diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-11 10:16:13 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-11 10:16:13 -0700 |
commit | d54d35c501bcbd57b9722a6b371c0608b5d34199 (patch) | |
tree | 3dcbc5b272a7c18634a238f7503af452cbed1fd8 /fs | |
parent | a2225d931f75ddd3c39f4d0d195fad99dfd68671 (diff) | |
parent | dfa742803fbbd8b82790c152600e09c5ad99caca (diff) |
Merge tag 'f2fs-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs
Pull f2fs updates from Jaegeuk Kim:
"In this round, we've mainly focused on discard, aka unmap, control
along with fstrim for Android-specific usage model. In addition, we've
fixed writepage flow which returned EAGAIN previously resulting in EIO
of fsync(2) due to mapping's error state. In order to avoid old MM bug
[1], we decided not to use __GFP_ZERO for the mapping for node and
meta page caches. As always, we've cleaned up many places for future
fsverity and symbol conflicts.
Enhancements:
- do discard/fstrim in lower priority considering fs utilization
- split large discard commands into smaller ones for better responsiveness
- add more sanity checks to address syzbot reports
- add a mount option, fsync_mode=nobarrier, which can reduce # of cache flushes
- clean up symbol namespace with modified function names
- be strict on block allocation and IO control in corner cases
Bug fixes:
- don't use __GFP_ZERO for mappings
- fix error reports in writepage to avoid fsync() failure
- avoid selinux denial on CAP_RESOURCE on resgid/resuid
- fix some subtle race conditions in GC/atomic writes/shutdown
- fix overflow bugs in sanity_check_raw_super
- fix missing bits on get_flags
Clean-ups:
- prepare the generic flow for future fsverity integration
- fix some broken coding standard"
[1] https://lkml.org/lkml/2018/4/8/661
* tag 'f2fs-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (79 commits)
f2fs: fix to clear FI_VOLATILE_FILE correctly
f2fs: let sync node IO interrupt async one
f2fs: don't change wbc->sync_mode
f2fs: fix to update mtime correctly
fs: f2fs: insert space around that ':' and ', '
fs: f2fs: add missing blank lines after declarations
fs: f2fs: changed variable type of offset "unsigned" to "loff_t"
f2fs: clean up symbol namespace
f2fs: make set_de_type() static
f2fs: make __f2fs_write_data_pages() static
f2fs: fix to avoid accessing cross the boundary
f2fs: fix to let caller retry allocating block address
disable loading f2fs module on PAGE_SIZE > 4KB
f2fs: fix error path of move_data_page
f2fs: don't drop dentry pages after fs shutdown
f2fs: fix to avoid race during access gc_thread pointer
f2fs: clean up with clear_radix_tree_dirty_tag
f2fs: fix to don't trigger writeback during recovery
f2fs: clear discard_wake earlier
f2fs: let discard thread wait a little longer if dev is busy
...
Diffstat (limited to 'fs')
-rw-r--r-- | fs/crypto/bio.c | 35 | ||||
-rw-r--r-- | fs/crypto/crypto.c | 8 | ||||
-rw-r--r-- | fs/crypto/fscrypt_private.h | 1 | ||||
-rw-r--r-- | fs/ext4/readpage.c | 2 | ||||
-rw-r--r-- | fs/f2fs/checkpoint.c | 149 | ||||
-rw-r--r-- | fs/f2fs/data.c | 399 | ||||
-rw-r--r-- | fs/f2fs/debug.c | 6 | ||||
-rw-r--r-- | fs/f2fs/dir.c | 76 | ||||
-rw-r--r-- | fs/f2fs/extent_cache.c | 22 | ||||
-rw-r--r-- | fs/f2fs/f2fs.h | 460 | ||||
-rw-r--r-- | fs/f2fs/file.c | 335 | ||||
-rw-r--r-- | fs/f2fs/gc.c | 183 | ||||
-rw-r--r-- | fs/f2fs/gc.h | 2 | ||||
-rw-r--r-- | fs/f2fs/inline.c | 78 | ||||
-rw-r--r-- | fs/f2fs/inode.c | 115 | ||||
-rw-r--r-- | fs/f2fs/namei.c | 67 | ||||
-rw-r--r-- | fs/f2fs/node.c | 285 | ||||
-rw-r--r-- | fs/f2fs/recovery.c | 65 | ||||
-rw-r--r-- | fs/f2fs/segment.c | 621 | ||||
-rw-r--r-- | fs/f2fs/segment.h | 31 | ||||
-rw-r--r-- | fs/f2fs/shrinker.c | 4 | ||||
-rw-r--r-- | fs/f2fs/super.c | 198 | ||||
-rw-r--r-- | fs/f2fs/sysfs.c | 63 | ||||
-rw-r--r-- | fs/f2fs/xattr.c | 26 |
24 files changed, 1855 insertions, 1376 deletions
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index 0d5e6a569d58..0959044c5cee 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -26,15 +26,8 @@ #include <linux/namei.h> #include "fscrypt_private.h" -/* - * Call fscrypt_decrypt_page on every single page, reusing the encryption - * context. - */ -static void completion_pages(struct work_struct *work) +static void __fscrypt_decrypt_bio(struct bio *bio, bool done) { - struct fscrypt_ctx *ctx = - container_of(work, struct fscrypt_ctx, r.work); - struct bio *bio = ctx->r.bio; struct bio_vec *bv; int i; @@ -46,22 +39,38 @@ static void completion_pages(struct work_struct *work) if (ret) { WARN_ON_ONCE(1); SetPageError(page); - } else { + } else if (done) { SetPageUptodate(page); } - unlock_page(page); + if (done) + unlock_page(page); } +} + +void fscrypt_decrypt_bio(struct bio *bio) +{ + __fscrypt_decrypt_bio(bio, false); +} +EXPORT_SYMBOL(fscrypt_decrypt_bio); + +static void completion_pages(struct work_struct *work) +{ + struct fscrypt_ctx *ctx = + container_of(work, struct fscrypt_ctx, r.work); + struct bio *bio = ctx->r.bio; + + __fscrypt_decrypt_bio(bio, true); fscrypt_release_ctx(ctx); bio_put(bio); } -void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio) +void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, struct bio *bio) { INIT_WORK(&ctx->r.work, completion_pages); ctx->r.bio = bio; - queue_work(fscrypt_read_workqueue, &ctx->r.work); + fscrypt_enqueue_decrypt_work(&ctx->r.work); } -EXPORT_SYMBOL(fscrypt_decrypt_bio_pages); +EXPORT_SYMBOL(fscrypt_enqueue_decrypt_bio); void fscrypt_pullback_bio_page(struct page **page, bool restore) { diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 243a269e6c5f..0f46cf550907 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -45,12 +45,18 @@ static mempool_t *fscrypt_bounce_page_pool = NULL; static LIST_HEAD(fscrypt_free_ctxs); static DEFINE_SPINLOCK(fscrypt_ctx_lock); -struct workqueue_struct *fscrypt_read_workqueue; +static struct workqueue_struct *fscrypt_read_workqueue; static DEFINE_MUTEX(fscrypt_init_mutex); static struct kmem_cache *fscrypt_ctx_cachep; struct kmem_cache *fscrypt_info_cachep; +void fscrypt_enqueue_decrypt_work(struct work_struct *work) +{ + queue_work(fscrypt_read_workqueue, work); +} +EXPORT_SYMBOL(fscrypt_enqueue_decrypt_work); + /** * fscrypt_release_ctx() - Releases an encryption context * @ctx: The encryption context to release. diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 37562394c5de..39c20ef26db4 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -93,7 +93,6 @@ static inline bool fscrypt_valid_enc_modes(u32 contents_mode, /* crypto.c */ extern struct kmem_cache *fscrypt_info_cachep; extern int fscrypt_initialize(unsigned int cop_flags); -extern struct workqueue_struct *fscrypt_read_workqueue; extern int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, u64 lblk_num, struct page *src_page, diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 9ffa6fad18db..19b87a8de6ff 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -77,7 +77,7 @@ static void mpage_end_io(struct bio *bio) if (bio->bi_status) { fscrypt_release_ctx(bio->bi_private); } else { - fscrypt_decrypt_bio_pages(bio->bi_private, bio); + fscrypt_enqueue_decrypt_bio(bio->bi_private, bio); return; } } diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index bf779461df13..9624a8f7254b 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -24,7 +24,7 @@ #include <trace/events/f2fs.h> static struct kmem_cache *ino_entry_slab; -struct kmem_cache *inode_entry_slab; +struct kmem_cache *f2fs_inode_entry_slab; void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io) { @@ -36,7 +36,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io) /* * We guarantee no failure on the returned page. */ -struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) { struct address_space *mapping = META_MAPPING(sbi); struct page *page = NULL; @@ -100,24 +100,27 @@ repeat: * readonly and make sure do not write checkpoint with non-uptodate * meta page. */ - if (unlikely(!PageUptodate(page))) + if (unlikely(!PageUptodate(page))) { + memset(page_address(page), 0, PAGE_SIZE); f2fs_stop_checkpoint(sbi, false); + } out: return page; } -struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) { return __get_meta_page(sbi, index, true); } /* for POR only */ -struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index) +struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index) { return __get_meta_page(sbi, index, false); } -bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) +bool f2fs_is_valid_meta_blkaddr(struct f2fs_sb_info *sbi, + block_t blkaddr, int type) { switch (type) { case META_NAT: @@ -151,7 +154,7 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) /* * Readahead CP/NAT/SIT/SSA pages */ -int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, +int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type, bool sync) { struct page *page; @@ -173,7 +176,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, blk_start_plug(&plug); for (; nrpages-- > 0; blkno++) { - if (!is_valid_blkaddr(sbi, blkno, type)) + if (!f2fs_is_valid_meta_blkaddr(sbi, blkno, type)) goto out; switch (type) { @@ -217,7 +220,7 @@ out: return blkno - start; } -void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) +void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) { struct page *page; bool readahead = false; @@ -228,7 +231,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) f2fs_put_page(page, 0); if (readahead) - ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true); + f2fs_ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true); } static int __f2fs_write_meta_page(struct page *page, @@ -249,7 +252,7 @@ static int __f2fs_write_meta_page(struct page *page, if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0)) goto redirty_out; - write_meta_page(sbi, page, io_type); + f2fs_do_write_meta_page(sbi, page, io_type); dec_page_count(sbi, F2FS_DIRTY_META); if (wbc->for_reclaim) @@ -294,7 +297,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping, trace_f2fs_writepages(mapping->host, wbc, META); diff = nr_pages_to_write(sbi, META, wbc); - written = sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO); + written = f2fs_sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO); mutex_unlock(&sbi->cp_mutex); wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff); return 0; @@ -305,7 +308,7 @@ skip_write: return 0; } -long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, +long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, long nr_to_write, enum iostat_type io_type) { struct address_space *mapping = META_MAPPING(sbi); @@ -382,7 +385,7 @@ static int f2fs_set_meta_page_dirty(struct page *page) if (!PageUptodate(page)) SetPageUptodate(page); if (!PageDirty(page)) { - f2fs_set_page_dirty_nobuffers(page); + __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META); SetPagePrivate(page); f2fs_trace_pid(page); @@ -455,20 +458,20 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) spin_unlock(&im->ino_lock); } -void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) +void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { /* add new dirty ino entry into list */ __add_ino_entry(sbi, ino, 0, type); } -void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) +void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { /* remove dirty ino entry from list */ __remove_ino_entry(sbi, ino, type); } /* mode should be APPEND_INO or UPDATE_INO */ -bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) +bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) { struct inode_management *im = &sbi->im[mode]; struct ino_entry *e; @@ -479,7 +482,7 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) return e ? true : false; } -void release_ino_entry(struct f2fs_sb_info *sbi, bool all) +void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all) { struct ino_entry *e, *tmp; int i; @@ -498,13 +501,13 @@ void release_ino_entry(struct f2fs_sb_info *sbi, bool all) } } -void set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, +void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, unsigned int devidx, int type) { __add_ino_entry(sbi, ino, devidx, type); } -bool is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, +bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, unsigned int devidx, int type) { struct inode_management *im = &sbi->im[type]; @@ -519,7 +522,7 @@ bool is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, return is_dirty; } -int acquire_orphan_inode(struct f2fs_sb_info *sbi) +int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi) { struct inode_management *im = &sbi->im[ORPHAN_INO]; int err = 0; @@ -542,7 +545,7 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi) return err; } -void release_orphan_inode(struct f2fs_sb_info *sbi) +void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi) { struct inode_management *im = &sbi->im[ORPHAN_INO]; @@ -552,14 +555,14 @@ void release_orphan_inode(struct f2fs_sb_info *sbi) spin_unlock(&im->ino_lock); } -void add_orphan_inode(struct inode *inode) +void f2fs_add_orphan_inode(struct inode *inode) { /* add new orphan ino entry into list */ __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO); - update_inode_page(inode); + f2fs_update_inode_page(inode); } -void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) { /* remove orphan entry from orphan list */ __remove_ino_entry(sbi, ino, ORPHAN_INO); @@ -569,7 +572,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) { struct inode *inode; struct node_info ni; - int err = acquire_orphan_inode(sbi); + int err = f2fs_acquire_orphan_inode(sbi); if (err) goto err_out; @@ -587,16 +590,17 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) } err = dquot_initialize(inode); - if (err) + if (err) { + iput(inode); goto err_out; + } - dquot_initialize(inode); clear_nlink(inode); /* truncate all the data during iput */ iput(inode); - get_node_info(sbi, ino, &ni); + f2fs_get_node_info(sbi, ino, &ni); /* ENOMEM was fully retried in f2fs_evict_inode. */ if (ni.blk_addr != NULL_ADDR) { @@ -614,7 +618,7 @@ err_out: return err; } -int recover_orphan_inodes(struct f2fs_sb_info *sbi) +int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) { block_t start_blk, orphan_blocks, i, j; unsigned int s_flags = sbi->sb->s_flags; @@ -642,10 +646,10 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi) start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi); - ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true); + f2fs_ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true); for (i = 0; i < orphan_blocks; i++) { - struct page *page = get_meta_page(sbi, start_blk + i); + struct page *page = f2fs_get_meta_page(sbi, start_blk + i); struct f2fs_orphan_block *orphan_blk; orphan_blk = (struct f2fs_orphan_block *)page_address(page); @@ -695,7 +699,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) /* loop for each orphan inode entry and write them in Jornal block */ list_for_each_entry(orphan, head, list) { if (!page) { - page = grab_meta_page(sbi, start_blk++); + page = f2fs_grab_meta_page(sbi, start_blk++); orphan_blk = (struct f2fs_orphan_block *)page_address(page); memset(orphan_blk, 0, sizeof(*orphan_blk)); @@ -737,7 +741,7 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr, size_t crc_offset = 0; __u32 crc = 0; - *cp_page = get_meta_page(sbi, cp_addr); + *cp_page = f2fs_get_meta_page(sbi, cp_addr); *cp_block = (struct f2fs_checkpoint *)page_address(*cp_page); crc_offset = le32_to_cpu((*cp_block)->checksum_offset); @@ -790,7 +794,7 @@ invalid_cp1: return NULL; } -int get_valid_checkpoint(struct f2fs_sb_info *sbi) +int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi) { struct f2fs_checkpoint *cp_block; struct f2fs_super_block *fsb = sbi->raw_super; @@ -834,7 +838,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi) memcpy(sbi->ckpt, cp_block, blk_size); /* Sanity checking of checkpoint */ - if (sanity_check_ckpt(sbi)) + if (f2fs_sanity_check_ckpt(sbi)) goto free_fail_no_cp; if (cur_page == cp1) @@ -853,7 +857,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi) void *sit_bitmap_ptr; unsigned char *ckpt = (unsigned char *)sbi->ckpt; - cur_page = get_meta_page(sbi, cp_blk_no + i); + cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i); sit_bitmap_ptr = page_address(cur_page); memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size); f2fs_put_page(cur_page, 1); @@ -898,7 +902,7 @@ static void __remove_dirty_inode(struct inode *inode, enum inode_type type) stat_dec_dirty_inode(F2FS_I_SB(inode), type); } -void update_dirty_page(struct inode *inode, struct page *page) +void f2fs_update_dirty_page(struct inode *inode, struct page *page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE; @@ -917,7 +921,7 @@ void update_dirty_page(struct inode *inode, struct page *page) f2fs_trace_pid(page); } -void remove_dirty_inode(struct inode *inode) +void f2fs_remove_dirty_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE; @@ -934,7 +938,7 @@ void remove_dirty_inode(struct inode *inode) spin_unlock(&sbi->inode_lock[type]); } -int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) +int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) { struct list_head *head; struct inode *inode; @@ -1017,7 +1021,7 @@ int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi) /* it's on eviction */ if (is_inode_flag_set(inode, FI_DIRTY_INODE)) - update_inode_page(inode); + f2fs_update_inode_page(inode); iput(inode); } } @@ -1057,7 +1061,7 @@ retry_flush_dents: /* write all the dirty dentry pages */ if (get_pages(sbi, F2FS_DIRTY_DENTS)) { f2fs_unlock_all(sbi); - err = sync_dirty_inodes(sbi, DIR_INODE); + err = f2fs_sync_dirty_inodes(sbi, DIR_INODE); if (err) goto out; cond_resched(); @@ -1085,7 +1089,9 @@ retry_flush_nodes: if (get_pages(sbi, F2FS_DIRTY_NODES)) { up_write(&sbi->node_write); - err = sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO); + atomic_inc(&sbi->wb_sync_req[NODE]); + err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO); + atomic_dec(&sbi->wb_sync_req[NODE]); if (err) { up_write(&sbi->node_change); f2fs_unlock_all(sbi); @@ -1179,10 +1185,10 @@ static void commit_checkpoint(struct f2fs_sb_info *sbi, /* * pagevec_lookup_tag and lock_page again will take - * some extra time. Therefore, update_meta_pages and - * sync_meta_pages are combined in this function. + * some extra time. Therefore, f2fs_update_meta_pages and + * f2fs_sync_meta_pages are combined in this function. */ - struct page *page = grab_meta_page(sbi, blk_addr); + struct page *page = f2fs_grab_meta_page(sbi, blk_addr); int err; memcpy(page_address(page), src, PAGE_SIZE); @@ -1220,7 +1226,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* Flush all the NAT/SIT pages */ while (get_pages(sbi, F2FS_DIRTY_META)) { - sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); + f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); if (unlikely(f2fs_cp_error(sbi))) return -EIO; } @@ -1229,7 +1235,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) * modify checkpoint * version number is already updated */ - ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi)); + ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi, true)); ckpt->free_segment_count = cpu_to_le32(free_segments(sbi)); for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { ckpt->cur_node_segno[i] = @@ -1249,7 +1255,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) } /* 2 cp + n data seg summary + orphan inode blocks */ - data_sum_blocks = npages_for_summary_flush(sbi, false); + data_sum_blocks = f2fs_npages_for_summary_flush(sbi, false); spin_lock_irqsave(&sbi->cp_lock, flags); if (data_sum_blocks < NR_CURSEG_DATA_TYPE) __set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); @@ -1294,22 +1300,23 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks; for (i = 0; i < nm_i->nat_bits_blocks; i++) - update_meta_page(sbi, nm_i->nat_bits + + f2fs_update_meta_page(sbi, nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS), blk + i); /* Flush all the NAT BITS pages */ while (get_pages(sbi, F2FS_DIRTY_META)) { - sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); + f2fs_sync_meta_pages(sbi, META, LONG_MAX, + FS_CP_META_IO); if (unlikely(f2fs_cp_error(sbi))) return -EIO; } } /* write out checkpoint buffer at block 0 */ - update_meta_page(sbi, ckpt, start_blk++); + f2fs_update_meta_page(sbi, ckpt, start_blk++); for (i = 1; i < 1 + cp_payload_blks; i++) - update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE, + f2fs_update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE, start_blk++); if (orphan_num) { @@ -1317,7 +1324,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) start_blk += orphan_blocks; } - write_data_summaries(sbi, start_blk); + f2fs_write_data_summaries(sbi, start_blk); start_blk += data_sum_blocks; /* Record write statistics in the hot node summary */ @@ -1328,7 +1335,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written); if (__remain_node_summaries(cpc->reason)) { - write_node_summaries(sbi, start_blk); + f2fs_write_node_summaries(sbi, start_blk); start_blk += NR_CURSEG_NODE_TYPE; } @@ -1337,7 +1344,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) percpu_counter_set(&sbi->alloc_valid_block_count, 0); /* Here, we have one bio having CP pack except cp pack 2 page */ - sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); + f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); /* wait for previous submitted meta pages writeback */ wait_on_all_pages_writeback(sbi); @@ -1354,7 +1361,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) commit_checkpoint(sbi, ckpt, start_blk); wait_on_all_pages_writeback(sbi); - release_ino_entry(sbi, false); + f2fs_release_ino_entry(sbi, false); if (unlikely(f2fs_cp_error(sbi))) return -EIO; @@ -1379,7 +1386,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* * We guarantee that this checkpoint procedure will not fail. */ -int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) +int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); unsigned long long ckpt_ver; @@ -1412,7 +1419,7 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* this is the case of multiple fstrims without any changes */ if (cpc->reason & CP_DISCARD) { - if (!exist_trim_candidates(sbi, cpc)) { + if (!f2fs_exist_trim_candidates(sbi, cpc)) { unblock_operations(sbi); goto out; } @@ -1420,8 +1427,8 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (NM_I(sbi)->dirty_nat_cnt == 0 && SIT_I(sbi)->dirty_sentries == 0 && prefree_segments(sbi) == 0) { - flush_sit_entries(sbi, cpc); - clear_prefree_segments(sbi, cpc); + f2fs_flush_sit_entries(sbi, cpc); + f2fs_clear_prefree_segments(sbi, cpc); unblock_operations(sbi); goto out; } @@ -1436,15 +1443,15 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver); /* write cached NAT/SIT entries to NAT/SIT area */ - flush_nat_entries(sbi, cpc); - flush_sit_entries(sbi, cpc); + f2fs_flush_nat_entries(sbi, cpc); + f2fs_flush_sit_entries(sbi, cpc); /* unlock all the fs_lock[] in do_checkpoint() */ err = do_checkpoint(sbi, cpc); if (err) - release_discard_addrs(sbi); + f2fs_release_discard_addrs(sbi); else - clear_prefree_segments(sbi, cpc); + f2fs_clear_prefree_segments(sbi, cpc); unblock_operations(sbi); stat_inc_cp_count(sbi->stat_info); @@ -1461,7 +1468,7 @@ out: return err; } -void init_ino_entry_info(struct f2fs_sb_info *sbi) +void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi) { int i; @@ -1479,23 +1486,23 @@ void init_ino_entry_info(struct f2fs_sb_info *sbi) F2FS_ORPHANS_PER_BLOCK; } -int __init create_checkpoint_caches(void) +int __init f2fs_create_checkpoint_caches(void) { ino_entry_slab = f2fs_kmem_cache_create("f2fs_ino_entry", sizeof(struct ino_entry)); if (!ino_entry_slab) return -ENOMEM; - inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry", + f2fs_inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry", sizeof(struct inode_entry)); - if (!inode_entry_slab) { + if (!f2fs_inode_entry_slab) { kmem_cache_destroy(ino_entry_slab); return -ENOMEM; } return 0; } -void destroy_checkpoint_caches(void) +void f2fs_destroy_checkpoint_caches(void) { kmem_cache_destroy(ino_entry_slab); - kmem_cache_destroy(inode_entry_slab); + kmem_cache_destroy(f2fs_inode_entry_slab); } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 02237d4d91f5..8f931d699287 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -19,8 +19,6 @@ #include <linux/bio.h> #include <linux/prefetch.h> #include <linux/uio.h> -#include <linux/mm.h> -#include <linux/memcontrol.h> #include <linux/cleancache.h> #include <linux/sched/signal.h> @@ -30,6 +28,11 @@ #include "trace.h" #include <trace/events/f2fs.h> +#define NUM_PREALLOC_POST_READ_CTXS 128 + +static struct kmem_cache *bio_post_read_ctx_cache; +static mempool_t *bio_post_read_ctx_pool; + static bool __is_cp_guaranteed(struct page *page) { struct address_space *mapping = page->mapping; @@ -45,16 +48,84 @@ static bool __is_cp_guaranteed(struct page *page) if (inode->i_ino == F2FS_META_INO(sbi) || inode->i_ino == F2FS_NODE_INO(sbi) || S_ISDIR(inode->i_mode) || + (S_ISREG(inode->i_mode) && + is_inode_flag_set(inode, FI_ATOMIC_FILE)) || is_cold_data(page)) return true; return false; } -static void f2fs_read_end_io(struct bio *bio) +/* postprocessing steps for read bios */ +enum bio_post_read_step { + STEP_INITIAL = 0, + STEP_DECRYPT, +}; + +struct bio_post_read_ctx { + struct bio *bio; + struct work_struct work; + unsigned int cur_step; + unsigned int enabled_steps; +}; + +static void __read_end_io(struct bio *bio) { - struct bio_vec *bvec; + struct page *page; + struct bio_vec *bv; int i; + bio_for_each_segment_all(bv, bio, i) { + page = bv->bv_page; + + /* PG_error was set if any post_read step failed */ + if (bio->bi_status || PageError(page)) { + ClearPageUptodate(page); + SetPageError(page); + } else { + SetPageUptodate(page); + } + unlock_page(page); + } + if (bio->bi_private) + mempool_free(bio->bi_private, bio_post_read_ctx_pool); + bio_put(bio); +} + +static void bio_post_read_processing(struct bio_post_read_ctx *ctx); + +static void decrypt_work(struct work_struct *work) +{ + struct bio_post_read_ctx *ctx = + container_of(work, struct bio_post_read_ctx, work); + + fscrypt_decrypt_bio(ctx->bio); + + bio_post_read_processing(ctx); +} + +static void bio_post_read_processing(struct bio_post_read_ctx *ctx) +{ + switch (++ctx->cur_step) { + case STEP_DECRYPT: + if (ctx->enabled_steps & (1 << STEP_DECRYPT)) { + INIT_WORK(&ctx->work, decrypt_work); + fscrypt_enqueue_decrypt_work(&ctx->work); + return; + } + ctx->cur_step++; + /* fall-through */ + default: + __read_end_io(ctx->bio); + } +} + +static bool f2fs_bio_post_read_required(struct bio *bio) +{ + return bio->bi_private && !bio->bi_status; +} + +static void f2fs_read_end_io(struct bio *bio) +{ #ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(F2FS_P_SB(bio_first_page_all(bio)), FAULT_IO)) { f2fs_show_injection_info(FAULT_IO); @@ -62,28 +133,15 @@ static void f2fs_read_end_io(struct bio *bio) } #endif - if (f2fs_bio_encrypted(bio)) { - if (bio->bi_status) { - fscrypt_release_ctx(bio->bi_private); - } else { - fscrypt_decrypt_bio_pages(bio->bi_private, bio); - return; - } - } - - bio_for_each_segment_all(bvec, bio, i) { - struct page *page = bvec->bv_page; + if (f2fs_bio_post_read_required(bio)) { + struct bio_post_read_ctx *ctx = bio->bi_private; - if (!bio->bi_status) { - if (!PageUptodate(page)) - SetPageUptodate(page); - } else { - ClearPageUptodate(page); - SetPageError(page); - } - unlock_page(page); + ctx->cur_step = STEP_INITIAL; + bio_post_read_processing(ctx); + return; } - bio_put(bio); + + __read_end_io(bio); } static void f2fs_write_end_io(struct bio *bio) @@ -189,7 +247,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, } else { bio->bi_end_io = f2fs_write_end_io; bio->bi_private = sbi; - bio->bi_write_hint = io_type_to_rw_hint(sbi, type, temp); + bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi, type, temp); } if (wbc) wbc_init_bio(wbc, bio); @@ -404,13 +462,12 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) return 0; } -int f2fs_submit_page_write(struct f2fs_io_info *fio) +void f2fs_submit_page_write(struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp; struct page *bio_page; - int err = 0; f2fs_bug_on(sbi, is_read_io(fio->op)); @@ -420,7 +477,7 @@ next: spin_lock(&io->io_lock); if (list_empty(&io->io_list)) { spin_unlock(&io->io_lock); - goto out_fail; + goto out; } fio = list_first_entry(&io->io_list, struct f2fs_io_info, list); @@ -428,7 +485,7 @@ next: spin_unlock(&io->io_lock); } - if (fio->old_blkaddr != NEW_ADDR) + if (is_valid_blkaddr(fio->old_blkaddr)) verify_block_addr(fio, fio->old_blkaddr); verify_block_addr(fio, fio->new_blkaddr); @@ -447,9 +504,9 @@ alloc_new: if (io->bio == NULL) { if ((fio->type == DATA || fio->type == NODE) && fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) { - err = -EAGAIN; dec_page_count(sbi, WB_DATA_TYPE(bio_page)); - goto out_fail; + fio->retry = true; + goto skip; } io->bio = __bio_alloc(sbi, fio->new_blkaddr, fio->io_wbc, BIO_MAX_PAGES, false, @@ -469,41 +526,44 @@ alloc_new: f2fs_trace_ios(fio, 0); trace_f2fs_submit_page_write(fio->page, fio); - +skip: if (fio->in_list) goto next; -out_fail: +out: up_write(&io->io_rwsem); - return err; } static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, unsigned nr_pages) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct fscrypt_ctx *ctx = NULL; struct bio *bio; - - if (f2fs_encrypted_file(inode)) { - ctx = fscrypt_get_ctx(inode, GFP_NOFS); - if (IS_ERR(ctx)) - return ERR_CAST(ctx); - - /* wait the page to be moved by cleaning */ - f2fs_wait_on_block_writeback(sbi, blkaddr); - } + struct bio_post_read_ctx *ctx; + unsigned int post_read_steps = 0; bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false); - if (!bio) { - if (ctx) - fscrypt_release_ctx(ctx); + if (!bio) return ERR_PTR(-ENOMEM); - } f2fs_target_device(sbi, blkaddr, bio); bio->bi_end_io = f2fs_read_end_io; - bio->bi_private = ctx; bio_set_op_attrs(bio, REQ_OP_READ, 0); + if (f2fs_encrypted_file(inode)) + post_read_steps |= 1 << STEP_DECRYPT; + if (post_read_steps) { + ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS); + if (!ctx) { + bio_put(bio); + return ERR_PTR(-ENOMEM); + } + ctx->bio = bio; + ctx->enabled_steps = post_read_steps; + bio->bi_private = ctx; + + /* wait the page to be moved by cleaning */ + f2fs_wait_on_block_writeback(sbi, blkaddr); + } + return bio; } @@ -544,7 +604,7 @@ static void __set_data_blkaddr(struct dnode_of_data *dn) * ->node_page * update block addresses in the node page */ -void set_data_blkaddr(struct dnode_of_data *dn) +void f2fs_set_data_blkaddr(struct dnode_of_data *dn) { f2fs_wait_on_page_writeback(dn->node_page, NODE, true); __set_data_blkaddr(dn); @@ -555,12 +615,12 @@ void set_data_blkaddr(struct dnode_of_data *dn) void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { dn->data_blkaddr = blkaddr; - set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn); f2fs_update_extent_cache(dn); } /* dn->ofs_in_node will be returned with up-to-date last block pointer */ -int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) +int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); int err; @@ -594,12 +654,12 @@ int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) } /* Should keep dn->ofs_in_node unchanged */ -int reserve_new_block(struct dnode_of_data *dn) +int f2fs_reserve_new_block(struct dnode_of_data *dn) { unsigned int ofs_in_node = dn->ofs_in_node; int ret; - ret = reserve_new_blocks(dn, 1); + ret = f2fs_reserve_new_blocks(dn, 1); dn->ofs_in_node = ofs_in_node; return ret; } @@ -609,12 +669,12 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) bool need_put = dn->inode_page ? false : true; int err; - err = get_dnode_of_data(dn, index, ALLOC_NODE); + err = f2fs_get_dnode_of_data(dn, index, ALLOC_NODE); if (err) return err; if (dn->data_blkaddr == NULL_ADDR) - err = reserve_new_block(dn); + err = f2fs_reserve_new_block(dn); if (err || need_put) f2fs_put_dnode(dn); return err; @@ -633,7 +693,7 @@ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index) return f2fs_reserve_block(dn, index); } -struct page *get_read_data_page(struct inode *inode, pgoff_t index, +struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, int op_flags, bool for_write) { struct address_space *mapping = inode->i_mapping; @@ -652,7 +712,7 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index, } set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); if (err) goto put_err; f2fs_put_dnode(&dn); @@ -671,7 +731,8 @@ got_it: * A new dentry page is allocated but not able to be written, since its * new inode page couldn't be allocated due to -ENOSPC. * In such the case, its blkaddr can be remained as NEW_ADDR. - * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata. + * see, f2fs_add_link -> f2fs_get_new_data_page -> + * f2fs_init_inode_metadata. */ if (dn.data_blkaddr == NEW_ADDR) { zero_user_segment(page, 0, PAGE_SIZE); @@ -691,7 +752,7 @@ put_err: return ERR_PTR(err); } -struct page *find_data_page(struct inode *inode, pgoff_t index) +struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index) { struct address_space *mapping = inode->i_mapping; struct page *page; @@ -701,7 +762,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index) return page; f2fs_put_page(page, 0); - page = get_read_data_page(inode, index, 0, false); + page = f2fs_get_read_data_page(inode, index, 0, false); if (IS_ERR(page)) return page; @@ -721,13 +782,13 @@ struct page *find_data_page(struct inode *inode, pgoff_t index) * Because, the callers, functions in dir.c and GC, should be able to know * whether this page exists or not. */ -struct page *get_lock_data_page(struct inode *inode, pgoff_t index, +struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, bool for_write) { struct address_space *mapping = inode->i_mapping; struct page *page; repeat: - page = get_read_data_page(inode, index, 0, for_write); + page = f2fs_get_read_data_page(inode, index, 0, for_write); if (IS_ERR(page)) return page; @@ -753,7 +814,7 @@ repeat: * Note that, ipage