For tests that are using the maximal number of BPF instruction, each
run takes 20 usec. Looping 10,000 times on them totals 200 ms, which
is bad when the loop is not preemptible.

test_bpf: #264 BPF_MAXINSNS: Call heavy transformations jited:1 19248
18548 PASS
test_bpf: #269 BPF_MAXINSNS: ld_abs+get_processor_id jited:1 20896 PASS

Lets divide by ten the number of iterations, so that max latency is
20ms. We could use need_resched() to break the loop earlier if we
believe 20 ms is too much.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

While working on 16338a9b ("bpf, arm64: fix out of bounds access in
tail call") I noticed that ppc64 JIT is partially affected as well. While
the bound checking is correctly performed as unsigned comparison, the
register with the index value however, is never truncated into 32 bit
space, so e.g. a index value of 0x100000000ULL with a map of 1 element
would pass with PPC_CMPLW() whereas we later on continue with the full
64 bit register value. Therefore, as we do in interpreter and other JITs
truncate the value to 32 bit initially in order to fix access.

Fixes: ce076141 ("powerpc/bpf: Implement support for tail calls")
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Reviewed-by: NNaveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Tested-by: NNaveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>

test_bpf() is taking 1.6 seconds nowadays, it is time
to add a schedule point in it.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

The requirements around atomic_add() / atomic64_add() resp. their
JIT implementations differ across architectures. E.g. while x86_64
seems just fine with BPF's xadd on unaligned memory, on arm64 it
triggers via interpreter but also JIT the following crash:

  [  830.864985] Unable to handle kernel paging request at virtual address ffff8097d7ed6703
  [...]
  [  830.916161] Internal error: Oops: 96000021 [#1] SMP
  [  830.984755] CPU: 37 PID: 2788 Comm: test_verifier Not tainted 4.16.0-rc2+ #8
  [  830.991790] Hardware name: Huawei TaiShan 2280 /BC11SPCD, BIOS 1.29 07/17/2017
  [  830.998998] pstate: 80400005 (Nzcv daif +PAN -UAO)
  [  831.003793] pc : __ll_sc_atomic_add+0x4/0x18
  [  831.008055] lr : ___bpf_prog_run+0x1198/0x1588
  [  831.012485] sp : ffff00001ccabc20
  [  831.015786] x29: ffff00001ccabc20 x28: ffff8017d56a0f00
  [  831.021087] x27: 0000000000000001 x26: 0000000000000000
  [  831.026387] x25: 000000c168d9db98 x24: 0000000000000000
  [  831.031686] x23: ffff000008203878 x22: ffff000009488000
  [  831.036986] x21: ffff000008b14e28 x20: ffff00001ccabcb0
  [  831.042286] x19: ffff0000097b5080 x18: 0000000000000a03
  [  831.047585] x17: 0000000000000000 x16: 0000000000000000
  [  831.052885] x15: 0000ffffaeca8000 x14: 0000000000000000
  [  831.058184] x13: 0000000000000000 x12: 0000000000000000
  [  831.063484] x11: 0000000000000001 x10: 0000000000000000
  [  831.068783] x9 : 0000000000000000 x8 : 0000000000000000
  [  831.074083] x7 : 0000000000000000 x6 : 000580d428000000
  [  831.079383] x5 : 0000000000000018 x4 : 0000000000000000
  [  831.084682] x3 : ffff00001ccabcb0 x2 : 0000000000000001
  [  831.089982] x1 : ffff8097d7ed6703 x0 : 0000000000000001
  [  831.095282] Process test_verifier (pid: 2788, stack limit = 0x0000000018370044)
  [  831.102577] Call trace:
  [  831.105012]  __ll_sc_atomic_add+0x4/0x18
  [  831.108923]  __bpf_prog_run32+0x4c/0x70
  [  831.112748]  bpf_test_run+0x78/0xf8
  [  831.116224]  bpf_prog_test_run_xdp+0xb4/0x120
  [  831.120567]  SyS_bpf+0x77c/0x1110
  [  831.123873]  el0_svc_naked+0x30/0x34
  [  831.127437] Code: 97fffe97 17ffffec 00000000 f9800031 (885f7c31)

Reason for this is because memory is required to be aligned. In
case of BPF, we always enforce alignment in terms of stack access,
but not when accessing map values or packet data when the underlying
arch (e.g. arm64) has CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS set.

xadd on packet data that is local to us anyway is just wrong, so
forbid this case entirely. The only place where xadd makes sense in
fact are map values; xadd on stack is wrong as well, but it's been
around for much longer. Specifically enforce strict alignment in case
of xadd, so that we handle this case generically and avoid such crashes
in the first place.

Fixes: 17a52670 ("bpf: verifier (add verifier core)")
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>

pfifo_fast got percpu stats lately, uncovering a bug I introduced last
year in linux-4.10.

