summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/afs/cmservice.c10
-rw-r--r--fs/afs/dir.c89
-rw-r--r--fs/afs/file.c12
-rw-r--r--fs/afs/vlclient.c11
-rw-r--r--fs/block_dev.c49
-rw-r--r--fs/btrfs/ctree.h4
-rw-r--r--fs/btrfs/disk-io.c2
-rw-r--r--fs/btrfs/extent-tree.c71
-rw-r--r--fs/btrfs/volumes.c13
-rw-r--r--fs/io_uring.c20
-rw-r--r--fs/seq_file.c2
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c29
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c19
-rw-r--r--fs/xfs/libxfs/xfs_dir2_node.c3
-rw-r--r--fs/xfs/xfs_log.c5
15 files changed, 176 insertions, 163 deletions
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 4f1b6f466ff5..b86195e4dc6c 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -505,18 +505,14 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work)
struct afs_call *call = container_of(work, struct afs_call, work);
struct afs_uuid *r = call->request;
- struct {
- __be32 match;
- } reply;
-
_enter("");
if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0)
- reply.match = htonl(0);
+ afs_send_empty_reply(call);
else
- reply.match = htonl(1);
+ rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+ 1, 1, "K-1");
- afs_send_simple_reply(call, &reply, sizeof(reply));
afs_put_call(call);
_leave("");
}
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index e640d67274be..81207dc3c997 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -440,7 +440,7 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode,
* iterate through the data blob that lists the contents of an AFS directory
*/
static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
- struct key *key)
+ struct key *key, afs_dataversion_t *_dir_version)
{
struct afs_vnode *dvnode = AFS_FS_I(dir);
struct afs_xdr_dir_page *dbuf;
@@ -460,6 +460,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
req = afs_read_dir(dvnode, key);
if (IS_ERR(req))
return PTR_ERR(req);
+ *_dir_version = req->data_version;
/* round the file position up to the next entry boundary */
ctx->pos += sizeof(union afs_xdr_dirent) - 1;
@@ -514,7 +515,10 @@ out:
*/
static int afs_readdir(struct file *file, struct dir_context *ctx)
{
- return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file));
+ afs_dataversion_t dir_version;
+
+ return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file),
+ &dir_version);
}
/*
@@ -555,7 +559,8 @@ static int afs_lookup_one_filldir(struct dir_context *ctx, const char *name,
* - just returns the FID the dentry name maps to if found
*/
static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry,
- struct afs_fid *fid, struct key *key)
+ struct afs_fid *fid, struct key *key,
+ afs_dataversion_t *_dir_version)
{
struct afs_super_info *as = dir->i_sb->s_fs_info;
struct afs_lookup_one_cookie cookie = {
@@ -568,7 +573,7 @@ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry,
_enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry);
/* search the directory */
- ret = afs_dir_iterate(dir, &cookie.ctx, key);
+ ret = afs_dir_iterate(dir, &cookie.ctx, key, _dir_version);
if (ret < 0) {
_leave(" = %d [iter]", ret);
return ret;
@@ -642,6 +647,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
struct afs_server *server;
struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode;
struct inode *inode = NULL, *ti;
+ afs_dataversion_t data_version = READ_ONCE(dvnode->status.data_version);
int ret, i;
_enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry);
@@ -669,12 +675,14 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
cookie->fids[i].vid = as->volume->vid;
/* search the directory */
- ret = afs_dir_iterate(dir, &cookie->ctx, key);
+ ret = afs_dir_iterate(dir, &cookie->ctx, key, &data_version);
if (ret < 0) {
inode = ERR_PTR(ret);
goto out;
}
+ dentry->d_fsdata = (void *)(unsigned long)data_version;
+
inode = ERR_PTR(-ENOENT);
if (!cookie->found)
goto out;
@@ -968,7 +976,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
struct dentry *parent;
struct inode *inode;
struct key *key;
- long dir_version, de_version;
+ afs_dataversion_t dir_version;
+ long de_version;
int ret;
if (flags & LOOKUP_RCU)
@@ -1014,20 +1023,20 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
* on a 32-bit system, we only have 32 bits in the dentry to store the
* version.
