From e286781d5f2e9c846e012a39653a166e9d31777d Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:30 -0700 Subject: mm: speculative page references If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin Cc: Jeff Garzik Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Hugh Dickins Cc: "Paul E. McKenney" Reviewed-by: Peter Zijlstra Signed-off-by: Daisuke Nishimura Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: KOSAKI Motohiro Signed-off-by: Hugh Dickins Acked-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 2d3ec1ffc66e..4e182a9a14c0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -442,39 +442,43 @@ int filemap_write_and_wait_range(struct address_space *mapping, } /** - * add_to_page_cache - add newly allocated pagecache pages + * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add * @mapping: the page's address_space * @offset: page index * @gfp_mask: page allocation mode * - * This function is used to add newly allocated pagecache pages; - * the page is new, so we can just run SetPageLocked() against it. - * The other page state flags were set by rmqueue(). - * + * This function is used to add a page to the pagecache. It must be locked. * This function does not add the page to the LRU. The caller must do that. */ -int add_to_page_cache(struct page *page, struct address_space *mapping, +int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { - int error = mem_cgroup_cache_charge(page, current->mm, + int error; + + VM_BUG_ON(!PageLocked(page)); + + error = mem_cgroup_cache_charge(page, current->mm, gfp_mask & ~__GFP_HIGHMEM); if (error) goto out; error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM); if (error == 0) { + page_cache_get(page); + page->mapping = mapping; + page->index = offset; + write_lock_irq(&mapping->tree_lock); error = radix_tree_insert(&mapping->page_tree, offset, page); - if (!error) { - page_cache_get(page); - SetPageLocked(page); - page->mapping = mapping; - page->index = offset; + if (likely(!error)) { mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); - } else + } else { + page->mapping = NULL; mem_cgroup_uncharge_cache_page(page); + page_cache_release(page); + } write_unlock_irq(&mapping->tree_lock); radix_tree_preload_end(); @@ -483,7 +487,7 @@ int add_to_page_cache(struct page *page, struct address_space *mapping, out: return error; } -EXPORT_SYMBOL(add_to_page_cache); +EXPORT_SYMBOL(add_to_page_cache_locked); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) -- cgit v1.2.3 From a60637c85893e7191faaafa6a72e197c24386727 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:31 -0700 Subject: mm: lockless pagecache Combine page_cache_get_speculative with lockless radix tree lookups to introduce lockless page cache lookups (ie. no mapping->tree_lock on the read-side). The only atomicity changes this introduces is that the gang pagecache lookup functions now behave as if they are implemented with multiple find_get_page calls, rather than operating on a snapshot of the pages. In practice, this atomicity guarantee is not used anyway, and it is to replace individual lookups, so these semantics are natural. Signed-off-by: Nick Piggin Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Hugh Dickins Cc: "Paul E. McKenney" Reviewed-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 179 ++++++++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 134 insertions(+), 45 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 4e182a9a14c0..feb8448d8618 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -637,15 +637,35 @@ void __lock_page_nosync(struct page *page) * Is there a pagecache struct page at the given (mapping, offset) tuple? * If yes, increment its refcount and return it; if no, return NULL. */ -struct page * find_get_page(struct address_space *mapping, pgoff_t offset) +struct page *find_get_page(struct address_space *mapping, pgoff_t offset) { + void **pagep; struct page *page; - read_lock_irq(&mapping->tree_lock); - page = radix_tree_lookup(&mapping->page_tree, offset); - if (page) - page_cache_get(page); - read_unlock_irq(&mapping->tree_lock); + rcu_read_lock(); +repeat: + page = NULL; + pagep = radix_tree_lookup_slot(&mapping->page_tree, offset); + if (pagep) { + page = radix_tree_deref_slot(pagep); + if (unlikely(!page || page == RADIX_TREE_RETRY)) + goto repeat; + + if (!page_cache_get_speculative(page)) + goto repeat; + + /* + * Has the page moved? + * This is part of the lockless pagecache protocol. See + * include/linux/pagemap.h for details. + */ + if (unlikely(page != *pagep)) { + page_cache_release(page); + goto repeat; + } + } + rcu_read_unlock(); + return page; } EXPORT_SYMBOL(find_get_page); @@ -660,32 +680,22 @@ EXPORT_SYMBOL(find_get_page); * * Returns zero if the page was