summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/vfs_addr.c3
-rw-r--r--fs/afs/file.c3
-rw-r--r--fs/binfmt_flat.c4
-rw-r--r--fs/btrfs/block-group.c13
-rw-r--r--fs/btrfs/ctree.h1
-rw-r--r--fs/btrfs/delayed-ref.c67
-rw-r--r--fs/btrfs/delayed-ref.h2
-rw-r--r--fs/btrfs/direct-io.c38
-rw-r--r--fs/btrfs/extent-tree.c54
-rw-r--r--fs/btrfs/extent_io.c14
-rw-r--r--fs/btrfs/extent_map.c24
-rw-r--r--fs/btrfs/file.c22
-rw-r--r--fs/btrfs/free-space-cache.c4
-rw-r--r--fs/btrfs/inode.c28
-rw-r--r--fs/btrfs/print-tree.c2
-rw-r--r--fs/btrfs/scrub.c25
-rw-r--r--fs/btrfs/send.c52
-rw-r--r--fs/btrfs/space-info.c5
-rw-r--r--fs/btrfs/space-info.h1
-rw-r--r--fs/btrfs/super.c15
-rw-r--r--fs/btrfs/tests/extent-map-tests.c99
-rw-r--r--fs/btrfs/tree-checker.c54
-rw-r--r--fs/ceph/addr.c28
-rw-r--r--fs/ceph/caps.c35
-rw-r--r--fs/ceph/inode.c2
-rw-r--r--fs/ceph/super.h7
-rw-r--r--fs/exec.c8
-rw-r--r--fs/file.c31
-rw-r--r--fs/inode.c39
-rw-r--r--fs/libfs.c35
-rw-r--r--fs/locks.c2
-rw-r--r--fs/netfs/Kconfig2
-rw-r--r--fs/netfs/buffered_read.c123
-rw-r--r--fs/netfs/buffered_write.c2
-rw-r--r--fs/netfs/fscache_cookie.c4
-rw-r--r--fs/netfs/io.c161
-rw-r--r--fs/netfs/objects.c10
-rw-r--r--fs/netfs/write_issue.c4
-rw-r--r--fs/nfs/fscache.c5
-rw-r--r--fs/nfs/fscache.h2
-rw-r--r--fs/nfsd/nfsctl.c3
-rw-r--r--fs/smb/client/cifs_debug.c2
-rw-r--r--fs/smb/client/cifsfs.h4
-rw-r--r--fs/smb/client/cifsglob.h36
-rw-r--r--fs/smb/client/cifsproto.h2
-rw-r--r--fs/smb/client/file.c3
-rw-r--r--fs/smb/client/inode.c17
-rw-r--r--fs/smb/client/ioctl.c32
-rw-r--r--fs/smb/client/misc.c65
-rw-r--r--fs/smb/client/reparse.c4
-rw-r--r--fs/smb/client/reparse.h19
-rw-r--r--fs/smb/client/smb2inode.c8
-rw-r--r--fs/smb/client/smb2pdu.c3
-rw-r--r--fs/smb/client/smbdirect.c8
-rw-r--r--fs/smb/client/trace.h51
-rw-r--r--fs/smb/client/transport.c2
-rw-r--r--fs/smb/server/mgmt/share_config.c15
-rw-r--r--fs/smb/server/mgmt/share_config.h4
-rw-r--r--fs/smb/server/mgmt/tree_connect.c9
-rw-r--r--fs/smb/server/mgmt/tree_connect.h4
-rw-r--r--fs/smb/server/smb2pdu.c9
-rw-r--r--fs/smb/server/smb_common.c9
-rw-r--r--fs/smb/server/smb_common.h2
-rw-r--r--fs/squashfs/inode.c7
-rw-r--r--fs/tracefs/event_inode.c4
-rw-r--r--fs/tracefs/inode.c12
-rw-r--r--fs/tracefs/internal.h5
-rw-r--r--fs/xfs/libxfs/xfs_quota_defs.h2
-rw-r--r--fs/xfs/libxfs/xfs_trans_resv.c28
-rw-r--r--fs/xfs/scrub/agheader_repair.c2
-rw-r--r--fs/xfs/scrub/parent.c2
-rw-r--r--fs/xfs/scrub/trace.h10
-rw-r--r--fs/xfs/xfs_attr_list.c2
-rw-r--r--fs/xfs/xfs_trace.h10
-rw-r--r--fs/xfs/xfs_xattr.c19
75 files changed, 1095 insertions, 349 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index a97ceb105cd8..24fdc74caeba 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -75,7 +75,8 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
/* if we just extended the file size, any portion not in
* cache won't be on server and is zeroes */
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
netfs_subreq_terminated(subreq, err ?: total, false);
}
diff --git a/fs/afs/file.c b/fs/afs/file.c
index c3f0c45ae9a9..ec1be0091fdb 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -242,7 +242,8 @@ static void afs_fetch_data_notify(struct afs_operation *op)
req->error = error;
if (subreq) {
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
netfs_subreq_terminated(subreq, error ?: req->actual_len, false);
req->subreq = NULL;
} else if (req->done) {
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index c26545d71d39..cd6d5bbb4b9d 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -72,8 +72,10 @@
#ifdef CONFIG_BINFMT_FLAT_NO_DATA_START_OFFSET
#define DATA_START_OFFSET_WORDS (0)
+#define MAX_SHARED_LIBS_UPDATE (0)
#else
#define DATA_START_OFFSET_WORDS (MAX_SHARED_LIBS)
+#define MAX_SHARED_LIBS_UPDATE (MAX_SHARED_LIBS)
#endif
struct lib_info {
@@ -880,7 +882,7 @@ static int load_flat_binary(struct linux_binprm *bprm)
return res;
/* Update data segment pointers for all libraries */
- for (i = 0; i < MAX_SHARED_LIBS; i++) {
+ for (i = 0; i < MAX_SHARED_LIBS_UPDATE; i++) {
if (!libinfo.lib_list[i].loaded)
continue;
for (j = 0; j < MAX_SHARED_LIBS; j++) {
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 498442d0c216..2e49d978f504 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1223,8 +1223,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
block_group->space_info->total_bytes -= block_group->length;
block_group->space_info->bytes_readonly -=
(block_group->length - block_group->zone_unusable);
- block_group->space_info->bytes_zone_unusable -=
- block_group->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(fs_info, block_group->space_info,
+ -block_group->zone_unusable);
block_group->space_info->disk_total -= block_group->length * factor;
spin_unlock(&block_group->space_info->lock);
@@ -1396,7 +1396,8 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
if (btrfs_is_zoned(cache->fs_info)) {
/* Migrate zone_unusable bytes to readonly */
sinfo->bytes_readonly += cache->zone_unusable;
- sinfo->bytes_zone_unusable -= cache->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo,
+ -cache->zone_unusable);
cache->zone_unusable = 0;
}
cache->ro++;
@@ -3056,9 +3057,11 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache)
if (btrfs_is_zoned(cache->fs_info)) {
/* Migrate zone_unusable bytes back */
cache->zone_unusable =
- (cache->alloc_offset - cache->used) +
+ (cache->alloc_offset - cache->used - cache->pinned -
+ cache->reserved) +
(cache->length - cache->zone_capacity);
- sinfo->bytes_zone_unusable += cache->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo,
+ cache->zone_unusable);
sinfo->bytes_readonly -= cache->zone_unusable;
}
num_bytes = cache->length - cache->reserved -
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index c8568b1a61c4..75fa563e4cac 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -459,6 +459,7 @@ struct btrfs_file_private {
void *filldir_buf;
u64 last_index;
struct extent_state *llseek_cached_state;
+ bool fsync_skip_inode_lock;
};
static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info)
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 2ac9296edccb..06a9e0542d70 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -1134,6 +1134,73 @@ btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 byt
return find_ref_head(delayed_refs, bytenr, false);
}
+static int find_comp(struct btrfs_delayed_ref_node *entry, u64 root, u64 parent)
+{
+ int type = parent ? BTRFS_SHARED_BLOCK_REF_KEY : BTRFS_TREE_BLOCK_REF_KEY;
+
+ if (type < entry->type)
+ return -1;
+ if (type > entry->type)
+ return 1;
+
+ if (type == BTRFS_TREE_BLOCK_REF_KEY) {
+ if (root < entry->ref_root)
+ return -1;
+ if (root > entry->ref_root)
+ return 1;
+ } else {
+ if (parent < entry->parent)
+ return -1;
+ if (parent > entry->parent)
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Check to see if a given root/parent reference is attached to the head. This
+ * only checks for BTRFS_ADD_DELAYED_REF references that match, as that
+ * indicates the reference exists for the given root or parent. This is for
+ * tree blocks only.
+ *
+ * @head: the head of the bytenr we're searching.
+ * @root: the root objectid of the reference if it is a normal reference.
+ * @parent: the parent if this is a shared backref.
+ */
+bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head,
+ u64 root, u64 parent)
+{
+ struct rb_node *node;
+ bool found = false;
+
+ lockdep_assert_held(&head->mutex);
+
+ spin_lock(&head->lock);
+ node = head->ref_tree.rb_root.rb_node;
+ while (node) {
+ struct btrfs_delayed_ref_node *entry;
+ int ret;
+
+ entry = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
+ ret = find_comp(entry, root, parent);
+ if (ret < 0) {
+ node = node->rb_left;
+ } else if (ret > 0) {
+ node = node->rb_right;
+ } else {
+ /*
+ * We only want to count ADD actions, as drops mean the
+ * ref doesn't exist.
+ */
+ if (entry->action == BTRFS_ADD_DELAYED_REF)
+ found = true;
+ break;
+ }
+ }
+ spin_unlock(&head->lock);
+ return found;
+}
+
void __cold btrfs_delayed_ref_exit(void)
{
kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index ef15e998be03..05f634eb472d 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -389,6 +389,8 @@ void btrfs_dec_delayed_refs_rsv_bg_updates(struct btrfs_fs_info *fs_info);
int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
enum btrfs_reserve_flush_enum flush);
bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info);
+bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head,
+ u64 root, u64 parent);
static inline u64 btrfs_delayed_ref_owner(struct btrfs_delayed_ref_node *node)
{
diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c
index f9fb2db6a1e4..67adbe9d294a 100644
--- a/fs/btrfs/direct-io.c
+++ b/fs/btrfs/direct-io.c
@@ -856,21 +856,37 @@ relock:
* So here we disable page faults in the iov_iter and then retry if we
* got -EFAULT, faulting in the pages before the retry.
*/
+again:
from->nofault = true;
dio = btrfs_dio_write(iocb, from, written);
from->nofault = false;
- /*
- * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync
- * iocb, and that needs to lock the inode. So unlock it before calling
- * iomap_dio_complete() to avoid a deadlock.
- */
- btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
-
- if (IS_ERR_OR_NULL(dio))
+ if (IS_ERR_OR_NULL(dio)) {
ret = PTR_ERR_OR_ZERO(dio);
- else
+ } else {
+ struct btrfs_file_private stack_private = { 0 };
+ struct btrfs_file_private *private;
+ const bool have_private = (file->private_data != NULL);
+
+ if (!have_private)
+ file->private_data = &stack_private;
+
+ /*
+ * If we have a synchronous write, we must make sure the fsync
+ * triggered by the iomap_dio_complete() call below doesn't
+ * deadlock on the inode lock - we are already holding it and we
+ * can't call it after unlocking because we may need to complete
+ * partial writes due to the input buffer (or parts of it) not
+ * being already faulted in.
+ */
+ private = file->private_data;
+ private->fsync_skip_inode_lock = true;
ret = iomap_dio_complete(dio);
+ private->fsync_skip_inode_lock = false;
+
+ if (!have_private)
+ file->private_data = NULL;
+ }
/* No increment (+=) because iomap returns a cumulative value. */
if (ret > 0)
@@ -897,10 +913,12 @@ relock:
} else {
fault_in_iov_iter_readable(from, left);
prev_left = left;
- goto relock;
+ goto again;
}
}
+ btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
+
/*
* If 'ret' is -ENOTBLK or we have not written all data, then it means
* we must fallback to buffered IO.
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d77498e7671c..feec49e6f9c8 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2793,7 +2793,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
readonly = true;
} else if (btrfs_is_zoned(fs_info)) {
/* Need reset before reusing in a zoned block group */
- space_info->bytes_zone_unusable += len;
+ btrfs_space_info_update_bytes_zone_unusable(fs_info, space_info,
+ len);
readonly = true;
}
spin_unlock(&cache->lock);
@@ -5471,23 +5472,62 @@ static int check_ref_exists(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytenr, u64 parent,
int level)
{
+ struct btrfs_delayed_ref_root *delayed_refs;
+ struct btrfs_delayed_ref_head *head;
struct btrfs_path *path;
struct btrfs_extent_inline_ref *iref;
int ret;
+ bool exists = false;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
-
+again:
ret = lookup_extent_backref(trans, path, &iref, bytenr,
root->fs_info->nodesize, parent,
btrfs_root_id(root), level, 0);
+ if (ret != -ENOENT) {
+ /*
+ * If we get 0 then we found our reference, return 1, else
+ * return the error if it's not -ENOENT;
+ */
+ btrfs_free_path(path);
+ return (ret < 0 ) ? ret : 1;
+ }
+
+ /*
+ * We could have a delayed ref with this reference, so look it up while
+ * we're holding the path open to make sure we don't race with the
+ * delayed ref running.
+ */
+ delayed_refs = &trans->transaction->delayed_refs;
+ spin_lock(&delayed_refs->lock);
+ head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
+ if (!head)
+ goto out;
+ if (!mutex_trylock(&head->mutex)) {
+ /*
+ * We're contended, means that the delayed ref is running, get a
+ * reference and wait for the ref head to be complete and then
+ * try again.
