diff options
Diffstat (limited to 'fs')
48 files changed, 410 insertions, 244 deletions
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index fb7ee026d101..adbb3a1edcbf 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -73,6 +73,7 @@ static sector_t _adfs_bmap(struct address_space *mapping, sector_t block) } static const struct address_space_operations adfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = adfs_readpage, .writepage = adfs_writepage, .write_begin = adfs_write_begin, diff --git a/fs/affs/file.c b/fs/affs/file.c index d91b0133d95d..75ebd2b576ca 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -453,6 +453,7 @@ static sector_t _affs_bmap(struct address_space *mapping, sector_t block) } const struct address_space_operations affs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = affs_readpage, .writepage = affs_writepage, .write_begin = affs_write_begin, @@ -833,6 +834,7 @@ err_bh: } const struct address_space_operations affs_aops_ofs = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = affs_readpage_ofs, //.writepage = affs_writepage_ofs, .write_begin = affs_write_begin_ofs, diff --git a/fs/bfs/file.c b/fs/bfs/file.c index 0dceefc54b48..7f8544abf636 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -188,6 +188,7 @@ static sector_t bfs_bmap(struct address_space *mapping, sector_t block) } const struct address_space_operations bfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = bfs_readpage, .writepage = bfs_writepage, .write_begin = bfs_write_begin, diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 3e84e9bb9084..145917f734fe 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -222,7 +222,7 @@ static int load_aout_binary(struct linux_binprm * bprm) error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, PROT_READ | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE, + MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE, fd_offset); if (error != N_TXTADDR(ex)) @@ -230,7 +230,7 @@ static int load_aout_binary(struct linux_binprm * bprm) error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE, + MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE, fd_offset + ex.a_text); if (error != N_DATADDR(ex)) return error; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 3d73cbb439fa..439ed81e755a 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1070,7 +1070,7 @@ out_free_interp: elf_prot = make_prot(elf_ppnt->p_flags, &arch_state, !!interpreter, false); - elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE; + elf_flags = MAP_PRIVATE | MAP_DENYWRITE; vaddr = elf_ppnt->p_vaddr; /* diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index ab9c31ddffda..cf4028487dcc 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -928,7 +928,7 @@ static int elf_fdpic_map_file_constdisp_on_uclinux( { struct elf32_fdpic_loadseg *seg; struct elf32_phdr *phdr; - unsigned long load_addr, base = ULONG_MAX, top = 0, maddr = 0, mflags; + unsigned long load_addr, base = ULONG_MAX, top = 0, maddr = 0; int loop, ret; load_addr = params->load_addr; @@ -948,12 +948,8 @@ static int elf_fdpic_map_file_constdisp_on_uclinux( } /* allocate one big anon block for everything */ - mflags = MAP_PRIVATE; - if (params->flags & ELF_FDPIC_FLAG_EXECUTABLE) - mflags |= MAP_EXECUTABLE; - maddr = vm_mmap(NULL, load_addr, top - base, - PROT_READ | PROT_WRITE | PROT_EXEC, mflags, 0); + PROT_READ | PROT_WRITE | PROT_EXEC, MAP_PRIVATE, 0); if (IS_ERR_VALUE(maddr)) return (int) maddr; @@ -1046,9 +1042,6 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, if (phdr->p_flags & PF_X) prot |= PROT_EXEC; flags = MAP_PRIVATE | MAP_DENYWRITE; - if (params->flags & ELF_FDPIC_FLAG_EXECUTABLE) - flags |= MAP_EXECUTABLE; - maddr = 0; switch (params->flags & ELF_FDPIC_FLAG_ARRANGEMENT) { diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index a1072c6a2341..5d776f80ee50 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -573,7 +573,7 @@ static int load_flat_file(struct linux_binprm *bprm, pr_debug("ROM mapping of file (we hope)\n"); textpos = vm_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC, - MAP_PRIVATE|MAP_EXECUTABLE, 0); + MAP_PRIVATE, 0); if (!textpos || IS_ERR_VALUE(textpos)) { ret = textpos; if (!textpos) diff --git a/fs/block_dev.c b/fs/block_dev.c index 6cc4d4cfe0c2..eb34f5c357cf 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1754,6 +1754,7 @@ static int blkdev_writepages(struct address_space *mapping, } static const struct address_space_operations def_blk_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = blkdev_readpage, .readahead = blkdev_readahead, .writepage = blkdev_writepage, diff --git a/fs/buffer.c b/fs/buffer.c index ea48c01fb76b..6290c3afdba4 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -589,31 +589,6 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) EXPORT_SYMBOL(mark_buffer_dirty_inode); /* - * Mark the page dirty, and set it dirty in the page cache, and mark the inode - * dirty. - * - * If warn is true, then emit a warning if the page is not uptodate and has - * not been truncated. - * - * The caller must hold lock_page_memcg(). - */ -void __set_page_dirty(struct page *page, struct address_space *mapping, - int warn) -{ - unsigned long flags; - - xa_lock_irqsave(&mapping->i_pages, flags); - if (page->mapping) { /* Race with truncate? */ - WARN_ON_ONCE(warn && !PageUptodate(page)); - account_page_dirtied(page, mapping); - __xa_set_mark(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_DIRTY); - } - xa_unlock_irqrestore(&mapping->i_pages, flags); -} -EXPORT_SYMBOL_GPL(__set_page_dirty); - -/* * Add a page to the dirty page list. * * It is a sad fact of life that this function is called from several places diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index eb5ec3e46283..b601610e9907 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -28,12 +28,6 @@ static struct lock_class_key default_group_class[MAX_LOCK_DEPTH]; #endif -static const struct address_space_operations configfs_aops = { - .readpage = simple_readpage, - .write_begin = simple_write_begin, - .write_end = simple_write_end, -}; - static const struct inode_operations configfs_inode_operations ={ .setattr = configfs_setattr, }; @@ -114,7 +108,7 @@ struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd, struct inode * inode = new_inode(s); if (inode) { inode->i_ino = get_next_ino(); - inode->i_mapping->a_ops = &configfs_aops; + inode->i_mapping->a_ops = &ram_aops; inode->i_op = &configfs_inode_operations; if (sd->s_iattr) { @@ -488,10 +488,11 @@ static void *grab_mapping_entry(struct xa_state *xas, struct address_space *mapping, unsigned int order) { unsigned long index = xas->xa_index; - bool pmd_downgrade = false; /* splitting PMD entry into PTE entries? */ + bool pmd_downgrade; /* splitting PMD entry into PTE entries? */ void *entry; retry: + pmd_downgrade = false; xas_lock_irq(xas); entry = get_unlocked_entry(xas, order); diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 392e721b50a3..7d85e64ea62f 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -533,7 +533,20 @@ static sector_t ecryptfs_bmap(struct address_space *mapping, sector_t block) return block; } +#include <linux/buffer_head.h> + const struct address_space_operations ecryptfs_aops = { + /* + * XXX: This is pretty broken for multiple reasons: ecryptfs does not + * actually use buffer_heads, and ecryptfs will crash without + * CONFIG_BLOCK. But it matches the behavior before the default for + * address_space_operations without the ->set_page_dirty method was + * cleaned up, so this is the best we can do without maintainer + * feedback. + */ +#ifdef CONFIG_BLOCK + .set_page_dirty = __set_page_dirty_buffers, +#endif .writepage = ecryptfs_writepage, .readpage = ecryptfs_readpage, .write_begin = ecryptfs_write_begin, diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index 1803ef3220fd..ca37d4344361 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -491,6 +491,7 @@ int exfat_block_truncate_page(struct inode *inode, loff_t from) } static const struct address_space_operations exfat_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = exfat_readpage, .readahead = exfat_readahead, .writepage = exfat_writepage, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 68178b2234bd..dadb121beb22 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -961,6 +961,7 @@ ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc } const struct address_space_operations ext2_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = ext2_readpage, .readahead = ext2_readahead, .writepage = ext2_writepage, @@ -975,6 +976,7 @@ const struct address_space_operations ext2_aops = { }; const struct address_space_operations ext2_nobh_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = ext2_readpage, .readahead = ext2_readahead, .writepage = ext2_nobh_writepage, @@ -990,7 +992,7 @@ const struct address_space_operations ext2_nobh_aops = { static const struct address_space_operations ext2_dax_aops = { .writepages = ext2_dax_writepages, .direct_IO = noop_direct_IO, - .set_page_dirty = noop_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, .invalidatepage = noop_invalidatepage, }; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fe6045a46599..b8170a008590 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3701,7 +3701,7 @@ static const struct address_space_operations ext4_da_aops = { static const struct address_space_operations ext4_dax_aops = { .writepages = ext4_dax_writepages, .direct_IO = noop_direct_IO, - .set_page_dirty = noop_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, .bmap = ext4_bmap, .invalidatepage = noop_invalidatepage, .swap_activate = ext4_iomap_swap_activate, diff --git a/fs/fat/inode.c b/fs/fat/inode.c index bab9b202b496..de0c9b013a85 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -342,6 +342,7 @@ int fat_block_truncate_page(struct inode *inode, loff_t from) } static const struct address_space_operations fat_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = fat_readpage, .readahead = fat_readahead, .writepage = fat_writepage, diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e91980f49388..62193106683d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -131,25 +131,6 @@ static bool inode_io_list_move_locked(struct inode *inode, return false; } -/** - * inode_io_list_del_locked - remove an inode from its bdi_writeback IO list - * @inode: inode to be removed - * @wb: bdi_writeback @inode is being removed from - * - * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and - * clear %WB_has_dirty_io if all are empty afterwards. - */ -static void inode_io_list_del_locked(struct inode *inode, - struct bdi_writeback *wb) -{ - assert_spin_locked(&wb->list_lock); - assert_spin_locked(&inode->i_lock); - - inode->i_state &= ~I_SYNC_QUEUED; - list_del_init(&inode->i_io_list); - wb_io_lists_depopulated(wb); -} - static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_bh(&wb->work_lock); @@ -244,6 +225,13 @@ void wb_wait_for_completion(struct wb_completion *done) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ +/* + * Maximum inodes per isw. A specific value has been chosen to make + * struct inode_switch_wbs_context fit into 1024 bytes kmalloc. + */ +#define WB_MAX_INODES_PER_ISW ((1024UL - sizeof(struct inode_switch_wbs_context)) \ + / sizeof(struct inode *)) + static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; @@ -279,6 +267,28 @@ void __inode_attach_wb(struct inode *inode, struct page *page) EXPORT_SYMBOL_GPL(__inode_attach_wb); /** + * inode_cgwb_move_to_attached - put the inode onto wb->b_attached list + * @inode: inode of interest with i_lock