diff options
Diffstat (limited to 'arch/powerpc')
34 files changed, 1259 insertions, 335 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d500772a1d9b..b580ce0c25a8 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -94,6 +94,7 @@ config PPC select OF_RESERVED_MEM select HAVE_FTRACE_MCOUNT_RECORD select HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select SYSCTL_EXCEPTION_TRACE @@ -373,6 +374,24 @@ config PPC_TRANSACTIONAL_MEM ---help--- Support user-mode Transactional Memory on POWERPC. +config DISABLE_MPROFILE_KERNEL + bool "Disable use of mprofile-kernel for kernel tracing" + depends on PPC64 && CPU_LITTLE_ENDIAN + default y + help + Selecting this options disables use of the mprofile-kernel ABI for + kernel tracing. That will cause options such as live patching + (CONFIG_LIVEPATCH) which depend on CONFIG_DYNAMIC_FTRACE_WITH_REGS to + be disabled also. + + If you have a toolchain which supports mprofile-kernel, then you can + enable this. Otherwise leave it disabled. If you're not sure, say + "N". + +config MPROFILE_KERNEL + depends on PPC64 && CPU_LITTLE_ENDIAN + def_bool !DISABLE_MPROFILE_KERNEL + config IOMMU_HELPER def_bool PPC64 diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 1a0ee01b0f46..709a22a3e824 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -133,6 +133,21 @@ else CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64 endif +ifdef CONFIG_MPROFILE_KERNEL + ifeq ($(shell $(srctree)/arch/powerpc/scripts/gcc-check-mprofile-kernel.sh $(CC) -I$(srctree)/include -D__KERNEL__),OK) + CC_FLAGS_FTRACE := -pg -mprofile-kernel + KBUILD_CPPFLAGS += -DCC_USING_MPROFILE_KERNEL + else + # If the user asked for mprofile-kernel but the toolchain doesn't + # support it, emit a warning and deliberately break the build later + # with mprofile-kernel-not-supported. We would prefer to make this an + # error right here, but then the user would never be able to run + # oldconfig to change their configuration. + $(warning Compiler does not support mprofile-kernel, set CONFIG_DISABLE_MPROFILE_KERNEL) + CC_FLAGS_FTRACE := -mprofile-kernel-not-supported + endif +endif + CFLAGS-$(CONFIG_CELL_CPU) += $(call cc-option,-mcpu=cell) CFLAGS-$(CONFIG_POWER4_CPU) += $(call cc-option,-mcpu=power4) CFLAGS-$(CONFIG_POWER5_CPU) += $(call cc-option,-mcpu=power5) diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 840a5509b3f1..994c60a857ce 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -99,4 +99,25 @@ static inline unsigned long ppc_global_function_entry(void *func) #endif } +#ifdef CONFIG_PPC64 +/* + * Some instruction encodings commonly used in dynamic ftracing + * and function live patching. + */ + +/* This must match the definition of STK_GOT in <asm/ppc_asm.h> */ +#if defined(_CALL_ELF) && _CALL_ELF == 2 +#define R2_STACK_OFFSET 24 +#else +#define R2_STACK_OFFSET 40 +#endif + +#define PPC_INST_LD_TOC (PPC_INST_LD | ___PPC_RT(__REG_R2) | \ + ___PPC_RA(__REG_R1) | R2_STACK_OFFSET) + +/* usually preceded by a mflr r0 */ +#define PPC_INST_STD_LR (PPC_INST_STD | ___PPC_RS(__REG_R0) | \ + ___PPC_RA(__REG_R1) | PPC_LR_STKOFF) +#endif /* CONFIG_PPC64 */ + #endif /* _ASM_POWERPC_CODE_PATCHING_H */ diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 867c39b45df6..fb9f376ae27b 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -72,6 +72,7 @@ struct pci_dn; #define EEH_PE_PHB (1 << 1) /* PHB PE */ #define EEH_PE_DEVICE (1 << 2) /* Device PE */ #define EEH_PE_BUS (1 << 3) /* Bus PE */ +#define EEH_PE_VF (1 << 4) /* VF PE */ #define EEH_PE_ISOLATED (1 << 0) /* Isolated PE */ #define EEH_PE_RECOVERING (1 << 1) /* Recovering PE */ @@ -136,11 +137,15 @@ struct eeh_dev { int pcix_cap; /* Saved PCIx capability */ int pcie_cap; /* Saved PCIe capability */ int aer_cap; /* Saved AER capability */ + int af_cap; /* Saved AF capability */ struct eeh_pe *pe; /* Associated PE */ struct list_head list; /* Form link list in the PE */ + struct list_head rmv_list; /* Record the removed edevs */ struct pci_controller *phb; /* Associated PHB */ struct pci_dn *pdn; /* Associated PCI device node */ struct pci_dev *pdev; /* Associated PCI device */ + bool in_error; /* Error flag for edev */ + struct pci_dev *physfn; /* Associated SRIOV PF */ struct pci_bus *bus; /* PCI bus for partial hotplug */ }; diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index ef89b1465573..50ca7585abe2 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -46,6 +46,8 @@ extern void _mcount(void); #ifdef CONFIG_DYNAMIC_FTRACE +# define FTRACE_ADDR ((unsigned long)ftrace_caller) +# define FTRACE_REGS_ADDR FTRACE_ADDR static inline unsigned long ftrace_call_adjust(unsigned long addr) { /* reloction of mcount call site is the same as the address */ @@ -58,6 +60,9 @@ struct dyn_arch_ftrace { #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* __ASSEMBLY__ */ +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#define ARCH_SUPPORTS_FTRACE_OPS 1 +#endif #endif #if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && !defined(__ASSEMBLY__) diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index e3b54dd4f730..0bc9c284aa10 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -94,6 +94,7 @@ #define H_SG_LIST -72 #define H_OP_MODE -73 #define H_COP_HW -74 +#define H_STATE -75 #define H_UNSUPPORTED_FLAG_START -256 #define H_UNSUPPORTED_FLAG_END -511 #define H_MULTI_THREADS_ACTIVE -9005 diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 5f1526fddccf..cd4ffd86765f 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -78,10 +78,18 @@ struct mod_arch_specific { # endif /* MODULE */ #endif -bool is_module_trampoline(u32 *insns); -int module_trampoline_target(struct module *mod, u32 *trampoline, +int module_trampoline_target(struct module *mod, unsigned long trampoline, unsigned long *target); +#ifdef CONFIG_DYNAMIC_FTRACE +int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs); +#else +static inline int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs) +{ + return 0; +} +#endif + struct exception_table_entry; void sort_ex_table(struct exception_table_entry *start, struct exception_table_entry *finish); diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index b0b43f5fbc5f..9f165e8a77bf 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -212,6 +212,7 @@ struct pci_dn { #define IODA_INVALID_PE (-1) #ifdef CONFIG_PPC_POWERNV int pe_number; + int vf_index; /* VF index in the PF */ #ifdef CONFIG_PCI_IOV u16 vfs_expanded; /* number of VFs IOV BAR expanded */ u16 num_vfs; /* number of VFs enabled*/ @@ -220,6 +221,7 @@ struct pci_dn { #define IODA_INVALID_M64 (-1) int (*m64_map)[PCI_SRIOV_NUM_BARS]; #endif /* CONFIG_PCI_IOV */ + int mps; /* Maximum Payload Size */ #endif struct list_head child_list; struct list_head list; diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 814622146d5a..e157489ee7a1 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -136,16 +136,24 @@ extern ssize_t power_events_sysfs_show(struct device *dev, * event 'cpu-cycles' can have two entries in sysfs: 'cpu-cycles' and * 'PM_CYC' where the latter is the name by which the event is known in * POWER CPU specification. + * + * Similarly, some hardware and cache events use the same event code. Eg. + * on POWER8, both "cache-references" and "L1-dcache-loads" events refer + * to the same event, PM_LD_REF_L1. The suffix, allows us to have two + * sysfs objects for the same event and thus two entries/aliases in sysfs. */ #define EVENT_VAR(_id, _suffix) event_attr_##_id##_suffix #define EVENT_PTR(_id, _suffix) &EVENT_VAR(_id, _suffix).attr.attr #define EVENT_ATTR(_name, _id, _suffix) \ - PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_##_id, \ + PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), _id, \ power_events_sysfs_show) #define GENERIC_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _g) #define GENERIC_EVENT_PTR(_id) EVENT_PTR(_id, _g) +#define CACHE_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _c) +#define CACHE_EVENT_PTR(_id) EVENT_PTR(_id, _c) + #define POWER_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _p) #define POWER_EVENT_PTR(_id) EVENT_PTR(_id, _p) diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index a5e930aca804..abf5866e08c6 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -22,6 +22,18 @@ static inline int in_kernel_text(unsigned long addr) return 0; } +static inline unsigned long kernel_toc_addr(void) +{ + /* Defined by the linker, see vmlinux.lds.S */ + extern unsigned long __toc_start; + + /* + * The TOC register (r2) points 32kB into the TOC, so that 64kB of + * the TOC can be addressed using a single machine instruction. + */ + return (unsigned long)(&__toc_start) + 0x8000UL; +} + static inline int overlaps_interrupt_vector_text(unsigned long start, unsigned long end) { diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 794f22adf99d..2da380fcc34c 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -16,14 +16,14 @@ endif ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code -CFLAGS_REMOVE_cputable.o = -pg -mno-sched-epilog -CFLAGS_REMOVE_prom_init.o = -pg -mno-sched-epilog -CFLAGS_REMOVE_btext.o = -pg -mno-sched-epilog -CFLAGS_REMOVE_prom.o = -pg -mno-sched-epilog +CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_prom_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_btext.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_prom.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) # do not trace tracer code -CFLAGS_REMOVE_ftrace.o = -pg -mno-sched-epilog +CFLAGS_REMOVE_ftrace.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) # timers used by tracing -CFLAGS_REMOVE_time.o = -pg -mno-sched-epilog +CFLAGS_REMOVE_time.