+ */
+ refcount_inc(&head->refs);
+ spin_unlock(&delayed_refs->lock);
+
+ btrfs_release_path(path);
+
+ mutex_lock(&head->mutex);
+ mutex_unlock(&head->mutex);
+ btrfs_put_delayed_ref_head(head);
+ goto again;
+ }
+
+ exists = btrfs_find_delayed_tree_ref(head, root->root_key.objectid, parent);
+ mutex_unlock(&head->mutex);
+out:
+ spin_unlock(&delayed_refs->lock);
btrfs_free_path(path);
- if (ret == -ENOENT)
- return 0;
- if (ret < 0)
- return ret;
- return 1;
+ return exists ? 1 : 0;
}
/*
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index aa7f8148cd0d..c73cd4f89015 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1496,6 +1496,13 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
free_extent_map(em);
em = NULL;
+ /*
+ * Although the PageDirty bit might be cleared before entering
+ * this function, subpage dirty bit is not cleared.
+ * So clear subpage dirty bit here so next time we won't submit
+ * page for range already written to disk.
+ */
+ btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize);
btrfs_set_range_writeback(inode, cur, cur + iosize - 1);
if (!PageWriteback(page)) {
btrfs_err(inode->root->fs_info,
@@ -1503,13 +1510,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
page->index, cur, end);
}
- /*
- * Although the PageDirty bit is cleared before entering this
- * function, subpage dirty bit is not cleared.
- * So clear subpage dirty bit here so next time we won't submit
- * page for range already written to disk.
- */
- btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize);
submit_extent_page(bio_ctrl, disk_bytenr, page, iosize,
cur - page_offset(page));
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 81558f90ee80..10ac5f657e38 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -664,7 +664,7 @@ static noinline int merge_extent_mapping(struct btrfs_inode *inode,
start_diff = start - em->start;
em->start = start;
em->len = end - start;
- if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE && !extent_map_is_compressed(em))
+ if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE)
em->offset += start_diff;
return add_extent_mapping(inode, em, 0);
}
@@ -1147,8 +1147,7 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
return 0;
/*
- * We want to be fast because we can be called from any path trying to
- * allocate memory, so if the lock is busy we don't want to spend time
+ * We want to be fast so if the lock is busy we don't want to spend time
* waiting for it - either some task is about to do IO for the inode or
* we may have another task shrinking extent maps, here in this code, so
* skip this inode.
@@ -1191,9 +1190,7 @@ next:
/*
* Stop if we need to reschedule or there's contention on the
* lock. This is to avoid slowing other tasks trying to take the
- * lock and because the shrinker might be called during a memory
- * allocation path and we want to avoid taking a very long time
- * and slowing down all sorts of tasks.
+ * lock.
*/
if (need_resched() || rwlock_needbreak(&tree->lock))
break;
@@ -1222,12 +1219,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
if (ctx->scanned >= ctx->nr_to_scan)
break;
- /*
- * We may be called from memory allocation paths, so we don't
- * want to take too much time and slowdown tasks.
- */
- if (need_resched())
- break;
+ cond_resched();
inode = btrfs_find_first_inode(root, min_ino);
}
@@ -1285,14 +1277,12 @@ long btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan)
ctx.last_ino);
}
- /*
- * We may be called from memory allocation paths, so we don't want to
- * take too much time and slowdown tasks, so stop if we need reschedule.
- */
- while (ctx.scanned < ctx.nr_to_scan && !need_resched()) {
+ while (ctx.scanned < ctx.nr_to_scan) {
struct btrfs_root *root;
unsigned long count;
+ cond_resched();
+
spin_lock(&fs_info->fs_roots_radix_lock);
count = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
(void **)&root,
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 21381de906f6..9914419f3b7d 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1603,6 +1603,7 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
*/
int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
+ struct btrfs_file_private *private = file->private_data;
struct dentry *dentry = file_dentry(file);
struct btrfs_inode *inode = BTRFS_I(d_inode(dentry));
struct btrfs_root *root = inode->root;
@@ -1612,6 +1613,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
int ret = 0, err;
u64 len;
bool full_sync;
+ const bool skip_ilock = (private ? private->fsync_skip_inode_lock : false);
trace_btrfs_sync_file(file, datasync);
@@ -1639,7 +1641,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (ret)
goto out;
- btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);
+ if (skip_ilock)
+ down_write(&inode->i_mmap_lock);
+ else
+ btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);
atomic_inc(&root->log_batch);
@@ -1663,7 +1668,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
*/
ret = start_ordered_ops(inode, start, end);
if (ret) {
- btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
+ if (skip_ilock)
+ up_write(&inode->i_mmap_lock);
+ else
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
goto out;
}
@@ -1788,7 +1796,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* file again, but that will end up using the synchronization
* inside btrfs_sync_log to keep things safe.
*/
- btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
+ if (skip_ilock)
+ up_write(&inode->i_mmap_lock);
+ else
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
if (ret == BTRFS_NO_LOG_SYNC) {
ret = btrfs_end_transaction(trans);
@@ -1857,7 +1868,10 @@ out:
out_release_extents:
btrfs_release_log_ctx_extents(&ctx);
- btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
+ if (skip_ilock)
+ up_write(&inode->i_mmap_lock);
+ else
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
goto out;
}
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 3f9b7507543a..f5996a43db24 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2723,8 +2723,10 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
* If the block group is read-only, we should account freed space into
* bytes_readonly.
*/
- if (!block_group->ro)
+ if (!block_group->ro) {
block_group->zone_unusable += to_unusable;
+ WARN_ON(block_group->zone_unusable > block_group->length);
+ }
spin_unlock(&ctl->tree_lock);
if (!used) {
spin_lock(&block_group->lock);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 01eab6955647..333b0e8587a2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -714,8 +714,9 @@ out:
return ret;
}
-static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 offset,
- u64 end,
+static noinline int cow_file_range_inline(struct btrfs_inode *inode,
+ struct page *locked_page,
+ u64 offset, u64 end,
size_t compressed_size,
int compress_type,
struct folio *compressed_folio,
@@ -739,7 +740,10 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 offset,
return ret;
}
- extent_clear_unlock_delalloc(inode, offset, end, NULL, &cached,
+ if (ret == 0)
+ locked_page = NULL;
+
+ extent_clear_unlock_delalloc(inode, offset, end, locked_page, &cached,
clear_flags,
PAGE_UNLOCK | PAGE_START_WRITEBACK |
PAGE_END_WRITEBACK);
@@ -1043,10 +1047,10 @@ again:
* extent for the subpage case.
*/
if (total_in < actual_end)
- ret = cow_file_range_inline(inode, start, end, 0,
+ ret = cow_file_range_inline(inode, NULL, start, end, 0,
BTRFS_COMPRESS_NONE, NULL, false);
else
- ret = cow_file_range_inline(inode, start, end, total_compressed,
+ ret = cow_file_range_inline(inode, NULL, start, end, total_compressed,
compress_type, folios[0], false);
if (ret <= 0) {
if (ret < 0)
@@ -1359,7 +1363,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
if (!no_inline) {
/* lets try to make an inline extent */
- ret = cow_file_range_inline(inode, start, end, 0,
+ ret = cow_file_range_inline(inode, locked_page, start, end, 0,
BTRFS_COMPRESS_NONE, NULL, false);
if (ret <= 0) {
/*
@@ -1581,6 +1585,7 @@ out_unlock:
locked_page, &cached,
clear_bits,
page_ops);
+ btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL);
start += cur_alloc_size;
}
@@ -1594,6 +1599,7 @@ out_unlock:
clear_bits |= EXTENT_CLEAR_DATA_RESV;
extent_clear_unlock_delalloc(inode, start, end, locked_page,
&cached, clear_bits, page_ops);
+ btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL);
}
return ret;
}
@@ -2255,6 +2261,7 @@ error:
EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
PAGE_START_WRITEBACK |
PAGE_END_WRITEBACK);
+ btrfs_qgroup_free_data(inode, NULL, cur_offset, end - cur_offset + 1, NULL);
}
btrfs_free_path(path);
return ret;
@@ -5660,7 +5667,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
struct inode *inode;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_root *sub_root = root;
- struct btrfs_key location;
+ struct btrfs_key location = { 0 };
u8 di_type = 0;
int ret = 0;
@@ -7198,6 +7205,12 @@ static void wait_subpage_spinlock(struct page *page)
spin_unlock_irq(&subpage->lock);
}
+static int btrfs_launder_folio(struct folio *folio)
+{
+ return btrfs_qgroup_free_data(folio_to_inode(folio), NULL, folio_pos(folio),
+ PAGE_SIZE, NULL);
+}
+
static bool __btrfs_release_folio(struct folio *folio, gfp_t gfp_flags)
{
if (try_release_extent_mapping(&folio->page, gfp_flags)) {
@@ -10133,6 +10146,7 @@ static const struct address_space_operations btrfs_aops = {
.writepages = btrfs_writepages,
.readahead = btrfs_readahead,
.invalidate_folio = btrfs_invalidate_folio,
+ .launder_folio = btrfs_launder_folio,
.release_folio = btrfs_release_folio,
.migrate_folio = btrfs_migrate_folio,
.dirty_folio = filemap_dirty_folio,
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 32dcea662da3..fc821aa446f0 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -14,7 +14,7 @@
struct root_name_map {
u64 id;
- char name[16];
+ const char *name;
};
static const struct root_name_map root_map[] = {
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 14a8d7100018..0de9162ff481 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1648,14 +1648,20 @@ static void scrub_reset_stripe(struct scrub_stripe *stripe)
}
}
+static u32 stripe_length(const struct scrub_stripe *stripe)
+{
+ ASSERT(stripe->bg);
+
+ return min(BTRFS_STRIPE_LEN,
+ stripe->bg->start + stripe->bg->length - stripe->logical);
+}
+
static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
struct scrub_stripe *stripe)
{
struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
struct btrfs_bio *bbio = NULL;
- unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
- stripe->bg->length - stripe->logical) >>
- fs_info->sectorsize_bits;
+ unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits;
u64 stripe_len = BTRFS_STRIPE_LEN;
int mirror = stripe->mirror_num;
int i;
@@ -1729,9 +1735,7 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
{
struct btrfs_fs_info *fs_info = sctx->fs_info;
struct btrfs_bio *bbio;
- unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
- stripe->bg->length - stripe->logical) >>
- fs_info->sectorsize_bits;
+ unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits;
int mirror = stripe->mirror_num;
ASSERT(stripe->bg);
@@ -1871,6 +1875,9 @@ static int flush_scrub_stripes(struct scrub_ctx *sctx)
stripe = &sctx->stripes[i];
wait_scrub_stripe_io(stripe);
+ spin_lock(&sctx->stat_lock);
+ sctx->stat.last_physical = stripe->physical + stripe_length(stripe);
+ spin_unlock(&sctx->stat_lock);
scrub_reset_stripe(stripe);
}
out:
@@ -2139,7 +2146,9 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
cur_physical, &found_logical);
if (ret > 0) {
/* No more extent, just update the accounting */
+ spin_lock(&sctx->stat_lock);
sctx->stat.last_physical = physical + logical_length;
+ spin_unlock(&sctx->stat_lock);
ret = 0;
break;
}
@@ -2336,6 +2345,10 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
stripe_logical += chunk_logical;
ret = scrub_raid56_parity_stripe(sctx, scrub_dev, bg,
map, stripe_logical);
+ spin_lock(&sctx->stat_lock);
+ sctx->stat.last_physical = min(physical + BTRFS_STRIPE_LEN,
+ physical_end);
+ spin_unlock(&sctx->stat_lock);
if (ret)
goto out;
goto next;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 4ca711a773ef..7fc692fc76e1 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -6157,25 +6157,51 @@ static int send_write_or_clone(struct send_ctx *sctx,
u64 offset = key->offset;
u64 end;
u64 bs = sctx->send_root->fs_info->sectorsize;
+ struct btrfs_file_extent_item *ei;
+ u64 disk_byte;
+ u64 data_offset;
+ u64 num_bytes;
+ struct btrfs_inode_info info = { 0 };
end = min_t(u64, btrfs_file_extent_end(path), sctx->cur_inode_size);
if (offset >= end)
return 0;
- if (clone_root && IS_ALIGNED(end, bs)) {
- struct btrfs_file_extent_item *ei;
- u64 disk_byte;
- u64 data_offset;
+ num_bytes = end - offset;
- ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
- disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei);
- data_offset = btrfs_file_extent_offset(path->nodes[0], ei);
- ret = clone_range(sctx, path, clone_root, disk_byte,
- data_offset, offset, end - offset);
- } else {
- ret = send_extent_data(sctx, path, offset, end - offset);
- }
+ if (!clone_root)
+ goto write_data;
+
+ if (IS_ALIGNED(end, bs))
+ goto clone_data;
+
+ /*
+ * If the extent end is not aligned, we can clone if the extent ends at
+ * the i_size of the inode and the clone range ends at the i_size of the
+ * source inode, otherwise the clone operation fails with -EINVAL.
