summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/ctree.c52
-rw-r--r--fs/btrfs/ioctl.c4
-rw-r--r--fs/btrfs/super.c4
-rw-r--r--fs/btrfs/transaction.h4
-rw-r--r--fs/erofs/decompressor_lzma.c5
-rw-r--r--fs/erofs/super.c2
-rw-r--r--fs/nfs/nfs4proc.c4
-rw-r--r--fs/nfs/nfs4state.c45
-rw-r--r--fs/nfs/write.c2
-rw-r--r--fs/overlayfs/export.c2
-rw-r--r--fs/overlayfs/file.c2
-rw-r--r--fs/overlayfs/ovl_entry.h10
-rw-r--r--fs/overlayfs/params.c17
-rw-r--r--fs/overlayfs/super.c27
-rw-r--r--fs/smb/client/connect.c26
-rw-r--r--fs/xfs/xfs_discard.c266
-rw-r--r--fs/xfs/xfs_discard.h6
-rw-r--r--fs/xfs/xfs_extent_busy.c34
-rw-r--r--fs/xfs/xfs_extent_busy.h24
-rw-r--r--fs/xfs/xfs_log_cil.c93
-rw-r--r--fs/xfs/xfs_log_priv.h5
21 files changed, 441 insertions, 193 deletions
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index a4cb4b642987..da519c1b6ad0 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -682,18 +682,30 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
u64 search_start;
int ret;
- if (test_bit(BTRFS_ROOT_DELETING, &root->state))
- btrfs_err(fs_info,
- "COW'ing blocks on a fs root that's being dropped");
-
- if (trans->transaction != fs_info->running_transaction)
- WARN(1, KERN_CRIT "trans %llu running %llu\n",
- trans->transid,
- fs_info->running_transaction->transid);
+ if (unlikely(test_bit(BTRFS_ROOT_DELETING, &root->state))) {
+ btrfs_abort_transaction(trans, -EUCLEAN);
+ btrfs_crit(fs_info,
+ "attempt to COW block %llu on root %llu that is being deleted",
+ buf->start, btrfs_root_id(root));
+ return -EUCLEAN;
+ }
- if (trans->transid != fs_info->generation)
- WARN(1, KERN_CRIT "trans %llu running %llu\n",
- trans->transid, fs_info->generation);
+ /*
+ * COWing must happen through a running transaction, which always
+ * matches the current fs generation (it's a transaction with a state
+ * less than TRANS_STATE_UNBLOCKED). If it doesn't, then turn the fs
+ * into error state to prevent the commit of any transaction.
+ */
+ if (unlikely(trans->transaction != fs_info->running_transaction ||
+ trans->transid != fs_info->generation)) {
+ btrfs_abort_transaction(trans, -EUCLEAN);
+ btrfs_crit(fs_info,
+"unexpected transaction when attempting to COW block %llu on root %llu, transaction %llu running transaction %llu fs generation %llu",
+ buf->start, btrfs_root_id(root), trans->transid,
+ fs_info->running_transaction->transid,
+ fs_info->generation);
+ return -EUCLEAN;
+ }
if (!should_cow_block(trans, root, buf)) {
*cow_ret = buf;
@@ -805,8 +817,22 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
int progress_passed = 0;
struct btrfs_disk_key disk_key;
- WARN_ON(trans->transaction != fs_info->running_transaction);
- WARN_ON(trans->transid != fs_info->generation);
+ /*
+ * COWing must happen through a running transaction, which always
+ * matches the current fs generation (it's a transaction with a state
+ * less than TRANS_STATE_UNBLOCKED). If it doesn't, then turn the fs
+ * into error state to prevent the commit of any transaction.
+ */
+ if (unlikely(trans->transaction != fs_info->running_transaction ||
+ trans->transid != fs_info->generation)) {
+ btrfs_abort_transaction(trans, -EUCLEAN);
+ btrfs_crit(fs_info,
+"unexpected transaction when attempting to reallocate parent %llu for root %llu, transaction %llu running transaction %llu fs generation %llu",
+ parent->start, btrfs_root_id(root), trans->transid,
+ fs_info->running_transaction->transid,
+ fs_info->generation);
+ return -EUCLEAN;
+ }
parent_nritems = btrfs_header_nritems(parent);
blocksize = fs_info->nodesize;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 75ab766fe156..8e7d03bc1b56 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2978,7 +2978,7 @@ static void get_block_group_info(struct list_head *groups_list,
static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info,
void __user *arg)
{
- struct btrfs_ioctl_space_args space_args;
+ struct btrfs_ioctl_space_args space_args = { 0 };
struct btrfs_ioctl_space_info space;
struct btrfs_ioctl_space_info *dest;
struct btrfs_ioctl_space_info *dest_orig;
@@ -4338,7 +4338,7 @@ static int _btrfs_ioctl_send(struct inode *inode, void __user *argp, bool compat
if (compat) {
#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT)
- struct btrfs_ioctl_send_args_32 args32;
+ struct btrfs_ioctl_send_args_32 args32 = { 0 };
ret = copy_from_user(&args32, argp, sizeof(args32));
if (ret)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 1a093ec0f7e3..f49e597e197f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -954,6 +954,10 @@ static int btrfs_parse_subvol_options(const char *options, char **subvol_name,
*subvol_objectid = subvolid;
break;
+ case Opt_err:
+ btrfs_err(NULL, "unrecognized mount option '%s'", p);
+ error = -EINVAL;
+ goto out;
default:
break;
}
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 6b309f8a99a8..93869cda6af9 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -219,8 +219,8 @@ do { \
(errno))) { \
/* Stack trace printed. */ \
} else { \
- btrfs_debug((trans)->fs_info, \
- "Transaction aborted (error %d)", \
+ btrfs_err((trans)->fs_info, \
+ "Transaction aborted (error %d)", \
(errno)); \
} \
} \
diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c
index 73091fbe3ea4..dee10d22ada9 100644
--- a/fs/erofs/decompressor_lzma.c
+++ b/fs/erofs/decompressor_lzma.c
@@ -217,9 +217,12 @@ again:
strm->buf.out_size = min_t(u32, outlen,
PAGE_SIZE - pageofs);
outlen -= strm->buf.out_size;
- if (!rq->out[no] && rq->fillgaps) /* deduped */
+ if (!rq->out[no] && rq->fillgaps) { /* deduped */
rq->out[no] = erofs_allocpage(pagepool,
GFP_KERNEL | __GFP_NOFAIL);
+ set_page_private(rq->out[no],
+ Z_EROFS_SHORTLIVED_PAGE);
+ }
if (rq->out[no])
strm->buf.out = kmap(rq->out[no]) + pageofs;
pageofs = 0;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 44a24d573f1f..3700af9ee173 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -235,7 +235,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
