10 files changed, 70 insertions, 31 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 210c94ac8818..4607af38c72e 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2647,7 +2647,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 
                 btrfs_free_delayed_extent_op(extent_op);
                 if (ret) {
+                        spin_lock(&delayed_refs->lock);
                         locked_ref->processing = 0;
+                        delayed_refs->num_heads_ready++;
+                        spin_unlock(&delayed_refs->lock);
                         btrfs_delayed_ref_unlock(locked_ref);
                         btrfs_put_delayed_ref(ref);
                         btrfs_debug(fs_info, "run_one_delayed_ref returned %d",
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 66a755150056..8ed05d95584a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5569,7 +5569,7 @@ void le_bitmap_set(u8 *map, unsigned int start, int len)
                 *p |= mask_to_set;
                 len -= bits_to_set;
                 bits_to_set = BITS_PER_BYTE;
-                mask_to_set = ~(u8)0;
+                mask_to_set = ~0;
                 p++;
         }
         if (len) {
@@ -5589,7 +5589,7 @@ void le_bitmap_clear(u8 *map, unsigned int start, int len)
                 *p &= ~mask_to_clear;
                 len -= bits_to_clear;
                 bits_to_clear = BITS_PER_BYTE;
-                mask_to_clear = ~(u8)0;
+                mask_to_clear = ~0;
                 p++;
         }
         if (len) {
@@ -5679,7 +5679,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
                 kaddr[offset] |= mask_to_set;
                 len -= bits_to_set;
                 bits_to_set = BITS_PER_BYTE;
-                mask_to_set = ~(u8)0;
+                mask_to_set = ~0;
                 if (++offset >= PAGE_SIZE && len > 0) {
                         offset = 0;
                         page = eb->pages[++i];
@@ -5721,7 +5721,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
                 kaddr[offset] &= ~mask_to_clear;
                 len -= bits_to_clear;
                 bits_to_clear = BITS_PER_BYTE;
-                mask_to_clear = ~(u8)0;
+                mask_to_clear = ~0;
                 if (++offset >= PAGE_SIZE && len > 0) {
                         offset = 0;
                         page = eb->pages[++i];
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2b790bda7998..8e3a5a266917 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4605,8 +4605,8 @@ delete:
                         BUG_ON(ret);
                         if (btrfs_should_throttle_delayed_refs(trans, root))
                                 btrfs_async_run_delayed_refs(root,
-                                                             trans->transid,
-                                        trans->delayed_ref_updates * 2, 0);
+                                        trans->delayed_ref_updates * 2,
+                                        trans->transid, 0);
                         if (be_nice) {
                                 if (truncate_space_check(trans, root,
                                                          extent_num_bytes)) {
@@ -8931,9 +8931,14 @@ again:
          *    So even we call qgroup_free_data(), it won't decrease reserved
          *    space.
          * 2) Not written to disk
-         *    This means the reserved space should be freed here.
+         *    This means the reserved space should be freed here. However,
+         *    if a truncate invalidates the page (by clearing PageDirty)
+         *    and the page is accounted for while allocating extent
+         *    in btrfs_check_data_free_space() we let delayed_ref to
+         *    free the entire extent.
          */
-        btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
+        if (PageDirty(page))
+                btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
         if (!inode_evicting) {
                 clear_extent_bit(tree, page_start, page_end,
                                  EXTENT_LOCKED | EXTENT_DIRTY |
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 18e1aa0f85f5..7acbd2cf6192 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3814,6 +3814,11 @@ process_slot:
                 }
                 btrfs_release_path(path);
                 key.offset = next_key_min_offset;
+
+                if (fatal_signal_pending(current)) {
+                        ret = -EINTR;
+                        goto out;
+                }
         }
         ret = 0;
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 0ec8ffa37ab0..c4af0cdb783d 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2728,7 +2728,14 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 
                 bytenr = btrfs_node_blockptr(upper->eb, slot);
                 if (lowest) {
-                        BUG_ON(bytenr != node->bytenr);
+                        if (bytenr != node->bytenr) {
+                                btrfs_err(root->fs_info,
+                "lowest leaf/node mismatch: bytenr %llu node->bytenr %llu slot %d upper %llu",
+                                          bytenr, node->bytenr, slot,
+                                          upper->eb->start);
+                                err = -EIO;
+                                goto next;
+                        }
                 } else {
                         if (node->eb->start == bytenr)
                                 goto next;
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index b10d557f9c9e..ee36efd5aece 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -84,6 +84,8 @@ struct nfsd_net {
         struct list_head client_lru;
         struct list_head close_lru;
         struct list_head del_recall_lru;
+
+        /* protected by blocked_locks_lock */
         struct list_head blocked_locks_lru;
 
