[PATCH AUTOSEL 4.19 112/206] nfsd: Don't add locks to closed or closing open stateids

[PATCH AUTOSEL 4.19 112/206] nfsd: Don't add locks to closed or closing open stateids

[Sasha Levin]

From: Trond Myklebust <trondmy@gmail.com>

[ Upstream commit a451b12311aa8c96c6f6e01c783a86995dc3ec6b ]

In NFSv4, the lock stateids are tied to the lockowner, and the open stateid,
so that the action of closing the file also results in either an automatic
loss of the locks, or an error of the form NFS4ERR_LOCKS_HELD.

In practice this means we must not add new locks to the open stateid
after the close process has been invoked. In fact doing so, can result
in the following panic:

 kernel BUG at lib/list_debug.c:51!
 invalid opcode: 0000 [#1] SMP NOPTI
 CPU: 2 PID: 1085 Comm: nfsd Not tainted 5.6.0-rc3+ #2
 Hardware name: VMware, Inc. VMware7,1/440BX Desktop Reference Platform, BIOS VMW71.00V.14410784.B64.1908150010 08/15/2019
 RIP: 0010:__list_del_entry_valid.cold+0x31/0x55
 Code: 1a 3d 9b e8 74 10 c2 ff 0f 0b 48 c7 c7 f0 1a 3d 9b e8 66 10 c2 ff 0f 0b 48 89 f2 48 89 fe 48 c7 c7 b0 1a 3d 9b e8 52 10 c2 ff <0f> 0b 48 89 fe 4c 89 c2 48 c7 c7 78 1a 3d 9b e8 3e 10 c2 ff 0f 0b
 RSP: 0018:ffffb296c1d47d90 EFLAGS: 00010246
 RAX: 0000000000000054 RBX: ffff8ba032456ec8 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: ffff8ba039e99cc8 RDI: ffff8ba039e99cc8
 RBP: ffff8ba032456e60 R08: 0000000000000781 R09: 0000000000000003
 R10: 0000000000000000 R11: 0000000000000001 R12: ffff8ba009a4abe0
 R13: ffff8ba032456e8c R14: 0000000000000000 R15: ffff8ba00adb01d8
 FS:  0000000000000000(0000) GS:ffff8ba039e80000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007fb213f0b008 CR3: 00000001347de006 CR4: 00000000003606e0
 Call Trace:
  release_lock_stateid+0x2b/0x80 [nfsd]
  nfsd4_free_stateid+0x1e9/0x210 [nfsd]
  nfsd4_proc_compound+0x414/0x700 [nfsd]
  ? nfs4svc_decode_compoundargs+0x407/0x4c0 [nfsd]
  nfsd_dispatch+0xc1/0x200 [nfsd]
  svc_process_common+0x476/0x6f0 [sunrpc]
  ? svc_sock_secure_port+0x12/0x30 [sunrpc]
  ? svc_recv+0x313/0x9c0 [sunrpc]
  ? nfsd_svc+0x2d0/0x2d0 [nfsd]
  svc_process+0xd4/0x110 [sunrpc]
  nfsd+0xe3/0x140 [nfsd]
  kthread+0xf9/0x130
  ? nfsd_destroy+0x50/0x50 [nfsd]
  ? kthread_park+0x90/0x90
  ret_from_fork+0x1f/0x40

The fix is to ensure that lock creation tests for whether or not the
open stateid is unhashed, and to fail if that is the case.

Fixes: 659aefb68eca ("nfsd: Ensure we don't recognise lock stateids after freeing them")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfsd/nfs4state.c | 73 ++++++++++++++++++++++++++-------------------
 1 file changed, 43 insertions(+), 30 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c24306af9758f..655079ae1dd1f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -471,6 +471,8 @@ find_any_file(struct nfs4_file *f)
 {
 	struct file *ret;
 
+	if (!f)
+		return NULL;
 	spin_lock(&f->fi_lock);
 	ret = __nfs4_get_fd(f, O_RDWR);
 	if (!ret) {
@@ -1207,6 +1209,12 @@ static void nfs4_put_stateowner(struct nfs4_stateowner *sop)
 	nfs4_free_stateowner(sop);
 }
 
+static bool
+nfs4_ol_stateid_unhashed(const struct nfs4_ol_stateid *stp)
+{
+	return list_empty(&stp->st_perfile);
+}
+
 static bool unhash_ol_stateid(struct nfs4_ol_stateid *stp)
 {
 	struct nfs4_file *fp = stp->st_stid.sc_file;
@@ -1274,9 +1282,11 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 {
 	lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);
 
