summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/super.c2
-rw-r--r--fs/crypto/keyinfo.c5
-rw-r--r--fs/direct-io.c39
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h24
-rw-r--r--fs/ecryptfs/keystore.c9
-rw-r--r--fs/exec.c1
-rw-r--r--fs/ext4/super.c4
-rw-r--r--fs/fscache/object-list.c7
-rw-r--r--fs/fuse/inode.c2
-rw-r--r--fs/iomap.c41
-rw-r--r--fs/namespace.c3
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c11
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h1
-rw-r--r--fs/xfs/xfs_aops.c47
-rw-r--r--fs/xfs/xfs_fsmap.c48
-rw-r--r--fs/xfs/xfs_super.c2
16 files changed, 165 insertions, 81 deletions
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 35a128acfbd1..161694b66038 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1135,7 +1135,7 @@ static int btrfs_fill_super(struct super_block *sb,
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
sb->s_flags |= MS_POSIXACL;
#endif
- sb->s_flags |= MS_I_VERSION;
+ sb->s_flags |= SB_I_VERSION;
sb->s_iflags |= SB_I_CGROUPWB;
err = super_setup_bdi(sb);
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 018c588c7ac3..8e704d12a1cf 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -109,6 +109,11 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
goto out;
}
ukp = user_key_payload_locked(keyring_key);
+ if (!ukp) {
+ /* key was revoked before we acquired its semaphore */
+ res = -EKEYREVOKED;
+ goto out;
+ }
if (ukp->datalen != sizeof(struct fscrypt_key)) {
res = -EINVAL;
goto out;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 96415c65bbdc..b53e66d9abd7 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -45,6 +45,12 @@
#define DIO_PAGES 64
/*
+ * Flags for dio_complete()
+ */
+#define DIO_COMPLETE_ASYNC 0x01 /* This is async IO */
+#define DIO_COMPLETE_INVALIDATE 0x02 /* Can invalidate pages */
+
+/*
* This code generally works in units of "dio_blocks". A dio_block is
* somewhere between the hard sector size and the filesystem block size. it
* is determined on a per-invocation basis. When talking to the filesystem
@@ -225,7 +231,7 @@ static inline struct page *dio_get_page(struct dio *dio,
* filesystems can use it to hold additional state between get_block calls and
* dio_complete.
*/
-static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
+static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
{
loff_t offset = dio->iocb->ki_pos;
ssize_t transferred = 0;
@@ -259,14 +265,27 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
if (ret == 0)
ret = transferred;
+ if (dio->end_io) {
+ // XXX: ki_pos??
+ err = dio->end_io(dio->iocb, offset, ret, dio->private);
+ if (err)
+ ret = err;
+ }
+
/*
* Try again to invalidate clean pages which might have been cached by
* non-direct readahead, or faulted in by get_user_pages() if the source
* of the write was an mmap'ed region of the file we're writing. Either
* one is a pretty crazy thing to do, so we don't support it 100%. If
* this invalidation fails, tough, the write still worked...
+ *
+ * And this page cache invalidation has to be after dio->end_io(), as
+ * some filesystems convert unwritten extents to real allocations in
+ * end_io() when necessary, otherwise a racing buffer read would cache
+ * zeros from unwritten extents.
*/
- if (ret > 0 && dio->op == REQ_OP_WRITE &&
+ if (flags & DIO_COMPLETE_INVALIDATE &&
+ ret > 0 && dio->op == REQ_OP_WRITE &&
dio->inode->i_mapping->nrpages) {
err = invalidate_inode_pages2_range(dio->inode->i_mapping,
offset >> PAGE_SHIFT,
@@ -274,18 +293,10 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
WARN_ON_ONCE(err);
}
- if (dio->end_io) {
-
- // XXX: ki_pos??
