From edbe7d23b4482e7f33179290bcff3b1feae1c5f3 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 25 Aug 2010 13:39:16 -0700 Subject: memblock: Add find_memory_core_early() According to node range in early_node_map[] with __memblock_find_in_range to find free range. Will be used by memblock_x86_find_in_range_node() memblock_x86_find_in_range_node will be used to find right buffer for NODE_DATA Signed-off-by: Yinghai Lu Signed-off-by: H. Peter Anvin --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index a2b48041b910..993e85f0afcb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1164,6 +1164,8 @@ extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); int add_from_early_node_map(struct range *range, int az, int nr_range, int nid); +u64 __init find_memory_core_early(int nid, u64 size, u64 align, + u64 goal, u64 limit); void *__alloc_memory_core_early(int nodeid, u64 size, u64 align, u64 goal, u64 limit); typedef int (*work_fn_t)(unsigned long, unsigned long, void *); -- cgit v1.2.2 From aa50d3a7aa8147b9e14dc9d5972a5d2359db4ef8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 6 Oct 2010 21:45:00 +0200 Subject: Encode huge page size for VM_FAULT_HWPOISON errors This fixes a problem introduced with the hugetlb hwpoison handling The user space SIGBUS signalling wants to know the size of the hugepage that caused a HWPOISON fault. Unfortunately the architecture page fault handlers do not have easy access to the struct page. Pass the information out in the fault error code instead. I added a separate VM_FAULT_HWPOISON_LARGE bit for this case and encode the hpage index in some free upper bits of the fault code. The small page hwpoison keeps stays with the VM_FAULT_HWPOISON name to minimize changes. Also add code to hugetlb.h to convert that index into a page shift. Will be used in a further patch. Cc: Naoya Horiguchi Cc: fengguang.wu@intel.com Signed-off-by: Andi Kleen --- include/linux/mm.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 74949fbef8c6..f7e9efc6720b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -718,12 +718,20 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_SIGBUS 0x0002 #define VM_FAULT_MAJOR 0x0004 #define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ -#define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned page */ +#define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned small page */ +#define VM_FAULT_HWPOISON_LARGE 0x0020 /* Hit poisoned large page. Index encoded in upper bits */ #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ -#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON) +#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ + +#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \ + VM_FAULT_HWPOISON_LARGE) + +/* Encode hstate index for a hwpoisoned large page */ +#define VM_FAULT_SET_HINDEX(x) ((x) << 12) +#define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf) /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. -- cgit v1.2.2 From f629d1c9bd0dbc44a6c4f9a4a67d1646c42bfc6f Mon Sep 17 00:00:00 2001 From: Michael Rubin Date: Tue, 26 Oct 2010 14:21:33 -0700 Subject: mm: add account_page_writeback() To help developers and applications gain visibility into writeback behaviour this patch adds two counters to /proc/vmstat. # grep nr_dirtied /proc/vmstat nr_dirtied 3747 # grep nr_written /proc/vmstat nr_written 3618 These entries allow user apps to understand writeback behaviour over time and learn how it is impacting their performance. Currently there is no way to inspect dirty and writeback speed over time. It's not possible for nr_dirty/nr_writeback. These entries are necessary to give visibility into writeback behaviour. We have /proc/diskstats which lets us understand the io in the block layer. We have blktrace for more in depth understanding. We have e2fsprogs and debugsfs to give insight into the file systems behaviour, but we don't offer our users the ability understand what writeback is doing. There is no way to know how active it is over the whole system, if it's falling behind or to quantify it's efforts. With these values exported users can easily see how much data applications are sending through writeback and also at what rates writeback is processing this data. Comparing the rates of change between the two allow developers to see when writeback is not able to keep up with incoming traffic and the rate of dirty memory being sent to the IO back end. This allows folks to understand their io workloads and track kernel issues. Non kernel engineers at Google often use these counters to solve puzzling performance problems. Patch #4 adds a pernode vmstat file with nr_dirtied and nr_written Patch #5 add writeback thresholds to /proc/vmstat Currently these values are in debugfs. But they should be promoted to /proc since they are useful for developers who are writing databases and file servers and are not debugging the kernel. The output is as below: # grep threshold /proc/vmstat nr_pages_dirty_threshold 409111 nr_pages_dirty_background_threshold 818223 This patch: This allows code outside of the mm core to safely manipulate page writeback state and not worry about the other accounting. Not using these routines means that some code will lose track of the accounting and we get bugs. Modify nilfs2 to use interface. Signed-off-by: Michael Rubin Reviewed-by: KOSAKI Motohiro Reviewed-by: Wu Fengguang Cc: KONISHI Ryusuke Cc: Jiro SEKIBA Cc: Dave Chinner Cc: Jens Axboe Cc: KOSAKI Motohiro Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index a4c66846fb8f..c36297faf7cb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -868,6 +868,7 @@ int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); void account_page_dirtied(struct page *page, struct address_space *mapping); +void account_page_writeback(struct page *page); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); -- cgit v1.2.2 From bce54bbfde07e8b300f39dae14756c12a6ceca65 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 26 Oct 2010 14:21:37 -0700 Subject: mm: fix typo in mm.h when NODE_NOT_IN_PAGE_FLAGS NODE_NOT_IN_PAGE_FLAGS is defined in mm.h when the node information is not stored in the page flags bitmap. Unfortunately, there's a typo in one of the checks for it. This patch fixes it (s/NODE_NOT_IN_PAGEFLAGS/NODE_NOT_IN_PAGE_FLAGS/). Since this has been around for ages, I doubt it's been causing any serious problems. Signed-off-by: Will Deacon Cc: Christoph Lameter Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index c36297faf7cb..2862009f9573 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -497,8 +497,8 @@ static inline void set_compound_order(struct page *page, unsigned long order) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) -/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allcator */ -#ifdef NODE_NOT_IN_PAGEFLAGS +/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ +#ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF)? \ SECTIONS_PGOFF : ZONES_PGOFF) -- cgit v1.2.2 From d065bd810b6deb67d4897a14bfe21f8eb526ba99 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Tue, 26 Oct 2010 14:21:57 -0700 Subject: mm: retry page fault when blocking on disk transfer This change reduces mmap_sem hold times that are caused by waiting for disk transfers when accessing file mapped VMAs. It introduces the VM_FAULT_ALLOW_RETRY flag, which indicates that the call site wants mmap_sem to be released if blocking on a pending disk transfer. In that case, filemap_fault() returns the VM_FAULT_RETRY status bit and do_page_fault() will then re-acquire mmap_sem and retry the page fault. It is expected that the retry will hit the same page which will now be cached, and thus it will complete with a low mmap_sem hold time. Tests: - microbenchmark: thread A mmaps a large file and does random read accesses to the mmaped area - achieves about 55 iterations/s. Thread B does mmap/munmap in a loop at a separate location - achieves 55 iterations/s before, 15000 iterations/s after. - We are seeing related effects in some applications in house, which show significant performance regressions when running without this change. [akpm@linux-foundation.org: fix warning & crash] Signed-off-by: Michel Lespinasse Acked-by: Rik van Riel Acked-by: Linus Torvalds Cc: Nick Piggin Reviewed-by: Wu Fengguang Cc: Ying Han Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Thomas Gleixner Acked-by: "H. Peter Anvin" Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2862009f9573..3bf46655b50a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -144,6 +144,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */ #define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ #define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ +#define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */ /* * This interface is used by x86 PAT code to identify a pfn mapping that is @@ -723,6 +724,7 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ +#define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */ #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ -- cgit v1.2.2 From 25ca1d6c02fe1c6d90d918867ef670d323725458 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 26 Oct 2010 14:21:59 -0700 Subject: mm: wrap get_locked_pte() using __cond_lock() The get_locked_pte() conditionally grabs 'ptl' in case of returning non-NULL. This leads sparse to complain about context imbalance. Rename and wrap it using __cond_lock() to make sparse happy. Signed-off-by: Namhyung Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3bf46655b50a..721f451c3029 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1034,7 +1034,15 @@ extern void unregister_shrinker(struct shrinker *); int vma_wants_writenotify(struct vm_area_struct *vma); -extern pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); +extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, + spinlock_t **ptl); +static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, + spinlock_t **ptl) +{ + pte_t *ptep; + __cond_lock(*ptl, ptep = __get_locked_pte(mm, addr, ptl)); + return ptep; +} #ifdef __PAGETABLE_PUD_FOLDED static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, -- cgit v1.2.2 From 110d74a921f4d272b47ef6104fcf937df808f4c8 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Thu, 13 Jan 2011 15:46:11 -0800 Subject: mm: add FOLL_MLOCK follow_page flag. Move the code to mlock pages from __mlock_vma_pages_range() to follow_page(). This allows __mlock_vma_pages_range() to not have to break down work into 16-page batches. An additional motivation for doing this within the present patch series is that it'll make it easier for a later chagne to drop mmap_sem when blocking on disk (we'd like to be able to resume at the page that was read from disk instead of at the start of a 16-page batch). Signed-off-by: Michel Lespinasse Cc: Hugh Dickins Cc: Rik van Riel Cc: Peter Zijlstra Cc: Nick Piggin Cc: KOSAKI Motohiro Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 