svn commit: r272130 - head/sys/kern

[Konstantin Belousov]

Author: kib
Date: Thu Sep 25 20:42:25 2014
New Revision: 272130
URL: http://svnweb.freebsd.org/changeset/base/272130

Log:
  In kern_linkat() and kern_renameat(), do not call namei(9) while
  holding a write reference on the filesystem.  Try to get write
  reference in unblocked way after all vnodes are resolved; if failed,
  drop all locks and retry after waiting for suspension end.
  
  The VFS_UNMOUNT() methods for UFS and tmpfs try to establish
  suspension on unmount, while covered vnode is locked by VFS, which
  prevents namei() from stepping over the mount point.  The thread doing
  namei() sleeps on the covered vnode lock, owning the write ref.
  
  Reported by:	bdrewery
  Tested by:	bdrewery (previous version), pho
  Sponsored by:	The FreeBSD Foundation
  MFC after:	1 week

Modified:
  head/sys/kern/vfs_syscalls.c

Modified: head/sys/kern/vfs_syscalls.c
==============================================================================
--- head/sys/kern/vfs_syscalls.c	Thu Sep 25 20:40:24 2014	(r272129)
+++ head/sys/kern/vfs_syscalls.c	Thu Sep 25 20:42:25 2014	(r272130)
@@ -1551,10 +1551,10 @@ kern_linkat(struct thread *td, int fd1, 
 	cap_rights_t rights;
 	int error;
 
+again:
 	bwillwrite();
 	NDINIT_AT(&nd, LOOKUP, follow | AUDITVNODE1, segflg, path1, fd1, td);
 
-again:
 	if ((error = namei(&nd)) != 0)
 		return (error);
 	NDFREE(&nd, NDF_ONLY_PNBUF);
@@ -1563,50 +1563,65 @@ again:
 		vrele(vp);
 		return (EPERM);		/* POSIX */
 	}
-	if ((error = vn_start_write(vp, &mp, V_WAIT | PCATCH)) != 0) {
-		vrele(vp);
-		return (error);
-	}
 	NDINIT_ATRIGHTS(&nd, CREATE, LOCKPARENT | SAVENAME | AUDITVNODE2,
 	    segflg, path2, fd2, cap_rights_init(&rights, CAP_LINKAT), td);
 	if ((error = namei(&nd)) == 0) {
 		if (nd.ni_vp != NULL) {
+			NDFREE(&nd, NDF_ONLY_PNBUF);
 			if (nd.ni_dvp == nd.ni_vp)
 				vrele(nd.ni_dvp);
 			else
 				vput(nd.ni_dvp);
 			vrele(nd.ni_vp);
-			error = EEXIST;
-		} else if ((error = vn_lock(vp, LK_EXCLUSIVE)) == 0) {
+			vrele(vp);
+			return (EEXIST);
+		} else if (nd.ni_dvp->v_mount != vp->v_mount) {
 			/*
-			 * Check for cross-device links.  No need to
-			 * recheck vp->v_type, since it cannot change
-			 * for non-doomed vnode.
+			 * Cross-device link.  No need to recheck
+			 * vp->v_type, since it cannot change, except
+			 * to VBAD.
 			 */
-			if (nd.ni_dvp->v_mount != vp->v_mount)
-				error = EXDEV;
-			else
-				error = can_hardlink(vp, td->td_ucred);
-			if (error == 0)
+			NDFREE(&nd, NDF_ONLY_PNBUF);
+			vput(nd.ni_dvp);
+			vrele(vp);
+			return (EXDEV);
+		} else if ((error = vn_lock(vp, LK_EXCLUSIVE)) == 0) {
+			error = can_hardlink(vp, td->td_ucred);
 #ifdef MAC
+			if (error == 0)
 				error = mac_vnode_check_link(td->td_ucred,
 				    nd.ni_dvp, vp, &nd.ni_cnd);
-			if (error == 0)
 #endif
-				error = VOP_LINK(nd.ni_dvp, vp, &nd.ni_cnd);
+			if (error != 0) {
+				vput(vp);
+				vput(nd.ni_dvp);
+				NDFREE(&nd, NDF_ONLY_PNBUF);
+				return (error);
+			}
+			error = vn_start_write(vp, &mp, V_NOWAIT);
+			if (error != 0) {
+				vput(vp);
+				vput(nd.ni_dvp);
+				NDFREE(&nd, NDF_ONLY_PNBUF);
+				error = vn_start_write(NULL, &mp,
+				    V_XSLEEP | PCATCH);
+				if (error != 0)
+					return (error);
+				goto again;
+			}
+			error = VOP_LINK(nd.ni_dvp, vp, &nd.ni_cnd);
 			VOP_UNLOCK(vp, 0);
 			vput(nd.ni_dvp);
+			vn_finished_write(mp);
+			NDFREE(&nd, NDF_ONLY_PNBUF);
 		} else {
 			vput(nd.ni_dvp);
 			NDFREE(&nd, NDF_ONLY_PNBUF);
 			vrele(vp);
-			vn_finished_write(mp);
 			goto again;
 		}
-		NDFREE(&nd, NDF_ONLY_PNBUF);
 	}
 	vrele(vp);
-	vn_finished_write(mp);
 	return (error);
 }
 
