 - pop %rbp pop %rbx ret diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S index a4109506a5e8..6204bd53528c 100644 --- a/arch/x86/crypto/sha1_ssse3_asm.S +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -37,7 +37,7 @@ #define REG_A %ecx #define REG_B %esi #define REG_C %edi -#define REG_D %ebp +#define REG_D %r12d #define REG_E %edx #define REG_T1 %eax @@ -74,10 +74,10 @@ ENTRY(\name) push %rbx - push %rbp push %r12 + push %rbp + mov %rsp, %rbp - mov %rsp, %r12 sub $64, %rsp # allocate workspace and $~15, %rsp # align stack @@ -99,10 +99,9 @@ xor %rax, %rax rep stosq - mov %r12, %rsp # deallocate workspace - - pop %r12 + mov %rbp, %rsp # deallocate workspace pop %rbp + pop %r12 pop %rbx ret diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index e08888a1a5f2..001bbcf93c79 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -103,7 +103,7 @@ SRND = %rsi # clobbers INP c = %ecx d = %r8d e = %edx -TBL = %rbp +TBL = %r12 a = %eax b = %ebx @@ -350,13 +350,13 @@ a = TMP_ ENTRY(sha256_transform_avx) .align 32 pushq %rbx - pushq %rbp + pushq %r12 pushq %r13 pushq %r14 pushq %r15 - pushq %r12 + pushq %rbp + movq %rsp, %rbp - mov %rsp, %r12 subq $STACK_SIZE, %rsp # allocate stack space and $~15, %rsp # align stack pointer @@ -452,13 +452,12 @@ loop2: done_hash: - mov %r12, %rsp - - popq %r12 + mov %rbp, %rsp + popq %rbp popq %r15 popq %r14 popq %r13 - popq %rbp + popq %r12 popq %rbx ret ENDPROC(sha256_transform_avx) diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 89c8f09787d2..1420db15dcdd 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -98,8 +98,6 @@ d = %r8d e = %edx # clobbers NUM_BLKS y3 = %esi # clobbers INP - -TBL = %rbp SRND = CTX # SRND is same register as CTX a = %eax @@ -531,7 +529,6 @@ STACK_SIZE = _RSP + _RSP_SIZE ENTRY(sha256_transform_rorx) .align 32 pushq %rbx - pushq %rbp pushq %r12 pushq %r13 pushq %r14 @@ -568,8 +565,6 @@ ENTRY(sha256_transform_rorx) mov CTX, _CTX(%rsp) loop0: - lea K256(%rip), TBL - ## Load first 16 dwords from two blocks VMOVDQ 0*32(INP),XTMP0 VMOVDQ 1*32(INP),XTMP1 @@ -597,19 +592,19 @@ last_block_enter: .align 16 loop1: - vpaddd 0*32(TBL, SRND), X0, XFER + vpaddd K256+0*32(SRND), X0, XFER vmovdqa XFER, 0*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 0*32 - vpaddd 1*32(TBL, SRND), X0, XFER + vpaddd K256+1*32(SRND), X0, XFER vmovdqa XFER, 1*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 1*32 - vpaddd 2*32(TBL, SRND), X0, XFER + vpaddd K256+2*32(SRND), X0, XFER vmovdqa XFER, 2*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 2*32 - vpaddd 3*32(TBL, SRND), X0, XFER + vpaddd K256+3*32(SRND), X0, XFER vmovdqa XFER, 3*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 3*32 @@ -619,10 +614,11 @@ loop1: loop2: ## Do last 16 rounds with no scheduling - vpaddd 0*32(TBL, SRND), X0, XFER + vpaddd K256+0*32(SRND), X0, XFER vmovdqa XFER, 0*32+_XFER(%rsp, SRND) DO_4ROUNDS _XFER + 0*32 - vpaddd 1*32(TBL, SRND), X1, XFER + + vpaddd K256+1*32(SRND), X1, XFER vmovdqa XFER, 1*32+_XFER(%rsp, SRND) DO_4ROUNDS _XFER + 1*32 add $2*32, SRND @@ -676,9 +672,6 @@ loop3: ja done_hash do_last_block: - #### do last block - lea K256(%rip), TBL - VMOVDQ 0*16(INP),XWORD0 VMOVDQ 1*16(INP),XWORD1 VMOVDQ 2*16(INP),XWORD2 @@ -718,7 +711,6 @@ done_hash: popq %r14 popq %r13 popq %r12 - popq %rbp popq %rbx ret ENDPROC(sha256_transform_rorx) diff --git a/arch/x86/crypto/sha256-mb/Makefile b/arch/x86/crypto/sha256-mb/Makefile index 45b4fca6c4a8..53ad6e7db747 100644 --- a/arch/x86/crypto/sha256-mb/Makefile +++ b/arch/x86/crypto/sha256-mb/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Arch-specific CryptoAPI modules. # diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S index 8fe6338bcc84..16c4ccb1f154 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S +++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S @@ -155,8 +155,8 @@ LABEL skip_ %I .endr # Find min length - vmovdqa _lens+0*16(state), %xmm0 - vmovdqa _lens+1*16(state), %xmm1 + vmovdqu _lens+0*16(state), %xmm0 + vmovdqu _lens+1*16(state), %xmm1 vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A} vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C} @@ -176,8 +176,8 @@ LABEL skip_ %I vpsubd %xmm2, %xmm0, %xmm0 vpsubd %xmm2, %xmm1, %xmm1 - vmovdqa %xmm0, _lens+0*16(state) - vmovdqa %xmm1, _lens+1*16(state) + vmovdqu %xmm0, _lens+0*16(state) + vmovdqu %xmm1, _lens+1*16(state) # "state" and "args" are the same address, arg1 # len is arg2 @@ -234,8 +234,8 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2) jc .return_null # Find min length - vmovdqa _lens(state), %xmm0 - vmovdqa _lens+1*16(state), %xmm1 + vmovdqu _lens(state), %xmm0 + vmovdqu _lens+1*16(state), %xmm1 vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A} vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C} diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S index 39b83c93e7fd..c6c05ed2c16a 100644 --- a/arch/x86/crypto/sha256-ssse3-asm.S +++ b/arch/x86/crypto/sha256-ssse3-asm.S @@ -95,7 +95,7 @@ SRND = %rsi # clobbers INP c = %ecx d = %r8d e = %edx -TBL = %rbp +TBL = %r12 a = %eax b = %ebx @@ -356,13 +356,13 @@ a = TMP_ ENTRY(sha256_transform_ssse3) .align 32 pushq %rbx - pushq %rbp + pushq %r12 pushq %r13 pushq %r14 pushq %r15 - pushq %r12 + pushq %rbp + mov %rsp, %rbp - mov %rsp, %r12 subq $STACK_SIZE, %rsp and $~15, %rsp @@ -462,13 +462,12 @@ loop2: done_hash: - mov %r12, %rsp - - popq %r12 + mov %rbp, %rsp + popq %rbp popq %r15 popq %r14 popq %r13 - popq %rbp + popq %r12 popq %rbx ret diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index 7f5f6c6ec72e..b16d56005162 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -69,8 +69,9 @@ XFER = YTMP0 BYTE_FLIP_MASK = %ymm9 -# 1st arg -CTX = %rdi +# 1st arg is %rdi, which is saved to the stack and accessed later via %r12 +CTX1 = %rdi +CTX2 = %r12 # 2nd arg INP = %rsi # 3rd arg @@ -81,7 +82,7 @@ d = %r8 e = %rdx y3 = %rsi -TBL = %rbp +TBL = %rdi # clobbers CTX1 a = %rax b = %rbx @@ -91,26 +92,26 @@ g = %r10 h = %r11 old_h = %r11 -T1 = %r12 +T1 = %r12 # clobbers CTX2 y0 = %r13 y1 = %r14 y2 = %r15 -y4 = %r12 - # Local variables (stack frame) XFER_SIZE = 4*8 SRND_SIZE = 1*8 INP_SIZE = 1*8 INPEND_SIZE = 1*8 +CTX_SIZE = 1*8 RSPSAVE_SIZE = 1*8 -GPRSAVE_SIZE = 6*8 +GPRSAVE_SIZE = 5*8 frame_XFER = 0 frame_SRND = frame_XFER + XFER_SIZE frame_INP = frame_SRND + SRND_SIZE frame_INPEND = frame_INP + INP_SIZE -frame_RSPSAVE = frame_INPEND + INPEND_SIZE +frame_CTX = frame_INPEND + INPEND_SIZE +frame_RSPSAVE = frame_CTX + CTX_SIZE frame_GPRSAVE = frame_RSPSAVE + RSPSAVE_SIZE frame_size = frame_GPRSAVE + GPRSAVE_SIZE @@ -576,12 +577,11 @@ ENTRY(sha512_transform_rorx) mov %rax, frame_RSPSAVE(%rsp) # Save GPRs - mov %rbp, frame_GPRSAVE(%rsp) - mov %rbx, 8*1+frame_GPRSAVE(%rsp) - mov %r12, 8*2+frame_GPRSAVE(%rsp) - mov %r13, 8*3+frame_GPRSAVE(%rsp) - mov %r14, 8*4+frame_GPRSAVE(%rsp) - mov %r15, 8*5+frame_GPRSAVE(%rsp) + mov %rbx, 8*0+frame_GPRSAVE(%rsp) + mov %r12, 8*1+frame_GPRSAVE(%rsp) + mov %r13, 8*2+frame_GPRSAVE(%rsp) + mov %r14, 8*3+frame_GPRSAVE(%rsp) + mov %r15, 8*4+frame_GPRSAVE(%rsp) shl $7, NUM_BLKS # convert to bytes jz done_hash @@ -589,14 +589,17 @@ ENTRY(sha512_transform_rorx) mov NUM_BLKS, frame_INPEND(%rsp) ## load initial digest - mov 8*0(CTX),a - mov 8*1(CTX),b - mov 8*2(CTX),c - mov 8*3(CTX),d - mov 8*4(CTX),e - mov 8*5(CTX),f - mov 8*6(CTX),g - mov 8*7(CTX),h + mov 8*0(CTX1), a + mov 8*1(CTX1), b + mov 8*2(CTX1), c + mov 8*3(CTX1), d + mov 8*4(CTX1), e + mov 8*5(CTX1), f + mov 8*6(CTX1), g + mov 8*7(CTX1), h + + # save %rdi (CTX) before it gets clobbered + mov %rdi, frame_CTX(%rsp) vmovdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK @@ -652,14 +655,15 @@ loop2: subq $1, frame_SRND(%rsp) jne loop2 - addm 8*0(CTX),a - addm 8*1(CTX),b - addm 8*2(CTX),c - addm 8*3(CTX),d - addm 8*4(CTX),e - addm 8*5(CTX),f - addm 8*6(CTX),g - addm 8*7(CTX),h + mov frame_CTX(%rsp), CTX2 + addm 8*0(CTX2), a + addm 8*1(CTX2), b + addm 8*2(CTX2), c + addm 8*3(CTX2), d + addm 8*4(CTX2), e + addm 8*5(CTX2), f + addm 8*6(CTX2), g + addm 8*7(CTX2), h mov frame_INP(%rsp), INP add $128, INP @@ -669,12 +673,11 @@ loop2: done_hash: # Restore GPRs - mov frame_GPRSAVE(%rsp) ,%rbp - mov 8*1+frame_GPRSAVE(%rsp) ,%rbx - mov 8*2+frame_GPRSAVE(%rsp) ,%r12 - mov 8*3+frame_GPRSAVE(%rsp) ,%r13 - mov 8*4+frame_GPRSAVE(%rsp) ,%r14 - mov 8*5+frame_GPRSAVE(%rsp) ,%r15 + mov 8*0+frame_GPRSAVE(%rsp), %rbx + mov 8*1+frame_GPRSAVE(%rsp), %r12 + mov 8*2+frame_GPRSAVE(%rsp), %r13 + mov 8*3+frame_GPRSAVE(%rsp), %r14 + mov 8*4+frame_GPRSAVE(%rsp), %r15 # Restore Stack Pointer mov frame_RSPSAVE(%rsp), %rsp diff --git a/arch/x86/crypto/sha512-mb/Makefile b/arch/x86/crypto/sha512-mb/Makefile index 0a57e2103980..90f1ef69152e 100644 --- a/arch/x86/crypto/sha512-mb/Makefile +++ b/arch/x86/crypto/sha512-mb/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Arch-specific CryptoAPI modules. # diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S index b3f49d286348..73b471da3622 100644 --- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S @@ -76,8 +76,8 @@ #define RT %xmm14 #define RR %xmm15 -#define RID1 %rbp -#define RID1d %ebp +#define RID1 %r13 +#define RID1d %r13d #define RID2 %rsi #define RID2d %esi @@ -259,7 +259,7 @@ __twofish_enc_blk8: vmovdqu w(CTX), RK1; - pushq %rbp; + pushq %r13; pushq %rbx; pushq %rcx; @@ -282,7 +282,7 @@ __twofish_enc_blk8: popq %rcx; popq %rbx; - popq %rbp; + popq %r13; outunpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2); outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2); @@ -301,7 +301,7 @@ __twofish_dec_blk8: vmovdqu (w+4*4)(CTX), RK1; - pushq %rbp; + pushq %r13; pushq %rbx; inpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2); @@ -322,7 +322,7 @@ __twofish_dec_blk8: vmovdqu (w)(CTX), RK1; popq %rbx; - popq %rbp; + popq %r13; outunpack_blocks(RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2); outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2); diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index af28a8a24366..06fc70cf5433 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the x86 low level entry code # diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 640aafebdc00..3fd8bc560fae 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <linux/jump_label.h> #include <asm/unwind_hints.h> @@ -141,56 +142,25 @@ For 32-bit we have the following conventions - kernel is built with UNWIND_HINT_REGS offset=\offset .endm - .macro RESTORE_EXTRA_REGS offset=0 - movq 0*8+\offset(%rsp), %r15 - movq 1*8+\offset(%rsp), %r14 - movq 2*8+\offset(%rsp), %r13 - movq 3*8+\offset(%rsp), %r12 - movq 4*8+\offset(%rsp), %rbp - movq 5*8+\offset(%rsp), %rbx - UNWIND_HINT_REGS offset=\offset extra=0 - .endm - - .macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1 - .if \rstor_r11 - movq 6*8(%rsp), %r11 - .endif - .if \rstor_r8910 - movq 7*8(%rsp), %r10 - movq 8*8(%rsp), %r9 - movq 9*8(%rsp), %r8 - .endif - .if \rstor_rax - movq 10*8(%rsp), %rax - .endif - .if \rstor_rcx - movq 11*8(%rsp), %rcx - .endif - .if \rstor_rdx - movq 12*8(%rsp), %rdx - .endif - movq 13*8(%rsp), %rsi - movq 14*8(%rsp), %rdi - UNWIND_HINT_IRET_REGS offset=16*8 - .endm - .macro RESTORE_C_REGS - RESTORE_C_REGS_HELPER 1,1,1,1,1 - .endm - .macro RESTORE_C_REGS_EXCEPT_RAX - RESTORE_C_REGS_HELPER 0,1,1,1,1 - .endm - .macro RESTORE_C_REGS_EXCEPT_RCX - RESTORE_C_REGS_HELPER 1,0,1,1,1 - .endm - .macro RESTORE_C_REGS_EXCEPT_R11 - RESTORE_C_REGS_HELPER 1,1,0,1,1 - .endm - .macro RESTORE_C_REGS_EXCEPT_RCX_R11 - RESTORE_C_REGS_HELPER 1,0,0,1,1 - .endm - - .macro REMOVE_PT_GPREGS_FROM_STACK addskip=0 - subq $-(15*8+\addskip), %rsp + .macro POP_EXTRA_REGS + popq %r15 + popq %r14 + popq %r13 + popq %r12 + popq %rbp + popq %rbx + .endm + + .macro POP_C_REGS + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + popq %rdi .endm .macro icebp diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 03505ffbe1b6..d7d3cc24baf4 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -75,7 +75,7 @@ static long syscall_trace_enter(struct pt_regs *regs) if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) BUG_ON(regs != task_pt_regs(current)); - work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; + work = READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; if (unlikely(work & _TIF_SYSCALL_EMU)) emulated = true; @@ -186,9 +186,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) addr_limit_user_check(); - if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) - local_irq_disable(); - + lockdep_assert_irqs_disabled(); lockdep_sys_exit(); cached_flags = READ_ONCE(ti->flags); diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 8a13d468635a..4838037f97f6 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1991,1992 Linus Torvalds * @@ -176,7 +177,7 @@ /* * This is a sneaky trick to help the unwinder find pt_regs on the stack. The * frame pointer is replaced with an encoded pointer to pt_regs. The encoding - * is just setting the LSB, which makes it an invalid stack address and is also + * is just clearing the MSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * * NOTE: This macro must be used *after* SAVE_ALL because it corrupts the @@ -185,7 +186,7 @@ .macro ENCODE_FRAME_POINTER #ifdef CONFIG_FRAME_POINTER mov %esp, %ebp - orl $0x1, %ebp + andl $0x7fffffff, %ebp #endif .endm diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 49167258d587..f81d50d7ceac 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * linux/arch/x86_64/entry.S * @@ -50,15 +51,19 @@ ENTRY(native_usergs_sysret64) END(native_usergs_sysret64) #endif /* CONFIG_PARAVIRT */ -.macro TRACE_IRQS_IRETQ +.macro TRACE_IRQS_FLAGS flags:req #ifdef CONFIG_TRACE_IRQFLAGS - bt $9, EFLAGS(%rsp) /* interrupts off? */ + bt $9, \flags /* interrupts off? */ jnc 1f TRACE_IRQS_ON 1: #endif .endm +.macro TRACE_IRQS_IRETQ + TRACE_IRQS_FLAGS EFLAGS(%rsp) +.endm + /* * When dynamic function tracer is enabled it will add a breakpoint * to all locations that it is about to modify, sync CPUs, update @@ -147,8 +152,6 @@ ENTRY(entry_SYSCALL_64) movq %rsp, PER_CPU_VAR(rsp_scratch) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - TRACE_IRQS_OFF - /* Construct struct pt_regs on stack */ pushq $__USER_DS /* pt_regs->ss */ pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */ @@ -169,6 +172,8 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ UNWIND_HINT_REGS extra=0 + TRACE_IRQS_OFF + /* * If we need to do entry work or if we guess we'll need to do * exit work, go straight to the slow path. @@ -220,10 +225,9 @@ entry_SYSCALL_64_fastpath: TRACE_IRQS_ON /* user mode is traced as IRQs on */ movq RIP(%rsp), %rcx movq EFLAGS(%rsp), %r11 - RESTORE_C_REGS_EXCEPT_RCX_R11 - movq RSP(%rsp), %rsp + addq $6*8, %rsp /* skip extra regs -- they were preserved */ UNWIND_HINT_EMPTY - USERGS_SYSRET64 + jmp .Lpop_c_regs_except_rcx_r11_and_sysret 1: /* @@ -245,17 +249,18 @@ entry_SYSCALL64_slow_path: call do_syscall_64 /* returns with IRQs disabled */ return_from_SYSCALL_64: - RESTORE_EXTRA_REGS TRACE_IRQS_IRETQ /* we're about to change IF */ /* * Try to use SYSRET instead of IRET if we're returning to - * a completely clean 64-bit userspace context. + * a completely clean 64-bit userspace context. If we're not, + * go to the slow exit path. */ movq RCX(%rsp), %rcx movq RIP(%rsp), %r11 - cmpq %rcx, %r11 /* RCX == RIP */ - jne opportunistic_sysret_failed + + cmpq %rcx, %r11 /* SYSRET requires RCX == RIP */ + jne swapgs_restore_regs_and_return_to_usermode /* * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP @@ -273,14 +278,14 @@ return_from_SYSCALL_64: /* If this changed %rcx, it was not canonical */ cmpq %rcx, %r11 - jne opportunistic_sysret_failed + jne swapgs_restore_regs_and_return_to_usermode cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */ - jne opportunistic_sysret_failed + jne swapgs_restore_regs_and_return_to_usermode movq R11(%rsp), %r11 cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */ - jne opportunistic_sysret_failed + jne swapgs_restore_regs_and_return_to_usermode /* * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot @@ -301,12 +306,12 @@ return_from_SYSCALL_64: * would never get past 'stuck_here'. */ testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 - jnz opportunistic_sysret_failed + jnz swapgs_restore_regs_and_return_to_usermode /* nothing to check for RSP */ cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */ - jne opportunistic_sysret_failed + jne swapgs_restore_regs_and_return_to_usermode /* * We win! This label is here just for ease of understanding @@ -314,14 +319,20 @@ return_from_SYSCALL_64: */ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ - RESTORE_C_REGS_EXCEPT_RCX_R11 - movq RSP(%rsp), %rsp UNWIND_HINT_EMPTY + POP_EXTRA_REGS +.Lpop_c_regs_except_rcx_r11_and_sysret: + popq %rsi /* skip r11 */ + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rsi /* skip rcx */ + popq %rdx + popq %rsi + popq %rdi + movq RSP-ORIG_RAX(%rsp), %rsp USERGS_SYSRET64 - -opportunistic_sysret_failed: - SWAPGS - jmp restore_c_regs_and_iret END(entry_SYSCALL_64) ENTRY(stub_ptregs_64) @@ -422,8 +433,7 @@ ENTRY(ret_from_fork) movq %rsp, %rdi call syscall_return_slowpath /* returns with IRQs disabled */ TRACE_IRQS_ON /* user mode is traced as IRQS on */ - SWAPGS - jmp restore_regs_and_iret + jmp swapgs_restore_regs_and_return_to_usermode 1: /* kernel thread */ @@ -611,8 +621,21 @@ GLOBAL(retint_user) mov %rsp,%rdi call prepare_exit_to_usermode TRACE_IRQS_IRETQ + +GLOBAL(swapgs_restore_regs_and_return_to_usermode) +#ifdef CONFIG_DEBUG_ENTRY + /* Assert that pt_regs indicates user mode. */ + testb $3, CS(%rsp) + jnz 1f + ud2 +1: +#endif SWAPGS - jmp restore_regs_and_iret + POP_EXTRA_REGS + POP_C_REGS + addq $8, %rsp /* skip regs->orig_ax */ + INTERRUPT_RETURN + /* Returning to kernel space */ retint_kernel: @@ -632,15 +655,17 @@ retint_kernel: */ TRACE_IRQS_IRETQ -/* - * At this label, code paths which return to kernel and to user, - * which come from interrupts/exception and from syscalls, merge. - */ -GLOBAL(restore_regs_and_iret) - RESTORE_EXTRA_REGS -restore_c_regs_and_iret: - RESTORE_C_REGS - REMOVE_PT_GPREGS_FROM_STACK 8 +GLOBAL(restore_regs_and_return_to_kernel) +#ifdef CONFIG_DEBUG_ENTRY + /* Assert that pt_regs indicates kernel mode. */ + testb $3, CS(%rsp) + jz 1f + ud2 +1: +#endif + POP_EXTRA_REGS + POP_C_REGS + addq $8, %rsp /* skip regs->orig_ax */ INTERRUPT_RETURN ENTRY(native_iret) @@ -808,7 +833,7 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) - UNWIND_HINT_IRET_REGS offset=8 + UNWIND_HINT_IRET_REGS offset=\has_error_code*8 /* Sanity check */ .if \shift_ist != -1 && \paranoid == 0 @@ -817,7 +842,7 @@ ENTRY(\sym) ASM_CLAC - .ifeq \has_error_code + .if \has_error_code == 0 pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif @@ -922,11 +947,13 @@ ENTRY(native_load_gs_index) FRAME_BEGIN pushfq DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) + TRACE_IRQS_OFF SWAPGS .Lgs_change: movl %edi, %gs 2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE SWAPGS + TRACE_IRQS_FLAGS (%rsp) popfq FRAME_END ret @@ -1058,6 +1085,7 @@ idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK idtentry stack_segment do_stack_segment has_error_code=1 #ifdef CONFIG_XEN +idtentry xennmi do_nmi has_error_code=0 idtentry xendebug do_debug has_error_code=0 idtentry xenint3 do_int3 has_error_code=0 #endif @@ -1111,17 +1139,14 @@ ENTRY(paranoid_exit) DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF_DEBUG testl %ebx, %ebx /* swapgs needed? */ - jnz paranoid_exit_no_swapgs + jnz .Lparanoid_exit_no_swapgs TRACE_IRQS_IRETQ SWAPGS_UNSAFE_STACK - jmp paranoid_exit_restore -paranoid_exit_no_swapgs: + jmp .Lparanoid_exit_restore +.Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG -paranoid_exit_restore: - RESTORE_EXTRA_REGS - RESTORE_C_REGS - REMOVE_PT_GPREGS_FROM_STACK 8 - INTERRUPT_RETURN +.Lparanoid_exit_restore: + jmp restore_regs_and_return_to_kernel END(paranoid_exit) /* @@ -1222,10 +1247,13 @@ ENTRY(error_exit) jmp retint_user END(error_exit) -/* Runs on exception stack */ -/* XXX: broken on Xen PV */ +/* + * Runs on exception stack. Xen PV does not go through this path at all, + * so we can use real assembly here. + */ ENTRY(nmi) UNWIND_HINT_IRET_REGS + /* * We allow breakpoints in NMIs. If a breakpoint occurs, then * the iretq it performs will take us out of NMI context. @@ -1283,7 +1311,7 @@ ENTRY(nmi) * stacks lest we corrupt the "NMI executing" variable. */ - SWAPGS_UNSAFE_STACK + swapgs cld movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp @@ -1327,8 +1355,7 @@ ENTRY(nmi) * Return back to user mode. We must *not* do the normal exit * work, because we don't want to enable interrupts. */ - SWAPGS - jmp restore_regs_and_iret + jmp swapgs_restore_regs_and_return_to_usermode .Lnmi_from_kernel: /* @@ -1449,7 +1476,7 @@ nested_nmi_out: popq %rdx /* We are returning to kernel mode, so this cannot result in a fault. */ - INTERRUPT_RETURN + iretq first_nmi: /* Restore rdx. */ @@ -1480,7 +1507,7 @@ first_nmi: pushfq /* RFLAGS */ pushq $__KERNEL_CS /* CS */ pushq $1f /* RIP */ - INTERRUPT_RETURN /* continues at repeat_nmi below */ + iretq /* continues at repeat_nmi below */ UNWIND_HINT_IRET_REGS 1: #endif @@ -1543,29 +1570,34 @@ end_repeat_nmi: nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: - RESTORE_EXTRA_REGS - RESTORE_C_REGS + POP_EXTRA_REGS + POP_C_REGS - /* Point RSP at the "iret" frame. */ - REMOVE_PT_GPREGS_FROM_STACK 6*8 + /* + * Skip orig_ax and the "outermost" frame to point RSP at the "iret" + * at the "iret" frame. + */ + addq $6*8, %rsp /* * Clear "NMI executing". Set DF first so that we can easily * distinguish the remaining code between here and IRET from - * the SYSCALL entry and exit paths. On a native kernel, we - * could just inspect RIP, but, on paravirt kernels, - * INTERRUPT_RETURN can translate into a jump into a - * hypercall page. + * the SYSCALL entry and exit paths. + * + * We arguably should just inspect RIP instead, but I (Andy) wrote + * this code when I had the misapprehension that Xen PV supported + * NMIs, and Xen PV would break that approach. */ std movq $0, 5*8(%rsp) /* clear "NMI executing" */ /* - * INTERRUPT_RETURN reads the "iret" frame and exits the NMI - * stack in a single instruction. We are returning to kernel - * mode, so this cannot result in a fault. + * iretq reads the "iret" frame and exits the NMI stack in a + * single instruction. We are returning to kernel mode, so this + * cannot result in a fault. Similarly, we don't need to worry + * about espfix64 on the way back to kernel mode. */ - INTERRUPT_RETURN + iretq END(nmi) ENTRY(ignore_sysret) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index e26c25ca7756..568e130d932c 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Compatibility mode system call entry point for x86-64. * @@ -336,8 +337,7 @@ ENTRY(entry_INT80_compat) /* Go back to user mode. */ TRACE_IRQS_ON - SWAPGS - jmp restore_regs_and_iret + jmp swapgs_restore_regs_and_return_to_usermode END(entry_INT80_compat) ENTRY(stub32_clone) diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 8f895ee13a1c..95c294963612 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* System call table for i386. */ #include <linux/linkage.h> diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 9dbc5abb6162..9c09775e589d 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* System call table for x86-64. */ #include <linux/linkage.h> diff --git a/arch/x86/entry/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile index 57aa59fd140c..6fb9b57ed5ba 100644 --- a/arch/x86/entry/syscalls/Makefile +++ b/arch/x86/entry/syscalls/Makefile @@ -1,5 +1,6 @@ -out := $(obj)/../../include/generated/asm -uapi := $(obj)/../../include/generated/uapi/asm +# SPDX-License-Identifier: GPL-2.0 +out := arch/$(SRCARCH)/include/generated/asm +uapi := arch/$(SRCARCH)/include/generated/uapi/asm # Create output directory if not already present _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \ diff --git a/arch/x86/entry/syscalls/syscallhdr.sh b/arch/x86/entry/syscalls/syscallhdr.sh index 31fd5f1f38f7..12fbbcfe7ef3 100644 --- a/arch/x86/entry/syscalls/syscallhdr.sh +++ b/arch/x86/entry/syscalls/syscallhdr.sh @@ -1,4 +1,5 @@ #!/bin/sh +# SPDX-License-Identifier: GPL-2.0 in="$1" out="$2" diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh index 751d1f992630..d71ef4bd3615 100644 --- a/arch/x86/entry/syscalls/syscalltbl.sh +++ b/arch/x86/entry/syscalls/syscalltbl.sh @@ -1,4 +1,5 @@ #!/bin/sh +# SPDX-License-Identifier: GPL-2.0 in="$1" out="$2" diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index d5409660f5de..1943aebadede 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Building vDSO images for x86. # @@ -129,10 +130,6 @@ $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1 -# This makes sure the $(obj) subdirectory exists even though vdso32/ -# is not a kbuild sub-make subdirectory. -override obj-dirs = $(dir $(obj)) $(obj)/vdso32/ - targets += vdso32/vdso32.lds targets += vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o targets += vdso32/vclock_gettime.o diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index fa8dbfcf7ed3..11b13c4b43d5 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -318,7 +318,7 @@ int gettimeofday(struct timeval *, struct timezone *) notrace time_t __vdso_time(time_t *t) { /* This is atomic on x86 so we don't need any locks. */ - time_t result = ACCESS_ONCE(gtod->wall_time_sec); + time_t result = READ_ONCE(gtod->wall_time_sec); if (t) *t = result; diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index 8ebb4b6454fe..acfd5ba7d943 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <asm/vdso.h> /* diff --git a/arch/x86/entry/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S index 6807932643c2..d3a2dce4cfa9 100644 --- a/arch/x86/entry/vdso/vdso.lds.S +++ b/arch/x86/entry/vdso/vdso.lds.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Linker script for 64-bit vDSO. * We #include the file to define the layout details. diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 0780a443a53b..4674f58581a1 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -65,6 +65,7 @@ #include <linux/elf.h> #include <linux/types.h> +#include <linux/kernel.h> const char *outfilename; @@ -151,7 +152,7 @@ extern void bad_put_le(void); PLE(x, val, 64, PLE(x, val, 32, PLE(x, val, 16, LAST_PLE(x, val)))) -#define NSYMS (sizeof(required_syms) / sizeof(required_syms[0])) +#define NSYMS ARRAY_SIZE(required_syms) #define BITSFUNC3(name, bits, suffix) name##bits##suffix #define BITSFUNC2(name, bits, suffix) BITSFUNC3(name, bits, suffix) diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h index 3dab75f2a673..fa847a620f40 100644 --- a/arch/x86/entry/vdso/vdso2c.h +++ b/arch/x86/entry/vdso/vdso2c.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * This file is included twice from vdso2c.c. It generates code for 32-bit * and 64-bit vDSOs. We need both for 64-bit builds, since 32-bit vDSOs diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 3f9d1a83891a..42d4c89f990e 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * (C) Copyright 2002 Linus Torvalds * Portions based on the vdso-randomization code from exec-shield: diff --git a/arch/x86/entry/vdso/vdso32/note.S b/arch/x86/entry/vdso/vdso32/note.S index c83f25734696..9fd51f206314 100644 --- a/arch/x86/entry/vdso/vdso32/note.S +++ b/arch/x86/entry/vdso/vdso32/note.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. * Here we can supply some information useful to userland. diff --git a/arch/x86/entry/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S index 20633e026e82..c3233ee98a6b 100644 --- a/arch/x86/entry/vdso/vdso32/sigreturn.S +++ b/arch/x86/entry/vdso/vdso32/sigreturn.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <asm/unistd_32.h> #include <asm/asm-offsets.h> diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S index ed4bc9731cbb..263d7433dea8 100644 --- a/arch/x86/entry/vdso/vdso32/system_call.S +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * AT_SYSINFO entry point */ diff --git a/arch/x86/entry/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c index 87a86e017f0e..7780bbfb06ef 100644 --- a/arch/x86/entry/vdso/vdso32/vclock_gettime.c +++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #define BUILD_VDSO32 #ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE diff --git a/arch/x86/entry/vdso/vdso32/vdso32.lds.S b/arch/x86/entry/vdso/vdso32/vdso32.lds.S index 31056cf294bf..422764a81d32 100644 --- a/arch/x86/entry/vdso/vdso32/vdso32.lds.S +++ b/arch/x86/entry/vdso/vdso32/vdso32.lds.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Linker script for 32-bit vDSO. * We #include the file to define the layout details. diff --git a/arch/x86/entry/vdso/vdsox32.lds.S b/arch/x86/entry/vdso/vdsox32.lds.S index 697c11ece90c..05cd1c5c4a15 100644 --- a/arch/x86/entry/vdso/vdsox32.lds.S +++ b/arch/x86/entry/vdso/vdsox32.lds.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Linker script for x32 vDSO. * We #include the file to define the layout details. diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 1911310959f8..5b8b556dbb12 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -112,12 +112,13 @@ static int vvar_fault(const struct vm_special_mapping *sm, __pa_symbol(&__vvar_page) >> PAGE_SHIFT); } else if (sym_offset == image->sym_pvclock_page) { struct pvclock_vsyscall_time_info *pvti = - pvclock_pvti_cpu0_va(); + pvclock_get_pvti_cpu0_va(); if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) { - ret = vm_insert_pfn( + ret = vm_insert_pfn_prot( vma, vmf->address, - __pa(pvti) >> PAGE_SHIFT); + __pa(pvti) >> PAGE_SHIFT, + pgprot_decrypted(vma->vm_page_prot)); } } else if (sym_offset == image->sym_hvclock_page) { struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page(); diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index ce1d7534fa53..f279ba2643dc 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net> * diff --git a/arch/x86/entry/vsyscall/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c index 0fb3a104ac62..e1216dd95c04 100644 --- a/arch/x86/entry/vsyscall/vsyscall_gtod.c +++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE * Copyright 2003 Andi Kleen, SuSE Labs. diff --git a/arch/x86/entry/vsyscall/vsyscall_trace.h b/arch/x86/entry/vsyscall/vsyscall_trace.h index 9dd7359a38a8..3c3f9765a85c 100644 --- a/arch/x86/entry/vsyscall/vsyscall_trace.h +++ b/arch/x86/entry/vsyscall/vsyscall_trace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM vsyscall diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig index 98397db5ceae..9a7a1446cb3a 100644 --- a/arch/x86/events/Kconfig +++ b/arch/x86/events/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 menu "Performance monitoring" config PERF_EVENTS_INTEL_UNCORE diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile index b1da46f396e0..fe8795a67385 100644 --- a/arch/x86/events/amd/Makefile +++ b/arch/x86/events/amd/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_CPU_SUP_AMD) += core.o uncore.o obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c index 3641e24fdac5..38b5d41b0c37 100644 --- a/arch/x86/events/amd/iommu.c +++ b/arch/x86/events/amd/iommu.c @@ -405,7 +405,7 @@ const struct attribute_group *amd_iommu_attr_groups[] = { NULL, }; -static struct pmu iommu_pmu = { +static const struct pmu iommu_pmu __initconst = { .event_init = perf_iommu_event_init, .add = perf_iommu_add, .del = perf_iommu_del, diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 80534d3c2480..140d33288e78 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2118,7 +2118,7 @@ static int x86_pmu_event_init(struct perf_event *event) event->destroy(event); } - if (ACCESS_ONCE(x86_pmu.attr_rdpmc)) + if (READ_ONCE(x86_pmu.attr_rdpmc)) event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED; return err; @@ -2371,7 +2371,7 @@ static unsigned long get_segment_base(unsigned int segment) struct ldt_struct *ldt; /* IRQs are off, so this synchronizes with smp_store_release */ - ldt = lockless_dereference(current->active_mm->context.ldt); + ldt = READ_ONCE(current->active_mm->context.ldt); if (!ldt || idx >= ldt->nr_entries) return 0; diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile index e9d8520a801a..3468b0c1dc7c 100644 --- a/arch/x86/events/intel/Makefile +++ b/arch/x86/events/intel/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 16076eb34699..141e07b06216 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -546,9 +546,6 @@ static int bts_event_init(struct perf_event *event) if (event->attr.type != bts_pmu.type) return -ENOENT; - if (x86_add_exclusive(x86_lbr_exclusive_bts)) - return -EBUSY; - /* * BTS leaks kernel addresses even when CPL0 tracing is * disabled, so disallow intel_bts driver for unprivileged @@ -562,6 +559,9 @@ static int bts_event_init(struct perf_event *event) !capable(CAP_SYS_ADMIN)) return -EACCES; + if (x86_add_exclusive(x86_lbr_exclusive_bts)) + return -EBUSY; + ret = x86_reserve_hardware(); if (ret) { x86_del_exclusive(x86_lbr_exclusive_bts); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 829e89cfcee2..09c26a4f139c 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2958,6 +2958,10 @@ static unsigned long intel_pmu_free_running_flags(struct perf_event *event) if (event->attr.use_clockid) flags &= ~PERF_SAMPLE_TIME; + if (!event->attr.exclude_kernel) + flags &= ~PERF_SAMPLE_REGS_USER; + if (event->attr.sample_regs_user & ~PEBS_REGS) + flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR); return flags; } @@ -3730,6 +3734,19 @@ EVENT_ATTR_STR(cycles-t, cycles_t, "event=0x3c,in_tx=1"); EVENT_ATTR_STR(cycles-ct, cycles_ct, "event=0x3c,in_tx=1,in_tx_cp=1"); static struct attribute *hsw_events_attrs[] = { + EVENT_PTR(mem_ld_hsw), + EVENT_PTR(mem_st_hsw), + EVENT_PTR(td_slots_issued), + EVENT_PTR(td_slots_retired), + EVENT_PTR(td_fetch_bubbles), + EVENT_PTR(td_total_slots), + EVENT_PTR(td_total_slots_scale), + EVENT_PTR(td_recovery_bubbles), + EVENT_PTR(td_recovery_bubbles_scale), + NULL +}; + +static struct attribute *hsw_tsx_events_attrs[] = { EVENT_PTR(tx_start), EVENT_PTR(tx_commit), EVENT_PTR(tx_abort), @@ -3742,18 +3759,16 @@ static struct attribute *hsw_events_attrs[] = { EVENT_PTR(el_conflict), EVENT_PTR(cycles_t), EVENT_PTR(cycles_ct), - EVENT_PTR(mem_ld_hsw), - EVENT_PTR(mem_st_hsw), - EVENT_PTR(td_slots_issued), - EVENT_PTR(td_slots_retired), - EVENT_PTR(td_fetch_bubbles), - EVENT_PTR(td_total_slots), - EVENT_PTR(td_total_slots_scale), - EVENT_PTR(td_recovery_bubbles), - EVENT_PTR(td_recovery_bubbles_scale), NULL }; +static __init struct attribute **get_hsw_events_attrs(void) +{ + return boot_cpu_has(X86_FEATURE_RTM) ? + merge_attr(hsw_events_attrs, hsw_tsx_events_attrs) : + hsw_events_attrs; +} + static ssize_t freeze_on_smi_show(struct device *cdev, struct device_attribute *attr, char *buf) @@ -4182,7 +4197,7 @@ __init int intel_pmu_init(void) x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; - x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.cpu_events = get_hsw_events_attrs(); x86_pmu.lbr_double_abort = true; extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? hsw_format_attr : nhm_format_attr; @@ -4221,7 +4236,7 @@ __init int intel_pmu_init(void) x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; - x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.cpu_events = get_hsw_events_attrs(); x86_pmu.limit_period = bdw_limit_period; extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? hsw_format_attr : nhm_format_attr; @@ -4279,7 +4294,7 @@ __init int intel_pmu_init(void) extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? hsw_format_attr : nhm_format_attr; extra_attr = merge_attr(extra_attr, skl_format_attr); - x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.cpu_events = get_hsw_events_attrs(); intel_pmu_pebs_data_source_skl( boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X); pr_cont("Skylake events, "); @@ -4409,10 +4424,9 @@ static __init int fixup_ht_bug(void) return 0; } - if (lockup_detector_suspend() != 0) { - pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n"); - return 0; - } + cpus_read_lock(); + + hardlockup_detector_perf_stop(); x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); @@ -4420,9 +4434,7 @@ static __init int fixup_ht_bug(void) x86_pmu.commit_scheduling = NULL; x86_pmu.stop_scheduling = NULL; - lockup_detector_resume(); - - cpus_read_lock(); + hardlockup_detector_perf_restart(); for_each_online_cpu(c) free_excl_cntrs(c); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 4cf100ff2a37..72db0664a53d 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -552,6 +552,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates), @@ -560,6 +561,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates), + + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index e1965e5ff570..3674a4b6f8bd 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> #include <linux/types.h> #include <linux/slab.h> diff --git a/arch/x86/events/intel/knc.c b/arch/x86/events/intel/knc.c index 548d5f774b07..618001c208e8 100644 --- a/arch/x86/events/intel/knc.c +++ b/arch/x86/events/intel/knc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Driver for Intel Xeon Phi "Knights Corner" PMU */ #include <linux/perf_event.h> diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 8a6bbacd17dc..ae64d0b69729 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/perf_event.h> #include <linux/types.h> diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c index 1f5c47ab4c65..a5604c352930 100644 --- a/arch/x86/events/intel/p6.c +++ b/arch/x86/events/intel/p6.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/perf_event.h> #include <linux/types.h> diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 8e2457cb6b4a..005908ee9333 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -775,6 +775,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init), + + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init), {}, }; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 1c5390f1cf09..7874c980d569 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -822,7 +822,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) pmus[i].type = type; pmus[i].boxes = kzalloc(size, GFP_KERNEL); if (!pmus[i].boxes) - return -ENOMEM; + goto err; } type->pmus = pmus; @@ -836,7 +836,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) + sizeof(*attr_group), GFP_KERNEL); if (!attr_group) - return -ENOMEM; + goto err; attrs = (struct attribute **)(attr_group + 1); attr_group->name = "events"; @@ -849,7 +849,15 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) } type->pmu_group = &uncore_pmu_attr_group; + return 0; + +err: + for (i = 0; i < type->num_boxes; i++) + kfree(pmus[i].boxes); + kfree(pmus); + + return -ENOMEM; } static int __init @@ -967,10 +975,10 @@ static void uncore_pci_remove(struct pci_dev *pdev) int i, phys_id, pkg; phys_id = uncore_pcibus_to_physid(pdev->bus); - pkg = topology_phys_to_logical_pkg(phys_id); box = pci_get_drvdata(pdev); if (!box) { + pkg = topology_phys_to_logical_pkg(phys_id); for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { if (uncore_extra_pci_dev[pkg].dev[i] == pdev) { uncore_extra_pci_dev[pkg].dev[i] = NULL; @@ -986,7 +994,7 @@ static void uncore_pci_remove(struct pci_dev *pdev) return; pci_set_drvdata(pdev, NULL); - pmu->boxes[pkg] = NULL; + pmu->boxes[box->pkgid] = NULL; if (atomic_dec_return(&pmu->activeboxes) == 0) uncore_pmu_unregister(pmu); uncore_box_exit(box); diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index df5989f27b1b..414dc7e7c950 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <linux/slab.h> #include <linux/pci.h> #include <asm/apicdef.h> @@ -99,7 +100,7 @@ struct intel_uncore_extra_reg { struct intel_uncore_box { int pci_phys_id; - int pkgid; + int pkgid; /* Logical package ID */ int n_active; /* number of active events */ int n_events; int cpu; /* cpu to collect events */ diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c index 6a5cbe90f859..93e7a8397cde 100644 --- a/arch/x86/events/intel/uncore_nhmex.c +++ b/arch/x86/events/intel/uncore_nhmex.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Nehalem-EX/Westmere-EX uncore support */ #include "uncore.h" diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index db1127ce685e..aee5e8496be4 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Nehalem/SandBridge/Haswell/Broadwell/Skylake uncore support */ #include "uncore.h" diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index db1fe377e6dd..6d8044ab1060 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* SandyBridge-EP/IvyTown uncore support */ #include "uncore.h" @@ -1056,7 +1057,7 @@ static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_eve if (reg1->idx != EXTRA_REG_NONE) { int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; - int pkg = topology_phys_to_logical_pkg(box->pci_phys_id); + int pkg = box->pkgid; struct pci_dev *filter_pdev = uncore_extra_pci_dev[pkg].dev[idx]; if (filter_pdev) { @@ -3034,11 +3035,19 @@ static struct intel_uncore_type *bdx_msr_uncores[] = { NULL, }; +/* Bit 7 'Use Occupancy' is not available for counter 0 on BDX */ +static struct event_constraint bdx_uncore_pcu_constraints[] = { + EVENT_CONSTRAINT(0x80, 0xe, 0x80), + EVENT_CONSTRAINT_END +}; + void bdx_uncore_cpu_init(void) { if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; uncore_msr_uncores = bdx_msr_uncores; + + hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints; } static struct intel_uncore_type bdx_uncore_ha = { @@ -3462,7 +3471,7 @@ static struct intel_uncore_ops skx_uncore_iio_ops = { static struct intel_uncore_type skx_uncore_iio = { .name = "iio", .num_counters = 4, - .num_boxes = 5, + .num_boxes = 6, .perf_ctr_bits = 48, .event_ctl = SKX_IIO0_MSR_PMON_CTL0, .perf_ctr = SKX_IIO0_MSR_PMON_CTR0, @@ -3492,7 +3501,7 @@ static const struct attribute_group skx_uncore_format_group = { static struct intel_uncore_type skx_uncore_irp = { .name = "irp", .num_counters = 2, - .num_boxes = 5, + .num_boxes = 6, .perf_ctr_bits = 48, .event_ctl = SKX_IRP0_MSR_PMON_CTL0, .perf_ctr = SKX_IRP0_MSR_PMON_CTR0, diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 4bb3ec69e8ea..14efaa0e8684 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/perf_event.h> #include <asm/intel-family.h> @@ -63,6 +64,14 @@ static bool test_intel(int idx) case INTEL_FAM6_ATOM_SILVERMONT1: case INTEL_FAM6_ATOM_SILVERMONT2: case INTEL_FAM6_ATOM_AIRMONT: + + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_ATOM_DENVERTON: + + case INTEL_FAM6_ATOM_GEMINI_LAKE: + + case INTEL_FAM6_XEON_PHI_KNL: + case INTEL_FAM6_XEON_PHI_KNM: if (idx == PERF_MSR_SMI) return true; break; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 4196f81ec0e1..f7aaadf9331f 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -85,13 +85,15 @@ struct amd_nb { * Flags PEBS can handle without an PMI. * * TID can only be handled by flushing at context switch. + * REGS_USER can be handled for events limited to ring 3. * */ #define PEBS_FREERUNNING_FLAGS \ (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ - PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR) + PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \ + PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER) /* * A debug store configuration. @@ -110,6 +112,26 @@ struct debug_store { u64 pebs_event_reset[MAX_PEBS_EVENTS]; }; +#define PEBS_REGS \ + (PERF_REG_X86_AX | \ + PERF_REG_X86_BX | \ + PERF_REG_X86_CX | \ + PERF_REG_X86_DX | \ + PERF_REG_X86_DI | \ + PERF_REG_X86_SI | \ + PERF_REG_X86_SP | \ + PERF_REG_X86_BP | \ + PERF_REG_X86_IP | \ + PERF_REG_X86_FLAGS | \ + PERF_REG_X86_R8 | \ + PERF_REG_X86_R9 | \ + PERF_REG_X86_R10 | \ + PERF_REG_X86_R11 | \ + PERF_REG_X86_R12 | \ + PERF_REG_X86_R13 | \ + PERF_REG_X86_R14 | \ + PERF_REG_X86_R15) + /* * Per register state. */ diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 1a8eb550c40f..189a398290db 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -85,6 +85,8 @@ EXPORT_SYMBOL_GPL(hyperv_cs); u32 *hv_vp_index; EXPORT_SYMBOL_GPL(hv_vp_index); +u32 hv_max_vp_index; + static int hv_cpu_init(unsigned int cpu) { u64 msr_vp_index; @@ -93,6 +95,9 @@ static int hv_cpu_init(unsigned int cpu) hv_vp_index[smp_processor_id()] = msr_vp_index; + if (msr_vp_index > hv_max_vp_index) + hv_max_vp_index = msr_vp_index; + return 0; } @@ -108,7 +113,7 @@ void hyperv_init(void) u64 guest_id; union hv_x64_msr_hypercall_contents hypercall_msr; - if (x86_hyper != &x86_hyper_ms_hyperv) + if (x86_hyper_type != X86_HYPER_MS_HYPERV) return; /* Allocate percpu VP index */ @@ -205,9 +210,10 @@ void hyperv_cleanup(void) } EXPORT_SYMBOL_GPL(hyperv_cleanup); -void hyperv_report_panic(struct pt_regs *regs) +void hyperv_report_panic(struct pt_regs *regs, long err) { static bool panic_reported; + u64 guest_id; /* * We prefer to report panic on 'die' chain as we have proper @@ -218,11 +224,13 @@ void hyperv_report_panic(struct pt_regs *regs) return; panic_reported = true; - wrmsrl(HV_X64_MSR_CRASH_P0, regs->ip); - wrmsrl(HV_X64_MSR_CRASH_P1, regs->ax); - wrmsrl(HV_X64_MSR_CRASH_P2, regs->bx); - wrmsrl(HV_X64_MSR_CRASH_P3, regs->cx); - wrmsrl(HV_X64_MSR_CRASH_P4, regs->dx); + rdmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id); + + wrmsrl(HV_X64_MSR_CRASH_P0, err); + wrmsrl(HV_X64_MSR_CRASH_P1, guest_id); + wrmsrl(HV_X64_MSR_CRASH_P2, regs->ip); + wrmsrl(HV_X64_MSR_CRASH_P3, regs->ax); + wrmsrl(HV_X64_MSR_CRASH_P4, regs->sp); /* * Let Hyper-V know there is crash data available diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 39e7f6e50919..9cc9e1c1e2db 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -36,9 +36,9 @@ struct hv_flush_pcpu_ex { /* Each gva in gva_list encodes up to 4096 pages to flush */ #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE) -static struct hv_flush_pcpu __percpu *pcpu_flush; +static struct hv_flush_pcpu __percpu **pcpu_flush; -static struct hv_flush_pcpu_ex __percpu *pcpu_flush_ex; +static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex; /* * Fills in gva_list starting from offset. Returns the number of items added. @@ -76,6 +76,18 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, { int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; + /* valid_bank_mask can represent up to 64 banks */ + if (hv_max_vp_index / 64 >= 64) + return 0; + + /* + * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex + * structs are not cleared between calls, we risk flushing unneeded + * vCPUs otherwise. + */ + for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++) + flush->hv_vp_set.bank_contents[vcpu_bank] = 0; + /* * Some banks may end up being empty but this is acceptable. */ @@ -83,11 +95,6 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, vcpu = hv_cpu_number_to_vp_number(cpu); vcpu_bank = vcpu / 64; vcpu_offset = vcpu % 64; - - /* valid_bank_mask can represent up to 64 banks */ - if (vcpu_bank >= 64) - return 0; - __set_bit(vcpu_offset, (unsigned long *) &flush->hv_vp_set.bank_contents[vcpu_bank]); if (vcpu_bank >= nr_bank) @@ -102,6 +109,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, const struct flush_tlb_info *info) { int cpu, vcpu, gva_n, max_gvas; + struct hv_flush_pcpu **flush_pcpu; struct hv_flush_pcpu *flush; u64 status = U64_MAX; unsigned long flags; @@ -116,7 +124,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, local_irq_save(flags); - flush = this_cpu_ptr(pcpu_flush); + flush_pcpu = this_cpu_ptr(pcpu_flush); + + if (unlikely(!*flush_pcpu)) + *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + + flush = *flush_pcpu; + + if (unlikely(!flush)) { + local_irq_restore(flags); + goto do_native; + } if (info->mm) { flush->address_space = virt_to_phys(info->mm->pgd); @@ -173,6 +191,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, const struct flush_tlb_info *info) { int nr_bank = 0, max_gvas, gva_n; + struct hv_flush_pcpu_ex **flush_pcpu; struct hv_flush_pcpu_ex *flush; u64 status = U64_MAX; unsigned long flags; @@ -187,7 +206,17 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, local_irq_save(flags); - flush = this_cpu_ptr(pcpu_flush_ex); + flush_pcpu = this_cpu_ptr(pcpu_flush_ex); + + if (unlikely(!*flush_pcpu)) + *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + + flush = *flush_pcpu; + + if (unlikely(!flush)) { + local_irq_restore(flags); + goto do_native; + } if (info->mm) { flush->address_space = virt_to_phys(info->mm->pgd); @@ -222,18 +251,18 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY; status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, - 0, nr_bank + 2, flush, NULL); + 0, nr_bank, flush, NULL); } else if (info->end && ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) { status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, - 0, nr_bank + 2, flush, NULL); + 0, nr_bank, flush, NULL); } else { gva_n = fill_gva_list(flush->gva_list, nr_bank, info->start, info->end); status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX, - gva_n, nr_bank + 2, flush, NULL); + gva_n, nr_bank, flush, NULL); } local_irq_restore(flags); @@ -266,7 +295,7 @@ void hyper_alloc_mmu(void) return; if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - pcpu_flush = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); + pcpu_flush = alloc_percpu(struct hv_flush_pcpu *); else - pcpu_flush_ex = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); + pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *); } diff --git a/arch/x86/ia32/audit.c b/arch/x86/ia32/audit.c index 2eccc8932ae6..3d21eab7aaed 100644 --- a/arch/x86/ia32/audit.c +++ b/arch/x86/ia32/audit.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <asm/unistd_32.h> unsigned ia32_dir_class[] = { diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index e0bb46c02857..41c671854642 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/arch/x86_64/ia32/ia32_signal.c * @@ -231,7 +232,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, ksig->ka.sa.sa_restorer) sp = (unsigned long) ksig->ka.sa.sa_restorer; - if (fpu->fpstate_active) { + if (fpu->initialized) { unsigned long fx_aligned, math_size; sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 47956c6a4fd8..96cd33bbfc85 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * sys_ia32.c: Conversion between 32bit and 64bit native syscalls. Based on * sys_sparc32 diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 72d867f6b518..8d0ec9df1cbe 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -150,6 +150,8 @@ static inline void disable_acpi(void) { } extern int x86_acpi_numa_init(void); #endif /* CONFIG_ACPI_NUMA */ +#define acpi_unlazy_tlb(x) leave_mm(x) + #ifdef CONFIG_ACPI_APEI static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) { diff --git a/arch/x86/include/asm/agp.h b/arch/x86/include/asm/agp.h index eec2a70d4376..8e25bf4f323a 100644 --- a/arch/x86/include/asm/agp.h +++ b/arch/x86/include/asm/agp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_AGP_H #define _ASM_X86_AGP_H diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index e7636bac7372..31b627b43a8e 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ALTERNATIVE_ASM_H #define _ASM_X86_ALTERNATIVE_ASM_H @@ -62,8 +63,10 @@ #define new_len2 145f-144f /* - * max without conditionals. Idea adapted from: + * gas compatible max based on the idea from: * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax + * + * The additional "-" is needed because gas uses a "true" value of -1. */ #define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 1b020381ab38..dbfd0854651f 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ALTERNATIVE_H #define _ASM_X86_ALTERNATIVE_H @@ -103,12 +104,12 @@ static inline int alternatives_text_reserved(void *start, void *end) alt_end_marker ":\n" /* - * max without conditionals. Idea adapted from: + * gas compatible max based on the idea from: * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax * - * The additional "-" is needed because gas works with s32s. + * The additional "-" is needed because gas uses a "true" value of -1. */ -#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") - (" b ")))))" +#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))" /* * Pad the second replacement alternative with additional NOPs if it is @@ -218,10 +219,9 @@ static inline int alternatives_text_reserved(void *start, void *end) #define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \ output, input...) \ { \ - register void *__sp asm(_ASM_SP); \ asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ "call %P[new2]", feature2) \ - : output, "+r" (__sp) \ + : output, ASM_CALL_CONSTRAINT \ : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ [new2] "i" (newfunc2), ## input); \ } diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index da181ad1d5f8..fddb6d26239f 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_AMD_NB_H #define _ASM_X86_AMD_NB_H diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 5f01671c68f2..a9e57f08bfa6 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -53,6 +53,15 @@ extern int local_apic_timer_c2_ok; extern int disable_apic; extern unsigned int lapic_timer_frequency; +extern enum apic_intr_mode_id apic_intr_mode; +enum apic_intr_mode_id { + APIC_PIC, + APIC_VIRTUAL_WIRE, + APIC_VIRTUAL_WIRE_NO_CONFIG, + APIC_SYMMETRIC_IO, + APIC_SYMMETRIC_IO_NO_ROUTING +}; + #ifdef CONFIG_SMP extern void __inquire_remote_apic(int apicid); #else /* CONFIG_SMP */ @@ -127,14 +136,13 @@ extern void disconnect_bsp_APIC(int virt_wire_setup); extern void disable_local_APIC(void); extern void lapic_shutdown(void); extern void sync_Arb_IDs(void); -extern void init_bsp_APIC(void); +extern void apic_intr_mode_init(void); extern void setup_local_APIC(void); extern void init_apic_mappings(void); void register_lapic_address(unsigned long address); extern void setup_boot_APIC_clock(void); extern void setup_secondary_APIC_clock(void); extern void lapic_update_tsc_freq(void); -extern int APIC_init_uniprocessor(void); #ifdef CONFIG_X86_64 static inline int apic_force_enable(unsigned long addr) @@ -145,7 +153,7 @@ static inline int apic_force_enable(unsigned long addr) extern int apic_force_enable(unsigned long addr); #endif -extern int apic_bsp_setup(bool upmode); +extern void apic_bsp_setup(bool upmode); extern void apic_ap_setup(void); /* @@ -161,6 +169,10 @@ static inline int apic_is_clustered_box(void) #endif extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask); +extern void lapic_assign_system_vectors(void); +extern void lapic_assign_legacy_vector(unsigned int isairq, bool replace); +extern void lapic_online(void); +extern void lapic_offline(void); #else /* !CONFIG_X86_LOCAL_APIC */ static inline void lapic_shutdown(void) { } @@ -170,6 +182,9 @@ static inline void disable_local_APIC(void) { } # define setup_boot_APIC_clock x86_init_noop # define setup_secondary_APIC_clock x86_init_noop static inline void lapic_update_tsc_freq(void) { } +static inline void apic_intr_mode_init(void) { } +static inline void lapic_assign_system_vectors(void) { } +static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { } #endif /* !CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_X2APIC @@ -265,73 +280,63 @@ struct irq_data; * James Cleverdon. */ struct apic { - char *name; - - int (*probe)(void); - int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id); - int (*apic_id_valid)(int apicid); - int (*apic_id_registered)(void); - - u32 irq_delivery_mode; - u32 irq_dest_mode; - - const struct cpumask *(*target_cpus)(void); - - int disable_esr; - - int dest_logical; - unsigned long (*check_apicid_used)(physid_mask_t *map, int apicid); - - void (*vector_allocation_domain)(int cpu, struct cpumask *retmask, - const struct cpumask *mask); - void (*init_apic_ldr)(void); - - void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap); - - void (*setup_apic_routing)(void); - int (*cpu_present_to_apicid)(int mps_cpu); - void (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap); - int (*check_phys_apicid_present)(int phys_apicid); - int (*phys_pkg_id)(int cpuid_apic, int index_msb); - - unsigned int (*get_apic_id)(unsigned long x); - /* Can't be NULL on 64-bit */ - unsigned long (*set_apic_id)(unsigned int id); - - int (*cpu_mask_to_apicid)(const struct cpumask *cpumask, - struct irq_data *irqdata, - unsigned int *apicid); - - /* ipi */ - void (*send_IPI)(int cpu, int vector); - void (*send_IPI_mask)(const struct cpumask *mask, int vector); - void (*send_IPI_mask_allbutself)(const struct cpumask *mask, - int vector); - void (*send_IPI_allbutself)(int vector); - void (*send_IPI_all)(int vector); - void (*send_IPI_self)(int vector); + /* Hotpath functions first */ + void (*eoi_write)(u32 reg, u32 v); + void (*native_eoi_write)(u32 reg, u32 v); + void (*write)(u32 reg, u32 v); + u32 (*read)(u32 reg); + + /* IPI related functions */ + void (*wait_icr_idle)(void); + u32 (*safe_wait_icr_idle)(void); + + void (*send_IPI)(int cpu, int vector); + void (*send_IPI_mask)(const struct cpumask *mask, int vector); + void (*send_IPI_mask_allbutself)(const struct cpumask *msk, int vec); + void (*send_IPI_allbutself)(int vector); + void (*send_IPI_all)(int vector); + void (*send_IPI_self)(int vector); + + /* dest_logical is used by the IPI functions */ + u32 dest_logical; + u32 disable_esr; + u32 irq_delivery_mode; + u32 irq_dest_mode; + + /* Functions and data related to vector allocation */ + void (*vector_allocation_domain)(int cpu, struct cpumask *retmask, + const struct cpumask *mask); + int (*cpu_mask_to_apicid)(const struct cpumask *cpumask, + struct irq_data *irqdata, + unsigned int *apicid); + u32 (*calc_dest_apicid)(unsigned int cpu); + + /* ICR related functions */ + u64 (*icr_read)(void); + void (*icr_write)(u32 low, u32 high); + + /* Probe, setup and smpboot functions */ + int (*probe)(void); + int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id); + int (*apic_id_valid)(int apicid); + int (*apic_id_registered)(void); + + bool (*check_apicid_used)(physid_mask_t *map, int apicid); + void (*init_apic_ldr)(void); + void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap); + void (*setup_apic_routing)(void); + int (*cpu_present_to_apicid)(int mps_cpu); + void (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap); + int (*check_phys_apicid_present)(int phys_apicid); + int (*phys_pkg_id)(int cpuid_apic, int index_msb); + + u32 (*get_apic_id)(unsigned long x); + u32 (*set_apic_id)(unsigned int id); /* wakeup_secondary_cpu */ - int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); + int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); - void (*inquire_remote_apic)(int apicid); - - /* apic ops */ - u32 (*read)(u32 reg); - void (*write)(u32 reg, u32 v); - /* - * ->eoi_write() has the same signature as ->write(). - * - * Drivers can support both ->eoi_write() and ->write() by passing the same - * callback value. Kernel can override ->eoi_write() and fall back - * on write for EOI. - */ - void (*eoi_write)(u32 reg, u32 v); - void (*native_eoi_write)(u32 reg, u32 v); - u64 (*icr_read)(void); - void (*icr_write)(u32 low, u32 high); - void (*wait_icr_idle)(void); - u32 (*safe_wait_icr_idle)(void); + void (*inquire_remote_apic)(int apicid); #ifdef CONFIG_X86_32 /* @@ -346,6 +351,7 @@ struct apic { */ int (*x86_32_early_logical_apicid)(int cpu); #endif + char *name; }; /* @@ -380,6 +386,7 @@ extern struct apic *__apicdrivers[], *__apicdrivers_end[]; */ #ifdef CONFIG_SMP extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); +extern int lapic_can_unplug_cpu(void); #endif #ifdef CONFIG_X86_LOCAL_APIC @@ -463,84 +470,33 @@ static inline unsigned default_get_apic_id(unsigned long x) extern void apic_send_IPI_self(int vector); DECLARE_PER_CPU(int, x2apic_extra_bits); - -extern int default_cpu_present_to_apicid(int mps_cpu); -extern int default_check_phys_apicid_present(int phys_apicid); #endif extern void generic_bigsmp_probe(void); - #ifdef CONFIG_X86_LOCAL_APIC #include <asm/smp.h> #define APIC_DFR_VALUE (APIC_DFR_FLAT) -static inline const struct cpumask *default_target_cpus(void) -{ -#ifdef CONFIG_SMP - return cpu_online_mask; -#else - return cpumask_of(0); -#endif -} - -static inline const struct cpumask *online_target_cpus(void) -{ - return cpu_online_mask; -} - DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid); +extern struct apic apic_noop; static inline unsigned int read_apic_id(void) { - unsigned int reg; - - reg = apic_read(APIC_ID); + unsigned int reg = apic_read(APIC_ID); return apic->get_apic_id(reg); } -static inline int default_apic_id_valid(int apicid) -{ - return (apicid < 255); -} - +extern int default_apic_id_valid(int apicid); extern int default_acpi_madt_oem_check(char *, char *); - extern void default_setup_apic_routing(void); -extern struct apic apic_noop; - -#ifdef CONFIG_X86_32 - -static inline int noop_x86_32_early_logical_apicid(int cpu) -{ - return BAD_APICID; -} - -/* - * Set up the logical destination ID. - * - * Intel recommends to set DFR, LDR and TPR before enabling - * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel - * document number 292116). So here it goes... - */ -extern void default_init_apic_ldr(void); - -static inline int default_apic_id_registered(void) -{ - return physid_isset(read_apic_id(), phys_cpu_present_map); -} - -static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - -#endif +extern u32 apic_default_calc_apicid(unsigned int cpu); +extern u32 apic_flat_calc_apicid(unsigned int cpu); extern int flat_cpu_mask_to_apicid(const struct cpumask *cpumask, struct irq_data *irqdata, @@ -548,71 +504,17 @@ extern int flat_cpu_mask_to_apicid(const struct cpumask *cpumask, extern int default_cpu_mask_to_apicid(const struct cpumask *cpumask, struct irq_data *irqdata, unsigned int *apicid); - -static inline void -flat_vector_allocation_domain(int cpu, struct cpumask *retmask, - const struct cpumask *mask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - cpumask_clear(retmask); - cpumask_bits(retmask)[0] = APIC_ALL_CPUS; -} - -static inline void -default_vector_allocation_domain(int cpu, struct cpumask *retmask, - const struct cpumask *mask) -{ - cpumask_copy(retmask, cpumask_of(cpu)); -} - -static inline unsigned long default_check_apicid_used(physid_mask_t *map, int apicid) -{ - return physid_isset(apicid, *map); -} - -static inline void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) -{ - *retmap = *phys_map; -} - -static inline int __default_cpu_present_to_apicid(int mps_cpu) -{ - if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu)) - return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu); - else - return BAD_APICID; -} - -static inline int -__default_check_phys_apicid_present(int phys_apicid) -{ - return physid_isset(phys_apicid, phys_cpu_present_map); -} - -#ifdef CONFIG_X86_32 -static inline int default_cpu_present_to_apicid(int mps_cpu) -{ - return __default_cpu_present_to_apicid(mps_cpu); -} - -static inline int -default_check_phys_apicid_present(int phys_apicid) -{ - return __default_check_phys_apicid_present(phys_apicid); -} -#else +extern bool default_check_apicid_used(physid_mask_t *map, int apicid); +extern void flat_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask); +extern void default_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask); +extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap); extern int default_cpu_present_to_apicid(int mps_cpu); extern int default_check_phys_apicid_present(int phys_apicid); -#endif #endif /* CONFIG_X86_LOCAL_APIC */ + extern void irq_enter(void); extern void irq_exit(void); diff --git a/arch/x86/include/asm/apic_flat_64.h b/arch/x86/include/asm/apic_flat_64.h index a2d312796440..d3a2b3876ce6 100644 --- a/arch/x86/include/asm/apic_flat_64.h +++ b/arch/x86/include/asm/apic_flat_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_APIC_FLAT_64_H #define _ASM_X86_APIC_FLAT_64_H diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index c46bb99d5fb2..05e694ed8386 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_APICDEF_H #define _ASM_X86_APICDEF_H diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index 93eebc636c76..4d4015ddcf26 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Machine specific APM BIOS functions for generic. * Split out from apm.c by Osamu Tomita <tomita@cinet.co.jp> diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h index e7cd63175de4..34a10b2d5b73 100644 --- a/arch/x86/include/asm/arch_hweight.h +++ b/arch/x86/include/asm/arch_hweight.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_HWEIGHT_H #define _ASM_X86_HWEIGHT_H diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h index 5b0579abb398..3ac991d81e74 100644 --- a/arch/x86/include/asm/archrandom.h +++ b/arch/x86/include/asm/archrandom.h @@ -45,7 +45,7 @@ static inline bool rdrand_long(unsigned long *v) bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { - asm volatile(RDRAND_LONG "\n\t" + asm volatile(RDRAND_LONG CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); if (ok) @@ -59,7 +59,7 @@ static inline bool rdrand_int(unsigned int *v) bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { - asm volatile(RDRAND_INT "\n\t" + asm volatile(RDRAND_INT CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); if (ok) @@ -71,7 +71,7 @@ static inline bool rdrand_int(unsigned int *v) static inline bool rdseed_long(unsigned long *v) { bool ok; - asm volatile(RDSEED_LONG "\n\t" + asm volatile(RDSEED_LONG CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); return ok; @@ -80,7 +80,7 @@ static inline bool rdseed_long(unsigned long *v) static inline bool rdseed_int(unsigned int *v) { bool ok; - asm volatile(RDSEED_INT "\n\t" + asm volatile(RDSEED_INT CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); return ok; diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 830b19dbfa31..ff700d81e91e 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <asm/ftrace.h> #include <linux/uaccess.h> #include <asm/string.h> diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 676ee5807d86..219faaec51df 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ASM_H #define _ASM_X86_ASM_H @@ -11,10 +12,12 @@ # define __ASM_FORM_COMMA(x) " " #x "," #endif -#ifdef CONFIG_X86_32 +#ifndef __x86_64__ +/* 32 bit */ # define __ASM_SEL(a,b) __ASM_FORM(a) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a) #else +/* 64 bit */ # define __ASM_SEL(a,b) __ASM_FORM(b) # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b) #endif @@ -132,4 +135,15 @@ /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif +#ifndef __ASSEMBLY__ +/* + * This output constraint should be used for any inline asm which has a "call" + * instruction. Otherwise the asm may be inserted before the frame pointer + * gets set up by the containing function. If you forget to do this, objtool + * may print a "call without frame pointer save/setup" warning. + */ +register unsigned long current_stack_pointer asm(_ASM_SP); +#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) +#endif + #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 0874ebda3069..72759f131cc5 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ATOMIC_H #define _ASM_X86_ATOMIC_H diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 9e206f31ce2a..97c46b8169b7 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ATOMIC64_32_H #define _ASM_X86_ATOMIC64_32_H diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 5d9de36a2f04..738495caf05f 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ATOMIC64_64_H #define _ASM_X86_ATOMIC64_64_H diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index bfb28caf97b1..7fb336210e1b 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BARRIER_H #define _ASM_X86_BARRIER_H @@ -11,11 +12,11 @@ */ #ifdef CONFIG_X86_32 -#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \ +#define mb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "mfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") -#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \ +#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "lfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") -#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \ +#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") #else #define mb() asm volatile("mfence":::"memory") @@ -30,7 +31,11 @@ #endif #define dma_wmb() barrier() -#define __smp_mb() mb() +#ifdef CONFIG_X86_32 +#define __smp_mb() asm volatile("lock; addl $0,-4(%%esp)" ::: "memory", "cc") +#else +#define __smp_mb() asm volatile("lock; addl $0,-4(%%rsp)" ::: "memory", "cc") +#endif #define __smp_rmb() dma_rmb() #define __smp_wmb() barrier() #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) diff --git a/arch/x86/include/asm/bios_ebda.h b/arch/x86/include/asm/bios_ebda.h index 4b7b8e71607e..4d5a17e2febe 100644 --- a/arch/x86/include/asm/bios_ebda.h +++ b/arch/x86/include/asm/bios_ebda.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BIOS_EBDA_H #define _ASM_X86_BIOS_EBDA_H diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 854022772c5b..3fa039855b8f 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BITOPS_H #define _ASM_X86_BITOPS_H @@ -142,7 +143,7 @@ static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) { bool negative; - asm volatile(LOCK_PREFIX "andb %2,%1\n\t" + asm volatile(LOCK_PREFIX "andb %2,%1" CC_SET(s) : CC_OUT(s) (negative), ADDR : "ir" ((char) ~(1 << nr)) : "memory"); @@ -245,7 +246,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * { bool oldbit; - asm("bts %2,%1\n\t" + asm("bts %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -285,7 +286,7 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long { bool oldbit; - asm volatile("btr %2,%1\n\t" + asm volatile("btr %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -297,7 +298,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon { bool oldbit; - asm volatile("btc %2,%1\n\t" + asm volatile("btc %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr) : "memory"); @@ -328,7 +329,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l { bool oldbit; - asm volatile("bt %2,%1\n\t" + asm volatile("bt %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr)); diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index abd06b19ddd2..680c320363db 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BOOT_H #define _ASM_X86_BOOT_H diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index 4a8cb8d7cbd5..a07ffd23e4dd 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BOOTPARAM_UTILS_H #define _ASM_X86_BOOTPARAM_UTILS_H diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index aa6b2023d8f8..34d99af43994 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BUG_H #define _ASM_X86_BUG_H diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h index 5490bbaf71d5..542509b53e0f 100644 --- a/arch/x86/include/asm/bugs.h +++ b/arch/x86/include/asm/bugs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BUGS_H #define _ASM_X86_BUGS_H diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h index 48f99f15452e..abe08690a887 100644 --- a/arch/x86/include/asm/cache.h +++ b/arch/x86/include/asm/cache.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CACHE_H #define _ASM_X86_CACHE_H diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index cb9a1af109b4..63feaf2a5f93 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CACHEFLUSH_H #define _ASM_X86_CACHEFLUSH_H diff --git a/arch/x86/include/asm/ce4100.h b/arch/x86/include/asm/ce4100.h index e656ad8c0a2e..2930f560d7f3 100644 --- a/arch/x86/include/asm/ce4100.h +++ b/arch/x86/include/asm/ce4100.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_CE4100_H_ #define _ASM_CE4100_H_ diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h index 5f5bb0f97361..d79d1e622dcf 100644 --- a/arch/x86/include/asm/checksum.h +++ b/arch/x86/include/asm/checksum.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifdef CONFIG_X86_32 # include <asm/checksum_32.h> #else diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h index 7b53743ed267..7a659c74cd03 100644 --- a/arch/x86/include/asm/checksum_32.h +++ b/arch/x86/include/asm/checksum_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CHECKSUM_32_H #define _ASM_X86_CHECKSUM_32_H diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h index 08e7efb2c140..3ec6d3267cf9 100644 --- a/arch/x86/include/asm/checksum_64.h +++ b/arch/x86/include/asm/checksum_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CHECKSUM_64_H #define _ASM_X86_CHECKSUM_64_H diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h index 47bea8cadbd0..dc4cfc888d6d 100644 --- a/arch/x86/include/asm/clocksource.h +++ b/arch/x86/include/asm/clocksource.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* x86-specific clocksource additions */ #ifndef _ASM_X86_CLOCKSOURCE_H diff --git a/arch/x86/include/asm/cmdline.h b/arch/x86/include/asm/cmdline.h index 84ae170bc3d0..6faaf27e8899 100644 --- a/arch/x86/include/asm/cmdline.h +++ b/arch/x86/include/asm/cmdline.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CMDLINE_H #define _ASM_X86_CMDLINE_H diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index b5069e802d5c..56bd436ed01b 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ASM_X86_CMPXCHG_H #define ASM_X86_CMPXCHG_H diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index e4959d023af8..1732704f0445 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CMPXCHG_32_H #define _ASM_X86_CMPXCHG_32_H diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index caa23a34c963..03cad196a301 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CMPXCHG_64_H #define _ASM_X86_CMPXCHG_64_H diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 5343c19814b3..2cbd75dd2fd3 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_COMPAT_H #define _ASM_X86_COMPAT_H @@ -6,6 +7,7 @@ */ #include <linux/types.h> #include <linux/sched.h> +#include <linux/sched/task_stack.h> #include <asm/processor.h> #include <asm/user32.h> #include <asm/unistd.h> @@ -208,7 +210,6 @@ typedef struct compat_siginfo { } compat_siginfo_t; #define COMPAT_OFF_T_MAX 0x7fffffff -#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL struct compat_ipc64_perm { compat_key_t key; diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 9b7fa6313f1a..adc6cc86b062 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPU_H #define _ASM_X86_CPU_H diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index ff501e511d91..baeba0567126 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _CPU_DEVICE_ID #define _CPU_DEVICE_ID 1 diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index d59c15c3defd..bf6a76202a77 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPUFEATURE_H #define _ASM_X86_CPUFEATURE_H @@ -125,11 +126,10 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) -#define clear_cpu_cap(c, bit) clear_bit(bit, (unsigned long *)((c)->x86_capability)) -#define setup_clear_cpu_cap(bit) do { \ - clear_cpu_cap(&boot_cpu_data, bit); \ - set_bit(bit, (unsigned long *)cpu_caps_cleared); \ -} while (0) + +extern void setup_clear_cpu_cap(unsigned int bit); +extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); + #define setup_force_cpu_cap(bit) do { \ set_cpu_cap(&boot_cpu_data, bit); \ set_bit(bit, (unsigned long *)cpu_caps_set); \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 2519c6c801c9..c0b0e9e8aa66 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPUFEATURES_H #define _ASM_X86_CPUFEATURES_H @@ -12,173 +13,176 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 18 /* N 32-bit words worth of info */ -#define NBUGINTS 1 /* N 32-bit bug flags */ +#define NCAPINTS 18 /* N 32-bit words worth of info */ +#define NBUGINTS 1 /* N 32-bit bug flags */ /* * Note: If the comment begins with a quoted string, that string is used * in /proc/cpuinfo instead of the macro name. If the string is "", * this feature bit is not displayed in /proc/cpuinfo at all. + * + * When adding new features here that depend on other features, + * please update the table in kernel/cpu/cpuid-deps.c as well. */ -/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */ -#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ -#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ -#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ -#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ -#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ -#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ -#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ -#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ -#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ -#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ -#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ -#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ -#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ -#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ -#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions */ - /* (plus FCMOVcc, FCOMI with FPU) */ -#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ -#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ -#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ -#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ -#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ -#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ -#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ -#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ -#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ -#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ -#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ -#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ -#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ -#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ -#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ +/* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */ +#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ +#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ +#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ +#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ +#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ +#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ +#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ +#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ +#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ +#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ +#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ +#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ +#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ +#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ +#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */ +#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ +#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ +#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ +#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ +#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ +#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ +#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ +#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ +#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ +#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ +#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ +#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ +#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ +#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ +#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */ /* Don't duplicate feature flags which are redundant with Intel! */ -#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ -#define X86_FEATURE_MP ( 1*32+19) /* MP Capable. */ -#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ -#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ -#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ -#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ -#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ -#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64) */ -#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow! extensions */ -#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow! */ +#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ +#define X86_FEATURE_MP ( 1*32+19) /* MP Capable */ +#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ +#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ +#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ +#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ +#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ +#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64, 64-bit support) */ +#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow extensions */ +#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow */ /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */ -#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ -#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ -#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ +#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ +#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ +#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ /* Other features, Linux-defined mapping, word 3 */ /* This range is used for feature bits which conflict or are synthesized */ -#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ -#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ -#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ -#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ -/* cpu types for specific tunings: */ -#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ -#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ -#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ -#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ -#define X86_FEATURE_UP ( 3*32+ 9) /* smp kernel running on up */ -#define X86_FEATURE_ART ( 3*32+10) /* Platform has always running timer (ART) */ -#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ -#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ -#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ -#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in ia32 userspace */ -#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in ia32 userspace */ -#define X86_FEATURE_REP_GOOD ( 3*32+16) /* rep microcode works well */ -#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */ -#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ -#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ -#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ -#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */ -#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ -#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ -#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ -#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ -#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ -#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ -#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ -#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */ +#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ +#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ +#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ +#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ + +/* CPU types for specific tunings: */ +#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ +#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ +#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ +#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ +#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ +#define X86_FEATURE_UP ( 3*32+ 9) /* SMP kernel running on UP */ +#define X86_FEATURE_ART ( 3*32+10) /* Always running timer (ART) */ +#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ +#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ +#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ +#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ +#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ +#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ +#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" MFENCE synchronizes RDTSC */ +#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ +#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ +#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ +#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ +#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* CPU topology enum extensions */ +#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ +#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ +#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ +#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* Extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM ( 3*32+27) /* AMD multi-node processor */ +#define X86_FEATURE_APERFMPERF ( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */ +#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ +#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */ -/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ -#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ -#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ -#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ -#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" Monitor/Mwait support */ -#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */ -#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ -#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer mode */ -#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ -#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ -#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ -#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ -#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ -#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ -#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 */ -#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ -#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit fp conversions */ -#define X86_FEATURE_RDRAND ( 4*32+30) /* The RDRAND instruction */ -#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ +/* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */ +#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ +#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ +#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ +#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */ +#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */ +#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ +#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer Mode eXtensions */ +#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ +#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ +#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ +#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ +#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ +#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B instruction */ +#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ +#define X86_FEATURE_PDCM ( 4*32+15) /* Perf/Debug Capabilities MSR */ +#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 instructions */ +#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE instruction enabled in the OS */ +#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ +#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit FP conversions */ +#define X86_FEATURE_RDRAND ( 4*32+30) /* RDRAND instruction */ +#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ -#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ -#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ -#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ -#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ -#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ -#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ -#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ -#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ -#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ -#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ +#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ +#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ +#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ +#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ +#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ +#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ +#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ +#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ +#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ +#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ -/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */ -#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ -#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ -#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure virtual machine */ -#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ -#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ -#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ -#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ -#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ -#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ -#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ -#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ -#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ -#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ -#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ -#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ -#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ -#define X86_FEATURE_TCE ( 6*32+17) /* translation cache extension */ -#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ -#define X86_FEATURE_TBM ( 6*32+21) /* trailing bit manipulations */ -#define X86_FEATURE_TOPOEXT ( 6*32+22) /* topology extensions CPUID leafs */ -#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */ -#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ -#define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ -#define X86_FEATURE_PTSC ( 6*32+27) /* performance time-stamp counter */ -#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ -#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ +/* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */ +#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ +#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ +#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure Virtual Machine */ +#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ +#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ +#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ +#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ +#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ +#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ +#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ +#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ +#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ +#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ +#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ +#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ +#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ +#define X86_FEATURE_TCE ( 6*32+17) /* Translation Cache Extension */ +#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ +#define X86_FEATURE_TBM ( 6*32+21) /* Trailing Bit Manipulations */ +#define X86_FEATURE_TOPOEXT ( 6*32+22) /* Topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* Core performance counter extensions */ +#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ +#define X86_FEATURE_BPEXT ( 6*32+26) /* Data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* Performance time-stamp counter */ +#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -186,146 +190,154 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */ -#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ -#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ -#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ -#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ -#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ -#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ +#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ +#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ +#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ +#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ -#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ -#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ +#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ +#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ -#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ -#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ +#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ +#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */ -#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ +#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ /* Virtualization flags: Linux defined, word 8 */ -#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ +#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ -#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ -#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ +#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ +#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ -/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ -#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ -#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3b */ -#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ -#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ -#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ -#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ -#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ -#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */ -#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ -#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ -#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ -#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ -#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ -#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ -#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ -#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ -#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ -#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ -#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ -#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ -#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ -#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ -#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ -#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ -#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */ -#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */ +/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ +#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ +#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3B */ +#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ +#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ +#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ +#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */ +#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ +#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ +#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ +#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ +#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ +#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ +#define X86_FEATURE_RDSEED ( 9*32+18) /* RDSEED instruction */ +#define X86_FEATURE_ADX ( 9*32+19) /* ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ +#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ +#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ +#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ +#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */ +#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */ -/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */ -#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */ -#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC */ -#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 */ -#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS */ +/* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */ +#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT instruction */ +#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */ +#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */ +#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */ -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */ -#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */ +#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ -/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ -#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */ -#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */ -#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */ +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */ +#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring */ +#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */ +#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */ -/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ -#define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ -#define X86_FEATURE_IRPERF (13*32+1) /* Instructions Retired Count */ +/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ +#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ -/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ -#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ -#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ -#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ -#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ -#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ -#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ -#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ +/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ -/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */ -#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ -#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ -#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ -#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ -#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ -#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ -#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ -#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ -#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ +/* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */ +#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ +#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ +#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ -/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ -#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ -#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ -#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ -#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ -#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ -#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ +#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ +#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */ +#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ +#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */ +#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */ +#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */ +#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */ +#define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */ +#define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ +#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ +#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ -/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ -#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ -#define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ -#define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */ +/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */ /* * BUG word(s) */ -#define X86_BUG(x) (NCAPINTS*32 + (x)) +#define X86_BUG(x) (NCAPINTS*32 + (x)) -#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ -#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ -#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ -#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ -#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ -#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ -#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ -#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ -#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ +#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ +#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ +#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ +#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ +#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ +#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ +#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ +#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ +#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional * to avoid confusion. */ -#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ +#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif -#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ -#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ -#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ +#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ + #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h index 61c852fa346b..6722ffcef2e6 100644 --- a/arch/x86/include/asm/cpumask.h +++ b/arch/x86/include/asm/cpumask.