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

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

From: Stefano Brivio sbrivio@redhat.com

[ Upstream commit 66033f47ca60294a95fc85ec3a3cc909dab7b765 ]

Even if we send an IPv6 packet without options, MAX_HEADER might not be enough to account for the additional headroom required by alignment of hardware headers.

On a configuration without HYPERV_NET, WLAN, AX25, and with IPV6_TUNNEL, sending short SCTP packets over IPv4 over L2TP over IPv6, we start with 100 bytes of allocated headroom in sctp_packet_transmit(), end up with 54 bytes after l2tp_xmit_skb(), and 14 bytes in ip6_finish_output2().

Those would be enough to append our 14 bytes header, but we're going to align that to 16 bytes, and write 2 bytes out of the allocated slab in neigh_hh_output().

KASan says:

[ 264.967848] ================================================================== [ 264.967861] BUG: KASAN: slab-out-of-bounds in ip6_finish_output2+0x1aec/0x1c70 [ 264.967866] Write of size 16 at addr 000000006af1c7fe by task netperf/6201 [ 264.967870] [ 264.967876] CPU: 0 PID: 6201 Comm: netperf Not tainted 4.20.0-rc4+ #1 [ 264.967881] Hardware name: IBM 2827 H43 400 (z/VM 6.4.0) [ 264.967887] Call Trace: [ 264.967896] ([<00000000001347d6>] show_stack+0x56/0xa0) [ 264.967903] [<00000000017e379c>] dump_stack+0x23c/0x290 [ 264.967912] [<00000000007bc594>] print_address_description+0xf4/0x290 [ 264.967919] [<00000000007bc8fc>] kasan_report+0x13c/0x240 [ 264.967927] [<000000000162f5e4>] ip6_finish_output2+0x1aec/0x1c70 [ 264.967935] [<000000000163f890>] ip6_finish_output+0x430/0x7f0 [ 264.967943] [<000000000163fe44>] ip6_output+0x1f4/0x580 [ 264.967953] [<000000000163882a>] ip6_xmit+0xfea/0x1ce8 [ 264.967963] [<00000000017396e2>] inet6_csk_xmit+0x282/0x3f8 [ 264.968033] [<000003ff805fb0ba>] l2tp_xmit_skb+0xe02/0x13e0 [l2tp_core] [ 264.968037] [<000003ff80631192>] l2tp_eth_dev_xmit+0xda/0x150 [l2tp_eth] [ 264.968041] [<0000000001220020>] dev_hard_start_xmit+0x268/0x928 [ 264.968069] [<0000000001330e8e>] sch_direct_xmit+0x7ae/0x1350 [ 264.968071] [<000000000122359c>] __dev_queue_xmit+0x2b7c/0x3478 [ 264.968075] [<00000000013d2862>] ip_finish_output2+0xce2/0x11a0 [ 264.968078] [<00000000013d9b14>] ip_finish_output+0x56c/0x8c8 [ 264.968081] [<00000000013ddd1e>] ip_output+0x226/0x4c0 [ 264.968083] [<00000000013dbd6c>] __ip_queue_xmit+0x894/0x1938 [ 264.968100] [<000003ff80bc3a5c>] sctp_packet_transmit+0x29d4/0x3648 [sctp] [ 264.968116] [<000003ff80b7bf68>] sctp_outq_flush_ctrl.constprop.5+0x8d0/0xe50 [sctp] [ 264.968131] [<000003ff80b7c716>] sctp_outq_flush+0x22e/0x7d8 [sctp] [ 264.968146] [<000003ff80b35c68>] sctp_cmd_interpreter.isra.16+0x530/0x6800 [sctp] [ 264.968161] [<000003ff80b3410a>] sctp_do_sm+0x222/0x648 [sctp] [ 264.968177] [<000003ff80bbddac>] sctp_primitive_ASSOCIATE+0xbc/0xf8 [sctp] [ 264.968192] [<000003ff80b93328>] __sctp_connect+0x830/0xc20 [sctp] [ 264.968208] [<000003ff80bb11ce>] sctp_inet_connect+0x2e6/0x378 [sctp] [ 264.968212] [<0000000001197942>] __sys_connect+0x21a/0x450 [ 264.968215] [<000000000119aff8>] sys_socketcall+0x3d0/0xb08 [ 264.968218] [<000000000184ea7a>] system_call+0x2a2/0x2c0

[...]

Just like ip_finish_output2() does for IPv4, check that we have enough headroom in ip6_xmit(), and reallocate it if we don't.

This issue is older than git history.

Reported-by: Jianlin Shi jishi@redhat.com Signed-off-by: Stefano Brivio sbrivio@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/ip6_output.c | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-)

--- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -169,37 +169,37 @@ int ip6_xmit(const struct sock *sk, stru const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); + unsigned int head_room; struct ipv6hdr *hdr; u8 proto = fl6->flowi6_proto; int seg_len = skb->len; int hlimit = -1; u32 mtu;

- if (opt) { - unsigned int head_room; - - /* First: exthdrs may take lots of space (~8K for now) - MAX_HEADER is not enough. - */ - head_room = opt->opt_nflen + opt->opt_flen; - seg_len += head_room; - head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev); + head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev); + if (opt) + head_room += opt->opt_nflen + opt->opt_flen;

- if (skb_headroom(skb) < head_room) { - struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); - if (!skb2) { - IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTDISCARDS); - kfree_skb(skb); - return -ENOBUFS; - } - if (skb->sk) - skb_set_owner_w(skb2, skb->sk); - consume_skb(skb); - skb = skb2; + if (unlikely(skb_headroom(skb) < head_room)) { + struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room); + if (!skb2) { + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); + return -ENOBUFS; } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); + consume_skb(skb); + skb = skb2; + } + + if (opt) { + seg_len += opt->opt_nflen + opt->opt_flen; + if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); + if (opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop); }

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

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

From: Heiner Kallweit hkallweit1@gmail.com

[ Upstream commit d2a36971ef595069b7a600d1144c2e0881a930a1 ]

Currently __set_phy_supported allows to add modes w/o checking whether the PHY supports them. This is wrong, it should never add modes but only remove modes we don't want to support.

The commit marked as fixed didn't do anything wrong, it just copied existing functionality to the helper which is being fixed now.

Fixes: f3a6bd393c2c ("phylib: Add phy_set_max_speed helper") Signed-off-by: Heiner Kallweit hkallweit1@gmail.com Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/phy_device.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-)

--- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1265,20 +1265,17 @@ static int gen10g_resume(struct phy_devi

static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) { - phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES | - PHY_10BT_FEATURES); - switch (max_speed) { - default: - return -ENOTSUPP; - case SPEED_1000: - phydev->supported |= PHY_1000BT_FEATURES; + case SPEED_10: + phydev->supported &= ~PHY_100BT_FEATURES; /* fall through */ case SPEED_100: - phydev->supported |= PHY_100BT_FEATURES; - /* fall through */ - case SPEED_10: - phydev->supported |= PHY_10BT_FEATURES; + phydev->supported &= ~PHY_1000BT_FEATURES; + break; + case SPEED_1000: + break; + default: + return -ENOTSUPP; }

return 0;

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

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

From: Eric Dumazet edumazet@google.com

[ Upstream commit 688838934c231bb08f46db687e57f6d8bf82709c ]

kmsan was able to trigger a kernel-infoleak using a gre device [1]

nlmsg_populate_fdb_fill() has a hard coded assumption that dev->addr_len is ETH_ALEN, as normally guaranteed for ARPHRD_ETHER devices.

A similar issue was fixed recently in commit da71577545a5 ("rtnetlink: Disallow FDB configuration for non-Ethernet device")

[1] BUG: KMSAN: kernel-infoleak in copyout lib/iov_iter.c:143 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x4c0/0x2700 lib/iov_iter.c:576 CPU: 0 PID: 6697 Comm: syz-executor310 Not tainted 4.20.0-rc3+ #95 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+0x32d/0x480 lib/dump_stack.c:113 kmsan_report+0x12c/0x290 mm/kmsan/kmsan.c:683 kmsan_internal_check_memory+0x32a/0xa50 mm/kmsan/kmsan.c:743 kmsan_copy_to_user+0x78/0xd0 mm/kmsan/kmsan_hooks.c:634 copyout lib/iov_iter.c:143 [inline] _copy_to_iter+0x4c0/0x2700 lib/iov_iter.c:576 copy_to_iter include/linux/uio.h:143 [inline] skb_copy_datagram_iter+0x4e2/0x1070 net/core/datagram.c:431 skb_copy_datagram_msg include/linux/skbuff.h:3316 [inline] netlink_recvmsg+0x6f9/0x19d0 net/netlink/af_netlink.c:1975 sock_recvmsg_nosec net/socket.c:794 [inline] sock_recvmsg+0x1d1/0x230 net/socket.c:801 ___sys_recvmsg+0x444/0xae0 net/socket.c:2278 __sys_recvmsg net/socket.c:2327 [inline] __do_sys_recvmsg net/socket.c:2337 [inline] __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334 do_syscall_64+0xcf/0x110 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x441119 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 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 0f 83 db 0a fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fffc7f008a8 EFLAGS: 00000207 ORIG_RAX: 000000000000002f RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 0000000000441119 RDX: 0000000000000040 RSI: 00000000200005c0 RDI: 0000000000000003 RBP: 00000000006cc018 R08: 0000000000000100 R09: 0000000000000100 R10: 0000000000000100 R11: 0000000000000207 R12: 0000000000402080 R13: 0000000000402110 R14: 0000000000000000 R15: 0000000000000000

Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:246 [inline] kmsan_save_stack mm/kmsan/kmsan.c:261 [inline] kmsan_internal_chain_origin+0x13d/0x240 mm/kmsan/kmsan.c:469 kmsan_memcpy_memmove_metadata+0x1a9/0xf70 mm/kmsan/kmsan.c:344 kmsan_memcpy_metadata+0xb/0x10 mm/kmsan/kmsan.c:362 __msan_memcpy+0x61/0x70 mm/kmsan/kmsan_instr.c:162 __nla_put lib/nlattr.c:744 [inline] nla_put+0x20a/0x2d0 lib/nlattr.c:802 nlmsg_populate_fdb_fill+0x444/0x810 net/core/rtnetlink.c:3466 nlmsg_populate_fdb net/core/rtnetlink.c:3775 [inline] ndo_dflt_fdb_dump+0x73a/0x960 net/core/rtnetlink.c:3807 rtnl_fdb_dump+0x1318/0x1cb0 net/core/rtnetlink.c:3979 netlink_dump+0xc79/0x1c90 net/netlink/af_netlink.c:2244 __netlink_dump_start+0x10c4/0x11d0 net/netlink/af_netlink.c:2352 netlink_dump_start include/linux/netlink.h:216 [inline] rtnetlink_rcv_msg+0x141b/0x1540 net/core/rtnetlink.c:4910 netlink_rcv_skb+0x394/0x640 net/netlink/af_netlink.c:2477 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4965 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0x1699/0x1740 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x13c7/0x1440 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xe3b/0x1240 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x305/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xcf/0x110 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:246 [inline] kmsan_internal_poison_shadow+0x6d/0x130 mm/kmsan/kmsan.c:170 kmsan_kmalloc+0xa1/0x100 mm/kmsan/kmsan_hooks.c:186 __kmalloc+0x14c/0x4d0 mm/slub.c:3825 kmalloc include/linux/slab.h:551 [inline] __hw_addr_create_ex net/core/dev_addr_lists.c:34 [inline] __hw_addr_add_ex net/core/dev_addr_lists.c:80 [inline] __dev_mc_add+0x357/0x8a0 net/core/dev_addr_lists.c:670 dev_mc_add+0x6d/0x80 net/core/dev_addr_lists.c:687 ip_mc_filter_add net/ipv4/igmp.c:1128 [inline] igmp_group_added+0x4d4/0xb80 net/ipv4/igmp.c:1311 __ip_mc_inc_group+0xea9/0xf70 net/ipv4/igmp.c:1444 ip_mc_inc_group net/ipv4/igmp.c:1453 [inline] ip_mc_up+0x1c3/0x400 net/ipv4/igmp.c:1775 inetdev_event+0x1d03/0x1d80 net/ipv4/devinet.c:1522 notifier_call_chain kernel/notifier.c:93 [inline] __raw_notifier_call_chain kernel/notifier.c:394 [inline] raw_notifier_call_chain+0x13d/0x240 kernel/notifier.c:401 __dev_notify_flags+0x3da/0x860 net/core/dev.c:1733 dev_change_flags+0x1ac/0x230 net/core/dev.c:7569 do_setlink+0x165f/0x5ea0 net/core/rtnetlink.c:2492 rtnl_newlink+0x2ad7/0x35a0 net/core/rtnetlink.c:3111 rtnetlink_rcv_msg+0x1148/0x1540 net/core/rtnetlink.c:4947 netlink_rcv_skb+0x394/0x640 net/netlink/af_netlink.c:2477 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:4965 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0x1699/0x1740 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x13c7/0x1440 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xe3b/0x1240 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x305/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xcf/0x110 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Bytes 36-37 of 105 are uninitialized Memory access of size 105 starts at ffff88819686c000 Data copied to user address 0000000020000380

Fixes: d83b06036048 ("net: add fdb generic dump routine") Signed-off-by: Eric Dumazet edumazet@google.com Cc: John Fastabend john.fastabend@gmail.com Cc: Ido Schimmel idosch@mellanox.com Cc: David Ahern dsahern@gmail.com Reviewed-by: Ido Schimmel idosch@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/rtnetlink.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2931,6 +2931,9 @@ int ndo_dflt_fdb_dump(struct sk_buff *sk { int err;

+ if (dev->type != ARPHRD_ETHER) + return -EINVAL; + netif_addr_lock_bh(dev); err = nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->uc); if (err)

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

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

From: Nicolas Dichtel nicolas.dichtel@6wind.com

[ Upstream commit 35b827b6d06199841a83839e8bb69c0cd13a28be ]

It's not supported right now (the goal of the initial patch was to support 'ip link del' only).

Before the patch: $ ip link add foo type tun [ 239.632660] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 [snip] [ 239.636410] RIP: 0010:register_netdevice+0x8e/0x3a0

This panic occurs because dev->netdev_ops is not set by tun_setup(). But to have something usable, it will require more than just setting netdev_ops.

Fixes: f019a7a594d9 ("tun: Implement ip link del tunXXX") CC: Eric W. Biederman ebiederm@xmission.com Signed-off-by: Nicolas Dichtel nicolas.dichtel@6wind.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/tun.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1475,9 +1475,9 @@ static void tun_setup(struct net_device */ static int tun_validate(struct nlattr *tb[], struct nlattr *data[]) { - if (!data) - return 0; - return -EINVAL; + /* NL_SET_ERR_MSG(extack, + "tun/tap creation via rtnetlink is not supported."); */ + return -EOPNOTSUPP; }

static struct rtnl_link_ops tun_link_ops __read_mostly = {

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

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

From: Jiri Wiesner jwiesner@suse.com

[ Upstream commit ebaf39e6032faf77218220707fc3fa22487784e0 ]

The *_frag_reasm() functions are susceptible to miscalculating the byte count of packet fragments in case the truesize of a head buffer changes. The truesize member may be changed by the call to skb_unclone(), leaving the fragment memory limit counter unbalanced even if all fragments are processed. This miscalculation goes unnoticed as long as the network namespace which holds the counter is not destroyed.

Should an attempt be made to destroy a network namespace that holds an unbalanced fragment memory limit counter the cleanup of the namespace never finishes. The thread handling the cleanup gets stuck in inet_frags_exit_net() waiting for the percpu counter to reach zero. The thread is usually in running state with a stacktrace similar to:

PID: 1073 TASK: ffff880626711440 CPU: 1 COMMAND: "kworker/u48:4" #5 [ffff880621563d48] _raw_spin_lock at ffffffff815f5480 #6 [ffff880621563d48] inet_evict_bucket at ffffffff8158020b #7 [ffff880621563d80] inet_frags_exit_net at ffffffff8158051c #8 [ffff880621563db0] ops_exit_list at ffffffff814f5856 #9 [ffff880621563dd8] cleanup_net at ffffffff814f67c0 #10 [ffff880621563e38] process_one_work at ffffffff81096f14

It is not possible to create new network namespaces, and processes that call unshare() end up being stuck in uninterruptible sleep state waiting to acquire the net_mutex.

The bug was observed in the IPv6 netfilter code by Per Sundstrom. I thank him for his analysis of the problem. The parts of this patch that apply to IPv4 and IPv6 fragment reassembly are preemptive measures.

Signed-off-by: Jiri Wiesner jwiesner@suse.com Reported-by: Per Sundstrom per.sundstrom@redqube.se Acked-by: Peter Oskolkov posk@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/ip_fragment.c | 7 +++++++ net/ipv6/netfilter/nf_conntrack_reasm.c | 8 +++++++- net/ipv6/reassembly.c | 8 +++++++- 3 files changed, 21 insertions(+), 2 deletions(-)

--- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -538,6 +538,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *fp, *head = qp->q.fragments; int len; int ihlen; + int delta; int err; u8 ecn;

@@ -578,10 +579,16 @@ static int ip_frag_reasm(struct ipq *qp, if (len > 65535) goto out_oversize;

+ delta = - head->truesize; + /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) goto out_nomem;

+ delta += head->truesize; + if (delta) + add_frag_mem_limit(qp->q.net, delta); + /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -380,7 +380,7 @@ static struct sk_buff * nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) { struct sk_buff *fp, *op, *head = fq->q.fragments; - int payload_len; + int payload_len, delta; u8 ecn;

inet_frag_kill(&fq->q, &nf_frags); @@ -401,12 +401,18 @@ nf_ct_frag6_reasm(struct frag_queue *fq, goto out_oversize; }

+ delta = - head->truesize; + /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) { pr_debug("skb is cloned but can't expand head"); goto out_oom; }

+ delta += head->truesize; + if (delta) + add_frag_mem_limit(fq->q.net, delta); + /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -381,7 +381,7 @@ static int ip6_frag_reasm(struct frag_qu { struct net *net = container_of(fq->q.net, struct net, ipv6.frags); struct sk_buff *fp, *head = fq->q.fragments; - int payload_len; + int payload_len, delta; unsigned int nhoff; int sum_truesize; u8 ecn; @@ -422,10 +422,16 @@ static int ip6_frag_reasm(struct frag_qu if (payload_len > IPV6_MAXPLEN) goto out_oversize;

+ delta = - head->truesize; + /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) goto out_oom;

+ delta += head->truesize; + if (delta) + add_frag_mem_limit(fq->q.net, delta); + /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */

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

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

[ Upstream commit eef3dc34a1e0b01d53328b88c25237bcc7323777 ]

When building the kernel with Clang, the following section mismatch warning appears:

WARNING: vmlinux.o(.text+0x38b3c): Section mismatch in reference from the function omap44xx_prm_late_init() to the function .init.text:omap44xx_prm_enable_io_wakeup() The function omap44xx_prm_late_init() references the function __init omap44xx_prm_enable_io_wakeup(). This is often because omap44xx_prm_late_init lacks a __init annotation or the annotation of omap44xx_prm_enable_io_wakeup is wrong.

Remove the __init annotation from omap44xx_prm_enable_io_wakeup so there is no more mismatch.

Signed-off-by: Nathan Chancellor natechancellor@gmail.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-omap2/prm44xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c index 30768003f854..8c505284bc0c 100644 --- a/arch/arm/mach-omap2/prm44xx.c +++ b/arch/arm/mach-omap2/prm44xx.c @@ -344,7 +344,7 @@ static void omap44xx_prm_reconfigure_io_chain(void) * to occur, WAKEUPENABLE bits must be set in the pad mux registers, and * omap44xx_prm_reconfigure_io_chain() must be called. No return value. */ -static void __init omap44xx_prm_enable_io_wakeup(void) +static void omap44xx_prm_enable_io_wakeup(void) { s32 inst = omap4_prmst_get_prm_dev_inst();

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

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

[ Upstream commit c4b7d1ba7d263b74bb72e9325262a67139605cde ]

Fixes gcc '-Wunused-but-set-variable' warning:

fs/sysv/inode.c: In function '__sysv_write_inode': fs/sysv/inode.c:239:6: warning: variable 'err' set but not used [-Wunused-but-set-variable]

__sysv_write_inode should return 'err' instead of 0

Fixes: 05459ca81ac3 ("repair sysv_write_inode(), switch sysv to simple_fsync()") Signed-off-by: YueHaibing yuehaibing@huawei.com Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- fs/sysv/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 02fa1dcc5969..29f5b2e589a1 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -275,7 +275,7 @@ static int __sysv_write_inode(struct inode *inode, int wait) } } brelse(bh); - return 0; + return err; }

int sysv_write_inode(struct inode *inode, struct writeback_control *wbc)

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

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

[ Upstream commit 38cd989ee38c16388cde89db5b734f9d55b905f9 ]

The current register (04h) has a sign bit at MSB. The comments for this calculation also mention that it's a signed register.

However, the regval is unsigned type so result of calculation turns out to be an incorrect value when current is negative.

This patch simply fixes this by adding a casting to s16.

Fixes: 5d389b125186c ("hwmon: (ina2xx) Make calibration register value fixed") Signed-off-by: Nicolin Chen nicoleotsuka@gmail.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/ina2xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index 9ac6e1673375..1f291b344178 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -273,7 +273,7 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg, break; case INA2XX_CURRENT: /* signed register, result in mA */ - val = regval * data->current_lsb_uA; + val = (s16)regval * data->current_lsb_uA; val = DIV_ROUND_CLOSEST(val, 1000); break; case INA2XX_CALIBRATION:

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

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

[ Upstream commit 09aaf6813cfca4c18034fda7a43e68763f34abb1 ]

Both datasheet and comments of store_temp_mode() tell us that temp1~4_type is writable, so fix it.

Signed-off-by: Yao Wang wangyao@lemote.com Signed-off-by: Huacai Chen chenhc@lemote.com Fixes: 39deb6993e7c (" hwmon: (w83795) Simplify temperature sensor type handling") Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/w83795.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/w83795.c b/drivers/hwmon/w83795.c index 49276bbdac3d..1bb80f992aa8 100644 --- a/drivers/hwmon/w83795.c +++ b/drivers/hwmon/w83795.c @@ -1691,7 +1691,7 @@ store_sf_setup(struct device *dev, struct device_attribute *attr, * somewhere else in the code */ #define SENSOR_ATTR_TEMP(index) { \ - SENSOR_ATTR_2(temp##index##_type, S_IRUGO | (index < 4 ? S_IWUSR : 0), \ + SENSOR_ATTR_2(temp##index##_type, S_IRUGO | (index < 5 ? S_IWUSR : 0), \ show_temp_mode, store_temp_mode, NOT_USED, index - 1), \ SENSOR_ATTR_2(temp##index##_input, S_IRUGO, show_temp, \ NULL, TEMP_READ, index - 1), \

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

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

[ Upstream commit 373a500e34aea97971c9d71e45edad458d3da98f ]

We need to block sleep states which would require longer time to leave than the time the DMA must react to the DMA request in order to keep the FIFO serviced without under of overrun.

Signed-off-by: Peter Ujfalusi peter.ujfalusi@ti.com Acked-by: Jarkko Nikula jarkko.nikula@bitmer.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/omap/omap-mcpdm.c | 43 ++++++++++++++++++++++++++++++++++++- 1 file changed, 42 insertions(+), 1 deletion(-)

diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c index 8d0d45d330e7..8eb2d12b6a34 100644 --- a/sound/soc/omap/omap-mcpdm.c +++ b/sound/soc/omap/omap-mcpdm.c @@ -54,6 +54,8 @@ struct omap_mcpdm { unsigned long phys_base; void __iomem *io_base; int irq; + struct pm_qos_request pm_qos_req; + int latency[2];

struct mutex mutex;

@@ -273,6 +275,9 @@ static void omap_mcpdm_dai_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); + int tx = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK); + int stream1 = tx ? SNDRV_PCM_STREAM_PLAYBACK : SNDRV_PCM_STREAM_CAPTURE; + int stream2 = tx ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;

mutex_lock(&mcpdm->mutex);

@@ -285,6 +290,14 @@ static void omap_mcpdm_dai_shutdown(struct snd_pcm_substream *substream, } }

+ if (mcpdm->latency[stream2]) + pm_qos_update_request(&mcpdm->pm_qos_req, + mcpdm->latency[stream2]); + else if (mcpdm->latency[stream1]) + pm_qos_remove_request(&mcpdm->pm_qos_req); + + mcpdm->latency[stream1] = 0; + mutex_unlock(&mcpdm->mutex); }

@@ -296,7 +309,7 @@ static int omap_mcpdm_dai_hw_params(struct snd_pcm_substream *substream, int stream = substream->stream; struct snd_dmaengine_dai_dma_data *dma_data; u32 threshold; - int channels; + int channels, latency; int link_mask = 0;

channels = params_channels(params); @@ -336,14 +349,25 @@ static int omap_mcpdm_dai_hw_params(struct snd_pcm_substream *substream,

dma_data->maxburst = (MCPDM_DN_THRES_MAX - threshold) * channels; + latency = threshold; } else { /* If playback is not running assume a stereo stream to come */ if (!mcpdm->config[!stream].link_mask) mcpdm->config[!stream].link_mask = (0x3 << 3);

dma_data->maxburst = threshold * channels; + latency = (MCPDM_DN_THRES_MAX - threshold); }

+ /* + * The DMA must act to a DMA request within latency time (usec) to avoid + * under/overflow + */ + mcpdm->latency[stream] = latency * USEC_PER_SEC / params_rate(params); + + if (!mcpdm->latency[stream]) + mcpdm->latency[stream] = 10; + /* Check if we need to restart McPDM with this stream */ if (mcpdm->config[stream].link_mask && mcpdm->config[stream].link_mask != link_mask) @@ -358,6 +382,20 @@ static int omap_mcpdm_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); + struct pm_qos_request *pm_qos_req = &mcpdm->pm_qos_req; + int tx = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK); + int stream1 = tx ? SNDRV_PCM_STREAM_PLAYBACK : SNDRV_PCM_STREAM_CAPTURE; + int stream2 = tx ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK; + int latency = mcpdm->latency[stream2]; + + /* Prevent omap hardware from hitting off between FIFO fills */ + if (!latency || mcpdm->latency[stream1] < latency) + latency = mcpdm->latency[stream1]; + + if (pm_qos_request_active(pm_qos_req)) + pm_qos_update_request(pm_qos_req, latency); + else if (latency) + pm_qos_add_request(pm_qos_req, PM_QOS_CPU_DMA_LATENCY, latency);

if (!omap_mcpdm_active(mcpdm)) { omap_mcpdm_start(mcpdm); @@ -419,6 +457,9 @@ static int omap_mcpdm_remove(struct snd_soc_dai *dai) free_irq(mcpdm->irq, (void *)mcpdm); pm_runtime_disable(mcpdm->dev);

+ if (pm_qos_request_active(&mcpdm->pm_qos_req)) + pm_qos_remove_request(&mcpdm->pm_qos_req); + return 0; }

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

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

[ Upstream commit 2084ac6c505a58f7efdec13eba633c6aaa085ca5 ]

The function dentry_connected calls dput(dentry) to drop the previously acquired reference to dentry. In this case, dentry can be released. After that, IS_ROOT(dentry) checks the condition (dentry == dentry->d_parent), which may result in a use-after-free bug. This patch directly compares dentry with its parent obtained before dropping the reference.