721f451c3029..9ade803bcc1b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1415,6 +1415,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address, #define FOLL_GET 0x04 /* do get_page on page */ #define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ +#define FOLL_MLOCK 0x40 /* mark page as mlocked */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); -- cgit v1.2.2 From e20e87795834f2f14cb53baf657b91d9c39f92c8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 13 Jan 2011 15:46:17 -0800 Subject: mm: remove unlikely() from page_mapping() page_mapping() has a unlikely that the mapping has PAGE_MAPPING_ANON set. But running the annotated branch profiler on a normal desktop system doing vairous tasks (xchat, evolution, firefox, distcc), it is not really that unlikely that the mapping here will have the PAGE_MAPPING_ANON flag set: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 35935762 1270265395 97 page_mapping mm.h 659 1306198001 143659 0 page_mapping mm.h 657 203131478 121586 0 page_mapping mm.h 657 5415491 1116 0 page_mapping mm.h 657 74899487 1116 0 page_mapping mm.h 657 203132845 224 0 page_mapping mm.h 659 5415464 27 0 page_mapping mm.h 659 13552 0 0 page_mapping mm.h 657 13552 0 0 page_mapping mm.h 659 242630 0 0 page_mapping mm.h 657 242630 0 0 page_mapping mm.h 659 74899487 0 0 page_mapping mm.h 659 The page_mapping() is a static inline, which is why it shows up multiple times. The unlikely in page_mapping() was correct a total of 1909540379 times and incorrect 1270533123 times, with a 39% being incorrect. With this much of an error, it's best to simply remove the unlikely and have the compiler and branch prediction figure this out. Signed-off-by: Steven Rostedt Cc: KOSAKI Motohiro Cc: Nick Piggin Cc: Rik van Riel Cc: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9ade803bcc1b..57e11b2a18ba 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -657,7 +657,7 @@ static inline struct address_space *page_mapping(struct page *page) VM_BUG_ON(PageSlab(page)); if (unlikely(PageSwapCache(page))) mapping = &swapper_space; - else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON)) + else if ((unsigned long)mapping & PAGE_MAPPING_ANON) mapping = NULL; return mapping; } -- cgit v1.2.2 From e9da73d67729b58bba256123e2b4651e0d8a01ac Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:32 -0800 Subject: thp: compound_lock Add a new compound_lock() needed to serialize put_page against __split_huge_page_refcount(). Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 57e11b2a18ba..3b1754ad8785 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -14,6 +14,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -305,6 +306,39 @@ static inline int is_vmalloc_or_module_addr(const void *x) } #endif +static inline void compound_lock(struct page *page) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + bit_spin_lock(PG_compound_lock, &page->flags); +#endif +} + +static inline void compound_unlock(struct page *page) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + bit_spin_unlock(PG_compound_lock, &page->flags); +#endif +} + +static inline unsigned long compound_lock_irqsave(struct page *page) +{ + unsigned long uninitialized_var(flags); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + local_irq_save(flags); + compound_lock(page); +#endif + return flags; +} + +static inline void compound_unlock_irqrestore(struct page *page, + unsigned long flags) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + compound_unlock(page); + local_irq_restore(flags); +#endif +} + static inline struct page *compound_head(struct page *page) { if (unlikely(PageTail(page))) -- cgit v1.2.2 From 9180706344487700b40da9eca5dedd3d11cb33b4 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:32 -0800 Subject: thp: alter compound get_page/put_page Alter compound get_page/put_page to keep references on subpages too, in order to allow __split_huge_page_refcount to split an hugepage even while subpages have been pinned by one of the get_user_pages() variants. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3b1754ad8785..a2718e1ed585 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -353,9 +353,29 @@ static inline int page_count(struct page *page) static inline void get_page(struct page *page) { - page = compound_head(page); - VM_BUG_ON(atomic_read(&page->_count) == 0); + /* + * Getting a normal page or the head of a compound page + * requires to already have an elevated page->_count. Only if + * we're getting a tail page, the elevated page->_count is + * required only in the head page, so for tail pages the + * bugcheck only verifies that the page->_count isn't + * negative. + */ + VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page)); atomic_inc(&page->_count); + /* + * Getting a tail page will elevate both the head and tail + * page->_count(s). + */ + if (unlikely(PageTail(page))) { + /* + * This is safe only because + * __split_huge_page_refcount can't run under + * get_page(). + */ + VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0); + atomic_inc(&page->first_page->_count); + } } static inline struct page *virt_to_head_page(const void *x) -- cgit v1.2.2 From 14fd403f2146f740942d78af4e0ee59396ad8eab Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:37 -0800 Subject: thp: export maybe_mkwrite huge_memory.c needs it too when it fallbacks in copying hugepages into regular fragmented pages if hugepage allocation fails during COW. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index a2718e1ed585..6bef67d74adf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -429,6 +429,19 @@ static inline void set_compound_order(struct page *page, unsigned long order) page[1].lru.prev = (void *)order; } +/* + * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when + * servicing faults for write access. In the normal case, do always want + * pte_mkwrite. But get_user_pages can cause write faults for mappings + * that do not have writing enabled, when used by access_process_vm. + */ +static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) +{ + if (likely(vma->vm_flags & VM_WRITE)) + pte = pte_mkwrite(pte); + return pte; +} + /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of -- cgit v1.2.2 From 8ac1f8320a0073f28cf9e0491af4cd98f504f92a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:43 -0800 Subject: thp: pte alloc trans splitting pte alloc routines must wait for split_huge_page if the pmd is not present and not null (i.e. pmd_trans_splitting). The additional branches are optimized away at compile time by pmd_trans_splitting if the config option is off. However we must pass the vma down in order to know the anon_vma lock to wait for. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6bef67d74adf..14ddd98b063f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1131,7 +1131,8 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); #endif -int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address); +int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long address); int __pte_alloc_kernel(pmd_t *pmd, unsigned long address); /* @@ -1200,16 +1201,18 @@ static inline void pgtable_page_dtor(struct page *page) pte_unmap(pte); \ } while (0) -#define pte_alloc_map(mm, pmd, address) \ - ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \ - NULL: pte_offset_map(pmd, address)) +#define pte_alloc_map(mm, vma, pmd, address) \ + ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, vma, \ + pmd, address))? \ + NULL: pte_offset_map(pmd, address)) #define pte_alloc_map_lock(mm, pmd, address, ptlp) \ - ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \ + ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, NULL, \ + pmd, address))? \ NULL: pte_offset_map_lock(mm, pmd, address, ptlp)) #define pte_alloc_kernel(pmd, address) \ - ((unlikely(!pmd_present(*(pmd))) && __pte_alloc_kernel(pmd, address))? \ + ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \ NULL: pte_offset_kernel(pmd, address)) extern void free_area_init(unsigned long * zones_size); -- cgit v1.2.2 From 47ad8475c000141eacb3ecda5e5ce4b43a9cd04d Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:47 -0800 Subject: thp: clear_copy_huge_page Move the copy/clear_huge_page functions to common code to share between hugetlb.c and huge_memory.c. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 14ddd98b063f..cc6ab1038f6f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1589,5 +1589,14 @@ static inline int is_hwpoison_address(unsigned long addr) extern void dump_page(struct page *page); +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) +extern void clear_huge_page(struct page *page, + unsigned long addr, + unsigned int pages_per_huge_page); +extern void copy_user_huge_page(struct page *dst, struct page *src, + unsigned long addr, struct vm_area_struct *vma, + unsigned int pages_per_huge_page); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ -- cgit v1.2.2 From 71e3aac0724ffe8918992d76acfe3aad7d8724a5 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:52 -0800 Subject: thp: transparent hugepage core Lately I've been working to make KVM use hugepages transparently without the usual restrictions of hugetlbfs. Some of the restrictions I'd like to see removed: 1) hugepages have to be swappable or the guest physical memory remains locked in RAM and can't be paged out to swap 2) if a hugepage allocation fails, regular pages should be allocated instead and mixed in the same vma without any failure and without userland noticing 3) if some task quits and more hugepages become available in the buddy, guest physical memory backed by regular pages should be relocated on hugepages automatically in regions under madvise(MADV_HUGEPAGE) (ideally event driven by waking up the kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes not null) 4) avoidance of reservation and maximization of use of hugepages whenever possible. Reservation (needed to avoid runtime fatal faliures) may be ok for 1 machine with 1 database with 1 database cache with 1 database cache size known at boot time. It's definitely not feasible with a virtualization hypervisor usage like RHEV-H that runs an unknown number of virtual machines with an unknown size of each virtual machine with an unknown amount of pagecache that could be potentially useful in the host for guest not using O_DIRECT (aka cache=off). hugepages in the virtualization hypervisor (and also in the guest!) are much more important than in a regular host not using virtualization, becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24 to 19 in case only the hypervisor uses transparent hugepages, and they decrease the tlb-miss cacheline accesses from 19 to 15 in case both the linux hypervisor and the linux guest both uses this patch (though the guest will limit the addition speedup to anonymous regions only for now...). Even more important is that the tlb miss handler is much