4.17.3-stable review

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

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

From: Julian Anastasov <[email protected]>

[ Upstream commit 0975764684487bf3f7a47eef009e750ea41bd514 ]

IPVS setups with local client and remote tunnel server need to create exception for the local virtual IP. What we do is to change PMTU from 64KB (on "lo") to 1460 in the common case.

---
 net/ipv6/route.c |    3 ---
 1 file changed, 3 deletions(-)

@@ -2149,9 +2149,6 @@ static void __ip6_rt_update_pmtu(struct
 	const struct in6_addr *daddr, *saddr;
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
 
-	if (rt6->rt6i_flags & RTF_LOCAL)
-		return;
-
 	if (dst_metric_locked(dst, RTAX_MTU))
 		return;
 

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

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

From: Zhouyang Jia <[email protected]>

[ Upstream commit 349b71d6f427ff8211adf50839dbbff3f27c1805 ]

When pskb_trim_rcsum fails, the lack of error-handling code may cause unexpected results.

This patch adds error-handling code after calling pskb_trim_rcsum.

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

@@ -75,7 +75,8 @@ static struct sk_buff *trailer_rcv(struc
 	if (!skb->dev)
 		return NULL;
 
-	pskb_trim_rcsum(skb, skb->len - 4);
+	if (pskb_trim_rcsum(skb, skb->len - 4))
+		return NULL;
 
 	return skb;
 }

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

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

From: Frank van der Linden <[email protected]>

[ Upstream commit 4fd44a98ffe0d048246efef67ed640fdf2098a62 ]

commit 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") introduced an optimization for the handling of child sockets created for a new TCP connection.

But this optimization passes any data associated with the last ACK of the connection handshake up the stack without verifying its checksum, because it calls tcp_child_process(), which in turn calls tcp_rcv_state_process() directly. These lower-level processing functions do not do any checksum verification.

Insert a tcp_checksum_complete call in the TCP_NEW_SYN_RECEIVE path to fix this.

---
 net/ipv4/tcp_ipv4.c |    4 ++++
 net/ipv6/tcp_ipv6.c |    4 ++++
 2 files changed, 8 insertions(+)

@@ -1689,6 +1689,10 @@ process:
 			reqsk_put(req);
 			goto discard_it;
 		}
+		if (tcp_checksum_complete(skb)) {
+			reqsk_put(req);
+			goto csum_error;
+		}
 		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;

@@ -1475,6 +1475,10 @@ process:
 			reqsk_put(req);
 			goto discard_it;
 		}
+		if (tcp_checksum_complete(skb)) {
+			reqsk_put(req);
+			goto csum_error;
+		}
 		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;

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

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

From: Paolo Abeni <[email protected]>

[ Upstream commit 6c206b20092a3623184cff9470dba75d21507874 ]

After commit 6b229cf77d68 ("udp: add batching to udp_rmem_release()") the sk_rmem_alloc field does not measure exactly anymore the receive queue length, because we batch the rmem release. The issue is really apparent only after commit 0d4a6608f68c ("udp: do rmem bulk free even if the rx sk queue is empty"): the user space can easily check for an empty socket with not-0 queue length reported by the 'ss' tool or the procfs interface.

We need to use a custom UDP helper to report the correct queue length, taking into account the forward allocation deficit.

---
 include/net/transp_v6.h |   11 +++++++++--
 include/net/udp.h       |    5 +++++
 net/ipv4/udp.c          |    2 +-
 net/ipv4/udp_diag.c     |    2 +-
 net/ipv6/datagram.c     |    6 +++---
 net/ipv6/udp.c          |    3 ++-
 6 files changed, 21 insertions(+), 8 deletions(-)

@@ -45,8 +45,15 @@ int ip6_datagram_send_ctl(struct net *ne
 			  struct flowi6 *fl6, struct ipcm6_cookie *ipc6,
 			  struct sockcm_cookie *sockc);
 
-void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
-			     __u16 srcp, __u16 destp, int bucket);
+void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
+			       __u16 srcp, __u16 destp, int rqueue, int bucket);
+static inline void
+ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, __u16 srcp,
+			__u16 destp, int bucket)
+{
+	__ip6_dgram_sock_seq_show(seq, sp, srcp, destp, sk_rmem_alloc_get(sp),
+				  bucket);
+}
 
 #define LOOPBACK4_IPV6 cpu_to_be32(0x7f000006)
 

@@ -244,6 +244,11 @@ static inline __be16 udp_flow_src_port(s
 	return htons((((u64) hash * (max - min)) >> 32) + min);
 }
 
+static inline int udp_rqueue_get(struct sock *sk)
+{
+	return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit);
+}
+
 /* net/ipv4/udp.c */
 void udp_destruct_sock(struct sock *sk);
 void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);

@@ -2718,7 +2718,7 @@ static void udp4_format_sock(struct sock
 		" %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d",
 		bucket, src, srcp, dest, destp, sp->sk_state,
 		sk_wmem_alloc_get(sp),
-		sk_rmem_alloc_get(sp),
+		udp_rqueue_get(sp),
 		0, 0L, 0,
 		from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
 		0, sock_i_ino(sp),

@@ -163,7 +163,7 @@ static int udp_diag_dump_one(struct sk_b
 static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 		void *info)
 {
-	r->idiag_rqueue = sk_rmem_alloc_get(sk);
+	r->idiag_rqueue = udp_rqueue_get(sk);
 	r->idiag_wqueue = sk_wmem_alloc_get(sk);
 }
 

@@ -1019,8 +1019,8 @@ exit_f:
 }
 EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl);
 
-void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
-			     __u16 srcp, __u16 destp, int bucket)
+void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
+			       __u16 srcp, __u16 destp, int rqueue, int bucket)
 {
 	const struct in6_addr *dest, *src;
 

@@ -1036,7 +1036,7 @@ void ip6_dgram_sock_seq_show(struct seq_
 		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
 		   sp->sk_state,
 		   sk_wmem_alloc_get(sp),
-		   sk_rmem_alloc_get(sp),
+		   rqueue,
 		   0, 0L, 0,
 		   from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
 		   0,

@@ -1475,7 +1475,8 @@ int udp6_seq_show(struct seq_file *seq,
 		struct inet_sock *inet = inet_sk(v);
 		__u16 srcp = ntohs(inet->inet_sport);
 		__u16 destp = ntohs(inet->inet_dport);
-		ip6_dgram_sock_seq_show(seq, v, srcp, destp, bucket);
+		__ip6_dgram_sock_seq_show(seq, v, srcp, destp,
+					  udp_rqueue_get(v), bucket);
 	}
 	return 0;
 }

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

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

From: Willem de Bruijn <[email protected]>

[ Upstream commit fd3a88625844907151737fc3b4201676effa6d27 ]

Tun, tap, virtio, packet and uml vector all use struct virtio_net_hdr to communicate packet metadata to userspace.

For skbuffs with vlan, the first two return the packet as it may have existed on the wire, inserting the VLAN tag in the user buffer. Then virtio_net_hdr.csum_start needs to be adjusted by VLAN_HLEN bytes.

Commit f09e2249c4f5 ("macvtap: restore vlan header on user read") added this feature to macvtap. Commit 3ce9b20f1971 ("macvtap: Fix csum_start when VLAN tags are present") then fixed up csum_start.

Virtio, packet and uml do not insert the vlan header in the user buffer.

When introducing virtio_net_hdr_from_skb to deduplicate filling in the virtio_net_hdr, the variant from macvtap which adds VLAN_HLEN was applied uniformly, breaking csum offset for packets with vlan on virtio and packet.

Make insertion of VLAN_HLEN optional. Convert the callers to pass it when needed.

---
 arch/um/drivers/vector_transports.c |    3 ++-
 drivers/net/tap.c                   |    5 ++++-
 drivers/net/tun.c                   |    3 ++-
 drivers/net/virtio_net.c            |    3 ++-
 include/linux/virtio_net.h          |   11 ++++-------
 net/packet/af_packet.c              |    4 ++--
 6 files changed, 16 insertions(+), 13 deletions(-)

@@ -120,7 +120,8 @@ static int raw_form_header(uint8_t *head
 		skb,
 		vheader,
 		virtio_legacy_is_little_endian(),
-		false
+		false,
+		0
 	);
 
 	return 0;

@@ -774,13 +774,16 @@ static ssize_t tap_put_user(struct tap_q
 	int total;
 
 	if (q->flags & IFF_VNET_HDR) {
+		int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0;
 		struct virtio_net_hdr vnet_hdr;
+
 		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 		if (iov_iter_count(iter) < vnet_hdr_len)
 			return -EINVAL;
 
 		if (virtio_net_hdr_from_skb(skb, &vnet_hdr,
-					    tap_is_little_endian(q), true))
+					    tap_is_little_endian(q), true,
+					    vlan_hlen))
 			BUG();
 
 		if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=

@@ -2078,7 +2078,8 @@ static ssize_t tun_put_user(struct tun_s
 			return -EINVAL;
 
 		if (virtio_net_hdr_from_skb(skb, &gso,
-					    tun_is_little_endian(tun), true)) {
+					    tun_is_little_endian(tun), true,
+					    vlan_hlen)) {
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
 			pr_err("unexpected GSO type: "
 			       "0x%x, gso_size %d, hdr_len %d\n",

@@ -1358,7 +1358,8 @@ static int xmit_skb(struct send_queue *s
 		hdr = skb_vnet_hdr(skb);
 
 	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
-				    virtio_is_little_endian(vi->vdev), false))
+				    virtio_is_little_endian(vi->vdev), false,
+				    0))
 		BUG();
 
 	if (vi->mergeable_rx_bufs)

@@ -58,7 +58,8 @@ static inline int virtio_net_hdr_to_skb(
 static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 					  struct virtio_net_hdr *hdr,
 					  bool little_endian,
-					  bool has_data_valid)
+					  bool has_data_valid,
+					  int vlan_hlen)
 {
 	memset(hdr, 0, sizeof(*hdr));   /* no info leak */
 

@@ -83,12 +84,8 @@ static inline int virtio_net_hdr_from_sk
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		if (skb_vlan_tag_present(skb))
-			hdr->csum_start = __cpu_to_virtio16(little_endian,
-				skb_checksum_start_offset(skb) + VLAN_HLEN);
-		else
-			hdr->csum_start = __cpu_to_virtio16(little_endian,
-				skb_checksum_start_offset(skb));
+		hdr->csum_start = __cpu_to_virtio16(little_endian,
+			skb_checksum_start_offset(skb) + vlan_hlen);
 		hdr->csum_offset = __cpu_to_virtio16(little_endian,
 				skb->csum_offset);
 	} else if (has_data_valid &&

@@ -2037,7 +2037,7 @@ static int packet_rcv_vnet(struct msghdr
 		return -EINVAL;
 	*len -= sizeof(vnet_hdr);
 
-	if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le(), true))
+	if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le(), true, 0))
 		return -EINVAL;
 
 	return memcpy_to_msg(msg, (void *)&vnet_hdr, sizeof(vnet_hdr));

@@ -2304,7 +2304,7 @@ static int tpacket_rcv(struct sk_buff *s
 	if (do_vnet) {
 		if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
 					    sizeof(struct virtio_net_hdr),
-					    vio_le(), true)) {
+					    vio_le(), true, 0)) {
 			spin_lock(&sk->sk_receive_queue.lock);
 			goto drop_n_account;
 		}

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

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

From: Jan Kara <[email protected]>

commit 2ee3ee06a8fd792765fa3267ddf928997797eec5 upstream.

When ext4_ind_map_blocks() computes a length of a hole, it doesn't count with the fact that mapped offset may be somewhere in the middle of the completely empty subtree. In such case it will return too large length of the hole which then results in lseek(SEEK_DATA) to end up returning an incorrect offset beyond the end of the hole.

Fix the problem by correctly taking offset within a subtree into account when computing a length of a hole.

---
 fs/ext4/indirect.c |   14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

@@ -561,10 +561,16 @@ int ext4_ind_map_blocks(handle_t *handle
 		unsigned epb = inode->i_sb->s_blocksize / sizeof(u32);
 		int i;
 
-		/* Count number blocks in a subtree under 'partial' */
-		count = 1;
-		for (i = 0; partial + i != chain + depth - 1; i++)
-			count *= epb;
+		/*
+		 * Count number blocks in a subtree under 'partial'. At each
+		 * level we count number of complete empty subtrees beyond
+		 * current offset and then descend into the subtree only
+		 * partially beyond current offset.
+		 */
+		count = 0;
+		for (i = partial - chain + 1; i < depth; i++)
+			count = count * epb + (epb - offsets[i] - 1);
+		count++;
 		/* Fill in size of a hole we found */
 		map->m_pblk = 0;
 		map->m_len = min_t(unsigned int, map->m_len, count);

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

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

From: Theodore Ts'o <[email protected]>

commit eb9b5f01c33adebc31cbc236c02695f605b0e417 upstream.

If ext4_find_inline_data_nolock() returns an error it needs to get reflected up to ext4_iget(). In order to fix this, ext4_iget_extra_inode() needs to return an error (and not return void).

This is related to "ext4: do not allow external inodes for inline data" (which fixes CVE-2018-11412) in that in the errors=continue case, it would be useful to for userspace to receive an error indicating that file system is corrupted.

---
 fs/ext4/inode.c |   10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

@@ -4701,19 +4701,21 @@ static blkcnt_t ext4_inode_blocks(struct
 	}
 }
 
-static inline void ext4_iget_extra_inode(struct inode *inode,
+static inline int ext4_iget_extra_inode(struct inode *inode,
 					 struct ext4_inode *raw_inode,
 					 struct ext4_inode_info *ei)
 {
 	__le32 *magic = (void *)raw_inode +
 			EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize;
+
 	if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <=
 	    EXT4_INODE_SIZE(inode->i_sb) &&
 	    *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
 		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
-		ext4_find_inline_data_nolock(inode);
+		return ext4_find_inline_data_nolock(inode);
 	} else
 		EXT4_I(inode)->i_inline_off = 0;
+	return 0;
 }
 
 int ext4_get_projid(struct inode *inode, kprojid_t *projid)

@@ -4893,7 +4895,9 @@ struct inode *ext4_iget(struct super_blo
 			ei->i_extra_isize = sizeof(struct ext4_inode) -
 					    EXT4_GOOD_OLD_INODE_SIZE;
 		} else {
-			ext4_iget_extra_inode(inode, raw_inode, ei);
+			ret = ext4_iget_extra_inode(inode, raw_inode, ei);
+			if (ret)
+				goto bad_inode;
 		}
 	}
 

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

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

From: Takashi Iwai <[email protected]>

commit f16041df4c360eccacfe90f96673b37829e4c959 upstream.

