From 3b5e6454aaf6b4439b19400d8365e2ec2d24e411 Mon Sep 17 00:00:00 2001 From: Gioh Kim Date: Thu, 4 Sep 2014 22:04:42 -0400 Subject: fs/buffer.c: support buffer cache allocations with gfp modifiers A buffer cache is allocated from movable area because it is referred for a while and released soon. But some filesystems are taking buffer cache for a long time and it can disturb page migration. New APIs are introduced to allocate buffer cache with user specific flag. *_gfp APIs are for user want to set page allocation flag for page cache allocation. And *_unmovable APIs are for the user wants to allocate page cache from non-movable area. Signed-off-by: Gioh Kim Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- include/linux/buffer_head.h | 47 ++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 42 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 324329ceea1e..73b45225a7ca 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -175,12 +175,13 @@ void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, unsigned size); -struct buffer_head *__getblk(struct block_device *bdev, sector_t block, - unsigned size); +struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp); void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); -struct buffer_head *__bread(struct block_device *, sector_t block, unsigned size); +struct buffer_head *__bread_gfp(struct block_device *, + sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); @@ -295,7 +296,13 @@ static inline void bforget(struct buffer_head *bh) static inline struct buffer_head * sb_bread(struct super_block *sb, sector_t block) { - return __bread(sb->s_bdev, block, sb->s_blocksize); + return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); +} + +static inline struct buffer_head * +sb_bread_unmovable(struct super_block *sb, sector_t block) +{ + return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, 0); } static inline void @@ -307,7 +314,7 @@ sb_breadahead(struct super_block *sb, sector_t block) static inline struct buffer_head * sb_getblk(struct super_block *sb, sector_t block) { - return __getblk(sb->s_bdev, block, sb->s_blocksize); + return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } static inline struct buffer_head * @@ -344,6 +351,36 @@ static inline void lock_buffer(struct buffer_head *bh) __lock_buffer(bh); } +static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, + sector_t block, + unsigned size) +{ + return __getblk_gfp(bdev, block, size, 0); +} + +static inline struct buffer_head *__getblk(struct block_device *bdev, + sector_t block, + unsigned size) +{ + return __getblk_gfp(bdev, block, size, __GFP_MOVABLE); +} + +/** + * __bread() - reads a specified block and returns the bh + * @bdev: the block_device to read from + * @block: number of block + * @size: size (in bytes) to read + * + * Reads a specified block, and returns buffer head that contains it. + * The page cache is allocated from movable area so that it can be migrated. + * It returns NULL if the block was unreadable. + */ +static inline struct buffer_head * +__bread(struct block_device *bdev, sector_t block, unsigned size) +{ + return __bread_gfp(bdev, block, size, __GFP_MOVABLE); +} + extern int __set_page_dirty_buffers(struct page *page); #else /* CONFIG_BLOCK */ -- cgit v1.2.3-70-g09d2 From 50849db32a9f529235a84bcc84a6b8e631b1d0ec Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 18 Sep 2014 00:58:12 -0400 Subject: jbd2: simplify calling convention around __jbd2_journal_clean_checkpoint_list __jbd2_journal_clean_checkpoint_list() returns number of buffers it freed but noone was using the value so just stop doing that. This also allows for simplifying the calling convention for journal_clean_once_cp_list(). Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/jbd2/checkpoint.c | 56 ++++++++++++++++++++++------------------------------ include/linux/jbd2.h | 2 +- 2 files changed, 25 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 3ab4c5ee12ce..988b32ed4c87 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -421,16 +421,15 @@ int jbd2_cleanup_journal_tail(journal_t *journal) * release them. * * Called with j_list_lock held. - * Returns number of buffers reaped (for debug) + * Returns 1 if we freed the transaction, 0 otherwise. */ - -static int journal_clean_one_cp_list(struct journal_head *jh, int *released) +static int journal_clean_one_cp_list(struct journal_head *jh) { struct journal_head *last_jh; struct journal_head *next_jh = jh; - int ret, freed = 0; + int ret; + int freed = 0; - *released = 0; if (!jh) return 0; @@ -441,11 +440,9 @@ static int journal_clean_one_cp_list(struct journal_head *jh, int *released) ret = __try_to_free_cp_buf(jh); if (!ret) return freed; - freed++; - if (ret == 2) { - *released = 1; - return freed; - } + if (ret == 2) + return 1; + freed = 1; /* * This function only frees up some memory * if possible so we dont have an obligation @@ -465,53 +462,48 @@ static int journal_clean_one_cp_list(struct journal_head *jh, int *released) * Find all the written-back checkpoint buffers in the journal and release them. * * Called with j_list_lock held. - * Returns number of buffers reaped (for debug) */ - -int __jbd2_journal_clean_checkpoint_list(journal_t *journal) +void __jbd2_journal_clean_checkpoint_list(journal_t *journal) { transaction_t *transaction, *last_transaction, *next_transaction; int ret; - int freed = 0; - int released; transaction = journal->j_checkpoint_transactions; if (!transaction) - goto out; + return; last_transaction = transaction->t_cpprev; next_transaction = transaction; do { transaction = next_transaction; next_transaction = transaction->t_cpnext; - ret = journal_clean_one_cp_list(transaction-> - t_checkpoint_list, &released); + ret = journal_clean_one_cp_list(transaction->t_checkpoint_list); /* * This function only frees up some memory if possible so we * dont have an obligation to finish processing. Bail out if * preemption requested: */ - if (need_resched()) { - freed += ret; - goto out; - } - if (released) { - freed += ret; + if (need_resched()) + return; + if (ret) continue; - } /* * It