+ */
+ if (end != sctx->cur_inode_size)
+ goto write_data;
+
+ ret = get_inode_info(clone_root->root, clone_root->ino, &info);
+ if (ret < 0)
+ return ret;
+
+ if (clone_root->offset + num_bytes == info.size)
+ goto clone_data;
+
+write_data:
+ ret = send_extent_data(sctx, path, offset, num_bytes);
+ sctx->cur_inode_next_write_offset = end;
+ return ret;
+
+clone_data:
+ ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_file_extent_item);
+ disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei);
+ data_offset = btrfs_file_extent_offset(path->nodes[0], ei);
+ ret = clone_range(sctx, path, clone_root, disk_byte, data_offset, offset,
+ num_bytes);
sctx->cur_inode_next_write_offset = end;
return ret;
}
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 9ac94d3119e8..68e14fd48638 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -316,7 +316,7 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info,
found->bytes_used += block_group->used;
found->disk_used += block_group->used * factor;
found->bytes_readonly += block_group->bytes_super;
- found->bytes_zone_unusable += block_group->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(info, found, block_group->zone_unusable);
if (block_group->length > 0)
found->full = 0;
btrfs_try_granting_tickets(info, found);
@@ -583,8 +583,7 @@ again:
spin_lock(&cache->lock);
avail = cache->length - cache->used - cache->pinned -
- cache->reserved - cache->delalloc_bytes -
- cache->bytes_super - cache->zone_unusable;
+ cache->reserved - cache->bytes_super - cache->zone_unusable;
btrfs_info(fs_info,
"block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %llu delalloc %llu super %llu zone_unusable (%llu bytes available) %s",
cache->start, cache->length, cache->used, cache->pinned,
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 4db8a0267c16..88b44221ce97 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -249,6 +249,7 @@ btrfs_space_info_update_##name(struct btrfs_fs_info *fs_info, \
DECLARE_SPACE_INFO_UPDATE(bytes_may_use, "space_info");
DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned");
+DECLARE_SPACE_INFO_UPDATE(bytes_zone_unusable, "zone_unusable");
int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 08d33cb372fb..11044e9e2cb1 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -28,6 +28,7 @@
#include <linux/btrfs.h>
#include <linux/security.h>
#include <linux/fs_parser.h>
+#include <linux/swap.h>
#include "messages.h"
#include "delayed-inode.h"
#include "ctree.h"
@@ -683,8 +684,11 @@ bool btrfs_check_options(const struct btrfs_fs_info *info,
ret = false;
if (!test_bit(BTRFS_FS_STATE_REMOUNTING, &info->fs_state)) {
- if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE))
+ if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE)) {
btrfs_info(info, "disk space caching is enabled");
+ btrfs_warn(info,
+"space cache v1 is being deprecated and will be removed in a future release, please use -o space_cache=v2");
+ }
if (btrfs_raw_test_opt(*mount_opt, FREE_SPACE_TREE))
btrfs_info(info, "using free-space-tree");
}
@@ -2406,6 +2410,15 @@ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_cont
const long nr_to_scan = min_t(unsigned long, LONG_MAX, sc->nr_to_scan);
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+ /*
+ * We may be called from any task trying to allocate memory and we don't
+ * want to slow it down with scanning and dropping extent maps. It would
+ * also cause heavy lock contention if many tasks concurrently enter
+ * here. Therefore only allow kswapd tasks to scan and drop extent maps.
+ */
+ if (!current_is_kswapd())
+ return 0;
+
return btrfs_free_extent_maps(fs_info, nr_to_scan);
}
diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c
index ebec4ab361b8..56e61ac1cc64 100644
--- a/fs/btrfs/tests/extent-map-tests.c
+++ b/fs/btrfs/tests/extent-map-tests.c
@@ -900,6 +900,102 @@ out:
return ret;
}
+/*
+ * Test a regression for compressed extent map adjustment when we attempt to
+ * add an extent map that is partially overlapped by another existing extent
+ * map. The resulting extent map offset was left unchanged despite having
+ * incremented its start offset.
+ */
+static int test_case_8(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode)
+{
+ struct extent_map_tree *em_tree = &inode->extent_tree;
+ struct extent_map *em;
+ int ret;
+ int ret2;
+
+ em = alloc_extent_map();
+ if (!em) {
+ test_std_err(TEST_ALLOC_EXTENT_MAP);
+ return -ENOMEM;
+ }
+
+ /* Compressed extent for the file range [120K, 128K). */
+ em->start = SZ_1K * 120;
+ em->len = SZ_8K;
+ em->disk_num_bytes = SZ_4K;
+ em->ram_bytes = SZ_8K;
+ em->flags |= EXTENT_FLAG_COMPRESS_ZLIB;
+ write_lock(&em_tree->lock);
+ ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
+ write_unlock(&em_tree->lock);
+ free_extent_map(em);
+ if (ret < 0) {
+ test_err("couldn't add extent map for range [120K, 128K)");
+ goto out;
+ }
+
+ em = alloc_extent_map();
+ if (!em) {
+ test_std_err(TEST_ALLOC_EXTENT_MAP);
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /*
+ * Compressed extent for the file range [108K, 144K), which overlaps
+ * with the [120K, 128K) we previously inserted.
+ */
+ em->start = SZ_1K * 108;
+ em->len = SZ_1K * 36;
+ em->disk_num_bytes = SZ_4K;
+ em->ram_bytes = SZ_1K * 36;
+ em->flags |= EXTENT_FLAG_COMPRESS_ZLIB;
+
+ /*
+ * Try to add the extent map but with a search range of [140K, 144K),
+ * this should succeed and adjust the extent map to the range
+ * [128K, 144K), with a length of 16K and an offset of 20K.
+ *
+ * This simulates a scenario where in the subvolume tree of an inode we
+ * have a compressed file extent item for the range [108K, 144K) and we
+ * have an overlapping compressed extent map for the range [120K, 128K),
+ * which was created by an encoded write, but its ordered extent was not
+ * yet completed, so the subvolume tree doesn't have yet the file extent
+ * item for that range - we only have the extent map in the inode's
+ * extent map tree.
+ */
+ write_lock(&em_tree->lock);
+ ret = btrfs_add_extent_mapping(inode, &em, SZ_1K * 140, SZ_4K);
+ write_unlock(&em_tree->lock);
+ free_extent_map(em);
+ if (ret < 0) {
+ test_err("couldn't add extent map for range [108K, 144K)");
+ goto out;
+ }
+
+ if (em->start != SZ_128K) {
+ test_err("unexpected extent map start %llu (should be 128K)", em->start);
+ ret = -EINVAL;
+ goto out;
+ }
+ if (em->len != SZ_16K) {
+ test_err("unexpected extent map length %llu (should be 16K)", em->len);
+ ret = -EINVAL;
+ goto out;
+ }
+ if (em->offset != SZ_1K * 20) {
+ test_err("unexpected extent map offset %llu (should be 20K)", em->offset);
+ ret = -EINVAL;
+ goto out;
+ }
+out:
+ ret2 = free_extent_map_tree(inode);
+ if (ret == 0)
+ ret = ret2;
+
+ return ret;
+}
+
struct rmap_test_vector {
u64 raid_type;
u64 physical_start;
@@ -1078,6 +1174,9 @@ int btrfs_test_extent_map(void)
ret = test_case_7(fs_info, BTRFS_I(inode));
if (ret)
goto out;
+ ret = test_case_8(fs_info, BTRFS_I(inode));
+ if (ret)
+ goto out;
test_msg("running rmap tests");
for (i = 0; i < ARRAY_SIZE(rmap_tests); i++) {
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 6388786fd8b5..6f1e2f2215d9 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -569,9 +569,10 @@ static int check_dir_item(struct extent_buffer *leaf,
/* dir type check */
dir_type = btrfs_dir_ftype(leaf, di);
- if (unlikely(dir_type >= BTRFS_FT_MAX)) {
+ if (unlikely(dir_type <= BTRFS_FT_UNKNOWN ||
+ dir_type >= BTRFS_FT_MAX)) {
dir_item_err(leaf, slot,
- "invalid dir item type, have %u expect [0, %u)",
+ "invalid dir item type, have %u expect (0, %u)",
dir_type, BTRFS_FT_MAX);
return -EUCLEAN;
}
@@ -634,7 +635,7 @@ static int check_dir_item(struct extent_buffer *leaf,
*/
if (key->type == BTRFS_DIR_ITEM_KEY ||
key->type == BTRFS_XATTR_ITEM_KEY) {
- char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
+ char namebuf[MAX(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
read_extent_buffer(leaf, namebuf,
(unsigned long)(di + 1), name_len);
@@ -1289,6 +1290,19 @@ static void extent_err(const struct extent_buffer *eb, int slot,
va_end(args);
}
+static bool is_valid_dref_root(u64 rootid)
+{
+ /*
+ * The following tree root objectids are allowed to have a data backref:
+ * - subvolume trees
+ * - data reloc tree
+ * - tree root
+ * For v1 space cache
+ */
+ return is_fstree(rootid) || rootid == BTRFS_DATA_RELOC_TREE_OBJECTID ||
+ rootid == BTRFS_ROOT_TREE_OBJECTID;
+}
+
static int check_extent_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot,
struct btrfs_key *prev_key)
@@ -1441,6 +1455,8 @@ static int check_extent_item(struct extent_buffer *leaf,
struct btrfs_extent_data_ref *dref;
struct btrfs_shared_data_ref *sref;
u64 seq;
+ u64 dref_root;
+ u64 dref_objectid;
u64 dref_offset;
u64 inline_offset;
u8 inline_type;
@@ -1484,11 +1500,26 @@ static int check_extent_item(struct extent_buffer *leaf,
*/
case BTRFS_EXTENT_DATA_REF_KEY:
dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+ dref_root = btrfs_extent_data_ref_root(leaf, dref);
+ dref_objectid = btrfs_extent_data_ref_objectid(leaf, dref);
dref_offset = btrfs_extent_data_ref_offset(leaf, dref);
seq = hash_extent_data_ref(
btrfs_extent_data_ref_root(leaf, dref),
btrfs_extent_data_ref_objectid(leaf, dref),
btrfs_extent_data_ref_offset(leaf, dref));
+ if (unlikely(!is_valid_dref_root(dref_root))) {
+ extent_err(leaf, slot,
+ "invalid data ref root value %llu",
+ dref_root);
+ return -EUCLEAN;
+ }
+ if (unlikely(dref_objectid < BTRFS_FIRST_FREE_OBJECTID ||
+ dref_objectid > BTRFS_LAST_FREE_OBJECTID)) {
+ extent_err(leaf, slot,
+ "invalid data ref objectid value %llu",
+ dref_root);
+ return -EUCLEAN;
+ }
if (unlikely(!IS_ALIGNED(dref_offset,
fs_info->sectorsize))) {
extent_err(leaf, slot,
@@ -1627,6 +1658,8 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
return -EUCLEAN;
}
for (; ptr < end; ptr += sizeof(*dref)) {
+ u64 root;
+ u64 objectid;
u64 offset;
/*
@@ -1634,7 +1667,22 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
* overflow from the leaf due to hash collisions.
*/
dref = (struct btrfs_extent_data_ref *)ptr;
+ root = btrfs_extent_data_ref_root(leaf, dref);
+ objectid = btrfs_extent_data_ref_objectid(leaf, dref);
offset = btrfs_extent_data_ref_offset(leaf, dref);
+ if (unlikely(!is_valid_dref_root(root))) {
+ extent_err(leaf, slot,
+ "invalid extent data backref root value %llu",
+ root);
+ return -EUCLEAN;
+ }
+ if (unlikely(objectid < BTRFS_FIRST_FREE_OBJECTID ||
+ objectid > BTRFS_LAST_FREE_OBJECTID)) {
+ extent_err(leaf, slot,
+ "invalid extent data backref objectid value %llu",
+ root);
+ return -EUCLEAN;
+ }
if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) {
extent_err(leaf, slot,
"invalid extent data backref offset, have %llu expect aligned to %u",
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 8c16bc5250ef..c4744a02db75 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -246,7 +246,8 @@ static void finish_netfs_read(struct ceph_osd_request *req)
if (err >= 0) {
if (sparse && err > 0)
err = ceph_sparse_ext_map_end(op);
- if (err < subreq->len)
+ if (err < subreq->len &&
+ subreq->rreq->origin != NETFS_DIO_READ)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
if (IS_ENCRYPTED(inode) && err > 0) {
err = ceph_fscrypt_decrypt_extents(inode,
@@ -282,7 +283,8 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
size_t len;
int mode;
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
if (subreq->start >= inode->i_size)
@@ -424,6 +426,9 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
struct ceph_netfs_request_data *priv;
int ret = 0;
+ /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
+ __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags);
+
if (rreq->origin != NETFS_READAHEAD)
return 0;
@@ -498,6 +503,11 @@ const struct netfs_request_ops ceph_netfs_ops = {
};
#ifdef CONFIG_CEPH_FSCACHE
+static void ceph_set_page_fscache(struct page *page)
+{
+ folio_start_private_2(page_folio(page)); /* [DEPRECATED] */
+}
+
static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
{
struct inode *inode = priv;
@@ -515,6 +525,10 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b
ceph_fscache_write_terminated, inode, true, caching);
}
#else
+static inline void ceph_set_page_fscache(struct page *page)
+{
+}
+
static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching)
{
}
@@ -706,6 +720,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
len = wlen;
set_page_writeback(page);
+ if (caching)
+ ceph_set_page_fscache(page);
ceph_fscache_write_to_cache(inode, page_off, len, caching);
if (IS_ENCRYPTED(inode)) {
@@ -789,6 +805,8 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc)
return AOP_WRITEPAGE_ACTIVATE;
}
+ folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
+
err = writepage_nounlock(page, wbc);
if (err == -ERESTARTSYS) {
/* direct memory reclaimer was killed by SIGKILL. return 0
@@ -1062,7 +1080,8 @@ get_more_pages:
unlock_page(page);
break;
}
- if (PageWriteback(page)) {
+ if (PageWriteback(page) ||
+ PagePrivate2(page) /* [DEPRECATED] */) {
if (wbc->sync_mode == WB_SYNC_NONE) {
doutc(cl, "%p under writeback\n", page);
unlock_page(page);
@@ -1070,6 +1089,7 @@ get_more_pages:
}
doutc(cl, "waiting on writeback %p\n", page);
wait_on_page_writeback(page);
+ folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
}
if (!clear_page_dirty_for_io(page)) {
@@ -1254,6 +1274,8 @@ new_request:
}
set_page_writeback(page);
+ if (caching)
+ ceph_set_page_fscache(page);
len += thp_size(page);
}
ceph_fscache_write_to_cache(inode, offset, len, caching);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index e98aa8219303..808c9c048276 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2016,6 +2016,8 @@ bool __ceph_should_report_size(struct ceph_inode_info *ci)
* CHECK_CAPS_AUTHONLY - we should only check the auth cap
* CHECK_CAPS_FLUSH - we should flush any dirty caps immediately, without
* further delay.
+ * CHECK_CAPS_FLUSH_FORCE - we should flush any caps immediately, without
+ * further delay.