return PTR_ERR(ptr);
dis = ptr + erofs_blkoff(sb, *pos);
- if (!dif->path) {
+ if (!sbi->devs->flatdev && !dif->path) {
if (!dis->tag[0]) {
erofs_err(sb, "empty device tag @ pos %llu", *pos);
return -EINVAL;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 3508d8238826..7016eaadf555 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -10622,7 +10622,9 @@ static void nfs4_disable_swap(struct inode *inode)
*/
struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
- nfs4_schedule_state_manager(clp);
+ set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
+ clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
+ wake_up_var(&clp->cl_state);
}
static const struct inode_operations nfs4_dir_inode_operations = {
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e079987af4a3..9a5d911a7edc 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1209,16 +1209,26 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
{
struct task_struct *task;
char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1];
+ struct rpc_clnt *clnt = clp->cl_rpcclient;
+ bool swapon = false;
- if (clp->cl_rpcclient->cl_shutdown)
+ if (clnt->cl_shutdown)
return;
set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state);
- if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) {
- wake_up_var(&clp->cl_state);
- return;
+
+ if (atomic_read(&clnt->cl_swapper)) {
+ swapon = !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE,
+ &clp->cl_state);
+ if (!swapon) {
+ wake_up_var(&clp->cl_state);
+ return;
+ }
}
- set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
+
+ if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
+ return;
+
__module_get(THIS_MODULE);
refcount_inc(&clp->cl_count);
@@ -1235,8 +1245,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
__func__, PTR_ERR(task));
if (!nfs_client_init_is_complete(clp))
nfs_mark_client_ready(clp, PTR_ERR(task));
+ if (swapon)
+ clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
nfs4_clear_state_manager_bit(clp);
- clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
nfs_put_client(clp);
module_put(THIS_MODULE);
}
@@ -2703,6 +2714,13 @@ static void nfs4_state_manager(struct nfs_client *clp)
nfs4_end_drain_session(clp);
nfs4_clear_state_manager_bit(clp);
+ if (test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) &&
+ !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING,
+ &clp->cl_state)) {
+ memflags = memalloc_nofs_save();
+ continue;
+ }
+
if (!test_and_set_bit(NFS4CLNT_RECALL_RUNNING, &clp->cl_state)) {
if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) {
nfs_client_return_marked_delegations(clp);
@@ -2741,22 +2759,25 @@ static int nfs4_run_state_manager(void *ptr)
allow_signal(SIGKILL);
again:
- set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
nfs4_state_manager(clp);
- if (atomic_read(&cl->cl_swapper)) {
+
+ if (test_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) &&
+ !test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) {
wait_var_event_interruptible(&clp->cl_state,
test_bit(NFS4CLNT_RUN_MANAGER,
&clp->cl_state));
- if (atomic_read(&cl->cl_swapper) &&
- test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state))
+ if (!atomic_read(&cl->cl_swapper))
+ clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
+ if (refcount_read(&clp->cl_count) > 1 && !signalled() &&
+ !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state))
goto again;
/* Either no longer a swapper, or were signalled */
+ clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
}
- clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state);
if (refcount_read(&clp->cl_count) > 1 && !signalled() &&
test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) &&
- !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state))
+ !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state))
goto again;
nfs_put_client(clp);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 8c1ee1a1a28f..7720b5e43014 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -802,8 +802,8 @@ static void nfs_inode_remove_request(struct nfs_page *req)
}
if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
- nfs_release_request(req);
atomic_long_dec(&NFS_I(nfs_page_to_inode(req))->nrequests);
+ nfs_release_request(req);
}
}
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index c8c8588bd98c..26b782c53910 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -188,7 +188,7 @@ static int ovl_check_encode_origin(struct dentry *dentry)
/* Lower file handle for non-upper non-decodable */
if (!ovl_dentry_upper(dentry) && !decodable)
- return 0;
+ return 1;
/* Upper file handle for pure upper */
if (!ovl_dentry_lower(dentry))
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 693971d20280..8be4dc050d1e 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -341,7 +341,6 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
if (!aio_req)
goto out;
- real.flags = 0;
aio_req->orig_iocb = iocb;
kiocb_clone(&aio_req->iocb, iocb, get_file(real.file));
aio_req->iocb.ki_complete = ovl_aio_rw_complete;
@@ -413,7 +412,6 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
if (!aio_req)
goto out;
- real.flags = 0;
aio_req->orig_iocb = iocb;
kiocb_clone(&aio_req->iocb, iocb, get_file(real.file));
aio_req->iocb.ki_flags = ifl;
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index e9539f98e86a..d82d2a043da2 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -8,6 +8,7 @@
struct ovl_config {
char *upperdir;
char *workdir;
+ char **lowerdirs;
bool default_permissions;
int redirect_mode;
int verity_mode;
@@ -39,17 +40,8 @@ struct ovl_layer {
int idx;
/* One fsid per unique underlying sb (upper fsid == 0) */
int fsid;
- char *name;
};
-/*
- * ovl_free_fs() relies on @mnt being the first member when unmounting
- * the private mounts created for each layer. Let's check both the
- * offset and type.
