diff options
67 files changed, 634 insertions, 374 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 39d07c02f7d8..8af6a7d93148 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -197,7 +197,7 @@ config PPC select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_KERNEL_GZIP - select HAVE_KERNEL_XZ if PPC_BOOK3S + select HAVE_KERNEL_XZ if PPC_BOOK3S || 44x select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE select HAVE_KRETPROBES @@ -216,7 +216,7 @@ config PPC select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE if SMP select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_RELIABLE_STACKTRACE if PPC64 && CPU_LITTLE_ENDIAN + select HAVE_RELIABLE_STACKTRACE if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING select HAVE_IRQ_TIME_ACCOUNTING @@ -474,9 +474,6 @@ config ARCH_CPU_PROBE_RELEASE config ARCH_ENABLE_MEMORY_HOTPLUG def_bool y -config ARCH_HAS_WALK_MEMORY - def_bool y - config ARCH_ENABLE_MEMORY_HOTREMOVE def_bool y diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 488c9edffa58..ac033341ed55 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -213,9 +213,9 @@ endif asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1) KBUILD_CPPFLAGS += -Iarch/$(ARCH) $(asinstr) -KBUILD_AFLAGS += -Iarch/$(ARCH) $(AFLAGS-y) +KBUILD_AFLAGS += $(AFLAGS-y) KBUILD_CFLAGS += $(call cc-option,-msoft-float) -KBUILD_CFLAGS += -pipe -Iarch/$(ARCH) $(CFLAGS-y) +KBUILD_CFLAGS += -pipe $(CFLAGS-y) CPP = $(CC) -E $(KBUILD_CFLAGS) CHECKFLAGS += -m$(BITS) -D__powerpc__ -D__powerpc$(BITS)__ diff --git a/arch/powerpc/boot/dts/Makefile b/arch/powerpc/boot/dts/Makefile index fb335d05aae8..1cbc0e4ce857 100644 --- a/arch/powerpc/boot/dts/Makefile +++ b/arch/powerpc/boot/dts/Makefile @@ -4,3 +4,4 @@ subdir-y += fsl dtstree := $(srctree)/$(src) dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts)) +dtb-$(CONFIG_XILINX_VIRTEX440_GENERIC_BOARD) += virtex440-ml507.dtb virtex440-ml510.dtb diff --git a/arch/powerpc/boot/dts/wii.dts b/arch/powerpc/boot/dts/wii.dts index 104b1d6d5695..c406bdb4f36f 100644 --- a/arch/powerpc/boot/dts/wii.dts +++ b/arch/powerpc/boot/dts/wii.dts @@ -14,6 +14,7 @@ /dts-v1/; #include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/input/input.h> /* * This is commented-out for now. @@ -187,6 +188,11 @@ "DEBUG0", "DEBUG1", "DEBUG2", "DEBUG3", "DEBUG4", "DEBUG5", "DEBUG6", "DEBUG7"; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <10>; + interrupt-parent = <&PIC1>; + /* * This is commented out while a standard binding * for i2c over gpio is defined. @@ -235,5 +241,21 @@ panic-indicator; }; }; + + gpio-keys { + compatible = "gpio-keys"; + + power { + label = "Power Button"; + gpios = <&GPIO 0 GPIO_ACTIVE_HIGH>; + linux,code = <KEY_POWER>; + }; + + eject { + label = "Eject Button"; + gpios = <&GPIO 6 GPIO_ACTIVE_HIGH>; + linux,code = <KEY_EJECTCD>; + }; + }; }; diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 2e6ada28da64..404e0f48f3f3 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -811,7 +811,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, return hash__set_pte_at(mm, addr, ptep, pte, percpu); } -#define _PAGE_CACHE_CTL (_PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT) +#define _PAGE_CACHE_CTL (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT) #define pgprot_noncached pgprot_noncached static inline pgprot_t pgprot_noncached(pgprot_t prot) @@ -904,7 +904,7 @@ static inline int pud_none(pud_t pud) static inline int pud_present(pud_t pud) { - return (pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); } extern struct page *pud_page(pud_t pud); @@ -951,7 +951,7 @@ static inline int pgd_none(pgd_t pgd) static inline int pgd_present(pgd_t pgd) { - return (pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); + return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); } static inline pte_t pgd_pte(pgd_t pgd) @@ -1258,21 +1258,13 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, #define pmd_move_must_withdraw pmd_move_must_withdraw struct spinlock; -static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, - struct spinlock *old_pmd_ptl, - struct vm_area_struct *vma) -{ - if (radix_enabled()) - return false; - /* - * Archs like ppc64 use pgtable to store per pmd - * specific information. So when we switch the pmd, - * we should also withdraw and deposit the pgtable - */ - return true; -} - - +extern int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma); +/* + * Hash translation mode use the deposited table to store hash pte + * slot information. + */ #define arch_needs_pgtable_deposit arch_needs_pgtable_deposit static inline bool arch_needs_pgtable_deposit(void) { diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 671316f9e95d..05147cecb8df 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -13,8 +13,32 @@ static inline int mmu_get_ap(int psize) #ifdef CONFIG_PPC_RADIX_MMU extern void radix__tlbiel_all(unsigned int action); +extern void radix__flush_tlb_lpid_page(unsigned int lpid, + unsigned long addr, + unsigned long page_size); +extern void radix__flush_pwc_lpid(unsigned int lpid); +extern void radix__flush_tlb_lpid(unsigned int lpid); +extern void radix__local_flush_tlb_lpid_guest(unsigned int lpid); #else static inline void radix__tlbiel_all(unsigned int action) { WARN_ON(1); }; +static inline void radix__flush_tlb_lpid_page(unsigned int lpid, + unsigned long addr, + unsigned long page_size) +{ + WARN_ON(1); +} +static inline void radix__flush_pwc_lpid(unsigned int lpid) +{ + WARN_ON(1); +} +static inline void radix__flush_tlb_lpid(unsigned int lpid) +{ + WARN_ON(1); +} +static inline void radix__local_flush_tlb_lpid_guest(unsigned int lpid) +{ + WARN_ON(1); +} #endif extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, @@ -49,12 +73,6 @@ extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr); extern void radix__flush_tlb_all(void); -extern void radix__flush_tlb_lpid_page(unsigned int lpid, - unsigned long addr, - unsigned long page_size); -extern void radix__flush_pwc_lpid(unsigned int lpid); -extern void radix__flush_tlb_lpid(unsigned int lpid); extern void radix__local_flush_tlb_lpid(unsigned int lpid); -extern void radix__local_flush_tlb_lpid_guest(unsigned int lpid); #endif diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 8b596d096ebe..0b655810f32d 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -293,14 +293,14 @@ void eeh_add_device_late(struct pci_dev *); void eeh_add_device_tree_late(struct pci_bus *); void eeh_add_sysfs_files(struct pci_bus *); void eeh_remove_device(struct pci_dev *); -int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state); +int eeh_unfreeze_pe(struct eeh_pe *pe); int eeh_pe_reset_and_recover(struct eeh_pe *pe); int eeh_dev_open(struct pci_dev *pdev); void eeh_dev_release(struct pci_dev *pdev); struct eeh_pe *eeh_iommu_group_to_pe(struct iommu_group *group); int eeh_pe_set_option(struct eeh_pe *pe, int option); int eeh_pe_get_state(struct eeh_pe *pe); -int eeh_pe_reset(struct eeh_pe *pe, int option); +int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed); int eeh_pe_configure(struct eeh_pe *pe); int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func, unsigned long addr, unsigned long mask); diff --git a/arch/powerpc/include/asm/hvsi.h b/arch/powerpc/include/asm/hvsi.h index 3fdc54df63c9..464a7519ed64 100644 --- a/arch/powerpc/include/asm/hvsi.h +++ b/arch/powerpc/include/asm/hvsi.h @@ -64,7 +64,7 @@ struct hvsi_priv { unsigned int inbuf_len; /* data in input buffer */ unsigned char inbuf[HVSI_INBUF_SIZE]; unsigned int inbuf_cur; /* Cursor in input buffer */ - unsigned int inbuf_pktlen; /* packet lenght from cursor */ + unsigned int inbuf_pktlen; /* packet length from cursor */ atomic_t seqno; /* packet sequence number */ unsigned int opened:1; /* driver opened */ unsigned int established:1; /* protocol established */ diff --git a/arch/powerpc/include/asm/ipic.h b/arch/powerpc/include/asm/ipic.h index 3dbd47f2bffe..abad50a745db 100644 --- a/arch/powerpc/include/asm/ipic.h +++ b/arch/powerpc/include/asm/ipic.h @@ -69,10 +69,7 @@ enum ipic_mcp_irq { IPIC_MCP_MU = 7, }; -extern void ipic_set_highest_priority(unsigned int irq); extern void ipic_set_default_priority(void); -extern void ipic_enable_mcp(enum ipic_mcp_irq mcp_irq); -extern void ipic_disable_mcp(enum ipic_mcp_irq mcp_irq); extern u32 ipic_get_mcp_status(void); extern void ipic_clear_mcp_status(u32 mask); diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 5c5ea2413413..aa4497175bd3 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -326,7 +326,6 @@ struct page; extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg); extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *p); -extern