summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/afs/write.c2
-rw-r--r--fs/btrfs/compression.c17
-rw-r--r--fs/btrfs/disk-io.c26
-rw-r--r--fs/btrfs/extent-tree.c2
-rw-r--r--fs/btrfs/file-item.c108
-rw-r--r--fs/btrfs/file.c4
-rw-r--r--fs/btrfs/inode.c19
-rw-r--r--fs/btrfs/reflink.c38
-rw-r--r--fs/btrfs/tree-log.c37
-rw-r--r--fs/btrfs/zoned.c23
-rw-r--r--fs/coredump.c2
-rw-r--r--fs/debugfs/file.c2
-rw-r--r--fs/ext4/extents.c43
-rw-r--r--fs/ext4/fast_commit.c170
-rw-r--r--fs/ext4/fast_commit.h19
-rw-r--r--fs/ext4/ialloc.c6
-rw-r--r--fs/ext4/mballoc.c2
-rw-r--r--fs/ext4/namei.c6
-rw-r--r--fs/ext4/super.c11
-rw-r--r--fs/ext4/sysfs.c4
-rw-r--r--fs/gfs2/file.c5
-rw-r--r--fs/gfs2/glock.c28
-rw-r--r--fs/gfs2/glops.c2
-rw-r--r--fs/gfs2/log.c6
-rw-r--r--fs/gfs2/log.h1
-rw-r--r--fs/gfs2/lops.c7
-rw-r--r--fs/gfs2/lops.h1
-rw-r--r--fs/gfs2/util.c1
-rw-r--r--fs/io_uring.c43
-rw-r--r--fs/nfs/client.c2
-rw-r--r--fs/nfs/nfs4_fs.h1
-rw-r--r--fs/nfs/nfs4client.c2
-rw-r--r--fs/nfs/nfs4proc.c37
-rw-r--r--fs/nfs/nfstrace.h4
-rw-r--r--fs/notify/fanotify/fanotify_user.c30
-rw-r--r--fs/notify/fdinfo.c2
-rw-r--r--fs/ocfs2/file.c55
-rw-r--r--fs/proc/base.c9
38 files changed, 526 insertions, 251 deletions
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 3edb6204b937..a523bb86915d 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -730,7 +730,7 @@ static int afs_writepages_region(struct address_space *mapping,
return ret;
}
- start += ret * PAGE_SIZE;
+ start += ret;
cond_resched();
} while (wbc->nr_to_write > 0);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index d17ac301032e..1346d698463a 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -457,7 +457,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
bytes_left = compressed_len;
for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) {
int submit = 0;
- int len;
+ int len = 0;
page = compressed_pages[pg_index];
page->mapping = inode->vfs_inode.i_mapping;
@@ -465,10 +465,17 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE, bio,
0);
- if (pg_index == 0 && use_append)
- len = bio_add_zone_append_page(bio, page, PAGE_SIZE, 0);
- else
- len = bio_add_page(bio, page, PAGE_SIZE, 0);
+ /*
+ * Page can only be added to bio if the current bio fits in
+ * stripe.
+ */
+ if (!submit) {
+ if (pg_index == 0 && use_append)
+ len = bio_add_zone_append_page(bio, page,
+ PAGE_SIZE, 0);
+ else
+ len = bio_add_page(bio, page, PAGE_SIZE, 0);
+ }
page->mapping = NULL;
if (submit || len < PAGE_SIZE) {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c9a3036c23bf..8d386a5587ee 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2648,6 +2648,24 @@ static int validate_super(struct btrfs_fs_info *fs_info,
ret = -EINVAL;
}
+ if (memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid,
+ BTRFS_FSID_SIZE)) {
+ btrfs_err(fs_info,
+ "superblock fsid doesn't match fsid of fs_devices: %pU != %pU",
+ fs_info->super_copy->fsid, fs_info->fs_devices->fsid);
+ ret = -EINVAL;
+ }
+
+ if (btrfs_fs_incompat(fs_info, METADATA_UUID) &&
+ memcmp(fs_info->fs_devices->metadata_uuid,
+ fs_info->super_copy->metadata_uuid, BTRFS_FSID_SIZE)) {
+ btrfs_err(fs_info,
+"superblock metadata_uuid doesn't match metadata uuid of fs_devices: %pU != %pU",
+ fs_info->super_copy->metadata_uuid,
+ fs_info->fs_devices->metadata_uuid);
+ ret = -EINVAL;
+ }
+
if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid,
BTRFS_FSID_SIZE) != 0) {
btrfs_err(fs_info,
@@ -3279,14 +3297,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
disk_super = fs_info->super_copy;
- ASSERT(!memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid,
- BTRFS_FSID_SIZE));
-
- if (btrfs_fs_incompat(fs_info, METADATA_UUID)) {
- ASSERT(!memcmp(fs_info->fs_devices->metadata_uuid,
- fs_info->super_copy->metadata_uuid,
- BTRFS_FSID_SIZE));
- }
features = btrfs_super_flags(disk_super);
if (features & BTRFS_SUPER_FLAG_CHANGING_FSID_V2) {
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index f1d15b68994a..3d5c35e4cb76 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1868,7 +1868,7 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
trace_run_delayed_ref_head(fs_info, head, 0);
btrfs_delayed_ref_unlock(head);
btrfs_put_delayed_ref_head(head);
- return 0;
+ return ret;
}
static struct btrfs_delayed_ref_head *btrfs_obtain_ref_head(
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 294602f139ef..441cee7fbb62 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -788,7 +788,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
u64 end_byte = bytenr + len;
u64 csum_end;
struct extent_buffer *leaf;
- int ret;
+ int ret = 0;
const u32 csum_size = fs_info->csum_size;
u32 blocksize_bits = fs_info->sectorsize_bits;
@@ -806,6 +806,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
if (ret > 0) {
+ ret = 0;
if (path->slots[0] == 0)
break;
path->slots[0]--;
@@ -862,7 +863,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
ret = btrfs_del_items(trans, root, path,
path->slots[0], del_nr);
if (ret)
- goto out;
+ break;
if (key.offset == bytenr)
break;
} else if (key.offset < bytenr && csum_end > end_byte) {
@@ -906,8 +907,9 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
ret = btrfs_split_item(trans, root, path, &key, offset);
if (ret && ret != -EAGAIN) {
btrfs_abort_transaction(trans, ret);
- goto out;
+ break;
}
+ ret = 0;
key.offset = end_byte - 1;
} else {
@@ -917,12 +919,41 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
}
btrfs_release_path(path);
}
- ret = 0;
-out:
btrfs_free_path(path);
return ret;
}
+static int find_next_csum_offset(struct btrfs_root *root,
+ struct btrfs_path *path,
+ u64 *next_offset)
+{
+ const u32 nritems = btrfs_header_nritems(path->nodes[0]);
+ struct btrfs_key found_key;
+ int slot = path->slots[0] + 1;
+ int ret;
+
+ if (nritems == 0 || slot >= nritems) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0) {
+ return ret;
+ } else if (ret > 0) {
+ *next_offset = (u64)-1;
+ return 0;
+ }
+ slot = path->slots[0];
+ }
+
+ btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
+
+ if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
+ found_key.type != BTRFS_EXTENT_CSUM_KEY)
+ *next_offset = (u64)-1;
+ else
+ *next_offset = found_key.offset;
+
+ return 0;
+}
+
int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_ordered_sum *sums)
@@ -938,7 +969,6 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
u64 total_bytes = 0;
u64 csum_offset;
u64 bytenr;
- u32 nritems;
u32 ins_size;
int index = 0;
int found_next;
@@ -981,26 +1011,10 @@ again:
goto insert;
}
} else {
- int slot = path->slots[0] + 1;
- /* we didn't find a csum item, insert one */
- nritems = btrfs_header_nritems(path->nodes[0]);
- if (!nritems || (path->slots[0] >= nritems - 1)) {
- ret = btrfs_next_leaf(root, path);
- if (ret < 0) {
- goto out;
- } else if (ret > 0) {
- found_next = 1;
- goto insert;
- }
- slot = path->slots[0];
- }
- btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
- if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
- found_key.type != BTRFS_EXTENT_CSUM_KEY) {
- found_next = 1;
- goto insert;
- }
- next_offset = found_key.offset;
+ /* We didn't find a csum item, insert one. */
+ ret = find_next_csum_offset(root, path, &next_offset);
+ if (ret < 0)
+ goto out;
found_next = 1;
goto insert;
}
@@ -1056,8 +1070,48 @@ extend_csum:
tmp = sums->len - total_bytes;
tmp >>= fs_info->sectorsize_bits;
WARN_ON(tmp < 1);
+ extend_nr = max_t(int, 1, tmp);
+
+ /*
+ * A log tree can already have checksum items with a subset of
+ * the checksums we are trying to log. This can happen after
+ * doing a sequence of partial writes into prealloc extents and
+ * fsyncs in between, with a full fsync logging a larger subrange
+ * of an extent for which a previous fast fsync logged a smaller
+ * subrange. And this happens in particular due to merging file
+ * extent items when we complete an ordered extent for a range
+ * covered by a prealloc extent - this is done at
+ * btrfs_mark_extent_written().