held + * @wb: target bdi_writeback + * + * Remove the inode from wb's io lists and if necessarily put onto b_attached + * list. Only inodes attached to cgwb's are kept on this list. + */ +static void inode_cgwb_move_to_attached(struct inode *inode, + struct bdi_writeback *wb) +{ + assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); + + inode->i_state &= ~I_SYNC_QUEUED; + if (wb != &wb->bdi->wb) + list_move(&inode->i_io_list, &wb->b_attached); + else + list_del_init(&inode->i_io_list); + wb_io_lists_depopulated(wb); +} + +/** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held * @@ -332,11 +342,18 @@ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) } struct inode_switch_wbs_context { - struct inode *inode; - struct bdi_writeback *new_wb; + struct rcu_work work; - struct rcu_head rcu_head; - struct work_struct work; + /* + * Multiple inodes can be switched at once. The switching procedure + * consists of two parts, separated by a RCU grace period. To make + * sure that the second part is executed for each inode gone through + * the first part, all inode pointers are placed into a NULL-terminated + * array embedded into struct inode_switch_wbs_context. Otherwise + * an inode could be left in a non-consistent state. + */ + struct bdi_writeback *new_wb; + struct inode *inodes[]; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) @@ -349,50 +366,23 @@ static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) up_write(&bdi->wb_switch_rwsem); } -static void inode_switch_wbs_work_fn(struct work_struct *work) +static bool inode_do_switch_wbs(struct inode *inode, + struct bdi_writeback *old_wb, + struct bdi_writeback *new_wb) { - struct inode_switch_wbs_context *isw = - container_of(work, struct inode_switch_wbs_context, work); - struct inode *inode = isw->inode; - struct backing_dev_info *bdi = inode_to_bdi(inode); struct address_space *mapping = inode->i_mapping; - struct bdi_writeback *old_wb = inode->i_wb; - struct bdi_writeback *new_wb = isw->new_wb; XA_STATE(xas, &mapping->i_pages, 0); struct page *page; bool switched = false; - /* - * If @inode switches cgwb membership while sync_inodes_sb() is - * being issued, sync_inodes_sb() might miss it. Synchronize. - */ - down_read(&bdi->wb_switch_rwsem); - - /* - * By the time control reaches here, RCU grace period has passed - * since I_WB_SWITCH assertion and all wb stat update transactions - * between unlocked_inode_to_wb_begin/end() are guaranteed to be - * synchronizing against the i_pages lock. - * - * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock - * gives us exclusion against all wb related operations on @inode - * including IO list manipulations and stat updates. - */ - if (old_wb < new_wb) { - spin_lock(&old_wb->list_lock); - spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); - } else { - spin_lock(&new_wb->list_lock); - spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); - } spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* - * Once I_FREEING is visible under i_lock, the eviction path owns - * the inode and we shouldn't modify ->i_io_list. + * Once I_FREEING or I_WILL_FREE are visible under i_lock, the eviction + * path owns the inode and we shouldn't modify ->i_io_list. */ - if (unlikely(inode->i_state & I_FREEING)) + if (unlikely(inode->i_state & (I_FREEING | I_WILL_FREE))) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); @@ -419,21 +409,28 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) wb_get(new_wb); /* - * Transfer to @new_wb's IO list if necessary. The specific list - * @inode was on is ignored and the inode is put on ->b_dirty which - * is always correct including from ->b_dirty_time. The transfer - * preserves @inode->dirtied_when ordering. + * Transfer to @new_wb's IO list if necessary. If the @inode is dirty, + * the specific list @inode was on is ignored and the @inode is put on + * ->b_dirty which is always correct including from ->b_dirty_time. + * The transfer preserves @inode->dirtied_when ordering. If the @inode + * was clean, it means it was on the b_attached list, so move it onto + * the b_attached list of @new_wb. */ if (!list_empty(&inode->i_io_list)) { - struct inode *pos; - - inode_io_list_del_locked(inode, old_wb); inode->i_wb = new_wb; - list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) - if (time_after_eq(inode->dirtied_when, - pos->dirtied_when)) - break; - inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); + + if (inode->i_state & I_DIRTY_ALL) { + struct inode *pos; + + list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) + if (time_after_eq(inode->dirtied_when, + pos->dirtied_when)) + break; + inode_io_list_move_locked(inode, new_wb, + pos->i_io_list.prev); + } else { + inode_cgwb_move_to_attached(inode, new_wb); + } } else { inode->i_wb = new_wb; } @@ -452,31 +449,91 @@ skip_switch: xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); + + return switched; +} + +static void inode_switch_wbs_work_fn(struct work_struct *work) +{ + struct inode_switch_wbs_context *isw = + container_of(to_rcu_work(work), struct inode_switch_wbs_context, work); + struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]); + struct bdi_writeback *old_wb = isw->inodes[0]->i_wb; + struct bdi_writeback *new_wb = isw->new_wb; + unsigned long nr_switched = 0; + struct inode **inodep; + + /* + * If @inode switches cgwb membership while sync_inodes_sb() is + * being issued, sync_inodes_sb() might miss it. Synchronize. + */ + down_read(&bdi->wb_switch_rwsem); + + /* + * By the time control reaches here, RCU grace period has passed + * since I_WB_SWITCH assertion and all wb stat update transactions + * between unlocked_inode_to_wb_begin/end() are guaranteed to be + * synchronizing against the i_pages lock. + * + * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock + * gives us exclusion against all wb related operations on @inode + * including IO list manipulations and stat updates. + */ + if (old_wb < new_wb) { + spin_lock(&old_wb->list_lock); + spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock(&new_wb->list_lock); + spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); + } + + for (inodep = isw->inodes; *inodep; inodep++) { + WARN_ON_ONCE((*inodep)->i_wb != old_wb); + if (inode_do_switch_wbs(*inodep, old_wb, new_wb)) + nr_switched++; + } + spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); - if (switched) { + if (nr_switched) { wb_wakeup(new_wb); - wb_put(old_wb); + wb_put_many(old_wb, nr_switched); } - wb_put(new_wb); - iput(inode); + for (inodep = isw->inodes; *inodep; inodep++) + iput(*inodep); + wb_put(new_wb); kfree(isw); - atomic_dec(&isw_nr_in_flight); } -static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) +static bool inode_prepare_wbs_switch(struct inode *inode, + struct bdi_writeback *new_wb) { - struct inode_switch_wbs_context *isw = container_of(rcu_head, - struct inode_switch_wbs_context, rcu_head); + /* + * Paired with smp_mb() in cgroup_writeback_umount(). + * isw_nr_in_flight must be increased before checking SB_ACTIVE and + * grabbing an inode, otherwise isw_nr_in_flight can be observed as 0 + * in cgroup_writeback_umount() and the isw_wq will be not flushed. + */ + smp_mb(); + + /* while holding I_WB_SWITCH, no one else can update the association */ + spin_lock(&inode->i_lock); + if (!(inode->i_sb->s_flags & SB_ACTIVE) || + inode->i_state & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) || + inode_to_wb(inode) == new_wb) { + spin_unlock(&inode->i_lock); + return false; + } + inode->i_state |= I_WB_SWITCH; + __iget(inode); + spin_unlock(&inode->i_lock); - /* needs to grab bh-unsafe locks, bounce to work item */ - INIT_WORK(&isw->work, inode_switch_wbs_work_fn); - queue_work(isw_wq, &isw->work); + return true; } /** @@ -501,10 +558,12 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; - isw = kzalloc(sizeof(*isw), GFP_ATOMIC); + isw = kzalloc(sizeof(*isw) + 2 * sizeof(struct inode *), GFP_ATOMIC); if (!isw) return; + atomic_inc(&isw_nr_in_flight); + /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); @@ -514,19 +573,10 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) if (!isw->new_wb) goto out_free; - /* while holding I_WB_SWITCH, no one else can update the association */ - spin_lock(&inode->i_lock); - if (!(inode->i_sb->s_flags & SB_ACTIVE) || - inode->i_state & (I_WB_SWITCH | I_FREEING) || - inode_to_wb(inode) == isw->new_wb) { - spin_unlock(&inode->i_lock); + if (!inode_prepare_wbs_switch(inode, isw->new_wb)) goto out_free; - } - inode->i_state |= I_WB_SWITCH; - __iget(inode); - spin_unlock(&inode->i_lock); - isw->inode = inode; + isw->inodes[0] = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells @@ -534,18 +584,85 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ - call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); - - atomic_inc(&isw_nr_in_flight); + INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); + queue_rcu_work(isw_wq, &isw->work); return; out_free: + atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } /** + * cleanup_offline_cgwb - detach associated inodes + * @wb: target wb + * + * Switch all inodes attached to @wb to a nearest living ancestor's wb in order + * to eventually release the dying @wb. Returns %true if not all inodes were + * switched and the function has to be restarted. + */ +bool cleanup_offline_cgwb(struct bdi_writeback *wb) +{ + struct cgroup_subsys_state *memcg_css; + struct inode_switch_wbs_context *isw; + struct inode *inode; + int nr; + bool restart = false; + + isw = kzalloc(sizeof(*isw) + WB_MAX_INODES_PER_ISW * + sizeof(struct inode *), GFP_KERNEL); + if (!isw) + return restart; + + atomic_inc(&isw_nr_in_flight); + + for (memcg_css = wb->memcg_css->parent; memcg_css; + memcg_css = memcg_css->parent) { + isw->new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL); + if (isw->new_wb) + break; + } + if (unlikely(!isw->new_wb)) + isw->new_wb = &wb->bdi->wb; /* wb_get() is noop for bdi's wb */ + + nr = 0; + spin_lock(&wb->list_lock); + list_for_each_entry(inode, &wb->b_attached, i_io_list) { + if (!inode_prepare_wbs_switch(inode, isw->new_wb)) + continue; + + isw->inodes[nr++] = inode; + + if (nr >= WB_MAX_INODES_PER_ISW - 1) { + restart = true; + break; + } + } + spin_unlock(&wb->list_lock); + + /* no attached inodes? bail out */ + if (nr == 0) { + atomic_dec(&isw_nr_in_flight); + wb_put(isw->new_wb); + kfree(isw); + return restart; + } + + /* + * In addition to synchronizing among switchers, I_WB_SWITCH tells + * the RCU protected stat update paths to grab the i_page + * lock so that stat transfer can synchronize against them. + * Let's continue after I_WB_SWITCH is guaranteed to be visible. + */ + INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); + queue_rcu_work(isw_wq, &isw->work); + + return restart; +} + +/** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest * @inode: target inode @@ -1000,6 +1117,12 @@ out_bdi_put: */ void cgroup_writeback_umount(void) { + /* + * SB_ACTIVE should be reliably cleared before checking + * isw_nr_in_flight, see generic_shutdown_super(). + */ + smp_mb(); + if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to @@ -1024,6 +1147,17 @@ fs_initcall(cgroup_writeback_init); static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } +static void inode_cgwb_move_to_attached(struct inode *inode, + struct bdi_writeback *wb) +{ + assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); + + inode->i_state &= ~I_SYNC_QUEUED; + list_del_init(&inode->i_io_list); + wb_io_lists_depopulated(wb); +} + static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) @@ -1124,7 +1258,11 @@ void inode_io_list_del(struct inode *inode) wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); - inode_io_list_del_locked(inode, wb); + + inode->i_state &= ~I_SYNC_QUEUED; + list_del_init(&inode->i_io_list); + wb_io_lists_depopulated(wb); + spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } @@ -1437,7 +1575,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ - inode_io_list_del_locked(inode, wb); + inode_cgwb_move_to_attached(inode, wb); } } @@ -1589,7 +1727,7 @@ static int writeback_single_inode(struct inode *inode, * responsible for the writeback lists. */ if (!