*/
- dir_version = (long)dir->status.data_version;
+ dir_version = dir->status.data_version;
de_version = (long)dentry->d_fsdata;
- if (de_version == dir_version)
- goto out_valid;
+ if (de_version == (long)dir_version)
+ goto out_valid_noupdate;
- dir_version = (long)dir->invalid_before;
- if (de_version - dir_version >= 0)
+ dir_version = dir->invalid_before;
+ if (de_version - (long)dir_version >= 0)
goto out_valid;
_debug("dir modified");
afs_stat_v(dir, n_reval);
/* search the directory for this vnode */
- ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key);
+ ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key, &dir_version);
switch (ret) {
case 0:
/* the filename maps to something */
@@ -1080,7 +1089,8 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
}
out_valid:
- dentry->d_fsdata = (void *)dir_version;
+ dentry->d_fsdata = (void *)(unsigned long)dir_version;
+out_valid_noupdate:
dput(parent);
key_put(key);
_leave(" = 1 [valid]");
@@ -1186,6 +1196,20 @@ static void afs_prep_for_new_inode(struct afs_fs_cursor *fc,
}
/*
+ * Note that a dentry got changed. We need to set d_fsdata to the data version
+ * number derived from the result of the operation. It doesn't matter if
+ * d_fsdata goes backwards as we'll just revalidate.
+ */
+static void afs_update_dentry_version(struct afs_fs_cursor *fc,
+ struct dentry *dentry,
+ struct afs_status_cb *scb)
+{
+ if (fc->ac.error == 0)
+ dentry->d_fsdata =
+ (void *)(unsigned long)scb->status.data_version;
+}
+
+/*
* create a directory on an AFS filesystem
*/
static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
@@ -1227,6 +1251,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
afs_check_for_remote_deletion(&fc, dvnode);
afs_vnode_commit_status(&fc, dvnode, fc.cb_break,
&data_version, &scb[0]);
+ afs_update_dentry_version(&fc, dentry, &scb[0]);
afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]);
ret = afs_end_vnode_operation(&fc);
if (ret < 0)
@@ -1319,6 +1344,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
afs_vnode_commit_status(&fc, dvnode, fc.cb_break,
&data_version, scb);
+ afs_update_dentry_version(&fc, dentry, scb);
ret = afs_end_vnode_operation(&fc);
if (ret == 0) {
afs_dir_remove_subdir(dentry);
@@ -1458,6 +1484,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
&data_version, &scb[0]);
afs_vnode_commit_status(&fc, vnode, fc.cb_break_2,
&data_version_2, &scb[1]);
+ afs_update_dentry_version(&fc, dentry, &scb[0]);
ret = afs_end_vnode_operation(&fc);
if (ret == 0 && !(scb[1].have_status || scb[1].have_error))
ret = afs_dir_remove_link(dvnode, dentry, key);
@@ -1526,6 +1553,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
afs_check_for_remote_deletion(&fc, dvnode);
afs_vnode_commit_status(&fc, dvnode, fc.cb_break,
&data_version, &scb[0]);
+ afs_update_dentry_version(&fc, dentry, &scb[0]);
afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]);
ret = afs_end_vnode_operation(&fc);
if (ret < 0)
@@ -1607,6 +1635,7 @@ static int afs_link(struct dentry *from, struct inode *dir,
afs_vnode_commit_status(&fc, vnode, fc.cb_break_2,
NULL, &scb[1]);
ihold(&vnode->vfs_inode);
+ afs_update_dentry_version(&fc, dentry, &scb[0]);
d_instantiate(dentry, &vnode->vfs_inode);
mutex_unlock(&vnode->io_lock);
@@ -1686,6 +1715,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
afs_check_for_remote_deletion(&fc, dvnode);
afs_vnode_commit_status(&fc, dvnode, fc.cb_break,
&data_version, &scb[0]);
+ afs_update_dentry_version(&fc, dentry, &scb[0]);
afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]);
ret = afs_end_vnode_operation(&fc);
if (ret < 0)
@@ -1791,6 +1821,17 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
}
+ /* This bit is potentially nasty as there's a potential race with
+ * afs_d_revalidate{,_rcu}(). We have to change d_fsdata on the dentry
+ * to reflect it's new parent's new data_version after the op, but
+ * d_revalidate may see old_dentry between the op having taken place
+ * and the version being updated.