- */
-static_assert(offsetof(struct ovl_layer, mnt) == 0);
-static_assert(__same_type(typeof_member(struct ovl_layer, mnt), struct vfsmount *));
-
struct ovl_path {
const struct ovl_layer *layer;
struct dentry *dentry;
diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c
index b9355bb6d75a..95b751507ac8 100644
--- a/fs/overlayfs/params.c
+++ b/fs/overlayfs/params.c
@@ -752,12 +752,12 @@ void ovl_free_fs(struct ovl_fs *ofs)
if (ofs->upperdir_locked)
ovl_inuse_unlock(ovl_upper_mnt(ofs)->mnt_root);
- /* Hack! Reuse ofs->layers as a vfsmount array before freeing it */
- mounts = (struct vfsmount **) ofs->layers;
+ /* Reuse ofs->config.lowerdirs as a vfsmount array before freeing it */
+ mounts = (struct vfsmount **) ofs->config.lowerdirs;
for (i = 0; i < ofs->numlayer; i++) {
iput(ofs->layers[i].trap);
+ kfree(ofs->config.lowerdirs[i]);
mounts[i] = ofs->layers[i].mnt;
- kfree(ofs->layers[i].name);
}
kern_unmount_array(mounts, ofs->numlayer);
kfree(ofs->layers);
@@ -765,6 +765,7 @@ void ovl_free_fs(struct ovl_fs *ofs)
free_anon_bdev(ofs->fs[i].pseudo_dev);
kfree(ofs->fs);
+ kfree(ofs->config.lowerdirs);
kfree(ofs->config.upperdir);
kfree(ofs->config.workdir);
if (ofs->creator_cred)
@@ -949,16 +950,16 @@ int ovl_show_options(struct seq_file *m, struct dentry *dentry)
struct super_block *sb = dentry->d_sb;
struct ovl_fs *ofs = OVL_FS(sb);
size_t nr, nr_merged_lower = ofs->numlayer - ofs->numdatalayer;
- const struct ovl_layer *data_layers = &ofs->layers[nr_merged_lower];
+ char **lowerdatadirs = &ofs->config.lowerdirs[nr_merged_lower];
- /* ofs->layers[0] is the upper layer */
- seq_printf(m, ",lowerdir=%s", ofs->layers[1].name);
+ /* lowerdirs[] starts from offset 1 */
+ seq_printf(m, ",lowerdir=%s", ofs->config.lowerdirs[1]);
/* dump regular lower layers */
for (nr = 2; nr < nr_merged_lower; nr++)
- seq_printf(m, ":%s", ofs->layers[nr].name);
+ seq_printf(m, ":%s", ofs->config.lowerdirs[nr]);
/* dump data lower layers */
for (nr = 0; nr < ofs->numdatalayer; nr++)
- seq_printf(m, "::%s", data_layers[nr].name);
+ seq_printf(m, "::%s", lowerdatadirs[nr]);
if (ofs->config.upperdir) {
seq_show_option(m, "upperdir", ofs->config.upperdir);
seq_show_option(m, "workdir", ofs->config.workdir);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index def266b5e2a3..3fa2416264a4 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -104,8 +104,8 @@ static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak)
static int ovl_dentry_revalidate_common(struct dentry *dentry,
unsigned int flags, bool weak)
{
- struct ovl_entry *oe = OVL_E(dentry);
- struct ovl_path *lowerstack = ovl_lowerstack(oe);
+ struct ovl_entry *oe;
+ struct ovl_path *lowerstack;
struct inode *inode = d_inode_rcu(dentry);
struct dentry *upper;
unsigned int i;
@@ -115,6 +115,8 @@ static int ovl_dentry_revalidate_common(struct dentry *dentry,
if (!inode)
return -ECHILD;
+ oe = OVL_I_E(inode);
+ lowerstack = ovl_lowerstack(oe);
upper = ovl_i_dentry_upper(inode);
if (upper)
ret = ovl_revalidate_real(upper, flags, weak);
@@ -167,6 +169,7 @@ static void ovl_free_inode(struct inode *inode)
struct ovl_inode *oi = OVL_I(inode);
kfree(oi->redirect);
+ kfree(oi->oe);
mutex_destroy(&oi->lock);
kmem_cache_free(ovl_inode_cachep, oi);
}
@@ -176,7 +179,7 @@ static void ovl_destroy_inode(struct inode *inode)
struct ovl_inode *oi = OVL_I(inode);
dput(oi->__upperdentry);
- ovl_free_entry(oi->oe);
+ ovl_stack_put(ovl_lowerstack(oi->oe), ovl_numlower(oi->oe));
if (S_ISDIR(inode->i_mode))
ovl_dir_cache_free(inode);
else
@@ -569,11 +572,6 @@ static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs,
upper_layer->idx = 0;
upper_layer->fsid = 0;
- err = -ENOMEM;
- upper_layer->name = kstrdup(ofs->config.upperdir, GFP_KERNEL);
- if (!upper_layer->name)
- goto out;
-
/*
* Inherit SB_NOSEC flag from upperdir.