I missed the fact that we have to clear our temporary storage
before calling __gnet_stats_copy_basic() in the case of percpu stats.

Without this fix, rate estimators (tc qd replace dev xxx root est 1sec
4sec pfifo_fast) are utterly broken.

Fixes: 1c0d32fd ("net_sched: gen_estimator: complete rewrite of rate estimators")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Alexei Starovoitov says:

====================
pull-request: bpf 2018-02-22

The following pull-request contains BPF updates for your *net* tree.

The main changes are:

1) two urgent fixes for bpf_tail_call logic for x64 and arm64 JITs, from Daniel.

2) cond_resched points in percpu array alloc/free paths, from Eric.

3) lockdep and other minor fixes, from Yonghong, Arnd, Anders, Li.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Previously, buffer descriptors containing only the frame check sequence
(FCS) were skipped and not added to the skb. However, the page reference
count was still incremented, leading to a memory leak.

Fixing this inside gfar_add_rx_frag() is difficult due to reserved
memory handling and page reuse. Instead, move the FCS handling to
gfar_process_frame() and trim off the FCS before passing the skb up the
networking stack.
Signed-off-by: NAndy Spencer <aspencer@spacex.com>
Signed-off-by: NJim Gruen <jgruen@spacex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

gcc-8 has a new warning that detects overlapping input and output arguments
in memcpy(). It triggers for sit_init_net() calling ipip6_tunnel_clone_6rd(),
which is actually correct:

net/ipv6/sit.c: In function 'sit_init_net':
net/ipv6/sit.c:192:3: error: 'memcpy' source argument is the same as destination [-Werror=restrict]

The problem here is that the logic detecting the memcpy() arguments finds them
to be the same, but the conditional that tests for the input and output of
ipip6_tunnel_clone_6rd() to be identical is not a compile-time constant.

We know that netdev_priv(t->dev) is the same as t for a tunnel device,
and comparing "dev" directly here lets the compiler figure out as well
that 'dev == sitn->fb_tunnel_dev' when called from sit_init_net(), so
it no longer warns.

This code is old, so Cc stable to make sure that we don't get the warning
for older kernels built with new gcc.

Cc: Martin Sebor <msebor@gmail.com>
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83456Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The following use-after-free was reported by KASan when running
LTP macvtap01 test on 4.16-rc2:

[10642.528443] BUG: KASAN: use-after-free in
               macvlan_common_newlink+0x12ef/0x14a0 [macvlan]
[10642.626607] Read of size 8 at addr ffff880ba49f2100 by task ip/18450
...
[10642.963873] Call Trace:
[10642.994352]  dump_stack+0x5c/0x7c
[10643.035325]  print_address_description+0x75/0x290
[10643.092938]  kasan_report+0x28d/0x390
[10643.137971]  ? macvlan_common_newlink+0x12ef/0x14a0 [macvlan]
[10643.207963]  macvlan_common_newlink+0x12ef/0x14a0 [macvlan]
[10643.275978]  macvtap_newlink+0x171/0x260 [macvtap]
[10643.334532]  rtnl_newlink+0xd4f/0x1300
...
[10646.256176] Allocated by task 18450:
[10646.299964]  kasan_kmalloc+0xa6/0xd0
[10646.343746]  kmem_cache_alloc_trace+0xf1/0x210
[10646.397826]  macvlan_common_newlink+0x6de/0x14a0 [macvlan]
[10646.464386]  macvtap_newlink+0x171/0x260 [macvtap]
[10646.522728]  rtnl_newlink+0xd4f/0x1300
...
[10647.022028] Freed by task 18450:
[10647.061549]  __kasan_slab_free+0x138/0x180
[10647.111468]  kfree+0x9e/0x1c0
[10647.147869]  macvlan_port_destroy+0x3db/0x650 [macvlan]
[10647.211411]  rollback_registered_many+0x5b9/0xb10
[10647.268715]  rollback_registered+0xd9/0x190
[10647.319675]  register_netdevice+0x8eb/0xc70
[10647.370635]  macvlan_common_newlink+0xe58/0x14a0 [macvlan]
[10647.437195]  macvtap_newlink+0x171/0x260 [macvtap]

Commit d02fd6e7 ("macvlan: Fix one possible double free") handles
the case when register_netdevice() invokes ndo_uninit() on error and
as a result free the port. But 'macvlan_port_get_rtnl(dev))' check
(returns dev->rx_handler_data), which was added by this commit in order
to prevent double free, is not quite correct:

* for macvlan it always returns NULL because 'lowerdev' is the one that
  was used to register rx handler (port) in macvlan_port_create() as
  well as to unregister it in macvlan_port_destroy().
* for macvtap it always returns a valid pointer because macvtap registers
  its own rx handler before macvlan_common_newlink().