*/
void ceph_check_caps(struct ceph_inode_info *ci, int flags)
{
@@ -2097,7 +2099,7 @@ retry:
}
doutc(cl, "%p %llx.%llx file_want %s used %s dirty %s "
- "flushing %s issued %s revoking %s retain %s %s%s%s\n",
+ "flushing %s issued %s revoking %s retain %s %s%s%s%s\n",
inode, ceph_vinop(inode), ceph_cap_string(file_wanted),
ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps),
ceph_cap_string(ci->i_flushing_caps),
@@ -2105,7 +2107,8 @@ retry:
ceph_cap_string(retain),
(flags & CHECK_CAPS_AUTHONLY) ? " AUTHONLY" : "",
(flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "",
- (flags & CHECK_CAPS_NOINVAL) ? " NOINVAL" : "");
+ (flags & CHECK_CAPS_NOINVAL) ? " NOINVAL" : "",
+ (flags & CHECK_CAPS_FLUSH_FORCE) ? " FLUSH_FORCE" : "");
/*
* If we no longer need to hold onto old our caps, and we may
@@ -2180,6 +2183,11 @@ retry:
queue_writeback = true;
}
+ if (flags & CHECK_CAPS_FLUSH_FORCE) {
+ doutc(cl, "force to flush caps\n");
+ goto ack;
+ }
+
if (cap == ci->i_auth_cap &&
(cap->issued & CEPH_CAP_FILE_WR)) {
/* request larger max_size from MDS? */
@@ -3510,6 +3518,8 @@ static void handle_cap_grant(struct inode *inode,
bool queue_invalidate = false;
bool deleted_inode = false;
bool fill_inline = false;
+ bool revoke_wait = false;
+ int flags = 0;
/*
* If there is at least one crypto block then we'll trust
@@ -3705,16 +3715,18 @@ static void handle_cap_grant(struct inode *inode,
ceph_cap_string(cap->issued), ceph_cap_string(newcaps),
ceph_cap_string(revoking));
if (S_ISREG(inode->i_mode) &&
- (revoking & used & CEPH_CAP_FILE_BUFFER))
+ (revoking & used & CEPH_CAP_FILE_BUFFER)) {
writeback = true; /* initiate writeback; will delay ack */
- else if (queue_invalidate &&
+ revoke_wait = true;
+ } else if (queue_invalidate &&
revoking == CEPH_CAP_FILE_CACHE &&
- (newcaps & CEPH_CAP_FILE_LAZYIO) == 0)
- ; /* do nothing yet, invalidation will be queued */
- else if (cap == ci->i_auth_cap)
+ (newcaps & CEPH_CAP_FILE_LAZYIO) == 0) {
+ revoke_wait = true; /* do nothing yet, invalidation will be queued */
+ } else if (cap == ci->i_auth_cap) {
check_caps = 1; /* check auth cap only */
- else
+ } else {
check_caps = 2; /* check all caps */
+ }
/* If there is new caps, try to wake up the waiters */
if (~cap->issued & newcaps)
wake = true;
@@ -3741,8 +3753,9 @@ static void handle_cap_grant(struct inode *inode,
BUG_ON(cap->issued & ~cap->implemented);
/* don't let check_caps skip sending a response to MDS for revoke msgs */
- if (le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) {
+ if (!revoke_wait && le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) {
cap->mds_wanted = 0;
+ flags |= CHECK_CAPS_FLUSH_FORCE;
if (cap == ci->i_auth_cap)
check_caps = 1; /* check auth cap only */
else
@@ -3798,9 +3811,9 @@ static void handle_cap_grant(struct inode *inode,
mutex_unlock(&session->s_mutex);
if (check_caps == 1)
- ceph_check_caps(ci, CHECK_CAPS_AUTHONLY | CHECK_CAPS_NOINVAL);
+ ceph_check_caps(ci, flags | CHECK_CAPS_AUTHONLY | CHECK_CAPS_NOINVAL);
else if (check_caps == 2)
- ceph_check_caps(ci, CHECK_CAPS_NOINVAL);
+ ceph_check_caps(ci, flags | CHECK_CAPS_NOINVAL);
}
/*
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8f8de8f33abb..71cd70514efa 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -577,8 +577,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
/* Set parameters for the netfs library */
netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false);
- /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
- __set_bit(NETFS_ICTX_USE_PGPRIV2, &ci->netfs.flags);
spin_lock_init(&ci->i_ceph_lock);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b63b4cd9b5b6..6e817bf1337c 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -200,9 +200,10 @@ struct ceph_cap {
struct list_head caps_item;
};
-#define CHECK_CAPS_AUTHONLY 1 /* only check auth cap */
-#define CHECK_CAPS_FLUSH 2 /* flush any dirty caps */
-#define CHECK_CAPS_NOINVAL 4 /* don't invalidate pagecache */
+#define CHECK_CAPS_AUTHONLY 1 /* only check auth cap */
+#define CHECK_CAPS_FLUSH 2 /* flush any dirty caps */
+#define CHECK_CAPS_NOINVAL 4 /* don't invalidate pagecache */
+#define CHECK_CAPS_FLUSH_FORCE 8 /* force flush any caps */
struct ceph_cap_flush {
u64 tid;
diff --git a/fs/exec.c b/fs/exec.c
index a126e3d1cacb..50e76cc633c4 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1692,6 +1692,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
unsigned int mode;
vfsuid_t vfsuid;
vfsgid_t vfsgid;
+ int err;
if (!mnt_may_suid(file->f_path.mnt))
return;
@@ -1708,12 +1709,17 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
/* Be careful if suid/sgid is set */
inode_lock(inode);
- /* reload atomically mode/uid/gid now that lock held */
+ /* Atomically reload and check mode/uid/gid now that lock held. */
mode = inode->i_mode;
vfsuid = i_uid_into_vfsuid(idmap, inode);
vfsgid = i_gid_into_vfsgid(idmap, inode);
+ err = inode_permission(idmap, inode, MAY_EXEC);
inode_unlock(inode);
+ /* Did the exec bit vanish out from under us? Give up. */
+ if (err)
+ return;
+
/* We ignore suid/sgid if there are no mappings for them in the ns */
if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) ||
!vfsgid_has_mapping(bprm->cred->user_ns, vfsgid))
diff --git a/fs/file.c b/fs/file.c
index a3b72aa64f11..655338effe9c 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -46,27 +46,23 @@ static void free_fdtable_rcu(struct rcu_head *rcu)
#define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr))
#define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long))
+#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds
/*
* Copy 'count' fd bits from the old table to the new table and clear the extra
* space if any. This does not copy the file pointers. Called with the files
* spinlock held for write.
*/
-static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
- unsigned int count)
+static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
+ unsigned int copy_words)
{
- unsigned int cpy, set;
-
- cpy = count / BITS_PER_BYTE;
- set = (nfdt->max_fds - count) / BITS_PER_BYTE;
- memcpy(nfdt->open_fds, ofdt->open_fds, cpy);
- memset((char *)nfdt->open_fds + cpy, 0, set);
- memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy);
- memset((char *)nfdt->close_on_exec + cpy, 0, set);
-
- cpy = BITBIT_SIZE(count);
- set = BITBIT_SIZE(nfdt->max_fds) - cpy;
- memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy);
- memset((char *)nfdt->full_fds_bits + cpy, 0, set);
+ unsigned int nwords = fdt_words(nfdt);
+
+ bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds,
+ copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
+ bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec,
+ copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
+ bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits,
+ copy_words, nwords);
}
/*
@@ -84,7 +80,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
memcpy(nfdt->fd, ofdt->fd, cpy);
memset((char *)nfdt->fd + cpy, 0, set);
- copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds);
+ copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt));
}
/*
@@ -379,7 +375,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
open_files = sane_fdtable_size(old_fdt, max_fds);
}
- copy_fd_bitmaps(new_fdt, old_fdt, open_files);
+ copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG);
old_fds = old_fdt->fd;
new_fds = new_fdt->fd;
@@ -1248,6 +1244,7 @@ __releases(&files->file_lock)
* tables and this condition does not arise without those.
*/
fdt = files_fdtable(files);
+ fd = array_index_nospec(fd, fdt->max_fds);
tofree = fdt->fd[fd];
if (!tofree && fd_is_open(fd, fdt))
goto Ebusy;
diff --git a/fs/inode.c b/fs/inode.c
index 86670941884b..10c4619faeef 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -488,6 +488,39 @@ static void inode_lru_list_del(struct inode *inode)
this_cpu_dec(nr_unused);
}
+static void inode_pin_lru_isolating(struct inode *inode)
+{
+ lockdep_assert_held(&inode->i_lock);
+ WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE));
+ inode->i_state |= I_LRU_ISOLATING;
+}
+
+static void inode_unpin_lru_isolating(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ WARN_ON(!(inode->i_state & I_LRU_ISOLATING));
+ inode->i_state &= ~I_LRU_ISOLATING;
+ smp_mb();
+ wake_up_bit(&inode->i_state, __I_LRU_ISOLATING);
+ spin_unlock(&inode->i_lock);
+}
+
+static void inode_wait_for_lru_isolating(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ if (inode->i_state & I_LRU_ISOLATING) {
+ DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING);
+ wait_queue_head_t *wqh;
+
+ wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING);
+ spin_unlock(&inode->i_lock);
+ __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE);
+ spin_lock(&inode->i_lock);
+ WARN_ON(inode->i_state & I_LRU_ISOLATING);
+ }
+ spin_unlock(&inode->i_lock);
+}
+
/**
* inode_sb_list_add - add inode to the superblock list of inodes
* @inode: inode to add
@@ -657,6 +690,8 @@ static void evict(struct inode *inode)
inode_sb_list_del(inode);
+ inode_wait_for_lru_isolating(inode);
+
/*
* Wait for flusher thread to be done with the inode so that filesystem
* does not start destroying it while writeback is still running. Since
@@ -855,7 +890,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
* be under pressure before the cache inside the highmem zone.
*/
if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) {
- __iget(inode);
+ inode_pin_lru_isolating(inode);
spin_unlock(&inode->i_lock);
spin_unlock(lru_lock);
if (remove_inode_buffers(inode)) {
@@ -867,7 +902,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
__count_vm_events(PGINODESTEAL, reap);
mm_account_reclaimed_pages(reap);
}
- iput(inode);
+ inode_unpin_lru_isolating(inode);
spin_lock(lru_lock);
return LRU_RETRY;
}
diff --git a/fs/libfs.c b/fs/libfs.c
index 8aa34870449f..02602d00939e 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -450,6 +450,14 @@ void simple_offset_destroy(struct offset_ctx *octx)
mtree_destroy(&octx->mt);
}
+static int offset_dir_open(struct inode *inode, struct file *file)
+{
+ struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode);
+
+ file->private_data = (void *)ctx->next_offset;
+ return 0;
+}
+
/**
* offset_dir_llseek - Advance the read position of a directory descriptor
* @file: an open directory whose position is to be updated
@@ -463,6 +471,9 @@ void simple_offset_destroy(struct offset_ctx *octx)
*/
static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
{
+ struct inode *inode = file->f_inode;
+ struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode);
+
switch (whence) {
case SEEK_CUR:
offset += file->f_pos;
@@ -476,7 +487,8 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
}
/* In this case, ->private_data is protected by f_pos_lock */
- file->private_data = NULL;
+ if (!offset)
+ file->private_data = (void *)ctx->next_offset;
return vfs_setpos(file, offset, LONG_MAX);
}
@@ -507,7 +519,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
inode->i_ino, fs_umode_to_dtype(inode->i_mode));
}
-static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
+static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index)
{
struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode);
struct dentry *dentry;
@@ -515,17 +527,21 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
while (true) {
dentry = offset_find_next(octx, ctx->pos);
if (!dentry)
- return ERR_PTR(-ENOENT);
+ return;
+
+ if (dentry2offset(dentry) >= last_index) {
+ dput(dentry);
+ return;
+ }
if (!offset_dir_emit(ctx, dentry)) {
dput(dentry);
- break;
+ return;
}
ctx->pos = dentry2offset(dentry) + 1;
dput(dentry);
}
- return NULL;
}
/**
@@ -552,22 +568,19 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
static int offset_readdir(struct file *file, struct dir_context *ctx)
{
struct dentry *dir = file->f_path.dentry;
+ long last_index = (long)file->private_data;
lockdep_assert_held(&d_inode(dir)->i_rwsem);
if (!dir_emit_dots(file, ctx))
return 0;
- /* In this case, ->private_data is protected by f_pos_lock */
- if (ctx->pos == DIR_OFFSET_MIN)
- file->private_data = NULL;
- else if (file->private_data == ERR_PTR(-ENOENT))
- return 0;
- file->private_data = offset_iterate_dir(d_inode(dir), ctx);
+ offset_iterate_dir(d_inode(dir), ctx, last_index);
return 0;
}
const struct file_operations simple_offset_dir_operations = {
+ .open = offset_dir_open,
.llseek = offset_dir_llseek,
.iterate_shared = offset_readdir,
.read = generic_read_dir,
diff --git a/fs/locks.c b/fs/locks.c
index 9afb16e0683f..e45cad40f8b6 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2984,7 +2984,7 @@ static int __init filelock_init(void)
filelock_cache = kmem_cache_create("file_lock_cache",
sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
- filelease_cache = kmem_cache_create("file_lock_cache",
+ filelease_cache = kmem_cache_create("file_lease_cache",
sizeof(struct file_lease), 0, SLAB_PANIC, NULL);
for_each_possible_cpu(i) {
diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig
index 1b78e8b65ebc..7701c037c328 100644
--- a/fs/netfs/Kconfig
+++ b/fs/netfs/Kconfig
@@ -24,7 +24,7 @@ config NETFS_STATS
config NETFS_DEBUG
bool "Enable dynamic debugging netfslib and FS-Cache"
- depends on NETFS
+ depends on NETFS_SUPPORT
help
This permits debugging to be dynamically enabled in the local caching
management module. If this is set, the debugging output may be
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index a688d4c75d99..27c750d39476 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -10,6 +10,97 @@
#include "internal.h"
/*
+ * [DEPRECATED] Unlock the folios in a read operation for when the filesystem
+ * is using PG_private_2 and direct writing to the cache from here rather than
+ * marking the page for writeback.
+ *
+ * Note that we don't touch folio->private in this code.
