From 7a3ef208e662f4b63d43a23f61a64a129c525bbc Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 8 Jan 2015 14:32:15 -0800 Subject: mm: prevent endless growth of anon_vma hierarchy Constantly forking task causes unlimited grow of anon_vma chain. Each next child allocates new level of anon_vmas and links vma to all previous levels because pages might be inherited from any level. This patch adds heuristic which decides to reuse existing anon_vma instead of forking new one. It adds counter anon_vma->degree which counts linked vmas and directly descending anon_vmas and reuses anon_vma if counter is lower than two. As a result each anon_vma has either vma or at least two descending anon_vmas. In such trees half of nodes are leafs with alive vmas, thus count of anon_vmas is no more than two times bigger than count of vmas. This heuristic reuses anon_vmas as few as possible because each reuse adds false aliasing among vmas and rmap walker ought to scan more ptes when it searches where page is might be mapped. Link: http://lkml.kernel.org/r/20120816024610.GA5350@evergreen.ssec.wisc.edu Fixes: 5beb49305251 ("mm: change anon_vma linking to fix multi-process server scalability issue") [akpm@linux-foundation.org: fix typo, per Rik] Signed-off-by: Konstantin Khlebnikov Reported-by: Daniel Forrest Tested-by: Michal Hocko Tested-by: Jerome Marchand Reviewed-by: Michal Hocko Reviewed-by: Rik van Riel Cc: [2.6.34+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index c0c2bce6b0b..d9d7e7e5635 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -36,6 +36,16 @@ struct anon_vma { */ atomic_t refcount; + /* + * Count of child anon_vmas and VMAs which points to this anon_vma. + * + * This counter is used for making decision about reusing anon_vma + * instead of forking new one. See comments in function anon_vma_clone. + */ + unsigned degree; + + struct anon_vma *parent; /* Parent of this anon_vma */ + /* * NOTE: the LSB of the rb_root.rb_node is set by * mm_take_all_locks() _after_ taking the above lock. So the -- cgit v1.2.3-70-g09d2 From 2d6d7f98284648c5ed113fe22a132148950b140f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 8 Jan 2015 14:32:18 -0800 Subject: mm: protect set_page_dirty() from ongoing truncation Tejun, while reviewing the code, spotted the following race condition between the dirtying and truncation of a page: __set_page_dirty_nobuffers() __delete_from_page_cache() if (TestSetPageDirty(page)) page->mapping = NULL if (PageDirty()) dec_zone_page_state(page, NR_FILE_DIRTY); dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); if (page->mapping) account_page_dirtied(page) __inc_zone_page_state(page, NR_FILE_DIRTY); __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); which results in an imbalance of NR_FILE_DIRTY and BDI_RECLAIMABLE. Dirtiers usually lock out truncation, either by holding the page lock directly, or in case of zap_pte_range(), by pinning the mapcount with the page table lock held. The notable exception to this rule, though, is do_wp_page(), for which this race exists. However, do_wp_page() already waits for a locked page to unlock before setting the dirty bit, in order to prevent a race where clear_page_dirty() misses the page bit in the presence of dirty ptes. Upgrade that wait to a fully locked set_page_dirty() to also cover the situation explained above. Afterwards, the code in set_page_dirty() dealing with a truncation race is no longer needed. Remove it. Reported-by: Tejun Heo Signed-off-by: Johannes Weiner Acked-by: Kirill A. Shutemov Reviewed-by: Jan Kara Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/writeback.h | 1 - mm/memory.c | 27 +++++++++++++++++---------- mm/page-writeback.c | 43 ++++++++++++------------------------------- 3 files changed, 29 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index a219be961c0..00048339c23 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -177,7 +177,6 @@ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data); int do_writepages(struct address_space *mapping, struct writeback_control *wbc); -void set_page_dirty_balance(struct page *page); void writeback_set_ratelimit(void); void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end); diff --git a/mm/memory.c b/mm/memory.c index d7e497e98f4..c6565f00fb3 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2137,17 +2137,24 @@ reuse: if (!dirty_page) return ret; - /* - * Yes, Virginia, this is actually required to prevent a race - * with clear_page_dirty_for_io() from clearing the page dirty - * bit after it clear all dirty ptes, but before a racing - * do_wp_page installs a dirty pte. - * - * do_shared_fault is protected similarly. - */ if (!page_mkwrite) { - wait_on_page_locked(dirty_page); - set_page_dirty_balance(dirty_page); + struct address_space *mapping; + int dirtied; + + lock_page(dirty_page); + dirtied = set_page_dirty(dirty_page); + VM_BUG_ON_PAGE(PageAnon(dirty_page), dirty_page); + mapping = dirty_page->mapping; + unlock_page(dirty_page); + + if (dirtied && mapping) { + /* + * Some device drivers do not set page.mapping + * but still dirty their pages + */ + balance_dirty_pages_ratelimited(mapping); + } + /* file_update_time outside page_lock */ if (vma->vm_file) file_update_time(vma->vm_file); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d5d81f5384d..6f4335238e3 