aboutsummaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/afs/dir.c10
-rw-r--r--fs/f2fs/checkpoint.c6
-rw-r--r--fs/f2fs/compress.c36
-rw-r--r--fs/f2fs/data.c72
-rw-r--r--fs/f2fs/f2fs.h48
-rw-r--r--fs/f2fs/file.c28
-rw-r--r--fs/f2fs/gc.c8
-rw-r--r--fs/f2fs/node.c2
-rw-r--r--fs/f2fs/segment.c59
-rw-r--r--fs/f2fs/super.c13
-rw-r--r--fs/fhandle.c2
-rw-r--r--fs/nfs/nfs42.h7
-rw-r--r--fs/nfs/nfs4proc.c16
-rw-r--r--fs/nfs/nfsroot.c4
-rw-r--r--fs/quota/dquot.c226
-rw-r--r--fs/select.c2
16 files changed, 314 insertions, 225 deletions
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index c4e22e9f7a66..cec18f9f8bd7 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -492,16 +492,6 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode,
continue;
}
- /* Don't expose silly rename entries to userspace. */
- if (nlen > 6 &&
- dire->u.name[0] == '.' &&
- ctx->actor != afs_lookup_filldir &&
- ctx->actor != afs_lookup_one_filldir &&
- memcmp(dire->u.name, ".__afs", 6) == 0) {
- ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent);
- continue;
- }
-
/* found the next entry */
if (!dir_emit(ctx, dire->u.name, nlen,
ntohl(dire->u.vnode),
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index d6ae6de35af2..7d3e7418d8fd 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -66,7 +66,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
.old_blkaddr = index,
.new_blkaddr = index,
.encrypted_page = NULL,
- .is_por = !is_meta,
+ .is_por = !is_meta ? 1 : 0,
};
int err;
@@ -229,8 +229,8 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
.op = REQ_OP_READ,
.op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD,
.encrypted_page = NULL,
- .in_list = false,
- .is_por = (type == META_POR),
+ .in_list = 0,
+ .is_por = (type == META_POR) ? 1 : 0,
};
struct blk_plug plug;
int err;
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 7b4479d5b531..88799c6ebd7d 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -1233,10 +1233,11 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
.page = NULL,
.encrypted_page = NULL,
.compressed_page = NULL,
- .submitted = false,
+ .submitted = 0,
.io_type = io_type,
.io_wbc = wbc,
- .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode),
+ .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode) ?
+ 1 : 0,
};
struct dnode_of_data dn;
struct node_info ni;
@@ -1444,12 +1445,14 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page)
}
static int f2fs_write_raw_pages(struct compress_ctx *cc,
- int *submitted,
+ int *submitted_p,
struct writeback_control *wbc,
enum iostat_type io_type)
{
struct address_space *mapping = cc->inode->i_mapping;
- int _submitted, compr_blocks, ret, i;
+ struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
+ int submitted, compr_blocks, i;
+ int ret = 0;
compr_blocks = f2fs_compressed_blocks(cc);
@@ -1464,6 +1467,10 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc,
if (compr_blocks < 0)
return compr_blocks;
+ /* overwrite compressed cluster w/ normal cluster */
+ if (compr_blocks > 0)
+ f2fs_lock_op(sbi);
+
for (i = 0; i < cc->cluster_size; i++) {
if (!cc->rpages[i])
continue;
@@ -1488,7 +1495,7 @@ continue_unlock:
if (!clear_page_dirty_for_io(cc->rpages[i]))
goto continue_unlock;
- ret = f2fs_write_single_data_page(cc->rpages[i], &_submitted,
+ ret = f2fs_write_single_data_page(cc->rpages[i], &submitted,
NULL, NULL, wbc, io_type,
compr_blocks, false);
if (ret) {
@@ -1496,28 +1503,29 @@ continue_unlock:
unlock_page(cc->rpages[i]);
ret = 0;
} else if (ret == -EAGAIN) {
+ ret = 0;
/*
* for quota file, just redirty left pages to
* avoid deadlock caused by cluster update race
* from foreground operation.
