4.9.51-stable review

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stefano Brivio <[email protected]>

[ Upstream commit 3de33e1ba0506723ab25734e098cf280ecc34756 ]

A packet length of exactly IPV6_MAXPLEN is allowed, we should refuse parsing options only if the size is 64KiB or more.

While at it, remove one extra variable and one assignment which were also introduced by the commit that introduced the size check. Checking the sum 'offset + len' and only later adding 'len' to 'offset' doesn't provide any advantage over directly summing to 'offset' and checking it.

---
 net/ipv6/output_core.c |    6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

@@ -86,7 +86,6 @@ int ip6_find_1stfragopt(struct sk_buff *
 
 	while (offset <= packet_len) {
 		struct ipv6_opt_hdr *exthdr;
-		unsigned int len;
 
 		switch (**nexthdr) {
 

@@ -112,10 +111,9 @@ int ip6_find_1stfragopt(struct sk_buff *
 
 		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
 						 offset);
-		len = ipv6_optlen(exthdr);
-		if (len + offset >= IPV6_MAXPLEN)
+		offset += ipv6_optlen(exthdr);
+		if (offset > IPV6_MAXPLEN)
 			return -EINVAL;
-		offset += len;
 		*nexthdr = &exthdr->nexthdr;
 	}
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Benjamin Poirier <[email protected]>

[ Upstream commit edbd58be15a957f6a760c4a514cd475217eb97fd ]

... which may happen with certain values of tp_reserve and maclen.

---
 net/packet/af_packet.c |   12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

@@ -2151,6 +2151,7 @@ static int tpacket_rcv(struct sk_buff *s
 	struct timespec ts;
 	__u32 ts_status;
 	bool is_drop_n_account = false;
+	bool do_vnet = false;
 
 	/* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
 	 * We may add members to them until current aligned size without forcing

@@ -2201,8 +2202,10 @@ static int tpacket_rcv(struct sk_buff *s
 		netoff = TPACKET_ALIGN(po->tp_hdrlen +
 				       (maclen < 16 ? 16 : maclen)) +
 				       po->tp_reserve;
-		if (po->has_vnet_hdr)
+		if (po->has_vnet_hdr) {
 			netoff += sizeof(struct virtio_net_hdr);
+			do_vnet = true;
+		}
 		macoff = netoff - maclen;
 	}
 	if (po->tp_version <= TPACKET_V2) {

@@ -2219,8 +2222,10 @@ static int tpacket_rcv(struct sk_buff *s
 					skb_set_owner_r(copy_skb, sk);
 			}
 			snaplen = po->rx_ring.frame_size - macoff;
-			if ((int)snaplen < 0)
+			if ((int)snaplen < 0) {
 				snaplen = 0;
+				do_vnet = false;
+			}
 		}
 	} else if (unlikely(macoff + snaplen >
 			    GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) {

@@ -2233,6 +2238,7 @@ static int tpacket_rcv(struct sk_buff *s
 		if (unlikely((int)snaplen < 0)) {
 			snaplen = 0;
 			macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len;
+			do_vnet = false;
 		}
 	}
 	spin_lock(&sk->sk_receive_queue.lock);

@@ -2258,7 +2264,7 @@ static int tpacket_rcv(struct sk_buff *s
 	}
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	if (po->has_vnet_hdr) {
+	if (do_vnet) {
 		if (__packet_rcv_vnet(skb, h.raw + macoff -
 					   sizeof(struct virtio_net_hdr))) {
 			spin_lock(&sk->sk_receive_queue.lock);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sabrina Dubroca <[email protected]>

[ Upstream commit ba1cc08d9488c94cb8d94f545305688b72a2a300 ]

fib6_net_exit only frees the main and local tables. If another table was created with fib6_alloc_table, we leak it when the netns is destroyed.

Fix this in the same way ip_fib_net_exit cleans up tables, by walking through the whole hashtable of fib6_table's. We can get rid of the special cases for local and main, since they're also part of the hashtable.

Reproducer:
ip netns add x
ip -net x -6 rule add from 6003:1::/64 table 100 ip netns del x

---
 net/ipv6/ip6_fib.c |   25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

@@ -201,6 +201,12 @@ static void rt6_release(struct rt6_info
 	}
 }
 
+static void fib6_free_table(struct fib6_table *table)
+{
+	inetpeer_invalidate_tree(&table->tb6_peers);
+	kfree(table);
+}
+
 static void fib6_link_table(struct net *net, struct fib6_table *tb)
 {
 	unsigned int h;

@@ -1893,15 +1899,22 @@ out_timer:
 
 static void fib6_net_exit(struct net *net)
 {
+	unsigned int i;
+
 	rt6_ifdown(net, NULL);
 	del_timer_sync(&net->ipv6.ip6_fib_timer);
 
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	inetpeer_invalidate_tree(&net->ipv6.fib6_local_tbl->tb6_peers);
-	kfree(net->ipv6.fib6_local_tbl);
-#endif
-	inetpeer_invalidate_tree(&net->ipv6.fib6_main_tbl->tb6_peers);
-	kfree(net->ipv6.fib6_main_tbl);
+	for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+		struct hlist_head *head = &net->ipv6.fib_table_hash[i];
+		struct hlist_node *tmp;
+		struct fib6_table *tb;
+
+		hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) {
+			hlist_del(&tb->tb6_hlist);
+			fib6_free_table(tb);
+		}
+	}
+
 	kfree(net->ipv6.fib_table_hash);
 	kfree(net->ipv6.rt6_stats);
 }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wei Wang <[email protected]>

[ Upstream commit c5cff8561d2d0006e972bd114afd51f082fee77c ]

We currently keep rt->rt6i_node pointing to the fib6_node for the route. And some functions make use of this pointer to dereference the fib6_node from rt structure, e.g. rt6_check(). However, as there is neither refcount nor rcu taken when dereferencing rt->rt6i_node, it could potentially cause crashes as rt->rt6i_node could be set to NULL by other CPUs when doing a route deletion.
This patch introduces an rcu grace period before freeing fib6_node and makes sure the functions that dereference it takes rcu_read_lock().

Note: there is no "Fixes" tag because this bug was there in a very early stage.

---
 include/net/ip6_fib.h |   30 +++++++++++++++++++++++++++++-
 net/ipv6/ip6_fib.c    |   20 ++++++++++++++++----
 net/ipv6/route.c      |   14 +++++++++++---
 3 files changed, 56 insertions(+), 8 deletions(-)

@@ -68,6 +68,7 @@ struct fib6_node {
 	__u16			fn_flags;
 	int			fn_sernum;
 	struct rt6_info		*rr_ptr;
+	struct rcu_head		rcu;
 };
 
 #ifndef CONFIG_IPV6_SUBTREES

@@ -165,13 +166,40 @@ static inline void rt6_update_expires(st
 	rt0->rt6i_flags |= RTF_EXPIRES;
 }
 
+/* Function to safely get fn->sernum for passed in rt
+ * and store result in passed in cookie.
+ * Return true if we can get cookie safely
+ * Return false if not
+ */
+static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
+				       u32 *cookie)
+{
+	struct fib6_node *fn;
+	bool status = false;
+
+	rcu_read_lock();
+	fn = rcu_dereference(rt->rt6i_node);
+
+	if (fn) {
+		*cookie = fn->fn_sernum;
+		status = true;
+	}
+
+	rcu_read_unlock();
+	return status;
+}
+
 static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 {
+	u32 cookie = 0;
+
 	if (rt->rt6i_flags & RTF_PCPU ||
 	    (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from))
 		rt = (struct rt6_info *)(rt->dst.from);
 
-	return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+	rt6_get_cookie_safe(rt, &cookie);
+
+	return cookie;
 }
 
 static inline void ip6_rt_put(struct rt6_info *rt)

@@ -148,11 +148,23 @@ static struct fib6_node *node_alloc(void
 	return fn;
 }
 
-static void node_free(struct fib6_node *fn)
+static void node_free_immediate(struct fib6_node *fn)
+{
+	kmem_cache_free(fib6_node_kmem, fn);
+}
+
+static void node_free_rcu(struct rcu_head *head)
 {
+	struct fib6_node *fn = container_of(head, struct fib6_node, rcu);
+
 	kmem_cache_free(fib6_node_kmem, fn);
 }
 
+static void node_free(struct fib6_node *fn)
+{
+	call_rcu(&fn->rcu, node_free_rcu);
+}
+
 static void rt6_rcu_free(struct rt6_info *rt)
 {
 	call_rcu(&rt->dst.rcu_head, dst_rcu_free);

@@ -589,9 +601,9 @@ insert_above:
 
 		if (!in || !ln) {
 			if (in)
-				node_free(in);
+				node_free_immediate(in);
 			if (ln)
-				node_free(ln);
+				node_free_immediate(ln);
 			return ERR_PTR(-ENOMEM);
 		}
 

@@ -1020,7 +1032,7 @@ int fib6_add(struct fib6_node *root, str
 				   root, and then (in failure) stale node
 				   in main tree.
 				 */
-				node_free(sfn);
+				node_free_immediate(sfn);
 				err = PTR_ERR(sn);
 				goto failure;
 			}

@@ -1267,7 +1267,9 @@ static void rt6_dst_from_metrics_check(s
 
 static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
 {
-	if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
+	u32 rt_cookie;
+
+	if (!rt6_get_cookie_safe(rt, &rt_cookie) || rt_cookie != cookie)
 		return NULL;
 
 	if (rt6_check_expired(rt))

@@ -1335,8 +1337,14 @@ static void ip6_link_failure(struct sk_b
 		if (rt->rt6i_flags & RTF_CACHE) {
 			dst_hold(&rt->dst);
 			ip6_del_rt(rt);
-		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) {
-			rt->rt6i_node->fn_sernum = -1;
+		} else {
+			struct fib6_node *fn;
+
+			rcu_read_lock();
+			fn = rcu_dereference(rt->rt6i_node);
+			if (fn && (rt->rt6i_flags & RTF_DEFAULT))
+				fn->fn_sernum = -1;
+			rcu_read_unlock();
 		}
 	}
 }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wei Wang <[email protected]>

[ Upstream commit 4e587ea71bf924f7dac621f1351653bd41e446cb ]

Commit c5cff8561d2d adds rcu grace period before freeing fib6_node. This generates a new sparse warning on rt->rt6i_node related code:
net/ipv6/route.c:1394:30: error: incompatible types in comparison expression (different address spaces) ./include/net/ip6_fib.h:187:14: error: incompatible types in comparison expression (different address spaces)

This commit adds "__rcu" tag for rt6i_node and makes sure corresponding rcu API is used for it.
After this fix, sparse no longer generates the above warning.

---
 include/net/ip6_fib.h |    2 +-
 net/ipv6/addrconf.c   |    2 +-
 net/ipv6/ip6_fib.c    |   11 +++++++----
 net/ipv6/route.c      |    3 ++-
 4 files changed, 11 insertions(+), 7 deletions(-)

@@ -103,7 +103,7 @@ struct rt6_info {
 	 * the same cache line.
 	 */
 	struct fib6_table		*rt6i_table;
-	struct fib6_node		*rt6i_node;
+	struct fib6_node __rcu		*rt6i_node;
 
 	struct in6_addr			rt6i_gateway;
 

@@ -5443,7 +5443,7 @@ static void __ipv6_ifa_notify(int event,
 		 * our DAD process, so we don't need
 		 * to do it again
 		 */
-		if (!(ifp->rt->rt6i_node))
+		if (!rcu_access_pointer(ifp->rt->rt6i_node))
 			ip6_ins_rt(ifp->rt);
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);

@@ -874,7 +874,7 @@ add:
 
 		rt->dst.rt6_next = iter;
 		*ins = rt;
-		rt->rt6i_node = fn;
+		rcu_assign_pointer(rt->rt6i_node, fn);
 		atomic_inc(&rt->rt6i_ref);
 		inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
 		info->nl_net->ipv6.rt6_stats->fib_rt_entries++;

@@ -899,7 +899,7 @@ add:
 			return err;
 
 		*ins = rt;
-		rt->rt6i_node = fn;
+		rcu_assign_pointer(rt->rt6i_node, fn);
 		rt->dst.rt6_next = iter->dst.rt6_next;
 		atomic_inc(&rt->rt6i_ref);
 		inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);

@@ -1459,8 +1459,9 @@ static void fib6_del_route(struct fib6_n
 
 int fib6_del(struct rt6_info *rt, struct nl_info *info)
 {
+	struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
+				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
 	struct net *net = info->nl_net;
-	struct fib6_node *fn = rt->rt6i_node;
 	struct rt6_info **rtp;
 
 #if RT6_DEBUG >= 2

@@ -1649,7 +1650,9 @@ static int fib6_clean_node(struct fib6_w
 			if (res) {
 #if RT6_DEBUG >= 2
 				pr_debug("%s: del failed: rt=%p@%p err=%d\n",
-					 __func__, rt, rt->rt6i_node, res);
+					 __func__, rt,
+					 rcu_access_pointer(rt->rt6i_node),
+					 res);
 #endif
 				continue;
 			}

@@ -1361,7 +1361,8 @@ static void rt6_do_update_pmtu(struct rt
 static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
 {
 	return !(rt->rt6i_flags & RTF_CACHE) &&
-		(rt->rt6i_flags & RTF_PCPU || rt->rt6i_node);
+		(rt->rt6i_flags & RTF_PCPU ||
+		 rcu_access_pointer(rt->rt6i_node));
 }
 
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sabrina Dubroca <[email protected]>

[ Upstream commit 78362998f58c7c271e2719dcd0aaced435c801f9 ]

This helps tools such as wpa_supplicant can start even if the macsec module isn't loaded yet.

---
 drivers/net/macsec.c |    1 +
 1 file changed, 1 insertion(+)

@@ -3510,6 +3510,7 @@ module_init(macsec_init);
 module_exit(macsec_exit);
 
 MODULE_ALIAS_RTNL_LINK("macsec");
+MODULE_ALIAS_GENL_FAMILY("macsec");
 
 MODULE_DESCRIPTION("MACsec IEEE 802.1AE");
 MODULE_LICENSE("GPL v2");

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit fd6055a806edc4019be1b9fb7d25262599bca5b1 ]

When peeking, if a bad csum is discovered, the skb is unlinked from the queue with __sk_queue_drop_skb and the peek operation restarted.

__sk_queue_drop_skb only drops packets that match the queue head.

This fails if the skb was found after the head, using SO_PEEK_OFF socket option. This causes an infinite loop.

We MUST drop this problematic skb, and we can simply check if skb was already removed by another thread, by looking at skb->next :

This pointer is set to NULL by the __skb_unlink() operation, that might have happened only under the spinlock protection.

Many thanks to syzkaller team (and particularly Dmitry Vyukov who provided us nice C reproducers exhibiting the lockup) and Willem de Bruijn who provided first version for this patch and a test program.

---
 net/core/datagram.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -351,7 +351,7 @@ int skb_kill_datagram(struct sock *sk, s
 	if (flags & MSG_PEEK) {
 		err = -ENOENT;
 		spin_lock_bh(&sk->sk_receive_queue.lock);
-		if (skb == skb_peek(&sk->sk_receive_queue)) {
+		if (skb->next) {
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			atomic_dec(&skb->users);
 			err = 0;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Fainelli <[email protected]>

[ Upstream commit a1a50c8e4c241a505b7270e1a3c6e50d94e794b1 ]

Junote Cai reported that he was not able to get a DSA setup involving the Freescale DPAA/FMAN driver to work and narrowed it down to of_find_net_device_by_node(). This function requires the network device's device reference to be correctly set which is the case here, though we have lost any device_node association there.

The problem is that dpaa_eth_add_device() allocates a "dpaa-ethernet" platform device, and later on dpaa_eth_probe() is called but SET_NETDEV_DEV() won't be propagating &pdev->dev.of_node properly. Fix this by inherenting both the parent device and the of_node when dpaa_eth_add_device() creates the platform device.