+ *
+ * So drop the old_dentry for now to make other threads go through
+ * lookup instead - which we hold a lock against.
+ */
+ d_drop(old_dentry);
+
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, orig_dvnode, key, true)) {
afs_dataversion_t orig_data_version;
@@ -1802,9 +1843,9 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (orig_dvnode != new_dvnode) {
if (mutex_lock_interruptible_nested(&new_dvnode->io_lock, 1) < 0) {
afs_end_vnode_operation(&fc);
- goto error_rehash;
+ goto error_rehash_old;
}
- new_data_version = new_dvnode->status.data_version;
+ new_data_version = new_dvnode->status.data_version + 1;
} else {
new_data_version = orig_data_version;
new_scb = &scb[0];
@@ -1827,7 +1868,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
ret = afs_end_vnode_operation(&fc);
if (ret < 0)
- goto error_rehash;
+ goto error_rehash_old;
}
if (ret == 0) {
@@ -1853,10 +1894,26 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
drop_nlink(new_inode);
spin_unlock(&new_inode->i_lock);
}
+
+ /* Now we can update d_fsdata on the dentries to reflect their
+ * new parent's data_version.
+ *
+ * Note that if we ever implement RENAME_EXCHANGE, we'll have
+ * to update both dentries with opposing dir versions.
+ */
+ if (new_dvnode != orig_dvnode) {
+ afs_update_dentry_version(&fc, old_dentry, &scb[1]);
+ afs_update_dentry_version(&fc, new_dentry, &scb[1]);
+ } else {
+ afs_update_dentry_version(&fc, old_dentry, &scb[0]);
+ afs_update_dentry_version(&fc, new_dentry, &scb[0]);
+ }
d_move(old_dentry, new_dentry);
goto error_tmp;
}
+error_rehash_old:
+ d_rehash(new_dentry);
error_rehash:
if (rehash)
d_rehash(rehash);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 56b69576274d..dd3c55c9101c 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -191,11 +191,13 @@ void afs_put_read(struct afs_read *req)
int i;
if (refcount_dec_and_test(&req->usage)) {
- for (i = 0; i < req->nr_pages; i++)
- if (req->pages[i])
- put_page(req->pages[i]);
- if (req->pages != req->array)
- kfree(req->pages);
+ if (req->pages) {
+ for (i = 0; i < req->nr_pages; i++)
+ if (req->pages[i])
+ put_page(req->pages[i]);
+ if (req->pages != req->array)
+ kfree(req->pages);
+ }
kfree(req);
}
}
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index d7e0fd3c00df..cfb0ac4bd039 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -56,23 +56,24 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
struct afs_uuid__xdr *xdr;
struct afs_uuid *uuid;
int j;
+ int n = entry->nr_servers;
tmp = ntohl(uvldb->serverFlags[i]);
if (tmp & AFS_VLSF_DONTUSE ||
(new_only && !(tmp & AFS_VLSF_NEWREPSITE)))
continue;
if (tmp & AFS_VLSF_RWVOL) {
- entry->fs_mask[i] |= AFS_VOL_VTM_RW;
+ entry->fs_mask[n] |= AFS_VOL_VTM_RW;
if (vlflags & AFS_VLF_BACKEXISTS)
- entry->fs_mask[i] |= AFS_VOL_VTM_BAK;
+ entry->fs_mask[n] |= AFS_VOL_VTM_BAK;
}
if (tmp & AFS_VLSF_ROVOL)
- entry->fs_mask[i] |= AFS_VOL_VTM_RO;
- if (!entry->fs_mask[i])
+ entry->fs_mask[n] |= AFS_VOL_VTM_RO;
+ if (!entry->fs_mask[n])
continue;
xdr = &uvldb->serverNumber[i];
- uuid = (struct afs_uuid *)&entry->fs_server[i];
+ uuid = (struct afs_uuid *)&entry->fs_server[n];
uuid->time_low = xdr->time_low;
uuid->time_mid = htons(ntohl(xdr->time_mid));
uuid->time_hi_and_version = htons(ntohl(xdr->time_hi_and_version));
diff --git a/fs/block_dev.c b/fs/block_dev.c
index eb657ab94060..677cb364d33f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -345,24 +345,15 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