*/
if (IS_NOQUOTA(cc->inode))
- return 0;
- ret = 0;
- cond_resched();
- congestion_wait(BLK_RW_ASYNC,
- DEFAULT_IO_TIMEOUT);
+ goto out;
+ f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
goto retry_write;
}
- return ret;
+ goto out;
}
- *submitted += _submitted;
+ *submitted_p += submitted;
}
- f2fs_balance_fs(F2FS_M_SB(mapping), true);
+out:
+ if (compr_blocks > 0)
+ f2fs_unlock_op(sbi);
- return 0;
+ f2fs_balance_fs(sbi, true);
+ return ret;
}
int f2fs_write_multi_pages(struct compress_ctx *cc,
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 73a7906a49b1..a8e99da8edc1 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -932,7 +932,7 @@ next:
bio_page = fio->page;
/* set submitted = true as a return value */
- fio->submitted = true;
+ fio->submitted = 1;
inc_page_count(sbi, WB_DATA_TYPE(bio_page));
@@ -948,7 +948,7 @@ alloc_new:
(fio->type == DATA || fio->type == NODE) &&
fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
dec_page_count(sbi, WB_DATA_TYPE(bio_page));
- fio->retry = true;
+ fio->retry = 1;
goto skip;
}
io->bio = __bio_alloc(fio, BIO_MAX_VECS);
@@ -1467,10 +1467,15 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
struct extent_info ei = {0, };
block_t blkaddr;
unsigned int start_pgofs;
+ int bidx = 0;
if (!maxblocks)
return 0;
+ map->m_bdev = inode->i_sb->s_bdev;
+ map->m_multidev_dio =
+ f2fs_allow_multi_device_dio(F2FS_I_SB(inode), flag);
+
map->m_len = 0;
map->m_flags = 0;
@@ -1493,6 +1498,21 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
if (flag == F2FS_GET_BLOCK_DIO)
f2fs_wait_on_block_writeback_range(inode,
map->m_pblk, map->m_len);
+
+ if (map->m_multidev_dio) {
+ block_t blk_addr = map->m_pblk;
+
+ bidx = f2fs_target_device_index(sbi, map->m_pblk);
+
+ map->m_bdev = FDEV(bidx).bdev;
+ map->m_pblk -= FDEV(bidx).start_blk;
+ map->m_len = min(map->m_len,
+ FDEV(bidx).end_blk + 1 - map->m_pblk);
+
+ if (map->m_may_create)
+ f2fs_update_device_state(sbi, inode->i_ino,
+ blk_addr, map->m_len);
+ }
goto out;
}
@@ -1611,6 +1631,9 @@ next_block:
if (flag == F2FS_GET_BLOCK_PRE_AIO)
goto skip;
+ if (map->m_multidev_dio)
+ bidx = f2fs_target_device_index(sbi, blkaddr);
+
if (map->m_len == 0) {
/* preallocated unwritten block should be mapped for fiemap. */
if (blkaddr == NEW_ADDR)
@@ -1619,10 +1642,15 @@ next_block:
map->m_pblk = blkaddr;
map->m_len = 1;
+
+ if (map->m_multidev_dio)
+ map->m_bdev = FDEV(bidx).bdev;
} else if ((map->m_pblk != NEW_ADDR &&
blkaddr == (map->m_pblk + ofs)) ||
(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
flag == F2FS_GET_BLOCK_PRE_DIO) {
+ if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev)
+ goto sync_out;
ofs++;
map->m_len++;
} else {
@@ -1675,11 +1703,31 @@ skip:
sync_out:
- /* for hardware encryption, but to avoid potential issue in future */
- if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED)
+ if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) {
+ /*
+ * for hardware encryption, but to avoid potential issue
+ * in future
+ */
f2fs_wait_on_block_writeback_range(inode,
map->m_pblk, map->m_len);
+ if (map->m_multidev_dio) {
+ block_t blk_addr = map->m_pblk;
+
+ bidx = f2fs_target_device_index(sbi, map->m_pblk);
+
+ map->m_bdev = FDEV(bidx).bdev;
+ map->m_pblk -= FDEV(bidx).start_blk;
+
+ if (map->m_may_create)
+ f2fs_update_device_state(sbi, inode->i_ino,
+ blk_addr, map->m_len);
+
+ f2fs_bug_on(sbi, blk_addr + map->m_len >
+ FDEV(bidx).end_blk + 1);
+ }
+ }
+
if (flag == F2FS_GET_BLOCK_PRECACHE) {
if (map->m_flags & F2FS_MAP_MAPPED) {
unsigned int ofs = start_pgofs - map->m_lblk;
@@ -1698,7 +1746,7 @@ unlock_out:
f2fs_balance_fs(sbi, dn.node_changed);
}
out:
- trace_f2fs_map_blocks(inode, map, err);
+ trace_f2fs_map_blocks(inode, map, create, flag, err);
return err;
}
@@ -1757,6 +1805,9 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
bh->b_size = blks_to_bytes(inode, map.m_len);
+
+ if (map.m_multidev_dio)
+ bh->b_bdev = map.m_bdev;
}
return err;
}
@@ -2748,9 +2799,10 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
.old_blkaddr = NULL_ADDR,
.page = page,
.encrypted_page = NULL,
- .submitted = false,
+ .submitted = 0,
.compr_blocks = compr_blocks,
- .need_lock = LOCK_RETRY,
+ .need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY,
+ .post_read = f2fs_post_read_required(inode) ? 1 : 0,
.io_type = io_type,
.io_wbc = wbc,
.bio = bio,
@@ -2834,6 +2886,7 @@ write:
if (err == -EAGAIN) {
err = f2fs_do_write_data_page(&fio);
if (err == -EAGAIN) {
+ f2fs_bug_on(sbi, compr_blocks);
fio.need_lock = LOCK_REQ;
err = f2fs_do_write_data_page(&fio);
}
@@ -2878,7 +2931,7 @@ out:
}
if (submitted)
- *submitted = fio.submitted ? 1 : 0;
+ *submitted = fio.submitted;
return 0;
@@ -3104,8 +3157,7 @@ result:
} else if (ret == -EAGAIN) {
ret = 0;
if (wbc->sync_mode == WB_SYNC_ALL) {
- cond_resched();
- congestion_wait(BLK_RW_ASYNC,
+ f2fs_io_schedule_timeout(