int page_is_ram(unsigned long pfn); extern int devmem_is_allowed(unsigned long pfn); #ifdef CONFIG_PPC_SMLPAR diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h index 2f3ff7a27881..362ea12a4501 100644 --- a/arch/powerpc/include/asm/powernv.h +++ b/arch/powerpc/include/asm/powernv.h @@ -40,7 +40,6 @@ static inline int pnv_npu2_handle_fault(struct npu_context *context, } static inline void pnv_tm_init(void) { } -static inline void pnv_power9_force_smt4(void) { } #endif #endif /* _ASM_POWERNV_H */ diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index f67da277d652..f191ef0d2a0a 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -53,13 +53,13 @@ void eeh_addr_cache_rmv_dev(struct pci_dev *dev); struct eeh_dev *eeh_addr_cache_get_dev(unsigned long addr); void eeh_slot_error_detail(struct eeh_pe *pe, int severity); int eeh_pci_enable(struct eeh_pe *pe, int function); -int eeh_pe_reset_full(struct eeh_pe *pe); +int eeh_pe_reset_full(struct eeh_pe *pe, bool include_passed); void eeh_save_bars(struct eeh_dev *edev); int rtas_write_config(struct pci_dn *, int where, int size, u32 val); int rtas_read_config(struct pci_dn *, int where, int size, u32 *val); void eeh_pe_state_mark(struct eeh_pe *pe, int state); void eeh_pe_mark_isolated(struct eeh_pe *pe); -void eeh_pe_state_clear(struct eeh_pe *pe, int state); +void eeh_pe_state_clear(struct eeh_pe *pe, int state, bool include_passed); void eeh_pe_state_mark_with_cfg(struct eeh_pe *pe, int state); void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode); diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index a4a718dbfec6..f85e2b01c3df 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -132,6 +132,8 @@ static inline void shared_proc_topology_init(void) {} #define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_core_id(cpu) (cpu_to_core_id(cpu)) + +int dlpar_cpu_readd(int cpu); #endif #endif diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h index ff91192407d1..f599064dd8dc 100644 --- a/arch/powerpc/include/uapi/asm/perf_regs.h +++ b/arch/powerpc/include/uapi/asm/perf_regs.h @@ -47,6 +47,7 @@ enum perf_event_powerpc_regs { PERF_REG_POWERPC_DAR, PERF_REG_POWERPC_DSISR, PERF_REG_POWERPC_SIER, + PERF_REG_POWERPC_MMCRA, PERF_REG_POWERPC_MAX, }; #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */ diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index ae05203eb4de..98d8755ac4c8 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -823,15 +823,15 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat switch (state) { case pcie_deassert_reset: eeh_ops->reset(pe, EEH_RESET_DEACTIVATE); - eeh_unfreeze_pe(pe, false); + eeh_unfreeze_pe(pe); if (!(pe->type & EEH_PE_VF)) - eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, true); eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev); - eeh_pe_state_clear(pe, EEH_PE_ISOLATED); + eeh_pe_state_clear(pe, EEH_PE_ISOLATED, true); break; case pcie_hot_reset: eeh_pe_mark_isolated(pe); - eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, true); eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); if (!(pe->type & EEH_PE_VF)) @@ -840,7 +840,7 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat break; case pcie_warm_reset: eeh_pe_mark_isolated(pe); - eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, true); eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); if (!(pe->type & EEH_PE_VF)) @@ -848,7 +848,7 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); break; default: - eeh_pe_state_clear(pe, EEH_PE_ISOLATED | EEH_PE_CFG_BLOCKED); + eeh_pe_state_clear(pe, EEH_PE_ISOLATED | EEH_PE_CFG_BLOCKED, true); return -EINVAL; }; @@ -877,6 +877,24 @@ static void *eeh_set_dev_freset(struct eeh_dev *edev, void *flag) return NULL; } +static void eeh_pe_refreeze_passed(struct eeh_pe *root) +{ + struct eeh_pe *pe; + int state; + + eeh_for_each_pe(root, pe) { + if (eeh_pe_passed(pe)) { + state = eeh_ops->get_state(pe, NULL); + if (state & + (EEH_STATE_MMIO_ACTIVE | EEH_STATE_MMIO_ENABLED)) { + pr_info("EEH: Passed-through PE PHB#%x-PE#%x was thawed by reset, re-freezing for safety.\n", + pe->phb->global_number, pe->addr); + eeh_pe_set_option(pe, EEH_OPT_FREEZE_PE); + } + } + } +} + /** * eeh_pe_reset_full - Complete a full reset process on the indicated PE * @pe: EEH PE @@ -889,12 +907,12 @@ static void *eeh_set_dev_freset(struct eeh_dev *edev, void *flag) * * This function will attempt to reset a PE three times before failing. */ -int eeh_pe_reset_full(struct eeh_pe *pe) +int eeh_pe_reset_full(struct eeh_pe *pe, bool include_passed) { int reset_state = (EEH_PE_RESET | EEH_PE_CFG_BLOCKED); int type = EEH_RESET_HOT; unsigned int freset = 0; - int i, state, ret; + int i, state = 0, ret; /* * Determine the type of reset to perform - hot or fundamental. @@ -911,32 +929,42 @@ int eeh_pe_reset_full(struct eeh_pe *pe) /* Make three attempts at resetting the bus */ for (i = 0; i < 3; i++) { - ret = eeh_pe_reset(pe, type); - if (ret) - break; - - ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE); - if (ret) - break; + ret = eeh_pe_reset(pe, type, include_passed); + if (!ret) + ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE, + include_passed); + if (ret) { + ret = -EIO; + pr_warn("EEH: Failure %d resetting PHB#%x-PE#%x (attempt %d)\n\n", + state, pe->phb->global_number, pe->addr, i + 1); + continue; + } + if (i) + pr_warn("EEH: PHB#%x-PE#%x: Successful reset (attempt %d)\n", + pe->phb->global_number, pe->addr, i + 1); /* Wait until the PE is in a functioning state */ state = eeh_wait_state(pe, PCI_BUS_RESET_WAIT_MSEC); if (state < 0) { - pr_warn("%s: Unrecoverable slot failure on PHB#%x-PE#%x", - __func__, pe->phb->global_number, pe->addr); + pr_warn("EEH: Unrecoverable slot failure on PHB#%x-PE#%x", + pe->phb->global_number, pe->addr); ret = -ENOTRECOVERABLE; break; } if (eeh_state_active(state)) break; - - /* Set error in case this is our last attempt */ - ret = -EIO; - pr_warn("%s: Failure %d resetting PHB#%x-PE#%x\n (%d)\n", - __func__, state, pe->phb->global_number, pe->addr, (i + 1)); + else + pr_warn("EEH: PHB#%x-PE#%x: Slot inactive after reset: 0x%x (attempt %d)\n", + pe->phb->global_number, pe->addr, state, i + 1); } - eeh_pe_state_clear(pe, reset_state); + /* Resetting the PE may have unfrozen child PEs. If those PEs have been + * (potentially) passed through to a guest, re-freeze them: + */ + if (!include_passed) + eeh_pe_refreeze_passed(pe); + + eeh_pe_state_clear(pe, reset_state, true); return ret; } @@ -1309,7 +1337,7 @@ void eeh_remove_device(struct pci_dev *dev) edev->mode &= ~EEH_DEV_SYSFS; } -int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state) +int eeh_unfreeze_pe(struct eeh_pe *pe) { int ret; @@ -1327,10 +1355,6 @@ int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state) return ret; } - /* Clear software isolated state */ - if (sw_state && (pe->state & EEH_PE_ISOLATED)) - eeh_pe_state_clear(pe, EEH_PE_ISOLATED); - return ret; } @@ -1382,7 +1406,10 @@ static int eeh_pe_change_owner(struct eeh_pe *pe) } } - return eeh_unfreeze_pe(pe, true); + ret = eeh_unfreeze_pe(pe); + if (!ret) + eeh_pe_state_clear(pe, EEH_PE_ISOLATED, true); + return ret; } /** @@ -1612,13 +1639,12 @@ int eeh_pe_get_state(struct eeh_pe *pe) } EXPORT_SYMBOL_GPL(eeh_pe_get_state); -static int eeh_pe_reenable_devices(struct eeh_pe *pe) +static int eeh_pe_reenable_devices(struct eeh_pe *pe, bool include_passed) { struct eeh_dev *edev, *tmp; struct pci_dev *pdev; int ret = 0; - /* Restore config space */ eeh_pe_restore_bars(pe); /* @@ -1639,7 +1665,14 @@ static int eeh_pe_reenable_devices(struct eeh_pe *pe) } /* The PE is still in frozen state */ - return eeh_unfreeze_pe(pe, true); + if (include_passed || !eeh_pe_passed(pe)) { + ret = eeh_unfreeze_pe(pe); + } else + pr_info("EEH: Note: Leaving passthrough PHB#%x-PE#%x frozen.