(inode->i_state & I_DIRTY_ALL)) - inode_io_list_del_locked(inode, wb); + inode_cgwb_move_to_attached(inode, wb); spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index ff99ab2a3c43..fb733eb5aead 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -9,6 +9,7 @@ #include <linux/delay.h> #include <linux/dax.h> #include <linux/uio.h> +#include <linux/pagemap.h> #include <linux/pfn_t.h> #include <linux/iomap.h> #include <linux/interval_tree.h> @@ -1329,7 +1330,7 @@ bool fuse_dax_inode_alloc(struct super_block *sb, struct fuse_inode *fi) static const struct address_space_operations fuse_dax_file_aops = { .writepages = fuse_dax_writepages, .direct_IO = noop_direct_IO, - .set_page_dirty = noop_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, .invalidatepage = noop_invalidatepage, }; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 23b5be3db044..81d8f064126e 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -784,7 +784,7 @@ static const struct address_space_operations gfs2_aops = { .writepages = gfs2_writepages, .readpage = gfs2_readpage, .readahead = gfs2_readahead, - .set_page_dirty = iomap_set_page_dirty, + .set_page_dirty = __set_page_dirty_nobuffers, .releasepage = iomap_releasepage, .invalidatepage = iomap_invalidatepage, .bmap = gfs2_bmap, diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index d68184ebbfdd..7c9619997355 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -89,11 +89,13 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb } const struct address_space_operations gfs2_meta_aops = { + .set_page_dirty = __set_page_dirty_buffers, .writepage = gfs2_aspace_writepage, .releasepage = gfs2_releasepage, }; const struct address_space_operations gfs2_rgrp_aops = { + .set_page_dirty = __set_page_dirty_buffers, .writepage = gfs2_aspace_writepage, .releasepage = gfs2_releasepage, }; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 3fc5cb346586..4a95a92546a0 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -159,6 +159,7 @@ static int hfs_writepages(struct address_space *mapping, } const struct address_space_operations hfs_btree_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = hfs_readpage, .writepage = hfs_writepage, .write_begin = hfs_write_begin, @@ -168,6 +169,7 @@ const struct address_space_operations hfs_btree_aops = { }; const struct address_space_operations hfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = hfs_readpage, .writepage = hfs_writepage, .write_begin = hfs_write_begin, diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 8ea447e5c470..70e8374ddac4 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -156,6 +156,7 @@ static int hfsplus_writepages(struct address_space *mapping, } const struct address_space_operations hfsplus_btree_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = hfsplus_readpage, .writepage = hfsplus_writepage, .write_begin = hfsplus_write_begin, @@ -165,6 +166,7 @@ const struct address_space_operations hfsplus_btree_aops = { }; const struct address_space_operations hfsplus_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = hfsplus_readpage, .writepage = hfsplus_writepage, .write_begin = hfsplus_write_begin, diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 077c25128eb7..c3a49aacf20a 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -196,6 +196,7 @@ static int hpfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } const struct address_space_operations hpfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = hpfs_readpage, .writepage = hpfs_writepage, .readahead = hpfs_readahead, diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 9023717c5188..0065781935c7 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -640,31 +640,6 @@ out_no_page: return status; } -int -iomap_set_page_dirty(struct page *page) -{ - struct address_space *mapping = page_mapping(page); - int newly_dirty; - - if (unlikely(!mapping)) - return !TestSetPageDirty(page); - - /* - * Lock out page's memcg migration to keep PageDirty - * synchronized with per-memcg dirty page counters. - */ - lock_page_memcg(page); - newly_dirty = !TestSetPageDirty(page); - if (newly_dirty) - __set_page_dirty(page, mapping, 0); - unlock_page_memcg(page); - - if (newly_dirty) - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - return newly_dirty; -} -EXPORT_SYMBOL_GPL(iomap_set_page_dirty); - static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len, size_t copied, struct page *page) { @@ -684,7 +659,7 @@ static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len, if (unlikely(copied < len && !PageUptodate(page))) return 0; iomap_set_range_uptodate(page, offset_in_page(pos), len); - iomap_set_page_dirty(page); + __set_page_dirty_nobuffers(page); return copied; } diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 6f65bfa9f18d..3663dd5a23bc 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -356,6 +356,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } const struct address_space_operations jfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = jfs_readpage, .readahead = jfs_readahead, .writepage = jfs_writepage, diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index d73950fc3d57..26f2aa3586f9 