+ *
+ * So if we try to extend the previous checksum item, which has
+ * a range that ends at the start of the range we want to insert,
+ * make sure we don't extend beyond the start offset of the next
+ * checksum item. If we are at the last item in the leaf, then
+ * forget the optimization of extending and add a new checksum
+ * item - it is not worth the complexity of releasing the path,
+ * getting the first key for the next leaf, repeat the btree
+ * search, etc, because log trees are temporary anyway and it
+ * would only save a few bytes of leaf space.
+ */
+ if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
+ if (path->slots[0] + 1 >=
+ btrfs_header_nritems(path->nodes[0])) {
+ ret = find_next_csum_offset(root, path, &next_offset);
+ if (ret < 0)
+ goto out;
+ found_next = 1;
+ goto insert;
+ }
+
+ ret = find_next_csum_offset(root, path, &next_offset);
+ if (ret < 0)
+ goto out;
+
+ tmp = (next_offset - bytenr) >> fs_info->sectorsize_bits;
+ if (tmp <= INT_MAX)
+ extend_nr = min_t(int, extend_nr, tmp);
+ }
- extend_nr = max_t(int, 1, (int)tmp);
diff = (csum_offset + extend_nr) * csum_size;
diff = min(diff,
MAX_CSUM_ITEMS(fs_info, csum_size) * csum_size);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 3b10d98b4ebb..55f68422061d 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1094,7 +1094,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
int del_nr = 0;
int del_slot = 0;
int recow;
- int ret;
+ int ret = 0;
u64 ino = btrfs_ino(inode);
path = btrfs_alloc_path();
@@ -1315,7 +1315,7 @@ again:
}
out:
btrfs_free_path(path);
- return 0;
+ return ret;
}
/*
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 33f14573f2ec..46f392943f4d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3000,6 +3000,18 @@ out:
if (ret || truncated) {
u64 unwritten_start = start;
+ /*
+ * If we failed to finish this ordered extent for any reason we
+ * need to make sure BTRFS_ORDERED_IOERR is set on the ordered
+ * extent, and mark the inode with the error if it wasn't
+ * already set. Any error during writeback would have already
+ * set the mapping error, so we need to set it if we're the ones
+ * marking this ordered extent as failed.
+ */
+ if (ret && !test_and_set_bit(BTRFS_ORDERED_IOERR,
+ &ordered_extent->flags))
+ mapping_set_error(ordered_extent->inode->i_mapping, -EIO);
+
if (truncated)
unwritten_start += logical_len;
clear_extent_uptodate(io_tree, unwritten_start, end, NULL);
@@ -9076,6 +9088,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
int ret2;
bool root_log_pinned = false;
bool dest_log_pinned = false;
+ bool need_abort = false;
/* we only allow rename subvolume link between subvolumes */
if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
@@ -9135,6 +9148,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
old_idx);
if (ret)
goto out_fail;
+ need_abort = true;
}
/* And now for the dest. */
@@ -9150,8 +9164,11 @@ static int btrfs_rename_exchange(struct inode *old_dir,
new_ino,
btrfs_ino(BTRFS_I(old_dir)),
new_idx);
- if (ret)
+ if (ret) {
+ if (need_abort)
+ btrfs_abort_transaction(trans, ret);
goto out_fail;
+ }
}
/* Update inode version and ctime/mtime. */
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index d434dc78dadf..9178da07cc9c 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -203,10 +203,7 @@ static int clone_copy_inline_extent(struct inode *dst,
* inline extent's data to the page.
*/
ASSERT(key.offset > 0);
- ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
- inline_data, size, datal,
- comp_type);
- goto out;
+ goto copy_to_page;
}
} else if (i_size_read(dst) <= datal) {
struct btrfs_file_extent_item *ei;
@@ -222,13 +219,10 @@ static int clone_copy_inline_extent(struct inode *dst,
BTRFS_FILE_EXTENT_INLINE)
goto copy_inline_extent;
- ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
- inline_data, size, datal, comp_type);
- goto out;
+ goto copy_to_page;
}
copy_inline_extent:
- ret = 0;
/*
* We have no extent items, or we have an extent at offset 0 which may
* or may not be inlined. All these cases are dealt the same way.
@@ -240,11 +234,13 @@ copy_inline_extent:
* clone. Deal with all these cases by copying the inline extent
* data into the respective page at the destination inode.
*/
- ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
- inline_data, size, datal, comp_type);
- goto out;
+ goto copy_to_page;
}
+ /*
+ * Release path before starting a new transaction so we don't hold locks
+ * that would confuse lockdep.
+ */
btrfs_release_path(path);
/*
* If we end up here it means were copy the inline extent into a leaf
@@ -282,11 +278,6 @@ copy_inline_extent:
out:
if (!ret && !trans) {
/*
- * Release path before starting a new transaction so we don't
- * hold locks that would confuse lockdep.
- */
- btrfs_release_path(path);
- /*
* No transaction here means we copied the inline extent into a
* page of the destination inode.
*
@@ -306,6 +297,21 @@ out:
*trans_out = trans;
return ret;
+
+copy_to_page:
+ /*
+ * Release our path because we don't need it anymore and also because
+ * copy_inline_to_page() needs to reserve data and metadata, which may
+ * need to flush delalloc when we are low on available space and
+ * therefore cause a deadlock if writeback of an inline extent needs to
+ * write to the same leaf or an ordered extent completion needs to write
+ * to the same leaf.
+ */
+ btrfs_release_path(path);
+
+ ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
+ inline_data, size, datal, comp_type);
+ goto out;
}
/**
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 326be57f2828..dbcf8bb2f3b9 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1574,7 +1574,9 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
if (ret)
goto out;
- btrfs_update_inode(trans, root, BTRFS_I(inode));
+ ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+ if (ret)
+ goto out;
}
ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + namelen;
@@ -1749,7 +1751,9 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
if (nlink != inode->i_nlink) {
set_nlink(inode, nlink);
- btrfs_update_inode(trans, root, BTRFS_I(inode));
+ ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+ if (ret)
+ goto out;
}
BTRFS_I(inode)->index_cnt = (u64)-1;
@@ -1787,6 +1791,7 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans,
break;
if (ret == 1) {
+ ret = 0;
if (path->slots[0] == 0)
break;
path->slots[0]--;
@@ -1799,17 +1804,19 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans,
ret = btrfs_del_item(trans, root, path);
if (ret)
- goto out;
+ break;
btrfs_release_path(path);
inode = read_one_inode(root, key.offset);
- if (!inode)
- return -EIO;
+ if (!inode) {
+ ret = -EIO;
+ break;
+ }
ret = fixup_inode_link_count(trans, root, inode);
iput(inode);
if (ret)
- goto out;
+ break;
/*
* fixup on a directory may create new entries,
@@ -1818,8 +1825,6 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans,
*/
key.offset = (u64)-1;
}
- ret = 0;
-out:
btrfs_release_path(path);
return ret;
}
@@ -3297,6 +3302,22 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
* begins and releases it only after writing its superblock.
