diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-01-15 13:18:47 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-01-15 13:18:47 -0800 |
commit | f689b742f217b2ffe7925f8a6521b208ee995309 (patch) | |
tree | 40ed4482ce5808fd5498fe935205b06782bbbca4 /arch/powerpc/platforms | |
parent | 37cea93b99d2d89bef3adcb4632d71e1f377c447 (diff) | |
parent | be6bfc29bc759670fb3a2519325c4ab2edf259c9 (diff) | |
download | linux-f689b742f217b2ffe7925f8a6521b208ee995309.tar.gz linux-f689b742f217b2ffe7925f8a6521b208ee995309.tar.bz2 linux-f689b742f217b2ffe7925f8a6521b208ee995309.zip |
Merge tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"Core:
- Ground work for the new Power9 MMU from Aneesh Kumar K.V
- Optimise FP/VMX/VSX context switching from Anton Blanchard
Misc:
- Various cleanups from Krzysztof Kozlowski, John Ogness, Rashmica
Gupta, Russell Currey, Gavin Shan, Daniel Axtens, Michael Neuling,
Andrew Donnellan
- Allow wrapper to work on non-english system from Laurent Vivier
- Add rN aliases to the pt_regs_offset table from Rashmica Gupta
- Fix module autoload for rackmeter & axonram drivers from Luis de
Bethencourt
- Include KVM guest test in all interrupt vectors from Paul Mackerras
- Fix DSCR inheritance over fork() from Anton Blanchard
- Make value-returning atomics & {cmp}xchg* & their atomic_ versions
fully ordered from Boqun Feng
- Print MSR TM bits in oops messages from Michael Neuling
- Add TM signal return & invalid stack selftests from Michael Neuling
- Limit EPOW reset event warnings from Vipin K Parashar
- Remove the Cell QPACE code from Rashmica Gupta
- Append linux_banner to exception information in xmon from Rashmica
Gupta
- Add selftest to check if VSRs are corrupted from Rashmica Gupta
- Remove broken GregorianDay() from Daniel Axtens
- Import Anton's context_switch2 benchmark into selftests from
Michael Ellerman
- Add selftest script to test HMI functionality from Daniel Axtens
- Remove obsolete OPAL v2 support from Stewart Smith
- Make enter_rtas() private from Michael Ellerman
- PPR exception cleanups from Michael Ellerman
- Add page soft dirty tracking from Laurent Dufour
- Add support for Nvlink NPUs from Alistair Popple
- Add support for kexec on 476fpe from Alistair Popple
- Enable kernel CPU dlpar from sysfs from Nathan Fontenot
- Copy only required pieces of the mm_context_t to the paca from
Michael Neuling
- Add a kmsg_dumper that flushes OPAL console output on panic from
Russell Currey
- Implement save_stack_trace_regs() to enable kprobe stack tracing
from Steven Rostedt
- Add HWCAP bits for Power9 from Michael Ellerman
- Fix _PAGE_PTE breaking swapoff from Aneesh Kumar K.V
- Fix _PAGE_SWP_SOFT_DIRTY breaking swapoff from Hugh Dickins
- scripts/recordmcount.pl: support data in text section on powerpc
from Ulrich Weigand
- Handle R_PPC64_ENTRY relocations in modules from Ulrich Weigand
cxl:
- cxl: Fix possible idr warning when contexts are released from
Vaibhav Jain
- cxl: use correct operator when writing pcie config space values
from Andrew Donnellan
- cxl: Fix DSI misses when the context owning task exits from Vaibhav
Jain
- cxl: fix build for GCC 4.6.x from Brian Norris
- cxl: use -Werror only with CONFIG_PPC_WERROR from Brian Norris
- cxl: Enable PCI device ID for future IBM CXL adapter from Uma
Krishnan
Freescale:
- Freescale updates from Scott: Highlights include moving QE code out
of arch/powerpc (to be shared with arm), device tree updates, and
minor fixes"
* tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (149 commits)
powerpc/module: Handle R_PPC64_ENTRY relocations
scripts/recordmcount.pl: support data in text section on powerpc
powerpc/powernv: Fix OPAL_CONSOLE_FLUSH prototype and usages
powerpc/mm: fix _PAGE_SWP_SOFT_DIRTY breaking swapoff
powerpc/mm: Fix _PAGE_PTE breaking swapoff
cxl: Enable PCI device ID for future IBM CXL adapter
cxl: use -Werror only with CONFIG_PPC_WERROR
cxl: fix build for GCC 4.6.x
powerpc: Add HWCAP bits for Power9
powerpc/powernv: Reserve PE#0 on NPU
powerpc/powernv: Change NPU PE# assignment
powerpc/powernv: Fix update of NVLink DMA mask
powerpc/powernv: Remove misleading comment in pci.c
powerpc: Implement save_stack_trace_regs() to enable kprobe stack tracing
powerpc: Fix build break due to paca mm_context_t changes
cxl: Fix DSI misses when the context owning task exits
MAINTAINERS: Update Scott Wood's e-mail address
powerpc/powernv: Fix minor off-by-one error in opal_mce_check_early_recovery()
powerpc: Fix style of self-test config prompts
powerpc/powernv: Only delay opal_rtc_read() retry when necessary
...
Diffstat (limited to 'arch/powerpc/platforms')
41 files changed, 1358 insertions, 577 deletions
diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c index bf4c4473abb9..4bc6bbbe9ada 100644 --- a/arch/powerpc/platforms/83xx/km83xx.c +++ b/arch/powerpc/platforms/83xx/km83xx.c @@ -37,8 +37,8 @@ #include <asm/udbg.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include "mpc83xx.h" @@ -136,8 +136,6 @@ static void __init mpc83xx_km_setup_arch(void) mpc83xx_setup_pci(); #ifdef CONFIG_QUICC_ENGINE - qe_reset(); - np = of_find_node_by_name(NULL, "par_io"); if (np != NULL) { par_io_init(np); diff --git a/arch/powerpc/platforms/83xx/misc.c b/arch/powerpc/platforms/83xx/misc.c index ef9d01a049c1..7e923cad56cf 100644 --- a/arch/powerpc/platforms/83xx/misc.c +++ b/arch/powerpc/platforms/83xx/misc.c @@ -17,7 +17,7 @@ #include <asm/io.h> #include <asm/hw_irq.h> #include <asm/ipic.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe_ic.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c index 8d762203eeff..a973b2ae5df6 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c @@ -36,8 +36,8 @@ #include <asm/udbg.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include "mpc83xx.h" @@ -74,8 +74,6 @@ static void __init mpc832x_sys_setup_arch(void) mpc83xx_setup_pci(); #ifdef CONFIG_QUICC_ENGINE - qe_reset(); - if ((np = of_find_node_by_name(NULL, "par_io")) != NULL) { par_io_init(np); of_node_put(np); diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c index eff5baabc3fb..ea2b87d202ca 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c @@ -25,8 +25,8 @@ #include <asm/time.h> #include <asm/ipic.h> #include <asm/udbg.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> @@ -203,8 +203,6 @@ static void __init mpc832x_rdb_setup_arch(void) mpc83xx_setup_pci(); #ifdef CONFIG_QUICC_ENGINE - qe_reset(); - if ((np = of_find_node_by_name(NULL, "par_io")) != NULL) { par_io_init(np); of_node_put(np); diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c index 1a26d2f83401..dd70b85f56d4 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c @@ -44,8 +44,8 @@ #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> #include <sysdev/simple_gpio.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include "mpc83xx.h" @@ -82,8 +82,6 @@ static void __init mpc836x_mds_setup_arch(void) mpc83xx_setup_pci(); #ifdef CONFIG_QUICC_ENGINE - qe_reset(); - if ((np = of_find_node_by_name(NULL, "par_io")) != NULL) { par_io_init(np); of_node_put(np); diff --git a/arch/powerpc/platforms/83xx/mpc836x_rdk.c b/arch/powerpc/platforms/83xx/mpc836x_rdk.c index b63b42d11d6c..4cd7153a6c88 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_rdk.c +++ b/arch/powerpc/platforms/83xx/mpc836x_rdk.c @@ -20,8 +20,8 @@ #include <asm/time.h> #include <asm/ipic.h> #include <asm/udbg.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> @@ -35,9 +35,6 @@ static void __init mpc836x_rdk_setup_arch(void) ppc_md.progress("mpc836x_rdk_setup_arch()", 0); mpc83xx_setup_pci(); -#ifdef CONFIG_QUICC_ENGINE - qe_reset(); -#endif } /* diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c index f0927e58af25..dcfafd6b91ee 100644 --- a/arch/powerpc/platforms/85xx/bsc913x_qds.c +++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c @@ -17,6 +17,7 @@ #include <linux/pci.h> #include <asm/mpic.h> #include <sysdev/fsl_soc.h> +#include <sysdev/fsl_pci.h> #include <asm/udbg.h> #include "mpc85xx.h" @@ -46,10 +47,12 @@ static void __init bsc913x_qds_setup_arch(void) mpc85xx_smp_init(); #endif + fsl_pci_assign_primary(); + pr_info("bsc913x board from Freescale Semiconductor\n"); } -machine_device_initcall(bsc9132_qds, mpc85xx_common_publish_devices); +machine_arch_initcall(bsc9132_qds, mpc85xx_common_publish_devices); /* * Called very early, device-tree isn't unflattened @@ -67,6 +70,9 @@ define_machine(bsc9132_qds) { .probe = bsc9132_qds_probe, .setup_arch = bsc913x_qds_setup_arch, .init_IRQ = bsc913x_qds_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, +#endif .get_irq = mpic_get_irq, .restart = fsl_rstcr_restart, .calibrate_decr = generic_calibrate_decr, diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c index 23791de7b688..949f22c86e61 100644 --- a/arch/powerpc/platforms/85xx/common.c +++ b/arch/powerpc/platforms/85xx/common.c @@ -9,7 +9,7 @@ #include <linux/of_irq.h> #include <linux/of_platform.h> -#include <asm/qe.h> +#include <soc/fsl/qe/qe.h> #include <sysdev/cpm2_pic.h> #include "mpc85xx.h" @@ -105,7 +105,6 @@ void __init mpc85xx_qe_init(void) return; } - qe_reset(); of_node_put(np); } diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index 46d05c94add6..a2b0bc859de0 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -27,7 +27,7 @@ #include <asm/udbg.h> #include <asm/mpic.h> #include <asm/ehv_pic.