summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorJonathan Cameron <Jonathan.Cameron@huawei.com>2024-10-12 11:22:25 +0100
committerJonathan Cameron <Jonathan.Cameron@huawei.com>2024-10-12 11:43:29 +0100
commit220c71dafaa28cbb75fd785670cf68a758347026 (patch)
tree47a974cd3ea71ba59116037b56a509c41a430b63 /fs
parent6a9262edff8ea44e9968b6b271c36d81c6a1f841 (diff)
parent8cf0b93919e13d1e8d4466eb4080a4c4d9d66d7b (diff)
Merge tag 'v6.12-rc2' into test2
Linux 6.12-rc2 Resolved movement of asm/unaligned.h to linux/unaligned.h
Diffstat (limited to 'fs')
-rw-r--r--fs/adfs/map.c2
-rw-r--r--fs/afs/afs_vl.h9
-rw-r--r--fs/afs/file.c1
-rw-r--r--fs/afs/fs_operation.c2
-rw-r--r--fs/afs/fs_probe.c4
-rw-r--r--fs/afs/rotate.c11
-rw-r--r--fs/bcachefs/alloc_background.c30
-rw-r--r--fs/bcachefs/alloc_background_format.h2
-rw-r--r--fs/bcachefs/bcachefs_format.h2
-rw-r--r--fs/bcachefs/bset.c2
-rw-r--r--fs/bcachefs/btree_gc.c3
-rw-r--r--fs/bcachefs/btree_trans_commit.c3
-rw-r--r--fs/bcachefs/error.c23
-rw-r--r--fs/bcachefs/error.h9
-rw-r--r--fs/bcachefs/fs.c33
-rw-r--r--fs/bcachefs/fsck.c194
-rw-r--r--fs/bcachefs/inode.c46
-rw-r--r--fs/bcachefs/inode.h28
-rw-r--r--fs/bcachefs/io_misc.c63
-rw-r--r--fs/bcachefs/logged_ops.c16
-rw-r--r--fs/bcachefs/logged_ops.h2
-rw-r--r--fs/bcachefs/lru.c34
-rw-r--r--fs/bcachefs/move.c2
-rw-r--r--fs/bcachefs/movinggc.c12
-rw-r--r--fs/bcachefs/sb-errors_format.h33
-rw-r--r--fs/bcachefs/siphash.c2
-rw-r--r--fs/bcachefs/subvolume.c16
-rw-r--r--fs/bcachefs/subvolume.h2
-rw-r--r--fs/bcachefs/util.c2
-rw-r--r--fs/bcachefs/varint.c2
-rw-r--r--fs/binfmt_flat.c2
-rw-r--r--fs/btrfs/accessors.c2
-rw-r--r--fs/btrfs/accessors.h2
-rw-r--r--fs/btrfs/backref.c12
-rw-r--r--fs/btrfs/disk-io.c13
-rw-r--r--fs/btrfs/inode.c7
-rw-r--r--fs/btrfs/messages.c3
-rw-r--r--fs/btrfs/relocation.c77
-rw-r--r--fs/btrfs/send.c31
-rw-r--r--fs/btrfs/uuid-tree.c2
-rw-r--r--fs/cachefiles/namei.c7
-rw-r--r--fs/ceph/addr.c7
-rw-r--r--fs/ceph/export.c2
-rw-r--r--fs/ceph/super.h2
-rw-r--r--fs/crypto/keyring.c2
-rw-r--r--fs/dax.c6
-rw-r--r--fs/ecryptfs/crypto.c2
-rw-r--r--fs/ecryptfs/inode.c2
-rw-r--r--fs/ecryptfs/mmap.c2
-rw-r--r--fs/erofs/zmap.c2
-rw-r--r--fs/exfat/cache.c2
-rw-r--r--fs/exfat/fatent.c2
-rw-r--r--fs/exfat/nls.c2
-rw-r--r--fs/ext4/fast_commit.c19
-rw-r--r--fs/ext4/resize.c18
-rw-r--r--fs/ext4/xattr.c3
-rw-r--r--fs/f2fs/dir.c2
-rw-r--r--fs/f2fs/recovery.c2
-rw-r--r--fs/fat/inode.c2
-rw-r--r--fs/file.c95
-rw-r--r--fs/hfsplus/wrapper.c2
-rw-r--r--fs/hpfs/hpfs_fn.h2
-rw-r--r--fs/iomap/buffered-io.c9
-rw-r--r--fs/isofs/isofs.h2
-rw-r--r--fs/lockd/mon.c2
-rw-r--r--fs/netfs/misc.c2
-rw-r--r--fs/netfs/write_issue.c54
-rw-r--r--fs/nfsd/filecache.c2
-rw-r--r--fs/nls/nls_ucs2_utils.c2
-rw-r--r--fs/notify/dnotify/dnotify.c3
-rw-r--r--fs/notify/fanotify/fanotify_user.c2
-rw-r--r--fs/notify/fsnotify.c21
-rw-r--r--fs/notify/group.c11
-rw-r--r--fs/notify/inotify/inotify_user.c2
-rw-r--r--fs/notify/mark.c8
-rw-r--r--fs/ntfs3/lib/decompress_common.h2
-rw-r--r--fs/orangefs/orangefs-kernel.h2
-rw-r--r--fs/pidfs.c5
-rw-r--r--fs/reiserfs/inode.c2
-rw-r--r--fs/reiserfs/reiserfs.h2
-rw-r--r--fs/smb/client/cifsacl.h2
-rw-r--r--fs/smb/client/cifsencrypt.c3
-rw-r--r--fs/smb/client/cifsfs.c17
-rw-r--r--fs/smb/client/cifsglob.h5
-rw-r--r--fs/smb/client/cifspdu.h6
-rw-r--r--fs/smb/client/cifssmb.c6
-rw-r--r--fs/smb/client/compress/lz77.c2
-rw-r--r--fs/smb/client/file.c2
-rw-r--r--fs/smb/client/fs_context.h2
-rw-r--r--fs/smb/client/inode.c8
-rw-r--r--fs/smb/client/misc.c2
-rw-r--r--fs/smb/client/netmisc.c2
-rw-r--r--fs/smb/client/readdir.c4
-rw-r--r--fs/smb/client/reparse.c39
-rw-r--r--fs/smb/client/sess.c2
-rw-r--r--fs/smb/client/smb1ops.c2
-rw-r--r--fs/smb/client/smb2inode.c24
-rw-r--r--fs/smb/client/smb2misc.c28
-rw-r--r--fs/smb/client/smb2ops.c23
-rw-r--r--fs/smb/client/smb2pdu.c4
-rw-r--r--fs/smb/client/smb2proto.h2
-rw-r--r--fs/smb/client/smb2transport.c32
-rw-r--r--fs/smb/client/smbdirect.c4
-rw-r--r--fs/smb/client/smbdirect.h2
-rw-r--r--fs/smb/common/smbfsctl.h7
-rw-r--r--fs/smb/server/smb2pdu.c7
-rw-r--r--fs/smb/server/smb2pdu.h14
-rw-r--r--fs/smb/server/transport_rdma.c4
-rw-r--r--fs/smb/server/unicode.c2
-rw-r--r--fs/udf/balloc.c38
-rw-r--r--fs/udf/directory.c23
-rw-r--r--fs/udf/inode.c202
-rw-r--r--fs/udf/partition.c6
-rw-r--r--fs/udf/super.c3
-rw-r--r--fs/udf/truncate.c43
-rw-r--r--fs/udf/udfdecl.h15
-rw-r--r--fs/ufs/namei.c2
-rw-r--r--fs/xfs/xfs_linux.h2
-rw-r--r--fs/zonefs/sysfs.c1
119 files changed, 994 insertions, 657 deletions
diff --git a/fs/adfs/map.c b/fs/adfs/map.c
index a81de80c45c1..a0ce272b4098 100644
--- a/fs/adfs/map.c
+++ b/fs/adfs/map.c
@@ -6,7 +6,7 @@
*/
#include <linux/slab.h>
#include <linux/statfs.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "adfs.h"
/*
diff --git a/fs/afs/afs_vl.h b/fs/afs/afs_vl.h
index 9c65ffb8a523..a06296c8827d 100644
--- a/fs/afs/afs_vl.h
+++ b/fs/afs/afs_vl.h
@@ -134,13 +134,4 @@ struct afs_uvldbentry__xdr {
__be32 spares9;
};
-struct afs_address_list {
- refcount_t usage;
- unsigned int version;
- unsigned int nr_addrs;
- struct sockaddr_rxrpc addrs[];
-};
-
-extern void afs_put_address_list(struct afs_address_list *alist);
-
#endif /* AFS_VL_H */
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 492d857a3fa0..6762eff97517 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -420,6 +420,7 @@ const struct netfs_request_ops afs_req_ops = {
.begin_writeback = afs_begin_writeback,
.prepare_write = afs_prepare_write,
.issue_write = afs_issue_write,
+ .retry_request = afs_retry_request,
};
static void afs_add_open_mmap(struct afs_vnode *vnode)
diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c
index 3546b087e791..428721bbe4f6 100644
--- a/fs/afs/fs_operation.c
+++ b/fs/afs/fs_operation.c
@@ -201,7 +201,7 @@ void afs_wait_for_operation(struct afs_operation *op)
}
}
- if (op->call_responded)
+ if (op->call_responded && op->server)
set_bit(AFS_SERVER_FL_RESPONDING, &op->server->flags);
if (!afs_op_error(op)) {
diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c
index 580de4adaaf6..b516d05b0fef 100644
--- a/fs/afs/fs_probe.c
+++ b/fs/afs/fs_probe.c
@@ -506,10 +506,10 @@ int afs_wait_for_one_fs_probe(struct afs_server *server, struct afs_endpoint_sta
finish_wait(&server->probe_wq, &wait);
dont_wait:
- if (estate->responsive_set & ~exclude)
- return 1;
if (test_bit(AFS_ESTATE_SUPERSEDED, &estate->flags))
return 0;
+ if (estate->responsive_set & ~exclude)
+ return 1;
if (is_intr && signal_pending(current))
return -ERESTARTSYS;
if (timo == 0)
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index ed09d4d4c211..d612983d6f38 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -632,8 +632,10 @@ iterate_address:
wait_for_more_probe_results:
error = afs_wait_for_one_fs_probe(op->server, op->estate, op->addr_tried,
!(op->flags & AFS_OPERATION_UNINTR));
- if (!error)
+ if (error == 1)
goto iterate_address;
+ if (!error)
+ goto restart_from_beginning;
/* We've now had a failure to respond on all of a server's addresses -
* immediately probe them again and consider retrying the server.
@@ -644,10 +646,13 @@ wait_for_more_probe_results:
error = afs_wait_for_one_fs_probe(op->server, op->estate, op->addr_tried,
!(op->flags & AFS_OPERATION_UNINTR));
switch (error) {
- case 0:
+ case 1:
op->flags &= ~AFS_OPERATION_RETRY_SERVER;
- trace_afs_rotate(op, afs_rotate_trace_retry_server, 0);
+ trace_afs_rotate(op, afs_rotate_trace_retry_server, 1);
goto retry_server;
+ case 0:
+ trace_afs_rotate(op, afs_rotate_trace_retry_server, 0);
+ goto restart_from_beginning;
case -ERESTARTSYS:
afs_op_set_error(op, error);
goto failed;
diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index 645b5ed4babb..4e4a448f6931 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -332,7 +332,6 @@ void bch2_alloc_v4_swab(struct bkey_s k)
a->io_time[1] = swab64(a->io_time[1]);
a->stripe = swab32(a->stripe);
a->nr_external_backpointers = swab32(a->nr_external_backpointers);
- a->fragmentation_lru = swab64(a->fragmentation_lru);
a->stripe_sectors = swab32(a->stripe_sectors);
bps = alloc_v4_backpointers(a);
@@ -347,6 +346,7 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c
{
struct bch_alloc_v4 _a;
const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &_a);
+ struct bch_dev *ca = c ? bch2_dev_bucket_tryget_noerror(c, k.k->p) : NULL;
prt_newline(out);
printbuf_indent_add(out, 2);
@@ -364,9 +364,13 @@ void bch2_alloc_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c
prt_printf(out, "stripe_redundancy %u\n", a->stripe_redundancy);
prt_printf(out, "io_time[READ] %llu\n", a->io_time[READ]);
prt_printf(out, "io_time[WRITE] %llu\n", a->io_time[WRITE]);
- prt_printf(out, "fragmentation %llu\n", a->fragmentation_lru);
+
+ if (ca)
+ prt_printf(out, "fragmentation %llu\n", alloc_lru_idx_fragmentation(*a, ca));
prt_printf(out, "bp_start %llu\n", BCH_ALLOC_V4_BACKPOINTERS_START(a));
printbuf_indent_sub(out, 2);
+
+ bch2_dev_put(ca);
}
void __bch2_alloc_to_v4(struct bkey_s_c k, struct bch_alloc_v4 *out)
@@ -882,12 +886,13 @@ int bch2_trigger_alloc(struct btree_trans *trans,
goto err;
}
- new_a->fragmentation_lru = alloc_lru_idx_fragmentation(*new_a, ca);
- if (old_a->fragmentation_lru != new_a->fragmentation_lru) {
+ old_lru = alloc_lru_idx_fragmentation(*old_a, ca);
+ new_lru = alloc_lru_idx_fragmentation(*new_a, ca);
+ if (old_lru != new_lru) {
ret = bch2_lru_change(trans,
BCH_LRU_FRAGMENTATION_START,
bucket_to_u64(new.k->p),
- old_a->fragmentation_lru, new_a->fragmentation_lru);
+ old_lru, new_lru);
if (ret)
goto err;
}
@@ -1629,18 +1634,22 @@ static int bch2_check_alloc_to_lru_ref(struct btree_trans *trans,
if (ret)
return ret;
+ struct bch_dev *ca = bch2_dev_tryget_noerror(c, alloc_k.k->p.inode);
+ if (!ca)
+ return 0;
+
a = bch2_alloc_to_v4(alloc_k, &a_convert);
- if (a->fragmentation_lru) {
+ u64 lru_idx = alloc_lru_idx_fragmentation(*a, ca);
+ if (lru_idx) {
ret = bch2_lru_check_set(trans, BCH_LRU_FRAGMENTATION_START,
- a->fragmentation_lru,
- alloc_k, last_flushed);
+ lru_idx, alloc_k, last_flushed);
if (ret)
- return ret;
+ goto err;
}
if (a->data_type != BCH_DATA_cached)
- return 0;
+ goto err;
if (fsck_err_on(!a->io_time[READ],
trans, alloc_key_cached_but_read_time_zero,
@@ -1669,6 +1678,7 @@ static int bch2_check_alloc_to_lru_ref(struct btree_trans *trans,
goto err;
err:
fsck_err:
+ bch2_dev_put(ca);
printbuf_exit(&buf);
return ret;
}
diff --git a/fs/bcachefs/alloc_background_format.h b/fs/bcachefs/alloc_background_format.h
index f754a2951d8a..befdaa95c515 100644
--- a/fs/bcachefs/alloc_background_format.h
+++ b/fs/bcachefs/alloc_background_format.h
@@ -70,7 +70,7 @@ struct bch_alloc_v4 {
__u32 stripe;
__u32 nr_external_backpointers;
/* end of fields in original version of alloc_v4 */
- __u64 fragmentation_lru;
+ __u64 _fragmentation_lru; /* obsolete */
__u32 stripe_sectors;
__u32 pad;
} __packed __aligned(8);
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 203ee627cab5..84832c2d4df9 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -223,7 +223,7 @@ struct bkey {
#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
struct bpos p;
__u32 size; /* extent size, in sectors */
- struct bversion version;
+ struct bversion bversion;
__u8 pad[1];
#endif
diff --git a/fs/bcachefs/bset.c b/fs/bcachefs/bset.c
index d1f6092624d8..9a4a83d6fd2d 100644
--- a/fs/bcachefs/bset.c
+++ b/fs/bcachefs/bset.c
@@ -13,7 +13,7 @@
#include "trace.h"
#include "util.h"
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/console.h>
#include <linux/random.h>
#include <linux/prefetch.h>
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 660d2fa02da2..771154e3a291 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -828,8 +828,6 @@ static int bch2_alloc_write_key(struct btree_trans *trans,
return ret;
}
- gc.fragmentation_lru = alloc_lru_idx_fragmentation(gc, ca);
-
if (fsck_err_on(new.data_type != gc.data_type,
trans, alloc_key_data_type_wrong,
"bucket %llu:%llu gen %u has wrong data_type"
@@ -857,7 +855,6 @@ static int bch2_alloc_write_key(struct btree_trans *trans,
copy_bucket_field(alloc_key_cached_sectors_wrong, cached_sectors);
copy_bucket_field(alloc_key_stripe_wrong, stripe);
copy_bucket_field(alloc_key_stripe_redundancy_wrong, stripe_redundancy);
- copy_bucket_field(alloc_key_fragmentation_lru_wrong, fragmentation_lru);
#undef copy_bucket_field
if (!bch2_alloc_v4_cmp(*old, new))
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index 1a74a1a252ee..9bf471fa4361 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -832,7 +832,8 @@ revert_fs_usage:
for (struct jset_entry *entry2 = trans->journal_entries;
entry2 != entry;
entry2 = vstruct_next(entry2))
- if (jset_entry_is_key(entry2) && entry2->start->k.type == KEY_TYPE_accounting) {
+ if (entry2->type == BCH_JSET_ENTRY_write_buffer_keys &&
+ entry2->start->k.type == KEY_TYPE_accounting) {
struct bkey_s_accounting a = bkey_i_to_s_accounting(entry2->start);
bch2_accounting_neg(a);
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index 3a16b535b6c3..7a79f695ba2e 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -393,6 +393,14 @@ int __bch2_fsck_err(struct bch_fs *c,
!(flags & FSCK_CAN_IGNORE)))
ret = -BCH_ERR_fsck_errors_not_fixed;
+ bool exiting =
+ test_bit(BCH_FS_fsck_running, &c->flags) &&
+ (ret != -BCH_ERR_fsck_fix &&
+ ret != -BCH_ERR_fsck_ignore);
+
+ if (exiting)
+ print = true;
+
if (print) {
if (bch2_fs_stdio_redirect(c))
bch2_print(c, "%s\n", out->buf);
@@ -400,9 +408,7 @@ int __bch2_fsck_err(struct bch_fs *c,
bch2_print_string_as_lines(KERN_ERR, out->buf);
}
- if (test_bit(BCH_FS_fsck_running, &c->flags) &&
- (ret != -BCH_ERR_fsck_fix &&
- ret != -BCH_ERR_fsck_ignore))
+ if (exiting)
bch_err(c, "Unable to continue, halting");
else if (suppressing)
bch_err(c, "Ratelimiting new instances of previous error");
@@ -430,10 +436,17 @@ err:
int __bch2_bkey_fsck_err(struct bch_fs *c,
struct bkey_s_c k,
- enum bch_fsck_flags flags,
+ enum bch_validate_flags validate_flags,
enum bch_sb_error_id err,
const char *fmt, ...)