HP Z2 G4 requires the same workaround as other HP machines that have no mic-pin detection.

---
 sound/pci/hda/patch_conexant.c |    1 +
 1 file changed, 1 insertion(+)

@@ -965,6 +965,7 @@ static const struct snd_pci_quirk cxt506
 	SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
 	SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),

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

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

From: Dennis Wassenberg <[email protected]>

commit 2861751f67b91e1d24e68010ced96614fb3140f4 upstream.

This patch adds missing initialisation for HP 2013 UltraSlim Dock Line-In/Out PINs and activates keyboard mute/micmute leds for HP EliteBook 830 G5

---
 sound/pci/hda/patch_conexant.c |    1 +
 1 file changed, 1 insertion(+)

@@ -959,6 +959,7 @@ static const struct snd_pci_quirk cxt506
 	SND_PCI_QUIRK(0x103c, 0x8079, "HP EliteBook 840 G3", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x807C, "HP EliteBook 820 G3", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x80FD, "HP ProBook 640 G2", CXT_FIXUP_HP_DOCK),
+	SND_PCI_QUIRK(0x103c, 0x83b3, "HP EliteBook 830 G5", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE),
 	SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
 	SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO),

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

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

From: Tony Luck <[email protected]>

commit 985c78d3ff8e9c74450fa2bb08eb55e680d999ca upstream.

Each of the strings that we want to put into the buf[MAX_FLAG_OPT_SIZE] in flags_read() is two characters long. But the sprintf() adds a trailing newline and will add a terminating NUL byte. So MAX_FLAG_OPT_SIZE needs to be 4.

sprintf() calls vsnprintf() and *that* does return:

" * The return value is the number of characters which would
* be generated for the given input, excluding the trailing
* '\0', as per ISO C99."

Note the "excluding".

---
 arch/x86/kernel/cpu/mcheck/mce-inject.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--
To unsubscribe from this list: send the line "unsubscribe linux-edac" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

@@ -48,7 +48,7 @@ static struct dentry *dfs_inj;
 
 static u8 n_banks;
 
-#define MAX_FLAG_OPT_SIZE	3
+#define MAX_FLAG_OPT_SIZE	4
 #define NBCFG			0x44
 
 enum injection_type {

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

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

From: Mark Syms <[email protected]>

commit d81243c697ffc71f983736e7da2db31a8be0001f upstream.

Handle this additional status in the same way as SESSION_EXPIRED.

---
 fs/cifs/smb2ops.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

@@ -1277,10 +1277,11 @@ smb2_is_session_expired(char *buf)
 {
 	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
 
-	if (shdr->Status != STATUS_NETWORK_SESSION_EXPIRED)
+	if (shdr->Status != STATUS_NETWORK_SESSION_EXPIRED &&
+	    shdr->Status != STATUS_USER_SESSION_DELETED)
 		return false;
 
-	cifs_dbg(FYI, "Session expired\n");
+	cifs_dbg(FYI, "Session expired or deleted\n");
 	return true;
 }
 

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

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

From: Josef Bacik <[email protected]>

commit 9e2b19675d1338d2a38e99194756f2db44a081df upstream.

When we stopped relying on the bdev everywhere I broke updating the block device size on the fly, which ceph relies on. We can't just do set_capacity, we also have to do bd_set_size so things like parted will notice the device size change.

---
 drivers/block/nbd.c |   10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

@@ -234,9 +234,18 @@ static void nbd_size_clear(struct nbd_de
 static void nbd_size_update(struct nbd_device *nbd)
 {
 	struct nbd_config *config = nbd->config;
+	struct block_device *bdev = bdget_disk(nbd->disk, 0);
+
 	blk_queue_logical_block_size(nbd->disk->queue, config->blksize);
 	blk_queue_physical_block_size(nbd->disk->queue, config->blksize);
 	set_capacity(nbd->disk, config->bytesize >> 9);
+	if (bdev) {
+		if (bdev->bd_disk)
+			bd_set_size(bdev, config->bytesize);
+		else
+			bdev->bd_invalidated = 1;
+		bdput(bdev);
+	}
 	kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
 }
 

@@ -1114,7 +1123,6 @@ static int nbd_start_device_ioctl(struct
 	if (ret)
 		return ret;
 
-	bd_set_size(bdev, config->bytesize);
 	if (max_part)
 		bdev->bd_invalidated = 1;
 	mutex_unlock(&nbd->config_lock);

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

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

From: Roman Pen <[email protected]>

commit a347c7ad8edf4c5685154f3fdc3c12fc1db800ba upstream.

It is not allowed to reinit q->tag_set_list list entry while RCU grace period has not completed yet, otherwise the following soft lockup in blk_mq_sched_restart() happens:

[ 1064.252652] watchdog: BUG: soft lockup - CPU#12 stuck for 23s! [fio:9270]
[ 1064.254445] task: ffff99b912e8b900 task.stack: ffffa6d54c758000
[ 1064.254613] RIP: 0010:blk_mq_sched_restart+0x96/0x150
[ 1064.256510] Call Trace:
[ 1064.256664]  <IRQ>
[ 1064.256824]  blk_mq_free_request+0xea/0x100
[ 1064.256987]  msg_io_conf+0x59/0xd0 [ibnbd_client]
[ 1064.257175]  complete_rdma_req+0xf2/0x230 [ibtrs_client]
[ 1064.257340]  ? ibtrs_post_recv_empty+0x4d/0x70 [ibtrs_core]
[ 1064.257502]  ibtrs_clt_rdma_done+0xd1/0x1e0 [ibtrs_client]
[ 1064.257669]  ib_create_qp+0x321/0x380 [ib_core]
[ 1064.257841]  ib_process_cq_direct+0xbd/0x120 [ib_core]
[ 1064.258007]  irq_poll_softirq+0xb7/0xe0
[ 1064.258165]  __do_softirq+0x106/0x2a2
[ 1064.258328]  irq_exit+0x92/0xa0
[ 1064.258509]  do_IRQ+0x4a/0xd0
[ 1064.258660]  common_interrupt+0x7a/0x7a
[ 1064.258818]  </IRQ>

Meanwhile another context frees other queue but with the same set of shared tags:

[ 1288.201183] INFO: task bash:5910 blocked for more than 180 seconds.
[ 1288.201833] bash            D    0  5910   5820 0x00000000
[ 1288.202016] Call Trace:
[ 1288.202315]  schedule+0x32/0x80
[ 1288.202462]  schedule_timeout+0x1e5/0x380
[ 1288.203838]  wait_for_completion+0xb0/0x120
[ 1288.204137]  __wait_rcu_gp+0x125/0x160
[ 1288.204287]  synchronize_sched+0x6e/0x80
[ 1288.204770]  blk_mq_free_queue+0x74/0xe0
[ 1288.204922]  blk_cleanup_queue+0xc7/0x110
[ 1288.205073]  ibnbd_clt_unmap_device+0x1bc/0x280 [ibnbd_client]
[ 1288.205389]  ibnbd_clt_unmap_dev_store+0x169/0x1f0 [ibnbd_client]
[ 1288.205548]  kernfs_fop_write+0x109/0x180
[ 1288.206328]  vfs_write+0xb3/0x1a0
[ 1288.206476]  SyS_write+0x52/0xc0
[ 1288.206624]  do_syscall_64+0x68/0x1d0
[ 1288.206774]  entry_SYSCALL_64_after_hwframe+0x3d/0xa2

What happened is the following:

1. There are several MQ queues with shared tags.
2. One queue is about to be freed and now task is in blk_mq_del_queue_tag_set().
3. Other CPU is in blk_mq_sched_restart() and loops over all queues in tag list in order to find hctx to restart.

Because linked list entry was modified in blk_mq_del_queue_tag_set() without proper waiting for a grace period, blk_mq_sched_restart() never ends, spining in list_for_each_entry_rcu_rr(), thus soft lockup.

Fix is simple: reinit list entry after an RCU grace period elapsed.

---
 block/blk-mq.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -2473,7 +2473,6 @@ static void blk_mq_del_queue_tag_set(str
 
 	mutex_lock(&set->tag_list_lock);
 	list_del_rcu(&q->tag_set_list);
-	INIT_LIST_HEAD(&q->tag_set_list);
 	if (list_is_singular(&set->tag_list)) {
 		/* just transitioned to unshared */
 		set->flags &= ~BLK_MQ_F_TAG_SHARED;

@@ -2481,8 +2480,8 @@ static void blk_mq_del_queue_tag_set(str
 		blk_mq_update_tag_set_depth(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
-
 	synchronize_rcu();
+	INIT_LIST_HEAD(&q->tag_set_list);
 }
 
 static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,

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

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

From: Tejun Heo <[email protected]>

commit f183464684190bacbfb14623bd3e4e51b7575b4c upstream.

From: Tejun Heo <[email protected]>
Date: Wed, 23 May 2018 10:29:00 -0700

cgwb_release() punts the actual release to cgwb_release_workfn() on system_wq. Depending on the number of cgroups or block devices, there can be a lot of cgwb_release_workfn() in flight at the same time.

We're periodically seeing close to 256 kworkers getting stuck with the following stack trace and overtime the entire system gets stuck.

  [<ffffffff810ee40c>] _synchronize_rcu_expedited.constprop.72+0x2fc/0x330
  [<ffffffff810ee634>] synchronize_rcu_expedited+0x24/0x30
  [<ffffffff811ccf23>] bdi_unregister+0x53/0x290
  [<ffffffff811cd1e9>] release_bdi+0x89/0xc0
  [<ffffffff811cd645>] wb_exit+0x85/0xa0
  [<ffffffff811cdc84>] cgwb_release_workfn+0x54/0xb0
  [<ffffffff810a68d0>] process_one_work+0x150/0x410
  [<ffffffff810a71fd>] worker_thread+0x6d/0x520
  [<ffffffff810ad3dc>] kthread+0x12c/0x160
  [<ffffffff81969019>] ret_from_fork+0x29/0x40
  [<ffffffffffffffff>] 0xffffffffffffffff

The events leading to the lockup are...

1. A lot of cgwb_release_workfn() is queued at the same time and all system_wq kworkers are assigned to execute them.

2. They all end up calling synchronize_rcu_expedited(). One of them wins and tries to perform the expedited synchronization.

3. However, that invovles queueing rcu_exp_work to system_wq and waiting for it. Because #1 is holding all available kworkers on system_wq, rcu_exp_work can't be executed. cgwb_release_workfn() is waiting for synchronize_rcu_expedited() which in turn is waiting for cgwb_release_workfn() to free up some of the kworkers.

We shouldn't be scheduling hundreds of cgwb_release_workfn() at the same time. There's nothing to be gained from that. This patch updates cgwb release path to use a dedicated percpu workqueue with @max_active of 1.

While this resolves the problem at hand, it might be a good idea to isolate rcu_exp_work to its own workqueue too as it can be used from various paths and is prone to this sort of indirect A-A deadlocks.

---
 mm/backing-dev.c |   18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

@@ -412,6 +412,7 @@ static void wb_exit(struct bdi_writeback
  * protected.
  */
 static DEFINE_SPINLOCK(cgwb_lock);
+static struct workqueue_struct *cgwb_release_wq;
 
 /**
  * wb_congested_get_create - get or create a wb_congested

@@ -522,7 +523,7 @@ static void cgwb_release(struct percpu_r
 {
 	struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback,
 						refcnt);
-	schedule_work(&wb->release_work);
+	queue_work(cgwb_release_wq, &wb->release_work);
 }
 
 static void cgwb_kill(struct bdi_writeback *wb)

@@ -784,6 +785,21 @@ static void cgwb_bdi_register(struct bac
 	spin_unlock_irq(&cgwb_lock);
 }
 
+static int __init cgwb_init(void)
+{
+	/*
+	 * There can be many concurrent release work items overwhelming
+	 * system_wq.  Put them in a separate wq and limit concurrency.
+	 * There's no point in executing many of these in parallel.
+	 */
+	cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1);
+	if (!cgwb_release_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+subsys_initcall(cgwb_init);
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static int cgwb_bdi_init(struct backing_dev_info *bdi)

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

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

From: Suman Anna <[email protected]>

commit e5d295b06d69a1924665a16a4987be475addd00f upstream.

Commit 05829d9431df (cpufreq: ti-cpufreq: kfree opp_data when failure) has fixed a memory leak in the failure path, however the patch returned a positive value on get_cpu_device() failure instead of the previous negative value. Fix this incorrect error return value properly.

---
 drivers/cpufreq/ti-cpufreq.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -226,7 +226,7 @@ static int ti_cpufreq_probe(struct platf
 	opp_data->cpu_dev = get_cpu_device(0);
 	if (!opp_data->cpu_dev) {
 		pr_err("%s: Failed to get device for CPU0\n", __func__);
-		ret = ENODEV;
+		ret = -ENODEV;
 		goto free_opp_data;
 	}
 

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

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

From: Hans de Goede <[email protected]>

commit 2cfce3a86b64b53f0a70e92a6a659c720c319b45 upstream.

Commit 184add2ca23c ("libata: Apply NOLPM quirk for SanDisk SD7UB3Q*G1001 SSDs") disabled LPM for SanDisk SD7UB3Q*G1001 SSDs.

This has lead to several reports of users of that SSD where LPM was working fine and who know have a significantly increased idle power consumption on their laptops.

Likely there is another problem on the T450s from the original reporter which gets exposed by the uncore reaching deeper sleep states (higher PC-states) due to LPM being enabled. The problem as reported, a hardfreeze about once a day, already did not sound like it would be caused by LPM and the reports of the SSD working fine confirm this. The original reporter is ok with dropping the quirk.

A X250 user has reported the same hard freeze problem and for him the problem went away after unrelated updates, I suspect some GPU driver stack changes fixed things.

TL;DR: The original reporters problem were triggered by LPM but not an LPM issue, so drop the quirk for the SSD in question.

---
 drivers/ata/libata-core.c |    3 ---
 1 file changed, 3 deletions(-)

@@ -4557,9 +4557,6 @@ static const struct ata_blacklist_entry
 	{ "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, },
 	{ "SAMSUNG SSD PM830 mSATA *",  "CXM13D1Q", ATA_HORKAGE_NOLPM, },
 
-	/* Sandisk devices which are known to not handle LPM well */
-	{ "SanDisk SD7UB3Q*G1001",	NULL,	ATA_HORKAGE_NOLPM, },
-
 	/* devices that don't properly handle queued TRIM commands */
 	{ "Micron_M500IT_*",		"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },

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

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

From: Stefan Potyra <[email protected]>

commit 955bc61328dc0a297fb3baccd84e9d3aee501ed8 upstream.