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPUMASK_H #define _ASM_X86_CPUMASK_H #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h index f498411f2500..a7adb2bfbf0b 100644 --- a/arch/x86/include/asm/crash.h +++ b/arch/x86/include/asm/crash.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CRASH_H #define _ASM_X86_CRASH_H diff --git a/arch/x86/include/asm/crypto/aes.h b/arch/x86/include/asm/crypto/aes.h index 80545a1cbe39..c508521dd190 100644 --- a/arch/x86/include/asm/crypto/aes.h +++ b/arch/x86/include/asm/crypto/aes.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ASM_X86_AES_H #define ASM_X86_AES_H diff --git a/arch/x86/include/asm/crypto/camellia.h b/arch/x86/include/asm/crypto/camellia.h index bb93333d9200..10f8d590bcfe 100644 --- a/arch/x86/include/asm/crypto/camellia.h +++ b/arch/x86/include/asm/crypto/camellia.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ASM_X86_CAMELLIA_H #define ASM_X86_CAMELLIA_H diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h index ed8b66de541f..553a03de55c3 100644 --- a/arch/x86/include/asm/crypto/glue_helper.h +++ b/arch/x86/include/asm/crypto/glue_helper.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Shared glue code for 128bit block ciphers */ diff --git a/arch/x86/include/asm/crypto/serpent-avx.h b/arch/x86/include/asm/crypto/serpent-avx.h index 33c2b8a435da..c958b7bd0fcb 100644 --- a/arch/x86/include/asm/crypto/serpent-avx.h +++ b/arch/x86/include/asm/crypto/serpent-avx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ASM_X86_SERPENT_AVX_H #define ASM_X86_SERPENT_AVX_H diff --git a/arch/x86/include/asm/crypto/serpent-sse2.h b/arch/x86/include/asm/crypto/serpent-sse2.h index e6e77dffbdab..1a345e8a7496 100644 --- a/arch/x86/include/asm/crypto/serpent-sse2.h +++ b/arch/x86/include/asm/crypto/serpent-sse2.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ASM_X86_SERPENT_SSE2_H #define ASM_X86_SERPENT_SSE2_H diff --git a/arch/x86/include/asm/crypto/twofish.h b/arch/x86/include/asm/crypto/twofish.h index 878c51ceebb5..65bb80adba3e 100644 --- a/arch/x86/include/asm/crypto/twofish.h +++ b/arch/x86/include/asm/crypto/twofish.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ASM_X86_TWOFISH_H #define ASM_X86_TWOFISH_H diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h index 9476c04ee635..3e204e6140b5 100644 --- a/arch/x86/include/asm/current.h +++ b/arch/x86/include/asm/current.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CURRENT_H #define _ASM_X86_CURRENT_H diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 12cb66f6d3a5..4505ac2735ad 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DEBUGREG_H #define _ASM_X86_DEBUGREG_H diff --git a/arch/x86/include/asm/delay.h b/arch/x86/include/asm/delay.h index 36a760bda462..de9e7841f953 100644 --- a/arch/x86/include/asm/delay.h +++ b/arch/x86/include/asm/delay.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DELAY_H #define _ASM_X86_DELAY_H diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 9d0e13738ed3..4011cb03ef08 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DESC_H #define _ASM_X86_DESC_H @@ -392,7 +393,7 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) void update_intr_gate(unsigned int n, const void *addr); void alloc_intr_gate(unsigned int n, const void *addr); -extern unsigned long used_vectors[]; +extern unsigned long system_vectors[]; #ifdef CONFIG_X86_64 DECLARE_PER_CPU(u32, debug_idt_ctr); diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h index 346d252029b7..a91f3b6e4f2a 100644 --- a/arch/x86/include/asm/desc_defs.h +++ b/arch/x86/include/asm/desc_defs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* Written 2000 by Andi Kleen */ #ifndef _ASM_X86_DESC_DEFS_H #define _ASM_X86_DESC_DEFS_H diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index 1b3ef26e77df..5e12c63b47aa 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DEVICE_H #define _ASM_X86_DEVICE_H diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index c10c9128f54e..14d6d5007314 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -16,6 +16,12 @@ # define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31)) #endif +#ifdef CONFIG_X86_INTEL_UMIP +# define DISABLE_UMIP 0 +#else +# define DISABLE_UMIP (1<<(X86_FEATURE_UMIP & 31)) +#endif + #ifdef CONFIG_X86_64 # define DISABLE_VME (1<<(X86_FEATURE_VME & 31)) # define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) @@ -63,7 +69,7 @@ #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 -#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57) +#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP) #define DISABLED_MASK17 0 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h index af95c47d5c9e..20a46150e0a8 100644 --- a/arch/x86/include/asm/div64.h +++ b/arch/x86/include/asm/div64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DIV64_H #define _ASM_X86_DIV64_H diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 1387dafdba2d..0350d99bb8fd 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DMA_MAPPING_H #define _ASM_X86_DMA_MAPPING_H @@ -6,7 +7,6 @@ * Documentation/DMA-API.txt for documentation. */ -#include <linux/kmemcheck.h> #include <linux/scatterlist.h> #include <linux/dma-debug.h> #include <asm/io.h> @@ -67,13 +67,6 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) } #endif /* CONFIG_X86_DMA_REMAP */ -static inline void -dma_cache_sync(struct device *dev, void *vaddr, size_t size, - enum dma_data_direction dir) -{ - flush_write_buffers(); -} - static inline unsigned long dma_alloc_coherent_mask(struct device *dev, gfp_t gfp) { diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h index fe884e18fa6e..00f7cf45e699 100644 --- a/arch/x86/include/asm/dma.h +++ b/arch/x86/include/asm/dma.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * linux/include/asm/dma.h: Defines for using and allocating dma channels. * Written by Hennus Bergman, 1992. diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h index a8e15b04565b..0ab2ab27ad1f 100644 --- a/arch/x86/include/asm/dmi.h +++ b/arch/x86/include/asm/dmi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DMI_H #define _ASM_X86_DMI_H diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h index b7a1ab865d68..ae391f609840 100644 --- a/arch/x86/include/asm/dwarf2.h +++ b/arch/x86/include/asm/dwarf2.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DWARF2_H #define _ASM_X86_DWARF2_H diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h index cd266d830e49..62be73b23d5c 100644 --- a/arch/x86/include/asm/e820/api.h +++ b/arch/x86/include/asm/e820/api.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_E820_API_H #define _ASM_E820_API_H diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h index 4adeed03a9a1..c3aa4b5e49e2 100644 --- a/arch/x86/include/asm/e820/types.h +++ b/arch/x86/include/asm/e820/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_E820_TYPES_H #define _ASM_E820_TYPES_H diff --git a/arch/x86/include/asm/edac.h b/arch/x86/include/asm/edac.h index cf8fdf83b231..426fc53ff803 100644 --- a/arch/x86/include/asm/edac.h +++ b/arch/x86/include/asm/edac.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_EDAC_H #define _ASM_X86_EDAC_H diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 796ff6c1aa53..85f6ccb80b91 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_EFI_H #define _ASM_X86_EFI_H diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 04330c8d9af9..0d157d2a1e2a 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ELF_H #define _ASM_X86_ELF_H @@ -252,7 +253,7 @@ extern int force_personality32; * space open for things that want to use the area for 32-bit pointers. */ #define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \ - (TASK_SIZE / 3 * 2)) + (DEFAULT_MAP_WINDOW / 3 * 2)) /* This yields a mask that user programs can use to figure out what instruction set this CPU supports. This could be done in user space, @@ -308,6 +309,7 @@ static inline int mmap_is_ia32(void) extern unsigned long task_size_32bit(void); extern unsigned long task_size_64bit(int full_addr_space); extern unsigned long get_mmap_base(int is_legacy); +extern bool mmap_address_hint_valid(unsigned long addr, unsigned long len); #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/emergency-restart.h b/arch/x86/include/asm/emergency-restart.h index 77a99ac06d00..2abde717db31 100644 --- a/arch/x86/include/asm/emergency-restart.h +++ b/arch/x86/include/asm/emergency-restart.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_EMERGENCY_RESTART_H #define _ASM_X86_EMERGENCY_RESTART_H diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index aa15d1f7e530..416422762845 100644 --- a/arch/x86/include/asm/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * This file is designed to contain the BUILD_INTERRUPT specifications for * all of the extra named interrupt vectors used by the architecture. diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h index ca3ce9ab9385..0211029076ea 100644 --- a/arch/x86/include/asm/espfix.h +++ b/arch/x86/include/asm/espfix.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_ESPFIX_H #define _ASM_X86_ESPFIX_H diff --git a/arch/x86/include/asm/export.h b/arch/x86/include/asm/export.h index 138de56b13eb..2a51d66689c5 100644 --- a/arch/x86/include/asm/export.h +++ b/arch/x86/include/asm/export.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifdef CONFIG_64BIT #define KSYM_ALIGN 16 #endif diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h index c66d19e3c23e..f9c3a5d502f4 100644 --- a/arch/x86/include/asm/extable.h +++ b/arch/x86/include/asm/extable.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_EXTABLE_H #define _ASM_X86_EXTABLE_H /* diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h index c3dd5e71f439..ab4c960146e3 100644 --- a/arch/x86/include/asm/fb.h +++ b/arch/x86/include/asm/fb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FB_H #define _ASM_X86_FB_H diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index dcd9fb55e679..b0c505fe9a95 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -104,6 +104,12 @@ enum fixed_addresses { FIX_GDT_REMAP_BEGIN, FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1, +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif + __end_of_permanent_fixed_addresses, /* diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 0877ae018fc9..a9caac9d4a72 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1994 Linus Torvalds * diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 554cdb205d17..a38bf5a1e37a 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1994 Linus Torvalds * @@ -23,11 +24,9 @@ /* * High level FPU state handling functions: */ -extern void fpu__activate_curr(struct fpu *fpu); -extern void fpu__activate_fpstate_read(struct fpu *fpu); -extern void fpu__activate_fpstate_write(struct fpu *fpu); -extern void fpu__current_fpstate_write_begin(void); -extern void fpu__current_fpstate_write_end(void); +extern void fpu__initialize(struct fpu *fpu); +extern void fpu__prepare_read(struct fpu *fpu); +extern void fpu__prepare_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); extern void fpu__restore(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); @@ -120,20 +119,11 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu); err; \ }) -#define check_insn(insn, output, input...) \ -({ \ - int err; \ +#define kernel_insn(insn, output, input...) \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \ + : output : input) static inline int copy_fregs_to_user(struct fregs_state __user *fx) { @@ -153,20 +143,16 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { - int err; - if (IS_ENABLED(CONFIG_X86_32)) { - err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) { - err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); + kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } else { /* See comment in copy_fxregs_to_kernel() below. */ - err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); + kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); } } - /* Copying from a kernel buffer to FPU registers should never fail: */ - WARN_ON_FPU(err); } static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) @@ -183,9 +169,7 @@ static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) static inline void copy_kernel_to_fregs(struct fregs_state *fx) { - int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - - WARN_ON_FPU(err); + kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fregs(struct fregs_state __user *fx) @@ -281,18 +265,13 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ -#define XSTATE_XRESTORE(st, lmask, hmask, err) \ +#define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile(ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ - "xor %[err], %[err]\n" \ "3:\n" \ - ".pushsection .fixup,\"ax\"\n" \ - "4: movl $-2, %[err]\n" \ - "jmp 3b\n" \ - ".popsection\n" \ - _ASM_EXTABLE(661b, 4b) \ - : [err] "=r" (err) \ + _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\ + : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") @@ -336,7 +315,10 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); - /* We should never fault when copying from a kernel buffer: */ + /* + * We should never fault when copying from a kernel buffer, and the FPU + * state we set at boot time should be valid. + */ WARN_ON_FPU(err); } @@ -350,7 +332,7 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) u32 hmask = mask >> 32; int err; - WARN_ON(!alternatives_patched); + WARN_ON_FPU(!alternatives_patched); XSTATE_XSAVE(xstate, lmask, hmask, err); @@ -365,12 +347,8 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; - int err; - - XSTATE_XRESTORE(xstate, lmask, hmask, err); - /* We should never fault when copying from a kernel buffer: */ - WARN_ON_FPU(err); + XSTATE_XRESTORE(xstate, lmask, hmask); } /* @@ -526,38 +504,17 @@ static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) */ static inline void fpregs_deactivate(struct fpu *fpu) { - WARN_ON_FPU(!fpu->fpregs_active); - - fpu->fpregs_active = 0; this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { - WARN_ON_FPU(fpu->fpregs_active); - - fpu->fpregs_active = 1; this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* - * The question "does this thread have fpu access?" - * is slightly racy, since preemption could come in - * and revoke it immediately after the test. - * - * However, even in that very unlikely scenario, - * we can just assume we have FPU access - typically - * to save the FP state - we'll just take a #NM - * fault and get the FPU access back. - */ -static inline int fpregs_active(void) -{ - return current->thread.fpu.fpregs_active; -} - -/* * FPU state switching for scheduling. * * This is a two-stage process: @@ -571,14 +528,13 @@ static inline int fpregs_active(void) static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { - if (old_fpu->fpregs_active) { + if (old_fpu->initialized) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else old_fpu->last_cpu = cpu; /* But leave fpu_fpregs_owner_ctx! */ - old_fpu->fpregs_active = 0; trace_x86_fpu_regs_deactivated(old_fpu); } else old_fpu->last_cpu = -1; @@ -595,7 +551,7 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu) static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu) { bool preload = static_cpu_has(X86_FEATURE_FPU) && - new_fpu->fpstate_active; + new_fpu->initialized; if (preload) { if (!fpregs_state_valid(new_fpu, cpu)) @@ -617,8 +573,7 @@ static inline void user_fpu_begin(void) struct fpu *fpu = ¤t->thread.fpu; preempt_disable(); - if (!fpregs_active()) - fpregs_activate(fpu); + fpregs_activate(fpu); preempt_enable(); } diff --git a/arch/x86/include/asm/fpu/regset.h b/arch/x86/include/asm/fpu/regset.h index 39d3107ac6c7..d5bdffb9d27f 100644 --- a/arch/x86/include/asm/fpu/regset.h +++ b/arch/x86/include/asm/fpu/regset.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * FPU regset handling methods: */ diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h index 20a1fbf7fe4e..4df2754ef380 100644 --- a/arch/x86/include/asm/fpu/signal.h +++ b/arch/x86/include/asm/fpu/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * x86 FPU signal frame handling methods: */ diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 3c80f5b9c09d..202c53918ecf 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * FPU data structures: */ @@ -68,6 +69,9 @@ struct fxregs_state { /* Default value for fxregs_state.mxcsr: */ #define MXCSR_DEFAULT 0x1f80 +/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */ +#define MXCSR_AND_FLAGS_SIZE sizeof(u64) + /* * Software based FPU emulation state. This is arbitrary really, * it matches the x87 format to make it easier to understand: @@ -290,36 +294,13 @@ struct fpu { unsigned int last_cpu; /* - * @fpstate_active: + * @initialized: * - * This flag indicates whether this context is active: if the task + * This flag indicates whether this context is initialized: if the task * is not running then we can restore from this context, if the task * is running then we should save into this context. */ - unsigned char fpstate_active; - - /* - * @fpregs_active: - * - * This flag determines whether a given context is actively - * loaded into the FPU's registers and that those registers - * represent the task's current FPU state. - * - * Note the interaction with fpstate_active: - * - * # task does not use the FPU: - * fpstate_active == 0 - * - * # task uses the FPU and regs are active: - * fpstate_active == 1 && fpregs_active == 1 - * - * # the regs are inactive but still match fpstate: - * fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu - * - * The third state is what we use for the lazy restore optimization - * on lazy-switching CPUs. - */ - unsigned char fpregs_active; + unsigned char initialized; /* * @state: diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 1b2799e0699a..48581988d78c 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_X86_XSAVE_H #define __ASM_X86_XSAVE_H @@ -48,8 +49,12 @@ void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); const void *get_xsave_field_ptr(int xstate_field); int using_compacted_format(void); -int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave); -int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave); +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size); +int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf); +int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf); + +/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ +extern int validate_xstate_header(const struct xstate_header *hdr); + #endif diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h index 6e4d170726b7..5cbce6fbb534 100644 --- a/arch/x86/include/asm/frame.h +++ b/arch/x86/include/asm/frame.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FRAME_H #define _ASM_X86_FRAME_H diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index eccd0ac6bc38..09ad88572746 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FTRACE_H #define _ASM_X86_FTRACE_H diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index f4dc9b63bdda..de4d68852d3a 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FUTEX_H #define _ASM_X86_FUTEX_H diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h index 1d268098ac2e..318556574345 100644 --- a/arch/x86/include/asm/gart.h +++ b/arch/x86/include/asm/gart.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_GART_H #define _ASM_X86_GART_H diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index ad1ed531febc..51cc979dd364 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_HARDIRQ_H #define _ASM_X86_HARDIRQ_H diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index 1c0b43724ce3..a8059930056d 100644 --- a/arch/x86/include/asm/highmem.h +++ b/arch/x86/include/asm/highmem.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * highmem.h: virtual kernel memory mappings for high memory * diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index cc285ec4b2c1..67385d56d4f4 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_HPET_H #define _ASM_X86_HPET_H diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index 535af0f2d8ac..5ed826da5e07 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_HUGETLB_H #define _ASM_X86_HUGETLB_H diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index 6c98be864a75..f59c39835a5a 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _I386_HW_BREAKPOINT_H #define _I386_HW_BREAKPOINT_H diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 6dfe366a8804..2851077b6051 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_HW_IRQ_H #define _ASM_X86_HW_IRQ_H @@ -15,6 +16,8 @@ #include <asm/irq_vectors.h> +#define IRQ_MATRIX_BITS NR_VECTORS + #ifndef __ASSEMBLY__ #include <linux/percpu.h> @@ -96,14 +99,6 @@ struct irq_alloc_info { void *dmar_data; }; #endif -#ifdef CONFIG_HT_IRQ - struct { - int ht_pos; - int ht_idx; - struct pci_dev *ht_dev; - void *ht_update; - }; -#endif #ifdef CONFIG_X86_UV struct { int uv_limit; @@ -122,15 +117,13 @@ struct irq_alloc_info { struct irq_cfg { unsigned int dest_apicid; - u8 vector; - u8 old_vector; + unsigned int vector; }; extern struct irq_cfg *irq_cfg(unsigned int irq); extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data); extern void lock_vector_lock(void); extern void unlock_vector_lock(void); -extern void setup_vector_irq(int cpu); #ifdef CONFIG_SMP extern void send_cleanup_vector(struct irq_cfg *); extern void irq_complete_move(struct irq_cfg *cfg); diff --git a/arch/x86/include/asm/hypertransport.h b/arch/x86/include/asm/hypertransport.h deleted file mode 100644 index 334b1a885d9c..000000000000 --- a/arch/x86/include/asm/hypertransport.h +++ /dev/null @@ -1,45 +0,0 @@ -#ifndef _ASM_X86_HYPERTRANSPORT_H -#define _ASM_X86_HYPERTRANSPORT_H - -/* - * Constants for x86 Hypertransport Interrupts. - */ - -#define HT_IRQ_LOW_BASE 0xf8000000 - -#define HT_IRQ_LOW_VECTOR_SHIFT 16 -#define HT_IRQ_LOW_VECTOR_MASK 0x00ff0000 -#define HT_IRQ_LOW_VECTOR(v) \ - (((v) << HT_IRQ_LOW_VECTOR_SHIFT) & HT_IRQ_LOW_VECTOR_MASK) - -#define HT_IRQ_LOW_DEST_ID_SHIFT 8 -#define HT_IRQ_LOW_DEST_ID_MASK 0x0000ff00 -#define HT_IRQ_LOW_DEST_ID(v) \ - (((v) << HT_IRQ_LOW_DEST_ID_SHIFT) & HT_IRQ_LOW_DEST_ID_MASK) - -#define HT_IRQ_LOW_DM_PHYSICAL 0x0000000 -#define HT_IRQ_LOW_DM_LOGICAL 0x0000040 - -#define HT_IRQ_LOW_RQEOI_EDGE 0x0000000 -#define HT_IRQ_LOW_RQEOI_LEVEL 0x0000020 - - -#define HT_IRQ_LOW_MT_FIXED 0x0000000 -#define HT_IRQ_LOW_MT_ARBITRATED 0x0000004 -#define HT_IRQ_LOW_MT_SMI 0x0000008 -#define HT_IRQ_LOW_MT_NMI 0x000000c -#define HT_IRQ_LOW_MT_INIT 0x0000010 -#define HT_IRQ_LOW_MT_STARTUP 0x0000014 -#define HT_IRQ_LOW_MT_EXTINT 0x0000018 -#define HT_IRQ_LOW_MT_LINT1 0x000008c -#define HT_IRQ_LOW_MT_LINT0 0x0000098 - -#define HT_IRQ_LOW_IRQ_MASKED 0x0000001 - - -#define HT_IRQ_HIGH_DEST_ID_SHIFT 0 -#define HT_IRQ_HIGH_DEST_ID_MASK 0x00ffffff -#define HT_IRQ_HIGH_DEST_ID(v) \ - ((((v) >> 8) << HT_IRQ_HIGH_DEST_ID_SHIFT) & HT_IRQ_HIGH_DEST_ID_MASK) - -#endif /* _ASM_X86_HYPERTRANSPORT_H */ diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 0ead9dbb9130..1b0a5abcd8ae 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -23,11 +23,22 @@ #ifdef CONFIG_HYPERVISOR_GUEST #include <asm/kvm_para.h> +#include <asm/x86_init.h> #include <asm/xen/hypervisor.h> /* * x86 hypervisor information */ + +enum x86_hypervisor_type { + X86_HYPER_NATIVE = 0, + X86_HYPER_VMWARE, + X86_HYPER_MS_HYPERV, + X86_HYPER_XEN_PV, + X86_HYPER_XEN_HVM, + X86_HYPER_KVM, +}; + struct hypervisor_x86 { /* Hypervisor name */ const char *name; @@ -35,40 +46,19 @@ struct hypervisor_x86 { /* Detection routine */ uint32_t (*detect)(void); - /* Platform setup (run once per boot) */ - void (*init_platform)(void); - - /* X2APIC detection (run once per boot) */ - bool (*x2apic_available)(void); + /* Hypervisor type */ + enum x86_hypervisor_type type; - /* pin current vcpu to specified physical cpu (run rarely) */ - void (*pin_vcpu)(int); + /* init time callbacks */ + struct x86_hyper_init init; - /* called during init_mem_mapping() to setup early mappings. */ - void (*init_mem_mapping)(void); + /* runtime callbacks */ + struct x86_hyper_runtime runtime; }; -extern const struct hypervisor_x86 *x86_hyper; - -/* Recognized hypervisors */ -extern const struct hypervisor_x86 x86_hyper_vmware; -extern const struct hypervisor_x86 x86_hyper_ms_hyperv; -extern const struct hypervisor_x86 x86_hyper_xen_pv; -extern const struct hypervisor_x86 x86_hyper_xen_hvm; -extern const struct hypervisor_x86 x86_hyper_kvm; - +extern enum x86_hypervisor_type x86_hyper_type; extern void init_hypervisor_platform(void); -extern bool hypervisor_x2apic_available(void); -extern void hypervisor_pin_vcpu(int cpu); - -static inline void hypervisor_init_mem_mapping(void) -{ - if (x86_hyper && x86_hyper->init_mem_mapping) - x86_hyper->init_mem_mapping(); -} #else static inline void init_hypervisor_platform(void) { } -static inline bool hypervisor_x2apic_available(void) { return false; } -static inline void hypervisor_init_mem_mapping(void) { } #endif /* CONFIG_HYPERVISOR_GUEST */ #endif /* _ASM_X86_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h index 39bcefc20de7..c8376b40e882 100644 --- a/arch/x86/include/asm/i8259.h +++ b/arch/x86/include/asm/i8259.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_I8259_H #define _ASM_X86_I8259_H diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index a9bdf5569ab3..2c5f7861d373 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_IA32_H #define _ASM_X86_IA32_H diff --git a/arch/x86/include/asm/ia32_unistd.h b/arch/x86/include/asm/ia32_unistd.h index b0d5716ca1e4..aa065c94ccf5 100644 --- a/arch/x86/include/asm/ia32_unistd.h +++ b/arch/x86/include/asm/ia32_unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_IA32_UNISTD_H #define _ASM_X86_IA32_UNISTD_H diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h index 02aff0867211..1c78580e58be 100644 --- a/arch/x86/include/asm/inat.h +++ b/arch/x86/include/asm/inat.h @@ -97,6 +97,16 @@ #define INAT_MAKE_GROUP(grp) ((grp << INAT_GRP_OFFS) | INAT_MODRM) #define INAT_MAKE_IMM(imm) (imm << INAT_IMM_OFFS) +/* Identifiers for segment registers */ +#define INAT_SEG_REG_IGNORE 0 +#define INAT_SEG_REG_DEFAULT 1 +#define INAT_SEG_REG_CS 2 +#define INAT_SEG_REG_SS 3 +#define INAT_SEG_REG_DS 4 +#define INAT_SEG_REG_ES 5 +#define INAT_SEG_REG_FS 6 +#define INAT_SEG_REG_GS 7 + /* Attribute search APIs */ extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode); extern int inat_get_last_prefix_id(insn_byte_t last_pfx); diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 05c4aa00cc86..5f1d3c421f68 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_INIT_H #define _ASM_X86_INIT_H diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h new file mode 100644 index 000000000000..2b6ccf2c49f1 --- /dev/null +++ b/arch/x86/include/asm/insn-eval.h @@ -0,0 +1,23 @@ +#ifndef _ASM_X86_INSN_EVAL_H +#define _ASM_X86_INSN_EVAL_H +/* + * A collection of utility functions for x86 instruction analysis to be + * used in a kernel context. Useful when, for instance, making sense + * of the registers indicated by operands. + */ + +#include <linux/compiler.h> +#include <linux/bug.h> +#include <linux/err.h> +#include <asm/ptrace.h> + +#define INSN_CODE_SEG_ADDR_SZ(params) ((params >> 4) & 0xf) +#define INSN_CODE_SEG_OPND_SZ(params) (params & 0xf) +#define INSN_CODE_SEG_PARAMS(oper_sz, addr_sz) (oper_sz | (addr_sz << 4)) + +void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs); +int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs); +unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx); +int insn_get_code_seg_params(struct pt_regs *regs); + +#endif /* _ASM_X86_INSN_EVAL_H */ diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h index 3e115273ed88..f5a796da07f8 100644 --- a/arch/x86/include/asm/inst.h +++ b/arch/x86/include/asm/inst.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Generate .byte code for some instructions not supported by old * binutils. diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 75b748a1deb8..35a6bc4da8ad 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_INTEL_FAMILY_H #define _ASM_X86_INTEL_FAMILY_H diff --git a/arch/x86/include/asm/intel_mid_vrtc.h b/arch/x86/include/asm/intel_mid_vrtc.h index 86ff4685c409..35555016b1be 100644 --- a/arch/x86/include/asm/intel_mid_vrtc.h +++ b/arch/x86/include/asm/intel_mid_vrtc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _INTEL_MID_VRTC_H #define _INTEL_MID_VRTC_H diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h index fac89eb78a6b..528ed4be4393 100644 --- a/arch/x86/include/asm/intel_pmc_ipc.h +++ b/arch/x86/include/asm/intel_pmc_ipc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_INTEL_PMC_IPC_H_ #define _ASM_X86_INTEL_PMC_IPC_H_ diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h index e1a411786bf5..b523f51c5400 100644 --- a/arch/x86/include/asm/intel_pt.h +++ b/arch/x86/include/asm/intel_pt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_INTEL_PT_H #define _ASM_X86_INTEL_PT_H diff --git a/arch/x86/include/asm/intel_punit_ipc.h b/arch/x86/include/asm/intel_punit_ipc.h index 201eb9dce595..ce16da719596 100644 --- a/arch/x86/include/asm/intel_punit_ipc.h +++ b/arch/x86/include/asm/intel_punit_ipc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_INTEL_PUNIT_IPC_H_ #define _ASM_X86_INTEL_PUNIT_IPC_H_ diff --git a/arch/x86/include/asm/intel_rdt_sched.h b/arch/x86/include/asm/intel_rdt_sched.h index b4bbf8b21512..9acb06b6f81e 100644 --- a/arch/x86/include/asm/intel_rdt_sched.h +++ b/arch/x86/include/asm/intel_rdt_sched.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_INTEL_RDT_SCHED_H #define _ASM_X86_INTEL_RDT_SCHED_H diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h index 81d3d8776fd9..4a8c6e817398 100644 --- a/arch/x86/include/asm/intel_scu_ipc.h +++ b/arch/x86/include/asm/intel_scu_ipc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_INTEL_SCU_IPC_H_ #define _ASM_X86_INTEL_SCU_IPC_H_ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index c40a95c33bb8..95e948627fd0 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_IO_H #define _ASM_X86_IO_H @@ -110,6 +111,10 @@ build_mmio_write(__writeq, "q", unsigned long, "r", ) #endif +#define ARCH_HAS_VALID_PHYS_ADDR_RANGE +extern int valid_phys_addr_range(phys_addr_t addr, size_t size); +extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); + /** * virt_to_phys - map virtual addresses to physical * @address: address to remap @@ -265,6 +270,21 @@ static inline void slow_down_io(void) #endif +#ifdef CONFIG_AMD_MEM_ENCRYPT +#include <linux/jump_label.h> + +extern struct static_key_false sev_enable_key; +static inline bool sev_key_active(void) +{ + return static_branch_unlikely(&sev_enable_key); +} + +#else /* !CONFIG_AMD_MEM_ENCRYPT */ + +static inline bool sev_key_active(void) { return false; } + +#endif /* CONFIG_AMD_MEM_ENCRYPT */ + #define BUILDIO(bwl, bw, type) \ static inline void out##bwl(unsigned type value, int port) \ { \ @@ -295,14 +315,34 @@ static inline unsigned type in##bwl##_p(int port) \ \ static inline void outs##bwl(int port, const void *addr, unsigned long count) \ { \ - asm volatile("rep; outs" #bwl \ - : "+S"(addr), "+c"(count) : "d"(port) : "memory"); \ + if (sev_key_active()) { \ + unsigned type *value = (unsigned type *)addr; \ + while (count) { \ + out##bwl(*value, port); \ + value++; \ + count--; \ + } \ + } else { \ + asm volatile("rep; outs" #bwl \ + : "+S"(addr), "+c"(count) \ + : "d"(port) : "memory"); \ + } \ } \ \ static inline void ins##bwl(int port, void *addr, unsigned long count) \ { \ - asm volatile("rep; ins" #bwl \ - : "+D"(addr), "+c"(count) : "d"(port) : "memory"); \ + if (sev_key_active()) { \ + unsigned type *value = (unsigned type *)addr; \ + while (count) { \ + *value = in##bwl(port); \ + value++; \ + count--; \ + } \ + } else { \ + asm volatile("rep; ins" #bwl \ + : "+D"(addr), "+c"(count) \ + : "d"(port) : "memory"); \ + } \ } BUILDIO(b, b, char) diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 6cbf2cfb3f8a..a8834dd546cd 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_IO_APIC_H #define _ASM_X86_IO_APIC_H @@ -192,7 +193,6 @@ static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) extern void setup_IO_APIC(void); extern void enable_IO_APIC(void); extern void disable_IO_APIC(void); -extern void setup_ioapic_dest(void); extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin); extern void print_IO_APICs(void); #else /* !CONFIG_X86_IO_APIC */ @@ -232,7 +232,6 @@ static inline void io_apic_init_mappings(void) { } static inline void setup_IO_APIC(void) { } static inline void enable_IO_APIC(void) { } -static inline void setup_ioapic_dest(void) { } #endif diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index fca144a104e4..1e5d5d92eb40 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_IOMMU_H #define _ASM_X86_IOMMU_H diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h index e37d6b3ad983..1fb3fd1a83c2 100644 --- a/arch/x86/include/asm/iommu_table.h +++ b/arch/x86/include/asm/iommu_table.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_IOMMU_TABLE_H #define _ASM_X86_IOMMU_TABLE_H diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index c313cac36f56..7d87437bd030 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Intel OnChip System Fabric MailBox access support */ diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 9958ceea2fa3..2395bb794c7b 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_IRQ_H #define _ASM_X86_IRQ_H /* @@ -25,11 +26,7 @@ extern void irq_ctx_init(int cpu); struct irq_desc; -#ifdef CONFIG_HOTPLUG_CPU -#include <linux/cpumask.h> -extern int check_irq_vectors_for_cpu_disable(void); extern void fixup_irqs(void); -#endif #ifdef CONFIG_HAVE_KVM extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); diff --git a/arch/x86/include/asm/irq_regs.h b/arch/x86/include/asm/irq_regs.h index d82250b1debb..8f3bee821e6c 100644 --- a/arch/x86/include/asm/irq_regs.h +++ b/arch/x86/include/asm/irq_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Per-cpu current frame pointer - the location of the last exception frame on * the stack, stored in the per-cpu area. diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index aaf8d28b5d00..67421f649cfa 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_IRQ_VECTORS_H #define _ASM_X86_IRQ_VECTORS_H @@ -101,12 +102,8 @@ #define POSTED_INTR_NESTED_VECTOR 0xf0 #endif -/* - * Local APIC timer IRQ vector is on a different priority level, - * to work around the 'lost local interrupt if more than 2 IRQ - * sources per level' errata. - */ -#define LOCAL_TIMER_VECTOR 0xef +#define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef +#define LOCAL_TIMER_VECTOR 0xee #define NR_VECTORS 256 diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h index ddbb8ea0f5a9..800ffce0db29 100644 --- a/arch/x86/include/asm/irq_work.h +++ b/arch/x86/include/asm/irq_work.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_IRQ_WORK_H #define _ASM_IRQ_WORK_H diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h index d26075b52885..139feef467f7 100644 --- a/arch/x86/include/asm/irqdomain.h +++ b/arch/x86/include/asm/irqdomain.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_IRQDOMAIN_H #define _ASM_IRQDOMAIN_H @@ -8,6 +9,7 @@ enum { /* Allocate contiguous CPU vectors */ X86_IRQ_ALLOC_CONTIGUOUS_VECTORS = 0x1, + X86_IRQ_ALLOC_LEGACY = 0x2, }; extern struct irq_domain *x86_vector_domain; @@ -41,8 +43,8 @@ extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg); extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs); -extern void mp_irqdomain_activate(struct irq_domain *domain, - struct irq_data *irq_data); +extern int mp_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early); extern void mp_irqdomain_deactivate(struct irq_domain *domain, struct irq_data *irq_data); extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain); @@ -54,10 +56,4 @@ extern void arch_init_msi_domain(struct irq_domain *domain); static inline void arch_init_msi_domain(struct irq_domain *domain) { } #endif -#ifdef CONFIG_HT_IRQ -extern void arch_init_htirq_domain(struct irq_domain *domain); -#else -static inline void arch_init_htirq_domain(struct irq_domain *domain) { } -#endif - #endif diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index ac7692dcfa2e..c8ef23f2c28f 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X86_IRQFLAGS_H_ #define _X86_IRQFLAGS_H_ diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index adc54c12cbd1..8c0de4282659 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h index f527b02a0ee3..b577dd0916aa 100644 --- a/arch/x86/include/asm/kasan.h +++ b/arch/x86/include/asm/kasan.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_KASAN_H #define _ASM_X86_KASAN_H diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h index 1052a797d71d..460991e3b529 100644 --- a/arch/x86/include/asm/kaslr.h +++ b/arch/x86/include/asm/kaslr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_KASLR_H_ #define _ASM_KASLR_H_ diff --git a/arch/x86/include/asm/kbdleds.h b/arch/x86/include/asm/kbdleds.h index f27ac5ff597d..197ea4fedd53 100644 --- a/arch/x86/include/asm/kbdleds.h +++ b/arch/x86/include/asm/kbdleds.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_KBDLEDS_H #define _ASM_X86_KBDLEDS_H diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 29a594a3b82a..f86a8caa561e 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_KDEBUG_H #define _ASM_X86_KDEBUG_H diff --git a/arch/x86/include/asm/kexec-bzimage64.h b/arch/x86/include/asm/kexec-bzimage64.h index d1b5d194e31d..9f07cff43705 100644 --- a/arch/x86/include/asm/kexec-bzimage64.h +++ b/arch/x86/include/asm/kexec-bzimage64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_KEXEC_BZIMAGE64_H #define _ASM_KEXEC_BZIMAGE64_H diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 942c1f444da8..f327236f0fa7 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_KEXEC_H #define _ASM_X86_KEXEC_H diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h index 22a8537eb780..aacaf2502bd2 100644 --- a/arch/x86/include/asm/kgdb.h +++ b/arch/x86/include/asm/kgdb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_KGDB_H #define _ASM_X86_KGDB_H diff --git a/arch/x86/include/asm/kmap_types.h b/arch/x86/include/asm/kmap_types.h index 9e00a731a7fb..04ab8266e347 100644 --- a/arch/x86/include/asm/kmap_types.h +++ b/arch/x86/include/asm/kmap_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_KMAP_TYPES_H #define _ASM_X86_KMAP_TYPES_H diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h index ed01518f297e..ea32a7d3cf1b 100644 --- a/arch/x86/include/asm/kmemcheck.h +++ b/arch/x86/include/asm/kmemcheck.h @@ -1,42 +1 @@ -#ifndef ASM_X86_KMEMCHECK_H -#define ASM_X86_KMEMCHECK_H - -#include <linux/types.h> -#include <asm/ptrace.h> - -#ifdef CONFIG_KMEMCHECK -bool kmemcheck_active(struct pt_regs *regs); - -void kmemcheck_show(struct pt_regs *regs); -void kmemcheck_hide(struct pt_regs *regs); - -bool kmemcheck_fault(struct pt_regs *regs, - unsigned long address, unsigned long error_code); -bool kmemcheck_trap(struct pt_regs *regs); -#else -static inline bool kmemcheck_active(struct pt_regs *regs) -{ - return false; -} - -static inline void kmemcheck_show(struct pt_regs *regs) -{ -} - -static inline void kmemcheck_hide(struct pt_regs *regs) -{ -} - -static inline bool kmemcheck_fault(struct pt_regs *regs, - unsigned long address, unsigned long error_code) -{ - return false; -} - -static inline bool kmemcheck_trap(struct pt_regs *regs) -{ - return false; -} -#endif /* CONFIG_KMEMCHECK */ - -#endif +/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 6cf65437b5e5..9f2e3102e0bb 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -58,8 +58,8 @@ extern __visible kprobe_opcode_t optprobe_template_call[]; extern __visible kprobe_opcode_t optprobe_template_end[]; #define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE) #define MAX_OPTINSN_SIZE \ - (((unsigned long)&optprobe_template_end - \ - (unsigned long)&optprobe_template_entry) + \ + (((unsigned long)optprobe_template_end - \ + (unsigned long)optprobe_template_entry) + \ MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE) extern const int kretprobe_blacklist_size; diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index fa2558e12024..034caa1a084e 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /****************************************************************************** * x86_emulate.h * @@ -225,6 +226,8 @@ struct x86_emulate_ops { unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags); + int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase); + }; typedef u32 __attribute__((vector_size(16))) sse128_t; diff --git a/arch/x86/include/asm/kvm_guest.h b/arch/x86/include/asm/kvm_guest.h index a92b1763c419..46185263d9c2 100644 --- a/arch/x86/include/asm/kvm_guest.h +++ b/arch/x86/include/asm/kvm_guest.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_KVM_GUEST_H #define _ASM_X86_KVM_GUEST_H diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c73e493adf07..1bfb99770c34 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1061,6 +1061,11 @@ struct kvm_x86_ops { void (*cancel_hv_timer)(struct kvm_vcpu *vcpu); void (*setup_mce)(struct kvm_vcpu *vcpu); + + int (*smi_allowed)(struct kvm_vcpu *vcpu); + int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); + int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase); + int (*enable_smi_window)(struct kvm_vcpu *vcpu); }; struct kvm_arch_async_pf { @@ -1419,11 +1424,14 @@ static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} static inline int kvm_cpu_get_apicid(int mps_cpu) { #ifdef CONFIG_X86_LOCAL_APIC - return __default_cpu_present_to_apicid(mps_cpu); + return default_cpu_present_to_apicid(mps_cpu); #else WARN_ON_ONCE(1); return BAD_APICID; #endif } +#define put_smstate(type, buf, offset, val) \ + *(type *)((buf) + (offset) - 0x7e00) = val + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index c4eda791f877..172f9749dbb2 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_KVM_PAGE_TRACK_H #define _ASM_X86_KVM_PAGE_TRACK_H diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index bc62e7cbf1b1..7b407dda2bd7 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_KVM_PARA_H #define _ASM_X86_KVM_PARA_H @@ -87,8 +88,7 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, #ifdef CONFIG_KVM_GUEST bool kvm_para_available(void); unsigned int kvm_arch_para_features(void); -void __init kvm_guest_init(void); -void kvm_async_pf_task_wait(u32 token); +void kvm_async_pf_task_wait(u32 token, int interrupt_kernel); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_pf_reason(void); extern void kvm_disable_steal_time(void); @@ -102,8 +102,7 @@ static inline void kvm_spinlock_init(void) #endif /* CONFIG_PARAVIRT_SPINLOCKS */ #else /* CONFIG_KVM_GUEST */ -#define kvm_guest_init() do {} while (0) -#define kvm_async_pf_task_wait(T) do {} while(0) +#define kvm_async_pf_task_wait(T, I) do {} while(0) #define kvm_async_pf_task_wake(T) do {} while(0) static inline bool kvm_para_available(void) diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h index f260bef63591..eceea9299097 100644 --- a/arch/x86/include/asm/kvmclock.h +++ b/arch/x86/include/asm/kvmclock.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_KVM_CLOCK_H #define _ASM_X86_KVM_CLOCK_H diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 0ccb26dda126..14caa9d9fb7f 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_LINKAGE_H #define _ASM_X86_LINKAGE_H diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 7511978093eb..c91083c59845 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_LOCAL_H #define _ASM_X86_LOCAL_H diff --git a/arch/x86/include/asm/mach_timer.h b/arch/x86/include/asm/mach_timer.h index 88d0c3c74c13..044daf6fb8f6 100644 --- a/arch/x86/include/asm/mach_timer.h +++ b/arch/x86/include/asm/mach_timer.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Machine specific calibrate_tsc() for generic. * Split out from timer_tsc.c by Osamu Tomita <tomita@cinet.co.jp> diff --git a/arch/x86/include/asm/mach_traps.h b/arch/x86/include/asm/mach_traps.h index a01e7ec7d237..e39a517467cd 100644 --- a/arch/x86/include/asm/mach_traps.h +++ b/arch/x86/include/asm/mach_traps.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Machine specific NMI handling for generic. * Split out from traps.c by Osamu Tomita <tomita@cinet.co.jp> diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h index 0d9b14f60d2c..3c42743083ed 100644 --- a/arch/x86/include/asm/math_emu.h +++ b/arch/x86/include/asm/math_emu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MATH_EMU_H #define _ASM_X86_MATH_EMU_H diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h index 24acd9ba7837..1775a32f7ea6 100644 --- a/arch/x86/include/asm/mc146818rtc.h +++ b/arch/x86/include/asm/mc146818rtc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Machine dependent access functions for RTC registers. */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 181264989db5..b1e8d8db921f 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MCE_H #define _ASM_X86_MCE_H @@ -187,7 +188,6 @@ struct mca_msr_regs { extern struct mce_vendor_flags mce_flags; -extern struct mca_config mca_cfg; extern struct mca_msr_regs msr_ops; enum mce_notifier_prios { diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 6a77c63540f7..c9459a4c3c68 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -42,11 +42,17 @@ void __init sme_early_init(void); void __init sme_encrypt_kernel(void); void __init sme_enable(struct boot_params *bp); +int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); +int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); + /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void); void swiotlb_set_mem_attributes(void *vaddr, unsigned long size); +bool sme_active(void); +bool sev_active(void); + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define sme_me_mask 0ULL @@ -64,6 +70,14 @@ static inline void __init sme_early_init(void) { } static inline void __init sme_encrypt_kernel(void) { } static inline void __init sme_enable(struct boot_params *bp) { } +static inline bool sme_active(void) { return false; } +static inline bool sev_active(void) { return false; } + +static inline int __init +early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; } +static inline int __init +early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } + #endif /* CONFIG_AMD_MEM_ENCRYPT */ /* diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index daadeeea00b1..55520cec8b27 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MICROCODE_H #define _ASM_X86_MICROCODE_H diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 3d57009e168b..209492849566 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MICROCODE_AMD_H #define _ASM_X86_MICROCODE_AMD_H diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index e793fc9a9b20..d85a07d7154f 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MICROCODE_INTEL_H #define _ASM_X86_MICROCODE_INTEL_H diff --git a/arch/x86/include/asm/misc.h b/arch/x86/include/asm/misc.h index 475f5bbc7f53..bb049cca3729 100644 --- a/arch/x86/include/asm/misc.h +++ b/arch/x86/include/asm/misc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MISC_H #define _ASM_X86_MISC_H diff --git a/arch/x86/include/asm/mmconfig.h b/arch/x86/include/asm/mmconfig.h index 04a3fed22cfe..976486447e10 100644 --- a/arch/x86/include/asm/mmconfig.h +++ b/arch/x86/include/asm/mmconfig.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MMCONFIG_H #define _ASM_X86_MMCONFIG_H diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index bb8c597c2248..9ea26f167497 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MMU_H #define _ASM_X86_MMU_H diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 7ae318c340d9..6d16d15d09a0 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MMU_CONTEXT_H #define _ASM_X86_MMU_CONTEXT_H @@ -72,8 +73,8 @@ static inline void load_mm_ldt(struct mm_struct *mm) #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; - /* lockless_dereference synchronizes with smp_store_release */ - ldt = lockless_dereference(mm->context.ldt); + /* READ_ONCE synchronizes with smp_store_release */ + ldt = READ_ONCE(mm->context.ldt); /* * Any change to mm->context.ldt is followed by an IPI to all @@ -126,13 +127,7 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) DEBUG_LOCKS_WARN_ON(preemptible()); } -static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ - int cpu = smp_processor_id(); - - if (cpumask_test_cpu(cpu, mm_cpumask(mm))) - cpumask_clear_cpu(cpu, mm_cpumask(mm)); -} +void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) @@ -286,6 +281,32 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, return __pkru_allows_pkey(vma_pkey(vma), write); } +/* + * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID + * bits. This serves two purposes. It prevents a nasty situation in + * which PCID-unaware code saves CR3, loads some other value (with PCID + * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if + * the saved ASID was nonzero. It also means that any bugs involving + * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger + * deterministically. + */ + +static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid) +{ + if (static_cpu_has(X86_FEATURE_PCID)) { + VM_WARN_ON_ONCE(asid > 4094); + return __sme_pa(mm->pgd) | (asid + 1); + } else { + VM_WARN_ON_ONCE(asid != 0); + return __sme_pa(mm->pgd); + } +} + +static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid) +{ + VM_WARN_ON_ONCE(asid > 4094); + return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH; +} /* * This can be used from process context to figure out what the value of @@ -296,10 +317,8 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, */ static inline unsigned long __get_current_cr3_fast(void) { - unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd); - - if (static_cpu_has(X86_FEATURE_PCID)) - cr3 |= this_cpu_read(cpu_tlbstate.loaded_mm_asid); + unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm), + this_cpu_read(cpu_tlbstate.loaded_mm_asid)); /* For now, be very restrictive about when this can be called. */ VM_WARN_ON(in_nmi() || preemptible()); diff --git a/arch/x86/include/asm/mmx.h b/arch/x86/include/asm/mmx.h index 5cbf3135b971..f572d0f944bb 100644 --- a/arch/x86/include/asm/mmx.h +++ b/arch/x86/include/asm/mmx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MMX_H #define _ASM_X86_MMX_H diff --git a/arch/x86/include/asm/mmzone.h b/arch/x86/include/asm/mmzone.h index d497bc425cae..c41b41edd691 100644 --- a/arch/x86/include/asm/mmzone.h +++ b/arch/x86/include/asm/mmzone.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifdef CONFIG_X86_32 # include <asm/mmzone_32.h> #else diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index 1ec990bd7dc0..73d8dd14dda2 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Written by Pat Gaughen (gone@us.ibm.com) Mar 2002 * diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h index 129d9aa3ceb3..0c585046f744 100644 --- a/arch/x86/include/asm/mmzone_64.h +++ b/arch/x86/include/asm/mmzone_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* K8 NUMA support */ /* Copyright 2002,2003 by Andi Kleen, SuSE Labs */ /* 2.5 Version loosely based on the NUMAQ Code by Pat Gaughen. */ diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index 9eb7c718aaf8..7948a17febb4 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MODULE_H #define _ASM_X86_MODULE_H @@ -5,7 +6,7 @@ #include <asm/orc_types.h> struct mod_arch_specific { -#ifdef CONFIG_ORC_UNWINDER +#ifdef CONFIG_UNWINDER_ORC unsigned int num_orcs; int *orc_unwind_ip; struct orc_entry *orc_unwind; diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index c471ca1f9412..606cbaebd336 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MPSPEC_H #define _ASM_X86_MPSPEC_H diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h index b31f8c098271..a6bec8028480 100644 --- a/arch/x86/include/asm/mpspec_def.h +++ b/arch/x86/include/asm/mpspec_def.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MPSPEC_DEF_H #define _ASM_X86_MPSPEC_DEF_H @@ -58,7 +59,7 @@ struct mpc_table { #define MP_TRANSLATION 192 #define CPU_ENABLED 1 /* Processor is available */ -#define CPU_BOOTPROCESSOR 2 /* Processor is the BP */ +#define CPU_BOOTPROCESSOR 2 /* Processor is the boot CPU */ #define CPU_STEPPING_MASK 0x000F #define CPU_MODEL_MASK 0x00F0 diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h index 7d7404756bb4..61eb4b63c5ec 100644 --- a/arch/x86/include/asm/mpx.h +++ b/arch/x86/include/asm/mpx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MPX_H #define _ASM_X86_MPX_H diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 63cc96f064dc..5400add2885b 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MSHYPER_H #define _ASM_X86_MSHYPER_H @@ -179,7 +180,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) u64 input_address = input ? virt_to_phys(input) : 0; u64 output_address = output ? virt_to_phys(output) : 0; u64 hv_status; - register void *__sp asm(_ASM_SP); #ifdef CONFIG_X86_64 if (!hv_hypercall_pg) @@ -187,7 +187,7 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) __asm__ __volatile__("mov %4, %%r8\n" "call *%5" - : "=a" (hv_status), "+r" (__sp), + : "=a" (hv_status), ASM_CALL_CONSTRAINT, "+c" (control), "+d" (input_address) : "r" (output_address), "m" (hv_hypercall_pg) : "cc", "memory", "r8", "r9", "r10", "r11"); @@ -202,7 +202,7 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) __asm__ __volatile__("call *%7" : "=A" (hv_status), - "+c" (input_address_lo), "+r" (__sp) + "+c" (input_address_lo), ASM_CALL_CONSTRAINT : "A" (control), "b" (input_address_hi), "D"(output_address_hi), "S"(output_address_lo), @@ -224,12 +224,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) { u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT; - register void *__sp asm(_ASM_SP); #ifdef CONFIG_X86_64 { __asm__ __volatile__("call *%4" - : "=a" (hv_status), "+r" (__sp), + : "=a" (hv_status), ASM_CALL_CONSTRAINT, "+c" (control), "+d" (input1) : "m" (hv_hypercall_pg) : "cc", "r8", "r9", "r10", "r11"); @@ -242,7 +241,7 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) __asm__ __volatile__ ("call *%5" : "=A"(hv_status), "+c"(input1_lo), - "+r"(__sp) + ASM_CALL_CONSTRAINT : "A" (control), "b" (input1_hi), "m" (hv_hypercall_pg) @@ -291,6 +290,7 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, * to this information. */ extern u32 *hv_vp_index; +extern u32 hv_max_vp_index; /** * hv_cpu_number_to_vp_number() - Map CPU to VP. @@ -311,7 +311,7 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number) void hyperv_init(void); void hyperv_setup_mmu_ops(void); void hyper_alloc_mmu(void); -void hyperv_report_panic(struct pt_regs *regs); +void hyperv_report_panic(struct pt_regs *regs, long err); bool hv_is_hypercall_page_setup(void); void hyperv_cleanup(void); #else /* CONFIG_HYPERV */ diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index eb4b09b41df5..25ddd0916bb2 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MSI_H #define _ASM_X86_MSI_H #include <asm/hw_irq.h> diff --git a/arch/x86/include/asm/msidef.h b/arch/x86/include/asm/msidef.h index 4cc48af23fef..ee2f8ccc32d0 100644 --- a/arch/x86/include/asm/msidef.h +++ b/arch/x86/include/asm/msidef.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MSIDEF_H #define _ASM_X86_MSIDEF_H diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 17f5c12e1afd..34c4922bbc3f 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MSR_INDEX_H #define _ASM_X86_MSR_INDEX_H @@ -323,6 +324,9 @@ #define MSR_AMD64_IBSBRTARGET 0xc001103b #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_SEV 0xc0010131 +#define MSR_AMD64_SEV_ENABLED_BIT 0 +#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 diff --git a/arch/x86/include/asm/msr-trace.h b/arch/x86/include/asm/msr-trace.h index 7567225747d8..f6adbe96856a 100644 --- a/arch/x86/include/asm/msr-trace.h +++ b/arch/x86/include/asm/msr-trace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM msr diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 898dba2e2e2c..07962f5f6fba 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MSR_H #define _ASM_X86_MSR_H diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index bda3c27f0da0..39a2fb29378a 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MWAIT_H #define _ASM_X86_MWAIT_H diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 5f2fc4441b11..75ded1d13d98 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_NMI_H #define _ASM_X86_NMI_H diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h index aff2b3356101..12f12b5cf2ca 100644 --- a/arch/x86/include/asm/nops.h +++ b/arch/x86/include/asm/nops.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_NOPS_H #define _ASM_X86_NOPS_H diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index 01b493e5a99b..bbfde3d2662f 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_NUMA_H #define _ASM_X86_NUMA_H diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h index e7d6b8254742..9c8e9e85be77 100644 --- a/arch/x86/include/asm/numa_32.h +++ b/arch/x86/include/asm/numa_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_NUMA_32_H #define _ASM_X86_NUMA_32_H diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h index 72f9adf6eca4..c2bf1de5d901 100644 --- a/arch/x86/include/asm/olpc.h +++ b/arch/x86/include/asm/olpc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* OLPC machine specific definitions */ #ifndef _ASM_X86_OLPC_H diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h index 24487712e0b1..8c2a1daf7f72 100644 --- a/arch/x86/include/asm/olpc_ofw.h +++ b/arch/x86/include/asm/olpc_ofw.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_OLPC_OFW_H #define _ASM_X86_OLPC_OFW_H diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index cf8f619b305f..7555b48803a8 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_H #define _ASM_X86_PAGE_H diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h index 904f528cc8e8..94dbd51df58f 100644 --- a/arch/x86/include/asm/page_32.h +++ b/arch/x86/include/asm/page_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_32_H #define _ASM_X86_PAGE_32_H diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h index 3bae4969ac65..aa30c3241ea7 100644 --- a/arch/x86/include/asm/page_32_types.h +++ b/arch/x86/include/asm/page_32_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_32_DEFS_H #define _ASM_X86_PAGE_32_DEFS_H diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index b50df06ad251..4baa6bceb232 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_64_H #define _ASM_X86_PAGE_64_H diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 3f5f08b010d0..e1407312c412 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_64_DEFS_H #define _ASM_X86_PAGE_64_DEFS_H diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index b98ed9d14630..1e53560a84bb 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_DEFS_H #define _ASM_X86_PAGE_DEFS_H diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 12deec722cf0..283efcaac8af 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PARAVIRT_H #define _ASM_X86_PARAVIRT_H /* Various instructions on x86 need to be replaced for @@ -15,10 +16,9 @@ #include <linux/cpumask.h> #include <asm/frame.h> -static inline void load_sp0(struct tss_struct *tss, - struct thread_struct *thread) +static inline void load_sp0(unsigned long sp0) { - PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread); + PVOP_VCALL1(pv_cpu_ops.load_sp0, sp0); } /* The paravirtualized CPUID instruction. */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 42873edd9f9d..6ec54d01972d 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PARAVIRT_TYPES_H #define _ASM_X86_PARAVIRT_TYPES_H @@ -133,7 +134,7 @@ struct pv_cpu_ops { void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries); void (*free_ldt)(struct desc_struct *ldt, unsigned entries); - void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t); + void (*load_sp0)(unsigned long sp0); void (*set_iopl_mask)(unsigned mask); @@ -459,8 +460,8 @@ int paravirt_disable_iospace(void); */ #ifdef CONFIG_X86_32 #define PVOP_VCALL_ARGS \ - unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; \ - register void *__sp asm("esp") + unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; + #define PVOP_CALL_ARGS PVOP_VCALL_ARGS #define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x)) @@ -480,8 +481,8 @@ int paravirt_disable_iospace(void); /* [re]ax isn't an arg, but the return val */ #define PVOP_VCALL_ARGS \ unsigned long __edi = __edi, __esi = __esi, \ - __edx = __edx, __ecx = __ecx, __eax = __eax; \ - register void *__sp asm("rsp") + __edx = __edx, __ecx = __ecx, __eax = __eax; + #define PVOP_CALL_ARGS PVOP_VCALL_ARGS #define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x)) @@ -532,7 +533,7 @@ int paravirt_disable_iospace(void); asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : call_clbr, "+r" (__sp) \ + : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ paravirt_clobber(clbr), \ ##__VA_ARGS__ \ @@ -542,7 +543,7 @@ int paravirt_disable_iospace(void); asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : call_clbr, "+r" (__sp) \ + : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ paravirt_clobber(clbr), \ ##__VA_ARGS__ \ @@ -569,7 +570,7 @@ int paravirt_disable_iospace(void); asm volatile(pre \ paravirt_alt(PARAVIRT_CALL) \ post \ - : call_clbr, "+r" (__sp) \ + : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ paravirt_clobber(clbr), \ ##__VA_ARGS__ \ diff --git a/arch/x86/include/asm/parport.h b/arch/x86/include/asm/parport.h index 0d2d3b29118f..163f78259a7e 100644 --- a/arch/x86/include/asm/parport.h +++ b/arch/x86/include/asm/parport.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PARPORT_H #define _ASM_X86_PARPORT_H diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index fffb2794dd89..8a3ee355b422 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAT_H #define _ASM_X86_PAT_H diff --git a/arch/x86/include/asm/pci-direct.h b/arch/x86/include/asm/pci-direct.h index b1e7a45d868a..e1084f71a295 100644 --- a/arch/x86/include/asm/pci-direct.h +++ b/arch/x86/include/asm/pci-direct.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PCI_DIRECT_H #define _ASM_X86_PCI_DIRECT_H diff --git a/arch/x86/include/asm/pci-functions.h b/arch/x86/include/asm/pci-functions.h index ed0bab427354..1bbc10812ae1 100644 --- a/arch/x86/include/asm/pci-functions.h +++ b/arch/x86/include/asm/pci-functions.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * PCI BIOS function numbering for conventional PCI BIOS * systems diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 473a7295ab10..d32175e30259 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PCI_H #define _ASM_X86_PCI_H @@ -88,10 +89,8 @@ extern unsigned long pci_mem_start; #define PCIBIOS_MIN_CARDBUS_IO 0x4000 extern int pcibios_enabled; -void pcibios_config_init(void); void pcibios_scan_root(int bus); -void pcibios_set_master(struct pci_dev *dev); struct irq_routing_table *pcibios_get_irq_routing_table(void); int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h index fe15cfb21b9b..f5411de0ae11 100644 --- a/arch/x86/include/asm/pci_64.h +++ b/arch/x86/include/asm/pci_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PCI_64_H #define _ASM_X86_PCI_64_H diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 9f1b21f372fe..7a5d6695abd3 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Low-Level PCI Access for i386 machines. * diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 9fa03604b2b3..ba3c523aaf16 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PERCPU_H #define _ASM_X86_PERCPU_H @@ -525,7 +526,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr, { bool oldbit; - asm volatile("bt "__percpu_arg(2)",%1\n\t" + asm volatile("bt "__percpu_arg(2)",%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long __percpu *)addr), "Ir" (nr)); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index f353061bba1d..12f54082f4c8 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PERF_EVENT_H #define _ASM_X86_PERF_EVENT_H diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index d725382c2ae0..94de1a05aeba 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Netburst Performance Events (P4, old Xeon) */ diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index b2d0cd8288aa..4b5e1eafada7 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGALLOC_H #define _ASM_X86_PGALLOC_H diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index a8b96e708c2b..685ffe8a0eaf 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_2LEVEL_H #define _ASM_X86_PGTABLE_2LEVEL_H diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h index 373ab1de909f..f982ef808e7e 100644 --- a/arch/x86/include/asm/pgtable-2level_types.h +++ b/arch/x86/include/asm/pgtable-2level_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_2LEVEL_DEFS_H #define _ASM_X86_PGTABLE_2LEVEL_DEFS_H diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index c8821bab938f..bc4af5453802 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_3LEVEL_H #define _ASM_X86_PGTABLE_3LEVEL_H diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h index b8a4341faafa..876b4c77d983 100644 --- a/arch/x86/include/asm/pgtable-3level_types.h +++ b/arch/x86/include/asm/pgtable-3level_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_3LEVEL_DEFS_H #define _ASM_X86_PGTABLE_3LEVEL_DEFS_H diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index b714934512b3..09f9e1e00e3b 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_H #define _ASM_X86_PGTABLE_H @@ -666,11 +667,6 @@ static inline bool pte_accessible(struct mm_struct *mm, pte_t a) return false; } -static inline int pte_hidden(pte_t pte) -{ - return pte_flags(pte) & _PAGE_HIDDEN; -} - static inline int pmd_present(pmd_t pmd) { /* diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index bfab55675c16..e67c0620aec2 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_32_H #define _ASM_X86_PGTABLE_32_H diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index 9fb2f2bc8245..f2ca9b28fd68 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_32_DEFS_H #define _ASM_X86_PGTABLE_32_DEFS_H diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 972a4698c530..e9f05331e732 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_64_H #define _ASM_X86_PGTABLE_64_H diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 06470da156ba..6d5f45dcd4a1 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_64_DEFS_H #define _ASM_X86_PGTABLE_64_DEFS_H diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index f1492473f10e..3696398a9475 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_DEFS_H #define _ASM_X86_PGTABLE_DEFS_H @@ -31,7 +32,6 @@ #define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 #define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 -#define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ #define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ #define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4 @@ -78,18 +78,6 @@ #define _PAGE_KNL_ERRATUM_MASK 0 #endif -#ifdef CONFIG_KMEMCHECK -#define _PAGE_HIDDEN (_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN) -#else -#define _PAGE_HIDDEN (_AT(pteval_t, 0)) -#endif - -/* - * The same hidden bit is used by kmemcheck, but since kmemcheck - * works on kernel pages while soft-dirty engine on user space, - * they do not conflict with each other. - */ - #ifdef CONFIG_MEM_SOFT_DIRTY #define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY) #else @@ -199,10 +187,9 @@ enum page_cache_mode { #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) -#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ - _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_ENC) #define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ _PAGE_DIRTY | _PAGE_ENC) +#define _PAGE_TABLE (_KERNPG_TABLE | _PAGE_USER) #define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _PAGE_ENC) #define __PAGE_KERNEL_ENC_WP (__PAGE_KERNEL_WP | _PAGE_ENC) diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index b3b09b98896d..a0ba1ffda0df 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H diff --git a/arch/x86/include/asm/pm-trace.h b/arch/x86/include/asm/pm-trace.h index 7b7ac42c3661..bfa32aa428e5 100644 --- a/arch/x86/include/asm/pm-trace.h +++ b/arch/x86/include/asm/pm-trace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PM_TRACE_H #define _ASM_X86_PM_TRACE_H diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h index f565f6dd59d4..374336e217ff 100644 --- a/arch/x86/include/asm/posix_types.h +++ b/arch/x86/include/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ # ifdef CONFIG_X86_32 # include <asm/posix_types_32.h> # else diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index ec1f3c651150..7f2dbd91fc74 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_PREEMPT_H #define __ASM_PREEMPT_H @@ -100,19 +101,14 @@ static __always_inline bool should_resched(int preempt_offset) #ifdef CONFIG_PREEMPT extern asmlinkage void ___preempt_schedule(void); -# define __preempt_schedule() \ -({ \ - register void *__sp asm(_ASM_SP); \ - asm volatile ("call ___preempt_schedule" : "+r"(__sp)); \ -}) +# define __preempt_schedule() \ + asm volatile ("call ___preempt_schedule" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule(void); extern asmlinkage void ___preempt_schedule_notrace(void); -# define __preempt_schedule_notrace() \ -({ \ - register void *__sp asm(_ASM_SP); \ - asm volatile ("call ___preempt_schedule_notrace" : "+r"(__sp)); \ -}) +# define __preempt_schedule_notrace() \ + asm volatile ("call ___preempt_schedule_notrace" : ASM_CALL_CONSTRAINT) + extern asmlinkage void preempt_schedule_notrace(void); #endif diff --git a/arch/x86/include/asm/probe_roms.h b/arch/x86/include/asm/probe_roms.h index 4950a0b1d09c..1c7f3815bbd6 100644 --- a/arch/x86/include/asm/probe_roms.h +++ b/arch/x86/include/asm/probe_roms.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PROBE_ROMS_H_ #define _PROBE_ROMS_H_ struct pci_dev; diff --git a/arch/x86/include/asm/processor-cyrix.h b/arch/x86/include/asm/processor-cyrix.h index 1198f2a0e42c..aaedd73ea2c6 100644 --- a/arch/x86/include/asm/processor-cyrix.h +++ b/arch/x86/include/asm/processor-cyrix.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * NSC/Cyrix CPU indexed register access. Must be inlined instead of * macros to ensure correct access ordering diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index dc723b64acf0..43212a43ee69 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PROCESSOR_FLAGS_H #define _ASM_X86_PROCESSOR_FLAGS_H diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 3fa26a61eabc..cc16fa882e3e 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PROCESSOR_H #define _ASM_X86_PROCESSOR_H @@ -131,6 +132,7 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; + unsigned initialized : 1; } __randomize_layout; struct cpuid_regs { @@ -430,7 +432,9 @@ typedef struct { struct thread_struct { /* Cached TLS descriptors: */ struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES]; +#ifdef CONFIG_X86_32 unsigned long sp0; +#endif unsigned long sp; #ifdef CONFIG_X86_32 unsigned long sysenter_cs; @@ -517,16 +521,9 @@ static inline void native_set_iopl_mask(unsigned mask) } static inline void -native_load_sp0(struct tss_struct *tss, struct thread_struct *thread) +native_load_sp0(unsigned long sp0) { - tss->x86_tss.sp0 = thread->sp0; -#ifdef CONFIG_X86_32 - /* Only happens when SEP is enabled, no need to test "SEP"arately: */ - if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) { - tss->x86_tss.ss1 = thread->sysenter_cs; - wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); - } -#endif + this_cpu_write(cpu_tss.x86_tss.sp0, sp0); } static inline void native_swapgs(void) @@ -546,15 +543,20 @@ static inline unsigned long current_top_of_stack(void) #endif } +static inline bool on_thread_stack(void) +{ + return (unsigned long)(current_top_of_stack() - + current_stack_pointer) < THREAD_SIZE; +} + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else #define __cpuid native_cpuid -static inline void load_sp0(struct tss_struct *tss, - struct thread_struct *thread) +static inline void load_sp0(unsigned long sp0) { - native_load_sp0(tss, thread); + native_load_sp0(sp0); } #define set_iopl_mask native_set_iopl_mask @@ -677,8 +679,6 @@ static inline void sync_core(void) * Like all of Linux's memory ordering operations, this is a * compiler barrier as well. */ - register void *__sp asm(_ASM_SP); - #ifdef CONFIG_X86_32 asm volatile ( "pushfl\n\t" @@ -686,7 +686,7 @@ static inline void sync_core(void) "pushl $1f\n\t" "iret\n\t" "1:" - : "+r" (__sp) : : "memory"); + : ASM_CALL_CONSTRAINT : : "memory"); #else unsigned int tmp; @@ -703,7 +703,7 @@ static inline void sync_core(void) "iretq\n\t" UNWIND_HINT_RESTORE "1:" - : "=&r" (tmp), "+r" (__sp) : : "cc", "memory"); + : "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory"); #endif } @@ -805,6 +805,15 @@ static inline void spin_lock_prefetch(const void *x) #define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \ TOP_OF_KERNEL_STACK_PADDING) +#define task_top_of_stack(task) ((unsigned long)(task_pt_regs(task) + 1)) + +#define task_pt_regs(task) \ +({ \ + unsigned long __ptr = (unsigned long)task_stack_page(task); \ + __ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; \ + ((struct pt_regs *)__ptr) - 1; \ +}) + #ifdef CONFIG_X86_32 /* * User space process size: 3GB (default). @@ -824,23 +833,6 @@ static inline void spin_lock_prefetch(const void *x) .addr_limit = KERNEL_DS, \ } -/* - * TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack. - * This is necessary to guarantee that the entire "struct pt_regs" - * is accessible even if the CPU haven't stored the SS/ESP registers - * on the stack (interrupt gate does not save these registers - * when switching to the same priv ring). - * Therefore beware: accessing the ss/esp fields of the - * "struct pt_regs" is possible, but they may contain the - * completely wrong values. - */ -#define task_pt_regs(task) \ -({ \ - unsigned long __ptr = (unsigned long)task_stack_page(task); \ - __ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; \ - ((struct pt_regs *)__ptr) - 1; \ -}) - #define KSTK_ESP(task) (task_pt_regs(task)->sp) #else @@ -874,11 +866,9 @@ static inline void spin_lock_prefetch(const void *x) #define STACK_TOP_MAX TASK_SIZE_MAX #define INIT_THREAD { \ - .sp0 = TOP_OF_INIT_STACK, \ .addr_limit = KERNEL_DS, \ } -#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1) extern unsigned long KSTK_ESP(struct task_struct *task); #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index b408b1886195..6e81788a30c1 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PROTO_H #define _ASM_X86_PROTO_H diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 91c04c8e67fa..14131dd06b29 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PTRACE_H #define _ASM_X86_PTRACE_H @@ -135,9 +136,9 @@ static inline int v8086_mode(struct pt_regs *regs) #endif } -#ifdef CONFIG_X86_64 static inline bool user_64bit_mode(struct pt_regs *regs) { +#ifdef CONFIG_X86_64 #ifndef CONFIG_PARAVIRT /* * On non-paravirt systems, this is the only long mode CPL 3 @@ -148,8 +149,12 @@ static inline bool user_64bit_mode(struct pt_regs *regs) /* Headers are too twisted for this to go in paravirt.h. */ return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs; #endif +#else /* !CONFIG_X86_64 */ + return false; +#endif } +#ifdef CONFIG_X86_64 #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp #endif diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h index d7da2729903d..92c34e517da1 100644 --- a/arch/x86/include/asm/purgatory.h +++ b/arch/x86/include/asm/purgatory.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PURGATORY_H #define _ASM_X86_PURGATORY_H diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h index 67f08230103a..1436226efe3e 100644 --- a/arch/x86/include/asm/pvclock-abi.h +++ b/arch/x86/include/asm/pvclock-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PVCLOCK_ABI_H #define _ASM_X86_PVCLOCK_ABI_H #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 448cfe1b48cf..a7471dcd2205 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -1,18 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PVCLOCK_H #define _ASM_X86_PVCLOCK_H #include <linux/clocksource.h> #include <asm/pvclock-abi.h> -#ifdef CONFIG_KVM_GUEST -extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void); -#else -static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) -{ - return NULL; -} -#endif - /* some helper functions for xen and kvm pv clock sources */ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src); @@ -101,4 +93,14 @@ struct pvclock_vsyscall_time_info { #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) +#ifdef CONFIG_PARAVIRT_CLOCK +void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti); +struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void); +#else +static inline struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void) +{ + return NULL; +} +#endif + #endif /* _ASM_X86_PVCLOCK_H */ diff --git a/arch/x86/include/asm/qrwlock.h b/arch/x86/include/asm/qrwlock.h index c537cbb038a7..8656b5a6e8e7 100644 --- a/arch/x86/include/asm/qrwlock.h +++ b/arch/x86/include/asm/qrwlock.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_QRWLOCK_H #define _ASM_X86_QRWLOCK_H diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index 48a706f641f2..5e16b5d40d32 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -1,6 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_QSPINLOCK_H #define _ASM_X86_QSPINLOCK_H +#include <linux/jump_label.h> #include <asm/cpufeature.h> #include <asm-generic/qspinlock_types.h> #include <asm/paravirt.h> @@ -46,10 +48,14 @@ static inline void queued_spin_unlock(struct qspinlock *lock) #endif #ifdef CONFIG_PARAVIRT +DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key); + +void native_pv_lock_init(void) __init; + #define virt_spin_lock virt_spin_lock static inline bool virt_spin_lock(struct qspinlock *lock) { - if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) + if (!static_branch_likely(&virt_spin_lock_key)) return false; /* @@ -65,6 +71,10 @@ static inline bool virt_spin_lock(struct qspinlock *lock) return true; } +#else +static inline void native_pv_lock_init(void) +{ +} #endif /* CONFIG_PARAVIRT */ #include <asm-generic/qspinlock.h> diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 9d55f9b6e167..923307ea11c7 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_QSPINLOCK_PARAVIRT_H #define __ASM_QSPINLOCK_PARAVIRT_H diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 90d91520c13a..63b3393bd98e 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ARCH_X86_REALMODE_H #define _ARCH_X86_REALMODE_H diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index fc62ba8dce93..a671a1145906 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_REBOOT_H #define _ASM_X86_REBOOT_H diff --git a/arch/x86/include/asm/reboot_fixups.h b/arch/x86/include/asm/reboot_fixups.h index 765debe4c54c..96515658ce12 100644 --- a/arch/x86/include/asm/reboot_fixups.h +++ b/arch/x86/include/asm/reboot_fixups.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_REBOOT_FIXUPS_H #define _ASM_X86_REBOOT_FIXUPS_H diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index ff871210b9f2..4e44250e7d0d 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -15,7 +15,7 @@ * back to the regular execution flow in .text. */ #define _REFCOUNT_EXCEPTION \ - ".pushsection .text.unlikely\n" \ + ".pushsection .text..refcount\n" \ "111:\tlea %[counter], %%" _ASM_CX "\n" \ "112:\t" ASM_UD0 "\n" \ ASM_UNREACHABLE \ diff --git a/arch/x86/include/asm/rio.h b/arch/x86/include/asm/rio.h index 97bab6388a92..0a21986d2238 100644 --- a/arch/x86/include/asm/rio.h +++ b/arch/x86/include/asm/rio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Derived from include/asm-x86/mach-summit/mach_mpparse.h * and include/asm-x86/mach-default/bios_ebda.h diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 045f99211a99..f91c365e57c3 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_RMWcc #define _ASM_X86_RMWcc @@ -28,7 +29,7 @@ cc_label: \ #define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \ do { \ bool c; \ - asm volatile (fullop ";" CC_SET(cc) \ + asm volatile (fullop CC_SET(cc) \ : [counter] "+m" (var), CC_OUT(cc) (c) \ : __VA_ARGS__ : clobbers); \ return c; \ diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index a34e0d4b957d..4c25cf6caefa 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+ * * Written by David Howells (dhowells@redhat.com). @@ -60,18 +61,33 @@ /* * lock for reading */ +#define ____down_read(sem, slow_path) \ +({ \ + struct rw_semaphore* ret; \ + asm volatile("# beginning down_read\n\t" \ + LOCK_PREFIX _ASM_INC "(%[sem])\n\t" \ + /* adds 0x00000001 */ \ + " jns 1f\n" \ + " call " slow_path "\n" \ + "1:\n\t" \ + "# ending down_read\n\t" \ + : "+m" (sem->count), "=a" (ret), \ + ASM_CALL_CONSTRAINT \ + : [sem] "a" (sem) \ + : "memory", "cc"); \ + ret; \ +}) + static inline void __down_read(struct rw_semaphore *sem) { - asm volatile("# beginning down_read\n\t" - LOCK_PREFIX _ASM_INC "(%1)\n\t" - /* adds 0x00000001 */ - " jns 1f\n" - " call call_rwsem_down_read_failed\n" - "1:\n\t" - "# ending down_read\n\t" - : "+m" (sem->count) - : "a" (sem) - : "memory", "cc"); + ____down_read(sem, "call_rwsem_down_read_failed"); +} + +static inline int __down_read_killable(struct rw_semaphore *sem) +{ + if (IS_ERR(____down_read(sem, "call_rwsem_down_read_failed_killable"))) + return -EINTR; + return 0; } /* @@ -81,17 +97,18 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem) { long result, tmp; asm volatile("# beginning __down_read_trylock\n\t" - " mov %0,%1\n\t" + " mov %[count],%[result]\n\t" "1:\n\t" - " mov %1,%2\n\t" - " add %3,%2\n\t" + " mov %[result],%[tmp]\n\t" + " add %[inc],%[tmp]\n\t" " jle 2f\n\t" - LOCK_PREFIX " cmpxchg %2,%0\n\t" + LOCK_PREFIX " cmpxchg %[tmp],%[count]\n\t" " jnz 1b\n\t" "2:\n\t" "# ending __down_read_trylock\n\t" - : "+m" (sem->count), "=&a" (result), "=&r" (tmp) - : "i" (RWSEM_ACTIVE_READ_BIAS) + : [count] "+m" (sem->count), [result] "=&a" (result), + [tmp] "=&r" (tmp) + : [inc] "i" (RWSEM_ACTIVE_READ_BIAS) : "memory", "cc"); return result >= 0; } @@ -103,10 +120,9 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem) ({ \ long tmp; \ struct rw_semaphore* ret; \ - register void *__sp asm(_ASM_SP); \ \ asm volatile("# beginning down_write\n\t" \ - LOCK_PREFIX " xadd %1,(%4)\n\t" \ + LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" \ /* adds 0xffff0001, returns the old value */ \ " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \ /* was the active mask 0 before? */\ @@ -114,8 +130,9 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem) " call " slow_path "\n" \ "1:\n" \ "# ending down_write" \ - : "+m" (sem->count), "=d" (tmp), "=a" (ret), "+r" (__sp) \ - : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \ + : "+m" (sem->count), [tmp] "=d" (tmp), \ + "=a" (ret), ASM_CALL_CONSTRAINT \ + : [sem] "a" (sem), "[tmp]" (RWSEM_ACTIVE_WRITE_BIAS) \ : "memory", "cc"); \ ret; \ }) @@ -141,21 +158,21 @@ static inline bool __down_write_trylock(struct rw_semaphore *sem) bool result; long tmp0, tmp1; asm volatile("# beginning __down_write_trylock\n\t" - " mov %0,%1\n\t" + " mov %[count],%[tmp0]\n\t" "1:\n\t" " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" /* was the active mask 0 before? */ " jnz 2f\n\t" - " mov %1,%2\n\t" - " add %4,%2\n\t" - LOCK_PREFIX " cmpxchg %2,%0\n\t" + " mov %[tmp0],%[tmp1]\n\t" + " add %[inc],%[tmp1]\n\t" + LOCK_PREFIX " cmpxchg %[tmp1],%[count]\n\t" " jnz 1b\n\t" "2:\n\t" CC_SET(e) "# ending __down_write_trylock\n\t" - : "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1), - CC_OUT(e) (result) - : "er" (RWSEM_ACTIVE_WRITE_BIAS) + : [count] "+m" (sem->count), [tmp0] "=&a" (tmp0), + [tmp1] "=&r" (tmp1), CC_OUT(e) (result) + : [inc] "er" (RWSEM_ACTIVE_WRITE_BIAS) : "memory"); return result; } @@ -167,14 +184,14 @@ static inline void __up_read(struct rw_semaphore *sem) { long tmp; asm volatile("# beginning __up_read\n\t" - LOCK_PREFIX " xadd %1,(%2)\n\t" + LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" /* subtracts 1, returns the old value */ " jns 1f\n\t" " call call_rwsem_wake\n" /* expects old value in %edx */ "1:\n" "# ending __up_read\n" - : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (-RWSEM_ACTIVE_READ_BIAS) + : "+m" (sem->count), [tmp] "=d" (tmp) + : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_READ_BIAS) : "memory", "cc"); } @@ -185,14 +202,14 @@ static inline void __up_write(struct rw_semaphore *sem) { long tmp; asm volatile("# beginning __up_write\n\t" - LOCK_PREFIX " xadd %1,(%2)\n\t" + LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" /* subtracts 0xffff0001, returns the old value */ " jns 1f\n\t" " call call_rwsem_wake\n" /* expects old value in %edx */ "1:\n\t" "# ending __up_write\n" - : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (-RWSEM_ACTIVE_WRITE_BIAS) + : "+m" (sem->count), [tmp] "=d" (tmp) + : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_WRITE_BIAS) : "memory", "cc"); } @@ -202,7 +219,7 @@ static inline void __up_write(struct rw_semaphore *sem) static inline void __downgrade_write(struct rw_semaphore *sem) { asm volatile("# beginning __downgrade_write\n\t" - LOCK_PREFIX _ASM_ADD "%2,(%1)\n\t" + LOCK_PREFIX _ASM_ADD "%[inc],(%[sem])\n\t" /* * transitions 0xZZZZ0001 -> 0xYYYY0001 (i386) * 0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64) @@ -212,7 +229,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem) "1:\n\t" "# ending __downgrade_write\n" : "+m" (sem->count) - : "a" (sem), "er" (-RWSEM_WAITING_BIAS) + : [sem] "a" (sem), [inc] "er" (-RWSEM_WAITING_BIAS) : "memory", "cc"); } diff --git a/arch/x86/include/asm/seccomp.h b/arch/x86/include/asm/seccomp.h index 0c8c7c8861b4..2bd1338de236 100644 --- a/arch/x86/include/asm/seccomp.h +++ b/arch/x86/include/asm/seccomp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SECCOMP_H #define _ASM_X86_SECCOMP_H diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 2f75f30cb2f6..d6baf23782bc 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SECTIONS_H #define _ASM_X86_SECTIONS_H diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 066aaf813141..b20f9d623f9c 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SEGMENT_H #define _ASM_X86_SEGMENT_H diff --git a/arch/x86/include/asm/serial.h b/arch/x86/include/asm/serial.h index bb658211edad..ece8299d2695 100644 --- a/arch/x86/include/asm/serial.h +++ b/arch/x86/include/asm/serial.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SERIAL_H #define _ASM_X86_SERIAL_H diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index cd71273ec49d..bd090367236c 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SET_MEMORY_H #define _ASM_X86_SET_MEMORY_H diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index a65cf544686a..ae13bc974416 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SETUP_H #define _ASM_X86_SETUP_H diff --git a/arch/x86/include/asm/shmparam.h b/arch/x86/include/asm/shmparam.h index 0880cf0917b9..c4041819c3e5 100644 --- a/arch/x86/include/asm/shmparam.h +++ b/arch/x86/include/asm/shmparam.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SHMPARAM_H #define _ASM_X86_SHMPARAM_H diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index e6cd2c489dbb..140d890c2c98 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SIGCONTEXT_H #define _ASM_X86_SIGCONTEXT_H diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h index 34edd1650bae..f176114c04d4 100644 --- a/arch/x86/include/asm/sigframe.h +++ b/arch/x86/include/asm/sigframe.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SIGFRAME_H #define _ASM_X86_SIGFRAME_H diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h index 452c88b8ad06..bd26834724e5 100644 --- a/arch/x86/include/asm/sighandling.h +++ b/arch/x86/include/asm/sighandling.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SIGHANDLING_H #define _ASM_X86_SIGHANDLING_H diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 8af22be0fe61..5f9012ff52ed 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SIGNAL_H #define _ASM_X86_SIGNAL_H diff --git a/arch/x86/include/asm/simd.h b/arch/x86/include/asm/simd.h index 6c8a7ed13365..a341c878e977 100644 --- a/arch/x86/include/asm/simd.h +++ b/arch/x86/include/asm/simd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <asm/fpu/api.h> diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 47103eca3775..461f53d27708 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SMP_H #define _ASM_X86_SMP_H #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 1f5bee2c202f..4fc1e9d3c43e 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SPARSEMEM_H #define _ASM_X86_SPARSEMEM_H diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index a24dfcf79f4a..317fc59b512c 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SPECIAL_INSNS_H #define _ASM_X86_SPECIAL_INSNS_H diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 6d391909e864..5b6bc7016c22 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SPINLOCK_H #define _ASM_X86_SPINLOCK_H @@ -41,11 +42,4 @@ #include <asm/qrwlock.h> -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - -#define arch_spin_relax(lock) cpu_relax() -#define arch_read_relax(lock) cpu_relax() -#define arch_write_relax(lock) cpu_relax() - #endif /* _ASM_X86_SPINLOCK_H */ diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index 25311ebb446c..bf3e34b25afc 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SPINLOCK_TYPES_H #define _ASM_X86_SPINLOCK_TYPES_H diff --git a/arch/x86/include/asm/sta2x11.h b/arch/x86/include/asm/sta2x11.h index e9d32df89ccc..e0975e9c4f47 100644 --- a/arch/x86/include/asm/sta2x11.h +++ b/arch/x86/include/asm/sta2x11.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Header file for STMicroelectronics ConneXt (STA2X11) IOHub */ diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 8abedf1d650e..371b3a4af000 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * GCC stack protector support. * diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 2e41c50ddf47..8da111b3c342 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs diff --git a/arch/x86/include/asm/string.h b/arch/x86/include/asm/string.h index 09224d7a5862..c3c2c1914d65 100644 --- a/arch/x86/include/asm/string.h +++ b/arch/x86/include/asm/string.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifdef CONFIG_X86_32 # include <asm/string_32.h> #else diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h index e371e7229042..55d392c6bd29 100644 --- a/arch/x86/include/asm/string_32.h +++ b/arch/x86/include/asm/string_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_STRING_32_H #define _ASM_X86_STRING_32_H @@ -178,8 +179,6 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len) * No 3D Now! */ -#ifndef CONFIG_KMEMCHECK - #if (__GNUC__ >= 4) #define memcpy(t, f, n) __builtin_memcpy(t, f, n) #else @@ -188,13 +187,6 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len) ? __constant_memcpy((t), (f), (n)) \ : __memcpy((t), (f), (n))) #endif -#else -/* - * kmemcheck becomes very happy if we use the REP instructions unconditionally, - * because it means that we know both memory operands in advance. - */ -#define memcpy(t, f, n) __memcpy((t), (f), (n)) -#endif #endif #endif /* !CONFIG_FORTIFY_SOURCE */ diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index f372a70a523f..533f74c300c2 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_STRING_64_H #define _ASM_X86_STRING_64_H @@ -32,7 +33,6 @@ extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); #ifndef CONFIG_FORTIFY_SOURCE -#ifndef CONFIG_KMEMCHECK #if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 #define memcpy(dst, src, len) \ ({ \ @@ -45,13 +45,6 @@ extern void *__memcpy(void *to, const void *from, size_t len); __ret; \ }) #endif -#else -/* - * kmemcheck becomes very happy if we use the REP instructions unconditionally, - * because it means that we know both memory operands in advance. - */ -#define memcpy(dst, src, len) __inline_memcpy((dst), (src), (len)) -#endif #endif /* !CONFIG_FORTIFY_SOURCE */ #define __HAVE_ARCH_MEMSET diff --git a/arch/x86/include/asm/suspend.h b/arch/x86/include/asm/suspend.h index 2fab6c2c3575..ecffe81ff65c 100644 --- a/arch/x86/include/asm/suspend.h +++ b/arch/x86/include/asm/suspend.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifdef CONFIG_X86_32 # include <asm/suspend_32.h> #else diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 8e9dbe7b73a1..982c325dad33 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright 2001-2002 Pavel Machek <pavel@suse.cz> * Based on code diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 2bd96b4df140..7306e911faee 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright 2001-2003 Pavel Machek <pavel@suse.cz> * Based on code diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 14835dd205a5..78dd9df88157 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SVM_H #define __SVM_H diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h index d2f69b9ff732..bdf9aed40403 100644 --- a/arch/x86/include/asm/swiotlb.h +++ b/arch/x86/include/asm/swiotlb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SWIOTLB_H #define _ASM_X86_SWIOTLB_H diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index fcc5cd387fd1..8c6bd6863db9 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -1,6 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SWITCH_TO_H #define _ASM_X86_SWITCH_TO_H +#include <linux/sched/task_stack.h> + struct task_struct; /* one of the stranger aspects of C forward declarations */ struct task_struct *__switch_to_asm(struct task_struct *prev, @@ -72,4 +75,26 @@ do { \ ((last) = __switch_to_asm((prev), (next))); \ } while (0) +#ifdef CONFIG_X86_32 +static inline void refresh_sysenter_cs(struct thread_struct *thread) +{ + /* Only happens when SEP is enabled, no need to test "SEP"arately: */ + if (unlikely(this_cpu_read(cpu_tss.x86_tss.ss1) == thread->sysenter_cs)) + return; + + this_cpu_write(cpu_tss.x86_tss.ss1, thread->sysenter_cs); + wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); +} +#endif + +/* This is used when switching tasks or entering/exiting vm86 mode. */ +static inline void update_sp0(struct task_struct *task) +{ +#ifdef CONFIG_X86_32 + load_sp0(task->thread.sp0); +#else + load_sp0(task_top_of_stack(task)); +#endif +} + #endif /* _ASM_X86_SWITCH_TO_H */ diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h index cbf8847d02a0..2fe745356fb1 100644 --- a/arch/x86/include/asm/sync_bitops.h +++ b/arch/x86/include/asm/sync_bitops.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SYNC_BITOPS_H #define _ASM_X86_SYNC_BITOPS_H diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 91dfcafe27a6..bad25bb80679 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -21,7 +21,7 @@ asmlinkage long sys_ioperm(unsigned long, unsigned long, int); asmlinkage long sys_iopl(unsigned int); /* kernel/ldt.c */ -asmlinkage int sys_modify_ldt(int, void __user *, unsigned long); +asmlinkage long sys_modify_ldt(int, void __user *, unsigned long); /* kernel/signal.c */ asmlinkage long sys_rt_sigreturn(void); diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 90395063383c..2ecd34e2d46c 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TEXT_PATCHING_H #define _ASM_X86_TEXT_PATCHING_H diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 5161da1a0fa0..70f425947dc5 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: low-level thread information * * Copyright (C) 2002 David Howells (dhowells@redhat.com) @@ -158,17 +159,6 @@ struct thread_info { */ #ifndef __ASSEMBLY__ -static inline unsigned long current_stack_pointer(void) -{ - unsigned long sp; -#ifdef CONFIG_X86_64 - asm("mov %%rsp,%0" : "=g" (sp)); -#else - asm("mov %%esp,%0" : "=g" (sp)); -#endif - return sp; -} - /* * Walks up the stack frames to make sure that the specified object is * entirely contained by a single stack frame. diff --git a/arch/x86/include/asm/time.h b/arch/x86/include/asm/time.h index 92b8aec06970..cef818b16045 100644 --- a/arch/x86/include/asm/time.h +++ b/arch/x86/include/asm/time.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TIME_H #define _ASM_X86_TIME_H diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 2016962103df..7365dd4acffb 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TIMER_H #define _ASM_X86_TIMER_H #include <linux/pm.h> @@ -8,7 +9,7 @@ #define TICK_SIZE (tick_nsec / 1000) unsigned long long native_sched_clock(void); -extern int recalibrate_cpu_khz(void); +extern void recalibrate_cpu_khz(void); extern int no_timer_check; diff --git a/arch/x86/include/asm/timex.h b/arch/x86/include/asm/timex.h index 1375cfc93960..a4a8b1b16c0c 100644 --- a/arch/x86/include/asm/timex.h +++ b/arch/x86/include/asm/timex.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TIMEX_H #define _ASM_X86_TIMEX_H diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index 79a4ca6a9606..cb0a1f470980 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TLB_H #define _ASM_X86_TLB_H diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h index f4a6ff352a0e..1ad56eb3e8a8 100644 --- a/arch/x86/include/asm/tlbbatch.h +++ b/arch/x86/include/asm/tlbbatch.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ARCH_X86_TLBBATCH_H #define _ARCH_X86_TLBBATCH_H diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 4893abf7f74f..509046cfa5ce 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TLBFLUSH_H #define _ASM_X86_TLBFLUSH_H @@ -82,6 +83,22 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) #define __flush_tlb_single(addr) __native_flush_tlb_single(addr) #endif +static inline bool tlb_defer_switch_to_init_mm(void) +{ + /* + * If we have PCID, then switching to init_mm is reasonably + * fast. If we don't have PCID, then switching to init_mm is + * quite slow, so we try to defer it in the hopes that we can + * avoid it entirely. The latter approach runs the risk of + * receiving otherwise unnecessary IPIs. + * + * This choice is just a heuristic. The tlb code can handle this + * function returning true or false regardless of whether we have + * PCID. + */ + return !static_cpu_has(X86_FEATURE_PCID); +} + /* * 6 because 6 should be plenty and struct tlb_state will fit in * two cache lines. @@ -105,6 +122,23 @@ struct tlb_state { u16 next_asid; /* + * We can be in one of several states: + * + * - Actively using an mm. Our CPU's bit will be set in + * mm_cpumask(loaded_mm) and is_lazy == false; + * + * - Not using a real mm. loaded_mm == &init_mm. Our CPU's bit + * will not be set in mm_cpumask(&init_mm) and is_lazy == false. + * + * - Lazily using a real mm. loaded_mm != &init_mm, our bit + * is set in mm_cpumask(loaded_mm), but is_lazy == true. + * We're heuristically guessing that the CR3 load we + * skipped more than makes up for the overhead added by + * lazy mode. + */ + bool is_lazy; + + /* * Access to this CR4 shadow and to H/W CR4 is protected by * disabling interrupts when modifying either one. */ diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h index 5665bf205b8d..69615e387973 100644 --- a/arch/x86/include/asm/trace/exceptions.h +++ b/arch/x86/include/asm/trace/exceptions.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM exceptions diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h index 342e59789fcd..069c04be1507 100644 --- a/arch/x86/include/asm/trace/fpu.h +++ b/arch/x86/include/asm/trace/fpu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM x86_fpu @@ -12,35 +13,27 @@ DECLARE_EVENT_CLASS(x86_fpu, TP_STRUCT__entry( __field(struct fpu *, fpu) - __field(bool, fpregs_active) - __field(bool, fpstate_active) + __field(bool, initialized) __field(u64, xfeatures) __field(u64, xcomp_bv) ), TP_fast_assign( __entry->fpu = fpu; - __entry->fpregs_active = fpu->fpregs_active; - __entry->fpstate_active = fpu->fpstate_active; + __entry->initialized = fpu->initialized; if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->state.xsave.header.xfeatures; __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv; } ), - TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx", + TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, - __entry->fpregs_active, - __entry->fpstate_active, + __entry->initialized, __entry->xfeatures, __entry->xcomp_bv ) ); -DEFINE_EVENT(x86_fpu, x86_fpu_state, - TP_PROTO(struct fpu *fpu), - TP_ARGS(fpu) -); - DEFINE_EVENT(x86_fpu, x86_fpu_before_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) @@ -76,11 +69,6 @@ DEFINE_EVENT(x86_fpu, x86_fpu_activate_state, TP_ARGS(fpu) ); -DEFINE_EVENT(x86_fpu, x86_fpu_deactivate_state, - TP_PROTO(struct fpu *fpu), - TP_ARGS(fpu) -); - DEFINE_EVENT(x86_fpu, x86_fpu_init_state, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h index 1599d394c8c1..84b9ec0c1bc0 100644 --- a/arch/x86/include/asm/trace/irq_vectors.h +++ b/arch/x86/include/asm/trace/irq_vectors.