Fixes: d02fd6e7 ("macvlan: Fix one possible double free")
Signed-off-by: NAlexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I recently noticed a crash on arm64 when feeding a bogus index
into BPF tail call helper. The crash would not occur when the
interpreter is used, but only in case of JIT. Output looks as
follows:

  [  347.007486] Unable to handle kernel paging request at virtual address fffb850e96492510
  [...]
  [  347.043065] [fffb850e96492510] address between user and kernel address ranges
  [  347.050205] Internal error: Oops: 96000004 [#1] SMP
  [...]
  [  347.190829] x13: 0000000000000000 x12: 0000000000000000
  [  347.196128] x11: fffc047ebe782800 x10: ffff808fd7d0fd10
  [  347.201427] x9 : 0000000000000000 x8 : 0000000000000000
  [  347.206726] x7 : 0000000000000000 x6 : 001c991738000000
  [  347.212025] x5 : 0000000000000018 x4 : 000000000000ba5a
  [  347.217325] x3 : 00000000000329c4 x2 : ffff808fd7cf0500
  [  347.222625] x1 : ffff808fd7d0fc00 x0 : ffff808fd7cf0500
  [  347.227926] Process test_verifier (pid: 4548, stack limit = 0x000000007467fa61)
  [  347.235221] Call trace:
  [  347.237656]  0xffff000002f3a4fc
  [  347.240784]  bpf_test_run+0x78/0xf8
  [  347.244260]  bpf_prog_test_run_skb+0x148/0x230
  [  347.248694]  SyS_bpf+0x77c/0x1110
  [  347.251999]  el0_svc_naked+0x30/0x34
  [  347.255564] Code: 9100075a d280220a 8b0a002a d37df04b (f86b694b)
  [...]

In this case the index used in BPF r3 is the same as in r1
at the time of the call, meaning we fed a pointer as index;
here, it had the value 0xffff808fd7cf0500 which sits in x2.

While I found tail calls to be working in general (also for
hitting the error cases), I noticed the following in the code
emission:

  # bpftool p d j i 988
  [...]
  38:   ldr     w10, [x1,x10]
  3c:   cmp     w2, w10
  40:   b.ge    0x000000000000007c              <-- signed cmp
  44:   mov     x10, #0x20                      // #32
  48:   cmp     x26, x10
  4c:   b.gt    0x000000000000007c
  50:   add     x26, x26, #0x1
  54:   mov     x10, #0x110                     // #272
  58:   add     x10, x1, x10
  5c:   lsl     x11, x2, #3
  60:   ldr     x11, [x10,x11]                  <-- faulting insn (f86b694b)
  64:   cbz     x11, 0x000000000000007c
  [...]

Meaning, the tests passed because commit ddb55992 ("arm64:
bpf: implement bpf_tail_call() helper") was using signed compares
instead of unsigned which as a result had the test wrongly passing.

Change this but also the tail call count test both into unsigned
and cap the index as u32. Latter we did as well in 90caccdd
("bpf: fix bpf_tail_call() x64 JIT") and is needed in addition here,
too. Tested on HiSilicon Hi1616.

Result after patch:

  # bpftool p d j i 268
  [...]
  38:	ldr	w10, [x1,x10]
  3c:	add	w2, w2, #0x0
  40:	cmp	w2, w10
  44:	b.cs	0x0000000000000080
  48:	mov	x10, #0x20                  	// #32
  4c:	cmp	x26, x10
  50:	b.hi	0x0000000000000080
  54:	add	x26, x26, #0x1
  58:	mov	x10, #0x110                 	// #272
  5c:	add	x10, x1, x10
  60:	lsl	x11, x2, #3
  64:	ldr	x11, [x10,x11]
  68:	cbz	x11, 0x0000000000000080
  [...]

Fixes: ddb55992 ("arm64: bpf: implement bpf_tail_call() helper")
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>

Implement a retpoline [0] for the BPF tail call JIT'ing that converts
the indirect jump via jmp %rax that is used to make the long jump into
another JITed BPF image. Since this is subject to speculative execution,
we need to control the transient instruction sequence here as well
when CONFIG_RETPOLINE is set, and direct it into a pause + lfence loop.
The latter aligns also with what gcc / clang emits (e.g. [1]).

JIT dump after patch:

  # bpftool p d x i 1
   0: (18) r2 = map[id:1]
   2: (b7) r3 = 0
   3: (85) call bpf_tail_call#12
   4: (b7) r0 = 2
   5: (95) exit

With CONFIG_RETPOLINE:

  # bpftool p d j i 1
  [...]
  33:	cmp    %edx,0x24(%rsi)
  36:	jbe    0x0000000000000072  |*
  38:	mov    0x24(%rbp),%eax
  3e:	cmp    $0x20,%eax
  41:	ja     0x0000000000000072  |
  43:	add    $0x1,%eax
  46:	mov    %eax,0x24(%rbp)
  4c:	mov    0x90(%rsi,%rdx,8),%rax
  54:	test   %rax,%rax
  57:	je     0x0000000000000072  |
  59:	mov    0x28(%rax),%rax
  5d:	add    $0x25,%rax
  61:	callq  0x000000000000006d  |+
  66:	pause                      |
  68:	lfence                     |
  6b:	jmp    0x0000000000000066  |
  6d:	mov    %rax,(%rsp)         |
  71:	retq                       |
  72:	mov    $0x2,%eax
  [...]