{
+ if (validate_flags & BCH_VALIDATE_silent)
+ return -BCH_ERR_fsck_delete_bkey;
+
+ unsigned fsck_flags = 0;
+ if (!(validate_flags & (BCH_VALIDATE_write|BCH_VALIDATE_commit)))
+ fsck_flags |= FSCK_AUTOFIX|FSCK_CAN_FIX;
+
struct printbuf buf = PRINTBUF;
va_list args;
@@ -445,7 +458,7 @@ int __bch2_bkey_fsck_err(struct bch_fs *c,
va_end(args);
prt_str(&buf, ": delete?");
- int ret = __bch2_fsck_err(c, NULL, flags, err, "%s", buf.buf);
+ int ret = __bch2_fsck_err(c, NULL, fsck_flags, err, "%s", buf.buf);
printbuf_exit(&buf);
return ret;
}
diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h
index 21ee7211b03e..6551ada926b6 100644
--- a/fs/bcachefs/error.h
+++ b/fs/bcachefs/error.h
@@ -167,10 +167,11 @@ void bch2_flush_fsck_errs(struct bch_fs *);
#define fsck_err_on(cond, c, _err_type, ...) \
__fsck_err_on(cond, c, FSCK_CAN_FIX|FSCK_CAN_IGNORE, _err_type, __VA_ARGS__)
+enum bch_validate_flags;
__printf(5, 6)
int __bch2_bkey_fsck_err(struct bch_fs *,
struct bkey_s_c,
- enum bch_fsck_flags,
+ enum bch_validate_flags,
enum bch_sb_error_id,
const char *, ...);
@@ -180,11 +181,7 @@ int __bch2_bkey_fsck_err(struct bch_fs *,
*/
#define bkey_fsck_err(c, _err_type, _err_msg, ...) \
do { \
- if ((flags & BCH_VALIDATE_silent)) { \
- ret = -BCH_ERR_fsck_delete_bkey; \
- goto fsck_err; \
- } \
- int _ret = __bch2_bkey_fsck_err(c, k, FSCK_CAN_FIX|FSCK_AUTOFIX,\
+ int _ret = __bch2_bkey_fsck_err(c, k, flags, \
BCH_FSCK_ERR_##_err_type, \
_err_msg, ##__VA_ARGS__); \
if (_ret != -BCH_ERR_fsck_fix && \
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 4a1bb07a2574..5bfc26d58270 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -174,20 +174,24 @@ static const struct rhashtable_params bch2_vfs_inodes_params = {
.automatic_shrinking = true,
};
-static void __wait_on_freeing_inode(struct inode *inode)
+struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *c, subvol_inum inum)
{
- wait_queue_head_t *wq;
- DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW);
- wq = bit_waitqueue(&inode->i_state, __I_NEW);
- prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
- spin_unlock(&inode->i_lock);
- schedule();
- finish_wait(wq, &wait.wq_entry);
+ return rhashtable_lookup_fast(&c->vfs_inodes_table, &inum, bch2_vfs_inodes_params);
}
-struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *c, subvol_inum inum)
+static void __wait_on_freeing_inode(struct bch_fs *c,
+ struct bch_inode_info *inode,
+ subvol_inum inum)
{
- return rhashtable_lookup_fast(&c->vfs_inodes_table, &inum, bch2_vfs_inodes_params);
+ wait_queue_head_t *wq;
+ DEFINE_WAIT_BIT(wait, &inode->v.i_state, __I_NEW);
+ wq = inode_bit_waitqueue(&wait, &inode->v, __I_NEW);
+ prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+ spin_unlock(&inode->v.i_lock);
+
+ if (__bch2_inode_hash_find(c, inum) == inode)
+ schedule_timeout(HZ * 10);
+ finish_wait(wq, &wait.wq_entry);
}
static struct bch_inode_info *bch2_inode_hash_find(struct bch_fs *c, struct btree_trans *trans,
@@ -204,10 +208,10 @@ repeat:
}
if ((inode->v.i_state & (I_FREEING|I_WILL_FREE))) {
if (!trans) {
- __wait_on_freeing_inode(&inode->v);
+ __wait_on_freeing_inode(c, inode, inum);
} else {
bch2_trans_unlock(trans);
- __wait_on_freeing_inode(&inode->v);
+ __wait_on_freeing_inode(c, inode, inum);
int ret = bch2_trans_relock(trans);
if (ret)
return ERR_PTR(ret);
@@ -232,6 +236,11 @@ static void bch2_inode_hash_remove(struct bch_fs *c, struct bch_inode_info *inod
&inode->hash, bch2_vfs_inodes_params);
BUG_ON(ret);
inode->v.i_hash.pprev = NULL;
+ /*
+ * This pairs with the bch2_inode_hash_find() ->
+ * __wait_on_freeing_inode() path
+ */
+ inode_wake_up_bit(&inode->v, __I_NEW);
}
}
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 0d8b782b63fb..b8a6ceb0cc7a 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -28,8 +28,8 @@ static bool inode_points_to_dirent(struct bch_inode_unpacked *inode,
inode->bi_dir_offset == d.k->p.offset;
}
-static bool dirent_points_to_inode_nowarn(struct bkey_s_c_dirent d,
- struct bch_inode_unpacked *inode)
+static int dirent_points_to_inode_nowarn(struct bkey_s_c_dirent d,
+ struct bch_inode_unpacked *inode)
{
if (d.v->d_type == DT_SUBVOL
? le32_to_cpu(d.v->d_child_subvol) == inode->bi_subvol
@@ -137,16 +137,15 @@ found:
return ret;
}
-static int lookup_inode(struct btree_trans *trans, u64 inode_nr,
- struct bch_inode_unpacked *inode,
- u32 *snapshot)
+static int lookup_inode(struct btree_trans *trans, u64 inode_nr, u32 snapshot,
+ struct bch_inode_unpacked *inode)
{
struct btree_iter iter;
struct bkey_s_c k;
int ret;
k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes,
- SPOS(0, inode_nr, *snapshot), 0);
+ SPOS(0, inode_nr, snapshot), 0);
ret = bkey_err(k);
if (ret)
goto err;
@@ -154,8 +153,6 @@ static int lookup_inode(struct btree_trans *trans, u64 inode_nr,
ret = bkey_is_inode(k.k)
? bch2_inode_unpack(k, inode)
: -BCH_ERR_ENOENT_inode;
- if (!ret)
- *snapshot = iter.pos.snapshot;
err:
bch2_trans_iter_exit(trans, &iter);
return ret;
@@ -250,8 +247,7 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot,
struct bch_inode_unpacked root_inode;
struct bch_hash_info root_hash_info;
- u32 root_inode_snapshot = snapshot;
- ret = lookup_inode(trans, root_inum.inum, &root_inode, &root_inode_snapshot);
+ ret = lookup_inode(trans, root_inum.inum, snapshot, &root_inode);
bch_err_msg(c, ret, "looking up root inode %llu for subvol %u",
root_inum.inum, le32_to_cpu(st.master_subvol));
if (ret)
@@ -277,17 +273,23 @@ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot,
* The bch2_check_dirents pass has already run, dangling dirents
* shouldn't exist here:
*/
- ret = lookup_inode(trans, inum, lostfound, &snapshot);
+ ret = lookup_inode(trans, inum, snapshot, lostfound);
bch_err_msg(c, ret, "looking up lost+found %llu:%u in (root inode %llu, snapshot root %u)",
inum, snapshot, root_inum.inum, bch2_snapshot_root(c, snapshot));
return ret;
create_lostfound:
/*
+ * we always create lost+found in the root snapshot; we don't want
+ * different branches of the snapshot tree to have different lost+found
+ */
+ snapshot = le32_to_cpu(st.root_snapshot);
+ /*
* XXX: we could have a nicer log message here if we had a nice way to
* walk backpointers to print a path
*/
- bch_notice(c, "creating lost+found in snapshot %u", le32_to_cpu(st.root_snapshot));
+ bch_notice(c, "creating lost+found in subvol %llu snapshot %u",
+ root_inum.subvol, le32_to_cpu(st.root_snapshot));
u64 now = bch2_current_time(c);
struct btree_iter lostfound_iter = { NULL };
@@ -296,6 +298,7 @@ create_lostfound:
bch2_inode_init_early(c, lostfound);
bch2_inode_init_late(lostfound, now, 0, 0, S_IFDIR|0700, 0, &root_inode);
lostfound->bi_dir = root_inode.bi_inum;
+ lostfound->bi_snapshot = le32_to_cpu(st.root_snapshot);
root_inode.bi_nlink++;
@@ -323,9 +326,7 @@ err:
return ret;
}
-static int reattach_inode(struct btree_trans *trans,
- struct bch_inode_unpacked *inode,
- u32 inode_snapshot)
+static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode)
{
struct bch_fs *c = trans->c;
struct bch_hash_info dir_hash;
@@ -333,7 +334,7 @@ static int reattach_inode(struct btree_trans *trans,
char name_buf[20];
struct qstr name;
u64 dir_offset = 0;
- u32 dirent_snapshot = inode_snapshot;
+ u32 dirent_snapshot = inode->bi_snapshot;
int ret;
if (inode->bi_subvol) {
@@ -354,14 +355,18 @@ static int reattach_inode(struct btree_trans *trans,
if (ret)
return ret;
- if (S_ISDIR(inode->bi_mode)) {
- lostfound.bi_nlink++;
+ lostfound.bi_nlink += S_ISDIR(inode->bi_mode);
- ret = __bch2_fsck_write_inode(trans, &lostfound, U32_MAX);
- if (ret)
- return ret;
+ /* ensure lost+found inode is also present in inode snapshot */
+ if (!inode->bi_subvol) {
+ BUG_ON(!bch2_snapshot_is_ancestor(c, inode->bi_snapshot, lostfound.bi_snapshot));
+ lostfound.bi_snapshot = inode->bi_snapshot;
}
+ ret = __bch2_fsck_write_inode(trans, &lostfound);
+ if (ret)
+ return ret;
+
dir_hash = bch2_hash_info_init(c, &lostfound);
name = (struct qstr) QSTR(name_buf);
@@ -383,7 +388,7 @@ static int reattach_inode(struct btree_trans *trans,
inode->bi_dir = lostfound.bi_inum;
inode->bi_dir_offset = dir_offset;
- return __bch2_fsck_write_inode(trans, inode, inode_snapshot);
+ return __bch2_fsck_write_inode(trans, inode);
}
static int remove_backpointer(struct btree_trans *trans,
@@ -422,7 +427,7 @@ static int reattach_subvol(struct btree_trans *trans, struct bkey_s_c_subvolume
if (ret)
return ret;
- ret = reattach_inode(trans, &inode, le32_to_cpu(s.v->snapshot));
+ ret = reattach_inode(trans, &inode);
bch_err_msg(c, ret, "reattaching inode %llu", inode.bi_inum);
return ret;
}
@@ -540,8 +545,9 @@ static int reconstruct_inode(struct btree_trans *trans, enum btree_id btree, u32
bch2_inode_init_late(&new_inode, bch2_current_time(c), 0, 0, i_mode|0600, 0, NULL);
new_inode.bi_size = i_size;
new_inode.bi_inum = inum;
+ new_inode.bi_snapshot = snapshot;
- return __bch2_fsck_write_inode(trans, &new_inode, snapshot);
+ return __bch2_fsck_write_inode(trans, &new_inode);
}
struct snapshots_seen {
@@ -1024,6 +1030,7 @@ static int check_inode(struct btree_trans *trans,
bool full)
{
struct bch_fs *c = trans->c;
+ struct printbuf buf = PRINTBUF;
struct bch_inode_unpacked u;
bool do_update = false;
int ret;
@@ -1057,7 +1064,41 @@ static int check_inode(struct btree_trans *trans,
trans, inode_snapshot_mismatch,
"inodes in different snapshots don't match")) {
bch_err(c, "repair not implemented yet");
- return -BCH_ERR_fsck_repair_unimplemented;
+ ret = -BCH_ERR_fsck_repair_unimplemented;
+ goto err_noprint;
+ }
+
+ if (u.bi_dir || u.bi_dir_offset) {
+ ret = check_inode_dirent_inode(trans, &u, &do_update);
+ if (ret)
+ goto err;
+ }
+
+ if (fsck_err_on(u.bi_dir && (u.bi_flags & BCH_INODE_unlinked),
+ trans, inode_unlinked_but_has_dirent,
+ "inode unlinked but has dirent\n%s",
+ (printbuf_reset(&buf),
+ bch2_inode_unpacked_to_text(&buf, &u),
+ buf.buf))) {
+ u.bi_flags &= ~BCH_INODE_unlinked;
+ do_update = true;
+ }
+
+ if (S_ISDIR(u.bi_mode) && (u.bi_flags & BCH_INODE_unlinked)) {
+ /* Check for this early so that check_unreachable_inode() will reattach it */
+
+ ret = bch2_empty_dir_snapshot(trans, k.k->p.offset, 0, k.k->p.snapshot);
+ if (ret && ret != -BCH_ERR_ENOTEMPTY_dir_not_empty)
+ goto err;
+
+ fsck_err_on(ret, trans, inode_dir_unlinked_but_not_empty,
+ "dir unlinked but not empty\n%s",
+ (printbuf_reset(&buf),
+ bch2_inode_unpacked_to_text(&buf, &u),
+ buf.buf));
+ u.bi_flags &= ~BCH_INODE_unlinked;
+ do_update = true;
+ ret = 0;
}
if ((u.bi_flags & (BCH_INODE_i_size_dirty|BCH_INODE_unlinked)) &&
@@ -1070,15 +1111,15 @@ static int check_inode(struct btree_trans *trans,
u.bi_flags &= ~BCH_INODE_i_size_dirty|BCH_INODE_unlinked;
- ret = __bch2_fsck_write_inode(trans, &u, iter->pos.snapshot);
+ ret = __bch2_fsck_write_inode(trans, &u);
bch_err_msg(c, ret, "in fsck updating inode");
if (ret)
- return ret;
+ goto err_noprint;
if (!bpos_eq(new_min_pos, POS_MIN))
bch2_btree_iter_set_pos(iter, bpos_predecessor(new_min_pos));
- return 0;
+ goto err_noprint;
}
if (u.bi_flags & BCH_INODE_unlinked) {
@@ -1095,7 +1136,7 @@ static int check_inode(struct btree_trans *trans,
*/
ret = check_inode_deleted_list(trans, k.k->p);
if (ret < 0)
- return ret;
+ goto err_noprint;
fsck_err_on(!ret,
trans, unlinked_inode_not_on_deleted_list,
@@ -1106,13 +1147,13 @@ static int check_inode(struct btree_trans *trans,
if (ret)
goto err;
} else {
- if (fsck_err_on(bch2_inode_is_open(c, k.k->p),
+ if (fsck_err_on(!bch2_inode_is_open(c, k.k->p),
trans, inode_unlinked_and_not_open,
"inode %llu%u unlinked and not open",
u.bi_inum, u.bi_snapshot)) {
ret = bch2_inode_rm_snapshot(trans, u.bi_inum, iter->pos.snapshot);
bch_err_msg(c, ret, "in fsck deleting inode");
- return ret;
+ goto err_noprint;
}
}
}
@@ -1177,12 +1218,6 @@ static int check_inode(struct btree_trans *trans,
do_update = true;
}
- if (u.bi_dir || u.bi_dir_offset) {
- ret = check_inode_dirent_inode(trans, &u, &do_update);
- if (ret)
- goto err;
- }
-
if (fsck_err_on(u.bi_parent_subvol &&
(u.bi_subvol == 0 ||
u.bi_subvol == BCACHEFS_ROOT_SUBVOL),
@@ -1224,14 +1259,16 @@ static int check_inode(struct btree_trans *trans,
}
do_update:
if (do_update) {
- ret = __bch2_fsck_write_inode(trans, &u, iter->pos.snapshot);
+ ret = __bch2_fsck_write_inode(trans, &u);
bch_err_msg(c, ret, "in fsck updating inode");
if (ret)
- return ret;
+ goto err_noprint;
}
err:
fsck_err:
bch_err_fn(c, ret);
+err_noprint:
+ printbuf_exit(&buf);
return ret;
}
@@ -1347,7 +1384,7 @@ static int check_i_sectors_notnested(struct btree_trans *trans, struct inode_wal
w->last_pos.inode, i->snapshot,
i->inode.bi_sectors, i->count)) {
i->inode.bi_sectors = i->count;
- ret = bch2_fsck_write_inode(trans, &i->inode, i->snapshot);
+ ret = bch2_fsck_write_inode(trans, &i->inode);
if (ret)
break;
}
@@ -1789,7 +1826,7 @@ static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_
"directory %llu:%u with wrong i_nlink: got %u, should be %llu",
w->last_pos.inode, i->snapshot, i->inode.bi_nlink, i->count)) {
i->inode.bi_nlink = i->count;
- ret = bch2_fsck_write_inode(trans, &i->inode, i->snapshot);
+ ret = bch2_fsck_write_inode(trans, &i->inode);
if (ret)
break;
}
@@ -1810,8 +1847,7 @@ noinline_for_stack
static int check_dirent_inode_dirent(struct btree_trans *trans,
struct btree_iter *iter,
struct bkey_s_c_dirent d,
- struct bch_inode_unpacked *target,
- u32 target_snapshot)
+ struct bch_inode_unpacked *target)
{
struct bch_fs *c = trans->c;
struct printbuf buf = PRINTBUF;
@@ -1821,6 +1857,32 @@ static int check_dirent_inode_dirent(struct btree_trans *trans,
if (inode_points_to_dirent(target, d))
return 0;
+ if (!target->bi_dir &&
+ !target->bi_dir_offset) {
+ fsck_err_on(S_ISDIR(target->bi_mode),
+ trans, inode_dir_missing_backpointer,
+ "directory with missing backpointer\n%s",
+ (printbuf_reset(&buf),
+ bch2_bkey_val_to_text(&buf, c, d.s_c),
+ prt_printf(&buf, "\n"),
+ bch2_inode_unpacked_to_text(&buf, target),
+ buf.buf));
+
+ fsck_err_on(target->bi_flags & BCH_INODE_unlinked,
+ trans, inode_unlinked_but_has_dirent,
+ "inode unlinked but has dirent\n%s",
+ (printbuf_reset(&buf),
+ bch2_bkey_val_to_text(&buf, c, d.s_c),
+ prt_printf(&buf, "\n"),
+ bch2_inode_unpacked_to_text(&buf, target),
+ buf.buf));
+
+ target->bi_flags &= ~BCH_INODE_unlinked;
+ target->bi_dir = d.k->p.inode;
+ target->bi_dir_offset = d.k->p.offset;
+ return __bch2_fsck_write_inode(trans, target);
+ }
+
if (bch2_inode_should_have_bp(target) &&
!fsck_err(trans, inode_wrong_backpointer,
"dirent points to inode that does not point back:\n %s",
@@ -1830,15 +1892,8 @@ static int check_dirent_inode_dirent(struct btree_trans *trans,
buf.buf)))
goto err;
- if (!target->bi_dir &&
- !target->bi_dir_offset) {
- target->bi_dir = d.k->p.inode;
- target->bi_dir_offset = d.k->p.offset;
- return __bch2_fsck_write_inode(trans, target, target_snapshot);
- }
-
struct bkey_s_c_dirent bp_dirent = dirent_get_by_pos(trans, &bp_iter,
- SPOS(target->bi_dir, target->bi_dir_offset, target_snapshot));
+ SPOS(target->bi_dir, target->bi_dir_offset, target->bi_snapshot));
ret = bkey_err(bp_dirent);
if (ret && !bch2_err_matches(ret, ENOENT))
goto err;
@@ -1851,14 +1906,14 @@ static int check_dirent_inode_dirent(struct btree_trans *trans,
"inode %llu:%u has wrong backpointer:\n"
"got %llu:%llu\n"
"should be %llu:%llu",
- target->bi_inum, target_snapshot,
+ target->bi_inum, target->bi_snapshot,
target->bi_dir,
target->bi_dir_offset,
d.k->p.inode,
d.k->p.offset)) {
target->bi_dir = d.k->p.inode;
target->bi_dir_offset = d.k->p.offset;
- ret = __bch2_fsck_write_inode(trans, target, target_snapshot);
+ ret = __bch2_fsck_write_inode(trans, target);
goto out;
}
@@ -1873,7 +1928,7 @@ static int check_dirent_inode_dirent(struct btree_trans *trans,
trans, inode_dir_multiple_links,
"%s %llu:%u with multiple links\n%s",
S_ISDIR(target->bi_mode) ? "directory" : "subvolume",
- target->bi_inum, target_snapshot, buf.buf)) {
+ target->bi_inum, target->bi_snapshot, buf.buf)) {
ret = __remove_dirent(trans, d.k->p);
goto out;
}
@@ -1886,10 +1941,10 @@ static int check_dirent_inode_dirent(struct btree_trans *trans,
if (fsck_err_on(backpointer_exists && !target->bi_nlink,
trans, inode_multiple_links_but_nlink_0,
"inode %llu:%u type %s has multiple links but i_nlink 0\n%s",
- target->bi_inum, target_snapshot, bch2_d_types[d.v->d_type], buf.buf)) {
+ target->bi_inum, target->bi_snapshot, bch2_d_types[d.v->d_type], buf.buf)) {
target->bi_nlink++;
target->bi_flags &= ~BCH_INODE_unlinked;
- ret = __bch2_fsck_write_inode(trans, target, target_snapshot);
+ ret = __bch2_fsck_write_inode(trans, target);
if (ret)
goto err;
}
@@ -1906,15 +1961,14 @@ noinline_for_stack
static int check_dirent_target(struct btree_trans *trans,
struct btree_iter *iter,
struct bkey_s_c_dirent d,
- struct bch_inode_unpacked *target,
- u32 target_snapshot)
+ struct bch_inode_unpacked *target)
{
struct bch_fs *c = trans->c;
struct bkey_i_dirent *n;
struct printbuf buf = PRINTBUF;
int ret = 0;
- ret = check_dirent_inode_dirent(trans, iter, d, target, target_snapshot);
+ ret = check_dirent_inode_dirent(trans, iter, d, target);
if (ret)
goto err;
@@ -2073,7 +2127,7 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter *
u64 target_inum = le64_to_cpu(s.v->inode);
u32 target_snapshot = le32_to_cpu(s.v->snapshot);
- ret = lookup_inode(trans, target_inum, &subvol_root, &target_snapshot);
+ ret = lookup_inode(trans, target_inum, target_snapshot, &subvol_root);
if (ret && !bch2_err_matches(ret, ENOENT))
goto err;
@@ -2089,13 +2143,13 @@ static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter *
target_inum,
subvol_root.bi_parent_subvol, parent_subvol)) {
subvol_root.bi_parent_subvol = parent_subvol;
- ret = __bch2_fsck_write_inode(trans, &subvol_root, target_snapshot);
+ subvol_root.bi_snapshot = le32_to_cpu(s.v->snapshot);
+ ret = __bch2_fsck_write_inode(trans, &subvol_root);
if (ret)
goto err;
}
- ret = check_dirent_target(trans, iter, d, &subvol_root,
- target_snapshot);
+ ret = check_dirent_target(trans, iter, d, &subvol_root);
if (ret)
goto err;
out:
@@ -2188,8 +2242,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
}
darray_for_each(target->inodes, i) {
- ret = check_dirent_target(trans, iter, d,
- &i->inode, i->snapshot);
+ ret = check_dirent_target(trans, iter, d, &i->inode);
if (ret)
goto err;
}
@@ -2330,7 +2383,7 @@ static int check_root_trans(struct btree_trans *trans)
goto err;
}
- ret = lookup_inode(trans, BCACHEFS_ROOT_INO, &root_inode, &snapshot);
+ ret = lookup_inode(trans, BCACHEFS_ROOT_INO, snapshot, &root_inode);
if (ret && !bch2_err_matches(ret, ENOENT))
return ret;
@@ -2343,8 +2396,9 @@ static int check_root_trans(struct btree_trans *trans)
bch2_inode_init(c, &root_inode, 0, 0, S_IFDIR|0755,
0, NULL);
root_inode.bi_inum = inum;