slower on a NPT/EPT guest than for a regular shadow paging or no-virtualization scenario. So maximizing the amount of virtual memory cached by the TLB pays off significantly more with NPT/EPT than without (even if there would be no significant speedup in the tlb-miss runtime). The first (and more tedious) part of this work requires allowing the VM to handle anonymous hugepages mixed with regular pages transparently on regular anonymous vmas. This is what this patch tries to achieve in the least intrusive possible way. We want hugepages and hugetlb to be used in a way so that all applications can benefit without changes (as usual we leverage the KVM virtualization design: by improving the Linux VM at large, KVM gets the performance boost too). The most important design choice is: always fallback to 4k allocation if the hugepage allocation fails! This is the _very_ opposite of some large pagecache patches that failed with -EIO back then if a 64k (or similar) allocation failed... Second important decision (to reduce the impact of the feature on the existing pagetable handling code) is that at any time we can split an hugepage into 512 regular pages and it has to be done with an operation that can't fail. This way the reliability of the swapping isn't decreased (no need to allocate memory when we are short on memory to swap) and it's trivial to plug a split_huge_page* one-liner where needed without polluting the VM. Over time we can teach mprotect, mremap and friends to handle pmd_trans_huge natively without calling split_huge_page*. The fact it can't fail isn't just for swap: if split_huge_page would return -ENOMEM (instead of the current void) we'd need to rollback the mprotect from the middle of it (ideally including undoing the split_vma) which would be a big change and in the very wrong direction (it'd likely be simpler not to call split_huge_page at all and to teach mprotect and friends to handle hugepages instead of rolling them back from the middle). In short the very value of split_huge_page is that it can't fail. The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and incremental and it'll just be an "harmless" addition later if this initial part is agreed upon. It also should be noted that locking-wise replacing regular pages with hugepages is going to be very easy if compared to what I'm doing below in split_huge_page, as it will only happen when page_count(page) matches page_mapcount(page) if we can take the PG_lock and mmap_sem in write mode. collapse_huge_page will be a "best effort" that (unlike split_huge_page) can fail at the minimal sign of trouble and we can try again later. collapse_huge_page will be similar to how KSM works and the madvise(MADV_HUGEPAGE) will work similar to madvise(MADV_MERGEABLE). The default I like is that transparent hugepages are used at page fault time. This can be changed with /sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set to three values "always", "madvise", "never" which mean respectively that hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions, or never used. /sys/kernel/mm/transparent_hugepage/defrag instead controls if the hugepage allocation should defrag memory aggressively "always", only inside "madvise" regions, or "never". The pmd_trans_splitting/pmd_trans_huge locking is very solid. The put_page (from get_user_page users that can't use mmu notifier like O_DIRECT) that runs against a __split_huge_page_refcount instead was a pain to serialize in a way that would result always in a coherent page count for both tail and head. I think my locking solution with a compound_lock taken only after the page_first is valid and is still a PageHead should be safe but it surely needs review from SMP race point of view. In short there is no current existing way to serialize the O_DIRECT final put_page against split_huge_page_refcount so I had to invent a new one (O_DIRECT loses knowledge on the mapping status by the time gup_fast returns so...). And I didn't want to impact all gup/gup_fast users for now, maybe if we change the gup interface substantially we can avoid this locking, I admit I didn't think too much about it because changing the gup unpinning interface would be invasive. If we ignored O_DIRECT we could stick to the existing compound refcounting code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM (and any other mmu notifier user) would call it without FOLL_GET (and if FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the current task mmu notifier list yet). But O_DIRECT is fundamental for decent performance of virtualized I/O on fast storage so we can't avoid it to solve the race of put_page against split_huge_page_refcount to achieve a complete hugepage feature for KVM. Swap and oom works fine (well just like with regular pages ;). MMU notifier is handled transparently too, with the exception of the young bit on the pmd, that didn't have a range check but I think KVM will be fine because the whole point of hugepages is that EPT/NPT will also use a huge pmd when they notice gup returns pages with PageCompound set, so they won't care of a range and there's just the pmd young bit to check in that case. NOTE: in some cases if the L2 cache is small, this may slowdown and waste memory during COWs because 4M of memory are accessed in a single fault instead of 8k (the payoff is that after COW the program can run faster). So we might want to switch the copy_huge_page (and clear_huge_page too) to not temporal stores. I also extensively researched ways to avoid this cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k up to 1M (I can send those patches that fully implemented prefault) but I concluded they're not worth it and they add an huge additional complexity and they remove all tlb benefits until the full hugepage has been faulted in, to save a little bit of memory and some cache during app startup, but they still don't improve substantially the cache-trashing during startup if the prefault happens in >4k chunks. One reason is that those 4k pte entries copied are still mapped on a perfectly cache-colored hugepage, so the trashing is the worst one can generate in those copies (cow of 4k page copies aren't so well colored so they trashes less, but again this results in software running faster after the page fault). Those prefault patches allowed things like a pte where post-cow pages were local 4k regular anon pages and the not-yet-cowed pte entries were pointing in the middle of some hugepage mapped read-only. If it doesn't payoff substantially with todays hardware it will payoff even less in the future with larger l2 caches, and the prefault logic would blot the VM a lot. If one is emebdded transparent_hugepage can be disabled during boot with sysfs or with the boot commandline parameter transparent_hugepage=0 (or transparent_hugepage=2 to restrict hugepages inside madvise regions) that will ensure not a single hugepage is allocated at boot time. It is simple enough to just disable transparent hugepage globally and let transparent hugepages be allocated selectively by applications in the MADV_HUGEPAGE region (both at page fault time, and if enabled with the collapse_huge_page too through the kernel daemon). This patch supports only hugepages mapped in the pmd, archs that have smaller hugepages will not fit in this patch alone. Also some archs like power have certain tlb limits that prevents mixing different page size in the same regions so they will not fit in this framework that requires "graceful fallback" to basic PAGE_SIZE in case of physical memory fragmentation. hugetlbfs remains a perfect fit for those because its software limits happen to match the hardware limits. hugetlbfs also remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped to be found not fragmented after a certain system uptime and that would be very expensive to defragment with relocation, so requiring reservation. hugetlbfs is the "reservation way", the point of transparent hugepages is not to have any reservation at all and maximizing the use of cache and hugepages at all times automatically. Some performance result: vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep ages3 memset page fault 1566023 memset tlb miss 453854 memset second tlb miss 453321 random access tlb miss 41635 random access second tlb miss 41658 vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3 memset page fault 1566471 memset tlb miss 453375 memset second tlb miss 453320 random access tlb miss 41636 random access second tlb miss 41637 vmx andrea # ./largepages3 memset page fault 1566642 memset tlb miss 453417 memset second tlb miss 453313 random access tlb miss 41630 random access second tlb miss 41647 vmx andrea # ./largepages3 memset page fault 1566872 memset tlb miss 453418 memset second tlb miss 453315 random access tlb miss 41618 random access second tlb miss 41659 vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage vmx andrea # ./largepages3 memset page fault 2182476 memset tlb miss 460305 memset second tlb miss 460179 random access tlb miss 44483 random access second tlb miss 44186 vmx andrea # ./largepages3 memset page fault 2182791 memset tlb miss 460742 memset second tlb miss 459962 random access tlb miss 43981 random access second tlb miss 43988 ============ #include #include #include #include #define SIZE (3UL*1024*1024*1024) int main() { char *p = malloc(SIZE), *p2; struct timeval before, after; gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset page fault %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); return 0; } ============ Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index cc6ab1038f6f..78adec4ba9f4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -111,6 +111,9 @@ extern unsigned int kobjsize(const void *objp); #define VM_SAO 0x20000000 /* Strong Access Ordering (powerpc) */ #define VM_PFN_AT_MMAP 0x40000000 /* PFNMAP vma that is fully mapped at mmap time */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ +#if BITS_PER_LONG > 32 +#define VM_HUGEPAGE 0x100000000UL /* MADV_HUGEPAGE marked this vma */ +#endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) @@ -243,6 +246,7 @@ struct inode; * files which need it (119 of them) */ #include +#include /* * Methods to modify the page usage count. -- cgit v1.2.2 From 500d65d471018d9a13b0d51b7e141ed2a3555c1d Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:55 -0800 Subject: thp: pmd_trans_huge migrate bugcheck No pmd_trans_huge should ever materialize in migration ptes areas, because we split the hugepage before migration ptes are instantiated. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 78adec4ba9f4..2ec5138badab 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1490,6 +1490,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address, #define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ #define FOLL_MLOCK 0x40 /* mark page as mlocked */ +#define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); -- cgit v1.2.2 From 5f24ce5fd34c3ca1b3d10d30da754732da64d5c0 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:00 -0800 Subject: thp: remove PG_buddy PG_buddy can be converted to _mapcount == -2. So the PG_compound_lock can be added to page->flags without overflowing (because of the sparse section bits increasing) with CONFIG_X86_PAE=y and CONFIG_X86_PAT=y. This also has to move the memory hotplug code from _mapcount to lru.next to avoid any risk of clashes. We can't use lru.next for PG_buddy removal, but memory hotplug can use lru.next even more easily than the mapcount instead. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2ec5138badab..7ab7d2b60041 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -397,6 +397,27 @@ static inline void init_page_count(struct page *page) atomic_set(&page->_count, 1); } +/* + * PageBuddy() indicate that the page is free and in the buddy system + * (see mm/page_alloc.c). + */ +static inline int PageBuddy(struct page *page) +{ + return atomic_read(&page->_mapcount) == -2; +} + +static inline void __SetPageBuddy(struct page *page) +{ + VM_BUG_ON(atomic_read(&page->_mapcount) != -1); + atomic_set(&page->_mapcount, -2); +} + +static inline void __ClearPageBuddy(struct page *page) +{ + VM_BUG_ON(!PageBuddy(page)); + atomic_set(&page->_mapcount, -1); +} + void put_page(struct page *page); void put_pages_list(struct list_head *pages); -- cgit v1.2.2 From f2d6bfe9ff0acec30b713614260e78b03d20e909 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 13 Jan 2011 15:47:01 -0800 Subject: thp: add x86 32bit support Add support for transparent hugepages to x86 32bit. Share the same VM_ bitflag for VM_MAPPED_COPY. mm/nommu.c will never support transparent hugepages. Signed-off-by: Johannes Weiner Signed-off-by: Andrea Arcangeli Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7ab7d2b60041..9c2695beab86 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -102,7 +102,11 @@ extern unsigned int kobjsize(const void *objp); #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ +#ifndef CONFIG_TRANSPARENT_HUGEPAGE #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ +#else +#define VM_HUGEPAGE 0x01000000 /* MADV_HUGEPAGE marked this vma */ +#endif #define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ @@ -111,9 +115,6 @@ extern unsigned int kobjsize(const void *objp); #define VM_SAO 0x20000000 /* Strong Access Ordering (powerpc) */ #define VM_PFN_AT_MMAP 0x40000000 /* PFNMAP vma that is fully mapped at mmap time */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ -#if BITS_PER_LONG > 32 -#define VM_HUGEPAGE 0x100000000UL /* MADV_HUGEPAGE marked this vma */ -#endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) -- cgit v1.2.2 From 37c2ac7872a9387542616f658d20ac25f5bdb32e Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:16 -0800 Subject: thp: compound_trans_order Read compound_trans_order safe. Noop for CONFIG_TRANSPARENT_HUGEPAGE=n. Signed-off-by: Andrea Arcangeli Cc: Daisuke Nishimura Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9c2695beab86..ce97a2bb0b19 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -450,6 +450,20 @@ static inline int compound_order(struct page *page) return (unsigned long)page[1].lru.prev; } +static inline int compound_trans_order(struct page *page) +{ + int order; + unsigned long flags; + + if (!PageHead(page)) + return 0; + + flags = compound_lock_irqsave(page); + order = compound_order(page); + compound_unlock_irqrestore(page, flags); + return order; +} + static inline void set_compound_order(struct page *page, unsigned long order) { page[1].lru.prev = (void *)order; -- cgit v1.2.2 From a664b2d8555c659127bf8fe049a58449d394a707 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:17 -0800 Subject: thp: madvise(MADV_NOHUGEPAGE) Add madvise MADV_NOHUGEPAGE to mark regions that are not important to be hugepage backed. Return -EINVAL if the vma is not of an anonymous type, or the feature isn't built into the kernel. Never silently return success. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index ce97a2bb0b19..956a35532f47 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -83,6 +83,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_GROWSUP 0x00000200 #else #define VM_GROWSUP 0x00000000 +#define VM_NOHUGEPAGE 0x00000200 /* MADV_NOHUGEPAGE marked this vma */ #endif #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ -- cgit v1.2.2 From 3dece370ecc7c6152b3fdd21c6de28179f6e643d Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Fri, 21 Jan 2011 08:49:56 +0100 Subject: mm: System without MMU do not need pte_mkwrite The patch "thp: export maybe_mkwrite" (commit 14fd403f2146) breaks systems without MMU. Error log: CC arch/microblaze/mm/init.o In file included from include/linux/mman.h:14, from arch/microblaze/mm/consistent.c:24: include/linux/mm.h: In function 'maybe_mkwrite': include/linux/mm.h:482: error: implicit declaration of function 'pte_mkwrite' include/linux/mm.h:482: error: incompatible types in assignment Signed-off-by: Michal Simek CC: Andrea Arcangeli Reviewed-by: Rik van Riel CC: Andrew Morton CC: Ingo Molnar Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 956a35532f47..f6385fc17ad4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -470,6 +470,7 @@ static inline void set_compound_order(struct page *page, unsigned long order) page[1].lru.prev = (void *)order; } +#ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want @@ -482,6 +483,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) pte = pte_mkwrite(pte); return pte; } +#endif /* * Multiple processes may "see" the same page. E.g. for untouched -- cgit v1.2.2 From 8bc1f91e1f0e977fb95b11d8fa686f5091888110 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Feb 2011 14:43:06 +0100 Subject: bootmem: Move __alloc_memory_core_early() to nobootmem.c Now that bootmem.c and nobootmem.c are separate, there's no reason to define __alloc_memory_core_early(), which is used only by nobootmem, inside #ifdef in page_alloc.c. Move it to nobootmem.c and make it static. This patch doesn't introduce any behavior change. -tj: Updated commit description. Signed-off-by: Yinghai Lu Acked-by: Andrew Morton Signed-off-by: Tejun Heo --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index f6385fc17ad4..679300c050f5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1309,8 +1309,6 @@ int add_from_early_node_map(struct range *range, int az, int nr_range, int nid); u64 __init find_memory_core_early(int nid, u64 size, u64 align, u64 goal, u64 limit); -void *__alloc_memory_core_early(int nodeid, u64 size, u64 align, - u64 goal, u64 limit); typedef int (*work_fn_t)(unsigned long, unsigned long, void *); extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data); extern void sparse_memory_present_with_active_regions(int nid); -- cgit v1.2.2 From 0014bd990e69063b0fb78940b35439d7980ce3ee Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Sun, 30 Jan 2011 11:15:47 +0800 Subject: mm: export __get_user_pages In most cases, get_user_pages and get_user_pages_fast should be used to pin user pages in memory. But sometimes, some special flags except FOLL_GET, FOLL_WRITE and FOLL_FORCE are needed, for example in following patch, KVM needs FOLL_HWPOISON. To support these users, __get_user_pages is exported directly. There are some symbol name conflicts in infiniband driver, fixed them too. Signed-off-by: Huang Ying CC: Andrew Morton CC: Michel Lespinasse CC: Roland Dreier CC: Ralph Campbell Signed-off-by: Marcelo Tosatti --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 679300c050f5..46150c66318e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -965,6 +965,10 @@ static inline int handle_mm_fault(struct mm_struct *mm, extern int make_pages_present(unsigned long addr, unsigned long end); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); +int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, int len, unsigned int foll_flags, + struct page **pages, struct vm_area_struct **vmas, + int *nonblocking); int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas); -- cgit v1.2.2 From 69ebb83e13e514222b0ae4f8bd813a17679ed876 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Sun, 30 Jan 2011 11:15:48 +0800 Subject: mm: make __get_user_pages return -EHWPOISON for HWPOISON page optionally Make __get_user_pages return -EHWPOISON for HWPOISON page only if FOLL_HWPOISON is specified. With this patch, the interested callers can distinguish HWPOISON pages from general FAULT pages, while other callers will still get -EFAULT for all these pages, so the user space interface need not to be changed. This feature is needed by KVM, where UCR MCE should be relayed to guest for HWPOISON page, while instruction emulation and MMIO will be tried for general FAULT page. The idea comes from Andrew Morton. Signed-off-by: Huang Ying Cc: Andrew Morton Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 46150c66318e..a77c82c56e05 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1532,6 +1532,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address, #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ #define FOLL_MLOCK 0x40 /* mark page as mlocked */ #define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */ +#define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); -- cgit v1.2.2 From f58c9df78c0360f0eb3852b9cc3a61e689bc2dd1 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Sun, 30 Jan 2011 11:15:49 +0800 Subject: mm: remove is_hwpoison_address Unused. Signed-off-by: Huang Ying Signed-off-by: Marcelo Tosatti --- include/linux/mm.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index a77c82c56e05..78219887308e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1625,14 +1625,6 @@ extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); extern atomic_long_t mce_bad_pages; extern int soft_offline_page(struct page *page, int flags); -#ifdef CONFIG_MEMORY_FAILURE -int is_hwpoison_address(unsigned long addr); -#else -static inline int is_hwpoison_address(unsigned long addr) -{ - return 0; -} -#endif extern void dump_page(struct page *page); -- cgit v1.2.2 From ef2b4b95a63a1d23958dcb99eb2c6898eddc87d0 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 18 Mar 2011 00:16:35 +0100 Subject: mm: PageBuddy and mapcount robustness Change the _mapcount value indicating PageBuddy from -2 to -128 for more robusteness against page_mapcount() undeflows. Use reset_page_mapcount instead of __ClearPageBuddy in bad_page to ignore the previous retval of PageBuddy(). Signed-off-by: Andrea Arcangeli Reported-by: Hugh Dickins Signed-off-by: Linus Torvalds --- include/linux/mm.