According to the API, you may only call clk_get_rate() after actually enabling it.

Found by Linux Driver Verification project (linuxtesting.org).

---
 drivers/w1/masters/mxc_w1.c |   20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

@@ -112,6 +112,10 @@ static int mxc_w1_probe(struct platform_
 	if (IS_ERR(mdev->clk))
 		return PTR_ERR(mdev->clk);
 
+	err = clk_prepare_enable(mdev->clk);
+	if (err)
+		return err;
+
 	clkrate = clk_get_rate(mdev->clk);
 	if (clkrate < 10000000)
 		dev_warn(&pdev->dev,

@@ -125,12 +129,10 @@ static int mxc_w1_probe(struct platform_
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	mdev->regs = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(mdev->regs))
-		return PTR_ERR(mdev->regs);
-
-	err = clk_prepare_enable(mdev->clk);
-	if (err)
-		return err;
+	if (IS_ERR(mdev->regs)) {
+		err = PTR_ERR(mdev->regs);
+		goto out_disable_clk;
+	}
 
 	/* Software reset 1-Wire module */
 	writeb(MXC_W1_RESET_RST, mdev->regs + MXC_W1_RESET);

@@ -146,8 +148,12 @@ static int mxc_w1_probe(struct platform_
 
 	err = w1_add_master_device(&mdev->bus_master);
 	if (err)
-		clk_disable_unprepare(mdev->clk);
+		goto out_disable_clk;
+
+	return 0;
 
+out_disable_clk:
+	clk_disable_unprepare(mdev->clk);
 	return err;
 }
 

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

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

From: Thomas Gleixner <[email protected]>

commit 839b0f1c4ef674cd929a42304c078afca278581a upstream.

To address the EBUSY fail of interrupt affinity settings in case that the previous setting has not been cleaned up yet, use the new apic_ack_irq() function instead of the special uv_ack_apic() implementation which is merily a wrapper around ack_APIC_irq().

Preparatory change for the real fix

---
 arch/x86/platform/uv/uv_irq.c |    7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

@@ -47,11 +47,6 @@ static void uv_program_mmr(struct irq_cf
 
 static void uv_noop(struct irq_data *data) { }
 
-static void uv_ack_apic(struct irq_data *data)
-{
-	ack_APIC_irq();
-}
-
 static int
 uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
 		    bool force)

@@ -73,7 +68,7 @@ static struct irq_chip uv_irq_chip = {
 	.name			= "UV-CORE",
 	.irq_mask		= uv_noop,
 	.irq_unmask		= uv_noop,
-	.irq_eoi		= uv_ack_apic,
+	.irq_eoi		= apic_ack_irq,
 	.irq_set_affinity	= uv_set_irq_affinity,
 };
 

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

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

From: Thomas Gleixner <[email protected]>

commit 8a2b7d142e7ac477d52f5f92251e59fc136d7ddd upstream.

To address the EBUSY fail of interrupt affinity settings in case that the previous setting has not been cleaned up yet, use the new apic_ack_irq() function instead of the special ir_ack_apic_edge() implementation which is merily a wrapper around ack_APIC_irq().

Preparatory change for the real fix

---
 drivers/iommu/amd_iommu.c           |    2 +-
 drivers/iommu/intel_irq_remapping.c |    2 +-
 drivers/iommu/irq_remapping.c       |    5 -----
 drivers/iommu/irq_remapping.h       |    2 --
 4 files changed, 2 insertions(+), 9 deletions(-)

@@ -4379,7 +4379,7 @@ static void ir_compose_msi_msg(struct ir
 
 static struct irq_chip amd_ir_chip = {
 	.name			= "AMD-IR",
-	.irq_ack		= ir_ack_apic_edge,
+	.irq_ack		= apic_ack_irq,
 	.irq_set_affinity	= amd_ir_set_affinity,
 	.irq_set_vcpu_affinity	= amd_ir_set_vcpu_affinity,
 	.irq_compose_msi_msg	= ir_compose_msi_msg,

@@ -1223,7 +1223,7 @@ static int intel_ir_set_vcpu_affinity(st
 
 static struct irq_chip intel_ir_chip = {
 	.name			= "INTEL-IR",
-	.irq_ack		= ir_ack_apic_edge,
+	.irq_ack		= apic_ack_irq,
 	.irq_set_affinity	= intel_ir_set_affinity,
 	.irq_compose_msi_msg	= intel_ir_compose_msi_msg,
 	.irq_set_vcpu_affinity	= intel_ir_set_vcpu_affinity,

@@ -156,11 +156,6 @@ void panic_if_irq_remap(const char *msg)
 		panic(msg);
 }
 
-void ir_ack_apic_edge(struct irq_data *data)
-{
-	ack_APIC_irq();
-}
-
 /**
  * irq_remapping_get_ir_irq_domain - Get the irqdomain associated with the IOMMU
  *				     device serving request @info

@@ -65,8 +65,6 @@ struct irq_remap_ops {
 extern struct irq_remap_ops intel_irq_remap_ops;
 extern struct irq_remap_ops amd_iommu_irq_ops;
 
-extern void ir_ack_apic_edge(struct irq_data *data);
-
 #else  /* CONFIG_IRQ_REMAP */
 
 #define irq_remapping_enabled 0

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

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

From: Thomas Gleixner <[email protected]>

commit d340ebd696f921d3ad01b8c0c29dd38f2ad2bf3e upstream.

The upcoming fix for the -EBUSY return from affinity settings requires to use the irq_move_irq() functionality even on irq remapped interrupts. To avoid the out of line call, move the check for the pending bit into an inline helper.

Preparatory change for the real fix. No functional change.

---
 include/linux/irq.h    |    7 ++++++-
 kernel/irq/migration.c |    5 +----
 2 files changed, 7 insertions(+), 5 deletions(-)

@@ -551,7 +551,12 @@ extern int irq_affinity_online_cpu(unsig
 #endif
 
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
-void irq_move_irq(struct irq_data *data);
+void __irq_move_irq(struct irq_data *data);
+static inline void irq_move_irq(struct irq_data *data)
+{
+	if (unlikely(irqd_is_setaffinity_pending(data)))
+		__irq_move_irq(data);
+}
 void irq_move_masked_irq(struct irq_data *data);
 void irq_force_complete_move(struct irq_desc *desc);
 #else

@@ -91,7 +91,7 @@ void irq_move_masked_irq(struct irq_data
 	cpumask_clear(desc->pending_mask);
 }
 
-void irq_move_irq(struct irq_data *idata)
+void __irq_move_irq(struct irq_data *idata)
 {
 	bool masked;
 

@@ -102,9 +102,6 @@ void irq_move_irq(struct irq_data *idata
 	 */
 	idata = irq_desc_get_irq_data(irq_data_to_desc(idata));
 
-	if (likely(!irqd_is_setaffinity_pending(idata)))
-		return;
-
 	if (unlikely(irqd_irq_disabled(idata)))
 		return;
 

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

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

From: Tony Luck <[email protected]>

commit 1d9f3e20a56d33e55748552aeec597f58542f92d upstream.

New stepping of Skylake has fixes for cache occupancy and memory bandwidth monitoring.

Update the code to enable these by default on newer steppings.

---
 arch/x86/kernel/cpu/intel_rdt.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -821,6 +821,8 @@ static __init void rdt_quirks(void)
 	case INTEL_FAM6_SKYLAKE_X:
 		if (boot_cpu_data.x86_stepping <= 4)
 			set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat");
+		else
+			set_rdt_options("!l3cat");
 	}
 }
 

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

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

From: Luca Coelho <[email protected]>

commit 9039d985811d5b109b58b202b7594fd24e433fed upstream.

The page loading code trusts the data provided in the firmware images a bit too much and may cause a buffer overflow or copy unknown data if the block sizes don't match what we expect.

To prevent potential problems, harden the code by checking if the sizes we are copying are what we expect.

---
 drivers/net/wireless/intel/iwlwifi/fw/paging.c |   49 ++++++++++++++++++++-----
 1 file changed, 41 insertions(+), 8 deletions(-)

@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018        Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as

@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018        Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without

@@ -163,7 +165,7 @@ static int iwl_alloc_fw_paging_mem(struc
 static int iwl_fill_paging_mem(struct iwl_fw_runtime *fwrt,
 			       const struct fw_img *image)
 {
-	int sec_idx, idx;
+	int sec_idx, idx, ret;
 	u32 offset = 0;
 
 	/*

@@ -190,17 +192,23 @@ static int iwl_fill_paging_mem(struct iw
 	 */
 	if (sec_idx >= image->num_sec - 1) {
 		IWL_ERR(fwrt, "Paging: Missing CSS and/or paging sections\n");
-		iwl_free_fw_paging(fwrt);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err;
 	}
 
 	/* copy the CSS block to the dram */
 	IWL_DEBUG_FW(fwrt, "Paging: load paging CSS to FW, sec = %d\n",
 		     sec_idx);
 
+	if (image->sec[sec_idx].len > fwrt->fw_paging_db[0].fw_paging_size) {
+		IWL_ERR(fwrt, "CSS block is larger than paging size\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
 	memcpy(page_address(fwrt->fw_paging_db[0].fw_paging_block),
 	       image->sec[sec_idx].data,
-	       fwrt->fw_paging_db[0].fw_paging_size);
+	       image->sec[sec_idx].len);
 	dma_sync_single_for_device(fwrt->trans->dev,
 				   fwrt->fw_paging_db[0].fw_paging_phys,
 				   fwrt->fw_paging_db[0].fw_paging_size,

@@ -221,6 +229,14 @@ static int iwl_fill_paging_mem(struct iw
 	for (idx = 1; idx < fwrt->num_of_paging_blk; idx++) {
 		struct iwl_fw_paging *block = &fwrt->fw_paging_db[idx];
 
+		if (block->fw_paging_size > image->sec[sec_idx].len - offset) {
+			IWL_ERR(fwrt,
+				"Paging: paging size is larger than remaining data in block %d\n",
+				idx);
+			ret = -EINVAL;
+			goto err;
+		}
+
 		memcpy(page_address(block->fw_paging_block),
 		       image->sec[sec_idx].data + offset,
 		       block->fw_paging_size);

@@ -231,19 +247,32 @@ static int iwl_fill_paging_mem(struct iw
 
 		IWL_DEBUG_FW(fwrt,
 			     "Paging: copied %d paging bytes to block %d\n",
-			     fwrt->fw_paging_db[idx].fw_paging_size,
-			     idx);
+			     block->fw_paging_size, idx);
+
+		offset += block->fw_paging_size;
 
-		offset += fwrt->fw_paging_db[idx].fw_paging_size;
+		if (offset > image->sec[sec_idx].len) {
+			IWL_ERR(fwrt,
+				"Paging: offset goes over section size\n");
+			ret = -EINVAL;
+			goto err;
+		}
 	}
 
 	/* copy the last paging block */
 	if (fwrt->num_of_pages_in_last_blk > 0) {
 		struct iwl_fw_paging *block = &fwrt->fw_paging_db[idx];
 
+		if (image->sec[sec_idx].len - offset > block->fw_paging_size) {
+			IWL_ERR(fwrt,
+				"Paging: last block is larger than paging size\n");
+			ret = -EINVAL;
+			goto err;
+		}
+
 		memcpy(page_address(block->fw_paging_block),
 		       image->sec[sec_idx].data + offset,
-		       FW_PAGING_SIZE * fwrt->num_of_pages_in_last_blk);
+		       image->sec[sec_idx].len - offset);
 		dma_sync_single_for_device(fwrt->trans->dev,
 					   block->fw_paging_phys,
 					   block->fw_paging_size,

@@ -255,6 +284,10 @@ static int iwl_fill_paging_mem(struct iw
 	}
 
 	return 0;
+
+err:
+	iwl_free_fw_paging(fwrt);
+	return ret;
 }
 
 static int iwl_save_fw_paging(struct iwl_fw_runtime *fwrt,

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

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

From: Thadeu Lima de Souza Cascardo <[email protected]>

commit 5cc41e099504b77014358b58567c5ea6293dd220 upstream.

WHen registering a new binfmt_misc handler, it is possible to overflow the offset to get a negative value, which might crash the system, or possibly leak kernel data.

Here is a crash log when 2500000000 was used as an offset:

  BUG: unable to handle kernel paging request at ffff989cfd6edca0
  IP: load_misc_binary+0x22b/0x470 [binfmt_misc]
  PGD 1ef3e067 P4D 1ef3e067 PUD 0
  Oops: 0000 [#1] SMP NOPTI
  Modules linked in: binfmt_misc kvm_intel ppdev kvm irqbypass joydev input_leds serio_raw mac_hid parport_pc qemu_fw_cfg parpy
  CPU: 0 PID: 2499 Comm: bash Not tainted 4.15.0-22-generic #24-Ubuntu
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.1-1 04/01/2014
  RIP: 0010:load_misc_binary+0x22b/0x470 [binfmt_misc]
  Call Trace:
    search_binary_handler+0x97/0x1d0
    do_execveat_common.isra.34+0x667/0x810
    SyS_execve+0x31/0x40
    do_syscall_64+0x73/0x130
    entry_SYSCALL_64_after_hwframe+0x3d/0xa2

Use kstrtoint instead of simple_strtoul. It will work as the code already set the delimiter byte to '\0' and we only do it when the field is not empty.

Tested with offsets -1, 2500000000, UINT_MAX and INT_MAX. Also tested with examples documented at Documentation/admin-guide/binfmt-misc.rst and other registrations from packages on Ubuntu.

---
 fs/binfmt_misc.c |   12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

@@ -387,8 +387,13 @@ static Node *create_entry(const char __u
 		s = strchr(p, del);
 		if (!s)
 			goto einval;
-		*s++ = '\0';
-		e->offset = simple_strtoul(p, &p, 10);
+		*s = '\0';
+		if (p != s) {
+			int r = kstrtoint(p, 10, &e->offset);
+			if (r != 0 || e->offset < 0)
+				goto einval;
+		}
+		p = s;
 		if (*p++)
 			goto einval;
 		pr_debug("register: offset: %#x\n", e->offset);

@@ -428,7 +433,8 @@ static Node *create_entry(const char __u
 		if (e->mask &&
 		    string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size)
 			goto einval;
-		if (e->size + e->offset > BINPRM_BUF_SIZE)
+		if (e->size > BINPRM_BUF_SIZE ||
+		    BINPRM_BUF_SIZE - e->size < e->offset)
 			goto einval;
 		pr_debug("register: magic/mask length: %i\n", e->size);
 		if (USE_DEBUG) {

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

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

From: Daniel Borkmann <[email protected]>

[ Upstream commit 06030dbaf3b6c5801dcdb7fe4fbab3b91c8da84a ]

Current behavior in tls_sw_recvmsg() is to wait for incoming tls messages and copy up to exactly len bytes of data that the user provided. This is problematic in the sense that i) if no packet is currently queued in strparser we keep waiting until one has been processed and pushed into tls receive layer for tls_wait_data() to wake up and push the decrypted bits to user space. Given after tls decryption, we're back at streaming data, use sock_rcvlowat() hint from tcp socket instead. Retain current behavior with MSG_WAITALL flag and otherwise use the hint target for breaking the loop and returning to application. This is done if currently no ctx->recv_pkt is ready, otherwise continue to process it from our strparser backlog.