*
@@ -1122,7 +1120,8 @@ static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
layers[ofs->numlayer].idx = ofs->numlayer;
layers[ofs->numlayer].fsid = fsid;
layers[ofs->numlayer].fs = &ofs->fs[fsid];
- layers[ofs->numlayer].name = l->name;
+ /* Store for printing lowerdir=... in ovl_show_options() */
+ ofs->config.lowerdirs[ofs->numlayer] = l->name;
l->name = NULL;
ofs->numlayer++;
ofs->fs[fsid].is_lower = true;
@@ -1367,8 +1366,16 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
if (!layers)
goto out_err;
+ ofs->config.lowerdirs = kcalloc(ctx->nr + 1, sizeof(char *), GFP_KERNEL);
+ if (!ofs->config.lowerdirs) {
+ kfree(layers);
+ goto out_err;
+ }
ofs->layers = layers;
- /* Layer 0 is reserved for upper even if there's no upper */
+ /*
+ * Layer 0 is reserved for upper even if there's no upper.
+ * For consistency, config.lowerdirs[0] is NULL.
+ */
ofs->numlayer = 1;
sb->s_stack_depth = 0;
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 3902e90dca6b..7b923e36501b 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -2474,8 +2474,9 @@ cifs_put_tcon(struct cifs_tcon *tcon)
static struct cifs_tcon *
cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
{
- int rc, xid;
struct cifs_tcon *tcon;
+ bool nohandlecache;
+ int rc, xid;
tcon = cifs_find_tcon(ses, ctx);
if (tcon) {
@@ -2493,14 +2494,17 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
goto out_fail;
}
- if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING)
- tcon = tcon_info_alloc(true);
+ if (ses->server->dialect >= SMB20_PROT_ID &&
+ (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING))
+ nohandlecache = ctx->nohandlecache;
else
- tcon = tcon_info_alloc(false);
+ nohandlecache = true;
+ tcon = tcon_info_alloc(!nohandlecache);
if (tcon == NULL) {
rc = -ENOMEM;
goto out_fail;
}
+ tcon->nohandlecache = nohandlecache;
if (ctx->snapshot_time) {
if (ses->server->vals->protocol_id == 0) {
@@ -2662,10 +2666,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
tcon->nocase = ctx->nocase;
tcon->broken_sparse_sup = ctx->no_sparse;
tcon->max_cached_dirs = ctx->max_cached_dirs;
- if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING)
- tcon->nohandlecache = ctx->nohandlecache;
- else
- tcon->nohandlecache = true;
tcon->nodelete = ctx->nodelete;
tcon->local_lease = ctx->local_lease;
INIT_LIST_HEAD(&tcon->pending_opens);
@@ -2895,9 +2895,9 @@ bind_socket(struct TCP_Server_Info *server)
if (server->srcaddr.ss_family != AF_UNSPEC) {
/* Bind to the specified local IP address */
struct socket *socket = server->ssocket;
- rc = socket->ops->bind(socket,
- (struct sockaddr *) &server->srcaddr,
- sizeof(server->srcaddr));
+ rc = kernel_bind(socket,
+ (struct sockaddr *) &server->srcaddr,
+ sizeof(server->srcaddr));
if (rc < 0) {
struct sockaddr_in *saddr4;
struct sockaddr_in6 *saddr6;
@@ -3046,8 +3046,8 @@ generic_ip_connect(struct TCP_Server_Info *server)
socket->sk->sk_sndbuf,
socket->sk->sk_rcvbuf, socket->sk->sk_rcvtimeo);
- rc = socket->ops->connect(socket, saddr, slen,
- server->noblockcnt ? O_NONBLOCK : 0);
+ rc = kernel_connect(socket, saddr, slen,
+ server->noblockcnt ? O_NONBLOCK : 0);
/*
* When mounting SMB root file systems, we do not want to block in
* connect. Otherwise bail out and then let cifs_reconnect() perform
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index afc4c78b9eed..d5787991bb5b 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * Copyright (C) 2010 Red Hat, Inc.
+ * Copyright (C) 2010, 2023 Red Hat, Inc.
* All Rights Reserved.
*/
#include "xfs.h"
@@ -19,21 +19,147 @@
#include "xfs_log.h"
#include "xfs_ag.h"
-STATIC int
-xfs_trim_extents(
+/*
+ * Notes on an efficient, low latency fstrim algorithm
+ *
+ * We need to walk the filesystem free space and issue discards on the free
+ * space that meet the search criteria (size and location). We cannot issue
+ * discards on extents that might be in use, or are so recently in use they are
+ * still marked as busy. To serialise against extent state changes whilst we are
+ * gathering extents to trim, we must hold the AGF lock to lock out other
+ * allocations and extent free operations that might change extent state.