\n", + pe->phb->global_number, pe->addr); + if (!ret) + eeh_pe_state_clear(pe, EEH_PE_ISOLATED, include_passed); + return ret; } @@ -1652,7 +1685,7 @@ static int eeh_pe_reenable_devices(struct eeh_pe *pe) * indicated type, either fundamental reset or hot reset. * PE reset is the most important part for error recovery. */ -int eeh_pe_reset(struct eeh_pe *pe, int option) +int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed) { int ret = 0; @@ -1666,11 +1699,11 @@ int eeh_pe_reset(struct eeh_pe *pe, int option) switch (option) { case EEH_RESET_DEACTIVATE: ret = eeh_ops->reset(pe, option); - eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); + eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED, include_passed); if (ret) break; - ret = eeh_pe_reenable_devices(pe); + ret = eeh_pe_reenable_devices(pe, include_passed); break; case EEH_RESET_HOT: case EEH_RESET_FUNDAMENTAL: diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 99eab7bc7edc..89623962c727 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -510,22 +510,11 @@ static void *eeh_rmv_device(struct eeh_dev *edev, void *userdata) * support EEH. So we just care about PCI devices for * simplicity here. */ - if (!dev || (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)) - return NULL; - - /* - * We rely on count-based pcibios_release_device() to - * detach permanently offlined PEs. Unfortunately, that's - * not reliable enough. We might have the permanently - * offlined PEs attached, but we needn't take care of - * them and their child devices. - */ - if (eeh_dev_removed(edev)) + if (!eeh_edev_actionable(edev) || + (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)) return NULL; if (rmv_data) { - if (eeh_pe_passed(edev->pe)) - return NULL; driver = eeh_pcid_get(dev); if (driver) { if (driver->err_handler && @@ -539,8 +528,8 @@ static void *eeh_rmv_device(struct eeh_dev *edev, void *userdata) } /* Remove it from PCI subsystem */ - pr_debug("EEH: Removing %s without EEH sensitive driver\n", - pci_name(dev)); + pr_info("EEH: Removing %s without EEH sensitive driver\n", + pci_name(dev)); edev->mode |= EEH_DEV_DISCONNECTED; if (rmv_data) rmv_data->removed_dev_count++; @@ -591,34 +580,22 @@ static void *eeh_pe_detach_dev(struct eeh_pe *pe, void *userdata) * PE reset (for 3 times), we try to clear the frozen state * for 3 times as well. */ -static void *__eeh_clear_pe_frozen_state(struct eeh_pe *pe, void *flag) +static int eeh_clear_pe_frozen_state(struct eeh_pe *root, bool include_passed) { - bool clear_sw_state = *(bool *)flag; - int i, rc = 1; - - for (i = 0; rc && i < 3; i++) - rc = eeh_unfreeze_pe(pe, clear_sw_state); + struct eeh_pe *pe; + int i; - /* Stop immediately on any errors */ - if (rc) { - pr_warn("%s: Failure %d unfreezing PHB#%x-PE#%x\n", - __func__, rc, pe->phb->global_number, pe->addr); - return (void *)pe; + eeh_for_each_pe(root, pe) { + if (include_passed || !eeh_pe_passed(pe)) { + for (i = 0; i < 3; i++) + if (!eeh_unfreeze_pe(pe)) + break; + if (i >= 3) + return -EIO; + } } - - return NULL; -} - -static int eeh_clear_pe_frozen_state(struct eeh_pe *pe, - bool clear_sw_state) -{ - void *rc; - - rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, &clear_sw_state); - if (!rc) - eeh_pe_state_clear(pe, EEH_PE_ISOLATED); - - return rc ? -EIO : 0; + eeh_pe_state_clear(root, EEH_PE_ISOLATED, include_passed); + return 0; } int eeh_pe_reset_and_recover(struct eeh_pe *pe) @@ -636,16 +613,16 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL); /* Issue reset */ - ret = eeh_pe_reset_full(pe); + ret = eeh_pe_reset_full(pe, true); if (ret) { - eeh_pe_state_clear(pe, EEH_PE_RECOVERING); + eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true); return ret; } /* Unfreeze the PE */ ret = eeh_clear_pe_frozen_state(pe, true); if (ret) { - eeh_pe_state_clear(pe, EEH_PE_RECOVERING); + eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true); return ret; } @@ -653,7 +630,7 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) eeh_pe_dev_traverse(pe, eeh_dev_restore_state, NULL); /* Clear recovery mode */ - eeh_pe_state_clear(pe, EEH_PE_RECOVERING); + eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true); return 0; } @@ -676,6 +653,11 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, time64_t tstamp; int cnt, rc; struct eeh_dev *edev; + struct eeh_pe *tmp_pe; + bool any_passed = false; + + eeh_for_each_pe(pe, tmp_pe) + any_passed |= eeh_pe_passed(tmp_pe); /* pcibios will clear the counter; save the value */ cnt = pe->freeze_count; @@ -688,7 +670,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, * into pci_hp_add_devices(). */ eeh_pe_state_mark(pe, EEH_PE_KEEP); - if (driver_eeh_aware || (pe->type & EEH_PE_VF)) { + if (any_passed || driver_eeh_aware || (pe->type & EEH_PE_VF)) { eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data); } else { pci_lock_rescan_remove(); @@ -705,7 +687,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, * config accesses. So we prefer to block them. However, controlled * PCI config accesses initiated from EEH itself are allowed. */ - rc = eeh_pe_reset_full(pe); + rc = eeh_pe_reset_full(pe, false); if (rc) return rc; @@ -744,11 +726,11 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, eeh_add_virt_device(edev); } else { if (!driver_eeh_aware) - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); pci_hp_add_devices(bus); } } - eeh_pe_state_clear(pe, EEH_PE_KEEP); + eeh_pe_state_clear(pe, EEH_PE_KEEP, true); pe->tstamp = tstamp; pe->freeze_count = cnt; @@ -900,7 +882,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe) * is still in frozen state. Clear it before * resuming the PE. */ - eeh_pe_state_clear(pe, EEH_PE_ISOLATED); + eeh_pe_state_clear(pe, EEH_PE_ISOLATED, true); result = PCI_ERS_RESULT_RECOVERED; } } @@ -977,7 +959,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe) 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_state_clear(pe, EEH_PE_PRI_BUS, true); eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); pci_lock_rescan_remove(); @@ -987,7 +969,7 @@ void eeh_handle_normal_event(struct eeh_pe *pe) return; } } - eeh_pe_state_clear(pe, EEH_PE_RECOVERING); + eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true); } /** @@ -1069,7 +1051,7 @@ void eeh_handle_special_event(void) continue; /* Notify all devices to be down */ - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); eeh_set_channel_state(pe, pci_channel_io_perm_failure); eeh_pe_report( "error_detected(permanent failure)", pe, diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 6fa2032e0594..8b578891f27c 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -657,62 +657,52 @@ void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode) } /** - * __eeh_pe_state_clear - Clear state for the PE + * eeh_pe_state_clear - Clear state for the PE * @data: EEH PE - * @flag: state + * @state: state + * @include_passed: include passed-through devices? * * The function is used to clear the indicated state from the * given PE. Besides, we also clear the check count of the PE * as well. */ -static void *__eeh_pe_state_clear(struct eeh_pe *pe, void *flag) +void eeh_pe_state_clear(struct eeh_pe *root, int state, bool include_passed) { - int state = *((int *)flag); + struct eeh_pe *pe; struct eeh_dev *edev, *tmp; struct pci_dev *pdev; - /* Keep the state of permanently removed PE intact */ - if (pe->state & EEH_PE_REMOVED) - return NULL; + eeh_for_each_pe(root, pe) { + /* Keep the state of permanently removed PE intact */ + if (pe->state & EEH_PE_REMOVED) + continue; - pe->state &= ~state; + if (!include_passed && eeh_pe_passed(pe)) + continue; - /* - * Special treatment on clearing isolated state. Clear - * check count since last isolation and put all affected - * devices to normal state. - */ - if (!(state & EEH_PE_ISOLATED)) - return NULL; + pe->state &= ~state; - pe->check_count = 0; - eeh_pe_for_each_dev(pe, edev, tmp) { - pdev = eeh_dev_to_pci_dev(edev); - if (!pdev) + /* + * Special treatment on clearing isolated state. Clear + * check count since last isolation and put all affected + * devices to normal state. + */ + if (!(state & EEH_PE_ISOLATED)) continue; - pdev->error_state = pci_channel_io_normal; - } - - /* Unblock PCI config access if required */ - if (pe->state & EEH_PE_CFG_RESTRICTED) - pe->state &= ~EEH_PE_CFG_BLOCKED; + pe->check_count = 0; + eeh_pe_for_each_dev(pe, edev, tmp) { + pdev = eeh_dev_to_pci_dev(edev); + if (!pdev) + continue; - return NULL; -} + pdev->error_state = pci_channel_io_normal; + } -/** - * eeh_pe_state_clear - Clear state for the PE and its children - * @pe: PE - * @state: state to be cleared - * - * When the PE and its children has been recovered from error, - * we need clear the error state for that. The function is used - * for the purpose. - */ -void eeh_pe_state_clear(struct eeh_pe *pe, int state) -{ - eeh_pe_traverse(pe, __eeh_pe_state_clear, &state); + /* Unblock PCI config access if required */ + if (pe->state & EEH_PE_CFG_RESTRICTED) + pe->state &= ~EEH_PE_CFG_BLOCKED; + } } /* diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index deed906dd8f1..3fa04dda1737 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -82,8 +82,9 @@ static ssize_t eeh_pe_state_store(struct device *dev, if (!