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

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

[ Upstream commit 7c0db24cc431e2196d98a5d5ddaa9088e2fcbfe5 ]

The GPIO interrupt controller on the espressobin board only supports edge interrupts. If one enables the use of hardware interrupts in the device tree for the 88E6341, it is possible to miss an edge. When this happens, the INTn pin on the Marvell switch is stuck low and no further interrupts occur.

I found after adding debug statements to mv88e6xxx_g1_irq_thread_work() that there is a race in handling device interrupts (e.g. PHY link interrupts). Some interrupts are directly cleared by reading the Global 1 status register. However, the device interrupt flag, for example, is not cleared until all the unmasked SERDES and PHY ports are serviced. This is done by reading the relevant SERDES and PHY status register.

The code only services interrupts whose status bit is set at the time of reading its status register. If an interrupt event occurs after its status is read and before all interrupts are serviced, then this event will not be serviced and the INTn output pin will remain low.

This is not a problem with polling or level interrupts since the handler will be called again to process the event. However, it's a big problem when using level interrupts.

The fix presented here is to add a loop around the code servicing switch interrupts. If any pending interrupts remain after the current set has been handled, we loop and process the new set. If there are no pending interrupts after servicing, we are sure that INTn has gone high and we will get an edge when a new event occurs.

Tested on espressobin board.

Fixes: dc30c35be720 ("net: dsa: mv88e6xxx: Implement interrupt support.") Signed-off-by: John David Anglin dave.anglin@bell.net Tested-by: Andrew Lunn andrew@lunn.ch Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/mv88e6xxx/chip.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 258918d8a4165..9f697a5b8e3df 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -261,6 +261,7 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) unsigned int sub_irq; unsigned int n; u16 reg; + u16 ctl1; int err;

mutex_lock(&chip->reg_lock); @@ -270,13 +271,28 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) if (err) goto out;

- for (n = 0; n < chip->g1_irq.nirqs; ++n) { - if (reg & (1 << n)) { - sub_irq = irq_find_mapping(chip->g1_irq.domain, n); - handle_nested_irq(sub_irq); - ++nhandled; + do { + for (n = 0; n < chip->g1_irq.nirqs; ++n) { + if (reg & (1 << n)) { + sub_irq = irq_find_mapping(chip->g1_irq.domain, + n); + handle_nested_irq(sub_irq); + ++nhandled; + } } - } + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &ctl1); + if (err) + goto unlock; + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &reg); +unlock: + mutex_unlock(&chip->reg_lock); + if (err) + goto out; + ctl1 &= GENMASK(chip->g1_irq.nirqs, 0); + } while (reg & ctl1); + out: return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE); }

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

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

[ Upstream commit 9060cb719e61b685ec0102574e10337fa5f445ea ]

KASAN has found use-after-free in sockfs_setattr. The existed commit 6d8c50dcb029 ("socket: close race condition between sock_close() and sockfs_setattr()") is to fix this simillar issue, but it seems to ignore that crypto module forgets to set the sk to NULL after af_alg_release.

KASAN report details as below: BUG: KASAN: use-after-free in sockfs_setattr+0x120/0x150 Write of size 4 at addr ffff88837b956128 by task syz-executor0/4186

CPU: 2 PID: 4186 Comm: syz-executor0 Not tainted xxx + #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 Call Trace: dump_stack+0xca/0x13e print_address_description+0x79/0x330 ? vprintk_func+0x5e/0xf0 kasan_report+0x18a/0x2e0 ? sockfs_setattr+0x120/0x150 sockfs_setattr+0x120/0x150 ? sock_register+0x2d0/0x2d0 notify_change+0x90c/0xd40 ? chown_common+0x2ef/0x510 chown_common+0x2ef/0x510 ? chmod_common+0x3b0/0x3b0 ? __lock_is_held+0xbc/0x160 ? __sb_start_write+0x13d/0x2b0 ? __mnt_want_write+0x19a/0x250 do_fchownat+0x15c/0x190 ? __ia32_sys_chmod+0x80/0x80 ? trace_hardirqs_on_thunk+0x1a/0x1c __x64_sys_fchownat+0xbf/0x160 ? lockdep_hardirqs_on+0x39a/0x5e0 do_syscall_64+0xc8/0x580 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x462589 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fb4b2c83c58 EFLAGS: 00000246 ORIG_RAX: 0000000000000104 RAX: ffffffffffffffda RBX: 000000000072bfa0 RCX: 0000000000462589 RDX: 0000000000000000 RSI: 00000000200000c0 RDI: 0000000000000007 RBP: 0000000000000005 R08: 0000000000001000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fb4b2c846bc R13: 00000000004bc733 R14: 00000000006f5138 R15: 00000000ffffffff