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -17,12 +17,6 @@ #include "kernfs-internal.h" -static const struct address_space_operations kernfs_aops = { - .readpage = simple_readpage, - .write_begin = simple_write_begin, - .write_end = simple_write_end, -}; - static const struct inode_operations kernfs_iops = { .permission = kernfs_iop_permission, .setattr = kernfs_iop_setattr, @@ -203,7 +197,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode) { kernfs_get(kn); inode->i_private = kn; - inode->i_mapping->a_ops = &kernfs_aops; + inode->i_mapping->a_ops = &ram_aops; inode->i_op = &kernfs_iops; inode->i_generation = kernfs_gen(kn); diff --git a/fs/libfs.c b/fs/libfs.c index e9b29c6ffccb..51b4de3b3447 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -512,7 +512,7 @@ int simple_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, } EXPORT_SYMBOL(simple_setattr); -int simple_readpage(struct file *file, struct page *page) +static int simple_readpage(struct file *file, struct page *page) { clear_highpage(page); flush_dcache_page(page); @@ -520,7 +520,6 @@ int simple_readpage(struct file *file, struct page *page) unlock_page(page); return 0; } -EXPORT_SYMBOL(simple_readpage); int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, @@ -568,7 +567,7 @@ EXPORT_SYMBOL(simple_write_begin); * * Use *ONLY* with simple_readpage() */ -int simple_write_end(struct file *file, struct address_space *mapping, +static int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { @@ -597,7 +596,17 @@ int simple_write_end(struct file *file, struct address_space *mapping, return copied; } -EXPORT_SYMBOL(simple_write_end); + +/* + * Provides ramfs-style behavior: data in the pagecache, but no writeback. + */ +const struct address_space_operations ram_aops = { + .readpage = simple_readpage, + .write_begin = simple_write_begin, + .write_end = simple_write_end, + .set_page_dirty = __set_page_dirty_no_writeback, +}; +EXPORT_SYMBOL(ram_aops); /* * the inodes created here are not hashed. If you use iunique to generate @@ -1162,22 +1171,6 @@ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync) } EXPORT_SYMBOL(noop_fsync); -int noop_set_page_dirty(struct page *page) -{ - /* - * Unlike __set_page_dirty_no_writeback that handles dirty page - * tracking in the page object, dax does all dirty tracking in - * the inode address_space in response to mkwrite faults. In the - * dax case we only need to worry about potentially dirty CPU - * caches, not dirty page cache pages to write back. - * - * This callback is defined to prevent fallback to - * __set_page_dirty_buffers() in set_page_dirty(). - */ - return 0; -} -EXPORT_SYMBOL_GPL(noop_set_page_dirty); - void noop_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { @@ -1208,19 +1201,10 @@ void kfree_link(void *p) } EXPORT_SYMBOL(kfree_link); -/* - * nop .set_page_dirty method so that people can use .page_mkwrite on - * anon inodes. - */ -static int anon_set_page_dirty(struct page *page) -{ - return 0; -}; - struct inode *alloc_anon_inode(struct super_block *s) { static const struct address_space_operations anon_aops = { - .set_page_dirty = anon_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, }; struct inode *inode = new_inode_pseudo(s); diff --git a/fs/minix/inode.c b/fs/minix/inode.c index a532a99bbe81..a71f1cf894b9 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -442,6 +442,7 @@ static sector_t minix_bmap(struct address_space *mapping, sector_t block) } static const struct address_space_operations minix_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = minix_readpage, .writepage = minix_writepage, .write_begin = minix_write_begin, diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index c0361ce45f62..97769fe4d588 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -434,6 +434,7 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc) static const struct address_space_operations def_mdt_aops = { + .set_page_dirty = __set_page_dirty_buffers, .writepage = nilfs_mdt_write_page, }; diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index f5c058b3192c..4474adb393ca 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -477,7 +477,7 @@ err_corrupt_attr: } file_name_attr = (FILE_NAME_ATTR*)((u8*)attr + le16_to_cpu(attr->data.resident.value_offset)); - p2 = (u8*)attr + le32_to_cpu(attr->data.resident.value_length); + p2 = (u8 *)file_name_attr + le32_to_cpu(attr->data.resident.value_length); if (p2 < (u8*)attr || p2 > p) goto err_corrupt_attr; /* This attribute is ok, but is it in the $Extend directory? */ diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 1294925ac94a..68d11c295dd3 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -632,8 +632,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno, } if (PageUptodate(page)) { - if (!buffer_uptodate(bh)) - set_buffer_uptodate(bh); + set_buffer_uptodate(bh); } else if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_new(bh) && ocfs2_should_read_blk(inode, page, block_start) && @@ -2454,6 +2453,7 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } const struct address_space_operations ocfs2_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = ocfs2_readpage, .readahead = ocfs2_readahead, .writepage = ocfs2_writepage, diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index e829c2595543..f89ffcbd585f 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1442,8 +1442,6 @@ void o2hb_init(void) for (i = 0; i < ARRAY_SIZE(o2hb_live_slots); i++) INIT_LIST_HEAD(&o2hb_live_slots[i]); - INIT_LIST_HEAD(&o2hb_node_events); - memset(o2hb_live_node_bitmap, 0, sizeof(o2hb_live_node_bitmap)); memset(o2hb_region_bitmap, 0, sizeof(o2hb_region_bitmap)); memset(o2hb_live_region_bitmap, 0, sizeof(o2hb_live_region_bitmap)); @@ -1598,12 +1596,13 @@ static ssize_t o2hb_region_start_block_store(struct config_item *item, struct