not present. find_lock_page() may sleep. */ -struct page *find_lock_page(struct address_space *mapping, - pgoff_t offset) +struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) { struct page *page; repeat: - read_lock_irq(&mapping->tree_lock); - page = radix_tree_lookup(&mapping->page_tree, offset); + page = find_get_page(mapping, offset); if (page) { - page_cache_get(page); - if (TestSetPageLocked(page)) { - read_unlock_irq(&mapping->tree_lock); - __lock_page(page); - - /* Has the page been truncated while we slept? */ - if (unlikely(page->mapping != mapping)) { - unlock_page(page); - page_cache_release(page); - goto repeat; - } - VM_BUG_ON(page->index != offset); - goto out; + lock_page(page); + /* Has the page been truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + page_cache_release(page); + goto repeat; } + VM_BUG_ON(page->index != offset); } - read_unlock_irq(&mapping->tree_lock); -out: return page; } EXPORT_SYMBOL(find_lock_page); @@ -751,13 +761,39 @@ unsigned find_get_pages(struct address_space *mapping, pgoff_t start, { unsigned int i; unsigned int ret; + unsigned int nr_found; + + rcu_read_lock(); +restart: + nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, + (void ***)pages, start, nr_pages); + ret = 0; + for (i = 0; i < nr_found; i++) { + struct page *page; +repeat: + page = radix_tree_deref_slot((void **)pages[i]); + if (unlikely(!page)) + continue; + /* + * this can only trigger if nr_found == 1, making livelock + * a non issue. + */ + if (unlikely(page == RADIX_TREE_RETRY)) + goto restart; + + if (!page_cache_get_speculative(page)) + goto repeat; - read_lock_irq(&mapping->tree_lock); - ret = radix_tree_gang_lookup(&mapping->page_tree, - (void **)pages, start, nr_pages); - for (i = 0; i < ret; i++) - page_cache_get(pages[i]); - read_unlock_irq(&mapping->tree_lock); + /* Has the page moved? */ + if (unlikely(page != *((void **)pages[i]))) { + page_cache_release(page); + goto repeat; + } + + pages[ret] = page; + ret++; + } + rcu_read_unlock(); return ret; } @@ -778,19 +814,44 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, { unsigned int i; unsigned int ret; + unsigned int nr_found; + + rcu_read_lock(); +restart: + nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, + (void ***)pages, index, nr_pages); + ret = 0; + for (i = 0; i < nr_found; i++) { + struct page *page; +repeat: + page = radix_tree_deref_slot((void **)pages[i]); + if (unlikely(!page)) + continue; + /* + * this can only trigger if nr_found == 1, making livelock + * a non issue. + */ + if (unlikely(page == RADIX_TREE_RETRY)) + goto restart; - read_lock_irq(&mapping->tree_lock); - ret = radix_tree_gang_lookup(&mapping->page_tree, - (void **)pages, index, nr_pages); - for (i = 0; i < ret; i++) { - if (pages[i]->mapping == NULL || pages[i]->index != index) + if (page->mapping == NULL || page->index != index) break; - page_cache_get(pages[i]); + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *((void **)pages[i]))) { + page_cache_release(page); + goto repeat; + } + + pages[ret] = page; + ret++; index++; } - read_unlock_irq(&mapping->tree_lock); - return i; + rcu_read_unlock(); + return ret; } EXPORT_SYMBOL(find_get_pages_contig); @@ -810,15 +871,43 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, { unsigned int i; unsigned int ret; + unsigned int nr_found; + + rcu_read_lock(); +restart: + nr_found = radix_tree_gang_lookup_tag_slot(&mapping->page_tree, + (void ***)pages, *index, nr_pages, tag); + ret = 0; + for (i = 0; i < nr_found; i++) { + struct page *page; +repeat: + page = radix_tree_deref_slot((void **)pages[i]); + if (unlikely(!page)) + continue; + /* + * this can only trigger if nr_found == 1, making livelock + * a non issue. + */ + if (unlikely(page == RADIX_TREE_RETRY)) + goto restart; + + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *((void **)pages[i]))) { + page_cache_release(page); + goto repeat; + } + + pages[ret] = page; + ret++; + } + rcu_read_unlock(); - read_lock_irq(&mapping->tree_lock); - ret = radix_tree_gang_lookup_tag(&mapping->page_tree, - (void **)pages, *index, nr_pages, tag); - for (i = 0; i < ret; i++) - page_cache_get(pages[i]); if (ret) *index = pages[ret - 1]->index + 1; - read_unlock_irq(&mapping->tree_lock); + return ret; } EXPORT_SYMBOL(find_get_pages_tag); -- cgit v1.2.3 From 19fd6231279be3c3bdd02ed99f9b0eb195978064 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:32 -0700 Subject: mm: spinlock tree_lock mapping->tree_lock has no read lockers. convert the lock from an rwlock to a spinlock. Signed-off-by: Nick Piggin Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Hugh Dickins Cc: "Paul E. McKenney" Reviewed-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 4 ++-- fs/inode.c | 2 +- include/asm-arm/cacheflush.h | 4 ++-- include/asm-parisc/cacheflush.h | 4 ++-- include/linux/fs.h | 2 +- mm/filemap.c | 10 +++++----- mm/migrate.c | 11 +++++------ mm/page-writeback.c | 12 ++++++------ mm/swap_state.c | 10 +++++----- mm/swapfile.c | 4 ++-- mm/truncate.c | 6 +++--- mm/vmscan.c | 8 ++++---- 12 files changed, 38 insertions(+), 39 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/buffer.c b/fs/buffer.c index d48caee12e2a..109b261192d9 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -706,7 +706,7 @@ static int __set_page_dirty(struct page *page, if (TestSetPageDirty(page)) return 0; - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); if (page->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !PageUptodate(page)); @@ -719,7 +719,7 @@ static int __set_page_dirty(struct page *page, radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return 1; diff --git a/fs/inode.c b/fs/inode.c index c36d9480335c..35b6414522ea 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -209,7 +209,7 @@ void inode_init_once(struct inode *inode) INIT_LIST_HEAD(&inode->i_dentry); INIT_LIST_HEAD(&inode->i_devices); INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC); - rwlock_init(&inode->i_data.tree_lock); + spin_lock_init(&inode->i_data.tree_lock); spin_lock_init(&inode->i_data.i_mmap_lock); INIT_LIST_HEAD(&inode->i_data.private_list); spin_lock_init(&inode->i_data.private_lock); diff --git a/include/asm-arm/cacheflush.h b/include/asm-arm/cacheflush.h index 70b0fe724b62..03cf1ee977b7 100644 --- a/include/asm-arm/cacheflush.h +++ b/include/asm-arm/cacheflush.h @@ -424,9 +424,9 @@ static inline void flush_anon_page(struct vm_area_struct *vma, } #define flush_dcache_mmap_lock(mapping) \ - write_lock_irq(&(mapping)->tree_lock) + spin_lock_irq(&(mapping)->tree_lock) #define flush_dcache_mmap_unlock(mapping) \ - write_unlock_irq(&(mapping)->tree_lock) + spin_unlock_irq(&(mapping)->tree_lock) #define flush_icache_user_range(vma,page,addr,len) \ flush_dcache_page(page) diff --git a/include/asm-parisc/cacheflush.h b/include/asm-parisc/cacheflush.h index 2f1e1b05440a..b7ca6dc7fddc 100644 --- a/include/asm-parisc/cacheflush.h +++ b/include/asm-parisc/cacheflush.h @@ -45,9 +45,9 @@ void flush_cache_mm(struct mm_struct *mm); extern void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) \ - write_lock_irq(&(mapping)->tree_lock) + spin_lock_irq(&(mapping)->tree_lock) #define flush_dcache_mmap_unlock(mapping) \ - write_unlock_irq(&(mapping)->tree_lock) + spin_unlock_irq(&(mapping)->tree_lock) #define flush_icache_page(vma,page) do { \ flush_kernel_dcache_page(page); \ diff --git a/include/linux/fs.h b/include/linux/fs.h index 49d8eb7a71be..53d2edb709b3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -499,7 +499,7 @@ struct backing_dev_info; struct address_space { struct inode *host; /* owner: inode, block_device */ struct radix_tree_root page_tree; /* radix tree of all pages */ - rwlock_t tree_lock; /* and rwlock protecting it */ + spinlock_t tree_lock; /* and lock protecting it */ unsigned int i_mmap_writable;/* count VM_SHARED mappings */ struct prio_tree_root i_mmap; /* tree of private and shared mappings */ struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ diff --git a/mm/filemap.c b/mm/filemap.c index feb8448d8618..2ed8b0389c51 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -109,7 +109,7 @@ /* * Remove a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage - * is safe. The caller must hold a write_lock on the mapping's tree_lock. + * is safe. The caller must hold the mapping's tree_lock. */ void __remove_from_page_cache(struct page *page) { @@ -141,9 +141,9 @@ void remove_from_page_cache(struct page *page) BUG_ON(!PageLocked(page)); - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); __remove_from_page_cache(page); - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); } static int sync_page(void *word) @@ -469,7 +469,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, page->mapping = mapping; page->index = offset; - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); error = radix_tree_insert(&mapping->page_tree, offset, page); if (likely(!error)) { mapping->nrpages++; @@ -480,7 +480,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, page_cache_release(page); } - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); radix_tree_preload_end(); } else mem_cgroup_uncharge_cache_page(page); diff --git a/mm/migrate.c b/mm/migrate.c index 3ca6392e82cc..153572fb60b8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -323,7 +323,7 @@ static int migrate_page_move_mapping(struct address_space *mapping, return 0; } - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); pslot = radix_tree_lookup_slot(&mapping->page_tree, page_index(page)); @@ -331,12 +331,12 @@ static int migrate_page_move_mapping(struct address_space *mapping, expected_count = 2 + !!PagePrivate(page); if (page_count(page) != expected_count || (struct page *)radix_tree_deref_slot(pslot) != page) { - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } if (!page_freeze_refs(page, expected_count)) { - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } @@ -373,10 +373,9 @@ static int migrate_page_move_mapping(struct address_space *mapping, __dec_zone_page_state(page, NR_FILE_PAGES); __inc_zone_page_state(newpage, NR_FILE_PAGES); - write_unlock_irq(&mapping->tree_lock); - if (!PageSwapCache(newpage)) { + spin_unlock_irq(&mapping->tree_lock); + if (!PageSwapCache(newpage)) mem_cgroup_uncharge_cache_page(page); - } return 0; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 94c6d8988ab3..24de8b65fdbd 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1088,7 +1088,7 @@ int __set_page_dirty_nobuffers(struct page *page) if (!mapping) return 1; - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); mapping2 = page_mapping(page); if (mapping2) { /* Race with truncate? */ BUG_ON(mapping2 != mapping); @@ -1102,7 +1102,7 @@ int __set_page_dirty_nobuffers(struct page *page) radix_tree_tag_set(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); } - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); @@ -1258,7 +1258,7 @@ int test_clear_page_writeback(struct page *page) struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; - write_lock_irqsave(&mapping->tree_lock, flags); + spin_lock_irqsave(&mapping->tree_lock, flags); ret = TestClearPageWriteback(page); if (ret) { radix_tree_tag_clear(&mapping->page_tree, @@ -1269,7 +1269,7 @@ int test_clear_page_writeback(struct page *page) __bdi_writeout_inc(bdi); } } - write_unlock_irqrestore(&mapping->tree_lock, flags); + spin_unlock_irqrestore(&mapping->tree_lock, flags); } else { ret = TestClearPageWriteback(page); } @@ -1287,7 +1287,7 @@ int test_set_page_writeback(struct page *page) struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; - write_lock_irqsave(&mapping->tree_lock, flags); + spin_lock_irqsave(&mapping->tree_lock, flags); ret = TestSetPageWriteback(page); if (!ret) { radix_tree_tag_set(&mapping->page_tree, @@ -1300,7 +1300,7 @@ int test_set_page_writeback(struct page *page) radix_tree_tag_clear(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); - write_unlock_irqrestore(&mapping->tree_lock, flags); + spin_unlock_irqrestore(&mapping->tree_lock, flags); } else { ret = TestSetPageWriteback(page); } diff --git a/mm/swap_state.c b/mm/swap_state.c index 3e3381d6c7ee..2c217e33d497 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -39,7 +39,7 @@ static struct backing_dev_info swap_backing_dev_info = { struct address_space swapper_space = { .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), - .tree_lock = __RW_LOCK_UNLOCKED(swapper_space.tree_lock), + .tree_lock = __SPIN_LOCK_UNLOCKED(swapper_space.tree_lock), .a_ops = &swap_aops, .i_mmap_nonlinear = LIST_HEAD_INIT(swapper_space.i_mmap_nonlinear), .backing_dev_info = &swap_backing_dev_info, @@ -80,7 +80,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask) SetPageSwapCache(page); set_page_private(page, entry.val); - write_lock_irq(&swapper_space.tree_lock); + spin_lock_irq(&swapper_space.tree_lock); error = radix_tree_insert(&swapper_space.page_tree, entry.val, page); if (likely(!error)) { @@ -88,7 +88,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask) __inc_zone_page_state(page, NR_FILE_PAGES); INC_CACHE_INFO(add_total); } - write_unlock_irq(&swapper_space.tree_lock); + spin_unlock_irq(&swapper_space.tree_lock); radix_tree_preload_end(); if (unlikely(error)) { @@ -182,9 +182,9 @@ void delete_from_swap_cache(struct page *page) entry.val = page_private(page); - write_lock_irq(&swapper_space.tree_lock); + spin_lock_irq(&swapper_space.tree_lock); __delete_from_swap_cache(page); - write_unlock_irq(&swapper_space.tree_lock); + spin_unlock_irq(&swapper_space.tree_lock); swap_free(entry); page_cache_release(page); diff --git a/mm/swapfile.c b/mm/swapfile.c index 2f33edb8bee9..af283933c14e 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -369,13 +369,13 @@ int remove_exclusive_swap_page(struct page *page) retval = 0; if (p->swap_map[swp_offset(entry)] == 1) { /* Recheck the page count with the swapcache lock held.. */ - write_lock_irq(&swapper_space.tree_lock); + spin_lock_irq(&swapper_space.tree_lock); if ((page_count(page) == 2) && !PageWriteback(page)) { __delete_from_swap_cache(page); SetPageDirty(page); retval = 1; } - write_unlock_irq(&swapper_space.tree_lock); + spin_unlock_irq(&swapper_space.tree_lock); } spin_unlock(&swap_lock); diff --git a/mm/truncate.c b/mm/truncate.c index