---
 net/tls/tls_sw.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -755,7 +755,7 @@ int tls_sw_recvmsg(struct sock *sk,
 	struct sk_buff *skb;
 	ssize_t copied = 0;
 	bool cmsg = false;
-	int err = 0;
+	int target, err = 0;
 	long timeo;
 
 	flags |= nonblock;

@@ -765,6 +765,7 @@ int tls_sw_recvmsg(struct sock *sk,
 
 	lock_sock(sk);
 
+	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
 	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 	do {
 		bool zc = false;

@@ -857,6 +858,9 @@ fallback_to_reg_recv:
 					goto recv_end;
 			}
 		}
+		/* If we have a new message from strparser, continue now. */
+		if (copied >= target && !ctx->recv_pkt)
+			break;
 	} while (len);
 
 recv_end:

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

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

From: Cong Wang <[email protected]>

[ Upstream commit 6d8c50dcb029872b298eea68cc6209c866fd3e14 ]

fchownat() doesn't even hold refcnt of fd until it figures out fd is really needed (otherwise is ignored) and releases it after it resolves the path. This means sock_close() could race with sockfs_setattr(), which leads to a NULL pointer dereference since typically we set sock->sk to NULL in ->release().

As pointed out by Al, this is unique to sockfs. So we can fix this in socket layer by acquiring inode_lock in sock_close() and checking against NULL in sockfs_setattr().

sock_release() is called in many places, only the sock_close() path matters here. And fortunately, this should not affect normal sock_close() as it is only called when the last fd refcnt is gone. It only affects sock_close() with a parallel sockfs_setattr() in progress, which is not common.

---
 net/socket.c |   18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

@@ -537,7 +537,10 @@ static int sockfs_setattr(struct dentry
 	if (!err && (iattr->ia_valid & ATTR_UID)) {
 		struct socket *sock = SOCKET_I(d_inode(dentry));
 
-		sock->sk->sk_uid = iattr->ia_uid;
+		if (sock->sk)
+			sock->sk->sk_uid = iattr->ia_uid;
+		else
+			err = -ENOENT;
 	}
 
 	return err;

@@ -586,12 +589,16 @@ EXPORT_SYMBOL(sock_alloc);
  *	an inode not a file.
  */
 
-void sock_release(struct socket *sock)
+static void __sock_release(struct socket *sock, struct inode *inode)
 {
 	if (sock->ops) {
 		struct module *owner = sock->ops->owner;
 
+		if (inode)
+			inode_lock(inode);
 		sock->ops->release(sock);
+		if (inode)
+			inode_unlock(inode);
 		sock->ops = NULL;
 		module_put(owner);
 	}

@@ -605,6 +612,11 @@ void sock_release(struct socket *sock)
 	}
 	sock->file = NULL;
 }
+
+void sock_release(struct socket *sock)
+{
+	__sock_release(sock, NULL);
+}
 EXPORT_SYMBOL(sock_release);
 
 void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags)

@@ -1146,7 +1158,7 @@ static int sock_mmap(struct file *file,
 
 static int sock_close(struct inode *inode, struct file *filp)
 {
-	sock_release(SOCKET_I(inode));
+	__sock_release(SOCKET_I(inode), inode);
 	return 0;
 }
 

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

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

From: Xiangning Yu <[email protected]>

[ Upstream commit eb55bbf865d9979098c6a7a17cbdb41237ece951 ]

There is a timing issue under active-standy mode, when bond_enslave() is called, bond->params.primary might not be initialized yet.

Any time the primary slave string changes, bond->force_primary should be set to true to make sure the primary becomes the active slave.

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

@@ -1142,6 +1142,7 @@ static int bond_option_primary_set(struc
 				   slave->dev->name);
 			rcu_assign_pointer(bond->primary_slave, slave);
 			strcpy(bond->params.primary, slave->dev->name);
+			bond->force_primary = true;
 			bond_select_active_slave(bond);
 			goto out;
 		}

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

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

From: Alvaro Gamez Machado <[email protected]>

[ Upstream commit b718e8c8f4f5920aaddc2e52d5e32f494c91129c ]

DP83620 register set is compatible with the DP83848, but it also supports 100base-FX. When the hardware is configured such as that fiber mode is enabled, autonegotiation is not possible.

The chip, however, doesn't expose this information via BMSR_ANEGCAPABLE. Instead, this bit is always set high, even if the particular hardware configuration makes it so that auto negotiation is not possible [1]. Under these circumstances, the phy subsystem keeps trying for autonegotiation to happen, without success.

Hereby, we inspect BMCR_ANENABLE bit after genphy_config_init, which on reset is set to 0 when auto negotiation is disabled, and so we use this value instead of BMSR_ANEGCAPABLE.

[1] https://e2e.ti.com/support/interface/ethernet/f/903/p/697165/2571170

---
 drivers/net/phy/dp83848.c |   35 +++++++++++++++++++++++++++++------
 1 file changed, 29 insertions(+), 6 deletions(-)

@@ -74,6 +74,25 @@ static int dp83848_config_intr(struct ph
 	return phy_write(phydev, DP83848_MICR, control);
 }
 
+static int dp83848_config_init(struct phy_device *phydev)
+{
+	int err;
+	int val;
+
+	err = genphy_config_init(phydev);
+	if (err < 0)
+		return err;
+
+	/* DP83620 always reports Auto Negotiation Ability on BMSR. Instead,
+	 * we check initial value of BMCR Auto negotiation enable bit
+	 */
+	val = phy_read(phydev, MII_BMCR);
+	if (!(val & BMCR_ANENABLE))
+		phydev->autoneg = AUTONEG_DISABLE;
+
+	return 0;
+}
+
 static struct mdio_device_id __maybe_unused dp83848_tbl[] = {
 	{ TI_DP83848C_PHY_ID, 0xfffffff0 },
 	{ NS_DP83848C_PHY_ID, 0xfffffff0 },

@@ -83,7 +102,7 @@ static struct mdio_device_id __maybe_unu
 };
 MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 
-#define DP83848_PHY_DRIVER(_id, _name)				\
+#define DP83848_PHY_DRIVER(_id, _name, _config_init)		\
 	{							\
 		.phy_id		= _id,				\
 		.phy_id_mask	= 0xfffffff0,			\

@@ -92,7 +111,7 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 		.flags		= PHY_HAS_INTERRUPT,		\
 								\
 		.soft_reset	= genphy_soft_reset,		\
-		.config_init	= genphy_config_init,		\
+		.config_init	= _config_init,			\
 		.suspend	= genphy_suspend,		\
 		.resume		= genphy_resume,		\
 								\

@@ -102,10 +121,14 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 	}
 
 static struct phy_driver dp83848_driver[] = {
-	DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY"),
-	DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY"),
-	DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY"),
-	DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY"),
+	DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY",
+			   genphy_config_init),
+	DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY",
+			   genphy_config_init),
+	DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY",
+			   dp83848_config_init),
+	DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY",
+			   genphy_config_init),
 };
 module_phy_driver(dp83848_driver);
 

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

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

From: Davide Caratti <[email protected]>

[ Upstream commit 8d499533e0bc02d44283dbdab03142b599b8ba16 ]

use nla_strlcpy() to avoid copying data beyond the length of TCA_DEF_DATA netlink attribute, in case it is less than SIMP_MAX_DATA and it does not end with '\0' character.

v2: fix errors in the commit message, thanks Hangbin Liu

---
 net/sched/act_simple.c |   15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

@@ -53,22 +53,22 @@ static void tcf_simp_release(struct tc_a
 	kfree(d->tcfd_defdata);
 }
 
-static int alloc_defdata(struct tcf_defact *d, char *defdata)
+static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata)
 {
 	d->tcfd_defdata = kzalloc(SIMP_MAX_DATA, GFP_KERNEL);
 	if (unlikely(!d->tcfd_defdata))
 		return -ENOMEM;
-	strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+	nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
 	return 0;
 }
 
-static void reset_policy(struct tcf_defact *d, char *defdata,
+static void reset_policy(struct tcf_defact *d, const struct nlattr *defdata,
 			 struct tc_defact *p)
 {
 	spin_lock_bh(&d->tcf_lock);
 	d->tcf_action = p->action;
 	memset(d->tcfd_defdata, 0, SIMP_MAX_DATA);
-	strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+	nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
 	spin_unlock_bh(&d->tcf_lock);
 }
 

@@ -87,7 +87,6 @@ static int tcf_simp_init(struct net *net
 	struct tcf_defact *d;
 	bool exists = false;
 	int ret = 0, err;
-	char *defdata;
 
 	if (nla == NULL)
 		return -EINVAL;

@@ -110,8 +109,6 @@ static int tcf_simp_init(struct net *net
 		return -EINVAL;
 	}
 
-	defdata = nla_data(tb[TCA_DEF_DATA]);
-
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_simp_ops, bind, false);

@@ -119,7 +116,7 @@ static int tcf_simp_init(struct net *net
 			return ret;
 
 		d = to_defact(*a);
-		ret = alloc_defdata(d, defdata);
+		ret = alloc_defdata(d, tb[TCA_DEF_DATA]);
 		if (ret < 0) {
 			tcf_idr_release(*a, bind);
 			return ret;

@@ -133,7 +130,7 @@ static int tcf_simp_init(struct net *net
 		if (!ovr)
 			return -EEXIST;
 
-		reset_policy(d, defdata, parm);
+		reset_policy(d, tb[TCA_DEF_DATA], parm);
 	}
 
 	if (ret == ACT_P_CREATED)

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

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

From: Daniel Borkmann <[email protected]>

[ Upstream commit a447da7d00410278c90d3576782a43f8b675d7be ]

syzkaller managed to trigger a use-after-free in tls like the following:

  BUG: KASAN: use-after-free in tls_push_record.constprop.15+0x6a2/0x810 [tls]
  Write of size 1 at addr ffff88037aa08000 by task a.out/2317

  CPU: 3 PID: 2317 Comm: a.out Not tainted 4.17.0+ #144
  Hardware name: LENOVO 20FBCTO1WW/20FBCTO1WW, BIOS N1FET47W (1.21 ) 11/28/2016
  Call Trace:
   dump_stack+0x71/0xab
   print_address_description+0x6a/0x280
   kasan_report+0x258/0x380
   ? tls_push_record.constprop.15+0x6a2/0x810 [tls]
   tls_push_record.constprop.15+0x6a2/0x810 [tls]
   tls_sw_push_pending_record+0x2e/0x40 [tls]
   tls_sk_proto_close+0x3fe/0x710 [tls]
   ? tcp_check_oom+0x4c0/0x4c0
   ? tls_write_space+0x260/0x260 [tls]
   ? kmem_cache_free+0x88/0x1f0
   inet_release+0xd6/0x1b0
   __sock_release+0xc0/0x240
   sock_close+0x11/0x20
   __fput+0x22d/0x660
   task_work_run+0x114/0x1a0
   do_exit+0x71a/0x2780
   ? mm_update_next_owner+0x650/0x650
   ? handle_mm_fault+0x2f5/0x5f0
   ? __do_page_fault+0x44f/0xa50
   ? mm_fault_error+0x2d0/0x2d0
   do_group_exit+0xde/0x300
   __x64_sys_exit_group+0x3a/0x50
   do_syscall_64+0x9a/0x300
   ? page_fault+0x8/0x30
   entry_SYSCALL_64_after_hwframe+0x44/0xa9

This happened through fault injection where aead_req allocation in tls_do_encryption() eventually failed and we returned -ENOMEM from the function. Turns out that the use-after-free is triggered from tls_sw_sendmsg() in the second tls_push_record(). The error then triggers a jump to waiting for memory in sk_stream_wait_memory() resp. returning immediately in case of MSG_DONTWAIT. What follows is the trim_both_sgl(sk, orig_size), which drops elements from the sg list added via tls_sw_sendmsg(). Now the use-after-free gets triggered when the socket is being closed, where tls_sk_proto_close() callback is invoked. The tls_complete_pending_work() will figure that there's a pending closed tls record to be flushed and thus calls into the tls_push_pending_closed_record() from there. ctx->push_pending_record() is called from the latter, which is the tls_sw_push_pending_record() from sw path. This again calls into tls_push_record(). And here the tls_fill_prepend() will panic since the buffer address has been freed earlier via trim_both_sgl(). One way to fix it is to move the aead request allocation out of tls_do_encryption() early into tls_push_record(). This means we don't prep the tls header and advance state to the TLS_PENDING_CLOSED_RECORD before allocation which could potentially fail happened. That fixes the issue on my side.

