From b69ec42b1b194cc88f04b3fbcda8d3f93182d6c3 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 8 Oct 2012 16:28:11 -0700 Subject: Kconfig: clean up the long arch list for the DEBUG_KMEMLEAK config option Introduce HAVE_DEBUG_KMEMLEAK config option and select it in corresponding architecture Kconfig files. DEBUG_KMEMLEAK now only depends on HAVE_DEBUG_KMEMLEAK. Signed-off-by: Catalin Marinas Cc: Russell King Cc: Michal Simek Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Paul Mundt Cc: "David S. Miller" Cc: Chris Metcalf Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 4ce0be32d153..6a798a70a6d1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -113,6 +113,7 @@ config PPC select HAVE_DMA_API_DEBUG select USE_GENERIC_SMP_HELPERS if SMP select HAVE_OPROFILE + select HAVE_DEBUG_KMEMLEAK select HAVE_SYSCALL_WRAPPERS if PPC64 select GENERIC_ATOMIC64 if PPC32 select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE -- cgit v1.2.1 From 7ac57a89de958fbb5271dc504d0c25e34dbeec32 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 8 Oct 2012 16:28:16 -0700 Subject: Kconfig: clean up the "#if defined(arch)" list for exception-trace sysctl entry Introduce SYSCTL_EXCEPTION_TRACE config option and selec it in the architectures requiring support for the "exception-trace" debug_table entry in kernel/sysctl.c. Signed-off-by: Catalin Marinas Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: "David S. Miller" Cc: Chris Metcalf Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 6a798a70a6d1..df7edb887a04 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -99,6 +99,7 @@ config PPC select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER + select SYSCTL_EXCEPTION_TRACE select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_IDE select HAVE_IOREMAP_PROT -- cgit v1.2.1 From 2dd8ad81e31d0d36a5d448329c646ab43eb17788 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 8 Oct 2012 16:28:51 -0700 Subject: mm: use mm->exe_file instead of first VM_EXECUTABLE vma->vm_file Some security modules and oprofile still uses VM_EXECUTABLE for retrieving a task's executable file. After this patch they will use mm->exe_file directly. mm->exe_file is protected with mm->mmap_sem, so locking stays the same. Signed-off-by: Konstantin Khlebnikov Acked-by: Chris Metcalf [arch/tile] Acked-by: Tetsuo Handa [tomoyo] Cc: Alexander Viro Cc: Carsten Otte Cc: Cyrill Gorcunov Cc: Eric Paris Cc: H. Peter Anvin Cc: Hugh Dickins Cc: Ingo Molnar Acked-by: James Morris Cc: Jason Baron Cc: Kentaro Takeda Cc: Matt Helsley Cc: Nick Piggin Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Robert Richter Cc: Suresh Siddha Cc: Venkatesh Pallipadi Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/oprofile/cell/spu_task_sync.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c index 642fca137ccb..28f1af2db1f5 100644 --- a/arch/powerpc/oprofile/cell/spu_task_sync.c +++ b/arch/powerpc/oprofile/cell/spu_task_sync.c @@ -304,7 +304,7 @@ static inline unsigned long fast_get_dcookie(struct path *path) return cookie; } -/* Look up the dcookie for the task's first VM_EXECUTABLE mapping, +/* Look up the dcookie for the task's mm->exe_file, * which corresponds loosely to "application name". Also, determine * the offset for the SPU ELF object. If computed offset is * non-zero, it implies an embedded SPU object; otherwise, it's a @@ -321,7 +321,6 @@ get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp, { unsigned long app_cookie = 0; unsigned int my_offset = 0; - struct file *app = NULL; struct vm_area_struct *vma; struct mm_struct *mm = spu->mm; @@ -330,16 +329,10 @@ get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp, down_read(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (!vma->vm_file) - continue; - if (!