struct bio *bio;
bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0;
bool is_read = (iov_iter_rw(iter) == READ), is_sync;
- bool nowait = (iocb->ki_flags & IOCB_NOWAIT) != 0;
loff_t pos = iocb->ki_pos;
blk_qc_t qc = BLK_QC_T_NONE;
- gfp_t gfp;
- int ret;
+ int ret = 0;
if ((pos | iov_iter_alignment(iter)) &
(bdev_logical_block_size(bdev) - 1))
return -EINVAL;
- if (nowait)
- gfp = GFP_NOWAIT;
- else
- gfp = GFP_KERNEL;
-
- bio = bio_alloc_bioset(gfp, nr_pages, &blkdev_dio_pool);
- if (!bio)
- return -EAGAIN;
+ bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool);
dio = container_of(bio, struct blkdev_dio, bio);
dio->is_sync = is_sync = is_sync_kiocb(iocb);
@@ -384,7 +375,6 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
if (!is_poll)
blk_start_plug(&plug);
- ret = 0;
for (;;) {
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = pos >> 9;
@@ -409,14 +399,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
task_io_account_write(bio->bi_iter.bi_size);
}
- /*
- * Tell underlying layer to not block for resource shortage.
- * And if we would have blocked, return error inline instead
- * of through the bio->bi_end_io() callback.
- */
- if (nowait)
- bio->bi_opf |= (REQ_NOWAIT | REQ_NOWAIT_INLINE);
-
+ dio->size += bio->bi_iter.bi_size;
pos += bio->bi_iter.bi_size;
nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES);
@@ -428,13 +411,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
polled = true;
}
- dio->size += bio->bi_iter.bi_size;
qc = submit_bio(bio);
- if (qc == BLK_QC_T_EAGAIN) {
- dio->size -= bio->bi_iter.bi_size;
- ret = -EAGAIN;
- goto error;
- }
if (polled)
WRITE_ONCE(iocb->ki_cookie, qc);
@@ -455,19 +432,8 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
atomic_inc(&dio->ref);
}
- dio->size += bio->bi_iter.bi_size;
- qc = submit_bio(bio);
- if (qc == BLK_QC_T_EAGAIN) {
- dio->size -= bio->bi_iter.bi_size;
- ret = -EAGAIN;
- goto error;
- }
-
- bio = bio_alloc(gfp, nr_pages);
- if (!bio) {
- ret = -EAGAIN;
- goto error;
- }
+ submit_bio(bio);
+ bio = bio_alloc(GFP_KERNEL, nr_pages);
}
if (!is_poll)
@@ -487,7 +453,6 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
}
__set_current_state(TASK_RUNNING);
-out:
if (!ret)
ret = blk_status_to_errno(dio->bio.bi_status);
if (likely(!ret))
@@ -495,10 +460,6 @@ out:
bio_put(&dio->bio);
return ret;
-error:
- if (!is_poll)
- blk_finish_plug(&plug);
- goto out;
}
static ssize_t
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 299e11e6c554..94660063a162 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -401,7 +401,6 @@ struct btrfs_dev_replace {
struct raid_kobject {
u64 flags;
struct kobject kobj;
- struct list_head list;
};
/*
@@ -915,8 +914,6 @@ struct btrfs_fs_info {
u32 thread_pool_size;
struct kobject *space_info_kobj;
- struct list_head pending_raid_kobjs;
- spinlock_t pending_raid_kobjs_lock; /* uncontended */
u64 total_pinned;
@@ -2698,7 +2695,6 @@ int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr);
int btrfs_make_block_group(struct btrfs_trans_handle *trans,
u64 bytes_used, u64 type, u64 chunk_offset,
u64 size);
-void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info);
struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
struct btrfs_fs_info *fs_info,
const u64 chunk_offset);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 5f7ee70b3d1a..97beb351a10c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2683,8 +2683,6 @@ int open_ctree(struct super_block *sb,
INIT_LIST_HEAD(&fs_info->delayed_iputs);