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM irq_vectors @@ -137,6 +138,254 @@ DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic); DEFINE_IRQ_VECTOR_EVENT(thermal_apic); #endif +TRACE_EVENT(vector_config, + + TP_PROTO(unsigned int irq, unsigned int vector, + unsigned int cpu, unsigned int apicdest), + + TP_ARGS(irq, vector, cpu, apicdest), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( unsigned int, vector ) + __field( unsigned int, cpu ) + __field( unsigned int, apicdest ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->vector = vector; + __entry->cpu = cpu; + __entry->apicdest = apicdest; + ), + + TP_printk("irq=%u vector=%u cpu=%u apicdest=0x%08x", + __entry->irq, __entry->vector, __entry->cpu, + __entry->apicdest) +); + +DECLARE_EVENT_CLASS(vector_mod, + + TP_PROTO(unsigned int irq, unsigned int vector, + unsigned int cpu, unsigned int prev_vector, + unsigned int prev_cpu), + + TP_ARGS(irq, vector, cpu, prev_vector, prev_cpu), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( unsigned int, vector ) + __field( unsigned int, cpu ) + __field( unsigned int, prev_vector ) + __field( unsigned int, prev_cpu ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->vector = vector; + __entry->cpu = cpu; + __entry->prev_vector = prev_vector; + __entry->prev_cpu = prev_cpu; + + ), + + TP_printk("irq=%u vector=%u cpu=%u prev_vector=%u prev_cpu=%u", + __entry->irq, __entry->vector, __entry->cpu, + __entry->prev_vector, __entry->prev_cpu) +); + +#define DEFINE_IRQ_VECTOR_MOD_EVENT(name) \ +DEFINE_EVENT_FN(vector_mod, name, \ + TP_PROTO(unsigned int irq, unsigned int vector, \ + unsigned int cpu, unsigned int prev_vector, \ + unsigned int prev_cpu), \ + TP_ARGS(irq, vector, cpu, prev_vector, prev_cpu), NULL, NULL); \ + +DEFINE_IRQ_VECTOR_MOD_EVENT(vector_update); +DEFINE_IRQ_VECTOR_MOD_EVENT(vector_clear); + +DECLARE_EVENT_CLASS(vector_reserve, + + TP_PROTO(unsigned int irq, int ret), + + TP_ARGS(irq, ret), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->ret = ret; + ), + + TP_printk("irq=%u ret=%d", __entry->irq, __entry->ret) +); + +#define DEFINE_IRQ_VECTOR_RESERVE_EVENT(name) \ +DEFINE_EVENT_FN(vector_reserve, name, \ + TP_PROTO(unsigned int irq, int ret), \ + TP_ARGS(irq, ret), NULL, NULL); \ + +DEFINE_IRQ_VECTOR_RESERVE_EVENT(vector_reserve_managed); +DEFINE_IRQ_VECTOR_RESERVE_EVENT(vector_reserve); + +TRACE_EVENT(vector_alloc, + + TP_PROTO(unsigned int irq, unsigned int vector, bool reserved, + int ret), + + TP_ARGS(irq, vector, ret, reserved), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( unsigned int, vector ) + __field( bool, reserved ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->vector = ret < 0 ? 0 : vector; + __entry->reserved = reserved; + __entry->ret = ret > 0 ? 0 : ret; + ), + + TP_printk("irq=%u vector=%u reserved=%d ret=%d", + __entry->irq, __entry->vector, + __entry->reserved, __entry->ret) +); + +TRACE_EVENT(vector_alloc_managed, + + TP_PROTO(unsigned int irq, unsigned int vector, + int ret), + + TP_ARGS(irq, vector, ret), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( unsigned int, vector ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->vector = ret < 0 ? 0 : vector; + __entry->ret = ret > 0 ? 0 : ret; + ), + + TP_printk("irq=%u vector=%u ret=%d", + __entry->irq, __entry->vector, __entry->ret) +); + +DECLARE_EVENT_CLASS(vector_activate, + + TP_PROTO(unsigned int irq, bool is_managed, bool can_reserve, + bool early), + + TP_ARGS(irq, is_managed, can_reserve, early), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( bool, is_managed ) + __field( bool, can_reserve ) + __field( bool, early ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->is_managed = is_managed; + __entry->can_reserve = can_reserve; + __entry->early = early; + ), + + TP_printk("irq=%u is_managed=%d can_reserve=%d early=%d", + __entry->irq, __entry->is_managed, __entry->can_reserve, + __entry->early) +); + +#define DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(name) \ +DEFINE_EVENT_FN(vector_activate, name, \ + TP_PROTO(unsigned int irq, bool is_managed, \ + bool can_reserve, bool early), \ + TP_ARGS(irq, is_managed, can_reserve, early), NULL, NULL); \ + +DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_activate); +DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_deactivate); + +TRACE_EVENT(vector_teardown, + + TP_PROTO(unsigned int irq, bool is_managed, bool has_reserved), + + TP_ARGS(irq, is_managed, has_reserved), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( bool, is_managed ) + __field( bool, has_reserved ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->is_managed = is_managed; + __entry->has_reserved = has_reserved; + ), + + TP_printk("irq=%u is_managed=%d has_reserved=%d", + __entry->irq, __entry->is_managed, __entry->has_reserved) +); + +TRACE_EVENT(vector_setup, + + TP_PROTO(unsigned int irq, bool is_legacy, int ret), + + TP_ARGS(irq, is_legacy, ret), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( bool, is_legacy ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->is_legacy = is_legacy; + __entry->ret = ret; + ), + + TP_printk("irq=%u is_legacy=%d ret=%d", + __entry->irq, __entry->is_legacy, __entry->ret) +); + +TRACE_EVENT(vector_free_moved, + + TP_PROTO(unsigned int irq, unsigned int cpu, unsigned int vector, + bool is_managed), + + TP_ARGS(irq, cpu, vector, is_managed), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( unsigned int, cpu ) + __field( unsigned int, vector ) + __field( bool, is_managed ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->cpu = cpu; + __entry->vector = vector; + __entry->is_managed = is_managed; + ), + + TP_printk("irq=%u cpu=%u vector=%u is_managed=%d", + __entry->irq, __entry->cpu, __entry->vector, + __entry->is_managed) +); + + #endif /* CONFIG_X86_LOCAL_APIC */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h index 0f492fc50bce..7bd92db09e8d 100644 --- a/arch/x86/include/asm/trace/mpx.h +++ b/arch/x86/include/asm/trace/mpx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mpx diff --git a/arch/x86/include/asm/trace_clock.h b/arch/x86/include/asm/trace_clock.h index beab86cc282d..7061a5650969 100644 --- a/arch/x86/include/asm/trace_clock.h +++ b/arch/x86/include/asm/trace_clock.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TRACE_CLOCK_H #define _ASM_X86_TRACE_CLOCK_H diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 5545f6459bf5..1fadd310ff68 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TRAPS_H #define _ASM_X86_TRAPS_H @@ -37,9 +38,9 @@ asmlinkage void simd_coprocessor_error(void); #if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) asmlinkage void xen_divide_error(void); +asmlinkage void xen_xennmi(void); asmlinkage void xen_xendebug(void); asmlinkage void xen_xenint3(void); -asmlinkage void xen_nmi(void); asmlinkage void xen_overflow(void); asmlinkage void xen_bounds(void); asmlinkage void xen_invalid_op(void); @@ -144,4 +145,22 @@ enum { X86_TRAP_IRET = 32, /* 32, IRET Exception */ }; +/* + * Page fault error code bits: + * + * bit 0 == 0: no page found 1: protection fault + * bit 1 == 0: read access 1: write access + * bit 2 == 0: kernel-mode access 1: user-mode access + * bit 3 == 1: use of reserved bit detected + * bit 4 == 1: fault was an instruction fetch + * bit 5 == 1: protection keys block access + */ +enum x86_pf_error_code { + X86_PF_PROT = 1 << 0, + X86_PF_WRITE = 1 << 1, + X86_PF_USER = 1 << 2, + X86_PF_RSVD = 1 << 3, + X86_PF_INSTR = 1 << 4, + X86_PF_PK = 1 << 5, +}; #endif /* _ASM_X86_TRAPS_H */ diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index f5e6f1c417df..cf5d53c3f9ea 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * x86 TSC related functions */ @@ -31,15 +32,22 @@ static inline cycles_t get_cycles(void) extern struct system_counterval_t convert_art_to_tsc(u64 art); +extern void tsc_early_delay_calibrate(void); extern void tsc_init(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); +extern void mark_tsc_async_resets(char *reason); extern unsigned long native_calibrate_cpu(void); extern unsigned long native_calibrate_tsc(void); extern unsigned long long native_sched_clock_from_tsc(u64 tsc); extern int tsc_clocksource_reliable; +#ifdef CONFIG_X86_TSC +extern bool tsc_async_resets; +#else +# define tsc_async_resets false +#endif /* * Boot-time check whether the TSCs are synchronized across diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 184eb9894dae..574dff4d2913 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_H #define _ASM_X86_UACCESS_H /* @@ -166,11 +167,11 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) ({ \ int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ - register void *__sp asm(_ASM_SP); \ __chk_user_ptr(ptr); \ might_fault(); \ asm volatile("call __get_user_%P4" \ - : "=a" (__ret_gu), "=r" (__val_gu), "+r" (__sp) \ + : "=a" (__ret_gu), "=r" (__val_gu), \ + ASM_CALL_CONSTRAINT \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ @@ -337,7 +338,7 @@ do { \ _ASM_EXTABLE(1b, 4b) \ _ASM_EXTABLE(2b, 4b) \ : "=r" (retval), "=&A"(x) \ - : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1), \ + : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1), \ "i" (errret), "0" (retval)); \ }) diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index aeda9bb8af50..72950401b223 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_32_H #define _ASM_X86_UACCESS_32_H diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index b16f6a1d8b26..f07ef3c575db 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_64_H #define _ASM_X86_UACCESS_64_H diff --git a/arch/x86/include/asm/umip.h b/arch/x86/include/asm/umip.h new file mode 100644 index 000000000000..db43f2a0d92c --- /dev/null +++ b/arch/x86/include/asm/umip.h @@ -0,0 +1,12 @@ +#ifndef _ASM_X86_UMIP_H +#define _ASM_X86_UMIP_H + +#include <linux/types.h> +#include <asm/ptrace.h> + +#ifdef CONFIG_X86_INTEL_UMIP +bool fixup_umip_exception(struct pt_regs *regs); +#else +static inline bool fixup_umip_exception(struct pt_regs *regs) { return false; } +#endif /* CONFIG_X86_INTEL_UMIP */ +#endif /* _ASM_X86_UMIP_H */ diff --git a/arch/x86/include/asm/unaligned.h b/arch/x86/include/asm/unaligned.h index a7bd416b4763..9c754a7447aa 100644 --- a/arch/x86/include/asm/unaligned.h +++ b/arch/x86/include/asm/unaligned.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UNALIGNED_H #define _ASM_X86_UNALIGNED_H diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 1ba1536f627e..51c4eee00732 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UNISTD_H #define _ASM_X86_UNISTD_H 1 diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index e9f793e2df7a..e9cc6fe1fc6f 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UNWIND_H #define _ASM_X86_UNWIND_H @@ -12,11 +13,11 @@ struct unwind_state { struct task_struct *task; int graph_idx; bool error; -#if defined(CONFIG_ORC_UNWINDER) +#if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; struct pt_regs *regs; -#elif defined(CONFIG_FRAME_POINTER_UNWINDER) +#elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; struct pt_regs *regs; @@ -50,7 +51,7 @@ void unwind_start(struct unwind_state *state, struct task_struct *task, __unwind_start(state, task, regs, first_frame); } -#if defined(CONFIG_ORC_UNWINDER) || defined(CONFIG_FRAME_POINTER_UNWINDER) +#if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) { if (unwind_done(state)) @@ -65,7 +66,7 @@ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) } #endif -#ifdef CONFIG_ORC_UNWINDER +#ifdef CONFIG_UNWINDER_ORC void unwind_init(void); void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size); diff --git a/arch/x86/include/asm/user.h b/arch/x86/include/asm/user.h index 59a54e869f15..413c91746b27 100644 --- a/arch/x86/include/asm/user.h +++ b/arch/x86/include/asm/user.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_USER_H #define _ASM_X86_USER_H diff --git a/arch/x86/include/asm/user32.h b/arch/x86/include/asm/user32.h index 14cbb73ebcba..fa577312f63a 100644 --- a/arch/x86/include/asm/user32.h +++ b/arch/x86/include/asm/user32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_USER32_H #define _ASM_X86_USER32_H diff --git a/arch/x86/include/asm/user_32.h b/arch/x86/include/asm/user_32.h index bebfd8644016..d72c3d66e94f 100644 --- a/arch/x86/include/asm/user_32.h +++ b/arch/x86/include/asm/user_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_USER_32_H #define _ASM_X86_USER_32_H diff --git a/arch/x86/include/asm/user_64.h b/arch/x86/include/asm/user_64.h index faf2cd3e0d76..db909923611c 100644 --- a/arch/x86/include/asm/user_64.h +++ b/arch/x86/include/asm/user_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_USER_64_H #define _ASM_X86_USER_64_H diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index b5a32231abd8..a80c0673798f 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UV_UV_H #define _ASM_X86_UV_UV_H diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 9cffb44a3cf5..036e26d63d9a 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -776,23 +776,36 @@ static inline int uv_num_possible_blades(void) extern void uv_nmi_setup(void); extern void uv_nmi_setup_hubless(void); +/* BIOS/Kernel flags exchange MMR */ +#define UVH_BIOS_KERNEL_MMR UVH_SCRATCH5 +#define UVH_BIOS_KERNEL_MMR_ALIAS UVH_SCRATCH5_ALIAS +#define UVH_BIOS_KERNEL_MMR_ALIAS_2 UVH_SCRATCH5_ALIAS_2 + +/* TSC sync valid, set by BIOS */ +#define UVH_TSC_SYNC_MMR UVH_BIOS_KERNEL_MMR +#define UVH_TSC_SYNC_SHIFT 10 +#define UVH_TSC_SYNC_SHIFT_UV2K 16 /* UV2/3k have different bits */ +#define UVH_TSC_SYNC_MASK 3 /* 0011 */ +#define UVH_TSC_SYNC_VALID 3 /* 0011 */ +#define UVH_TSC_SYNC_INVALID 2 /* 0010 */ + /* BMC sets a bit this MMR non-zero before sending an NMI */ -#define UVH_NMI_MMR UVH_SCRATCH5 -#define UVH_NMI_MMR_CLEAR UVH_SCRATCH5_ALIAS +#define UVH_NMI_MMR UVH_BIOS_KERNEL_MMR +#define UVH_NMI_MMR_CLEAR UVH_BIOS_KERNEL_MMR_ALIAS #define UVH_NMI_MMR_SHIFT 63 -#define UVH_NMI_MMR_TYPE "SCRATCH5" +#define UVH_NMI_MMR_TYPE "SCRATCH5" /* Newer SMM NMI handler, not present in all systems */ #define UVH_NMI_MMRX UVH_EVENT_OCCURRED0 #define UVH_NMI_MMRX_CLEAR UVH_EVENT_OCCURRED0_ALIAS #define UVH_NMI_MMRX_SHIFT UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT -#define UVH_NMI_MMRX_TYPE "EXTIO_INT0" +#define UVH_NMI_MMRX_TYPE "EXTIO_INT0" /* Non-zero indicates newer SMM NMI handler present */ #define UVH_NMI_MMRX_SUPPORTED UVH_EXTIO_INT0_BROADCAST /* Indicates to BIOS that we want to use the newer SMM NMI handler */ -#define UVH_NMI_MMRX_REQ UVH_SCRATCH5_ALIAS_2 +#define UVH_NMI_MMRX_REQ UVH_BIOS_KERNEL_MMR_ALIAS_2 #define UVH_NMI_MMRX_REQ_SHIFT 62 struct uv_hub_nmi_s { diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index bccdf4938ddf..27566e57e87d 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_VDSO_H #define _ASM_X86_VDSO_H diff --git a/arch/x86/include/asm/vga.h b/arch/x86/include/asm/vga.h index 9f42beefc67a..46f9b2deab4d 100644 --- a/arch/x86/include/asm/vga.h +++ b/arch/x86/include/asm/vga.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Access to VGA videoram * diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index 022e59714562..fb856c9f0449 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_VGTOD_H #define _ASM_X86_VGTOD_H @@ -48,7 +49,7 @@ static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s) unsigned ret; repeat: - ret = ACCESS_ONCE(s->seq); + ret = READ_ONCE(s->seq); if (unlikely(ret & 1)) { cpu_relax(); goto repeat; diff --git a/arch/x86/include/asm/vm86.h b/arch/x86/include/asm/vm86.h index 1e491f3af317..26efbec94448 100644 --- a/arch/x86/include/asm/vm86.h +++ b/arch/x86/include/asm/vm86.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_VM86_H #define _ASM_X86_VM86_H diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index caec8417539f..8b6780751132 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -70,11 +70,11 @@ #define SECONDARY_EXEC_APIC_REGISTER_VIRT 0x00000100 #define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY 0x00000200 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400 -#define SECONDARY_EXEC_RDRAND 0x00000800 +#define SECONDARY_EXEC_RDRAND_EXITING 0x00000800 #define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000 #define SECONDARY_EXEC_ENABLE_VMFUNC 0x00002000 #define SECONDARY_EXEC_SHADOW_VMCS 0x00004000 -#define SECONDARY_EXEC_RDSEED 0x00010000 +#define SECONDARY_EXEC_RDSEED_EXITING 0x00010000 #define SECONDARY_EXEC_ENABLE_PML 0x00020000 #define SECONDARY_EXEC_XSAVES 0x00100000 #define SECONDARY_EXEC_TSC_SCALING 0x02000000 diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index 6ba66ee79710..d9a7c659009c 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_VSYSCALL_H #define _ASM_X86_VSYSCALL_H diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h index 5b238981542a..06006b0351f3 100644 --- a/arch/x86/include/asm/word-at-a-time.h +++ b/arch/x86/include/asm/word-at-a-time.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H diff --git a/arch/x86/include/asm/x2apic.h b/arch/x86/include/asm/x2apic.h deleted file mode 100644 index f90f0a587c66..000000000000 --- a/arch/x86/include/asm/x2apic.h +++ /dev/null @@ -1,49 +0,0 @@ -/* - * Common bits for X2APIC cluster/physical modes. - */ - -#ifndef _ASM_X86_X2APIC_H -#define _ASM_X86_X2APIC_H - -#include <asm/apic.h> -#include <asm/ipi.h> -#include <linux/cpumask.h> - -static int x2apic_apic_id_valid(int apicid) -{ - return 1; -} - -static int x2apic_apic_id_registered(void) -{ - return 1; -} - -static void -__x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest) -{ - unsigned long cfg = __prepare_ICR(0, vector, dest); - native_x2apic_icr_write(cfg, apicid); -} - -static unsigned int x2apic_get_apic_id(unsigned long id) -{ - return id; -} - -static unsigned long x2apic_set_apic_id(unsigned int id) -{ - return id; -} - -static int x2apic_phys_pkg_id(int initial_apicid, int index_msb) -{ - return initial_apicid >> index_msb; -} - -static void x2apic_send_IPI_self(int vector) -{ - apic_write(APIC_SELF_IPI, vector); -} - -#endif /* _ASM_X86_X2APIC_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 7ba7e90a9ad6..aa4747569e23 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H @@ -50,11 +51,13 @@ struct x86_init_resources { * are set up. * @intr_init: interrupt init code * @trap_init: platform specific trap setup + * @intr_mode_init: interrupt delivery mode setup */ struct x86_init_irqs { void (*pre_vector_init)(void); void (*intr_init)(void); void (*trap_init)(void); + void (*intr_mode_init)(void); }; /** @@ -114,6 +117,20 @@ struct x86_init_pci { }; /** + * struct x86_hyper_init - x86 hypervisor init functions + * @init_platform: platform setup + * @guest_late_init: guest late init + * @x2apic_available: X2APIC detection + * @init_mem_mapping: setup early mappings during init_mem_mapping() + */ +struct x86_hyper_init { + void (*init_platform)(void); + void (*guest_late_init)(void); + bool (*x2apic_available)(void); + void (*init_mem_mapping)(void); +}; + +/** * struct x86_init_ops - functions for platform specific setup * */ @@ -126,6 +143,7 @@ struct x86_init_ops { struct x86_init_timers timers; struct x86_init_iommu iommu; struct x86_init_pci pci; + struct x86_hyper_init hyper; }; /** @@ -194,11 +212,21 @@ enum x86_legacy_i8042_state { struct x86_legacy_features { enum x86_legacy_i8042_state i8042; int rtc; + int no_vga; int reserve_bios_regions; struct x86_legacy_devices devices; }; /** + * struct x86_hyper_runtime - x86 hypervisor specific runtime callbacks + * + * @pin_vcpu: pin current vcpu to specified physical cpu (run rarely) + */ +struct x86_hyper_runtime { + void (*pin_vcpu)(int cpu); +}; + +/** * struct x86_platform_ops - platform specific runtime functions * @calibrate_cpu: calibrate CPU * @calibrate_tsc: calibrate TSC, if different from CPU @@ -217,6 +245,7 @@ struct x86_legacy_features { * possible in x86_early_init_platform_quirks() by * only using the current x86_hardware_subarch * semantics. + * @hyper: x86 hypervisor specific runtime callbacks */ struct x86_platform_ops { unsigned long (*calibrate_cpu)(void); @@ -232,6 +261,7 @@ struct x86_platform_ops { void (*apic_post_init)(void); struct x86_legacy_features legacy; void (*set_legacy_features)(void); + struct x86_hyper_runtime hyper; }; struct pci_dev; diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h index 3bdd10d71223..a9630104f1c4 100644 --- a/arch/x86/include/asm/xen/cpuid.h +++ b/arch/x86/include/asm/xen/cpuid.h @@ -74,21 +74,43 @@ #define XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD (1u<<0) /* + * Leaf 4 (0x40000x03) + * Sub-leaf 0: EAX: bit 0: emulated tsc + * bit 1: host tsc is known to be reliable + * bit 2: RDTSCP instruction available + * EBX: tsc_mode: 0=default (emulate if necessary), 1=emulate, + * 2=no emulation, 3=no emulation + TSC_AUX support + * ECX: guest tsc frequency in kHz + * EDX: guest tsc incarnation (migration count) + * Sub-leaf 1: EAX: tsc offset low part + * EBX: tsc offset high part + * ECX: multiplicator for tsc->ns conversion + * EDX: shift amount for tsc->ns conversion + * Sub-leaf 2: EAX: host tsc frequency in kHz + */ + +/* * Leaf 5 (0x40000x04) * HVM-specific features - * EAX: Features - * EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag) + * Sub-leaf 0: EAX: Features + * Sub-leaf 0: EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag) */ - -/* Virtualized APIC registers */ -#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0) -/* Virtualized x2APIC accesses */ -#define XEN_HVM_CPUID_X2APIC_VIRT (1u << 1) +#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0) /* Virtualized APIC registers */ +#define XEN_HVM_CPUID_X2APIC_VIRT (1u << 1) /* Virtualized x2APIC accesses */ /* Memory mapped from other domains has valid IOMMU entries */ #define XEN_HVM_CPUID_IOMMU_MAPPINGS (1u << 2) -/* vcpu id is present in EBX */ -#define XEN_HVM_CPUID_VCPU_ID_PRESENT (1u << 3) +#define XEN_HVM_CPUID_VCPU_ID_PRESENT (1u << 3) /* vcpu id is present in EBX */ + +/* + * Leaf 6 (0x40000x05) + * PV-specific parameters + * Sub-leaf 0: EAX: max available sub-leaf + * Sub-leaf 0: EBX: bits 0-7: max machine address width + */ + +/* Max. address width in bits taking memory hotplug into account. */ +#define XEN_CPUID_MACHINE_ADDRESS_WIDTH_MASK (0xffu << 0) -#define XEN_CPUID_MAX_NUM_LEAVES 4 +#define XEN_CPUID_MAX_NUM_LEAVES 5 #endif /* __XEN_PUBLIC_ARCH_X86_CPUID_H__ */ diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h index e6911caf5bbf..d383140e1dc8 100644 --- a/arch/x86/include/asm/xen/events.h +++ b/arch/x86/include/asm/xen/events.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_XEN_EVENTS_H #define _ASM_X86_XEN_EVENTS_H diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 9606688caa4b..7cb282e9e587 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -113,10 +113,9 @@ extern struct { char _entry[32]; } hypercall_page[]; register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \ register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \ register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \ - register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; \ - register void *__sp asm(_ASM_SP); + register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; -#define __HYPERCALL_0PARAM "=r" (__res), "+r" (__sp) +#define __HYPERCALL_0PARAM "=r" (__res), ASM_CALL_CONSTRAINT #define __HYPERCALL_1PARAM __HYPERCALL_0PARAM, "+r" (__arg1) #define __HYPERCALL_2PARAM __HYPERCALL_1PARAM, "+r" (__arg2) #define __HYPERCALL_3PARAM __HYPERCALL_2PARAM, "+r" (__arg3) @@ -552,13 +551,13 @@ static inline void MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, struct desc_struct desc) { - u32 *p = (u32 *) &desc; - mcl->op = __HYPERVISOR_update_descriptor; if (sizeof(maddr) == sizeof(long)) { mcl->args[0] = maddr; mcl->args[1] = *(unsigned long *)&desc; } else { + u32 *p = (u32 *)&desc; + mcl->args[0] = maddr; mcl->args[1] = maddr >> 32; mcl->args[2] = *p++; diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h index 8413688b2571..dc40578abded 100644 --- a/arch/x86/include/asm/xen/interface_32.h +++ b/arch/x86/include/asm/xen/interface_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /****************************************************************************** * arch-x86_32.h * diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h index 839a4811cf98..c599ec269a25 100644 --- a/arch/x86/include/asm/xen/interface_64.h +++ b/arch/x86/include/asm/xen/interface_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_XEN_INTERFACE_64_H #define _ASM_X86_XEN_INTERFACE_64_H diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h index f02f025ff988..116777e7f387 100644 --- a/arch/x86/include/asm/xen/page-coherent.h +++ b/arch/x86/include/asm/xen/page-coherent.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_XEN_PAGE_COHERENT_H #define _ASM_X86_XEN_PAGE_COHERENT_H diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 07b6531813c4..123e669bf363 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_XEN_PAGE_H #define _ASM_X86_XEN_PAGE_H @@ -26,6 +27,15 @@ typedef struct xpaddr { phys_addr_t paddr; } xpaddr_t; +#ifdef CONFIG_X86_64 +#define XEN_PHYSICAL_MASK __sme_clr((1UL << 52) - 1) +#else +#define XEN_PHYSICAL_MASK __PHYSICAL_MASK +#endif + +#define XEN_PTE_MFN_MASK ((pteval_t)(((signed long)PAGE_MASK) & \ + XEN_PHYSICAL_MASK)) + #define XMADDR(x) ((xmaddr_t) { .maddr = (x) }) #define XPADDR(x) ((xpaddr_t) { .paddr = (x) }) @@ -277,7 +287,7 @@ static inline unsigned long bfn_to_local_pfn(unsigned long mfn) static inline unsigned long pte_mfn(pte_t pte) { - return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT; + return (pte.pte & XEN_PTE_MFN_MASK) >> PAGE_SHIFT; } static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot) diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index f320ee32d5a1..3506d8c598c1 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_XEN_PCI_H #define _ASM_X86_XEN_PCI_H diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h index ee52fcac6f72..6b56d0d45d15 100644 --- a/arch/x86/include/asm/xen/swiotlb-xen.h +++ b/arch/x86/include/asm/xen/swiotlb-xen.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SWIOTLB_XEN_H #define _ASM_X86_SWIOTLB_XEN_H diff --git a/arch/x86/include/asm/xen/trace_types.h b/arch/x86/include/asm/xen/trace_types.h index 21e1874c0a0b..2aad0abd68e2 100644 --- a/arch/x86/include/asm/xen/trace_types.h +++ b/arch/x86/include/asm/xen/trace_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_XEN_TRACE_TYPES_H #define _ASM_XEN_TRACE_TYPES_H diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h index 1f5c5161ead6..45c8605467f1 100644 --- a/arch/x86/include/asm/xor.h +++ b/arch/x86/include/asm/xor.h @@ -1,7 +1,4 @@ -#ifdef CONFIG_KMEMCHECK -/* kmemcheck doesn't handle MMX/SSE/SSE2 instructions */ -# include <asm-generic/xor.h> -#elif !defined(_ASM_X86_XOR_H) +#ifndef _ASM_X86_XOR_H #define _ASM_X86_XOR_H /* diff --git a/arch/x86/include/asm/xor_64.h b/arch/x86/include/asm/xor_64.h index 546f1e3b87cc..0307e4ec5044 100644 --- a/arch/x86/include/asm/xor_64.h +++ b/arch/x86/include/asm/xor_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_XOR_64_H #define _ASM_X86_XOR_64_H diff --git a/arch/x86/include/uapi/asm/a.out.h b/arch/x86/include/uapi/asm/a.out.h index 4684f97a5bbd..094c49d8ea8e 100644 --- a/arch/x86/include/uapi/asm/a.out.h +++ b/arch/x86/include/uapi/asm/a.out.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_A_OUT_H #define _ASM_X86_A_OUT_H diff --git a/arch/x86/include/uapi/asm/auxvec.h b/arch/x86/include/uapi/asm/auxvec.h index 77203ac352de..580e3c567046 100644 --- a/arch/x86/include/uapi/asm/auxvec.h +++ b/arch/x86/include/uapi/asm/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_AUXVEC_H #define _ASM_X86_AUXVEC_H /* diff --git a/arch/x86/include/uapi/asm/bitsperlong.h b/arch/x86/include/uapi/asm/bitsperlong.h index 217909b4d6f5..5d72c8458838 100644 --- a/arch/x86/include/uapi/asm/bitsperlong.h +++ b/arch/x86/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_X86_BITSPERLONG_H #define __ASM_X86_BITSPERLONG_H diff --git a/arch/x86/include/uapi/asm/boot.h b/arch/x86/include/uapi/asm/boot.h index 94292c4c8122..88ffc5aee087 100644 --- a/arch/x86/include/uapi/asm/boot.h +++ b/arch/x86/include/uapi/asm/boot.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_BOOT_H #define _UAPI_ASM_X86_BOOT_H diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 66b8f93333d1..afdd5ae0fcc4 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_BOOTPARAM_H #define _ASM_X86_BOOTPARAM_H diff --git a/arch/x86/include/uapi/asm/byteorder.h b/arch/x86/include/uapi/asm/byteorder.h index b13a7a88f3eb..484e3cfd7ef2 100644 --- a/arch/x86/include/uapi/asm/byteorder.h +++ b/arch/x86/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BYTEORDER_H #define _ASM_X86_BYTEORDER_H diff --git a/arch/x86/include/uapi/asm/debugreg.h b/arch/x86/include/uapi/asm/debugreg.h index 3c0874dd9861..d95d080b30e3 100644 --- a/arch/x86/include/uapi/asm/debugreg.h +++ b/arch/x86/include/uapi/asm/debugreg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_DEBUGREG_H #define _UAPI_ASM_X86_DEBUGREG_H diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h index 9dafe59cf6e2..2f491efe3a12 100644 --- a/arch/x86/include/uapi/asm/e820.h +++ b/arch/x86/include/uapi/asm/e820.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_E820_H #define _UAPI_ASM_X86_E820_H #define E820MAP 0x2d0 /* our map */ diff --git a/arch/x86/include/uapi/asm/hw_breakpoint.h b/arch/x86/include/uapi/asm/hw_breakpoint.h index 79a9626b5500..6789884c7701 100644 --- a/arch/x86/include/uapi/asm/hw_breakpoint.h +++ b/arch/x86/include/uapi/asm/hw_breakpoint.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* */ diff --git a/arch/x86/include/uapi/asm/hwcap2.h b/arch/x86/include/uapi/asm/hwcap2.h index 0bd2be5c7617..6ebaae90e207 100644 --- a/arch/x86/include/uapi/asm/hwcap2.h +++ b/arch/x86/include/uapi/asm/hwcap2.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_HWCAP2_H #define _ASM_X86_HWCAP2_H diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index f65d12504e80..1a5bfead93b4 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_HYPERV_H #define _ASM_X86_HYPERV_H diff --git a/arch/x86/include/uapi/asm/ist.h b/arch/x86/include/uapi/asm/ist.h index bad9f5ea4070..eac5b207939d 100644 --- a/arch/x86/include/uapi/asm/ist.h +++ b/arch/x86/include/uapi/asm/ist.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Include file for the interface to IST BIOS * Copyright 2002 Andy Grover <andrew.grover@intel.com> diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index c2824d02ba37..f3a960488eae 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_KVM_H #define _ASM_X86_KVM_H diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index a965e5b0d328..09cc06483bed 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_KVM_PARA_H #define _UAPI_ASM_X86_KVM_PARA_H @@ -109,5 +110,4 @@ struct kvm_vcpu_pv_apf_data { #define KVM_PV_EOI_ENABLED KVM_PV_EOI_MASK #define KVM_PV_EOI_DISABLED 0x0 - #endif /* _UAPI_ASM_X86_KVM_PARA_H */ diff --git a/arch/x86/include/uapi/asm/kvm_perf.h b/arch/x86/include/uapi/asm/kvm_perf.h index 3bb964f88aa1..125cf5cdf6c5 100644 --- a/arch/x86/include/uapi/asm/kvm_perf.h +++ b/arch/x86/include/uapi/asm/kvm_perf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_KVM_PERF_H #define _ASM_X86_KVM_PERF_H diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h index 6e1aaf73852a..d62ac5db093b 100644 --- a/arch/x86/include/uapi/asm/ldt.h +++ b/arch/x86/include/uapi/asm/ldt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ldt.h * diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index eb6247a7009b..91723461dc1f 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_MCE_H #define _UAPI_ASM_X86_MCE_H diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h index 3be08f07695c..d4a8d0424bfb 100644 --- a/arch/x86/include/uapi/asm/mman.h +++ b/arch/x86/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_MMAN_H #define _ASM_X86_MMAN_H diff --git a/arch/x86/include/uapi/asm/msr.h b/arch/x86/include/uapi/asm/msr.h index c41f4fe25483..e7516b402a00 100644 --- a/arch/x86/include/uapi/asm/msr.h +++ b/arch/x86/include/uapi/asm/msr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_MSR_H #define _UAPI_ASM_X86_MSR_H diff --git a/arch/x86/include/uapi/asm/mtrr.h b/arch/x86/include/uapi/asm/mtrr.h index 7528dcf59691..376563f2bac1 100644 --- a/arch/x86/include/uapi/asm/mtrr.h +++ b/arch/x86/include/uapi/asm/mtrr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.0+ WITH Linux-syscall-note */ /* Generic MTRR (Memory Type Range Register) ioctls. Copyright (C) 1997-1999 Richard Gooch diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h index 3f2207bfd17b..f3329cabce5c 100644 --- a/arch/x86/include/uapi/asm/perf_regs.h +++ b/arch/x86/include/uapi/asm/perf_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_PERF_REGS_H #define _ASM_X86_PERF_REGS_H diff --git a/arch/x86/include/uapi/asm/posix_types.h b/arch/x86/include/uapi/asm/posix_types.h index 85506b383627..c661e95f0134 100644 --- a/arch/x86/include/uapi/asm/posix_types.h +++ b/arch/x86/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __KERNEL__ # ifdef __i386__ # include <asm/posix_types_32.h> diff --git a/arch/x86/include/uapi/asm/posix_types_32.h b/arch/x86/include/uapi/asm/posix_types_32.h index 8e525059e7d8..840659f4b96f 100644 --- a/arch/x86/include/uapi/asm/posix_types_32.h +++ b/arch/x86/include/uapi/asm/posix_types_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_POSIX_TYPES_32_H #define _ASM_X86_POSIX_TYPES_32_H diff --git a/arch/x86/include/uapi/asm/posix_types_64.h b/arch/x86/include/uapi/asm/posix_types_64.h index cba0c1ead162..515afb8059ce 100644 --- a/arch/x86/include/uapi/asm/posix_types_64.h +++ b/arch/x86/include/uapi/asm/posix_types_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_POSIX_TYPES_64_H #define _ASM_X86_POSIX_TYPES_64_H diff --git a/arch/x86/include/uapi/asm/posix_types_x32.h b/arch/x86/include/uapi/asm/posix_types_x32.h index 85f9bdafa93c..f60479b07fc8 100644 --- a/arch/x86/include/uapi/asm/posix_types_x32.h +++ b/arch/x86/include/uapi/asm/posix_types_x32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_POSIX_TYPES_X32_H #define _ASM_X86_POSIX_TYPES_X32_H diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index c45765517092..5a6aac9fa41f 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_PRCTL_H #define _ASM_X86_PRCTL_H diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 185f3d10c194..7e1e730396ae 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_PROCESSOR_FLAGS_H #define _UAPI_ASM_X86_PROCESSOR_FLAGS_H /* Various flags defined: can be included from assembler. */ @@ -104,6 +105,8 @@ #define X86_CR4_OSFXSR _BITUL(X86_CR4_OSFXSR_BIT) #define X86_CR4_OSXMMEXCPT_BIT 10 /* enable unmasked SSE exceptions */ #define X86_CR4_OSXMMEXCPT _BITUL(X86_CR4_OSXMMEXCPT_BIT) +#define X86_CR4_UMIP_BIT 11 /* enable UMIP support */ +#define X86_CR4_UMIP _BITUL(X86_CR4_UMIP_BIT) #define X86_CR4_LA57_BIT 12 /* enable 5-level page tables */ #define X86_CR4_LA57 _BITUL(X86_CR4_LA57_BIT) #define X86_CR4_VMXE_BIT 13 /* enable VMX virtualization */ @@ -151,5 +154,8 @@ #define CX86_ARR_BASE 0xc4 #define CX86_RCR_BASE 0xdc +#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ + X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ + X86_CR0_PG) #endif /* _UAPI_ASM_X86_PROCESSOR_FLAGS_H */ diff --git a/arch/x86/include/uapi/asm/ptrace-abi.h b/arch/x86/include/uapi/asm/ptrace-abi.h index 580aee3072e0..16074b9c93bb 100644 --- a/arch/x86/include/uapi/asm/ptrace-abi.h +++ b/arch/x86/include/uapi/asm/ptrace-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_PTRACE_ABI_H #define _ASM_X86_PTRACE_ABI_H diff --git a/arch/x86/include/uapi/asm/ptrace.h b/arch/x86/include/uapi/asm/ptrace.h index bc16115af39b..85165c0edafc 100644 --- a/arch/x86/include/uapi/asm/ptrace.h +++ b/arch/x86/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_PTRACE_H #define _UAPI_ASM_X86_PTRACE_H diff --git a/arch/x86/include/uapi/asm/sembuf.h b/arch/x86/include/uapi/asm/sembuf.h index cc2d6a3aeae7..cabd7476bd6c 100644 --- a/arch/x86/include/uapi/asm/sembuf.h +++ b/arch/x86/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_SEMBUF_H #define _ASM_X86_SEMBUF_H diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h index 62d4111c1c54..844d60eb1882 100644 --- a/arch/x86/include/uapi/asm/sigcontext.h +++ b/arch/x86/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_SIGCONTEXT_H #define _UAPI_ASM_X86_SIGCONTEXT_H diff --git a/arch/x86/include/uapi/asm/sigcontext32.h b/arch/x86/include/uapi/asm/sigcontext32.h index a92b0f0dc09e..6b18e88de8a6 100644 --- a/arch/x86/include/uapi/asm/sigcontext32.h +++ b/arch/x86/include/uapi/asm/sigcontext32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SIGCONTEXT32_H #define _ASM_X86_SIGCONTEXT32_H diff --git a/arch/x86/include/uapi/asm/siginfo.h b/arch/x86/include/uapi/asm/siginfo.h index 34c47b3341c0..b3d157957177 100644 --- a/arch/x86/include/uapi/asm/siginfo.h +++ b/arch/x86/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_SIGINFO_H #define _ASM_X86_SIGINFO_H diff --git a/arch/x86/include/uapi/asm/signal.h b/arch/x86/include/uapi/asm/signal.h index 8264f47cf53e..e5745d593dc7 100644 --- a/arch/x86/include/uapi/asm/signal.h +++ b/arch/x86/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_SIGNAL_H #define _UAPI_ASM_X86_SIGNAL_H diff --git a/arch/x86/include/uapi/asm/stat.h b/arch/x86/include/uapi/asm/stat.h index bc03eb5d6360..9e3982d95d0f 100644 --- a/arch/x86/include/uapi/asm/stat.h +++ b/arch/x86/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_STAT_H #define _ASM_X86_STAT_H diff --git a/arch/x86/include/uapi/asm/statfs.h b/arch/x86/include/uapi/asm/statfs.h index 2d0adbf99a8e..13c2464cd2c4 100644 --- a/arch/x86/include/uapi/asm/statfs.h +++ b/arch/x86/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_STATFS_H #define _ASM_X86_STATFS_H diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index 3725e145aa58..a9731f8a480f 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__SVM_H #define _UAPI__SVM_H diff --git a/arch/x86/include/uapi/asm/swab.h b/arch/x86/include/uapi/asm/swab.h index 7f235c7105c1..cd3fd8ddbe9a 100644 --- a/arch/x86/include/uapi/asm/swab.h +++ b/arch/x86/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_SWAB_H #define _ASM_X86_SWAB_H diff --git a/arch/x86/include/uapi/asm/types.h b/arch/x86/include/uapi/asm/types.h index 8e8c23fef08c..df55e1ddb0c9 100644 --- a/arch/x86/include/uapi/asm/types.h +++ b/arch/x86/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TYPES_H #define _ASM_X86_TYPES_H diff --git a/arch/x86/include/uapi/asm/ucontext.h b/arch/x86/include/uapi/asm/ucontext.h index e3d1ec90616e..5657b7a49f03 100644 --- a/arch/x86/include/uapi/asm/ucontext.h +++ b/arch/x86/include/uapi/asm/ucontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_UCONTEXT_H #define _ASM_X86_UCONTEXT_H diff --git a/arch/x86/include/uapi/asm/unistd.h b/arch/x86/include/uapi/asm/unistd.h index a26df0d75cd0..30d7d04d72d6 100644 --- a/arch/x86/include/uapi/asm/unistd.h +++ b/arch/x86/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_UNISTD_H #define _UAPI_ASM_X86_UNISTD_H diff --git a/arch/x86/include/uapi/asm/vm86.h b/arch/x86/include/uapi/asm/vm86.h index e0b243e9d859..d2ee4e307ef8 100644 --- a/arch/x86/include/uapi/asm/vm86.h +++ b/arch/x86/include/uapi/asm/vm86.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_VM86_H #define _UAPI_ASM_X86_VM86_H diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 690a2dcf4078..f0b0c90dd398 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * vmx.h: VMX Architecture related definitions * Copyright (c) 2004, Intel Corporation. diff --git a/arch/x86/include/uapi/asm/vsyscall.h b/arch/x86/include/uapi/asm/vsyscall.h index b97dd6e263d2..75275f547444 100644 --- a/arch/x86/include/uapi/asm/vsyscall.h +++ b/arch/x86/include/uapi/asm/vsyscall.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_VSYSCALL_H #define _UAPI_ASM_X86_VSYSCALL_H diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index fd0a7895b63f..81bb565f4497 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the linux kernel. # @@ -24,9 +25,9 @@ endif KASAN_SANITIZE_head$(BITS).o := n KASAN_SANITIZE_dumpstack.o := n KASAN_SANITIZE_dumpstack_$(BITS).o := n -KASAN_SANITIZE_stacktrace.o := n +KASAN_SANITIZE_stacktrace.o := n +KASAN_SANITIZE_paravirt.o := n -OBJECT_FILES_NON_STANDARD_head_$(BITS).o := y OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y @@ -126,10 +127,11 @@ obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o obj-$(CONFIG_SCHED_MC_PRIO) += itmt.o +obj-$(CONFIG_X86_INTEL_UMIP) += umip.o -obj-$(CONFIG_ORC_UNWINDER) += unwind_orc.o -obj-$(CONFIG_FRAME_POINTER_UNWINDER) += unwind_frame.o -obj-$(CONFIG_GUESS_UNWINDER) += unwind_guess.o +obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o +obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o +obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o ### # 64 bit specific files diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index 85a9e17e0dbc..f1bb57b0e41e 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD_wakeup_$(BITS).o := y obj-$(CONFIG_ACPI) += boot.o diff --git a/arch/x86/kernel/acpi/apei.c b/arch/x86/kernel/acpi/apei.c index ea3046e0b0cf..bb8d300fecbd 100644 --- a/arch/x86/kernel/acpi/apei.c +++ b/arch/x86/kernel/acpi/apei.c @@ -52,8 +52,3 @@ void arch_apei_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) apei_mce_report_mem_error(sev, mem_err); #endif } - -void arch_apei_flush_tlb_one(unsigned long addr) -{ - __flush_tlb_one(addr); -} diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 079535e53e2a..f4c463df8b08 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -342,13 +342,12 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e #ifdef CONFIG_X86_IO_APIC #define MP_ISA_BUS 0 +static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, + u8 trigger, u32 gsi); + static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) { - int ioapic; - int pin; - struct mpc_intsrc mp_irq; - /* * Check bus_irq boundary. */ @@ -358,14 +357,6 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, } /* - * Convert 'gsi' to 'ioapic.pin'. - */ - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return; - pin = mp_find_ioapic_pin(ioapic, gsi); - - /* * TBD: This check is for faulty timer entries, where the override * erroneously sets the trigger to level, resulting in a HUGE * increase of timer interrupts! @@ -373,16 +364,8 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, if ((bus_irq == 0) && (trigger == 3)) trigger = 1; - mp_irq.type = MP_INTSRC; - mp_irq.irqtype = mp_INT; - mp_irq.irqflag = (trigger << 2) | polarity; - mp_irq.srcbus = MP_ISA_BUS; - mp_irq.srcbusirq = bus_irq; /* IRQ */ - mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */ - mp_irq.dstirq = pin; /* INTIN# */ - - mp_save_irq(&mp_irq); - + if (mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi) < 0) + return; /* * Reset default identity mapping if gsi is also an legacy IRQ, * otherwise there will be more than one entry with the same GSI @@ -429,6 +412,34 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, return 0; } +static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, + u8 trigger, u32 gsi) +{ + struct mpc_intsrc mp_irq; + int ioapic, pin; + + /* Convert 'gsi' to 'ioapic.pin'(INTIN#) */ + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) { + pr_warn("Failed to find ioapic for gsi : %u\n", gsi); + return ioapic; + } + + pin = mp_find_ioapic_pin(ioapic, gsi); + + mp_irq.type = MP_INTSRC; + mp_irq.irqtype = mp_INT; + mp_irq.irqflag = (trigger << 2) | polarity; + mp_irq.srcbus = MP_ISA_BUS; + mp_irq.srcbusirq = bus_irq; + mp_irq.dstapic = mpc_ioapic_id(ioapic); + mp_irq.dstirq = pin; + + mp_save_irq(&mp_irq); + + return 0; +} + static int __init acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) { @@ -473,7 +484,11 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, if (acpi_sci_flags & ACPI_MADT_POLARITY_MASK) polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; - mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + if (bus_irq < NR_IRQS_LEGACY) + mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + else + mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi); + acpi_penalize_sci_irq(bus_irq, trigger, polarity); /* @@ -961,6 +976,11 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table) x86_platform.legacy.rtc = 0; } + if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_VGA) { + pr_debug("ACPI: probing for VGA not safe\n"); + x86_platform.legacy.no_vga = 1; + } + #ifdef CONFIG_X86_PM_TIMER /* detect the location of the ACPI PM Timer */ if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) { diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index ed014814ea35..7188aea91549 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * sleep.c - x86-specific ACPI sleep support. * diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index 65c7b606b606..fbb60ca4255c 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Variables and functions used by the code in sleep.c */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 3344d3382e91..dbaf14d69ebd 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -442,7 +442,6 @@ static void alternatives_smp_lock(const s32 *start, const s32 *end, { const s32 *poff; - mutex_lock(&text_mutex); for (poff = start; poff < end; poff++) { u8 *ptr = (u8 *)poff + *poff; @@ -452,7 +451,6 @@ static void alternatives_smp_lock(const s32 *start, const s32 *end, if (*ptr == 0x3e) text_poke(ptr, ((unsigned char []){0xf0}), 1); } - mutex_unlock(&text_mutex); } static void alternatives_smp_unlock(const s32 *start, const s32 *end, @@ -460,7 +458,6 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end, { const s32 *poff; - mutex_lock(&text_mutex); for (poff = start; poff < end; poff++) { u8 *ptr = (u8 *)poff + *poff; @@ -470,7 +467,6 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end, if (*ptr == 0xf0) text_poke(ptr, ((unsigned char []){0x3E}), 1); } - mutex_unlock(&text_mutex); } struct smp_alt_module { @@ -489,8 +485,7 @@ struct smp_alt_module { struct list_head next; }; static LIST_HEAD(smp_alt_modules); -static DEFINE_MUTEX(smp_alt); -static bool uniproc_patched = false; /* protected by smp_alt */ +static bool uniproc_patched = false; /* protected by text_mutex */ void __init_or_module alternatives_smp_module_add(struct module *mod, char *name, @@ -499,7 +494,7 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, { struct smp_alt_module *smp; - mutex_lock(&smp_alt); + mutex_lock(&text_mutex); if (!uniproc_patched) goto unlock; @@ -526,14 +521,14 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, smp_unlock: alternatives_smp_unlock(locks, locks_end, text, text_end); unlock: - mutex_unlock(&smp_alt); + mutex_unlock(&text_mutex); } void __init_or_module alternatives_smp_module_del(struct module *mod) { struct smp_alt_module *item; - mutex_lock(&smp_alt); + mutex_lock(&text_mutex); list_for_each_entry(item, &smp_alt_modules, next) { if (mod != item->mod) continue; @@ -541,7 +536,7 @@ void __init_or_module alternatives_smp_module_del(struct module *mod) kfree(item); break; } - mutex_unlock(&smp_alt); + mutex_unlock(&text_mutex); } void alternatives_enable_smp(void) @@ -551,7 +546,7 @@ void alternatives_enable_smp(void) /* Why bother if there are no other CPUs? */ BUG_ON(num_possible_cpus() == 1); - mutex_lock(&smp_alt); + mutex_lock(&text_mutex); if (uniproc_patched) { pr_info("switching to SMP code\n"); @@ -563,10 +558,13 @@ void alternatives_enable_smp(void) mod->text, mod->text_end); uniproc_patched = false; } - mutex_unlock(&smp_alt); + mutex_unlock(&text_mutex); } -/* Return 1 if the address range is reserved for smp-alternatives */ +/* + * Return 1 if the address range is reserved for SMP-alternatives. + * Must hold text_mutex. + */ int alternatives_text_reserved(void *start, void *end) { struct smp_alt_module *mod; @@ -574,6 +572,8 @@ int alternatives_text_reserved(void *start, void *end) u8 *text_start = start; u8 *text_end = end; + lockdep_assert_held(&text_mutex); + list_for_each_entry(mod, &smp_alt_modules, next) { if (mod->text > text_end || mod->text_end < text_start) continue; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 458da8509b75..6db28f17ff28 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -27,6 +27,8 @@ static const struct pci_device_id amd_root_ids[] = { {} }; +#define PCI_DEVICE_ID_AMD_CNB17H_F4 0x1704 + const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, @@ -37,6 +39,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, {} }; EXPORT_SYMBOL_GPL(amd_nb_misc_ids); @@ -48,6 +51,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; @@ -402,11 +406,48 @@ void amd_flush_garts(void) } EXPORT_SYMBOL_GPL(amd_flush_garts); +static void __fix_erratum_688(void *info) +{ +#define MSR_AMD64_IC_CFG 0xC0011021 + + msr_set_bit(MSR_AMD64_IC_CFG, 3); + msr_set_bit(MSR_AMD64_IC_CFG, 14); +} + +/* Apply erratum 688 fix so machines without a BIOS fix work. */ +static __init void fix_erratum_688(void) +{ + struct pci_dev *F4; + u32 val; + + if (boot_cpu_data.x86 != 0x14) + return; + + if (!amd_northbridges.num) + return; + + F4 = node_to_amd_nb(0)->link; + if (!F4) + return; + + if (pci_read_config_dword(F4, 0x164, &val)) + return; + + if (val & BIT(2)) + return; + + on_each_cpu(__fix_erratum_688, NULL, 0); + + pr_info("x86/cpu/AMD: CPU erratum 688 worked around\n"); +} + static __init int init_amd_nbs(void) { amd_cache_northbridges(); amd_cache_gart(); + fix_erratum_688(); + return 0; } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index ef2859f9fcce..f5d92bc3b884 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Firmware replacement code. * diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 8e63ebdcbd0b..a6fcaf16cdbf 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for local APIC drivers and for the IO-APIC code # @@ -6,12 +7,11 @@ # In particualr, smp_apic_timer_interrupt() is called in random places. KCOV_INSTRUMENT := n -obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o ipi.o vector.o +obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_common.o apic_noop.o ipi.o vector.o obj-y += hw_nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_PCI_MSI) += msi.o -obj-$(CONFIG_HT_IRQ) += htirq.o obj-$(CONFIG_SMP) += ipi.o ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d705c769f77d..6e272f3ea984 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -211,11 +211,7 @@ static inline int lapic_get_version(void) */ static inline int lapic_is_integrated(void) { -#ifdef CONFIG_X86_64 - return 1; -#else return APIC_INTEGRATED(lapic_get_version()); -#endif } /* @@ -298,14 +294,11 @@ int get_physical_broadcast(void) */ int lapic_get_maxlvt(void) { - unsigned int v; - - v = apic_read(APIC_LVR); /* * - we always have APIC integrated on 64bit mode * - 82489DXs do not report # of LVT entries */ - return APIC_INTEGRATED(GET_APIC_VERSION(v)) ? GET_APIC_MAXLVT(v) : 2; + return lapic_is_integrated() ? GET_APIC_MAXLVT(apic_read(APIC_LVR)) : 2; } /* @@ -573,11 +566,21 @@ static u32 bdx_deadline_rev(void) return ~0U; } +static u32 skx_deadline_rev(void) +{ + switch (boot_cpu_data.x86_mask) { + case 0x03: return 0x01000136; + case 0x04: return 0x02000014; + } + + return ~0U; +} + static const struct x86_cpu_id deadline_match[] = { DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_X, 0x02000014), + DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X, skx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE, 0x22), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT, 0x20), @@ -600,7 +603,8 @@ static void apic_check_deadline_errata(void) const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || + boot_cpu_has(X86_FEATURE_HYPERVISOR)) return; m = x86_match_cpu(deadline_match); @@ -1218,53 +1222,100 @@ void __init sync_Arb_IDs(void) APIC_INT_LEVELTRIG | APIC_DM_INIT); } -/* - * An initial setup of the virtual wire mode. - */ -void __init init_bsp_APIC(void) +enum apic_intr_mode_id apic_intr_mode; + +static int __init apic_intr_mode_select(void) { - unsigned int value; + /* Check kernel option */ + if (disable_apic) { + pr_info("APIC disabled via kernel command line\n"); + return APIC_PIC; + } - /* - * Don't do the setup now if we have a SMP BIOS as the - * through-I/O-APIC virtual wire mode might be active. - */ - if (smp_found_config || !boot_cpu_has(X86_FEATURE_APIC)) - return; + /* Check BIOS */ +#ifdef CONFIG_X86_64 + /* On 64-bit, the APIC must be integrated, Check local APIC only */ + if (!boot_cpu_has(X86_FEATURE_APIC)) { + disable_apic = 1; + pr_info("APIC disabled by BIOS\n"); + return APIC_PIC; + } +#else + /* On 32-bit, the APIC may be integrated APIC or 82489DX */ - /* - * Do not trust the local APIC being empty at bootup. - */ - clear_local_APIC(); + /* Neither 82489DX nor integrated APIC ? */ + if (!boot_cpu_has(X86_FEATURE_APIC) && !smp_found_config) { + disable_apic = 1; + return APIC_PIC; + } - /* - * Enable APIC. - */ - value = apic_read(APIC_SPIV); - value &= ~APIC_VECTOR_MASK; - value |= APIC_SPIV_APIC_ENABLED; + /* If the BIOS pretends there is an integrated APIC ? */ + if (!boot_cpu_has(X86_FEATURE_APIC) && + APIC_INTEGRATED(boot_cpu_apic_version)) { + disable_apic = 1; + pr_err(FW_BUG "Local APIC %d not detected, force emulation\n", + boot_cpu_physical_apicid); + return APIC_PIC; + } +#endif -#ifdef CONFIG_X86_32 - /* This bit is reserved on P4/Xeon and should be cleared */ - if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && - (boot_cpu_data.x86 == 15)) - value &= ~APIC_SPIV_FOCUS_DISABLED; - else + /* Check MP table or ACPI MADT configuration */ + if (!smp_found_config) { + disable_ioapic_support(); + if (!acpi_lapic) { + pr_info("APIC: ACPI MADT or MP tables are not detected\n"); + return APIC_VIRTUAL_WIRE_NO_CONFIG; + } + return APIC_VIRTUAL_WIRE; + } + +#ifdef CONFIG_SMP + /* If SMP should be disabled, then really disable it! */ + if (!setup_max_cpus) { + pr_info("APIC: SMP mode deactivated\n"); + return APIC_SYMMETRIC_IO_NO_ROUTING; + } + + if (read_apic_id() != boot_cpu_physical_apicid) { + panic("Boot APIC ID in local APIC unexpected (%d vs %d)", + read_apic_id(), boot_cpu_physical_apicid); + /* Or can we switch back to PIC here? */ + } #endif - value |= APIC_SPIV_FOCUS_DISABLED; - value |= SPURIOUS_APIC_VECTOR; - apic_write(APIC_SPIV, value); - /* - * Set up the virtual wire mode. - */ - apic_write(APIC_LVT0, APIC_DM_EXTINT); - value = APIC_DM_NMI; - if (!lapic_is_integrated()) /* 82489DX */ - value |= APIC_LVT_LEVEL_TRIGGER; - if (apic_extnmi == APIC_EXTNMI_NONE) - value |= APIC_LVT_MASKED; - apic_write(APIC_LVT1, value); + return APIC_SYMMETRIC_IO; +} + +/* Init the interrupt delivery mode for the BSP */ +void __init apic_intr_mode_init(void) +{ + bool upmode = IS_ENABLED(CONFIG_UP_LATE_INIT); + + apic_intr_mode = apic_intr_mode_select(); + + switch (apic_intr_mode) { + case APIC_PIC: + pr_info("APIC: Keep in PIC mode(8259)\n"); + return; + case APIC_VIRTUAL_WIRE: + pr_info("APIC: Switch to virtual wire mode setup\n"); + default_setup_apic_routing(); + break; + case APIC_VIRTUAL_WIRE_NO_CONFIG: + pr_info("APIC: Switch to virtual wire mode setup with no configuration\n"); + upmode = true; + default_setup_apic_routing(); + break; + case APIC_SYMMETRIC_IO: + pr_info("APIC: Switch to symmetric I/O mode setup\n"); + default_setup_apic_routing(); + break; + case APIC_SYMMETRIC_IO_NO_ROUTING: + pr_info("APIC: Switch to symmetric I/O mode setup in no SMP routine\n"); + break; + } + + apic_bsp_setup(upmode); } static void lapic_setup_esr(void) @@ -1462,7 +1513,7 @@ void setup_local_APIC(void) /* * Set up LVT0, LVT1: * - * set up through-local-APIC on the BP's LINT0. This is not + * set up through-local-APIC on the boot CPU's LINT0. This is not * strictly necessary in pure symmetric-IO mode, but sometimes * we delegate interrupts to the 8259A. */ @@ -1488,7 +1539,9 @@ void setup_local_APIC(void) value = APIC_DM_NMI; else value = APIC_DM_NMI | APIC_LVT_MASKED; - if (!lapic_is_integrated()) /* 82489DX */ + + /* Is 82489DX ? */ + if (!lapic_is_integrated()) value |= APIC_LVT_LEVEL_TRIGGER; apic_write(APIC_LVT1, value); @@ -1634,7 +1687,7 @@ static __init void try_to_enable_x2apic(int remap_mode) * under KVM */ if (max_physical_apicid > 255 || - !hypervisor_x2apic_available()) { + !x86_init.hyper.x2apic_available()) { pr_info("x2apic: IRQ remapping doesn't support X2APIC mode\n"); x2apic_disable(); return; @@ -1874,8 +1927,8 @@ void __init init_apic_mappings(void) * yeah -- we lie about apic_version * in case if apic was disabled via boot option * but it's not a problem for SMP compiled kernel - * since smp_sanity_check is prepared for such a case - * and disable smp mode + * since apic_intr_mode_select is prepared for such + * a case and disable smp mode */ boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR)); } @@ -2231,44 +2284,6 @@ int hard_smp_processor_id(void) return read_apic_id(); } -void default_init_apic_ldr(void) -{ - unsigned long val; - - apic_write(APIC_DFR, APIC_DFR_VALUE); - val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; - val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id()); - apic_write(APIC_LDR, val); -} - -int default_cpu_mask_to_apicid(const struct cpumask *mask, - struct irq_data *irqdata, - unsigned int *apicid) -{ - unsigned int cpu = cpumask_first(mask); - - if (cpu >= nr_cpu_ids) - return -EINVAL; - *apicid = per_cpu(x86_cpu_to_apicid, cpu); - irq_data_update_effective_affinity(irqdata, cpumask_of(cpu)); - return 0; -} - -int flat_cpu_mask_to_apicid(const struct cpumask *mask, - struct irq_data *irqdata, - unsigned int *apicid) - -{ - struct cpumask *effmsk = irq_data_get_effective_affinity_mask(irqdata); - unsigned long cpu_mask = cpumask_bits(mask)[0] & APIC_ALL_CPUS; - - if (!cpu_mask) - return -EINVAL; - *apicid = (unsigned int)cpu_mask; - cpumask_bits(effmsk)[0] = cpu_mask; - return 0; -} - /* * Override the generic EOI implementation with an optimized version. * Only called during early boot when only one CPU is active and with @@ -2311,72 +2326,27 @@ static void __init apic_bsp_up_setup(void) * Returns: * apic_id of BSP APIC */ -int __init apic_bsp_setup(bool upmode) +void __init apic_bsp_setup(bool upmode) { - int id; - connect_bsp_APIC(); if (upmode) apic_bsp_up_setup(); setup_local_APIC(); - if (x2apic_mode) - id = apic_read(APIC_LDR); - else - id = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); - enable_IO_APIC(); end_local_APIC_setup(); irq_remap_enable_fault_handling(); setup_IO_APIC(); - /* Setup local timer */ - x86_init.timers.setup_percpu_clockev(); - return id; -} - -/* - * This initializes the IO-APIC and APIC hardware if this is - * a UP kernel. - */ -int __init APIC_init_uniprocessor(void) -{ - if (disable_apic) { - pr_info("Apic disabled\n"); - return -1; - } -#ifdef CONFIG_X86_64 - if (!boot_cpu_has(X86_FEATURE_APIC)) { - disable_apic = 1; - pr_info("Apic disabled by BIOS\n"); - return -1; - } -#else - if (!smp_found_config && !boot_cpu_has(X86_FEATURE_APIC)) - return -1; - - /* - * Complain if the BIOS pretends there is one. - */ - if (!boot_cpu_has(X86_FEATURE_APIC) && - APIC_INTEGRATED(boot_cpu_apic_version)) { - pr_err("BIOS bug, local APIC 0x%x not detected!...\n", - boot_cpu_physical_apicid); - return -1; - } -#endif - - if (!smp_found_config) - disable_ioapic_support(); - - default_setup_apic_routing(); - apic_bsp_setup(true); - return 0; } #ifdef CONFIG_UP_LATE_INIT void __init up_late_init(void) { - APIC_init_uniprocessor(); + if (apic_intr_mode == APIC_PIC) + return; + + /* Setup local timer */ + x86_init.timers.setup_percpu_clockev(); } #endif diff --git a/arch/x86/kernel/apic/apic_common.c b/arch/x86/kernel/apic/apic_common.c new file mode 100644 index 000000000000..a360801779ae --- /dev/null +++ b/arch/x86/kernel/apic/apic_common.c @@ -0,0 +1,46 @@ +/* + * Common functions shared between the various APIC flavours + * + * SPDX-License-Identifier: GPL-2.0 + */ +#include <linux/irq.h> +#include <asm/apic.h> + +u32 apic_default_calc_apicid(unsigned int cpu) +{ + return per_cpu(x86_cpu_to_apicid, cpu); +} + +u32 apic_flat_calc_apicid(unsigned int cpu) +{ + return 1U << cpu; +} + +bool default_check_apicid_used(physid_mask_t *map, int apicid) +{ + return physid_isset(apicid, *map); +} + +void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) +{ + *retmap = *phys_map; +} + +int default_cpu_present_to_apicid(int mps_cpu) +{ + if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu)) + return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu); + else + return BAD_APICID; +} +EXPORT_SYMBOL_GPL(default_cpu_present_to_apicid); + +int default_check_phys_apicid_present(int phys_apicid) +{ + return physid_isset(phys_apicid, phys_cpu_present_map); +} + +int default_apic_id_valid(int apicid) +{ + return (apicid < 255); +} diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index dedd5a41ba48..aa85690e9b64 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -119,7 +119,7 @@ static unsigned int flat_get_apic_id(unsigned long x) return (x >> 24) & 0xFF; } -static unsigned long set_apic_id(unsigned int id) +static u32 set_apic_id(unsigned int id) { return (id & 0xFF) << 24; } @@ -154,12 +154,10 @@ static struct apic apic_flat __ro_after_init = { .irq_delivery_mode = dest_LowestPrio, .irq_dest_mode = 1, /* logical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, - .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = flat_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -172,7 +170,7 @@ static struct apic apic_flat __ro_after_init = { .get_apic_id = flat_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, + .calc_dest_apicid = apic_flat_calc_apicid, .send_IPI = default_send_IPI_single, .send_IPI_mask = flat_send_IPI_mask, @@ -249,12 +247,10 @@ static struct apic apic_physflat __ro_after_init = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, - .vector_allocation_domain = default_vector_allocation_domain, /* not needed, but shouldn't hurt: */ .init_apic_ldr = flat_init_apic_ldr, @@ -268,7 +264,7 @@ static struct apic apic_physflat __ro_after_init = { .get_apic_id = flat_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .calc_dest_apicid = apic_default_calc_apicid, .send_IPI = default_send_IPI_single_phys, .send_IPI_mask = default_send_IPI_mask_sequence_phys, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 6599f437b4ab..7b659c4480c9 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NOOP APIC driver. * @@ -83,20 +84,6 @@ static int noop_apic_id_registered(void) return physid_isset(0, phys_cpu_present_map); } -static const struct cpumask *noop_target_cpus(void) -{ - /* only BSP here */ - return cpumask_of(0); -} - -static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask, - const struct cpumask *mask) -{ - if (cpu != 0) - pr_warning("APIC: Vector allocated for non-BSP cpu\n"); - cpumask_copy(retmask, cpumask_of(cpu)); -} - static u32 noop_apic_read(u32 reg) { WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); @@ -108,6 +95,13 @@ static void noop_apic_write(u32 reg, u32 v) WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); } +#ifdef CONFIG_X86_32 +static int noop_x86_32_early_logical_apicid(int cpu) +{ + return BAD_APICID; +} +#endif + struct apic apic_noop __ro_after_init = { .name = "noop", .probe = noop_probe, @@ -120,12 +114,10 @@ struct apic apic_noop __ro_after_init = { /* logical delivery broadcast to all CPUs: */ .irq_dest_mode = 1, - .target_cpus = noop_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = default_check_apicid_used, - .vector_allocation_domain = noop_vector_allocation_domain, .init_apic_ldr = noop_init_apic_ldr, .ioapic_phys_id_map = default_ioapic_phys_id_map, @@ -141,7 +133,7 @@ struct apic apic_noop __ro_after_init = { .get_apic_id = noop_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, + .calc_dest_apicid = apic_flat_calc_apicid, .send_IPI = noop_send_IPI, .send_IPI_mask = noop_send_IPI_mask, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 2fda912219a6..134e04506ab4 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -38,7 +38,7 @@ static unsigned int numachip1_get_apic_id(unsigned long x) return id; } -static unsigned long numachip1_set_apic_id(unsigned int id) +static u32 numachip1_set_apic_id(unsigned int id) { return (id & 0xff) << 24; } @@ -51,7 +51,7 @@ static unsigned int numachip2_get_apic_id(unsigned long x) return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24); } -static unsigned long numachip2_set_apic_id(unsigned int id) +static u32 numachip2_set_apic_id(unsigned int id) { return id << 24; } @@ -249,12 +249,10 @@ static const struct apic apic_numachip1 __refconst = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, - .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = flat_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -267,7 +265,7 @@ static const struct apic apic_numachip1 __refconst = { .get_apic_id = numachip1_get_apic_id, .set_apic_id = numachip1_set_apic_id, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .calc_dest_apicid = apic_default_calc_apicid, .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, @@ -300,12 +298,10 @@ static const struct apic apic_numachip2 __refconst = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, - .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = flat_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -318,7 +314,7 @@ static const struct apic apic_numachip2 __refconst = { .get_apic_id = numachip2_get_apic_id, .set_apic_id = numachip2_set_apic_id, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .calc_dest_apicid = apic_default_calc_apicid, .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 456e45e8bf84..afee386ff711 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * APIC driver for "bigsmp" xAPIC machines with more than 8 virtual CPUs. * @@ -26,9 +27,9 @@ static int bigsmp_apic_id_registered(void) return 1; } -static unsigned long bigsmp_check_apicid_used(physid_mask_t *map, int apicid) +static bool bigsmp_check_apicid_used(physid_mask_t *map, int apicid) { - return 0; + return false; } static int bigsmp_early_logical_apicid(int cpu) @@ -154,12 +155,10 @@ static struct apic apic_bigsmp __ro_after_init = { /* phys delivery to target CPU: */ .irq_dest_mode = 0, - .target_cpus = default_target_cpus, .disable_esr = 1, .dest_logical = 0, .check_apicid_used = bigsmp_check_apicid_used, - .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = bigsmp_init_apic_ldr, .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map, @@ -172,7 +171,7 @@ static struct apic apic_bigsmp __ro_after_init = { .get_apic_id = bigsmp_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .calc_dest_apicid = apic_default_calc_apicid, .send_IPI = default_send_IPI_single_phys, .send_IPI_mask = default_send_IPI_mask_sequence_phys, diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c deleted file mode 100644 index 56ccf9346b08..000000000000 --- a/arch/x86/kernel/apic/htirq.c +++ /dev/null @@ -1,197 +0,0 @@ -/* - * Support Hypertransport IRQ - * - * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo - * Moved from arch/x86/kernel/apic/io_apic.c. - * Jiang Liu <jiang.liu@linux.intel.com> - * Add support of hierarchical irqdomain - * - * 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/mm.h> -#include <linux/interrupt.h> -#include <linux/init.h> -#include <linux/device.h> -#include <linux/pci.h> -#include <linux/htirq.h> -#include <asm/irqdomain.h> -#include <asm/hw_irq.h> -#include <asm/apic.h> -#include <asm/hypertransport.h> - -static struct irq_domain *htirq_domain; - -/* - * Hypertransport interrupt support - */ -static int -ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) -{ - struct irq_data *parent = data->parent_data; - int ret; - - ret = parent->chip->irq_set_affinity(parent, mask, force); - if (ret >= 0) { - struct ht_irq_msg msg; - struct irq_cfg *cfg = irqd_cfg(data); - - fetch_ht_irq_msg(data->irq, &msg); - msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | - HT_IRQ_LOW_DEST_ID_MASK); - msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) | - HT_IRQ_LOW_DEST_ID(cfg->dest_apicid); - msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK); - msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid); - write_ht_irq_msg(data->irq, &msg); - } - - return ret; -} - -static struct irq_chip ht_irq_chip = { - .name = "PCI-HT", - .irq_mask = mask_ht_irq, - .irq_unmask = unmask_ht_irq, - .irq_ack = irq_chip_ack_parent, - .irq_set_affinity = ht_set_affinity, - .irq_retrigger = irq_chip_retrigger_hierarchy, - .flags = IRQCHIP_SKIP_SET_WAKE, -}; - -static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs, void *arg) -{ - struct ht_irq_cfg *ht_cfg; - struct irq_alloc_info *info = arg; - struct pci_dev *dev; - irq_hw_number_t hwirq; - int ret; - - if (nr_irqs > 1 || !info) - return -EINVAL; - - dev = info->ht_dev; - hwirq = (info->ht_idx & 0xFF) | - PCI_DEVID(dev->bus->number, dev->devfn) << 8 | - (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24; - if (irq_find_mapping(domain, hwirq) > 0) - return -EEXIST; - - ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL); - if (!ht_cfg) - return -ENOMEM; - - ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); - if (ret < 0) { - kfree(ht_cfg); - return ret; - } - - /* Initialize msg to a value that will never match the first write. */ - ht_cfg->msg.address_lo = 0xffffffff; - ht_cfg->msg.address_hi = 0xffffffff; - ht_cfg->dev = info->ht_dev; - ht_cfg->update = info->ht_update; - ht_cfg->pos = info->ht_pos; - ht_cfg->idx = 0x10 + (info->ht_idx * 2); - irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg, - handle_edge_irq, ht_cfg, "edge"); - - return 0; -} - -static void htirq_domain_free(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs) -{ - struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); - - BUG_ON(nr_irqs != 1); - kfree(irq_data->chip_data); - irq_domain_free_irqs_top(domain, virq, nr_irqs); -} - -static void htirq_domain_activate(struct irq_domain *domain, - struct irq_data *irq_data) -{ - struct ht_irq_msg msg; - struct irq_cfg *cfg = irqd_cfg(irq_data); - - msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid); - msg.address_lo = - HT_IRQ_LOW_BASE | - HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) | - HT_IRQ_LOW_VECTOR(cfg->vector) | - ((apic->irq_dest_mode == 0) ? - HT_IRQ_LOW_DM_PHYSICAL : - HT_IRQ_LOW_DM_LOGICAL) | - HT_IRQ_LOW_RQEOI_EDGE | - ((apic->irq_delivery_mode != dest_LowestPrio) ? - HT_IRQ_LOW_MT_FIXED : - HT_IRQ_LOW_MT_ARBITRATED) | - HT_IRQ_LOW_IRQ_MASKED; - write_ht_irq_msg(irq_data->irq, &msg); -} - -static void htirq_domain_deactivate(struct irq_domain *domain, - struct irq_data *irq_data) -{ - struct ht_irq_msg msg; - - memset(&msg, 0, sizeof(msg)); - write_ht_irq_msg(irq_data->irq, &msg); -} - -static const struct irq_domain_ops htirq_domain_ops = { - .alloc = htirq_domain_alloc, - .free = htirq_domain_free, - .activate = htirq_domain_activate, - .deactivate = htirq_domain_deactivate, -}; - -void __init arch_init_htirq_domain(struct irq_domain *parent) -{ - struct fwnode_handle *fn; - - if (disable_apic) - return; - - fn = irq_domain_alloc_named_fwnode("PCI-HT"); - if (!fn) - goto warn; - - htirq_domain = irq_domain_create_tree(fn, &htirq_domain_ops, NULL); - irq_domain_free_fwnode(fn); - if (!htirq_domain) - goto warn; - - htirq_domain->parent = parent; - return; - -warn: - pr_warn("Failed to initialize irqdomain for HTIRQ.\n"); -} - -int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev, - ht_irq_update_t *update) -{ - struct irq_alloc_info info; - - if (!htirq_domain) - return -ENOSYS; - - init_irq_alloc_info(&info, NULL); - info.ht_idx = idx; - info.ht_pos = pos; - info.ht_dev = dev; - info.ht_update = update; - - return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev), - &info); -} - -void arch_teardown_ht_irq(unsigned int irq) -{ - irq_domain_free_irqs(irq, 1); -} diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index d6f387780849..d1fc62a67320 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * HW NMI watchdog support * diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 70e48aa6af98..201579dc5242 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel IO-APIC support for multi-Pentium hosts. * @@ -1013,6 +1014,7 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, info->ioapic_pin)) return -ENOMEM; } else { + info->flags |= X86_IRQ_ALLOC_LEGACY; irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true, NULL); if (irq >= 0) { @@ -1585,6 +1587,43 @@ static int __init notimercheck(char *s) } __setup("no_timer_check", notimercheck); +static void __init delay_with_tsc(void) +{ + unsigned long long start, now; + unsigned long end = jiffies + 4; + + start = rdtsc(); + + /* + * We don't know the TSC frequency yet, but waiting for + * 40000000000/HZ TSC cycles is safe: + * 4 GHz == 10 jiffies + * 1 GHz == 40 jiffies + */ + do { + rep_nop(); + now = rdtsc(); + } while ((now - start) < 40000000000UL / HZ && + time_before_eq(jiffies, end)); +} + +static void __init delay_without_tsc(void) +{ + unsigned long end = jiffies + 4; + int band = 1; + + /* + * We don't know any frequency yet, but waiting for + * 40940000000/HZ cycles is safe: + * 4 GHz == 10 jiffies + * 1 GHz == 40 jiffies + * 1 << 1 + 1 << 2 +...+ 1 << 11 = 4094 + */ + do { + __delay(((1U << band++) * 10000000UL) / HZ); + } while (band < 12 && time_before_eq(jiffies, end)); +} + /* * There is a nasty bug in some older SMP boards, their mptable lies * about the timer IRQ. We do the following to work around the situation: @@ -1603,8 +1642,12 @@ static int __init timer_irq_works(void) local_save_flags(flags); local_irq_enable(); - /* Let ten ticks pass... */ - mdelay((10 * 1000) / HZ); + + if (boot_cpu_has(X86_FEATURE_TSC)) + delay_with_tsc(); + else + delay_without_tsc(); + local_irq_restore(flags); /* @@ -1820,26 +1863,36 @@ static void ioapic_ir_ack_level(struct irq_data *irq_data) eoi_ioapic_pin(data->entry.vector, data); } +static void ioapic_configure_entry(struct irq_data *irqd) +{ + struct mp_chip_data *mpd = irqd->chip_data; + struct irq_cfg *cfg = irqd_cfg(irqd); + struct irq_pin_list *entry; + + /* + * Only update when the parent is the vector domain, don't touch it + * if the parent is the remapping domain. Check the installed + * ioapic chip to verify that. + */ + if (irqd->chip == &ioapic_chip) { + mpd->entry.dest = cfg->dest_apicid; + mpd->entry.vector = cfg->vector; + } + for_each_irq_pin(entry, mpd->irq_2_pin) + __ioapic_write_entry(entry->apic, entry->pin, mpd->entry); +} + static int ioapic_set_affinity(struct irq_data *irq_data, const struct cpumask *mask, bool force) { struct irq_data *parent = irq_data->parent_data; - struct mp_chip_data *data = irq_data->chip_data; - struct irq_pin_list *entry; - struct irq_cfg *cfg; unsigned long flags; int ret; ret = parent->chip->irq_set_affinity(parent, mask, force); raw_spin_lock_irqsave(&ioapic_lock, flags); - if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) { - cfg = irqd_cfg(irq_data); - data->entry.dest = cfg->dest_apicid; - data->entry.vector = cfg->vector; - for_each_irq_pin(entry, data->irq_2_pin) - __ioapic_write_entry(entry->apic, entry->pin, - data->entry); - } + if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) + ioapic_configure_entry(irq_data); raw_spin_unlock_irqrestore(&ioapic_lock, flags); return ret; @@ -2096,7 +2149,7 @@ static inline void __init check_timer(void) unmask_ioapic_irq(irq_get_irq_data(0)); } irq_domain_deactivate_irq(irq_data); - irq_domain_activate_irq(irq_data); + irq_domain_activate_irq(irq_data, false); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) clear_IO_APIC_pin(0, pin1); @@ -2118,7 +2171,7 @@ static inline void __init check_timer(void) */ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); irq_domain_deactivate_irq(irq_data); - irq_domain_activate_irq(irq_data); + irq_domain_activate_irq(irq_data, false); legacy_pic->unmask(0); if (timer_irq_works()) { apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); @@ -2512,52 +2565,9 @@ int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) } /* - * This function currently is only a helper for the i386 smp boot process where - * we need to reprogram the ioredtbls to cater for the cpus which have come online - * so mask in all cases should simply be apic->target_cpus() + * This function updates target affinity of IOAPIC interrupts to include + * the CPUs which came online during SMP bringup. */ -#ifdef CONFIG_SMP -void __init setup_ioapic_dest(void) -{ - int pin, ioapic, irq, irq_entry; - const struct cpumask *mask; - struct irq_desc *desc; - struct irq_data *idata; - struct irq_chip *chip; - - if (skip_ioapic_setup == 1) - return; - - for_each_ioapic_pin(ioapic, pin) { - irq_entry = find_irq_entry(ioapic, pin, mp_INT); - if (irq_entry == -1) - continue; - - irq = pin_2_irq(irq_entry, ioapic, pin, 0); - if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq)) - continue; - - desc = irq_to_desc(irq); - raw_spin_lock_irq(&desc->lock); - idata = irq_desc_get_irq_data(desc); - - /* - * Honour affinities which have been set in early boot - */ - if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata)) - mask = irq_data_get_affinity_mask(idata); - else - mask = apic->target_cpus(); - - chip = irq_data_get_irq_chip(idata); - /* Might be lapic_chip for irq 0 */ - if (chip->irq_set_affinity) - chip->irq_set_affinity(idata, mask, false); - raw_spin_unlock_irq(&desc->lock); - } -} -#endif - #define IOAPIC_RESOURCE_NAME_SIZE 11 static struct resource *ioapic_resources; @@ -2977,17 +2987,15 @@ void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, irq_domain_free_irqs_top(domain, virq, nr_irqs); } -void mp_irqdomain_activate(struct irq_domain *domain, - struct irq_data *irq_data) +int mp_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early) { unsigned long flags; - struct irq_pin_list *entry; - struct mp_chip_data *data = irq_data->chip_data; raw_spin_lock_irqsave(&ioapic_lock, flags); - for_each_irq_pin(entry, data->irq_2_pin) - __ioapic_write_entry(entry->apic, entry->pin, data->entry); + ioapic_configure_entry(irq_data); raw_spin_unlock_irqrestore(&ioapic_lock, flags); + return 0; } void mp_irqdomain_deactivate(struct irq_domain *domain, diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 3a205d4a12d0..82f9244fe61f 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/cpumask.h> #include <linux/interrupt.h> diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 63287659adb6..fa22017de806 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -66,6 +66,31 @@ static void setup_apic_flat_routing(void) #endif } +static int default_apic_id_registered(void) +{ + return physid_isset(read_apic_id(), phys_cpu_present_map); +} + +/* + * Set up the logical destination ID. Intel recommends to set DFR, LDR and + * TPR before enabling an APIC. See e.g. "AP-388 82489DX User's Manual" + * (Intel document number 292116). + */ +static void default_init_apic_ldr(void) +{ + unsigned long val; + + apic_write(APIC_DFR, APIC_DFR_VALUE); + val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; + val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id()); + apic_write(APIC_LDR, val); +} + +static int default_phys_pkg_id(int cpuid_apic, int index_msb) +{ + return cpuid_apic >> index_msb; +} + /* should be called last. */ static int probe_default(void) { @@ -84,12 +109,10 @@ static struct apic apic_default __ro_after_init = { /* logical delivery broadcast to all CPUs: */ .irq_dest_mode = 1, - .target_cpus = default_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = default_check_apicid_used, - .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = default_init_apic_ldr, .ioapic_phys_id_map = default_ioapic_phys_id_map, @@ -102,7 +125,7 @@ static struct apic apic_default __ro_after_init = { .get_apic_id = default_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, + .calc_dest_apicid = apic_flat_calc_apicid, .send_IPI = default_send_IPI_single, .send_IPI_mask = default_send_IPI_mask_logical, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 88c214e75a6b..6a823a25eaff 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -1,5 +1,5 @@ /* - * Local APIC related interfaces to support IOAPIC, MSI, HT_IRQ etc. + * Local APIC related interfaces to support IOAPIC, MSI, etc. * * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * Moved from arch/x86/kernel/apic/io_apic.c. @@ -11,6 +11,7 @@ * published by the Free Software Foundation. */ #include <linux/interrupt.h> +#include <linux/seq_file.h> #include <linux/init.h> #include <linux/compiler.h> #include <linux/slab.h> @@ -21,20 +22,30 @@ #include <asm/desc.h> #include <asm/irq_remapping.h> +#include <asm/trace/irq_vectors.h> + struct apic_chip_data { - struct irq_cfg cfg; - cpumask_var_t domain; - cpumask_var_t old_domain; - u8 move_in_progress : 1; + struct irq_cfg hw_irq_cfg; + unsigned int vector; + unsigned int prev_vector; + unsigned int cpu; + unsigned int prev_cpu; + unsigned int irq; + struct hlist_node clist; + unsigned int move_in_progress : 1, + is_managed : 1, + can_reserve : 1, + has_reserved : 1; }; struct irq_domain *x86_vector_domain; EXPORT_SYMBOL_GPL(x86_vector_domain); static DEFINE_RAW_SPINLOCK(vector_lock); -static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask; +static cpumask_var_t vector_searchmask; static struct irq_chip lapic_controller; -#ifdef CONFIG_X86_IO_APIC -static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY]; +static struct irq_matrix *vector_matrix; +#ifdef CONFIG_SMP +static DEFINE_PER_CPU(struct hlist_head, cleanup_list); #endif void lock_vector_lock(void) @@ -50,22 +61,37 @@ void unlock_vector_lock(void) raw_spin_unlock(&vector_lock); } -static struct apic_chip_data *apic_chip_data(struct irq_data *irq_data) +void init_irq_alloc_info(struct irq_alloc_info *info, + const struct cpumask *mask) +{ + memset(info, 0, sizeof(*info)); + info->mask = mask; +} + +void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) { - if (!irq_data) + if (src) + *dst = *src; + else + memset(dst, 0, sizeof(*dst)); +} + +static struct apic_chip_data *apic_chip_data(struct irq_data *irqd) +{ + if (!irqd) return NULL; - while (irq_data->parent_data) - irq_data = irq_data->parent_data; + while (irqd->parent_data) + irqd = irqd->parent_data; - return irq_data->chip_data; + return irqd->chip_data; } -struct irq_cfg *irqd_cfg(struct irq_data *irq_data) +struct irq_cfg *irqd_cfg(struct irq_data *irqd) { - struct apic_chip_data *data = apic_chip_data(irq_data); + struct apic_chip_data *apicd = apic_chip_data(irqd); - return data ? &data->cfg : NULL; + return apicd ? &apicd->hw_irq_cfg : NULL; } EXPORT_SYMBOL_GPL(irqd_cfg); @@ -76,270 +102,395 @@ struct irq_cfg *irq_cfg(unsigned int irq) static struct apic_chip_data *alloc_apic_chip_data(int node) { - struct apic_chip_data *data; + struct apic_chip_data *apicd; - data = kzalloc_node(sizeof(*data), GFP_KERNEL, node); - if (!data) - return NULL; - if (!zalloc_cpumask_var_node(&data->domain, GFP_KERNEL, node)) - goto out_data; - if (!zalloc_cpumask_var_node(&data->old_domain, GFP_KERNEL, node)) - goto out_domain; - return data; -out_domain: - free_cpumask_var(data->domain); -out_data: - kfree(data); - return NULL; -} - -static void free_apic_chip_data(struct apic_chip_data *data) -{ - if (data) { - free_cpumask_var(data->domain); - free_cpumask_var(data->old_domain); - kfree(data); + apicd = kzalloc_node(sizeof(*apicd), GFP_KERNEL, node); + if (apicd) + INIT_HLIST_NODE(&apicd->clist); + return apicd; +} + +static void free_apic_chip_data(struct apic_chip_data *apicd) +{ + kfree(apicd); +} + +static void apic_update_irq_cfg(struct irq_data *irqd, unsigned int vector, + unsigned int cpu) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + + lockdep_assert_held(&vector_lock); + + apicd->hw_irq_cfg.vector = vector; + apicd->hw_irq_cfg.dest_apicid = apic->calc_dest_apicid(cpu); + irq_data_update_effective_affinity(irqd, cpumask_of(cpu)); + trace_vector_config(irqd->irq, vector, cpu, + apicd->hw_irq_cfg.dest_apicid); +} + +static void apic_update_vector(struct irq_data *irqd, unsigned int newvec, + unsigned int newcpu) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + struct irq_desc *desc = irq_data_to_desc(irqd); + + lockdep_assert_held(&vector_lock); + + trace_vector_update(irqd->irq, newvec, newcpu, apicd->vector, + apicd->cpu); + + /* Setup the vector move, if required */ + if (apicd->vector && cpu_online(apicd->cpu)) { + apicd->move_in_progress = true; + apicd->prev_vector = apicd->vector; + apicd->prev_cpu = apicd->cpu; + } else { + apicd->prev_vector = 0; } + + apicd->vector = newvec; + apicd->cpu = newcpu; + BUG_ON(!IS_ERR_OR_NULL(per_cpu(vector_irq, newcpu)[newvec])); + per_cpu(vector_irq, newcpu)[newvec] = desc; } -static int __assign_irq_vector(int irq, struct apic_chip_data *d, - const struct cpumask *mask, - struct irq_data *irqdata) +static void vector_assign_managed_shutdown(struct irq_data *irqd) { - /* - * NOTE! The local APIC isn't very good at handling - * multiple interrupts at the same interrupt level. - * As the interrupt level is determined by taking the - * vector number and shifting that right by 4, we - * want to spread these out a bit so that they don't - * all fall in the same interrupt level. - * - * Also, we've got to be careful not to trash gate - * 0x80, because int 0x80 is hm, kind of importantish. ;) - */ - static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; - static int current_offset = VECTOR_OFFSET_START % 16; - int cpu, vector; + unsigned int cpu = cpumask_first(cpu_online_mask); - /* - * If there is still a move in progress or the previous move has not - * been cleaned up completely, tell the caller to come back later. - */ - if (d->move_in_progress || - cpumask_intersects(d->old_domain, cpu_online_mask)) - return -EBUSY; + apic_update_irq_cfg(irqd, MANAGED_IRQ_SHUTDOWN_VECTOR, cpu); +} - /* Only try and allocate irqs on cpus that are present */ - cpumask_clear(d->old_domain); - cpumask_clear(searched_cpumask); - cpu = cpumask_first_and(mask, cpu_online_mask); - while (cpu < nr_cpu_ids) { - int new_cpu, offset; +static int reserve_managed_vector(struct irq_data *irqd) +{ + const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd); + struct apic_chip_data *apicd = apic_chip_data(irqd); + unsigned long flags; + int ret; - /* Get the possible target cpus for @mask/@cpu from the apic */ - apic->vector_allocation_domain(cpu, vector_cpumask, mask); + raw_spin_lock_irqsave(&vector_lock, flags); + apicd->is_managed = true; + ret = irq_matrix_reserve_managed(vector_matrix, affmsk); + raw_spin_unlock_irqrestore(&vector_lock, flags); + trace_vector_reserve_managed(irqd->irq, ret); + return ret; +} - /* - * Clear the offline cpus from @vector_cpumask for searching - * and verify whether the result overlaps with @mask. If true, - * then the call to apic->cpu_mask_to_apicid() will - * succeed as well. If not, no point in trying to find a - * vector in this mask. - */ - cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask); - if (!cpumask_intersects(vector_searchmask, mask)) - goto next_cpu; - - if (cpumask_subset(vector_cpumask, d->domain)) { - if (cpumask_equal(vector_cpumask, d->domain)) - goto success; - /* - * Mark the cpus which are not longer in the mask for - * cleanup. - */ - cpumask_andnot(d->old_domain, d->domain, vector_cpumask); - vector = d->cfg.vector; - goto update; - } +static void reserve_irq_vector_locked(struct irq_data *irqd) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); - vector = current_vector; - offset = current_offset; -next: - vector += 16; - if (vector >= FIRST_SYSTEM_VECTOR) { - offset = (offset + 1) % 16; - vector = FIRST_EXTERNAL_VECTOR + offset; - } + irq_matrix_reserve(vector_matrix); + apicd->can_reserve = true; + apicd->has_reserved = true; + trace_vector_reserve(irqd->irq, 0); + vector_assign_managed_shutdown(irqd); +} - /* If the search wrapped around, try the next cpu */ - if (unlikely(current_vector == vector)) - goto next_cpu; +static int reserve_irq_vector(struct irq_data *irqd) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&vector_lock, flags); + reserve_irq_vector_locked(irqd); + raw_spin_unlock_irqrestore(&vector_lock, flags); + return 0; +} - if (test_bit(vector, used_vectors)) - goto next; +static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + bool resvd = apicd->has_reserved; + unsigned int cpu = apicd->cpu; + int vector = apicd->vector; - for_each_cpu(new_cpu, vector_searchmask) { - if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector])) - goto next; - } - /* Found one! */ - current_vector = vector; - current_offset = offset; - /* Schedule the old vector for cleanup on all cpus */ - if (d->cfg.vector) - cpumask_copy(d->old_domain, d->domain); - for_each_cpu(new_cpu, vector_searchmask) - per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq); - goto update; - -next_cpu: - /* - * We exclude the current @vector_cpumask from the requested - * @mask and try again with the next online cpu in the - * result. We cannot modify @mask, so we use @vector_cpumask - * as a temporary buffer here as it will be reassigned when - * calling apic->vector_allocation_domain() above. - */ - cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask); - cpumask_andnot(vector_cpumask, mask, searched_cpumask); - cpu = cpumask_first_and(vector_cpumask, cpu_online_mask); - continue; - } - return -ENOSPC; + lockdep_assert_held(&vector_lock); -update: /* - * Exclude offline cpus from the cleanup mask and set the - * move_in_progress flag when the result is not empty. + * If the current target CPU is online and in the new requested + * affinity mask, there is no point in moving the interrupt from + * one CPU to another. */ - cpumask_and(d->old_domain, d->old_domain, cpu_online_mask); - d->move_in_progress = !cpumask_empty(d->old_domain); - d->cfg.old_vector = d->move_in_progress ? d->cfg.vector : 0; - d->cfg.vector = vector; - cpumask_copy(d->domain, vector_cpumask); -success: - /* - * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail - * as we already established, that mask & d->domain & cpu_online_mask - * is not empty. - * - * vector_searchmask is a subset of d->domain and has the offline - * cpus masked out. - */ - cpumask_and(vector_searchmask, vector_searchmask, mask); - BUG_ON(apic->cpu_mask_to_apicid(vector_searchmask, irqdata, - &d->cfg.dest_apicid)); + if (vector && cpu_online(cpu) && cpumask_test_cpu(cpu, dest)) + return 0; + + vector = irq_matrix_alloc(vector_matrix, dest, resvd, &cpu); + if (vector > 0) + apic_update_vector(irqd, vector, cpu); + trace_vector_alloc(irqd->irq, vector, resvd, vector); + return vector; +} + +static int assign_vector_locked(struct irq_data *irqd, + const struct cpumask *dest) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + int vector = allocate_vector(irqd, dest); + + if (vector < 0) + return vector; + + apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu); return 0; } -static int assign_irq_vector(int irq, struct apic_chip_data *data, - const struct cpumask *mask, - struct irq_data *irqdata) +static int assign_irq_vector(struct irq_data *irqd, const struct cpumask *dest) { - int err; unsigned long flags; + int ret; raw_spin_lock_irqsave(&vector_lock, flags); - err = __assign_irq_vector(irq, data, mask, irqdata); + cpumask_and(vector_searchmask, dest, cpu_online_mask); + ret = assign_vector_locked(irqd, vector_searchmask); raw_spin_unlock_irqrestore(&vector_lock, flags); - return err; + return ret; } -static int assign_irq_vector_policy(int irq, int node, - struct apic_chip_data *data, - struct irq_alloc_info *info, - struct irq_data *irqdata) +static int assign_irq_vector_any_locked(struct irq_data *irqd) { - if (info && info->mask) - return assign_irq_vector(irq, data, info->mask, irqdata); - if (node != NUMA_NO_NODE && - assign_irq_vector(irq, data, cpumask_of_node(node), irqdata) == 0) + /* Get the affinity mask - either irq_default_affinity or (user) set */ + const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd); + int node = irq_data_get_node(irqd); + + if (node == NUMA_NO_NODE) + goto all; + /* Try the intersection of @affmsk and node mask */ + cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk); + if (!assign_vector_locked(irqd, vector_searchmask)) + return 0; + /* Try the node mask */ + if (!assign_vector_locked(irqd, cpumask_of_node(node))) return 0; - return assign_irq_vector(irq, data, apic->target_cpus(), irqdata); +all: + /* Try the full affinity mask */ + cpumask_and(vector_searchmask, affmsk, cpu_online_mask); + if (!assign_vector_locked(irqd, vector_searchmask)) + return 0; + /* Try the full online mask */ + return assign_vector_locked(irqd, cpu_online_mask); +} + +static int +assign_irq_vector_policy(struct irq_data *irqd, struct irq_alloc_info *info) +{ + if (irqd_affinity_is_managed(irqd)) + return reserve_managed_vector(irqd); + if (info->mask) + return assign_irq_vector(irqd, info->mask); + /* + * Make only a global reservation with no guarantee. A real vector + * is associated at activation time. + */ + return reserve_irq_vector(irqd); } -static void clear_irq_vector(int irq, struct apic_chip_data *data) +static int +assign_managed_vector(struct irq_data *irqd, const struct cpumask *dest) { - struct irq_desc *desc; - int cpu, vector; + const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd); + struct apic_chip_data *apicd = apic_chip_data(irqd); + int vector, cpu; - if (!data->cfg.vector) + cpumask_and(vector_searchmask, vector_searchmask, affmsk); + cpu = cpumask_first(vector_searchmask); + if (cpu >= nr_cpu_ids) + return -EINVAL; + /* set_affinity might call here for nothing */ + if (apicd->vector && cpumask_test_cpu(apicd->cpu, vector_searchmask)) + return 0; + vector = irq_matrix_alloc_managed(vector_matrix, cpu); + trace_vector_alloc_managed(irqd->irq, vector, vector); + if (vector < 0) + return vector; + apic_update_vector(irqd, vector, cpu); + apic_update_irq_cfg(irqd, vector, cpu); + return 0; +} + +static void clear_irq_vector(struct irq_data *irqd) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + bool managed = irqd_affinity_is_managed(irqd); + unsigned int vector = apicd->vector; + + lockdep_assert_held(&vector_lock); + + if (!vector) return; - vector = data->cfg.vector; - for_each_cpu_and(cpu, data->domain, cpu_online_mask) - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; + trace_vector_clear(irqd->irq, vector, apicd->cpu, apicd->prev_vector, + apicd->prev_cpu); - data->cfg.vector = 0; - cpumask_clear(data->domain); + per_cpu(vector_irq, apicd->cpu)[vector] = VECTOR_UNUSED; + irq_matrix_free(vector_matrix, apicd->cpu, vector, managed); + apicd->vector = 0; - /* - * If move is in progress or the old_domain mask is not empty, - * i.e. the cleanup IPI has not been processed yet, we need to remove - * the old references to desc from all cpus vector tables. - */ - if (!data->move_in_progress && cpumask_empty(data->old_domain)) + /* Clean up move in progress */ + vector = apicd->prev_vector; + if (!vector) return; - desc = irq_to_desc(irq); - for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) { - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; - vector++) { - if (per_cpu(vector_irq, cpu)[vector] != desc) - continue; - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; - break; - } + per_cpu(vector_irq, apicd->prev_cpu)[vector] = VECTOR_UNUSED; + irq_matrix_free(vector_matrix, apicd->prev_cpu, vector, managed); + apicd->prev_vector = 0; + apicd->move_in_progress = 0; + hlist_del_init(&apicd->clist); +} + +static void x86_vector_deactivate(struct irq_domain *dom, struct irq_data *irqd) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + unsigned long flags; + + trace_vector_deactivate(irqd->irq, apicd->is_managed, + apicd->can_reserve, false); + + /* Regular fixed assigned interrupt */ + if (!apicd->is_managed && !apicd->can_reserve) + return; + /* If the interrupt has a global reservation, nothing to do */ + if (apicd->has_reserved) + return; + + raw_spin_lock_irqsave(&vector_lock, flags); + clear_irq_vector(irqd); + if (apicd->can_reserve) + reserve_irq_vector_locked(irqd); + else + vector_assign_managed_shutdown(irqd); + raw_spin_unlock_irqrestore(&vector_lock, flags); +} + +static int activate_reserved(struct irq_data *irqd) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + int ret; + + ret = assign_irq_vector_any_locked(irqd); + if (!ret) + apicd->has_reserved = false; + return ret; +} + +static int activate_managed(struct irq_data *irqd) +{ + const struct cpumask *dest = irq_data_get_affinity_mask(irqd); + int ret; + + cpumask_and(vector_searchmask, dest, cpu_online_mask); + if (WARN_ON_ONCE(cpumask_empty(vector_searchmask))) { + /* Something in the core code broke! Survive gracefully */ + pr_err("Managed startup for irq %u, but no CPU\n", irqd->irq); + return EINVAL; + } + + ret = assign_managed_vector(irqd, vector_searchmask); + /* + * This should not happen. The vector reservation got buggered. Handle + * it gracefully. + */ + if (WARN_ON_ONCE(ret < 0)) { + pr_err("Managed startup irq %u, no vector available\n", + irqd->irq); } - data->move_in_progress = 0; + return ret; } -void init_irq_alloc_info(struct irq_alloc_info *info, - const struct cpumask *mask) +static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, + bool early) { - memset(info, 0, sizeof(*info)); - info->mask = mask; + struct apic_chip_data *apicd = apic_chip_data(irqd); + unsigned long flags; + int ret = 0; + + trace_vector_activate(irqd->irq, apicd->is_managed, + apicd->can_reserve, early); + + /* Nothing to do for fixed assigned vectors */ + if (!apicd->can_reserve && !apicd->is_managed) + return 0; + + raw_spin_lock_irqsave(&vector_lock, flags); + if (early || irqd_is_managed_and_shutdown(irqd)) + vector_assign_managed_shutdown(irqd); + else if (apicd->is_managed) + ret = activate_managed(irqd); + else if (apicd->has_reserved) + ret = activate_reserved(irqd); + raw_spin_unlock_irqrestore(&vector_lock, flags); + return ret; } -void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) +static void vector_free_reserved_and_managed(struct irq_data *irqd) { - if (src) - *dst = *src; - else - memset(dst, 0, sizeof(*dst)); + const struct cpumask *dest = irq_data_get_affinity_mask(irqd); + struct apic_chip_data *apicd = apic_chip_data(irqd); + + trace_vector_teardown(irqd->irq, apicd->is_managed, + apicd->has_reserved); + + if (apicd->has_reserved) + irq_matrix_remove_reserved(vector_matrix); + if (apicd->is_managed) + irq_matrix_remove_managed(vector_matrix, dest); } static void x86_vector_free_irqs(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { - struct apic_chip_data *apic_data; - struct irq_data *irq_data; + struct apic_chip_data *apicd; + struct irq_data *irqd; unsigned long flags; int i; for (i = 0; i < nr_irqs; i++) { - irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i); - if (irq_data && irq_data->chip_data) { + irqd = irq_domain_get_irq_data(x86_vector_domain, virq + i); + if (irqd && irqd->chip_data) { raw_spin_lock_irqsave(&vector_lock, flags); - clear_irq_vector(virq + i, irq_data->chip_data); - apic_data = irq_data->chip_data; - irq_domain_reset_irq_data(irq_data); + clear_irq_vector(irqd); + vector_free_reserved_and_managed(irqd); + apicd = irqd->chip_data; + irq_domain_reset_irq_data(irqd); raw_spin_unlock_irqrestore(&vector_lock, flags); - free_apic_chip_data(apic_data); -#ifdef CONFIG_X86_IO_APIC - if (virq + i < nr_legacy_irqs()) - legacy_irq_data[virq + i] = NULL; -#endif + free_apic_chip_data(apicd); } } } +static bool vector_configure_legacy(unsigned int virq, struct irq_data *irqd, + struct apic_chip_data *apicd) +{ + unsigned long flags; + bool realloc = false; + + apicd->vector = ISA_IRQ_VECTOR(virq); + apicd->cpu = 0; + + raw_spin_lock_irqsave(&vector_lock, flags); + /* + * If the interrupt is activated, then it must stay at this vector + * position. That's usually the timer interrupt (0). + */ + if (irqd_is_activated(irqd)) { + trace_vector_setup(virq, true, 0); + apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu); + } else { + /* Release the vector */ + apicd->can_reserve = true; + clear_irq_vector(irqd); + realloc = true; + } + raw_spin_unlock_irqrestore(&vector_lock, flags); + return realloc; +} + static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { struct irq_alloc_info *info = arg; - struct apic_chip_data *data; - struct irq_data *irq_data; + struct apic_chip_data *apicd; + struct irq_data *irqd; int i, err, node; if (disable_apic) @@ -350,34 +501,37 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, return -ENOSYS; for (i = 0; i < nr_irqs; i++) { - irq_data = irq_domain_get_irq_data(domain, virq + i); - BUG_ON(!irq_data); - node = irq_data_get_node(irq_data); -#ifdef CONFIG_X86_IO_APIC - if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i]) - data = legacy_irq_data[virq + i]; - else -#endif - data = alloc_apic_chip_data(node); - if (!data) { + irqd = irq_domain_get_irq_data(domain, virq + i); + BUG_ON(!irqd); + node = irq_data_get_node(irqd); + WARN_ON_ONCE(irqd->chip_data); + apicd = alloc_apic_chip_data(node); + if (!apicd) { err = -ENOMEM; goto error; } - irq_data->chip = &lapic_controller; - irq_data->chip_data = data; - irq_data->hwirq = virq + i; - err = assign_irq_vector_policy(virq + i, node, data, info, - irq_data); - if (err) - goto error; + apicd->irq = virq + i; + irqd->chip = &lapic_controller; + irqd->chip_data = apicd; + irqd->hwirq = virq + i; + irqd_set_single_target(irqd); /* - * If the apic destination mode is physical, then the - * effective affinity is restricted to a single target - * CPU. Mark the interrupt accordingly. + * Legacy vectors are already assigned when