From 88247e8d7ba6639f2c199e147ebbc91f7673150c Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 12 Feb 2014 09:13:36 +0530 Subject: powerpc/mm: Add new "set" flag argument to pte/pmd update function pte_update() is a powerpc-ism used to change the bits of a PTE when the access permission is being restricted (a flush is potentially needed). It uses atomic operations on when needed and handles the hash synchronization on hash based processors. It is currently only used to clear PTE bits and so the current implementation doesn't provide a way to also set PTE bits. The new _PAGE_NUMA bit, when set, is actually restricting access so it must use that function too, so this change adds the ability for pte_update() to also set bits. We will use this later to set the _PAGE_NUMA bit. Acked-by: Mel Gorman Acked-by: Rik van Riel Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/hugetlb.h | 2 +- arch/powerpc/include/asm/pgtable-ppc64.h | 26 +++++++++++++++----------- 2 files changed, 16 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index d750336b171d..623f2971ce0e 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/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index bc141c950b1e..eb9261024f51 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 -- cgit v1.2.3-70-g09d2 From 56eecdb912b536a4fa97fb5bfe5a940a54d79be6 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 12 Feb 2014 09:13:38 +0530 Subject: mm: Use ptep/pmdp_set_numa() for updating _PAGE_NUMA bit Archs like ppc64 doesn't do tlb flush in set_pte/pmd functions when using a hash table MMU for various reasons (the flush is handled as part of the PTE modification when necessary). ppc64 thus doesn't implement flush_tlb_range for hash based MMUs. Additionally ppc64 require the tlb flushing to be batched within ptl locks. The reason to do that is to ensure that the hash page table is in sync with linux page table. We track the hpte index in linux pte and if we clear them without flushing hash and drop the ptl lock, we can have another cpu update the pte and can end up with duplicate entry in the hash table, which is fatal. We also want to keep set_pte_at simpler by not requiring them to do hash flush for performance reason. We do that by assuming that set_pte_at() is never *ever* called on a PTE that is already valid. This was the case until the NUMA code went in which broke that assumption. Fix that by introducing a new pair of helpers to set _PAGE_NUMA in a way similar to ptep/pmdp_set_wrprotect(), with a generic implementation using set_pte_at() and a powerpc specific one using the appropriate mechanism needed to keep the hash table in sync. Acked-by: Mel Gorman Reviewed-by: Rik van Riel Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/pgtable.h | 22 +++++++++++++++++++++ include/asm-generic/pgtable.h | 39 ++++++++++++++++++++++++++++++++++++++ mm/huge_memory.c | 9 ++------- mm/mprotect.c | 4 +--- 4 files changed, 64 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index f83b6f3e1b39..3ebb188c3ff5 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/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 8e4f41d9af4d..34c7bdc06014 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -701,6 +701,18 @@ static inline pte_t pte_mknuma(pte_t pte) } #endif +#ifndef ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_t ptent = *ptep; + + ptent = pte_mknuma(ptent); + set_pte_at(mm, addr, ptep, ptent); + return; +} +#endif + #ifndef pmd_mknuma static inline pmd_t pmd_mknuma(pmd_t pmd) { @@ -708,6 +720,18 @@ static inline pmd_t pmd_mknuma(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT); } #endif + +#ifndef pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + + pmd = pmd_mknuma(pmd); + set_pmd_at(mm, addr, pmdp, pmd); + return; +} +#endif #else extern int pte_numa(pte_t pte); extern int pmd_numa(pmd_t pmd); @@ -715,6 +739,8 @@ extern pte_t pte_mknonnuma(pte_t pte); extern pmd_t pmd_mknonnuma(pmd_t pmd); extern pte_t pte_mknuma(pte_t pte); extern pmd_t pmd_mknuma(pmd_t pmd); +extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); #endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */ #else static inline int pmd_numa(pmd_t pmd) @@ -742,10 +768,23 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + return; +} + + static inline pmd_t pmd_mknuma(pmd_t pmd) { return pmd; } + +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + return ; +} #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_MMU */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 82166bf974e1..da23eb96779f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1545,6 +1545,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); BUG_ON(pmd_write(entry)); } else { struct page *page = pmd_page(*pmd); @@ -1557,16 +1558,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, */ if (!is_huge_zero_page(page) && !pmd_numa(*pmd)) { - entry = *pmd; - entry = pmd_mknuma(entry); + pmdp_set_numa(mm, addr, pmd); ret = HPAGE_PMD_NR; } } - - /* Set PMD if cleared earlier */ - if (ret == HPAGE_PMD_NR) - set_pmd_at(mm, addr, pmd, entry); - spin_unlock(ptl); } diff --git a/mm/mprotect.c b/mm/mprotect.c index 33eab902f10e..769a67a15803 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -69,12 +69,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } else { struct page *page; - ptent = *pte; page = vm_normal_page(vma, addr, oldpte); if (page && !PageKsm(page)) { if (!pte_numa(oldpte)) { - ptent = pte_mknuma(ptent); - set_pte_at(mm, addr, pte, ptent); + ptep_set_numa(mm, addr, pte); updated = true; } } -- cgit v1.2.3-70-g09d2 From a0a4419e302fedb548d56129e02130347810f892 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 12 Feb 2014 17:17:05 +1100 Subject: powerpc: Link VDSOs at 0x0 perf is failing to resolve symbols in the VDSO. A while (1) gettimeofday() loop shows: 93.99% [vdso] [.] 