INIT_LIST_HEAD(&fs_info->delalloc_roots);
INIT_LIST_HEAD(&fs_info->caching_block_groups);
- INIT_LIST_HEAD(&fs_info->pending_raid_kobjs);
- spin_lock_init(&fs_info->pending_raid_kobjs_lock);
spin_lock_init(&fs_info->delalloc_root_lock);
spin_lock_init(&fs_info->trans_lock);
spin_lock_init(&fs_info->fs_roots_radix_lock);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d3b58e388535..8b7eb22d508a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4,6 +4,7 @@
*/
#include <linux/sched.h>
+#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
@@ -7888,33 +7889,6 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
return 0;
}
-/* link_block_group will queue up kobjects to add when we're reclaim-safe */
-void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info)
-{
- struct btrfs_space_info *space_info;
- struct raid_kobject *rkobj;
- LIST_HEAD(list);
- int ret = 0;
-
- spin_lock(&fs_info->pending_raid_kobjs_lock);
- list_splice_init(&fs_info->pending_raid_kobjs, &list);
- spin_unlock(&fs_info->pending_raid_kobjs_lock);
-
- list_for_each_entry(rkobj, &list, list) {
- space_info = btrfs_find_space_info(fs_info, rkobj->flags);
-
- ret = kobject_add(&rkobj->kobj, &space_info->kobj,
- "%s", btrfs_bg_type_to_raid_name(rkobj->flags));
- if (ret) {
- kobject_put(&rkobj->kobj);
- break;
- }
- }
- if (ret)
- btrfs_warn(fs_info,
- "failed to add kobject for block cache, ignoring");
-}
-
static void link_block_group(struct btrfs_block_group_cache *cache)
{
struct btrfs_space_info *space_info = cache->space_info;
@@ -7929,18 +7903,36 @@ static void link_block_group(struct btrfs_block_group_cache *cache)
up_write(&space_info->groups_sem);
if (first) {
- struct raid_kobject *rkobj = kzalloc(sizeof(*rkobj), GFP_NOFS);
+ struct raid_kobject *rkobj;
+ unsigned int nofs_flag;
+ int ret;
+
+ /*
+ * Setup a NOFS context because kobject_add(), deep in its call
+ * chain, does GFP_KERNEL allocations, and we are often called
+ * in a context where if reclaim is triggered we can deadlock
+ * (we are either holding a transaction handle or some lock
+ * required for a transaction commit).
+ */
+ nofs_flag = memalloc_nofs_save();
+ rkobj = kzalloc(sizeof(*rkobj), GFP_KERNEL);
if (!rkobj) {
+ memalloc_nofs_restore(nofs_flag);
btrfs_warn(cache->fs_info,
"couldn't alloc memory for raid level kobject");
return;
}
rkobj->flags = cache->flags;
kobject_init(&rkobj->kobj, &btrfs_raid_ktype);
-
- spin_lock(&fs_info->pending_raid_kobjs_lock);
- list_add_tail(&rkobj->list, &fs_info->pending_raid_kobjs);
- spin_unlock(&fs_info->pending_raid_kobjs_lock);
+ ret = kobject_add(&rkobj->kobj, &space_info->kobj, "%s",
+ btrfs_bg_type_to_raid_name(rkobj->flags));
+ memalloc_nofs_restore(nofs_flag);
+ if (ret) {
+ kobject_put(&rkobj->kobj);
+ btrfs_warn(fs_info,
+ "failed to add kobject for block cache, ignoring");
+ return;
+ }
space_info->block_group_kobjs[index] = &rkobj->kobj;
}
}
@@ -8206,7 +8198,6 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
inc_block_group_ro(cache, 1);
}
- btrfs_add_raid_kobjects(info);
btrfs_init_global_block_rsv(info);
ret = check_chunk_block_group_mappings(info);
error:
@@ -8975,6 +8966,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
struct btrfs_device *device;
struct list_head *devices;
u64 group_trimmed;
+ u64 range_end = U64_MAX;
u64 start;
u64 end;
u64 trimmed = 0;
@@ -8984,16 +8976,23 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
int dev_ret = 0;
int ret = 0;
+ /*
+ * Check range overflow if range->len is set.