+	if (!unhash_ol_stateid(stp))
+		return false;
 	list_del_init(&stp->st_locks);
 	nfs4_unhash_stid(&stp->st_stid);
-	return unhash_ol_stateid(stp);
+	return true;
 }
 
 static void release_lock_stateid(struct nfs4_ol_stateid *stp)
@@ -1341,13 +1351,12 @@ static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp,
 static bool unhash_open_stateid(struct nfs4_ol_stateid *stp,
 				struct list_head *reaplist)
 {
-	bool unhashed;
-
 	lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);
 
-	unhashed = unhash_ol_stateid(stp);
+	if (!unhash_ol_stateid(stp))
+		return false;
 	release_open_stateid_locks(stp, reaplist);
-	return unhashed;
+	return true;
 }
 
 static void release_open_stateid(struct nfs4_ol_stateid *stp)
@@ -5774,21 +5783,21 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp,
 }
 
 static struct nfs4_ol_stateid *
-find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
+find_lock_stateid(const struct nfs4_lockowner *lo,
+		  const struct nfs4_ol_stateid *ost)
 {
 	struct nfs4_ol_stateid *lst;
-	struct nfs4_client *clp = lo->lo_owner.so_client;
 
-	lockdep_assert_held(&clp->cl_lock);
+	lockdep_assert_held(&ost->st_stid.sc_client->cl_lock);
 
-	list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
-		if (lst->st_stid.sc_type != NFS4_LOCK_STID)
-			continue;
-		if (lst->st_stid.sc_file == fp) {
-			refcount_inc(&lst->st_stid.sc_count);
-			return lst;
+	/* If ost is not hashed, ost->st_locks will not be valid */
+	if (!nfs4_ol_stateid_unhashed(ost))
+		list_for_each_entry(lst, &ost->st_locks, st_locks) {
+			if (lst->st_stateowner == &lo->lo_owner) {
+				refcount_inc(&lst->st_stid.sc_count);
+				return lst;
+			}
 		}
-	}
 	return NULL;
 }
 
@@ -5804,11 +5813,11 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 	mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX);
 retry:
 	spin_lock(&clp->cl_lock);
-	spin_lock(&fp->fi_lock);
-	retstp = find_lock_stateid(lo, fp);
+	if (nfs4_ol_stateid_unhashed(open_stp))
+		goto out_close;
+	retstp = find_lock_stateid(lo, open_stp);
 	if (retstp)
-		goto out_unlock;
-
+		goto out_found;
 	refcount_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_LOCK_STID;
 	stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner);
@@ -5817,22 +5826,26 @@ retry:
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = open_stp->st_deny_bmap;
 	stp->st_openstp = open_stp;
+	spin_lock(&fp->fi_lock);
 	list_add(&stp->st_locks, &open_stp->st_locks);
 	list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
 	list_add(&stp->st_perfile, &fp->fi_stateids);
-out_unlock:
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&clp->cl_lock);
-	if (retstp) {
-		if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
-			nfs4_put_stid(&retstp->st_stid);
-			goto retry;
-		}
-		/* To keep mutex tracking happy */
-		mutex_unlock(&stp->st_mutex);
-		stp = retstp;
-	}
 	return stp;
+out_found:
+	spin_unlock(&clp->cl_lock);
+	if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
+		nfs4_put_stid(&retstp->st_stid);
+		goto retry;
+	}
+	/* To keep mutex tracking happy */
+	mutex_unlock(&stp->st_mutex);
+	return retstp;
+out_close:
+	spin_unlock(&clp->cl_lock);
+	mutex_unlock(&stp->st_mutex);
+	return NULL;
 }
 
 static struct nfs4_ol_stateid *
@@ -5847,7 +5860,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi,
 
 	*new = false;
 	spin_lock(&clp->cl_lock);
-	lst = find_lock_stateid(lo, fi);
+	lst = find_lock_stateid(lo, ost);
 	spin_unlock(&clp->cl_lock);
 	if (lst != NULL) {
 		if (nfsd4_lock_ol_stateid(lst) == nfs_ok)
-- 
2.25.1

[PATCH AUTOSEL 4.19 130/206] SUNRPC: Fix a potential buffer overflow in 'svc_print_xprts()'

[Sasha Levin]

From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>

[ Upstream commit b25b60d7bfb02a74bc3c2d998e09aab159df8059 ]

'maxlen' is the total size of the destination buffer. There is only one
caller and this value is 256.

When we compute the size already used and what we would like to add in
the buffer, the trailling NULL character is not taken into account.
However, this trailling character will be added by the 'strcat' once we
have checked that we have enough place.

So, there is a off-by-one issue and 1 byte of the stack could be
erroneously overwridden.

Take into account the trailling NULL, when checking if there is enough
place in the destination buffer.

While at it, also replace a 'sprintf' by a safer 'snprintf', check for
output truncation and avoid a superfluous 'strlen'.

