summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/f2fs/checkpoint.c16
-rw-r--r--fs/f2fs/data.c213
-rw-r--r--fs/f2fs/debug.c18
-rw-r--r--fs/f2fs/dir.c3
-rw-r--r--fs/f2fs/f2fs.h133
-rw-r--r--fs/f2fs/file.c307
-rw-r--r--fs/f2fs/gc.c186
-rw-r--r--fs/f2fs/hash.c11
-rw-r--r--fs/f2fs/inline.c29
-rw-r--r--fs/f2fs/inode.c34
-rw-r--r--fs/f2fs/namei.c38
-rw-r--r--fs/f2fs/node.c29
-rw-r--r--fs/f2fs/node.h1
-rw-r--r--fs/f2fs/segment.c460
-rw-r--r--fs/f2fs/segment.h40
-rw-r--r--fs/f2fs/super.c88
-rw-r--r--fs/f2fs/verity.c2
17 files changed, 817 insertions, 791 deletions
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 456c1e89386a..6d8b2bf14de0 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -98,13 +98,7 @@ repeat:
}
if (unlikely(!PageUptodate(page))) {
- if (page->index == sbi->metapage_eio_ofs) {
- if (sbi->metapage_eio_cnt++ == MAX_RETRY_META_PAGE_EIO)
- set_ckpt_flags(sbi, CP_ERROR_FLAG);
- } else {
- sbi->metapage_eio_ofs = page->index;
- sbi->metapage_eio_cnt = 0;
- }
+ f2fs_handle_page_eio(sbi, page->index, META);
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
@@ -158,7 +152,7 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
blkaddr, exist);
set_sbi_flag(sbi, SBI_NEED_FSCK);
- WARN_ON(1);
+ dump_stack();
}
return exist;
}
@@ -196,7 +190,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
f2fs_warn(sbi, "access invalid blkaddr:%u",
blkaddr);
set_sbi_flag(sbi, SBI_NEED_FSCK);
- WARN_ON(1);
+ dump_stack();
return false;
} else {
return __is_bitmap_valid(sbi, blkaddr, type);
@@ -1010,9 +1004,7 @@ static void __add_dirty_inode(struct inode *inode, enum inode_type type)
return;
set_inode_flag(inode, flag);
- if (!f2fs_is_volatile_file(inode))
- list_add_tail(&F2FS_I(inode)->dirty_list,
- &sbi->inode_list[type]);
+ list_add_tail(&F2FS_I(inode)->dirty_list, &sbi->inode_list[type]);
stat_inc_dirty_inode(sbi, type);
}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 8f38c26bb16c..7fcbcf979737 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -69,8 +69,7 @@ static bool __is_cp_guaranteed(struct page *page)
if (f2fs_is_compressed_page(page))
return false;
- if ((S_ISREG(inode->i_mode) &&
- (f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) ||
+ if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) ||
page_private_gcing(page))
return true;
return false;
@@ -585,6 +584,34 @@ static bool __has_merged_page(struct bio *bio, struct inode *inode,
return false;
}
+int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi)
+{
+ int i;
+
+ for (i = 0; i < NR_PAGE_TYPE; i++) {
+ int n = (i == META) ? 1 : NR_TEMP_TYPE;
+ int j;
+
+ sbi->write_io[i] = f2fs_kmalloc(sbi,
+ array_size(n, sizeof(struct f2fs_bio_info)),
+ GFP_KERNEL);
+ if (!sbi->write_io[i])
+ return -ENOMEM;
+
+ for (j = HOT; j < n; j++) {
+ init_f2fs_rwsem(&sbi->write_io[i][j].io_rwsem);
+ sbi->write_io[i][j].sbi = sbi;
+ sbi->write_io[i][j].bio = NULL;
+ spin_lock_init(&sbi->write_io[i][j].io_lock);
+ INIT_LIST_HEAD(&sbi->write_io[i][j].io_list);
+ INIT_LIST_HEAD(&sbi->write_io[i][j].bio_list);
+ init_f2fs_rwsem(&sbi->write_io[i][j].bio_list_lock);
+ }
+ }
+
+ return 0;
+}
+
static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
enum page_type type, enum temp_type temp)
{
@@ -2564,7 +2591,12 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
bool ipu_force = false;
int err = 0;
- set_new_dnode(&dn, inode, NULL, NULL, 0);
+ /* Use COW inode to make dnode_of_data for atomic write */
+ if (f2fs_is_atomic_file(inode))
+ set_new_dnode(&dn, F2FS_I(inode)->cow_inode, NULL, NULL, 0);
+ else
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+
if (need_inplace_update(fio) &&
f2fs_lookup_extent_cache(inode, page->index, &ei)) {
fio->old_blkaddr = ei.blk + page->index - ei.fofs;
@@ -2601,6 +2633,7 @@ got_it:
err = -EFSCORRUPTED;
goto out_writepage;
}
+
/*
* If current allocation needs SSR,
* it had better in-place writes for updated data.
@@ -2737,11 +2770,6 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
write:
if (f2fs_is_drop_cache(inode))
goto out;
- /* we should not write 0'th page having journal header */
- if (f2fs_is_volatile_file(inode) && (!page->index ||
- (!wbc->for_reclaim &&
- f2fs_available_free_memory(sbi, BASE_CHECK))))
- goto redirty_out;
/* Dentry/quota blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) {
@@ -3314,6 +3342,100 @@ unlock_out:
return err;
}
+static int __find_data_block(struct inode *inode, pgoff_t index,
+ block_t *blk_addr)
+{
+ struct dnode_of_data dn;
+ struct page *ipage;
+ struct extent_info ei = {0, };
+ int err = 0;
+
+ ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
+
+ set_new_dnode(&dn, inode, ipage, ipage, 0);
+
+ if (f2fs_lookup_extent_cache(inode, index, &ei)) {
+ dn.data_blkaddr = ei.blk + index - ei.fofs;
+ } else {
+ /* hole case */
+ err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
+ if (err) {
+ dn.data_blkaddr = NULL_ADDR;
+ err = 0;
+ }
+ }
+ *blk_addr = dn.data_blkaddr;
+ f2fs_put_dnode(&dn);
+ return err;
+}
+
+static int __reserve_data_block(struct inode *inode, pgoff_t index,
+ block_t *blk_addr, bool *node_changed)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct dnode_of_data dn;
+ struct page *ipage;
+ int err = 0;
+
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+
+ ipage = f2fs_get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(ipage)) {
+ err = PTR_ERR(ipage);
+ goto unlock_out;
+ }
+ set_new_dnode(&dn, inode, ipage, ipage, 0);
+
+ err = f2fs_get_block(&dn, index);
+
+ *blk_addr = dn.data_blkaddr;
+ *node_changed = dn.node_changed;
+ f2fs_put_dnode(&dn);
+
+unlock_out:
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
+ return err;
+}
+
+static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
+ struct page *page, loff_t pos, unsigned int len,
+ block_t *blk_addr, bool *node_changed)
+{
+ struct inode *inode = page->mapping->host;
+ struct inode *cow_inode = F2FS_I(inode)->cow_inode;
+ pgoff_t index = page->index;
+ int err = 0;
+ block_t ori_blk_addr;
+
+ /* If pos is beyond the end of file, reserve a new block in COW inode */
+ if ((pos & PAGE_MASK) >= i_size_read(inode))
+ return __reserve_data_block(cow_inode, index, blk_addr,
+ node_changed);
+
+ /* Look for the block in COW inode first */
+ err = __find_data_block(cow_inode, index, blk_addr);
+ if (err)
+ return err;
+ else if (*blk_addr != NULL_ADDR)
+ return 0;
+
+ /* Look for the block in the original inode */
+ err = __find_data_block(inode, index, &ori_blk_addr);
+ if (err)
+ return err;
+
+ /* Finally, we should reserve a new block in COW inode for the update */
+ err = __reserve_data_block(cow_inode, index, blk_addr, node_changed);
+ if (err)
+ return err;
+
+ if (ori_blk_addr != NULL_ADDR)
+ *blk_addr = ori_blk_addr;
+ return 0;
+}
+
static int f2fs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, struct page **pagep, void **fsdata)
{
@@ -3321,7 +3443,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page = NULL;
pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
- bool need_balance = false, drop_atomic = false;
+ bool need_balance = false;
block_t blkaddr = NULL_ADDR;
int err = 0;
@@ -3332,14 +3454,6 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
goto fail;
}
- if ((f2fs_is_atomic_file(inode) &&
- !f2fs_available_free_memory(sbi, INMEM_PAGES)) ||
- is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) {
- err = -ENOMEM;
- drop_atomic = true;
- goto fail;
- }
-
/*
* We should check this at this moment to avoid deadlock on inode page
* and #0 page. The locking rule for inline_data conversion should be:
@@ -3387,7 +3501,11 @@ repeat:
*pagep = page;
- err = prepare_write_begin(sbi, page, pos, len,
+ if (f2fs_is_atomic_file(inode))
+ err = prepare_atomic_write_begin(sbi, page, pos, len,
+ &blkaddr, &need_balance);
+ else
+ err = prepare_write_begin(sbi, page, pos, len,
&blkaddr, &need_balance);
if (err)
goto fail;
@@ -3443,8 +3561,6 @@ repeat:
fail:
f2fs_put_page(page, 1);
f2fs_write_failed(inode, pos + len);
- if (drop_atomic)
- f2fs_drop_inmem_pages_all(sbi, false);
return err;
}
@@ -3488,8 +3604,12 @@ static int f2fs_write_end(struct file *file,
set_page_dirty(page);
if (pos + copied > i_size_read(inode) &&
- !f2fs_verity_in_progress(inode))
+ !f2fs_verity_in_progress(inode)) {
f2fs_i_size_write(inode, pos + copied);
+ if (f2fs_is_atomic_file(inode))
+ f2fs_i_size_write(F2FS_I(inode)->cow_inode,
+ pos + copied);
+ }
unlock_out:
f2fs_put_page(page, 1);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
@@ -3522,9 +3642,6 @@ void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
inode->i_ino == F2FS_COMPRESS_INO(sbi))
clear_page_private_data(&folio->page);
- if (page_private_atomic(&folio->page))
- return f2fs_drop_inmem_page(inode, &folio->page);
-
folio_detach_private(folio);
}
@@ -3536,10 +3653,6 @@ bool f2fs_release_folio(struct folio *folio, gfp_t wait)
if (folio_test_dirty(folio))
return false;
- /* This is atomic written page, keep Private */
- if (page_private_atomic(&folio->page))
- return false;
-
sbi = F2FS_M_SB(folio->mapping);
if (test_opt(sbi, COMPRESS_CACHE)) {
struct inode *inode = folio->mapping->host;
@@ -3565,18 +3678,6 @@ static bool f2fs_dirty_data_folio(struct address_space *mapping,
folio_mark_uptodate(folio);
BUG_ON(folio_test_swapcache(folio));
- if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) {
- if (!page_private_atomic(&folio->page)) {
- f2fs_register_inmem_page(inode, &folio->page);
- return true;
- }
- /*
- * Previously, this page has been registered, we just
- * return here.
