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

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

From: Hangbin Liu liuhangbin@gmail.com

[ Upstream commit e8238fc2bd7b4c3c7554fa2df067e796610212fc ]

When we set a bond slave's master to bridge via ioctl, we only check the IFF_BRIDGE_PORT flag. Although we will find the slave's real master at netdev_master_upper_dev_link() later, it already does some settings and allocates some resources. It would be better to return as early as possible.

v1 -> v2: use netdev_master_upper_dev_get() instead of netdev_has_any_upper_dev() to check if we have a master, because not all upper devs are masters, e.g. vlan device.

Reported-by: syzbot+de73361ee4971b6e6f75@syzkaller.appspotmail.com Signed-off-by: Hangbin Liu liuhangbin@gmail.com Acked-by: Nikolay Aleksandrov nikolay@cumulusnetworks.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_if.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -504,8 +504,8 @@ int br_add_if(struct net_bridge *br, str if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) return -ELOOP;

- /* Device is already being bridged */ - if (br_port_exists(dev)) + /* Device has master upper dev */ + if (netdev_master_upper_dev_get(dev)) return -EBUSY;

/* No bridging devices that dislike that (e.g. wireless) */

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

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

From: Andrey Ignatov rdna@fb.com

[ Upstream commit 1b97013bfb11d66f041de691de6f0fec748ce016 ]

Fix more memory leaks in ip_cmsg_send() callers. Part of them were fixed earlier in 919483096bfe.

* udp_sendmsg one was there since the beginning when linux sources were first added to git; * ping_v4_sendmsg one was copy/pasted in c319b4d76b9e.

Whenever return happens in udp_sendmsg() or ping_v4_sendmsg() IP options have to be freed if they were allocated previously.

Add label so that future callers (if any) can use it instead of kfree() before return that is easy to forget.

Fixes: c319b4d76b9e (net: ipv4: add IPPROTO_ICMP socket kind) Signed-off-by: Andrey Ignatov rdna@fb.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/ping.c | 7 +++++-- net/ipv4/udp.c | 7 +++++-- 2 files changed, 10 insertions(+), 4 deletions(-)

--- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -775,8 +775,10 @@ static int ping_v4_sendmsg(struct sock * ipc.addr = faddr = daddr;

if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; } tos = get_rttos(&ipc, inet); @@ -841,6 +843,7 @@ back_from_confirm:

out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) { --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -982,8 +982,10 @@ int udp_sendmsg(struct sock *sk, struct sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);

if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; connected = 0; } @@ -1090,6 +1092,7 @@ do_append_data:

out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err)

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

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

From: Rob Taglang rob@taglang.io

[ Upstream commit 14224923c3600bae2ac4dcae3bf0c3d4dc2812be ]

Currently, skb->len and skb->data_len are set to the page size, not the packet size. This causes the frame check sequence to not be located at the "end" of the packet resulting in ethernet frame check errors. The driver does work currently, but stricter kernel facing networking solutions like OpenVSwitch will drop these packets as invalid.

These changes set the packet size correctly so that these errors no longer occur. The length does not include the frame check sequence, so that subtraction was removed.

Tested on Oracle/SUN Multithreaded 10-Gigabit Ethernet Network Controller [108e:abcd] and validated in wireshark.

Signed-off-by: Rob Taglang rob@taglang.io Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/sun/niu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -3442,7 +3442,7 @@ static int niu_process_rx_pkt(struct nap

len = (val & RCR_ENTRY_L2_LEN) >> RCR_ENTRY_L2_LEN_SHIFT; - len -= ETH_FCS_LEN; + append_size = len + ETH_HLEN + ETH_FCS_LEN;

addr = (val & RCR_ENTRY_PKT_BUF_ADDR) << RCR_ENTRY_PKT_BUF_ADDR_SHIFT; @@ -3452,7 +3452,6 @@ static int niu_process_rx_pkt(struct nap RCR_ENTRY_PKTBUFSZ_SHIFT];

off = addr & ~PAGE_MASK; - append_size = rcr_size; if (num_rcr == 1) { int ptype;

@@ -3465,7 +3464,7 @@ static int niu_process_rx_pkt(struct nap else skb_checksum_none_assert(skb); } else if (!(val & RCR_ENTRY_MULTI)) - append_size = len - skb->len; + append_size = append_size - skb->len;

niu_rx_skb_append(skb, page, off, append_size, rcr_size); if ((page->index + rp->rbr_block_size) - rcr_size == addr) {

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

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

From: Moshe Shemesh moshe@mellanox.com

[ Upstream commit 6ad4e91c6d796b38a7f0e724db1de28eeb122bad ]

Add check of coalescing parameters received through ethtool are within range of values supported by the HW. Driver gets the coalescing rx/tx-usecs and rx/tx-frames as set by the users through ethtool. The ethtool support up to 32 bit value for each. However, mlx4 modify cq limits the coalescing time parameter and coalescing frames parameters to 16 bits. Return out of range error if user tries to set these parameters to higher values. Change type of sample-interval and adaptive_rx_coal parameters in mlx4 driver to u32 as the ethtool holds them as u32 and these parameters are not limited due to mlx4 HW.

Fixes: c27a02cd94d6 ('mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC') Signed-off-by: Moshe Shemesh moshe@mellanox.com Signed-off-by: Tariq Toukan tariqt@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 16 ++++++++++++++++ drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 7 +++++-- 2 files changed, 21 insertions(+), 2 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -970,6 +970,22 @@ static int mlx4_en_set_coalesce(struct n if (!coal->tx_max_coalesced_frames_irq) return -EINVAL;

+ if (coal->tx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME || + coal->rx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME || + coal->rx_coalesce_usecs_low > MLX4_EN_MAX_COAL_TIME || + coal->rx_coalesce_usecs_high > MLX4_EN_MAX_COAL_TIME) { + netdev_info(dev, "%s: maximum coalesce time supported is %d usecs\n", + __func__, MLX4_EN_MAX_COAL_TIME); + return -ERANGE; + } + + if (coal->tx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS || + coal->rx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS) { + netdev_info(dev, "%s: maximum coalesced frames supported is %d\n", + __func__, MLX4_EN_MAX_COAL_PKTS); + return -ERANGE; + } + priv->rx_frames = (coal->rx_max_coalesced_frames == MLX4_EN_AUTO_CONF) ? MLX4_EN_RX_COAL_TARGET : --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -141,6 +141,9 @@ enum { #define MLX4_EN_TX_COAL_PKTS 16 #define MLX4_EN_TX_COAL_TIME 0x10

+#define MLX4_EN_MAX_COAL_PKTS U16_MAX +#define MLX4_EN_MAX_COAL_TIME U16_MAX + #define MLX4_EN_RX_RATE_LOW 400000 #define MLX4_EN_RX_COAL_TIME_LOW 0 #define MLX4_EN_RX_RATE_HIGH 450000 @@ -543,8 +546,8 @@ struct mlx4_en_priv { u16 rx_usecs_low; u32 pkt_rate_high; u16 rx_usecs_high; - u16 sample_interval; - u16 adaptive_rx_coal; + u32 sample_interval; + u32 adaptive_rx_coal; u32 msg_enable; u32 loopback_ok; u32 validate_loopback;

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

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

From: Eric Dumazet edumazet@google.com

[ Upstream commit 7df40c2673a1307c3260aab6f9d4b9bf97ca8fd7 ]

Normally, a socket can not be freed/reused unless all its TX packets left qdisc and were TX-completed. However connect(AF_UNSPEC) allows this to happen.