(edev->pe->state & EEH_PE_ISOLATED)) return count; - if (eeh_unfreeze_pe(edev->pe, true)) + if (eeh_unfreeze_pe(edev->pe)) return -EIO; + eeh_pe_state_clear(edev->pe, EEH_PE_ISOLATED, true); return count; } diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 435927f549c4..a2c168b395d2 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -1002,6 +1002,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r2,_NIP(r1) mtspr SPRN_SRR0,r2 + /* + * Leaving a stale exception_marker on the stack can confuse + * the reliable stack unwinder later on. Clear it. + */ + li r2,0 + std r2,STACK_FRAME_OVERHEAD-16(r1) + ld r0,GPR0(r1) ld r2,GPR2(r1) ld r3,GPR3(r1) diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 57deb1e9ffea..20cc816b3508 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -852,11 +852,12 @@ start_here: /* set up the PTE pointers for the Abatron bdiGDB. */ - tovirt(r6,r6) lis r5, abatron_pteptrs@h ori r5, r5, abatron_pteptrs@l stw r5, 0xf0(0) /* Must match your Abatron config file */ tophys(r5,r5) + lis r6, swapper_pg_dir@h + ori r6, r6, swapper_pg_dir@l stw r6, 0(r5) /* Now turn on the MMU for real! */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 916ddc4aac44..bb299613a462 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -827,11 +827,6 @@ int irq_choose_cpu(const struct cpumask *mask) } #endif -int arch_early_irq_init(void) -{ - return 0; -} - #ifdef CONFIG_PPC64 static int __init setup_noirqdistrib(char *str) { diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index cdd5d1d3ae41..7535f89e08cd 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -33,6 +33,7 @@ #include <linux/hw_breakpoint.h> #include <linux/perf_event.h> #include <linux/context_tracking.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <linux/pkeys.h> @@ -274,6 +275,8 @@ static int set_user_trap(struct task_struct *task, unsigned long trap) */ int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data) { + unsigned int regs_max; + if ((task->thread.regs == NULL) || !data) return -EIO; @@ -297,7 +300,9 @@ int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data) } #endif - if (regno < (sizeof(struct user_pt_regs) / sizeof(unsigned long))) { + regs_max = sizeof(struct user_pt_regs) / sizeof(unsigned long); + if (regno < regs_max) { + regno = array_index_nospec(regno, regs_max); *data = ((unsigned long *)task->thread.regs)[regno]; return 0; } @@ -321,6 +326,7 @@ int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data) return set_user_dscr(task, data); if (regno <= PT_MAX_PUT_REG) { + regno = array_index_nospec(regno, PT_MAX_PUT_REG + 1); ((unsigned long *)task->thread.regs)[regno] = data; return 0; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index bd5e6834ca69..6794466f6420 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -755,11 +755,12 @@ SYSCALL_DEFINE0(rt_sigreturn) if (restore_tm_sigcontexts(current, &uc->uc_mcontext, &uc_transact->uc_mcontext)) goto badframe; - } + } else #endif - /* Fall through, for non-TM restore */ - if (!MSR_TM_ACTIVE(msr)) { + { /* + * Fall through, for non-TM restore + * * Unset MSR[TS] on the thread regs since MSR from user * context does not have MSR active, and recheckpoint was * not called since restore_tm_sigcontexts() was not called diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index e2c50b55138f..cf31ce6c1f53 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -84,25 +84,22 @@ save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) EXPORT_SYMBOL_GPL(save_stack_trace_regs); #ifdef CONFIG_HAVE_RELIABLE_STACKTRACE +/* + * This function returns an error if it detects any unreliable features of the + * stack. Otherwise it guarantees that the stack trace is reliable. + * + * If the task is not 'current', the caller *must* ensure the task is inactive. + */ int save_stack_trace_tsk_reliable(struct task_struct *tsk, struct stack_trace *trace) { unsigned long sp; + unsigned long newsp; unsigned long stack_page = (unsigned long)task_stack_page(tsk); unsigned long stack_end; int graph_idx = 0; - - /* - * The last frame (unwinding first) may not yet have saved - * its LR onto the stack. - */ - int firstframe = 1; - - if (tsk == current) - sp = current_stack_pointer(); - else - sp = tsk->thread.ksp; + bool firstframe; stack_end = stack_page + THREAD_SIZE; if (!is_idle_task(tsk)) { @@ -129,40 +126,53 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk, stack_end -= STACK_FRAME_OVERHEAD; } + if (tsk == current) + sp = current_stack_pointer(); + else + sp = tsk->thread.ksp; + if (sp < stack_page + sizeof(struct thread_struct) || sp > stack_end - STACK_FRAME_MIN_SIZE) { - return 1; + return -EINVAL; } - for (;;) { + for (firstframe = true; sp != stack_end; + firstframe = false, sp = newsp) { unsigned long *stack = (unsigned long *) sp; - unsigned long newsp, ip; + unsigned long ip; /* sanity check: ABI requires SP to be aligned 16 bytes. */ if (sp & 0xF) - return 1; - - /* Mark stacktraces with exception frames as unreliable. */ - if (sp <= stack_end - STACK_INT_FRAME_SIZE && - stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) { - return 1; - } + return -EINVAL; newsp = stack[0]; /* Stack grows downwards; unwinder may only go up. */ if (newsp <= sp) - return 1; + return -EINVAL; if (newsp != stack_end && newsp > stack_end - STACK_FRAME_MIN_SIZE) { - return 1; /* invalid backlink, too far up. */ + return -EINVAL; /* invalid backlink, too far up. */ + } + + /* + * We can only trust the bottom frame's backlink, the + * rest of the frame may be uninitialized, continue to + * the next. + */ + if (firstframe) + continue; + + /* Mark stacktraces with exception frames as unreliable. */ + if (sp <= stack_end - STACK_INT_FRAME_SIZE && + stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) { + return -EINVAL; } /* Examine the saved LR: it must point into kernel code. */ ip = stack[STACK_FRAME_LR_SAVE]; - if (!firstframe && !__kernel_text_address(ip)) - return 1; - firstframe = 0; + if (!__kernel_text_address(ip)) + return -EINVAL; /* * FIXME: IMHO these tests do not belong in @@ -175,21 +185,15 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk, * as unreliable. */ if (ip == (unsigned long)kretprobe_trampoline) - return 1; + return -EINVAL; #endif + if (trace->nr_entries >= trace->max_entries) + return -E2BIG; if (!trace->skip) trace->entries[trace->nr_entries++] = ip; else trace->skip--; - - if (newsp == stack_end) - break; - - if (trace->nr_entries >= trace->max_entries) - return -E2BIG; - - sp = newsp; } return 0; } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 3646affae963..bc0503ef9c9c 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -57,7 +57,6 @@ #include <linux/irq_work.h> #include <linux/clk-provider.h> #include <linux/suspend.h> -#include <linux/rtc.h> #include <linux/sched/cputime.h> #include <linux/processor.h> #include <asm/trace.h> diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 29746dc28df5..517662a56bdc 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -967,13 +967,6 @@ out: } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) -unsigned long __init arch_syscall_addr(int nr) -{ - return sys_call_table[nr*2]; -} -#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */ - #ifdef PPC64_ELF_ABI_v1 char *arch_ftrace_match_adjust(char *str, const char *search) { diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 64936b60d521..040b60293613 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -257,24 +257,17 @@ static int __die(const char *str, struct pt_regs *regs, long err) { printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); - if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) - printk("LE "); - else - printk("BE "); - - if (IS_ENABLED(CONFIG_PREEMPT)) - pr_cont("PREEMPT "); - - if (IS_ENABLED(CONFIG_SMP)) - pr_cont("SMP NR_CPUS=%d ", NR_CPUS); - - if (debug_pagealloc_enabled()) - pr_cont("DEBUG_PAGEALLOC "); - - if (IS_ENABLED(CONFIG_NUMA)) - pr_cont("NUMA "); - - pr_cont("%s\n", ppc_md.name ? ppc_md.name : ""); + printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s%s %s\n", + IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE", + PAGE_SIZE / 1024, + early_radix_enabled() ? " MMU=Radix" : "", + early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ? " MMU=Hash" : "", + IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", + IS_ENABLED(CONFIG_SMP) ? " SMP" : "", + IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "", + debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", + IS_ENABLED(CONFIG_NUMA) ? " NUMA" : "", + ppc_md.name ? ppc_md.name : ""); if (notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV) == NOTIFY_STOP) return 1; @@ -1542,8 +1535,8 @@ bail: void StackOverflow(struct pt_regs *regs) { - printk(KERN_CRIT "Kernel stack overflow in process %p, r1=%lx\n", - current, regs->gpr[1]); + pr_crit("Kernel stack overflow