Fixes: a056cc8934c("exportfs: stop retrying once we race with rename/remove")

Signed-off-by: Pan Bian bianpan2016@163.com Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- fs/exportfs/expfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 714cd37a6ba3..6599c6124552 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -76,7 +76,7 @@ static bool dentry_connected(struct dentry *dentry) struct dentry *parent = dget_parent(dentry);

dput(dentry); - if (IS_ROOT(dentry)) { + if (dentry == parent) { dput(parent); return false; }

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

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

[ Upstream commit 286afdde1640d8ea8916a0f05e811441fbbf4b9d ]

The current code fails to release the third irq on the error path (observed by reading the code), and we get also multiple WARNs with failing gadget drivers due to duplicate IRQ releases. Fix by using devm_request_irq().

Signed-off-by: Aaro Koskinen aaro.koskinen@iki.fi Signed-off-by: Felipe Balbi felipe.balbi@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/gadget/udc/omap_udc.c | 37 +++++++++---------------------- 1 file changed, 10 insertions(+), 27 deletions(-)

diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c index 9b7d39484ed3..b25eac2dcaf8 100644 --- a/drivers/usb/gadget/udc/omap_udc.c +++ b/drivers/usb/gadget/udc/omap_udc.c @@ -2886,8 +2886,8 @@ static int omap_udc_probe(struct platform_device *pdev) udc->clr_halt = UDC_RESET_EP;

/* USB general purpose IRQ: ep0, state changes, dma, etc */ - status = request_irq(pdev->resource[1].start, omap_udc_irq, - 0, driver_name, udc); + status = devm_request_irq(&pdev->dev, pdev->resource[1].start, + omap_udc_irq, 0, driver_name, udc); if (status != 0) { ERR("can't get irq %d, err %d\n", (int) pdev->resource[1].start, status); @@ -2895,20 +2895,20 @@ static int omap_udc_probe(struct platform_device *pdev) }

/* USB "non-iso" IRQ (PIO for all but ep0) */ - status = request_irq(pdev->resource[2].start, omap_udc_pio_irq, - 0, "omap_udc pio", udc); + status = devm_request_irq(&pdev->dev, pdev->resource[2].start, + omap_udc_pio_irq, 0, "omap_udc pio", udc); if (status != 0) { ERR("can't get irq %d, err %d\n", (int) pdev->resource[2].start, status); - goto cleanup2; + goto cleanup1; } #ifdef USE_ISO - status = request_irq(pdev->resource[3].start, omap_udc_iso_irq, - 0, "omap_udc iso", udc); + status = devm_request_irq(&pdev->dev, pdev->resource[3].start, + omap_udc_iso_irq, 0, "omap_udc iso", udc); if (status != 0) { ERR("can't get irq %d, err %d\n", (int) pdev->resource[3].start, status); - goto cleanup3; + goto cleanup1; } #endif if (cpu_is_omap16xx() || cpu_is_omap7xx()) { @@ -2921,22 +2921,11 @@ static int omap_udc_probe(struct platform_device *pdev) create_proc_file(); status = usb_add_gadget_udc_release(&pdev->dev, &udc->gadget, omap_udc_release); - if (status) - goto cleanup4; - - return 0; + if (!status) + return 0;

-cleanup4: remove_proc_file();

-#ifdef USE_ISO -cleanup3: - free_irq(pdev->resource[2].start, udc); -#endif - -cleanup2: - free_irq(pdev->resource[1].start, udc); - cleanup1: kfree(udc); udc = NULL; @@ -2980,12 +2969,6 @@ static int omap_udc_remove(struct platform_device *pdev)

remove_proc_file();

-#ifdef USE_ISO - free_irq(pdev->resource[3].start, udc); -#endif - free_irq(pdev->resource[2].start, udc); - free_irq(pdev->resource[1].start, udc); - if (udc->dc_clk) { if (udc->clk_requested) omap_udc_enable_clock(0);

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

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

[ Upstream commit 6ca6695f576b8453fe68865e84d25946d63b10ad ]

On OMAP 15xx machines there are no transceivers, and omap_udc_start() always fails as it forgot to adjust the default return value.

Signed-off-by: Aaro Koskinen aaro.koskinen@iki.fi Signed-off-by: Felipe Balbi felipe.balbi@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/gadget/udc/omap_udc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c index da1030f69145..653963459d78 100644 --- a/drivers/usb/gadget/udc/omap_udc.c +++ b/drivers/usb/gadget/udc/omap_udc.c @@ -2045,7 +2045,7 @@ static inline int machine_without_vbus_sense(void) static int omap_udc_start(struct usb_gadget *g, struct usb_gadget_driver *driver) { - int status = -ENODEV; + int status; struct omap_ep *ep; unsigned long flags;

@@ -2083,6 +2083,7 @@ static int omap_udc_start(struct usb_gadget *g, goto done; } } else { + status = 0; if (can_pullup(udc)) pullup_enable(udc); else

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

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

[ Upstream commit 354cb410d87314e2eda344feea84809e4261570a ]

We get the following warnings about empty statements when building with 'W=1':

arch/x86/kvm/lapic.c:632:53: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] arch/x86/kvm/lapic.c:1907:42: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] arch/x86/kvm/lapic.c:1936:65: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body] arch/x86/kvm/lapic.c:1975:44: warning: suggest braces around empty body in an ‘if’ statement [-Wempty-body]

Rework the debug helper macro to get rid of these warnings.

Signed-off-by: Yi Wang wang.yi59@zte.com.cn Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/lapic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index a1afd80a68aa..3c70f6c76d3a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -56,7 +56,7 @@ #define APIC_BUS_CYCLE_NS 1

/* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */ -#define apic_debug(fmt, arg...) +#define apic_debug(fmt, arg...) do {} while (0)

#define APIC_LVT_NUM 6 /* 14 is the version for Xeon and Pentium 8.4.8*/

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

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

[ Upstream commit a8bf879af7b1999eba36303ce9cc60e0e7dd816c ]

Add the two 1000BaseLX enum values to the X550's check for 1Gbps modules, allowing the core driver code to establish a link over this SFP type.

This is done by the out-of-tree driver but the fix wasn't in mainline.

Fixes: e23f33367882 ("ixgbe: Fix 1G and 10G link stability for X550EM_x SFP+”) Fixes: 6a14ee0cfb19 ("ixgbe: Add X550 support function pointers") Signed-off-by: Josh Elsasser jelsasser@appneta.com Tested-by: Andrew Bowers andrewx.bowers@intel.com Signed-off-by: Jeff Kirsher jeffrey.t.kirsher@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index ffd2e74e5638..dcd718ce13d5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -1429,7 +1429,9 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, *autoneg = false;

if (hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || - hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1) { + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1) { *speed = IXGBE_LINK_SPEED_1GB_FULL; return 0; }

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

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

[ Upstream commit 300625620314194d9e6d4f6dda71f2dc9cf62d9f ]

v1: over-sample data to increase the stability with some specific monitors v2: refine to avoid infinite loop v3: remove un-necessary "volatile" declaration

[airlied: fix two checkpatch warnings]

Signed-off-by: Y.C. Chen yc_chen@aspeedtech.com Signed-off-by: Dave Airlie airlied@redhat.com Link: https://patchwork.freedesktop.org/patch/msgid/1542858988-1127-1-git-send-ema... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/ast/ast_mode.c | 36 ++++++++++++++++++++++++++++------ 1 file changed, 30 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 21085f669e21..b19ba1792607 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -968,9 +968,21 @@ static int get_clock(void *i2c_priv) { struct ast_i2c_chan *i2c = i2c_priv; struct ast_private *ast = i2c->dev->dev_private; - uint32_t val; + uint32_t val, val2, count, pass; + + count = 0; + pass = 0; + val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4) & 0x01; + do { + val2 = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4) & 0x01; + if (val == val2) { + pass++; + } else { + pass = 0; + val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4) & 0x01; + } + } while ((pass < 5) && (count++ < 0x10000));

- val = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4; return val & 1 ? 1 : 0; }

@@ -978,9 +990,21 @@ static int get_data(void *i2c_priv) { struct ast_i2c_chan *i2c = i2c_priv; struct ast_private *ast = i2c->dev->dev_private; - uint32_t val; + uint32_t val, val2, count, pass; + + count = 0; + pass = 0; + val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5) & 0x01; + do { + val2 = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5) & 0x01; + if (val == val2) { + pass++; + } else { + pass = 0; + val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5) & 0x01; + } + } while ((pass < 5) && (count++ < 0x10000));

- val = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5; return val & 1 ? 1 : 0; }

@@ -993,7 +1017,7 @@ static void set_clock(void *i2c_priv, int clock)

for (i = 0; i < 0x10000; i++) { ujcrb7 = ((clock & 0x01) ? 0 : 1); - ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xfe, ujcrb7); + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xf4, ujcrb7); jtemp = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x01); if (ujcrb7 == jtemp) break; @@ -1009,7 +1033,7 @@ static void set_data(void *i2c_priv, int data)

for (i = 0; i < 0x10000; i++) { ujcrb7 = ((data & 0x01) ? 0 : 1) << 2; - ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xfb, ujcrb7); + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xf1, ujcrb7); jtemp = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x04); if (ujcrb7 == jtemp) break;

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

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

[ Upstream commit c5a94f434c82529afda290df3235e4d85873c5b4 ]

It was observed that a process blocked indefintely in __fscache_read_or_alloc_page(), waiting for FSCACHE_COOKIE_LOOKING_UP to be cleared via fscache_wait_for_deferred_lookup().

At this time, ->backing_objects was empty, which would normaly prevent __fscache_read_or_alloc_page() from getting to the point of waiting. This implies that ->backing_objects was cleared *after* __fscache_read_or_alloc_page was was entered.

When an object is "killed" and then "dropped", FSCACHE_COOKIE_LOOKING_UP is cleared in fscache_lookup_failure(), then KILL_OBJECT and DROP_OBJECT are "called" and only in DROP_OBJECT is ->backing_objects cleared. This leaves a window where something else can set FSCACHE_COOKIE_LOOKING_UP and __fscache_read_or_alloc_page() can start waiting, before ->backing_objects is cleared

There is some uncertainty in this analysis, but it seems to be fit the observations. Adding the wake in this patch will be handled correctly by __fscache_read_or_alloc_page(), as it checks if ->backing_objects is empty again, after waiting.

Customer which reported the hang, also report that the hang cannot be reproduced with this fix.

The backtrace for the blocked process looked like:

PID: 29360 TASK: ffff881ff2ac0f80 CPU: 3 COMMAND: "zsh" #0 [ffff881ff43efbf8] schedule at ffffffff815e56f1 #1 [ffff881ff43efc58] bit_wait at ffffffff815e64ed #2 [ffff881ff43efc68] __wait_on_bit at ffffffff815e61b8 #3 [ffff881ff43efca0] out_of_line_wait_on_bit at ffffffff815e625e #4 [ffff881ff43efd08] fscache_wait_for_deferred_lookup at ffffffffa04f2e8f [fscache] #5 [ffff881ff43efd18] __fscache_read_or_alloc_page at ffffffffa04f2ffe [fscache] #6 [ffff881ff43efd58] __nfs_readpage_from_fscache at ffffffffa0679668 [nfs] #7 [ffff881ff43efd78] nfs_readpage at ffffffffa067092b [nfs] #8 [ffff881ff43efda0] generic_file_read_iter at ffffffff81187a73 #9 [ffff881ff43efe50] nfs_file_read at ffffffffa066544b [nfs] #10 [ffff881ff43efe70] __vfs_read at ffffffff811fc756 #11 [ffff881ff43efee8] vfs_read at ffffffff811fccfa #12 [ffff881ff43eff18] sys_read at ffffffff811fda62 #13 [ffff881ff43eff50] entry_SYSCALL_64_fastpath at ffffffff815e986e

Signed-off-by: NeilBrown neilb@suse.com Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/fscache/object.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 7a182c87f378..ab1d7f35f6c2 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -715,6 +715,9 @@ static const struct fscache_state *fscache_drop_object(struct fscache_object *ob

if (awaken) wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING); + if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) + wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); +

/* Prevent a race with our last child, which has to signal EV_CLEARED * before dropping our spinlock.

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

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

[ Upstream commit e21e57445a64598b29a6f629688f9b9a39e7242a ]

ocfs2_defrag_extent may fall into deadlock.

ocfs2_ioctl_move_extents ocfs2_ioctl_move_extents ocfs2_move_extents ocfs2_defrag_extent ocfs2_lock_allocators_move_extents

ocfs2_reserve_clusters inode_lock GLOBAL_BITMAP_SYSTEM_INODE

__ocfs2_flush_truncate_log inode_lock GLOBAL_BITMAP_SYSTEM_INODE

As backtrace shows above, ocfs2_reserve_clusters() will call inode_lock against the global bitmap if local allocator has not sufficient cluters. Once global bitmap could meet the demand, ocfs2_reserve_cluster will return success with global bitmap locked.

After ocfs2_reserve_cluster(), if truncate log is full, __ocfs2_flush_truncate_log() will definitely fall into deadlock because it needs to inode_lock global bitmap, which has already been locked.

To fix this bug, we could remove from ocfs2_lock_allocators_move_extents() the code which intends to lock global allocator, and put the removed code after __ocfs2_flush_truncate_log().

ocfs2_lock_allocators_move_extents() is referred by 2 places, one is here, the other does not need the data allocator context, which means this patch does not affect the caller so far.

Link: http://lkml.kernel.org/r/20181101071422.14470-1-lchen@suse.com Signed-off-by: Larry Chen lchen@suse.com Reviewed-by: Changwei Ge ge.changwei@h3c.com Cc: Mark Fasheh mark@fasheh.com Cc: Joel Becker jlbec@evilplan.org Cc: Junxiao Bi junxiao.bi@oracle.com Cc: Joseph Qi jiangqi903@gmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ocfs2/move_extents.c | 47 +++++++++++++++++++++++------------------ 1 file changed, 26 insertions(+), 21 deletions(-)

diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 124471d26a73..c1a83c58456e 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -156,18 +156,14 @@ static int __ocfs2_move_extent(handle_t *handle, }

/* - * lock allocators, and reserving appropriate number of bits for - * meta blocks and data clusters. - * - * in some cases, we don't need to reserve clusters, just let data_ac - * be NULL. + * lock allocator, and reserve appropriate number of bits for + * meta blocks. */ -static int ocfs2_lock_allocators_move_extents(struct inode *inode, +static int ocfs2_lock_meta_allocator_move_extents(struct inode *inode, struct ocfs2_extent_tree *et, u32 clusters_to_move, u32 extents_to_split, struct ocfs2_alloc_context **meta_ac, - struct ocfs2_alloc_context **data_ac, int extra_blocks, int *credits) { @@ -192,13 +188,6 @@ static int ocfs2_lock_allocators_move_extents(struct inode *inode, goto out; }

- if (data_ac) { - ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac); - if (ret) { - mlog_errno(ret); - goto out; - } - }

*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el);

@@ -260,10 +249,10 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, } }

- ret = ocfs2_lock_allocators_move_extents(inode, &context->et, *len, 1, - &context->meta_ac, - &context->data_ac, - extra_blocks, &credits); + ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et, + *len, 1, + &context->meta_ac, + extra_blocks, &credits); if (ret) { mlog_errno(ret); goto out; @@ -286,6 +275,21 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, } }

+ /* + * Make sure ocfs2_reserve_cluster is called after + * __ocfs2_flush_truncate_log, otherwise, dead lock may happen. + * + * If ocfs2_reserve_cluster is called + * before __ocfs2_flush_truncate_log, dead lock on global bitmap + * may happen. + * + */ + ret = ocfs2_reserve_clusters(osb, *len, &context->data_ac); + if (ret) { + mlog_errno(ret); + goto out_unlock_mutex; + } + handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); @@ -606,9 +610,10 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context, } }

- ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1, - &context->meta_ac, - NULL, extra_blocks, &credits); + ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et, + len, 1, + &context->meta_ac, + extra_blocks, &credits); if (ret) { mlog_errno(ret); goto out;

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

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

[ Upstream commit c7d7d620dcbd2a1c595092280ca943f2fced7bbd ]

hfs_bmap_free() frees node via hfs_bnode_put(node). However it then reads node->this when dumping error message on an error path, which may result in a use-after-free bug. This patch frees node only when it is never used.

Link: http://lkml.kernel.org/r/1543053441-66942-1-git-send-email-bianpan2016@163.c... Signed-off-by: Pan Bian bianpan2016@163.com Reviewed-by: Andrew Morton akpm@linux-foundation.org Cc: Ernesto A. Fernandez ernesto.mnd.fernandez@gmail.com Cc: Joe Perches joe@perches.com Cc: Viacheslav Dubeyko slava@dubeyko.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/hfsplus/btree.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index 3345c7553edc..7adc8a327e03 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -453,14 +453,15 @@ void hfs_bmap_free(struct hfs_bnode *node)

nidx -= len * 8; i = node->next; - hfs_bnode_put(node); if (!i) { /* panic */; pr_crit("unable to free bnode %u. " "bmap not found!\n", node->this); + hfs_bnode_put(node); return; } + hfs_bnode_put(node); node = hfs_bnode_find(tree, i); if (IS_ERR(node)) return;

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

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

[ Upstream commit 164f7e586739d07eb56af6f6d66acebb11f315c8 ]

ocfs2_get_dentry() calls iput(inode) to drop the reference count of inode, and if the reference count hits 0, inode is freed. However, in this function, it then reads inode->i_generation, which may result in a use after free bug. Move the put operation later.

Link: http://lkml.kernel.org/r/1543109237-110227-1-git-send-email-bianpan2016@163.... Fixes: 781f200cb7a("ocfs2: Remove masklog ML_EXPORT.") Signed-off-by: Pan Bian bianpan2016@163.com Reviewed-by: Andrew Morton akpm@linux-foundation.org Cc: Mark Fasheh mark@fasheh.com Cc: Joel Becker jlbec@evilplan.org Cc: Junxiao Bi junxiao.bi@oracle.com Cc: Joseph Qi jiangqi903@gmail.com Cc: Changwei Ge ge.changwei@h3c.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ocfs2/export.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 827fc9809bc2..3494e220b510 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -125,10 +125,10 @@ static struct dentry *ocfs2_get_dentry(struct super_block *sb,

check_gen: if (handle->ih_generation != inode->i_generation) { - iput(inode); trace_ocfs2_get_dentry_generation((unsigned long long)blkno, handle->ih_generation, inode->i_generation); + iput(inode); result = ERR_PTR(-ESTALE); goto bail; }

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

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

From: Takashi Sakamoto o-takashi@sakamocchi.jp

commit e11f0f90a626f93899687b1cc909ee37dd6c5809 upstream.

Drivers can implement 'struct snd_pcm_ops.ioctl' to handle some requests from ALSA PCM core. These requests are internal purpose in kernel land. Usually common set of operations are used for it.

SNDRV_PCM_IOCTL1_INFO is one of the requests. According to code comment, it has been obsoleted in the old days.

We can see old releases in ftp.alsa-project.org. The command was firstly introduced in v0.5.0 release as SND_PCM_IOCTL1_INFO, to allow drivers to fill data of 'struct snd_pcm_channel_info' type. In v0.9.0 release, this was obsoleted by the other commands for ioctl(2) such as SNDRV_PCM_IOCTL_CHANNEL_INFO.

This commit removes the long-abandoned command, bye.

Signed-off-by: Takashi Sakamoto o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/sound/pcm.h | 2 +- sound/core/pcm_lib.c | 2 -- sound/core/pcm_native.c | 6 +----- 3 files changed, 2 insertions(+), 8 deletions(-)

--- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -100,7 +100,7 @@ struct snd_pcm_ops { #endif

#define SNDRV_PCM_IOCTL1_RESET 0 -#define SNDRV_PCM_IOCTL1_INFO 1 +/* 1 is absent slot. */ #define SNDRV_PCM_IOCTL1_CHANNEL_INFO 2 #define SNDRV_PCM_IOCTL1_GSTATE 3 #define SNDRV_PCM_IOCTL1_FIFO_SIZE 4 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1849,8 +1849,6 @@ int snd_pcm_lib_ioctl(struct snd_pcm_sub unsigned int cmd, void *arg) { switch (cmd) { - case SNDRV_PCM_IOCTL1_INFO: - return 0; case SNDRV_PCM_IOCTL1_RESET: return snd_pcm_lib_ioctl_reset(substream, arg); case SNDRV_PCM_IOCTL1_CHANNEL_INFO: --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -214,11 +214,7 @@ int snd_pcm_info(struct snd_pcm_substrea info->subdevices_avail = pstr->substream_count - pstr->substream_opened; strlcpy(info->subname, substream->name, sizeof(info->subname)); runtime = substream->runtime; - /* AB: FIXME!!! This is definitely nonsense */ - if (runtime) { - info->sync = runtime->sync; - substream->ops->ioctl(substream, SNDRV_PCM_IOCTL1_INFO, info); - } + return 0; }

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

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

From: David Matlack dmatlack@google.com

commit c9f04407f2e0b3fc9ff7913c65fcfcb0a4b61570 upstream.

The host physical addresses of L1's Virtual APIC Page and Posted Interrupt descriptor are loaded into the VMCS02. The CPU may write to these pages via their host physical address while L2 is running, bypassing address-translation-based dirty tracking (e.g. EPT write protection). Mark them dirty on every exit from L2 to prevent them from getting out of sync with dirty tracking.

Also mark the virtual APIC page and the posted interrupt descriptor dirty when KVM is virtualizing posted interrupt processing.

Signed-off-by: David Matlack dmatlack@google.com Reviewed-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Radim Krčmář rkrcmar@redhat.com Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx.c | 53 +++++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 43 insertions(+), 10 deletions(-)

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4527,6 +4527,28 @@ static int vmx_cpu_uses_apicv(struct kvm return enable_apicv && lapic_in_kernel(vcpu); }

+static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + gfn_t gfn; + + /* + * Don't need to mark the APIC access page dirty; it is never + * written to by the CPU during APIC virtualization. + */ + + if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { + gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } + + if (nested_cpu_has_posted_intr(vmcs12)) { + gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + } +} + + static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -4534,18 +4556,15 @@ static void vmx_complete_nested_posted_i void *vapic_page; u16 status;

- if (vmx->nested.pi_desc && - vmx->nested.pi_pending) { - vmx->nested.pi_pending = false; - if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return; - - max_irr = find_last_bit( - (unsigned long *)vmx->nested.pi_desc->pir, 256); + if (!vmx->nested.pi_desc || !vmx->nested.pi_pending) + return;

- if (max_irr == 256) - return; + vmx->nested.pi_pending = false; + if (!pi_test_and_clear_on(vmx->nested.pi_desc)) + return;

+ max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); + if (max_irr != 256) { vapic_page = kmap(vmx->nested.virtual_apic_page); __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); kunmap(vmx->nested.virtual_apic_page); @@ -4557,6 +4576,8 @@ static void vmx_complete_nested_posted_i vmcs_write16(GUEST_INTR_STATUS, status); } } + + nested_mark_vmcs12_pages_dirty(vcpu); }

static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) @@ -7761,6 +7782,18 @@ static bool nested_vmx_exit_handled(stru vmcs_read32(VM_EXIT_INTR_ERROR_CODE), KVM_ISA_VMX);

+ /* + * The host physical addresses of some pages of guest memory + * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU + * may write to these pages via their host physical address while + * L2 is running, bypassing any address-translation-based dirty + * tracking (e.g. EPT write protection). + * + * Mark them dirty on every exit from L2 to prevent them from + * getting out of sync with dirty tracking. + */ + nested_mark_vmcs12_pages_dirty(vcpu); + if (vmx->nested.nested_run_pending) return false;

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

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

From: Paolo Bonzini pbonzini@redhat.com

commit f21f165ef922c2146cc5bdc620f542953c41714b upstream.

