diff options
Diffstat (limited to 'arch/powerpc')
49 files changed, 735 insertions, 360 deletions
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 84fdf6857c3..a613d2c82fd 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -200,10 +200,11 @@ static inline void __user *arch_compat_alloc_user_space(long len) /* * We can't access below the stack pointer in the 32bit ABI and - * can access 288 bytes in the 64bit ABI + * can access 288 bytes in the 64bit big-endian ABI, + * or 512 bytes with the new ELFv2 little-endian ABI. */ if (!is_32bit_task()) - usp -= 288; + usp -= USER_REDZONE_SIZE; return (void __user *) (usp - len); } diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index e27e9ad6818..150866b2a3f 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -134,6 +134,7 @@ static inline int dma_supported(struct device *dev, u64 mask) } extern int dma_set_mask(struct device *dev, u64 dma_mask); +extern int __dma_set_mask(struct device *dev, u64 dma_mask); #define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 9e39ceb1d19..d4dd41fb951 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -172,10 +172,20 @@ struct eeh_ops { }; extern struct eeh_ops *eeh_ops; -extern int eeh_subsystem_enabled; +extern bool eeh_subsystem_enabled; extern raw_spinlock_t confirm_error_lock; extern int eeh_probe_mode; +static inline bool eeh_enabled(void) +{ + return eeh_subsystem_enabled; +} + +static inline void eeh_set_enable(bool mode) +{ + eeh_subsystem_enabled = mode; +} + #define EEH_PROBE_MODE_DEV (1<<0) /* From PCI device */ #define EEH_PROBE_MODE_DEVTREE (1<<1) /* From device tree */ @@ -246,7 +256,7 @@ void eeh_remove_device(struct pci_dev *); * If this macro yields TRUE, the caller relays to eeh_check_failure() * which does further tests out of line. */ -#define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_subsystem_enabled) +#define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_enabled()) /* * Reads from a device which has been isolated by EEH will return @@ -257,6 +267,13 @@ void eeh_remove_device(struct pci_dev *); #else /* !CONFIG_EEH */ +static inline bool eeh_enabled(void) +{ + return false; +} + +static inline void eeh_set_enable(bool mode) { } + static inline int eeh_init(void) { return 0; diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index d750336b171..623f2971ce0 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -127,7 +127,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { #ifdef CONFIG_PPC64 - return __pte(pte_update(mm, addr, ptep, ~0UL, 1)); + return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1)); #else return __pte(pte_update(ptep, ~0UL, 0)); #endif diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index f7a8036579b..42632c7a2a4 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -77,6 +77,7 @@ struct iommu_table { #ifdef CONFIG_IOMMU_API struct iommu_group *it_group; #endif + void (*set_bypass)(struct iommu_table *tbl, bool enable); }; /* Pure 2^n version of get_order */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 40157e2ca69..ed82142a325 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -816,8 +816,8 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe, int64_t opal_pci_poll(uint64_t phb_id); int64_t opal_return_cpu(void); -int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val); -int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val); +int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val); +int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val); int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type, uint32_t addr, uint32_t data, uint32_t sz); diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index bc141c950b1..eb9261024f5 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -195,6 +195,7 @@ extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr, static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long clr, + unsigned long set, int huge) { #ifdef PTE_ATOMIC_UPDATES @@ -205,14 +206,15 @@ static inline unsigned long pte_update(struct mm_struct *mm, andi. %1,%0,%6\n\ bne- 1b \n\ andc %1,%0,%4 \n\ + or %1,%1,%7\n\ stdcx. %1,0,%3 \n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*ptep) - : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY) + : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set) : "cc" ); #else unsigned long old = pte_val(*ptep); - *ptep = __pte(old & ~clr); + *ptep = __pte((old & ~clr) | set); #endif /* huge pages use the old page table lock */ if (!huge) @@ -231,9 +233,9 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, { unsigned long old; - if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) + if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) return 0; - old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0); + old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); return (old & _PAGE_ACCESSED) != 0; } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG @@ -252,7 +254,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, if ((pte_val(*ptep) & _PAGE_RW) == 0) return; - pte_update(mm, addr, ptep, _PAGE_RW, 0); + pte_update(mm, addr, ptep, _PAGE_RW, 0, 0); } static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, @@ -261,7 +263,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, if ((pte_val(*ptep) & _PAGE_RW) == 0) return; - pte_update(mm, addr, ptep, _PAGE_RW, 1); + pte_update(mm, addr, ptep, _PAGE_RW, 0, 1); } /* @@ -284,14 +286,14 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0); + unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0); return __pte(old); } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t * ptep) { - pte_update(mm, addr, ptep, ~0UL, 0); + pte_update(mm, addr, ptep, ~0UL, 0, 0); } @@ -506,7 +508,9 @@ extern int pmdp_set_access_flags(struct vm_area_struct *vma, extern unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, unsigned long clr); + pmd_t *pmdp, + unsigned long clr, + unsigned long set); static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) @@ -515,7 +519,7 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) return 0; - old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED); + old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0); return ((old & _PAGE_ACCESSED) != 0); } @@ -542,7 +546,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, if ((pmd_val(*pmdp) & _PAGE_RW) == 0) return; - pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW); + pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0); } #define __HAVE_ARCH_PMDP_SPLITTING_FLUSH diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index f83b6f3e1b3..3ebb188c3ff 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -75,12 +75,34 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +#define ptep_set_numa ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + if ((pte_val(*ptep) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0); + return; +} + #define pmd_numa pmd_numa static inline int pmd_numa(pmd_t pmd) { return pte_numa(pmd_pte(pmd)); } +#define pmdp_set_numa pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA); + return; +} + #define pmd_mknonnuma pmd_mknonnuma static inline pmd_t pmd_mknonnuma(pmd_t pmd) { diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index becc08e6a65..279b80f3bb2 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -28,11 +28,23 @@ #ifdef __powerpc64__ +/* + * Size of redzone that userspace is allowed to use below the stack + * pointer. This is 288 in the 64-bit big-endian ELF ABI, and 512 in + * the new ELFv2 little-endian ABI, so we allow the larger amount. + * + * For kernel code we allow a 288-byte redzone, in order to conserve + * kernel stack space; gcc currently only uses 288 bytes, and will + * hopefully allow explicit control of the redzone size in future. + */ +#define USER_REDZONE_SIZE 512 +#define KERNEL_REDZONE_SIZE 288 + #define STACK_FRAME_OVERHEAD 112 /* size of minimum stack frame */ #define