*/
mutex_lock(&fs_info->tree_log_mutex);
+
+ /*
+ * The previous transaction writeout phase could have failed, and thus
+ * marked the fs in an error state. We must not commit here, as we
+ * could have updated our generation in the super_for_commit and
+ * writing the super here would result in transid mismatches. If there
+ * is an error here just bail.
+ */
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
+ ret = -EIO;
+ btrfs_set_log_full_commit(trans);
+ btrfs_abort_transaction(trans, ret);
+ mutex_unlock(&fs_info->tree_log_mutex);
+ goto out_wake_log_root;
+ }
+
btrfs_set_super_log_root(fs_info->super_for_commit, log_root_start);
btrfs_set_super_log_root_level(fs_info->super_for_commit, log_root_level);
ret = write_all_supers(fs_info, 1);
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 1bb8ee97aae0..f1f3b10d1dbb 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -150,6 +150,18 @@ static inline u32 sb_zone_number(int shift, int mirror)
return (u32)zone;
}
+static inline sector_t zone_start_sector(u32 zone_number,
+ struct block_device *bdev)
+{
+ return (sector_t)zone_number << ilog2(bdev_zone_sectors(bdev));
+}
+
+static inline u64 zone_start_physical(u32 zone_number,
+ struct btrfs_zoned_device_info *zone_info)
+{
+ return (u64)zone_number << zone_info->zone_size_shift;
+}
+
/*
* Emulate blkdev_report_zones() for a non-zoned device. It slices up the block
* device into static sized chunks and fake a conventional zone on each of
@@ -405,8 +417,8 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
if (sb_zone + 1 >= zone_info->nr_zones)
continue;
- sector = sb_zone << (zone_info->zone_size_shift - SECTOR_SHIFT);
- ret = btrfs_get_dev_zones(device, sector << SECTOR_SHIFT,
+ ret = btrfs_get_dev_zones(device,
+ zone_start_physical(sb_zone, zone_info),
&zone_info->sb_zones[sb_pos],
&nr_zones);
if (ret)
@@ -721,7 +733,7 @@ int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw,
if (sb_zone + 1 >= nr_zones)
return -ENOENT;
- ret = blkdev_report_zones(bdev, sb_zone << zone_sectors_shift,
+ ret = blkdev_report_zones(bdev, zone_start_sector(sb_zone, bdev),
BTRFS_NR_SB_LOG_ZONES, copy_zone_info_cb,
zones);
if (ret < 0)
@@ -826,7 +838,7 @@ int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
return -ENOENT;
return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
- sb_zone << zone_sectors_shift,
+ zone_start_sector(sb_zone, bdev),
zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS);
}
@@ -878,7 +890,8 @@ u64 btrfs_find_allocatable_zones(struct btrfs_device *device, u64 hole_start,
if (!(end <= sb_zone ||
sb_zone + BTRFS_NR_SB_LOG_ZONES <= begin)) {
have_sb = true;
- pos = ((u64)sb_zone + BTRFS_NR_SB_LOG_ZONES) << shift;
+ pos = zone_start_physical(
+ sb_zone + BTRFS_NR_SB_LOG_ZONES, zinfo);
break;
}
diff --git a/fs/coredump.c b/fs/coredump.c
index 2868e3e171ae..c3d8fc14b993 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -519,7 +519,7 @@ static bool dump_interrupted(void)
* but then we need to teach dump_write() to restart and clear
* TIF_SIGPENDING.
*/
- return signal_pending(current);
+ return fatal_signal_pending(current) || freezing(current);
}
static void wait_for_dump_helpers(struct file *file)
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index e813acfaa6e8..ba7c01cd9a5d 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -893,7 +893,7 @@ ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf,
copy[copy_len] = '\n';
- ret = simple_read_from_buffer(user_buf, count, ppos, copy, copy_len);
+ ret = simple_read_from_buffer(user_buf, count, ppos, copy, len);
kfree(copy);
return ret;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 77c84d6f1af6..cbf37b2cf871 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3206,7 +3206,10 @@ static int ext4_split_extent_at(handle_t *handle,
ext4_ext_mark_unwritten(ex2);
err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags);
- if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+ if (err != -ENOSPC && err != -EDQUOT)
+ goto out;
+
+ if (EXT4_EXT_MAY_ZEROOUT & split_flag) {
if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
if (split_flag & EXT4_EXT_DATA_VALID1) {
err = ext4_ext_zeroout(inode, ex2);
@@ -3232,25 +3235,22 @@ static int ext4_split_extent_at(handle_t *handle,
ext4_ext_pblock(&orig_ex));
}
- if (err)
- goto fix_extent_len;
- /* update the extent length and mark as initialized */
- ex->ee_len = cpu_to_le16(ee_len);
- ext4_ext_try_to_merge(handle, inode, path, ex);
- err = ext4_ext_dirty(handle, inode, path + path->p_depth);
- if (err)
- goto fix_extent_len;
-
- /* update extent status tree */
- err = ext4_zeroout_es(inode, &zero_ex);
-
- goto out;
- } else if (err)
- goto fix_extent_len;
-
-out:
- ext4_ext_show_leaf(inode, path);
- return err;
+ if (!err) {
+ /* update the extent length and mark as initialized */
+ ex->ee_len = cpu_to_le16(ee_len);
+ ext4_ext_try_to_merge(handle, inode, path, ex);
+ err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+ if (!err)
+ /* update extent status tree */
+ err = ext4_zeroout_es(inode, &zero_ex);
+ /* If we failed at this point, we don't know in which
+ * state the extent tree exactly is so don't try to fix
+ * length of the original extent as it may do even more
+ * damage.
+ */
+ goto out;
+ }
+ }
fix_extent_len:
ex->ee_len = orig_ex.ee_len;
@@ -3260,6 +3260,9 @@ fix_extent_len:
*/
ext4_ext_dirty(handle, inode, path + path->p_depth);
return err;
+out:
+ ext4_ext_show_leaf(inode, path);
+ return err;
}
/*
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index f98ca4f37ef6..e8195229c252 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1288,28 +1288,29 @@ struct dentry_info_args {
};
static inline void tl_to_darg(struct dentry_info_args *darg,
- struct ext4_fc_tl *tl)
+ struct ext4_fc_tl *tl, u8 *val)
{
- struct ext4_fc_dentry_info *fcd;
+ struct ext4_fc_dentry_info fcd;
- fcd = (struct ext4_fc_dentry_info *)ext4_fc_tag_val(tl);
+ memcpy(&fcd, val, sizeof(fcd));
- darg->parent_ino = le32_to_cpu(fcd->fc_parent_ino);
- darg->ino = le32_to_cpu(fcd->fc_ino);
- darg->dname = fcd->fc_dname;
- darg->dname_len = ext4_fc_tag_len(tl) -
- sizeof(struct ext4_fc_dentry_info);
+ darg->parent_ino = le32_to_cpu(fcd.fc_parent_ino);
+ darg->ino = le32_to_cpu(fcd.fc_ino);
+ darg->dname = val + offsetof(struct ext4_fc_dentry_info, fc_dname);
+ darg->dname_len = le16_to_cpu(tl->fc_len) -
+ sizeof(struct ext4_fc_dentry_info);
}
/* Unlink replay function */
-static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl)
+static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl,
+ u8 *val)
{
struct inode *inode, *old_parent;
struct qstr entry;
struct dentry_info_args darg;
int ret = 0;
- tl_to_darg(&darg, tl);
+ tl_to_darg(&darg, tl, val);
trace_ext4_fc_replay(sb, EXT4_FC_TAG_UNLINK, darg.ino,
darg.parent_ino, darg.dname_len);
@@ -1399,13 +1400,14 @@ out:
}
/* Link replay function */
-static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl)
+static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl,
+ u8 *val)
{
struct inode *inode;
struct dentry_info_args darg;
int ret = 0;
- tl_to_darg(&darg, tl);
+ tl_to_darg(&darg, tl, val);
trace_ext4_fc_replay(sb, EXT4_FC_TAG_LINK, darg.ino,
darg.parent_ino, darg.dname_len);
@@ -1450,9 +1452,10 @@ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino)
/*
* Inode replay function
*/
-static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
+static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl,
+ u8 *val)
{
- struct ext4_fc_inode *fc_inode;
+ struct ext4_fc_inode fc_inode;
struct ext4_inode *raw_inode;
struct ext4_inode *raw_fc_inode;
struct inode *inode = NULL;
@@ -1460,9 +1463,9 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
int inode_len, ino, ret, tag = le16_to_cpu(tl->fc_tag);
struct ext4_extent_header *eh;
- fc_inode = (struct ext4_fc_inode *)ext4_fc_tag_val(tl);
+ memcpy(&fc_inode, val, sizeof(fc_inode));
- ino = le32_to_cpu(fc_inode->fc_ino);
+ ino = le32_to_cpu(fc_inode.fc_ino);
trace_ext4_fc_replay(sb, tag, ino, 0, 0);
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
@@ -1474,12 +1477,13 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
ext4_fc_record_modified_inode(sb, ino);
- raw_fc_inode = (struct ext4_inode *)fc_inode->fc_raw_inode;
+ raw_fc_inode = (struct ext4_inode *)
+ (val + offsetof(struct ext4_fc_inode, fc_raw_inode));
ret = ext4_get_fc_inode_loc(sb, ino, &iloc);
if (ret)
goto out;
- inode_len = ext4_fc_tag_len(tl) - sizeof(struct ext4_fc_inode);
+ inode_len = le16_to_cpu(tl->fc_len) - sizeof(struct ext4_fc_inode);
raw_inode = ext4_raw_inode(&iloc);
memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block));
@@ -1547,14 +1551,15 @@ out:
* inode for which we are trying to create a dentry here, should already have
* been replayed before we start here.