is set only by make_empty_dir, and if any error occur, * ipage should be released by this function. */ -struct page *get_new_data_page(struct inode *inode, +struct page *f2fs_get_new_data_page(struct inode *inode, struct page *ipage, pgoff_t index, bool new_i_size) { struct address_space *mapping = inode->i_mapping; @@ -792,7 +853,7 @@ struct page *get_new_data_page(struct inode *inode, /* if ipage exists, blkaddr should be NEW_ADDR */ f2fs_bug_on(F2FS_I_SB(inode), ipage); - page = get_lock_data_page(inode, index, true); + page = f2fs_get_lock_data_page(inode, index, true); if (IS_ERR(page)) return page; } @@ -824,15 +885,15 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) return err; alloc: - get_node_info(sbi, dn->nid, &ni); + f2fs_get_node_info(sbi, dn->nid, &ni); set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); - allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr, + f2fs_allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr, &sum, seg_type, NULL, false); - set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn); /* update i_size */ - fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + + fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + dn->ofs_in_node; if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT)) f2fs_i_size_write(dn->inode, @@ -870,7 +931,7 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from) map.m_seg_type = NO_CHECK_TYPE; if (direct_io) { - map.m_seg_type = rw_hint_to_seg_type(iocb->ki_hint); + map.m_seg_type = f2fs_rw_hint_to_seg_type(iocb->ki_hint); flag = f2fs_force_buffered_io(inode, WRITE) ? F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO; @@ -960,7 +1021,7 @@ next_dnode: /* When reading holes, we need its node page */ set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, pgofs, mode); + err = f2fs_get_dnode_of_data(&dn, pgofs, mode); if (err) { if (flag == F2FS_GET_BLOCK_BMAP) map->m_pblk = 0; @@ -968,10 +1029,10 @@ next_dnode: err = 0; if (map->m_next_pgofs) *map->m_next_pgofs = - get_next_page_offset(&dn, pgofs); + f2fs_get_next_page_offset(&dn, pgofs); if (map->m_next_extent) *map->m_next_extent = - get_next_page_offset(&dn, pgofs); + f2fs_get_next_page_offset(&dn, pgofs); } goto unlock_out; } @@ -984,7 +1045,7 @@ next_dnode: next_block: blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); - if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) { + if (!is_valid_blkaddr(blkaddr)) { if (create) { if (unlikely(f2fs_cp_error(sbi))) { err = -EIO; @@ -1057,7 +1118,7 @@ skip: (pgofs == end || dn.ofs_in_node == end_offset)) { dn.ofs_in_node = ofs_in_node; - err = reserve_new_blocks(&dn, prealloc); + err = f2fs_reserve_new_blocks(&dn, prealloc); if (err) goto sync_out; @@ -1176,7 +1237,7 @@ static int get_data_block_dio(struct inode *inode, sector_t iblock, { return __get_data_block(inode, iblock, bh_result, create, F2FS_GET_BLOCK_DEFAULT, NULL, - rw_hint_to_seg_type( + f2fs_rw_hint_to_seg_type( inode->i_write_hint)); } @@ -1221,7 +1282,7 @@ static int f2fs_xattr_fiemap(struct inode *inode, if (!page) return -ENOMEM; - get_node_info(sbi, inode->i_ino, &ni); + f2fs_get_node_info(sbi, inode->i_ino, &ni); phys = (__u64)blk_to_logical(inode, ni.blk_addr); offset = offsetof(struct f2fs_inode, i_addr) + @@ -1248,7 +1309,7 @@ static int f2fs_xattr_fiemap(struct inode *inode, if (!page) return -ENOMEM; - get_node_info(sbi, xnid, &ni); + f2fs_get_node_info(sbi, xnid, &ni); phys = (__u64)blk_to_logical(inode, ni.blk_addr); len = inode->i_sb->s_blocksize; @@ -1525,7 +1586,7 @@ static int encrypt_one_page(struct f2fs_io_info *fio) if (!f2fs_encrypted_file(inode)) return 0; - /* wait for GCed encrypted page writeback */ + /* wait for GCed page writeback via META_MAPPING */ f2fs_wait_on_block_writeback(fio->sbi, fio->old_blkaddr); retry_encrypt: @@ -1552,12 +1613,12 @@ static inline bool check_inplace_update_policy(struct inode *inode, if (policy & (0x1 << F2FS_IPU_FORCE)) return true; - if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi)) + if (policy & (0x1 << F2FS_IPU_SSR) && f2fs_need_SSR(sbi)) return true; if (policy & (0x1 << F2FS_IPU_UTIL) && utilization(sbi) > SM_I(sbi)->min_ipu_util) return true; - if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && need_SSR(sbi) && + if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && f2fs_need_SSR(sbi) && utilization(sbi) > SM_I(sbi)->min_ipu_util) return true; @@ -1578,7 +1639,7 @@ static inline bool check_inplace_update_policy(struct inode *inode, return false; } -bool should_update_inplace(struct inode *inode, struct f2fs_io_info *fio) +bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio) { if (f2fs_is_pinned_file(inode)) return true; @@ -1590,7 +1651,7 @@ bool should_update_inplace(struct inode *inode, struct f2fs_io_info *fio) return check_inplace_update_policy(inode, fio); } -bool should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) +bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -1613,22 +1674,13 @@ static inline bool need_inplace_update(struct f2fs_io_info *fio) { struct inode *inode = fio->page->mapping->host; - if (should_update_outplace(inode, fio)) + if (f2fs_should_update_outplace(inode, fio)) return false; - return should_update_inplace(inode, fio); + return f2fs_should_update_inplace(inode, fio); } -static inline bool valid_ipu_blkaddr(struct f2fs_io_info *fio) -{ - if (fio->old_blkaddr == NEW_ADDR) - return false; - if (fio->old_blkaddr == NULL_ADDR) - return false; - return true; -} - -int do_write_data_page(struct f2fs_io_info *fio) +int f2fs_do_write_data_page(struct f2fs_io_info *fio) { struct page *page = fio->page; struct inode *inode = page->mapping->host; @@ -1642,7 +1694,7 @@ int do_write_data_page(struct f2fs_io_info *fio) f2fs_lookup_extent_cache(inode, page->index, &ei)) { fio->old_blkaddr = ei.blk + page->index - ei.fofs; - if (valid_ipu_blkaddr(fio)) { + if (is_valid_blkaddr(fio->old_blkaddr)) { ipu_force = true; fio->need_lock = LOCK_DONE; goto got_it; @@ -1653,7 +1705,7 @@ int do_write_data_page(struct f2fs_io_info *fio) if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi)) return -EAGAIN; - err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE); if (err) goto out; @@ -1669,16 +1721,18 @@ got_it: * If current allocation needs SSR, * it had better in-place writes for updated data. */ - if (ipu_force || (valid_ipu_blkaddr(fio) && need_inplace_update(fio))) { + if (ipu_force || (is_valid_blkaddr(fio->old_blkaddr) && + need_inplace_update(fio))) { err = encrypt_one_page(fio); if (err) goto out_writepage; set_page_writeback(page); + ClearPageError(page); f2fs_put_dnode(&dn); if (fio->need_lock == LOCK_REQ) f2fs_unlock_op(fio->sbi); - err = rewrite_data_page(fio); + err = f2fs_inplace_write_data(fio); trace_f2fs_do_write_data_page(fio->page, IPU); set_inode_flag(inode, FI_UPDATE_WRITE); return err; @@ -1697,9 +1751,10 @@ got_it: goto out_writepage; set_page_writeback(page); + ClearPageError(page); /* LFS mode write path */ - write_data_page(&dn, fio); + f2fs_outplace_write_data(&dn, fio); trace_f2fs_do_write_data_page(page, OPU); set_inode_flag(inode, FI_APPEND_WRITE); if (page->index == 0) @@ -1745,6 +1800,12 @@ static int __write_data_page(struct page *page, bool *submitted, /* we should bypass data pages to proceed the kworkder jobs */ if (unlikely(f2fs_cp_error(sbi))) { mapping_set_error(page->mapping, -EIO); + /* + * don't drop any dirty dentry pages for keeping lastest + * directory structure. + */ + if (S_ISDIR(inode->i_mode)) + goto redirty_out; goto out; } @@ -1769,13 +1830,13 @@ write: /* we should not write 0'th page having journal header */ if (f2fs_is_volatile_file(inode) && (!page->index || (!wbc->for_reclaim && - available_free_memory(sbi, BASE_CHECK)))) + f2fs_available_free_memory(sbi, BASE_CHECK)))) goto redirty_out; /* Dentry blocks are controlled by checkpoint */ if (S_ISDIR(inode->i_mode)) { fio.need_lock = LOCK_DONE; - err = do_write_data_page(&fio); + err = f2fs_do_write_data_page(&fio); goto done; } @@ -1794,10 +1855,10 @@ write: } if (err == -EAGAIN) { - err = do_write_data_page(&fio); + err = f2fs_do_write_data_page(&fio); if (err == -EAGAIN) { fio.need_lock = LOCK_REQ; - err = do_write_data_page(&fio); + err = f2fs_do_write_data_page(&fio); } } @@ -1822,7 +1883,7 @@ out: if (wbc->for_reclaim) { f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA); clear_inode_flag(inode, FI_HOT_DATA); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); submitted = NULL; } @@ -1842,7 +1903,13 @@ out: redirty_out: redirty_page_for_writepage(wbc, page); - if (!err) + /* + * pageout() in MM traslates EAGAIN, so calls handle_write_error() + * -> mapping_set_error() -> set_bit(AS_EIO, ...). + * file_write_and_wait_range() will see EIO error, which is critical + * to return value of fsync() followed by atomic_write failure to user. + */ + if (!err || wbc->for_reclaim) return AOP_WRITEPAGE_ACTIVATE; unlock_page(page); return err; @@ -1866,6 +1933,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping, int ret = 0; int done = 0; struct pagevec pvec; + struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); int nr_pages; pgoff_t uninitialized_var(writeback_index); pgoff_t index; @@ -1919,6 +1987,13 @@ retry: struct page *page = pvec.pages[i]; bool submitted = false; + /* give a priority to WB_SYNC threads */ + if (atomic_read(&sbi->wb_sync_req[DATA]) && + wbc->sync_mode == WB_SYNC_NONE) { + done = 1; + break; + } + done_index = page->index; retry_write: lock_page(page); @@ -1973,9 +2048,7 @@ continue_unlock: last_idx = page->index; } - /* give a priority to WB_SYNC threads */ - if ((atomic_read(&F2FS_M_SB(mapping)->wb_sync_req) || - --wbc->nr_to_write <= 0) && + if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) { done = 1; break; @@ -2001,7 +2074,7 @@ continue_unlock: return ret; } -int __f2fs_write_data_pages(struct address_space *mapping, +static int __f2fs_write_data_pages(struct address_space *mapping, struct writeback_control *wbc, enum iostat_type io_type) { @@ -2024,7 +2097,7 @@ int __f2fs_write_data_pages(struct address_space *mapping, if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE && get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) && - available_free_memory(sbi, DIRTY_DENTS)) + f2fs_available_free_memory(sbi, DIRTY_DENTS)) goto skip_write; /* skip writing during file defragment */ @@ -2035,8 +2108,8 @@ int __f2fs_write_data_pages(struct address_space *mapping, /* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */ if (wbc->sync_mode == WB_SYNC_ALL) - atomic_inc(&sbi->wb_sync_req); - else if (atomic_read(&sbi->wb_sync_req)) + atomic_inc(&sbi->wb_sync_req[DATA]); + else if (atomic_read(&sbi->wb_sync_req[DATA])) goto skip_write; blk_start_plug(&plug); @@ -2044,13 +2117,13 @@ int __f2fs_write_data_pages(struct address_space *mapping, blk_finish_plug(&plug); if (wbc->sync_mode == WB_SYNC_ALL) - atomic_dec(&sbi->wb_sync_req); + atomic_dec(&sbi->wb_sync_req[DATA]); /* * if some pages were truncated, we cannot guarantee its mapping->host * to detect pending bios. */ - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); return ret; skip_write: @@ -2077,7 +2150,7 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to) if (to > i_size) { down_write(&F2FS_I(inode)->i_mmap_sem); truncate_pagecache(inode, i_size); - truncate_blocks(inode, i_size, true); + f2fs_truncate_blocks(inode, i_size, true); up_write(&F2FS_I(inode)->i_mmap_sem); } } @@ -2109,7 +2182,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi, } restart: /* check inline_data */ - ipage = get_node_page(sbi, inode->i_ino); + ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto unlock_out; @@ -2119,7 +2192,7 @@ restart: if (f2fs_has_inline_data(inode)) { if (pos + len <= MAX_INLINE_DATA(inode)) { - read_inline_data(page, ipage); + f2fs_do_read_inline_data(page, ipage); set_inode_flag(inode, FI_DATA_EXIST); if (inode->i_nlink) set_inline_node(ipage); @@ -2137,7 +2210,7 @@ restart: dn.data_blkaddr = ei.blk + index - ei.fofs; } else { /* hole case */ - err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); if (err || dn.data_blkaddr == NULL_ADDR) { f2fs_put_dnode(&dn); __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, @@ -2174,7 +2247,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, trace_f2fs_write_begin(inode, pos, len, flags); if (f2fs_is_atomic_file(inode) && - !available_free_memory(sbi, INMEM_PAGES)) { + !f2fs_available_free_memory(sbi, INMEM_PAGES)) { err = -ENOMEM; drop_atomic = true; goto fail; @@ -2222,8 +2295,8 @@ repeat: f2fs_wait_on_page_writeback(page, DATA, false); - /* wait for GCed encrypted page writeback */ - if (f2fs_encrypted_file(inode)) + /* wait for GCed page writeback via META_MAPPING */ + if (f2fs_post_read_required(inode)) f2fs_wait_on_block_writeback(sbi, blkaddr); if (len == PAGE_SIZE || PageUptodate(page)) @@ -2258,7 +2331,7 @@ fail: f2fs_put_page(page, 1); f2fs_write_failed(mapping, pos + len); if (drop_atomic) - drop_inmem_pages_all(sbi); + f2fs_drop_inmem_pages_all(sbi, false); return err; } @@ -2333,17 +2406,17 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) if (rw == WRITE && whint_mode == WHINT_MODE_OFF) iocb->ki_hint = WRITE_LIFE_NOT_SET; - if (!down_read_trylock(&F2FS_I(inode)->dio_rwsem[rw])) { + if (!down_read_trylock(&F2FS_I(inode)->i_gc_rwsem[rw])) { if (iocb->ki_flags & IOCB_NOWAIT) { iocb->ki_hint = hint; err = -EAGAIN; goto out; } - down_read(&F2FS_I(inode)->dio_rwsem[rw]); + down_read(&F2FS_I(inode)->i_gc_rwsem[rw]); } err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio); - up_read(&F2FS_I(inode)->dio_rwsem[rw]); + up_read(&F2FS_I(inode)->i_gc_rwsem[rw]); if (rw == WRITE) { if (whint_mode == WHINT_MODE_OFF) @@ -2380,13 +2453,13 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, dec_page_count(sbi, F2FS_DIRTY_NODES); } else { inode_dec_dirty_pages(inode); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); } } /* This is atomic written page, keep Private */ if (IS_ATOMIC_WRITTEN_PAGE(page)) - return drop_inmem_page(inode, page); + return f2fs_drop_inmem_page(inode, page); set_page_private(page, 0); ClearPagePrivate(page); @@ -2407,35 +2480,6 @@ int f2fs_release_page(struct page *page, gfp_t wait) return 1; } -/* - * This was copied from __set_page_dirty_buffers which gives higher performance - * in very high speed storages. (e.g., pmem) - */ -void f2fs_set_page_dirty_nobuffers(struct page *page) -{ - struct address_space *mapping = page->mapping; - unsigned long flags; - - if (unlikely(!mapping)) - return; - - spin_lock(&mapping->private_lock); - lock_page_memcg(page); - SetPageDirty(page); - spin_unlock(&mapping->private_lock); - - xa_lock_irqsave(&mapping->i_pages, flags); - WARN_ON_ONCE(!PageUptodate(page)); - account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->i_pages, - page_index(page), PAGECACHE_TAG_DIRTY); - xa_unlock_irqrestore(&mapping->i_pages, flags); - unlock_page_memcg(page); - - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - return; -} - static int f2fs_set_data_page_dirty(struct page *page) { struct address_space *mapping = page->mapping; @@ -2448,7 +2492,7 @@ static int f2fs_set_data_page_dirty(struct page *page) if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) { if (!IS_ATOMIC_WRITTEN_PAGE(page)) { - register_inmem_page(inode, page); + f2fs_register_inmem_page(inode, page); return 1; } /* @@ -2459,8 +2503,8 @@ static int f2fs_set_data_page_dirty(struct page *page) } if (!PageDirty(page)) { - f2fs_set_page_dirty_nobuffers(page); - update_dirty_page(inode, page); + __set_page_dirty_nobuffers(page); + f2fs_update_dirty_page(inode, page); return 1; } return 0; @@ -2555,3 +2599,38 @@ const struct address_space_operations f2fs_dblock_aops = { .migratepage = f2fs_migrate_page, #endif }; + +void f2fs_clear_radix_tree_dirty_tag(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + unsigned long flags; + + xa_lock_irqsave(&mapping->i_pages, flags); + radix_tree_tag_clear(&mapping->i_pages, page_index(page), + PAGECACHE_TAG_DIRTY); + xa_unlock_irqrestore(&mapping->i_pages, flags); +} + +int __init f2fs_init_post_read_processing(void) +{ + bio_post_read_ctx_cache = KMEM_CACHE(bio_post_read_ctx, 0); + if (!bio_post_read_ctx_cache) + goto fail; + bio_post_read_ctx_pool = + mempool_create_slab_pool(NUM_PREALLOC_POST_READ_CTXS, + bio_post_read_ctx_cache); + if (!bio_post_read_ctx_pool) + goto fail_free_cache; + return 0; + +fail_free_cache: + kmem_cache_destroy(bio_post_read_ctx_cache); +fail: + return -ENOMEM; +} + +void __exit f2fs_destroy_post_read_processing(void) +{ + mempool_destroy(bio_post_read_ctx_pool); + kmem_cache_destroy(bio_post_read_ctx_cache); +} diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index a66107b5cfff..2d65e77ae5cf 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -104,6 +104,8 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->avail_nids = NM_I(sbi)->available_nids; si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID]; si->bg_gc = sbi->bg_gc; + si->skipped_atomic_files[BG_GC] = sbi->skipped_atomic_files[BG_GC]; + si->skipped_atomic_files[FG_GC] = sbi->skipped_atomic_files[FG_GC]; si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg) * 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg) / 2; @@ -342,6 +344,10 @@ static int stat_show(struct seq_file *s, void *v) si->bg_data_blks); seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks, si->bg_node_blks); + seq_printf(s, "Skipped : atomic write %llu (%llu)\n", + si->skipped_atomic_files[BG_GC] + + si->skipped_atomic_files[FG_GC], + si->skipped_atomic_files[BG_GC]); seq_puts(s, "\nExtent Cache:\n"); seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n", si->hit_largest, si->hit_cached, diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 8c9c2f31b253..7f955c4e86a4 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -60,12 +60,12 @@ static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = { [S_IFLNK >> S_SHIFT] = F2FS_FT_SYMLINK, }; -void set_de_type(struct f2fs_dir_entry *de, umode_t mode) +static void set_de_type(struct f2fs_dir_entry *de, umode_t mode) { de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT]; } -unsigned char get_de_type(struct f2fs_dir_entry *de) +unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de) { if (de->file_type < F2FS_FT_MAX) return f2fs_filetype_table[de->file_type]; @@ -97,14 +97,14 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page); make_dentry_ptr_block(NULL, &d, dentry_blk); - de = find_target_dentry(fname, namehash, max_slots, &d); + de = f2fs_find_target_dentry(fname, namehash, max_slots, &d); if (de) *res_page = dentry_page; return de; } -struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname, +struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname, f2fs_hash_t namehash, int *max_slots, struct f2fs_dentry_ptr *d) { @@ -171,7 +171,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, for (; bidx < end_block; bidx++) { /* no need to allocate new dentry pages to all the indices */ - dentry_page = find_data_page(dir, bidx); + dentry_page = f2fs_find_data_page(dir, bidx); if (IS_ERR(dentry_page)) { if (PTR_ERR(dentry_page) == -ENOENT) { room = true; @@ -210,7 +210,7 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, if (f2fs_has_inline_dentry(dir)) { *res_page = NULL; - de = find_in_inline_dir(dir, fname, res_page); + de = f2fs_find_in_inline_dir(dir, fname, res_page); goto out; } @@ -319,7 +319,7 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage) set_page_dirty(ipage); } -void do_make_empty_dir(struct inode *inode, struct inode *parent, +void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent, struct f2fs_dentry_ptr *d) { struct qstr dot = QSTR_INIT(".", 1); @@ -340,23 +340,23 @@ static int make_empty_dir(struct inode *inode, struct f2fs_dentry_ptr d; if (f2fs_has_inline_dentry(inode)) - return make_empty_inline_dir(inode, parent, page); + return f2fs_make_empty_inline_dir(inode, parent, page); - dentry_page = get_new_data_page(inode, page, 0, true); + dentry_page = f2fs_get_new_data_page(inode, page, 0, true); if (IS_ERR(dentry_page)) return PTR_ERR(dentry_page); dentry_blk = page_address(dentry_page); make_dentry_ptr_block(NULL, &d, dentry_blk); - do_make_empty_dir(inode, parent, &d); + f2fs_do_make_empty_dir(inode, parent, &d); set_page_dirty(dentry_page); f2fs_put_page(dentry_page, 1); return 0; } -struct page *init_inode_metadata(struct inode *inode, struct inode *dir, +struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir, const struct qstr *new_name, const struct qstr *orig_name, struct page *dpage) { @@ -365,7 +365,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, int err; if (is_inode_flag_set(inode, FI_NEW_INODE)) { - page = new_inode_page(inode); + page = f2fs_new_inode_page(inode); if (IS_ERR(page)) return page; @@ -395,7 +395,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, goto put_error; } } else { - page = get_node_page(F2FS_I_SB(dir), inode->i_ino); + page = f2fs_get_node_page(F2FS_I_SB(dir), inode->i_ino); if (IS_ERR(page)) return page; } @@ -418,19 +418,19 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, * we should remove this inode from orphan list. */ if (inode->i_nlink == 0) - remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino); + f2fs_remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino); f2fs_i_links_write(inode, true); } return page; put_error: clear_nlink(inode); - update_inode(inode, page); + f2fs_update_inode(inode, page); f2fs_put_page(page, 1); return ERR_PTR(err); } -void update_parent_metadata(struct inode *dir, struct inode *inode, +void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode, unsigned int current_depth) { if (inode && is_inode_flag_set(inode, FI_NEW_INODE)) { @@ -448,7 +448,7 @@ void update_parent_metadata(struct inode *dir, struct inode *inode, clear_inode_flag(inode, FI_INC_LINK); } -int room_for_filename(const void *bitmap, int slots, int max_slots) +int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots) { int bit_start = 0; int zero_start, zero_end; @@ -537,12 +537,12 @@ start: (le32_to_cpu(dentry_hash) % nbucket)); for (block = bidx; block <= (bidx + nblock - 1); block++) { - dentry_page = get_new_data_page(dir, NULL, block, true); + dentry_page = f2fs_get_new_data_page(dir, NULL, block, true); if (IS_ERR(dentry_page)) return PTR_ERR(dentry_page); dentry_blk = page_address(dentry_page); - bit_pos = room_for_filename(&dentry_blk->dentry_bitmap, + bit_pos = f2fs_room_for_filename(&dentry_blk->dentry_bitmap, slots, NR_DENTRY_IN_BLOCK); if (bit_pos < NR_DENTRY_IN_BLOCK) goto add_dentry; @@ -558,7 +558,7 @@ add_dentry: if (inode) { down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, new_name, + page = f2fs_init_inode_metadata(inode, dir, new_name, orig_name, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); @@ -576,7 +576,7 @@ add_dentry: f2fs_put_page(page, 1); } - update_parent_metadata(dir, inode, current_depth); + f2fs_update_parent_metadata(dir, inode, current_depth); fail: if (inode) up_write(&F2FS_I(inode)->i_sem); @@ -586,7 +586,7 @@ fail: return err; } -int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname, +int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname, struct inode *inode, nid_t ino, umode_t mode) { struct qstr new_name; @@ -610,7 +610,7 @@ int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname, * Caller should grab and release a rwsem by calling f2fs_lock_op() and * f2fs_unlock_op(). */ -int __f2fs_add_link(struct inode *dir, const struct qstr *name, +int f2fs_do_add_link(struct inode *dir, const struct qstr *name, struct inode *inode, nid_t ino, umode_t mode) { struct fscrypt_name fname; @@ -639,7 +639,7 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, } else if (IS_ERR(page)) { err = PTR_ERR(page); } else { - err = __f2fs_do_add_link(dir, &fname, inode, ino, mode); + err = f2fs_add_dentry(dir, &fname, inode, ino, mode); } fscrypt_free_filename(&fname); return err; @@ -651,7 +651,7 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir) int err = 0; down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, NULL, NULL, NULL); + page = f2fs_init_inode_metadata(inode, dir, NULL, NULL, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; @@ -683,9 +683,9 @@ void f2fs_drop_nlink(struct inode *dir, struct inode *inode) up_write(&F2FS_I(inode)->i_sem); if (inode->i_nlink == 0) - add_orphan_inode(inode); + f2fs_add_orphan_inode(inode); else - release_orphan_inode(sbi); + f2fs_release_orphan_inode(sbi); } /* @@ -698,14 +698,12 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, struct f2fs_dentry_block *dentry_blk; unsigned int bit_pos; int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); - struct address_space *mapping = page_mapping(page); - unsigned long flags; int i; f2fs_update_time(F2FS_I_SB(dir), REQ_TIME); if (F2FS_OPTION(F2FS_I_SB(dir)).fsync_mode == FSYNC_MODE_STRICT) - add_ino_entry(F2FS_I_SB(dir), dir->i_ino, TRANS_DIR_INO); + f2fs_add_ino_entry(F2FS_I_SB(dir), dir->i_ino, TRANS_DIR_INO); if (f2fs_has_inline_dentry(dir)) return f2fs_delete_inline_entry(dentry, page, dir, inode); @@ -731,17 +729,13 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, f2fs_drop_nlink(dir, inode); if (bit_pos == NR_DENTRY_IN_BLOCK && - !truncate_hole(dir, page->index, page->index + 1)) { - xa_lock_irqsave(&mapping->i_pages, flags); - radix_tree_tag_clear(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_DIRTY); - xa_unlock_irqrestore(&mapping->i_pages, flags); - + !f2fs_truncate_hole(dir, page->index, page->index + 1)) { + f2fs_clear_radix_tree_dirty_tag(page); clear_page_dirty_for_io(page); ClearPagePrivate(page); ClearPageUptodate(page); inode_dec_dirty_pages(dir); - remove_dirty_inode(dir); + f2fs_remove_dirty_inode(dir); } f2fs_put_page(page, 1); } @@ -758,7 +752,7 @@ bool f2fs_empty_dir(struct inode *dir) return f2fs_empty_inline_dir(dir); for (bidx = 0; bidx < nblock; bidx++) { - dentry_page = get_lock_data_page(dir, bidx, false); + dentry_page = f2fs_get_lock_data_page(dir, bidx, false); if (IS_ERR(dentry_page)) { if (PTR_ERR(dentry_page) == -ENOENT) continue; @@ -806,7 +800,7 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, continue; } - d_type = get_de_type(de); + d_type = f2fs_get_de_type(de); de_name.name = d->filename[bit_pos]; de_name.len = le16_to_cpu(de->name_len); @@ -830,7 +824,7 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, return 1; if (sbi->readdir_ra == 1) - ra_node_page(sbi, le32_to_cpu(de->ino)); + f2fs_ra_node_page(sbi, le32_to_cpu(de->ino)); bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); ctx->pos = start_pos + bit_pos; @@ -880,7 +874,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) page_cache_sync_readahead(inode->i_mapping, ra, file, n, min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES)); - dentry_page = get_lock_data_page(inode, n, false); + dentry_page = f2fs_get_lock_data_page(inode, n, false); if (IS_ERR(dentry_page)) { err = PTR_ERR(dentry_page); if (err == -ENOENT) { diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index d5a861bf2b42..231b77ef5a53 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -49,7 +49,7 @@ static struct rb_entry *__lookup_rb_tree_slow(struct rb_root *root, return NULL; } -struct rb_entry *__lookup_rb_tree(struct rb_root *root, +struct rb_entry *f2fs_lookup_rb_tree(struct rb_root *root, struct rb_entry *cached_re, unsigned int ofs) { struct rb_entry *re; @@ -61,7 +61,7 @@ struct rb_entry *__lookup_rb_tree(struct rb_root *root, return re; } -struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, +struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, struct rb_root *root, struct rb_node **parent, unsigned int ofs) { @@ -92,7 +92,7 @@ struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, * in order to simpfy the insertion after. * tree must stay unchanged between lookup and insertion. */ -struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root, +struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root *root, struct rb_entry *cached_re, unsigned int ofs, struct rb_entry **prev_entry, @@ -159,7 +159,7 @@ lookup_neighbors: return re; } -bool __check_rb_tree_consistence(struct f2fs_sb_info *sbi, +bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi, struct rb_root *root) { #ifdef CONFIG_F2FS_CHECK_FS @@ -390,7 +390,7 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, goto out; } - en = (struct extent_node *)__lookup_rb_tree(&et->root, + en = (struct extent_node *)f2fs_lookup_rb_tree(&et->root, (struct rb_entry *)et->cached_en, pgofs); if (!en) goto out; @@ -470,7 +470,7 @@ static struct extent_node *__insert_extent_tree(struct inode *inode, goto do_insert; } - p = __lookup_rb_tree_for_insert(sbi, &et->root, &parent, ei->fofs); + p = f2fs_lookup_rb_tree_for_insert(sbi, &et->root, &parent, ei->fofs); do_insert: en = __attach_extent_node(sbi, et, ei, parent, p); if (!en) @@ -520,7 +520,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode, __drop_largest_extent(inode, fofs, len); /* 1. lookup first extent node in range [fofs, fofs + len - 1] */ - en = (struct extent_node *)__lookup_rb_tree_ret(&et->root, + en = (struct extent_node *)f2fs_lookup_rb_tree_ret(&et->root, (struct rb_entry *)et->cached_en, fofs, (struct rb_entry **)&prev_en, (struct rb_entry **)&next_en, @@ -773,7 +773,7 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn) else blkaddr = dn->data_blkaddr; - fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + + fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + dn->ofs_in_node; f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1); } @@ -788,7 +788,7 @@ void f2fs_update_extent_cache_range(struct dnode_of_data *dn, f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len); } -void init_extent_cache_info(struct f2fs_sb_info *sbi) +void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi) { INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO); mutex_init(&sbi->extent_tree_lock); @@ -800,7 +800,7 @@ void init_extent_cache_info(struct f2fs_sb_info *sbi) atomic_set(&sbi->total_ext_node, 0); } -int __init create_extent_cache(void) +int __init f2fs_create_extent_cache(void) { extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree", sizeof(struct extent_tree)); @@ -815,7 +815,7 @@ int __init create_extent_cache(void) return 0; } -void destroy_extent_cache(void) +void f2fs_destroy_extent_cache(void) { kmem_cache_destroy(extent_node_slab); kmem_cache_destroy(extent_tree_slab); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 1df7f10476d6..4c09e770a0a3 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -176,15 +176,13 @@ enum { #define CP_DISCARD 0x00000010 #define CP_TRIMMED 0x00000020 -#define DEF_BATCHED_TRIM_SECTIONS 2048 -#define BATCHED_TRIM_SEGMENTS(sbi) \ - (GET_SEG_FROM_SEC(sbi, SM_I(sbi)->trim_sections)) -#define BATCHED_TRIM_BLOCKS(sbi) \ - (BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg) #define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi) #define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */ +#define DEF_MAX_DISCARD_LEN 512 /* Max. 2MB per discard */ #define DEF_MIN_DISCARD_ISSUE_TIME 50 /* 50 ms, if exists */ +#define DEF_MID_DISCARD_ISSUE_TIME 500 /* 500 ms, if device busy */ #define DEF_MAX_DISCARD_ISSUE_TIME 60000 /* 60 s, if no candidates */ +#define DEF_DISCARD_URGENT_UTIL 80 /* do more discard over 80% */ #define DEF_CP_INTERVAL 60 /* 60 secs */ #define DEF_IDLE_INTERVAL 5 /* 5 secs */ @@ -285,6 +283,7 @@ enum { struct discard_policy { int type; /* type of discard */ unsigned int min_interval; /* used for candidates exist */ + unsigned int mid_interval; /* used for device busy */ unsigned int max_interval; /* used for candidates not exist */ unsigned int max_requests; /* # of discards issued per round */ unsigned int io_aware_gran; /* minimum granularity discard not be aware of I/O */ @@ -620,15 +619,20 @@ enum { #define DEF_DIR_LEVEL 0 +enum { + GC_FAILURE_PIN, + GC_FAILURE_ATOMIC, + MAX_GC_FAILURE +}; + struct f2fs_inode_info { struct inode vfs_inode; /* serve a vfs inode */ unsigned long i_flags; /* keep an inode flags for ioctl */ unsigned char i_advise; /* use to give file attribute hints */ unsigned char i_dir_level; /* use for dentry level for large dir */ - union { - unsigned int i_current_depth; /* only for directory depth */ - unsigned short i_gc_failures; /* only for regular file */ - }; + unsigned int i_current_depth; /* only for directory depth */ + /* for gc failure statistic */ + unsigned int i_gc_failures[MAX_GC_FAILURE]; unsigned int i_pino; /* parent inode number */ umode_t i_acl_mode; /* keep file acl mode temporarily */ @@ -656,7 +660,9 @@ struct f2fs_inode_info { struct task_struct *inmem_task; /* store inmemory task */ struct mutex inmem_lock; /* lock for inmemory pages */ struct extent_tree *extent_tree; /* cached extent_tree entry */ - struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */ + + /* avoid racing between foreground op and gc */ + struct rw_semaphore i_gc_rwsem[2]; struct rw_semaphore i_mmap_sem; struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */ @@ -694,7 +700,8 @@ static inline void set_extent_info(struct extent_info *ei, unsigned int fofs, static inline bool __is_discard_mergeable(struct discard_info *back, struct discard_info *front) { - return back->lstart + back->len == front->lstart; + return (back->lstart + back->len == front->lstart) && + (back->len + front->len < DEF_MAX_DISCARD_LEN); } static inline bool __is_discard_back_mergeable(struct discard_info *cur, @@ -1005,6 +1012,7 @@ struct f2fs_io_info { int need_lock; /* indicate we need to lock cp_rwsem */ bool in_list; /* indicate fio is in io_list */ bool is_meta; /* indicate borrow meta inode mapping or not */ + bool retry; /* need to reallocate block address */ enum iostat_type io_type; /* io type */ struct writeback_control *io_wbc; /* writeback control */ }; @@ -1067,6 +1075,13 @@ enum { }; enum { + GC_NORMAL, + GC_IDLE_CB, + GC_IDLE_GREEDY, + GC_URGENT, +}; + +enum { WHINT_MODE_OFF, /* not pass down write hints */ WHINT_MODE_USER, /* try to pass down hints given by users */ WHINT_MODE_FS, /* pass down hints with F2FS policy */ @@ -1080,6 +1095,7 @@ enum { enum fsync_mode { FSYNC_MODE_POSIX, /* fsync follows posix semantics */ FSYNC_MODE_STRICT, /* fsync behaves in line with ext4 */ + FSYNC_MODE_NOBARRIER, /* fsync behaves nobarrier based on posix */ }; #ifdef CONFIG_F2FS_FS_ENCRYPTION @@ -1113,6 +1129,8 @@ struct f2fs_sb_info { struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */ struct mutex wio_mutex[NR_PAGE_TYPE - 1][NR_TEMP_TYPE]; /* bio ordering for NODE/DATA */ + /* keep migration IO order for LFS mode */ + struct rw_semaphore io_order_lock; mempool_t *write_io_dummy; /* Dummy pages */ /* for checkpoint */ @@ -1183,7 +1201,7 @@ struct f2fs_sb_info { struct percpu_counter alloc_valid_block_count; /* writeback control */ - atomic_t wb_sync_req; /* count # of WB_SYNC threads */ + atomic_t wb_sync_req[META]; /* count # of WB_SYNC threads */ /* valid inode count */ struct percpu_counter total_valid_inode_count; @@ -1194,9 +1212,9 @@ struct f2fs_sb_info { struct mutex gc_mutex; /* mutex for GC */ struct f2fs_gc_kthread *gc_thread; /* GC thread */ unsigned int cur_victim_sec; /* current victim section num */ - - /* threshold for converting bg victims for fg */ - u64 fggc_threshold; + unsigned int gc_mode; /* current GC state */ + /* for skip statistic */ + unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */ /* threshold for gc trials on pinned files */ u64 gc_pin_file_threshold; @@ -1587,18 +1605,6 @@ static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi) } /* - * Check whether the given nid is within node id range. - */ -static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) -{ - if (unlikely(nid < F2FS_ROOT_INO(sbi))) - return -EINVAL; - if (unlikely(nid >= NM_I(sbi)->max_nid)) - return -EINVAL; - return 0; -} - -/* * Check whether the inode has blocks or not */ static inline int F2FS_HAS_BLOCKS(struct inode *inode) @@ -1614,7 +1620,7 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs) } static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi, - struct inode *inode) + struct inode *inode, bool cap) { if (!inode) return true; @@ -1627,7 +1633,7 @@ static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi, if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) && in_group_p(F2FS_OPTION(sbi).s_resgid)) return true; - if (capable(CAP_SYS_RESOURCE)) + if (cap && capable(CAP_SYS_RESOURCE)) return true; return false; } @@ -1662,7 +1668,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, avail_user_block_count = sbi->user_block_count - sbi->current_reserved_blocks; - if (!