+ root_inode.bi_snapshot = snapshot;
- ret = __bch2_fsck_write_inode(trans, &root_inode, snapshot);
+ ret = __bch2_fsck_write_inode(trans, &root_inode);
bch_err_msg(c, ret, "writing root inode");
}
err:
@@ -2511,7 +2565,7 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino
(printbuf_reset(&buf),
bch2_bkey_val_to_text(&buf, c, inode_k),
buf.buf)))
- ret = reattach_inode(trans, &inode, snapshot);
+ ret = reattach_inode(trans, &inode);
goto out;
}
@@ -2557,7 +2611,7 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino
if (ret)
break;
- ret = reattach_inode(trans, &inode, snapshot);
+ ret = reattach_inode(trans, &inode);
bch_err_msg(c, ret, "reattaching inode %llu", inode.bi_inum);
}
break;
@@ -2787,7 +2841,7 @@ static int check_nlinks_update_inode(struct btree_trans *trans, struct btree_ite
u.bi_inum, bch2_d_types[mode_to_type(u.bi_mode)],
bch2_inode_nlink_get(&u), link->count)) {
bch2_inode_nlink_set(&u, link->count);
- ret = __bch2_fsck_write_inode(trans, &u, k.k->p.snapshot);
+ ret = __bch2_fsck_write_inode(trans, &u);
}
fsck_err:
return ret;
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index 753c208896c3..3e5bc01961b8 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -20,7 +20,7 @@
#include <linux/random.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#define x(name, ...) #name,
const char * const bch2_inode_opts[] = {
@@ -327,22 +327,20 @@ int bch2_inode_unpack(struct bkey_s_c k,
: bch2_inode_unpack_slowpath(k, unpacked);
}
-int bch2_inode_peek_nowarn(struct btree_trans *trans,
- struct btree_iter *iter,
- struct bch_inode_unpacked *inode,
- subvol_inum inum, unsigned flags)
+int __bch2_inode_peek(struct btree_trans *trans,
+ struct btree_iter *iter,
+ struct bch_inode_unpacked *inode,
+ subvol_inum inum, unsigned flags,
+ bool warn)
{
- struct bkey_s_c k;
u32 snapshot;
- int ret;
-
- ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot);
+ int ret = __bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot, warn);
if (ret)
return ret;
- k = bch2_bkey_get_iter(trans, iter, BTREE_ID_inodes,
- SPOS(0, inum.inum, snapshot),
- flags|BTREE_ITER_cached);
+ struct bkey_s_c k = bch2_bkey_get_iter(trans, iter, BTREE_ID_inodes,
+ SPOS(0, inum.inum, snapshot),
+ flags|BTREE_ITER_cached);
ret = bkey_err(k);
if (ret)
return ret;
@@ -357,20 +355,12 @@ int bch2_inode_peek_nowarn(struct btree_trans *trans,
return 0;
err:
+ if (warn)
+ bch_err_msg(trans->c, ret, "looking up inum %llu:%llu:", inum.subvol, inum.inum);
bch2_trans_iter_exit(trans, iter);
return ret;
}
-int bch2_inode_peek(struct btree_trans *trans,
- struct btree_iter *iter,
- struct bch_inode_unpacked *inode,
- subvol_inum inum, unsigned flags)
-{
- int ret = bch2_inode_peek_nowarn(trans, iter, inode, inum, flags);
- bch_err_msg(trans->c, ret, "looking up inum %llu:%llu:", inum.subvol, inum.inum);
- return ret;
-}
-
int bch2_inode_write_flags(struct btree_trans *trans,
struct btree_iter *iter,
struct bch_inode_unpacked *inode,
@@ -387,9 +377,7 @@ int bch2_inode_write_flags(struct btree_trans *trans,
return bch2_trans_update(trans, iter, &inode_p->inode.k_i, flags);
}
-int __bch2_fsck_write_inode(struct btree_trans *trans,
- struct bch_inode_unpacked *inode,
- u32 snapshot)
+int __bch2_fsck_write_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode)
{
struct bkey_inode_buf *inode_p =
bch2_trans_kmalloc(trans, sizeof(*inode_p));
@@ -398,19 +386,17 @@ int __bch2_fsck_write_inode(struct btree_trans *trans,
return PTR_ERR(inode_p);
bch2_inode_pack(inode_p, inode);
- inode_p->inode.k.p.snapshot = snapshot;
+ inode_p->inode.k.p.snapshot = inode->bi_snapshot;
return bch2_btree_insert_nonextent(trans, BTREE_ID_inodes,
&inode_p->inode.k_i,
BTREE_UPDATE_internal_snapshot_node);
}
-int bch2_fsck_write_inode(struct btree_trans *trans,
- struct bch_inode_unpacked *inode,
- u32 snapshot)
+int bch2_fsck_write_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode)
{
int ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
- __bch2_fsck_write_inode(trans, inode, snapshot));
+ __bch2_fsck_write_inode(trans, inode));
bch_err_fn(trans->c, ret);
return ret;
}
diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h
index 695abd707cb6..9c1f67705684 100644
--- a/fs/bcachefs/inode.h
+++ b/fs/bcachefs/inode.h
@@ -97,10 +97,26 @@ struct bkey_i *bch2_inode_to_v3(struct btree_trans *, struct bkey_i *);
void bch2_inode_unpacked_to_text(struct printbuf *, struct bch_inode_unpacked *);
-int bch2_inode_peek_nowarn(struct btree_trans *, struct btree_iter *,
- struct bch_inode_unpacked *, subvol_inum, unsigned);
-int bch2_inode_peek(struct btree_trans *, struct btree_iter *,
- struct bch_inode_unpacked *, subvol_inum, unsigned);
+int __bch2_inode_peek(struct btree_trans *, struct btree_iter *,
+ struct bch_inode_unpacked *, subvol_inum, unsigned, bool);
+
+static inline int bch2_inode_peek_nowarn(struct btree_trans *trans,
+ struct btree_iter *iter,
+ struct bch_inode_unpacked *inode,
+ subvol_inum inum, unsigned flags)
+{
+ return __bch2_inode_peek(trans, iter, inode, inum, flags, false);
+}
+
+static inline int bch2_inode_peek(struct btree_trans *trans,
+ struct btree_iter *iter,
+ struct bch_inode_unpacked *inode,
+ subvol_inum inum, unsigned flags)
+{
+ return __bch2_inode_peek(trans, iter, inode, inum, flags, true);
+ int ret = bch2_inode_peek_nowarn(trans, iter, inode, inum, flags);
+ return ret;
+}
int bch2_inode_write_flags(struct btree_trans *, struct btree_iter *,
struct bch_inode_unpacked *, enum btree_iter_update_trigger_flags);
@@ -112,8 +128,8 @@ static inline int bch2_inode_write(struct btree_trans *trans,
return bch2_inode_write_flags(trans, iter, inode, 0);
}
-int __bch2_fsck_write_inode(struct btree_trans *, struct bch_inode_unpacked *, u32);
-int bch2_fsck_write_inode(struct btree_trans *, struct bch_inode_unpacked *, u32);
+int __bch2_fsck_write_inode(struct btree_trans *, struct bch_inode_unpacked *);
+int bch2_fsck_write_inode(struct btree_trans *, struct bch_inode_unpacked *);
void bch2_inode_init_early(struct bch_fs *,
struct bch_inode_unpacked *);
diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c
index 177ed331c00b..307ed0a45184 100644
--- a/fs/bcachefs/io_misc.c
+++ b/fs/bcachefs/io_misc.c
@@ -224,13 +224,14 @@ void bch2_logged_op_truncate_to_text(struct printbuf *out, struct bch_fs *c, str
static int truncate_set_isize(struct btree_trans *trans,
subvol_inum inum,
- u64 new_i_size)
+ u64 new_i_size,
+ bool warn)
{
struct btree_iter iter = { NULL };
struct bch_inode_unpacked inode_u;
int ret;
- ret = bch2_inode_peek(trans, &iter, &inode_u, inum, BTREE_ITER_intent) ?:
+ ret = __bch2_inode_peek(trans, &iter, &inode_u, inum, BTREE_ITER_intent, warn) ?:
(inode_u.bi_size = new_i_size, 0) ?:
bch2_inode_write(trans, &iter, &inode_u);
@@ -247,10 +248,11 @@ static int __bch2_resume_logged_op_truncate(struct btree_trans *trans,
struct bkey_i_logged_op_truncate *op = bkey_i_to_logged_op_truncate(op_k);
subvol_inum inum = { le32_to_cpu(op->v.subvol), le64_to_cpu(op->v.inum) };
u64 new_i_size = le64_to_cpu(op->v.new_i_size);
+ bool warn_errors = i_sectors_delta != NULL;
int ret;
ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
- truncate_set_isize(trans, inum, new_i_size));
+ truncate_set_isize(trans, inum, new_i_size, i_sectors_delta != NULL));
if (ret)
goto err;
@@ -263,8 +265,8 @@ static int __bch2_resume_logged_op_truncate(struct btree_trans *trans,
if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
ret = 0;
err:
- bch2_logged_op_finish(trans, op_k);
- bch_err_fn(c, ret);
+ if (warn_errors)
+ bch_err_fn(c, ret);
return ret;
}
@@ -288,9 +290,14 @@ int bch2_truncate(struct bch_fs *c, subvol_inum inum, u64 new_i_size, u64 *i_sec
* resume only proceeding in one of the snapshots
*/
down_read(&c->snapshot_create_lock);
- int ret = bch2_trans_run(c,
- bch2_logged_op_start(trans, &op.k_i) ?:
- __bch2_resume_logged_op_truncate(trans, &op.k_i, i_sectors_delta));
+ struct btree_trans *trans = bch2_trans_get(c);
+ int ret = bch2_logged_op_start(trans, &op.k_i);
+ if (ret)
+ goto out;
+ ret = __bch2_resume_logged_op_truncate(trans, &op.k_i, i_sectors_delta);
+ ret = bch2_logged_op_finish(trans, &op.k_i) ?: ret;
+out:
+ bch2_trans_put(trans);
up_read(&c->snapshot_create_lock);
return ret;
@@ -308,7 +315,8 @@ void bch2_logged_op_finsert_to_text(struct printbuf *out, struct bch_fs *c, stru
prt_printf(out, " src_offset=%llu", le64_to_cpu(op.v->src_offset));
}
-static int adjust_i_size(struct btree_trans *trans, subvol_inum inum, u64 offset, s64 len)
+static int adjust_i_size(struct btree_trans *trans, subvol_inum inum,
+ u64 offset, s64 len, bool warn)
{
struct btree_iter iter;
struct bch_inode_unpacked inode_u;
@@ -317,7 +325,7 @@ static int adjust_i_size(struct btree_trans *trans, subvol_inum inum, u64 offset
offset <<= 9;
len <<= 9;
- ret = bch2_inode_peek(trans, &iter, &inode_u, inum, BTREE_ITER_intent);
+ ret = __bch2_inode_peek(trans, &iter, &inode_u, inum, BTREE_ITER_intent, warn);
if (ret)
return ret;
@@ -357,12 +365,22 @@ static int __bch2_resume_logged_op_finsert(struct btree_trans *trans,
u64 len = abs(shift);
u64 pos = le64_to_cpu(op->v.pos);
bool insert = shift > 0;
+ u32 snapshot;
+ bool warn_errors = i_sectors_delta != NULL;
int ret = 0;
ret = bch2_inum_opts_get(trans, inum, &opts);
if (ret)
return ret;
+ /*
+ * check for missing subvolume before fpunch, as in resume we don't want
+ * it to be a fatal error
+ */
+ ret = __bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot, warn_errors);
+ if (ret)
+ return ret;
+
bch2_trans_iter_init(trans, &iter, BTREE_ID_extents,
POS(inum.inum, 0),
BTREE_ITER_intent);
@@ -373,7 +391,7 @@ case LOGGED_OP_FINSERT_start:
if (insert) {
ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
- adjust_i_size(trans, inum, src_offset, len) ?:
+ adjust_i_size(trans, inum, src_offset, len, warn_errors) ?:
bch2_logged_op_update(trans, &op->k_i));
if (ret)
goto err;
@@ -396,11 +414,11 @@ case LOGGED_OP_FINSERT_shift_extents:
struct bkey_i delete, *copy;
struct bkey_s_c k;
struct bpos src_pos = POS(inum.inum, src_offset);
- u32 snapshot;
bch2_trans_begin(trans);
- ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot);
+ ret = __bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot,
+ warn_errors);
if (ret)
goto btree_err;
@@ -463,12 +481,12 @@ btree_err:
if (!insert) {
ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
- adjust_i_size(trans, inum, src_offset, shift) ?:
+ adjust_i_size(trans, inum, src_offset, shift, warn_errors) ?:
bch2_logged_op_update(trans, &op->k_i));
} else {
/* We need an inode update to update bi_journal_seq for fsync: */
ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
- adjust_i_size(trans, inum, 0, 0) ?:
+ adjust_i_size(trans, inum, 0, 0, warn_errors) ?:
bch2_logged_op_update(trans, &op->k_i));
}
@@ -477,9 +495,9 @@ case LOGGED_OP_FINSERT_finish:
break;
}
err:
- bch_err_fn(c, ret);
- bch2_logged_op_finish(trans, op_k);
bch2_trans_iter_exit(trans, &iter);
+ if (warn_errors)
+ bch_err_fn(c, ret);
return ret;
}
@@ -508,9 +526,14 @@ int bch2_fcollapse_finsert(struct bch_fs *c, subvol_inum inum,
* resume only proceeding in one of the snapshots
*/
down_read(&c->snapshot_create_lock);
- int ret = bch2_trans_run(c,
- bch2_logged_op_start(trans, &op.k_i) ?:
- __bch2_resume_logged_op_finsert(trans, &op.k_i, i_sectors_delta));
+ struct btree_trans *trans = bch2_trans_get(c);
+ int ret = bch2_logged_op_start(trans, &op.k_i);
+ if (ret)
+ goto out;
+ ret = __bch2_resume_logged_op_finsert(trans, &op.k_i, i_sectors_delta);
+ ret = bch2_logged_op_finish(trans, &op.k_i) ?: ret;
+out:
+ bch2_trans_put(trans);
up_read(&c->snapshot_create_lock);
return ret;
diff --git a/fs/bcachefs/logged_ops.c b/fs/bcachefs/logged_ops.c
index 6f4a4e1083c9..60e00702d1a4 100644
--- a/fs/bcachefs/logged_ops.c
+++ b/fs/bcachefs/logged_ops.c
@@ -34,8 +34,6 @@ static int resume_logged_op(struct btree_trans *trans, struct btree_iter *iter,
struct bkey_s_c k)
{
struct bch_fs *c = trans->c;
- const struct bch_logged_op_fn *fn = logged_op_fn(k.k->type);
- struct bkey_buf sk;
u32 restart_count = trans->restart_count;
struct printbuf buf = PRINTBUF;
int ret = 0;
@@ -46,13 +44,15 @@ static int resume_logged_op(struct btree_trans *trans, struct btree_iter *iter,
(bch2_bkey_val_to_text(&buf, c, k),
buf.buf));
- if (!fn)
- return 0;
-
+ struct bkey_buf sk;
bch2_bkey_buf_init(&sk);
bch2_bkey_buf_reassemble(&sk, c, k);
- fn->resume(trans, sk.k);
+ const struct bch_logged_op_fn *fn = logged_op_fn(sk.k->k.type);
+ if (fn)
+ fn->resume(trans, sk.k);
+
+ ret = bch2_logged_op_finish(trans, sk.k);
bch2_bkey_buf_exit(&sk, c);
fsck_err:
@@ -93,7 +93,7 @@ int bch2_logged_op_start(struct btree_trans *trans, struct bkey_i *k)
__bch2_logged_op_start(trans, k));
}
-void bch2_logged_op_finish(struct btree_trans *trans, struct bkey_i *k)
+int bch2_logged_op_finish(struct btree_trans *trans, struct bkey_i *k)
{
int ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc,
bch2_btree_delete(trans, BTREE_ID_logged_ops, k->k.p, 0));
@@ -113,4 +113,6 @@ void bch2_logged_op_finish(struct btree_trans *trans, struct bkey_i *k)
buf.buf, bch2_err_str(ret));
printbuf_exit(&buf);
}
+
+ return ret;
}
diff --git a/fs/bcachefs/logged_ops.h b/fs/bcachefs/logged_ops.h
index 4d1e786a27a8..30ae9ef737dd 100644
--- a/fs/bcachefs/logged_ops.h
+++ b/fs/bcachefs/logged_ops.h
@@ -15,6 +15,6 @@ static inline int bch2_logged_op_update(struct btree_trans *trans, struct bkey_i
int bch2_resume_logged_ops(struct bch_fs *);
int bch2_logged_op_start(struct btree_trans *, struct bkey_i *);
-void bch2_logged_op_finish(struct btree_trans *, struct bkey_i *);
+int bch2_logged_op_finish(struct btree_trans *, struct bkey_i *);
#endif /* _BCACHEFS_LOGGED_OPS_H */
diff --git a/fs/bcachefs/lru.c b/fs/bcachefs/lru.c
index 96f2f4f8c397..10857eccdeaf 100644
--- a/fs/bcachefs/lru.c
+++ b/fs/bcachefs/lru.c
@@ -2,6 +2,7 @@
#include "bcachefs.h"
#include "alloc_background.h"
+#include "bkey_buf.h"
#include "btree_iter.h"
#include "btree_update.h"
#include "btree_write_buffer.h"
@@ -118,7 +119,7 @@ fsck_err:
static int bch2_check_lru_key(struct btree_trans *trans,
struct btree_iter *lru_iter,
struct bkey_s_c lru_k,
- struct bpos *last_flushed_pos)
+ struct bkey_buf *last_flushed)
{
struct bch_fs *c = trans->c;
struct btree_iter iter;
@@ -132,11 +133,13 @@ static int bch2_check_lru_key(struct btree_trans *trans,
u64 idx;
int ret;
- if (fsck_err_on(!bch2_dev_bucket_exists(c, alloc_pos),
+ struct bch_dev *ca = bch2_dev_bucket_tryget_noerror(c, alloc_pos);
+
+ if (fsck_err_on(!ca,
trans, lru_entry_to_invalid_bucket,
"lru key points to nonexistent device:bucket %llu:%llu",
alloc_pos.inode, alloc_pos.offset))
- return bch2_btree_delete_at(trans, lru_iter, 0);
+ return bch2_btree_bit_mod_buffered(trans, BTREE_ID_lru, lru_iter->pos, false);
k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_alloc, alloc_pos, 0);
ret = bkey_err(k);
@@ -150,18 +153,15 @@ static int bch2_check_lru_key(struct btree_trans *trans,
idx = alloc_lru_idx_read(*a);
break;
case BCH_LRU_fragmentation:
- idx = a->fragmentation_lru;
+ idx = alloc_lru_idx_fragmentation(*a, ca);
break;
}
if (lru_k.k->type != KEY_TYPE_set ||
lru_pos_time(lru_k.k->p) != idx) {
- if (!bpos_eq(*last_flushed_pos, lru_k.k->p)) {
- *last_flushed_pos = lru_k.k->p;
- ret = bch2_btree_write_buffer_flush_sync(trans) ?:
- -BCH_ERR_transaction_restart_write_buffer_flush;
- goto out;
- }
+ ret = bch2_btree_write_buffer_maybe_flush(trans, lru_k, last_flushed);
+ if (ret)
+ goto err;
if (fsck_err(trans, lru_entry_bad,
"incorrect lru entry: lru %s time %llu\n"
@@ -171,12 +171,12 @@ static int bch2_check_lru_key(struct btree_trans *trans,
lru_pos_time(lru_k.k->p),
(bch2_bkey_val_to_text(&buf1, c, lru_k), buf1.buf),
(bch2_bkey_val_to_text(&buf2, c, k), buf2.buf)))
- ret = bch2_btree_delete_at(trans, lru_iter, 0);
+ ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_lru, lru_iter->pos, false);
}
-out:
err:
fsck_err:
bch2_trans_iter_exit(trans, &iter);
+ bch2_dev_put(ca);
printbuf_exit(&buf2);
printbuf_exit(&buf1);
return ret;
@@ -184,12 +184,18 @@ fsck_err:
int bch2_check_lrus(struct bch_fs *c)
{
- struct bpos last_flushed_pos = POS_MIN;
+ struct bkey_buf last_flushed;
+
+ bch2_bkey_buf_init(&last_flushed);
+ bkey_init(&last_flushed.k->k);
+
int ret = bch2_trans_run(c,
for_each_btree_key_commit(trans, iter,
BTREE_ID_lru, POS_MIN, BTREE_ITER_prefetch, k,
NULL, NULL, BCH_TRANS_COMMIT_no_enospc|BCH_TRANS_COMMIT_lazy_rw,
- bch2_check_lru_key(trans, &iter, k, &last_flushed_pos)));
+ bch2_check_lru_key(trans, &iter, k, &last_flushed)));
+
+ bch2_bkey_buf_exit(&last_flushed, c);
bch_err_fn(c, ret);
return ret;
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index 7d3920e03742..8c456d8b8b99 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -692,7 +692,7 @@ int bch2_evacuate_bucket(struct moving_context *ctxt,
a = bch2_alloc_to_v4(k, &a_convert);
dirty_sectors = bch2_bucket_sectors_dirty(*a);
bucket_size = ca->mi.bucket_size;
- fragmentation = a->fragmentation_lru;
+ fragmentation = alloc_lru_idx_fragmentation(*a, ca);
ret = bch2_btree_write_buffer_tryflush(trans);
bch_err_msg(c, ret, "flushing btree write buffer");
diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index d86565bf07c8..d658be90f737 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -73,6 +73,7 @@ move_bucket_in_flight_add(struct buckets_in_flight *list, struct move_bucket b)
static int bch2_bucket_is_movable(struct btree_trans *trans,
struct move_bucket *b, u64 time)
{
+ struct bch_fs *c = trans->c;
struct btree_iter iter;
struct bkey_s_c k;
struct bch_alloc_v4 _a;
@@ -90,14 +91,19 @@ static int bch2_bucket_is_movable(struct btree_trans *trans,
if (ret)
return ret;
+ struct bch_dev *ca = bch2_dev_tryget(c, k.k->p.inode);
+ if (!ca)
+ goto out;
+
a = bch2_alloc_to_v4(k, &_a);
b->k.gen = a->gen;
b->sectors = bch2_bucket_sectors_dirty(*a);
+ u64 lru_idx = alloc_lru_idx_fragmentation(*a, ca);
- ret = data_type_movable(a->data_type) &&
- a->fragmentation_lru &&
- a->fragmentation_lru <= time;
+ ret = lru_idx && lru_idx <= time;
+ bch2_dev_put(ca);
+out:
bch2_trans_iter_exit(trans, &iter);
return ret;
}
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index ed5dca5e1161..4135b1ea2fec 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -115,8 +115,8 @@ enum bch_fsck_flags {
x(alloc_key_data_type_inconsistency, 101, 0) \
x(alloc_key_to_missing_dev_bucket, 102, 0) \
x(alloc_key_cached_inconsistency, 103, 0) \
- x(alloc_key_cached_but_read_time_zero, 104, 0) \
- x(alloc_key_to_missing_lru_entry, 105, 0) \
+ x(alloc_key_cached_but_read_time_zero, 104, FSCK_AUTOFIX) \
+ x(alloc_key_to_missing_lru_entry, 105, FSCK_AUTOFIX) \
x(alloc_key_data_type_wrong, 106, FSCK_AUTOFIX) \
x(alloc_key_gen_wrong, 107, FSCK_AUTOFIX) \