+ * The default range->len is U64_MAX.
+ */
+ if (range->len != U64_MAX &&
+ check_add_overflow(range->start, range->len, &range_end))
+ return -EINVAL;
+
cache = btrfs_lookup_first_block_group(fs_info, range->start);
for (; cache; cache = next_block_group(cache)) {
- if (cache->key.objectid >= (range->start + range->len)) {
+ if (cache->key.objectid >= range_end) {
btrfs_put_block_group(cache);
break;
}
start = max(range->start, cache->key.objectid);
- end = min(range->start + range->len,
- cache->key.objectid + cache->key.offset);
+ end = min(range_end, cache->key.objectid + cache->key.offset);
if (end - start >= range->minlen) {
if (!block_group_cache_done(cache)) {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index d74b74ca07af..a447d3ec48d5 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3087,16 +3087,6 @@ static int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
if (ret)
return ret;
- /*
- * We add the kobjects here (and after forcing data chunk creation)
- * since relocation is the only place we'll create chunks of a new
- * type at runtime. The only place where we'll remove the last
- * chunk of a type is the call immediately below this one. Even
- * so, we're protected against races with the cleaner thread since
- * we're covered by the delete_unused_bgs_mutex.
- */
- btrfs_add_raid_kobjects(fs_info);
-
trans = btrfs_start_trans_remove_block_group(root->fs_info,
chunk_offset);
if (IS_ERR(trans)) {
@@ -3223,9 +3213,6 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
btrfs_end_transaction(trans);
if (ret < 0)
return ret;
-
- btrfs_add_raid_kobjects(fs_info);
-
return 1;
}
}
diff --git a/fs/io_uring.c b/fs/io_uring.c
index d542f1cf4428..24bbe3cb7ad4 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1097,10 +1097,8 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
iter->bvec = bvec + seg_skip;
iter->nr_segs -= seg_skip;
- iter->count -= (seg_skip << PAGE_SHIFT);
+ iter->count -= bvec->bv_len + offset;
iter->iov_offset = offset & ~PAGE_MASK;
- if (iter->iov_offset)
- iter->count -= iter->iov_offset;
}
}
@@ -2025,6 +2023,15 @@ static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
{
int ret;
+ ret = io_req_defer(ctx, req, s->sqe);
+ if (ret) {
+ if (ret != -EIOCBQUEUED) {
+ io_free_req(req);
+ io_cqring_add_event(ctx, s->sqe->user_data, ret);
+ }
+ return 0;
+ }
+
ret = __io_submit_sqe(ctx, req, s, true);
if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
struct io_uring_sqe *sqe_copy;
@@ -2097,13 +2104,6 @@ err:
return;
}
- ret = io_req_defer(ctx, req, s->sqe);
- if (ret) {
- if (ret != -EIOCBQUEUED)
- goto err_req;
- return;
- }
-
/*
* If we already have a head request, queue this one for async
* submittal once the head completes. If we don't have a head but
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 04f09689cd6d..1600034a929b 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -119,6 +119,7 @@ static int traverse(struct seq_file *m, loff_t offset)
}
if (seq_has_overflowed(m))
goto Eoverflow;
+ p = m->op->next(m, p, &m->index);
if (pos + m->count > offset) {
m->from = offset - pos;
m->count -= m->from;
@@ -126,7 +127,6 @@ static int traverse(struct seq_file *m, loff_t offset)
}
pos += m->count;
m->count = 0;
- p = m->op->next(m, p, &m->index);
if (pos == offset)
break;
}
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index baf0b72c0a37..07aad70f3931 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3835,15 +3835,28 @@ xfs_bmapi_read(
XFS_STATS_INC(mp, xs_blk_mapr);
ifp = XFS_IFORK_PTR(ip, whichfork);
+ if (!ifp) {
+ /* No CoW fork? Return a hole. */
+ if (whichfork == XFS_COW_FORK) {
+ mval->br_startoff = bno;
+ mval->br_startblock = HOLESTARTBLOCK;
+ mval->br_blockcount = len;
+ mval->br_state = XFS_EXT_NORM;
+ *nmap = 1;
+ return 0;
+ }
- /* No CoW fork? Return a hole. */
- if (whichfork == XFS_COW_FORK && !ifp) {
- mval->br_startoff = bno;
- mval->br_startblock = HOLESTARTBLOCK;
- mval->br_blockcount = len;
- mval->br_state = XFS_EXT_NORM;
- *nmap = 1;
- return 0;
+ /*
+ * A missing attr ifork implies that the inode says we're in
+ * extents or btree format but failed to pass the inode fork
+ * verifier while trying to load it. Treat that as a file
+ * corruption too.