the IOAPIC + * takes them over. They stay on the same vector. This is + * required for check_timer() to work correctly as it might + * switch back to legacy mode. Only update the hardware + * config. */ - if (!apic->irq_dest_mode) - irqd_set_single_target(irq_data); + if (info->flags & X86_IRQ_ALLOC_LEGACY) { + if (!vector_configure_legacy(virq + i, irqd, apicd)) + continue; + } + + err = assign_irq_vector_policy(irqd, info); + trace_vector_setup(virq + i, false, err); + if (err) + goto error; } return 0; @@ -387,9 +541,56 @@ error: return err; } +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS +void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d, + struct irq_data *irqd, int ind) +{ + unsigned int cpu, vector, prev_cpu, prev_vector; + struct apic_chip_data *apicd; + unsigned long flags; + int irq; + + if (!irqd) { + irq_matrix_debug_show(m, vector_matrix, ind); + return; + } + + irq = irqd->irq; + if (irq < nr_legacy_irqs() && !test_bit(irq, &io_apic_irqs)) { + seq_printf(m, "%*sVector: %5d\n", ind, "", ISA_IRQ_VECTOR(irq)); + seq_printf(m, "%*sTarget: Legacy PIC all CPUs\n", ind, ""); + return; + } + + apicd = irqd->chip_data; + if (!apicd) { + seq_printf(m, "%*sVector: Not assigned\n", ind, ""); + return; + } + + raw_spin_lock_irqsave(&vector_lock, flags); + cpu = apicd->cpu; + vector = apicd->vector; + prev_cpu = apicd->prev_cpu; + prev_vector = apicd->prev_vector; + raw_spin_unlock_irqrestore(&vector_lock, flags); + seq_printf(m, "%*sVector: %5u\n", ind, "", vector); + seq_printf(m, "%*sTarget: %5u\n", ind, "", cpu); + if (prev_vector) { + seq_printf(m, "%*sPrevious vector: %5u\n", ind, "", prev_vector); + seq_printf(m, "%*sPrevious target: %5u\n", ind, "", prev_cpu); + } +} +#endif + static const struct irq_domain_ops x86_vector_domain_ops = { - .alloc = x86_vector_alloc_irqs, - .free = x86_vector_free_irqs, + .alloc = x86_vector_alloc_irqs, + .free = x86_vector_free_irqs, + .activate = x86_vector_activate, + .deactivate = x86_vector_deactivate, +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS + .debug_show = x86_vector_debug_show, +#endif }; int __init arch_probe_nr_irqs(void) @@ -400,7 +601,7 @@ int __init arch_probe_nr_irqs(void) nr_irqs = NR_VECTORS * nr_cpu_ids; nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids; -#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ) +#if defined(CONFIG_PCI_MSI) /* * for MSI and HT dyn irq */ @@ -419,35 +620,40 @@ int __init arch_probe_nr_irqs(void) return legacy_pic->probe(); } -#ifdef CONFIG_X86_IO_APIC -static void __init init_legacy_irqs(void) +void lapic_assign_legacy_vector(unsigned int irq, bool replace) { - int i, node = cpu_to_node(0); - struct apic_chip_data *data; - /* - * For legacy IRQ's, start with assigning irq0 to irq15 to - * ISA_IRQ_VECTOR(i) for all cpu's. + * Use assign system here so it wont get accounted as allocated + * and moveable in the cpu hotplug check and it prevents managed + * irq reservation from touching it. */ - for (i = 0; i < nr_legacy_irqs(); i++) { - data = legacy_irq_data[i] = alloc_apic_chip_data(node); - BUG_ON(!data); + irq_matrix_assign_system(vector_matrix, ISA_IRQ_VECTOR(irq), replace); +} + +void __init lapic_assign_system_vectors(void) +{ + unsigned int i, vector = 0; - data->cfg.vector = ISA_IRQ_VECTOR(i); - cpumask_setall(data->domain); - irq_set_chip_data(i, data); + for_each_set_bit_from(vector, system_vectors, NR_VECTORS) + irq_matrix_assign_system(vector_matrix, vector, false); + + if (nr_legacy_irqs() > 1) + lapic_assign_legacy_vector(PIC_CASCADE_IR, false); + + /* System vectors are reserved, online it */ + irq_matrix_online(vector_matrix); + + /* Mark the preallocated legacy interrupts */ + for (i = 0; i < nr_legacy_irqs(); i++) { + if (i != PIC_CASCADE_IR) + irq_matrix_assign(vector_matrix, ISA_IRQ_VECTOR(i)); } } -#else -static inline void init_legacy_irqs(void) { } -#endif int __init arch_early_irq_init(void) { struct fwnode_handle *fn; - init_legacy_irqs(); - fn = irq_domain_alloc_named_fwnode("VECTOR"); BUG_ON(!fn); x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops, @@ -457,102 +663,116 @@ int __init arch_early_irq_init(void) irq_set_default_host(x86_vector_domain); arch_init_msi_domain(x86_vector_domain); - arch_init_htirq_domain(x86_vector_domain); - BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL)); - BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL)); + + /* + * Allocate the vector matrix allocator data structure and limit the + * search area. + */ + vector_matrix = irq_alloc_matrix(NR_VECTORS, FIRST_EXTERNAL_VECTOR, + FIRST_SYSTEM_VECTOR); + BUG_ON(!vector_matrix); return arch_early_ioapic_init(); } -/* Initialize vector_irq on a new cpu */ -static void __setup_vector_irq(int cpu) +#ifdef CONFIG_SMP + +static struct irq_desc *__setup_vector_irq(int vector) { - struct apic_chip_data *data; - struct irq_desc *desc; - int irq, vector; + int isairq = vector - ISA_IRQ_VECTOR(0); + + /* Check whether the irq is in the legacy space */ + if (isairq < 0 || isairq >= nr_legacy_irqs()) + return VECTOR_UNUSED; + /* Check whether the irq is handled by the IOAPIC */ + if (test_bit(isairq, &io_apic_irqs)) + return VECTOR_UNUSED; + return irq_to_desc(isairq); +} - /* Mark the inuse vectors */ - for_each_irq_desc(irq, desc) { - struct irq_data *idata = irq_desc_get_irq_data(desc); +/* Online the local APIC infrastructure and initialize the vectors */ +void lapic_online(void) +{ + unsigned int vector; - data = apic_chip_data(idata); - if (!data || !cpumask_test_cpu(cpu, data->domain)) - continue; - vector = data->cfg.vector; - per_cpu(vector_irq, cpu)[vector] = desc; - } - /* Mark the free vectors */ - for (vector = 0; vector < NR_VECTORS; ++vector) { - desc = per_cpu(vector_irq, cpu)[vector]; - if (IS_ERR_OR_NULL(desc)) - continue; + lockdep_assert_held(&vector_lock); - data = apic_chip_data(irq_desc_get_irq_data(desc)); - if (!cpumask_test_cpu(cpu, data->domain)) - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; - } + /* Online the vector matrix array for this CPU */ + irq_matrix_online(vector_matrix); + + /* + * The interrupt affinity logic never targets interrupts to offline + * CPUs. The exception are the legacy PIC interrupts. In general + * they are only targeted to CPU0, but depending on the platform + * they can be distributed to any online CPU in hardware. The + * kernel has no influence on that. So all active legacy vectors + * must be installed on all CPUs. All non legacy interrupts can be + * cleared. + */ + for (vector = 0; vector < NR_VECTORS; vector++) + this_cpu_write(vector_irq[vector], __setup_vector_irq(vector)); } -/* - * Setup the vector to irq mappings. Must be called with vector_lock held. - */ -void setup_vector_irq(int cpu) +void lapic_offline(void) { - int irq; + lock_vector_lock(); + irq_matrix_offline(vector_matrix); + unlock_vector_lock(); +} + +static int apic_set_affinity(struct irq_data *irqd, + const struct cpumask *dest, bool force) +{ + struct apic_chip_data *apicd = apic_chip_data(irqd); + int err; - lockdep_assert_held(&vector_lock); /* - * On most of the platforms, legacy PIC delivers the interrupts on the - * boot cpu. But there are certain platforms where PIC interrupts are - * delivered to multiple cpu's. If the legacy IRQ is handled by the - * legacy PIC, for the new cpu that is coming online, setup the static - * legacy vector to irq mapping: + * Core code can call here for inactive interrupts. For inactive + * interrupts which use managed or reservation mode there is no + * point in going through the vector assignment right now as the + * activation will assign a vector which fits the destination + * cpumask. Let the core code store the destination mask and be + * done with it. */ - for (irq = 0; irq < nr_legacy_irqs(); irq++) - per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq_to_desc(irq); + if (!irqd_is_activated(irqd) && + (apicd->is_managed || apicd->can_reserve)) + return IRQ_SET_MASK_OK; - __setup_vector_irq(cpu); + raw_spin_lock(&vector_lock); + cpumask_and(vector_searchmask, dest, cpu_online_mask); + if (irqd_affinity_is_managed(irqd)) + err = assign_managed_vector(irqd, vector_searchmask); + else + err = assign_vector_locked(irqd, vector_searchmask); + raw_spin_unlock(&vector_lock); + return err ? err : IRQ_SET_MASK_OK; } -static int apic_retrigger_irq(struct irq_data *irq_data) +#else +# define apic_set_affinity NULL +#endif + +static int apic_retrigger_irq(struct irq_data *irqd) { - struct apic_chip_data *data = apic_chip_data(irq_data); + struct apic_chip_data *apicd = apic_chip_data(irqd); unsigned long flags; - int cpu; raw_spin_lock_irqsave(&vector_lock, flags); - cpu = cpumask_first_and(data->domain, cpu_online_mask); - apic->send_IPI_mask(cpumask_of(cpu), data->cfg.vector); + apic->send_IPI(apicd->cpu, apicd->vector); raw_spin_unlock_irqrestore(&vector_lock, flags); return 1; } -void apic_ack_edge(struct irq_data *data) +void apic_ack_edge(struct irq_data *irqd) { - irq_complete_move(irqd_cfg(data)); - irq_move_irq(data); + irq_complete_move(irqd_cfg(irqd)); + irq_move_irq(irqd); ack_APIC_irq(); } -static int apic_set_affinity(struct irq_data *irq_data, - const struct cpumask *dest, bool force) -{ - struct apic_chip_data *data = irq_data->chip_data; - int err, irq = irq_data->irq; - - if (!IS_ENABLED(CONFIG_SMP)) - return -EPERM; - - if (!cpumask_intersects(dest, cpu_online_mask)) - return -EINVAL; - - err = assign_irq_vector(irq, data, dest, irq_data); - return err ? err : IRQ_SET_MASK_OK; -} - static struct irq_chip lapic_controller = { .name = "APIC", .irq_ack = apic_ack_edge, @@ -561,115 +781,98 @@ static struct irq_chip lapic_controller = { }; #ifdef CONFIG_SMP -static void __send_cleanup_vector(struct apic_chip_data *data) -{ - raw_spin_lock(&vector_lock); - cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); - data->move_in_progress = 0; - if (!cpumask_empty(data->old_domain)) - apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR); - raw_spin_unlock(&vector_lock); -} -void send_cleanup_vector(struct irq_cfg *cfg) +static void free_moved_vector(struct apic_chip_data *apicd) { - struct apic_chip_data *data; + unsigned int vector = apicd->prev_vector; + unsigned int cpu = apicd->prev_cpu; + bool managed = apicd->is_managed; - data = container_of(cfg, struct apic_chip_data, cfg); - if (data->move_in_progress) - __send_cleanup_vector(data); + /* + * This should never happen. Managed interrupts are not + * migrated except on CPU down, which does not involve the + * cleanup vector. But try to keep the accounting correct + * nevertheless. + */ + WARN_ON_ONCE(managed); + + trace_vector_free_moved(apicd->irq, cpu, vector, managed); + irq_matrix_free(vector_matrix, cpu, vector, managed); + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; + hlist_del_init(&apicd->clist); + apicd->prev_vector = 0; + apicd->move_in_progress = 0; } asmlinkage __visible void __irq_entry smp_irq_move_cleanup_interrupt(void) { - unsigned vector, me; + struct hlist_head *clhead = this_cpu_ptr(&cleanup_list); + struct apic_chip_data *apicd; + struct hlist_node *tmp; entering_ack_irq(); - /* Prevent vectors vanishing under us */ raw_spin_lock(&vector_lock); - me = smp_processor_id(); - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - struct apic_chip_data *data; - struct irq_desc *desc; - unsigned int irr; - - retry: - desc = __this_cpu_read(vector_irq[vector]); - if (IS_ERR_OR_NULL(desc)) - continue; - - if (!raw_spin_trylock(&desc->lock)) { - raw_spin_unlock(&vector_lock); - cpu_relax(); - raw_spin_lock(&vector_lock); - goto retry; - } - - data = apic_chip_data(irq_desc_get_irq_data(desc)); - if (!data) - goto unlock; + hlist_for_each_entry_safe(apicd, tmp, clhead, clist) { + unsigned int irr, vector = apicd->prev_vector; /* - * Nothing to cleanup if irq migration is in progress - * or this cpu is not set in the cleanup mask. - */ - if (data->move_in_progress || - !cpumask_test_cpu(me, data->old_domain)) - goto unlock; - - /* - * We have two cases to handle here: - * 1) vector is unchanged but the target mask got reduced - * 2) vector and the target mask has changed - * - * #1 is obvious, but in #2 we have two vectors with the same - * irq descriptor: the old and the new vector. So we need to - * make sure that we only cleanup the old vector. The new - * vector has the current @vector number in the config and - * this cpu is part of the target mask. We better leave that - * one alone. - */ - if (vector == data->cfg.vector && - cpumask_test_cpu(me, data->domain)) - goto unlock; - - irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); - /* - * Check if the vector that needs to be cleanedup is - * registered at the cpu's IRR. If so, then this is not - * the best time to clean it up. Lets clean it up in the + * Paranoia: Check if the vector that needs to be cleaned + * up is registered at the APICs IRR. If so, then this is + * not the best time to clean it up. Clean it up in the * next attempt by sending another IRQ_MOVE_CLEANUP_VECTOR - * to myself. + * to this CPU. IRQ_MOVE_CLEANUP_VECTOR is the lowest + * priority external vector, so on return from this + * interrupt the device interrupt will happen first. */ - if (irr & (1 << (vector % 32))) { + irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); + if (irr & (1U << (vector % 32))) { apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR); - goto unlock; + continue; } - __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); - cpumask_clear_cpu(me, data->old_domain); -unlock: - raw_spin_unlock(&desc->lock); + free_moved_vector(apicd); } raw_spin_unlock(&vector_lock); - exiting_irq(); } +static void __send_cleanup_vector(struct apic_chip_data *apicd) +{ + unsigned int cpu; + + raw_spin_lock(&vector_lock); + apicd->move_in_progress = 0; + cpu = apicd->prev_cpu; + if (cpu_online(cpu)) { + hlist_add_head(&apicd->clist, per_cpu_ptr(&cleanup_list, cpu)); + apic->send_IPI(cpu, IRQ_MOVE_CLEANUP_VECTOR); + } else { + apicd->prev_vector = 0; + } + raw_spin_unlock(&vector_lock); +} + +void send_cleanup_vector(struct irq_cfg *cfg) +{ + struct apic_chip_data *apicd; + + apicd = container_of(cfg, struct apic_chip_data, hw_irq_cfg); + if (apicd->move_in_progress) + __send_cleanup_vector(apicd); +} + static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) { - unsigned me; - struct apic_chip_data *data; + struct apic_chip_data *apicd; - data = container_of(cfg, struct apic_chip_data, cfg); - if (likely(!data->move_in_progress)) + apicd = container_of(cfg, struct apic_chip_data, hw_irq_cfg); + if (likely(!apicd->move_in_progress)) return; - me = smp_processor_id(); - if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain)) - __send_cleanup_vector(data); + if (vector == apicd->vector && apicd->cpu == smp_processor_id()) + __send_cleanup_vector(apicd); } void irq_complete_move(struct irq_cfg *cfg) @@ -682,10 +885,9 @@ void irq_complete_move(struct irq_cfg *cfg) */ void irq_force_complete_move(struct irq_desc *desc) { - struct irq_data *irqdata; - struct apic_chip_data *data; - struct irq_cfg *cfg; - unsigned int cpu; + struct apic_chip_data *apicd; + struct irq_data *irqd; + unsigned int vector; /* * The function is called for all descriptors regardless of which @@ -696,43 +898,31 @@ void irq_force_complete_move(struct irq_desc *desc) * Check first that the chip_data is what we expect * (apic_chip_data) before touching it any further. */ - irqdata = irq_domain_get_irq_data(x86_vector_domain, - irq_desc_get_irq(desc)); - if (!irqdata) + irqd = irq_domain_get_irq_data(x86_vector_domain, + irq_desc_get_irq(desc)); + if (!irqd) return; - data = apic_chip_data(irqdata); - cfg = data ? &data->cfg : NULL; + raw_spin_lock(&vector_lock); + apicd = apic_chip_data(irqd); + if (!apicd) + goto unlock; - if (!cfg) - return; + /* + * If prev_vector is empty, no action required. + */ + vector = apicd->prev_vector; + if (!vector) + goto unlock; /* - * This is tricky. If the cleanup of @data->old_domain has not been + * This is tricky. If the cleanup of the old vector has not been * done yet, then the following setaffinity call will fail with * -EBUSY. This can leave the interrupt in a stale state. * * All CPUs are stuck in stop machine with interrupts disabled so * calling __irq_complete_move() would be completely pointless. - */ - raw_spin_lock(&vector_lock); - /* - * Clean out all offline cpus (including the outgoing one) from the - * old_domain mask. - */ - cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); - - /* - * If move_in_progress is cleared and the old_domain mask is empty, - * then there is nothing to cleanup. fixup_irqs() will take care of - * the stale vectors on the outgoing cpu. - */ - if (!data->move_in_progress && cpumask_empty(data->old_domain)) { - raw_spin_unlock(&vector_lock); - return; - } - - /* + * * 1) The interrupt is in move_in_progress state. That means that we * have not seen an interrupt since the io_apic was reprogrammed to * the new vector. @@ -740,7 +930,7 @@ void irq_force_complete_move(struct irq_desc *desc) * 2) The interrupt has fired on the new vector, but the cleanup IPIs * have not been processed yet. */ - if (data->move_in_progress) { + if (apicd->move_in_progress) { /* * In theory there is a race: * @@ -774,21 +964,43 @@ void irq_force_complete_move(struct irq_desc *desc) * area arises. */ pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n", - irqdata->irq, cfg->old_vector); + irqd->irq, vector); } - /* - * If old_domain is not empty, then other cpus still have the irq - * descriptor set in their vector array. Clean it up. - */ - for_each_cpu(cpu, data->old_domain) - per_cpu(vector_irq, cpu)[cfg->old_vector] = VECTOR_UNUSED; + free_moved_vector(apicd); +unlock: + raw_spin_unlock(&vector_lock); +} + +#ifdef CONFIG_HOTPLUG_CPU +/* + * Note, this is not accurate accounting, but at least good enough to + * prevent that the actual interrupt move will run out of vectors. + */ +int lapic_can_unplug_cpu(void) +{ + unsigned int rsvd, avl, tomove, cpu = smp_processor_id(); + int ret = 0; - /* Cleanup the left overs of the (half finished) move */ - cpumask_clear(data->old_domain); - data->move_in_progress = 0; + raw_spin_lock(&vector_lock); + tomove = irq_matrix_allocated(vector_matrix); + avl = irq_matrix_available(vector_matrix, true); + if (avl < tomove) { + pr_warn("CPU %u has %u vectors, %u available. Cannot disable CPU\n", + cpu, tomove, avl); + ret = -ENOSPC; + goto out; + } + rsvd = irq_matrix_reserved(vector_matrix); + if (avl < rsvd) { + pr_warn("Reserved vectors %u > available %u. IRQ request may fail\n", + rsvd, avl); + } +out: raw_spin_unlock(&vector_lock); + return ret; } -#endif +#endif /* HOTPLUG_CPU */ +#endif /* SMP */ static void __init print_APIC_field(int base) { diff --git a/arch/x86/kernel/apic/x2apic.h b/arch/x86/kernel/apic/x2apic.h new file mode 100644 index 000000000000..b107de381cb5 --- /dev/null +++ b/arch/x86/kernel/apic/x2apic.h @@ -0,0 +1,9 @@ +/* Common bits for X2APIC cluster/physical modes. */ + +int x2apic_apic_id_valid(int apicid); +int x2apic_apic_id_registered(void); +void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest); +unsigned int x2apic_get_apic_id(unsigned long id); +u32 x2apic_set_apic_id(unsigned int id); +int x2apic_phys_pkg_id(int initial_apicid, int index_msb); +void x2apic_send_IPI_self(int vector); diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 481237cb1544..622f13ca8a94 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/string.h> @@ -8,22 +9,24 @@ #include <linux/cpu.h> #include <asm/smp.h> -#include <asm/x2apic.h> +#include "x2apic.h" + +struct cluster_mask { + unsigned int clusterid; + int node; + struct cpumask mask; +}; static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid); -static DEFINE_PER_CPU(cpumask_var_t, cpus_in_cluster); static DEFINE_PER_CPU(cpumask_var_t, ipi_mask); +static DEFINE_PER_CPU(struct cluster_mask *, cluster_masks); +static struct cluster_mask *cluster_hotplug_mask; static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return x2apic_enabled(); } -static inline u32 x2apic_cluster(int cpu) -{ - return per_cpu(x86_cpu_to_logical_apicid, cpu) >> 16; -} - static void x2apic_send_IPI(int cpu, int vector) { u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu); @@ -35,49 +38,34 @@ static void x2apic_send_IPI(int cpu, int vector) static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { - struct cpumask *cpus_in_cluster_ptr; - struct cpumask *ipi_mask_ptr; - unsigned int cpu, this_cpu; + unsigned int cpu, clustercpu; + struct cpumask *tmpmsk; unsigned long flags; u32 dest; x2apic_wrmsr_fence(); - local_irq_save(flags); - this_cpu = smp_processor_id(); + tmpmsk = this_cpu_cpumask_var_ptr(ipi_mask); + cpumask_copy(tmpmsk, mask); + /* If IPI should not be sent to self, clear current CPU */ + if (apic_dest != APIC_DEST_ALLINC) + cpumask_clear_cpu(smp_processor_id(), tmpmsk); - /* - * We are to modify mask, so we need an own copy - * and be sure it's manipulated with irq off. - */ - ipi_mask_ptr = this_cpu_cpumask_var_ptr(ipi_mask); - cpumask_copy(ipi_mask_ptr, mask); - - /* - * The idea is to send one IPI per cluster. - */ - for_each_cpu(cpu, ipi_mask_ptr) { - unsigned long i; + /* Collapse cpus in a cluster so a single IPI per cluster is sent */ + for_each_cpu(cpu, tmpmsk) { + struct cluster_mask *cmsk = per_cpu(cluster_masks, cpu); - cpus_in_cluster_ptr = per_cpu(cpus_in_cluster, cpu); dest = 0; - - /* Collect cpus in cluster. */ - for_each_cpu_and(i, ipi_mask_ptr, cpus_in_cluster_ptr) { - if (apic_dest == APIC_DEST_ALLINC || i != this_cpu) - dest |= per_cpu(x86_cpu_to_logical_apicid, i); - } + for_each_cpu_and(clustercpu, tmpmsk, &cmsk->mask) + dest |= per_cpu(x86_cpu_to_logical_apicid, clustercpu); if (!dest) continue; __x2apic_send_IPI_dest(dest, vector, apic->dest_logical); - /* - * Cluster sibling cpus should be discared now so - * we would not send IPI them second time. - */ - cpumask_andnot(ipi_mask_ptr, ipi_mask_ptr, cpus_in_cluster_ptr); + /* Remove cluster CPUs from tmpmask */ + cpumask_andnot(tmpmsk, tmpmsk, &cmsk->mask); } local_irq_restore(flags); @@ -104,125 +92,90 @@ static void x2apic_send_IPI_all(int vector) __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC); } -static int -x2apic_cpu_mask_to_apicid(const struct cpumask *mask, struct irq_data *irqdata, - unsigned int *apicid) +static u32 x2apic_calc_apicid(unsigned int cpu) { - struct cpumask *effmsk = irq_data_get_effective_affinity_mask(irqdata); - unsigned int cpu; - u32 dest = 0; - u16 cluster; - - cpu = cpumask_first(mask); - if (cpu >= nr_cpu_ids) - return -EINVAL; - - dest = per_cpu(x86_cpu_to_logical_apicid, cpu); - cluster = x2apic_cluster(cpu); - - cpumask_clear(effmsk); - for_each_cpu(cpu, mask) { - if (cluster != x2apic_cluster(cpu)) - continue; - dest |= per_cpu(x86_cpu_to_logical_apicid, cpu); - cpumask_set_cpu(cpu, effmsk); - } - - *apicid = dest; - return 0; + return per_cpu(x86_cpu_to_logical_apicid, cpu); } static void init_x2apic_ldr(void) { - unsigned int this_cpu = smp_processor_id(); + struct cluster_mask *cmsk = this_cpu_read(cluster_masks); + u32 cluster, apicid = apic_read(APIC_LDR); unsigned int cpu; - per_cpu(x86_cpu_to_logical_apicid, this_cpu) = apic_read(APIC_LDR); + this_cpu_write(x86_cpu_to_logical_apicid, apicid); + + if (cmsk) + goto update; - cpumask_set_cpu(this_cpu, per_cpu(cpus_in_cluster, this_cpu)); + cluster = apicid >> 16; for_each_online_cpu(cpu) { - if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu)) - continue; - cpumask_set_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu)); - cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu)); + cmsk = per_cpu(cluster_masks, cpu); + /* Matching cluster found. Link and update it. */ + if (cmsk && cmsk->clusterid == cluster) + goto update; } + cmsk = cluster_hotplug_mask; + cluster_hotplug_mask = NULL; +update: + this_cpu_write(cluster_masks, cmsk); + cpumask_set_cpu(smp_processor_id(), &cmsk->mask); } -/* - * At CPU state changes, update the x2apic cluster sibling info. - */ -static int x2apic_prepare_cpu(unsigned int cpu) +static int alloc_clustermask(unsigned int cpu, int node) { - if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL)) - return -ENOMEM; + if (per_cpu(cluster_masks, cpu)) + return 0; + /* + * If a hotplug spare mask exists, check whether it's on the right + * node. If not, free it and allocate a new one. + */ + if (cluster_hotplug_mask) { + if (cluster_hotplug_mask->node == node) + return 0; + kfree(cluster_hotplug_mask); + } - if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL)) { - free_cpumask_var(per_cpu(cpus_in_cluster, cpu)); + cluster_hotplug_mask = kzalloc_node(sizeof(*cluster_hotplug_mask), + GFP_KERNEL, node); + if (!cluster_hotplug_mask) return -ENOMEM; - } + cluster_hotplug_mask->node = node; + return 0; +} +static int x2apic_prepare_cpu(unsigned int cpu) +{ + if (alloc_clustermask(cpu, cpu_to_node(cpu)) < 0) + return -ENOMEM; + if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL)) + return -ENOMEM; return 0; } -static int x2apic_dead_cpu(unsigned int this_cpu) +static int x2apic_dead_cpu(unsigned int dead_cpu) { - int cpu; + struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu); - for_each_online_cpu(cpu) { - if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu)) - continue; - cpumask_clear_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu)); - cpumask_clear_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu)); - } - free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu)); - free_cpumask_var(per_cpu(ipi_mask, this_cpu)); + cpumask_clear_cpu(dead_cpu, &cmsk->mask); + free_cpumask_var(per_cpu(ipi_mask, dead_cpu)); return 0; } static int x2apic_cluster_probe(void) { - int cpu = smp_processor_id(); - int ret; - if (!x2apic_mode) return 0; - ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare", - x2apic_prepare_cpu, x2apic_dead_cpu); - if (ret < 0) { + if (cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare", + x2apic_prepare_cpu, x2apic_dead_cpu) < 0) { pr_err("Failed to register X2APIC_PREPARE\n"); return 0; } - cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu)); + init_x2apic_ldr(); return 1; } -static const struct cpumask *x2apic_cluster_target_cpus(void) -{ - return cpu_all_mask; -} - -/* - * Each x2apic cluster is an allocation domain. - */ -static void cluster_vector_allocation_domain(int cpu, struct cpumask *retmask, - const struct cpumask *mask) -{ - /* - * To minimize vector pressure, default case of boot, device bringup - * etc will use a single cpu for the interrupt destination. - * - * On explicit migration requests coming from irqbalance etc, - * interrupts will be routed to the x2apic cluster (cluster-id - * derived from the first cpu in the mask) members specified - * in the mask. - */ - if (mask == x2apic_cluster_target_cpus()) - cpumask_copy(retmask, cpumask_of(cpu)); - else - cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu)); -} - static struct apic apic_x2apic_cluster __ro_after_init = { .name = "cluster x2apic", @@ -234,12 +187,10 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .irq_delivery_mode = dest_LowestPrio, .irq_dest_mode = 1, /* logical */ - .target_cpus = x2apic_cluster_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, - .vector_allocation_domain = cluster_vector_allocation_domain, .init_apic_ldr = init_x2apic_ldr, .ioapic_phys_id_map = NULL, @@ -252,7 +203,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = x2apic_set_apic_id, - .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, + .calc_dest_apicid = x2apic_calc_apicid, .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 3baf0c3dc875..f8d9d69994e6 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/string.h> @@ -6,7 +7,8 @@ #include <linux/dmar.h> #include <asm/smp.h> -#include <asm/x2apic.h> +#include <asm/ipi.h> +#include "x2apic.h" int x2apic_phys; @@ -98,6 +100,43 @@ static int x2apic_phys_probe(void) return apic == &apic_x2apic_phys; } +/* Common x2apic functions, also used by x2apic_cluster */ +int x2apic_apic_id_valid(int apicid) +{ + return 1; +} + +int x2apic_apic_id_registered(void) +{ + return 1; +} + +void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest) +{ + unsigned long cfg = __prepare_ICR(0, vector, dest); + native_x2apic_icr_write(cfg, apicid); +} + +unsigned int x2apic_get_apic_id(unsigned long id) +{ + return id; +} + +u32 x2apic_set_apic_id(unsigned int id) +{ + return id; +} + +int x2apic_phys_pkg_id(int initial_apicid, int index_msb) +{ + return initial_apicid >> index_msb; +} + +void x2apic_send_IPI_self(int vector) +{ + apic_write(APIC_SELF_IPI, vector); +} + static struct apic apic_x2apic_phys __ro_after_init = { .name = "physical x2apic", @@ -109,12 +148,10 @@ static struct apic apic_x2apic_phys __ro_after_init = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, - .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = init_x2apic_ldr, .ioapic_phys_id_map = NULL, @@ -127,7 +164,7 @@ static struct apic apic_x2apic_phys __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = x2apic_set_apic_id, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .calc_dest_apicid = apic_default_calc_apicid, .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 0d57bb9079c9..e1b8e8bf6b3c 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -154,6 +154,48 @@ static int __init early_get_pnodeid(void) return pnode; } +static void __init uv_tsc_check_sync(void) +{ + u64 mmr; + int sync_state; + int mmr_shift; + char *state; + bool valid; + + /* Accommodate different UV arch BIOSes */ + mmr = uv_early_read_mmr(UVH_TSC_SYNC_MMR); + mmr_shift = + is_uv1_hub() ? 0 : + is_uv2_hub() ? UVH_TSC_SYNC_SHIFT_UV2K : UVH_TSC_SYNC_SHIFT; + if (mmr_shift) + sync_state = (mmr >> mmr_shift) & UVH_TSC_SYNC_MASK; + else + sync_state = 0; + + switch (sync_state) { + case UVH_TSC_SYNC_VALID: + state = "in sync"; + valid = true; + break; + + case UVH_TSC_SYNC_INVALID: + state = "unstable"; + valid = false; + break; + default: + state = "unknown: assuming valid"; + valid = true; + break; + } + pr_info("UV: TSC sync state from BIOS:0%d(%s)\n", sync_state, state); + + /* Mark flag that says TSC != 0 is valid for socket 0 */ + if (valid) + mark_tsc_async_resets("UV BIOS"); + else + mark_tsc_unstable("UV BIOS"); +} + /* [Copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */ #define SMT_LEVEL 0 /* Leaf 0xb SMT level */ @@ -288,6 +330,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) } pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n", oem_id, oem_table_id, uv_system_type, uv_min_hub_revision_id, uv_apic); + uv_tsc_check_sync(); return uv_apic; @@ -525,16 +568,9 @@ static void uv_init_apic_ldr(void) { } -static int -uv_cpu_mask_to_apicid(const struct cpumask *mask, struct irq_data *irqdata, - unsigned int *apicid) +static u32 apic_uv_calc_apicid(unsigned int cpu) { - int ret = default_cpu_mask_to_apicid(mask, irqdata, apicid); - - if (!ret) - *apicid |= uv_apicid_hibits; - - return ret; + return apic_default_calc_apicid(cpu) | uv_apicid_hibits; } static unsigned int x2apic_get_apic_id(unsigned long x) @@ -547,7 +583,7 @@ static unsigned int x2apic_get_apic_id(unsigned long x) return id; } -static unsigned long set_apic_id(unsigned int id) +static u32 set_apic_id(unsigned int id) { /* CHECKME: Do we need to mask out the xapic extra bits? */ return id; @@ -584,12 +620,10 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* Physical */ - .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, - .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = uv_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -602,7 +636,7 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid = uv_cpu_mask_to_apicid, + .calc_dest_apicid = apic_uv_calc_apicid, .send_IPI = uv_send_IPI_one, .send_IPI_mask = uv_send_IPI_mask, @@ -920,9 +954,8 @@ static __init void uv_rtc_init(void) /* * percpu heartbeat timer */ -static void uv_heartbeat(unsigned long ignored) +static void uv_heartbeat(struct timer_list *timer) { - struct timer_list *timer = &uv_scir_info->timer; unsigned char bits = uv_scir_info->state; /* Flip heartbeat bit: */ @@ -947,7 +980,7 @@ static int uv_heartbeat_enable(unsigned int cpu) struct timer_list *timer = &uv_cpu_scir_info(cpu)->timer; uv_set_cpu_scir_bits(cpu, SCIR_CPU_HEARTBEAT|SCIR_CPU_ACTIVITY); - setup_pinned_timer(timer, uv_heartbeat, cpu); + timer_setup(timer, uv_heartbeat, TIMER_PINNED); timer->expires = jiffies + SCIR_CPU_HB_INTERVAL; add_timer_on(timer, cpu); uv_cpu_scir_info(cpu)->enabled = 1; diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index de827d6ac8c2..8ea78275480d 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generate definitions needed by assembly language modules. * This code generates raw asm output which is post-processed to extract diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 710edab9e644..dedf428b20b6 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #ifndef __LINUX_KBUILD_H # error "Please do not build this file directly, build asm-offsets.c instead" #endif diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index cf42206926af..630212fa9b9d 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #ifndef __LINUX_KBUILD_H # error "Please do not build this file directly, build asm-offsets.c instead" #endif diff --git a/arch/x86/kernel/audit_64.c b/arch/x86/kernel/audit_64.c index f3672508b249..e1efe44ebefc 100644 --- a/arch/x86/kernel/audit_64.c +++ b/arch/x86/kernel/audit_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/types.h> #include <linux/audit.h> diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c index 52c8e3c7789d..3fed7ae58b60 100644 --- a/arch/x86/kernel/bootflag.c +++ b/arch/x86/kernel/bootflag.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Implement 'Simple Boot Flag Specification 2.0' */ diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 145863d4d343..33399426793e 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/sched.h> #include <linux/kthread.h> diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index e17942c131c8..570e8bb1f386 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for x86-compatible CPU details, features and quirks # @@ -21,7 +22,8 @@ obj-y += common.o obj-y += rdrand.o obj-y += match.o obj-y += bugs.o -obj-$(CONFIG_CPU_FREQ) += aperfmperf.o +obj-y += aperfmperf.o +obj-y += cpuid-deps.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9862e2cd6d93..d58184b7cd44 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -763,6 +763,16 @@ static void init_amd_bd(struct cpuinfo_x86 *c) } } +static void init_amd_zn(struct cpuinfo_x86 *c) +{ + /* + * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects + * all up to and including B1. + */ + if (c->x86_model <= 1 && c->x86_mask <= 1) + set_cpu_cap(c, X86_FEATURE_CPB); +} + static void init_amd(struct cpuinfo_x86 *c) { early_init_amd(c); @@ -791,6 +801,7 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x10: init_amd_gh(c); break; case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; + case 0x17: init_amd_zn(c); break; } /* Enable workaround for FXSAVE leak */ diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index 0ee83321a313..7eba34df54c3 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -14,6 +14,8 @@ #include <linux/percpu.h> #include <linux/smp.h> +#include "cpu.h" + struct aperfmperf_sample { unsigned int khz; ktime_t time; @@ -24,7 +26,7 @@ struct aperfmperf_sample { static DEFINE_PER_CPU(struct aperfmperf_sample, samples); #define APERFMPERF_CACHE_THRESHOLD_MS 10 -#define APERFMPERF_REFRESH_DELAY_MS 20 +#define APERFMPERF_REFRESH_DELAY_MS 10 #define APERFMPERF_STALE_THRESHOLD_MS 1000 /* @@ -38,14 +40,8 @@ static void aperfmperf_snapshot_khz(void *dummy) u64 aperf, aperf_delta; u64 mperf, mperf_delta; struct aperfmperf_sample *s = this_cpu_ptr(&samples); - ktime_t now = ktime_get(); - s64 time_delta = ktime_ms_delta(now, s->time); unsigned long flags; - /* Don't bother re-computing within the cache threshold time. */ - if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS) - return; - local_irq_save(flags); rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); @@ -61,31 +57,68 @@ static void aperfmperf_snapshot_khz(void *dummy) if (mperf_delta == 0) return; - s->time = now; + s->time = ktime_get(); s->aperf = aperf; s->mperf = mperf; + s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); +} - /* If the previous iteration was too long ago, discard it. */ - if (time_delta > APERFMPERF_STALE_THRESHOLD_MS) - s->khz = 0; - else - s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); +static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait) +{ + s64 time_delta = ktime_ms_delta(now, per_cpu(samples.time, cpu)); + + /* Don't bother re-computing within the cache threshold time. */ + if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS) + return true; + + smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, wait); + + /* Return false if the previous iteration was too long ago. */ + return time_delta <= APERFMPERF_STALE_THRESHOLD_MS; } -unsigned int arch_freq_get_on_cpu(int cpu) +unsigned int aperfmperf_get_khz(int cpu) { - unsigned int khz; + if (!cpu_khz) + return 0; + + if (!static_cpu_has(X86_FEATURE_APERFMPERF)) + return 0; + aperfmperf_snapshot_cpu(cpu, ktime_get(), true); + return per_cpu(samples.khz, cpu); +} + +void arch_freq_prepare_all(void) +{ + ktime_t now = ktime_get(); + bool wait = false; + int cpu; + + if (!cpu_khz) + return; + + if (!static_cpu_has(X86_FEATURE_APERFMPERF)) + return; + + for_each_online_cpu(cpu) + if (!aperfmperf_snapshot_cpu(cpu, now, false)) + wait = true; + + if (wait) + msleep(APERFMPERF_REFRESH_DELAY_MS); +} + +unsigned int arch_freq_get_on_cpu(int cpu) +{ if (!cpu_khz) return 0; if (!static_cpu_has(X86_FEATURE_APERFMPERF)) return 0; - smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1); - khz = per_cpu(samples.khz, cpu); - if (khz) - return khz; + if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true)) + return per_cpu(samples.khz, cpu); msleep(APERFMPERF_REFRESH_DELAY_MS); smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index db684880d74a..ba0b2424c9b0 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1994 Linus Torvalds * @@ -21,14 +22,6 @@ void __init check_bugs(void) { -#ifdef CONFIG_X86_32 - /* - * Regardless of whether PCID is enumerated, the SDM says - * that it can't be enabled in 32-bit mode. - */ - setup_clear_cpu_cap(X86_FEATURE_PCID); -#endif - identify_boot_cpu(); if (!IS_ENABLED(CONFIG_SMP)) { diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 44207b71fee1..68bc6d9b3132 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/sched.h> #include <linux/sched/clock.h> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 775f10100d7f..fa998ca8aa5a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -329,6 +329,30 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) } } +static __always_inline void setup_umip(struct cpuinfo_x86 *c) +{ + /* Check the boot processor, plus build option for UMIP. */ + if (!cpu_feature_enabled(X86_FEATURE_UMIP)) + goto out; + + /* Check the current processor's cpuid bits. */ + if (!cpu_has(c, X86_FEATURE_UMIP)) + goto out; + + cr4_set_bits(X86_CR4_UMIP); + + pr_info("x86/cpu: Activated the Intel User Mode Instruction Prevention (UMIP) CPU feature\n"); + + return; + +out: + /* + * Make sure UMIP is disabled in case it was enabled in a + * previous boot (e.g., via kexec). + */ + cr4_clear_bits(X86_CR4_UMIP); +} + /* * Protection Keys are not available in 32-bit mode. */ @@ -863,8 +887,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) * cache alignment. * The others are not touched to avoid unwanted side effects. * - * WARNING: this function is only called on the BP. Don't add code here - * that is supposed to run on all CPUs. + * WARNING: this function is only called on the boot CPU. Don't add code + * here that is supposed to run on all CPUs. */ static void __init early_identify_cpu(struct cpuinfo_x86 *c) { @@ -904,6 +928,14 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ALWAYS); fpu__init_system(c); + +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif } void __init early_cpu_init(void) @@ -1139,9 +1171,10 @@ static void identify_cpu(struct cpuinfo_x86 *c) /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); - /* Set up SMEP/SMAP */ + /* Set up SMEP/SMAP/UMIP */ setup_smep(c); setup_smap(c); + setup_umip(c); /* * The vendor-specific functions might have changed features. @@ -1293,18 +1326,16 @@ void print_cpu_info(struct cpuinfo_x86 *c) pr_cont(")\n"); } -static __init int setup_disablecpuid(char *arg) +/* + * clearcpuid= was already parsed in fpu__init_parse_early_param. + * But we need to keep a dummy __setup around otherwise it would + * show up as an environment variable for init. + */ +static __init int setup_clearcpuid(char *arg) { - int bit; - - if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32) - setup_clear_cpu_cap(bit); - else - return 0; - return 1; } -__setup("clearcpuid=", setup_disablecpuid); +__setup("clearcpuid=", setup_clearcpuid); #ifdef CONFIG_X86_64 DEFINE_PER_CPU_FIRST(union irq_stack_union, @@ -1564,9 +1595,13 @@ void cpu_init(void) initialize_tlbstate_and_flush(); enter_lazy_tlb(&init_mm, me); - load_sp0(t, ¤t->thread); + /* + * Initialize the TSS. Don't bother initializing sp0, as the initial + * task never enters user mode. + */ set_tss_desc(cpu, t); load_TR_desc(); + load_mm_ldt(&init_mm); clear_all_debug_regs(); @@ -1588,7 +1623,6 @@ void cpu_init(void) int cpu = smp_processor_id(); struct task_struct *curr = current; struct tss_struct *t = &per_cpu(cpu_tss, cpu); - struct thread_struct *thread = &curr->thread; wait_for_master_cpu(cpu); @@ -1619,9 +1653,13 @@ void cpu_init(void) initialize_tlbstate_and_flush(); enter_lazy_tlb(&init_mm, curr); - load_sp0(t, thread); + /* + * Initialize the TSS. Don't bother initializing sp0, as the initial + * task never enters user mode. + */ set_tss_desc(cpu, t); load_TR_desc(); + load_mm_ldt(&init_mm); t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 2584265d4745..e806b11a99af 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ARCH_X86_CPU_H #define ARCH_X86_CPU_H @@ -46,4 +47,7 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[], extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); + +unsigned int aperfmperf_get_khz(int cpu); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c new file mode 100644 index 000000000000..904b0a3c4e53 --- /dev/null +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -0,0 +1,121 @@ +/* Declare dependencies between CPUIDs */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <asm/cpufeature.h> + +struct cpuid_dep { + unsigned int feature; + unsigned int depends; +}; + +/* + * Table of CPUID features that depend on others. + * + * This only includes dependencies that can be usefully disabled, not + * features part of the base set (like FPU). + * + * Note this all is not __init / __initdata because it can be + * called from cpu hotplug. It shouldn't do anything in this case, + * but it's difficult to tell that to the init reference checker. + */ +const static struct cpuid_dep cpuid_deps[] = { + { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE }, + { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE }, + { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE }, + { X86_FEATURE_AVX, X86_FEATURE_XSAVE }, + { X86_FEATURE_PKU, X86_FEATURE_XSAVE }, + { X86_FEATURE_MPX, X86_FEATURE_XSAVE }, + { X86_FEATURE_XGETBV1, X86_FEATURE_XSAVE }, + { X86_FEATURE_FXSR_OPT, X86_FEATURE_FXSR }, + { X86_FEATURE_XMM, X86_FEATURE_FXSR }, + { X86_FEATURE_XMM2, X86_FEATURE_XMM }, + { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM4_1, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM4_2, X86_FEATURE_XMM2 }, + { X86_FEATURE_XMM3, X86_FEATURE_XMM2 }, + { X86_FEATURE_PCLMULQDQ, X86_FEATURE_XMM2 }, + { X86_FEATURE_SSSE3, X86_FEATURE_XMM2, }, + { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, + { X86_FEATURE_AES, X86_FEATURE_XMM2 }, + { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, + { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, + { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512PF, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512ER, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512CD, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512DQ, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512BW, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, + { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, + { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, + { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_4FMAPS, X86_FEATURE_AVX512F }, + { X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F }, + {} +}; + +static inline void clear_feature(struct cpuinfo_x86 *c, unsigned int feature) +{ + /* + * Note: This could use the non atomic __*_bit() variants, but the + * rest of the cpufeature code uses atomics as well, so keep it for + * consistency. Cleanup all of it separately. + */ + if (!c) { + clear_cpu_cap(&boot_cpu_data, feature); + set_bit(feature, (unsigned long *)cpu_caps_cleared); + } else { + clear_bit(feature, (unsigned long *)c->x86_capability); + } +} + +/* Take the capabilities and the BUG bits into account */ +#define MAX_FEATURE_BITS ((NCAPINTS + NBUGINTS) * sizeof(u32) * 8) + +static void do_clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature) +{ + DECLARE_BITMAP(disable, MAX_FEATURE_BITS); + const struct cpuid_dep *d; + bool changed; + + if (WARN_ON(feature >= MAX_FEATURE_BITS)) + return; + + clear_feature(c, feature); + + /* Collect all features to disable, handling dependencies */ + memset(disable, 0, sizeof(disable)); + __set_bit(feature, disable); + + /* Loop until we get a stable state. */ + do { + changed = false; + for (d = cpuid_deps; d->feature; d++) { + if (!test_bit(d->depends, disable)) + continue; + if (__test_and_set_bit(d->feature, disable)) + continue; + + changed = true; + clear_feature(c, d->feature); + } + } while (changed); +} + +void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int feature) +{ + do_clear_cpu_cap(c, feature); +} + +void setup_clear_cpu_cap(unsigned int feature) +{ + do_clear_cpu_cap(NULL, feature); +} diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 6f077445647a..6b4bb335641f 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> #include <linux/delay.h> #include <linux/pci.h> diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 4fa90006ac68..bea8d3e24f50 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -26,6 +26,12 @@ #include <asm/processor.h> #include <asm/hypervisor.h> +extern const struct hypervisor_x86 x86_hyper_vmware; +extern const struct hypervisor_x86 x86_hyper_ms_hyperv; +extern const struct hypervisor_x86 x86_hyper_xen_pv; +extern const struct hypervisor_x86 x86_hyper_xen_hvm; +extern const struct hypervisor_x86 x86_hyper_kvm; + static const __initconst struct hypervisor_x86 * const hypervisors[] = { #ifdef CONFIG_XEN_PV @@ -41,54 +47,52 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] = #endif }; -const struct hypervisor_x86 *x86_hyper; -EXPORT_SYMBOL(x86_hyper); +enum x86_hypervisor_type x86_hyper_type; +EXPORT_SYMBOL(x86_hyper_type); -static inline void __init +static inline const struct hypervisor_x86 * __init detect_hypervisor_vendor(void) { - const struct hypervisor_x86 *h, * const *p; + const struct hypervisor_x86 *h = NULL, * const *p; uint32_t pri, max_pri = 0; for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) { - h = *p; - pri = h->detect(); - if (pri != 0 && pri > max_pri) { + pri = (*p)->detect(); + if (pri > max_pri) { max_pri = pri; - x86_hyper = h; + h = *p; } } - if (max_pri) - pr_info("Hypervisor detected: %s\n", x86_hyper->name); + if (h) + pr_info("Hypervisor detected: %s\n", h->name); + + return h; } -void __init init_hypervisor_platform(void) +static void __init copy_array(const void *src, void *target, unsigned int size) { + unsigned int i, n = size / sizeof(void *); + const void * const *from = (const void * const *)src; + const void **to = (const void **)target; - detect_hypervisor_vendor(); - - if (!x86_hyper) - return; - - if (x86_hyper->init_platform) - x86_hyper->init_platform(); + for (i = 0; i < n; i++) + if (from[i]) + to[i] = from[i]; } -bool __init hypervisor_x2apic_available(void) +void __init init_hypervisor_platform(void) { - return x86_hyper && - x86_hyper->x2apic_available && - x86_hyper->x2apic_available(); -} + const struct hypervisor_x86 *h; -void hypervisor_pin_vcpu(int cpu) -{ - if (!x86_hyper) + h = detect_hypervisor_vendor(); + + if (!h) return; - if (x86_hyper->pin_vcpu) - x86_hyper->pin_vcpu(cpu); - else - WARN_ONCE(1, "vcpu pinning requested but not supported!\n"); + copy_array(&h->init, &x86_init.hyper, sizeof(h->init)); + copy_array(&h->runtime, &x86_platform.hyper, sizeof(h->runtime)); + + x86_hyper_type = h->type; + x86_init.hyper.init_platform(); } diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index dfa90a3a5145..b1af22073e28 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/string.h> @@ -186,21 +187,6 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86 == 6 && c->x86_model < 15) clear_cpu_cap(c, X86_FEATURE_PAT); -#ifdef CONFIG_KMEMCHECK - /* - * P4s have a "fast strings" feature which causes single- - * stepping REP instructions to only generate a #DB on - * cache-line boundaries. - * - * Ingo Molnar reported a Pentium D (model 6) and a Xeon - * (model 2) with the same problem. - */ - if (c->x86 == 15) - if (msr_clear_bit(MSR_IA32_MISC_ENABLE, - MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0) - pr_info("kmemcheck: Disabling fast string operations\n"); -#endif - /* * If fast string is not enabled in IA32_MISC_ENABLE for any reason, * clear the fast string and enhanced fast string CPU capabilities. diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 24f749324c0f..54d04d574148 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Routines to identify caches on Intel CPU. * @@ -831,7 +832,6 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, } else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { unsigned int apicid, nshared, first, last; - this_leaf = this_cpu_ci->info_list + index; nshared = base->eax.split.num_threads_sharing + 1; apicid = cpu_data(cpu).apicid; first = apicid - (apicid % nshared); diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index cd5fc61ba450..88dcf8479013 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -267,6 +267,7 @@ static void rdt_get_cdp_l3_config(int type) r->num_closid = r_l3->num_closid / 2; r->cache.cbm_len = r_l3->cache.cbm_len; r->default_ctrl = r_l3->default_ctrl; + r->cache.shareable_bits = r_l3->cache.shareable_bits; r->data_width = (r->cache.cbm_len + 3) / 4; r->alloc_capable = true; /* diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index ebaddaeef023..3397244984f5 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_INTEL_RDT_H #define _ASM_X86_INTEL_RDT_H @@ -126,12 +127,15 @@ struct rdtgroup { #define RFTYPE_BASE BIT(1) #define RF_CTRLSHIFT 4 #define RF_MONSHIFT 5 +#define RF_TOPSHIFT 6 #define RFTYPE_CTRL BIT(RF_CTRLSHIFT) #define RFTYPE_MON BIT(RF_MONSHIFT) +#define RFTYPE_TOP BIT(RF_TOPSHIFT) #define RFTYPE_RES_CACHE BIT(8) #define RFTYPE_RES_MB BIT(9) #define RF_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) #define RF_MON_INFO (RFTYPE_INFO | RFTYPE_MON) +#define RF_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP) #define RF_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) /* List of all resource groups */ @@ -408,6 +412,10 @@ union cpuid_0x10_x_edx { unsigned int full; }; +void rdt_last_cmd_clear(void); +void rdt_last_cmd_puts(const char *s); +void rdt_last_cmd_printf(const char *fmt, ...); + void rdt_ctrl_update(void *arg); struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn); void rdtgroup_kn_unlock(struct kernfs_node *kn); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index f6ea94f8954a..23e1d5c249c6 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -42,15 +42,22 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) /* * Only linear delay values is supported for current Intel SKUs. */ - if (!r->membw.delay_linear) + if (!r->membw.delay_linear) { + rdt_last_cmd_puts("No support for non-linear MB domains\n"); return false; + } ret = kstrtoul(buf, 10, &bw); - if (ret) + if (ret) { + rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf); return false; + } - if (bw < r->membw.min_bw || bw > r->default_ctrl) + if (bw < r->membw.min_bw || bw > r->default_ctrl) { + rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw, + r->membw.min_bw, r->default_ctrl); return false; + } *data = roundup(bw, (unsigned long)r->membw.bw_gran); return true; @@ -60,8 +67,10 @@ int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d) { unsigned long data; - if (d->have_new_ctrl) + if (d->have_new_ctrl) { + rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; + } if (!bw_validate(buf, &data, r)) return -EINVAL; @@ -84,20 +93,29 @@ static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r) int ret; ret = kstrtoul(buf, 16, &val); - if (ret) + if (ret) { + rdt_last_cmd_printf("non-hex character in mask %s\n", buf); return false; + } - if (val == 0 || val > r->default_ctrl) + if (val == 0 || val > r->default_ctrl) { + rdt_last_cmd_puts("mask out of range\n"); return false; + } first_bit = find_first_bit(&val, cbm_len); zero_bit = find_next_zero_bit(&val, cbm_len, first_bit); - if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) + if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) { + rdt_last_cmd_printf("mask %lx has non-consecutive 1-bits\n", val); return false; + } - if ((zero_bit - first_bit) < r->cache.min_cbm_bits) + if ((zero_bit - first_bit) < r->cache.min_cbm_bits) { + rdt_last_cmd_printf("Need at least %d bits in mask\n", + r->cache.min_cbm_bits); return false; + } *data = val; return true; @@ -111,8 +129,10 @@ int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d) { unsigned long data; - if (d->have_new_ctrl) + if (d->have_new_ctrl) { + rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; + } if(!cbm_validate(buf, &data, r)) return -EINVAL; @@ -139,8 +159,10 @@ next: return 0; dom = strsep(&line, ";"); id = strsep(&dom, "="); - if (!dom || kstrtoul(id, 10, &dom_id)) + if (!dom || kstrtoul(id, 10, &dom_id)) { + rdt_last_cmd_puts("Missing '=' or non-numeric domain\n"); return -EINVAL; + } dom = strim(dom); list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { @@ -196,6 +218,7 @@ static int rdtgroup_parse_resource(char *resname, char *tok, int closid) if (!strcmp(resname, r->name) && closid < r->num_closid) return parse_line(tok, r); } + rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname); return -EINVAL; } @@ -218,6 +241,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, rdtgroup_kn_unlock(of->kn); return -ENOENT; } + rdt_last_cmd_clear(); closid = rdtgrp->closid; @@ -229,6 +253,12 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, while ((tok = strsep(&buf, "\n")) != NULL) { resname = strim(strsep(&tok, ":")); if (!tok) { + rdt_last_cmd_puts("Missing ':'\n"); + ret = -EINVAL; + goto out; + } + if (tok[0] == '\0') { + rdt_last_cmd_printf("Missing '%s' value\n", resname); ret = -EINVAL; goto out; } diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c index 30827510094b..681450eee428 100644 --- a/arch/x86/kernel/cpu/intel_rdt_monitor.c +++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c @@ -51,7 +51,7 @@ static LIST_HEAD(rmid_free_lru); * may have a occupancy value > intel_cqm_threshold. User can change * the threshold occupancy value. */ -unsigned int rmid_limbo_count; +static unsigned int rmid_limbo_count; /** * @rmid_entry - The entry in the limbo and free lists. diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index a869d4a073c5..64c5ff97ee0d 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -24,6 +24,7 @@ #include <linux/fs.h> #include <linux/sysfs.h> #include <linux/kernfs.h> +#include <linux/seq_buf.h> #include <linux/seq_file.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> @@ -51,6 +52,31 @@ static struct kernfs_node *kn_mongrp; /* Kernel fs node for "mon_data" directory under root */ static struct kernfs_node *kn_mondata; +static struct seq_buf last_cmd_status; +static char last_cmd_status_buf[512]; + +void rdt_last_cmd_clear(void) +{ + lockdep_assert_held(&rdtgroup_mutex); + seq_buf_clear(&last_cmd_status); +} + +void rdt_last_cmd_puts(const char *s) +{ + lockdep_assert_held(&rdtgroup_mutex); + seq_buf_puts(&last_cmd_status, s); +} + +void rdt_last_cmd_printf(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + lockdep_assert_held(&rdtgroup_mutex); + seq_buf_vprintf(&last_cmd_status, fmt, ap); + va_end(ap); +} + /* * Trivial allocator for CLOSIDs. Since h/w only supports a small number, * we can keep a bitmap of free CLOSIDs in a single integer. @@ -238,8 +264,10 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, /* Check whether cpus belong to parent ctrl group */ cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask); - if (cpumask_weight(tmpmask)) + if (cpumask_weight(tmpmask)) { + rdt_last_cmd_puts("can only add CPUs to mongroup that belong to parent\n"); return -EINVAL; + } /* Check whether cpus are dropped from this group */ cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); @@ -291,8 +319,10 @@ static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); if (cpumask_weight(tmpmask)) { /* Can't drop from default group */ - if (rdtgrp == &rdtgroup_default) + if (rdtgrp == &rdtgroup_default) { + rdt_last_cmd_puts("Can't drop CPUs from default group\n"); return -EINVAL; + } /* Give any dropped cpus to rdtgroup_default */ cpumask_or(&rdtgroup_default.cpu_mask, @@ -357,8 +387,10 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, } rdtgrp = rdtgroup_kn_lock_live(of->kn); + rdt_last_cmd_clear(); if (!rdtgrp) { ret = -ENOENT; + rdt_last_cmd_puts("directory was removed\n"); goto unlock; } @@ -367,13 +399,16 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, else ret = cpumask_parse(buf, newmask); - if (ret) + if (ret) { + rdt_last_cmd_puts("bad cpu list/mask\n"); goto unlock; + } /* check that user didn't specify any offline cpus */ cpumask_andnot(tmpmask, newmask, cpu_online_mask); if (cpumask_weight(tmpmask)) { ret = -EINVAL; + rdt_last_cmd_puts("can only assign online cpus\n"); goto unlock; } @@ -452,6 +487,7 @@ static int __rdtgroup_move_task(struct task_struct *tsk, */ atomic_dec(&rdtgrp->waitcount); kfree(callback); + rdt_last_cmd_puts("task exited\n"); } else { /* * For ctrl_mon groups move both closid and rmid. @@ -462,10 +498,12 @@ static int __rdtgroup_move_task(struct task_struct *tsk, tsk->closid = rdtgrp->closid; tsk->rmid = rdtgrp->mon.rmid; } else if (rdtgrp->type == RDTMON_GROUP) { - if (rdtgrp->mon.parent->closid == tsk->closid) + if (rdtgrp->mon.parent->closid == tsk->closid) { tsk->rmid = rdtgrp->mon.rmid; - else + } else { + rdt_last_cmd_puts("Can't move task to different control group\n"); ret = -EINVAL; + } } } return ret; @@ -484,8 +522,10 @@ static int rdtgroup_task_write_permission(struct task_struct *task, */ if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && - !uid_eq(cred->euid, tcred->suid)) + !uid_eq(cred->euid, tcred->suid)) { + rdt_last_cmd_printf("No permission to move task %d\n", task->pid); ret = -EPERM; + } put_cred(tcred); return ret; @@ -502,6 +542,7 @@ static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp, tsk = find_task_by_vpid(pid); if (!tsk) { rcu_read_unlock(); + rdt_last_cmd_printf("No task %d\n", pid); return -ESRCH; } } else { @@ -529,6 +570,7 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return -EINVAL; rdtgrp = rdtgroup_kn_lock_live(of->kn); + rdt_last_cmd_clear(); if (rdtgrp) ret = rdtgroup_move_task(pid, rdtgrp, of); @@ -569,6 +611,21 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of, return ret; } +static int rdt_last_cmd_status_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + int len; + + mutex_lock(&rdtgroup_mutex); + len = seq_buf_used(&last_cmd_status); + if (len) + seq_printf(seq, "%.*s", len, last_cmd_status_buf); + else + seq_puts(seq, "ok\n"); + mutex_unlock(&rdtgroup_mutex); + return 0; +} + static int rdt_num_closids_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -686,6 +743,13 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of, /* rdtgroup information files for one cache resource. */ static struct rftype res_common_files[] = { { + .name = "last_cmd_status", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_last_cmd_status_show, + .fflags = RF_TOP_INFO, + }, + { .name = "num_closids", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, @@ -855,6 +919,10 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) return PTR_ERR(kn_info); kernfs_get(kn_info); + ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); + if (ret) + goto out_destroy; + for_each_alloc_enabled_rdt_resource(r) { fflags = r->fflags | RF_CTRL_INFO; ret = rdtgroup_mkdir_info_resdir(r, r->name, fflags); @@ -1081,6 +1149,7 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, struct dentry *dentry; int ret; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /* * resctrl file system can only be mounted once. @@ -1130,12 +1199,12 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, goto out_mondata; if (rdt_alloc_capable) - static_branch_enable(&rdt_alloc_enable_key); + static_branch_enable_cpuslocked(&rdt_alloc_enable_key); if (rdt_mon_capable) - static_branch_enable(&rdt_mon_enable_key); + static_branch_enable_cpuslocked(&rdt_mon_enable_key); if (rdt_alloc_capable || rdt_mon_capable) - static_branch_enable(&rdt_enable_key); + static_branch_enable_cpuslocked(&rdt_enable_key); if (is_mbm_enabled()) { r = &rdt_resources_all[RDT_RESOURCE_L3]; @@ -1156,7 +1225,9 @@ out_info: out_cdp: cdp_disable(); out: + rdt_last_cmd_clear(); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return dentry; } @@ -1295,9 +1366,7 @@ static void rmdir_all_sub(void) kfree(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ - get_online_cpus(); update_closid_rmid(cpu_online_mask, &rdtgroup_default); - put_online_cpus(); kernfs_remove(kn_info); kernfs_remove(kn_mongrp); @@ -1308,6 +1377,7 @@ static void rdt_kill_sb(struct super_block *sb) { struct rdt_resource *r; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /*Put everything back to default values. */ @@ -1315,11 +1385,12 @@ static void rdt_kill_sb(struct super_block *sb) reset_all_ctrls(r); cdp_disable(); rmdir_all_sub(); - static_branch_disable(&rdt_alloc_enable_key); - static_branch_disable(&rdt_mon_enable_key); - static_branch_disable(&rdt_enable_key); + static_branch_disable_cpuslocked(&rdt_alloc_enable_key); + static_branch_disable_cpuslocked(&rdt_mon_enable_key); + static_branch_disable_cpuslocked(&rdt_enable_key); kernfs_kill_sb(sb); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); } static struct file_system_type rdt_fs_type = { @@ -1524,8 +1595,10 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, int ret; prdtgrp = rdtgroup_kn_lock_live(prgrp_kn); + rdt_last_cmd_clear(); if (!prdtgrp) { ret = -ENODEV; + rdt_last_cmd_puts("directory was removed\n"); goto out_unlock; } @@ -1533,6 +1606,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); if (!rdtgrp) { ret = -ENOSPC; + rdt_last_cmd_puts("kernel out of memory\n"); goto out_unlock; } *r = rdtgrp; @@ -1544,6 +1618,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp); if (IS_ERR(kn)) { ret = PTR_ERR(kn); + rdt_last_cmd_puts("kernfs create error\n"); goto out_free_rgrp; } rdtgrp->kn = kn; @@ -1557,24 +1632,31 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, kernfs_get(kn); ret = rdtgroup_kn_set_ugid(kn); - if (ret) + if (ret) { + rdt_last_cmd_puts("kernfs perm error\n"); goto out_destroy; + } - files = RFTYPE_BASE | RFTYPE_CTRL; files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype); ret = rdtgroup_add_files(kn, files); - if (ret) + if (ret) { + rdt_last_cmd_puts("kernfs fill error\n"); goto out_destroy; + } if (rdt_mon_capable) { ret = alloc_rmid(); - if (ret < 0) + if (ret < 0) { + rdt_last_cmd_puts("out of RMIDs\n"); goto out_destroy; + } rdtgrp->mon.rmid = ret; ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn); - if (ret) + if (ret) { + rdt_last_cmd_puts("kernfs subdir error\n"); goto out_idfree; + } } kernfs_activate(kn); @@ -1652,8 +1734,10 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, kn = rdtgrp->kn; ret = closid_alloc(); - if (ret < 0) + if (ret < 0) { + rdt_last_cmd_puts("out of CLOSIDs\n"); goto out_common_fail; + } closid = ret; rdtgrp->closid = closid; @@ -1665,8 +1749,10 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, * of tasks and cpus to monitor. */ ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); - if (ret) + if (ret) { + rdt_last_cmd_puts("kernfs subdir error\n"); goto out_id_free; + } } goto out_unlock; @@ -1902,6 +1988,9 @@ int __init rdtgroup_init(void) { int ret = 0; + seq_buf_init(&last_cmd_status, last_cmd_status_buf, + sizeof(last_cmd_status_buf)); + ret = rdtgroup_setup_root(); if (ret) return ret; diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index e42117d5f4d7..3fed38812eea 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <asm/cpu_device_id.h> #include <asm/cpufeature.h> #include <linux/cpu.h> diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile index 43051f0777d4..bcc7c54c7041 100644 --- a/arch/x86/kernel/cpu/mcheck/Makefile +++ b/arch/x86/kernel/cpu/mcheck/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-y = mce.o mce-severity.o mce-genpool.o obj-$(CONFIG_X86_ANCIENT_MCE) += winchip.o p5.o diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c index 10cec43aac38..7f85b76f43bc 100644 --- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c @@ -24,14 +24,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); static char mce_helper[128]; static char *mce_helper_argv[2] = { mce_helper, NULL }; -#define mce_log_get_idx_check(p) \ -({ \ - RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ - !lockdep_is_held(&mce_chrdev_read_mutex), \ - "suspicious mce_log_get_idx_check() usage"); \ - smp_load_acquire(&(p)); \ -}) - /* * Lockless MCE logging infrastructure. * This avoids deadlocks on printk locks without having to break locks. Also @@ -53,43 +45,32 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val, void *data) { struct mce *mce = (struct mce *)data; - unsigned int next, entry; - - wmb(); - for (;;) { - entry = mce_log_get_idx_check(mcelog.next); - for (;;) { - - /* - * When the buffer fills up discard new entries. - * Assume that the earlier errors are the more - * interesting ones: - */ - if (entry >= MCE_LOG_LEN) { - set_bit(MCE_OVERFLOW, - (unsigned long *)&mcelog.flags); - return NOTIFY_OK; - } - /* Old left over entry. Skip: */ - if (mcelog.entry[entry].finished) { - entry++; - continue; - } - break; - } - smp_rmb(); - next = entry + 1; - if (cmpxchg(&mcelog.next, entry, next) == entry) - break; + unsigned int entry; + + mutex_lock(&mce_chrdev_read_mutex); + + entry = mcelog.next; + + /* + * When the buffer fills up discard new entries. Assume that the + * earlier errors are the more interesting ones: + */ + if (entry >= MCE_LOG_LEN) { + set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog.flags); + goto unlock; } + + mcelog.next = entry + 1; + memcpy(mcelog.entry + entry, mce, sizeof(struct mce)); - wmb(); mcelog.entry[entry].finished = 1; - wmb(); /* wake processes polling /dev/mcelog */ wake_up_interruptible(&mce_chrdev_wait); +unlock: + mutex_unlock(&mce_chrdev_read_mutex); + return NOTIFY_OK; } @@ -177,13 +158,6 @@ static int mce_chrdev_release(struct inode *inode, struct file *file) return 0; } -static void collect_tscs(void *data) -{ - unsigned long *cpu_tsc = (unsigned long *)data; - - cpu_tsc[smp_processor_id()] = rdtsc(); -} - static int mce_apei_read_done; /* Collect MCE record of previous boot in persistent storage via APEI ERST. */ @@ -231,14 +205,9 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, size_t usize, loff_t *off) { char __user *buf = ubuf; - unsigned long *cpu_tsc; - unsigned prev, next; + unsigned next; int i, err; - cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL); - if (!cpu_tsc) - return -ENOMEM; - mutex_lock(&mce_chrdev_read_mutex); if (!mce_apei_read_done) { @@ -247,65 +216,29 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, goto out; } - next = mce_log_get_idx_check(mcelog.next); - /* Only supports full reads right now */ err = -EINVAL; if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) goto out; + next = mcelog.next; err = 0; - prev = 0; - do { - for (i = prev; i < next; i++) { - unsigned long start = jiffies; - struct mce *m = &mcelog.entry[i]; - - while (!m->finished) { - if (time_after_eq(jiffies, start + 2)) { - memset(m, 0, sizeof(*m)); - goto timeout; - } - cpu_relax(); - } - smp_rmb(); - err |= copy_to_user(buf, m, sizeof(*m)); - buf += sizeof(*m); -timeout: - ; - } - - memset(mcelog.entry + prev, 0, - (next - prev) * sizeof(struct mce)); - prev = next; - next = cmpxchg(&mcelog.next, prev, 0); - } while (next != prev); - - synchronize_sched(); - /* - * Collect entries that were still getting written before the - * synchronize. - */ - on_each_cpu(collect_tscs, cpu_tsc, 1); - - for (i = next; i < MCE_LOG_LEN; i++) { + for (i = 0; i < next; i++) { struct mce *m = &mcelog.entry[i]; - if (m->finished && m->tsc < cpu_tsc[m->cpu]) { - err |= copy_to_user(buf, m, sizeof(*m)); - smp_rmb(); - buf += sizeof(*m); - memset(m, 0, sizeof(*m)); - } + err |= copy_to_user(buf, m, sizeof(*m)); + buf += sizeof(*m); } + memset(mcelog.entry, 0, next * sizeof(struct mce)); + mcelog.next = 0; + if (err) err = -EFAULT; out: mutex_unlock(&mce_chrdev_read_mutex); - kfree(cpu_tsc); return err ? err : buf - ubuf; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 098530a93bb7..aa0d5df9dc60 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -1,3 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_MCE_INTERNAL_H__ +#define __X86_MCE_INTERNAL_H__ + #include <linux/device.h> #include <asm/mce.h> @@ -108,3 +112,7 @@ static inline void mce_work_trigger(void) { } static inline void mce_register_injector_chain(struct notifier_block *nb) { } static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } #endif + +extern struct mca_config mca_cfg; + +#endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 87cc9ab7a13c..4ca632a06e0b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -204,7 +204,7 @@ static int error_context(struct mce *m) return IN_KERNEL; } -static int mce_severity_amd_smca(struct mce *m, int err_ctx) +static int mce_severity_amd_smca(struct mce *m, enum context err_ctx) { u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank); u32 low, high; @@ -245,6 +245,9 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc if (m->status & MCI_STATUS_UC) { + if (ctx == IN_KERNEL) + return MCE_PANIC_SEVERITY; + /* * On older systems where overflow_recov flag is not present, we * should simply panic if an error overflow occurs. If @@ -255,10 +258,6 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc if (mce_flags.smca) return mce_severity_amd_smca(m, ctx); - /* software can try to contain */ - if (!(m->mcgstatus & MCG_STATUS_RIPV) && (ctx == IN_KERNEL)) - return MCE_PANIC_SEVERITY; - /* kill current process */ return MCE_AR_SEVERITY; } else { diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 3b413065c613..b1d616d08eee 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1367,13 +1367,12 @@ static void __start_timer(struct timer_list *t, unsigned long interval) local_irq_restore(flags); } -static void mce_timer_fn(unsigned long data) +static void mce_timer_fn(struct timer_list *t) { - struct timer_list *t = this_cpu_ptr(&mce_timer); - int cpu = smp_processor_id(); + struct timer_list *cpu_t = this_cpu_ptr(&mce_timer); unsigned long iv; - WARN_ON(cpu != data); + WARN_ON(cpu_t != t); iv = __this_cpu_read(mce_next_interval); @@ -1763,17 +1762,15 @@ static void mce_start_timer(struct timer_list *t) static void __mcheck_cpu_setup_timer(void) { struct timer_list *t = this_cpu_ptr(&mce_timer); - unsigned int cpu = smp_processor_id(); - setup_pinned_timer(t, mce_timer_fn, cpu); + timer_setup(t, mce_timer_fn, TIMER_PINNED); } static void __mcheck_cpu_init_timer(void) { struct timer_list *t = this_cpu_ptr(&mce_timer); - unsigned int cpu = smp_processor_id(); - setup_pinned_timer(t, mce_timer_fn, cpu); + timer_setup(t, mce_timer_fn, TIMER_PINNED); mce_start_timer(t); } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 40e28ed77fbf..486f640b02ef 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -28,6 +28,8 @@ #include <asm/msr.h> #include <asm/trace/irq_vectors.h> +#include "mce-internal.h" + #define NR_BLOCKS 5 #define THRESHOLD_MAX 0xFFF #define INT_TYPE_APIC 0x00020000 diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index e84db79ef272..d05be307d081 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel specific MCE features. * Copyright 2004 Zwane Mwaikambo <zwane@linuxpower.ca> diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 2a0717bf8033..5cddf831720f 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * P5 specific Machine Check Exception Reporting * (C) Copyright 2002 Alan Cox <alan@lxorguk.ukuu.org.uk> diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c index 5e7249e42f8f..2b584b319eff 100644 --- a/arch/x86/kernel/cpu/mcheck/threshold.c +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Common corrected MCE threshold handler code: */ diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index c6a722e1d011..3b45b270a865 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * IDT Winchip specific Machine Check Exception Reporting * (C) Copyright 2002 Alan Cox <alan@lxorguk.ukuu.org.uk> diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 86e8f0b2537b..c4fa4a85d4cb 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -122,9 +122,6 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (!have_cpuid_p()) - return *res; - /* * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not * completely accurate as xen pv guests don't see that CPUID bit set but @@ -166,24 +163,36 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name) void __init load_ucode_bsp(void) { unsigned int cpuid_1_eax; + bool intel = true; - if (check_loader_disabled_bsp()) + if (!have_cpuid_p()) return; cpuid_1_eax = native_cpuid_eax(1); switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (x86_family(cpuid_1_eax) >= 6) - load_ucode_intel_bsp(); + if (x86_family(cpuid_1_eax) < 6) + return; break; + case X86_VENDOR_AMD: - if (x86_family(cpuid_1_eax) >= 0x10) - load_ucode_amd_bsp(cpuid_1_eax); + if (x86_family(cpuid_1_eax) < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(cpuid_1_eax); } static bool check_loader_disabled_ap(void) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 8f7a9bbad514..7dbcb7adf797 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -34,6 +34,7 @@ #include <linux/mm.h> #include <asm/microcode_intel.h> +#include <asm/intel-family.h> #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/setup.h> @@ -918,6 +919,18 @@ static int get_ucode_fw(void *to, const void *from, size_t n) return 0; } +static bool is_blacklisted(unsigned int cpu) +{ + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) { + pr_err_once("late loading on model 79 is disabled.\n"); + return true; + } + + return false; +} + static enum ucode_state request_microcode_fw(int cpu, struct device *device, bool refresh_fw) { @@ -926,6 +939,9 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, const struct firmware *firmware; enum ucode_state ret; + if (is_blacklisted(cpu)) + return UCODE_NFOUND; + sprintf(name, "intel-ucode/%02x-%02x-%02x", c->x86, c->x86_model, c->x86_mask); @@ -950,6 +966,9 @@ static int get_ucode_user(void *to, const void *from, size_t n) static enum ucode_state request_microcode_user(int cpu, const void __user *buf, size_t size) { + if (is_blacklisted(cpu)) + return UCODE_NFOUND; + return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user); } diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index 6988c74409a8..d0dfb892c72f 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -1,4 +1,5 @@ #!/bin/sh +# SPDX-License-Identifier: GPL-2.0 # # Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeatures.h # diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 236324e83a3a..85eb5fc180c8 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -254,9 +254,9 @@ static void __init ms_hyperv_init_platform(void) #endif } -const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { +const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = { .name = "Microsoft Hyper-V", .detect = ms_hyperv_platform, - .init_platform = ms_hyperv_init_platform, + .type = X86_HYPER_MS_HYPERV, + .init.init_platform = ms_hyperv_init_platform, }; -EXPORT_SYMBOL(x86_hyper_ms_hyperv); diff --git a/arch/x86/kernel/cpu/mtrr/amd.c b/arch/x86/kernel/cpu/mtrr/amd.c index 92ba9cd31c9a..a65a0272096d 100644 --- a/arch/x86/kernel/cpu/mtrr/amd.c +++ b/arch/x86/kernel/cpu/mtrr/amd.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/mm.h> #include <asm/mtrr.h> diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c index 3d689937fc1b..f27177816569 100644 --- a/arch/x86/kernel/cpu/mtrr/centaur.c +++ b/arch/x86/kernel/cpu/mtrr/centaur.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/mm.h> diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index b1086f79e57e..4296c702a3f7 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/io.h> #include <linux/mm.h> diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 6d9b45549109..558444b23923 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/capability.h> #include <linux/seq_file.h> #include <linux/uaccess.h> diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index ad8bd763efa5..2ac99e561181 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * local MTRR defines. */ diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 181eabecae25..d389083330c5 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * local apic based NMI watchdog for various CPUs. * diff --git a/arch/x86/kernel/cpu/powerflags.c b/arch/x86/kernel/cpu/powerflags.c index 1dd8294fd730..fd6ec2aa0303 100644 --- a/arch/x86/kernel/cpu/powerflags.c +++ b/arch/x86/kernel/cpu/powerflags.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Strings for the various x86 power flags * diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 218f79825b3c..e7ecedafa1c8 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -1,7 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/smp.h> #include <linux/timex.h> #include <linux/string.h> #include <linux/seq_file.h> +#include <linux/cpufreq.h> + +#include "cpu.h" /* * Get CPU information for use by the procfs. @@ -75,9 +79,16 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (c->microcode) seq_printf(m, "microcode\t: 0x%x\n", c->microcode); - if (cpu_has(c, X86_FEATURE_TSC)) + if (cpu_has(c, X86_FEATURE_TSC)) { + unsigned int freq = aperfmperf_get_khz(cpu); + + if (!freq) + freq = cpufreq_quick_get(cpu); + if (!freq) + freq = cpu_khz; seq_printf(m, "cpu MHz\t\t: %u.%03u\n", - cpu_khz / 1000, (cpu_khz % 1000)); + freq / 1000, (freq % 1000)); + } /* Cache size */ if (c->x86_cache_size >= 0) diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index cd531355e838..b099024d339c 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Check for extended topology enumeration cpuid leaf 0xb and if it * exists, use it for populating initial_apicid and cpu topology diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index d77d07ab310b..42c939827621 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/clock.h> diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c index ef9c2a0078bd..65a58a390fc3 100644 --- a/arch/x86/kernel/cpu/umc.c +++ b/arch/x86/kernel/cpu/umc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <asm/processor.h> #include "cpu.h" diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 40ed26852ebd..8e005329648b 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -205,10 +205,10 @@ static bool __init vmware_legacy_x2apic_available(void) (eax & (1 << VMWARE_PORT_CMD_LEGACY_X2APIC)) != 0; } -const __refconst struct hypervisor_x86 x86_hyper_vmware = { +const __initconst struct hypervisor_x86 x86_hyper_vmware = { .name = "VMware", .detect = vmware_platform, - .init_platform = vmware_platform_setup, - .x2apic_available = vmware_legacy_x2apic_available, + .type = X86_HYPER_VMWARE, + .init.init_platform = vmware_platform_setup, + .init.x2apic_available = vmware_legacy_x2apic_available, }; -EXPORT_SYMBOL(x86_hyper_vmware); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 44404e2307bb..10e74d4778a1 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -209,7 +209,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs) } #ifdef CONFIG_KEXEC_FILE -static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg) +static int get_nr_ram_ranges_callback(struct resource *res, void *arg) { unsigned int *nr_ranges = arg; @@ -342,7 +342,7 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced, return ret; } -static int prepare_elf64_ram_headers_callback(u64 start, u64 end, void *arg) +static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) { struct crash_elf_data *ced = arg; Elf64_Ehdr *ehdr; @@ -355,7 +355,7 @@ static int prepare_elf64_ram_headers_callback(u64 start, u64 end, void *arg) ehdr = ced->ehdr; /* Exclude unwanted mem ranges */ - ret = elf_header_exclude_ranges(ced, start, end); + ret = elf_header_exclude_ranges(ced, res->start, res->end); if (ret) return ret; @@ -518,14 +518,14 @@ static int add_e820_entry(struct boot_params *params, struct e820_entry *entry) return 0; } -static int memmap_entry_callback(u64 start, u64 end, void *arg) +static int memmap_entry_callback(struct resource *res, void *arg) { struct crash_memmap_data *cmd = arg; struct boot_params *params = cmd->params; struct e820_entry ei; - ei.addr = start; - ei.size = end - start + 1; + ei.addr = res->start; + ei.size = resource_size(res); ei.type = cmd->type; add_e820_entry(params, &ei); @@ -619,12 +619,12 @@ out: return ret; } -static int determine_backup_region(u64 start, u64 end, void *arg) +static int determine_backup_region(struct resource *res, void *arg) { struct kimage *image = arg; - image->arch.backup_src_start = start; - image->arch.backup_src_sz = end - start + 1; + image->arch.backup_src_start = res->start; + image->arch.backup_src_sz = resource_size(res); /* Expecting only one range for backup region */ return 1; diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c index 538fedea9b3f..33ee47670b99 100644 --- a/arch/x86/kernel/crash_dump_32.c +++ b/arch/x86/kernel/crash_dump_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Memory preserving reboot related code. * diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index afa64adb75ee..4f2e0778feac 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Memory preserving reboot related code. * diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index cbf1f6ba39a8..76e07698e6d1 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Architecture specific OF callbacks. */ diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c index f9c324e08d85..0e662c55ae90 100644 --- a/arch/x86/kernel/doublefault.c +++ b/arch/x86/kernel/doublefault.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/debug.h> diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 4f0481474903..daefae83a3aa 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 225af4184f06..88ce2ffdb110 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 927abeaf63e2..1e82f787c160 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Various workarounds for chipset bugs. This code runs very early and can't use the regular PCI subsystem The entries are keyed to PCI bridges which usually identify chipsets diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 0f0840304452..5e801c8c8ce7 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/console.h> #include <linux/kernel.h> #include <linux/init.h> diff --git a/arch/x86/kernel/ebda.c b/arch/x86/kernel/ebda.c index 4312f8ae71b7..38e7d597b660 100644 --- a/arch/x86/kernel/ebda.c +++ b/arch/x86/kernel/ebda.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/init.h> #include <linux/memblock.h> diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 9c4e7ba6870c..e5ec3cafa72e 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -57,7 +57,7 @@ # error "Need more virtual address space for the ESPFIX hack" #endif -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO) /* This contains the *bottom* address of the espfix stack */ DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); @@ -155,14 +155,14 @@ void init_espfix_ap(int cpu) page = cpu/ESPFIX_STACKS_PER_PAGE; /* Did another CPU already set this up? */ - stack_page = ACCESS_ONCE(espfix_pages[page]); + stack_page = READ_ONCE(espfix_pages[page]); if (likely(stack_page)) goto done; mutex_lock(&espfix_init_mutex); /* Did we race on the lock? */ - stack_page = ACCESS_ONCE(espfix_pages[page]); + stack_page = READ_ONCE(espfix_pages[page]); if (stack_page) goto unlock_done; @@ -200,7 +200,7 @@ void init_espfix_ap(int cpu) set_pte(&pte_p[n*PTE_STRIDE], pte); /* Job is done for this CPU and any CPU which shares this page */ - ACCESS_ONCE(espfix_pages[page]) = stack_page; + WRITE_ONCE(espfix_pages[page], stack_page); unlock_done: mutex_unlock(&espfix_init_mutex); diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index d913047f832c..2954fab15e51 100644 --- a/arch/x86/kernel/fpu/bugs.c +++ b/arch/x86/kernel/fpu/bugs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * x86 FPU bug checks: */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e1114f070c2d..f92a6593de1e 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -100,7 +100,7 @@ void __kernel_fpu_begin(void) kernel_fpu_disable(); - if (fpu->fpregs_active) { + if (fpu->initialized) { /* * Ignore return value -- we don't care if reg state * is clobbered. @@ -116,7 +116,7 @@ void __kernel_fpu_end(void) { struct fpu *fpu = ¤t->thread.fpu; - if (fpu->fpregs_active) + if (fpu->initialized) copy_kernel_to_fpregs(&fpu->state); kernel_fpu_enable(); @@ -148,7 +148,7 @@ void fpu__save(struct fpu *fpu) preempt_disable(); trace_x86_fpu_before_save(fpu); - if (fpu->fpregs_active) { + if (fpu->initialized) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } @@ -189,10 +189,9 @@ EXPORT_SYMBOL_GPL(fpstate_init); int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) { - dst_fpu->fpregs_active = 0; dst_fpu->last_cpu = -1; - if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU)) + if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); @@ -206,26 +205,14 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) /* * Save current FPU registers directly into the child * FPU context, without any memory-to-memory copying. - * In lazy mode, if the FPU context isn't loaded into - * fpregs, CR0.TS will be set and do_device_not_available - * will load the FPU context. * - * We have to do all this with preemption disabled, - * mostly because of the FNSAVE case, because in that - * case we must not allow preemption in the window - * between the FNSAVE and us marking the context lazy. - * - * It shouldn't be an issue as even FNSAVE is plenty - * fast in terms of critical section length. + * ( The function 'fails' in the FNSAVE case, which destroys + * register contents so we have to copy them back. ) */ - preempt_disable(); if (!copy_fpregs_to_fpstate(dst_fpu)) { - memcpy(&src_fpu->state, &dst_fpu->state, - fpu_kernel_xstate_size); - + memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size); copy_kernel_to_fpregs(&src_fpu->state); } - preempt_enable(); trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); @@ -237,45 +224,48 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) * Activate the current task's in-memory FPU context, * if it has not been used before: */ -void fpu__activate_curr(struct fpu *fpu) +void fpu__initialize(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for the current task: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } -EXPORT_SYMBOL_GPL(fpu__activate_curr); +EXPORT_SYMBOL_GPL(fpu__initialize); /* * This function must be called before we read a task's fpstate. * - * If the task has not used the FPU before then initialize its - * fpstate. + * There's two cases where this gets called: + * + * - for the current task (when coredumping), in which case we have + * to save the latest FPU registers into the fpstate, + * + * - or it's called for stopped tasks (ptrace), in which case the + * registers were already saved by the context-switch code when + * the task scheduled out - we only have to initialize the registers + * if they've never been initialized. * * If the task has used the FPU before then save it. */ -void fpu__activate_fpstate_read(struct fpu *fpu) +void fpu__prepare_read(struct fpu *fpu) { - /* - * If fpregs are active (in the current CPU), then - * copy them to the fpstate: - */ - if (fpu->fpregs_active) { + if (fpu == ¤t->thread.fpu) { fpu__save(fpu); } else { - if (!fpu->fpstate_active) { + if (!fpu->initialized) { fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); trace_x86_fpu_activate_state(fpu); /* Safe to do for current and for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } } @@ -283,17 +273,17 @@ void fpu__activate_fpstate_read(struct fpu *fpu) /* * This function must be called before we write a task's fpstate. * - * If the task has used the FPU before then unlazy it. + * If the task has used the FPU before then invalidate any cached FPU registers. * If the task has not used the FPU before then initialize its fpstate. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we - * didn't clear its lazy status here then the lazy in-registers + * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ -void fpu__activate_fpstate_write(struct fpu *fpu) +void fpu__prepare_write(struct fpu *fpu) { /* * Only stopped child tasks can be used to modify the FPU @@ -301,8 +291,8 @@ void fpu__activate_fpstate_write(struct fpu *fpu) */ WARN_ON_FPU(fpu == ¤t->thread.fpu); - if (fpu->fpstate_active) { - /* Invalidate any lazy state: */ + if (fpu->initialized) { + /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } else { fpstate_init(&fpu->state); @@ -310,74 +300,11 @@ void fpu__activate_fpstate_write(struct fpu *fpu) trace_x86_fpu_activate_state(fpu); /* Safe to do for stopped child tasks: */ - fpu->fpstate_active = 1; + fpu->initialized = 1; } } /* - * This function must be called before we write the current - * task's fpstate. - * - * This call gets the current FPU register state and moves - * it in to the 'fpstate'. Preemption is disabled so that - * no writes to the 'fpstate' can occur from context - * swiches. - * - * Must be followed by a fpu__current_fpstate_write_end(). - */ -void fpu__current_fpstate_write_begin(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * Ensure that the context-switching code does not write - * over the fpstate while we are doing our update. - */ - preempt_disable(); - - /* - * Move the fpregs in to the fpu's 'fpstate'. - */ - fpu__activate_fpstate_read(fpu); - - /* - * The caller is about to write to 'fpu'. Ensure that no - * CPU thinks that its fpregs match the fpstate. This - * ensures we will not be lazy and skip a XRSTOR in the - * future. - */ - __fpu_invalidate_fpregs_state(fpu); -} - -/* - * This function must be paired with fpu__current_fpstate_write_begin() - * - * This will ensure that the modified fpstate gets placed back in - * the fpregs if necessary. - * - * Note: This function may be called whether or not an _actual_ - * write to the fpstate occurred. - */ -void fpu__current_fpstate_write_end(void) -{ - struct fpu *fpu = ¤t->thread.fpu; - - /* - * 'fpu' now has an updated copy of the state, but the - * registers may still be out of date. Update them with - * an XRSTOR if they are active. - */ - if (fpregs_active()) - copy_kernel_to_fpregs(&fpu->state); - - /* - * Our update is done and the fpregs/fpstate are in sync - * if necessary. Context switches can happen again. - */ - preempt_enable(); -} - -/* * 'fpu__restore()' is called to copy FPU registers from * the FPU fpstate to the live hw registers and to activate * access to the hardware registers, so that FPU instructions @@ -389,7 +316,7 @@ void fpu__current_fpstate_write_end(void) */ void fpu__restore(struct fpu *fpu) { - fpu__activate_curr(fpu); + fpu__initialize(fpu); /* Avoid __kernel_fpu_begin() right after fpregs_activate() */ kernel_fpu_disable(); @@ -414,15 +341,17 @@ void fpu__drop(struct fpu *fpu) { preempt_disable(); - if (fpu->fpregs_active) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - fpregs_deactivate(fpu); + if (fpu == ¤t->thread.fpu) { + if (fpu->initialized) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + fpregs_deactivate(fpu); + } } - fpu->fpstate_active = 0; + fpu->initialized = 0; trace_x86_fpu_dropped(fpu); @@ -462,9 +391,11 @@ void fpu__clear(struct fpu *fpu) * Make sure fpstate is cleared and initialized. */ if (static_cpu_has(X86_FEATURE_FPU)) { - fpu__activate_curr(fpu); + preempt_disable(); + fpu__initialize(fpu); user_fpu_begin(); copy_init_fpstate_to_fpregs(); + preempt_enable(); } } diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index d5d44c452624..6abd83572b01 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -240,7 +240,7 @@ static void __init fpu__init_system_ctx_switch(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; - WARN_ON_FPU(current->thread.fpu.fpstate_active); + WARN_ON_FPU(current->thread.fpu.initialized); } /* @@ -249,6 +249,10 @@ static void __init fpu__init_system_ctx_switch(void) */ static void __init fpu__init_parse_early_param(void) { + char arg[32]; + char *argptr = arg; + int bit; + if (cmdline_find_option_bool(boot_command_line, "no387")) setup_clear_cpu_cap(X86_FEATURE_FPU); @@ -266,6 +270,13 @@ static void __init fpu__init_parse_early_param(void) if (cmdline_find_option_bool(boot_command_line, "noxsaves")) setup_clear_cpu_cap(X86_FEATURE_XSAVES); + + if (cmdline_find_option(boot_command_line, "clearcpuid", arg, + sizeof(arg)) && + get_option(&argptr, &bit) && + bit >= 0 && + bit < NCAPINTS * 32) + setup_clear_cpu_cap(bit); } /* diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index b188b16841e3..bc02f5144b95 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * FPU register's regset abstraction, for ptrace, core dumps, etc. */ @@ -16,14 +17,14 @@ int regset_fpregs_active(struct task_struct *target, const struct user_regset *r { struct fpu *target_fpu = &target->thread.fpu; - return target_fpu->fpstate_active ? regset->n : 0; + return target_fpu->initialized ? regset->n : 0; } int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset) { struct fpu *target_fpu = &target->thread.fpu; - if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active) + if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized) return regset->n; else return 0; @@ -38,7 +39,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); fpstate_sanitize_xstate(fpu); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -55,7 +56,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (!boot_cpu_has(X86_FEATURE_FXSR)) return -ENODEV; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -89,10 +90,13 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (using_compacted_format()) { - ret = copyout_from_xsaves(pos, count, kbuf, ubuf, xsave); + if (kbuf) + ret = copy_xstate_to_kernel(kbuf, xsave, pos, count); + else + ret = copy_xstate_to_user(ubuf, xsave, pos, count); } else { fpstate_sanitize_xstate(fpu); /* @@ -129,28 +133,29 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, xsave = &fpu->state.xsave; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - ret = copyin_to_xsaves(kbuf, ubuf, xsave); - else + if (using_compacted_format()) { + if (kbuf) + ret = copy_kernel_to_xstate(xsave, kbuf); + else + ret = copy_user_to_xstate(xsave, ubuf); + } else { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - - /* - * In case of failure, mark all states as init: - */ - if (ret) - fpstate_init(&fpu->state); + if (!ret) + ret = validate_xstate_header(&xsave->header); + } /* * mxcsr reserved bits must be masked to zero for security reasons. */ xsave->i387.mxcsr &= mxcsr_feature_mask; - xsave->header.xfeatures &= xfeatures_mask; + /* - * These bits must be zero. + * In case of failure, mark all states as init: */ - memset(&xsave->header.reserved, 0, 48); + if (ret) + fpstate_init(&fpu->state); return ret; } @@ -299,7 +304,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; struct user_i387_ia32_struct env; - fpu__activate_fpstate_read(fpu); + fpu__prepare_read(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); @@ -329,7 +334,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, struct user_i387_ia32_struct env; int ret; - fpu__activate_fpstate_write(fpu); + fpu__prepare_write(fpu); fpstate_sanitize_xstate(fpu); if (!boot_cpu_has(X86_FEATURE_FPU)) @@ -369,7 +374,7 @@ int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu) struct fpu *fpu = &tsk->thread.fpu; int fpvalid; - fpvalid = fpu->fpstate_active; + fpvalid = fpu->initialized; if (fpvalid) fpvalid = !fpregs_get(tsk, NULL, 0, sizeof(struct user_i387_ia32_struct), diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 83c23c230b4c..23f1691670b6 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * FPU signal frame handling routines. */ @@ -155,7 +156,8 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) */ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) { - struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; + struct fpu *fpu = ¤t->thread.fpu; + struct xregs_state *xsave = &fpu->state.xsave; struct task_struct *tsk = current; int ia32_fxstate = (buf != buf_fx); @@ -170,13 +172,13 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) sizeof(struct user_i387_ia32_struct), NULL, (struct _fpstate_32 __user *) buf) ? -1 : 1; - if (fpregs_active() || using_compacted_format()) { + if (fpu->initialized || using_compacted_format()) { /* Save the live register state to the user directly. */ if (copy_fpregs_to_sigframe(buf_fx)) return -1; /* Update the thread's fxstate to save the fsave header. */ if (ia32_fxstate) - copy_fxregs_to_kernel(&tsk->thread.fpu); + copy_fxregs_to_kernel(fpu); } else { /* * It is a *bug* if kernel uses compacted-format for xsave @@ -189,7 +191,7 @@ int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) return -1; } - fpstate_sanitize_xstate(&tsk->thread.fpu); + fpstate_sanitize_xstate(fpu); if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size)) return -1; } @@ -213,8 +215,11 @@ sanitize_restored_xstate(struct task_struct *tsk, struct xstate_header *header = &xsave->header; if (use_xsave()) { - /* These bits must be zero. */ - memset(header->reserved, 0, 48); + /* + * Note: we don't need to zero the reserved bits in the + * xstate_header here because we either didn't copy them at all, + * or we checked earlier that they aren't set. + */ /* * Init the state that is not present in the memory @@ -223,7 +228,7 @@ sanitize_restored_xstate(struct task_struct *tsk, if (fx_only) header->xfeatures = XFEATURE_MASK_FPSSE; else - header->xfeatures &= (xfeatures_mask & xfeatures); + header->xfeatures &= xfeatures; } if (use_fxsr()) { @@ -279,7 +284,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) if (!access_ok(VERIFY_READ, buf, size)) return -EACCES; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (!static_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_set(current, NULL, @@ -307,28 +312,29 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) /* * For 32-bit frames with fxstate, copy the user state to the * thread's fpu state, reconstruct fxstate from the fsave - * header. Sanitize the copied state etc. + * header. Validate and sanitize the copied state. */ struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; /* - * Drop the current fpu which clears fpu->fpstate_active. This ensures + * Drop the current fpu which clears fpu->initialized. This ensures * that any context-switch during the copy of the new state, * avoids the intermediate state from getting restored/saved. * Thus avoiding the new restored state from getting corrupted. * We will be ready to restore/save the state only after - * fpu->fpstate_active is again set. + * fpu->initialized is again set. */ fpu__drop(fpu); if (using_compacted_format()) { - err = copyin_to_xsaves(NULL, buf_fx, - &fpu->state.xsave); + err = copy_user_to_xstate(&fpu->state.xsave, buf_fx); } else { - err = __copy_from_user(&fpu->state.xsave, - buf_fx, state_size); + err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); + + if (!err && state_size > offsetof(struct xregs_state, header)) + err = validate_xstate_header(&fpu->state.xsave.header); } if (err || __copy_from_user(&env, buf, sizeof(env))) { @@ -339,7 +345,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); } - fpu->fpstate_active = 1; + fpu->initialized = 1; preempt_disable(); fpu__restore(fpu); preempt_enable(); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index c24ac1efb12d..87a57b7642d3 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -15,6 +15,7 @@ #include <asm/fpu/xstate.h> #include <asm/tlbflush.h> +#include <asm/cpufeature.h> /* * Although we spell it out in here, the Processor Trace @@ -36,6 +37,19 @@ static const char *xfeature_names[] = "unknown xstate feature" , }; +static short xsave_cpuid_features[] __initdata = { + X86_FEATURE_FPU, + X86_FEATURE_XMM, + X86_FEATURE_AVX, + X86_FEATURE_MPX, + X86_FEATURE_MPX, + X86_FEATURE_AVX512F, + X86_FEATURE_AVX512F, + X86_FEATURE_AVX512F, + X86_FEATURE_INTEL_PT, + X86_FEATURE_PKU, +}; + /* * Mask of xstate features supported by the CPU and the kernel: */ @@ -59,26 +73,6 @@ unsigned int fpu_user_xstate_size; void fpu__xstate_clear_all_cpu_caps(void) { setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - setup_clear_cpu_cap(X86_FEATURE_XSAVEC); - setup_clear_cpu_cap(X86_FEATURE_XSAVES); - setup_clear_cpu_cap(X86_FEATURE_AVX); - setup_clear_cpu_cap(X86_FEATURE_AVX2); - setup_clear_cpu_cap(X86_FEATURE_AVX512F); - setup_clear_cpu_cap(X86_FEATURE_AVX512IFMA); - setup_clear_cpu_cap(X86_FEATURE_AVX512PF); - setup_clear_cpu_cap(X86_FEATURE_AVX512ER); - setup_clear_cpu_cap(X86_FEATURE_AVX512CD); - setup_clear_cpu_cap(X86_FEATURE_AVX512DQ); - setup_clear_cpu_cap(X86_FEATURE_AVX512BW); - setup_clear_cpu_cap(X86_FEATURE_AVX512VL); - setup_clear_cpu_cap(X86_FEATURE_MPX); - setup_clear_cpu_cap(X86_FEATURE_XGETBV1); - setup_clear_cpu_cap(X86_FEATURE_AVX512VBMI); - setup_clear_cpu_cap(X86_FEATURE_PKU); - setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW); - setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS); - setup_clear_cpu_cap(X86_FEATURE_AVX512_VPOPCNTDQ); } /* @@ -483,6 +477,30 @@ int using_compacted_format(void) return boot_cpu_has(X86_FEATURE_XSAVES); } +/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ +int validate_xstate_header(const struct xstate_header *hdr) +{ + /* No unknown or supervisor features may be set */ + if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR)) + return -EINVAL; + + /* Userspace must use the uncompacted format */ + if (hdr->xcomp_bv) + return -EINVAL; + + /* + * If 'reserved' is shrunken to add a new field, make sure to validate + * that new field here! + */ + BUILD_BUG_ON(sizeof(hdr->reserved) != 48); + + /* No reserved bits may be set */ + if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved))) + return -EINVAL; + + return 0; +} + static void __xstate_dump_leaves(void) { int i; @@ -702,6 +720,7 @@ void __init fpu__init_system_xstate(void) unsigned int eax, ebx, ecx, edx; static int on_boot_cpu __initdata = 1; int err; + int i; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -735,6 +754,14 @@ void __init fpu__init_system_xstate(void) goto out_disable; } + /* + * Clear XSAVE features that are disabled in the normal CPUID. + */ + for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) { + if (!boot_cpu_has(xsave_cpuid_features[i])) + xfeatures_mask &= ~BIT(i); + } + xfeatures_mask &= fpu__get_supported_xfeatures_mask(); /* Enable xstate instructions to be able to continue with initialization: */ @@ -867,7 +894,7 @@ const void *get_xsave_field_ptr(int xsave_state) { struct fpu *fpu = ¤t->thread.fpu; - if (!fpu->fpstate_active) + if (!fpu->initialized) return NULL; /* * fpu__save() takes the CPU's xstate registers @@ -921,38 +948,129 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, #endif /* ! CONFIG_ARCH_HAS_PKEYS */ /* + * Weird legacy quirk: SSE and YMM states store information in the + * MXCSR and MXCSR_FLAGS fields of the FP area. That means if the FP + * area is marked as unused in the xfeatures header, we need to copy + * MXCSR and MXCSR_FLAGS if either SSE or YMM are in use. + */ +static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) +{ + if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM))) + return false; + + if (xfeatures & XFEATURE_MASK_FP) + return false; + + return true; +} + +/* * This is similar to user_regset_copyout(), but will not add offset to * the source data pointer or increment pos, count, kbuf, and ubuf. */ -static inline int xstate_copyout(unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf, - const void *data, const int start_pos, - const int end_pos) +static inline void +__copy_xstate_to_kernel(void *kbuf, const void *data, + unsigned int offset, unsigned int size, unsigned int size_total) { - if ((count == 0) || (pos < start_pos)) - return 0; + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); - if (end_pos < 0 || pos < end_pos) { - unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos)); + memcpy(kbuf + offset, data, copy); + } +} - if (kbuf) { - memcpy(kbuf + pos, data, copy); - } else { - if (__copy_to_user(ubuf + pos, data, copy)) - return -EFAULT; +/* + * Convert from kernel XSAVES compacted format to standard format and copy + * to a kernel-space ptrace buffer. + * + * It supports partial copy but pos always starts from zero. This is called + * from xstateregs_get() and there we check the CPU has XSAVES. + */ +int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) +{ + unsigned int offset, size; + struct xstate_header header; + int i; + + /* + * Currently copy_regset_to_user() starts from pos 0: + */ + if (unlikely(offset_start != 0)) + return -EFAULT; + + /* + * The destination is a ptrace buffer; we put in only user xstates: + */ + memset(&header, 0, sizeof(header)); + header.xfeatures = xsave->header.xfeatures; + header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + + /* + * Copy xregs_state->header: + */ + offset = offsetof(struct xregs_state, header); + size = sizeof(header); + + __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); + + for (i = 0; i < XFEATURE_MAX; i++) { + /* + * Copy only in-use xstates: + */ + if ((header.xfeatures >> i) & 1) { + void *src = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + + __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); } + + } + + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total); + } + + /* + * Fill xsave->i387.sw_reserved value for ptrace frame: + */ + offset = offsetof(struct fxregs_state, sw_reserved); + size = sizeof(xstate_fx_sw_bytes); + + __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); + + return 0; +} + +static inline int +__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, unsigned int size_total) +{ + if (!size) + return 0; + + if (offset < size_total) { + unsigned int copy = min(size, size_total - offset); + + if (__copy_to_user(ubuf + offset, data, copy)) + return -EFAULT; } return 0; } /* * Convert from kernel XSAVES compacted format to standard format and copy - * to a ptrace buffer. It supports partial copy but pos always starts from + * to a user-space buffer. It supports partial copy but pos always starts from * zero. This is called from xstateregs_get() and there we check the CPU * has XSAVES. */ -int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, - void __user *ubuf, struct xregs_state *xsave) +int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { unsigned int offset, size; int ret, i; @@ -961,7 +1079,7 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, /* * Currently copy_regset_to_user() starts from pos 0: */ - if (unlikely(pos != 0)) + if (unlikely(offset_start != 0)) return -EFAULT; /* @@ -977,8 +1095,7 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, offset = offsetof(struct xregs_state, header); size = sizeof(header); - ret = xstate_copyout(offset, size, kbuf, ubuf, &header, 0, count); - + ret = __copy_xstate_to_user(ubuf, &header, offset, size, size_total); if (ret) return ret; @@ -992,25 +1109,30 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, offset = xstate_offsets[i]; size = xstate_sizes[i]; - ret = xstate_copyout(offset, size, kbuf, ubuf, src, 0, count); + /* The next component has to fit fully into the output buffer: */ + if (offset + size > size_total) + break; + ret = __copy_xstate_to_user(ubuf, src, offset, size, size_total); if (ret) return ret; - - if (offset + size >= count) - break; } } + if (xfeatures_mxcsr_quirk(header.