- */
- return false;
- }
-
if (!folio_test_dirty(folio)) {
filemap_dirty_folio(mapping, folio);
f2fs_update_dirty_folio(inode, folio);
@@ -3656,42 +3757,14 @@ out:
int f2fs_migrate_page(struct address_space *mapping,
struct page *newpage, struct page *page, enum migrate_mode mode)
{
- int rc, extra_count;
- struct f2fs_inode_info *fi = F2FS_I(mapping->host);
- bool atomic_written = page_private_atomic(page);
+ int rc, extra_count = 0;
BUG_ON(PageWriteback(page));
- /* migrating an atomic written page is safe with the inmem_lock hold */
- if (atomic_written) {
- if (mode != MIGRATE_SYNC)
- return -EBUSY;
- if (!mutex_trylock(&fi->inmem_lock))
- return -EAGAIN;
- }
-
- /* one extra reference was held for atomic_write page */
- extra_count = atomic_written ? 1 : 0;
rc = migrate_page_move_mapping(mapping, newpage,
page, extra_count);
- if (rc != MIGRATEPAGE_SUCCESS) {
- if (atomic_written)
- mutex_unlock(&fi->inmem_lock);
+ if (rc != MIGRATEPAGE_SUCCESS)
return rc;
- }
-
- if (atomic_written) {
- struct inmem_pages *cur;
-
- list_for_each_entry(cur, &fi->inmem_pages, list)
- if (cur->page == page) {
- cur->page = newpage;
- break;
- }
- mutex_unlock(&fi->inmem_lock);
- put_page(page);
- get_page(newpage);
- }
/* guarantee to start from no stale private field */
set_page_private(newpage, 0);
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index fcdf253cd211..c92625ef16d0 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -91,11 +91,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
si->nquota_files = sbi->nquota_files;
si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
- si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
si->aw_cnt = sbi->atomic_files;
- si->vw_cnt = atomic_read(&sbi->vw_cnt);
si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt);
- si->max_vw_cnt = atomic_read(&sbi->max_vw_cnt);
si->nr_dio_read = get_pages(sbi, F2FS_DIO_READ);
si->nr_dio_write = get_pages(sbi, F2FS_DIO_WRITE);
si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA);
@@ -167,8 +164,6 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID];
si->io_skip_bggc = sbi->io_skip_bggc;
si->other_skip_bggc = sbi->other_skip_bggc;
- 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;
@@ -296,7 +291,6 @@ get_cache:
sizeof(struct nat_entry);
si->cache_mem += NM_I(sbi)->nat_cnt[DIRTY_NAT] *
sizeof(struct nat_entry_set);
- si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
for (i = 0; i < MAX_INO_ENTRY; i++)
si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
si->cache_mem += atomic_read(&sbi->total_ext_tree) *
@@ -491,10 +485,6 @@ 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_printf(s, "BG skip : IO: %u, Other: %u\n",
si->io_skip_bggc, si->other_skip_bggc);
seq_puts(s, "\nExtent Cache:\n");
@@ -519,10 +509,8 @@ static int stat_show(struct seq_file *s, void *v)
si->flush_list_empty,
si->nr_discarding, si->nr_discarded,
si->nr_discard_cmd, si->undiscard_blks);
- seq_printf(s, " - inmem: %4d, atomic IO: %4d (Max. %4d), "
- "volatile IO: %4d (Max. %4d)\n",
- si->inmem_pages, si->aw_cnt, si->max_aw_cnt,
- si->vw_cnt, si->max_vw_cnt);
+ seq_printf(s, " - atomic IO: %4d (Max. %4d)\n",
+ si->aw_cnt, si->max_aw_cnt);
seq_printf(s, " - compress: %4d, hit:%8d\n", si->compress_pages, si->compress_page_hit);
seq_printf(s, " - nodes: %4d in %4d\n",
si->ndirty_node, si->node_pages);
@@ -623,9 +611,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
for (i = META_CP; i < META_MAX; i++)
atomic_set(&sbi->meta_count[i], 0);
- atomic_set(&sbi->vw_cnt, 0);
atomic_set(&sbi->max_aw_cnt, 0);
- atomic_set(&sbi->max_vw_cnt, 0);
raw_spin_lock_irqsave(&f2fs_stat_lock, flags);
list_add_tail(&si->stat_list, &f2fs_stat_list);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index a0e51937d92e..d5bd7932fb64 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -82,7 +82,8 @@ int f2fs_init_casefolded_name(const struct inode *dir,
#if IS_ENABLED(CONFIG_UNICODE)
struct super_block *sb = dir->i_sb;
- if (IS_CASEFOLDED(dir)) {
+ if (IS_CASEFOLDED(dir) &&
+ !is_dot_dotdot(fname->usr_fname->name, fname->usr_fname->len)) {
fname->cf_name.name = f2fs_kmem_cache_alloc(f2fs_cf_name_slab,
GFP_NOFS, false, F2FS_SB(sb));
if (!fname->cf_name.name)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 10d1f138d14f..d9bbecd008d2 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -509,11 +509,11 @@ struct f2fs_filename {
#if IS_ENABLED(CONFIG_UNICODE)
/*
* For casefolded directories: the casefolded name, but it's left NULL
- * if the original name is not valid Unicode, if the directory is both
- * casefolded and encrypted and its encryption key is unavailable, or if
- * the filesystem is doing an internal operation where usr_fname is also
- * NULL. In all these cases we fall back to treating the name as an
- * opaque byte sequence.
+ * if the original name is not valid Unicode, if the original name is
+ * "." or "..", if the directory is both casefolded and encrypted and
+ * its encryption key is unavailable, or if the filesystem is doing an
+ * internal operation where usr_fname is also NULL. In all these cases
+ * we fall back to treating the name as an opaque byte sequence.
*/
struct fscrypt_str cf_name;
#endif
@@ -579,8 +579,8 @@ enum {
/* maximum retry quota flush count */
#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT 8
-/* maximum retry of EIO'ed meta page */
-#define MAX_RETRY_META_PAGE_EIO 100
+/* maximum retry of EIO'ed page */
+#define MAX_RETRY_PAGE_EIO 100
#define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */
@@ -717,7 +717,6 @@ enum {
enum {
GC_FAILURE_PIN,
- GC_FAILURE_ATOMIC,
MAX_GC_FAILURE
};
@@ -739,8 +738,6 @@ enum {
FI_UPDATE_WRITE, /* inode has in-place-update data */
FI_NEED_IPU, /* used for ipu per file */
FI_ATOMIC_FILE, /* indicate atomic file */
- FI_ATOMIC_COMMIT, /* indicate the state of atomical committing */
- FI_VOLATILE_FILE, /* indicate volatile file */
FI_FIRST_BLOCK_WRITTEN, /* indicate #0 data block was written */
FI_DROP_CACHE, /* drop dirty page cache */
FI_DATA_EXIST, /* indicate data exists */
@@ -753,7 +750,6 @@ 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 */
FI_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */
FI_COMPRESSED_FILE, /* indicate file's data can be compressed */
FI_COMPRESS_CORRUPT, /* indicate compressed cluster is corrupted */
@@ -795,11 +791,9 @@ struct f2fs_inode_info {
#endif
struct list_head dirty_list; /* dirty list for dirs and files */
struct list_head gdirty_list; /* linked in global dirty list */
- struct list_head inmem_ilist; /* list for inmem inodes */
- struct list_head inmem_pages; /* inmemory pages managed by f2fs */
- struct task_struct *inmem_task; /* store inmemory task */
- struct mutex inmem_lock; /* lock for inmemory pages */
+ struct task_struct *atomic_write_task; /* store atomic write task */
struct extent_tree *extent_tree; /* cached extent_tree entry */
+ struct inode *cow_inode; /* copy-on-write inode for atomic write */
/* avoid racing between foreground op and gc */
struct f2fs_rwsem i_gc_rwsem[2];
@@ -1093,7 +1087,6 @@ enum count_type {
F2FS_DIRTY_QDATA,
F2FS_DIRTY_NODES,
F2FS_DIRTY_META,
- F2FS_INMEM_PAGES,
F2FS_DIRTY_IMETA,
F2FS_WB_CP_DATA,
F2FS_WB_DATA,
@@ -1118,16 +1111,12 @@ enum count_type {
*/
#define PAGE_TYPE_OF_BIO(type) ((type) > META ? META : (type))
enum page_type {
- DATA,
- NODE,
+ DATA = 0,
+ NODE = 1, /* should not change this */
META,
NR_PAGE_TYPE,
META_FLUSH,
- INMEM, /* the below types are used by tracepoints only. */
- INMEM_DROP,
- INMEM_INVALIDATE,
- INMEM_REVOKE,
- IPU,
+ IPU, /* the below types are used by tracepoints only. */
OPU,
};
@@ -1277,6 +1266,15 @@ struct atgc_management {
unsigned long long age_threshold; /* age threshold */
};
+struct f2fs_gc_control {
+ unsigned int victim_segno; /* target victim segment number */
+ int init_gc_type; /* FG_GC or BG_GC */
+ bool no_bg_gc; /* check the space and stop bg_gc */
+ bool should_migrate_blocks; /* should migrate blocks */
+ bool err_gc_skipped; /* return EAGAIN if GC skipped */
+ unsigned int nr_free_secs; /* # of free sections to do GC */
+};
+
/* For s_flag in struct f2fs_sb_info */
enum {
SBI_IS_DIRTY, /* dirty flag for checkpoint */
@@ -1615,8 +1613,8 @@ struct f2fs_sb_info {
/* keep migration IO order for LFS mode */
struct f2fs_rwsem io_order_lock;
mempool_t *write_io_dummy; /* Dummy pages */
- pgoff_t metapage_eio_ofs; /* EIO page offset */
- int metapage_eio_cnt; /* EIO count */
+ pgoff_t page_eio_ofs[NR_PAGE_TYPE]; /* EIO page offset */
+ int page_eio_cnt[NR_PAGE_TYPE]; /* EIO count */
/* for checkpoint */
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
@@ -1719,7 +1717,6 @@ struct f2fs_sb_info {
/* for skip statistic */
unsigned int atomic_files; /* # of opened atomic file */
- unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */
unsigned long long skipped_gc_rwsem; /* FG_GC only */
/* threshold for gc trials on pinned files */
@@ -1750,9 +1747,7 @@ struct f2fs_sb_info {
atomic_t inline_dir; /* # of inline_dentry inodes */
atomic_t compr_inode; /* # of compressed inodes */
atomic64_t compr_blocks; /* # of compressed blocks */
- atomic_t vw_cnt; /* # of volatile writes */
atomic_t max_aw_cnt; /* max # of atomic writes */
- atomic_t max_vw_cnt; /* max # of volatile writes */
unsigned int io_skip_bggc; /* skip background gc for in-flight IO */
unsigned int other_skip_bggc; /* skip background gc for other reasons */
unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */
@@ -1763,7 +1758,7 @@ struct f2fs_sb_info {
unsigned int data_io_flag;
unsigned int node_io_flag;
- /* For sysfs suppport */
+ /* For sysfs support */
struct kobject s_kobj; /* /sys/fs/f2fs/<devname> */
struct completion s_kobj_unregister;
@@ -2606,11 +2601,17 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
{
spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi, !sbi->total_valid_block_count);
- f2fs_bug_on(sbi, !sbi->total_valid_node_count);
+ if (unlikely(!sbi->total_valid_block_count ||
+ !sbi->total_valid_node_count)) {
+ f2fs_warn(sbi, "dec_valid_node_count: inconsistent block counts, total_valid_block:%u, total_valid_node:%u",
+ sbi->total_valid_block_count,
+ sbi->total_valid_node_count);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ } else {
+ sbi->total_valid_block_count--;
+ sbi->total_valid_node_count--;
+ }
- sbi->total_valid_node_count--;
- sbi->total_valid_block_count--;
if (sbi->reserved_blocks &&
sbi->current_reserved_blocks < sbi->reserved_blocks)
sbi->current_reserved_blocks++;
@@ -3173,6 +3174,10 @@ static inline int inline_xattr_size(struct inode *inode)
return 0;
}
+/*
+ * Notice: check inline_data flag without inode page lock is unsafe.
+ * It could change at any time by f2fs_convert_inline_page().