  * relative fall-through jumps in error case
  + retpoline for indirect jump

Without CONFIG_RETPOLINE:

  # bpftool p d j i 1
  [...]
  33:	cmp    %edx,0x24(%rsi)
  36:	jbe    0x0000000000000063  |*
  38:	mov    0x24(%rbp),%eax
  3e:	cmp    $0x20,%eax
  41:	ja     0x0000000000000063  |
  43:	add    $0x1,%eax
  46:	mov    %eax,0x24(%rbp)
  4c:	mov    0x90(%rsi,%rdx,8),%rax
  54:	test   %rax,%rax
  57:	je     0x0000000000000063  |
  59:	mov    0x28(%rax),%rax
  5d:	add    $0x25,%rax
  61:	jmpq   *%rax               |-
  63:	mov    $0x2,%eax
  [...]

  * relative fall-through jumps in error case
  - plain indirect jump as before

  [0] https://support.google.com/faqs/answer/7625886
  [1] https://github.com/gcc-mirror/gcc/commit/a31e654fa107be968b802786d747e962c2fcdb2bSigned-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>

All the kernel_sendmsg() calls in rxrpc_send_data_packet() need to send
both parts of the iov[] buffer, but one of them does not.  Fix it so that
it does.

Without this, short IPv6 rxrpc DATA packets may be seen that have the rxrpc
header included, but no payload.

Fixes: 5a924b89 ("rxrpc: Don't store the rxrpc header in the Tx queue sk_buffs")
Reported-by: NMarc Dionne <marc.dionne@auristor.com>
Signed-off-by: NDavid Howells <dhowells@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We should check "self->aq_hw" for allocation failure, and also we should
free it on the error paths.

Fixes: 23ee07ad ("net: aquantia: Cleanup pci functions module")
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 9a3efb6b ("bpf: fix memory leak in lpm_trie map_free callback function")
fixed a memory leak and removed unnecessary locks in map_free callback function.
Unfortrunately, it introduced a lockdep warning. When lockdep checking is turned on,
running tools/testing/selftests/bpf/test_lpm_map will have:

  [   98.294321] =============================
  [   98.294807] WARNING: suspicious RCU usage
  [   98.295359] 4.16.0-rc2+ #193 Not tainted
  [   98.295907] -----------------------------
  [   98.296486] /home/yhs/work/bpf/kernel/bpf/lpm_trie.c:572 suspicious rcu_dereference_check() usage!
  [   98.297657]
  [   98.297657] other info that might help us debug this:
  [   98.297657]
  [   98.298663]
  [   98.298663] rcu_scheduler_active = 2, debug_locks = 1
  [   98.299536] 2 locks held by kworker/2:1/54:
  [   98.300152]  #0:  ((wq_completion)"events"){+.+.}, at: [<00000000196bc1f0>] process_one_work+0x157/0x5c0
  [   98.301381]  #1:  ((work_completion)(&map->work)){+.+.}, at: [<00000000196bc1f0>] process_one_work+0x157/0x5c0

Since actual trie tree removal happens only after no other
accesses to the tree are possible, replacing
  rcu_dereference_protected(*slot, lockdep_is_held(&trie->lock))
with
  rcu_dereference_protected(*slot, 1)
fixed the issue.

Fixes: 9a3efb6b ("bpf: fix memory leak in lpm_trie map_free callback function")
Reported-by: NEric Dumazet <edumazet@google.com>
Suggested-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NYonghong Song <yhs@fb.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

syszbot managed to trigger RCU detected stalls in
bpf_array_free_percpu()

It takes time to allocate a huge percpu map, but even more time to free
it.

Since we run in process context, use cond_resched() to yield cpu if
needed.

Fixes: a10423b8 ("bpf: introduce BPF_MAP_TYPE_PERCPU_ARRAY map")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: Nsyzbot <syzkaller@googlegroups.com>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

Merge tag 'mac80211-for-davem-2018-02-22' of git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211

Johannes Berg says:

