From 3ca7b3c5b64d35fe02c35b5d44c2c58b49499fee Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Dec 2009 17:58:57 -0800 Subject: mm: define PAGE_MAPPING_FLAGS At present we define PageAnon(page) by the low PAGE_MAPPING_ANON bit set in page->mapping, with the higher bits a pointer to the anon_vma; and have defined PageKsm(page) as that with NULL anon_vma. But KSM swapping will need to store a pointer there: so in preparation for that, now define PAGE_MAPPING_FLAGS as the low two bits, including PAGE_MAPPING_KSM (always set along with PAGE_MAPPING_ANON, until some other use for the bit emerges). Declare page_rmapping(page) to return the pointer part of page->mapping, and page_anon_vma(page) to return the anon_vma pointer when that's what it is. Use these in a few appropriate places: notably, unuse_vma() has been testing page->mapping, but is better to be testing page_anon_vma() (cases may be added in which flag bits are set without any pointer). Signed-off-by: Hugh Dickins Cc: Izik Eidus Cc: Andrea Arcangeli Cc: Nick Piggin Cc: KOSAKI Motohiro Reviewed-by: Rik van Riel Cc: Lee Schermerhorn Cc: Andi Kleen Cc: KAMEZAWA Hiroyuki Cc: Wu Fengguang Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 24c3956..1202cd3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -620,13 +620,22 @@ void page_address_init(void); /* * On an anonymous page mapped into a user virtual memory area, * page->mapping points to its anon_vma, not to a struct address_space; - * with the PAGE_MAPPING_ANON bit set to distinguish it. + * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. + * + * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, + * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit; + * and then page->mapping points, not to an anon_vma, but to a private + * structure which KSM associates with that merged page. See ksm.h. + * + * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used. * * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" * refers to user virtual address space into which the page is mapped. */ #define PAGE_MAPPING_ANON 1 +#define PAGE_MAPPING_KSM 2 +#define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM) extern struct address_space swapper_space; static inline struct address_space *page_mapping(struct page *page) @@ -644,6 +653,12 @@ static inline struct address_space *page_mapping(struct page *page) return mapping; } +/* Neutral page->mapping pointer to address_space or anon_vma or other */ +static inline void *page_rmapping(struct page *page) +{ + return (void *)((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS); +} + static inline int PageAnon(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; -- cgit v1.1 From f096e59e844ba3c5d5a7b54b3deafd2aeeebf921 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Mon, 14 Dec 2009 17:59:51 -0800 Subject: include/linux/mm.h: remove unneeded ifdef The check code for CONFIG_SWAP is redundant, because there is a non-CONFIG_SWAP version for PageSwapCache() which just returns 0. Signed-off-by: Huang Shijie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1202cd3..52b2645 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -643,12 +643,9 @@ static inline struct address_space *page_mapping(struct page *page) struct address_space *mapping = page->mapping; VM_BUG_ON(PageSlab(page)); -#ifdef CONFIG_SWAP if (unlikely(PageSwapCache(page))) mapping = &swapper_space; - else -#endif - if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON)) + else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON)) mapping = NULL; return mapping; } -- cgit v1.1 From 5dc37642cbce34619e4588a9f0bdad1d2f870956 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Mon, 14 Dec 2009 18:00:01 -0800 Subject: mm hugetlb: add hugepage support to pagemap This patch enables extraction of the pfn of a hugepage from /proc/pid/pagemap in an architecture independent manner. Details ------- My test program (leak_pagemap) works as follows: - creat() and mmap() a file on hugetlbfs (file size is 200MB == 100 hugepages,) - read()/write() something on it, - call page-types with option -p, - munmap() and unlink() the file on hugetlbfs Without my patches ------------------ $ ./leak_pagemap flags page-count MB symbolic-flags long-symbolic-flags 0x0000000000000000 1 0 __________________________________ 0x0000000000000804 1 0 __R________M______________________ referenced,mmap 0x000000000000086c 81 0 __RU_lA____M______________________ referenced,uptodate,lru,active,mmap 0x0000000000005808 5 0 ___U_______Ma_b___________________ uptodate,mmap,anonymous,swapbacked 0x0000000000005868 12 0 ___U_lA____Ma_b___________________ uptodate,lru,active,mmap,anonymous,swapbacked 0x000000000000586c 1 0 __RU_lA____Ma_b___________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked total 101 0 The output of page-types don't show any hugepage. With my patches --------------- $ ./leak_pagemap flags page-count MB symbolic-flags long-symbolic-flags 0x0000000000000000 1 0 __________________________________ 0x0000000000030000 51100 199 ________________TG________________ compound_tail,huge 0x0000000000028018 100 0 ___UD__________H_G________________ uptodate,dirty,compound_head,huge 0x0000000000000804 1 0 __R________M______________________ referenced,mmap 0x000000000000080c 1 0 __RU_______M______________________ referenced,uptodate,mmap 0x000000000000086c 80 0 __RU_lA____M______________________ referenced,uptodate,lru,active,mmap 0x0000000000005808 4 0 ___U_______Ma_b___________________ uptodate,mmap,anonymous,swapbacked 0x0000000000005868 12 0 ___U_lA____Ma_b___________________ uptodate,lru,active,mmap,anonymous,swapbacked 0x000000000000586c 1 0 __RU_lA____Ma_b___________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked total 51300 200 The output of page-types shows 51200 pages contributing to hugepages, containing 100 head pages and 51100 tail pages as expected. [akpm@linux-foundation.org: build fix] Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Wu Fengguang Cc: Hugh Dickins Cc: Mel Gorman Cc: Lee Schermerhorn Cc: Andy Whitcroft Cc: David Rientjes 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 52b2645..9d65ae4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -770,6 +770,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlb, * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry * @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 * * (see walk_page_range for more details) */ @@ -779,6 +780,8 @@ struct mm_walk { int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *); int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *); int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *); + int (*hugetlb_entry)(pte_t *, unsigned long, unsigned long, + struct mm_walk *); struct mm_struct *mm; void *private; }; -- cgit v1.1 From 588f9ce6ca61ecb4663ee6ef2f75d2d96c73151e Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Dec 2009 12:19:57 +0100 Subject: HWPOISON: Be more aggressive at freeing non LRU caches shake_page handles more types of page caches than lru_drain_all() - per cpu page allocator pages - per CPU LRU Stops early when the page became free. Used in followon patches. Signed-off-by: Andi Kleen --- 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 9d65ae4..68c84bb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1335,6 +1335,7 @@ extern void memory_failure(unsigned long pfn, int trapno); extern int __memory_failure(unsigned long pfn, int trapno, int ref); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; +extern void shake_page(struct page *p); extern atomic_long_t mce_bad_pages; #endif /* __KERNEL__ */ -- cgit v1.1 From 82ba011b9041dd31c15e4f63797b08aa0a288e61 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Dec 2009 12:19:57 +0100 Subject: HWPOISON: Turn ref argument into flags argument Now that "ref" is just a boolean turn it into a flags argument. First step is only a single flag that makes the code's intention more clear, but more may follow. Signed-off-by: Andi Kleen --- include/linux/mm.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 68c84bb..135e191 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1331,8 +1331,11 @@ extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim, size_t size); extern void refund_locked_memory(struct mm_struct *mm, size_t size); +enum mf_flags { + MF_COUNT_INCREASED = 1 << 0, +}; extern void memory_failure(unsigned long pfn, int trapno); -extern int __memory_failure(unsigned long pfn, int trapno, int ref); +extern int __memory_failure(unsigned long pfn, int trapno, int flags); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); -- cgit v1.1 From 847ce401df392b0704369fd3f75df614ac1414b4 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 16 Dec 2009 12:19:58 +0100 Subject: HWPOISON: Add unpoisoning support The unpoisoning interface is useful for stress testing tools to reclaim poisoned pages (to prevent OOM) There is no hardware level unpoisioning, so this cannot be used for real memory errors, only for software injected errors. Note that it may leak pages silently - those who have been removed from LRU cache, but not isolated from page cache/swap cache at hwpoison time. Especially the stress test of dirty swap cache pages shall reboot system before exhausting memory. AK: Fix comments, add documentation, add printks, rename symbol Signed-off-by: Wu Fengguang Signed-off-by: Andi Kleen --- 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 135e191..8cdb941 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1336,6 +1336,7 @@ enum mf_flags { }; extern void memory_failure(unsigned long pfn, int trapno); extern int __memory_failure(unsigned long pfn, int trapno, int flags); +extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); -- cgit v1.1 From facb6011f3993947283fa15d039dacb4ad140230 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Dec 2009 12:20:00 +0100 Subject: HWPOISON: Add soft page offline support This is a simpler, gentler variant of memory_failure() for soft page offlining controlled from user space. It doesn't kill anything, just tries to invalidate and if that doesn't work migrate the page away. This is useful for predictive failure analysis, where a page has a high rate of corrected errors, but hasn't gone bad yet. Instead it can be offlined early and avoided. The offlining is controlled from sysfs, including a new generic entry point for hard page offlining for symmetry too. We use the page isolate facility to prevent re-allocation race. Normally this is only used by memory hotplug. To avoid races with memory allocation I am using lock_system_sleep(). This avoids the situation where memory hotplug is about to isolate a page range and then hwpoison undoes that work. This is a big hammer currently, but the simplest solution currently. When the page is not free or LRU we try to free pages from slab and other caches. The slab freeing is currently quite dumb and does not try to focus on the specific slab cache which might own the page. This could be potentially improved later. Thanks to Fengguang Wu and Haicheng Li for some fixes. [Added fix from Andrew Morton to adapt to new migrate_pages