Merge tag 'v4.12-rc5' into nfsd tree

Update to get f0c3192ceee3 "virtio_net: lower limit on buffer size".
That bug was interfering with my nfsd testing.

70 files changed, 748 insertions, 404 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 643c70d2b2e6..4f8f75d9e839 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2563,7 +2563,7 @@ u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes);
 static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info,
 						 unsigned num_items)
 {
-	return fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
+	return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
 }
 
 /*
@@ -2573,7 +2573,7 @@ static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info,
 static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info,
 						 unsigned num_items)
 {
-	return fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
+	return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
 }
 
 int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index 60a750678a82..c24d615e3d7f 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -468,7 +468,7 @@ int verify_dir_item(struct btrfs_fs_info *fs_info,
 
 	if (btrfs_dir_name_len(leaf, dir_item) > namelen) {
 		btrfs_crit(fs_info, "invalid dir item name len: %u",
-		       (unsigned)btrfs_dir_data_len(leaf, dir_item));
+		       (unsigned)btrfs_dir_name_len(leaf, dir_item));
 		return 1;
 	}
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8685d67185d0..5f678dcb20e6 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3467,10 +3467,12 @@ static int write_dev_supers(struct btrfs_device *device,
 		 * we fua the first super.  The others we allow
 		 * to go down lazy.
 		 */
-		if (i == 0)
-			ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_FUA, bh);
-		else
+		if (i == 0) {
+			ret = btrfsic_submit_bh(REQ_OP_WRITE,
+						REQ_SYNC | REQ_FUA, bh);
+		} else {
 			ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+		}
 		if (ret)
 			errors++;
 	}
@@ -3535,7 +3537,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
 
 	bio->bi_end_io = btrfs_end_empty_barrier;
 	bio->bi_bdev = device->bdev;
-	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
 	init_completion(&device->flush_wait);
 	bio->bi_private = &device->flush_wait;
 	device->flush_bio = bio;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e390451c72e6..33d979e9ea2a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3993,6 +3993,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 				    info->space_info_kobj, "%s",
 				    alloc_name(found->flags));
 	if (ret) {
+		percpu_counter_destroy(&found->total_bytes_pinned);
 		kfree(found);
 		return ret;
 	}
@@ -4844,7 +4845,7 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 	spin_unlock(&delayed_rsv->lock);
 
 commit:
-	trans = btrfs_join_transaction(fs_info->fs_root);
+	trans = btrfs_join_transaction(fs_info->extent_root);
 	if (IS_ERR(trans))
 		return -ENOSPC;
 
@@ -4862,7 +4863,7 @@ static int flush_space(struct btrfs_fs_info *fs_info,
 		       struct btrfs_space_info *space_info, u64 num_bytes,
 		       u64 orig_bytes, int state)
 {
-	struct btrfs_root *root = fs_info->fs_root;
+	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_trans_handle *trans;
 	int nr;
 	int ret = 0;
@@ -5062,7 +5063,7 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 	int flush_state = FLUSH_DELAYED_ITEMS_NR;
 
 	spin_lock(&space_info->lock);
-	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
+	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->extent_root,
 						      space_info);
 	if (!to_reclaim) {
 		spin_unlock(&space_info->lock);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d8da3edf2ac3..d3619e010005 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2458,7 +2458,7 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 	if (!uptodate) {
 		ClearPageUptodate(page);
 		SetPageError(page);
-		ret = ret < 0 ? ret : -EIO;
+		ret = err < 0 ? err : -EIO;
 		mapping_set_error(page->mapping, ret);
 	}
 }
@@ -4377,6 +4377,123 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode,
 	return NULL;
 }
 