STACK_FRAME_LR_SAVE 2 /* Location of LR in stack frame */ #define STACK_FRAME_REGS_MARKER ASM_CONST(0x7265677368657265) #define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + \ - STACK_FRAME_OVERHEAD + 288) + STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE) #define STACK_FRAME_MARKER 12 /* Size of dummy stack frame allocated when calling signal handler. */ @@ -41,6 +53,8 @@ #else /* __powerpc64__ */ +#define USER_REDZONE_SIZE 0 +#define KERNEL_REDZONE_SIZE 0 #define STACK_FRAME_OVERHEAD 16 /* size of minimum stack frame */ #define STACK_FRAME_LR_SAVE 1 /* Location of LR in stack frame */ #define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773) diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 4ee06fe15de..d0e784e0ff4 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -8,6 +8,7 @@ #ifdef __powerpc64__ +extern char __start_interrupts[]; extern char __end_interrupts[]; extern char __prom_init_toc_start[]; @@ -21,6 +22,17 @@ static inline int in_kernel_text(unsigned long addr) return 0; } +static inline int overlaps_interrupt_vector_text(unsigned long start, + unsigned long end) +{ + unsigned long real_start, real_end; + real_start = __start_interrupts - _stext; + real_end = __end_interrupts - _stext; + + return start < (unsigned long)__va(real_end) && + (unsigned long)__va(real_start) < end; +} + static inline int overlaps_kernel_text(unsigned long start, unsigned long end) { return start < (unsigned long)__init_end && diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h index 0d9cecddf8a..c53f5f6d176 100644 --- a/arch/powerpc/include/asm/vdso.h +++ b/arch/powerpc/include/asm/vdso.h @@ -4,11 +4,11 @@ #ifdef __KERNEL__ /* Default link addresses for the vDSOs */ -#define VDSO32_LBASE 0x100000 -#define VDSO64_LBASE 0x100000 +#define VDSO32_LBASE 0x0 +#define VDSO64_LBASE 0x0 /* Default map addresses for 32bit vDSO */ -#define VDSO32_MBASE VDSO32_LBASE +#define VDSO32_MBASE 0x100000 #define VDSO_VERSION_STRING LINUX_2.6.15 diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 11c1d069d92..7a13f378ca2 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -98,17 +98,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, unsigned long offset, int userbuf) { void *vaddr; + phys_addr_t paddr; if (!csize) return 0; csize = min_t(size_t, csize, PAGE_SIZE); + paddr = pfn << PAGE_SHIFT; - if ((min_low_pfn < pfn) && (pfn < max_pfn)) { - vaddr = __va(pfn << PAGE_SHIFT); + if (memblock_is_region_memory(paddr, csize)) { + vaddr = __va(paddr); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); } else { - vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0); + vaddr = __ioremap(paddr, PAGE_SIZE, 0); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); iounmap(vaddr); } diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 8032b97ccdc..ee78f6e49d6 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -191,12 +191,10 @@ EXPORT_SYMBOL(dma_direct_ops); #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) -int dma_set_mask(struct device *dev, u64 dma_mask) +int __dma_set_mask(struct device *dev, u64 dma_mask) { struct dma_map_ops *dma_ops = get_dma_ops(dev); - if (ppc_md.dma_set_mask) - return ppc_md.dma_set_mask(dev, dma_mask); if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL)) return dma_ops->set_dma_mask(dev, dma_mask); if (!dev->dma_mask || !dma_supported(dev, dma_mask)) @@ -204,6 +202,12 @@ int dma_set_mask(struct device *dev, u64 dma_mask) *dev->dma_mask = dma_mask; return 0; } +int dma_set_mask(struct device *dev, u64 dma_mask) +{ + if (ppc_md.dma_set_mask) + return ppc_md.dma_set_mask(dev, dma_mask); + return __dma_set_mask(dev, dma_mask); +} EXPORT_SYMBOL(dma_set_mask); u64 dma_get_required_mask(struct device *dev) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 148db72a8c4..e7b76a6bf15 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -28,6 +28,7 @@ #include <linux/pci.h> #include <linux/proc_fs.h> #include <linux/rbtree.h> +#include <linux/reboot.h> #include <linux/seq_file.h> #include <linux/spinlock.h> #include <linux/export.h> @@ -89,7 +90,7 @@ /* Platform dependent EEH operations */ struct eeh_ops *eeh_ops = NULL; -int eeh_subsystem_enabled; +bool eeh_subsystem_enabled = false; EXPORT_SYMBOL(eeh_subsystem_enabled); /* @@ -364,7 +365,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) eeh_stats.total_mmio_ffs++; - if (!eeh_subsystem_enabled) + if (!eeh_enabled()) return 0; if (!edev) { @@ -747,6 +748,17 @@ int __exit eeh_ops_unregister(const char *name) return -EEXIST; } +static int eeh_reboot_notifier(struct notifier_block *nb, + unsigned long action, void *unused) +{ + eeh_set_enable(false); + return NOTIFY_DONE; +} + +static struct notifier_block eeh_reboot_nb = { + .notifier_call = eeh_reboot_notifier, +}; + /** * eeh_init - EEH initialization * @@ -778,6 +790,14 @@ int eeh_init(void) if (machine_is(powernv) && cnt++ <= 0) return ret; + /* Register reboot notifier */ + ret = register_reboot_notifier(&eeh_reboot_nb); + if (ret) { + pr_warn("%s: Failed to register notifier (%d)\n", + __func__, ret); + return ret; + } + /* call platform initialization function */ if (!eeh_ops) { pr_warning("%s: Platform EEH operation not found\n", @@ -822,7 +842,7 @@ int eeh_init(void) return ret; } - if (eeh_subsystem_enabled) + if (eeh_enabled()) pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); else pr_warning("EEH: No capable adapters found\n"); @@ -897,7 +917,7 @@ void eeh_add_device_late(struct pci_dev *dev) struct device_node *dn; struct eeh_dev *edev; - if (!dev || !eeh_subsystem_enabled) + if (!dev || !eeh_enabled()) return; pr_debug("EEH: Adding device %s\n", pci_name(dev)); @@ -1005,7 +1025,7 @@ void eeh_remove_device(struct pci_dev *dev) { struct eeh_dev *edev; - if (!dev || !eeh_subsystem_enabled) + if (!dev || !eeh_enabled()) return; edev = pci_dev_to_eeh_dev(dev); @@ -1045,7 +1065,7 @@ void eeh_remove_device(struct pci_dev *dev) static int proc_eeh_show(struct seq_file *m, void *v) { - if (0 == eeh_subsystem_enabled) { + if (!eeh_enabled()) { seq_printf(m, "EEH Subsystem is globally disabled\n"); seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs); } else { diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 7bb30dca4e1..fdc679d309e 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -362,9 +362,13 @@ static void *eeh_rmv_device(void *data, void *userdata) */ if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)) return NULL; + driver = eeh_pcid_get(dev); - if (driver && driver->err_handler) - return NULL; + if (driver) { + eeh_pcid_put(dev); + if (driver->err_handler) + return NULL; + } /* Remove it from PCI subsystem */ pr_debug("EEH: Removing %s without EEH sensitive driver\n", diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 9b27b293a92..b0ded97ee4e 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -74,6 +74,7 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new) */ static int test_24bit_addr(unsigned long ip, unsigned long addr) { + addr = ppc_function_entry((void *)addr); /* use the create_branch to verify that this offset can be branched */ return create_branch((unsigned int *)ip, addr, 0); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index d773dd440a4..88e3ec6e1d9 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1088,6 +1088,14 @@ int iommu_take_ownership(struct iommu_table *tbl) memset(tbl->it_map, 0xff, sz); iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size); + /* + * Disable iommu bypass, otherwise the user can DMA to all of + * our physical memory via the bypass window instead of just + * the pages that has been explicitly mapped into the iommu + */ + if (tbl->set_bypass) + tbl->set_bypass(tbl, false); + return 0; } EXPORT_SYMBOL_GPL(iommu_take_ownership); @@ -1102,6 +1110,10 @@ void iommu_release_ownership(struct iommu_table *tbl) /* Restore bit#0 set by iommu_init_table() */ if (tbl->it_offset == 0) set_bit(0, tbl->it_map); + + /* The kernel