Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 23 7月, 2018 3 次提交
  3. 04 7月, 2018 4 次提交
  5. 23 6月, 2018 1 次提交
  7. 13 6月, 2018 1 次提交
    • K
      treewide: kmalloc() -> kmalloc_array() · 6da2ec56
      由 Kees Cook 提交于 
      The kmalloc() function has a 2-factor argument form, kmalloc_array(). This
patch replaces cases of:

        kmalloc(a * b, gfp)

with:
        kmalloc_array(a * b, gfp)

as well as handling cases of:

        kmalloc(a * b * c, gfp)

with:

        kmalloc(array3_size(a, b, c), gfp)

as it's slightly less ugly than:

        kmalloc_array(array_size(a, b), c, gfp)

This does, however, attempt to ignore constant size factors like:

        kmalloc(4 * 1024, gfp)

though any constants defined via macros get caught up in the conversion.

Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.

The tools/ directory was manually excluded, since it has its own
implementation of kmalloc().

The Coccinelle script used for this was:

// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@

(
  kmalloc(
-	(sizeof(TYPE)) * E
+	sizeof(TYPE) * E
  , ...)
|
  kmalloc(
-	(sizeof(THING)) * E
+	sizeof(THING) * E
  , ...)
)

// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@

(
  kmalloc(
-	sizeof(u8) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(__u8) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(char) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(unsigned char) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(u8) * COUNT
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(__u8) * COUNT
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(char) * COUNT
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(unsigned char) * COUNT
+	COUNT
  , ...)
)

// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@

(
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * (COUNT_ID)
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * COUNT_ID
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * (COUNT_CONST)
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * COUNT_CONST
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * (COUNT_ID)
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * COUNT_ID
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * (COUNT_CONST)
+	COUNT_CONST, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * COUNT_CONST
+	COUNT_CONST, sizeof(THING)
  , ...)
)

// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@

- kmalloc
+ kmalloc_array
  (
-	SIZE * COUNT
+	COUNT, SIZE
  , ...)

// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@

(
  kmalloc(
-	sizeof(TYPE) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(TYPE) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(TYPE) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(TYPE) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(THING) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kmalloc(
-	sizeof(THING) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kmalloc(
-	sizeof(THING) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kmalloc(
-	sizeof(THING) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
)

// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@

(
  kmalloc(
-	sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kmalloc(
-	sizeof(THING1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kmalloc(
-	sizeof(THING1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
|
  kmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
)

// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@

(
  kmalloc(
-	(COUNT) * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	(COUNT) * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	(COUNT) * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	(COUNT) * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
)

// Any remaining multi-factor products, first at least 3-factor products,
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@

(
  kmalloc(C1 * C2 * C3, ...)
|
  kmalloc(
-	(E1) * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kmalloc(
-	(E1) * (E2) * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kmalloc(
-	(E1) * (E2) * (E3)
+	array3_size(E1, E2, E3)
  , ...)
|
  kmalloc(
-	E1 * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
)

// And then all remaining 2 factors products when they're not all constants,
// keeping sizeof() as the second factor argument.
@@
expression THING, E1, E2;
type TYPE;
constant C1, C2, C3;
@@

(
  kmalloc(sizeof(THING) * C2, ...)
|
  kmalloc(sizeof(TYPE) * C2, ...)
|
  kmalloc(C1 * C2 * C3, ...)
|
  kmalloc(C1 * C2, ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * (E2)
+	E2, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * E2
+	E2, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * (E2)
+	E2, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * E2
+	E2, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	(E1) * E2
+	E1, E2
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	(E1) * (E2)
+	E1, E2
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	E1 * E2
+	E1, E2
  , ...)
)
Signed-off-by: NKees Cook <keescook@chromium.org>
      6da2ec56
  9. 31 5月, 2018 1 次提交
  11. 24 4月, 2018 1 次提交
    • P
      vhost_net: use packet weight for rx handler, too · db688c24
      由 Paolo Abeni 提交于 
      Similar to commit a2ac9990 ("vhost-net: set packet weight of
tx polling to 2 * vq size"), we need a packet-based limit for
handler_rx, too - elsewhere, under rx flood with small packets,
tx can be delayed for a very long time, even without busypolling.

The pkt limit applied to handle_rx must be the same applied by
handle_tx, or we will get unfair scheduling between rx and tx.
Tying such limit to the queue length makes it less effective for
large queue length values and can introduce large process
scheduler latencies, so a constant valued is used - likewise
the existing bytes limit.