DEFAULT_IO_TIMEOUT);
goto retry_write;
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 835ef98643bd..647d53df6a3d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -622,6 +622,7 @@ struct extent_tree {
F2FS_MAP_UNWRITTEN)
struct f2fs_map_blocks {
+ struct block_device *m_bdev; /* for multi-device dio */
block_t m_pblk;
block_t m_lblk;
unsigned int m_len;
@@ -630,6 +631,7 @@ struct f2fs_map_blocks {
pgoff_t *m_next_extent; /* point to next possible extent */
int m_seg_type;
bool m_may_create; /* indicate it is from write path */
+ bool m_multidev_dio; /* indicate it allows multi-device dio */
};
/* for flag in get_data_block */
@@ -1168,18 +1170,19 @@ struct f2fs_io_info {
struct page *encrypted_page; /* encrypted page */
struct page *compressed_page; /* compressed page */
struct list_head list; /* serialize IOs */
- bool submitted; /* indicate IO submission */
- int need_lock; /* indicate we need to lock cp_rwsem */
- bool in_list; /* indicate fio is in io_list */
- bool is_por; /* indicate IO is from recovery or not */
- bool retry; /* need to reallocate block address */
- int compr_blocks; /* # of compressed block addresses */
- bool encrypted; /* indicate file is encrypted */
+ unsigned int compr_blocks; /* # of compressed block addresses */
+ unsigned int need_lock:8; /* indicate we need to lock cp_rwsem */
+ unsigned int version:8; /* version of the node */
+ unsigned int submitted:1; /* indicate IO submission */
+ unsigned int in_list:1; /* indicate fio is in io_list */
+ unsigned int is_por:1; /* indicate IO is from recovery or not */
+ unsigned int retry:1; /* need to reallocate block address */
+ unsigned int encrypted:1; /* indicate file is encrypted */
+ unsigned int post_read:1; /* require post read */
enum iostat_type io_type; /* io type */
struct writeback_control *io_wbc; /* writeback control */
struct bio **bio; /* bio for ipu */
sector_t *last_block; /* last block number in bio */
- unsigned char version; /* version of the node */
};
struct bio_entry {
@@ -1736,12 +1739,15 @@ struct f2fs_sb_info {
/* For shrinker support */
struct list_head s_list;
+ struct mutex umount_mutex;
+ unsigned int shrinker_run_no;
+
+ /* For multi devices */
int s_ndevs; /* number of devices */
struct f2fs_dev_info *devs; /* for device list */
unsigned int dirty_device; /* for checkpoint data flush */
spinlock_t dev_lock; /* protect dirty_device */
- struct mutex umount_mutex;
- unsigned int shrinker_run_no;
+ bool aligned_blksize; /* all devices has the same logical blksize */
/* For write statistics */
u64 sectors_written_start;
@@ -3517,6 +3523,8 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type,
struct f2fs_io_info *fio);
+void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
+ block_t blkaddr, unsigned int blkcnt);
void f2fs_wait_on_page_writeback(struct page *page,
enum page_type type, bool ordered, bool locked);
void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
@@ -4334,6 +4342,16 @@ static inline int block_unaligned_IO(struct inode *inode,
return align & blocksize_mask;
}
+static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi,
+ int flag)
+{
+ if (!f2fs_is_multi_device(sbi))
+ return false;
+ if (flag != F2FS_GET_BLOCK_DIO)
+ return false;
+ return sbi->aligned_blksize;
+}
+
static inline bool f2fs_force_buffered_io(struct inode *inode,
struct kiocb *iocb, struct iov_iter *iter)
{
@@ -4342,7 +4360,9 @@ static inline bool f2fs_force_buffered_io(struct inode *inode,
if (f2fs_post_read_required(inode))
return true;
- if (f2fs_is_multi_device(sbi))
+
+ /* disallow direct IO if any of devices has unaligned blksize */
+ if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize)
return true;
/*
* for blkzoned device, fallback direct IO to buffered IO, so
@@ -4393,6 +4413,12 @@ static inline bool f2fs_block_unit_discard(struct f2fs_sb_info *sbi)
return F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_BLOCK;
}
+static inline void f2fs_io_schedule_timeout(long timeout)
+{
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ io_schedule_timeout(timeout);
+}
+
#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 489854d841e7..378ab6bd1b8d 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -3532,10 +3532,10 @@ out:
return ret;
}
-static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
+static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count,
+ unsigned int *reserved_blocks)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
- unsigned int reserved_blocks = 0;
int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
block_t blkaddr;
int i;
@@ -3566,7 +3566,13 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
goto next;
}
- if (__is_valid_data_blkaddr(blkaddr)) {
+ /*
+ * compressed cluster was not released due to it
+ * fails in release_compress_blocks(), so NEW_ADDR
+ * is a possible case.