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe_ic.h> #include <linux/of_platform.h> #include <sysdev/fsl_soc.h> diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c index 7d12a19aa7ee..de72a5f464b1 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c @@ -36,17 +36,6 @@ #include "mpc85xx.h" -#ifdef CONFIG_PCI -static int mpc85xx_exclude_device(struct pci_controller *hose, - u_char bus, u_char devfn) -{ - if (bus == 0 && PCI_SLOT(devfn) == 0) - return PCIBIOS_DEVICE_NOT_FOUND; - else - return PCIBIOS_SUCCESSFUL; -} -#endif /* CONFIG_PCI */ - static void __init mpc85xx_ads_pic_init(void) { struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN, @@ -145,10 +134,6 @@ static void __init mpc85xx_ads_setup_arch(void) init_ioports(); #endif -#ifdef CONFIG_PCI - ppc_md.pci_exclude_device = mpc85xx_exclude_device; -#endif - fsl_pci_assign_primary(); } diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index f0be439ceaaa..f61cbe235581 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -48,8 +48,8 @@ #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> #include <sysdev/simple_gpio.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include <asm/mpic.h> #include <asm/swiotlb.h> #include "smp.h" diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index 50dcc00a0f5a..3f4dad133338 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -26,8 +26,8 @@ #include <asm/prom.h> #include <asm/udbg.h> #include <asm/mpic.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c index 892e613519cc..71bc255b4324 100644 --- a/arch/powerpc/platforms/85xx/twr_p102x.c +++ b/arch/powerpc/platforms/85xx/twr_p102x.c @@ -22,8 +22,8 @@ #include <asm/pci-bridge.h> #include <asm/udbg.h> #include <asm/mpic.h> -#include <asm/qe.h> -#include <asm/qe_ic.h> +#include <soc/fsl/qe/qe.h> +#include <soc/fsl/qe/qe_ic.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index b7f9c408bf24..46a3533d3acb 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -272,17 +272,6 @@ config TAU_AVERAGE If in doubt, say N here. -config QUICC_ENGINE - bool "Freescale QUICC Engine (QE) Support" - depends on FSL_SOC && PPC32 - select PPC_LIB_RHEAP - select CRC32 - help - The QUICC Engine (QE) is a new generation of communications - coprocessors on Freescale embedded CPUs (akin to CPM in older chips). - Selecting this option means that you wish to build a kernel - for a machine with a QE coprocessor. - config QE_GPIO bool "QE GPIO support" depends on QUICC_ENGINE @@ -295,7 +284,6 @@ config CPM2 bool "Enable support for the CPM2 (Communications Processor Module)" depends on (FSL_SOC_BOOKE && PPC32) || 8260 select CPM - select PPC_LIB_RHEAP select PPC_PCI_CHOICE select ARCH_REQUIRE_GPIOLIB help @@ -325,6 +313,7 @@ config FSL_ULI1575 config CPM bool + select GENERIC_ALLOCATOR config OF_RTC bool diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 429fc59d2a47..d9088f0b8fcc 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -33,11 +33,6 @@ config PPC_IBM_CELL_BLADE select PPC_UDBG_16550 select UDBG_RTAS_CONSOLE -config PPC_CELL_QPACE - bool "IBM Cell - QPACE" - depends on PPC64 && PPC_BOOK3S && CPU_BIG_ENDIAN - select PPC_CELL_COMMON - config AXON_MSI bool depends on PPC_IBM_CELL_BLADE && PCI_MSI diff --git a/arch/powerpc/platforms/cell/Makefile b/arch/powerpc/platforms/cell/Makefile index 34699bddfddd..00464305763d 100644 --- a/arch/powerpc/platforms/cell/Makefile +++ b/arch/powerpc/platforms/cell/Makefile @@ -11,7 +11,6 @@ obj-$(CONFIG_PPC_IBM_CELL_POWERBUTTON) += cbe_powerbutton.o ifeq ($(CONFIG_SMP),y) obj-$(CONFIG_PPC_CELL_NATIVE) += smp.o -obj-$(CONFIG_PPC_CELL_QPACE) += smp.o endif # needed only when building loadable spufs.ko @@ -26,6 +25,3 @@ obj-$(CONFIG_SPU_BASE) += spu_callbacks.o spu_base.o \ spufs/ obj-$(CONFIG_AXON_MSI) += axon_msi.o - -# qpace setup -obj-$(CONFIG_PPC_CELL_QPACE) += qpace_setup.o diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c deleted file mode 100644 index d328140dc6f5..000000000000 --- a/arch/powerpc/platforms/cell/qpace_setup.c +++ /dev/null @@ -1,148 +0,0 @@ -/* - * linux/arch/powerpc/platforms/cell/qpace_setup.c - * - * Copyright (C) 1995 Linus Torvalds - * Adapted from 'alpha' version by Gary Thomas - * Modified by Cort Dougan (cort@cs.nmt.edu) - * Modified by PPC64 Team, IBM Corp - * Modified by Cell Team, IBM Deutschland Entwicklung GmbH - * Modified by Benjamin Krill <ben@codiert.org>, IBM Corp. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/export.h> -#include <linux/delay.h> -#include <linux/irq.h> -#include <linux/console.h> -#include <linux/of_platform.h> - -#include <asm/mmu.h> -#include <asm/processor.h> -#include <asm/io.h> -#include <asm/kexec.h> -#include <asm/pgtable.h> -#include <asm/prom.h> -#include <asm/rtas.h> -#include <asm/dma.h> -#include <asm/machdep.h> -#include <asm/time.h> -#include <asm/cputable.h> -#include <asm/irq.h> -#include <asm/spu.h> -#include <asm/spu_priv1.h> -#include <asm/udbg.h> -#include <asm/cell-regs.h> - -#include "interrupt.h" -#include "pervasive.h" -#include "ras.h" - -static void qpace_show_cpuinfo(struct seq_file *m) -{ - struct device_node *root; - const char *model = ""; - - root = of_find_node_by_path("/"); - if (root) - model = of_get_property(root, "model", NULL); - seq_printf(m, "machine\t\t: CHRP %s\n", model); - of_node_put(root); -} - -static void qpace_progress(char *s, unsigned short hex) -{ - printk("*** %04x : %s\n", hex, s ? s : ""); -} - -static const struct of_device_id qpace_bus_ids[] __initconst = { - { .type = "soc", }, - { .compatible = "soc", }, - { .type = "spider", }, - { .type = "axon", }, - { .type = "plb5", }, - { .type = "plb4", }, - { .type = "opb", }, - { .type = "ebc", }, - {}, -}; - -static int __init qpace_publish_devices(void) -{ - int node; - - /* Publish OF platform devices for southbridge IOs */ - of_platform_bus_probe(NULL, qpace_bus_ids, NULL); - - /* There is no device for the MIC memory controller, thus we create - * a platform device for it to attach the EDAC driver to. - */ - for_each_online_node(node) { - if (cbe_get_cpu_mic_tm_regs(cbe_node_to_cpu(node)) == NULL) - continue; - platform_device_register_simple("cbe-mic", node, NULL, 0); - } - - return 0; -} -machine_subsys_initcall(qpace, qpace_publish_devices); - -static void __init qpace_setup_arch(void) -{ -#ifdef CONFIG_SPU_BASE - spu_priv1_ops = &spu_priv1_mmio_ops; - spu_management_ops = &spu_management_of_ops; -#endif - - cbe_regs_init(); - -#ifdef CONFIG_CBE_RAS - cbe_ras_init(); -#endif - -#ifdef CONFIG_SMP - smp_init_cell(); -#endif - - /* init to some ~sane value until calibrate_delay() runs */ - loops_per_jiffy = 50000000; - - cbe_pervasive_init(); -#ifdef CONFIG_DUMMY_CONSOLE - conswitchp = &dummy_con; -#endif -} - -static int __init qpace_probe(void) -{ - unsigned long root = of_get_flat_dt_root(); - - if (!of_flat_dt_is_compatible(root, "IBM,QPACE")) - return 0; - - hpte_init_native(); - pm_power_off = rtas_power_off; - - return 1; -} - -define_machine(qpace) { - .name = "QPACE", - .probe = qpace_probe, - .setup_arch = qpace_setup_arch, - .show_cpuinfo = qpace_show_cpuinfo, - .restart = rtas_restart, - .halt = rtas_halt, - .get_boot_time = rtas_get_boot_time, - .get_rtc_time = rtas_get_rtc_time, - .set_rtc_time = rtas_set_rtc_time, - .calibrate_decr = generic_calibrate_decr, - .progress = qpace_progress, - .init_IRQ = iic_init_IRQ, -}; diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c index 4ddf769a64e5..9f79004e6d6f 100644 --- a/arch/powerpc/platforms/cell/spufs/run.c +++ b/arch/powerpc/platforms/cell/spufs/run.c @@ -326,7 +326,7 @@ static int spu_process_callback(struct spu_context *ctx) spu_ret = -ENOSYS; npc += 4; - if (s.nr_ret < __NR_syscalls) { + if (s.nr_ret < NR_syscalls) { spu_release(ctx); /* do actual system call from here */ spu_ret = spu_sys_callback(&s); diff --git a/arch/powerpc/platforms/maple/time.c b/arch/powerpc/platforms/maple/time.c index b4a369dac3a8..81799d70a1ee 100644 --- a/arch/powerpc/platforms/maple/time.c +++ b/arch/powerpc/platforms/maple/time.c @@ -77,7 +77,7 @@ void maple_get_rtc_time(struct rtc_time *tm) if ((tm->tm_year + 1900) < 1970) tm->tm_year += 100; - GregorianDay(tm); + tm->tm_wday = -1; } int maple_set_rtc_time(struct rtc_time *tm) diff --git a/arch/powerpc/platforms/powermac/bootx_init.c b/arch/powerpc/platforms/powermac/bootx_init.c index 76f5013c35e5..c3c9bbb3573a 100644 --- a/arch/powerpc/platforms/powermac/bootx_init.c +++ b/arch/powerpc/platforms/powermac/bootx_init.c @@ -84,6 +84,7 @@ static void __init bootx_printf(const char *format, ...) break; } } + va_end(args); } #else /* CONFIG_BOOTX_TEXT */ static void __init bootx_printf(const char *format, ...) {} diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 6f4f8b060def..981546345033 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -258,13 +258,14 @@ static unsigned int pmac_pic_get_irq(void) #ifdef CONFIG_XMON static struct irqaction xmon_action = { .handler = xmon_irq, - .flags = 0, + .flags = IRQF_NO_THREAD, .name = "NMI - XMON" }; #endif static struct irqaction gatwick_cascade_action = { .handler = gatwick_action, + .flags = IRQF_NO_THREAD, .name = "cascade", }; diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 1c8cdb6250e7..f1516b5ecec9 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -2,9 +2,10 @@ obj-y += setup.o opal-wrappers.o opal.o opal-async.o idle.o obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o +obj-y += opal-kmsg.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o -obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o +obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o npu-dma.o obj-$(CONFIG_EEH) += eeh-powernv.o obj-$(CONFIG_PPC_SCOM) += opal-xscom.o obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index e1c90725522a..5f152b95ca0c 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -48,8 +48,8 @@ static int pnv_eeh_init(void) struct pci_controller *hose; struct pnv_phb *phb; - if (!firmware_has_feature(FW_FEATURE_OPALv3)) { - pr_warn("%s: OPALv3 is required !\n", + if (!firmware_has_feature(FW_FEATURE_OPAL)) { + pr_warn("%s: OPAL is required !