With commit fc59d5bdf1e3 ("pkt_sched: fq: clear time_next_packet for reused flows") we cleared f->time_next_packet but took no special action if the flow was still in the throttled rb-tree.

Since f->time_next_packet is the key used in the rb-tree searches, blindly clearing it might break rb-tree integrity. We need to make sure the flow is no longer in the rb-tree to avoid this problem.

Fixes: fc59d5bdf1e3 ("pkt_sched: fq: clear time_next_packet for reused flows") Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/sch_fq.c | 37 +++++++++++++++++++++++++------------ 1 file changed, 25 insertions(+), 12 deletions(-)

--- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -128,6 +128,28 @@ static bool fq_flow_is_detached(const st return f->next == &detached; }

+static bool fq_flow_is_throttled(const struct fq_flow *f) +{ + return f->next == &throttled; +} + +static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow) +{ + if (head->first) + head->last->next = flow; + else + head->first = flow; + head->last = flow; + flow->next = NULL; +} + +static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f) +{ + rb_erase(&f->rate_node, &q->delayed); + q->throttled_flows--; + fq_flow_add_tail(&q->old_flows, f); +} + static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f) { struct rb_node **p = &q->delayed.rb_node, *parent = NULL; @@ -155,15 +177,6 @@ static void fq_flow_set_throttled(struct

static struct kmem_cache *fq_flow_cachep __read_mostly;

-static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow) -{ - if (head->first) - head->last->next = flow; - else - head->first = flow; - head->last = flow; - flow->next = NULL; -}

/* limit number of collected flows per round */ #define FQ_GC_MAX 8 @@ -267,6 +280,8 @@ static struct fq_flow *fq_classify(struc f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + if (fq_flow_is_throttled(f)) + fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; } return f; @@ -430,9 +445,7 @@ static void fq_check_throttled(struct fq q->time_next_delayed_flow = f->time_next_packet; break; } - rb_erase(p, &q->delayed); - q->throttled_flows--; - fq_flow_add_tail(&q->old_flows, f); + fq_flow_unset_throttled(q, f); } }

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

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

From: Stefano Brivio sbrivio@redhat.com

[ Upstream commit 72f17baf2352ded6a1d3f4bb2d15da8c678cd2cb ]

If an OVS_ATTR_NESTED attribute type is found while walking through netlink attributes, we call nlattr_set() recursively passing the length table for the following nested attributes, if different from the current one.

However, once we're done with those sub-nested attributes, we should continue walking through attributes using the current table, instead of using the one related to the sub-nested attributes.

For example, given this sequence:

1 OVS_KEY_ATTR_PRIORITY 2 OVS_KEY_ATTR_TUNNEL 3 OVS_TUNNEL_KEY_ATTR_ID 4 OVS_TUNNEL_KEY_ATTR_IPV4_SRC 5 OVS_TUNNEL_KEY_ATTR_IPV4_DST 6 OVS_TUNNEL_KEY_ATTR_TTL 7 OVS_TUNNEL_KEY_ATTR_TP_SRC 8 OVS_TUNNEL_KEY_ATTR_TP_DST 9 OVS_KEY_ATTR_IN_PORT 10 OVS_KEY_ATTR_SKB_MARK 11 OVS_KEY_ATTR_MPLS

we switch to the 'ovs_tunnel_key_lens' table on attribute #3, and we don't switch back to 'ovs_key_lens' while setting attributes #9 to #11 in the sequence. As OVS_KEY_ATTR_MPLS evaluates to 21, and the array size of 'ovs_tunnel_key_lens' is 15, we also get this kind of KASan splat while accessing the wrong table:

[ 7654.586496] ================================================================== [ 7654.594573] BUG: KASAN: global-out-of-bounds in nlattr_set+0x164/0xde9 [openvswitch] [ 7654.603214] Read of size 4 at addr ffffffffc169ecf0 by task handler29/87430 [ 7654.610983] [ 7654.612644] CPU: 21 PID: 87430 Comm: handler29 Kdump: loaded Not tainted 3.10.0-866.el7.test.x86_64 #1 [ 7654.623030] Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.1.7 06/16/2016 [ 7654.631379] Call Trace: [ 7654.634108] [<ffffffffb65a7c50>] dump_stack+0x19/0x1b [ 7654.639843] [<ffffffffb53ff373>] print_address_description+0x33/0x290 [ 7654.647129] [<ffffffffc169b37b>] ? nlattr_set+0x164/0xde9 [openvswitch] [ 7654.654607] [<ffffffffb53ff812>] kasan_report.part.3+0x242/0x330 [ 7654.661406] [<ffffffffb53ff9b4>] __asan_report_load4_noabort+0x34/0x40 [ 7654.668789] [<ffffffffc169b37b>] nlattr_set+0x164/0xde9 [openvswitch] [ 7654.676076] [<ffffffffc167ef68>] ovs_nla_get_match+0x10c8/0x1900 [openvswitch] [ 7654.684234] [<ffffffffb61e9cc8>] ? genl_rcv+0x28/0x40 [ 7654.689968] [<ffffffffb61e7733>] ? netlink_unicast+0x3f3/0x590 [ 7654.696574] [<ffffffffc167dea0>] ? ovs_nla_put_tunnel_info+0xb0/0xb0 [openvswitch] [ 7654.705122] [<ffffffffb4f41b50>] ? unwind_get_return_address+0xb0/0xb0 [ 7654.712503] [<ffffffffb65d9355>] ? system_call_fastpath+0x1c/0x21 [ 7654.719401] [<ffffffffb4f41d79>] ? update_stack_state+0x229/0x370 [ 7654.726298] [<ffffffffb4f41d79>] ? update_stack_state+0x229/0x370 [ 7654.733195] [<ffffffffb53fe4b5>] ? kasan_unpoison_shadow+0x35/0x50 [ 7654.740187] [<ffffffffb53fe62a>] ? kasan_kmalloc+0xaa/0xe0 [ 7654.746406] [<ffffffffb53fec32>] ? kasan_slab_alloc+0x12/0x20 [ 7654.752914] [<ffffffffb53fe711>] ? memset+0x31/0x40 [ 7654.758456] [<ffffffffc165bf92>] ovs_flow_cmd_new+0x2b2/0xf00 [openvswitch]