---
 drivers/net/ethernet/freescale/fman/mac.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -622,6 +622,9 @@ static struct platform_device *dpaa_eth_
 		goto no_mem;
 	}
 
+	pdev->dev.of_node = node;
+	pdev->dev.parent = priv->dev;
+
 	ret = platform_device_add_data(pdev, &data, sizeof(data));
 	if (ret)
 		goto err;

This is the start of the stable review cycle for the 4.9.51 release. There are 78 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Wed Sep 20 09:10:51 UTC 2017. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.9.51-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.9.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 4.9.51-rc1

Song Liu <[email protected]>
md/raid5: release/flush io in raid5_do_work()

Pan Bian <[email protected]>
xfs: use kmem_free to free return value of kmem_zalloc

Christoph Hellwig <[email protected]>
xfs: open code end_buffer_async_write in xfs_finish_page_writeback

Christoph Hellwig <[email protected]>
xfs: don't set v3 xflags for v2 inodes

Amir Goldstein <[email protected]>
xfs: fix incorrect log_flushed on fsync

Christoph Hellwig <[email protected]>
xfs: disable per-inode DAX flag

Brian Foster <[email protected]>
xfs: relog dirty buffers during swapext bmbt owner change

Brian Foster <[email protected]>
xfs: disallow marking previously dirty buffers as ordered

Brian Foster <[email protected]>
xfs: move bmbt owner change to last step of extent swap

Brian Foster <[email protected]>
xfs: skip bmbt block ino validation during owner change

Brian Foster <[email protected]>
xfs: don't log dirty ranges for ordered buffers

Brian Foster <[email protected]>
xfs: refactor buffer logging into buffer dirtying helper

Brian Foster <[email protected]>
xfs: ordered buffer log items are never formatted

Brian Foster <[email protected]>
xfs: remove unnecessary dirty bli format check for ordered bufs

Brian Foster <[email protected]>
xfs: open-code xfs_buf_item_dirty()

Omar Sandoval <[email protected]>
xfs: check for race with xfs_reclaim_inode() in xfs_ifree_cluster()

Darrick J. Wong <[email protected]>
xfs: evict all inodes involved with log redo item

Carlos Maiolino <[email protected]>
xfs: stop searching for free slots in an inode chunk when there are none

Brian Foster <[email protected]>
xfs: add log recovery tracepoint for head/tail

Brian Foster <[email protected]>
xfs: handle -EFSCORRUPTED during head/tail verification

Brian Foster <[email protected]>
xfs: fix log recovery corruption error due to tail overwrite

Brian Foster <[email protected]>
xfs: always verify the log tail during recovery

Brian Foster <[email protected]>
xfs: fix recovery failure when log record header wraps log end

Carlos Maiolino <[email protected]>
xfs: Properly retry failed inode items in case of error during buffer writeback

Carlos Maiolino <[email protected]>
xfs: Add infrastructure needed for error propagation during buffer IO failure

Christoph Hellwig <[email protected]>
xfs: remove xfs_trans_ail_delete_bulk

Eric Sandeen <[email protected]>
xfs: toggle readonly state around xfs_log_mount_finish

Eric Sandeen <[email protected]>
xfs: write unmount record for ro mounts

Christoph Hellwig <[email protected]>
iomap: fix integer truncation issues in the zeroing and dirtying helpers

Darrick J. Wong <[email protected]>
xfs: don't leak quotacheck dquots when cow recovery

Darrick J. Wong <[email protected]>
xfs: clear MS_ACTIVE after finishing log recovery

Omar Sandoval <[email protected]>
xfs: fix inobt inode allocation search optimization

Lukas Czerner <[email protected]>
xfs: Fix per-inode DAX flag inheritance

Christoph Hellwig <[email protected]>
xfs: fix multi-AG deadlock in xfs_bunmapi

Brian Foster <[email protected]>
xfs: fix quotacheck dquot id overflow infinite loop

Darrick J. Wong <[email protected]>
xfs: check _alloc_read_agf buffer pointer before using

Darrick J. Wong <[email protected]>
xfs: set firstfsb to NULLFSBLOCK before feeding it to _bmapi_write

Darrick J. Wong <[email protected]>
xfs: check _btree_check_block value

Darrick J. Wong <[email protected]>
xfs: don't crash on unexpected holes in dir/attr btrees

Brian Foster <[email protected]>
xfs: free cowblocks and retry on buffered write ENOSPC

Brian Foster <[email protected]>
xfs: free uncommitted transactions during log recovery

Darrick J. Wong <[email protected]>
xfs: don't allow bmap on rt files

Brian Foster <[email protected]>
xfs: remove bli from AIL before release on transaction abort

Brian Foster <[email protected]>
xfs: release bli from transaction properly on fs shutdown

Darrick J. Wong <[email protected]>
xfs: try to avoid blowing out the transaction reservation when bunmaping a shared extent

Brian Foster <[email protected]>
xfs: push buffer of flush locked dquot to avoid quotacheck deadlock

Brian Foster <[email protected]>
xfs: fix spurious spin_is_locked() assert failures on non-smp kernels

Jan Kara <[email protected]>
xfs: Move handling of missing page into one place in xfs_find_get_desired_pgoff()

Andy Lutomirski <[email protected]>
x86/switch_to/64: Rewrite FS/GS switching yet again to fix AMD CPUs

Andy Lutomirski <[email protected]>
x86/fsgsbase/64: Report FSBASE and GSBASE correctly in core dumps

Andy Lutomirski <[email protected]>
x86/fsgsbase/64: Fully initialize FS and GS state in start_thread_common

Jaegeuk Kim <[email protected]>
f2fs: check hot_data for roll-forward recovery

Jaegeuk Kim <[email protected]>
f2fs: let fill_super handle roll-forward errors

Haishuang Yan <[email protected]>
ip_tunnel: fix setting ttl and tos value in collect_md mode

Marcelo Ricardo Leitner <[email protected]>
sctp: fix missing wake ups in some situations

Eric Dumazet <[email protected]>
ipv6: fix typo in fib6_net_exit()

Sabrina Dubroca <[email protected]>
ipv6: fix memory leak with multiple tables during netns destruction

Xin Long <[email protected]>
ip6_gre: update mtu properly in ip6gre_err

Jason Wang <[email protected]>
vhost_net: correctly check tx avail during rx busy polling

Claudiu Manoil <[email protected]>
gianfar: Fix Tx flow control deactivation

Jesper Dangaard Brouer <[email protected]>
Revert "net: fix percpu memory leaks"

Jesper Dangaard Brouer <[email protected]>
Revert "net: use lib/percpu_counter API for fragmentation mem accounting"

Ido Schimmel <[email protected]>
bridge: switchdev: Clear forward mark when transmitting packet

Ido Schimmel <[email protected]>
mlxsw: spectrum: Forbid linking to devices that have uppers

Wei Wang <[email protected]>
tcp: initialize rcv_mss to TCP_MIN_MSS instead of 0

Florian Fainelli <[email protected]>
Revert "net: phy: Correctly process PHY_HALTED in phy_stop_machine()"

Eric Dumazet <[email protected]>
kcm: do not attach PF_KCM sockets to avoid deadlock

Benjamin Poirier <[email protected]>
packet: Don't write vnet header beyond end of buffer

Stefano Brivio <[email protected]>
cxgb4: Fix stack out-of-bounds read due to wrong size to t4_record_mbox()

stephen hemminger <[email protected]>
netvsc: fix deadlock betwen link status and removal

Arnd Bergmann <[email protected]>
qlge: avoid memcpy buffer overflow

Stefano Brivio <[email protected]>
sctp: Avoid out-of-bounds reads from address storage

Florian Fainelli <[email protected]>
fsl/man: Inherit parent device and of_node

Eric Dumazet <[email protected]>
udp: on peeking bad csum, drop packets even if not at head

Sabrina Dubroca <[email protected]>
macsec: add genl family module alias

Wei Wang <[email protected]>
ipv6: fix sparse warning on rt6i_node

Wei Wang <[email protected]>
ipv6: add rcu grace period before freeing fib6_node

Stefano Brivio <[email protected]>
ipv6: accept 64k - 1 packet length in ip6_find_1stfragopt()

-------------

Diffstat:

 Makefile                                       |   4 +-
 arch/x86/include/asm/elf.h                     |   5 +-
 arch/x86/kernel/process_64.c                   | 236 ++++++++++++++-----------
 drivers/md/raid5.c                             |   2 +
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c     |   6 +-
 drivers/net/ethernet/freescale/fman/mac.c      |   3 +
 drivers/net/ethernet/freescale/gianfar.c       |   2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c |   6 +
 drivers/net/ethernet/qlogic/qlge/qlge_dbg.c    |   2 +-
 drivers/net/hyperv/netvsc_drv.c                |   7 +-
 drivers/net/macsec.c                           |   1 +
 drivers/net/phy/phy.c                          |   3 -
 drivers/vhost/net.c                            |   7 +-
 fs/f2fs/recovery.c                             |   4 +-
 fs/inode.c                                     |   1 +
 fs/internal.h                                  |   1 -
 fs/iomap.c                                     |   4 +-
 fs/xfs/libxfs/xfs_attr_leaf.c                  |   2 +-
 fs/xfs/libxfs/xfs_bmap.c                       |  58 +++++-
 fs/xfs/libxfs/xfs_bmap.h                       |   2 +-
 fs/xfs/libxfs/xfs_bmap_btree.c                 |   1 +
 fs/xfs/libxfs/xfs_btree.c                      |  33 ++--
 fs/xfs/libxfs/xfs_btree.h                      |   3 +-
 fs/xfs/libxfs/xfs_da_btree.c                   |   2 +-
 fs/xfs/libxfs/xfs_dir2_block.c                 |   2 +-
 fs/xfs/libxfs/xfs_dir2_leaf.c                  |   4 +-
 fs/xfs/libxfs/xfs_ialloc.c                     |  59 +++----
 fs/xfs/libxfs/xfs_refcount.c                   |  14 +-
 fs/xfs/libxfs/xfs_refcount.h                   |  16 ++
 fs/xfs/xfs_aops.c                              |  79 ++++++---
 fs/xfs/xfs_bmap_item.c                         |  17 +-
 fs/xfs/xfs_bmap_util.c                         |  95 +++++++---
 fs/xfs/xfs_buf.c                               |  62 ++++++-
 fs/xfs/xfs_buf.h                               |   1 +
 fs/xfs/xfs_buf_item.c                          | 154 ++++++++++------
 fs/xfs/xfs_buf_item.h                          |   5 +-
 fs/xfs/xfs_file.c                              |  39 +---
 fs/xfs/xfs_icache.c                            |  15 +-
 fs/xfs/xfs_inode.c                             |  35 ++--
 fs/xfs/xfs_inode_item.c                        |  74 ++++++--
 fs/xfs/xfs_ioctl.c                             |  41 +++--
 fs/xfs/xfs_log.c                               |  44 ++++-
 fs/xfs/xfs_log_recover.c                       | 178 ++++++++++++-------
 fs/xfs/xfs_mount.c                             |  12 +-
 fs/xfs/xfs_qm.c                                |  31 +++-
 fs/xfs/xfs_reflink.c                           |   4 +-
 fs/xfs/xfs_super.c                             |   2 +-
 fs/xfs/xfs_trace.h                             |  20 ++-
 fs/xfs/xfs_trans.h                             |  16 +-
 fs/xfs/xfs_trans_ail.c                         |  72 ++++----
 fs/xfs/xfs_trans_bmap.c                        |  11 +-
 fs/xfs/xfs_trans_buf.c                         |  98 ++++++----
 fs/xfs/xfs_trans_priv.h                        |  46 +++--
 include/linux/fs.h                             |   1 +
 include/linux/netdevice.h                      |   2 +
 include/net/inet_frag.h                        |  41 +----
 include/net/ip6_fib.h                          |  32 +++-
 net/bridge/br_device.c                         |   3 +
 net/core/datagram.c                            |   2 +-
 net/core/dev.c                                 |   3 +-
 net/ieee802154/6lowpan/reassembly.c            |  11 +-
 net/ipv4/inet_fragment.c                       |   4 +-
 net/ipv4/ip_fragment.c                         |  12 +-
 net/ipv4/ip_tunnel.c                           |   4 +-
 net/ipv4/tcp.c                                 |   4 +
 net/ipv6/addrconf.c                            |   2 +-
 net/ipv6/ip6_fib.c                             |  56 ++++--
 net/ipv6/ip6_gre.c                             |   4 +-
 net/ipv6/netfilter/nf_conntrack_reasm.c        |  12 +-
 net/ipv6/output_core.c                         |   6 +-
 net/ipv6/reassembly.c                          |  12 +-
 net/ipv6/route.c                               |  17 +-
 net/kcm/kcmsock.c                              |   4 +
 net/packet/af_packet.c                         |  12 +-
 net/sctp/sctp_diag.c                           |   7 +-
 net/sctp/socket.c                              |   3 +-
 net/sctp/ulpqueue.c                            |   3 +-
 77 files changed, 1236 insertions(+), 662 deletions(-)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann <[email protected]>

[ Upstream commit e58f95831e7468d25eb6e41f234842ecfe6f014f ]

gcc-8.0.0 (snapshot) points out that we copy a variable-length string into a fixed length field using memcpy() with the destination length, and that ends up copying whatever follows the string:

inlined from 'ql_core_dump' at drivers/net/ethernet/qlogic/qlge/qlge_dbg.c:1106:2:
drivers/net/ethernet/qlogic/qlge/qlge_dbg.c:708:2: error: 'memcpy' reading 15 bytes from a region of size 14 [-Werror=stringop-overflow=]
memcpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);

Changing it to use strncpy() will instead zero-pad the destination, which seems to be the right thing to do here.

The bug is probably harmless, but it seems like a good idea to address it in stable kernels as well, if only for the purpose of building with gcc-8 without warnings.

---
 drivers/net/ethernet/qlogic/qlge/qlge_dbg.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -724,7 +724,7 @@ static void ql_build_coredump_seg_header
 	seg_hdr->cookie = MPI_COREDUMP_COOKIE;
 	seg_hdr->segNum = seg_number;
 	seg_hdr->segSize = seg_size;
-	memcpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);
+	strncpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1);
 }
 
 /*

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jesper Dangaard Brouer <[email protected]>

[ Upstream commit fb452a1aa3fd4034d7999e309c5466ff2d7005aa ]

This reverts commit 6d7b857d541ecd1d9bd997c97242d4ef94b19de2.

There is a bug in fragmentation codes use of the percpu_counter API, that can cause issues on systems with many CPUs.

The frag_mem_limit() just reads the global counter (fbc->count), without considering other CPUs can have upto batch size (130K) that haven't been subtracted yet. Due to the 3MBytes lower thresh limit, this become dangerous at >=24 CPUs (3*1024*1024/130000=24).

The correct API usage would be to use __percpu_counter_compare() which does the right thing, and takes into account the number of (online) CPUs and batch size, to account for this and call __percpu_counter_sum() when needed.

We choose to revert the use of the lib/percpu_counter API for frag memory accounting for several reasons:

1) On systems with CPUs > 24, the heavier fully locked __percpu_counter_sum() is always invoked, which will be more expensive than the atomic_t that is reverted to.

Given systems with more than 24 CPUs are becoming common this doesn't seem like a good option. To mitigate this, the batch size could be decreased and thresh be increased.

2) The add_frag_mem_limit+sub_frag_mem_limit pairs happen on the RX CPU, before SKBs are pushed into sockets on remote CPUs. Given NICs can only hash on L2 part of the IP-header, the NIC-RXq's will likely be limited. Thus, a fair chance that atomic add+dec happen on the same CPU.

Revert note that commit 1d6119baf061 ("net: fix percpu memory leaks") removed init_frag_mem_limit() and instead use inet_frags_init_net(). After this revert, inet_frags_uninit_net() becomes empty.

---
 include/net/inet_frag.h  |   36 +++++++++---------------------------
 net/ipv4/inet_fragment.c |    4 +---
 2 files changed, 10 insertions(+), 30 deletions(-)

@@ -1,14 +1,9 @@
 #ifndef __NET_FRAG_H__
 #define __NET_FRAG_H__
 
-#include <linux/percpu_counter.h>
-
 struct netns_frags {
-	/* The percpu_counter "mem" need to be cacheline aligned.
-	 *  mem.count must not share cacheline with other writers
-	 */
-	struct percpu_counter   mem ____cacheline_aligned_in_smp;
-
+	/* Keep atomic mem on separate cachelines in structs that include it */
+	atomic_t		mem ____cacheline_aligned_in_smp;
 	/* sysctls */
 	int			timeout;
 	int			high_thresh;

@@ -110,11 +105,11 @@ void inet_frags_fini(struct inet_frags *
 
 static inline int inet_frags_init_net(struct netns_frags *nf)
 {
-	return percpu_counter_init(&nf->mem, 0, GFP_KERNEL);
+	atomic_set(&nf->mem, 0);
+	return 0;
 }
 static inline void inet_frags_uninit_net(struct netns_frags *nf)
 {
-	percpu_counter_destroy(&nf->mem);
 }
 
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);

@@ -140,37 +135,24 @@ static inline bool inet_frag_evicting(st
 
 /* Memory Tracking Functions. */
 
-/* The default percpu_counter batch size is not big enough to scale to
- * fragmentation mem acct sizes.
- * The mem size of a 64K fragment is approx:
- *  (44 fragments * 2944 truesize) + frag_queue struct(200) = 129736 bytes
- */
-static unsigned int frag_percpu_counter_batch = 130000;
-
 static inline int frag_mem_limit(struct netns_frags *nf)
 {
-	return percpu_counter_read(&nf->mem);
+	return atomic_read(&nf->mem);
 }
 
 static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch);
+	atomic_sub(i, &nf->mem);
 }
 
 static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch);
+	atomic_add(i, &nf->mem);
 }
 
-static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)
+static inline int sum_frag_mem_limit(struct netns_frags *nf)
 {
-	unsigned int res;
-
-	local_bh_disable();
-	res = percpu_counter_sum_positive(&nf->mem);
-	local_bh_enable();
-
-	return res;
+	return atomic_read(&nf->mem);
 }
 
 /* RFC 3168 support :

@@ -234,10 +234,8 @@ evict_again:
 	cond_resched();
 
 	if (read_seqretry(&f->rnd_seqlock, seq) ||
-	    percpu_counter_sum(&nf->mem))
+	    sum_frag_mem_limit(nf))
 		goto evict_again;
-
-	percpu_counter_destroy(&nf->mem);
 }
 EXPORT_SYMBOL(inet_frags_exit_net);
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jesper Dangaard Brouer <[email protected]>

[ Upstream commit 5a63643e583b6a9789d7a225ae076fb4e603991c ]

This reverts commit 1d6119baf0610f813eb9d9580eb4fd16de5b4ceb.