__allow_reserved_blocks(sbi, inode)) + if (!__allow_reserved_blocks(sbi, inode, true)) avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { @@ -1869,7 +1875,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, valid_block_count = sbi->total_valid_block_count + sbi->current_reserved_blocks + 1; - if (!__allow_reserved_blocks(sbi, inode)) + if (!__allow_reserved_blocks(sbi, inode, false)) valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks; if (unlikely(valid_block_count > sbi->user_block_count)) { @@ -2156,9 +2162,60 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr) *addr ^= mask; } -#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL)) -#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL) -#define F2FS_FL_INHERITED (FS_PROJINHERIT_FL) +/* + * Inode flags + */ +#define F2FS_SECRM_FL 0x00000001 /* Secure deletion */ +#define F2FS_UNRM_FL 0x00000002 /* Undelete */ +#define F2FS_COMPR_FL 0x00000004 /* Compress file */ +#define F2FS_SYNC_FL 0x00000008 /* Synchronous updates */ +#define F2FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define F2FS_APPEND_FL 0x00000020 /* writes to file may only append */ +#define F2FS_NODUMP_FL 0x00000040 /* do not dump file */ +#define F2FS_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define F2FS_DIRTY_FL 0x00000100 +#define F2FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define F2FS_NOCOMPR_FL 0x00000400 /* Don't compress */ +#define F2FS_ENCRYPT_FL 0x00000800 /* encrypted file */ +/* End compression flags --- maybe not all used */ +#define F2FS_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define F2FS_IMAGIC_FL 0x00002000 /* AFS directory */ +#define F2FS_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */ +#define F2FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define F2FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define F2FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define F2FS_HUGE_FILE_FL 0x00040000 /* Set to each huge file */ +#define F2FS_EXTENTS_FL 0x00080000 /* Inode uses extents */ +#define F2FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */ +#define F2FS_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ +#define F2FS_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ +#define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ +#define F2FS_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ + +#define F2FS_FL_USER_VISIBLE 0x304BDFFF /* User visible flags */ +#define F2FS_FL_USER_MODIFIABLE 0x204BC0FF /* User modifiable flags */ + +/* Flags we can manipulate with through F2FS_IOC_FSSETXATTR */ +#define F2FS_FL_XFLAG_VISIBLE (F2FS_SYNC_FL | \ + F2FS_IMMUTABLE_FL | \ + F2FS_APPEND_FL | \ + F2FS_NODUMP_FL | \ + F2FS_NOATIME_FL | \ + F2FS_PROJINHERIT_FL) + +/* Flags that should be inherited by new inodes from their parent. */ +#define F2FS_FL_INHERITED (F2FS_SECRM_FL | F2FS_UNRM_FL | F2FS_COMPR_FL |\ + F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL |\ + F2FS_NOCOMPR_FL | F2FS_JOURNAL_DATA_FL |\ + F2FS_NOTAIL_FL | F2FS_DIRSYNC_FL |\ + F2FS_PROJINHERIT_FL) + +/* Flags that are appropriate for regular files (all but dir-specific ones). */ +#define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_TOPDIR_FL)) + +/* Flags that are appropriate for non-directories/regular files. */ +#define F2FS_OTHER_FLMASK (F2FS_NODUMP_FL | F2FS_NOATIME_FL) static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags) { @@ -2201,6 +2258,7 @@ enum { FI_EXTRA_ATTR, /* indicate file has extra attribute */ FI_PROJ_INHERIT, /* indicate file inherits projectid */ FI_PIN_FILE, /* indicate file should not be gced */ + FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */ }; static inline void __mark_inode_dirty_flag(struct inode *inode, @@ -2299,7 +2357,7 @@ static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth) static inline void f2fs_i_gc_failures_write(struct inode *inode, unsigned int count) { - F2FS_I(inode)->i_gc_failures = count; + F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = count; f2fs_mark_inode_dirty_sync(inode, true); } @@ -2568,7 +2626,7 @@ static inline int get_inline_xattr_addrs(struct inode *inode) return F2FS_I(inode)->i_inline_xattr_size; } -#define get_inode_mode(i) \ +#define f2fs_get_inode_mode(i) \ ((is_inode_flag_set(i, FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) @@ -2607,18 +2665,25 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi, spin_unlock(&sbi->iostat_lock); } +static inline bool is_valid_blkaddr(block_t blkaddr) +{ + if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) + return false; + return true; +} + /* * file.c */ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); -void truncate_data_blocks(struct dnode_of_data *dn); -int truncate_blocks(struct inode *inode, u64 from, bool lock); +void f2fs_truncate_data_blocks(struct dnode_of_data *dn); +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate(struct inode *inode); int f2fs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); int f2fs_setattr(struct dentry *dentry, struct iattr *attr); -int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end); -void truncate_data_blocks_range(struct dnode_of_data *dn, int count); +int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end); +void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count); int f2fs_precache_extents(struct inode *inode); long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -2632,38 +2697,37 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page); void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page); struct inode *f2fs_iget(struct super_block *sb, unsigned long ino); struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino); -int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink); -void update_inode(struct inode *inode, struct page *node_page); -void update_inode_page(struct inode *inode); +int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink); +void f2fs_update_inode(struct inode *inode, struct page *node_page); +void f2fs_update_inode_page(struct inode *inode); int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc); void f2fs_evict_inode(struct inode *inode); -void handle_failed_inode(struct inode *inode); +void f2fs_handle_failed_inode(struct inode *inode); /* * namei.c */ -int update_extension_list(struct f2fs_sb_info *sbi, const char *name, +int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, bool hot, bool set); struct dentry *f2fs_get_parent(struct dentry *child); /* * dir.c */ -void set_de_type(struct f2fs_dir_entry *de, umode_t mode); -unsigned char get_de_type(struct f2fs_dir_entry *de); -struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname, +unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de); +struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname, f2fs_hash_t namehash, int *max_slots, struct f2fs_dentry_ptr *d); int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, unsigned int start_pos, struct fscrypt_str *fstr); -void do_make_empty_dir(struct inode *inode, struct inode *parent, +void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent, struct f2fs_dentry_ptr *d); -struct page *init_inode_metadata(struct inode *inode, struct inode *dir, +struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir, const struct qstr *new_name, const struct qstr *orig_name, struct page *dpage); -void update_parent_metadata(struct inode *dir, struct inode *inode, +void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode, unsigned int current_depth); -int room_for_filename(const void *bitmap, int slots, int max_slots); +int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots); void f2fs_drop_nlink(struct inode *dir, struct inode *inode); struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, struct fscrypt_name *fname, struct page **res_page); @@ -2680,9 +2744,9 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d, int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name, const struct qstr *orig_name, struct inode *inode, nid_t ino, umode_t mode); -int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname, +int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname, struct inode *inode, nid_t ino, umode_t mode); -int __f2fs_add_link(struct inode *dir, const struct qstr *name, +int f2fs_do_add_link(struct inode *dir, const struct qstr *name, struct inode *inode, nid_t ino, umode_t mode); void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, struct inode *dir, struct inode *inode); @@ -2691,7 +2755,7 @@ bool f2fs_empty_dir(struct inode *dir); static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) { - return __f2fs_add_link(d_inode(dentry->d_parent), &dentry->d_name, + return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name, inode, inode->i_ino, inode->i_mode); } @@ -2706,7 +2770,7 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); int f2fs_sync_fs(struct super_block *sb, int sync); extern __printf(3, 4) void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); -int sanity_check_ckpt(struct f2fs_sb_info *sbi); +int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi); /* * hash.c @@ -2720,179 +2784,183 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info, struct dnode_of_data; struct node_info; -bool available_free_memory(struct f2fs_sb_info *sbi, int type); -int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid); -bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid); -bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino); -void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni); -pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs); -int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode); -int truncate_inode_blocks(struct inode *inode, pgoff_t from); -int truncate_xattr_node(struct inode *inode); -int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino); -int remove_inode_page(struct inode *inode); -struct page *new_inode_page(struct inode *inode); -struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs); -void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid); -struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid); -struct page *get_node_page_ra(struct page *parent, int start); -void move_node_page(struct page *node_page, int gc_type); -int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, +int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid); +bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type); +int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid); +bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid); +bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino); +void f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, + struct node_info *ni); +pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs); +int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode); +int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from); +int f2fs_truncate_xattr_node(struct inode *inode); +int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino); +int f2fs_remove_inode_page(struct inode *inode); +struct page *f2fs_new_inode_page(struct inode *inode); +struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs); +void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid); +struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid); +struct page *f2fs_get_node_page_ra(struct page *parent, int start); +void f2fs_move_node_page(struct page *node_page, int gc_type); +int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, struct writeback_control *wbc, bool atomic); -int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, +int f2fs_sync_node_pages(struct f2fs_sb_info *sbi, + struct writeback_control *wbc, bool do_balance, enum iostat_type io_type); -void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount); -bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid); -void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid); -void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid); -int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink); -void recover_inline_xattr(struct inode *inode, struct page *page); -int recover_xattr_data(struct inode *inode, struct page *page); -int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page); -void restore_node_summary(struct f2fs_sb_info *sbi, +void f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount); +bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid); +void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid); +void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid); +int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink); +void f2fs_recover_inline_xattr(struct inode *inode, struct page *page); +int f2fs_recover_xattr_data(struct inode *inode, struct page *page); +int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page); +void f2fs_restore_node_summary(struct f2fs_sb_info *sbi, unsigned int segno, struct f2fs_summary_block *sum); -void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); -int build_node_manager(struct f2fs_sb_info *sbi); -void destroy_node_manager(struct f2fs_sb_info *sbi); -int __init create_node_manager_caches(void); -void destroy_node_manager_caches(void); +void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); +int f2fs_build_node_manager(struct f2fs_sb_info *sbi); +void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi); +int __init f2fs_create_node_manager_caches(void); +void f2fs_destroy_node_manager_caches(void); /* * segment.c */ -bool need_SSR(struct f2fs_sb_info *sbi); -void register_inmem_page(struct inode *inode, struct page *page); -void drop_inmem_pages_all(struct f2fs_sb_info *sbi); -void drop_inmem_pages(struct inode *inode); -void drop_inmem_page(struct inode *inode, struct page *page); -int commit_inmem_pages(struct inode *inode); +bool f2fs_need_SSR(struct f2fs_sb_info *sbi); +void f2fs_register_inmem_page(struct inode *inode, struct page *page); +void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure); +void f2fs_drop_inmem_pages(struct inode *inode); +void f2fs_drop_inmem_page(struct inode *inode, struct page *page); +int f2fs_commit_inmem_pages(struct inode *inode); void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need); void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi); int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino); -int create_flush_cmd_control(struct f2fs_sb_info *sbi); +int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi); int f2fs_flush_device_cache(struct f2fs_sb_info *sbi); -void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free); -void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); -bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); -void init_discard_policy(struct discard_policy *dpolicy, int discard_type, - unsigned int granularity); -void drop_discard_cmd(struct f2fs_sb_info *sbi); -void stop_discard_thread(struct f2fs_sb_info *sbi); +void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free); +void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); +bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); +void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi); +void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi); bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi); -void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); -void release_discard_addrs(struct f2fs_sb_info *sbi); -int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); -void allocate_new_segments(struct f2fs_sb_info *sbi); +void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, + struct cp_control *cpc); +void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi); +int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); +void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi); int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range); -bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc); -struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno); -void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr); -void write_meta_page(struct f2fs_sb_info *sbi, struct page *page, +bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi, + struct cp_control *cpc); +struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno); +void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src, + block_t blk_addr); +void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page, enum iostat_type io_type); -void write_node_page(unsigned int nid, struct f2fs_io_info *fio); -void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio); -int rewrite_data_page(struct f2fs_io_info *fio); -void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, +void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio); +void f2fs_outplace_write_data(struct dnode_of_data *dn, + struct f2fs_io_info *fio); +int f2fs_inplace_write_data(struct f2fs_io_info *fio); +void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t old_blkaddr, block_t new_blkaddr, bool recover_curseg, bool recover_newaddr); void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, block_t old_addr, block_t new_addr, unsigned char version, bool recover_curseg, bool recover_newaddr); -void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, +void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, struct f2fs_io_info *fio, bool add_list); void f2fs_wait_on_page_writeback(struct page *page, enum page_type type, bool ordered); void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr); -void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk); -void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk); -int lookup_journal_in_cursum(struct f2fs_journal *journal, int type, +void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk); +void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk); +int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, unsigned int val, int alloc); -void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); -int build_segment_manager(struct f2fs_sb_info *sbi); -void destroy_segment_manager(struct f2fs_sb_info *sbi); -int __init create_segment_manager_caches(void); -void destroy_segment_manager_caches(void); -int rw_hint_to_seg_type(enum rw_hint hint); -enum rw_hint io_type_to_rw_hint(struct f2fs_sb_info *sbi, enum page_type type, - enum temp_type temp); +void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); +int f2fs_build_segment_manager(struct f2fs_sb_info *sbi); +void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi); +int __init f2fs_create_segment_manager_caches(void); +void f2fs_destroy_segment_manager_caches(void); +int f2fs_rw_hint_to_seg_type(enum rw_hint hint); +enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, + enum page_type type, enum temp_type temp); /* * checkpoint.c */ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io); -struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); -struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); -struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index); -bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); -int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, +struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); +struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); +struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index); +bool f2fs_is_valid_meta_blkaddr(struct f2fs_sb_info *sbi, + block_t blkaddr, int type); +int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type, bool sync); -void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index); -long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, +void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index); +long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, long nr_to_write, enum iostat_type io_type); -void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); -void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); -void release_ino_entry(struct f2fs_sb_info *sbi, bool all); -bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode); -void set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, +void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); +void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); +void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all); +bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode); +void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, unsigned int devidx, int type); -bool is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, +bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, unsigned int devidx, int type); int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi); -int acquire_orphan_inode(struct f2fs_sb_info *sbi); -void release_orphan_inode(struct f2fs_sb_info *sbi); -void add_orphan_inode(struct inode *inode); -void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino); -int recover_orphan_inodes(struct f2fs_sb_info *sbi); -int get_valid_checkpoint(struct f2fs_sb_info *sbi); -void update_dirty_page(struct inode *inode, struct page *page); -void remove_dirty_inode(struct inode *inode); -int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type); -int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc); -void init_ino_entry_info(struct f2fs_sb_info *sbi); -int __init create_checkpoint_caches(void); -void destroy_checkpoint_caches(void); +int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi); +void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi); +void f2fs_add_orphan_inode(struct inode *inode); +void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino); +int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi); +int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi); +void f2fs_update_dirty_page(struct inode *inode, struct page *page); +void f2fs_remove_dirty_inode(struct inode *inode); +int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type); +int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc); +void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi); +int __init f2fs_create_checkpoint_caches(void); +void f2fs_destroy_checkpoint_caches(void); /* * data.c */ +int f2fs_init_post_read_processing(void); +void f2fs_destroy_post_read_processing(void); void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type); void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, struct inode *inode, nid_t ino, pgoff_t idx, enum page_type type); void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi); int f2fs_submit_page_bio(struct f2fs_io_info *fio); -int f2fs_submit_page_write(struct f2fs_io_info *fio); +void f2fs_submit_page_write(struct f2fs_io_info *fio); struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, block_t blk_addr, struct bio *bio); int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr); -void set_data_blkaddr(struct dnode_of_data *dn); +void f2fs_set_data_blkaddr(struct dnode_of_data *dn); void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); -int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count); -int reserve_new_block(struct dnode_of_data *dn); +int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count); +int f2fs_reserve_new_block(struct dnode_of_data *dn); int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index); int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from); int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index); -struct page *get_read_data_page(struct inode *inode, pgoff_t index, +struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, int op_flags, bool for_write); -struct page *find_data_page(struct inode *inode, pgoff_t index); -struct page *get_lock_data_page(struct inode *inode, pgoff_t index, +struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index); +struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, bool for_write); -struct page *get_new_data_page(struct inode *inode, +struct page *f2fs_get_new_data_page(struct inode *inode, struct page *ipage, pgoff_t index, bool new_i_size); -int do_write_data_page(struct f2fs_io_info *fio); +int f2fs_do_write_data_page(struct f2fs_io_info *fio); int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int create, int flag); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); -bool should_update_inplace(struct inode *inode, struct f2fs_io_info *fio); -bool should_update_outplace(struct inode *inode, struct f2fs_io_info *fio); -void f2fs_set_page_dirty_nobuffers(struct page *page); -int __f2fs_write_data_pages(struct address_space *mapping, - struct writeback_control *wbc, - enum iostat_type io_type); +bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio); +bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio); void f2fs_invalidate_page(struct page *page, unsigned int offset, unsigned int length); int f2fs_release_page(struct page *page, gfp_t wait); @@ -2901,22 +2969,23 @@ int f2fs_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode); #endif bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len); +void f2fs_clear_radix_tree_dirty_tag(struct page *page); /* * gc.c */ -int start_gc_thread(struct f2fs_sb_info *sbi); -void stop_gc_thread(struct f2fs_sb_info *sbi); -block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode); +int f2fs_start_gc_thread(struct f2fs_sb_info *sbi); +void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi); +block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode); int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background, unsigned int segno); -void build_gc_manager(struct f2fs_sb_info *sbi); +void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); /* * recovery.c */ -int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only); -bool space_for_roll_forward(struct f2fs_sb_info *sbi); +int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only); +bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi); /* * debug.c @@ -2954,6 +3023,7 @@ struct f2fs_stat_info { int bg_node_segs, bg_data_segs; int tot_blks, data_blks, node_blks; int bg_data_blks, bg_node_blks; + unsigned long long skipped_atomic_files[2]; int curseg[NR_CURSEG_TYPE]; int cursec[NR_CURSEG_TYPE]; int curzone[NR_CURSEG_TYPE]; @@ -3120,29 +3190,31 @@ extern const struct inode_operations f2fs_dir_inode_operations; extern const struct inode_operations f2fs_symlink_inode_operations; extern const struct inode_operations f2fs_encrypted_symlink_inode_operations; extern const struct inode_operations f2fs_special_inode_operations; -extern struct kmem_cache *inode_entry_slab; +extern struct kmem_cache *f2fs_inode_entry_slab; /* * inline.c */ bool f2fs_may_inline_data(struct inode *inode); bool f2fs_may_inline_dentry(struct inode *inode); -void read_inline_data(struct page *page, struct page *ipage); -void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from); +void f2fs_do_read_inline_data(struct page *page, struct page *ipage); +void f2fs_truncate_inline_inode(struct inode *inode, + struct page *ipage, u64 from); int f2fs_read_inline_data(struct inode *inode, struct page *page); int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page); int f2fs_convert_inline_inode(struct inode *inode); int f2fs_write_inline_data(struct inode *inode, struct page *page); -bool recover_inline_data(struct inode *inode, struct page *npage); -struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, +bool f2fs_recover_inline_data(struct inode *inode, struct page *npage); +struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, struct fscrypt_name *fname, struct page **res_page); -int make_empty_inline_dir(struct inode *inode, struct inode *parent, +int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent, struct page *ipage); int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, const struct qstr *orig_name, struct inode *inode, nid_t ino, umode_t mode); -void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page, - struct inode *dir, struct inode *inode); +void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, + struct page *page, struct inode *dir, + struct inode *inode); bool f2fs_empty_inline_dir(struct inode *dir); int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, struct fscrypt_str *fstr); @@ -3163,17 +3235,17 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi); /* * extent_cache.c */ -struct rb_entry *__lookup_rb_tree(struct rb_root *root, +struct rb_entry *f2fs_lookup_rb_tree(struct rb_root *root, struct rb_entry *cached_re, unsigned int ofs); -struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, +struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, struct rb_root *root, struct rb_node **parent, unsigned int ofs); -struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root, +struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root *root, struct rb_entry *cached_re, unsigned int ofs, struct rb_entry **prev_entry, struct rb_entry **next_entry, struct rb_node ***insert_p, struct rb_node **insert_parent, bool force); -bool __check_rb_tree_consistence(struct f2fs_sb_info *sbi, +bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi, struct rb_root *root); unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink); bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext); @@ -3185,9 +3257,9 @@ bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs, void f2fs_update_extent_cache(struct dnode_of_data *dn); void f2fs_update_extent_cache_range(struct dnode_of_data *dn, pgoff_t fofs, block_t blkaddr, unsigned int len); -void init_extent_cache_info(struct f2fs_sb_info *sbi); -int __init create_extent_cache(void); -void destroy_extent_cache(void); +void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi); +int __init f2fs_create_extent_cache(void); +void f2fs_destroy_extent_cache(void); /* * sysfs.c @@ -3218,9 +3290,13 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode) #endif } -static inline bool f2fs_bio_encrypted(struct bio *bio) +/* + * Returns true if the reads of the inode's data need to undergo some + * postprocessing step, like decryption or authenticity verification. + */ +static inline bool f2fs_post_read_required(struct inode *inode) { - return bio->bi_private != NULL; + return f2fs_encrypted_file(inode); } #define F2FS_FEATURE_FUNCS(name, flagname) \ @@ -3288,7 +3364,7 @@ static inline bool f2fs_may_encrypt(struct inode *inode) static inline bool f2fs_force_buffered_io(struct inode *inode, int rw) { - return (f2fs_encrypted_file(inode) || + return (f2fs_post_read_required(inode) || (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) || F2FS_I_SB(inode)->s_ndevs); } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 6b94f19b3fa8..13f2f6845e87 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -33,19 +33,19 @@ #include "trace.h" #include <trace/events/f2fs.h> -static int f2fs_filemap_fault(struct vm_fault *vmf) +static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); - int err; + vm_fault_t ret; down_read(&F2FS_I(inode)->i_mmap_sem); - err = filemap_fault(vmf); + ret = filemap_fault(vmf); up_read(&F2FS_I(inode)->i_mmap_sem); - return err; + return ret; } -static int f2fs_vm_page_mkwrite(struct vm_fault *vmf) +static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); @@ -95,7 +95,8 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf) /* page is wholly or partially inside EOF */ if (((loff_t)(page->index + 1) << PAGE_SHIFT) > i_size_read(inode)) { - unsigned offset; + loff_t offset; + offset = i_size_read(inode) & ~PAGE_MASK; zero_user_segment(page, offset, PAGE_SIZE); } @@ -110,8 +111,8 @@ mapped: /* fill the page */ f2fs_wait_on_page_writeback(page, DATA, false); - /* wait for GCed encrypted page writeback */ - if (f2fs_encrypted_file(inode)) + /* wait for GCed page writeback via META_MAPPING */ + if (f2fs_post_read_required(inode)) f2fs_wait_on_block_writeback(sbi, dn.data_blkaddr); out_sem: @@ -157,17 +158,18 @@ static inline enum cp_reason_type need_do_checkpoint(struct inode *inode) cp_reason = CP_SB_NEED_CP; else if (file_wrong_pino(inode)) cp_reason = CP_WRONG_PINO; - else if (!space_for_roll_forward(sbi)) + else if (!f2fs_space_for_roll_forward(sbi)) cp_reason = CP_NO_SPC_ROLL; - else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino)) + else if (!f2fs_is_checkpointed_node(sbi, F2FS_I(inode)->i_pino)) cp_reason = CP_NODE_NEED_CP; else if (test_opt(sbi, FASTBOOT)) cp_reason = CP_FASTBOOT_MODE; else if (F2FS_OPTION(sbi).active_logs == 2) cp_reason = CP_SPEC_LOG_NUM; else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT && - need_dentry_mark(sbi, inode->i_ino) && - exist_written_data(sbi, F2FS_I(inode)->i_pino, TRANS_DIR_INO)) + f2fs_need_dentry_mark(sbi, inode->i_ino) && + f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino, + TRANS_DIR_INO)) cp_reason = CP_RECOVER_DIR; return cp_reason; @@ -178,7 +180,7 @@ static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino) struct page *i = find_get_page(NODE_MAPPING(sbi), ino); bool ret = false; /* But we need to avoid that there are some inode updates */ - if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino)) + if ((i && PageDirty(i)) || f2fs_need_inode_block_update(sbi, ino)) ret = true; f2fs_put_page(i, 0); return ret; @@ -238,14 +240,14 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, * if there is no written data, don't waste time to write recovery info. */ if (!is_inode_flag_set(inode, FI_APPEND_WRITE) && - !exist_written_data(sbi, ino, APPEND_INO)) { + !f2fs_exist_written_data(sbi, ino, APPEND_INO)) { /* it may call write_inode just prior to fsync */ if (need_inode_page_update(sbi, ino)) goto go_write; if (is_inode_flag_set(inode, FI_UPDATE_WRITE) || - exist_written_data(sbi, ino, UPDATE_INO)) + f2fs_exist_written_data(sbi, ino, UPDATE_INO)) goto flush_out; goto out; } @@ -272,7 +274,9 @@ go_write: goto out; } sync_nodes: - ret = fsync_node_pages(sbi, inode, &wbc, atomic); + atomic_inc(&sbi->wb_sync_req[NODE]); + ret = f2fs_fsync_node_pages(sbi, inode, &wbc, atomic); + atomic_dec(&sbi->wb_sync_req[NODE]); if (ret) goto out; @@ -282,7 +286,7 @@ sync_nodes: goto out; } - if (need_inode_block_update(sbi, ino)) { + if (f2fs_need_inode_block_update(sbi, ino)) { f2fs_mark_inode_dirty_sync(inode, true); f2fs_write_inode(inode, NULL); goto sync_nodes; @@ -297,21 +301,21 @@ sync_nodes: * given fsync mark. */ if (!atomic) { - ret = wait_on_node_pages_writeback(sbi, ino); + ret = f2fs_wait_on_node_pages_writeback(sbi, ino); if (ret) goto out; } /* once recovery info is written, don't need to tack this */ - remove_ino_entry(sbi, ino, APPEND_INO); + f2fs_remove_ino_entry(sbi, ino, APPEND_INO); clear_inode_flag(inode, FI_APPEND_WRITE); flush_out: - if (!atomic) + if (!