*/
-static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
+static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl,
+ u8 *val)
{
int ret = 0;
struct inode *inode = NULL;
struct inode *dir = NULL;
struct dentry_info_args darg;
- tl_to_darg(&darg, tl);
+ tl_to_darg(&darg, tl, val);
trace_ext4_fc_replay(sb, EXT4_FC_TAG_CREAT, darg.ino,
darg.parent_ino, darg.dname_len);
@@ -1633,9 +1638,9 @@ static int ext4_fc_record_regions(struct super_block *sb, int ino,
/* Replay add range tag */
static int ext4_fc_replay_add_range(struct super_block *sb,
- struct ext4_fc_tl *tl)
+ struct ext4_fc_tl *tl, u8 *val)
{
- struct ext4_fc_add_range *fc_add_ex;
+ struct ext4_fc_add_range fc_add_ex;
struct ext4_extent newex, *ex;
struct inode *inode;
ext4_lblk_t start, cur;
@@ -1645,15 +1650,14 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
struct ext4_ext_path *path = NULL;
int ret;
- fc_add_ex = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl);
- ex = (struct ext4_extent *)&fc_add_ex->fc_ex;
+ memcpy(&fc_add_ex, val, sizeof(fc_add_ex));
+ ex = (struct ext4_extent *)&fc_add_ex.fc_ex;
trace_ext4_fc_replay(sb, EXT4_FC_TAG_ADD_RANGE,
- le32_to_cpu(fc_add_ex->fc_ino), le32_to_cpu(ex->ee_block),
+ le32_to_cpu(fc_add_ex.fc_ino), le32_to_cpu(ex->ee_block),
ext4_ext_get_actual_len(ex));
- inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino),
- EXT4_IGET_NORMAL);
+ inode = ext4_iget(sb, le32_to_cpu(fc_add_ex.fc_ino), EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
@@ -1762,32 +1766,33 @@ next:
/* Replay DEL_RANGE tag */
static int
-ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
+ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl,
+ u8 *val)
{
struct inode *inode;
- struct ext4_fc_del_range *lrange;
+ struct ext4_fc_del_range lrange;
struct ext4_map_blocks map;
ext4_lblk_t cur, remaining;
int ret;
- lrange = (struct ext4_fc_del_range *)ext4_fc_tag_val(tl);
- cur = le32_to_cpu(lrange->fc_lblk);
- remaining = le32_to_cpu(lrange->fc_len);
+ memcpy(&lrange, val, sizeof(lrange));
+ cur = le32_to_cpu(lrange.fc_lblk);
+ remaining = le32_to_cpu(lrange.fc_len);
trace_ext4_fc_replay(sb, EXT4_FC_TAG_DEL_RANGE,
- le32_to_cpu(lrange->fc_ino), cur, remaining);
+ le32_to_cpu(lrange.fc_ino), cur, remaining);
- inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL);
+ inode = ext4_iget(sb, le32_to_cpu(lrange.fc_ino), EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
- jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino));
+ jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange.fc_ino));
return 0;
}
ret = ext4_fc_record_modified_inode(sb, inode->i_ino);
jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n",
- inode->i_ino, le32_to_cpu(lrange->fc_lblk),
- le32_to_cpu(lrange->fc_len));
+ inode->i_ino, le32_to_cpu(lrange.fc_lblk),
+ le32_to_cpu(lrange.fc_len));
while (remaining > 0) {
map.m_lblk = cur;
map.m_len = remaining;
@@ -1808,8 +1813,8 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
}
ret = ext4_punch_hole(inode,
- le32_to_cpu(lrange->fc_lblk) << sb->s_blocksize_bits,
- le32_to_cpu(lrange->fc_len) << sb->s_blocksize_bits);
+ le32_to_cpu(lrange.fc_lblk) << sb->s_blocksize_bits,
+ le32_to_cpu(lrange.fc_len) << sb->s_blocksize_bits);
if (ret)
jbd_debug(1, "ext4_punch_hole returned %d", ret);
ext4_ext_replay_shrink_inode(inode,
@@ -1925,11 +1930,11 @@ static int ext4_fc_replay_scan(journal_t *journal,
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_fc_replay_state *state;
int ret = JBD2_FC_REPLAY_CONTINUE;
- struct ext4_fc_add_range *ext;
- struct ext4_fc_tl *tl;
- struct ext4_fc_tail *tail;
- __u8 *start, *end;
- struct ext4_fc_head *head;
+ struct ext4_fc_add_range ext;
+ struct ext4_fc_tl tl;
+ struct ext4_fc_tail tail;
+ __u8 *start, *end, *cur, *val;
+ struct ext4_fc_head head;
struct ext4_extent *ex;
state = &sbi->s_fc_replay_state;
@@ -1956,15 +1961,17 @@ static int ext4_fc_replay_scan(journal_t *journal,
}
state->fc_replay_expected_off++;
- fc_for_each_tl(start, end, tl) {
+ for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) {
+ memcpy(&tl, cur, sizeof(tl));
+ val = cur + sizeof(tl);
jbd_debug(3, "Scan phase, tag:%s, blk %lld\n",
- tag2str(le16_to_cpu(tl->fc_tag)), bh->b_blocknr);
- switch (le16_to_cpu(tl->fc_tag)) {
+ tag2str(le16_to_cpu(tl.fc_tag)), bh->b_blocknr);
+ switch (le16_to_cpu(tl.fc_tag)) {
case EXT4_FC_TAG_ADD_RANGE:
- ext = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl);
- ex = (struct ext4_extent *)&ext->fc_ex;
+ memcpy(&ext, val, sizeof(ext));
+ ex = (struct ext4_extent *)&ext.fc_ex;
ret = ext4_fc_record_regions(sb,
- le32_to_cpu(ext->fc_ino),
+ le32_to_cpu(ext.fc_ino),
le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex),
ext4_ext_get_actual_len(ex));
if (ret < 0)
@@ -1978,18 +1985,18 @@ static int ext4_fc_replay_scan(journal_t *journal,
case EXT4_FC_TAG_INODE:
case EXT4_FC_TAG_PAD:
state->fc_cur_tag++;
- state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
- sizeof(*tl) + ext4_fc_tag_len(tl));
+ state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur,
+ sizeof(tl) + le16_to_cpu(tl.fc_len));
break;
case EXT4_FC_TAG_TAIL:
state->fc_cur_tag++;
- tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl);
- state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
- sizeof(*tl) +
+ memcpy(&tail, val, sizeof(tail));
+ state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur,
+ sizeof(tl) +
offsetof(struct ext4_fc_tail,
fc_crc));
- if (le32_to_cpu(tail->fc_tid) == expected_tid &&
- le32_to_cpu(tail->fc_crc) == state->fc_crc) {
+ if (le32_to_cpu(tail.fc_tid) == expected_tid &&
+ le32_to_cpu(tail.fc_crc) == state->fc_crc) {
state->fc_replay_num_tags = state->fc_cur_tag;
state->fc_regions_valid =
state->fc_regions_used;
@@ -2000,19 +2007,19 @@ static int ext4_fc_replay_scan(journal_t *journal,
state->fc_crc = 0;
break;
case EXT4_FC_TAG_HEAD:
- head = (struct ext4_fc_head *)ext4_fc_tag_val(tl);
- if (le32_to_cpu(head->fc_features) &
+ memcpy(&head, val, sizeof(head));
+ if (le32_to_cpu(head.fc_features) &
~EXT4_FC_SUPPORTED_FEATURES) {
ret = -EOPNOTSUPP;
break;
}
- if (le32_to_cpu(head->fc_tid) != expected_tid) {
+ if (le32_to_cpu(head.fc_tid) != expected_tid) {
ret = JBD2_FC_REPLAY_STOP;
break;
}
state->fc_cur_tag++;
- state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
- sizeof(*tl) + ext4_fc_tag_len(tl));
+ state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur,
+ sizeof(tl) + le16_to_cpu(tl.fc_len));
break;
default:
ret = state->fc_replay_num_tags ?