After reverting commit 6d7b857d541e ("net: use lib/percpu_counter API for fragmentation mem accounting") then here is no need for this fix-up patch. As percpu_counter is no longer used, it cannot memory leak it any-longer.

---
 include/net/inet_frag.h                 |    7 +------
 net/ieee802154/6lowpan/reassembly.c     |   11 +++--------
 net/ipv4/ip_fragment.c                  |   12 +++---------
 net/ipv6/netfilter/nf_conntrack_reasm.c |   12 +++---------
 net/ipv6/reassembly.c                   |   12 +++---------
 5 files changed, 13 insertions(+), 41 deletions(-)

@@ -103,15 +103,10 @@ struct inet_frags {
 int inet_frags_init(struct inet_frags *);
 void inet_frags_fini(struct inet_frags *);
 
-static inline int inet_frags_init_net(struct netns_frags *nf)
+static inline void inet_frags_init_net(struct netns_frags *nf)
 {
 	atomic_set(&nf->mem, 0);
-	return 0;
 }
-static inline void inet_frags_uninit_net(struct netns_frags *nf)
-{
-}
-
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
 
 void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);

@@ -580,19 +580,14 @@ static int __net_init lowpan_frags_init_
 {
 	struct netns_ieee802154_lowpan *ieee802154_lowpan =
 		net_ieee802154_lowpan(net);
-	int res;
 
 	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&ieee802154_lowpan->frags);
-	if (res)
-		return res;
-	res = lowpan_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&ieee802154_lowpan->frags);
-	return res;
+	inet_frags_init_net(&ieee802154_lowpan->frags);
+
+	return lowpan_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit lowpan_frags_exit_net(struct net *net)

@@ -835,8 +835,6 @@ static void __init ip4_frags_ctl_registe
 
 static int __net_init ipv4_frags_init_net(struct net *net)
 {
-	int res;
-
 	/* Fragment cache limits.
 	 *
 	 * The fragment memory accounting code, (tries to) account for

@@ -862,13 +860,9 @@ static int __net_init ipv4_frags_init_ne
 
 	net->ipv4.frags.max_dist = 64;
 
-	res = inet_frags_init_net(&net->ipv4.frags);
-	if (res)
-		return res;
-	res = ip4_frags_ns_ctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv4.frags);
-	return res;
+	inet_frags_init_net(&net->ipv4.frags);
+
+	return ip4_frags_ns_ctl_register(net);
 }
 
 static void __net_exit ipv4_frags_exit_net(struct net *net)

@@ -622,18 +622,12 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
 
 static int nf_ct_net_init(struct net *net)
 {
-	int res;
-
 	net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
-	res = inet_frags_init_net(&net->nf_frag.frags);
-	if (res)
-		return res;
-	res = nf_ct_frag6_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->nf_frag.frags);
-	return res;
+	inet_frags_init_net(&net->nf_frag.frags);
+
+	return nf_ct_frag6_sysctl_register(net);
 }
 
 static void nf_ct_net_exit(struct net *net)

@@ -709,19 +709,13 @@ static void ip6_frags_sysctl_unregister(
 
 static int __net_init ipv6_frags_init_net(struct net *net)
 {
-	int res;
-
 	net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
 	net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
 	net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
 
-	res = inet_frags_init_net(&net->ipv6.frags);
-	if (res)
-		return res;
-	res = ip6_frags_ns_sysctl_register(net);
-	if (res)
-		inet_frags_uninit_net(&net->ipv6.frags);
-	return res;
+	inet_frags_init_net(&net->ipv6.frags);
+
+	return ip6_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit ipv6_frags_exit_net(struct net *net)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Claudiu Manoil <[email protected]>

[ Upstream commit 5d621672bc1a1e5090c1ac5432a18c79e0e13e03 ]

The wrong register is checked for the Tx flow control bit,
it should have been maccfg1 not maccfg2.
This went unnoticed for so long probably because the impact is hardly visible, not to mention the tangled code from adjust_link(). First, link flow control (i.e. handling of Rx/Tx link level pause frames) is disabled by default (needs to be enabled via 'ethtool -A'). Secondly, maccfg2 always returns 0 for tx_flow_oldval (except for a few old boards), which results in Tx flow control remaining always on once activated.

---
 drivers/net/ethernet/freescale/gianfar.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -3690,7 +3690,7 @@ static noinline void gfar_update_link_st
 		u32 tempval1 = gfar_read(&regs->maccfg1);
 		u32 tempval = gfar_read(&regs->maccfg2);
 		u32 ecntrl = gfar_read(&regs->ecntrl);
-		u32 tx_flow_oldval = (tempval & MACCFG1_TX_FLOW);
+		u32 tx_flow_oldval = (tempval1 & MACCFG1_TX_FLOW);
 
 		if (phydev->duplex != priv->oldduplex) {
 			if (!(phydev->duplex))

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: stephen hemminger <[email protected]>

[ Upstream commit 9b4e946ce14e20d7addbfb7d9139e604f9fda107 ]

There is a deadlock possible when canceling the link status delayed work queue. The removal process is run with RTNL held, and the link status callback is acquring RTNL.

Resolve the issue by using trylock and rescheduling. If cancel is in process, that block it from happening.

---
 drivers/net/hyperv/netvsc_drv.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

@@ -1084,7 +1084,12 @@ static void netvsc_link_change(struct wo
 	bool notify = false, reschedule = false;
 	unsigned long flags, next_reconfig, delay;
 
-	rtnl_lock();
+	/* if changes are happening, comeback later */
+	if (!rtnl_trylock()) {
+		schedule_delayed_work(&ndev_ctx->dwork, LINKCHANGE_INT);
+		return;
+	}
+
 	if (ndev_ctx->start_remove)
 		goto out_unlock;
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stefano Brivio <[email protected]>

[ Upstream commit 0f3086868e8889a823a6e0f3d299102aa895d947 ]

Passing commands for logging to t4_record_mbox() with size MBOX_LEN, when the actual command size is actually smaller, causes out-of-bounds stack accesses in t4_record_mbox() while copying command words here:

	for (i = 0; i < size / 8; i++)
		entry->cmd[i] = be64_to_cpu(cmd[i]);

Up to 48 bytes from the stack are then leaked to debugfs.

This happens whenever we send (and log) commands described by structs fw_sched_cmd (32 bytes leaked), fw_vi_rxmode_cmd (48), fw_hello_cmd (48), fw_bye_cmd (48), fw_initialize_cmd (48), fw_reset_cmd (48), fw_pfvf_cmd (32), fw_eq_eth_cmd (16), fw_eq_ctrl_cmd (32), fw_eq_ofld_cmd (32), fw_acl_mac_cmd(16), fw_rss_glb_config_cmd(32), fw_rss_vi_config_cmd(32), fw_devlog_cmd(32), fw_vi_enable_cmd(48), fw_port_cmd(32), fw_sched_cmd(32), fw_devlog_cmd(32).

The cxgb4vf driver got this right instead.

When we call t4_record_mbox() to log a command reply, a MBOX_LEN size can be used though, as get_mbox_rpl() will fill cmd_rpl up completely.

---
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -317,12 +317,12 @@ int t4_wr_mbox_meat_timeout(struct adapt
 
 	if (v != MBOX_OWNER_DRV) {
 		ret = (v == MBOX_OWNER_FW) ? -EBUSY : -ETIMEDOUT;
-		t4_record_mbox(adap, cmd, MBOX_LEN, access, ret);
+		t4_record_mbox(adap, cmd, size, access, ret);
 		return ret;
 	}
 
 	/* Copy in the new mailbox command and send it on its way ... */
-	t4_record_mbox(adap, cmd, MBOX_LEN, access, 0);
+	t4_record_mbox(adap, cmd, size, access, 0);
 	for (i = 0; i < size; i += 8)
 		t4_write_reg64(adap, data_reg + i, be64_to_cpu(*p++));
 

@@ -371,7 +371,7 @@ int t4_wr_mbox_meat_timeout(struct adapt
 	}
 
 	ret = (pcie_fw & PCIE_FW_ERR_F) ? -ENXIO : -ETIMEDOUT;
-	t4_record_mbox(adap, cmd, MBOX_LEN, access, ret);
+	t4_record_mbox(adap, cmd, size, access, ret);
 	dev_err(adap->pdev_dev, "command %#x in mailbox %d timed out\n",
 		*(const u8 *)cmd, mbox);
 	t4_report_fw_error(adap);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 351050ecd6523374b370341cc29fe61e2201556b ]

syzkaller had no problem to trigger a deadlock, attaching a KCM socket to another one (or itself). (original syzkaller report was a very confusing lockdep splat during a sendmsg())

It seems KCM claims to only support TCP, but no enforcement is done, so we might need to add additional checks.

---
 net/kcm/kcmsock.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -1381,6 +1381,10 @@ static int kcm_attach(struct socket *soc
 	if (!csk)
 		return -EINVAL;
 
+	/* We must prevent loops or risk deadlock ! */
+	if (csk->sk_family == PF_KCM)
+		return -EOPNOTSUPP;
+
 	psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL);
 	if (!psock)
 		return -ENOMEM;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Florian Fainelli <[email protected]>

[ Upstream commit ebc8254aeae34226d0bc8fda309fd9790d4dccfe ]

This reverts commit 7ad813f208533cebfcc32d3d7474dc1677d1b09a ("net: phy:
Correctly process PHY_HALTED in phy_stop_machine()") because it is creating the possibility for a NULL pointer dereference.

David Daney provide the following call trace and diagram of events:

When ndo_stop() is called we call:

phy_disconnect()

    +---> phy_stop_interrupts() implies: phydev->irq = PHY_POLL;
    +---> phy_stop_machine()
    |      +---> phy_state_machine()
    |              +----> queue_delayed_work(): Work queued.
    +--->phy_detach() implies: phydev->attached_dev = NULL;

Now at a later time the queued work does:

phy_state_machine()

    +---->netif_carrier_off(phydev->attached_dev): Oh no! It is NULL:

CPU 12 Unable to handle kernel paging request at virtual address
0000000000000048, epc == ffffffff80de37ec, ra == ffffffff80c7c Oops[#1]:

CPU: 12 PID: 1502 Comm: kworker/12:1 Not tainted 4.9.43-Cavium-Octeon+ #1
Workqueue: events_power_efficient phy_state_machine
task: 80000004021ed100 task.stack: 8000000409d70000
$ 0   : 0000000000000000 ffffffff84720060 0000000000000048 0000000000000004
$ 4   : 0000000000000000 0000000000000001 0000000000000004 0000000000000000
$ 8   : 0000000000000000 0000000000000000 00000000ffff98f3 0000000000000000
$12   : 8000000409d73fe0 0000000000009c00 ffffffff846547c8 000000000000af3b
$16   : 80000004096bab68 80000004096babd0 0000000000000000 80000004096ba800
$20   : 0000000000000000 0000000000000000 ffffffff81090000 0000000000000008
$24   : 0000000000000061 ffffffff808637b0
$28   : 8000000409d70000 8000000409d73cf0 80000000271bd300 ffffffff80c7804c
Hi    : 000000000000002a
Lo    : 000000000000003f
epc   : ffffffff80de37ec netif_carrier_off+0xc/0x58
ra    : ffffffff80c7804c phy_state_machine+0x48c/0x4f8
Status: 14009ce3        KX SX UX KERNEL EXL IE
Cause : 00800008 (ExcCode 02)
BadVA : 0000000000000048
PrId  : 000d9501 (Cavium Octeon III)
Modules linked in:
Process kworker/12:1 (pid: 1502, threadinfo=8000000409d70000,
task=80000004021ed100, tls=0000000000000000)
Stack : 8000000409a54000 80000004096bab68 80000000271bd300 80000000271c1e00
        0000000000000000 ffffffff808a1708 8000000409a54000 80000000271bd300
        80000000271bd320 8000000409a54030 ffffffff80ff0f00 0000000000000001
        ffffffff81090000 ffffffff808a1ac0 8000000402182080 ffffffff84650000
        8000000402182080 ffffffff84650000 ffffffff80ff0000 8000000409a54000
        ffffffff808a1970 0000000000000000 80000004099e8000 8000000402099240
        0000000000000000 ffffffff808a8598 0000000000000000 8000000408eeeb00
        8000000409a54000 00000000810a1d00 0000000000000000 8000000409d73de8
        8000000409d73de8 0000000000000088 000000000c009c00 8000000409d73e08
        8000000409d73e08 8000000402182080 ffffffff808a84d0 8000000402182080
        ...
Call Trace:
[<ffffffff80de37ec>] netif_carrier_off+0xc/0x58
[<ffffffff80c7804c>] phy_state_machine+0x48c/0x4f8
[<ffffffff808a1708>] process_one_work+0x158/0x368
[<ffffffff808a1ac0>] worker_thread+0x150/0x4c0
[<ffffffff808a8598>] kthread+0xc8/0xe0
[<ffffffff808617f0>] ret_from_kernel_thread+0x14/0x1c

The original motivation for this change originated from Marc Gonzales indicating that his network driver did not have its adjust_link callback executing with phydev->link = 0 while he was expecting it.

PHYLIB has never made any such guarantees ever because phy_stop() merely just tells the workqueue to move into PHY_HALTED state which will happen asynchronously.

---
 drivers/net/phy/phy.c |    3 ---
 1 file changed, 3 deletions(-)

@@ -674,9 +674,6 @@ void phy_stop_machine(struct phy_device
 	if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
 		phydev->state = PHY_UP;
 	mutex_unlock(&phydev->lock);
-
-	/* Now we can run the state machine synchronously */
-	phy_state_machine(&phydev->state_queue.work);
 }
 
 /**

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wei Wang <[email protected]>

[ Upstream commit 499350a5a6e7512d9ed369ed63a4244b6536f4f8 ]

When tcp_disconnect() is called, inet_csk_delack_init() sets icsk->icsk_ack.rcv_mss to 0.
This could potentially cause tcp_recvmsg() => tcp_cleanup_rbuf() => __tcp_select_window() call path to have division by 0 issue. So this patch initializes rcv_mss to TCP_MIN_MSS instead of 0.

---
 net/ipv4/tcp.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -2297,6 +2297,10 @@ int tcp_disconnect(struct sock *sk, int
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tcp_clear_retrans(tp);
 	inet_csk_delack_init(sk);
+	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
+	 * issue in __tcp_select_window()
+	 */
+	icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ido Schimmel <[email protected]>

[ Upstream commit 25cc72a33835ed8a6f53180a822cadab855852ac ]

The mlxsw driver relies on NETDEV_CHANGEUPPER events to configure the device in case a port is enslaved to a master netdev such as bridge or bond.

Since the driver ignores events unrelated to its ports and their uppers, it's possible to engineer situations in which the device's data path differs from the kernel's.

One example to such a situation is when a port is enslaved to a bond that is already enslaved to a bridge. When the bond was enslaved the driver ignored the event - as the bond wasn't one of its uppers - and therefore a bridge port instance isn't created in the device.

Until such configurations are supported forbid them by checking that the upper device doesn't have uppers of its own.

---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c |    6 ++++++
 include/linux/netdevice.h                      |    2 ++
 net/core/dev.c                                 |    3 ++-
 3 files changed, 10 insertions(+), 1 deletion(-)

@@ -4172,6 +4172,8 @@ static int mlxsw_sp_netdevice_port_upper
 			return -EINVAL;
 		if (!info->linking)
 			break;
+		if (netdev_has_any_upper_dev(upper_dev))
+			return -EINVAL;
 		/* HW limitation forbids to put ports to multiple bridges. */
 		if (netif_is_bridge_master(upper_dev) &&
 		    !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev))

@@ -4185,6 +4187,10 @@ static int mlxsw_sp_netdevice_port_upper
 		if (netif_is_lag_port(dev) && is_vlan_dev(upper_dev) &&
 		    !netif_is_lag_master(vlan_dev_real_dev(upper_dev)))
 			return -EINVAL;
+		if (!info->linking)
+			break;
+		if (netdev_has_any_upper_dev(upper_dev))
+			return -EINVAL;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;

@@ -3901,6 +3901,8 @@ struct net_device *netdev_all_upper_get_
 	     updev; \
 	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
 
+bool netdev_has_any_upper_dev(struct net_device *dev);
+
 void *netdev_lower_get_next_private(struct net_device *dev,
 				    struct list_head **iter);
 void *netdev_lower_get_next_private_rcu(struct net_device *dev,

@@ -5337,12 +5337,13 @@ EXPORT_SYMBOL(netdev_has_upper_dev);
  * Find out if a device is linked to an upper device and return true in case
  * it is. The caller must hold the RTNL lock.
  */
-static bool netdev_has_any_upper_dev(struct net_device *dev)
+bool netdev_has_any_upper_dev(struct net_device *dev)
 {
 	ASSERT_RTNL();
 
 	return !list_empty(&dev->all_adj_list.upper);
 }
+EXPORT_SYMBOL(netdev_has_any_upper_dev);
 
 /**
  * netdev_master_upper_dev_get - Get master upper device

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ido Schimmel <[email protected]>

[ Upstream commit 79e99bdd60b484af9afe0147e85a13e66d5c1cdb ]

Commit 6bc506b4fb06 ("bridge: switchdev: Add forward mark support for stacked devices") added the 'offload_fwd_mark' bit to the skb in order to allow drivers to indicate to the bridge driver that they already forwarded the packet in L2.