is essential that we are as careful as in the case of * t_checkpoint_list with removing the buffer from the list as * we can possibly see not yet submitted buffers on io_list */ - ret += journal_clean_one_cp_list(transaction-> - t_checkpoint_io_list, &released); - freed += ret; - if (need_resched() || !ret) - goto out; + ret = journal_clean_one_cp_list(transaction-> + t_checkpoint_io_list); + if (need_resched()) + return; + /* + * Stop scanning if we couldn't free the transaction. This + * avoids pointless scanning of transactions which still + * weren't checkpointed. + */ + if (!ret) + return; } while (transaction != last_transaction); -out: - return freed; } /* diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 0dae71e9971c..704b9a599b26 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1042,7 +1042,7 @@ void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ -int __jbd2_journal_clean_checkpoint_list(journal_t *journal); +void __jbd2_journal_clean_checkpoint_list(journal_t *journal); int __jbd2_journal_remove_checkpoint(struct journal_head *); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); -- cgit v1.2.3-70-g09d2 From 90a8020278c1598fafd071736a0846b38510309c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 1 Oct 2014 21:49:18 -0400 Subject: vfs: fix data corruption when blocksize < pagesize for mmaped data ->page_mkwrite() is used by filesystems to allocate blocks under a page which is becoming writeably mmapped in some process' address space. This allows a filesystem to return a page fault if there is not enough space available, user exceeds quota or similar problem happens, rather than silently discarding data later when writepage is called. However VFS fails to call ->page_mkwrite() in all the cases where filesystems need it when blocksize < pagesize. For example when blocksize = 1024, pagesize = 4096 the following is problematic: ftruncate(fd, 0); pwrite(fd, buf, 1024, 0); map = mmap(NULL, 1024, PROT_WRITE, MAP_SHARED, fd, 0); map[0] = 'a'; ----> page_mkwrite() for index 0 is called ftruncate(fd, 10000); /* or even pwrite(fd, buf, 1, 10000) */ mremap(map, 1024, 10000, 0); map[4095] = 'a'; ----> no page_mkwrite() called At the moment ->page_mkwrite() is called, filesystem can allocate only one block for the page because i_size == 1024. Otherwise it would create blocks beyond i_size which is generally undesirable. But later at ->writepage() time, we also need to store data at offset 4095 but we don't have block allocated for it. This patch introduces a helper function filesystems can use to have ->page_mkwrite() called at all the necessary moments. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o Cc: stable@vger.kernel.org --- fs/buffer.c | 3 +++ include/linux/mm.h | 1 + mm/truncate.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 61 insertions(+) (limited to 'include/linux') diff --git a/fs/buffer.c b/fs/buffer.c index 9a6029e0dd71..6dc1475dcb2d 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2087,6 +2087,7 @@ int generic_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; int i_size_changed = 0; copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); @@ -2106,6 +2107,8 @@ int generic_write_end(struct file *file, struct address_space *mapping, unlock_page(page); page_cache_release(page); + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock diff --git a/include/linux/mm.h b/include/linux/mm.h index 8981cc882ed2..5005464fe012 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1155,6 +1155,7 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); +void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); diff --git a/mm/truncate.c b/mm/truncate.c index 96d167372d89..261eaf6e5a19 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -20,6 +20,7 @@ #include /* grr. try_to_release_page, do_invalidatepage */ #include +#include #include "internal.h" static void clear_exceptional_entry(struct address_space *mapping, @@ -719,11 +720,67 @@ EXPORT_SYMBOL(truncate_pagecache); */ void truncate_setsize(struct inode *inode, loff_t newsize) { + loff_t oldsize = inode->i_size; + i_size_write(inode, newsize); + if (newsize > oldsize) + pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); +/** + * pagecache_isize_extended - update pagecache after extension of i_size + * @inode: inode for which i_size was extended + * @from: original inode size + * @to: new inode size + * + * Handle extension of inode size either caused by extending truncate or by + * write starting after current i_size. We mark the page straddling current + * i_size RO so that page_mkwrite() is called on the nearest write access to + * the page. This way filesystem can be sure that page_mkwrite() is called on + * the page before user writes to the page via mmap after the i_size has been + * changed. + * + * The function must be called after i_size is updated so that page fault + * coming after we unlock the page will already see the new i_size. + * The function must be called while we still hold i_mutex - this not only + * makes sure i_size is stable but also that userspace cannot observe new + * i_size value before we are prepared to store mmap writes at new inode size. + */ +void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) +{ + int bsize = 1 << inode->i_blkbits; + loff_t rounded_from; + struct page *page; + pgoff_t index; + + WARN_ON(!mutex_is_locked(&inode->i_mutex)); + WARN_ON(to > inode->i_size); + + if (from >= to || bsize == PAGE_CACHE_SIZE) + return; + /* Page straddling @from will not have any hole block created? */ + rounded_from = round_up(from, bsize); + if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1))) + return; + + index = from >> PAGE_CACHE_SHIFT; + page = find_lock_page(inode->i_mapping, index); + /* Page not cached? Nothing to do */ + if (!page) + return; + /* + * See clear_page_dirty_for_io() for details why set_page_dirty() + * is needed. + */ + if (page_mkclean(page)) + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); +} +EXPORT_SYMBOL(pagecache_isize_extended); + /** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode -- cgit v1.2.3-70-g09d2