x(alloc_key_dirty_sectors_wrong, 108, FSCK_AUTOFIX) \
@@ -129,20 +129,20 @@ enum bch_fsck_flags {
x(freespace_key_wrong, 115, 0) \
x(freespace_hole_missing, 116, 0) \
x(bucket_gens_val_size_bad, 117, 0) \
- x(bucket_gens_key_wrong, 118, 0) \
- x(bucket_gens_hole_wrong, 119, 0) \
- x(bucket_gens_to_invalid_dev, 120, 0) \
- x(bucket_gens_to_invalid_buckets, 121, 0) \
- x(bucket_gens_nonzero_for_invalid_buckets, 122, 0) \
+ x(bucket_gens_key_wrong, 118, FSCK_AUTOFIX) \
+ x(bucket_gens_hole_wrong, 119, FSCK_AUTOFIX) \
+ x(bucket_gens_to_invalid_dev, 120, FSCK_AUTOFIX) \
+ x(bucket_gens_to_invalid_buckets, 121, FSCK_AUTOFIX) \
+ x(bucket_gens_nonzero_for_invalid_buckets, 122, FSCK_AUTOFIX) \
x(need_discard_freespace_key_to_invalid_dev_bucket, 123, 0) \
x(need_discard_freespace_key_bad, 124, 0) \
x(backpointer_bucket_offset_wrong, 125, 0) \
x(backpointer_to_missing_device, 126, 0) \
x(backpointer_to_missing_alloc, 127, 0) \
x(backpointer_to_missing_ptr, 128, 0) \
- x(lru_entry_at_time_0, 129, 0) \
- x(lru_entry_to_invalid_bucket, 130, 0) \
- x(lru_entry_bad, 131, 0) \
+ x(lru_entry_at_time_0, 129, FSCK_AUTOFIX) \
+ x(lru_entry_to_invalid_bucket, 130, FSCK_AUTOFIX) \
+ x(lru_entry_bad, 131, FSCK_AUTOFIX) \
x(btree_ptr_val_too_big, 132, 0) \
x(btree_ptr_v2_val_too_big, 133, 0) \
x(btree_ptr_has_non_ptr, 134, 0) \
@@ -158,9 +158,9 @@ enum bch_fsck_flags {
x(ptr_after_last_bucket, 144, 0) \
x(ptr_before_first_bucket, 145, 0) \
x(ptr_spans_multiple_buckets, 146, 0) \
- x(ptr_to_missing_backpointer, 147, 0) \
- x(ptr_to_missing_alloc_key, 148, 0) \
- x(ptr_to_missing_replicas_entry, 149, 0) \
+ x(ptr_to_missing_backpointer, 147, FSCK_AUTOFIX) \
+ x(ptr_to_missing_alloc_key, 148, FSCK_AUTOFIX) \
+ x(ptr_to_missing_replicas_entry, 149, FSCK_AUTOFIX) \
x(ptr_to_missing_stripe, 150, 0) \
x(ptr_to_incorrect_stripe, 151, 0) \
x(ptr_gen_newer_than_bucket_gen, 152, 0) \
@@ -194,7 +194,7 @@ enum bch_fsck_flags {
x(snapshot_skiplist_not_normalized, 180, 0) \
x(snapshot_skiplist_bad, 181, 0) \
x(snapshot_should_not_have_subvol, 182, 0) \
- x(snapshot_to_bad_snapshot_tree, 183, 0) \
+ x(snapshot_to_bad_snapshot_tree, 183, FSCK_AUTOFIX) \
x(snapshot_bad_depth, 184, 0) \
x(snapshot_bad_skiplist, 185, 0) \
x(subvol_pos_bad, 186, 0) \
@@ -211,6 +211,7 @@ enum bch_fsck_flags {
x(inode_unlinked_but_clean, 197, 0) \
x(inode_unlinked_but_nlink_nonzero, 198, 0) \
x(inode_unlinked_and_not_open, 281, 0) \
+ x(inode_unlinked_but_has_dirent, 285, 0) \
x(inode_checksum_type_invalid, 199, 0) \
x(inode_compression_type_invalid, 200, 0) \
x(inode_subvol_root_but_not_dir, 201, 0) \
@@ -219,6 +220,8 @@ enum bch_fsck_flags {
x(inode_i_sectors_wrong, 204, FSCK_AUTOFIX) \
x(inode_dir_wrong_nlink, 205, FSCK_AUTOFIX) \
x(inode_dir_multiple_links, 206, FSCK_AUTOFIX) \
+ x(inode_dir_missing_backpointer, 284, FSCK_AUTOFIX) \
+ x(inode_dir_unlinked_but_not_empty, 286, FSCK_AUTOFIX) \
x(inode_multiple_links_but_nlink_0, 207, FSCK_AUTOFIX) \
x(inode_wrong_backpointer, 208, FSCK_AUTOFIX) \
x(inode_wrong_nlink, 209, FSCK_AUTOFIX) \
@@ -295,7 +298,7 @@ enum bch_fsck_flags {
x(accounting_key_replicas_devs_unsorted, 280, FSCK_AUTOFIX) \
x(accounting_key_version_0, 282, FSCK_AUTOFIX) \
x(logged_op_but_clean, 283, FSCK_AUTOFIX) \
- x(MAX, 284, 0)
+ x(MAX, 287, 0)
enum bch_sb_error_id {
#define x(t, n, ...) BCH_FSCK_ERR_##t = n,
diff --git a/fs/bcachefs/siphash.c b/fs/bcachefs/siphash.c
index dc1a27cc31cd..a1cc44e66c7e 100644
--- a/fs/bcachefs/siphash.c
+++ b/fs/bcachefs/siphash.c
@@ -45,7 +45,7 @@
*/
#include <asm/byteorder.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/bitops.h>
#include <linux/string.h>
diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c
index 6845dde1b339..91d8187ee168 100644
--- a/fs/bcachefs/subvolume.c
+++ b/fs/bcachefs/subvolume.c
@@ -102,7 +102,8 @@ static int check_subvol(struct btree_trans *trans,
inode.bi_inum, inode.bi_snapshot,
inode.bi_subvol, subvol.k->p.offset)) {
inode.bi_subvol = subvol.k->p.offset;
- ret = __bch2_fsck_write_inode(trans, &inode, le32_to_cpu(subvol.v->snapshot));
+ inode.bi_snapshot = le32_to_cpu(subvol.v->snapshot);
+ ret = __bch2_fsck_write_inode(trans, &inode);
if (ret)
goto err;
}
@@ -331,8 +332,8 @@ int bch2_snapshot_get_subvol(struct btree_trans *trans, u32 snapshot,
bch2_subvolume_get(trans, le32_to_cpu(snap.subvol), true, 0, subvol);
}
-int bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid,
- u32 *snapid)
+int __bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid,
+ u32 *snapid, bool warn)
{
struct btree_iter iter;
struct bkey_s_c_subvolume subvol;
@@ -343,7 +344,8 @@ int bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid,
BTREE_ITER_cached|BTREE_ITER_with_updates,
subvolume);
ret = bkey_err(subvol);
- bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c,
+
+ bch2_fs_inconsistent_on(warn && bch2_err_matches(ret, ENOENT), trans->c,
"missing subvolume %u", subvolid);
if (likely(!ret))
@@ -352,6 +354,12 @@ int bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid,
return ret;
}
+int bch2_subvolume_get_snapshot(struct btree_trans *trans, u32 subvolid,
+ u32 *snapid)
+{
+ return __bch2_subvolume_get_snapshot(trans, subvolid, snapid, true);
+}
+
static int bch2_subvolume_reparent(struct btree_trans *trans,
struct btree_iter *iter,
struct bkey_s_c k,
diff --git a/fs/bcachefs/subvolume.h b/fs/bcachefs/subvolume.h
index e62f876541fe..f897d106e142 100644
--- a/fs/bcachefs/subvolume.h
+++ b/fs/bcachefs/subvolume.h
@@ -26,6 +26,8 @@ int bch2_subvolume_trigger(struct btree_trans *, enum btree_id, unsigned,
int bch2_subvol_has_children(struct btree_trans *, u32);
int bch2_subvolume_get(struct btree_trans *, unsigned,
bool, int, struct bch_subvolume *);
+int __bch2_subvolume_get_snapshot(struct btree_trans *, u32,
+ u32 *, bool);
int bch2_subvolume_get_snapshot(struct btree_trans *, u32, u32 *);
int bch2_subvol_is_ro_trans(struct btree_trans *, u32);
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index 42f565c76181..e0a876cbaa6b 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -222,7 +222,7 @@ u64 bch2_read_flag_list(const char *opt, const char * const list[])
break;
}
- ret |= 1 << flag;
+ ret |= BIT_ULL(flag);
}
kfree(d);
diff --git a/fs/bcachefs/varint.c b/fs/bcachefs/varint.c
index a9ebcd82c602..6a78553d9b0c 100644
--- a/fs/bcachefs/varint.c
+++ b/fs/bcachefs/varint.c
@@ -3,7 +3,7 @@
#include <linux/bitops.h>
#include <linux/math.h>
#include <linux/string.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#ifdef CONFIG_VALGRIND
#include <valgrind/memcheck.h>
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index cd6d5bbb4b9d..390808ce935d 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -39,7 +39,7 @@
#include <linux/vmalloc.h>
#include <asm/byteorder.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <asm/cacheflush.h>
#include <asm/page.h>
#include <asm/flat.h>
diff --git a/fs/btrfs/accessors.c b/fs/btrfs/accessors.c
index 79026917db19..e3716516ca38 100644
--- a/fs/btrfs/accessors.c
+++ b/fs/btrfs/accessors.c
@@ -3,7 +3,7 @@
* Copyright (C) 2007 Oracle. All rights reserved.
*/
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "messages.h"
#include "extent_io.h"
#include "fs.h"
diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h
index b2eb9cde2c5d..7a7e0ef69973 100644
--- a/fs/btrfs/accessors.h
+++ b/fs/btrfs/accessors.h
@@ -3,7 +3,7 @@
#ifndef BTRFS_ACCESSORS_H
#define BTRFS_ACCESSORS_H
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/stddef.h>
#include <linux/types.h>
#include <linux/align.h>
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index e2f478ecd7fd..f8e1d5b2c512 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -3179,10 +3179,14 @@ void btrfs_backref_release_cache(struct btrfs_backref_cache *cache)
btrfs_backref_cleanup_node(cache, node);
}
- cache->last_trans = 0;
-
- for (i = 0; i < BTRFS_MAX_LEVEL; i++)
- ASSERT(list_empty(&cache->pending[i]));
+ for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
+ while (!list_empty(&cache->pending[i])) {
+ node = list_first_entry(&cache->pending[i],
+ struct btrfs_backref_node,
+ list);
+ btrfs_backref_cleanup_node(cache, node);
+ }
+ }
ASSERT(list_empty(&cache->pending_edge));
ASSERT(list_empty(&cache->useless_node));
ASSERT(list_empty(&cache->changed));
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 25d768e67e37..4ad5db619b00 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -17,7 +17,7 @@
#include <linux/error-injection.h>
#include <linux/crc32c.h>
#include <linux/sched/mm.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/hash.h>
#include "ctree.h"
#include "disk-io.h"
@@ -4256,6 +4256,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
btrfs_cleanup_defrag_inodes(fs_info);
/*
+ * Wait for any fixup workers to complete.
+ * If we don't wait for them here and they are still running by the time
+ * we call kthread_stop() against the cleaner kthread further below, we
+ * get an use-after-free on the cleaner because the fixup worker adds an
+ * inode to the list of delayed iputs and then attempts to wakeup the
+ * cleaner kthread, which was already stopped and destroyed. We parked
+ * already the cleaner, but below we run all pending delayed iputs.
+ */
+ btrfs_flush_workqueue(fs_info->fixup_workers);
+
+ /*
* After we parked the cleaner kthread, ordered extents may have
* completed and created new delayed iputs. If one of the async reclaim
* tasks is running and in the RUN_DELAYED_IPUTS flush state, then we
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index edac499fd83d..5618ca02934a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -32,7 +32,7 @@
#include <linux/migrate.h>
#include <linux/sched/mm.h>
#include <linux/iomap.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/fsverity.h>
#include "misc.h"
#include "ctree.h"
@@ -3111,6 +3111,11 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent)
ret = btrfs_update_inode_fallback(trans, inode);
if (ret) /* -ENOMEM or corruption */
btrfs_abort_transaction(trans, ret);
+
+ ret = btrfs_insert_raid_extent(trans, ordered_extent);
+ if (ret)
+ btrfs_abort_transaction(trans, ret);
+
goto out;
}
diff --git a/fs/btrfs/messages.c b/fs/btrfs/messages.c
index 77752eec125d..363fd28c0268 100644
--- a/fs/btrfs/messages.c
+++ b/fs/btrfs/messages.c
@@ -239,7 +239,8 @@ void __cold _btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt,
vaf.fmt = fmt;
vaf.va = &args;
- if (__ratelimit(ratelimit)) {
+ /* Do not ratelimit if CONFIG_BTRFS_DEBUG is enabled. */
+ if (IS_ENABLED(CONFIG_BTRFS_DEBUG) || __ratelimit(ratelimit)) {
if (fs_info) {
char statestr[STATE_STRING_BUF_LEN];
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index ea4ed85919ec..f3834f8d26b4 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -232,70 +232,6 @@ static struct btrfs_backref_node *walk_down_backref(
return NULL;
}
-static void update_backref_node(struct btrfs_backref_cache *cache,
- struct btrfs_backref_node *node, u64 bytenr)
-{
- struct rb_node *rb_node;
- rb_erase(&node->rb_node, &cache->rb_root);
- node->bytenr = bytenr;
- rb_node = rb_simple_insert(&cache->rb_root, node->bytenr, &node->rb_node);
- if (rb_node)
- btrfs_backref_panic(cache->fs_info, bytenr, -EEXIST);
-}
-
-/*
- * update backref cache after a transaction commit
- */
-static int update_backref_cache(struct btrfs_trans_handle *trans,
- struct btrfs_backref_cache *cache)
-{
- struct btrfs_backref_node *node;
- int level = 0;
-
- if (cache->last_trans == 0) {
- cache->last_trans = trans->transid;
- return 0;
- }
-
- if (cache->last_trans == trans->transid)
- return 0;
-
- /*
- * detached nodes are used to avoid unnecessary backref
- * lookup. transaction commit changes the extent tree.
- * so the detached nodes are no longer useful.
- */
- while (!list_empty(&cache->detached)) {
- node = list_entry(cache->detached.next,
- struct btrfs_backref_node, list);
- btrfs_backref_cleanup_node(cache, node);
- }
-
- while (!list_empty(&cache->changed)) {
- node = list_entry(cache->changed.next,
- struct btrfs_backref_node, list);
- list_del_init(&node->list);
- BUG_ON(node->pending);
- update_backref_node(cache, node, node->new_bytenr);
- }
-
- /*
- * some nodes can be left in the pending list if there were
- * errors during processing the pending nodes.
- */
- for (level = 0; level < BTRFS_MAX_LEVEL; level++) {
- list_for_each_entry(node, &cache->pending[level], list) {
- BUG_ON(!node->pending);
- if (node->bytenr == node->new_bytenr)
- continue;
- update_backref_node(cache, node, node->new_bytenr);
- }
- }
-
- cache->last_trans = 0;
- return 1;
-}
-
static bool reloc_root_is_dead(const struct btrfs_root *root)
{
/*
@@ -551,9 +487,6 @@ static int clone_backref_node(struct btrfs_trans_handle *trans,
struct btrfs_backref_edge *new_edge;
struct rb_node *rb_node;
- if (cache->last_trans > 0)
- update_backref_cache(trans, cache);
-
rb_node = rb_simple_search(&cache->rb_root, src->commit_root->start);
if (rb_node) {
node = rb_entry(rb_node, struct btrfs_backref_node, rb_node);
@@ -923,7 +856,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
btrfs_grab_root(reloc_root);
/* root->reloc_root will stay until current relocation finished */
- if (fs_info->reloc_ctl->merge_reloc_tree &&
+ if (fs_info->reloc_ctl && fs_info->reloc_ctl->merge_reloc_tree &&
btrfs_root_refs(root_item) == 0) {
set_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state);
/*
@@ -3698,11 +3631,9 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
break;
}
restart:
- if (update_backref_cache(trans, &rc->backref_cache)) {
- btrfs_end_transaction(trans);
- trans = NULL;
- continue;
- }
+ if (rc->backref_cache.last_trans != trans->transid)
+ btrfs_backref_release_cache(&rc->backref_cache);
+ rc->backref_cache.last_trans = trans->transid;
ret = find_next_extent(rc, path, &key);
if (ret < 0)
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 7f48ba6c1c77..27306d98ec43 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -346,8 +346,10 @@ struct name_cache_entry {
u64 parent_gen;
int ret;
int need_later_update;
+ /* Name length without NUL terminator. */
int name_len;
- char name[] __counted_by(name_len);
+ /* Not NUL terminated. */
+ char name[] __counted_by(name_len) __nonstring;
};
/* See the comment at lru_cache.h about struct btrfs_lru_cache_entry. */
@@ -2388,7 +2390,7 @@ out_cache:
/*
* Store the result of the lookup in the name cache.
*/
- nce = kmalloc(sizeof(*nce) + fs_path_len(dest) + 1, GFP_KERNEL);
+ nce = kmalloc(sizeof(*nce) + fs_path_len(dest), GFP_KERNEL);
if (!nce) {
ret = -ENOMEM;
goto out;
@@ -2400,7 +2402,7 @@ out_cache:
nce->parent_gen = *parent_gen;
nce->name_len = fs_path_len(dest);
nce->ret = ret;
- strcpy(nce->name, dest->start);
+ memcpy(nce->name, dest->start, nce->name_len);
if (ino < sctx->send_progress)
nce->need_later_update = 0;
@@ -6187,8 +6189,29 @@ static int send_write_or_clone(struct send_ctx *sctx,
if (ret < 0)
return ret;
- if (clone_root->offset + num_bytes == info.size)
+ if (clone_root->offset + num_bytes == info.size) {
+ /*
+ * The final size of our file matches the end offset, but it may
+ * be that its current size is larger, so we have to truncate it
+ * to any value between the start offset of the range and the
+ * final i_size, otherwise the clone operation is invalid
+ * because it's unaligned and it ends before the current EOF.
+ * We do this truncate to the final i_size when we finish
+ * processing the inode, but it's too late by then. And here we
+ * truncate to the start offset of the range because it's always
+ * sector size aligned while if it were the final i_size it
+ * would result in dirtying part of a page, filling part of a
+ * page with zeroes and then having the clone operation at the
+ * receiver trigger IO and wait for it due to the dirty page.
+ */
+ if (sctx->parent_root != NULL) {
+ ret = send_truncate(sctx, sctx->cur_ino,
+ sctx->cur_inode_gen, offset);
+ if (ret < 0)
+ return ret;
+ }
goto clone_data;
+ }
write_data:
ret = send_extent_data(sctx, path, offset, num_bytes);
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index c6399513c66f..aca2861f2187 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -5,7 +5,7 @@
#include <linux/kthread.h>
#include <linux/uuid.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "messages.h"
#include "ctree.h"
#include "transaction.h"
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index f53977169db4..2b3f9935dbb4 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -595,14 +595,12 @@ static bool cachefiles_open_file(struct cachefiles_object *object,
* write and readdir but not lookup or open).
*/
touch_atime(&file->f_path);
- dput(dentry);
return true;
check_failed:
fscache_cookie_lookup_negative(object->cookie);
cachefiles_unmark_inode_in_use(object, file);
fput(file);
- dput(dentry);
if (ret == -ESTALE)
return cachefiles_create_file(object);
return false;
@@ -611,7 +609,6 @@ error_fput:
fput(file);
error:
cachefiles_do_unmark_inode_in_use(object, d_inode(dentry));
- dput(dentry);
return false;
}
@@ -654,7 +651,9 @@ bool cachefiles_look_up_object(struct cachefiles_object *object)
goto new_file;
}
- if (!cachefiles_open_file(object, dentry))
+ ret = cachefiles_open_file(object, dentry);
+ dput(dentry);
+ if (!ret)
return false;
_leave(" = t [%lu]", file_inode(object->file)->i_ino);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 53fef258c2bc..c2a9e2cc03de 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -489,8 +489,11 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
rreq->io_streams[0].sreq_max_len = fsc->mount_options->rsize;
out:
- if (ret < 0)
+ if (ret < 0) {
+ if (got)
+ ceph_put_cap_refs(ceph_inode(inode), got);
kfree(priv);
+ }
return ret;
}
@@ -2145,7 +2148,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
}
pool_ns_len = pool_ns ? pool_ns->len : 0;
- perm = kmalloc(sizeof(*perm) + pool_ns_len + 1, GFP_NOFS);
+ perm = kmalloc(struct_size(perm, pool_ns, pool_ns_len + 1), GFP_NOFS);
if (!perm) {
err = -ENOMEM;
goto out_unlock;
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index a79f163ae4ed..44451749c544 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -3,7 +3,7 @@
#include <linux/exportfs.h>
#include <linux/slab.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "super.h"
#include "mds_client.h"
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 2508aa8950b7..037eac35a9e0 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -5,7 +5,7 @@
#include <linux/ceph/ceph_debug.h>
#include <linux/ceph/osd_client.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/backing-dev.h>
#include <linux/completion.h>
#include <linux/exportfs.h>
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index 6681a71625f0..206835e31efa 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -18,7 +18,7 @@
* information about these ioctls.