In case the bit is set, before transmitting the packet from each port, the port's mark is compared with the mark stored in the skb's control block. If both marks are equal, we know the packet arrived from a switch device that already forwarded the packet and it's not re-transmitted.

However, if the packet is transmitted from the bridge device itself (e.g., br0), we should clear the 'offload_fwd_mark' bit as the mark stored in the skb's control block isn't valid.

This scenario can happen in rare cases where a packet was trapped during L3 forwarding and forwarded by the kernel to a bridge device.

---
 net/bridge/br_device.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -53,6 +53,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *
 	brstats->tx_bytes += skb->len;
 	u64_stats_update_end(&brstats->syncp);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+#endif
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
 
 	skb_reset_mac_header(skb);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Stefano Brivio <[email protected]>

[ Upstream commit ee6c88bb754e3d363e568da78086adfedb692447 ]

inet_diag_msg_sctp{,l}addr_fill() and sctp_get_sctp_info() copy sizeof(sockaddr_storage) bytes to fill in sockaddr structs used to export diagnostic information to userspace.

However, the memory allocated to store sockaddr information is smaller than that and depends on the address family, so we leak up to 100 uninitialized bytes to userspace. Just use the size of the source structs instead, in all the three cases this is what userspace expects. Zero out the remaining memory.

Unused bytes (i.e. when IPv4 addresses are used) in source structs sctp_sockaddr_entry and sctp_transport are already cleared by sctp_add_bind_addr() and sctp_transport_new(), respectively.

Noticed while testing KASAN-enabled kernel with 'ss':

[ 2326.885243] BUG: KASAN: slab-out-of-bounds in inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag] at addr ffff881be8779800
[ 2326.896800] Read of size 128 by task ss/9527
[ 2326.901564] CPU: 0 PID: 9527 Comm: ss Not tainted 4.11.0-22.el7a.x86_64 #1
[ 2326.909236] Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017
[ 2326.917585] Call Trace:
[ 2326.920312]  dump_stack+0x63/0x8d
[ 2326.924014]  kasan_object_err+0x21/0x70
[ 2326.928295]  kasan_report+0x288/0x540
[ 2326.932380]  ? inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag]
[ 2326.938500]  ? skb_put+0x8b/0xd0
[ 2326.942098]  ? memset+0x31/0x40
[ 2326.945599]  check_memory_region+0x13c/0x1a0
[ 2326.950362]  memcpy+0x23/0x50
[ 2326.953669]  inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag]
[ 2326.959596]  ? inet_diag_msg_sctpasoc_fill+0x460/0x460 [sctp_diag]
[ 2326.966495]  ? __lock_sock+0x102/0x150
[ 2326.970671]  ? sock_def_wakeup+0x60/0x60
[ 2326.975048]  ? remove_wait_queue+0xc0/0xc0
[ 2326.979619]  sctp_diag_dump+0x44a/0x760 [sctp_diag]
[ 2326.985063]  ? sctp_ep_dump+0x280/0x280 [sctp_diag]
[ 2326.990504]  ? memset+0x31/0x40
[ 2326.994007]  ? mutex_lock+0x12/0x40
[ 2326.997900]  __inet_diag_dump+0x57/0xb0 [inet_diag]
[ 2327.003340]  ? __sys_sendmsg+0x150/0x150
[ 2327.007715]  inet_diag_dump+0x4d/0x80 [inet_diag]
[ 2327.012979]  netlink_dump+0x1e6/0x490
[ 2327.017064]  __netlink_dump_start+0x28e/0x2c0
[ 2327.021924]  inet_diag_handler_cmd+0x189/0x1a0 [inet_diag]
[ 2327.028045]  ? inet_diag_rcv_msg_compat+0x1b0/0x1b0 [inet_diag]
[ 2327.034651]  ? inet_diag_dump_compat+0x190/0x190 [inet_diag]
[ 2327.040965]  ? __netlink_lookup+0x1b9/0x260
[ 2327.045631]  sock_diag_rcv_msg+0x18b/0x1e0
[ 2327.050199]  netlink_rcv_skb+0x14b/0x180
[ 2327.054574]  ? sock_diag_bind+0x60/0x60
[ 2327.058850]  sock_diag_rcv+0x28/0x40
[ 2327.062837]  netlink_unicast+0x2e7/0x3b0
[ 2327.067212]  ? netlink_attachskb+0x330/0x330
[ 2327.071975]  ? kasan_check_write+0x14/0x20
[ 2327.076544]  netlink_sendmsg+0x5be/0x730
[ 2327.080918]  ? netlink_unicast+0x3b0/0x3b0
[ 2327.085486]  ? kasan_check_write+0x14/0x20
[ 2327.090057]  ? selinux_socket_sendmsg+0x24/0x30
[ 2327.095109]  ? netlink_unicast+0x3b0/0x3b0
[ 2327.099678]  sock_sendmsg+0x74/0x80
[ 2327.103567]  ___sys_sendmsg+0x520/0x530
[ 2327.107844]  ? __get_locked_pte+0x178/0x200
[ 2327.112510]  ? copy_msghdr_from_user+0x270/0x270
[ 2327.117660]  ? vm_insert_page+0x360/0x360
[ 2327.122133]  ? vm_insert_pfn_prot+0xb4/0x150
[ 2327.126895]  ? vm_insert_pfn+0x32/0x40
[ 2327.131077]  ? vvar_fault+0x71/0xd0
[ 2327.134968]  ? special_mapping_fault+0x69/0x110
[ 2327.140022]  ? __do_fault+0x42/0x120
[ 2327.144008]  ? __handle_mm_fault+0x1062/0x17a0
[ 2327.148965]  ? __fget_light+0xa7/0xc0
[ 2327.153049]  __sys_sendmsg+0xcb/0x150
[ 2327.157133]  ? __sys_sendmsg+0xcb/0x150
[ 2327.161409]  ? SyS_shutdown+0x140/0x140
[ 2327.165688]  ? exit_to_usermode_loop+0xd0/0xd0
[ 2327.170646]  ? __do_page_fault+0x55d/0x620
[ 2327.175216]  ? __sys_sendmsg+0x150/0x150
[ 2327.179591]  SyS_sendmsg+0x12/0x20
[ 2327.183384]  do_syscall_64+0xe3/0x230
[ 2327.187471]  entry_SYSCALL64_slow_path+0x25/0x25
[ 2327.192622] RIP: 0033:0x7f41d18fa3b0
[ 2327.196608] RSP: 002b:00007ffc3b731218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[ 2327.205055] RAX: ffffffffffffffda RBX: 00007ffc3b731380 RCX: 00007f41d18fa3b0
[ 2327.213017] RDX: 0000000000000000 RSI: 00007ffc3b731340 RDI: 0000000000000003
[ 2327.220978] RBP: 0000000000000002 R08: 0000000000000004 R09: 0000000000000040
[ 2327.228939] R10: 00007ffc3b730f30 R11: 0000000000000246 R12: 0000000000000003
[ 2327.236901] R13: 00007ffc3b731340 R14: 00007ffc3b7313d0 R15: 0000000000000084
[ 2327.244865] Object at ffff881be87797e0, in cache kmalloc-64 size: 64
[ 2327.251953] Allocated:
[ 2327.254581] PID = 9484
[ 2327.257215]  save_stack_trace+0x1b/0x20
[ 2327.261485]  save_stack+0x46/0xd0
[ 2327.265179]  kasan_kmalloc+0xad/0xe0
[ 2327.269165]  kmem_cache_alloc_trace+0xe6/0x1d0
[ 2327.274138]  sctp_add_bind_addr+0x58/0x180 [sctp]
[ 2327.279400]  sctp_do_bind+0x208/0x310 [sctp]
[ 2327.284176]  sctp_bind+0x61/0xa0 [sctp]
[ 2327.288455]  inet_bind+0x5f/0x3a0
[ 2327.292151]  SYSC_bind+0x1a4/0x1e0
[ 2327.295944]  SyS_bind+0xe/0x10
[ 2327.299349]  do_syscall_64+0xe3/0x230
[ 2327.303433]  return_from_SYSCALL_64+0x0/0x6a
[ 2327.308194] Freed:
[ 2327.310434] PID = 4131
[ 2327.313065]  save_stack_trace+0x1b/0x20
[ 2327.317344]  save_stack+0x46/0xd0
[ 2327.321040]  kasan_slab_free+0x73/0xc0
[ 2327.325220]  kfree+0x96/0x1a0
[ 2327.328530]  dynamic_kobj_release+0x15/0x40
[ 2327.333195]  kobject_release+0x99/0x1e0
[ 2327.337472]  kobject_put+0x38/0x70
[ 2327.341266]  free_notes_attrs+0x66/0x80
[ 2327.345545]  mod_sysfs_teardown+0x1a5/0x270
[ 2327.350211]  free_module+0x20/0x2a0
[ 2327.354099]  SyS_delete_module+0x2cb/0x2f0
[ 2327.358667]  do_syscall_64+0xe3/0x230
[ 2327.362750]  return_from_SYSCALL_64+0x0/0x6a
[ 2327.367510] Memory state around the buggy address:
[ 2327.372855]  ffff881be8779700: fc fc fc fc 00 00 00 00 00 00 00 00 fc fc fc fc
[ 2327.380914]  ffff881be8779780: fb fb fb fb fb fb fb fb fc fc fc fc 00 00 00 00
[ 2327.388972] >ffff881be8779800: 00 00 00 00 fc fc fc fc fb fb fb fb fb fb fb fb
[ 2327.397031]                                ^
[ 2327.401792]  ffff881be8779880: fc fc fc fc fb fb fb fb fb fb fb fb fc fc fc fc
[ 2327.409850]  ffff881be8779900: 00 00 00 00 00 04 fc fc fc fc fc fc 00 00 00 00
[ 2327.417907] ==================================================================

This fixes CVE-2017-7558.

References: https://bugzilla.redhat.com/show_bug.cgi?id=1480266

---
 net/sctp/sctp_diag.c |    7 +++++--
 net/sctp/socket.c    |    3 +--
 2 files changed, 6 insertions(+), 4 deletions(-)

@@ -70,7 +70,8 @@ static int inet_diag_msg_sctpladdrs_fill
 
 	info = nla_data(attr);
 	list_for_each_entry_rcu(laddr, address_list, list) {
-		memcpy(info, &laddr->a, addrlen);
+		memcpy(info, &laddr->a, sizeof(laddr->a));
+		memset(info + sizeof(laddr->a), 0, addrlen - sizeof(laddr->a));
 		info += addrlen;
 	}
 

@@ -93,7 +94,9 @@ static int inet_diag_msg_sctpaddrs_fill(
 	info = nla_data(attr);
 	list_for_each_entry(from, &asoc->peer.transport_addr_list,
 			    transports) {
-		memcpy(info, &from->ipaddr, addrlen);
+		memcpy(info, &from->ipaddr, sizeof(from->ipaddr));
+		memset(info + sizeof(from->ipaddr), 0,
+		       addrlen - sizeof(from->ipaddr));
 		info += addrlen;
 	}
 

@@ -4373,8 +4373,7 @@ int sctp_get_sctp_info(struct sock *sk,
 	info->sctpi_ictrlchunks = asoc->stats.ictrlchunks;
 
 	prim = asoc->peer.primary_path;
-	memcpy(&info->sctpi_p_address, &prim->ipaddr,
-	       sizeof(struct sockaddr_storage));
+	memcpy(&info->sctpi_p_address, &prim->ipaddr, sizeof(prim->ipaddr));
 	info->sctpi_p_state = prim->state;
 	info->sctpi_p_cwnd = prim->cwnd;
 	info->sctpi_p_srtt = prim->srtt;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xin Long <[email protected]>

[ Upstream commit 5c25f30c93fdc5bf25e62101aeaae7a4f9b421b3 ]

Now when probessing ICMPV6_PKT_TOOBIG, ip6gre_err only subtracts the offset of gre header from mtu info. The expected mtu of gre device should also subtract gre header. Otherwise, the next packets still can't be sent out.

Jianlin found this issue when using the topo:
client(ip6gre)<---->(nic1)route(nic2)<----->(ip6gre)server

and reducing nic2's mtu, then both tcp and sctp's performance with big size data became 0.

This patch is to fix it by also subtracting grehdr (tun->tun_hlen) from mtu info when updating gre device's mtu in ip6gre_err(). It also needs to subtract ETH_HLEN if gre dev'type is ARPHRD_ETHER.

---
 net/ipv6/ip6_gre.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -432,7 +432,9 @@ static void ip6gre_err(struct sk_buff *s
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
-		mtu = be32_to_cpu(info) - offset;
+		mtu = be32_to_cpu(info) - offset - t->tun_hlen;
+		if (t->dev->type == ARPHRD_ETHER)
+			mtu -= ETH_HLEN;
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit e137a4d8f4dd2e277e355495b6b2cb241a8693c3 upstream.

Switching FS and GS is a mess, and the current code is still subtly
wrong: it assumes that "Loading a nonzero value into FS sets the index and base", which is false on AMD CPUs if the value being loaded is 1, 2, or 3.

(The current code came from commit 3e2b68d752c9 ("x86/asm, sched/x86: Rewrite the FS and GS context switch code"), which made it better but didn't fully fix it.)

Rewrite it to be much simpler and more obviously correct. This should fix it fully on AMD CPUs and shouldn't adversely affect performance.

---
 arch/x86/kernel/process_64.c |  227 +++++++++++++++++++++++--------------------
 1 file changed, 122 insertions(+), 105 deletions(-)

@@ -136,6 +136,123 @@ void release_thread(struct task_struct *
 	}
 }
 
+enum which_selector {
+	FS,
+	GS
+};
+
+/*
+ * Saves the FS or GS base for an outgoing thread if FSGSBASE extensions are
+ * not available.  The goal is to be reasonably fast on non-FSGSBASE systems.
+ * It's forcibly inlined because it'll generate better code and this function
+ * is hot.
+ */
+static __always_inline void save_base_legacy(struct task_struct *prev_p,
+					     unsigned short selector,
+					     enum which_selector which)
+{
+	if (likely(selector == 0)) {
+		/*
+		 * On Intel (without X86_BUG_NULL_SEG), the segment base could
+		 * be the pre-existing saved base or it could be zero.  On AMD
+		 * (with X86_BUG_NULL_SEG), the segment base could be almost
+		 * anything.
+		 *
+		 * This branch is very hot (it's hit twice on almost every
+		 * context switch between 64-bit programs), and avoiding
+		 * the RDMSR helps a lot, so we just assume that whatever
+		 * value is already saved is correct.  This matches historical
+		 * Linux behavior, so it won't break existing applications.
+		 *
+		 * To avoid leaking state, on non-X86_BUG_NULL_SEG CPUs, if we
+		 * report that the base is zero, it needs to actually be zero:
+		 * see the corresponding logic in load_seg_legacy.
+		 */
+	} else {
+		/*
+		 * If the selector is 1, 2, or 3, then the base is zero on
+		 * !X86_BUG_NULL_SEG CPUs and could be anything on
+		 * X86_BUG_NULL_SEG CPUs.  In the latter case, Linux
+		 * has never attempted to preserve the base across context
+		 * switches.
+		 *
+		 * If selector > 3, then it refers to a real segment, and
+		 * saving the base isn't necessary.
+		 */
+		if (which == FS)
+			prev_p->thread.fsbase = 0;
+		else
+			prev_p->thread.gsbase = 0;
+	}
+}
+
+static __always_inline void save_fsgs(struct task_struct *task)
+{
+	savesegment(fs, task->thread.fsindex);
+	savesegment(gs, task->thread.gsindex);
+	save_base_legacy(task, task->thread.fsindex, FS);
+	save_base_legacy(task, task->thread.gsindex, GS);
+}
+
+static __always_inline void loadseg(enum which_selector which,
+				    unsigned short sel)
+{
+	if (which == FS)
+		loadsegment(fs, sel);
+	else
+		load_gs_index(sel);
+}
+
+static __always_inline void load_seg_legacy(unsigned short prev_index,
+					    unsigned long prev_base,
+					    unsigned short next_index,
+					    unsigned long next_base,
+					    enum which_selector which)
+{
+	if (likely(next_index <= 3)) {
+		/*
+		 * The next task is using 64-bit TLS, is not using this
+		 * segment at all, or is having fun with arcane CPU features.
+		 */
+		if (next_base == 0) {
+			/*
+			 * Nasty case: on AMD CPUs, we need to forcibly zero
+			 * the base.
+			 */
+			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
+				loadseg(which, __USER_DS);
+				loadseg(which, next_index);
+			} else {
+				/*
+				 * We could try to exhaustively detect cases
+				 * under which we can skip the segment load,
+				 * but there's really only one case that matters
+				 * for performance: if both the previous and
+				 * next states are fully zeroed, we can skip
+				 * the load.
+				 *
+				 * (This assumes that prev_base == 0 has no
+				 * false positives.  This is the case on
+				 * Intel-style CPUs.)
+				 */
+				if (likely(prev_index | next_index | prev_base))
+					loadseg(which, next_index);
+			}
+		} else {
+			if (prev_index != next_index)
+				loadseg(which, next_index);
+			wrmsrl(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE,
+			       next_base);
+		}
+	} else {
+		/*
+		 * The next task is using a real segment.  Loading the selector
+		 * is sufficient.
+		 */
+		loadseg(which, next_index);
+	}
+}
+
 int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 		unsigned long arg, struct task_struct *p, unsigned long tls)
 {