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER) ret = f2fs_issue_flush(sbi, inode->i_ino); if (!ret) { - remove_ino_entry(sbi, ino, UPDATE_INO); + f2fs_remove_ino_entry(sbi, ino, UPDATE_INO); clear_inode_flag(inode, FI_UPDATE_WRITE); - remove_ino_entry(sbi, ino, FLUSH_INO); + f2fs_remove_ino_entry(sbi, ino, FLUSH_INO); } f2fs_update_time(sbi, REQ_TIME); out: @@ -352,7 +356,7 @@ static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs, switch (whence) { case SEEK_DATA: if ((blkaddr == NEW_ADDR && dirty == pgofs) || - (blkaddr != NEW_ADDR && blkaddr != NULL_ADDR)) + is_valid_blkaddr(blkaddr)) return true; break; case SEEK_HOLE: @@ -392,13 +396,13 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) { set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, pgofs, LOOKUP_NODE); if (err && err != -ENOENT) { goto fail; } else if (err == -ENOENT) { /* direct node does not exists */ if (whence == SEEK_DATA) { - pgofs = get_next_page_offset(&dn, pgofs); + pgofs = f2fs_get_next_page_offset(&dn, pgofs); continue; } else { goto found; @@ -412,6 +416,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) dn.ofs_in_node++, pgofs++, data_ofs = (loff_t)pgofs << PAGE_SHIFT) { block_t blkaddr; + blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); @@ -486,7 +491,7 @@ static int f2fs_file_open(struct inode *inode, struct file *filp) return dquot_file_open(inode, filp); } -void truncate_data_blocks_range(struct dnode_of_data *dn, int count) +void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct f2fs_node *raw_node; @@ -502,12 +507,13 @@ void truncate_data_blocks_range(struct dnode_of_data *dn, int count) for (; count > 0; count--, addr++, dn->ofs_in_node++) { block_t blkaddr = le32_to_cpu(*addr); + if (blkaddr == NULL_ADDR) continue; dn->data_blkaddr = NULL_ADDR; - set_data_blkaddr(dn); - invalidate_blocks(sbi, blkaddr); + f2fs_set_data_blkaddr(dn); + f2fs_invalidate_blocks(sbi, blkaddr); if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN); nr_free++; @@ -519,7 +525,7 @@ void truncate_data_blocks_range(struct dnode_of_data *dn, int count) * once we invalidate valid blkaddr in range [ofs, ofs + count], * we will invalidate all blkaddr in the whole range. */ - fofs = start_bidx_of_node(ofs_of_node(dn->node_page), + fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + ofs; f2fs_update_extent_cache_range(dn, fofs, 0, len); dec_valid_block_count(sbi, dn->inode, nr_free); @@ -531,15 +537,15 @@ void truncate_data_blocks_range(struct dnode_of_data *dn, int count) dn->ofs_in_node, nr_free); } -void truncate_data_blocks(struct dnode_of_data *dn) +void f2fs_truncate_data_blocks(struct dnode_of_data *dn) { - truncate_data_blocks_range(dn, ADDRS_PER_BLOCK); + f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK); } static int truncate_partial_data_page(struct inode *inode, u64 from, bool cache_only) { - unsigned offset = from & (PAGE_SIZE - 1); + loff_t offset = from & (PAGE_SIZE - 1); pgoff_t index = from >> PAGE_SHIFT; struct address_space *mapping = inode->i_mapping; struct page *page; @@ -555,7 +561,7 @@ static int truncate_partial_data_page(struct inode *inode, u64 from, return 0; } - page = get_lock_data_page(inode, index, true); + page = f2fs_get_lock_data_page(inode, index, true); if (IS_ERR(page)) return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page); truncate_out: @@ -570,7 +576,7 @@ truncate_out: return 0; } -int truncate_blocks(struct inode *inode, u64 from, bool lock) +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; @@ -589,21 +595,21 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) if (lock) f2fs_lock_op(sbi); - ipage = get_node_page(sbi, inode->i_ino); + ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto out; } if (f2fs_has_inline_data(inode)) { - truncate_inline_inode(inode, ipage, from); + f2fs_truncate_inline_inode(inode, ipage, from); f2fs_put_page(ipage, 1); truncate_page = true; goto out; } set_new_dnode(&dn, inode, ipage, NULL, 0); - err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA); + err = f2fs_get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA); if (err) { if (err == -ENOENT) goto free_next; @@ -616,13 +622,13 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) f2fs_bug_on(sbi, count < 0); if (dn.ofs_in_node || IS_INODE(dn.node_page)) { - truncate_data_blocks_range(&dn, count); + f2fs_truncate_data_blocks_range(&dn, count); free_from += count; } f2fs_put_dnode(&dn); free_next: - err = truncate_inode_blocks(inode, free_from); + err = f2fs_truncate_inode_blocks(inode, free_from); out: if (lock) f2fs_unlock_op(sbi); @@ -661,7 +667,7 @@ int f2fs_truncate(struct inode *inode) return err; } - err = truncate_blocks(inode, i_size_read(inode), true); + err = f2fs_truncate_blocks(inode, i_size_read(inode), true); if (err) return err; @@ -686,16 +692,16 @@ int f2fs_getattr(const struct path *path, struct kstat *stat, stat->btime.tv_nsec = fi->i_crtime.tv_nsec; } - flags = fi->i_flags & (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL); - if (flags & FS_APPEND_FL) + flags = fi->i_flags & F2FS_FL_USER_VISIBLE; + if (flags & F2FS_APPEND_FL) stat->attributes |= STATX_ATTR_APPEND; - if (flags & FS_COMPR_FL) + if (flags & F2FS_COMPR_FL) stat->attributes |= STATX_ATTR_COMPRESSED; if (f2fs_encrypted_inode(inode)) stat->attributes |= STATX_ATTR_ENCRYPTED; - if (flags & FS_IMMUTABLE_FL) + if (flags & F2FS_IMMUTABLE_FL) stat->attributes |= STATX_ATTR_IMMUTABLE; - if (flags & FS_NODUMP_FL) + if (flags & F2FS_NODUMP_FL) stat->attributes |= STATX_ATTR_NODUMP; stat->attributes_mask |= (STATX_ATTR_APPEND | @@ -811,7 +817,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) __setattr_copy(inode, attr); if (attr->ia_valid & ATTR_MODE) { - err = posix_acl_chmod(inode, get_inode_mode(inode)); + err = posix_acl_chmod(inode, f2fs_get_inode_mode(inode)); if (err || is_inode_flag_set(inode, FI_ACL_MODE)) { inode->i_mode = F2FS_I(inode)->i_acl_mode; clear_inode_flag(inode, FI_ACL_MODE); @@ -850,7 +856,7 @@ static int fill_zero(struct inode *inode, pgoff_t index, f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); - page = get_new_data_page(inode, NULL, index, false); + page = f2fs_get_new_data_page(inode, NULL, index, false); f2fs_unlock_op(sbi); if (IS_ERR(page)) @@ -863,7 +869,7 @@ static int fill_zero(struct inode *inode, pgoff_t index, return 0; } -int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) +int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) { int err; @@ -872,10 +878,11 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) pgoff_t end_offset, count; set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, pg_start, LOOKUP_NODE); if (err) { if (err == -ENOENT) { - pg_start = get_next_page_offset(&dn, pg_start); + pg_start = f2fs_get_next_page_offset(&dn, + pg_start); continue; } return err; @@ -886,7 +893,7 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset); - truncate_data_blocks_range(&dn, count); + f2fs_truncate_data_blocks_range(&dn, count); f2fs_put_dnode(&dn); pg_start += count; @@ -942,7 +949,7 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) blk_end - 1); f2fs_lock_op(sbi); - ret = truncate_hole(inode, pg_start, pg_end); + ret = f2fs_truncate_hole(inode, pg_start, pg_end); f2fs_unlock_op(sbi); up_write(&F2FS_I(inode)->i_mmap_sem); } @@ -960,7 +967,7 @@ static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr, next_dnode: set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, off, LOOKUP_NODE_RA); + ret = f2fs_get_dnode_of_data(&dn, off, LOOKUP_NODE_RA); if (ret && ret != -ENOENT) { return ret; } else if (ret == -ENOENT) { @@ -977,7 +984,7 @@ next_dnode: for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) { *blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); - if (!is_checkpointed_data(sbi, *blkaddr)) { + if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) { if (test_opt(sbi, LFS)) { f2fs_put_dnode(&dn); @@ -1010,10 +1017,10 @@ static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr, continue; set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA); + ret = f2fs_get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA); if (ret) { dec_valid_block_count(sbi, inode, 1); - invalidate_blocks(sbi, *blkaddr); + f2fs_invalidate_blocks(sbi, *blkaddr); } else { f2fs_update_data_blkaddr(&dn, *blkaddr); } @@ -1043,18 +1050,18 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, pgoff_t ilen; set_new_dnode(&dn, dst_inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, dst + i, ALLOC_NODE); + ret = f2fs_get_dnode_of_data(&dn, dst + i, ALLOC_NODE); if (ret) return ret; - get_node_info(sbi, dn.nid, &ni); + f2fs_get_node_info(sbi, dn.nid, &ni); ilen = min((pgoff_t) ADDRS_PER_PAGE(dn.node_page, dst_inode) - dn.ofs_in_node, len - i); do { dn.data_blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); - truncate_data_blocks_range(&dn, 1); + f2fs_truncate_data_blocks_range(&dn, 1); if (do_replace[i]) { f2fs_i_blocks_write(src_inode, @@ -1077,10 +1084,11 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, } else { struct page *psrc, *pdst; - psrc = get_lock_data_page(src_inode, src + i, true); + psrc = f2fs_get_lock_data_page(src_inode, + src + i, true); if (IS_ERR(psrc)) return PTR_ERR(psrc); - pdst = get_new_data_page(dst_inode, NULL, dst + i, + pdst = f2fs_get_new_data_page(dst_inode, NULL, dst + i, true); if (IS_ERR(pdst)) { f2fs_put_page(psrc, 1); @@ -1091,7 +1099,8 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, f2fs_put_page(pdst, 1); f2fs_put_page(psrc, 1); - ret = truncate_hole(src_inode, src + i, src + i + 1); + ret = f2fs_truncate_hole(src_inode, + src + i, src + i + 1); if (ret) return ret; i++; @@ -1144,7 +1153,7 @@ static int __exchange_data_block(struct inode *src_inode, return 0; roll_back: - __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, len); + __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, olen); kvfree(src_blkaddr); kvfree(do_replace); return ret; @@ -1187,7 +1196,7 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) pg_end = (offset + len) >> PAGE_SHIFT; /* avoid gc operation during block exchange */ - down_write(&F2FS_I(inode)->dio_rwsem[WRITE]); + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); down_write(&F2FS_I(inode)->i_mmap_sem); /* write out all dirty pages from offset */ @@ -1208,12 +1217,12 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) new_size = i_size_read(inode) - len; truncate_pagecache(inode, new_size); - ret = truncate_blocks(inode, new_size, true); + ret = f2fs_truncate_blocks(inode, new_size, true); if (!ret) f2fs_i_size_write(inode, new_size); out_unlock: up_write(&F2FS_I(inode)->i_mmap_sem); - up_write(&F2FS_I(inode)->dio_rwsem[WRITE]); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); return ret; } @@ -1233,7 +1242,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, } dn->ofs_in_node = ofs_in_node; - ret = reserve_new_blocks(dn, count); + ret = f2fs_reserve_new_blocks(dn, count); if (ret) return ret; @@ -1242,7 +1251,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, dn->data_blkaddr = datablock_addr(dn->inode, dn->node_page, dn->ofs_in_node); /* - * reserve_new_blocks will not guarantee entire block + * f2fs_reserve_new_blocks will not guarantee entire block * allocation. */ if (dn->data_blkaddr == NULL_ADDR) { @@ -1250,9 +1259,9 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, break; } if (dn->data_blkaddr != NEW_ADDR) { - invalidate_blocks(sbi, dn->data_blkaddr); + f2fs_invalidate_blocks(sbi, dn->data_blkaddr); dn->data_blkaddr = NEW_ADDR; - set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn); } } @@ -1318,7 +1327,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, f2fs_lock_op(sbi); set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, index, ALLOC_NODE); + ret = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE); if (ret) { f2fs_unlock_op(sbi); goto out; @@ -1389,10 +1398,10 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); /* avoid gc operation during block exchange */ - down_write(&F2FS_I(inode)->dio_rwsem[WRITE]); + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); down_write(&F2FS_I(inode)->i_mmap_sem); - ret = truncate_blocks(inode, i_size_read(inode), true); + ret = f2fs_truncate_blocks(inode, i_size_read(inode), true); if (ret) goto out; @@ -1430,7 +1439,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_i_size_write(inode, new_size); out: up_write(&F2FS_I(inode)->i_mmap_sem); - up_write(&F2FS_I(inode)->dio_rwsem[WRITE]); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); return ret; } @@ -1473,7 +1482,7 @@ static int expand_inode_data(struct inode *inode, loff_t offset, last_off = map.m_lblk + map.m_len - 1; /* update new size to the failed position */ - new_size = (last_off == pg_end) ? offset + len: + new_size = (last_off == pg_end) ? offset + len : (loff_t)(last_off + 1) << PAGE_SHIFT; } else { new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end; @@ -1553,13 +1562,13 @@ static int f2fs_release_file(struct inode *inode, struct file *filp) /* some remained atomic pages should discarded */ if (f2fs_is_atomic_file(inode)) - drop_inmem_pages(inode); + f2fs_drop_inmem_pages(inode); if (f2fs_is_volatile_file(inode)) { - clear_inode_flag(inode, FI_VOLATILE_FILE); - stat_dec_volatile_write(inode); set_inode_flag(inode, FI_DROP_CACHE); filemap_fdatawrite(inode->i_mapping); clear_inode_flag(inode, FI_DROP_CACHE); + clear_inode_flag(inode, FI_VOLATILE_FILE); + stat_dec_volatile_write(inode); } return 0; } @@ -1576,7 +1585,7 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id) */ if (f2fs_is_atomic_file(inode) && F2FS_I(inode)->inmem_task == current) - drop_inmem_pages(inode); + f2fs_drop_inmem_pages(inode); return 0; } @@ -1584,8 +1593,15 @@ static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); - unsigned int flags = fi->i_flags & - (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL); + unsigned int flags = fi->i_flags; + + if (file_is_encrypt(inode)) + flags |= F2FS_ENCRYPT_FL; + if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) + flags |= F2FS_INLINE_DATA_FL; + + flags &= F2FS_FL_USER_VISIBLE; + return put_user(flags, (int __user *)arg); } @@ -1602,15 +1618,15 @@ static int __f2fs_ioc_setflags(struct inode *inode, unsigned int flags) oldflags = fi->i_flags; - if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) + if ((flags ^ oldflags) & (F2FS_APPEND_FL | F2FS_IMMUTABLE_FL)) if (!capable(CAP_LINUX_IMMUTABLE)) return -EPERM; - flags = flags & (FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL); - flags |= oldflags & ~(FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL); + flags = flags & F2FS_FL_USER_MODIFIABLE; + flags |= oldflags & ~F2FS_FL_USER_MODIFIABLE; fi->i_flags = flags; - if (fi->i_flags & FS_PROJINHERIT_FL) + if (fi->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); else clear_inode_flag(inode, FI_PROJ_INHERIT); @@ -1670,6 +1686,8 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) inode_lock(inode); + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + if (f2fs_is_atomic_file(inode)) goto out; @@ -1677,28 +1695,25 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) if (ret) goto out; - set_inode_flag(inode, FI_ATOMIC_FILE); - set_inode_flag(inode, FI_HOT_DATA); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); - if (!get_dirty_pages(inode)) - goto inc_stat; + goto skip_flush; f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, "Unexpected flush for atomic writes: ino=%lu, npages=%u", inode->i_ino, get_dirty_pages(inode)); ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); - if (ret) { - clear_inode_flag(inode, FI_ATOMIC_FILE); - clear_inode_flag(inode, FI_HOT_DATA); + if (ret) goto out; - } +skip_flush: + set_inode_flag(inode, FI_ATOMIC_FILE); + clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); -inc_stat: F2FS_I(inode)->inmem_task = current; stat_inc_atomic_write(inode); stat_update_max_atomic_write(inode); out: + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); inode_unlock(inode); mnt_drop_write_file(filp); return ret; @@ -1718,27 +1733,33 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) inode_lock(inode); - down_write(&F2FS_I(inode)->dio_rwsem[WRITE]); + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - if (f2fs_is_volatile_file(inode)) + if (f2fs_is_volatile_file(inode)) { + ret = -EINVAL; goto err_out; + } if (f2fs_is_atomic_file(inode)) { - ret = commit_inmem_pages(inode); + ret = f2fs_commit_inmem_pages(inode); if (ret) goto err_out; ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); if (!ret) { clear_inode_flag(inode, FI_ATOMIC_FILE); - clear_inode_flag(inode, FI_HOT_DATA); + F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC] = 0; stat_dec_atomic_write(inode); } } else { ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false); } err_out: - up_write(&F2FS_I(inode)->dio_rwsem[WRITE]); + if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) { + clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); + ret = -EINVAL; + } + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); inode_unlock(inode); mnt_drop_write_file(filp); return ret; @@ -1823,7 +1844,7 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp) inode_lock(inode); if (f2fs_is_atomic_file(inode)) - drop_inmem_pages(inode); + f2fs_drop_inmem_pages(inode); if (f2fs_is_volatile_file(inode)) { clear_inode_flag(inode, FI_VOLATILE_FILE); stat_dec_volatile_write(inode); @@ -1851,9 +1872,11 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) if (get_user(in, (__u32 __user *)arg)) return -EFAULT; - ret = mnt_want_write_file(filp); - if (ret) - return ret; + if (in != F2FS_GOING_DOWN_FULLSYNC) { + ret = mnt_want_write_file(filp); + if (ret) + return ret; + } switch (in) { case F2FS_GOING_DOWN_FULLSYNC: @@ -1878,7 +1901,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) f2fs_stop_checkpoint(sbi, false); break; case F2FS_GOING_DOWN_METAFLUSH: - sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO); + f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO); f2fs_stop_checkpoint(sbi, false); break; default: @@ -1886,15 +1909,16 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) goto out; } - stop_gc_thread(sbi); - stop_discard_thread(sbi); + f2fs_stop_gc_thread(sbi); + f2fs_stop_discard_thread(sbi); - drop_discard_cmd(sbi); + f2fs_drop_discard_cmd(sbi); clear_opt(sbi, DISCARD); f2fs_update_time(sbi, REQ_TIME); out: - mnt_drop_write_file(filp); + if (in != F2FS_GOING_DOWN_FULLSYNC) + mnt_drop_write_file(filp); return ret; } @@ -2053,15 +2077,15 @@ static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + end = range.start + range.len; + if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) { + return -EINVAL; + } + ret = mnt_want_write_file(filp); if (ret) return ret; - end = range.start + range.len; - if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) { - ret = -EINVAL; - goto out; - } do_more: if (!range.sync) { if (!mutex_trylock(&sbi->gc_mutex)) { @@ -2081,7 +2105,7 @@ out: return ret; } -static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) +static int f2fs_ioc_f2fs_write_checkpoint(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -2110,7 +2134,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, struct inode *inode = file_inode(filp); struct f2fs_map_blocks map = { .m_next_extent = NULL, .m_seg_type = NO_CHECK_TYPE }; - struct extent_info ei = {0,0,0}; + struct extent_info ei = {0, 0, 0}; pgoff_t pg_start, pg_end, next_pgofs; unsigned int blk_per_seg = sbi->blocks_per_seg; unsigned int total = 0, sec_num; @@ -2119,7 +2143,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, int err; /* if in-place-update policy is enabled, don't waste time here */ - if (should_update_inplace(inode, NULL)) + if (f2fs_should_update_inplace(inode, NULL)) return -EINVAL; pg_start = range->start >> PAGE_SHIFT; @@ -2214,7 +2238,7 @@ do_map: while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) { struct page *page; - page = get_lock_data_page(inode, idx, true); + page = f2fs_get_lock_data_page(inode, idx, true); if (IS_ERR(page)) { err = PTR_ERR(page); goto clear_out; @@ -2325,12 +2349,12 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, } inode_lock(src); - down_write(&F2FS_I(src)->dio_rwsem[WRITE]); + down_write(&F2FS_I(src)->i_gc_rwsem[WRITE]); if (src != dst) { ret = -EBUSY; if (!inode_trylock(dst)) goto out; - if (!down_write_trylock(&F2FS_I(dst)->dio_rwsem[WRITE])) { + if (!down_write_trylock(&F2FS_I(dst)->i_gc_rwsem[WRITE])) { inode_unlock(dst); goto out; } @@ -2392,11 +2416,11 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, f2fs_unlock_op(sbi); out_unlock: if (src != dst) { - up_write(&F2FS_I(dst)->dio_rwsem[WRITE]); + up_write(&F2FS_I(dst)->i_gc_rwsem[WRITE]); inode_unlock(dst); } out: - up_write(&F2FS_I(src)->dio_rwsem[WRITE]); + up_write(&F2FS_I(src)->i_gc_rwsem[WRITE]); inode_unlock(src); return ret; } @@ -2554,7 +2578,7 @@ static int f2fs_ioc_setproject(struct file *filp, __u32 projid) if (IS_NOQUOTA(inode)) goto out_unlock; - ipage = get_node_page(sbi, inode->i_ino); + ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto out_unlock; @@ -2568,7 +2592,9 @@ static int f2fs_ioc_setproject(struct file *filp, __u32 projid) } f2fs_put_page(ipage, 1); - dquot_initialize(inode); + err = dquot_initialize(inode); + if (err) + goto out_unlock; transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); if (!IS_ERR(transfer_to[PRJQUOTA])) { @@ -2601,17 +2627,17 @@ static inline __u32 f2fs_iflags_to_xflags(unsigned long iflags) { __u32 xflags = 0; - if (iflags & FS_SYNC_FL) + if (iflags & F2FS_SYNC_FL) xflags |= FS_XFLAG_SYNC; - if (iflags & FS_IMMUTABLE_FL) + if (iflags & F2FS_IMMUTABLE_FL) xflags |= FS_XFLAG_IMMUTABLE; - if (iflags & FS_APPEND_FL) + if (iflags & F2FS_APPEND_FL) xflags |= FS_XFLAG_APPEND; - if (iflags & FS_NODUMP_FL) + if (iflags & F2FS_NODUMP_FL) xflags |= FS_XFLAG_NODUMP; - if (iflags & FS_NOATIME_FL) + if (iflags & F2FS_NOATIME_FL) xflags |= FS_XFLAG_NOATIME; - if (iflags & FS_PROJINHERIT_FL) + if (iflags & F2FS_PROJINHERIT_FL) xflags |= FS_XFLAG_PROJINHERIT; return xflags; } @@ -2620,31 +2646,23 @@ static inline __u32 f2fs_iflags_to_xflags(unsigned long iflags) FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \ FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT) -/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */ -#define F2FS_FL_XFLAG_VISIBLE (FS_SYNC_FL | \ - FS_IMMUTABLE_FL | \ - FS_APPEND_FL | \ - FS_NODUMP_FL | \ - FS_NOATIME_FL | \ - FS_PROJINHERIT_FL) - /* Transfer xflags flags to internal */ static inline unsigned long f2fs_xflags_to_iflags(__u32 xflags) { unsigned long iflags = 0; if (xflags & FS_XFLAG_SYNC) - iflags |= FS_SYNC_FL; + iflags |= F2FS_SYNC_FL; if (xflags & FS_XFLAG_IMMUTABLE) - iflags |= FS_IMMUTABLE_FL; + iflags |= F2FS_IMMUTABLE_FL; if (xflags & FS_XFLAG_APPEND) - iflags |= FS_APPEND_FL; + iflags |= F2FS_APPEND_FL; if (xflags & FS_XFLAG_NODUMP) - iflags |= FS_NODUMP_FL; + iflags |= F2FS_NODUMP_FL; if (xflags & FS_XFLAG_NOATIME) - iflags |= FS_NOATIME_FL; + iflags |= F2FS_NOATIME_FL; if (xflags & FS_XFLAG_PROJINHERIT) - iflags |= FS_PROJINHERIT_FL; + iflags |= F2FS_PROJINHERIT_FL; return iflags; } @@ -2657,7 +2675,7 @@ static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) memset(&fa, 0, sizeof(struct fsxattr)); fa.fsx_xflags = f2fs_iflags_to_xflags(fi->i_flags & - (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL)); + F2FS_FL_USER_VISIBLE); if (f2fs_sb_has_project_quota(inode->i_sb)) fa.fsx_projid = (__u32)from_kprojid(&init_user_ns, @@ -2717,12 +2735,14 @@ int f2fs_pin_file_control(struct inode *inode, bool inc) /* Use i_gc_failures for normal file as a risk signal. */ if (inc) - f2fs_i_gc_failures_write(inode, fi->i_gc_failures + 1); + f2fs_i_gc_failures_write(inode, + fi->i_gc_failures[GC_FAILURE_PIN] + 1); - if (fi->i_gc_failures > sbi->gc_pin_file_threshold) { + if (fi->i_gc_failures[GC_FAILURE_PIN] > sbi->gc_pin_file_threshold) { f2fs_msg(sbi->sb, KERN_WARNING, "%s: Enable GC = ino %lx after %x GC trials\n", - __func__, inode->i_ino, fi->i_gc_failures); + __func__, inode->i_ino, + fi->i_gc_failures[GC_FAILURE_PIN]); clear_inode_flag(inode, FI_PIN_FILE); return -EAGAIN; } @@ -2753,14 +2773,14 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) inode_lock(inode); - if (should_update_outplace(inode, NULL)) { + if (f2fs_should_update_outplace(inode, NULL)) { ret = -EINVAL; goto out; } if (!pin) { clear_inode_flag(inode, FI_PIN_FILE); - F2FS_I(inode)->i_gc_failures = 1; + F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = 1; goto done; } @@ -2773,7 +2793,7 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) goto out; set_inode_flag(inode, FI_PIN_FILE); - ret = F2FS_I(inode)->i_gc_failures; + ret = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN]; done: f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); out: @@ -2788,7 +2808,7 @@ static int f2fs_ioc_get_pin_file(struct file *filp, unsigned long arg) __u32 pin = 0; if (is_inode_flag_set(inode, FI_PIN_FILE)) - pin = F2FS_I(inode)->i_gc_failures; + pin = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN]; return put_user(pin, (u32 __user *)arg); } @@ -2812,9 +2832,9 @@ int f2fs_precache_extents(struct inode *inode) while (map.m_lblk < end) { map.m_len = end - map.m_lblk; - down_write(&fi->dio_rwsem[WRITE]); + down_write(&fi->i_gc_rwsem[WRITE]); err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_PRECACHE); - up_write(&fi->dio_rwsem[WRITE]); + up_write(&fi->i_gc_rwsem[WRITE]); if (err) return err; @@ -2866,7 +2886,7 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case F2FS_IOC_GARBAGE_COLLECT_RANGE: return f2fs_ioc_gc_range(filp, arg); case F2FS_IOC_WRITE_CHECKPOINT: - return f2fs_ioc_write_checkpoint(filp, arg); + return f2fs_ioc_f2fs_write_checkpoint(filp, arg); case F2FS_IOC_DEFRAGMENT: return f2fs_ioc_defragment(filp, arg); case F2FS_IOC_MOVE_RANGE: @@ -2894,7 +2914,6 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - struct blk_plug plug; ssize_t ret; if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) @@ -2924,6 +2943,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) iov_iter_count(from)) || f2fs_has_inline_data(inode) || f2fs_force_buffered_io(inode, WRITE)) { + clear_inode_flag(inode, + FI_NO_PREALLOC); inode_unlock(inode); return -EAGAIN; } @@ -2939,9 +2960,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) return err; } } - blk_start_plug(&plug); ret = __generic_file_write_iter(iocb, from); - blk_finish_plug(&plug); clear_inode_flag(inode, FI_NO_PREALLOC); /* if we couldn't write data, we should deallocate blocks. */ diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 9327411fd93b..9093be6e7a7d 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -76,7 +76,7 @@ static int gc_thread_func(void *data) * invalidated soon after by user update or deletion. * So, I'd like to wait some time to collect dirty segments. */ - if (gc_th->gc_urgent) { + if (sbi->gc_mode == GC_URGENT) { wait_ms = gc_th->urgent_sleep_time; mutex_lock(&sbi->gc_mutex); goto do_gc; @@ -114,7 +114,7 @@ next: return 0; } -int start_gc_thread(struct f2fs_sb_info *sbi) +int f2fs_start_gc_thread(struct f2fs_sb_info *sbi) { struct f2fs_gc_kthread *gc_th; dev_t dev = sbi->sb->s_bdev->bd_dev; @@ -131,8 +131,6 @@ int start_gc_thread(struct f2fs_sb_info *sbi) gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME; gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME; - gc_th->gc_idle = 0; - gc_th->gc_urgent = 0; gc_th->gc_wake= 0; sbi->gc_thread = gc_th; @@ -148,7 +146,7 @@ out: return err; } -void stop_gc_thread(struct f2fs_sb_info *sbi) +void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi) { struct f2fs_gc_kthread *gc_th = sbi->gc_thread; if (!gc_th) @@ -158,21 +156,19 @@ void stop_gc_thread(struct f2fs_sb_info *sbi) sbi->gc_thread = NULL; } -static int select_gc_type(struct f2fs_gc_kthread *gc_th, int gc_type) +static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type) { int gc_mode = (gc_type == BG_GC) ? GC_CB : GC_GREEDY; - if (!gc_th) - return gc_mode; - - if (gc_th->gc_idle) { - if (gc_th->gc_idle == 1) - gc_mode = GC_CB; - else if (gc_th->gc_idle == 2) - gc_mode = GC_GREEDY; - } - if (gc_th->gc_urgent) + switch (sbi->gc_mode) { + case GC_IDLE_CB: + gc_mode = GC_CB; + break; + case GC_IDLE_GREEDY: + case GC_URGENT: gc_mode = GC_GREEDY; + break; + } return gc_mode; } @@ -187,7 +183,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, p->max_search = dirty_i->nr_dirty[type]; p->ofs_unit = 1; } else { - p->gc_mode = select_gc_type(sbi->gc_thread, gc_type); + p->gc_mode = select_gc_type(sbi, gc_type); p->dirty_segmap = dirty_i->dirty_segmap[DIRTY]; p->max_search = dirty_i->nr_dirty[DIRTY]; p->ofs_unit = sbi->segs_per_sec; @@ -195,7 +191,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, /* we need to check every dirty segments in the FG_GC case */ if (gc_type != FG_GC && - (sbi->gc_thread && !sbi->gc_thread->gc_urgent) && + (sbi->gc_mode != GC_URGENT) && p->max_search > sbi->max_victim_search) p->max_search = sbi->max_victim_search; @@ -234,10 +230,6 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi) for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) { if (sec_usage_check(sbi, secno)) continue; - - if (no_fggc_candidate(sbi, secno)) - continue; - clear_bit(secno, dirty_i->victim_secmap); return GET_SEG_FROM_SEC(sbi, secno); } @@ -377,9 +369,6 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, goto next; if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap)) goto next; - if (gc_type == FG_GC && p.alloc_mode == LFS && - no_fggc_candidate(sbi, secno)) - goto next; cost = get_gc_cost(sbi, segno, &p); @@ -440,7 +429,7 @@ static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode) iput(inode); return; } - new_ie = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); + new_ie = f2fs_kmem_cache_alloc(f2fs_inode_entry_slab, GFP_NOFS); new_ie->inode = inode; f2fs_radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie); @@ -454,7 +443,7 @@ static void put_gc_inode(struct gc_inode_list *gc_list) radix_tree_delete(&gc_list->iroot, ie->inode->i_ino); iput(ie->inode); list_del(&ie->list); - kmem_cache_free(inode_entry_slab, ie); + kmem_cache_free(f2fs_inode_entry_slab, ie); } } @@ -484,12 +473,16 @@ static void gc_node_segment(struct f2fs_sb_info *sbi, block_t start_addr; int off; int phase = 0; + bool fggc = (gc_type == FG_GC); start_addr = START_BLOCK(sbi, segno); next_step: entry = sum; + if (fggc && phase == 2) + atomic_inc(&sbi->wb_sync_req[NODE]); + for (off = 0; off < sbi->blocks_per_seg; off++, entry++) { nid_t nid = le32_to_cpu(entry->nid); struct page *node_page; @@ -503,39 +496,42 @@ next_step: continue; if (phase == 0) { - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, + f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, META_NAT, true); continue; } if (phase == 1) { - ra_node_page(sbi, nid); + f2fs_ra_node_page(sbi, nid); continue; } /* phase == 2 */ - node_page = get_node_page(sbi, nid); + node_page = f2fs_get_node_page(sbi, nid); if (IS_ERR(node_page)) continue; - /* block may become