Group together the calls to alloc_vmcs and loaded_vmcs_init. Soon we'll also allocate an MSR bitmap there.

Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org [bwh: Backported to 4.4: - No loaded_vmcs::shadow_vmcs field to initialise - Adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx.c | 35 ++++++++++++++++++++++------------- 1 file changed, 22 insertions(+), 13 deletions(-)

--- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3345,11 +3345,6 @@ static struct vmcs *alloc_vmcs_cpu(int c return vmcs; }

-static struct vmcs *alloc_vmcs(void) -{ - return alloc_vmcs_cpu(raw_smp_processor_id()); -} - static void free_vmcs(struct vmcs *vmcs) { free_pages((unsigned long)vmcs, vmcs_config.order); @@ -3367,6 +3362,21 @@ static void free_loaded_vmcs(struct load loaded_vmcs->vmcs = NULL; }

+static struct vmcs *alloc_vmcs(void) +{ + return alloc_vmcs_cpu(raw_smp_processor_id()); +} + +static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) +{ + loaded_vmcs->vmcs = alloc_vmcs(); + if (!loaded_vmcs->vmcs) + return -ENOMEM; + + loaded_vmcs_init(loaded_vmcs); + return 0; +} + static void free_kvm_area(void) { int cpu; @@ -6699,6 +6709,7 @@ static int handle_vmon(struct kvm_vcpu * struct vmcs *shadow_vmcs; const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; + int r;

/* The Intel VMX Instruction Reference lists a bunch of bits that * are prerequisite to running VMXON, most notably cr4.VMXE must be @@ -6738,10 +6749,9 @@ static int handle_vmon(struct kvm_vcpu * return 1; }

- vmx->nested.vmcs02.vmcs = alloc_vmcs(); - if (!vmx->nested.vmcs02.vmcs) + r = alloc_loaded_vmcs(&vmx->nested.vmcs02); + if (r < 0) goto out_vmcs02; - loaded_vmcs_init(&vmx->nested.vmcs02);

if (cpu_has_vmx_msr_bitmap()) { vmx->nested.msr_bitmap = @@ -8802,16 +8812,15 @@ static struct kvm_vcpu *vmx_create_vcpu( if (!vmx->guest_msrs) goto free_pml;

- vmx->loaded_vmcs = &vmx->vmcs01; - vmx->loaded_vmcs->vmcs = alloc_vmcs(); - if (!vmx->loaded_vmcs->vmcs) - goto free_msrs; if (!vmm_exclusive) kvm_cpu_vmxon(__pa(per_cpu(vmxarea, raw_smp_processor_id()))); - loaded_vmcs_init(vmx->loaded_vmcs); + err = alloc_loaded_vmcs(&vmx->vmcs01); if (!vmm_exclusive) kvm_cpu_vmxoff(); + if (err < 0) + goto free_msrs;

+ vmx->loaded_vmcs = &vmx->vmcs01; cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); vmx->vcpu.cpu = cpu;

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

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

From: Ashok Raj ashok.raj@intel.com

commit 15d45071523d89b3fb7372e2135fbd72f6af9506 upstream.

The Indirect Branch Predictor Barrier (IBPB) is an indirect branch control mechanism. It keeps earlier branches from influencing later ones.

Unlike IBRS and STIBP, IBPB does not define a new mode of operation. It's a command that ensures predicted branch targets aren't used after the barrier. Although IBRS and IBPB are enumerated by the same CPUID enumeration, IBPB is very different.

IBPB helps mitigate against three potential attacks:

* Mitigate guests from being attacked by other guests. - This is addressed by issing IBPB when we do a guest switch.

* Mitigate attacks from guest/ring3->host/ring3. These would require a IBPB during context switch in host, or after VMEXIT. The host process has two ways to mitigate - Either it can be compiled with retpoline - If its going through context switch, and has set !dumpable then there is a IBPB in that path. (Tim's patch: https://patchwork.kernel.org/patch/10192871) - The case where after a VMEXIT you return back to Qemu might make Qemu attackable from guest when Qemu isn't compiled with retpoline. There are issues reported when doing IBPB on every VMEXIT that resulted in some tsc calibration woes in guest.

* Mitigate guest/ring0->host/ring0 attacks. When host kernel is using retpoline it is safe against these attacks. If host kernel isn't using retpoline we might need to do a IBPB flush on every VMEXIT.

Even when using retpoline for indirect calls, in certain conditions 'ret' can use the BTB on Skylake-era CPUs. There are other mitigations available like RSB stuffing/clearing.

* IBPB is issued only for SVM during svm_free_vcpu(). VMX has a vmclear and SVM doesn't. Follow discussion here: https://lkml.org/lkml/2018/1/15/146

Please refer to the following spec for more details on the enumeration and control.

Refer here to get documentation about mitigations.

https://software.intel.com/en-us/side-channel-security-support

[peterz: rebase and changelog rewrite] [karahmed: - rebase - vmx: expose PRED_CMD if guest has it in CPUID - svm: only pass through IBPB if guest has it in CPUID - vmx: support !cpu_has_vmx_msr_bitmap()] - vmx: support nested] [dwmw2: Expose CPUID bit too (AMD IBPB only for now as we lack IBRS) PRED_CMD is a write-only MSR]

Signed-off-by: Ashok Raj ashok.raj@intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: KarimAllah Ahmed karahmed@amazon.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Cc: Andrea Arcangeli aarcange@redhat.com Cc: Andi Kleen ak@linux.intel.com Cc: kvm@vger.kernel.org Cc: Asit Mallick asit.k.mallick@intel.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Andy Lutomirski luto@kernel.org Cc: Dave Hansen dave.hansen@intel.com Cc: Arjan Van De Ven arjan.van.de.ven@intel.com Cc: Greg KH gregkh@linuxfoundation.org Cc: Jun Nakajima jun.nakajima@intel.com Cc: Paolo Bonzini pbonzini@redhat.com Cc: Dan Williams dan.j.williams@intel.com Cc: Tim Chen tim.c.chen@linux.intel.com Link: http://lkml.kernel.org/r/1515720739-43819-6-git-send-email-ashok.raj@intel.c... Link: https://lkml.kernel.org/r/1517522386-18410-3-git-send-email-karahmed@amazon.... Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org [bwh: Backported to 4.4: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/cpuid.c | 11 ++++++- arch/x86/kvm/cpuid.h | 12 +++++++ arch/x86/kvm/svm.c | 28 ++++++++++++++++++ arch/x86/kvm/vmx.c | 79 +++++++++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 127 insertions(+), 3 deletions(-)

--- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -341,6 +341,10 @@ static inline int __do_cpuid_ent(struct F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);

+ /* cpuid 0x80000008.ebx */ + const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(IBPB); + /* cpuid 0xC0000001.edx */ const u32 kvm_supported_word5_x86_features = F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | @@ -583,7 +587,12 @@ static inline int __do_cpuid_ent(struct if (!g_phys_as) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); - entry->ebx = entry->edx = 0; + entry->edx = 0; + /* IBPB isn't necessarily present in hardware cpuid */ + if (boot_cpu_has(X86_FEATURE_IBPB)) + entry->ebx |= F(IBPB); + entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); break; } case 0x80000019: --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -159,6 +159,18 @@ static inline bool guest_cpuid_has_rdtsc return best && (best->edx & bit(X86_FEATURE_RDTSCP)); }

+static inline bool guest_cpuid_has_ibpb(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best && (best->ebx & bit(X86_FEATURE_IBPB))) + return true; + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); +} + + /* * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3 */ --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -182,6 +182,7 @@ static const struct svm_direct_access_ms { .index = MSR_CSTAR, .always = true }, { .index = MSR_SYSCALL_MASK, .always = true }, #endif + { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -411,6 +412,7 @@ struct svm_cpu_data { struct kvm_ldttss_desc *tss_desc;

struct page *save_area; + struct vmcb *current_vmcb; };

static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); @@ -1210,11 +1212,17 @@ static void svm_free_vcpu(struct kvm_vcp __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); + /* + * The vmcb page can be recycled, causing a false negative in + * svm_vcpu_load(). So do a full IBPB now. + */ + indirect_branch_prediction_barrier(); }

static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int i;

if (unlikely(cpu != vcpu->cpu)) { @@ -1239,6 +1247,10 @@ static void svm_vcpu_load(struct kvm_vcp wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio); } } + if (sd->current_vmcb != svm->vmcb) { + sd->current_vmcb = svm->vmcb; + indirect_branch_prediction_barrier(); + } }

static void svm_vcpu_put(struct kvm_vcpu *vcpu) @@ -3125,6 +3137,22 @@ static int svm_set_msr(struct kvm_vcpu * case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr); break; + case MSR_IA32_PRED_CMD: + if (!msr->host_initiated && + !guest_cpuid_has_ibpb(vcpu)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + if (is_guest_mode(vcpu)) + break; + set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); + break; case MSR_STAR: svm->vmcb->save.star = data; break; --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -544,6 +544,7 @@ struct vcpu_vmx { u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; #endif + u32 vm_entry_controls_shadow; u32 vm_exit_controls_shadow; /* @@ -892,6 +893,8 @@ static void copy_vmcs12_to_shadow(struct static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); static int alloc_identity_pagetable(struct kvm *kvm); static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); +static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, + u32 msr, int type);

static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); @@ -1687,6 +1690,29 @@ static void update_exception_bitmap(stru vmcs_write32(EXCEPTION_BITMAP, eb); }

+/* + * Check if MSR is intercepted for L01 MSR bitmap. + */ +static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, unsigned long entry, unsigned long exit) { @@ -2072,6 +2098,7 @@ static void vmx_vcpu_load(struct kvm_vcp if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) { per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs; vmcs_load(vmx->loaded_vmcs->vmcs); + indirect_branch_prediction_barrier(); }

if (vmx->loaded_vmcs->cpu != cpu) { @@ -2904,6 +2931,33 @@ static int vmx_set_msr(struct kvm_vcpu * case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_PRED_CMD: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibpb(vcpu)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, + MSR_TYPE_W); + break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -9172,9 +9226,23 @@ static inline bool nested_vmx_merge_msr_ struct page *page; unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; + /* + * pred_cmd is trying to verify two things: + * + * 1. L0 gave a permission to L1 to actually passthrough the MSR. This + * ensures that we do not accidentally generate an L02 MSR bitmap + * from the L12 MSR bitmap that is too permissive. + * 2. That L1 or L2s have actually used the MSR. This avoids + * unnecessarily merging of the bitmap if the MSR is unused. This + * works properly because we only update the L01 MSR bitmap lazily. + * So even if L0 should pass L1 these MSRs, the L01 bitmap is only + * updated to reflect this when L1 (or its L2s) actually write to + * the MSR. + */ + bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);

- /* This shortcut is ok because we support only x2APIC MSRs so far. */ - if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) + if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && + !pred_cmd) return false;

page = nested_get_page(vcpu, vmcs12->msr_bitmap); @@ -9209,6 +9277,13 @@ static inline bool nested_vmx_merge_msr_ MSR_TYPE_W); } } + + if (pred_cmd) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, + MSR_TYPE_W); + kunmap(page); nested_release_page_clean(page);

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

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

From: KarimAllah Ahmed karahmed@amazon.de

commit d28b387fb74da95d69d2615732f50cceb38e9a4d upstream.

[ Based on a patch from Ashok Raj ashok.raj@intel.com ]

Add direct access to MSR_IA32_SPEC_CTRL for guests. This is needed for guests that will only mitigate Spectre V2 through IBRS+IBPB and will not be using a retpoline+IBPB based approach.

To avoid the overhead of saving and restoring the MSR_IA32_SPEC_CTRL for guests that do not actually use the MSR, only start saving and restoring when a non-zero is written to it.

No attempt is made to handle STIBP here, intentionally. Filtering STIBP may be added in a future patch, which may require trapping all writes if we don't want to pass it through directly to the guest.

[dwmw2: Clean up CPUID bits, save/restore manually, handle reset]

Signed-off-by: KarimAllah Ahmed karahmed@amazon.de Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Darren Kenny darren.kenny@oracle.com Reviewed-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Reviewed-by: Jim Mattson jmattson@google.com Cc: Andrea Arcangeli aarcange@redhat.com Cc: Andi Kleen ak@linux.intel.com Cc: Jun Nakajima jun.nakajima@intel.com Cc: kvm@vger.kernel.org Cc: Dave Hansen dave.hansen@intel.com Cc: Tim Chen tim.c.chen@linux.intel.com Cc: Andy Lutomirski luto@kernel.org Cc: Asit Mallick asit.k.mallick@intel.com Cc: Arjan Van De Ven arjan.van.de.ven@intel.com Cc: Greg KH gregkh@linuxfoundation.org Cc: Paolo Bonzini pbonzini@redhat.com Cc: Dan Williams dan.j.williams@intel.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Ashok Raj ashok.raj@intel.com Link: https://lkml.kernel.org/r/1517522386-18410-5-git-send-email-karahmed@amazon.... Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/cpuid.c | 8 ++- arch/x86/kvm/cpuid.h | 11 +++++ arch/x86/kvm/vmx.c | 103 ++++++++++++++++++++++++++++++++++++++++++++++++++- arch/x86/kvm/x86.c | 2 4 files changed, 118 insertions(+), 6 deletions(-)

--- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -343,7 +343,7 @@ static inline int __do_cpuid_ent(struct

/* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = - F(IBPB); + F(IBPB) | F(IBRS);

/* cpuid 0xC0000001.edx */ const u32 kvm_supported_word5_x86_features = @@ -364,7 +364,7 @@ static inline int __do_cpuid_ent(struct

/* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = - F(ARCH_CAPABILITIES); + F(SPEC_CTRL) | F(ARCH_CAPABILITIES);

/* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -595,9 +595,11 @@ static inline int __do_cpuid_ent(struct g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; - /* IBPB isn't necessarily present in hardware cpuid */ + /* IBRS and IBPB aren't necessarily present in hardware cpuid */ if (boot_cpu_has(X86_FEATURE_IBPB)) entry->ebx |= F(IBPB); + if (boot_cpu_has(X86_FEATURE_IBRS)) + entry->ebx |= F(IBRS); entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); break; --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -170,6 +170,17 @@ static inline bool guest_cpuid_has_ibpb( return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); }

+static inline bool guest_cpuid_has_ibrs(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best && (best->ebx & bit(X86_FEATURE_IBRS))) + return true; + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); +} + static inline bool guest_cpuid_has_arch_capabilities(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -546,6 +546,7 @@ struct vcpu_vmx { #endif

u64 arch_capabilities; + u64 spec_ctrl;

u32 vm_entry_controls_shadow; u32 vm_exit_controls_shadow; @@ -1693,6 +1694,29 @@ static void update_exception_bitmap(stru }

/* + * Check if MSR is intercepted for currently loaded MSR bitmap. + */ +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +{ + unsigned long *msr_bitmap; + int f = sizeof(unsigned long); + + if (!cpu_has_vmx_msr_bitmap()) + return true; + + msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; + + if (msr <= 0x1fff) { + return !!test_bit(msr, msr_bitmap + 0x800 / f); + } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { + msr &= 0x1fff; + return !!test_bit(msr, msr_bitmap + 0xc00 / f); + } + + return true; +} + +/* * Check if MSR is intercepted for L01 MSR bitmap. */ static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) @@ -2834,6 +2858,13 @@ static int vmx_get_msr(struct kvm_vcpu * case MSR_IA32_TSC: msr_info->data = guest_read_tsc(vcpu); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + msr_info->data = to_vmx(vcpu)->spec_ctrl; + break; case MSR_IA32_ARCH_CAPABILITIES: if (!msr_info->host_initiated && !guest_cpuid_has_arch_capabilities(vcpu)) @@ -2939,6 +2970,36 @@ static int vmx_set_msr(struct kvm_vcpu * case MSR_IA32_TSC: kvm_write_tsc(vcpu, msr_info); break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_ibrs(vcpu)) + return 1; + + /* The STIBP bit doesn't fault even if it's not advertised */ + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + return 1; + + vmx->spec_ctrl = data; + + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_merge_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. We update the vmcs01 here for L1 as well + * since it will end up touching the MSR anyway now. + */ + vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_RW); + break; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && !guest_cpuid_has_ibpb(vcpu)) @@ -5045,6 +5106,7 @@ static void vmx_vcpu_reset(struct kvm_vc u64 cr0;

vmx->rmode.vm86_active = 0; + vmx->spec_ctrl = 0;

vmx->soft_vnmi_blocked = 0;

@@ -8589,6 +8651,15 @@ static void __noclone vmx_vcpu_run(struc atomic_switch_perf_msrs(vmx); debugctlmsr = get_debugctlmsr();

+ /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + vmx->__launched = vmx->loaded_vmcs->launched; asm( /* Store host registers */ @@ -8707,6 +8778,27 @@ static void __noclone vmx_vcpu_run(struc #endif );

+ /* + * We do not use IBRS in the kernel. If this vCPU has used the + * SPEC_CTRL MSR it may have left it on; save the value and + * turn it off. This is much more efficient than blindly adding + * it to the atomic save/restore list. Especially as the former + * (Saving guest MSRs on vmexit) doesn't even exist in KVM. + * + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + + if (vmx->spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB();

@@ -9242,7 +9334,7 @@ static inline bool nested_vmx_merge_msr_ unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; /* - * pred_cmd is trying to verify two things: + * pred_cmd & spec_ctrl are trying to verify two things: * * 1. L0 gave a permission to L1 to actually passthrough the MSR. This * ensures that we do not accidentally generate an L02 MSR bitmap @@ -9255,9 +9347,10 @@ static inline bool nested_vmx_merge_msr_ * the MSR. */ bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); + bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);

if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && - !pred_cmd) + !pred_cmd && !spec_ctrl) return false;

page = nested_get_page(vcpu, vmcs12->msr_bitmap); @@ -9293,6 +9386,12 @@ static inline bool nested_vmx_merge_msr_ } }

+ if (spec_ctrl) + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, + MSR_TYPE_R | MSR_TYPE_W); + if (pred_cmd) nested_vmx_disable_intercept_for_msr( msr_bitmap_l1, msr_bitmap_l0, --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -961,7 +961,7 @@ static u32 msrs_to_save[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_ARCH_CAPABILITIES + MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES };

static unsigned num_msrs_to_save;

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

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

From: Paolo Bonzini pbonzini@redhat.com

commit ecb586bd29c99fb4de599dec388658e74388daad upstream.

Having a paravirt indirect call in the IBRS restore path is not a good idea, since we are trying to protect from speculative execution of bogus indirect branch targets. It is also slower, so use native_wrmsrl() on the vmentry path too.

Signed-off-by: Paolo Bonzini pbonzini@redhat.com Reviewed-by: Jim Mattson jmattson@google.com Cc: David Woodhouse dwmw@amazon.co.uk Cc: KarimAllah Ahmed karahmed@amazon.de Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Radim Krčmář rkrcmar@redhat.com Cc: Thomas Gleixner tglx@linutronix.de Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Fixes: d28b387fb74da95d69d2615732f50cceb38e9a4d Link: http://lkml.kernel.org/r/20180222154318.20361-2-pbonzini@redhat.com Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org [bwh: Backported to 4.4: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/svm.c | 7 ++++--- arch/x86/kvm/vmx.c | 7 ++++--- 2 files changed, 8 insertions(+), 6 deletions(-)

--- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -37,6 +37,7 @@ #include <asm/desc.h> #include <asm/debugreg.h> #include <asm/kvm_para.h> +#include <asm/microcode.h> #include <asm/spec-ctrl.h>

#include <asm/virtext.h> @@ -3904,7 +3905,7 @@ static void svm_vcpu_run(struct kvm_vcpu * being speculatively taken. */ if (svm->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);

asm volatile ( "push %%" _ASM_BP "; \n\t" @@ -4014,10 +4015,10 @@ static void svm_vcpu_run(struct kvm_vcpu * save it. */ if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) - rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);

if (svm->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, 0); + native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);

/* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -48,6 +48,7 @@ #include <asm/kexec.h> #include <asm/apic.h> #include <asm/irq_remapping.h> +#include <asm/microcode.h> #include <asm/spec-ctrl.h>

#include "trace.h" @@ -8658,7 +8659,7 @@ static void __noclone vmx_vcpu_run(struc * being speculatively taken. */ if (vmx->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);

vmx->__launched = vmx->loaded_vmcs->launched; asm( @@ -8794,10 +8795,10 @@ static void __noclone vmx_vcpu_run(struc * save it. */ if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) - rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);

if (vmx->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, 0); + native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);

/* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB();

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

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

From: Linus Torvalds torvalds@linux-foundation.org

commit de9e478b9d49f3a0214310d921450cf5bb4a21e6 upstream.

In commit 11f1a4b9755f ("x86: reorganize SMAP handling in user space accesses") I changed how the stac/clac instructions were generated around the user space accesses, which then made it possible to do batched accesses efficiently for user string copies etc.

However, in doing so, I completely spaced out, and didn't even think about the 32-bit case. And nobody really even seemed to notice, because SMAP doesn't even exist until modern Skylake processors, and you'd have to be crazy to run 32-bit kernels on a modern CPU.

Which brings us to Andy Lutomirski.

He actually tested the 32-bit kernel on new hardware, and noticed that it doesn't work. My bad. The trivial fix is to add the required uaccess begin/end markers around the raw accesses in <asm/uaccess_32.h>.

I feel a bit bad about this patch, just because that header file really should be cleaned up to avoid all the duplicated code in it, and this commit just expands on the problem. But this just fixes the bug without any bigger cleanup surgery.

Reported-and-tested-by: Andy Lutomirski luto@kernel.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/uaccess_32.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+)

--- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -48,20 +48,28 @@ __copy_to_user_inatomic(void __user *to,

switch (n) { case 1: + __uaccess_begin(); __put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret, 4); + __uaccess_end(); return ret; case 8: + __uaccess_begin(); __put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret, 8); + __uaccess_end(); return ret; } } @@ -103,13 +111,19 @@ __copy_from_user_inatomic(void *to, cons

switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } @@ -148,13 +162,19 @@ __copy_from_user(void *to, const void __

switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } @@ -170,13 +190,19 @@ static __always_inline unsigned long __c

switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } }

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

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

From: Dan Williams dan.j.williams@intel.com

commit b5c4ae4f35325d520b230bab6eb3310613b72ac1 upstream.

In preparation for converting some __uaccess_begin() instances to __uacess_begin_nospec(), make sure all 'from user' uaccess paths are using the _begin(), _end() helpers rather than open-coded stac() and clac().

No functional changes.

Suggested-by: Ingo Molnar mingo@redhat.com Signed-off-by: Dan Williams dan.j.williams@intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: linux-arch@vger.kernel.org Cc: Tom Lendacky thomas.lendacky@amd.com Cc: Kees Cook keescook@chromium.org Cc: kernel-hardening@lists.openwall.com Cc: gregkh@linuxfoundation.org Cc: Al Viro viro@zeniv.linux.org.uk Cc: torvalds@linux-foundation.org Cc: alan@linux.intel.com Link: https://lkml.kernel.org/r/151727416438.33451.17309465232057176966.stgit@dwil... [bwh: Backported to 4.4: - Convert several more functions to use __uaccess_begin_nospec(), that are just wrappers in mainline - Adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/lib/usercopy_32.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)

--- a/arch/x86/lib/usercopy_32.c +++ b/arch/x86/lib/usercopy_32.c @@ -570,12 +570,12 @@ do { \ unsigned long __copy_to_user_ll(void __user *to, const void *from, unsigned long n) { - stac(); + __uaccess_begin(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else n = __copy_user_intel(to, from, n); - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_to_user_ll); @@ -583,12 +583,12 @@ EXPORT_SYMBOL(__copy_to_user_ll); unsigned long __copy_from_user_ll(void *to, const void __user *from, unsigned long n) { - stac(); + __uaccess_begin(); if (movsl_is_ok(to, from, n)) __copy_user_zeroing(to, from, n); else n = __copy_user_zeroing_intel(to, from, n); - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_from_user_ll); @@ -596,13 +596,13 @@ EXPORT_SYMBOL(__copy_from_user_ll); unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from, unsigned long n) { - stac(); + __uaccess_begin(); if (movsl_is_ok(to, from, n)) __copy_user(to, from, n); else n = __copy_user_intel((void __user *)to, (const void *)from, n); - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nozero); @@ -610,7 +610,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nozero unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from, unsigned long n) { - stac(); + __uaccess_begin(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && cpu_has_xmm2) n = __copy_user_zeroing_intel_nocache(to, from, n); @@ -619,7 +619,7 @@ unsigned long __copy_from_user_ll_nocach #else __copy_user_zeroing(to, from, n); #endif - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nocache); @@ -627,7 +627,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocach unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from, unsigned long n) { - stac(); + __uaccess_begin(); #ifdef CONFIG_X86_INTEL_USERCOPY if (n > 64 && cpu_has_xmm2) n = __copy_user_intel_nocache(to, from, n); @@ -636,7 +636,7 @@ unsigned long __copy_from_user_ll_nocach #else __copy_user(to, from, n); #endif - clac(); + __uaccess_end(); return n; } EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);

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

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

From: Konrad Rzeszutek Wilk konrad.wilk@oracle.com

commit 5cf687548705412da47c9cec342fd952d71ed3d5 upstream.

A guest may modify the SPEC_CTRL MSR from the value used by the kernel. Since the kernel doesn't use IBRS, this means a value of zero is what is needed in the host.