---
 net/tls/tls_sw.c |   26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

@@ -191,18 +191,12 @@ static void tls_free_both_sg(struct sock
 }
 
 static int tls_do_encryption(struct tls_context *tls_ctx,
-			     struct tls_sw_context *ctx, size_t data_len,
-			     gfp_t flags)
+			     struct tls_sw_context *ctx,
+			     struct aead_request *aead_req,
+			     size_t data_len)
 {
-	unsigned int req_size = sizeof(struct aead_request) +
-		crypto_aead_reqsize(ctx->aead_send);
-	struct aead_request *aead_req;
 	int rc;
 
-	aead_req = kzalloc(req_size, flags);
-	if (!aead_req)
-		return -ENOMEM;
-
 	ctx->sg_encrypted_data[0].offset += tls_ctx->tx.prepend_size;
 	ctx->sg_encrypted_data[0].length -= tls_ctx->tx.prepend_size;
 

@@ -219,7 +213,6 @@ static int tls_do_encryption(struct tls_
 	ctx->sg_encrypted_data[0].offset -= tls_ctx->tx.prepend_size;
 	ctx->sg_encrypted_data[0].length += tls_ctx->tx.prepend_size;
 
-	kfree(aead_req);
 	return rc;
 }
 

@@ -228,8 +221,14 @@ static int tls_push_record(struct sock *
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
+	struct aead_request *req;
 	int rc;
 
+	req = kzalloc(sizeof(struct aead_request) +
+		      crypto_aead_reqsize(ctx->aead_send), sk->sk_allocation);
+	if (!req)
+		return -ENOMEM;
+
 	sg_mark_end(ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem - 1);
 	sg_mark_end(ctx->sg_encrypted_data + ctx->sg_encrypted_num_elem - 1);
 

@@ -245,15 +244,14 @@ static int tls_push_record(struct sock *
 	tls_ctx->pending_open_record_frags = 0;
 	set_bit(TLS_PENDING_CLOSED_RECORD, &tls_ctx->flags);
 
-	rc = tls_do_encryption(tls_ctx, ctx, ctx->sg_plaintext_size,
-			       sk->sk_allocation);
+	rc = tls_do_encryption(tls_ctx, ctx, req, ctx->sg_plaintext_size);
 	if (rc < 0) {
 		/* If we are called from write_space and
 		 * we fail, we need to set this SOCK_NOSPACE
 		 * to trigger another write_space in the future.
 		 */
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-		return rc;
+		goto out_req;
 	}
 
 	free_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem,

@@ -268,6 +266,8 @@ static int tls_push_record(struct sock *
 		tls_err_abort(sk, EBADMSG);
 
 	tls_advance_record_sn(sk, &tls_ctx->tx);
+out_req:
+	kfree(req);
 	return rc;
 }
 

This is the start of the stable review cycle for the 4.17.3 release. There are 70 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 Tue Jun 26 14:27:20 UTC 2018. Anything received after that time might be too late.

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

	https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.17.3-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-4.17.y
and the diffstat can be found below.

thanks,

greg k-h

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

Greg Kroah-Hartman <[email protected]>

    Linux 4.17.3-rc1

Vlastimil Babka <[email protected]>
mm, page_alloc: do not break __GFP_THISNODE by zonelist reset

Thadeu Lima de Souza Cascardo <[email protected]>
fs/binfmt_misc.c: do not allow offset overflow

Michael S. Tsirkin <[email protected]>
vhost: fix info leak due to uninitialized memory

Jason Gerecke <[email protected]>
HID: wacom: Correct logical maximum Y for 2nd-gen Intuos Pro large

Even Xu <[email protected]>
HID: intel_ish-hid: ipc: register more pm callbacks to support hibernation

Martin Brandenburg <[email protected]>
orangefs: report attributes_mask and attributes for statx

Martin Brandenburg <[email protected]>
orangefs: set i_size on new symlink

Luca Coelho <[email protected]>
iwlwifi: fw: harden page loading code

Sean Young <[email protected]>
media: rc: ensure input/lirc device can be opened after register

Kieran Bingham <[email protected]>
media: uvcvideo: Prevent setting unavailable flags

Tony Luck <[email protected]>
x86/intel_rdt: Enable CMT and MBM on new Skylake stepping

Thomas Gleixner <[email protected]>
genirq/migration: Avoid out of line call if pending is not set

Thomas Gleixner <[email protected]>
genirq/affinity: Defer affinity setting if irq chip is busy

Thomas Gleixner <[email protected]>
genirq/generic_pending: Do not lose pending affinity update

Thomas Gleixner <[email protected]>
irq_remapping: Use apic_ack_irq()

Thomas Gleixner <[email protected]>

    x86/platform/uv: Use apic_ack_irq()

Thomas Gleixner <[email protected]>

    x86/ioapic: Use apic_ack_irq()

Thomas Gleixner <[email protected]>
x86/apic: Provide apic_ack_irq()

Thomas Gleixner <[email protected]>
x86/apic/vector: Prevent hlist corruption and leaks

Dou Liyang <[email protected]>
x86/vector: Fix the args of vector_alloc tracepoint

Stefan Potyra <[email protected]>
w1: mxc_w1: Enable clock before calling clk_get_rate() on it

Keith Busch <[email protected]>
nvme/pci: Sync controller reset for AER slot_reset

Hans de Goede <[email protected]>
libata: Drop SanDisk SD7UB3Q*G1001 NOLPM quirk

Dan Carpenter <[email protected]>
libata: zpodd: small read overflow in eject_tray()

Chen Yu <[email protected]>
cpufreq: governors: Fix long idle detection logic in load calculation

Suman Anna <[email protected]>
cpufreq: ti-cpufreq: Fix an incorrect error return value

Tao Wang <[email protected]>
cpufreq: Fix new policy initialization during limits updates via sysfs

Tejun Heo <[email protected]>
bdi: Move cgroup bdi_writeback to a dedicated low concurrency workqueue

Roman Pen <[email protected]>

    blk-mq: reinit q->tag_set_list entry only after grace period

Josef Bacik <[email protected]>
nbd: use bd_set_size when updating disk size

Josef Bacik <[email protected]>
nbd: update size when connected

Josef Bacik <[email protected]>
nbd: fix nbd device deletion

Shirish Pargaonkar <[email protected]>
cifs: For SMB2 security informaion query, check for minimum sized security descriptor instead of sizeof FileAllInformation class

Mark Syms <[email protected]>

    CIFS: 511c54a2f69195b28afb9dd119f03787b1625bb4 adds a check for session expiry

Steve French <[email protected]>
smb3: on reconnect set PreviousSessionId field

Steve French <[email protected]>
smb3: fix various xid leaks

Tony Luck <[email protected]>
x86/MCE: Fix stack out-of-bounds write in mce-inject.c: Flags_read()

Dennis Wassenberg <[email protected]>
ALSA: hda: add dock and led support for HP ProBook 640 G4

Dennis Wassenberg <[email protected]>
ALSA: hda: add dock and led support for HP EliteBook 830 G5

Bo Chen <[email protected]>
ALSA: hda - Handle kzalloc() failure in snd_hda_attach_pcm_stream()

Takashi Iwai <[email protected]>
ALSA: hda/conexant - Add fixup for HP Z2 G4 workstation

Hui Wang <[email protected]>
ALSA: hda/realtek - Enable mic-mute hotkey for several Lenovo AIOs

Takashi Iwai <[email protected]>
ALSA: usb-audio: Disable the quirk for Nura headset

Qu Wenruo <[email protected]>
btrfs: scrub: Don't use inode pages for device replace

Su Yue <[email protected]>
btrfs: return error value if create_io_em failed in cow_file_range

Omar Sandoval <[email protected]>
Btrfs: fix memory and mount leak in btrfs_ioctl_rm_dev_v2()

Omar Sandoval <[email protected]>
Btrfs: fix clone vs chattr NODATASUM race

Omar Sandoval <[email protected]>
Btrfs: allow empty subvol= again

Tetsuo Handa <[email protected]>
driver core: Don't ignore class_dir_create_and_add() failure.

Jan Kara <[email protected]>
ext4: fix fencepost error in check for inode count overflow during resize

Theodore Ts'o <[email protected]>
ext4: correctly handle a zero-length xattr with a non-zero e_value_offs

Theodore Ts'o <[email protected]>
ext4: bubble errors from ext4_find_inline_data_nolock() up to ext4_iget()

Theodore Ts'o <[email protected]>
ext4: do not allow external inodes for inline data

Lukas Czerner <[email protected]>
ext4: update mtime in ext4_punch_hole even if no blocks are released

Jan Kara <[email protected]>
ext4: fix hole length detection in ext4_ind_map_blocks()

Erik Schmauss <[email protected]>
ACPICA: AML parser: attempt to continue loading table after error

Dexuan Cui <[email protected]>
hv_netvsc: Fix a network regression after ifdown/ifup

Willem de Bruijn <[email protected]>
net: in virtio_net_hdr only add VLAN_HLEN to csum_start if payload holds vlan

Paolo Abeni <[email protected]>
udp: fix rx queue len reported by diag and proc interface

Cong Wang <[email protected]>
socket: close race condition between sock_close() and sockfs_setattr()

Daniel Borkmann <[email protected]>
tls: fix waitall behavior in tls_sw_recvmsg

Daniel Borkmann <[email protected]>
tls: fix use-after-free in tls_push_record

Frank van der Linden <[email protected]>
tcp: verify the checksum of the first data segment in a new connection

Davide Caratti <[email protected]>
net/sched: act_simple: fix parsing of TCA_DEF_DATA

Alvaro Gamez Machado <[email protected]>
net: phy: dp83822: use BMCR_ANENABLE instead of BMSR_ANEGCAPABLE for DP83620

Zhouyang Jia <[email protected]>
net: dsa: add error handling for pskb_trim_rcsum

Julian Anastasov <[email protected]>
ipv6: allow PMTU exceptions to local routes

Bjørn Mork <[email protected]>
cdc_ncm: avoid padding beyond end of skb

Xiangning Yu <[email protected]>
bonding: re-evaluate force_primary when the primary slave name changes

Colin Ian King <[email protected]>
net: aquantia: fix unsigned numvecs comparison with less than zero

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

Diffstat:

 Makefile                                           |  4 +-
 arch/um/drivers/vector_transports.c                |  3 +-
 arch/x86/include/asm/apic.h                        |  2 +
 arch/x86/include/asm/trace/irq_vectors.h           |  2 +-
 arch/x86/kernel/apic/io_apic.c                     |  2 +-
 arch/x86/kernel/apic/vector.c                      | 18 +++++-
 arch/x86/kernel/cpu/intel_rdt.c                    |  2 +
 arch/x86/kernel/cpu/mcheck/mce-inject.c            |  2 +-
 arch/x86/platform/uv/uv_irq.c                      |  7 +--
 block/blk-mq.c                                     |  3 +-
 drivers/acpi/acpica/psloop.c                       | 51 +++++++++++++++-
 drivers/acpi/acpica/psobject.c                     | 30 ++++++++++
 drivers/acpi/acpica/uterror.c                      | 10 ++--
 drivers/ata/libata-core.c                          |  3 -
 drivers/ata/libata-zpodd.c                         |  2 +-
 drivers/base/core.c                                | 14 ++++-
 drivers/block/nbd.c                                | 17 +++++-
 drivers/cpufreq/cpufreq.c                          |  2 +
 drivers/cpufreq/cpufreq_governor.c                 | 12 ++--
 drivers/cpufreq/ti-cpufreq.c                       |  2 +-
 drivers/hid/intel-ish-hid/ipc/pci-ish.c            | 22 +++----
 drivers/hid/wacom_sys.c                            |  8 +++
 drivers/iommu/amd_iommu.c                          |  2 +-
 drivers/iommu/intel_irq_remapping.c                |  2 +-
 drivers/iommu/irq_remapping.c                      |  5 --
 drivers/iommu/irq_remapping.h                      |  2 -
 drivers/media/rc/rc-main.c                         |  4 +-
 drivers/media/usb/uvc/uvc_ctrl.c                   | 17 +++---
 drivers/net/bonding/bond_options.c                 |  1 +
 .../net/ethernet/aquantia/atlantic/aq_pci_func.c   | 11 ++--
 drivers/net/hyperv/netvsc_drv.c                    |  4 +-
 drivers/net/phy/dp83848.c                          | 35 +++++++++--
 drivers/net/tap.c                                  |  5 +-
 drivers/net/tun.c                                  |  3 +-
 drivers/net/usb/cdc_ncm.c                          |  4 +-
 drivers/net/virtio_net.c                           |  3 +-
 drivers/net/wireless/intel/iwlwifi/fw/paging.c     | 49 +++++++++++++---
 drivers/nvme/host/pci.c                            | 11 +++-
 drivers/vhost/vhost.c                              |  3 +
 drivers/w1/masters/mxc_w1.c                        | 20 ++++---
 fs/binfmt_misc.c                                   | 12 +++-
 fs/btrfs/inode.c                                   |  4 +-
 fs/btrfs/ioctl.c                                   | 18 +++---
 fs/btrfs/scrub.c                                   |  2 +-
 fs/btrfs/super.c                                   |  3 +
 fs/cifs/cifsacl.h                                  | 14 +++++
 fs/cifs/smb2ops.c                                  | 68 +++++++++++++++-------
 fs/cifs/smb2pdu.c                                  |  4 +-
 fs/ext4/indirect.c                                 | 14 +++--
 fs/ext4/inline.c                                   |  6 ++
 fs/ext4/inode.c                                    | 46 ++++++++-------
 fs/ext4/resize.c                                   |  2 +-
 fs/ext4/xattr.c                                    |  2 +-
 fs/orangefs/inode.c                                |  7 +++
 fs/orangefs/namei.c                                |  7 +++
 include/linux/irq.h                                |  7 ++-
 include/linux/virtio_net.h                         | 11 ++--
 include/net/transp_v6.h                            | 11 +++-
 include/net/udp.h                                  |  5 ++
 kernel/irq/manage.c                                | 37 +++++++++++-
 kernel/irq/migration.c                             | 31 ++++++----
 mm/backing-dev.c                                   | 18 +++++-
 mm/page_alloc.c                                    |  1 -
 net/dsa/tag_trailer.c                              |  3 +-
 net/ipv4/tcp_ipv4.c                                |  4 ++
 net/ipv4/udp.c                                     |  2 +-
 net/ipv4/udp_diag.c                                |  2 +-
 net/ipv6/datagram.c                                |  6 +-
 net/ipv6/route.c                                   |  3 -
 net/ipv6/tcp_ipv6.c                                |  4 ++
 net/ipv6/udp.c                                     |  3 +-
 net/packet/af_packet.c                             |  4 +-
 net/sched/act_simple.c                             | 15 ++---
 net/socket.c                                       | 18 +++++-
 net/tls/tls_sw.c                                   | 32 +++++-----
 sound/pci/hda/hda_controller.c                     |  4 +-
 sound/pci/hda/patch_conexant.c                     |  3 +
 sound/pci/hda/patch_realtek.c                      |  6 +-
 sound/usb/quirks-table.h                           |  5 ++
 79 files changed, 609 insertions(+), 234 deletions(-)

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

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

From: Tetsuo Handa <[email protected]>

commit 84d0c27d6233a9ba0578b20f5a09701eb66cee42 upstream.

syzbot is hitting WARN() at kernfs_add_one() [1].
This is because kernfs_create_link() is confused by previous device_add() call which continued without setting dev->kobj.parent field when get_device_parent() failed by memory allocation fault injection. Fix this by propagating the error from class_dir_create_and_add() to the calllers of get_device_parent().

