summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/aio.c7
-rw-r--r--fs/btrfs/ordered-data.c11
-rw-r--r--fs/btrfs/volumes.c8
-rw-r--r--fs/coredump.c2
-rw-r--r--fs/ext4/extents_status.c4
-rw-r--r--fs/ext4/ialloc.c16
-rw-r--r--fs/ext4/mballoc.c4
-rw-r--r--fs/ext4/super.c60
-rw-r--r--fs/f2fs/data.c23
-rw-r--r--fs/f2fs/dir.c2
-rw-r--r--fs/f2fs/f2fs.h6
-rw-r--r--fs/f2fs/file.c12
-rw-r--r--fs/f2fs/inode.c1
-rw-r--r--fs/f2fs/namei.c13
-rw-r--r--fs/f2fs/node.c2
-rw-r--r--fs/f2fs/segment.c5
-rw-r--r--fs/f2fs/super.c4
-rw-r--r--fs/fuse/dev.c51
-rw-r--r--fs/fuse/dir.c41
-rw-r--r--fs/fuse/file.c8
-rw-r--r--fs/fuse/inode.c22
-rw-r--r--fs/gfs2/file.c4
-rw-r--r--fs/gfs2/glock.c14
-rw-r--r--fs/gfs2/glops.c4
-rw-r--r--fs/gfs2/lock_dlm.c4
-rw-r--r--fs/gfs2/rgrp.c4
-rw-r--r--fs/jbd2/transaction.c5
-rw-r--r--fs/kernfs/mount.c30
-rw-r--r--fs/nfs/direct.c2
-rw-r--r--fs/nfs/internal.h1
-rw-r--r--fs/nfs/nfs3acl.c43
-rw-r--r--fs/nfs/nfs3proc.c4
-rw-r--r--fs/nfs/pagelist.c20
-rw-r--r--fs/nfs/write.c335
-rw-r--r--fs/nfsd/nfs4xdr.c2
-rw-r--r--fs/quota/dquot.c2
-rw-r--r--fs/xattr.c2
-rw-r--r--fs/xfs/xfs_bmap.c7
-rw-r--r--fs/xfs/xfs_bmap.h4
-rw-r--r--fs/xfs/xfs_bmap_util.c53
-rw-r--r--fs/xfs/xfs_bmap_util.h4
-rw-r--r--fs/xfs/xfs_btree.c82
-rw-r--r--fs/xfs/xfs_iomap.c3
-rw-r--r--fs/xfs/xfs_sb.c25
44 files changed, 677 insertions, 279 deletions
diff --git a/fs/aio.c b/fs/aio.c
index 955947ef3e02..1c9c5f0a9e2b 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -830,16 +830,20 @@ void exit_aio(struct mm_struct *mm)
static void put_reqs_available(struct kioctx *ctx, unsigned nr)
{
struct kioctx_cpu *kcpu;
+ unsigned long flags;
preempt_disable();
kcpu = this_cpu_ptr(ctx->cpu);
+ local_irq_save(flags);
kcpu->reqs_available += nr;
+
while (kcpu->reqs_available >= ctx->req_batch * 2) {
kcpu->reqs_available -= ctx->req_batch;
atomic_add(ctx->req_batch, &ctx->reqs_available);
}
+ local_irq_restore(flags);
preempt_enable();
}
@@ -847,10 +851,12 @@ static bool get_reqs_available(struct kioctx *ctx)
{
struct kioctx_cpu *kcpu;
bool ret = false;
+ unsigned long flags;
preempt_disable();
kcpu = this_cpu_ptr(ctx->cpu);
+ local_irq_save(flags);
if (!kcpu->reqs_available) {
int old, avail = atomic_read(&ctx->reqs_available);
@@ -869,6 +875,7 @@ static bool get_reqs_available(struct kioctx *ctx)
ret = true;
kcpu->reqs_available--;
out:
+ local_irq_restore(flags);
preempt_enable();
return ret;
}
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index e12441c7cf1d..7187b14faa6c 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -484,8 +484,19 @@ void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
log_list);
list_del_init(&ordered->log_list);
spin_unlock_irq(&log->log_extents_lock[index]);
+
+ if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
+ !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
+ struct inode *inode = ordered->inode;
+ u64 start = ordered->file_offset;
+ u64 end = ordered->file_offset + ordered->len - 1;
+
+ WARN_ON(!inode);
+ filemap_fdatawrite_range(inode->i_mapping, start, end);
+ }
wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
&ordered->flags));
+
btrfs_put_ordered_extent(ordered);
spin_lock_irq(&log->log_extents_lock[index]);
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6104676857f5..6cb82f62cb7c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1680,11 +1680,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
if (device->bdev == root->fs_info->fs_devices->latest_bdev)
root->fs_info->fs_devices->latest_bdev = next_device->bdev;
- if (device->bdev)
+ if (device->bdev) {
device->fs_devices->open_devices--;
-
- /* remove sysfs entry */
- btrfs_kobj_rm_device(root->fs_info, device);
+ /* remove sysfs entry */
+ btrfs_kobj_rm_device(root->fs_info, device);
+ }
call_rcu(&device->rcu, free_device);
diff --git a/fs/coredump.c b/fs/coredump.c
index 0b2528fb640e..a93f7e6ea4cf 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -306,7 +306,7 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
if (unlikely(nr < 0))
return nr;
- tsk->flags = PF_DUMPCORE;
+ tsk->flags |= PF_DUMPCORE;
if (atomic_read(&mm->mm_users) == nr + 1)
goto done;
/*
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 3f5c188953a4..0b7e28e7eaa4 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -966,10 +966,10 @@ retry:
continue;
}
- if (ei->i_es_lru_nr == 0 || ei == locked_ei)
+ if (ei->i_es_lru_nr == 0 || ei == locked_ei ||
+ !write_trylock(&ei->i_es_lock))
continue;
- write_lock(&ei->i_es_lock);
shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
if (ei->i_es_lru_nr == 0)
list_del_init(&ei->i_es_lru);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index a87455df38bc..5b87fc36aab8 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -338,7 +338,7 @@ out:
fatal = err;
} else {
ext4_error(sb, "bit already cleared for inode %lu", ino);
- if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+ if (gdp && !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
int count;
count = ext4_free_inodes_count(sb, gdp);
percpu_counter_sub(&sbi->s_freeinodes_counter,
@@ -874,6 +874,13 @@ got:
goto out;
}
+ BUFFER_TRACE(group_desc_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, group_desc_bh);
+ if (err) {
+ ext4_std_error(sb, err);
+ goto out;
+ }
+
/* We may have to initialize the block bitmap if it isn't already */
if (ext4_has_group_desc_csum(sb) &&
gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
@@ -910,13 +917,6 @@ got:
}
}
- BUFFER_TRACE(group_desc_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, group_desc_bh);
- if (err) {
- ext4_std_error(sb, err);
- goto out;
- }
-
/* Update the relevant bg descriptor fields */
if (ext4_has_group_desc_csum(sb)) {
int free;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 7f72f50a8fa7..2dcb936be90e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -752,8 +752,8 @@ void ext4_mb_generate_buddy(struct super_block *sb,
if (free != grp->bb_free) {
ext4_grp_locked_error(sb, group, 0, 0,
- "%u clusters in bitmap, %u in gd; "
- "block bitmap corrupt.",
+ "block bitmap and bg descriptor "
+ "inconsistent: %u vs %u free clusters",
free, grp->bb_free);
/*
* If we intend to continue, we consider group descriptor
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b9b9aabfb4d2..6df7bc611dbd 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1525,8 +1525,6 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
sbi->s_commit_interval = HZ * arg;
} else if (token == Opt_max_batch_time) {
- if (arg == 0)
- arg = EXT4_DEF_MAX_BATCH_TIME;
sbi->s_max_batch_time = arg;
} else if (token == Opt_min_batch_time) {
sbi->s_min_batch_time = arg;
@@ -2809,10 +2807,11 @@ static void print_daily_error_info(unsigned long arg)
es = sbi->s_es;
if (es->s_error_count)
- ext4_msg(sb, KERN_NOTICE, "error count: %u",
+ /* fsck newer than v1.41.13 is needed to clean this condition. */
+ ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
le32_to_cpu(es->s_error_count));
if (es->s_first_error_time) {
- printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+ printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
sb->s_id, le32_to_cpu(es->s_first_error_time),
(int) sizeof(es->s_first_error_func),
es->s_first_error_func,
@@ -2826,7 +2825,7 @@ static void print_daily_error_info(unsigned long arg)
printk("\n");
}
if (es->s_last_error_time) {
- printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+ printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
sb->s_id, le32_to_cpu(es->s_last_error_time),
(int) sizeof(es->s_last_error_func),