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + __copy_xstate_to_user(ubuf, &xsave->i387.mxcsr, offset, size, size_total); + } + /* * Fill xsave->i387.sw_reserved value for ptrace frame: */ offset = offsetof(struct fxregs_state, sw_reserved); size = sizeof(xstate_fx_sw_bytes); - ret = xstate_copyout(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count); - + ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, size_total); if (ret) return ret; @@ -1018,55 +1140,98 @@ int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf, } /* - * Convert from a ptrace standard-format buffer to kernel XSAVES format - * and copy to the target thread. This is called from xstateregs_set() and - * there we check the CPU has XSAVES and a whole standard-sized buffer - * exists. + * Convert from a ptrace standard-format kernel buffer to kernel XSAVES format + * and copy to the target thread. This is called from xstateregs_set(). */ -int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, - struct xregs_state *xsave) +int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) { unsigned int offset, size; int i; - u64 xfeatures; - u64 allowed_features; + struct xstate_header hdr; offset = offsetof(struct xregs_state, header); - size = sizeof(xfeatures); + size = sizeof(hdr); - if (kbuf) { - memcpy(&xfeatures, kbuf + offset, size); - } else { - if (__copy_from_user(&xfeatures, ubuf + offset, size)) - return -EFAULT; + memcpy(&hdr, kbuf + offset, size); + + if (validate_xstate_header(&hdr)) + return -EINVAL; + + for (i = 0; i < XFEATURE_MAX; i++) { + u64 mask = ((u64)1 << i); + + if (hdr.xfeatures & mask) { + void *dst = __raw_xsave_addr(xsave, 1 << i); + + offset = xstate_offsets[i]; + size = xstate_sizes[i]; + + memcpy(dst, kbuf + offset, size); + } + } + + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + memcpy(&xsave->i387.mxcsr, kbuf + offset, size); } /* - * Reject if the user sets any disabled or supervisor features: + * The state that came in from userspace was user-state only. + * Mask all the user states out of 'xfeatures': + */ + xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR; + + /* + * Add back in the features that came in from userspace: */ - allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR; + xsave->header.xfeatures |= hdr.xfeatures; + + return 0; +} - if (xfeatures & ~allowed_features) +/* + * Convert from a ptrace or sigreturn standard-format user-space buffer to + * kernel XSAVES format and copy to the target thread. This is called from + * xstateregs_set(), as well as potentially from the sigreturn() and + * rt_sigreturn() system calls. + */ +int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) +{ + unsigned int offset, size; + int i; + struct xstate_header hdr; + + offset = offsetof(struct xregs_state, header); + size = sizeof(hdr); + + if (__copy_from_user(&hdr, ubuf + offset, size)) + return -EFAULT; + + if (validate_xstate_header(&hdr)) return -EINVAL; for (i = 0; i < XFEATURE_MAX; i++) { u64 mask = ((u64)1 << i); - if (xfeatures & mask) { + if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, 1 << i); offset = xstate_offsets[i]; size = xstate_sizes[i]; - if (kbuf) { - memcpy(dst, kbuf + offset, size); - } else { - if (__copy_from_user(dst, ubuf + offset, size)) - return -EFAULT; - } + if (__copy_from_user(dst, ubuf + offset, size)) + return -EFAULT; } } + if (xfeatures_mxcsr_quirk(hdr.xfeatures)) { + offset = offsetof(struct fxregs_state, mxcsr); + size = MXCSR_AND_FLAGS_SIZE; + if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size)) + return -EFAULT; + } + /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': @@ -1076,7 +1241,7 @@ int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, /* * Add back in the features that came in from userspace: */ - xsave->header.xfeatures |= xfeatures; + xsave->header.xfeatures |= hdr.xfeatures; return 0; } diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 9bef1bbeba63..01ebcb6f263e 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Dynamic function tracing support. * diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index 722a145b4139..b6c6468e10bc 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2017 Steven Rostedt, VMware Inc. */ diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 1dfac634bbf7..c832291d948a 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2014 Steven Rostedt, Red Hat Inc */ diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index cf2ce063f65a..ec6fefbfd3c0 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/arch/i386/kernel/head32.c -- prepare to run common code * @@ -30,10 +31,11 @@ static void __init i386_default_early_setup(void) asmlinkage __visible void __init i386_start_kernel(void) { - cr4_init_shadow(); - + /* Make sure IDT is set up before any exception happens */ idt_setup_early_handler(); + cr4_init_shadow(); + sanitize_boot_params(&boot_params); x86_early_init_platform_quirks(); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index bab4fa579450..6a5d757b9cfd 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * prepare to run common code * diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 9ed3074d0d27..c29020907886 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * * Copyright (C) 1991, 1992 Linus Torvalds @@ -211,9 +212,6 @@ ENTRY(startup_32_smp) #endif .Ldefault_entry: -#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ - X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ - X86_CR0_PG) movl $(CR0_STATE & ~X86_CR0_PG),%eax movl %eax,%cr0 @@ -401,7 +399,7 @@ ENTRY(early_idt_handler_array) # 24(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 + .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 pushl $0 # Dummy error code, to make stack frame uniform .endif pushl $i # 20(%esp) Vector number diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 513cbb012ecc..7dca675fe78d 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * linux/arch/x86/kernel/head_64.S -- start in 32bit and switch to 64bit * @@ -37,11 +38,12 @@ * */ -#define p4d_index(x) (((x) >> P4D_SHIFT) & (PTRS_PER_P4D-1)) #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) +#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH) PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) PGD_START_KERNEL = pgd_index(__START_KERNEL_map) +#endif L3_START_KERNEL = pud_index(__START_KERNEL_map) .text @@ -49,6 +51,7 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map) .code64 .globl startup_64 startup_64: + UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded an identity mapped page table @@ -88,6 +91,7 @@ startup_64: addq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f ENTRY(secondary_startup_64) + UNWIND_HINT_EMPTY /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded a mapped page table. @@ -132,6 +136,7 @@ ENTRY(secondary_startup_64) movq $1f, %rax jmp *%rax 1: + UNWIND_HINT_EMPTY /* Check if nx is implemented */ movl $0x80000001, %eax @@ -149,9 +154,6 @@ ENTRY(secondary_startup_64) 1: wrmsr /* Make changes effective */ /* Setup cr0 */ -#define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ - X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ - X86_CR0_PG) movl $CR0_STATE, %eax /* Make changes effective */ movq %rax, %cr0 @@ -234,7 +236,7 @@ ENTRY(secondary_startup_64) pushq %rax # target address in negative space lretq .Lafter_lret: -ENDPROC(secondary_startup_64) +END(secondary_startup_64) #include "verify_cpu.S" @@ -246,6 +248,7 @@ ENDPROC(secondary_startup_64) */ ENTRY(start_cpu0) movq initial_stack(%rip), %rsp + UNWIND_HINT_EMPTY jmp .Ljump_to_C_code ENDPROC(start_cpu0) #endif @@ -265,26 +268,24 @@ ENDPROC(start_cpu0) .quad init_thread_union + THREAD_SIZE - SIZEOF_PTREGS __FINITDATA -bad_address: - jmp bad_address - __INIT ENTRY(early_idt_handler_array) - # 104(%rsp) %rflags - # 96(%rsp) %cs - # 88(%rsp) %rip - # 80(%rsp) error code i = 0 .rept NUM_EXCEPTION_VECTORS - .ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1 - pushq $0 # Dummy error code, to make stack frame uniform + .if ((EXCEPTION_ERRCODE_MASK >> i) & 1) == 0 + UNWIND_HINT_IRET_REGS + pushq $0 # Dummy error code, to make stack frame uniform + .else + UNWIND_HINT_IRET_REGS offset=8 .endif pushq $i # 72(%rsp) Vector number jmp early_idt_handler_common + UNWIND_HINT_IRET_REGS i = i + 1 .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr -ENDPROC(early_idt_handler_array) + UNWIND_HINT_IRET_REGS offset=16 +END(early_idt_handler_array) early_idt_handler_common: /* @@ -312,6 +313,7 @@ early_idt_handler_common: pushq %r13 /* pt_regs->r13 */ pushq %r14 /* pt_regs->r14 */ pushq %r15 /* pt_regs->r15 */ + UNWIND_HINT_REGS cmpq $14,%rsi /* Page fault? */ jnz 10f @@ -326,8 +328,8 @@ early_idt_handler_common: 20: decl early_recursion_flag(%rip) - jmp restore_regs_and_iret -ENDPROC(early_idt_handler_common) + jmp restore_regs_and_return_to_kernel +END(early_idt_handler_common) __INITDATA @@ -361,10 +363,7 @@ NEXT_PAGE(early_dynamic_pgts) .data -#ifndef CONFIG_XEN -NEXT_PAGE(init_top_pgt) - .fill 512,8,0 -#else +#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH) NEXT_PAGE(init_top_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + PGD_PAGE_OFFSET*8, 0 @@ -381,6 +380,9 @@ NEXT_PAGE(level2_ident_pgt) * Don't set NX because code runs from these pages. */ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) +#else +NEXT_PAGE(init_top_pgt) + .fill 512,8,0 #endif #ifdef CONFIG_X86_5LEVEL @@ -434,7 +436,7 @@ ENTRY(phys_base) EXPORT_SYMBOL(phys_base) #include "../../x86/xen/xen-head.S" - + __PAGE_ALIGNED_BSS NEXT_PAGE(empty_zero_page) .skip PAGE_SIZE diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 6ebe00cb4a3b..0d307a657abb 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * 8253/PIT functions * diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 4e3b8a587c88..86c4439f9d74 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/linkage.h> #include <linux/errno.h> #include <linux/signal.h> @@ -113,6 +114,7 @@ static void make_8259A_irq(unsigned int irq) io_apic_irqs &= ~(1<<irq); irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq); enable_irq(irq); + lapic_assign_legacy_vector(irq, true); } /* diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 6107ee1cb8d5..d985cef3984f 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -92,8 +92,6 @@ static const __initdata struct idt_data def_idts[] = { INTG(X86_TRAP_DF, double_fault), #endif INTG(X86_TRAP_DB, debug), - INTG(X86_TRAP_NMI, nmi), - INTG(X86_TRAP_BP, int3), #ifdef CONFIG_X86_MCE INTG(X86_TRAP_MC, &machine_check), @@ -225,7 +223,7 @@ idt_setup_from_table(gate_desc *idt, const struct idt_data *t, int size, bool sy idt_init_desc(&desc, t); write_idt_entry(idt, t->vector, &desc); if (sys) - set_bit(t->vector, used_vectors); + set_bit(t->vector, system_vectors); } } @@ -313,14 +311,14 @@ void __init idt_setup_apic_and_irq_gates(void) idt_setup_from_table(idt_table, apic_idts, ARRAY_SIZE(apic_idts), true); - for_each_clear_bit_from(i, used_vectors, FIRST_SYSTEM_VECTOR) { + for_each_clear_bit_from(i, system_vectors, FIRST_SYSTEM_VECTOR) { entry = irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR); set_intr_gate(i, entry); } - for_each_clear_bit_from(i, used_vectors, NR_VECTORS) { + for_each_clear_bit_from(i, system_vectors, NR_VECTORS) { #ifdef CONFIG_X86_LOCAL_APIC - set_bit(i, used_vectors); + set_bit(i, system_vectors); set_intr_gate(i, spurious_interrupt); #else entry = irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR); @@ -358,7 +356,7 @@ void idt_invalidate(void *addr) void __init update_intr_gate(unsigned int n, const void *addr) { - if (WARN_ON_ONCE(!test_bit(n, used_vectors))) + if (WARN_ON_ONCE(!test_bit(n, system_vectors))) return; set_intr_gate(n, addr); } @@ -366,6 +364,6 @@ void __init update_intr_gate(unsigned int n, const void *addr) void alloc_intr_gate(unsigned int n, const void *addr) { BUG_ON(n < FIRST_SYSTEM_VECTOR); - if (!test_and_set_bit(n, used_vectors)) + if (!test_and_set_bit(n, system_vectors)) set_intr_gate(n, addr); } diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c index 7ebcc4a74438..805b7a341aca 100644 --- a/arch/x86/kernel/io_delay.c +++ b/arch/x86/kernel/io_delay.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * I/O delay strategies for inb_p/outb_p * diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 9c3cf0944bce..3feb648781c4 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This contains the io-permission bitmap code - written by obz, with changes * by Linus. 32/64 bits code unification by Miguel Botón. diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 52089c043160..49cfd9fe7589 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -134,7 +134,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Machine check polls\n"); #endif #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) - if (test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) { + if (test_bit(HYPERVISOR_CALLBACK_VECTOR, system_vectors)) { seq_printf(p, "%*s: ", prec, "HYP"); for_each_online_cpu(j) seq_printf(p, "%10u ", @@ -333,105 +333,6 @@ __visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs) #ifdef CONFIG_HOTPLUG_CPU - -/* These two declarations are only used in check_irq_vectors_for_cpu_disable() - * below, which is protected by stop_machine(). Putting them on the stack - * results in a stack frame overflow. Dynamically allocating could result in a - * failure so declare these two cpumasks as global. - */ -static struct cpumask affinity_new, online_new; - -/* - * This cpu is going to be removed and its vectors migrated to the remaining - * online cpus. Check to see if there are enough vectors in the remaining cpus. - * This function is protected by stop_machine(). - */ -int check_irq_vectors_for_cpu_disable(void) -{ - unsigned int this_cpu, vector, this_count, count; - struct irq_desc *desc; - struct irq_data *data; - int cpu; - - this_cpu = smp_processor_id(); - cpumask_copy(&online_new, cpu_online_mask); - cpumask_clear_cpu(this_cpu, &online_new); - - this_count = 0; - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - desc = __this_cpu_read(vector_irq[vector]); - if (IS_ERR_OR_NULL(desc)) - continue; - /* - * Protect against concurrent action removal, affinity - * changes etc. - */ - raw_spin_lock(&desc->lock); - data = irq_desc_get_irq_data(desc); - cpumask_copy(&affinity_new, - irq_data_get_affinity_mask(data)); - cpumask_clear_cpu(this_cpu, &affinity_new); - - /* Do not count inactive or per-cpu irqs. */ - if (!irq_desc_has_action(desc) || irqd_is_per_cpu(data)) { - raw_spin_unlock(&desc->lock); - continue; - } - - raw_spin_unlock(&desc->lock); - /* - * A single irq may be mapped to multiple cpu's - * vector_irq[] (for example IOAPIC cluster mode). In - * this case we have two possibilities: - * - * 1) the resulting affinity mask is empty; that is - * this the down'd cpu is the last cpu in the irq's - * affinity mask, or - * - * 2) the resulting affinity mask is no longer a - * subset of the online cpus but the affinity mask is - * not zero; that is the down'd cpu is the last online - * cpu in a user set affinity mask. - */ - if (cpumask_empty(&affinity_new) || - !cpumask_subset(&affinity_new, &online_new)) - this_count++; - } - /* No need to check any further. */ - if (!this_count) - return 0; - - count = 0; - for_each_online_cpu(cpu) { - if (cpu == this_cpu) - continue; - /* - * We scan from FIRST_EXTERNAL_VECTOR to first system - * vector. If the vector is marked in the used vectors - * bitmap or an irq is assigned to it, we don't count - * it as available. - * - * As this is an inaccurate snapshot anyway, we can do - * this w/o holding vector_lock. - */ - for (vector = FIRST_EXTERNAL_VECTOR; - vector < FIRST_SYSTEM_VECTOR; vector++) { - if (!test_bit(vector, used_vectors) && - IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) { - if (++count == this_count) - return 0; - } - } - } - - if (count < this_count) { - pr_warn("CPU %d disable failed: CPU has %u vectors assigned and there are only %u available.\n", - this_cpu, this_count, count); - return -ERANGE; - } - return 0; -} - /* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ void fixup_irqs(void) { diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 1f38d9a4d9de..a83b3346a0e1 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar * @@ -64,7 +65,7 @@ static void call_on_stack(void *func, void *stack) static inline void *current_stack(void) { - return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); + return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); } static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) @@ -88,7 +89,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) /* Save the next esp at the bottom of the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -139,7 +140,7 @@ void do_softirq_own_stack(void) /* Push the previous esp onto the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer; call_on_stack(__do_softirq, isp); } diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 3be74fbdeff2..020efbf5786b 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar * diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 70dee056f92b..80bee7695a20 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * x86 specific code for irq_work * diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 1add9e08e83e..8da3e909e967 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/linkage.h> #include <linux/errno.h> #include <linux/signal.h> @@ -60,9 +61,6 @@ void __init init_ISA_irqs(void) struct irq_chip *chip = legacy_pic->chip; int i; -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC) - init_bsp_APIC(); -#endif legacy_pic->init(0); for (i = 0; i < nr_legacy_irqs(); i++) @@ -93,6 +91,7 @@ void __init native_init_IRQ(void) x86_init.irqs.pre_vector_init(); idt_setup_apic_and_irq_gates(); + lapic_assign_system_vectors(); if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) setup_irq(2, &irq2); diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index ab4f491da2a9..e56c95be2808 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * jump label x86 support * diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index db2182d63ed0..ae38dccf0c8f 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -1,8 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_KPROBES_COMMON_H #define __X86_KERNEL_KPROBES_COMMON_H /* Kprobes and Optprobes common header */ +#include <asm/asm.h> + +#ifdef CONFIG_FRAME_POINTER +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" \ + " mov %" _ASM_SP ", %" _ASM_BP "\n" +#else +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" +#endif + #ifdef CONFIG_X86_64 #define SAVE_REGS_STRING \ /* Skip cs, ip, orig_ax. */ \ @@ -17,7 +27,7 @@ " pushq %r10\n" \ " pushq %r11\n" \ " pushq %rbx\n" \ - " pushq %rbp\n" \ + SAVE_RBP_STRING \ " pushq %r12\n" \ " pushq %r13\n" \ " pushq %r14\n" \ @@ -48,7 +58,7 @@ " pushl %es\n" \ " pushl %ds\n" \ " pushl %eax\n" \ - " pushl %ebp\n" \ + SAVE_RBP_STRING \ " pushl %edi\n" \ " pushl %esi\n" \ " pushl %edx\n" \ @@ -75,11 +85,11 @@ extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, * Copy an instruction and adjust the displacement if the instruction * uses the %rip-relative addressing mode. */ -extern int __copy_instruction(u8 *dest, u8 *src, struct insn *insn); +extern int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn); /* Generate a relative-jump/call instruction */ -extern void synthesize_reljump(void *from, void *to); -extern void synthesize_relcall(void *from, void *to); +extern void synthesize_reljump(void *dest, void *from, void *to); +extern void synthesize_relcall(void *dest, void *from, void *to); #ifdef CONFIG_OPTPROBES extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index f0153714ddac..bd36f3c33cd0 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -119,29 +119,29 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = { const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); static nokprobe_inline void -__synthesize_relative_insn(void *from, void *to, u8 op) +__synthesize_relative_insn(void *dest, void *from, void *to, u8 op) { struct __arch_relative_insn { u8 op; s32 raddr; } __packed *insn; - insn = (struct __arch_relative_insn *)from; + insn = (struct __arch_relative_insn *)dest; insn->raddr = (s32)((long)(to) - ((long)(from) + 5)); insn->op = op; } /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ -void synthesize_reljump(void *from, void *to) +void synthesize_reljump(void *dest, void *from, void *to) { - __synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE); + __synthesize_relative_insn(dest, from, to, RELATIVEJUMP_OPCODE); } NOKPROBE_SYMBOL(synthesize_reljump); /* Insert a call instruction at address 'from', which calls address 'to'.*/ -void synthesize_relcall(void *from, void *to) +void synthesize_relcall(void *dest, void *from, void *to) { - __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); + __synthesize_relative_insn(dest, from, to, RELATIVECALL_OPCODE); } NOKPROBE_SYMBOL(synthesize_relcall); @@ -346,10 +346,11 @@ static int is_IF_modifier(kprobe_opcode_t *insn) /* * Copy an instruction with recovering modified instruction by kprobes * and adjust the displacement if the instruction uses the %rip-relative - * addressing mode. + * addressing mode. Note that since @real will be the final place of copied + * instruction, displacement must be adjust by @real, not @dest. * This returns the length of copied instruction, or 0 if it has an error. */ -int __copy_instruction(u8 *dest, u8 *src, struct insn *insn) +int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) { kprobe_opcode_t buf[MAX_INSN_SIZE]; unsigned long recovered_insn = @@ -387,11 +388,11 @@ int __copy_instruction(u8 *dest, u8 *src, struct insn *insn) * have given. */ newdisp = (u8 *) src + (s64) insn->displacement.value - - (u8 *) dest; + - (u8 *) real; if ((s64) (s32) newdisp != newdisp) { pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp); pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", - src, dest, insn->displacement.value); + src, real, insn->displacement.value); return 0; } disp = (u8 *) dest + insn_offset_displacement(insn); @@ -402,20 +403,38 @@ int __copy_instruction(u8 *dest, u8 *src, struct insn *insn) } /* Prepare reljump right after instruction to boost */ -static void prepare_boost(struct kprobe *p, struct insn *insn) +static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p, + struct insn *insn) { + int len = insn->length; + if (can_boost(insn, p->addr) && - MAX_INSN_SIZE - insn->length >= RELATIVEJUMP_SIZE) { + MAX_INSN_SIZE - len >= RELATIVEJUMP_SIZE) { /* * These instructions can be executed directly if it * jumps back to correct address. */ - synthesize_reljump(p->ainsn.insn + insn->length, + synthesize_reljump(buf + len, p->ainsn.insn + len, p->addr + insn->length); + len += RELATIVEJUMP_SIZE; p->ainsn.boostable = true; } else { p->ainsn.boostable = false; } + + return len; +} + +/* Make page to RO mode when allocate it */ +void *alloc_insn_page(void) +{ + void *page; + + page = module_alloc(PAGE_SIZE); + if (page) + set_memory_ro((unsigned long)page & PAGE_MASK, 1); + + return page; } /* Recover page to RW mode before releasing it */ @@ -429,12 +448,11 @@ void free_insn_page(void *page) static int arch_copy_kprobe(struct kprobe *p) { struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; int len; - set_memory_rw((unsigned long)p->ainsn.insn & PAGE_MASK, 1); - /* Copy an instruction with recovering if other optprobe modifies it.*/ - len = __copy_instruction(p->ainsn.insn, p->addr, &insn); + len = __copy_instruction(buf, p->addr, p->ainsn.insn, &insn); if (!len) return -EINVAL; @@ -442,15 +460,16 @@ static int arch_copy_kprobe(struct kprobe *p) * __copy_instruction can modify the displacement of the instruction, * but it doesn't affect boostable check. */ - prepare_boost(p, &insn); - - set_memory_ro((unsigned long)p->ainsn.insn & PAGE_MASK, 1); + len = prepare_boost(buf, p, &insn); /* Check whether the instruction modifies Interrupt Flag or not */ - p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn); + p->ainsn.if_modifier = is_IF_modifier(buf); /* Also, displacement change doesn't affect the first byte */ - p->opcode = p->ainsn.insn[0]; + p->opcode = buf[0]; + + /* OK, write back the instruction(s) into ROX insn buffer */ + text_poke(p->ainsn.insn, buf, len); return 0; } @@ -1080,8 +1099,6 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) * raw stack chunk with redzones: */ __memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr)); - regs->flags &= ~X86_EFLAGS_IF; - trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); /* diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 041f7b6dfa0f..8dc0161cec8f 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -26,7 +26,7 @@ #include "common.h" static nokprobe_inline -int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, +void __skip_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, unsigned long orig_ip) { /* @@ -41,33 +41,31 @@ int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, __this_cpu_write(current_kprobe, NULL); if (orig_ip) regs->ip = orig_ip; - return 1; } int skip_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { - if (kprobe_ftrace(p)) - return __skip_singlestep(p, regs, kcb, 0); - else - return 0; + if (kprobe_ftrace(p)) { + __skip_singlestep(p, regs, kcb, 0); + preempt_enable_no_resched(); + return 1; + } + return 0; } NOKPROBE_SYMBOL(skip_singlestep); -/* Ftrace callback handler for kprobes */ +/* Ftrace callback handler for kprobes -- called under preepmt disabed */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *regs) { struct kprobe *p; struct kprobe_ctlblk *kcb; - unsigned long flags; - - /* Disable irq for emulating a breakpoint and avoiding preempt */ - local_irq_save(flags); + /* Preempt is disabled by ftrace */ p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) - goto end; + return; kcb = get_kprobe_ctlblk(); if (kprobe_running()) { @@ -77,17 +75,19 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ regs->ip = ip + sizeof(kprobe_opcode_t); + /* To emulate trap based kprobes, preempt_disable here */ + preempt_disable(); __this_cpu_write(current_kprobe, p); kcb->kprobe_status = KPROBE_HIT_ACTIVE; - if (!p->pre_handler || !p->pre_handler(p, regs)) + if (!p->pre_handler || !p->pre_handler(p, regs)) { __skip_singlestep(p, regs, kcb, orig_ip); + preempt_enable_no_resched(); + } /* * If pre_handler returns !0, it sets regs->ip and - * resets current kprobe. + * resets current kprobe, and keep preempt count +1. */ } -end: - local_irq_restore(flags); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 4f98aad38237..e941136e24d8 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -142,11 +142,11 @@ void optprobe_template_func(void); STACK_FRAME_NON_STANDARD(optprobe_template_func); #define TMPL_MOVE_IDX \ - ((long)&optprobe_template_val - (long)&optprobe_template_entry) + ((long)optprobe_template_val - (long)optprobe_template_entry) #define TMPL_CALL_IDX \ - ((long)&optprobe_template_call - (long)&optprobe_template_entry) + ((long)optprobe_template_call - (long)optprobe_template_entry) #define TMPL_END_IDX \ - ((long)&optprobe_template_end - (long)&optprobe_template_entry) + ((long)optprobe_template_end - (long)optprobe_template_entry) #define INT3_SIZE sizeof(kprobe_opcode_t) @@ -154,17 +154,15 @@ STACK_FRAME_NON_STANDARD(optprobe_template_func); static void optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) { - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long flags; - /* This is possible if op is under delayed unoptimizing */ if (kprobe_disabled(&op->kp)) return; - local_irq_save(flags); + preempt_disable(); if (kprobe_running()) { kprobes_inc_nmissed_count(&op->kp); } else { + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); /* Save skipped registers */ #ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; @@ -180,17 +178,17 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) opt_pre_handler(&op->kp, regs); __this_cpu_write(current_kprobe, NULL); } - local_irq_restore(flags); + preempt_enable_no_resched(); } NOKPROBE_SYMBOL(optimized_callback); -static int copy_optimized_instructions(u8 *dest, u8 *src) +static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) { struct insn insn; int len = 0, ret; while (len < RELATIVEJUMP_SIZE) { - ret = __copy_instruction(dest + len, src + len, &insn); + ret = __copy_instruction(dest + len, src + len, real, &insn); if (!ret || !can_boost(&insn, src + len)) return -EINVAL; len += ret; @@ -343,57 +341,66 @@ void arch_remove_optimized_kprobe(struct optimized_kprobe *op) int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *__unused) { - u8 *buf; - int ret; + u8 *buf = NULL, *slot; + int ret, len; long rel; if (!can_optimize((unsigned long)op->kp.addr)) return -EILSEQ; - op->optinsn.insn = get_optinsn_slot(); - if (!op->optinsn.insn) + buf = kzalloc(MAX_OPTINSN_SIZE, GFP_KERNEL); + if (!buf) return -ENOMEM; + op->optinsn.insn = slot = get_optinsn_slot(); + if (!slot) { + ret = -ENOMEM; + goto out; + } + /* * Verify if the address gap is in 2GB range, because this uses * a relative jump. */ - rel = (long)op->optinsn.insn - (long)op->kp.addr + RELATIVEJUMP_SIZE; + rel = (long)slot - (long)op->kp.addr + RELATIVEJUMP_SIZE; if (abs(rel) > 0x7fffffff) { - __arch_remove_optimized_kprobe(op, 0); - return -ERANGE; + ret = -ERANGE; + goto err; } - buf = (u8 *)op->optinsn.insn; - set_memory_rw((unsigned long)buf & PAGE_MASK, 1); + /* Copy arch-dep-instance from template */ + memcpy(buf, optprobe_template_entry, TMPL_END_IDX); /* Copy instructions into the out-of-line buffer */ - ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr); - if (ret < 0) { - __arch_remove_optimized_kprobe(op, 0); - return ret; - } + ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr, + slot + TMPL_END_IDX); + if (ret < 0) + goto err; op->optinsn.size = ret; - - /* Copy arch-dep-instance from template */ - memcpy(buf, &optprobe_template_entry, TMPL_END_IDX); + len = TMPL_END_IDX + op->optinsn.size; /* Set probe information */ synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); /* Set probe function call */ - synthesize_relcall(buf + TMPL_CALL_IDX, optimized_callback); + synthesize_relcall(buf + TMPL_CALL_IDX, + slot + TMPL_CALL_IDX, optimized_callback); /* Set returning jmp instruction at the tail of out-of-line buffer */ - synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size, + synthesize_reljump(buf + len, slot + len, (u8 *)op->kp.addr + op->optinsn.size); - - set_memory_ro((unsigned long)buf & PAGE_MASK, 1); - - flush_icache_range((unsigned long) buf, - (unsigned long) buf + TMPL_END_IDX + - op->optinsn.size + RELATIVEJUMP_SIZE); - return 0; + len += RELATIVEJUMP_SIZE; + + /* We have to use text_poke for instuction buffer because it is RO */ + text_poke(slot, buf, len); + ret = 0; +out: + kfree(buf); + return ret; + +err: + __arch_remove_optimized_kprobe(op, 0); + goto out; } /* diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index 4b0592ca9e47..8c1cc08f514f 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -299,7 +299,7 @@ static int __init create_setup_data_nodes(struct kobject *parent) return 0; out_clean_nodes: - for (j = i - 1; j > 0; j--) + for (j = i - 1; j >= 0; j--) cleanup_setup_data_node(*(kobjp + j)); kfree(kobjp); out_setup_data_kobj: diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index aa60a08b65b1..b40ffbf156c1 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -75,8 +75,8 @@ static int parse_no_kvmclock_vsyscall(char *arg) early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); -static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); -static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64); +static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); +static DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64); static int has_steal_clock = 0; /* @@ -117,7 +117,11 @@ static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b, return NULL; } -void kvm_async_pf_task_wait(u32 token) +/* + * @interrupt_kernel: Is this called from a routine which interrupts the kernel + * (other than user space)? + */ +void kvm_async_pf_task_wait(u32 token, int interrupt_kernel) { u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; @@ -140,7 +144,10 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); - n.halted = is_idle_task(current) || preempt_count() > 1; + n.halted = is_idle_task(current) || + (IS_ENABLED(CONFIG_PREEMPT_COUNT) + ? preempt_count() > 1 || rcu_preempt_depth() + : interrupt_kernel); init_swait_queue_head(&n.wq); hlist_add_head(&n.link, &b->list); raw_spin_unlock(&b->lock); @@ -268,7 +275,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ prev_state = exception_enter(); - kvm_async_pf_task_wait((u32)read_cr2()); + kvm_async_pf_task_wait((u32)read_cr2(), !user_mode(regs)); exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: @@ -305,7 +312,7 @@ static void kvm_register_steal_time(void) cpu, (unsigned long long) slow_virt_to_phys(st)); } -static DEFINE_PER_CPU(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED; +static DEFINE_PER_CPU_DECRYPTED(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED; static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val) { @@ -419,9 +426,42 @@ void kvm_disable_steal_time(void) wrmsr(MSR_KVM_STEAL_TIME, 0, 0); } +static inline void __set_percpu_decrypted(void *ptr, unsigned long size) +{ + early_set_memory_decrypted((unsigned long) ptr, size); +} + +/* + * Iterate through all possible CPUs and map the memory region pointed + * by apf_reason, steal_time and kvm_apic_eoi as decrypted at once. + * + * Note: we iterate through all possible CPUs to ensure that CPUs + * hotplugged will have their per-cpu variable already mapped as + * decrypted. + */ +static void __init sev_map_percpu_data(void) +{ + int cpu; + + if (!sev_active()) + return; + + for_each_possible_cpu(cpu) { + __set_percpu_decrypted(&per_cpu(apf_reason, cpu), sizeof(apf_reason)); + __set_percpu_decrypted(&per_cpu(steal_time, cpu), sizeof(steal_time)); + __set_percpu_decrypted(&per_cpu(kvm_apic_eoi, cpu), sizeof(kvm_apic_eoi)); + } +} + #ifdef CONFIG_SMP static void __init kvm_smp_prepare_boot_cpu(void) { + /* + * Map the per-cpu variables as decrypted before kvm_guest_cpu_init() + * shares the guest physical address with the hypervisor. + */ + sev_map_percpu_data(); + kvm_guest_cpu_init(); native_smp_prepare_boot_cpu(); kvm_spinlock_init(); @@ -458,7 +498,7 @@ static void __init kvm_apf_trap_init(void) update_intr_gate(X86_TRAP_PF, async_page_fault); } -void __init kvm_guest_init(void) +static void __init kvm_guest_init(void) { int i; @@ -489,6 +529,7 @@ void __init kvm_guest_init(void) kvm_cpu_online, kvm_cpu_down_prepare) < 0) pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n"); #else + sev_map_percpu_data(); kvm_guest_cpu_init(); #endif @@ -537,12 +578,13 @@ static uint32_t __init kvm_detect(void) return kvm_cpuid_base(); } -const struct hypervisor_x86 x86_hyper_kvm __refconst = { +const __initconst struct hypervisor_x86 x86_hyper_kvm = { .name = "KVM", .detect = kvm_detect, - .x2apic_available = kvm_para_available, + .type = X86_HYPER_KVM, + .init.guest_late_init = kvm_guest_init, + .init.x2apic_available = kvm_para_available, }; -EXPORT_SYMBOL_GPL(x86_hyper_kvm); static __init int activate_jump_labels(void) { diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d88967659098..8b26c9e01cc4 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -27,6 +27,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/mem_encrypt.h> #include <asm/x86_init.h> #include <asm/reboot.h> #include <asm/kvmclock.h> @@ -45,13 +46,7 @@ early_param("no-kvmclock", parse_no_kvmclock); /* The hypervisor will put information about time periodically here */ static struct pvclock_vsyscall_time_info *hv_clock; -static struct pvclock_wall_clock wall_clock; - -struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) -{ - return hv_clock; -} -EXPORT_SYMBOL_GPL(pvclock_pvti_cpu0_va); +static struct pvclock_wall_clock *wall_clock; /* * The wallclock is the time of day when we booted. Since then, some time may @@ -64,22 +59,22 @@ static void kvm_get_wallclock(struct timespec *now) int low, high; int cpu; - low = (int)__pa_symbol(&wall_clock); - high = ((u64)__pa_symbol(&wall_clock) >> 32); + low = (int)slow_virt_to_phys(wall_clock); + high = ((u64)slow_virt_to_phys(wall_clock) >> 32); native_write_msr(msr_kvm_wall_clock, low, high); cpu = get_cpu(); vcpu_time = &hv_clock[cpu].pvti; - pvclock_read_wallclock(&wall_clock, vcpu_time, now); + pvclock_read_wallclock(wall_clock, vcpu_time, now); put_cpu(); } static int kvm_set_wallclock(const struct timespec *now) { - return -1; + return -ENODEV; } static u64 kvm_clock_read(void) @@ -249,11 +244,39 @@ static void kvm_shutdown(void) native_machine_shutdown(); } +static phys_addr_t __init kvm_memblock_alloc(phys_addr_t size, + phys_addr_t align) +{ + phys_addr_t mem; + + mem = memblock_alloc(size, align); + if (!mem) + return 0; + + if (sev_active()) { + if (early_set_memory_decrypted((unsigned long)__va(mem), size)) + goto e_free; + } + + return mem; +e_free: + memblock_free(mem, size); + return 0; +} + +static void __init kvm_memblock_free(phys_addr_t addr, phys_addr_t size) +{ + if (sev_active()) + early_set_memory_encrypted((unsigned long)__va(addr), size); + + memblock_free(addr, size); +} + void __init kvmclock_init(void) { struct pvclock_vcpu_time_info *vcpu_time; - unsigned long mem; - int size, cpu; + unsigned long mem, mem_wall_clock; + int size, cpu, wall_clock_size; u8 flags; size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); @@ -267,21 +290,35 @@ void __init kvmclock_init(void) } else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE))) return; - printk(KERN_INFO "kvm-clock: Using msrs %x and %x", - msr_kvm_system_time, msr_kvm_wall_clock); + wall_clock_size = PAGE_ALIGN(sizeof(struct pvclock_wall_clock)); + mem_wall_clock = kvm_memblock_alloc(wall_clock_size, PAGE_SIZE); + if (!mem_wall_clock) + return; - mem = memblock_alloc(size, PAGE_SIZE); - if (!mem) + wall_clock = __va(mem_wall_clock); + memset(wall_clock, 0, wall_clock_size); + + mem = kvm_memblock_alloc(size, PAGE_SIZE); + if (!mem) { + kvm_memblock_free(mem_wall_clock, wall_clock_size); + wall_clock = NULL; return; + } + hv_clock = __va(mem); memset(hv_clock, 0, size); if (kvm_register_clock("primary cpu clock")) { hv_clock = NULL; - memblock_free(mem, size); + kvm_memblock_free(mem, size); + kvm_memblock_free(mem_wall_clock, wall_clock_size); + wall_clock = NULL; return; } + printk(KERN_INFO "kvm-clock: Using msrs %x and %x", + msr_kvm_system_time, msr_kvm_wall_clock); + if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); @@ -334,6 +371,7 @@ int __init kvm_setup_vsyscall_timeinfo(void) return 1; } + pvclock_set_pvti_cpu0_va(hv_clock); put_cpu(); kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index f0e64db18ac8..1c1eae961340 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com> @@ -12,6 +13,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/smp.h> +#include <linux/syscalls.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> @@ -101,7 +103,7 @@ static void finalize_ldt_struct(struct ldt_struct *ldt) static void install_ldt(struct mm_struct *current_mm, struct ldt_struct *ldt) { - /* Synchronizes with lockless_dereference in load_mm_ldt. */ + /* Synchronizes with READ_ONCE in load_mm_ldt. */ smp_store_release(¤t_mm->context.ldt, ldt); /* Activate the LDT for all CPUs using current_mm. */ @@ -294,8 +296,8 @@ out: return error; } -asmlinkage int sys_modify_ldt(int func, void __user *ptr, - unsigned long bytecount) +SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , + unsigned long , bytecount) { int ret = -ENOSYS; @@ -313,5 +315,14 @@ asmlinkage int sys_modify_ldt(int func, void __user *ptr, ret = write_ldt(ptr, bytecount, 0); break; } - return ret; + /* + * The SYSCALL_DEFINE() macros give us an 'unsigned long' + * return type, but tht ABI for sys_modify_ldt() expects + * 'int'. This cast gives us an int-sized value in %rax + * for the return code. The 'unsigned' is necessary so + * the compiler does not try to sign-extend the negative + * return codes into the high half of the register when + * taking the value from int->long. + */ + return (unsigned int)ret; } diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index f4c886d9165c..b5cb49e57df8 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * AMD Family 10h mmconfig enablement */ diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 62e7d70aadd5..da0c160e5589 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -172,19 +172,27 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_X86_64_NONE: break; case R_X86_64_64: + if (*(u64 *)loc != 0) + goto invalid_relocation; *(u64 *)loc = val; break; case R_X86_64_32: + if (*(u32 *)loc != 0) + goto invalid_relocation; *(u32 *)loc = val; if (val != *(u32 *)loc) goto overflow; break; case R_X86_64_32S: + if (*(s32 *)loc != 0) + goto invalid_relocation; *(s32 *)loc = val; if ((s64)val != *(s32 *)loc) goto overflow; break; case R_X86_64_PC32: + if (*(u32 *)loc != 0) + goto invalid_relocation; val -= (u64)loc; *(u32 *)loc = val; #if 0 @@ -200,6 +208,11 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, } return 0; +invalid_relocation: + pr_err("x86/modules: Skipping invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n", + (int)ELF64_R_TYPE(rel[i].r_info), loc, val); + return -ENOEXEC; + overflow: pr_err("overflow in relocation type %d val %Lx\n", (int)ELF64_R_TYPE(rel[i].r_info), val); diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 5cbb3177ed17..3a4b12809ab5 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel Multiprocessor Specification 1.1 and 1.4 * compliant MP-table parsing routines. @@ -430,6 +431,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) } static unsigned long mpf_base; +static bool mpf_found; static unsigned long __init get_mpc_size(unsigned long physptr) { @@ -503,7 +505,7 @@ void __init default_get_smp_config(unsigned int early) if (!smp_found_config) return; - if (!mpf_base) + if (!mpf_found) return; if (acpi_lapic && early) @@ -592,6 +594,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) smp_found_config = 1; #endif mpf_base = base; + mpf_found = true; pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n", base, base + sizeof(*mpf) - 1, mpf); @@ -857,7 +860,7 @@ static int __init update_mp_table(void) if (!enable_update_mptable) return 0; - if (!mpf_base) + if (!mpf_found) return 0; mpf = early_memremap(mpf_base, sizeof(*mpf)); diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 35aafc95e4b8..18bc9b51ac9b 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -105,7 +105,7 @@ static void nmi_max_handler(struct irq_work *w) { struct nmiaction *a = container_of(w, struct nmiaction, irq_work); int remainder_ns, decimal_msecs; - u64 whole_msecs = ACCESS_ONCE(a->max_duration); + u64 whole_msecs = READ_ONCE(a->max_duration); remainder_ns = do_div(whole_msecs, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c index d27f8d84c4ff..a1a96df3dff1 100644 --- a/arch/x86/kernel/nmi_selftest.c +++ b/arch/x86/kernel/nmi_selftest.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * arch/x86/kernel/nmi-selftest.c * diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 8f2d1c9d43a8..71f2d1125ec0 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Split spinlock implementation out into its own file, so it can be * compiled in a FTRACE-compatible way. diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 19a3e8f961c7..041096bdef86 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -115,8 +115,18 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target, return 5; } -/* Neat trick to map patch type back to the call within the - * corresponding structure. */ +DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); + +void __init native_pv_lock_init(void) +{ + if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) + static_branch_disable(&virt_spin_lock_key); +} + +/* + * Neat trick to map patch type back to the call within the + * corresponding structure. + */ static void *get_call_destination(u8 type) { struct paravirt_patch_template tmpl = { diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index 553acbbb4d32..758e69d72ebf 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <asm/paravirt.h> DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 11aaf1eaa0e4..ac0be8283325 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <asm/paravirt.h> #include <asm/asm-offsets.h> #include <linux/stringify.h> diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 5286a4a92cf7..35c461f21815 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -898,10 +898,9 @@ static void calioc2_dump_error_regs(struct iommu_table *tbl) PHB_ROOT_COMPLEX_STATUS); } -static void calgary_watchdog(unsigned long data) +static void calgary_watchdog(struct timer_list *t) { - struct pci_dev *dev = (struct pci_dev *)data; - struct iommu_table *tbl = pci_iommu(dev->bus); + struct iommu_table *tbl = from_timer(tbl, t, watchdog_timer); void __iomem *bbar = tbl->bbar; u32 val32; void __iomem *target; @@ -1016,8 +1015,7 @@ static void __init calgary_enable_translation(struct pci_dev *dev) writel(cpu_to_be32(val32), target); readl(target); /* flush */ - setup_timer(&tbl->watchdog_timer, &calgary_watchdog, - (unsigned long)dev); + timer_setup(&tbl->watchdog_timer, calgary_watchdog, 0); mod_timer(&tbl->watchdog_timer, jiffies); } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 0accc2404b92..599d7462eccc 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/dma-mapping.h> #include <linux/dma-debug.h> #include <linux/dmar.h> diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c index f712dfdf1357..4dfd90a75e63 100644 --- a/arch/x86/kernel/pci-iommu_table.c +++ b/arch/x86/kernel/pci-iommu_table.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/dma-mapping.h> #include <asm/iommu_table.h> #include <linux/string.h> diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 4fc3cb60ea11..b0caae27e1b7 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Fallback functions when the main IOMMU code is not compiled in. This code is roughly equivalent to i386. */ #include <linux/dma-mapping.h> diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 677077510e30..53bd05ea90d8 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Glue code to lib/swiotlb.c */ #include <linux/pci.h> diff --git a/arch/x86/kernel/pcspeaker.c b/arch/x86/kernel/pcspeaker.c index a311ffcaad16..da5190a1ea16 100644 --- a/arch/x86/kernel/pcspeaker.c +++ b/arch/x86/kernel/pcspeaker.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/platform_device.h> #include <linux/err.h> #include <linux/init.h> diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index 587d887f7f17..e47b2dbbdef3 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/errno.h> #include <linux/kernel.h> #include <linux/sched.h> diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c index 502a77d0adb0..39a59299bfa0 100644 --- a/arch/x86/kernel/platform-quirks.c +++ b/arch/x86/kernel/platform-quirks.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/init.h> diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 0c5315d322c8..6b07faaa1579 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2015, Christoph Hellwig. * Copyright (c) 2015, Intel Corporation. @@ -6,7 +7,7 @@ #include <linux/init.h> #include <linux/ioport.h> -static int found(u64 start, u64 end, void *data) +static int found(struct resource *res, void *data) { return 1; } diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index 963e3fb56437..ee0286390a4c 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/sched.h> #include <linux/mm.h> #include <linux/uaccess.h> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index bd6b85fac666..97fb3e5737f5 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/errno.h> @@ -48,7 +49,13 @@ */ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { .x86_tss = { - .sp0 = TOP_OF_INIT_STACK, + /* + * .sp0 is only used when entering ring 0 from a lower + * privilege level. Since the init task never runs anything + * but ring 0 code, there is no need for a valid value here. + * Poison it. + */ + .sp0 = (1UL << (BITS_PER_LONG-1)) + 1, #ifdef CONFIG_X86_32 .ss0 = __KERNEL_DS, .ss1 = __KERNEL_CS, diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 11966251cd42..45bf0c5f93e1 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -284,9 +284,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* * Reload esp0 and cpu_current_top_of_stack. This changes - * current_thread_info(). + * current_thread_info(). Refresh the SYSENTER configuration in + * case prev or next is vm86. */ - load_sp0(tss, next); + update_sp0(next_p); + refresh_sysenter_cs(next); this_cpu_write(cpu_current_top_of_stack, (unsigned long)task_stack_page(next_p) + THREAD_SIZE); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 302e7b2572d1..eeeb34f85c25 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -274,7 +274,6 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, struct inactive_task_frame *frame; struct task_struct *me = current; - p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE; childregs = task_pt_regs(p); fork_frame = container_of(childregs, struct fork_frame, regs); frame = &fork_frame->frame; @@ -464,8 +463,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ this_cpu_write(current_task, next_p); - /* Reload esp0 and ss1. This changes current_thread_info(). */ - load_sp0(tss, next); + /* Reload sp0. */ + update_sp0(next_p); /* * Now maybe reload the debug registers and handle I/O bitmaps diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 5c3f6d6a5078..761f6af6efa5 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -25,8 +25,10 @@ #include <asm/fixmap.h> #include <asm/pvclock.h> +#include <asm/vgtod.h> static u8 valid_flags __read_mostly = 0; +static struct pvclock_vsyscall_time_info *pvti_cpu0_va __read_mostly; void pvclock_set_flags(u8 flags) { @@ -144,3 +146,15 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } + +void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti) +{ + WARN_ON(vclock_was_used(VCLOCK_PVCLOCK)); + pvti_cpu0_va = pvti; +} + +struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void) +{ + return pvti_cpu0_va; +} +EXPORT_SYMBOL_GPL(pvclock_get_pvti_cpu0_va); diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index eaa591cfd98b..697a4ce04308 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This file contains work-arounds for x86 and x86_64 platform bugs. */ diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 54180fa6f66f..2126b9d27c34 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/export.h> @@ -105,6 +106,10 @@ void __noreturn machine_real_restart(unsigned int type) load_cr3(initial_page_table); #else write_cr3(real_mode_header->trampoline_pgd); + + /* Exiting long mode will fail if CR4.PCIDE is set. */ + if (static_cpu_has(X86_FEATURE_PCID)) + cr4_clear_bits(X86_CR4_PCIDE); #endif /* Jump to the identity-mapped low memory code */ diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c index c8e41e90f59c..b7c0f142d026 100644 --- a/arch/x86/kernel/reboot_fixups_32.c +++ b/arch/x86/kernel/reboot_fixups_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This is a good place to put board specific reboot fixups. * diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 5ab3895516ac..9b9fb7882c20 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/ioport.h> #include <asm/e820/api.h> diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 5b21cb7d84d6..69ac9cb9cac6 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * RTC related functions */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 0957dd73d127..8af2e8d0c0a1 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -136,18 +136,6 @@ RESERVE_BRK(dmi_alloc, 65536); static __initdata unsigned long _brk_start = (unsigned long)__brk_base; unsigned long _brk_end = (unsigned long)__brk_base; -#ifdef CONFIG_X86_64 -int default_cpu_present_to_apicid(int mps_cpu) -{ - return __default_cpu_present_to_apicid(mps_cpu); -} - -int default_check_phys_apicid_present(int phys_apicid) -{ - return __default_check_phys_apicid_present(phys_apicid); -} -#endif - struct boot_params boot_params; /* @@ -380,9 +368,11 @@ static void __init reserve_initrd(void) * If SME is active, this memory will be marked encrypted by the * kernel when it is accessed (including relocation). However, the * ramdisk image was loaded decrypted by the bootloader, so make - * sure that it is encrypted before accessing it. + * sure that it is encrypted before accessing it. For SEV the + * ramdisk will already be encrypted, so only do this for SME. */ - sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image); + if (sme_active()) + sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image); initrd_start = 0; @@ -822,26 +812,6 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } -static void __init simple_udelay_calibration(void) -{ - unsigned int tsc_khz, cpu_khz; - unsigned long lpj; - - if (!boot_cpu_has(X86_FEATURE_TSC)) - return; - - cpu_khz = x86_platform.calibrate_cpu(); - tsc_khz = x86_platform.calibrate_tsc(); - - tsc_khz = tsc_khz ? : cpu_khz; - if (!tsc_khz) - return; - - lpj = tsc_khz * 1000; - do_div(lpj, HZ); - loops_per_jiffy = lpj; -} - /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -1045,12 +1015,10 @@ void __init setup_arch(char **cmdline_p) /* * VMware detection requires dmi to be available, so this - * needs to be done after dmi_scan_machine, for the BP. + * needs to be done after dmi_scan_machine(), for the boot CPU. */ init_hypervisor_platform(); - simple_udelay_calibration(); - x86_init.resources.probe_roms(); /* after parse_early_param, so could debug it */ @@ -1135,9 +1103,6 @@ void __init setup_arch(char **cmdline_p) memblock_set_current_limit(ISA_END_ADDRESS); e820__memblock_setup(); - if (!early_xdbc_setup_hardware()) - early_xdbc_register_console(); - reserve_bios_regions(); if (efi_enabled(EFI_MEMMAP)) { @@ -1243,6 +1208,10 @@ void __init setup_arch(char **cmdline_p) kvmclock_init(); #endif + tsc_early_delay_calibrate(); + if (!early_xdbc_setup_hardware()) + early_xdbc_register_console(); + x86_init.paging.pagetable_init(); kasan_init(); @@ -1294,7 +1263,7 @@ void __init setup_arch(char **cmdline_p) io_apic_init_mappings(); - kvm_guest_init(); + x86_init.hyper.guest_late_init(); e820__reserve_resources(); e820__register_nosave_regions(max_low_pfn); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 28dafed6c682..497aa766fab3 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index e04442345fc0..b9e00e8f1c9b 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs @@ -263,7 +264,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, sp = (unsigned long) ka->sa.sa_restorer; } - if (fpu->fpstate_active) { + if (fpu->initialized) { sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32), &buf_fx, &math_size); *fpstate = (void __user *)sp; @@ -279,7 +280,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)-1L; /* save i387 and extended state */ - if (fpu->fpstate_active && + if (fpu->initialized && copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; @@ -755,7 +756,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Ensure the signal handler starts with the new fpu state. */ - if (fpu->fpstate_active) + if (fpu->initialized) fpu__clear(fpu); } signal_setup_done(failed, ksig, stepping); diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index ab9feb5887b1..8c6da1a643da 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/compat.h> #include <linux/uaccess.h> #include <linux/ptrace.h> diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0854ff169274..3d01df7d7cf6 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -77,6 +77,7 @@ #include <asm/i8259.h> #include <asm/realmode.h> #include <asm/misc.h> +#include <asm/qspinlock.h> /* Number of siblings per CPU package */ int smp_num_siblings = 1; @@ -100,9 +101,6 @@ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); /* Logical package management. We might want to allocate that dynamically */ -static int *physical_to_logical_pkg __read_mostly; -static unsigned long *physical_package_map __read_mostly;; -static unsigned int max_physical_pkg_id __read_mostly; unsigned int __max_logical_packages __read_mostly; EXPORT_SYMBOL(__max_logical_packages); static unsigned int logical_packages __read_mostly; @@ -194,6 +192,12 @@ static void smp_callin(void) smp_store_cpu_info(cpuid); /* + * The topology information must be up to date before + * calibrate_delay() and notify_cpu_starting(). + */ + set_cpu_sibling_map(raw_smp_processor_id()); + + /* * Get our bogomips. * Update loops_per_jiffy in cpu_data. Previous call to * smp_store_cpu_info() stored a value that is close but not as @@ -203,11 +207,6 @@ static void smp_callin(void) cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy; pr_debug("Stack at about %p\n", &cpuid); - /* - * This must be done before setting cpu_online_mask - * or calling notify_cpu_starting. - */ - set_cpu_sibling_map(raw_smp_processor_id()); wmb(); notify_cpu_starting(cpuid); @@ -232,12 +231,6 @@ static void notrace start_secondary(void *unused) */ if (boot_cpu_has(X86_FEATURE_PCID)) __write_cr4(__read_cr4() | X86_CR4_PCIDE); - cpu_init(); - x86_cpuinit.early_percpu_clock_init(); - preempt_disable(); - smp_callin(); - - enable_start_cpu0 = 0; #ifdef CONFIG_X86_32 /* switch away from the initial page table */ @@ -245,22 +238,29 @@ static void notrace start_secondary(void *unused) __flush_tlb_all(); #endif + cpu_init(); + x86_cpuinit.early_percpu_clock_init(); + preempt_disable(); + smp_callin(); + + enable_start_cpu0 = 0; + /* otherwise gcc will move up smp_processor_id before the cpu_init */ barrier(); /* - * Check TSC synchronization with the BP: + * Check TSC synchronization with the boot CPU: */ check_tsc_sync_target(); /* - * Lock vector_lock and initialize the vectors on this cpu - * before setting the cpu online. We must set it online with - * vector_lock held to prevent a concurrent setup/teardown - * from seeing a half valid vector space. + * Lock vector_lock, set CPU online and bring the vector + * allocator online. Online must be set with vector_lock held + * to prevent a concurrent irq setup/teardown from seeing a + * half valid vector space. */ lock_vector_lock(); - setup_vector_irq(smp_processor_id()); set_cpu_online(smp_processor_id(), true); + lapic_online(); unlock_vector_lock(); cpu_set_state_online(smp_processor_id()); x86_platform.nmi_init(); @@ -278,108 +278,48 @@ static void notrace start_secondary(void *unused) } /** + * topology_phys_to_logical_pkg - Map a physical package id to a logical + * + * Returns logical package id or -1 if not found + */ +int topology_phys_to_logical_pkg(unsigned int phys_pkg) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->initialized && c->phys_proc_id == phys_pkg) + return c->logical_proc_id; + } + return -1; +} +EXPORT_SYMBOL(topology_phys_to_logical_pkg); + +/** * topology_update_package_map - Update the physical to logical package map * @pkg: The physical package id as retrieved via CPUID * @cpu: The cpu for which this is updated */ int topology_update_package_map(unsigned int pkg, unsigned int cpu) { - unsigned int new; - - /* Called from early boot ? */ - if (!physical_package_map) - return 0; - - if (pkg >= max_physical_pkg_id) - return -EINVAL; + int new; - /* Set the logical package id */ - if (test_and_set_bit(pkg, physical_package_map)) + /* Already available somewhere? */ + new = topology_phys_to_logical_pkg(pkg); + if (new >= 0) goto found; - if (logical_packages >= __max_logical_packages) { - pr_warn("Package %u of CPU %u exceeds BIOS package data %u.\n", - logical_packages, cpu, __max_logical_packages); - return -ENOSPC; - } - new = logical_packages++; if (new != pkg) { pr_info("CPU %u Converting physical %u to logical package %u\n", cpu, pkg, new); } - physical_to_logical_pkg[pkg] = new; - found: - cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[pkg]; + cpu_data(cpu).logical_proc_id = new; return 0; } -/** - * topology_phys_to_logical_pkg - Map a physical package id to a logical - * - * Returns logical package id or -1 if not found - */ -int topology_phys_to_logical_pkg(unsigned int phys_pkg) -{ - if (phys_pkg >= max_physical_pkg_id) - return -1; - return physical_to_logical_pkg[phys_pkg]; -} -EXPORT_SYMBOL(topology_phys_to_logical_pkg); - -static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu) -{ - unsigned int ncpus; - size_t size; - - /* - * Today neither Intel nor AMD support heterogenous systems. That - * might change in the future.... - * - * While ideally we'd want '* smp_num_siblings' in the below @ncpus - * computation, this won't actually work since some Intel BIOSes - * report inconsistent HT data when they disable HT. - * - * In particular, they reduce the APIC-IDs to only include the cores, - * but leave the CPUID topology to say there are (2) siblings. - * This means we don't know how many threads there will be until - * after the APIC enumeration. - * - * By not including this we'll sometimes over-estimate the number of - * logical packages by the amount of !present siblings, but this is - * still better than MAX_LOCAL_APIC. - * - * We use total_cpus not nr_cpu_ids because nr_cpu_ids can be limited - * on the command line leading to a similar issue as the HT disable - * problem because the hyperthreads are usually enumerated after the - * primary cores. - */ - ncpus = boot_cpu_data.x86_max_cores; - if (!ncpus) { - pr_warn("x86_max_cores == zero !?!?"); - ncpus = 1; - } - - __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus); - logical_packages = 0; - - /* - * Possibly larger than what we need as the number of apic ids per - * package can be smaller than the actual used apic ids. - */ - max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus); - size = max_physical_pkg_id * sizeof(unsigned int); - physical_to_logical_pkg = kmalloc(size, GFP_KERNEL); - memset(physical_to_logical_pkg, 0xff, size); - size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long); - physical_package_map = kzalloc(size, GFP_KERNEL); - - pr_info("Max logical packages: %u\n", __max_logical_packages); - - topology_update_package_map(c->phys_proc_id, cpu); -} - void __init smp_store_boot_cpu_info(void) { int id = 0; /* CPU 0 */ @@ -387,7 +327,8 @@ void __init smp_store_boot_cpu_info(void) *c = boot_cpu_data; c->cpu_index = id; - smp_init_package_map(c, id); + topology_update_package_map(c->phys_proc_id, id); + c->initialized = true; } /* @@ -398,13 +339,16 @@ void smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = &cpu_data(id); - *c = boot_cpu_data; + /* Copy boot_cpu_data only on the first bringup */ + if (!c->initialized) + *c = boot_cpu_data; c->cpu_index = id; /* * During boot time, CPU0 has this setup already. Save the info when * bringing up AP or offlined CPU0. */ identify_secondary_cpu(c); + c->initialized = true; } static bool @@ -960,8 +904,7 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle) #ifdef CONFIG_X86_32 /* Stack for startup_32 can be just as for start_secondary onwards */ irq_ctx_init(cpu); - per_cpu(cpu_current_top_of_stack, cpu) = - (unsigned long)task_stack_page(idle) + THREAD_SIZE; + per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle); #else initial_gs = per_cpu_offset(cpu); #endif @@ -1093,7 +1036,7 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) unsigned long flags; int err, ret = 0; - WARN_ON(irqs_disabled()); + lockdep_assert_irqs_enabled(); pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu); @@ -1189,17 +1132,10 @@ static __init void disable_smp(void) cpumask_set_cpu(0, topology_core_cpumask(0)); } -enum { - SMP_OK, - SMP_NO_CONFIG, - SMP_NO_APIC, - SMP_FORCE_UP, -}; - /* * Various sanity checks. */ -static int __init smp_sanity_check(unsigned max_cpus) +static void __init smp_sanity_check(void) { preempt_disable(); @@ -1237,16 +1173,6 @@ static int __init smp_sanity_check(unsigned max_cpus) } /* - * If we couldn't find an SMP configuration at boot time, - * get out of here now! - */ - if (!smp_found_config && !acpi_lapic) { - preempt_enable(); - pr_notice("SMP motherboard not detected\n"); - return SMP_NO_CONFIG; - } - - /* * Should not be necessary because the MP table should list the boot * CPU too, but we do it for the sake of robustness anyway. */ @@ -1256,29 +1182,6 @@ static int __init smp_sanity_check(unsigned max_cpus) physid_set(hard_smp_processor_id(), phys_cpu_present_map); } preempt_enable(); - - /* - * If we couldn't find a local APIC, then get out of here now! - */ - if (APIC_INTEGRATED(boot_cpu_apic_version) && - !boot_cpu_has(X86_FEATURE_APIC)) { - if (!disable_apic) { - pr_err("BIOS bug, local APIC #%d not detected!...\n", - boot_cpu_physical_apicid); - pr_err("... forcing use of dummy APIC emulation (tell your hw vendor)\n"); - } - return SMP_NO_APIC; - } - - /* - * If SMP should be disabled, then really disable it! - */ - if (!max_cpus) { - pr_info("SMP mode deactivated\n"); - return SMP_FORCE_UP; - } - - return SMP_OK; } static void __init smp_cpu_index_default(void) @@ -1293,9 +1196,18 @@ static void __init smp_cpu_index_default(void) } } +static void __init smp_get_logical_apicid(void) +{ + if (x2apic_mode) + cpu0_logical_apicid = apic_read(APIC_LDR); + else + cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); +} + /* - * Prepare for SMP bootup. The MP table or ACPI has been read - * earlier. Just do some sanity checking here and enable APIC mode. + * Prepare for SMP bootup. + * @max_cpus: configured maximum number of CPUs, It is a legacy parameter + * for common interface support. */ void __init native_smp_prepare_cpus(unsigned int max_cpus) { @@ -1327,35 +1239,33 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_cpu_sibling_map(0); - switch (smp_sanity_check(max_cpus)) { - case SMP_NO_CONFIG: - disable_smp(); - if (APIC_init_uniprocessor()) - pr_notice("Local APIC not detected. Using dummy APIC emulation.\n"); - return; - case SMP_NO_APIC: + smp_sanity_check(); + + switch (apic_intr_mode) { + case APIC_PIC: + case APIC_VIRTUAL_WIRE_NO_CONFIG: disable_smp(); return; - case SMP_FORCE_UP: + case APIC_SYMMETRIC_IO_NO_ROUTING: disable_smp(); - apic_bsp_setup(false); + /* Setup local timer */ + x86_init.timers.setup_percpu_clockev(); return; - case SMP_OK: + case APIC_VIRTUAL_WIRE: + case APIC_SYMMETRIC_IO: break; } - if (read_apic_id() != boot_cpu_physical_apicid) { - panic("Boot APIC ID in local APIC unexpected (%d vs %d)", - read_apic_id(), boot_cpu_physical_apicid); - /* Or can we switch back to PIC here? */ - } + /* Setup local timer */ + x86_init.timers.setup_percpu_clockev(); - default_setup_apic_routing(); - cpu0_logical_apicid = apic_bsp_setup(false); + smp_get_logical_apicid(); pr_info("CPU0: "); print_cpu_info(&cpu_data(0)); + native_pv_lock_init(); + uv_system_init(); set_mtrr_aps_delayed_init(); @@ -1387,14 +1297,22 @@ void __init native_smp_prepare_boot_cpu(void) void __init native_smp_cpus_done(unsigned int max_cpus) { + int ncpus; + pr_debug("Boot done\n"); + /* + * Today neither Intel nor AMD support heterogenous systems so + * extrapolate the boot cpu's data to all packages. + */ + ncpus = cpu_data(0).booted_cores * smp_num_siblings; + __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); + pr_info("Max logical packages: %u\n", __max_logical_packages); if (x86_has_numa_in_package) set_sched_topology(x86_numa_in_package_topology); nmi_selftest(); impress_friends(); - setup_ioapic_dest(); mtrr_aps_init(); } @@ -1553,13 +1471,14 @@ void cpu_disable_common(void) remove_cpu_from_maps(cpu); unlock_vector_lock(); fixup_irqs(); + lapic_offline(); } int native_cpu_disable(void) { int ret; - ret = check_irq_vectors_for_cpu_disable(); + ret = lapic_can_unplug_cpu(); if (ret) return ret; diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 8dabd7bf1673..77835bc021c7 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -30,7 +30,7 @@ static int save_stack_address(struct stack_trace *trace, unsigned long addr, return 0; } -static void __save_stack_trace(struct stack_trace *trace, +static void noinline __save_stack_trace(struct stack_trace *trace, struct task_struct *task, struct pt_regs *regs, bool nosched) { @@ -56,6 +56,7 @@ static void __save_stack_trace(struct stack_trace *trace, */ void save_stack_trace(struct stack_trace *trace) { + trace->skip++; __save_stack_trace(trace, current, NULL, false); } EXPORT_SYMBOL_GPL(save_stack_trace); @@ -70,6 +71,8 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) if (!try_get_task_stack(tsk)) return; + if (tsk == current) + trace->skip++; __save_stack_trace(trace, tsk, NULL, true); put_task_stack(tsk); @@ -88,8 +91,9 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk); } \ }) -static int __save_stack_trace_reliable(struct stack_trace *trace, - struct task_struct *task) +static int __always_inline +__save_stack_trace_reliable(struct stack_trace *trace, + struct task_struct *task) { struct unwind_state state; struct pt_regs *regs; diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 5ee663836c08..60d2c3798ba2 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * x86 single-step support code, common to 32-bit and 64-bit. */ diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 73e4d28112f8..676774b9bb8d 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/errno.h> #include <linux/sched.h> #include <linux/sched/mm.h> @@ -187,6 +188,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, if (len > TASK_SIZE) return -ENOMEM; + /* No address checking. See comment at mmap_address_hint_valid() */ if (flags & MAP_FIXED) return addr; @@ -196,12 +198,15 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, /* requesting a specific address */ if (addr) { - addr = PAGE_ALIGN(addr); + addr &= PAGE_MASK; + if (!mmap_address_hint_valid(addr, len)) + goto get_unmapped_area; + vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vm_start_gap(vma))) + if (!vma || addr + len <= vm_start_gap(vma)) return addr; } +get_unmapped_area: info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index e0754cdbad37..749d189f8cd4 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 1991,1992,1995 Linus Torvalds * Copyright (c) 1994 Alan Modra @@ -84,6 +85,11 @@ void __init hpet_time_init(void) static __init void x86_late_time_init(void) { x86_init.timers.timer_init(); + /* + * After PIT/HPET timers init, select and setup + * the final interrupt mode for delivering IRQs. + */ + x86_init.irqs.intr_mode_init(); tsc_init(); } diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index a106b9719c58..9a9c9b076955 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/sched.h> diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c index 80bb24d9b880..b8e7abe00b06 100644 --- a/arch/x86/kernel/trace_clock.c +++ b/arch/x86/kernel/trace_clock.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * X86 trace clocks */ diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c index c6636d1f60b9..5bd30c442794 100644 --- a/arch/x86/kernel/tracepoint.c +++ b/arch/x86/kernel/tracepoint.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Code for supporting irq vector tracepoints. * diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 34ea3651362e..989514c94a55 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -42,7 +42,6 @@ #include <linux/edac.h> #endif -#include <asm/kmemcheck.h> #include <asm/stacktrace.h> #include <asm/processor.h> #include <asm/debugreg.h> @@ -60,6 +59,7 @@ #include <asm/trace/mpx.h> #include <asm/mpx.h> #include <asm/vm86.h> +#include <asm/umip.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -71,7 +71,7 @@ #include <asm/proto.h> #endif -DECLARE_BITMAP(used_vectors, NR_VECTORS); +DECLARE_BITMAP(system_vectors, NR_VECTORS); static inline void cond_local_irq_enable(struct pt_regs *regs) { @@ -141,8 +141,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) * will catch asm bugs and any attempt to use ist_preempt_enable * from double_fault. */ - BUG_ON((unsigned long)(current_top_of_stack() - - current_stack_pointer()) >= THREAD_SIZE); + BUG_ON(!on_thread_stack()); preempt_enable_no_resched(); } @@ -209,9 +208,6 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, if (fixup_exception(regs, trapnr)) return 0; - if (fixup_bug(regs, trapnr)) - return 0; - tsk->thread.error_code = error_code; tsk->thread.trap_nr = trapnr; die(str, regs, error_code); @@ -292,6 +288,13 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str, RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + /* + * WARN*()s end up here; fix them up before we call the + * notifier chain. + */ + if (!user_mode(regs) && fixup_bug(regs, trapnr)) + return; + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) != NOTIFY_STOP) { cond_local_irq_enable(regs); @@ -514,6 +517,11 @@ do_general_protection(struct pt_regs *regs, long error_code) RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); cond_local_irq_enable(regs); + if (static_cpu_has(X86_FEATURE_UMIP)) { + if (user_mode(regs) && fixup_umip_exception(regs)) + return; + } + if (v8086_mode(regs)) { local_irq_enable(); handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); @@ -740,10 +748,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) if (!dr6 && user_mode(regs)) user_icebp = 1; - /* Catch kmemcheck conditions! */ - if ((dr6 & DR_STEP) && kmemcheck_trap(regs)) - goto exit; - /* Store the virtualized DR6 value */ tsk->thread.debugreg6 = dr6; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 796d96bb0821..8ea117f8142e 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -112,7 +112,7 @@ static void cyc2ns_data_init(struct cyc2ns_data *data) data->cyc2ns_offset = 0; } -static void cyc2ns_init(int cpu) +static void __init cyc2ns_init(int cpu) { struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); @@ -812,13 +812,13 @@ unsigned long native_calibrate_cpu(void) return tsc_pit_min; } -int recalibrate_cpu_khz(void) +void recalibrate_cpu_khz(void) { #ifndef CONFIG_SMP unsigned long cpu_khz_old = cpu_khz; if (!boot_cpu_has(X86_FEATURE_TSC)) - return -ENODEV; + return; cpu_khz = x86_platform.calibrate_cpu(); tsc_khz = x86_platform.calibrate_tsc(); @@ -828,10 +828,6 @@ int recalibrate_cpu_khz(void) cpu_khz = tsc_khz; cpu_data(0).loops_per_jiffy = cpufreq_scale(cpu_data(0).loops_per_jiffy, cpu_khz_old, cpu_khz); - - return 0; -#else - return -ENODEV; #endif } @@ -959,17 +955,21 @@ core_initcall(cpufreq_register_tsc_scaling); /* * If ART is present detect the numerator:denominator to convert to TSC */ -static void detect_art(void) +static void __init detect_art(void) { unsigned int unused[2]; if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF) return; - /* Don't enable ART in a VM, non-stop TSC and TSC_ADJUST required */ + /* + * Don't enable ART in a VM, non-stop TSC and TSC_ADJUST required, + * and the TSC counter resets must not occur asynchronously. + */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR) || !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) || - !boot_cpu_has(X86_FEATURE_TSC_ADJUST)) + !boot_cpu_has(X86_FEATURE_TSC_ADJUST) || + tsc_async_resets) return; cpuid(ART_CPUID_LEAF, &art_to_tsc_denominator, @@ -1263,6 +1263,25 @@ static int __init init_tsc_clocksource(void) */ device_initcall(init_tsc_clocksource); +void __init tsc_early_delay_calibrate(void) +{ + unsigned long lpj; + + if (!boot_cpu_has(X86_FEATURE_TSC)) + return; + + cpu_khz = x86_platform.calibrate_cpu(); + tsc_khz = x86_platform.calibrate_tsc(); + + tsc_khz = tsc_khz ? : cpu_khz; + if (!tsc_khz) + return; + + lpj = tsc_khz * 1000; + do_div(lpj, HZ); + loops_per_jiffy = lpj; +} + void __init tsc_init(void) { u64 lpj, cyc; @@ -1346,12 +1365,10 @@ void __init tsc_init(void) unsigned long calibrate_delay_is_known(void) { int sibling, cpu = smp_processor_id(); - struct cpumask *mask = topology_core_cpumask(cpu); - - if (!tsc_disabled && !cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC)) - return 0; + int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC); + const struct cpumask *mask = topology_core_cpumask(cpu); - if (!mask) + if (tsc_disabled || !constant_tsc || !mask) return 0; sibling = cpumask_any_but(mask, cpu); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 7842371bc9e4..ec534f978867 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * check TSC synchronization. * @@ -30,6 +31,20 @@ struct tsc_adjust { static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust); +/* + * TSC's on different sockets may be reset asynchronously. + * This may cause the TSC ADJUST value on socket 0 to be NOT 0. + */ +bool __read_mostly tsc_async_resets; + +void mark_tsc_async_resets(char *reason) +{ + if (tsc_async_resets) + return; + tsc_async_resets = true; + pr_info("tsc: Marking TSC async resets true due to %s\n", reason); +} + void tsc_verify_tsc_adjust(bool resume) { struct tsc_adjust *adj = this_cpu_ptr(&tsc_adjust); @@ -38,6 +53,10 @@ void tsc_verify_tsc_adjust(bool resume) if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST)) return; + /* Skip unnecessary error messages if TSC already unstable */ + if (check_tsc_unstable()) + return; + /* Rate limit the MSR check */ if (!resume && time_before(jiffies, adj->nextcheck)) return; @@ -71,12 +90,22 @@ static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval, * non zero. We don't do that on non boot cpus because physical * hotplug should have set the ADJUST register to a value > 0 so * the TSC is in sync with the already running cpus. + * + * Also don't force the ADJUST value to zero if that is a valid value + * for socket 0 as determined by the system arch. This is required + * when multiple sockets are reset asynchronously with each other + * and socket 0 may not have an TSC ADJUST value of 0. */ if (bootcpu && bootval != 0) { - pr_warn(FW_BUG "TSC ADJUST: CPU%u: %lld force to 0\n", cpu, - bootval); - wrmsrl(MSR_IA32_TSC_ADJUST, 0); - bootval = 0; + if (likely(!tsc_async_resets)) { + pr_warn(FW_BUG "TSC ADJUST: CPU%u: %lld force to 0\n", + cpu, bootval); + wrmsrl(MSR_IA32_TSC_ADJUST, 0); + bootval = 0; + } else { + pr_info("TSC ADJUST: CPU%u: %lld NOT forced to 0\n", + cpu, bootval); + } } cur->adjusted = bootval; } @@ -90,6 +119,10 @@ bool __init tsc_store_and_check_tsc_adjust(bool bootcpu) if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST)) return false; + /* Skip unnecessary error messages if TSC already unstable */ + if (check_tsc_unstable()) + return false; + rdmsrl(MSR_IA32_TSC_ADJUST, bootval); cur->bootval = bootval; cur->nextcheck = jiffies + HZ; @@ -118,6 +151,13 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu) cur->warned = false; /* + * If a non-zero TSC value for socket 0 may be valid then the default + * adjusted value cannot assumed to be zero either. + */ + if (tsc_async_resets) + cur->adjusted = bootval; + + /* * Check whether this CPU is the first in a package to come up. In * this case do not check the boot value against another package * because the new package might have been physically hotplugged, @@ -138,10 +178,9 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu) * Compare the boot value and complain if it differs in the * package. */ - if (bootval != ref->bootval) { - pr_warn(FW_BUG "TSC ADJUST differs: Reference CPU%u: %lld CPU%u: %lld\n", - refcpu, ref->bootval, cpu, bootval); - } + if (bootval != ref->bootval) + printk_once(FW_BUG "TSC ADJUST differs within socket(s), fixing all errors\n"); + /* * The TSC_ADJUST values in a package must be the same. If the boot * value on this newly upcoming CPU differs from the adjustment @@ -149,8 +188,6 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu) * adjusted value. */ if (bootval != ref->adjusted) { - pr_warn("TSC ADJUST synchronize: Reference CPU%u: %lld CPU%u: %lld\n", - refcpu, ref->adjusted, cpu, bootval); cur->adjusted = ref->adjusted; wrmsrl(MSR_IA32_TSC_ADJUST, ref->adjusted); } diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c new file mode 100644 index 000000000000..f44ce0fb3583 --- /dev/null +++ b/arch/x86/kernel/umip.c @@ -0,0 +1,428 @@ +/* + * umip.c Emulation for instruction protected by the Intel User-Mode + * Instruction Prevention feature + * + * Copyright (c) 2017, Intel Corporation. + * Ricardo Neri <ricardo.neri-calderon@linux.intel.com> + */ + +#include <linux/uaccess.h> +#include <asm/umip.h> +#include <asm/traps.h> +#include <asm/insn.h> +#include <asm/insn-eval.h> +#include <linux/ratelimit.h> + +#undef pr_fmt +#define pr_fmt(fmt) "umip: " fmt + +/** DOC: Emulation for User-Mode Instruction Prevention (UMIP) + * + * The feature User-Mode Instruction Prevention present in recent Intel + * processor prevents a group of instructions (sgdt, sidt, sldt, smsw, and str) + * from being executed with CPL > 0. Otherwise, a general protection fault is + * issued. + * + * Rather than relaying to the user space the general protection fault caused by + * the UMIP-protected instructions (in the form of a SIGSEGV signal), it can be + * trapped and emulate the result of such instructions to provide dummy values. + * This allows to both conserve the current kernel behavior and not reveal the + * system resources that UMIP intends to protect (i.e., the locations of the + * global descriptor and interrupt descriptor tables, the segment selectors of + * the local descriptor table, the value of the task state register and the + * contents of the CR0 register). + * + * This emulation is needed because certain applications (e.g., WineHQ and + * DOSEMU2) rely on this subset of instructions to function. + * + * The instructions protected by UMIP can be split in two groups. Those which + * return a kernel memory address (sgdt and sidt) and those which return a + * value (sldt, str and smsw). + * + * For the instructions that return a kernel memory address, applications + * such as WineHQ rely on the result being located in the kernel memory space, + * not the actual location of the table. The result is emulated as a hard-coded + * value that, lies close to the top of the kernel memory. The limit for the GDT + * and the IDT are set to zero. + * + * Given that sldt and str are not commonly used in programs that run on WineHQ + * or DOSEMU2, they are not emulated. + * + * The instruction smsw is emulated to return the value that the register CR0 + * has at boot time as set in the head_32. + * + * Also, emulation is provided only for 32-bit processes; 64-bit processes + * that attempt to use the instructions that UMIP protects will receive the + * SIGSEGV signal issued as a consequence of the general protection fault. + * + * Care is taken to appropriately emulate the results when segmentation is + * used. That is, rather than relying on USER_DS and USER_CS, the function + * insn_get_addr_ref() inspects the segment descriptor pointed by the + * registers in pt_regs. This ensures that we correctly obtain the segment + * base address and the address and operand sizes even if the user space + * application uses a local descriptor table. + */ + +#define UMIP_DUMMY_GDT_BASE 0xfffe0000 +#define UMIP_DUMMY_IDT_BASE 0xffff0000 + +/* + * The SGDT and SIDT instructions store the contents of the global descriptor + * table and interrupt table registers, respectively. The destination is a + * memory operand of X+2 bytes. X bytes are used to store the base address of + * the table and 2 bytes are used to store the limit. In 32-bit processes, the + * only processes for which emulation is provided, X has a value of 4. + */ +#define UMIP_GDT_IDT_BASE_SIZE 4 +#define UMIP_GDT_IDT_LIMIT_SIZE 2 + +#define UMIP_INST_SGDT 0 /* 0F 01 /0 */ +#define UMIP_INST_SIDT 1 /* 0F 01 /1 */ +#define UMIP_INST_SMSW 2 /* 0F 01 /4 */ +#define UMIP_INST_SLDT 3 /* 0F 00 /0 */ +#define UMIP_INST_STR 4 /* 0F 00 /1 */ + +const char * const umip_insns[5] = { + [UMIP_INST_SGDT] = "SGDT", + [UMIP_INST_SIDT] = "SIDT", + [UMIP_INST_SMSW] = "SMSW", + [UMIP_INST_SLDT] = "SLDT", + [UMIP_INST_STR] = "STR", +}; + +#define umip_pr_err(regs, fmt, ...) \ + umip_printk(regs, KERN_ERR, fmt, ##__VA_ARGS__) +#define umip_pr_warning(regs, fmt, ...) \ + umip_printk(regs, KERN_WARNING, fmt, ##__VA_ARGS__) + +/** + * umip_printk() - Print a rate-limited message + * @regs: Register set with the context in which the warning is printed + * @log_level: Kernel log level to print the message + * @fmt: The text string to print + * + * Print the text contained in @fmt. The print rate is limited to bursts of 5 + * messages every two minutes. The purpose of this customized version of + * printk() is to print messages when user space processes use any of the + * UMIP-protected instructions. Thus, the printed text is prepended with the + * task name and process ID number of the current task as well as the + * instruction and stack pointers in @regs as seen when entering kernel mode. + * + * Returns: + * + * None. + */ +static __printf(3, 4) +void umip_printk(const struct pt_regs *regs, const char *log_level, + const char *fmt, ...) +{ + /* Bursts of 5 messages every two minutes */ + static DEFINE_RATELIMIT_STATE(ratelimit, 2 * 60 * HZ, 5); + struct task_struct *tsk = current; + struct va_format vaf; + va_list args; + + if (!__ratelimit(&ratelimit)) + return; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + printk("%s" pr_fmt("%s[%d] ip:%lx sp:%lx: %pV"), log_level, tsk->comm, + task_pid_nr(tsk), regs->ip, regs->sp, &vaf); + va_end(args); +} + +/** + * identify_insn() - Identify a UMIP-protected instruction + * @insn: Instruction structure with opcode and ModRM byte. + * + * From the opcode and ModRM.reg in @insn identify, if any, a UMIP-protected + * instruction that can be emulated. + * + * Returns: + * + * On success, a constant identifying a specific UMIP-protected instruction that + * can be emulated. + * + * -EINVAL on error or when not an UMIP-protected instruction that can be + * emulated. + */ +static int identify_insn(struct insn *insn) +{ + /* By getting modrm we also get the opcode. */ + insn_get_modrm(insn); + + if (!insn->modrm.nbytes) + return -EINVAL; + + /* All the instructions of interest start with 0x0f. */ + if (insn->opcode.bytes[0] != 0xf) + return -EINVAL; + + if (insn->opcode.bytes[1] == 0x1) { + switch (X86_MODRM_REG(insn->modrm.value)) { + case 0: + return UMIP_INST_SGDT; + case 1: + return UMIP_INST_SIDT; + case 4: + return UMIP_INST_SMSW; + default: + return -EINVAL; + } + } else if (insn->opcode.bytes[1] == 0x0) { + if (X86_MODRM_REG(insn->modrm.value) == 0) + return UMIP_INST_SLDT; + else if (X86_MODRM_REG(insn->modrm.value) == 1) + return UMIP_INST_STR; + else + return -EINVAL; + } else { + return -EINVAL; + } +} + +/** + * emulate_umip_insn() - Emulate UMIP instructions and return dummy values + * @insn: Instruction structure with operands + * @umip_inst: A constant indicating the instruction to emulate + * @data: Buffer into which the dummy result is stored + * @data_size: Size of the emulated result + * + * Emulate an instruction protected by UMIP and provide a dummy result. The + * result of the emulation is saved in @data. The size of the results depends + * on both the instruction and type of operand (register vs memory address). + * The size of the result is updated in @data_size. Caller is responsible + * of providing a @data buffer of at least UMIP_GDT_IDT_BASE_SIZE + + * UMIP_GDT_IDT_LIMIT_SIZE bytes. + * + * Returns: + * + * 0 on success, -EINVAL on error while emulating. + */ +static int emulate_umip_insn(struct insn *insn, int umip_inst, + unsigned char *data, int *data_size) +{ + unsigned long dummy_base_addr, dummy_value; + unsigned short dummy_limit = 0; + + if (!data || !data_size || !insn) + return -EINVAL; + /* + * These two instructions return the base address and limit of the + * global and interrupt descriptor table, respectively. According to the + * Intel Software Development manual, the base address can be 24-bit, + * 32-bit or 64-bit. Limit is always 16-bit. If the operand size is + * 16-bit, the returned value of the base address is supposed to be a + * zero-extended 24-byte number. However, it seems that a 32-byte number + * is always returned irrespective of the operand size. + */ + if (umip_inst == UMIP_INST_SGDT || umip_inst == UMIP_INST_SIDT) { + /* SGDT and SIDT do not use registers operands. */ + if (X86_MODRM_MOD(insn->modrm.value) == 3) + return -EINVAL; + + if (umip_inst == UMIP_INST_SGDT) + dummy_base_addr = UMIP_DUMMY_GDT_BASE; + else + dummy_base_addr = UMIP_DUMMY_IDT_BASE; + + *data_size = UMIP_GDT_IDT_LIMIT_SIZE + UMIP_GDT_IDT_BASE_SIZE; + + memcpy(data + 2, &dummy_base_addr, UMIP_GDT_IDT_BASE_SIZE); + memcpy(data, &dummy_limit, UMIP_GDT_IDT_LIMIT_SIZE); + + } else if (umip_inst == UMIP_INST_SMSW) { + dummy_value = CR0_STATE; + + /* + * Even though the CR0 register has 4 bytes, the number + * of bytes to be copied in the result buffer is determined + * by whether the operand is a register or a memory location. + * If operand is a register, return as many bytes as the operand + * size. If operand is memory, return only the two least + * siginificant bytes of CR0. + */ + if (X86_MODRM_MOD(insn->modrm.value) == 3) + *data_size = insn->opnd_bytes; + else + *data_size = 2; + + memcpy(data, &dummy_value, *data_size); + /* STR and SLDT are not emulated */ + } else { + return -EINVAL; + } + + return 0; +} + +/** + * force_sig_info_umip_fault() - Force a SIGSEGV with SEGV_MAPERR + * @addr: Address that caused the signal + * @regs: Register set containing the instruction pointer + * + * Force a SIGSEGV signal with SEGV_MAPERR as the error code. This function is + * intended to be used to provide a segmentation fault when the result of the + * UMIP emulation could not be copied to the user space memory. + * + * Returns: none + */ +static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs) +{ + siginfo_t info; + struct task_struct *tsk = current; + + tsk->thread.cr2 = (unsigned long)addr; + tsk->thread.error_code = X86_PF_USER | X86_PF_WRITE; + tsk->thread.trap_nr = X86_TRAP_PF; + + info.si_signo = SIGSEGV; + info.si_errno = 0; + info.si_code = SEGV_MAPERR; + info.si_addr = addr; + force_sig_info(SIGSEGV, &info, tsk); + + if (!(show_unhandled_signals && unhandled_signal(tsk, SIGSEGV))) + return; + + umip_pr_err(regs, "segfault in emulation. error%x\n", + X86_PF_USER | X86_PF_WRITE); +} + +/** + * fixup_umip_exception() - Fixup a general protection fault caused by UMIP + * @regs: Registers as saved when entering the #GP handler + * + * The instructions sgdt, sidt, str, smsw, sldt cause a general protection + * fault if executed with CPL > 0 (i.e., from user space). If the offending + * user-space process is not in long mode, this function fixes the exception + * up and provides dummy results for sgdt, sidt and smsw; str and sldt are not + * fixed up. Also long mode user-space processes are not fixed up. + * + * If operands are memory addresses, results are copied to user-space memory as + * indicated by the instruction pointed by eIP using the registers indicated in + * the instruction operands. If operands are registers, results are copied into + * the context that was saved when entering kernel mode. + * + * Returns: + * + * True if emulation was successful; false if not. + */ +bool fixup_umip_exception(struct pt_regs *regs) +{ + int not_copied, nr_copied, reg_offset, dummy_data_size, umip_inst; + unsigned long seg_base = 0, *reg_addr; + /* 10 bytes is the maximum size of the result of UMIP instructions */ + unsigned char dummy_data[10] = { 0 }; + unsigned char buf[MAX_INSN_SIZE]; + void __user *uaddr; + struct insn insn; + int seg_defs; + + if (!regs) + return false; + + /* + * If not in user-space long mode, a custom code segment could be in + * use. This is true in protected mode (if the process defined a local + * descriptor table), or virtual-8086 mode. In most of the cases + * seg_base will be zero as in USER_CS. + */ + if (!user_64bit_mode(regs)) + seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS); + + if (seg_base == -1L) + return false; + + not_copied = copy_from_user(buf, (void __user *)(seg_base + regs->ip), + sizeof(buf)); + nr_copied = sizeof(buf) - not_copied; + + /* + * The copy_from_user above could have failed if user code is protected + * by a memory protection key. Give up on emulation in such a case. + * Should we issue a page fault? + */ + if (!nr_copied) + return false; + + insn_init(&insn, buf, nr_copied, user_64bit_mode(regs)); + + /* + * Override the default operand and address sizes with what is specified + * in the code segment descriptor. The instruction decoder only sets + * the address size it to either 4 or 8 address bytes and does nothing + * for the operand bytes. This OK for most of the cases, but we could + * have special cases where, for instance, a 16-bit code segment + * descriptor is used. + * If there is an address override prefix, the instruction decoder + * correctly updates these values, even for 16-bit defaults. + */ + seg_defs = insn_get_code_seg_params(regs); + if (seg_defs == -EINVAL) + return false; + + insn.addr_bytes = INSN_CODE_SEG_ADDR_SZ(seg_defs); + insn.opnd_bytes = INSN_CODE_SEG_OPND_SZ(seg_defs); + + insn_get_length(&insn); + if (nr_copied < insn.length) + return false; + + umip_inst = identify_insn(&insn); + if (umip_inst < 0) + return false; + + umip_pr_warning(regs, "%s instruction cannot be used by applications.\n", + umip_insns[umip_inst]); + + /* Do not emulate SLDT, STR or user long mode processes. */ + if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT || user_64bit_mode(regs)) + return false; + + umip_pr_warning(regs, "For now, expensive software emulation returns the result.