- err = dio->end_io(dio->iocb, offset, ret, dio->private);
- if (err)
- ret = err;
- }
-
if (!(dio->flags & DIO_SKIP_DIO_COUNT))
inode_dio_end(dio->inode);
- if (is_async) {
+ if (flags & DIO_COMPLETE_ASYNC) {
/*
* generic_write_sync expects ki_pos to have been updated
* already, but the submission path only does this for
@@ -306,7 +317,7 @@ static void dio_aio_complete_work(struct work_struct *work)
{
struct dio *dio = container_of(work, struct dio, complete_work);
- dio_complete(dio, 0, true);
+ dio_complete(dio, 0, DIO_COMPLETE_ASYNC | DIO_COMPLETE_INVALIDATE);
}
static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio);
@@ -348,7 +359,7 @@ static void dio_bio_end_aio(struct bio *bio)
queue_work(dio->inode->i_sb->s_dio_done_wq,
&dio->complete_work);
} else {
- dio_complete(dio, 0, true);
+ dio_complete(dio, 0, DIO_COMPLETE_ASYNC);
}
}
}
@@ -1360,7 +1371,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
dio_await_completion(dio);
if (drop_refcount(dio) == 0) {
- retval = dio_complete(dio, retval, false);
+ retval = dio_complete(dio, retval, DIO_COMPLETE_INVALIDATE);
} else
BUG_ON(retval != -EIOCBQUEUED);
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 9c351bf757b2..3fbc0ff79699 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -84,11 +84,16 @@ struct ecryptfs_page_crypt_context {
static inline struct ecryptfs_auth_tok *
ecryptfs_get_encrypted_key_payload_data(struct key *key)
{
- if (key->type == &key_type_encrypted)
- return (struct ecryptfs_auth_tok *)
- (&((struct encrypted_key_payload *)key->payload.data[0])->payload_data);
- else
+ struct encrypted_key_payload *payload;
+
+ if (key->type != &key_type_encrypted)
return NULL;
+
+ payload = key->payload.data[0];
+ if (!payload)
+ return ERR_PTR(-EKEYREVOKED);
+
+ return (struct ecryptfs_auth_tok *)payload->payload_data;
}
static inline struct key *ecryptfs_get_encrypted_key(char *sig)
@@ -114,12 +119,17 @@ static inline struct ecryptfs_auth_tok *
ecryptfs_get_key_payload_data(struct key *key)
{
struct ecryptfs_auth_tok *auth_tok;
+ struct user_key_payload *ukp;
auth_tok = ecryptfs_get_encrypted_key_payload_data(key);
- if (!auth_tok)
- return (struct ecryptfs_auth_tok *)user_key_payload_locked(key)->data;
- else
+ if (auth_tok)
return auth_tok;
+
+ ukp = user_key_payload_locked(key);
+ if (!ukp)
+ return ERR_PTR(-EKEYREVOKED);
+
+ return (struct ecryptfs_auth_tok *)ukp->data;
}
#define ECRYPTFS_MAX_KEYSET_SIZE 1024
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 3cf1546dca82..fa218cd64f74 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -459,7 +459,8 @@ out:
* @auth_tok_key: key containing the authentication token
* @auth_tok: authentication token
*
- * Returns zero on valid auth tok; -EINVAL otherwise
+ * Returns zero on valid auth tok; -EINVAL if the payload is invalid; or
+ * -EKEYREVOKED if the key was revoked before we acquired its semaphore.