es->s_last_error_func,
@@ -3880,38 +3879,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount2;
}
}
-
- /*
- * set up enough so that it can read an inode,
- * and create new inode for buddy allocator
- */
- sbi->s_gdb_count = db_count;
- if (!test_opt(sb, NOLOAD) &&
- EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
- sb->s_op = &ext4_sops;
- else
- sb->s_op = &ext4_nojournal_sops;
-
- ext4_ext_init(sb);
- err = ext4_mb_init(sb);
- if (err) {
- ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
- err);
- goto failed_mount2;
- }
-
if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
- goto failed_mount2a;
+ goto failed_mount2;
}
if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
if (!ext4_fill_flex_info(sb)) {
ext4_msg(sb, KERN_ERR,
"unable to initialize "
"flex_bg meta info!");
- goto failed_mount2a;
+ goto failed_mount2;
}
+ sbi->s_gdb_count = db_count;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
@@ -3946,6 +3926,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_stripe = ext4_get_stripe_size(sbi);
sbi->s_extent_max_zeroout_kb = 32;
+ /*
+ * set up enough so that it can read an inode
+ */
+ if (!test_opt(sb, NOLOAD) &&
+ EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+ sb->s_op = &ext4_sops;
+ else
+ sb->s_op = &ext4_nojournal_sops;
sb->s_export_op = &ext4_export_ops;
sb->s_xattr = ext4_xattr_handlers;
#ifdef CONFIG_QUOTA
@@ -4135,13 +4123,21 @@ no_journal:
if (err) {
ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
"reserved pool", ext4_calculate_resv_clusters(sb));
- goto failed_mount5;
+ goto failed_mount4a;
}
err = ext4_setup_system_zone(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize system "
"zone (%d)", err);
+ goto failed_mount4a;
+ }
+
+ ext4_ext_init(sb);
+ err = ext4_mb_init(sb);
+ if (err) {
+ ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
+ err);
goto failed_mount5;
}
@@ -4218,8 +4214,11 @@ failed_mount8:
failed_mount7:
ext4_unregister_li_request(sb);
failed_mount6:
- ext4_release_system_zone(sb);
+ ext4_mb_release(sb);
failed_mount5:
+ ext4_ext_release(sb);
+ ext4_release_system_zone(sb);
+failed_mount4a:
dput(sb->s_root);
sb->s_root = NULL;
failed_mount4:
@@ -4243,14 +4242,11 @@ failed_mount3:
percpu_counter_destroy(&sbi->s_extent_cache_cnt);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
-failed_mount2a:
- ext4_mb_release(sb);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
ext4_kvfree(sbi->s_group_desc);
failed_mount:
- ext4_ext_release(sb);
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
if (sbi->s_proc) {
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0924521306b4..f8cf619edb5f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -608,8 +608,8 @@ static int __allocate_data_block(struct dnode_of_data *dn)
* b. do not use extent cache for better performance
* c. give the block addresses to blockdev
*/
-static int get_data_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
+static int __get_data_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create, bool fiemap)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
unsigned int blkbits = inode->i_sb->s_blocksize_bits;
@@ -637,7 +637,7 @@ static int get_data_block(struct inode *inode, sector_t iblock,
err = 0;
goto unlock_out;
}
- if (dn.data_blkaddr == NEW_ADDR)
+ if (dn.data_blkaddr == NEW_ADDR && !fiemap)
goto put_out;
if (dn.data_blkaddr != NULL_ADDR) {
@@ -671,7 +671,7 @@ get_next:
err = 0;
goto unlock_out;
}
- if (dn.data_blkaddr == NEW_ADDR)
+ if (dn.data_blkaddr == NEW_ADDR && !fiemap)
goto put_out;
end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
@@ -708,10 +708,23 @@ out:
return err;
}
+static int get_data_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ return __get_data_block(inode, iblock, bh_result, create, false);
+}
+
+static int get_data_block_fiemap(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ return __get_data_block(inode, iblock, bh_result, create, true);
+}
+
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
- return generic_block_fiemap(inode, fieinfo, start, len, get_data_block);
+ return generic_block_fiemap(inode, fieinfo,
+ start, len, get_data_block_fiemap);
}
static int f2fs_read_data_page(struct file *file, struct page *page)
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 966acb039e3b..a4addd72ebbd 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -376,11 +376,11 @@ static struct page *init_inode_metadata(struct inode *inode,
put_error:
f2fs_put_page(page, 1);
+error:
/* once the failed inode becomes a bad inode, i_mode is S_IFREG */
truncate_inode_pages(&inode->i_data, 0);
truncate_blocks(inode, 0);
remove_dirty_dir_inode(inode);
-error:
remove_inode_page(inode);
return ERR_PTR(err);
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e51c732b0dd9..58df97e174d0 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -342,9 +342,6 @@ struct f2fs_sm_info {
struct dirty_seglist_info *dirty_info; /* dirty segment information */
struct curseg_info *curseg_array; /* active segment information */
- struct list_head wblist_head; /* list of under-writeback pages */
- spinlock_t wblist_lock; /* lock for checkpoint */
-
block_t seg0_blkaddr; /* block address of 0'th segment */
block_t main_blkaddr; /* start block address of main area */
block_t ssa_blkaddr; /* start block address of SSA area */
@@ -644,7 +641,8 @@ static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
*/
static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
{
- WARN_ON((nid >= NM_I(sbi)->max_nid));
+ if (unlikely(nid < F2FS_ROOT_INO(sbi)))
+ return -EINVAL;
if (unlikely(nid >= NM_I(sbi)->max_nid))
return -EINVAL;
return 0;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index c58e33075719..7d8b96275092 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -659,16 +659,19 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
off_start = offset & (PAGE_CACHE_SIZE - 1);
off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
+ f2fs_lock_op(sbi);
+
for (index = pg_start; index <= pg_end; index++) {
struct dnode_of_data dn;
- f2fs_lock_op(sbi);
+ if (index == pg_end && !off_end)
+ goto noalloc;
+
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_reserve_block(&dn, index);
- f2fs_unlock_op(sbi);
if (ret)
break;
-
+noalloc:
if (pg_start == pg_end)
new_size = offset + len;
else if (index == pg_start && off_start)
@@ -683,8 +686,9 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
i_size_read(inode) < new_size) {
i_size_write(inode, new_size);
mark_inode_dirty(inode);
- f2fs_write_inode(inode, NULL);
+ update_inode_page(inode);
}
+ f2fs_unlock_op(sbi);
return ret;
}
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index adc622c6bdce..2cf6962f6cc8 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -78,6 +78,7 @@ static int do_read_inode(struct inode *inode)
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);
return -EINVAL;
}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 9138c32aa698..a6bdddc33ce2 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -417,9 +417,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
- down_write(&F2FS_I(old_inode)->i_sem);
- F2FS_I(old_inode)->i_pino = new_dir->i_ino;
- up_write(&F2FS_I(old_inode)->i_sem);
new_inode->i_ctime = CURRENT_TIME;
down_write(&F2FS_I(new_inode)->i_sem);
@@ -448,6 +445,10 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
}
+ down_write(&F2FS_I(old_inode)->i_sem);
+ file_lost_pino(old_inode);
+ up_write(&F2FS_I(old_inode)->i_sem);
+
old_inode->i_ctime = CURRENT_TIME;