@@ -273,7 +390,6 @@ __switch_to(struct task_struct *prev_p,
 	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
-	unsigned prev_fsindex, prev_gsindex;
 	fpu_switch_t fpu_switch;
 
 	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);

@@ -283,8 +399,7 @@ __switch_to(struct task_struct *prev_p,
 	 *
 	 * (e.g. xen_load_tls())
 	 */
-	savesegment(fs, prev_fsindex);
-	savesegment(gs, prev_gsindex);
+	save_fsgs(prev_p);
 
 	/*
 	 * Load TLS before restoring any segments so that segment loads

@@ -323,108 +438,10 @@ __switch_to(struct task_struct *prev_p,
 	if (unlikely(next->ds | prev->ds))
 		loadsegment(ds, next->ds);
 
-	/*
-	 * Switch FS and GS.
-	 *
-	 * These are even more complicated than DS and ES: they have
-	 * 64-bit bases are that controlled by arch_prctl.  The bases
-	 * don't necessarily match the selectors, as user code can do
-	 * any number of things to cause them to be inconsistent.
-	 *
-	 * We don't promise to preserve the bases if the selectors are
-	 * nonzero.  We also don't promise to preserve the base if the
-	 * selector is zero and the base doesn't match whatever was
-	 * most recently passed to ARCH_SET_FS/GS.  (If/when the
-	 * FSGSBASE instructions are enabled, we'll need to offer
-	 * stronger guarantees.)
-	 *
-	 * As an invariant,
-	 * (fsbase != 0 && fsindex != 0) || (gsbase != 0 && gsindex != 0) is
-	 * impossible.
-	 */
-	if (next->fsindex) {
-		/* Loading a nonzero value into FS sets the index and base. */
-		loadsegment(fs, next->fsindex);
-	} else {
-		if (next->fsbase) {
-			/* Next index is zero but next base is nonzero. */
-			if (prev_fsindex)
-				loadsegment(fs, 0);
-			wrmsrl(MSR_FS_BASE, next->fsbase);
-		} else {
-			/* Next base and index are both zero. */
-			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
-				/*
-				 * We don't know the previous base and can't
-				 * find out without RDMSR.  Forcibly clear it.
-				 */
-				loadsegment(fs, __USER_DS);
-				loadsegment(fs, 0);
-			} else {
-				/*
-				 * If the previous index is zero and ARCH_SET_FS
-				 * didn't change the base, then the base is
-				 * also zero and we don't need to do anything.
-				 */
-				if (prev->fsbase || prev_fsindex)
-					loadsegment(fs, 0);
-			}
-		}
-	}
-	/*
-	 * Save the old state and preserve the invariant.
-	 * NB: if prev_fsindex == 0, then we can't reliably learn the base
-	 * without RDMSR because Intel user code can zero it without telling
-	 * us and AMD user code can program any 32-bit value without telling
-	 * us.
-	 */
-	if (prev_fsindex)
-		prev->fsbase = 0;
-	prev->fsindex = prev_fsindex;
-
-	if (next->gsindex) {
-		/* Loading a nonzero value into GS sets the index and base. */
-		load_gs_index(next->gsindex);
-	} else {
-		if (next->gsbase) {
-			/* Next index is zero but next base is nonzero. */
-			if (prev_gsindex)
-				load_gs_index(0);
-			wrmsrl(MSR_KERNEL_GS_BASE, next->gsbase);
-		} else {
-			/* Next base and index are both zero. */
-			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
-				/*
-				 * We don't know the previous base and can't
-				 * find out without RDMSR.  Forcibly clear it.
-				 *
-				 * This contains a pointless SWAPGS pair.
-				 * Fixing it would involve an explicit check
-				 * for Xen or a new pvop.
-				 */
-				load_gs_index(__USER_DS);
-				load_gs_index(0);
-			} else {
-				/*
-				 * If the previous index is zero and ARCH_SET_GS
-				 * didn't change the base, then the base is
-				 * also zero and we don't need to do anything.
-				 */
-				if (prev->gsbase || prev_gsindex)
-					load_gs_index(0);
-			}
-		}
-	}
-	/*
-	 * Save the old state and preserve the invariant.
-	 * NB: if prev_gsindex == 0, then we can't reliably learn the base
-	 * without RDMSR because Intel user code can zero it without telling
-	 * us and AMD user code can program any 32-bit value without telling
-	 * us.
-	 */
-	if (prev_gsindex)
-		prev->gsbase = 0;
-	prev->gsindex = prev_gsindex;
+	load_seg_legacy(prev->fsindex, prev->fsbase,
+			next->fsindex, next->fsbase, FS);
+	load_seg_legacy(prev->gsindex, prev->gsbase,
+			next->gsindex, next->gsbase, GS);
 
 	switch_fpu_finish(next_fpu, fpu_switch);
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jan Kara <[email protected]>

commit a54fba8f5a0dc36161cacdf2aa90f007f702ec1a upstream.

Currently several places in xfs_find_get_desired_pgoff() handle the case of a missing page. Make them all handled in one place after the loop has terminated.

---
 fs/xfs/xfs_file.c |   38 ++++++++------------------------------
 1 file changed, 8 insertions(+), 30 deletions(-)

@@ -1139,29 +1139,8 @@ xfs_find_get_desired_pgoff(
 		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  want);
-		/*
-		 * No page mapped into given range.  If we are searching holes
-		 * and if this is the first time we got into the loop, it means
-		 * that the given offset is landed in a hole, return it.
-		 *
-		 * If we have already stepped through some block buffers to find
-		 * holes but they all contains data.  In this case, the last
-		 * offset is already updated and pointed to the end of the last
-		 * mapped page, if it does not reach the endpoint to search,
-		 * that means there should be a hole between them.
-		 */
-		if (nr_pages == 0) {
-			/* Data search found nothing */
-			if (type == DATA_OFF)
-				break;
-
-			ASSERT(type == HOLE_OFF);
-			if (lastoff == startoff || lastoff < endoff) {
-				found = true;
-				*offset = lastoff;
-			}
+		if (nr_pages == 0)
 			break;
-		}
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page	*page = pvec.pages[i];

@@ -1227,21 +1206,20 @@ xfs_find_get_desired_pgoff(
 
 		/*
 		 * The number of returned pages less than our desired, search
-		 * done.  In this case, nothing was found for searching data,
-		 * but we found a hole behind the last offset.
+		 * done.
 		 */
-		if (nr_pages < want) {
-			if (type == HOLE_OFF) {
-				*offset = lastoff;
-				found = true;
-			}
+		if (nr_pages < want)
 			break;
-		}
 
 		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index <= end);
 
+	/* No page at lastoff and we are not done - we found a hole. */
+	if (type == HOLE_OFF && lastoff < endoff) {
+		*offset = lastoff;
+		found = true;
+	}
 out:
 	pagevec_release(&pvec);
 	return found;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 32a805baf0fb70b6dbedefcd7249ac7f580f9e3b ]

IPv6 FIB should use FIB6_TABLE_HASHSZ, not FIB_TABLE_HASHSZ.

---
 net/ipv6/ip6_fib.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1904,7 +1904,7 @@ static void fib6_net_exit(struct net *ne
 	rt6_ifdown(net, NULL);
 	del_timer_sync(&net->ipv6.ip6_fib_timer);
 
-	for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+	for (i = 0; i < FIB6_TABLE_HASHSZ; i++) {
 		struct hlist_head *head = &net->ipv6.fib_table_hash[i];
 		struct hlist_node *tmp;
 		struct fib6_table *tb;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marcelo Ricardo Leitner <[email protected]>

[ Upstream commit 7906b00f5cd1cd484fced7fcda892176e3202c8a ]

Commit fb586f25300f ("sctp: delay calls to sk_data_ready() as much as possible") minimized the number of wake ups that are triggered in case the association receives a packet with multiple data chunks on it and/or when io_events are enabled and then commit 0970f5b36659 ("sctp: signal sk_data_ready earlier on data chunks reception") moved the wake up to as soon as possible. It thus relies on the state machine running later to clean the flag that the event was already generated.

The issue is that there are 2 call paths that calls sctp_ulpq_tail_event() outside of the state machine, causing the flag to linger and possibly omitting a needed wake up in the sequence.

One of the call paths is when enabling SCTP_SENDER_DRY_EVENTS via setsockopt(SCTP_EVENTS), as noticed by Harald Welte. The other is when partial reliability triggers removal of chunks from the send queue when the application calls sendmsg().

This commit fixes it by not setting the flag in case the socket is not owned by the user, as it won't be cleaned later. This works for user-initiated calls and also for rx path processing.

---
 net/sctp/ulpqueue.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -265,7 +265,8 @@ int sctp_ulpq_tail_event(struct sctp_ulp
 		sctp_ulpq_clear_pd(ulpq);
 
 	if (queue == &sk->sk_receive_queue && !sp->data_ready_signalled) {
-		sp->data_ready_signalled = 1;
+		if (!sock_owned_by_user(sk))
+			sp->data_ready_signalled = 1;
 		sk->sk_data_ready(sk);
 	}
 	return 1;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Haishuang Yan <[email protected]>

[ Upstream commit 0f693f1995cf002432b70f43ce73f79bf8d0b6c9 ]

ttl and tos variables are declared and assigned, but are not used in iptunnel_xmit() function.

---
 net/ipv4/ip_tunnel.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -609,8 +609,8 @@ void ip_md_tunnel_xmit(struct sk_buff *s
 		ip_rt_put(rt);
 		goto tx_dropped;
 	}
-	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos,
-		      key->ttl, df, !net_eq(tunnel->net, dev_net(dev)));
+	iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl,
+		      df, !net_eq(tunnel->net, dev_net(dev)));
 	return;
 tx_error:
 	dev->stats.tx_errors++;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaegeuk Kim <[email protected]>

commit afd2b4da40b3b567ef8d8e6881479345a2312a03 upstream.

If we set CP_ERROR_FLAG in roll-forward error, f2fs is no longer to proceed any IOs due to f2fs_cp_error(). But, for example, if some stale data is involved on roll-forward process, we're able to get -ENOENT, getting fs stuck. If we get any error, let fill_super set SBI_NEED_FSCK and try to recover back to stable point.

---
 fs/f2fs/recovery.c |    2 --
 1 file changed, 2 deletions(-)

@@ -626,8 +626,6 @@ out:
 	}
 
 	clear_sbi_flag(sbi, SBI_POR_DOING);
-	if (err)
-		set_ckpt_flags(sbi, CP_ERROR_FLAG);
 	mutex_unlock(&sbi->cp_mutex);
 
 	/* let's drop all the directory inodes for clean checkpoint */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaegeuk Kim <[email protected]>

commit 125c9fb1ccb53eb2ea9380df40f3c743f3fb2fed upstream.

We need to check HOT_DATA to truncate any previous data block when doing roll-forward recovery.

---
 fs/f2fs/recovery.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -316,7 +316,7 @@ static int check_index_in_prev_nodes(str
 		return 0;
 
 	/* Get the previous summary */
-	for (i = CURSEG_WARM_DATA; i <= CURSEG_COLD_DATA; i++) {
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
 		struct curseg_info *curseg = CURSEG_I(sbi, i);
 		if (curseg->segno == segno) {
 			sum = curseg->sum_blk->entries[blkoff];

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit 767d035d838f4fd6b5a5bbd7a3f6d293b7f65a49 upstream.

execve used to leak FSBASE and GSBASE on AMD CPUs. Fix it.

The security impact of this bug is small but not quite zero -- it could weaken ASLR when a privileged task execs a less privileged program, but only if program changed bitness across the exec, or the child binary was highly unusual or actively malicious. A child program that was compromised after the exec would not have access to the leaked base.

---
 arch/x86/kernel/process_64.c |    9 +++++++++
 1 file changed, 9 insertions(+)

@@ -216,10 +216,19 @@ start_thread_common(struct pt_regs *regs
 		    unsigned long new_sp,
 		    unsigned int _cs, unsigned int _ss, unsigned int _ds)
 {
+	WARN_ON_ONCE(regs != current_pt_regs());
+
+	if (static_cpu_has(X86_BUG_NULL_SEG)) {
+		/* Loading zero below won't clear the base. */
+		loadsegment(fs, __USER_DS);
+		load_gs_index(__USER_DS);
+	}
+
 	loadsegment(fs, 0);
 	loadsegment(es, _ds);
 	loadsegment(ds, _ds);
 	load_gs_index(0);
+
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
 	regs->cs		= _cs;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <[email protected]>

commit 9584d98bed7a7a904d0702ad06bbcc94703cb5b4 upstream.

In ELF_COPY_CORE_REGS, we're copying from the current task, so accessing thread.fsbase and thread.gsbase makes no sense. Just read the values from the CPU registers.

In practice, the old code would have been correct most of the time simply because thread.fsbase and thread.gsbase usually matched the CPU registers.

---
 arch/x86/include/asm/elf.h |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

@@ -204,6 +204,7 @@ void set_personality_ia32(bool);
 
 #define ELF_CORE_COPY_REGS(pr_reg, regs)			\
 do {								\
+	unsigned long base;					\
 	unsigned v;						\
 	(pr_reg)[0] = (regs)->r15;				\
 	(pr_reg)[1] = (regs)->r14;				\

@@ -226,8 +227,8 @@ do {								\
 	(pr_reg)[18] = (regs)->flags;				\
 	(pr_reg)[19] = (regs)->sp;				\
 	(pr_reg)[20] = (regs)->ss;				\
-	(pr_reg)[21] = current->thread.fsbase;			\
-	(pr_reg)[22] = current->thread.gsbase;			\
+	rdmsrl(MSR_FS_BASE, base); (pr_reg)[21] = base;		\
+	rdmsrl(MSR_KERNEL_GS_BASE, base); (pr_reg)[22] = base;	\
 	asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v;	\
 	asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v;	\
 	asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v;	\

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jason Wang <[email protected]>

[ Upstream commit 8b949bef9172ca69d918e93509a4ecb03d0355e0 ]

We check tx avail through vhost_enable_notify() in the past which is wrong since it only checks whether or not guest has filled more available buffer since last avail idx synchronization which was just done by vhost_vq_avail_empty() before. What we really want is checking pending buffers in the avail ring. Fix this by calling vhost_vq_avail_empty() instead.

This issue could be noticed by doing netperf TCP_RR benchmark as client from guest (but not host). With this fix, TCP_RR from guest to localhost restores from 1375.91 trans per sec to 55235.28 trans per sec on my laptop (Intel(R) Core(TM) i7-5600U CPU @ 2.60GHz).

---
 drivers/vhost/net.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

@@ -537,8 +537,13 @@ static int vhost_net_rx_peek_head_len(st
 
 		preempt_enable();
 
-		if (vhost_enable_notify(&net->dev, vq))
+		if (!vhost_vq_avail_empty(&net->dev, vq))
 			vhost_poll_queue(&vq->poll);
+		else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+			vhost_disable_notify(&net->dev, vq);
+			vhost_poll_queue(&vq->poll);
+		}
+
 		mutex_unlock(&vq->mutex);
 
 		len = peek_head_len(sk);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Foster <[email protected]>

commit 7912e7fef2aebe577f0b46d3cba261f2783c5695 upstream.

Reclaim during quotacheck can lead to deadlocks on the dquot flush lock:

- Quotacheck populates a local delwri queue with the physical dquot buffers.
- Quotacheck performs the xfs_qm_dqusage_adjust() bulkstat and dirties all of the dquots.
- Reclaim kicks in and attempts to flush a dquot whose buffer is already queud on the quotacheck queue. The flush succeeds but queueing to the reclaim delwri queue fails as the backing buffer is already queued. The flush unlock is now deferred to I/O completion of the buffer from the quotacheck queue.
- The dqadjust bulkstat continues and dirties the recently flushed dquot once again.
- Quotacheck proceeds to the xfs_qm_flush_one() walk which requires the flush lock to update the backing buffers with the in-core recalculated values. It deadlocks on the redirtied dquot as the flush lock was already acquired by reclaim, but the buffer resides on the local delwri queue which isn't submitted until the end of quotacheck.

This is reproduced by running quotacheck on a filesystem with a couple million inodes in low memory (512MB-1GB) situations. This is a regression as of commit 43ff2122e6 ("xfs: on-stack delayed write buffer lists"), which removed a trylock and buffer I/O submission from the quotacheck dquot flush sequence.