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 679300c050f5..ff83798e1c27 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -402,16 +402,23 @@ static inline void init_page_count(struct page *page) /* * PageBuddy() indicate that the page is free and in the buddy system * (see mm/page_alloc.c). + * + * PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to + * -2 so that an underflow of the page_mapcount() won't be mistaken + * for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very + * efficiently by most CPU architectures. */ +#define PAGE_BUDDY_MAPCOUNT_VALUE (-128) + static inline int PageBuddy(struct page *page) { - return atomic_read(&page->_mapcount) == -2; + return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE; } static inline void __SetPageBuddy(struct page *page) { VM_BUG_ON(atomic_read(&page->_mapcount) != -1); - atomic_set(&page->_mapcount, -2); + atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE); } static inline void __ClearPageBuddy(struct page *page) -- cgit v1.2.2 From ddd588b5dd55f14320379961e47683db4e4c1d90 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 22 Mar 2011 16:30:46 -0700 Subject: oom: suppress nodes that are not allowed from meminfo on oom kill The oom killer is extremely verbose for machines with a large number of cpus and/or nodes. This verbosity can often be harmful if it causes other important messages to be scrolled from the kernel log and incurs a signicant time delay, specifically for kernels with CONFIG_NODES_SHIFT > 8. This patch causes only memory information to be displayed for nodes that are allowed by current's cpuset when dumping the VM state. Information for all other nodes is irrelevant to the oom condition; we don't care if there's an abundance of memory elsewhere if we can't access it. This only affects the behavior of dumping memory information when an oom is triggered. Other dumps, such as for sysrq+m, still display the unfiltered form when using the existing show_mem() interface. Additionally, the per-cpu pageset statistics are extremely verbose in oom killer output, so it is now suppressed. This removes nodes_weight(current->mems_allowed) * (1 + nr_cpus) lines from the oom killer output. Callers may use __show_mem(SHOW_MEM_FILTER_NODES) to filter disallowed nodes. Signed-off-by: David Rientjes Cc: Mel Gorman Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 581703d86fbd..1f82adc85352 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -859,7 +859,14 @@ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) +/* + * Flags passed to __show_mem() and __show_free_areas() to suppress output in + * various contexts. + */ +#define SHOW_MEM_FILTER_NODES (0x0001u) /* filter disallowed nodes */ + extern void show_free_areas(void); +extern void __show_free_areas(unsigned int flags); int shmem_lock(struct file *file, int lock, struct user_struct *user); struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); @@ -1348,6 +1355,7 @@ extern void calculate_zone_inactive_ratio(struct zone *zone); extern void mem_init(void); extern void __init mmap_init(void); extern void show_mem(void); +extern void __show_mem(unsigned int flags); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); extern int after_bootmem; -- cgit v1.2.2 From 318b275fbca1ab9ec0862de71420e0e92c3d1aa7 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Tue, 22 Mar 2011 16:30:51 -0700 Subject: mm: allow GUP to fail instead of waiting on a page GUP user may want to try to acquire a reference to a page if it is already in memory, but not if IO, to bring it in, is needed. For example KVM may tell vcpu to schedule another guest process if current one is trying to access swapped out page. Meanwhile, the page will be swapped in and the guest process, that depends on it, will be able to run again. This patch adds FAULT_FLAG_RETRY_NOWAIT (suggested by Linus) and FOLL_NOWAIT follow_page flags. FAULT_FLAG_RETRY_NOWAIT, when used in conjunction with VM_FAULT_ALLOW_RETRY, indicates to handle_mm_fault that it shouldn't drop mmap_sem and wait on a page, but return VM_FAULT_RETRY instead. [akpm@linux-foundation.org: improve FOLL_NOWAIT comment] Signed-off-by: Gleb Natapov Cc: Linus Torvalds Cc: Hugh Dickins Acked-by: Rik van Riel Cc: Michel Lespinasse Cc: Avi Kivity Cc: Marcelo Tosatti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1f82adc85352..901435e3a9a9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -151,6 +151,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ #define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ #define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */ +#define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */ /* * This interface is used by x86 PAT code to identify a pfn mapping that is @@ -1545,6 +1546,8 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address, #define FOLL_GET 0x04 /* do get_page on page */ #define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ +#define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO + * and return without waiting upon it */ #define FOLL_MLOCK 0x40 /* mark page as mlocked */ #define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ -- cgit v1.2.2 From 033193275b3ffcfe7f3fde7b569f3d207f6cd6a0 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 22 Mar 2011 16:32:56 -0700 Subject: pagewalk: only split huge pages when necessary Right now, if a mm_walk has either ->pte_entry or ->pmd_entry set, it will unconditionally split any transparent huge pages it runs in to. In practice, that means that anyone doing a cat /proc/$pid/smaps will unconditionally break down every huge page in the process and depend on khugepaged to re-collapse it later. This is fairly suboptimal. This patch changes that behavior. It teaches each ->pmd_entry handler (there are five) that they must break down the THPs themselves. Also, the _generic_ code will never break down a THP unless a ->pte_entry handler is actually set. This means that the ->pmd_entry handlers can now choose to deal with THPs without breaking them down. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Dave Hansen Acked-by: Mel Gorman Acked-by: David Rientjes Reviewed-by: Eric B Munson Tested-by: Eric B Munson Cc: Michael J Wolf Cc: Andrea Arcangeli Cc: Johannes Weiner Cc: Matt Mackall Cc: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 901435e3a9a9..294104e0891d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -914,6 +914,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlb, * @pgd_entry: if set, called for each non-empty PGD (top-level) entry * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry + * this handler is required to be able to handle + * pmd_trans_huge() pmds. They may simply choose to + * split_huge_page() instead of handling it explicitly. * @pte_entry: if set, called for each non-empty PTE (4th-level) entry * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry -- cgit v1.2.2 From 31db58b3ab432f72ea76be58b12e6ffaf627d5db Mon Sep 17 00:00:00 2001 From: Stephen Wilson Date: Sun, 13 Mar 2011 15:49:15 -0400 Subject: mm: arch: make get_gate_vma take an mm_struct instead of a task_struct Morally, the presence of a gate vma is more an attribute of a particular mm than a particular task. Moreover, dropping the dependency on task_struct will help make both existing and future operations on mm's more flexible and convenient. Signed-off-by: Stephen Wilson Reviewed-by: Michel Lespinasse Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Al Viro --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 581703d86fbd..18b4a6358ab4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1578,7 +1578,7 @@ static inline bool kernel_page_present(struct page *page) { return true; } #endif /* CONFIG_HIBERNATION */ #endif -extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk); +extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); #ifdef __HAVE_ARCH_GATE_AREA int in_gate_area_no_task(unsigned long addr); int in_gate_area(struct task_struct *task, unsigned long addr); -- cgit v1.2.2 From 83b964bbf82eb13a8f31bb49ca420787fe01f7a6 Mon Sep 17 00:00:00 2001 From: Stephen Wilson Date: Sun, 13 Mar 2011 15:49:16 -0400 Subject: mm: arch: make in_gate_area take an mm_struct instead of a task_struct Morally, the question of whether an address lies in a gate vma should be asked with respect to an mm, not a particular task. Moreover, dropping the dependency on task_struct will help make existing and future operations on mm's more flexible and convenient. Signed-off-by: Stephen Wilson Reviewed-by: Michel Lespinasse Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Al Viro --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 18b4a6358ab4..5c6d916cd302 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1581,10 +1581,10 @@ static inline bool kernel_page_present(struct page *page) { return true; } extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); #ifdef __HAVE_ARCH_GATE_AREA int in_gate_area_no_task(unsigned long addr); -int in_gate_area(struct task_struct *task, unsigned long addr); +int in_gate_area(struct mm_struct *mm, unsigned long addr); #else int in_gate_area_no_task(unsigned long addr); -#define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);}) +#define in_gate_area(mm, addr) ({(void)mm; in_gate_area_no_task(addr);}) #endif /* __HAVE_ARCH_GATE_AREA */ int drop_caches_sysctl_handler(struct ctl_table *, int, -- cgit v1.2.2 From cae5d39032acf26c265f6b1dc73d7ce6ff4bc387 Mon Sep 17 00:00:00 2001 From: Stephen Wilson Date: Sun, 13 Mar 2011 15:49:17 -0400 Subject: mm: arch: rename in_gate_area_no_task to in_gate_area_no_mm Now that gate vma's are referenced with respect to a particular mm and not a particular task it only makes sense to propagate the change to this predicate as well. Signed-off-by: Stephen Wilson Reviewed-by: Michel Lespinasse Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Al Viro --- include/linux/mm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5c6d916cd302..9d6efefdde50 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1580,11 +1580,11 @@ static inline bool kernel_page_present(struct page *page) { return true; } extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); #ifdef __HAVE_ARCH_GATE_AREA -int in_gate_area_no_task(unsigned long addr); +int in_gate_area_no_mm(unsigned long addr); int in_gate_area(struct mm_struct *mm, unsigned long addr); #else -int in_gate_area_no_task(unsigned long addr); -#define in_gate_area(mm, addr) ({(void)mm; in_gate_area_no_task(addr);}) +int in_gate_area_no_mm(unsigned long addr); +#define in_gate_area(mm, addr) ({(void)mm; in_gate_area_no_mm(addr);}) #endif /* __HAVE_ARCH_GATE_AREA */ int drop_caches_sysctl_handler(struct ctl_table *, int, -- cgit v1.2.2 From 5ddd36b9c59887c6416e21daf984fbdd9b1818df Mon Sep 17 00:00:00 2001 From: Stephen Wilson Date: Sun, 13 Mar 2011 15:49:20 -0400 Subject: mm: implement access_remote_vm Provide an alternative to access_process_vm that allows the caller to obtain a reference to the supplied mm_struct. Signed-off-by: Stephen Wilson Signed-off-by: Al Viro --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9d6efefdde50..60011d26bffc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -971,6 +971,8 @@ static inline int