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1541,16 +1541,6 @@ pause: bdi_start_background_writeback(bdi); } -void set_page_dirty_balance(struct page *page) -{ - if (set_page_dirty(page)) { - struct address_space *mapping = page_mapping(page); - - if (mapping) - balance_dirty_pages_ratelimited(mapping); - } -} - static DEFINE_PER_CPU(int, bdp_ratelimits); /* @@ -2123,32 +2113,25 @@ EXPORT_SYMBOL(account_page_dirtied); * page dirty in that case, but not all the buffers. This is a "bottom-up" * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying. * - * Most callers have locked the page, which pins the address_space in memory. - * But zap_pte_range() does not lock the page, however in that case the - * mapping is pinned by the vma's ->vm_file reference. - * - * We take care to handle the case where the page was truncated from the - * mapping by re-checking page_mapping() inside tree_lock. + * The caller must ensure this doesn't race with truncation. Most will simply + * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and + * the pte lock held, which also locks out truncation. */ int __set_page_dirty_nobuffers(struct page *page) { if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); - struct address_space *mapping2; unsigned long flags; if (!mapping) return 1; spin_lock_irqsave(&mapping->tree_lock, flags); - mapping2 = page_mapping(page); - if (mapping2) { /* Race with truncate? */ - BUG_ON(mapping2 != mapping); - WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); - account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), PAGECACHE_TAG_DIRTY); - } + BUG_ON(page_mapping(page) != mapping); + WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); + account_page_dirtied(page, mapping); + radix_tree_tag_set(&mapping->page_tree, page_index(page), + PAGECACHE_TAG_DIRTY); spin_unlock_irqrestore(&mapping->tree_lock, flags); if (mapping->host) { /* !PageAnon && !swapper_space */ @@ -2305,12 +2288,10 @@ int clear_page_dirty_for_io(struct page *page) /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the page dirty - * at this point. We do this by having them hold the - * page lock at some point after installing their - * pte, but before marking the page dirty. - * Pages are always locked coming in here, so we get - * the desired exclusion. See mm/memory.c:do_wp_page() - * for more comments. + * at this point. We do this by having them hold the + * page lock while dirtying the page, and pages are + * always locked coming in here, so we get the desired + * exclusion. */ if (TestClearPageDirty(page)) { dec_zone_page_state(page, NR_FILE_DIRTY); -- cgit v1.2.3-70-g09d2 From 75069f2b5bfb5164beafaf3da597279c25b5535a Mon Sep 17 00:00:00 2001 From: David Drysdale Date: Thu, 8 Jan 2015 14:32:29 -0800 Subject: vfs: renumber FMODE_NONOTIFY and add to uniqueness check Fix clashing values for O_PATH and FMODE_NONOTIFY on sparc. The clashing O_PATH value was added in commit 5229645bdc35 ("vfs: add nonconflicting values for O_PATH") but this can't be changed as it is user-visible. FMODE_NONOTIFY is only used internally in the kernel, but it is in the same numbering space as the other O_* flags, as indicated by the comment at the top of include/uapi/asm-generic/fcntl.h (and its use in fs/notify/fanotify/fanotify_user.c). So renumber it to avoid the clash. All of this has happened before (commit 12ed2e36c98a: "fanotify: FMODE_NONOTIFY and __O_SYNC in sparc conflict"), and all of this will happen again -- so update the uniqueness check in fcntl_init() to include __FMODE_NONOTIFY. Signed-off-by: David Drysdale Acked-by: David S. Miller Acked-by: Jan Kara Cc: Heinrich Schuchardt Cc: Alexander Viro Cc: Arnd Bergmann Cc: Stephen Rothwell Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fcntl.c | 5 +++-- include/linux/fs.h | 2 +- include/uapi/asm-generic/fcntl.h | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/fs/fcntl.c b/fs/fcntl.c index 99d440a4a6b..ee85cd4e136 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -740,14 +740,15 @@ static int __init fcntl_init(void) * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ - BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( + BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | O_APPEND | /* O_NONBLOCK | */ __O_SYNC | O_DSYNC | FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | O_NOATIME | O_CLOEXEC | - __FMODE_EXEC | O_PATH | __O_TMPFILE + __FMODE_EXEC | O_PATH | __O_TMPFILE | + __FMODE_NONOTIFY )); fasync_cache = kmem_cache_create("fasync_cache", diff --git a/include/linux/fs.h b/include/linux/fs.h index f90c0282c11..42efe13077b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -135,7 +135,7 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_CAN_WRITE ((__force fmode_t)0x40000) /* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)0x1000000) +#define FMODE_NONOTIFY ((__force fmode_t)0x4000000) /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index 7543b3e5133..e063effe0cc 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -5,7 +5,7 @@ /* * FMODE_EXEC is 0x20 - * FMODE_NONOTIFY is 0x1000000 + * FMODE_NONOTIFY is 0x4000000 * These cannot be used by userspace O_* until internal and external open * flags are split. * -Eric Paris -- cgit v1.2.3-70-g09d2