Quotacheck first resets and collects the physical dquot buffers in a delwri queue. Then, it traverses the filesystem inodes via bulkstat, updates the in-core dquots, flushes the corrected dquots to the backing buffers and finally submits the delwri queue for I/O. Since the backing buffers are queued across the entire quotacheck operation, dquot reclaim cannot possibly complete a dquot flush before quotacheck completes.

Therefore, quotacheck must submit the buffer for I/O in order to cycle the flush lock and flush the dirty in-core dquot to the buffer. Add a delwri queue buffer push mechanism to submit an individual buffer for I/O without losing the delwri queue status and use it from quotacheck to avoid the deadlock. This restores quotacheck behavior to as before the regression was introduced.

---
 fs/xfs/xfs_buf.c   |   60 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_buf.h   |    1 
 fs/xfs/xfs_qm.c    |   28 +++++++++++++++++++++++-
 fs/xfs/xfs_trace.h |    1 
 4 files changed, 89 insertions(+), 1 deletion(-)

@@ -2022,6 +2022,66 @@ xfs_buf_delwri_submit(
 	return error;
 }
 
+/*
+ * Push a single buffer on a delwri queue.
+ *
+ * The purpose of this function is to submit a single buffer of a delwri queue
+ * and return with the buffer still on the original queue. The waiting delwri
+ * buffer submission infrastructure guarantees transfer of the delwri queue
+ * buffer reference to a temporary wait list. We reuse this infrastructure to
+ * transfer the buffer back to the original queue.
+ *
+ * Note the buffer transitions from the queued state, to the submitted and wait
+ * listed state and back to the queued state during this call. The buffer
+ * locking and queue management logic between _delwri_pushbuf() and
+ * _delwri_queue() guarantee that the buffer cannot be queued to another list
+ * before returning.
+ */
+int
+xfs_buf_delwri_pushbuf(
+	struct xfs_buf		*bp,
+	struct list_head	*buffer_list)
+{
+	LIST_HEAD		(submit_list);
+	int			error;
+
+	ASSERT(bp->b_flags & _XBF_DELWRI_Q);
+
+	trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_);
+
+	/*
+	 * Isolate the buffer to a new local list so we can submit it for I/O
+	 * independently from the rest of the original list.
+	 */
+	xfs_buf_lock(bp);
+	list_move(&bp->b_list, &submit_list);
+	xfs_buf_unlock(bp);
+
+	/*
+	 * Delwri submission clears the DELWRI_Q buffer flag and returns with
+	 * the buffer on the wait list with an associated reference. Rather than
+	 * bounce the buffer from a local wait list back to the original list
+	 * after I/O completion, reuse the original list as the wait list.
+	 */
+	xfs_buf_delwri_submit_buffers(&submit_list, buffer_list);
+
+	/*
+	 * The buffer is now under I/O and wait listed as during typical delwri
+	 * submission. Lock the buffer to wait for I/O completion. Rather than
+	 * remove the buffer from the wait list and release the reference, we
+	 * want to return with the buffer queued to the original list. The
+	 * buffer already sits on the original list with a wait list reference,
+	 * however. If we let the queue inherit that wait list reference, all we
+	 * need to do is reset the DELWRI_Q flag.
+	 */
+	xfs_buf_lock(bp);
+	error = bp->b_error;
+	bp->b_flags |= _XBF_DELWRI_Q;
+	xfs_buf_unlock(bp);
+
+	return error;
+}
+
 int __init
 xfs_buf_init(void)
 {

@@ -333,6 +333,7 @@ extern void xfs_buf_delwri_cancel(struct
 extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
 extern int xfs_buf_delwri_submit(struct list_head *);
 extern int xfs_buf_delwri_submit_nowait(struct list_head *);
+extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *);
 
 /* Buffer Daemon Setup Routines */
 extern int xfs_buf_init(void);

@@ -1247,6 +1247,7 @@ xfs_qm_flush_one(
 	struct xfs_dquot	*dqp,
 	void			*data)
 {
+	struct xfs_mount	*mp = dqp->q_mount;
 	struct list_head	*buffer_list = data;
 	struct xfs_buf		*bp = NULL;
 	int			error = 0;

@@ -1257,7 +1258,32 @@ xfs_qm_flush_one(
 	if (!XFS_DQ_IS_DIRTY(dqp))
 		goto out_unlock;
 
-	xfs_dqflock(dqp);
+	/*
+	 * The only way the dquot is already flush locked by the time quotacheck
+	 * gets here is if reclaim flushed it before the dqadjust walk dirtied
+	 * it for the final time. Quotacheck collects all dquot bufs in the
+	 * local delwri queue before dquots are dirtied, so reclaim can't have
+	 * possibly queued it for I/O. The only way out is to push the buffer to
+	 * cycle the flush lock.
+	 */
+	if (!xfs_dqflock_nowait(dqp)) {
+		/* buf is pinned in-core by delwri list */
+		DEFINE_SINGLE_BUF_MAP(map, dqp->q_blkno,
+				      mp->m_quotainfo->qi_dqchunklen);
+		bp = _xfs_buf_find(mp->m_ddev_targp, &map, 1, 0, NULL);
+		if (!bp) {
+			error = -EINVAL;
+			goto out_unlock;
+		}
+		xfs_buf_unlock(bp);
+
+		xfs_buf_delwri_pushbuf(bp, buffer_list);
+		xfs_buf_rele(bp);
+
+		error = -EAGAIN;
+		goto out_unlock;
+	}
+
 	error = xfs_qm_dqflush(dqp, &bp);
 	if (error)
 		goto out_unlock;

@@ -366,6 +366,7 @@ DEFINE_BUF_EVENT(xfs_buf_iowait_done);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queue);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queued);
 DEFINE_BUF_EVENT(xfs_buf_delwri_split);
+DEFINE_BUF_EVENT(xfs_buf_delwri_pushbuf);
 DEFINE_BUF_EVENT(xfs_buf_get_uncached);
 DEFINE_BUF_EVENT(xfs_bdstrat_shut);
 DEFINE_BUF_EVENT(xfs_buf_item_relse);

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <[email protected]>

commit 4c1a67bd3606540b9b42caff34a1d5cd94b1cf65 upstream.

We must initialize the firstfsb parameter to _bmapi_write so that it doesn't incorrectly treat stack garbage as a restriction on which AGs it can search for free space.

Fixes-coverity-id: 1402025
Fixes-coverity-id: 1415167

---
 fs/xfs/libxfs/xfs_bmap.c |    9 +++++++++
 fs/xfs/xfs_reflink.c     |    2 +-
 2 files changed, 10 insertions(+), 1 deletion(-)

@@ -6639,6 +6639,15 @@ xfs_bmap_finish_one(
 	bmap.br_blockcount = *blockcount;
 	bmap.br_state = state;
 
+	/*
+	 * firstfsb is tied to the transaction lifetime and is used to
+	 * ensure correct AG locking order and schedule work item
+	 * continuations.  XFS_BUI_MAX_FAST_EXTENTS (== 1) restricts us
+	 * to only making one bmap call per transaction, so it should
+	 * be safe to have it as a local variable here.
+	 */
+	firstfsb = NULLFSBLOCK;
+
 	trace_xfs_bmap_deferred(tp->t_mountp,
 			XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type,
 			XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),

@@ -333,7 +333,7 @@ xfs_reflink_convert_cow_extent(
 	struct xfs_defer_ops		*dfops)
 {
 	struct xfs_bmbt_irec		irec = *imap;
-	xfs_fsblock_t			first_block;
+	xfs_fsblock_t			first_block = NULLFSBLOCK;
 	int				nimaps = 1;
 
 	if (imap->br_state == XFS_EXT_NORM)

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <[email protected]>

commit 10479e2dea83d4c421ad05dfc55d918aa8dfc0cd upstream.

In some circumstances, _alloc_read_agf can return an error code of zero but also a null AGF buffer pointer. Check for this and jump out.

Fixes-coverity-id: 1415250
Fixes-coverity-id: 1415320

---
 fs/xfs/libxfs/xfs_refcount.c |    4 ++++
 fs/xfs/xfs_reflink.c         |    2 ++
 2 files changed, 6 insertions(+)

@@ -1640,6 +1640,10 @@ xfs_refcount_recover_cow_leftovers(
 	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		goto out_trans;
+	if (!agbp) {
+		error = -ENOMEM;
+		goto out_trans;
+	}
 	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
 
 	/* Find all the leftover CoW staging extents. */

@@ -169,6 +169,8 @@ xfs_reflink_find_shared(
 	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
 	if (error)
 		return error;
+	if (!agbp)
+		return -ENOMEM;
 
 	cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL);
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Foster <[email protected]>

commit cfaf2d034360166e569a4929dd83ae9698bed856 upstream.

If a dquot has an id of U32_MAX, the next lookup index increment overflows the uint32_t back to 0. This starts the lookup sequence over from the beginning, repeats indefinitely and results in a livelock.

Update xfs_qm_dquot_walk() to explicitly check for the lookup overflow and exit the loop.

---
 fs/xfs/xfs_qm.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -111,6 +111,9 @@ restart:
 			skipped = 0;
 			break;
 		}
+		/* we're done if id overflows back to zero */
+		if (!next_index)
+			break;
 	}
 
 	if (skipped) {

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Darrick J. Wong <[email protected]>

commit e1a4e37cc7b665b6804fba812aca2f4d7402c249 upstream.

In a pathological scenario where we are trying to bunmapi a single extent in which every other block is shared, it's possible that trying to unmap the entire large extent in a single transaction can generate so many EFIs that we overflow the transaction reservation.

Therefore, use a heuristic to guess at the number of blocks we can safely unmap from a reflink file's data fork in an single transaction. This should prevent problems such as the log head slamming into the tail and ASSERTs that trigger because we've exceeded the transaction reservation.

Note that since bunmapi can fail to unmap the entire range, we must also teach the deferred unmap code to roll into a new transaction whenever we get low on reservation.

---
 fs/xfs/libxfs/xfs_bmap.c     |   37 ++++++++++++++++++++++++++++---------
 fs/xfs/libxfs/xfs_bmap.h     |    2 +-
 fs/xfs/libxfs/xfs_refcount.c |   10 +---------
 fs/xfs/libxfs/xfs_refcount.h |   16 ++++++++++++++++
 fs/xfs/xfs_bmap_item.c       |   17 +++++++++++++++--
 fs/xfs/xfs_trans.h           |    2 +-
 fs/xfs/xfs_trans_bmap.c      |   11 +++++++++--
 7 files changed, 71 insertions(+), 24 deletions(-)

@@ -5555,6 +5555,7 @@ __xfs_bunmapi(
 	int			whichfork;	/* data or attribute fork */
 	xfs_fsblock_t		sum;
 	xfs_filblks_t		len = *rlen;	/* length to unmap in file */
+	xfs_fileoff_t		max_len;
 
 	trace_xfs_bunmap(ip, bno, len, flags, _RET_IP_);
 

@@ -5576,6 +5577,16 @@ __xfs_bunmapi(
 	ASSERT(len > 0);
 	ASSERT(nexts >= 0);
 
+	/*
+	 * Guesstimate how many blocks we can unmap without running the risk of
+	 * blowing out the transaction with a mix of EFIs and reflink
+	 * adjustments.
+	 */
+	if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK)
+		max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res));
+	else
+		max_len = len;
+
 	if (!(ifp->if_flags & XFS_IFEXTENTS) &&
 	    (error = xfs_iread_extents(tp, ip, whichfork)))
 		return error;

@@ -5621,7 +5632,7 @@ __xfs_bunmapi(
 
 	extno = 0;
 	while (bno != (xfs_fileoff_t)-1 && bno >= start && lastx >= 0 &&
-	       (nexts == 0 || extno < nexts)) {
+	       (nexts == 0 || extno < nexts) && max_len > 0) {
 		/*
 		 * Is the found extent after a hole in which bno lives?
 		 * Just back up to the previous extent, if so.

@@ -5655,6 +5666,15 @@ __xfs_bunmapi(
 		}
 		if (del.br_startoff + del.br_blockcount > bno + 1)
 			del.br_blockcount = bno + 1 - del.br_startoff;
+
+		/* How much can we safely unmap? */
+		if (max_len < del.br_blockcount) {
+			del.br_startoff += del.br_blockcount - max_len;
+			if (!wasdel)
+				del.br_startblock += del.br_blockcount - max_len;
+			del.br_blockcount = max_len;
+		}
+
 		sum = del.br_startblock + del.br_blockcount;
 		if (isrt &&
 		    (mod = do_mod(sum, mp->m_sb.sb_rextsize))) {

@@ -5835,6 +5855,7 @@ __xfs_bunmapi(
 		if (!isrt && wasdel)
 			xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, false);
 
+		max_len -= del.br_blockcount;
 		bno = del.br_startoff - 1;
 nodelete:
 		/*

@@ -6604,25 +6625,24 @@ xfs_bmap_finish_one(
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,
-	xfs_filblks_t			blockcount,
+	xfs_filblks_t			*blockcount,
 	xfs_exntst_t			state)
 {
 	struct xfs_bmbt_irec		bmap;
 	int				nimaps = 1;
 	xfs_fsblock_t			firstfsb;
 	int				flags = XFS_BMAPI_REMAP;
-	int				done;
 	int				error = 0;
 
 	bmap.br_startblock = startblock;
 	bmap.br_startoff = startoff;
-	bmap.br_blockcount = blockcount;
+	bmap.br_blockcount = *blockcount;
 	bmap.br_state = state;
 
 	trace_xfs_bmap_deferred(tp->t_mountp,
 			XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type,
 			XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
-			ip->i_ino, whichfork, startoff, blockcount, state);
+			ip->i_ino, whichfork, startoff, *blockcount, state);
 
 	if (whichfork != XFS_DATA_FORK && whichfork != XFS_ATTR_FORK)
 		return -EFSCORRUPTED;

@@ -6641,12 +6661,11 @@ xfs_bmap_finish_one(
 					bmap.br_blockcount, flags, &firstfsb,
 					bmap.br_blockcount, &bmap, &nimaps,
 					dfops);
+		*blockcount = 0;
 		break;
 	case XFS_BMAP_UNMAP:
-		error = xfs_bunmapi(tp, ip, bmap.br_startoff,
-				bmap.br_blockcount, flags, 1, &firstfsb,
-				dfops, &done);
-		ASSERT(done);
+		error = __xfs_bunmapi(tp, ip, startoff, blockcount,
+				XFS_BMAPI_REMAP, 1, &firstfsb, dfops);
 		break;
 	default:
 		ASSERT(0);

@@ -265,7 +265,7 @@ struct xfs_bmap_intent {
 int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_defer_ops *dfops,
 		struct xfs_inode *ip, enum xfs_bmap_intent_type type,
 		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
-		xfs_filblks_t blockcount, xfs_exntst_t state);
+		xfs_filblks_t *blockcount, xfs_exntst_t state);
 int	xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 		struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
 int	xfs_bmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,

@@ -784,14 +784,6 @@ xfs_refcount_merge_extents(
 }
 
 /*
- * While we're adjusting the refcounts records of an extent, we have
- * to keep an eye on the number of extents we're dirtying -- run too
- * many in a single transaction and we'll exceed the transaction's
- * reservation and crash the fs.  Each record adds 12 bytes to the
- * log (plus any key updates) so we'll conservatively assume 24 bytes
- * per record.  We must also leave space for btree splits on both ends
- * of the range and space for the CUD and a new CUI.
- *
  * XXX: This is a pretty hand-wavy estimate.  The penalty for guessing
  * true incorrectly is a shutdown FS; the penalty for guessing false
  * incorrectly is more transaction rolls than might be necessary.