====================
Various fixes across the tree, the shortlog basically says it all:

  cfg80211: fix cfg80211_beacon_dup
  -> old bug in this code

  cfg80211: clear wep keys after disconnection
  -> certain ways of disconnecting left the keys

  mac80211: round IEEE80211_TX_STATUS_HEADROOM up to multiple of 4
  -> alignment issues with using 14 bytes

  mac80211: Do not disconnect on invalid operating class
  -> if the AP has a bogus operating class, let it be

  mac80211: Fix sending ADDBA response for an ongoing session
  -> don't send the same frame twice

  cfg80211: use only 1Mbps for basic rates in mesh
  -> interop issue with old versions of our code

  mac80211_hwsim: don't use WQ_MEM_RECLAIM
  -> it causes splats because it flushes work on a non-reclaim WQ

  regulatory: add NUL to request alpha2
  -> nla_put_string() issue from Kees

  mac80211: mesh: fix wrong mesh TTL offset calculation
  -> protocol issue

  mac80211: fix a possible leak of station stats
  -> error path might leak memory

  mac80211: fix calling sleeping function in atomic context
  -> percpu allocations need to be made with gfp flags
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Similar to the ancient commit a5fe8e76 ("regulatory: add NUL
to alpha2"), add another byte to alpha2 in the request struct so
that when we use nla_put_string(), we don't overrun anything.

Fixes: 73d54c9e ("cfg80211: add regulatory netlink multicast group")
Reported-by: NKees Cook <keescook@google.com>
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>

The login buffer is released before the driver can perform
sanity checks between resources the driver requested and what
firmware will provide. Don't release the login buffer until
the sanity check is performed.

Fixes: 34f0f4e3 ("ibmvnic: Fix login buffer memory leaks")
Signed-off-by: NThomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

AFAIK the only version of smc9194.c with Mac support is the one in the
linux-mac68k CVS repo, which never made it to the mainline.

Despite that, from v2.3.45, arch/m68k/config.in listed CONFIG_SMC9194
under CONFIG_MAC. This mistake got carried over into Kconfig in v2.5.55.
(See pre-git era "[PATCH] add m68k dependencies to net driver config".)
Signed-off-by: NFinn Thain <fthain@telegraphics.com.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The result of the skb flow dissect is copied from keys to hash_keys to
ensure only the intended data is hashed. The original L4 hash patch
overlooked setting the addr_type for this case; add it.

Fixes: bf4e0a3d ("net: ipv4: add support for ECMP hash policy choice")
Reported-by: NIdo Schimmel <idosch@idosch.org>
Signed-off-by: NDavid Ahern <dsahern@gmail.com>
Acked-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

BBR uses tcp_tso_autosize() in an attempt to probe what would be the
burst sizes and to adjust cwnd in bbr_target_cwnd() with following
gold formula :

/* Allow enough full-sized skbs in flight to utilize end systems. */
cwnd += 3 * bbr->tso_segs_goal;

But GSO can be lacking or be constrained to very small
units (ip link set dev ... gso_max_segs 2)

What we really want is to have enough packets in flight so that both
GSO and GRO are efficient.

So in the case GSO is off or downgraded, we still want to have the same
number of packets in flight as if GSO/TSO was fully operational, so
that GRO can hopefully be working efficiently.

To fix this issue, we make tcp_tso_autosize() unaware of
sk->sk_gso_max_segs

Only tcp_tso_segs() has to enforce the gso_max_segs limit.

Tested:

ethtool -K eth0 tso off gso off
tc qd replace dev eth0 root pfifo_fast

Before patch:
for f in {1..5}; do ./super_netperf 1 -H lpaa24 -- -K bbr; done
    691  (ss -temoi shows cwnd is stuck around 6 )
    667
    651
    631
    517

After patch :
# for f in {1..5}; do ./super_netperf 1 -H lpaa24 -- -K bbr; done
   1733 (ss -temoi shows cwnd is around 386 )
   1778
   1746
   1781
   1718

Fixes: 0f8782ea ("tcp_bbr: add BBR congestion control")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Acked-by: NSoheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If an attempt is made to disable RX checksums, USB adapter is changed
but netdev->features is not, because smsc75xx_set_features() returns a
non zero value.

This throws errors from netdev_rx_csum_fault() :
<devname>: hw csum failure
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Steve Glendinning <steve.glendinning@shawell.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Before, if cb->start() failed, the module reference would never be put,
because cb->cb_running is intentionally false at this point. Users are
generally annoyed by this because they can no longer unload modules that
leak references. Also, it may be possible to tediously wrap a reference
counter back to zero, especially since module.c still uses atomic_inc
instead of refcount_inc.

This patch expands the error path to simply call module_put if
cb->start() fails.