*/
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/skcipher.h>
#include <linux/key-type.h>
#include <linux/random.h>
diff --git a/fs/dax.c b/fs/dax.c
index becb4a6920c6..c62acd2812f8 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1305,11 +1305,15 @@ int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len,
struct iomap_iter iter = {
.inode = inode,
.pos = pos,
- .len = len,
.flags = IOMAP_WRITE | IOMAP_UNSHARE | IOMAP_DAX,
};
+ loff_t size = i_size_read(inode);
int ret;
+ if (pos < 0 || pos >= size)
+ return 0;
+
+ iter.len = min(len, size - pos);
while ((ret = iomap_iter(&iter, ops)) > 0)
iter.processed = dax_unshare_iter(&iter);
return ret;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index d39a1a69fecc..827278525fd9 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -21,7 +21,7 @@
#include <linux/file.h>
#include <linux/scatterlist.h>
#include <linux/slab.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/kernel.h>
#include <linux/xattr.h>
#include "ecryptfs_kernel.h"
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 5ed1e4cf6c0b..cbdf82f0183f 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -21,7 +21,7 @@
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#include <linux/fileattr.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "ecryptfs_kernel.h"
static int lock_parent(struct dentry *dentry,
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 287e5d407f08..ceda5555971a 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -19,7 +19,7 @@
#include <linux/scatterlist.h>
#include <linux/slab.h>
#include <linux/xattr.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "ecryptfs_kernel.h"
/*
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index e980e29873a5..1253a8456e59 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -4,7 +4,7 @@
* https://www.huawei.com/
*/
#include "internal.h"
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <trace/events/erofs.h>
struct z_erofs_maprecorder {
diff --git a/fs/exfat/cache.c b/fs/exfat/cache.c
index 7cc200d89821..d5ce0ae660ba 100644
--- a/fs/exfat/cache.c
+++ b/fs/exfat/cache.c
@@ -11,7 +11,7 @@
*/
#include <linux/slab.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/buffer_head.h>
#include "exfat_raw.h"
diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c
index 56b870d9cc0d..773c320d68f3 100644
--- a/fs/exfat/fatent.c
+++ b/fs/exfat/fatent.c
@@ -4,7 +4,7 @@
*/
#include <linux/slab.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
diff --git a/fs/exfat/nls.c b/fs/exfat/nls.c
index 1ac011088ce7..d47896a89596 100644
--- a/fs/exfat/nls.c
+++ b/fs/exfat/nls.c
@@ -6,7 +6,7 @@
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/buffer_head.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "exfat_raw.h"
#include "exfat_fs.h"
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index eaa5f5b51f50..b33664f6ce2a 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -379,7 +379,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl
*/
static int ext4_fc_track_template(
handle_t *handle, struct inode *inode,
- int (*__fc_track_fn)(struct inode *, void *, bool),
+ int (*__fc_track_fn)(handle_t *handle, struct inode *, void *, bool),
void *args, int enqueue)
{
bool update = false;
@@ -396,7 +396,7 @@ static int ext4_fc_track_template(
ext4_fc_reset_inode(inode);
ei->i_sync_tid = tid;
}
- ret = __fc_track_fn(inode, args, update);
+ ret = __fc_track_fn(handle, inode, args, update);
mutex_unlock(&ei->i_fc_lock);
if (!enqueue)
@@ -420,7 +420,8 @@ struct __track_dentry_update_args {
};
/* __track_fn for directory entry updates. Called with ei->i_fc_lock. */
-static int __track_dentry_update(struct inode *inode, void *arg, bool update)
+static int __track_dentry_update(handle_t *handle, struct inode *inode,
+ void *arg, bool update)
{
struct ext4_fc_dentry_update *node;
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -435,14 +436,14 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
if (IS_ENCRYPTED(dir)) {
ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_ENCRYPTED_FILENAME,
- NULL);
+ handle);
mutex_lock(&ei->i_fc_lock);
return -EOPNOTSUPP;
}
node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS);
if (!node) {
- ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, NULL);
+ ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle);
mutex_lock(&ei->i_fc_lock);
return -ENOMEM;
}
@@ -454,7 +455,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
node->fcd_name.name = kmalloc(dentry->d_name.len, GFP_NOFS);
if (!node->fcd_name.name) {
kmem_cache_free(ext4_fc_dentry_cachep, node);
- ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, NULL);
+ ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle);
mutex_lock(&ei->i_fc_lock);
return -ENOMEM;
}
@@ -576,7 +577,8 @@ void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
}
/* __track_fn for inode tracking */
-static int __track_inode(struct inode *inode, void *arg, bool update)
+static int __track_inode(handle_t *handle, struct inode *inode, void *arg,
+ bool update)
{
if (update)
return -EEXIST;
@@ -614,7 +616,8 @@ struct __track_range_args {
};
/* __track_fn for tracking data updates */
-static int __track_range(struct inode *inode, void *arg, bool update)
+static int __track_range(handle_t *handle, struct inode *inode, void *arg,
+ bool update)
{
struct ext4_inode_info *ei = EXT4_I(inode);
ext4_lblk_t oldstart;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index e04eb08b9060..a2704f064361 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -230,8 +230,8 @@ struct ext4_new_flex_group_data {
#define MAX_RESIZE_BG 16384
/*
- * alloc_flex_gd() allocates a ext4_new_flex_group_data with size of
- * @flexbg_size.
+ * alloc_flex_gd() allocates an ext4_new_flex_group_data that satisfies the
+ * resizing from @o_group to @n_group, its size is typically @flexbg_size.
*
* Returns NULL on failure otherwise address of the allocated structure.
*/
@@ -239,25 +239,27 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size,
ext4_group_t o_group, ext4_group_t n_group)
{
ext4_group_t last_group;
+ unsigned int max_resize_bg;
struct ext4_new_flex_group_data *flex_gd;
flex_gd = kmalloc(sizeof(*flex_gd), GFP_NOFS);
if (flex_gd == NULL)
goto out3;
- if (unlikely(flexbg_size > MAX_RESIZE_BG))
- flex_gd->resize_bg = MAX_RESIZE_BG;
- else
- flex_gd->resize_bg = flexbg_size;
+ max_resize_bg = umin(flexbg_size, MAX_RESIZE_BG);
+ flex_gd->resize_bg = max_resize_bg;
/* Avoid allocating large 'groups' array if not needed */
last_group = o_group | (flex_gd->resize_bg - 1);
if (n_group <= last_group)
- flex_gd->resize_bg = 1 << fls(n_group - o_group + 1);
+ flex_gd->resize_bg = 1 << fls(n_group - o_group);
else if (n_group - last_group < flex_gd->resize_bg)
- flex_gd->resize_bg = 1 << max(fls(last_group - o_group + 1),
+ flex_gd->resize_bg = 1 << max(fls(last_group - o_group),
fls(n_group - last_group));
+ if (WARN_ON_ONCE(flex_gd->resize_bg > max_resize_bg))
+ flex_gd->resize_bg = max_resize_bg;
+
flex_gd->groups = kmalloc_array(flex_gd->resize_bg,
sizeof(struct ext4_new_group_data),
GFP_NOFS);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index e0e1956dcdd3..7647e9f6e190 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -2559,6 +2559,8 @@ retry:
error = ext4_xattr_set_handle(handle, inode, name_index, name,
value, value_len, flags);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR,
+ handle);
error2 = ext4_journal_stop(handle);
if (error == -ENOSPC &&
ext4_should_retry_alloc(sb, &retries))
@@ -2566,7 +2568,6 @@ retry:
if (error == 0)
error = error2;
}
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, NULL);
return error;
}
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 1136539a57a8..47a5c806cf16 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -5,7 +5,7 @@
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/sched/signal.h>
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 9756f0f2b7f7..e4d81b8705d1 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -5,7 +5,7 @@
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/sched/mm.h>
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 75722bbd6b5f..3852bb66358c 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -19,7 +19,7 @@
#include <linux/uio.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/random.h>
#include <linux/iversion.h>
#include "fat.h"
diff --git a/fs/file.c b/fs/file.c
index 5125607d040a..eb093e736972 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -272,59 +272,45 @@ static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt)
return test_bit(fd, fdt->open_fds);
}
-static unsigned int count_open_files(struct fdtable *fdt)
-{
- unsigned int size = fdt->max_fds;
- unsigned int i;
-
- /* Find the last open fd */
- for (i = size / BITS_PER_LONG; i > 0; ) {
- if (fdt->open_fds[--i])
- break;
- }
- i = (i + 1) * BITS_PER_LONG;
- return i;
-}
-
/*
* Note that a sane fdtable size always has to be a multiple of
* BITS_PER_LONG, since we have bitmaps that are sized by this.
*
- * 'max_fds' will normally already be properly aligned, but it
- * turns out that in the close_range() -> __close_range() ->
- * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end
- * up having a 'max_fds' value that isn't already aligned.
- *
- * Rather than make close_range() have to worry about this,
- * just make that BITS_PER_LONG alignment be part of a sane
- * fdtable size. Becuase that's really what it is.
+ * punch_hole is optional - when close_range() is asked to unshare
+ * and close, we don't need to copy descriptors in that range, so
+ * a smaller cloned descriptor table might suffice if the last
+ * currently opened descriptor falls into that range.
*/
-static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds)
+static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole)
{
- unsigned int count;
-
- count = count_open_files(fdt);
- if (max_fds < NR_OPEN_DEFAULT)
- max_fds = NR_OPEN_DEFAULT;
- return ALIGN(min(count, max_fds), BITS_PER_LONG);
+ unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds);
+
+ if (last == fdt->max_fds)
+ return NR_OPEN_DEFAULT;
+ if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) {
+ last = find_last_bit(fdt->open_fds, punch_hole->from);
+ if (last == punch_hole->from)
+ return NR_OPEN_DEFAULT;
+ }
+ return ALIGN(last + 1, BITS_PER_LONG);
}
/*
- * Allocate a new files structure and copy contents from the
- * passed in files structure.
- * errorp will be valid only when the returned files_struct is NULL.
+ * Allocate a new descriptor table and copy contents from the passed in
+ * instance. Returns a pointer to cloned table on success, ERR_PTR()
+ * on failure. For 'punch_hole' see sane_fdtable_size().
*/
-struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp)
+struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole)
{
struct files_struct *newf;
struct file **old_fds, **new_fds;
unsigned int open_files, i;
struct fdtable *old_fdt, *new_fdt;
+ int error;
- *errorp = -ENOMEM;
newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
if (!newf)
- goto out;
+ return ERR_PTR(-ENOMEM);
atomic_set(&newf->count, 1);
@@ -341,7 +327,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
- open_files = sane_fdtable_size(old_fdt, max_fds);
+ open_files = sane_fdtable_size(old_fdt, punch_hole);
/*
* Check whether we need to allocate a larger fd array and fd set.
@@ -354,14 +340,14 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
new_fdt = alloc_fdtable(open_files - 1);
if (!new_fdt) {
- *errorp = -ENOMEM;
+ error = -ENOMEM;
goto out_release;
}
/* beyond sysctl_nr_open; nothing to do */
if (unlikely(new_fdt->max_fds < open_files)) {
__free_fdtable(new_fdt);
- *errorp = -EMFILE;
+ error = -EMFILE;
goto out_release;
}
@@ -372,7 +358,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
*/
spin_lock(&oldf->file_lock);
old_fdt = files_fdtable(oldf);
- open_files = sane_fdtable_size(old_fdt, max_fds);
+ open_files = sane_fdtable_size(old_fdt, punch_hole);
}
copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG);
@@ -406,8 +392,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
out_release:
kmem_cache_free(files_cachep, newf);
-out:
- return NULL;
+ return ERR_PTR(error);
}
static struct fdtable *close_files(struct files_struct * files)
@@ -748,37 +733,25 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
if (fd > max_fd)
return -EINVAL;
- if (flags & CLOSE_RANGE_UNSHARE) {
- int ret;
- unsigned int max_unshare_fds = NR_OPEN_MAX;
+ if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) {
+ struct fd_range range = {fd, max_fd}, *punch_hole = &range;
/*
* If the caller requested all fds to be made cloexec we always
* copy all of the file descriptors since they still want to
* use them.
*/
- if (!(flags & CLOSE_RANGE_CLOEXEC)) {
- /*
- * If the requested range is greater than the current
- * maximum, we're closing everything so only copy all
- * file descriptors beneath the lowest file descriptor.
- */
- rcu_read_lock();
- if (max_fd >= last_fd(files_fdtable(cur_fds)))
- max_unshare_fds = fd;
- rcu_read_unlock();
- }
-
- ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds);
- if (ret)
- return ret;
+ if (flags & CLOSE_RANGE_CLOEXEC)
+ punch_hole = NULL;
+ fds = dup_fd(cur_fds, punch_hole);
+ if (IS_ERR(fds))
+ return PTR_ERR(fds);
/*
* We used to share our file descriptor table, and have now
* created a private one, make sure we're using it below.
*/
- if (fds)
- swap(cur_fds, fds);
+ swap(cur_fds, fds);
}
if (flags & CLOSE_RANGE_CLOEXEC)
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index ce9346099c72..9592ffcb44e5 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -12,7 +12,7 @@
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/cdrom.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index f5a2476c47bf..237c1c23e855 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -21,7 +21,7 @@
#include <linux/slab.h>
#include <linux/sched/signal.h>
#include <linux/blkdev.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "hpfs.h"
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 11ea747228ae..78ebd265f425 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1321,7 +1321,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
return length;
/*
- * Don't bother with holes or unwritten extents.
+ * Don't bother with delalloc reservations, holes or unwritten extents.
*
* Note that we use srcmap directly instead of iomap_iter_srcmap as
* unsharing requires providing a separate source map, and the presence
@@ -1330,6 +1330,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
* fork for XFS.
*/
if (iter->srcmap.type == IOMAP_HOLE ||
+ iter->srcmap.type == IOMAP_DELALLOC ||
iter->srcmap.type == IOMAP_UNWRITTEN)
return length;
@@ -1374,11 +1375,15 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
struct iomap_iter iter = {
.inode = inode,
.pos = pos,
- .len = len,
.flags = IOMAP_WRITE | IOMAP_UNSHARE,
};
+ loff_t size = i_size_read(inode);
int ret;
+ if (pos < 0 || pos >= size)
+ return 0;
+
+ iter.len = min(len, size - pos);
while ((ret = iomap_iter(&iter, ops)) > 0)
iter.processed = iomap_unshare_iter(&iter);
return ret;
diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h
index dcdc191ed183..2d55207c9a99 100644
--- a/fs/isofs/isofs.h
+++ b/fs/isofs/isofs.h
@@ -3,7 +3,7 @@
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/iso_fs.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
enum isofs_file_format {
isofs_file_normal = 0,
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 87a0f207df0b..b8fc732e1c67 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -18,7 +18,7 @@
#include <linux/sunrpc/svc.h>
#include <linux/lockd/lockd.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "netns.h"
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 63280791de3b..78fe5796b2b2 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -102,7 +102,7 @@ void netfs_clear_buffer(struct netfs_io_request *rreq)
while ((p = rreq->buffer)) {
rreq->buffer = p->next;
- for (int slot = 0; slot < folioq_nr_slots(p); slot++) {
+ for (int slot = 0; slot < folioq_count(p); slot++) {
struct folio *folio = folioq_folio(p, slot);
if (!folio)
continue;
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 0929d9fd4ce7..bf6d507578e5 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -317,6 +317,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
struct netfs_io_stream *stream;
struct netfs_group *fgroup; /* TODO: Use this with ceph */
struct netfs_folio *finfo;
+ size_t iter_off = 0;
size_t fsize = folio_size(folio), flen = fsize, foff = 0;
loff_t fpos = folio_pos(folio), i_size;
bool to_eof = false, streamw = false;
@@ -472,7 +473,12 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
if (choose_s < 0)
break;
stream = &wreq->io_streams[choose_s];
- wreq->io_iter.iov_offset = stream->submit_off;
+
+ /* Advance the iterator(s). */
+ if (stream->submit_off > iter_off) {
+ iov_iter_advance(&wreq->io_iter, stream->submit_off - iter_off);
+ iter_off = stream->submit_off;
+ }
atomic64_set(&wreq->issued_to, fpos + stream->submit_off);
stream->submit_extendable_to = fsize - stream->submit_off;
@@ -487,8 +493,8 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
debug = true;
}
- wreq->io_iter.iov_offset = 0;
- iov_iter_advance(&wreq->io_iter, fsize);
+ if (fsize > iter_off)
+ iov_iter_advance(&wreq->io_iter, fsize - iter_off);
atomic64_set(&wreq->issued_to, fpos + fsize);
if (!debug)
@@ -503,6 +509,30 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
}
/*
+ * End the issuing of writes, letting the collector know we're done.
+ */
+static void netfs_end_issue_write(struct netfs_io_request *wreq)
+{
+ bool needs_poke = true;
+
+ smp_wmb(); /* Write subreq lists before ALL_QUEUED. */
+ set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags);
+
+ for (int s = 0; s < NR_IO_STREAMS; s++) {
+ struct netfs_io_stream *stream = &wreq->io_streams[s];
+
+ if (!stream->active)
+ continue;
+ if (!list_empty(&stream->subrequests))
+ needs_poke = false;
+ netfs_issue_write(wreq, stream);
+ }
+
+ if (needs_poke)
+ netfs_wake_write_collector(wreq, false);
+}
+
+/*
* Write some of the pending data back to the server
*/
int netfs_writepages(struct address_space *mapping,
@@ -553,10 +583,7 @@ int netfs_writepages(struct address_space *mapping,
break;
} while ((folio = writeback_iter(mapping, wbc, folio, &error)));
- for (int s = 0; s < NR_IO_STREAMS; s++)
- netfs_issue_write(wreq, &wreq->io_streams[s]);
- smp_wmb(); /* Write lists before ALL_QUEUED. */
- set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags);
+ netfs_end_issue_write(wreq);
mutex_unlock(&ictx->wb_lock);
@@ -644,10 +671,7 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_contr
if (writethrough_cache)
netfs_write_folio(wreq, wbc, writethrough_cache);
- netfs_issue_write(wreq, &wreq->io_streams[0]);
- netfs_issue_write(wreq, &wreq->io_streams[1]);
- smp_wmb(); /* Write lists before ALL_QUEUED. */
- set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags);
+ netfs_end_issue_write(wreq);
mutex_unlock(&ictx->wb_lock);
@@ -693,13 +717,7 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t
break;
}
- netfs_issue_write(wreq, upload);
-
- smp_wmb(); /* Write lists before ALL_QUEUED. */
- set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags);
- if (list_empty(&upload->subrequests))
- netfs_wake_write_collector(wreq, false);
-
+ netfs_end_issue_write(wreq);
_leave(" = %d", error);
return error;
}
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 19bb88c7eebd..ea1ca374cdab 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -792,7 +792,7 @@ nfsd_file_cache_init(void)
}
nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops,
- FSNOTIFY_GROUP_NOFS);
+ 0);
if (IS_ERR(nfsd_file_fsnotify_group)) {
pr_err("nfsd: unable to create fsnotify group: %ld\n",
PTR_ERR(nfsd_file_fsnotify_group));
diff --git a/fs/nls/nls_ucs2_utils.c b/fs/nls/nls_ucs2_utils.c
index d4564b79d7bf..b81c298e4966 100644
--- a/fs/nls/nls_ucs2_utils.c
+++ b/fs/nls/nls_ucs2_utils.c
@@ -13,7 +13,7 @@
#include <linux/fs.h>
#include <linux/module.h>
#include <linux/slab.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "nls_ucs2_utils.h"
MODULE_DESCRIPTION("NLS UCS-2");
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 46440fbb8662..d5dbef7f5c95 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -406,8 +406,7 @@ static int __init dnotify_init(void)
SLAB_PANIC|SLAB_ACCOUNT);
dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT);
- dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops,
- FSNOTIFY_GROUP_NOFS);
+ dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, 0);
if (IS_ERR(dnotify_group))
panic("unable to allocate fsnotify group for dnotify\n");
dnotify_sysctl_init();
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 13454e5fd3fb..9644bc72e457 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1480,7 +1480,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
/* fsnotify_alloc_group takes a ref. Dropped in fanotify_release */
group = fsnotify_alloc_group(&fanotify_fsnotify_ops,
- FSNOTIFY_GROUP_USER | FSNOTIFY_GROUP_NOFS);
+ FSNOTIFY_GROUP_USER);
if (IS_ERR(group)) {
return PTR_ERR(group);
}
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 272c8a1dab3c..82ae8254c068 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -183,8 +183,10 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask,
BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT);
/* Did either inode/sb/mount subscribe for events with parent/name? */
- marks_mask |= fsnotify_parent_needed_mask(inode->i_fsnotify_mask);
- marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask);
+ marks_mask |= fsnotify_parent_needed_mask(
+ READ_ONCE(inode->i_fsnotify_mask));
+ marks_mask |= fsnotify_parent_needed_mask(
+ READ_ONCE(inode->i_sb->s_fsnotify_mask));
marks_mask |= fsnotify_parent_needed_mask(mnt_mask);
/* Did they subscribe for this event with parent/name info? */
@@ -195,8 +197,8 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask,
static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask,
__u32 mask)
{
- __u32 marks_mask = inode->i_fsnotify_mask | mnt_mask |
- inode->i_sb->s_fsnotify_mask;
+ __u32 marks_mask = READ_ONCE(inode->i_fsnotify_mask) | mnt_mask |
+ READ_ONCE(inode->i_sb->s_fsnotify_mask);
return mask & marks_mask & ALL_FSNOTIFY_EVENTS;
}
@@ -213,7 +215,8 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
int data_type)
{
const struct path *path = fsnotify_data_path(data, data_type);
- __u32 mnt_mask = path ? real_mount(path->mnt)->mnt_fsnotify_mask : 0;
+ __u32 mnt_mask = path ?
+ READ_ONCE(real_mount(path->mnt)->mnt_fsnotify_mask) : 0;
struct inode *inode = d_inode(dentry);
struct dentry *parent;
bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED;
@@ -557,13 +560,13 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
(!inode2 || !inode2->i_fsnotify_marks))
return 0;
- marks_mask = sb->s_fsnotify_mask;
+ marks_mask = READ_ONCE(sb->s_fsnotify_mask);
if (mnt)
- marks_mask |= mnt->mnt_fsnotify_mask;
+ marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask);
if (inode)
- marks_mask |= inode->i_fsnotify_mask;
+ marks_mask |= READ_ONCE(inode->i_fsnotify_mask);
if (inode2)
- marks_mask |= inode2->i_fsnotify_mask;
+ marks_mask |= READ_ONCE(inode2->i_fsnotify_mask);
/*
diff --git a/fs/notify/group.c b/fs/notify/group.c
index 1de6631a3925..18446b7b0d49 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -115,7 +115,6 @@ static struct fsnotify_group *__fsnotify_alloc_group(
const struct fsnotify_ops *ops,
int flags, gfp_t gfp)
{
- static struct lock_class_key nofs_marks_lock;
struct fsnotify_group *group;
group = kzalloc(sizeof(struct fsnotify_group), gfp);
@@ -136,16 +135,6 @@ static struct fsnotify_group *__fsnotify_alloc_group(
group->ops = ops;
group->flags = flags;
- /*
- * For most backends, eviction of inode with a mark is not expected,
- * because marks hold a refcount on the inode against eviction.
- *
- * Use a different lockdep class for groups that support evictable
- * inode marks, because with evictable marks, mark_mutex is NOT
- * fs-reclaim safe - the mutex is taken when evicting inodes.
- */
- if (flags & FSNOTIFY_GROUP_NOFS)
- lockdep_set_class(&group->mark_mutex, &nofs_marks_lock);
return group;
}
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index c7e451d5bd51..0794dcaf1e47 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -569,7 +569,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
/* more bits in old than in new? */
int dropped = (old_mask & ~new_mask);
/* more bits in this fsn_mark than the inode's mask? */
- int do_inode = (new_mask & ~inode->i_fsnotify_mask);
+ int do_inode = (new_mask & ~READ_ONCE(inode->i_fsnotify_mask));
/* update the inode with this new fsn_mark */
if (dropped || do_inode)
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 5e170e713088..c45b222cf9c1 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -128,7 +128,7 @@ __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn)
if (WARN_ON(!fsnotify_valid_obj_type(conn->type)))
return 0;
- return *fsnotify_conn_mask_p(conn);
+ return READ_ONCE(*fsnotify_conn_mask_p(conn));
}
static void fsnotify_get_sb_watched_objects(struct super_block *sb)
@@ -245,7 +245,11 @@ static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
!(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF))
want_iref = true;
}
- *fsnotify_conn_mask_p(conn) = new_mask;
+ /*
+ * We use WRITE_ONCE() to prevent silly compiler optimizations from
+ * confusing readers not holding conn->lock with partial updates.