+/*
+ * To cache previous fiemap extent
+ *
+ * Will be used for merging fiemap extent
+ */
+struct fiemap_cache {
+	u64 offset;
+	u64 phys;
+	u64 len;
+	u32 flags;
+	bool cached;
+};
+
+/*
+ * Helper to submit fiemap extent.
+ *
+ * Will try to merge current fiemap extent specified by @offset, @phys,
+ * @len and @flags with cached one.
+ * And only when we fails to merge, cached one will be submitted as
+ * fiemap extent.
+ *
+ * Return value is the same as fiemap_fill_next_extent().
+ */
+static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
+				struct fiemap_cache *cache,
+				u64 offset, u64 phys, u64 len, u32 flags)
+{
+	int ret = 0;
+
+	if (!cache->cached)
+		goto assign;
+
+	/*
+	 * Sanity check, extent_fiemap() should have ensured that new
+	 * fiemap extent won't overlap with cahced one.
+	 * Not recoverable.
+	 *
+	 * NOTE: Physical address can overlap, due to compression
+	 */
+	if (cache->offset + cache->len > offset) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	/*
+	 * Only merges fiemap extents if
+	 * 1) Their logical addresses are continuous
+	 *
+	 * 2) Their physical addresses are continuous
+	 *    So truly compressed (physical size smaller than logical size)
+	 *    extents won't get merged with each other
+	 *
+	 * 3) Share same flags except FIEMAP_EXTENT_LAST
+	 *    So regular extent won't get merged with prealloc extent
+	 */
+	if (cache->offset + cache->len  == offset &&
+	    cache->phys + cache->len == phys  &&
+	    (cache->flags & ~FIEMAP_EXTENT_LAST) ==
+			(flags & ~FIEMAP_EXTENT_LAST)) {
+		cache->len += len;
+		cache->flags |= flags;
+		goto try_submit_last;
+	}
+
+	/* Not mergeable, need to submit cached one */
+	ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
+				      cache->len, cache->flags);
+	cache->cached = false;
+	if (ret)
+		return ret;
+assign:
+	cache->cached = true;
+	cache->offset = offset;
+	cache->phys = phys;
+	cache->len = len;
+	cache->flags = flags;
+try_submit_last:
+	if (cache->flags & FIEMAP_EXTENT_LAST) {
+		ret = fiemap_fill_next_extent(fieinfo, cache->offset,
+				cache->phys, cache->len, cache->flags);
+		cache->cached = false;
+	}
+	return ret;
+}
+
+/*
+ * Sanity check for fiemap cache
+ *
+ * All fiemap cache should be submitted by emit_fiemap_extent()
+ * Iteration should be terminated either by last fiemap extent or
+ * fieinfo->fi_extents_max.
+ * So no cached fiemap should exist.
+ */
+static int check_fiemap_cache(struct btrfs_fs_info *fs_info,
+			       struct fiemap_extent_info *fieinfo,
+			       struct fiemap_cache *cache)
+{
+	int ret;
+
+	if (!cache->cached)
+		return 0;
+
+	/* Small and recoverbale problem, only to info developer */
+#ifdef CONFIG_BTRFS_DEBUG
+	WARN_ON(1);
+#endif
+	btrfs_warn(fs_info,
+		   "unhandled fiemap cache detected: offset=%llu phys=%llu len=%llu flags=0x%x",
+		   cache->offset, cache->phys, cache->len, cache->flags);
+	ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
+				      cache->len, cache->flags);
+	cache->cached = false;
+	if (ret > 0)
+		ret = 0;
+	return ret;
+}
+
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len, get_extent_t *get_extent)
 {
@@ -4394,6 +4511,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	struct extent_state *cached_state = NULL;
 	struct btrfs_path *path;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct fiemap_cache cache = { 0 };
 	int end = 0;
 	u64 em_start = 0;
 	u64 em_len = 0;
@@ -4573,8 +4691,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			flags |= FIEMAP_EXTENT_LAST;
 			end = 1;
 		}
-		ret = fiemap_fill_next_extent(fieinfo, em_start, disko,
-					      em_len, flags);
+		ret = emit_fiemap_extent(fieinfo, &cache, em_start, disko,
+					   em_len, flags);
 		if (ret) {
 			if (ret == 1)
 				ret = 0;
@@ -4582,6 +4700,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		}
 	}
 out_free:
+	if (!ret)
+		ret = check_fiemap_cache(root->fs_info, fieinfo, &cache);
 	free_extent_map(em);
 out:
 	btrfs_free_path(path);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 17cbe9306faf..ef3c98c527c1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2952,7 +2952,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 
 	ret = test_range_bit(io_tree, ordered_extent->file_offset,
 			ordered_extent->file_offset + ordered_extent->len - 1,
-			EXTENT_DEFRAG, 1, cached_state);
+			EXTENT_DEFRAG, 0, cached_state);
 	if (ret) {
 		u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
 		if (0 && last_snapshot >= BTRFS_I(inode)->generation)
@@ -7483,8 +7483,8 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
 	int found = false;
 	void **pagep = NULL;
 	struct page *page = NULL;
-	int start_idx;
-	int end_idx;
+	unsigned long start_idx;
+	unsigned long end_idx;
 