+ *
+ * However, we cannot just hold the AGF for the entire AG free space walk whilst
+ * we issue discards on each free space that is found. Storage devices can have
+ * extremely slow discard implementations (e.g. ceph RBD) and so walking a
+ * couple of million free extents and issuing synchronous discards on each
+ * extent can take a *long* time. Whilst we are doing this walk, nothing else
+ * can access the AGF, and we can stall transactions and hence the log whilst
+ * modifications wait for the AGF lock to be released. This can lead hung tasks
+ * kicking the hung task timer and rebooting the system. This is bad.
+ *
+ * Hence we need to take a leaf from the bulkstat playbook. It takes the AGI
+ * lock, gathers a range of inode cluster buffers that are allocated, drops the
+ * AGI lock and then reads all the inode cluster buffers and processes them. It
+ * loops doing this, using a cursor to keep track of where it is up to in the AG
+ * for each iteration to restart the INOBT lookup from.
+ *
+ * We can't do this exactly with free space - once we drop the AGF lock, the
+ * state of the free extent is out of our control and we cannot run a discard
+ * safely on it in this situation. Unless, of course, we've marked the free
+ * extent as busy and undergoing a discard operation whilst we held the AGF
+ * locked.
+ *
+ * This is exactly how online discard works - free extents are marked busy when
+ * they are freed, and once the extent free has been committed to the journal,
+ * the busy extent record is marked as "undergoing discard" and the discard is
+ * then issued on the free extent. Once the discard completes, the busy extent
+ * record is removed and the extent is able to be allocated again.
+ *
+ * In the context of fstrim, if we find a free extent we need to discard, we
+ * don't have to discard it immediately. All we need to do it record that free
+ * extent as being busy and under discard, and all the allocation routines will
+ * now avoid trying to allocate it. Hence if we mark the extent as busy under
+ * the AGF lock, we can safely discard it without holding the AGF lock because
+ * nothing will attempt to allocate that free space until the discard completes.
+ *
+ * This also allows us to issue discards asynchronously like we do with online
+ * discard, and so for fast devices fstrim will run much faster as we can have
+ * multiple discard operations in flight at once, as well as pipeline the free
+ * extent search so that it overlaps in flight discard IO.
+ */
+
+struct workqueue_struct *xfs_discard_wq;
+
+static void
+xfs_discard_endio_work(
+ struct work_struct *work)
+{
+ struct xfs_busy_extents *extents =
+ container_of(work, struct xfs_busy_extents, endio_work);
+
+ xfs_extent_busy_clear(extents->mount, &extents->extent_list, false);
+ kmem_free(extents->owner);
+}
+
+/*
+ * Queue up the actual completion to a thread to avoid IRQ-safe locking for
+ * pagb_lock.
+ */
+static void
+xfs_discard_endio(
+ struct bio *bio)
+{
+ struct xfs_busy_extents *extents = bio->bi_private;
+
+ INIT_WORK(&extents->endio_work, xfs_discard_endio_work);
+ queue_work(xfs_discard_wq, &extents->endio_work);
+ bio_put(bio);
+}
+
+/*
+ * Walk the discard list and issue discards on all the busy extents in the
+ * list. We plug and chain the bios so that we only need a single completion
+ * call to clear all the busy extents once the discards are complete.
+ */
+int
+xfs_discard_extents(
+ struct xfs_mount *mp,
+ struct xfs_busy_extents *extents)
+{
+ struct xfs_extent_busy *busyp;
+ struct bio *bio = NULL;
+ struct blk_plug plug;
+ int error = 0;
+
+ blk_start_plug(&plug);
+ list_for_each_entry(busyp, &extents->extent_list, list) {
+ trace_xfs_discard_extent(mp, busyp->agno, busyp->bno,
+ busyp->length);
+
+ error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
+ XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
+ XFS_FSB_TO_BB(mp, busyp->length),
+ GFP_NOFS, &bio);
+ if (error && error != -EOPNOTSUPP) {
+ xfs_info(mp,
+ "discard failed for extent [0x%llx,%u], error %d",
+ (unsigned long long)busyp->bno,
+ busyp->length,
+ error);
+ break;
+ }
+ }
+
+ if (bio) {
+ bio->bi_private = extents;
+ bio->bi_end_io = xfs_discard_endio;
+ submit_bio(bio);
+ } else {
+ xfs_discard_endio_work(&extents->endio_work);
+ }
+ blk_finish_plug(&plug);
+
+ return error;
+}
+
+
+static int
+xfs_trim_gather_extents(
struct xfs_perag *pag,
xfs_daddr_t start,
xfs_daddr_t end,
xfs_daddr_t minlen,
+ struct xfs_alloc_rec_incore *tcur,
+ struct xfs_busy_extents *extents,
uint64_t *blocks_trimmed)
{
struct xfs_mount *mp = pag->pag_mount;
- struct block_device *bdev = mp->m_ddev_targp->bt_bdev;
struct xfs_btree_cur *cur;
struct xfs_buf *agbp;
- struct xfs_agf *agf;
int error;
int i;
+ int batch = 100;
/*
* Force out the log. This means any transactions that might have freed
@@ -45,20 +171,28 @@ xfs_trim_extents(
error = xfs_alloc_read_agf(pag, NULL, 0, &agbp);
if (error)
return error;
- agf = agbp->b_addr;
cur = xfs_allocbt_init_cursor(mp, NULL, agbp, pag, XFS_BTNUM_CNT);
/*
- * Look up the longest btree in the AGF and start with it.