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) endif obj-y := cputable.o ptrace.o syscalls.o \ diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 8c6005cf1583..6544017eb90b 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -268,13 +268,6 @@ static void *eeh_dump_pe_log(void *data, void *flag) struct eeh_dev *edev, *tmp; size_t *plen = flag; - /* If the PE's config space is blocked, 0xFF's will be - * returned. It's pointless to collect the log in this - * case. - */ - if (pe->state & EEH_PE_CFG_BLOCKED) - return NULL; - eeh_pe_for_each_dev(pe, edev, tmp) *plen += eeh_dump_dev_log(edev, pci_regs_buf + *plen, EEH_PCI_REGS_LOG_LEN - *plen); @@ -677,7 +670,7 @@ int eeh_pci_enable(struct eeh_pe *pe, int function) /* Check if the request is finished successfully */ if (active_flag) { rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); - if (rc <= 0) + if (rc < 0) return rc; if (rc & active_flag) @@ -761,7 +754,8 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat case pcie_deassert_reset: eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); eeh_unfreeze_pe(pe, false); - eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); + if (!(pe->type & EEH_PE_VF)) + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev); eeh_pe_state_clear(pe, EEH_PE_ISOLATED); break; @@ -769,14 +763,16 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED); eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); - eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); + if (!(pe->type & EEH_PE_VF)) + eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_HOT); break; case pcie_warm_reset: eeh_pe_state_mark_with_cfg(pe, EEH_PE_ISOLATED); eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); - eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); + if (!(pe->type & EEH_PE_VF)) + eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); break; default: @@ -1243,6 +1239,14 @@ void eeh_remove_device(struct pci_dev *dev) * from the parent PE during the BAR resotre. */ edev->pdev = NULL; + + /* + * The flag "in_error" is used to trace EEH devices for VFs + * in error state or not. It's set in eeh_report_error(). If + * it's not set, eeh_report_{reset,resume}() won't be called + * for the VF EEH device. + */ + edev->in_error = false; dev->dev.archdata.edev = NULL; if (!(edev->pe->state & EEH_PE_KEEP)) eeh_rmv_from_parent_pe(edev); @@ -1537,6 +1541,17 @@ int eeh_pe_get_state(struct eeh_pe *pe) if (!eeh_ops || !eeh_ops->get_state) return -ENOENT; + /* + * If the parent PE is owned by the host kernel and is undergoing + * error recovery, we should return the PE state as temporarily + * unavailable so that the error recovery on the guest is suspended + * until the recovery completes on the host. + */ + if (pe->parent && + !(pe->state & EEH_PE_REMOVED) && + (pe->parent->state & (EEH_PE_ISOLATED | EEH_PE_RECOVERING))) + return EEH_PE_STATE_UNAVAIL; + result = eeh_ops->get_state(pe, NULL); rst_active = !!(result & EEH_STATE_RESET_ACTIVE); dma_en = !!(result & EEH_STATE_DMA_ENABLED); diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index a1e86e172e3c..ddbcfab7efdf 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -195,8 +195,11 @@ static void __eeh_addr_cache_insert_dev(struct pci_dev *dev) return; } - /* Walk resources on this device, poke them into the tree */ - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { + /* + * Walk resources on this device, poke the first 7 (6 normal BAR and 1 + * ROM BAR) into the tree. + */ + for (i = 0; i <= PCI_ROM_RESOURCE; i++) { resource_size_t start = pci_resource_start(dev,i); resource_size_t end = pci_resource_end(dev,i); unsigned long flags = pci_resource_flags(dev,i); @@ -222,10 +225,6 @@ void eeh_addr_cache_insert_dev(struct pci_dev *dev) { unsigned long flags; - /* Ignore PCI bridges */ - if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE) - return; - spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); __eeh_addr_cache_insert_dev(dev); spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c index aabba94ff9cb..7815095fe3d8 100644 --- a/arch/powerpc/kernel/eeh_dev.c +++ b/arch/powerpc/kernel/eeh_dev.c @@ -67,6 +67,7 @@ void *eeh_dev_init(struct pci_dn *pdn, void *data) edev->pdn = pdn; edev->phb = phb; INIT_LIST_HEAD(&edev->list); + INIT_LIST_HEAD(&edev->rmv_list); return NULL; } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 650cfb31ea3d..fb6207d2c604 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -34,6 +34,11 @@ #include <asm/prom.h> #include <asm/rtas.h> +struct eeh_rmv_data { + struct list_head edev_list; + int removed; +}; + /** * eeh_pcid_name - Retrieve name of PCI device driver * @pdev: PCI device @@ -190,7 +195,7 @@ static void *eeh_report_error(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - if (!dev || eeh_dev_removed(edev)) + if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; dev->error_state = pci_channel_io_frozen; @@ -211,6 +216,7 @@ static void *eeh_report_error(void *data, void *userdata) if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc; if (*res == PCI_ERS_RESULT_NONE) *res = rc; + edev->in_error = true; eeh_pcid_put(dev); return NULL; } @@ -231,7 +237,7 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - if (!dev || eeh_dev_removed(edev)) + if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; driver = eeh_pcid_get(dev); @@ -271,7 +277,7 @@ static void *eeh_report_reset(void *data, void *userdata) enum pci_ers_result rc, *res = userdata; struct pci_driver *driver; - if (!dev || eeh_dev_removed(edev)) + if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; dev->error_state = pci_channel_io_normal; @@ -282,7 +288,8 @@ static void *eeh_report_reset(void *data, void *userdata) if (!driver->err_handler || !driver->err_handler->slot_reset || - (edev->mode & EEH_DEV_NO_HANDLER)) { + (edev->mode & EEH_DEV_NO_HANDLER) || + (!edev->in_error)) { eeh_pcid_put(dev); return NULL; } @@ -326,20 +333,23 @@ static void *eeh_report_resume(void *data, void *userdata) { struct eeh_dev *edev = (struct eeh_dev *)data; struct pci_dev *dev = eeh_dev_to_pci_dev(edev); + bool was_in_error; struct pci_driver *driver; - if (!dev || eeh_dev_removed(edev)) + if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; dev->error_state = pci_channel_io_normal; driver = eeh_pcid_get(dev); if (!driver) return NULL; + was_in_error = edev->in_error; + edev->in_error = false; eeh_enable_irq(dev); if (!driver->err_handler || !driver->err_handler->resume || - (edev->mode & EEH_DEV_NO_HANDLER)) { + (edev->mode & EEH_DEV_NO_HANDLER) || !was_in_error) { edev->mode &= ~EEH_DEV_NO_HANDLER; eeh_pcid_put(dev); return NULL; @@ -365,7 +375,7 @@ static void *eeh_report_failure(void *data, void *userdata) struct pci_dev *dev = eeh_dev_to_pci_dev(edev); struct pci_driver *driver; - if (!dev || eeh_dev_removed(edev)) + if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe)) return NULL; dev->error_state = pci_channel_io_perm_failure; @@ -386,12 +396,40 @@ static void *eeh_report_failure(void *data, void *userdata) return NULL; } +static void *eeh_add_virt_device(void *data, void *userdata) +{ + struct pci_driver *driver; + struct eeh_dev *edev = (struct eeh_dev *)data; + struct pci_dev *dev = eeh_dev_to_pci_dev(edev); + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + + if (!(edev->physfn)) { + pr_warn("%s: EEH dev %04x:%02x:%02x.%01x not for VF\n", + __func__, edev->phb->global_number, pdn->busno, + PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); + return NULL; + } + + driver = eeh_pcid_get(dev); + if (driver) { + eeh_pcid_put(dev); + if (driver->err_handler) + return NULL; + } + +#ifdef CONFIG_PPC_POWERNV + pci_iov_add_virtfn(edev->physfn, pdn->vf_index, 0); +#endif + return NULL; +} + static void *eeh_rmv_device(void *data, void *userdata) { struct pci_driver *driver; struct eeh_dev *edev = (struct eeh_dev *)data; struct pci_dev *dev = eeh_dev_to_pci_dev(edev); - int *removed = (int *)userdata; + struct eeh_rmv_data *rmv_data = (struct eeh_rmv_data *)userdata; + int *removed = rmv_data ? &rmv_data->removed : NULL; /* * Actually, we should remove the PCI bridges as well. @@ -416,7 +454,11 @@ static void *eeh_rmv_device(void *data, void *userdata) driver = eeh_pcid_get(dev); if (driver) { eeh_pcid_put(dev); - if (driver->err_handler && + if (removed && + eeh_pe_passed(edev->pe)) + return NULL; + if (removed && + driver->err_handler && driver->err_handler->error_detected && driver->err_handler->slot_reset) return NULL; @@ -427,11 +469,29 @@ static void *eeh_rmv_device(void *data, void *userdata) pci_name(dev)); edev->bus = dev->bus; edev->mode |= EEH_DEV_DISCONNECTED; - (*removed)++; + if (removed) + (*removed)++; - pci_lock_rescan_remove(); - pci_stop_and_remove_bus_device(dev); - pci_unlock_rescan_remove(); + if (edev->physfn) { +#ifdef CONFIG_PPC_POWERNV + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + + pci_iov_remove_virtfn(edev->physfn, pdn->vf_index, 0); + edev->pdev = NULL; + + /* + * We have to set the VF PE number to invalid one, which is + * required to plug the VF successfully. + */ + pdn->pe_number = IODA_INVALID_PE; +#endif + if (rmv_data) + list_add(&edev->rmv_list, &rmv_data->edev_list); + } else { + pci_lock_rescan_remove(); + pci_stop_and_remove_bus_device(dev); + pci_unlock_rescan_remove(); + } return NULL; } @@ -545,11 +605,13 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) * During the reset, udev might be invoked because those affected * PCI devices will be removed and then added. */ -static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) +static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, + struct eeh_rmv_data *rmv_data) { struct pci_bus *frozen_bus = eeh_pe_bus_get(pe); struct timeval tstamp; - int cnt, rc, removed = 0; + int cnt, rc; + struct eeh_dev *edev; /* pcibios will clear the counter; save the value */ cnt = pe->freeze_count; @@ -563,12 +625,16 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) */ eeh_pe_state_mark(pe, EEH_PE_KEEP); if (bus) { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); - pci_lock_rescan_remove(); - pcibios_remove_pci_devices(bus); - pci_unlock_rescan_remove(); + if (pe->type & EEH_PE_VF) { + eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); + pci_lock_rescan_remove(); + pcibios_remove_pci_devices(bus); + pci_unlock_rescan_remove(); + } } else if (frozen_bus) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed); + eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data); } /* @@ -610,14 +676,22 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) * PE. We should disconnect it so the binding can be * rebuilt when adding PCI devices. */ + edev = list_first_entry(&pe->edevs, struct eeh_dev, list); eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL); - pcibios_add_pci_devices(bus); - } else if (frozen_bus && removed) { + if (pe->type & EEH_PE_VF) + eeh_add_virt_device(edev, NULL); + else + pcibios_add_pci_devices(bus); + } else if (frozen_bus && rmv_data->removed) { pr_info("EEH: Sleep 5s ahead of partial hotplug\n"); ssleep(5); + edev = list_first_entry(&pe->edevs, struct eeh_dev, list); eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL); - pcibios_add_pci_devices(frozen_bus); + if (pe->type & EEH_PE_VF) + eeh_add_virt_device(edev, NULL); + else + pcibios_add_pci_devices(frozen_bus); } eeh_pe_state_clear(pe, EEH_PE_KEEP); @@ -636,8 +710,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) static void eeh_handle_normal_event(struct eeh_pe *pe) { struct pci_bus *frozen_bus; + struct eeh_dev *edev, *tmp; int rc = 0; enum pci_ers_result result = PCI_ERS_RESULT_NONE; + struct eeh_rmv_data rmv_data = {LIST_HEAD_INIT(rmv_data.edev_list), 0}; frozen_bus = eeh_pe_bus_get(pe); if (!frozen_bus) { @@ -692,7 +768,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) */ if (result == PCI_ERS_RESULT_NONE) { pr_info("EEH: Reset with hotplug activity\n"); - rc = eeh_reset_device(pe, frozen_bus); + rc = eeh_reset_device(pe, frozen_bus, NULL); if (rc) { pr_warn("%s: Unable to reset, err=%d\n", __func__, rc); @@ -744,7 +820,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) /* If any device called out for a reset, then reset the slot */ if (result == PCI_ERS_RESULT_NEED_RESET) { pr_info("EEH: Reset without hotplug activity\n"); - rc = eeh_reset_device(pe, NULL); + rc = eeh_reset_device(pe, NULL, &rmv_data); if (rc) { pr_warn("%s: Cannot reset, err=%d\n", __func__, rc); @@ -764,6 +840,15 @@ static void eeh_handle_normal_event(struct eeh_pe *pe) goto hard_fail; } + /* + * For those hot removed VFs, we should add back them after PF get + * recovered properly. + */ + list_for_each_entry_safe(edev, tmp, &rmv_data.edev_list, rmv_list) { + eeh_add_virt_device(edev, NULL); + list_del(&edev->rmv_list); + } + /* Tell all device drivers that they can resume operations */ pr_info("EEH: Notify device driver to resume\n"); eeh_pe_dev_traverse(pe, eeh_report_resume, NULL); @@ -803,12 +888,17 @@ perm_error: * the their PCI config any more. */ if (frozen_bus) { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); - eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + if (pe->type & EEH_PE_VF) { + eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); + eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); - pci_lock_rescan_remove(); - pcibios_remove_pci_devices(frozen_bus); - pci_unlock_rescan_remove(); + pci_lock_rescan_remove(); + pcibios_remove_pci_devices(frozen_bus); + pci_unlock_rescan_remove(); + } } } diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 98f81800e00c..eea48d8baf49 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -299,7 +299,10 @@ static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev) * EEH device already having associated PE, but * the direct parent EEH device doesn't have yet. */ - pdn = pdn ? pdn->parent : NULL; + if (edev->physfn) + pdn = pci_get_pdn(edev->physfn); + else + pdn = pdn ? pdn->parent : NULL; while (pdn) { /* We're poking out of PCI territory */ parent = pdn_to_eeh_dev(pdn); @@ -382,7 +385,10 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) } /* Create a new EEH PE */ - pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE); + if (edev->physfn) + pe = eeh_pe_alloc(edev->phb, EEH_PE_VF); + else + pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE); if (!pe) { pr_err("%s: out of memory!\n", __func__); return -ENOMEM; @@ -920,25 +926,21 @@ const char *eeh_pe_loc_get(struct eeh_pe *pe) */ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) { - struct pci_bus *bus = NULL; struct eeh_dev *edev; struct pci_dev *pdev; - if (pe->type & EEH_PE_PHB) { - bus = pe->phb->bus; - } else if (pe->type & EEH_PE_BUS || - pe->type & EEH_PE_DEVICE) { - if (pe->state & EEH_PE_PRI_BUS) { - bus = pe->bus; - goto out; - } + if (pe->type & EEH_PE_PHB) + return pe->phb->bus; - edev = list_first_entry(&pe->edevs, struct eeh_dev, list); - pdev = eeh_dev_to_pci_dev(edev); - if (pdev) - bus = pdev->bus; - } + /* The primary bus might be cached during probe time */ + if (pe->state & EEH_PE_PRI_BUS) + return pe->bus; -out: - return bus; + /* Retrieve the parent PCI bus of first (top) PCI device */ + edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, list); + pdev = eeh_dev_to_pci_dev(edev); + if (pdev) + return pdev->bus; + + return NULL; } diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 038e0a1425e7..b9b125327f27 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -1158,8 +1158,12 @@ _GLOBAL(enter_prom) #ifdef CONFIG_DYNAMIC_FTRACE _GLOBAL(mcount) _GLOBAL(_mcount) - blr + mflr r12 + mtctr r12 + mtlr r0 + bctr +#ifndef CC_USING_MPROFILE_KERNEL _GLOBAL_TOC(ftrace_caller) /* Taken from output of objdump from lib64/glibc */ mflr r3 @@ -1181,6 +1185,115 @@ _GLOBAL(ftrace_graph_stub) ld r0, 128(r1) mtlr r0 addi r1, r1, 112 + +#else /* CC_USING_MPROFILE_KERNEL */ +/* + * + * ftrace_caller() is the function that replaces _mcount() when ftrace is + * active. + * + * We arrive here after a function A calls function B, and we are the trace + * function for B. When we enter r1 points to A's stack frame, B has not yet + * had a chance to allocate one yet. + * + * Additionally r2 may point either to the TOC for A, or B, depending on + * whether B did a TOC setup sequence before calling us. + * + * On entry the LR points back to the _mcount() call site, and r0 holds the + * saved LR as it was on entry to B, ie. the original return address at the + * call site in A. + * + * Our job is to save the register state into a struct pt_regs (on the stack) + * and then arrange for the ftrace function to be called. + */ +_GLOBAL(ftrace_caller) + /* Save the original return address in A's stack frame */ + std r0,LRSAVE(r1) + + /* Create our stack frame + pt_regs */ + stdu r1,-SWITCH_FRAME_SIZE(r1) + + /* Save all gprs to pt_regs */ + SAVE_8GPRS(0,r1) + SAVE_8GPRS(8,r1) + SAVE_8GPRS(16,r1) + SAVE_8GPRS(24,r1) + + /* Load special regs for save below */ + mfmsr r8 + mfctr r9 + mfxer r10 + mfcr r11 + + /* Get the _mcount() call site out of LR */ + mflr r7 + /* Save it as pt_regs->nip & pt_regs->link */ + std r7, _NIP(r1) + std r7, _LINK(r1) + + /* Save callee's TOC in the ABI compliant location */ + std r2, 24(r1) + ld r2,PACATOC(r13) /* get kernel TOC in r2 */ + + addis r3,r2,function_trace_op@toc@ha + addi r3,r3,function_trace_op@toc@l + ld r5,0(r3) + + /* Calculate ip from nip-4 into r3 for call below */ + subi r3, r7, MCOUNT_INSN_SIZE + + /* Put the original return address in r4 as parent_ip */ + mr r4, r0 + + /* Save special regs */ + std r8, _MSR(r1) + std r9, _CTR(r1) + std r10, _XER(r1) + std r11, _CCR(r1) + + /* Load &pt_regs in r6 for call below */ + addi r6, r1 ,STACK_FRAME_OVERHEAD + + /* ftrace_call(r3, r4, r5, r6) */ +.globl ftrace_call +ftrace_call: + bl ftrace_stub + nop + + /* Load ctr with the possibly modified NIP */ + ld r3, _NIP(r1) + mtctr r3 + + /* Restore gprs */ + REST_8GPRS(0,r1) + REST_8GPRS(8,r1) + REST_8GPRS(16,r1) + REST_8GPRS(24,r1) + + /* Restore callee's TOC */ + ld r2, 24(r1) + + /* Pop our stack frame */ + addi r1, r1, SWITCH_FRAME_SIZE + + /* Restore original LR for return to B */ + ld r0, LRSAVE(r1) + mtlr r0 + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + stdu r1, -112(r1) +.globl ftrace_graph_call +ftrace_graph_call: + b ftrace_graph_stub +_GLOBAL(ftrace_graph_stub) + addi r1, r1, 112 +#endif + + ld r0,LRSAVE(r1) /* restore callee's lr at _mcount site */ + mtlr r0 + bctr /* jump after _mcount site */ +#endif /* CC_USING_MPROFILE_KERNEL */ + _GLOBAL(ftrace_stub) blr #else @@ -1213,6 +1326,7 @@ _GLOBAL(ftrace_stub) #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER +#ifndef CC_USING_MPROFILE_KERNEL _GLOBAL(ftrace_graph_caller) /* load r4 with local address */ ld r4, 128(r1) @@ -1237,6 +1351,56 @@ _GLOBAL(ftrace_graph_caller) addi r1, r1, 112 blr +#else /* CC_USING_MPROFILE_KERNEL */ +_GLOBAL(ftrace_graph_caller) + /* with -mprofile-kernel, parameter regs are still alive at _mcount */ + std r10, 104(r1) + std r9, 96(r1) + std r8, 88(r1) + std r7, 80(r1) + std r6, 72(r1) + std r5, 64(r1) + std r4, 56(r1) + std r3, 48(r1) + + /* Save callee's TOC in the ABI compliant location */ + std r2, 24(r1) + ld r2, PACATOC(r13) /* get kernel TOC in r2 */ + + mfctr r4 /* ftrace_caller has moved local addr here */ + std r4, 40(r1) + mflr r3 /* ftrace_caller has restored LR from stack */ + subi r4, r4, MCOUNT_INSN_SIZE + + bl prepare_ftrace_return + nop + + /* + * prepare_ftrace_return gives us the address we divert to. + * Change the LR to this. + */ + mtlr r3 + + ld r0, 40(r1) + mtctr r0 + ld r10, 104(r1) + ld r9, 96(r1) + ld r8, 88(r1) + ld r7, 80(r1) + ld r6, 72(r1) + ld r5, 64(r1) + ld r4, 56(r1) + ld r3, 48(r1) + + /* Restore callee's TOC */ + ld r2, 24(r1) + + addi r1, r1, 112 + mflr r0 + std r0, LRSAVE(r1) + bctr +#endif /* CC_USING_MPROFILE_KERNEL */ + _GLOBAL(return_to_handler) /* need to save return values */ std r4, -32(r1) diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 44d4d8eb3c85..9dac18dabd03 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -61,8 +61,11 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new) return -EFAULT; /* Make sure it is what we expect it to be */ - if (replaced != old) + if (replaced != old) { + pr_err("%p: replaced (%#x) != old (%#x)", + (void *)ip, replaced, old); return -EINVAL; + } /* replace the text with the new text */ if (patch_instruction((unsigned int *)ip, new)) @@ -106,14 +109,15 @@ static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned int op; - unsigned long entry, ptr; + unsigned long entry, ptr, tramp; unsigned long ip = rec->ip; - void *tramp; + unsigned int op, pop; /* read where this goes */ - if (probe_kernel_read(&op, (void *)ip, sizeof(int))) + if (probe_kernel_read(&op, (void *)ip, sizeof(int))) { + pr_err("Fetching opcode failed.