*/
static int
ecryptfs_verify_auth_tok_from_key(struct key *auth_tok_key,
@@ -468,6 +469,12 @@ ecryptfs_verify_auth_tok_from_key(struct key *auth_tok_key,
int rc = 0;
(*auth_tok) = ecryptfs_get_key_payload_data(auth_tok_key);
+ if (IS_ERR(*auth_tok)) {
+ rc = PTR_ERR(*auth_tok);
+ *auth_tok = NULL;
+ goto out;
+ }
+
if (ecryptfs_verify_version((*auth_tok)->version)) {
printk(KERN_ERR "Data structure version mismatch. Userspace "
"tools must match eCryptfs kernel module with major "
diff --git a/fs/exec.c b/fs/exec.c
index 5470d3c1892a..3e14ba25f678 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1802,6 +1802,7 @@ static int do_execveat_common(int fd, struct filename *filename,
/* execve succeeded */
current->fs->in_exec = 0;
current->in_execve = 0;
+ membarrier_execve(current);
acct_update_integrals(current);
task_numa_free(current);
free_bprm(bprm);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b104096fce9e..b0915b734a38 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1677,7 +1677,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
return 1;
case Opt_i_version:
- sb->s_flags |= MS_I_VERSION;
+ sb->s_flags |= SB_I_VERSION;
return 1;
case Opt_lazytime:
sb->s_flags |= MS_LAZYTIME;
@@ -2060,7 +2060,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time);
if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME)
SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time);
- if (sb->s_flags & MS_I_VERSION)
+ if (sb->s_flags & SB_I_VERSION)
SEQ_OPTS_PUTS("i_version");
if (nodefs || sbi->s_stripe)
SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index b5ab06fabc60..0438d4cd91ef 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -331,6 +331,13 @@ static void fscache_objlist_config(struct fscache_objlist_data *data)
rcu_read_lock();
confkey = user_key_payload_rcu(key);
+ if (!confkey) {
+ /* key was revoked */
+ rcu_read_unlock();
+ key_put(key);
+ goto no_config;
+ }
+
buf = confkey->data;
for (len = confkey->datalen - 1; len >= 0; len--) {
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 65c88379a3a1..94a745acaef8 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1059,7 +1059,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
if (sb->s_flags & MS_MANDLOCK)
goto err;
- sb->s_flags &= ~(MS_NOSEC | MS_I_VERSION);
+ sb->s_flags &= ~(MS_NOSEC | SB_I_VERSION);
if (!parse_fuse_opt(data, &d, is_bdev))
goto err;
diff --git a/fs/iomap.c b/fs/iomap.c
index be61cf742b5e..d4801f8dd4fd 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -714,23 +714,9 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
{
struct kiocb *iocb = dio->iocb;
struct inode *inode = file_inode(iocb->ki_filp);
+ loff_t offset = iocb->ki_pos;
ssize_t ret;
- /*
- * Try again to invalidate clean pages which might have been cached by
- * non-direct readahead, or faulted in by get_user_pages() if the source
- * of the write was an mmap'ed region of the file we're writing. Either
- * one is a pretty crazy thing to do, so we don't support it 100%. If
- * this invalidation fails, tough, the write still worked...
- */
- if (!dio->error &&
- (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
- ret = invalidate_inode_pages2_range(inode->i_mapping,
- iocb->ki_pos >> PAGE_SHIFT,
- (iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT);
- WARN_ON_ONCE(ret);
- }
-
if (dio->end_io) {
ret = dio->end_io(iocb,
dio->error ? dio->error : dio->size,
@@ -742,12 +728,33 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
if (likely(!ret)) {
ret = dio->size;
/* check for short read */
- if (iocb->ki_pos + ret > dio->i_size &&
+ if (offset + ret > dio->i_size &&
!(dio->flags & IOMAP_DIO_WRITE))
- ret = dio->i_size - iocb->ki_pos;
+ ret = dio->i_size - offset;
iocb->ki_pos += ret;
}
+ /*
+ * Try again to invalidate clean pages which might have been cached by
+ * non-direct readahead, or faulted in by get_user_pages() if the source
+ * of the write was an mmap'ed region of the file we're writing. Either
+ * one is a pretty crazy thing to do, so we don't support it 100%. If
+ * this invalidation fails, tough, the write still worked...