+ */
+ if (blkaddr == NEW_ADDR ||
+ __is_valid_data_blkaddr(blkaddr)) {
compr_blocks++;
continue;
}
@@ -3576,6 +3582,11 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
}
reserved = cluster_size - compr_blocks;
+
+ /* for the case all blocks in cluster were reserved */
+ if (reserved == 1)
+ goto next;
+
ret = inc_valid_block_count(sbi, dn->inode, &reserved);
if (ret)
return ret;
@@ -3585,12 +3596,12 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true);
- reserved_blocks += reserved;
+ *reserved_blocks += reserved;
next:
count -= cluster_size;
}
- return reserved_blocks;
+ return 0;
}
static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
@@ -3651,7 +3662,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
count = round_up(count, F2FS_I(inode)->i_cluster_size);
- ret = reserve_compress_blocks(&dn, count);
+ ret = reserve_compress_blocks(&dn, count, &reserved_blocks);
f2fs_put_dnode(&dn);
@@ -3659,13 +3670,12 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
break;
page_idx += count;
- reserved_blocks += ret;
}
filemap_invalidate_unlock(inode->i_mapping);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- if (ret >= 0) {
+ if (!ret) {
clear_inode_flag(inode, FI_COMPRESS_RELEASED);
inode->i_ctime = current_time(inode);
f2fs_mark_inode_dirty_sync(inode, true);
@@ -3675,7 +3685,7 @@ unlock_inode:
out:
mnt_drop_write_file(filp);
- if (ret >= 0) {
+ if (!ret) {
ret = put_user(reserved_blocks, (u64 __user *)arg);
} else if (reserved_blocks &&
atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 2c13f308c74e..9a57754e6e0c 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1080,8 +1080,8 @@ static int ra_data_block(struct inode *inode, pgoff_t index)
.op = REQ_OP_READ,
.op_flags = 0,
.encrypted_page = NULL,
- .in_list = false,
- .retry = false,
+ .in_list = 0,
+ .retry = 0,
};
int err;
@@ -1167,8 +1167,8 @@ static int move_data_block(struct inode *inode, block_t bidx,
.op = REQ_OP_READ,
.op_flags = 0,
.encrypted_page = NULL,
- .in_list = false,
- .retry = false,
+ .in_list = 0,
+ .retry = 0,
};
struct dnode_of_data dn;
struct f2fs_summary sum;
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 195658263f0a..dc85dd55314c 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1583,7 +1583,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
.op_flags = wbc_to_write_flags(wbc),
.page = page,
.encrypted_page = NULL,
- .submitted = false,
+ .submitted = 0,
.io_type = io_type,
.io_wbc = wbc,
};
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 79ad696cddec..b454496ca67a 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -313,8 +313,7 @@ next:
skip:
iput(inode);
}
- congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
- cond_resched();
+ f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
if (gc_failure) {
if (++looped >= count)
return;
@@ -789,8 +788,7 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi)
do {
ret = __submit_flush_wait(sbi, FDEV(i).bdev);
if (ret)
- congestion_wait(BLK_RW_ASYNC,
- DEFAULT_IO_TIMEOUT);
+ f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
} while (ret && --count);
if (ret) {
@@ -3106,7 +3104,7 @@ next:
blk_finish_plug(&plug);
mutex_unlock(&dcc->cmd_lock);
trimmed += __wait_all_discard_cmd(sbi, NULL);
- congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
+ f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
goto next;
}
skip:
@@ -3475,10 +3473,10 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
struct f2fs_bio_info *io;
if (F2FS_IO_ALIGNED(sbi))
- fio->retry = false;
+ fio->retry = 0;
INIT_LIST_HEAD(&fio->list);
- fio->in_list = true;
+ fio->in_list = 1;
io = sbi->write_io[fio->type] + fio->temp;
spin_lock(&io->io_lock);
list_add_tail(&fio->list, &io->io_list);
@@ -3490,24 +3488,30 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
up_read(&SM_I(sbi)->curseg_lock);
}
-static void update_device_state(struct f2fs_io_info *fio)
+void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
+ block_t blkaddr, unsigned int blkcnt)
{
- struct f2fs_sb_info *sbi = fio->sbi;
- unsigned int devidx;
-
if (!f2fs_is_multi_device(sbi))
return;
- devidx = f2fs_target_device_index(sbi, fio->new_blkaddr);
+ while (1) {
+ unsigned int devidx = f2fs_target_device_index(sbi, blkaddr);
+ unsigned int blks = FDEV(devidx).end_blk - blkaddr + 1;
- /* update device state for fsync */
- f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO);
+ /* update device state for fsync */
+ f2fs_set_dirty_device(sbi, ino, devidx, FLUSH_INO);
- /* update device state for checkpoint */
- if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) {
- spin_lock(&sbi->dev_lock);
- f2fs_set_bit(devidx, (char *)&sbi->dirty_device);
- spin_unlock(&sbi->dev_lock);
+ /* update device state for checkpoint */
+ if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) {
+ spin_lock(&sbi->dev_lock);
+ f2fs_set_bit(devidx, (char *)&sbi->dirty_device);
+ spin_unlock(&sbi->dev_lock);
+ }
+
+ if (blkcnt <= blks)
+ break;
+ blkcnt -= blks;
+ blkaddr += blks;
}
}
@@ -3534,7 +3538,7 @@ reallocate:
goto reallocate;
}
- update_device_state(fio);
+ f2fs_update_device_state(fio->sbi, fio->ino, fio->new_blkaddr, 1);
if (keep_order)
up_read(&fio->sbi->io_order_lock);
@@ -3553,7 +3557,7 @@ void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
.new_blkaddr = page->index,
.page = page,
.encrypted_page = NULL,
- .in_list = false,
+ .in_list = 0,
};
if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
@@ -3616,6 +3620,10 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
goto drop_bio;
}
+ if (fio->post_read)
+ invalidate_mapping_pages(META_MAPPING(sbi),
+ fio->new_blkaddr, fio->new_blkaddr);
+
stat_inc_inplace_blocks(fio->sbi);
if (fio->bio && !(SM_I(sbi)->ipu_policy & (1 << F2FS_IPU_NOCACHE)))
@@ -3623,7 +3631,8 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
else
err = f2fs_submit_page_bio(fio);
if (!err) {
- update_device_state(fio);
+ f2fs_update_device_state(fio->sbi, fio->ino,
+ fio->new_blkaddr, 1);
f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
}
@@ -3795,10 +3804,16 @@ void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr)
void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
block_t len)
{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
block_t i;
+ if (!f2fs_post_read_required(inode))
+ return;
+
for (i = 0; i < len; i++)
f2fs_wait_on_block_writeback(inode, blkaddr + i);
+