\n"); return -EFAULT; + } /* Make sure that that this is still a 24bit jump */ if (!is_bl_op(op)) { @@ -122,14 +126,9 @@ __ftrace_make_nop(struct module *mod, } /* lets find where the pointer goes */ - tramp = (void *)find_bl_target(ip, op); - - pr_devel("ip:%lx jumps to %p", ip, tramp); + tramp = find_bl_target(ip, op); - if (!is_module_trampoline(tramp)) { - pr_err("Not a trampoline\n"); - return -EINVAL; - } + pr_devel("ip:%lx jumps to %lx", ip, tramp); if (module_trampoline_target(mod, tramp, &ptr)) { pr_err("Failed to get trampoline target\n"); @@ -158,10 +157,42 @@ __ftrace_make_nop(struct module *mod, * * Use a b +8 to jump over the load. */ - op = 0x48000008; /* b +8 */ - if (patch_instruction((unsigned int *)ip, op)) + pop = PPC_INST_BRANCH | 8; /* b +8 */ + + /* + * Check what is in the next instruction. We can see ld r2,40(r1), but + * on first pass after boot we will see mflr r0. + */ + if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) { + pr_err("Fetching op failed.\n"); + return -EFAULT; + } + + if (op != PPC_INST_LD_TOC) { + unsigned int inst; + + if (probe_kernel_read(&inst, (void *)(ip - 4), 4)) { + pr_err("Fetching instruction at %lx failed.\n", ip - 4); + return -EFAULT; + } + + /* We expect either a mlfr r0, or a std r0, LRSAVE(r1) */ + if (inst != PPC_INST_MFLR && inst != PPC_INST_STD_LR) { + pr_err("Unexpected instructions around bl _mcount\n" + "when enabling dynamic ftrace!\t" + "(%08x,bl,%08x)\n", inst, op); + return -EINVAL; + } + + /* When using -mkernel_profile there is no load to jump over */ + pop = PPC_INST_NOP; + } + + if (patch_instruction((unsigned int *)ip, pop)) { + pr_err("Patching NOP failed.\n"); return -EPERM; + } return 0; } @@ -287,16 +318,15 @@ int ftrace_make_nop(struct module *mod, #ifdef CONFIG_MODULES #ifdef CONFIG_PPC64 +/* + * Examine the existing instructions for __ftrace_make_call. + * They should effectively be a NOP, and follow formal constraints, + * depending on the ABI. Return false if they don't. + */ +#ifndef CC_USING_MPROFILE_KERNEL static int -__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1) { - unsigned int op[2]; - void *ip = (void *)rec->ip; - - /* read where this goes */ - if (probe_kernel_read(op, ip, sizeof(op))) - return -EFAULT; - /* * We expect to see: * @@ -306,8 +336,34 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * The load offset is different depending on the ABI. For simplicity * just mask it out when doing the compare. */ - if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) { - pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]); + if ((op0 != 0x48000008) || ((op1 & 0xffff0000) != 0xe8410000)) + return 0; + return 1; +} +#else +static int +expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1) +{ + /* look for patched "NOP" on ppc64 with -mprofile-kernel */ + if (op0 != PPC_INST_NOP) + return 0; + return 1; +} +#endif + +static int +__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned int op[2]; + void *ip = (void *)rec->ip; + + /* read where this goes */ + if (probe_kernel_read(op, ip, sizeof(op))) + return -EFAULT; + + if (!expected_nop_sequence(ip, op[0], op[1])) { + pr_err("Unexpected call sequence at %p: %x %x\n", + ip, op[0], op[1]); return -EINVAL; } @@ -330,7 +386,16 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return 0; } -#else + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + return ftrace_make_call(rec, addr); +} +#endif + +#else /* !CONFIG_PPC64: */ static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { @@ -455,20 +520,13 @@ void ftrace_replace_code(int enable) } } +/* + * Use the default ftrace_modify_all_code, but without + * stop_machine(). + */ void arch_ftrace_update_code(int command) { - if (command & FTRACE_UPDATE_CALLS) - ftrace_replace_code(1); - else if (command & FTRACE_DISABLE_CALLS) - ftrace_replace_code(0); - - if (command & FTRACE_UPDATE_TRACE_FUNC) - ftrace_update_ftrace_func(ftrace_trace_function); - - if (command & FTRACE_START_FUNC_RET) - ftrace_enable_ftrace_graph_caller(); - else if (command & FTRACE_STOP_FUNC_RET) - ftrace_disable_ftrace_graph_caller(); + ftrace_modify_all_code(command); } int __init ftrace_dyn_arch_init(void) diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 9547381b631a..d1f1b35bf0c7 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -47,6 +47,11 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { const Elf_Shdr *sect; + int rc; + + rc = module_finalize_ftrace(me, sechdrs); + if (rc) + return rc; /* Apply feature fixups */ sect = find_section(hdr, sechdrs, "__ftr_fixup"); diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 2c01665eb410..5a7a78f12562 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -181,7 +181,7 @@ static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val) /* Set up a trampoline in the PLT to bounce us to the distant function */ static uint32_t do_plt_call(void *location, Elf32_Addr val, - Elf32_Shdr *sechdrs, + const Elf32_Shdr *sechdrs, struct module *mod) { struct ppc_plt_entry *entry; @@ -294,11 +294,19 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, return -ENOEXEC; } } + + return 0; +} + #ifdef CONFIG_DYNAMIC_FTRACE - module->arch.tramp = - do_plt_call(module->core_layout.base, - (unsigned long)ftrace_caller, - sechdrs, module); -#endif +int module_finalize_ftrace(struct module *module, const Elf_Shdr *sechdrs) +{ + module->arch.tramp = do_plt_call(module->core_layout.base, + (unsigned long)ftrace_caller, + sechdrs, module); + if (!module->arch.tramp) + return -ENOENT; + return 0; } +#endif diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 08b7a40de5f8..9ce9a25f58b5 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -31,6 +31,7 @@ #include <asm/code-patching.h> #include <linux/sort.h> #include <asm/setup.h> +#include <asm/sections.h> /* FIXME: We don't do .init separately. To do this, we'd need to have a separate r2 value in the init and core section, and stub between @@ -41,7 +42,6 @@ --RR. */ #if defined(_CALL_ELF) && _CALL_ELF == 2 -#define R2_STACK_OFFSET 24 /* An address is simply the address of the function. */ typedef unsigned long func_desc_t; @@ -73,7 +73,6 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym) return PPC64_LOCAL_ENTRY_OFFSET(sym->st_other); } #else -#define R2_STACK_OFFSET 40 /* An address is address of the OPD entry, which contains address of fn. */ typedef struct ppc64_opd_entry func_desc_t; @@ -96,6 +95,8 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym) } #endif +#define STUB_MAGIC 0x73747562 /* stub */ + /* Like PPC32, we need little trampolines to do > 24-bit jumps (into the kernel itself). But on PPC64, these need to be used for every jump, actually, to reset r2 (TOC+0x8000). */ @@ -105,7 +106,8 @@ struct ppc64_stub_entry * need 6 instructions on ABIv2 but we always allocate 7 so * so we don't have to modify the trampoline load instruction. */ u32 jump[7]; - u32 unused; + /* Used by ftrace to identify stubs */ + u32 magic; /* Data for the above code */ func_desc_t funcdata; }; @@ -139,70 +141,39 @@ static u32 ppc64_stub_insns[] = { }; #ifdef CONFIG_DYNAMIC_FTRACE - -static u32 ppc64_stub_mask[] = { - 0xffff0000, - 0xffff0000, - 0xffffffff, - 0xffffffff, -#if !defined(_CALL_ELF) || _CALL_ELF != 2 - 0xffffffff, -#endif - 0xffffffff, - 0xffffffff -}; - -bool is_module_trampoline(u32 *p) +int module_trampoline_target(struct module *mod, unsigned long addr, + unsigned long *target) { - unsigned int i; - u32 insns[ARRAY_SIZE(ppc64_stub_insns)]; - - BUILD_BUG_ON(sizeof(ppc64_stub_insns) != sizeof(ppc64_stub_mask)); + struct ppc64_stub_entry *stub; + func_desc_t funcdata; + u32 magic; - if (probe_kernel_read(insns, p, sizeof(insns))) + if (!within_module_core(addr, mod)) { + pr_err("%s: stub %lx not in module %s\n", __func__, addr, mod->name); return -EFAULT; - - for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) { - u32 insna = insns[i]; - u32 insnb = ppc64_stub_insns[i]; - u32 mask = ppc64_stub_mask[i]; - - if ((insna & mask) != (insnb & mask)) - return false; } - return true; -} - -int module_trampoline_target(struct module *mod, u32 *trampoline, - unsigned long *target) -{ - u32 buf[2]; - u16 upper, lower; - long offset; - void *toc_entry; + stub = (struct ppc64_stub_entry *)addr; - if (probe_kernel_read(buf, trampoline, sizeof(buf))) + if (probe_kernel_read(&magic, &stub->magic, sizeof(magic))) { + pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name); return -EFAULT; + } - upper = buf[0] & 0xffff; - lower = buf[1] & 0xffff; - - /* perform the addis/addi, both signed */ - offset = ((short)upper << 16) + (short)lower; + if (magic != STUB_MAGIC) { + pr_err("%s: bad magic for stub %lx for %s\n", __func__, addr, mod->name); + return -EFAULT; + } - /* - * Now