 	start_idx = start >> PAGE_SHIFT;
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 3fdde0b283c9..29308a80d66f 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1671,8 +1671,12 @@ static long ceph_fallocate(struct file *file, int mode,
 	}
 
 	size = i_size_read(inode);
-	if (!(mode & FALLOC_FL_KEEP_SIZE))
+	if (!(mode & FALLOC_FL_KEEP_SIZE)) {
 		endoff = offset + length;
+		ret = inode_newsize_ok(inode, endoff);
+		if (ret)
+			goto unlock;
+	}
 
 	if (fi->fmode & CEPH_FILE_MODE_LAZY)
 		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 15bac390dff9..b98436f5c7c7 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1135,20 +1135,19 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
 	u32 acllen = 0;
 	int rc = 0;
 	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
-	struct cifs_tcon *tcon;
+	struct smb_version_operations *ops;
 
 	cifs_dbg(NOISY, "converting ACL to mode for %s\n", path);
 
 	if (IS_ERR(tlink))
 		return PTR_ERR(tlink);
-	tcon = tlink_tcon(tlink);
 
-	if (pfid && (tcon->ses->server->ops->get_acl_by_fid))
-		pntsd = tcon->ses->server->ops->get_acl_by_fid(cifs_sb, pfid,
-							  &acllen);
-	else if (tcon->ses->server->ops->get_acl)
-		pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
-							&acllen);
+	ops = tlink_tcon(tlink)->ses->server->ops;
+
+	if (pfid && (ops->get_acl_by_fid))
+		pntsd = ops->get_acl_by_fid(cifs_sb, pfid, &acllen);
+	else if (ops->get_acl)
+		pntsd = ops->get_acl(cifs_sb, inode, path, &acllen);
 	else {
 		cifs_put_tlink(tlink);
 		return -EOPNOTSUPP;
@@ -1181,23 +1180,23 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
 	struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
-	struct cifs_tcon *tcon;
+	struct smb_version_operations *ops;
 
 	if (IS_ERR(tlink))
 		return PTR_ERR(tlink);
-	tcon = tlink_tcon(tlink);
+
+	ops = tlink_tcon(tlink)->ses->server->ops;
 
 	cifs_dbg(NOISY, "set ACL from mode for %s\n", path);
 
 	/* Get the security descriptor */
 
-	if (tcon->ses->server->ops->get_acl == NULL) {
+	if (ops->get_acl == NULL) {
 		cifs_put_tlink(tlink);
 		return -EOPNOTSUPP;
 	}
 
-	pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
-						&secdesclen);
+	pntsd = ops->get_acl(cifs_sb, inode, path, &secdesclen);
 	if (IS_ERR(pntsd)) {
 		rc = PTR_ERR(pntsd);
 		cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc);
@@ -1224,13 +1223,12 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
 
 	cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc);
 
-	if (tcon->ses->server->ops->set_acl == NULL)
+	if (ops->set_acl == NULL)
 		rc = -EOPNOTSUPP;
 
 	if (!rc) {
 		/* Set the security descriptor */
-		rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode,
-						     path, aclflag);
+		rc = ops->set_acl(pnntsd, secdesclen, inode, path, aclflag);
 		cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc);
 	}
 	cifs_put_tlink(tlink);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 8be55be70faf..bcc7d9acad64 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -418,7 +418,7 @@ struct smb_version_operations {
 	int (*validate_negotiate)(const unsigned int, struct cifs_tcon *);
 	ssize_t (*query_all_EAs)(const unsigned int, struct cifs_tcon *,
 			const unsigned char *, const unsigned char *, char *,
-			size_t, const struct nls_table *, int);
+			size_t, struct cifs_sb_info *);
 	int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *,
 			const char *, const void *, const __u16,
 			const struct nls_table *, int);
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index e49958c3f8bb..6eb3147132e3 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -480,8 +480,7 @@ extern int CIFSSMBCopy(unsigned int xid,
 extern ssize_t CIFSSMBQAllEAs(const unsigned int xid, struct cifs_tcon *tcon,
 			const unsigned char *searchName,
 			const unsigned char *ea_name, char *EAData,
-			size_t bufsize, const struct nls_table *nls_codepage,
-			int remap_special_chars);
+			size_t bufsize, struct cifs_sb_info *cifs_sb);
 extern int CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon,
 		const char *fileName, const char *ea_name,
 		const void *ea_value, const __u16 ea_value_len,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 4c01b3f9abf0..fbb0d4cbda41 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -697,9 +697,7 @@ cifs_echo_callback(struct mid_q_entry *mid)
 {
 	struct TCP_Server_Info *server = mid->callback_data;
 