+ */
+#ifdef DEBUG
+ xfs_alert(mp, "%s: inode %llu missing fork %d",
+ __func__, ip->i_ino, whichfork);
+#endif /* DEBUG */
+ return -EFSCORRUPTED;
}
if (!(ifp->if_flags & XFS_IFEXTENTS)) {
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index d1c77fd0815d..0bf56e94bfe9 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -487,10 +487,8 @@ xfs_da3_split(
ASSERT(state->path.active == 0);
oldblk = &state->path.blk[0];
error = xfs_da3_root_split(state, oldblk, addblk);
- if (error) {
- addblk->bp = NULL;
- return error; /* GROT: dir is inconsistent */
- }
+ if (error)
+ goto out;
/*
* Update pointers to the node which used to be block 0 and just got
@@ -505,7 +503,10 @@ xfs_da3_split(
*/
node = oldblk->bp->b_addr;
if (node->hdr.info.forw) {
- ASSERT(be32_to_cpu(node->hdr.info.forw) == addblk->blkno);
+ if (be32_to_cpu(node->hdr.info.forw) != addblk->blkno) {
+ error = -EFSCORRUPTED;
+ goto out;
+ }
node = addblk->bp->b_addr;
node->hdr.info.back = cpu_to_be32(oldblk->blkno);
xfs_trans_log_buf(state->args->trans, addblk->bp,
@@ -514,15 +515,19 @@ xfs_da3_split(
}
node = oldblk->bp->b_addr;
if (node->hdr.info.back) {
- ASSERT(be32_to_cpu(node->hdr.info.back) == addblk->blkno);
+ if (be32_to_cpu(node->hdr.info.back) != addblk->blkno) {
+ error = -EFSCORRUPTED;
+ goto out;
+ }
node = addblk->bp->b_addr;
node->hdr.info.forw = cpu_to_be32(oldblk->blkno);
xfs_trans_log_buf(state->args->trans, addblk->bp,
XFS_DA_LOGRANGE(node, &node->hdr.info,
sizeof(node->hdr.info)));
}
+out:
addblk->bp = NULL;
- return 0;
+ return error;
}
/*
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index afcc6642690a..1fc44efc344d 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -741,7 +741,8 @@ xfs_dir2_leafn_lookup_for_entry(
ents = dp->d_ops->leaf_ents_p(leaf);
xfs_dir3_leaf_check(dp, bp);
- ASSERT(leafhdr.count > 0);
+ if (leafhdr.count <= 0)
+ return -EFSCORRUPTED;
/*
* Look up the hash value in the leaf entries.
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 00e9f5c388d3..7fc3c1ad36bc 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -429,10 +429,7 @@ xfs_log_reserve(
ASSERT(*ticp == NULL);
tic = xlog_ticket_alloc(log, unit_bytes, cnt, client, permanent,
- KM_SLEEP | KM_MAYFAIL);
- if (!tic)
- return -ENOMEM;
-
+ KM_SLEEP);
*ticp = tic;
xlog_grant_push_ail(log, tic->t_cnt ? tic->t_unit_res * tic->t_cnt