mark_inode_dirty(old_inode);
@@ -457,9 +458,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (old_dir != new_dir) {
f2fs_set_link(old_inode, old_dir_entry,
old_dir_page, new_dir);
- down_write(&F2FS_I(old_inode)->i_sem);
- F2FS_I(old_inode)->i_pino = new_dir->i_ino;
- up_write(&F2FS_I(old_inode)->i_sem);
update_inode_page(old_inode);
} else {
kunmap(old_dir_page);
@@ -474,7 +472,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
return 0;
put_out_dir:
- f2fs_put_page(new_page, 1);
+ kunmap(new_page);
+ f2fs_put_page(new_page, 0);
out_dir:
if (old_dir_entry) {
kunmap(old_dir_page);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 9dfb9a042fd2..4b697ccc9b0c 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -42,6 +42,8 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> 12;
res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
} else if (type == DIRTY_DENTS) {
+ if (sbi->sb->s_bdi->dirty_exceeded)
+ return false;
mem_size = get_pages(sbi, F2FS_DIRTY_DENTS);
res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1);
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index f25f0e07e26f..d04613df710a 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -272,14 +272,15 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
return -ENOMEM;
spin_lock_init(&fcc->issue_lock);
init_waitqueue_head(&fcc->flush_wait_queue);
+ sbi->sm_info->cmd_control_info = fcc;
fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(fcc->f2fs_issue_flush)) {
err = PTR_ERR(fcc->f2fs_issue_flush);
kfree(fcc);
+ sbi->sm_info->cmd_control_info = NULL;
return err;
}
- sbi->sm_info->cmd_control_info = fcc;
return err;
}
@@ -1885,8 +1886,6 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
/* init sm info */
sbi->sm_info = sm_info;
- INIT_LIST_HEAD(&sm_info->wblist_head);
- spin_lock_init(&sm_info->wblist_lock);
sm_info->seg0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
sm_info->main_blkaddr = le32_to_cpu(raw_super->main_blkaddr);
sm_info->segment_count = le32_to_cpu(raw_super->segment_count);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index b2b18637cb9e..8f96d9372ade 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -689,9 +689,7 @@ static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *inode;
- if (unlikely(ino < F2FS_ROOT_INO(sbi)))
- return ERR_PTR(-ESTALE);
- if (unlikely(ino >= NM_I(sbi)->max_nid))
+ if (check_nid_range(sbi, ino))
return ERR_PTR(-ESTALE);
/*
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 098f97bdcf1b..ca887314aba9 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -643,9 +643,8 @@ struct fuse_copy_state {
unsigned long seglen;
unsigned long addr;
struct page *pg;
- void *mapaddr;
- void *buf;
unsigned len;
+ unsigned offset;
unsigned move_pages:1;
};
@@ -666,23 +665,17 @@ static void fuse_copy_finish(struct fuse_copy_state *cs)
if (cs->currbuf) {
struct pipe_buffer *buf = cs->currbuf;
- if (!cs->write) {
- kunmap_atomic(cs->mapaddr);
- } else {
- kunmap_atomic(cs->mapaddr);
+ if (cs->write)
buf->len = PAGE_SIZE - cs->len;
- }
cs->currbuf = NULL;
- cs->mapaddr = NULL;
- } else if (cs->mapaddr) {
- kunmap_atomic(cs->mapaddr);
+ } else if (cs->pg) {
if (cs->write) {
flush_dcache_page(cs->pg);
set_page_dirty_lock(cs->pg);
}
put_page(cs->pg);
- cs->mapaddr = NULL;
}
+ cs->pg = NULL;
}
/*
@@ -691,7 +684,7 @@ static void fuse_copy_finish(struct fuse_copy_state *cs)
*/
static int fuse_copy_fill(struct fuse_copy_state *cs)
{
- unsigned long offset;
+ struct page *page;
int err;
unlock_request(cs->fc, cs->req);
@@ -706,14 +699,12 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
BUG_ON(!cs->nr_segs);
cs->currbuf = buf;
- cs->mapaddr = kmap_atomic(buf->page);
+ cs->pg = buf->page;
+ cs->offset = buf->offset;
cs->len = buf->len;
- cs->buf = cs->mapaddr + buf->offset;
cs->pipebufs++;
cs->nr_segs--;
} else {
- struct page *page;
-
if (cs->nr_segs == cs->pipe->buffers)
return -EIO;
@@ -726,8 +717,8 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
buf->len = 0;
cs->currbuf = buf;
- cs->mapaddr = kmap_atomic(page);
- cs->buf = cs->mapaddr;
+ cs->pg = page;
+ cs->offset = 0;
cs->len = PAGE_SIZE;
cs->pipebufs++;
cs->nr_segs++;
@@ -740,14 +731,13 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
cs->iov++;
cs->nr_segs--;
}
- err = get_user_pages_fast(cs->addr, 1, cs->write, &cs->pg);
+ err = get_user_pages_fast(cs->addr, 1, cs->write, &page);
if (err < 0)
return err;
BUG_ON(err != 1);
- offset = cs->addr % PAGE_SIZE;
- cs->mapaddr = kmap_atomic(cs->pg);
- cs->buf = cs->mapaddr + offset;
- cs->len = min(PAGE_SIZE - offset, cs->seglen);
+ cs->pg = page;
+ cs->offset = cs->addr % PAGE_SIZE;
+ cs->len = min(PAGE_SIZE - cs->offset, cs->seglen);
cs->seglen -= cs->len;
cs->addr += cs->len;
}
@@ -760,15 +750,20 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
{
unsigned ncpy = min(*size, cs->len);
if (val) {
+ void *pgaddr = kmap_atomic(cs->pg);
+ void *buf = pgaddr + cs->offset;
+
if (cs->write)
- memcpy(cs->buf, *val, ncpy);
+ memcpy(buf, *val, ncpy);
else
- memcpy(*val, cs->buf, ncpy);
+ memcpy(*val, buf, ncpy);
+
+ kunmap_atomic(pgaddr);
*val += ncpy;
}
*size -= ncpy;
cs->len -= ncpy;
- cs->buf += ncpy;
+ cs->offset += ncpy;
return ncpy;
}
@@ -874,8 +869,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
out_fallback_unlock:
unlock_page(newpage);
out_fallback:
- cs->mapaddr = kmap_atomic(buf->page);
- cs->buf = cs->mapaddr + buf->offset;
+ cs->pg = buf->page;
+ cs->offset = buf->offset;
err = lock_request(cs->fc, cs->req);
if (err)
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 42198359fa1b..0c6048247a34 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -198,7 +198,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
inode = ACCESS_ONCE(entry->d_inode);
if (inode && is_bad_inode(inode))
goto invalid;
- else if (fuse_dentry_time(entry) < get_jiffies_64()) {
+ else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) ||
+ (flags & LOOKUP_REVAL)) {
int err;
struct fuse_entry_out outarg;
struct fuse_req *req;
@@ -814,13 +815,6 @@ static int fuse_rename_common(struct inode *olddir, struct dentry *oldent,
return err;
}
-static int fuse_rename(struct inode *olddir, struct dentry *oldent,
- struct inode *newdir, struct dentry *newent)
-{
- return fuse_rename_common(olddir, oldent, newdir, newent, 0,
- FUSE_RENAME, sizeof(struct fuse_rename_in));
-}
-
static int fuse_rename2(struct inode *olddir, struct dentry *oldent,
struct inode *newdir, struct dentry *newent,
unsigned int flags)
@@ -831,17 +825,30 @@ static int fuse_rename2(struct inode *olddir, struct dentry *oldent,
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
return -EINVAL;
- if (fc->no_rename2 || fc->minor < 23)
- return -EINVAL;
+ if (flags) {
+ if (fc->no_rename2 || fc->minor < 23)
+ return -EINVAL;
- err = fuse_rename_common(olddir, oldent, newdir, newent, flags,
- FUSE_RENAME2, sizeof(struct fuse_rename2_in));
- if (err == -ENOSYS) {
- fc->no_rename2 = 1;
- err = -EINVAL;
+ err = fuse_rename_common(olddir, oldent, newdir, newent, flags,
+ FUSE_RENAME2,
+ sizeof(struct fuse_rename2_in));
+ if (err == -ENOSYS) {
+ fc->no_rename2 = 1;
+ err = -EINVAL;
+ }
+ } else {
+ err = fuse_rename_common(olddir, oldent, newdir, newent, 0,
+ FUSE_RENAME,
+ sizeof(struct fuse_rename_in));
}
+
return err;
+}
+static int fuse_rename(struct inode *olddir, struct dentry *oldent,
+ struct inode *newdir, struct dentry *newent)
+{
+ return fuse_rename2(olddir, oldent, newdir, newent, 0);
}
static int fuse_link(struct dentry *entry, struct inode *newdir,