\n"); + + if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size)) + return false; + + /* + * If operand is a register, write result to the copy of the register + * value that was pushed to the stack when entering into kernel mode. + * Upon exit, the value we write will be restored to the actual hardware + * register. + */ + if (X86_MODRM_MOD(insn.modrm.value) == 3) { + reg_offset = insn_get_modrm_rm_off(&insn, regs); + + /* + * Negative values are usually errors. In memory addressing, + * the exception is -EDOM. Since we expect a register operand, + * all negative values are errors. + */ + if (reg_offset < 0) + return false; + + reg_addr = (unsigned long *)((unsigned long)regs + reg_offset); + memcpy(reg_addr, dummy_data, dummy_data_size); + } else { + uaddr = insn_get_addr_ref(&insn, regs); + if ((unsigned long)uaddr == -1L) + return false; + + nr_copied = copy_to_user(uaddr, dummy_data, dummy_data_size); + if (nr_copied > 0) { + /* + * If copy fails, send a signal and tell caller that + * fault was fixed up. + */ + force_sig_info_umip_fault(uaddr, regs); + return true; + } + } + + /* increase IP to let the program keep going */ + regs->ip += insn.length; + return true; +} diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index d145a0b1f529..3dc26f95d46e 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -44,7 +44,8 @@ static void unwind_dump(struct unwind_state *state) state->stack_info.type, state->stack_info.next_sp, state->stack_mask, state->graph_idx); - for (sp = state->orig_sp; sp; sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + for (sp = PTR_ALIGN(state->orig_sp, sizeof(long)); sp; + sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { if (get_stack_info(sp, state->task, &stack_info, &visit_mask)) break; @@ -174,6 +175,7 @@ static bool is_last_task_frame(struct unwind_state *state) * This determines if the frame pointer actually contains an encoded pointer to * pt_regs on the stack. See ENCODE_FRAME_POINTER. */ +#ifdef CONFIG_X86_64 static struct pt_regs *decode_frame_pointer(unsigned long *bp) { unsigned long regs = (unsigned long)bp; @@ -183,6 +185,23 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp) return (struct pt_regs *)(regs & ~0x1); } +#else +static struct pt_regs *decode_frame_pointer(unsigned long *bp) +{ + unsigned long regs = (unsigned long)bp; + + if (regs & 0x80000000) + return NULL; + + return (struct pt_regs *)(regs | 0x80000000); +} +#endif + +#ifdef CONFIG_X86_32 +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs) - 2*sizeof(long)) +#else +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs)) +#endif static bool update_stack_state(struct unwind_state *state, unsigned long *next_bp) @@ -202,7 +221,7 @@ static bool update_stack_state(struct unwind_state *state, regs = decode_frame_pointer(next_bp); if (regs) { frame = (unsigned long *)regs; - len = regs_size(regs); + len = KERNEL_REGS_SIZE; state->got_irq = true; } else { frame = next_bp; @@ -226,6 +245,14 @@ static bool update_stack_state(struct unwind_state *state, frame < prev_frame_end) return false; + /* + * On 32-bit with user mode regs, make sure the last two regs are safe + * to access: + */ + if (IS_ENABLED(CONFIG_X86_32) && regs && user_mode(regs) && + !on_stack(info, frame, len + 2*sizeof(long))) + return false; + /* Move state to the next frame: */ if (regs) { state->regs = regs; @@ -328,6 +355,13 @@ bad_address: state->regs->sp < (unsigned long)task_pt_regs(state->task)) goto the_end; + /* + * There are some known frame pointer issues on 32-bit. Disable + * unwinder warnings on 32-bit until it gets objtool support. + */ + if (IS_ENABLED(CONFIG_X86_32)) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 570b70d3f604..a3f973b2c97a 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -86,8 +86,8 @@ static struct orc_entry *orc_find(unsigned long ip) idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE; if (unlikely((idx >= lookup_num_blocks-1))) { - orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%lx\n", - idx, lookup_num_blocks, ip); + orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%pB\n", + idx, lookup_num_blocks, (void *)ip); return NULL; } @@ -96,8 +96,8 @@ static struct orc_entry *orc_find(unsigned long ip) if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) || (__start_orc_unwind + stop > __stop_orc_unwind))) { - orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%lx\n", - idx, lookup_num_blocks, start, stop, ip); + orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%pB\n", + idx, lookup_num_blocks, start, stop, (void *)ip); return NULL; } @@ -279,7 +279,7 @@ static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, if (!stack_access_ok(state, addr, sizeof(long))) return false; - *val = READ_ONCE_TASK_STACK(state->task, *(unsigned long *)addr); + *val = READ_ONCE_NOCHECK(*(unsigned long *)addr); return true; } @@ -373,7 +373,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_R10: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R10 at ip %p\n", + orc_warn("missing regs for base reg R10 at ip %pB\n", (void *)state->ip); goto done; } @@ -382,7 +382,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_R13: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R13 at ip %p\n", + orc_warn("missing regs for base reg R13 at ip %pB\n", (void *)state->ip); goto done; } @@ -391,7 +391,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_DI: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DI at ip %p\n", + orc_warn("missing regs for base reg DI at ip %pB\n", (void *)state->ip); goto done; } @@ -400,7 +400,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_REG_DX: if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DX at ip %p\n", + orc_warn("missing regs for base reg DX at ip %pB\n", (void *)state->ip); goto done; } @@ -408,7 +408,7 @@ bool unwind_next_frame(struct unwind_state *state) break; default: - orc_warn("unknown SP base reg %d for ip %p\n", + orc_warn("unknown SP base reg %d for ip %pB\n", orc->sp_reg, (void *)state->ip); goto done; } @@ -436,7 +436,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_TYPE_REGS: if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) { - orc_warn("can't dereference registers at %p for ip %p\n", + orc_warn("can't dereference registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; } @@ -448,7 +448,7 @@ bool unwind_next_frame(struct unwind_state *state) case ORC_TYPE_REGS_IRET: if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) { - orc_warn("can't dereference iret registers at %p for ip %p\n", + orc_warn("can't dereference iret registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; } @@ -465,7 +465,8 @@ bool unwind_next_frame(struct unwind_state *state) break; default: - orc_warn("unknown .orc_unwind entry type %d\n", orc->type); + orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", + orc->type, (void *)orig_ip); break; } @@ -487,7 +488,7 @@ bool unwind_next_frame(struct unwind_state *state) break; default: - orc_warn("unknown BP base reg %d for ip %p\n", + orc_warn("unknown BP base reg %d for ip %pB\n", orc->bp_reg, (void *)orig_ip); goto done; } @@ -496,7 +497,7 @@ bool unwind_next_frame(struct unwind_state *state) if (state->stack_info.type == prev_type && on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) && state->sp <= prev_sp) { - orc_warn("stack going in the wrong direction? ip=%p\n", + orc_warn("stack going in the wrong direction? ip=%pB\n", (void *)orig_ip); goto done; } diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 495c776de4b4..a3755d293a48 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -271,12 +271,15 @@ static bool is_prefix_bad(struct insn *insn) int i; for (i = 0; i < insn->prefixes.nbytes; i++) { - switch (insn->prefixes.bytes[i]) { - case 0x26: /* INAT_PFX_ES */ - case 0x2E: /* INAT_PFX_CS */ - case 0x36: /* INAT_PFX_DS */ - case 0x3E: /* INAT_PFX_SS */ - case 0xF0: /* INAT_PFX_LOCK */ + insn_attr_t attr; + + attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]); + switch (attr) { + case INAT_MAKE_PREFIX(INAT_PFX_ES): + case INAT_MAKE_PREFIX(INAT_PFX_CS): + case INAT_MAKE_PREFIX(INAT_PFX_DS): + case INAT_MAKE_PREFIX(INAT_PFX_SS): + case INAT_MAKE_PREFIX(INAT_PFX_LOCK): return true; } } diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index 014ea59aa153..3d3c2f71f617 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -33,7 +33,7 @@ #include <asm/cpufeatures.h> #include <asm/msr-index.h> -verify_cpu: +ENTRY(verify_cpu) pushf # Save caller passed flags push $0 # Kill any dangerous flags popf @@ -139,3 +139,4 @@ verify_cpu: popf # Restore caller passed flags xorl %eax, %eax ret +ENDPROC(verify_cpu) diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 7924a5356c8a..5edb27f1a2c4 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1994 Linus Torvalds * @@ -54,6 +55,7 @@ #include <asm/irq.h> #include <asm/traps.h> #include <asm/vm86.h> +#include <asm/switch_to.h> /* * Known problems: @@ -93,7 +95,6 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) { - struct tss_struct *tss; struct task_struct *tsk = current; struct vm86plus_struct __user *user; struct vm86 *vm86 = current->thread.vm86; @@ -145,12 +146,13 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) do_exit(SIGSEGV); } - tss = &per_cpu(cpu_tss, get_cpu()); + preempt_disable(); tsk->thread.sp0 = vm86->saved_sp0; tsk->thread.sysenter_cs = __KERNEL_CS; - load_sp0(tss, &tsk->thread); + update_sp0(tsk); + refresh_sysenter_cs(&tsk->thread); vm86->saved_sp0 = 0; - put_cpu(); + preempt_enable(); memcpy(®s->pt, &vm86->regs32, sizeof(struct pt_regs)); @@ -236,7 +238,6 @@ SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg) static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) { - struct tss_struct *tss; struct task_struct *tsk = current; struct vm86 *vm86 = tsk->thread.vm86; struct kernel_vm86_regs vm86regs; @@ -364,15 +365,17 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) vm86->saved_sp0 = tsk->thread.sp0; lazy_save_gs(vm86->regs32.gs); - tss = &per_cpu(cpu_tss, get_cpu()); /* make room for real-mode segments */ + preempt_disable(); tsk->thread.sp0 += 16; - if (static_cpu_has(X86_FEATURE_SEP)) + if (static_cpu_has(X86_FEATURE_SEP)) { tsk->thread.sysenter_cs = 0; + refresh_sysenter_cs(&tsk->thread); + } - load_sp0(tss, &tsk->thread); - put_cpu(); + update_sp0(tsk); + preempt_enable(); if (vm86->flags & VM86_SCREEN_BITMAP) mark_screen_rdonly(tsk->mm); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index f05f00acac89..a4009fb9be87 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * ld script for the x86 kernel * diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index b034b1b14b9c..44685fb2a192 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -26,9 +26,6 @@ #define TOPOLOGY_REGISTER_OFFSET 0x10 -/* Flag below is initialized once during vSMP PCI initialization. */ -static int irq_routing_comply = 1; - #if defined CONFIG_PCI && defined CONFIG_PARAVIRT /* * Interrupt control on vSMPowered systems: @@ -105,9 +102,6 @@ static void __init set_vsmp_pv_ops(void) if (cap & ctl & BIT(8)) { ctl &= ~BIT(8); - /* Interrupt routing set to ignore */ - irq_routing_comply = 0; - #ifdef CONFIG_PROC_FS /* Don't let users change irq affinity via procfs */ no_irq_affinity = 1; @@ -211,23 +205,10 @@ static int apicid_phys_pkg_id(int initial_apic_id, int index_msb) return hard_smp_processor_id() >> index_msb; } -/* - * In vSMP, all cpus should be capable of handling interrupts, regardless of - * the APIC used. - */ -static void fill_vector_allocation_domain(int cpu, struct cpumask *retmask, - const struct cpumask *mask) -{ - cpumask_setall(retmask); -} - static void vsmp_apic_post_init(void) { /* need to update phys_pkg_id */ apic->phys_pkg_id = apicid_phys_pkg_id; - - if (!irq_routing_comply) - apic->vector_allocation_domain = fill_vector_allocation_domain; } void __init vsmp_init(void) diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index a088b2c47f73..1151ccd72ce9 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -28,6 +28,8 @@ void x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } int __init iommu_init_noop(void) { return 0; } void iommu_shutdown_noop(void) { } +bool __init bool_x86_init_noop(void) { return false; } +void x86_op_int_noop(int cpu) { } /* * The platform setup functions are preset with the default functions @@ -55,6 +57,7 @@ struct x86_init_ops x86_init __initdata = { .pre_vector_init = init_ISA_irqs, .intr_init = native_init_IRQ, .trap_init = x86_init_noop, + .intr_mode_init = apic_intr_mode_init }, .oem = { @@ -81,6 +84,13 @@ struct x86_init_ops x86_init __initdata = { .init_irq = x86_default_pci_init_irq, .fixup_irqs = x86_default_pci_fixup_irqs, }, + + .hyper = { + .init_platform = x86_init_noop, + .guest_late_init = x86_init_noop, + .x2apic_available = bool_x86_init_noop, + .init_mem_mapping = x86_init_noop, + }, }; struct x86_cpuinit_ops x86_cpuinit = { @@ -101,6 +111,7 @@ struct x86_platform_ops x86_platform __ro_after_init = { .get_nmi_reason = default_get_nmi_reason, .save_sched_clock_state = tsc_save_sched_clock_state, .restore_sched_clock_state = tsc_restore_sched_clock_state, + .hyper.pin_vcpu = x86_op_int_noop, }; EXPORT_SYMBOL_GPL(x86_platform); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 3ea624452f93..3df51c287844 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # KVM configuration # @@ -23,6 +24,7 @@ config KVM depends on HIGH_RES_TIMERS # for TASKSTATS/TASK_DELAY_ACCT: depends on NET && MULTIUSER + depends on X86_LOCAL_APIC select PREEMPT_NOTIFIERS select MMU_NOTIFIER select ANON_INODES diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 09d4b17be022..dc4f2fdf5e57 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 ccflags-y += -Iarch/x86/kvm diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 0bc5c1315708..cdc70a3a6583 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ARCH_X86_KVM_CPUID_H #define ARCH_X86_KVM_CPUID_H diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 16bf6655aa85..8079d141792a 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -425,8 +425,10 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); #op " %al \n\t" \ FOP_RET -asm(".global kvm_fastop_exception \n" - "kvm_fastop_exception: xor %esi, %esi; ret"); +asm(".pushsection .fixup, \"ax\"\n" + ".global kvm_fastop_exception \n" + "kvm_fastop_exception: xor %esi, %esi; ret\n" + ".popsection"); FOP_START(setcc) FOP_SETCC(seto) @@ -2589,6 +2591,15 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) ctxt->ops->set_msr(ctxt, MSR_EFER, efer); smbase = ctxt->ops->get_smbase(ctxt); + + /* + * Give pre_leave_smm() a chance to make ISA-specific changes to the + * vCPU state (e.g. enter guest mode) before loading state from the SMM + * state-save area. + */ + if (ctxt->ops->pre_leave_smm(ctxt, smbase)) + return X86EMUL_UNHANDLEABLE; + if (emulator_has_longmode(ctxt)) ret = rsm_load_state_64(ctxt, smbase + 0x8000); else @@ -4102,10 +4113,12 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt) ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if (efer & EFER_LMA) { u64 maxphyaddr; - u32 eax = 0x80000008; + u32 eax, ebx, ecx, edx; - if (ctxt->ops->get_cpuid(ctxt, &eax, NULL, NULL, - NULL, false)) + eax = 0x80000008; + ecx = 0; + if (ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, + &edx, false)) maxphyaddr = eax & 0xff; else maxphyaddr = 36; @@ -5296,7 +5309,6 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) { - register void *__sp asm(_ASM_SP); ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; if (!(ctxt->d & ByteOp)) @@ -5304,7 +5316,7 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [fastop]"+S"(fop), "+r"(__sp) + [fastop]"+S"(fop), ASM_CALL_CONSTRAINT : "c"(ctxt->src2.val)); ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index 600bee9dcbbd..394d9527da7e 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __I8254_H #define __I8254_H diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 29ce19732ccf..ea1a4e0297da 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KVM_IO_APIC_H #define __KVM_IO_APIC_H diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 9add410f195f..f500293dad8d 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ASM_KVM_CACHE_REGS_H #define ASM_KVM_CACHE_REGS_H diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 69c5612be786..943acbf00c69 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1301,14 +1301,42 @@ static void update_divide_count(struct kvm_lapic *apic) apic->divide_count); } +static void limit_periodic_timer_frequency(struct kvm_lapic *apic) +{ + /* + * 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) && apic->lapic_timer.period) { + 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; + } + } +} + static void apic_update_lvtt(struct kvm_lapic *apic) { u32 timer_mode = kvm_lapic_get_reg(apic, APIC_LVTT) & apic->lapic_timer.timer_mode_mask; if (apic->lapic_timer.timer_mode != timer_mode) { + if (apic_lvtt_tscdeadline(apic) != (timer_mode == + APIC_LVT_TIMER_TSCDEADLINE)) { + hrtimer_cancel(&apic->lapic_timer.timer); + kvm_lapic_set_reg(apic, APIC_TMICT, 0); + apic->lapic_timer.period = 0; + apic->lapic_timer.tscdeadline = 0; + } apic->lapic_timer.timer_mode = timer_mode; - hrtimer_cancel(&apic->lapic_timer.timer); + limit_periodic_timer_frequency(apic); } } @@ -1430,6 +1458,30 @@ static void start_sw_period(struct kvm_lapic *apic) HRTIMER_MODE_ABS_PINNED); } +static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_divisor) +{ + ktime_t now, remaining; + u64 ns_remaining_old, ns_remaining_new; + + apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT) + * APIC_BUS_CYCLE_NS * apic->divide_count; + limit_periodic_timer_frequency(apic); + + now = ktime_get(); + remaining = ktime_sub(apic->lapic_timer.target_expiration, now); + if (ktime_to_ns(remaining) < 0) + remaining = 0; + + ns_remaining_old = ktime_to_ns(remaining); + ns_remaining_new = mul_u64_u32_div(ns_remaining_old, + apic->divide_count, old_divisor); + + apic->lapic_timer.tscdeadline += + nsec_to_cycles(apic->vcpu, ns_remaining_new) - + nsec_to_cycles(apic->vcpu, ns_remaining_old); + apic->lapic_timer.target_expiration = ktime_add_ns(now, ns_remaining_new); +} + static bool set_target_expiration(struct kvm_lapic *apic) { ktime_t now; @@ -1439,27 +1491,13 @@ static bool set_target_expiration(struct kvm_lapic *apic) apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT) * APIC_BUS_CYCLE_NS * apic->divide_count; - if (!apic->lapic_timer.period) + if (!apic->lapic_timer.period) { + apic->lapic_timer.tscdeadline = 0; return false; - - /* - * 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; - } } + limit_periodic_timer_frequency(apic); + apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" PRIx64 ", " "timer initial count 0x%x, period %lldns, " @@ -1515,6 +1553,9 @@ static bool start_hv_timer(struct kvm_lapic *apic) if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending)) return false; + if (!ktimer->tscdeadline) + return false; + r = kvm_x86_ops->set_hv_timer(apic->vcpu, ktimer->tscdeadline); if (r < 0) return false; @@ -1738,13 +1779,21 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) start_apic_timer(apic); break; - case APIC_TDCR: + case APIC_TDCR: { + uint32_t old_divisor = apic->divide_count; + if (val & 4) apic_debug("KVM_WRITE:TDCR %x\n", val); kvm_lapic_set_reg(apic, APIC_TDCR, val); update_divide_count(apic); + if (apic->divide_count != old_divisor && + apic->lapic_timer.period) { + hrtimer_cancel(&apic->lapic_timer.timer); + update_target_expiration(apic, old_divisor); + restart_apic_timer(apic); + } break; - + } case APIC_ESR: if (apic_x2apic_mode(apic) && val != 0) { apic_debug("KVM_WRITE:ESR not zero %x\n", val); @@ -1992,6 +2041,11 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.apic_base | MSR_IA32_APICBASE_BSP); vcpu->arch.pv_eoi.msr_val = 0; apic_update_ppr(apic); + if (vcpu->arch.apicv_active) { + kvm_x86_ops->apicv_post_state_restore(vcpu); + kvm_x86_ops->hwapic_irr_update(vcpu, -1); + kvm_x86_ops->hwapic_isr_update(vcpu, -1); + } vcpu->arch.apic_arb_prio = 0; vcpu->arch.apic_attention = 0; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 215721e1426a..4b9935a38347 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KVM_X86_LAPIC_H #define __KVM_X86_LAPIC_H diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index eca30c1eb1d9..e5e66e5c6640 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -150,6 +150,20 @@ module_param(dbg, bool, 0644); /* make pte_list_desc fit well in cache line */ #define PTE_LIST_EXT 3 +/* + * Return values of handle_mmio_page_fault and mmu.page_fault: + * RET_PF_RETRY: let CPU fault again on the address. + * RET_PF_EMULATE: mmio page fault, emulate the instruction directly. + * + * For handle_mmio_page_fault only: + * RET_PF_INVALID: the spte is invalid, let the real page fault path update it. + */ +enum { + RET_PF_RETRY = 0, + RET_PF_EMULATE = 1, + RET_PF_INVALID = 2, +}; + struct pte_list_desc { u64 *sptes[PTE_LIST_EXT]; struct pte_list_desc *more; @@ -443,7 +457,7 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) static u64 __get_spte_lockless(u64 *sptep) { - return ACCESS_ONCE(*sptep); + return READ_ONCE(*sptep); } #else union split_spte { @@ -2424,7 +2438,7 @@ static void __shadow_walk_next(struct kvm_shadow_walk_iterator *iterator, static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) { - return __shadow_walk_next(iterator, *iterator->sptep); + __shadow_walk_next(iterator, *iterator->sptep); } static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, @@ -2794,13 +2808,13 @@ done: return ret; } -static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, - int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, - bool speculative, bool host_writable) +static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, + int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, + bool speculative, bool host_writable) { int was_rmapped = 0; int rmap_count; - bool emulate = false; + int ret = RET_PF_RETRY; pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, *sptep, write_fault, gfn); @@ -2830,12 +2844,12 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative, true, host_writable)) { if (write_fault) - emulate = true; + ret = RET_PF_EMULATE; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } if (unlikely(is_mmio_spte(*sptep))) - emulate = true; + ret = RET_PF_EMULATE; pgprintk("%s: setting spte %llx\n", __func__, *sptep); pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", @@ -2855,7 +2869,7 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, kvm_release_pfn_clean(pfn); - return emulate; + return ret; } static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, @@ -2994,14 +3008,13 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) * Do not cache the mmio info caused by writing the readonly gfn * into the spte otherwise read access on readonly gfn also can * caused mmio page fault and treat it as mmio access. - * Return 1 to tell kvm to emulate it. */ if (pfn == KVM_PFN_ERR_RO_FAULT) - return 1; + return RET_PF_EMULATE; if (pfn == KVM_PFN_ERR_HWPOISON) { kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current); - return 0; + return RET_PF_RETRY; } return -EFAULT; @@ -3286,13 +3299,13 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, } if (fast_page_fault(vcpu, v, level, error_code)) - return 0; + return RET_PF_RETRY; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable)) - return 0; + return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r)) return r; @@ -3312,7 +3325,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return 0; + return RET_PF_RETRY; } @@ -3659,54 +3672,38 @@ exit: return reserved; } -/* - * Return values of handle_mmio_page_fault: - * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction - * directly. - * RET_MMIO_PF_INVALID: invalid spte is detected then let the real page - * fault path update the mmio spte. - * RET_MMIO_PF_RETRY: let CPU fault again on the address. - * RET_MMIO_PF_BUG: a bug was detected (and a WARN was printed). - */ -enum { - RET_MMIO_PF_EMULATE = 1, - RET_MMIO_PF_INVALID = 2, - RET_MMIO_PF_RETRY = 0, - RET_MMIO_PF_BUG = -1 -}; - static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) { u64 spte; bool reserved; if (mmio_info_in_cache(vcpu, addr, direct)) - return RET_MMIO_PF_EMULATE; + return RET_PF_EMULATE; reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte); if (WARN_ON(reserved)) - return RET_MMIO_PF_BUG; + return -EINVAL; if (is_mmio_spte(spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); unsigned access = get_mmio_spte_access(spte); if (!check_mmio_spte(vcpu, spte)) - return RET_MMIO_PF_INVALID; + return RET_PF_INVALID; if (direct) addr = 0; trace_handle_mmio_page_fault(addr, gfn, access); vcpu_cache_mmio_info(vcpu, addr, gfn, access); - return RET_MMIO_PF_EMULATE; + return RET_PF_EMULATE; } /* * If the page table is zapped by other cpus, let CPU fault again on * the address. */ - return RET_MMIO_PF_RETRY; + return RET_PF_RETRY; } EXPORT_SYMBOL_GPL(handle_mmio_page_fault); @@ -3756,7 +3753,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); if (page_fault_handle_page_track(vcpu, error_code, gfn)) - return 1; + return RET_PF_EMULATE; r = mmu_topup_memory_caches(vcpu); if (r) @@ -3820,8 +3817,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, } int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, - u64 fault_address, char *insn, int insn_len, - bool need_unprotect) + u64 fault_address, char *insn, int insn_len) { int r = 1; @@ -3829,7 +3825,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, default: trace_kvm_page_fault(fault_address, error_code); - if (need_unprotect && kvm_event_needs_reinjection(vcpu)) + if (kvm_event_needs_reinjection(vcpu)) kvm_mmu_unprotect_page_virt(vcpu, fault_address); r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn, insn_len); @@ -3837,7 +3833,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, case KVM_PV_REASON_PAGE_NOT_PRESENT: vcpu->arch.apf.host_apf_reason = 0; local_irq_disable(); - kvm_async_pf_task_wait(fault_address); + kvm_async_pf_task_wait(fault_address, 0); local_irq_enable(); break; case KVM_PV_REASON_PAGE_READY: @@ -3876,7 +3872,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); if (page_fault_handle_page_track(vcpu, error_code, gfn)) - return 1; + return RET_PF_EMULATE; r = mmu_topup_memory_caches(vcpu); if (r) @@ -3893,13 +3889,13 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, } if (fast_page_fault(vcpu, gpa, level, error_code)) - return 0; + return RET_PF_RETRY; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) - return 0; + return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r)) return r; @@ -3919,7 +3915,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return 0; + return RET_PF_RETRY; } static void nonpaging_init_context(struct kvm_vcpu *vcpu, @@ -3974,19 +3970,19 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte) { /* - * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set - * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means - * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then. - */ - gpte |= level - PT_PAGE_TABLE_LEVEL - 1; - - /* * The RHS has bit 7 set iff level < mmu->last_nonleaf_level. * If it is clear, there are no large pages at this level, so clear * PT_PAGE_SIZE_MASK in gpte if that is the case. */ gpte &= level - mmu->last_nonleaf_level; + /* + * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set + * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means + * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then. + */ + gpte |= level - PT_PAGE_TABLE_LEVEL - 1; + return gpte & PT_PAGE_SIZE_MASK; } @@ -4555,6 +4551,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, update_permission_bitmask(vcpu, context, true); update_pkru_bitmask(vcpu, context, true); + update_last_nonleaf_level(vcpu, context); reset_rsvds_bits_mask_ept(vcpu, context, execonly); reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } @@ -4818,7 +4815,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, * If we don't have indirect shadow pages, it means no page is * write-protected, so we can exit simply. */ - if (!ACCESS_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) + if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages)) return; remote_flush = local_flush = false; @@ -4917,25 +4914,25 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, vcpu->arch.gpa_val = cr2; } + r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { r = handle_mmio_page_fault(vcpu, cr2, direct); - if (r == RET_MMIO_PF_EMULATE) { + if (r == RET_PF_EMULATE) { emulation_type = 0; goto emulate; } - if (r == RET_MMIO_PF_RETRY) - return 1; - if (r < 0) - return r; - /* Must be RET_MMIO_PF_INVALID. */ } - r = vcpu->arch.mmu.page_fault(vcpu, cr2, lower_32_bits(error_code), - false); + if (r == RET_PF_INVALID) { + r = vcpu->arch.mmu.page_fault(vcpu, cr2, lower_32_bits(error_code), + false); + WARN_ON(r == RET_PF_INVALID); + } + + if (r == RET_PF_RETRY) + return 1; if (r < 0) return r; - if (!r) - return 1; /* * Before emulating the instruction, check if the error code @@ -4992,8 +4989,7 @@ EXPORT_SYMBOL_GPL(kvm_disable_tdp); static void free_mmu_pages(struct kvm_vcpu *vcpu) { free_page((unsigned long)vcpu->arch.mmu.pae_root); - if (vcpu->arch.mmu.lm_root != NULL) - free_page((unsigned long)vcpu->arch.mmu.lm_root); + free_page((unsigned long)vcpu->arch.mmu.lm_root); } static int alloc_mmu_pages(struct kvm_vcpu *vcpu) @@ -5463,10 +5459,8 @@ static struct shrinker mmu_shrinker = { static void mmu_destroy_caches(void) { - if (pte_list_desc_cache) - kmem_cache_destroy(pte_list_desc_cache); - if (mmu_page_header_cache) - kmem_cache_destroy(mmu_page_header_cache); + kmem_cache_destroy(pte_list_desc_cache); + kmem_cache_destroy(mmu_page_header_cache); } int kvm_mmu_module_init(void) @@ -5475,13 +5469,13 @@ int kvm_mmu_module_init(void) pte_list_desc_cache = kmem_cache_create("pte_list_desc", sizeof(struct pte_list_desc), - 0, 0, NULL); + 0, SLAB_ACCOUNT, NULL); if (!pte_list_desc_cache) goto nomem; mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header", sizeof(struct kvm_mmu_page), - 0, 0, NULL); + 0, SLAB_ACCOUNT, NULL); if (!mmu_page_header_cache) goto nomem; diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 64a2dbd2b1af..5b408c0ad612 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KVM_X86_MMU_H #define __KVM_X86_MMU_H @@ -65,8 +66,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool accessed_dirty); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, - u64 fault_address, char *insn, int insn_len, - bool need_unprotect); + u64 fault_address, char *insn, int insn_len); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 8b97a6cba8d1..c73bf4e4988c 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #if !defined(_TRACE_KVMMMU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KVMMMU_H diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c index ea67dc876316..01c1371f39f8 100644 --- a/arch/x86/kvm/page_track.c +++ b/arch/x86/kvm/page_track.c @@ -157,7 +157,7 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn, return false; index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL); - return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]); + return !!READ_ONCE(slot->arch.gfn_track[mode][index]); } void kvm_page_track_cleanup(struct kvm *kvm) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 86b68dc5a649..5abae72266b7 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -334,10 +334,11 @@ retry_walk: --walker->level; index = PT_INDEX(addr, walker->level); - table_gfn = gpte_to_gfn(pte); offset = index * sizeof(pt_element_t); pte_gpa = gfn_to_gpa(table_gfn) + offset; + + BUG_ON(walker->level < 1); walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; @@ -592,7 +593,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; - int top_level, emulate; + int top_level, ret; direct_access = gw->pte_access; @@ -658,15 +659,15 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, } clear_sp_write_flooding_count(it.sptep); - emulate = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, - it.level, gw->gfn, pfn, prefault, map_writable); + ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, + it.level, gw->gfn, pfn, prefault, map_writable); FNAME(pte_prefetch)(vcpu, gw, it.sptep); - return emulate; + return ret; out_gpte_changed: kvm_release_pfn_clean(pfn); - return 0; + return RET_PF_RETRY; } /* @@ -761,12 +762,12 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (!prefault) inject_page_fault(vcpu, &walker.fault); - return 0; + return RET_PF_RETRY; } if (page_fault_handle_page_track(vcpu, error_code, walker.gfn)) { shadow_page_table_clear_flood(vcpu, addr); - return 1; + return RET_PF_EMULATE; } vcpu->arch.write_fault_to_shadow_pgtable = false; @@ -788,7 +789,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, write_fault, &map_writable)) - return 0; + return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r)) return r; @@ -833,7 +834,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); - return 0; + return RET_PF_RETRY; } static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index f96e1f962587..a9a62b9a73e2 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KVM_X86_PMU_H #define __KVM_X86_PMU_H diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 0e68f0b3cbf7..59e13a79c2e3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1034,15 +1034,12 @@ static int avic_ga_log_notifier(u32 ga_tag) } spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); - if (!vcpu) - return 0; - /* Note: * At this point, the IOMMU should have already set the pending * bit in the vAPIC backing page. So, we just need to schedule * in the vcpu. */ - if (vcpu->mode == OUTSIDE_GUEST_MODE) + if (vcpu) kvm_vcpu_wake_up(vcpu); return 0; @@ -2144,7 +2141,18 @@ static int pf_interception(struct vcpu_svm *svm) return kvm_handle_page_fault(&svm->vcpu, error_code, fault_address, svm->vmcb->control.insn_bytes, - svm->vmcb->control.insn_len, !npt_enabled); + svm->vmcb->control.insn_len); +} + +static int npf_interception(struct vcpu_svm *svm) +{ + u64 fault_address = svm->vmcb->control.exit_info_2; + u64 error_code = svm->vmcb->control.exit_info_1; + + trace_kvm_page_fault(fault_address, error_code); + return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code, + svm->vmcb->control.insn_bytes, + svm->vmcb->control.insn_len); } static int db_interception(struct vcpu_svm *svm) @@ -2916,70 +2924,9 @@ static bool nested_vmcb_checks(struct vmcb *vmcb) return true; } -static bool nested_svm_vmrun(struct vcpu_svm *svm) +static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, + struct vmcb *nested_vmcb, struct page *page) { - struct vmcb *nested_vmcb; - struct vmcb *hsave = svm->nested.hsave; - struct vmcb *vmcb = svm->vmcb; - struct page *page; - u64 vmcb_gpa; - - vmcb_gpa = svm->vmcb->save.rax; - - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); - if (!nested_vmcb) - return false; - - if (!nested_vmcb_checks(nested_vmcb)) { - nested_vmcb->control.exit_code = SVM_EXIT_ERR; - nested_vmcb->control.exit_code_hi = 0; - nested_vmcb->control.exit_info_1 = 0; - nested_vmcb->control.exit_info_2 = 0; - - nested_svm_unmap(page); - - return false; - } - - trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa, - nested_vmcb->save.rip, - nested_vmcb->control.int_ctl, - nested_vmcb->control.event_inj, - nested_vmcb->control.nested_ctl); - - trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr & 0xffff, - nested_vmcb->control.intercept_cr >> 16, - nested_vmcb->control.intercept_exceptions, - nested_vmcb->control.intercept); - - /* Clear internal status */ - kvm_clear_exception_queue(&svm->vcpu); - kvm_clear_interrupt_queue(&svm->vcpu); - - /* - * Save the old vmcb, so we don't need to pick what we save, but can - * restore everything when a VMEXIT occurs - */ - hsave->save.es = vmcb->save.es; - hsave->save.cs = vmcb->save.cs; - hsave->save.ss = vmcb->save.ss; - hsave->save.ds = vmcb->save.ds; - hsave->save.gdtr = vmcb->save.gdtr; - hsave->save.idtr = vmcb->save.idtr; - hsave->save.efer = svm->vcpu.arch.efer; - hsave->save.cr0 = kvm_read_cr0(&svm->vcpu); - hsave->save.cr4 = svm->vcpu.arch.cr4; - hsave->save.rflags = kvm_get_rflags(&svm->vcpu); - hsave->save.rip = kvm_rip_read(&svm->vcpu); - hsave->save.rsp = vmcb->save.rsp; - hsave->save.rax = vmcb->save.rax; - if (npt_enabled) - hsave->save.cr3 = vmcb->save.cr3; - else - hsave->save.cr3 = kvm_read_cr3(&svm->vcpu); - - copy_vmcb_control_area(hsave, vmcb); - if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF) svm->vcpu.arch.hflags |= HF_HIF_MASK; else @@ -3072,6 +3019,73 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) enable_gif(svm); mark_all_dirty(svm->vmcb); +} + +static bool nested_svm_vmrun(struct vcpu_svm *svm) +{ + struct vmcb *nested_vmcb; + struct vmcb *hsave = svm->nested.hsave; + struct vmcb *vmcb = svm->vmcb; + struct page *page; + u64 vmcb_gpa; + + vmcb_gpa = svm->vmcb->save.rax; + + nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); + if (!nested_vmcb) + return false; + + if (!nested_vmcb_checks(nested_vmcb)) { + nested_vmcb->control.exit_code = SVM_EXIT_ERR; + nested_vmcb->control.exit_code_hi = 0; + nested_vmcb->control.exit_info_1 = 0; + nested_vmcb->control.exit_info_2 = 0; + + nested_svm_unmap(page); + + return false; + } + + trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa, + nested_vmcb->save.rip, + nested_vmcb->control.int_ctl, + nested_vmcb->control.event_inj, + nested_vmcb->control.nested_ctl); + + trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr & 0xffff, + nested_vmcb->control.intercept_cr >> 16, + nested_vmcb->control.intercept_exceptions, + nested_vmcb->control.intercept); + + /* Clear internal status */ + kvm_clear_exception_queue(&svm->vcpu); + kvm_clear_interrupt_queue(&svm->vcpu); + + /* + * Save the old vmcb, so we don't need to pick what we save, but can + * restore everything when a VMEXIT occurs + */ + hsave->save.es = vmcb->save.es; + hsave->save.cs = vmcb->save.cs; + hsave->save.ss = vmcb->save.ss; + hsave->save.ds = vmcb->save.ds; + hsave->save.gdtr = vmcb->save.gdtr; + hsave->save.idtr = vmcb->save.idtr; + hsave->save.efer = svm->vcpu.arch.efer; + hsave->save.cr0 = kvm_read_cr0(&svm->vcpu); + hsave->save.cr4 = svm->vcpu.arch.cr4; + hsave->save.rflags = kvm_get_rflags(&svm->vcpu); + hsave->save.rip = kvm_rip_read(&svm->vcpu); + hsave->save.rsp = vmcb->save.rsp; + hsave->save.rax = vmcb->save.rax; + if (npt_enabled) + hsave->save.cr3 = vmcb->save.cr3; + else + hsave->save.cr3 = kvm_read_cr3(&svm->vcpu); + + copy_vmcb_control_area(hsave, vmcb); + + enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, page); return true; } @@ -3173,7 +3187,7 @@ static int stgi_interception(struct vcpu_svm *svm) /* * If VGIF is enabled, the STGI intercept is only added to - * detect the opening of the NMI window; remove it now. + * detect the opening of the SMI/NMI window; remove it now. */ if (vgif_enabled(svm)) clr_intercept(svm, INTERCEPT_STGI); @@ -3657,6 +3671,13 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) u32 ecx = msr->index; u64 data = msr->data; switch (ecx) { + case MSR_IA32_CR_PAT: + if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) + return 1; + vcpu->arch.pat = data; + svm->vmcb->save.g_pat = data; + mark_dirty(svm->vmcb, VMCB_NPT); + break; case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr); break; @@ -4131,7 +4152,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_MONITOR] = monitor_interception, [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, - [SVM_EXIT_NPF] = pf_interception, + [SVM_EXIT_NPF] = npf_interception, [SVM_EXIT_RSM] = emulate_on_interception, [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, [SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception, @@ -5393,6 +5414,88 @@ static void svm_setup_mce(struct kvm_vcpu *vcpu) vcpu->arch.mcg_cap &= 0x1ff; } +static int svm_smi_allowed(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* Per APM Vol.2 15.22.2 "Response to SMI" */ + if (!gif_set(svm)) + return 0; + + if (is_guest_mode(&svm->vcpu) && + svm->nested.intercept & (1ULL << INTERCEPT_SMI)) { + /* TODO: Might need to set exit_info_1 and exit_info_2 here */ + svm->vmcb->control.exit_code = SVM_EXIT_SMI; + svm->nested.exit_required = true; + return 0; + } + + return 1; +} + +static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int ret; + + if (is_guest_mode(vcpu)) { + /* FED8h - SVM Guest */ + put_smstate(u64, smstate, 0x7ed8, 1); + /* FEE0h - SVM Guest VMCB Physical Address */ + put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb); + + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; + + ret = nested_svm_vmexit(svm); + if (ret) + return ret; + } + return 0; +} + +static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *nested_vmcb; + struct page *page; + struct { + u64 guest; + u64 vmcb; + } svm_state_save; + int ret; + + ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfed8, &svm_state_save, + sizeof(svm_state_save)); + if (ret) + return ret; + + if (svm_state_save.guest) { + vcpu->arch.hflags &= ~HF_SMM_MASK; + nested_vmcb = nested_svm_map(svm, svm_state_save.vmcb, &page); + if (nested_vmcb) + enter_svm_guest_mode(svm, svm_state_save.vmcb, nested_vmcb, page); + else + ret = 1; + vcpu->arch.hflags |= HF_SMM_MASK; + } + return ret; +} + +static int enable_smi_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!gif_set(svm)) { + if (vgif_enabled(svm)) + set_intercept(svm, INTERCEPT_STGI); + /* STGI will cause a vm exit */ + return 1; + } + return 0; +} + static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -5503,6 +5606,11 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .deliver_posted_interrupt = svm_deliver_avic_intr, .update_pi_irte = svm_update_pi_irte, .setup_mce = svm_setup_mce, + + .smi_allowed = svm_smi_allowed, + .pre_enter_smm = svm_pre_enter_smm, + .pre_leave_smm = svm_pre_leave_smm, + .enable_smi_window = enable_smi_window, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 8a202c49e2a0..9807c314c478 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KVM_H diff --git a/arch/x86/kvm/tss.h b/arch/x86/kvm/tss.h index 622aa10f692f..3f9150125e70 100644 --- a/arch/x86/kvm/tss.h +++ b/arch/x86/kvm/tss.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __TSS_SEGMENT_H #define __TSS_SEGMENT_H diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 06c0c6d0541e..714a0673ec3c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -70,6 +70,9 @@ MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id); static bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); +static bool __read_mostly enable_vnmi = 1; +module_param_named(vnmi, enable_vnmi, bool, S_IRUGO); + static bool __read_mostly flexpriority_enabled = 1; module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO); @@ -200,6 +203,12 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; + unsigned long vmcs_host_cr3; /* May not match real cr3 */ + unsigned long vmcs_host_cr4; /* May not match real cr4 */ + /* Support for vnmi-less CPUs */ + int soft_vnmi_blocked; + ktime_t entry_time; + s64 vnmi_blocked_time; struct list_head loaded_vmcss_on_cpu_link; }; @@ -484,6 +493,14 @@ struct nested_vmx { u64 nested_vmx_cr4_fixed1; u64 nested_vmx_vmcs_enum; u64 nested_vmx_vmfunc_controls; + + /* SMM related state */ + struct { + /* in VMX operation on SMM entry? */ + bool vmxon; + /* in guest mode on SMM entry? */ + bool guest_mode; + } smm; }; #define POSTED_INTR_ON 0 @@ -600,8 +617,6 @@ struct vcpu_vmx { int gs_ldt_reload_needed; int fs_reload_needed; u64 msr_host_bndcfgs; - unsigned long vmcs_host_cr3; /* May not match real cr3 */ - unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { int vm86_active; @@ -900,16 +915,13 @@ static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu); static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu); static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa); static bool vmx_xsaves_supported(void); -static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); static void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); static bool guest_state_valid(struct kvm_vcpu *vcpu); static u32 vmx_segment_access_rights(struct kvm_segment *var); -static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); -static int alloc_identity_pagetable(struct kvm *kvm); static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, @@ -1286,6 +1298,11 @@ static inline bool cpu_has_vmx_invpcid(void) SECONDARY_EXEC_ENABLE_INVPCID; } +static inline bool cpu_has_virtual_nmis(void) +{ + return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS; +} + static inline bool cpu_has_vmx_wbinvd_exit(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -1343,11 +1360,6 @@ static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit) (vmcs12->secondary_vm_exec_control & bit); } -static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12) -{ - return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS; -} - static inline bool nested_cpu_has_preemption_timer(struct vmcs12 *vmcs12) { return vmcs12->pin_based_vm_exec_control & @@ -1598,18 +1610,15 @@ static inline void vpid_sync_context(int vpid) static inline void ept_sync_global(void) { - if (cpu_has_vmx_invept_global()) - __invept(VMX_EPT_EXTENT_GLOBAL, 0, 0); + __invept(VMX_EPT_EXTENT_GLOBAL, 0, 0); } static inline void ept_sync_context(u64 eptp) { - if (enable_ept) { - if (cpu_has_vmx_invept_context()) - __invept(VMX_EPT_EXTENT_CONTEXT, eptp, 0); - else - ept_sync_global(); - } + if (cpu_has_vmx_invept_context()) + __invept(VMX_EPT_EXTENT_CONTEXT, eptp, 0); + else + ept_sync_global(); } static __always_inline void vmcs_check16(unsigned long field) @@ -2202,46 +2211,44 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) struct pi_desc old, new; unsigned int dest; - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + /* + * In case of hot-plug or hot-unplug, we may have to undo + * vmx_vcpu_pi_put even if there is no assigned device. And we + * always keep PI.NDST up to date for simplicity: it makes the + * code easier, and CPU migration is not a fast path. + */ + if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; + /* + * First handle the simple case where no cmpxchg is necessary; just + * allow posting non-urgent interrupts. + * + * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change + * PI.NDST: pi_post_block will do it for us and the wakeup_handler + * expects the VCPU to be on the blocked_vcpu_list that matches + * PI.NDST. + */ + if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || + vcpu->cpu == cpu) { + pi_clear_sn(pi_desc); + return; + } + + /* The full case. */ do { old.control = new.control = pi_desc->control; - /* - * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there - * are two possible cases: - * 1. After running 'pre_block', context switch - * happened. For this case, 'sn' was set in - * vmx_vcpu_put(), so we need to clear it here. - * 2. After running 'pre_block', we were blocked, - * and woken up by some other guy. For this case, - * we don't need to do anything, 'pi_post_block' - * will do everything for us. However, we cannot - * check whether it is case #1 or case #2 here - * (maybe, not needed), so we also clear sn here, - * I think it is not a big deal. - */ - if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) { - if (vcpu->cpu != cpu) { - dest = cpu_physical_id(cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - } + dest = cpu_physical_id(cpu); - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; - /* Allow posting non-urgent interrupts */ new.sn = 0; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); } static void decache_tsc_multiplier(struct vcpu_vmx *vmx) @@ -2833,8 +2840,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) SECONDARY_EXEC_ENABLE_PML; vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT; } - } else - vmx->nested.nested_vmx_ept_caps = 0; + } if (cpu_has_vmx_vmfunc()) { vmx->nested.nested_vmx_secondary_ctls_high |= @@ -2843,8 +2849,9 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) * Advertise EPTP switching unconditionally * since we emulate it */ - vmx->nested.nested_vmx_vmfunc_controls = - VMX_VMFUNC_EPTP_SWITCHING; + if (enable_ept) + vmx->nested.nested_vmx_vmfunc_controls = + VMX_VMFUNC_EPTP_SWITCHING; } /* @@ -2858,8 +2865,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) SECONDARY_EXEC_ENABLE_VPID; vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | VMX_VPID_EXTENT_SUPPORTED_MASK; - } else - vmx->nested.nested_vmx_vpid_caps = 0; + } if (enable_unrestricted_guest) vmx->nested.nested_vmx_secondary_ctls_high |= @@ -3546,7 +3552,8 @@ static int hardware_enable(void) wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits); } kvm_cpu_vmxon(phys_addr); - ept_sync_global(); + if (enable_ept) + ept_sync_global(); return 0; } @@ -3659,8 +3666,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_SHADOW_VMCS | SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_RDSEED | - SECONDARY_EXEC_RDRAND | + SECONDARY_EXEC_RDSEED_EXITING | + SECONDARY_EXEC_RDRAND_EXITING | SECONDARY_EXEC_ENABLE_PML | SECONDARY_EXEC_TSC_SCALING | SECONDARY_EXEC_ENABLE_VMFUNC; @@ -3681,14 +3688,25 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); + rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP, + &vmx_capability.ept, &vmx_capability.vpid); + if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) { /* CR3 accesses and invlpg don't need to cause VM Exits when EPT enabled */ _cpu_based_exec_control &= ~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | CPU_BASED_INVLPG_EXITING); - rdmsr(MSR_IA32_VMX_EPT_VPID_CAP, - vmx_capability.ept, vmx_capability.vpid); + } else if (vmx_capability.ept) { + vmx_capability.ept = 0; + pr_warn_once("EPT CAP should not exist if not support " + "1-setting enable EPT VM-execution control\n"); + } + if (!(_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_VPID) && + vmx_capability.vpid) { + vmx_capability.vpid = 0; + pr_warn_once("VPID CAP should not exist if not support " + "1-setting enable VPID VM-execution control\n"); } min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT; @@ -3701,9 +3719,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) &_vmexit_control) < 0) return -EIO; - min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | - PIN_BASED_VIRTUAL_NMIS; - opt = PIN_BASED_POSTED_INTR | PIN_BASED_VMX_PREEMPTION_TIMER; + min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; + opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR | + PIN_BASED_VMX_PREEMPTION_TIMER; if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, &_pin_based_exec_control) < 0) return -EIO; @@ -4783,18 +4801,18 @@ static int init_rmode_identity_map(struct kvm *kvm) kvm_pfn_t identity_map_pfn; u32 tmp; - if (!enable_ept) - return 0; - /* Protect kvm->arch.ept_identity_pagetable_done. */ mutex_lock(&kvm->slots_lock); if (likely(kvm->arch.ept_identity_pagetable_done)) goto out2; + if (!kvm->arch.ept_identity_map_addr) + kvm->arch.ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR; identity_map_pfn = kvm->arch.ept_identity_map_addr >> PAGE_SHIFT; - r = alloc_identity_pagetable(kvm); + r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, + kvm->arch.ept_identity_map_addr, PAGE_SIZE); if (r < 0) goto out2; @@ -4866,20 +4884,6 @@ out: return r; } -static int alloc_identity_pagetable(struct kvm *kvm) -{ - /* Called with kvm->slots_lock held. */ - - int r = 0; - - BUG_ON(kvm->arch.ept_identity_pagetable_done); - - r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, - kvm->arch.ept_identity_map_addr, PAGE_SIZE); - - return r; -} - static int allocate_vpid(void) { int vpid; @@ -5077,21 +5081,30 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR; if (vcpu->mode == IN_GUEST_MODE) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * Currently, we don't support urgent interrupt, - * all interrupts are recognized as non-urgent - * interrupt, so we cannot post interrupts when - * 'SN' is set. + * The vector of interrupt to be delivered to vcpu had + * been set in PIR before this function. + * + * Following cases will be reached in this block, and + * we always send a notification event in all cases as + * explained below. * - * If the vcpu is in guest mode, it means it is - * running instead of being scheduled out and - * waiting in the run queue, and that's the only - * case when 'SN' is set currently, warning if - * 'SN' is set. + * Case 1: vcpu keeps in non-root mode. Sending a + * notification event posts the interrupt to vcpu. + * + * Case 2: vcpu exits to root mode and is still + * runnable. PIR will be synced to vIRR before the + * next vcpu entry. Sending a notification event in + * this case has no effect, as vcpu is not in root + * mode. + * + * Case 3: vcpu exits to root mode and is blocked. + * vcpu_block() has already synced PIR to vIRR and + * never blocks vcpu if vIRR is not cleared. Therefore, + * a blocked vcpu here does not wait for any requested + * interrupts in PIR, and sending a notification event + * which has no effect is safe here. */ - WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc)); apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); return true; @@ -5169,12 +5182,12 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) */ cr3 = __read_cr3(); vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 @@ -5226,6 +5239,10 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) if (!kvm_vcpu_apicv_active(&vmx->vcpu)) pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; + + if (!enable_vnmi) + pin_based_exec_ctrl &= ~PIN_BASED_VIRTUAL_NMIS; + /* Enable the preemption timer dynamically */ pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER; return pin_based_exec_ctrl; @@ -5275,13 +5292,13 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) static bool vmx_rdrand_supported(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & - SECONDARY_EXEC_RDRAND; + SECONDARY_EXEC_RDRAND_EXITING; } static bool vmx_rdseed_supported(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & - SECONDARY_EXEC_RDSEED; + SECONDARY_EXEC_RDSEED_EXITING; } static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) @@ -5375,30 +5392,30 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) if (vmx_rdrand_supported()) { bool rdrand_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDRAND); if (rdrand_enabled) - exec_control &= ~SECONDARY_EXEC_RDRAND; + exec_control &= ~SECONDARY_EXEC_RDRAND_EXITING; if (nested) { if (rdrand_enabled) vmx->nested.nested_vmx_secondary_ctls_high |= - SECONDARY_EXEC_RDRAND; + SECONDARY_EXEC_RDRAND_EXITING; else vmx->nested.nested_vmx_secondary_ctls_high &= - ~SECONDARY_EXEC_RDRAND; + ~SECONDARY_EXEC_RDRAND_EXITING; } } if (vmx_rdseed_supported()) { bool rdseed_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDSEED); if (rdseed_enabled) - exec_control &= ~SECONDARY_EXEC_RDSEED; + exec_control &= ~SECONDARY_EXEC_RDSEED_EXITING; if (nested) { if (rdseed_enabled) vmx->nested.nested_vmx_secondary_ctls_high |= - SECONDARY_EXEC_RDSEED; + SECONDARY_EXEC_RDSEED_EXITING; else vmx->nested.nested_vmx_secondary_ctls_high &= - ~SECONDARY_EXEC_RDSEED; + ~SECONDARY_EXEC_RDSEED_EXITING; } } @@ -5419,7 +5436,7 @@ static void ept_set_mmio_spte_mask(void) /* * Sets up the vmcs for emulated real mode. */ -static int vmx_vcpu_setup(struct vcpu_vmx *vmx) +static void vmx_vcpu_setup(struct vcpu_vmx *vmx) { #ifdef CONFIG_X86_64 unsigned long a; @@ -5532,8 +5549,6 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); } - - return 0; } static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -5597,6 +5612,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0); + if (kvm_mpx_supported()) + vmcs_write64(GUEST_BNDCFGS, 0); setup_msrs(vmx); @@ -5612,9 +5629,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - if (kvm_vcpu_apicv_active(vcpu)) - memset(&vmx->pi_desc, 0, sizeof(struct pi_desc)); - if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); @@ -5663,7 +5677,8 @@ static void enable_irq_window(struct kvm_vcpu *vcpu) static void enable_nmi_window(struct kvm_vcpu *vcpu) { - if (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { + if (!enable_vnmi || + vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { enable_irq_window(vcpu); return; } @@ -5703,6 +5718,19 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (!enable_vnmi) { + /* + * Tracking the NMI-blocked state in software is built upon + * finding the next open IRQ window. This, in turn, depends on + * well-behaving guests: They have to keep IRQs disabled at + * least as long as the NMI handler runs. Otherwise we may + * cause NMI nesting, maybe breaking the guest. But as this is + * highly unlikely, we can live with the residual risk. + */ + vmx->loaded_vmcs->soft_vnmi_blocked = 1; + vmx->loaded_vmcs->vnmi_blocked_time = 0; + } + ++vcpu->stat.nmi_injections; vmx->loaded_vmcs->nmi_known_unmasked = false; @@ -5721,6 +5749,8 @@ static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); bool masked; + if (!enable_vnmi) + return vmx->loaded_vmcs->soft_vnmi_blocked; if (vmx->loaded_vmcs->nmi_known_unmasked) return false; masked = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_NMI; @@ -5732,13 +5762,20 @@ static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) { struct vcpu_vmx *vmx = to_vmx(vcpu); - vmx->loaded_vmcs->nmi_known_unmasked = !masked; - if (masked) - vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); - else - vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); + if (!enable_vnmi) { + if (vmx->loaded_vmcs->soft_vnmi_blocked != masked) { + vmx->loaded_vmcs->soft_vnmi_blocked = masked; + vmx->loaded_vmcs->vnmi_blocked_time = 0; + } + } else { + vmx->loaded_vmcs->nmi_known_unmasked = !masked; + if (masked) + vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + else + vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + } } static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) @@ -5746,6 +5783,10 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) if (to_vmx(vcpu)->nested.nested_run_pending) return 0; + if (!enable_vnmi && + to_vmx(vcpu)->loaded_vmcs->soft_vnmi_blocked) + return 0; + return !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & (GUEST_INTR_STATE_MOV_SS | GUEST_INTR_STATE_STI | GUEST_INTR_STATE_NMI)); @@ -5908,8 +5949,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) cr2 = vmcs_readl(EXIT_QUALIFICATION); /* EPT won't cause page fault directly */ WARN_ON_ONCE(!vcpu->arch.apf.host_apf_reason && enable_ept); - return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0, - true); + return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0); } ex_no = intr_info & INTR_INFO_VECTOR_MASK; @@ -6474,6 +6514,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) * AAK134, BY25. */ if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && + enable_vnmi && (exit_qualification & INTR_INFO_UNBLOCK_NMI)) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); @@ -6533,6 +6574,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) static int handle_nmi_window(struct kvm_vcpu *vcpu) { + WARN_ON_ONCE(!enable_vnmi); vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_VIRTUAL_NMI_PENDING); ++vcpu->stat.nmi_window_exits; @@ -6743,21 +6785,22 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_ept() || !cpu_has_vmx_ept_4levels() || - !cpu_has_vmx_ept_mt_wb()) { + !cpu_has_vmx_ept_mt_wb() || + !cpu_has_vmx_invept_global()) enable_ept = 0; - enable_unrestricted_guest = 0; - enable_ept_ad_bits = 0; - } if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) enable_ept_ad_bits = 0; - if (!cpu_has_vmx_unrestricted_guest()) + if (!cpu_has_vmx_unrestricted_guest() || !enable_ept) enable_unrestricted_guest = 0; if (!cpu_has_vmx_flexpriority()) flexpriority_enabled = 0; + if (!cpu_has_virtual_nmis()) + enable_vnmi = 0; + /* * set_apic_access_page_addr() is used to reload apic access * page upon invalidation. No need to do anything if not @@ -6772,8 +6815,13 @@ static __init int hardware_setup(void) if (enable_ept && !cpu_has_vmx_ept_2m_page()) kvm_disable_largepages(); - if (!cpu_has_vmx_ple()) + if (!cpu_has_vmx_ple()) { ple_gap = 0; + ple_window = 0; + ple_window_grow = 0; + ple_window_max = 0; + ple_window_shrink = 0; + } if (!cpu_has_vmx_apicv()) { enable_apicv = 0; @@ -6957,7 +7005,7 @@ static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) } /* Create a new VMCS */ - item = kmalloc(sizeof(struct vmcs02_list), GFP_KERNEL); + item = kzalloc(sizeof(struct vmcs02_list), GFP_KERNEL); if (!item) return NULL; item->vmcs02.vmcs = alloc_vmcs(); @@ -7974,6 +8022,7 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) * "blocked by NMI" bit has to be set before next VM entry. */ if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && + enable_vnmi && (exit_qualification & INTR_INFO_UNBLOCK_NMI)) vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI); @@ -8411,9 +8460,9 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) case EXIT_REASON_RDPMC: return nested_cpu_has(vmcs12, CPU_BASED_RDPMC_EXITING); case EXIT_REASON_RDRAND: - return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDRAND); + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDRAND_EXITING); case EXIT_REASON_RDSEED: - return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDSEED); + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDSEED_EXITING); case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP: return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING); case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR: @@ -8818,6 +8867,25 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) return 0; } + if (unlikely(!enable_vnmi && + vmx->loaded_vmcs->soft_vnmi_blocked)) { + if (vmx_interrupt_allowed(vcpu)) { + vmx->loaded_vmcs->soft_vnmi_blocked = 0; + } else if (vmx->loaded_vmcs->vnmi_blocked_time > 1000000000LL && + vcpu->arch.nmi_pending) { + /* + * This CPU don't support us in finding the end of an + * NMI-blocked window if the guest runs with IRQs + * disabled. So we pull the trigger after 1 s of + * futile waiting, but inform the user about this. + */ + printk(KERN_WARNING "%s: Breaking out of NMI-blocked " + "state on VCPU %d after 1 s timeout\n", + __func__, vcpu->vcpu_id); + vmx->loaded_vmcs->soft_vnmi_blocked = 0; + } + } + if (exit_reason < kvm_vmx_max_exit_handlers && kvm_vmx_exit_handlers[exit_reason]) return kvm_vmx_exit_handlers[exit_reason](vcpu); @@ -9036,7 +9104,6 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) { u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - register void *__sp asm(_ASM_SP); if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) { @@ -9065,7 +9132,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 [sp]"=&r"(tmp), #endif - "+r"(__sp) + ASM_CALL_CONSTRAINT : [entry]"r"(entry), [ss]"i"(__KERNEL_DS), @@ -9101,33 +9168,38 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK; - if (vmx->loaded_vmcs->nmi_known_unmasked) - return; - /* - * Can't use vmx->exit_intr_info since we're not sure what - * the exit reason is. - */ - exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0; - vector = exit_intr_info & INTR_INFO_VECTOR_MASK; - /* - * SDM 3: 27.7.1.2 (September 2008) - * Re-set bit "block by NMI" before VM entry if vmexit caused by - * a guest IRET fault. - * SDM 3: 23.2.2 (September 2008) - * Bit 12 is undefined in any of the following cases: - * If the VM exit sets the valid bit in the IDT-vectoring - * information field. - * If the VM exit is due to a double fault. - */ - if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi && - vector != DF_VECTOR && !idtv_info_valid) - vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, - GUEST_INTR_STATE_NMI); - else - vmx->loaded_vmcs->nmi_known_unmasked = - !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) - & GUEST_INTR_STATE_NMI); + if (enable_vnmi) { + if (vmx->loaded_vmcs->nmi_known_unmasked) + return; + /* + * Can't use vmx->exit_intr_info since we're not sure what + * the exit reason is. + */ + exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); + unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0; + vector = exit_intr_info & INTR_INFO_VECTOR_MASK; + /* + * SDM 3: 27.7.1.2 (September 2008) + * Re-set bit "block by NMI" before VM entry if vmexit caused by + * a guest IRET fault. + * SDM 3: 23.2.2 (September 2008) + * Bit 12 is undefined in any of the following cases: + * If the VM exit sets the valid bit in the IDT-vectoring + * information field. + * If the VM exit is due to a double fault. + */ + if ((exit_intr_info & INTR_INFO_VALID_MASK) && unblock_nmi && + vector != DF_VECTOR && !idtv_info_valid) + vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + else + vmx->loaded_vmcs->nmi_known_unmasked = + !(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) + & GUEST_INTR_STATE_NMI); + } else if (unlikely(vmx->loaded_vmcs->soft_vnmi_blocked)) + vmx->loaded_vmcs->vnmi_blocked_time += + ktime_to_ns(ktime_sub(ktime_get(), + vmx->loaded_vmcs->entry_time)); } static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, @@ -9244,6 +9316,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long debugctlmsr, cr3, cr4; + /* Record the guest's net vcpu time for enforced NMI injections. */ + if (unlikely(!enable_vnmi && + vmx->loaded_vmcs->soft_vnmi_blocked)) + vmx->loaded_vmcs->entry_time = ktime_get(); + /* Don't enter VMX if guest state is invalid, let the exit handler start emulation until we arrive back to a valid state */ if (vmx->emulation_required) @@ -9265,15 +9342,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); cr3 = __get_current_cr3_fast(); - if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) { + if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) { vmcs_writel(HOST_CR3, cr3); - vmx->host_state.vmcs_host_cr3 = cr3; + vmx->loaded_vmcs->vmcs_host_cr3 = cr3; } cr4 = cr4_read_shadow(); - if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { + if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) { vmcs_writel(HOST_CR4, cr4); - vmx->host_state.vmcs_host_cr4 = cr4; + vmx->loaded_vmcs->vmcs_host_cr4 = cr4; } /* When single-stepping over STI and MOV SS, we must clear the @@ -9472,7 +9549,6 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) vmx->loaded_vmcs = vmcs; vmx_vcpu_put(vcpu); vmx_vcpu_load(vcpu, cpu); - vcpu->cpu = cpu; put_cpu(); } @@ -9553,11 +9629,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); vmx->vcpu.cpu = cpu; - err = vmx_vcpu_setup(vmx); + vmx_vcpu_setup(vmx); vmx_vcpu_put(&vmx->vcpu); put_cpu(); - if (err) - goto free_vmcs; if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { err = alloc_apic_access_page(kvm); if (err) @@ -9565,9 +9639,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) } if (enable_ept) { - if (!kvm->arch.ept_identity_map_addr) - kvm->arch.ept_identity_map_addr = - VMX_EPT_IDENTITY_PAGETABLE_ADDR; err = init_rmode_identity_map(kvm); if (err) goto free_vmcs; @@ -9583,6 +9654,13 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED; + /* + * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR + * or POSTED_INTR_WAKEUP_VECTOR. + */ + vmx->pi_desc.nv = POSTED_INTR_VECTOR; + vmx->pi_desc.sn = 1; + return &vmx->vcpu; free_vmcs: @@ -9831,7 +9909,8 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, WARN_ON(!is_guest_mode(vcpu)); - if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) { + if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) && + !to_vmx(vcpu)->nested.nested_run_pending) { vmcs12->vm_exit_intr_error_code = fault->error_code; nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, PF_VECTOR | INTR_TYPE_HARD_EXCEPTION | @@ -11283,7 +11362,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, /* Same as above - no reason to call set_cr4_guest_host_mask(). */ vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); - kvm_set_cr4(vcpu, vmcs12->host_cr4); + vmx_set_cr4(vcpu, vmcs12->host_cr4); nested_ept_uninit_mmu_context(vcpu); @@ -11314,6 +11393,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip); vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base); vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base); + vmcs_write32(GUEST_IDTR_LIMIT, 0xFFFF); + vmcs_write32(GUEST_GDTR_LIMIT, 0xFFFF); /* If not VM_EXIT_CLEAR_BNDCFGS, the L2 value propagates to L1. */ if (vmcs12->vm_exit_controls & VM_EXIT_CLEAR_BNDCFGS) @@ -11410,8 +11491,11 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, leave_guest_mode(vcpu); if (likely(!vmx->fail)) { - prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, - exit_qualification); + if (exit_reason == -1) + sync_vmcs12(vcpu, vmcs12); + else + prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, + exit_qualification); if (nested_vmx_store_msr(vcpu, vmcs12->vm_exit_msr_store_addr, vmcs12->vm_exit_msr_store_count)) @@ -11475,7 +11559,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, */ kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - if (enable_shadow_vmcs) + if (enable_shadow_vmcs && exit_reason != -1) vmx->nested.sync_shadow_vmcs = true; /* in case we halted in L2 */ @@ -11499,12 +11583,13 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR; } - trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, - vmcs12->exit_qualification, - vmcs12->idt_vectoring_info_field, - vmcs12->vm_exit_intr_info, - vmcs12->vm_exit_intr_error_code, - KVM_ISA_VMX); + if (exit_reason != -1) + trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, + vmcs12->exit_qualification, + vmcs12->idt_vectoring_info_field, + vmcs12->vm_exit_intr_info, + vmcs12->vm_exit_intr_error_code, + KVM_ISA_VMX); load_vmcs12_host_state(vcpu, vmcs12); @@ -11696,6 +11781,37 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); } +static void __pi_post_block(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + + do { + old.control = new.control = pi_desc->control; + WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR, + "Wakeup handler not enabled while the VCPU is blocked\n"); + + dest = cpu_physical_id(vcpu->cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); + + if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) { + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + vcpu->pre_pcpu = -1; + } +} + /* * This routine does the following things for vCPU which is going * to be blocked if VT-d PI is enabled. @@ -11711,7 +11827,6 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, */ static int pi_pre_block(struct kvm_vcpu *vcpu) { - unsigned long flags; unsigned int dest; struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); @@ -11721,34 +11836,20 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) !kvm_vcpu_apicv_active(vcpu)) return 0; - vcpu->pre_pcpu = vcpu->cpu; - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, - vcpu->pre_pcpu)); - spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); + WARN_ON(irqs_disabled()); + local_irq_disable(); + if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) { + vcpu->pre_pcpu = vcpu->cpu; + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, + vcpu->pre_pcpu)); + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu)); + } do { old.control = new.control = pi_desc->control; - /* - * We should not block the vCPU if - * an interrupt is posted for it. - */ - if (pi_test_on(pi_desc) == 1) { - spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - - return 1; - } - WARN((pi_desc->sn == 1), "Warning: SN field of posted-interrupts " "is set before blocking\n"); @@ -11770,10 +11871,15 @@ static int pi_pre_block(struct kvm_vcpu *vcpu) /* set 'NV' to 'wakeup vector' */ new.nv = POSTED_INTR_WAKEUP_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); + } while (cmpxchg64(&pi_desc->control, old.control, + new.control) != old.control); - return 0; + /* We should not block the vCPU if an interrupt is posted for it. */ + if (pi_test_on(pi_desc) == 1) + __pi_post_block(vcpu); + + local_irq_enable(); + return (vcpu->pre_pcpu == -1); } static int vmx_pre_block(struct kvm_vcpu *vcpu) @@ -11789,44 +11895,13 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu) static void pi_post_block(struct kvm_vcpu *vcpu) { - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); - struct pi_desc old, new; - unsigned int dest; - unsigned long flags; - - if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (vcpu->pre_pcpu == -1) return; - do { - old.control = new.control = pi_desc->control; - - dest = cpu_physical_id(vcpu->cpu); - - if (x2apic_enabled()) - new.ndst = dest; - else - new.ndst = (dest << 8) & 0xFF00; - - /* Allow posting non-urgent interrupts */ - new.sn = 0; - - /* set 'NV' to 'notification vector' */ - new.nv = POSTED_INTR_VECTOR; - } while (cmpxchg(&pi_desc->control, old.control, - new.control) != old.control); - - if(vcpu->pre_pcpu != -1) { - spin_lock_irqsave( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - list_del(&vcpu->blocked_vcpu_list); - spin_unlock_irqrestore( - &per_cpu(blocked_vcpu_on_cpu_lock, - vcpu->pre_pcpu), flags); - vcpu->pre_pcpu = -1; - } + WARN_ON(irqs_disabled()); + local_irq_disable(); + __pi_post_block(vcpu); + local_irq_enable(); } static void vmx_post_block(struct kvm_vcpu *vcpu) @@ -11911,12 +11986,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, if (set) ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); - else { - /* suppress notification event before unposting */ - pi_set_sn(vcpu_to_pi_desc(vcpu)); + else ret = irq_set_vcpu_affinity(host_irq, NULL); - pi_clear_sn(vcpu_to_pi_desc(vcpu)); - } if (ret < 0) { printk(KERN_INFO "%s: failed to update PI IRTE\n", @@ -11941,6 +12012,54 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) ~FEATURE_CONTROL_LMCE; } +static int vmx_smi_allowed(struct kvm_vcpu *vcpu) +{ + /* we need a nested vmexit to enter SMM, postpone if run is pending */ + if (to_vmx(vcpu)->nested.nested_run_pending) + return 0; + return 1; +} + +static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + vmx->nested.smm.guest_mode = is_guest_mode(vcpu); + if (vmx->nested.smm.guest_mode) + nested_vmx_vmexit(vcpu, -1, 0, 0); + + vmx->nested.smm.vmxon = vmx->nested.vmxon; + vmx->nested.vmxon = false; + return 0; +} + +static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int ret; + + if (vmx->nested.smm.vmxon) { + vmx->nested.vmxon = true; + vmx->nested.smm.vmxon = false; + } + + if (vmx->nested.smm.guest_mode) { + vcpu->arch.hflags &= ~HF_SMM_MASK; + ret = enter_vmx_non_root_mode(vcpu, false); + vcpu->arch.hflags |= HF_SMM_MASK; + if (ret) + return ret; + + vmx->nested.smm.guest_mode = false; + } + return 0; +} + +static int enable_smi_window(struct kvm_vcpu *vcpu) +{ + return 0; +} + static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -12066,6 +12185,11 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { #endif .setup_mce = vmx_setup_mce, + + .smi_allowed = vmx_smi_allowed, + .pre_enter_smm = vmx_pre_enter_smm, + .pre_leave_smm = vmx_pre_leave_smm, + .enable_smi_window = enable_smi_window, }; static int __init vmx_init(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cd17b7d9a107..34c85aa2e2d1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2006,10 +2006,12 @@ static void kvmclock_sync_fn(struct work_struct *work) KVMCLOCK_SYNC_PERIOD); } -static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) +static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u64 mcg_cap = vcpu->arch.mcg_cap; unsigned bank_num = mcg_cap & 0xff; + u32 msr = msr_info->index; + u64 data = msr_info->data; switch (msr) { case MSR_IA32_MCG_STATUS: @@ -2034,6 +2036,9 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) if ((offset & 0x3) == 0 && data != 0 && (data | (1 << 10)) != ~(u64)0) return -1; + if (!msr_info->host_initiated && + (offset & 0x3) == 1 && data != 0) + return -1; vcpu->arch.mce_banks[offset] = data; break; } @@ -2283,7 +2288,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: - return set_msr_mce(vcpu, msr, data); + return set_msr_mce(vcpu, msr_info); case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: @@ -4034,10 +4039,16 @@ long kvm_arch_vm_ioctl(struct file *filp, case KVM_SET_IDENTITY_MAP_ADDR: { u64 ident_addr; + mutex_lock(&kvm->lock); + r = -EINVAL; + if (kvm->created_vcpus) + goto set_identity_unlock; r = -EFAULT; if (copy_from_user(&ident_addr, argp, sizeof ident_addr)) - goto out; + goto set_identity_unlock; r = kvm_vm_ioctl_set_identity_map_addr(kvm, ident_addr); +set_identity_unlock: + mutex_unlock(&kvm->lock); break; } case KVM_SET_NR_MMU_PAGES: @@ -5275,6 +5286,11 @@ static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_fla kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags); } +static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase) +{ + return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase); +} + static const struct x86_emulate_ops emulate_ops = { .read_gpr = emulator_read_gpr, .write_gpr = emulator_write_gpr, @@ -5316,6 +5332,7 @@ static const struct x86_emulate_ops emulate_ops = { .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, .set_hflags = emulator_set_hflags, + .pre_leave_smm = emulator_pre_leave_smm, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -6426,7 +6443,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) } kvm_x86_ops->queue_exception(vcpu); - } else if (vcpu->arch.smi_pending && !is_smm(vcpu)) { + } else if (vcpu->arch.smi_pending && !is_smm(vcpu) && kvm_x86_ops->smi_allowed(vcpu)) { vcpu->arch.smi_pending = false; enter_smm(vcpu); } else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { @@ -6473,9 +6490,6 @@ static void process_nmi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } -#define put_smstate(type, buf, offset, val) \ - *(type *)((buf) + (offset) - 0x7e00) = val - static u32 enter_smm_get_segment_flags(struct kvm_segment *seg) { u32 flags = 0; @@ -6641,13 +6655,20 @@ static void enter_smm(struct kvm_vcpu *vcpu) u32 cr0; trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true); - vcpu->arch.hflags |= HF_SMM_MASK; memset(buf, 0, 512); if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) enter_smm_save_state_64(vcpu, buf); else enter_smm_save_state_32(vcpu, buf); + /* + * Give pre_enter_smm() a chance to make ISA-specific changes to the + * vCPU state (e.g. leave guest mode) after we've saved the state into + * the SMM state-save area. + */ + kvm_x86_ops->pre_enter_smm(vcpu, buf); + + vcpu->arch.hflags |= HF_SMM_MASK; kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); if (kvm_x86_ops->get_nmi_mask(vcpu)) @@ -6876,17 +6897,23 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (inject_pending_event(vcpu, req_int_win) != 0) req_immediate_exit = true; else { - /* Enable NMI/IRQ window open exits if needed. + /* Enable SMI/NMI/IRQ window open exits if needed. * - * SMIs have two cases: 1) they can be nested, and - * then there is nothing to do here because RSM will - * cause a vmexit anyway; 2) or the SMI can be pending - * because inject_pending_event has completed the - * injection of an IRQ or NMI from the previous vmexit, - * and then we request an immediate exit to inject the SMI. + * SMIs have three cases: + * 1) They can be nested, and then there is nothing to + * do here because RSM will cause a vmexit anyway. + * 2) There is an ISA-specific reason why SMI cannot be + * injected, and the moment when this changes can be + * intercepted. + * 3) Or the SMI can be pending because + * inject_pending_event has completed the injection + * of an IRQ or NMI from the previous vmexit, and + * then we request an immediate exit to inject the + * SMI. */ if (vcpu->arch.smi_pending && !is_smm(vcpu)) - req_immediate_exit = true; + if (!kvm_x86_ops->enable_smi_window(vcpu)) + req_immediate_exit = true; if (vcpu->arch.nmi_pending) kvm_x86_ops->enable_nmi_window(vcpu); if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) @@ -7225,7 +7252,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int r; sigset_t sigsaved; - fpu__activate_curr(fpu); + fpu__initialize(fpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); @@ -7798,18 +7825,40 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; + if (kvm_mpx_supported()) { + void *mpx_state_buffer; + + /* + * To avoid have the INIT path from kvm_apic_has_events() that be + * called with loaded FPU and does not let userspace fix the state. + */ + kvm_put_guest_fpu(vcpu); + mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu.state.xsave, + XFEATURE_MASK_BNDREGS); + if (mpx_state_buffer) + memset(mpx_state_buffer, 0, sizeof(struct mpx_bndreg_state)); + mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu.state.xsave, + XFEATURE_MASK_BNDCSR); + if (mpx_state_buffer) + memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr)); + } + if (!init_event) { kvm_pmu_reset(vcpu); vcpu->arch.smbase = 0x30000; vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; vcpu->arch.msr_misc_features_enables = 0; + + vcpu->arch.xcr0 = XFEATURE_MASK_FP; } memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; + vcpu->arch.ia32_xss = 0; + kvm_x86_ops->vcpu_reset(vcpu, init_event); } @@ -7974,16 +8023,11 @@ EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu); int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { struct page *page; - struct kvm *kvm; int r; - BUG_ON(vcpu->kvm == NULL); - kvm = vcpu->kvm; - vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); - vcpu->arch.pv.pv_unhalted = false; vcpu->arch.emulate_ctxt.ops = &emulate_ops; - if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu)) + if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; @@ -8001,7 +8045,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) if (r < 0) goto fail_free_pio_data; - if (irqchip_in_kernel(kvm)) { + if (irqchip_in_kernel(vcpu->kvm)) { r = kvm_create_lapic(vcpu); if (r < 0) goto fail_mmu_destroy; @@ -8023,10 +8067,6 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) fx_init(vcpu); - vcpu->arch.ia32_tsc_adjust_msr = 0x0; - vcpu->arch.pv_time_enabled = false; - - vcpu->arch.guest_supported_xcr0 = 0; vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 51e349cf5f45..d0b95b7a90b4 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ARCH_X86_KVM_X86_H #define ARCH_X86_KVM_X86_H diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 34a74131a12c..7b181b61170e 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for x86 specific library files. # @@ -23,7 +24,7 @@ lib-y := delay.o misc.o cmdline.o cpu.o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o -lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o +lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c index 216a629a4a1a..1811fa4a1b1a 100644 --- a/arch/x86/lib/cache-smp.c +++ b/arch/x86/lib/cache-smp.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/smp.h> #include <linux/export.h> diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index e8508156c99d..fd2d09afa097 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */ #include <linux/linkage.h> diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index 378e5d5bf9b1..9baca3e054be 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * arch/x86_64/lib/csum-partial.c * diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 29df077cb089..553f8fd23cc4 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Precise Delay Loops for i386 * diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 37b62d412148..c97d935a29e8 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * __get_user functions. * diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S index 23d893cbc200..a14f9939c365 100644 --- a/arch/x86/lib/hweight.S +++ b/arch/x86/lib/hweight.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <asm/export.h> diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c new file mode 100644 index 000000000000..9119d8e41f1f --- /dev/null +++ b/arch/x86/lib/insn-eval.c @@ -0,0 +1,1364 @@ +/* + * Utility functions for x86 operand and address decoding + * + * Copyright (C) Intel Corporation 2017 + */ +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/ratelimit.h> +#include <linux/mmu_context.h> +#include <asm/desc_defs.h> +#include <asm/desc.h> +#include <asm/inat.h> +#include <asm/insn.h> +#include <asm/insn-eval.h> +#include <asm/ldt.h> +#include <asm/vm86.h> + +#undef pr_fmt +#define pr_fmt(fmt) "insn: " fmt + +enum reg_type { + REG_TYPE_RM = 0, + REG_TYPE_INDEX, + REG_TYPE_BASE, +}; + +/** + * is_string_insn() - Determine if instruction is a string instruction + * @insn: Instruction containing the opcode to inspect + * + * Returns: + * + * true if the instruction, determined by the opcode, is any of the + * string instructions as defined in the Intel Software Development manual. + * False otherwise. + */ +static bool is_string_insn(struct insn *insn) +{ + insn_get_opcode(insn); + + /* All string instructions have a 1-byte opcode. */ + if (insn->opcode.nbytes != 1) + return false; + + switch (insn->opcode.bytes[0]) { + case 0x6c ... 0x6f: /* INS, OUTS */ + case 0xa4 ... 0xa7: /* MOVS, CMPS */ + case 0xaa ... 0xaf: /* STOS, LODS, SCAS */ + return true; + default: + return false; + } +} + +/** + * get_seg_reg_override_idx() - obtain segment register override index + * @insn: Valid instruction with segment override prefixes + * + * Inspect the instruction prefixes in @insn and find segment overrides, if any. + * + * Returns: + * + * A constant identifying the segment register to use, among CS, SS, DS, + * ES, FS, or GS. INAT_SEG_REG_DEFAULT is returned if no segment override + * prefixes were found. + * + * -EINVAL in case of error. + */ +static int get_seg_reg_override_idx(struct insn *insn) +{ + int idx = INAT_SEG_REG_DEFAULT; + int num_overrides = 0, i; + + insn_get_prefixes(insn); + + /* Look for any segment override prefixes. */ + for (i = 0; i < insn->prefixes.nbytes; i++) { + insn_attr_t attr; + + attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]); + switch (attr) { + case INAT_MAKE_PREFIX(INAT_PFX_CS): + idx = INAT_SEG_REG_CS; + num_overrides++; + break; + case INAT_MAKE_PREFIX(INAT_PFX_SS): + idx = INAT_SEG_REG_SS; + num_overrides++; + break; + case INAT_MAKE_PREFIX(INAT_PFX_DS): + idx = INAT_SEG_REG_DS; + num_overrides++; + break; + case INAT_MAKE_PREFIX(INAT_PFX_ES): + idx = INAT_SEG_REG_ES; + num_overrides++; + break; + case INAT_MAKE_PREFIX(INAT_PFX_FS): + idx = INAT_SEG_REG_FS; + num_overrides++; + break; + case INAT_MAKE_PREFIX(INAT_PFX_GS): + idx = INAT_SEG_REG_GS; + num_overrides++; + break; + /* No default action needed. */ + } + } + + /* More than one segment override prefix leads to undefined behavior. */ + if (num_overrides > 1) + return -EINVAL; + + return idx; +} + +/** + * check_seg_overrides() - check if segment override prefixes are allowed + * @insn: Valid instruction with segment override prefixes + * @regoff: Operand offset, in pt_regs, for which the check is performed + * + * For a particular register used in register-indirect addressing, determine if + * segment override prefixes can be used. Specifically, no overrides are allowed + * for rDI if used with a string instruction. + * + * Returns: + * + * True if segment override prefixes can be used with the register indicated + * in @regoff. False if otherwise. + */ +static bool check_seg_overrides(struct insn *insn, int regoff) +{ + if (regoff == offsetof(struct pt_regs, di) && is_string_insn(insn)) + return false; + + return true; +} + +/** + * resolve_default_seg() - resolve default segment register index for an operand + * @insn: Instruction with opcode and address size. Must be valid. + * @regs: Register values as seen when entering kernel mode + * @off: Operand offset, in pt_regs, for which resolution is needed + * + * Resolve the default segment register index associated with the instruction + * operand register indicated by @off. Such index is resolved based on defaults + * described in the Intel Software Development Manual. + * + * Returns: + * + * If in protected mode, a constant identifying the segment register to use, + * among CS, SS, ES or DS. If in long mode, INAT_SEG_REG_IGNORE. + * + * -EINVAL in case of error. + */ +static int resolve_default_seg(struct insn *insn, struct pt_regs *regs, int off) +{ + if (user_64bit_mode(regs)) + return INAT_SEG_REG_IGNORE; + /* + * Resolve the default segment register as described in Section 3.7.4 + * of the Intel Software Development Manual Vol. 1: + * + * + DS for all references involving r[ABCD]X, and rSI. + * + If used in a string instruction, ES for rDI. Otherwise, DS. + * + AX, CX and DX are not valid register operands in 16-bit address + * encodings but are valid for 32-bit and 64-bit encodings. + * + -EDOM is reserved to identify for cases in which no register + * is used (i.e., displacement-only addressing). Use DS. + * + SS for rSP or rBP. + * + CS for rIP. + */ + + switch (off) { + case offsetof(struct pt_regs, ax): + case offsetof(struct pt_regs, cx): + case offsetof(struct pt_regs, dx): + /* Need insn to verify address size. */ + if (insn->addr_bytes == 2) + return -EINVAL; + + case -EDOM: + case offsetof(struct pt_regs, bx): + case offsetof(struct pt_regs, si): + return INAT_SEG_REG_DS; + + case offsetof(struct pt_regs, di): + if (is_string_insn(insn)) + return INAT_SEG_REG_ES; + return INAT_SEG_REG_DS; + + case offsetof(struct pt_regs, bp): + case offsetof(struct pt_regs, sp): + return INAT_SEG_REG_SS; + + case offsetof(struct pt_regs, ip): + return INAT_SEG_REG_CS; + + default: + return -EINVAL; + } +} + +/** + * resolve_seg_reg() - obtain segment register index + * @insn: Instruction with operands + * @regs: Register values as seen when entering kernel mode + * @regoff: Operand offset, in pt_regs, used to deterimine segment register + * + * Determine the segment register associated with the operands and, if + * applicable, prefixes and the instruction pointed by @insn. + * + * The segment register associated to an operand used in register-indirect + * addressing depends on: + * + * a) Whether running in long mode (in such a case segments are ignored, except + * if FS or GS are used). + * + * b) Whether segment override prefixes can be used. Certain instructions and + * registers do not allow override prefixes. + * + * c) Whether segment overrides prefixes are found in the instruction prefixes. + * + * d) If there are not segment override prefixes or they cannot be used, the + * default segment register associated with the operand register is used. + * + * The function checks first if segment override prefixes can be used with the + * operand indicated by @regoff. If allowed, obtain such overridden segment + * register index. Lastly, if not prefixes were found or cannot be used, resolve + * the segment register index to use based on the defaults described in the + * Intel documentation. In long mode, all segment register indexes will be + * ignored, except if overrides were found for FS or GS. All these operations + * are done using helper functions. + * + * The operand register, @regoff, is represented as the offset from the base of + * pt_regs. + * + * As stated, the main use of this function is to determine the segment register + * index based on the instruction, its operands and prefixes. Hence, @insn + * must be valid. However, if @regoff indicates rIP, we don't need to inspect + * @insn at all as in this case CS is used in all cases. This case is checked + * before proceeding further. + * + * Please note that this function does not return the value in the segment + * register (i.e., the segment selector) but our defined index. The segment + * selector needs to be obtained using get_segment_selector() and passing the + * segment register index resolved by this function. + * + * Returns: + * + * An index identifying the segment register to use, among CS, SS, DS, + * ES, FS, or GS. INAT_SEG_REG_IGNORE is returned if running in long mode. + * + * -EINVAL in case of error. + */ +static int resolve_seg_reg(struct insn *insn, struct pt_regs *regs, int regoff) +{ + int idx; + + /* + * In the unlikely event of having to resolve the segment register + * index for rIP, do it first. Segment override prefixes should not + * be used. Hence, it is not necessary to inspect the instruction, + * which may be invalid at this point. + */ + if (regoff == offsetof(struct pt_regs, ip)) { + if (user_64bit_mode(regs)) + return INAT_SEG_REG_IGNORE; + else + return INAT_SEG_REG_CS; + } + + if (!insn) + return -EINVAL; + + if (!check_seg_overrides(insn, regoff)) + return resolve_default_seg(insn, regs, regoff); + + idx = get_seg_reg_override_idx(insn); + if (idx < 0) + return idx; + + if (idx == INAT_SEG_REG_DEFAULT) + return resolve_default_seg(insn, regs, regoff); + + /* + * In long mode, segment override prefixes are ignored, except for + * overrides for FS and GS. + */ + if (user_64bit_mode(regs)) { + if (idx != INAT_SEG_REG_FS && + idx != INAT_SEG_REG_GS) + idx = INAT_SEG_REG_IGNORE; + } + + return idx; +} + +/** + * get_segment_selector() - obtain segment selector + * @regs: Register values as seen when entering kernel mode + * @seg_reg_idx: Segment register index to use + * + * Obtain the segment selector from any of the CS, SS, DS, ES, FS, GS segment + * registers. In CONFIG_X86_32, the segment is obtained from either pt_regs or + * kernel_vm86_regs as applicable. In CONFIG_X86_64, CS and SS are obtained + * from pt_regs. DS, ES, FS and GS are obtained by reading the actual CPU + * registers. This done for only for completeness as in CONFIG_X86_64 segment + * registers are ignored. + * + * Returns: + * + * Value of the segment selector, including null when running in + * long mode. + * + * -EINVAL on error. + */ +static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) +{ +#ifdef CONFIG_X86_64 + unsigned short sel; + + switch (seg_reg_idx) { + case INAT_SEG_REG_IGNORE: + return 0; + case INAT_SEG_REG_CS: + return (unsigned short)(regs->cs & 0xffff); + case INAT_SEG_REG_SS: + return (unsigned short)(regs->ss & 0xffff); + case INAT_SEG_REG_DS: + savesegment(ds, sel); + return sel; + case INAT_SEG_REG_ES: + savesegment(es, sel); + return sel; + case INAT_SEG_REG_FS: + savesegment(fs, sel); + return sel; + case INAT_SEG_REG_GS: + savesegment(gs, sel); + return sel; + default: + return -EINVAL; + } +#else /* CONFIG_X86_32 */ + struct kernel_vm86_regs *vm86regs = (struct kernel_vm86_regs *)regs; + + if (v8086_mode(regs)) { + switch (seg_reg_idx) { + case INAT_SEG_REG_CS: + return (unsigned short)(regs->cs & 0xffff); + case INAT_SEG_REG_SS: + return (unsigned short)(regs->ss & 0xffff); + case INAT_SEG_REG_DS: + return vm86regs->ds; + case INAT_SEG_REG_ES: + return vm86regs->es; + case INAT_SEG_REG_FS: + return vm86regs->fs; + case INAT_SEG_REG_GS: + return vm86regs->gs; + case INAT_SEG_REG_IGNORE: + /* fall through */ + default: + return -EINVAL; + } + } + + switch (seg_reg_idx) { + case INAT_SEG_REG_CS: + return (unsigned short)(regs->cs & 0xffff); + case INAT_SEG_REG_SS: + return (unsigned short)(regs->ss & 0xffff); + case INAT_SEG_REG_DS: + return (unsigned short)(regs->ds & 0xffff); + case INAT_SEG_REG_ES: + return (unsigned short)(regs->es & 0xffff); + case INAT_SEG_REG_FS: + return (unsigned short)(regs->fs & 0xffff); + case INAT_SEG_REG_GS: + /* + * GS may or may not be in regs as per CONFIG_X86_32_LAZY_GS. + * The macro below takes care of both cases. + */ + return get_user_gs(regs); + case INAT_SEG_REG_IGNORE: + /* fall through */ + default: + return -EINVAL; + } +#endif /* CONFIG_X86_64 */ +} + +static int get_reg_offset(struct insn *insn, struct pt_regs *regs, + enum reg_type type) +{ + int regno = 0; + + static const int regoff[] = { + offsetof(struct pt_regs, ax), + offsetof(struct pt_regs, cx), + offsetof(struct pt_regs, dx), + offsetof(struct pt_regs, bx), + offsetof(struct pt_regs, sp), + offsetof(struct pt_regs, bp), + offsetof(struct pt_regs, si), + offsetof(struct pt_regs, di), +#ifdef CONFIG_X86_64 + offsetof(struct pt_regs, r8), + offsetof(struct pt_regs, r9), + offsetof(struct pt_regs, r10), + offsetof(struct pt_regs, r11), + offsetof(struct pt_regs, r12), + offsetof(struct pt_regs, r13), + offsetof(struct pt_regs, r14), + offsetof(struct pt_regs, r15), +#endif + }; + int nr_registers = ARRAY_SIZE(regoff); + /* + * Don't possibly decode a 32-bit instructions as + * reading a 64-bit-only register. + */ + if (IS_ENABLED(CONFIG_X86_64) && !insn->x86_64) + nr_registers -= 8; + + switch (type) { + case REG_TYPE_RM: + regno = X86_MODRM_RM(insn->modrm.value); + + /* + * ModRM.mod == 0 and ModRM.rm == 5 means a 32-bit displacement + * follows the ModRM byte. + */ + if (!X86_MODRM_MOD(insn->modrm.value) && regno == 5) + return -EDOM; + + if (X86_REX_B(insn->rex_prefix.value)) + regno += 8; + break; + + case REG_TYPE_INDEX: + regno = X86_SIB_INDEX(insn->sib.value); + if (X86_REX_X(insn->rex_prefix.value)) + regno += 8; + + /* + * If ModRM.mod != 3 and SIB.index = 4 the scale*index + * portion of the address computation is null. This is + * true only if REX.X is 0. In such a case, the SIB index + * is used in the address computation. + */ + if (X86_MODRM_MOD(insn->modrm.value) != 3 && regno == 4) + return -EDOM; + break; + + case REG_TYPE_BASE: + regno = X86_SIB_BASE(insn->sib.value); + /* + * If ModRM.mod is 0 and SIB.base == 5, the base of the + * register-indirect addressing is 0. In this case, a + * 32-bit displacement follows the SIB byte. + */ + if (!X86_MODRM_MOD(insn->modrm.value) && regno == 5) + return -EDOM; + + if (X86_REX_B(insn->rex_prefix.value)) + regno += 8; + break; + + default: + pr_err_ratelimited("invalid register type: %d\n", type); + return -EINVAL; + } + + if (regno >= nr_registers) { + WARN_ONCE(1, "decoded an instruction with an invalid register"); + return -EINVAL; + } + return regoff[regno]; +} + +/** + * get_reg_offset_16() - Obtain offset of register indicated by instruction + * @insn: Instruction containing ModRM byte + * @regs: Register values as seen when entering kernel mode + * @offs1: Offset of the first operand register + * @offs2: Offset of the second opeand register, if applicable + * + * Obtain the offset, in pt_regs, of the registers indicated by the ModRM byte + * in @insn. This function is to be used with 16-bit address encodings. The + * @offs1 and @offs2 will be written with the offset of the two registers + * indicated by the instruction. In cases where any of the registers is not + * referenced by the instruction, the value will be set to -EDOM. + * + * Returns: + * + * 0 on success, -EINVAL on error. + */ +static int get_reg_offset_16(struct insn *insn, struct pt_regs *regs, + int *offs1, int *offs2) +{ + /* + * 16-bit addressing can use one or two registers. Specifics of + * encodings are given in Table 2-1. "16-Bit Addressing Forms with the + * ModR/M Byte" of the Intel Software Development Manual. + */ + static const int regoff1[] = { + offsetof(struct pt_regs, bx), + offsetof(struct pt_regs, bx), + offsetof(struct pt_regs, bp), + offsetof(struct pt_regs, bp), + offsetof(struct pt_regs, si), + offsetof(struct pt_regs, di), + offsetof(struct pt_regs, bp), + offsetof(struct pt_regs, bx), + }; + + static const int regoff2[] = { + offsetof(struct pt_regs, si), + offsetof(struct pt_regs, di), + offsetof(struct pt_regs, si), + offsetof(struct pt_regs, di), + -EDOM, + -EDOM, + -EDOM, + -EDOM, + }; + + if (!offs1 || !offs2) + return -EINVAL; + + /* Operand is a register, use the generic function. */ + if (X86_MODRM_MOD(insn->modrm.value) == 3) { + *offs1 = insn_get_modrm_rm_off(insn, regs); + *offs2 = -EDOM; + return 0; + } + + *offs1 = regoff1[X86_MODRM_RM(insn->modrm.value)]; + *offs2 = regoff2[X86_MODRM_RM(insn->modrm.value)]; + + /* + * If ModRM.mod is 0 and ModRM.rm is 110b, then we use displacement- + * only addressing. This means that no registers are involved in + * computing the effective address. Thus, ensure that the first + * register offset is invalild. The second register offset is already + * invalid under the aforementioned conditions. + */ + if ((X86_MODRM_MOD(insn->modrm.value) == 0) && + (X86_MODRM_RM(insn->modrm.value) == 6)) + *offs1 = -EDOM; + + return 0; +} + +/** + * get_desc() - Obtain pointer to a segment descriptor + * @sel: Segment selector + * + * Given a segment selector, obtain a pointer to the segment descriptor. + * Both global and local descriptor tables are supported. + * + * Returns: + * + * Pointer to segment descriptor on success. + * + * NULL on error. + */ +static struct desc_struct *get_desc(unsigned short sel) +{ + struct desc_ptr gdt_desc = {0, 0}; + unsigned long desc_base; + +#ifdef CONFIG_MODIFY_LDT_SYSCALL + if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) { + struct desc_struct *desc = NULL; + struct ldt_struct *ldt; + + /* Bits [15:3] contain the index of the desired entry. */ + sel >>= 3; + + mutex_lock(¤t->active_mm->context.lock); + ldt = current->active_mm->context.ldt; + if (ldt && sel < ldt->nr_entries) + desc = &ldt->entries[sel]; + + mutex_unlock(¤t->active_mm->context.lock); + + return desc; + } +#endif + native_store_gdt(&gdt_desc); + + /* + * Segment descriptors have a size of 8 bytes. Thus, the index is + * multiplied by 8 to obtain the memory offset of the desired descriptor + * from the base of the GDT. As bits [15:3] of the segment selector + * contain the index, it can be regarded as multiplied by 8 already. + * All that remains is to clear bits [2:0]. + */ + desc_base = sel & ~(SEGMENT_RPL_MASK | SEGMENT_TI_MASK); + + if (desc_base > gdt_desc.size) + return NULL; + + return (struct desc_struct *)(gdt_desc.address + desc_base); +} + +/** + * insn_get_seg_base() - Obtain base address of segment descriptor. + * @regs: Register values as seen when entering kernel mode + * @seg_reg_idx: Index of the segment register pointing to seg descriptor + * + * Obtain the base address of the segment as indicated by the segment descriptor + * pointed by the segment selector. The segment selector is obtained from the + * input segment register index @seg_reg_idx. + * + * Returns: + * + * In protected mode, base address of the segment. Zero in long mode, + * except when FS or GS are used. In virtual-8086 mode, the segment + * selector shifted 4 bits to the right. + * + * -1L in case of error. + */ +unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx) +{ + struct desc_struct *desc; + short sel; + + sel = get_segment_selector(regs, seg_reg_idx); + if (sel < 0) + return -1L; + + if (v8086_mode(regs)) + /* + * Base is simply the segment selector shifted 4 + * bits to the right. + */ + return (unsigned long)(sel << 4); + + if (user_64bit_mode(regs)) { + /* + * Only FS or GS will have a base address, the rest of + * the segments' bases are forced to 0. + */ + unsigned long base; + + if (seg_reg_idx == INAT_SEG_REG_FS) + rdmsrl(MSR_FS_BASE, base); + else if (seg_reg_idx == INAT_SEG_REG_GS) + /* + * swapgs was called at the kernel entry point. Thus, + * MSR_KERNEL_GS_BASE will have the user-space GS base. + */ + rdmsrl(MSR_KERNEL_GS_BASE, base); + else + base = 0; + return base; + } + + /* In protected mode the segment selector cannot be null. */ + if (!sel) + return -1L; + + desc = get_desc(sel); + if (!desc) + return -1L; + + return get_desc_base(desc); +} + +/** + * get_seg_limit() - Obtain the limit of a segment descriptor + * @regs: Register values as seen when entering kernel mode + * @seg_reg_idx: Index of the segment register pointing to seg descriptor + * + * Obtain the limit of the segment as indicated by the segment descriptor + * pointed by the segment selector. The segment selector is obtained from the + * input segment register index @seg_reg_idx. + * + * Returns: + * + * In protected mode, the limit of the segment descriptor in bytes. + * In long mode and virtual-8086 mode, segment limits are not enforced. Thus, + * limit is returned as -1L to imply a limit-less segment. + * + * Zero is returned on error. + */ +static unsigned long get_seg_limit(struct pt_regs *regs, int seg_reg_idx) +{ + struct desc_struct *desc; + unsigned long limit; + short sel; + + sel = get_segment_selector(regs, seg_reg_idx); + if (sel < 0) + return 0; + + if (user_64bit_mode(regs) || v8086_mode(regs)) + return -1L; + + if (!sel) + return 0; + + desc = get_desc(sel); + if (!desc) + return 0; + + /* + * If the granularity bit is set, the limit is given in multiples + * of 4096. This also means that the 12 least significant bits are + * not tested when checking the segment limits. In practice, + * this means that the segment ends in (limit << 12) + 0xfff. + */ + limit = get_desc_limit(desc); + if (desc->g) + limit = (limit << 12) + 0xfff; + + return limit; +} + +/** + * insn_get_code_seg_params() - Obtain code segment parameters + * @regs: Structure with register values as seen when entering kernel mode + * + * Obtain address and operand sizes of the code segment. It is obtained from the + * selector contained in the CS register in regs. In protected mode, the default + * address is determined by inspecting the L and D bits of the segment + * descriptor. In virtual-8086 mode, the default is always two bytes for both + * address and operand sizes. + * + * Returns: + * + * An int containing ORed-in default parameters on success. + * + * -EINVAL on error. + */ +int insn_get_code_seg_params(struct pt_regs *regs) +{ + struct desc_struct *desc; + short sel; + + if (v8086_mode(regs)) + /* Address and operand size are both 16-bit. */ + return INSN_CODE_SEG_PARAMS(2, 2); + + sel = get_segment_selector(regs, INAT_SEG_REG_CS); + if (sel < 0) + return sel; + + desc = get_desc(sel); + if (!desc) + return -EINVAL; + + /* + * The most significant byte of the Type field of the segment descriptor + * determines whether a segment contains data or code. If this is a data + * segment, return error. + */ + if (!