But the 336996-Speculative-Execution-Side-Channel-Mitigations.pdf refers to the other bits as reserved so the kernel should respect the boot time SPEC_CTRL value and use that.

This allows to deal with future extensions to the SPEC_CTRL interface if any at all.

Note: This uses wrmsrl() instead of native_wrmsl(). I does not make any difference as paravirt will over-write the callq *0xfff.. with the wrmsrl assembler code.

Signed-off-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Borislav Petkov bp@suse.de Reviewed-by: Ingo Molnar mingo@kernel.org [bwh: Backported to 4.4: This was partly applied before; apply just the missing bits] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/svm.c | 6 ++---- arch/x86/kvm/vmx.c | 6 ++---- 2 files changed, 4 insertions(+), 8 deletions(-)

--- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3904,8 +3904,7 @@ static void svm_vcpu_run(struct kvm_vcpu * is no need to worry about the conditional branch over the wrmsr * being speculatively taken. */ - if (svm->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + x86_spec_ctrl_set_guest(svm->spec_ctrl);

asm volatile ( "push %%" _ASM_BP "; \n\t" @@ -4017,8 +4016,7 @@ static void svm_vcpu_run(struct kvm_vcpu if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);

- if (svm->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); + x86_spec_ctrl_restore_host(svm->spec_ctrl);

/* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8658,8 +8658,7 @@ static void __noclone vmx_vcpu_run(struc * is no need to worry about the conditional branch over the wrmsr * being speculatively taken. */ - if (vmx->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + x86_spec_ctrl_set_guest(vmx->spec_ctrl);

vmx->__launched = vmx->loaded_vmcs->launched; asm( @@ -8797,8 +8796,7 @@ static void __noclone vmx_vcpu_run(struc if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);

- if (vmx->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); + x86_spec_ctrl_restore_host(vmx->spec_ctrl);

/* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB();

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

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

From: Thomas Gleixner tglx@linutronix.de

commit 15e6c22fd8e5a42c5ed6d487b7c9fe44c2517765 upstream.

svm_vcpu_run() invokes x86_spec_ctrl_restore_host() after VMEXIT, but before the host GS is restored. x86_spec_ctrl_restore_host() uses 'current' to determine the host SSBD state of the thread. 'current' is GS based, but host GS is not yet restored and the access causes a triple fault.

Move the call after the host GS restore.

Fixes: 885f82bfbc6f x86/process: Allow runtime control of Speculative Store Bypass Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Borislav Petkov bp@suse.de Reviewed-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Acked-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/svm.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-)

--- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3998,6 +3998,18 @@ static void svm_vcpu_run(struct kvm_vcpu #endif );

+ /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + +#ifdef CONFIG_X86_64 + wrmsrl(MSR_GS_BASE, svm->host.gs_base); +#else + loadsegment(fs, svm->host.fs); +#ifndef CONFIG_X86_32_LAZY_GS + loadsegment(gs, svm->host.gs); +#endif +#endif + /* * We do not use IBRS in the kernel. If this vCPU has used the * SPEC_CTRL MSR it may have left it on; save the value and @@ -4018,18 +4030,6 @@ static void svm_vcpu_run(struct kvm_vcpu

x86_spec_ctrl_restore_host(svm->spec_ctrl);

- /* Eliminate branch target predictions from guest mode */ - vmexit_fill_RSB(); - -#ifdef CONFIG_X86_64 - wrmsrl(MSR_GS_BASE, svm->host.gs_base); -#else - loadsegment(fs, svm->host.fs); -#ifndef CONFIG_X86_32_LAZY_GS - loadsegment(gs, svm->host.gs); -#endif -#endif - reload_tss(vcpu);

local_irq_disable();

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

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

From: Borislav Petkov bp@suse.de

commit e7c587da125291db39ddf1f49b18e5970adbac17 upstream.

Intel and AMD have different CPUID bits hence for those use synthetic bits which get set on the respective vendor's in init_speculation_control(). So that debacles like what the commit message of

c65732e4f721 ("x86/cpu: Restore CPUID_8000_0008_EBX reload")

talks about don't happen anymore.

Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Tested-by: Jörg Otte jrg.otte@gmail.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: "Kirill A. Shutemov" kirill.shutemov@linux.intel.com Link: https://lkml.kernel.org/r/20180504161815.GG9257@pd.tnic Signed-off-by: David Woodhouse dwmw@amazon.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org [bwh: Backported to 4.4: This was partly applied before; apply just the missing bits] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/cpuid.c | 10 +++++----- arch/x86/kvm/cpuid.h | 4 ++-- 2 files changed, 7 insertions(+), 7 deletions(-)

--- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -343,7 +343,7 @@ static inline int __do_cpuid_ent(struct

/* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = - F(IBPB) | F(IBRS); + F(AMD_IBPB) | F(AMD_IBRS);

/* cpuid 0xC0000001.edx */ const u32 kvm_supported_word5_x86_features = @@ -596,10 +596,10 @@ static inline int __do_cpuid_ent(struct entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; /* IBRS and IBPB aren't necessarily present in hardware cpuid */ - if (boot_cpu_has(X86_FEATURE_IBPB)) - entry->ebx |= F(IBPB); - if (boot_cpu_has(X86_FEATURE_IBRS)) - entry->ebx |= F(IBRS); + if (boot_cpu_has(X86_FEATURE_AMD_IBPB)) + entry->ebx |= F(AMD_IBPB); + if (boot_cpu_has(X86_FEATURE_AMD_IBRS)) + entry->ebx |= F(AMD_IBRS); entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); break; --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -164,7 +164,7 @@ static inline bool guest_cpuid_has_ibpb( struct kvm_cpuid_entry2 *best;

best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); - if (best && (best->ebx & bit(X86_FEATURE_IBPB))) + if (best && (best->ebx & bit(X86_FEATURE_AMD_IBPB))) return true; best = kvm_find_cpuid_entry(vcpu, 7, 0); return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); @@ -175,7 +175,7 @@ static inline bool guest_cpuid_has_spec_ struct kvm_cpuid_entry2 *best;

best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); - if (best && (best->ebx & bit(X86_FEATURE_IBRS))) + if (best && (best->ebx & bit(X86_FEATURE_AMD_IBRS))) return true; best = kvm_find_cpuid_entry(vcpu, 7, 0); return best && (best->edx & (bit(X86_FEATURE_SPEC_CTRL) | bit(X86_FEATURE_SPEC_CTRL_SSBD)));

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

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

From: Alexei Starovoitov ast@fb.com

commit cedaf52693f02372010548c63b2e63228b959099 upstream.

The verifier supported only 4-byte metafields in struct __sk_buff and struct xdp_md. The metafields in upcoming struct bpf_perf_event are 8-byte to match register width in struct pt_regs. Teach verifier to recognize 8-byte metafield access. The patch doesn't affect safety of sockets and xdp programs. They check for 4-byte only ctx access before these conditions are hit.

Signed-off-by: Alexei Starovoitov ast@kernel.org Acked-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/bpf/verifier.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

--- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1844,7 +1844,8 @@ static int do_check(struct verifier_env if (err) return err;

- if (BPF_SIZE(insn->code) != BPF_W) { + if (BPF_SIZE(insn->code) != BPF_W && + BPF_SIZE(insn->code) != BPF_DW) { insn_idx++; continue; } @@ -2220,9 +2221,11 @@ static int convert_ctx_accesses(struct v for (i = 0; i < insn_cnt; i++, insn++) { u32 cnt;

- if (insn->code == (BPF_LDX | BPF_MEM | BPF_W)) + if (insn->code == (BPF_LDX | BPF_MEM | BPF_W) || + insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) type = BPF_READ; - else if (insn->code == (BPF_STX | BPF_MEM | BPF_W)) + else if (insn->code == (BPF_STX | BPF_MEM | BPF_W) || + insn->code == (BPF_STX | BPF_MEM | BPF_DW)) type = BPF_WRITE; else continue;

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

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

From: Ben Hutchings ben.hutchings@codethink.co.uk

Extracted from commit 31fd85816dbe "bpf: permits narrower load from bpf program context fields".

Cc: Daniel Borkmann daniel@iogearbox.net Cc: Alexei Starovoitov ast@kernel.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/bpf/verifier.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

--- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -694,7 +694,7 @@ static bool is_ctx_reg(struct verifier_e * if t==write && value_regno==-1, some unknown value is stored into memory * if t==read && value_regno==-1, don't care what we read from memory */ -static int check_mem_access(struct verifier_env *env, u32 regno, int off, +static int check_mem_access(struct verifier_env *env, int insn_idx, u32 regno, int off, int bpf_size, enum bpf_access_type t, int value_regno) { @@ -758,7 +758,7 @@ static int check_mem_access(struct verif return err; }

-static int check_xadd(struct verifier_env *env, struct bpf_insn *insn) +static int check_xadd(struct verifier_env *env, int insn_idx, struct bpf_insn *insn) { struct reg_state *regs = env->cur_state.regs; int err; @@ -791,13 +791,13 @@ static int check_xadd(struct verifier_en }

/* check whether atomic_add can read the memory */ - err = check_mem_access(env, insn->dst_reg, insn->off, + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1); if (err) return err;

/* check whether atomic_add can write into the same memory */ - return check_mem_access(env, insn->dst_reg, insn->off, + return check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1); }

@@ -1836,7 +1836,7 @@ static int do_check(struct verifier_env /* check that memory (src_reg + off) is readable, * the state of dst_reg will be updated by this func */ - err = check_mem_access(env, insn->src_reg, insn->off, + err = check_mem_access(env, insn_idx, insn->src_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, insn->dst_reg); if (err) @@ -1875,7 +1875,7 @@ static int do_check(struct verifier_env enum bpf_reg_type *prev_dst_type, dst_reg_type;

if (BPF_MODE(insn->code) == BPF_XADD) { - err = check_xadd(env, insn); + err = check_xadd(env, insn_idx, insn); if (err) return err; insn_idx++; @@ -1894,7 +1894,7 @@ static int do_check(struct verifier_env dst_reg_type = regs[insn->dst_reg].type;

/* check that memory (dst_reg + off) is writeable */ - err = check_mem_access(env, insn->dst_reg, insn->off, + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, insn->src_reg); if (err) @@ -1929,7 +1929,7 @@ static int do_check(struct verifier_env }

/* check that memory (dst_reg + off) is writeable */ - err = check_mem_access(env, insn->dst_reg, insn->off, + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1); if (err)

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

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

From: Lior David qca_liord@qca.qualcomm.com

commit b5a8ffcae4103a9d823ea3aa3a761f65779fbe2a upstream.

Add a length check in wmi_set_ie to detect unsigned integer overflow.

Signed-off-by: Lior David qca_liord@qca.qualcomm.com Signed-off-by: Maya Erez qca_merez@qca.qualcomm.com Signed-off-by: Kalle Valo kvalo@qca.qualcomm.com Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/ath/wil6210/wmi.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

--- a/drivers/net/wireless/ath/wil6210/wmi.c +++ b/drivers/net/wireless/ath/wil6210/wmi.c @@ -1035,8 +1035,14 @@ int wmi_set_ie(struct wil6210_priv *wil, }; int rc; u16 len = sizeof(struct wmi_set_appie_cmd) + ie_len; - struct wmi_set_appie_cmd *cmd = kzalloc(len, GFP_KERNEL); + struct wmi_set_appie_cmd *cmd;

+ if (len < ie_len) { + rc = -EINVAL; + goto out; + } + + cmd = kzalloc(len, GFP_KERNEL); if (!cmd) { rc = -ENOMEM; goto out;

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

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

From: Mike Kravetz mike.kravetz@oracle.com

commit ff8c0c53c47530ffea82c22a0a6df6332b56c957 upstream.

Changes to hugetlbfs reservation maps is a two step process. The first step is a call to region_chg to determine what needs to be changed, and prepare that change. This should be followed by a call to call to region_add to commit the change, or region_abort to abort the change.

The error path in hugetlb_reserve_pages called region_abort after a failed call to region_chg. As a result, the adds_in_progress counter in the reservation map is off by 1. This is caught by a VM_BUG_ON in resv_map_release when the reservation map is freed.

syzkaller fuzzer (when using an injected kmalloc failure) found this bug, that resulted in the following:

kernel BUG at mm/hugetlb.c:742! Call Trace: hugetlbfs_evict_inode+0x7b/0xa0 fs/hugetlbfs/inode.c:493 evict+0x481/0x920 fs/inode.c:553 iput_final fs/inode.c:1515 [inline] iput+0x62b/0xa20 fs/inode.c:1542 hugetlb_file_setup+0x593/0x9f0 fs/hugetlbfs/inode.c:1306 newseg+0x422/0xd30 ipc/shm.c:575 ipcget_new ipc/util.c:285 [inline] ipcget+0x21e/0x580 ipc/util.c:639 SYSC_shmget ipc/shm.c:673 [inline] SyS_shmget+0x158/0x230 ipc/shm.c:657 entry_SYSCALL_64_fastpath+0x1f/0xc2 RIP: resv_map_release+0x265/0x330 mm/hugetlb.c:742

Link: http://lkml.kernel.org/r/1490821682-23228-1-git-send-email-mike.kravetz@orac... Signed-off-by: Mike Kravetz mike.kravetz@oracle.com Reported-by: Dmitry Vyukov dvyukov@google.com Acked-by: Hillf Danton hillf.zj@alibaba-inc.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/hugetlb.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4142,7 +4142,9 @@ int hugetlb_reserve_pages(struct inode * return 0; out_err: if (!vma || vma->vm_flags & VM_MAYSHARE) - region_abort(resv_map, from, to); + /* Don't call region_abort if region_chg failed */ + if (chg >= 0) + region_abort(resv_map, from, to); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) kref_put(&resv_map->refs, resv_map_release); return ret;

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

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

From: Mike Kravetz mike.kravetz@oracle.com

commit 63489f8e821144000e0bdca7e65a8d1cc23a7ee7 upstream.

A vma with vm_pgoff large enough to overflow a loff_t type when converted to a byte offset can be passed via the remap_file_pages system call. The hugetlbfs mmap routine uses the byte offset to calculate reservations and file size.

A sequence such as:

mmap(0x20a00000, 0x600000, 0, 0x66033, -1, 0); remap_file_pages(0x20a00000, 0x600000, 0, 0x20000000000000, 0);

will result in the following when task exits/file closed,

kernel BUG at mm/hugetlb.c:749! Call Trace: hugetlbfs_evict_inode+0x2f/0x40 evict+0xcb/0x190 __dentry_kill+0xcb/0x150 __fput+0x164/0x1e0 task_work_run+0x84/0xa0 exit_to_usermode_loop+0x7d/0x80 do_syscall_64+0x18b/0x190 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

The overflowed pgoff value causes hugetlbfs to try to set up a mapping with a negative range (end < start) that leaves invalid state which causes the BUG.

The previous overflow fix to this code was incomplete and did not take the remap_file_pages system call into account.

[mike.kravetz@oracle.com: v3] Link: http://lkml.kernel.org/r/20180309002726.7248-1-mike.kravetz@oracle.com [akpm@linux-foundation.org: include mmdebug.h] [akpm@linux-foundation.org: fix -ve left shift count on sh] Link: http://lkml.kernel.org/r/20180308210502.15952-1-mike.kravetz@oracle.com Fixes: 045c7a3f53d9 ("hugetlbfs: fix offset overflow in hugetlbfs mmap") Signed-off-by: Mike Kravetz mike.kravetz@oracle.com Reported-by: Nic Losby blurbdust@gmail.com Acked-by: Michal Hocko mhocko@suse.com Cc: "Kirill A . Shutemov" kirill.shutemov@linux.intel.com Cc: Yisheng Xie xieyisheng1@huawei.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org [bwh: Backported to 4.4: Use a conditional WARN() instead of VM_WARN()] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/hugetlbfs/inode.c | 17 ++++++++++++++--- mm/hugetlb.c | 8 ++++++++ 2 files changed, 22 insertions(+), 3 deletions(-)

--- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -118,6 +118,16 @@ static void huge_pagevec_release(struct pagevec_reinit(pvec); }

+/* + * Mask used when checking the page offset value passed in via system + * calls. This value will be converted to a loff_t which is signed. + * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the + * value. The extra bit (- 1 in the shift value) is to take the sign + * bit into account. + */ +#define PGOFF_LOFFT_MAX \ + (((1UL << (PAGE_SHIFT + 1)) - 1) << (BITS_PER_LONG - (PAGE_SHIFT + 1))) + static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); @@ -137,12 +147,13 @@ static int hugetlbfs_file_mmap(struct fi vma->vm_ops = &hugetlb_vm_ops;

/* - * Offset passed to mmap (before page shift) could have been - * negative when represented as a (l)off_t. + * page based offset in vm_pgoff could be sufficiently large to + * overflow a (l)off_t when converted to byte offset. */ - if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0) + if (vma->vm_pgoff & PGOFF_LOFFT_MAX) return -EINVAL;

+ /* must be huge page aligned */ if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL;

--- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4053,6 +4053,14 @@ int hugetlb_reserve_pages(struct inode * struct resv_map *resv_map; long gbl_reserve;

+ /* This should never happen */ + if (from > to) { +#ifdef CONFIG_DEBUG_VM + WARN(1, "%s called with a negative range\n", __func__); +#endif + return -EINVAL; + } + /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page

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

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

From: Kees Cook keescook@chromium.org

commit 7d63fb3af87aa67aa7d24466e792f9d7c57d8e79 upstream.

This removes needless use of '%p', and refactors the printk calls to use pr_*() helpers instead.

Signed-off-by: Kees Cook keescook@chromium.org Reviewed-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Signed-off-by: Christoph Hellwig hch@lst.de [bwh: Backported to 4.4: - Adjust filename - Remove "swiotlb: " prefix from an additional log message] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- lib/swiotlb.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-)

--- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -17,6 +17,8 @@ * 08/12/11 beckyb Add highmem support */

+#define pr_fmt(fmt) "software IO TLB: " fmt + #include <linux/cache.h> #include <linux/dma-mapping.h> #include <linux/mm.h> @@ -143,20 +145,16 @@ static bool no_iotlb_memory; void swiotlb_print_info(void) { unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; - unsigned char *vstart, *vend;

if (no_iotlb_memory) { - pr_warn("software IO TLB: No low mem\n"); + pr_warn("No low mem\n"); return; }

- vstart = phys_to_virt(io_tlb_start); - vend = phys_to_virt(io_tlb_end); - - printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n", + pr_info("mapped [mem %#010llx-%#010llx] (%luMB)\n", (unsigned long long)io_tlb_start, (unsigned long long)io_tlb_end, - bytes >> 20, vstart, vend - 1); + bytes >> 20); }

int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) @@ -230,7 +228,7 @@ swiotlb_init(int verbose) if (io_tlb_start) memblock_free_early(io_tlb_start, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); - pr_warn("Cannot allocate SWIOTLB buffer"); + pr_warn("Cannot allocate buffer"); no_iotlb_memory = true; }

@@ -272,8 +270,8 @@ swiotlb_late_init_with_default_size(size return -ENOMEM; } if (order != get_order(bytes)) { - printk(KERN_WARNING "Warning: only able to allocate %ld MB " - "for software IO TLB\n", (PAGE_SIZE << order) >> 20); + pr_warn("only able to allocate %ld MB\n", + (PAGE_SIZE << order) >> 20); io_tlb_nslabs = SLABS_PER_PAGE << order; } rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs); @@ -680,7 +678,7 @@ swiotlb_alloc_coherent(struct device *hw return ret;

err_warn: - pr_warn("swiotlb: coherent allocation failed for device %s size=%zu\n", + pr_warn("coherent allocation failed for device %s size=%zu\n", dev_name(hwdev), size); dump_stack();

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

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

From: Lorenzo Stoakes lstoakes@gmail.com

commit 859110d7497cdd0e6b21010d6f777049d676382c upstream.

This removes the redundant 'write' and 'force' parameters from __get_user_pages_locked() to make the use of FOLL_FORCE explicit in callers as use of this flag can result in surprising behaviour (and hence bugs) within the mm subsystem.

Signed-off-by: Lorenzo Stoakes lstoakes@gmail.com Reviewed-by: Jan Kara jack@suse.cz Acked-by: Michal Hocko mhocko@suse.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org [bwh: Backported to 4.4: - Drop change in get_user_pages_remote() - Adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/gup.c | 37 ++++++++++++++++++++++++++----------- 1 file changed, 26 insertions(+), 11 deletions(-)

--- a/mm/gup.c +++ b/mm/gup.c @@ -627,7 +627,6 @@ static __always_inline long __get_user_p struct mm_struct *mm, unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages, struct vm_area_struct **vmas, int *locked, bool notify_drop, @@ -645,10 +644,6 @@ static __always_inline long __get_user_p

if (pages) flags |= FOLL_GET; - if (write) - flags |= FOLL_WRITE; - if (force) - flags |= FOLL_FORCE;

pages_done = 0; lock_dropped = false; @@ -745,8 +740,15 @@ long get_user_pages_locked(struct task_s int write, int force, struct page **pages, int *locked) { - return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, - pages, NULL, locked, true, FOLL_TOUCH); + unsigned int flags = FOLL_TOUCH; + + if (write) + flags |= FOLL_WRITE; + if (force) + flags |= FOLL_FORCE; + + return __get_user_pages_locked(tsk, mm, start, nr_pages, + pages, NULL, locked, true, flags); } EXPORT_SYMBOL(get_user_pages_locked);

@@ -767,9 +769,15 @@ __always_inline long __get_user_pages_un { long ret; int locked = 1; + + if (write) + gup_flags |= FOLL_WRITE; + if (force) + gup_flags |= FOLL_FORCE; + down_read(&mm->mmap_sem); - ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, - pages, NULL, &locked, false, gup_flags); + ret = __get_user_pages_locked(tsk, mm, start, nr_pages, pages, NULL, + &locked, false, gup_flags); if (locked) up_read(&mm->mmap_sem); return ret; @@ -861,8 +869,15 @@ long get_user_pages(struct task_struct * unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas) { - return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, - pages, vmas, NULL, false, FOLL_TOUCH); + unsigned int flags = FOLL_TOUCH; + + if (write) + flags |= FOLL_WRITE; + if (force) + flags |= FOLL_FORCE; + + return __get_user_pages_locked(tsk, mm, start, nr_pages, + pages, vmas, NULL, false, flags); } EXPORT_SYMBOL(get_user_pages);

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

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

From: Lorenzo Stoakes lstoakes@gmail.com

commit c164154f66f0c9b02673f07aa4f044f1d9c70274 upstream.

This removes the 'write' and 'force' use from get_user_pages_unlocked() and replaces them with 'gup_flags' to make the use of FOLL_FORCE explicit in callers as use of this flag can result in surprising behaviour (and hence bugs) within the mm subsystem.