Allocated by task 4185: kasan_kmalloc+0xa0/0xd0 __kmalloc+0x14a/0x350 sk_prot_alloc+0xf6/0x290 sk_alloc+0x3d/0xc00 af_alg_accept+0x9e/0x670 hash_accept+0x4a3/0x650 __sys_accept4+0x306/0x5c0 __x64_sys_accept4+0x98/0x100 do_syscall_64+0xc8/0x580 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 4184: __kasan_slab_free+0x12e/0x180 kfree+0xeb/0x2f0 __sk_destruct+0x4e6/0x6a0 sk_destruct+0x48/0x70 __sk_free+0xa9/0x270 sk_free+0x2a/0x30 af_alg_release+0x5c/0x70 __sock_release+0xd3/0x280 sock_close+0x1a/0x20 __fput+0x27f/0x7f0 task_work_run+0x136/0x1b0 exit_to_usermode_loop+0x1a7/0x1d0 do_syscall_64+0x461/0x580 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Syzkaller reproducer: r0 = perf_event_open(&(0x7f0000000000)={0x0, 0x70, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, @perf_config_ext}, 0x0, 0x0, 0xffffffffffffffff, 0x0) r1 = socket$alg(0x26, 0x5, 0x0) getrusage(0x0, 0x0) bind(r1, &(0x7f00000001c0)=@alg={0x26, 'hash\x00', 0x0, 0x0, 'sha256-ssse3\x00'}, 0x80) r2 = accept(r1, 0x0, 0x0) r3 = accept4$unix(r2, 0x0, 0x0, 0x0) r4 = dup3(r3, r0, 0x0) fchownat(r4, &(0x7f00000000c0)='\x00', 0x0, 0x0, 0x1000)

Fixes: 6d8c50dcb029 ("socket: close race condition between sock_close() and sockfs_setattr()") Signed-off-by: Mao Wenan maowenan@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- crypto/af_alg.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 17eb09d222ff4..ec78a04eb136e 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -122,8 +122,10 @@ static void alg_do_release(const struct af_alg_type *type, void *private)

int af_alg_release(struct socket *sock) { - if (sock->sk) + if (sock->sk) { sock_put(sock->sk); + sock->sk = NULL; + } return 0; } EXPORT_SYMBOL_GPL(af_alg_release);

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

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

[ Upstream commit e75913c93f7cd5f338ab373c34c93a655bd309cb ]

Follow those steps: # ip addr add 2001:123::1/32 dev eth0 # ip addr add 2001:123:456::2/64 dev eth0 # ip addr del 2001:123::1/32 dev eth0 # ip addr del 2001:123:456::2/64 dev eth0 and then prefix route of 2001:123::1/32 will still exist.

This is because ipv6_prefix_equal in check_cleanup_prefix_route func does not check whether two IPv6 addresses have the same prefix length. If the prefix of one address starts with another shorter address prefix, even though their prefix lengths are different, the return value of ipv6_prefix_equal is true.

Here I add a check of whether two addresses have the same prefix to decide whether their prefixes are equal.

Fixes: 5b84efecb7d9 ("ipv6 addrconf: don't cleanup prefix route for IFA_F_NOPREFIXROUTE") Signed-off-by: Zhiqiang Liu liuzhiqiang26@huawei.com Reported-by: Wenhao Zhang zhangwenhao8@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/addrconf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3dfc50cd86d68..c57efd5c5b387 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1148,7 +1148,8 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa == ifp) continue; - if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr, + if (ifa->prefix_len != ifp->prefix_len || + !ipv6_prefix_equal(&ifa->addr, &ifp->addr, ifp->prefix_len)) continue; if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE))

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

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

[ Upstream commit c09551c6ff7fe16a79a42133bcecba5fc2fc3291 ]

According to the algorithm described in the comment block at the beginning of ip_rt_send_redirect, the host should try to send 'ip_rt_redirect_number' ICMP redirect packets with an exponential backoff and then stop sending them at all assuming that the destination ignores redirects. If the device has previously sent some ICMP error packets that are rate-limited (e.g TTL expired) and continues to receive traffic, the redirect packets will never be transmitted. This happens since peer->rate_tokens will be typically greater than 'ip_rt_redirect_number' and so it will never be reset even if the redirect silence timeout (ip_rt_redirect_silence) has elapsed without receiving any packet requiring redirects.

Fix it by using a dedicated counter for the number of ICMP redirect packets that has been sent by the host

I have not been able to identify a given commit that introduced the issue since ip_rt_send_redirect implements the same rate-limiting algorithm from commit 1da177e4c3f4 ("Linux-2.6.12-rc2")

Signed-off-by: Lorenzo Bianconi lorenzo.bianconi@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/inetpeer.h | 1 + net/ipv4/inetpeer.c | 1 + net/ipv4/route.c | 7 +++++-- 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 00b5e7825508a..74ff688568a0c 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -39,6 +39,7 @@ struct inet_peer {

u32 metrics[RTAX_MAX]; u32 rate_tokens; /* rate limiting for ICMP */ + u32 n_redirects; unsigned long rate_last; /* * Once inet_peer is queued for deletion (refcnt == 0), following field diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d757b9642d0d1..be778599bfedf 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -216,6 +216,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; + p->n_redirects = 0; /* 60*HZ is arbitrary, but chosen enough high so that the first * calculation of tokens is at its maximum. */ diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8501554e96a4a..436b46c0e687f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -887,13 +887,15 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ - if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) + if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) { peer->rate_tokens = 0; + peer->n_redirects = 0; + }

/* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ - if (peer->rate_tokens >= ip_rt_redirect_number) { + if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; goto out_put_peer; } @@ -910,6 +912,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->rate_tokens; + ++peer->n_redirects; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && peer->rate_tokens == ip_rt_redirect_number)

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

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

[ Upstream commit 8a7493e58ad688eb23b81e45461c5d314f4402f1 ]

We are saving the status of EEE even before we try to enable it. This leads to a race with XMIT function that tries to arm EEE timer before we set it up.