+ *
+ * And this page cache invalidation has to be after dio->end_io(), as
+ * some filesystems convert unwritten extents to real allocations in
+ * end_io() when necessary, otherwise a racing buffer read would cache
+ * zeros from unwritten extents.
+ */
+ if (!dio->error &&
+ (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
+ int err;
+ err = invalidate_inode_pages2_range(inode->i_mapping,
+ offset >> PAGE_SHIFT,
+ (offset + dio->size - 1) >> PAGE_SHIFT);
+ WARN_ON_ONCE(err);
+ }
+
inode_dio_end(file_inode(iocb->ki_filp));
kfree(dio);
diff --git a/fs/namespace.c b/fs/namespace.c
index 3b601f115b6c..d18deb4c410b 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2825,7 +2825,8 @@ long do_mount(const char *dev_name, const char __user *dir_name,
SB_MANDLOCK |
SB_DIRSYNC |
SB_SILENT |
- SB_POSIXACL);
+ SB_POSIXACL |
+ SB_I_VERSION);
if (flags & MS_REMOUNT)
retval = do_remount(&path, flags, sb_flags, mnt_flags,
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index def32fa1c225..89263797cf32 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3852,6 +3852,17 @@ xfs_trim_extent(
}
}
+/* trim extent to within eof */
+void
+xfs_trim_extent_eof(
+ struct xfs_bmbt_irec *irec,
+ struct xfs_inode *ip)
+
+{
+ xfs_trim_extent(irec, 0, XFS_B_TO_FSB(ip->i_mount,
+ i_size_read(VFS_I(ip))));
+}
+
/*
* Trim the returned map to the required bounds
*/
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 851982a5dfbc..502e0d8fb4ff 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -208,6 +208,7 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
xfs_filblks_t len);
+void xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *);
int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index f18e5932aec4..a3eeaba156c5 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -446,6 +446,19 @@ xfs_imap_valid(
{
offset >>= inode->i_blkbits;
+ /*
+ * We have to make sure the cached mapping is within EOF to protect
+ * against eofblocks trimming on file release leaving us with a stale
+ * mapping. Otherwise, a page for a subsequent file extending buffered
+ * write could get picked up by this writeback cycle and written to the
+ * wrong blocks.
+ *
+ * Note that what we really want here is a generic mapping invalidation
+ * mechanism to protect us from arbitrary extent modifying contexts, not
+ * just eofblocks.
+ */
+ xfs_trim_extent_eof(imap, XFS_I(inode));
+
return offset >= imap->br_startoff &&
offset < imap->br_startoff + imap->br_blockcount;
}
@@ -735,6 +748,14 @@ xfs_vm_invalidatepage(
{
trace_xfs_invalidatepage(page->mapping->host, page, offset,
length);
+
+ /*
+ * If we are invalidating the entire page, clear the dirty state from it
+ * so that we can check for attempts to release dirty cached pages in
+ * xfs_vm_releasepage().
+ */
+ if (offset == 0 && length >= PAGE_SIZE)
+ cancel_dirty_page(page);
block_invalidatepage(page, offset, length);
}
@@ -1190,25 +1211,27 @@ xfs_vm_releasepage(
* mm accommodates an old ext3 case where clean pages might not have had
* the dirty bit cleared. Thus, it can send actual dirty pages to
* ->releasepage() via shrink_active_list(). Conversely,
- * block_invalidatepage() can send pages that are still marked dirty
- * but otherwise have invalidated buffers.
+ * block_invalidatepage() can send pages that are still marked dirty but
+ * otherwise have invalidated buffers.
*
* We want to release the latter to avoid unnecessary buildup of the
- * LRU, skip the former and warn if we've left any lingering
- * delalloc/unwritten buffers on clean pages. Skip pages with delalloc
- * or unwritten buffers and warn if the page is not dirty. Otherwise
- * try to release the buffers.