[snip]

[ 7655.132484] The buggy address belongs to the variable: [ 7655.138226] ovs_tunnel_key_lens+0xf0/0xffffffffffffd400 [openvswitch] [ 7655.145507] [ 7655.147166] Memory state around the buggy address: [ 7655.152514] ffffffffc169eb80: 00 00 00 00 00 00 00 00 00 00 fa fa fa fa fa fa [ 7655.160585] ffffffffc169ec00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 7655.168644] >ffffffffc169ec80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fa fa [ 7655.176701] ^ [ 7655.184372] ffffffffc169ed00: fa fa fa fa 00 00 00 00 fa fa fa fa 00 00 00 05 [ 7655.192431] ffffffffc169ed80: fa fa fa fa 00 00 00 00 00 00 00 00 00 00 00 00 [ 7655.200490] ==================================================================

Reported-by: Hangbin Liu liuhangbin@gmail.com Fixes: 982b52700482 ("openvswitch: Fix mask generation for nested attributes.") Signed-off-by: Stefano Brivio sbrivio@redhat.com Reviewed-by: Sabrina Dubroca sd@queasysnail.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/openvswitch/flow_netlink.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)

--- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1296,13 +1296,10 @@ static void nlattr_set(struct nlattr *at

/* The nlattr stream should already have been validated */ nla_for_each_nested(nla, attr, rem) { - if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) { - if (tbl[nla_type(nla)].next) - tbl = tbl[nla_type(nla)].next; - nlattr_set(nla, val, tbl); - } else { + if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) + nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl); + else memset(nla_data(nla), val, nla_len(nla)); - }

if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE) *(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK;

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

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

From: Xin Long lucien.xin@gmail.com

[ Upstream commit d625329b06e46bd20baf9ee40847d11982569204 ]

Since sctp ipv6 socket also supports v4 addrs, it's possible to compare two v4 addrs in pf v6 .cmp_addr, sctp_inet6_cmp_addr.

However after Commit 1071ec9d453a ("sctp: do not check port in sctp_inet6_cmp_addr"), it no longer calls af1->cmp_addr, which in this case is sctp_v4_cmp_addr, but calls __sctp_v6_cmp_addr where it handles them as two v6 addrs. It would cause a out of bounds crash.

syzbot found this crash when trying to bind two v4 addrs to a v6 socket.

This patch fixes it by adding the process for two v4 addrs in sctp_inet6_cmp_addr.

Fixes: 1071ec9d453a ("sctp: do not check port in sctp_inet6_cmp_addr") Reported-by: syzbot+cd494c1dd681d4d93ebb@syzkaller.appspotmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Acked-by: Neil Horman nhorman@tuxdriver.com Acked-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sctp/ipv6.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -864,6 +864,9 @@ static int sctp_inet6_cmp_addr(const uni if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2)) return 1;

+ if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET) + return addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr; + return __sctp_v6_cmp_addr(addr1, addr2); }

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

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

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 46e16d4b956867013e0bbd7f2bad206f4aa55752 ]

When processing a duplicate cookie-echo chunk, for case 'D', sctp will not process the param from this chunk. It means old asoc has nothing to be updated, and the new temp asoc doesn't have the complete info.

So there's no reason to use the new asoc when creating the cookie-ack chunk. Otherwise, like when auth is enabled for cookie-ack, the chunk can not be set with auth, and it will definitely be dropped by peer.

This issue is there since very beginning, and we fix it by using the old asoc instead.

Signed-off-by: Xin Long lucien.xin@gmail.com Acked-by: Neil Horman nhorman@tuxdriver.com Acked-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sctp/sm_statefuns.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1959,7 +1959,7 @@ static sctp_disposition_t sctp_sf_do_dup } }

- repl = sctp_make_cookie_ack(new_asoc, chunk); + repl = sctp_make_cookie_ack(asoc, chunk); if (!repl) goto nomem;

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

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

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit d89a2adb8bfe6f8949ff389acdb9fa298b6e8e12 ]

tg3_free_consistent() calls dma_free_coherent() to free tp->hw_stats under spinlock and can trigger BUG_ON() in vunmap() because vunmap() may sleep. Fix it by removing the spinlock and relying on the TG3_FLAG_INIT_COMPLETE flag to prevent race conditions between tg3_get_stats64() and tg3_free_consistent(). TG3_FLAG_INIT_COMPLETE is always cleared under tp->lock before tg3_free_consistent() and therefore tg3_get_stats64() can safely access tp->hw_stats under tp->lock if TG3_FLAG_INIT_COMPLETE is set.

Fixes: f5992b72ebe0 ("tg3: Fix race condition in tg3_get_stats64().") Reported-by: Zumeng Chen zumeng.chen@gmail.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/tg3.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

--- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -8720,14 +8720,15 @@ static void tg3_free_consistent(struct t tg3_mem_rx_release(tp); tg3_mem_tx_release(tp);

- /* Protect tg3_get_stats64() from reading freed tp->hw_stats. */ - tg3_full_lock(tp, 0); + /* tp->hw_stats can be referenced safely: + * 1. under rtnl_lock + * 2. or under tp->lock if TG3_FLAG_INIT_COMPLETE is set. + */ if (tp->hw_stats) { dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats), tp->hw_stats, tp->stats_mapping); tp->hw_stats = NULL; } - tg3_full_unlock(tp); }

/* @@ -14161,7 +14162,7 @@ static struct rtnl_link_stats64 *tg3_get struct tg3 *tp = netdev_priv(dev);

spin_lock_bh(&tp->lock); - if (!tp->hw_stats) { + if (!tp->hw_stats || !tg3_flag(tp, INIT_COMPLETE)) { *stats = tp->net_stats_prev; spin_unlock_bh(&tp->lock); return stats;

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

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

From: Talat Batheesh talatb@mellanox.com

[ Upstream commit 9c26f5f89d01ca21560c6b8a8e4054c271cc3a9c ]

When we fail to initialize the RX root namespace, we need to clean only that and not the entire flow steering.

Currently the code may try to clean the flow steering twice on error witch leads to null pointer deference. Make sure we clean correctly.