@@ -2036,11 +2043,11 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
{
struct super_block *sb = journal->j_private;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_fc_tl *tl;
- __u8 *start, *end;
+ struct ext4_fc_tl tl;
+ __u8 *start, *end, *cur, *val;
int ret = JBD2_FC_REPLAY_CONTINUE;
struct ext4_fc_replay_state *state = &sbi->s_fc_replay_state;
- struct ext4_fc_tail *tail;
+ struct ext4_fc_tail tail;
if (pass == PASS_SCAN) {
state->fc_current_pass = PASS_SCAN;
@@ -2067,49 +2074,52 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
start = (u8 *)bh->b_data;
end = (__u8 *)bh->b_data + journal->j_blocksize - 1;
- fc_for_each_tl(start, end, tl) {
+ for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) {
+ memcpy(&tl, cur, sizeof(tl));
+ val = cur + sizeof(tl);
+
if (state->fc_replay_num_tags == 0) {
ret = JBD2_FC_REPLAY_STOP;
ext4_fc_set_bitmaps_and_counters(sb);
break;
}
jbd_debug(3, "Replay phase, tag:%s\n",
- tag2str(le16_to_cpu(tl->fc_tag)));
+ tag2str(le16_to_cpu(tl.fc_tag)));
state->fc_replay_num_tags--;
- switch (le16_to_cpu(tl->fc_tag)) {
+ switch (le16_to_cpu(tl.fc_tag)) {
case EXT4_FC_TAG_LINK:
- ret = ext4_fc_replay_link(sb, tl);
+ ret = ext4_fc_replay_link(sb, &tl, val);
break;
case EXT4_FC_TAG_UNLINK:
- ret = ext4_fc_replay_unlink(sb, tl);
+ ret = ext4_fc_replay_unlink(sb, &tl, val);
break;
case EXT4_FC_TAG_ADD_RANGE:
- ret = ext4_fc_replay_add_range(sb, tl);
+ ret = ext4_fc_replay_add_range(sb, &tl, val);
break;
case EXT4_FC_TAG_CREAT:
- ret = ext4_fc_replay_create(sb, tl);
+ ret = ext4_fc_replay_create(sb, &tl, val);
break;
case EXT4_FC_TAG_DEL_RANGE:
- ret = ext4_fc_replay_del_range(sb, tl);
+ ret = ext4_fc_replay_del_range(sb, &tl, val);
break;
case EXT4_FC_TAG_INODE:
- ret = ext4_fc_replay_inode(sb, tl);
+ ret = ext4_fc_replay_inode(sb, &tl, val);
break;
case EXT4_FC_TAG_PAD:
trace_ext4_fc_replay(sb, EXT4_FC_TAG_PAD, 0,
- ext4_fc_tag_len(tl), 0);
+ le16_to_cpu(tl.fc_len), 0);
break;
case EXT4_FC_TAG_TAIL:
trace_ext4_fc_replay(sb, EXT4_FC_TAG_TAIL, 0,
- ext4_fc_tag_len(tl), 0);
- tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl);
- WARN_ON(le32_to_cpu(tail->fc_tid) != expected_tid);
+ le16_to_cpu(tl.fc_len), 0);
+ memcpy(&tail, val, sizeof(tail));
+ WARN_ON(le32_to_cpu(tail.fc_tid) != expected_tid);
break;
case EXT4_FC_TAG_HEAD:
break;
default:
- trace_ext4_fc_replay(sb, le16_to_cpu(tl->fc_tag), 0,
- ext4_fc_tag_len(tl), 0);
+ trace_ext4_fc_replay(sb, le16_to_cpu(tl.fc_tag), 0,
+ le16_to_cpu(tl.fc_len), 0);
ret = -ECANCELED;
break;
}
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index b77f70f55a62..937c381b4c85 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -153,13 +153,6 @@ struct ext4_fc_replay_state {
#define region_last(__region) (((__region)->lblk) + ((__region)->len) - 1)
#endif
-#define fc_for_each_tl(__start, __end, __tl) \
- for (tl = (struct ext4_fc_tl *)(__start); \
- (__u8 *)tl < (__u8 *)(__end); \
- tl = (struct ext4_fc_tl *)((__u8 *)tl + \
- sizeof(struct ext4_fc_tl) + \
- + le16_to_cpu(tl->fc_len)))
-
static inline const char *tag2str(__u16 tag)
{
switch (tag) {
@@ -186,16 +179,4 @@ static inline const char *tag2str(__u16 tag)
}
}
-/* Get length of a particular tlv */
-static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl)
-{
- return le16_to_cpu(tl->fc_len);
-}
-
-/* Get a pointer to "value" of a tlv */
-static inline __u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl)
-{
- return (__u8 *)tl + sizeof(*tl);
-}
-
#endif /* __FAST_COMMIT_H__ */
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 81a17a3cd80e..9bab7fd4ccd5 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -322,14 +322,16 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
if (is_directory) {
count = ext4_used_dirs_count(sb, gdp) - 1;
ext4_used_dirs_set(sb, gdp, count);
- percpu_counter_dec(&sbi->s_dirs_counter);
+ if (percpu_counter_initialized(&sbi->s_dirs_counter))
+ percpu_counter_dec(&sbi->s_dirs_counter);
}
ext4_inode_bitmap_csum_set(sb, block_group, gdp, bitmap_bh,
EXT4_INODES_PER_GROUP(sb) / 8);
ext4_group_desc_csum_set(sb, block_group, gdp);
ext4_unlock_group(sb, block_group);
- percpu_counter_inc(&sbi->s_freeinodes_counter);
+ if (percpu_counter_initialized(&sbi->s_freeinodes_counter))
+ percpu_counter_inc(&sbi->s_freeinodes_counter);
if (sbi->s_log_groups_per_flex) {
struct flex_groups *fg;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 3239e6669e84..c2c22c2baac0 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3217,7 +3217,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
*/
if (sbi->s_es->s_log_groups_per_flex >= 32) {
ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group");
- goto err_freesgi;
+ goto err_freebuddy;
}
sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex,
BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9));
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index afb9d05a99ba..a4af26d4459a 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1376,7 +1376,8 @@ int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
struct dx_hash_info *hinfo = &name->hinfo;
int len;
- if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding) {
+ if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding ||
+ (IS_ENCRYPTED(dir) && !fscrypt_has_encryption_key(dir))) {
cf_name->name = NULL;
return 0;
}
@@ -1427,7 +1428,8 @@ static bool ext4_match(struct inode *parent,
#endif
#ifdef CONFIG_UNICODE
- if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent)) {
+ if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) &&
+ (!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) {
if (fname->cf_name.name) {
struct qstr cf = {.name = fname->cf_name.name,
.len = fname->cf_name.len};
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7dc94f3e18e6..d29f6aa7d96e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4462,14 +4462,20 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
if (sb->s_blocksize != blocksize) {
+ /*
+ * bh must be released before kill_bdev(), otherwise
+ * it won't be freed and its page also. kill_bdev()
+ * is called by sb_set_blocksize().