@@ -985,7 +992,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat,
int err;
bool r;
- if (fi->i_time < get_jiffies_64()) {
+ if (time_before64(fi->i_time, get_jiffies_64())) {
r = true;
err = fuse_do_getattr(inode, stat, file);
} else {
@@ -1171,7 +1178,7 @@ static int fuse_permission(struct inode *inode, int mask)
((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) {
struct fuse_inode *fi = get_fuse_inode(inode);
- if (fi->i_time < get_jiffies_64()) {
+ if (time_before64(fi->i_time, get_jiffies_64())) {
refreshed = true;
err = fuse_perm_getattr(inode, mask);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 6e16dad13e9b..40ac2628ddcf 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1687,7 +1687,7 @@ static int fuse_writepage_locked(struct page *page)
error = -EIO;
req->ff = fuse_write_file_get(fc, fi);
if (!req->ff)
- goto err_free;
+ goto err_nofile;
fuse_write_fill(req, req->ff, page_offset(page), 0);
@@ -1715,6 +1715,8 @@ static int fuse_writepage_locked(struct page *page)
return 0;
+err_nofile:
+ __free_page(tmp_page);
err_free:
fuse_request_free(req);
err:
@@ -1955,8 +1957,8 @@ static int fuse_writepages(struct address_space *mapping,
data.ff = NULL;
err = -ENOMEM;
- data.orig_pages = kzalloc(sizeof(struct page *) *
- FUSE_MAX_PAGES_PER_REQ,
+ data.orig_pages = kcalloc(FUSE_MAX_PAGES_PER_REQ,
+ sizeof(struct page *),
GFP_NOFS);
if (!data.orig_pages)
goto out;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 754dcf23de8a..8474028d7848 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -478,6 +478,17 @@ static const match_table_t tokens = {
{OPT_ERR, NULL}
};
+static int fuse_match_uint(substring_t *s, unsigned int *res)
+{
+ int err = -ENOMEM;
+ char *buf = match_strdup(s);
+ if (buf) {
+ err = kstrtouint(buf, 10, res);
+ kfree(buf);
+ }
+ return err;
+}
+
static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
{
char *p;
@@ -488,6 +499,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
while ((p = strsep(&opt, ",")) != NULL) {
int token;
int value;
+ unsigned uv;
substring_t args[MAX_OPT_ARGS];
if (!*p)
continue;
@@ -511,18 +523,18 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
break;
case OPT_USER_ID:
- if (match_int(&args[0], &value))
+ if (fuse_match_uint(&args[0], &uv))
return 0;
- d->user_id = make_kuid(current_user_ns(), value);
+ d->user_id = make_kuid(current_user_ns(), uv);
if (!uid_valid(d->user_id))
return 0;
d->user_id_present = 1;
break;
case OPT_GROUP_ID:
- if (match_int(&args[0], &value))
+ if (fuse_match_uint(&args[0], &uv))
return 0;
- d->group_id = make_kgid(current_user_ns(), value);
+ d->group_id = make_kgid(current_user_ns(), uv);
if (!gid_valid(d->group_id))
return 0;
d->group_id_present = 1;
@@ -1006,7 +1018,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
sb->s_flags &= ~(MS_NOSEC | MS_I_VERSION);
- if (!parse_fuse_opt((char *) data, &d, is_bdev))
+ if (!parse_fuse_opt(data, &d, is_bdev))
goto err;
if (is_bdev) {
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 4fc3a3046174..26b3f952e6b1 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -981,7 +981,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
int error = 0;
state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
- flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
+ flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT;
mutex_lock(&fp->f_fl_mutex);
@@ -991,7 +991,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
goto out;
flock_lock_file_wait(file,
&(struct file_lock){.fl_type = F_UNLCK});
- gfs2_glock_dq_wait(fl_gh);
+ gfs2_glock_dq(fl_gh);
gfs2_holder_reinit(state, flags, fl_gh);
} else {
error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index c355f7320e44..ee4e04fe60fc 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -731,14 +731,14 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
cachep = gfs2_glock_aspace_cachep;
else
cachep = gfs2_glock_cachep;
- gl = kmem_cache_alloc(cachep, GFP_KERNEL);
+ gl = kmem_cache_alloc(cachep, GFP_NOFS);
if (!gl)
return -ENOMEM;
memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));
if (glops->go_flags & GLOF_LVB) {
- gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_KERNEL);
+ gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_NOFS);
if (!gl->gl_lksb.sb_lvbptr) {
kmem_cache_free(cachep, gl);
return -ENOMEM;
@@ -1404,12 +1404,16 @@ __acquires(&lru_lock)
gl = list_entry(list->next, struct gfs2_glock, gl_lru);
list_del_init(&gl->gl_lru);
if (!spin_trylock(&gl->gl_spin)) {
+add_back_to_lru:
list_add(&gl->gl_lru, &lru_list);
atomic_inc(&lru_count);
continue;
}
+ if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
+ spin_unlock(&gl->gl_spin);
+ goto add_back_to_lru;
+ }
clear_bit(GLF_LRU, &gl->gl_flags);
- spin_unlock(&lru_lock);
gl->gl_lockref.count++;
if (demote_ok(gl))
handle_callback(gl, LM_ST_UNLOCKED, 0, false);
@@ -1417,7 +1421,7 @@ __acquires(&lru_lock)
if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
gl->gl_lockref.count--;
spin_unlock(&gl->gl_spin);
- spin_lock(&lru_lock);
+ cond_resched_lock(&lru_lock);
}
}
@@ -1442,7 +1446,7 @@ static long gfs2_scan_glock_lru(int nr)
gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
/* Test for being demotable */
- if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
+ if (!test_bit(GLF_LOCK, &gl->gl_flags)) {
list_move(&gl->gl_lru, &dispose);
atomic_dec(&lru_count);
freed++;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index fc1100781bbc..2ffc67dce87f 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -234,8 +234,8 @@ static void inode_go_sync(struct gfs2_glock *gl)
* inode_go_inval - prepare a inode glock to be released
* @gl: the glock
* @flags:
- *
- * Normally we invlidate everything, but if we are moving into
+ *
+ * Normally we invalidate everything, but if we are moving into
* LM_ST_DEFERRED from LM_ST_SHARED or LM_ST_EXCLUSIVE then we
* can keep hold of the metadata, since it won't have changed.
*
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 91f274de1246..4fafea1c9ecf 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -1036,8 +1036,8 @@ static int set_recover_size(struct gfs2_sbd *sdp, struct dlm_slot *slots,
new_size = old_size + RECOVER_SIZE_INC;
- submit = kzalloc(new_size * sizeof(uint32_t), GFP_NOFS);
- result = kzalloc(new_size * sizeof(uint32_t), GFP_NOFS);
+ submit = kcalloc(new_size, sizeof(uint32_t), GFP_NOFS);
+ result = kcalloc(new_size, sizeof(uint32_t), GFP_NOFS);
if (!submit || !result) {
kfree(submit);
kfree(result);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index db629d1bd1bd..f4cb9c0d6bbd 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -337,7 +337,7 @@ static bool gfs2_unaligned_extlen(struct gfs2_rbm *rbm, u32 n_unaligned, u32 *le
/**
* gfs2_free_extlen - Return extent length of free blocks
- * @rbm: Starting position
+ * @rrbm: Starting position
* @len: Max length to check
*
* Starting at the block specified by the rbm, see how many free blocks
@@ -2522,7 +2522,7 @@ void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state)
/**
* gfs2_rlist_free - free a resource group list
- * @list: the list of resource groups
+ * @rlist: the list of resource groups
*
*/
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 38cfcf5f6fce..6f0f590cc5a3 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1588,9 +1588,12 @@ int jbd2_journal_stop(handle_t *handle)
* to perform a synchronous write. We do this to detect the
* case where a single process is doing a stream of sync
* writes. No point in waiting for joiners in that case.