in process %s[%d], r1=%lx\n", + current->comm, task_pid_nr(current), regs->gpr[1]); debugger(regs); show_regs(regs); panic("kernel stack overflow"); diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c index 7cc38b5b58bc..8db4891acdaf 100644 --- a/arch/powerpc/kernel/udbg.c +++ b/arch/powerpc/kernel/udbg.c @@ -74,7 +74,7 @@ void __init udbg_early_init(void) #endif #ifdef CONFIG_PPC_EARLY_DEBUG - console_loglevel = 10; + console_loglevel = CONSOLE_LOGLEVEL_DEBUG; register_early_udbg_console(); #endif diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index ad1c77f71f54..c3efb972c8c1 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -86,11 +86,11 @@ SECTIONS #ifdef CONFIG_PPC64 /* - * BLOCK(0) overrides the default output section alignment because + * ALIGN(0) overrides the default output section alignment because * this needs to start right after .head.text in order for fixed * section placement to work. */ - .text BLOCK(0) : AT(ADDR(.text) - LOAD_OFFSET) { + .text ALIGN(0) : AT(ADDR(.text) - LOAD_OFFSET) { #ifdef CONFIG_LD_HEAD_STUB_CATCH KEEP(*(.linker_stub_catch)); . = . ; @@ -319,6 +319,7 @@ SECTIONS *(.sdata2) *(.got.plt) *(.got) *(.plt) + *(.branch_lt) } #else .data : AT(ADDR(.data) - LOAD_OFFSET) { diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 64f1135e7732..3223aec88b2c 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -10,11 +10,6 @@ common-objs-y = $(KVM)/kvm_main.o $(KVM)/eventfd.o common-objs-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o common-objs-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o -CFLAGS_e500_mmu.o := -I. -CFLAGS_e500_mmu_host.o := -I. -CFLAGS_emulate.o := -I. -CFLAGS_emulate_loadstore.o := -I. - common-objs-y += powerpc.o emulate_loadstore.o obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o obj-$(CONFIG_KVM_BOOK3S_HANDLER) += book3s_exports.o diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile index 494df26c5988..a8794032f15f 100644 --- a/arch/powerpc/math-emu/Makefile +++ b/arch/powerpc/math-emu/Makefile @@ -17,4 +17,4 @@ obj-$(CONFIG_SPE) += math_efp.o CFLAGS_fabs.o = -fno-builtin-fabs CFLAGS_math.o = -fno-builtin-fabs -ccflags-y = -I. -Iinclude/math-emu -w +ccflags-y = -w diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 0cc7fbc3bd1c..4aa0797000f7 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1889,12 +1889,12 @@ static int hpt_order_set(void *data, u64 val) return mmu_hash_ops.resize_hpt(val); } -DEFINE_SIMPLE_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n"); static int __init hash64_debugfs(void) { - if (!debugfs_create_file("hpt_order", 0600, powerpc_debugfs_root, - NULL, &fops_hpt_order)) { + if (!debugfs_create_file_unsafe("hpt_order", 0600, powerpc_debugfs_root, + NULL, &fops_hpt_order)) { pr_err("lpar: unable to create hpt_order debugsfs file\n"); } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index a10ee3645a6c..f6787f90e158 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -77,11 +77,6 @@ static inline pte_t *virt_to_kpte(unsigned long vaddr) } #endif -int page_is_ram(unsigned long pfn) -{ - return memblock_is_memory(__pfn_to_phys(pfn)); -} - pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { @@ -173,34 +168,6 @@ int __meminit arch_remove_memory(int nid, u64 start, u64 size, #endif #endif /* CONFIG_MEMORY_HOTPLUG */ -/* - * walk_memory_resource() needs to make sure there is no holes in a given - * memory range. PPC64 does not maintain the memory layout in /proc/iomem. - * Instead it maintains it in memblock.memory structures. Walk through the - * memory regions, find holes and callback for contiguous regions. - */ -int -walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, - void *arg, int (*func)(unsigned long, unsigned long, void *)) -{ - struct memblock_region *reg; - unsigned long end_pfn = start_pfn + nr_pages; - unsigned long tstart, tend; - int ret = -1; - - for_each_memblock(memory, reg) { - tstart = max(start_pfn, memblock_region_memory_base_pfn(reg)); - tend = min(end_pfn, memblock_region_memory_end_pfn(reg)); - if (tstart >= tend) - continue; - ret = (*func)(tstart, tend - tstart, arg); - if (ret) - break; - } - return ret; -} -EXPORT_SYMBOL_GPL(walk_system_ram_range); - #ifndef CONFIG_NEED_MULTIPLE_NODES void __init mem_topology_setup(void) { @@ -563,3 +530,9 @@ int devmem_is_allowed(unsigned long pfn) return 0; } #endif /* CONFIG_STRICT_DEVMEM */ + +/* + * This is defined in kernel/resource.c but only powerpc needs to export it, for + * the EHEA driver. Drop this when drivers/net/ethernet/ibm/ehea is removed. + */ +EXPORT_SYMBOL_GPL(walk_system_ram_range); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 87f0dd004295..b5d1c45c1475 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1460,13 +1460,6 @@ static void reset_topology_timer(void) #ifdef CONFIG_SMP -static void stage_topology_update(int core_id) -{ - cpumask_or(&cpu_associativity_changes_mask, - &cpu_associativity_changes_mask, cpu_sibling_mask(core_id)); - reset_topology_timer(); -} - static int dt_update_callback(struct notifier_block *nb, unsigned long action, void *data) { @@ -1479,7 +1472,7 @@ static int dt_update_callback(struct notifier_block *nb, !of_prop_cmp(update->prop->name, "ibm,associativity")) { u32 core_id; of_property_read_u32(update->dn, "reg", &core_id); - stage_topology_update(core_id); + rc = dlpar_cpu_readd(core_id); rc = NOTIFY_OK; } break; diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index f3c31f5e1026..ecd31569a120 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -400,3 +400,25 @@ void arch_report_meminfo(struct seq_file *m) atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20); } #endif /* CONFIG_PROC_FS */ + +/* + * For hash translation mode, we use the deposited table to store hash slot + * information and they are stored at PTRS_PER_PMD offset from related pmd + * location. Hence a pmd move requires deposit and withdraw. + * + * For radix translation with split pmd ptl, we store the deposited table in the + * pmd page. Hence if we have different pmd page we need to withdraw during pmd + * move. + * + * With hash we use deposited table always irrespective of anon or not. + * With radix we use deposited table only for anonymous mapping. + */ +int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma) +{ + if (radix_enabled()) + return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma); + + return true; +} diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index ae5d568e267f..ac23dc1c6535 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -302,7 +302,7 @@ void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, * This function as well as __local_flush_tlb_page() must only be called * for user contexts. */ - if (unlikely(WARN_ON(!mm))) + if (WARN_ON(!mm)) return; preempt_disable(); diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index 5c36b3a8d47a..3349f3f8fe84 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -70,6 +70,7 @@ static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = { PT_REGS_OFFSET(PERF_REG_POWERPC_DAR, dar), PT_REGS_OFFSET(PERF_REG_POWERPC_DSISR, dsisr), PT_REGS_OFFSET(PERF_REG_POWERPC_SIER, dar), + PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr), }; u64 perf_reg_value(struct pt_regs *regs, int idx) @@ -83,6 +84,11 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) !is_sier_available())) return 0; + if (idx == PERF_REG_POWERPC_MMCRA && + (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) || + IS_ENABLED(CONFIG_PPC32))) + return 0; + return regs_get_register(regs, pt_regs_offset[idx]); } diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h index 7de344b7d9cc..063c9d9f2516 100644 --- a/arch/powerpc/perf/power9-events-list.h +++ b/arch/powerpc/perf/power9-events-list.h @@ -97,3 +97,27 @@ EVENT(PM_MRK_DTLB_MISS_64K, 0x3d156) EVENT(PM_DTLB_MISS_16M, 0x4c056) EVENT(PM_DTLB_MISS_1G, 0x4c05a) EVENT(PM_MRK_DTLB_MISS_16M, 0x4c15e) + +/* + * Memory Access Events + * + * Primary PMU event used here is PM_MRK_INST_CMPL (0x401e0) + * To enable capturing of memory profiling, these MMCRA bits + * needs to be programmed and corresponding raw event format + * encoding. + * + * MMCRA bits encoding needed are + * SM (Sampling Mode) + * EM (Eligibility for Random Sampling) + * TECE (Threshold Event Counter Event) + * TS (Threshold Start Event) + * TE (Threshold End Event) + * + * Corresponding Raw Encoding bits: + * sample [EM,SM] + * thresh_sel (TECE) + * thresh start (TS) + * thresh end (TE) + */ +EVENT(MEM_LOADS, 0x34340401e0) +EVENT(MEM_STORES, 0x343c0401e0) diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 0ff9c43733e9..030544e35959 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -160,6 +160,8 @@ GENERIC_EVENT_ATTR(branch-instructions, PM_BR_CMPL); 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_FIN); +GENERIC_EVENT_ATTR(mem-loads, MEM_LOADS); +GENERIC_EVENT_ATTR(mem-stores, MEM_STORES); CACHE_EVENT_ATTR(L1-dcache-load-misses, PM_LD_MISS_L1_FIN); CACHE_EVENT_ATTR(L1-dcache-loads, PM_LD_REF_L1); @@ -185,6 +187,8 @@ static struct attribute *power9_events_attr[] = { GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL), GENERIC_EVENT_PTR(PM_LD_REF_L1), GENERIC_EVENT_PTR(PM_LD_MISS_L1_FIN), + GENERIC_EVENT_PTR(MEM_LOADS), + GENERIC_EVENT_PTR(MEM_STORES), CACHE_EVENT_PTR(PM_LD_MISS_L1_FIN), CACHE_EVENT_PTR(PM_LD_REF_L1), CACHE_EVENT_PTR(PM_L1_PREF), diff --git a/arch/powerpc/platforms/4xx/ocm.c b/arch/powerpc/platforms/4xx/ocm.c index a1aaa1569d7c..f0e488d97567 100644 --- a/arch/powerpc/platforms/4xx/ocm.c +++ b/arch/powerpc/platforms/4xx/ocm.c @@ -237,12 +237,12 @@ static int ocm_debugfs_show(struct seq_file *m, void *v) continue; seq_printf(m, "PPC4XX OCM : %d\n", ocm->index); - seq_printf(m, "PhysAddr : %pa[p]\n", &(ocm->phys)); + seq_printf(m, "PhysAddr : %pa\n", &(ocm->phys)); seq_printf(m, "MemTotal : %d Bytes\n", ocm->memtotal); seq_printf(m, "MemTotal(NC) : %d Bytes\n", ocm->nc.memtotal); seq_printf(m, "MemTotal(C) : %d Bytes\n\n", ocm->c.memtotal); - seq_printf(m, "NC.PhysAddr : %pa[p]\n", &(ocm->nc.phys)); + seq_printf(m, "NC.PhysAddr : %pa\n", &(ocm->nc.phys)); seq_printf(m, "NC.VirtAddr : 0x%p\n", ocm->nc.virt); seq_printf(m, "NC.MemTotal : %d Bytes\n", ocm->nc.memtotal); seq_printf(m, "NC.MemFree : %d Bytes\n", ocm->nc.memfree); @@ -252,7 +252,7 @@ static int ocm_debugfs_show(struct seq_file *m, void *v) blk->size, blk->owner); } - seq_printf(m, "\nC.PhysAddr : %pa[p]\n", &(ocm->c.phys)); + seq_printf(m, "\nC.PhysAddr : %pa\n", &(ocm->c.phys)); seq_printf(m, "C.VirtAddr : 0x%p\n", ocm->c.virt); seq_printf(m, "C.MemTotal : %d Bytes\n", ocm->c.memtotal); seq_printf(m, "C.MemFree : %d Bytes\n", ocm->c.memfree); diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 47db4934c1cf..842b2c7e156a 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -153,6 +153,11 @@ config E300C3_CPU bool "e300c3 (831x)" depends on PPC_BOOK3S_32 +config G4_CPU + bool "G4 (74xx)" + depends on PPC_BOOK3S_32 + select ALTIVEC + endchoice config TARGET_CPU_BOOL @@ -171,6 +176,7 @@ config TARGET_CPU default "860" if 860_CPU default "e300c2" if E300C2_CPU default "e300c3" if E300C3_CPU + default "G4" if G4_CPU config PPC_BOOK3S def_bool y diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c index 263413a34823..b95d6afc39b5 100644 --- a/arch/powerpc/platforms/cell/spu_syscalls.c +++ b/arch/powerpc/platforms/cell/spu_syscalls.c @@ -26,7 +26,6 @@ #include <linux/syscalls.h> #include <linux/rcupdate.h> #include <linux/binfmts.h> -#include <linux/syscalls.h> #include <asm/spu.h> diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index ae8123edddc6..48c2477e7e2a 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -2338,9 +2338,8 @@ static int spufs_switch_log_open(struct inode *inode, struct file *file) goto out; } - ctx->switch_log = kmalloc(sizeof(struct switch_log) + - SWITCH_LOG_BUFSIZE * sizeof(struct switch_log_entry), - GFP_KERNEL); + ctx->switch_log = kmalloc(struct_size(ctx->switch_log, log, + SWITCH_LOG_BUFSIZE), GFP_KERNEL); if (!ctx->switch_log) { rc = -ENOMEM; diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 4e87e13fa0fc..ccf186bb60ec 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -28,10 +28,6 @@ */ static DEFINE_SPINLOCK(npu_context_lock); -/* - * Other types of TCE cache invalidation are not functional in the - * hardware. - */ static struct pci_dev *get_pci_dev(struct device_node *dn) { struct pci_dn *pdn = PCI_DN(dn); @@ -564,7 +560,7 @@ struct iommu_table_group *pnv_try_setup_npu_table_group(struct pnv_ioda_pe *pe) } } else { /* Create a group for 1 GPU and attached NPUs for POWER8 */ - pe->npucomp = kzalloc(sizeof(pe->npucomp), GFP_KERNEL); + pe->npucomp = kzalloc(sizeof(*pe->npucomp), GFP_KERNEL); table_group = &pe->npucomp->table_group; table_group->ops = &pnv_npu_peers_ops; iommu_register_group(table_group, hose->global_number, diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 79586f127521..d1072d464e99 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -26,7 +26,6 @@ #include <linux/memblock.h> #include <linux/kthread.h> #include <linux/freezer.h> -#include <linux/printk.h> #include <linux/kmsg_dump.h> #include <linux/console.h> #include <linux/sched/debug.h> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 6438f38235e8..e9986c9f779d 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2613,7 +2613,8 @@ static void pnv_pci_ioda_setup_iommu_api(void) list_for_each_entry(hose, &hose_list, list_node) { phb = hose->private_data; - if (phb->type == PNV_PHB_NPU_NVLINK) + if (phb->type == PNV_PHB_NPU_NVLINK || + phb->type == PNV_PHB_NPU_OCAPI) continue; list_for_each_entry(pe, &phb->ioda.pe_list, list) { @@ -3865,9 +3866,12 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, * shutdown PCI devices correctly. We already got IODA table * cleaned out. So we have to issue PHB reset to stop all PCI * transactions from previous kernel. The ppc_pci_reset_phbs - * kernel parameter will force this reset too. + * kernel parameter will force this reset too. Additionally, + * if the IODA reset above failed then use a bigger hammer. + * This can happen if we get a PHB fatal error in very early + * boot. */ - if (is_kdump_kernel() || pci_reset_phbs) { + if (is_kdump_kernel() || pci_reset_phbs || rc) { pr_info(" Issue PHB reset ...\n"); pnv_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL); pnv_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE); diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c index e7075aaff1bb..59587b75493d 100644 --- a/arch/powerpc/platforms/ps3/device-init.c +++ b/arch/powerpc/platforms/ps3/device-init.c @@ -354,9 +354,7 @@ static int ps3_setup_storage_dev(const struct ps3_repository_device *repo, repo->dev_index, repo->dev_type, port, blk_size, num_blocks, num_regions); - p = kzalloc(sizeof(struct ps3_storage_device) + - num_regions * sizeof(struct ps3_storage_region), - GFP_KERNEL); + p = kzalloc(struct_size(p, regions, num_regions), GFP_KERNEL); if (!p) { result = -ENOMEM; goto fail_malloc; diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c index f5387ad82279..4d65c5380020 100644 --- a/arch/powerpc/platforms/ps3/os-area.c +++ b/arch/powerpc/platforms/ps3/os-area.c @@ -205,11 +205,11 @@ static const struct os_area_db_id os_area_db_id_rtc_diff = { * 3) The number of seconds from 1970 to 2000. */ -struct saved_params { +static struct saved_params { unsigned int valid; s64 rtc_diff; unsigned int av_multi_out; -} static saved_params; +} saved_params; static struct property property_rtc_diff = { .name = "linux,rtc_diff", diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index 5cc35d6b94b6..7c227e784247 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -37,12 +37,12 @@ static struct device ps3_system_bus = { }; /* FIXME: need device usage counters! */ -struct { +static struct { struct mutex mutex; int sb_11; /* usb 0 */ int sb_12; /* usb 0 */ int gpu; -} static usage_hack; +} usage_hack; static int ps3_is_device(struct ps3_system_bus_device *dev, u64 bus_id, u64 dev_id) diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 2f8e62163602..97feb6e79f1a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -802,6 +802,25 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add) return rc; } +int dlpar_cpu_readd(int cpu) +{ + struct device_node *dn; + struct device *dev; + u32 drc_index; + int rc; + + dev = get_cpu_device(cpu); + dn = dev->of_node; + + rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index); + + rc = dlpar_cpu_remove_by_index(drc_index); + if (!rc) + rc = dlpar_cpu_add(drc_index); + + return rc; +} + int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) { u32 count, drc_index; diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 7d6457ab5d34..bba281b1fe1b 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -43,6 +43,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; uint64_t rc, token; + uint64_t saved = 0; /* * When the hypervisor cannot map all the requested memory in a single @@ -56,6 +57,8 @@ static int drc_pmem_bind(struct papr_scm_priv *p) rc = plpar_hcall(H_SCM_BIND_MEM, ret, p->drc_index, 0, p->blocks, BIND_ANY_ADDR, token); token = ret[0]; + if (!saved) + saved = ret[1]; cond_resched(); } while (rc == H_BUSY); @@ -64,7 +67,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) return -ENXIO; } - p->bound_addr = ret[1]; + p->bound_addr = saved; dev_dbg(&p->pdev->dev, "bound drc %x to %pR\n", p->drc_index, &p->res); diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 7725825d887d..37a77e57893e 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -264,7 +264,9 @@ void __init pSeries_final_fixup(void) if (!of_device_is_compatible(nvdn->parent, "ibm,power9-npu")) continue; +#ifdef CONFIG_PPC_POWERNV WARN_ON_ONCE(pnv_npu2_init(hose)); +#endif break; } } diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c index 8030a0f55e96..fd129c8ecceb 100644 --- a/arch/powerpc/sysdev/ipic.c +++ b/arch/powerpc/sysdev/ipic.c @@ -771,21 +771,6 @@ struct ipic * __init ipic_init(struct device_node *node, unsigned int flags) return ipic; } -void ipic_set_highest_priority(unsigned int virq) -{ - struct ipic *ipic = ipic_from_irq(virq); - unsigned int src = virq_to_hw(virq); - u32 temp; - - temp = ipic_read(ipic->regs, IPIC_SICFR); - - /* clear and set HPI */ - temp &= 0x7f000000; - temp |= (src & 0x7f) << 24; - - ipic_write(ipic->regs, IPIC_SICFR, temp); -} - void ipic_set_default_priority(void) { ipic_write(primary_ipic->regs, IPIC_SIPRR_A, IPIC_PRIORITY_DEFAULT); @@ -796,26 +781,6 @@ void ipic_set_default_priority(void) ipic_write(primary_ipic->regs, IPIC_SMPRR_B, IPIC_PRIORITY_DEFAULT); } -void ipic_enable_mcp(enum ipic_mcp_irq mcp_irq) -{ - struct ipic *ipic = primary_ipic; - u32 temp; - - temp = ipic_read(ipic->regs, IPIC_SERMR); - temp |= (1 << (31 - mcp_irq)); - ipic_write(ipic->regs, IPIC_SERMR, temp); -} - -void ipic_disable_mcp(enum ipic_mcp_irq mcp_irq) -{ - struct ipic *ipic = primary_ipic; - u32 temp; - - temp = ipic_read(ipic->regs, IPIC_SERMR); - temp &= (1 << (31 - mcp_irq)); - ipic_write(ipic->regs, IPIC_SERMR, temp); -} - u32 ipic_get_mcp_status(void) { return primary_ipic ? ipic_read(primary_ipic->regs, IPIC_SERSR) : 0; diff --git a/arch/powerpc/sysdev/tsi108_dev.c b/arch/powerpc/sysdev/tsi108_dev.c index 1fd0717ade02..1f1af12f23e2 100644 --- a/arch/powerpc/sysdev/tsi108_dev.c +++ b/arch/powerpc/sysdev/tsi108_dev.c @@ -51,7 +51,7 @@ phys_addr_t get_csrbase(void) const void *prop = of_get_property(tsi, "reg", &size); tsi108_csr_base = of_translate_address(tsi, prop); of_node_put(tsi); - }; + } return tsi108_csr_base; } diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 94a69a62f5db..70a8f9e31a2d 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -442,7 +442,7 @@ static void xive_dec_target_count(int cpu) struct xive_cpu *xc = per_cpu(xive_cpu, cpu); struct xive_q *q = &xc->queue[xive_irq_priority]; - if (unlikely(WARN_ON(cpu < 0 || !xc))) { + if (WARN_ON(cpu < 0 || !xc)) { pr_err("%s: cpu=%d xc=%p\n", __func__, cpu, xc); return; } diff --git a/drivers/misc/cxl/guest.c b/drivers/misc/cxl/guest.c index 5d28d9e454f5..08f4a512afad 100644 --- a/drivers/misc/cxl/guest.c +++ b/drivers/misc/cxl/guest.c @@ -267,6 +267,7 @@ static int guest_reset(struct cxl *adapter) int i, rc; pr_devel("Adapter reset request\n"); + spin_lock(&adapter->afu_list_lock); for (i = 0; i < adapter->slices; i++) { if ((afu = adapter->afu[i])) { pci_error_handlers(afu, CXL_ERROR_DETECTED_EVENT, @@ -283,6 +284,7 @@ static int guest_reset(struct cxl *adapter) pci_error_handlers(afu, CXL_RESUME_EVENT, 0); } } + spin_unlock(&adapter->afu_list_lock); return rc; } diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index c79ba1c699ad..300531d6136f 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -1805,7 +1805,7 @@ static pci_ers_result_t cxl_vphb_error_detected(struct cxl_afu *afu, /* There should only be one entry, but go through the list * anyway */ - if (afu->phb == NULL) + if (afu == NULL || afu->phb == NULL) return result; list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) { @@ -1832,7 +1832,8 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, { struct cxl *adapter = pci_get_drvdata(pdev); struct cxl_afu *afu; - pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET, afu_result; + pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET; + pci_ers_result_t afu_result = PCI_ERS_RESULT_NEED_RESET; int i; /* At this point, we could still have an interrupt pending. @@ -1843,6 +1844,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, /* If we're permanently dead, give up. */ if (state == pci_channel_io_perm_failure) { + spin_lock(&adapter->afu_list_lock); for (i = 0; i < adapter->slices; i++) { afu = adapter->afu[i]; /* @@ -1851,6 +1853,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, */ cxl_vphb_error_detected(afu, state); } + spin_unlock(&adapter->afu_list_lock); return PCI_ERS_RESULT_DISCONNECT; } @@ -1932,11 +1935,17 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, * * In slot_reset, free the old resources and allocate new ones. * * In resume, clear the flag to allow things to start. */ + + /* Make sure no one else changes the afu list */ + spin_lock(&adapter->afu_list_lock); + for (i = 0; i < adapter->slices; i++) { afu = adapter->afu[i]; - afu_result = cxl_vphb_error_detected(afu, state); + if (afu == NULL) + continue; + afu_result = cxl_vphb_error_detected(afu, state); cxl_context_detach_all(afu); cxl_ops->afu_deactivate_mode(afu, afu->current_mode); pci_deconfigure_afu(afu); @@ -1948,6 +1957,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, (result == PCI_ERS_RESULT_NEED_RESET)) result = PCI_ERS_RESULT_NONE; } + spin_unlock(&adapter->afu_list_lock); /* should take the context lock here */ if (cxl_adapter_context_lock(adapter) != 0) @@ -1980,14 +1990,18 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) */ cxl_adapter_context_unlock(adapter); + spin_lock(&adapter->afu_list_lock); for (i = 0; i < adapter->slices; i++) { afu = adapter->afu[i]; + if (afu == NULL) + continue; + if (pci_configure_afu(afu, adapter, pdev)) - goto err; + goto err_unlock; if (cxl_afu_select_best_mode(afu)) - goto err; + goto err_unlock; if (afu->phb == NULL) continue; @@ -1999,16 +2013,16 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) ctx = cxl_get_context(afu_dev); if (ctx && cxl_release_context(ctx)) - goto err; + goto err_unlock; ctx = cxl_dev_context_init(afu_dev); if (IS_ERR(ctx)) - goto err; + goto err_unlock; afu_dev->dev.archdata.cxl_ctx = ctx; if (cxl_ops->afu_check_and_enable(afu)) - goto err; + goto err_unlock; afu_dev->error_state = pci_channel_io_normal; @@ -2029,8 +2043,13 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) result = PCI_ERS_RESULT_DISCONNECT; } } + + spin_unlock(&adapter->afu_list_lock); return result; +err_unlock: + spin_unlock(&adapter->afu_list_lock); + err: /* All the bits that happen in both error_detected and cxl_remove * should be idempotent, so we don't need to worry about leaving a mix @@ -2051,10 +2070,11 @@ static void cxl_pci_resume(struct pci_dev *pdev) * This is not the place to be checking if everything came back up * properly, because there's no return value: do that in slot_reset. */ + spin_lock(&adapter->afu_list_lock); for (i = 0; i < adapter->slices; i++) { afu = adapter->afu[i]; - if (afu->phb == NULL) + if (afu == NULL || afu->phb == NULL) continue; list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) { @@ -2063,6 +2083,7 @@ static void cxl_pci_resume(struct pci_dev *pdev) afu_dev->driver->err_handler->resume(afu_dev); } } + spin_unlock(&adapter->afu_list_lock); } static const struct pci_error_handlers cxl_err_handler = { diff --git a/drivers/vfio/vfio_spapr_eeh.c b/drivers/vfio/vfio_spapr_eeh.c index 38edeb4729a9..1a742fe8f6db 100644 --- a/drivers/vfio/vfio_spapr_eeh.c +++ b/drivers/vfio/vfio_spapr_eeh.c @@ -74,13 +74,13 @@ long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, ret = eeh_pe_get_state(pe); break; case VFIO_EEH_PE_RESET_DEACTIVATE: - ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE); + ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE, true); break; case VFIO_EEH_PE_RESET_HOT: - ret = eeh_pe_reset(pe, EEH_RESET_HOT); + ret = eeh_pe_reset(pe, EEH_RESET_HOT, true); break; case VFIO_EEH_PE_RESET_FUNDAMENTAL: - ret = eeh_pe_reset(pe, EEH_RESET_FUNDAMENTAL); + ret = eeh_pe_reset(pe, EEH_RESET_FUNDAMENTAL, true); break; case VFIO_EEH_PE_CONFIGURE: ret = eeh_pe_configure(pe); diff --git a/kernel/resource.c b/kernel/resource.c index 915c02e8e5dd..e81b17b53fa5 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -448,8 +448,6 @@ int walk_mem_res(u64 start, u64 end, void *arg, arg, func); } -#if !defined(CONFIG_ARCH_HAS_WALK_MEMORY) - /* * This function calls the @func callback against all memory ranges of type * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. @@ -481,8 +479,6 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, return ret; } -#endif - static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg) { return 