+ */
+ brelse(bh);
/* Validate the filesystem blocksize */
if (!sb_set_blocksize(sb, blocksize)) {
ext4_msg(sb, KERN_ERR, "bad block size %d",
blocksize);
+ bh = NULL;
goto failed_mount;
}
- brelse(bh);
logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
offset = do_div(logical_sb_block, blocksize);
bh = ext4_sb_bread_unmovable(sb, logical_sb_block);
@@ -5202,8 +5208,9 @@ failed_mount:
kfree(get_qf_name(sb, sbi, i));
#endif
fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
- ext4_blkdev_remove(sbi);
+ /* ext4_blkdev_remove() calls kill_bdev(), release bh before it. */
brelse(bh);
+ ext4_blkdev_remove(sbi);
out_fail:
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 6f825dedc3d4..55fcab60a59a 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -315,7 +315,9 @@ EXT4_ATTR_FEATURE(verity);
#endif
EXT4_ATTR_FEATURE(metadata_csum_seed);
EXT4_ATTR_FEATURE(fast_commit);
+#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
EXT4_ATTR_FEATURE(encrypted_casefold);
+#endif
static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(lazy_itable_init),
@@ -333,7 +335,9 @@ static struct attribute *ext4_feat_attrs[] = {
#endif
ATTR_LIST(metadata_csum_seed),
ATTR_LIST(fast_commit),
+#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
ATTR_LIST(encrypted_casefold),
+#endif
NULL,
};
ATTRIBUTE_GROUPS(ext4_feat);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index a0b542d84cd9..493a83e3f590 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -911,8 +911,11 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
current->backing_dev_info = inode_to_bdi(inode);
buffered = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
current->backing_dev_info = NULL;
- if (unlikely(buffered <= 0))
+ if (unlikely(buffered <= 0)) {
+ if (!ret)
+ ret = buffered;
goto out_unlock;
+ }
/*
* We need to ensure that the page cache pages are written to
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index ea7fc5c641c7..d9cb261f55b0 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -582,6 +582,16 @@ out_locked:
spin_unlock(&gl->gl_lockref.lock);
}
+static bool is_system_glock(struct gfs2_glock *gl)
+{
+ struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+ struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+
+ if (gl == m_ip->i_gl)
+ return true;
+ return false;
+}
+
/**
* do_xmote - Calls the DLM to change the state of a lock
* @gl: The lock state
@@ -671,17 +681,25 @@ skip_inval:
* to see sd_log_error and withdraw, and in the meantime, requeue the
* work for later.
*
+ * We make a special exception for some system glocks, such as the
+ * system statfs inode glock, which needs to be granted before the
+ * gfs2_quotad daemon can exit, and that exit needs to finish before
+ * we can unmount the withdrawn file system.
+ *
* However, if we're just unlocking the lock (say, for unmount, when
* gfs2_gl_hash_clear calls clear_glock) and recovery is complete
* then it's okay to tell dlm to unlock it.
*/
if (unlikely(sdp->sd_log_error && !gfs2_withdrawn(sdp)))
gfs2_withdraw_delayed(sdp);
- if (glock_blocked_by_withdraw(gl)) {
- if (target != LM_ST_UNLOCKED ||
- test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags)) {
+ if (glock_blocked_by_withdraw(gl) &&
+ (target != LM_ST_UNLOCKED ||
+ test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags))) {
+ if (!is_system_glock(gl)) {
gfs2_glock_queue_work(gl, GL_GLOCK_DFT_HOLD);
goto out;
+ } else {
+ clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
}
}
@@ -1466,9 +1484,11 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
glock_blocked_by_withdraw(gl) &&
gh->gh_gl != sdp->sd_jinode_gl) {
sdp->sd_glock_dqs_held++;
+ spin_unlock(&gl->gl_lockref.lock);
might_sleep();
wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY,
TASK_UNINTERRUPTIBLE);
+ spin_lock(&gl->gl_lockref.lock);
}
if (gh->gh_flags & GL_NOCACHE)
handle_callback(gl, LM_ST_UNLOCKED, 0, false);
@@ -1775,6 +1795,7 @@ __acquires(&lru_lock)
while(!list_empty(list)) {
gl = list_first_entry(list, struct gfs2_glock, gl_lru);
list_del_init(&gl->gl_lru);
+ clear_bit(GLF_LRU, &gl->gl_flags);
if (!spin_trylock(&gl->gl_lockref.lock)) {
add_back_to_lru:
list_add(&gl->gl_lru, &lru_list);
@@ -1820,7 +1841,6 @@ static long gfs2_scan_glock_lru(int nr)
if (!test_bit(GLF_LOCK, &gl->gl_flags)) {
list_move(&gl->gl_lru, &dispose);
atomic_dec(&lru_count);
- clear_bit(GLF_LRU, &gl->gl_flags);
freed++;
continue;
}
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 454095e9fedf..54d3fbeb3002 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -396,7 +396,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
struct timespec64 atime;
u16 height, depth;
umode_t mode = be32_to_cpu(str->di_mode);
- bool is_new = ip->i_inode.i_flags & I_NEW;
+ bool is_new = ip->i_inode.i_state & I_NEW;
if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
goto corrupt;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 97d54e581a7b..42c15cfc0821 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -926,10 +926,10 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
}
/**
- * ail_drain - drain the ail lists after a withdraw
+ * gfs2_ail_drain - drain the ail lists after a withdraw
* @sdp: Pointer to GFS2 superblock
*/
-static void ail_drain(struct gfs2_sbd *sdp)
+void gfs2_ail_drain(struct gfs2_sbd *sdp)
{
struct gfs2_trans *tr;
@@ -956,6 +956,7 @@ static void ail_drain(struct gfs2_sbd *sdp)
list_del(&tr->tr_list);
gfs2_trans_free(sdp, tr);
}
+ gfs2_drain_revokes(sdp);
spin_unlock(&sdp->sd_ail_lock);
}
@@ -1162,7 +1163,6 @@ out_withdraw:
if (tr && list_empty(&tr->tr_list))
list_add(&tr->tr_list, &sdp->sd_ail1_list);
spin_unlock(&sdp->sd_ail_lock);
- ail_drain(sdp); /* frees all transactions */
tr = NULL;
goto out_end;
}
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index eea58015710e..fc905c2af53c 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -93,5 +93,6 @@ extern int gfs2_logd(void *data);
extern void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
extern void gfs2_glock_remove_revoke(struct gfs2_glock *gl);
extern void gfs2_flush_revokes(struct gfs2_sbd *sdp);
+extern void gfs2_ail_drain(struct gfs2_sbd *sdp);
#endif /* __LOG_DOT_H__ */
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 221e7118cc3b..8ee05d25dfa6 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -885,7 +885,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
gfs2_log_write_page(sdp, page);
}
-static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+void gfs2_drain_revokes(struct gfs2_sbd *sdp)
{
struct list_head *head = &sdp->sd_log_revokes;
struct gfs2_bufdata *bd;
@@ -900,6 +900,11 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
}
}
+static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+{
+ gfs2_drain_revokes(sdp);
+}
+
static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
struct gfs2_log_header_host *head, int pass)
{