The selected limit has been validated with PVP[1] performance
test with different queue sizes:

queue size		256	512	1024

baseline		366	354	362
weight 128		715	723	670
weight 256		740	745	733
weight 512		600	460	583
weight 1024		423	427	418

A packet weight of 256 gives peek performances in under all the
tested scenarios.

No measurable regression in unidirectional performance tests has
been detected.

[1] https://developers.redhat.com/blog/2017/06/05/measuring-and-comparing-open-vswitch-performance/Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Acked-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      db688c24
  13. 17 4月, 2018 1 次提交
  15. 09 4月, 2018 1 次提交
    • H
      vhost-net: set packet weight of tx polling to 2 * vq size · a2ac9990
      由 haibinzhang(张海斌) 提交于 
      handle_tx will delay rx for tens or even hundreds of milliseconds when tx busy
polling udp packets with small length(e.g. 1byte udp payload), because setting
VHOST_NET_WEIGHT takes into account only sent-bytes but no single packet length.

Ping-Latencies shown below were tested between two Virtual Machines using
netperf (UDP_STREAM, len=1), and then another machine pinged the client:

vq size=256
Packet-Weight   Ping-Latencies(millisecond)
                   min      avg       max
Origin           3.319   18.489    57.303
64               1.643    2.021     2.552
128              1.825    2.600     3.224
256              1.997    2.710     4.295
512              1.860    3.171     4.631
1024             2.002    4.173     9.056
2048             2.257    5.650     9.688
4096             2.093    8.508    15.943

vq size=512
Packet-Weight   Ping-Latencies(millisecond)
                   min      avg       max
Origin           6.537   29.177    66.245
64               2.798    3.614     4.403
128              2.861    3.820     4.775
256              3.008    4.018     4.807
512              3.254    4.523     5.824
1024             3.079    5.335     7.747
2048             3.944    8.201    12.762
4096             4.158   11.057    19.985

Seems pretty consistent, a small dip at 2 VQ sizes.
Ring size is a hint from device about a burst size it can tolerate. Based on
benchmarks, set the weight to 2 * vq size.

To evaluate this change, another tests were done using netperf(RR, TX) between
two machines with Intel(R) Xeon(R) Gold 6133 CPU @ 2.50GHz, and vq size was
tweaked through qemu. Results shown below does not show obvious changes.

vq size=256 TCP_RR                vq size=512 TCP_RR
size/sessions/+thu%/+normalize%   size/sessions/+thu%/+normalize%
   1/       1/  -7%/        -2%      1/       1/   0%/        -2%
   1/       4/  +1%/         0%      1/       4/  +1%/         0%
   1/       8/  +1%/        -2%      1/       8/   0%/        +1%
  64/       1/  -6%/         0%     64/       1/  +7%/        +3%
  64/       4/   0%/        +2%     64/       4/  -1%/        +1%
  64/       8/   0%/         0%     64/       8/  -1%/        -2%
 256/       1/  -3%/        -4%    256/       1/  -4%/        -2%
 256/       4/  +3%/        +4%    256/       4/  +1%/        +2%
 256/       8/  +2%/         0%    256/       8/  +1%/        -1%

vq size=256 UDP_RR                vq size=512 UDP_RR
size/sessions/+thu%/+normalize%   size/sessions/+thu%/+normalize%
   1/       1/  -5%/        +1%      1/       1/  -3%/        -2%
   1/       4/  +4%/        +1%      1/       4/  -2%/        +2%
   1/       8/  -1%/        -1%      1/       8/  -1%/         0%
  64/       1/  -2%/        -3%     64/       1/  +1%/        +1%
  64/       4/  -5%/        -1%     64/       4/  +2%/         0%
  64/       8/   0%/        -1%     64/       8/  -2%/        +1%
 256/       1/  +7%/        +1%    256/       1/  -7%/         0%
 256/       4/  +1%/        +1%    256/       4/  -3%/        -4%
 256/       8/  +2%/        +2%    256/       8/  +1%/        +1%