+ * LRU, so xfs_vm_invalidatepage() clears the page dirty flag on pages
+ * that are entirely invalidated and need to be released. Hence the
+ * only time we should get dirty pages here is through
+ * shrink_active_list() and so we can simply skip those now.
+ *
+ * warn if we've left any lingering delalloc/unwritten buffers on clean
+ * or invalidated pages we are about to release.
*/
+ if (PageDirty(page))
+ return 0;
+
xfs_count_page_state(page, &delalloc, &unwritten);
- if (delalloc) {
- WARN_ON_ONCE(!PageDirty(page));
+ if (WARN_ON_ONCE(delalloc))
return 0;
- }
- if (unwritten) {
- WARN_ON_ONCE(!PageDirty(page));
+ if (WARN_ON_ONCE(unwritten))
return 0;
- }
return try_to_free_buffers(page);
}
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 560e0b40ac1b..43cfc07996a4 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -367,29 +367,6 @@ xfs_getfsmap_datadev_helper(
return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr);
}
-/* Transform a rtbitmap "record" into a fsmap */
-STATIC int
-xfs_getfsmap_rtdev_rtbitmap_helper(
- struct xfs_trans *tp,
- struct xfs_rtalloc_rec *rec,
- void *priv)
-{
- struct xfs_mount *mp = tp->t_mountp;
- struct xfs_getfsmap_info *info = priv;
- struct xfs_rmap_irec irec;
- xfs_daddr_t rec_daddr;
-
- rec_daddr = XFS_FSB_TO_BB(mp, rec->ar_startblock);
-
- irec.rm_startblock = rec->ar_startblock;
- irec.rm_blockcount = rec->ar_blockcount;
- irec.rm_owner = XFS_RMAP_OWN_NULL; /* "free" */
- irec.rm_offset = 0;
- irec.rm_flags = 0;
-
- return xfs_getfsmap_helper(tp, info, &irec, rec_daddr);
-}
-
/* Transform a bnobt irec into a fsmap */
STATIC int
xfs_getfsmap_datadev_bnobt_helper(
@@ -475,6 +452,30 @@ xfs_getfsmap_logdev(
return xfs_getfsmap_helper(tp, info, &rmap, 0);
}
+#ifdef CONFIG_XFS_RT
+/* Transform a rtbitmap "record" into a fsmap */
+STATIC int
+xfs_getfsmap_rtdev_rtbitmap_helper(
+ struct xfs_trans *tp,
+ struct xfs_rtalloc_rec *rec,
+ void *priv)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_getfsmap_info *info = priv;
+ struct xfs_rmap_irec irec;
+ xfs_daddr_t rec_daddr;
+
+ rec_daddr = XFS_FSB_TO_BB(mp, rec->ar_startblock);
+
+ irec.rm_startblock = rec->ar_startblock;
+ irec.rm_blockcount = rec->ar_blockcount;
+ irec.rm_owner = XFS_RMAP_OWN_NULL; /* "free" */
+ irec.rm_offset = 0;
+ irec.rm_flags = 0;
+
+ return xfs_getfsmap_helper(tp, info, &irec, rec_daddr);
+}
+
/* Execute a getfsmap query against the realtime device. */
STATIC int
__xfs_getfsmap_rtdev(
@@ -521,7 +522,6 @@ __xfs_getfsmap_rtdev(
return query_fn(tp, info);
}
-#ifdef CONFIG_XFS_RT
/* Actually query the realtime bitmap. */
STATIC int
xfs_getfsmap_rtdev_rtbitmap_query(
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 584cf2d573ba..f663022353c0 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1637,7 +1637,7 @@ xfs_fs_fill_super(
/* version 5 superblocks support inode version counters. */
if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
- sb->s_flags |= MS_I_VERSION;
+ sb->s_flags |= SB_I_VERSION;
if (mp->m_flags & XFS_MOUNT_DAX) {
xfs_warn(mp,
generated by cgit (git 2.34.1) at 2024-06-06 14:45:43 +0000