owns the device now, we can restore the iommu bypass */ + if (tbl->set_bypass) + tbl->set_bypass(tbl, true); } EXPORT_SYMBOL_GPL(iommu_release_ownership); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 9729b23bfb0..1d0848bba04 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -559,8 +559,13 @@ void exc_lvl_ctx_init(void) #ifdef CONFIG_PPC64 cpu_nr = i; #else +#ifdef CONFIG_SMP cpu_nr = get_hard_smp_processor_id(i); +#else + cpu_nr = 0; #endif +#endif + memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE); tp = critirq_ctx[cpu_nr]; tp->cpu = cpu_nr; diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 75d4f7340da..015ae55c186 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -196,7 +196,9 @@ int overlaps_crashkernel(unsigned long start, unsigned long size) /* Values we need to export to the second kernel via the device tree. */ static phys_addr_t kernel_end; +static phys_addr_t crashk_base; static phys_addr_t crashk_size; +static unsigned long long mem_limit; static struct property kernel_end_prop = { .name = "linux,kernel-end", @@ -207,7 +209,7 @@ static struct property kernel_end_prop = { static struct property crashk_base_prop = { .name = "linux,crashkernel-base", .length = sizeof(phys_addr_t), - .value = &crashk_res.start, + .value = &crashk_base }; static struct property crashk_size_prop = { @@ -219,9 +221,11 @@ static struct property crashk_size_prop = { static struct property memory_limit_prop = { .name = "linux,memory-limit", .length = sizeof(unsigned long long), - .value = &memory_limit, + .value = &mem_limit, }; +#define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG) + static void __init export_crashk_values(struct device_node *node) { struct property *prop; @@ -237,8 +241,9 @@ static void __init export_crashk_values(struct device_node *node) of_remove_property(node, prop); if (crashk_res.start != 0) { + crashk_base = cpu_to_be_ulong(crashk_res.start), of_add_property(node, &crashk_base_prop); - crashk_size = resource_size(&crashk_res); + crashk_size = cpu_to_be_ulong(resource_size(&crashk_res)); of_add_property(node, &crashk_size_prop); } @@ -246,6 +251,7 @@ static void __init export_crashk_values(struct device_node *node) * memory_limit is required by the kexec-tools to limit the * crash regions to the actual memory used. */ + mem_limit = cpu_to_be_ulong(memory_limit); of_update_property(node, &memory_limit_prop); } @@ -264,7 +270,7 @@ static int __init kexec_setup(void) of_remove_property(node, prop); /* information needed by userspace when using default_machine_kexec */ - kernel_end = __pa(_end); + kernel_end = cpu_to_be_ulong(__pa(_end)); of_add_property(node, &kernel_end_prop); export_crashk_values(node); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index be4e6d648f6..59d229a2a3e 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -369,6 +369,7 @@ void default_machine_kexec(struct kimage *image) /* Values we need to export to the second kernel via the device tree. */ static unsigned long htab_base; +static unsigned long htab_size; static struct property htab_base_prop = { .name = "linux,htab-base", @@ -379,7 +380,7 @@ static struct property htab_base_prop = { static struct property htab_size_prop = { .name = "linux,htab-size", .length = sizeof(unsigned long), - .value = &htab_size_bytes, + .value = &htab_size, }; static int __init export_htab_values(void) @@ -403,8 +404,9 @@ static int __init export_htab_values(void) if (prop) of_remove_property(node, prop); - htab_base = __pa(htab_address); + htab_base = cpu_to_be64(__pa(htab_address)); of_add_property(node, &htab_base_prop); + htab_size = cpu_to_be64(htab_size_bytes); of_add_property(node, &htab_size_prop); of_node_put(node); diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 879f09620f8..7c6bb4b17b4 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -57,11 +57,14 @@ _GLOBAL(call_do_softirq) mtlr r0 blr +/* + * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp); + */ _GLOBAL(call_do_irq) mflr r0 stw r0,4(r1) lwz r10,THREAD+KSP_LIMIT(r2) - addi r11,r3,THREAD_INFO_GAP + addi r11,r4,THREAD_INFO_GAP stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4) mr r1,r4 stw r10,8(r1) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 8d4c247f173..af064d28b36 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1048,6 +1048,15 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) flush_altivec_to_thread(src); flush_vsx_to_thread(src); flush_spe_to_thread(src); + /* + * Flush TM state out so we can copy it. __switch_to_tm() does this + * flush but it removes the checkpointed state from the current CPU and + * transitions the CPU out of TM mode. Hence we need to call + * tm_recheckpoint_new_task() (on the same task) to restore the + * checkpointed state back and the TM mode. + */ + __switch_to_tm(src); + tm_recheckpoint_new_task(src); *dst = *src; diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index b47a0e1ab00..d88736fbece 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -69,8 +69,8 @@ _GLOBAL(relocate) * R_PPC64_RELATIVE ones. */ mtctr r8 -5: lwz r0,12(9) /* ELF64_R_TYPE(reloc->r_info) */ - cmpwi r0,R_PPC64_RELATIVE +5: ld r0,8(9) /* ELF64_R_TYPE(reloc->r_info) */ + cmpdi r0,R_PPC64_RELATIVE bne 6f ld r6,0(r9) /* reloc->r_offset */ ld r0,16(r9) /* reloc->r_addend */ @@ -81,6 +81,7 @@ _GLOBAL(relocate) 6: blr +.balign 8 p_dyn: .llong __dynamic_start - 0b p_rela: .llong __rela_dyn_start - 0b p_st: .llong _stext - 0b diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 2b0da27eaee..04cc4fcca78 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -247,7 +247,12 @@ static void __init exc_lvl_early_init(void) /* interrupt stacks must be in lowmem, we get that for free on ppc32 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */ for_each_possible_cpu(i) { +#ifdef CONFIG_SMP hw_cpu = get_hard_smp_processor_id(i); +#else + hw_cpu = 0; +#endif + critirq_ctx[hw_cpu] = (struct thread_info *) __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); #ifdef CONFIG_BOOKE diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index e35bf773df7..8d253c29649 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -65,8 +65,8 @@ struct rt_sigframe { struct siginfo __user *pinfo; void __user *puc; struct siginfo info; - /* 64 bit ABI allows for 288 bytes below sp before decrementing it. */ - char abigap[288]; + /* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */ + char abigap[USER_REDZONE_SIZE]; } __attribute__ ((aligned (16))); static const char fmt32[] = KERN_INFO \ diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S index 79683d0393f..6ac107ac402 100644 --- a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S @@ -6,7 +6,7 @@ .globl vdso32_start, vdso32_end .balign PAGE_SIZE vdso32_start: - .incbin "arch/powerpc/kernel/vdso32/vdso32.so" + .incbin "arch/powerpc/kernel/vdso32/vdso32.so.dbg" .balign PAGE_SIZE vdso32_end: diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S index 8df9e246300..df60fca6a13 100644 --- a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S @@ -6,7 +6,7 @@ .globl vdso64_start, vdso64_end .balign PAGE_SIZE vdso64_start: - .incbin "arch/powerpc/kernel/vdso64/vdso64.so" + .incbin "arch/powerpc/kernel/vdso64/vdso64.so.dbg" .balign PAGE_SIZE vdso64_end: diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index e66d4ec04d9..818dce344e8 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1504,73 +1504,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 1: addi r8,r8,16 .endr - /* Save DEC */ - mfspr r5,SPRN_DEC - mftb r6 - extsw r5,r5 - add r5,r5,r6 - std r5,VCPU_DEC_EXPIRES(r9) - -BEGIN_FTR_SECTION - b 8f -END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) - /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */ - mfmsr r8 - li r0, 1 - rldimi r8, r0, MSR_TM_LG, 63-MSR_TM_LG - mtmsrd r8 - - /* Save POWER8-specific registers */ - mfspr r5, SPRN_IAMR - mfspr r6, SPRN_PSPB - mfspr r7, SPRN_FSCR - std