+ */
+ WRITE_ONCE(*fsnotify_conn_mask_p(conn), new_mask);
return fsnotify_update_iref(conn, want_iref);
}
diff --git a/fs/ntfs3/lib/decompress_common.h b/fs/ntfs3/lib/decompress_common.h
index dd7ced000d0e..f0cad9c4a289 100644
--- a/fs/ntfs3/lib/decompress_common.h
+++ b/fs/ntfs3/lib/decompress_common.h
@@ -12,7 +12,7 @@
#include <linux/compiler.h>
#include <linux/types.h>
#include <linux/slab.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
/* "Force inline" macro (not required, but helpful for performance) */
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index e2df7eeadc7a..3d4b883a7660 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -53,7 +53,7 @@
#include <linux/exportfs.h>
#include <linux/hashtable.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "orangefs-dev-proto.h"
diff --git a/fs/pidfs.c b/fs/pidfs.c
index 7ffdc88dfb52..80675b6bf884 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -120,6 +120,7 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
struct nsproxy *nsp __free(put_nsproxy) = NULL;
struct pid *pid = pidfd_pid(file);
struct ns_common *ns_common = NULL;
+ struct pid_namespace *pid_ns;
if (arg)
return -EINVAL;
@@ -202,7 +203,9 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case PIDFD_GET_PID_NAMESPACE:
if (IS_ENABLED(CONFIG_PID_NS)) {
rcu_read_lock();
- ns_common = to_ns_common( get_pid_ns(task_active_pid_ns(task)));
+ pid_ns = task_active_pid_ns(task);
+ if (pid_ns)
+ ns_common = to_ns_common(get_pid_ns(pid_ns));
rcu_read_unlock();
}
break;
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 72c53129c952..d39ee5f6c075 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -12,7 +12,7 @@
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index f0e1f29f20ee..12fc20af8e17 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -11,7 +11,7 @@
#include <linux/sched.h>
#include <linux/bug.h>
#include <linux/workqueue.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/bitops.h>
#include <linux/proc_fs.h>
#include <linux/buffer_head.h>
diff --git a/fs/smb/client/cifsacl.h b/fs/smb/client/cifsacl.h
index 6529478b7f48..31b51a8fc256 100644
--- a/fs/smb/client/cifsacl.h
+++ b/fs/smb/client/cifsacl.h
@@ -55,7 +55,7 @@ struct smb3_sd {
#define ACL_CONTROL_SI 0x0800 /* SACL Auto-Inherited */
#define ACL_CONTROL_DI 0x0400 /* DACL Auto-Inherited */
#define ACL_CONTROL_SC 0x0200 /* SACL computed through inheritance */
-#define ACL_CONTROL_DC 0x0100 /* DACL computed through inheritence */
+#define ACL_CONTROL_DC 0x0100 /* DACL computed through inheritance */
#define ACL_CONTROL_SS 0x0080 /* Create server ACL */
#define ACL_CONTROL_DT 0x0040 /* DACL provided by trusted source */
#define ACL_CONTROL_SD 0x0020 /* SACL defaulted */
diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c
index 2d851f596a72..7a43daacc815 100644
--- a/fs/smb/client/cifsencrypt.c
+++ b/fs/smb/client/cifsencrypt.c
@@ -239,7 +239,7 @@ int cifs_verify_signature(struct smb_rqst *rqst,
cifs_dbg(FYI, "dummy signature received for smb command 0x%x\n",
cifs_pdu->Command);
- /* save off the origiginal signature so we can modify the smb and check
+ /* save off the original signature so we can modify the smb and check
its signature against what the server sent */
memcpy(server_response_sig, cifs_pdu->Signature.SecuritySignature, 8);
@@ -700,6 +700,7 @@ cifs_crypto_secmech_release(struct TCP_Server_Info *server)
cifs_free_hash(&server->secmech.aes_cmac);
cifs_free_hash(&server->secmech.hmacsha256);
cifs_free_hash(&server->secmech.md5);
+ cifs_free_hash(&server->secmech.sha512);
if (!SERVER_IS_CHAN(server)) {
if (server->secmech.enc) {
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 2a2523c93944..000e1ef3beea 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -161,7 +161,7 @@ __u32 cifs_lock_secret;
/*
* Bumps refcount for cifs super block.
- * Note that it should be only called if a referece to VFS super block is
+ * Note that it should be only called if a reference to VFS super block is
* already held, e.g. in open-type syscalls context. Otherwise it can race with
* atomic_dec_and_test in deactivate_locked_super.
*/
@@ -289,7 +289,7 @@ static void cifs_kill_sb(struct super_block *sb)
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
/*
- * We ned to release all dentries for the cached directories
+ * We need to release all dentries for the cached directories
* before we kill the sb.
*/
if (cifs_sb->root) {
@@ -313,8 +313,17 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
struct TCP_Server_Info *server = tcon->ses->server;
unsigned int xid;
int rc = 0;
+ const char *full_path;
+ void *page;
xid = get_xid();
+ page = alloc_dentry_path();
+
+ full_path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
+ goto statfs_out;
+ }
if (le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength) > 0)
buf->f_namelen =
@@ -330,8 +339,10 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_ffree = 0; /* unlimited */
if (server->ops->queryfs)
- rc = server->ops->queryfs(xid, tcon, cifs_sb, buf);
+ rc = server->ops->queryfs(xid, tcon, full_path, cifs_sb, buf);
+statfs_out:
+ free_dentry_path(page);
free_xid(xid);
return rc;
}
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 315aac5dec05..5041b1ffc244 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -180,6 +180,7 @@ struct session_key {
struct cifs_secmech {
struct shash_desc *md5; /* md5 hash function, for CIFS/SMB1 signatures */
struct shash_desc *hmacsha256; /* hmac-sha256 hash function, for SMB2 signatures */
+ struct shash_desc *sha512; /* sha512 hash function, for SMB3.1.1 preauth hash */
struct shash_desc *aes_cmac; /* block-cipher based MAC function, for SMB3 signatures */
struct crypto_aead *enc; /* smb3 encryption AEAD TFM (AES-CCM and AES-GCM) */
@@ -480,7 +481,7 @@ struct smb_version_operations {
__u16 net_fid, struct cifsInodeInfo *cifs_inode);
/* query remote filesystem */
int (*queryfs)(const unsigned int, struct cifs_tcon *,
- struct cifs_sb_info *, struct kstatfs *);
+ const char *, struct cifs_sb_info *, struct kstatfs *);
/* send mandatory brlock to the server */
int (*mand_lock)(const unsigned int, struct cifsFileInfo *, __u64,
__u64, __u32, int, int, bool);
@@ -774,7 +775,7 @@ struct TCP_Server_Info {
} compression;
__u16 signing_algorithm;
__le16 cipher_type;
- /* save initital negprot hash */
+ /* save initial negprot hash */
__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
bool signing_negotiated; /* true if valid signing context rcvd from server */
bool posix_ext_supported;
diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h
index c3b6263060b0..ee78bb6741d6 100644
--- a/fs/smb/client/cifspdu.h
+++ b/fs/smb/client/cifspdu.h
@@ -10,7 +10,7 @@
#define _CIFSPDU_H
#include <net/sock.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "../common/smbfsctl.h"
#define CIFS_PROT 0
@@ -781,7 +781,7 @@ typedef struct smb_com_logoff_andx_rsp {
__u16 ByteCount;
} __attribute__((packed)) LOGOFF_ANDX_RSP;
-typedef union smb_com_tree_disconnect { /* as an altetnative can use flag on
+typedef union smb_com_tree_disconnect { /* as an alternative can use flag on
tree_connect PDU to effect disconnect */
/* tdis is probably simplest SMB PDU */
struct {
@@ -2406,7 +2406,7 @@ struct cifs_posix_ace { /* access control entry (ACE) */
__le64 cifs_uid; /* or gid */
} __attribute__((packed));
-struct cifs_posix_acl { /* access conrol list (ACL) */
+struct cifs_posix_acl { /* access control list (ACL) */
__le16 version;
__le16 access_entry_count; /* access ACL - count of entries */
__le16 default_entry_count; /* default ACL - count of entries */
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 131f20b91c3e..c6f15dbe860a 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1215,7 +1215,7 @@ openRetry:
req->CreateDisposition = cpu_to_le32(disposition);
req->CreateOptions = cpu_to_le32(create_options & CREATE_OPTIONS_MASK);
- /* BB Expirement with various impersonation levels and verify */
+ /* BB Experiment with various impersonation levels and verify */
req->ImpersonationLevel = cpu_to_le32(SECURITY_IMPERSONATION);
req->SecurityFlags = SECURITY_CONTEXT_TRACKING|SECURITY_EFFECTIVE_ONLY;
@@ -3018,7 +3018,7 @@ static void cifs_init_ace(struct cifs_posix_ace *cifs_ace,
/**
* posix_acl_to_cifs - convert ACLs from POSIX ACL to cifs format
- * @parm_data: ACLs in cifs format to conver to
+ * @parm_data: ACLs in cifs format to convert to
* @acl: ACLs in POSIX ACL format to convert from
* @acl_type: the type of POSIX ACLs stored in @acl
*
@@ -3995,7 +3995,7 @@ findFirstRetry:
name_len =
cifsConvertToUTF16((__le16 *) pSMB->FileName, searchName,
PATH_MAX, nls_codepage, remap);
- /* We can not add the asterik earlier in case
+ /* We can not add the asterisk earlier in case
it got remapped to 0xF03A as if it were part of the
directory name instead of a wildcard */
name_len *= 2;
diff --git a/fs/smb/client/compress/lz77.c b/fs/smb/client/compress/lz77.c
index 553e253ada29..96e8a8057a77 100644
--- a/fs/smb/client/compress/lz77.c
+++ b/fs/smb/client/compress/lz77.c
@@ -9,7 +9,7 @@
#include <linux/slab.h>
#include <linux/sizes.h>
#include <linux/count_zeros.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "lz77.h"
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 78b59c4ef3ce..a58a3333ecc3 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -2502,7 +2502,7 @@ refind_writable:
}
}
}
- /* couldn't find useable FH with same pid, try any available */
+ /* couldn't find usable FH with same pid, try any available */
if (!any_available) {
any_available = true;
goto refind_writable;
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index 69f9d938b336..890d6d9d4a59 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -260,7 +260,7 @@ struct smb3_fs_context {
unsigned int min_offload;
unsigned int retrans;
bool sockopt_tcp_nodelay:1;
- /* attribute cache timemout for files and directories in jiffies */
+ /* attribute cache timeout for files and directories in jiffies */
unsigned long acregmax;
unsigned long acdirmax;
/* timeout for deferred close of files in jiffies */
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 647f9bedd9fc..eff3f57235ee 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -629,10 +629,16 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path,
&symlink_len_utf16,
&symlink_buf_utf16,
&buf_type);
+ /*
+ * Check that read buffer has valid length and does not
+ * contain UTF-16 null codepoint (via UniStrnlen() call)
+ * because Linux cannot process symlink with null byte.
+ */
if ((rc == 0) &&
(symlink_len_utf16 > 0) &&
(symlink_len_utf16 < fattr->cf_eof-8 + 1) &&
- (symlink_len_utf16 % 2 == 0)) {
+ (symlink_len_utf16 % 2 == 0) &&
+ (UniStrnlen((wchar_t *)symlink_buf_utf16, symlink_len_utf16/2) == symlink_len_utf16/2)) {
fattr->cf_symlink_target =
cifs_strndup_from_utf16(symlink_buf_utf16,
symlink_len_utf16,
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index 054f10ebf65a..4373dd64b66d 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -254,7 +254,7 @@ free_rsp_buf(int resp_buftype, void *rsp)
}
/* NB: MID can not be set if treeCon not passed in, in that
- case it is responsbility of caller to set the mid */
+ case it is responsibility of caller to set the mid */
void
header_assemble(struct smb_hdr *buffer, char smb_command /* command */ ,
const struct cifs_tcon *treeCon, int word_count
diff --git a/fs/smb/client/netmisc.c b/fs/smb/client/netmisc.c
index 1b52e6ac431c..2a8d71221e5e 100644
--- a/fs/smb/client/netmisc.c
+++ b/fs/smb/client/netmisc.c
@@ -1003,7 +1003,7 @@ struct timespec64 cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
year is 2**7, the last year is 1980+127, which means we need only
consider 2 special case years, ie the years 2000 and 2100, and only
adjust for the lack of leap year for the year 2100, as 2000 was a
- leap year (divisable by 400) */
+ leap year (divisible by 400) */
if (year >= 120) /* the year 2100 */
days = days - 1; /* do not count leap year for the year 2100 */
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index ebe1cb30e18e..b3a8f9c6fcff 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -553,7 +553,7 @@ static void cifs_fill_dirent_std(struct cifs_dirent *de,
const FIND_FILE_STANDARD_INFO *info)
{
de->name = &info->FileName[0];
- /* one byte length, no endianess conversion */
+ /* one byte length, no endianness conversion */
de->namelen = info->FileNameLength;
de->resume_key = info->ResumeKey;
}
@@ -815,7 +815,7 @@ static bool emit_cached_dirents(struct cached_dirents *cde,
* However, this sequence of ->pos values may have holes
* in it, for example dot-dirs returned from the server
* are suppressed.
- * Handle this bu forcing ctx->pos to be the same as the
+ * Handle this by forcing ctx->pos to be the same as the
* ->pos of the current dirent we emit from the cache.
* This means that when we emit these entries from the cache
* we now emit them with the same ->pos value as in the
diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index 3b48a093cfb1..c848b5e88d32 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -320,22 +320,51 @@ static int parse_reparse_posix(struct reparse_posix_data *buf,
unsigned int len;
u64 type;
+ len = le16_to_cpu(buf->ReparseDataLength);
+ if (len < sizeof(buf->InodeType)) {
+ cifs_dbg(VFS, "srv returned malformed nfs buffer\n");
+ return -EIO;
+ }
+
+ len -= sizeof(buf->InodeType);
+
switch ((type = le64_to_cpu(buf->InodeType))) {
case NFS_SPECFILE_LNK:
- len = le16_to_cpu(buf->ReparseDataLength);
+ if (len == 0 || (len % 2)) {
+ cifs_dbg(VFS, "srv returned malformed nfs symlink buffer\n");
+ return -EIO;
+ }
+ /*
+ * Check that buffer does not contain UTF-16 null codepoint
+ * because Linux cannot process symlink with null byte.
+ */
+ if (UniStrnlen((wchar_t *)buf->DataBuffer, len/2) != len/2) {
+ cifs_dbg(VFS, "srv returned null byte in nfs symlink target location\n");
+ return -EIO;
+ }
data->symlink_target = cifs_strndup_from_utf16(buf->DataBuffer,
len, true,
cifs_sb->local_nls);
if (!data->symlink_target)
return -ENOMEM;
- convert_delimiter(data->symlink_target, '/');
cifs_dbg(FYI, "%s: target path: %s\n",
__func__, data->symlink_target);
break;
case NFS_SPECFILE_CHR:
case NFS_SPECFILE_BLK:
+ /* DataBuffer for block and char devices contains two 32-bit numbers */
+ if (len != 8) {
+ cifs_dbg(VFS, "srv returned malformed nfs buffer for type: 0x%llx\n", type);
+ return -EIO;
+ }
+ break;
case NFS_SPECFILE_FIFO:
case NFS_SPECFILE_SOCK:
+ /* DataBuffer for fifos and sockets is empty */
+ if (len != 0) {
+ cifs_dbg(VFS, "srv returned malformed nfs buffer for type: 0x%llx\n", type);
+ return -EIO;
+ }
break;
default:
cifs_dbg(VFS, "%s: unhandled inode type: 0x%llx\n",
@@ -482,12 +511,18 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
u32 tag = data->reparse.tag;
if (tag == IO_REPARSE_TAG_NFS && buf) {
+ if (le16_to_cpu(buf->ReparseDataLength) < sizeof(buf->InodeType))
+ return false;
switch (le64_to_cpu(buf->InodeType)) {
case NFS_SPECFILE_CHR:
+ if (le16_to_cpu(buf->ReparseDataLength) != sizeof(buf->InodeType) + 8)
+ return false;
fattr->cf_mode |= S_IFCHR;
fattr->cf_rdev = reparse_mkdev(buf->DataBuffer);
break;
case NFS_SPECFILE_BLK:
+ if (le16_to_cpu(buf->ReparseDataLength) != sizeof(buf->InodeType) + 8)
+ return false;
fattr->cf_mode |= S_IFBLK;
fattr->cf_rdev = reparse_mkdev(buf->DataBuffer);
break;
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index 03c0b484a4b5..3216f786908f 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -624,7 +624,7 @@ cifs_ses_add_channel(struct cifs_ses *ses,
* to sign packets before we generate the channel signing key
* (we sign with the session key)
*/
- rc = smb3_crypto_shash_allocate(chan->server);
+ rc = smb311_crypto_shash_allocate(chan->server);
if (rc) {
cifs_dbg(VFS, "%s: crypto alloc failed\n", __func__);
mutex_unlock(&ses->session_mutex);
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index e03c91a49650..9a6ece66c4d3 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -909,7 +909,7 @@ cifs_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid,
static int
cifs_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
- struct cifs_sb_info *cifs_sb, struct kstatfs *buf)
+ const char *path, struct cifs_sb_info *cifs_sb, struct kstatfs *buf)
{
int rc = -EOPNOTSUPP;
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index b992117377e9..4e9e225520a6 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -1205,9 +1205,12 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data,
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct cifsFileInfo *cfile;
struct inode *new = NULL;
+ int out_buftype[4] = {};
+ struct kvec out_iov[4] = {};
struct kvec in_iov[2];
int cmds[2];
int rc;
+ int i;
oparms = CIFS_OPARMS(cifs_sb, tcon, full_path,
SYNCHRONIZE | DELETE |
@@ -1228,7 +1231,7 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data,
cmds[1] = SMB2_OP_POSIX_QUERY_INFO;
cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms,
- in_iov, cmds, 2, cfile, NULL, NULL, NULL);
+ in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL);
if (!rc) {
rc = smb311_posix_get_inode_info(&new, full_path,
data, sb, xid);
@@ -1237,12 +1240,29 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data,
cmds[1] = SMB2_OP_QUERY_INFO;
cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms,
- in_iov, cmds, 2, cfile, NULL, NULL, NULL);
+ in_iov, cmds, 2, cfile, out_iov, out_buftype, NULL);
if (!rc) {
rc = cifs_get_inode_info(&new, full_path,
data, sb, xid, NULL);
}
}
+
+
+ /*
+ * If CREATE was successful but SMB2_OP_SET_REPARSE failed then
+ * remove the intermediate object created by CREATE. Otherwise
+ * empty object stay on the server when reparse call failed.
+ */
+ if (rc &&
+ out_iov[0].iov_base != NULL && out_buftype[0] != CIFS_NO_BUFFER &&
+ ((struct smb2_hdr *)out_iov[0].iov_base)->Status == STATUS_SUCCESS &&
+ (out_iov[1].iov_base == NULL || out_buftype[1] == CIFS_NO_BUFFER ||
+ ((struct smb2_hdr *)out_iov[1].iov_base)->Status != STATUS_SUCCESS))
+ smb2_unlink(xid, tcon, full_path, cifs_sb, NULL);
+
+ for (i = 0; i < ARRAY_SIZE(out_buftype); i++)
+ free_rsp_buf(out_buftype[i], out_iov[i].iov_base);
+
return rc ? ERR_PTR(rc) : new;
}
diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c
index bdeb12ff53e3..f3c4b70b77b9 100644
--- a/fs/smb/client/smb2misc.c
+++ b/fs/smb/client/smb2misc.c
@@ -906,41 +906,41 @@ smb311_update_preauth_hash(struct cifs_ses *ses, struct TCP_Server_Info *server,
|| (hdr->Status !=
cpu_to_le32(NT_STATUS_MORE_PROCESSING_REQUIRED))))
return 0;
+
ok:
- rc = cifs_alloc_hash("sha512", &sha512);
- if (rc) {
- cifs_dbg(VFS, "%s: Could not allocate SHA512 shash, rc=%d\n", __func__, rc);
+ rc = smb311_crypto_shash_allocate(server);
+ if (rc)
return rc;
- }
+ sha512 = server->secmech.sha512;
rc = crypto_shash_init(sha512);
if (rc) {
- cifs_dbg(VFS, "%s: Could not init SHA512 shash, rc=%d\n", __func__, rc);
- goto err_free;
+ cifs_dbg(VFS, "%s: Could not init sha512 shash\n", __func__);
+ return rc;
}
rc = crypto_shash_update(sha512, ses->preauth_sha_hash,
SMB2_PREAUTH_HASH_SIZE);
if (rc) {
- cifs_dbg(VFS, "%s: Could not update SHA512 shash, rc=%d\n", __func__, rc);
- goto err_free;
+ cifs_dbg(VFS, "%s: Could not update sha512 shash\n", __func__);
+ return rc;
}
for (i = 0; i < nvec; i++) {
rc = crypto_shash_update(sha512, iov[i].iov_base, iov[i].iov_len);
if (rc) {
- cifs_dbg(VFS, "%s: Could not update SHA512 shash, rc=%d\n", __func__, rc);
- goto err_free;
+ cifs_dbg(VFS, "%s: Could not update sha512 shash\n",
+ __func__);
+ return rc;
}
}
rc = crypto_shash_final(sha512, ses->preauth_sha_hash);
if (rc) {
- cifs_dbg(VFS, "%s: Could not finalize SHA12 shash, rc=%d\n", __func__, rc);
- goto err_free;
+ cifs_dbg(VFS, "%s: Could not finalize sha512 shash\n",
+ __func__);
+ return rc;
}
-err_free:
- cifs_free_hash(&sha512);
return 0;
}
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 177173072bfa..6b385fce3f2a 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -2177,7 +2177,7 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
NULL, 0 /* no input data */, max_response_size,
(char **)&retbuf,
&ret_data_len);
- cifs_dbg(FYI, "enum snaphots ioctl returned %d and ret buflen is %d\n",
+ cifs_dbg(FYI, "enum snapshots ioctl returned %d and ret buflen is %d\n",
rc, ret_data_len);
if (rc)
return rc;
@@ -2838,7 +2838,7 @@ out_free_path:
static int
smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
- struct cifs_sb_info *cifs_sb, struct kstatfs *buf)
+ const char *path, struct cifs_sb_info *cifs_sb, struct kstatfs *buf)
{
struct smb2_query_info_rsp *rsp;
struct smb2_fs_full_size_info *info = NULL;
@@ -2847,7 +2847,7 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
int rc;
- rc = smb2_query_info_compound(xid, tcon, "",
+ rc = smb2_query_info_compound(xid, tcon, path,
FILE_READ_ATTRIBUTES,
FS_FULL_SIZE_INFORMATION,
SMB2_O_INFO_FILESYSTEM,
@@ -2875,28 +2875,33 @@ qfs_exit:
static int
smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
- struct cifs_sb_info *cifs_sb, struct kstatfs *buf)
+ const char *path, struct cifs_sb_info *cifs_sb, struct kstatfs *buf)
{
int rc;
- __le16 srch_path = 0; /* Null - open root of share */
+ __le16 *utf16_path = NULL;
u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
struct cifs_open_parms oparms;
struct cifs_fid fid;
if (!tcon->posix_extensions)
- return smb2_queryfs(xid, tcon, cifs_sb, buf);
+ return smb2_queryfs(xid, tcon, path, cifs_sb, buf);
oparms = (struct cifs_open_parms) {
.tcon = tcon,
- .path = "",
+ .path = path,
.desired_access = FILE_READ_ATTRIBUTES,
.disposition = FILE_OPEN,
.create_options = cifs_create_options(cifs_sb, 0),
.fid = &fid,
};
- rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL,
+ utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
+ if (utf16_path == NULL)
+ return -ENOMEM;
+
+ rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL,
NULL, NULL);
+ kfree(utf16_path);
if (rc)
return rc;
@@ -3583,7 +3588,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
/*
* At this point, we are trying to fallocate an internal
* regions of a sparse file. Since smb2 does not have a
- * fallocate command we have two otions on how to emulate this.