+ */
+static void netfs_rreq_unlock_folios_pgpriv2(struct netfs_io_request *rreq,
+ size_t *account)
+{
+ struct netfs_io_subrequest *subreq;
+ struct folio *folio;
+ pgoff_t start_page = rreq->start / PAGE_SIZE;
+ pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
+ bool subreq_failed = false;
+
+ XA_STATE(xas, &rreq->mapping->i_pages, start_page);
+
+ /* Walk through the pagecache and the I/O request lists simultaneously.
+ * We may have a mixture of cached and uncached sections and we only
+ * really want to write out the uncached sections. This is slightly
+ * complicated by the possibility that we might have huge pages with a
+ * mixture inside.
+ */
+ subreq = list_first_entry(&rreq->subrequests,
+ struct netfs_io_subrequest, rreq_link);
+ subreq_failed = (subreq->error < 0);
+
+ trace_netfs_rreq(rreq, netfs_rreq_trace_unlock_pgpriv2);
+
+ rcu_read_lock();
+ xas_for_each(&xas, folio, last_page) {
+ loff_t pg_end;
+ bool pg_failed = false;
+ bool folio_started = false;
+
+ if (xas_retry(&xas, folio))
+ continue;
+
+ pg_end = folio_pos(folio) + folio_size(folio) - 1;
+
+ for (;;) {
+ loff_t sreq_end;
+
+ if (!subreq) {
+ pg_failed = true;
+ break;
+ }
+
+ if (!folio_started &&
+ test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags) &&
+ fscache_operation_valid(&rreq->cache_resources)) {
+ trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache);
+ folio_start_private_2(folio);
+ folio_started = true;
+ }
+
+ pg_failed |= subreq_failed;
+ sreq_end = subreq->start + subreq->len - 1;
+ if (pg_end < sreq_end)
+ break;
+
+ *account += subreq->transferred;
+ if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
+ subreq = list_next_entry(subreq, rreq_link);
+ subreq_failed = (subreq->error < 0);
+ } else {
+ subreq = NULL;
+ subreq_failed = false;
+ }
+
+ if (pg_end == sreq_end)
+ break;
+ }
+
+ if (!pg_failed) {
+ flush_dcache_folio(folio);
+ folio_mark_uptodate(folio);
+ }
+
+ if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
+ if (folio->index == rreq->no_unlock_folio &&
+ test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags))
+ _debug("no unlock");
+ else
+ folio_unlock(folio);
+ }
+ }
+ rcu_read_unlock();
+}
+
+/*
* Unlock the folios in a read operation. We need to set PG_writeback on any
* folios we're going to write back before we unlock them.
*
@@ -35,6 +126,12 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
}
}
+ /* Handle deprecated PG_private_2 case. */
+ if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) {
+ netfs_rreq_unlock_folios_pgpriv2(rreq, &account);
+ goto out;
+ }
+
/* Walk through the pagecache and the I/O request lists simultaneously.
* We may have a mixture of cached and uncached sections and we only
* really want to write out the uncached sections. This is slightly
@@ -52,7 +149,6 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
loff_t pg_end;
bool pg_failed = false;
bool wback_to_cache = false;
- bool folio_started = false;
if (xas_retry(&xas, folio))
continue;
@@ -66,17 +162,8 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
pg_failed = true;
break;
}
- if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) {
- if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE,
- &subreq->flags)) {
- trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache);
- folio_start_private_2(folio);
- folio_started = true;
- }
- } else {
- wback_to_cache |=
- test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
- }
+
+ wback_to_cache |= test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
pg_failed |= subreq_failed;
sreq_end = subreq->start + subreq->len - 1;
if (pg_end < sreq_end)
@@ -124,6 +211,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
}
rcu_read_unlock();
+out:
task_io_account_read(account);
if (rreq->netfs_ops->done)
rreq->netfs_ops->done(rreq);
@@ -395,7 +483,7 @@ zero_out:
}
/**
- * netfs_write_begin - Helper to prepare for writing
+ * netfs_write_begin - Helper to prepare for writing [DEPRECATED]
* @ctx: The netfs context
* @file: The file to read from
* @mapping: The mapping to read from
@@ -426,6 +514,9 @@ zero_out:
* inode before calling this.
*
* This is usable whether or not caching is enabled.
+ *
+ * Note that this should be considered deprecated and netfs_perform_write()
+ * used instead.
*/
int netfs_write_begin(struct netfs_inode *ctx,
struct file *file, struct address_space *mapping,
@@ -466,7 +557,7 @@ retry:
if (!netfs_is_cache_enabled(ctx) &&
netfs_skip_folio_read(folio, pos, len, false)) {
netfs_stat(&netfs_n_rh_write_zskip);
- goto have_folio;
+ goto have_folio_no_wait;
}
rreq = netfs_alloc_request(mapping, file,
@@ -507,6 +598,10 @@ retry:
netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
have_folio:
+ ret = folio_wait_private_2_killable(folio);
+ if (ret < 0)
+ goto error;
+have_folio_no_wait:
*_folio = folio;
_leave(" = 0");
return 0;
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 4726c315453c..ca53c5d1622e 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -184,7 +184,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0;
ssize_t written = 0, ret, ret2;
loff_t i_size, pos = iocb->ki_pos, from, to;
- size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
+ size_t max_chunk = mapping_max_folio_size(mapping);
bool maybe_trouble = false;
if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) ||
diff --git a/fs/netfs/fscache_cookie.c b/fs/netfs/fscache_cookie.c
index bce2492186d0..d4d4b3a8b106 100644
--- a/fs/netfs/fscache_cookie.c
+++ b/fs/netfs/fscache_cookie.c
@@ -741,6 +741,10 @@ again_locked:
spin_lock(&cookie->lock);
}
if (test_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) {
+ if (atomic_read(&cookie->n_accesses) != 0)
+ /* still being accessed: postpone it */
+ break;
+
__fscache_set_cookie_state(cookie,
FSCACHE_COOKIE_STATE_LRU_DISCARDING);
wake = true;
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index c93851b98368..5367caf3fa28 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -99,6 +99,146 @@ static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async)
}
/*
+ * [DEPRECATED] Deal with the completion of writing the data to the cache. We
+ * have to clear the PG_fscache bits on the folios involved and release the
+ * caller's ref.
+ *
+ * May be called in softirq mode and we inherit a ref from the caller.
+ */
+static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq,
+ bool was_async)
+{
+ struct netfs_io_subrequest *subreq;
+ struct folio *folio;
+ pgoff_t unlocked = 0;
+ bool have_unlocked = false;
+
+ rcu_read_lock();
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE);
+
+ xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) {
+ if (xas_retry(&xas, folio))
+ continue;
+
+ /* We might have multiple writes from the same huge
+ * folio, but we mustn't unlock a folio more than once.
+ */
+ if (have_unlocked && folio->index <= unlocked)
+ continue;
+ unlocked = folio_next_index(folio) - 1;
+ trace_netfs_folio(folio, netfs_folio_trace_end_copy);
+ folio_end_private_2(folio);
+ have_unlocked = true;
+ }
+ }
+
+ rcu_read_unlock();
+ netfs_rreq_completed(rreq, was_async);
+}
+
+static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error,
+ bool was_async) /* [DEPRECATED] */
+{
+ struct netfs_io_subrequest *subreq = priv;
+ struct netfs_io_request *rreq = subreq->rreq;
+
+ if (IS_ERR_VALUE(transferred_or_error)) {
+ netfs_stat(&netfs_n_rh_write_failed);
+ trace_netfs_failure(rreq, subreq, transferred_or_error,
+ netfs_fail_copy_to_cache);
+ } else {
+ netfs_stat(&netfs_n_rh_write_done);
+ }
+
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write_term);
+
+ /* If we decrement nr_copy_ops to 0, the ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_copy_ops))
+ netfs_rreq_unmark_after_write(rreq, was_async);
+
+ netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated);
+}
+
+/*
+ * [DEPRECATED] Perform any outstanding writes to the cache. We inherit a ref
+ * from the caller.
+ */
+static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq)
+{
+ struct netfs_cache_resources *cres = &rreq->cache_resources;
+ struct netfs_io_subrequest *subreq, *next, *p;
+ struct iov_iter iter;
+ int ret;
+
+ trace_netfs_rreq(rreq, netfs_rreq_trace_copy);
+
+ /* We don't want terminating writes trying to wake us up whilst we're
+ * still going through the list.
+ */
+ atomic_inc(&rreq->nr_copy_ops);
+
+ list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) {
+ if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) {
+ list_del_init(&subreq->rreq_link);
+ netfs_put_subrequest(subreq, false,
+ netfs_sreq_trace_put_no_copy);
+ }
+ }
+
+ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+ /* Amalgamate adjacent writes */
+ while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
+ next = list_next_entry(subreq, rreq_link);
+ if (next->start != subreq->start + subreq->len)
+ break;
+ subreq->len += next->len;
+ list_del_init(&next->rreq_link);
+ netfs_put_subrequest(next, false,
+ netfs_sreq_trace_put_merged);
+ }
+
+ ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len,
+ subreq->len, rreq->i_size, true);
+ if (ret < 0) {
+ trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip);
+ continue;
+ }
+
+ iov_iter_xarray(&iter, ITER_SOURCE, &rreq->mapping->i_pages,
+ subreq->start, subreq->len);
+
+ atomic_inc(&rreq->nr_copy_ops);
+ netfs_stat(&netfs_n_rh_write);
+ netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_write);
+ cres->ops->write(cres, subreq->start, &iter,
+ netfs_rreq_copy_terminated, subreq);
+ }
+
+ /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */
+ if (atomic_dec_and_test(&rreq->nr_copy_ops))
+ netfs_rreq_unmark_after_write(rreq, false);
+}
+
+static void netfs_rreq_write_to_cache_work(struct work_struct *work) /* [DEPRECATED] */
+{
+ struct netfs_io_request *rreq =
+ container_of(work, struct netfs_io_request, work);
+
+ netfs_rreq_do_write_to_cache(rreq);
+}
+
+static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) /* [DEPRECATED] */
+{
+ rreq->work.func = netfs_rreq_write_to_cache_work;
+ if (!queue_work(system_unbound_wq, &rreq->work))
+ BUG();
+}
+
+/*
* Handle a short read.
*/
static void netfs_rreq_short_read(struct netfs_io_request *rreq,
@@ -275,6 +415,10 @@ again:
clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
+ if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags) &&
+ test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags))
+ return netfs_rreq_write_to_cache(rreq);
+
netfs_rreq_completed(rreq, was_async);
}
@@ -386,7 +530,8 @@ incomplete:
if (transferred_or_error == 0) {
if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) {
- subreq->error = -ENODATA;
+ if (rreq->origin != NETFS_DIO_READ)
+ subreq->error = -ENODATA;
goto failed;
}
} else {
@@ -457,9 +602,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
}
if (subreq->len > ictx->zero_point - subreq->start)
subreq->len = ictx->zero_point - subreq->start;
+
+ /* We limit buffered reads to the EOF, but let the
+ * server deal with larger-than-EOF DIO/unbuffered
+ * reads.
+ */
+ if (subreq->len > rreq->i_size - subreq->start)
+ subreq->len = rreq->i_size - subreq->start;
}
- if (subreq->len > rreq->i_size - subreq->start)
- subreq->len = rreq->i_size - subreq->start;
if (rreq->rsize && subreq->len > rreq->rsize)
subreq->len = rreq->rsize;
@@ -595,11 +745,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
do {
_debug("submit %llx + %llx >= %llx",
rreq->start, rreq->submitted, rreq->i_size);
- if (rreq->origin == NETFS_DIO_READ &&
- rreq->start + rreq->submitted >= rreq->i_size)
- break;
if (!netfs_rreq_submit_slice(rreq, &io_iter))
break;
+ if (test_bit(NETFS_SREQ_NO_PROGRESS, &rreq->flags))
+ break;
if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) &&
test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags))
break;
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index f4a642727479..0294df70c3ff 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -24,10 +24,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
struct netfs_io_request *rreq;
mempool_t *mempool = ctx->ops->request_pool ?: &netfs_request_pool;
struct kmem_cache *cache = mempool->pool_data;
- bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE ||
- origin == NETFS_DIO_READ ||
- origin == NETFS_DIO_WRITE);
- bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx);
int ret;
for (;;) {
@@ -56,12 +52,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
refcount_set(&rreq->ref, 1);
__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
- if (cached) {
- __set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags);
- if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags))
- /* Filesystem uses deprecated PG_private_2 marking. */
- __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags);
- }
if (file && file->f_flags & O_NONBLOCK)
__set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags);
if (rreq->netfs_ops->init_request) {
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 9258d30cffe3..3f7e37e50c7d 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -94,6 +94,8 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
{
struct netfs_io_request *wreq;
struct netfs_inode *ictx;
+ bool is_buffered = (origin == NETFS_WRITEBACK ||
+ origin == NETFS_WRITETHROUGH);
wreq = netfs_alloc_request(mapping, file, start, 0, origin);
if (IS_ERR(wreq))
@@ -102,7 +104,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
_enter("R=%x", wreq->debug_id);
ictx = netfs_inode(wreq->inode);
- if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags))
+ if (is_buffered && netfs_is_cache_enabled(ictx))
fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx));
wreq->contiguity = wreq->start;
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 7202ce84d0eb..7a558dea75c4 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -265,6 +265,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi
{
rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file));
rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id);
+ /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
+ __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags);
return 0;
}
@@ -361,7 +363,8 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr)
return;
sreq = netfs->sreq;
- if (test_bit(NFS_IOHDR_EOF, &hdr->flags))
+ if (test_bit(NFS_IOHDR_EOF, &hdr->flags) &&
+ sreq->rreq->origin != NETFS_DIO_READ)
__set_bit(NETFS_SREQ_CLEAR_TAIL, &sreq->flags);
if (hdr->error)
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index fbed0027996f..e8adae1bc260 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -81,8 +81,6 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs)
static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi)
{
netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false);
- /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
- __set_bit(NETFS_ICTX_USE_PGPRIV2, &nfsi->netfs.flags);
}
extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr);
extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 9e0ea6fc2aa3..34eb2c2cbcde 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -2069,8 +2069,7 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info)
continue;
}
- ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa,
- SVC_SOCK_ANONYMOUS,
+ ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa, 0,
get_current_cred());
/* always save the latest error */
if (ret < 0)
diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index c71ae5c04306..4a20e92474b2 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -1072,7 +1072,7 @@ static int cifs_security_flags_proc_open(struct inode *inode, struct file *file)
static void
cifs_security_flags_handle_must_flags(unsigned int *flags)
{
- unsigned int signflags = *flags & CIFSSEC_MUST_SIGN;
+ unsigned int signflags = *flags & (CIFSSEC_MUST_SIGN | CIFSSEC_MUST_SEAL);
if ((*flags & CIFSSEC_MUST_KRB5) == CIFSSEC_MUST_KRB5)
*flags = CIFSSEC_MUST_KRB5;
diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h
index 62d5fee3e5eb..ca2bd204bcc5 100644
--- a/fs/smb/client/cifsfs.h
+++ b/fs/smb/client/cifsfs.h
@@ -147,6 +147,6 @@ extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
/* when changing internal version - update following two lines at same time */
-#define SMB3_PRODUCT_BUILD 49
-#define CIFS_VERSION "2.49"
+#define SMB3_PRODUCT_BUILD 50
+#define CIFS_VERSION "2.50"
#endif /* _CIFSFS_H */
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 8e86fec7dcd2..5c9b3e6cd95f 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -345,7 +345,7 @@ struct smb_version_operations {
/* connect to a server share */
int (*tree_connect)(const unsigned int, struct cifs_ses *, const char *,
struct cifs_tcon *, const struct nls_table *);
- /* close tree connecion */
+ /* close tree connection */
int (*tree_disconnect)(const unsigned int, struct cifs_tcon *);
/* get DFS referrals */
int (*get_dfs_refer)(const unsigned int, struct cifs_ses *,
@@ -816,7 +816,7 @@ struct TCP_Server_Info {
* Protected by @refpath_lock and @srv_lock. The @refpath_lock is
* mostly used for not requiring a copy of @leaf_fullpath when getting
* cached or new DFS referrals (which might also sleep during I/O).