Fixes: dc9a16e49dbba ("svc: Add /proc/sys/sunrpc/transport files")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
[ cel: very minor fix to documenting comment
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/svc_xprt.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index c8ee8e801edb8..709c082dc9059 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -103,8 +103,17 @@ void svc_unreg_xprt_class(struct svc_xprt_class *xcl)
 }
 EXPORT_SYMBOL_GPL(svc_unreg_xprt_class);
 
-/*
- * Format the transport list for printing
+/**
+ * svc_print_xprts - Format the transport list for printing
+ * @buf: target buffer for formatted address
+ * @maxlen: length of target buffer
+ *
+ * Fills in @buf with a string containing a list of transport names, each name
+ * terminated with '\n'. If the buffer is too small, some entries may be
+ * missing, but it is guaranteed that all lines in the output buffer are
+ * complete.
+ *
+ * Returns positive length of the filled-in string.
  */
 int svc_print_xprts(char *buf, int maxlen)
 {
@@ -117,9 +126,9 @@ int svc_print_xprts(char *buf, int maxlen)
 	list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
 		int slen;
 
-		sprintf(tmpstr, "%s %d\n", xcl->xcl_name, xcl->xcl_max_payload);
-		slen = strlen(tmpstr);
-		if (len + slen > maxlen)
+		slen = snprintf(tmpstr, sizeof(tmpstr), "%s %d\n",
+				xcl->xcl_name, xcl->xcl_max_payload);
+		if (slen >= sizeof(tmpstr) || len + slen >= maxlen)
 			break;
 		len += slen;
 		strcat(buf, tmpstr);
-- 
2.25.1

[PATCH AUTOSEL 4.19 131/206] svcrdma: Fix leak of transport addresses

[Sasha Levin]

From: Chuck Lever <chuck.lever@oracle.com>

[ Upstream commit 1a33d8a284b1e85e03b8c7b1ea8fb985fccd1d71 ]

Kernel memory leak detected:

unreferenced object 0xffff888849cdf480 (size 8):
  comm "kworker/u8:3", pid 2086, jiffies 4297898756 (age 4269.856s)
  hex dump (first 8 bytes):
    30 00 cd 49 88 88 ff ff                          0..I....
  backtrace:
    [<00000000acfc370b>] __kmalloc_track_caller+0x137/0x183
    [<00000000a2724354>] kstrdup+0x2b/0x43
    [<0000000082964f84>] xprt_rdma_format_addresses+0x114/0x17d [rpcrdma]
    [<00000000dfa6ed00>] xprt_setup_rdma_bc+0xc0/0x10c [rpcrdma]
    [<0000000073051a83>] xprt_create_transport+0x3f/0x1a0 [sunrpc]
    [<0000000053531a8e>] rpc_create+0x118/0x1cd [sunrpc]
    [<000000003a51b5f8>] setup_callback_client+0x1a5/0x27d [nfsd]
    [<000000001bd410af>] nfsd4_process_cb_update.isra.7+0x16c/0x1ac [nfsd]
    [<000000007f4bbd56>] nfsd4_run_cb_work+0x4c/0xbd [nfsd]
    [<0000000055c5586b>] process_one_work+0x1b2/0x2fe
    [<00000000b1e3e8ef>] worker_thread+0x1a6/0x25a
    [<000000005205fb78>] kthread+0xf6/0xfb
    [<000000006d2dc057>] ret_from_fork+0x3a/0x50

Introduce a call to xprt_rdma_free_addresses() similar to the way
that the TCP backchannel releases a transport's peer address
strings.

Fixes: 5d252f90a800 ("svcrdma: Add class for RDMA backwards direction transport")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index b9827665ff355..d183d4aee822c 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -256,6 +256,7 @@ xprt_rdma_bc_put(struct rpc_xprt *xprt)
 {
 	dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);
 
+	xprt_rdma_free_addresses(xprt);
 	xprt_free(xprt);
 	module_put(THIS_MODULE);
 }
-- 
2.25.1

[PATCH AUTOSEL 4.19 136/206] NFS: Fix races nfs_page_group_destroy() vs nfs_destroy_unlinked_subrequests()

[Sasha Levin]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

[ Upstream commit 08ca8b21f760c0ed5034a5c122092eec22ccf8f4 ]

When a subrequest is being detached from the subgroup, we want to
ensure that it is not holding the group lock, or in the process
of waiting for the group lock.