\n", __func__); return -EINVAL; } diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 59d735d2e5c0..15bfbcd5debc 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -242,7 +242,7 @@ static int __init pnv_init_idle_states(void) if (cpuidle_disable != IDLE_NO_OVERRIDE) goto out; - if (!firmware_has_feature(FW_FEATURE_OPALv3)) + if (!firmware_has_feature(FW_FEATURE_OPAL)) goto out; power_mgt = of_find_node_by_path("/ibm,opal/power-mgt"); diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c new file mode 100644 index 000000000000..e85aa900f5c0 --- /dev/null +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -0,0 +1,348 @@ +/* + * This file implements the DMA operations for NVLink devices. The NPU + * devices all point to the same iommu table as the parent PCI device. + * + * Copyright Alistair Popple, IBM Corporation 2015. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ + +#include <linux/export.h> +#include <linux/pci.h> +#include <linux/memblock.h> + +#include <asm/iommu.h> +#include <asm/pnv-pci.h> +#include <asm/msi_bitmap.h> +#include <asm/opal.h> + +#include "powernv.h" +#include "pci.h" + +/* + * Other types of TCE cache invalidation are not functional in the + * hardware. + */ +#define TCE_KILL_INVAL_ALL PPC_BIT(0) + +static struct pci_dev *get_pci_dev(struct device_node *dn) +{ + return PCI_DN(dn)->pcidev; +} + +/* Given a NPU device get the associated PCI device. */ +struct pci_dev *pnv_pci_get_gpu_dev(struct pci_dev *npdev) +{ + struct device_node *dn; + struct pci_dev *gpdev; + + /* Get assoicated PCI device */ + dn = of_parse_phandle(npdev->dev.of_node, "ibm,gpu", 0); + if (!dn) + return NULL; + + gpdev = get_pci_dev(dn); + of_node_put(dn); + + return gpdev; +} +EXPORT_SYMBOL(pnv_pci_get_gpu_dev); + +/* Given the real PCI device get a linked NPU device. */ +struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index) +{ + struct device_node *dn; + struct pci_dev *npdev; + + /* Get assoicated PCI device */ + dn = of_parse_phandle(gpdev->dev.of_node, "ibm,npu", index); + if (!dn) + return NULL; + + npdev = get_pci_dev(dn); + of_node_put(dn); + + return npdev; +} +EXPORT_SYMBOL(pnv_pci_get_npu_dev); + +#define NPU_DMA_OP_UNSUPPORTED() \ + dev_err_once(dev, "%s operation unsupported for NVLink devices\n", \ + __func__) + +static void *dma_npu_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flag, + struct dma_attrs *attrs) +{ + NPU_DMA_OP_UNSUPPORTED(); + return NULL; +} + +static void dma_npu_free(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ + NPU_DMA_OP_UNSUPPORTED(); +} + +static dma_addr_t dma_npu_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + NPU_DMA_OP_UNSUPPORTED(); + return 0; +} + +static int dma_npu_map_sg(struct device *dev, struct scatterlist *sglist, + int nelems, enum dma_data_direction direction, + struct dma_attrs *attrs) +{ + NPU_DMA_OP_UNSUPPORTED(); + return 0; +} + +static int dma_npu_dma_supported(struct device *dev, u64 mask) +{ + NPU_DMA_OP_UNSUPPORTED(); + return 0; +} + +static u64 dma_npu_get_required_mask(struct device *dev) +{ + NPU_DMA_OP_UNSUPPORTED(); + return 0; +} + +struct dma_map_ops dma_npu_ops = { + .map_page = dma_npu_map_page, + .map_sg = dma_npu_map_sg, + .alloc = dma_npu_alloc, + .free = dma_npu_free, + .dma_supported = dma_npu_dma_supported, + .get_required_mask = dma_npu_get_required_mask, +}; + +/* + * Returns the PE assoicated with the PCI device of the given + * NPU. Returns the linked pci device if pci_dev != NULL. + */ +static struct pnv_ioda_pe *get_gpu_pci_dev_and_pe(struct pnv_ioda_pe *npe, + struct pci_dev **gpdev) +{ + struct pnv_phb *phb; + struct pci_controller *hose; + struct pci_dev *pdev; + struct pnv_ioda_pe *pe; + struct pci_dn *pdn; + + if (npe->flags & PNV_IODA_PE_PEER) { + pe = npe->peers[0]; + pdev = pe->pdev; + } else { + pdev = pnv_pci_get_gpu_dev(npe->pdev); + if (!pdev) + return NULL; + + pdn = pci_get_pdn(pdev); + if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) + return NULL; + + hose = pci_bus_to_host(pdev->bus); + phb = hose->private_data; + pe = &phb->ioda.pe_array[pdn->pe_number]; + } + + if (gpdev) + *gpdev = pdev; + + return pe; +} + +void pnv_npu_tce_invalidate_entire(struct pnv_ioda_pe *npe) +{ + struct pnv_phb *phb = npe->phb; + + if (WARN_ON(phb->type != PNV_PHB_NPU || + !phb->ioda.tce_inval_reg || + !(npe->flags & PNV_IODA_PE_DEV))) + return; + + mb(); /* Ensure previous TCE table stores are visible */ + __raw_writeq(cpu_to_be64(TCE_KILL_INVAL_ALL), + phb->ioda.tce_inval_reg); +} + +void pnv_npu_tce_invalidate(struct pnv_ioda_pe *npe, + struct iommu_table *tbl, + unsigned long index, + unsigned long npages, + bool rm) +{ + struct pnv_phb *phb = npe->phb; + + /* We can only invalidate the whole cache on NPU */ + unsigned long val = TCE_KILL_INVAL_ALL; + + if (WARN_ON(phb->type != PNV_PHB_NPU || + !phb->ioda.tce_inval_reg || + !(npe->flags & PNV_IODA_PE_DEV))) + return; + + mb(); /* Ensure previous TCE table stores are visible */ + if (rm) + __raw_rm_writeq(cpu_to_be64(val), + (__be64 __iomem *) phb->ioda.tce_inval_reg_phys); + else + __raw_writeq(cpu_to_be64(val), + phb->ioda.tce_inval_reg); +} + +void pnv_npu_init_dma_pe(struct pnv_ioda_pe *npe) +{ + struct pnv_ioda_pe *gpe; + struct pci_dev *gpdev; + int i, avail = -1; + + if (!npe->pdev || !(npe->flags & PNV_IODA_PE_DEV)) + return; + + gpe = get_gpu_pci_dev_and_pe(npe, &gpdev); + if (!gpe) + return; + + for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) { + /* Nothing to do if the PE is already connected. */ + if (gpe->peers[i] == npe) + return; + + if (!gpe->peers[i]) + avail = i; + } + + if (WARN_ON(avail < 0)) + return; + + gpe->peers[avail] = npe; + gpe->flags |= PNV_IODA_PE_PEER; + + /* + * We assume that the NPU devices only have a single peer PE + * (the GPU PCIe device PE). + */ + npe->peers[0] = gpe; + npe->flags |= PNV_IODA_PE_PEER; +} + +/* + * For the NPU we want to point the TCE table at the same table as the + * real PCI device. + */ +static void pnv_npu_disable_bypass(struct pnv_ioda_pe *npe) +{ + struct pnv_phb *phb = npe->phb; + struct pci_dev *gpdev; + struct pnv_ioda_pe *gpe; + void *addr; + unsigned int size; + int64_t rc; + + /* + * Find the assoicated PCI devices and get the dma window + * information from there. + */ + if (!npe->pdev || !(npe->flags & PNV_IODA_PE_DEV)) + return; + + gpe = get_gpu_pci_dev_and_pe(npe, &gpdev); + if (!gpe) + return; + + addr = (void *)gpe->table_group.tables[0]->it_base; + size = gpe->table_group.tables[0]->it_size << 3; + rc = opal_pci_map_pe_dma_window(phb->opal_id, npe->pe_number, + npe->pe_number, 1, __pa(addr), + size, 0x1000); + if (rc != OPAL_SUCCESS) + pr_warn("%s: Error %lld setting DMA window on PHB#%d-PE#%d\n", + __func__, rc, phb->hose->global_number, npe->pe_number); + + /* + * We don't initialise npu_pe->tce32_table as we always use + * dma_npu_ops which are nops. + */ + set_dma_ops(&npe->pdev->dev, &dma_npu_ops); +} + +/* + * Enable/disable bypass mode on the NPU. The NPU only supports one + * window per link, so bypass needs to be explicity enabled or + * disabled. Unlike for a PHB3 bypass and non-bypass modes can't be + * active at the same time. + */ +int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe, bool enable) +{ + struct pnv_phb *phb = npe->phb; + int64_t rc = 0; + + if (phb->type != PNV_PHB_NPU || !npe->pdev) + return -EINVAL; + + if (enable) { + /* Enable the bypass window */ + phys_addr_t top = memblock_end_of_DRAM(); + + npe->tce_bypass_base = 0; + top = roundup_pow_of_two(top); + dev_info(&npe->pdev->dev, "Enabling bypass for PE %d\n", + npe->pe_number); + rc = opal_pci_map_pe_dma_window_real(phb->opal_id, + npe->pe_number, npe->pe_number, + npe->tce_bypass_base, top); + } else { + /* + * Disable the bypass window by replacing it with the + * TCE32 window. + */ + pnv_npu_disable_bypass(npe); + } + + return rc; +} + +int pnv_npu_dma_set_mask(struct pci_dev *npdev, u64 dma_mask) +{ + struct pci_controller *hose = pci_bus_to_host(npdev->bus); + struct pnv_phb *phb = hose->private_data; + struct pci_dn *pdn = pci_get_pdn(npdev); + struct pnv_ioda_pe *npe, *gpe; + struct pci_dev *gpdev; + uint64_t top; + bool bypass = false; + + if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) + return -ENXIO; + + /* We only do bypass if it's enabled on the linked device */ + npe = &phb->ioda.pe_array[pdn->pe_number]; + gpe = get_gpu_pci_dev_and_pe(npe, &gpdev); + if (!gpe) + return -ENODEV; + + if (gpe->tce_bypass_enabled) { + top = gpe->tce_bypass_base + memblock_end_of_DRAM() - 1; + bypass = (dma_mask >= top); + } + + if (bypass) + dev_info(&npdev->dev, "Using 64-bit DMA iommu bypass\n"); + else + dev_info(&npdev->dev, "Using 32-bit DMA via iommu\n"); + + pnv_npu_dma_set_bypass(npe, bypass); + *npdev->dev.dma_mask = dma_mask; + + return 0; +} diff --git a/arch/powerpc/platforms/powernv/opal-kmsg.c b/arch/powerpc/platforms/powernv/opal-kmsg.c new file mode 100644 index 000000000000..6f1214d4de92 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-kmsg.c @@ -0,0 +1,75 @@ +/* + * kmsg dumper that ensures the OPAL console fully flushes panic messages + * + * Author: Russell Currey <ruscur@russell.cc> + * + * Copyright 2015 IBM Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/kmsg_dump.h> + +#include <asm/opal.h> +#include <asm/opal-api.h> + +/* + * Console output is controlled by OPAL firmware. The kernel regularly calls + * OPAL_POLL_EVENTS, which flushes some console output. In a panic state, + * however, the kernel no longer calls OPAL_POLL_EVENTS and the panic message + * may not be completely printed. This function does not actually dump the + * message, it just ensures that OPAL completely flushes the console buffer. + */ +static void force_opal_console_flush(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason) +{ + int i; + int64_t ret; + + /* + * Outside of a panic context the pollers will continue to run, + * so we don't need to do any special flushing. + */ + if (reason != KMSG_DUMP_PANIC) + return; + + if (opal_check_token(OPAL_CONSOLE_FLUSH)) { + ret = opal_console_flush(0); + + if (ret == OPAL_UNSUPPORTED || ret == OPAL_PARAMETER) + return; + + /* Incrementally flush until there's nothing left */ + while (opal_console_flush(0) != OPAL_SUCCESS); + } else { + /* + * If OPAL_CONSOLE_FLUSH is not implemented in the firmware, + * the console can still be flushed by calling the polling + * function enough times to flush the buffer. We don't know + * how much output still needs to be flushed, but we can be + * generous since the kernel is in panic and doesn't need + * to do much else. + */ + printk(KERN_NOTICE "opal: OPAL_CONSOLE_FLUSH missing.