- * While @srv_lock is held for making string and NULL comparions against
+ * While @srv_lock is held for making string and NULL comparisons against
* both fields as in mount(2) and cache refresh.
*
* format: \\HOST\SHARE[\OPTIONAL PATH]
@@ -1471,29 +1471,6 @@ struct cifs_io_parms {
struct TCP_Server_Info *server;
};
-struct cifs_aio_ctx {
- struct kref refcount;
- struct list_head list;
- struct mutex aio_mutex;
- struct completion done;
- struct iov_iter iter;
- struct kiocb *iocb;
- struct cifsFileInfo *cfile;
- struct bio_vec *bv;
- loff_t pos;
- unsigned int nr_pinned_pages;
- ssize_t rc;
- unsigned int len;
- unsigned int total_len;
- unsigned int bv_need_unpin; /* If ->bv[] needs unpinning */
- bool should_dirty;
- /*
- * Indicates if this aio_ctx is for direct_io,
- * If yes, iter is a copy of the user passed iov_iter
- */
- bool direct_io;
-};
-
struct cifs_io_request {
struct netfs_io_request rreq;
struct cifsFileInfo *cfile;
@@ -1904,7 +1881,7 @@ static inline bool is_replayable_error(int error)
#define CIFSSEC_MAY_SIGN 0x00001
#define CIFSSEC_MAY_NTLMV2 0x00004
#define CIFSSEC_MAY_KRB5 0x00008
-#define CIFSSEC_MAY_SEAL 0x00040 /* not supported yet */
+#define CIFSSEC_MAY_SEAL 0x00040
#define CIFSSEC_MAY_NTLMSSP 0x00080 /* raw ntlmssp with ntlmv2 */
#define CIFSSEC_MUST_SIGN 0x01001
@@ -1914,11 +1891,11 @@ require use of the stronger protocol */
#define CIFSSEC_MUST_NTLMV2 0x04004
#define CIFSSEC_MUST_KRB5 0x08008
#ifdef CONFIG_CIFS_UPCALL
-#define CIFSSEC_MASK 0x8F08F /* flags supported if no weak allowed */
+#define CIFSSEC_MASK 0xCF0CF /* flags supported if no weak allowed */
#else
-#define CIFSSEC_MASK 0x87087 /* flags supported if no weak allowed */
+#define CIFSSEC_MASK 0xC70C7 /* flags supported if no weak allowed */
#endif /* UPCALL */
-#define CIFSSEC_MUST_SEAL 0x40040 /* not supported yet */
+#define CIFSSEC_MUST_SEAL 0x40040
#define CIFSSEC_MUST_NTLMSSP 0x80080 /* raw ntlmssp with ntlmv2 */
#define CIFSSEC_DEF (CIFSSEC_MAY_SIGN | CIFSSEC_MAY_NTLMV2 | CIFSSEC_MAY_NTLMSSP | CIFSSEC_MAY_SEAL)
@@ -2010,7 +1987,6 @@ require use of the stronger protocol */
* cifsFileInfo->file_info_lock cifsFileInfo->count cifs_new_fileinfo
* ->invalidHandle initiate_cifs_search
* ->oplock_break_cancelled
- * cifs_aio_ctx->aio_mutex cifs_aio_ctx cifs_aio_ctx_alloc
****************************************************************************/
#ifdef DECLARE_GLOBALS_HERE
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index c15bb5ee7eb7..497bf3c447bc 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -619,8 +619,6 @@ int __cifs_calc_signature(struct smb_rqst *rqst,
struct shash_desc *shash);
enum securityEnum cifs_select_sectype(struct TCP_Server_Info *,
enum securityEnum);
-struct cifs_aio_ctx *cifs_aio_ctx_alloc(void);
-void cifs_aio_ctx_release(struct kref *refcount);
int cifs_alloc_hash(const char *name, struct shash_desc **sdesc);
void cifs_free_hash(struct shash_desc **sdesc);
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index b2405dd4d4d4..3f3842e7b44a 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -217,7 +217,8 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq)
goto out;
}
- __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+ if (subreq->rreq->origin != NETFS_DIO_READ)
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
rc = rdata->server->ops->async_readv(rdata);
out:
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 4a8aa1de9522..dd0afa23734c 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -1042,13 +1042,26 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
}
rc = -EOPNOTSUPP;
- switch ((data->reparse.tag = tag)) {
- case 0: /* SMB1 symlink */
+ data->reparse.tag = tag;
+ if (!data->reparse.tag) {
if (server->ops->query_symlink) {
rc = server->ops->query_symlink(xid, tcon,
cifs_sb, full_path,
&data->symlink_target);
}
+ if (rc == -EOPNOTSUPP)
+ data->reparse.tag = IO_REPARSE_TAG_INTERNAL;
+ }
+
+ switch (data->reparse.tag) {
+ case 0: /* SMB1 symlink */
+ break;
+ case IO_REPARSE_TAG_INTERNAL:
+ rc = 0;
+ if (le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY) {
+ cifs_create_junction_fattr(fattr, sb);
+ goto out;
+ }
break;
case IO_REPARSE_TAG_MOUNT_POINT:
cifs_create_junction_fattr(fattr, sb);
diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c
index 855ac5a62edf..44dbaf9929a4 100644
--- a/fs/smb/client/ioctl.c
+++ b/fs/smb/client/ioctl.c
@@ -170,7 +170,10 @@ static long smb_mnt_get_fsinfo(unsigned int xid, struct cifs_tcon *tcon,
static int cifs_shutdown(struct super_block *sb, unsigned long arg)
{
struct cifs_sb_info *sbi = CIFS_SB(sb);
+ struct tcon_link *tlink;
+ struct cifs_tcon *tcon;
__u32 flags;
+ int rc;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -178,14 +181,21 @@ static int cifs_shutdown(struct super_block *sb, unsigned long arg)
if (get_user(flags, (__u32 __user *)arg))
return -EFAULT;
- if (flags > CIFS_GOING_FLAGS_NOLOGFLUSH)
- return -EINVAL;
+ tlink = cifs_sb_tlink(sbi);
+ if (IS_ERR(tlink))
+ return PTR_ERR(tlink);
+ tcon = tlink_tcon(tlink);
+
+ trace_smb3_shutdown_enter(flags, tcon->tid);
+ if (flags > CIFS_GOING_FLAGS_NOLOGFLUSH) {
+ rc = -EINVAL;
+ goto shutdown_out_err;
+ }
if (cifs_forced_shutdown(sbi))
- return 0;
+ goto shutdown_good;
cifs_dbg(VFS, "shut down requested (%d)", flags);
-/* trace_cifs_shutdown(sb, flags);*/
/*
* see:
@@ -201,7 +211,8 @@ static int cifs_shutdown(struct super_block *sb, unsigned long arg)
*/
case CIFS_GOING_FLAGS_DEFAULT:
cifs_dbg(FYI, "shutdown with default flag not supported\n");
- return -EINVAL;
+ rc = -EINVAL;
+ goto shutdown_out_err;
/*
* FLAGS_LOGFLUSH is easy since it asks to write out metadata (not
* data) but metadata writes are not cached on the client, so can treat
@@ -210,11 +221,18 @@ static int cifs_shutdown(struct super_block *sb, unsigned long arg)
case CIFS_GOING_FLAGS_LOGFLUSH:
case CIFS_GOING_FLAGS_NOLOGFLUSH:
sbi->mnt_cifs_flags |= CIFS_MOUNT_SHUTDOWN;
- return 0;
+ goto shutdown_good;
default:
- return -EINVAL;
+ rc = -EINVAL;
+ goto shutdown_out_err;
}
+
+shutdown_good:
+ trace_smb3_shutdown_done(flags, tcon->tid);
return 0;
+shutdown_out_err:
+ trace_smb3_shutdown_err(rc, flags, tcon->tid);
+ return rc;
}
static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug_info __user *in)
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index 07c468ddb88a..c6f11e6f9eb9 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -352,7 +352,7 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server)
* on simple responses (wct, bcc both zero)
* in particular have seen this on
* ulogoffX and FindClose. This leaves
- * one byte of bcc potentially unitialized
+ * one byte of bcc potentially uninitialized
*/
/* zero rest of bcc */
tmp[sizeof(struct smb_hdr)+1] = 0;
@@ -995,60 +995,6 @@ parse_DFS_referrals_exit:
return rc;
}
-struct cifs_aio_ctx *
-cifs_aio_ctx_alloc(void)
-{
- struct cifs_aio_ctx *ctx;
-
- /*
- * Must use kzalloc to initialize ctx->bv to NULL and ctx->direct_io
- * to false so that we know when we have to unreference pages within
- * cifs_aio_ctx_release()
- */
- ctx = kzalloc(sizeof(struct cifs_aio_ctx), GFP_KERNEL);
- if (!ctx)
- return NULL;
-
- INIT_LIST_HEAD(&ctx->list);
- mutex_init(&ctx->aio_mutex);
- init_completion(&ctx->done);
- kref_init(&ctx->refcount);
- return ctx;
-}
-
-void
-cifs_aio_ctx_release(struct kref *refcount)
-{
- struct cifs_aio_ctx *ctx = container_of(refcount,
- struct cifs_aio_ctx, refcount);
-
- cifsFileInfo_put(ctx->cfile);
-
- /*
- * ctx->bv is only set if setup_aio_ctx_iter() was call successfuly
- * which means that iov_iter_extract_pages() was a success and thus
- * that we may have references or pins on pages that we need to
- * release.
- */
- if (ctx->bv) {
- if (ctx->should_dirty || ctx->bv_need_unpin) {
- unsigned int i;
-
- for (i = 0; i < ctx->nr_pinned_pages; i++) {
- struct page *page = ctx->bv[i].bv_page;
-
- if (ctx->should_dirty)
- set_page_dirty(page);
- if (ctx->bv_need_unpin)
- unpin_user_page(page);
- }
- }
- kvfree(ctx->bv);
- }
-
- kfree(ctx);
-}
-
/**
* cifs_alloc_hash - allocate hash and hash context together
* @name: The name of the crypto hash algo
@@ -1288,6 +1234,7 @@ int cifs_inval_name_dfs_link_error(const unsigned int xid,
const char *full_path,
bool *islink)
{
+ struct TCP_Server_Info *server = tcon->ses->server;
struct cifs_ses *ses = tcon->ses;
size_t len;
char *path;
@@ -1304,12 +1251,12 @@ int cifs_inval_name_dfs_link_error(const unsigned int xid,
!is_tcon_dfs(tcon))
return 0;
- spin_lock(&tcon->tc_lock);
- if (!tcon->origin_fullpath) {
- spin_unlock(&tcon->tc_lock);
+ spin_lock(&server->srv_lock);
+ if (!server->leaf_fullpath) {
+ spin_unlock(&server->srv_lock);
return 0;
}
- spin_unlock(&tcon->tc_lock);
+ spin_unlock(&server->srv_lock);
/*
* Slow path - tcon is DFS and @full_path has prefix path, so attempt
diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index a0ffbda90733..689d8a506d45 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -505,6 +505,10 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
}
switch (tag) {
+ case IO_REPARSE_TAG_INTERNAL:
+ if (!(fattr->cf_cifsattrs & ATTR_DIRECTORY))
+ return false;
+ fallthrough;
case IO_REPARSE_TAG_DFS:
case IO_REPARSE_TAG_DFSR:
case IO_REPARSE_TAG_MOUNT_POINT:
diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h
index 6b55d1df9e2f..2c0644bc4e65 100644
--- a/fs/smb/client/reparse.h
+++ b/fs/smb/client/reparse.h
@@ -12,6 +12,12 @@
#include "fs_context.h"
#include "cifsglob.h"
+/*
+ * Used only by cifs.ko to ignore reparse points from files when client or
+ * server doesn't support FSCTL_GET_REPARSE_POINT.