get the address this trampoline jumps to. This - * is always 32 bytes into our trampoline stub. - */ - toc_entry = (void *)mod->arch.toc + offset + 32; + if (probe_kernel_read(&funcdata, &stub->funcdata, sizeof(funcdata))) { + pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name); + return -EFAULT; + } - if (probe_kernel_read(target, toc_entry, sizeof(*target))) - return -EFAULT; + *target = stub_func_addr(funcdata); return 0; } - #endif /* Count how many different 24-bit relocations (different symbol, @@ -413,7 +384,7 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, /* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this gives the value maximum span in an instruction which uses a signed offset) */ -static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me) +static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me) { return sechdrs[me->arch.toc_section].sh_addr + 0x8000; } @@ -426,7 +397,7 @@ static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me) #define PPC_HA(v) PPC_HI ((v) + 0x8000) /* Patch stub to reference function and correct r2 value. */ -static inline int create_stub(Elf64_Shdr *sechdrs, +static inline int create_stub(const Elf64_Shdr *sechdrs, struct ppc64_stub_entry *entry, unsigned long addr, struct module *me) @@ -447,12 +418,14 @@ static inline int create_stub(Elf64_Shdr *sechdrs, entry->jump[0] |= PPC_HA(reladdr); entry->jump[1] |= PPC_LO(reladdr); entry->funcdata = func_desc(addr); + entry->magic = STUB_MAGIC; + return 1; } /* Create stub to jump to function described in this OPD/ptr: we need the stub to set up the TOC ptr (r2) for the function. */ -static unsigned long stub_for_addr(Elf64_Shdr *sechdrs, +static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs, unsigned long addr, struct module *me) { @@ -476,17 +449,60 @@ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs, return (unsigned long)&stubs[i]; } +#ifdef CC_USING_MPROFILE_KERNEL +static bool is_early_mcount_callsite(u32 *instruction) +{ + /* + * Check if this is one of the -mprofile-kernel sequences. + */ + if (instruction[-1] == PPC_INST_STD_LR && + instruction[-2] == PPC_INST_MFLR) + return true; + + if (instruction[-1] == PPC_INST_MFLR) + return true; + + return false; +} + +/* + * In case of _mcount calls, do not save the current callee's TOC (in r2) into + * the original caller's stack frame. If we did we would clobber the saved TOC + * value of the original caller. + */ +static void squash_toc_save_inst(const char *name, unsigned long addr) +{ + struct ppc64_stub_entry *stub = (struct ppc64_stub_entry *)addr; + + /* Only for calls to _mcount */ + if (strcmp("_mcount", name) != 0) + return; + + stub->jump[2] = PPC_INST_NOP; +} +#else +static void squash_toc_save_inst(const char *name, unsigned long addr) { } + +/* without -mprofile-kernel, mcount calls are never early */ +static bool is_early_mcount_callsite(u32 *instruction) +{ + return false; +} +#endif + /* We expect a noop next: if it is, replace it with instruction to restore r2. */ static int restore_r2(u32 *instruction, struct module *me) { if (*instruction != PPC_INST_NOP) { + if (is_early_mcount_callsite(instruction - 1)) + return 1; pr_err("%s: Expect noop after relocate, got %08x\n", me->name, *instruction); return 0; } /* ld r2,R2_STACK_OFFSET(r1) */ - *instruction = 0xe8410000 | R2_STACK_OFFSET; + *instruction = PPC_INST_LD_TOC; return 1; } @@ -611,6 +627,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, return -ENOENT; if (!restore_r2((u32 *)location + 1, me)) return -ENOEXEC; + + squash_toc_save_inst(strtab + sym->st_name, value); } else value += local_entry_offset(sym); @@ -693,12 +711,84 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, } } + return 0; +} + #ifdef CONFIG_DYNAMIC_FTRACE - me->arch.toc = my_r2(sechdrs, me); - me->arch.tramp = stub_for_addr(sechdrs, - (unsigned long)ftrace_caller, - me); + +#ifdef CC_USING_MPROFILE_KERNEL + +#define PACATOC offsetof(struct paca_struct, kernel_toc) + +/* + * For mprofile-kernel we use a special stub for ftrace_caller() because we + * can't rely on r2 containing this module's TOC when we enter the stub. + * + * That can happen if the function calling us didn't need to use the toc. In + * that case it won't have setup r2, and the r2 value will be either the + * kernel's toc, or possibly another modules toc. + * + * To deal with that this stub uses the kernel toc, which is always accessible + * via the paca (in r13). The target (ftrace_caller()) is responsible for + * saving and restoring the toc before returning. + */ +static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me) +{ + struct ppc64_stub_entry *entry; + unsigned int i, num_stubs; + static u32 stub_insns[] = { + 0xe98d0000 | PACATOC, /* ld r12,PACATOC(r13) */ + 0x3d8c0000, /* addis r12,r12,<high> */ + 0x398c0000, /* addi r12,r12,<low> */ + 0x7d8903a6, /* mtctr r12 */ + 0x4e800420, /* bctr */ + }; + long reladdr; + + num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*entry); + + /* Find the next available stub entry */ + entry = (void *)sechdrs[me->arch.stubs_section].sh_addr; + for (i = 0; i < num_stubs && stub_func_addr(entry->funcdata); i++, entry++); + + if (i >= num_stubs) { + pr_err("%s: Unable to find a free slot for ftrace stub.\n", me->name); + return 0; + } + + memcpy(entry->jump, stub_insns, sizeof(stub_insns)); + + /* Stub uses address relative to kernel toc (from the paca) */ + reladdr = (unsigned long)ftrace_caller - kernel_toc_addr(); + if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { + pr_err("%s: Address of ftrace_caller out of range of kernel_toc.\n", me->name); + return 0; + } + + entry->jump[1] |= PPC_HA(reladdr); + entry->jump[2] |= PPC_LO(reladdr); + + /* Eventhough we don't use funcdata in the stub, it's needed elsewhere. */ + entry->funcdata = func_desc((unsigned long)ftrace_caller); + entry->magic = STUB_MAGIC; + + return (unsigned long)entry; +} +#else +static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me) +{ + return stub_for_addr(sechdrs, (unsigned long)ftrace_caller, me); +} #endif +int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs) +{ + mod->arch.toc = my_r2(sechdrs, mod); + mod->arch.tramp = create_ftrace_stub(sechdrs, mod); + + if (!mod->arch.tramp) + return -ENOENT; + return 0; } +#endif diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 01ea0edf0579..93dae296b6be 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -17,10 +17,6 @@ #include <asm/pgtable.h> #include <asm/kexec.h> -/* This symbol is provided by the linker - let it fill in the paca - * field correctly */ -extern unsigned long __toc_start; - #ifdef CONFIG_PPC_BOOK3S /* @@ -149,11 +145,6 @@ EXPORT_SYMBOL(paca); void __init initialise_paca(struct paca_struct *new_paca, int cpu) { - /* The TOC register (GPR2) points 32kB into the TOC, so that 64kB - * of the TOC can be addressed using a single machine instruction. - */ - unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL; - #ifdef CONFIG_PPC_BOOK3S new_paca->lppaca_ptr = new_lppaca(cpu); #else @@ -161,7 +152,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) #endif new_paca->lock_token = 0x8000; new_paca->paca_index = cpu; - new_paca->kernel_toc = kernel_toc; + new_paca->kernel_toc = kernel_toc_addr(); new_paca->kernelbase = (unsigned long) _stext; /* Only set MSR:IR/DR when MMU is initialized */ new_paca->kernel_msr = MSR_KERNEL & ~(MSR_IR | MSR_DR); diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c index 7f9ed0c1f6b9..59c436189f46 100644 --- a/arch/powerpc/kernel/pci-hotplug.c +++ b/arch/powerpc/kernel/pci-hotplug.c @@ -55,7 +55,7 @@ void pcibios_remove_pci_devices(struct pci_bus *bus) pr_debug("PCI: Removing devices on bus %04x:%02x\n", pci_domain_nr(bus), bus->number); - list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) { + list_for_each_entry_safe_reverse(dev, tmp, &bus->devices, bus_list) { pr_debug(" Removing %s...\n", pci_name(dev)); pci_stop_and_remove_bus_device(dev); } diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index b3b4df91b792..38102cb9baa9 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -139,6 +139,7 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev) #ifdef CONFIG_PCI_IOV static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent, struct pci_dev *pdev, + int vf_index, int busno, int devfn) { struct pci_dn *pdn; @@ -158,6 +159,7 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent, pdn->busno = busno; pdn->devfn = devfn; #ifdef CONFIG_PPC_POWERNV + pdn->vf_index = vf_index; pdn->pe_number = IODA_INVALID_PE; #endif INIT_LIST_HEAD(&pdn->child_list); @@ -179,6 +181,7 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) { #ifdef CONFIG_PCI_IOV struct pci_dn *parent, *pdn; + struct eeh_dev *edev; int i; /* Only support IOV for now */ @@ -196,7 +199,7 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) return NULL; for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) { - pdn = add_one_dev_pci_data(parent, NULL, + pdn = add_one_dev_pci_data(parent, NULL, i, pci_iov_virtfn_bus(pdev, i), pci_iov_virtfn_devfn(pdev, i)); if (!pdn) { @@ -204,6 +207,12 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) __func__, i); return NULL; } + + /* Create the EEH device for the VF */ + eeh_dev_init(pdn, pci_bus_to_host(pdev->bus)); + edev = pdn_to_eeh_dev(pdn); + BUG_ON(!edev); + edev->physfn = pdev; } #endif /* CONFIG_PCI_IOV */ @@ -215,6 +224,7 @@ void remove_dev_pci_data(struct pci_dev *pdev) #ifdef CONFIG_PCI_IOV struct pci_dn *parent; struct pci_dn *pdn, *tmp; + struct eeh_dev *edev; int i; /* @@ -256,6 +266,13 @@ void remove_dev_pci_data(struct pci_dev *pdev) pdn->devfn != pci_iov_virtfn_devfn(pdev, i)) continue; + /* Release EEH device for the VF */ + edev = pdn_to_eeh_dev(pdn); + if (edev) { + pdn->edev = NULL; + kfree(edev); + } + if (!list_empty(&pdn->list)) list_del(&pdn->list); diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index e46b06822bea..ba21be15310f 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -6,8 +6,8 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) -CFLAGS_REMOVE_code-patching.o = -pg -CFLAGS_REMOVE_feature-fixups.o = -pg +CFLAGS_REMOVE_code-patching.