+ * Look up the extent length requested in the AGF and start with it.
*/
- error = xfs_alloc_lookup_ge(cur, 0, be32_to_cpu(agf->agf_longest), &i);
+ if (tcur->ar_startblock == NULLAGBLOCK)
+ error = xfs_alloc_lookup_ge(cur, 0, tcur->ar_blockcount, &i);
+ else
+ error = xfs_alloc_lookup_le(cur, tcur->ar_startblock,
+ tcur->ar_blockcount, &i);
if (error)
goto out_del_cursor;
+ if (i == 0) {
+ /* nothing of that length left in the AG, we are done */
+ tcur->ar_blockcount = 0;
+ goto out_del_cursor;
+ }
/*
* Loop until we are done with all extents that are large
- * enough to be worth discarding.
+ * enough to be worth discarding or we hit batch limits.
*/
while (i) {
xfs_agblock_t fbno;
@@ -73,7 +207,16 @@ xfs_trim_extents(
error = -EFSCORRUPTED;
break;
}
- ASSERT(flen <= be32_to_cpu(agf->agf_longest));
+
+ if (--batch <= 0) {
+ /*
+ * Update the cursor to point at this extent so we
+ * restart the next batch from this extent.
+ */
+ tcur->ar_startblock = fbno;
+ tcur->ar_blockcount = flen;
+ break;
+ }
/*
* use daddr format for all range/len calculations as that is
@@ -88,6 +231,7 @@ xfs_trim_extents(
*/
if (dlen < minlen) {
trace_xfs_discard_toosmall(mp, pag->pag_agno, fbno, flen);
+ tcur->ar_blockcount = 0;
break;
}
@@ -110,29 +254,103 @@ xfs_trim_extents(
goto next_extent;
}
- trace_xfs_discard_extent(mp, pag->pag_agno, fbno, flen);
- error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS);
- if (error)
- break;
+ xfs_extent_busy_insert_discard(pag, fbno, flen,
+ &extents->extent_list);
*blocks_trimmed += flen;
-
next_extent:
error = xfs_btree_decrement(cur, 0, &i);
if (error)
break;
- if (fatal_signal_pending(current)) {
- error = -ERESTARTSYS;
- break;
- }
+ /*
+ * If there's no more records in the tree, we are done. Set the
+ * cursor block count to 0 to indicate to the caller that there
+ * is no more extents to search.
+ */
+ if (i == 0)
+ tcur->ar_blockcount = 0;
}
+ /*
+ * If there was an error, release all the gathered busy extents because
+ * we aren't going to issue a discard on them any more.
+ */
+ if (error)
+ xfs_extent_busy_clear(mp, &extents->extent_list, false);
out_del_cursor:
xfs_btree_del_cursor(cur, error);
xfs_buf_relse(agbp);
return error;
}
+static bool
+xfs_trim_should_stop(void)
+{
+ return fatal_signal_pending(current) || freezing(current);
+}
+
+/*
+ * Iterate the free list gathering extents and discarding them. We need a cursor
+ * for the repeated iteration of gather/discard loop, so use the longest extent
+ * we found in the last batch as the key to start the next.
+ */
+static int
+xfs_trim_extents(
+ struct xfs_perag *pag,
+ xfs_daddr_t start,
+ xfs_daddr_t end,
+ xfs_daddr_t minlen,
+ uint64_t *blocks_trimmed)
+{
+ struct xfs_alloc_rec_incore tcur = {
+ .ar_blockcount = pag->pagf_longest,
+ .ar_startblock = NULLAGBLOCK,
+ };
+ int error = 0;
+
+ do {
+ struct xfs_busy_extents *extents;
+
+ extents = kzalloc(sizeof(*extents), GFP_KERNEL);
+ if (!extents) {
+ error = -ENOMEM;
+ break;
+ }
+
+ extents->mount = pag->pag_mount;
+ extents->owner = extents;
+ INIT_LIST_HEAD(&extents->extent_list);
+
+ error = xfs_trim_gather_extents(pag, start, end, minlen,
+ &tcur, extents, blocks_trimmed);
+ if (error) {
+ kfree(extents);
+ break;
+ }
+
+ /*
+ * We hand the extent list to the discard function here so the
+ * discarded extents can be removed from the busy extent list.
+ * This allows the discards to run asynchronously with gathering
+ * the next round of extents to discard.
+ *
+ * However, we must ensure that we do not reference the extent
+ * list after this function call, as it may have been freed by
+ * the time control returns to us.
+ */
+ error = xfs_discard_extents(pag->pag_mount, extents);
+ if (error)
+ break;
+
+ if (xfs_trim_should_stop())
+ break;
+
+ } while (tcur.ar_blockcount != 0);
+
+ return error;
+
+}
+
/*
* trim a range of the filesystem.