1; diff --git a/tools/arch/powerpc/include/uapi/asm/perf_regs.h b/tools/arch/powerpc/include/uapi/asm/perf_regs.h index ff91192407d1..f599064dd8dc 100644 --- a/tools/arch/powerpc/include/uapi/asm/perf_regs.h +++ b/tools/arch/powerpc/include/uapi/asm/perf_regs.h @@ -47,6 +47,7 @@ enum perf_event_powerpc_regs { PERF_REG_POWERPC_DAR, PERF_REG_POWERPC_DSISR, PERF_REG_POWERPC_SIER, + PERF_REG_POWERPC_MMCRA, PERF_REG_POWERPC_MAX, }; #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */ diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h index 1076393e6f43..e18a3556f5e3 100644 --- a/tools/perf/arch/powerpc/include/perf_regs.h +++ b/tools/perf/arch/powerpc/include/perf_regs.h @@ -63,7 +63,8 @@ static const char *reg_names[] = { [PERF_REG_POWERPC_TRAP] = "trap", [PERF_REG_POWERPC_DAR] = "dar", [PERF_REG_POWERPC_DSISR] = "dsisr", - [PERF_REG_POWERPC_SIER] = "sier" + [PERF_REG_POWERPC_SIER] = "sier", + [PERF_REG_POWERPC_MMCRA] = "mmcra" }; static inline const char *perf_reg_name(int id) diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index 07fcd977d93e..34d5134681d9 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -53,6 +53,7 @@ const struct sample_reg sample_reg_masks[] = { SMPL_REG(dar, PERF_REG_POWERPC_DAR), SMPL_REG(dsisr, PERF_REG_POWERPC_DSISR), SMPL_REG(sier, PERF_REG_POWERPC_SIER), + SMPL_REG(mmcra, PERF_REG_POWERPC_MMCRA), SMPL_REG_END }; diff --git a/tools/testing/selftests/powerpc/include/reg.h b/tools/testing/selftests/powerpc/include/reg.h index 52b4710469d2..96043b9b9829 100644 --- a/tools/testing/selftests/powerpc/include/reg.h +++ b/tools/testing/selftests/powerpc/include/reg.h @@ -77,6 +77,14 @@ #define TEXASR_TE 0x0000000004000000 #define TEXASR_ROT 0x0000000002000000 +/* MSR register bits */ +#define MSR_TS_S_LG 33 /* Trans Mem state: Suspended */ + +#define __MASK(X) (1UL<<(X)) + +/* macro to check TM MSR bits */ +#define MSR_TS_S __MASK(MSR_TS_S_LG) /* Transaction Suspended */ + /* Vector Instructions */ #define VSX_XX1(xs, ra, rb) (((xs) & 0x1f) << 21 | ((ra) << 16) | \ ((rb) << 11) | (((xs) >> 5))) diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index ae43a614835d..7636bf45d5d5 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -102,8 +102,10 @@ do { \ #if defined(__powerpc64__) #define UCONTEXT_NIA(UC) (UC)->uc_mcontext.gp_regs[PT_NIP] +#define UCONTEXT_MSR(UC) (UC)->uc_mcontext.gp_regs[PT_MSR] #elif defined(__powerpc__) #define UCONTEXT_NIA(UC) (UC)->uc_mcontext.uc_regs->gregs[PT_NIP] +#define UCONTEXT_MSR(UC) (UC)->uc_mcontext.uc_regs->gregs[PT_MSR] #else #error implement UCONTEXT_NIA #endif diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore index 208452a93e2c..951fe855f7cd 100644 --- a/tools/testing/selftests/powerpc/tm/.gitignore +++ b/tools/testing/selftests/powerpc/tm/.gitignore @@ -11,6 +11,7 @@ tm-signal-context-chk-fpu tm-signal-context-chk-gpr tm-signal-context-chk-vmx tm-signal-context-chk-vsx +tm-signal-context-force-tm tm-signal-sigreturn-nt tm-vmx-unavail tm-unavailable diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index 75a685359129..c0734ed0ef56 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -4,7 +4,8 @@ SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \ tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail tm-unavailable tm-trap \ - $(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn tm-signal-sigreturn-nt + $(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn tm-signal-sigreturn-nt \ + tm-signal-context-force-tm top_srcdir = ../../../../.. include ../../lib.mk @@ -20,6 +21,7 @@ $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64 $(OUTPUT)/tm-resched-dscr: ../pmu/lib.c $(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx $(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64 +$(OUTPUT)/tm-signal-context-force-tm: CFLAGS += -pthread -m64 SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS)) $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c b/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c new file mode 100644 index 000000000000..31717625f318 --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2018, Breno Leitao, Gustavo Romero, IBM Corp. + * + * This test raises a SIGUSR1 signal, and toggle the MSR[TS] + * fields at the signal handler. With MSR[TS] being set, the kernel will + * force a recheckpoint, which may cause a segfault when returning to + * user space. Since the test needs to re-run, the segfault needs to be + * caught and handled. + * + * In order to continue the test even after a segfault, the context is + * saved prior to the signal being raised, and it is restored when there is + * a segmentation fault. This happens for COUNT_MAX times. + * + * This test never fails (as returning EXIT_FAILURE). It either succeeds, + * or crash the kernel (on a buggy kernel). + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <string.h> +#include <ucontext.h> +#include <unistd.h> +#include <sys/mman.h> + +#include "tm.h" +#include "utils.h" +#include "reg.h" + +#define COUNT_MAX 5000 /* Number of interactions */ + +/* + * This test only runs on 64 bits system. Unsetting MSR_TS_S to avoid + * compilation issue on 32 bits system. There is no side effect, since the + * whole test will be skipped if it is not running on 64 bits system. + */ +#ifndef __powerpc64__ +#undef MSR_TS_S +#define MSR_TS_S 0 +#endif + +/* Setting contexts because the test will crash and we want to recover */ +ucontext_t init_context, main_context; + +static int count, first_time; + +void usr_signal_handler(int signo, siginfo_t *si, void *uc) +{ + ucontext_t *ucp = uc; + int ret; + + /* + * Allocating memory in a signal handler, and never freeing it on + * purpose, forcing the heap increase, so, the memory leak is what + * we want here. + */ + ucp->uc_link = mmap(NULL, sizeof(ucontext_t), + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); + if (ucp->uc_link == (void *)-1) { + perror("Mmap failed"); + exit(-1); + } + + /* Forcing the page to be allocated in a page fault */ + ret = madvise(ucp->uc_link, sizeof(ucontext_t), MADV_DONTNEED); + if (ret) { + perror("madvise failed"); + exit(-1); + } + + memcpy(&ucp->uc_link->uc_mcontext, &ucp->uc_mcontext, + sizeof(ucp->uc_mcontext)); + + /* Forcing to enable MSR[TM] */ + UCONTEXT_MSR(ucp) |= MSR_TS_S; + + /* + * A fork inside a signal handler seems to be more efficient than a + * fork() prior to the signal being raised. + */ + if (fork() == 0) { + /* + * Both child and parent will return, but, child returns + * with count set so it will exit in the next segfault. + * Parent will continue to loop. + */ + count = COUNT_MAX; + } + + /* + * If the change above does not hit the bug, it will cause a + * segmentation fault, since the ck structures are NULL. + */ +} + +void seg_signal_handler(int signo, siginfo_t *si, void *uc) +{ + if (count == COUNT_MAX) { + /* Return to tm_signal_force_msr() and exit */ + setcontext(&main_context); + } + + count++; + + /* Reexecute the test */ + setcontext(&init_context); +} + +void tm_trap_test(void) +{ + struct sigaction usr_sa, seg_sa; + stack_t ss; + + usr_sa.sa_flags = SA_SIGINFO | SA_ONSTACK; + usr_sa.sa_sigaction = usr_signal_handler; + + seg_sa.sa_flags = SA_SIGINFO; + seg_sa.sa_sigaction = seg_signal_handler; + + /* + * Set initial context. Will get back here from + * seg_signal_handler() + */ + getcontext(&init_context); + + /* Allocated an alternative signal stack area */ + ss.ss_sp = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); + ss.ss_size = SIGSTKSZ; + ss.ss_flags = 0; + + if (ss.ss_sp == (void *)-1) { + perror("mmap error\n"); + exit(-1); + } + + /* Force the allocation through a page fault */ + if (madvise(ss.ss_sp, SIGSTKSZ, MADV_DONTNEED)) { + perror("madvise\n"); + exit(-1); + } + + /* Setting an alternative stack to generate a page fault when + * the signal is raised. + */ + if (sigaltstack(&ss, NULL)) { + perror("sigaltstack\n"); + exit(-1); + } + + /* The signal handler will enable MSR_TS */ + sigaction(SIGUSR1, &usr_sa, NULL); + /* If it does not crash, it will segfault, avoid it to retest */ + sigaction(SIGSEGV, &seg_sa, NULL); + + raise(SIGUSR1); +} + +int tm_signal_context_force_tm(void) +{ + SKIP_IF(!have_htm()); + /* + * Skipping if not running on 64 bits system, since I think it is + * not possible to set mcontext's [MSR] with TS, due to it being 32 + * bits. + */ + SKIP_IF(!is_ppc64le()); + + /* Will get back here after COUNT_MAX interactions */ + getcontext(&main_context); + + if (!first_time++) + tm_trap_test(); + + return EXIT_SUCCESS; +} + +int main(int argc, char **argv) +{ + test_harness(tm_signal_context_force_tm, "tm_signal_context_force_tm"); +} |