[1] https://syzkaller.appspot.com/bug?id=fae0fb607989ea744526d1c082a5b8de6529116f

---
 drivers/base/core.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

@@ -1467,7 +1467,7 @@ class_dir_create_and_add(struct class *c
 
 	dir = kzalloc(sizeof(*dir), GFP_KERNEL);
 	if (!dir)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	dir->class = class;
 	kobject_init(&dir->kobj, &class_dir_ktype);

@@ -1477,7 +1477,7 @@ class_dir_create_and_add(struct class *c
 	retval = kobject_add(&dir->kobj, parent_kobj, "%s", class->name);
 	if (retval < 0) {
 		kobject_put(&dir->kobj);
-		return NULL;
+		return ERR_PTR(retval);
 	}
 	return &dir->kobj;
 }

@@ -1784,6 +1784,10 @@ int device_add(struct device *dev)
 
 	parent = get_device(dev->parent);
 	kobj = get_device_parent(dev, parent);
+	if (IS_ERR(kobj)) {
+		error = PTR_ERR(kobj);
+		goto parent_error;
+	}
 	if (kobj)
 		dev->kobj.parent = kobj;
 

@@ -1882,6 +1886,7 @@ done:
 	kobject_del(&dev->kobj);
  Error:
 	cleanup_glue_dir(dev, glue_dir);
+parent_error:
 	put_device(parent);
 name_error:
 	kfree(dev->p);

@@ -2701,6 +2706,11 @@ int device_move(struct device *dev, stru
 	device_pm_lock();
 	new_parent = get_device(new_parent);
 	new_parent_kobj = get_device_parent(dev, new_parent);
+	if (IS_ERR(new_parent_kobj)) {
+		error = PTR_ERR(new_parent_kobj);
+		put_device(new_parent);
+		goto out;
+	}
 
 	pr_debug("device: '%s': %s: moving to '%s'\n", dev_name(dev),
 		 __func__, new_parent ? dev_name(new_parent) : "<NULL>");

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

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

From: Omar Sandoval <[email protected]>

commit 37becec95ac31b209eb1c8e096f1093a7db00f32 upstream.

I got a report that after upgrading to 4.16, someone's filesystems weren't mounting:

[   23.845852] BTRFS info (device loop0): unrecognized mount option 'subvol='

Before 4.16, this mounted the default subvolume. It turns out that this empty "subvol=" is actually an application bug, but it was causing the application to fail, so it's an ABI break if you squint.

The generic parsing code we use for mount options (match_token()) doesn't match an empty string as "%s". Previously, setup_root_args() removed the "subvol=" string, but the mount path was cleaned up to not need that. Add a dummy Opt_subvol_empty to fix this.

The simple workaround is to use / or . for the value of 'subvol=' .

---
 fs/btrfs/super.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -323,6 +323,7 @@ enum {
 	Opt_ssd, Opt_nossd,
 	Opt_ssd_spread, Opt_nossd_spread,
 	Opt_subvol,
+	Opt_subvol_empty,
 	Opt_subvolid,
 	Opt_thread_pool,
 	Opt_treelog, Opt_notreelog,

@@ -388,6 +389,7 @@ static const match_table_t tokens = {
 	{Opt_ssd_spread, "ssd_spread"},
 	{Opt_nossd_spread, "nossd_spread"},
 	{Opt_subvol, "subvol=%s"},
+	{Opt_subvol_empty, "subvol="},
 	{Opt_subvolid, "subvolid=%s"},
 	{Opt_thread_pool, "thread_pool=%u"},
 	{Opt_treelog, "treelog"},

@@ -461,6 +463,7 @@ int btrfs_parse_options(struct btrfs_fs_
 			btrfs_set_opt(info->mount_opt, DEGRADED);
 			break;
 		case Opt_subvol:
+		case Opt_subvol_empty:
 		case Opt_subvolid:
 		case Opt_subvolrootid:
 		case Opt_device:

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

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

From: Omar Sandoval <[email protected]>

commit b5c40d598f5408bd0ca22dfffa82f03cd9433f23 upstream.

In btrfs_clone_files(), we must check the NODATASUM flag while the inodes are locked. Otherwise, it's possible that btrfs_ioctl_setflags() will change the flags after we check and we can end up with a party checksummed file.

The race window is only a few instructions in size, between the if and the locks which is:

3834 if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
3835 return -EISDIR;

where the setflags must be run and toggle the NODATASUM flag (provided the file size is 0). The clone will block on the inode lock, segflags takes the inode lock, changes flags, releases log and clone continues.

Not impossible but still needs a lot of bad luck to hit unintentionally.

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

@@ -3826,11 +3826,6 @@ static noinline int btrfs_clone_files(st
 	    src->i_sb != inode->i_sb)
 		return -EXDEV;
 
-	/* don't make the dst file partly checksummed */
-	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
-	    (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
-		return -EINVAL;
-
 	if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
 		return -EISDIR;
 

@@ -3840,6 +3835,13 @@ static noinline int btrfs_clone_files(st
 		inode_lock(src);
 	}
 
+	/* don't make the dst file partly checksummed */
+	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
+	    (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	/* determine range to clone */
 	ret = -EINVAL;
 	if (off + len > src->i_size || off + len < off)

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

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

From: Omar Sandoval <[email protected]>

commit fd4e994bd1f9dc9628e168a7f619bf69f6984635 upstream.

If we have invalid flags set, when we error out we must drop our writer counter and free the buffer we allocated for the arguments. This bug is trivially reproduced with the following program on 4.7+:

	#include <fcntl.h>
	#include <stdint.h>
	#include <stdio.h>
	#include <stdlib.h>
	#include <unistd.h>
	#include <sys/ioctl.h>
	#include <sys/stat.h>
	#include <sys/types.h>
	#include <linux/btrfs.h>
	#include <linux/btrfs_tree.h>

	int main(int argc, char **argv)
	{
		struct btrfs_ioctl_vol_args_v2 vol_args = {
			.flags = UINT64_MAX,
		};
		int ret;
		int fd;

		if (argc != 2) {
			fprintf(stderr, "usage: %s PATH\n", argv[0]);
			return EXIT_FAILURE;
		}

		fd = open(argv[1], O_WRONLY);
		if (fd == -1) {
			perror("open");
			return EXIT_FAILURE;
		}

		ret = ioctl(fd, BTRFS_IOC_RM_DEV_V2, &vol_args);
		if (ret == -1)
			perror("ioctl");

		close(fd);
		return EXIT_SUCCESS;
	}

When unmounting the filesystem, we'll hit the WARN_ON(mnt_get_writers(mnt)) in cleanup_mnt() and also may prevent the filesystem to be remounted read-only as the writer count will stay lifted.

---
 fs/btrfs/ioctl.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

@@ -2654,8 +2654,10 @@ static long btrfs_ioctl_rm_dev_v2(struct
 	}
 
 	/* Check for compatibility reject unknown flags */
-	if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED)
-		return -EOPNOTSUPP;
+	if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
 
 	if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
 		ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;

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

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

From: Su Yue <[email protected]>

commit 090a127afa8f73e9618d4058d6755f7ec7453dd6 upstream.

In cow_file_range(), create_io_em() may fail, but its return value is not recorded. Then return value may be 0 even it failed which is a wrong behavior.

Let cow_file_range() return PTR_ERR(em) if create_io_em() failed.

---
 fs/btrfs/inode.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -1018,8 +1018,10 @@ static noinline int cow_file_range(struc
 				  ram_size, /* ram_bytes */
 				  BTRFS_COMPRESS_NONE, /* compress_type */
 				  BTRFS_ORDERED_REGULAR /* type */);
-		if (IS_ERR(em))
+		if (IS_ERR(em)) {
+			ret = PTR_ERR(em);
 			goto out_reserve;
+		}
 		free_extent_map(em);
 
 		ret = btrfs_add_ordered_extent(inode, start, ins.objectid,

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

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

From: Qu Wenruo <[email protected]>

commit ac0b4145d662a3b9e34085dea460fb06ede9b69b upstream.

[BUG]
Btrfs can create compressed extent without checksum (even though it shouldn't), and if we then try to replace device containing such extent, the result device will contain all the uncompressed data instead of the compressed one.

Test case already submitted to fstests:
https://patchwork.kernel.org/patch/10442353/

[CAUSE]
When handling compressed extent without checksum, device replace will goe into copy_nocow_pages() function.

In that function, btrfs will get all inodes referring to this data extents and then use find_or_create_page() to get pages direct from that inode.

The problem here is, pages directly from inode are always uncompressed. And for compressed data extent, they mismatch with on-disk data. Thus this leads to corrupted compressed data extent written to replace device.

[FIX]
In this attempt, we could just remove the "optimization" branch, and let unified scrub_pages() to handle it.

Although scrub_pages() won't bother reusing page cache, it will be a little slower, but it does the correct csum checking and won't cause such data corruption caused by "optimization".

Note about the fix: this is the minimal fix that can be backported to older stable trees without conflicts. The whole callchain from copy_nocow_pages() can be deleted, and will be in followup patches.

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

@@ -2799,7 +2799,7 @@ static int scrub_extent(struct scrub_ctx
 			have_csum = scrub_find_csum(sctx, logical, csum);
 			if (have_csum == 0)
 				++sctx->stat.no_csum;
-			if (sctx->is_dev_replace && !have_csum) {
+			if (0 && sctx->is_dev_replace && !have_csum) {
 				ret = copy_nocow_pages(sctx, logical, l,
 						       mirror_num,
 						      physical_for_dev_replace);

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

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

From: Takashi Iwai <[email protected]>

commit 5ebf6b1e459606d7fbf4fc67d2c28a6540953d93 upstream.

The commit 33193dca671c ("ALSA: usb-audio: Add a quirk for Nura's first gen headset") added a quirk for Nura headset with USB ID 0a12:1243, with a hope that it doesn't conflict with others. Unfortunately, other devices (e.g. Philips Wecall) with the very same ID got broken by this change, spewing an error like:
usb 2-1.8.2: 2:1: cannot set freq 48000 to ep 0x3

Until we find a proper solution, fix the regression at first by disabling the added quirk entry.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199905

---
 sound/usb/quirks-table.h |    5 +++++
 1 file changed, 5 insertions(+)

@@ -3277,6 +3277,10 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge
 	}
 },
 
+/* disabled due to regression for other devices;
+ * see https://bugzilla.kernel.org/show_bug.cgi?id=199905
+ */
+#if 0
 {
 	/*
 	 * Nura's first gen headphones use Cambridge Silicon Radio's vendor

@@ -3324,6 +3328,7 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge
 		}
 	}
 },
+#endif /* disabled */
 
 {
 	/*

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

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

From: Hui Wang <[email protected]>

commit 986376b68dcc95bb7df60ad30c2353c1f7578fa5 upstream.

We have several Lenovo AIOs like M810z, M820z and M920z, they have the same design for mic-mute hotkey and led and they use the same codec with the same pin configuration, so use the pin conf table to apply fix to all of them.

---
 sound/pci/hda/patch_realtek.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -6580,7 +6580,6 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x3138, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
-	SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),

@@ -6752,6 +6751,11 @@ static const struct snd_hda_pin_quirk al
 		{0x1b, 0x01111010},
 		{0x1e, 0x01451130},
 		{0x21, 0x02211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0235, 0x17aa, "Lenovo", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY,
+		{0x12, 0x90a60140},
+		{0x14, 0x90170110},
+		{0x19, 0x02a11030},
+		{0x21, 0x02211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60140},
 		{0x14, 0x90170110},

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

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

From: Bo Chen <[email protected]>

commit a3aa60d511746bd6c0d0366d4eb90a7998bcde8b upstream.

When 'kzalloc()' fails in 'snd_hda_attach_pcm_stream()', a new pcm instance is created without setting its operators via 'snd_pcm_set_ops()'. Following operations on the new pcm instance can trigger kernel null pointer dereferences and cause kernel oops.

This bug was found with my work on building a gray-box fault-injection tool for linux-kernel-module binaries. A kernel null pointer dereference was confirmed from line 'substream->ops->open()' in function 'snd_pcm_open_substream()' in file 'sound/core/pcm_native.c'.

This patch fixes the bug by calling 'snd_device_free()' in the error handling path of 'kzalloc()', which removes the new pcm instance from the snd card before returns with an error code.

---
 sound/pci/hda/hda_controller.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -748,8 +748,10 @@ int snd_hda_attach_pcm_stream(struct hda
 		return err;
 	strlcpy(pcm->name, cpcm->name, sizeof(pcm->name));
 	apcm = kzalloc(sizeof(*apcm), GFP_KERNEL);
-	if (apcm == NULL)
+	if (apcm == NULL) {
+		snd_device_free(chip->card, pcm);
 		return -ENOMEM;
+	}
 	apcm->chip = chip;
 	apcm->pcm = pcm;
 	apcm->codec = codec;

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

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

From: Dexuan Cui <[email protected]>

[ Upstream commit 52acf73b6e9a6962045feb2ba5a8921da2201915 ]

Recently people reported the NIC stops working after
"ifdown eth0; ifup eth0". It turns out in this case the TX queues are not enabled, after the refactoring of the common detach logic: when the NIC has sub-channels, usually we enable all the TX queues after all sub-channels are set up: see rndis_set_subchannel() -> netif_device_attach(), but in the case of "ifdown eth0; ifup eth0" where the number of channels doesn't change, we also must make sure the TX queues are enabled. The patch fixes the regression.

---
 drivers/net/hyperv/netvsc_drv.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -126,8 +126,10 @@ static int netvsc_open(struct net_device
 	}
 
 	rdev = nvdev->extension;
-	if (!rdev->link_state)
+	if (!rdev->link_state) {
 		netif_carrier_on(net);
+		netif_tx_wake_all_queues(net);
+	}
 
 	if (vf_netdev) {
 		/* Setting synthetic device up transparently sets

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

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

From: Dennis Wassenberg <[email protected]>

commit 7eef32c1ef895a3a96463f9cbd04203007cd5555 upstream.

This patch adds missing initialisation for HP 2013 UltraSlim Dock Line-In/Out PINs and activates keyboard mute/micmute leds for HP ProBook 640 G4

---
 sound/pci/hda/patch_conexant.c |    1 +
 1 file changed, 1 insertion(+)

@@ -960,6 +960,7 @@ static const struct snd_pci_quirk cxt506
 	SND_PCI_QUIRK(0x103c, 0x807C, "HP EliteBook 820 G3", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x80FD, "HP ProBook 640 G2", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x83b3, "HP EliteBook 830 G5", CXT_FIXUP_HP_DOCK),
+	SND_PCI_QUIRK(0x103c, 0x83d3, "HP ProBook 640 G4", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE),
 	SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
 	SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO),

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

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

From: Steve French <[email protected]>

commit cfe89091644c441a1ade6dae6d2e47b715648615 upstream.

Fix a few cases where we were not freeing the xid which led to active requests being non-zero at unmount time.