r5, VCPU_IAMR(r9) - stw r6, VCPU_PSPB(r9) - std r7, VCPU_FSCR(r9) - mfspr r5, SPRN_IC - mfspr r6, SPRN_VTB - mfspr r7, SPRN_TAR - std r5, VCPU_IC(r9) - std r6, VCPU_VTB(r9) - std r7, VCPU_TAR(r9) -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM - mfspr r5, SPRN_TFHAR - mfspr r6, SPRN_TFIAR - mfspr r7, SPRN_TEXASR - std r5, VCPU_TFHAR(r9) - std r6, VCPU_TFIAR(r9) - std r7, VCPU_TEXASR(r9) -#endif - mfspr r8, SPRN_EBBHR - std r8, VCPU_EBBHR(r9) - mfspr r5, SPRN_EBBRR - mfspr r6, SPRN_BESCR - mfspr r7, SPRN_CSIGR - mfspr r8, SPRN_TACR - std r5, VCPU_EBBRR(r9) - std r6, VCPU_BESCR(r9) - std r7, VCPU_CSIGR(r9) - std r8, VCPU_TACR(r9) - mfspr r5, SPRN_TCSCR - mfspr r6, SPRN_ACOP - mfspr r7, SPRN_PID - mfspr r8, SPRN_WORT - std r5, VCPU_TCSCR(r9) - std r6, VCPU_ACOP(r9) - stw r7, VCPU_GUEST_PID(r9) - std r8, VCPU_WORT(r9) -8: - - /* Save and reset AMR and UAMOR before turning on the MMU */ -BEGIN_FTR_SECTION - mfspr r5,SPRN_AMR - mfspr r6,SPRN_UAMOR - std r5,VCPU_AMR(r9) - std r6,VCPU_UAMOR(r9) - li r6,0 - mtspr SPRN_AMR,r6 -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206) - /* Unset guest mode */ li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) @@ -2203,7 +2136,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif mfspr r6,SPRN_VRSAVE - stw r6,VCPU_VRSAVE(r3) + stw r6,VCPU_VRSAVE(r31) mtlr r30 mtmsrd r5 isync @@ -2240,7 +2173,7 @@ BEGIN_FTR_SECTION bl .load_vr_state END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif - lwz r7,VCPU_VRSAVE(r4) + lwz r7,VCPU_VRSAVE(r31) mtspr SPRN_VRSAVE,r7 mtlr r30 mr r4,r31 diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index de6881259ae..d766d6ee33f 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -207,6 +207,20 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, if (overlaps_kernel_text(vaddr, vaddr + step)) tprot &= ~HPTE_R_N; + /* + * If relocatable, check if it overlaps interrupt vectors that + * are copied down to real 0. For relocatable kernel + * (e.g. kdump case) we copy interrupt vectors down to real + * address 0. Mark that region as executable. This is + * because on p8 system with relocation on exception feature + * enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence + * in order to execute the interrupt handlers in virtual + * mode the vector region need to be marked as executable. + */ + if ((PHYSICAL_START > MEMORY_START) && + overlaps_interrupt_vector_text(vaddr, vaddr + step)) + tprot &= ~HPTE_R_N; + hash = hpt_hash(vpn, shift, ssize); hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 65b7b65e870..62bf5e8e78d 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -510,7 +510,8 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, } unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, unsigned long clr) + pmd_t *pmdp, unsigned long clr, + unsigned long set) { unsigned long old, tmp; @@ -526,14 +527,15 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, andi. %1,%0,%6\n\ bne- 1b \n\ andc %1,%0,%4 \n\ + or %1,%1,%7\n\ stdcx. %1,0,%3 \n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*pmdp) - : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY) + : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY), "r" (set) : "cc" ); #else old = pmd_val(*pmdp); - *pmdp = __pmd(old & ~clr); + *pmdp = __pmd((old & ~clr) | set); #endif if (old & _PAGE_HASHPTE) hpte_do_hugepage_flush(mm, addr, pmdp); @@ -708,7 +710,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { - pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT); + pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0); } /* @@ -835,7 +837,7 @@ pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long old; pgtable_t *pgtable_slot; - old = pmd_hugepage_update(mm, addr, pmdp, ~0UL); + old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0); old_pmd = __pmd(old); /* * We have pmd == none and we are holding page_table_lock. diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index a770df2dae7..6c0b1f5f8d2 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -78,7 +78,7 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr, pte = pte_offset_map_lock(mm, pmd, addr, &ptl); arch_enter_lazy_mmu_mode(); for (; npages > 0; --npages) { - pte_update(mm, addr, pte, 0, 0); + pte_update(mm, addr, pte, 0, 0, 0); addr += PAGE_SIZE; ++pte; } diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 29b89e863d7..67cf22083f4 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1147,6 +1147,9 @@ static void power_pmu_enable(struct pmu *pmu) mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]); mb(); + if (cpuhw->bhrb_users) + ppmu->config_bhrb(cpuhw->bhrb_filter); + write_mmcr0(cpuhw, mmcr0); /* @@ -1158,8 +1161,6 @@ static void power_pmu_enable(struct pmu *pmu) } out: - if (cpuhw->bhrb_users) - ppmu->config_bhrb(cpuhw->bhrb_filter); local_irq_restore(flags); } diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index a3f7abd2f13..96cee20dcd3 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -25,6 +25,37 @@ #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 + /* * Raw event encoding for POWER8: @@ -557,6 +588,8 @@ static int power8_generic_events[] = { [PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_CMPL, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BRU_FIN, [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL, + [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1, + [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1, }; static u64 power8_bhrb_filter_map(u64 branch_sample_type) @@ -596,6 +629,116 @@ static void power8_config_bhrb(u64 pmu_bhrb_filter) mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter)); } +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_LD_REF_L1, + [ C(RESULT_MISS) ] = PM_LD_MISS_L1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_ST_MISS_L1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_L1_PREF, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(L1I) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_INST_FROM_L1, + [ C(RESULT_MISS) ] = PM_L1_ICACHE_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = PM_L1_DEMAND_WRITE, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_IC_PREF_WRITE, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_DATA_FROM_L3, + [ C(RESULT_MISS) ] = PM_DATA_FROM_L3MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = PM_L2_ST, + [ C(RESULT_MISS) ] = PM_L2_ST_MISS, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_DTLB_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_ITLB_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_BRU_FIN, + [ C(RESULT_MISS) ] = PM_BR_MPRED_CMPL, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +#undef C + static struct power_pmu power8_pmu = { .name = "POWER8", .n_counter = 6, @@ -611,6 +754,7 @@ static struct power_pmu power8_pmu = { .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB, .n_generic = ARRAY_SIZE(power8_generic_events), .generic_events = power8_generic_events, + .cache_events = &power8_cache_events, .attr_groups = power8_pmu_attr_groups, .bhrb_nr = 32, }; diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c index 5ec1e47a0d7..e865d748179 100644 --- a/arch/powerpc/platforms/cell/ras.c +++ b/arch/powerpc/platforms/cell/ras.c @@ -123,7 +123,8 @@ static int __init cbe_ptcal_enable_on_node(int nid, int order) area->nid = nid; area->order = order; - area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL|GFP_THISNODE, + area->pages = alloc_pages_exact_node(area->nid, + GFP_KERNEL|__GFP_THISNODE, area->order); if (!area->pages) { diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index e1e71618b70..253fefe3d1a 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -44,7 +44,8 @@ static int ioda_eeh_event(struct notifier_block *nb, /* We simply send special EEH event */ if ((changed_evts & OPAL_EVENT_PCI_ERROR) && - (events & OPAL_EVENT_PCI_ERROR)) + (events & OPAL_EVENT_PCI_ERROR) && + eeh_enabled()) eeh_send_failure_event(NULL); return 0; @@ -113,6 +114,7 @@ DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get, ioda_eeh_inbB_dbgfs_set, "0x%llx\n"); #endif /* CONFIG_DEBUG_FS */ + /** * ioda_eeh_post_init - Chip dependent post initialization * @hose: PCI controller @@ -220,6 +222,22 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option) return ret; } +static void ioda_eeh_phb_diag(struct pci_controller *hose) +{ + struct pnv_phb *phb = hose->private_data; + long rc; + + rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob, + PNV_PCI_DIAG_BUF_SIZE); + if (rc != OPAL_SUCCESS) { + pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n", + __func__, hose->global_number, rc); + return; + } + + pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); +} + /** * ioda_eeh_get_state - Retrieve the state of PE * @pe: EEH PE @@ -271,6 +289,9 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) result |= EEH_STATE_DMA_ACTIVE; result |= EEH_STATE_MMIO_ENABLED; result |= EEH_STATE_DMA_ENABLED; + } else if (!