+ *
+ * Setting max_batch_time to 0 disables this completely.
*/
pid = current->pid;
- if (handle->h_sync && journal->j_last_sync_writer != pid) {
+ if (handle->h_sync && journal->j_last_sync_writer != pid &&
+ journal->j_max_batch_time) {
u64 commit_time, trans_time;
journal->j_last_sync_writer = pid;
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index d171b98a6cdd..f973ae9b05f1 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -211,6 +211,36 @@ void kernfs_kill_sb(struct super_block *sb)
kernfs_put(root_kn);
}
+/**
+ * kernfs_pin_sb: try to pin the superblock associated with a kernfs_root
+ * @kernfs_root: the kernfs_root in question
+ * @ns: the namespace tag
+ *
+ * Pin the superblock so the superblock won't be destroyed in subsequent
+ * operations. This can be used to block ->kill_sb() which may be useful
+ * for kernfs users which dynamically manage superblocks.
+ *
+ * Returns NULL if there's no superblock associated to this kernfs_root, or
+ * -EINVAL if the superblock is being freed.
+ */
+struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns)
+{
+ struct kernfs_super_info *info;
+ struct super_block *sb = NULL;
+
+ mutex_lock(&kernfs_mutex);
+ list_for_each_entry(info, &root->supers, node) {
+ if (info->ns == ns) {
+ sb = info->sb;
+ if (!atomic_inc_not_zero(&info->sb->s_active))
+ sb = ERR_PTR(-EINVAL);
+ break;
+ }
+ }
+ mutex_unlock(&kernfs_mutex);
+ return sb;
+}
+
void __init kernfs_init(void)
{
kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 8f98138cbc43..f11b9eed0de1 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -756,7 +756,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
spin_unlock(&dreq->lock);
while (!list_empty(&hdr->pages)) {
- bool do_destroy = true;
req = nfs_list_entry(hdr->pages.next);
nfs_list_remove_request(req);
@@ -765,7 +764,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
case NFS_IOHDR_NEED_COMMIT:
kref_get(&req->wb_kref);
nfs_mark_request_commit(req, hdr->lseg, &cinfo);
- do_destroy = false;
}
nfs_unlock_and_release_request(req);
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 82ddbf46660e..f415cbf9f6c3 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -244,6 +244,7 @@ void nfs_pgio_data_release(struct nfs_pgio_data *);
int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_data *,
const struct rpc_call_ops *, int, int);
+void nfs_free_request(struct nfs_page *req);
static inline void nfs_iocounter_init(struct nfs_io_counter *c)
{
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 871d6eda8dba..8f854dde4150 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -247,3 +247,46 @@ const struct xattr_handler *nfs3_xattr_handlers[] = {
&posix_acl_default_xattr_handler,
NULL,
};
+
+static int
+nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data,
+ size_t size, ssize_t *result)
+{
+ struct posix_acl *acl;
+ char *p = data + *result;
+
+ acl = get_acl(inode, type);
+ if (!acl)
+ return 0;
+
+ posix_acl_release(acl);
+
+ *result += strlen(name);
+ *result += 1;
+ if (!size)
+ return 0;
+ if (*result > size)
+ return -ERANGE;
+
+ strcpy(p, name);
+ return 0;
+}
+
+ssize_t
+nfs3_listxattr(struct dentry *dentry, char *data, size_t size)
+{
+ struct inode *inode = dentry->d_inode;
+ ssize_t result = 0;
+ int error;
+
+ error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS,
+ POSIX_ACL_XATTR_ACCESS, data, size, &result);
+ if (error)
+ return error;
+
+ error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT,
+ POSIX_ACL_XATTR_DEFAULT, data, size, &result);
+ if (error)
+ return error;
+ return result;
+}
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index e7daa42bbc86..f0afa291fd58 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -885,7 +885,7 @@ static const struct inode_operations nfs3_dir_inode_operations = {
.getattr = nfs_getattr,
.setattr = nfs_setattr,
#ifdef CONFIG_NFS_V3_ACL
- .listxattr = generic_listxattr,
+ .listxattr = nfs3_listxattr,
.getxattr = generic_getxattr,
.setxattr = generic_setxattr,
.removexattr = generic_removexattr,
@@ -899,7 +899,7 @@ static const struct inode_operations nfs3_file_inode_operations = {
.getattr = nfs_getattr,
.setattr = nfs_setattr,
#ifdef CONFIG_NFS_V3_ACL
- .listxattr = generic_listxattr,
+ .listxattr = nfs3_listxattr,
.getxattr = generic_getxattr,
.setxattr = generic_setxattr,
.removexattr = generic_removexattr,
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index b6ee3a6ee96d..17fab89f6358 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -29,8 +29,6 @@
static struct kmem_cache *nfs_page_cachep;
static const struct rpc_call_ops nfs_pgio_common_ops;
-static void nfs_free_request(struct nfs_page *);
-
static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
{
p->npages = pagecount;
@@ -239,20 +237,28 @@ nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev)
WARN_ON_ONCE(prev == req);
if (!prev) {
+ /* a head request */
req->wb_head = req;
req->wb_this_page = req;
} else {
+ /* a subrequest */
WARN_ON_ONCE(prev->wb_this_page != prev->wb_head);
WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &prev->wb_head->wb_flags));
req->wb_head = prev->wb_head;
req->wb_this_page = prev->wb_this_page;
prev->wb_this_page = req;
+ /* All subrequests take a ref on the head request until
+ * nfs_page_group_destroy is called */
+ kref_get(&req->wb_head->wb_kref);
+
/* grab extra ref if head request has extra ref from
* the write/commit path to handle handoff between write
* and commit lists */
- if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags))
+ if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) {
+ set_bit(PG_INODE_REF, &req->wb_flags);
kref_get(&req->wb_kref);
+ }
}
}
@@ -269,6 +275,10 @@ nfs_page_group_destroy(struct kref *kref)
struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref);
struct nfs_page *tmp, *next;
+ /* subrequests must release the ref on the head request */
+ if (req->wb_head != req)
+ nfs_release_request(req->wb_head);
+
if (!nfs_page_group_sync_on_bit(req, PG_TEARDOWN))
return;
@@ -394,7 +404,7 @@ static void nfs_clear_request(struct nfs_page *req)
*
* Note: Should never be called with the spinlock held!
*/
-static void nfs_free_request(struct nfs_page *req)
+void nfs_free_request(struct nfs_page *req)
{
WARN_ON_ONCE(req->wb_this_page != req);
@@ -925,7 +935,6 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
nfs_pageio_doio(desc);
if (desc->pg_error < 0)
return 0;
- desc->pg_moreio = 0;
if (desc->pg_recoalesce)
return 0;
/* retry add_request for this subreq */
@@ -972,6 +981,7 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
desc->pg_count = 0;
desc->pg_base = 0;
desc->pg_recoalesce = 0;
+ desc->pg_moreio = 0;
while (!list_empty(&head)) {
struct nfs_page *req;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 98ff061ccaf3..5e2f10304548 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -46,6 +46,7 @@ static const struct rpc_call_ops nfs_commit_ops;
static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops;
static const struct nfs_commit_completion_ops nfs_commit_completion_ops;
static const struct nfs_rw_ops nfs_rw_write_ops;
+static void nfs_clear_request_commit(struct nfs_page *req);
static struct kmem_cache *nfs_wdata_cachep;
static mempool_t *nfs_wdata_mempool;
@@ -91,8 +92,15 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
}
+/*
+ * nfs_page_find_head_request_locked - find head request associated with @page
+ *
+ * must be called while holding the inode lock.
+ *
+ * returns matching head request with reference held, or NULL if not found.