(desc->type & BIT(3))) + return -EINVAL; + + switch ((desc->l << 1) | desc->d) { + case 0: /* + * Legacy mode. CS.L=0, CS.D=0. Address and operand size are + * both 16-bit. + */ + return INSN_CODE_SEG_PARAMS(2, 2); + case 1: /* + * Legacy mode. CS.L=0, CS.D=1. Address and operand size are + * both 32-bit. + */ + return INSN_CODE_SEG_PARAMS(4, 4); + case 2: /* + * IA-32e 64-bit mode. CS.L=1, CS.D=0. Address size is 64-bit; + * operand size is 32-bit. + */ + return INSN_CODE_SEG_PARAMS(4, 8); + case 3: /* Invalid setting. CS.L=1, CS.D=1 */ + /* fall through */ + default: + return -EINVAL; + } +} + +/** + * insn_get_modrm_rm_off() - Obtain register in r/m part of the ModRM byte + * @insn: Instruction containing the ModRM byte + * @regs: Register values as seen when entering kernel mode + * + * Returns: + * + * The register indicated by the r/m part of the ModRM byte. The + * register is obtained as an offset from the base of pt_regs. In specific + * cases, the returned value can be -EDOM to indicate that the particular value + * of ModRM does not refer to a register and shall be ignored. + */ +int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs) +{ + return get_reg_offset(insn, regs, REG_TYPE_RM); +} + +/** + * get_seg_base_limit() - obtain base address and limit of a segment + * @insn: Instruction. Must be valid. + * @regs: Register values as seen when entering kernel mode + * @regoff: Operand offset, in pt_regs, used to resolve segment descriptor + * @base: Obtained segment base + * @limit: Obtained segment limit + * + * Obtain the base address and limit of the segment associated with the operand + * @regoff and, if any or allowed, override prefixes in @insn. This function is + * different from insn_get_seg_base() as the latter does not resolve the segment + * associated with the instruction operand. If a limit is not needed (e.g., + * when running in long mode), @limit can be NULL. + * + * Returns: + * + * 0 on success. @base and @limit will contain the base address and of the + * resolved segment, respectively. + * + * -EINVAL on error. + */ +static int get_seg_base_limit(struct insn *insn, struct pt_regs *regs, + int regoff, unsigned long *base, + unsigned long *limit) +{ + int seg_reg_idx; + + if (!base) + return -EINVAL; + + seg_reg_idx = resolve_seg_reg(insn, regs, regoff); + if (seg_reg_idx < 0) + return seg_reg_idx; + + *base = insn_get_seg_base(regs, seg_reg_idx); + if (*base == -1L) + return -EINVAL; + + if (!limit) + return 0; + + *limit = get_seg_limit(regs, seg_reg_idx); + if (!(*limit)) + return -EINVAL; + + return 0; +} + +/** + * get_eff_addr_reg() - Obtain effective address from register operand + * @insn: Instruction. Must be valid. + * @regs: Register values as seen when entering kernel mode + * @regoff: Obtained operand offset, in pt_regs, with the effective address + * @eff_addr: Obtained effective address + * + * Obtain the effective address stored in the register operand as indicated by + * the ModRM byte. This function is to be used only with register addressing + * (i.e., ModRM.mod is 3). The effective address is saved in @eff_addr. The + * register operand, as an offset from the base of pt_regs, is saved in @regoff; + * such offset can then be used to resolve the segment associated with the + * operand. This function can be used with any of the supported address sizes + * in x86. + * + * Returns: + * + * 0 on success. @eff_addr will have the effective address stored in the + * operand indicated by ModRM. @regoff will have such operand as an offset from + * the base of pt_regs. + * + * -EINVAL on error. + */ +static int get_eff_addr_reg(struct insn *insn, struct pt_regs *regs, + int *regoff, long *eff_addr) +{ + insn_get_modrm(insn); + + if (!insn->modrm.nbytes) + return -EINVAL; + + if (X86_MODRM_MOD(insn->modrm.value) != 3) + return -EINVAL; + + *regoff = get_reg_offset(insn, regs, REG_TYPE_RM); + if (*regoff < 0) + return -EINVAL; + + /* Ignore bytes that are outside the address size. */ + if (insn->addr_bytes == 2) + *eff_addr = regs_get_register(regs, *regoff) & 0xffff; + else if (insn->addr_bytes == 4) + *eff_addr = regs_get_register(regs, *regoff) & 0xffffffff; + else /* 64-bit address */ + *eff_addr = regs_get_register(regs, *regoff); + + return 0; +} + +/** + * get_eff_addr_modrm() - Obtain referenced effective address via ModRM + * @insn: Instruction. Must be valid. + * @regs: Register values as seen when entering kernel mode + * @regoff: Obtained operand offset, in pt_regs, associated with segment + * @eff_addr: Obtained effective address + * + * Obtain the effective address referenced by the ModRM byte of @insn. After + * identifying the registers involved in the register-indirect memory reference, + * its value is obtained from the operands in @regs. The computed address is + * stored @eff_addr. Also, the register operand that indicates the associated + * segment is stored in @regoff, this parameter can later be used to determine + * such segment. + * + * Returns: + * + * 0 on success. @eff_addr will have the referenced effective address. @regoff + * will have a register, as an offset from the base of pt_regs, that can be used + * to resolve the associated segment. + * + * -EINVAL on error. + */ +static int get_eff_addr_modrm(struct insn *insn, struct pt_regs *regs, + int *regoff, long *eff_addr) +{ + long tmp; + + if (insn->addr_bytes != 8 && insn->addr_bytes != 4) + return -EINVAL; + + insn_get_modrm(insn); + + if (!insn->modrm.nbytes) + return -EINVAL; + + if (X86_MODRM_MOD(insn->modrm.value) > 2) + return -EINVAL; + + *regoff = get_reg_offset(insn, regs, REG_TYPE_RM); + + /* + * -EDOM means that we must ignore the address_offset. In such a case, + * in 64-bit mode the effective address relative to the rIP of the + * following instruction. + */ + if (*regoff == -EDOM) { + if (user_64bit_mode(regs)) + tmp = regs->ip + insn->length; + else + tmp = 0; + } else if (*regoff < 0) { + return -EINVAL; + } else { + tmp = regs_get_register(regs, *regoff); + } + + if (insn->addr_bytes == 4) { + int addr32 = (int)(tmp & 0xffffffff) + insn->displacement.value; + + *eff_addr = addr32 & 0xffffffff; + } else { + *eff_addr = tmp + insn->displacement.value; + } + + return 0; +} + +/** + * get_eff_addr_modrm_16() - Obtain referenced effective address via ModRM + * @insn: Instruction. Must be valid. + * @regs: Register values as seen when entering kernel mode + * @regoff: Obtained operand offset, in pt_regs, associated with segment + * @eff_addr: Obtained effective address + * + * Obtain the 16-bit effective address referenced by the ModRM byte of @insn. + * After identifying the registers involved in the register-indirect memory + * reference, its value is obtained from the operands in @regs. The computed + * address is stored @eff_addr. Also, the register operand that indicates + * the associated segment is stored in @regoff, this parameter can later be used + * to determine such segment. + * + * Returns: + * + * 0 on success. @eff_addr will have the referenced effective address. @regoff + * will have a register, as an offset from the base of pt_regs, that can be used + * to resolve the associated segment. + * + * -EINVAL on error. + */ +static int get_eff_addr_modrm_16(struct insn *insn, struct pt_regs *regs, + int *regoff, short *eff_addr) +{ + int addr_offset1, addr_offset2, ret; + short addr1 = 0, addr2 = 0, displacement; + + if (insn->addr_bytes != 2) + return -EINVAL; + + insn_get_modrm(insn); + + if (!insn->modrm.nbytes) + return -EINVAL; + + if (X86_MODRM_MOD(insn->modrm.value) > 2) + return -EINVAL; + + ret = get_reg_offset_16(insn, regs, &addr_offset1, &addr_offset2); + if (ret < 0) + return -EINVAL; + + /* + * Don't fail on invalid offset values. They might be invalid because + * they cannot be used for this particular value of ModRM. Instead, use + * them in the computation only if they contain a valid value. + */ + if (addr_offset1 != -EDOM) + addr1 = regs_get_register(regs, addr_offset1) & 0xffff; + + if (addr_offset2 != -EDOM) + addr2 = regs_get_register(regs, addr_offset2) & 0xffff; + + displacement = insn->displacement.value & 0xffff; + *eff_addr = addr1 + addr2 + displacement; + + /* + * The first operand register could indicate to use of either SS or DS + * registers to obtain the segment selector. The second operand + * register can only indicate the use of DS. Thus, the first operand + * will be used to obtain the segment selector. + */ + *regoff = addr_offset1; + + return 0; +} + +/** + * get_eff_addr_sib() - Obtain referenced effective address via SIB + * @insn: Instruction. Must be valid. + * @regs: Register values as seen when entering kernel mode + * @regoff: Obtained operand offset, in pt_regs, associated with segment + * @eff_addr: Obtained effective address + * + * Obtain the effective address referenced by the SIB byte of @insn. After + * identifying the registers involved in the indexed, register-indirect memory + * reference, its value is obtained from the operands in @regs. The computed + * address is stored @eff_addr. Also, the register operand that indicates the + * associated segment is stored in @regoff, this parameter can later be used to + * determine such segment. + * + * Returns: + * + * 0 on success. @eff_addr will have the referenced effective address. + * @base_offset will have a register, as an offset from the base of pt_regs, + * that can be used to resolve the associated segment. + * + * -EINVAL on error. + */ +static int get_eff_addr_sib(struct insn *insn, struct pt_regs *regs, + int *base_offset, long *eff_addr) +{ + long base, indx; + int indx_offset; + + if (insn->addr_bytes != 8 && insn->addr_bytes != 4) + return -EINVAL; + + insn_get_modrm(insn); + + if (!insn->modrm.nbytes) + return -EINVAL; + + if (X86_MODRM_MOD(insn->modrm.value) > 2) + return -EINVAL; + + insn_get_sib(insn); + + if (!insn->sib.nbytes) + return -EINVAL; + + *base_offset = get_reg_offset(insn, regs, REG_TYPE_BASE); + indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX); + + /* + * Negative values in the base and index offset means an error when + * decoding the SIB byte. Except -EDOM, which means that the registers + * should not be used in the address computation. + */ + if (*base_offset == -EDOM) + base = 0; + else if (*base_offset < 0) + return -EINVAL; + else + base = regs_get_register(regs, *base_offset); + + if (indx_offset == -EDOM) + indx = 0; + else if (indx_offset < 0) + return -EINVAL; + else + indx = regs_get_register(regs, indx_offset); + + if (insn->addr_bytes == 4) { + int addr32, base32, idx32; + + base32 = base & 0xffffffff; + idx32 = indx & 0xffffffff; + + addr32 = base32 + idx32 * (1 << X86_SIB_SCALE(insn->sib.value)); + addr32 += insn->displacement.value; + + *eff_addr = addr32 & 0xffffffff; + } else { + *eff_addr = base + indx * (1 << X86_SIB_SCALE(insn->sib.value)); + *eff_addr += insn->displacement.value; + } + + return 0; +} + +/** + * get_addr_ref_16() - Obtain the 16-bit address referred by instruction + * @insn: Instruction containing ModRM byte and displacement + * @regs: Register values as seen when entering kernel mode + * + * This function is to be used with 16-bit address encodings. Obtain the memory + * address referred by the instruction's ModRM and displacement bytes. Also, the + * segment used as base is determined by either any segment override prefixes in + * @insn or the default segment of the registers involved in the address + * computation. In protected mode, segment limits are enforced. + * + * Returns: + * + * Linear address referenced by the instruction operands on success. + * + * -1L on error. + */ +static void __user *get_addr_ref_16(struct insn *insn, struct pt_regs *regs) +{ + unsigned long linear_addr = -1L, seg_base, seg_limit; + int ret, regoff; + short eff_addr; + long tmp; + + insn_get_modrm(insn); + insn_get_displacement(insn); + + if (insn->addr_bytes != 2) + goto out; + + if (X86_MODRM_MOD(insn->modrm.value) == 3) { + ret = get_eff_addr_reg(insn, regs, ®off, &tmp); + if (ret) + goto out; + + eff_addr = tmp; + } else { + ret = get_eff_addr_modrm_16(insn, regs, ®off, &eff_addr); + if (ret) + goto out; + } + + ret = get_seg_base_limit(insn, regs, regoff, &seg_base, &seg_limit); + if (ret) + goto out; + + /* + * Before computing the linear address, make sure the effective address + * is within the limits of the segment. In virtual-8086 mode, segment + * limits are not enforced. In such a case, the segment limit is -1L to + * reflect this fact. + */ + if ((unsigned long)(eff_addr & 0xffff) > seg_limit) + goto out; + + linear_addr = (unsigned long)(eff_addr & 0xffff) + seg_base; + + /* Limit linear address to 20 bits */ + if (v8086_mode(regs)) + linear_addr &= 0xfffff; + +out: + return (void __user *)linear_addr; +} + +/** + * get_addr_ref_32() - Obtain a 32-bit linear address + * @insn: Instruction with ModRM, SIB bytes and displacement + * @regs: Register values as seen when entering kernel mode + * + * This function is to be used with 32-bit address encodings to obtain the + * linear memory address referred by the instruction's ModRM, SIB, + * displacement bytes and segment base address, as applicable. If in protected + * mode, segment limits are enforced. + * + * Returns: + * + * Linear address referenced by instruction and registers on success. + * + * -1L on error. + */ +static void __user *get_addr_ref_32(struct insn *insn, struct pt_regs *regs) +{ + unsigned long linear_addr = -1L, seg_base, seg_limit; + int eff_addr, regoff; + long tmp; + int ret; + + if (insn->addr_bytes != 4) + goto out; + + if (X86_MODRM_MOD(insn->modrm.value) == 3) { + ret = get_eff_addr_reg(insn, regs, ®off, &tmp); + if (ret) + goto out; + + eff_addr = tmp; + + } else { + if (insn->sib.nbytes) { + ret = get_eff_addr_sib(insn, regs, ®off, &tmp); + if (ret) + goto out; + + eff_addr = tmp; + } else { + ret = get_eff_addr_modrm(insn, regs, ®off, &tmp); + if (ret) + goto out; + + eff_addr = tmp; + } + } + + ret = get_seg_base_limit(insn, regs, regoff, &seg_base, &seg_limit); + if (ret) + goto out; + + /* + * In protected mode, before computing the linear address, make sure + * the effective address is within the limits of the segment. + * 32-bit addresses can be used in long and virtual-8086 modes if an + * address override prefix is used. In such cases, segment limits are + * not enforced. When in virtual-8086 mode, the segment limit is -1L + * to reflect this situation. + * + * After computed, the effective address is treated as an unsigned + * quantity. + */ + if (!user_64bit_mode(regs) && ((unsigned int)eff_addr > seg_limit)) + goto out; + + /* + * Even though 32-bit address encodings are allowed in virtual-8086 + * mode, the address range is still limited to [0x-0xffff]. + */ + if (v8086_mode(regs) && (eff_addr & ~0xffff)) + goto out; + + /* + * Data type long could be 64 bits in size. Ensure that our 32-bit + * effective address is not sign-extended when computing the linear + * address. + */ + linear_addr = (unsigned long)(eff_addr & 0xffffffff) + seg_base; + + /* Limit linear address to 20 bits */ + if (v8086_mode(regs)) + linear_addr &= 0xfffff; + +out: + return (void __user *)linear_addr; +} + +/** + * get_addr_ref_64() - Obtain a 64-bit linear address + * @insn: Instruction struct with ModRM and SIB bytes and displacement + * @regs: Structure with register values as seen when entering kernel mode + * + * This function is to be used with 64-bit address encodings to obtain the + * linear memory address referred by the instruction's ModRM, SIB, + * displacement bytes and segment base address, as applicable. + * + * Returns: + * + * Linear address referenced by instruction and registers on success. + * + * -1L on error. + */ +#ifndef CONFIG_X86_64 +static void __user *get_addr_ref_64(struct insn *insn, struct pt_regs *regs) +{ + return (void __user *)-1L; +} +#else +static void __user *get_addr_ref_64(struct insn *insn, struct pt_regs *regs) +{ + unsigned long linear_addr = -1L, seg_base; + int regoff, ret; + long eff_addr; + + if (insn->addr_bytes != 8) + goto out; + + if (X86_MODRM_MOD(insn->modrm.value) == 3) { + ret = get_eff_addr_reg(insn, regs, ®off, &eff_addr); + if (ret) + goto out; + + } else { + if (insn->sib.nbytes) { + ret = get_eff_addr_sib(insn, regs, ®off, &eff_addr); + if (ret) + goto out; + } else { + ret = get_eff_addr_modrm(insn, regs, ®off, &eff_addr); + if (ret) + goto out; + } + + } + + ret = get_seg_base_limit(insn, regs, regoff, &seg_base, NULL); + if (ret) + goto out; + + linear_addr = (unsigned long)eff_addr + seg_base; + +out: + return (void __user *)linear_addr; +} +#endif /* CONFIG_X86_64 */ + +/** + * insn_get_addr_ref() - Obtain the linear address referred by instruction + * @insn: Instruction structure containing ModRM byte and displacement + * @regs: Structure with register values as seen when entering kernel mode + * + * Obtain the linear address referred by the instruction's ModRM, SIB and + * displacement bytes, and segment base, as applicable. In protected mode, + * segment limits are enforced. + * + * Returns: + * + * Linear address referenced by instruction and registers on success. + * + * -1L on error. + */ +void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs) +{ + if (!insn || !regs) + return (void __user *)-1L; + + switch (insn->addr_bytes) { + case 2: + return get_addr_ref_16(insn, regs); + case 4: + return get_addr_ref_32(insn, regs); + case 8: + return get_addr_ref_64(insn, regs); + default: + return (void __user *)-1L; + } +} diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index ab2d1d73e9e7..79778ab200e4 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Entropy functions used on early boot for KASLR base and memory * randomization. The base randomization is done in the compressed diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c index 2eab7d0bfedd..e565d1c9019e 100644 --- a/arch/x86/lib/memcpy_32.c +++ b/arch/x86/lib/memcpy_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/string.h> #include <linux/export.h> diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 15de86cd15b0..bbec69d8223b 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Normally compiler builtins are used, but sometimes the compiler calls out * of line code. Based on asm-i386/string.h. diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 55b95db30a61..9bc861c71e75 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* Copyright 2002 Andi Kleen, SuSE Labs */ #include <linux/linkage.h> diff --git a/arch/x86/lib/misc.c b/arch/x86/lib/misc.c index 76b373af03f0..a018ec4fba53 100644 --- a/arch/x86/lib/misc.c +++ b/arch/x86/lib/misc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Count the digits of @val including a possible sign. * diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index c2311a678332..4321fa02e18d 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * MMX 3DNow! library helper functions * diff --git a/arch/x86/lib/msr-reg-export.c b/arch/x86/lib/msr-reg-export.c index ff29e8d39414..876b4168ab0a 100644 --- a/arch/x86/lib/msr-reg-export.c +++ b/arch/x86/lib/msr-reg-export.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <asm/msr.h> diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S index 10ffa7e8519f..ed33cbab3958 100644 --- a/arch/x86/lib/msr-reg.S +++ b/arch/x86/lib/msr-reg.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <linux/errno.h> #include <asm/asm.h> diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c index ce68b6a9d7d1..693cce0be82d 100644 --- a/arch/x86/lib/msr-smp.c +++ b/arch/x86/lib/msr-smp.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/preempt.h> #include <linux/smp.h> diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 07764255b611..3bd905e10ee2 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/percpu.h> #include <linux/preempt.h> diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index cd5d716d2897..96dce5fe2a35 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * __put_user functions. * diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S index bf2c6074efd2..dc2ab6ea6768 100644 --- a/arch/x86/lib/rwsem.S +++ b/arch/x86/lib/rwsem.S @@ -98,6 +98,18 @@ ENTRY(call_rwsem_down_read_failed) ret ENDPROC(call_rwsem_down_read_failed) +ENTRY(call_rwsem_down_read_failed_killable) + FRAME_BEGIN + save_common_regs + __ASM_SIZE(push,) %__ASM_REG(dx) + movq %rax,%rdi + call rwsem_down_read_failed_killable + __ASM_SIZE(pop,) %__ASM_REG(dx) + restore_common_regs + FRAME_END + ret +ENDPROC(call_rwsem_down_read_failed_killable) + ENTRY(call_rwsem_down_write_failed) FRAME_BEGIN save_common_regs diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c index dc0ad12f80bb..d15fdae9656e 100644 --- a/arch/x86/lib/string_32.c +++ b/arch/x86/lib/string_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Most of the string-functions are rather heavily hand-optimized, * see especially strsep,strstr,str[c]spn. They should work, but are not diff --git a/arch/x86/lib/strstr_32.c b/arch/x86/lib/strstr_32.c index a03b1c750bfe..38f37df056f7 100644 --- a/arch/x86/lib/strstr_32.c +++ b/arch/x86/lib/strstr_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/string.h> #include <linux/export.h> diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c index bd057a4ffe6e..1b377f734e64 100644 --- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * User address space access functions. * The non inlined parts of asm-i386/uaccess.h are here. diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 12e377184ee4..c4d55919fac1 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -896,7 +896,7 @@ EndTable GrpTable: Grp3_1 0: TEST Eb,Ib -1: +1: TEST Eb,Ib 2: NOT Eb 3: NEG Eb 4: MUL AL,Eb diff --git a/arch/x86/math-emu/Makefile b/arch/x86/math-emu/Makefile index 1b2dac174321..02211fc6f2ec 100644 --- a/arch/x86/math-emu/Makefile +++ b/arch/x86/math-emu/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for wm-FPU-emu # diff --git a/arch/x86/math-emu/control_w.h b/arch/x86/math-emu/control_w.h index ae2274dbd305..60f4dcc5edc3 100644 --- a/arch/x86/math-emu/control_w.h +++ b/arch/x86/math-emu/control_w.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | control_w.h | | | diff --git a/arch/x86/math-emu/div_Xsig.S b/arch/x86/math-emu/div_Xsig.S index 066996dba6a2..ee08449d20fd 100644 --- a/arch/x86/math-emu/div_Xsig.S +++ b/arch/x86/math-emu/div_Xsig.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .file "div_Xsig.S" /*---------------------------------------------------------------------------+ | div_Xsig.S | diff --git a/arch/x86/math-emu/div_small.S b/arch/x86/math-emu/div_small.S index 2c71527bd917..8f5025c80ee0 100644 --- a/arch/x86/math-emu/div_small.S +++ b/arch/x86/math-emu/div_small.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .file "div_small.S" /*---------------------------------------------------------------------------+ | div_small.S | diff --git a/arch/x86/math-emu/errors.c b/arch/x86/math-emu/errors.c index 2ccc424a57d9..6b468517ab71 100644 --- a/arch/x86/math-emu/errors.c +++ b/arch/x86/math-emu/errors.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | errors.c | | | diff --git a/arch/x86/math-emu/exception.h b/arch/x86/math-emu/exception.h index 67f43a4683d5..75230b977577 100644 --- a/arch/x86/math-emu/exception.h +++ b/arch/x86/math-emu/exception.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | exception.h | | | diff --git a/arch/x86/math-emu/fpu_arith.c b/arch/x86/math-emu/fpu_arith.c index aeab24e083c4..09006dc474a0 100644 --- a/arch/x86/math-emu/fpu_arith.c +++ b/arch/x86/math-emu/fpu_arith.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | fpu_arith.c | | | diff --git a/arch/x86/math-emu/fpu_asm.h b/arch/x86/math-emu/fpu_asm.h index 955b932735a4..a83353d5271c 100644 --- a/arch/x86/math-emu/fpu_asm.h +++ b/arch/x86/math-emu/fpu_asm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | fpu_asm.h | | | diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c index 024f6e971174..034748459482 100644 --- a/arch/x86/math-emu/fpu_aux.c +++ b/arch/x86/math-emu/fpu_aux.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | fpu_aux.c | | | diff --git a/arch/x86/math-emu/fpu_emu.h b/arch/x86/math-emu/fpu_emu.h index c9c320dccca1..a5a41ec58072 100644 --- a/arch/x86/math-emu/fpu_emu.h +++ b/arch/x86/math-emu/fpu_emu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | fpu_emu.h | | | diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c index d4a7df2205b8..9e2ba7e667f6 100644 --- a/arch/x86/math-emu/fpu_entry.c +++ b/arch/x86/math-emu/fpu_entry.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | fpu_entry.c | | | @@ -114,7 +115,7 @@ void math_emulate(struct math_emu_info *info) struct desc_struct code_descriptor; struct fpu *fpu = ¤t->thread.fpu; - fpu__activate_curr(fpu); + fpu__initialize(fpu); #ifdef RE_ENTRANT_CHECKING if (emulating) { diff --git a/arch/x86/math-emu/fpu_etc.c b/arch/x86/math-emu/fpu_etc.c index 233e5af566f5..1b118fd93140 100644 --- a/arch/x86/math-emu/fpu_etc.c +++ b/arch/x86/math-emu/fpu_etc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | fpu_etc.c | | | diff --git a/arch/x86/math-emu/fpu_proto.h b/arch/x86/math-emu/fpu_proto.h index caff438b9c1d..70d35c200945 100644 --- a/arch/x86/math-emu/fpu_proto.h +++ b/arch/x86/math-emu/fpu_proto.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FPU_PROTO_H #define _FPU_PROTO_H diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 699f329f1d40..c8b1b31ed7c4 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | fpu_system.h | | | diff --git a/arch/x86/math-emu/fpu_tags.c b/arch/x86/math-emu/fpu_tags.c index d9c657cd7746..bff95d4e7dca 100644 --- a/arch/x86/math-emu/fpu_tags.c +++ b/arch/x86/math-emu/fpu_tags.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | fpu_tags.c | | | diff --git a/arch/x86/math-emu/fpu_trig.c b/arch/x86/math-emu/fpu_trig.c index ecd06680581c..783c509f957a 100644 --- a/arch/x86/math-emu/fpu_trig.c +++ b/arch/x86/math-emu/fpu_trig.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | fpu_trig.c | | | diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index c48967c6a0e2..b82ca14ba718 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | get_address.c | | | diff --git a/arch/x86/math-emu/load_store.c b/arch/x86/math-emu/load_store.c index 1643054766eb..f821a9cd7753 100644 --- a/arch/x86/math-emu/load_store.c +++ b/arch/x86/math-emu/load_store.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | load_store.c | | | diff --git a/arch/x86/math-emu/mul_Xsig.S b/arch/x86/math-emu/mul_Xsig.S index 22e0631bb85a..3e489122a2b0 100644 --- a/arch/x86/math-emu/mul_Xsig.S +++ b/arch/x86/math-emu/mul_Xsig.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | mul_Xsig.S | | | diff --git a/arch/x86/math-emu/poly.h b/arch/x86/math-emu/poly.h index 168eb44c93c8..fc1c887ca073 100644 --- a/arch/x86/math-emu/poly.h +++ b/arch/x86/math-emu/poly.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | poly.h | | | diff --git a/arch/x86/math-emu/poly_2xm1.c b/arch/x86/math-emu/poly_2xm1.c index b00e9e10cdce..aa33006bafd5 100644 --- a/arch/x86/math-emu/poly_2xm1.c +++ b/arch/x86/math-emu/poly_2xm1.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | poly_2xm1.c | | | diff --git a/arch/x86/math-emu/poly_atan.c b/arch/x86/math-emu/poly_atan.c index 20c28e58e2d4..7e7412c5a1fe 100644 --- a/arch/x86/math-emu/poly_atan.c +++ b/arch/x86/math-emu/poly_atan.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | poly_atan.c | | | diff --git a/arch/x86/math-emu/poly_l2.c b/arch/x86/math-emu/poly_l2.c index 8e2ff4b28a0a..98b6949bb854 100644 --- a/arch/x86/math-emu/poly_l2.c +++ b/arch/x86/math-emu/poly_l2.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | poly_l2.c | | | diff --git a/arch/x86/math-emu/poly_sin.c b/arch/x86/math-emu/poly_sin.c index b862039c728e..c192fba51526 100644 --- a/arch/x86/math-emu/poly_sin.c +++ b/arch/x86/math-emu/poly_sin.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | poly_sin.c | | | diff --git a/arch/x86/math-emu/poly_tan.c b/arch/x86/math-emu/poly_tan.c index 1875763e0c02..1f5b1d712323 100644 --- a/arch/x86/math-emu/poly_tan.c +++ b/arch/x86/math-emu/poly_tan.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | poly_tan.c | | | diff --git a/arch/x86/math-emu/polynom_Xsig.S b/arch/x86/math-emu/polynom_Xsig.S index a9aaf414135d..604f0b2d17e8 100644 --- a/arch/x86/math-emu/polynom_Xsig.S +++ b/arch/x86/math-emu/polynom_Xsig.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | polynomial_Xsig.S | | | diff --git a/arch/x86/math-emu/reg_add_sub.c b/arch/x86/math-emu/reg_add_sub.c index deea48b9f13a..29451dd07556 100644 --- a/arch/x86/math-emu/reg_add_sub.c +++ b/arch/x86/math-emu/reg_add_sub.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | reg_add_sub.c | | | diff --git a/arch/x86/math-emu/reg_compare.c b/arch/x86/math-emu/reg_compare.c index 19b33b50adfa..eacb5128fc09 100644 --- a/arch/x86/math-emu/reg_compare.c +++ b/arch/x86/math-emu/reg_compare.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | reg_compare.c | | | diff --git a/arch/x86/math-emu/reg_constant.c b/arch/x86/math-emu/reg_constant.c index 00548354912f..8dc9095bab22 100644 --- a/arch/x86/math-emu/reg_constant.c +++ b/arch/x86/math-emu/reg_constant.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | reg_constant.c | | | diff --git a/arch/x86/math-emu/reg_constant.h b/arch/x86/math-emu/reg_constant.h index 1bffaec3a134..f2fdd344dcaa 100644 --- a/arch/x86/math-emu/reg_constant.h +++ b/arch/x86/math-emu/reg_constant.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | reg_constant.h | | | diff --git a/arch/x86/math-emu/reg_convert.c b/arch/x86/math-emu/reg_convert.c index 108060779977..251180623ce0 100644 --- a/arch/x86/math-emu/reg_convert.c +++ b/arch/x86/math-emu/reg_convert.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | reg_convert.c | | | diff --git a/arch/x86/math-emu/reg_divide.c b/arch/x86/math-emu/reg_divide.c index 6827012db341..08c2f6de0288 100644 --- a/arch/x86/math-emu/reg_divide.c +++ b/arch/x86/math-emu/reg_divide.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | reg_divide.c | | | diff --git a/arch/x86/math-emu/reg_ld_str.c b/arch/x86/math-emu/reg_ld_str.c index 2c98965a60ba..d40ff45497b9 100644 --- a/arch/x86/math-emu/reg_ld_str.c +++ b/arch/x86/math-emu/reg_ld_str.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | reg_ld_str.c | | | diff --git a/arch/x86/math-emu/reg_mul.c b/arch/x86/math-emu/reg_mul.c index 36c37f71f713..d69618572f14 100644 --- a/arch/x86/math-emu/reg_mul.c +++ b/arch/x86/math-emu/reg_mul.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /*---------------------------------------------------------------------------+ | reg_mul.c | | | diff --git a/arch/x86/math-emu/reg_norm.S b/arch/x86/math-emu/reg_norm.S index 53ac1a343c69..7f6b4392a15d 100644 --- a/arch/x86/math-emu/reg_norm.S +++ b/arch/x86/math-emu/reg_norm.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | reg_norm.S | | | diff --git a/arch/x86/math-emu/reg_round.S b/arch/x86/math-emu/reg_round.S index 41af5b208d88..04563421ee7d 100644 --- a/arch/x86/math-emu/reg_round.S +++ b/arch/x86/math-emu/reg_round.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .file "reg_round.S" /*---------------------------------------------------------------------------+ | reg_round.S | diff --git a/arch/x86/math-emu/reg_u_add.S b/arch/x86/math-emu/reg_u_add.S index 3b1bc5e9b2f6..50fe9f8c893c 100644 --- a/arch/x86/math-emu/reg_u_add.S +++ b/arch/x86/math-emu/reg_u_add.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .file "reg_u_add.S" /*---------------------------------------------------------------------------+ | reg_u_add.S | diff --git a/arch/x86/math-emu/reg_u_div.S b/arch/x86/math-emu/reg_u_div.S index 796eb5ab921b..94d545e118e4 100644 --- a/arch/x86/math-emu/reg_u_div.S +++ b/arch/x86/math-emu/reg_u_div.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .file "reg_u_div.S" /*---------------------------------------------------------------------------+ | reg_u_div.S | diff --git a/arch/x86/math-emu/reg_u_mul.S b/arch/x86/math-emu/reg_u_mul.S index 6196f68cf3c1..21cde47fb3e5 100644 --- a/arch/x86/math-emu/reg_u_mul.S +++ b/arch/x86/math-emu/reg_u_mul.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .file "reg_u_mul.S" /*---------------------------------------------------------------------------+ | reg_u_mul.S | diff --git a/arch/x86/math-emu/reg_u_sub.S b/arch/x86/math-emu/reg_u_sub.S index d115b900919a..f05dea7dec38 100644 --- a/arch/x86/math-emu/reg_u_sub.S +++ b/arch/x86/math-emu/reg_u_sub.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .file "reg_u_sub.S" /*---------------------------------------------------------------------------+ | reg_u_sub.S | diff --git a/arch/x86/math-emu/round_Xsig.S b/arch/x86/math-emu/round_Xsig.S index 87c99749a495..226a51e991f1 100644 --- a/arch/x86/math-emu/round_Xsig.S +++ b/arch/x86/math-emu/round_Xsig.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | round_Xsig.S | | | diff --git a/arch/x86/math-emu/shr_Xsig.S b/arch/x86/math-emu/shr_Xsig.S index c8552edeec75..96f4779aa9c1 100644 --- a/arch/x86/math-emu/shr_Xsig.S +++ b/arch/x86/math-emu/shr_Xsig.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .file "shr_Xsig.S" /*---------------------------------------------------------------------------+ | shr_Xsig.S | diff --git a/arch/x86/math-emu/status_w.h b/arch/x86/math-emu/status_w.h index 54a3f226982d..b77bafec9526 100644 --- a/arch/x86/math-emu/status_w.h +++ b/arch/x86/math-emu/status_w.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /*---------------------------------------------------------------------------+ | status_w.h | | | diff --git a/arch/x86/math-emu/wm_shrx.S b/arch/x86/math-emu/wm_shrx.S index 340dd6897f85..d588874eb6fb 100644 --- a/arch/x86/math-emu/wm_shrx.S +++ b/arch/x86/math-emu/wm_shrx.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .file "wm_shrx.S" /*---------------------------------------------------------------------------+ | wm_shrx.S | diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S index 695afae38fdf..f031c0e19356 100644 --- a/arch/x86/math-emu/wm_sqrt.S +++ b/arch/x86/math-emu/wm_sqrt.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .file "wm_sqrt.S" /*---------------------------------------------------------------------------+ | wm_sqrt.S | diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 72bf8c01c6e3..8e13b8cc6bed 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,5 +1,13 @@ -# Kernel does not boot with instrumentation of tlb.c. -KCOV_INSTRUMENT_tlb.o := n +# SPDX-License-Identifier: GPL-2.0 +# Kernel does not boot with instrumentation of tlb.c and mem_encrypt.c +KCOV_INSTRUMENT_tlb.o := n +KCOV_INSTRUMENT_mem_encrypt.o := n + +KASAN_SANITIZE_mem_encrypt.o := n + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_mem_encrypt.o = -pg +endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o physaddr.o setup_nx.o tlb.o @@ -21,8 +29,6 @@ obj-$(CONFIG_X86_PTDUMP) += debug_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o -obj-$(CONFIG_KMEMCHECK) += kmemcheck/ - KASAN_SANITIZE_kasan_init_$(BITS).o := n obj-$(CONFIG_KASAN) += kasan_init_$(BITS).o diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index 91f501b2da3b..048c761d97b0 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * AMD NUMA support. * Discover the memory map and associated nodes. diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index c076f710de4c..3321b446b66c 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -2,6 +2,7 @@ #include <linux/uaccess.h> #include <linux/sched/debug.h> +#include <asm/fpu/internal.h> #include <asm/traps.h> #include <asm/kdebug.h> @@ -66,18 +67,46 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup, * wrapped around) will be set. Additionally, seeing the refcount * reach 0 will set ZF (Zero Flag: result was zero). In each of * these cases we want a report, since it's a boundary condition. - * + * The SF case is not reported since it indicates post-boundary + * manipulations below zero or above INT_MAX. And if none of the + * flags are set, something has gone very wrong, so report it. */ if (regs->flags & (X86_EFLAGS_OF | X86_EFLAGS_ZF)) { bool zero = regs->flags & X86_EFLAGS_ZF; refcount_error_report(regs, zero ? "hit zero" : "overflow"); + } else if ((regs->flags & X86_EFLAGS_SF) == 0) { + /* Report if none of OF, ZF, nor SF are set. */ + refcount_error_report(regs, "unexpected saturation"); } return true; } EXPORT_SYMBOL_GPL(ex_handler_refcount); +/* + * Handler for when we fail to restore a task's FPU state. We should never get + * here because the FPU state of a task using the FPU (task->thread.fpu.state) + * should always be valid. However, past bugs have allowed userspace to set + * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn(). + * These caused XRSTOR to fail when switching to the task, leaking the FPU + * registers of the task previously executing on the CPU. Mitigate this class + * of vulnerability by restoring from the initial state (essentially, zeroing + * out all the FPU registers) if we can't restore from the task's FPU state. + */ +bool ex_handler_fprestore(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + regs->ip = ex_fixup_addr(fixup); + + WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", + (void *)instruction_pointer(regs)); + + __copy_kernel_to_fpregs(&init_fpstate, -1); + return true; +} +EXPORT_SYMBOL_GPL(ex_handler_fprestore); + bool ex_handler_ext(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b836a7274e12..78ca9a8ee454 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1995 Linus Torvalds * Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs. @@ -19,7 +20,6 @@ #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/pgalloc.h> /* pgd_*(), ... */ -#include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_ADDR */ #include <asm/vsyscall.h> /* emulate_vsyscall */ #include <asm/vm86.h> /* struct vm86 */ @@ -29,26 +29,6 @@ #include <asm/trace/exceptions.h> /* - * Page fault error code bits: - * - * bit 0 == 0: no page found 1: protection fault - * bit 1 == 0: read access 1: write access - * bit 2 == 0: kernel-mode access 1: user-mode access - * bit 3 == 1: use of reserved bit detected - * bit 4 == 1: fault was an instruction fetch - * bit 5 == 1: protection keys block access - */ -enum x86_pf_error_code { - - PF_PROT = 1 << 0, - PF_WRITE = 1 << 1, - PF_USER = 1 << 2, - PF_RSVD = 1 << 3, - PF_INSTR = 1 << 4, - PF_PK = 1 << 5, -}; - -/* * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ @@ -149,7 +129,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * If it was a exec (instruction fetch) fault on NX page, then * do not ignore the fault: */ - if (error_code & PF_INSTR) + if (error_code & X86_PF_INSTR) return 0; instr = (void *)convert_ip_to_linear(current, regs); @@ -179,7 +159,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * siginfo so userspace can discover which protection key was set * on the PTE. * - * If we get here, we know that the hardware signaled a PF_PK + * If we get here, we know that the hardware signaled a X86_PF_PK * fault and that there was a VMA once we got in the fault * handler. It does *not* guarantee that the VMA we find here * was the one that we faulted on. @@ -192,8 +172,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ -static void fill_sig_info_pkey(int si_code, siginfo_t *info, - struct vm_area_struct *vma) +static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey) { /* This is effectively an #ifdef */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) @@ -205,11 +184,11 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info, /* * force_sig_info_fault() is called from a number of * contexts, some of which have a VMA and some of which - * do not. The PF_PK handing happens after we have a + * do not. The X86_PF_PK handing happens after we have a * valid VMA, so we should never reach this without a * valid VMA. */ - if (!vma) { + if (!pkey) { WARN_ONCE(1, "PKU fault with no VMA passed in"); info->si_pkey = 0; return; @@ -219,13 +198,12 @@ static void fill_sig_info_pkey(int si_code, siginfo_t *info, * absolutely guranteed to be 100% accurate because of * the race explained above. */ - info->si_pkey = vma_pkey(vma); + info->si_pkey = *pkey; } static void force_sig_info_fault(int si_signo, int si_code, unsigned long address, - struct task_struct *tsk, struct vm_area_struct *vma, - int fault) + struct task_struct *tsk, u32 *pkey, int fault) { unsigned lsb = 0; siginfo_t info; @@ -240,7 +218,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, lsb = PAGE_SHIFT; info.si_addr_lsb = lsb; - fill_sig_info_pkey(si_code, &info, vma); + fill_sig_info_pkey(si_code, &info, pkey); force_sig_info(si_signo, &info, tsk); } @@ -699,7 +677,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, if (!oops_may_print()) return; - if (error_code & PF_INSTR) { + if (error_code & X86_PF_INSTR) { unsigned int level; pgd_t *pgd; pte_t *pte; @@ -762,8 +740,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, struct task_struct *tsk = current; unsigned long flags; int sig; - /* No context means no VMA to pass down */ - struct vm_area_struct *vma = NULL; /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs, X86_TRAP_PF)) { @@ -783,12 +759,12 @@ no_context(struct pt_regs *regs, unsigned long error_code, */ if (current->thread.sig_on_uaccess_err && signal) { tsk->thread.trap_nr = X86_TRAP_PF; - tsk->thread.error_code = error_code | PF_USER; + tsk->thread.error_code = error_code | X86_PF_USER; tsk->thread.cr2 = address; /* XXX: hwpoison faults will set the wrong code. */ force_sig_info_fault(signal, si_code, address, - tsk, vma, 0); + tsk, NULL, 0); } /* @@ -806,7 +782,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, if (is_vmalloc_addr((void *)address) && (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) || address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) { - register void *__sp asm("rsp"); unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *); /* * We're likely to be running with very little stack space @@ -821,7 +796,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, asm volatile ("movq %[stack], %%rsp\n\t" "call handle_stack_overflow\n\t" "1: jmp 1b" - : "+r" (__sp) + : ASM_CALL_CONSTRAINT : "D" ("kernel stack overflow (page fault)"), "S" (regs), "d" (address), [stack] "rm" (stack)); @@ -897,13 +872,12 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma, - int si_code) + unsigned long address, u32 *pkey, int si_code) { struct task_struct *tsk = current; /* User mode accesses just cause a SIGSEGV */ - if (error_code & PF_USER) { + if (error_code & X86_PF_USER) { /* * It's possible to have interrupts off here: */ @@ -924,7 +898,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, * Instruction fetch faults in the vsyscall page might need * emulation. */ - if (unlikely((error_code & PF_INSTR) && + if (unlikely((error_code & X86_PF_INSTR) && ((address & ~0xfff) == VSYSCALL_ADDR))) { if (emulate_vsyscall(regs, address)) return; @@ -937,7 +911,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, * are always protection faults. */ if (address >= TASK_SIZE_MAX) - error_code |= PF_PROT; + error_code |= X86_PF_PROT; if (likely(show_unhandled_signals)) show_signal_msg(regs, error_code, address, tsk); @@ -946,7 +920,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_PF; - force_sig_info_fault(SIGSEGV, si_code, address, tsk, vma, 0); + force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0); return; } @@ -959,9 +933,9 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, static noinline void bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma) + unsigned long address, u32 *pkey) { - __bad_area_nosemaphore(regs, error_code, address, vma, SEGV_MAPERR); + __bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR); } static void @@ -969,6 +943,10 @@ __bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct vm_area_struct *vma, int si_code) { struct mm_struct *mm = current->mm; + u32 pkey; + + if (vma) + pkey = vma_pkey(vma); /* * Something tried to access memory that isn't in our memory map.. @@ -976,7 +954,8 @@ __bad_area(struct pt_regs *regs, unsigned long error_code, */ up_read(&mm->mmap_sem); - __bad_area_nosemaphore(regs, error_code, address, vma, si_code); + __bad_area_nosemaphore(regs, error_code, address, + (vma) ? &pkey : NULL, si_code); } static noinline void @@ -993,11 +972,11 @@ static inline bool bad_area_access_from_pkeys(unsigned long error_code, if (!boot_cpu_has(X86_FEATURE_OSPKE)) return false; - if (error_code & PF_PK) + if (error_code & X86_PF_PK) return true; /* this checks permission keys on the VMA: */ - if (!arch_vma_access_permitted(vma, (error_code & PF_WRITE), - (error_code & PF_INSTR), foreign)) + if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), + (error_code & X86_PF_INSTR), foreign)) return true; return false; } @@ -1019,13 +998,13 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code, static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, - struct vm_area_struct *vma, unsigned int fault) + u32 *pkey, unsigned int fault) { struct task_struct *tsk = current; int code = BUS_ADRERR; /* Kernel mode? Handle exceptions or die: */ - if (!(error_code & PF_USER)) { + if (!(error_code & X86_PF_USER)) { no_context(regs, error_code, address, SIGBUS, BUS_ADRERR); return; } @@ -1046,22 +1025,21 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, code = BUS_MCEERR_AR; } #endif - force_sig_info_fault(SIGBUS, code, address, tsk, vma, fault); + force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault); } static noinline void mm_fault_error(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma, - unsigned int fault) + unsigned long address, u32 *pkey, unsigned int fault) { - if (fatal_signal_pending(current) && !(error_code & PF_USER)) { + if (fatal_signal_pending(current) && !(error_code & X86_PF_USER)) { no_context(regs, error_code, address, 0, 0); return; } if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ - if (!(error_code & PF_USER)) { + if (!(error_code & X86_PF_USER)) { no_context(regs, error_code, address, SIGSEGV, SEGV_MAPERR); return; @@ -1076,9 +1054,9 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) - do_sigbus(regs, error_code, address, vma, fault); + do_sigbus(regs, error_code, address, pkey, fault); else if (fault & VM_FAULT_SIGSEGV) - bad_area_nosemaphore(regs, error_code, address, vma); + bad_area_nosemaphore(regs, error_code, address, pkey); else BUG(); } @@ -1086,16 +1064,16 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, static int spurious_fault_check(unsigned long error_code, pte_t *pte) { - if ((error_code & PF_WRITE) && !pte_write(*pte)) + if ((error_code & X86_PF_WRITE) && !pte_write(*pte)) return 0; - if ((error_code & PF_INSTR) && !pte_exec(*pte)) + if ((error_code & X86_PF_INSTR) && !pte_exec(*pte)) return 0; /* * Note: We do not do lazy flushing on protection key - * changes, so no spurious fault will ever set PF_PK. + * changes, so no spurious fault will ever set X86_PF_PK. */ - if ((error_code & PF_PK)) + if ((error_code & X86_PF_PK)) return 1; return 1; @@ -1141,8 +1119,8 @@ spurious_fault(unsigned long error_code, unsigned long address) * change, so user accesses are not expected to cause spurious * faults. */ - if (error_code != (PF_WRITE | PF_PROT) - && error_code != (PF_INSTR | PF_PROT)) + if (error_code != (X86_PF_WRITE | X86_PF_PROT) && + error_code != (X86_PF_INSTR | X86_PF_PROT)) return 0; pgd = init_mm.pgd + pgd_index(address); @@ -1202,19 +1180,19 @@ access_error(unsigned long error_code, struct vm_area_struct *vma) * always an unconditional error and can never result in * a follow-up action to resolve the fault, like a COW. */ - if (error_code & PF_PK) + if (error_code & X86_PF_PK) return 1; /* * Make sure to check the VMA so that we do not perform - * faults just to hit a PF_PK as soon as we fill in a + * faults just to hit a X86_PF_PK as soon as we fill in a * page. */ - if (!arch_vma_access_permitted(vma, (error_code & PF_WRITE), - (error_code & PF_INSTR), foreign)) + if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), + (error_code & X86_PF_INSTR), foreign)) return 1; - if (error_code & PF_WRITE) { + if (error_code & X86_PF_WRITE) { /* write, present and write, not present: */ if (unlikely(!(vma->vm_flags & VM_WRITE))) return 1; @@ -1222,7 +1200,7 @@ access_error(unsigned long error_code, struct vm_area_struct *vma) } /* read, present: */ - if (unlikely(error_code & PF_PROT)) + if (unlikely(error_code & X86_PF_PROT)) return 1; /* read, not present: */ @@ -1245,7 +1223,7 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs) if (!static_cpu_has(X86_FEATURE_SMAP)) return false; - if (error_code & PF_USER) + if (error_code & X86_PF_USER) return false; if (!user_mode(regs) && (regs->flags & X86_EFLAGS_AC)) @@ -1268,6 +1246,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, struct mm_struct *mm; int fault, major = 0; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + u32 pkey; tsk = current; mm = tsk->mm; @@ -1276,8 +1255,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, * Detect and handle instructions that would cause a page fault for * both a tracked kernel page and a userspace page. */ - if (kmemcheck_active(regs)) - kmemcheck_hide(regs); prefetchw(&mm->mmap_sem); if (unlikely(kmmio_fault(regs, address))) @@ -1297,12 +1274,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, * protection error (error_code & 9) == 0. */ if (unlikely(fault_in_kernel_space(address))) { - if (!(error_code & (PF_RSVD | PF_USER | PF_PROT))) { + if (!(error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) { if (vmalloc_fault(address) >= 0) return; - - if (kmemcheck_fault(regs, address, error_code)) - return; } /* Can handle a stale RO->RW TLB: */ @@ -1325,7 +1299,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, if (unlikely(kprobes_fault(regs))) return; - if (unlikely(error_code & PF_RSVD)) + if (unlikely(error_code & X86_PF_RSVD)) pgtable_bad(regs, error_code, address); if (unlikely(smap_violation(error_code, regs))) { @@ -1351,7 +1325,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, */ if (user_mode(regs)) { local_irq_enable(); - error_code |= PF_USER; + error_code |= X86_PF_USER; flags |= FAULT_FLAG_USER; } else { if (regs->flags & X86_EFLAGS_IF) @@ -1360,9 +1334,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); - if (error_code & PF_WRITE) + if (error_code & X86_PF_WRITE) flags |= FAULT_FLAG_WRITE; - if (error_code & PF_INSTR) + if (error_code & X86_PF_INSTR) flags |= FAULT_FLAG_INSTRUCTION; /* @@ -1382,7 +1356,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, * space check, thus avoiding the deadlock: */ if (unlikely(!down_read_trylock(&mm->mmap_sem))) { - if ((error_code & PF_USER) == 0 && + if (!(error_code & X86_PF_USER) && !search_exception_tables(regs->ip)) { bad_area_nosemaphore(regs, error_code, address, NULL); return; @@ -1409,7 +1383,7 @@ retry: bad_area(regs, error_code, address); return; } - if (error_code & PF_USER) { + if (error_code & X86_PF_USER) { /* * Accessing the stack below %sp is always a bug. * The large cushion allows instructions like enter @@ -1441,7 +1415,17 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if * we get VM_FAULT_RETRY back, the mmap_sem has been unlocked. + * + * Note that handle_userfault() may also release and reacquire mmap_sem + * (and not return with VM_FAULT_RETRY), when returning to userland to + * repeat the page fault later with a VM_FAULT_NOPAGE retval + * (potentially after handling any pending signal during the return to + * userland). The return to userland is identified whenever + * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags. + * Thus we have to be careful about not touching vma after handling the + * fault, so we read the pkey beforehand. */ + pkey = vma_pkey(vma); fault = handle_mm_fault(vma, address, flags); major |= fault & VM_FAULT_MAJOR; @@ -1470,7 +1454,7 @@ good_area: up_read(&mm->mmap_sem); if (unlikely(fault & VM_FAULT_ERROR)) { - mm_fault_error(regs, error_code, address, vma, fault); + mm_fault_error(regs, error_code, address, &pkey, fault); return; } diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 6d06cf33e3de..00b296617ca4 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * IA-32 Huge TLB Page Support for Kernel. * @@ -157,6 +158,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, if (len > TASK_SIZE) return -ENOMEM; + /* No address checking. See comment at mmap_address_hint_valid() */ if (flags & MAP_FIXED) { if (prepare_hugepage_range(file, addr, len)) return -EINVAL; @@ -164,12 +166,16 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, } if (addr) { - addr = ALIGN(addr, huge_page_size(h)); + addr &= huge_page_mask(h); + if (!mmap_address_hint_valid(addr, len)) + goto get_unmapped_area; + vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vm_start_gap(vma))) + if (!vma || addr + len <= vm_start_gap(vma)) return addr; } + +get_unmapped_area: if (mm->get_unmapped_area == arch_get_unmapped_area) return hugetlb_get_unmapped_area_bottomup(file, addr, len, pgoff, flags); diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index 31cea988fa36..ab33a32df2a8 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Helper routines for building identity mapping page tables. This is * included by both the compressed kernel and the regular kernel. diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index af5c1ed21d43..6fdf91ef130a 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -92,8 +92,7 @@ __ref void *alloc_low_pages(unsigned int num) unsigned int order; order = get_order((unsigned long)num << PAGE_SHIFT); - return (void *)__get_free_pages(GFP_ATOMIC | __GFP_NOTRACK | - __GFP_ZERO, order); + return (void *)__get_free_pages(GFP_ATOMIC | __GFP_ZERO, order); } if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) { @@ -164,12 +163,11 @@ static int page_size_mask; static void __init probe_page_size_mask(void) { /* - * For CONFIG_KMEMCHECK or pagealloc debugging, identity mapping will - * use small pages. + * For pagealloc debugging, identity mapping will use small pages. * This will simplify cpa(), which otherwise needs to support splitting * large pages into small in interrupt context, etc. */ - if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled() && !IS_ENABLED(CONFIG_KMEMCHECK)) + if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled()) page_size_mask |= 1 << PG_LEVEL_2M; else direct_gbpages = 0; @@ -671,7 +669,7 @@ void __init init_mem_mapping(void) load_cr3(swapper_pg_dir); __flush_tlb_all(); - hypervisor_init_mem_mapping(); + x86_init.hyper.init_mem_mapping(); early_memtest(0, max_pfn_mapped << PAGE_SHIFT); } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 048fbe8fc274..4a837289f2ad 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -184,7 +184,7 @@ static __ref void *spp_getpage(void) void *ptr; if (after_bootmem) - ptr = (void *) get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK); + ptr = (void *) get_zeroed_page(GFP_ATOMIC); else ptr = alloc_bootmem_pages(PAGE_SIZE); @@ -1173,12 +1173,18 @@ void __init mem_init(void) /* clear_bss() already clear the empty_zero_page */ - register_page_bootmem_info(); - /* this will put all memory onto the freelists */ free_all_bootmem(); after_bootmem = 1; + /* + * Must be done after boot memory is put on freelist, because here we + * might set fields in deferred struct pages that have not yet been + * initialized, and free_all_bootmem() initializes all the reserved + * deferred pages for us. + */ + register_page_bootmem_info(); + /* Register memory areas for /proc/kcore */ kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_OTHER); @@ -1399,7 +1405,6 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, vmemmap_verify((pte_t *)pmd, node, addr, next); continue; } - pr_warn_once("vmemmap: falling back to regular page backing\n"); if (vmemmap_populate_basepages(addr, next, node)) return -ENOMEM; } @@ -1426,16 +1431,16 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE) void register_page_bootmem_memmap(unsigned long section_nr, - struct page *start_page, unsigned long size) + struct page *start_page, unsigned long nr_pages) { unsigned long addr = (unsigned long)start_page; - unsigned long end = (unsigned long)(start_page + size); + unsigned long end = (unsigned long)(start_page + nr_pages); unsigned long next; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; - unsigned int nr_pages; + unsigned int nr_pmd_pages; struct page *page; for (; addr < end; addr = next) { @@ -1482,9 +1487,9 @@ void register_page_bootmem_memmap(unsigned long section_nr, if (pmd_none(*pmd)) continue; - nr_pages = 1 << (get_order(PMD_SIZE)); + nr_pmd_pages = 1 << get_order(PMD_SIZE); page = pmd_page(*pmd); - while (nr_pages--) + while (nr_pmd_pages--) get_page_bootmem(section_nr, page++, SECTION_INFO); } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 34f0e1847dd6..6e4573b1da34 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -27,6 +27,11 @@ #include "physaddr.h" +struct ioremap_mem_flags { + bool system_ram; + bool desc_other; +}; + /* * Fix up the linear direct mapping of the kernel to avoid cache attribute * conflicts. @@ -56,17 +61,59 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, return err; } -static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, - void *arg) +static bool __ioremap_check_ram(struct resource *res) { + unsigned long start_pfn, stop_pfn; unsigned long i; - for (i = 0; i < nr_pages; ++i) - if (pfn_valid(start_pfn + i) && - !PageReserved(pfn_to_page(start_pfn + i))) - return 1; + if ((res->flags & IORESOURCE_SYSTEM_RAM) != IORESOURCE_SYSTEM_RAM) + return false; - return 0; + start_pfn = (res->start + PAGE_SIZE - 1) >> PAGE_SHIFT; + stop_pfn = (res->end + 1) >> PAGE_SHIFT; + if (stop_pfn > start_pfn) { + for (i = 0; i < (stop_pfn - start_pfn); ++i) + if (pfn_valid(start_pfn + i) && + !PageReserved(pfn_to_page(start_pfn + i))) + return true; + } + + return false; +} + +static int __ioremap_check_desc_other(struct resource *res) +{ + return (res->desc != IORES_DESC_NONE); +} + +static int __ioremap_res_check(struct resource *res, void *arg) +{ + struct ioremap_mem_flags *flags = arg; + + if (!flags->system_ram) + flags->system_ram = __ioremap_check_ram(res); + + if (!flags->desc_other) + flags->desc_other = __ioremap_check_desc_other(res); + + return flags->system_ram && flags->desc_other; +} + +/* + * To avoid multiple resource walks, this function walks resources marked as + * IORESOURCE_MEM and IORESOURCE_BUSY and looking for system RAM and/or a + * resource described not as IORES_DESC_NONE (e.g. IORES_DESC_ACPI_TABLES). + */ +static void __ioremap_check_mem(resource_size_t addr, unsigned long size, + struct ioremap_mem_flags *flags) +{ + u64 start, end; + + start = (u64)addr; + end = start + size - 1; + memset(flags, 0, sizeof(*flags)); + + walk_mem_res(start, end, flags, __ioremap_res_check); } /* @@ -87,9 +134,10 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, unsigned long size, enum page_cache_mode pcm, void *caller) { unsigned long offset, vaddr; - resource_size_t pfn, last_pfn, last_addr; + resource_size_t last_addr; const resource_size_t unaligned_phys_addr = phys_addr; const unsigned long unaligned_size = size; + struct ioremap_mem_flags mem_flags; struct vm_struct *area; enum page_cache_mode new_pcm; pgprot_t prot; @@ -108,13 +156,12 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, return NULL; } + __ioremap_check_mem(phys_addr, size, &mem_flags); + /* * Don't allow anybody to remap normal RAM that we're using.. */ - pfn = phys_addr >> PAGE_SHIFT; - last_pfn = last_addr >> PAGE_SHIFT; - if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, - __ioremap_check_ram) == 1) { + if (mem_flags.system_ram) { WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n", &phys_addr, &last_addr); return NULL; @@ -146,7 +193,15 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, pcm = new_pcm; } + /* + * If the page being mapped is in memory and SEV is active then + * make sure the memory encryption attribute is enabled in the + * resulting mapping. + */ prot = PAGE_KERNEL_IO; + if (sev_active() && mem_flags.desc_other) + prot = pgprot_encrypted(prot); + switch (pcm) { case _PAGE_CACHE_MODE_UC: default: @@ -422,6 +477,9 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) * areas should be mapped decrypted. And since the encryption key can * change across reboots, persistent memory should also be mapped * decrypted. + * + * If SEV is active, that implies that BIOS/UEFI also ran encrypted so + * only persistent memory should be mapped decrypted. */ static bool memremap_should_map_decrypted(resource_size_t phys_addr, unsigned long size) @@ -458,6 +516,11 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr, case E820_TYPE_ACPI: case E820_TYPE_NVS: case E820_TYPE_UNUSABLE: + /* For SEV, these areas are encrypted */ + if (sev_active()) + break; + /* Fallthrough */ + case E820_TYPE_PRAM: return true; default: @@ -581,7 +644,7 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size, unsigned long flags) { - if (!sme_active()) + if (!mem_encrypt_active()) return true; if (flags & MEMREMAP_ENC) @@ -590,12 +653,13 @@ bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size, if (flags & MEMREMAP_DEC) return false; - if (memremap_is_setup_data(phys_addr, size) || - memremap_is_efi_data(phys_addr, size) || - memremap_should_map_decrypted(phys_addr, size)) - return false; + if (sme_active()) { + if (memremap_is_setup_data(phys_addr, size) || + memremap_is_efi_data(phys_addr, size)) + return false; + } - return true; + return !memremap_should_map_decrypted(phys_addr, size); } /* @@ -608,17 +672,24 @@ pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr, unsigned long size, pgprot_t prot) { - if (!sme_active()) + bool encrypted_prot; + + if (!mem_encrypt_active()) return prot; - if (early_memremap_is_setup_data(phys_addr, size) || - memremap_is_efi_data(phys_addr, size) || - memremap_should_map_decrypted(phys_addr, size)) - prot = pgprot_decrypted(prot); - else - prot = pgprot_encrypted(prot); + encrypted_prot = true; + + if (sme_active()) { + if (early_memremap_is_setup_data(phys_addr, size) || + memremap_is_efi_data(phys_addr, size)) + encrypted_prot = false; + } + + if (encrypted_prot && memremap_should_map_decrypted(phys_addr, size)) + encrypted_prot = false; - return prot; + return encrypted_prot ? pgprot_encrypted(prot) + : pgprot_decrypted(prot); } bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size) diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index bc84b73684b7..99dfed6dfef8 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -1,21 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0 #define DISABLE_BRANCH_PROFILING #define pr_fmt(fmt) "kasan: " fmt #include <linux/bootmem.h> #include <linux/kasan.h> #include <linux/kdebug.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/vmalloc.h> #include <asm/e820/types.h> +#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/pgtable.h> extern struct range pfn_mapped[E820_MAX_ENTRIES]; -static int __init map_range(struct range *range) +static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); + +static __init void *early_alloc(size_t size, int nid) +{ + return memblock_virt_alloc_try_nid_nopanic(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); +} + +static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, + unsigned long end, int nid) +{ + pte_t *pte; + + if (pmd_none(*pmd)) { + void *p; + + if (boot_cpu_has(X86_FEATURE_PSE) && + ((end - addr) == PMD_SIZE) && + IS_ALIGNED(addr, PMD_SIZE)) { + p = early_alloc(PMD_SIZE, nid); + if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) + return; + else if (p) + memblock_free(__pa(p), PMD_SIZE); + } + + p = early_alloc(PAGE_SIZE, nid); + pmd_populate_kernel(&init_mm, pmd, p); + } + + pte = pte_offset_kernel(pmd, addr); + do { + pte_t entry; + void *p; + + if (!pte_none(*pte)) + continue; + + p = early_alloc(PAGE_SIZE, nid); + entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL); + set_pte_at(&init_mm, addr, pte, entry); + } while (pte++, addr += PAGE_SIZE, addr != end); +} + +static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, + unsigned long end, int nid) +{ + pmd_t *pmd; + unsigned long next; + + if (pud_none(*pud)) { + void *p; + + if (boot_cpu_has(X86_FEATURE_GBPAGES) && + ((end - addr) == PUD_SIZE) && + IS_ALIGNED(addr, PUD_SIZE)) { + p = early_alloc(PUD_SIZE, nid); + if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) + return; + else if (p) + memblock_free(__pa(p), PUD_SIZE); + } + + p = early_alloc(PAGE_SIZE, nid); + pud_populate(&init_mm, pud, p); + } + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if (!pmd_large(*pmd)) + kasan_populate_pmd(pmd, addr, next, nid); + } while (pmd++, addr = next, addr != end); +} + +static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr, + unsigned long end, int nid) +{ + pud_t *pud; + unsigned long next; + + if (p4d_none(*p4d)) { + void *p = early_alloc(PAGE_SIZE, nid); + + p4d_populate(&init_mm, p4d, p); + } + + pud = pud_offset(p4d, addr); + do { + next = pud_addr_end(addr, end); + if (!pud_large(*pud)) + kasan_populate_pud(pud, addr, next, nid); + } while (pud++, addr = next, addr != end); +} + +static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr, + unsigned long end, int nid) +{ + void *p; + p4d_t *p4d; + unsigned long next; + + if (pgd_none(*pgd)) { + p = early_alloc(PAGE_SIZE, nid); + pgd_populate(&init_mm, pgd, p); + } + + p4d = p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + kasan_populate_p4d(p4d, addr, next, nid); + } while (p4d++, addr = next, addr != end); +} + +static void __init kasan_populate_shadow(unsigned long addr, unsigned long end, + int nid) +{ + pgd_t *pgd; + unsigned long next; + + addr = addr & PAGE_MASK; + end = round_up(end, PAGE_SIZE); + pgd = pgd_offset_k(addr); + do { + next = pgd_addr_end(addr, end); + kasan_populate_pgd(pgd, addr, next, nid); + } while (pgd++, addr = next, addr != end); +} + +static void __init map_range(struct range *range) { unsigned long start; unsigned long end; @@ -23,15 +155,17 @@ static int __init map_range(struct range *range) start = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->start)); end = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->end)); - return vmemmap_populate(start, end, NUMA_NO_NODE); + kasan_populate_shadow(start, end, early_pfn_to_nid(range->start)); } static void __init clear_pgds(unsigned long start, unsigned long end) { pgd_t *pgd; + /* See comment in kasan_init() */ + unsigned long pgd_end = end & PGDIR_MASK; - for (; start < end; start += PGDIR_SIZE) { + for (; start < pgd_end; start += PGDIR_SIZE) { pgd = pgd_offset_k(start); /* * With folded p4d, pgd_clear() is nop, use p4d_clear() @@ -42,29 +176,61 @@ static void __init clear_pgds(unsigned long start, else pgd_clear(pgd); } + + pgd = pgd_offset_k(start); + for (; start < end; start += P4D_SIZE) + p4d_clear(p4d_offset(pgd, start)); +} + +static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr) +{ + unsigned long p4d; + + if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + return (p4d_t *)pgd; + + p4d = __pa_nodebug(pgd_val(*pgd)) & PTE_PFN_MASK; + p4d += __START_KERNEL_map - phys_base; + return (p4d_t *)p4d + p4d_index(addr); +} + +static void __init kasan_early_p4d_populate(pgd_t *pgd, + unsigned long addr, + unsigned long end) +{ + pgd_t pgd_entry; + p4d_t *p4d, p4d_entry; + unsigned long next; + + if (pgd_none(*pgd)) { + pgd_entry = __pgd(_KERNPG_TABLE | __pa_nodebug(kasan_zero_p4d)); + set_pgd(pgd, pgd_entry); + } + + p4d = early_p4d_offset(pgd, addr); + do { + next = p4d_addr_end(addr, end); + + if (!p4d_none(*p4d)) + continue; + + p4d_entry = __p4d(_KERNPG_TABLE | __pa_nodebug(kasan_zero_pud)); + set_p4d(p4d, p4d_entry); + } while (p4d++, addr = next, addr != end && p4d_none(*p4d)); } static void __init kasan_map_early_shadow(pgd_t *pgd) { - int i; - unsigned long start = KASAN_SHADOW_START; + /* See comment in kasan_init() */ + unsigned long addr = KASAN_SHADOW_START & PGDIR_MASK; unsigned long end = KASAN_SHADOW_END; + unsigned long next; - for (i = pgd_index(start); start < end; i++) { - switch (CONFIG_PGTABLE_LEVELS) { - case 4: - pgd[i] = __pgd(__pa_nodebug(kasan_zero_pud) | - _KERNPG_TABLE); - break; - case 5: - pgd[i] = __pgd(__pa_nodebug(kasan_zero_p4d) | - _KERNPG_TABLE); - break; - default: - BUILD_BUG(); - } - start += PGDIR_SIZE; - } + pgd += pgd_index(addr); + do { + next = pgd_addr_end(addr, end); + kasan_early_p4d_populate(pgd, addr, next); + } while (pgd++, addr = next, addr != end); } #ifdef CONFIG_KASAN_INLINE @@ -101,7 +267,7 @@ void __init kasan_early_init(void) for (i = 0; i < PTRS_PER_PUD; i++) kasan_zero_pud[i] = __pud(pud_val); - for (i = 0; CONFIG_PGTABLE_LEVELS >= 5 && i < PTRS_PER_P4D; i++) + for (i = 0; IS_ENABLED(CONFIG_X86_5LEVEL) && i < PTRS_PER_P4D; i++) kasan_zero_p4d[i] = __p4d(p4d_val); kasan_map_early_shadow(early_top_pgt); @@ -117,28 +283,51 @@ void __init kasan_init(void) #endif memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt)); + + /* + * We use the same shadow offset for 4- and 5-level paging to + * facilitate boot-time switching between paging modes. + * As result in 5-level paging mode KASAN_SHADOW_START and + * KASAN_SHADOW_END are not aligned to PGD boundary. + * + * KASAN_SHADOW_START doesn't share PGD with anything else. + * We claim whole PGD entry to make things easier. + * + * KASAN_SHADOW_END lands in the last PGD entry and it collides with + * bunch of things like kernel code, modules, EFI mapping, etc. + * We need to take extra steps to not overwrite them. + */ + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + void *ptr; + + ptr = (void *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END)); + memcpy(tmp_p4d_table, (void *)ptr, sizeof(tmp_p4d_table)); + set_pgd(&early_top_pgt[pgd_index(KASAN_SHADOW_END)], + __pgd(__pa(tmp_p4d_table) | _KERNPG_TABLE)); + } + load_cr3(early_top_pgt); __flush_tlb_all(); - clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); + clear_pgds(KASAN_SHADOW_START & PGDIR_MASK, KASAN_SHADOW_END); - kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, + kasan_populate_zero_shadow((void *)(KASAN_SHADOW_START & PGDIR_MASK), kasan_mem_to_shadow((void *)PAGE_OFFSET)); for (i = 0; i < E820_MAX_ENTRIES; i++) { if (pfn_mapped[i].end == 0) break; - if (map_range(&pfn_mapped[i])) - panic("kasan: unable to allocate shadow!"); + map_range(&pfn_mapped[i]); } + kasan_populate_zero_shadow( kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), kasan_mem_to_shadow((void *)__START_KERNEL_map)); - vmemmap_populate((unsigned long)kasan_mem_to_shadow(_stext), - (unsigned long)kasan_mem_to_shadow(_end), - NUMA_NO_NODE); + kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext), + (unsigned long)kasan_mem_to_shadow(_end), + early_pfn_to_nid(__pa(_stext))); kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), (void *)KASAN_SHADOW_END); diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index af599167fe3c..879ef930e2c2 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This file implements KASLR memory randomization for x86_64. It randomizes * the virtual address space of kernel memory regions (physical memory diff --git a/arch/x86/mm/kmemcheck/Makefile b/arch/x86/mm/kmemcheck/Makefile deleted file mode 100644 index 520b3bce4095..000000000000 --- a/arch/x86/mm/kmemcheck/Makefile +++ /dev/null @@ -1 +0,0 @@ -obj-y := error.o kmemcheck.o opcode.o pte.o selftest.o shadow.o diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c index dab41876cdd5..cec594032515 100644 --- a/arch/x86/mm/kmemcheck/error.c +++ b/arch/x86/mm/kmemcheck/error.c @@ -1,227 +1 @@ -#include <linux/interrupt.h> -#include <linux/kdebug.h> -#include <linux/kmemcheck.h> -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/ptrace.h> -#include <linux/stacktrace.h> -#include <linux/string.h> - -#include "error.h" -#include "shadow.h" - -enum kmemcheck_error_type { - KMEMCHECK_ERROR_INVALID_ACCESS, - KMEMCHECK_ERROR_BUG, -}; - -#define SHADOW_COPY_SIZE (1 << CONFIG_KMEMCHECK_SHADOW_COPY_SHIFT) - -struct kmemcheck_error { - enum kmemcheck_error_type type; - - union { - /* KMEMCHECK_ERROR_INVALID_ACCESS */ - struct { - /* Kind of access that caused the error */ - enum kmemcheck_shadow state; - /* Address and size of the erroneous read */ - unsigned long address; - unsigned int size; - }; - }; - - struct pt_regs regs; - struct stack_trace trace; - unsigned long trace_entries[32]; - - /* We compress it to a char. */ - unsigned char shadow_copy[SHADOW_COPY_SIZE]; - unsigned char memory_copy[SHADOW_COPY_SIZE]; -}; - -/* - * Create a ring queue of errors to output. We can't call printk() directly - * from the kmemcheck traps, since this may call the console drivers and - * result in a recursive fault. - */ -static struct kmemcheck_error error_fifo[CONFIG_KMEMCHECK_QUEUE_SIZE]; -static unsigned int error_count; -static unsigned int error_rd; -static unsigned int error_wr; -static unsigned int error_missed_count; - -static struct kmemcheck_error *error_next_wr(void) -{ - struct kmemcheck_error *e; - - if (error_count == ARRAY_SIZE(error_fifo)) { - ++error_missed_count; - return NULL; - } - - e = &error_fifo[error_wr]; - if (++error_wr == ARRAY_SIZE(error_fifo)) - error_wr = 0; - ++error_count; - return e; -} - -static struct kmemcheck_error *error_next_rd(void) -{ - struct kmemcheck_error *e; - - if (error_count == 0) - return NULL; - - e = &error_fifo[error_rd]; - if (++error_rd == ARRAY_SIZE(error_fifo)) - error_rd = 0; - --error_count; - return e; -} - -void kmemcheck_error_recall(void) -{ - static const char *desc[] = { - [KMEMCHECK_SHADOW_UNALLOCATED] = "unallocated", - [KMEMCHECK_SHADOW_UNINITIALIZED] = "uninitialized", - [KMEMCHECK_SHADOW_INITIALIZED] = "initialized", - [KMEMCHECK_SHADOW_FREED] = "freed", - }; - - static const char short_desc[] = { - [KMEMCHECK_SHADOW_UNALLOCATED] = 'a', - [KMEMCHECK_SHADOW_UNINITIALIZED] = 'u', - [KMEMCHECK_SHADOW_INITIALIZED] = 'i', - [KMEMCHECK_SHADOW_FREED] = 'f', - }; - - struct kmemcheck_error *e; - unsigned int i; - - e = error_next_rd(); - if (!e) - return; - - switch (e->type) { - case KMEMCHECK_ERROR_INVALID_ACCESS: - printk(KERN_WARNING "WARNING: kmemcheck: Caught %d-bit read from %s memory (%p)\n", - 8 * e->size, e->state < ARRAY_SIZE(desc) ? - desc[e->state] : "(invalid shadow state)", - (void *) e->address); - - printk(KERN_WARNING); - for (i = 0; i < SHADOW_COPY_SIZE; ++i) - printk(KERN_CONT "%02x", e->memory_copy[i]); - printk(KERN_CONT "\n"); - - printk(KERN_WARNING); - for (i = 0; i < SHADOW_COPY_SIZE; ++i) { - if (e->shadow_copy[i] < ARRAY_SIZE(short_desc)) - printk(KERN_CONT " %c", short_desc[e->shadow_copy[i]]); - else - printk(KERN_CONT " ?"); - } - printk(KERN_CONT "\n"); - printk(KERN_WARNING "%*c\n", 2 + 2 - * (int) (e->address & (SHADOW_COPY_SIZE - 1)), '^'); - break; - case KMEMCHECK_ERROR_BUG: - printk(KERN_EMERG "ERROR: kmemcheck: Fatal error\n"); - break; - } - - __show_regs(&e->regs, 1); - print_stack_trace(&e->trace, 0); -} - -static void do_wakeup(unsigned long data) -{ - while (error_count > 0) - kmemcheck_error_recall(); - - if (error_missed_count > 0) { - printk(KERN_WARNING "kmemcheck: Lost %d error reports because " - "the queue was too small\n", error_missed_count); - error_missed_count = 0; - } -} - -static DECLARE_TASKLET(kmemcheck_tasklet, &do_wakeup, 0); - -/* - * Save the context of an error report. - */ -void kmemcheck_error_save(enum kmemcheck_shadow state, - unsigned long address, unsigned int size, struct pt_regs *regs) -{ - static unsigned long prev_ip; - - struct kmemcheck_error *e; - void *shadow_copy; - void *memory_copy; - - /* Don't report several adjacent errors from the same EIP. */ - if (regs->ip == prev_ip) - return; - prev_ip = regs->ip; - - e = error_next_wr(); - if (!e) - return; - - e->type = KMEMCHECK_ERROR_INVALID_ACCESS; - - e->state = state; - e->address = address; - e->size = size; - - /* Save regs */ - memcpy(&e->regs, regs, sizeof(*regs)); - - /* Save stack trace */ - e->trace.nr_entries = 0; - e->trace.entries = e->trace_entries; - e->trace.max_entries = ARRAY_SIZE(e->trace_entries); - e->trace.skip = 0; - save_stack_trace_regs(regs, &e->trace); - - /* Round address down to nearest 16 bytes */ - shadow_copy = kmemcheck_shadow_lookup(address - & ~(SHADOW_COPY_SIZE - 1)); - BUG_ON(!shadow_copy); - - memcpy(e->shadow_copy, shadow_copy, SHADOW_COPY_SIZE); - - kmemcheck_show_addr(address); - memory_copy = (void *) (address & ~(SHADOW_COPY_SIZE - 1)); - memcpy(e->memory_copy, memory_copy, SHADOW_COPY_SIZE); - kmemcheck_hide_addr(address); - - tasklet_hi_schedule_first(&kmemcheck_tasklet); -} - -/* - * Save the context of a kmemcheck bug. - */ -void kmemcheck_error_save_bug(struct pt_regs *regs) -{ - struct kmemcheck_error *e; - - e = error_next_wr(); - if (!e) - return; - - e->type = KMEMCHECK_ERROR_BUG; - - memcpy(&e->regs, regs, sizeof(*regs)); - - e->trace.nr_entries = 0; - e->trace.entries = e->trace_entries; - e->trace.max_entries = ARRAY_SIZE(e->trace_entries); - e->trace.skip = 1; - save_stack_trace(&e->trace); - - tasklet_hi_schedule_first(&kmemcheck_tasklet); -} +// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h index 0efc2e8d0a20..ea32a7d3cf1b 100644 --- a/arch/x86/mm/kmemcheck/error.h +++ b/arch/x86/mm/kmemcheck/error.h @@ -1,15 +1 @@ -#ifndef ARCH__X86__MM__KMEMCHECK__ERROR_H -#define ARCH__X86__MM__KMEMCHECK__ERROR_H - -#include <linux/ptrace.h> - -#include "shadow.h" - -void kmemcheck_error_save(enum kmemcheck_shadow state, - unsigned long address, unsigned int size, struct pt_regs *regs); - -void kmemcheck_error_save_bug(struct pt_regs *regs); - -void kmemcheck_error_recall(void); - -#endif +/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c deleted file mode 100644 index 4515bae36bbe..000000000000 --- a/arch/x86/mm/kmemcheck/kmemcheck.c +++ /dev/null @@ -1,658 +0,0 @@ -/** - * kmemcheck - a heavyweight memory checker for the linux kernel - * Copyright (C) 2007, 2008 Vegard Nossum <vegardno@ifi.uio.no> - * (With a lot of help from Ingo Molnar and Pekka Enberg.) - * - * 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/init.h> -#include <linux/interrupt.h> -#include <linux/kallsyms.h> -#include <linux/kernel.h> -#include <linux/kmemcheck.h> -#include <linux/mm.h> -#include <linux/page-flags.h> -#include <linux/percpu.h> -#include <linux/ptrace.h> -#include <linux/string.h> -#include <linux/types.h> - -#include <asm/cacheflush.h> -#include <asm/kmemcheck.h> -#include <asm/pgtable.h> -#include <asm/tlbflush.h> - -#include "error.h" -#include "opcode.h" -#include "pte.h" -#include "selftest.h" -#include "shadow.h" - - -#ifdef CONFIG_KMEMCHECK_DISABLED_BY_DEFAULT -# define KMEMCHECK_ENABLED 0 -#endif - -#ifdef CONFIG_KMEMCHECK_ENABLED_BY_DEFAULT -# define KMEMCHECK_ENABLED 1 -#endif - -#ifdef CONFIG_KMEMCHECK_ONESHOT_BY_DEFAULT -# define KMEMCHECK_ENABLED 2 -#endif - -int kmemcheck_enabled = KMEMCHECK_ENABLED; - -int __init kmemcheck_init(void) -{ -#ifdef CONFIG_SMP - /* - * Limit SMP to use a single CPU. We rely on the fact that this code - * runs before SMP is set up. - */ - if (setup_max_cpus > 1) { - printk(KERN_INFO - "kmemcheck: Limiting number of CPUs to 1.\n"); - setup_max_cpus = 1; - } -#endif - - if (!kmemcheck_selftest()) { - printk(KERN_INFO "kmemcheck: self-tests failed; disabling\n"); - kmemcheck_enabled = 0; - return -EINVAL; - } - - printk(KERN_INFO "kmemcheck: Initialized\n"); - return 0; -} - -early_initcall(kmemcheck_init); - -/* - * We need to parse the kmemcheck= option before any memory is allocated. - */ -static int __init param_kmemcheck(char *str) -{ - int val; - int ret; - - if (!str) - return -EINVAL; - - ret = kstrtoint(str, 0, &val); - if (ret) - return ret; - kmemcheck_enabled = val; - return 0; -} - -early_param("kmemcheck", param_kmemcheck); - -int kmemcheck_show_addr(unsigned long address) -{ - pte_t *pte; - - pte = kmemcheck_pte_lookup(address); - if (!pte) - return 0; - - set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); - __flush_tlb_one(address); - return 1; -} - -int kmemcheck_hide_addr(unsigned long address) -{ - pte_t *pte; - - pte = kmemcheck_pte_lookup(address); - if (!pte) - return 0; - - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); - __flush_tlb_one(address); - return 1; -} - -struct kmemcheck_context { - bool busy; - int balance; - - /* - * There can be at most two memory operands to an instruction, but - * each address can cross a page boundary -- so we may need up to - * four addresses that must be hidden/revealed for each fault. - */ - unsigned long addr[4]; - unsigned long n_addrs; - unsigned long flags; - - /* Data size of the instruction that caused a fault. */ - unsigned int size; -}; - -static DEFINE_PER_CPU(struct kmemcheck_context, kmemcheck_context); - -bool kmemcheck_active(struct pt_regs *regs) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - - return data->balance > 0; -} - -/* Save an address that needs to be shown/hidden */ -static void kmemcheck_save_addr(unsigned long addr) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - - BUG_ON(data->n_addrs >= ARRAY_SIZE(data->addr)); - data->addr[data->n_addrs++] = addr; -} - -static unsigned int kmemcheck_show_all(void) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - unsigned int i; - unsigned int n; - - n = 0; - for (i = 0; i < data->n_addrs; ++i) - n += kmemcheck_show_addr(data->addr[i]); - - return n; -} - -static unsigned int kmemcheck_hide_all(void) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - unsigned int i; - unsigned int n; - - n = 0; - for (i = 0; i < data->n_addrs; ++i) - n += kmemcheck_hide_addr(data->addr[i]); - - return n; -} - -/* - * Called from the #PF handler. - */ -void kmemcheck_show(struct pt_regs *regs) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - - BUG_ON(!irqs_disabled()); - - if (unlikely(data->balance != 0)) { - kmemcheck_show_all(); - kmemcheck_error_save_bug(regs); - data->balance = 0; - return; - } - - /* - * None of the addresses actually belonged to kmemcheck. Note that - * this is not an error. - */ - if (kmemcheck_show_all() == 0) - return; - - ++data->balance; - - /* - * The IF needs to be cleared as well, so that the faulting - * instruction can run "uninterrupted". Otherwise, we might take - * an interrupt and start executing that before we've had a chance - * to hide the page again. - * - * NOTE: In the rare case of multiple faults, we must not override - * the original flags: - */ - if (!(regs->flags & X86_EFLAGS_TF)) - data->flags = regs->flags; - - regs->flags |= X86_EFLAGS_TF; - regs->flags &= ~X86_EFLAGS_IF; -} - -/* - * Called from the #DB handler. - */ -void kmemcheck_hide(struct pt_regs *regs) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - int n; - - BUG_ON(!irqs_disabled()); - - if (unlikely(data->balance != 1)) { - kmemcheck_show_all(); - kmemcheck_error_save_bug(regs); - data->n_addrs = 0; - data->balance = 0; - - if (!(data->flags & X86_EFLAGS_TF)) - regs->flags &= ~X86_EFLAGS_TF; - if (data->flags & X86_EFLAGS_IF) - regs->flags |= X86_EFLAGS_IF; - return; - } - - if (kmemcheck_enabled) - n = kmemcheck_hide_all(); - else - n = kmemcheck_show_all(); - - if (n == 0) - return; - - --data->balance; - - data->n_addrs = 0; - - if (!(data->flags & X86_EFLAGS_TF)) - regs->flags &= ~X86_EFLAGS_TF; - if (data->flags & X86_EFLAGS_IF) - regs->flags |= X86_EFLAGS_IF; -} - -void kmemcheck_show_pages(struct page *p, unsigned int n) -{ - unsigned int i; - - for (i = 0; i < n; ++i) { - unsigned long address; - pte_t *pte; - unsigned int level; - - address = (unsigned long) page_address(&p[i]); - pte = lookup_address(address, &level); - BUG_ON(!pte); - BUG_ON(level != PG_LEVEL_4K); - - set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_HIDDEN)); - __flush_tlb_one(address); - } -} - -bool kmemcheck_page_is_tracked(struct page *p) -{ - /* This will also check the "hidden" flag of the PTE. */ - return kmemcheck_pte_lookup((unsigned long) page_address(p)); -} - -void kmemcheck_hide_pages(struct page *p, unsigned int n) -{ - unsigned int i; - - for (i = 0; i < n; ++i) { - unsigned long address; - pte_t *pte; - unsigned int level; - - address = (unsigned long) page_address(&p[i]); - pte = lookup_address(address, &level); - BUG_ON(!pte); - BUG_ON(level != PG_LEVEL_4K); - - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); - set_pte(pte, __pte(pte_val(*pte) | _PAGE_HIDDEN)); - __flush_tlb_one(address); - } -} - -/* Access may NOT cross page boundary */ -static void kmemcheck_read_strict(struct pt_regs *regs, - unsigned long addr, unsigned int size) -{ - void *shadow; - enum kmemcheck_shadow status; - - shadow = kmemcheck_shadow_lookup(addr); - if (!shadow) - return; - - kmemcheck_save_addr(addr); - status = kmemcheck_shadow_test(shadow, size); - if (status == KMEMCHECK_SHADOW_INITIALIZED) - return; - - if (kmemcheck_enabled) - kmemcheck_error_save(status, addr, size, regs); - - if (kmemcheck_enabled == 2) - kmemcheck_enabled = 0; - - /* Don't warn about it again. */ - kmemcheck_shadow_set(shadow, size); -} - -bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size) -{ - enum kmemcheck_shadow status; - void *shadow; - - shadow = kmemcheck_shadow_lookup(addr); - if (!shadow) - return true; - - status = kmemcheck_shadow_test_all(shadow, size); - - return status == KMEMCHECK_SHADOW_INITIALIZED; -} - -/* Access may cross page boundary */ -static void kmemcheck_read(struct pt_regs *regs, - unsigned long addr, unsigned int size) -{ - unsigned long page = addr & PAGE_MASK; - unsigned long next_addr = addr + size - 1; - unsigned long next_page = next_addr & PAGE_MASK; - - if (likely(page == next_page)) { - kmemcheck_read_strict(regs, addr, size); - return; - } - - /* - * What we do is basically to split the access across the - * two pages and handle each part separately. Yes, this means - * that we may now see reads that are 3 + 5 bytes, for - * example (and if both are uninitialized, there will be two - * reports), but it makes the code a lot simpler. - */ - kmemcheck_read_strict(regs, addr, next_page - addr); - kmemcheck_read_strict(regs, next_page, next_addr - next_page); -} - -static void kmemcheck_write_strict(struct pt_regs *regs, - unsigned long addr, unsigned int size) -{ - void *shadow; - - shadow = kmemcheck_shadow_lookup(addr); - if (!shadow) - return; - - kmemcheck_save_addr(addr); - kmemcheck_shadow_set(shadow, size); -} - -static void kmemcheck_write(struct pt_regs *regs, - unsigned long addr, unsigned int size) -{ - unsigned long page = addr & PAGE_MASK; - unsigned long next_addr = addr + size - 1; - unsigned long next_page = next_addr & PAGE_MASK; - - if (likely(page == next_page)) { - kmemcheck_write_strict(regs, addr, size); - return; - } - - /* See comment in kmemcheck_read(). */ - kmemcheck_write_strict(regs, addr, next_page - addr); - kmemcheck_write_strict(regs, next_page, next_addr - next_page); -} - -/* - * Copying is hard. We have two addresses, each of which may be split across - * a page (and each page will have different shadow addresses). - */ -static void kmemcheck_copy(struct pt_regs *regs, - unsigned long src_addr, unsigned long dst_addr, unsigned int size) -{ - uint8_t shadow[8]; - enum kmemcheck_shadow status; - - unsigned long page; - unsigned long next_addr; - unsigned long next_page; - - uint8_t *x; - unsigned int i; - unsigned int n; - - BUG_ON(size > sizeof(shadow)); - - page = src_addr & PAGE_MASK; - next_addr = src_addr + size - 1; - next_page = next_addr & PAGE_MASK; - - if (likely(page == next_page)) { - /* Same page */ - x = kmemcheck_shadow_lookup(src_addr); - if (x) { - kmemcheck_save_addr(src_addr); - for (i = 0; i < size; ++i) - shadow[i] = x[i]; - } else { - for (i = 0; i < size; ++i) - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - } else { - n = next_page - src_addr; - BUG_ON(n > sizeof(shadow)); - - /* First page */ - x = kmemcheck_shadow_lookup(src_addr); - if (x) { - kmemcheck_save_addr(src_addr); - for (i = 0; i < n; ++i) - shadow[i] = x[i]; - } else { - /* Not tracked */ - for (i = 0; i < n; ++i) - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - - /* Second page */ - x = kmemcheck_shadow_lookup(next_page); - if (x) { - kmemcheck_save_addr(next_page); - for (i = n; i < size; ++i) - shadow[i] = x[i - n]; - } else { - /* Not tracked */ - for (i = n; i < size; ++i) - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - } - - page = dst_addr & PAGE_MASK; - next_addr = dst_addr + size - 1; - next_page = next_addr & PAGE_MASK; - - if (likely(page == next_page)) { - /* Same page */ - x = kmemcheck_shadow_lookup(dst_addr); - if (x) { - kmemcheck_save_addr(dst_addr); - for (i = 0; i < size; ++i) { - x[i] = shadow[i]; - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - } - } else { - n = next_page - dst_addr; - BUG_ON(n > sizeof(shadow)); - - /* First page */ - x = kmemcheck_shadow_lookup(dst_addr); - if (x) { - kmemcheck_save_addr(dst_addr); - for (i = 0; i < n; ++i) { - x[i] = shadow[i]; - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - } - - /* Second page */ - x = kmemcheck_shadow_lookup(next_page); - if (x) { - kmemcheck_save_addr(next_page); - for (i = n; i < size; ++i) { - x[i - n] = shadow[i]; - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - } - } - - status = kmemcheck_shadow_test(shadow, size); - if (status == KMEMCHECK_SHADOW_INITIALIZED) - return; - - if (kmemcheck_enabled) - kmemcheck_error_save(status, src_addr, size, regs); - - if (kmemcheck_enabled == 2) - kmemcheck_enabled = 0; -} - -enum kmemcheck_method { - KMEMCHECK_READ, - KMEMCHECK_WRITE, -}; - -static void kmemcheck_access(struct pt_regs *regs, - unsigned long fallback_address, enum kmemcheck_method fallback_method) -{ - const uint8_t *insn; - const uint8_t *insn_primary; - unsigned int size; - - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - - /* Recursive fault -- ouch. */ - if (data->busy) { - kmemcheck_show_addr(fallback_address); - kmemcheck_error_save_bug(regs); - return; - } - - data->busy = true; - - insn = (const uint8_t *) regs->ip; - insn_primary = kmemcheck_opcode_get_primary(insn); - - kmemcheck_opcode_decode(insn, &size); - - switch (insn_primary[0]) { -#ifdef CONFIG_KMEMCHECK_BITOPS_OK - /* AND, OR, XOR */ - /* - * Unfortunately, these instructions have to be excluded from - * our regular checking since they access only some (and not - * all) bits. This clears out "bogus" bitfield-access warnings. - */ - case 0x80: - case 0x81: - case 0x82: - case 0x83: - switch ((insn_primary[1] >> 3) & 7) { - /* OR */ - case 1: - /* AND */ - case 4: - /* XOR */ - case 6: - kmemcheck_write(regs, fallback_address, size); - goto out; - - /* ADD */ - case 0: - /* ADC */ - case 2: - /* SBB */ - case 3: - /* SUB */ - case 5: - /* CMP */ - case 7: - break; - } - break; -#endif - - /* MOVS, MOVSB, MOVSW, MOVSD */ - case 0xa4: - case 0xa5: - /* - * These instructions are special because they take two - * addresses, but we only get one page fault. - */ - kmemcheck_copy(regs, regs->si, regs->di, size); - goto out; - - /* CMPS, CMPSB, CMPSW, CMPSD */ - case 0xa6: - case 0xa7: - kmemcheck_read(regs, regs->si, size); - kmemcheck_read(regs, regs->di, size); - goto out; - } - - /* - * If the opcode isn't special in any way, we use the data from the - * page fault handler to determine the address and type of memory - * access. - */ - switch (fallback_method) { - case KMEMCHECK_READ: - kmemcheck_read(regs, fallback_address, size); - goto out; - case KMEMCHECK_WRITE: - kmemcheck_write(regs, fallback_address, size); - goto out; - } - -out: - data->busy = false; -} - -bool kmemcheck_fault(struct pt_regs *regs, unsigned long address, - unsigned long error_code) -{ - pte_t *pte; - - /* - * XXX: Is it safe to assume that memory accesses from virtual 86 - * mode or non-kernel code segments will _never_ access kernel - * memory (e.g. tracked pages)? For now, we need this to avoid - * invoking kmemcheck for PnP BIOS calls. - */ - if (regs->flags & X86_VM_MASK) - return false; - if (regs->cs != __KERNEL_CS) - return false; - - pte = kmemcheck_pte_lookup(address); - if (!pte) - return false; - - WARN_ON_ONCE(in_nmi()); - - if (error_code & 2) - kmemcheck_access(regs, address, KMEMCHECK_WRITE); - else - kmemcheck_access(regs, address, KMEMCHECK_READ); - - kmemcheck_show(regs); - return true; -} - -bool kmemcheck_trap(struct pt_regs *regs) -{ - if (!kmemcheck_active(regs)) - return false; - - /* We're done. */ - kmemcheck_hide(regs); - return true; -} diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c index 324aa3f07237..cec594032515 100644 --- a/arch/x86/mm/kmemcheck/opcode.c +++ b/arch/x86/mm/kmemcheck/opcode.c @@ -1,106 +1 @@ -#include <linux/types.h> - -#include "opcode.h" - -static bool opcode_is_prefix(uint8_t b) -{ - return - /* Group 1 */ - b == 0xf0 || b == 0xf2 || b == 0xf3 - /* Group 2 */ - || b == 0x2e || b == 0x36 || b == 0x3e || b == 0x26 - || b == 0x64 || b == 0x65 - /* Group 3 */ - || b == 0x66 - /* Group 4 */ - || b == 0x67; -} - -#ifdef CONFIG_X86_64 -static bool opcode_is_rex_prefix(uint8_t b) -{ - return (b & 0xf0) == 0x40; -} -#else -static bool opcode_is_rex_prefix(uint8_t b) -{ - return false; -} -#endif - -#define REX_W (1 << 3) - -/* - * This is a VERY crude opcode decoder. We only need to find the size of the - * load/store that caused our #PF and this should work for all the opcodes - * that we care about. Moreover, the ones who invented this instruction set - * should be shot. - */ -void kmemcheck_opcode_decode(const uint8_t *op, unsigned int *size) -{ - /* Default operand size */ - int operand_size_override = 4; - - /* prefixes */ - for (; opcode_is_prefix(*op); ++op) { - if (*op == 0x66) - operand_size_override = 2; - } - - /* REX prefix */ - if (opcode_is_rex_prefix(*op)) { - uint8_t rex = *op; - - ++op; - if (rex & REX_W) { - switch (*op) { - case 0x63: - *size = 4; - return; - case 0x0f: - ++op; - - switch (*op) { - case 0xb6: - case 0xbe: - *size = 1; - return; - case 0xb7: - case 0xbf: - *size = 2; - return; - } - - break; - } - - *size = 8; - return; - } - } - - /* escape opcode */ - if (*op == 0x0f) { - ++op; - - /* - * This is move with zero-extend and sign-extend, respectively; - * we don't have to think about 0xb6/0xbe, because this is - * already handled in the conditional below. - */ - if (*op == 0xb7 || *op == 0xbf) - operand_size_override = 2; - } - - *size = (*op & 1) ? operand_size_override : 1; -} - -const uint8_t *kmemcheck_opcode_get_primary(const uint8_t *op) -{ - /* skip prefixes */ - while (opcode_is_prefix(*op)) - ++op; - if (opcode_is_rex_prefix(*op)) - ++op; - return op; -} +// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h index 6956aad66b5b..ea32a7d3cf1b 100644 --- a/arch/x86/mm/kmemcheck/opcode.h +++ b/arch/x86/mm/kmemcheck/opcode.h @@ -1,9 +1 @@ -#ifndef ARCH__X86__MM__KMEMCHECK__OPCODE_H -#define ARCH__X86__MM__KMEMCHECK__OPCODE_H - -#include <linux/types.h> - -void kmemcheck_opcode_decode(const uint8_t *op, unsigned int *size); -const uint8_t *kmemcheck_opcode_get_primary(const uint8_t *op); - -#endif +/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c index 4ead26eeaf96..cec594032515 100644 --- a/arch/x86/mm/kmemcheck/pte.c +++ b/arch/x86/mm/kmemcheck/pte.c @@ -1,22 +1 @@ -#include <linux/mm.h> - -#include <asm/pgtable.h> - -#include "pte.h" - -pte_t *kmemcheck_pte_lookup(unsigned long address) -{ - pte_t *pte; - unsigned int level; - - pte = lookup_address(address, &level); - if (!pte) - return NULL; - if (level != PG_LEVEL_4K) - return NULL; - if (!pte_hidden(*pte)) - return NULL; - - return pte; -} - +// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h index 9f5966456492..ea32a7d3cf1b 100644 --- a/arch/x86/mm/kmemcheck/pte.h +++ b/arch/x86/mm/kmemcheck/pte.h @@ -1,10 +1 @@ -#ifndef ARCH__X86__MM__KMEMCHECK__PTE_H -#define ARCH__X86__MM__KMEMCHECK__PTE_H - -#include <linux/mm.h> - -#include <asm/pgtable.h> - -pte_t *kmemcheck_pte_lookup(unsigned long address); - -#endif +/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c index aef7140c0063..cec594032515 100644 --- a/arch/x86/mm/kmemcheck/selftest.c +++ b/arch/x86/mm/kmemcheck/selftest.c @@ -1,70 +1 @@ -#include <linux/bug.h> -#include <linux/kernel.h> - -#include "opcode.h" -#include "selftest.h" - -struct selftest_opcode { - unsigned int expected_size; - const uint8_t *insn; - const char *desc; -}; - -static const struct selftest_opcode selftest_opcodes[] = { - /* REP MOVS */ - {1, "\xf3\xa4", "rep movsb <mem8>, <mem8>"}, - {4, "\xf3\xa5", "rep movsl <mem32>, <mem32>"}, - - /* MOVZX / MOVZXD */ - {1, "\x66\x0f\xb6\x51\xf8", "movzwq <mem8>, <reg16>"}, - {1, "\x0f\xb6\x51\xf8", "movzwq <mem8>, <reg32>"}, - - /* MOVSX / MOVSXD */ - {1, "\x66\x0f\xbe\x51\xf8", "movswq <mem8>, <reg16>"}, - {1, "\x0f\xbe\x51\xf8", "movswq <mem8>, <reg32>"}, - -#ifdef CONFIG_X86_64 - /* MOVZX / MOVZXD */ - {1, "\x49\x0f\xb6\x51\xf8", "movzbq <mem8>, <reg64>"}, - {2, "\x49\x0f\xb7\x51\xf8", "movzbq <mem16>, <reg64>"}, - - /* MOVSX / MOVSXD */ - {1, "\x49\x0f\xbe\x51\xf8", "movsbq <mem8>, <reg64>"}, - {2, "\x49\x0f\xbf\x51\xf8", "movsbq <mem16>, <reg64>"}, - {4, "\x49\x63\x51\xf8", "movslq <mem32>, <reg64>"}, -#endif -}; - -static bool selftest_opcode_one(const struct selftest_opcode *op) -{ - unsigned size; - - kmemcheck_opcode_decode(op->insn, &size); - - if (size == op->expected_size) - return true; - - printk(KERN_WARNING "kmemcheck: opcode %s: expected size %d, got %d\n", - op->desc, op->expected_size, size); - return false; -} - -static bool selftest_opcodes_all(void) -{ - bool pass = true; - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(selftest_opcodes); ++i) - pass = pass && selftest_opcode_one(&selftest_opcodes[i]); - - return pass; -} - -bool kmemcheck_selftest(void) -{ - bool pass = true; - - pass = pass && selftest_opcodes_all(); - - return pass; -} +// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h index 8fed4fe11f95..ea32a7d3cf1b 100644 --- a/arch/x86/mm/kmemcheck/selftest.h +++ b/arch/x86/mm/kmemcheck/selftest.h @@ -1,6 +1 @@ -#ifndef ARCH_X86_MM_KMEMCHECK_SELFTEST_H -#define ARCH_X86_MM_KMEMCHECK_SELFTEST_H - -bool kmemcheck_selftest(void); - -#endif +/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/shadow.c b/arch/x86/mm/kmemcheck/shadow.c deleted file mode 100644 index c2638a7d2c10..000000000000 --- a/arch/x86/mm/kmemcheck/shadow.c +++ /dev/null @@ -1,173 +0,0 @@ -#include <linux/kmemcheck.h> -#include <linux/export.h> -#include <linux/mm.h> - -#include <asm/page.h> -#include <asm/pgtable.h> - -#include "pte.h" -#include "shadow.h" - -/* - * Return the shadow address for the given address. Returns NULL if the - * address is not tracked. - * - * We need to be extremely careful not to follow any invalid pointers, - * because this function can be called for *any* possible address. - */ -void *kmemcheck_shadow_lookup(unsigned long address) -{ - pte_t *pte; - struct page *page; - - if (!virt_addr_valid(address)) - return NULL; - - pte = kmemcheck_pte_lookup(address); - if (!pte) - return NULL; - - page = virt_to_page(address); - if (!page->shadow) - return NULL; - return page->shadow + (address & (PAGE_SIZE - 1)); -} - -static void mark_shadow(void *address, unsigned int n, - enum kmemcheck_shadow status) -{ - unsigned long addr = (unsigned long) address; - unsigned long last_addr = addr + n - 1; - unsigned long page = addr & PAGE_MASK; - unsigned long last_page = last_addr & PAGE_MASK; - unsigned int first_n; - void *shadow; - - /* If the memory range crosses a page boundary, stop there. */ - if (page == last_page) - first_n = n; - else - first_n = page + PAGE_SIZE - addr; - - shadow = kmemcheck_shadow_lookup(addr); - if (shadow) - memset(shadow, status, first_n); - - addr += first_n; - n -= first_n; - - /* Do full-page memset()s. */ - while (n >= PAGE_SIZE) { - shadow = kmemcheck_shadow_lookup(addr); - if (shadow) - memset(shadow, status, PAGE_SIZE); - - addr += PAGE_SIZE; - n -= PAGE_SIZE; - } - - /* Do the remaining page, if any. */ - if (n > 0) { - shadow = kmemcheck_shadow_lookup(addr); - if (shadow) - memset(shadow, status, n); - } -} - -void kmemcheck_mark_unallocated(void *address, unsigned int n) -{ - mark_shadow(address, n, KMEMCHECK_SHADOW_UNALLOCATED); -} - -void kmemcheck_mark_uninitialized(void *address, unsigned int n) -{ - mark_shadow(address, n, KMEMCHECK_SHADOW_UNINITIALIZED); -} - -/* - * Fill the shadow memory of the given address such that the memory at that - * address is marked as being initialized. - */ -void kmemcheck_mark_initialized(void *address, unsigned int n) -{ - mark_shadow(address, n, KMEMCHECK_SHADOW_INITIALIZED); -} -EXPORT_SYMBOL_GPL(kmemcheck_mark_initialized); - -void kmemcheck_mark_freed(void *address, unsigned int n) -{ - mark_shadow(address, n, KMEMCHECK_SHADOW_FREED); -} - -void kmemcheck_mark_unallocated_pages(struct page *p, unsigned int n) -{ - unsigned int i; - - for (i = 0; i < n; ++i) - kmemcheck_mark_unallocated(page_address(&p[i]), PAGE_SIZE); -} - -void kmemcheck_mark_uninitialized_pages(struct page *p, unsigned int n) -{ - unsigned int i; - - for (i = 0; i < n; ++i) - kmemcheck_mark_uninitialized(page_address(&p[i]), PAGE_SIZE); -} - -void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n) -{ - unsigned int i; - - for (i = 0; i < n; ++i) - kmemcheck_mark_initialized(page_address(&p[i]), PAGE_SIZE); -} - -enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size) -{ -#ifdef CONFIG_KMEMCHECK_PARTIAL_OK - uint8_t *x; - unsigned int i; - - x = shadow; - - /* - * Make sure _some_ bytes are initialized. Gcc frequently generates - * code to access neighboring bytes. - */ - for (i = 0; i < size; ++i) { - if (x[i] == KMEMCHECK_SHADOW_INITIALIZED) - return x[i]; - } - - return x[0]; -#else - return kmemcheck_shadow_test_all(shadow, size); -#endif -} - -enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow, unsigned int size) -{ - uint8_t *x; - unsigned int i; - - x = shadow; - - /* All bytes must be initialized. */ - for (i = 0; i < size; ++i) { - if (x[i] != KMEMCHECK_SHADOW_INITIALIZED) - return x[i]; - } - - return x[0]; -} - -void kmemcheck_shadow_set(void *shadow, unsigned int size) -{ - uint8_t *x; - unsigned int i; - - x = shadow; - for (i = 0; i < size; ++i) - x[i] = KMEMCHECK_SHADOW_INITIALIZED; -} diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h index ff0b2f70fbcb..ea32a7d3cf1b 100644 --- a/arch/x86/mm/kmemcheck/shadow.h +++ b/arch/x86/mm/kmemcheck/shadow.h @@ -1,18 +1 @@ -#ifndef ARCH__X86__MM__KMEMCHECK__SHADOW_H -#define ARCH__X86__MM__KMEMCHECK__SHADOW_H - -enum kmemcheck_shadow { - KMEMCHECK_SHADOW_UNALLOCATED, - KMEMCHECK_SHADOW_UNINITIALIZED, - KMEMCHECK_SHADOW_INITIALIZED, - KMEMCHECK_SHADOW_FREED, -}; - -void *kmemcheck_shadow_lookup(unsigned long address); - -enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size); -enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow, - unsigned int size); -void kmemcheck_shadow_set(void *shadow, unsigned int size); - -#endif +/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index afc47f5c9531..c21c2ed04612 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Support for MMIO probes. * Benfit many code from kprobes * (C) 2002 Louis Zhuang <louis.zhuang@intel.com>. diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 3fcc8e01683b..d9a9e9fc75dd 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -10,6 +10,8 @@ * published by the Free Software Foundation. */ +#define DISABLE_BRANCH_PROFILING + #include <linux/linkage.h> #include <linux/init.h> #include <linux/mm.h> @@ -28,6 +30,8 @@ #include <asm/msr.h> #include <asm/cmdline.h> +#include "mm_internal.h" + static char sme_cmdline_arg[] __initdata = "mem_encrypt"; static char sme_cmdline_on[] __initdata = "on"; static char sme_cmdline_off[] __initdata = "off"; @@ -38,7 +42,11 @@ static char sme_cmdline_off[] __initdata = "off"; * section is later cleared. */ u64 sme_me_mask __section(.data) = 0; -EXPORT_SYMBOL_GPL(sme_me_mask); +EXPORT_SYMBOL(sme_me_mask); +DEFINE_STATIC_KEY_FALSE(sev_enable_key); +EXPORT_SYMBOL_GPL(sev_enable_key); + +static bool sev_enabled __section(.data); /* Buffer used for early in-place encryption by BSP, no locking needed */ static char sme_early_buffer[PAGE_SIZE] __aligned(PAGE_SIZE); @@ -61,7 +69,6 @@ static void __init __sme_early_enc_dec(resource_size_t paddr, if (!sme_me_mask) return; - local_flush_tlb(); wbinvd(); /* @@ -188,8 +195,238 @@ void __init sme_early_init(void) /* Update the protection map with memory encryption mask */ for (i = 0; i < ARRAY_SIZE(protection_map); i++) protection_map[i] = pgprot_encrypted(protection_map[i]); + + if (sev_active()) + swiotlb_force = SWIOTLB_FORCE; +} + +static void *sev_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) +{ + unsigned long dma_mask; + unsigned int order; + struct page *page; + void *vaddr = NULL; + + dma_mask = dma_alloc_coherent_mask(dev, gfp); + order = get_order(size); + + /* + * Memory will be memset to zero after marking decrypted, so don't + * bother clearing it before. + */ + gfp &= ~__GFP_ZERO; + + page = alloc_pages_node(dev_to_node(dev), gfp, order); + if (page) { + dma_addr_t addr; + + /* + * Since we will be clearing the encryption bit, check the + * mask with it already cleared. + */ + addr = __sme_clr(phys_to_dma(dev, page_to_phys(page))); + if ((addr + size) > dma_mask) { + __free_pages(page, get_order(size)); + } else { + vaddr = page_address(page); + *dma_handle = addr; + } + } + + if (!vaddr) + vaddr = swiotlb_alloc_coherent(dev, size, dma_handle, gfp); + + if (!vaddr) + return NULL; + + /* Clear the SME encryption bit for DMA use if not swiotlb area */ + if (!is_swiotlb_buffer(dma_to_phys(dev, *dma_handle))) { + set_memory_decrypted((unsigned long)vaddr, 1 << order); + memset(vaddr, 0, PAGE_SIZE << order); + *dma_handle = __sme_clr(*dma_handle); + } + + return vaddr; +} + +static void sev_free(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_handle, unsigned long attrs) +{ + /* Set the SME encryption bit for re-use if not swiotlb area */ + if (!is_swiotlb_buffer(dma_to_phys(dev, dma_handle))) + set_memory_encrypted((unsigned long)vaddr, + 1 << get_order(size)); + + swiotlb_free_coherent(dev, size, vaddr, dma_handle); +} + +static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) +{ + pgprot_t old_prot, new_prot; + unsigned long pfn, pa, size; + pte_t new_pte; + + switch (level) { + case PG_LEVEL_4K: + pfn = pte_pfn(*kpte); + old_prot = pte_pgprot(*kpte); + break; + case PG_LEVEL_2M: + pfn = pmd_pfn(*(pmd_t *)kpte); + old_prot = pmd_pgprot(*(pmd_t *)kpte); + break; + case PG_LEVEL_1G: + pfn = pud_pfn(*(pud_t *)kpte); + old_prot = pud_pgprot(*(pud_t *)kpte); + break; + default: + return; + } + + new_prot = old_prot; + if (enc) + pgprot_val(new_prot) |= _PAGE_ENC; + else + pgprot_val(new_prot) &= ~_PAGE_ENC; + + /* If prot is same then do nothing. */ + if (pgprot_val(old_prot) == pgprot_val(new_prot)) + return; + + pa = pfn << page_level_shift(level); + size = page_level_size(level); + + /* + * We are going to perform in-place en-/decryption and change the + * physical page attribute from C=1 to C=0 or vice versa. Flush the + * caches to ensure that data gets accessed with the correct C-bit. + */ + clflush_cache_range(__va(pa), size); + + /* Encrypt/decrypt the contents in-place */ + if (enc) + sme_early_encrypt(pa, size); + else + sme_early_decrypt(pa, size); + + /* Change the page encryption mask. */ + new_pte = pfn_pte(pfn, new_prot); + set_pte_atomic(kpte, new_pte); +} + +static int __init early_set_memory_enc_dec(unsigned long vaddr, + unsigned long size, bool enc) +{ + unsigned long vaddr_end, vaddr_next; + unsigned long psize, pmask; + int split_page_size_mask; + int level, ret; + pte_t *kpte; + + vaddr_next = vaddr; + vaddr_end = vaddr + size; + + for (; vaddr < vaddr_end; vaddr = vaddr_next) { + kpte = lookup_address(vaddr, &level); + if (!kpte || pte_none(*kpte)) { + ret = 1; + goto out; + } + + if (level == PG_LEVEL_4K) { + __set_clr_pte_enc(kpte, level, enc); + vaddr_next = (vaddr & PAGE_MASK) + PAGE_SIZE; + continue; + } + + psize = page_level_size(level); + pmask = page_level_mask(level); + + /* + * Check whether we can change the large page in one go. + * We request a split when the address is not aligned and + * the number of pages to set/clear encryption bit is smaller + * than the number of pages in the large page. + */ + if (vaddr == (vaddr & pmask) && + ((vaddr_end - vaddr) >= psize)) { + __set_clr_pte_enc(kpte, level, enc); + vaddr_next = (vaddr & pmask) + psize; + continue; + } + + /* + * The virtual address is part of a larger page, create the next + * level page table mapping (4K or 2M). If it is part of a 2M + * page then we request a split of the large page into 4K + * chunks. A 1GB large page is split into 2M pages, resp. + */ + if (level == PG_LEVEL_2M) + split_page_size_mask = 0; + else + split_page_size_mask = 1 << PG_LEVEL_2M; + + kernel_physical_mapping_init(__pa(vaddr & pmask), + __pa((vaddr_end & pmask) + psize), + split_page_size_mask); + } + + ret = 0; + +out: + __flush_tlb_all(); + return ret; +} + +int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size) +{ + return early_set_memory_enc_dec(vaddr, size, false); +} + +int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) +{ + return early_set_memory_enc_dec(vaddr, size, true); } +/* + * SME and SEV are very similar but they are not the same, so there are + * times that the kernel will need to distinguish between SME and SEV. The + * sme_active() and sev_active() functions are used for this. When a + * distinction isn't needed, the mem_encrypt_active() function can be used. + * + * The trampoline code is a good example for this requirement. Before + * paging is activated, SME will access all memory as decrypted, but SEV + * will access all memory as encrypted. So, when APs are being brought + * up under SME the trampoline area cannot be encrypted, whereas under SEV + * the trampoline area must be encrypted. + */ +bool sme_active(void) +{ + return sme_me_mask && !sev_enabled; +} +EXPORT_SYMBOL_GPL(sme_active); + +bool sev_active(void) +{ + return sme_me_mask && sev_enabled; +} +EXPORT_SYMBOL_GPL(sev_active); + +static const struct dma_map_ops sev_dma_ops = { + .alloc = sev_alloc, + .free = sev_free, + .map_page = swiotlb_map_page, + .unmap_page = swiotlb_unmap_page, + .map_sg = swiotlb_map_sg_attrs, + .unmap_sg = swiotlb_unmap_sg_attrs, + .sync_single_for_cpu = swiotlb_sync_single_for_cpu, + .sync_single_for_device = swiotlb_sync_single_for_device, + .