+ */
static inline int f2fs_has_inline_data(struct inode *inode)
{
return is_inode_flag_set(inode, FI_INLINE_DATA);
@@ -3203,16 +3208,6 @@ static inline bool f2fs_is_atomic_file(struct inode *inode)
return is_inode_flag_set(inode, FI_ATOMIC_FILE);
}
-static inline bool f2fs_is_commit_atomic_write(struct inode *inode)
-{
- return is_inode_flag_set(inode, FI_ATOMIC_COMMIT);
-}
-
-static inline bool f2fs_is_volatile_file(struct inode *inode)
-{
- return is_inode_flag_set(inode, FI_VOLATILE_FILE);
-}
-
static inline bool f2fs_is_first_block_written(struct inode *inode)
{
return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN);
@@ -3445,6 +3440,8 @@ void f2fs_handle_failed_inode(struct inode *inode);
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);
+int f2fs_get_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct inode **new_inode);
/*
* dir.c
@@ -3580,11 +3577,8 @@ void f2fs_destroy_node_manager_caches(void);
* segment.c
*/
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);
+int f2fs_commit_atomic_write(struct inode *inode);
+void f2fs_abort_atomic_write(struct inode *inode, bool clean);
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg);
int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
@@ -3726,6 +3720,7 @@ int f2fs_init_bio_entry_cache(void);
void f2fs_destroy_bio_entry_cache(void);
void f2fs_submit_bio(struct f2fs_sb_info *sbi,
struct bio *bio, enum page_type type);
+int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi);
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, struct page *page,
@@ -3787,8 +3782,7 @@ extern const struct iomap_ops f2fs_iomap_ops;
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, bool force,
- unsigned int segno);
+int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control);
void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count);
int __init f2fs_create_garbage_collection_cache(void);
@@ -3816,7 +3810,6 @@ struct f2fs_stat_info {
int ext_tree, zombie_tree, ext_node;
int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
int ndirty_data, ndirty_qdata;
- int inmem_pages;
unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
int nats, dirty_nats, sits, dirty_sits;
int free_nids, avail_nids, alloc_nids;
@@ -3834,7 +3827,7 @@ struct f2fs_stat_info {
int inline_xattr, inline_inode, inline_dir, append, update, orphans;
int compr_inode;
unsigned long long compr_blocks;
- int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
+ int aw_cnt, max_aw_cnt;
unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
unsigned int bimodal, avg_vblocks;
int util_free, util_valid, util_invalid;
@@ -3846,7 +3839,6 @@ 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];
@@ -3946,17 +3938,6 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
if (cur > max) \
atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur); \
} while (0)
-#define stat_inc_volatile_write(inode) \
- (atomic_inc(&F2FS_I_SB(inode)->vw_cnt))
-#define stat_dec_volatile_write(inode) \
- (atomic_dec(&F2FS_I_SB(inode)->vw_cnt))
-#define stat_update_max_volatile_write(inode) \
- do { \
- int cur = atomic_read(&F2FS_I_SB(inode)->vw_cnt); \
- int max = atomic_read(&F2FS_I_SB(inode)->max_vw_cnt); \
- if (cur > max) \
- atomic_set(&F2FS_I_SB(inode)->max_vw_cnt, cur); \
- } while (0)
#define stat_inc_seg_count(sbi, type, gc_type) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
@@ -4018,9 +3999,6 @@ void f2fs_update_sit_info(struct f2fs_sb_info *sbi);
#define stat_add_compr_blocks(inode, blocks) do { } while (0)
#define stat_sub_compr_blocks(inode, blocks) do { } while (0)
#define stat_update_max_atomic_write(inode) do { } while (0)
-#define stat_inc_volatile_write(inode) do { } while (0)
-#define stat_dec_volatile_write(inode) do { } while (0)
-#define stat_update_max_volatile_write(inode) do { } while (0)
#define stat_inc_meta_count(sbi, blkaddr) do { } while (0)
#define stat_inc_seg_type(sbi, curseg) do { } while (0)
#define stat_inc_block_count(sbi, curseg) do { } while (0)
@@ -4053,6 +4031,7 @@ extern struct kmem_cache *f2fs_inode_entry_slab;
* inline.c
*/
bool f2fs_may_inline_data(struct inode *inode);
+bool f2fs_sanity_check_inline_data(struct inode *inode);
bool f2fs_may_inline_dentry(struct inode *inode);
void f2fs_do_read_inline_data(struct page *page, struct page *ipage);
void f2fs_truncate_inline_inode(struct inode *inode,
@@ -4422,8 +4401,7 @@ static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi)
static inline bool f2fs_may_compress(struct inode *inode)
{
if (IS_SWAPFILE(inode) || f2fs_is_pinned_file(inode) ||
- f2fs_is_atomic_file(inode) ||
- f2fs_is_volatile_file(inode))
+ f2fs_is_atomic_file(inode))
return false;
return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode);
}
@@ -4431,8 +4409,8 @@ static inline bool f2fs_may_compress(struct inode *inode)
static inline void f2fs_i_compr_blocks_update(struct inode *inode,
u64 blocks, bool add)
{
- int diff = F2FS_I(inode)->i_cluster_size - blocks;
struct f2fs_inode_info *fi = F2FS_I(inode);
+ int diff = fi->i_cluster_size - blocks;
/* don't update i_compr_blocks if saved blocks were released */
if (!add && !atomic_read(&fi->i_compr_blocks))
@@ -4540,6 +4518,21 @@ static inline void f2fs_io_schedule_timeout(long timeout)
io_schedule_timeout(timeout);
}
+static inline void f2fs_handle_page_eio(struct f2fs_sb_info *sbi, pgoff_t ofs,
+ enum page_type type)
+{
+ if (unlikely(f2fs_cp_error(sbi)))
+ return;
+
+ if (ofs == sbi->page_eio_ofs[type]) {
+ if (sbi->page_eio_cnt[type]++ == MAX_RETRY_PAGE_EIO)
+ set_ckpt_flags(sbi, CP_ERROR_FLAG);
+ } else {
+ sbi->page_eio_ofs[type] = ofs;
+ sbi->page_eio_cnt[type] = 0;
+ }
+}
+
#define EFSBADCRC EBADMSG /* Bad CRC detected */
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 100637b1adb3..bd14cef1b08f 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -372,7 +372,8 @@ sync_nodes:
f2fs_remove_ino_entry(sbi, ino, APPEND_INO);
clear_inode_flag(inode, FI_APPEND_WRITE);
flush_out:
- if (!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER)
+ if ((!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER) ||
+ (atomic && !test_opt(sbi, NOBARRIER) && f2fs_sb_has_blkzoned(sbi)))
ret = f2fs_issue_flush(sbi, inode->i_ino);
if (!ret) {
f2fs_remove_ino_entry(sbi, ino, UPDATE_INO);
@@ -1437,11 +1438,19 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
ret = -ENOSPC;
break;
}
- if (dn->data_blkaddr != NEW_ADDR) {
- f2fs_invalidate_blocks(sbi, dn->data_blkaddr);
- dn->data_blkaddr = NEW_ADDR;
- f2fs_set_data_blkaddr(dn);
+
+ if (dn->data_blkaddr == NEW_ADDR)
+ continue;
+
+ if (!f2fs_is_valid_blkaddr(sbi, dn->data_blkaddr,
+ DATA_GENERIC_ENHANCE)) {
+ ret = -EFSCORRUPTED;
+ break;
}
+
+ f2fs_invalidate_blocks(sbi, dn->data_blkaddr);
+ dn->data_blkaddr = NEW_ADDR;
+ f2fs_set_data_blkaddr(dn);
}
f2fs_update_extent_cache_range(dn, start, 0, index - start);
@@ -1638,6 +1647,11 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
struct f2fs_map_blocks map = { .m_next_pgofs = NULL,
.m_next_extent = NULL, .m_seg_type = NO_CHECK_TYPE,
.m_may_create = true };
+ struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO,
+ .init_gc_type = FG_GC,
+ .should_migrate_blocks = false,
+ .err_gc_skipped = true,
+ .nr_free_secs = 0 };
pgoff_t pg_start, pg_end;
loff_t new_size = i_size_read(inode);
loff_t off_end;
@@ -1675,8 +1689,8 @@ next_alloc:
if (has_not_enough_free_secs(sbi, 0,
GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
f2fs_down_write(&sbi->gc_lock);
- err = f2fs_gc(sbi, true, false, false, NULL_SEGNO);
- if (err && err != -ENODATA && err != -EAGAIN)
+ err = f2fs_gc(sbi, &gc_control);
+ if (err && err != -ENODATA)
goto out_err;
}
@@ -1766,6 +1780,10 @@ static long f2fs_fallocate(struct file *file, int mode,
inode_lock(inode);
+ ret = file_modified(file);
+ if (ret)
+ goto out;
+
if (mode & FALLOC_FL_PUNCH_HOLE) {
if (offset >= inode->i_size)
goto out;
@@ -1804,16 +1822,8 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
atomic_read(&inode->i_writecount) != 1)
return 0;
- /* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
- f2fs_drop_inmem_pages(inode);
- if (f2fs_is_volatile_file(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);
- }
+ f2fs_abort_atomic_write(inode, true);
return 0;
}
@@ -1828,8 +1838,8 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id)
* before dropping file lock, it needs to do in ->flush.
*/
if (f2fs_is_atomic_file(inode) &&
- F2FS_I(inode)->inmem_task == current)
- f2fs_drop_inmem_pages(inode);
+ F2FS_I(inode)->atomic_write_task == current)
+ f2fs_abort_atomic_write(inode, true);
return 0;
}
@@ -1992,6 +2002,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
struct user_namespace *mnt_userns = file_mnt_user_ns(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct inode *pinode;
int ret;
if (!inode_owner_or_capable(mnt_userns, inode))
@@ -2014,44 +2025,55 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
goto out;
}
- if (f2fs_is_atomic_file(inode)) {
- if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST))
- ret = -EINVAL;
+ if (f2fs_is_atomic_file(inode))
goto out;
- }
ret = f2fs_convert_inline_inode(inode);
if (ret)
goto out;
- f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
/*
* Should wait end_io to count F2FS_WB_CP_DATA correctly by
* f2fs_is_atomic_file.