(vma->vm_flags & VM_EXECUTABLE)) - continue; - app_cookie = fast_get_dcookie(&vma->vm_file->f_path); + if (mm->exe_file) { + app_cookie = fast_get_dcookie(&mm->exe_file->f_path); pr_debug("got dcookie for %s\n", - vma->vm_file->f_dentry->d_name.name); - app = vma->vm_file; - break; + mm->exe_file->f_dentry->d_name.name); } for (vma = mm->mmap; vma; vma = vma->vm_next) { -- cgit v1.2.1 From 314e51b9851b4f4e8ab302243ff5a6fc6147f379 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 8 Oct 2012 16:29:02 -0700 Subject: mm: kill vma flag VM_RESERVED and mm->reserved_vm counter A long time ago, in v2.4, VM_RESERVED kept swapout process off VMA, currently it lost original meaning but still has some effects: | effect | alternative flags -+------------------------+--------------------------------------------- 1| account as reserved_vm | VM_IO 2| skip in core dump | VM_IO, VM_DONTDUMP 3| do not merge or expand | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP 4| do not mlock | VM_IO, VM_DONTEXPAND, VM_HUGETLB, VM_PFNMAP This patch removes reserved_vm counter from mm_struct. Seems like nobody cares about it, it does not exported into userspace directly, it only reduces total_vm showed in proc. Thus VM_RESERVED can be replaced with VM_IO or pair VM_DONTEXPAND | VM_DONTDUMP. remap_pfn_range() and io_remap_pfn_range() set VM_IO|VM_DONTEXPAND|VM_DONTDUMP. remap_vmalloc_range() set VM_DONTEXPAND | VM_DONTDUMP. [akpm@linux-foundation.org: drivers/vfio/pci/vfio_pci.c fixup] Signed-off-by: Konstantin Khlebnikov Cc: Alexander Viro Cc: Carsten Otte Cc: Chris Metcalf Cc: Cyrill Gorcunov Cc: Eric Paris Cc: H. Peter Anvin Cc: Hugh Dickins Cc: Ingo Molnar Cc: James Morris Cc: Jason Baron Cc: Kentaro Takeda Cc: Matt Helsley Cc: Nick Piggin Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Robert Richter Cc: Suresh Siddha Cc: Tetsuo Handa Cc: Venkatesh Pallipadi Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kvm/book3s_hv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 83e929e66f9d..721d4603a235 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1183,7 +1183,7 @@ static const struct vm_operations_struct kvm_rma_vm_ops = { static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma) { - vma->vm_flags |= VM_RESERVED; + vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; vma->vm_ops = &kvm_rma_vm_ops; return 0; } -- cgit v1.2.1 From 5d3a551c28c6669dc43be40d8fafafbc2ec8f42b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 8 Oct 2012 16:29:32 -0700 Subject: mm: hugetlb: add arch hook for clearing page flags before entering pool The core page allocator ensures that page flags are zeroed when freeing pages via free_pages_check. A number of architectures (ARM, PPC, MIPS) rely on this property to treat new pages as dirty with respect to the data cache and perform the appropriate flushing before mapping the pages into userspace. This can lead to cache synchronisation problems when using hugepages, since the allocator keeps its own pool of pages above the usual page allocator and does not reset the page flags when freeing a page into the pool. This patch adds a new architecture hook, arch_clear_hugepage_flags, so that architectures which rely on the page flags being in a particular state for fresh allocations can adjust the flags accordingly when a page is freed into the pool. Signed-off-by: Will Deacon Cc: Michal Hocko Reviewed-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/hugetlb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index dfdb95bc59a5..62e11a32c4c2 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -151,6 +151,10 @@ static inline void arch_release_hugepage(struct page *page) { } +static inline void arch_clear_hugepage_flags(struct page *page) +{ +} + #else /* ! CONFIG_HUGETLB_PAGE */ static inline void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr) -- cgit v1.2.1 From e79bee24fd6134f90af4228cfebd010136d67631 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Mon, 8 Oct 2012 16:32:18 -0700 Subject: atomic: implement generic atomic_dec_if_positive() The x86 implementation of atomic_dec_if_positive is quite generic, so make it available to all architectures. This is needed for "swap: add a simple detector for inappropriate swapin readahead". [akpm@linux-foundation.org: do the "#define foo foo" trick in the conventional manner] Signed-off-by: Shaohua Li Cc: Stephen Rothwell Cc: "David S. Miller" Cc: Rik van Riel Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Benjamin Herrenschmidt Cc: Michal Simek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/atomic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index da29032ae38f..e3b1d41c89be 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -268,6 +268,7 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v) return t; } +#define atomic_dec_if_positive atomic_dec_if_positive #define smp_mb__before_atomic_dec() smp_mb() #define smp_mb__after_atomic_dec() smp_mb() -- cgit v1.2.1 From 45cac65b0fcd287ebb877b141d40ba9bbe8e5da7 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Mon, 8 Oct 2012 16:32:19 -0700 Subject: readahead: fault retry breaks mmap file read random detection .fault now can retry. The retry can break state machine of .fault. In filemap_fault, if page is miss, ra->mmap_miss is increased. In the second try, since the page is in page cache now, ra->mmap_miss is decreased. And these are done in one fault, so we can't detect random mmap file access. Add a new flag to indicate .fault is tried once. In the second try, skip ra->mmap_miss decreasing. The filemap_fault state machine is ok with it. I only tested x86, didn't test other archs, but looks the change for other archs is obvious, but who knows :) Signed-off-by: Shaohua Li Cc: Rik van Riel Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/mm/fault.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 5495ebe983a2..0a6b28336eb0 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -451,6 +451,7 @@ good_area: /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk * of starvation. */ flags &= ~FAULT_FLAG_ALLOW_RETRY; + flags |= FAULT_FLAG_TRIED; goto retry; } } -- cgit v1.2.1 From d760afd4d2570653891f94e13b848e97150dc5a6 Mon Sep 17 00:00:00 2001 From: Yasuaki Ishimatsu Date: Mon, 8 Oct 2012 16:34:14 -0700 Subject: memory-hotplug: suppress "Trying to free nonexistent resource " warning When our x86 box calls __remove_pages(), release_mem_region() shows many warnings. And x86 box cannot unregister iomem_resource. "Trying to free nonexistent resource " release_mem_region() has been changed to be called in each PAGES_PER_SECTION by commit de7f0cba9678 ("memory hotplug: release memory regions in PAGES_PER_SECTION chunks"). Because powerpc registers iomem_resource in each PAGES_PER_SECTION chunk. But when I hot add memory on x86 box, iomem_resource is register in each _CRS not PAGES_PER_SECTION chunk. So x86 box unregisters iomem_resource. The patch fixes the problem. Signed-off-by: Yasuaki Ishimatsu Cc: David Rientjes Cc: Jiang Liu Cc: Len Brown Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Christoph Lameter Cc: Minchan Kim Cc: Andrew Morton Cc: KOSAKI Motohiro Cc: Wen Congyang Cc: Dave Hansen Cc: Nathan Fontenot Cc: Badari Pulavarty Cc: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/pseries/hotplug-memory.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'arch/powerpc') diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 11d8e0544ac0..dc0a035e63bb 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -77,7 +77,8 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz { unsigned long start, start_pfn; struct zone *zone; - int ret; + int i, ret; + int sections_to_remove; start_pfn = base >> PAGE_SHIFT; @@ -97,9 +98,13 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz * to sysfs "state" file and we can't remove sysfs entries * while writing to it. So we have to defer it to here. */ - ret = __remove_pages(zone, start_pfn, memblock_size >> PAGE_SHIFT); - if (ret) - return ret; + sections_to_remove = (memblock_size >> PAGE_SHIFT) / PAGES_PER_SECTION; + for (i = 0; i < sections_to_remove; i++) { + unsigned long pfn = start_pfn + i * PAGES_PER_SECTION; + ret = __remove_pages(zone, start_pfn, PAGES_PER_SECTION); + if (ret) + return ret; + } /* * Update memory regions for memory remove -- cgit v1.2.1