Fix this by only saving the EEE parameters after all operations are performed with success.

Signed-off-by: Jose Abreu joabreu@synopsys.com Fixes: d765955d2ae0 ("stmmac: add the Energy Efficient Ethernet support") Cc: Joao Pinto jpinto@synopsys.com Cc: David S. Miller davem@davemloft.net Cc: Giuseppe Cavallaro peppe.cavallaro@st.com Cc: Alexandre Torgue alexandre.torgue@st.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../ethernet/stmicro/stmmac/stmmac_ethtool.c | 22 ++++++++++--------- 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 5710864fa8090..9caf79ba5ef16 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -692,25 +692,27 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, struct ethtool_eee *edata) { struct stmmac_priv *priv = netdev_priv(dev); + int ret;

- priv->eee_enabled = edata->eee_enabled; - - if (!priv->eee_enabled) + if (!edata->eee_enabled) { stmmac_disable_eee_mode(priv); - else { + } else { /* We are asking for enabling the EEE but it is safe * to verify all by invoking the eee_init function. * In case of failure it will return an error. */ - priv->eee_enabled = stmmac_eee_init(priv); - if (!priv->eee_enabled) + edata->eee_enabled = stmmac_eee_init(priv); + if (!edata->eee_enabled) return -EOPNOTSUPP; - - /* Do not change tx_lpi_timer in case of failure */ - priv->tx_lpi_timer = edata->tx_lpi_timer; }

- return phy_ethtool_set_eee(dev->phydev, edata); + ret = phy_ethtool_set_eee(dev->phydev, edata); + if (ret) + return ret; + + priv->eee_enabled = edata->eee_enabled; + priv->tx_lpi_timer = edata->tx_lpi_timer; + return 0; }

static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv)

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

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

[ Upstream commit d5be7f632bad0f489879eed0ff4b99bd7fe0b74c ]

Syzkaller again found a path to a kernel crash through bad gso input. By building an excessively large packet to cause an skb field to wrap.

If VIRTIO_NET_HDR_F_NEEDS_CSUM was set this would have been dropped in skb_partial_csum_set.

GSO packets that do not set checksum offload are suspicious and rare. Most callers of virtio_net_hdr_to_skb already pass them to skb_probe_transport_header.

Move that test forward, change it to detect parse failure and drop packets on failure as those cleary are not one of the legitimate VIRTIO_NET_HDR_GSO types.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.") Fixes: f43798c27684 ("tun: Allow GSO using virtio_net_hdr") Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: Willem de Bruijn willemb@google.com Reviewed-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/skbuff.h | 2 +- include/linux/virtio_net.h | 9 +++++++++ 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5d69e208e8d91..a404d475acee3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2392,7 +2392,7 @@ static inline void skb_probe_transport_header(struct sk_buff *skb,

if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); - else + else if (offset_hint >= 0) skb_set_transport_header(skb, offset_hint); }

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index cb462f9ab7dd5..71f2394abbf7c 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -57,6 +57,15 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,

if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; + } else { + /* gso packets without NEEDS_CSUM do not set transport_offset. + * probe and drop if does not match one of the above types. + */ + if (gso_type) { + skb_probe_transport_header(skb, -1); + if (!skb_transport_header_was_set(skb)) + return -EINVAL; + } }

if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {

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

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

[ Upstream commit 816db7663565cd23f74ed3d5c9240522e3fb0dda ]

When fail, translate_desc() returns negative value, otherwise the number of iovs. So we should fail when the return value is negative instead of a blindly check against zero.

Detected by CoverityScan, CID# 1442593: Control flow issues (DEADCODE)

Fixes: cc5e71075947 ("vhost: log dirty page correctly") Acked-by: Michael S. Tsirkin mst@redhat.com Reported-by: Stephen Hemminger stephen@networkplumber.org Signed-off-by: Jason Wang jasowang@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/vhost/vhost.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index cf82e72663976..5eaeca805c95c 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1784,7 +1784,7 @@ static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len)

ret = translate_desc(vq, (uintptr_t)vq->used + used_offset, len, iov, 64, VHOST_ACCESS_WO); - if (ret) + if (ret < 0) return ret;

for (i = 0; i < ret; i++) {

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

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

[ Upstream commit 4179cb5a4c924cd233eaadd081882425bc98f44e ]

netif_rx() must be called under a strict contract.

At device dismantle phase, core networking clears IFF_UP and flush_all_backlogs() is called after rcu grace period to make sure no incoming packet might be in a cpu backlog and still referencing the device.

Most drivers call netif_rx() from their interrupt handler, and since the interrupts are disabled at device dismantle, netif_rx() does not have to check dev->flags & IFF_UP

Virtual drivers do not have this guarantee, and must therefore make the check themselves.

Otherwise we risk use-after-free and/or crashes.

Note this patch also fixes a small issue that came with commit ce6502a8f957 ("vxlan: fix a use after free in vxlan_encap_bypass"), since the dev->stats.rx_dropped change was done on the wrong device.