*/
if (get_dirty_pages(inode))
- f2fs_warn(F2FS_I_SB(inode), "Unexpected flush for atomic writes: ino=%lu, npages=%u",
+ f2fs_warn(sbi, "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) {
- f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
+ goto out;
+ }
+
+ /* Create a COW inode for atomic write */
+ pinode = f2fs_iget(inode->i_sb, fi->i_pino);
+ if (IS_ERR(pinode)) {
+ f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
+ ret = PTR_ERR(pinode);
+ goto out;
+ }
+
+ ret = f2fs_get_tmpfile(mnt_userns, pinode, &fi->cow_inode);
+ iput(pinode);
+ if (ret) {
+ f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
goto out;
}
+ f2fs_i_size_write(fi->cow_inode, i_size_read(inode));
spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
- if (list_empty(&fi->inmem_ilist))
- list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]);
sbi->atomic_files++;
spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
- /* add inode in inmem_list first and set atomic_file */
set_inode_flag(inode, FI_ATOMIC_FILE);
- clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
- f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ set_inode_flag(fi->cow_inode, FI_ATOMIC_FILE);
+ clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
+ f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
- f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- F2FS_I(inode)->inmem_task = current;
+ f2fs_update_time(sbi, REQ_TIME);
+ fi->atomic_write_task = current;
stat_update_max_atomic_write(inode);
out:
inode_unlock(inode);
@@ -2076,127 +2098,20 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
inode_lock(inode);
- if (f2fs_is_volatile_file(inode)) {
- ret = -EINVAL;
- goto err_out;
- }
-
if (f2fs_is_atomic_file(inode)) {
- ret = f2fs_commit_inmem_pages(inode);
+ ret = f2fs_commit_atomic_write(inode);
if (ret)
- goto err_out;
+ goto unlock_out;
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
if (!ret)
- f2fs_drop_inmem_pages(inode);
+ f2fs_abort_atomic_write(inode, false);
} else {
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false);
}
-err_out:
- if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) {
- clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
- ret = -EINVAL;
- }
- inode_unlock(inode);
- mnt_drop_write_file(filp);
- return ret;
-}
-
-static int f2fs_ioc_start_volatile_write(struct file *filp)
-{
- struct inode *inode = file_inode(filp);
- struct user_namespace *mnt_userns = file_mnt_user_ns(filp);
- int ret;
-
- if (!inode_owner_or_capable(mnt_userns, inode))
- return -EACCES;
-
- if (!S_ISREG(inode->i_mode))
- return -EINVAL;
-
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
-
- inode_lock(inode);
-
- if (f2fs_is_volatile_file(inode))
- goto out;
-
- ret = f2fs_convert_inline_inode(inode);
- if (ret)
- goto out;
-
- stat_inc_volatile_write(inode);
- stat_update_max_volatile_write(inode);
-
- set_inode_flag(inode, FI_VOLATILE_FILE);
- f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
-out:
- inode_unlock(inode);
- mnt_drop_write_file(filp);
- return ret;
-}
-
-static int f2fs_ioc_release_volatile_write(struct file *filp)
-{
- struct inode *inode = file_inode(filp);
- struct user_namespace *mnt_userns = file_mnt_user_ns(filp);
- int ret;
-
- if (!inode_owner_or_capable(mnt_userns, inode))
- return -EACCES;
-
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
-
- inode_lock(inode);
-
- if (!f2fs_is_volatile_file(inode))
- goto out;
-
- if (!f2fs_is_first_block_written(inode)) {
- ret = truncate_partial_data_page(inode, 0, true);
- goto out;
- }
-
- ret = punch_hole(inode, 0, F2FS_BLKSIZE);
-out:
- inode_unlock(inode);
- mnt_drop_write_file(filp);
- return ret;
-}
-
-static int f2fs_ioc_abort_volatile_write(struct file *filp)
-{
- struct inode *inode = file_inode(filp);
- struct user_namespace *mnt_userns = file_mnt_user_ns(filp);
- int ret;
-
- if (!inode_owner_or_capable(mnt_userns, inode))
- return -EACCES;
-
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
-
- inode_lock(inode);
-
- if (f2fs_is_atomic_file(inode))
- f2fs_drop_inmem_pages(inode);
- if (f2fs_is_volatile_file(inode)) {
- clear_inode_flag(inode, FI_VOLATILE_FILE);
- stat_dec_volatile_write(inode);
- ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
- }
-
- clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
-
+unlock_out:
inode_unlock(inode);
-
mnt_drop_write_file(filp);
- f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return ret;
}
@@ -2437,6 +2352,10 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO,
+ .no_bg_gc = false,
+ .should_migrate_blocks = false,
+ .nr_free_secs = 0 };
__u32 sync;
int ret;
@@ -2462,7 +2381,9 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
f2fs_down_write(&sbi->gc_lock);
}
- ret = f2fs_gc(sbi, sync, true, false, NULL_SEGNO);
+ gc_control.init_gc_type = sync ? FG_GC : BG_GC;
+ gc_control.err_gc_skipped = sync;
+ ret = f2fs_gc(sbi, &gc_control);
out:
mnt_drop_write_file(filp);
return ret;
@@ -2471,6 +2392,12 @@ out:
static int __f2fs_ioc_gc_range(struct file *filp, struct f2fs_gc_range *range)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp));
+ struct f2fs_gc_control gc_control = {
+ .init_gc_type = range->sync ? FG_GC : BG_GC,
+ .no_bg_gc = false,
+ .should_migrate_blocks = false,
+ .err_gc_skipped = range->sync,
+ .nr_free_secs = 0 };
u64 end;
int ret;
@@ -2498,8 +2425,8 @@ do_more:
f2fs_down_write(&sbi->gc_lock);
}
- ret = f2fs_gc(sbi, range->sync, true, false,
- GET_SEGNO(sbi, range->start));
+ gc_control.victim_segno = GET_SEGNO(sbi, range->start);
+ ret = f2fs_gc(sbi, &gc_control);
if (ret) {
if (ret == -EBUSY)
ret = -EAGAIN;
@@ -2674,6 +2601,7 @@ do_map:
}
set_page_dirty(page);
+ set_page_private_gcing(page);
f2fs_put_page(page, 1);
idx++;
@@ -2913,6 +2841,11 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
unsigned int start_segno = 0, end_segno = 0;
unsigned int dev_start_segno = 0, dev_end_segno = 0;
struct f2fs_flush_device range;
+ struct f2fs_gc_control gc_control = {
+ .init_gc_type = FG_GC,
+ .should_migrate_blocks = true,
+ .err_gc_skipped = true,
+ .nr_free_secs = 0 };
int ret;
if (!capable(CAP_SYS_ADMIN))
@@ -2956,7 +2889,9 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
sm->last_victim[GC_CB] = end_segno + 1;
sm->last_victim[GC_GREEDY] = end_segno + 1;
sm->last_victim[ALLOC_NEXT] = end_segno + 1;
- ret = f2fs_gc(sbi, true, true, true, start_segno);
+
+ gc_control.victim_segno = start_segno;
+ ret = f2fs_gc(sbi, &gc_control);
if (ret == -EAGAIN)
ret = 0;
else if (ret < 0)
@@ -3017,7 +2952,7 @@ static int f2fs_ioc_setproject(struct inode *inode, __u32 projid)
kprojid = make_kprojid(&init_user_ns, (projid_t)projid);
- if (projid_eq(kprojid, F2FS_I(inode)->i_projid))
+ if (projid_eq(kprojid, fi->i_projid))
return 0;
err = -EPERM;
@@ -3037,7 +2972,7 @@ static int f2fs_ioc_setproject(struct inode *inode, __u32 projid)
if (err)
goto out_unlock;
- F2FS_I(inode)->i_projid = kprojid;
+ fi->i_projid = kprojid;
inode->i_ctime = current_time(inode);
f2fs_mark_inode_dirty_sync(inode, true);
out_unlock:
@@ -3987,7 +3922,7 @@ static int f2fs_ioc_decompress_file(struct file *filp, unsigned long arg)
struct f2fs_inode_info *fi = F2FS_I(inode);
pgoff_t page_idx = 0, last_idx;
unsigned int blk_per_seg = sbi->blocks_per_seg;
- int cluster_size = F2FS_I(inode)->i_cluster_size;
+ int cluster_size = fi->i_cluster_size;
int count, ret;
if (!f2fs_sb_has_compression(sbi) ||
@@ -4010,11 +3945,6 @@ static int f2fs_ioc_decompress_file(struct file *filp, unsigned long arg)
goto out;
}
- if (f2fs_is_mmap_file(inode)) {
- ret = -EBUSY;
- goto out;
- }
-
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
if (ret)
goto out;
@@ -4082,11 +4012,6 @@ static int f2fs_ioc_compress_file(struct file *filp, unsigned long arg)
goto out;
}
- if (f2fs_is_mmap_file(inode)) {
- ret = -EBUSY;
- goto out;
- }
-
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
if (ret)
goto out;
@@ -4136,11 +4061,9 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
case F2FS_IOC_COMMIT_ATOMIC_WRITE:
return f2fs_ioc_commit_atomic_write(filp);
case F2FS_IOC_START_VOLATILE_WRITE:
- return f2fs_ioc_start_volatile_write(filp);
case F2FS_IOC_RELEASE_VOLATILE_WRITE:
- return f2fs_ioc_release_volatile_write(filp);
case F2FS_IOC_ABORT_VOLATILE_WRITE:
- return f2fs_ioc_abort_volatile_write(filp);
+ return -EOPNOTSUPP;
case F2FS_IOC_SHUTDOWN:
return f2fs_ioc_shutdown(filp, arg);
case FITRIM:
@@ -4328,17 +4251,39 @@ out:
static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct inode *inode = file_inode(iocb->ki_filp);
+ const loff_t pos = iocb->ki_pos;
ssize_t ret;
if (!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
- if (f2fs_should_use_dio(inode, iocb, to))
- return f2fs_dio_read_iter(iocb, to);
+ if (trace_f2fs_dataread_start_enabled()) {
+ char *p = f2fs_kmalloc(F2FS_I_SB(inode), PATH_MAX, GFP_KERNEL);
+ char *path;
+
+ if (!p)
+ goto skip_read_trace;
+
+ path = dentry_path_raw(file_dentry(iocb->ki_filp), p, PATH_MAX);
+ if (IS_ERR(path)) {
+ kfree(p);
+ goto skip_read_trace;
+ }
- ret = filemap_read(iocb, to, 0);
- if (ret > 0)
- f2fs_update_iostat(F2FS_I_SB(inode), APP_BUFFERED_READ_IO, ret);
+ trace_f2fs_dataread_start(inode, pos, iov_iter_count(to),
+ current->pid, path, current->comm);
+ kfree(p);
+ }
+skip_read_trace:
+ if (f2fs_should_use_dio(inode, iocb, to)) {
+ ret = f2fs_dio_read_iter(iocb, to);
+ } else {
+ ret = filemap_read(iocb, to, 0);
+ if (ret > 0)
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_BUFFERED_READ_IO, ret);
+ }
+ if (trace_f2fs_dataread_end_enabled())
+ trace_f2fs_dataread_end(inode, pos, ret);
return ret;
}
@@ -4630,14 +4575,36 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
/* Possibly preallocate the blocks for the write. */
target_size = iocb->ki_pos + iov_iter_count(from);
preallocated = f2fs_preallocate_blocks(iocb, from, dio);
- if (preallocated < 0)
+ if (preallocated < 0) {
ret = preallocated;
- else
+ } else {
+ if (trace_f2fs_datawrite_start_enabled()) {
+ char *p = f2fs_kmalloc(F2FS_I_SB(inode),
+ PATH_MAX, GFP_KERNEL);
+ char *path;
+
+ if (!p)
+ goto skip_write_trace;
+ path = dentry_path_raw(file_dentry(iocb->ki_filp),
+ p, PATH_MAX);
+ if (IS_ERR(path)) {
+ kfree(p);
+ goto skip_write_trace;
+ }
+ trace_f2fs_datawrite_start(inode, orig_pos, orig_count,
+ current->pid, path, current->comm);
+ kfree(p);
+ }
+skip_write_trace:
/* Do the actual write. */
ret = dio ?
f2fs_dio_write_iter(iocb, from, &may_need_sync):
f2fs_buffered_write_iter(iocb, from);
+ if (trace_f2fs_datawrite_end_enabled())
+ trace_f2fs_datawrite_end(inode, orig_pos, ret);
+ }
+
/* Don't leave any preallocated blocks around past i_size. */
if (preallocated && i_size_read(inode) < target_size) {
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index ea5b93b689cd..d5fb426e0747 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -35,6 +35,10 @@ static int gc_thread_func(void *data)
wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head;
wait_queue_head_t *fggc_wq = &sbi->gc_thread->fggc_wq;
unsigned int wait_ms;
+ struct f2fs_gc_control gc_control = {
+ .victim_segno = NULL_SEGNO,
+ .should_migrate_blocks = false,
+ .err_gc_skipped = false };
wait_ms = gc_th->min_sleep_time;
@@ -141,8 +145,12 @@ do_gc:
if (foreground)
sync_mode = false;
+ gc_control.init_gc_type = sync_mode ? FG_GC : BG_GC;
+ gc_control.no_bg_gc = foreground;
+ gc_control.nr_free_secs = foreground ? 1 : 0;
+
/* if return value is not zero, no victim was selected */
- if (f2fs_gc(sbi, sync_mode, !foreground, false, NULL_SEGNO))
+ if (f2fs_gc(sbi, &gc_control))
wait_ms = gc_th->no_gc_sleep_time;
if (foreground)
@@ -646,6 +654,54 @@ static void release_victim_entry(struct f2fs_sb_info *sbi)
f2fs_bug_on(sbi, !list_empty(&am->victim_list));
}
+static bool f2fs_pin_section(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+ struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+
+ if (!dirty_i->enable_pin_section)
+ return false;
+ if (!test_and_set_bit(secno, dirty_i->pinned_secmap))
+ dirty_i->pinned_secmap_cnt++;
+ return true;
+}
+
+static bool f2fs_pinned_section_exists(struct dirty_seglist_info *dirty_i)
+{
+ return dirty_i->pinned_secmap_cnt;
+}
+
+static bool f2fs_section_is_pinned(struct dirty_seglist_info *dirty_i,
+ unsigned int secno)
+{
+ return dirty_i->enable_pin_section &&
+ f2fs_pinned_section_exists(dirty_i) &&
+ test_bit(secno, dirty_i->pinned_secmap);
+}
+
+static void f2fs_unpin_all_sections(struct f2fs_sb_info *sbi, bool enable)
+{
+ unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
+
+ if (f2fs_pinned_section_exists(DIRTY_I(sbi))) {
+ memset(DIRTY_I(sbi)->pinned_secmap, 0, bitmap_size);
+ DIRTY_I(sbi)->pinned_secmap_cnt = 0;
+ }
+ DIRTY_I(sbi)->enable_pin_section = enable;
+}
+
+static int f2fs_gc_pinned_control(struct inode *inode, int gc_type,
+ unsigned int segno)
+{
+ if (!f2fs_is_pinned_file(inode))
+ return 0;
+ if (gc_type != FG_GC)
+ return -EBUSY;
+ if (!f2fs_pin_section(F2FS_I_SB(inode), segno))
+ f2fs_pin_file_control(inode, true);
+ return -EAGAIN;
+}
+
/*
* This function is called from two paths.