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index 31b6dd0d2e5d..f707601597dc 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -20,6 +20,7 @@ extern void gfs2_log_submit_bio(struct bio **biop, int opf);
extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
struct gfs2_log_header_host *head, bool keep_cache);
+extern void gfs2_drain_revokes(struct gfs2_sbd *sdp);
static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
{
return sdp->sd_ldptrs;
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 3e08027a6c81..f4325b44956d 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -131,6 +131,7 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) || !sdp->sd_jdesc)
return;
+ gfs2_ail_drain(sdp); /* frees all transactions */
inode = sdp->sd_jdesc->jd_inode;
ip = GFS2_I(inode);
i_gl = ip->i_gl;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 903458afd56c..fa8794c61af7 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -783,6 +783,11 @@ struct io_task_work {
task_work_func_t func;
};
+enum {
+ IORING_RSRC_FILE = 0,
+ IORING_RSRC_BUFFER = 1,
+};
+
/*
* NOTE! Each of the iocb union members has the file pointer
* as the first entry in their struct definition. So you can
@@ -8228,6 +8233,7 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages,
{
int i, ret;
+ imu->acct_pages = 0;
for (i = 0; i < nr_pages; i++) {
if (!PageCompound(pages[i])) {
imu->acct_pages++;
@@ -9670,7 +9676,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL |
IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED |
- IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS;
+ IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS |
+ IORING_FEAT_RSRC_TAGS;
if (copy_to_user(params, p, sizeof(*p))) {
ret = -EFAULT;
@@ -9910,7 +9917,7 @@ static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg,
}
static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
- unsigned size)
+ unsigned size, unsigned type)
{
struct io_uring_rsrc_update2 up;
@@ -9918,13 +9925,13 @@ static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
return -EINVAL;
if (copy_from_user(&up, arg, sizeof(up)))
return -EFAULT;
- if (!up.nr)
+ if (!up.nr || up.resv)
return -EINVAL;
- return __io_register_rsrc_update(ctx, up.type, &up, up.nr);
+ return __io_register_rsrc_update(ctx, type, &up, up.nr);
}
static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
- unsigned int size)
+ unsigned int size, unsigned int type)
{
struct io_uring_rsrc_register rr;
@@ -9935,10 +9942,10 @@ static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
memset(&rr, 0, sizeof(rr));
if (copy_from_user(&rr, arg, size))
return -EFAULT;
- if (!rr.nr)
+ if (!rr.nr || rr.resv || rr.resv2)
return -EINVAL;
- switch (rr.type) {
+ switch (type) {
case IORING_RSRC_FILE:
return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data),
rr.nr, u64_to_user_ptr(rr.tags));
@@ -9960,8 +9967,10 @@ static bool io_register_op_must_quiesce(int op)
case IORING_REGISTER_PROBE:
case IORING_REGISTER_PERSONALITY:
case IORING_UNREGISTER_PERSONALITY:
- case IORING_REGISTER_RSRC:
- case IORING_REGISTER_RSRC_UPDATE:
+ case IORING_REGISTER_FILES2:
+ case IORING_REGISTER_FILES_UPDATE2:
+ case IORING_REGISTER_BUFFERS2:
+ case IORING_REGISTER_BUFFERS_UPDATE:
return false;
default:
return true;
@@ -10087,11 +10096,19 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
case IORING_REGISTER_RESTRICTIONS:
ret = io_register_restrictions(ctx, arg, nr_args);
break;
- case IORING_REGISTER_RSRC:
- ret = io_register_rsrc(ctx, arg, nr_args);
+ case IORING_REGISTER_FILES2:
+ ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE);
+ break;
+ case IORING_REGISTER_FILES_UPDATE2:
+ ret = io_register_rsrc_update(ctx, arg, nr_args,
+ IORING_RSRC_FILE);
+ break;
+ case IORING_REGISTER_BUFFERS2:
+ ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER);
break;
- case IORING_REGISTER_RSRC_UPDATE:
- ret = io_register_rsrc_update(ctx, arg, nr_args);
+ case IORING_REGISTER_BUFFERS_UPDATE:
+ ret = io_register_rsrc_update(ctx, arg, nr_args,
+ IORING_RSRC_BUFFER);
break;
default:
ret = -EINVAL;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index cfeaadf56bf0..330f65727c45 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -406,7 +406,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
if (cl_init->hostname == NULL) {
WARN_ON(1);
- return NULL;
+ return ERR_PTR(-EINVAL);
}
/* see if the client already exists */
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 065cb04222a1..543d916f79ab 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -205,6 +205,7 @@ struct nfs4_exception {
struct inode *inode;
nfs4_stateid *stateid;
long timeout;
+ unsigned char task_is_privileged : 1;
unsigned char delay : 1,
recovering : 1,
retry : 1;
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 889a9f4c0310..42719384e25f 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -435,8 +435,8 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
*/
nfs_mark_client_ready(clp, -EPERM);
}
- nfs_put_client(clp);
clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags);
+ nfs_put_client(clp);
return old;
error:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0cd965882232..e653654c10bc 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -589,6 +589,8 @@ int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_
goto out_retry;
}
if (exception->recovering) {
+ if (exception->task_is_privileged)
+ return -EDEADLOCK;
ret = nfs4_wait_clnt_recover(clp);
if (test_bit(NFS_MIG_FAILED, &server->mig_status))
return -EIO;
@@ -614,6 +616,8 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server,
goto out_retry;
}
if (exception->recovering) {
+ if (exception->task_is_privileged)
+ return -EDEADLOCK;
rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task);
@@ -3878,6 +3882,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
server->caps |= NFS_CAP_HARDLINKS;
if (res.has_symlinks != 0)
server->caps |= NFS_CAP_SYMLINKS;
+#ifdef CONFIG_NFS_V4_SECURITY_LABEL
+ if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL)
+ server->caps |= NFS_CAP_SECURITY_LABEL;
+#endif
if (!(res.attr_bitmask[0] & FATTR4_WORD0_FILEID))
server->fattr_valid &= ~NFS_ATTR_FATTR_FILEID;
if (!(res.attr_bitmask[1] & FATTR4_WORD1_MODE))
@@ -3898,10 +3906,6 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
server->fattr_valid &= ~NFS_ATTR_FATTR_CTIME;
if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY))
server->fattr_valid &= ~NFS_ATTR_FATTR_MTIME;
-#ifdef CONFIG_NFS_V4_SECURITY_LABEL
- if (!(res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL))
- server->fattr_valid &= ~NFS_ATTR_FATTR_V4_SECURITY_LABEL;
-#endif
memcpy(server->attr_bitmask_nl, res.attr_bitmask,
sizeof(server->attr_bitmask));
server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
@@ -5968,6 +5972,14 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen
do {
err = __nfs4_proc_set_acl(inode, buf, buflen);
trace_nfs4_set_acl(inode, err);
+ if (err == -NFS4ERR_BADOWNER || err == -NFS4ERR_BADNAME) {
+ /*
+ * no need to retry since the kernel
+ * isn't involved in encoding the ACEs.