*
@@ -195,12 +413,12 @@ xfs_ioc_trim(
for_each_perag_range(mp, agno, xfs_daddr_to_agno(mp, end), pag) {
error = xfs_trim_extents(pag, start, end, minlen,
&blocks_trimmed);
- if (error) {
+ if (error)
last_error = error;
- if (error == -ERESTARTSYS) {
- xfs_perag_rele(pag);
- break;
- }
+
+ if (xfs_trim_should_stop()) {
+ xfs_perag_rele(pag);
+ break;
}
}
diff --git a/fs/xfs/xfs_discard.h b/fs/xfs/xfs_discard.h
index de92d9cc958f..2b1a85223a56 100644
--- a/fs/xfs/xfs_discard.h
+++ b/fs/xfs/xfs_discard.h
@@ -3,8 +3,10 @@
#define XFS_DISCARD_H 1
struct fstrim_range;
-struct list_head;
+struct xfs_mount;
+struct xfs_busy_extents;
-extern int xfs_ioc_trim(struct xfs_mount *, struct fstrim_range __user *);
+int xfs_discard_extents(struct xfs_mount *mp, struct xfs_busy_extents *busy);
+int xfs_ioc_trim(struct xfs_mount *mp, struct fstrim_range __user *fstrim);
#endif /* XFS_DISCARD_H */
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 7c2fdc71e42d..746814815b1d 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -19,13 +19,13 @@
#include "xfs_log.h"
#include "xfs_ag.h"
-void
-xfs_extent_busy_insert(
- struct xfs_trans *tp,
+static void
+xfs_extent_busy_insert_list(
struct xfs_perag *pag,
xfs_agblock_t bno,
xfs_extlen_t len,
- unsigned int flags)
+ unsigned int flags,
+ struct list_head *busy_list)
{
struct xfs_extent_busy *new;
struct xfs_extent_busy *busyp;
@@ -40,7 +40,7 @@ xfs_extent_busy_insert(
new->flags = flags;
/* trace before insert to be able to see failed inserts */
- trace_xfs_extent_busy(tp->t_mountp, pag->pag_agno, bno, len);
+ trace_xfs_extent_busy(pag->pag_mount, pag->pag_agno, bno, len);
spin_lock(&pag->pagb_lock);
rbp = &pag->pagb_tree.rb_node;
@@ -62,10 +62,32 @@ xfs_extent_busy_insert(
rb_link_node(&new->rb_node, parent, rbp);
rb_insert_color(&new->rb_node, &pag->pagb_tree);
- list_add(&new->list, &tp->t_busy);
+ list_add(&new->list, busy_list);
spin_unlock(&pag->pagb_lock);
}
+void
+xfs_extent_busy_insert(
+ struct xfs_trans *tp,
+ struct xfs_perag *pag,
+ xfs_agblock_t bno,
+ xfs_extlen_t len,
+ unsigned int flags)
+{
+ xfs_extent_busy_insert_list(pag, bno, len, flags, &tp->t_busy);
+}
+
+void
+xfs_extent_busy_insert_discard(
+ struct xfs_perag *pag,
+ xfs_agblock_t bno,
+ xfs_extlen_t len,
+ struct list_head *busy_list)
+{
+ xfs_extent_busy_insert_list(pag, bno, len, XFS_EXTENT_BUSY_DISCARDED,
+ busy_list);
+}
+
/*
* Search for a busy extent within the range of the extent we are about to
* allocate. You need to be holding the busy extent tree lock when calling
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index c37bf87e6781..0639aab336f3 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -16,9 +16,6 @@ struct xfs_alloc_arg;
/*
* Busy block/extent entry. Indexed by a rbtree in perag to mark blocks that
* have been freed but whose transactions aren't committed to disk yet.
- *
- * Note that we use the transaction ID to record the transaction, not the
- * transaction structure itself. See xfs_extent_busy_insert() for details.
*/
struct xfs_extent_busy {
struct rb_node rb_node; /* ag by-bno indexed search tree */
@@ -31,11 +28,32 @@ struct xfs_extent_busy {
#define XFS_EXTENT_BUSY_SKIP_DISCARD 0x02 /* do not discard */
};
+/*
+ * List used to track groups of related busy extents all the way through
+ * to discard completion.
+ */
+struct xfs_busy_extents {
+ struct xfs_mount *mount;
+ struct list_head extent_list;
+ struct work_struct endio_work;
+
+ /*
+ * Owner is the object containing the struct xfs_busy_extents to free
+ * once the busy extents have been processed. If only the
+ * xfs_busy_extents object needs freeing, then point this at itself.