b8961cb63414..e68443d74567 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -349,18 +349,18 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); if (PageDirty(page)) goto failed; BUG_ON(PagePrivate(page)); __remove_from_page_cache(page); - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); ClearPageUptodate(page); page_cache_release(page); /* pagecache ref */ return 1; failed: - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); return 0; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 0075eac1cd04..8f71761bc4b7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -399,7 +399,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); /* * The non racy check for a busy page. * @@ -436,17 +436,17 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) if (PageSwapCache(page)) { swp_entry_t swap = { .val = page_private(page) }; __delete_from_swap_cache(page); - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); swap_free(swap); } else { __remove_from_page_cache(page); - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); } return 1; cannot_free: - write_unlock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); return 0; } -- cgit v1.2.3 From 2f1936b87783a3a56c9441b27b9ba7a747f11e8e Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 24 Jun 2008 16:50:14 +0200 Subject: [patch 3/5] vfs: change remove_suid() to file_remove_suid() All calls to remove_suid() are made with a file pointer, because (similarly to file_update_time) it is called when the file is written. Clean up callers by passing in a file instead of a dentry. Signed-off-by: Miklos Szeredi --- fs/fuse/file.c | 2 +- fs/ntfs/file.c | 2 +- fs/splice.c | 4 ++-- fs/xfs/linux-2.6/xfs_lrw.c | 2 +- include/linux/fs.h | 2 +- mm/filemap.c | 7 ++++--- mm/filemap_xip.c | 2 +- 7 files changed, 11 insertions(+), 10 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 67ff2c6a8f63..2bada6bbc317 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -893,7 +893,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; - err = remove_suid(file->f_path.dentry); + err = file_remove_suid(file); if (err) goto out; diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 3c5550cd11d6..d020866d4232 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2118,7 +2118,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb, goto out; if (!count) goto out; - err = remove_suid(file->f_path.dentry); + err = file_remove_suid(file); if (err) goto out; file_update_time(file); diff --git a/fs/splice.c b/fs/splice.c index 47dc1a445d1f..b30311ba8af6 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -772,7 +772,7 @@ generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out, ssize_t ret; int err; - err = remove_suid(out->f_path.dentry); + err = file_remove_suid(out); if (unlikely(err)) return err; @@ -830,7 +830,7 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, ssize_t ret; inode_double_lock(inode, pipe->inode); - ret = remove_suid(out->f_path.dentry); + ret = file_remove_suid(out); if (likely(!ret)) ret = __splice_from_pipe(pipe, &sd, pipe_to_file); inode_double_unlock(inode, pipe->inode); diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c index 5e3b57516ec7..82333b3e118e 100644 --- a/fs/xfs/linux-2.6/xfs_lrw.c +++ b/fs/xfs/linux-2.6/xfs_lrw.c @@ -711,7 +711,7 @@ start: !capable(CAP_FSETID)) { error = xfs_write_clear_setuid(xip); if (likely(!error)) - error = -remove_suid(file->f_path.dentry); + error = -file_remove_suid(file); if (unlikely(error)) { goto out_unlock_internal; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c923c9b79bc..1a3546e69f9e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1834,7 +1834,7 @@ extern void clear_inode(struct inode *); extern void destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); extern int should_remove_suid(struct dentry *); -extern int remove_suid(struct dentry *); +extern int file_remove_suid(struct file *); extern void __insert_inode_hash(struct inode *, unsigned long hashval); extern void remove_inode_hash(struct inode *); diff --git a/mm/filemap.c b/mm/filemap.c index 2ed8b0389c51..5de7633e1dbe 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1758,8 +1758,9 @@ static int __remove_suid(struct dentry *dentry, int kill) return notify_change(dentry, &newattrs); } -int remove_suid(struct dentry *dentry) +int file_remove_suid(struct file *file) { + struct dentry *dentry = file->f_path.dentry; int killsuid = should_remove_suid(dentry); int killpriv = security_inode_need_killpriv(dentry); int error = 0; @@ -1773,7 +1774,7 @@ int remove_suid(struct dentry *dentry) return error; } -EXPORT_SYMBOL(remove_suid); +EXPORT_SYMBOL(file_remove_suid); static size_t __iovec_copy_from_user_inatomic(char *vaddr, const struct iovec *iov, size_t base, size_t bytes) @@ -2529,7 +2530,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; - err = remove_suid(file->f_path.dentry); + err = file_remove_suid(file); if (err) goto out; diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 3e744abcce9d..98a3f31ccd6a 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -380,7 +380,7 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len, if (count == 0) goto out_backing; - ret = remove_suid(filp->f_path.dentry); + ret = file_remove_suid(filp); if (ret) goto out_backing; -- cgit v1.2.3 From 8ab22b9abb5c55413802e4adc9aa6223324547c3 Mon Sep 17 00:00:00 2001 From: Hisashi Hifumi Date: Mon, 28 Jul 2008 15:46:36 -0700 Subject: vfs: pagecache usage optimization for pagesize!