+ */
+#define IO_REPARSE_TAG_INTERNAL ((__u32)~0U)
+
static inline dev_t reparse_nfs_mkdev(struct reparse_posix_data *buf)
{
u64 v = le64_to_cpu(*(__le64 *)buf->DataBuffer);
@@ -78,10 +84,19 @@ static inline u32 reparse_mode_wsl_tag(mode_t mode)
static inline bool reparse_inode_match(struct inode *inode,
struct cifs_fattr *fattr)
{
+ struct cifsInodeInfo *cinode = CIFS_I(inode);
struct timespec64 ctime = inode_get_ctime(inode);
- return (CIFS_I(inode)->cifsAttrs & ATTR_REPARSE) &&
- CIFS_I(inode)->reparse_tag == fattr->cf_cifstag &&
+ /*
+ * Do not match reparse tags when client or server doesn't support
+ * FSCTL_GET_REPARSE_POINT. @fattr->cf_cifstag should contain correct
+ * reparse tag from query dir response but the client won't be able to
+ * read the reparse point data anyway. This spares us a revalidation.
+ */
+ if (cinode->reparse_tag != IO_REPARSE_TAG_INTERNAL &&
+ cinode->reparse_tag != fattr->cf_cifstag)
+ return false;
+ return (cinode->cifsAttrs & ATTR_REPARSE) &&
timespec64_equal(&ctime, &fattr->cf_ctime);
}
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 5c02a12251c8..9f5bc41433c1 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -930,6 +930,8 @@ int smb2_query_path_info(const unsigned int xid,
switch (rc) {
case 0:
+ rc = parse_create_response(data, cifs_sb, &out_iov[0]);
+ break;
case -EOPNOTSUPP:
/*
* BB TODO: When support for special files added to Samba
@@ -948,7 +950,8 @@ int smb2_query_path_info(const unsigned int xid,
cmds[num_cmds++] = SMB2_OP_GET_REPARSE;
oparms = CIFS_OPARMS(cifs_sb, tcon, full_path,
- FILE_READ_ATTRIBUTES | FILE_READ_EA,
+ FILE_READ_ATTRIBUTES |
+ FILE_READ_EA | SYNCHRONIZE,
FILE_OPEN, create_options |
OPEN_REPARSE_POINT, ACL_NO_MODE);
cifs_get_readable_path(tcon, full_path, &cfile);
@@ -1256,7 +1259,8 @@ int smb2_query_reparse_point(const unsigned int xid,
cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
cifs_get_readable_path(tcon, full_path, &cfile);
- oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_READ_ATTRIBUTES,
+ oparms = CIFS_OPARMS(cifs_sb, tcon, full_path,
+ FILE_READ_ATTRIBUTES | FILE_READ_EA | SYNCHRONIZE,
FILE_OPEN, OPEN_REPARSE_POINT, ACL_NO_MODE);
rc = smb2_compound_op(xid, tcon, cifs_sb,
full_path, &oparms, &in_iov,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 9a06b5594669..83facb54276a 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -82,6 +82,9 @@ int smb3_encryption_required(const struct cifs_tcon *tcon)
if (tcon->seal &&
(tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
return 1;
+ if (((global_secflags & CIFSSEC_MUST_SEAL) == CIFSSEC_MUST_SEAL) &&
+ (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
+ return 1;
return 0;
}
diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
index d74e829de51c..7bcc379014ca 100644
--- a/fs/smb/client/smbdirect.c
+++ b/fs/smb/client/smbdirect.c
@@ -406,7 +406,7 @@ static void smbd_post_send_credits(struct work_struct *work)
else
response = get_empty_queue_buffer(info);
if (!response) {
- /* now switch to emtpy packet queue */
+ /* now switch to empty packet queue */
if (use_receive_queue) {
use_receive_queue = 0;
continue;
@@ -618,7 +618,7 @@ out:
/*
* Test if FRWR (Fast Registration Work Requests) is supported on the device
- * This implementation requries FRWR on RDMA read/write
+ * This implementation requires FRWR on RDMA read/write
* return value: true if it is supported
*/
static bool frwr_is_supported(struct ib_device_attr *attrs)
@@ -2177,7 +2177,7 @@ cleanup_entries:
* MR available in the list. It may access the list while the
* smbd_mr_recovery_work is recovering the MR list. This doesn't need a lock
* as they never modify the same places. However, there may be several CPUs
- * issueing I/O trying to get MR at the same time, mr_list_lock is used to
+ * issuing I/O trying to get MR at the same time, mr_list_lock is used to
* protect this situation.
*/
static struct smbd_mr *get_mr(struct smbd_connection *info)
@@ -2311,7 +2311,7 @@ struct smbd_mr *smbd_register_mr(struct smbd_connection *info,
/*
* There is no need for waiting for complemtion on ib_post_send
* on IB_WR_REG_MR. Hardware enforces a barrier and order of execution
- * on the next ib_post_send when we actaully send I/O to remote peer
+ * on the next ib_post_send when we actually send I/O to remote peer
*/
rc = ib_post_send(info->id->qp, &reg_wr->wr, NULL);
if (!rc)
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 6b3bdfb97211..0f0c10c7ada7 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -1388,7 +1388,7 @@ DECLARE_EVENT_CLASS(smb3_ioctl_class,
__entry->command = command;
),
TP_printk("xid=%u fid=0x%llx ioctl cmd=0x%x",
- __entry->xid, __entry->fid, __entry->command)
+ __entry->xid, __entry->fid, __entry->command)
)
#define DEFINE_SMB3_IOCTL_EVENT(name) \
@@ -1400,9 +1400,58 @@ DEFINE_EVENT(smb3_ioctl_class, smb3_##name, \
DEFINE_SMB3_IOCTL_EVENT(ioctl);
+DECLARE_EVENT_CLASS(smb3_shutdown_class,
+ TP_PROTO(__u32 flags,
+ __u32 tid),
+ TP_ARGS(flags, tid),
+ TP_STRUCT__entry(
+ __field(__u32, flags)
+ __field(__u32, tid)
+ ),
+ TP_fast_assign(
+ __entry->flags = flags;
+ __entry->tid = tid;
+ ),
+ TP_printk("flags=0x%x tid=0x%x",
+ __entry->flags, __entry->tid)
+)
+
+#define DEFINE_SMB3_SHUTDOWN_EVENT(name) \
+DEFINE_EVENT(smb3_shutdown_class, smb3_##name, \
+ TP_PROTO(__u32 flags, \
+ __u32 tid), \
+ TP_ARGS(flags, tid))
+
+DEFINE_SMB3_SHUTDOWN_EVENT(shutdown_enter);
+DEFINE_SMB3_SHUTDOWN_EVENT(shutdown_done);
+DECLARE_EVENT_CLASS(smb3_shutdown_err_class,
+ TP_PROTO(int rc,
+ __u32 flags,
+ __u32 tid),
+ TP_ARGS(rc, flags, tid),
+ TP_STRUCT__entry(
+ __field(int, rc)
+ __field(__u32, flags)
+ __field(__u32, tid)
+ ),
+ TP_fast_assign(
+ __entry->rc = rc;
+ __entry->flags = flags;
+ __entry->tid = tid;
+ ),
+ TP_printk("rc=%d flags=0x%x tid=0x%x",
+ __entry->rc, __entry->flags, __entry->tid)
+)
+#define DEFINE_SMB3_SHUTDOWN_ERR_EVENT(name) \
+DEFINE_EVENT(smb3_shutdown_err_class, smb3_##name, \
+ TP_PROTO(int rc, \
+ __u32 flags, \
+ __u32 tid), \
+ TP_ARGS(rc, flags, tid))
+DEFINE_SMB3_SHUTDOWN_ERR_EVENT(shutdown_err);
DECLARE_EVENT_CLASS(smb3_credit_class,
TP_PROTO(__u64 currmid,
diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index adfe0d058701..6e68aaf5bd20 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -1289,7 +1289,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
out:
/*
* This will dequeue all mids. After this it is important that the
- * demultiplex_thread will not process any of these mids any futher.
+ * demultiplex_thread will not process any of these mids any further.
* This is prevented above by using a noop callback that will not
* wake this thread except for the very last PDU.
*/
diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c
index e0a6b758094f..d8d03070ae44 100644
--- a/fs/smb/server/mgmt/share_config.c
+++ b/fs/smb/server/mgmt/share_config.c
@@ -15,6 +15,7 @@
#include "share_config.h"
#include "user_config.h"
#include "user_session.h"
+#include "../connection.h"
#include "../transport_ipc.h"
#include "../misc.h"
@@ -120,12 +121,13 @@ static int parse_veto_list(struct ksmbd_share_config *share,
return 0;
}
-static struct ksmbd_share_config *share_config_request(struct unicode_map *um,
+static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work,
const char *name)
{
struct ksmbd_share_config_response *resp;
struct ksmbd_share_config *share = NULL;
struct ksmbd_share_config *lookup;
+ struct unicode_map *um = work->conn->um;
int ret;
resp = ksmbd_ipc_share_config_request(name);
@@ -181,7 +183,14 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um,
KSMBD_SHARE_CONFIG_VETO_LIST(resp),
resp->veto_list_sz);
if (!ret && share->path) {
+ if (__ksmbd_override_fsids(work, share)) {
+ kill_share(share);
+ share = NULL;
+ goto out;
+ }
+
ret = kern_path(share->path, 0, &share->vfs_path);
+ ksmbd_revert_fsids(work);
if (ret) {
ksmbd_debug(SMB, "failed to access '%s'\n",
share->path);
@@ -214,7 +223,7 @@ out:
return share;
}
-struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um,
+struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work,
const char *name)
{
struct ksmbd_share_config *share;
@@ -227,7 +236,7 @@ struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um,
if (share)
return share;
- return share_config_request(um, name);
+ return share_config_request(work, name);
}
bool ksmbd_share_veto_filename(struct ksmbd_share_config *share,
diff --git a/fs/smb/server/mgmt/share_config.h b/fs/smb/server/mgmt/share_config.h
index 5f591751b923..d4ac2dd4de20 100644
--- a/fs/smb/server/mgmt/share_config.h
+++ b/fs/smb/server/mgmt/share_config.h
@@ -11,6 +11,8 @@
#include <linux/path.h>
#include <linux/unicode.h>
+struct ksmbd_work;
+
struct ksmbd_share_config {
char *name;
char *path;
@@ -68,7 +70,7 @@ static inline void ksmbd_share_config_put(struct ksmbd_share_config *share)
__ksmbd_share_config_put(share);
}
-struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um,
+struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work,
const char *name);
bool ksmbd_share_veto_filename(struct ksmbd_share_config *share,
const char *filename);
diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c
index d2c81a8a11dd..94a52a75014a 100644
--- a/fs/smb/server/mgmt/tree_connect.c
+++ b/fs/smb/server/mgmt/tree_connect.c
@@ -16,17 +16,18 @@
#include "user_session.h"
struct ksmbd_tree_conn_status
-ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess,
- const char *share_name)
+ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name)
{
struct ksmbd_tree_conn_status status = {-ENOENT, NULL};
struct ksmbd_tree_connect_response *resp = NULL;
struct ksmbd_share_config *sc;
struct ksmbd_tree_connect *tree_conn = NULL;
struct sockaddr *peer_addr;
+ struct ksmbd_conn *conn = work->conn;
+ struct ksmbd_session *sess = work->sess;
int ret;
- sc = ksmbd_share_config_get(conn->um, share_name);
+ sc = ksmbd_share_config_get(work, share_name);
if (!sc)
return status;
@@ -61,7 +62,7 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess,
struct ksmbd_share_config *new_sc;
ksmbd_share_config_del(sc);
- new_sc = ksmbd_share_config_get(conn->um, share_name);
+ new_sc = ksmbd_share_config_get(work, share_name);
if (!new_sc) {
pr_err("Failed to update stale share config\n");
status.ret = -ESTALE;
diff --git a/fs/smb/server/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h
index 6377a70b811c..a42cdd051041 100644
--- a/fs/smb/server/mgmt/tree_connect.h
+++ b/fs/smb/server/mgmt/tree_connect.h
@@ -13,6 +13,7 @@
struct ksmbd_share_config;
struct ksmbd_user;
struct ksmbd_conn;
+struct ksmbd_work;
enum {
TREE_NEW = 0,
@@ -50,8 +51,7 @@ static inline int test_tree_conn_flag(struct ksmbd_tree_connect *tree_conn,
struct ksmbd_session;
struct ksmbd_tree_conn_status
-ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess,
- const char *share_name);
+ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name);
void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon);
int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess,
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 37a39ab4ee65..2df1354288e6 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -1955,7 +1955,7 @@ int smb2_tree_connect(struct ksmbd_work *work)
ksmbd_debug(SMB, "tree connect request for tree %s treename %s\n",
name, treename);
- status = ksmbd_tree_conn_connect(conn, sess, name);
+ status = ksmbd_tree_conn_connect(work, name);
if (status.ret == KSMBD_TREE_CONN_STATUS_OK)
rsp->hdr.Id.SyncId.TreeId = cpu_to_le32(status.tree_conn->id);
else
@@ -5596,6 +5596,11 @@ int smb2_query_info(struct ksmbd_work *work)
ksmbd_debug(SMB, "GOT query info request\n");
+ if (ksmbd_override_fsids(work)) {
+ rc = -ENOMEM;
+ goto err_out;
+ }
+
switch (req->InfoType) {
case SMB2_O_INFO_FILE:
ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n");
@@ -5614,6 +5619,7 @@ int smb2_query_info(struct ksmbd_work *work)
req->InfoType);
rc = -EOPNOTSUPP;
}
+ ksmbd_revert_fsids(work);
if (!rc) {
rsp->StructureSize = cpu_to_le16(9);
@@ -5623,6 +5629,7 @@ int smb2_query_info(struct ksmbd_work *work)
le32_to_cpu(rsp->OutputBufferLength));
}
+err_out:
if (rc < 0) {
if (rc == -EACCES)
rsp->hdr.Status = STATUS_ACCESS_DENIED;
diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c
index 474dadf6b7b8..13818ecb6e1b 100644
--- a/fs/smb/server/smb_common.c
+++ b/fs/smb/server/smb_common.c
@@ -732,10 +732,10 @@ bool is_asterisk(char *p)
return p && p[0] == '*';