+ invalidate_mapping_pages(META_MAPPING(sbi), blkaddr, blkaddr + len - 1);
}
static int read_compacted_summaries(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index d4a76c2deb80..df1e5496352c 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2168,8 +2168,7 @@ static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi)
/* we should flush all the data to keep data consistency */
do {
sync_inodes_sb(sbi->sb);
- cond_resched();
- congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
+ f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
} while (get_pages(sbi, F2FS_DIRTY_DATA) && retry--);
if (unlikely(retry < 0))
@@ -2540,8 +2539,7 @@ retry:
&page, &fsdata);
if (unlikely(err)) {
if (err == -ENOMEM) {
- congestion_wait(BLK_RW_ASYNC,
- DEFAULT_IO_TIMEOUT);
+ f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
goto retry;
}
set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
@@ -3831,6 +3829,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
unsigned int max_devices = MAX_DEVICES;
+ unsigned int logical_blksize;
int i;
/* Initialize single device information */
@@ -3851,6 +3850,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
if (!sbi->devs)
return -ENOMEM;
+ logical_blksize = bdev_logical_block_size(sbi->sb->s_bdev);
+ sbi->aligned_blksize = true;
+
for (i = 0; i < max_devices; i++) {
if (i > 0 && !RDEV(i).path[0])
@@ -3887,6 +3889,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
/* to release errored devices */
sbi->s_ndevs = i + 1;
+ if (logical_blksize != bdev_logical_block_size(FDEV(i).bdev))
+ sbi->aligned_blksize = false;
+
#ifdef CONFIG_BLK_DEV_ZONED
if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM &&
!f2fs_sb_has_blkzoned(sbi)) {
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 6630c69c23a2..55e5ffacc0e4 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -37,7 +37,7 @@ static long do_sys_name_to_handle(struct path *path,
if (f_handle.handle_bytes > MAX_HANDLE_SZ)
return -EINVAL;
- handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
+ handle = kzalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
GFP_KERNEL);
if (!handle)
return -ENOMEM;
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index 0fe5aacbcfdf..e7192d0eea3d 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -54,11 +54,14 @@ int nfs42_proc_removexattr(struct inode *inode, const char *name);
* They would be 7 bytes long in the eventual buffer ("user.x\0"), and
* 8 bytes long XDR-encoded.
*
- * Include the trailing eof word as well.
+ * Include the trailing eof word as well and make the result a multiple
+ * of 4 bytes.
*/
static inline u32 nfs42_listxattr_xdrsize(u32 buflen)
{
- return ((buflen / (XATTR_USER_PREFIX_LEN + 2)) * 8) + 4;
+ u32 size = 8 * buflen / (XATTR_USER_PREFIX_LEN + 2) + 4;
+
+ return (size + 3) & ~3;
}
#endif /* CONFIG_NFS_V4_2 */
#endif /* __LINUX_FS_NFS_NFS4_2_H */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a865b384f0fc..925ad7dbe6a0 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -10517,29 +10517,33 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
{
ssize_t error, error2, error3;
+ size_t left = size;
- error = generic_listxattr(dentry, list, size);
+ error = generic_listxattr(dentry, list, left);
if (error < 0)
return error;
if (list) {
list += error;
- size -= error;
+ left -= error;
}
- error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size);
+ error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, left);
if (error2 < 0)
return error2;
if (list) {
list += error2;
- size -= error2;
+ left -= error2;
}
- error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, size);
+ error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left);
if (error3 < 0)
return error3;
- return error + error2 + error3;
+ error += error2 + error3;
+ if (size && error > size)
+ return -ERANGE;
+ return error;
}
static void nfs4_enable_swap(struct inode *inode)
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index fa148308822c..c2cf4ff62881 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -175,10 +175,10 @@ static int __init root_nfs_cat(char *dest, const char *src,
size_t len = strlen(dest);
if (len && dest[len - 1] != ',')
- if (strlcat(dest, ",", destlen) > destlen)
+ if (strlcat(dest, ",", destlen) >= destlen)
return -1;
- if (strlcat(dest, src, destlen) > destlen)
+ if (strlcat(dest, src, destlen) >= destlen)
return -1;
return 0;
}
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 75e593b1c03e..edb414d3fd16 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -399,15 +399,17 @@ int dquot_mark_dquot_dirty(struct dquot *dquot)
EXPORT_SYMBOL(dquot_mark_dquot_dirty);
/* Dirtify all the dquots - this can block when journalling */
-static inline int mark_all_dquot_dirty(struct dquot * const *dquot)
+static inline int mark_all_dquot_dirty(struct dquot __rcu * const *dquots)
{
int ret, err, cnt;
+ struct dquot *dquot;
ret = err = 0;
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (dquot[cnt])
+ dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
+ if (dquot)
/* Even in case of error we have to continue */
- ret = mark_dquot_dirty(dquot[cnt]);
+ ret = mark_dquot_dirty(dquot);
if (!err)
err = ret;
}
@@ -1004,14 +1006,15 @@ out:
}
EXPORT_SYMBOL(dqget);
-static inline struct dquot **i_dquot(struct inode *inode)
+static inline struct dquot __rcu **i_dquot(struct inode *inode)
{
- return inode->i_sb->s_op->get_dquots(inode);
+ /* Force __rcu for now until filesystems are fixed */
+ return (struct dquot __rcu **)inode->i_sb->s_op->get_dquots(inode);
}
static int dqinit_needed(struct inode *inode, int type)
{
- struct dquot * const *dquots;
+ struct dquot __rcu * const *dquots;
int cnt;
if (IS_NOQUOTA(inode))
@@ -1084,59 +1087,7 @@ out:
return err;
}
-/*
- * Remove references to dquots from inode and add dquot to list for freeing
- * if we have the last reference to dquot
- */
-static void remove_inode_dquot_ref(struct inode *inode, int type,
- struct list_head *tofree_head)
-{
- struct dquot **dquots = i_dquot(inode);
- struct dquot *dquot = dquots[type];
-
- if (!dquot)
- return;
-
- dquots[type] = NULL;
- if (list_empty(&dquot->dq_free)) {
- /*
- * The inode still has reference to dquot so it can't be in the
- * free list
- */
- spin_lock(&dq_list_lock);
- list_add(&dquot->dq_free, tofree_head);
- spin_unlock(&dq_list_lock);
- } else {
- /*
- * Dquot is already in a list to put so we won't drop the last
- * reference here.