handle_mm_fault(struct mm_struct *mm, extern int make_pages_present(unsigned long addr, unsigned long end); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); +extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, + void *buf, int len, int write); int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, unsigned int foll_flags, -- cgit v1.2.2 From b2b755b5f10eb32fbdc73a9907c07006b17f714b Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 24 Mar 2011 15:18:15 -0700 Subject: lib, arch: add filter argument to show_mem and fix private implementations Commit ddd588b5dd55 ("oom: suppress nodes that are not allowed from meminfo on oom kill") moved lib/show_mem.o out of lib/lib.a, which resulted in build warnings on all architectures that implement their own versions of show_mem(): lib/lib.a(show_mem.o): In function `show_mem': show_mem.c:(.text+0x1f4): multiple definition of `show_mem' arch/sparc/mm/built-in.o:(.text+0xd70): first defined here The fix is to remove __show_mem() and add its argument to show_mem() in all implementations to prevent this breakage. Architectures that implement their own show_mem() actually don't do anything with the argument yet, but they could be made to filter nodes that aren't allowed in the current context in the future just like the generic implementation. Reported-by: Stephen Rothwell Reported-by: James Bottomley Suggested-by: Andrew Morton Signed-off-by: David Rientjes Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index f9535b2c9558..7606d7db96c9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -861,7 +861,7 @@ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) /* - * Flags passed to __show_mem() and __show_free_areas() to suppress output in + * Flags passed to show_mem() and __show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* filter disallowed nodes */ @@ -1360,8 +1360,7 @@ extern void setup_per_zone_wmarks(void); extern void calculate_zone_inactive_ratio(struct zone *zone); extern void mem_init(void); extern void __init mmap_init(void); -extern void show_mem(void); -extern void __show_mem(unsigned int flags); +extern void show_mem(unsigned int flags); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); extern int after_bootmem; -- cgit v1.2.2 From 25985edcedea6396277003854657b5f3cb31a628 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Wed, 30 Mar 2011 22:57:33 -0300 Subject: Fix common misspellings Fixes generated by 'codespell' and manually reviewed. Signed-off-by: Lucas De Marchi --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7606d7db96c9..692dbae6ffa7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -608,7 +608,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) #endif /* - * Define the bit shifts to access each section. For non-existant + * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ -- cgit v1.2.2 From 78f11a255749d09025f54d4e2df4fbcb031530e2 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 27 Apr 2011 15:26:45 -0700 Subject: mm: thp: fix /dev/zero MAP_PRIVATE and vm_flags cleanups The huge_memory.c THP page fault was allowed to run if vm_ops was null (which would succeed for /dev/zero MAP_PRIVATE, as the f_op->mmap wouldn't setup a special vma->vm_ops and it would fallback to regular anonymous memory) but other THP logics weren't fully activated for vmas with vm_file not NULL (/dev/zero has a not NULL vma->vm_file). So this removes the vm_file checks so that /dev/zero also can safely use THP (the other albeit safer approach to fix this bug would have been to prevent the THP initial page fault to run if vm_file was set). After removing the vm_file checks, this also makes huge_memory.c stricter in khugepaged for the DEBUG_VM=y case. It doesn't replace the vm_file check with a is_pfn_mapping check (but it keeps checking for VM_PFNMAP under VM_BUG_ON) because for a is_cow_mapping() mapping VM_PFNMAP should only be allowed to exist before the first page fault, and in turn when vma->anon_vma is null (so preventing khugepaged registration). So I tend to think the previous comment saying if vm_file was set, VM_PFNMAP might have been set and we could still be registered in khugepaged (despite anon_vma was not NULL to be registered in khugepaged) was too paranoid. The is_linear_pfn_mapping check is also I think superfluous (as described by comment) but under DEBUG_VM it is safe to stay. Addresses https://bugzilla.kernel.org/show_bug.cgi?id=33682 Signed-off-by: Andrea Arcangeli Reported-by: Caspar Zhang Acked-by: Mel Gorman Acked-by: Rik van Riel Cc: [2.6.38.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 692dbae6ffa7..2348db26bc3d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -137,7 +137,8 @@ extern unsigned int kobjsize(const void *objp); #define VM_RandomReadHint(v) ((v)->vm_flags & VM_RAND_READ) /* - * special vmas that are non-mergable, non-mlock()able + * Special vmas that are non-mergable, non-mlock()able. + * Note: mm/huge_memory.c VM_NO_THP depends on this definition. */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP) -- cgit v1.2.2 From a09a79f66874c905af35d5bb5e5f2fdc7b6b894d Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 9 May 2011 13:01:09 +0200 Subject: Don't lock guardpage if the stack is growing up Linux kernel excludes guard page when performing mlock on a VMA with down-growing stack. However, some architectures have up-growing stack and locking the guard page should be excluded in this case too. This patch fixes lvm2 on PA-RISC (and possibly other architectures with up-growing stack). lvm2 calculates number of used pages when locking and when unlocking and reports an internal error if the numbers mismatch. [ Patch changed fairly extensively to also fix /proc//maps for the grows-up case, and to move things around a bit to clean it all up and share the infrstructure with the /proc bits. Tested on ia64 that has both grow-up and grow-down segments - Linus ] Signed-off-by: Mikulas Patocka Tested-by: Tony Luck Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2348db26bc3d..6507dde38b16 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1011,11 +1011,33 @@ int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); /* Is the vma a continuation of the stack vma above it? */ -static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr) +static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr) { return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); } +static inline int stack_guard_page_start(struct vm_area_struct *vma, + unsigned long addr) +{ + return (vma->vm_flags & VM_GROWSDOWN) && + (vma->vm_start == addr) && + !vma_growsdown(vma->vm_prev, addr); +} + +/* Is the vma a continuation of the stack vma below it? */ +static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr) +{ + return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP); +} + +static inline int stack_guard_page_end(struct vm_area_struct *vma, + unsigned long addr) +{ + return (vma->vm_flags & VM_GROWSUP) && + (vma->vm_end == addr) && + !vma_growsup(vma->vm_next, addr); +} + extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len); -- cgit v1.2.2 From 7bf02ea22c6cdd09e2d3f1d3c3fe366b834ae9af Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 24 May 2011 17:11:16 -0700 Subject: arch, mm: filter disallowed nodes from arch specific show_mem functions Architectures that implement their own show_mem() function did not pass the filter argument to show_free_areas() to appropriately avoid emitting the state of nodes that are disallowed in the current context. This patch now passes the filter argument to show_free_areas() so those nodes are now avoided. This patch also removes the show_free_areas() wrapper around __show_free_areas() and converts existing callers to pass an empty filter. ia64 emits additional information for each node, so skip_free_areas_zone() must be made global to filter disallowed nodes and it is converted to use a nid argument rather than a zone for this use case. Signed-off-by: David Rientjes Cc: Russell King Cc: Tony Luck Cc: Fenghua Yu Cc: Kyle McMartin Cc: Helge Deller Cc: James Bottomley Cc: "David S. Miller" Cc: Guan Xuetao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6507dde38b16..1746f67c33de 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -862,13 +862,13 @@ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) /* - * Flags passed to show_mem() and __show_free_areas() to suppress output in + * Flags passed to show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* filter disallowed nodes */ -extern void show_free_areas(void); -extern void __show_free_areas(unsigned int flags); +extern void show_free_areas(unsigned int flags); +extern bool skip_free_areas_node(unsigned int flags, int nid); int shmem_lock(struct file *file, int lock, struct user_struct *user); struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); -- cgit v1.2.2 From 37b23e0525d393d48a7d59f870b3bc061a30ccdb Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 24 May 2011 17:11:30 -0700 Subject: x86,mm: make pagefault killable When an oom killing occurs, almost all processes are getting stuck at the following two points. 1) __alloc_pages_nodemask 2) __lock_page_or_retry 1) is not very problematic because TIF_MEMDIE leads to an allocation failure and getting out from page allocator. 2) is more problematic. In an OOM situation, zones typically don't have page cache at all and memory starvation might lead to greatly reduced IO performance. When a fork bomb occurs, TIF_MEMDIE tasks don't die quickly, meaning that a fork bomb may create new process quickly rather than the oom-killer killing it. Then, the system may become livelocked. This patch makes the pagefault interruptible by SIGKILL. Signed-off-by: KOSAKI Motohiro Reviewed-by: KAMEZAWA Hiroyuki Cc: Minchan Kim Cc: Matthew Wilcox Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1746f67c33de..57d3d5fade16 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -153,6 +153,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ #define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */ #define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */ +#define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */ /* * This interface is used by x86 PAT code to identify a pfn mapping that is -- cgit v1.2.2 From 1b79acc91115ba47e744b70bb166b77bd94f5855 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 24 May 2011 17:11:32 -0700 Subject: mm, mem-hotplug: recalculate lowmem_reserve when memory hotplug occurs Currently, memory hotplug calls setup_per_zone_wmarks() and calculate_zone_inactive_ratio(), but doesn't call setup_per_zone_lowmem_reserve(). It means the number of reserved pages aren't updated even if memory hot plug occur. This patch fixes it. Signed-off-by: KOSAKI Motohiro Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Mel Gorman Reviewed-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 57d3d5fade16..e173cd297d88 