Signed-off-by: Lorenzo Stoakes lstoakes@gmail.com Reviewed-by: Jan Kara jack@suse.cz Acked-by: Michal Hocko mhocko@suse.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org [bwh: Backported to 4.4: - Also update calls from process_vm_rw_single_vec() and async_pf_execute() - Adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/mips/mm/gup.c | 2 +- arch/s390/mm/gup.c | 2 +- arch/sh/mm/gup.c | 3 ++- arch/sparc/mm/gup.c | 3 ++- arch/x86/mm/gup.c | 2 +- drivers/media/pci/ivtv/ivtv-udma.c | 3 ++- drivers/media/pci/ivtv/ivtv-yuv.c | 8 ++++---- drivers/scsi/st.c | 5 ++--- drivers/video/fbdev/pvr2fb.c | 2 +- include/linux/mm.h | 2 +- mm/gup.c | 14 ++++---------- mm/nommu.c | 11 ++--------- mm/process_vm_access.c | 6 +++++- mm/util.c | 2 +- net/ceph/pagevec.c | 2 +- virt/kvm/async_pf.c | 2 +- 16 files changed, 31 insertions(+), 38 deletions(-)

--- a/arch/mips/mm/gup.c +++ b/arch/mips/mm/gup.c @@ -303,7 +303,7 @@ slow_irqon:

ret = get_user_pages_unlocked(current, mm, start, (end - start) >> PAGE_SHIFT, - write, 0, pages); + pages, write ? FOLL_WRITE : 0);

/* Have to be a bit careful with return values */ if (nr > 0) { --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -242,7 +242,7 @@ int get_user_pages_fast(unsigned long st start += nr << PAGE_SHIFT; pages += nr; ret = get_user_pages_unlocked(current, mm, start, - nr_pages - nr, write, 0, pages); + nr_pages - nr, pages, write ? FOLL_WRITE : 0); /* Have to be a bit careful with return values */ if (nr > 0) ret = (ret < 0) ? nr : ret + nr; --- a/arch/sh/mm/gup.c +++ b/arch/sh/mm/gup.c @@ -258,7 +258,8 @@ slow_irqon: pages += nr;

ret = get_user_pages_unlocked(current, mm, start, - (end - start) >> PAGE_SHIFT, write, 0, pages); + (end - start) >> PAGE_SHIFT, pages, + write ? FOLL_WRITE : 0);

/* Have to be a bit careful with return values */ if (nr > 0) { --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -250,7 +250,8 @@ slow: pages += nr;

ret = get_user_pages_unlocked(current, mm, start, - (end - start) >> PAGE_SHIFT, write, 0, pages); + (end - start) >> PAGE_SHIFT, pages, + write ? FOLL_WRITE : 0);

/* Have to be a bit careful with return values */ if (nr > 0) { --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -388,7 +388,7 @@ slow_irqon:

ret = get_user_pages_unlocked(current, mm, start, (end - start) >> PAGE_SHIFT, - write, 0, pages); + pages, write ? FOLL_WRITE : 0);

/* Have to be a bit careful with return values */ if (nr > 0) { --- a/drivers/media/pci/ivtv/ivtv-udma.c +++ b/drivers/media/pci/ivtv/ivtv-udma.c @@ -125,7 +125,8 @@ int ivtv_udma_setup(struct ivtv *itv, un

/* Get user pages for DMA Xfer */ err = get_user_pages_unlocked(current, current->mm, - user_dma.uaddr, user_dma.page_count, 0, 1, dma->map); + user_dma.uaddr, user_dma.page_count, dma->map, + FOLL_FORCE);

if (user_dma.page_count != err) { IVTV_DEBUG_WARN("failed to map user pages, returned %d instead of %d\n", --- a/drivers/media/pci/ivtv/ivtv-yuv.c +++ b/drivers/media/pci/ivtv/ivtv-yuv.c @@ -76,13 +76,13 @@ static int ivtv_yuv_prep_user_dma(struct

/* Get user pages for DMA Xfer */ y_pages = get_user_pages_unlocked(current, current->mm, - y_dma.uaddr, y_dma.page_count, 0, 1, - &dma->map[0]); + y_dma.uaddr, y_dma.page_count, + &dma->map[0], FOLL_FORCE); uv_pages = 0; /* silence gcc. value is set and consumed only if: */ if (y_pages == y_dma.page_count) { uv_pages = get_user_pages_unlocked(current, current->mm, - uv_dma.uaddr, uv_dma.page_count, 0, 1, - &dma->map[y_pages]); + uv_dma.uaddr, uv_dma.page_count, + &dma->map[y_pages], FOLL_FORCE); }

if (y_pages != y_dma.page_count || uv_pages != uv_dma.page_count) { --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -4821,9 +4821,8 @@ static int sgl_map_user_pages(struct st_ current->mm, uaddr, nr_pages, - rw == READ, - 0, /* don't force */ - pages); + pages, + rw == READ ? FOLL_WRITE : 0); /* don't force */

/* Errors and no page mapped should return here */ if (res < nr_pages) --- a/drivers/video/fbdev/pvr2fb.c +++ b/drivers/video/fbdev/pvr2fb.c @@ -687,7 +687,7 @@ static ssize_t pvr2fb_write(struct fb_in return -ENOMEM;

ret = get_user_pages_unlocked(current, current->mm, (unsigned long)buf, - nr_pages, WRITE, 0, pages); + nr_pages, pages, FOLL_WRITE);

if (ret < nr_pages) { nr_pages = ret; --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1210,7 +1210,7 @@ long __get_user_pages_unlocked(struct ta struct page **pages, unsigned int gup_flags); long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages); + struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages);

--- a/mm/gup.c +++ b/mm/gup.c @@ -797,17 +797,10 @@ EXPORT_SYMBOL(__get_user_pages_unlocked) */ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages) + struct page **pages, unsigned int gup_flags) { - unsigned int flags = FOLL_TOUCH; - - if (write) - flags |= FOLL_WRITE; - if (force) - flags |= FOLL_FORCE; - return __get_user_pages_unlocked(tsk, mm, start, nr_pages, - pages, flags); + pages, gup_flags | FOLL_TOUCH); } EXPORT_SYMBOL(get_user_pages_unlocked);

@@ -1427,7 +1420,8 @@ int get_user_pages_fast(unsigned long st pages += nr;

ret = get_user_pages_unlocked(current, mm, start, - nr_pages - nr, write, 0, pages); + nr_pages - nr, pages, + write ? FOLL_WRITE : 0);

/* Have to be a bit careful with return values */ if (nr > 0) { --- a/mm/nommu.c +++ b/mm/nommu.c @@ -224,17 +224,10 @@ EXPORT_SYMBOL(__get_user_pages_unlocked)

long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages) + struct page **pages, unsigned int gup_flags) { - unsigned int flags = 0; - - if (write) - flags |= FOLL_WRITE; - if (force) - flags |= FOLL_FORCE; - return __get_user_pages_unlocked(tsk, mm, start, nr_pages, - pages, flags); + pages, gup_flags); } EXPORT_SYMBOL(get_user_pages_unlocked);

--- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -88,19 +88,23 @@ static int process_vm_rw_single_vec(unsi ssize_t rc = 0; unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES / sizeof(struct pages *); + unsigned int flags = 0;

/* Work out address and page range required */ if (len == 0) return 0; nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;

+ if (vm_write) + flags |= FOLL_WRITE; + while (!rc && nr_pages && iov_iter_count(iter)) { int pages = min(nr_pages, max_pages_per_loop); size_t bytes;

/* Get the pages we're interested in */ pages = get_user_pages_unlocked(task, mm, pa, pages, - vm_write, 0, process_pages); + process_pages, flags); if (pages <= 0) return -EFAULT;

--- a/mm/util.c +++ b/mm/util.c @@ -278,7 +278,7 @@ int __weak get_user_pages_fast(unsigned { struct mm_struct *mm = current->mm; return get_user_pages_unlocked(current, mm, start, nr_pages, - write, 0, pages); + pages, write ? FOLL_WRITE : 0); } EXPORT_SYMBOL_GPL(get_user_pages_fast);

--- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -26,7 +26,7 @@ struct page **ceph_get_direct_page_vecto while (got < num_pages) { rc = get_user_pages_unlocked(current, current->mm, (unsigned long)data + ((unsigned long)got * PAGE_SIZE), - num_pages - got, write_page, 0, pages + got); + num_pages - got, pages + got, write_page ? FOLL_WRITE : 0); if (rc < 0) break; BUG_ON(rc == 0); --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -80,7 +80,7 @@ static void async_pf_execute(struct work

might_sleep();

- get_user_pages_unlocked(NULL, mm, addr, 1, 1, 0, NULL); + get_user_pages_unlocked(NULL, mm, addr, 1, NULL, FOLL_WRITE); kvm_async_page_present_sync(vcpu, apf);

spin_lock(&vcpu->async_pf.lock);

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

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

From: Lorenzo Stoakes lstoakes@gmail.com

commit 7f23b3504a0df63b724180262c5f3f117f21bcae upstream.

This removes the 'write' and 'force' from get_vaddr_frames() and replaces them with 'gup_flags' to make the use of FOLL_FORCE explicit in callers as use of this flag can result in surprising behaviour (and hence bugs) within the mm subsystem.

Signed-off-by: Lorenzo Stoakes lstoakes@gmail.com Acked-by: Michal Hocko mhocko@suse.com Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/exynos/exynos_drm_g2d.c | 3 ++- drivers/media/platform/omap/omap_vout.c | 2 +- drivers/media/v4l2-core/videobuf2-memops.c | 6 +++++- include/linux/mm.h | 2 +- mm/frame_vector.c | 13 ++----------- 5 files changed, 11 insertions(+), 15 deletions(-)

--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -471,7 +471,8 @@ static dma_addr_t *g2d_userptr_get_dma_a goto err_free; }

- ret = get_vaddr_frames(start, npages, true, true, g2d_userptr->vec); + ret = get_vaddr_frames(start, npages, FOLL_FORCE | FOLL_WRITE, + g2d_userptr->vec); if (ret != npages) { DRM_ERROR("failed to get user pages from userptr.\n"); if (ret < 0) --- a/drivers/media/platform/omap/omap_vout.c +++ b/drivers/media/platform/omap/omap_vout.c @@ -214,7 +214,7 @@ static int omap_vout_get_userptr(struct if (!vec) return -ENOMEM;

- ret = get_vaddr_frames(virtp, 1, true, false, vec); + ret = get_vaddr_frames(virtp, 1, FOLL_WRITE, vec); if (ret != 1) { frame_vector_destroy(vec); return -EINVAL; --- a/drivers/media/v4l2-core/videobuf2-memops.c +++ b/drivers/media/v4l2-core/videobuf2-memops.c @@ -42,6 +42,10 @@ struct frame_vector *vb2_create_framevec unsigned long first, last; unsigned long nr; struct frame_vector *vec; + unsigned int flags = FOLL_FORCE; + + if (write) + flags |= FOLL_WRITE;

first = start >> PAGE_SHIFT; last = (start + length - 1) >> PAGE_SHIFT; @@ -49,7 +53,7 @@ struct frame_vector *vb2_create_framevec vec = frame_vector_create(nr); if (!vec) return ERR_PTR(-ENOMEM); - ret = get_vaddr_frames(start & PAGE_MASK, nr, write, true, vec); + ret = get_vaddr_frames(start & PAGE_MASK, nr, flags, vec); if (ret < 0) goto out_destroy; /* We accept only complete set of PFNs */ --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1227,7 +1227,7 @@ struct frame_vector { struct frame_vector *frame_vector_create(unsigned int nr_frames); void frame_vector_destroy(struct frame_vector *vec); int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, - bool write, bool force, struct frame_vector *vec); + unsigned int gup_flags, struct frame_vector *vec); void put_vaddr_frames(struct frame_vector *vec); int frame_vector_to_pages(struct frame_vector *vec); void frame_vector_to_pfns(struct frame_vector *vec); --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -11,10 +11,7 @@ * get_vaddr_frames() - map virtual addresses to pfns * @start: starting user address * @nr_frames: number of pages / pfns from start to map - * @write: whether pages will be written to by the caller - * @force: whether to force write access even if user mapping is - * readonly. See description of the same argument of - get_user_pages(). + * @gup_flags: flags modifying lookup behaviour * @vec: structure which receives pages / pfns of the addresses mapped. * It should have space for at least nr_frames entries. * @@ -34,23 +31,17 @@ * This function takes care of grabbing mmap_sem as necessary. */ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, - bool write, bool force, struct frame_vector *vec) + unsigned int gup_flags, struct frame_vector *vec) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int ret = 0; int err; int locked; - unsigned int gup_flags = 0;

if (nr_frames == 0) return 0;

- if (write) - gup_flags |= FOLL_WRITE; - if (force) - gup_flags |= FOLL_FORCE; - if (WARN_ON_ONCE(nr_frames > vec->nr_allocated)) nr_frames = vec->nr_allocated;

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

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

From: Lorenzo Stoakes lstoakes@gmail.com

commit 442486ec1096781c50227b73f721a63974b0fdda upstream.

This removes the 'write' argument from __access_remote_vm() and replaces it with 'gup_flags' as use of this function previously silently implied FOLL_FORCE, whereas after this patch callers explicitly pass this flag.

We make this explicit as use of FOLL_FORCE can result in surprising behaviour (and hence bugs) within the mm subsystem.

Signed-off-by: Lorenzo Stoakes lstoakes@gmail.com Acked-by: Michal Hocko mhocko@suse.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org [bwh: Backported to 4.4: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/memory.c | 23 +++++++++++++++-------- mm/nommu.c | 9 ++++++--- 2 files changed, 21 insertions(+), 11 deletions(-)

--- a/mm/memory.c +++ b/mm/memory.c @@ -3711,14 +3711,11 @@ EXPORT_SYMBOL_GPL(generic_access_phys); * given task for page fault accounting. */ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, - unsigned long addr, void *buf, int len, int write) + unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct vm_area_struct *vma; void *old_buf = buf; - unsigned int flags = FOLL_FORCE; - - if (write) - flags |= FOLL_WRITE; + int write = gup_flags & FOLL_WRITE;

down_read(&mm->mmap_sem); /* ignore errors, just check how much was successfully transferred */ @@ -3728,7 +3725,7 @@ static int __access_remote_vm(struct tas struct page *page = NULL;

ret = get_user_pages(tsk, mm, addr, 1, - flags, &page, &vma); + gup_flags, &page, &vma); if (ret <= 0) { #ifndef CONFIG_HAVE_IOREMAP_PROT break; @@ -3787,7 +3784,12 @@ static int __access_remote_vm(struct tas int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, int write) { - return __access_remote_vm(NULL, mm, addr, buf, len, write); + unsigned int flags = FOLL_FORCE; + + if (write) + flags |= FOLL_WRITE; + + return __access_remote_vm(NULL, mm, addr, buf, len, flags); }

/* @@ -3800,12 +3802,17 @@ int access_process_vm(struct task_struct { struct mm_struct *mm; int ret; + unsigned int flags = FOLL_FORCE;

mm = get_task_mm(tsk); if (!mm) return 0;

- ret = __access_remote_vm(tsk, mm, addr, buf, len, write); + if (write) + flags |= FOLL_WRITE; + + ret = __access_remote_vm(tsk, mm, addr, buf, len, flags); + mmput(mm);

return ret; --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1929,9 +1929,10 @@ void filemap_map_pages(struct vm_area_st EXPORT_SYMBOL(filemap_map_pages);

static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, - unsigned long addr, void *buf, int len, int write) + unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct vm_area_struct *vma; + int write = gup_flags & FOLL_WRITE;

down_read(&mm->mmap_sem);

@@ -1973,7 +1974,8 @@ static int __access_remote_vm(struct tas int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, int write) { - return __access_remote_vm(NULL, mm, addr, buf, len, write); + return __access_remote_vm(NULL, mm, addr, buf, len, + write ? FOLL_WRITE : 0); }

/* @@ -1991,7 +1993,8 @@ int access_process_vm(struct task_struct if (!mm) return 0;

- len = __access_remote_vm(tsk, mm, addr, buf, len, write); + len = __access_remote_vm(tsk, mm, addr, buf, len, + write ? FOLL_WRITE : 0);

mmput(mm); return len;

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

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

From: Linus Torvalds torvalds@linux-foundation.org

commit 272ddc8b37354c3fe111ab26d25e792629148eee upstream.

Now that Lorenzo cleaned things up and made the FOLL_FORCE users explicit, it becomes obvious how some of them don't really need FOLL_FORCE at all.

So remove FOLL_FORCE from the proc code that reads the command line and arguments from user space.

The mem_rw() function actually does want FOLL_FORCE, because gdd (and possibly many other debuggers) use it as a much more convenient version of PTRACE_PEEKDATA, but we should consider making the FOLL_FORCE part conditional on actually being a ptracer. This does not actually do that, just moves adds a comment to that effect and moves the gup_flags settings next to each other.

Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/proc/base.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-)

--- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -254,7 +254,7 @@ 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, FOLL_FORCE); + rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0); if (rv <= 0) goto out_free_page;

@@ -272,8 +272,7 @@ 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, - FOLL_FORCE); + nr_read = access_remote_vm(mm, p, page, _count, 0); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -308,8 +307,7 @@ 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, - FOLL_FORCE); + nr_read = access_remote_vm(mm, p, page, _count, 0); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -358,8 +356,7 @@ skip_argv: bool final;

_count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, - FOLL_FORCE); + nr_read = access_remote_vm(mm, p, page, _count, 0); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -871,7 +868,7 @@ static ssize_t mem_rw(struct file *file, unsigned long addr = *ppos; ssize_t copied; char *page; - unsigned int flags = FOLL_FORCE; + unsigned int flags;

if (!mm) return 0; @@ -884,6 +881,8 @@ static ssize_t mem_rw(struct file *file, if (!atomic_inc_not_zero(&mm->mm_users)) goto free;

+ /* Maybe we should limit FOLL_FORCE to actual ptrace users? */ + flags = FOLL_FORCE; if (write) flags |= FOLL_WRITE;

@@ -1007,8 +1006,7 @@ 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, FOLL_FORCE); + retval = access_remote_vm(mm, (env_start + src), page, this_len, 0);

if (retval <= 0) { ret = retval;

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

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

From: Arnd Bergmann arnd@arndb.de

commit 3cd890dbe2a4f14cc44c85bb6cf37e5e22d4dd0e upstream.

A typical code fragment was copied across many dvb-frontend drivers and causes large stack frames when built with with CONFIG_KASAN on gcc-5/6/7:

drivers/media/dvb-frontends/cxd2841er.c:3225:1: error: the frame size of 3992 bytes is larger than 3072 bytes [-Werror=frame-larger-than=] drivers/media/dvb-frontends/cxd2841er.c:3404:1: error: the frame size of 3136 bytes is larger than 3072 bytes [-Werror=frame-larger-than=] drivers/media/dvb-frontends/stv0367.c:3143:1: error: the frame size of 4016 bytes is larger than 3072 bytes [-Werror=frame-larger-than=] drivers/media/dvb-frontends/stv090x.c:3430:1: error: the frame size of 5312 bytes is larger than 3072 bytes [-Werror=frame-larger-than=] drivers/media/dvb-frontends/stv090x.c:4248:1: error: the frame size of 4872 bytes is larger than 3072 bytes [-Werror=frame-larger-than=]

gcc-8 now solves this by consolidating the stack slots for the argument variables, but on older compilers we can get the same behavior by taking the pointer of a local variable rather than the inline function argument.

Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715

Cc: stable@vger.kernel.org Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Mauro Carvalho Chehab mchehab@s-opensource.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/media/dvb-frontends/ascot2e.c | 4 +++- drivers/media/dvb-frontends/cxd2841er.c | 4 +++- drivers/media/dvb-frontends/horus3a.c | 4 +++- drivers/media/dvb-frontends/itd1000.c | 5 +++-- drivers/media/dvb-frontends/mt312.c | 5 ++++- drivers/media/dvb-frontends/stb0899_drv.c | 3 ++- drivers/media/dvb-frontends/stb6100.c | 6 ++++-- drivers/media/dvb-frontends/stv0367.c | 4 +++- drivers/media/dvb-frontends/stv090x.c | 4 +++- drivers/media/dvb-frontends/stv6110x.c | 4 +++- drivers/media/dvb-frontends/zl10039.c | 4 +++- 11 files changed, 34 insertions(+), 13 deletions(-)

--- a/drivers/media/dvb-frontends/ascot2e.c +++ b/drivers/media/dvb-frontends/ascot2e.c @@ -155,7 +155,9 @@ static int ascot2e_write_regs(struct asc

static int ascot2e_write_reg(struct ascot2e_priv *priv, u8 reg, u8 val) { - return ascot2e_write_regs(priv, reg, &val, 1); + u8 tmp = val; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ + + return ascot2e_write_regs(priv, reg, &tmp, 1); }

static int ascot2e_read_regs(struct ascot2e_priv *priv, --- a/drivers/media/dvb-frontends/cxd2841er.c +++ b/drivers/media/dvb-frontends/cxd2841er.c @@ -241,7 +241,9 @@ static int cxd2841er_write_regs(struct c static int cxd2841er_write_reg(struct cxd2841er_priv *priv, u8 addr, u8 reg, u8 val) { - return cxd2841er_write_regs(priv, addr, reg, &val, 1); + u8 tmp = val; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ + + return cxd2841er_write_regs(priv, addr, reg, &tmp, 1); }

static int cxd2841er_read_regs(struct cxd2841er_priv *priv, --- a/drivers/media/dvb-frontends/horus3a.c +++ b/drivers/media/dvb-frontends/horus3a.c @@ -89,7 +89,9 @@ static int horus3a_write_regs(struct hor

static int horus3a_write_reg(struct horus3a_priv *priv, u8 reg, u8 val) { - return horus3a_write_regs(priv, reg, &val, 1); + u8 tmp = val; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ + + return horus3a_write_regs(priv, reg, &tmp, 1); }

static int horus3a_enter_power_save(struct horus3a_priv *priv) --- a/drivers/media/dvb-frontends/itd1000.c +++ b/drivers/media/dvb-frontends/itd1000.c @@ -99,8 +99,9 @@ static int itd1000_read_reg(struct itd10

static inline int itd1000_write_reg(struct itd1000_state *state, u8 r, u8 v) { - int ret = itd1000_write_regs(state, r, &v, 1); - state->shadow[r] = v; + u8 tmp = v; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ + int ret = itd1000_write_regs(state, r, &tmp, 1); + state->shadow[r] = tmp; return ret; }

--- a/drivers/media/dvb-frontends/mt312.c +++ b/drivers/media/dvb-frontends/mt312.c @@ -142,7 +142,10 @@ static inline int mt312_readreg(struct m static inline int mt312_writereg(struct mt312_state *state, const enum mt312_reg_addr reg, const u8 val) { - return mt312_write(state, reg, &val, 1); + u8 tmp = val; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ + + + return mt312_write(state, reg, &tmp, 1); }

static inline u32 mt312_div(u32 a, u32 b) --- a/drivers/media/dvb-frontends/stb0899_drv.c +++ b/drivers/media/dvb-frontends/stb0899_drv.c @@ -552,7 +552,8 @@ int stb0899_write_regs(struct stb0899_st

int stb0899_write_reg(struct stb0899_state *state, unsigned int reg, u8 data) { - return stb0899_write_regs(state, reg, &data, 1); + u8 tmp = data; + return stb0899_write_regs(state, reg, &tmp, 1); }

/* --- a/drivers/media/dvb-frontends/stb6100.c +++ b/drivers/media/dvb-frontends/stb6100.c @@ -226,12 +226,14 @@ static int stb6100_write_reg_range(struc

static int stb6100_write_reg(struct stb6100_state *state, u8 reg, u8 data) { + u8 tmp = data; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ + if (unlikely(reg >= STB6100_NUMREGS)) { dprintk(verbose, FE_ERROR, 1, "Invalid register offset 0x%x", reg); return -EREMOTEIO; } - data = (data & stb6100_template[reg].mask) | stb6100_template[reg].set; - return stb6100_write_reg_range(state, &data, reg, 1); + tmp = (tmp & stb6100_template[reg].mask) | stb6100_template[reg].set; + return stb6100_write_reg_range(state, &tmp, reg, 1); }

--- a/drivers/media/dvb-frontends/stv0367.c +++ b/drivers/media/dvb-frontends/stv0367.c @@ -804,7 +804,9 @@ int stv0367_writeregs(struct stv0367_sta

static int stv0367_writereg(struct stv0367_state *state, u16 reg, u8 data) { - return stv0367_writeregs(state, reg, &data, 1); + u8 tmp = data; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ + + return stv0367_writeregs(state, reg, &tmp, 1); }

static u8 stv0367_readreg(struct stv0367_state *state, u16 reg) --- a/drivers/media/dvb-frontends/stv090x.c +++ b/drivers/media/dvb-frontends/stv090x.c @@ -761,7 +761,9 @@ static int stv090x_write_regs(struct stv

static int stv090x_write_reg(struct stv090x_state *state, unsigned int reg, u8 data) { - return stv090x_write_regs(state, reg, &data, 1); + u8 tmp = data; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ + + return stv090x_write_regs(state, reg, &tmp, 1); }

static int stv090x_i2c_gate_ctrl(struct stv090x_state *state, int enable) --- a/drivers/media/dvb-frontends/stv6110x.c +++ b/drivers/media/dvb-frontends/stv6110x.c @@ -97,7 +97,9 @@ static int stv6110x_write_regs(struct st

static int stv6110x_write_reg(struct stv6110x_state *stv6110x, u8 reg, u8 data) { - return stv6110x_write_regs(stv6110x, reg, &data, 1); + u8 tmp = data; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ + + return stv6110x_write_regs(stv6110x, reg, &tmp, 1); }

static int stv6110x_init(struct dvb_frontend *fe) --- a/drivers/media/dvb-frontends/zl10039.c +++ b/drivers/media/dvb-frontends/zl10039.c @@ -138,7 +138,9 @@ static inline int zl10039_writereg(struc const enum zl10039_reg_addr reg, const u8 val) { - return zl10039_write(state, reg, &val, 1); + const u8 tmp = val; /* see gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 */ + + return zl10039_write(state, reg, &tmp, 1); }

static int zl10039_init(struct dvb_frontend *fe)

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

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

From: Guenter Roeck linux@roeck-us.net

commit fd29edc7232bc19f969e8f463138afc5472b3d5f upstream.

gcc 8.1.0 generates the following warnings.

drivers/staging/speakup/kobjects.c: In function 'punc_store': drivers/staging/speakup/kobjects.c:522:2: warning: 'strncpy' output truncated before terminating nul copying as many bytes from a string as its length drivers/staging/speakup/kobjects.c:504:6: note: length computed here

drivers/staging/speakup/kobjects.c: In function 'synth_store': drivers/staging/speakup/kobjects.c:391:2: warning: 'strncpy' output truncated before terminating nul copying as many bytes from a string as its length drivers/staging/speakup/kobjects.c:388:8: note: length computed here

Using strncpy() is indeed less than perfect since the length of data to be copied has already been determined with strlen(). Replace strncpy() with memcpy() to address the warning and optimize the code a little.

Signed-off-by: Guenter Roeck linux@roeck-us.net Reviewed-by: Samuel Thibault samuel.thibault@ens-lyon.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/staging/speakup/kobjects.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/staging/speakup/kobjects.c +++ b/drivers/staging/speakup/kobjects.c @@ -387,7 +387,7 @@ static ssize_t synth_store(struct kobjec len = strlen(buf); if (len < 2 || len > 9) return -EINVAL; - strncpy(new_synth_name, buf, len); + memcpy(new_synth_name, buf, len); if (new_synth_name[len - 1] == '\n') len--; new_synth_name[len] = '\0'; @@ -514,7 +514,7 @@ static ssize_t punc_store(struct kobject return -EINVAL; }

- strncpy(punc_buf, buf, x); + memcpy(punc_buf, buf, x);

while (x && punc_buf[x - 1] == '\n') x--;

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

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

From: Shuah Khan shuahkh@osg.samsung.com

commit 3d2c86e3057995270e08693231039d9d942871f0 upstream.

Remove networking from Documentation Makefile to move the test to selftests. Update networking/timestamping Makefile to work under selftests. These tests will not be run as part of selftests suite and will not be included in install targets. They can be built and run separately for now.