invalid during get_node_page */ + /* block may become invalid during f2fs_get_node_page */ if (check_valid_map(sbi, segno, off) == 0) { f2fs_put_page(node_page, 1); continue; } - get_node_info(sbi, nid, &ni); + f2fs_get_node_info(sbi, nid, &ni); if (ni.blk_addr != start_addr + off) { f2fs_put_page(node_page, 1); continue; } - move_node_page(node_page, gc_type); + f2fs_move_node_page(node_page, gc_type); stat_inc_node_blk_count(sbi, 1, gc_type); } if (++phase < 3) goto next_step; + + if (fggc) + atomic_dec(&sbi->wb_sync_req[NODE]); } /* @@ -545,7 +541,7 @@ next_step: * as indirect or double indirect node blocks, are given, it must be a caller's * bug. */ -block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode) +block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode) { unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4; unsigned int bidx; @@ -576,11 +572,11 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, nid = le32_to_cpu(sum->nid); ofs_in_node = le16_to_cpu(sum->ofs_in_node); - node_page = get_node_page(sbi, nid); + node_page = f2fs_get_node_page(sbi, nid); if (IS_ERR(node_page)) return false; - get_node_info(sbi, nid, dni); + f2fs_get_node_info(sbi, nid, dni); if (sum->version != dni->version) { f2fs_msg(sbi->sb, KERN_WARNING, @@ -603,7 +599,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, * This can be used to move blocks, aka LBAs, directly on disk. */ static void move_data_block(struct inode *inode, block_t bidx, - unsigned int segno, int off) + int gc_type, unsigned int segno, int off) { struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), @@ -614,6 +610,7 @@ static void move_data_block(struct inode *inode, block_t bidx, .op_flags = 0, .encrypted_page = NULL, .in_list = false, + .retry = false, }; struct dnode_of_data dn; struct f2fs_summary sum; @@ -621,6 +618,7 @@ static void move_data_block(struct inode *inode, block_t bidx, struct page *page; block_t newaddr; int err; + bool lfs_mode = test_opt(fio.sbi, LFS); /* do not read out */ page = f2fs_grab_cache_page(inode->i_mapping, bidx, false); @@ -630,8 +628,11 @@ static void move_data_block(struct inode *inode, block_t bidx, if (!check_valid_map(F2FS_I_SB(inode), segno, off)) goto out; - if (f2fs_is_atomic_file(inode)) + if (f2fs_is_atomic_file(inode)) { + F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++; + F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++; goto out; + } if (f2fs_is_pinned_file(inode)) { f2fs_pin_file_control(inode, true); @@ -639,7 +640,7 @@ static void move_data_block(struct inode *inode, block_t bidx, } set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, bidx, LOOKUP_NODE); if (err) goto out; @@ -654,14 +655,17 @@ static void move_data_block(struct inode *inode, block_t bidx, */ f2fs_wait_on_page_writeback(page, DATA, true); - get_node_info(fio.sbi, dn.nid, &ni); + f2fs_get_node_info(fio.sbi, dn.nid, &ni); set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); /* read page */ fio.page = page; fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr; - allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, + if (lfs_mode) + down_write(&fio.sbi->io_order_lock); + + f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, &sum, CURSEG_COLD_DATA, NULL, false); fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi), @@ -693,6 +697,7 @@ static void move_data_block(struct inode *inode, block_t bidx, dec_page_count(fio.sbi, F2FS_DIRTY_META); set_page_writeback(fio.encrypted_page); + ClearPageError(page); /* allocate block address */ f2fs_wait_on_page_writeback(dn.node_page, NODE, true); @@ -700,8 +705,8 @@ static void move_data_block(struct inode *inode, block_t bidx, fio.op = REQ_OP_WRITE; fio.op_flags = REQ_SYNC; fio.new_blkaddr = newaddr; - err = f2fs_submit_page_write(&fio); - if (err) { + f2fs_submit_page_write(&fio); + if (fio.retry) { if (PageWriteback(fio.encrypted_page)) end_page_writeback(fio.encrypted_page); goto put_page_out; @@ -716,8 +721,10 @@ static void move_data_block(struct inode *inode, block_t bidx, put_page_out: f2fs_put_page(fio.encrypted_page, 1); recover_block: + if (lfs_mode) + up_write(&fio.sbi->io_order_lock); if (err) - __f2fs_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr, + f2fs_do_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr, true, true); put_out: f2fs_put_dnode(&dn); @@ -730,15 +737,18 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type, { struct page *page; - page = get_lock_data_page(inode, bidx, true); + page = f2fs_get_lock_data_page(inode, bidx, true); if (IS_ERR(page)) return; if (!check_valid_map(F2FS_I_SB(inode), segno, off)) goto out; - if (f2fs_is_atomic_file(inode)) + if (f2fs_is_atomic_file(inode)) { + F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++; + F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++; goto out; + } if (f2fs_is_pinned_file(inode)) { if (gc_type == FG_GC) f2fs_pin_file_control(inode, true); @@ -772,15 +782,20 @@ retry: f2fs_wait_on_page_writeback(page, DATA, true); if (clear_page_dirty_for_io(page)) { inode_dec_dirty_pages(inode); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); } set_cold_data(page); - err = do_write_data_page(&fio); - if (err == -ENOMEM && is_dirty) { - congestion_wait(BLK_RW_ASYNC, HZ/50); - goto retry; + err = f2fs_do_write_data_page(&fio); + if (err) { + clear_cold_data(page); + if (err == -ENOMEM) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; + } + if (is_dirty) + set_page_dirty(page); } } out: @@ -824,13 +839,13 @@ next_step: continue; if (phase == 0) { - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, + f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, META_NAT, true); continue; } if (phase == 1) { - ra_node_page(sbi, nid); + f2fs_ra_node_page(sbi, nid); continue; } @@ -839,7 +854,7 @@ next_step: continue; if (phase == 2) { - ra_node_page(sbi, dni.ino); + f2fs_ra_node_page(sbi, dni.ino); continue; } @@ -850,23 +865,23 @@ next_step: if (IS_ERR(inode) || is_bad_inode(inode)) continue; - /* if encrypted inode, let's go phase 3 */ - if (f2fs_encrypted_file(inode)) { + /* if inode uses special I/O path, let's go phase 3 */ + if (f2fs_post_read_required(inode)) { add_gc_inode(gc_list, inode); continue; } if (!down_write_trylock( - &F2FS_I(inode)->dio_rwsem[WRITE])) { + &F2FS_I(inode)->i_gc_rwsem[WRITE])) { iput(inode); continue; } - start_bidx = start_bidx_of_node(nofs, inode); - data_page = get_read_data_page(inode, + start_bidx = f2fs_start_bidx_of_node(nofs, inode); + data_page = f2fs_get_read_data_page(inode, start_bidx + ofs_in_node, REQ_RAHEAD, true); - up_write(&F2FS_I(inode)->dio_rwsem[WRITE]); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); if (IS_ERR(data_page)) { iput(inode); continue; @@ -884,11 +899,11 @@ next_step: bool locked = false; if (S_ISREG(inode->i_mode)) { - if (!down_write_trylock(&fi->dio_rwsem[READ])) + if (!down_write_trylock(&fi->i_gc_rwsem[READ])) continue; if (!down_write_trylock( - &fi->dio_rwsem[WRITE])) { - up_write(&fi->dio_rwsem[READ]); + &fi->i_gc_rwsem[WRITE])) { + up_write(&fi->i_gc_rwsem[READ]); continue; } locked = true; @@ -897,17 +912,18 @@ next_step: inode_dio_wait(inode); } - start_bidx = start_bidx_of_node(nofs, inode) + start_bidx = f2fs_start_bidx_of_node(nofs, inode) + ofs_in_node; - if (f2fs_encrypted_file(inode)) - move_data_block(inode, start_bidx, segno, off); + if (f2fs_post_read_required(inode)) + move_data_block(inode, start_bidx, gc_type, + segno, off); else move_data_page(inode, start_bidx, gc_type, segno, off); if (locked) { - up_write(&fi->dio_rwsem[WRITE]); - up_write(&fi->dio_rwsem[READ]); + up_write(&fi->i_gc_rwsem[WRITE]); + up_write(&fi->i_gc_rwsem[READ]); } stat_inc_data_blk_count(sbi, 1, gc_type); @@ -946,12 +962,12 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, /* readahead multi ssa blocks those have contiguous address */ if (sbi->segs_per_sec > 1) - ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), + f2fs_ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), sbi->segs_per_sec, META_SSA, true); /* reference all summary page */ while (segno < end_segno) { - sum_page = get_sum_page(sbi, segno++); + sum_page = f2fs_get_sum_page(sbi, segno++); unlock_page(sum_page); } @@ -1017,6 +1033,8 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, .ilist = LIST_HEAD_INIT(gc_list.ilist), .iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS), }; + unsigned long long last_skipped = sbi->skipped_atomic_files[FG_GC]; + unsigned int skipped_round = 0, round = 0; trace_f2fs_gc_begin(sbi->sb, sync, background, get_pages(sbi, F2FS_DIRTY_NODES), @@ -1045,7 +1063,7 @@ gc_more: * secure free segments which doesn't need fggc any more. */ if (prefree_segments(sbi)) { - ret = write_checkpoint(sbi, &cpc); + ret = f2fs_write_checkpoint(sbi, &cpc); if (ret) goto stop; } @@ -1068,17 +1086,27 @@ gc_more: sec_freed++; total_freed += seg_freed; + if (gc_type == FG_GC) { + if (sbi->skipped_atomic_files[FG_GC] > last_skipped) + skipped_round++; + last_skipped = sbi->skipped_atomic_files[FG_GC]; + round++; + } + if (gc_type == FG_GC) sbi->cur_victim_sec = NULL_SEGNO; if (!sync) { if (has_not_enough_free_secs(sbi, sec_freed, 0)) { + if (skipped_round > MAX_SKIP_ATOMIC_COUNT && + skipped_round * 2 >= round) + f2fs_drop_inmem_pages_all(sbi, true); segno = NULL_SEGNO; goto gc_more; } if (gc_type == FG_GC) - ret = write_checkpoint(sbi, &cpc); + ret = f2fs_write_checkpoint(sbi, &cpc); } stop: SIT_I(sbi)->last_victim[ALLOC_NEXT] = 0; @@ -1102,19 +1130,10 @@ stop: return ret; } -void build_gc_manager(struct f2fs_sb_info *sbi) +void f2fs_build_gc_manager(struct f2fs_sb_info *sbi) { - u64 main_count, resv_count, ovp_count; - DIRTY_I(sbi)->v_ops = &default_v_ops; - /* threshold of # of valid blocks in a section for victims of FG_GC */ - main_count = SM_I(sbi)->main_segments << sbi->log_blocks_per_seg; - resv_count = SM_I(sbi)->reserved_segments << sbi->log_blocks_per_seg; - ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg; - - sbi->fggc_threshold = div64_u64((main_count - ovp_count) * - BLKS_PER_SEC(sbi), (main_count - resv_count)); sbi->gc_pin_file_threshold = DEF_GC_FAILED_PINNED_FILES; /* give warm/cold data area from slower device */ diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index b0045d4c8d1e..c8619e408009 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -36,8 +36,6 @@ struct f2fs_gc_kthread { unsigned int no_gc_sleep_time; /* for changing gc mode */ - unsigned int gc_idle; - unsigned int gc_urgent; unsigned int gc_wake; }; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 265da200daa8..043830be5662 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -25,7 +25,7 @@ bool f2fs_may_inline_data(struct inode *inode) if (i_size_read(inode) > MAX_INLINE_DATA(inode)) return false; - if (f2fs_encrypted_file(inode)) + if (f2fs_post_read_required(inode)) return false; return true; @@ -42,7 +42,7 @@ bool f2fs_may_inline_dentry(struct inode *inode) return true; } -void read_inline_data(struct page *page, struct page *ipage) +void f2fs_do_read_inline_data(struct page *page, struct page *ipage) { struct inode *inode = page->mapping->host; void *src_addr, *dst_addr; @@ -64,7 +64,8 @@ void read_inline_data(struct page *page, struct page *ipage) SetPageUptodate(page); } -void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from) +void f2fs_truncate_inline_inode(struct inode *inode, + struct page *ipage, u64 from) { void *addr; @@ -85,7 +86,7 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page) { struct page *ipage; - ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) { unlock_page(page); return PTR_ERR(ipage); @@ -99,7 +100,7 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page) if (page->index) zero_user_segment(page, 0, PAGE_SIZE); else - read_inline_data(page, ipage); + f2fs_do_read_inline_data(page, ipage); if (!PageUptodate(page)) SetPageUptodate(page); @@ -131,7 +132,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page)); - read_inline_data(page, dn->inode_page); + f2fs_do_read_inline_data(page, dn->inode_page); set_page_dirty(page); /* clear dirty state */ @@ -139,20 +140,21 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) /* write data page to try to make data consistent */ set_page_writeback(page); + ClearPageError(page); fio.old_blkaddr = dn->data_blkaddr; set_inode_flag(dn->inode, FI_HOT_DATA); - write_data_page(dn, &fio); + f2fs_outplace_write_data(dn, &fio); f2fs_wait_on_page_writeback(page, DATA, true); if (dirty) { inode_dec_dirty_pages(dn->inode); - remove_dirty_inode(dn->inode); + f2fs_remove_dirty_inode(dn->inode); } /* this converted inline_data should be recovered. */ set_inode_flag(dn->inode, FI_APPEND_WRITE); /* clear inline data and flag after data writeback */ - truncate_inline_inode(dn->inode, dn->inode_page, 0); + f2fs_truncate_inline_inode(dn->inode, dn->inode_page, 0); clear_inline_node(dn->inode_page); clear_out: stat_dec_inline_inode(dn->inode); @@ -177,7 +179,7 @@ int f2fs_convert_inline_inode(struct inode *inode) f2fs_lock_op(sbi); - ipage = get_node_page(sbi, inode->i_ino); + ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto out; @@ -203,12 +205,10 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; struct dnode_of_data dn; - struct address_space *mapping = page_mapping(page); - unsigned long flags; int err; set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, 0, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE); if (err) return err; @@ -226,10 +226,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) kunmap_atomic(src_addr); set_page_dirty(dn.inode_page); - xa_lock_irqsave(&mapping->i_pages, flags); - radix_tree_tag_clear(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_DIRTY); - xa_unlock_irqrestore(&mapping->i_pages, flags); + f2fs_clear_radix_tree_dirty_tag(page); set_inode_flag(inode, FI_APPEND_WRITE); set_inode_flag(inode, FI_DATA_EXIST); @@ -239,7 +236,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) return 0; } -bool recover_inline_data(struct inode *inode, struct page *npage) +bool f2fs_recover_inline_data(struct inode *inode, struct page *npage) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode *ri = NULL; @@ -260,7 +257,7 @@ bool recover_inline_data(struct inode *inode, struct page *npage) if (f2fs_has_inline_data(inode) && ri && (ri->i_inline & F2FS_INLINE_DATA)) { process_inline: - ipage = get_node_page(sbi, inode->i_ino); + ipage = f2fs_get_node_page(sbi, inode->i_ino); f2fs_bug_on(sbi, IS_ERR(ipage)); f2fs_wait_on_page_writeback(ipage, NODE, true); @@ -278,20 +275,20 @@ process_inline: } if (f2fs_has_inline_data(inode)) { - ipage = get_node_page(sbi, inode->i_ino); + ipage = f2fs_get_node_page(sbi, inode->i_ino); f2fs_bug_on(sbi, IS_ERR(ipage)); - truncate_inline_inode(inode, ipage, 0); + f2fs_truncate_inline_inode(inode, ipage, 0); clear_inode_flag(inode, FI_INLINE_DATA); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { - if (truncate_blocks(inode, 0, false)) + if (f2fs_truncate_blocks(inode, 0, false)) return false; goto process_inline; } return false; } -struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, +struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, struct fscrypt_name *fname, struct page **res_page) { struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); @@ -302,7 +299,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, void *inline_dentry; f2fs_hash_t namehash; - ipage = get_node_page(sbi, dir->i_ino); + ipage = f2fs_get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) { *res_page = ipage; return NULL; @@ -313,7 +310,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, inline_dentry = inline_data_addr(dir, ipage); make_dentry_ptr_inline(dir, &d, inline_dentry); - de = find_target_dentry(fname, namehash, NULL, &d); + de = f2fs_find_target_dentry(fname, namehash, NULL, &d); unlock_page(ipage); if (de) *res_page = ipage; @@ -323,7 +320,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, return de; } -int make_empty_inline_dir(struct inode *inode, struct inode *parent, +int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent, struct page *ipage) { struct f2fs_dentry_ptr d; @@ -332,7 +329,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent, inline_dentry = inline_data_addr(inode, ipage); make_dentry_ptr_inline(inode, &d, inline_dentry); - do_make_empty_dir(inode, parent, &d); + f2fs_do_make_empty_dir(inode, parent, &d); set_page_dirty(ipage); @@ -367,7 +364,6 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, goto out; f2fs_wait_on_page_writeback(page, DATA, true); - zero_user_segment(page, MAX_INLINE_DATA(dir), PAGE_SIZE); dentry_blk = page_address(page); @@ -391,7 +387,7 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, set_page_dirty(page); /* clear inline dir and flag after data writeback */ - truncate_inline_inode(dir, ipage, 0); + f2fs_truncate_inline_inode(dir, ipage, 0); stat_dec_inline_dir(dir); clear_inode_flag(dir, FI_INLINE_DENTRY); @@ -434,7 +430,7 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) new_name.len = le16_to_cpu(de->name_len); ino = le32_to_cpu(de->ino); - fake_mode = get_de_type(de) << S_SHIFT; + fake_mode = f2fs_get_de_type(de) << S_SHIFT; err = f2fs_add_regular_entry(dir, &new_name, NULL, NULL, ino, fake_mode); @@ -446,8 +442,8 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) return 0; punch_dentry_pages: truncate_inode_pages(&dir->i_data, 0); - truncate_blocks(dir, 0, false); - remove_dirty_inode(dir); + f2fs_truncate_blocks(dir, 0, false); + f2fs_remove_dirty_inode(dir); return err; } @@ -465,7 +461,7 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage, } memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA(dir)); - truncate_inline_inode(dir, ipage, 0); + f2fs_truncate_inline_inode(dir, ipage, 0); unlock_page(ipage); @@ -514,14 +510,14 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, struct page *page = NULL; int err = 0; - ipage = get_node_page(sbi, dir->i_ino); + ipage = f2fs_get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); inline_dentry = inline_data_addr(dir, ipage); make_dentry_ptr_inline(dir, &d, inline_dentry); - bit_pos = room_for_filename(d.bitmap, slots, d.max); + bit_pos = f2fs_room_for_filename(d.bitmap, slots, d.max); if (bit_pos >= d.max) { err = f2fs_convert_inline_dir(dir, ipage, inline_dentry); if (err) @@ -532,7 +528,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, if (inode) { down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, new_name, + page = f2fs_init_inode_metadata(inode, dir, new_name, orig_name, ipage); if (IS_ERR(page)) { err = PTR_ERR(page); @@ -553,7 +549,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, f2fs_put_page(page, 1); } - update_parent_metadata(dir, inode, 0); + f2fs_update_parent_metadata(dir, inode, 0); fail: if (inode) up_write(&F2FS_I(inode)->i_sem); @@ -599,7 +595,7 @@ bool f2fs_empty_inline_dir(struct inode *dir) void *inline_dentry; struct f2fs_dentry_ptr d; - ipage = get_node_page(sbi, dir->i_ino); + ipage = f2fs_get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) return false; @@ -630,7 +626,7 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, if (ctx->pos == d.max) return 0; - ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); @@ -656,7 +652,7 @@ int f2fs_inline_data_fiemap(struct inode *inode, struct page *ipage; int err = 0; - ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); @@ -672,7 +668,7 @@ int f2fs_inline_data_fiemap(struct inode *inode, ilen = start + len; ilen -= start; - get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni); + f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni); byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits; byteaddr += (char *)inline_data_addr(inode, ipage) - (char *)F2FS_INODE(ipage); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index e0d9e8f27ed2..30a777369d2b 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -36,15 +36,15 @@ void f2fs_set_inode_flags(struct inode *inode) unsigned int flags = F2FS_I(inode)->i_flags; unsigned int new_fl = 0; - if (flags & FS_SYNC_FL) + if (flags & F2FS_SYNC_FL) new_fl |= S_SYNC; - if (flags & FS_APPEND_FL) + if (flags & F2FS_APPEND_FL) new_fl |= S_APPEND; - if (flags & FS_IMMUTABLE_FL) + if (flags & F2FS_IMMUTABLE_FL) new_fl |= S_IMMUTABLE; - if (flags & FS_NOATIME_FL) + if (flags & F2FS_NOATIME_FL) new_fl |= S_NOATIME; - if (flags & FS_DIRSYNC_FL) + if (flags & F2FS_DIRSYNC_FL) new_fl |= S_DIRSYNC; if (f2fs_encrypted_inode(inode)) new_fl |= S_ENCRYPTED; @@ -72,7 +72,7 @@ static bool __written_first_block(struct f2fs_inode *ri) { block_t addr = le32_to_cpu(ri->i_addr[offset_in_addr(ri)]); - if (addr != NEW_ADDR && addr != NULL_ADDR) + if (is_valid_blkaddr(addr)) return true; return false; } @@ -117,7 +117,6 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage) static bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct page *page) { struct f2fs_inode *ri = &F2FS_NODE(page)->i; - int extra_isize = le32_to_cpu(ri->i_extra_isize); if (!f2fs_sb_has_inode_chksum(sbi->sb)) return false; @@ -125,7 +124,8 @@ static bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct page *page if (!RAW_IS_INODE(F2FS_NODE(page)) || !(ri->i_inline & F2FS_EXTRA_ATTR)) return false; - if (!F2FS_FITS_IN_INODE(ri, extra_isize, i_inode_checksum)) + if (!F2FS_FITS_IN_INODE(ri, le16_to_cpu(ri->i_extra_isize), + i_inode_checksum)) return false; return true; @@ -185,6 +185,21 @@ void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page) ri->i_inode_checksum = cpu_to_le32(f2fs_inode_chksum(sbi, page)); } +static bool sanity_check_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (f2fs_sb_has_flexible_inline_xattr(sbi->sb) + && !f2fs_has_extra_attr(inode)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: corrupted inode ino=%lx, run fsck to fix.", + __func__, inode->i_ino); + return false; + } + return true; +} + static int do_read_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -194,14 +209,10 @@ static int do_read_inode(struct inode *inode) projid_t i_projid; /* Check if ino is within scope */ - if (check_nid_range(sbi, inode->i_ino)) { - f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu", - (unsigned long) inode->i_ino); - WARN_ON(1); + if (f2fs_check_nid_range(sbi, inode->i_ino)) return -EINVAL; - } - node_page = get_node_page(sbi, inode->i_ino); + node_page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(node_page)) return PTR_ERR(node_page); @@ -221,8 +232,11 @@ static int do_read_inode(struct inode *inode) inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec); inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec); inode->i_generation = le32_to_cpu(ri->i_generation); - - fi->i_current_depth = le32_to_cpu(ri->i_current_depth); + if (S_ISDIR(inode->i_mode)) + fi->i_current_depth = le32_to_cpu(ri->i_current_depth); + else if (S_ISREG(inode->i_mode)) + fi->i_gc_failures[GC_FAILURE_PIN] = + le16_to_cpu(ri->i_gc_failures); fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid); fi->i_flags = le32_to_cpu(ri->i_flags); fi->flags = 0; @@ -239,7 +253,6 @@ static int do_read_inode(struct inode *inode) le16_to_cpu(ri->i_extra_isize) : 0; if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)) { - f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode)); fi->i_inline_xattr_size = le16_to_cpu(ri->i_inline_xattr_size); } else if (f2fs_has_inline_xattr(inode) || f2fs_has_inline_dentry(inode)) { @@ -265,10 +278,10 @@ static int do_read_inode(struct inode *inode) if (__written_first_block(ri)) set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); - if (!need_inode_block_update(sbi, inode->i_ino)) + if (!f2fs_need_inode_block_update(sbi, inode->i_ino)) fi->last_disk_size = inode->i_size; - if (fi->i_flags & FS_PROJINHERIT_FL) + if (fi->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); if (f2fs_has_extra_attr(inode) && f2fs_sb_has_project_quota(sbi->sb) && @@ -317,13 +330,17 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino) ret = do_read_inode(inode); if (ret) goto bad_inode; + if (!sanity_check_inode(inode)) { + ret = -EINVAL; + goto bad_inode; + } make_now: if (ino == F2FS_NODE_INO(sbi)) { inode->i_mapping->a_ops = &f2fs_node_aops; - mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO); + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); } else if (ino == F2FS_META_INO(sbi)) { inode->i_mapping->a_ops = &f2fs_meta_aops; - mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO); + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); } else if (S_ISREG(inode->i_mode)) { inode->i_op = &f2fs_file_inode_operations; inode->i_fop = &f2fs_file_operations; @@ -373,7 +390,7 @@ retry: return inode; } -void update_inode(struct inode *inode, struct page *node_page) +void f2fs_update_inode(struct inode *inode, struct page *node_page) { struct f2fs_inode *ri; struct extent_tree *et = F2FS_I(inode)->extent_tree; @@ -408,7 +425,12 @@ void update_inode(struct inode *inode, struct page *node_page) ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec); ri->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec); ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); - ri->i_current_depth = cpu_to_le32(F2FS_I(inode)->i_current_depth); + if (S_ISDIR(inode->i_mode)) + ri->i_current_depth = + cpu_to_le32(F2FS_I(inode)->i_current_depth); + else if (S_ISREG(inode->i_mode)) + ri->i_gc_failures = + cpu_to_le16(F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN]); ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid); ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags); ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino); @@ -454,12 +476,12 @@ void update_inode(struct inode *inode, struct page *node_page) F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime; } -void update_inode_page(struct inode *inode) +void f2fs_update_inode_page(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *node_page; retry: - node_page = get_node_page(sbi, inode->i_ino); + node_page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(node_page)) { int err = PTR_ERR(node_page); if (err == -ENOMEM) { @@ -470,7 +492,7 @@ retry: } return; } - update_inode(inode, node_page); + f2fs_update_inode(inode, node_page); f2fs_put_page(node_page, 1); } @@ -489,7 +511,7 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) * We need to balance fs here to prevent from producing dirty node pages * during the urgent cleaning time when runing out of free sections. */ - update_inode_page(inode); + f2fs_update_inode_page(inode); if (wbc && wbc->nr_to_write) f2fs_balance_fs(sbi, true); return 0; @@ -506,7 +528,7 @@ void f2fs_evict_inode(struct inode *inode) /* some remained atomic pages should discarded */ if (f2fs_is_atomic_file(inode)) - drop_inmem_pages(inode); + f2fs_drop_inmem_pages(inode); trace_f2fs_evict_inode(inode); truncate_inode_pages_final(&inode->i_data); @@ -516,7 +538,7 @@ void f2fs_evict_inode(struct inode *inode) goto out_clear; f2fs_bug_on(sbi, get_dirty_pages(inode)); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); f2fs_destroy_extent_tree(inode); @@ -525,9 +547,9 @@ void f2fs_evict_inode(struct inode *inode) dquot_initialize(inode); - remove_ino_entry(sbi, inode->i_ino, APPEND_INO); - remove_ino_entry(sbi, inode->i_ino, UPDATE_INO); - remove_ino_entry(sbi, inode->i_ino, FLUSH_INO); + f2fs_remove_ino_entry(sbi, inode->i_ino, APPEND_INO); + f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO); + f2fs_remove_ino_entry(sbi, inode->i_ino, FLUSH_INO); sb_start_intwrite(inode->i_sb); set_inode_flag(inode, FI_NO_ALLOC); @@ -544,7 +566,7 @@ retry: #endif if (!err) { f2fs_lock_op(sbi); - err = remove_inode_page(inode); + err = f2fs_remove_inode_page(inode); f2fs_unlock_op(sbi); if (err == -ENOENT) err = 0; @@ -557,7 +579,7 @@ retry: } if (err) - update_inode_page(inode); + f2fs_update_inode_page(inode); dquot_free_inode(inode); sb_end_intwrite(inode->i_sb); no_delete: @@ -580,16 +602,19 @@ no_delete: invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid); if (inode->i_nlink) { if (is_inode_flag_set(inode, FI_APPEND_WRITE)) - add_ino_entry(sbi, inode->i_ino, APPEND_INO); + f2fs_add_ino_entry(sbi, inode->i_ino, APPEND_INO); if (is_inode_flag_set(inode, FI_UPDATE_WRITE)) - add_ino_entry(sbi, inode->i_ino, UPDATE_INO); + f2fs_add_ino_entry(sbi, inode->i_ino, UPDATE_INO); } if (is_inode_flag_set(inode, FI_FREE_NID)) { - alloc_nid_failed(sbi, inode->i_ino); + f2fs_alloc_nid_failed(sbi, inode->i_ino); clear_inode_flag(inode, FI_FREE_NID); } else { - f2fs_bug_on(sbi, err && - !exist_written_data(sbi, inode->i_ino, ORPHAN_INO)); + /* + * If xattr nid is corrupted, we can reach out error condition, + * err & !f2fs_exist_written_data(sbi, inode->i_ino, ORPHAN_INO)). + * In that case, f2fs_check_nid_range() is enough to give a clue. + */ } out_clear: fscrypt_put_encryption_info(inode); @@ -597,7 +622,7 @@ out_clear: } /* caller should call f2fs_lock_op() */ -void handle_failed_inode(struct inode *inode) +void f2fs_handle_failed_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct node_info ni; @@ -612,7 +637,7 @@ void handle_failed_inode(struct inode *inode) * we must call this to avoid inode being remained as dirty, resulting * in a panic when flushing dirty inodes in gdirty_list. */ - update_inode_page(inode); + f2fs_update_inode_page(inode); f2fs_inode_synced(inode); /* don't make bad inode, since it becomes a regular file. */ @@ -623,18 +648,18 @@ void handle_failed_inode(struct inode *inode) * so we can prevent losing this orphan when encoutering checkpoint * and following suddenly power-off. */ - get_node_info(sbi, inode->i_ino, &ni); + f2fs_get_node_info(sbi, inode->i_ino, &ni); if (ni.blk_addr != NULL_ADDR) { - int err = acquire_orphan_inode(sbi); + int err = f2fs_acquire_orphan_inode(sbi); if (err) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_msg(sbi->sb, KERN_WARNING, "Too many orphan inodes, run fsck to fix."); } else { - add_orphan_inode(inode); + f2fs_add_orphan_inode(inode); } - alloc_nid_done(sbi, inode->i_ino); + f2fs_alloc_nid_done(sbi, inode->i_ino); } else { set_inode_flag(inode, FI_FREE_NID); } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 75e37fd720b2..64050c84d353 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -37,7 +37,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) return ERR_PTR(-ENOMEM); f2fs_lock_op(sbi); - if (!alloc_nid(sbi, &ino)) { + if (!f2fs_alloc_nid(sbi, &ino)) { f2fs_unlock_op(sbi); err = -ENOSPC; goto fail; @@ -54,6 +54,9 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) F2FS_I(inode)->i_crtime = current_time(inode); inode->i_generation = sbi->s_next_generation++; + if (S_ISDIR(inode->i_mode)) + F2FS_I(inode)->i_current_depth = 1; + err = insert_inode_locked(inode); if (err) { err = -EINVAL; @@ -61,7 +64,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) } if (f2fs_sb_has_project_quota(sbi->sb) && - (F2FS_I(dir)->i_flags & FS_PROJINHERIT_FL)) + (F2FS_I(dir)->i_flags & F2FS_PROJINHERIT_FL)) F2FS_I(inode)->i_projid = F2FS_I(dir)->i_projid; else F2FS_I(inode)->i_projid = make_kprojid(&init_user_ns, @@ -116,9 +119,9 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) f2fs_mask_flags(mode, F2FS_I(dir)->i_flags & F2FS_FL_INHERITED); if (S_ISDIR(inode->i_mode)) - F2FS_I(inode)->i_flags |= FS_INDEX_FL; + F2FS_I(inode)->i_flags |= F2FS_INDEX_FL; - if (F2FS_I(inode)->i_flags & FS_PROJINHERIT_FL) + if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); trace_f2fs_new_inode(inode, 0); @@ -193,7 +196,7 @@ static inline void set_file_temperature(struct f2fs_sb_info *sbi, struct inode * up_read(&sbi->sb_lock); } -int update_extension_list(struct f2fs_sb_info *sbi, const char *name, +int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, bool hot, bool set) { __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list; @@ -292,7 +295,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, goto out; f2fs_unlock_op(sbi); - alloc_nid_done(sbi, ino); + f2fs_alloc_nid_done(sbi, ino); d_instantiate_new(dentry, inode); @@ -302,7 +305,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, f2fs_balance_fs(sbi, true); return 0; out: - handle_failed_inode(inode); + f2fs_handle_failed_inode(inode); return err; } @@ -397,7 +400,7 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) err = PTR_ERR(page); goto out; } else { - err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR); + err = f2fs_do_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR); if (err) goto out; } @@ -408,7 +411,7 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) else if (IS_ERR(page)) err = PTR_ERR(page); else - err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR); + err = f2fs_do_add_link(dir, &dotdot, NULL, pino, S_IFDIR); out: if (!err) clear_inode_flag(dir, FI_INLINE_DOTS); @@ -520,7 +523,7 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); - err = acquire_orphan_inode(sbi); + err = f2fs_acquire_orphan_inode(sbi); if (err) { f2fs_unlock_op(sbi); f2fs_put_page(page, 0); @@ -585,9 +588,9 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) - goto out_handle_failed_inode; + goto out_f2fs_handle_failed_inode; f2fs_unlock_op(sbi); - alloc_nid_done(sbi, inode->i_ino); + f2fs_alloc_nid_done(sbi, inode->i_ino); err = fscrypt_encrypt_symlink(inode, symname, len, &disk_link); if (err) @@ -620,8 +623,8 @@ err_out: f2fs_balance_fs(sbi, true); goto out_free_encrypted_link; -out_handle_failed_inode: - handle_failed_inode(inode); +out_f2fs_handle_failed_inode: + f2fs_handle_failed_inode(inode); out_free_encrypted_link: if (disk_link.name != (unsigned char *)symname) kfree(disk_link.name); @@ -657,7 +660,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) goto out_fail; f2fs_unlock_op(sbi); - alloc_nid_done(sbi, inode->i_ino); + f2fs_alloc_nid_done(sbi, inode->i_ino); d_instantiate_new(dentry, inode); @@ -669,7 +672,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) out_fail: clear_inode_flag(inode, FI_INC_LINK); - handle_failed_inode(inode); + f2fs_handle_failed_inode(inode); return err; } @@ -708,7 +711,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, goto out; f2fs_unlock_op(sbi); - alloc_nid_done(sbi, inode->i_ino); + f2fs_alloc_nid_done(sbi, inode->i_ino); d_instantiate_new(dentry, inode); @@ -718,7 +721,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, f2fs_balance_fs(sbi, true); return 0; out: - handle_failed_inode(inode); + f2fs_handle_failed_inode(inode); return err; } @@ -747,7 +750,7 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, } f2fs_lock_op(sbi); - err = acquire_orphan_inode(sbi); + err = f2fs_acquire_orphan_inode(sbi); if (err) goto out; @@ -759,8 +762,8 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, * add this non-linked tmpfile to orphan list, in this way we could * remove all unused data of tmpfile after abnormal power-off. */ - add_orphan_inode(inode); - alloc_nid_done(sbi, inode->i_ino); + f2fs_add_orphan_inode(inode); + f2fs_alloc_nid_done(sbi, inode->i_ino); if (whiteout) { f2fs_i_links_write(inode, false); @@ -776,9 +779,9 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, return 0; release_out: - release_orphan_inode(sbi); + f2fs_release_orphan_inode(sbi); out: - handle_failed_inode(inode); + f2fs_handle_failed_inode(inode); return err; } @@ -885,7 +888,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_lock_op(sbi); - err = acquire_orphan_inode(sbi); + err = f2fs_acquire_orphan_inode(sbi); if (err) goto put_out_dir; @@ -899,9 +902,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, up_write(&F2FS_I(new_inode)->i_sem); if (!new_inode->i_nlink) - add_orphan_inode(new_inode); + f2fs_add_orphan_inode(new_inode); else - release_orphan_inode(sbi); + f2fs_release_orphan_inode(sbi); } else { f2fs_balance_fs(sbi, true); @@ -969,8 +972,12 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_put_page(old_dir_page, 0); f2fs_i_links_write(old_dir, false); } - if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) - add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); + if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) { + f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); + if (S_ISDIR(old_inode->i_mode)) + f2fs_add_ino_entry(sbi, old_inode->i_ino, + TRANS_DIR_INO); + } f2fs_unlock_op(sbi); @@ -1121,8 +1128,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_mark_inode_dirty_sync(new_dir, false); if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) { - add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO); - add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); + f2fs_add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO); + f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); } f2fs_unlock_op(sbi); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index f202398e20ea..47d0e64a95a8 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -23,13 +23,28 @@ #include "trace.h" #include <trace/events/f2fs.h> -#define on_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock) +#define on_f2fs_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock) static struct kmem_cache *nat_entry_slab; static struct kmem_cache *free_nid_slab; static struct kmem_cache *nat_entry_set_slab; -bool available_free_memory(struct f2fs_sb_info *sbi, int type) +/* + * Check whether the given nid is within node id range. + */ +int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) +{ + if (unlikely(nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: out-of-range nid=%x, run fsck to fix.", + __func__, nid); + return -EINVAL; + } + return 0; +} + +bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct sysinfo val; @@ -87,18 +102,10 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) static void clear_node_page_dirty(struct page *page) { - struct address_space *mapping = page->mapping; - unsigned int long flags; - if (PageDirty(page)) { - xa_lock_irqsave(&mapping->i_pages, flags); - radix_tree_tag_clear(&mapping->i_pages, - page_index(page), - PAGECACHE_TAG_DIRTY); - xa_unlock_irqrestore(&mapping->i_pages, flags); - + f2fs_clear_radix_tree_dirty_tag(page); clear_page_dirty_for_io(page); - dec_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES); + dec_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); } ClearPageUptodate(page); } @@ -106,7 +113,7 @@ static void clear_node_page_dirty(struct page *page) static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid) { pgoff_t index = current_nat_addr(sbi, nid); - return get_meta_page(sbi, index); + return f2fs_get_meta_page(sbi, index); } static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) @@ -123,8 +130,8 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) dst_off = next_nat_addr(sbi, src_off); /* get current nat block page with lock */ - src_page = get_meta_page(sbi, src_off); - dst_page = grab_meta_page(sbi, dst_off); + src_page = f2fs_get_meta_page(sbi, src_off); + dst_page = f2fs_grab_meta_page(sbi, dst_off); f2fs_bug_on(sbi, PageDirty(src_page)); src_addr = page_address(src_page); @@ -260,7 +267,7 @@ static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i, start, nr); } -int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) +int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; @@ -277,7 +284,7 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) return need; } -bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) +bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; @@ -291,7 +298,7 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) return is_cp; } -bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) +bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; @@ -364,8 +371,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, new_blkaddr == NULL_ADDR); f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR && new_blkaddr == NEW_ADDR); - f2fs_bug_on(sbi, nat_get_blkaddr(e) != NEW_ADDR && - nat_get_blkaddr(e) != NULL_ADDR && + f2fs_bug_on(sbi, is_valid_blkaddr(nat_get_blkaddr(e)) && new_blkaddr == NEW_ADDR); /* increment version no as node is removed */ @@ -376,7 +382,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, /* change address */ nat_set_blkaddr(e, new_blkaddr); - if (new_blkaddr == NEW_ADDR || new_blkaddr == NULL_ADDR) + if (!is_valid_blkaddr(new_blkaddr)) set_nat_flag(e, IS_CHECKPOINTED, false); __set_nat_cache_dirty(nm_i, e); @@ -391,7 +397,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, up_write(&nm_i->nat_tree_lock); } -int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) +int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) { struct f2fs_nm_info *nm_i = NM_I(sbi); int nr = nr_shrink; @@ -413,7 +419,8 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) /* * This function always returns success */ -void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) +void f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, + struct node_info *ni) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -443,7 +450,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) /* Check current segment summary */ down_read(&curseg->journal_rwsem); - i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0); + i = f2fs_lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0); if (i >= 0) { ne = nat_in_journal(journal, i); node_info_from_raw_nat(ni, &ne); @@ -458,7 +465,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) index = current_nat_addr(sbi, nid); up_read(&nm_i->nat_tree_lock); - page = get_meta_page(sbi, index); + page = f2fs_get_meta_page(sbi, index); nat_blk = (struct f2fs_nat_block *)page_address(page); ne = nat_blk->entries[nid - start_nid]; node_info_from_raw_nat(ni, &ne); @@ -471,7 +478,7 @@ cache: /* * readahead MAX_RA_NODE number of node pages. */ -static void ra_node_pages(struct page *parent, int start, int n) +static void f2fs_ra_node_pages(struct page *parent, int start, int n) { struct f2fs_sb_info *sbi = F2FS_P_SB(parent); struct blk_plug plug; @@ -485,13 +492,13 @@ static void ra_node_pages(struct page *parent, int start, int n) end = min(end, NIDS_PER_BLOCK); for (i = start; i < end; i++) { nid = get_nid(parent, i, false); - ra_node_page(sbi, nid); + f2fs_ra_node_page(sbi, nid); } blk_finish_plug(&plug); } -pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) +pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) { const long direct_index = ADDRS_PER_INODE(dn->inode); const long direct_blks = ADDRS_PER_BLOCK; @@ -606,7 +613,7 @@ got: * f2fs_unlock_op() only if ro is not set RDONLY_NODE. * In the case of RDONLY_NODE, we don't need to care about mutex. */ -int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) +int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct page *npage[4]; @@ -625,7 +632,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) npage[0] = dn->inode_page; if (!npage[0]) { - npage[0] = get_node_page(sbi, nids[0]); + npage[0] = f2fs_get_node_page(sbi, nids[0]); if (IS_ERR(npage[0])) return PTR_ERR(npage[0]); } @@ -649,24 +656,24 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) if (!nids[i] && mode == ALLOC_NODE) { /* alloc new node */ - if (!alloc_nid(sbi, &(nids[i]))) { + if (!f2fs_alloc_nid(sbi, &(nids[i]))) { err = -ENOSPC; goto release_pages; } dn->nid = nids[i]; - npage[i] = new_node_page(dn, noffset[i]); + npage[i] = f2fs_new_node_page(dn, noffset[i]); if (IS_ERR(npage[i])) { - alloc_nid_failed(sbi, nids[i]); + f2fs_alloc_nid_failed(sbi, nids[i]); err = PTR_ERR(npage[i]); goto release_pages; } set_nid(parent, offset[i - 1], nids[i], i == 1); - alloc_nid_done(sbi, nids[i]); + f2fs_alloc_nid_done(sbi, nids[i]); done = true; } else if (mode == LOOKUP_NODE_RA && i == level && level > 1) { - npage[i] = get_node_page_ra(parent, offset[i - 1]); + npage[i] = f2fs_get_node_page_ra(parent, offset[i - 1]); if (IS_ERR(npage[i])) { err = PTR_ERR(npage[i]); goto release_pages; @@ -681,7 +688,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) } if (!done) { - npage[i] = get_node_page(sbi, nids[i]); + npage[i] = f2fs_get_node_page(sbi, nids[i]); if (IS_ERR(npage[i])) { err = PTR_ERR(npage[i]); f2fs_put_page(npage[0], 0); @@ -720,15 +727,15 @@ static void truncate_node(struct dnode_of_data *dn) struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info ni; - get_node_info(sbi, dn->nid, &ni); + f2fs_get_node_info(sbi, dn->nid, &ni); /* Deallocate node address */ - invalidate_blocks(sbi, ni.blk_addr); + f2fs_invalidate_blocks(sbi, ni.blk_addr); dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino); set_node_addr(sbi, &ni, NULL_ADDR, false); if (dn->nid == dn->inode->i_ino) { - remove_orphan_inode(sbi, dn->nid); + f2fs_remove_orphan_inode(sbi, dn->nid); dec_valid_inode_count(sbi); f2fs_inode_synced(dn->inode); } @@ -753,7 +760,7 @@ static int truncate_dnode(struct dnode_of_data *dn) return 1; /* get direct node */ - page = get_node_page(F2FS_I_SB(dn->inode), dn->nid); + page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); if (IS_ERR(page) && PTR_ERR(page) == -ENOENT) return 1; else if (IS_ERR(page)) @@ -762,7 +769,7 @@ static int truncate_dnode(struct dnode_of_data *dn) /* Make dnode_of_data for parameter */ dn->node_page = page; dn->ofs_in_node = 0; - truncate_data_blocks(dn); + f2fs_truncate_data_blocks(dn); truncate_node(dn); return 1; } @@ -783,13 +790,13 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr); - page = get_node_page(F2FS_I_SB(dn->inode), dn->nid); + page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); if (IS_ERR(page)) { trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page)); return PTR_ERR(page); } - ra_node_pages(page, ofs, NIDS_PER_BLOCK); + f2fs_ra_node_pages(page, ofs, NIDS_PER_BLOCK); rn = F2FS_NODE(page); if (depth < 3) { @@ -859,7 +866,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, /* get indirect nodes in the path */ for (i = 0; i < idx + 1; i++) { /* reference count'll be increased */ - pages[i] = get_node_page(F2FS_I_SB(dn->inode), nid[i]); + pages[i] = f2fs_get_node_page(F2FS_I_SB(dn->inode), nid[i]); if (IS_ERR(pages[i])) { err = PTR_ERR(pages[i]); idx = i - 1; @@ -868,7 +875,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, nid[i + 1] = get_nid(pages[i], offset[i + 1], false); } - ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK); + f2fs_ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK); /* free direct nodes linked to a partial indirect node */ for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) { @@ -905,7 +912,7 @@ fail: /* * All the block addresses of data and nodes should be nullified. */ -int truncate_inode_blocks(struct inode *inode, pgoff_t from) +int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int err = 0, cont = 1; @@ -921,7 +928,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from) if (level < 0) return level; - page = get_node_page(sbi, inode->i_ino); + page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page)); return PTR_ERR(page); @@ -1001,7 +1008,7 @@ fail: } /* caller must lock inode page */ -int truncate_xattr_node(struct inode *inode) +int f2fs_truncate_xattr_node(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t nid = F2FS_I(inode)->i_xattr_nid; @@ -1011,7 +1018,7 @@ int truncate_xattr_node(struct inode *inode) if (!nid) return 0; - npage = get_node_page(sbi, nid); + npage = f2fs_get_node_page(sbi, nid); if (IS_ERR(npage)) return PTR_ERR(npage); @@ -1026,17 +1033,17 @@ int truncate_xattr_node(struct inode *inode) * Caller should grab and release a rwsem by calling f2fs_lock_op() and * f2fs_unlock_op(). */ -int remove_inode_page(struct inode *inode) +int f2fs_remove_inode_page(struct inode *inode) { struct dnode_of_data dn; int err; set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); - err = get_dnode_of_data(&dn, 0, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE); if (err) return err; - err = truncate_xattr_node(inode); + err = f2fs_truncate_xattr_node(inode); if (err) { f2fs_put_dnode(&dn); return err; @@ -1045,7 +1052,7 @@ int remove_inode_page(struct inode *inode) /* remove potential inline_data blocks */ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) - truncate_data_blocks_range(&dn, 1); + f2fs_truncate_data_blocks_range(&dn, 1); /* 0 is possible, after f2fs_new_inode() has failed */ f2fs_bug_on(F2FS_I_SB(inode), @@ -1056,7 +1063,7 @@ int remove_inode_page(struct inode *inode) return 0; } -struct page *new_inode_page(struct inode *inode) +struct page *f2fs_new_inode_page(struct inode *inode) { struct dnode_of_data dn; @@ -1064,10 +1071,10 @@ struct page *new_inode_page(struct inode *inode) set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); /* caller should f2fs_put_page(page, 1); */ - return new_node_page(&dn, 0); + return f2fs_new_node_page(&dn, 0); } -struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) +struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info new_ni; @@ -1085,7 +1092,7 @@ struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) goto fail; #ifdef CONFIG_F2FS_CHECK_FS - get_node_info(sbi, dn->nid, &new_ni); + f2fs_get_node_info(sbi, dn->nid, &new_ni); f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR); #endif new_ni.nid = dn->nid; @@ -1137,7 +1144,7 @@ static int read_node_page(struct page *page, int op_flags) if (PageUptodate(page)) return LOCKED_PAGE; - get_node_info(sbi, page->index, &ni); + f2fs_get_node_info(sbi, page->index, &ni); if (unlikely(ni.blk_addr == NULL_ADDR)) { ClearPageUptodate(page); @@ -1151,14 +1158,15 @@ static int read_node_page(struct page *page, int op_flags) /* * Readahead a node page */ -void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) +void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) { struct page *apage; int err; if (!nid) return; - f2fs_bug_on(sbi, check_nid_range(sbi, nid)); + if (f2fs_check_nid_range(sbi, nid)) + return; rcu_read_lock(); apage = radix_tree_lookup(&NODE_MAPPING(sbi)->i_pages, nid); @@ -1182,7 +1190,8 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid, if (!nid) return ERR_PTR(-ENOENT); - f2fs_bug_on(sbi, check_nid_range(sbi, nid)); + if (f2fs_check_nid_range(sbi, nid)) + return ERR_PTR(-EINVAL); repeat: page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false); if (!page) @@ -1198,7 +1207,7 @@ repeat: } if (parent) - ra_node_pages(parent, start + 1, MAX_RA_NODE); + f2fs_ra_node_pages(parent, start + 1, MAX_RA_NODE); lock_page(page); @@ -1232,12 +1241,12 @@ out_err: return page; } -struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) { return __get_node_page(sbi, nid, NULL, 0); } -struct page *get_node_page_ra(struct page *parent, int start) +struct page *f2fs_get_node_page_ra(struct page *parent, int start) { struct f2fs_sb_info *sbi = F2FS_P_SB(parent); nid_t nid = get_nid(parent, start, false); @@ -1272,7 +1281,7 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino) ret = f2fs_write_inline_data(inode, page); inode_dec_dirty_pages(inode); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); if (ret) set_page_dirty(page); page_out: @@ -1359,11 +1368,8 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, trace_f2fs_writepage(page, NODE); - if (unlikely(f2fs_cp_error(sbi))) { - dec_page_count(sbi, F2FS_DIRTY_NODES); - unlock_page(page); - return 0; - } + if (unlikely(f2fs_cp_error(sbi))) + goto redirty_out; if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; @@ -1379,7 +1385,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, down_read(&sbi->node_write); } - get_node_info(sbi, nid, &ni); + f2fs_get_node_info(sbi, nid, &ni); /* This page is already truncated */ if (unlikely(ni.blk_addr == NULL_ADDR)) { @@ -1394,8 +1400,9 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, fio.op_flags |= REQ_PREFLUSH | REQ_FUA; set_page_writeback(page); + ClearPageError(page); fio.old_blkaddr = ni.blk_addr; - write_node_page(nid, &fio); + f2fs_do_write_node_page(nid, &fio); set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page)); dec_page_count(sbi, F2FS_DIRTY_NODES); up_read(&sbi->node_write); @@ -1424,7 +1431,7 @@ redirty_out: return AOP_WRITEPAGE_ACTIVATE; } -void move_node_page(struct page *node_page, int gc_type) +void f2fs_move_node_page(struct page *node_page, int gc_type) { if (gc_type == FG_GC) { struct writeback_control wbc = { @@ -1461,7 +1468,7 @@ static int f2fs_write_node_page(struct page *page, return __write_node_page(page, false, NULL, wbc, false, FS_NODE_IO); } -int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, +int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, struct writeback_control *wbc, bool atomic) { pgoff_t index; @@ -1528,9 +1535,9 @@ continue_unlock: if (IS_INODE(page)) { if (is_inode_flag_set(inode, FI_DIRTY_INODE)) - update_inode(inode, page); + f2fs_update_inode(inode, page); set_dentry_mark(page, - need_dentry_mark(sbi, ino)); + f2fs_need_dentry_mark(sbi, ino)); } /* may be written by other thread */ if (!PageDirty(page)) @@ -1580,7 +1587,8 @@ out: return ret ? -EIO: 0; } -int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, +int f2fs_sync_node_pages(struct f2fs_sb_info *sbi, + struct writeback_control *wbc, bool do_balance, enum iostat_type io_type) { pgoff_t index; @@ -1588,21 +1596,28 @@ int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, int step = 0; int nwritten = 0; int ret = 0; - int nr_pages; + int nr_pages, done = 0; pagevec_init(&pvec); next_step: index = 0; - while ((nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, - PAGECACHE_TAG_DIRTY))) { + while (!done && (nr_pages = pagevec_lookup_tag(&pvec, + NODE_MAPPING(sbi), &index, PAGECACHE_TAG_DIRTY))) { int i; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; bool submitted = false; + /* give a priority to WB_SYNC threads */ + if (atomic_read(&sbi->wb_sync_req[NODE]) && + wbc->sync_mode == WB_SYNC_NONE) { + done = 1; + break; + } + /* * flushing sequence with step: * 0. indirect nodes @@ -1681,7 +1696,7 @@ continue_unlock: return ret; } -int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino) +int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino) { pgoff_t index = 0; struct pagevec pvec; @@ -1730,14 +1745,21 @@ static int f2fs_write_node_pages(struct address_space *mapping, if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE)) goto skip_write; + if (wbc->sync_mode == WB_SYNC_ALL) + atomic_inc(&sbi->wb_sync_req[NODE]); + else if (atomic_read(&sbi->wb_sync_req[NODE])) + goto skip_write; + trace_f2fs_writepages(mapping->host, wbc, NODE); diff = nr_pages_to_write(sbi, NODE, wbc); - wbc->sync_mode = WB_SYNC_NONE; blk_start_plug(&plug); - sync_node_pages(sbi, wbc, true, FS_NODE_IO); + f2fs_sync_node_pages(sbi, wbc, true, FS_NODE_IO); blk_finish_plug(&plug); wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); + + if (wbc->sync_mode == WB_SYNC_ALL) + atomic_dec(&sbi->wb_sync_req[NODE]); return 0; skip_write: @@ -1753,7 +1775,7 @@ static int f2fs_set_node_page_dirty(struct page *page) if (!PageUptodate(page)) SetPageUptodate(page); if (!PageDirty(page)) { - f2fs_set_page_dirty_nobuffers(page); + __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); SetPagePrivate(page); f2fs_trace_pid(page); @@ -1883,20 +1905,20 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, * Thread A Thread B * - f2fs_create * - f2fs_new_inode - * - alloc_nid + * - f2fs_alloc_nid * - __insert_nid_to_list(PREALLOC_NID) * - f2fs_balance_fs_bg - * - build_free_nids - * - __build_free_nids + * - f2fs_build_free_nids + * - __f2fs_build_free_nids * - scan_nat_page * - add_free_nid * - __lookup_nat_cache * - f2fs_add_link - * - init_inode_metadata - * - new_inode_page - * - new_node_page + * - f2fs_init_inode_metadata + * - f2fs_new_inode_page + * - f2fs_new_node_page * - set_node_addr - * - alloc_nid_done + * - f2fs_alloc_nid_done * - __remove_nid_from_list(PREALLOC_NID) * - __insert_nid_to_list(FREE_NID) */ @@ -2028,7 +2050,8 @@ out: up_read(&nm_i->nat_tree_lock); } -static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) +static void __f2fs_build_free_nids(struct f2fs_sb_info *sbi, + bool sync, bool mount) { struct f2fs_nm_info *nm_i = NM_I(sbi); int i = 0; @@ -2041,7 +2064,7 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK) return; - if (!sync && !available_free_memory(sbi, FREE_NIDS)) + if (!sync && !f2fs_available_free_memory(sbi, FREE_NIDS)) return; if (!mount) { @@ -2053,7 +2076,7 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) } /* readahead nat pages to be scanned */ - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, + f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT, true); down_read(&nm_i->nat_tree_lock); @@ -2083,14 +2106,14 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) up_read(&nm_i->nat_tree_lock); - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), + f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); } -void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) +void f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) { mutex_lock(&NM_I(sbi)->build_lock); - __build_free_nids(sbi, sync, mount); + __f2fs_build_free_nids(sbi, sync, mount); mutex_unlock(&NM_I(sbi)->build_lock); } @@ -2099,7 +2122,7 @@ void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) * from second parameter of this function. * The returned nid could be used ino as well as nid when inode is created. */ -bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid) +bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i = NULL; @@ -2117,8 +2140,8 @@ retry: return false; } - /* We should not use stale free nids created by build_free_nids */ - if (nm_i->nid_cnt[FREE_NID] && !on_build_free_nids(nm_i)) { + /* We should not use stale free nids created by f2fs_build_free_nids */ + if (nm_i->nid_cnt[FREE_NID] && !on_f2fs_build_free_nids(nm_i)) { f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list)); i = list_first_entry(&nm_i->free_nid_list, struct free_nid, list); @@ -2135,14 +2158,14 @@ retry: spin_unlock(&nm_i->nid_list_lock); /* Let's scan nat pages and its caches to get free nids */ - build_free_nids(sbi, true, false); + f2fs_build_free_nids(sbi, true, false); goto retry; } /* - * alloc_nid() should be called prior to this function. + * f2fs_alloc_nid() should be called prior to this function. */ -void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) +void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; @@ -2157,9 +2180,9 @@ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) } /* - * alloc_nid() should be called prior to this function. + * f2fs_alloc_nid() should be called prior to this function. */ -void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) +void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; @@ -2172,7 +2195,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) i = __lookup_free_nid_list(nm_i, nid); f2fs_bug_on(sbi, !i); - if (!available_free_memory(sbi, FREE_NIDS)) { + if (!f2fs_available_free_memory(sbi, FREE_NIDS)) { __remove_free_nid(sbi, i, PREALLOC_NID); need_free = true; } else { @@ -2189,7 +2212,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) kmem_cache_free(free_nid_slab, i); } -int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) +int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i, *next; @@ -2217,14 +2240,14 @@ int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) return nr - nr_shrink; } -void recover_inline_xattr(struct inode *inode, struct page *page) +void f2fs_recover_inline_xattr(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; size_t inline_size; struct page *ipage; struct f2fs_inode *ri; - ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage)); ri = F2FS_INODE(page); @@ -2242,11 +2265,11 @@ void recover_inline_xattr(struct inode *inode, struct page *page) f2fs_wait_on_page_writeback(ipage, NODE, true); memcpy(dst_addr, src_addr, inline_size); update_inode: - update_inode(inode, ipage); + f2fs_update_inode(inode, ipage); f2fs_put_page(ipage, 1); } -int recover_xattr_data(struct inode *inode, struct page *page) +int f2fs_recover_xattr_data(struct inode *inode, struct page *page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid; @@ -2259,25 +2282,25 @@ int recover_xattr_data(struct inode *inode, struct page *page) goto recover_xnid; /* 1: invalidate the previous xattr nid */ - get_node_info(sbi, prev_xnid, &ni); - invalidate_blocks(sbi, ni.blk_addr); + f2fs_get_node_info(sbi, prev_xnid, &ni); + f2fs_invalidate_blocks(sbi, ni.blk_addr); dec_valid_node_count(sbi, inode, false); set_node_addr(sbi, &ni, NULL_ADDR, false); recover_xnid: /* 2: update xattr nid in inode */ - if (!alloc_nid(sbi, &new_xnid)) + if (!f2fs_alloc_nid(sbi, &new_xnid)) return -ENOSPC; set_new_dnode(&dn, inode, NULL, NULL, new_xnid); - xpage = new_node_page(&dn, XATTR_NODE_OFFSET); + xpage = f2fs_new_node_page(&dn, XATTR_NODE_OFFSET); if (IS_ERR(xpage)) { - alloc_nid_failed(sbi, new_xnid); + f2fs_alloc_nid_failed(sbi, new_xnid); return PTR_ERR(xpage); } - alloc_nid_done(sbi, new_xnid); - update_inode_page(inode); + f2fs_alloc_nid_done(sbi, new_xnid); + f2fs_update_inode_page(inode); /* 3: update and set xattr node page dirty */ memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE); @@ -2288,14 +2311,14 @@ recover_xnid: return 0; } -int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) +int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) { struct f2fs_inode *src, *dst; nid_t ino = ino_of_node(page); struct node_info old_ni, new_ni; struct page *ipage; - get_node_info(sbi, ino, &old_ni); + f2fs_get_node_info(sbi, ino, &old_ni); if (unlikely(old_ni.blk_addr != NULL_ADDR)) return -EINVAL; @@ -2349,7 +2372,7 @@ retry: return 0; } -void restore_node_summary(struct f2fs_sb_info *sbi, +void f2fs_restore_node_summary(struct f2fs_sb_info *sbi, unsigned int segno, struct f2fs_summary_block *sum) { struct f2fs_node *rn; @@ -2366,10 +2389,10 @@ void restore_node_summary(struct f2fs_sb_info *sbi, nrpages = min(last_offset - i, BIO_MAX_PAGES); /* readahead node pages */ - ra_meta_pages(sbi, addr, nrpages, META_POR, true); + f2fs_ra_meta_pages(sbi, addr, nrpages, META_POR, true); for (idx = addr; idx < addr + nrpages; idx++) { - struct page *page = get_tmp_page(sbi, idx); + struct page *page = f2fs_get_tmp_page(sbi, idx); rn = F2FS_NODE(page); sum_entry->nid = rn->footer.nid; @@ -2511,7 +2534,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, nat_get_blkaddr(ne) == NEW_ADDR); if (to_journal) { - offset = lookup_journal_in_cursum(journal, + offset = f2fs_lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 1); f2fs_bug_on(sbi, offset < 0); raw_ne = &nat_in_journal(journal, offset); @@ -2548,7 +2571,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, /* * This function is called during the checkpointing process. */ -void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) +void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -2611,7 +2634,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) nat_bits_addr = __start_cp_addr(sbi) + sbi->blocks_per_seg - nm_i->nat_bits_blocks; for (i = 0; i < nm_i->nat_bits_blocks; i++) { - struct page *page = get_meta_page(sbi, nat_bits_addr++); + struct page *page = f2fs_get_meta_page(sbi, nat_bits_addr++); memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS), page_address(page), F2FS_BLKSIZE); @@ -2754,7 +2777,7 @@ static int init_free_nid_cache(struct f2fs_sb_info *sbi) return 0; } -int build_node_manager(struct f2fs_sb_info *sbi) +int f2fs_build_node_manager(struct f2fs_sb_info *sbi) { int err; @@ -2774,11 +2797,11 @@ int build_node_manager(struct f2fs_sb_info *sbi) /* load free nid status from nat_bits table */ load_free_nid_bitmap(sbi); - build_free_nids(sbi, true, true); + f2fs_build_free_nids(sbi, true, true); return 0; } -void destroy_node_manager(struct f2fs_sb_info *sbi) +void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i, *next_i; @@ -2850,7 +2873,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) kfree(nm_i); } -int __init create_node_manager_caches(void) +int __init f2fs_create_node_manager_caches(void) { nat_entry_slab = f2fs_kmem_cache_create("nat_entry", sizeof(struct nat_entry)); @@ -2876,7 +2899,7 @@ fail: return -ENOMEM; } -void destroy_node_manager_caches(void) +void f2fs_destroy_node_manager_caches(void) { kmem_cache_destroy(nat_entry_set_slab); kmem_cache_destroy(free_nid_slab); diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 1b23d3febe4c..38f25f0b193a 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -47,7 +47,7 @@ static struct kmem_cache *fsync_entry_slab; -bool space_for_roll_forward(struct f2fs_sb_info *sbi) +bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi) { s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count); @@ -162,7 +162,7 @@ retry: goto out_put; } - err = acquire_orphan_inode(F2FS_I_SB(inode)); + err = f2fs_acquire_orphan_inode(F2FS_I_SB(inode)); if (err) { iput(einode); goto out_put; @@ -173,7 +173,7 @@ retry: } else if (IS_ERR(page)) { err = PTR_ERR(page); } else { - err = __f2fs_do_add_link(dir, &fname, inode, + err = f2fs_add_dentry(dir, &fname, inode, inode->i_ino, inode->i_mode); } if (err == -ENOMEM) @@ -204,8 +204,6 @@ static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri) set_inode_flag(inode, FI_DATA_EXIST); else clear_inode_flag(inode, FI_DATA_EXIST); - if (!