* One is garbage collection and the other is SSR segment selection.
@@ -787,6 +843,9 @@ retry:
if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
goto next;
+ if (gc_type == FG_GC && f2fs_section_is_pinned(dirty_i, secno))
+ goto next;
+
if (is_atgc) {
add_victim_entry(sbi, &p, segno);
goto next;
@@ -1194,18 +1253,9 @@ static int move_data_block(struct inode *inode, block_t bidx,
goto out;
}
- if (f2fs_is_atomic_file(inode)) {
- F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++;
- F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++;
- err = -EAGAIN;
- goto out;
- }
-
- if (f2fs_is_pinned_file(inode)) {
- f2fs_pin_file_control(inode, true);
- err = -EAGAIN;
+ err = f2fs_gc_pinned_control(inode, gc_type, segno);
+ if (err)
goto out;
- }
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
@@ -1344,18 +1394,9 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
goto out;
}
- if (f2fs_is_atomic_file(inode)) {
- F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++;
- F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++;
- err = -EAGAIN;
- goto out;
- }
- if (f2fs_is_pinned_file(inode)) {
- if (gc_type == FG_GC)
- f2fs_pin_file_control(inode, true);
- err = -EAGAIN;
+ err = f2fs_gc_pinned_control(inode, gc_type, segno);
+ if (err)
goto out;
- }
if (gc_type == BG_GC) {
if (PageWriteback(page)) {
@@ -1475,11 +1516,19 @@ next_step:
ofs_in_node = le16_to_cpu(entry->ofs_in_node);
if (phase == 3) {
+ int err;
+
inode = f2fs_iget(sb, dni.ino);
if (IS_ERR(inode) || is_bad_inode(inode) ||
special_file(inode->i_mode))
continue;
+ err = f2fs_gc_pinned_control(inode, gc_type, segno);
+ if (err == -EAGAIN) {
+ iput(inode);
+ return submitted;
+ }
+
if (!f2fs_down_write_trylock(
&F2FS_I(inode)->i_gc_rwsem[WRITE])) {
iput(inode);
@@ -1699,23 +1748,21 @@ skip:
return seg_freed;
}
-int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
- bool background, bool force, unsigned int segno)
+int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control)
{
- int gc_type = sync ? FG_GC : BG_GC;
+ int gc_type = gc_control->init_gc_type;
+ unsigned int segno = gc_control->victim_segno;
int sec_freed = 0, seg_freed = 0, total_freed = 0;
int ret = 0;
struct cp_control cpc;
- unsigned int init_segno = segno;
struct gc_inode_list gc_list = {
.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 long long first_skipped;
unsigned int skipped_round = 0, round = 0;
- trace_f2fs_gc_begin(sbi->sb, sync, background,
+ trace_f2fs_gc_begin(sbi->sb, gc_type, gc_control->no_bg_gc,
+ gc_control->nr_free_secs,
get_pages(sbi, F2FS_DIRTY_NODES),
get_pages(sbi, F2FS_DIRTY_DENTS),
get_pages(sbi, F2FS_DIRTY_IMETA),
@@ -1726,7 +1773,6 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
cpc.reason = __get_cp_reason(sbi);
sbi->skipped_gc_rwsem = 0;
- first_skipped = last_skipped;
gc_more:
if (unlikely(!(sbi->sb->s_flags & SB_ACTIVE))) {
ret = -EINVAL;
@@ -1743,8 +1789,7 @@ gc_more:
* threshold, we can make them free by checkpoint. Then, we
* secure free segments which doesn't need fggc any more.
*/
- if (prefree_segments(sbi) &&
- !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
+ if (prefree_segments(sbi)) {
ret = f2fs_write_checkpoint(sbi, &cpc);
if (ret)
goto stop;
@@ -1754,54 +1799,69 @@ gc_more:
}
/* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
- if (gc_type == BG_GC && !background) {
+ if (gc_type == BG_GC && gc_control->no_bg_gc) {
ret = -EINVAL;
goto stop;
}
+retry:
ret = __get_victim(sbi, &segno, gc_type);
- if (ret)
+ if (ret) {
+ /* allow to search victim from sections has pinned data */
+ if (ret == -ENODATA && gc_type == FG_GC &&
+ f2fs_pinned_section_exists(DIRTY_I(sbi))) {
+ f2fs_unpin_all_sections(sbi, false);
+ goto retry;
+ }
goto stop;
+ }
- seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type, force);
- if (gc_type == FG_GC &&
- seg_freed == f2fs_usable_segs_in_sec(sbi, segno))
- sec_freed++;
+ seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type,
+ gc_control->should_migrate_blocks);
total_freed += seg_freed;
- if (gc_type == FG_GC) {
- if (sbi->skipped_atomic_files[FG_GC] > last_skipped ||
- sbi->skipped_gc_rwsem)
- skipped_round++;
- last_skipped = sbi->skipped_atomic_files[FG_GC];
- round++;
- }
+ if (seg_freed == f2fs_usable_segs_in_sec(sbi, segno))
+ sec_freed++;
if (gc_type == FG_GC)
sbi->cur_victim_sec = NULL_SEGNO;
- if (sync)
+ if (gc_control->init_gc_type == FG_GC ||
+ !has_not_enough_free_secs(sbi,
+ (gc_type == FG_GC) ? sec_freed : 0, 0)) {
+ if (gc_type == FG_GC && sec_freed < gc_control->nr_free_secs)
+ goto go_gc_more;
goto stop;
+ }
- if (has_not_enough_free_secs(sbi, sec_freed, 0)) {
- if (skipped_round <= MAX_SKIP_GC_COUNT ||
- skipped_round * 2 < round) {
- segno = NULL_SEGNO;
- goto gc_more;
+ /* FG_GC stops GC by skip_count */
+ if (gc_type == FG_GC) {
+ if (sbi->skipped_gc_rwsem)
+ skipped_round++;
+ round++;
+ if (skipped_round > MAX_SKIP_GC_COUNT &&
+ skipped_round * 2 >= round) {
+ ret = f2fs_write_checkpoint(sbi, &cpc);
+ goto stop;
}
+ }
- if (first_skipped < last_skipped &&
- (last_skipped - first_skipped) >
- sbi->skipped_gc_rwsem) {
- f2fs_drop_inmem_pages_all(sbi, true);
- segno = NULL_SEGNO;
- goto gc_more;
- }
- if (gc_type == FG_GC && !is_sbi_flag_set(sbi, SBI_CP_DISABLED))
- ret = f2fs_write_checkpoint(sbi, &cpc);
+ /* Write checkpoint to reclaim prefree segments */
+ if (free_sections(sbi) < NR_CURSEG_PERSIST_TYPE &&
+ prefree_segments(sbi)) {
+ ret = f2fs_write_checkpoint(sbi, &cpc);
+ if (ret)
+ goto stop;
}
+go_gc_more:
+ segno = NULL_SEGNO;
+ goto gc_more;
+
stop:
SIT_I(sbi)->last_victim[ALLOC_NEXT] = 0;
- SIT_I(sbi)->last_victim[FLUSH_DEVICE] = init_segno;
+ SIT_I(sbi)->last_victim[FLUSH_DEVICE] = gc_control->victim_segno;
+
+ if (gc_type == FG_GC)
+ f2fs_unpin_all_sections(sbi, true);
trace_f2fs_gc_end(sbi->sb, ret, total_freed, sec_freed,
get_pages(sbi, F2FS_DIRTY_NODES),
@@ -1816,7 +1876,7 @@ stop:
put_gc_inode(&gc_list);
- if (sync && !ret)
+ if (gc_control->err_gc_skipped && !ret)
ret = sec_freed ? 0 : -EAGAIN;
return ret;
}
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index 3cb1e7a24740..049ce50cec9b 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -91,7 +91,7 @@ static u32 TEA_hash_name(const u8 *p, size_t len)
/*
* Compute @fname->hash. For all directories, @fname->disk_name must be set.
* For casefolded directories, @fname->usr_fname must be set, and also
- * @fname->cf_name if the filename is valid Unicode.
+ * @fname->cf_name if the filename is valid Unicode and is not "." or "..".
*/
void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
{
@@ -110,10 +110,11 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
/*
* If the casefolded name is provided, hash it instead of the
* on-disk name. If the casefolded name is *not* provided, that
- * should only be because the name wasn't valid Unicode, so fall
- * back to treating the name as an opaque byte sequence. Note
- * that to handle encrypted directories, the fallback must use
- * usr_fname (plaintext) rather than disk_name (ciphertext).
+ * should only be because the name wasn't valid Unicode or was
+ * "." or "..", so fall back to treating the name as an opaque
+ * byte sequence. Note that to handle encrypted directories,
+ * the fallback must use usr_fname (plaintext) rather than
+ * disk_name (ciphertext).
*/
WARN_ON_ONCE(!fname->usr_fname->name);
if (fname->cf_name.name) {
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index a578bf83b803..bf46a7dfbea2 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -14,21 +14,40 @@
#include "node.h"
#include <trace/events/f2fs.h>
-bool f2fs_may_inline_data(struct inode *inode)
+static bool support_inline_data(struct inode *inode)
{
if (f2fs_is_atomic_file(inode))
return false;
-
if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))
return false;
-
if (i_size_read(inode) > MAX_INLINE_DATA(inode))
return false;
+ return true;
+}
- if (f2fs_post_read_required(inode))
+bool f2fs_may_inline_data(struct inode *inode)
+{
+ if (!support_inline_data(inode))
return false;
- return true;
+ return !f2fs_post_read_required(inode);
+}
+
+bool f2fs_sanity_check_inline_data(struct inode *inode)
+{
+ if (!f2fs_has_inline_data(inode))
+ return false;
+
+ if (!support_inline_data(inode))
+ return true;
+
+ /*
+ * used by sanity_check_inode(), when disk layout fields has not
+ * been synchronized to inmem fields.
+ */
+ return (S_ISREG(inode->i_mode) &&
+ (file_is_encrypt(inode) || file_is_verity(inode) ||
+ (F2FS_I(inode)->i_flags & F2FS_COMPR_FL)));
}
bool f2fs_may_inline_dentry(struct inode *inode)
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 83639238a1fe..fc55f5bd1fcc 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -260,8 +260,8 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
return false;
}
- if (F2FS_I(inode)->extent_tree) {
- struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest;
+ if (fi->extent_tree) {
+ struct extent_info *ei = &fi->extent_tree->largest;
if (ei->len &&
(!f2fs_is_valid_blkaddr(sbi, ei->blk,
@@ -276,8 +276,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
}
}
- if (f2fs_has_inline_data(inode) &&
- (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))) {
+ if (f2fs_sanity_check_inline_data(inode)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_warn(sbi, "%s: inode (ino=%lx, mode=%u) should not have inline_data, run fsck to fix",
__func__, inode->i_ino, inode->i_mode);
@@ -466,10 +465,10 @@ static int do_read_inode(struct inode *inode)
}
}
- F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
- F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
- F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
- F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
+ fi->i_disk_time[0] = inode->i_atime;
+ fi->i_disk_time[1] = inode->i_ctime;
+ fi->i_disk_time[2] = inode->i_mtime;
+ fi->i_disk_time[3] = fi->i_crtime;
f2fs_put_page(node_page, 1);
stat_inc_inline_xattr(inode);
@@ -745,9 +744,8 @@ void f2fs_evict_inode(struct inode *inode)
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
int err = 0;
- /* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
- f2fs_drop_inmem_pages(inode);
+ f2fs_abort_atomic_write(inode, true);
trace_f2fs_evict_inode(inode);
truncate_inode_pages_final(&inode->i_data);
@@ -796,8 +794,22 @@ retry:
f2fs_lock_op(sbi);
err = f2fs_remove_inode_page(inode);
f2fs_unlock_op(sbi);
- if (err == -ENOENT)
+ if (err == -ENOENT) {
err = 0;
+
+ /*
+ * in fuzzed image, another node may has the same
+ * block address as inode's, if it was truncated
+ * previously, truncation of inode node will fail.