(pe->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + ioda_eeh_phb_diag(hose); } return result; @@ -314,6 +335,15 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) __func__, fstate, hose->global_number, pe_no); } + /* Dump PHB diag-data for frozen PE */ + if (result != EEH_STATE_NOT_SUPPORT && + (result & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) != + (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) && + !(pe->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + ioda_eeh_phb_diag(hose); + } + return result; } @@ -489,8 +519,7 @@ static int ioda_eeh_bridge_reset(struct pci_controller *hose, static int ioda_eeh_reset(struct eeh_pe *pe, int option) { struct pci_controller *hose = pe->phb; - struct eeh_dev *edev; - struct pci_dev *dev; + struct pci_bus *bus; int ret; /* @@ -519,73 +548,17 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option) if (pe->type & EEH_PE_PHB) { ret = ioda_eeh_phb_reset(hose, option); } else { - if (pe->type & EEH_PE_DEVICE) { - /* - * If it's device PE, we didn't refer to the parent - * PCI bus yet. So we have to figure it out indirectly. - */ - edev = list_first_entry(&pe->edevs, - struct eeh_dev, list); - dev = eeh_dev_to_pci_dev(edev); - dev = dev->bus->self; - } else { - /* - * If it's bus PE, the parent PCI bus is already there - * and just pick it up. - */ - dev = pe->bus->self; - } - - /* - * Do reset based on the fact that the direct upstream bridge - * is root bridge (port) or not. - */ - if (dev->bus->number == 0) + bus = eeh_pe_bus_get(pe); + if (pci_is_root_bus(bus)) ret = ioda_eeh_root_reset(hose, option); else - ret = ioda_eeh_bridge_reset(hose, dev, option); + ret = ioda_eeh_bridge_reset(hose, bus->self, option); } return ret; } /** - * ioda_eeh_get_log - Retrieve error log - * @pe: EEH PE - * @severity: Severity level of the log - * @drv_log: buffer to store the log - * @len: space of the log buffer - * - * The function is used to retrieve error log from P7IOC. - */ -static int ioda_eeh_get_log(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len) -{ - s64 ret; - unsigned long flags; - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - - spin_lock_irqsave(&phb->lock, flags); - - ret = opal_pci_get_phb_diag_data2(phb->opal_id, - phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE); - if (ret) { - spin_unlock_irqrestore(&phb->lock, flags); - pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n", - __func__, hose->global_number, pe->addr, ret); - return -EIO; - } - - /* The PHB diag-data is always indicative */ - pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); - - spin_unlock_irqrestore(&phb->lock, flags); - - return 0; -} - -/** * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE * @pe: EEH PE * @@ -666,22 +639,6 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose) } } -static void ioda_eeh_phb_diag(struct pci_controller *hose) -{ - struct pnv_phb *phb = hose->private_data; - long rc; - - rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob, - PNV_PCI_DIAG_BUF_SIZE); - if (rc != OPAL_SUCCESS) { - pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n", - __func__, hose->global_number, rc); - return; - } - - pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); -} - static int ioda_eeh_get_phb_pe(struct pci_controller *hose, struct eeh_pe **pe) { @@ -855,6 +812,20 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) } /* + * EEH core will try recover from fenced PHB or + * frozen PE. In the time for frozen PE, EEH core + * enable IO path for that before collecting logs, + * but it ruins the site. So we have to dump the + * log in advance here. + */ + if ((ret == EEH_NEXT_ERR_FROZEN_PE || + ret == EEH_NEXT_ERR_FENCED_PHB) && + !((*pe)->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + ioda_eeh_phb_diag(hose); + } + + /* * If we have no errors on the specific PHB or only * informative error there, we continue poking it. * Otherwise, we need actions to be taken by upper @@ -872,7 +843,6 @@ struct pnv_eeh_ops ioda_eeh_ops = { .set_option = ioda_eeh_set_option, .get_state = ioda_eeh_get_state, .reset = ioda_eeh_reset, - .get_log = ioda_eeh_get_log, .configure_bridge = ioda_eeh_configure_bridge, .next_error = ioda_eeh_next_error }; diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index a79fddc5e74..a59788e83b8 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -145,7 +145,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * Enable EEH explicitly so that we will do EEH check * while accessing I/O stuff */ - eeh_subsystem_enabled = 1; + eeh_set_enable(true); /* Save memory bars */ eeh_save_bars(edev); diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c index 4fbf276ac99..4cd2ea6c0db 100644 --- a/arch/powerpc/platforms/powernv/opal-xscom.c +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -71,11 +71,11 @@ static int opal_xscom_err_xlate(int64_t rc) } } -static u64 opal_scom_unmangle(u64 reg) +static u64 opal_scom_unmangle(u64 addr) { /* * XSCOM indirect addresses have the top bit set. Additionally - * the reset of the top 3 nibbles is always 0. + * the rest of the top 3 nibbles is always 0. * * Because the debugfs interface uses signed offsets and shifts * the address left by 3, we basically cannot use the top 4 bits @@ -86,10 +86,13 @@ static u64 opal_scom_unmangle(u64 reg) * conversion here. To leave room for further xscom address * expansion, we only clear out the top byte * + * For in-kernel use, we also support the real indirect bit, so + * we test for any of the top 5 bits + * */ - if (reg & (1ull << 59)) - reg = (reg & ~(0xffull << 56)) | (1ull << 63); - return reg; + if (addr & (0x1full << 59)) + addr = (addr & ~(0xffull << 56)) | (1ull << 63); + return addr; } static int opal_scom_read(scom_map_t map, u64 reg, u64 *value) @@ -98,8 +101,8 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value) int64_t rc; __be64 v; - reg = opal_scom_unmangle(reg); - rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v)); + reg = opal_scom_unmangle(m->addr + reg); + rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v)); *value = be64_to_cpu(v); return opal_xscom_err_xlate(rc); } @@ -109,8 +112,8 @@ static int opal_scom_write(scom_map_t map, u64 reg, u64 value) struct opal_scom_map *m = map; int64_t rc; - reg = opal_scom_unmangle(reg); - rc = opal_xscom_write(m->chip, m->addr + reg, value); + reg = opal_scom_unmangle(m->addr + reg); + rc = opal_xscom_write(m->chip, reg, value); return opal_xscom_err_xlate(rc); } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 7d6dcc6d5fa..3b2b4fb3585 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -21,6 +21,7 @@ #include <linux/irq.h> #include <linux/io.h> #include <linux/msi.h> +#include <linux/memblock.h> #include <asm/sections.h> #include <asm/io.h> @@ -460,9 +461,39 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev return; pe = &phb->ioda.pe_array[pdn->pe_number]; + WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops); set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table); } +static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, + struct pci_dev *pdev, u64 dma_mask) +{ + struct pci_dn *pdn = pci_get_pdn(pdev); + struct pnv_ioda_pe *pe; + uint64_t top; + bool bypass = false; + + if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) + return -ENODEV;; + + pe = &phb->ioda.pe_array[pdn->pe_number]; + if (pe->tce_bypass_enabled) { + top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1; + bypass = (dma_mask >= top); + } + + if (bypass) { + dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n"); + set_dma_ops(&pdev->dev, &dma_direct_ops); + set_dma_offset(&pdev->dev, pe->tce_bypass_base); + } else { + dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n"); + set_dma_ops(&pdev->dev, &dma_iommu_ops); + set_iommu_table_base(&pdev->dev, &pe->tce32_table); + } + return 0; +} + static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) { struct pci_dev *dev; @@ -657,6 +688,56 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, __free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs)); } +static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable) +{ + struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, + tce32_table); + uint16_t window_id = (pe->pe_number << 1 ) + 1; + int64_t rc; + + pe_info(pe, "%sabling 64-bit DMA bypass\n", enable ? "En" : "Dis"); + if (enable) { + phys_addr_t top = memblock_end_of_DRAM(); + + top = roundup_pow_of_two(top); + rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, + pe->pe_number, + window_id, + pe->tce_bypass_base, + top); + } else { + rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, + pe->pe_number, + window_id, + pe->tce_bypass_base, + 0); + + /* + * We might want to reset the DMA ops of all devices on + * this PE. However in theory, that shouldn't be necessary + * as this is used for VFIO/KVM pass-through and the device + * hasn't yet been returned to its kernel driver + */ + } + if (rc) + pe_err(pe, "OPAL error %lld configuring bypass window\n", rc); + else + pe->tce_bypass_enabled = enable; +} + +static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe) +{ + /* TVE #1 is selected by PCI address bit 59 */ + pe->tce_bypass_base = 1ull << 59; + + /* Install set_bypass callback for VFIO */ + pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass; + + /* Enable bypass by default */ + pnv_pci_ioda2_set_bypass(&pe->tce32_table, true); +} + static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { @@ -727,6 +808,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, else pnv_ioda_setup_bus_dma(pe, pe->pbus); + /* Also create a bypass window */ + pnv_pci_ioda2_setup_bypass_pe(phb, pe); return; fail: if (pe->tce32_seg >= 0) @@ -1286,6 +1369,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, /* Setup TCEs */ phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup; + phb->dma_set_mask = pnv_pci_ioda_dma_set_mask; /* Setup shutdown function for kexec */ phb->shutdown = pnv_pci_ioda_shutdown; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index b555ebc57ef..8518817dcdf 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -134,57 +134,72 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose, pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n", hose->global_number, common->version); - pr_info(" brdgCtl: %08x\n", data->brdgCtl); - - pr_info(" portStatusReg: %08x\n", data->portStatusReg); - pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus); - pr_info(" busAgentStatus: %08x\n", data->busAgentStatus); - - pr_info(" deviceStatus: %08x\n", data->deviceStatus); - pr_info(" slotStatus: %08x\n", data->slotStatus); - pr_info(" linkStatus: %08x\n", data->linkStatus); - pr_info(" devCmdStatus: %08x\n", data->devCmdStatus); - pr_info(" devSecStatus: %08x\n", data->devSecStatus); - - pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus); - pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus); - pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus); - pr_info(" tlpHdr1: %08x\n", data->tlpHdr1); - pr_info(" tlpHdr2: %08x\n", data->tlpHdr2); - pr_info(" tlpHdr3: %08x\n", data->tlpHdr3); - pr_info(" tlpHdr4: %08x\n", data->tlpHdr4); - pr_info(" sourceId: %08x\n", data->sourceId); - pr_info(" errorClass: %016llx\n", data->errorClass); - pr_info(" correlator: %016llx\n", data->correlator); - pr_info(" p7iocPlssr: %016llx\n", data->p7iocPlssr); - pr_info(" p7iocCsr: %016llx\n", data->p7iocCsr); - pr_info(" lemFir: %016llx\n", data->lemFir); - pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask); - pr_info(" lemWOF: %016llx\n", data->lemWOF); - pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus); - pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus); - pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0); - pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1); - pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus); - pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus); - pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0); - pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1); - pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus); - pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus); - pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0); - pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1); - pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus); - pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus); - pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0); - pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1); + if (data->brdgCtl) + pr_info(" brdgCtl: %08x\n", + data->brdgCtl); + if (data->portStatusReg || data->rootCmplxStatus || + data->busAgentStatus) + pr_info(" UtlSts: %08x %08x %08x\n", + data->portStatusReg, data->rootCmplxStatus, + data->busAgentStatus); + if (data->deviceStatus || data->slotStatus || + data->linkStatus || data->devCmdStatus || + data->devSecStatus) + pr_info(" RootSts: %08x %08x %08x %08x %08x\n", + data->deviceStatus, data->slotStatus, + data->linkStatus, data->devCmdStatus, + data->devSecStatus); + if (data->rootErrorStatus || data->uncorrErrorStatus || + data->corrErrorStatus) + pr_info(" RootErrSts: %08x %08x %08x\n", + data->rootErrorStatus, data->uncorrErrorStatus, + data->corrErrorStatus); + if (data->tlpHdr1 || data->tlpHdr2 || + data->tlpHdr3 || data->tlpHdr4) + pr_info(" RootErrLog: %08x %08x %08x %08x\n", + data->tlpHdr1, data->tlpHdr2, + data->tlpHdr3, data->tlpHdr4); + if (data->sourceId || data->errorClass || + data->correlator) + pr_info(" RootErrLog1: %08x %016llx %016llx\n", + data->sourceId, data->errorClass, + data->correlator); + if (data->p7iocPlssr || data->p7iocCsr) + pr_info(" PhbSts: %016llx %016llx\n", + data->p7iocPlssr, data->p7iocCsr); + if (data->lemFir || data->lemErrorMask || + data->lemWOF) + pr_info(" Lem: %016llx %016llx %016llx\n", + data->lemFir, data->lemErrorMask, + data->lemWOF); + if (data->phbErrorStatus || data->phbFirstErrorStatus || + data->phbErrorLog0 || data->phbErrorLog1) + pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n", + data->phbErrorStatus, data->phbFirstErrorStatus, + data->phbErrorLog0, data->phbErrorLog1); + if (data->mmioErrorStatus || data->mmioFirstErrorStatus || + data->mmioErrorLog0 || data->mmioErrorLog1) + pr_info(" OutErr: %016llx %016llx %016llx %016llx\n", + data->mmioErrorStatus, data->mmioFirstErrorStatus, + data->mmioErrorLog0, data->mmioErrorLog1); + if (data->dma0ErrorStatus || data->dma0FirstErrorStatus || + data->dma0ErrorLog0 || data->dma0ErrorLog1) + pr_info(" InAErr: %016llx %016llx %016llx %016llx\n", + data->dma0ErrorStatus, data->dma0FirstErrorStatus, + data->dma0ErrorLog0, data->dma0ErrorLog1); + if (data->dma1ErrorStatus || data->dma1FirstErrorStatus || + data->dma1ErrorLog0 || data->dma1ErrorLog1) + pr_info(" InBErr: %016llx %016llx %016llx %016llx\n", + data->dma1ErrorStatus, data->dma1FirstErrorStatus, + data->dma1ErrorLog0, data->dma1ErrorLog1); for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) { if ((data->pestA[i] >> 63) == 0 && (data->pestB[i] >> 63) == 0) continue; - pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]); - pr_info(" PESTB: %016llx\n", data->pestB[i]); + pr_info(" PE[%3d] A/B: %016llx %016llx\n", + i, data->pestA[i], data->pestB[i]); } } @@ -197,62 +212,77 @@ static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose, data = (struct OpalIoPhb3ErrorData*)common; pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n", hose->global_number, common->version); - - pr_info(" brdgCtl: %08x\n", data->brdgCtl); - - pr_info(" portStatusReg: %08x\n", data->portStatusReg); - pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus); - pr_info(" busAgentStatus: %08x\n", data->busAgentStatus); - - pr_info(" deviceStatus: %08x\n", data->deviceStatus); - pr_info(" slotStatus: %08x\n", data->slotStatus); - pr_info(" linkStatus: %08x\n", data->linkStatus); - pr_info(" devCmdStatus: %08x\n", data->devCmdStatus); - pr_info(" devSecStatus: %08x\n", data->devSecStatus); - - pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus); - pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus); - pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus); - pr_info(" tlpHdr1: %08x\n", data->tlpHdr1); - pr_info(" tlpHdr2: %08x\n", data->tlpHdr2); - pr_info(" tlpHdr3: %08x\n", data->tlpHdr3); - pr_info(" tlpHdr4: %08x\n", data->tlpHdr4); - pr_info(" sourceId: %08x\n", data->sourceId); - pr_info(" errorClass: %016llx\n", data->errorClass); - pr_info(" correlator: %016llx\n", data->correlator); - - pr_info(" nFir: %016llx\n", data->nFir); - pr_info(" nFirMask: %016llx\n", data->nFirMask); - pr_info(" nFirWOF: %016llx\n", data->nFirWOF); - pr_info(" PhbPlssr: %016llx\n", data->phbPlssr); - pr_info(" PhbCsr: %016llx\n", data->phbCsr); - pr_info(" lemFir: %016llx\n", data->lemFir); - pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask); - pr_info(" lemWOF: %016llx\n", data->lemWOF); - pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus); - pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus); - pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0); - pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1); - pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus); - pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus); - pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0); - pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1); - pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus); - pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus); - pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0); - pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1); - pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus); - pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus); - pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0); - pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1); + if (data->brdgCtl) + pr_info(" brdgCtl: %08x\n", + data->brdgCtl); + if (data->portStatusReg || data->rootCmplxStatus || + data->busAgentStatus) + pr_info(" UtlSts: %08x %08x %08x\n", + data->portStatusReg, data->rootCmplxStatus, + data->busAgentStatus); + if (data->deviceStatus || data->slotStatus || + data->linkStatus || data->devCmdStatus || + data->devSecStatus) + pr_info(" RootSts: %08x %08x %08x %08x %08x\n", + data->deviceStatus, data->slotStatus, + data->linkStatus, data->devCmdStatus, + data->devSecStatus); + if (data->rootErrorStatus || data->uncorrErrorStatus || + data->corrErrorStatus) + pr_info(" RootErrSts: %08x %08x %08x\n", + data->rootErrorStatus, data->uncorrErrorStatus, + data->corrErrorStatus); + if (data->tlpHdr1 || data->tlpHdr2 || + data->tlpHdr3 || data->tlpHdr4) + pr_info(" RootErrLog: %08x %08x %08x %08x\n", + data->tlpHdr1, data->tlpHdr2, + data->tlpHdr3, data->tlpHdr4); + if (data->sourceId || data->errorClass || + data->correlator) + pr_info(" RootErrLog1: %08x %016llx %016llx\n", + data->sourceId, data->errorClass, + data->correlator); + if (data->nFir || data->nFirMask || + data->nFirWOF) + pr_info(" nFir: %016llx %016llx %016llx\n", + data->nFir, data->nFirMask, + data->nFirWOF); + if (data->phbPlssr || data->phbCsr) + pr_info(" PhbSts: %016llx %016llx\n", + data->phbPlssr, data->phbCsr); + if (data->lemFir || data->lemErrorMask || + data->lemWOF) + pr_info(" Lem: %016llx %016llx %016llx\n", + data->lemFir, data->lemErrorMask, + data->lemWOF); + if (data->phbErrorStatus || data->phbFirstErrorStatus || + data->phbErrorLog0 || data->phbErrorLog1) + pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n", + data->phbErrorStatus, data->phbFirstErrorStatus, + data->phbErrorLog0, data->phbErrorLog1); + if (data->mmioErrorStatus || data->mmioFirstErrorStatus || + data->mmioErrorLog0 || data->mmioErrorLog1) + pr_info(" OutErr: %016llx %016llx %016llx %016llx\n", + data->mmioErrorStatus, data->mmioFirstErrorStatus, + data->mmioErrorLog0, data->mmioErrorLog1); + if (data->dma0ErrorStatus || data->dma0FirstErrorStatus || + data->dma0ErrorLog0 || data->dma0ErrorLog1) + pr_info(" InAErr: %016llx %016llx %016llx %016llx\n", + data->dma0ErrorStatus, data->dma0FirstErrorStatus, + data->dma0ErrorLog0, data->dma0ErrorLog1); + if (data->dma1ErrorStatus || data->dma1FirstErrorStatus || + data->dma1ErrorLog0 || data->dma1ErrorLog1) + pr_info(" InBErr: %016llx %016llx %016llx %016llx\n", + data->dma1ErrorStatus, data->dma1FirstErrorStatus, + data->dma1ErrorLog0, data->dma1ErrorLog1); for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) { if ((data->pestA[i] >> 63) == 0 && (data->pestB[i] >> 63) == 0) continue; - pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]); - pr_info(" PESTB: %016llx\n", data->pestB[i]); + pr_info(" PE[%3d] A/B: %016llx %016llx\n", + i, data->pestA[i], data->pestB[i]); } } @@ -634,6 +664,16 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) pnv_pci_dma_fallback_setup(hose, pdev); } +int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) +{ + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + struct pnv_phb *phb = hose->private_data; + + if (phb && phb->dma_set_mask) + return phb->dma_set_mask(phb, pdev, dma_mask); + return __dma_set_mask(&pdev->dev, dma_mask); +} + void pnv_pci_shutdown(void) { struct pci_controller *hose; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 13f1942a9a5..cde16944277 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -54,7 +54,9 @@ struct pnv_ioda_pe { struct iommu_table tce32_table; phys_addr_t tce_inval_reg_phys; - /* XXX TODO: Add support for additional 64-bit iommus */ + /* 64-bit TCE bypass region */ + bool tce_bypass_enabled; + uint64_t tce_bypass_base; /* MSIs. MVE index is identical for for 32 and 64 bit MSI * and -1 if not supported. (It's actually identical to the @@ -113,6 +115,8 @@ struct pnv_phb { unsigned int hwirq, unsigned int virq, unsigned int is_64, struct msi_msg *msg); void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev); + int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev, + u64 dma_mask); void (*fixup_phb)(struct pci_controller *hose); u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn); void (*shutdown)(struct pnv_phb *phb); diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index de6819be1f9..0051e108ef0 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -7,12 +7,20 @@ extern void pnv_smp_init(void); static inline void pnv_smp_init(void) { } #endif +struct pci_dev; + #ifdef CONFIG_PCI extern void pnv_pci_init(void); extern void pnv_pci_shutdown(void); +extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask); #else static inline void pnv_pci_init(void) { } static inline void pnv_pci_shutdown(void) { } + +static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) +{ + return -ENODEV; +} #endif extern void pnv_lpc_init(void); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 