Merge tag 'ceph-for-5.3-rc6' of git://github.com/ceph/ceph-client

Pull ceph fixes from Ilya Dryomov:
 "Three important fixes tagged for stable (an indefinite hang, a crash
  on an assert and a NULL pointer dereference) plus a small series from
  Luis fixing instances of vfree() under spinlock"

* tag 'ceph-for-5.3-rc6' of git://github.com/ceph/ceph-client:
  libceph: fix PG split vs OSD (re)connect race
  ceph: don't try fill file_lock on unsuccessful GETFILELOCK reply
  ceph: clear page dirty before invalidate page
  ceph: fix buffer free while holding i_ceph_lock in fill_inode()
  ceph: fix buffer free while holding i_ceph_lock in __ceph_build_xattrs_blob()
  ceph: fix buffer free while holding i_ceph_lock in __ceph_setxattr()
  libceph: allow ceph_buffer_put() to receive a NULL ceph_buffer

7 files changed, 30 insertions, 15 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e078cc55b989..b3c8b886bf64 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -913,8 +913,9 @@ get_more_pages:
 			if (page_offset(page) >= ceph_wbc.i_size) {
 				dout("%p page eof %llu\n",
 				     page, ceph_wbc.i_size);
-				if (ceph_wbc.size_stable ||
-				    page_offset(page) >= i_size_read(inode))
+				if ((ceph_wbc.size_stable ||
+				    page_offset(page) >= i_size_read(inode)) &&
+				    clear_page_dirty_for_io(page))
 					mapping->a_ops->invalidatepage(page,
 								0, PAGE_SIZE);
 				unlock_page(page);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d98dcd976c80..ce0f5658720a 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1301,6 +1301,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 {
 	struct ceph_inode_info *ci = cap->ci;
 	struct inode *inode = &ci->vfs_inode;
+	struct ceph_buffer *old_blob = NULL;
 	struct cap_msg_args arg;
 	int held, revoking;
 	int wake = 0;
@@ -1365,7 +1366,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 	ci->i_requested_max_size = arg.max_size;
 
 	if (flushing & CEPH_CAP_XATTR_EXCL) {
-		__ceph_build_xattrs_blob(ci);
+		old_blob = __ceph_build_xattrs_blob(ci);
 		arg.xattr_version = ci->i_xattrs.version;
 		arg.xattr_buf = ci->i_xattrs.blob;
 	} else {
@@ -1409,6 +1410,8 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 
 	spin_unlock(&ci->i_ceph_lock);
 
+	ceph_buffer_put(old_blob);
+
 	ret = send_cap_msg(&arg);
 	if (ret < 0) {
 		dout("error sending cap msg, must requeue %p\n", inode);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 791f84a13bb8..18500edefc56 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -736,6 +736,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	int issued, new_issued, info_caps;
 	struct timespec64 mtime, atime, ctime;
 	struct ceph_buffer *xattr_blob = NULL;
+	struct ceph_buffer *old_blob = NULL;
 	struct ceph_string *pool_ns = NULL;
 	struct ceph_cap *new_cap = NULL;
 	int err = 0;
@@ -881,7 +882,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	if ((ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL))  &&
 	    le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) {
 		if (ci->i_xattrs.blob)
-			ceph_buffer_put(ci->i_xattrs.blob);
+			old_blob = ci->i_xattrs.blob;
 		ci->i_xattrs.blob = xattr_blob;
 		if (xattr_blob)
 			memcpy(ci->i_xattrs.blob->vec.iov_base,
@@ -1022,8 +1023,8 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 out:
 	if (new_cap)
 		ceph_put_cap(mdsc, new_cap);
-	if (xattr_blob)
-		ceph_buffer_put(xattr_blob);
+	ceph_buffer_put(old_blob);
+	ceph_buffer_put(xattr_blob);
 	ceph_put_string(pool_ns);
 	return err;
 }
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index ac9b53b89365..5083e238ad15 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -111,8 +111,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
 		req->r_wait_for_completion = ceph_lock_wait_for_completion;
 