=blocksize When we read some part of a file through pagecache, if there is a pagecache of corresponding index but this page is not uptodate, read IO is issued and this page will be uptodate. I think this is good for pagesize == blocksize environment but there is room for improvement on pagesize != blocksize environment. Because in this case a page can have multiple buffers and even if a page is not uptodate, some buffers can be uptodate. So I suggest that when all buffers which correspond to a part of a file that we want to read are uptodate, use this pagecache and copy data from this pagecache to user buffer even if a page is not uptodate. This can reduce read IO and improve system throughput. I wrote a benchmark program and got result number with this program. This benchmark do: 1: mount and open a test file. 2: create a 512MB file. 3: close a file and umount. 4: mount and again open a test file. 5: pwrite randomly 300000 times on a test file. offset is aligned by IO size(1024bytes). 6: measure time of preading randomly 100000 times on a test file. The result was: 2.6.26 330 sec 2.6.26-patched 226 sec Arch:i386 Filesystem:ext3 Blocksize:1024 bytes Memory: 1GB On ext3/4, a file is written through buffer/block. So random read/write mixed workloads or random read after random write workloads are optimized with this patch under pagesize != blocksize environment. This test result showed this. The benchmark program is as follows: #include #include #include #include #include #include #include #include #include #define LEN 1024 #define LOOP 1024*512 /* 512MB */ main(void) { unsigned long i, offset, filesize; int fd; char buf[LEN]; time_t t1, t2; if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } memset(buf, 0, LEN); fd = open("/root/test1/testfile", O_CREAT|O_RDWR|O_TRUNC); if (fd < 0) { perror("cannot open file\n"); exit(1); } for (i = 0; i < LOOP; i++) write(fd, buf, LEN); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } fd = open("/root/test1/testfile", O_RDWR); if (fd < 0) { perror("cannot open file\n"); exit(1); } filesize = LEN * LOOP; for (i = 0; i < 300000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pwrite(fd, buf, LEN, offset); } printf("start test\n"); time(&t1); for (i = 0; i < 100000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pread(fd, buf, LEN, offset); } time(&t2); printf("%ld sec\n", t2-t1); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } } Signed-off-by: Hisashi Hifumi Cc: Nick Piggin Cc: Christoph Hellwig Cc: Jan Kara Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 46 +++++++++++++++++++++++ fs/ext2/inode.c | 1 + fs/ext3/inode.c | 67 +++++++++++++++++---------------- fs/ext4/inode.c | 92 +++++++++++++++++++++++---------------------- include/linux/buffer_head.h | 2 + include/linux/fs.h | 44 +++++++++++----------- mm/filemap.c | 14 ++++++- 7 files changed, 167 insertions(+), 99 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/buffer.c b/fs/buffer.c index f95805019639..ca12a6bb82b1 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2095,6 +2095,52 @@ int generic_write_end(struct file *file, struct address_space *mapping, } EXPORT_SYMBOL(generic_write_end); +/* + * block_is_partially_uptodate checks whether buffers within a page are + * uptodate or not. + * + * Returns true if all buffers which correspond to a file portion + * we want to read are uptodate. + */ +int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, + unsigned long from) +{ + struct inode *inode = page->mapping->host; + unsigned block_start, block_end, blocksize; + unsigned to; + struct buffer_head *bh, *head; + int ret = 1; + + if (!page_has_buffers(page)) + return 0; + + blocksize = 1 << inode->i_blkbits; + to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count); + to = from + to; + if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize) + return 0; + + head = page_buffers(page); + bh = head; + block_start = 0; + do { + block_end = block_start + blocksize; + if (block_end > from && block_start < to) { + if (!buffer_uptodate(bh)) { + ret = 0; + break; + } + if (block_end >= to) + break; + } + block_start = block_end; + bh = bh->b_this_page; + } while (bh != head); + + return ret; +} +EXPORT_SYMBOL(block_is_partially_uptodate); + /* * Generic "read page" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 384fc0d1dd74..991d6dfeb51f 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -791,6 +791,7 @@ const struct address_space_operations ext2_aops = { .direct_IO = ext2_direct_IO, .writepages = ext2_writepages, .