Fixes: fba53f7b5719 ("net/mlx5: Introduce mlx5_flow_steering structure") Signed-off-by: Talat Batheesh talatb@mellanox.com Reviewed-by: Mark Bloch markb@mellanox.com Signed-off-by: Saeed Mahameed saeedm@mellanox.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -153,6 +153,7 @@ static void del_rule(struct fs_node *nod static void del_flow_table(struct fs_node *node); static void del_flow_group(struct fs_node *node); static void del_fte(struct fs_node *node); +static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns);

static void tree_init_node(struct fs_node *node, unsigned int refcount, @@ -1690,24 +1691,28 @@ static int create_anchor_flow_table(stru

static int init_root_ns(struct mlx5_flow_steering *steering) { + int err;

steering->root_ns = create_root_ns(steering, FS_FT_NIC_RX); if (!steering->root_ns) - goto cleanup; + return -ENOMEM;

- if (init_root_tree(steering, &root_fs, &steering->root_ns->ns.node)) - goto cleanup; + err = init_root_tree(steering, &root_fs, &steering->root_ns->ns.node); + if (err) + goto out_err;

set_prio_attrs(steering->root_ns);

- if (create_anchor_flow_table(steering)) - goto cleanup; + err = create_anchor_flow_table(steering); + if (err) + goto out_err;

return 0;

-cleanup: - mlx5_cleanup_fs(steering->dev); - return -ENOMEM; +out_err: + cleanup_root_ns(steering->root_ns); + steering->root_ns = NULL; + return err; }

static void clean_tree(struct fs_node *node)

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

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

From: Yuchung Cheng ycheng@google.com

[ Upstream commit 16ae6aa1705299789f71fdea59bfb119c1fbd9c0 ]

The TCP repair sequence of operation is to first set the socket in repair mode, then inject the TCP stats into the socket with repair socket options, then call connect() to re-activate the socket. The connect syscall simply returns and set state to ESTABLISHED mode. As a result Fast Open is meaningless for TCP repair.

However allowing sendto() system call with MSG_FASTOPEN flag half-way during the repair operation could unexpectedly cause data to be sent, before the operation finishes changing the internal TCP stats (e.g. MSS). This in turn triggers TCP warnings on inconsistent packet accounting.

The fix is to simply disallow Fast Open operation once the socket is in the repair mode.

Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: Yuchung Cheng ycheng@google.com Reviewed-by: Neal Cardwell ncardwell@google.com Reviewed-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1118,7 +1118,7 @@ int tcp_sendmsg(struct sock *sk, struct lock_sock(sk);

flags = msg->msg_flags; - if (flags & MSG_FASTOPEN) { + if ((flags & MSG_FASTOPEN) && !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out;

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

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

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 59d8d4434f429b4fa8a346fd889058bda427a837 ]

Now sctp only delays the authentication for the normal cookie-echo chunk by setting chunk->auth_chunk in sctp_endpoint_bh_rcv(). But for the duplicated one with auth, in sctp_assoc_bh_rcv(), it does authentication first based on the old asoc, which will definitely fail due to the different auth info in the old asoc.

The duplicated cookie-echo chunk will create a new asoc with the auth info from this chunk, and the authentication should also be done with the new asoc's auth info for all of the collision 'A', 'B' and 'D'. Otherwise, the duplicated cookie-echo chunk with auth will never pass the authentication and create the new connection.

This issue exists since very beginning, and this fix is to make sctp_assoc_bh_rcv() follow the way sctp_endpoint_bh_rcv() does for the normal cookie-echo chunk to delay the authentication.

While at it, remove the unused params from sctp_sf_authenticate() and define sctp_auth_chunk_verify() used for all the places that do the delayed authentication.

v1->v2: fix the typo in changelog as Marcelo noticed.

Acked-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Acked-by: Neil Horman nhorman@tuxdriver.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sctp/associola.c | 30 ++++++++++++++++ net/sctp/sm_statefuns.c | 87 ++++++++++++++++++++++++++---------------------- 2 files changed, 77 insertions(+), 40 deletions(-)

--- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1006,9 +1006,10 @@ static void sctp_assoc_bh_rcv(struct wor struct sctp_endpoint *ep; struct sctp_chunk *chunk; struct sctp_inq *inqueue; - int state; sctp_subtype_t subtype; + int first_time = 1; /* is this the first time through the loop */ int error = 0; + int state;

/* The association should be held so we should be safe. */ ep = asoc->ep; @@ -1019,6 +1020,30 @@ static void sctp_assoc_bh_rcv(struct wor state = asoc->state; subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type);

+ /* If the first chunk in the packet is AUTH, do special + * processing specified in Section 6.3 of SCTP-AUTH spec + */ + if (first_time && subtype.chunk == SCTP_CID_AUTH) { + struct sctp_chunkhdr *next_hdr; + + next_hdr = sctp_inq_peek(inqueue); + if (!next_hdr) + goto normal; + + /* If the next chunk is COOKIE-ECHO, skip the AUTH + * chunk while saving a pointer to it so we can do + * Authentication later (during cookie-echo + * processing). + */ + if (next_hdr->type == SCTP_CID_COOKIE_ECHO) { + chunk->auth_chunk = skb_clone(chunk->skb, + GFP_ATOMIC); + chunk->auth = 1; + continue; + } + } + +normal: /* SCTP-AUTH, Section 6.3: * The receiver has a list of chunk types which it expects * to be received only after an AUTH-chunk. This list has @@ -1057,6 +1082,9 @@ static void sctp_assoc_bh_rcv(struct wor /* If there is an error on chunk, discard this packet. */ if (error && chunk) chunk->pdiscard = 1; + + if (first_time) + first_time = 0; } sctp_association_put(asoc); } --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -144,10 +144,8 @@ static sctp_disposition_t sctp_sf_violat void *arg, sctp_cmd_seq_t *commands);

-static sctp_ierror_t sctp_sf_authenticate(struct net *net, - const struct sctp_endpoint *ep, +static sctp_ierror_t sctp_sf_authenticate( const struct sctp_association *asoc, - const sctp_subtype_t type, struct sctp_chunk *chunk);

static sctp_disposition_t __sctp_sf_do_9_1_abort(struct net *net, @@ -615,6 +613,38 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(s return SCTP_DISPOSITION_CONSUME; }