 	err = ceph_mdsc_do_request(mdsc, inode, req);
-
-	if (operation == CEPH_MDS_OP_GETFILELOCK) {
+	if (!err && operation == CEPH_MDS_OP_GETFILELOCK) {
 		fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
 		if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
 			fl->fl_type = F_RDLCK;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 4c6494eb02b5..ccfcc66aaf44 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -465,6 +465,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap_snap *capsnap;
 	struct ceph_snap_context *old_snapc, *new_snapc;
+	struct ceph_buffer *old_blob = NULL;
 	int used, dirty;
 
 	capsnap = kzalloc(sizeof(*capsnap), GFP_NOFS);
@@ -541,7 +542,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 	capsnap->gid = inode->i_gid;
 
 	if (dirty & CEPH_CAP_XATTR_EXCL) {
-		__ceph_build_xattrs_blob(ci);
+		old_blob = __ceph_build_xattrs_blob(ci);
 		capsnap->xattr_blob =
 			ceph_buffer_get(ci->i_xattrs.blob);
 		capsnap->xattr_version = ci->i_xattrs.version;
@@ -584,6 +585,7 @@ update_snapc:
 	}
 	spin_unlock(&ci->i_ceph_lock);
 
+	ceph_buffer_put(old_blob);
 	kfree(capsnap);
 	ceph_put_snap_context(old_snapc);
 }
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index d2352fd95dbc..6b9f1ee7de85 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -926,7 +926,7 @@ extern int ceph_getattr(const struct path *path, struct kstat *stat,
 int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int);
 ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t);
 extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
-extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
+extern struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci);
 extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
 extern const struct xattr_handler *ceph_xattr_handlers[];
 
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 37b458a9af3a..939eab7aa219 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -754,12 +754,15 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,
 
 /*
  * If there are dirty xattrs, reencode xattrs into the prealloc_blob
- * and swap into place.
+ * and swap into place.  It returns the old i_xattrs.blob (or NULL) so
+ * that it can be freed by the caller as the i_ceph_lock is likely to be
+ * held.
  */
-void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
+struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci)
 {
 	struct rb_node *p;
 	struct ceph_inode_xattr *xattr = NULL;
+	struct ceph_buffer *old_blob = NULL;
 	void *dest;
 
 	dout("__build_xattrs_blob %p\n", &ci->vfs_inode);
@@ -790,12 +793,14 @@ void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
 			dest - ci->i_xattrs.prealloc_blob->vec.iov_base;
 
 		if (ci->i_xattrs.blob)
-			ceph_buffer_put(ci->i_xattrs.blob);
+			old_blob = ci->i_xattrs.blob;
 		ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob;
 		ci->i_xattrs.prealloc_blob = NULL;
 		ci->i_xattrs.dirty = false;
 		ci->i_xattrs.version++;
 	}
+
+	return old_blob;
 }
 
 static inline int __get_request_mask(struct inode *in) {
@@ -1036,6 +1041,7 @@ int __ceph_setxattr(struct inode *inode, const char *name,
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_cap_flush *prealloc_cf = NULL;
+	struct ceph_buffer *old_blob = NULL;
 	int issued;
 	int err;
 	int dirty = 0;
@@ -1109,13 +1115,15 @@ retry:
 		struct ceph_buffer *blob;
 
 		spin_unlock(&ci->i_ceph_lock);
-		dout(" preaallocating new blob size=%d\n", required_blob_size);
+		ceph_buffer_put(old_blob); /* Shouldn't be required */
+		dout(" pre-allocating new blob size=%d\n", required_blob_size);
 		blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
 		if (!blob)
 			goto do_sync_unlocked;
 		spin_lock(&ci->i_ceph_lock);
+		/* prealloc_blob can't be released while holding i_ceph_lock */
 		if (ci->i_xattrs.prealloc_blob)
-			ceph_buffer_put(ci->i_xattrs.prealloc_blob);
+			old_blob = ci->i_xattrs.prealloc_blob;
 		ci->i_xattrs.prealloc_blob = blob;
 		goto retry;
 	}
@@ -1131,6 +1139,7 @@ retry:
 	}
 
 	spin_unlock(&ci->i_ceph_lock);
+	ceph_buffer_put(old_blob);
 	if (lock_snap_rwsem)
 		up_read(&mdsc->snap_rwsem);
 	if (dirty)