+ */
static struct nfs_page *
-nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page)
+nfs_page_find_head_request_locked(struct nfs_inode *nfsi, struct page *page)
{
struct nfs_page *req = NULL;
@@ -104,25 +112,33 @@ nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page)
/* Linearly search the commit list for the correct req */
list_for_each_entry_safe(freq, t, &nfsi->commit_info.list, wb_list) {
if (freq->wb_page == page) {
- req = freq;
+ req = freq->wb_head;
break;
}
}
}
- if (req)
+ if (req) {
+ WARN_ON_ONCE(req->wb_head != req);
+
kref_get(&req->wb_kref);
+ }
return req;
}
-static struct nfs_page *nfs_page_find_request(struct page *page)
+/*
+ * nfs_page_find_head_request - find head request associated with @page
+ *
+ * returns matching head request with reference held, or NULL if not found.
+ */
+static struct nfs_page *nfs_page_find_head_request(struct page *page)
{
struct inode *inode = page_file_mapping(page)->host;
struct nfs_page *req = NULL;
spin_lock(&inode->i_lock);
- req = nfs_page_find_request_locked(NFS_I(inode), page);
+ req = nfs_page_find_head_request_locked(NFS_I(inode), page);
spin_unlock(&inode->i_lock);
return req;
}
@@ -274,36 +290,246 @@ static void nfs_end_page_writeback(struct nfs_page *req)
clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
}
-static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock)
+
+/* nfs_page_group_clear_bits
+ * @req - an nfs request
+ * clears all page group related bits from @req
+ */
+static void
+nfs_page_group_clear_bits(struct nfs_page *req)
+{
+ clear_bit(PG_TEARDOWN, &req->wb_flags);
+ clear_bit(PG_UNLOCKPAGE, &req->wb_flags);
+ clear_bit(PG_UPTODATE, &req->wb_flags);
+ clear_bit(PG_WB_END, &req->wb_flags);
+ clear_bit(PG_REMOVE, &req->wb_flags);
+}
+
+
+/*
+ * nfs_unroll_locks_and_wait - unlock all newly locked reqs and wait on @req
+ *
+ * this is a helper function for nfs_lock_and_join_requests
+ *
+ * @inode - inode associated with request page group, must be holding inode lock
+ * @head - head request of page group, must be holding head lock
+ * @req - request that couldn't lock and needs to wait on the req bit lock
+ * @nonblock - if true, don't actually wait
+ *
+ * NOTE: this must be called holding page_group bit lock and inode spin lock
+ * and BOTH will be released before returning.
+ *
+ * returns 0 on success, < 0 on error.
+ */
+static int
+nfs_unroll_locks_and_wait(struct inode *inode, struct nfs_page *head,
+ struct nfs_page *req, bool nonblock)
+ __releases(&inode->i_lock)
+{
+ struct nfs_page *tmp;
+ int ret;
+
+ /* relinquish all the locks successfully grabbed this run */
+ for (tmp = head ; tmp != req; tmp = tmp->wb_this_page)
+ nfs_unlock_request(tmp);
+
+ WARN_ON_ONCE(test_bit(PG_TEARDOWN, &req->wb_flags));
+
+ /* grab a ref on the request that will be waited on */
+ kref_get(&req->wb_kref);
+
+ nfs_page_group_unlock(head);
+ spin_unlock(&inode->i_lock);
+
+ /* release ref from nfs_page_find_head_request_locked */
+ nfs_release_request(head);
+
+ if (!nonblock)
+ ret = nfs_wait_on_request(req);
+ else
+ ret = -EAGAIN;
+ nfs_release_request(req);
+
+ return ret;
+}
+
+/*
+ * nfs_destroy_unlinked_subrequests - destroy recently unlinked subrequests
+ *
+ * @destroy_list - request list (using wb_this_page) terminated by @old_head
+ * @old_head - the old head of the list
+ *
+ * All subrequests must be locked and removed from all lists, so at this point
+ * they are only "active" in this function, and possibly in nfs_wait_on_request
+ * with a reference held by some other context.
+ */
+static void
+nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list,
+ struct nfs_page *old_head)
+{
+ while (destroy_list) {
+ struct nfs_page *subreq = destroy_list;
+
+ destroy_list = (subreq->wb_this_page == old_head) ?
+ NULL : subreq->wb_this_page;
+
+ WARN_ON_ONCE(old_head != subreq->wb_head);
+
+ /* make sure old group is not used */
+ subreq->wb_head = subreq;
+ subreq->wb_this_page = subreq;
+
+ nfs_clear_request_commit(subreq);
+
+ /* subreq is now totally disconnected from page group or any
+ * write / commit lists. last chance to wake any waiters */
+ nfs_unlock_request(subreq);
+
+ if (!test_bit(PG_TEARDOWN, &subreq->wb_flags)) {
+ /* release ref on old head request */
+ nfs_release_request(old_head);
+
+ nfs_page_group_clear_bits(subreq);
+
+ /* release the PG_INODE_REF reference */
+ if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags))
+ nfs_release_request(subreq);
+ else
+ WARN_ON_ONCE(1);
+ } else {
+ WARN_ON_ONCE(test_bit(PG_CLEAN, &subreq->wb_flags));
+ /* zombie requests have already released the last
+ * reference and were waiting on the rest of the
+ * group to complete. Since it's no longer part of a
+ * group, simply free the request */
+ nfs_page_group_clear_bits(subreq);
+ nfs_free_request(subreq);
+ }
+ }
+}
+
+/*
+ * nfs_lock_and_join_requests - join all subreqs to the head req and return
+ * a locked reference, cancelling any pending
+ * operations for this page.
+ *
+ * @page - the page used to lookup the "page group" of nfs_page structures
+ * @nonblock - if true, don't block waiting for request locks
+ *
+ * This function joins all sub requests to the head request by first
+ * locking all requests in the group, cancelling any pending operations
+ * and finally updating the head request to cover the whole range covered by
+ * the (former) group. All subrequests are removed from any write or commit
+ * lists, unlinked from the group and destroyed.
+ *
+ * Returns a locked, referenced pointer to the head request - which after
+ * this call is guaranteed to be the only request associated with the page.
+ * Returns NULL if no requests are found for @page, or a ERR_PTR if an
+ * error was encountered.
+ */
+static struct nfs_page *
+nfs_lock_and_join_requests(struct page *page, bool nonblock)
{
struct inode *inode = page_file_mapping(page)->host;
- struct nfs_page *req;
+ struct nfs_page *head, *subreq;
+ struct nfs_page *destroy_list = NULL;
+ unsigned int total_bytes;
int ret;
+try_again:
+ total_bytes = 0;
+
+ WARN_ON_ONCE(destroy_list);
+
spin_lock(&inode->i_lock);
- for (;;) {
- req = nfs_page_find_request_locked(NFS_I(inode), page);
- if (req == NULL)
- break;
- if (nfs_lock_request(req))
- break;
- /* Note: If we hold the page lock, as is the case in nfs_writepage,
- * then the call to nfs_lock_request() will always
- * succeed provided that someone hasn't already marked the
- * request as dirty (in which case we don't care).
- */
+
+ /*
+ * A reference is taken only on the head request which acts as a
+ * reference to the whole page group - the group will not be destroyed
+ * until the head reference is released.
+ */
+ head = nfs_page_find_head_request_locked(NFS_I(inode), page);
+
+ if (!head) {
spin_unlock(&inode->i_lock);
- if (!nonblock)
- ret = nfs_wait_on_request(req);
- else
- ret = -EAGAIN;
- nfs_release_request(req);
- if (ret != 0)
+ return NULL;
+ }
+
+ /* lock each request in the page group */
+ nfs_page_group_lock(head);
+ subreq = head;
+ do {
+ /*
+ * Subrequests are always contiguous, non overlapping
+ * and in order. If not, it's a programming error.