+ */
+ err = -EINVAL;
+ break;
+ }
err = nfs4_handle_exception(NFS_SERVER(inode), err,
&exception);
} while (exception.retry);
@@ -6409,6 +6421,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
struct nfs4_exception exception = {
.inode = data->inode,
.stateid = &data->stateid,
+ .task_is_privileged = data->args.seq_args.sa_privileged,
};
if (!nfs4_sequence_done(task, &data->res.seq_res))
@@ -6532,7 +6545,6 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
data = kzalloc(sizeof(*data), GFP_NOFS);
if (data == NULL)
return -ENOMEM;
- nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, 0);
nfs4_state_protect(server->nfs_client,
NFS_SP4_MACH_CRED_CLEANUP,
@@ -6563,6 +6575,12 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
}
}
+ if (!data->inode)
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1,
+ 1);
+ else
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1,
+ 0);
task_setup_data.callback_data = data;
msg.rpc_argp = &data->args;
msg.rpc_resp = &data->res;
@@ -9640,15 +9658,20 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync)
&task_setup_data.rpc_client, &msg);
dprintk("--> %s\n", __func__);
+ lrp->inode = nfs_igrab_and_active(lrp->args.inode);
if (!sync) {
- lrp->inode = nfs_igrab_and_active(lrp->args.inode);
if (!lrp->inode) {
nfs4_layoutreturn_release(lrp);
return -EAGAIN;
}
task_setup_data.flags |= RPC_TASK_ASYNC;
}
- nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1, 0);
+ if (!lrp->inode)
+ nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1,
+ 1);
+ else
+ nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1,
+ 0);
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index eb1ef3462e84..ccef43e02b48 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -430,10 +430,6 @@ TRACE_DEFINE_ENUM(O_CLOEXEC);
{ O_NOATIME, "O_NOATIME" }, \
{ O_CLOEXEC, "O_CLOEXEC" })
-TRACE_DEFINE_ENUM(FMODE_READ);
-TRACE_DEFINE_ENUM(FMODE_WRITE);
-TRACE_DEFINE_ENUM(FMODE_EXEC);
-
#define show_fmode_flags(mode) \
__print_flags(mode, "|", \
{ ((__force unsigned long)FMODE_READ), "READ" }, \
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 71fefb30e015..be5b6d2c01e7 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -424,11 +424,18 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
* events generated by the listener process itself, without disclosing
* the pids of other processes.
*/
- if (!capable(CAP_SYS_ADMIN) &&
+ if (FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) &&
task_tgid(current) != event->pid)
metadata.pid = 0;
- if (path && path->mnt && path->dentry) {
+ /*
+ * For now, fid mode is required for an unprivileged listener and
+ * fid mode does not report fd in events. Keep this check anyway
+ * for safety in case fid mode requirement is relaxed in the future
+ * to allow unprivileged listener to get events with no fd and no fid.
+ */
+ if (!FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) &&
+ path && path->mnt && path->dentry) {
fd = create_fd(group, path, &f);
if (fd < 0)
return fd;
@@ -1040,6 +1047,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
int f_flags, fd;
unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
unsigned int class = flags & FANOTIFY_CLASS_BITS;
+ unsigned int internal_flags = 0;
pr_debug("%s: flags=%x event_f_flags=%x\n",
__func__, flags, event_f_flags);
@@ -1053,6 +1061,13 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
*/
if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !fid_mode)
return -EPERM;
+
+ /*
+ * Setting the internal flag FANOTIFY_UNPRIV on the group
+ * prevents setting mount/filesystem marks on this group and
+ * prevents reporting pid and open fd in events.
+ */
+ internal_flags |= FANOTIFY_UNPRIV;
}
#ifdef CONFIG_AUDITSYSCALL
@@ -1105,7 +1120,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
goto out_destroy_group;
}
- group->fanotify_data.flags = flags;
+ group->fanotify_data.flags = flags | internal_flags;
group->memcg = get_mem_cgroup_from_mm(current->mm);
group->fanotify_data.merge_hash = fanotify_alloc_merge_hash();
@@ -1305,11 +1320,13 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
group = f.file->private_data;
/*
- * An unprivileged user is not allowed to watch a mount point nor
- * a filesystem.
+ * An unprivileged user is not allowed to setup mount nor filesystem
+ * marks. This also includes setting up such marks by a group that
+ * was initialized by an unprivileged user.
*/
ret = -EPERM;
- if (!capable(CAP_SYS_ADMIN) &&
+ if ((!capable(CAP_SYS_ADMIN) ||
+ FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV)) &&
mark_type != FAN_MARK_INODE)
goto fput_and_out;
@@ -1460,6 +1477,7 @@ static int __init fanotify_user_setup(void)
max_marks = clamp(max_marks, FANOTIFY_OLD_DEFAULT_MAX_MARKS,
FANOTIFY_DEFAULT_MAX_USER_MARKS);
+ BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10);
BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index a712b2aaa9ac..57f0d5d9f934 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -144,7 +144,7 @@ void fanotify_show_fdinfo(struct seq_file *m, struct file *f)
struct fsnotify_group *group = f->private_data;
seq_printf(m, "fanotify flags:%x event-flags:%x\n",
- group->fanotify_data.flags,
+ group->fanotify_data.flags & FANOTIFY_INIT_FLAGS,
group->fanotify_data.f_flags);
show_fdinfo(m, f, fanotify_fdinfo);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index f17c3d33fb18..775657943057 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1856,6 +1856,45 @@ out:
}
/*
+ * zero out partial blocks of one cluster.
+ *
+ * start: file offset where zero starts, will be made upper block aligned.
+ * len: it will be trimmed to the end of current cluster if "start + len"
+ * is bigger than it.
+ */
+static int ocfs2_zeroout_partial_cluster(struct inode *inode,
+ u64 start, u64 len)
+{
+ int ret;
+ u64 start_block, end_block, nr_blocks;
+ u64 p_block, offset;
+ u32 cluster, p_cluster, nr_clusters;
+ struct super_block *sb = inode->i_sb;
+ u64 end = ocfs2_align_bytes_to_clusters(sb, start);
+
+ if (start + len < end)
+ end = start + len;
+
+ start_block = ocfs2_blocks_for_bytes(sb, start);
+ end_block = ocfs2_blocks_for_bytes(sb, end);
+ nr_blocks = end_block - start_block;
+ if (!nr_blocks)
+ return 0;
+
+ cluster = ocfs2_bytes_to_clusters(sb, start);
+ ret = ocfs2_get_clusters(inode, cluster, &p_cluster,
+ &nr_clusters, NULL);
+ if (ret)
+ return ret;
+ if (!p_cluster)
+ return 0;
+
+ offset = start_block - ocfs2_clusters_to_blocks(sb, cluster);
+ p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset;
+ return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS);
+}
+
+/*
* Parts of this function taken from xfs_change_file_space()
*/
static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
@@ -1865,7 +1904,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
{
int ret;
s64 llen;
- loff_t size;
+ loff_t size, orig_isize;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct buffer_head *di_bh = NULL;
handle_t *handle;
@@ -1896,6 +1935,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
goto out_inode_unlock;
}
+ orig_isize = i_size_read(inode);
switch (sr->l_whence) {
case 0: /*SEEK_SET*/
break;
@@ -1903,7 +1943,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
sr->l_start += f_pos;
break;
case 2: /*SEEK_END*/
- sr->l_start += i_size_read(inode);
+ sr->l_start += orig_isize;
break;
default:
ret = -EINVAL;
@@ -1957,6 +1997,14 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
default:
ret = -EINVAL;
}
+
+ /* zeroout eof blocks in the cluster. */
+ if (!ret && change_size && orig_isize < size) {
+ ret = ocfs2_zeroout_partial_cluster(inode, orig_isize,
+ size - orig_isize);
+ if (!ret)
+ i_size_write(inode, size);
+ }
up_write(&OCFS2_I(inode)->ip_alloc_sem);
if (ret) {
mlog_errno(ret);
@@ -1973,9 +2021,6 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
goto out_inode_unlock;
}
- if (change_size && i_size_read(inode) < size)
- i_size_write(inode, size);
-
inode->i_ctime = inode->i_mtime = current_time(inode);
ret = ocfs2_mark_inode_dirty(handle, inode, di_bh);
if (ret < 0)
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 58bbf334265b..7118ebe38fa6 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2674,6 +2674,11 @@ out:
}
#ifdef CONFIG_SECURITY
+static int proc_pid_attr_open(struct inode *inode, struct file *file)
+{
+ return __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS);
+}
+
static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
@@ -2704,7 +2709,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
int rv;
/* A task may only write when it was the opener. */
- if (file->f_cred != current_real_cred())
+ if (file->private_data != current->mm)
return -EPERM;
rcu_read_lock();
@@ -2754,9 +2759,11 @@ out:
}
static const struct file_operations proc_pid_attr_operations = {
+ .open = proc_pid_attr_open,
.read = proc_pid_attr_read,
.write = proc_pid_attr_write,
.llseek = generic_file_llseek,
+ .release = mem_release,
};
#define LSM_DIR_OPS(LSM) \