This is part of the effort to move runnable code from Documentation.

Acked-by: Jonathan Corbet corbet@lwn.net Signed-off-by: Shuah Khan shuahkh@osg.samsung.com [ added to 4.4.y stable to remove a build warning - gregkh] Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- Documentation/Makefile | 3 Documentation/networking/Makefile | 1 Documentation/networking/timestamping/.gitignore | 3 Documentation/networking/timestamping/Makefile | 14 Documentation/networking/timestamping/hwtstamp_config.c | 134 -- Documentation/networking/timestamping/timestamping.c | 528 --------- Documentation/networking/timestamping/txtimestamp.c | 549 ---------- tools/testing/selftests/networking/timestamping/.gitignore | 3 tools/testing/selftests/networking/timestamping/Makefile | 8 tools/testing/selftests/networking/timestamping/hwtstamp_config.c | 134 ++ tools/testing/selftests/networking/timestamping/timestamping.c | 528 +++++++++ tools/testing/selftests/networking/timestamping/txtimestamp.c | 549 ++++++++++ 12 files changed, 1223 insertions(+), 1231 deletions(-)

--- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -1,4 +1,3 @@ subdir-y := accounting auxdisplay blackfin connector \ filesystems filesystems ia64 laptops misc-devices \ - networking pcmcia prctl ptp spi timers vDSO video4linux \ - watchdog + pcmcia prctl ptp spi timers vDSO video4linux watchdog --- a/Documentation/networking/Makefile +++ /dev/null @@ -1 +0,0 @@ -subdir-y := timestamping --- a/Documentation/networking/timestamping/.gitignore +++ /dev/null @@ -1,3 +0,0 @@ -timestamping -txtimestamp -hwtstamp_config --- a/Documentation/networking/timestamping/Makefile +++ /dev/null @@ -1,14 +0,0 @@ -# To compile, from the source root -# -# make headers_install -# make M=documentation - -# List of programs to build -hostprogs-y := hwtstamp_config timestamping txtimestamp - -# Tell kbuild to always build the programs -always := $(hostprogs-y) - -HOSTCFLAGS_timestamping.o += -I$(objtree)/usr/include -HOSTCFLAGS_txtimestamp.o += -I$(objtree)/usr/include -HOSTCFLAGS_hwtstamp_config.o += -I$(objtree)/usr/include --- a/Documentation/networking/timestamping/hwtstamp_config.c +++ /dev/null @@ -1,134 +0,0 @@ -/* Test program for SIOC{G,S}HWTSTAMP - * Copyright 2013 Solarflare Communications - * Author: Ben Hutchings - */ - -#include <errno.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> - -#include <sys/socket.h> -#include <sys/ioctl.h> - -#include <linux/if.h> -#include <linux/net_tstamp.h> -#include <linux/sockios.h> - -static int -lookup_value(const char **names, int size, const char *name) -{ - int value; - - for (value = 0; value < size; value++) - if (names[value] && strcasecmp(names[value], name) == 0) - return value; - - return -1; -} - -static const char * -lookup_name(const char **names, int size, int value) -{ - return (value >= 0 && value < size) ? names[value] : NULL; -} - -static void list_names(FILE *f, const char **names, int size) -{ - int value; - - for (value = 0; value < size; value++) - if (names[value]) - fprintf(f, " %s\n", names[value]); -} - -static const char *tx_types[] = { -#define TX_TYPE(name) [HWTSTAMP_TX_ ## name] = #name - TX_TYPE(OFF), - TX_TYPE(ON), - TX_TYPE(ONESTEP_SYNC) -#undef TX_TYPE -}; -#define N_TX_TYPES ((int)(sizeof(tx_types) / sizeof(tx_types[0]))) - -static const char *rx_filters[] = { -#define RX_FILTER(name) [HWTSTAMP_FILTER_ ## name] = #name - RX_FILTER(NONE), - RX_FILTER(ALL), - RX_FILTER(SOME), - RX_FILTER(PTP_V1_L4_EVENT), - RX_FILTER(PTP_V1_L4_SYNC), - RX_FILTER(PTP_V1_L4_DELAY_REQ), - RX_FILTER(PTP_V2_L4_EVENT), - RX_FILTER(PTP_V2_L4_SYNC), - RX_FILTER(PTP_V2_L4_DELAY_REQ), - RX_FILTER(PTP_V2_L2_EVENT), - RX_FILTER(PTP_V2_L2_SYNC), - RX_FILTER(PTP_V2_L2_DELAY_REQ), - RX_FILTER(PTP_V2_EVENT), - RX_FILTER(PTP_V2_SYNC), - RX_FILTER(PTP_V2_DELAY_REQ), -#undef RX_FILTER -}; -#define N_RX_FILTERS ((int)(sizeof(rx_filters) / sizeof(rx_filters[0]))) - -static void usage(void) -{ - fputs("Usage: hwtstamp_config if_name [tx_type rx_filter]\n" - "tx_type is any of (case-insensitive):\n", - stderr); - list_names(stderr, tx_types, N_TX_TYPES); - fputs("rx_filter is any of (case-insensitive):\n", stderr); - list_names(stderr, rx_filters, N_RX_FILTERS); -} - -int main(int argc, char **argv) -{ - struct ifreq ifr; - struct hwtstamp_config config; - const char *name; - int sock; - - if ((argc != 2 && argc != 4) || (strlen(argv[1]) >= IFNAMSIZ)) { - usage(); - return 2; - } - - if (argc == 4) { - config.flags = 0; - config.tx_type = lookup_value(tx_types, N_TX_TYPES, argv[2]); - config.rx_filter = lookup_value(rx_filters, N_RX_FILTERS, argv[3]); - if (config.tx_type < 0 || config.rx_filter < 0) { - usage(); - return 2; - } - } - - sock = socket(AF_INET, SOCK_DGRAM, 0); - if (sock < 0) { - perror("socket"); - return 1; - } - - strcpy(ifr.ifr_name, argv[1]); - ifr.ifr_data = (caddr_t)&config; - - if (ioctl(sock, (argc == 2) ? SIOCGHWTSTAMP : SIOCSHWTSTAMP, &ifr)) { - perror("ioctl"); - return 1; - } - - printf("flags = %#x\n", config.flags); - name = lookup_name(tx_types, N_TX_TYPES, config.tx_type); - if (name) - printf("tx_type = %s\n", name); - else - printf("tx_type = %d\n", config.tx_type); - name = lookup_name(rx_filters, N_RX_FILTERS, config.rx_filter); - if (name) - printf("rx_filter = %s\n", name); - else - printf("rx_filter = %d\n", config.rx_filter); - - return 0; -} --- a/Documentation/networking/timestamping/timestamping.c +++ /dev/null @@ -1,528 +0,0 @@ -/* - * This program demonstrates how the various time stamping features in - * the Linux kernel work. It emulates the behavior of a PTP - * implementation in stand-alone master mode by sending PTPv1 Sync - * multicasts once every second. It looks for similar packets, but - * beyond that doesn't actually implement PTP. - * - * Outgoing packets are time stamped with SO_TIMESTAMPING with or - * without hardware support. - * - * Incoming packets are time stamped with SO_TIMESTAMPING with or - * without hardware support, SIOCGSTAMP[NS] (per-socket time stamp) and - * SO_TIMESTAMP[NS]. - * - * Copyright (C) 2009 Intel Corporation. - * Author: Patrick Ohly patrick.ohly@intel.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include <stdio.h> -#include <stdlib.h> -#include <errno.h> -#include <string.h> - -#include <sys/time.h> -#include <sys/socket.h> -#include <sys/select.h> -#include <sys/ioctl.h> -#include <arpa/inet.h> -#include <net/if.h> - -#include <asm/types.h> -#include <linux/net_tstamp.h> -#include <linux/errqueue.h> - -#ifndef SO_TIMESTAMPING -# define SO_TIMESTAMPING 37 -# define SCM_TIMESTAMPING SO_TIMESTAMPING -#endif - -#ifndef SO_TIMESTAMPNS -# define SO_TIMESTAMPNS 35 -#endif - -#ifndef SIOCGSTAMPNS -# define SIOCGSTAMPNS 0x8907 -#endif - -#ifndef SIOCSHWTSTAMP -# define SIOCSHWTSTAMP 0x89b0 -#endif - -static void usage(const char *error) -{ - if (error) - printf("invalid option: %s\n", error); - printf("timestamping interface option*\n\n" - "Options:\n" - " IP_MULTICAST_LOOP - looping outgoing multicasts\n" - " SO_TIMESTAMP - normal software time stamping, ms resolution\n" - " SO_TIMESTAMPNS - more accurate software time stamping\n" - " SOF_TIMESTAMPING_TX_HARDWARE - hardware time stamping of outgoing packets\n" - " SOF_TIMESTAMPING_TX_SOFTWARE - software fallback for outgoing packets\n" - " SOF_TIMESTAMPING_RX_HARDWARE - hardware time stamping of incoming packets\n" - " SOF_TIMESTAMPING_RX_SOFTWARE - software fallback for incoming packets\n" - " SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n" - " SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n" - " SIOCGSTAMP - check last socket time stamp\n" - " SIOCGSTAMPNS - more accurate socket time stamp\n"); - exit(1); -} - -static void bail(const char *error) -{ - printf("%s: %s\n", error, strerror(errno)); - exit(1); -} - -static const unsigned char sync[] = { - 0x00, 0x01, 0x00, 0x01, - 0x5f, 0x44, 0x46, 0x4c, - 0x54, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, - 0x01, 0x01, - - /* fake uuid */ - 0x00, 0x01, - 0x02, 0x03, 0x04, 0x05, - - 0x00, 0x01, 0x00, 0x37, - 0x00, 0x00, 0x00, 0x08, - 0x00, 0x00, 0x00, 0x00, - 0x49, 0x05, 0xcd, 0x01, - 0x29, 0xb1, 0x8d, 0xb0, - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x01, - - /* fake uuid */ - 0x00, 0x01, - 0x02, 0x03, 0x04, 0x05, - - 0x00, 0x00, 0x00, 0x37, - 0x00, 0x00, 0x00, 0x04, - 0x44, 0x46, 0x4c, 0x54, - 0x00, 0x00, 0xf0, 0x60, - 0x00, 0x01, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x01, - 0x00, 0x00, 0xf0, 0x60, - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x04, - 0x44, 0x46, 0x4c, 0x54, - 0x00, 0x01, - - /* fake uuid */ - 0x00, 0x01, - 0x02, 0x03, 0x04, 0x05, - - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00 -}; - -static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len) -{ - struct timeval now; - int res; - - res = sendto(sock, sync, sizeof(sync), 0, - addr, addr_len); - gettimeofday(&now, 0); - if (res < 0) - printf("%s: %s\n", "send", strerror(errno)); - else - printf("%ld.%06ld: sent %d bytes\n", - (long)now.tv_sec, (long)now.tv_usec, - res); -} - -static void printpacket(struct msghdr *msg, int res, - char *data, - int sock, int recvmsg_flags, - int siocgstamp, int siocgstampns) -{ - struct sockaddr_in *from_addr = (struct sockaddr_in *)msg->msg_name; - struct cmsghdr *cmsg; - struct timeval tv; - struct timespec ts; - struct timeval now; - - gettimeofday(&now, 0); - - printf("%ld.%06ld: received %s data, %d bytes from %s, %zu bytes control messages\n", - (long)now.tv_sec, (long)now.tv_usec, - (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular", - res, - inet_ntoa(from_addr->sin_addr), - msg->msg_controllen); - for (cmsg = CMSG_FIRSTHDR(msg); - cmsg; - cmsg = CMSG_NXTHDR(msg, cmsg)) { - printf(" cmsg len %zu: ", cmsg->cmsg_len); - switch (cmsg->cmsg_level) { - case SOL_SOCKET: - printf("SOL_SOCKET "); - switch (cmsg->cmsg_type) { - case SO_TIMESTAMP: { - struct timeval *stamp = - (struct timeval *)CMSG_DATA(cmsg); - printf("SO_TIMESTAMP %ld.%06ld", - (long)stamp->tv_sec, - (long)stamp->tv_usec); - break; - } - case SO_TIMESTAMPNS: { - struct timespec *stamp = - (struct timespec *)CMSG_DATA(cmsg); - printf("SO_TIMESTAMPNS %ld.%09ld", - (long)stamp->tv_sec, - (long)stamp->tv_nsec); - break; - } - case SO_TIMESTAMPING: { - struct timespec *stamp = - (struct timespec *)CMSG_DATA(cmsg); - printf("SO_TIMESTAMPING "); - printf("SW %ld.%09ld ", - (long)stamp->tv_sec, - (long)stamp->tv_nsec); - stamp++; - /* skip deprecated HW transformed */ - stamp++; - printf("HW raw %ld.%09ld", - (long)stamp->tv_sec, - (long)stamp->tv_nsec); - break; - } - default: - printf("type %d", cmsg->cmsg_type); - break; - } - break; - case IPPROTO_IP: - printf("IPPROTO_IP "); - switch (cmsg->cmsg_type) { - case IP_RECVERR: { - struct sock_extended_err *err = - (struct sock_extended_err *)CMSG_DATA(cmsg); - printf("IP_RECVERR ee_errno '%s' ee_origin %d => %s", - strerror(err->ee_errno), - err->ee_origin, -#ifdef SO_EE_ORIGIN_TIMESTAMPING - err->ee_origin == SO_EE_ORIGIN_TIMESTAMPING ? - "bounced packet" : "unexpected origin" -#else - "probably SO_EE_ORIGIN_TIMESTAMPING" -#endif - ); - if (res < sizeof(sync)) - printf(" => truncated data?!"); - else if (!memcmp(sync, data + res - sizeof(sync), - sizeof(sync))) - printf(" => GOT OUR DATA BACK (HURRAY!)"); - break; - } - case IP_PKTINFO: { - struct in_pktinfo *pktinfo = - (struct in_pktinfo *)CMSG_DATA(cmsg); - printf("IP_PKTINFO interface index %u", - pktinfo->ipi_ifindex); - break; - } - default: - printf("type %d", cmsg->cmsg_type); - break; - } - break; - default: - printf("level %d type %d", - cmsg->cmsg_level, - cmsg->cmsg_type); - break; - } - printf("\n"); - } - - if (siocgstamp) { - if (ioctl(sock, SIOCGSTAMP, &tv)) - printf(" %s: %s\n", "SIOCGSTAMP", strerror(errno)); - else - printf("SIOCGSTAMP %ld.%06ld\n", - (long)tv.tv_sec, - (long)tv.tv_usec); - } - if (siocgstampns) { - if (ioctl(sock, SIOCGSTAMPNS, &ts)) - printf(" %s: %s\n", "SIOCGSTAMPNS", strerror(errno)); - else - printf("SIOCGSTAMPNS %ld.%09ld\n", - (long)ts.tv_sec, - (long)ts.tv_nsec); - } -} - -static void recvpacket(int sock, int recvmsg_flags, - int siocgstamp, int siocgstampns) -{ - char data[256]; - struct msghdr msg; - struct iovec entry; - struct sockaddr_in from_addr; - struct { - struct cmsghdr cm; - char control[512]; - } control; - int res; - - memset(&msg, 0, sizeof(msg)); - msg.msg_iov = &entry; - msg.msg_iovlen = 1; - entry.iov_base = data; - entry.iov_len = sizeof(data); - msg.msg_name = (caddr_t)&from_addr; - msg.msg_namelen = sizeof(from_addr); - msg.msg_control = &control; - msg.msg_controllen = sizeof(control); - - res = recvmsg(sock, &msg, recvmsg_flags|MSG_DONTWAIT); - if (res < 0) { - printf("%s %s: %s\n", - "recvmsg", - (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular", - strerror(errno)); - } else { - printpacket(&msg, res, data, - sock, recvmsg_flags, - siocgstamp, siocgstampns); - } -} - -int main(int argc, char **argv) -{ - int so_timestamping_flags = 0; - int so_timestamp = 0; - int so_timestampns = 0; - int siocgstamp = 0; - int siocgstampns = 0; - int ip_multicast_loop = 0; - char *interface; - int i; - int enabled = 1; - int sock; - struct ifreq device; - struct ifreq hwtstamp; - struct hwtstamp_config hwconfig, hwconfig_requested; - struct sockaddr_in addr; - struct ip_mreq imr; - struct in_addr iaddr; - int val; - socklen_t len; - struct timeval next; - - if (argc < 2) - usage(0); - interface = argv[1]; - - for (i = 2; i < argc; i++) { - if (!strcasecmp(argv[i], "SO_TIMESTAMP")) - so_timestamp = 1; - else if (!strcasecmp(argv[i], "SO_TIMESTAMPNS")) - so_timestampns = 1; - else if (!strcasecmp(argv[i], "SIOCGSTAMP")) - siocgstamp = 1; - else if (!strcasecmp(argv[i], "SIOCGSTAMPNS")) - siocgstampns = 1; - else if (!strcasecmp(argv[i], "IP_MULTICAST_LOOP")) - ip_multicast_loop = 1; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_TX_SOFTWARE; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RX_HARDWARE; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RX_SOFTWARE; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SOFTWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_SOFTWARE; - else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RAW_HARDWARE")) - so_timestamping_flags |= SOF_TIMESTAMPING_RAW_HARDWARE; - else - usage(argv[i]); - } - - sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_UDP); - if (sock < 0) - bail("socket"); - - memset(&device, 0, sizeof(device)); - strncpy(device.ifr_name, interface, sizeof(device.ifr_name)); - if (ioctl(sock, SIOCGIFADDR, &device) < 0) - bail("getting interface IP address"); - - memset(&hwtstamp, 0, sizeof(hwtstamp)); - strncpy(hwtstamp.ifr_name, interface, sizeof(hwtstamp.ifr_name)); - hwtstamp.ifr_data = (void *)&hwconfig; - memset(&hwconfig, 0, sizeof(hwconfig)); - hwconfig.tx_type = - (so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ? - HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; - hwconfig.rx_filter = - (so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ? - HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE; - hwconfig_requested = hwconfig; - if (ioctl(sock, SIOCSHWTSTAMP, &hwtstamp) < 0) { - if ((errno == EINVAL || errno == ENOTSUP) && - hwconfig_requested.tx_type == HWTSTAMP_TX_OFF && - hwconfig_requested.rx_filter == HWTSTAMP_FILTER_NONE) - printf("SIOCSHWTSTAMP: disabling hardware time stamping not possible\n"); - else - bail("SIOCSHWTSTAMP"); - } - printf("SIOCSHWTSTAMP: tx_type %d requested, got %d; rx_filter %d requested, got %d\n", - hwconfig_requested.tx_type, hwconfig.tx_type, - hwconfig_requested.rx_filter, hwconfig.rx_filter); - - /* bind to PTP port */ - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = htons(319 /* PTP event port */); - if (bind(sock, - (struct sockaddr *)&addr, - sizeof(struct sockaddr_in)) < 0) - bail("bind"); - - /* set multicast group for outgoing packets */ - inet_aton("224.0.1.130", &iaddr); /* alternate PTP domain 1 */ - addr.sin_addr = iaddr; - imr.imr_multiaddr.s_addr = iaddr.s_addr; - imr.imr_interface.s_addr = - ((struct sockaddr_in *)&device.ifr_addr)->sin_addr.s_addr; - if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_IF, - &imr.imr_interface.s_addr, sizeof(struct in_addr)) < 0) - bail("set multicast"); - - /* join multicast group, loop our own packet */ - if (setsockopt(sock, IPPROTO_IP, IP_ADD_MEMBERSHIP, - &imr, sizeof(struct ip_mreq)) < 0) - bail("join multicast group"); - - if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_LOOP, - &ip_multicast_loop, sizeof(enabled)) < 0) { - bail("loop multicast"); - } - - /* set socket options for time stamping */ - if (so_timestamp && - setsockopt(sock, SOL_SOCKET, SO_TIMESTAMP, - &enabled, sizeof(enabled)) < 0) - bail("setsockopt SO_TIMESTAMP"); - - if (so_timestampns && - setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS, - &enabled, sizeof(enabled)) < 0) - bail("setsockopt SO_TIMESTAMPNS"); - - if (so_timestamping_flags && - setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, - &so_timestamping_flags, - sizeof(so_timestamping_flags)) < 0) - bail("setsockopt SO_TIMESTAMPING"); - - /* request IP_PKTINFO for debugging purposes */ - if (setsockopt(sock, SOL_IP, IP_PKTINFO, - &enabled, sizeof(enabled)) < 0) - printf("%s: %s\n", "setsockopt IP_PKTINFO", strerror(errno)); - - /* verify socket options */ - len = sizeof(val); - if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMP, &val, &len) < 0) - printf("%s: %s\n", "getsockopt SO_TIMESTAMP", strerror(errno)); - else - printf("SO_TIMESTAMP %d\n", val); - - if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS, &val, &len) < 0) - printf("%s: %s\n", "getsockopt SO_TIMESTAMPNS", - strerror(errno)); - else - printf("SO_TIMESTAMPNS %d\n", val); - - if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &val, &len) < 0) { - printf("%s: %s\n", "getsockopt SO_TIMESTAMPING", - strerror(errno)); - } else { - printf("SO_TIMESTAMPING %d\n", val); - if (val != so_timestamping_flags) - printf(" not the expected value %d\n", - so_timestamping_flags); - } - - /* send packets forever every five seconds */ - gettimeofday(&next, 0); - next.tv_sec = (next.tv_sec + 1) / 5 * 5; - next.tv_usec = 0; - while (1) { - struct timeval now; - struct timeval delta; - long delta_us; - int res; - fd_set readfs, errorfs; - - gettimeofday(&now, 0); - delta_us = (long)(next.tv_sec - now.tv_sec) * 1000000 + - (long)(next.tv_usec - now.tv_usec); - if (delta_us > 0) { - /* continue waiting for timeout or data */ - delta.tv_sec = delta_us / 1000000; - delta.tv_usec = delta_us % 1000000; - - FD_ZERO(&readfs); - FD_ZERO(&errorfs); - FD_SET(sock, &readfs); - FD_SET(sock, &errorfs); - printf("%ld.%06ld: select %ldus\n", - (long)now.tv_sec, (long)now.tv_usec, - delta_us); - res = select(sock + 1, &readfs, 0, &errorfs, &delta); - gettimeofday(&now, 0); - printf("%ld.%06ld: select returned: %d, %s\n", - (long)now.tv_sec, (long)now.tv_usec, - res, - res < 0 ? strerror(errno) : "success"); - if (res > 0) { - if (FD_ISSET(sock, &readfs)) - printf("ready for reading\n"); - if (FD_ISSET(sock, &errorfs)) - printf("has error\n"); - recvpacket(sock, 0, - siocgstamp, - siocgstampns); - recvpacket(sock, MSG_ERRQUEUE, - siocgstamp, - siocgstampns); - } - } else { - /* write one packet */ - sendpacket(sock, - (struct sockaddr *)&addr, - sizeof(addr)); - next.tv_sec += 5; - continue; - } - } - - return 0; -} --- a/Documentation/networking/timestamping/txtimestamp.c +++ /dev/null @@ -1,549 +0,0 @@ -/* - * Copyright 2014 Google Inc. - * Author: willemb@google.com (Willem de Bruijn) - * - * Test software tx timestamping, including - * - * - SCHED, SND and ACK timestamps - * - RAW, UDP and TCP - * - IPv4 and IPv6 - * - various packet sizes (to test GSO and TSO) - * - * Consult the command line arguments for help on running - * the various testcases. - * - * This test requires a dummy TCP server. - * A simple `nc6 [-u] -l -p $DESTPORT` will do - * - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#define _GNU_SOURCE - -#include <arpa/inet.h> -#include <asm/types.h> -#include <error.h> -#include <errno.h> -#include <inttypes.h> -#include <linux/errqueue.h> -#include <linux/if_ether.h> -#include <linux/net_tstamp.h> -#include <netdb.h> -#include <net/if.h> -#include <netinet/in.h> -#include <netinet/ip.h> -#include <netinet/udp.h> -#include <netinet/tcp.h> -#include <netpacket/packet.h> -#include <poll.h> -#include <stdarg.h> -#include <stdbool.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <sys/ioctl.h> -#include <sys/select.h> -#include <sys/socket.h> -#include <sys/time.h> -#include <sys/types.h> -#include <time.h> -#include <unistd.h> - -/* command line parameters */ -static int cfg_proto = SOCK_STREAM; -static int cfg_ipproto = IPPROTO_TCP; -static int cfg_num_pkts = 4; -static int do_ipv4 = 1; -static int do_ipv6 = 1; -static int cfg_payload_len = 10; -static bool cfg_show_payload; -static bool cfg_do_pktinfo; -static bool cfg_loop_nodata; -static uint16_t dest_port = 9000; - -static struct sockaddr_in daddr; -static struct sockaddr_in6 daddr6; -static struct timespec ts_prev; - -static void __print_timestamp(const char *name, struct timespec *cur, - uint32_t key, int payload_len) -{ - if (!