---
 fs/cifs/smb2ops.c |   63 +++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 44 insertions(+), 19 deletions(-)

@@ -1593,8 +1593,11 @@ get_smb2_acl_by_path(struct cifs_sb_info
 		oparms.create_options = 0;
 
 	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
-	if (!utf16_path)
-		return ERR_PTR(-ENOMEM);
+	if (!utf16_path) {
+		rc = -ENOMEM;
+		free_xid(xid);
+		return ERR_PTR(rc);
+	}
 
 	oparms.tcon = tcon;
 	oparms.desired_access = READ_CONTROL;

@@ -1652,8 +1655,11 @@ set_smb2_acl(struct cifs_ntsd *pnntsd, _
 		access_flags = WRITE_DAC;
 
 	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
-	if (!utf16_path)
-		return -ENOMEM;
+	if (!utf16_path) {
+		rc = -ENOMEM;
+		free_xid(xid);
+		return rc;
+	}
 
 	oparms.tcon = tcon;
 	oparms.desired_access = access_flags;

@@ -1713,15 +1719,21 @@ static long smb3_zero_range(struct file
 
 	/* if file not oplocked can't be sure whether asking to extend size */
 	if (!CIFS_CACHE_READ(cifsi))
-		if (keep_size == false)
-			return -EOPNOTSUPP;
+		if (keep_size == false) {
+			rc = -EOPNOTSUPP;
+			free_xid(xid);
+			return rc;
+		}
 
 	/*
 	 * Must check if file sparse since fallocate -z (zero range) assumes
 	 * non-sparse allocation
 	 */
-	if (!(cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE))
-		return -EOPNOTSUPP;
+	if (!(cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE)) {
+		rc = -EOPNOTSUPP;
+		free_xid(xid);
+		return rc;
+	}
 
 	/*
 	 * need to make sure we are not asked to extend the file since the SMB3

@@ -1730,8 +1742,11 @@ static long smb3_zero_range(struct file
 	 * which for a non sparse file would zero the newly extended range
 	 */
 	if (keep_size == false)
-		if (i_size_read(inode) < offset + len)
-			return -EOPNOTSUPP;
+		if (i_size_read(inode) < offset + len) {
+			rc = -EOPNOTSUPP;
+			free_xid(xid);
+			return rc;
+		}
 
 	cifs_dbg(FYI, "offset %lld len %lld", offset, len);
 

@@ -1764,8 +1779,11 @@ static long smb3_punch_hole(struct file
 
 	/* Need to make file sparse, if not already, before freeing range. */
 	/* Consider adding equivalent for compressed since it could also work */
-	if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse))
-		return -EOPNOTSUPP;
+	if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) {
+		rc = -EOPNOTSUPP;
+		free_xid(xid);
+		return rc;
+	}
 
 	cifs_dbg(FYI, "offset %lld len %lld", offset, len);
 

@@ -1796,8 +1814,10 @@ static long smb3_simple_falloc(struct fi
 
 	/* if file not oplocked can't be sure whether asking to extend size */
 	if (!CIFS_CACHE_READ(cifsi))
-		if (keep_size == false)
-			return -EOPNOTSUPP;
+		if (keep_size == false) {
+			free_xid(xid);
+			return rc;
+		}
 
 	/*
 	 * Files are non-sparse by default so falloc may be a no-op

@@ -1806,14 +1826,16 @@ static long smb3_simple_falloc(struct fi
 	 */
 	if ((cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE) == 0) {
 		if (keep_size == true)
-			return 0;
+			rc = 0;
 		/* check if extending file */
 		else if (i_size_read(inode) >= off + len)
 			/* not extending file and already not sparse */
-			return 0;
+			rc = 0;
 		/* BB: in future add else clause to extend file */
 		else
-			return -EOPNOTSUPP;
+			rc = -EOPNOTSUPP;
+		free_xid(xid);
+		return rc;
 	}
 
 	if ((keep_size == true) || (i_size_read(inode) >= off + len)) {

@@ -1825,8 +1847,11 @@ static long smb3_simple_falloc(struct fi
 		 * ie potentially making a few extra pages at the beginning
 		 * or end of the file non-sparse via set_sparse is harmless.
 		 */
-		if ((off > 8192) || (off + len + 8192 < i_size_read(inode)))
-			return -EOPNOTSUPP;
+		if ((off > 8192) || (off + len + 8192 < i_size_read(inode))) {
+			rc = -EOPNOTSUPP;
+			free_xid(xid);
+			return rc;
+		}
 
 		rc = smb2_set_sparse(xid, tcon, cfile, inode, false);
 	}

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

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

From: Steve French <[email protected]>

commit b2adf22fdfba85a6701c481faccdbbb3a418ccfc upstream.

The server detects reconnect by the (non-zero) value in PreviousSessionId of SMB2/SMB3 SessionSetup request, but this behavior regressed due to commit 166cea4dc3a4f66f020cfb9286225ecd228ab61d
("SMB2: Separate RawNTLMSSP authentication from SMB2_sess_setup")

---
 fs/cifs/smb2pdu.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1276,6 +1276,7 @@ SMB2_sess_setup(const unsigned int xid,
 	sess_data->ses = ses;
 	sess_data->buf0_type = CIFS_NO_BUFFER;
 	sess_data->nls_cp = (struct nls_table *) nls_cp;
+	sess_data->previous_session = ses->Suid;
 
 #ifdef CONFIG_CIFS_SMB311
 	/*

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

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

From: Shirish Pargaonkar <[email protected]>

commit ee25c6dd7b05113783ce1f4fab6b30fc00d29b8d upstream.

Validate_buf () function checks for an expected minimum sized response passed to query_info() function.
For security information, the size of a security descriptor can be smaller (one subauthority, no ACEs) than the size of the structure that defines FileInfoClass of FileAllInformation.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199725

---
 fs/cifs/cifsacl.h |   14 ++++++++++++++
 fs/cifs/smb2pdu.c |    3 +--
 2 files changed, 15 insertions(+), 2 deletions(-)

@@ -98,4 +98,18 @@ struct cifs_ace {
 	struct cifs_sid sid; /* ie UUID of user or group who gets these perms */
 } __attribute__((packed));
 
+/*
+ * Minimum security identifier can be one for system defined Users
+ * and Groups such as NULL SID and World or Built-in accounts such
+ * as Administrator and Guest and consists of
+ * Revision + Num (Sub)Auths + Authority + Domain (one Subauthority)
+ */
+#define MIN_SID_LEN  (1 + 1 + 6 + 4) /* in bytes */
+
+/*
+ * Minimum security descriptor can be one without any SACL and DACL and can
+ * consist of revision, type, and two sids of minimum size for owner and group
+ */
+#define MIN_SEC_DESC_LEN  (sizeof(struct cifs_ntsd) + (2 * MIN_SID_LEN))
+
 #endif /* _CIFSACL_H */

@@ -2378,8 +2378,7 @@ SMB2_query_acl(const unsigned int xid, s
 
 	return query_info(xid, tcon, persistent_fid, volatile_fid,
 			  0, SMB2_O_INFO_SECURITY, additional_info,
-			  SMB2_MAX_BUFFER_SIZE,
-			  sizeof(struct smb2_file_all_info), data, plen);
+			  SMB2_MAX_BUFFER_SIZE, MIN_SEC_DESC_LEN, data, plen);
 }
 
 int

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

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

From: Erik Schmauss <[email protected]>

commit 5088814a6e931350e5bd29f5d59fa40c6dbbdf10 upstream.

This change alters the parser so that the table load does not abort upon an error.

Notable changes:

If there is an error while parsing an element of the termlist, we will skip parsing the current termlist element and continue parsing to the next opcode in the termlist.

If we get an error while parsing the conditional of If/Else/While or the device name of Scope, we will skip the body of the statement all together and pop the parser_state.

If we get an error while parsing the base offset and length of an operation region declaration, we will remove the operation region from the namespace.

---
 drivers/acpi/acpica/psloop.c   |   51 ++++++++++++++++++++++++++++++++++++++++-
 drivers/acpi/acpica/psobject.c |   30 ++++++++++++++++++++++++
 drivers/acpi/acpica/uterror.c  |   10 ++++----
 3 files changed, 85 insertions(+), 6 deletions(-)

@@ -515,6 +515,22 @@ acpi_status acpi_ps_parse_loop(struct ac
 				if (ACPI_FAILURE(status)) {
 					return_ACPI_STATUS(status);
 				}
+				if (walk_state->opcode == AML_SCOPE_OP) {
+					/*
+					 * If the scope op fails to parse, skip the body of the
+					 * scope op because the parse failure indicates that the
+					 * device may not exist.
+					 */
+					walk_state->parser_state.aml =
+					    walk_state->aml + 1;
+					walk_state->parser_state.aml =
+					    acpi_ps_get_next_package_end
+					    (&walk_state->parser_state);
+					walk_state->aml =
+					    walk_state->parser_state.aml;
+					ACPI_ERROR((AE_INFO,
+						    "Skipping Scope block"));
+				}
 
 				continue;
 			}

@@ -557,7 +573,40 @@ acpi_status acpi_ps_parse_loop(struct ac
 				if (ACPI_FAILURE(status)) {
 					return_ACPI_STATUS(status);
 				}
-
+				if ((walk_state->control_state) &&
+				    ((walk_state->control_state->control.
+				      opcode == AML_IF_OP)
+				     || (walk_state->control_state->control.
+					 opcode == AML_WHILE_OP))) {
+					/*
+					 * If the if/while op fails to parse, we will skip parsing
+					 * the body of the op.
+					 */
+					parser_state->aml =
+					    walk_state->control_state->control.
+					    aml_predicate_start + 1;
+					parser_state->aml =
+					    acpi_ps_get_next_package_end
+					    (parser_state);
+					walk_state->aml = parser_state->aml;
+
+					ACPI_ERROR((AE_INFO,
+						    "Skipping While/If block"));
+					if (*walk_state->aml == AML_ELSE_OP) {
+						ACPI_ERROR((AE_INFO,
+							    "Skipping Else block"));
+						walk_state->parser_state.aml =
+						    walk_state->aml + 1;
+						walk_state->parser_state.aml =
+						    acpi_ps_get_next_package_end
+						    (parser_state);
+						walk_state->aml =
+						    parser_state->aml;
+					}
+					ACPI_FREE(acpi_ut_pop_generic_state
+						  (&walk_state->control_state));
+				}
+				op = NULL;
 				continue;
 			}
 		}

@@ -12,6 +12,7 @@
 #include "acparser.h"
 #include "amlcode.h"
 #include "acconvert.h"
+#include "acnamesp.h"
 
 #define _COMPONENT          ACPI_PARSER
 ACPI_MODULE_NAME("psobject")

@@ -549,6 +550,21 @@ acpi_ps_complete_op(struct acpi_walk_sta
 
 		do {
 			if (*op) {
+				/*
+				 * These Opcodes need to be removed from the namespace because they
+				 * get created even if these opcodes cannot be created due to
+				 * errors.
+				 */
+				if (((*op)->common.aml_opcode == AML_REGION_OP)
+				    || ((*op)->common.aml_opcode ==
+					AML_DATA_REGION_OP)) {
+					acpi_ns_delete_children((*op)->common.
+								node);
+					acpi_ns_remove_node((*op)->common.node);
+					(*op)->common.node = NULL;
+					acpi_ps_delete_parse_tree(*op);
+				}
+
 				status2 =
 				    acpi_ps_complete_this_op(walk_state, *op);
 				if (ACPI_FAILURE(status2)) {

@@ -574,6 +590,20 @@ acpi_ps_complete_op(struct acpi_walk_sta
 #endif
 		walk_state->prev_op = NULL;
 		walk_state->prev_arg_types = walk_state->arg_types;
+
+		if (walk_state->parse_flags & ACPI_PARSE_MODULE_LEVEL) {
+			/*
+			 * There was something that went wrong while executing code at the
+			 * module-level. We need to skip parsing whatever caused the
+			 * error and keep going. One runtime error during the table load
+			 * should not cause the entire table to not be loaded. This is
+			 * because there could be correct AML beyond the parts that caused
+			 * the runtime error.
+			 */
+			ACPI_ERROR((AE_INFO,
+				    "Ignore error and continue table load"));
+			return_ACPI_STATUS(AE_OK);
+		}
 		return_ACPI_STATUS(status);
 	}
 

@@ -182,20 +182,20 @@ acpi_ut_prefixed_namespace_error(const c
 	switch (lookup_status) {
 	case AE_ALREADY_EXISTS:
 
-		acpi_os_printf(ACPI_MSG_BIOS_ERROR);
+		acpi_os_printf("\n" ACPI_MSG_BIOS_ERROR);
 		message = "Failure creating";
 		break;
 
 	case AE_NOT_FOUND:
 
-		acpi_os_printf(ACPI_MSG_BIOS_ERROR);
-		message = "Failure looking up";
+		acpi_os_printf("\n" ACPI_MSG_BIOS_ERROR);
+		message = "Could not resolve";
 		break;
 
 	default:
 
-		acpi_os_printf(ACPI_MSG_ERROR);
-		message = "Failure looking up";
+		acpi_os_printf("\n" ACPI_MSG_ERROR);
+		message = "Failure resolving";
 		break;
 	}
 

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

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

From: Lukas Czerner <[email protected]>

commit eee597ac931305eff3d3fd1d61d6aae553bc0984 upstream.

Currently in ext4_punch_hole we're going to skip the mtime update if there are no actual blocks to release. However we've actually modified the file by zeroing the partial block so the mtime should be updated.

Moreover the sync and datasync handling is skipped as well, which is also wrong. Fix it.

---
 fs/ext4/inode.c |   40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

@@ -4298,28 +4298,28 @@ int ext4_punch_hole(struct inode *inode,
 		EXT4_BLOCK_SIZE_BITS(sb);
 	stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
 
-	/* If there are no blocks to remove, return now */
-	if (first_block >= stop_block)
-		goto out_stop;
-
-	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode);
-
-	ret = ext4_es_remove_extent(inode, first_block,
-				    stop_block - first_block);
-	if (ret) {
-		up_write(&EXT4_I(inode)->i_data_sem);
-		goto out_stop;
-	}
+	/* If there are blocks to remove, do it */
+	if (stop_block > first_block) {
+
+		down_write(&EXT4_I(inode)->i_data_sem);
+		ext4_discard_preallocations(inode);
 
-	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		ret = ext4_ext_remove_space(inode, first_block,
-					    stop_block - 1);
-	else
-		ret = ext4_ind_remove_space(handle, inode, first_block,
-					    stop_block);
+		ret = ext4_es_remove_extent(inode, first_block,
+					    stop_block - first_block);
+		if (ret) {
+			up_write(&EXT4_I(inode)->i_data_sem);
+			goto out_stop;
+		}
+
+		if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+			ret = ext4_ext_remove_space(inode, first_block,
+						    stop_block - 1);
+		else
+			ret = ext4_ind_remove_space(handle, inode, first_block,
+						    stop_block);
 
-	up_write(&EXT4_I(inode)->i_data_sem);
+		up_write(&EXT4_I(inode)->i_data_sem);
+	}
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 

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

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

From: Theodore Ts'o <[email protected]>

commit 117166efb1ee8f13c38f9e96b258f16d4923f888 upstream.