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1381,7 +1381,7 @@ extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, enum memmap_context); extern void setup_per_zone_wmarks(void); -extern void calculate_zone_inactive_ratio(struct zone *zone); +extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); extern void show_mem(unsigned int flags); -- cgit v1.2.2 From d05f3169c0fbca16132ec7c2be71685c6de638b5 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 24 May 2011 17:11:44 -0700 Subject: mm: make expand_downwards() symmetrical with expand_upwards() Currently we have expand_upwards exported while expand_downwards is accessible only via expand_stack or expand_stack_downwards. check_stack_guard_page is a nice example of the asymmetry. It uses expand_stack for VM_GROWSDOWN while expand_upwards is called for VM_GROWSUP case. Let's clean this up by exporting both functions and make those names consistent. Let's use expand_{upwards,downwards} because expanding doesn't always involve stack manipulation (an example is ia64_do_page_fault which uses expand_upwards for registers backing store expansion). expand_downwards has to be defined for both CONFIG_STACK_GROWS{UP,DOWN} because get_arg_page calls the downwards version in the early process initialization phase for growsup configuration. Signed-off-by: Michal Hocko Acked-by: Hugh Dickins Cc: James Bottomley Cc: "Luck, Tony" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index e173cd297d88..d2948af126ca 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1518,15 +1518,17 @@ unsigned long ra_submit(struct file_ra_state *ra, struct address_space *mapping, struct file *filp); -/* Do stack extension */ +/* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); + +/* CONFIG_STACK_GROWSUP still needs to to grow downwards at some places */ +extern int expand_downwards(struct vm_area_struct *vma, + unsigned long address); #if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #else #define expand_upwards(vma, address) do { } while (0) #endif -extern int expand_stack_downwards(struct vm_area_struct *vma, - unsigned long address); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); -- cgit v1.2.2 From d16dfc550f5326a4000f3322582a7c05dec91d7a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 24 May 2011 17:11:45 -0700 Subject: mm: mmu_gather rework Rework the existing mmu_gather infrastructure. The direct purpose of these patches was to allow preemptible mmu_gather, but even without that I think these patches provide an improvement to the status quo. The first 9 patches rework the mmu_gather infrastructure. For review purpose I've split them into generic and per-arch patches with the last of those a generic cleanup. The next patch provides generic RCU page-table freeing, and the followup is a patch converting s390 to use this. I've also got 4 patches from DaveM lined up (not included in this series) that uses this to implement gup_fast() for sparc64. Then there is one patch that extends the generic mmu_gather batching. After that follow the mm preemptibility patches, these make part of the mm a lot more preemptible. It converts i_mmap_lock and anon_vma->lock to mutexes which together with the mmu_gather rework makes mmu_gather preemptible as well. Making i_mmap_lock a mutex also enables a clean-up of the truncate code. This also allows for preemptible mmu_notifiers, something that XPMEM I think wants. Furthermore, it removes the new and universially detested unmap_mutex. This patch: Remove the first obstacle towards a fully preemptible mmu_gather. The current scheme assumes mmu_gather is always done with preemption disabled and uses per-cpu storage for the page batches. Change this to try and allocate a page for batching and in case of failure, use a small on-stack array to make some progress. Preemptible mmu_gather is desired in general and usable once i_mmap_lock becomes a mutex. Doing it before the mutex conversion saves us from having to rework the code by moving the mmu_gather bits inside the pte_lock. Also avoid flushing the tlb batches from under the pte lock, this is useful even without the i_mmap_lock conversion as it significantly reduces pte lock hold times. [akpm@linux-foundation.org: fix comment tpyo] Signed-off-by: Peter Zijlstra Cc: Benjamin Herrenschmidt Cc: David Miller Cc: Martin Schwidefsky Cc: Russell King Cc: Paul Mundt Cc: Jeff Dike Cc: Richard Weinberger Cc: Tony Luck Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Hugh Dickins Acked-by: Mel Gorman Cc: KOSAKI Motohiro Cc: Nick Piggin Cc: Namhyung Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index d2948af126ca..ffcce9bf2b54 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -906,7 +906,7 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *); -unsigned long unmap_vmas(struct mmu_gather **tlb, +unsigned long unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long start_addr, unsigned long end_addr, unsigned long *nr_accounted, struct zap_details *); -- cgit v1.2.2 From 97a894136f29802da19a15541de3c019e1ca147e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 24 May 2011 17:12:04 -0700 Subject: mm: Remove i_mmap_lock lockbreak Hugh says: "The only significant loser, I think, would be page reclaim (when concurrent with truncation): could spin for a long time waiting for the i_mmap_mutex it expects would soon be dropped? " Counter points: - cpu contention makes the spin stop (need_resched()) - zap pages should be freeing pages at a higher rate than reclaim ever can I think the simplification of the truncate code is definitely worth it. Effectively reverts: 2aa15890f3c ("mm: prevent concurrent unmap_mapping_range() on the same inode") and takes out the code that caused its problem. Signed-off-by: Peter Zijlstra Reviewed-by: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Benjamin Herrenschmidt Cc: David Miller Cc: Martin Schwidefsky Cc: Russell King Cc: Paul Mundt Cc: Jeff Dike Cc: Richard Weinberger Cc: Tony Luck Cc: Mel Gorman Cc: KOSAKI Motohiro Cc: Nick Piggin Cc: Namhyung Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index ffcce9bf2b54..2ad0ac8c3f32 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -895,8 +895,6 @@ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ - spinlock_t *i_mmap_lock; /* For unmap_mapping_range: */ - unsigned long truncate_count; /* Compare vm_truncate_count */ }; struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, -- cgit v1.2.2 From a238ab5b0239575c179f4976064192c3f7409dad Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 24 May 2011 17:12:16 -0700 Subject: mm: break out page allocation warning code This originally started as a simple patch to give vmalloc() some more verbose output on failure on top of the plain page allocator messages. Johannes suggested that it might be nicer to lead with the vmalloc() info _before_ the page allocator messages. But, I do think there's a lot of value in what __alloc_pages_slowpath() does with its filtering and so forth. This patch creates a new function which other allocators can call instead of relying on the internal page allocator warnings. It also gives this function private rate-limiting which separates it from other printk_ratelimit() users. Signed-off-by: Dave Hansen Cc: Johannes Weiner Cc: David Rientjes Cc: Michal Nazarewicz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2ad0ac8c3f32..8e2f2cd821f7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1387,6 +1387,8 @@ extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); extern int after_bootmem; +extern void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...); + extern void setup_per_cpu_pageset(void); extern void zone_pcp_update(struct zone *zone); -- cgit v1.2.2 From a09ed5e00084448453c8bada4dcd31e5fbfc2f21 Mon Sep 17 00:00:00 2001 From: Ying Han Date: Tue, 24 May 2011 17:12:26 -0700 Subject: vmscan: change shrink_slab() interfaces by passing shrink_control Consolidate the existing parameters to shrink_slab() into a new shrink_control struct. This is needed later to pass the same struct to shrinkers. Signed-off-by: Ying Han Cc: KOSAKI Motohiro Cc: Minchan Kim Acked-by: Pavel Emelyanov Cc: KAMEZAWA Hiroyuki Cc: Mel Gorman Acked-by: Rik van Riel Cc: Johannes Weiner Cc: Hugh Dickins Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8e2f2cd821f7..32cfa9602d00 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1161,6 +1161,15 @@ static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm) } #endif +/* + * This struct is used to pass information from page reclaim to the shrinkers. + * We consolidate the values for easier extention later. + */ +struct shrink_control { + unsigned long nr_scanned; + gfp_t gfp_mask; +}; + /* * A callback you can register to apply pressure to ageable caches. * @@ -1630,8 +1639,8 @@ int in_gate_area_no_mm(unsigned long addr); int drop_caches_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, - unsigned long lru_pages); +unsigned long shrink_slab(struct shrink_control *shrink, + unsigned long lru_pages); #ifndef CONFIG_MMU #define randomize_va_space 0 -- cgit v1.2.2 From 1495f230fa7750479c79e3656286b9183d662077 Mon Sep 17 00:00:00 2001 From: Ying Han Date: Tue, 24 May 2011 17:12:27 -0700 Subject: vmscan: change shrinker API by passing shrink_control struct Change each shrinker's API by consolidating the existing parameters into shrink_control struct. This will simplify any further features added w/o touching each file of shrinker. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: fix warning] [kosaki.motohiro@jp.fujitsu.com: fix up new shrinker API] [akpm@linux-foundation.org: fix xfs warning] [akpm@linux-foundation.org: update gfs2] Signed-off-by: Ying Han Cc: KOSAKI Motohiro Cc: Minchan Kim Acked-by: Pavel Emelyanov Cc: KAMEZAWA Hiroyuki Cc: Mel Gorman Acked-by: Rik van Riel Cc: Johannes Weiner Cc: Hugh Dickins Cc: Dave Hansen Cc: Steven Whitehouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 32cfa9602d00..5cbbf78eaac7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1166,18 +1166,20 @@ static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm) * We consolidate the values for easier extention later. */ struct shrink_control { - unsigned long nr_scanned; gfp_t gfp_mask; + + /* How many slab objects shrinker() should scan and try to reclaim */ + unsigned long nr_to_scan; }; /* * A callback you can register to apply pressure to ageable caches. * - * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'. It should - * look through the least-recently-used 'nr_to_scan' entries and - * attempt to free them up. It should return the number of objects - * which remain in the cache. If it returns -1, it means it cannot do - * any scanning at this time (eg. there is a risk of deadlock). + * 'sc' is passed shrink_control which includes a count 'nr_to_scan' + * and a 'gfpmask'. It should look through the least-recently-used + * 'nr_to_scan' entries and attempt to free them up. It should return + * the number of objects which remain in the cache. If it returns -1, it means + * it cannot do any scanning at this time (eg. there is a risk of deadlock). * * The 'gfpmask' refers to the allocation we are currently trying to * fulfil. @@ -1186,7 +1188,7 @@ struct shrink_control { * querying the cache size, so a fastpath for that case is appropriate. */ struct shrinker { - int (*shrink)(struct shrinker *, int nr_to_scan, gfp_t gfp_mask); + int (*shrink)(struct shrinker *, struct shrink_control *sc); int seeks; /* seeks to recreate an obj */ /* These are for internal use */ @@ -1640,7 +1642,8 @@ int in_gate_area_no_mm(unsigned long addr); int drop_caches_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); unsigned long shrink_slab(struct shrink_control *shrink, - unsigned long lru_pages); + unsigned long nr_pages_scanned, + unsigned long lru_pages); #ifndef CONFIG_MMU #define randomize_va_space 0 -- cgit v1.2.2 From bf4e8902ee5080f5d2c810b639e7e778c8082b52 Mon Sep 17 00:00:00 2001 From: Daniel Kiper Date: Tue, 24 May 2011 17:12:32 -0700 Subject: mm: enable set_page_section() only if CONFIG_SPARSEMEM and !CONFIG_SPARSEMEM_VMEMMAP set_page_section() is meaningful only in CONFIG_SPARSEMEM and !CONFIG_SPARSEMEM_VMEMMAP context. Move it to proper place and amend accordingly functions which are using it. Signed-off-by: Daniel Kiper Acked-by: Dave Hansen Acked-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5cbbf78eaac7..6702171f8d0a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -682,6 +682,12 @@ static inline struct zone *page_zone(struct page *page) } #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) +static inline void set_page_section(struct page *page, unsigned long section) +{ + page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); + page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; +} + static inline unsigned long page_to_section(struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; @@ -700,18 +706,14 @@ static inline void set_page_node(struct page *page, unsigned long node) page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; } -static inline void set_page_section(struct page *page, unsigned long section) -{ - page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); - page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; -} - static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { set_page_zone(page, zone); set_page_node(page, node); +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) set_page_section(page, pfn_to_section_nr(pfn)); +#endif } /* -- cgit v1.2.2 From ba93fa81b5f2bf0076407a3a777fff122ce16220 Mon Sep 17 00:00:00 2001 From: Daniel Kiper Date: Tue, 24 May 2011 17:12:34 -0700 Subject: mm: do not define PFN_SECTION_SHIFT if !CONFIG_SPARSEMEM Do not define PFN_SECTION_SHIFT if !CONFIG_SPARSEMEM. Signed-off-by: Daniel Kiper Acked-by: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6702171f8d0a..32309f6542e8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -605,10 +605,6 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) #define NODE_NOT_IN_PAGE_FLAGS #endif -#ifndef PFN_SECTION_SHIFT -#define PFN_SECTION_SHIFT 0 -#endif - /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures -- cgit v1.2.2 From 172703b08cd05e2d5196ac13e94cc186f629d58b Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Tue, 24 May 2011 17:12:36 -0700 Subject: mm: delete non-atomic mm counter implementation The problem with having two different types of counters is that developers adding new code need to keep in mind whether it's safe to use both the atomic and non-atomic implementations. For example, when adding new callers of the *_mm_counter() functions a developer needs to ensure that those paths are always executed with page_table_lock held, in case we're using the non-atomic implementation of mm counters. Hugh Dickins introduced the atomic mm counters in commit f412ac08c986 ("[PATCH] mm: fix rss and mmlist locking"). When asked why he left the non-atomic counters around he said, | The only reason was to avoid adding costly atomic operations into a | configuration that had no need for them there: the page_table_lock | sufficed. | | Certainly it would be simpler just to delete the non-atomic variant. | | And I think it's fair to say that any configuration on which we're | measuring performance to that degree (rather than "does it boot fast?" | type measurements), would already be going the split ptlocks route. Removing the non-atomic counters eases the maintenance burden because developers no longer have to mindful of the two implementations when using *_mm_counter(). Note that all architectures provide a means of atomically updating atomic_long_t variables, even if they have to revert to the generic spinlock implementation because they don't support 64-bit atomic instructions (see lib/atomic64.c). Signed-off-by: Matt Fleming Acked-by: Dave Hansen Acked-by: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 44 +++++++------------------------------------- 1 file changed, 7 insertions(+), 37 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 32309f6542e8..48e458190d88 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1053,65 +1053,35 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, /* * per-process(per-mm_struct) statistics. */ -#if defined(SPLIT_RSS_COUNTING) -/* - * The mm counters are not protected by its page_table_lock, - * so must be incremented atomically. - */ static inline void set_mm_counter(struct mm_struct *mm, int member, long value) { atomic_long_set(&mm->rss_stat.count[member], value); } +#if defined(SPLIT_RSS_COUNTING) unsigned long get_mm_counter(struct mm_struct *mm, int member); - -static inline void add_mm_counter(struct mm_struct *mm, int member, long value) -{ - atomic_long_add(value, &mm->rss_stat.count[member]); -} - -static inline void inc_mm_counter(struct mm_struct *mm, int member) -{ - atomic_long_inc(&mm->rss_stat.count[member]); -} - -static inline void dec_mm_counter(struct mm_struct *mm, int member) -{ - atomic_long_dec(&mm->rss_stat.count[member]); -} - -#else /* !USE_SPLIT_PTLOCKS */ -/* - * The mm counters are protected by its page_table_lock, - * so can be incremented directly. - */ -static inline void set_mm_counter(struct mm_struct *mm, int member, long value) -{ - mm->rss_stat.count[member] = value; -} - +#else static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) { - return mm->rss_stat.count[member]; + return atomic_long_read(&mm->rss_stat.count[member]); } +#endif static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { - mm->rss_stat.count[member] += value; + atomic_long_add(value, &mm->rss_stat.count[member]); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { - mm->rss_stat.count[member]++; + atomic_long_inc(&mm->rss_stat.count[member]); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { - mm->rss_stat.count[member]--; + atomic_long_dec(&mm->rss_stat.count[member]); } -#endif /* !USE_SPLIT_PTLOCKS */ - static inline unsigned long get_mm_rss(struct mm_struct *mm) { return get_mm_counter(mm, MM_FILEPAGES) + -- cgit v1.2.2 From c856507f2b2b47a49d8587afb58930b463f6bff4 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 24 May 2011 17:12:40 -0700 Subject: mm: remove last trace of shmem_get_unmapped_area Remove noMMU declaration of shmem_get_unmapped_area() from mm.h: it fell out of use in 2.6.21 and ceased to exist in 2.6.29. Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 48e458190d88..8eb969ebf904 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -873,14 +873,6 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user); struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); int shmem_zero_setup(struct vm_area_struct *); -#ifndef CONFIG_MMU -extern unsigned long shmem_get_unmapped_area(struct file *file, - unsigned long addr, - unsigned long len, - unsigned long pgoff, - unsigned long flags); -#endif - extern int can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); extern void user_shm_unlock(size_t, struct user_struct *); -- cgit v1.2.2 From ca16d140af91febe25daeb9e032bf8bd46b8c31f Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 26 May 2011 19:16:19 +0900 Subject: mm: don't access vm_flags as 'int' The type of vma->vm_flags is 'unsigned long'. Neither 'int' nor 'unsigned int'. This patch fixes such misuse. Signed-off-by: KOSAKI Motohiro [ Changed to use a typedef - we'll extend it to cover more cases later, since there has been discussion about making it a 64-bit type.. - Linus ] Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8eb969ebf904..fb8e814f78dc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -165,12 +165,12 @@ extern pgprot_t protection_map[16]; */ static inline int is_linear_pfn_mapping(struct vm_area_struct *vma) { - return (vma->vm_flags & VM_PFN_AT_MMAP); + return !!(vma->vm_flags & VM_PFN_AT_MMAP); } static inline int is_pfn_mapping(struct vm_area_struct *vma) { - return (vma->vm_flags & VM_PFNMAP); + return !!(vma->vm_flags & VM_PFNMAP); } /* @@ -1432,7 +1432,7 @@ extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long flag, unsigned long pgoff); extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, unsigned long flags, - unsigned int vm_flags, unsigned long pgoff); + vm_flags_t vm_flags, unsigned long pgoff); static inline unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, -- cgit v1.2.2 From 3864601387cf4196371e3c1897fdffa5228296f9 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 26 May 2011 16:25:46 -0700 Subject: mm: extract exe_file handling from procfs Setup and cleanup of mm_struct->exe_file is currently done in fs/proc/. This was because exe_file was needed only for /proc//exe. Since we will need the exe_file functionality also for core dumps (so core name can contain full binary path), built this functionality always into the kernel. To achieve that move that out of proc FS to the kernel/ where in fact it should belong. By doing that we can make dup_mm_exe_file static. Also we can drop linux/proc_fs.h inclusion in fs/exec.c and kernel/fork.c. Signed-off-by: Jiri Slaby Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index fb8e814f78dc..9670f71d7be9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1408,17 +1408,11 @@ extern void exit_mmap(struct mm_struct *); extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); -#ifdef CONFIG_PROC_FS /* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */ extern void added_exe_file_vma(struct mm_struct *mm); extern void removed_exe_file_vma(struct mm_struct *mm); -#else -static inline void added_exe_file_vma(struct mm_struct *mm) -{} - -static inline void removed_exe_file_vma(struct mm_struct *mm) -{} -#endif /* CONFIG_PROC_FS */ +extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); +extern struct file *get_mm_exe_file(struct mm_struct *mm); extern int may_expand_vm(struct mm_struct *mm, unsigned long npages); extern int install_special_mapping(struct mm_struct *mm, -- cgit v1.2.2