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; const struct address_space_operations ext2_aops_xip = { diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 3bf07d70b914..507d8689b111 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1767,44 +1767,47 @@ static int ext3_journalled_set_page_dirty(struct page *page) } static const struct address_space_operations ext3_ordered_aops = { - .readpage = ext3_readpage, - .readpages = ext3_readpages, - .writepage = ext3_ordered_writepage, - .sync_page = block_sync_page, - .write_begin = ext3_write_begin, - .write_end = ext3_ordered_write_end, - .bmap = ext3_bmap, - .invalidatepage = ext3_invalidatepage, - .releasepage = ext3_releasepage, - .direct_IO = ext3_direct_IO, - .migratepage = buffer_migrate_page, + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_ordered_writepage, + .sync_page = block_sync_page, + .write_begin = ext3_write_begin, + .write_end = ext3_ordered_write_end, + .bmap = ext3_bmap, + .invalidatepage = ext3_invalidatepage, + .releasepage = ext3_releasepage, + .direct_IO = ext3_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations ext3_writeback_aops = { - .readpage = ext3_readpage, - .readpages = ext3_readpages, - .writepage = ext3_writeback_writepage, - .sync_page = block_sync_page, - .write_begin = ext3_write_begin, - .write_end = ext3_writeback_write_end, - .bmap = ext3_bmap, - .invalidatepage = ext3_invalidatepage, - .releasepage = ext3_releasepage, - .direct_IO = ext3_direct_IO, - .migratepage = buffer_migrate_page, + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_writeback_writepage, + .sync_page = block_sync_page, + .write_begin = ext3_write_begin, + .write_end = ext3_writeback_write_end, + .bmap = ext3_bmap, + .invalidatepage = ext3_invalidatepage, + .releasepage = ext3_releasepage, + .direct_IO = ext3_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations ext3_journalled_aops = { - .readpage = ext3_readpage, - .readpages = ext3_readpages, - .writepage = ext3_journalled_writepage, - .sync_page = block_sync_page, - .write_begin = ext3_write_begin, - .write_end = ext3_journalled_write_end, - .set_page_dirty = ext3_journalled_set_page_dirty, - .bmap = ext3_bmap, - .invalidatepage = ext3_invalidatepage, - .releasepage = ext3_releasepage, + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_journalled_writepage, + .sync_page = block_sync_page, + .write_begin = ext3_write_begin, + .write_end = ext3_journalled_write_end, + .set_page_dirty = ext3_journalled_set_page_dirty, + .bmap = ext3_bmap, + .invalidatepage = ext3_invalidatepage, + .releasepage = ext3_releasepage, + .is_partially_uptodate = block_is_partially_uptodate, }; void ext3_set_aops(struct inode *inode) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8ca2763df091..9843b046c235 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2806,59 +2806,63 @@ static int ext4_journalled_set_page_dirty(struct page *page) } static const struct address_space_operations ext4_ordered_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_normal_writepage, - .sync_page = block_sync_page, - .write_begin = ext4_write_begin, - .write_end = ext4_ordered_write_end, - .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, - .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, - .migratepage = buffer_migrate_page, + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_normal_writepage, + .sync_page = block_sync_page, + .write_begin = ext4_write_begin, + .write_end = ext4_ordered_write_end, + .bmap = ext4_bmap, + .invalidatepage = ext4_invalidatepage, + .releasepage = ext4_releasepage, + .direct_IO = ext4_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations ext4_writeback_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_normal_writepage, - .sync_page = block_sync_page, - .write_begin = ext4_write_begin, - .write_end = ext4_writeback_write_end, - .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, - .