-	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
-	mutex_unlock(&server->srv_mutex);
 	add_credits(server, 1, CIFS_ECHO_OP);
 }
 
@@ -1599,9 +1597,7 @@ cifs_readv_callback(struct mid_q_entry *mid)
 	}
 
 	queue_work(cifsiod_wq, &rdata->work);
-	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
-	mutex_unlock(&server->srv_mutex);
 	add_credits(server, 1, 0);
 }
 
@@ -2058,7 +2054,6 @@ cifs_writev_callback(struct mid_q_entry *mid)
 {
 	struct cifs_writedata *wdata = mid->callback_data;
 	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
-	struct TCP_Server_Info *server = tcon->ses->server;
 	unsigned int written;
 	WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf;
 
@@ -2095,9 +2090,7 @@ cifs_writev_callback(struct mid_q_entry *mid)
 	}
 
 	queue_work(cifsiod_wq, &wdata->work);
-	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
-	mutex_unlock(&server->srv_mutex);
 	add_credits(tcon->ses->server, 1, 0);
 }
 
@@ -6076,11 +6069,13 @@ ssize_t
 CIFSSMBQAllEAs(const unsigned int xid, struct cifs_tcon *tcon,
 		const unsigned char *searchName, const unsigned char *ea_name,
 		char *EAData, size_t buf_size,
-		const struct nls_table *nls_codepage, int remap)
+		struct cifs_sb_info *cifs_sb)
 {
 		/* BB assumes one setup word */
 	TRANSACTION2_QPI_REQ *pSMB = NULL;
 	TRANSACTION2_QPI_RSP *pSMBr = NULL;
+	int remap = cifs_remap(cifs_sb);
+	struct nls_table *nls_codepage = cifs_sb->local_nls;
 	int rc = 0;
 	int bytes_returned;
 	int list_len;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 6ef78ad838e6..0fd081bd2a2f 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -582,7 +582,7 @@ cifs_relock_file(struct cifsFileInfo *cfile)
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	int rc = 0;
 
-	down_read(&cinode->lock_sem);
+	down_read_nested(&cinode->lock_sem, SINGLE_DEPTH_NESTING);
 	if (cinode->can_cache_brlcks) {
 		/* can cache locks - no need to relock */
 		up_read(&cinode->lock_sem);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index c3b2fa0b2ec8..4d1fcd76d022 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -563,8 +563,7 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path,
 
 	rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path,
 			"SETFILEBITS", ea_value, 4 /* size of buf */,
-			cifs_sb->local_nls,
-			cifs_remap(cifs_sb));
+			cifs_sb);
 	cifs_put_tlink(tlink);
 	if (rc < 0)
 		return (int)rc;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 48ff7703b919..e4afdaae743f 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1240,15 +1240,19 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 		goto tcon_exit;
 	}
 
-	if (rsp->ShareType & SMB2_SHARE_TYPE_DISK)
+	switch (rsp->ShareType) {
+	case SMB2_SHARE_TYPE_DISK:
 		cifs_dbg(FYI, "connection to disk share\n");
-	else if (rsp->ShareType & SMB2_SHARE_TYPE_PIPE) {
+		break;
+	case SMB2_SHARE_TYPE_PIPE:
 		tcon->ipc = true;
 		cifs_dbg(FYI, "connection to pipe share\n");
-	} else if (rsp->ShareType & SMB2_SHARE_TYPE_PRINT) {
-		tcon->print = true;
+		break;
+	case SMB2_SHARE_TYPE_PRINT:
+		tcon->ipc = true;
 		cifs_dbg(FYI, "connection to printer\n");
-	} else {
+		break;
+	default:
 		cifs_dbg(VFS, "unknown share type %d\n", rsp->ShareType);
 		rc = -EOPNOTSUPP;
 		goto tcon_error_exit;
@@ -2173,9 +2177,7 @@ smb2_echo_callback(struct mid_q_entry *mid)
 	if (mid->mid_state == MID_RESPONSE_RECEIVED)
 		credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest);
 
-	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
-	mutex_unlock(&server->srv_mutex);
 	add_credits(server, credits_received, CIFS_ECHO_OP);
 }
 
@@ -2433,9 +2435,7 @@ smb2_readv_ca