+ * fallocate command we have two options on how to emulate this.
* We can either turn the entire file to become non-sparse
* which we only do if the fallocate is for virtually
* the whole file, or we can overwrite the region with zeroes
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 02828b9c3cb3..b2f16a7b696d 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -2986,7 +2986,7 @@ replay_again:
SMB2_close(xid, tcon, rsp->PersistentFileId, rsp->VolatileFileId);
- /* Eventually save off posix specific response info and timestaps */
+ /* Eventually save off posix specific response info and timestamps */
err_free_rsp_buf:
free_rsp_buf(resp_buftype, rsp);
@@ -4581,7 +4581,7 @@ smb2_readv_callback(struct mid_q_entry *mid)
}
#ifdef CONFIG_CIFS_SMB_DIRECT
/*
- * If this rdata has a memmory registered, the MR can be freed
+ * If this rdata has a memory registered, the MR can be freed
* MR needs to be freed as soon as I/O finishes to prevent deadlock
* because they have limited number and are used for future I/Os
*/
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 56a896ff7cd9..c7e1b149877a 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -291,7 +291,7 @@ extern int smb2_validate_and_copy_iov(unsigned int offset,
extern void smb2_copy_fs_info_to_kstatfs(
struct smb2_fs_full_size_info *pfs_inf,
struct kstatfs *kst);
-extern int smb3_crypto_shash_allocate(struct TCP_Server_Info *server);
+extern int smb311_crypto_shash_allocate(struct TCP_Server_Info *server);
extern int smb311_update_preauth_hash(struct cifs_ses *ses,
struct TCP_Server_Info *server,
struct kvec *iov, int nvec);
diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c
index f7e04c40d22e..b486b14bb330 100644
--- a/fs/smb/client/smb2transport.c
+++ b/fs/smb/client/smb2transport.c
@@ -26,7 +26,8 @@
#include "../common/smb2status.h"
#include "smb2glob.h"
-int smb3_crypto_shash_allocate(struct TCP_Server_Info *server)
+static int
+smb3_crypto_shash_allocate(struct TCP_Server_Info *server)
{
struct cifs_secmech *p = &server->secmech;
int rc;
@@ -45,6 +46,33 @@ err:
return rc;
}
+int
+smb311_crypto_shash_allocate(struct TCP_Server_Info *server)
+{
+ struct cifs_secmech *p = &server->secmech;
+ int rc = 0;
+
+ rc = cifs_alloc_hash("hmac(sha256)", &p->hmacsha256);
+ if (rc)
+ return rc;
+
+ rc = cifs_alloc_hash("cmac(aes)", &p->aes_cmac);
+ if (rc)
+ goto err;
+
+ rc = cifs_alloc_hash("sha512", &p->sha512);
+ if (rc)
+ goto err;
+
+ return 0;
+
+err:
+ cifs_free_hash(&p->aes_cmac);
+ cifs_free_hash(&p->hmacsha256);
+ return rc;
+}
+
+
static
int smb2_get_sign_key(__u64 ses_id, struct TCP_Server_Info *server, u8 *key)
{
@@ -668,7 +696,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
shdr->Command);
/*
- * Save off the origiginal signature so we can modify the smb and check
+ * Save off the original signature so we can modify the smb and check
* our calculated signature against what the server sent.
*/
memcpy(server_response_sig, shdr->Signature, SMB2_SIGNATURE_SIZE);
diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
index 0c64b37e2660..b0b7254661e9 100644
--- a/fs/smb/client/smbdirect.c
+++ b/fs/smb/client/smbdirect.c
@@ -219,7 +219,7 @@ static int smbd_conn_upcall(
case RDMA_CM_EVENT_DEVICE_REMOVAL:
case RDMA_CM_EVENT_DISCONNECTED:
- /* This happenes when we fail the negotiation */
+ /* This happens when we fail the negotiation */
if (info->transport_status == SMBD_NEGOTIATE_FAILED) {
info->transport_status = SMBD_DISCONNECTED;
wake_up(&info->conn_wait);
@@ -1344,7 +1344,7 @@ void smbd_destroy(struct TCP_Server_Info *server)
* are not locked by srv_mutex. It is possible some processes are
* blocked on transport srv_mutex while holding memory registration.
* Release the transport srv_mutex to allow them to hit the failure
- * path when sending data, and then release memory registartions.
+ * path when sending data, and then release memory registrations.
*/
log_rdma_event(INFO, "freeing mr list\n");
wake_up_interruptible_all(&info->wait_mr);
diff --git a/fs/smb/client/smbdirect.h b/fs/smb/client/smbdirect.h
index 83f239f376f0..c08e3665150d 100644
--- a/fs/smb/client/smbdirect.h
+++ b/fs/smb/client/smbdirect.h
@@ -111,7 +111,7 @@ struct smbd_connection {
/* Used by transport to wait until all MRs are returned */
wait_queue_head_t wait_for_mr_cleanup;
- /* Activity accoutning */
+ /* Activity accounting */
atomic_t send_pending;
wait_queue_head_t wait_send_pending;
wait_queue_head_t wait_post_send;
diff --git a/fs/smb/common/smbfsctl.h b/fs/smb/common/smbfsctl.h
index a94d658b88e8..4b379e84c46b 100644
--- a/fs/smb/common/smbfsctl.h
+++ b/fs/smb/common/smbfsctl.h
@@ -140,20 +140,21 @@
/* Used by the DFS filter See MS-DFSC */
#define IO_REPARSE_TAG_DFSR 0x80000012
#define IO_REPARSE_TAG_FILTER_MANAGER 0x8000000B
-/* See section MS-FSCC 2.1.2.4 */
+/* Native SMB symlinks since Windows Vista, see MS-FSCC 2.1.2.4 */
#define IO_REPARSE_TAG_SYMLINK 0xA000000C
#define IO_REPARSE_TAG_DEDUP 0x80000013
#define IO_REPARSE_APPXSTREAM 0xC0000014
-/* NFS symlinks, Win 8/SMB3 and later */
+/* NFS special files used by Windows NFS server since Windows Server 2012, see MS-FSCC 2.1.2.6 */
#define IO_REPARSE_TAG_NFS 0x80000014
/*
* AzureFileSync - see
* https://docs.microsoft.com/en-us/azure/storage/files/storage-sync-cloud-tiering
*/
#define IO_REPARSE_TAG_AZ_FILE_SYNC 0x8000001e
+/* Native Win32 AF_UNIX sockets since Windows 10 April 2018 Update, used also by WSL */
+#define IO_REPARSE_TAG_AF_UNIX 0x80000023
/* WSL reparse tags */
#define IO_REPARSE_TAG_LX_SYMLINK 0xA000001D
-#define IO_REPARSE_TAG_AF_UNIX 0x80000023
#define IO_REPARSE_TAG_LX_FIFO 0x80000024
#define IO_REPARSE_TAG_LX_CHR 0x80000025
#define IO_REPARSE_TAG_LX_BLK 0x80000026
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 7460089c186f..797b0f24097b 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -4883,7 +4883,7 @@ static void get_file_alternate_info(struct ksmbd_work *work,
spin_unlock(&dentry->d_lock);
file_info->FileNameLength = cpu_to_le32(conv_len);
rsp->OutputBufferLength =
- cpu_to_le32(sizeof(struct smb2_file_alt_name_info) + conv_len);
+ cpu_to_le32(struct_size(file_info, FileName, conv_len));
}
static int get_file_stream_info(struct ksmbd_work *work,
@@ -7562,7 +7562,6 @@ static int fsctl_copychunk(struct ksmbd_work *work,
ci_rsp->TotalBytesWritten =
cpu_to_le32(ksmbd_server_side_copy_max_total_size());
- chunks = (struct srv_copychunk *)&ci_req->Chunks[0];
chunk_count = le32_to_cpu(ci_req->ChunkCount);
if (chunk_count == 0)
goto out;
@@ -7570,12 +7569,12 @@ static int fsctl_copychunk(struct ksmbd_work *work,
/* verify the SRV_COPYCHUNK_COPY packet */
if (chunk_count > ksmbd_server_side_copy_max_chunk_count() ||
- input_count < offsetof(struct copychunk_ioctl_req, Chunks) +
- chunk_count * sizeof(struct srv_copychunk)) {
+ input_count < struct_size(ci_req, Chunks, chunk_count)) {
rsp->hdr.Status = STATUS_INVALID_PARAMETER;
return -EINVAL;
}
+ chunks = &ci_req->Chunks[0];
for (i = 0; i < chunk_count; i++) {
if (le32_to_cpu(chunks[i].Length) == 0 ||
le32_to_cpu(chunks[i].Length) > ksmbd_server_side_copy_max_chunk_size())
diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h
index 73aff20e22d0..649dacf7e8c4 100644
--- a/fs/smb/server/smb2pdu.h
+++ b/fs/smb/server/smb2pdu.h
@@ -190,13 +190,6 @@ struct resume_key_ioctl_rsp {
__u8 Context[4]; /* ignored, Windows sets to 4 bytes of zero */
} __packed;
-struct copychunk_ioctl_req {
- __le64 ResumeKey[3];
- __le32 ChunkCount;
- __le32 Reserved;
- __u8 Chunks[]; /* array of srv_copychunk */
-} __packed;
-
struct srv_copychunk {
__le64 SourceOffset;
__le64 TargetOffset;
@@ -204,6 +197,13 @@ struct srv_copychunk {
__le32 Reserved;
} __packed;
+struct copychunk_ioctl_req {
+ __le64 ResumeKey[3];
+ __le32 ChunkCount;
+ __le32 Reserved;
+ struct srv_copychunk Chunks[] __counted_by_le(ChunkCount);
+} __packed;
+
struct copychunk_ioctl_rsp {
__le32 ChunksWritten;
__le32 ChunkBytesWritten;
diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index 44c87e300c16..17c76713c6d0 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -1405,8 +1405,8 @@ static int smb_direct_rdma_xmit(struct smb_direct_transport *t,
/* build rdma_rw_ctx for each descriptor */
desc_buf = buf;
for (i = 0; i < desc_num; i++) {
- msg = kzalloc(offsetof(struct smb_direct_rdma_rw_msg, sg_list) +
- sizeof(struct scatterlist) * SG_CHUNK_SIZE, GFP_KERNEL);
+ msg = kzalloc(struct_size(msg, sg_list, SG_CHUNK_SIZE),
+ GFP_KERNEL);
if (!msg) {
ret = -ENOMEM;
goto out;
diff --git a/fs/smb/server/unicode.c b/fs/smb/server/unicode.c
index 43ed29ee44ea..217106ff7b82 100644
--- a/fs/smb/server/unicode.c
+++ b/fs/smb/server/unicode.c
@@ -8,7 +8,7 @@
*/
#include <linux/fs.h>
#include <linux/slab.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "glob.h"
#include "unicode.h"
#include "smb_common.h"
diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
index d8fc11765d61..807c493ed0cd 100644
--- a/fs/udf/balloc.c
+++ b/fs/udf/balloc.c
@@ -370,6 +370,7 @@ static void udf_table_free_blocks(struct super_block *sb,
struct extent_position oepos, epos;
int8_t etype;
struct udf_inode_info *iinfo;
+ int ret = 0;
mutex_lock(&sbi->s_alloc_mutex);
iinfo = UDF_I(table);
@@ -383,8 +384,12 @@ static void udf_table_free_blocks(struct super_block *sb,
epos.block = oepos.block = iinfo->i_location;
epos.bh = oepos.bh = NULL;
- while (count &&
- (etype = udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1) {
+ while (count) {
+ ret = udf_next_aext(table, &epos, &eloc, &elen, &etype, 1);
+ if (ret < 0)
+ goto error_return;
+ if (ret == 0)
+ break;
if (((eloc.logicalBlockNum +
(elen >> sb->s_blocksize_bits)) == start)) {
if ((0x3FFFFFFF - elen) <
@@ -459,11 +464,8 @@ static void udf_table_free_blocks(struct super_block *sb,
adsize = sizeof(struct short_ad);
else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
adsize = sizeof(struct long_ad);
- else {
- brelse(oepos.bh);
- brelse(epos.bh);
+ else
goto error_return;
- }
if (epos.offset + (2 * adsize) > sb->s_blocksize) {
/* Steal a block from the extent being free'd */
@@ -479,10 +481,10 @@ static void udf_table_free_blocks(struct super_block *sb,
__udf_add_aext(table, &epos, &eloc, elen, 1);
}
+error_return:
brelse(epos.bh);
brelse(oepos.bh);
-error_return:
mutex_unlock(&sbi->s_alloc_mutex);
return;
}
@@ -498,6 +500,7 @@ static int udf_table_prealloc_blocks(struct super_block *sb,
struct extent_position epos;
int8_t etype = -1;
struct udf_inode_info *iinfo;
+ int ret = 0;
if (first_block >= sbi->s_partmaps[partition].s_partition_len)
return 0;
@@ -516,11 +519,14 @@ static int udf_table_prealloc_blocks(struct super_block *sb,
epos.bh = NULL;
eloc.logicalBlockNum = 0xFFFFFFFF;
- while (first_block != eloc.logicalBlockNum &&
- (etype = udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1) {
+ while (first_block != eloc.logicalBlockNum) {
+ ret = udf_next_aext(table, &epos, &eloc, &elen, &etype, 1);
+ if (ret < 0)
+ goto err_out;
+ if (ret == 0)
+ break;
udf_debug("eloc=%u, elen=%u, first_block=%u\n",
eloc.logicalBlockNum, elen, first_block);
- ; /* empty loop body */
}
if (first_block == eloc.logicalBlockNum) {
@@ -539,6 +545,7 @@ static int udf_table_prealloc_blocks(struct super_block *sb,
alloc_count = 0;
}
+err_out:
brelse(epos.bh);
if (alloc_count)
@@ -560,6 +567,7 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb,
struct extent_position epos, goal_epos;
int8_t etype;
struct udf_inode_info *iinfo = UDF_I(table);
+ int ret = 0;
*err = -ENOSPC;
@@ -583,8 +591,10 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb,
epos.block = iinfo->i_location;
epos.bh = goal_epos.bh = NULL;
- while (spread &&
- (etype = udf_next_aext(table, &epos, &eloc, &elen, 1)) != -1) {
+ while (spread) {
+ ret = udf_next_aext(table, &epos, &eloc, &elen, &etype, 1);
+ if (ret <= 0)
+ break;
if (goal >= eloc.logicalBlockNum) {
if (goal < eloc.logicalBlockNum +
(elen >> sb->s_blocksize_bits))
@@ -612,9 +622,11 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb,
brelse(epos.bh);
- if (spread == 0xFFFFFFFF) {
+ if (ret < 0 || spread == 0xFFFFFFFF) {
brelse(goal_epos.bh);
mutex_unlock(&sbi->s_alloc_mutex);
+ if (ret < 0)
+ *err = ret;
return 0;
}
diff --git a/fs/udf/directory.c b/fs/udf/directory.c
index 93153665eb37..632453aa3893 100644
--- a/fs/udf/directory.c
+++ b/fs/udf/directory.c
@@ -166,13 +166,19 @@ static struct buffer_head *udf_fiiter_bread_blk(struct udf_fileident_iter *iter)
*/
static int udf_fiiter_advance_blk(struct udf_fileident_iter *iter)
{
+ int8_t etype = -1;
+ int err = 0;
+
iter->loffset++;
if (iter->loffset < DIV_ROUND_UP(iter->elen, 1<<iter->dir->i_blkbits))
return 0;
iter->loffset = 0;
- if (udf_next_aext(iter->dir, &iter->epos, &iter->eloc, &iter->elen, 1)
- != (EXT_RECORDED_ALLOCATED >> 30)) {
+ err = udf_next_aext(iter->dir, &iter->epos, &iter->eloc,
+ &iter->elen, &etype, 1);
+ if (err < 0)
+ return err;
+ else if (err == 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) {
if (iter->pos == iter->dir->i_size) {
iter->elen = 0;
return 0;
@@ -240,6 +246,7 @@ int udf_fiiter_init(struct udf_fileident_iter *iter, struct inode *dir,
{
struct udf_inode_info *iinfo = UDF_I(dir);
int err = 0;
+ int8_t etype;
iter->dir = dir;
iter->bh[0] = iter->bh[1] = NULL;
@@ -259,9 +266,9 @@ int udf_fiiter_init(struct udf_fileident_iter *iter, struct inode *dir,
goto out;
}
- if (inode_bmap(dir, iter->pos >> dir->i_blkbits, &iter->epos,
- &iter->eloc, &iter->elen, &iter->loffset) !=
- (EXT_RECORDED_ALLOCATED >> 30)) {
+ err = inode_bmap(dir, iter->pos >> dir->i_blkbits, &iter->epos,
+ &iter->eloc, &iter->elen, &iter->loffset, &etype);
+ if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) {
if (pos == dir->i_size)
return 0;
udf_err(dir->i_sb,
@@ -457,6 +464,7 @@ int udf_fiiter_append_blk(struct udf_fileident_iter *iter)
sector_t block;
uint32_t old_elen = iter->elen;
int err;
+ int8_t etype;
if (WARN_ON_ONCE(iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB))
return -EINVAL;
@@ -471,8 +479,9 @@ int udf_fiiter_append_blk(struct udf_fileident_iter *iter)
udf_fiiter_update_elen(iter, old_elen);
return err;
}
- if (inode_bmap(iter->dir, block, &iter->epos, &iter->eloc, &iter->elen,
- &iter->loffset) != (EXT_RECORDED_ALLOCATED >> 30)) {
+ err = inode_bmap(iter->dir, block, &iter->epos, &iter->eloc, &iter->elen,
+ &iter->loffset, &etype);
+ if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30)) {
udf_err(iter->dir->i_sb,
"block %llu not allocated in directory (ino %lu)\n",
(unsigned long long)block, iter->dir->i_ino);
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index eaee57b91c6c..70c907fe8af9 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -404,7 +404,7 @@ struct udf_map_rq {
static int udf_map_block(struct inode *inode, struct udf_map_rq *map)
{
- int err;
+ int ret;
struct udf_inode_info *iinfo = UDF_I(inode);
if (WARN_ON_ONCE(iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB))
@@ -416,18 +416,24 @@ static int udf_map_block(struct inode *inode, struct udf_map_rq *map)
uint32_t elen;
sector_t offset;
struct extent_position epos = {};
+ int8_t etype;
down_read(&iinfo->i_data_sem);
- if (inode_bmap(inode, map->lblk, &epos, &eloc, &elen, &offset)
- == (EXT_RECORDED_ALLOCATED >> 30)) {
+ ret = inode_bmap(inode, map->lblk, &epos, &eloc, &elen, &offset,
+ &etype);
+ if (ret < 0)
+ goto out_read;
+ if (ret > 0 && etype == (EXT_RECORDED_ALLOCATED >> 30)) {
map->pblk = udf_get_lb_pblock(inode->i_sb, &eloc,
offset);
map->oflags |= UDF_BLK_MAPPED;
+ ret = 0;
}
+out_read:
up_read(&iinfo->i_data_sem);
brelse(epos.bh);
- return 0;
+ return ret;
}
down_write(&iinfo->i_data_sem);
@@ -438,9 +444,9 @@ static int udf_map_block(struct inode *inode, struct udf_map_rq *map)
if (((loff_t)map->lblk) << inode->i_blkbits >= iinfo->i_lenExtents)
udf_discard_prealloc(inode);
udf_clear_extent_cache(inode);
- err = inode_getblk(inode, map);
+ ret = inode_getblk(inode, map);
up_write(&iinfo->i_data_sem);
- return err;
+ return ret;
}
static int __udf_get_block(struct inode *inode, sector_t block,
@@ -543,6 +549,7 @@ static int udf_do_extend_file(struct inode *inode,
} else {
struct kernel_lb_addr tmploc;
uint32_t tmplen;
+ int8_t tmptype;
udf_write_aext(inode, last_pos, &last_ext->extLocation,
last_ext->extLength, 1);
@@ -552,8 +559,12 @@ static int udf_do_extend_file(struct inode *inode,
* more extents, we may need to enter possible following
* empty indirect extent.