+ */
+ void *owner;
+};
+
void
xfs_extent_busy_insert(struct xfs_trans *tp, struct xfs_perag *pag,
xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags);
void
+xfs_extent_busy_insert_discard(struct xfs_perag *pag, xfs_agblock_t bno,
+ xfs_extlen_t len, struct list_head *busy_list);
+
+void
xfs_extent_busy_clear(struct xfs_mount *mp, struct list_head *list,
bool do_discard);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index ebc70aaa299c..67a99d94701e 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -16,8 +16,7 @@
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_trace.h"
-
-struct workqueue_struct *xfs_discard_wq;
+#include "xfs_discard.h"
/*
* Allocate a new ticket. Failing to get a new ticket makes it really hard to
@@ -103,7 +102,7 @@ xlog_cil_ctx_alloc(void)
ctx = kmem_zalloc(sizeof(*ctx), KM_NOFS);
INIT_LIST_HEAD(&ctx->committing);
- INIT_LIST_HEAD(&ctx->busy_extents);
+ INIT_LIST_HEAD(&ctx->busy_extents.extent_list);
INIT_LIST_HEAD(&ctx->log_items);
INIT_LIST_HEAD(&ctx->lv_chain);
INIT_WORK(&ctx->push_work, xlog_cil_push_work);
@@ -132,7 +131,7 @@ xlog_cil_push_pcp_aggregate(
if (!list_empty(&cilpcp->busy_extents)) {
list_splice_init(&cilpcp->busy_extents,
- &ctx->busy_extents);
+ &ctx->busy_extents.extent_list);
}
if (!list_empty(&cilpcp->log_items))
list_splice_init(&cilpcp->log_items, &ctx->log_items);
@@ -708,76 +707,6 @@ xlog_cil_free_logvec(
}
}
-static void
-xlog_discard_endio_work(
- struct work_struct *work)
-{
- struct xfs_cil_ctx *ctx =
- container_of(work, struct xfs_cil_ctx, discard_endio_work);
- struct xfs_mount *mp = ctx->cil->xc_log->l_mp;
-
- xfs_extent_busy_clear(mp, &ctx->busy_extents, false);
- kmem_free(ctx);
-}
-
-/*
- * Queue up the actual completion to a thread to avoid IRQ-safe locking for
- * pagb_lock. Note that we need a unbounded workqueue, otherwise we might
- * get the execution delayed up to 30 seconds for weird reasons.
- */
-static void
-xlog_discard_endio(
- struct bio *bio)
-{
- struct xfs_cil_ctx *ctx = bio->bi_private;
-
- INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work);
- queue_work(xfs_discard_wq, &ctx->discard_endio_work);
- bio_put(bio);
-}
-
-static void
-xlog_discard_busy_extents(
- struct xfs_mount *mp,
- struct xfs_cil_ctx *ctx)
-{
- struct list_head *list = &ctx->busy_extents;
- struct xfs_extent_busy *busyp;
- struct bio *bio = NULL;
- struct blk_plug plug;
- int error = 0;
-
- ASSERT(xfs_has_discard(mp));
-
- blk_start_plug(&plug);
- list_for_each_entry(busyp, list, list) {
- trace_xfs_discard_extent(mp, busyp->agno, busyp->bno,
- busyp->length);
-
- error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
- XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
- XFS_FSB_TO_BB(mp, busyp->length),
- GFP_NOFS, &bio);
- if (error && error != -EOPNOTSUPP) {
- xfs_info(mp,
- "discard failed for extent [0x%llx,%u], error %d",
- (unsigned long long)busyp->bno,
- busyp->length,
- error);
- break;
- }
- }
-
- if (bio) {
- bio->bi_private = ctx;
- bio->bi_end_io = xlog_discard_endio;
- submit_bio(bio);
- } else {
- xlog_discard_endio_work(&ctx->discard_endio_work);
- }
- blk_finish_plug(&plug);
-}
-
/*
* Mark all items committed and clear busy extents. We free the log vector
* chains in a separate pass so that we unpin the log items as quickly as
@@ -807,8 +736,8 @@ xlog_cil_committed(
xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, &ctx->lv_chain,
ctx->start_lsn, abort);
- xfs_extent_busy_sort(&ctx->busy_extents);
- xfs_extent_busy_clear(mp, &ctx->busy_extents,
+ xfs_extent_busy_sort(&ctx->busy_extents.extent_list);
+ xfs_extent_busy_clear(mp, &ctx->busy_extents.extent_list,
xfs_has_discard(mp) && !abort);
spin_lock(&ctx->cil->xc_push_lock);
@@ -817,10 +746,14 @@ xlog_cil_committed(
xlog_cil_free_logvec(&ctx->lv_chain);
- if (!list_empty(&ctx->busy_extents))
- xlog_discard_busy_extents(mp, ctx);
- else
- kmem_free(ctx);
+ if (!list_empty(&ctx->busy_extents.extent_list)) {
+ ctx->busy_extents.mount = mp;
+ ctx->busy_extents.owner = ctx;
+ xfs_discard_extents(mp, &ctx->busy_extents);
+ return;
+ }
+
+ kmem_free(ctx);
}
void
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index af87648331d5..fa3ad1d7b31c 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -6,6 +6,8 @@
#ifndef __XFS_LOG_PRIV_H__
#define __XFS_LOG_PRIV_H__
+#include "xfs_extent_busy.h" /* for struct xfs_busy_extents */
+
struct xfs_buf;
struct xlog;
struct xlog_ticket;
@@ -223,12 +225,11 @@ struct xfs_cil_ctx {
struct xlog_in_core *commit_iclog;
struct xlog_ticket *ticket; /* chkpt ticket */
atomic_t space_used; /* aggregate size of regions */
- struct list_head busy_extents; /* busy extents in chkpt */
+ struct xfs_busy_extents busy_extents;
struct list_head log_items; /* log items in chkpt */
struct list_head lv_chain; /* logvecs being pushed */
struct list_head iclog_entry;
struct list_head committing; /* ctx committing list */
- struct work_struct discard_endio_work;
struct work_struct push_work;
atomic_t order_id;
generated by cgit v1.2.3-58-ga151 (git 2.39.0) at 2024-11-22 05:20:40 +0000