(cur->tv_sec | cur->tv_nsec)) - return; - - fprintf(stderr, " %s: %lu s %lu us (seq=%u, len=%u)", - name, cur->tv_sec, cur->tv_nsec / 1000, - key, payload_len); - - if ((ts_prev.tv_sec | ts_prev.tv_nsec)) { - int64_t cur_ms, prev_ms; - - cur_ms = (long) cur->tv_sec * 1000 * 1000; - cur_ms += cur->tv_nsec / 1000; - - prev_ms = (long) ts_prev.tv_sec * 1000 * 1000; - prev_ms += ts_prev.tv_nsec / 1000; - - fprintf(stderr, " (%+" PRId64 " us)", cur_ms - prev_ms); - } - - ts_prev = *cur; - fprintf(stderr, "\n"); -} - -static void print_timestamp_usr(void) -{ - struct timespec ts; - struct timeval tv; /* avoid dependency on -lrt */ - - gettimeofday(&tv, NULL); - ts.tv_sec = tv.tv_sec; - ts.tv_nsec = tv.tv_usec * 1000; - - __print_timestamp(" USR", &ts, 0, 0); -} - -static void print_timestamp(struct scm_timestamping *tss, int tstype, - int tskey, int payload_len) -{ - const char *tsname; - - switch (tstype) { - case SCM_TSTAMP_SCHED: - tsname = " ENQ"; - break; - case SCM_TSTAMP_SND: - tsname = " SND"; - break; - case SCM_TSTAMP_ACK: - tsname = " ACK"; - break; - default: - error(1, 0, "unknown timestamp type: %u", - tstype); - } - __print_timestamp(tsname, &tss->ts[0], tskey, payload_len); -} - -/* TODO: convert to check_and_print payload once API is stable */ -static void print_payload(char *data, int len) -{ - int i; - - if (!len) - return; - - if (len > 70) - len = 70; - - fprintf(stderr, "payload: "); - for (i = 0; i < len; i++) - fprintf(stderr, "%02hhx ", data[i]); - fprintf(stderr, "\n"); -} - -static void print_pktinfo(int family, int ifindex, void *saddr, void *daddr) -{ - char sa[INET6_ADDRSTRLEN], da[INET6_ADDRSTRLEN]; - - fprintf(stderr, " pktinfo: ifindex=%u src=%s dst=%s\n", - ifindex, - saddr ? inet_ntop(family, saddr, sa, sizeof(sa)) : "unknown", - daddr ? inet_ntop(family, daddr, da, sizeof(da)) : "unknown"); -} - -static void __poll(int fd) -{ - struct pollfd pollfd; - int ret; - - memset(&pollfd, 0, sizeof(pollfd)); - pollfd.fd = fd; - ret = poll(&pollfd, 1, 100); - if (ret != 1) - error(1, errno, "poll"); -} - -static void __recv_errmsg_cmsg(struct msghdr *msg, int payload_len) -{ - struct sock_extended_err *serr = NULL; - struct scm_timestamping *tss = NULL; - struct cmsghdr *cm; - int batch = 0; - - for (cm = CMSG_FIRSTHDR(msg); - cm && cm->cmsg_len; - cm = CMSG_NXTHDR(msg, cm)) { - if (cm->cmsg_level == SOL_SOCKET && - cm->cmsg_type == SCM_TIMESTAMPING) { - tss = (void *) CMSG_DATA(cm); - } else if ((cm->cmsg_level == SOL_IP && - cm->cmsg_type == IP_RECVERR) || - (cm->cmsg_level == SOL_IPV6 && - cm->cmsg_type == IPV6_RECVERR)) { - serr = (void *) CMSG_DATA(cm); - if (serr->ee_errno != ENOMSG || - serr->ee_origin != SO_EE_ORIGIN_TIMESTAMPING) { - fprintf(stderr, "unknown ip error %d %d\n", - serr->ee_errno, - serr->ee_origin); - serr = NULL; - } - } else if (cm->cmsg_level == SOL_IP && - cm->cmsg_type == IP_PKTINFO) { - struct in_pktinfo *info = (void *) CMSG_DATA(cm); - print_pktinfo(AF_INET, info->ipi_ifindex, - &info->ipi_spec_dst, &info->ipi_addr); - } else if (cm->cmsg_level == SOL_IPV6 && - cm->cmsg_type == IPV6_PKTINFO) { - struct in6_pktinfo *info6 = (void *) CMSG_DATA(cm); - print_pktinfo(AF_INET6, info6->ipi6_ifindex, - NULL, &info6->ipi6_addr); - } else - fprintf(stderr, "unknown cmsg %d,%d\n", - cm->cmsg_level, cm->cmsg_type); - - if (serr && tss) { - print_timestamp(tss, serr->ee_info, serr->ee_data, - payload_len); - serr = NULL; - tss = NULL; - batch++; - } - } - - if (batch > 1) - fprintf(stderr, "batched %d timestamps\n", batch); -} - -static int recv_errmsg(int fd) -{ - static char ctrl[1024 /* overprovision*/]; - static struct msghdr msg; - struct iovec entry; - static char *data; - int ret = 0; - - data = malloc(cfg_payload_len); - if (!data) - error(1, 0, "malloc"); - - memset(&msg, 0, sizeof(msg)); - memset(&entry, 0, sizeof(entry)); - memset(ctrl, 0, sizeof(ctrl)); - - entry.iov_base = data; - entry.iov_len = cfg_payload_len; - msg.msg_iov = &entry; - msg.msg_iovlen = 1; - msg.msg_name = NULL; - msg.msg_namelen = 0; - msg.msg_control = ctrl; - msg.msg_controllen = sizeof(ctrl); - - ret = recvmsg(fd, &msg, MSG_ERRQUEUE); - if (ret == -1 && errno != EAGAIN) - error(1, errno, "recvmsg"); - - if (ret >= 0) { - __recv_errmsg_cmsg(&msg, ret); - if (cfg_show_payload) - print_payload(data, cfg_payload_len); - } - - free(data); - return ret == -1; -} - -static void do_test(int family, unsigned int opt) -{ - char *buf; - int fd, i, val = 1, total_len; - - if (family == AF_INET6 && cfg_proto != SOCK_STREAM) { - /* due to lack of checksum generation code */ - fprintf(stderr, "test: skipping datagram over IPv6\n"); - return; - } - - total_len = cfg_payload_len; - if (cfg_proto == SOCK_RAW) { - total_len += sizeof(struct udphdr); - if (cfg_ipproto == IPPROTO_RAW) - total_len += sizeof(struct iphdr); - } - - buf = malloc(total_len); - if (!buf) - error(1, 0, "malloc"); - - fd = socket(family, cfg_proto, cfg_ipproto); - if (fd < 0) - error(1, errno, "socket"); - - if (cfg_proto == SOCK_STREAM) { - if (setsockopt(fd, IPPROTO_TCP, TCP_NODELAY, - (char*) &val, sizeof(val))) - error(1, 0, "setsockopt no nagle"); - - if (family == PF_INET) { - if (connect(fd, (void *) &daddr, sizeof(daddr))) - error(1, errno, "connect ipv4"); - } else { - if (connect(fd, (void *) &daddr6, sizeof(daddr6))) - error(1, errno, "connect ipv6"); - } - } - - if (cfg_do_pktinfo) { - if (family == AF_INET6) { - if (setsockopt(fd, SOL_IPV6, IPV6_RECVPKTINFO, - &val, sizeof(val))) - error(1, errno, "setsockopt pktinfo ipv6"); - } else { - if (setsockopt(fd, SOL_IP, IP_PKTINFO, - &val, sizeof(val))) - error(1, errno, "setsockopt pktinfo ipv4"); - } - } - - opt |= SOF_TIMESTAMPING_SOFTWARE | - SOF_TIMESTAMPING_OPT_CMSG | - SOF_TIMESTAMPING_OPT_ID; - if (cfg_loop_nodata) - opt |= SOF_TIMESTAMPING_OPT_TSONLY; - - if (setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, - (char *) &opt, sizeof(opt))) - error(1, 0, "setsockopt timestamping"); - - for (i = 0; i < cfg_num_pkts; i++) { - memset(&ts_prev, 0, sizeof(ts_prev)); - memset(buf, 'a' + i, total_len); - - if (cfg_proto == SOCK_RAW) { - struct udphdr *udph; - int off = 0; - - if (cfg_ipproto == IPPROTO_RAW) { - struct iphdr *iph = (void *) buf; - - memset(iph, 0, sizeof(*iph)); - iph->ihl = 5; - iph->version = 4; - iph->ttl = 2; - iph->daddr = daddr.sin_addr.s_addr; - iph->protocol = IPPROTO_UDP; - /* kernel writes saddr, csum, len */ - - off = sizeof(*iph); - } - - udph = (void *) buf + off; - udph->source = ntohs(9000); /* random spoof */ - udph->dest = ntohs(dest_port); - udph->len = ntohs(sizeof(*udph) + cfg_payload_len); - udph->check = 0; /* not allowed for IPv6 */ - } - - print_timestamp_usr(); - if (cfg_proto != SOCK_STREAM) { - if (family == PF_INET) - val = sendto(fd, buf, total_len, 0, (void *) &daddr, sizeof(daddr)); - else - val = sendto(fd, buf, total_len, 0, (void *) &daddr6, sizeof(daddr6)); - } else { - val = send(fd, buf, cfg_payload_len, 0); - } - if (val != total_len) - error(1, errno, "send"); - - /* wait for all errors to be queued, else ACKs arrive OOO */ - usleep(50 * 1000); - - __poll(fd); - - while (!recv_errmsg(fd)) {} - } - - if (close(fd)) - error(1, errno, "close"); - - free(buf); - usleep(400 * 1000); -} - -static void __attribute__((noreturn)) usage(const char *filepath) -{ - fprintf(stderr, "\nUsage: %s [options] hostname\n" - "\nwhere options are:\n" - " -4: only IPv4\n" - " -6: only IPv6\n" - " -h: show this message\n" - " -I: request PKTINFO\n" - " -l N: send N bytes at a time\n" - " -n: set no-payload option\n" - " -r: use raw\n" - " -R: use raw (IP_HDRINCL)\n" - " -p N: connect to port N\n" - " -u: use udp\n" - " -x: show payload (up to 70 bytes)\n", - filepath); - exit(1); -} - -static void parse_opt(int argc, char **argv) -{ - int proto_count = 0; - char c; - - while ((c = getopt(argc, argv, "46hIl:np:rRux")) != -1) { - switch (c) { - case '4': - do_ipv6 = 0; - break; - case '6': - do_ipv4 = 0; - break; - case 'I': - cfg_do_pktinfo = true; - break; - case 'n': - cfg_loop_nodata = true; - break; - case 'r': - proto_count++; - cfg_proto = SOCK_RAW; - cfg_ipproto = IPPROTO_UDP; - break; - case 'R': - proto_count++; - cfg_proto = SOCK_RAW; - cfg_ipproto = IPPROTO_RAW; - break; - case 'u': - proto_count++; - cfg_proto = SOCK_DGRAM; - cfg_ipproto = IPPROTO_UDP; - break; - case 'l': - cfg_payload_len = strtoul(optarg, NULL, 10); - break; - case 'p': - dest_port = strtoul(optarg, NULL, 10); - break; - case 'x': - cfg_show_payload = true; - break; - case 'h': - default: - usage(argv[0]); - } - } - - if (!cfg_payload_len) - error(1, 0, "payload may not be nonzero"); - if (cfg_proto != SOCK_STREAM && cfg_payload_len > 1472) - error(1, 0, "udp packet might exceed expected MTU"); - if (!do_ipv4 && !do_ipv6) - error(1, 0, "pass -4 or -6, not both"); - if (proto_count > 1) - error(1, 0, "pass -r, -R or -u, not multiple"); - - if (optind != argc - 1) - error(1, 0, "missing required hostname argument"); -} - -static void resolve_hostname(const char *hostname) -{ - struct addrinfo *addrs, *cur; - int have_ipv4 = 0, have_ipv6 = 0; - - if (getaddrinfo(hostname, NULL, NULL, &addrs)) - error(1, errno, "getaddrinfo"); - - cur = addrs; - while (cur && !have_ipv4 && !have_ipv6) { - if (!have_ipv4 && cur->ai_family == AF_INET) { - memcpy(&daddr, cur->ai_addr, sizeof(daddr)); - daddr.sin_port = htons(dest_port); - have_ipv4 = 1; - } - else if (!have_ipv6 && cur->ai_family == AF_INET6) { - memcpy(&daddr6, cur->ai_addr, sizeof(daddr6)); - daddr6.sin6_port = htons(dest_port); - have_ipv6 = 1; - } - cur = cur->ai_next; - } - if (addrs) - freeaddrinfo(addrs); - - do_ipv4 &= have_ipv4; - do_ipv6 &= have_ipv6; -} - -static void do_main(int family) -{ - fprintf(stderr, "family: %s\n", - family == PF_INET ? "INET" : "INET6"); - - fprintf(stderr, "test SND\n"); - do_test(family, SOF_TIMESTAMPING_TX_SOFTWARE); - - fprintf(stderr, "test ENQ\n"); - do_test(family, SOF_TIMESTAMPING_TX_SCHED); - - fprintf(stderr, "test ENQ + SND\n"); - do_test(family, SOF_TIMESTAMPING_TX_SCHED | - SOF_TIMESTAMPING_TX_SOFTWARE); - - if (cfg_proto == SOCK_STREAM) { - fprintf(stderr, "\ntest ACK\n"); - do_test(family, SOF_TIMESTAMPING_TX_ACK); - - fprintf(stderr, "\ntest SND + ACK\n"); - do_test(family, SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_TX_ACK); - - fprintf(stderr, "\ntest ENQ + SND + ACK\n"); - do_test(family, SOF_TIMESTAMPING_TX_SCHED | - SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_TX_ACK); - } -} - -const char *sock_names[] = { NULL, "TCP", "UDP", "RAW" }; - -int main(int argc, char **argv) -{ - if (argc == 1) - usage(argv[0]); - - parse_opt(argc, argv); - resolve_hostname(argv[argc - 1]); - - fprintf(stderr, "protocol: %s\n", sock_names[cfg_proto]); - fprintf(stderr, "payload: %u\n", cfg_payload_len); - fprintf(stderr, "server port: %u\n", dest_port); - fprintf(stderr, "\n"); - - if (do_ipv4) - do_main(PF_INET); - if (do_ipv6) - do_main(PF_INET6); - - return 0; -} --- /dev/null +++ b/tools/testing/selftests/networking/timestamping/.gitignore @@ -0,0 +1,3 @@ +timestamping +txtimestamp +hwtstamp_config --- /dev/null +++ b/tools/testing/selftests/networking/timestamping/Makefile @@ -0,0 +1,8 @@ +TEST_PROGS := hwtstamp_config timestamping txtimestamp + +all: $(TEST_PROGS) + +include ../../lib.mk + +clean: + rm -fr $(TEST_PROGS) --- /dev/null +++ b/tools/testing/selftests/networking/timestamping/hwtstamp_config.c @@ -0,0 +1,134 @@ +/* Test program for SIOC{G,S}HWTSTAMP + * Copyright 2013 Solarflare Communications + * Author: Ben Hutchings + */ + +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <sys/socket.h> +#include <sys/ioctl.h> + +#include <linux/if.h> +#include <linux/net_tstamp.h> +#include <linux/sockios.h> + +static int +lookup_value(const char **names, int size, const char *name) +{ + int value; + + for (value = 0; value < size; value++) + if (names[value] && strcasecmp(names[value], name) == 0) + return value; + + return -1; +} + +static const char * +lookup_name(const char **names, int size, int value) +{ + return (value >= 0 && value < size) ? names[value] : NULL; +} + +static void list_names(FILE *f, const char **names, int size) +{ + int value; + + for (value = 0; value < size; value++) + if (names[value]) + fprintf(f, " %s\n", names[value]); +} + +static const char *tx_types[] = { +#define TX_TYPE(name) [HWTSTAMP_TX_ ## name] = #name + TX_TYPE(OFF), + TX_TYPE(ON), + TX_TYPE(ONESTEP_SYNC) +#undef TX_TYPE +}; +#define N_TX_TYPES ((int)(sizeof(tx_types) / sizeof(tx_types[0]))) + +static const char *rx_filters[] = { +#define RX_FILTER(name) [HWTSTAMP_FILTER_ ## name] = #name + RX_FILTER(NONE), + RX_FILTER(ALL), + RX_FILTER(SOME), + RX_FILTER(PTP_V1_L4_EVENT), + RX_FILTER(PTP_V1_L4_SYNC), + RX_FILTER(PTP_V1_L4_DELAY_REQ), + RX_FILTER(PTP_V2_L4_EVENT), + RX_FILTER(PTP_V2_L4_SYNC), + RX_FILTER(PTP_V2_L4_DELAY_REQ), + RX_FILTER(PTP_V2_L2_EVENT), + RX_FILTER(PTP_V2_L2_SYNC), + RX_FILTER(PTP_V2_L2_DELAY_REQ), + RX_FILTER(PTP_V2_EVENT), + RX_FILTER(PTP_V2_SYNC), + RX_FILTER(PTP_V2_DELAY_REQ), +#undef RX_FILTER +}; +#define N_RX_FILTERS ((int)(sizeof(rx_filters) / sizeof(rx_filters[0]))) + +static void usage(void) +{ + fputs("Usage: hwtstamp_config if_name [tx_type rx_filter]\n" + "tx_type is any of (case-insensitive):\n", + stderr); + list_names(stderr, tx_types, N_TX_TYPES); + fputs("rx_filter is any of (case-insensitive):\n", stderr); + list_names(stderr, rx_filters, N_RX_FILTERS); +} + +int main(int argc, char **argv) +{ + struct ifreq ifr; + struct hwtstamp_config config; + const char *name; + int sock; + + if ((argc != 2 && argc != 4) || (strlen(argv[1]) >= IFNAMSIZ)) { + usage(); + return 2; + } + + if (argc == 4) { + config.flags = 0; + config.tx_type = lookup_value(tx_types, N_TX_TYPES, argv[2]); + config.rx_filter = lookup_value(rx_filters, N_RX_FILTERS, argv[3]); + if (config.tx_type < 0 || config.rx_filter < 0) { + usage(); + return 2; + } + } + + sock = socket(AF_INET, SOCK_DGRAM, 0); + if (sock < 0) { + perror("socket"); + return 1; + } + + strcpy(ifr.ifr_name, argv[1]); + ifr.ifr_data = (caddr_t)&config; + + if (ioctl(sock, (argc == 2) ? SIOCGHWTSTAMP : SIOCSHWTSTAMP, &ifr)) { + perror("ioctl"); + return 1; + } + + printf("flags = %#x\n", config.flags); + name = lookup_name(tx_types, N_TX_TYPES, config.tx_type); + if (name) + printf("tx_type = %s\n", name); + else + printf("tx_type = %d\n", config.tx_type); + name = lookup_name(rx_filters, N_RX_FILTERS, config.rx_filter); + if (name) + printf("rx_filter = %s\n", name); + else + printf("rx_filter = %d\n", config.rx_filter); + + return 0; +} --- /dev/null +++ b/tools/testing/selftests/networking/timestamping/timestamping.c @@ -0,0 +1,528 @@ +/* + * This program demonstrates how the various time stamping features in + * the Linux kernel work. It emulates the behavior of a PTP + * implementation in stand-alone master mode by sending PTPv1 Sync + * multicasts once every second. It looks for similar packets, but + * beyond that doesn't actually implement PTP. + * + * Outgoing packets are time stamped with SO_TIMESTAMPING with or + * without hardware support. + * + * Incoming packets are time stamped with SO_TIMESTAMPING with or + * without hardware support, SIOCGSTAMP[NS] (per-socket time stamp) and + * SO_TIMESTAMP[NS]. + * + * Copyright (C) 2009 Intel Corporation. + * Author: Patrick Ohly patrick.ohly@intel.com + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <errno.h> +#include <string.h> + +#include <sys/time.h> +#include <sys/socket.h> +#include <sys/select.h> +#include <sys/ioctl.h> +#include <arpa/inet.h> +#include <net/if.h> + +#include <asm/types.h> +#include <linux/net_tstamp.h> +#include <linux/errqueue.h> + +#ifndef SO_TIMESTAMPING +# define SO_TIMESTAMPING 37 +# define SCM_TIMESTAMPING SO_TIMESTAMPING +#endif + +#ifndef SO_TIMESTAMPNS +# define SO_TIMESTAMPNS 35 +#endif + +#ifndef SIOCGSTAMPNS +# define SIOCGSTAMPNS 0x8907 +#endif + +#ifndef SIOCSHWTSTAMP +# define SIOCSHWTSTAMP 0x89b0 +#endif + +static void usage(const char *error) +{ + if (error) + printf("invalid option: %s\n", error); + printf("timestamping interface option*\n\n" + "Options:\n" + " IP_MULTICAST_LOOP - looping outgoing multicasts\n" + " SO_TIMESTAMP - normal software time stamping, ms resolution\n" + " SO_TIMESTAMPNS - more accurate software time stamping\n" + " SOF_TIMESTAMPING_TX_HARDWARE - hardware time stamping of outgoing packets\n" + " SOF_TIMESTAMPING_TX_SOFTWARE - software fallback for outgoing packets\n" + " SOF_TIMESTAMPING_RX_HARDWARE - hardware time stamping of incoming packets\n" + " SOF_TIMESTAMPING_RX_SOFTWARE - software fallback for incoming packets\n" + " SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n" + " SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n" + " SIOCGSTAMP - check last socket time stamp\n" + " SIOCGSTAMPNS - more accurate socket time stamp\n"); + exit(1); +} + +static void bail(const char *error) +{ + printf("%s: %s\n", error, strerror(errno)); + exit(1); +} + +static const unsigned char sync[] = { + 0x00, 0x01, 0x00, 0x01, + 0x5f, 0x44, 0x46, 0x4c, + 0x54, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x01, 0x01, + + /* fake uuid */ + 0x00, 0x01, + 0x02, 0x03, 0x04, 0x05, + + 0x00, 0x01, 0x00, 0x37, + 0x00, 0x00, 0x00, 0x08, + 0x00, 0x00, 0x00, 0x00, + 0x49, 0x05, 0xcd, 0x01, + 0x29, 0xb1, 0x8d, 0xb0, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x01, + + /* fake uuid */ + 0x00, 0x01, + 0x02, 0x03, 0x04, 0x05, + + 0x00, 0x00, 0x00, 0x37, + 0x00, 0x00, 0x00, 0x04, + 0x44, 0x46, 0x4c, 0x54, + 0x00, 0x00, 0xf0, 0x60, + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x01, + 0x00, 0x00, 0xf0, 0x60, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x04, + 0x44, 0x46, 0x4c, 0x54, + 0x00, 0x01, + + /* fake uuid */ + 0x00, 0x01, + 0x02, 0x03, 0x04, 0x05, + + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00 +}; + +static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len) +{ + struct timeval now; + int res; + + res = sendto(sock, sync, sizeof(sync), 0, + addr, addr_len); + gettimeofday(&now, 0); + if (res < 0) + printf("%s: %s\n", "send", strerror(errno)); + else + printf("%ld.%06ld: sent %d bytes\n", + (long)now.tv_sec, (long)now.tv_usec, + res); +} + +static void printpacket(struct msghdr *msg, int res, + char *data, + int sock, int recvmsg_flags, + int siocgstamp, int siocgstampns) +{ + struct sockaddr_in *from_addr = (struct sockaddr_in *)msg->msg_name; + struct cmsghdr *cmsg; + struct timeval tv; + struct timespec ts; + struct timeval now; + + gettimeofday(&now, 0); + + printf("%ld.%06ld: received %s data, %d bytes from %s, %zu bytes control messages\n", + (long)now.tv_sec, (long)now.tv_usec, + (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular", + res, + inet_ntoa(from_addr->sin_addr), + msg->msg_controllen); + for (cmsg = CMSG_FIRSTHDR(msg); + cmsg; + cmsg = CMSG_NXTHDR(msg, cmsg)) { + printf(" cmsg len %zu: ", cmsg->cmsg_len); + switch (cmsg->cmsg_level) { + case SOL_SOCKET: + printf("SOL_SOCKET "); + switch (cmsg->cmsg_type) { + case SO_TIMESTAMP: { + struct timeval *stamp = + (struct timeval *)CMSG_DATA(cmsg); + printf("SO_TIMESTAMP %ld.%06ld", + (long)stamp->tv_sec, + (long)stamp->tv_usec); + break; + } + case SO_TIMESTAMPNS: { + struct timespec *stamp = + (struct timespec *)CMSG_DATA(cmsg); + printf("SO_TIMESTAMPNS %ld.%09ld", + (long)stamp->tv_sec, + (long)stamp->tv_nsec); + break; + } + case SO_TIMESTAMPING: { + struct timespec *stamp = + (struct timespec *)CMSG_DATA(cmsg); + printf("SO_TIMESTAMPING "); + printf("SW %ld.%09ld ", + (long)stamp->tv_sec, + (long)stamp->tv_nsec); + stamp++; + /* skip deprecated HW transformed */ + stamp++; + printf("HW raw %ld.%09ld", + (long)stamp->tv_sec, + (long)stamp->tv_nsec); + break; + } + default: + printf("type %d", cmsg->cmsg_type); + break; + } + break; + case IPPROTO_IP: + printf("IPPROTO_IP "); + switch (cmsg->cmsg_type) { + case IP_RECVERR: { + struct sock_extended_err *err = + (struct sock_extended_err *)CMSG_DATA(cmsg); + printf("IP_RECVERR ee_errno '%s' ee_origin %d => %s", + strerror(err->ee_errno), + err->ee_origin, +#ifdef SO_EE_ORIGIN_TIMESTAMPING + err->ee_origin == SO_EE_ORIGIN_TIMESTAMPING ? + "bounced packet" : "unexpected origin" +#else + "probably SO_EE_ORIGIN_TIMESTAMPING" +#endif + ); + if (res < sizeof(sync)) + printf(" => truncated data?!"); + else if (!memcmp(sync, data + res - sizeof(sync), + sizeof(sync))) + printf(" => GOT OUR DATA BACK (HURRAY!)"); + break; + } + case IP_PKTINFO: { + struct in_pktinfo *pktinfo = + (struct in_pktinfo *)CMSG_DATA(cmsg); + printf("IP_PKTINFO interface index %u", + pktinfo->ipi_ifindex); + break; + } + default: + printf("type %d", cmsg->cmsg_type); + break; + } + break; + default: + printf("level %d type %d", + cmsg->cmsg_level, + cmsg->cmsg_type); + break; + } + printf("\n"); + } + + if (siocgstamp) { + if (ioctl(sock, SIOCGSTAMP, &tv)) + printf(" %s: %s\n", "SIOCGSTAMP", strerror(errno)); + else + printf("SIOCGSTAMP %ld.