(ri->i_inline & F2FS_INLINE_DOTS)) - clear_inode_flag(inode, FI_INLINE_DOTS); } static void recover_inode(struct inode *inode, struct page *page) @@ -254,10 +252,10 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, while (1) { struct fsync_inode_entry *entry; - if (!is_valid_blkaddr(sbi, blkaddr, META_POR)) + if (!f2fs_is_valid_meta_blkaddr(sbi, blkaddr, META_POR)) return 0; - page = get_tmp_page(sbi, blkaddr); + page = f2fs_get_tmp_page(sbi, blkaddr); if (!is_recoverable_dnode(page)) break; @@ -271,7 +269,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, if (!check_only && IS_INODE(page) && is_dent_dnode(page)) { - err = recover_inode_page(sbi, page); + err = f2fs_recover_inode_page(sbi, page); if (err) break; quota_inode = true; @@ -312,7 +310,7 @@ next: blkaddr = next_blkaddr_of_node(page); f2fs_put_page(page, 1); - ra_meta_pages_cond(sbi, blkaddr); + f2fs_ra_meta_pages_cond(sbi, blkaddr); } f2fs_put_page(page, 1); return err; @@ -355,7 +353,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, } } - sum_page = get_sum_page(sbi, segno); + sum_page = f2fs_get_sum_page(sbi, segno); sum_node = (struct f2fs_summary_block *)page_address(sum_page); sum = sum_node->entries[blkoff]; f2fs_put_page(sum_page, 1); @@ -375,7 +373,7 @@ got_it: } /* Get the node page */ - node_page = get_node_page(sbi, nid); + node_page = f2fs_get_node_page(sbi, nid); if (IS_ERR(node_page)) return PTR_ERR(node_page); @@ -400,7 +398,8 @@ got_it: inode = dn->inode; } - bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node); + bidx = f2fs_start_bidx_of_node(offset, inode) + + le16_to_cpu(sum.ofs_in_node); /* * if inode page is locked, unlock temporarily, but its reference @@ -410,11 +409,11 @@ got_it: unlock_page(dn->inode_page); set_new_dnode(&tdn, inode, NULL, NULL, 0); - if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE)) + if (f2fs_get_dnode_of_data(&tdn, bidx, LOOKUP_NODE)) goto out; if (tdn.data_blkaddr == blkaddr) - truncate_data_blocks_range(&tdn, 1); + f2fs_truncate_data_blocks_range(&tdn, 1); f2fs_put_dnode(&tdn); out: @@ -427,7 +426,7 @@ out: truncate_out: if (datablock_addr(tdn.inode, tdn.node_page, tdn.ofs_in_node) == blkaddr) - truncate_data_blocks_range(&tdn, 1); + f2fs_truncate_data_blocks_range(&tdn, 1); if (dn->inode->i_ino == nid && !dn->inode_page_locked) unlock_page(dn->inode_page); return 0; @@ -443,25 +442,25 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, /* step 1: recover xattr */ if (IS_INODE(page)) { - recover_inline_xattr(inode, page); + f2fs_recover_inline_xattr(inode, page); } else if (f2fs_has_xattr_block(ofs_of_node(page))) { - err = recover_xattr_data(inode, page); + err = f2fs_recover_xattr_data(inode, page); if (!err) recovered++; goto out; } /* step 2: recover inline data */ - if (recover_inline_data(inode, page)) + if (f2fs_recover_inline_data(inode, page)) goto out; /* step 3: recover data indices */ - start = start_bidx_of_node(ofs_of_node(page), inode); + start = f2fs_start_bidx_of_node(ofs_of_node(page), inode); end = start + ADDRS_PER_PAGE(page, inode); set_new_dnode(&dn, inode, NULL, NULL, 0); retry_dn: - err = get_dnode_of_data(&dn, start, ALLOC_NODE); + err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE); if (err) { if (err == -ENOMEM) { congestion_wait(BLK_RW_ASYNC, HZ/50); @@ -472,7 +471,7 @@ retry_dn: f2fs_wait_on_page_writeback(dn.node_page, NODE, true); - get_node_info(sbi, dn.nid, &ni); + f2fs_get_node_info(sbi, dn.nid, &ni); f2fs_bug_on(sbi, ni.ino != ino_of_node(page)); f2fs_bug_on(sbi, ofs_of_node(dn.node_page) != ofs_of_node(page)); @@ -488,7 +487,7 @@ retry_dn: /* dest is invalid, just invalidate src block */ if (dest == NULL_ADDR) { - truncate_data_blocks_range(&dn, 1); + f2fs_truncate_data_blocks_range(&dn, 1); continue; } @@ -502,19 +501,19 @@ retry_dn: * and then reserve one new block in dnode page. */ if (dest == NEW_ADDR) { - truncate_data_blocks_range(&dn, 1); - reserve_new_block(&dn); + f2fs_truncate_data_blocks_range(&dn, 1); + f2fs_reserve_new_block(&dn); continue; } /* dest is valid block, try to recover from src to dest */ - if (is_valid_blkaddr(sbi, dest, META_POR)) { + if (f2fs_is_valid_meta_blkaddr(sbi, dest, META_POR)) { if (src == NULL_ADDR) { - err = reserve_new_block(&dn); + err = f2fs_reserve_new_block(&dn); #ifdef CONFIG_F2FS_FAULT_INJECTION while (err) - err = reserve_new_block(&dn); + err = f2fs_reserve_new_block(&dn); #endif /* We should not get -ENOSPC */ f2fs_bug_on(sbi, err); @@ -569,12 +568,12 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, while (1) { struct fsync_inode_entry *entry; - if (!is_valid_blkaddr(sbi, blkaddr, META_POR)) + if (!f2fs_is_valid_meta_blkaddr(sbi, blkaddr, META_POR)) break; - ra_meta_pages_cond(sbi, blkaddr); + f2fs_ra_meta_pages_cond(sbi, blkaddr); - page = get_tmp_page(sbi, blkaddr); + page = f2fs_get_tmp_page(sbi, blkaddr); if (!is_recoverable_dnode(page)) { f2fs_put_page(page, 1); @@ -612,11 +611,11 @@ next: f2fs_put_page(page, 1); } if (!err) - allocate_new_segments(sbi); + f2fs_allocate_new_segments(sbi); return err; } -int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) +int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) { struct list_head inode_list; struct list_head dir_list; @@ -691,7 +690,7 @@ skip: struct cp_control cpc = { .reason = CP_RECOVERY, }; - err = write_checkpoint(sbi, &cpc); + err = f2fs_write_checkpoint(sbi, &cpc); } kmem_cache_destroy(fsync_entry_slab); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 5854cc4e1d67..6dbdf2c48fba 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -169,7 +169,7 @@ found: return result - size + __reverse_ffz(tmp); } -bool need_SSR(struct f2fs_sb_info *sbi) +bool f2fs_need_SSR(struct f2fs_sb_info *sbi) { int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES); int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); @@ -177,14 +177,14 @@ bool need_SSR(struct f2fs_sb_info *sbi) if (test_opt(sbi, LFS)) return false; - if (sbi->gc_thread && sbi->gc_thread->gc_urgent) + if (sbi->gc_mode == GC_URGENT) return true; return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs + SM_I(sbi)->min_ssr_sections + reserved_sections(sbi)); } -void register_inmem_page(struct inode *inode, struct page *page) +void f2fs_register_inmem_page(struct inode *inode, struct page *page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); @@ -230,6 +230,8 @@ static int __revoke_inmem_pages(struct inode *inode, lock_page(page); + f2fs_wait_on_page_writeback(page, DATA, true); + if (recover) { struct dnode_of_data dn; struct node_info ni; @@ -237,7 +239,8 @@ static int __revoke_inmem_pages(struct inode *inode, trace_f2fs_commit_inmem_page(page, INMEM_REVOKE); retry: set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, page->index, + LOOKUP_NODE); if (err) { if (err == -ENOMEM) { congestion_wait(BLK_RW_ASYNC, HZ/50); @@ -247,9 +250,9 @@ retry: err = -EAGAIN; goto next; } - get_node_info(sbi, dn.nid, &ni); + f2fs_get_node_info(sbi, dn.nid, &ni); if (cur->old_addr == NEW_ADDR) { - invalidate_blocks(sbi, dn.data_blkaddr); + f2fs_invalidate_blocks(sbi, dn.data_blkaddr); f2fs_update_data_blkaddr(&dn, NEW_ADDR); } else f2fs_replace_block(sbi, &dn, dn.data_blkaddr, @@ -271,7 +274,7 @@ next: return err; } -void drop_inmem_pages_all(struct f2fs_sb_info *sbi) +void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure) { struct list_head *head = &sbi->inode_list[ATOMIC_FILE]; struct inode *inode; @@ -287,15 +290,23 @@ next: spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); if (inode) { - drop_inmem_pages(inode); + if (gc_failure) { + if (fi->i_gc_failures[GC_FAILURE_ATOMIC]) + goto drop; + goto skip; + } +drop: + set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); + f2fs_drop_inmem_pages(inode); iput(inode); } +skip: congestion_wait(BLK_RW_ASYNC, HZ/50); cond_resched(); goto next; } -void drop_inmem_pages(struct inode *inode) +void f2fs_drop_inmem_pages(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); @@ -309,11 +320,11 @@ void drop_inmem_pages(struct inode *inode) mutex_unlock(&fi->inmem_lock); clear_inode_flag(inode, FI_ATOMIC_FILE); - clear_inode_flag(inode, FI_HOT_DATA); + fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0; stat_dec_atomic_write(inode); } -void drop_inmem_page(struct inode *inode, struct page *page) +void f2fs_drop_inmem_page(struct inode *inode, struct page *page) { struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -328,7 +339,7 @@ void drop_inmem_page(struct inode *inode, struct page *page) break; } - f2fs_bug_on(sbi, !cur || cur->page != page); + f2fs_bug_on(sbi, list_empty(head) || cur->page != page); list_del(&cur->list); mutex_unlock(&fi->inmem_lock); @@ -343,8 +354,7 @@ void drop_inmem_page(struct inode *inode, struct page *page) trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE); } -static int __commit_inmem_pages(struct inode *inode, - struct list_head *revoke_list) +static int __f2fs_commit_inmem_pages(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); @@ -357,9 +367,12 @@ static int __commit_inmem_pages(struct inode *inode, .op_flags = REQ_SYNC | REQ_PRIO, .io_type = FS_DATA_IO, }; + struct list_head revoke_list; pgoff_t last_idx = ULONG_MAX; int err = 0; + INIT_LIST_HEAD(&revoke_list); + list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) { struct page *page = cur->page; @@ -371,14 +384,14 @@ static int __commit_inmem_pages(struct inode *inode, f2fs_wait_on_page_writeback(page, DATA, true); if (clear_page_dirty_for_io(page)) { inode_dec_dirty_pages(inode); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); } retry: fio.page = page; fio.old_blkaddr = NULL_ADDR; fio.encrypted_page = NULL; fio.need_lock = LOCK_DONE; - err = do_write_data_page(&fio); + err = f2fs_do_write_data_page(&fio); if (err) { if (err == -ENOMEM) { congestion_wait(BLK_RW_ASYNC, HZ/50); @@ -393,50 +406,46 @@ retry: last_idx = page->index; } unlock_page(page); - list_move_tail(&cur->list, revoke_list); + list_move_tail(&cur->list, &revoke_list); } if (last_idx != ULONG_MAX) f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA); - if (!err) - __revoke_inmem_pages(inode, revoke_list, false, false); + if (err) { + /* + * try to revoke all committed pages, but still we could fail + * due to no memory or other reason, if that happened, EAGAIN + * will be returned, which means in such case, transaction is + * already not integrity, caller should use journal to do the + * recovery or rewrite & commit last transaction. For other + * error number, revoking was done by filesystem itself. + */ + err = __revoke_inmem_pages(inode, &revoke_list, false, true); + + /* drop all uncommitted pages */ + __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); + } else { + __revoke_inmem_pages(inode, &revoke_list, false, false); + } return err; } -int commit_inmem_pages(struct inode *inode) +int f2fs_commit_inmem_pages(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); - struct list_head revoke_list; int err; - INIT_LIST_HEAD(&revoke_list); f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); set_inode_flag(inode, FI_ATOMIC_COMMIT); mutex_lock(&fi->inmem_lock); - err = __commit_inmem_pages(inode, &revoke_list); - if (err) { - int ret; - /* - * try to revoke all committed pages, but still we could fail - * due to no memory or other reason, if that happened, EAGAIN - * will be returned, which means in such case, transaction is - * already not integrity, caller should use journal to do the - * recovery or rewrite & commit last transaction. For other - * error number, revoking was done by filesystem itself. - */ - ret = __revoke_inmem_pages(inode, &revoke_list, false, true); - if (ret) - err = ret; + err = __f2fs_commit_inmem_pages(inode); - /* drop all uncommitted pages */ - __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); - } spin_lock(&sbi->inode_lock[ATOMIC_FILE]); if (!list_empty(&fi->inmem_ilist)) list_del_init(&fi->inmem_ilist); @@ -478,25 +487,28 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) { + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + return; + /* try to shrink extent cache when there is no enough memory */ - if (!available_free_memory(sbi, EXTENT_CACHE)) + if (!f2fs_available_free_memory(sbi, EXTENT_CACHE)) f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER); /* check the # of cached NAT entries */ - if (!available_free_memory(sbi, NAT_ENTRIES)) - try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK); + if (!f2fs_available_free_memory(sbi, NAT_ENTRIES)) + f2fs_try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK); - if (!available_free_memory(sbi, FREE_NIDS)) - try_to_free_nids(sbi, MAX_FREE_NIDS); + if (!f2fs_available_free_memory(sbi, FREE_NIDS)) + f2fs_try_to_free_nids(sbi, MAX_FREE_NIDS); else - build_free_nids(sbi, false, false); + f2fs_build_free_nids(sbi, false, false); if (!is_idle(sbi) && !excess_dirty_nats(sbi)) return; /* checkpoint is the only way to shrink partial cached entries */ - if (!available_free_memory(sbi, NAT_ENTRIES) || - !available_free_memory(sbi, INO_ENTRIES) || + if (!f2fs_available_free_memory(sbi, NAT_ENTRIES) || + !f2fs_available_free_memory(sbi, INO_ENTRIES) || excess_prefree_segs(sbi) || excess_dirty_nats(sbi) || f2fs_time_over(sbi, CP_TIME)) { @@ -504,7 +516,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) struct blk_plug plug; blk_start_plug(&plug); - sync_dirty_inodes(sbi, FILE_INODE); + f2fs_sync_dirty_inodes(sbi, FILE_INODE); blk_finish_plug(&plug); } f2fs_sync_fs(sbi->sb, true); @@ -537,7 +549,7 @@ static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino) return __submit_flush_wait(sbi, sbi->sb->s_bdev); for (i = 0; i < sbi->s_ndevs; i++) { - if (!is_dirty_device(sbi, ino, i, FLUSH_INO)) + if (!f2fs_is_dirty_device(sbi, ino, i, FLUSH_INO)) continue; ret = __submit_flush_wait(sbi, FDEV(i).bdev); if (ret) @@ -648,7 +660,7 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino) return cmd.ret; } -int create_flush_cmd_control(struct f2fs_sb_info *sbi) +int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi) { dev_t dev = sbi->sb->s_bdev->bd_dev; struct flush_cmd_control *fcc; @@ -685,7 +697,7 @@ init_thread: return err; } -void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free) +void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free) { struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info; @@ -915,6 +927,42 @@ static void __check_sit_bitmap(struct f2fs_sb_info *sbi, #endif } +static void __init_discard_policy(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy, + int discard_type, unsigned int granularity) +{ + /* common policy */ + dpolicy->type = discard_type; + dpolicy->sync = true; + dpolicy->granularity = granularity; + + dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST; + dpolicy->io_aware_gran = MAX_PLIST_NUM; + + if (discard_type == DPOLICY_BG) { + dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; + dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME; + dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME; + dpolicy->io_aware = true; + dpolicy->sync = false; + if (utilization(sbi) > DEF_DISCARD_URGENT_UTIL) { + dpolicy->granularity = 1; + dpolicy->max_interval = DEF_MIN_DISCARD_ISSUE_TIME; + } + } else if (discard_type == DPOLICY_FORCE) { + dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; + dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME; + dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME; + dpolicy->io_aware = false; + } else if (discard_type == DPOLICY_FSTRIM) { + dpolicy->io_aware = false; + } else if (discard_type == DPOLICY_UMOUNT) { + dpolicy->max_requests = UINT_MAX; + dpolicy->io_aware = false; + } +} + + /* this function is copied from blkdev_issue_discard from block/blk-lib.c */ static void __submit_discard_cmd(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy, @@ -929,6 +977,9 @@ static void __submit_discard_cmd(struct f2fs_sb_info *sbi, if (dc->state != D_PREP) return; + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) + return; + trace_f2fs_issue_discard(dc->bdev, dc->start, dc->len); dc->error = __blkdev_issue_discard(dc->bdev, @@ -972,7 +1023,7 @@ static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi, goto do_insert; } - p = __lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart); + p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart); do_insert: dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, p); if (!dc) @@ -1037,7 +1088,7 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, mutex_lock(&dcc->cmd_lock); - dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root, + dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root, NULL, lstart, (struct rb_entry **)&prev_dc, (struct rb_entry **)&next_dc, @@ -1130,68 +1181,6 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi, return 0; } -static void __issue_discard_cmd_range(struct f2fs_sb_info *sbi, - struct discard_policy *dpolicy, - unsigned int start, unsigned int end) -{ - struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - struct discard_cmd *prev_dc = NULL, *next_dc = NULL; - struct rb_node **insert_p = NULL, *insert_parent = NULL; - struct discard_cmd *dc; - struct blk_plug plug; - int issued; - -next: - issued = 0; - - mutex_lock(&dcc->cmd_lock); - f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root)); - - dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root, - NULL, start, - (struct rb_entry **)&prev_dc, - (struct rb_entry **)&next_dc, - &insert_p, &insert_parent, true); - if (!dc) - dc = next_dc; - - blk_start_plug(&plug); - - while (dc && dc->lstart <= end) { - struct rb_node *node; - - if (dc->len < dpolicy->granularity) - goto skip; - - if (dc->state != D_PREP) { - list_move_tail(&dc->list, &dcc->fstrim_list); - goto skip; - } - - __submit_discard_cmd(sbi, dpolicy, dc); - - if (++issued >= dpolicy->max_requests) { - start = dc->lstart + dc->len; - - blk_finish_plug(&plug); - mutex_unlock(&dcc->cmd_lock); - - schedule(); - - goto next; - } -skip: - node = rb_next(&dc->rb_node); - dc = rb_entry_safe(node, struct discard_cmd, rb_node); - - if (fatal_signal_pending(current)) - break; - } - - blk_finish_plug(&plug); - mutex_unlock(&dcc->cmd_lock); -} - static int __issue_discard_cmd(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy) { @@ -1210,7 +1199,8 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi, mutex_lock(&dcc->cmd_lock); if (list_empty(pend_list)) goto next; - f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root)); + f2fs_bug_on(sbi, + !f2fs_check_rb_tree_consistence(sbi, &dcc->root)); blk_start_plug(&plug); list_for_each_entry_safe(dc, tmp, pend_list, list) { f2fs_bug_on(sbi, dc->state != D_PREP); @@ -1263,7 +1253,7 @@ static bool __drop_discard_cmd(struct f2fs_sb_info *sbi) return dropped; } -void drop_discard_cmd(struct f2fs_sb_info *sbi) +void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi) { __drop_discard_cmd(sbi); } @@ -1332,7 +1322,18 @@ next: static void __wait_all_discard_cmd(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy) { - __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX); + struct discard_policy dp; + + if (dpolicy) { + __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX); + return; + } + + /* wait all */ + __init_discard_policy(sbi, &dp, DPOLICY_FSTRIM, 1); + __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX); + __init_discard_policy(sbi, &dp, DPOLICY_UMOUNT, 1); + __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX); } /* This should be covered by global mutex, &sit_i->sentry_lock */ @@ -1343,7 +1344,8 @@ static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr) bool need_wait = false; mutex_lock(&dcc->cmd_lock); - dc = (struct discard_cmd *)__lookup_rb_tree(&dcc->root, NULL, blkaddr); + dc = (struct discard_cmd *)f2fs_lookup_rb_tree(&dcc->root, + NULL, blkaddr); if (dc) { if (dc->state == D_PREP) { __punch_discard_cmd(sbi, dc, blkaddr); @@ -1358,7 +1360,7 @@ static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr) __wait_one_discard_bio(sbi, dc); } -void stop_discard_thread(struct f2fs_sb_info *sbi) +void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; @@ -1377,11 +1379,13 @@ bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi) struct discard_policy dpolicy; bool dropped; - init_discard_policy(&dpolicy, DPOLICY_UMOUNT, dcc->discard_granularity); + __init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT, + dcc->discard_granularity); __issue_discard_cmd(sbi, &dpolicy); dropped = __drop_discard_cmd(sbi); - __wait_all_discard_cmd(sbi, &dpolicy); + /* just to make sure there is no pending discard commands */ + __wait_all_discard_cmd(sbi, NULL); return dropped; } @@ -1397,32 +1401,39 @@ static int issue_discard_thread(void *data) set_freezable(); do { - init_discard_policy(&dpolicy, DPOLICY_BG, + __init_discard_policy(sbi, &dpolicy, DPOLICY_BG, dcc->discard_granularity); wait_event_interruptible_timeout(*q, kthread_should_stop() || freezing(current) || dcc->discard_wake, msecs_to_jiffies(wait_ms)); + + if (dcc->discard_wake) + dcc->discard_wake = 0; + if (try_to_freeze()) continue; if (f2fs_readonly(sbi->sb)) continue; if (kthread_should_stop()) return 0; + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) { + wait_ms = dpolicy.max_interval; + continue; + } - if (dcc->discard_wake) - dcc->discard_wake = 0; - - if (sbi->gc_thread && sbi->gc_thread->gc_urgent) - init_discard_policy(&dpolicy, DPOLICY_FORCE, 1); + if (sbi->gc_mode == GC_URGENT) + __init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1); sb_start_intwrite(sbi->sb); issued = __issue_discard_cmd(sbi, &dpolicy); - if (issued) { + if (issued > 0) { __wait_all_discard_cmd(sbi, &dpolicy); wait_ms = dpolicy.min_interval; + } else if (issued == -1){ + wait_ms = dpolicy.mid_interval; } else { wait_ms = dpolicy.max_interval; } @@ -1591,20 +1602,24 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, return false; } -void release_discard_addrs(struct f2fs_sb_info *sbi) +static void release_discard_addr(struct discard_entry *entry) +{ + list_del(&entry->list); + kmem_cache_free(discard_entry_slab, entry); +} + +void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi) { struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list); struct discard_entry *entry, *this; /* drop caches */ - list_for_each_entry_safe(entry, this, head, list) { - list_del(&entry->list); - kmem_cache_free(discard_entry_slab, entry); - } + list_for_each_entry_safe(entry, this, head, list) + release_discard_addr(entry); } /* - * Should call clear_prefree_segments after checkpoint is done. + * Should call f2fs_clear_prefree_segments after checkpoint is done. */ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi) { @@ -1617,7 +1632,8 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi) mutex_unlock(&dirty_i->seglist_lock); } -void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc) +void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, + struct cp_control *cpc) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *head = &dcc->entry_list; @@ -1700,40 +1716,13 @@ skip: if (cur_pos < sbi->blocks_per_seg) goto find_next; - list_del(&entry->list); + release_discard_addr(entry); dcc->nr_discards -= total_len; - kmem_cache_free(discard_entry_slab, entry); } wake_up_discard_thread(sbi, false); } -void init_discard_policy(struct discard_policy *dpolicy, - int discard_type, unsigned int granularity) -{ - /* common policy */ - dpolicy->type = discard_type; - dpolicy->sync = true; - dpolicy->granularity = granularity; - - dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST; - dpolicy->io_aware_gran = MAX_PLIST_NUM; - - if (discard_type == DPOLICY_BG) { - dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; - dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME; - dpolicy->io_aware = true; - } else if (discard_type == DPOLICY_FORCE) { - dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; - dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME; - dpolicy->io_aware = false; - } else if (discard_type == DPOLICY_FSTRIM) { - dpolicy->io_aware = false; - } else if (discard_type == DPOLICY_UMOUNT) { - dpolicy->io_aware = false; - } -} - static int create_discard_cmd_control(struct f2fs_sb_info *sbi) { dev_t dev = sbi->sb->s_bdev->bd_dev; @@ -1786,7 +1775,7 @@ static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi) if (!dcc) return; - stop_discard_thread(sbi); + f2fs_stop_discard_thread(sbi); kfree(dcc); SM_I(sbi)->dcc_info = NULL; @@ -1833,8 +1822,9 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) (new_vblocks > sbi->blocks_per_seg))); se->valid_blocks = new_vblocks; - se->mtime = get_mtime(sbi); - SIT_I(sbi)->max_mtime = se->mtime; + se->mtime = get_mtime(sbi, false); + if (se->mtime > SIT_I(sbi)->max_mtime) + SIT_I(sbi)->max_mtime = se->mtime; /* Update valid block bitmap */ if (del > 0) { @@ -1902,7 +1892,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) get_sec_entry(sbi, segno)->valid_blocks += del; } -void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) +void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) { unsigned int segno = GET_SEGNO(sbi, addr); struct sit_info *sit_i = SIT_I(sbi); @@ -1922,14 +1912,14 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) up_write(&sit_i->sentry_lock); } -bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) +bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) { struct sit_info *sit_i = SIT_I(sbi); unsigned int segno, offset; struct seg_entry *se; bool is_cp = false; - if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) + if (!is_valid_blkaddr(blkaddr)) return true; down_read(&sit_i->sentry_lock); @@ -1961,7 +1951,7 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type, /* * Calculate the number of current summary pages for writing */ -int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) +int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) { int valid_sum_count = 0; int i, sum_in_page; @@ -1991,14 +1981,15 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) /* * Caller should put this summary page */ -struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) +struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) { - return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno)); + return f2fs_get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno)); } -void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) +void f2fs_update_meta_page(struct f2fs_sb_info *sbi, + void *src, block_t blk_addr) { - struct page *page = grab_meta_page(sbi, blk_addr); + struct page *page = f2fs_grab_meta_page(sbi, blk_addr); memcpy(page_address(page), src, PAGE_SIZE); set_page_dirty(page); @@ -2008,18 +1999,19 @@ void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) static void write_sum_page(struct f2fs_sb_info *sbi, struct f2fs_summary_block *sum_blk, block_t blk_addr) { - update_meta_page(sbi, (void *)sum_blk, blk_addr); + f2fs_update_meta_page(sbi, (void *)sum_blk, blk_addr); } static void write_current_sum_page(struct f2fs_sb_info *sbi, int type, block_t blk_addr) { struct curseg_info *curseg = CURSEG_I(sbi, type); - struct page *page = grab_meta_page(sbi, blk_addr); + struct page *page = f2fs_grab_meta_page(sbi, blk_addr); struct f2fs_summary_block *src = curseg->sum_blk; struct f2fs_summary_block *dst; dst = (struct f2fs_summary_block *)page_address(page); + memset(dst, 0, PAGE_SIZE); mutex_lock(&curseg->curseg_mutex); @@ -2259,7 +2251,7 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type) curseg->alloc_type = SSR; __next_free_blkoff(sbi, curseg, 0); - sum_page = get_sum_page(sbi, new_segno); + sum_page = f2fs_get_sum_page(sbi, new_segno); sum_node = (struct f2fs_summary_block *)page_address(sum_page); memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE); f2fs_put_page(sum_page, 1); @@ -2273,7 +2265,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) int i, cnt; bool reversed = false; - /* need_SSR() already forces to do this */ + /* f2fs_need_SSR() already forces to do this */ if (v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) { curseg->next_segno = segno; return 1; @@ -2325,7 +2317,7 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, new_curseg(sbi, type, false); else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type)) new_curseg(sbi, type, false); - else if (need_SSR(sbi) && get_ssr_segment(sbi, type)) + else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type)) change_curseg(sbi, type); else new_curseg(sbi, type, false); @@ -2333,7 +2325,7 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, stat_inc_seg_type(sbi, curseg); } -void allocate_new_segments(struct f2fs_sb_info *sbi) +void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi) { struct curseg_info *curseg; unsigned int old_segno; @@ -2355,7 +2347,8 @@ static const struct segment_allocation default_salloc_ops = { .allocate_segment = allocate_segment_by_default, }; -bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc) +bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi, + struct cp_control *cpc) { __u64 trim_start = cpc->trim_start; bool has_candidate = false; @@ -2373,11 +2366,72 @@ bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc) return has_candidate; } +static void __issue_discard_cmd_range(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy, + unsigned int start, unsigned int end) +{ + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + struct discard_cmd *prev_dc = NULL, *next_dc = NULL; + struct rb_node **insert_p = NULL, *insert_parent = NULL; + struct discard_cmd *dc; + struct blk_plug plug; + int issued; + +next: + issued = 0; + + mutex_lock(&dcc->cmd_lock); + f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi, &dcc->root)); + + dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root, + NULL, start, + (struct rb_entry **)&prev_dc, + (struct rb_entry **)&next_dc, + &insert_p, &insert_parent, true); + if (!dc) + dc = next_dc; + + blk_start_plug(&plug); + + while (dc && dc->lstart <= end) { + struct rb_node *node; + + if (dc->len < dpolicy->granularity) + goto skip; + + if (dc->state != D_PREP) { + list_move_tail(&dc->list, &dcc->fstrim_list); + goto skip; + } + + __submit_discard_cmd(sbi, dpolicy, dc); + + if (++issued >= dpolicy->max_requests) { + start = dc->lstart + dc->len; + + blk_finish_plug(&plug); + mutex_unlock(&dcc->cmd_lock); + __wait_all_discard_cmd(sbi, NULL); + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto next; + } +skip: + node = rb_next(&dc->rb_node); + dc = rb_entry_safe(node, struct discard_cmd, rb_node); + + if (fatal_signal_pending(current)) + break; + } + + blk_finish_plug(&plug); + mutex_unlock(&dcc->cmd_lock); +} + int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) { __u64 start = F2FS_BYTES_TO_BLK(range->start); __u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1; - unsigned int start_segno, end_segno, cur_segno; + unsigned int start_segno, end_segno; block_t start_block, end_block; struct cp_control cpc; struct discard_policy dpolicy; @@ -2388,12 +2442,12 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) return -EINVAL; if (end <= MAIN_BLKADDR(sbi)) - goto out; + return -EINVAL; if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) { f2fs_msg(sbi->sb, KERN_WARNING, "Found FS corruption, run fsck to fix."); - goto out; + return -EIO; } /* start/end segment number in main_area */ @@ -2403,40 +2457,36 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) cpc.reason = CP_DISCARD; cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen)); + cpc.trim_start = start_segno; + cpc.trim_end = end_segno; - /* do checkpoint to issue discard commands safely */ - for (cur_segno = start_segno; cur_segno <= end_segno; - cur_segno = cpc.trim_end + 1) { - cpc.trim_start = cur_segno; - - if (sbi->discard_blks == 0) - break; - else if (sbi->discard_blks < BATCHED_TRIM_BLOCKS(sbi)) - cpc.trim_end = end_segno; - else - cpc.trim_end = min_t(unsigned int, - rounddown(cur_segno + - BATCHED_TRIM_SEGMENTS(sbi), - sbi->segs_per_sec) - 1, end_segno); - - mutex_lock(&sbi->gc_mutex); - err = write_checkpoint(sbi, &cpc); - mutex_unlock(&sbi->gc_mutex); - if (err) - break; + if (sbi->discard_blks == 0) + goto out; - schedule(); - } + mutex_lock(&sbi->gc_mutex); + err = f2fs_write_checkpoint(sbi, &cpc); + mutex_unlock(&sbi->gc_mutex); + if (err) + goto out; start_block = START_BLOCK(sbi, start_segno); - end_block = START_BLOCK(sbi, min(cur_segno, end_segno) + 1); + end_block = START_BLOCK(sbi, end_segno + 1); - init_discard_policy(&dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen); + __init_discard_policy(sbi, &dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen); __issue_discard_cmd_range(sbi, &dpolicy, start_block, end_block); - trimmed = __wait_discard_cmd_range(sbi, &dpolicy, + + /* + * We filed discard candidates, but actually we don't need to wait for + * all of them, since they'll be issued in idle time along with runtime + * discard option. User configuration looks like using runtime discard + * or periodic fstrim instead of it. + */ + if (!test_opt(sbi, DISCARD)) { + trimmed = __wait_discard_cmd_range(sbi, &dpolicy, start_block, end_block); + range->len = F2FS_BLK_TO_BYTES(trimmed); + } out: - range->len = F2FS_BLK_TO_BYTES(trimmed); return err; } @@ -2448,7 +2498,7 @@ static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type) return false; } -int rw_hint_to_seg_type(enum rw_hint hint) +int f2fs_rw_hint_to_seg_type(enum rw_hint hint) { switch (hint) { case WRITE_LIFE_SHORT: @@ -2521,7 +2571,7 @@ int rw_hint_to_seg_type(enum rw_hint hint) * WRITE_LIFE_LONG " WRITE_LIFE_LONG */ -enum rw_hint io_type_to_rw_hint(struct f2fs_sb_info *sbi, +enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, enum page_type type, enum temp_type temp) { if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) { @@ -2588,9 +2638,11 @@ static int __get_segment_type_6(struct f2fs_io_info *fio) if (is_cold_data(fio->page) || file_is_cold(inode)) return CURSEG_COLD_DATA; if (file_is_hot(inode) || - is_inode_flag_set(inode, FI_HOT_DATA)) + is_inode_flag_set(inode, FI_HOT_DATA) || + is_inode_flag_set(inode, FI_ATOMIC_FILE) || + is_inode_flag_set(inode, FI_VOLATILE_FILE)) return CURSEG_HOT_DATA; - return rw_hint_to_seg_type(inode->i_write_hint); + return f2fs_rw_hint_to_seg_type(inode->i_write_hint); } else { if (IS_DNODE(fio->page)) return is_cold_node(fio->page) ? CURSEG_WARM_NODE : @@ -2626,7 +2678,7 @@ static int __get_segment_type(struct f2fs_io_info *fio) return type; } -void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, +void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, struct f2fs_io_info *fio, bool add_list) @@ -2686,6 +2738,7 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, INIT_LIST_HEAD(&fio->list); fio->in_list = true; + fio->retry = false; io = sbi->write_io[fio->type] + fio->temp; spin_lock(&io->io_lock); list_add_tail(&fio->list, &io->io_list); @@ -2708,7 +2761,7 @@ static void update_device_state(struct f2fs_io_info *fio) devidx = f2fs_target_device_index(sbi, fio->new_blkaddr); /* update device state for fsync */ - set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO); + f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO); /* update device state for checkpoint */ if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) { @@ -2721,23 +2774,28 @@ static void update_device_state(struct f2fs_io_info *fio) static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) { int type = __get_segment_type(fio); - int err; + bool keep_order = (test_opt(fio->sbi, LFS) && type == CURSEG_COLD_DATA); + if (keep_order) + down_read(&fio->sbi->io_order_lock); reallocate: - allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, + f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, &fio->new_blkaddr, sum, type, fio, true); /* writeout dirty page into bdev */ - err = f2fs_submit_page_write(fio); - if (err == -EAGAIN) { + f2fs_submit_page_write(fio); + if (fio->retry) { fio->old_blkaddr = fio->new_blkaddr; goto reallocate; - } else if (!err) { - update_device_state(fio); } + + update_device_state(fio); + + if (keep_order) + up_read(&fio->sbi->io_order_lock); } -void write_meta_page(struct f2fs_sb_info *sbi, struct page *page, +void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page, enum iostat_type io_type) { struct f2fs_io_info fio = { @@ -2757,12 +2815,13 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page, fio.op_flags &= ~REQ_META; set_page_writeback(page); + ClearPageError(page); f2fs_submit_page_write(&fio); f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE); } -void write_node_page(unsigned int nid, struct f2fs_io_info *fio) +void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio) { struct f2fs_summary sum; @@ -2772,14 +2831,15 @@ void write_node_page(unsigned int nid, struct f2fs_io_info *fio) f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); } -void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio) +void f2fs_outplace_write_data(struct dnode_of_data *dn, + struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; struct f2fs_summary sum; struct node_info ni; f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR); - get_node_info(sbi, dn->nid, &ni); + f2fs_get_node_info(sbi, dn->nid, &ni); set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); do_write_page(&sum, fio); f2fs_update_data_blkaddr(dn, fio->new_blkaddr); @@ -2787,7 +2847,7 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio) f2fs_update_iostat(sbi, fio->io_type, F2FS_BLKSIZE); } -int rewrite_data_page(struct f2fs_io_info *fio) +int f2fs_inplace_write_data(struct f2fs_io_info *fio) { int err; struct f2fs_sb_info *sbi = fio->sbi; @@ -2822,7 +2882,7 @@ static inline int __f2fs_get_curseg(struct f2fs_sb_info *sbi, return i; } -void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, +void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t old_blkaddr, block_t new_blkaddr, bool recover_curseg, bool recover_newaddr) { @@ -2907,7 +2967,7 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, set_summary(&sum, dn->nid, dn->ofs_in_node, version); - __f2fs_replace_block(sbi, &sum, old_addr, new_addr, + f2fs_do_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg, recover_newaddr); f2fs_update_data_blkaddr(dn, new_addr); @@ -2932,7 +2992,7 @@ void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr) { struct page *cpage; - if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) + if (!is_valid_blkaddr(blkaddr)) return; cpage = find_lock_page(META_MAPPING(sbi), blkaddr); @@ -2953,7 +3013,7 @@ static void read_compacted_summaries(struct f2fs_sb_info *sbi) start = start_sum_block(sbi); - page = get_meta_page(sbi, start++); + page = f2fs_get_meta_page(sbi, start++); kaddr = (unsigned char *)page_address(page); /* Step 1: restore nat cache */ @@ -2993,7 +3053,7 @@ static void read_compacted_summaries(struct f2fs_sb_info *sbi) f2fs_put_page(page, 1); page = NULL; - page = get_meta_page(sbi, start++); + page = f2fs_get_meta_page(sbi, start++); kaddr = (unsigned char *)page_address(page); offset = 0; } @@ -3032,7 +3092,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) blk_addr = GET_SUM_BLOCK(sbi, segno); } - new = get_meta_page(sbi, blk_addr); + new = f2fs_get_meta_page(sbi, blk_addr); sum = (struct f2fs_summary_block *)page_address(new); if (IS_NODESEG(type)) { @@ -3044,7 +3104,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) ns->ofs_in_node = 0; } } else { - restore_node_summary(sbi, segno, sum); + f2fs_restore_node_summary(sbi, segno, sum); } } @@ -3076,10 +3136,10 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) int err; if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) { - int npages = npages_for_summary_flush(sbi, true); + int npages = f2fs_npages_for_summary_flush(sbi, true); if (npages >= 2) - ra_meta_pages(sbi, start_sum_block(sbi), npages, + f2fs_ra_meta_pages(sbi, start_sum_block(sbi), npages, META_CP, true); /* restore for compacted data summary */ @@ -3088,7 +3148,7 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) } if (__exist_node_summaries(sbi)) - ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type), + f2fs_ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type), NR_CURSEG_TYPE - type, META_CP, true); for (; type <= CURSEG_COLD_NODE; type++) { @@ -3114,8 +3174,9 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) int written_size = 0; int i, j; - page = grab_meta_page(sbi, blkaddr++); + page = f2fs_grab_meta_page(sbi, blkaddr++); kaddr = (unsigned char *)page_address(page); + memset(kaddr, 0, PAGE_SIZE); /* Step 1: write nat cache */ seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -3138,8 +3199,9 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) for (j = 0; j < blkoff; j++) { if (!page) { - page = grab_meta_page(sbi, blkaddr++); + page = f2fs_grab_meta_page(sbi, blkaddr++); kaddr = (unsigned char *)page_address(page); + memset(kaddr, 0, PAGE_SIZE); written_size = 0; } summary = (struct f2fs_summary *)(kaddr + written_size); @@ -3174,7 +3236,7 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi, write_current_sum_page(sbi, i, blkaddr + (i - type)); } -void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) +void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) { if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) write_compacted_summaries(sbi, start_blk); @@ -3182,12 +3244,12 @@ void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA); } -void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk) +void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk) { write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE); } -int lookup_journal_in_cursum(struct f2fs_journal *journal, int type, +int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, unsigned int val, int alloc) { int i; @@ -3212,7 +3274,7 @@ int lookup_journal_in_cursum(struct f2fs_journal *journal, int type, static struct page *get_current_sit_page(struct f2fs_sb_info *sbi, unsigned int segno) { - return get_meta_page(sbi, current_sit_addr(sbi, segno)); + return f2fs_get_meta_page(sbi, current_sit_addr(sbi, segno)); } static struct page *get_next_sit_page(struct f2fs_sb_info *sbi, @@ -3225,7 +3287,7 @@ static struct page *get_next_sit_page(struct f2fs_sb_info *sbi, src_off = current_sit_addr(sbi, start); dst_off = next_sit_addr(sbi, src_off); - page = grab_meta_page(sbi, dst_off); + page = f2fs_grab_meta_page(sbi, dst_off); seg_info_to_sit_page(sbi, page, start); set_page_dirty(page); @@ -3321,7 +3383,7 @@ static void remove_sits_in_journal(struct f2fs_sb_info *sbi) * CP calls this function, which flushes SIT entries including sit_journal, * and moves prefree segs to free segs. */ -void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) +void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct sit_info *sit_i = SIT_I(sbi); unsigned long *bitmap = sit_i->dirty_sentries_bitmap; @@ -3380,6 +3442,11 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) int offset, sit_offset; se = get_seg_entry(sbi, segno); +#ifdef CONFIG_F2FS_CHECK_FS + if (memcmp(se->cur_valid_map, se->cur_valid_map_mir, + SIT_VBLOCK_MAP_SIZE)) + f2fs_bug_on(sbi, 1); +#endif /* add discard candidates */ if (!(cpc->reason & CP_DISCARD)) { @@ -3388,17 +3455,21 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) } if (to_journal) { - offset = lookup_journal_in_cursum(journal, + offset = f2fs_lookup_journal_in_cursum(journal, SIT_JOURNAL, segno, 1); f2fs_bug_on(sbi, offset < 0); segno_in_journal(journal, offset) = cpu_to_le32(segno); seg_info_to_raw_sit(se, &sit_in_journal(journal, offset)); + check_block_count(sbi, segno, + &sit_in_journal(journal, offset)); } else { sit_offset = SIT_ENTRY_OFFSET(sit_i, segno); seg_info_to_raw_sit(se, &raw_sit->entries[sit_offset]); + check_block_count(sbi, segno, + &raw_sit->entries[sit_offset]); } __clear_bit(segno, bitmap); @@ -3597,9 +3668,10 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) unsigned int i, start, end; unsigned int readed, start_blk = 0; int err = 0; + block_t total_node_blocks = 0; do { - readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES, + readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES, META_SIT, true); start = start_blk * sit_i->sents_per_block; @@ -3619,6 +3691,8 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) if (err) return err; seg_info_from_raw_sit(se, &sit); + if (IS_NODESEG(se->type)) + total_node_blocks += se->valid_blocks; /* build discard map only one time */ if (f2fs_discard_en(sbi)) { @@ -3647,15 +3721,28 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) unsigned int old_valid_blocks; start = le32_to_cpu(segno_in_journal(journal, i)); + if (start >= MAIN_SEGS(sbi)) { + f2fs_msg(sbi->sb, KERN_ERR, + "Wrong journal entry on segno %u", + start); + set_sbi_flag(sbi, SBI_NEED_FSCK); + err = -EINVAL; + break; + } + se = &sit_i->sentries[start]; sit = sit_in_journal(journal, i); old_valid_blocks = se->valid_blocks; + if (IS_NODESEG(se->type)) + total_node_blocks -= old_valid_blocks; err = check_block_count(sbi, start, &sit); if (err) break; seg_info_from_raw_sit(se, &sit); + if (IS_NODESEG(se->type)) + total_node_blocks += se->valid_blocks; if (f2fs_discard_en(sbi)) { if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { @@ -3664,16 +3751,28 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) } else { memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += old_valid_blocks - - se->valid_blocks; + sbi->discard_blks += old_valid_blocks; + sbi->discard_blks -= se->valid_blocks; } } - if (sbi->segs_per_sec > 1) + if (sbi->segs_per_sec > 1) { get_sec_entry(sbi, start)->valid_blocks += - se->valid_blocks - old_valid_blocks; + se->valid_blocks; + get_sec_entry(sbi, start)->valid_blocks -= + old_valid_blocks; + } } up_read(&curseg->journal_rwsem); + + if (!err && total_node_blocks != valid_node_count(sbi)) { + f2fs_msg(sbi->sb, KERN_ERR, + "SIT is corrupted node# %u vs %u", + total_node_blocks, valid_node_count(sbi)); + set_sbi_flag(sbi, SBI_NEED_FSCK); + err = -EINVAL; + } + return err; } @@ -3772,7 +3871,7 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi) down_write(&sit_i->sentry_lock); - sit_i->min_mtime = LLONG_MAX; + sit_i->min_mtime = ULLONG_MAX; for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { unsigned int i; @@ -3786,11 +3885,11 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi) if (sit_i->min_mtime > mtime) sit_i->min_mtime = mtime; } - sit_i->max_mtime = get_mtime(sbi); + sit_i->max_mtime = get_mtime(sbi, false); up_write(&sit_i->sentry_lock); } -int build_segment_manager(struct f2fs_sb_info *sbi) +int f2fs_build_segment_manager(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -3822,14 +3921,12 @@ int build_segment_manager(struct f2fs_sb_info *sbi) sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS; sm_info->min_ssr_sections = reserved_sections(sbi); - sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS; - INIT_LIST_HEAD(&sm_info->sit_entry_set); init_rwsem(&sm_info->curseg_lock); if (!f2fs_readonly(sbi->sb)) { - err = create_flush_cmd_control(sbi); + err = f2fs_create_flush_cmd_control(sbi); if (err) return err; } @@ -3954,13 +4051,13 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi) kfree(sit_i); } -void destroy_segment_manager(struct f2fs_sb_info *sbi) +void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi) { struct f2fs_sm_info *sm_info = SM_I(sbi); if (!sm_info) return; - destroy_flush_cmd_control(sbi, true); + f2fs_destroy_flush_cmd_control(sbi, true); destroy_discard_cmd_control(sbi); destroy_dirty_segmap(sbi); destroy_curseg(sbi); @@ -3970,7 +4067,7 @@ void destroy_segment_manager(struct f2fs_sb_info *sbi) kfree(sm_info); } -int __init create_segment_manager_caches(void) +int __init f2fs_create_segment_manager_caches(void) { discard_entry_slab = f2fs_kmem_cache_create("discard_entry", sizeof(struct discard_entry)); @@ -4003,7 +4100,7 @@ fail: return -ENOMEM; } -void destroy_segment_manager_caches(void) +void f2fs_destroy_segment_manager_caches(void) { kmem_cache_destroy(sit_entry_set_slab); kmem_cache_destroy(discard_cmd_slab); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 3325d0769723..f18fc82fbe99 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -85,7 +85,7 @@ (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1)) #define GET_SEGNO(sbi, blk_addr) \ - ((((blk_addr) == NULL_ADDR) || ((blk_addr) == NEW_ADDR)) ? \ + ((!is_valid_blkaddr(blk_addr)) ? \ NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \ GET_SEGNO_FROM_SEG0(sbi, blk_addr))) #define BLKS_PER_SEC(sbi) \ @@ -215,6 +215,8 @@ struct segment_allocation { #define IS_DUMMY_WRITTEN_PAGE(page) \ (page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE) +#define MAX_SKIP_ATOMIC_COUNT 16 + struct inmem_pages { struct list_head list; struct page *page; @@ -375,6 +377,7 @@ static inline void seg_info_to_sit_page(struct f2fs_sb_info *sbi, int i; raw_sit = (struct f2fs_sit_block *)page_address(page); + memset(raw_sit, 0, PAGE_SIZE); for (i = 0; i < end - start; i++) { rs = &raw_sit->entries[i]; se = get_seg_entry(sbi, start + i); @@ -742,12 +745,23 @@ static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start) #endif } -static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi) +static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi, + bool base_time) { struct sit_info *sit_i = SIT_I(sbi); - time64_t now = ktime_get_real_seconds(); + time64_t diff, now = ktime_get_real_seconds(); + + if (now >= sit_i->mounted_time) + return sit_i->elapsed_time + now - sit_i->mounted_time; - return sit_i->elapsed_time + now - sit_i->mounted_time; + /* system time is set to the past */ + if (!base_time) { + diff = sit_i->mounted_time - now; + if (sit_i->elapsed_time >= diff) + return sit_i->elapsed_time - diff; + return 0; + } + return sit_i->elapsed_time; } static inline void set_summary(struct f2fs_summary *sum, nid_t nid, @@ -771,15 +785,6 @@ static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type) - (base + 1) + type; } -static inline bool no_fggc_candidate(struct f2fs_sb_info *sbi, - unsigned int secno) -{ - if (get_valid_blocks(sbi, GET_SEG_FROM_SEC(sbi, secno), true) > - sbi->fggc_threshold) - return true; - return false; -} - static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno) { if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno)) diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index 0b5664a1a6cc..36cfd816c160 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -109,11 +109,11 @@ unsigned long f2fs_shrink_scan(struct shrinker *shrink, /* shrink clean nat cache entries */ if (freed < nr) - freed += try_to_free_nats(sbi, nr - freed); + freed += f2fs_try_to_free_nats(sbi, nr - freed); /* shrink free nids cache entries */ if (freed < nr) - freed += try_to_free_nids(sbi, nr - freed); + freed += f2fs_try_to_free_nids(sbi, nr - freed); spin_lock(&f2fs_list_lock); p = p->next; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 970ae27f401c..e7441e8d1ff8 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -740,6 +740,10 @@ static int parse_options(struct super_block *sb, char *options) } else if (strlen(name) == 6 && !strncmp(name, "strict", 6)) { F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_STRICT; + } else if (strlen(name) == 9 && + !strncmp(name, "nobarrier", 9)) { + F2FS_OPTION(sbi).fsync_mode = + FSYNC_MODE_NOBARRIER; } else { kfree(name); return -EINVAL; @@ -826,15 +830,14 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) /* Initialize f2fs-specific inode info */ atomic_set(&fi->dirty_pages, 0); - fi->i_current_depth = 1; init_rwsem(&fi->i_sem); INIT_LIST_HEAD(&fi->dirty_list); INIT_LIST_HEAD(&fi->gdirty_list); INIT_LIST_HEAD(&fi->inmem_ilist); INIT_LIST_HEAD(&fi->inmem_pages); mutex_init(&fi->inmem_lock); - init_rwsem(&fi->dio_rwsem[READ]); - init_rwsem(&fi->dio_rwsem[WRITE]); + init_rwsem(&fi->i_gc_rwsem[READ]); + init_rwsem(&fi->i_gc_rwsem[WRITE]); init_rwsem(&fi->i_mmap_sem); init_rwsem(&fi->i_xattr_sem); @@ -862,7 +865,7 @@ static int f2fs_drop_inode(struct inode *inode) /* some remained atomic pages should discarded */ if (f2fs_is_atomic_file(inode)) - drop_inmem_pages(inode); + f2fs_drop_inmem_pages(inode); /* should remain fi->extent_tree for writepage */ f2fs_destroy_extent_node(inode); @@ -999,7 +1002,7 @@ static void f2fs_put_super(struct super_block *sb) struct cp_control cpc = { .reason = CP_UMOUNT, }; - write_checkpoint(sbi, &cpc); + f2fs_write_checkpoint(sbi, &cpc); } /* be sure to wait for any on-going discard commands */ @@ -1009,17 +1012,17 @@ static void f2fs_put_super(struct super_block *sb) struct cp_control cpc = { .reason = CP_UMOUNT | CP_TRIMMED, }; - write_checkpoint(sbi, &cpc); + f2fs_write_checkpoint(sbi, &cpc); } - /* write_checkpoint can update stat informaion */ + /* f2fs_write_checkpoint can update stat informaion */ f2fs_destroy_stats(sbi); /* * normally superblock is clean, so we need to release this. * In addition, EIO will skip do checkpoint, we need this as well. */ - release_ino_entry(sbi, true); + f2fs_release_ino_entry(sbi, true); f2fs_leave_shrinker(sbi); mutex_unlock(&sbi->umount_mutex); @@ -1031,8 +1034,8 @@ static void f2fs_put_super(struct super_block *sb) iput(sbi->meta_inode); /* destroy f2fs internal modules */ - destroy_node_manager(sbi); - destroy_segment_manager(sbi); + f2fs_destroy_node_manager(sbi); + f2fs_destroy_segment_manager(sbi); kfree(sbi->ckpt); @@ -1074,7 +1077,7 @@ int f2fs_sync_fs(struct super_block *sb, int sync) cpc.reason = __get_cp_reason(sbi); mutex_lock(&sbi->gc_mutex); - err = write_checkpoint(sbi, &cpc); + err = f2fs_write_checkpoint(sbi, &cpc); mutex_unlock(&sbi->gc_mutex); } f2fs_trace_ios(NULL, 1); @@ -1477,11 +1480,11 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) */ if ((*flags & SB_RDONLY) || !test_opt(sbi, BG_GC)) { if (sbi->gc_thread) { - stop_gc_thread(sbi); + f2fs_stop_gc_thread(sbi); need_restart_gc = true; } } else if (!sbi->gc_thread) { - err = start_gc_thread(sbi); + err = f2fs_start_gc_thread(sbi); if (err) goto restore_opts; need_stop_gc = true; @@ -1504,9 +1507,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) */ if ((*flags & SB_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) { clear_opt(sbi, FLUSH_MERGE); - destroy_flush_cmd_control(sbi, false); + f2fs_destroy_flush_cmd_control(sbi, false); } else { - err = create_flush_cmd_control(sbi); + err = f2fs_create_flush_cmd_control(sbi); if (err) goto restore_gc; } @@ -1524,11 +1527,11 @@ skip: return 0; restore_gc: if (need_restart_gc) { - if (start_gc_thread(sbi)) + if (f2fs_start_gc_thread(sbi)) f2fs_msg(sbi->sb, KERN_WARNING, "background gc thread has stopped"); } else if (need_stop_gc) { - stop_gc_thread(sbi); + f2fs_stop_gc_thread(sbi); } restore_opts: #ifdef CONFIG_QUOTA @@ -1800,7 +1803,7 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id, inode = d_inode(path->dentry); inode_lock(inode); - F2FS_I(inode)->i_flags |= FS_NOATIME_FL | FS_IMMUTABLE_FL; + F2FS_I(inode)->i_flags |= F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL; inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, S_NOATIME | S_IMMUTABLE); inode_unlock(inode); @@ -1824,7 +1827,7 @@ static int f2fs_quota_off(struct super_block *sb, int type) goto out_put; inode_lock(inode); - F2FS_I(inode)->i_flags &= ~(FS_NOATIME_FL | FS_IMMUTABLE_FL); + F2FS_I(inode)->i_flags &= ~(F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL); inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); @@ -1946,7 +1949,7 @@ static struct inode *f2fs_nfs_get_inode(struct super_block *sb, struct f2fs_sb_info *sbi = F2FS_SB(sb); struct inode *inode; - if (check_nid_range(sbi, ino)) + if (f2fs_check_nid_range(sbi, ino)) return ERR_PTR(-ESTALE); /* @@ -2129,6 +2132,8 @@ static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi, static int sanity_check_raw_super(struct f2fs_sb_info *sbi, struct buffer_head *bh) { + block_t segment_count, segs_per_sec, secs_per_zone; + block_t total_sections, blocks_per_seg; struct f2fs_super_block *raw_super = (struct f2fs_super_block *) (bh->b_data + F2FS_SUPER_OFFSET); struct super_block *sb = sbi->sb; @@ -2185,6 +2190,72 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, return 1; } + segment_count = le32_to_cpu(raw_super->segment_count); + segs_per_sec = le32_to_cpu(raw_super->segs_per_sec); + secs_per_zone = le32_to_cpu(raw_super->secs_per_zone); + total_sections = le32_to_cpu(raw_super->section_count); + + /* blocks_per_seg should be 512, given the above check */ + blocks_per_seg = 1 << le32_to_cpu(raw_super->log_blocks_per_seg); + + if (segment_count > F2FS_MAX_SEGMENT || + segment_count < F2FS_MIN_SEGMENTS) { + f2fs_msg(sb, KERN_INFO, + "Invalid segment count (%u)", + segment_count); + return 1; + } + + if (total_sections > segment_count || + total_sections < F2FS_MIN_SEGMENTS || + segs_per_sec > segment_count || !segs_per_sec) { + f2fs_msg(sb, KERN_INFO, + "Invalid segment/section count (%u, %u x %u)", + segment_count, total_sections, segs_per_sec); + return 1; + } + + if ((segment_count / segs_per_sec) < total_sections) { + f2fs_msg(sb, KERN_INFO, + "Small segment_count (%u < %u * %u)", + segment_count, segs_per_sec, total_sections); + return 1; + } + + if (segment_count > (le32_to_cpu(raw_super->block_count) >> 9)) { + f2fs_msg(sb, KERN_INFO, + "Wrong segment_count / block_count (%u > %u)", + segment_count, le32_to_cpu(raw_super->block_count)); + return 1; + } + + if (secs_per_zone > total_sections) { + f2fs_msg(sb, KERN_INFO, + "Wrong secs_per_zone (%u > %u)", + secs_per_zone, total_sections); + return 1; + } + if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION || + raw_super->hot_ext_count > F2FS_MAX_EXTENSION || + (le32_to_cpu(raw_super->extension_count) + + raw_super->hot_ext_count) > F2FS_MAX_EXTENSION) { + f2fs_msg(sb, KERN_INFO, + "Corrupted extension count (%u + %u > %u)", + le32_to_cpu(raw_super->extension_count), + raw_super->hot_ext_count, + F2FS_MAX_EXTENSION); + return 1; + } + + if (le32_to_cpu(raw_super->cp_payload) > + (blocks_per_seg - F2FS_CP_PACKS)) { + f2fs_msg(sb, KERN_INFO, + "Insane cp_payload (%u > %u)", + le32_to_cpu(raw_super->cp_payload), + blocks_per_seg - F2FS_CP_PACKS); + return 1; + } + /* check reserved ino info */ if (le32_to_cpu(raw_super->node_ino) != 1 || le32_to_cpu(raw_super->meta_ino) != 2 || @@ -2197,13 +2268,6 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, return 1; } - if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) { - f2fs_msg(sb, KERN_INFO, - "Invalid segment count (%u)", - le32_to_cpu(raw_super->segment_count)); - return 1; - } - /* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */ if (sanity_check_area_boundary(sbi, bh)) return 1; @@ -2211,7 +2275,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, return 0; } -int sanity_check_ckpt(struct f2fs_sb_info *sbi) +int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) { unsigned int total, fsmeta; struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); @@ -2292,13 +2356,15 @@ static void init_sb_info(struct f2fs_sb_info *sbi) for (i = 0; i < NR_COUNT_TYPE; i++) atomic_set(&sbi->nr_pages[i], 0); - atomic_set(&sbi->wb_sync_req, 0); + for (i = 0; i < META; i++) + atomic_set(&sbi->wb_sync_req[i], 0); INIT_LIST_HEAD(&sbi->s_list); mutex_init(&sbi->umount_mutex); for (i = 0; i < NR_PAGE_TYPE - 1; i++) for (j = HOT; j < NR_TEMP_TYPE; j++) mutex_init(&sbi->wio_mutex[i][j]); + init_rwsem(&sbi->io_order_lock); spin_lock_init(&sbi->cp_lock); sbi->dirty_device = 0; @@ -2759,7 +2825,7 @@ try_onemore: goto free_io_dummy; } - err = get_valid_checkpoint(sbi); + err = f2fs_get_valid_checkpoint(sbi); if (err) { f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint"); goto free_meta_inode; @@ -2789,18 +2855,18 @@ try_onemore: spin_lock_init(&sbi->inode_lock[i]); } - init_extent_cache_info(sbi); + f2fs_init_extent_cache_info(sbi); - init_ino_entry_info(sbi); + f2fs_init_ino_entry_info(sbi); /* setup f2fs internal modules */ - err = build_segment_manager(sbi); + err = f2fs_build_segment_manager(sbi); if (err) { f2fs_msg(sb, KERN_ERR, "Failed to initialize F2FS segment manager"); goto free_sm; } - err = build_node_manager(sbi); + err = f2fs_build_node_manager(sbi); if (err) { f2fs_msg(sb, KERN_ERR, "Failed to initialize F2FS node manager"); @@ -2818,7 +2884,7 @@ try_onemore: sbi->kbytes_written = le64_to_cpu(seg_i->journal->info.kbytes_written); - build_gc_manager(sbi); + f2fs_build_gc_manager(sbi); /* get an inode for node space */ sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi)); @@ -2870,7 +2936,7 @@ try_onemore: } #endif /* if there are nt orphan nodes free them */ - err = recover_orphan_inodes(sbi); + err = f2fs_recover_orphan_inodes(sbi); if (err) goto free_meta; @@ -2892,7 +2958,7 @@ try_onemore: if (!retry) goto skip_recovery; - err = recover_fsync_data(sbi, false); + err = f2fs_recover_fsync_data(sbi, false); if (err < 0) { need_fsck = true; f2fs_msg(sb, KERN_ERR, @@ -2900,7 +2966,7 @@ try_onemore: goto free_meta; } } else { - err = recover_fsync_data(sbi, true); + err = f2fs_recover_fsync_data(sbi, true); if (!f2fs_readonly(sb) && err > 0) { err = -EINVAL; @@ -2910,7 +2976,7 @@ try_onemore: } } skip_recovery: - /* recover_fsync_data() cleared this already */ + /* f2fs_recover_fsync_data() cleared this already */ clear_sbi_flag(sbi, SBI_POR_DOING); /* @@ -2919,7 +2985,7 @@ skip_recovery: */ if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) { /* After POR, we can run background GC thread.*/ - err = start_gc_thread(sbi); + err = f2fs_start_gc_thread(sbi); if (err) goto free_meta; } @@ -2950,10 +3016,10 @@ free_meta: #endif f2fs_sync_inode_meta(sbi); /* - * Some dirty meta pages can be produced by recover_orphan_inodes() + * Some dirty meta pages can be produced by f2fs_recover_orphan_inodes() * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg() - * followed by write_checkpoint() through f2fs_write_node_pages(), which - * falls into an infinite loop in sync_meta_pages(). + * followed by f2fs_write_checkpoint() through f2fs_write_node_pages(), which + * falls into an infinite loop in f2fs_sync_meta_pages(). */ truncate_inode_pages_final(META_MAPPING(sbi)); #ifdef CONFIG_QUOTA @@ -2966,13 +3032,13 @@ free_root_inode: free_stats: f2fs_destroy_stats(sbi); free_node_inode: - release_ino_entry(sbi, true); + f2fs_release_ino_entry(sbi, true); truncate_inode_pages_final(NODE_MAPPING(sbi)); iput(sbi->node_inode); free_nm: - destroy_node_manager(sbi); + f2fs_destroy_node_manager(sbi); free_sm: - destroy_segment_manager(sbi); + f2fs_destroy_segment_manager(sbi); free_devices: destroy_device_list(sbi); kfree(sbi->ckpt); @@ -3018,8 +3084,8 @@ static void kill_f2fs_super(struct super_block *sb) { if (sb->s_root) { set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE); - stop_gc_thread(F2FS_SB(sb)); - stop_discard_thread(F2FS_SB(sb)); + f2fs_stop_gc_thread(F2FS_SB(sb)); + f2fs_stop_discard_thread(F2FS_SB(sb)); } kill_block_super(sb); } @@ -3057,21 +3123,27 @@ static int __init init_f2fs_fs(void) { int err; + if (PAGE_SIZE != F2FS_BLKSIZE) { + printk("F2FS not supported on PAGE_SIZE(%lu) != %d\n", + PAGE_SIZE, F2FS_BLKSIZE); + return -EINVAL; + } + f2fs_build_trace_ios(); err = init_inodecache(); if (err) goto fail; - err = create_node_manager_caches(); + err = f2fs_create_node_manager_caches(); if (err) goto free_inodecache; - err = create_segment_manager_caches(); + err = f2fs_create_segment_manager_caches(); if (err) goto free_node_manager_caches; - err = create_checkpoint_caches(); + err = f2fs_create_checkpoint_caches(); if (err) goto free_segment_manager_caches; - err = create_extent_cache(); + err = f2fs_create_extent_cache(); if (err) goto free_checkpoint_caches; err = f2fs_init_sysfs(); @@ -3086,8 +3158,13 @@ static int __init init_f2fs_fs(void) err = f2fs_create_root_stats(); if (err) goto free_filesystem; + err = f2fs_init_post_read_processing(); + if (err) + goto free_root_stats; return 0; +free_root_stats: + f2fs_destroy_root_stats(); free_filesystem: unregister_filesystem(&f2fs_fs_type); free_shrinker: @@ -3095,13 +3172,13 @@ free_shrinker: free_sysfs: f2fs_exit_sysfs(); free_extent_cache: - destroy_extent_cache(); + f2fs_destroy_extent_cache(); free_checkpoint_caches: - destroy_checkpoint_caches(); + f2fs_destroy_checkpoint_caches(); free_segment_manager_caches: - destroy_segment_manager_caches(); + f2fs_destroy_segment_manager_caches(); free_node_manager_caches: - destroy_node_manager_caches(); + f2fs_destroy_node_manager_caches(); free_inodecache: destroy_inodecache(); fail: @@ -3110,14 +3187,15 @@ fail: static void __exit exit_f2fs_fs(void) { + f2fs_destroy_post_read_processing(); f2fs_destroy_root_stats(); unregister_filesystem(&f2fs_fs_type); unregister_shrinker(&f2fs_shrinker_info); f2fs_exit_sysfs(); - destroy_extent_cache(); - destroy_checkpoint_caches(); - destroy_segment_manager_caches(); - destroy_node_manager_caches(); + f2fs_destroy_extent_cache(); + f2fs_destroy_checkpoint_caches(); + f2fs_destroy_segment_manager_caches(); + f2fs_destroy_node_manager_caches(); destroy_inodecache(); f2fs_destroy_trace_ios(); } diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 4b47ca6296a7..2e7e611deaef 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -147,13 +147,13 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, int len = 0, i; len += snprintf(buf + len, PAGE_SIZE - len, - "cold file extenstion:\n"); + "cold file extension:\n"); for (i = 0; i < cold_count; i++) len += snprintf(buf + len, PAGE_SIZE - len, "%s\n", extlist[i]); len += snprintf(buf + len, PAGE_SIZE - len, - "hot file extenstion:\n"); + "hot file extension:\n"); for (i = cold_count; i < cold_count + hot_count; i++) len += snprintf(buf + len, PAGE_SIZE - len, "%s\n", extlist[i]); @@ -165,7 +165,7 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, return snprintf(buf, PAGE_SIZE, "%u\n", *ui); } -static ssize_t f2fs_sbi_store(struct f2fs_attr *a, +static ssize_t __sbi_store(struct f2fs_attr *a, struct f2fs_sb_info *sbi, const char *buf, size_t count) { @@ -201,13 +201,13 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, down_write(&sbi->sb_lock); - ret = update_extension_list(sbi, name, hot, set); + ret = f2fs_update_extension_list(sbi, name, hot, set); if (ret) goto out; ret = f2fs_commit_super(sbi, false); if (ret) - update_extension_list(sbi, name, hot, !set); + f2fs_update_extension_list(sbi, name, hot, !set); out: up_write(&sbi->sb_lock); return ret ? ret : count; @@ -245,19 +245,56 @@ out: return count; } + if (!strcmp(a->attr.name, "trim_sections")) + return -EINVAL; + + if (!strcmp(a->attr.name, "gc_urgent")) { + if (t >= 1) { + sbi->gc_mode = GC_URGENT; + if (sbi->gc_thread) { + wake_up_interruptible_all( + &sbi->gc_thread->gc_wait_queue_head); + wake_up_discard_thread(sbi, true); + } + } else { + sbi->gc_mode = GC_NORMAL; + } + return count; + } + if (!strcmp(a->attr.name, "gc_idle")) { + if (t == GC_IDLE_CB) + sbi->gc_mode = GC_IDLE_CB; + else if (t == GC_IDLE_GREEDY) + sbi->gc_mode = GC_IDLE_GREEDY; + else + sbi->gc_mode = GC_NORMAL; + return count; + } + *ui = t; if (!strcmp(a->attr.name, "iostat_enable") && *ui == 0) f2fs_reset_iostat(sbi); - if (!strcmp(a->attr.name, "gc_urgent") && t == 1 && sbi->gc_thread) { - sbi->gc_thread->gc_wake = 1; - wake_up_interruptible_all(&sbi->gc_thread->gc_wait_queue_head); - wake_up_discard_thread(sbi, true); - } - return count; } +static ssize_t f2fs_sbi_store(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, + const char *buf, size_t count) +{ + ssize_t ret; + bool gc_entry = (!strcmp(a->attr.name, "gc_urgent") || + a->struct_type == GC_THREAD); + + if (gc_entry) + down_read(&sbi->sb->s_umount); + ret = __sbi_store(a, sbi, buf, count); + if (gc_entry) + up_read(&sbi->sb->s_umount); + + return ret; +} + static ssize_t f2fs_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -346,8 +383,8 @@ F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent_sleep_time, F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time); F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time); F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time); -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle); -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent, gc_urgent); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle, gc_mode); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_urgent, gc_mode); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments); F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards); F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_granularity, discard_granularity); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index ae2dfa709f5d..708271871f94 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -252,7 +252,7 @@ static int read_inline_xattr(struct inode *inode, struct page *ipage, if (ipage) { inline_addr = inline_xattr_addr(inode, ipage); } else { - page = get_node_page(sbi, inode->i_ino); + page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) return PTR_ERR(page); @@ -273,7 +273,7 @@ static int read_xattr_block(struct inode *inode, void *txattr_addr) void *xattr_addr; /* The inode already has an extended attribute block. */ - xpage = get_node_page(sbi, xnid); + xpage = f2fs_get_node_page(sbi, xnid); if (IS_ERR(xpage)) return PTR_ERR(xpage); @@ -397,7 +397,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, int err = 0; if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid) - if (!alloc_nid(sbi, &new_nid)) + if (!f2fs_alloc_nid(sbi, &new_nid)) return -ENOSPC; /* write to inline xattr */ @@ -405,9 +405,9 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, if (ipage) { inline_addr = inline_xattr_addr(inode, ipage); } else { - in_page = get_node_page(sbi, inode->i_ino); + in_page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(in_page)) { - alloc_nid_failed(sbi, new_nid); + f2fs_alloc_nid_failed(sbi, new_nid); return PTR_ERR(in_page); } inline_addr = inline_xattr_addr(inode, in_page); @@ -417,8 +417,8 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, NODE, true); /* no need to use xattr node block */ if (hsize <= inline_size) { - err = truncate_xattr_node(inode); - alloc_nid_failed(sbi, new_nid); + err = f2fs_truncate_xattr_node(inode); + f2fs_alloc_nid_failed(sbi, new_nid); if (err) { f2fs_put_page(in_page, 1); return err; @@ -431,10 +431,10 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, /* write to xattr node block */ if (F2FS_I(inode)->i_xattr_nid) { - xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid); + xpage = f2fs_get_node_page(sbi, F2FS_I(inode)->i_xattr_nid); if (IS_ERR(xpage)) { err = PTR_ERR(xpage); - alloc_nid_failed(sbi, new_nid); + f2fs_alloc_nid_failed(sbi, new_nid); goto in_page_out; } f2fs_bug_on(sbi, new_nid); @@ -442,13 +442,13 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, } else { struct dnode_of_data dn; set_new_dnode(&dn, inode, NULL, NULL, new_nid); - xpage = new_node_page(&dn, XATTR_NODE_OFFSET); + xpage = f2fs_new_node_page(&dn, XATTR_NODE_OFFSET); if (IS_ERR(xpage)) { err = PTR_ERR(xpage); - alloc_nid_failed(sbi, new_nid); + f2fs_alloc_nid_failed(sbi, new_nid); goto in_page_out; } - alloc_nid_done(sbi, new_nid); + f2fs_alloc_nid_done(sbi, new_nid); } xattr_addr = page_address(xpage); @@ -693,7 +693,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, if (err) return err; - /* this case is only from init_inode_metadata */ + /* this case is only from f2fs_init_inode_metadata */ if (ipage) return __f2fs_setxattr(inode, index, name, value, size, ipage, flags); |