Fixes: 41c87425 ("netlink: do not set cb_running if dump's start() errs")
Signed-off-by: NJason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

test_maps contains a series of stress tests, and previously it will break the
rest tests when it failed to alloc memory.
-----------------------
Failed to create hashmap key=8 value=262144 'Cannot allocate memory'
Failed to create hashmap key=16 value=262144 'Cannot allocate memory'
Failed to create hashmap key=8 value=262144 'Cannot allocate memory'
Failed to create hashmap key=8 value=262144 'Cannot allocate memory'
test_maps: test_maps.c:955: run_parallel: Assertion `status == 0' failed.
Aborted
not ok 1..3 selftests:  test_maps [FAIL]
-----------------------
after this patch, the rest tests will be continue when it occurs an ENOMEM failure

CC: Alexei Starovoitov <alexei.starovoitov@gmail.com>
CC: Philip Li <philip.li@intel.com>
Suggested-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NLi Zhijian <zhijianx.li@intel.com>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

bpf builds a test program for loading BPF ELF files. Add the executable
to the .gitignore list.
Signed-off-by: NAnders Roxell <anders.roxell@linaro.org>
Tested-by: NDaniel Díaz <daniel.diaz@linaro.org>
Acked-by: NDavid S. Miller <davem@davemloft.net>
Acked-by: NShuah Khan <shuahkh@osg.samsung.com>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

Both glibc and the kernel have in6_* macros definitions. Build fails
because it picks up wrong in6_* macro from the kernel header and not the
header from glibc.

Fixes build error below:
clang -I. -I./include/uapi -I../../../include/uapi
     -Wno-compare-distinct-pointer-types \
         -O2 -target bpf -emit-llvm -c test_tcpbpf_kern.c -o - |      \
llc -march=bpf -mcpu=generic -filetype=obj
     -o .../tools/testing/selftests/bpf/test_tcpbpf_kern.o
In file included from test_tcpbpf_kern.c:12:
.../netinet/in.h:101:5: error: expected identifier
    IPPROTO_HOPOPTS = 0,   /* IPv6 Hop-by-Hop options.  */
    ^
.../linux/in6.h:131:26: note: expanded from macro 'IPPROTO_HOPOPTS'
                                ^
In file included from test_tcpbpf_kern.c:12:
/usr/include/netinet/in.h:103:5: error: expected identifier
    IPPROTO_ROUTING = 43,  /* IPv6 routing header.  */
    ^
.../linux/in6.h:132:26: note: expanded from macro 'IPPROTO_ROUTING'
                                ^
In file included from test_tcpbpf_kern.c:12:
.../netinet/in.h:105:5: error: expected identifier
    IPPROTO_FRAGMENT = 44, /* IPv6 fragmentation header.  */
    ^

Since both glibc and the kernel have in6_* macros definitions, use the
one from glibc.  Kernel headers will check for previous libc definitions
by including include/linux/libc-compat.h.
Reported-by: NDaniel Díaz <daniel.diaz@linaro.org>
Signed-off-by: NAnders Roxell <anders.roxell@linaro.org>
Tested-by: NDaniel Díaz <daniel.diaz@linaro.org>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

The only user of this variable is inside of an #ifdef, causing
a warning without CONFIG_INET:

net/core/filter.c: In function '____bpf_sock_ops_cb_flags_set':
net/core/filter.c:3382:6: error: unused variable 'val' [-Werror=unused-variable]
  int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS;

This replaces the #ifdef with a nicer IS_ENABLED() check that
makes the code more readable and avoids the warning.

Fixes: b13d8807 ("bpf: Adds field bpf_sock_ops_cb_flags to tcp_sock")
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>

After resuming from suspend, the PCI device support must re-enable the
interrupt setting so that interrupts are actually delivered.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Daniel Borkmann says:

====================
pull-request: bpf 2018-02-20

The following pull-request contains BPF updates for your *net* tree.

The main changes are:

1) Fix a memory leak in LPM trie's map_free() callback function, where
   the trie structure itself was not freed since initial implementation.
   Also a synchronize_rcu() was needed in order to wait for outstanding
   programs accessing the trie to complete, from Yonghong.

2) Fix sock_map_alloc()'s error path in order to correctly propagate
   the -EINVAL error in case of too large allocation requests. This
   was just recently introduced when fixing close hooks via ULP layer,
   fix from Eric.

3) Do not use GFP_ATOMIC in __cpu_map_entry_alloc(). Reason is that this
   will not work with the recent __ptr_ring_init_queue_alloc() conversion
   to kvmalloc_array(), where in case of fallback to vmalloc() that GFP
   flag is invalid, from Jason.

4) Fix two recent syzkaller warnings: i) fix bpf_prog_array_copy_to_user()
   when a prog query with a big number of ids was performed where we'd
   otherwise trigger a warning from allocator side, ii) fix a missing
   mlock precharge on arraymaps, from Daniel.

5) Two fixes for bpftool in order to avoid breaking JSON output when used
   in batch mode, from Quentin.

6) Move a pr_debug() in libbpf in order to avoid having an otherwise
   uninitialized variable in bpf_program__reloc_text(), from Jeremy.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jesper Dangaard Brouer says:

====================
virtio_net: several bugs in XDP code for driver virtio_net

The virtio_net driver actually violates the original memory model of
XDP causing hard to debug crashes.  Per request of John Fastabend,
instead of removing the XDP feature I'm fixing as much as possible.
While testing virtio_net with XDP_REDIRECT I found 4 different bugs.