+static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk, + const struct sctp_association *asoc) +{ + struct sctp_chunk auth; + + if (!chunk->auth_chunk) + return true; + + /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo + * is supposed to be authenticated and we have to do delayed + * authentication. We've just recreated the association using + * the information in the cookie and now it's much easier to + * do the authentication. + */ + + /* Make sure that we and the peer are AUTH capable */ + if (!net->sctp.auth_enable || !asoc->peer.auth_capable) + return false; + + /* set-up our fake chunk so that we can process it */ + auth.skb = chunk->auth_chunk; + auth.asoc = chunk->asoc; + auth.sctp_hdr = chunk->sctp_hdr; + auth.chunk_hdr = (struct sctp_chunkhdr *) + skb_push(chunk->auth_chunk, + sizeof(struct sctp_chunkhdr)); + skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); + auth.transport = chunk->transport; + + return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR; +} + /* * Respond to a normal COOKIE ECHO chunk. * We are the side that is being asked for an association. @@ -751,36 +781,9 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(st if (error) goto nomem_init;

- /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo - * is supposed to be authenticated and we have to do delayed - * authentication. We've just recreated the association using - * the information in the cookie and now it's much easier to - * do the authentication. - */ - if (chunk->auth_chunk) { - struct sctp_chunk auth; - sctp_ierror_t ret; - - /* Make sure that we and the peer are AUTH capable */ - if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } - - /* set-up our fake chunk so that we can process it */ - auth.skb = chunk->auth_chunk; - auth.asoc = chunk->asoc; - auth.sctp_hdr = chunk->sctp_hdr; - auth.chunk_hdr = (sctp_chunkhdr_t *)skb_push(chunk->auth_chunk, - sizeof(sctp_chunkhdr_t)); - skb_pull(chunk->auth_chunk, sizeof(sctp_chunkhdr_t)); - auth.transport = chunk->transport; - - ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth); - if (ret != SCTP_IERROR_NO_ERROR) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); }

repl = sctp_make_cookie_ack(new_asoc, chunk); @@ -1717,13 +1720,15 @@ static sctp_disposition_t sctp_sf_do_dup GFP_ATOMIC)) goto nomem;

+ if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Make sure no new addresses are being added during the * restart. Though this is a pretty complicated attack * since you'd have to get inside the cookie. */ - if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) { + if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) return SCTP_DISPOSITION_CONSUME; - }

/* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes * the peer has restarted (Action A), it MUST NOT setup a new @@ -1828,6 +1833,9 @@ static sctp_disposition_t sctp_sf_do_dup GFP_ATOMIC)) goto nomem;

+ if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, @@ -1920,6 +1928,9 @@ static sctp_disposition_t sctp_sf_do_dup * a COOKIE ACK. */

+ if (!sctp_auth_chunk_verify(net, chunk, asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Don't accidentally move back into established state. */ if (asoc->state < SCTP_STATE_ESTABLISHED) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, @@ -3981,10 +3992,8 @@ gen_shutdown: * * The return value is the disposition of the chunk. */ -static sctp_ierror_t sctp_sf_authenticate(struct net *net, - const struct sctp_endpoint *ep, +static sctp_ierror_t sctp_sf_authenticate( const struct sctp_association *asoc, - const sctp_subtype_t type, struct sctp_chunk *chunk) { struct sctp_authhdr *auth_hdr; @@ -4083,7 +4092,7 @@ sctp_disposition_t sctp_sf_eat_auth(stru commands);

auth_hdr = (struct sctp_authhdr *)chunk->skb->data; - error = sctp_sf_authenticate(net, ep, asoc, type, chunk); + error = sctp_sf_authenticate(asoc, chunk); switch (error) { case SCTP_IERROR_AUTH_BAD_HMAC: /* Generate the ERROR chunk and discard the rest

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

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

From: Jiri Slaby jslaby@suse.cz

commit 30d6e0a4190d37740e9447e4e4815f06992dd8c3 upstream.

There is code duplicated over all architecture's headers for futex_atomic_op_inuser. Namely op decoding, access_ok check for uaddr, and comparison of the result.

Remove this duplication and leave up to the arches only the needed assembly which is now in arch_futex_atomic_op_inuser.

This effectively distributes the Will Deacon's arm64 fix for undefined behaviour reported by UBSAN to all architectures. The fix was done in commit 5f16a046f8e1 (arm64: futex: Fix undefined behaviour with FUTEX_OP_OPARG_SHIFT usage). Look there for an example dump.

And as suggested by Thomas, check for negative oparg too, because it was also reported to cause undefined behaviour report.

Note that s390 removed access_ok check in d12a29703 ("s390/uaccess: remove pointless access_ok() checks") as access_ok there returns true. We introduce it back to the helper for the sake of simplicity (it gets optimized away anyway).

Signed-off-by: Jiri Slaby jslaby@suse.cz Signed-off-by: Thomas Gleixner tglx@linutronix.de Acked-by: Russell King rmk+kernel@armlinux.org.uk Acked-by: Michael Ellerman mpe@ellerman.id.au (powerpc) Acked-by: Heiko Carstens heiko.carstens@de.ibm.com [s390] Acked-by: Chris Metcalf cmetcalf@mellanox.com [for tile] Reviewed-by: Darren Hart (VMware) dvhart@infradead.org Reviewed-by: Will Deacon will.deacon@arm.com [core/arm64] Cc: linux-mips@linux-mips.org Cc: Rich Felker dalias@libc.org Cc: linux-ia64@vger.kernel.org Cc: linux-sh@vger.kernel.org Cc: peterz@infradead.org Cc: Benjamin Herrenschmidt benh@kernel.crashing.org Cc: Max Filippov jcmvbkbc@gmail.com Cc: Paul Mackerras paulus@samba.org Cc: sparclinux@vger.kernel.org Cc: Jonas Bonn jonas@southpole.se Cc: linux-s390@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: Yoshinori Sato ysato@users.sourceforge.jp Cc: linux-hexagon@vger.kernel.org Cc: Helge Deller deller@gmx.de Cc: "James E.J. Bottomley" jejb@parisc-linux.org Cc: Catalin Marinas catalin.marinas@arm.com Cc: Matt Turner mattst88@gmail.com Cc: linux-snps-arc@lists.infradead.org Cc: Fenghua Yu fenghua.yu@intel.com Cc: Arnd Bergmann arnd@arndb.de Cc: linux-xtensa@linux-xtensa.org Cc: Stefan Kristiansson stefan.kristiansson@saunalahti.fi Cc: openrisc@lists.librecores.org Cc: Ivan Kokshaysky ink@jurassic.park.msu.ru Cc: Stafford Horne shorne@gmail.com Cc: linux-arm-kernel@lists.infradead.org Cc: Richard Henderson rth@twiddle.net Cc: Chris Zankel chris@zankel.net Cc: Michal Simek monstr@monstr.eu Cc: Tony Luck tony.luck@intel.com Cc: linux-parisc@vger.kernel.org Cc: Vineet Gupta vgupta@synopsys.com Cc: Ralf Baechle ralf@linux-mips.org Cc: Richard Kuo rkuo@codeaurora.org Cc: linux-alpha@vger.kernel.org Cc: Martin Schwidefsky schwidefsky@de.ibm.com Cc: linuxppc-dev@lists.ozlabs.org Cc: "David S. Miller" davem@davemloft.net Link: http://lkml.kernel.org/r/20170824073105.3901-1-jslaby@suse.cz Cc: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- arch/alpha/include/asm/futex.h | 26 +++--------------- arch/arc/include/asm/futex.h | 40 +++------------------------- arch/arm/include/asm/futex.h | 26 ++---------------- arch/arm64/include/asm/futex.h | 27 ++----------------- arch/frv/include/asm/futex.h | 3 +- arch/frv/kernel/futex.c | 27 ++----------------- arch/hexagon/include/asm/futex.h | 38 ++------------------------- arch/ia64/include/asm/futex.h | 25 ++---------------- arch/microblaze/include/asm/futex.h | 38 ++------------------------- arch/mips/include/asm/futex.h | 25 ++---------------- arch/parisc/include/asm/futex.h | 26 ++---------------- arch/powerpc/include/asm/futex.h | 26 +++--------------- arch/s390/include/asm/futex.h | 23 +++------------- arch/sh/include/asm/futex.h | 26 ++---------------- arch/sparc/include/asm/futex_64.h | 26 +++--------------- arch/tile/include/asm/futex.h | 40 +++------------------------- arch/x86/include/asm/futex.h | 40 +++------------------------- arch/xtensa/include/asm/futex.h | 27 +++---------------- include/asm-generic/futex.h | 50 ++++++------------------------------ kernel/futex.c | 39 ++++++++++++++++++++++++++++ 20 files changed, 126 insertions(+), 472 deletions(-)