The inline data feature was implemented before we added support for external inodes for xattrs. It makes no sense to support that combination, but the problem is that there are a number of extended attribute checks that are skipped if e_value_inum is non-zero.

Unfortunately, the inline data code is completely e_value_inum unaware, and attempts to interpret the xattr fields as if it were an inline xattr --- at which point, Hilarty Ensues.

This addresses CVE-2018-11412.

https://bugzilla.kernel.org/show_bug.cgi?id=199803

---
 fs/ext4/inline.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -144,6 +144,12 @@ int ext4_find_inline_data_nolock(struct
 		goto out;
 
 	if (!is.s.not_found) {
+		if (is.s.here->e_value_inum) {
+			EXT4_ERROR_INODE(inode, "inline data xattr refers "
+					 "to an external xattr inode");
+			error = -EFSCORRUPTED;
+			goto out;
+		}
 		EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
 					(void *)ext4_raw_inode(&is.iloc));
 		EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE +

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

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

From: Theodore Ts'o <[email protected]>

commit 8a2b307c21d4b290e3cbe33f768f194286d07c23 upstream.

Ext4 will always create ext4 extended attributes which do not have a value (where e_value_size is zero) with e_value_offs set to zero. In most places e_value_offs will not be used in a substantive way if e_value_size is zero.

There was one exception to this, which is in ext4_xattr_set_entry(), where if there is a maliciously crafted file system where there is an extended attribute with e_value_offs is non-zero and e_value_size is 0, the attempt to remove this xattr will result in a negative value getting passed to memmove, leading to the following sadness:

[   41.225365] EXT4-fs (loop0): mounted filesystem with ordered data mode. Opts: (null)
[   44.538641] BUG: unable to handle kernel paging request at ffff9ec9a3000000
[   44.538733] IP: __memmove+0x81/0x1a0
[   44.538755] PGD 1249bd067 P4D 1249bd067 PUD 1249c1067 PMD 80000001230000e1
[   44.538793] Oops: 0003 [#1] SMP PTI
[   44.539074] CPU: 0 PID: 1470 Comm: poc Not tainted 4.16.0-rc1+ #1
    ...
[   44.539475] Call Trace:
[   44.539832]  ext4_xattr_set_entry+0x9e7/0xf80
    ...
[   44.539972]  ext4_xattr_block_set+0x212/0xea0
    ...
[   44.540041]  ext4_xattr_set_handle+0x514/0x610
[   44.540065]  ext4_xattr_set+0x7f/0x120
[   44.540090]  __vfs_removexattr+0x4d/0x60
[   44.540112]  vfs_removexattr+0x75/0xe0
[   44.540132]  removexattr+0x4d/0x80
    ...
[   44.540279]  path_removexattr+0x91/0xb0
[   44.540300]  SyS_removexattr+0xf/0x20
[   44.540322]  do_syscall_64+0x71/0x120
[   44.540344]  entry_SYSCALL_64_after_hwframe+0x21/0x86

https://bugzilla.kernel.org/show_bug.cgi?id=199347

This addresses CVE-2018-10840.

---
 fs/ext4/xattr.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1688,7 +1688,7 @@ static int ext4_xattr_set_entry(struct e
 
 	/* No failures allowed past this point. */
 
-	if (!s->not_found && here->e_value_offs) {
+	if (!s->not_found && here->e_value_size && here->e_value_offs) {
 		/* Remove the old value. */
 		void *first_val = s->base + min_offs;
 		size_t offs = le16_to_cpu(here->e_value_offs);

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

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

From: Jan Kara <[email protected]>

commit 4f2f76f751433908364ccff82f437a57d0e6e9b7 upstream.

ext4_resize_fs() has an off-by-one bug when checking whether growing of a filesystem will not overflow inode count. As a result it allows a filesystem with 8192 inodes per group to grow to 64TB which overflows inode count to 0 and makes filesystem unusable. Fix it.

---
 fs/ext4/resize.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1933,7 +1933,7 @@ retry:
 		return 0;
 
 	n_group = ext4_get_group_number(sb, n_blocks_count - 1);
-	if (n_group > (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) {
+	if (n_group >= (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) {
 		ext4_warning(sb, "resize would cause inodes_count overflow");
 		return -EINVAL;
 	}

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

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

From: Josef Bacik <[email protected]>

commit c3f7c9397609705ef848cc98a5fb429b3e90c3c4 upstream.

I messed up changing the size of an NBD device while it was connected by not actually updating the device or doing the uevent. Fix this by updating everything if we're connected and we change the size.

---
 drivers/block/nbd.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -246,6 +246,8 @@ static void nbd_size_set(struct nbd_devi
 	struct nbd_config *config = nbd->config;
 	config->blksize = blocksize;
 	config->bytesize = blocksize * nr_blocks;
+	if (nbd->task_recv != NULL)
+		nbd_size_update(nbd);
 }
 
 static void nbd_complete_rq(struct request *req)

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

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

From: Keith Busch <[email protected]>

commit cc1d5e749a2e1cf59fa940b976181e631d6985e1 upstream.

AER handling expects a successful return from slot_reset means the driver made the device functional again. The nvme driver had been using an asynchronous reset to recover the device, so the device may still be initializing after control is returned to the AER handler. This creates problems for subsequent event handling, causing the initializion to fail.

This patch fixes that by syncing the controller reset before returning to the AER driver, and reporting the true state of the reset.

---
 drivers/nvme/host/pci.c |   11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

@@ -2679,8 +2679,15 @@ static pci_ers_result_t nvme_slot_reset(
 
 	dev_info(dev->ctrl.device, "restart after slot reset\n");
 	pci_restore_state(pdev);
-	nvme_reset_ctrl(&dev->ctrl);
-	return PCI_ERS_RESULT_RECOVERED;
+	nvme_reset_ctrl_sync(&dev->ctrl);
+
+	switch (dev->ctrl.state) {
+	case NVME_CTRL_LIVE:
+	case NVME_CTRL_ADMIN_ONLY:
+		return PCI_ERS_RESULT_RECOVERED;
+	default:
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
 }
 
 static void nvme_error_resume(struct pci_dev *pdev)

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

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

From: Dou Liyang <[email protected]>

commit 838d76d63ec4eaeaa12bedfa50f261480f615200 upstream.

The vector_alloc tracepont reversed the reserved and ret aggs, that made the trace print wrong. Exchange them.

---
 arch/x86/include/asm/trace/irq_vectors.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -236,7 +236,7 @@ TRACE_EVENT(vector_alloc,
 	TP_PROTO(unsigned int irq, unsigned int vector, bool reserved,
 		 int ret),
 
-	TP_ARGS(irq, vector, ret, reserved),
+	TP_ARGS(irq, vector, reserved, ret),
 
 	TP_STRUCT__entry(
 		__field(	unsigned int,	irq		)

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

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

From: Thomas Gleixner <[email protected]>

commit 80ae7b1a918e78b0bae88b0c0ad413d3fdced968 upstream.

Several people observed the WARN_ON() in irq_matrix_free() which triggers when the caller tries to free an vector which is not in the allocation range. Song provided the trace information which allowed to decode the root cause.

The rework of the vector allocation mechanism failed to preserve a sanity check, which prevents setting a new target vector/CPU when the previous affinity change has not fully completed.

As a result a half finished affinity change can be overwritten, which can cause the leak of a irq descriptor pointer on the previous target CPU and double enqueue of the hlist head into the cleanup lists of two or more CPUs. After one CPU cleaned up its vector the next CPU will invoke the cleanup handler with vector 0, which triggers the out of range warning in the matrix allocator.

Prevent this by checking the apic_data of the interrupt whether the move_in_progress flag is false and the hlist node is not hashed. Return -EBUSY if not.

This prevents the damage and restores the behaviour before the vector allocation rework, but due to other changes in that area it also widens the chance that user space can observe -EBUSY. In theory this should be fine, but actually not all user space tools handle -EBUSY correctly. Addressing that is not part of this fix, but will be addressed in follow up patches.

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

@@ -235,6 +235,15 @@ static int allocate_vector(struct irq_da
 	if (vector && cpu_online(cpu) && cpumask_test_cpu(cpu, dest))
 		return 0;
 
+	/*
+	 * Careful here. @apicd might either have move_in_progress set or
+	 * be enqueued for cleanup. Assigning a new vector would either
+	 * leave a stale vector on some CPU around or in case of a pending
+	 * cleanup corrupt the hlist.
+	 */
+	if (apicd->move_in_progress || !hlist_unhashed(&apicd->clist))
+		return -EBUSY;
+
 	vector = irq_matrix_alloc(vector_matrix, dest, resvd, &cpu);
 	if (vector > 0)
 		apic_update_vector(irqd, vector, cpu);

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

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

From: Thomas Gleixner <[email protected]>

commit c0255770ccdc77ef2184d2a0a2e0cde09d2b44a4 upstream.

apic_ack_edge() is explicitely for handling interrupt affinity cleanup when interrupt remapping is not available or disable.

Remapped interrupts and also some of the platform specific special interrupts, e.g. UV, invoke ack_APIC_irq() directly.

To address the issue of failing an affinity update with -EBUSY the delayed affinity mechanism can be reused, but ack_APIC_irq() does not handle that. Adding this to ack_APIC_irq() is not possible, because that function is also used for exceptions and directly handled interrupts like IPIs.

Create a new function, which just contains the conditional invocation of irq_move_irq() and the final ack_APIC_irq().

Reuse the new function in apic_ack_edge().

Preparatory change for the real fix.

---
 arch/x86/include/asm/apic.h   |    2 ++
 arch/x86/kernel/apic/vector.c |    9 +++++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

@@ -436,6 +436,8 @@ static inline void apic_set_eoi_write(vo
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
+extern void apic_ack_irq(struct irq_data *data);
+
 static inline void ack_APIC_irq(void)
 {
 	/*

@@ -809,13 +809,18 @@ static int apic_retrigger_irq(struct irq
 	return 1;
 }
 
-void apic_ack_edge(struct irq_data *irqd)
+void apic_ack_irq(struct irq_data *irqd)
 {
-	irq_complete_move(irqd_cfg(irqd));
 	irq_move_irq(irqd);
 	ack_APIC_irq();
 }
 
+void apic_ack_edge(struct irq_data *irqd)
+{
+	irq_complete_move(irqd_cfg(irqd));
+	apic_ack_irq(irqd);
+}
+
 static struct irq_chip lapic_controller = {
 	.name			= "APIC",
 	.irq_ack		= apic_ack_edge,

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

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

From: Thomas Gleixner <[email protected]>

commit 2b04e46d8d0b9b7ac08ded672e3eab823f01d77a upstream.

To address the EBUSY fail of interrupt affinity settings in case that the previous setting has not been cleaned up yet, use the new apic_ack_irq() function instead of directly invoking ack_APIC_irq().

Preparatory change for the real fix

---
 arch/x86/kernel/apic/io_apic.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1851,7 +1851,7 @@ static void ioapic_ir_ack_level(struct i
 	 * intr-remapping table entry. Hence for the io-apic
 	 * EOI we use the pin number.
 	 */
-	ack_APIC_irq();
+	apic_ack_irq(irq_data);
 	eoi_ioapic_pin(data->entry.vector, data);
 }
 

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

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

From: Thomas Gleixner <[email protected]>

commit a33a5d2d16cb84bea8d5f5510f3a41aa48b5c467 upstream.

The generic pending interrupt mechanism moves interrupts from the interrupt handler on the original target CPU to the new destination CPU. This is required for x86 and ia64 due to the way the interrupt delivery and acknowledge works if the interrupts are not remapped.

However that update can fail for various reasons. Some of them are valid reasons to discard the pending update, but the case, when the previous move has not been fully cleaned up is not a legit reason to fail.

Check the return value of irq_do_set_affinity() for -EBUSY, which indicates a pending cleanup, and rearm the pending move in the irq dexcriptor so it's tried again when the next interrupt arrives.

---
 kernel/irq/migration.c |   24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

@@ -38,17 +38,18 @@ bool irq_fixup_move_pending(struct irq_d
 void irq_move_masked_irq(struct irq_data *idata)
 {
 	struct irq_desc *desc = irq_data_to_desc(idata);
-	struct irq_chip *chip = desc->irq_data.chip;
+	struct irq_data *data = &desc->irq_data;
+	struct irq_chip *chip = data->chip;
 
-	if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
+	if (likely(!irqd_is_setaffinity_pending(data)))
 		return;
 
-	irqd_clr_move_pending(&desc->irq_data);
+	irqd_clr_move_pending(data);
 
 	/*
 	 * Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
 	 */
-	if (irqd_is_per_cpu(&desc->irq_data)) {
+	if (irqd_is_per_cpu(data)) {
 		WARN_ON(1);
 		return;
 	}

@@ -73,9 +74,20 @@ void irq_move_masked_irq(struct irq_data
 	 * For correct operation this depends on the caller
 	 * masking the irqs.
 	 */
-	if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
-		irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
+	if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) {
+		int ret;
 
+		ret = irq_do_set_affinity(data, desc->pending_mask, false);
+		/*
+		 * If the there is a cleanup pending in the underlying
+		 * vector management, reschedule the move for the next
+		 * interrupt. Leave desc->pending_mask intact.
+		 */
+		if (ret == -EBUSY) {
+			irqd_set_move_pending(data);
+			return;
+		}
+	}
 	cpumask_clear(desc->pending_mask);
 }
 

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

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

From: Thomas Gleixner <[email protected]>

commit 12f47073a40f6aa75119d8f5df4077b7f334cced upstream.

The case that interrupt affinity setting fails with -EBUSY can be handled in the kernel completely by using the already available generic pending infrastructure.

If a irq_chip::set_affinity() fails with -EBUSY, handle it like the interrupts for which irq_chip::set_affinity() can only be invoked from interrupt context. Copy the new affinity mask to irq_desc::pending_mask and set the affinity pending bit. The next raised interrupt for the affected irq will check the pending bit and try to set the new affinity from the handler. This avoids that -EBUSY is returned when an affinity change is requested from user space and the previous change has not been cleaned up. The new affinity will take effect when the next interrupt is raised from the device.