21166f65c97..110f4fbd319 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -27,6 +27,7 @@ #include <linux/interrupt.h> #include <linux/bug.h> #include <linux/cpuidle.h> +#include <linux/pci.h> #include <asm/machdep.h> #include <asm/firmware.h> @@ -141,6 +142,13 @@ static void pnv_progress(char *s, unsigned short hex) { } +static int pnv_dma_set_mask(struct device *dev, u64 dma_mask) +{ + if (dev_is_pci(dev)) + return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask); + return __dma_set_mask(dev, dma_mask); +} + static void pnv_shutdown(void) { /* Let the PCI code clear up IODA tables */ @@ -238,6 +246,7 @@ define_machine(powernv) { .machine_shutdown = pnv_shutdown, .power_save = powernv_idle, .calibrate_decr = generic_calibrate_decr, + .dma_set_mask = pnv_dma_set_mask, #ifdef CONFIG_KEXEC .kexec_cpu_down = pnv_kexec_cpu_down, #endif diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 37300f6ee24..80b1d57c306 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -20,6 +20,7 @@ config PPC_PSERIES select PPC_DOORBELL select HAVE_CONTEXT_TRACKING select HOTPLUG_CPU if SMP + select ARCH_RANDOM default y config PPC_SPLPAR diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 9ef3cc8ebc1..8a8f0472d98 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -265,7 +265,7 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) enable = 1; if (enable) { - eeh_subsystem_enabled = 1; + eeh_set_enable(true); eeh_add_to_parent_pe(edev); pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n", diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 82789e79e53..0ea99e3d481 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -35,12 +35,7 @@ #include "offline_states.h" /* This version can't take the spinlock, because it never returns */ -static struct rtas_args rtas_stop_self_args = { - .token = RTAS_UNKNOWN_SERVICE, - .nargs = 0, - .nret = 1, - .rets = &rtas_stop_self_args.args[0], -}; +static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE; static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) = CPU_STATE_OFFLINE; @@ -93,15 +88,20 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - struct rtas_args *args = &rtas_stop_self_args; + struct rtas_args args = { + .token = cpu_to_be32(rtas_stop_self_token), + .nargs = 0, + .nret = 1, + .rets = &args.args[0], + }; local_irq_disable(); - BUG_ON(args->token == RTAS_UNKNOWN_SERVICE); + BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); printk("cpu %u (hwid %u) Ready to die...\n", smp_processor_id(), hard_smp_processor_id()); - enter_rtas(__pa(args)); + enter_rtas(__pa(&args)); panic("Alas, I survived.\n"); } @@ -392,10 +392,10 @@ static int __init pseries_cpu_hotplug_init(void) } } - rtas_stop_self_args.token = rtas_token("stop-self"); + rtas_stop_self_token = rtas_token("stop-self"); qcss_tok = rtas_token("query-cpu-stopped-state"); - if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE || + if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE || qcss_tok == RTAS_UNKNOWN_SERVICE) { printk(KERN_INFO "CPU Hotplug not supported by firmware " "- disabling.\n"); diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 70670a2d9cf..c413ec158ff 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -113,7 +113,8 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) { struct device_node *dn, *pdn; struct pci_bus *bus; - const __be32 *pcie_link_speed_stats; + u32 pcie_link_speed_stats[2]; + int rc; bus = bridge->bus; @@ -122,38 +123,45 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) return 0; for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) { - pcie_link_speed_stats = of_get_property(pdn, - "ibm,pcie-link-speed-stats", NULL); - if (pcie_link_speed_stats) + rc = of_property_read_u32_array(pdn, + "ibm,pcie-link-speed-stats", + &pcie_link_speed_stats[0], 2); + if (!rc) break; } of_node_put(pdn); - if (!pcie_link_speed_stats) { + if (rc) { pr_err("no ibm,pcie-link-speed-stats property\n"); return 0; } - switch (be32_to_cpup(pcie_link_speed_stats)) { + switch (pcie_link_speed_stats[0]) { case 0x01: bus->max_bus_speed = PCIE_SPEED_2_5GT; break; case 0x02: bus->max_bus_speed = PCIE_SPEED_5_0GT; break; + case 0x04: + bus->max_bus_speed = PCIE_SPEED_8_0GT; + break; default: bus->max_bus_speed = PCI_SPEED_UNKNOWN; break; } - switch (be32_to_cpup(pcie_link_speed_stats)) { + switch (pcie_link_speed_stats[1]) { case 0x01: bus->cur_bus_speed = PCIE_SPEED_2_5GT; break; case 0x02: bus->cur_bus_speed = PCIE_SPEED_5_0GT; break; + case 0x04: + bus->cur_bus_speed = PCIE_SPEED_8_0GT; + break; default: bus->cur_bus_speed = PCI_SPEED_UNKNOWN; break; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 8e639d7cbda..972df0ffd4d 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -430,8 +430,7 @@ static void pSeries_machine_kexec(struct kimage *image) { long rc; - if (firmware_has_feature(FW_FEATURE_SET_MODE) && - (image->type != KEXEC_TYPE_CRASH)) { + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { rc = pSeries_disable_reloc_on_exc(); if (rc != H_SUCCESS) pr_warning("Warning: Failed to disable relocation on " diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 0e166ed4cd1..8209744b282 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -886,25 +886,25 @@ int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type) /* Default: read HW settings */ if (flow_type == IRQ_TYPE_DEFAULT) { - switch(vold & (MPIC_INFO(VECPRI_POLARITY_MASK) | - MPIC_INFO(VECPRI_SENSE_MASK))) { - case MPIC_INFO(VECPRI_SENSE_EDGE) | - MPIC_INFO(VECPRI_POLARITY_POSITIVE): - flow_type = IRQ_TYPE_EDGE_RISING; - break; - case MPIC_INFO(VECPRI_SENSE_EDGE) | - MPIC_INFO(VECPRI_POLARITY_NEGATIVE): - flow_type = IRQ_TYPE_EDGE_FALLING; - break; - case MPIC_INFO(VECPRI_SENSE_LEVEL) | - MPIC_INFO(VECPRI_POLARITY_POSITIVE): - flow_type = IRQ_TYPE_LEVEL_HIGH; - break; - case MPIC_INFO(VECPRI_SENSE_LEVEL) | - MPIC_INFO(VECPRI_POLARITY_NEGATIVE): - flow_type = IRQ_TYPE_LEVEL_LOW; - break; - } + int vold_ps; + + vold_ps = vold & (MPIC_INFO(VECPRI_POLARITY_MASK) | + MPIC_INFO(VECPRI_SENSE_MASK)); + + if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) | + MPIC_INFO(VECPRI_POLARITY_POSITIVE))) + flow_type = IRQ_TYPE_EDGE_RISING; + else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) | + MPIC_INFO(VECPRI_POLARITY_NEGATIVE))) + flow_type = IRQ_TYPE_EDGE_FALLING; + else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) | + MPIC_INFO(VECPRI_POLARITY_POSITIVE))) + flow_type = IRQ_TYPE_LEVEL_HIGH; + else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) | + MPIC_INFO(VECPRI_POLARITY_NEGATIVE))) + flow_type = IRQ_TYPE_LEVEL_LOW; + else + WARN_ONCE(1, "mpic: unknown IRQ type %d\n", vold); } /* Apply to irq desc */ diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index a90731b3d44..b07909850f7 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -309,16 +309,23 @@ static void get_output_lock(void) if (xmon_speaker == me) return; + for (;;) { - if (xmon_speaker == 0) { - last_speaker = cmpxchg(&xmon_speaker, 0, me); - if (last_speaker == 0) - return; - } - timeout = 10000000; + last_speaker = cmpxchg(&xmon_speaker, 0, me); + if (last_speaker == 0) + return; + + /* + * Wait a full second for the lock, we might be on a slow + * console, but check every 100us. + */ + timeout = 10000; while (xmon_speaker == last_speaker) { - if (--timeout > 0) + if (--timeout > 0) { + udelay(100); continue; + } + /* hostile takeover */ prev = cmpxchg(&xmon_speaker, last_speaker, me); if (prev == last_speaker) @@ -397,7 +404,6 @@ static int xmon_core(struct pt_regs *regs, int fromipi) } xmon_fault_jmp[cpu] = recurse_jmp; - cpumask_set_cpu(cpu, &cpus_in_xmon); bp = NULL; if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT)) @@ -419,6 +425,8 @@ static int xmon_core(struct pt_regs *regs, int fromipi) release_output_lock(); } + cpumask_set_cpu(cpu, &cpus_in_xmon); + waiting: secondary = 1; while (secondary && !xmon_gate) { |