--- a/arch/alpha/include/asm/futex.h +++ b/arch/alpha/include/asm/futex.h @@ -29,18 +29,10 @@ : "r" (uaddr), "r"(oparg) \ : "memory")

-static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) +static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, + u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret; - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT;

pagefault_disable();

@@ -66,17 +58,9 @@ static inline int futex_atomic_op_inuser

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/arc/include/asm/futex.h +++ b/arch/arc/include/asm/futex.h @@ -73,20 +73,11 @@

#endif

-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, + u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret;

- if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) - return -EFAULT; - #ifndef CONFIG_ARC_HAS_LLSC preempt_disable(); /* to guarantee atomic r-m-w of futex op */ #endif @@ -118,30 +109,9 @@ static inline int futex_atomic_op_inuser preempt_enable(); #endif

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: - ret = (oldval == cmparg); - break; - case FUTEX_OP_CMP_NE: - ret = (oldval != cmparg); - break; - case FUTEX_OP_CMP_LT: - ret = (oldval < cmparg); - break; - case FUTEX_OP_CMP_GE: - ret = (oldval >= cmparg); - break; - case FUTEX_OP_CMP_LE: - ret = (oldval <= cmparg); - break; - case FUTEX_OP_CMP_GT: - ret = (oldval > cmparg); - break; - default: - ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -128,20 +128,10 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, #endif /* !SMP */

static inline int -futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) +arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret, tmp;

- if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT; - #ifndef CONFIG_SMP preempt_disable(); #endif @@ -172,17 +162,9 @@ futex_atomic_op_inuser (int encoded_op, preempt_enable(); #endif

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -51,20 +51,9 @@ : "memory")

static inline int -futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *_uaddr) +arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (int)(encoded_op << 8) >> 20; - int cmparg = (int)(encoded_op << 20) >> 20; int oldval = 0, ret, tmp; - u32 __user *uaddr = __uaccess_mask_ptr(_uaddr); - - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1U << (oparg & 0x1f); - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT;

pagefault_disable();

@@ -95,17 +84,9 @@ futex_atomic_op_inuser(unsigned int enco

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/frv/include/asm/futex.h +++ b/arch/frv/include/asm/futex.h @@ -7,7 +7,8 @@ #include <asm/errno.h> #include <asm/uaccess.h>

-extern int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr); +extern int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, + u32 __user *uaddr);

static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, --- a/arch/frv/kernel/futex.c +++ b/arch/frv/kernel/futex.c @@ -186,20 +186,10 @@ static inline int atomic_futex_op_xchg_x /* * do the futex operations */ -int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret;

- if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT; - pagefault_disable();

switch (op) { @@ -225,18 +215,9 @@ int futex_atomic_op_inuser(int encoded_o

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; break; - } - } + if (!ret) + *oval = oldval;

return ret;

-} /* end futex_atomic_op_inuser() */ +} /* end arch_futex_atomic_op_inuser() */ --- a/arch/hexagon/include/asm/futex.h +++ b/arch/hexagon/include/asm/futex.h @@ -31,18 +31,9 @@

static inline int -futex_atomic_op_inuser(int encoded_op, int __user *uaddr) +arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret; - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) - return -EFAULT;

pagefault_disable();

@@ -72,30 +63,9 @@ futex_atomic_op_inuser(int encoded_op, i

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: - ret = (oldval == cmparg); - break; - case FUTEX_OP_CMP_NE: - ret = (oldval != cmparg); - break; - case FUTEX_OP_CMP_LT: - ret = (oldval < cmparg); - break; - case FUTEX_OP_CMP_GE: - ret = (oldval >= cmparg); - break; - case FUTEX_OP_CMP_LE: - ret = (oldval <= cmparg); - break; - case FUTEX_OP_CMP_GT: - ret = (oldval > cmparg); - break; - default: - ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/ia64/include/asm/futex.h +++ b/arch/ia64/include/asm/futex.h @@ -45,18 +45,9 @@ do { \ } while (0)

static inline int -futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) +arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret; - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT;

pagefault_disable();

@@ -84,17 +75,9 @@ futex_atomic_op_inuser (int encoded_op,

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/microblaze/include/asm/futex.h +++ b/arch/microblaze/include/asm/futex.h @@ -29,18 +29,9 @@ })

static inline int -futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret; - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT;

pagefault_disable();

@@ -66,30 +57,9 @@ futex_atomic_op_inuser(int encoded_op, u

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: - ret = (oldval == cmparg); - break; - case FUTEX_OP_CMP_NE: - ret = (oldval != cmparg); - break; - case FUTEX_OP_CMP_LT: - ret = (oldval < cmparg); - break; - case FUTEX_OP_CMP_GE: - ret = (oldval >= cmparg); - break; - case FUTEX_OP_CMP_LE: - ret = (oldval <= cmparg); - break; - case FUTEX_OP_CMP_GT: - ret = (oldval > cmparg); - break; - default: - ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/mips/include/asm/futex.h +++ b/arch/mips/include/asm/futex.h @@ -83,18 +83,9 @@ }

static inline int -futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret; - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT;

pagefault_disable();