@@ -822,7 +814,7 @@ xfs_refcount_still_have_space(
 	else if (overhead > cur->bc_tp->t_log_res)
 		return false;
 	return  cur->bc_tp->t_log_res - overhead >
-		cur->bc_private.a.priv.refc.nr_ops * 32;
+		cur->bc_private.a.priv.refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD;
 }
 
 /*

@@ -67,4 +67,20 @@ extern int xfs_refcount_free_cow_extent(
 extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
 		xfs_agnumber_t agno);
 
+/*
+ * While we're adjusting the refcounts records of an extent, we have
+ * to keep an eye on the number of extents we're dirtying -- run too
+ * many in a single transaction and we'll exceed the transaction's
+ * reservation and crash the fs.  Each record adds 12 bytes to the
+ * log (plus any key updates) so we'll conservatively assume 32 bytes
+ * per record.  We must also leave space for btree splits on both ends
+ * of the range and space for the CUD and a new CUI.
+ */
+#define XFS_REFCOUNT_ITEM_OVERHEAD	32
+
+static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res)
+{
+	return (log_res * 3 / 4) / XFS_REFCOUNT_ITEM_OVERHEAD;
+}
+
 #endif	/* __XFS_REFCOUNT_H__ */

@@ -395,6 +395,7 @@ xfs_bui_recover(
 	struct xfs_map_extent		*bmap;
 	xfs_fsblock_t			startblock_fsb;
 	xfs_fsblock_t			inode_fsb;
+	xfs_filblks_t			count;
 	bool				op_ok;
 	struct xfs_bud_log_item		*budp;
 	enum xfs_bmap_intent_type	type;

@@ -403,6 +404,7 @@ xfs_bui_recover(
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip = NULL;
 	struct xfs_defer_ops		dfops;
+	struct xfs_bmbt_irec		irec;
 	xfs_fsblock_t			firstfsb;
 
 	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));

@@ -480,13 +482,24 @@ xfs_bui_recover(
 	}
 	xfs_trans_ijoin(tp, ip, 0);
 
+	count = bmap->me_len;
 	error = xfs_trans_log_finish_bmap_update(tp, budp, &dfops, type,
 			ip, whichfork, bmap->me_startoff,
-			bmap->me_startblock, bmap->me_len,
-			state);
+			bmap->me_startblock, &count, state);
 	if (error)
 		goto err_dfops;
 
+	if (count > 0) {
+		ASSERT(type == XFS_BMAP_UNMAP);
+		irec.br_startblock = bmap->me_startblock;
+		irec.br_blockcount = count;
+		irec.br_startoff = bmap->me_startoff;
+		irec.br_state = state;
+		error = xfs_bmap_unmap_extent(tp->t_mountp, &dfops, ip, &irec);
+		if (error)
+			goto err_dfops;
+	}
+
 	/* Finish transaction, free inodes. */
 	error = xfs_defer_finish(&tp, &dfops, NULL);
 	if (error)

@@ -277,6 +277,6 @@ int xfs_trans_log_finish_bmap_update(str
 		struct xfs_bud_log_item *rudp, struct xfs_defer_ops *dfops,
 		enum xfs_bmap_intent_type type, struct xfs_inode *ip,
 		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
-		xfs_filblks_t blockcount, xfs_exntst_t state);
+		xfs_filblks_t *blockcount, xfs_exntst_t state);
 
 #endif	/* __XFS_TRANS_H__ */

@@ -63,7 +63,7 @@ xfs_trans_log_finish_bmap_update(
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,
-	xfs_filblks_t			blockcount,
+	xfs_filblks_t			*blockcount,
 	xfs_exntst_t			state)
 {
 	int				error;

@@ -196,16 +196,23 @@ xfs_bmap_update_finish_item(
 	void				**state)
 {
 	struct xfs_bmap_intent		*bmap;
+	xfs_filblks_t			count;
 	int				error;
 
 	bmap = container_of(item, struct xfs_bmap_intent, bi_list);
+	count = bmap->bi_bmap.br_blockcount;
 	error = xfs_trans_log_finish_bmap_update(tp, done_item, dop,
 			bmap->bi_type,
 			bmap->bi_owner, bmap->bi_whichfork,
 			bmap->bi_bmap.br_startoff,
 			bmap->bi_bmap.br_startblock,
-			bmap->bi_bmap.br_blockcount,
+			&count,
 			bmap->bi_bmap.br_state);
+	if (!error && count > 0) {
+		ASSERT(bmap->bi_type == XFS_BMAP_UNMAP);
+		bmap->bi_bmap.br_blockcount = count;
+		return -EAGAIN;
+	}
 	kmem_free(bmap);
 	return error;
 }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Foster <[email protected]>

commit 79e641ce29cfae5b8fc55fb77ac62d11d2d849c0 upstream.

If a filesystem shutdown occurs with a buffer log item in the CIL and a log force occurs, the ->iop_unpin() handler is generally expected to tear down the bli properly. This entails freeing the bli memory and releasing the associated hold on the buffer so it can be released and the filesystem unmounted.

If this sequence occurs while ->bli_refcount is elevated (i.e., another transaction is open and attempting to modify the buffer), however, ->iop_unpin() may not be responsible for releasing the bli. Instead, the transaction may release the final ->bli_refcount reference and thus xfs_trans_brelse() is responsible for tearing down the bli.

While xfs_trans_brelse() does drop the reference count, it only attempts to release the bli if it is clean (i.e., not in the CIL/AIL). If the filesystem is shutdown and the bli is sitting dirty in the CIL as noted above, this ends up skipping the last opportunity to release the bli. In turn, this leaves the hold on the buffer and causes an unmount hang. This can be reproduced by running generic/388 in repetition.

Update xfs_trans_brelse() to handle this shutdown corner case correctly. If the final bli reference is dropped and the filesystem is shutdown, remove the bli from the AIL (if necessary) and release the bli to drop the buffer hold and ensure an unmount does not hang.

---
 fs/xfs/xfs_trans_buf.c |   23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

@@ -356,6 +356,7 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 		 xfs_buf_t	*bp)
 {
 	xfs_buf_log_item_t	*bip;
+	int			freed;
 
 	/*
 	 * Default to a normal brelse() call if the tp is NULL.

@@ -419,16 +420,22 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 	/*
 	 * Drop our reference to the buf log item.
 	 */
-	atomic_dec(&bip->bli_refcount);
+	freed = atomic_dec_and_test(&bip->bli_refcount);
 
 	/*
-	 * If the buf item is not tracking data in the log, then
-	 * we must free it before releasing the buffer back to the
-	 * free pool.  Before releasing the buffer to the free pool,
-	 * clear the transaction pointer in b_fsprivate2 to dissolve
-	 * its relation to this transaction.
-	 */
-	if (!xfs_buf_item_dirty(bip)) {
+	 * If the buf item is not tracking data in the log, then we must free it
+	 * before releasing the buffer back to the free pool.
+	 *
+	 * If the fs has shutdown and we dropped the last reference, it may fall
+	 * on us to release a (possibly dirty) bli if it never made it to the
+	 * AIL (e.g., the aborted unpin already happened and didn't release it
+	 * due to our reference). Since we're already shutdown and need xa_lock,
+	 * just force remove from the AIL and release the bli here.
+	 */
+	if (XFS_FORCED_SHUTDOWN(tp->t_mountp) && freed) {
+		xfs_trans_ail_remove(&bip->bli_item, SHUTDOWN_LOG_IO_ERROR);
+		xfs_buf_item_relse(bp);
+	} else if (!xfs_buf_item_dirty(bip)) {
 /***
 		ASSERT(bp->b_pincount == 0);
 ***/

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Foster <[email protected]>

commit 3d4b4a3e30ae7a949c31e1e10268a3da4723d290 upstream.

When a buffer is modified, logged and committed, it ultimately ends up sitting on the AIL with a dirty bli waiting for metadata writeback. If another transaction locks and invalidates the buffer (freeing an inode chunk, for example) in the meantime, the bli is flagged as stale, the dirty state is cleared and the bli remains in the AIL.

If a shutdown occurs before the transaction that has invalidated the buffer is committed, the transaction is ultimately aborted. The log items are flagged as such and ->iop_unlock() handles the aborted items. Because the bli is clean (due to the invalidation), ->iop_unlock() unconditionally releases it. The log item may still reside in the AIL, however, which means the I/O completion handler may still run and attempt to access it. This results in assert failure due to the release of the bli while still present in the AIL and a subsequent NULL dereference and panic in the buffer I/O completion handling. This can be reproduced by running generic/388 in repetition.

To avoid this problem, update xfs_buf_item_unlock() to first check whether the bli is aborted and if so, remove it from the AIL before it is released. This ensures that the bli is no longer accessed during the shutdown sequence after it has been freed.

---
 fs/xfs/xfs_buf_item.c |   21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

@@ -636,20 +636,23 @@ xfs_buf_item_unlock(
 
 	/*
 	 * Clean buffers, by definition, cannot be in the AIL. However, aborted
-	 * buffers may be dirty and hence in the AIL. Therefore if we are
-	 * aborting a buffer and we've just taken the last refernce away, we
-	 * have to check if it is in the AIL before freeing it. We need to free
-	 * it in this case, because an aborted transaction has already shut the
-	 * filesystem down and this is the last chance we will have to do so.
+	 * buffers may be in the AIL regardless of dirty state. An aborted
+	 * transaction that invalidates a buffer already in the AIL may have
+	 * marked it stale and cleared the dirty state, for example.
+	 *
+	 * Therefore if we are aborting a buffer and we've just taken the last
+	 * reference away, we have to check if it is in the AIL before freeing
+	 * it. We need to free it in this case, because an aborted transaction
+	 * has already shut the filesystem down and this is the last chance we
+	 * will have to do so.
 	 */
 	if (atomic_dec_and_test(&bip->bli_refcount)) {
-		if (clean)
-			xfs_buf_item_relse(bp);
-		else if (aborted) {
+		if (aborted) {
 			ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
 			xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR);
 			xfs_buf_item_relse(bp);
-		}
+		} else if (clean)
+			xfs_buf_item_relse(bp);
 	}
 
 	if (!(flags & XFS_BLI_HOLD))

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Darrick J. Wong <[email protected]>

commit 61d819e7bcb7f33da710bf3f5dcb2bcf1e48203c upstream.

bmap returns a dumb LBA address but not the block device that goes with that LBA. Swapfiles don't care about this and will blindly assume that the data volume is the correct blockdev, which is totally bogus for files on the rt subvolume. This results in the swap code doing IOs to arbitrary locations on the data device(!) if the passed in mapping is a realtime file, so just turn off bmap for rt files.

---
 fs/xfs/xfs_aops.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

@@ -1566,9 +1566,12 @@ xfs_vm_bmap(
 	 * The swap code (ab-)uses ->bmap to get a block mapping and then
 	 * bypasseѕ the file system for actual I/O.  We really can't allow
 	 * that on reflinks inodes, so we have to skip out here.  And yes,
-	 * 0 is the magic code for a bmap error..
+	 * 0 is the magic code for a bmap error.
+	 *
+	 * Since we don't pass back blockdev info, we can't return bmap
+	 * information for rt files either.
 	 */
-	if (xfs_is_reflink_inode(ip)) {
+	if (xfs_is_reflink_inode(ip) || XFS_IS_REALTIME_INODE(ip)) {
 		xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 		return 0;
 	}

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Foster <[email protected]>

commit 39775431f82f890f4aaa08860a30883d081bffc7 upstream.

Log recovery allocates in-core transaction and member item data structures on-demand as it processes the on-disk log. Transactions are allocated on first encounter on-disk and stored in a hash table structure where they are easily accessible for subsequent lookups. Transaction items are also allocated on demand and are attached to the associated transactions.

When a commit record is encountered in the log, the transaction is committed to the fs and the in-core structures are freed. If a filesystem crashes or shuts down before all in-core log buffers are flushed to the log, however, not all transactions may have commit records in the log. As expected, the modifications in such an incomplete transaction are not replayed to the fs. The in-core data structures for the partial transaction are never freed, however, resulting in a memory leak.

Update xlog_do_recovery_pass() to first correctly initialize the hash table array so empty lists can be distinguished from populated lists on function exit. Update xlog_recover_free_trans() to always remove the transaction from the list prior to freeing the associated memory. Finally, walk the hash table of transaction lists as the last step before it goes out of scope and free any transactions that may remain on the lists. This prevents a memory leak of partial transactions in the log.

---
 fs/xfs/xfs_log_recover.c |   21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

@@ -4152,7 +4152,7 @@ xlog_recover_commit_trans(
 
 	#define XLOG_RECOVER_COMMIT_QUEUE_MAX 100
 
-	hlist_del(&trans->r_list);
+	hlist_del_init(&trans->r_list);
 
 	error = xlog_recover_reorder_trans(log, trans, pass);
 	if (error)

@@ -4354,6 +4354,8 @@ xlog_recover_free_trans(
 	xlog_recover_item_t	*item, *n;
 	int			i;
 
+	hlist_del_init(&trans->r_list);
+
 	list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) {
 		/* Free the regions in the item. */
 		list_del(&item->ri_list);

@@ -5222,12 +5224,16 @@ xlog_do_recovery_pass(
 	int			error2 = 0;
 	int			bblks, split_bblks;
 	int			hblks, split_hblks, wrapped_hblks;
+	int			i;
 	struct hlist_head	rhash[XLOG_RHASH_SIZE];
 	LIST_HEAD		(buffer_list);
 
 	ASSERT(head_blk != tail_blk);
 	rhead_blk = 0;
 
+	for (i = 0; i < XLOG_RHASH_SIZE; i++)
+		INIT_HLIST_HEAD(&rhash[i]);
+
 	/*
 	 * Read the header of the tail block and get the iclog buffer size from
 	 * h_size.  Use this to tell how many sectors make up the log header.

@@ -5464,6 +5470,19 @@ xlog_do_recovery_pass(
 	if (error && first_bad)
 		*first_bad = rhead_blk;
 
+	/*
+	 * Transactions are freed at commit time but transactions without commit
+	 * records on disk are never committed. Free any that may be left in the
+	 * hash table.
+	 */
+	for (i = 0; i < XLOG_RHASH_SIZE; i++) {
+		struct hlist_node	*tmp;
+		struct xlog_recover	*trans;
+
+		hlist_for_each_entry_safe(trans, tmp, &rhash[i], r_list)
+			xlog_recover_free_trans(trans);
+	}
+
 	return error ? error : error2;
 }
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Foster <[email protected]>

commit cf2cb7845d6e101cb17bd62f8aa08cd514fc8988 upstream.

XFS runs an eofblocks reclaim scan before returning an ENOSPC error to userspace for buffered writes. This facilitates aggressive speculative preallocation without causing user visible side effects such as premature ENOSPC.

Run a cowblocks scan in the same situation to reclaim lingering COW fork preallocation throughout the filesystem.

---
 fs/xfs/xfs_file.c |    1 +
 1 file changed, 1 insertion(+)

@@ -729,6 +729,7 @@ write_retry:
 		xfs_rw_iunlock(ip, iolock);
 		eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
 		xfs_icache_free_eofblocks(ip->i_mount, &eofb);
+		xfs_icache_free_cowblocks(ip->i_mount, &eofb);
 		goto write_retry;
 	}
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <[email protected]>

commit cd87d867920155911d0d2e6485b769d853547750 upstream.

In quite a few places we call xfs_da_read_buf with a mappedbno that we don't control, then assume that the function passes back either an error code or a buffer pointer. Unfortunately, if mappedbno == -2 and bno maps to a hole, we get a return code of zero and a NULL buffer, which means that we crash if we actually try to use that buffer pointer. This happens immediately when we set the buffer type for transaction context.

Therefore, check that we have no error code and a non-NULL bp before trying to use bp. This patch is a follow-up to an incomplete fix in 96a3aefb8ffde231 ("xfs: don't crash if reading a directory results in an unexpected hole").

---
 fs/xfs/libxfs/xfs_attr_leaf.c  |    2 +-
 fs/xfs/libxfs/xfs_da_btree.c   |    2 +-
 fs/xfs/libxfs/xfs_dir2_block.c |    2 +-
 fs/xfs/libxfs/xfs_dir2_leaf.c  |    4 ++--
 4 files changed, 5 insertions(+), 5 deletions(-)

@@ -351,7 +351,7 @@ xfs_attr3_leaf_read(
 
 	err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp,
 				XFS_ATTR_FORK, &xfs_attr3_leaf_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF);
 	return err;
 }

@@ -263,7 +263,7 @@ xfs_da3_node_read(
 
 	err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp,
 					which_fork, &xfs_da3_node_buf_ops);
-	if (!err && tp) {
+	if (!err && tp && *bpp) {
 		struct xfs_da_blkinfo	*info = (*bpp)->b_addr;
 		int			type;
 

@@ -139,7 +139,7 @@ xfs_dir3_block_read(
 
 	err = xfs_da_read_buf(tp, dp, mp->m_dir_geo->datablk, -1, bpp,
 				XFS_DATA_FORK, &xfs_dir3_block_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_BLOCK_BUF);
 	return err;
 }

@@ -268,7 +268,7 @@ xfs_dir3_leaf_read(
 
 	err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
 				XFS_DATA_FORK, &xfs_dir3_leaf1_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF);
 	return err;
 }

@@ -285,7 +285,7 @@ xfs_dir3_leafn_read(
 
 	err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
 				XFS_DATA_FORK, &xfs_dir3_leafn_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF);
 	return err;
 }

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <[email protected]>

commit 1e86eabe73b73c82e1110c746ed3ec6d5e1c0a0d upstream.

Check the _btree_check_block return value for the firstrec and lastrec functions, since we have the ability to signal that the repositioning did not succeed.

Fixes-coverity-id: 114067
Fixes-coverity-id: 114068

---
 fs/xfs/libxfs/xfs_btree.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

@@ -714,7 +714,8 @@ xfs_btree_firstrec(
 	 * Get the block pointer for this level.
 	 */
 	block = xfs_btree_get_block(cur, level, &bp);
-	xfs_btree_check_block(cur, block, level, bp);
+	if (xfs_btree_check_block(cur, block, level, bp))
+		return 0;
 	/*
 	 * It's empty, there is no such record.
 	 */

@@ -743,7 +744,8 @@ xfs_btree_lastrec(
 	 * Get the block pointer for this level.
 	 */
 	block = xfs_btree_get_block(cur, level, &bp);
-	xfs_btree_check_block(cur, block, level, bp);
+	if (xfs_btree_check_block(cur, block, level, bp))
+		return 0;
 	/*
 	 * It's empty, there is no such record.
 	 */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Foster <[email protected]>

commit 95989c46d2a156365867b1d795fdefce71bce378 upstream.

The 0-day kernel test robot reports assertion failures on !CONFIG_SMP kernels due to failed spin_is_locked() checks. As it turns out, spin_is_locked() is hardcoded to return zero on !CONFIG_SMP kernels and so this function cannot be relied on to verify spinlock state in this configuration.