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE) obj-y += string.o alloc.o crtsavres.o ppc_ksyms.o code-patching.o \ feature-fixups.o diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index d1e65ce545b3..97a1d40d8696 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -651,7 +651,7 @@ static void pmao_restore_workaround(bool ebb) /* * We are already soft-disabled in power_pmu_enable(). We need to hard - * enable to actually prevent the PMU exception from firing. + * disable to actually prevent the PMU exception from firing. */ hard_irq_disable(); diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 9f9dfda9ed2c..59012e750abe 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -27,20 +27,6 @@ #include "hv-24x7-catalog.h" #include "hv-common.h" -static const char *event_domain_suffix(unsigned domain) -{ - switch (domain) { -#define DOMAIN(n, v, x, c) \ - case HV_PERF_DOMAIN_##n: \ - return "__" #n; -#include "hv-24x7-domains.h" -#undef DOMAIN - default: - WARN(1, "unknown domain %d\n", domain); - return "__UNKNOWN_DOMAIN_SUFFIX"; - } -} - static bool domain_is_valid(unsigned domain) { switch (domain) { @@ -68,6 +54,24 @@ static bool is_physical_domain(unsigned domain) } } +static const char *domain_name(unsigned domain) +{ + if (!domain_is_valid(domain)) + return NULL; + + switch (domain) { + case HV_PERF_DOMAIN_PHYS_CHIP: return "Physical Chip"; + case HV_PERF_DOMAIN_PHYS_CORE: return "Physical Core"; + case HV_PERF_DOMAIN_VCPU_HOME_CORE: return "VCPU Home Core"; + case HV_PERF_DOMAIN_VCPU_HOME_CHIP: return "VCPU Home Chip"; + case HV_PERF_DOMAIN_VCPU_HOME_NODE: return "VCPU Home Node"; + case HV_PERF_DOMAIN_VCPU_REMOTE_NODE: return "VCPU Remote Node"; + } + + WARN_ON_ONCE(domain); + return NULL; +} + static bool catalog_entry_domain_is_valid(unsigned domain) { return is_physical_domain(domain); @@ -101,6 +105,7 @@ static bool catalog_entry_domain_is_valid(unsigned domain) EVENT_DEFINE_RANGE_FORMAT(domain, config, 0, 3); /* u16 */ EVENT_DEFINE_RANGE_FORMAT(core, config, 16, 31); +EVENT_DEFINE_RANGE_FORMAT(chip, config, 16, 31); EVENT_DEFINE_RANGE_FORMAT(vcpu, config, 16, 31); /* u32, see "data_offset" */ EVENT_DEFINE_RANGE_FORMAT(offset, config, 32, 63); @@ -115,6 +120,7 @@ static struct attribute *format_attrs[] = { &format_attr_domain.attr, &format_attr_offset.attr, &format_attr_core.attr, + &format_attr_chip.attr, &format_attr_vcpu.attr, &format_attr_lpar.attr, NULL, @@ -274,32 +280,70 @@ static unsigned long h_get_24x7_catalog_page(char page[], version, index); } -static unsigned core_domains[] = { - HV_PERF_DOMAIN_PHYS_CORE, - HV_PERF_DOMAIN_VCPU_HOME_CORE, - HV_PERF_DOMAIN_VCPU_HOME_CHIP, - HV_PERF_DOMAIN_VCPU_HOME_NODE, - HV_PERF_DOMAIN_VCPU_REMOTE_NODE, -}; -/* chip event data always yeilds a single event, core yeilds multiple */ -#define MAX_EVENTS_PER_EVENT_DATA ARRAY_SIZE(core_domains) - +/* + * Each event we find in the catalog, will have a sysfs entry. Format the + * data for this sysfs entry based on the event's domain. + * + * Events belonging to the Chip domain can only be monitored in that domain. + * i.e the domain for these events is a fixed/knwon value. + * + * Events belonging to the Core domain can be monitored either in the physical + * core or in one of the virtual CPU domains. So the domain value for these + * events must be specified by the user (i.e is a required parameter). Format + * the Core events with 'domain=?' so the perf-tool can error check required + * parameters. + * + * NOTE: For the Core domain events, rather than making domain a required + * parameter we could default it to PHYS_CORE and allowe users to + * override the domain to one of the VCPU domains. + * + * However, this can make the interface a little inconsistent. + * + * If we set domain=2 (PHYS_CHIP) and allow user to override this field + * the user may be tempted to also modify the "offset=x" field in which + * can lead to confusing usage. Consider the HPM_PCYC (offset=0x18) and + * HPM_INST (offset=0x20) events. With: + * + * perf stat -e hv_24x7/HPM_PCYC,offset=0x20/ + * + * we end up monitoring HPM_INST, while the command line has HPM_PCYC. + * + * By not assigning a default value to the domain for the Core events, + * we can have simple guidelines: + * + * - Specifying values for parameters with "=?" is required. + * + * - Specifying (i.e overriding) values for other parameters + * is undefined. + */ static char *event_fmt(struct hv_24x7_event_data *event, unsigned domain) { const char *sindex; const char *lpar; + const char *domain_str; + char buf[8]; - if (is_physical_domain(domain)) { + switch (domain) { + case HV_PERF_DOMAIN_PHYS_CHIP: + snprintf(buf, sizeof(buf), "%d", domain); + domain_str = buf; + lpar = "0x0"; + sindex = "chip"; + break; + case HV_PERF_DOMAIN_PHYS_CORE: + domain_str = "?"; lpar = "0x0"; sindex = "core"; - } else { + break; + default: + domain_str = "?"; lpar = "?"; sindex = "vcpu"; } return kasprintf(GFP_KERNEL, - "domain=0x%x,offset=0x%x,%s=?,lpar=%s", - domain, + "domain=%s,offset=0x%x,%s=?,lpar=%s", + domain_str, be16_to_cpu(event->event_counter_offs) + be16_to_cpu(event->event_group_record_offs), sindex, @@ -339,6 +383,15 @@ static struct attribute *device_str_attr_create_(char *name, char *str) return &attr->attr.attr; } +/* + * Allocate and initialize strings representing event attributes. + * + * NOTE: The strings allocated here are never destroyed and continue to + * exist till shutdown. This is to allow us to create as many events + * from the catalog as possible, even if we encounter errors with some. + * In case of changes to error paths in future, these may need to be + * freed by the caller. + */ static struct attribute *device_str_attr_create(char *name, int name_max, int name_nonce, char *str, size_t str_max) @@ -370,16 +423,6 @@ out_s: return NULL; } -static void device_str_attr_destroy(struct attribute *attr) -{ - struct dev_ext_attribute *d; - - d = container_of(attr, struct dev_ext_attribute, attr.attr); - kfree(d->var); - kfree(d->attr.attr.name); - kfree(d); -} - static struct attribute *event_to_attr(unsigned ix, struct hv_24x7_event_data *event, unsigned domain, @@ -387,7 +430,6 @@ static struct attribute *event_to_attr(unsigned ix, { int event_name_len; char *ev_name, *a_ev_name, *val; - const char *ev_suffix; struct attribute *attr; if (!domain_is_valid(domain)) { @@ -400,14 +442,13 @@ static struct attribute *event_to_attr(unsigned ix, if (!val) return NULL; - ev_suffix = event_domain_suffix(domain); ev_name = event_name(event, &event_name_len); if (!nonce) - a_ev_name = kasprintf(GFP_KERNEL, "%.*s%s", - (int)event_name_len, ev_name, ev_suffix); + a_ev_name = kasprintf(GFP_KERNEL, "%.*s", + (int)event_name_len, ev_name); else - a_ev_name = kasprintf(GFP_KERNEL, "%.*s%s__%d", - (int)event_name_len, ev_name, ev_suffix, nonce); + a_ev_name = kasprintf(GFP_KERNEL, "%.*s__%d", + (int)event_name_len, ev_name, nonce); if (!a_ev_name) goto out_val; @@ -452,45 +493,14 @@ event_to_long_desc_attr(struct hv_24x7_event_data *event, int nonce) return device_str_attr_create(name, nl, nonce, desc, dl); } -static ssize_t event_data_to_attrs(unsigned ix, struct attribute **attrs, +static int event_data_to_attrs(unsigned ix, struct attribute **attrs, struct hv_24x7_event_data *event, int nonce) { - unsigned i; - - switch (event->domain) { - case HV_PERF_DOMAIN_PHYS_CHIP: - *attrs = event_to_attr(ix, event, event->domain, nonce); - return 1; - case HV_PERF_DOMAIN_PHYS_CORE: - for (i = 0; i < ARRAY_SIZE(core_domains); i++) { - attrs[i] = event_to_attr(ix, event, core_domains[i], - nonce); - if (!attrs[i]) { - pr_warn("catalog event %u: individual attr %u " - "creation failure\n", ix, i); - for (; i; i--) - device_str_attr_destroy(attrs[i - 1]); - return -1; - } - } - return i; - default: - pr_warn("catalog event %u: domain %u is not allowed in the " - "catalog\n", ix, event->domain); + *attrs = event_to_attr(ix, event, event->domain, nonce); + if (!*attrs) return -1; - } -} -static size_t event_to_attr_ct(struct hv_24x7_event_data *event) -{ - switch (event->domain) { - case HV_PERF_DOMAIN_PHYS_CHIP: - return 1; - case HV_PERF_DOMAIN_PHYS_CORE: - return ARRAY_SIZE(core_domains); - default: - return 0; - } + return 0; } static unsigned long vmalloc_to_phys(void *v) @@ -726,9 +736,8 @@ static int create_events_from_catalog(struct attribute ***events_, goto e_free; } - if (SIZE_MAX / MAX_EVENTS_PER_EVENT_DATA - 1 < event_entry_count) { - pr_err("event_entry_count %zu is invalid\n", - event_entry_count); + if (SIZE_MAX - 1 < event_entry_count) { + pr_err("event_entry_count %zu is invalid\n", event_entry_count); ret = -EIO; goto e_free; } @@ -801,7 +810,7 @@ static int create_events_from_catalog(struct attribute ***events_, continue; } - attr_max += event_to_attr_ct(event); + attr_max++; } event_idx_last = event_idx; @@ -851,12 +860,12 @@ static int create_events_from_catalog(struct attribute ***events_, nonce = event_uniq_add(&ev_uniq, name, nl, event->domain); ct = event_data_to_attrs(event_idx, events + event_attr_ct, event, nonce); - if (ct <= 0) { + if (ct < 0) { pr_warn("event %zu (%.