prototype] Signed-off-by: Andi Kleen --- 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 8cdb941..849b4a6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1339,8 +1339,9 @@ extern int __memory_failure(unsigned long pfn, int trapno, int flags); extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; -extern void shake_page(struct page *p); +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); #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ -- cgit v1.1 From 329962503692b42d8088f31584e42d52db179d52 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 15 Dec 2009 17:59:02 -0800 Subject: x86: Fix checking of SRAT when node 0 ram is not from 0 Found one system that boot from socket1 instead of socket0, SRAT get rejected... [ 0.000000] SRAT: Node 1 PXM 0 0-a0000 [ 0.000000] SRAT: Node 1 PXM 0 100000-80000000 [ 0.000000] SRAT: Node 1 PXM 0 100000000-2080000000 [ 0.000000] SRAT: Node 0 PXM 1 2080000000-4080000000 [ 0.000000] SRAT: Node 2 PXM 2 4080000000-6080000000 [ 0.000000] SRAT: Node 3 PXM 3 6080000000-8080000000 [ 0.000000] SRAT: Node 4 PXM 4 8080000000-a080000000 [ 0.000000] SRAT: Node 5 PXM 5 a080000000-c080000000 [ 0.000000] SRAT: Node 6 PXM 6 c080000000-e080000000 [ 0.000000] SRAT: Node 7 PXM 7 e080000000-10080000000 ... [ 0.000000] NUMA: Allocated memnodemap from 500000 - 701040 [ 0.000000] NUMA: Using 20 for the hash shift. [ 0.000000] Adding active range (0, 0x2080000, 0x4080000) 0 entries of 3200 used [ 0.000000] Adding active range (1, 0x0, 0x96) 1 entries of 3200 used [ 0.000000] Adding active range (1, 0x100, 0x7f750) 2 entries of 3200 used [ 0.000000] Adding active range (1, 0x100000, 0x2080000) 3 entries of 3200 used [ 0.000000] Adding active range (2, 0x4080000, 0x6080000) 4 entries of 3200 used [ 0.000000] Adding active range (3, 0x6080000, 0x8080000) 5 entries of 3200 used [ 0.000000] Adding active range (4, 0x8080000, 0xa080000) 6 entries of 3200 used [ 0.000000] Adding active range (5, 0xa080000, 0xc080000) 7 entries of 3200 used [ 0.000000] Adding active range (6, 0xc080000, 0xe080000) 8 entries of 3200 used [ 0.000000] Adding active range (7, 0xe080000, 0x10080000) 9 entries of 3200 used [ 0.000000] SRAT: PXMs only cover 917504MB of your 1048566MB e820 RAM. Not used. [ 0.000000] SRAT: SRAT not used. the early_node_map is not sorted because node0 with non zero start come first. so try to sort it right away after all regions are registered. also fixs refression by 8716273c (x86: Export srat physical topology) -v2: make it more solid to handle cross node case like node0 [0,4g), [8,12g) and node1 [4g, 8g), [12g, 16g) -v3: update comments. Reported-and-tested-by: Jens Axboe Signed-off-by: Yinghai Lu LKML-Reference: <4B2579D2.3010201@kernel.org> Signed-off-by: H. Peter Anvin --- 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 24c3956..20a2036 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1022,6 +1022,9 @@ extern void add_active_range(unsigned int nid, unsigned long start_pfn, extern void remove_active_range(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn); extern void remove_all_active_ranges(void); +void sort_node_map(void); +unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, + unsigned long end_pfn); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, -- cgit v1.1 From 7e6608724c640924aad1d556d17df33ebaa6124d Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 15 Jan 2010 17:01:39 -0800 Subject: nommu: fix shared mmap after truncate shrinkage problems Fix a problem in NOMMU mmap with ramfs whereby a shared mmap can happen over the end of a truncation. The problem is that ramfs_nommu_check_mappings() checks that the reduced file size against the VMA tree, but not the vm_region tree. The following sequence of events can cause the problem: fd = open("/tmp/x", O_RDWR|O_TRUNC|O_CREAT, 0600); ftruncate(fd, 32 * 1024); a = mmap(NULL, 32 * 1024, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); b = mmap(NULL, 16 * 1024, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); munmap(a, 32 * 1024); ftruncate(fd, 16 * 1024); c = mmap(NULL, 32 * 1024, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); Mapping 'a' creates a vm_region covering 32KB of the file. Mapping 'b' sees that the vm_region from 'a' is covering the region it wants and so shares it, pinning it in memory. Mapping 'a' then goes away and the file is truncated to the end of VMA 'b'. However, the region allocated by 'a' is still in effect, and has _not_ been reduced. Mapping 'c' is then created, and because there's a vm_region covering the desired region, get_unmapped_area() is _not_ called to repeat the check, and the mapping is granted, even though the pages from the latter half of the mapping have been discarded. However: d = mmap(NULL, 16 * 1024, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); Mapping 'd' should work, and should end up sharing the region allocated by 'a'. To deal with this, we shrink the vm_region struct during the truncation, lest do_mmap_pgoff() take it as licence to share the full region automatically without calling the get_unmapped_area() file op again. Signed-off-by: David Howells Acked-by: Al Viro Cc: Greg Ungerer 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 2265f28..60c467b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1089,6 +1089,7 @@ extern void zone_pcp_update(struct zone *zone); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; +extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); /* prio_tree.c */ void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old); -- cgit v1.1