*/
- if (new_block_bytes)
- udf_next_aext(inode, last_pos, &tmploc, &tmplen, 0);
+ if (new_block_bytes) {
+ err = udf_next_aext(inode, last_pos, &tmploc, &tmplen,
+ &tmptype, 0);
+ if (err < 0)
+ goto out_err;
+ }
}
iinfo->i_lenExtents += add;
@@ -657,8 +668,10 @@ static int udf_extend_file(struct inode *inode, loff_t newsize)
*/
udf_discard_prealloc(inode);
- etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset);
- within_last_ext = (etype != -1);
+ err = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset, &etype);
+ if (err < 0)
+ goto out;
+ within_last_ext = (err == 1);
/* We don't expect extents past EOF... */
WARN_ON_ONCE(within_last_ext &&
elen > ((loff_t)offset + 1) << inode->i_blkbits);
@@ -672,8 +685,10 @@ static int udf_extend_file(struct inode *inode, loff_t newsize)
extent.extLength = EXT_NOT_RECORDED_NOT_ALLOCATED;
} else {
epos.offset -= adsize;
- etype = udf_next_aext(inode, &epos, &extent.extLocation,
- &extent.extLength, 0);
+ err = udf_next_aext(inode, &epos, &extent.extLocation,
+ &extent.extLength, &etype, 0);
+ if (err <= 0)
+ goto out;
extent.extLength |= etype << 30;
}
@@ -710,11 +725,11 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map)
loff_t lbcount = 0, b_off = 0;
udf_pblk_t newblocknum;
sector_t offset = 0;
- int8_t etype;
+ int8_t etype, tmpetype;
struct udf_inode_info *iinfo = UDF_I(inode);
udf_pblk_t goal = 0, pgoal = iinfo->i_location.logicalBlockNum;
int lastblock = 0;
- bool isBeyondEOF;
+ bool isBeyondEOF = false;
int ret = 0;
prev_epos.offset = udf_file_entry_alloc_offset(inode);
@@ -746,9 +761,13 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map)
prev_epos.offset = cur_epos.offset;
cur_epos.offset = next_epos.offset;
- etype = udf_next_aext(inode, &next_epos, &eloc, &elen, 1);
- if (etype == -1)
+ ret = udf_next_aext(inode, &next_epos, &eloc, &elen, &etype, 1);
+ if (ret < 0) {
+ goto out_free;
+ } else if (ret == 0) {
+ isBeyondEOF = true;
break;
+ }
c = !c;
@@ -769,13 +788,17 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map)
* Move prev_epos and cur_epos into indirect extent if we are at
* the pointer to it
*/
- udf_next_aext(inode, &prev_epos, &tmpeloc, &tmpelen, 0);
- udf_next_aext(inode, &cur_epos, &tmpeloc, &tmpelen, 0);
+ ret = udf_next_aext(inode, &prev_epos, &tmpeloc, &tmpelen, &tmpetype, 0);
+ if (ret < 0)
+ goto out_free;
+ ret = udf_next_aext(inode, &cur_epos, &tmpeloc, &tmpelen, &tmpetype, 0);
+ if (ret < 0)
+ goto out_free;
/* if the extent is allocated and recorded, return the block
if the extent is not a multiple of the blocksize, round up */
- if (etype == (EXT_RECORDED_ALLOCATED >> 30)) {
+ if (!isBeyondEOF && etype == (EXT_RECORDED_ALLOCATED >> 30)) {
if (elen & (inode->i_sb->s_blocksize - 1)) {
elen = EXT_RECORDED_ALLOCATED |
((elen + inode->i_sb->s_blocksize - 1) &
@@ -791,10 +814,9 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map)
}
/* Are we beyond EOF and preallocated extent? */
- if (etype == -1) {
+ if (isBeyondEOF) {
loff_t hole_len;
- isBeyondEOF = true;
if (count) {
if (c)
laarr[0] = laarr[1];
@@ -830,7 +852,6 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map)
endnum = c + 1;
lastblock = 1;
} else {
- isBeyondEOF = false;
endnum = startnum = ((count > 2) ? 2 : count);
/* if the current extent is in position 0,
@@ -844,15 +865,17 @@ static int inode_getblk(struct inode *inode, struct udf_map_rq *map)
/* if the current block is located in an extent,
read the next extent */
- etype = udf_next_aext(inode, &next_epos, &eloc, &elen, 0);
- if (etype != -1) {
+ ret = udf_next_aext(inode, &next_epos, &eloc, &elen, &etype, 0);
+ if (ret > 0) {
laarr[c + 1].extLength = (etype << 30) | elen;
laarr[c + 1].extLocation = eloc;
count++;
startnum++;
endnum++;
- } else
+ } else if (ret == 0)
lastblock = 1;
+ else
+ goto out_free;
}
/* if the current extent is not recorded but allocated, get the
@@ -1170,6 +1193,7 @@ static int udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr,
int start = 0, i;
struct kernel_lb_addr tmploc;
uint32_t tmplen;
+ int8_t tmpetype;
int err;
if (startnum > endnum) {
@@ -1187,14 +1211,19 @@ static int udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr,
*/
if (err < 0)
return err;
- udf_next_aext(inode, epos, &laarr[i].extLocation,
- &laarr[i].extLength, 1);
+ err = udf_next_aext(inode, epos, &laarr[i].extLocation,
+ &laarr[i].extLength, &tmpetype, 1);
+ if (err < 0)
+ return err;
start++;
}
}
for (i = start; i < endnum; i++) {
- udf_next_aext(inode, epos, &tmploc, &tmplen, 0);
+ err = udf_next_aext(inode, epos, &tmploc, &tmplen, &tmpetype, 0);
+ if (err < 0)
+ return err;
+
udf_write_aext(inode, epos, &laarr[i].extLocation,
laarr[i].extLength, 1);
}
@@ -1953,6 +1982,7 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block,
struct extent_position nepos;
struct kernel_lb_addr neloc;
int ver, adsize;
+ int err = 0;
if (UDF_I(inode)->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
adsize = sizeof(struct short_ad);
@@ -1997,10 +2027,12 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block,
if (epos->offset + adsize > sb->s_blocksize) {
struct kernel_lb_addr cp_loc;
uint32_t cp_len;
- int cp_type;
+ int8_t cp_type;
epos->offset -= adsize;
- cp_type = udf_current_aext(inode, epos, &cp_loc, &cp_len, 0);
+ err = udf_current_aext(inode, epos, &cp_loc, &cp_len, &cp_type, 0);
+ if (err <= 0)
+ goto err_out;
cp_len |= ((uint32_t)cp_type) << 30;
__udf_add_aext(inode, &nepos, &cp_loc, cp_len, 1);
@@ -2015,6 +2047,9 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block,
*epos = nepos;
return 0;
+err_out:
+ brelse(bh);
+ return err;
}
/*
@@ -2160,21 +2195,30 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos,
*/
#define UDF_MAX_INDIR_EXTS 16
-int8_t udf_next_aext(struct inode *inode, struct extent_position *epos,
- struct kernel_lb_addr *eloc, uint32_t *elen, int inc)
+/*
+ * Returns 1 on success, -errno on error, 0 on hit EOF.
+ */
+int udf_next_aext(struct inode *inode, struct extent_position *epos,
+ struct kernel_lb_addr *eloc, uint32_t *elen, int8_t *etype,
+ int inc)
{
- int8_t etype;
unsigned int indirections = 0;
+ int ret = 0;
+ udf_pblk_t block;
- while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) ==
- (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) {
- udf_pblk_t block;
+ while (1) {
+ ret = udf_current_aext(inode, epos, eloc, elen,
+ etype, inc);
+ if (ret <= 0)
+ return ret;
+ if (*etype != (EXT_NEXT_EXTENT_ALLOCDESCS >> 30))
+ return ret;
if (++indirections > UDF_MAX_INDIR_EXTS) {
udf_err(inode->i_sb,
"too many indirect extents in inode %lu\n",
inode->i_ino);
- return -1;
+ return -EFSCORRUPTED;
}
epos->block = *eloc;
@@ -2184,18 +2228,19 @@ int8_t udf_next_aext(struct inode *inode, struct extent_position *epos,
epos->bh = sb_bread(inode->i_sb, block);
if (!epos->bh) {
udf_debug("reading block %u failed!\n", block);
- return -1;
+ return -EIO;
}
}
-
- return etype;
}
-int8_t udf_current_aext(struct inode *inode, struct extent_position *epos,
- struct kernel_lb_addr *eloc, uint32_t *elen, int inc)
+/*
+ * Returns 1 on success, -errno on error, 0 on hit EOF.
+ */
+int udf_current_aext(struct inode *inode, struct extent_position *epos,
+ struct kernel_lb_addr *eloc, uint32_t *elen, int8_t *etype,
+ int inc)
{
int alen;
- int8_t etype;
uint8_t *ptr;
struct short_ad *sad;
struct long_ad *lad;
@@ -2210,20 +2255,23 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos,
alen = udf_file_entry_alloc_offset(inode) +
iinfo->i_lenAlloc;
} else {
+ struct allocExtDesc *header =
+ (struct allocExtDesc *)epos->bh->b_data;
+
if (!epos->offset)
epos->offset = sizeof(struct allocExtDesc);
ptr = epos->bh->b_data + epos->offset;
- alen = sizeof(struct allocExtDesc) +
- le32_to_cpu(((struct allocExtDesc *)epos->bh->b_data)->
- lengthAllocDescs);
+ if (check_add_overflow(sizeof(struct allocExtDesc),
+ le32_to_cpu(header->lengthAllocDescs), &alen))
+ return -1;
}
switch (iinfo->i_alloc_type) {
case ICBTAG_FLAG_AD_SHORT:
sad = udf_get_fileshortad(ptr, alen, &epos->offset, inc);
if (!sad)
- return -1;
- etype = le32_to_cpu(sad->extLength) >> 30;
+ return 0;
+ *etype = le32_to_cpu(sad->extLength) >> 30;
eloc->logicalBlockNum = le32_to_cpu(sad->extPosition);
eloc->partitionReferenceNum =
iinfo->i_location.partitionReferenceNum;
@@ -2232,17 +2280,17 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos,
case ICBTAG_FLAG_AD_LONG:
lad = udf_get_filelongad(ptr, alen, &epos->offset, inc);
if (!lad)
- return -1;
- etype = le32_to_cpu(lad->extLength) >> 30;
+ return 0;
+ *etype = le32_to_cpu(lad->extLength) >> 30;
*eloc = lelb_to_cpu(lad->extLocation);
*elen = le32_to_cpu(lad->extLength) & UDF_EXTENT_LENGTH_MASK;
break;
default:
udf_debug("alloc_type = %u unsupported\n", iinfo->i_alloc_type);
- return -1;
+ return -EINVAL;
}
- return etype;
+ return 1;
}
static int udf_insert_aext(struct inode *inode, struct extent_position epos,
@@ -2251,20 +2299,24 @@ static int udf_insert_aext(struct inode *inode, struct extent_position epos,
struct kernel_lb_addr oeloc;
uint32_t oelen;
int8_t etype;
- int err;
+ int ret;
if (epos.bh)
get_bh(epos.bh);
- while ((etype = udf_next_aext(inode, &epos, &oeloc, &oelen, 0)) != -1) {
+ while (1) {
+ ret = udf_next_aext(inode, &epos, &oeloc, &oelen, &etype, 0);
+ if (ret <= 0)
+ break;
udf_write_aext(inode, &epos, &neloc, nelen, 1);
neloc = oeloc;
nelen = (etype << 30) | oelen;
}
- err = udf_add_aext(inode, &epos, &neloc, nelen, 1);
+ if (ret == 0)
+ ret = udf_add_aext(inode, &epos, &neloc, nelen, 1);
brelse(epos.bh);
- return err;
+ return ret;
}
int8_t udf_delete_aext(struct inode *inode, struct extent_position epos)
@@ -2276,6 +2328,7 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos)
struct udf_inode_info *iinfo;
struct kernel_lb_addr eloc;
uint32_t elen;
+ int ret;
if (epos.bh) {
get_bh(epos.bh);
@@ -2291,10 +2344,18 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos)
adsize = 0;
oepos = epos;
- if (udf_next_aext(inode, &epos, &eloc, &elen, 1) == -1)
+ if (udf_next_aext(inode, &epos, &eloc, &elen, &etype, 1) <= 0)
return -1;
- while ((etype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1) {
+ while (1) {
+ ret = udf_next_aext(inode, &epos, &eloc, &elen, &etype, 1);
+ if (ret < 0) {
+ brelse(epos.bh);
+ brelse(oepos.bh);
+ return -1;
+ }
+ if (ret == 0)
+ break;
udf_write_aext(inode, &oepos, &eloc, (etype << 30) | elen, 1);
if (oepos.bh != epos.bh) {
oepos.block = epos.block;
@@ -2351,14 +2412,17 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos)
return (elen >> 30);
}
-int8_t inode_bmap(struct inode *inode, sector_t block,
- struct extent_position *pos, struct kernel_lb_addr *eloc,
- uint32_t *elen, sector_t *offset)
+/*
+ * Returns 1 on success, -errno on error, 0 on hit EOF.
+ */
+int inode_bmap(struct inode *inode, sector_t block, struct extent_position *pos,
+ struct kernel_lb_addr *eloc, uint32_t *elen, sector_t *offset,
+ int8_t *etype)
{
unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
loff_t lbcount = 0, bcount = (loff_t) block << blocksize_bits;
- int8_t etype;
struct udf_inode_info *iinfo;
+ int err = 0;
iinfo = UDF_I(inode);
if (!udf_read_extent_cache(inode, bcount, &lbcount, pos)) {
@@ -2368,11 +2432,13 @@ int8_t inode_bmap(struct inode *inode, sector_t block,
}
*elen = 0;
do {
- etype = udf_next_aext(inode, pos, eloc, elen, 1);
- if (etype == -1) {
- *offset = (bcount - lbcount) >> blocksize_bits;
- iinfo->i_lenExtents = lbcount;
- return -1;
+ err = udf_next_aext(inode, pos, eloc, elen, etype, 1);
+ if (err <= 0) {
+ if (err == 0) {
+ *offset = (bcount - lbcount) >> blocksize_bits;
+ iinfo->i_lenExtents = lbcount;
+ }
+ return err;
}
lbcount += *elen;
} while (lbcount <= bcount);
@@ -2380,5 +2446,5 @@ int8_t inode_bmap(struct inode *inode, sector_t block,
udf_update_extent_cache(inode, lbcount - *elen, pos);
*offset = (bcount + *elen - lbcount) >> blocksize_bits;
- return etype;
+ return 1;
}
diff --git a/fs/udf/partition.c b/fs/udf/partition.c
index af877991edc1..2b85c9501bed 100644
--- a/fs/udf/partition.c
+++ b/fs/udf/partition.c
@@ -282,9 +282,11 @@ static uint32_t udf_try_read_meta(struct inode *inode, uint32_t block,
sector_t ext_offset;
struct extent_position epos = {};
uint32_t phyblock;
+ int8_t etype;
+ int err = 0;
- if (inode_bmap(inode, block, &epos, &eloc, &elen, &ext_offset) !=
- (EXT_RECORDED_ALLOCATED >> 30))
+ err = inode_bmap(inode, block, &epos, &eloc, &elen, &ext_offset, &etype);
+ if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30))
phyblock = 0xFFFFFFFF;
else {
map = &UDF_SB(sb)->s_partmaps[partition];
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 3460ecc826d1..1c8a736b3309 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -2482,13 +2482,14 @@ static unsigned int udf_count_free_table(struct super_block *sb,
uint32_t elen;
struct kernel_lb_addr eloc;
struct extent_position epos;
+ int8_t etype;
mutex_lock(&UDF_SB(sb)->s_alloc_mutex);
epos.block = UDF_I(table)->i_location;
epos.offset = sizeof(struct unallocSpaceEntry);
epos.bh = NULL;
- while (udf_next_aext(table, &epos, &eloc, &elen, 1) != -1)
+ while (udf_next_aext(table, &epos, &eloc, &elen, &etype, 1) > 0)
accum += (elen >> table->i_sb->s_blocksize_bits);
brelse(epos.bh);
diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c
index a686c10fd709..4f33a4a48886 100644
--- a/fs/udf/truncate.c
+++ b/fs/udf/truncate.c
@@ -69,6 +69,7 @@ void udf_truncate_tail_extent(struct inode *inode)
int8_t etype = -1, netype;
int adsize;
struct udf_inode_info *iinfo = UDF_I(inode);
+ int ret;
if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB ||
inode->i_size == iinfo->i_lenExtents)
@@ -85,7 +86,10 @@ void udf_truncate_tail_extent(struct inode *inode)
BUG();
/* Find the last extent in the file */
- while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1) {
+ while (1) {
+ ret = udf_next_aext(inode, &epos, &eloc, &elen, &netype, 1);
+ if (ret <= 0)
+ break;
etype = netype;
lbcount += elen;
if (lbcount > inode->i_size) {
@@ -101,7 +105,8 @@ void udf_truncate_tail_extent(struct inode *inode)
epos.offset -= adsize;
extent_trunc(inode, &epos, &eloc, etype, elen, nelen);
epos.offset += adsize;
- if (udf_next_aext(inode, &epos, &eloc, &elen, 1) != -1)
+ if (udf_next_aext(inode, &epos, &eloc, &elen,
+ &netype, 1) > 0)
udf_err(inode->i_sb,
"Extent after EOF in inode %u\n",
(unsigned)inode->i_ino);
@@ -110,7 +115,8 @@ void udf_truncate_tail_extent(struct inode *inode)
}
/* This inode entry is in-memory only and thus we don't have to mark
* the inode dirty */
- iinfo->i_lenExtents = inode->i_size;
+ if (ret == 0)
+ iinfo->i_lenExtents = inode->i_size;
brelse(epos.bh);
}
@@ -124,6 +130,8 @@ void udf_discard_prealloc(struct inode *inode)
int8_t etype = -1;
struct udf_inode_info *iinfo = UDF_I(inode);
int bsize = i_blocksize(inode);
+ int8_t tmpetype = -1;
+ int ret;
if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB ||
ALIGN(inode->i_size, bsize) == ALIGN(iinfo->i_lenExtents, bsize))
@@ -132,15 +140,23 @@ void udf_discard_prealloc(struct inode *inode)
epos.block = iinfo->i_location;
/* Find the last extent in the file */
- while (udf_next_aext(inode, &epos, &eloc, &elen, 0) != -1) {
+ while (1) {
+ ret = udf_next_aext(inode, &epos, &eloc, &elen, &tmpetype, 0);
+ if (ret < 0)
+ goto out;
+ if (ret == 0)
+ break;
brelse(prev_epos.bh);
prev_epos = epos;
if (prev_epos.bh)
get_bh(prev_epos.bh);
- etype = udf_next_aext(inode, &epos, &eloc, &elen, 1);
+ ret = udf_next_aext(inode, &epos, &eloc, &elen, &etype, 1);
+ if (ret < 0)
+ goto out;
lbcount += elen;
}
+
if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) {
lbcount -= elen;
udf_delete_aext(inode, prev_epos);
@@ -150,6 +166,7 @@ void udf_discard_prealloc(struct inode *inode)
/* This inode entry is in-memory only and thus we don't have to mark
* the inode dirty */
iinfo->i_lenExtents = lbcount;
+out:
brelse(epos.bh);
brelse(prev_epos.bh);
}
@@ -188,6 +205,7 @@ int udf_truncate_extents(struct inode *inode)
loff_t byte_offset;
int adsize;
struct udf_inode_info *iinfo = UDF_I(inode);
+ int ret = 0;
if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
adsize = sizeof(struct short_ad);
@@ -196,10 +214,12 @@ int udf_truncate_extents(struct inode *inode)
else
BUG();
- etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset);
+ ret = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset, &etype);
+ if (ret < 0)
+ return ret;
byte_offset = (offset << sb->s_blocksize_bits) +
(inode->i_size & (sb->s_blocksize - 1));
- if (etype == -1) {
+ if (ret == 0) {
/* We should extend the file? */
WARN_ON(byte_offset);
return 0;
@@ -217,8 +237,8 @@ int udf_truncate_extents(struct inode *inode)
else
lenalloc -= sizeof(struct allocExtDesc);
- while ((etype = udf_current_aext(inode, &epos, &eloc,
- &elen, 0)) != -1) {
+ while ((ret = udf_current_aext(inode, &epos, &eloc,
+ &elen, &etype, 0)) > 0) {
if (etype == (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) {
udf_write_aext(inode, &epos, &neloc, nelen, 0);
if (indirect_ext_len) {
@@ -253,6 +273,11 @@ int udf_truncate_extents(struct inode *inode)
}
}
+ if (ret < 0) {
+ brelse(epos.bh);
+ return ret;
+ }
+
if (indirect_ext_len) {
BUG_ON(!epos.bh);
udf_free_blocks(sb, NULL, &epos.block, 0, indirect_ext_len);
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 88692512a466..d159f20d61e8 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -157,8 +157,9 @@ extern struct buffer_head *udf_bread(struct inode *inode, udf_pblk_t block,
extern int udf_setsize(struct inode *, loff_t);
extern void udf_evict_inode(struct inode *);
extern int udf_write_inode(struct inode *, struct writeback_control *wbc);
-extern int8_t inode_bmap(struct inode *, sector_t, struct extent_position *,
- struct kernel_lb_addr *, uint32_t *, sector_t *);
+extern int inode_bmap(struct inode *inode, sector_t block,
+ struct extent_position *pos, struct kernel_lb_addr *eloc,
+ uint32_t *elen, sector_t *offset, int8_t *etype);
int udf_get_block(struct inode *, sector_t, struct buffer_head *, int);
extern int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block,
struct extent_position *epos);
@@ -169,10 +170,12 @@ extern int udf_add_aext(struct inode *, struct extent_position *,
extern void udf_write_aext(struct inode *, struct extent_position *,
struct kernel_lb_addr *, uint32_t, int);
extern int8_t udf_delete_aext(struct inode *, struct extent_position);
-extern int8_t udf_next_aext(struct inode *, struct extent_position *,
- struct kernel_lb_addr *, uint32_t *, int);
-extern int8_t udf_current_aext(struct inode *, struct extent_position *,
- struct kernel_lb_addr *, uint32_t *, int);
+extern int udf_next_aext(struct inode *inode, struct extent_position *epos,
+ struct kernel_lb_addr *eloc, uint32_t *elen,
+ int8_t *etype, int inc);
+extern int udf_current_aext(struct inode *inode, struct extent_position *epos,
+ struct kernel_lb_addr *eloc, uint32_t *elen,
+ int8_t *etype, int inc);
extern void udf_update_extra_perms(struct inode *inode, umode_t mode);
/* misc.c */
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 24bd12186647..c8390976ab6a 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -307,7 +307,7 @@ static int ufs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
if (old_dir != new_dir)
ufs_set_link(old_inode, dir_de, dir_folio, new_dir, 0);
else
- folio_release_kmap(dir_folio, new_dir);
+ folio_release_kmap(dir_folio, dir_de);
inode_dec_link_count(old_dir);
}
return 0;
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 54a098fe7285..9a2221b4aa21 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -69,7 +69,7 @@ typedef __u32 xfs_nlink_t;
#include <asm/param.h>
#include <linux/uaccess.h>
#include <asm/byteorder.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include "xfs_fs.h"
#include "xfs_stats.h"
diff --git a/fs/zonefs/sysfs.c b/fs/zonefs/sysfs.c
index 8ccb65c2b419..ff9a688f1f9c 100644
--- a/fs/zonefs/sysfs.c
+++ b/fs/zonefs/sysfs.c
@@ -92,6 +92,7 @@ int zonefs_sysfs_register(struct super_block *sb)
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
int ret;
+ super_set_sysfs_name_id(sb);
init_completion(&sbi->s_kobj_unregister);
ret = kobject_init_and_add(&sbi->s_kobj, &zonefs_sb_ktype,
zonefs_sysfs_root, "%s", sb->s_id);