- */
- dqput(dquot);
- }
-}
-
-/*
- * Free list of dquots
- * Dquots are removed from inodes and no new references can be got so we are
- * the only ones holding reference
- */
-static void put_dquot_list(struct list_head *tofree_head)
-{
- struct list_head *act_head;
- struct dquot *dquot;
-
- act_head = tofree_head->next;
- while (act_head != tofree_head) {
- dquot = list_entry(act_head, struct dquot, dq_free);
- act_head = act_head->next;
- /* Remove dquot from the list so we won't have problems... */
- list_del_init(&dquot->dq_free);
- dqput(dquot);
- }
-}
-
-static void remove_dquot_ref(struct super_block *sb, int type,
- struct list_head *tofree_head)
+static void remove_dquot_ref(struct super_block *sb, int type)
{
struct inode *inode;
#ifdef CONFIG_QUOTA_DEBUG
@@ -1153,11 +1104,18 @@ static void remove_dquot_ref(struct super_block *sb, int type,
*/
spin_lock(&dq_data_lock);
if (!IS_NOQUOTA(inode)) {
+ struct dquot __rcu **dquots = i_dquot(inode);
+ struct dquot *dquot = srcu_dereference_check(
+ dquots[type], &dquot_srcu,
+ lockdep_is_held(&dq_data_lock));
+
#ifdef CONFIG_QUOTA_DEBUG
if (unlikely(inode_get_rsv_space(inode) > 0))
reserved = 1;
#endif
- remove_inode_dquot_ref(inode, type, tofree_head);
+ rcu_assign_pointer(dquots[type], NULL);
+ if (dquot)
+ dqput(dquot);
}
spin_unlock(&dq_data_lock);
}
@@ -1174,13 +1132,8 @@ static void remove_dquot_ref(struct super_block *sb, int type,
/* Gather all references from inodes and drop them */
static void drop_dquot_ref(struct super_block *sb, int type)
{
- LIST_HEAD(tofree_head);
-
- if (sb->dq_op) {
- remove_dquot_ref(sb, type, &tofree_head);
- synchronize_srcu(&dquot_srcu);
- put_dquot_list(&tofree_head);
- }
+ if (sb->dq_op)
+ remove_dquot_ref(sb, type);
}
static inline
@@ -1513,7 +1466,8 @@ static int inode_quota_active(const struct inode *inode)
static int __dquot_initialize(struct inode *inode, int type)
{
int cnt, init_needed = 0;
- struct dquot **dquots, *got[MAXQUOTAS] = {};
+ struct dquot __rcu **dquots;
+ struct dquot *got[MAXQUOTAS] = {};
struct super_block *sb = inode->i_sb;
qsize_t rsv;
int ret = 0;
@@ -1588,7 +1542,7 @@ static int __dquot_initialize(struct inode *inode, int type)
if (!got[cnt])
continue;
if (!dquots[cnt]) {
- dquots[cnt] = got[cnt];
+ rcu_assign_pointer(dquots[cnt], got[cnt]);
got[cnt] = NULL;
/*
* Make quota reservation system happy if someone
@@ -1596,12 +1550,16 @@ static int __dquot_initialize(struct inode *inode, int type)
*/
rsv = inode_get_rsv_space(inode);
if (unlikely(rsv)) {
+ struct dquot *dquot = srcu_dereference_check(
+ dquots[cnt], &dquot_srcu,
+ lockdep_is_held(&dq_data_lock));
+
spin_lock(&inode->i_lock);
/* Get reservation again under proper lock */
rsv = __inode_get_rsv_space(inode);
- spin_lock(&dquots[cnt]->dq_dqb_lock);
- dquots[cnt]->dq_dqb.dqb_rsvspace += rsv;
- spin_unlock(&dquots[cnt]->dq_dqb_lock);
+ spin_lock(&dquot->dq_dqb_lock);
+ dquot->dq_dqb.dqb_rsvspace += rsv;
+ spin_unlock(&dquot->dq_dqb_lock);
spin_unlock(&inode->i_lock);
}
}
@@ -1623,7 +1581,7 @@ EXPORT_SYMBOL(dquot_initialize);
bool dquot_initialize_needed(struct inode *inode)
{
- struct dquot **dquots;
+ struct dquot __rcu **dquots;
int i;
if (!inode_quota_active(inode))
@@ -1648,13 +1606,14 @@ EXPORT_SYMBOL(dquot_initialize_needed);
static void __dquot_drop(struct inode *inode)
{
int cnt;
- struct dquot **dquots = i_dquot(inode);
+ struct dquot __rcu **dquots = i_dquot(inode);
struct dquot *put[MAXQUOTAS];
spin_lock(&dq_data_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- put[cnt] = dquots[cnt];
- dquots[cnt] = NULL;
+ put[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu,
+ lockdep_is_held(&dq_data_lock));
+ rcu_assign_pointer(dquots[cnt], NULL);
}
spin_unlock(&dq_data_lock);
dqput_all(put);
@@ -1662,7 +1621,7 @@ static void __dquot_drop(struct inode *inode)
void dquot_drop(struct inode *inode)
{
- struct dquot * const *dquots;
+ struct dquot __rcu * const *dquots;
int cnt;
if (IS_NOQUOTA(inode))
@@ -1735,7 +1694,8 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
int cnt, ret = 0, index;
struct dquot_warn warn[MAXQUOTAS];
int reserve = flags & DQUOT_SPACE_RESERVE;