*s) creation failure, skipping\n", event_idx, nl, name); junk_events++; } else { - event_attr_ct += ct; + event_attr_ct++; event_descs[desc_ct] = event_to_desc_attr(event, nonce); if (event_descs[desc_ct]) desc_ct++; @@ -961,6 +970,27 @@ e_free: return ret; } +static ssize_t domains_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + int d, n, count = 0; + const char *str; + + for (d = 0; d < HV_PERF_DOMAIN_MAX; d++) { + str = domain_name(d); + if (!str) + continue; + + n = sprintf(page, "%d: %s\n", d, str); + if (n < 0) + break; + + count += n; + page += n; + } + return count; +} + #define PAGE_0_ATTR(_name, _fmt, _expr) \ static ssize_t _name##_show(struct device *dev, \ struct device_attribute *dev_attr, \ @@ -989,6 +1019,7 @@ PAGE_0_ATTR(catalog_version, "%lld\n", PAGE_0_ATTR(catalog_len, "%lld\n", (unsigned long long)be32_to_cpu(page_0->length) * 4096); static BIN_ATTR_RO(catalog, 0/* real length varies */); +static DEVICE_ATTR_RO(domains); static struct bin_attribute *if_bin_attrs[] = { &bin_attr_catalog, @@ -998,6 +1029,7 @@ static struct bin_attribute *if_bin_attrs[] = { static struct attribute *if_attrs[] = { &dev_attr_catalog_len.attr, &dev_attr_catalog_version.attr, + &dev_attr_domains.attr, NULL, }; @@ -1089,10 +1121,16 @@ static int add_event_to_24x7_request(struct perf_event *event, return -EINVAL; } - if (is_physical_domain(event_get_domain(event))) + switch (event_get_domain(event)) { + case HV_PERF_DOMAIN_PHYS_CHIP: + idx = event_get_chip(event); + break; + case HV_PERF_DOMAIN_PHYS_CORE: idx = event_get_core(event); - else + break; + default: idx = event_get_vcpu(event); + } i = request_buffer->num_requests++; req = &request_buffer->requests[i]; @@ -1208,11 +1246,12 @@ static int h_24x7_event_init(struct perf_event *event) return -EACCES; } - /* see if the event complains */ + /* Get the initial value of the counter for this event */ if (single_24x7_request(event, &ct)) { pr_devel("test hcall failed\n"); return -EIO; } + (void)local64_xchg(&event->hw.prev_count, ct); return 0; } @@ -1275,6 +1314,16 @@ static void h_24x7_event_read(struct perf_event *event) h24x7hw = &get_cpu_var(hv_24x7_hw); h24x7hw->events[i] = event; put_cpu_var(h24x7hw); + /* + * Clear the event count so we can compute the _change_ + * in the 24x7 raw counter value at the end of the txn. + * + * Note that we could alternatively read the 24x7 value + * now and save its value in event->hw.prev_count. But + * that would require issuing a hcall, which would then + * defeat the purpose of using the txn interface. + */ + local64_set(&event->count, 0); } put_cpu_var(hv_24x7_reqb); diff --git a/arch/powerpc/perf/hv-24x7.h b/arch/powerpc/perf/hv-24x7.h index c57d67dc9f3f..791455e7f5cf 100644 --- a/arch/powerpc/perf/hv-24x7.h +++ b/arch/powerpc/perf/hv-24x7.h @@ -7,6 +7,7 @@ enum hv_perf_domains { #define DOMAIN(n, v, x, c) HV_PERF_DOMAIN_##n = v, #include "hv-24x7-domains.h" #undef DOMAIN + HV_PERF_DOMAIN_MAX, }; struct hv_24x7_request { diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index 5b62f2389290..a383c23a9070 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -54,7 +54,7 @@ * Power7 event codes. */ #define EVENT(_name, _code) \ - PME_##_name = _code, + _name = _code, enum { #include "power7-events-list.h" @@ -318,14 +318,14 @@ static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[]) } static int power7_generic_events[] = { - [PERF_COUNT_HW_CPU_CYCLES] = PME_PM_CYC, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = PME_PM_GCT_NOSLOT_CYC, - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = PME_PM_CMPLU_STALL, - [PERF_COUNT_HW_INSTRUCTIONS] = PME_PM_INST_CMPL, - [PERF_COUNT_HW_CACHE_REFERENCES] = PME_PM_LD_REF_L1, - [PERF_COUNT_HW_CACHE_MISSES] = PME_PM_LD_MISS_L1, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PME_PM_BRU_FIN, - [PERF_COUNT_HW_BRANCH_MISSES] = PME_PM_BR_MPRED, + [PERF_COUNT_HW_CPU_CYCLES] = PM_CYC, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = PM_GCT_NOSLOT_CYC, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = PM_CMPLU_STALL, + [PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_CMPL, + [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1, + [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BRU_FIN, + [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED, }; #define C(x) PERF_COUNT_HW_CACHE_##x diff --git a/arch/powerpc/perf/power8-events-list.h b/arch/powerpc/perf/power8-events-list.h new file mode 100644 index 000000000000..741b77edd03e --- /dev/null +++ b/arch/powerpc/perf/power8-events-list.h @@ -0,0 +1,51 @@ +/* + * Performance counter support for POWER8 processors. + * + * Copyright 2014 Sukadev Bhattiprolu, 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. + */ + +/* + * Power8 event codes. + */ +EVENT(PM_CYC, 0x0001e) +EVENT(PM_GCT_NOSLOT_CYC, 0x100f8) +EVENT(PM_CMPLU_STALL, 0x4000a) +EVENT(PM_INST_CMPL, 0x00002) +EVENT(PM_BRU_FIN, 0x10068) +EVENT(PM_BR_MPRED_CMPL, 0x400f6) + +/* All L1 D cache load references counted at finish, gated by reject */ +EVENT(PM_LD_REF_L1, 0x100ee) +/* Load Missed L1 */ +EVENT(PM_LD_MISS_L1, 0x3e054) +/* Store Missed L1 */ +EVENT(PM_ST_MISS_L1, 0x300f0) +/* L1 cache data prefetches */ +EVENT(PM_L1_PREF, 0x0d8b8) +/* Instruction fetches from L1 */ +EVENT(PM_INST_FROM_L1, 0x04080) +/* Demand iCache Miss */ +EVENT(PM_L1_ICACHE_MISS, 0x200fd) +/* Instruction Demand sectors wriittent into IL1 */ +EVENT(PM_L1_DEMAND_WRITE, 0x0408c) +/* Instruction prefetch written into IL1 */ +EVENT(PM_IC_PREF_WRITE, 0x0408e) +/* The data cache was reloaded from local core's L3 due to a demand load */ +EVENT(PM_DATA_FROM_L3, 0x4c042) +/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */ +EVENT(PM_DATA_FROM_L3MISS, 0x300fe) +/* All successful D-side store dispatches for this thread */ +EVENT(PM_L2_ST, 0x17080) +/* All successful D-side store dispatches for this thread that were L2 Miss */ +EVENT(PM_L2_ST_MISS, 0x17082) +/* Total HW L3 prefetches(Load+store) */ +EVENT(PM_L3_PREF_ALL, 0x4e052) +/* Data PTEG reload */ +EVENT(PM_DTLB_MISS, 0x300fc) +/* ITLB Reloaded */ +EVENT(PM_ITLB_MISS, 0x400fc) diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index be9b7aec216f..690d9186a855 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -17,48 +17,16 @@ #include <asm/firmware.h> #include <asm/cputable.h> - /* * Some power8 event codes. */ -#define PM_CYC 0x0001e -#define PM_GCT_NOSLOT_CYC 0x100f8 -#define PM_CMPLU_STALL 0x4000a -#define PM_INST_CMPL 0x00002 -#define PM_BRU_FIN 0x10068 -#define PM_BR_MPRED_CMPL 0x400f6 - -/* All L1 D cache load references counted at finish, gated by reject */ -#define PM_LD_REF_L1 0x100ee -/* Load Missed L1 */ -#define PM_LD_MISS_L1 0x3e054 -/* Store Missed L1 */ -#define PM_ST_MISS_L1 0x300f0 -/* L1 cache data prefetches */ -#define PM_L1_PREF 0x0d8b8 -/* Instruction fetches from L1 */ -#define PM_INST_FROM_L1 0x04080 -/* Demand iCache Miss */ -#define PM_L1_ICACHE_MISS 0x200fd -/* Instruction Demand sectors wriittent into IL1 */ -#define PM_L1_DEMAND_WRITE 0x0408c -/* Instruction prefetch written into IL1 */ -#define PM_IC_PREF_WRITE 0x0408e -/* The data cache was reloaded from local core's L3 due to a demand load */ -#define PM_DATA_FROM_L3 0x4c042 -/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */ -#define PM_DATA_FROM_L3MISS 0x300fe -/* All successful D-side store dispatches for this thread */ -#define PM_L2_ST 0x17080 -/* All successful D-side store dispatches for this thread that were L2 Miss */ -#define PM_L2_ST_MISS 0x17082 -/* Total HW L3 prefetches(Load+store) */ -#define PM_L3_PREF_ALL 0x4e052 -/* Data PTEG reload */ -#define PM_DTLB_MISS 0x300fc -/* ITLB Reloaded */ -#define PM_ITLB_MISS 0x400fc +#define EVENT(_name, _code) _name = _code, + +enum { +#include "power8-events-list.h" +}; +#undef EVENT /* * Raw event encoding for POWER8: @@ -604,6 +572,71 @@ static void power8_disable_pmc(unsigned int pmc, unsigned long mmcr[]) mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SHIFT(pmc + 1)); } +GENERIC_EVENT_ATTR(cpu-cycles, PM_CYC); +GENERIC_EVENT_ATTR(stalled-cycles-frontend, PM_GCT_NOSLOT_CYC); +GENERIC_EVENT_ATTR(stalled-cycles-backend, PM_CMPLU_STALL); +GENERIC_EVENT_ATTR(instructions, PM_INST_CMPL); +GENERIC_EVENT_ATTR(branch-instructions, PM_BRU_FIN); +GENERIC_EVENT_ATTR(branch-misses, PM_BR_MPRED_CMPL); +GENERIC_EVENT_ATTR(cache-references, PM_LD_REF_L1); +GENERIC_EVENT_ATTR(cache-misses, PM_LD_MISS_L1); + +CACHE_EVENT_ATTR(L1-dcache-load-misses, PM_LD_MISS_L1); +CACHE_EVENT_ATTR(L1-dcache-loads, PM_LD_REF_L1); + +CACHE_EVENT_ATTR(L1-dcache-prefetches, PM_L1_PREF); +CACHE_EVENT_ATTR(L1-dcache-store-misses, PM_ST_MISS_L1); +CACHE_EVENT_ATTR(L1-icache-load-misses, PM_L1_ICACHE_MISS); +CACHE_EVENT_ATTR(L1-icache-loads, PM_INST_FROM_L1); +CACHE_EVENT_ATTR(L1-icache-prefetches, PM_IC_PREF_WRITE); + +CACHE_EVENT_ATTR(LLC-load-misses, PM_DATA_FROM_L3MISS); +CACHE_EVENT_ATTR(LLC-loads, PM_DATA_FROM_L3); +CACHE_EVENT_ATTR(LLC-prefetches, PM_L3_PREF_ALL); +CACHE_EVENT_ATTR(LLC-store-misses, PM_L2_ST_MISS); +CACHE_EVENT_ATTR(LLC-stores, PM_L2_ST); + +CACHE_EVENT_ATTR(branch-load-misses, PM_BR_MPRED_CMPL); +CACHE_EVENT_ATTR(branch-loads, PM_BRU_FIN); +CACHE_EVENT_ATTR(dTLB-load-misses, PM_DTLB_MISS); +CACHE_EVENT_ATTR(iTLB-load-misses, PM_ITLB_MISS); + +static struct attribute *power8_events_attr[] = { + GENERIC_EVENT_PTR(PM_CYC), + GENERIC_EVENT_PTR(PM_GCT_NOSLOT_CYC), + GENERIC_EVENT_PTR(PM_CMPLU_STALL), + GENERIC_EVENT_PTR(PM_INST_CMPL), + GENERIC_EVENT_PTR(PM_BRU_FIN), + GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL), + GENERIC_EVENT_PTR(PM_LD_REF_L1), + GENERIC_EVENT_PTR(PM_LD_MISS_L1), + + CACHE_EVENT_PTR(PM_LD_MISS_L1), + CACHE_EVENT_PTR(PM_LD_REF_L1), + CACHE_EVENT_PTR(PM_L1_PREF), + CACHE_EVENT_PTR(PM_ST_MISS_L1), + CACHE_EVENT_PTR(PM_L1_ICACHE_MISS), + CACHE_EVENT_PTR(PM_INST_FROM_L1), + CACHE_EVENT_PTR(PM_IC_PREF_WRITE), + CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS), + CACHE_EVENT_PTR(PM_DATA_FROM_L3), + CACHE_EVENT_PTR(PM_L3_PREF_ALL), + CACHE_EVENT_PTR(PM_L2_ST_MISS), + CACHE_EVENT_PTR(PM_L2_ST), + + CACHE_EVENT_PTR(PM_BR_MPRED_CMPL), + CACHE_EVENT_PTR(PM_BRU_FIN), + + CACHE_EVENT_PTR(PM_DTLB_MISS), + CACHE_EVENT_PTR(PM_ITLB_MISS), + NULL +}; + +static struct attribute_group power8_pmu_events_group = { + .name = "events", + .attrs = power8_events_attr, +}; + PMU_FORMAT_ATTR(event, "config:0-49"); PMU_FORMAT_ATTR(pmcxsel, "config:0-7"); PMU_FORMAT_ATTR(mark, "config:8"); @@ -640,6 +673,7 @@ struct attribute_group power8_pmu_format_group = { static const struct attribute_group *power8_pmu_attr_groups[] = { &power8_pmu_format_group, + &power8_pmu_events_group, NULL, }; diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile index 52c6ce1cc985..1eb7b45e017d 100644 --- a/arch/powerpc/platforms/powermac/Makefile +++ b/arch/powerpc/platforms/powermac/Makefile @@ -2,7 +2,7 @@ CFLAGS_bootx_init.o += -fPIC ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code -CFLAGS_REMOVE_bootx_init.o = -pg -mno-sched-epilog +CFLAGS_REMOVE_bootx_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) endif obj-y += pic.o setup.o time.o feature.o pci.o \ diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 811917219bf1..950b3e539057 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -371,6 +371,7 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) edev->mode &= 0xFFFFFF00; edev->pcix_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_PCIX); edev->pcie_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_EXP); + edev->af_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_AF); edev->aer_cap = pnv_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR); if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; @@ -879,6 +880,120 @@ void pnv_pci_reset_secondary_bus(struct pci_dev *dev) } } +static void pnv_eeh_wait_for_pending(struct pci_dn *pdn, const char *type, + int pos, u16 mask) +{ + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + int i, status = 0; + + /* Wait for Transaction Pending bit to be cleared */ + for (i = 0; i < 4; i++) { + eeh_ops->read_config(pdn, pos, 2, &status); + if (!(status & mask)) + return; + + msleep((1 << i) * 100); + } + + pr_warn("%s: Pending transaction while issuing %sFLR to %04x:%02x:%02x.%01x\n", + __func__, type, + edev->phb->global_number, pdn->busno, + PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); +} + +static int pnv_eeh_do_flr(struct pci_dn *pdn, int option) +{ + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + u32 reg = 0; + + if (WARN_ON(!edev->pcie_cap)) + return -ENOTTY; + + eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP, 4, ®); + if (!(reg & PCI_EXP_DEVCAP_FLR)) + return -ENOTTY; + + switch (option) { + case EEH_RESET_HOT: + case EEH_RESET_FUNDAMENTAL: + pnv_eeh_wait_for_pending(pdn, "", + edev->pcie_cap + PCI_EXP_DEVSTA, + PCI_EXP_DEVSTA_TRPND); + eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 4, ®); + reg |= PCI_EXP_DEVCTL_BCR_FLR; + eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 4, reg); + msleep(EEH_PE_RST_HOLD_TIME); + break; + case EEH_RESET_DEACTIVATE: + eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 4, ®); + reg &= ~PCI_EXP_DEVCTL_BCR_FLR; + eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 4, reg); + msleep(EEH_PE_RST_SETTLE_TIME); + break; + } + + return 0; +} + +static int pnv_eeh_do_af_flr(struct pci_dn *pdn, int option) +{ + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + u32 cap = 0; + + if (WARN_ON(!edev->af_cap)) + return -ENOTTY; + + eeh_ops->read_config(pdn, edev->af_cap + PCI_AF_CAP, 1, &cap); + if (!(cap & PCI_AF_CAP_TP) || !(cap & PCI_AF_CAP_FLR)) + return -ENOTTY; + + switch (option) { + case EEH_RESET_HOT: + case EEH_RESET_FUNDAMENTAL: + /* + * Wait for Transaction Pending bit to clear. A word-aligned + * test is used, so we use the conrol offset rather than status + * and shift the test bit to match. + */ + pnv_eeh_wait_for_pending(pdn, "AF", + edev->af_cap + PCI_AF_CTRL, + PCI_AF_STATUS_TP << 8); + eeh_ops->write_config(pdn, edev->af_cap + PCI_AF_CTRL, + 1, PCI_AF_CTRL_FLR); + msleep(EEH_PE_RST_HOLD_TIME); + break; + case EEH_RESET_DEACTIVATE: + eeh_ops->write_config(pdn, edev->af_cap + PCI_AF_CTRL, 1, 0); + msleep(EEH_PE_RST_SETTLE_TIME); + break; + } + + return 0; +} + +static int pnv_eeh_reset_vf_pe(struct eeh_pe *pe, int option) +{ + struct eeh_dev *edev; + struct pci_dn *pdn; + int ret; + + /* The VF PE should have only one child device */ + edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, list); + pdn = eeh_dev_to_pdn(edev); + if (!pdn) + return -ENXIO; + + ret = pnv_eeh_do_flr(pdn, option); + if (!ret) + return ret; + + return pnv_eeh_do_af_flr(pdn, option); +} + /** * pnv_eeh_reset - Reset the specified PE * @pe: EEH PE @@ -940,7 +1055,9 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option) } bus = eeh_pe_bus_get(pe); - if (pci_is_root_bus(bus) || + if (pe->type & EEH_PE_VF) + ret = pnv_eeh_reset_vf_pe(pe, option); + else if (pci_is_root_bus(bus) || pci_is_root_bus(bus->parent)) ret = pnv_eeh_root_reset(hose, option); else @@ -1079,6 +1196,14 @@ static inline bool pnv_eeh_cfg_blocked(struct pci_dn *pdn) if (!edev || !edev->pe) return false; + /* + * We will issue FLR or AF FLR to all VFs, which are contained + * in VF PE. It relies on the EEH PCI config accessors. So we + * can't block them during the window. + */ + if (edev->physfn && (edev->pe->state & EEH_PE_RESET)) + return false; + if (edev->pe->state & EEH_PE_CFG_BLOCKED) return true; @@ -1463,6 +1588,65 @@ static int pnv_eeh_next_error(struct eeh_pe **pe) return ret; } +static int pnv_eeh_restore_vf_config(struct pci_dn *pdn) +{ + struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + u32 devctl, cmd, cap2, aer_capctl; + int old_mps; + + if (edev->pcie_cap) { + /* Restore MPS */ + old_mps = (ffs(pdn->mps) - 8) << 5; + eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 2, &devctl); + devctl &= ~PCI_EXP_DEVCTL_PAYLOAD; + devctl |= old_mps; + eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 2, devctl); + + /* Disable Completion Timeout */ + eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP2, + 4, &cap2); + if (cap2 & 0x10) { + eeh_ops->read_config(pdn, + edev->pcie_cap + PCI_EXP_DEVCTL2, + 4, &cap2); + cap2 |= 0x10; + eeh_ops->write_config(pdn, + edev->pcie_cap + PCI_EXP_DEVCTL2, + 4, cap2); + } + } + + /* Enable SERR and parity checking */ + eeh_ops->read_config(pdn, PCI_COMMAND, 2, &cmd); + cmd |= (PCI_COMMAND_PARITY | PCI_COMMAND_SERR); + eeh_ops->write_config(pdn, PCI_COMMAND, 2, cmd); + + /* Enable report various errors */ + if (edev->pcie_cap) { + eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 2, &devctl); + devctl &= ~PCI_EXP_DEVCTL_CERE; + devctl |= (PCI_EXP_DEVCTL_NFERE | + PCI_EXP_DEVCTL_FERE | + PCI_EXP_DEVCTL_URRE); + eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + 2, devctl); + } + + /* Enable ECRC generation and check */ + if (edev->pcie_cap && edev->aer_cap) { + eeh_ops->read_config(pdn, edev->aer_cap + PCI_ERR_CAP, + 4, &aer_capctl); + aer_capctl |= (PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE); + eeh_ops->write_config(pdn, edev->aer_cap + PCI_ERR_CAP, + 4, aer_capctl); + } + + return 0; +} + static int pnv_eeh_restore_config(struct pci_dn *pdn) { struct eeh_dev *edev = pdn_to_eeh_dev(pdn); @@ -1472,9 +1656,21 @@ static int pnv_eeh_restore_config(struct pci_dn *pdn) if (!edev) return -EEXIST; - phb = edev->phb->private_data; - ret = opal_pci_reinit(phb->opal_id, - OPAL_REINIT_PCI_DEV, edev->config_addr); + /* + * We have to restore the PCI config space after reset since the + * firmware can't see SRIOV VFs. + * + * FIXME: The MPS, error routing rules, timeout setting are worthy + * to be exported by firmware in extendible way. + */ + if (edev->physfn) { + ret = pnv_eeh_restore_vf_config(pdn); + } else { + phb = edev->phb->private_data; + ret = opal_pci_reinit(phb->opal_id, + OPAL_REINIT_PCI_DEV, edev->config_addr); + } + if (ret) { pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n", __func__, edev->config_addr, ret); @@ -1503,6 +1699,40 @@ static struct eeh_ops pnv_eeh_ops = { .restore_config = pnv_eeh_restore_config }; +void pcibios_bus_add_device(struct pci_dev *pdev) +{ + struct pci_dn *pdn = pci_get_pdn(pdev); + + if (!pdev->is_virtfn) + return; + + /* + * The following operations will fail if VF's sysfs files + * aren't created or its resources aren't finalized. + */ + eeh_add_device_early(pdn); + eeh_add_device_late(pdev); + eeh_sysfs_add_device(pdev); +} + +#ifdef CONFIG_PCI_IOV +static void pnv_pci_fixup_vf_mps(struct pci_dev *pdev) +{ + struct pci_dn *pdn = pci_get_pdn(pdev); + int parent_mps; + + if (!pdev->is_virtfn) + return; + + /* Synchronize MPS for VF and PF */ + parent_mps = pcie_get_mps(pdev->physfn); + if ((128 << pdev->pcie_mpss) >= parent_mps) + pcie_set_mps(pdev, parent_mps); + pdn->mps = pcie_get_mps(pdev); +} +DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pnv_pci_fixup_vf_mps); +#endif /* CONFIG_PCI_IOV */ + /** * eeh_powernv_init - Register platform dependent EEH operations * diff --git a/arch/powerpc/scripts/gcc-check-mprofile-kernel.sh b/arch/powerpc/scripts/gcc-check-mprofile-kernel.sh new file mode 100755 index 000000000000..c658d8cf760b --- /dev/null +++ b/arch/powerpc/scripts/gcc-check-mprofile-kernel.sh @@ -0,0 +1,23 @@ +#!/bin/bash + +set -e +set -o pipefail + +# To debug, uncomment the following line +# set -x + +# Test whether the compile option -mprofile-kernel exists and generates +# profiling code (ie. a call to _mcount()). +echo "int func() { return 0; }" | \ + $* -S -x c -O2 -p -mprofile-kernel - -o - 2> /dev/null | \ + grep -q "_mcount" + +# Test whether the notrace attribute correctly suppresses calls to _mcount(). + +echo -e "#include <linux/compiler.h>\nnotrace int func() { return 0; }" | \ + $* -S -x c -O2 -p -mprofile-kernel - -o - 2> /dev/null | \ + grep -q "_mcount" && \ + exit 1 + +echo "OK" +exit 0 |