Fixes: d342894c5d2f ("vxlan: virtual extensible lan") Fixes: ce6502a8f957 ("vxlan: fix a use after free in vxlan_encap_bypass") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Petr Machata petrm@mellanox.com Cc: Ido Schimmel idosch@mellanox.com Cc: Roopa Prabhu roopa@cumulusnetworks.com Cc: Stefano Brivio sbrivio@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/vxlan.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 27bd586b94b0a..9fc9aed6ca9a7 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2003,7 +2003,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; - struct net_device *dev = skb->dev; + struct net_device *dev; int len = skb->len;

tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); @@ -2023,9 +2023,15 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, #endif }

+ rcu_read_lock(); + dev = skb->dev; + if (unlikely(!(dev->flags & IFF_UP))) { + kfree_skb(skb); + goto drop; + } + if (dst_vxlan->cfg.flags & VXLAN_F_LEARN) - vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source, 0, - vni); + vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni);

u64_stats_update_begin(&tx_stats->syncp); tx_stats->tx_packets++; @@ -2038,8 +2044,10 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, rx_stats->rx_bytes += len; u64_stats_update_end(&rx_stats->syncp); } else { +drop: dev->stats.rx_dropped++; } + rcu_read_unlock(); }

static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev,

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

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

[ Upstream commit 04c03114be82194d4a4858d41dba8e286ad1787c ]

soukjin bae reported a crash in tcp_v4_err() handling ICMP_DEST_UNREACH after tcp_write_queue_head(sk) returned a NULL pointer.

Current logic should have prevented this :

if (seq != tp->snd_una || !icsk->icsk_retransmits || !icsk->icsk_backoff || fastopen) break;

Problem is the write queue might have been purged and icsk_backoff has not been cleared.

Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: soukjin bae soukjin.bae@samsung.com Acked-by: Neal Cardwell ncardwell@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 87fe44197aa1f..432dc9af11720 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2519,6 +2519,7 @@ void tcp_write_queue_purge(struct sock *sk) sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_sk(sk)->packets_out = 0; + inet_csk(sk)->icsk_backoff = 0; }

int tcp_disconnect(struct sock *sk, int flags) @@ -2567,7 +2568,6 @@ int tcp_disconnect(struct sock *sk, int flags) tp->write_seq += tp->max_window + 2; if (tp->write_seq == 0) tp->write_seq = 1; - icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;

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

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

[ Upstream commit 3bed3cc4156eedf652b4df72bdb35d4f1a2a739d ]

This patch addresses the fact that there are drivers, specifically tun, that will call into the network page fragment allocators with buffer sizes that are not cache aligned. Doing this could result in data alignment and DMA performance issues as these fragment pools are also shared with the skb allocator and any other devices that will use napi_alloc_frags or netdev_alloc_frags.

Fixes: ffde7328a36d ("net: Split netdev_alloc_frag into __alloc_page_frag and add __napi_alloc_frag") Reported-by: Jann Horn jannh@google.com Signed-off-by: Alexander Duyck alexander.h.duyck@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/skbuff.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -353,6 +353,8 @@ static void *__netdev_alloc_frag(unsigne */ void *netdev_alloc_frag(unsigned int fragsz) { + fragsz = SKB_DATA_ALIGN(fragsz); + return __netdev_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(netdev_alloc_frag); @@ -366,6 +368,8 @@ static void *__napi_alloc_frag(unsigned

void *napi_alloc_frag(unsigned int fragsz) { + fragsz = SKB_DATA_ALIGN(fragsz); + return __napi_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(napi_alloc_frag);

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

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

From: Wei Yongjun weiyongjun1@huawei.com

commit 8b2db98e814a5ec45e8800fc22ca9000ae0a517b upstream.

memory allocated by kmem_cache_alloc() should be freed using kmem_cache_free(), not kfree().

Fixes: ad669505c4e9 ("scsi: target/core: Make sure that target_wait_for_sess_cmds() waits long enough") Signed-off-by: Wei Yongjun weiyongjun1@huawei.com Reviewed-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

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

--- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -266,7 +266,7 @@ struct se_session *transport_alloc_sessi } ret = transport_init_session(se_sess); if (ret < 0) { - kfree(se_sess); + kmem_cache_free(se_sess_cache, se_sess); return ERR_PTR(ret); } se_sess->sup_prot_ops = sup_prot_ops;

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

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

From: Martin Blumenstingl martin.blumenstingl@googlemail.com

commit 83e418a805d880a8b18add07f94d19b2a5a80307 upstream.

Commit bb364890323cca ("mmc: meson-gx: Free irq in release() callback") changed the _probe code to use request_threaded_irq() instead of devm_request_threaded_irq(). Unfortunately this removes a fallback for the interrupt name: devm_request_threaded_irq() uses the device name as fallback if the given IRQ name is NULL. request_threaded_irq() has no such fallback, thus /proc/interrupts shows "(null)" instead.

Explicitly pass the dev_name() so we get the IRQ name shown in /proc/interrupts again. While here, also fix the indentation of the request_threaded_irq() parameter list.

Fixes: bb364890323cca ("mmc: meson-gx: Free irq in release() callback") Signed-off-by: Martin Blumenstingl martin.blumenstingl@googlemail.com Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/mmc/host/meson-gx-mmc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -1286,7 +1286,8 @@ static int meson_mmc_probe(struct platfo host->regs + SD_EMMC_IRQ_EN);

ret = request_threaded_irq(host->irq, meson_mmc_irq, - meson_mmc_irq_thread, IRQF_SHARED, NULL, host); + meson_mmc_irq_thread, IRQF_SHARED, + dev_name(&pdev->dev), host); if (ret) goto err_init_clk;

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

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

From: Scott Mayhew smayhew@redhat.com

commit e7afe6c1d486b516ed586dcc10b3e7e3e85a9c2b upstream.