\n"); + for (i = 0; i < 1024; i++) { + opal_poll_events(NULL); + } + } +} + +static struct kmsg_dumper opal_kmsg_dumper = { + .dump = force_opal_console_flush +}; + +void __init opal_kmsg_init(void) +{ + int rc; + + /* Add our dumper to the list */ + rc = kmsg_dump_register(&opal_kmsg_dumper); + if (rc != 0) + pr_err("opal: kmsg_dump_register failed; returned %d\n", rc); +} diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c index 4ece8e40dd54..e315e704cca7 100644 --- a/arch/powerpc/platforms/powernv/opal-prd.c +++ b/arch/powerpc/platforms/powernv/opal-prd.c @@ -434,7 +434,6 @@ static const struct of_device_id opal_prd_match[] = { static struct platform_driver opal_prd_driver = { .driver = { .name = "opal-prd", - .owner = THIS_MODULE, .of_match_table = opal_prd_match, }, .probe = opal_prd_probe, diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c index 37dbee15769f..f8868864f373 100644 --- a/arch/powerpc/platforms/powernv/opal-rtc.c +++ b/arch/powerpc/platforms/powernv/opal-rtc.c @@ -31,8 +31,7 @@ static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm) tm->tm_hour = bcd2bin((h_m_s_ms >> 56) & 0xff); tm->tm_min = bcd2bin((h_m_s_ms >> 48) & 0xff); tm->tm_sec = bcd2bin((h_m_s_ms >> 40) & 0xff); - - GregorianDay(tm); + tm->tm_wday = -1; } unsigned long __init opal_get_boot_time(void) @@ -51,7 +50,7 @@ unsigned long __init opal_get_boot_time(void) rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); if (rc == OPAL_BUSY_EVENT) opal_poll_events(NULL); - else + else if (rc == OPAL_BUSY) mdelay(10); } if (rc != OPAL_SUCCESS) diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index b7a464fef7a7..e45b88a5d7e0 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -301,3 +301,4 @@ OPAL_CALL(opal_flash_erase, OPAL_FLASH_ERASE); OPAL_CALL(opal_prd_msg, OPAL_PRD_MSG); OPAL_CALL(opal_leds_get_ind, OPAL_LEDS_GET_INDICATOR); OPAL_CALL(opal_leds_set_ind, OPAL_LEDS_SET_INDICATOR); +OPAL_CALL(opal_console_flush, OPAL_CONSOLE_FLUSH); diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c index 7634d1c62299..d0ac535cf5d7 100644 --- a/arch/powerpc/platforms/powernv/opal-xscom.c +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -126,7 +126,7 @@ static const struct scom_controller opal_scom_controller = { static int opal_xscom_init(void) { - if (firmware_has_feature(FW_FEATURE_OPALv3)) + if (firmware_has_feature(FW_FEATURE_OPAL)) scom_init(&opal_scom_controller); return 0; } diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 57cffb80bc36..4e0da5af94a1 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -98,16 +98,11 @@ int __init early_init_dt_scan_opal(unsigned long node, pr_debug("OPAL Entry = 0x%llx (sizep=%p runtimesz=%d)\n", opal.size, sizep, runtimesz); - powerpc_firmware_features |= FW_FEATURE_OPAL; if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) { - powerpc_firmware_features |= FW_FEATURE_OPALv2; - powerpc_firmware_features |= FW_FEATURE_OPALv3; - pr_info("OPAL V3 detected !\n"); - } else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) { - powerpc_firmware_features |= FW_FEATURE_OPALv2; - pr_info("OPAL V2 detected !\n"); + powerpc_firmware_features |= FW_FEATURE_OPAL; + pr_info("OPAL detected !\n"); } else { - pr_info("OPAL V1 detected !\n"); + panic("OPAL != V3 detected, no longer supported.\n"); } /* Reinit all cores with the right endian */ @@ -352,17 +347,15 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len) * enough room and be done with it */ spin_lock_irqsave(&opal_write_lock, flags); - if (firmware_has_feature(FW_FEATURE_OPALv2)) { - rc = opal_console_write_buffer_space(vtermno, &olen); - len = be64_to_cpu(olen); - if (rc || len < total_len) { - spin_unlock_irqrestore(&opal_write_lock, flags); - /* Closed -> drop characters */ - if (rc) - return total_len; - opal_poll_events(NULL); - return -EAGAIN; - } + rc = opal_console_write_buffer_space(vtermno, &olen); + len = be64_to_cpu(olen); + if (rc || len < total_len) { + spin_unlock_irqrestore(&opal_write_lock, flags); + /* Closed -> drop characters */ + if (rc) + return total_len; + opal_poll_events(NULL); + return -EAGAIN; } /* We still try to handle partial completions, though they @@ -555,7 +548,7 @@ bool opal_mce_check_early_recovery(struct pt_regs *regs) goto out; if ((regs->nip >= opal.base) && - (regs->nip <= (opal.base + opal.size))) + (regs->nip < (opal.base + opal.size))) recover_addr = find_recovery_address(regs->nip); /* @@ -696,10 +689,7 @@ static int __init opal_init(void) } /* Register OPAL consoles if any ports */ - if (firmware_has_feature(FW_FEATURE_OPALv2)) - consoles = of_find_node_by_path("/ibm,opal/consoles"); - else - consoles = of_node_get(opal_node); + consoles = of_find_node_by_path("/ibm,opal/consoles"); if (consoles) { for_each_child_of_node(consoles, np) { if (strcmp(np->name, "serial")) @@ -758,6 +748,9 @@ static int __init opal_init(void) opal_pdev_init(opal_node, "ibm,opal-flash"); opal_pdev_init(opal_node, "ibm,opal-prd"); + /* Initialise OPAL kmsg dumper for flushing console on panic */ + opal_kmsg_init(); + return 0; } machine_subsys_initcall(powernv, opal_init); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 414fd1a00fda..573ae1994097 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -116,16 +116,6 @@ static int __init iommu_setup(char *str) } early_param("iommu", iommu_setup); -/* - * stdcix is only supposed to be used in hypervisor real mode as per - * the architecture spec - */ -static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr) -{ - __asm__ __volatile__("stdcix %0,0,%1" - : : "r" (val), "r" (paddr) : "memory"); -} - static inline bool pnv_pci_is_mem_pref_64(unsigned long flags) { return ((flags & (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)) == @@ -344,7 +334,7 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb) return; } - if (!firmware_has_feature(FW_FEATURE_OPALv3)) { + if (!firmware_has_feature(FW_FEATURE_OPAL)) { pr_info(" Firmware too old to support M64 window\n"); return; } @@ -357,6 +347,7 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb) } res = &hose->mem_resources[1]; + res->name = dn->full_name; res->start = of_translate_address(dn, r + 2); res->end = res->start + of_read_number(r + 4, 2) - 1; res->flags = (IORESOURCE_MEM | IORESOURCE_MEM_64 | IORESOURCE_PREFETCH); @@ -780,8 +771,12 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) return -ENXIO; } - /* Configure PELTV */ - pnv_ioda_set_peltv(phb, pe, true); + /* + * Configure PELTV. NPUs don't have a PELTV table so skip + * configuration on them. + */ + if (phb->type != PNV_PHB_NPU) + pnv_ioda_set_peltv(phb, pe, true); /* Setup reverse map */ for (rid = pe->rid; rid < rid_end; rid++) @@ -924,7 +919,6 @@ static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset) } #endif /* CONFIG_PCI_IOV */ -#if 0 static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) { struct pci_controller *hose = pci_bus_to_host(dev->bus); @@ -941,11 +935,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) if (pdn->pe_number != IODA_INVALID_PE) return NULL; - /* PE#0 has been pre-set */ - if (dev->bus->number == 0) - pe_num = 0; - else - pe_num = pnv_ioda_alloc_pe(phb); + pe_num = pnv_ioda_alloc_pe(phb); if (pe_num == IODA_INVALID_PE) { pr_warning("%s: Not enough PE# available, disabling device\n", pci_name(dev)); @@ -963,6 +953,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) pci_dev_get(dev); pdn->pcidev = dev; pdn->pe_number = pe_num; + pe->flags = PNV_IODA_PE_DEV; pe->pdev = dev; pe->pbus = NULL; pe->tce32_seg = -1; @@ -993,7 +984,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) return pe; } -#endif /* Useful for SRIOV case */ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) { @@ -1007,6 +997,7 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe) pci_name(dev)); continue; } + pdn->pcidev = dev; pdn->pe_number = pe->pe_number; pe->dma_weight += pnv_ioda_dma_weight(dev); if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate) @@ -1083,6 +1074,77 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all) pnv_ioda_link_pe_by_weight(phb, pe); } +static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev) +{ + int pe_num, found_pe = false, rc; + long rid; + struct pnv_ioda_pe *pe; + struct pci_dev *gpu_pdev; + struct pci_dn *npu_pdn; + struct pci_controller *hose = pci_bus_to_host(npu_pdev->bus); + struct pnv_phb *phb = hose->private_data; + + /* + * Due to a hardware errata PE#0 on the NPU is reserved for + * error handling. This means we only have three PEs remaining + * which need to be assigned to four links, implying some + * links must share PEs. + * + * To achieve this we assign PEs such that NPUs linking the + * same GPU get assigned the same PE. + */ + gpu_pdev = pnv_pci_get_gpu_dev(npu_pdev); + for (pe_num = 0; pe_num < phb->ioda.total_pe; pe_num++) { + pe = &phb->ioda.pe_array[pe_num]; + if (!pe->pdev) + continue; + + if (pnv_pci_get_gpu_dev(pe->pdev) == gpu_pdev) { + /* + * This device has the same peer GPU so should + * be assigned the same PE as the existing + * peer NPU. + */ + dev_info(&npu_pdev->dev, + "Associating to existing PE %d\n", pe_num); + pci_dev_get(npu_pdev); + npu_pdn = pci_get_pdn(npu_pdev); + rid = npu_pdev->bus->number << 8 | npu_pdn->devfn; + npu_pdn->pcidev = npu_pdev; + npu_pdn->pe_number = pe_num; + pe->dma_weight += pnv_ioda_dma_weight(npu_pdev); + phb->ioda.pe_rmap[rid] = pe->pe_number; + + /* Map the PE to this link */ + rc = opal_pci_set_pe(phb->opal_id, pe_num, rid, + OpalPciBusAll, + OPAL_COMPARE_RID_DEVICE_NUMBER, + OPAL_COMPARE_RID_FUNCTION_NUMBER, + OPAL_MAP_PE); + WARN_ON(rc != OPAL_SUCCESS); + found_pe = true; + break; + } + } + + if (!found_pe) + /* + * Could not find an existing PE so allocate a new + * one. + */ + return pnv_ioda_setup_dev_PE(npu_pdev); + else + return pe; +} + +static void pnv_ioda_setup_npu_PEs(struct pci_bus *bus) +{ + struct pci_dev *pdev; + + list_for_each_entry(pdev, &bus->devices, bus_list) + pnv_ioda_setup_npu_PE(pdev); +} + static void pnv_ioda_setup_PEs(struct pci_bus *bus) { struct pci_dev *dev; @@ -1119,7 +1181,17 @@ static void pnv_pci_ioda_setup_PEs(void) if (phb->reserve_m64_pe) phb->reserve_m64_pe(hose->bus, NULL, true); - pnv_ioda_setup_PEs(hose->bus); + /* + * On NPU PHB, we expect separate PEs for individual PCI + * functions. PCI bus dependent PEs are required for the + * remaining types of PHBs. + */ + if (phb->type == PNV_PHB_NPU) { + /* PE#0 is needed for error reporting */ + pnv_ioda_reserve_pe(phb, 0); + pnv_ioda_setup_npu_PEs(hose->bus); + } else + pnv_ioda_setup_PEs(hose->bus); } } @@ -1578,6 +1650,8 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) struct pnv_ioda_pe *pe; uint64_t top; bool bypass = false; + struct pci_dev *linked_npu_dev; + int i; if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) return -ENODEV;; @@ -1596,6 +1670,18 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) set_dma_ops(&pdev->dev, &dma_iommu_ops); } *pdev->dev.dma_mask = dma_mask; + + /* Update peer npu devices */ + if (pe->flags & PNV_IODA_PE_PEER) + for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) { + if (!pe->peers[i]) + continue; + + linked_npu_dev = pe->peers[i]->pdev; + if (dma_get_mask(&linked_npu_dev->dev) != dma_mask) + dma_set_mask(&linked_npu_dev->dev, dma_mask); + } + return 0; } @@ -1740,12 +1826,23 @@ static inline void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_ioda_pe *pe) /* 01xb - invalidate TCEs that match the specified PE# */ unsigned long val = (0x4ull << 60) | (pe->pe_number & 0xFF); struct pnv_phb *phb = pe->phb; + struct pnv_ioda_pe *npe; + int i; if (!phb->ioda.tce_inval_reg) return; mb(); /* Ensure above stores are visible */ __raw_writeq(cpu_to_be64(val), phb->ioda.tce_inval_reg); + + if (pe->flags & PNV_IODA_PE_PEER) + for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) { + npe = pe->peers[i]; + if (!npe || npe->phb->type != PNV_PHB_NPU) + continue; + + pnv_npu_tce_invalidate_entire(npe); + } } static void pnv_pci_ioda2_do_tce_invalidate(unsigned pe_number, bool rm, @@ -1780,15 +1877,28 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl, struct iommu_table_group_link *tgl; list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) { + struct pnv_ioda_pe *npe; struct pnv_ioda_pe *pe = container_of(tgl->table_group, struct pnv_ioda_pe, table_group); __be64 __iomem *invalidate = rm ? (__be64 __iomem *)pe->phb->ioda.tce_inval_reg_phys : pe->phb->ioda.tce_inval_reg; + int i; pnv_pci_ioda2_do_tce_invalidate(pe->pe_number, rm, invalidate, tbl->it_page_shift, index, npages); + + if (pe->flags & PNV_IODA_PE_PEER) + /* Invalidate PEs using the same TCE table */ + for (i = 0; i < PNV_IODA_MAX_PEER_PES; i++) { + npe = pe->peers[i]; + if (!npe || npe->phb->type != PNV_PHB_NPU) + continue; + + pnv_npu_tce_invalidate(npe, tbl, index, + npages, rm); + } } } @@ -2436,10 +2546,17 @@ static void pnv_ioda_setup_dma(struct pnv_phb *phb) pe_info(pe, "DMA weight %d, assigned %d DMA32 segments\n", pe->dma_weight, segs); pnv_pci_ioda_setup_dma_pe(phb, pe, base, segs); - } else { + } else if (phb->type == PNV_PHB_IODA2) { pe_info(pe, "Assign DMA32 space\n"); segs = 0; pnv_pci_ioda2_setup_dma_pe(phb, pe); + } else if (phb->type == PNV_PHB_NPU) { + /* + * We initialise the DMA space for an NPU PHB + * after setup of the PHB is complete as we + * point the NPU TVT to the the same location + * as the PHB3 TVT. + */ } remaining -= segs; @@ -2881,6 +2998,11 @@ static void pnv_pci_ioda_setup_seg(void) list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { phb = hose->private_data; + + /* NPU PHB does not support IO or MMIO segmentation */ + if (phb->type == PNV_PHB_NPU) + continue; + list_for_each_entry(pe, &phb->ioda.pe_list, list) { pnv_ioda_setup_pe_seg(hose, pe); } @@ -2920,6 +3042,27 @@ static void pnv_pci_ioda_create_dbgfs(void) #endif /* CONFIG_DEBUG_FS */ } +static void pnv_npu_ioda_fixup(void) +{ + bool enable_bypass; + struct pci_controller *hose, *tmp; + struct pnv_phb *phb; + struct pnv_ioda_pe *pe; + + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { + phb = hose->private_data; + if (phb->type != PNV_PHB_NPU) + continue; + + list_for_each_entry(pe, &phb->ioda.pe_dma_list, dma_link) { + enable_bypass = dma_get_mask(&pe->pdev->dev) == + DMA_BIT_MASK(64); + pnv_npu_init_dma_pe(pe); + pnv_npu_dma_set_bypass(pe, enable_bypass); + } + } +} + static void pnv_pci_ioda_fixup(void) { pnv_pci_ioda_setup_PEs(); @@ -2932,6 +3075,9 @@ static void pnv_pci_ioda_fixup(void) eeh_init(); eeh_addr_cache_build(); #endif + + /* Link NPU IODA tables to their PCI devices. */ + pnv_npu_ioda_fixup(); } /* @@ -3046,6 +3192,19 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .shutdown = pnv_pci_ioda_shutdown, }; +static const struct pci_controller_ops pnv_npu_ioda_controller_ops = { + .dma_dev_setup = pnv_pci_dma_dev_setup, +#ifdef CONFIG_PCI_MSI + .setup_msi_irqs = pnv_setup_msi_irqs, + .teardown_msi_irqs = pnv_teardown_msi_irqs, +#endif + .enable_device_hook = pnv_pci_enable_device_hook, + .window_alignment = pnv_pci_window_alignment, + .reset_secondary_bus = pnv_pci_reset_secondary_bus, + .dma_set_mask = pnv_npu_dma_set_mask, + .shutdown = pnv_pci_ioda_shutdown, +}; + static void __init pnv_pci_init_ioda_phb(struct device_node *np, u64 hub_id, int ioda_type) { @@ -3101,6 +3260,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, phb->model = PNV_PHB_MODEL_P7IOC; else if (of_device_is_compatible(np, "ibm,power8-pciex")) phb->model = PNV_PHB_MODEL_PHB3; + else if (of_device_is_compatible(np, "ibm,power8-npu-pciex")) + phb->model = PNV_PHB_MODEL_NPU; else phb->model = PNV_PHB_MODEL_UNKNOWN; @@ -3201,7 +3362,11 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, * the child P2P bridges) can form individual PE. */ ppc_md.pcibios_fixup = pnv_pci_ioda_fixup; - hose->controller_ops = pnv_pci_ioda_controller_ops; + + if (phb->type == PNV_PHB_NPU) + hose->controller_ops = pnv_npu_ioda_controller_ops; + else + hose->controller_ops = pnv_pci_ioda_controller_ops; #ifdef CONFIG_PCI_IOV ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources; @@ -3236,6 +3401,11 @@ void __init pnv_pci_init_ioda2_phb(struct device_node *np) pnv_pci_init_ioda_phb(np, 0, PNV_PHB_IODA2); } +void __init pnv_pci_init_npu_phb(struct device_node *np) +{ + pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU); +} + void __init pnv_pci_init_ioda_hub(struct device_node *np) { struct device_node *phbn; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index f2dd77234240..2f55c86df703 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -1,8 +1,6 @@ /* * Support PCI/PCIe on PowerNV platforms * - * Currently supports only P5IOC2 - * * Copyright 2011 Benjamin Herrenschmidt, IBM Corp. * * This program is free software; you can redistribute it and/or @@ -807,6 +805,10 @@ void __init pnv_pci_init(void) for_each_compatible_node(np, NULL, "ibm,ioda2-phb") pnv_pci_init_ioda2_phb(np); + /* Look for NPU PHBs */ + for_each_compatible_node(np, NULL, "ibm,ioda2-npu-phb") + pnv_pci_init_npu_phb(np); + /* Setup the linkage between OF nodes and PHBs */ pci_devs_phb_init(); diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index c8ff50e90766..7f56313e8d72 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -7,6 +7,7 @@ enum pnv_phb_type { PNV_PHB_P5IOC2 = 0, PNV_PHB_IODA1 = 1, PNV_PHB_IODA2 = 2, + PNV_PHB_NPU = 3, }; /* Precise PHB model for error management */ @@ -15,6 +16,7 @@ enum pnv_phb_model { PNV_PHB_MODEL_P5IOC2, PNV_PHB_MODEL_P7IOC, PNV_PHB_MODEL_PHB3, + PNV_PHB_MODEL_NPU, }; #define PNV_PCI_DIAG_BUF_SIZE 8192 @@ -24,6 +26,7 @@ enum pnv_phb_model { #define PNV_IODA_PE_MASTER (1 << 3) /* Master PE in compound case */ #define PNV_IODA_PE_SLAVE (1 << 4) /* Slave PE in compound case */ #define PNV_IODA_PE_VF (1 << 5) /* PE for one VF */ +#define PNV_IODA_PE_PEER (1 << 6) /* PE has peers */ /* Data associated with a PE, including IOMMU tracking etc.. */ struct pnv_phb; @@ -31,6 +34,9 @@ struct pnv_ioda_pe { unsigned long flags; struct pnv_phb *phb; +#define PNV_IODA_MAX_PEER_PES 8 + struct pnv_ioda_pe *peers[PNV_IODA_MAX_PEER_PES]; + /* A PE can be associated with a single device or an * entire bus (& children). In the former case, pdev * is populated, in the later case, pbus is. @@ -229,6 +235,7 @@ extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, extern void pnv_pci_init_p5ioc2_hub(struct device_node *np); extern void pnv_pci_init_ioda_hub(struct device_node *np); extern void pnv_pci_init_ioda2_phb(struct device_node *np); +extern void pnv_pci_init_npu_phb(struct device_node *np); extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl, __be64 *startp, __be64 *endp, bool rm); extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); @@ -238,4 +245,16 @@ extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev); extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); +/* Nvlink functions */ +extern void pnv_npu_tce_invalidate_entire(struct pnv_ioda_pe *npe); +extern void pnv_npu_tce_invalidate(struct pnv_ioda_pe *npe, + struct iommu_table *tbl, + unsigned long index, + unsigned long npages, + bool rm); +extern void pnv_npu_init_dma_pe(struct pnv_ioda_pe *npe); +extern void pnv_npu_setup_dma_pe(struct pnv_ioda_pe *npe); +extern int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe, bool enabled); +extern int pnv_npu_dma_set_mask(struct pci_dev *npdev, u64 dma_mask); + #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index a9a8fa37a555..1acb0c72d923 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -90,12 +90,8 @@ static void pnv_show_cpuinfo(struct seq_file *m) if (root) model = of_get_property(root, "model", NULL); seq_printf(m, "machine\t\t: PowerNV %s\n", model); - if (firmware_has_feature(FW_FEATURE_OPALv3)) - seq_printf(m, "firmware\t: OPAL v3\n"); - else if (firmware_has_feature(FW_FEATURE_OPALv2)) - seq_printf(m, "firmware\t: OPAL v2\n"); - else if (firmware_has_feature(FW_FEATURE_OPAL)) - seq_printf(m, "firmware\t: OPAL v1\n"); + if (firmware_has_feature(FW_FEATURE_OPAL)) + seq_printf(m, "firmware\t: OPAL\n"); else seq_printf(m, "firmware\t: BML\n"); of_node_put(root); @@ -224,9 +220,9 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) { xics_kexec_teardown_cpu(secondary); - /* On OPAL v3, we return all CPUs to firmware */ + /* On OPAL, we return all CPUs to firmware */ - if (!firmware_has_feature(FW_FEATURE_OPALv3)) + if (!firmware_has_feature(FW_FEATURE_OPAL)) return; if (secondary) { diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index ca264833ee64..ad7b1a3dbed0 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -61,14 +61,15 @@ static int pnv_smp_kick_cpu(int nr) unsigned long start_here = __pa(ppc_function_entry(generic_secondary_smp_init)); long rc; + uint8_t status; BUG_ON(nr < 0 || nr >= NR_CPUS); /* - * If we already started or OPALv2 is not supported, we just + * If we already started or OPAL is not supported, we just * kick the CPU via the PACA */ - if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPALv2)) + if (paca[nr].cpu_start || !firmware_has_feature(FW_FEATURE_OPAL)) goto kick; /* @@ -77,55 +78,42 @@ static int pnv_smp_kick_cpu(int nr) * first time. OPAL v3 allows us to query OPAL to know if it * has the CPUs, so we do that */ - if (firmware_has_feature(FW_FEATURE_OPALv3)) { - uint8_t status; - - rc = opal_query_cpu_status(pcpu, &status); - if (rc != OPAL_SUCCESS) { - pr_warn("OPAL Error %ld querying CPU %d state\n", - rc, nr); - return -ENODEV; - } + rc = opal_query_cpu_status(pcpu, &status); + if (rc != OPAL_SUCCESS) { + pr_warn("OPAL Error %ld querying CPU %d state\n", rc, nr); + return -ENODEV; + } - /* - * Already started, just kick it, probably coming from - * kexec and spinning - */ - if (status == OPAL_THREAD_STARTED) - goto kick; + /* + * Already started, just kick it, probably coming from + * kexec and spinning + */ + if (status == OPAL_THREAD_STARTED) + goto kick; - /* - * Available/inactive, let's kick it - */ - if (status == OPAL_THREAD_INACTIVE) { - pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", - nr, pcpu); - rc = opal_start_cpu(pcpu, start_here); - if (rc != OPAL_SUCCESS) { - pr_warn("OPAL Error %ld starting CPU %d\n", - rc, nr); - return -ENODEV; - } - } else { - /* - * An unavailable CPU (or any other unknown status) - * shouldn't be started. It should also - * not be in the possible map but currently it can - * happen - */ - pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable" - " (status %d)...\n", nr, pcpu, status); + /* + * Available/inactive, let's kick it + */ + if (status == OPAL_THREAD_INACTIVE) { + pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu); + rc = opal_start_cpu(pcpu, start_here); + if (rc != OPAL_SUCCESS) { + pr_warn("OPAL Error %ld starting CPU %d\n", rc, nr); return -ENODEV; } } else { /* - * On OPAL v2, we just kick it and hope for the best, - * we must not test the error from opal_start_cpu() or - * we would fail to get CPUs from kexec. + * An unavailable CPU (or any other unknown status) + * shouldn't be started. It should also + * not be in the possible map but currently it can + * happen */ - opal_start_cpu(pcpu, start_here); + pr_devel("OPAL: CPU %d (HW 0x%x) is unavailable" + " (status %d)...\n", nr, pcpu, status); + return -ENODEV; } - kick: + +kick: return smp_generic_kick_cpu(nr); } diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index f244dcb4f2cf..2b93ae8d557a 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -20,7 +20,6 @@ #include <linux/of.h> #include "of_helpers.h" -#include "offline_states.h" #include "pseries.h" #include <asm/prom.h> @@ -338,185 +337,6 @@ int dlpar_release_drc(u32 drc_index) return 0; } -#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE - -static int dlpar_online_cpu(struct device_node *dn) -{ - int rc = 0; - unsigned int cpu; - int len, nthreads, i; - const __be32 *intserv; - u32 thread; - - intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); - if (!intserv) - return -EINVAL; - - nthreads = len / sizeof(u32); - - cpu_maps_update_begin(); - for (i = 0; i < nthreads; i++) { - thread = be32_to_cpu(intserv[i]); - for_each_present_cpu(cpu) { - if (get_hard_smp_processor_id(cpu) != thread) - continue; - BUG_ON(get_cpu_current_state(cpu) - != CPU_STATE_OFFLINE); - cpu_maps_update_done(); - rc = device_online(get_cpu_device(cpu)); - if (rc) - goto out; - cpu_maps_update_begin(); - - break; - } - if (cpu == num_possible_cpus()) - printk(KERN_WARNING "Could not find cpu to online " - "with physical id 0x%x\n", thread); - } - cpu_maps_update_done(); - -out: - return rc; - -} - -static ssize_t dlpar_cpu_probe(const char *buf, size_t count) -{ - struct device_node *dn, *parent; - u32 drc_index; - int rc; - - rc = kstrtou32(buf, 0, &drc_index); - if (rc) - return -EINVAL; - - rc = dlpar_acquire_drc(drc_index); - if (rc) - return -EINVAL; - - parent = of_find_node_by_path("/cpus"); - if (!parent) - return -ENODEV; - - dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent); - of_node_put(parent); - if (!dn) { - dlpar_release_drc(drc_index); - return -EINVAL; - } - - rc = dlpar_attach_node(dn); - if (rc) { - dlpar_release_drc(drc_index); - dlpar_free_cc_nodes(dn); - return rc; - } - - rc = dlpar_online_cpu(dn); - if (rc) - return rc; - - return count; -} - -static int dlpar_offline_cpu(struct device_node *dn) -{ - int rc = 0; - unsigned int cpu; - int len, nthreads, i; - const __be32 *intserv; - u32 thread; - - intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); - if (!intserv) - return -EINVAL; - - nthreads = len / sizeof(u32); - - cpu_maps_update_begin(); - for (i = 0; i < nthreads; i++) { - thread = be32_to_cpu(intserv[i]); - for_each_present_cpu(cpu) { - if (get_hard_smp_processor_id(cpu) != thread) - continue; - - if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE) - break; - - if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { - set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); - cpu_maps_update_done(); - rc = device_offline(get_cpu_device(cpu)); - if (rc) - goto out; - cpu_maps_update_begin(); - break; - - } - - /* - * The cpu is in CPU_STATE_INACTIVE. - * Upgrade it's state to CPU_STATE_OFFLINE. - */ - set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); - BUG_ON(plpar_hcall_norets(H_PROD, thread) - != H_SUCCESS); - __cpu_die(cpu); - break; - } - if (cpu == num_possible_cpus()) - printk(KERN_WARNING "Could not find cpu to offline " - "with physical id 0x%x\n", thread); - } - cpu_maps_update_done(); - -out: - return rc; - -} - -static ssize_t dlpar_cpu_release(const char *buf, size_t count) -{ - struct device_node *dn; - u32 drc_index; - int rc; - - dn = of_find_node_by_path(buf); - if (!dn) - return -EINVAL; - - rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index); - if (rc) { - of_node_put(dn); - return -EINVAL; - } - - rc = dlpar_offline_cpu(dn); - if (rc) { - of_node_put(dn); - return -EINVAL; - } - - rc = dlpar_release_drc(drc_index); - if (rc) { - of_node_put(dn); - return rc; - } - - rc = dlpar_detach_node(dn); - if (rc) { - dlpar_acquire_drc(drc_index); - return rc; - } - - of_node_put(dn); - - return count; -} - -#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ - static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) { int rc; @@ -536,6 +356,9 @@ static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) case PSERIES_HP_ELOG_RESOURCE_MEM: rc = dlpar_memory(hp_elog); break; + case PSERIES_HP_ELOG_RESOURCE_CPU: + rc = dlpar_cpu(hp_elog); + break; default: pr_warn_ratelimited("Invalid resource (%d) specified\n", hp_elog->resource); @@ -565,6 +388,9 @@ static ssize_t dlpar_store(struct class *class, struct class_attribute *attr, if (!strncmp(arg, "memory", 6)) { hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM; arg += strlen("memory "); + } else if (!strncmp(arg, "cpu", 3)) { + hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_CPU; + arg += strlen("cpu "); } else { pr_err("Invalid resource specified: \"%s\"\n", buf); rc = -EINVAL; @@ -624,16 +450,7 @@ static CLASS_ATTR(dlpar, S_IWUSR, NULL, dlpar_store); static int __init pseries_dlpar_init(void) { - int rc; - -#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE - ppc_md.cpu_probe = dlpar_cpu_probe; - ppc_md.cpu_release = dlpar_cpu_release; -#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ - - rc = sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr); - - return rc; + return sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr); } machine_device_initcall(pseries, pseries_dlpar_init); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 62475440fd45..32274f72fe3f 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -18,12 +18,15 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "pseries-hotplug-cpu: " fmt + #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/sched.h> /* for idle_task_exit */ #include <linux/cpu.h> #include <linux/of.h> +#include <linux/slab.h> #include <asm/prom.h> #include <asm/rtas.h> #include <asm/firmware.h> @@ -32,6 +35,7 @@ #include <asm/xics.h> #include <asm/plpar_wrappers.h> +#include "pseries.h" #include "offline_states.h" /* This version can't take the spinlock, because it never returns */ @@ -88,13 +92,7 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - static struct rtas_args args = { - .nargs = 0, - .nret = cpu_to_be32(1), - .rets = &args.args[0], - }; - - args.token = cpu_to_be32(rtas_stop_self_token); + static struct rtas_args args; local_irq_disable(); @@ -102,7 +100,8 @@ static void rtas_stop_self(void) printk("cpu %u (hwid %u) Ready to die...