@@ -3519,6 +3534,7 @@ kern_renameat(struct thread *td, int old
 	cap_rights_t rights;
 	int error;
 
+again:
 	bwillwrite();
 #ifdef MAC
 	NDINIT_ATRIGHTS(&fromnd, DELETE, LOCKPARENT | LOCKLEAF | SAVESTART |
@@ -3539,14 +3555,6 @@ kern_renameat(struct thread *td, int old
 		VOP_UNLOCK(fromnd.ni_vp, 0);
 #endif
 	fvp = fromnd.ni_vp;
-	if (error == 0)
-		error = vn_start_write(fvp, &mp, V_WAIT | PCATCH);
-	if (error != 0) {
-		NDFREE(&fromnd, NDF_ONLY_PNBUF);
-		vrele(fromnd.ni_dvp);
-		vrele(fvp);
-		goto out1;
-	}
 	NDINIT_ATRIGHTS(&tond, RENAME, LOCKPARENT | LOCKLEAF | NOCACHE |
 	    SAVESTART | AUDITVNODE2, pathseg, new, newfd,
 	    cap_rights_init(&rights, CAP_LINKAT), td);
@@ -3559,11 +3567,30 @@ kern_renameat(struct thread *td, int old
 		NDFREE(&fromnd, NDF_ONLY_PNBUF);
 		vrele(fromnd.ni_dvp);
 		vrele(fvp);
-		vn_finished_write(mp);
 		goto out1;
 	}
 	tdvp = tond.ni_dvp;
 	tvp = tond.ni_vp;
+	error = vn_start_write(fvp, &mp, V_NOWAIT);
+	if (error != 0) {
+		NDFREE(&fromnd, NDF_ONLY_PNBUF);
+		NDFREE(&tond, NDF_ONLY_PNBUF);
+		if (tvp != NULL)
+			vput(tvp);
+		if (tdvp == tvp)
+			vrele(tdvp);
+		else
+			vput(tdvp);
+		vrele(fromnd.ni_dvp);
+		vrele(fvp);
+		vrele(tond.ni_startdir);
+		if (fromnd.ni_startdir != NULL)
+			vrele(fromnd.ni_startdir);
+		error = vn_start_write(NULL, &mp, V_XSLEEP | PCATCH);
+		if (error != 0)
+			return (error);
+		goto again;
+	}
 	if (tvp != NULL) {
 		if (fvp->v_type == VDIR && tvp->v_type != VDIR) {
 			error = ENOTDIR;