         struct delayed_work laundromat_work;
@@ -91,6 +93,9 @@ struct nfsd_net {
         /* client_lock protects the client lru list and session hash table */
         spinlock_t client_lock;
 
+        /* protects blocked_locks_lru */
+        spinlock_t blocked_locks_lock;
+
         struct file *rec_file;
         bool in_grace;
         const struct nfsd4_client_tracking_ops *client_tracking_ops;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9752beb78659..4b4beaaa4eaa 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -217,7 +217,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 {
         struct nfsd4_blocked_lock *cur, *found = NULL;
 
-        spin_lock(&nn->client_lock);
+        spin_lock(&nn->blocked_locks_lock);
         list_for_each_entry(cur, &lo->lo_blocked, nbl_list) {
                 if (fh_match(fh, &cur->nbl_fh)) {
                         list_del_init(&cur->nbl_list);
@@ -226,7 +226,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
                         break;
                 }
         }
-        spin_unlock(&nn->client_lock);
+        spin_unlock(&nn->blocked_locks_lock);
         if (found)
                 posix_unblock_lock(&found->nbl_lock);
         return found;
@@ -1227,9 +1227,7 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp,
 
 static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 {
-        struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
-
-        lockdep_assert_held(&oo->oo_owner.so_client->cl_lock);
+        lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);
 
         list_del_init(&stp->st_locks);
         nfs4_unhash_stid(&stp->st_stid);
@@ -1238,12 +1236,12 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 
 static void release_lock_stateid(struct nfs4_ol_stateid *stp)
 {
-        struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
+        struct nfs4_client *clp = stp->st_stid.sc_client;
         bool unhashed;
 
-        spin_lock(&oo->oo_owner.so_client->cl_lock);
+        spin_lock(&clp->cl_lock);
         unhashed = unhash_lock_stateid(stp);
-        spin_unlock(&oo->oo_owner.so_client->cl_lock);
+        spin_unlock(&clp->cl_lock);
         if (unhashed)
                 nfs4_put_stid(&stp->st_stid);
 }
@@ -4665,7 +4663,7 @@ nfs4_laundromat(struct nfsd_net *nn)
          * indefinitely once the lock does become free.
          */
         BUG_ON(!list_empty(&reaplist));
-        spin_lock(&nn->client_lock);
+        spin_lock(&nn->blocked_locks_lock);
         while (!list_empty(&nn->blocked_locks_lru)) {
                 nbl = list_first_entry(&nn->blocked_locks_lru,
                                         struct nfsd4_blocked_lock, nbl_lru);
@@ -4678,7 +4676,7 @@ nfs4_laundromat(struct nfsd_net *nn)
                 list_move(&nbl->nbl_lru, &reaplist);
                 list_del_init(&nbl->nbl_list);
         }
-        spin_unlock(&nn->client_lock);
+        spin_unlock(&nn->blocked_locks_lock);
 
         while (!list_empty(&reaplist)) {
                 nbl = list_first_entry(&nn->blocked_locks_lru,
@@ -5439,13 +5437,13 @@ nfsd4_lm_notify(struct file_lock *fl)
         bool queue = false;
 