o2hb_region *reg = to_o2hb_region(item); unsigned long long tmp; char *p = (char *)page; + ssize_t ret; if (reg->hr_bdev) return -EINVAL; - tmp = simple_strtoull(p, &p, 0); - if (!p || (*p && (*p != '\n'))) + ret = kstrtoull(p, 0, &tmp); + if (ret) return -EINVAL; reg->hr_start_block = tmp; diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index bb82e6b1ff4e..625c92521416 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -824,7 +824,7 @@ static void __exit exit_o2nm(void) static int __init init_o2nm(void) { - int ret = -1; + int ret; o2hb_init(); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 4960a6de768d..9b88219febb5 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2977,7 +2977,7 @@ static u8 dlm_pick_migration_target(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { enum dlm_lockres_list idx; - struct list_head *queue = &res->granted; + struct list_head *queue; struct dlm_lock *lock; int noderef; u8 nodenum = O2NM_MAX_NODES; diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c index 90b8d300c1ee..de56e6231af8 100644 --- a/fs/ocfs2/filecheck.c +++ b/fs/ocfs2/filecheck.c @@ -326,11 +326,7 @@ static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj, ret = snprintf(buf + total, remain, "%lu\t\t%u\t%s\n", p->fe_ino, p->fe_done, ocfs2_filecheck_error(p->fe_status)); - if (ret < 0) { - total = ret; - break; - } - if (ret == remain) { + if (ret >= remain) { /* snprintf() didn't fit */ total = -E2BIG; break; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index d50e8b8dfea4..16f1bfc407f2 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -500,11 +500,7 @@ static ssize_t ocfs2_loaded_cluster_plugins_show(struct kobject *kobj, list_for_each_entry(p, &ocfs2_stack_list, sp_list) { ret = snprintf(buf, remain, "%s\n", p->sp_name); - if (ret < 0) { - total = ret; - break; - } - if (ret == remain) { + if (ret >= remain) { /* snprintf() didn't fit */ total = -E2BIG; break; @@ -531,7 +527,7 @@ static ssize_t ocfs2_active_cluster_plugin_show(struct kobject *kobj, if (active_stack) { ret = snprintf(buf, PAGE_SIZE, "%s\n", active_stack->sp_name); - if (ret == PAGE_SIZE) + if (ret >= PAGE_SIZE) ret = -E2BIG; } spin_unlock(&ocfs2_stack_lock); diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 11e733aab25d..89725b15a64b 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -372,6 +372,7 @@ const struct inode_operations omfs_file_inops = { }; const struct address_space_operations omfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = omfs_readpage, .readahead = omfs_readahead, .writepage = omfs_writepage, diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index fc9784544b24..66965ad88d8b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1047,7 +1047,7 @@ static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, return false; if (!is_cow_mapping(vma->vm_flags)) return false; - if (likely(!atomic_read(&vma->vm_mm->has_pinned))) + if (likely(!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))) return false; page = vm_normal_page(vma, addr, pte); if (!page) diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 9ebd17d7befb..65e7e56005b8 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -53,13 +53,6 @@ struct ramfs_fs_info { static const struct super_operations ramfs_ops; static const struct inode_operations ramfs_dir_inode_operations; -static const struct address_space_operations ramfs_aops = { - .readpage = simple_readpage, - .write_begin = simple_write_begin, - .write_end = simple_write_end, - .set_page_dirty = __set_page_dirty_no_writeback, -}; - struct inode *ramfs_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode, dev_t dev) { @@ -68,7 +61,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, if (inode) { inode->i_ino = get_next_ino(); inode_init_owner(&init_user_ns, inode, dir, mode); - inode->i_mapping->a_ops = &ramfs_aops; + inode->i_mapping->a_ops = &ram_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index b9e87ebb1060..855f0e87066d 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -226,8 +226,11 @@ out_free_bio: bio_free_pages(bio); bio_put(bio); out: - if (res < 0) + if (res < 0) { ERROR("Failed to read block 0x%llx: %d\n", index, res); + if (msblk->panic_on_errors) + panic("squashfs read failed"); + } return res; } diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 166e98806265..1e90c2575f9b 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -65,5 +65,6 @@ struct squashfs_sb_info { unsigned int fragments; int xattr_ids; unsigned int ids; + bool panic_on_errors; }; #endif diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 88cc94be1076..60d6951915f4 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -18,9 +18,11 @@ #include <linux/fs.h> #include <linux/fs_context.h> +#include <linux/fs_parser.h> #include <linux/vfs.h> #include <linux/slab.h> #include <linux/mutex.h> +#include <linux/seq_file.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/module.h> @@ -37,6 +39,51 @@ static struct file_system_type squashfs_fs_type; static const struct super_operations squashfs_super_ops; +enum Opt_errors { + Opt_errors_continue, + Opt_errors_panic, +}; + +enum squashfs_param { + Opt_errors, +}; + +struct squashfs_mount_opts { + enum Opt_errors errors; +}; + +static const struct constant_table squashfs_param_errors[] = { + {"continue", Opt_errors_continue }, + {"panic", Opt_errors_panic }, + {} +}; + +static const struct fs_parameter_spec squashfs_fs_parameters[] = { + fsparam_enum("errors", Opt_errors, squashfs_param_errors), + {} +}; + +static int squashfs_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct squashfs_mount_opts *opts = fc->fs_private; + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, squashfs_fs_parameters, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_errors: + opts->errors = result.uint_32; + break; + default: + return -EINVAL; + } + + return 0; +} + static const struct squashfs_decompressor *supported_squashfs_filesystem( struct fs_context *fc, short major, short minor, short id) @@ -67,6 +114,7 @@ static const struct squashfs_decompressor *supported_squashfs_filesystem( static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) { + struct squashfs_mount_opts *opts = fc->fs_private; struct squashfs_sb_info *msblk; struct squashfs_super_block *sblk = NULL; struct inode *root; @@ -85,6 +133,8 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) } msblk = sb->s_fs_info; + msblk->panic_on_errors = (opts->errors == Opt_errors_panic); + msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE); msblk->devblksize_log2 = ffz(~msblk->devblksize); @@ -350,18 +400,52 @@ static int squashfs_get_tree(struct fs_context *fc) static int squashfs_reconfigure(struct fs_context *fc) { + struct super_block *sb = fc->root->d_sb; + struct squashfs_sb_info *msblk = sb->s_fs_info; + struct squashfs_mount_opts *opts = fc->fs_private; + sync_filesystem(fc->root->d_sb); fc->sb_flags |= SB_RDONLY; + + msblk->panic_on_errors = (opts->errors == Opt_errors_panic); + return 0; } +static void squashfs_free_fs_context(struct fs_context *fc) +{ + kfree(fc->fs_private); +} + static const struct fs_context_operations squashfs_context_ops = { .get_tree = squashfs_get_tree, + .free = squashfs_free_fs_context, + .parse_param = squashfs_parse_param, .reconfigure = squashfs_reconfigure, }; +static int squashfs_show_options(struct seq_file *s, struct dentry *root) +{ + struct super_block *sb = root->d_sb; + struct squashfs_sb_info *msblk = sb->s_fs_info; + + if (msblk->panic_on_errors) + seq_puts(s, ",errors=panic"); + else + seq_puts(s, ",errors=continue"); + + return 0; +} + static int squashfs_init_fs_context(struct fs_context *fc) { + struct squashfs_mount_opts *opts; + + opts = kzalloc(sizeof(*opts), GFP_KERNEL); + if (!opts) + return -ENOMEM; + + fc->fs_private = opts; fc->ops = &squashfs_context_ops; return 0; } @@ -481,6 +565,7 @@ static struct file_system_type squashfs_fs_type = { .owner = THIS_MODULE, .name = "squashfs", .init_fs_context = squashfs_init_fs_context, + .parameters = squashfs_fs_parameters, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV }; @@ -491,6 +576,7 @@ static const struct super_operations squashfs_super_ops = { .free_inode = squashfs_free_inode, .statfs = squashfs_statfs, .put_super = squashfs_put_super, + .show_options = squashfs_show_options, }; module_init(init_squashfs_fs); diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 8b2e99b7bc9f..749385015a8d 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -495,6 +495,7 @@ static sector_t sysv_bmap(struct address_space *mapping, sector_t block) } const struct address_space_operations sysv_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = sysv_readpage, .writepage = sysv_writepage, .write_begin = sysv_write_begin, diff --git a/fs/udf/file.c b/fs/udf/file.c index 2846dcd92197..1baff8ddb754 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -125,6 +125,7 @@ static int udf_adinicb_write_end(struct file *file, struct address_space *mappin } const struct address_space_operations udf_adinicb_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = udf_adinicb_readpage, .writepage = udf_adinicb_writepage, .write_begin = udf_adinicb_write_begin, diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 0dd2f93ac048..4917670860a0 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -235,6 +235,7 @@ static sector_t udf_bmap(struct address_space *mapping, sector_t block) } const struct address_space_operations udf_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = udf_readpage, .readahead = udf_readahead, .writepage = udf_writepage, diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index debc282c1bb4..ac628de69601 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -526,6 +526,7 @@ static sector_t ufs_bmap(struct address_space *mapping, sector_t block) } const struct address_space_operations ufs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = ufs_readpage, .writepage = ufs_writepage, .write_begin = ufs_write_begin, diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 826caa6b4a5a..cb4e0fcf4c76 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -561,7 +561,7 @@ const struct address_space_operations xfs_address_space_operations = { .readahead = xfs_vm_readahead, .writepage = xfs_vm_writepage, .writepages = xfs_vm_writepages, - .set_page_dirty = iomap_set_page_dirty, + .set_page_dirty = __set_page_dirty_nobuffers, .releasepage = iomap_releasepage, .invalidatepage = iomap_invalidatepage, .bmap = xfs_vm_bmap, @@ -575,7 +575,7 @@ const struct address_space_operations xfs_address_space_operations = { const struct address_space_operations xfs_dax_aops = { .writepages = xfs_dax_writepages, .direct_IO = noop_direct_IO, - .set_page_dirty = noop_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, .invalidatepage = noop_invalidatepage, .swap_activate = xfs_iomap_swapfile_activate, }; diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index cd145d318b17..dbf03635869c 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -5,7 +5,7 @@ * Copyright (C) 2019 Western Digital Corporation or its affiliates. */ #include <linux/module.h> -#include <linux/fs.h> +#include <linux/pagemap.h> #include <linux/magic.h> #include <linux/iomap.h> #include <linux/init.h> @@ -185,7 +185,7 @@ static const struct address_space_operations zonefs_file_aops = { .readahead = zonefs_readahead, .writepage = zonefs_writepage, .writepages = zonefs_writepages, - .set_page_dirty = iomap_set_page_dirty, + .set_page_dirty = __set_page_dirty_nobuffers, .releasepage = iomap_releasepage, .invalidatepage = iomap_invalidatepage, .migratepage = iomap_migrate_page, |