While trying to reproduce a reported kernel panic on arm64, I discovered that AUTH_GSS basically doesn't work at all with older enctypes on arm64 systems with CONFIG_VMAP_STACK enabled. It turns out there still a few places using stack memory with scatterlists, causing krb5_encrypt() and krb5_decrypt() to produce incorrect results (or a BUG if CONFIG_DEBUG_SG is enabled).

Tested with cthon on v4.0/v4.1/v4.2 with krb5/krb5i/krb5p using des3-cbc-sha1 and arcfour-hmac-md5.

Signed-off-by: Scott Mayhew smayhew@redhat.com Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields bfields@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/sunrpc/auth_gss/gss_krb5_seqnum.c | 49 ++++++++++++++++++++++++++-------- 1 file changed, 38 insertions(+), 11 deletions(-)

--- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -44,7 +44,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *k unsigned char *cksum, unsigned char *buf) { struct crypto_skcipher *cipher; - unsigned char plain[8]; + unsigned char *plain; s32 code;

dprintk("RPC: %s:\n", __func__); @@ -53,6 +53,10 @@ krb5_make_rc4_seq_num(struct krb5_ctx *k if (IS_ERR(cipher)) return PTR_ERR(cipher);

+ plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; + plain[0] = (unsigned char) ((seqnum >> 24) & 0xff); plain[1] = (unsigned char) ((seqnum >> 16) & 0xff); plain[2] = (unsigned char) ((seqnum >> 8) & 0xff); @@ -69,6 +73,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *k code = krb5_encrypt(cipher, cksum, plain, buf, 8); out: crypto_free_skcipher(cipher); + kfree(plain); return code; } s32 @@ -78,12 +83,17 @@ krb5_make_seq_num(struct krb5_ctx *kctx, u32 seqnum, unsigned char *cksum, unsigned char *buf) { - unsigned char plain[8]; + unsigned char *plain; + s32 code;

if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) return krb5_make_rc4_seq_num(kctx, direction, seqnum, cksum, buf);

+ plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; + plain[0] = (unsigned char) (seqnum & 0xff); plain[1] = (unsigned char) ((seqnum >> 8) & 0xff); plain[2] = (unsigned char) ((seqnum >> 16) & 0xff); @@ -94,7 +104,9 @@ krb5_make_seq_num(struct krb5_ctx *kctx, plain[6] = direction; plain[7] = direction;

- return krb5_encrypt(key, cksum, plain, buf, 8); + code = krb5_encrypt(key, cksum, plain, buf, 8); + kfree(plain); + return code; }

static s32 @@ -102,7 +114,7 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kc unsigned char *buf, int *direction, s32 *seqnum) { struct crypto_skcipher *cipher; - unsigned char plain[8]; + unsigned char *plain; s32 code;

dprintk("RPC: %s:\n", __func__); @@ -115,20 +127,28 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kc if (code) goto out;

+ plain = kmalloc(8, GFP_NOFS); + if (!plain) { + code = -ENOMEM; + goto out; + } + code = krb5_decrypt(cipher, cksum, buf, plain, 8); if (code) - goto out; + goto out_plain;

if ((plain[4] != plain[5]) || (plain[4] != plain[6]) || (plain[4] != plain[7])) { code = (s32)KG_BAD_SEQ; - goto out; + goto out_plain; }

*direction = plain[4];

*seqnum = ((plain[0] << 24) | (plain[1] << 16) | (plain[2] << 8) | (plain[3])); +out_plain: + kfree(plain); out: crypto_free_skcipher(cipher); return code; @@ -141,26 +161,33 @@ krb5_get_seq_num(struct krb5_ctx *kctx, int *direction, u32 *seqnum) { s32 code; - unsigned char plain[8]; struct crypto_skcipher *key = kctx->seq; + unsigned char *plain;

dprintk("RPC: krb5_get_seq_num:\n");

if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) return krb5_get_rc4_seq_num(kctx, cksum, buf, direction, seqnum); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM;

if ((code = krb5_decrypt(key, cksum, buf, plain, 8))) - return code; + goto out;

if ((plain[4] != plain[5]) || (plain[4] != plain[6]) || - (plain[4] != plain[7])) - return (s32)KG_BAD_SEQ; + (plain[4] != plain[7])) { + code = (s32)KG_BAD_SEQ; + goto out; + }

*direction = plain[4];

*seqnum = ((plain[0]) | (plain[1] << 8) | (plain[2] << 16) | (plain[3] << 24));

- return 0; +out: + kfree(plain); + return code; }

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

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

From: Eric Dumazet edumazet@google.com

commit cf657d22ee1f0e887326a92169f2e28dc932fd10 upstream.

Due to quadratic behavior of x25_new_lci(), syzbot was able to trigger an rcu stall.

Fix this by not blocking BH for the whole duration of the function, and inserting a reschedule point when possible.