- struct dquot **dquots;
+ struct dquot __rcu **dquots;
+ struct dquot *dquot;
if (!inode_quota_active(inode)) {
if (reserve) {
@@ -1755,27 +1715,26 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags)
index = srcu_read_lock(&dquot_srcu);
spin_lock(&inode->i_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (!dquots[cnt])
+ dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
+ if (!dquot)
continue;
if (reserve) {
- ret = dquot_add_space(dquots[cnt], 0, number, flags,
- &warn[cnt]);
+ ret = dquot_add_space(dquot, 0, number, flags, &warn[cnt]);
} else {
- ret = dquot_add_space(dquots[cnt], number, 0, flags,
- &warn[cnt]);
+ ret = dquot_add_space(dquot, number, 0, flags, &warn[cnt]);
}
if (ret) {
/* Back out changes we already did */
for (cnt--; cnt >= 0; cnt--) {
- if (!dquots[cnt])
+ dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
+ if (!dquot)
continue;
- spin_lock(&dquots[cnt]->dq_dqb_lock);
+ spin_lock(&dquot->dq_dqb_lock);
if (reserve)
- dquot_free_reserved_space(dquots[cnt],
- number);
+ dquot_free_reserved_space(dquot, number);
else
- dquot_decr_space(dquots[cnt], number);
- spin_unlock(&dquots[cnt]->dq_dqb_lock);
+ dquot_decr_space(dquot, number);
+ spin_unlock(&dquot->dq_dqb_lock);
}
spin_unlock(&inode->i_lock);
goto out_flush_warn;
@@ -1805,7 +1764,8 @@ int dquot_alloc_inode(struct inode *inode)
{
int cnt, ret = 0, index;
struct dquot_warn warn[MAXQUOTAS];
- struct dquot * const *dquots;
+ struct dquot __rcu * const *dquots;
+ struct dquot *dquot;
if (!inode_quota_active(inode))
return 0;
@@ -1816,17 +1776,19 @@ int dquot_alloc_inode(struct inode *inode)
index = srcu_read_lock(&dquot_srcu);
spin_lock(&inode->i_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (!dquots[cnt])
+ dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
+ if (!dquot)
continue;
- ret = dquot_add_inodes(dquots[cnt], 1, &warn[cnt]);
+ ret = dquot_add_inodes(dquot, 1, &warn[cnt]);
if (ret) {
for (cnt--; cnt >= 0; cnt--) {
- if (!dquots[cnt])
+ dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
+ if (!dquot)
continue;
/* Back out changes we already did */
- spin_lock(&dquots[cnt]->dq_dqb_lock);
- dquot_decr_inodes(dquots[cnt], 1);
- spin_unlock(&dquots[cnt]->dq_dqb_lock);
+ spin_lock(&dquot->dq_dqb_lock);
+ dquot_decr_inodes(dquot, 1);
+ spin_unlock(&dquot->dq_dqb_lock);
}
goto warn_put_all;
}
@@ -1847,7 +1809,8 @@ EXPORT_SYMBOL(dquot_alloc_inode);
*/
int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
{
- struct dquot **dquots;
+ struct dquot __rcu **dquots;
+ struct dquot *dquot;
int cnt, index;
if (!inode_quota_active(inode)) {
@@ -1863,9 +1826,8 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
spin_lock(&inode->i_lock);
/* Claim reserved quotas to allocated quotas */
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (dquots[cnt]) {
- struct dquot *dquot = dquots[cnt];
-
+ dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
+ if (dquot) {
spin_lock(&dquot->dq_dqb_lock);
if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number))
number = dquot->dq_dqb.dqb_rsvspace;
@@ -1889,7 +1851,8 @@ EXPORT_SYMBOL(dquot_claim_space_nodirty);
*/
void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number)
{
- struct dquot **dquots;
+ struct dquot __rcu **dquots;
+ struct dquot *dquot;
int cnt, index;
if (!inode_quota_active(inode)) {
@@ -1905,9 +1868,8 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number)
spin_lock(&inode->i_lock);
/* Claim reserved quotas to allocated quotas */
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- if (dquots[cnt]) {
- struct dquot *dquot = dquots[cnt];
-
+ dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
+ if (dquot) {
spin_lock(&dquot->dq_dqb_lock);
if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number))
number = dquot->dq_dqb.dqb_curspace;
@@ -1933,7 +1895,8 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
{
unsigned int cnt;
struct dquot_warn warn[MAXQUOTAS];
- struct dquot **dquots;
+ struct dquot __rcu **dquots;
+ struct dquot *dquot;
int reserve = flags & DQUOT_SPACE_RESERVE, index;
if (!inode_quota_active(inode)) {
@@ -1954,17 +1917,18 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