%06ld\n", + (long)tv.tv_sec, + (long)tv.tv_usec); + } + if (siocgstampns) { + if (ioctl(sock, SIOCGSTAMPNS, &ts)) + printf(" %s: %s\n", "SIOCGSTAMPNS", strerror(errno)); + else + printf("SIOCGSTAMPNS %ld.%09ld\n", + (long)ts.tv_sec, + (long)ts.tv_nsec); + } +} + +static void recvpacket(int sock, int recvmsg_flags, + int siocgstamp, int siocgstampns) +{ + char data[256]; + struct msghdr msg; + struct iovec entry; + struct sockaddr_in from_addr; + struct { + struct cmsghdr cm; + char control[512]; + } control; + int res; + + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = &entry; + msg.msg_iovlen = 1; + entry.iov_base = data; + entry.iov_len = sizeof(data); + msg.msg_name = (caddr_t)&from_addr; + msg.msg_namelen = sizeof(from_addr); + msg.msg_control = &control; + msg.msg_controllen = sizeof(control); + + res = recvmsg(sock, &msg, recvmsg_flags|MSG_DONTWAIT); + if (res < 0) { + printf("%s %s: %s\n", + "recvmsg", + (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular", + strerror(errno)); + } else { + printpacket(&msg, res, data, + sock, recvmsg_flags, + siocgstamp, siocgstampns); + } +} + +int main(int argc, char **argv) +{ + int so_timestamping_flags = 0; + int so_timestamp = 0; + int so_timestampns = 0; + int siocgstamp = 0; + int siocgstampns = 0; + int ip_multicast_loop = 0; + char *interface; + int i; + int enabled = 1; + int sock; + struct ifreq device; + struct ifreq hwtstamp; + struct hwtstamp_config hwconfig, hwconfig_requested; + struct sockaddr_in addr; + struct ip_mreq imr; + struct in_addr iaddr; + int val; + socklen_t len; + struct timeval next; + + if (argc < 2) + usage(0); + interface = argv[1]; + + for (i = 2; i < argc; i++) { + if (!strcasecmp(argv[i], "SO_TIMESTAMP")) + so_timestamp = 1; + else if (!strcasecmp(argv[i], "SO_TIMESTAMPNS")) + so_timestampns = 1; + else if (!strcasecmp(argv[i], "SIOCGSTAMP")) + siocgstamp = 1; + else if (!strcasecmp(argv[i], "SIOCGSTAMPNS")) + siocgstampns = 1; + else if (!strcasecmp(argv[i], "IP_MULTICAST_LOOP")) + ip_multicast_loop = 1; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_TX_SOFTWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_HARDWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_RX_HARDWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_SOFTWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_RX_SOFTWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SOFTWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_SOFTWARE; + else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RAW_HARDWARE")) + so_timestamping_flags |= SOF_TIMESTAMPING_RAW_HARDWARE; + else + usage(argv[i]); + } + + sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_UDP); + if (sock < 0) + bail("socket"); + + memset(&device, 0, sizeof(device)); + strncpy(device.ifr_name, interface, sizeof(device.ifr_name)); + if (ioctl(sock, SIOCGIFADDR, &device) < 0) + bail("getting interface IP address"); + + memset(&hwtstamp, 0, sizeof(hwtstamp)); + strncpy(hwtstamp.ifr_name, interface, sizeof(hwtstamp.ifr_name)); + hwtstamp.ifr_data = (void *)&hwconfig; + memset(&hwconfig, 0, sizeof(hwconfig)); + hwconfig.tx_type = + (so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ? + HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + hwconfig.rx_filter = + (so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ? + HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE; + hwconfig_requested = hwconfig; + if (ioctl(sock, SIOCSHWTSTAMP, &hwtstamp) < 0) { + if ((errno == EINVAL || errno == ENOTSUP) && + hwconfig_requested.tx_type == HWTSTAMP_TX_OFF && + hwconfig_requested.rx_filter == HWTSTAMP_FILTER_NONE) + printf("SIOCSHWTSTAMP: disabling hardware time stamping not possible\n"); + else + bail("SIOCSHWTSTAMP"); + } + printf("SIOCSHWTSTAMP: tx_type %d requested, got %d; rx_filter %d requested, got %d\n", + hwconfig_requested.tx_type, hwconfig.tx_type, + hwconfig_requested.rx_filter, hwconfig.rx_filter); + + /* bind to PTP port */ + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = htons(319 /* PTP event port */); + if (bind(sock, + (struct sockaddr *)&addr, + sizeof(struct sockaddr_in)) < 0) + bail("bind"); + + /* set multicast group for outgoing packets */ + inet_aton("224.0.1.130", &iaddr); /* alternate PTP domain 1 */ + addr.sin_addr = iaddr; + imr.imr_multiaddr.s_addr = iaddr.s_addr; + imr.imr_interface.s_addr = + ((struct sockaddr_in *)&device.ifr_addr)->sin_addr.s_addr; + if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_IF, + &imr.imr_interface.s_addr, sizeof(struct in_addr)) < 0) + bail("set multicast"); + + /* join multicast group, loop our own packet */ + if (setsockopt(sock, IPPROTO_IP, IP_ADD_MEMBERSHIP, + &imr, sizeof(struct ip_mreq)) < 0) + bail("join multicast group"); + + if (setsockopt(sock, IPPROTO_IP, IP_MULTICAST_LOOP, + &ip_multicast_loop, sizeof(enabled)) < 0) { + bail("loop multicast"); + } + + /* set socket options for time stamping */ + if (so_timestamp && + setsockopt(sock, SOL_SOCKET, SO_TIMESTAMP, + &enabled, sizeof(enabled)) < 0) + bail("setsockopt SO_TIMESTAMP"); + + if (so_timestampns && + setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS, + &enabled, sizeof(enabled)) < 0) + bail("setsockopt SO_TIMESTAMPNS"); + + if (so_timestamping_flags && + setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, + &so_timestamping_flags, + sizeof(so_timestamping_flags)) < 0) + bail("setsockopt SO_TIMESTAMPING"); + + /* request IP_PKTINFO for debugging purposes */ + if (setsockopt(sock, SOL_IP, IP_PKTINFO, + &enabled, sizeof(enabled)) < 0) + printf("%s: %s\n", "setsockopt IP_PKTINFO", strerror(errno)); + + /* verify socket options */ + len = sizeof(val); + if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMP, &val, &len) < 0) + printf("%s: %s\n", "getsockopt SO_TIMESTAMP", strerror(errno)); + else + printf("SO_TIMESTAMP %d\n", val); + + if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPNS, &val, &len) < 0) + printf("%s: %s\n", "getsockopt SO_TIMESTAMPNS", + strerror(errno)); + else + printf("SO_TIMESTAMPNS %d\n", val); + + if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &val, &len) < 0) { + printf("%s: %s\n", "getsockopt SO_TIMESTAMPING", + strerror(errno)); + } else { + printf("SO_TIMESTAMPING %d\n", val); + if (val != so_timestamping_flags) + printf(" not the expected value %d\n", + so_timestamping_flags); + } + + /* send packets forever every five seconds */ + gettimeofday(&next, 0); + next.tv_sec = (next.tv_sec + 1) / 5 * 5; + next.tv_usec = 0; + while (1) { + struct timeval now; + struct timeval delta; + long delta_us; + int res; + fd_set readfs, errorfs; + + gettimeofday(&now, 0); + delta_us = (long)(next.tv_sec - now.tv_sec) * 1000000 + + (long)(next.tv_usec - now.tv_usec); + if (delta_us > 0) { + /* continue waiting for timeout or data */ + delta.tv_sec = delta_us / 1000000; + delta.tv_usec = delta_us % 1000000; + + FD_ZERO(&readfs); + FD_ZERO(&errorfs); + FD_SET(sock, &readfs); + FD_SET(sock, &errorfs); + printf("%ld.%06ld: select %ldus\n", + (long)now.tv_sec, (long)now.tv_usec, + delta_us); + res = select(sock + 1, &readfs, 0, &errorfs, &delta); + gettimeofday(&now, 0); + printf("%ld.%06ld: select returned: %d, %s\n", + (long)now.tv_sec, (long)now.tv_usec, + res, + res < 0 ? strerror(errno) : "success"); + if (res > 0) { + if (FD_ISSET(sock, &readfs)) + printf("ready for reading\n"); + if (FD_ISSET(sock, &errorfs)) + printf("has error\n"); + recvpacket(sock, 0, + siocgstamp, + siocgstampns); + recvpacket(sock, MSG_ERRQUEUE, + siocgstamp, + siocgstampns); + } + } else { + /* write one packet */ + sendpacket(sock, + (struct sockaddr *)&addr, + sizeof(addr)); + next.tv_sec += 5; + continue; + } + } + + return 0; +} --- /dev/null +++ b/tools/testing/selftests/networking/timestamping/txtimestamp.c @@ -0,0 +1,549 @@ +/* + * Copyright 2014 Google Inc. + * Author: willemb@google.com (Willem de Bruijn) + * + * Test software tx timestamping, including + * + * - SCHED, SND and ACK timestamps + * - RAW, UDP and TCP + * - IPv4 and IPv6 + * - various packet sizes (to test GSO and TSO) + * + * Consult the command line arguments for help on running + * the various testcases. + * + * This test requires a dummy TCP server. + * A simple `nc6 [-u] -l -p $DESTPORT` will do + * + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <asm/types.h> +#include <error.h> +#include <errno.h> +#include <inttypes.h> +#include <linux/errqueue.h> +#include <linux/if_ether.h> +#include <linux/net_tstamp.h> +#include <netdb.h> +#include <net/if.h> +#include <netinet/in.h> +#include <netinet/ip.h> +#include <netinet/udp.h> +#include <netinet/tcp.h> +#include <netpacket/packet.h> +#include <poll.h> +#include <stdarg.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/select.h> +#include <sys/socket.h> +#include <sys/time.h> +#include <sys/types.h> +#include <time.h> +#include <unistd.h> + +/* command line parameters */ +static int cfg_proto = SOCK_STREAM; +static int cfg_ipproto = IPPROTO_TCP; +static int cfg_num_pkts = 4; +static int do_ipv4 = 1; +static int do_ipv6 = 1; +static int cfg_payload_len = 10; +static bool cfg_show_payload; +static bool cfg_do_pktinfo; +static bool cfg_loop_nodata; +static uint16_t dest_port = 9000; + +static struct sockaddr_in daddr; +static struct sockaddr_in6 daddr6; +static struct timespec ts_prev; + +static void __print_timestamp(const char *name, struct timespec *cur, + uint32_t key, int payload_len) +{ + if (!(cur->tv_sec | cur->tv_nsec)) + return; + + fprintf(stderr, " %s: %lu s %lu us (seq=%u, len=%u)", + name, cur->tv_sec, cur->tv_nsec / 1000, + key, payload_len); + + if ((ts_prev.tv_sec | ts_prev.tv_nsec)) { + int64_t cur_ms, prev_ms; + + cur_ms = (long) cur->tv_sec * 1000 * 1000; + cur_ms += cur->tv_nsec / 1000; + + prev_ms = (long) ts_prev.tv_sec * 1000 * 1000; + prev_ms += ts_prev.tv_nsec / 1000; + + fprintf(stderr, " (%+" PRId64 " us)", cur_ms - prev_ms); + } + + ts_prev = *cur; + fprintf(stderr, "\n"); +} + +static void print_timestamp_usr(void) +{ + struct timespec ts; + struct timeval tv; /* avoid dependency on -lrt */ + + gettimeofday(&tv, NULL); + ts.tv_sec = tv.tv_sec; + ts.tv_nsec = tv.tv_usec * 1000; + + __print_timestamp(" USR", &ts, 0, 0); +} + +static void print_timestamp(struct scm_timestamping *tss, int tstype, + int tskey, int payload_len) +{ + const char *tsname; + + switch (tstype) { + case SCM_TSTAMP_SCHED: + tsname = " ENQ"; + break; + case SCM_TSTAMP_SND: + tsname = " SND"; + break; + case SCM_TSTAMP_ACK: + tsname = " ACK"; + break; + default: + error(1, 0, "unknown timestamp type: %u", + tstype); + } + __print_timestamp(tsname, &tss->ts[0], tskey, payload_len); +} + +/* TODO: convert to check_and_print payload once API is stable */ +static void print_payload(char *data, int len) +{ + int i; + + if (!len) + return; + + if (len > 70) + len = 70; + + fprintf(stderr, "payload: "); + for (i = 0; i < len; i++) + fprintf(stderr, "%02hhx ", data[i]); + fprintf(stderr, "\n"); +} + +static void print_pktinfo(int family, int ifindex, void *saddr, void *daddr) +{ + char sa[INET6_ADDRSTRLEN], da[INET6_ADDRSTRLEN]; + + fprintf(stderr, " pktinfo: ifindex=%u src=%s dst=%s\n", + ifindex, + saddr ? inet_ntop(family, saddr, sa, sizeof(sa)) : "unknown", + daddr ? inet_ntop(family, daddr, da, sizeof(da)) : "unknown"); +} + +static void __poll(int fd) +{ + struct pollfd pollfd; + int ret; + + memset(&pollfd, 0, sizeof(pollfd)); + pollfd.fd = fd; + ret = poll(&pollfd, 1, 100); + if (ret != 1) + error(1, errno, "poll"); +} + +static void __recv_errmsg_cmsg(struct msghdr *msg, int payload_len) +{ + struct sock_extended_err *serr = NULL; + struct scm_timestamping *tss = NULL; + struct cmsghdr *cm; + int batch = 0; + + for (cm = CMSG_FIRSTHDR(msg); + cm && cm->cmsg_len; + cm = CMSG_NXTHDR(msg, cm)) { + if (cm->cmsg_level == SOL_SOCKET && + cm->cmsg_type == SCM_TIMESTAMPING) { + tss = (void *) CMSG_DATA(cm); + } else if ((cm->cmsg_level == SOL_IP && + cm->cmsg_type == IP_RECVERR) || + (cm->cmsg_level == SOL_IPV6 && + cm->cmsg_type == IPV6_RECVERR)) { + serr = (void *) CMSG_DATA(cm); + if (serr->ee_errno != ENOMSG || + serr->ee_origin != SO_EE_ORIGIN_TIMESTAMPING) { + fprintf(stderr, "unknown ip error %d %d\n", + serr->ee_errno, + serr->ee_origin); + serr = NULL; + } + } else if (cm->cmsg_level == SOL_IP && + cm->cmsg_type == IP_PKTINFO) { + struct in_pktinfo *info = (void *) CMSG_DATA(cm); + print_pktinfo(AF_INET, info->ipi_ifindex, + &info->ipi_spec_dst, &info->ipi_addr); + } else if (cm->cmsg_level == SOL_IPV6 && + cm->cmsg_type == IPV6_PKTINFO) { + struct in6_pktinfo *info6 = (void *) CMSG_DATA(cm); + print_pktinfo(AF_INET6, info6->ipi6_ifindex, + NULL, &info6->ipi6_addr); + } else + fprintf(stderr, "unknown cmsg %d,%d\n", + cm->cmsg_level, cm->cmsg_type); + + if (serr && tss) { + print_timestamp(tss, serr->ee_info, serr->ee_data, + payload_len); + serr = NULL; + tss = NULL; + batch++; + } + } + + if (batch > 1) + fprintf(stderr, "batched %d timestamps\n", batch); +} + +static int recv_errmsg(int fd) +{ + static char ctrl[1024 /* overprovision*/]; + static struct msghdr msg; + struct iovec entry; + static char *data; + int ret = 0; + + data = malloc(cfg_payload_len); + if (!data) + error(1, 0, "malloc"); + + memset(&msg, 0, sizeof(msg)); + memset(&entry, 0, sizeof(entry)); + memset(ctrl, 0, sizeof(ctrl)); + + entry.iov_base = data; + entry.iov_len = cfg_payload_len; + msg.msg_iov = &entry; + msg.msg_iovlen = 1; + msg.msg_name = NULL; + msg.msg_namelen = 0; + msg.msg_control = ctrl; + msg.msg_controllen = sizeof(ctrl); + + ret = recvmsg(fd, &msg, MSG_ERRQUEUE); + if (ret == -1 && errno != EAGAIN) + error(1, errno, "recvmsg"); + + if (ret >= 0) { + __recv_errmsg_cmsg(&msg, ret); + if (cfg_show_payload) + print_payload(data, cfg_payload_len); + } + + free(data); + return ret == -1; +} + +static void do_test(int family, unsigned int opt) +{ + char *buf; + int fd, i, val = 1, total_len; + + if (family == AF_INET6 && cfg_proto != SOCK_STREAM) { + /* due to lack of checksum generation code */ + fprintf(stderr, "test: skipping datagram over IPv6\n"); + return; + } + + total_len = cfg_payload_len; + if (cfg_proto == SOCK_RAW) { + total_len += sizeof(struct udphdr); + if (cfg_ipproto == IPPROTO_RAW) + total_len += sizeof(struct iphdr); + } + + buf = malloc(total_len); + if (!buf) + error(1, 0, "malloc"); + + fd = socket(family, cfg_proto, cfg_ipproto); + if (fd < 0) + error(1, errno, "socket"); + + if (cfg_proto == SOCK_STREAM) { + if (setsockopt(fd, IPPROTO_TCP, TCP_NODELAY, + (char*) &val, sizeof(val))) + error(1, 0, "setsockopt no nagle"); + + if (family == PF_INET) { + if (connect(fd, (void *) &daddr, sizeof(daddr))) + error(1, errno, "connect ipv4"); + } else { + if (connect(fd, (void *) &daddr6, sizeof(daddr6))) + error(1, errno, "connect ipv6"); + } + } + + if (cfg_do_pktinfo) { + if (family == AF_INET6) { + if (setsockopt(fd, SOL_IPV6, IPV6_RECVPKTINFO, + &val, sizeof(val))) + error(1, errno, "setsockopt pktinfo ipv6"); + } else { + if (setsockopt(fd, SOL_IP, IP_PKTINFO, + &val, sizeof(val))) + error(1, errno, "setsockopt pktinfo ipv4"); + } + } + + opt |= SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_CMSG | + SOF_TIMESTAMPING_OPT_ID; + if (cfg_loop_nodata) + opt |= SOF_TIMESTAMPING_OPT_TSONLY; + + if (setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, + (char *) &opt, sizeof(opt))) + error(1, 0, "setsockopt timestamping"); + + for (i = 0; i < cfg_num_pkts; i++) { + memset(&ts_prev, 0, sizeof(ts_prev)); + memset(buf, 'a' + i, total_len); + + if (cfg_proto == SOCK_RAW) { + struct udphdr *udph; + int off = 0; + + if (cfg_ipproto == IPPROTO_RAW) { + struct iphdr *iph = (void *) buf; + + memset(iph, 0, sizeof(*iph)); + iph->ihl = 5; + iph->version = 4; + iph->ttl = 2; + iph->daddr = daddr.sin_addr.s_addr; + iph->protocol = IPPROTO_UDP; + /* kernel writes saddr, csum, len */ + + off = sizeof(*iph); + } + + udph = (void *) buf + off; + udph->source = ntohs(9000); /* random spoof */ + udph->dest = ntohs(dest_port); + udph->len = ntohs(sizeof(*udph) + cfg_payload_len); + udph->check = 0; /* not allowed for IPv6 */ + } + + print_timestamp_usr(); + if (cfg_proto != SOCK_STREAM) { + if (family == PF_INET) + val = sendto(fd, buf, total_len, 0, (void *) &daddr, sizeof(daddr)); + else + val = sendto(fd, buf, total_len, 0, (void *) &daddr6, sizeof(daddr6)); + } else { + val = send(fd, buf, cfg_payload_len, 0); + } + if (val != total_len) + error(1, errno, "send"); + + /* wait for all errors to be queued, else ACKs arrive OOO */ + usleep(50 * 1000); + + __poll(fd); + + while (!recv_errmsg(fd)) {} + } + + if (close(fd)) + error(1, errno, "close"); + + free(buf); + usleep(400 * 1000); +} + +static void __attribute__((noreturn)) usage(const char *filepath) +{ + fprintf(stderr, "\nUsage: %s [options] hostname\n" + "\nwhere options are:\n" + " -4: only IPv4\n" + " -6: only IPv6\n" + " -h: show this message\n" + " -I: request PKTINFO\n" + " -l N: send N bytes at a time\n" + " -n: set no-payload option\n" + " -r: use raw\n" + " -R: use raw (IP_HDRINCL)\n" + " -p N: connect to port N\n" + " -u: use udp\n" + " -x: show payload (up to 70 bytes)\n", + filepath); + exit(1); +} + +static void parse_opt(int argc, char **argv) +{ + int proto_count = 0; + char c; + + while ((c = getopt(argc, argv, "46hIl:np:rRux")) != -1) { + switch (c) { + case '4': + do_ipv6 = 0; + break; + case '6': + do_ipv4 = 0; + break; + case 'I': + cfg_do_pktinfo = true; + break; + case 'n': + cfg_loop_nodata = true; + break; + case 'r': + proto_count++; + cfg_proto = SOCK_RAW; + cfg_ipproto = IPPROTO_UDP; + break; + case 'R': + proto_count++; + cfg_proto = SOCK_RAW; + cfg_ipproto = IPPROTO_RAW; + break; + case 'u': + proto_count++; + cfg_proto = SOCK_DGRAM; + cfg_ipproto = IPPROTO_UDP; + break; + case 'l': + cfg_payload_len = strtoul(optarg, NULL, 10); + break; + case 'p': + dest_port = strtoul(optarg, NULL, 10); + break; + case 'x': + cfg_show_payload = true; + break; + case 'h': + default: + usage(argv[0]); + } + } + + if (!cfg_payload_len) + error(1, 0, "payload may not be nonzero"); + if (cfg_proto != SOCK_STREAM && cfg_payload_len > 1472) + error(1, 0, "udp packet might exceed expected MTU"); + if (!do_ipv4 && !do_ipv6) + error(1, 0, "pass -4 or -6, not both"); + if (proto_count > 1) + error(1, 0, "pass -r, -R or -u, not multiple"); + + if (optind != argc - 1) + error(1, 0, "missing required hostname argument"); +} + +static void resolve_hostname(const char *hostname) +{ + struct addrinfo *addrs, *cur; + int have_ipv4 = 0, have_ipv6 = 0; + + if (getaddrinfo(hostname, NULL, NULL, &addrs)) + error(1, errno, "getaddrinfo"); + + cur = addrs; + while (cur && !have_ipv4 && !have_ipv6) { + if (!have_ipv4 && cur->ai_family == AF_INET) { + memcpy(&daddr, cur->ai_addr, sizeof(daddr)); + daddr.sin_port = htons(dest_port); + have_ipv4 = 1; + } + else if (!have_ipv6 && cur->ai_family == AF_INET6) { + memcpy(&daddr6, cur->ai_addr, sizeof(daddr6)); + daddr6.sin6_port = htons(dest_port); + have_ipv6 = 1; + } + cur = cur->ai_next; + } + if (addrs) + freeaddrinfo(addrs); + + do_ipv4 &= have_ipv4; + do_ipv6 &= have_ipv6; +} + +static void do_main(int family) +{ + fprintf(stderr, "family: %s\n", + family == PF_INET ? "INET" : "INET6"); + + fprintf(stderr, "test SND\n"); + do_test(family, SOF_TIMESTAMPING_TX_SOFTWARE); + + fprintf(stderr, "test ENQ\n"); + do_test(family, SOF_TIMESTAMPING_TX_SCHED); + + fprintf(stderr, "test ENQ + SND\n"); + do_test(family, SOF_TIMESTAMPING_TX_SCHED | + SOF_TIMESTAMPING_TX_SOFTWARE); + + if (cfg_proto == SOCK_STREAM) { + fprintf(stderr, "\ntest ACK\n"); + do_test(family, SOF_TIMESTAMPING_TX_ACK); + + fprintf(stderr, "\ntest SND + ACK\n"); + do_test(family, SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_ACK); + + fprintf(stderr, "\ntest ENQ + SND + ACK\n"); + do_test(family, SOF_TIMESTAMPING_TX_SCHED | + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_ACK); + } +} + +const char *sock_names[] = { NULL, "TCP", "UDP", "RAW" }; + +int main(int argc, char **argv) +{ + if (argc == 1) + usage(argv[0]); + + parse_opt(argc, argv); + resolve_hostname(argv[argc - 1]); + + fprintf(stderr, "protocol: %s\n", sock_names[cfg_proto]); + fprintf(stderr, "payload: %u\n", cfg_payload_len); + fprintf(stderr, "server port: %u\n", dest_port); + fprintf(stderr, "\n"); + + if (do_ipv4) + do_main(PF_INET); + if (do_ipv6) + do_main(PF_INET6); + + return 0; +}