+ */
+ if (is_inode_flag_set(inode, FI_DIRTY_INODE)) {
+ f2fs_warn(F2FS_I_SB(inode),
+ "f2fs_evict_inode: inconsistent node id, ino:%lu",
+ inode->i_ino);
+ f2fs_inode_synced(inode);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ }
+ }
}
/* give more chances, if ENOMEM case */
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 5ed79b29999f..c549acb52ac4 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -37,13 +37,10 @@ static struct inode *f2fs_new_inode(struct user_namespace *mnt_userns,
if (!inode)
return ERR_PTR(-ENOMEM);
- f2fs_lock_op(sbi);
if (!f2fs_alloc_nid(sbi, &ino)) {
- f2fs_unlock_op(sbi);
err = -ENOSPC;
goto fail;
}
- f2fs_unlock_op(sbi);
nid_free = true;
@@ -461,6 +458,13 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
return 0;
}
+ if (!S_ISDIR(dir->i_mode)) {
+ f2fs_err(sbi, "inconsistent inode status, skip recovering inline_dots inode (ino:%lu, i_mode:%u, pino:%u)",
+ dir->i_ino, dir->i_mode, pino);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ return -ENOTDIR;
+ }
+
err = f2fs_dquot_initialize(dir);
if (err)
return err;
@@ -836,8 +840,8 @@ out:
}
static int __f2fs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
- struct dentry *dentry, umode_t mode,
- struct inode **whiteout)
+ struct dentry *dentry, umode_t mode, bool is_whiteout,
+ struct inode **new_inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
@@ -851,7 +855,7 @@ static int __f2fs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
if (IS_ERR(inode))
return PTR_ERR(inode);
- if (whiteout) {
+ if (is_whiteout) {
init_special_inode(inode, inode->i_mode, WHITEOUT_DEV);
inode->i_op = &f2fs_special_inode_operations;
} else {
@@ -876,21 +880,25 @@ static int __f2fs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
f2fs_add_orphan_inode(inode);
f2fs_alloc_nid_done(sbi, inode->i_ino);
- if (whiteout) {
+ if (is_whiteout) {
f2fs_i_links_write(inode, false);
spin_lock(&inode->i_lock);
inode->i_state |= I_LINKABLE;
spin_unlock(&inode->i_lock);
-
- *whiteout = inode;
} else {
- d_tmpfile(dentry, inode);
+ if (dentry)
+ d_tmpfile(dentry, inode);
+ else
+ f2fs_i_links_write(inode, false);
}
/* link_count was changed by d_tmpfile as well. */
f2fs_unlock_op(sbi);
unlock_new_inode(inode);
+ if (new_inode)
+ *new_inode = inode;
+
f2fs_balance_fs(sbi, true);
return 0;
@@ -911,7 +919,7 @@ static int f2fs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
if (!f2fs_is_checkpoint_ready(sbi))
return -ENOSPC;
- return __f2fs_tmpfile(mnt_userns, dir, dentry, mode, NULL);
+ return __f2fs_tmpfile(mnt_userns, dir, dentry, mode, false, NULL);
}
static int f2fs_create_whiteout(struct user_namespace *mnt_userns,
@@ -921,7 +929,13 @@ static int f2fs_create_whiteout(struct user_namespace *mnt_userns,
return -EIO;
return __f2fs_tmpfile(mnt_userns, dir, NULL,
- S_IFCHR | WHITEOUT_MODE, whiteout);
+ S_IFCHR | WHITEOUT_MODE, true, whiteout);
+}
+
+int f2fs_get_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct inode **new_inode)
+{
+ return __f2fs_tmpfile(mnt_userns, dir, NULL, S_IFREG, false, new_inode);
}
static int f2fs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 8ccff18560ff..836c79a20afc 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -90,10 +90,6 @@ bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type)
atomic_read(&sbi->total_ext_node) *
sizeof(struct extent_node)) >> PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
- } else if (type == INMEM_PAGES) {
- /* it allows 20% / total_ram for inmemory pages */
- mem_size = get_pages(sbi, F2FS_INMEM_PAGES);
- res = mem_size < (val.totalram / 5);
} else if (type == DISCARD_CACHE) {
mem_size = (atomic_read(&dcc->discard_cmd_cnt) *
sizeof(struct discard_cmd)) >> PAGE_SHIFT;
@@ -1416,8 +1412,7 @@ repeat:
err = read_node_page(page, 0);
if (err < 0) {
- f2fs_put_page(page, 1);
- return ERR_PTR(err);
+ goto out_put_err;
} else if (err == LOCKED_PAGE) {
err = 0;
goto page_hit;
@@ -1443,19 +1438,21 @@ repeat:
goto out_err;
}
page_hit:
- if (unlikely(nid != nid_of_node(page))) {
- f2fs_warn(sbi, "inconsistent node block, nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
+ if (likely(nid == nid_of_node(page)))
+ return page;
+
+ f2fs_warn(sbi, "inconsistent node block, nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
nid, nid_of_node(page), ino_of_node(page),
ofs_of_node(page), cpver_of_node(page),
next_blkaddr_of_node(page));
- set_sbi_flag(sbi, SBI_NEED_FSCK);
- err = -EINVAL;
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ err = -EINVAL;
out_err:
- ClearPageUptodate(page);
- f2fs_put_page(page, 1);
- return ERR_PTR(err);
- }
- return page;
+ ClearPageUptodate(page);
+out_put_err:
+ f2fs_handle_page_eio(sbi, page->index, NODE);
+ f2fs_put_page(page, 1);
+ return ERR_PTR(err);
}
struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
@@ -1631,7 +1628,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
goto redirty_out;
}
- if (atomic && !test_opt(sbi, NOBARRIER))
+ if (atomic && !test_opt(sbi, NOBARRIER) && !f2fs_sb_has_blkzoned(sbi))
fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
/* should add to global list before clearing PAGECACHE status */
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 4c1d34bfea78..3c09cae058b0 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -147,7 +147,6 @@ enum mem_type {
DIRTY_DENTS, /* indicates dirty dentry pages */
INO_ENTRIES, /* indicates inode entries */
EXTENT_CACHE, /* indicates extent cache */
- INMEM_PAGES, /* indicates inmemory pages */
DISCARD_CACHE, /* indicates memory of cached discard cmds */
COMPRESS_PAGE, /* indicates memory of cached compressed pages */
BASE_CHECK, /* check kernel status */
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 7225ce09f3ab..874c1b9c41a2 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -30,7 +30,7 @@
static struct kmem_cache *discard_entry_slab;
static struct kmem_cache *discard_cmd_slab;
static struct kmem_cache *sit_entry_set_slab;
-static struct kmem_cache *inmem_entry_slab;
+static struct kmem_cache *revoke_entry_slab;
static unsigned long __reverse_ulong(unsigned char *str)
{
@@ -185,301 +185,175 @@ bool f2fs_need_SSR(struct f2fs_sb_info *sbi)
SM_I(sbi)->min_ssr_sections + reserved_sections(sbi));
}
-void f2fs_register_inmem_page(struct inode *inode, struct page *page)
+void f2fs_abort_atomic_write(struct inode *inode, bool clean)
{
- struct inmem_pages *new;
-
- set_page_private_atomic(page);
-
- new = f2fs_kmem_cache_alloc(inmem_entry_slab,
- GFP_NOFS, true, NULL);
-
- /* add atomic page indices to the list */
- new->page = page;
- INIT_LIST_HEAD(&new->list);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
- /* increase reference count with clean state */
- get_page(page);
- mutex_lock(&F2FS_I(inode)->inmem_lock);
- list_add_tail(&new->list, &F2FS_I(inode)->inmem_pages);
- inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
- mutex_unlock(&F2FS_I(inode)->inmem_lock);
+ if (f2fs_is_atomic_file(inode)) {
+ if (clean)
+ truncate_inode_pages_final(inode->i_mapping);
+ clear_inode_flag(fi->cow_inode, FI_ATOMIC_FILE);
+ iput(fi->cow_inode);
+ fi->cow_inode = NULL;
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
- trace_f2fs_register_inmem_page(page, INMEM);
+ spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
+ sbi->atomic_files--;
+ spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
+ }
}
-static int __revoke_inmem_pages(struct inode *inode,
- struct list_head *head, bool drop, bool recover,
- bool trylock)
+static int __replace_atomic_write_block(struct inode *inode, pgoff_t index,
+ block_t new_addr, block_t *old_addr, bool recover)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct inmem_pages *cur, *tmp;
- int err = 0;
-
- list_for_each_entry_safe(cur, tmp, head, list) {
- struct page *page = cur->page;
-
- if (drop)
- trace_f2fs_commit_inmem_page(page, INMEM_DROP);
-
- if (trylock) {
- /*
- * to avoid deadlock in between page lock and
- * inmem_lock.