Fixes: 5b2b5187fa85 ("NFS: Fix nfs_page_group_destroy() and nfs_lock_and_join_requests() race cases")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfs/pagelist.c        | 67 +++++++++++++++++++++++++++-------------
 fs/nfs/write.c           | 10 ++++--
 include/linux/nfs_page.h |  2 ++
 3 files changed, 55 insertions(+), 24 deletions(-)

diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 5dae7c85d9b6e..2c7d76b4c5e18 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -132,47 +132,70 @@ nfs_async_iocounter_wait(struct rpc_task *task, struct nfs_lock_context *l_ctx)
 EXPORT_SYMBOL_GPL(nfs_async_iocounter_wait);
 
 /*
- * nfs_page_group_lock - lock the head of the page group
- * @req - request in group that is to be locked
+ * nfs_page_set_headlock - set the request PG_HEADLOCK
+ * @req: request that is to be locked
  *
- * this lock must be held when traversing or modifying the page
- * group list
+ * this lock must be held when modifying req->wb_head
  *
  * return 0 on success, < 0 on error
  */
 int
-nfs_page_group_lock(struct nfs_page *req)
+nfs_page_set_headlock(struct nfs_page *req)
 {
-	struct nfs_page *head = req->wb_head;
-
-	WARN_ON_ONCE(head != head->wb_head);
-
-	if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags))
+	if (!test_and_set_bit(PG_HEADLOCK, &req->wb_flags))
 		return 0;
 
-	set_bit(PG_CONTENDED1, &head->wb_flags);
+	set_bit(PG_CONTENDED1, &req->wb_flags);
 	smp_mb__after_atomic();
-	return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
+	return wait_on_bit_lock(&req->wb_flags, PG_HEADLOCK,
 				TASK_UNINTERRUPTIBLE);
 }
 
 /*
- * nfs_page_group_unlock - unlock the head of the page group
- * @req - request in group that is to be unlocked
+ * nfs_page_clear_headlock - clear the request PG_HEADLOCK
+ * @req: request that is to be locked
  */
 void
-nfs_page_group_unlock(struct nfs_page *req)
+nfs_page_clear_headlock(struct nfs_page *req)
 {
-	struct nfs_page *head = req->wb_head;
-
-	WARN_ON_ONCE(head != head->wb_head);
-
 	smp_mb__before_atomic();
-	clear_bit(PG_HEADLOCK, &head->wb_flags);
+	clear_bit(PG_HEADLOCK, &req->wb_flags);
 	smp_mb__after_atomic();
-	if (!test_bit(PG_CONTENDED1, &head->wb_flags))
+	if (!test_bit(PG_CONTENDED1, &req->wb_flags))
 		return;
-	wake_up_bit(&head->wb_flags, PG_HEADLOCK);
+	wake_up_bit(&req->wb_flags, PG_HEADLOCK);
+}
+
+/*
+ * nfs_page_group_lock - lock the head of the page group
+ * @req: request in group that is to be locked
+ *
+ * this lock must be held when traversing or modifying the page
+ * group list
+ *
+ * return 0 on success, < 0 on error
+ */
+int
+nfs_page_group_lock(struct nfs_page *req)
+{
+	int ret;
+
+	ret = nfs_page_set_headlock(req);
+	if (ret || req->wb_head == req)
+		return ret;
+	return nfs_page_set_headlock(req->wb_head);
+}
+
+/*
+ * nfs_page_group_unlock - unlock the head of the page group
+ * @req: request in group that is to be unlocked
+ */
+void
+nfs_page_group_unlock(struct nfs_page *req)
+{
+	if (req != req->wb_head)
+		nfs_page_clear_headlock(req->wb_head);
+	nfs_page_clear_headlock(req);
 }
 
 /*
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 63d20308a9bb7..d419d89b91f7c 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -416,22 +416,28 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list,
 		destroy_list = (subreq->wb_this_page == old_head) ?
 				   NULL : subreq->wb_this_page;
 
+		/* Note: lock subreq in order to change subreq->wb_head */
+		nfs_page_set_headlock(subreq);
 		WARN_ON_ONCE(old_head != subreq->wb_head);
 
 		/* make sure old group is not used */
 		subreq->wb_this_page = subreq;
+		subreq->wb_head = subreq;
 
 		clear_bit(PG_REMOVE, &subreq->wb_flags);
 
 		/* Note: races with nfs_page_group_destroy() */
 		if (!kref_read(&subreq->wb_kref)) {
 			/* Check if we raced with nfs_page_group_destroy() */
-			if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags))
+			if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags)) {
+				nfs_page_clear_headlock(subreq);
 				nfs_free_request(subreq);
+			} else
+				nfs_page_clear_headlock(subreq);
 			continue;
 		}
+		nfs_page_clear_headlock(subreq);
 
-		subreq->wb_head = subreq;
 		nfs_release_request(old_head);
 
 		if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) {
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index ad69430fd0eb5..5162fc1533c2f 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -142,6 +142,8 @@ extern	void nfs_unlock_and_release_request(struct nfs_page *);
 extern int nfs_page_group_lock(struct nfs_page *);
 extern void nfs_page_group_unlock(struct nfs_page *);
 extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int);
+extern	int nfs_page_set_headlock(struct nfs_page *req);
+extern void nfs_page_clear_headlock(struct nfs_page *req);
 extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *);
 
 /*
-- 
2.25.1