int wtype;
warn[cnt].w_type = QUOTA_NL_NOWARN;
- if (!dquots[cnt])
+ dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
+ if (!dquot)
continue;
- spin_lock(&dquots[cnt]->dq_dqb_lock);
- wtype = info_bdq_free(dquots[cnt], number);
+ spin_lock(&dquot->dq_dqb_lock);
+ wtype = info_bdq_free(dquot, number);
if (wtype != QUOTA_NL_NOWARN)
- prepare_warning(&warn[cnt], dquots[cnt], wtype);
+ prepare_warning(&warn[cnt], dquot, wtype);
if (reserve)
- dquot_free_reserved_space(dquots[cnt], number);
+ dquot_free_reserved_space(dquot, number);
else
- dquot_decr_space(dquots[cnt], number);
- spin_unlock(&dquots[cnt]->dq_dqb_lock);
+ dquot_decr_space(dquot, number);
+ spin_unlock(&dquot->dq_dqb_lock);
}
if (reserve)
*inode_reserved_space(inode) -= number;
@@ -1988,7 +1952,8 @@ void dquot_free_inode(struct inode *inode)
{
unsigned int cnt;
struct dquot_warn warn[MAXQUOTAS];
- struct dquot * const *dquots;
+ struct dquot __rcu * const *dquots;
+ struct dquot *dquot;
int index;
if (!inode_quota_active(inode))
@@ -1999,16 +1964,16 @@ void dquot_free_inode(struct inode *inode)
spin_lock(&inode->i_lock);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
int wtype;
-
warn[cnt].w_type = QUOTA_NL_NOWARN;
- if (!dquots[cnt])
+ dquot = srcu_dereference(dquots[cnt], &dquot_srcu);
+ if (!dquot)
continue;
- spin_lock(&dquots[cnt]->dq_dqb_lock);
- wtype = info_idq_free(dquots[cnt], 1);
+ spin_lock(&dquot->dq_dqb_lock);
+ wtype = info_idq_free(dquot, 1);
if (wtype != QUOTA_NL_NOWARN)
- prepare_warning(&warn[cnt], dquots[cnt], wtype);
- dquot_decr_inodes(dquots[cnt], 1);
- spin_unlock(&dquots[cnt]->dq_dqb_lock);
+ prepare_warning(&warn[cnt], dquot, wtype);
+ dquot_decr_inodes(dquot, 1);
+ spin_unlock(&dquot->dq_dqb_lock);
}
spin_unlock(&inode->i_lock);
mark_all_dquot_dirty(dquots);
@@ -2034,8 +1999,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
qsize_t cur_space;
qsize_t rsv_space = 0;
qsize_t inode_usage = 1;
+ struct dquot __rcu **dquots;
struct dquot *transfer_from[MAXQUOTAS] = {};
- int cnt, ret = 0;
+ int cnt, index, ret = 0;
char is_valid[MAXQUOTAS] = {};
struct dquot_warn warn_to[MAXQUOTAS];
struct dquot_warn warn_from_inodes[MAXQUOTAS];
@@ -2066,6 +2032,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
}
cur_space = __inode_get_bytes(inode);
rsv_space = __inode_get_rsv_space(inode);
+ dquots = i_dquot(inode);
/*
* Build the transfer_from list, check limits, and update usage in
* the target structures.
@@ -2080,7 +2047,8 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
if (!sb_has_quota_active(inode->i_sb, cnt))
continue;
is_valid[cnt] = 1;
- transfer_from[cnt] = i_dquot(inode)[cnt];
+ transfer_from[cnt] = srcu_dereference_check(dquots[cnt],
+ &dquot_srcu, lockdep_is_held(&dq_data_lock));
ret = dquot_add_inodes(transfer_to[cnt], inode_usage,
&warn_to[cnt]);
if (ret)
@@ -2119,13 +2087,21 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
rsv_space);
spin_unlock(&transfer_from[cnt]->dq_dqb_lock);
}
- i_dquot(inode)[cnt] = transfer_to[cnt];
+ rcu_assign_pointer(dquots[cnt], transfer_to[cnt]);
}
spin_unlock(&inode->i_lock);
spin_unlock(&dq_data_lock);
- mark_all_dquot_dirty(transfer_from);
- mark_all_dquot_dirty(transfer_to);
+ /*
+ * These arrays are local and we hold dquot references so we don't need
+ * the srcu protection but still take dquot_srcu to avoid warning in
+ * mark_all_dquot_dirty().
+ */
+ index = srcu_read_lock(&dquot_srcu);
+ mark_all_dquot_dirty((struct dquot __rcu **)transfer_from);
+ mark_all_dquot_dirty((struct dquot __rcu **)transfer_to);
+ srcu_read_unlock(&dquot_srcu, index);
+
flush_warnings(warn_to);
flush_warnings(warn_from_inodes);
flush_warnings(warn_from_space);
diff --git a/fs/select.c b/fs/select.c
index 5edffee1162c..668a5200503a 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -475,7 +475,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in,
wait->_key |= POLLOUT_SET;
}
-static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
+static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
{
ktime_t expire, *to = NULL;
struct poll_wqueues table;
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-06-07 13:35:49 +0000