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, + .sync_sg_for_device = swiotlb_sync_sg_for_device, + .mapping_error = swiotlb_dma_mapping_error, +}; + /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void) { @@ -199,7 +436,23 @@ void __init mem_encrypt_init(void) /* Call into SWIOTLB to update the SWIOTLB DMA buffers */ swiotlb_update_mem_attributes(); - pr_info("AMD Secure Memory Encryption (SME) active\n"); + /* + * With SEV, DMA operations cannot use encryption. New DMA ops + * are required in order to mark the DMA areas as decrypted or + * to use bounce buffers. + */ + if (sev_active()) + dma_ops = &sev_dma_ops; + + /* + * With SEV, we need to unroll the rep string I/O instructions. + */ + if (sev_active()) + static_branch_enable(&sev_enable_key); + + pr_info("AMD %s active\n", + sev_active() ? "Secure Encrypted Virtualization (SEV)" + : "Secure Memory Encryption (SME)"); } void swiotlb_set_mem_attributes(void *vaddr, unsigned long size) @@ -527,37 +780,63 @@ void __init __nostackprotector sme_enable(struct boot_params *bp) { const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off; unsigned int eax, ebx, ecx, edx; + unsigned long feature_mask; bool active_by_default; unsigned long me_mask; char buffer[16]; u64 msr; - /* Check for the SME support leaf */ + /* Check for the SME/SEV support leaf */ eax = 0x80000000; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); if (eax < 0x8000001f) return; +#define AMD_SME_BIT BIT(0) +#define AMD_SEV_BIT BIT(1) /* - * Check for the SME feature: - * CPUID Fn8000_001F[EAX] - Bit 0 - * Secure Memory Encryption support - * CPUID Fn8000_001F[EBX] - Bits 5:0 - * Pagetable bit position used to indicate encryption + * Set the feature mask (SME or SEV) based on whether we are + * running under a hypervisor. + */ + eax = 1; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + feature_mask = (ecx & BIT(31)) ? AMD_SEV_BIT : AMD_SME_BIT; + + /* + * Check for the SME/SEV feature: + * CPUID Fn8000_001F[EAX] + * - Bit 0 - Secure Memory Encryption support + * - Bit 1 - Secure Encrypted Virtualization support + * CPUID Fn8000_001F[EBX] + * - Bits 5:0 - Pagetable bit position used to indicate encryption */ eax = 0x8000001f; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); - if (!(eax & 1)) + if (!(eax & feature_mask)) return; me_mask = 1UL << (ebx & 0x3f); - /* Check if SME is enabled */ - msr = __rdmsr(MSR_K8_SYSCFG); - if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + /* Check if memory encryption is enabled */ + if (feature_mask == AMD_SME_BIT) { + /* For SME, check the SYSCFG MSR */ + msr = __rdmsr(MSR_K8_SYSCFG); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + return; + } else { + /* For SEV, check the SEV MSR */ + msr = __rdmsr(MSR_AMD64_SEV); + if (!(msr & MSR_AMD64_SEV_ENABLED)) + return; + + /* SEV state cannot be controlled by a command line option */ + sme_me_mask = me_mask; + sev_enabled = true; return; + } /* * Fixups have not been applied to phys_base yet and we're running diff --git a/arch/x86/mm/mm_internal.h b/arch/x86/mm/mm_internal.h index 62474ba66c8e..4e1f6e1b8159 100644 --- a/arch/x86/mm/mm_internal.h +++ b/arch/x86/mm/mm_internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_MM_INTERNAL_H #define __X86_MM_INTERNAL_H diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index a99679826846..155ecbac9e28 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -33,6 +33,8 @@ #include <linux/compat.h> #include <asm/elf.h> +#include "physaddr.h" + struct va_alignment __read_mostly va_align = { .flags = -1, }; @@ -174,3 +176,63 @@ const char *arch_vma_name(struct vm_area_struct *vma) return "[mpx]"; return NULL; } + +/** + * mmap_address_hint_valid - Validate the address hint of mmap + * @addr: Address hint + * @len: Mapping length + * + * Check whether @addr and @addr + @len result in a valid mapping. + * + * On 32bit this only checks whether @addr + @len is <= TASK_SIZE. + * + * On 64bit with 5-level page tables another sanity check is required + * because mappings requested by mmap(@addr, 0) which cross the 47-bit + * virtual address boundary can cause the following theoretical issue: + * + * An application calls mmap(addr, 0), i.e. without MAP_FIXED, where @addr + * is below the border of the 47-bit address space and @addr + @len is + * above the border. + * + * With 4-level paging this request succeeds, but the resulting mapping + * address will always be within the 47-bit virtual address space, because + * the hint address does not result in a valid mapping and is + * ignored. Hence applications which are not prepared to handle virtual + * addresses above 47-bit work correctly. + * + * With 5-level paging this request would be granted and result in a + * mapping which crosses the border of the 47-bit virtual address + * space. If the application cannot handle addresses above 47-bit this + * will lead to misbehaviour and hard to diagnose failures. + * + * Therefore ignore address hints which would result in a mapping crossing + * the 47-bit virtual address boundary. + * + * Note, that in the same scenario with MAP_FIXED the behaviour is + * different. The request with @addr < 47-bit and @addr + @len > 47-bit + * fails on a 4-level paging machine but succeeds on a 5-level paging + * machine. It is reasonable to expect that an application does not rely on + * the failure of such a fixed mapping request, so the restriction is not + * applied. + */ +bool mmap_address_hint_valid(unsigned long addr, unsigned long len) +{ + if (TASK_SIZE - len < addr) + return false; + + return (addr > DEFAULT_MAP_WINDOW) == (addr + len > DEFAULT_MAP_WINDOW); +} + +/* Can we access it for direct reading/writing? Must be RAM: */ +int valid_phys_addr_range(phys_addr_t addr, size_t count) +{ + return addr + count <= __pa(high_memory); +} + +/* Can we access it through mmap? Must be a valid physical address: */ +int valid_mmap_phys_addr_range(unsigned long pfn, size_t count) +{ + phys_addr_t addr = (phys_addr_t)pfn << PAGE_SHIFT; + + return phys_addr_valid(addr + count - 1); +} diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index 9ceaa955d2ba..e500949bae24 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * mpx.c - Memory Protection eXtensions * @@ -12,6 +13,7 @@ #include <linux/sched/sysctl.h> #include <asm/insn.h> +#include <asm/insn-eval.h> #include <asm/mman.h> #include <asm/mmu_context.h> #include <asm/mpx.h> @@ -60,123 +62,6 @@ static unsigned long mpx_mmap(unsigned long len) return addr; } -enum reg_type { - REG_TYPE_RM = 0, - REG_TYPE_INDEX, - REG_TYPE_BASE, -}; - -static int get_reg_offset(struct insn *insn, struct pt_regs *regs, - enum reg_type type) -{ - int regno = 0; - - static const int regoff[] = { - offsetof(struct pt_regs, ax), - offsetof(struct pt_regs, cx), - offsetof(struct pt_regs, dx), - offsetof(struct pt_regs, bx), - offsetof(struct pt_regs, sp), - offsetof(struct pt_regs, bp), - offsetof(struct pt_regs, si), - offsetof(struct pt_regs, di), -#ifdef CONFIG_X86_64 - offsetof(struct pt_regs, r8), - offsetof(struct pt_regs, r9), - offsetof(struct pt_regs, r10), - offsetof(struct pt_regs, r11), - offsetof(struct pt_regs, r12), - offsetof(struct pt_regs, r13), - offsetof(struct pt_regs, r14), - offsetof(struct pt_regs, r15), -#endif - }; - int nr_registers = ARRAY_SIZE(regoff); - /* - * Don't possibly decode a 32-bit instructions as - * reading a 64-bit-only register. - */ - if (IS_ENABLED(CONFIG_X86_64) && !insn->x86_64) - nr_registers -= 8; - - switch (type) { - case REG_TYPE_RM: - regno = X86_MODRM_RM(insn->modrm.value); - if (X86_REX_B(insn->rex_prefix.value)) - regno += 8; - break; - - case REG_TYPE_INDEX: - regno = X86_SIB_INDEX(insn->sib.value); - if (X86_REX_X(insn->rex_prefix.value)) - regno += 8; - break; - - case REG_TYPE_BASE: - regno = X86_SIB_BASE(insn->sib.value); - if (X86_REX_B(insn->rex_prefix.value)) - regno += 8; - break; - - default: - pr_err("invalid register type"); - BUG(); - break; - } - - if (regno >= nr_registers) { - WARN_ONCE(1, "decoded an instruction with an invalid register"); - return -EINVAL; - } - return regoff[regno]; -} - -/* - * return the address being referenced be instruction - * for rm=3 returning the content of the rm reg - * for rm!=3 calculates the address using SIB and Disp - */ -static void __user *mpx_get_addr_ref(struct insn *insn, struct pt_regs *regs) -{ - unsigned long addr, base, indx; - int addr_offset, base_offset, indx_offset; - insn_byte_t sib; - - insn_get_modrm(insn); - insn_get_sib(insn); - sib = insn->sib.value; - - if (X86_MODRM_MOD(insn->modrm.value) == 3) { - addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM); - if (addr_offset < 0) - goto out_err; - addr = regs_get_register(regs, addr_offset); - } else { - if (insn->sib.nbytes) { - base_offset = get_reg_offset(insn, regs, REG_TYPE_BASE); - if (base_offset < 0) - goto out_err; - - indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX); - if (indx_offset < 0) - goto out_err; - - base = regs_get_register(regs, base_offset); - indx = regs_get_register(regs, indx_offset); - addr = base + indx * (1 << X86_SIB_SCALE(sib)); - } else { - addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM); - if (addr_offset < 0) - goto out_err; - addr = regs_get_register(regs, addr_offset); - } - addr += insn->displacement.value; - } - return (void __user *)addr; -out_err: - return (void __user *)-1; -} - static int mpx_insn_decode(struct insn *insn, struct pt_regs *regs) { @@ -289,7 +174,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) info->si_signo = SIGSEGV; info->si_errno = 0; info->si_code = SEGV_BNDERR; - info->si_addr = mpx_get_addr_ref(&insn, regs); + info->si_addr = insn_get_addr_ref(&insn, regs); /* * We were not able to extract an address from the instruction, * probably because there was something invalid in it. diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 9405ffc91502..066f3511d5f1 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generic VM initialization for x86-64 NUMA setups. * Copyright 2002,2003 Andi Kleen, SuSE Labs. diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index d805162e6045..34a2a3bfde9c 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NUMA emulation */ diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h index ad86ec91e640..86860f279662 100644 --- a/arch/x86/mm/numa_internal.h +++ b/arch/x86/mm/numa_internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_MM_NUMA_INTERNAL_H #define __X86_MM_NUMA_INTERNAL_H diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 5f169d5d76a8..a25588ad75ef 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * self test for change_page_attr. * diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index dfb7d657cf43..85cf12219dea 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -753,7 +753,7 @@ static int split_large_page(struct cpa_data *cpa, pte_t *kpte, if (!debug_pagealloc_enabled()) spin_unlock(&cpa_lock); - base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0); + base = alloc_pages(GFP_KERNEL, 0); if (!debug_pagealloc_enabled()) spin_lock(&cpa_lock); if (!base) @@ -904,7 +904,7 @@ static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end) static int alloc_pte_page(pmd_t *pmd) { - pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL); if (!pte) return -1; @@ -914,7 +914,7 @@ static int alloc_pte_page(pmd_t *pmd) static int alloc_pmd_page(pud_t *pud) { - pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL); if (!pmd) return -1; @@ -1120,7 +1120,7 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) pgd_entry = cpa->pgd + pgd_index(addr); if (pgd_none(*pgd_entry)) { - p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL); if (!p4d) return -1; @@ -1132,7 +1132,7 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) */ p4d = p4d_offset(pgd_entry, addr); if (p4d_none(*p4d)) { - pud = (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK); + pud = (pud_t *)get_zeroed_page(GFP_KERNEL); if (!pud) return -1; @@ -1781,8 +1781,8 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) unsigned long start; int ret; - /* Nothing to do if the SME is not active */ - if (!sme_active()) + /* Nothing to do if memory encryption is not active */ + if (!mem_encrypt_active()) return 0; /* Should not be working on unaligned addresses */ diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h index a739bfc40690..eeb5caeb089b 100644 --- a/arch/x86/mm/pat_internal.h +++ b/arch/x86/mm/pat_internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PAT_INTERNAL_H_ #define __PAT_INTERNAL_H_ diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index d76485b22824..fa16036fa592 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Handle caching attributes in page tables (PAT) * diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index b372f3442bbf..96d456a94b03 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/gfp.h> #include <asm/pgalloc.h> @@ -6,7 +7,7 @@ #include <asm/fixmap.h> #include <asm/mtrr.h> -#define PGALLOC_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) #ifdef CONFIG_HIGHPTE #define PGALLOC_USER_GFP __GFP_HIGHMEM diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index b9bd5b8b14fa..6b9bf023a700 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/sched.h> #include <linux/kernel.h> #include <linux/errno.h> diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c index cfc3b9121ce4..7f9acb68324c 100644 --- a/arch/x86/mm/physaddr.c +++ b/arch/x86/mm/physaddr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/bootmem.h> #include <linux/mmdebug.h> #include <linux/export.h> diff --git a/arch/x86/mm/physaddr.h b/arch/x86/mm/physaddr.h index a3cd5a0c97b3..9f6419cafc32 100644 --- a/arch/x86/mm/physaddr.h +++ b/arch/x86/mm/physaddr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <asm/processor.h> static inline int phys_addr_valid(resource_size_t addr) diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index 2dab69a706ec..d7bc0eea20a5 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -18,7 +18,6 @@ #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/mmu_context.h> /* vma_pkey() */ -#include <asm/fpu/internal.h> /* fpregs_active() */ int __execute_only_pkey(struct mm_struct *mm) { @@ -45,7 +44,7 @@ int __execute_only_pkey(struct mm_struct *mm) */ preempt_disable(); if (!need_to_set_mm_pkey && - fpregs_active() && + current->thread.fpu.initialized && !__pkru_allows_read(read_pkru(), execute_only_pkey)) { preempt_enable(); return execute_only_pkey; diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index f65a33f505b6..adb3c5784dac 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/spinlock.h> #include <linux/errno.h> #include <linux/init.h> diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 3ea20d61b523..dac07e4f5834 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * ACPI 3.0 based NUMA setup * Copyright 2004 Andi Kleen, SuSE Labs. diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 1ab3821f9e26..3118392cdf75 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -30,6 +30,7 @@ atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1); + static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, u16 *new_asid, bool *need_flush) { @@ -80,10 +81,11 @@ void leave_mm(int cpu) return; /* Warn if we're not lazy. */ - WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))); + WARN_ON(!this_cpu_read(cpu_tlbstate.is_lazy)); switch_mm(NULL, &init_mm, NULL); } +EXPORT_SYMBOL_GPL(leave_mm); void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) @@ -126,8 +128,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * isn't free. */ #ifdef CONFIG_DEBUG_VM - if (WARN_ON_ONCE(__read_cr3() != - (__sme_pa(real_prev->pgd) | prev_asid))) { + if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) { /* * If we were to BUG here, we'd be very likely to kill * the system so hard that we don't see the call trace. @@ -143,45 +144,24 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, __flush_tlb_all(); } #endif + this_cpu_write(cpu_tlbstate.is_lazy, false); if (real_prev == next) { - VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != - next->context.ctx_id); - - if (cpumask_test_cpu(cpu, mm_cpumask(next))) { - /* - * There's nothing to do: we weren't lazy, and we - * aren't changing our mm. We don't need to flush - * anything, nor do we need to update CR3, CR4, or - * LDTR. - */ - return; - } - - /* Resume remote flushes and then read tlb_gen. */ - cpumask_set_cpu(cpu, mm_cpumask(next)); - next_tlb_gen = atomic64_read(&next->context.tlb_gen); - - if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) < - next_tlb_gen) { - /* - * Ideally, we'd have a flush_tlb() variant that - * takes the known CR3 value as input. This would - * be faster on Xen PV and on hypothetical CPUs - * on which INVPCID is fast. - */ - this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen, - next_tlb_gen); - write_cr3(__sme_pa(next->pgd) | prev_asid); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, - TLB_FLUSH_ALL); - } + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != + next->context.ctx_id); /* - * We just exited lazy mode, which means that CR4 and/or LDTR - * may be stale. (Changes to the required CR4 and LDTR states - * are not reflected in tlb_gen.) + * We don't currently support having a real mm loaded without + * our cpu set in mm_cpumask(). We have all the bookkeeping + * in place to figure out whether we would need to flush + * if our cpu were cleared in mm_cpumask(), but we don't + * currently use it. */ + if (WARN_ON_ONCE(real_prev != &init_mm && + !cpumask_test_cpu(cpu, mm_cpumask(next)))) + cpumask_set_cpu(cpu, mm_cpumask(next)); + + return; } else { u16 new_asid; bool need_flush; @@ -192,7 +172,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * mapped in the new pgd, we'll double-fault. Forcibly * map it. */ - unsigned int index = pgd_index(current_stack_pointer()); + unsigned int index = pgd_index(current_stack_pointer); pgd_t *pgd = next->pgd + index; if (unlikely(pgd_none(*pgd))) @@ -200,10 +180,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } /* Stop remote flushes for the previous mm */ - if (cpumask_test_cpu(cpu, mm_cpumask(real_prev))) - cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); - - VM_WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); + VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && + real_prev != &init_mm); + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); /* * Start remote flushes and then read tlb_gen. @@ -216,13 +195,23 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (need_flush) { this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); - write_cr3(__sme_pa(next->pgd) | new_asid); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, - TLB_FLUSH_ALL); + write_cr3(build_cr3(next, new_asid)); + + /* + * NB: This gets called via leave_mm() in the idle path + * where RCU functions differently. Tracing normally + * uses RCU, so we need to use the _rcuidle variant. + * + * (There is no good reason for this. The idle code should + * be rearranged to call this before rcu_idle_enter().) + */ + trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } else { /* The new ASID is already up to date. */ - write_cr3(__sme_pa(next->pgd) | new_asid | CR3_NOFLUSH); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0); + write_cr3(build_cr3_noflush(next, new_asid)); + + /* See above wrt _rcuidle. */ + trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); } this_cpu_write(cpu_tlbstate.loaded_mm, next); @@ -234,6 +223,40 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } /* + * Please ignore the name of this function. It should be called + * switch_to_kernel_thread(). + * + * enter_lazy_tlb() is a hint from the scheduler that we are entering a + * kernel thread or other context without an mm. Acceptable implementations + * include doing nothing whatsoever, switching to init_mm, or various clever + * lazy tricks to try to minimize TLB flushes. + * + * The scheduler reserves the right to call enter_lazy_tlb() several times + * in a row. It will notify us that we're going back to a real mm by + * calling switch_mm_irqs_off(). + */ +void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ + if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) + return; + + if (tlb_defer_switch_to_init_mm()) { + /* + * There's a significant optimization that may be possible + * here. We have accurate enough TLB flush tracking that we + * don't need to maintain coherence of TLB per se when we're + * lazy. We do, however, need to maintain coherence of + * paging-structure caches. We could, in principle, leave our + * old mm loaded and only switch to init_mm when + * tlb_remove_page() happens. + */ + this_cpu_write(cpu_tlbstate.is_lazy, true); + } else { + switch_mm(NULL, &init_mm, NULL); + } +} + +/* * Call this when reinitializing a CPU. It fixes the following potential * problems: * @@ -265,7 +288,7 @@ void initialize_tlbstate_and_flush(void) !(cr4_read_shadow() & X86_CR4_PCIDE)); /* Force ASID 0 and force a TLB flush. */ - write_cr3(cr3 & ~CR3_PCID_MASK); + write_cr3(build_cr3(mm, 0)); /* Reinitialize tlbstate. */ this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); @@ -304,16 +327,20 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, /* This code cannot presently handle being reentered. */ VM_WARN_ON(!irqs_disabled()); + if (unlikely(loaded_mm == &init_mm)) + return; + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) != loaded_mm->context.ctx_id); - if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))) { + if (this_cpu_read(cpu_tlbstate.is_lazy)) { /* - * We're in lazy mode -- don't flush. We can get here on - * remote flushes due to races and on local flushes if a - * kernel thread coincidentally flushes the mm it's lazily - * still using. + * We're in lazy mode. We need to at least flush our + * paging-structure cache to avoid speculatively reading + * garbage into our TLB. Since switching to init_mm is barely + * slower than a minimal flush, just switch to init_mm. */ + switch_mm_irqs_off(NULL, &init_mm, NULL); return; } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8c9573660d51..0554e8aef4d5 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -284,9 +284,9 @@ static void emit_bpf_tail_call(u8 **pprog) /* if (index >= array->map.max_entries) * goto out; */ - EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ + EMIT2(0x89, 0xD2); /* mov edx, edx */ + EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); - EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ #define OFFSET1 43 /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; diff --git a/arch/x86/oprofile/Makefile b/arch/x86/oprofile/Makefile index 1599f568f0e2..4d49b5a27025 100644 --- a/arch/x86/oprofile/Makefile +++ b/arch/x86/oprofile/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_OPROFILE) += oprofile.o DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index ffdbc4836b4f..174c59774cc9 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -592,7 +592,7 @@ enum __force_cpu_type { static int force_cpu_type; -static int set_cpu_type(const char *str, struct kernel_param *kp) +static int set_cpu_type(const char *str, const struct kernel_param *kp) { if (!strcmp(str, "timer")) { force_cpu_type = timer; diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index 350f7096baac..7913b6921959 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -212,8 +212,8 @@ static void arch_perfmon_setup_counters(void) eax.full = cpuid_eax(0xa); /* Workaround for BIOS bugs in 6/15. Taken from perfmon2 */ - if (eax.split.version_id == 0 && __this_cpu_read(cpu_info.x86) == 6 && - __this_cpu_read(cpu_info.x86_model) == 15) { + if (eax.split.version_id == 0 && boot_cpu_data.x86 == 6 && + boot_cpu_data.x86_model == 15) { eax.split.version_id = 2; eax.split.num_counters = 2; eax.split.bit_width = 40; diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index 5c6fc3577a49..c806b57d3f22 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-y := i386.o init.o obj-$(CONFIG_PCI_BIOS) += pcbios.o diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 3961103e9176..7df49c40665e 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/pci.h> #include <linux/acpi.h> #include <linux/init.h> diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index ae387e5ee6f7..649bdde63e32 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/pci.h> #include <linux/topology.h> diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c index 6eb3c8af96e2..2752c02e3f0e 100644 --- a/arch/x86/pci/bus_numa.c +++ b/arch/x86/pci/bus_numa.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/pci.h> #include <linux/range.h> diff --git a/arch/x86/pci/bus_numa.h b/arch/x86/pci/bus_numa.h index ff8f65b04574..697dd841b118 100644 --- a/arch/x86/pci/bus_numa.h +++ b/arch/x86/pci/bus_numa.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __BUS_NUMA_H #define __BUS_NUMA_H /* diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c index 15460590b8c5..2d9503323d10 100644 --- a/arch/x86/pci/direct.c +++ b/arch/x86/pci/direct.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * direct.c - Low-level direct PCI config space access */ diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c index d1067d539bee..f0114007e915 100644 --- a/arch/x86/pci/early.c +++ b/arch/x86/pci/early.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/pci.h> #include <asm/pci-direct.h> diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index f2228b150faa..1e996df687a3 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Exceptions for specific devices. Usually work-arounds for fatal design flaws. */ @@ -635,3 +636,88 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2030, quirk_no_aersid); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2031, quirk_no_aersid); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2032, quirk_no_aersid); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid); + +#ifdef CONFIG_PHYS_ADDR_T_64BIT + +#define AMD_141b_MMIO_BASE(x) (0x80 + (x) * 0x8) +#define AMD_141b_MMIO_BASE_RE_MASK BIT(0) +#define AMD_141b_MMIO_BASE_WE_MASK BIT(1) +#define AMD_141b_MMIO_BASE_MMIOBASE_MASK GENMASK(31,8) + +#define AMD_141b_MMIO_LIMIT(x) (0x84 + (x) * 0x8) +#define AMD_141b_MMIO_LIMIT_MMIOLIMIT_MASK GENMASK(31,8) + +#define AMD_141b_MMIO_HIGH(x) (0x180 + (x) * 0x4) +#define AMD_141b_MMIO_HIGH_MMIOBASE_MASK GENMASK(7,0) +#define AMD_141b_MMIO_HIGH_MMIOLIMIT_SHIFT 16 +#define AMD_141b_MMIO_HIGH_MMIOLIMIT_MASK GENMASK(23,16) + +/* + * The PCI Firmware Spec, rev 3.2, notes that ACPI should optionally allow + * configuring host bridge windows using the _PRS and _SRS methods. + * + * But this is rarely implemented, so we manually enable a large 64bit BAR for + * PCIe device on AMD Family 15h (Models 00h-1fh, 30h-3fh, 60h-7fh) Processors + * here. + */ +static void pci_amd_enable_64bit_bar(struct pci_dev *dev) +{ + unsigned i; + u32 base, limit, high; + struct resource *res, *conflict; + + for (i = 0; i < 8; i++) { + pci_read_config_dword(dev, AMD_141b_MMIO_BASE(i), &base); + pci_read_config_dword(dev, AMD_141b_MMIO_HIGH(i), &high); + + /* Is this slot free? */ + if (!(base & (AMD_141b_MMIO_BASE_RE_MASK | + AMD_141b_MMIO_BASE_WE_MASK))) + break; + + base >>= 8; + base |= high << 24; + + /* Abort if a slot already configures a 64bit BAR. */ + if (base > 0x10000) + return; + } + if (i == 8) + return; + + res = kzalloc(sizeof(*res), GFP_KERNEL); + if (!res) + return; + + res->name = "PCI Bus 0000:00"; + res->flags = IORESOURCE_PREFETCH | IORESOURCE_MEM | + IORESOURCE_MEM_64 | IORESOURCE_WINDOW; + res->start = 0x100000000ull; + res->end = 0xfd00000000ull - 1; + + /* Just grab the free area behind system memory for this */ + while ((conflict = request_resource_conflict(&iomem_resource, res))) + res->start = conflict->end + 1; + + dev_info(&dev->dev, "adding root bus resource %pR\n", res); + + base = ((res->start >> 8) & AMD_141b_MMIO_BASE_MMIOBASE_MASK) | + AMD_141b_MMIO_BASE_RE_MASK | AMD_141b_MMIO_BASE_WE_MASK; + limit = ((res->end + 1) >> 8) & AMD_141b_MMIO_LIMIT_MMIOLIMIT_MASK; + high = ((res->start >> 40) & AMD_141b_MMIO_HIGH_MMIOBASE_MASK) | + ((((res->end + 1) >> 40) << AMD_141b_MMIO_HIGH_MMIOLIMIT_SHIFT) + & AMD_141b_MMIO_HIGH_MMIOLIMIT_MASK); + + pci_write_config_dword(dev, AMD_141b_MMIO_HIGH(i), high); + pci_write_config_dword(dev, AMD_141b_MMIO_LIMIT(i), limit); + pci_write_config_dword(dev, AMD_141b_MMIO_BASE(i), base); + + pci_bus_add_resource(dev->bus, res, 0); +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1401, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x141b, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1571, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x15b1, pci_amd_enable_64bit_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x1601, pci_amd_enable_64bit_bar); + +#endif diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 7b4307163eac..ed4ac215305d 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Low-Level PCI Access for i386 machines * diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c index adb62aaa7ecd..5fc617edf108 100644 --- a/arch/x86/pci/init.c +++ b/arch/x86/pci/init.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/pci.h> #include <linux/init.h> #include <asm/pci_x86.h> diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index b901ece278dd..511921045312 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel MID PCI support * Copyright (c) 2008 Intel Corporation @@ -279,7 +280,7 @@ static void intel_mid_pci_irq_disable(struct pci_dev *dev) } } -static struct pci_ops intel_mid_pci_ops = { +static const struct pci_ops intel_mid_pci_ops __initconst = { .read = pci_read, .write = pci_write, }; diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 0f5f60b14f48..0452629148be 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Low-Level PCI Support for PC -- Routing of Interrupts * diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index d1b47d5bc9c3..96684d0adcf9 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * mmconfig-shared.c - Low-level direct PCI config space access via * MMCONFIG - common code between i386 and x86-64. diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index f1c1aa0430ae..887d181b769b 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * mmconfig.c - Low-level direct PCI config space access via MMCONFIG * diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 76595408ff53..9c97d814125e 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * BIOS32 and PCI BIOS handling. */ diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile index 184842ef332e..d0e835470d01 100644 --- a/arch/x86/platform/Makefile +++ b/arch/x86/platform/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # Platform specific code goes here obj-y += atom/ obj-y += ce4100/ diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index 2f56e1ed61c3..e4dc3862d423 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD_efi_thunk_$(BITS).o := y OBJECT_FILES_NON_STANDARD_efi_stub_$(BITS).o := y diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 928b6dceeca0..9061babfbc83 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Common EFI (Extensible Firmware Interface) support functions * Based on Extensible Firmware Interface Specification version 1.0 diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 52f7faa1538f..324b93328b37 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Extensible Firmware Interface * diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 12e83888e5b9..6a151ce70e86 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * x86_64 specific EFI support functions * Based on Extensible Firmware Interface Specification version 1.0 @@ -32,6 +33,7 @@ #include <linux/reboot.h> #include <linux/slab.h> #include <linux/ucs2_string.h> +#include <linux/mem_encrypt.h> #include <asm/setup.h> #include <asm/page.h> @@ -205,7 +207,7 @@ int __init efi_alloc_page_tables(void) if (efi_enabled(EFI_OLD_MEMMAP)) return 0; - gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO; + gfp_mask = GFP_KERNEL | __GFP_ZERO; efi_pgd = (pgd_t *)__get_free_page(gfp_mask); if (!efi_pgd) return -ENOMEM; @@ -369,7 +371,11 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) * as trim_bios_range() will reserve the first page and isolate it away * from memory allocators anyway. */ - if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, _PAGE_RW)) { + pf = _PAGE_RW; + if (sev_active()) + pf |= _PAGE_ENC; + + if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, pf)) { pr_err("Failed to create 1:1 mapping for the first page!\n"); return 1; } @@ -412,6 +418,9 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va) if (!(md->attribute & EFI_MEMORY_WB)) flags |= _PAGE_PCD; + if (sev_active()) + flags |= _PAGE_ENC; + pfn = md->phys_addr >> PAGE_SHIFT; if (kernel_map_pages_in_pgd(pgd, pfn, va, md->num_pages, flags)) pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n", @@ -538,6 +547,9 @@ static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *m if (!(md->attribute & EFI_MEMORY_RO)) pf |= _PAGE_RW; + if (sev_active()) + pf |= _PAGE_ENC; + return efi_update_mappings(md, pf); } @@ -589,6 +601,9 @@ void __init efi_runtime_update_mappings(void) (md->type != EFI_RUNTIME_SERVICES_CODE)) pf |= _PAGE_RW; + if (sev_active()) + pf |= _PAGE_ENC; + efi_update_mappings(md, pf); } } diff --git a/arch/x86/platform/efi/efi_stub_32.S b/arch/x86/platform/efi/efi_stub_32.S index 040192b50d02..ab2e91e76894 100644 --- a/arch/x86/platform/efi/efi_stub_32.S +++ b/arch/x86/platform/efi/efi_stub_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * EFI call stub for IA32. * diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index cd95075944ab..74628ec78f29 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Function calling ABI conversion from Linux to EFI for x86_64 * diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index ff85d28c50f2..189b218da87c 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2014 Intel Corporation; author Matt Fleming * diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile index 53e0235e308f..480fed21cc7d 100644 --- a/arch/x86/platform/intel-mid/device_libs/Makefile +++ b/arch/x86/platform/intel-mid/device_libs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # Family-Level Interface Shim (FLIS) obj-$(subst m,y,$(CONFIG_PINCTRL_MERRIFIELD)) += platform_mrfld_pinctrl.o # SDHCI Devices diff --git a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c index 74283875c7e8..e639e3116acf 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c @@ -62,10 +62,9 @@ static struct platform_device pb_device = { static int __init pb_keys_init(void) { struct gpio_keys_button *gb = gpio_button; - int i, num, good = 0; + int i, good = 0; - num = sizeof(gpio_button) / sizeof(struct gpio_keys_button); - for (i = 0; i < num; i++) { + for (i = 0; i < ARRAY_SIZE(gpio_button); i++) { gb[i].gpio = get_gpio_by_name(gb[i].desc); pr_debug("info[%2d]: name = %s, gpio = %d\n", i, gb[i].desc, gb[i].gpio); diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c index b8f562049cad..42f879b75f9b 100644 --- a/arch/x86/platform/intel-quark/imr_selftest.c +++ b/arch/x86/platform/intel-quark/imr_selftest.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /** * imr_selftest.c -- Intel Isolated Memory Region self-test driver * diff --git a/arch/x86/platform/olpc/Makefile b/arch/x86/platform/olpc/Makefile index fd332c533947..049f92a9379d 100644 --- a/arch/x86/platform/olpc/Makefile +++ b/arch/x86/platform/olpc/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_OLPC) += olpc.o olpc_ofw.o olpc_dt.o obj-$(CONFIG_OLPC_XO1_PM) += olpc-xo1-pm.o xo1-wakeup.o obj-$(CONFIG_OLPC_XO1_RTC) += olpc-xo1-rtc.o diff --git a/arch/x86/platform/olpc/xo1-wakeup.S b/arch/x86/platform/olpc/xo1-wakeup.S index 948deb289753..5fee3a2c2fd4 100644 --- a/arch/x86/platform/olpc/xo1-wakeup.S +++ b/arch/x86/platform/olpc/xo1-wakeup.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .text #include <linux/linkage.h> #include <asm/segment.h> diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index 03fc397335b7..5f6fd860820a 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -127,10 +127,11 @@ static void uv_domain_free(struct irq_domain *domain, unsigned int virq, * Re-target the irq to the specified CPU and enable the specified MMR located * on the specified blade to allow the sending of MSIs to the specified CPU. */ -static void uv_domain_activate(struct irq_domain *domain, - struct irq_data *irq_data) +static int uv_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early) { uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data); + return 0; } /* diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index 05041871ac90..a4701389562c 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD_hibernate_asm_$(BITS).o := y # __restore_processor_state() restores %gs after S3 resume and so should not diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S index 1d0fa0e24070..6e56815e13a0 100644 --- a/arch/x86/power/hibernate_asm_32.S +++ b/arch/x86/power/hibernate_asm_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * This may not use any stack, nor any variable that is not "NoSave": * diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 7dbdb780264d..2f15a2ac4209 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD := y purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string.o diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig index bb026699ad19..a9c3db125222 100644 --- a/arch/x86/ras/Kconfig +++ b/arch/x86/ras/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 config RAS_CEC bool "Correctable Errors Collector" depends on X86_MCE && MEMORY_FAILURE && DEBUG_FS diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 1f71980fc5e0..d10105825d57 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/io.h> #include <linux/slab.h> #include <linux/memblock.h> @@ -63,9 +64,10 @@ static void __init setup_real_mode(void) /* * If SME is active, the trampoline area will need to be in * decrypted memory in order to bring up other processors - * successfully. + * successfully. This is not needed for SEV. */ - set_memory_decrypted((unsigned long)base, size >> PAGE_SHIFT); + if (sme_active()) + set_memory_decrypted((unsigned long)base, size >> PAGE_SHIFT); memcpy(base, real_mode_blob, size); diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S index a28221d94e69..30b0d30d861a 100644 --- a/arch/x86/realmode/rm/header.S +++ b/arch/x86/realmode/rm/header.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Real-mode blob header; this should match realmode.h and be * readonly; for mutable data instead add pointers into the .data diff --git a/arch/x86/realmode/rm/realmode.h b/arch/x86/realmode/rm/realmode.h index d74cff6350ed..c76041a35397 100644 --- a/arch/x86/realmode/rm/realmode.h +++ b/arch/x86/realmode/rm/realmode.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ARCH_X86_REALMODE_RM_REALMODE_H #define ARCH_X86_REALMODE_RM_REALMODE_H diff --git a/arch/x86/realmode/rm/realmode.lds.S b/arch/x86/realmode/rm/realmode.lds.S index 86b2e8d6b1f1..df8e11e26bc3 100644 --- a/arch/x86/realmode/rm/realmode.lds.S +++ b/arch/x86/realmode/rm/realmode.lds.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * realmode.lds.S * diff --git a/arch/x86/realmode/rm/reboot.S b/arch/x86/realmode/rm/reboot.S index d66c607bdc58..cd2f97b9623b 100644 --- a/arch/x86/realmode/rm/reboot.S +++ b/arch/x86/realmode/rm/reboot.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <asm/segment.h> #include <asm/page_types.h> diff --git a/arch/x86/realmode/rm/stack.S b/arch/x86/realmode/rm/stack.S index 867ae87adfae..8d4cb64799ea 100644 --- a/arch/x86/realmode/rm/stack.S +++ b/arch/x86/realmode/rm/stack.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Common heap and stack allocations */ diff --git a/arch/x86/realmode/rm/trampoline_32.S b/arch/x86/realmode/rm/trampoline_32.S index 48ddd76bc4c3..2dd866c9e21e 100644 --- a/arch/x86/realmode/rm/trampoline_32.S +++ b/arch/x86/realmode/rm/trampoline_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * * Trampoline.S Derived from Setup.S by Linus Torvalds diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index 614fd7064d0a..de53bd15df5a 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * * Trampoline.S Derived from Setup.S by Linus Torvalds diff --git a/arch/x86/realmode/rm/trampoline_common.S b/arch/x86/realmode/rm/trampoline_common.S index b1ecdb9692ad..7c706772ab59 100644 --- a/arch/x86/realmode/rm/trampoline_common.S +++ b/arch/x86/realmode/rm/trampoline_common.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ .section ".rodata","a" .balign 16 tr_idt: .fill 1, 6, 0 diff --git a/arch/x86/realmode/rm/wakemain.c b/arch/x86/realmode/rm/wakemain.c index 91405d515ec6..1d6437e6d2ba 100644 --- a/arch/x86/realmode/rm/wakemain.c +++ b/arch/x86/realmode/rm/wakemain.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "wakeup.h" #include "boot.h" diff --git a/arch/x86/realmode/rm/wakeup.h b/arch/x86/realmode/rm/wakeup.h index 7dd86a419f5d..0e4fd08ae447 100644 --- a/arch/x86/realmode/rm/wakeup.h +++ b/arch/x86/realmode/rm/wakeup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Definitions for the wakeup data structure at the head of the * wakeup code. diff --git a/arch/x86/realmode/rm/wakeup_asm.S b/arch/x86/realmode/rm/wakeup_asm.S index 9e7e14797a72..05ac9c17c811 100644 --- a/arch/x86/realmode/rm/wakeup_asm.S +++ b/arch/x86/realmode/rm/wakeup_asm.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * ACPI wakeup real mode startup stub */ diff --git a/arch/x86/realmode/rmpiggy.S b/arch/x86/realmode/rmpiggy.S index 204c6ece0e97..c078dba40cef 100644 --- a/arch/x86/realmode/rmpiggy.S +++ b/arch/x86/realmode/rmpiggy.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Wrapper script for the realmode binary as a transport object * before copying to low memory. diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile index 604a37efd4d5..972b8e8d939c 100644 --- a/arch/x86/tools/Makefile +++ b/arch/x86/tools/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 PHONY += posttest ifeq ($(KBUILD_VERBOSE),1) diff --git a/arch/x86/tools/distill.awk b/arch/x86/tools/distill.awk index c13c0ee48ab4..e0edeccc1429 100644 --- a/arch/x86/tools/distill.awk +++ b/arch/x86/tools/distill.awk @@ -1,4 +1,5 @@ #!/bin/awk -f +# SPDX-License-Identifier: GPL-2.0 # Usage: objdump -d a.out | awk -f distill.awk | ./test_get_len # Distills the disassembly as follows: # - Removes all lines except the disassembled instructions. diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index a3d2c62fd805..b02a36b2c14f 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -1,4 +1,5 @@ #!/bin/awk -f +# SPDX-License-Identifier: GPL-2.0 # gen-insn-attr-x86.awk: Instruction attribute table generator # Written by Masami Hiramatsu <mhiramat@redhat.com> # diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 73eb7fd4aec4..5d73c443e778 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* This is included from relocs_32/64.c */ #define ElfW(type) _ElfW(ELF_BITS, type) diff --git a/arch/x86/tools/relocs.h b/arch/x86/tools/relocs.h index 1d23bf953a4a..43c83c0fd22c 100644 --- a/arch/x86/tools/relocs.h +++ b/arch/x86/tools/relocs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef RELOCS_H #define RELOCS_H diff --git a/arch/x86/tools/relocs_32.c b/arch/x86/tools/relocs_32.c index b2ade2bb4162..9442ff78be83 100644 --- a/arch/x86/tools/relocs_32.c +++ b/arch/x86/tools/relocs_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "relocs.h" #define ELF_BITS 32 diff --git a/arch/x86/tools/relocs_64.c b/arch/x86/tools/relocs_64.c index 56b61b743c4c..9029cb619cb1 100644 --- a/arch/x86/tools/relocs_64.c +++ b/arch/x86/tools/relocs_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "relocs.h" #define ELF_BITS 64 diff --git a/arch/x86/tools/relocs_common.c b/arch/x86/tools/relocs_common.c index acab636bcb34..6634352a20bc 100644 --- a/arch/x86/tools/relocs_common.c +++ b/arch/x86/tools/relocs_common.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "relocs.h" void die(char *fmt, ...) diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index ed56a1c4ae73..13ed827c7c66 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 mainmenu "User Mode Linux/$SUBARCH $KERNELVERSION Kernel Configuration" source "arch/um/Kconfig.common" diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index 46cbbfe03285..c2d3d7c51e9e 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) # diff --git a/arch/x86/um/asm/arch_hweight.h b/arch/x86/um/asm/arch_hweight.h index c656cf443f4a..0d2d5fbb3a39 100644 --- a/arch/x86/um/asm/arch_hweight.h +++ b/arch/x86/um/asm/arch_hweight.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_UM_HWEIGHT_H #define _ASM_UM_HWEIGHT_H diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index 00c319048d52..b7d73400ea29 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_UM_BARRIER_H_ #define _ASM_UM_BARRIER_H_ diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h index 54d96f1e3594..2a56cac64687 100644 --- a/arch/x86/um/asm/checksum.h +++ b/arch/x86/um/asm/checksum.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __UM_CHECKSUM_H #define __UM_CHECKSUM_H diff --git a/arch/x86/um/asm/desc.h b/arch/x86/um/asm/desc.h index 4ec34a51b62c..34de4e93d945 100644 --- a/arch/x86/um/asm/desc.h +++ b/arch/x86/um/asm/desc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __UM_DESC_H #define __UM_DESC_H diff --git a/arch/x86/um/asm/module.h b/arch/x86/um/asm/module.h index 61af80e932eb..a3b061d66082 100644 --- a/arch/x86/um/asm/module.h +++ b/arch/x86/um/asm/module.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __UM_MODULE_H #define __UM_MODULE_H diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h index c77db2288982..593d5f3902bd 100644 --- a/arch/x86/um/asm/processor.h +++ b/arch/x86/um/asm/processor.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __UM_PROCESSOR_H #define __UM_PROCESSOR_H diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h index b291ca5cf66b..83822fd42204 100644 --- a/arch/x86/um/asm/ptrace.h +++ b/arch/x86/um/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __UM_X86_PTRACE_H #define __UM_X86_PTRACE_H diff --git a/arch/x86/um/asm/segment.h b/arch/x86/um/asm/segment.h index 41dd5e1f3cd7..453db377150d 100644 --- a/arch/x86/um/asm/segment.h +++ b/arch/x86/um/asm/segment.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __UM_SEGMENT_H #define __UM_SEGMENT_H diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h index 11ab90dc5f14..ef898af102d1 100644 --- a/arch/x86/um/asm/syscall.h +++ b/arch/x86/um/asm/syscall.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __UM_ASM_SYSCALL_H #define __UM_ASM_SYSCALL_H diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c index 7bb89a27a5e4..48a3eb09d951 100644 --- a/arch/x86/um/elfcore.c +++ b/arch/x86/um/elfcore.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/elf.h> #include <linux/coredump.h> #include <linux/fs.h> diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c index 836a1eb5df43..3ee234b6234d 100644 --- a/arch/x86/um/ldt.c +++ b/arch/x86/um/ldt.c @@ -6,6 +6,7 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/syscalls.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <os.h> @@ -369,7 +370,9 @@ void free_ldt(struct mm_context *mm) mm->arch.ldt.entry_count = 0; } -int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount) +SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , + unsigned long , bytecount) { - return do_modify_ldt_skas(func, ptr, bytecount); + /* See non-um modify_ldt() for why we do this cast */ + return (unsigned int)do_modify_ldt_skas(func, ptr, bytecount); } diff --git a/arch/x86/um/mem_64.c b/arch/x86/um/mem_64.c index 7642e2e2aa61..c027e93d1002 100644 --- a/arch/x86/um/mem_64.c +++ b/arch/x86/um/mem_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <asm/elf.h> diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c index 1d33d72c6284..49c3744cac37 100644 --- a/arch/x86/um/os-Linux/mcontext.c +++ b/arch/x86/um/os-Linux/mcontext.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <sys/ucontext.h> #define __FRAME_OFFSETS #include <asm/ptrace.h> diff --git a/arch/x86/um/os-Linux/task_size.c b/arch/x86/um/os-Linux/task_size.c index 5adb6a2fd117..e62174638f00 100644 --- a/arch/x86/um/os-Linux/task_size.c +++ b/arch/x86/um/os-Linux/task_size.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <stdio.h> #include <stdlib.h> #include <signal.h> diff --git a/arch/x86/um/os-Linux/tls.c b/arch/x86/um/os-Linux/tls.c index ed8ea90967dc..3e1b1bf6acbc 100644 --- a/arch/x86/um/os-Linux/tls.c +++ b/arch/x86/um/os-Linux/tls.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <linux/unistd.h> diff --git a/arch/x86/um/setjmp_32.S b/arch/x86/um/setjmp_32.S index 39053192918d..62eaf8c80e04 100644 --- a/arch/x86/um/setjmp_32.S +++ b/arch/x86/um/setjmp_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ # # arch/i386/setjmp.S # diff --git a/arch/x86/um/setjmp_64.S b/arch/x86/um/setjmp_64.S index c56942e1a38c..1b5d40d4ff46 100644 --- a/arch/x86/um/setjmp_64.S +++ b/arch/x86/um/setjmp_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ # # arch/x86_64/setjmp.S # diff --git a/arch/x86/um/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp.h index ff7766d28226..166cedbab926 100644 --- a/arch/x86/um/shared/sysdep/archsetjmp.h +++ b/arch/x86/um/shared/sysdep/archsetjmp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifdef __i386__ #include "archsetjmp_32.h" #else diff --git a/arch/x86/um/shared/sysdep/archsetjmp_32.h b/arch/x86/um/shared/sysdep/archsetjmp_32.h index 0f312085ce1d..fb08f2576438 100644 --- a/arch/x86/um/shared/sysdep/archsetjmp_32.h +++ b/arch/x86/um/shared/sysdep/archsetjmp_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * arch/um/include/sysdep-i386/archsetjmp.h */ diff --git a/arch/x86/um/shared/sysdep/archsetjmp_64.h b/arch/x86/um/shared/sysdep/archsetjmp_64.h index 2af8f12ca161..9b499e457ba0 100644 --- a/arch/x86/um/shared/sysdep/archsetjmp_64.h +++ b/arch/x86/um/shared/sysdep/archsetjmp_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * arch/um/include/sysdep-x86_64/archsetjmp.h */ diff --git a/arch/x86/um/shared/sysdep/faultinfo.h b/arch/x86/um/shared/sysdep/faultinfo.h index 862ecb1c7781..4390803e07a1 100644 --- a/arch/x86/um/shared/sysdep/faultinfo.h +++ b/arch/x86/um/shared/sysdep/faultinfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifdef __i386__ #include "faultinfo_32.h" #else diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h index 7e1d35b6ad5c..a004bffb7b8d 100644 --- a/arch/x86/um/shared/sysdep/kernel-offsets.h +++ b/arch/x86/um/shared/sysdep/kernel-offsets.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <linux/stddef.h> #include <linux/sched.h> #include <linux/elf.h> diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h index eb9356904ad3..6ca4ecabc55b 100644 --- a/arch/x86/um/shared/sysdep/ptrace.h +++ b/arch/x86/um/shared/sysdep/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SYSDEP_X86_PTRACE_H #define __SYSDEP_X86_PTRACE_H diff --git a/arch/x86/um/shared/sysdep/ptrace_user.h b/arch/x86/um/shared/sysdep/ptrace_user.h index 16cd6b5e71f7..44782bbad41e 100644 --- a/arch/x86/um/shared/sysdep/ptrace_user.h +++ b/arch/x86/um/shared/sysdep/ptrace_user.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <generated/user_constants.h> #define PT_OFFSET(r) ((r) * sizeof(long)) diff --git a/arch/x86/um/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub.h index 3f55e5bd3cec..ce0ca46ad383 100644 --- a/arch/x86/um/shared/sysdep/stub.h +++ b/arch/x86/um/shared/sysdep/stub.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <asm/unistd.h> #include <sys/mman.h> #include <signal.h> diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h index bd9a89b67e41..b2060ac707f0 100644 --- a/arch/x86/um/shared/sysdep/syscalls.h +++ b/arch/x86/um/shared/sysdep/syscalls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifdef __i386__ #include "syscalls_32.h" #else diff --git a/arch/x86/um/shared/sysdep/tls.h b/arch/x86/um/shared/sysdep/tls.h index a682db13df23..b968016aa379 100644 --- a/arch/x86/um/shared/sysdep/tls.h +++ b/arch/x86/um/shared/sysdep/tls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _SYSDEP_TLS_H #define _SYSDEP_TLS_H diff --git a/arch/x86/um/stub_32.S b/arch/x86/um/stub_32.S index 98816804e131..a193e88536a9 100644 --- a/arch/x86/um/stub_32.S +++ b/arch/x86/um/stub_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <as-layout.h> .section .__syscall_stub, "ax" diff --git a/arch/x86/um/stub_64.S b/arch/x86/um/stub_64.S index ba914b3b8cc4..8a95c5b2eaf9 100644 --- a/arch/x86/um/stub_64.S +++ b/arch/x86/um/stub_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <as-layout.h> .section .__syscall_stub, "ax" diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index bfce503dffae..9649b5ad2ca2 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * System call table for UML/i386, copied from arch/x86/kernel/syscall_*.c * with some changes for UML. diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index f306413d3eb6..c8bc7fb8cbd6 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * System call table for UML/x86-64, copied from arch/x86/kernel/syscall_*.c * with some changes for UML. diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c index 627d68836b16..5c65254c8f35 100644 --- a/arch/x86/um/syscalls_32.c +++ b/arch/x86/um/syscalls_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/syscalls.h> #include <os.h> diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c index 3ad714373d7f..3a621e0d3925 100644 --- a/arch/x86/um/tls_64.c +++ b/arch/x86/um/tls_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/sched.h> #include <asm/ptrace-abi.h> diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index 3099c209546f..5b37b7f952dd 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <stdio.h> #include <stddef.h> #include <signal.h> diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 329406224330..10003359e633 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Building vDSO images for x86. # diff --git a/arch/x86/um/vdso/checkundef.sh b/arch/x86/um/vdso/checkundef.sh index 7ee90a9b549d..8e3ea6bb956f 100644 --- a/arch/x86/um/vdso/checkundef.sh +++ b/arch/x86/um/vdso/checkundef.sh @@ -1,4 +1,5 @@ #!/bin/sh +# SPDX-License-Identifier: GPL-2.0 nm="$1" file="$2" $nm "$file" | grep '^ *U' > /dev/null 2>&1 diff --git a/arch/x86/um/vdso/vdso-layout.lds.S b/arch/x86/um/vdso/vdso-layout.lds.S index 634a2cf62046..439b790df18f 100644 --- a/arch/x86/um/vdso/vdso-layout.lds.S +++ b/arch/x86/um/vdso/vdso-layout.lds.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Linker script for vDSO. This is an ELF shared object prelinked to * its virtual address, and with only one read-only segment. diff --git a/arch/x86/um/vdso/vdso.S b/arch/x86/um/vdso/vdso.S index 1cb468adacbb..a4a3870dc059 100644 --- a/arch/x86/um/vdso/vdso.S +++ b/arch/x86/um/vdso/vdso.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <linux/init.h> __INITDATA diff --git a/arch/x86/um/vdso/vdso.lds.S b/arch/x86/um/vdso/vdso.lds.S index b96b2677cad8..73c508587a98 100644 --- a/arch/x86/um/vdso/vdso.lds.S +++ b/arch/x86/um/vdso/vdso.lds.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Linker script for 64-bit vDSO. * We #include the file to define the layout details. diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 1ecd419811a2..f605825a04ab 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # This Kconfig describes xen options # diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index bced7a369a11..d83cb5478f54 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD_xen-asm_$(BITS).o := y OBJECT_FILES_NON_STANDARD_xen-pvh.o := y diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index b5e48da7fbff..6b830d4cb4c8 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <asm/x86_init.h> @@ -30,7 +31,7 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg) return 0xfd; } -static unsigned long xen_set_apic_id(unsigned int x) +static u32 xen_set_apic_id(unsigned int x) { WARN_ON(1); return x; @@ -160,12 +161,10 @@ static struct apic xen_pv_apic = { /* .irq_delivery_mode - used in native_compose_msi_msg only */ /* .irq_dest_mode - used in native_compose_msi_msg only */ - .target_cpus = default_target_cpus, .disable_esr = 0, /* .dest_logical - default_send_IPI_ use it but we use our own. */ .check_apicid_used = default_check_apicid_used, /* Used on 32-bit */ - .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = xen_noop, /* setup_local_APIC calls it */ .ioapic_phys_id_map = default_ioapic_phys_id_map, /* Used on 32-bit */ @@ -178,7 +177,7 @@ static struct apic xen_pv_apic = { .get_apic_id = xen_get_apic_id, .set_apic_id = xen_set_apic_id, /* Can be NULL on 32-bit. */ - .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, + .calc_dest_apicid = apic_flat_calc_apicid, #ifdef CONFIG_SMP .send_IPI_mask = xen_send_IPI_mask, diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c index 1daff5545c0a..13da87918b4f 100644 --- a/arch/x86/xen/debugfs.c +++ b/arch/x86/xen/debugfs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/debugfs.h> #include <linux/slab.h> diff --git a/arch/x86/xen/debugfs.h b/arch/x86/xen/debugfs.h index 12ebf3325c7b..6b813ad1091c 100644 --- a/arch/x86/xen/debugfs.h +++ b/arch/x86/xen/debugfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XEN_DEBUGFS_H #define _XEN_DEBUGFS_H diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 0e7ef69e8531..d669e9d89001 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -93,11 +93,11 @@ int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int), int rc; rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE, - "x86/xen/hvm_guest:prepare", + "x86/xen/guest:prepare", cpu_up_prepare_cb, cpu_dead_cb); if (rc >= 0) { rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, - "x86/xen/hvm_guest:online", + "x86/xen/guest:online", xen_cpu_up_online, NULL); if (rc < 0) cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index de503c225ae1..826898701045 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -1,3 +1,4 @@ +#include <linux/acpi.h> #include <linux/cpu.h> #include <linux/kexec.h> #include <linux/memblock.h> @@ -188,8 +189,6 @@ static void __init xen_hvm_guest_init(void) xen_hvm_init_time_ops(); xen_hvm_init_mmu_ops(); - if (xen_pvh_domain()) - machine_ops.emergency_restart = xen_emergency_restart; #ifdef CONFIG_KEXEC_CORE machine_ops.shutdown = xen_hvm_shutdown; machine_ops.crash_shutdown = xen_hvm_crash_shutdown; @@ -226,12 +225,33 @@ static uint32_t __init xen_platform_hvm(void) return xen_cpuid_base(); } -const struct hypervisor_x86 x86_hyper_xen_hvm = { +static __init void xen_hvm_guest_late_init(void) +{ +#ifdef CONFIG_XEN_PVH + /* Test for PVH domain (PVH boot path taken overrides ACPI flags). */ + if (!xen_pvh && + (x86_platform.legacy.rtc || !x86_platform.legacy.no_vga)) + return; + + /* PVH detected. */ + xen_pvh = true; + + /* Make sure we don't fall back to (default) ACPI_IRQ_MODEL_PIC. */ + if (!nr_ioapics && acpi_irq_model == ACPI_IRQ_MODEL_PIC) + acpi_irq_model = ACPI_IRQ_MODEL_PLATFORM; + + machine_ops.emergency_restart = xen_emergency_restart; + pv_info.name = "Xen PVH"; +#endif +} + +const __initconst struct hypervisor_x86 x86_hyper_xen_hvm = { .name = "Xen HVM", .detect = xen_platform_hvm, - .init_platform = xen_hvm_guest_init, - .pin_vcpu = xen_pin_vcpu, - .x2apic_available = xen_x2apic_para_available, - .init_mem_mapping = xen_hvm_init_mem_mapping, + .type = X86_HYPER_XEN_HVM, + .init.init_platform = xen_hvm_guest_init, + .init.x2apic_available = xen_x2apic_para_available, + .init.init_mem_mapping = xen_hvm_init_mem_mapping, + .init.guest_late_init = xen_hvm_guest_late_init, + .runtime.pin_vcpu = xen_pin_vcpu, }; -EXPORT_SYMBOL(x86_hyper_xen_hvm); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 69b9deff7e5c..5b2b3f3f6531 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Core of Xen paravirt_ops implementation. * @@ -600,7 +601,7 @@ static struct trap_array_entry trap_array[] = { #ifdef CONFIG_X86_MCE { machine_check, xen_machine_check, true }, #endif - { nmi, xen_nmi, true }, + { nmi, xen_xennmi, true }, { overflow, xen_overflow, false }, #ifdef CONFIG_IA32_EMULATION { entry_INT80_compat, xen_entry_INT80_compat, false }, @@ -810,15 +811,14 @@ static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry, } } -static void xen_load_sp0(struct tss_struct *tss, - struct thread_struct *thread) +static void xen_load_sp0(unsigned long sp0) { struct multicall_space mcs; mcs = xen_mc_entry(0); - MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0); + MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0); xen_mc_issue(PARAVIRT_LAZY_CPU); - tss->x86_tss.sp0 = thread->sp0; + this_cpu_write(cpu_tss.x86_tss.sp0, sp0); } void xen_set_iopl_mask(unsigned mask) @@ -1230,6 +1230,7 @@ asmlinkage __visible void __init xen_start_kernel(void) x86_platform.get_nmi_reason = xen_get_nmi_reason; x86_init.resources.memory_setup = xen_memory_setup; + x86_init.irqs.intr_mode_init = x86_init_noop; x86_init.oem.arch_setup = xen_arch_setup; x86_init.oem.banner = xen_banner; @@ -1459,9 +1460,9 @@ static uint32_t __init xen_platform_pv(void) return 0; } -const struct hypervisor_x86 x86_hyper_xen_pv = { +const __initconst struct hypervisor_x86 x86_hyper_xen_pv = { .name = "Xen PV", .detect = xen_platform_pv, - .pin_vcpu = xen_pin_vcpu, + .type = X86_HYPER_XEN_PV, + .runtime.pin_vcpu = xen_pin_vcpu, }; -EXPORT_SYMBOL(x86_hyper_xen_pv); diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 98ab17673454..436c4f003e17 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/acpi.h> #include <xen/hvc-console.h> @@ -24,13 +25,6 @@ struct boot_params pvh_bootparams __attribute__((section(".data"))); struct hvm_start_info pvh_start_info; unsigned int pvh_start_info_sz = sizeof(pvh_start_info); -static void xen_pvh_arch_setup(void) -{ - /* Make sure we don't fall back to (default) ACPI_IRQ_MODEL_PIC. */ - if (nr_ioapics == 0) - acpi_irq_model = ACPI_IRQ_MODEL_PLATFORM; -} - static void __init init_pvh_bootparams(void) { struct xen_memory_map memmap; @@ -101,6 +95,4 @@ void __init xen_prepare_pvh(void) wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); init_pvh_bootparams(); - - x86_init.oem.arch_setup = xen_pvh_arch_setup; } diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c index 809b6c812654..92ccc718152d 100644 --- a/arch/x86/xen/grant-table.c +++ b/arch/x86/xen/grant-table.c @@ -49,7 +49,7 @@ static struct gnttab_vm_area { struct vm_struct *area; pte_t **ptes; -} gnttab_shared_vm_area; +} gnttab_shared_vm_area, gnttab_status_vm_area; int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, unsigned long max_nr_gframes, @@ -73,16 +73,43 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, return 0; } +int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes, + unsigned long max_nr_gframes, + grant_status_t **__shared) +{ + grant_status_t *shared = *__shared; + unsigned long addr; + unsigned long i; + + if (shared == NULL) + *__shared = shared = gnttab_status_vm_area.area->addr; + + addr = (unsigned long)shared; + + for (i = 0; i < nr_gframes; i++) { + set_pte_at(&init_mm, addr, gnttab_status_vm_area.ptes[i], + mfn_pte(frames[i], PAGE_KERNEL)); + addr += PAGE_SIZE; + } + + return 0; +} + void arch_gnttab_unmap(void *shared, unsigned long nr_gframes) { + pte_t **ptes; unsigned long addr; unsigned long i; + if (shared == gnttab_status_vm_area.area->addr) + ptes = gnttab_status_vm_area.ptes; + else + ptes = gnttab_shared_vm_area.ptes; + addr = (unsigned long)shared; for (i = 0; i < nr_gframes; i++) { - set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i], - __pte(0)); + set_pte_at(&init_mm, addr, ptes[i], __pte(0)); addr += PAGE_SIZE; } } @@ -102,12 +129,35 @@ static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames) return 0; } -int arch_gnttab_init(unsigned long nr_shared) +static void arch_gnttab_vfree(struct gnttab_vm_area *area) { + free_vm_area(area->area); + kfree(area->ptes); +} + +int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status) +{ + int ret; + if (!xen_pv_domain()) return 0; - return arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared); + ret = arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared); + if (ret < 0) + return ret; + + /* + * Always allocate the space for the status frames in case + * we're migrated to a host with V2 support. + */ + ret = arch_gnttab_valloc(&gnttab_status_vm_area, nr_status); + if (ret < 0) + goto err; + + return 0; +err: + arch_gnttab_vfree(&gnttab_shared_vm_area); + return -ENOMEM; } #ifdef CONFIG_XEN_PVH diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index d4eff5676cfa..74179852e46c 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/hardirq.h> #include <asm/x86_init.h> diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 3e15345abfe7..d33e7dbe3129 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -172,6 +172,9 @@ int xen_remap_domain_gfn_range(struct vm_area_struct *vma, pgprot_t prot, unsigned domid, struct page **pages) { + if (xen_feature(XENFEAT_auto_translated_physmap)) + return -EOPNOTSUPP; + return do_remap_gfn(vma, addr, &gfn, nr, NULL, prot, domid, pages); } EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_range); @@ -182,6 +185,10 @@ int xen_remap_domain_gfn_array(struct vm_area_struct *vma, int *err_ptr, pgprot_t prot, unsigned domid, struct page **pages) { + if (xen_feature(XENFEAT_auto_translated_physmap)) + return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr, + prot, domid, pages); + /* We BUG_ON because it's a programmer error to pass a NULL err_ptr, * and the consequences later is quite hard to detect what the actual * cause of "wrong memory was mapped in". @@ -193,9 +200,12 @@ EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_array); /* Returns: 0 success */ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, - int numpgs, struct page **pages) + int nr, struct page **pages) { - if (!pages || !xen_feature(XENFEAT_auto_translated_physmap)) + if (xen_feature(XENFEAT_auto_translated_physmap)) + return xen_xlate_unmap_gfn_range(vma, nr, pages); + + if (!pages) return 0; return -EINVAL; diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 3fe2b3292915..a7e47cf7ec6c 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XEN_MMU_H #include <linux/linkage.h> diff --git a/arch/x86/xen/mmu_hvm.c b/arch/x86/xen/mmu_hvm.c index 1c57f1cd545c..2cfcfe4f6b2a 100644 --- a/arch/x86/xen/mmu_hvm.c +++ b/arch/x86/xen/mmu_hvm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/crash_dump.h> diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 509f560bd0c6..fc048ec686e7 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -315,7 +315,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, static pteval_t pte_mfn_to_pfn(pteval_t val) { if (val & _PAGE_PRESENT) { - unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; + unsigned long mfn = (val & XEN_PTE_MFN_MASK) >> PAGE_SHIFT; unsigned long pfn = mfn_to_pfn(mfn); pteval_t flags = val & PTE_FLAGS_MASK; @@ -449,7 +449,7 @@ __visible pmd_t xen_make_pmd(pmdval_t pmd) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd); -#if CONFIG_PGTABLE_LEVELS == 4 +#ifdef CONFIG_X86_64 __visible pudval_t xen_pud_val(pud_t pud) { return pte_mfn_to_pfn(pud.pud); @@ -538,7 +538,7 @@ static void xen_set_p4d(p4d_t *ptr, p4d_t val) xen_mc_issue(PARAVIRT_LAZY_MMU); } -#endif /* CONFIG_PGTABLE_LEVELS == 4 */ +#endif /* CONFIG_X86_64 */ static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd, int (*func)(struct mm_struct *mm, struct page *, enum pt_level), @@ -580,21 +580,17 @@ static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d, int (*func)(struct mm_struct *mm, struct page *, enum pt_level), bool last, unsigned long limit) { - int i, nr, flush = 0; + int flush = 0; + pud_t *pud; - nr = last ? p4d_index(limit) + 1 : PTRS_PER_P4D; - for (i = 0; i < nr; i++) { - pud_t *pud; - if (p4d_none(p4d[i])) - continue; + if (p4d_none(*p4d)) + return flush; - pud = pud_offset(&p4d[i], 0); - if (PTRS_PER_PUD > 1) - flush |= (*func)(mm, virt_to_page(pud), PT_PUD); - flush |= xen_pud_walk(mm, pud, func, - last && i == nr - 1, limit); - } + pud = pud_offset(p4d, 0); + if (PTRS_PER_PUD > 1) + flush |= (*func)(mm, virt_to_page(pud), PT_PUD); + flush |= xen_pud_walk(mm, pud, func, last, limit); return flush; } @@ -644,8 +640,6 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, continue; p4d = p4d_offset(&pgd[i], 0); - if (PTRS_PER_P4D > 1) - flush |= (*func)(mm, virt_to_page(p4d), PT_P4D); flush |= xen_p4d_walk(mm, p4d, func, i == nr - 1, limit); } @@ -1176,22 +1170,14 @@ static void __init xen_cleanmfnmap(unsigned long vaddr) { pgd_t *pgd; p4d_t *p4d; - unsigned int i; bool unpin; unpin = (vaddr == 2 * PGDIR_SIZE); vaddr &= PMD_MASK; pgd = pgd_offset_k(vaddr); p4d = p4d_offset(pgd, 0); - for (i = 0; i < PTRS_PER_P4D; i++) { - if (p4d_none(p4d[i])) - continue; - xen_cleanmfnmap_p4d(p4d + i, unpin); - } - if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - set_pgd(pgd, __pgd(0)); - xen_cleanmfnmap_free_pgtbl(p4d, unpin); - } + if (!p4d_none(*p4d)) + xen_cleanmfnmap_p4d(p4d, unpin); } static void __init xen_pagetable_p2m_free(void) @@ -1238,21 +1224,16 @@ static void __init xen_pagetable_cleanhighmap(void) * from _brk_limit way up to the max_pfn_mapped (which is the end of * the ramdisk). We continue on, erasing PMD entries that point to page * tables - do note that they are accessible at this stage via __va. - * For good measure we also round up to the PMD - which means that if + * As Xen is aligning the memory end to a 4MB boundary, for good + * measure we also round up to PMD_SIZE * 2 - which means that if * anybody is using __ka address to the initial boot-stack - and try * to use it - they are going to crash. The xen_start_info has been * taken care of already in xen_setup_kernel_pagetable. */ addr = xen_start_info->pt_base; - size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE); + size = xen_start_info->nr_pt_frames * PAGE_SIZE; - xen_cleanhighmap(addr, addr + size); + xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2)); xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base)); -#ifdef DEBUG - /* This is superfluous and is not necessary, but you know what - * lets do it. The MODULES_VADDR -> MODULES_END should be clear of - * anything at this stage. */ - xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1); -#endif } #endif @@ -1697,7 +1678,7 @@ static void xen_release_pmd(unsigned long pfn) xen_release_ptpage(pfn, PT_PMD); } -#if CONFIG_PGTABLE_LEVELS >= 4 +#ifdef CONFIG_X86_64 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn) { xen_alloc_ptpage(mm, pfn, PT_PUD); @@ -1740,7 +1721,7 @@ static unsigned long __init m2p(phys_addr_t maddr) { phys_addr_t paddr; - maddr &= PTE_PFN_MASK; + maddr &= XEN_PTE_MFN_MASK; paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT; return paddr; @@ -2034,13 +2015,12 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) */ void __init xen_relocate_p2m(void) { - phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys, p4d_phys; + phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys; unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end; - int n_pte, n_pt, n_pmd, n_pud, n_p4d, idx_pte, idx_pt, idx_pmd, idx_pud, idx_p4d; + int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud; pte_t *pt; pmd_t *pmd; pud_t *pud; - p4d_t *p4d = NULL; pgd_t *pgd; unsigned long *new_p2m; int save_pud; @@ -2050,11 +2030,7 @@ void __init xen_relocate_p2m(void) n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT; n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT; n_pud = roundup(size, P4D_SIZE) >> P4D_SHIFT; - if (PTRS_PER_P4D > 1) - n_p4d = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT; - else - n_p4d = 0; - n_frames = n_pte + n_pt + n_pmd + n_pud + n_p4d; + n_frames = n_pte + n_pt + n_pmd + n_pud; new_area = xen_find_free_area(PFN_PHYS(n_frames)); if (!new_area) { @@ -2070,76 +2046,56 @@ void __init xen_relocate_p2m(void) * To avoid any possible virtual address collision, just use * 2 * PUD_SIZE for the new area. */ - p4d_phys = new_area; - pud_phys = p4d_phys + PFN_PHYS(n_p4d); + pud_phys = new_area; pmd_phys = pud_phys + PFN_PHYS(n_pud); pt_phys = pmd_phys + PFN_PHYS(n_pmd); p2m_pfn = PFN_DOWN(pt_phys) + n_pt; pgd = __va(read_cr3_pa()); new_p2m = (unsigned long *)(2 * PGDIR_SIZE); - idx_p4d = 0; save_pud = n_pud; - do { - if (n_p4d > 0) { - p4d = early_memremap(p4d_phys, PAGE_SIZE); - clear_page(p4d); - n_pud = min(save_pud, PTRS_PER_P4D); - } - for (idx_pud = 0; idx_pud < n_pud; idx_pud++) { - pud = early_memremap(pud_phys, PAGE_SIZE); - clear_page(pud); - for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD); - idx_pmd++) { - pmd = early_memremap(pmd_phys, PAGE_SIZE); - clear_page(pmd); - for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD); - idx_pt++) { - pt = early_memremap(pt_phys, PAGE_SIZE); - clear_page(pt); - for (idx_pte = 0; - idx_pte < min(n_pte, PTRS_PER_PTE); - idx_pte++) { - set_pte(pt + idx_pte, - pfn_pte(p2m_pfn, PAGE_KERNEL)); - p2m_pfn++; - } - n_pte -= PTRS_PER_PTE; - early_memunmap(pt, PAGE_SIZE); - make_lowmem_page_readonly(__va(pt_phys)); - pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, - PFN_DOWN(pt_phys)); - set_pmd(pmd + idx_pt, - __pmd(_PAGE_TABLE | pt_phys)); - pt_phys += PAGE_SIZE; + for (idx_pud = 0; idx_pud < n_pud; idx_pud++) { + pud = early_memremap(pud_phys, PAGE_SIZE); + clear_page(pud); + for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD); + idx_pmd++) { + pmd = early_memremap(pmd_phys, PAGE_SIZE); + clear_page(pmd); + for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD); + idx_pt++) { + pt = early_memremap(pt_phys, PAGE_SIZE); + clear_page(pt); + for (idx_pte = 0; + idx_pte < min(n_pte, PTRS_PER_PTE); + idx_pte++) { + set_pte(pt + idx_pte, + pfn_pte(p2m_pfn, PAGE_KERNEL)); + p2m_pfn++; } - n_pt -= PTRS_PER_PMD; - early_memunmap(pmd, PAGE_SIZE); - make_lowmem_page_readonly(__va(pmd_phys)); - pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE, - PFN_DOWN(pmd_phys)); - set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys)); - pmd_phys += PAGE_SIZE; + n_pte -= PTRS_PER_PTE; + early_memunmap(pt, PAGE_SIZE); + make_lowmem_page_readonly(__va(pt_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, + PFN_DOWN(pt_phys)); + set_pmd(pmd + idx_pt, + __pmd(_PAGE_TABLE | pt_phys)); + pt_phys += PAGE_SIZE; } - n_pmd -= PTRS_PER_PUD; - early_memunmap(pud, PAGE_SIZE); - make_lowmem_page_readonly(__va(pud_phys)); - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys)); - if (n_p4d > 0) - set_p4d(p4d + idx_pud, __p4d(_PAGE_TABLE | pud_phys)); - else - set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys)); - pud_phys += PAGE_SIZE; - } - if (n_p4d > 0) { - save_pud -= PTRS_PER_P4D; - early_memunmap(p4d, PAGE_SIZE); - make_lowmem_page_readonly(__va(p4d_phys)); - pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, PFN_DOWN(p4d_phys)); - set_pgd(pgd + 2 + idx_p4d, __pgd(_PAGE_TABLE | p4d_phys)); - p4d_phys += PAGE_SIZE; + n_pt -= PTRS_PER_PMD; + early_memunmap(pmd, PAGE_SIZE); + make_lowmem_page_readonly(__va(pmd_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE, + PFN_DOWN(pmd_phys)); + set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys)); + pmd_phys += PAGE_SIZE; } - } while (++idx_p4d < n_p4d); + n_pmd -= PTRS_PER_PUD; + early_memunmap(pud, PAGE_SIZE); + make_lowmem_page_readonly(__va(pud_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys)); + set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys)); + pud_phys += PAGE_SIZE; + } /* Now copy the old p2m info to the new area. */ memcpy(new_p2m, xen_p2m_addr, size); @@ -2220,7 +2176,7 @@ static void __init xen_write_cr3_init(unsigned long cr3) * not the first page table in the page table pool. * Iterate through the initial page tables to find the real page table base. */ -static phys_addr_t xen_find_pt_base(pmd_t *pmd) +static phys_addr_t __init xen_find_pt_base(pmd_t *pmd) { phys_addr_t pt_base, paddr; unsigned pmdidx; @@ -2366,7 +2322,7 @@ static void __init xen_post_allocator_init(void) pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; pv_mmu_ops.set_pud = xen_set_pud; -#if CONFIG_PGTABLE_LEVELS >= 4 +#ifdef CONFIG_X86_64 pv_mmu_ops.set_p4d = xen_set_p4d; #endif @@ -2376,7 +2332,7 @@ static void __init xen_post_allocator_init(void) pv_mmu_ops.alloc_pmd = xen_alloc_pmd; pv_mmu_ops.release_pte = xen_release_pte; pv_mmu_ops.release_pmd = xen_release_pmd; -#if CONFIG_PGTABLE_LEVELS >= 4 +#ifdef CONFIG_X86_64 pv_mmu_ops.alloc_pud = xen_alloc_pud; pv_mmu_ops.release_pud = xen_release_pud; #endif @@ -2440,14 +2396,14 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), -#if CONFIG_PGTABLE_LEVELS >= 4 +#ifdef CONFIG_X86_64 .pud_val = PV_CALLEE_SAVE(xen_pud_val), .make_pud = PV_CALLEE_SAVE(xen_make_pud), .set_p4d = xen_set_p4d_hyper, .alloc_pud = xen_alloc_pmd_init, .release_pud = xen_release_pmd_init, -#endif /* CONFIG_PGTABLE_LEVELS == 4 */ +#endif /* CONFIG_X86_64 */ .activate_mm = xen_activate_mm, .dup_mmap = xen_dup_mmap, diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index ea54a08d8301..dc502ca8263e 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Xen hypercall batching. * diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h index 9c2e74f9096c..1c51b2c87f30 100644 --- a/arch/x86/xen/multicalls.h +++ b/arch/x86/xen/multicalls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XEN_MULTICALLS_H #define _XEN_MULTICALLS_H diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 6083ba462f35..13b4f19b9131 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -547,7 +547,7 @@ int xen_alloc_p2m_entry(unsigned long pfn) if (p2m_top_mfn && pfn < MAX_P2M_PFN) { topidx = p2m_top_index(pfn); top_mfn_p = &p2m_top_mfn[topidx]; - mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]); + mid_mfn = READ_ONCE(p2m_top_mfn_p[topidx]); BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p); diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index b9fc52556bcc..7d00d4ad44d4 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/interrupt.h> diff --git a/arch/x86/xen/pmu.h b/arch/x86/xen/pmu.h index 4be5355b56f7..0e83a160589b 100644 --- a/arch/x86/xen/pmu.h +++ b/arch/x86/xen/pmu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __XEN_PMU_H #define __XEN_PMU_H diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index ac55c02f98e9..c114ca767b3b 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Machine specific setup for xen * diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index e7f02eb73727..77c959cf81e7 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/smp.h> #include <linux/cpu.h> #include <linux/slab.h> diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h index 87d3c76cba37..bd02f9d50107 100644 --- a/arch/x86/xen/smp.h +++ b/arch/x86/xen/smp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XEN_SMP_H #ifdef CONFIG_SMP diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index fd60abedf658..f8d39440b292 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <asm/smp.h> #include <xen/events.h> diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 51471408fdd1..c0c756c76afe 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Xen SMP support * @@ -13,6 +14,7 @@ * single-threaded. */ #include <linux/sched.h> +#include <linux/sched/task_stack.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/smp.h> @@ -293,12 +295,19 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) #endif memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt)); + /* + * Bring up the CPU in cpu_bringup_and_idle() with the stack + * pointing just below where pt_regs would be if it were a normal + * kernel entry. + */ ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle; ctxt->flags = VGCF_IN_KERNEL; ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */ ctxt->user_regs.ds = __USER_DS; ctxt->user_regs.es = __USER_DS; ctxt->user_regs.ss = __KERNEL_DS; + ctxt->user_regs.cs = __KERNEL_CS; + ctxt->user_regs.esp = (unsigned long)task_pt_regs(idle); xen_copy_trap_info(ctxt->trap_ctxt); @@ -313,8 +322,13 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) ctxt->gdt_frames[0] = gdt_mfn; ctxt->gdt_ents = GDT_ENTRIES; + /* + * Set SS:SP that Xen will use when entering guest kernel mode + * from guest user mode. Subsequent calls to load_sp0() can + * change this value. + */ ctxt->kernel_ss = __KERNEL_DS; - ctxt->kernel_sp = idle->thread.sp0; + ctxt->kernel_sp = task_top_of_stack(idle); #ifdef CONFIG_X86_32 ctxt->event_callback_cs = __KERNEL_CS; @@ -326,10 +340,8 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) (unsigned long)xen_hypervisor_callback; ctxt->failsafe_callback_eip = (unsigned long)xen_failsafe_callback; - ctxt->user_regs.cs = __KERNEL_CS; per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir); - ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs); ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir)); if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt)) BUG(); diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 25a7c4302ce7..02f3445a2b5f 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Split spinlock implementation out into its own file, so it can be * compiled in a FTRACE-compatible way. @@ -10,6 +11,7 @@ #include <linux/slab.h> #include <asm/paravirt.h> +#include <asm/qspinlock.h> #include <xen/interface/xen.h> #include <xen/events.h> @@ -80,8 +82,11 @@ void xen_init_lock_cpu(int cpu) int irq; char *name; - if (!xen_pvspin) + if (!xen_pvspin) { + if (cpu == 0) + static_branch_disable(&virt_spin_lock_key); return; + } WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n", cpu, per_cpu(lock_kicker_irq, cpu)); diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index d6b1680693a9..d9f96cc5d743 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/tick.h> @@ -16,6 +17,8 @@ void xen_arch_pre_suspend(void) { + xen_save_time_memory_area(); + if (xen_pv_domain()) xen_pv_pre_suspend(); } @@ -26,6 +29,8 @@ void xen_arch_post_suspend(int cancelled) xen_pv_post_suspend(cancelled); else xen_hvm_post_suspend(cancelled); + + xen_restore_time_memory_area(); } static void xen_vcpu_notify_restore(void *data) diff --git a/arch/x86/xen/suspend_hvm.c b/arch/x86/xen/suspend_hvm.c index 484999416d8b..e666b614cf6d 100644 --- a/arch/x86/xen/suspend_hvm.c +++ b/arch/x86/xen/suspend_hvm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <xen/xen.h> diff --git a/arch/x86/xen/suspend_pv.c b/arch/x86/xen/suspend_pv.c index 3abe4f07f34a..a2e0f110af56 100644 --- a/arch/x86/xen/suspend_pv.c +++ b/arch/x86/xen/suspend_pv.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <asm/fixmap.h> diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 1ecb05db3632..29163c43ebbd 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Xen time implementation. * @@ -74,7 +75,7 @@ static void xen_get_wallclock(struct timespec *now) static int xen_set_wallclock(const struct timespec *now) { - return -1; + return -ENODEV; } static int xen_pvclock_gtod_notify(struct notifier_block *nb, @@ -370,8 +371,95 @@ static const struct pv_time_ops xen_time_ops __initconst = { .steal_clock = xen_steal_clock, }; +static struct pvclock_vsyscall_time_info *xen_clock __read_mostly; + +void xen_save_time_memory_area(void) +{ + struct vcpu_register_time_memory_area t; + int ret; + + if (!xen_clock) + return; + + t.addr.v = NULL; + + ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t); + if (ret != 0) + pr_notice("Cannot save secondary vcpu_time_info (err %d)", + ret); + else + clear_page(xen_clock); +} + +void xen_restore_time_memory_area(void) +{ + struct vcpu_register_time_memory_area t; + int ret; + + if (!xen_clock) + return; + + t.addr.v = &xen_clock->pvti; + + ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t); + + /* + * We don't disable VCLOCK_PVCLOCK entirely if it fails to register the + * secondary time info with Xen or if we migrated to a host without the + * necessary flags. On both of these cases what happens is either + * process seeing a zeroed out pvti or seeing no PVCLOCK_TSC_STABLE_BIT + * bit set. Userspace checks the latter and if 0, it discards the data + * in pvti and fallbacks to a system call for a reliable timestamp. + */ + if (ret != 0) + pr_notice("Cannot restore secondary vcpu_time_info (err %d)", + ret); +} + +static void xen_setup_vsyscall_time_info(void) +{ + struct vcpu_register_time_memory_area t; + struct pvclock_vsyscall_time_info *ti; + int ret; + + ti = (struct pvclock_vsyscall_time_info *)get_zeroed_page(GFP_KERNEL); + if (!ti) + return; + + t.addr.v = &ti->pvti; + + ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, 0, &t); + if (ret) { + pr_notice("xen: VCLOCK_PVCLOCK not supported (err %d)\n", ret); + free_page((unsigned long)ti); + return; + } + + /* + * If primary time info had this bit set, secondary should too since + * it's the same data on both just different memory regions. But we + * still check it in case hypervisor is buggy. + */ + if (!(ti->pvti.flags & PVCLOCK_TSC_STABLE_BIT)) { + t.addr.v = NULL; + ret = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_time_memory_area, + 0, &t); + if (!ret) + free_page((unsigned long)ti); + + pr_notice("xen: VCLOCK_PVCLOCK not supported (tsc unstable)\n"); + return; + } + + xen_clock = ti; + pvclock_set_pvti_cpu0_va(xen_clock); + + xen_clocksource.archdata.vclock_mode = VCLOCK_PVCLOCK; +} + static void __init xen_time_init(void) { + struct pvclock_vcpu_time_info *pvti; int cpu = smp_processor_id(); struct timespec tp; @@ -395,6 +483,16 @@ static void __init xen_time_init(void) setup_force_cpu_cap(X86_FEATURE_TSC); + /* + * We check ahead on the primary time info if this + * bit is supported hence speeding up Xen clocksource. + */ + pvti = &__this_cpu_read(xen_vcpu)->time; + if (pvti->flags & PVCLOCK_TSC_STABLE_BIT) { + pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); + xen_setup_vsyscall_time_info(); + } + xen_setup_runstate_info(cpu); xen_setup_timer(cpu); xen_setup_cpu_clockevents(); diff --git a/arch/x86/xen/trace.c b/arch/x86/xen/trace.c index a702ec2f5931..329f60eb95de 100644 --- a/arch/x86/xen/trace.c +++ b/arch/x86/xen/trace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/ftrace.h> #include <xen/interface/xen.h> #include <xen/interface/xen-mca.h> diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c index 6722e3733f02..e336f223f7f4 100644 --- a/arch/x86/xen/vga.c +++ b/arch/x86/xen/vga.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/screen_info.h> #include <linux/init.h> diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index dcd31fa39b5d..8019edd0125c 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Asm versions of Xen pv-ops, suitable for direct use. * diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index 1200e262a116..c15db060a242 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Asm versions of Xen pv-ops, suitable for direct use. * diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index dae2cc33afb5..8a10c9a9e2b5 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Asm versions of Xen pv-ops, suitable for direct use. * @@ -29,7 +30,7 @@ xen_pv_trap debug xen_pv_trap xendebug xen_pv_trap int3 xen_pv_trap xenint3 -xen_pv_trap nmi +xen_pv_trap xennmi xen_pv_trap overflow xen_pv_trap bounds xen_pv_trap invalid_op diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index a7525e95d53f..497cc55a0c16 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* Xen-specific pieces of head.S, intended to be included in the right place in head.S */ @@ -9,6 +10,7 @@ #include <asm/boot.h> #include <asm/asm.h> #include <asm/page_types.h> +#include <asm/unwind_hints.h> #include <xen/interface/elfnote.h> #include <xen/interface/features.h> @@ -19,6 +21,7 @@ #ifdef CONFIG_XEN_PV __INIT ENTRY(startup_xen) + UNWIND_HINT_EMPTY cld /* Clear .bss */ @@ -33,21 +36,24 @@ ENTRY(startup_xen) mov $init_thread_union+THREAD_SIZE, %_ASM_SP jmp xen_start_kernel - +END(startup_xen) __FINIT #endif .pushsection .text .balign PAGE_SIZE ENTRY(hypercall_page) - .skip PAGE_SIZE + .rept (PAGE_SIZE / 32) + UNWIND_HINT_EMPTY + .skip 32 + .endr #define HYPERCALL(n) \ .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 #include <asm/xen-hypercalls.h> #undef HYPERCALL - +END(hypercall_page) .popsection ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index c8a6d224f7ed..75011b80660f 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef XEN_OPS_H #define XEN_OPS_H @@ -69,6 +70,8 @@ void xen_setup_runstate_info(int cpu); void xen_teardown_timer(int cpu); u64 xen_clocksource_read(void); void xen_setup_cpu_clockevents(void); +void xen_save_time_memory_area(void); +void xen_restore_time_memory_area(void); void __init xen_init_time_ops(void); void __init xen_hvm_init_time_ops(void); |