+ */
+ WARN_ON_ONCE(subreq->wb_offset !=
+ (head->wb_offset + total_bytes));
+
+ /* keep track of how many bytes this group covers */
+ total_bytes += subreq->wb_bytes;
+
+ if (!nfs_lock_request(subreq)) {
+ /* releases page group bit lock and
+ * inode spin lock and all references */
+ ret = nfs_unroll_locks_and_wait(inode, head,
+ subreq, nonblock);
+
+ if (ret == 0)
+ goto try_again;
+
return ERR_PTR(ret);
- spin_lock(&inode->i_lock);
+ }
+
+ subreq = subreq->wb_this_page;
+ } while (subreq != head);
+
+ /* Now that all requests are locked, make sure they aren't on any list.
+ * Commit list removal accounting is done after locks are dropped */
+ subreq = head;
+ do {
+ nfs_list_remove_request(subreq);
+ subreq = subreq->wb_this_page;
+ } while (subreq != head);
+
+ /* unlink subrequests from head, destroy them later */
+ if (head->wb_this_page != head) {
+ /* destroy list will be terminated by head */
+ destroy_list = head->wb_this_page;
+ head->wb_this_page = head;
+
+ /* change head request to cover whole range that
+ * the former page group covered */
+ head->wb_bytes = total_bytes;
}
+
+ /*
+ * prepare head request to be added to new pgio descriptor
+ */
+ nfs_page_group_clear_bits(head);
+
+ /*
+ * some part of the group was still on the inode list - otherwise
+ * the group wouldn't be involved in async write.
+ * grab a reference for the head request, iff it needs one.
+ */
+ if (!test_and_set_bit(PG_INODE_REF, &head->wb_flags))
+ kref_get(&head->wb_kref);
+
+ nfs_page_group_unlock(head);
+
+ /* drop lock to clear_request_commit the head req and clean up
+ * requests on destroy list */
spin_unlock(&inode->i_lock);
- return req;
+
+ nfs_destroy_unlinked_subrequests(destroy_list, head);
+
+ /* clean up commit list state */
+ nfs_clear_request_commit(head);
+
+ /* still holds ref on head from nfs_page_find_head_request_locked
+ * and still has lock on head from lock loop */
+ return head;
}
/*
@@ -316,7 +542,7 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req;
int ret = 0;
- req = nfs_find_and_lock_request(page, nonblock);
+ req = nfs_lock_and_join_requests(page, nonblock);
if (!req)
goto out;
ret = PTR_ERR(req);
@@ -448,7 +674,9 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
set_page_private(req->wb_page, (unsigned long)req);
}
nfsi->npages++;
- set_bit(PG_INODE_REF, &req->wb_flags);
+ /* this a head request for a page group - mark it as having an
+ * extra reference so sub groups can follow suit */
+ WARN_ON(test_and_set_bit(PG_INODE_REF, &req->wb_flags));
kref_get(&req->wb_kref);
spin_unlock(&inode->i_lock);
}
@@ -474,7 +702,9 @@ static void nfs_inode_remove_request(struct nfs_page *req)
nfsi->npages--;
spin_unlock(&inode->i_lock);
}
- nfs_release_request(req);
+
+ if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags))
+ nfs_release_request(req);
}
static void
@@ -638,7 +868,6 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
{
struct nfs_commit_info cinfo;
unsigned long bytes = 0;
- bool do_destroy;
if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
goto out;
@@ -668,7 +897,6 @@ remove_req:
next:
nfs_unlock_request(req);
nfs_end_page_writeback(req);
- do_destroy = !test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags);
nfs_release_request(req);
}
out:
@@ -769,7 +997,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
spin_lock(&inode->i_lock);
for (;;) {
- req = nfs_page_find_request_locked(NFS_I(inode), page);
+ req = nfs_page_find_head_request_locked(NFS_I(inode), page);
if (req == NULL)
goto out_unlock;
@@ -877,7 +1105,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
* dropped page.
*/
do {
- req = nfs_page_find_request(page);
+ req = nfs_page_find_head_request(page);
if (req == NULL)
return 0;
l_ctx = req->wb_lock_context;
@@ -1569,27 +1797,28 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
struct nfs_page *req;
int ret = 0;
- for (;;) {
- wait_on_page_writeback(page);
- req = nfs_page_find_request(page);
- if (req == NULL)
- break;
- if (nfs_lock_request(req)) {
- nfs_clear_request_commit(req);
- nfs_inode_remove_request(req);
- /*
- * In case nfs_inode_remove_request has marked the
- * page as being dirty
- */
- cancel_dirty_page(page, PAGE_CACHE_SIZE);
- nfs_unlock_and_release_request(req);
- break;
- }
- ret = nfs_wait_on_request(req);
- nfs_release_request(req);
- if (ret < 0)
- break;
+ wait_on_page_writeback(page);
+
+ /* blocking call to cancel all requests and join to a single (head)
+ * request */
+ req = nfs_lock_and_join_requests(page, false);
+
+ if (IS_ERR(req)) {
+ ret = PTR_ERR(req);
+ } else if (req) {
+ /* all requests from this page have been cancelled by
+ * nfs_lock_and_join_requests, so just remove the head
+ * request from the inode / page_private pointer and
+ * release it */
+ nfs_inode_remove_request(req);
+ /*
+ * In case nfs_inode_remove_request has marked the
+ * page as being dirty
+ */
+ cancel_dirty_page(page, PAGE_CACHE_SIZE);
+ nfs_unlock_and_release_request(req);
}
+
return ret;
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2fc7abebeb9b..b56b1cc02718 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2641,7 +2641,7 @@ nfsd4_encode_rdattr_error(struct xdr_stream *xdr, __be32 nfserr)
{
__be32 *p;
- p = xdr_reserve_space(xdr, 6);
+ p = xdr_reserve_space(xdr, 20);
if (!p)
return NULL;
*p++ = htonl(2);
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 9cd5f63715c0..7f30bdc57d13 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -702,6 +702,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
struct dquot *dquot;
unsigned long freed = 0;
+ spin_lock(&dq_list_lock);
head = free_dquots.prev;
while (head != &free_dquots && sc->nr_to_scan) {
dquot = list_entry(head, struct dquot, dq_free);
@@ -713,6 +714,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
freed++;
head = free_dquots.prev;
}
+ spin_unlock(&dq_list_lock);
return freed;
}
diff --git a/fs/xattr.c b/fs/xattr.c
index 3377dff18404..c69e6d43a0d2 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -843,7 +843,7 @@ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size)
/* wrap around? */
len = sizeof(*new_xattr) + size;
- if (len <= sizeof(*new_xattr))
+ if (len < sizeof(*new_xattr))
return NULL;
new_xattr = kmalloc(len, GFP_KERNEL);
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 96175df211b1..75c3fe5f3d9d 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -4298,8 +4298,8 @@ xfs_bmapi_delay(
}
-int
-__xfs_bmapi_allocate(
+static int
+xfs_bmapi_allocate(
struct xfs_bmalloca *bma)
{
struct xfs_mount *mp = bma->ip->i_mount;
@@ -4578,9 +4578,6 @@ xfs_bmapi_write(
bma.flist = flist;
bma.firstblock = firstblock;
- if (flags & XFS_BMAPI_STACK_SWITCH)
- bma.stack_switch = 1;
-
while (bno < end && n < *nmap) {
inhole = eof || bma.got.br_startoff > bno;
wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index 38ba36e9b2f0..b879ca56a64c 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -77,7 +77,6 @@ typedef struct xfs_bmap_free
* from written to unwritten, otherwise convert from unwritten to written.
*/
#define XFS_BMAPI_CONVERT 0x040
-#define XFS_BMAPI_STACK_SWITCH 0x080
#define XFS_BMAPI_FLAGS \
{ XFS_BMAPI_ENTIRE, "ENTIRE" }, \
@@ -86,8 +85,7 @@ typedef struct xfs_bmap_free
{ XFS_BMAPI_PREALLOC, "PREALLOC" }, \
{ XFS_BMAPI_IGSTATE, "IGSTATE" }, \
{ XFS_BMAPI_CONTIG, "CONTIG" }, \
- { XFS_BMAPI_CONVERT, "CONVERT" }, \
- { XFS_BMAPI_STACK_SWITCH, "STACK_SWITCH" }
+ { XFS_BMAPI_CONVERT, "CONVERT" }
static inline int xfs_bmapi_aflag(int w)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 703b3ec1796c..64731ef3324d 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -249,59 +249,6 @@ xfs_bmap_rtalloc(
}
/*
- * Stack switching interfaces for allocation
- */
-static void
-xfs_bmapi_allocate_worker(
- struct work_struct *work)
-{
- struct xfs_bmalloca *args = container_of(work,
- struct xfs_bmalloca, work);
- unsigned long pflags;
- unsigned long new_pflags = PF_FSTRANS;
-
- /*
- * we are in a transaction context here, but may also be doing work
- * in kswapd context, and hence we may need to inherit that state
- * temporarily to ensure that we don't block waiting for memory reclaim
- * in any way.