         /* An empty list means that something else is going to be using it */
-        spin_lock(&nn->client_lock);
+        spin_lock(&nn->blocked_locks_lock);
         if (!list_empty(&nbl->nbl_list)) {
                 list_del_init(&nbl->nbl_list);
                 list_del_init(&nbl->nbl_lru);
                 queue = true;
         }
-        spin_unlock(&nn->client_lock);
+        spin_unlock(&nn->blocked_locks_lock);
 
         if (queue)
                 nfsd4_run_cb(&nbl->nbl_cb);
@@ -5868,10 +5866,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
         if (fl_flags & FL_SLEEP) {
                 nbl->nbl_time = jiffies;
-                spin_lock(&nn->client_lock);
+                spin_lock(&nn->blocked_locks_lock);
                 list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked);
                 list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru);
-                spin_unlock(&nn->client_lock);
+                spin_unlock(&nn->blocked_locks_lock);
         }
 
         err = vfs_lock_file(filp, F_SETLK, file_lock, conflock);
@@ -5900,10 +5898,10 @@ out:
         if (nbl) {
                 /* dequeue it if we queued it before */
                 if (fl_flags & FL_SLEEP) {
-                        spin_lock(&nn->client_lock);
+                        spin_lock(&nn->blocked_locks_lock);
                         list_del_init(&nbl->nbl_list);
                         list_del_init(&nbl->nbl_lru);
-                        spin_unlock(&nn->client_lock);
+                        spin_unlock(&nn->blocked_locks_lock);
                 }
                 free_blocked_lock(nbl);
         }
@@ -6943,9 +6941,11 @@ static int nfs4_state_create_net(struct net *net)
         INIT_LIST_HEAD(&nn->client_lru);
         INIT_LIST_HEAD(&nn->close_lru);
         INIT_LIST_HEAD(&nn->del_recall_lru);
-        INIT_LIST_HEAD(&nn->blocked_locks_lru);
         spin_lock_init(&nn->client_lock);
 
+        spin_lock_init(&nn->blocked_locks_lock);
+        INIT_LIST_HEAD(&nn->blocked_locks_lru);
+
         INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
         get_net(net);
 
@@ -7063,14 +7063,14 @@ nfs4_state_shutdown_net(struct net *net)
         }
 
         BUG_ON(!list_empty(&reaplist));
-        spin_lock(&nn->client_lock);
+        spin_lock(&nn->blocked_locks_lock);
         while (!list_empty(&nn->blocked_locks_lru)) {
                 nbl = list_first_entry(&nn->blocked_locks_lru,
                                         struct nfsd4_blocked_lock, nbl_lru);
                 list_move(&nbl->nbl_lru, &reaplist);
                 list_del_init(&nbl->nbl_list);
         }
-        spin_unlock(&nn->client_lock);
+        spin_unlock(&nn->blocked_locks_lock);
 
         while (!list_empty(&reaplist)) {
                 nbl = list_first_entry(&nn->blocked_locks_lru,
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index aeb60f791418..36795eed40b0 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -178,6 +178,8 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
                 len -= bytes;
         }
 
+        if (!error)
+                error = vfs_fsync(new_file, 0);
         fput(new_file);
 out_fput:
         fput(old_file);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index c58f01babf30..7fb53d055537 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -270,9 +270,6 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type)
         if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
                 return NULL;
 
-        if (!realinode->i_op->get_acl)
-                return NULL;
-
         old_cred = ovl_override_creds(inode->i_sb);
         acl = get_acl(realinode, type);
         revert_creds(old_cred);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index bcf3965be819..edd46a0e951d 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1037,6 +1037,21 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
 
         posix_acl_release(acl);
 
+        /*
+         * Check if sgid bit needs to be cleared (actual setacl operation will
+         * be done with mounter's capabilities and so that won't do it for us).
+         */
+        if (unlikely(inode->i_mode & S_ISGID) &&
+            handler->flags == ACL_TYPE_ACCESS &&
+            !in_group_p(inode->i_gid) &&
+            !capable_wrt_inode_uidgid(inode, CAP_FSETID)) {
+                struct iattr iattr = { .ia_valid = ATTR_KILL_SGID };
+
+                err = ovl_setattr(dentry, &iattr);
+                if (err)
+                        return err;
+        }
+
         err = ovl_xattr_set(dentry, handler->name, value, size, flags);
         if (!err)
                 ovl_copyattr(ovl_inode_real(inode, NULL), inode);