If we care enough, using a bitmap could get rid of the quadratic behavior.

syzbot report :

rcu: INFO: rcu_preempt self-detected stall on CPU rcu: 0-...!: (10500 ticks this GP) idle=4fa/1/0x4000000000000002 softirq=283376/283376 fqs=0 rcu: (t=10501 jiffies g=383105 q=136) rcu: rcu_preempt kthread starved for 10502 jiffies! g383105 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 ->cpu=0 rcu: RCU grace-period kthread stack dump: rcu_preempt I28928 10 2 0x80000000 Call Trace: context_switch kernel/sched/core.c:2844 [inline] __schedule+0x817/0x1cc0 kernel/sched/core.c:3485 schedule+0x92/0x180 kernel/sched/core.c:3529 schedule_timeout+0x4db/0xfd0 kernel/time/timer.c:1803 rcu_gp_fqs_loop kernel/rcu/tree.c:1948 [inline] rcu_gp_kthread+0x956/0x17a0 kernel/rcu/tree.c:2105 kthread+0x357/0x430 kernel/kthread.c:246 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352 NMI backtrace for cpu 0 CPU: 0 PID: 8759 Comm: syz-executor2 Not tainted 5.0.0-rc4+ #51 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 nmi_cpu_backtrace.cold+0x63/0xa4 lib/nmi_backtrace.c:101 nmi_trigger_cpumask_backtrace+0x1be/0x236 lib/nmi_backtrace.c:62 arch_trigger_cpumask_backtrace+0x14/0x20 arch/x86/kernel/apic/hw_nmi.c:38 trigger_single_cpu_backtrace include/linux/nmi.h:164 [inline] rcu_dump_cpu_stacks+0x183/0x1cf kernel/rcu/tree.c:1211 print_cpu_stall kernel/rcu/tree.c:1348 [inline] check_cpu_stall kernel/rcu/tree.c:1422 [inline] rcu_pending kernel/rcu/tree.c:3018 [inline] rcu_check_callbacks.cold+0x500/0xa4a kernel/rcu/tree.c:2521 update_process_times+0x32/0x80 kernel/time/timer.c:1635 tick_sched_handle+0xa2/0x190 kernel/time/tick-sched.c:161 tick_sched_timer+0x47/0x130 kernel/time/tick-sched.c:1271 __run_hrtimer kernel/time/hrtimer.c:1389 [inline] __hrtimer_run_queues+0x33e/0xde0 kernel/time/hrtimer.c:1451 hrtimer_interrupt+0x314/0x770 kernel/time/hrtimer.c:1509 local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1035 [inline] smp_apic_timer_interrupt+0x120/0x570 arch/x86/kernel/apic/apic.c:1060 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:807 </IRQ> RIP: 0010:__read_once_size include/linux/compiler.h:193 [inline] RIP: 0010:queued_write_lock_slowpath+0x13e/0x290 kernel/locking/qrwlock.c:86 Code: 00 00 fc ff df 4c 8d 2c 01 41 83 c7 03 41 0f b6 45 00 41 38 c7 7c 08 84 c0 0f 85 0c 01 00 00 8b 03 3d 00 01 00 00 74 1a f3 90 <41> 0f b6 55 00 41 38 d7 7c eb 84 d2 74 e7 48 89 df e8 6c 0f 4f 00 RSP: 0018:ffff88805f117bd8 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000300 RBX: ffffffff89413ba0 RCX: 1ffffffff1282774 RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffffffff89413ba0 RBP: ffff88805f117c70 R08: 1ffffffff1282774 R09: fffffbfff1282775 R10: fffffbfff1282774 R11: ffffffff89413ba3 R12: 00000000000000ff R13: fffffbfff1282774 R14: 1ffff1100be22f7d R15: 0000000000000003 queued_write_lock include/asm-generic/qrwlock.h:104 [inline] do_raw_write_lock+0x1d6/0x290 kernel/locking/spinlock_debug.c:203 __raw_write_lock_bh include/linux/rwlock_api_smp.h:204 [inline] _raw_write_lock_bh+0x3b/0x50 kernel/locking/spinlock.c:312 x25_insert_socket+0x21/0xe0 net/x25/af_x25.c:267 x25_bind+0x273/0x340 net/x25/af_x25.c:705 __sys_bind+0x23f/0x290 net/socket.c:1505 __do_sys_bind net/socket.c:1516 [inline] __se_sys_bind net/socket.c:1514 [inline] __x64_sys_bind+0x73/0xb0 net/socket.c:1514 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457e39 Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fafccd0dc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000031 RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457e39 RDX: 0000000000000012 RSI: 0000000020000240 RDI: 0000000000000004 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fafccd0e6d4 R13: 00000000004bdf8b R14: 00000000004ce4b8 R15: 00000000ffffffff Sending NMI from CPU 0 to CPUs 1: NMI backtrace for cpu 1 CPU: 1 PID: 8752 Comm: syz-executor4 Not tainted 5.0.0-rc4+ #51 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__x25_find_socket+0x78/0x120 net/x25/af_x25.c:328 Code: 89 f8 48 c1 e8 03 80 3c 18 00 0f 85 a6 00 00 00 4d 8b 64 24 68 4d 85 e4 74 7f e8 03 97 3d fb 49 83 ec 68 74 74 e8 f8 96 3d fb <49> 8d bc 24 88 04 00 00 48 89 f8 48 c1 e8 03 0f b6 04 18 84 c0 74 RSP: 0018:ffff8880639efc58 EFLAGS: 00000246 RAX: 0000000000040000 RBX: dffffc0000000000 RCX: ffffc9000e677000 RDX: 0000000000040000 RSI: ffffffff863244b8 RDI: ffff88806a764628 RBP: ffff8880639efc80 R08: ffff8880a80d05c0 R09: fffffbfff1282775 R10: fffffbfff1282774 R11: ffffffff89413ba3 R12: ffff88806a7645c0 R13: 0000000000000001 R14: ffff88809f29ac00 R15: 0000000000000000 FS: 00007fe8d0c58700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b32823000 CR3: 00000000672eb000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: x25_new_lci net/x25/af_x25.c:357 [inline] x25_connect+0x374/0xdf0 net/x25/af_x25.c:786 __sys_connect+0x266/0x330 net/socket.c:1686 __do_sys_connect net/socket.c:1697 [inline] __se_sys_connect net/socket.c:1694 [inline] __x64_sys_connect+0x73/0xb0 net/socket.c:1694 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457e39 Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fe8d0c57c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457e39 RDX: 0000000000000012 RSI: 0000000020000200 RDI: 0000000000000004 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fe8d0c586d4 R13: 00000000004be378 R14: 00000000004ceb00 R15: 00000000ffffffff

Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Cc: Andrew Hendry andrew.hendry@gmail.com Cc: linux-x25@vger.kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/x25/af_x25.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

--- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -352,17 +352,15 @@ static unsigned int x25_new_lci(struct x unsigned int lci = 1; struct sock *sk;

- read_lock_bh(&x25_list_lock); - - while ((sk = __x25_find_socket(lci, nb)) != NULL) { + while ((sk = x25_find_socket(lci, nb)) != NULL) { sock_put(sk); if (++lci == 4096) { lci = 0; break; } + cond_resched(); }

- read_unlock_bh(&x25_list_lock); return lci; }

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

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

From: Eric Dumazet edumazet@google.com

commit 63530aba7826a0f8e129874df9c4d264f9db3f9e upstream.

syzbot found that ax25 routes where not properly protected against concurrent use [1].

In this particular report the bug happened while copying ax25->digipeat.

Fix this problem by making sure we call ax25_get_route() while ax25_route_lock is held, so that no modification could happen while using the route.

The current two ax25_get_route() callers do not sleep, so this change should be fine.

Once we do that, ax25_get_route() no longer needs to grab a reference on the found route.

[1] ax25_connect(): syz-executor0 uses autobind, please contact jreuter@yaina.de BUG: KASAN: use-after-free in memcpy include/linux/string.h:352 [inline] BUG: KASAN: use-after-free in kmemdup+0x42/0x60 mm/util.c:113 Read of size 66 at addr ffff888066641a80 by task syz-executor2/531

ax25_connect(): syz-executor0 uses autobind, please contact jreuter@yaina.de CPU: 1 PID: 531 Comm: syz-executor2 Not tainted 5.0.0-rc2+ #10 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1db/0x2d0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 check_memory_region_inline mm/kasan/generic.c:185 [inline] check_memory_region+0x123/0x190 mm/kasan/generic.c:191 memcpy+0x24/0x50 mm/kasan/common.c:130 memcpy include/linux/string.h:352 [inline] kmemdup+0x42/0x60 mm/util.c:113 kmemdup include/linux/string.h:425 [inline] ax25_rt_autobind+0x25d/0x750 net/ax25/ax25_route.c:424 ax25_connect.cold+0x30/0xa4 net/ax25/af_ax25.c:1224 __sys_connect+0x357/0x490 net/socket.c:1664 __do_sys_connect net/socket.c:1675 [inline] __se_sys_connect net/socket.c:1672 [inline] __x64_sys_connect+0x73/0xb0 net/socket.c:1672 do_syscall_64+0x1a3/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x458099 Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f870ee22c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000458099 RDX: 0000000000000048 RSI: 0000000020000080 RDI: 0000000000000005 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 ax25_connect(): syz-executor4 uses autobind, please contact jreuter@yaina.de R10: 0000000000000000 R11: 0000000000000246 R12: 00007f870ee236d4 R13: 00000000004be48e R14: 00000000004ce9a8 R15: 00000000ffffffff

Allocated by task 526: save_stack+0x45/0xd0 mm/kasan/common.c:73 set_track mm/kasan/common.c:85 [inline] __kasan_kmalloc mm/kasan/common.c:496 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:469 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:504 ax25_connect(): syz-executor5 uses autobind, please contact jreuter@yaina.de kmem_cache_alloc_trace+0x151/0x760 mm/slab.c:3609 kmalloc include/linux/slab.h:545 [inline] ax25_rt_add net/ax25/ax25_route.c:95 [inline] ax25_rt_ioctl+0x3b9/0x1270 net/ax25/ax25_route.c:233 ax25_ioctl+0x322/0x10b0 net/ax25/af_ax25.c:1763 sock_do_ioctl+0xe2/0x400 net/socket.c:950 sock_ioctl+0x32f/0x6c0 net/socket.c:1074 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:509 [inline] do_vfs_ioctl+0x107b/0x17d0 fs/ioctl.c:696 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713 __do_sys_ioctl fs/ioctl.c:720 [inline] __se_sys_ioctl fs/ioctl.c:718 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718 do_syscall_64+0x1a3/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe

ax25_connect(): syz-executor5 uses autobind, please contact jreuter@yaina.de Freed by task 550: save_stack+0x45/0xd0 mm/kasan/common.c:73 set_track mm/kasan/common.c:85 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:458 kasan_slab_free+0xe/0x10 mm/kasan/common.c:466 __cache_free mm/slab.c:3487 [inline] kfree+0xcf/0x230 mm/slab.c:3806 ax25_rt_add net/ax25/ax25_route.c:92 [inline] ax25_rt_ioctl+0x304/0x1270 net/ax25/ax25_route.c:233 ax25_ioctl+0x322/0x10b0 net/ax25/af_ax25.c:1763 sock_do_ioctl+0xe2/0x400 net/socket.c:950 sock_ioctl+0x32f/0x6c0 net/socket.c:1074 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:509 [inline] do_vfs_ioctl+0x107b/0x17d0 fs/ioctl.c:696 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713 __do_sys_ioctl fs/ioctl.c:720 [inline] __se_sys_ioctl fs/ioctl.c:718 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718 do_syscall_64+0x1a3/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The buggy address belongs to the object at ffff888066641a80 which belongs to the cache kmalloc-96 of size 96 The buggy address is located 0 bytes inside of 96-byte region [ffff888066641a80, ffff888066641ae0) The buggy address belongs to the page: page:ffffea0001999040 count:1 mapcount:0 mapping:ffff88812c3f04c0 index:0x0 flags: 0x1fffc0000000200(slab) ax25_connect(): syz-executor4 uses autobind, please contact jreuter@yaina.de raw: 01fffc0000000200 ffffea0001817948 ffffea0002341dc8 ffff88812c3f04c0 raw: 0000000000000000 ffff888066641000 0000000100000020 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff888066641980: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ffff888066641a00: 00 00 00 00 00 00 00 00 02 fc fc fc fc fc fc fc

ffff888066641a80: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc

^ ffff888066641b00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ffff888066641b80: 00 00 00 00 00 00 00 00 00 00 00 00 fc fc fc fc

Signed-off-by: Eric Dumazet edumazet@google.com Cc: Ralf Baechle ralf@linux-mips.org Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/net/ax25.h | 12 ++++++++++++ net/ax25/ax25_ip.c | 4 ++-- net/ax25/ax25_route.c | 19 ++++++++----------- 3 files changed, 22 insertions(+), 13 deletions(-)

--- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -201,6 +201,18 @@ static inline void ax25_hold_route(ax25_

void __ax25_put_route(ax25_route *ax25_rt);

+extern rwlock_t ax25_route_lock; + +static inline void ax25_route_lock_use(void) +{ + read_lock(&ax25_route_lock); +} + +static inline void ax25_route_lock_unuse(void) +{ + read_unlock(&ax25_route_lock); +} + static inline void ax25_put_route(ax25_route *ax25_rt) { if (refcount_dec_and_test(&ax25_rt->refcount)) --- a/net/ax25/ax25_ip.c +++ b/net/ax25/ax25_ip.c @@ -114,6 +114,7 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff dst = (ax25_address *)(bp + 1); src = (ax25_address *)(bp + 8);

+ ax25_route_lock_use(); route = ax25_get_route(dst, NULL); if (route) { digipeat = route->digipeat; @@ -206,9 +207,8 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff ax25_queue_xmit(skb, dev);

put: - if (route) - ax25_put_route(route);

+ ax25_route_lock_unuse(); return NETDEV_TX_OK; }

--- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -40,7 +40,7 @@ #include <linux/export.h>

static ax25_route *ax25_route_list; -static DEFINE_RWLOCK(ax25_route_lock); +DEFINE_RWLOCK(ax25_route_lock);

void ax25_rt_device_down(struct net_device *dev) { @@ -335,6 +335,7 @@ const struct seq_operations ax25_rt_seqo * Find AX.25 route * * Only routes with a reference count of zero can be destroyed. + * Must be called with ax25_route_lock read locked. */ ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev) { @@ -342,7 +343,6 @@ ax25_route *ax25_get_route(ax25_address ax25_route *ax25_def_rt = NULL; ax25_route *ax25_rt;

- read_lock(&ax25_route_lock); /* * Bind to the physical interface we heard them on, or the default * route if none is found; @@ -365,11 +365,6 @@ ax25_route *ax25_get_route(ax25_address if (ax25_spe_rt != NULL) ax25_rt = ax25_spe_rt;

- if (ax25_rt != NULL) - ax25_hold_route(ax25_rt); - - read_unlock(&ax25_route_lock); - return ax25_rt; }

@@ -400,9 +395,12 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25 ax25_route *ax25_rt; int err = 0;

- if ((ax25_rt = ax25_get_route(addr, NULL)) == NULL) + ax25_route_lock_use(); + ax25_rt = ax25_get_route(addr, NULL); + if (!ax25_rt) { + ax25_route_lock_unuse(); return -EHOSTUNREACH; - + } if ((ax25->ax25_dev = ax25_dev_ax25dev(ax25_rt->dev)) == NULL) { err = -EHOSTUNREACH; goto put; @@ -437,8 +435,7 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25 }

put: - ax25_put_route(ax25_rt); - + ax25_route_lock_unuse(); return err; }