- */
- if (args->kswapd)
- new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
-
- current_set_flags_nested(&pflags, new_pflags);
-
- args->result = __xfs_bmapi_allocate(args);
- complete(args->done);
-
- current_restore_flags_nested(&pflags, new_pflags);
-}
-
-/*
- * Some allocation requests often come in with little stack to work on. Push
- * them off to a worker thread so there is lots of stack to use. Otherwise just
- * call directly to avoid the context switch overhead here.
- */
-int
-xfs_bmapi_allocate(
- struct xfs_bmalloca *args)
-{
- DECLARE_COMPLETION_ONSTACK(done);
-
- if (!args->stack_switch)
- return __xfs_bmapi_allocate(args);
-
-
- args->done = &done;
- args->kswapd = current_is_kswapd();
- INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
- queue_work(xfs_alloc_wq, &args->work);
- wait_for_completion(&done);
- destroy_work_on_stack(&args->work);
- return args->result;
-}
-
-/*
* Check if the endoff is outside the last extent. If so the caller will grow
* the allocation to a stripe unit boundary. All offsets are considered outside
* the end of file for an empty fork, so 1 is returned in *eof in that case.
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 075f72232a64..2fdb72d2c908 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -55,8 +55,6 @@ struct xfs_bmalloca {
bool userdata;/* set if is user data */
bool aeof; /* allocated space at eof */
bool conv; /* overwriting unwritten extents */
- bool stack_switch;
- bool kswapd; /* allocation in kswapd context */
int flags;
struct completion *done;
struct work_struct work;
@@ -66,8 +64,6 @@ struct xfs_bmalloca {
int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
int *committed);
int xfs_bmap_rtalloc(struct xfs_bmalloca *ap);
-int xfs_bmapi_allocate(struct xfs_bmalloca *args);
-int __xfs_bmapi_allocate(struct xfs_bmalloca *args);
int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff,
int whichfork, int *eof);
int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index bf810c6baf2b..cf893bc1e373 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -33,6 +33,7 @@
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
+#include "xfs_alloc.h"
/*
* Cursor allocation zone.
@@ -2323,7 +2324,7 @@ error1:
* record (to be inserted into parent).
*/
STATIC int /* error */
-xfs_btree_split(
+__xfs_btree_split(
struct xfs_btree_cur *cur,
int level,
union xfs_btree_ptr *ptrp,
@@ -2503,6 +2504,85 @@ error0:
return error;
}
+struct xfs_btree_split_args {
+ struct xfs_btree_cur *cur;
+ int level;
+ union xfs_btree_ptr *ptrp;
+ union xfs_btree_key *key;
+ struct xfs_btree_cur **curp;
+ int *stat; /* success/failure */
+ int result;
+ bool kswapd; /* allocation in kswapd context */
+ struct completion *done;
+ struct work_struct work;
+};
+
+/*
+ * Stack switching interfaces for allocation
+ */
+static void
+xfs_btree_split_worker(
+ struct work_struct *work)
+{
+ struct xfs_btree_split_args *args = container_of(work,
+ struct xfs_btree_split_args, work);
+ unsigned long pflags;
+ unsigned long new_pflags = PF_FSTRANS;
+
+ /*
+ * we are in a transaction context here, but may also be doing work
+ * in kswapd context, and hence we may need to inherit that state
+ * temporarily to ensure that we don't block waiting for memory reclaim
+ * in any way.
+ */
+ if (args->kswapd)
+ new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
+
+ current_set_flags_nested(&pflags, new_pflags);
+
+ args->result = __xfs_btree_split(args->cur, args->level, args->ptrp,
+ args->key, args->curp, args->stat);
+ complete(args->done);
+
+ current_restore_flags_nested(&pflags, new_pflags);
+}
+
+/*
+ * BMBT split requests often come in with little stack to work on. Push
+ * them off to a worker thread so there is lots of stack to use. For the other
+ * btree types, just call directly to avoid the context switch overhead here.
+ */
+STATIC int /* error */
+xfs_btree_split(
+ struct xfs_btree_cur *cur,
+ int level,
+ union xfs_btree_ptr *ptrp,
+ union xfs_btree_key *key,
+ struct xfs_btree_cur **curp,
+ int *stat) /* success/failure */
+{
+ struct xfs_btree_split_args args;
+ DECLARE_COMPLETION_ONSTACK(done);
+
+ if (cur->bc_btnum != XFS_BTNUM_BMAP)
+ return __xfs_btree_split(cur, level, ptrp, key, curp, stat);
+
+ args.cur = cur;
+ args.level = level;
+ args.ptrp = ptrp;
+ args.key = key;
+ args.curp = curp;
+ args.stat = stat;
+ args.done = &done;
+ args.kswapd = current_is_kswapd();
+ INIT_WORK_ONSTACK(&args.work, xfs_btree_split_worker);
+ queue_work(xfs_alloc_wq, &args.work);
+ wait_for_completion(&done);
+ destroy_work_on_stack(&args.work);
+ return args.result;
+}
+
+
/*
* Copy the old inode root contents into a real block and make the
* broot point to it.
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 6c5eb4c551e3..6d3ec2b6ee29 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -749,8 +749,7 @@ xfs_iomap_write_allocate(
* pointer that the caller gave to us.
*/
error = xfs_bmapi_write(tp, ip, map_start_fsb,
- count_fsb,
- XFS_BMAPI_STACK_SWITCH,
+ count_fsb, 0,
&first_block, 1,
imap, &nimaps, &free_list);
if (error)
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index c3453b11f563..7703fa6770ff 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -483,10 +483,16 @@ xfs_sb_quota_to_disk(
}
/*
- * GQUOTINO and PQUOTINO cannot be used together in versions
- * of superblock that do not have pquotino. from->sb_flags
- * tells us which quota is active and should be copied to
- * disk.
+ * GQUOTINO and PQUOTINO cannot be used together in versions of
+ * superblock that do not have pquotino. from->sb_flags tells us which
+ * quota is active and should be copied to disk. If neither are active,
+ * make sure we write NULLFSINO to the sb_gquotino field as a quota
+ * inode value of "0" is invalid when the XFS_SB_VERSION_QUOTA feature
+ * bit is set.
+ *
+ * Note that we don't need to handle the sb_uquotino or sb_pquotino here
+ * as they do not require any translation. Hence the main sb field loop
+ * will write them appropriately from the in-core superblock.
*/
if ((*fields & XFS_SB_GQUOTINO) &&
(from->sb_qflags & XFS_GQUOTA_ACCT))
@@ -494,6 +500,17 @@ xfs_sb_quota_to_disk(
else if ((*fields & XFS_SB_PQUOTINO) &&
(from->sb_qflags & XFS_PQUOTA_ACCT))
to->sb_gquotino = cpu_to_be64(from->sb_pquotino);
+ else {
+ /*
+ * We can't rely on just the fields being logged to tell us
+ * that it is safe to write NULLFSINO - we should only do that
+ * if quotas are not actually enabled. Hence only write
+ * NULLFSINO if both in-core quota inodes are NULL.
+ */
+ if (from->sb_gquotino == NULLFSINO &&
+ from->sb_pquotino == NULLFSINO)
+ to->sb_gquotino = cpu_to_be64(NULLFSINO);
+ }
*fields &= ~(XFS_SB_PQUOTINO | XFS_SB_GQUOTINO);
}