}
-int ksmbd_override_fsids(struct ksmbd_work *work)
+int __ksmbd_override_fsids(struct ksmbd_work *work,
+ struct ksmbd_share_config *share)
{
struct ksmbd_session *sess = work->sess;
- struct ksmbd_share_config *share = work->tcon->share_conf;
struct cred *cred;
struct group_info *gi;
unsigned int uid;
@@ -775,6 +775,11 @@ int ksmbd_override_fsids(struct ksmbd_work *work)
return 0;
}
+int ksmbd_override_fsids(struct ksmbd_work *work)
+{
+ return __ksmbd_override_fsids(work, work->tcon->share_conf);
+}
+
void ksmbd_revert_fsids(struct ksmbd_work *work)
{
const struct cred *cred;
diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h
index f1092519c0c2..4a3148b0167f 100644
--- a/fs/smb/server/smb_common.h
+++ b/fs/smb/server/smb_common.h
@@ -447,6 +447,8 @@ int ksmbd_extract_shortname(struct ksmbd_conn *conn,
int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command);
int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp);
+int __ksmbd_override_fsids(struct ksmbd_work *work,
+ struct ksmbd_share_config *share);
int ksmbd_override_fsids(struct ksmbd_work *work);
void ksmbd_revert_fsids(struct ksmbd_work *work);
diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c
index 16bd693d0b3a..d5918eba27e3 100644
--- a/fs/squashfs/inode.c
+++ b/fs/squashfs/inode.c
@@ -279,8 +279,13 @@ int squashfs_read_inode(struct inode *inode, long long ino)
if (err < 0)
goto failed_read;
- set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
inode->i_size = le32_to_cpu(sqsh_ino->symlink_size);
+ if (inode->i_size > PAGE_SIZE) {
+ ERROR("Corrupted symlink\n");
+ return -EINVAL;
+ }
+
+ set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
inode->i_op = &squashfs_symlink_inode_ops;
inode_nohighmem(inode);
inode->i_data.a_ops = &squashfs_symlink_aops;
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 5d88c184f0fc..01e99e98457d 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -112,7 +112,7 @@ static void release_ei(struct kref *ref)
entry->release(entry->name, ei->data);
}
- call_rcu(&ei->rcu, free_ei_rcu);
+ call_srcu(&eventfs_srcu, &ei->rcu, free_ei_rcu);
}
static inline void put_ei(struct eventfs_inode *ei)
@@ -736,7 +736,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
/* Was the parent freed? */
if (list_empty(&ei->list)) {
cleanup_ei(ei);
- ei = NULL;
+ ei = ERR_PTR(-EBUSY);
}
return ei;
}
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 1028ab6d9a74..1748dff58c3b 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -42,7 +42,7 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb)
struct tracefs_inode *ti;
unsigned long flags;
- ti = kmem_cache_alloc(tracefs_inode_cachep, GFP_KERNEL);
+ ti = alloc_inode_sb(sb, tracefs_inode_cachep, GFP_KERNEL);
if (!ti)
return NULL;
@@ -53,15 +53,14 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb)
return &ti->vfs_inode;
}
-static void tracefs_free_inode_rcu(struct rcu_head *rcu)
+static void tracefs_free_inode(struct inode *inode)
{
- struct tracefs_inode *ti;
+ struct tracefs_inode *ti = get_tracefs(inode);
- ti = container_of(rcu, struct tracefs_inode, rcu);
kmem_cache_free(tracefs_inode_cachep, ti);
}
-static void tracefs_free_inode(struct inode *inode)
+static void tracefs_destroy_inode(struct inode *inode)
{
struct tracefs_inode *ti = get_tracefs(inode);
unsigned long flags;
@@ -69,8 +68,6 @@ static void tracefs_free_inode(struct inode *inode)
spin_lock_irqsave(&tracefs_inode_lock, flags);
list_del_rcu(&ti->list);
spin_unlock_irqrestore(&tracefs_inode_lock, flags);
-
- call_rcu(&ti->rcu, tracefs_free_inode_rcu);
}
static ssize_t default_read_file(struct file *file, char __user *buf,
@@ -437,6 +434,7 @@ static int tracefs_drop_inode(struct inode *inode)
static const struct super_operations tracefs_super_operations = {
.alloc_inode = tracefs_alloc_inode,
.free_inode = tracefs_free_inode,
+ .destroy_inode = tracefs_destroy_inode,
.drop_inode = tracefs_drop_inode,
.statfs = simple_statfs,
.show_options = tracefs_show_options,
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index f704d8348357..d83c2a25f288 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -10,10 +10,7 @@ enum {
};
struct tracefs_inode {
- union {
- struct inode vfs_inode;
- struct rcu_head rcu;
- };
+ struct inode vfs_inode;
/* The below gets initialized with memset_after(ti, 0, vfs_inode) */
struct list_head list;
unsigned long flags;
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index cb035da3f990..fb05f44f6c75 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -56,7 +56,7 @@ typedef uint8_t xfs_dqtype_t;
* And, of course, we also need to take into account the dquot log format item
* used to describe each dquot.
*/
-#define XFS_DQUOT_LOGRES(mp) \
+#define XFS_DQUOT_LOGRES \
((sizeof(struct xfs_dq_logformat) + sizeof(struct xfs_disk_dquot)) * 6)
#define XFS_IS_QUOTA_ON(mp) ((mp)->m_qflags & XFS_ALL_QUOTA_ACCT)
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 3dc8f785bf29..45aaf169806a 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -338,11 +338,11 @@ xfs_calc_write_reservation(
blksz);
t1 += adj;
t3 += adj;
- return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3);
+ return XFS_DQUOT_LOGRES + max3(t1, t2, t3);
}
t4 = xfs_calc_refcountbt_reservation(mp, 1);
- return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3));
+ return XFS_DQUOT_LOGRES + max(t4, max3(t1, t2, t3));
}
unsigned int
@@ -410,11 +410,11 @@ xfs_calc_itruncate_reservation(
xfs_refcountbt_block_count(mp, 4),
blksz);
- return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3);
+ return XFS_DQUOT_LOGRES + max3(t1, t2, t3);
}
t4 = xfs_calc_refcountbt_reservation(mp, 2);
- return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3));
+ return XFS_DQUOT_LOGRES + max(t4, max3(t1, t2, t3));
}
unsigned int
@@ -466,7 +466,7 @@ STATIC uint
xfs_calc_rename_reservation(
struct xfs_mount *mp)
{
- unsigned int overhead = XFS_DQUOT_LOGRES(mp);
+ unsigned int overhead = XFS_DQUOT_LOGRES;
struct xfs_trans_resv *resp = M_RES(mp);
unsigned int t1, t2, t3 = 0;
@@ -577,7 +577,7 @@ STATIC uint
xfs_calc_link_reservation(
struct xfs_mount *mp)
{
- unsigned int overhead = XFS_DQUOT_LOGRES(mp);
+ unsigned int overhead = XFS_DQUOT_LOGRES;
struct xfs_trans_resv *resp = M_RES(mp);
unsigned int t1, t2, t3 = 0;
@@ -641,7 +641,7 @@ STATIC uint
xfs_calc_remove_reservation(
struct xfs_mount *mp)
{
- unsigned int overhead = XFS_DQUOT_LOGRES(mp);
+ unsigned int overhead = XFS_DQUOT_LOGRES;
struct xfs_trans_resv *resp = M_RES(mp);
unsigned int t1, t2, t3 = 0;
@@ -729,7 +729,7 @@ xfs_calc_icreate_reservation(
struct xfs_mount *mp)
{
struct xfs_trans_resv *resp = M_RES(mp);
- unsigned int overhead = XFS_DQUOT_LOGRES(mp);
+ unsigned int overhead = XFS_DQUOT_LOGRES;
unsigned int t1, t2, t3 = 0;
t1 = xfs_calc_icreate_resv_alloc(mp);
@@ -747,7 +747,7 @@ STATIC uint
xfs_calc_create_tmpfile_reservation(
struct xfs_mount *mp)
{
- uint res = XFS_DQUOT_LOGRES(mp);
+ uint res = XFS_DQUOT_LOGRES;
res += xfs_calc_icreate_resv_alloc(mp);
return res + xfs_calc_iunlink_add_reservation(mp);
@@ -829,7 +829,7 @@ STATIC uint
xfs_calc_ifree_reservation(
struct xfs_mount *mp)
{
- return XFS_DQUOT_LOGRES(mp) +
+ return XFS_DQUOT_LOGRES +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
xfs_calc_iunlink_remove_reservation(mp) +
@@ -846,7 +846,7 @@ STATIC uint
xfs_calc_ichange_reservation(
struct xfs_mount *mp)
{
- return XFS_DQUOT_LOGRES(mp) +
+ return XFS_DQUOT_LOGRES +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
@@ -955,7 +955,7 @@ STATIC uint
xfs_calc_addafork_reservation(
struct xfs_mount *mp)
{
- return XFS_DQUOT_LOGRES(mp) +
+ return XFS_DQUOT_LOGRES +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(1, mp->m_dir_geo->blksize) +
@@ -1003,7 +1003,7 @@ STATIC uint
xfs_calc_attrsetm_reservation(
struct xfs_mount *mp)
{
- return XFS_DQUOT_LOGRES(mp) +
+ return XFS_DQUOT_LOGRES +
xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1));
@@ -1043,7 +1043,7 @@ STATIC uint
xfs_calc_attrrm_reservation(
struct xfs_mount *mp)
{
- return XFS_DQUOT_LOGRES(mp) +
+ return XFS_DQUOT_LOGRES +
max((xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH,
XFS_FSB_TO_B(mp, 1)) +
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 0dbc484b182f..2f98d90d7fd6 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -696,7 +696,7 @@ xrep_agfl_init_header(
* step.
*/
xagb_bitmap_init(&af.used_extents);
- af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp),
+ af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp);
xagb_bitmap_walk(agfl_extents, xrep_agfl_fill, &af);
error = xagb_bitmap_disunion(agfl_extents, &af.used_extents);
if (error)
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 733c410a2279..91e7b51ce068 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -799,7 +799,7 @@ xchk_parent_pptr(
}
if (pp->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
- goto out_pp;
+ goto out_names;
/*
* Complain if the number of parent pointers doesn't match the link
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 92ef4cdc486e..c886d5d0eb02 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -959,18 +959,16 @@ TRACE_EVENT(xfile_create,
TP_STRUCT__entry(
__field(dev_t, dev)
__field(unsigned long, ino)
- __array(char, pathname, 256)
+ __array(char, pathname, MAXNAMELEN)
),
TP_fast_assign(
- char pathname[257];
char *path;
__entry->ino = file_inode(xf->file)->i_ino;
- memset(pathname, 0, sizeof(pathname));
- path = file_path(xf->file, pathname, sizeof(pathname) - 1);
+ path = file_path(xf->file, __entry->pathname, MAXNAMELEN);
if (IS_ERR(path))
- path = "(unknown)";
- strncpy(__entry->pathname, path, sizeof(__entry->pathname));
+ strncpy(__entry->pathname, "(unknown)",
+ sizeof(__entry->pathname));
),
TP_printk("xfino 0x%lx path '%s'",
__entry->ino,
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 5c947e5ce8b8..7db386304875 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -139,7 +139,7 @@ xfs_attr_shortform_list(
sbp->name = sfe->nameval;
sbp->namelen = sfe->namelen;
/* These are bytes, and both on-disk, don't endian-flip */
- sbp->value = &sfe->nameval[sfe->namelen],
+ sbp->value = &sfe->nameval[sfe->namelen];
sbp->valuelen = sfe->valuelen;
sbp->flags = sfe->flags;
sbp->hash = xfs_attr_hashval(dp->i_mount, sfe->flags,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 5646d300b286..180ce697305a 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -4715,20 +4715,18 @@ TRACE_EVENT(xmbuf_create,
TP_STRUCT__entry(
__field(dev_t, dev)
__field(unsigned long, ino)
- __array(char, pathname, 256)
+ __array(char, pathname, MAXNAMELEN)
),
TP_fast_assign(
- char pathname[257];
char *path;
struct file *file = btp->bt_file;
__entry->dev = btp->bt_mount->m_super->s_dev;
__entry->ino = file_inode(file)->i_ino;
- memset(pathname, 0, sizeof(pathname));
- path = file_path(file, pathname, sizeof(pathname) - 1);
+ path = file_path(file, __entry->pathname, MAXNAMELEN);
if (IS_ERR(path))
- path = "(unknown)";
- strncpy(__entry->pathname, path, sizeof(__entry->pathname));
+ strncpy(__entry->pathname, "(unknown)",
+ sizeof(__entry->pathname));
),
TP_printk("dev %d:%d xmino 0x%lx path '%s'",
MAJOR(__entry->dev), MINOR(__entry->dev),
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index ab3d22f662f2..eaf849260bd6 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -110,7 +110,24 @@ xfs_attr_change(
args->whichfork = XFS_ATTR_FORK;
xfs_attr_sethash(args);
- return xfs_attr_set(args, op, args->attr_filter & XFS_ATTR_ROOT);
+ /*
+ * Some xattrs must be resistant to allocation failure at ENOSPC, e.g.
+ * creating an inode with ACLs or security attributes requires the
+ * allocation of the xattr holding that information to succeed. Hence
+ * we allow xattrs in the VFS TRUSTED, SYSTEM, POSIX_ACL and SECURITY
+ * (LSM xattr) namespaces to dip into the reserve block pool to allow
+ * manipulation of these xattrs when at ENOSPC. These VFS xattr
+ * namespaces translate to the XFS_ATTR_ROOT and XFS_ATTR_SECURE on-disk
+ * namespaces.
+ *
+ * For most of these cases, these special xattrs will fit in the inode
+ * itself and so consume no extra space or only require temporary extra
+ * space while an overwrite is being made. Hence the use of the reserved
+ * pool is largely to avoid the worst case reservation from preventing
+ * the xattr from being created at ENOSPC.
+ */
+ return xfs_attr_set(args, op,
+ args->attr_filter & (XFS_ATTR_ROOT | XFS_ATTR_SECURE));
}