Patch-1: not enough tail-room for build_skb in receive_mergeable()
 only option is to disable XDP_REDIRECT in receive_mergeable()

Patch-2: XDP in receive_small() basically never worked (check wrong flag)

Patch-3: fix memory leak for XDP_REDIRECT in error cases

Patch-4: avoid crash when ndo_xdp_xmit is called on dev not ready for XDP

In the longer run, we should consider introducing a separate receive
function when attaching an XDP program, and also change the memory
model to be compatible with XDP when attaching an XDP prog.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When a driver implements the ndo_xdp_xmit() function, there is
(currently) no generic way to determine whether it is safe to call.

It is e.g. unsafe to call the drivers ndo_xdp_xmit, if it have not
allocated the needed XDP TX queues yet.  This is the case for
virtio_net, which first allocates the XDP TX queues once an XDP/bpf
prog is attached (in virtnet_xdp_set()).

Thus, a crash will occur for virtio_net when redirecting to another
virtio_net device's ndo_xdp_xmit, which have not attached a XDP prog.
The sample xdp_redirect_map tries to attach a dummy XDP prog to take
this into account, but it can also easily fail if the virtio_net (or
actually underlying vhost driver) have not allocated enough extra
queues for the device.

Allocating more queue this is currently a manual config.
Hint for libvirt XML add:

  <driver name='vhost' queues='16'>
    <host mrg_rxbuf='off'/>
    <guest tso4='off' tso6='off' ecn='off' ufo='off'/>
  </driver>

The solution in this patch is to check that the device have loaded an
XDP/bpf prog before proceeding.  This is similar to the check
performed in driver ixgbe.
Signed-off-by: NJesper Dangaard Brouer <brouer@redhat.com>
Acked-by: NJohn Fastabend <john.fastabend@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

XDP_REDIRECT calling xdp_do_redirect() can fail for multiple reasons
(which can be inspected by tracepoints). The current semantics is that
on failure the driver calling xdp_do_redirect() must handle freeing or
recycling the page associated with this frame.  This can be seen as an
optimization, as drivers usually have an optimized XDP_DROP code path
for frame recycling in place already.

The virtio_net driver didn't handle when xdp_do_redirect() failed.
This caused a memory leak as the page refcnt wasn't decremented on
failures.

The function __virtnet_xdp_xmit() did handle one type of failure,
when the xmit queue virtqueue_add_outbuf() is full, which "hides"
releasing a refcnt on the page.  Instead the function __virtnet_xdp_xmit()
must follow API of xdp_do_redirect(), which on errors leave it up to
the caller to free the page, of the failed send operation.

Fixes: 186b3c99 ("virtio-net: support XDP_REDIRECT")
Signed-off-by: NJesper Dangaard Brouer <brouer@redhat.com>
Acked-by: NJohn Fastabend <john.fastabend@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When configuring virtio_net to use the code path 'receive_small()',
in-order to get correct XDP_REDIRECT support, I discovered TCP packets
would get silently dropped when loading an XDP program action XDP_PASS.

The bug seems to be that receive_small() when XDP is loaded check that
hdr->hdr.flags is zero, which seems wrong as hdr.flags contains the
flags VIRTIO_NET_HDR_F_* :
 #define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 /* Use csum_start, csum_offset */
 #define VIRTIO_NET_HDR_F_DATA_VALID 2 /* Csum is valid */

TCP got dropped as it had the VIRTIO_NET_HDR_F_DATA_VALID flag set.

The flags that are relevant here are the VIRTIO_NET_HDR_GSO_* flags
stored in hdr->hdr.gso_type. Thus, the fix is just check that none of
the gso_type flags have been set.

Fixes: bb91accf ("virtio-net: XDP support for small buffers")
Signed-off-by: NJesper Dangaard Brouer <brouer@redhat.com>
Acked-by: NJohn Fastabend <john.fastabend@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The virtio_net code have three different RX code-paths in receive_buf().
Two of these code paths can handle XDP, but one of them is broken for
at least XDP_REDIRECT.

Function(1): receive_big() does not support XDP.
Function(2): receive_small() support XDP fully and uses build_skb().
Function(3): receive_mergeable() broken XDP_REDIRECT uses napi_alloc_skb().

The simple explanation is that receive_mergeable() is broken because
it uses napi_alloc_skb(), which violates XDP given XDP assumes packet
header+data in single page and enough tail room for skb_shared_info.

The longer explaination is that receive_mergeable() tries to
work-around and satisfy these XDP requiresments e.g. by having a
function xdp_linearize_page() that allocates and memcpy RX buffers
around (in case packet is scattered across multiple rx buffers).  This
does currently satisfy XDP_PASS, XDP_DROP and XDP_TX (but only because
we have not implemented bpf_xdp_adjust_tail yet).