To avoid this problem, replace the associated asserts with lockdep variants that do the right thing regardless of kernel configuration. Drop the one assert that checks for an unlocked lock as there is no suitable lockdep variant for that case. This moves the spinlock checks from XFS debug code to lockdep, but generally provides the same level of protection.

---
 fs/xfs/xfs_buf.c    |    2 +-
 fs/xfs/xfs_icache.c |    5 ++---
 2 files changed, 3 insertions(+), 4 deletions(-)

@@ -116,7 +116,7 @@ static inline void
 __xfs_buf_ioacct_dec(
 	struct xfs_buf	*bp)
 {
-	ASSERT(spin_is_locked(&bp->b_lock));
+	lockdep_assert_held(&bp->b_lock);
 
 	if (bp->b_state & XFS_BSTATE_IN_FLIGHT) {
 		bp->b_state &= ~XFS_BSTATE_IN_FLIGHT;

@@ -66,7 +66,6 @@ xfs_inode_alloc(
 
 	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
-	ASSERT(!spin_is_locked(&ip->i_flags_lock));
 	ASSERT(!xfs_isiflocked(ip));
 	ASSERT(ip->i_ino == 0);
 

@@ -192,7 +191,7 @@ xfs_perag_set_reclaim_tag(
 {
 	struct xfs_mount	*mp = pag->pag_mount;
 
-	ASSERT(spin_is_locked(&pag->pag_ici_lock));
+	lockdep_assert_held(&pag->pag_ici_lock);
 	if (pag->pag_ici_reclaimable++)
 		return;
 

@@ -214,7 +213,7 @@ xfs_perag_clear_reclaim_tag(
 {
 	struct xfs_mount	*mp = pag->pag_mount;
 
-	ASSERT(spin_is_locked(&pag->pag_ici_lock));
+	lockdep_assert_held(&pag->pag_ici_lock);
 	if (--pag->pag_ici_reclaimable)
 		return;
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lukas Czerner <[email protected]>

commit 56bdf855e676f1f2ed7033f288f57dfd315725ba upstream.

According to the commit that implemented per-inode DAX flag:
commit 58f88ca2df72 ("xfs: introduce per-inode DAX enablement") the flag is supposed to act as "inherit flag".

Currently this only works in the situations where parent directory already has a flag in di_flags set, otherwise inheritance does not work. This is because setting the XFS_DIFLAG2_DAX flag is done in a wrong branch designated for di_flags, not di_flags2.

Fix this by moving the code to branch designated for setting di_flags2, which does test for flags in di_flags2.

---
 fs/xfs/xfs_inode.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

@@ -881,7 +881,6 @@ xfs_ialloc(
 	case S_IFREG:
 	case S_IFDIR:
 		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
-			uint64_t	di_flags2 = 0;
 			uint		di_flags = 0;
 
 			if (S_ISDIR(mode)) {

@@ -918,20 +917,23 @@ xfs_ialloc(
 				di_flags |= XFS_DIFLAG_NODEFRAG;
 			if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
 				di_flags |= XFS_DIFLAG_FILESTREAM;
-			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
-				di_flags2 |= XFS_DIFLAG2_DAX;
 
 			ip->i_d.di_flags |= di_flags;
-			ip->i_d.di_flags2 |= di_flags2;
 		}
 		if (pip &&
 		    (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) &&
 		    pip->i_d.di_version == 3 &&
 		    ip->i_d.di_version == 3) {
+			uint64_t	di_flags2 = 0;
+
 			if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
-				ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+				di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
 				ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
 			}
+			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
+				di_flags2 |= XFS_DIFLAG2_DAX;
+
+			ip->i_d.di_flags2 |= di_flags2;
 		}
 		/* FALLTHROUGH */
 	case S_IFLNK:

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Carlos Maiolino <[email protected]>

commit d3a304b6292168b83b45d624784f973fdc1ca674 upstream.

When a buffer has been failed during writeback, the inode items into it are kept flush locked, and are never resubmitted due the flush lock, so, if any buffer fails to be written, the items in AIL are never written to disk and never unlocked.

This causes unmount operation to hang due these items flush locked in AIL, but this also causes the items in AIL to never be written back, even when the IO device comes back to normal.

I've been testing this patch with a DM-thin device, creating a filesystem larger than the real device.

When writing enough data to fill the DM-thin device, XFS receives ENOSPC errors from the device, and keep spinning on xfsaild (when 'retry forever' configuration is set).

At this point, the filesystem can not be unmounted because of the flush locked items in AIL, but worse, the items in AIL are never retried at all (once xfs_inode_item_push() will skip the items that are flush locked), even if the underlying DM-thin device is expanded to the proper size.

This patch fixes both cases, retrying any item that has been failed previously, using the infra-structure provided by the previous patch.

---
 fs/xfs/xfs_buf_item.c   |   28 ++++++++++++++++++++++++++++
 fs/xfs/xfs_buf_item.h   |    3 +++
 fs/xfs/xfs_inode_item.c |   47 +++++++++++++++++++++++++++++++++++++++++++----
 fs/xfs/xfs_trans.h      |    1 +
 fs/xfs/xfs_trans_ail.c  |    3 ++-
 fs/xfs/xfs_trans_priv.h |   31 +++++++++++++++++++++++++++++++
 6 files changed, 108 insertions(+), 5 deletions(-)

@@ -1234,3 +1234,31 @@ xfs_buf_iodone(
 	xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE);
 	xfs_buf_item_free(BUF_ITEM(lip));
 }
+
+/*
+ * Requeue a failed buffer for writeback
+ *
+ * Return true if the buffer has been re-queued properly, false otherwise
+ */
+bool
+xfs_buf_resubmit_failed_buffers(
+	struct xfs_buf		*bp,
+	struct xfs_log_item	*lip,
+	struct list_head	*buffer_list)
+{
+	struct xfs_log_item	*next;
+
+	/*
+	 * Clear XFS_LI_FAILED flag from all items before resubmit
+	 *
+	 * XFS_LI_FAILED set/clear is protected by xa_lock, caller  this
+	 * function already have it acquired
+	 */
+	for (; lip; lip = next) {
+		next = lip->li_bio_list;
+		xfs_clear_li_failed(lip);
+	}
+
+	/* Add this buffer back to the delayed write list */
+	return xfs_buf_delwri_queue(bp, buffer_list);
+}

@@ -70,6 +70,9 @@ void	xfs_buf_attach_iodone(struct xfs_bu
 			      xfs_log_item_t *);
 void	xfs_buf_iodone_callbacks(struct xfs_buf *);
 void	xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *);
+bool	xfs_buf_resubmit_failed_buffers(struct xfs_buf *,
+					struct xfs_log_item *,
+					struct list_head *);
 
 extern kmem_zone_t	*xfs_buf_item_zone;
 

@@ -50,6 +50,7 @@ typedef struct xfs_log_item {
 	struct xfs_ail			*li_ailp;	/* ptr to AIL */
 	uint				li_type;	/* item type */
 	uint				li_flags;	/* misc flags */
+	struct xfs_buf			*li_buf;	/* real buffer pointer */
 	struct xfs_log_item		*li_bio_list;	/* buffer item list */
 	void				(*li_cb)(struct xfs_buf *,
 						 struct xfs_log_item *);

@@ -687,12 +687,13 @@ xfs_trans_ail_update_bulk(
 bool
 xfs_ail_delete_one(
 	struct xfs_ail		*ailp,
-	struct xfs_log_item 	*lip)
+	struct xfs_log_item	*lip)
 {
 	struct xfs_log_item	*mlip = xfs_ail_min(ailp);
 
 	trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn);
 	xfs_ail_delete(ailp, lip);
+	xfs_clear_li_failed(lip);
 	lip->li_flags &= ~XFS_LI_IN_AIL;
 	lip->li_lsn = 0;
 

@@ -164,4 +164,35 @@ xfs_trans_ail_copy_lsn(
 	*dst = *src;
 }
 #endif
+
+static inline void
+xfs_clear_li_failed(
+	struct xfs_log_item	*lip)
+{
+	struct xfs_buf	*bp = lip->li_buf;
+
+	ASSERT(lip->li_flags & XFS_LI_IN_AIL);
+	lockdep_assert_held(&lip->li_ailp->xa_lock);
+
+	if (lip->li_flags & XFS_LI_FAILED) {
+		lip->li_flags &= ~XFS_LI_FAILED;
+		lip->li_buf = NULL;
+		xfs_buf_rele(bp);
+	}
+}
+
+static inline void
+xfs_set_li_failed(
+	struct xfs_log_item	*lip,
+	struct xfs_buf		*bp)
+{
+	lockdep_assert_held(&lip->li_ailp->xa_lock);
+
+	if (!(lip->li_flags & XFS_LI_FAILED)) {
+		xfs_buf_hold(bp);
+		lip->li_flags |= XFS_LI_FAILED;
+		lip->li_buf = bp;
+	}
+}
+
 #endif	/* __XFS_TRANS_PRIV_H__ */

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Foster <[email protected]>

commit 284f1c2c9bebf871861184b0e2c40fa921dd380b upstream.

The high-level log recovery algorithm consists of two loops that walk the physical log and process log records from the tail to the head. The first loop handles the case where the tail is beyond the head and processes records up to the end of the physical log. The subsequent loop processes records from the beginning of the physical log to the head.

Because log records can wrap around the end of the physical log, the first loop mentioned above must handle this case appropriately. Records are processed from in-core buffers, which means that this algorithm must split the reads of such records into two partial I/Os: 1.) from the beginning of the record to the end of the log and 2.) from the beginning of the log to the end of the record. This is further complicated by the fact that the log record header and log record data are read into independent buffers.

The current handling of each buffer correctly splits the reads when either the header or data starts before the end of the log and wraps around the end. The data read does not correctly handle the case where the prior header read wrapped or ends on the physical log end boundary. blk_no is incremented to or beyond the log end after the header read to point to the record data, but the split data read logic triggers, attempts to read from an invalid log block and ultimately causes log recovery to fail. This can be reproduced fairly reliably via xfstests tests generic/047 and generic/388 with large iclog sizes (256k) and small (10M) logs.

If the record header read has pushed beyond the end of the physical log, the subsequent data read is actually contiguous. Update the data read logic to detect the case where blk_no has wrapped, mod it against the log size to read from the correct address and issue one contiguous read for the log data buffer. The log record is processed as normal from the buffer(s), the loop exits after the current iteration and the subsequent loop picks up with the first new record after the start of the log.

---
 fs/xfs/xfs_log_recover.c |   18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

@@ -5216,7 +5216,7 @@ xlog_do_recovery_pass(
 	xfs_daddr_t		*first_bad)	/* out: first bad log rec */
 {
 	xlog_rec_header_t	*rhead;
-	xfs_daddr_t		blk_no;
+	xfs_daddr_t		blk_no, rblk_no;
 	xfs_daddr_t		rhead_blk;
 	char			*offset;
 	xfs_buf_t		*hbp, *dbp;

@@ -5369,9 +5369,19 @@ xlog_do_recovery_pass(
 			bblks = (int)BTOBB(be32_to_cpu(rhead->h_len));
 			blk_no += hblks;
 
-			/* Read in data for log record */
-			if (blk_no + bblks <= log->l_logBBsize) {
-				error = xlog_bread(log, blk_no, bblks, dbp,
+			/*
+			 * Read the log record data in multiple reads if it
+			 * wraps around the end of the log. Note that if the
+			 * header already wrapped, blk_no could point past the
+			 * end of the log. The record data is contiguous in
+			 * that case.
+			 */
+			if (blk_no + bblks <= log->l_logBBsize ||
+			    blk_no >= log->l_logBBsize) {
+				/* mod blk_no in case the header wrapped and
+				 * pushed it beyond the end of the log */
+				rblk_no = do_mod(blk_no, log->l_logBBsize);
+				error = xlog_bread(log, rblk_no, bblks, dbp,
 						   &offset);
 				if (error)
 					goto bread_err2;

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brian Foster <[email protected]>

commit 5297ac1f6d7cbf45464a49b9558831f271dfc559 upstream.

Log tail verification currently only occurs when torn writes are detected at the head of the log. This was introduced because a change in the head block due to torn writes can lead to a change in the tail block (each log record header references the current tail) and the tail block should be verified before log recovery proceeds.

Tail corruption is possible outside of torn write scenarios, however. For example, partial log writes can be detected and cleared during the initial head/tail block discovery process. If the partial write coincides with a tail overwrite, the log tail is corrupted and recovery fails.

To facilitate correct handling of log tail overwites, update log recovery to always perform tail verification. This is necessary to detect potential tail overwrite conditions when torn writes may not have occurred. This changes normal (i.e., no torn writes) recovery behavior slightly to detect and return CRC related errors near the tail before actual recovery starts.

---
 fs/xfs/xfs_log_recover.c |   26 +++-----------------------
 1 file changed, 3 insertions(+), 23 deletions(-)

@@ -1183,31 +1183,11 @@ xlog_verify_head(
 			ASSERT(0);
 			return 0;
 		}
-
-		/*
-		 * Now verify the tail based on the updated head. This is
-		 * required because the torn writes trimmed from the head could
-		 * have been written over the tail of a previous record. Return
-		 * any errors since recovery cannot proceed if the tail is
-		 * corrupt.
-		 *
-		 * XXX: This leaves a gap in truly robust protection from torn
-		 * writes in the log. If the head is behind the tail, the tail
-		 * pushes forward to create some space and then a crash occurs
-		 * causing the writes into the previous record's tail region to
-		 * tear, log recovery isn't able to recover.
-		 *
-		 * How likely is this to occur? If possible, can we do something
-		 * more intelligent here? Is it safe to push the tail forward if
-		 * we can determine that the tail is within the range of the
-		 * torn write (e.g., the kernel can only overwrite the tail if
-		 * it has actually been pushed forward)? Alternatively, could we
-		 * somehow prevent this condition at runtime?
-		 */
-		error = xlog_verify_tail(log, *head_blk, *tail_blk);
 	}
+	if (error)
+		return error;
 
-	return error;
+	return xlog_verify_tail(log, *head_blk, *tail_blk);
 }
 
 /*

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Omar Sandoval <[email protected]>

commit c44245b3d5435f533ca8346ece65918f84c057f9 upstream.

When we try to allocate a free inode by searching the inobt, we try to find the inode nearest the parent inode by searching chunks both left and right of the chunk containing the parent. As an optimization, we cache the leftmost and rightmost records that we previously searched; if we do another allocation with the same parent inode, we'll pick up the search where it last left off.

There's a bug in the case where we found a free inode to the left of the parent's chunk: we need to update the cached left and right records, but because we already reassigned the right record to point to the left, we end up assigning the left record to both the cached left and right records.

This isn't a correctness problem strictly, but it can result in the next allocation rechecking chunks unnecessarily or allocating inodes further away from the parent than it needs to. Fix it by swapping the record pointer after we update the cached left and right records.

---
 fs/xfs/libxfs/xfs_ialloc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1236,13 +1236,13 @@ xfs_dialloc_ag_inobt(
 
 			/* free inodes to the left? */
 			if (useleft && trec.ir_freecount) {
-				rec = trec;
 				xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 				cur = tcur;
 
 				pag->pagl_leftrec = trec.ir_startino;
 				pag->pagl_rightrec = rec.ir_startino;
 				pag->pagl_pagino = pagino;
+				rec = trec;
 				goto alloc_inode;
 			}
 

4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: "Darrick J. Wong" <[email protected]>

commit 8204f8ddaafafcae074746fcf2a05a45e6827603 upstream.

Way back when we established inode block-map redo log items, it was discovered that we needed to prevent the VFS from evicting inodes during log recovery because any given inode might be have bmap redo items to replay even if the inode has no link count and is ultimately deleted, and any eviction of an unlinked inode causes the inode to be truncated and freed too early.

To make this possible, we set MS_ACTIVE so that inodes would not be torn down immediately upon release. Unfortunately, this also results in the quota inodes not being released at all if a later part of the mount process should fail, because we never reclaim the inodes. So, set MS_ACTIVE right before we do the last part of log recovery and clear it immediately after we finish the log recovery so that everything will be torn down properly if we abort the mount.

---
 fs/xfs/xfs_log.c   |   11 +++++++++++
 fs/xfs/xfs_mount.c |   10 ----------
 2 files changed, 11 insertions(+), 10 deletions(-)

@@ -749,9 +749,20 @@ xfs_log_mount_finish(
 		return 0;
 	}
 
+	/*
+	 * During the second phase of log recovery, we need iget and
+	 * iput to behave like they do for an active filesystem.
+	 * xfs_fs_drop_inode needs to be able to prevent the deletion
+	 * of inodes before we're done replaying log items on those
+	 * inodes.  Turn it off immediately after recovery finishes
+	 * so that we don't leak the quota inodes if subsequent mount
+	 * activities fail.
+	 */
+	mp->m_super->s_flags |= MS_ACTIVE;
 	error = xlog_recover_finish(mp->m_log);
 	if (!error)
 		xfs_log_work_queue(mp);
+	mp->m_super->s_flags &= ~MS_ACTIVE;
 
 	return error;
 }