\n", smp_processor_id(), hard_smp_processor_id()); - enter_rtas(__pa(&args)); + + rtas_call_unlocked(&args, rtas_stop_self_token, 0, 1, NULL); panic("Alas, I survived.\n"); } @@ -339,6 +338,536 @@ static void pseries_remove_processor(struct device_node *np) cpu_maps_update_done(); } +static int dlpar_online_cpu(struct device_node *dn) +{ + int rc = 0; + unsigned int cpu; + int len, nthreads, i; + const __be32 *intserv; + u32 thread; + + intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); + if (!intserv) + return -EINVAL; + + nthreads = len / sizeof(u32); + + cpu_maps_update_begin(); + for (i = 0; i < nthreads; i++) { + thread = be32_to_cpu(intserv[i]); + for_each_present_cpu(cpu) { + if (get_hard_smp_processor_id(cpu) != thread) + continue; + BUG_ON(get_cpu_current_state(cpu) + != CPU_STATE_OFFLINE); + cpu_maps_update_done(); + rc = device_online(get_cpu_device(cpu)); + if (rc) + goto out; + cpu_maps_update_begin(); + + break; + } + if (cpu == num_possible_cpus()) + printk(KERN_WARNING "Could not find cpu to online " + "with physical id 0x%x\n", thread); + } + cpu_maps_update_done(); + +out: + return rc; + +} + +static bool dlpar_cpu_exists(struct device_node *parent, u32 drc_index) +{ + struct device_node *child = NULL; + u32 my_drc_index; + bool found; + int rc; + + /* Assume cpu doesn't exist */ + found = false; + + for_each_child_of_node(parent, child) { + rc = of_property_read_u32(child, "ibm,my-drc-index", + &my_drc_index); + if (rc) + continue; + + if (my_drc_index == drc_index) { + of_node_put(child); + found = true; + break; + } + } + + return found; +} + +static bool valid_cpu_drc_index(struct device_node *parent, u32 drc_index) +{ + bool found = false; + int rc, index; + + index = 0; + while (!found) { + u32 drc; + + rc = of_property_read_u32_index(parent, "ibm,drc-indexes", + index++, &drc); + if (rc) + break; + + if (drc == drc_index) + found = true; + } + + return found; +} + +static ssize_t dlpar_cpu_add(u32 drc_index) +{ + struct device_node *dn, *parent; + int rc, saved_rc; + + pr_debug("Attempting to add CPU, drc index: %x\n", drc_index); + + parent = of_find_node_by_path("/cpus"); + if (!parent) { + pr_warn("Failed to find CPU root node \"/cpus\"\n"); + return -ENODEV; + } + + if (dlpar_cpu_exists(parent, drc_index)) { + of_node_put(parent); + pr_warn("CPU with drc index %x already exists\n", drc_index); + return -EINVAL; + } + + if (!valid_cpu_drc_index(parent, drc_index)) { + of_node_put(parent); + pr_warn("Cannot find CPU (drc index %x) to add.\n", drc_index); + return -EINVAL; + } + + rc = dlpar_acquire_drc(drc_index); + if (rc) { + pr_warn("Failed to acquire DRC, rc: %d, drc index: %x\n", + rc, drc_index); + of_node_put(parent); + return -EINVAL; + } + + dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent); + of_node_put(parent); + if (!dn) { + pr_warn("Failed call to configure-connector, drc index: %x\n", + drc_index); + dlpar_release_drc(drc_index); + return -EINVAL; + } + + rc = dlpar_attach_node(dn); + if (rc) { + saved_rc = rc; + pr_warn("Failed to attach node %s, rc: %d, drc index: %x\n", + dn->name, rc, drc_index); + + rc = dlpar_release_drc(drc_index); + if (!rc) + dlpar_free_cc_nodes(dn); + + return saved_rc; + } + + rc = dlpar_online_cpu(dn); + if (rc) { + saved_rc = rc; + pr_warn("Failed to online cpu %s, rc: %d, drc index: %x\n", + dn->name, rc, drc_index); + + rc = dlpar_detach_node(dn); + if (!rc) + dlpar_release_drc(drc_index); + + return saved_rc; + } + + pr_debug("Successfully added CPU %s, drc index: %x\n", dn->name, + drc_index); + return rc; +} + +static int dlpar_offline_cpu(struct device_node *dn) +{ + int rc = 0; + unsigned int cpu; + int len, nthreads, i; + const __be32 *intserv; + u32 thread; + + intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); + if (!intserv) + return -EINVAL; + + nthreads = len / sizeof(u32); + + cpu_maps_update_begin(); + for (i = 0; i < nthreads; i++) { + thread = be32_to_cpu(intserv[i]); + for_each_present_cpu(cpu) { + if (get_hard_smp_processor_id(cpu) != thread) + continue; + + if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE) + break; + + if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { + set_preferred_offline_state(cpu, + CPU_STATE_OFFLINE); + cpu_maps_update_done(); + rc = device_offline(get_cpu_device(cpu)); + if (rc) + goto out; + cpu_maps_update_begin(); + break; + + } + + /* + * The cpu is in CPU_STATE_INACTIVE. + * Upgrade it's state to CPU_STATE_OFFLINE. + */ + set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); + BUG_ON(plpar_hcall_norets(H_PROD, thread) + != H_SUCCESS); + __cpu_die(cpu); + break; + } + if (cpu == num_possible_cpus()) + printk(KERN_WARNING "Could not find cpu to offline with physical id 0x%x\n", thread); + } + cpu_maps_update_done(); + +out: + return rc; + +} + +static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index) +{ + int rc; + + pr_debug("Attemping to remove CPU %s, drc index: %x\n", + dn->name, drc_index); + + rc = dlpar_offline_cpu(dn); + if (rc) { + pr_warn("Failed to offline CPU %s, rc: %d\n", dn->name, rc); + return -EINVAL; + } + + rc = dlpar_release_drc(drc_index); + if (rc) { + pr_warn("Failed to release drc (%x) for CPU %s, rc: %d\n", + drc_index, dn->name, rc); + dlpar_online_cpu(dn); + return rc; + } + + rc = dlpar_detach_node(dn); + if (rc) { + int saved_rc = rc; + + pr_warn("Failed to detach CPU %s, rc: %d", dn->name, rc); + + rc = dlpar_acquire_drc(drc_index); + if (!rc) + dlpar_online_cpu(dn); + + return saved_rc; + } + + pr_debug("Successfully removed CPU, drc index: %x\n", drc_index); + return 0; +} + +static struct device_node *cpu_drc_index_to_dn(u32 drc_index) +{ + struct device_node *dn; + u32 my_index; + int rc; + + for_each_node_by_type(dn, "cpu") { + rc = of_property_read_u32(dn, "ibm,my-drc-index", &my_index); + if (rc) + continue; + + if (my_index == drc_index) + break; + } + + return dn; +} + +static int dlpar_cpu_remove_by_index(u32 drc_index) +{ + struct device_node *dn; + int rc; + + dn = cpu_drc_index_to_dn(drc_index); + if (!dn) { + pr_warn("Cannot find CPU (drc index %x) to remove\n", + drc_index); + return -ENODEV; + } + + rc = dlpar_cpu_remove(dn, drc_index); + of_node_put(dn); + return rc; +} + +static int find_dlpar_cpus_to_remove(u32 *cpu_drcs, int cpus_to_remove) +{ + struct device_node *dn; + int cpus_found = 0; + int rc; + + /* We want to find cpus_to_remove + 1 CPUs to ensure we do not + * remove the last CPU. + */ + for_each_node_by_type(dn, "cpu") { + cpus_found++; + + if (cpus_found > cpus_to_remove) { + of_node_put(dn); + break; + } + + /* Note that cpus_found is always 1 ahead of the index + * into the cpu_drcs array, so we use cpus_found - 1 + */ + rc = of_property_read_u32(dn, "ibm,my-drc-index", + &cpu_drcs[cpus_found - 1]); + if (rc) { + pr_warn("Error occurred getting drc-index for %s\n", + dn->name); + of_node_put(dn); + return -1; + } + } + + if (cpus_found < cpus_to_remove) { + pr_warn("Failed to find enough CPUs (%d of %d) to remove\n", + cpus_found, cpus_to_remove); + } else if (cpus_found == cpus_to_remove) { + pr_warn("Cannot remove all CPUs\n"); + } + + return cpus_found; +} + +static int dlpar_cpu_remove_by_count(u32 cpus_to_remove) +{ + u32 *cpu_drcs; + int cpus_found; + int cpus_removed = 0; + int i, rc; + + pr_debug("Attempting to hot-remove %d CPUs\n", cpus_to_remove); + + cpu_drcs = kcalloc(cpus_to_remove, sizeof(*cpu_drcs), GFP_KERNEL); + if (!cpu_drcs) + return -EINVAL; + + cpus_found = find_dlpar_cpus_to_remove(cpu_drcs, cpus_to_remove); + if (cpus_found <= cpus_to_remove) { + kfree(cpu_drcs); + return -EINVAL; + } + + for (i = 0; i < cpus_to_remove; i++) { + rc = dlpar_cpu_remove_by_index(cpu_drcs[i]); + if (rc) + break; + + cpus_removed++; + } + + if (cpus_removed != cpus_to_remove) { + pr_warn("CPU hot-remove failed, adding back removed CPUs\n"); + + for (i = 0; i < cpus_removed; i++) + dlpar_cpu_add(cpu_drcs[i]); + + rc = -EINVAL; + } else { + rc = 0; + } + + kfree(cpu_drcs); + return rc; +} + +static int find_dlpar_cpus_to_add(u32 *cpu_drcs, u32 cpus_to_add) +{ + struct device_node *parent; + int cpus_found = 0; + int index, rc; + + parent = of_find_node_by_path("/cpus"); + if (!parent) { + pr_warn("Could not find CPU root node in device tree\n"); + kfree(cpu_drcs); + return -1; + } + + /* Search the ibm,drc-indexes array for possible CPU drcs to + * add. Note that the format of the ibm,drc-indexes array is + * the number of entries in the array followed by the array + * of drc values so we start looking at index = 1. + */ + index = 1; + while (cpus_found < cpus_to_add) { + u32 drc; + + rc = of_property_read_u32_index(parent, "ibm,drc-indexes", + index++, &drc); + if (rc) + break; + + if (dlpar_cpu_exists(parent, drc)) + continue; + + cpu_drcs[cpus_found++] = drc; + } + + of_node_put(parent); + return cpus_found; +} + +static int dlpar_cpu_add_by_count(u32 cpus_to_add) +{ + u32 *cpu_drcs; + int cpus_added = 0; + int cpus_found; + int i, rc; + + pr_debug("Attempting to hot-add %d CPUs\n", cpus_to_add); + + cpu_drcs = kcalloc(cpus_to_add, sizeof(*cpu_drcs), GFP_KERNEL); + if (!cpu_drcs) + return -EINVAL; + + cpus_found = find_dlpar_cpus_to_add(cpu_drcs, cpus_to_add); + if (cpus_found < cpus_to_add) { + pr_warn("Failed to find enough CPUs (%d of %d) to add\n", + cpus_found, cpus_to_add); + kfree(cpu_drcs); + return -EINVAL; + } + + for (i = 0; i < cpus_to_add; i++) { + rc = dlpar_cpu_add(cpu_drcs[i]); + if (rc) + break; + + cpus_added++; + } + + if (cpus_added < cpus_to_add) { + pr_warn("CPU hot-add failed, removing any added CPUs\n"); + + for (i = 0; i < cpus_added; i++) + dlpar_cpu_remove_by_index(cpu_drcs[i]); + + rc = -EINVAL; + } else { + rc = 0; + } + + kfree(cpu_drcs); + return rc; +} + +int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) +{ + u32 count, drc_index; + int rc; + + count = hp_elog->_drc_u.drc_count; + drc_index = hp_elog->_drc_u.drc_index; + + lock_device_hotplug(); + + switch (hp_elog->action) { + case PSERIES_HP_ELOG_ACTION_REMOVE: + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) + rc = dlpar_cpu_remove_by_count(count); + else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) + rc = dlpar_cpu_remove_by_index(drc_index); + else + rc = -EINVAL; + break; + case PSERIES_HP_ELOG_ACTION_ADD: + if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_COUNT) + rc = dlpar_cpu_add_by_count(count); + else if (hp_elog->id_type == PSERIES_HP_ELOG_ID_DRC_INDEX) + rc = dlpar_cpu_add(drc_index); + else + rc = -EINVAL; + break; + default: + pr_err("Invalid action (%d) specified\n", hp_elog->action); + rc = -EINVAL; + break; + } + + unlock_device_hotplug(); + return rc; +} + +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE + +static ssize_t dlpar_cpu_probe(const char *buf, size_t count) +{ + u32 drc_index; + int rc; + + rc = kstrtou32(buf, 0, &drc_index); + if (rc) + return -EINVAL; + + rc = dlpar_cpu_add(drc_index); + + return rc ? rc : count; +} + +static ssize_t dlpar_cpu_release(const char *buf, size_t count) +{ + struct device_node *dn; + u32 drc_index; + int rc; + + dn = of_find_node_by_path(buf); + if (!dn) + return -EINVAL; + + rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index); + if (rc) { + of_node_put(dn); + return -EINVAL; + } + + rc = dlpar_cpu_remove(dn, drc_index); + of_node_put(dn); + + return rc ? rc : count; +} + +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ + static int pseries_smp_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -385,6 +914,11 @@ static int __init pseries_cpu_hotplug_init(void) int cpu; int qcss_tok; +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE + ppc_md.cpu_probe = dlpar_cpu_probe; + ppc_md.cpu_release = dlpar_cpu_release; +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ + for_each_node_by_name(np, "interrupt-controller") { typep = of_get_property(np, "compatible", NULL); if (strstr(typep, "open-pic")) { diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index b7a67e3d2201..477290ad855e 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -315,48 +315,48 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot, return 0; } -static unsigned long pSeries_lpar_hpte_getword0(unsigned long slot) +static long __pSeries_lpar_hpte_find(unsigned long want_v, unsigned long hpte_group) { - unsigned long dword0; - unsigned long lpar_rc; - unsigned long dummy_word1; - unsigned long flags; + long lpar_rc; + unsigned long i, j; + struct { + unsigned long pteh; + unsigned long ptel; + } ptes[4]; - /* Read 1 pte at a time */ - /* Do not need RPN to logical page translation */ - /* No cross CEC PFT access */ - flags = 0; + for (i = 0; i < HPTES_PER_GROUP; i += 4, hpte_group += 4) { - lpar_rc = plpar_pte_read(flags, slot, &dword0, &dummy_word1); + lpar_rc = plpar_pte_read_4(0, hpte_group, (void *)ptes); + if (lpar_rc != H_SUCCESS) + continue; - BUG_ON(lpar_rc != H_SUCCESS); + for (j = 0; j < 4; j++) { + if (HPTE_V_COMPARE(ptes[j].pteh, want_v) && + (ptes[j].pteh & HPTE_V_VALID)) + return i + j; + } + } - return dword0; + return -1; } static long pSeries_lpar_hpte_find(unsigned long vpn, int psize, int ssize) { - unsigned long hash; - unsigned long i; long slot; - unsigned long want_v, hpte_v; + unsigned long hash; + unsigned long want_v; + unsigned long hpte_group; hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize); want_v = hpte_encode_avpn(vpn, psize, ssize); /* Bolted entries are always in the primary group */ - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; - for (i = 0; i < HPTES_PER_GROUP; i++) { - hpte_v = pSeries_lpar_hpte_getword0(slot); - - if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) - /* HPTE matches */ - return slot; - ++slot; - } - - return -1; -} + hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot = __pSeries_lpar_hpte_find(want_v, hpte_group); + if (slot < 0) + return -1; + return hpte_group + slot; +} static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, @@ -396,6 +396,7 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, BUG_ON(lpar_rc != H_SUCCESS); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need * to make sure that we avoid bouncing the hypervisor tlbie lock. @@ -494,6 +495,15 @@ static void pSeries_lpar_hugepage_invalidate(unsigned long vsid, __pSeries_lpar_hugepage_invalidate(slot_array, vpn_array, index, psize, ssize); } +#else +static void pSeries_lpar_hugepage_invalidate(unsigned long vsid, + unsigned long addr, + unsigned char *hpte_slot_array, + int psize, int ssize, int local) +{ + WARN(1, "%s called without THP support\n", __func__); +} +#endif static void pSeries_lpar_hpte_removebolted(unsigned long ea, int psize, int ssize) diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 8411c27293e4..7aa83f00ac62 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -73,6 +73,15 @@ static inline int dlpar_memory(struct pseries_hp_errorlog *hp_elog) } #endif +#ifdef CONFIG_HOTPLUG_CPU +int dlpar_cpu(struct pseries_hp_errorlog *hp_elog); +#else +static inline int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) +{ + return -EOPNOTSUPP; +} +#endif + /* PCI root bridge prepare function override for pseries */ struct pci_host_bridge; int pseries_root_bridge_prepare(struct pci_host_bridge *bridge); diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 3b6647e574b6..9a3e27b863ce 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -40,6 +40,9 @@ static int ras_check_exception_token; #define EPOW_SENSOR_TOKEN 9 #define EPOW_SENSOR_INDEX 0 +/* EPOW events counter variable */ +static int num_epow_events; + static irqreturn_t ras_epow_interrupt(int irq, void *dev_id); static irqreturn_t ras_error_interrupt(int irq, void *dev_id); @@ -82,32 +85,30 @@ static void handle_system_shutdown(char event_modifier) { switch (event_modifier) { case EPOW_SHUTDOWN_NORMAL: - pr_emerg("Firmware initiated power off"); + pr_emerg("Power off requested\n"); orderly_poweroff(true); break; case EPOW_SHUTDOWN_ON_UPS: - pr_emerg("Loss of power reported by firmware, system is " - "running on UPS/battery"); - pr_emerg("Check RTAS error log for details"); + pr_emerg("Loss of system power detected. System is running on" + " UPS/battery. Check RTAS error log for details\n"); orderly_poweroff(true); break; case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS: - pr_emerg("Loss of system critical functions reported by " - "firmware"); - pr_emerg("Check RTAS error log for details"); + pr_emerg("Loss of system critical functions detected. Check" + " RTAS error log for details\n"); orderly_poweroff(true); break; case EPOW_SHUTDOWN_AMBIENT_TEMPERATURE_TOO_HIGH: - pr_emerg("Ambient temperature too high reported by firmware"); - pr_emerg("Check RTAS error log for details"); + pr_emerg("High ambient temperature detected. Check RTAS" + " error log for details\n"); orderly_poweroff(true); break; default: - pr_err("Unknown power/cooling shutdown event (modifier %d)", + pr_err("Unknown power/cooling shutdown event (modifier = %d)\n", event_modifier); } } @@ -145,17 +146,20 @@ static void rtas_parse_epow_errlog(struct rtas_error_log *log) switch (action_code) { case EPOW_RESET: - pr_err("Non critical power or cooling issue cleared"); + if (num_epow_events) { + pr_info("Non critical power/cooling issue cleared\n"); + num_epow_events--; + } break; case EPOW_WARN_COOLING: - pr_err("Non critical cooling issue reported by firmware"); - pr_err("Check RTAS error log for details"); + pr_info("Non-critical cooling issue detected. Check RTAS error" + " log for details\n"); break; case EPOW_WARN_POWER: - pr_err("Non critical power issue reported by firmware"); - pr_err("Check RTAS error log for details"); + pr_info("Non-critical power issue detected. Check RTAS error" + " log for details\n"); break; case EPOW_SYSTEM_SHUTDOWN: @@ -163,23 +167,27 @@ static void rtas_parse_epow_errlog(struct rtas_error_log *log) break; case EPOW_SYSTEM_HALT: - pr_emerg("Firmware initiated power off"); + pr_emerg("Critical power/cooling issue detected. Check RTAS" + " error log for details. Powering off.\n"); orderly_poweroff(true); break; case EPOW_MAIN_ENCLOSURE: case EPOW_POWER_OFF: - pr_emerg("Critical power/cooling issue reported by firmware"); - pr_emerg("Check RTAS error log for details"); - pr_emerg("Immediate power off"); + pr_emerg("System about to lose power. Check RTAS error log " + " for details. Powering off immediately.\n"); emergency_sync(); kernel_power_off(); break; default: - pr_err("Unknown power/cooling event (action code %d)", + pr_err("Unknown power/cooling event (action code = %d)\n", action_code); } + + /* Increment epow events counter variable */ + if (action_code != EPOW_RESET) + num_epow_events++; } /* Handle environmental and power warning (EPOW) interrupts. */ @@ -249,13 +257,12 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, fatal); if (fatal) { - pr_emerg("Fatal hardware error reported by firmware"); - pr_emerg("Check RTAS error log for details"); - pr_emerg("Immediate power off"); + pr_emerg("Fatal hardware error detected. Check RTAS error" + " log for details. Powering off immediately\n"); emergency_sync(); kernel_power_off(); } else { - pr_err("Recoverable hardware error reported by firmware"); + pr_err("Recoverable hardware error detected\n"); } spin_unlock(&ras_log_buf_lock); |