The XDP_REDIRECT action combined with cpumap is broken, and cause hard
to debug crashes.  The main issue is that the RX packet does not have
the needed tail-room (SKB_DATA_ALIGN(skb_shared_info)), causing
skb_shared_info to overlap the next packets head-room (in which cpumap
stores info).

Reproducing depend on the packet payload length and if RX-buffer size
happened to have tail-room for skb_shared_info or not.  But to make
this even harder to troubleshoot, the RX-buffer size is runtime
dynamically change based on an Exponentially Weighted Moving Average
(EWMA) over the packet length, when refilling RX rings.

This patch only disable XDP_REDIRECT support in receive_mergeable()
case, because it can cause a real crash.

IMHO we should consider NOT supporting XDP in receive_mergeable() at
all, because the principles behind XDP are to gain speed by (1) code
simplicity, (2) sacrificing memory and (3) where possible moving
runtime checks to setup time.  These principles are clearly being
violated in receive_mergeable(), that e.g. runtime track average
buffer size to save memory consumption.

In the longer run, we should consider introducing a separate receive
function when attaching an XDP program, and also change the memory
model to be compatible with XDP when attaching an XDP prog.

Fixes: 186b3c99 ("virtio-net: support XDP_REDIRECT")
Signed-off-by: NJesper Dangaard Brouer <brouer@redhat.com>
Acked-by: NJohn Fastabend <john.fastabend@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Saeed Mahameed says:

====================
Mellanox, mlx5 fixes 2018-02-20

The following pull request includes some fixes for the mlx5 core and
netdevice driver.

Please pull and let me know if there's any issue.

-stable 4.10.y:
('net/mlx5e: Fix loopback self test when GRO is off')

-stable 4.12.y:
('net/mlx5e: Specify numa node when allocating drop rq')

-stable 4.13.y:
('net/mlx5e: Verify inline header size do not exceed SKB linear size')

-stable 4.15.y:
('net/mlx5e: Fix TCP checksum in LRO buffers')
('net/mlx5: Fix error handling when adding flow rules')
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following patchset contains large batch with Netfilter fixes for
your net tree, mostly due to syzbot report fixups and pr_err()
ratelimiting, more specifically, they are:

1) Get rid of superfluous unnecessary check in x_tables before vmalloc(),
   we don't hit BUG there anymore, patch from Michal Hock, suggested by
   Andrew Morton.

2) Race condition in proc file creation in ipt_CLUSTERIP, from Cong Wang.

3) Drop socket lock that results in circular locking dependency, patch
   from Paolo Abeni.

4) Drop packet if case of malformed blob that makes backpointer jump
   in x_tables, from Florian Westphal.

5) Fix refcount leak due to race in ipt_CLUSTERIP in
   clusterip_config_find_get(), from Cong Wang.

6) Several patches to ratelimit pr_err() for x_tables since this can be
   a problem where CAP_NET_ADMIN semantics can protect us in untrusted
   namespace, from Florian Westphal.

7) Missing .gitignore update for new autogenerated asn1 state machine
   for the SNMP NAT helper, from Zhu Lingshan.

8) Missing timer initialization in xt_LED, from Paolo Abeni.

9) Do not allow negative port range in NAT, also from Paolo.

10) Lock imbalance in the xt_hashlimit rate match mode, patch from
    Eric Dumazet.

11) Initialize workqueue before timer in the idletimer match,
    from Eric Dumazet.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

So far, if the filter was too large to fit in the allocated skb, the
kernel did not return any error and stopped dumping. Modify the dumper
so that it returns -EMSGSIZE when a filter fails to dump and it is the
first filter in the skb. If we are not first, we will get a next chance
with more room.

I understand this is pretty near to being an API change, but the
original design (silent truncation) can be considered a bug.

Note: The error case can happen pretty easily if you create a filter
with 32 actions and have 4kb pages. Also recent versions of iproute try
to be clever with their buffer allocation size, which in turn leads to
Signed-off-by: NRoman Kapl <code@rkapl.cz>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NCong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If building match list or adding existing fg fails when
node is locked, function returned without unlocking it.
This happened if node version changed or adding existing fg
returned with EAGAIN after jumping to search_again_locked label.

Fixes: bd71b08e ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: NVlad Buslov <vladbu@mellanox.com>
Reviewed-by: NMaor Gottlieb <maorg@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

First use of drop counters happens in esw_apply_vport_conf function,
while they are allocated later in the flow. Fix that by moving
esw_vport_create_drop_counters function to be called before the first use.

Fixes: b8a0dbe3 ("net/mlx5e: E-switch, Add steering drop counters")
Signed-off-by: NEugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

We can't allow only some of the rules sharing an FTE to ask for
header re-write, add it to the conflicting action checks.

Fixes: 0d235c3f ('net/mlx5: Add hash table to search FTEs in a flow-group')
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>