- */
- if (!trylock_page(page))
- continue;
- } else {
- lock_page(page);
- }
-
- f2fs_wait_on_page_writeback(page, DATA, true, true);
-
- if (recover) {
- struct dnode_of_data dn;
- struct node_info ni;
+ struct dnode_of_data dn;
+ struct node_info ni;
+ int err;
- trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
retry:
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = f2fs_get_dnode_of_data(&dn, page->index,
- LOOKUP_NODE);
- if (err) {
- if (err == -ENOMEM) {
- memalloc_retry_wait(GFP_NOFS);
- goto retry;
- }
- err = -EAGAIN;
- goto next;
- }
-
- err = f2fs_get_node_info(sbi, dn.nid, &ni, false);
- if (err) {
- f2fs_put_dnode(&dn);
- return err;
- }
-
- if (cur->old_addr == NEW_ADDR) {
- f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
- f2fs_update_data_blkaddr(&dn, NEW_ADDR);
- } else
- f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
- cur->old_addr, ni.version, true, true);
- f2fs_put_dnode(&dn);
- }
-next:
- /* we don't need to invalidate this in the sccessful status */
- if (drop || recover) {
- ClearPageUptodate(page);
- clear_page_private_gcing(page);
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE_RA);
+ if (err) {
+ if (err == -ENOMEM) {
+ f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
+ goto retry;
}
- detach_page_private(page);
- set_page_private(page, 0);
- f2fs_put_page(page, 1);
-
- list_del(&cur->list);
- kmem_cache_free(inmem_entry_slab, cur);
- dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
+ return err;
}
- return err;
-}
-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;
- struct f2fs_inode_info *fi;
- unsigned int count = sbi->atomic_files;
- unsigned int looped = 0;
-next:
- spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
- if (list_empty(head)) {
- spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
- return;
+ err = f2fs_get_node_info(sbi, dn.nid, &ni, false);
+ if (err) {
+ f2fs_put_dnode(&dn);
+ return err;
}
- fi = list_first_entry(head, struct f2fs_inode_info, inmem_ilist);
- inode = igrab(&fi->vfs_inode);
- if (inode)
- list_move_tail(&fi->inmem_ilist, head);
- spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
- if (inode) {
- if (gc_failure) {
- if (!fi->i_gc_failures[GC_FAILURE_ATOMIC])
- goto skip;
+ if (recover) {
+ /* dn.data_blkaddr is always valid */
+ if (!__is_valid_data_blkaddr(new_addr)) {
+ if (new_addr == NULL_ADDR)
+ dec_valid_block_count(sbi, inode, 1);
+ f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
+ f2fs_update_data_blkaddr(&dn, new_addr);
+ } else {
+ f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
+ new_addr, ni.version, true, true);
}
- set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
- f2fs_drop_inmem_pages(inode);
-skip:
- iput(inode);
- }
- f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
- if (gc_failure) {
- if (++looped >= count)
- return;
- }
- goto next;
-}
-
-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);
+ } else {
+ blkcnt_t count = 1;
- do {
- mutex_lock(&fi->inmem_lock);
- if (list_empty(&fi->inmem_pages)) {
- fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
-
- spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
- if (!list_empty(&fi->inmem_ilist))
- list_del_init(&fi->inmem_ilist);
- if (f2fs_is_atomic_file(inode)) {
- clear_inode_flag(inode, FI_ATOMIC_FILE);
- sbi->atomic_files--;
- }
- spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
+ *old_addr = dn.data_blkaddr;
+ f2fs_truncate_data_blocks_range(&dn, 1);
+ dec_valid_block_count(sbi, F2FS_I(inode)->cow_inode, count);
+ inc_valid_block_count(sbi, inode, &count);
+ f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr,
+ ni.version, true, false);
+ }
- mutex_unlock(&fi->inmem_lock);
- break;
- }
- __revoke_inmem_pages(inode, &fi->inmem_pages,
- true, false, true);
- mutex_unlock(&fi->inmem_lock);
- } while (1);
+ f2fs_put_dnode(&dn);
+ return 0;
}
-void f2fs_drop_inmem_page(struct inode *inode, struct page *page)
+static void __complete_revoke_list(struct inode *inode, struct list_head *head,
+ bool revoke)
{
- struct f2fs_inode_info *fi = F2FS_I(inode);
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct list_head *head = &fi->inmem_pages;
- struct inmem_pages *cur = NULL;
-
- f2fs_bug_on(sbi, !page_private_atomic(page));
+ struct revoke_entry *cur, *tmp;
- mutex_lock(&fi->inmem_lock);
- list_for_each_entry(cur, head, list) {
- if (cur->page == page)
- break;
+ list_for_each_entry_safe(cur, tmp, head, list) {
+ if (revoke)
+ __replace_atomic_write_block(inode, cur->index,
+ cur->old_addr, NULL, true);
+ list_del(&cur->list);
+ kmem_cache_free(revoke_entry_slab, cur);
}
-
- f2fs_bug_on(sbi, list_empty(head) || cur->page != page);
- list_del(&cur->list);
- mutex_unlock(&fi->inmem_lock);
-
- dec_page_count(sbi, F2FS_INMEM_PAGES);
- kmem_cache_free(inmem_entry_slab, cur);
-
- ClearPageUptodate(page);
- clear_page_private_atomic(page);
- f2fs_put_page(page, 0);
-
- detach_page_private(page);
- set_page_private(page, 0);
-
- trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE);
}
-static int __f2fs_commit_inmem_pages(struct inode *inode)
+static int __f2fs_commit_atomic_write(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
- struct inmem_pages *cur, *tmp;
- struct f2fs_io_info fio = {
- .sbi = sbi,
- .ino = inode->i_ino,
- .type = DATA,
- .op = REQ_OP_WRITE,
- .op_flags = REQ_SYNC | REQ_PRIO,
- .io_type = FS_DATA_IO,
- };
+ struct inode *cow_inode = fi->cow_inode;
+ struct revoke_entry *new;
struct list_head revoke_list;
- bool submit_bio = false;
- int err = 0;
+ block_t blkaddr;
+ struct dnode_of_data dn;
+ pgoff_t len = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+ pgoff_t off = 0, blen, index;
+ int ret = 0, i;
INIT_LIST_HEAD(&revoke_list);
- list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
- struct page *page = cur->page;
+ while (len) {
+ blen = min_t(pgoff_t, ADDRS_PER_BLOCK(cow_inode), len);
- lock_page(page);
- if (page->mapping == inode->i_mapping) {
- trace_f2fs_commit_inmem_page(page, INMEM);
+ set_new_dnode(&dn, cow_inode, NULL, NULL, 0);
+ ret = f2fs_get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
+ if (ret && ret != -ENOENT) {
+ goto out;
+ } else if (ret == -ENOENT) {
+ ret = 0;
+ if (dn.max_level == 0)
+ goto out;
+ goto next;
+ }
- f2fs_wait_on_page_writeback(page, DATA, true, true);
+ blen = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, cow_inode),
+ len);
+ index = off;
+ for (i = 0; i < blen; i++, dn.ofs_in_node++, index++) {
+ blkaddr = f2fs_data_blkaddr(&dn);
- set_page_dirty(page);
- if (clear_page_dirty_for_io(page)) {
- inode_dec_dirty_pages(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 = f2fs_do_write_data_page(&fio);
- if (err) {
- if (err == -ENOMEM) {
- memalloc_retry_wait(GFP_NOFS);
- goto retry;
- }
- unlock_page(page);
- break;
+ if (!__is_valid_data_blkaddr(blkaddr)) {
+ continue;
+ } else if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
+ DATA_GENERIC_ENHANCE)) {
+ f2fs_put_dnode(&dn);
+ ret = -EFSCORRUPTED;
+ goto out;
}
- /* record old blkaddr for revoking */
- cur->old_addr = fio.old_blkaddr;
- submit_bio = true;
- }
- unlock_page(page);
- list_move_tail(&cur->list, &revoke_list);
- }
- if (submit_bio)
- f2fs_submit_merged_write_cond(sbi, inode, NULL, 0, DATA);
+ new = f2fs_kmem_cache_alloc(revoke_entry_slab, GFP_NOFS,
+ true, NULL);
- 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, false);
+ ret = __replace_atomic_write_block(inode, index, blkaddr,
+ &new->old_addr, false);
+ if (ret) {
+ f2fs_put_dnode(&dn);
+ kmem_cache_free(revoke_entry_slab, new);
+ goto out;
+ }
- /* drop all uncommitted pages */
- __revoke_inmem_pages(inode, &fi->inmem_pages,
- true, false, false);
- } else {
- __revoke_inmem_pages(inode, &revoke_list,
- false, false, false);
+ f2fs_update_data_blkaddr(&dn, NULL_ADDR);
+ new->index = index;
+ list_add_tail(&new->list, &revoke_list);
+ }
+ f2fs_put_dnode(&dn);
+next:
+ off += blen;
+ len -= blen;
}
- return err;
+out:
+ __complete_revoke_list(inode, &revoke_list, ret ? true : false);
+
+ return ret;
}
-int f2fs_commit_inmem_pages(struct inode *inode)
+int f2fs_commit_atomic_write(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
int err;
- f2fs_balance_fs(sbi, true);
+ err = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
+ if (err)
+ return err;
f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
-
f2fs_lock_op(sbi);
- set_inode_flag(inode, FI_ATOMIC_COMMIT);
-
- mutex_lock(&fi->inmem_lock);
- err = __f2fs_commit_inmem_pages(inode);
- mutex_unlock(&fi->inmem_lock);
- clear_inode_flag(inode, FI_ATOMIC_COMMIT);
+ err = __f2fs_commit_atomic_write(inode);
f2fs_unlock_op(sbi);
f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
@@ -520,8 +394,15 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
io_schedule();
finish_wait(&sbi->gc_thread->fggc_wq, &wait);
} else {
+ struct f2fs_gc_control gc_control = {
+ .victim_segno = NULL_SEGNO,
+ .init_gc_type = BG_GC,
+ .no_bg_gc = true,
+ .should_migrate_blocks = false,
+ .err_gc_skipped = false,
+ .nr_free_secs = 1 };
f2fs_down_write(&sbi->gc_lock);
- f2fs_gc(sbi, false, false, false, NULL_SEGNO);
+ f2fs_gc(sbi, &gc_control);
}
}
}
@@ -1664,33 +1545,32 @@ static unsigned int __wait_discard_cmd_range(struct f2fs_sb_info *sbi,
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
&(dcc->fstrim_list) : &(dcc->wait_list);
- struct discard_cmd *dc, *tmp;
- bool need_wait;
+ struct discard_cmd *dc = NULL, *iter, *tmp;
unsigned int trimmed = 0;
next:
- need_wait = false;
+ dc = NULL;
mutex_lock(&dcc->cmd_lock);
- list_for_each_entry_safe(dc, tmp, wait_list, list) {
- if (dc->lstart + dc->len <= start || end <= dc->lstart)
+ list_for_each_entry_safe(iter, tmp, wait_list, list) {
+ if (iter->lstart + iter->len <= start || end <= iter->lstart)
continue;
- if (dc->len < dpolicy->granularity)
+ if (iter->len < dpolicy->granularity)
continue;
- if (dc->state == D_DONE && !dc->ref) {
- wait_for_completion_io(&dc->wait);
- if (!dc->error)
- trimmed += dc->len;
- __remove_discard_cmd(sbi, dc);
+ if (iter->state == D_DONE && !iter->ref) {
+ wait_for_completion_io(&iter->wait);
+ if (!iter->error)
+ trimmed += iter->len;
+ __remove_discard_cmd(sbi, iter);
} else {
- dc->ref++;
- need_wait = true;
+ iter->ref++;
+ dc = iter;
break;
}
}
mutex_unlock(&dcc->cmd_lock);
- if (need_wait) {
+ if (dc) {
trimmed += __wait_one_discard_bio(sbi, dc);
goto next;
}
@@ -3286,8 +3166,7 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
return CURSEG_COLD_DATA;
if (file_is_hot(inode) ||
is_inode_flag_set(inode, FI_HOT_DATA) ||
- f2fs_is_atomic_file(inode) ||
- f2fs_is_volatile_file(inode))
+ f2fs_is_atomic_file(inode))
return CURSEG_HOT_DATA;
return f2fs_rw_hint_to_seg_type(inode->i_write_hint);
} else {
@@ -4084,10 +3963,12 @@ static void adjust_sit_entry_set(struct sit_entry_set *ses,
return;
list_for_each_entry_continue(next, head, set_list)
- if (ses->entry_cnt <= next->entry_cnt)
- break;
+ if (ses->entry_cnt <= next->entry_cnt) {
+ list_move_tail(&ses->set_list, &next->set_list);
+ return;
+ }
- list_move_tail(&ses->set_list, &next->set_list);
+ list_move_tail(&ses->set_list, head);
}
static void add_sit_entry(unsigned int segno, struct list_head *head)
@@ -4455,7 +4336,7 @@ 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;
+ block_t sit_valid_blocks[2] = {0, 0};
do {
readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_VECS,
@@ -4480,8 +4361,8 @@ 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;
+
+ sit_valid_blocks[SE_PAGETYPE(se)] += se->valid_blocks;
if (f2fs_block_unit_discard(sbi)) {
/* build discard map only one time */
@@ -4521,15 +4402,15 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
sit = sit_in_journal(journal, i);
old_valid_blocks = se->valid_blocks;
- if (IS_NODESEG(se->type))
- total_node_blocks -= old_valid_blocks;
+
+ sit_valid_blocks[SE_PAGETYPE(se)] -= 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;
+