@@ -125,17 +116,9 @@ futex_atomic_op_inuser(int encoded_op, u

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/parisc/include/asm/futex.h +++ b/arch/parisc/include/asm/futex.h @@ -32,22 +32,12 @@ _futex_spin_unlock_irqrestore(u32 __user }

static inline int -futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) +arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { unsigned long int flags; - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval, ret; u32 tmp;

- if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr))) - return -EFAULT; - _futex_spin_lock_irqsave(uaddr, &flags); pagefault_disable();

@@ -85,17 +75,9 @@ out_pagefault_enable: pagefault_enable(); _futex_spin_unlock_irqrestore(uaddr, &flags);

- if (ret == 0) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -31,18 +31,10 @@ : "b" (uaddr), "i" (-EFAULT), "r" (oparg) \ : "cr0", "memory")

-static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) +static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, + u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret; - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT;

pagefault_disable();

@@ -68,17 +60,9 @@ static inline int futex_atomic_op_inuser

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/s390/include/asm/futex.h +++ b/arch/s390/include/asm/futex.h @@ -21,17 +21,12 @@ : "0" (-EFAULT), "d" (oparg), "a" (uaddr), \ "m" (*uaddr) : "cc");

-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, + u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, newval, ret;

load_kernel_asce(); - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg;

pagefault_disable(); switch (op) { @@ -60,17 +55,9 @@ static inline int futex_atomic_op_inuser } pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/sh/include/asm/futex.h +++ b/arch/sh/include/asm/futex.h @@ -27,21 +27,12 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, return atomic_futex_op_cmpxchg_inatomic(uval, uaddr, oldval, newval); }

-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, + u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - u32 oparg = (encoded_op << 8) >> 20; - u32 cmparg = (encoded_op << 20) >> 20; u32 oldval, newval, prev; int ret;

- if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT; - pagefault_disable();

do { @@ -80,17 +71,8 @@ static inline int futex_atomic_op_inuser

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = ((int)oldval < (int)cmparg); break; - case FUTEX_OP_CMP_GE: ret = ((int)oldval >= (int)cmparg); break; - case FUTEX_OP_CMP_LE: ret = ((int)oldval <= (int)cmparg); break; - case FUTEX_OP_CMP_GT: ret = ((int)oldval > (int)cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval;

return ret; } --- a/arch/sparc/include/asm/futex_64.h +++ b/arch/sparc/include/asm/futex_64.h @@ -29,22 +29,14 @@ : "r" (uaddr), "r" (oparg), "i" (-EFAULT) \ : "memory")

-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, + u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret, tem;

- if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))) - return -EFAULT; if (unlikely((((unsigned long) uaddr) & 0x3UL))) return -EINVAL;

- if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - pagefault_disable();

switch (op) { @@ -69,17 +61,9 @@ static inline int futex_atomic_op_inuser

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/tile/include/asm/futex.h +++ b/arch/tile/include/asm/futex.h @@ -106,12 +106,9 @@ lock = __atomic_hashed_lock((int __force *)uaddr) #endif

-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, + u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int uninitialized_var(val), ret;

__futex_prolog(); @@ -119,12 +116,6 @@ static inline int futex_atomic_op_inuser /* The 32-bit futex code makes this assumption, so validate it here. */ BUILD_BUG_ON(sizeof(atomic_t) != sizeof(int));

- if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT; - pagefault_disable(); switch (op) { case FUTEX_OP_SET: @@ -148,30 +139,9 @@ static inline int futex_atomic_op_inuser } pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: - ret = (val == cmparg); - break; - case FUTEX_OP_CMP_NE: - ret = (val != cmparg); - break; - case FUTEX_OP_CMP_LT: - ret = (val < cmparg); - break; - case FUTEX_OP_CMP_GE: - ret = (val >= cmparg); - break; - case FUTEX_OP_CMP_LE: - ret = (val <= cmparg); - break; - case FUTEX_OP_CMP_GT: - ret = (val > cmparg); - break; - default: - ret = -ENOSYS; - } - } + if (!ret) + *oval = val; + return ret; }

--- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -41,20 +41,11 @@ "+m" (*uaddr), "=&r" (tem) \ : "r" (oparg), "i" (-EFAULT), "1" (0))

-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, + u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret, tem;

- if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT; - pagefault_disable();

switch (op) { @@ -80,30 +71,9 @@ static inline int futex_atomic_op_inuser

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: - ret = (oldval == cmparg); - break; - case FUTEX_OP_CMP_NE: - ret = (oldval != cmparg); - break; - case FUTEX_OP_CMP_LT: - ret = (oldval < cmparg); - break; - case FUTEX_OP_CMP_GE: - ret = (oldval >= cmparg); - break; - case FUTEX_OP_CMP_LE: - ret = (oldval <= cmparg); - break; - case FUTEX_OP_CMP_GT: - ret = (oldval > cmparg); - break; - default: - ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/arch/xtensa/include/asm/futex.h +++ b/arch/xtensa/include/asm/futex.h @@ -44,18 +44,10 @@ : "r" (uaddr), "I" (-EFAULT), "r" (oparg) \ : "memory")

-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, + u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret; - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT;

#if !XCHAL_HAVE_S32C1I return -ENOSYS; @@ -89,19 +81,10 @@ static inline int futex_atomic_op_inuser

pagefault_enable();

- if (ret) - return ret; - - switch (cmp) { - case FUTEX_OP_CMP_EQ: return (oldval == cmparg); - case FUTEX_OP_CMP_NE: return (oldval != cmparg); - case FUTEX_OP_CMP_LT: return (oldval < cmparg); - case FUTEX_OP_CMP_GE: return (oldval >= cmparg); - case FUTEX_OP_CMP_LE: return (oldval <= cmparg); - case FUTEX_OP_CMP_GT: return (oldval > cmparg); - } + if (!ret) + *oval = oldval;

- return -ENOSYS; + return ret; }

static inline int --- a/include/asm-generic/futex.h +++ b/include/asm-generic/futex.h @@ -13,7 +13,7 @@ */

/** - * futex_atomic_op_inuser() - Atomic arithmetic operation with constant + * arch_futex_atomic_op_inuser() - Atomic arithmetic operation with constant * argument and comparison of the previous * futex value with another constant. * @@ -25,18 +25,11 @@ * <0 - On error */ static inline int -futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) +arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval, ret; u32 tmp;

- if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - preempt_disable(); pagefault_disable();