0x00000000000005e0 3.12% test [.] 00000037.plt_call.gettimeofday@@GLIBC_2.18 2.81% test [.] main The reason for this is that we are linking our VDSO shared libraries at 1MB, which is a little weird. Even though this is uncommon, Alan points out that it is valid and we should probably fix perf userspace. Regardless, I can't see a reason why we are doing this. The code is all position independent and we never rely on the VDSO ending up at 1M (and we never place it there on 64bit tasks). Changing our link address to 0x0 fixes perf VDSO symbol resolution: 73.18% [vdso] [.] 0x000000000000060c 12.39% [vdso] [.] __kernel_gettimeofday 3.58% test [.] 00000037.plt_call.gettimeofday@@GLIBC_2.18 2.94% [vdso] [.] __kernel_datapage_offset 2.90% test [.] main We still have some local symbol resolution issues that will be fixed in a subsequent patch. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/vdso.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h index 0d9cecddf8a4..c53f5f6d1761 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 -- cgit v1.2.3-70-g09d2 From 2ec5a0adf60c23bb6b0a95d3b96a8c1ff1e1aa5a Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Wed, 12 Feb 2014 15:24:55 +0800 Subject: powerpc/eeh: Cleanup on eeh_subsystem_enabled The patch cleans up variable eeh_subsystem_enabled so that we needn't refer the variable directly from external. Instead, we will use function eeh_enabled() and eeh_set_enable() to operate the variable. Signed-off-by: Gavin Shan Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/eeh.h | 21 +++++++++++++++++++-- arch/powerpc/kernel/eeh.c | 12 ++++++------ arch/powerpc/platforms/powernv/eeh-powernv.c | 2 +- arch/powerpc/platforms/pseries/eeh_pseries.c | 2 +- 4 files changed, 27 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 9e39ceb1d19f..d4dd41fb951b 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/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 148db72a8c43..f22f7b6f6b01 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -89,7 +89,7 @@ /* 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 +364,7 @@ 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) { @@ -822,7 +822,7 @@ 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 +897,7 @@ 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 +1005,7 @@ 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 +1045,7 @@ 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/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index a79fddc5e74e..a59788e83b8b 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/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 9ef3cc8ebc11..8a8f0472d98f 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", -- cgit v1.2.3-70-g09d2 From 573ebfa6601fa58b439e7f15828762839ccd306a Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 26 Feb 2014 17:07:38 +1100 Subject: powerpc: Increase stack redzone for 64-bit userspace to 512 bytes The new ELFv2 little-endian ABI increases the stack redzone -- the area below the stack pointer that can be used for storing data -- from 288 bytes to 512 bytes. This means that we need to allow more space on the user stack when delivering a signal to a 64-bit process. To make the code a bit clearer, we define new USER_REDZONE_SIZE and KERNEL_REDZONE_SIZE symbols in ptrace.h. For now, we leave the kernel redzone size at 288 bytes, since increasing it to 512 bytes would increase the size of interrupt stack frames correspondingly. Gcc currently only makes use of 288 bytes of redzone even when compiling for the new little-endian ABI, and the kernel cannot currently be compiled with the new ABI anyway. In the future, hopefully gcc will provide an option to control the amount of redzone used, and then we could reduce it even more. This also changes the code in arch_compat_alloc_user_space() to preserve the expanded redzone. It is not clear why this function would ever be used on a 64-bit process, though. Signed-off-by: Paul Mackerras CC: [v3.13] Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/compat.h | 5 +++-- arch/powerpc/include/asm/ptrace.h | 16 +++++++++++++++- arch/powerpc/kernel/signal_64.c | 4 ++-- 3 files changed, 20 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 84fdf6857c31..a613d2c82fd9 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/ptrace.h b/arch/powerpc/include/asm/ptrace.h index becc08e6a65c..279b80f3bb29 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/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index e35bf773df7a..8d253c29649b 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 \ -- cgit v1.2.3-70-g09d2 From 2f3f38e4d3d03dd4125cc9a1f49ab3cc91d8d670 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 28 Feb 2014 16:20:29 +1100 Subject: powerpc/powernv: Fix opal_xscom_{read,write} prototype The OPAL firmware functions opal_xscom_read and opal_xscom_write take a 64-bit argument for the XSCOM (PCB) address in order to support the indirect mode on P8. Signed-off-by: Benjamin Herrenschmidt CC: [v3.13] --- arch/powerpc/include/asm/opal.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/include') diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 40157e2ca691..ed82142a3251 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); -- cgit v1.2.3-70-g09d2