+ sit_valid_blocks[SE_PAGETYPE(se)] += se->valid_blocks;
if (f2fs_block_unit_discard(sbi)) {
if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
@@ -4551,13 +4432,24 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
}
up_read(&curseg->journal_rwsem);
- if (!err && total_node_blocks != valid_node_count(sbi)) {
+ if (err)
+ return err;
+
+ if (sit_valid_blocks[NODE] != valid_node_count(sbi)) {
f2fs_err(sbi, "SIT is corrupted node# %u vs %u",
- total_node_blocks, valid_node_count(sbi));
- err = -EFSCORRUPTED;
+ sit_valid_blocks[NODE], valid_node_count(sbi));
+ return -EFSCORRUPTED;
}
- return err;
+ if (sit_valid_blocks[DATA] + sit_valid_blocks[NODE] >
+ valid_user_blocks(sbi)) {
+ f2fs_err(sbi, "SIT is corrupted data# %u %u vs %u",
+ sit_valid_blocks[DATA], sit_valid_blocks[NODE],
+ valid_user_blocks(sbi));
+ return -EFSCORRUPTED;
+ }
+
+ return 0;
}
static void init_free_segmap(struct f2fs_sb_info *sbi)
@@ -4637,6 +4529,13 @@ static int init_victim_secmap(struct f2fs_sb_info *sbi)
dirty_i->victim_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL);
if (!dirty_i->victim_secmap)
return -ENOMEM;
+
+ dirty_i->pinned_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL);
+ if (!dirty_i->pinned_secmap)
+ return -ENOMEM;
+
+ dirty_i->pinned_secmap_cnt = 0;
+ dirty_i->enable_pin_section = true;
return 0;
}
@@ -5225,6 +5124,7 @@ static void destroy_victim_secmap(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ kvfree(dirty_i->pinned_secmap);
kvfree(dirty_i->victim_secmap);
}
@@ -5335,9 +5235,9 @@ int __init f2fs_create_segment_manager_caches(void)
if (!sit_entry_set_slab)
goto destroy_discard_cmd;
- inmem_entry_slab = f2fs_kmem_cache_create("f2fs_inmem_page_entry",
- sizeof(struct inmem_pages));
- if (!inmem_entry_slab)
+ revoke_entry_slab = f2fs_kmem_cache_create("f2fs_revoke_entry",
+ sizeof(struct revoke_entry));
+ if (!revoke_entry_slab)
goto destroy_sit_entry_set;
return 0;
@@ -5356,5 +5256,5 @@ void f2fs_destroy_segment_manager_caches(void)
kmem_cache_destroy(sit_entry_set_slab);
kmem_cache_destroy(discard_cmd_slab);
kmem_cache_destroy(discard_entry_slab);
- kmem_cache_destroy(inmem_entry_slab);
+ kmem_cache_destroy(revoke_entry_slab);
}
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 5c94caf0c0a1..3f277dfcb131 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -24,6 +24,7 @@
#define IS_DATASEG(t) ((t) <= CURSEG_COLD_DATA)
#define IS_NODESEG(t) ((t) >= CURSEG_HOT_NODE && (t) <= CURSEG_COLD_NODE)
+#define SE_PAGETYPE(se) ((IS_NODESEG((se)->type) ? NODE : DATA))
static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi,
unsigned short seg_type)
@@ -224,10 +225,10 @@ struct segment_allocation {
#define MAX_SKIP_GC_COUNT 16
-struct inmem_pages {
+struct revoke_entry {
struct list_head list;
- struct page *page;
block_t old_addr; /* for revoking when fail to commit */
+ pgoff_t index;
};
struct sit_info {
@@ -294,6 +295,9 @@ struct dirty_seglist_info {
struct mutex seglist_lock; /* lock for segment bitmaps */
int nr_dirty[NR_DIRTY_TYPE]; /* # of dirty segments */
unsigned long *victim_secmap; /* background GC victims */
+ unsigned long *pinned_secmap; /* pinned victims from foreground GC */
+ unsigned int pinned_secmap_cnt; /* count of victims which has pinned data */
+ bool enable_pin_section; /* enable pinning section */
};
/* victim selection function for cleaning and SSR */
@@ -572,11 +576,10 @@ static inline int reserved_sections(struct f2fs_sb_info *sbi)
return GET_SEC_FROM_SEG(sbi, reserved_segments(sbi));
}
-static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
+static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi,
+ unsigned int node_blocks, unsigned int dent_blocks)
{
- unsigned int node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) +
- get_pages(sbi, F2FS_DIRTY_DENTS);
- unsigned int dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS);
+
unsigned int segno, left_blocks;
int i;
@@ -602,19 +605,28 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
int freed, int needed)
{
- int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
- int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
- int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
+ unsigned int total_node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) +
+ get_pages(sbi, F2FS_DIRTY_DENTS) +
+ get_pages(sbi, F2FS_DIRTY_IMETA);
+ unsigned int total_dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS);
+ unsigned int node_secs = total_node_blocks / BLKS_PER_SEC(sbi);
+ unsigned int dent_secs = total_dent_blocks / BLKS_PER_SEC(sbi);
+ unsigned int node_blocks = total_node_blocks % BLKS_PER_SEC(sbi);
+ unsigned int dent_blocks = total_dent_blocks % BLKS_PER_SEC(sbi);
+ unsigned int free, need_lower, need_upper;
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
return false;
- if (free_sections(sbi) + freed == reserved_sections(sbi) + needed &&
- has_curseg_enough_space(sbi))
+ free = free_sections(sbi) + freed;
+ need_lower = node_secs + dent_secs + reserved_sections(sbi) + needed;
+ need_upper = need_lower + (node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0);
+
+ if (free > need_upper)
return false;
- return (free_sections(sbi) + freed) <=
- (node_secs + 2 * dent_secs + imeta_secs +
- reserved_sections(sbi) + needed);
+ else if (free <= need_lower)
+ return true;
+ return !has_curseg_enough_space(sbi, node_blocks, dent_blocks);
}
static inline bool f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index ed3e8b7a8260..37221e94e5ef 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -525,10 +525,11 @@ static int f2fs_set_test_dummy_encryption(struct super_block *sb,
return -EINVAL;
}
f2fs_warn(sbi, "Test dummy encryption mode enabled");
+ return 0;
#else
- f2fs_warn(sbi, "Test dummy encryption mount option ignored");
+ f2fs_warn(sbi, "test_dummy_encryption option not supported");
+ return -EINVAL;
#endif
- return 0;
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -1339,9 +1340,6 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
spin_lock_init(&fi->i_size_lock);
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_f2fs_rwsem(&fi->i_gc_rwsem[READ]);
init_f2fs_rwsem(&fi->i_gc_rwsem[WRITE]);
init_f2fs_rwsem(&fi->i_xattr_sem);
@@ -1382,9 +1380,8 @@ static int f2fs_drop_inode(struct inode *inode)
atomic_inc(&inode->i_count);
spin_unlock(&inode->i_lock);
- /* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
- f2fs_drop_inmem_pages(inode);
+ f2fs_abort_atomic_write(inode, true);
/* should remain fi->extent_tree for writepage */
f2fs_destroy_extent_node(inode);
@@ -1707,18 +1704,23 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
block_t total_count, user_block_count, start_count;
u64 avail_node_count;
+ unsigned int total_valid_node_count;
total_count = le64_to_cpu(sbi->raw_super->block_count);
- user_block_count = sbi->user_block_count;
start_count = le32_to_cpu(sbi->raw_super->segment0_blkaddr);
buf->f_type = F2FS_SUPER_MAGIC;
buf->f_bsize = sbi->blocksize;
buf->f_blocks = total_count - start_count;
+
+ spin_lock(&sbi->stat_lock);
+
+ user_block_count = sbi->user_block_count;
+ total_valid_node_count = valid_node_count(sbi);
+ avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
buf->f_bfree = user_block_count - valid_user_blocks(sbi) -
sbi->current_reserved_blocks;
- spin_lock(&sbi->stat_lock);
if (unlikely(buf->f_bfree <= sbi->unusable_block_count))
buf->f_bfree = 0;
else
@@ -1731,14 +1733,12 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
else
buf->f_bavail = 0;
- avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
-
if (avail_node_count > user_block_count) {
buf->f_files = user_block_count;
buf->f_ffree = buf->f_bavail;
} else {
buf->f_files = avail_node_count;
- buf->f_ffree = min(avail_node_count - valid_node_count(sbi),
+ buf->f_ffree = min(avail_node_count - total_valid_node_count,
buf->f_bavail);
}
@@ -2055,7 +2055,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
{
unsigned int s_flags = sbi->sb->s_flags;
struct cp_control cpc;
- unsigned int gc_mode;
+ unsigned int gc_mode = sbi->gc_mode;
int err = 0;
int ret;
block_t unusable;
@@ -2066,14 +2066,25 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
}
sbi->sb->s_flags |= SB_ACTIVE;
+ /* check if we need more GC first */
+ unusable = f2fs_get_unusable_blocks(sbi);
+ if (!f2fs_disable_cp_again(sbi, unusable))
+ goto skip_gc;
+
f2fs_update_time(sbi, DISABLE_TIME);
- gc_mode = sbi->gc_mode;
sbi->gc_mode = GC_URGENT_HIGH;
while (!f2fs_time_over(sbi, DISABLE_TIME)) {
+ struct f2fs_gc_control gc_control = {
+ .victim_segno = NULL_SEGNO,
+ .init_gc_type = FG_GC,
+ .should_migrate_blocks = false,
+ .err_gc_skipped = true,
+ .nr_free_secs = 1 };
+
f2fs_down_write(&sbi->gc_lock);
- err = f2fs_gc(sbi, true, false, false, NULL_SEGNO);
+ err = f2fs_gc(sbi, &gc_control);
if (err == -ENODATA) {
err = 0;
break;
@@ -2094,6 +2105,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
goto restore_flag;
}
+skip_gc:
f2fs_down_write(&sbi->gc_lock);
cpc.reason = CP_PAUSE;
set_sbi_flag(sbi, SBI_CP_DISABLED);
@@ -2684,7 +2696,8 @@ int f2fs_quota_sync(struct super_block *sb, int type)
if (!sb_has_quota_active(sb, cnt))
continue;
- inode_lock(dqopt->files[cnt]);
+ if (!f2fs_sb_has_quota_ino(sbi))
+ inode_lock(dqopt->files[cnt]);
/*
* do_quotactl
@@ -2703,7 +2716,8 @@ int f2fs_quota_sync(struct super_block *sb, int type)
f2fs_up_read(&sbi->quota_sem);
f2fs_unlock_op(sbi);
- inode_unlock(dqopt->files[cnt]);
+ if (!f2fs_sb_has_quota_ino(sbi))
+ inode_unlock(dqopt->files[cnt]);
if (ret)
break;
@@ -3648,22 +3662,29 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
struct block_device *bdev = FDEV(devi).bdev;
sector_t nr_sectors = bdev_nr_sectors(bdev);
struct f2fs_report_zones_args rep_zone_arg;
+ u64 zone_sectors;
int ret;
if (!f2fs_sb_has_blkzoned(sbi))
return 0;
+ zone_sectors = bdev_zone_sectors(bdev);
+ if (!is_power_of_2(zone_sectors)) {
+ f2fs_err(sbi, "F2FS does not support non power of 2 zone sizes\n");
+ return -EINVAL;
+ }
+
if (sbi->blocks_per_blkz && sbi->blocks_per_blkz !=
- SECTOR_TO_BLOCK(bdev_zone_sectors(bdev)))
+ SECTOR_TO_BLOCK(zone_sectors))
return -EINVAL;
- sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_sectors(bdev));
+ sbi->blocks_per_blkz = SECTOR_TO_BLOCK(zone_sectors);
if (sbi->log_blocks_per_blkz && sbi->log_blocks_per_blkz !=
__ilog2_u32(sbi->blocks_per_blkz))
return -EINVAL;
sbi->log_blocks_per_blkz = __ilog2_u32(sbi->blocks_per_blkz);
FDEV(devi).nr_blkz = SECTOR_TO_BLOCK(nr_sectors) >>
sbi->log_blocks_per_blkz;
- if (nr_sectors & (bdev_zone_sectors(bdev) - 1))
+ if (nr_sectors & (zone_sectors - 1))
FDEV(devi).nr_blkz++;
FDEV(devi).blkz_seq = f2fs_kvzalloc(sbi,
@@ -4070,30 +4091,9 @@ try_onemore:
set_sbi_flag(sbi, SBI_POR_DOING);
spin_lock_init(&sbi->stat_lock);
- for (i = 0; i < NR_PAGE_TYPE; i++) {
- int n = (i == META) ? 1 : NR_TEMP_TYPE;
- int j;
-
- sbi->write_io[i] =
- f2fs_kmalloc(sbi,
- array_size(n,
- sizeof(struct f2fs_bio_info)),
- GFP_KERNEL);
- if (!sbi->write_io[i]) {
- err = -ENOMEM;
- goto free_bio_info;
- }
-
- for (j = HOT; j < n; j++) {
- init_f2fs_rwsem(&sbi->write_io[i][j].io_rwsem);
- sbi->write_io[i][j].sbi = sbi;
- sbi->write_io[i][j].bio = NULL;
- spin_lock_init(&sbi->write_io[i][j].io_lock);
- INIT_LIST_HEAD(&sbi->write_io[i][j].io_list);
- INIT_LIST_HEAD(&sbi->write_io[i][j].bio_list);
- init_f2fs_rwsem(&sbi->write_io[i][j].bio_list_lock);
- }
- }
+ err = f2fs_init_write_merge_io(sbi);
+ if (err)
+ goto free_bio_info;
init_f2fs_rwsem(&sbi->cp_rwsem);
init_f2fs_rwsem(&sbi->quota_sem);
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index 65395ae188aa..7b8f2b41c29b 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -129,7 +129,7 @@ static int f2fs_begin_enable_verity(struct file *filp)
if (f2fs_verity_in_progress(inode))
return -EBUSY;
- if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
+ if (f2fs_is_atomic_file(inode))
return -EOPNOTSUPP;
/*
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 17:10:18 +0100