@@ -74,17 +67,9 @@ out_pagefault_enable: pagefault_enable(); preempt_enable();

- if (ret == 0) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (ret == 0) + *oval = oldval; + return ret; }

@@ -126,18 +111,9 @@ futex_atomic_cmpxchg_inatomic(u32 *uval,

#else static inline int -futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) +arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret; - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT;

pagefault_disable();

@@ -153,17 +129,9 @@ futex_atomic_op_inuser (int encoded_op,

pagefault_enable();

- if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; }

--- a/kernel/futex.c +++ b/kernel/futex.c @@ -1458,6 +1458,45 @@ out: return ret; }

+static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) +{ + unsigned int op = (encoded_op & 0x70000000) >> 28; + unsigned int cmp = (encoded_op & 0x0f000000) >> 24; + int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 12); + int cmparg = sign_extend32(encoded_op & 0x00000fff, 12); + int oldval, ret; + + if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) { + if (oparg < 0 || oparg > 31) + return -EINVAL; + oparg = 1 << oparg; + } + + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + return -EFAULT; + + ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr); + if (ret) + return ret; + + switch (cmp) { + case FUTEX_OP_CMP_EQ: + return oldval == cmparg; + case FUTEX_OP_CMP_NE: + return oldval != cmparg; + case FUTEX_OP_CMP_LT: + return oldval < cmparg; + case FUTEX_OP_CMP_GE: + return oldval >= cmparg; + case FUTEX_OP_CMP_LE: + return oldval <= cmparg; + case FUTEX_OP_CMP_GT: + return oldval > cmparg; + default: + return -ENOSYS; + } +} + /* * Wake up all waiters hashed on the physical page that is mapped * to this virtual address:

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

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

From: Vasily Averin vvs@virtuozzo.com

commit 3a2b19d1ee5633f76ae8a88da7bc039a5d1732aa upstream.

Commit efda760fe95ea ("lockd: fix lockd shutdown race") is incorrect, it removes lockd_manager and disarm grace_period_end for init_net only.

If nfsd was started from another net namespace lockd_up_net() calls set_grace_period() that adds lockd_manager into per-netns list and queues grace_period_end delayed work.

These action should be reverted in lockd_down_net(). Otherwise it can lead to double list_add on after restart nfsd in netns, and to use-after-free if non-disarmed delayed work will be executed after netns destroy.

Fixes: efda760fe95e ("lockd: fix lockd shutdown race") Cc: stable@vger.kernel.org Signed-off-by: Vasily Averin vvs@virtuozzo.com Signed-off-by: J. Bruce Fields bfields@redhat.com Cc: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/lockd/svc.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -274,6 +274,8 @@ static void lockd_down_net(struct svc_se if (ln->nlmsvc_users) { if (--ln->nlmsvc_users == 0) { nlm_shutdown_hosts_net(net); + cancel_delayed_work_sync(&ln->grace_period_end); + locks_end_grace(&ln->lockd_manager); svc_shutdown_net(serv, net); dprintk("lockd_down_net: per-net data destroyed; net=%p\n", net); }

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

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

From: James Chapman jchapman@katalix.com

commit de3b58bc359a861d5132300f53f95e83f71954b3 upstream.

Revert commit 820da5357572 ("l2tp: fix missing print session offset info"). The peer_offset parameter is removed.

Signed-off-by: James Chapman jchapman@katalix.com Signed-off-by: David S. Miller davem@davemloft.net Cc: Guillaume Nault g.nault@alphalink.fr Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- net/l2tp/l2tp_netlink.c | 2 -- 1 file changed, 2 deletions(-)

--- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -750,8 +750,6 @@ static int l2tp_nl_session_send(struct s

if ((session->ifname[0] && nla_put_string(skb, L2TP_ATTR_IFNAME, session->ifname)) || - (session->offset && - nla_put_u16(skb, L2TP_ATTR_OFFSET, session->offset)) || (session->cookie_len && nla_put(skb, L2TP_ATTR_COOKIE, session->cookie_len, &session->cookie[0])) ||

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

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

From: Willy Tarreau w@1wt.eu

commit 7f7ccc2ccc2e70c6054685f5e3522efa81556830 upstream.

proc_pid_cmdline_read() and environ_read() directly access the target process' VM to retrieve the command line and environment. If this process remaps these areas onto a file via mmap(), the requesting process may experience various issues such as extra delays if the underlying device is slow to respond.

Let's simply refuse to access file-backed areas in these functions. For this we add a new FOLL_ANON gup flag that is passed to all calls to access_remote_vm(). The code already takes care of such failures (including unmapped areas). Accesses via /proc/pid/mem were not changed though.

This was assigned CVE-2018-1120.

Note for stable backports: the patch may apply to kernels prior to 4.11 but silently miss one location; it must be checked that no call to access_remote_vm() keeps zero as the last argument.

Reported-by: Qualys Security Advisory qsa@qualys.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Andy Lutomirski luto@amacapital.net Cc: Oleg Nesterov oleg@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Willy Tarreau w@1wt.eu Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/proc/base.c | 10 +++++----- include/linux/mm.h | 1 + mm/gup.c | 3 +++ 3 files changed, 9 insertions(+), 5 deletions(-)

--- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -252,7 +252,7 @@ static ssize_t proc_pid_cmdline_read(str * Inherently racy -- command line shares address space * with code and data. */ - rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0); + rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON); if (rv <= 0) goto out_free_page;

@@ -270,7 +270,7 @@ static ssize_t proc_pid_cmdline_read(str int nr_read;

_count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, 0); + nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -305,7 +305,7 @@ static ssize_t proc_pid_cmdline_read(str bool final;

_count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, 0); + nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -354,7 +354,7 @@ skip_argv: bool final;

_count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, 0); + nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -970,7 +970,7 @@ static ssize_t environ_read(struct file max_len = min_t(size_t, PAGE_SIZE, count); this_len = min(max_len, this_len);

- retval = access_remote_vm(mm, (env_start + src), page, this_len, 0); + retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON);

if (retval <= 0) { ret = retval; --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2246,6 +2246,7 @@ static inline struct page *follow_page(s #define FOLL_MLOCK 0x1000 /* lock present pages */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ +#define FOLL_ANON 0x8000 /* don't do file mappings */

typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); --- a/mm/gup.c +++ b/mm/gup.c @@ -430,6 +430,9 @@ static int check_vma_flags(struct vm_are if (vm_flags & (VM_IO | VM_PFNMAP)) return -EFAULT;

+ if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma)) + return -EFAULT; + if (write) { if (!(vm_flags & VM_WRITE)) { if (!(gup_flags & FOLL_FORCE))