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, - .migratepage = buffer_migrate_page, + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_normal_writepage, + .sync_page = block_sync_page, + .write_begin = ext4_write_begin, + .write_end = ext4_writeback_write_end, + .bmap = ext4_bmap, + .invalidatepage = ext4_invalidatepage, + .releasepage = ext4_releasepage, + .direct_IO = ext4_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations ext4_journalled_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_journalled_writepage, - .sync_page = block_sync_page, - .write_begin = ext4_write_begin, - .write_end = ext4_journalled_write_end, - .set_page_dirty = ext4_journalled_set_page_dirty, - .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, - .releasepage = ext4_releasepage, + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_journalled_writepage, + .sync_page = block_sync_page, + .write_begin = ext4_write_begin, + .write_end = ext4_journalled_write_end, + .set_page_dirty = ext4_journalled_set_page_dirty, + .bmap = ext4_bmap, + .invalidatepage = ext4_invalidatepage, + .releasepage = ext4_releasepage, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations ext4_da_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_da_writepage, - .writepages = ext4_da_writepages, - .sync_page = block_sync_page, - .write_begin = ext4_da_write_begin, - .write_end = ext4_da_write_end, - .bmap = ext4_bmap, - .invalidatepage = ext4_da_invalidatepage, - .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, - .migratepage = buffer_migrate_page, + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_da_writepage, + .writepages = ext4_da_writepages, + .sync_page = block_sync_page, + .write_begin = ext4_da_write_begin, + .write_end = ext4_da_write_end, + .bmap = ext4_bmap, + .invalidatepage = ext4_da_invalidatepage, + .releasepage = ext4_releasepage, + .direct_IO = ext4_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; void ext4_set_aops(struct inode *inode) diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 82aa36c53ea7..50cfe8ceb478 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -205,6 +205,8 @@ void block_invalidatepage(struct page *page, unsigned long offset); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int block_read_full_page(struct page*, get_block_t*); +int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, + unsigned long from); int block_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); diff --git a/include/linux/fs.h b/include/linux/fs.h index 8252b045e624..580b513668fe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -443,6 +443,27 @@ static inline size_t iov_iter_count(struct iov_iter *i) return i->count; } +/* + * "descriptor" for what we're up to with a read. + * This allows us to use the same read code yet + * have multiple different users of the data that + * we read from a file. + * + * The simplest case just copies the data to user + * mode. + */ +typedef struct { + size_t written; + size_t count; + union { + char __user *buf; + void *data; + } arg; + int error; +} read_descriptor_t; + +typedef int (*read_actor_t)(read_descriptor_t *, struct page *, + unsigned long, unsigned long); struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); @@ -484,6 +505,8 @@ struct address_space_operations { int (*migratepage) (struct address_space *, struct page *, struct page *); int (*launder_page) (struct page *); + int (*is_partially_uptodate) (struct page *, read_descriptor_t *, + unsigned long); }; /* @@ -1198,27 +1221,6 @@ struct block_device_operations { struct module *owner; }; -/* - * "descriptor" for what we're up to with a read. - * This allows us to use the same read code yet - * have multiple different users of the data that - * we read from a file. - * - * The simplest case just copies the data to user - * mode. - */ -typedef struct { - size_t written; - size_t count; - union { - char __user * buf; - void *data; - } arg; - int error; -} read_descriptor_t; - -typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long); - /* These macros are for out of kernel modules to test that * the kernel supports the unlocked_ioctl and compat_ioctl * fields in struct file_operations. */ diff --git a/mm/filemap.c b/mm/filemap.c index 5de7633e1dbe..42bbc6909ba4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1023,8 +1023,17 @@ find_page: ra, filp, page, index, last_index - index); } - if (!PageUptodate(page)) - goto page_not_up_to_date; + if (!PageUptodate(page)) { + if (inode->i_blkbits == PAGE_CACHE_SHIFT || + !mapping->a_ops->is_partially_uptodate) + goto page_not_up_to_date; + if (TestSetPageLocked(page)) + goto page_not_up_to_date; + if (!mapping->a_ops->is_partially_uptodate(page, + desc, offset)) + goto page_not_up_to_date_locked; + unlock_page(page); + } page_ok: /* * i_size must be checked after we know the page is Uptodate. @@ -1094,6 +1103,7 @@ page_not_up_to_date: if (lock_page_killable(page)) goto readpage_eio; +page_not_up_to_date_locked: /* Did it get truncated before we got the lock? */ if (!page->mapping) { unlock_page(page); -- cgit v1.2.3