vq size=256 TCP_STREAM            vq size=512 TCP_STREAM
size/sessions/+thu%/+normalize%   size/sessions/+thu%/+normalize%
  64/       1/   0%/        -3%     64/       1/   0%/         0%
  64/       4/  +3%/        -1%     64/       4/  -2%/        +4%
  64/       8/  +9%/        -4%     64/       8/  -1%/        +2%
 256/       1/  +1%/        -4%    256/       1/  +1%/        +1%
 256/       4/  -1%/        -1%    256/       4/  -3%/         0%
 256/       8/  +7%/        +5%    256/       8/  -3%/         0%
 512/       1/  +1%/         0%    512/       1/  -1%/        -1%
 512/       4/  +1%/        -1%    512/       4/   0%/         0%
 512/       8/  +7%/        -5%    512/       8/  +6%/        -1%
1024/       1/   0%/        -1%   1024/       1/   0%/        +1%
1024/       4/  +3%/         0%   1024/       4/  +1%/         0%
1024/       8/  +8%/        +5%   1024/       8/  -1%/         0%
2048/       1/  +2%/        +2%   2048/       1/  -1%/         0%
2048/       4/  +1%/         0%   2048/       4/   0%/        -1%
2048/       8/  -2%/         0%   2048/       8/   5%/        -1%
4096/       1/  -2%/         0%   4096/       1/  -2%/         0%
4096/       4/  +2%/         0%   4096/       4/   0%/         0%
4096/       8/  +9%/        -2%   4096/       8/  -5%/        -1%
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NHaibin Zhang <haibinzhang@tencent.com>
Signed-off-by: NYunfang Tai <yunfangtai@tencent.com>
Signed-off-by: NLidong Chen <lidongchen@tencent.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      a2ac9990
  17. 27 3月, 2018 1 次提交
  19. 10 3月, 2018 3 次提交
    • J
      vhost_net: examine pointer types during un-producing · 3a403076
      由 Jason Wang 提交于 
      After commit fc72d1d5 ("tuntap: XDP transmission"), we can
actually queueing XDP pointers in the pointer ring, so we should
examine the pointer type before freeing the pointer.

Fixes: fc72d1d5 ("tuntap: XDP transmission")
Reported-by: NMichael S. Tsirkin <mst@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      3a403076
    • J
      vhost_net: keep private_data and rx_ring synced · 303fd71b
      由 Jason Wang 提交于 
      We get pointer ring from the exported sock, this means we should keep
rx_ring and vq->private synced during both vq stop and backend set,
otherwise we may see stale rx_ring.

Fixes: c67df11f ("vhost_net: try batch dequing from skb array")
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      303fd71b
    • A
      vhost_net: initialize rx_ring in vhost_net_open() · ab7e34b3
      由 Alexander Potapenko 提交于 
      KMSAN reported a use of uninit memory in vhost_net_buf_unproduce()
while trying to access n->vqs[VHOST_NET_VQ_TX].rx_ring:

==================================================================
BUG: KMSAN: use of uninitialized memory in vhost_net_buf_unproduce+0x7bb/0x9a0 drivers/vho
et.c:170
CPU: 0 PID: 3021 Comm: syz-fuzzer Not tainted 4.16.0-rc4+ #3853
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x185/0x1d0 lib/dump_stack.c:53
 kmsan_report+0x142/0x1f0 mm/kmsan/kmsan.c:1093
 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676
 vhost_net_buf_unproduce+0x7bb/0x9a0 drivers/vhost/net.c:170
 vhost_net_stop_vq drivers/vhost/net.c:974 [inline]
 vhost_net_stop+0x146/0x380 drivers/vhost/net.c:982
 vhost_net_release+0xb1/0x4f0 drivers/vhost/net.c:1015
 __fput+0x49f/0xa00 fs/file_table.c:209
 ____fput+0x37/0x40 fs/file_table.c:243
 task_work_run+0x243/0x2c0 kernel/task_work.c:113
 tracehook_notify_resume include/linux/tracehook.h:191 [inline]
 exit_to_usermode_loop arch/x86/entry/common.c:166 [inline]
 prepare_exit_to_usermode+0x349/0x3b0 arch/x86/entry/common.c:196
 syscall_return_slowpath+0xf3/0x6d0 arch/x86/entry/common.c:265
 do_syscall_64+0x34d/0x450 arch/x86/entry/common.c:292
...
origin:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:303 [inline]
 kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:213
 kmsan_kmalloc_large+0x6f/0xd0 mm/kmsan/kmsan.c:392
 kmalloc_large_node_hook mm/slub.c:1366 [inline]
 kmalloc_large_node mm/slub.c:3808 [inline]
 __kmalloc_node+0x100e/0x1290 mm/slub.c:3818
 kmalloc_node include/linux/slab.h:554 [inline]
 kvmalloc_node+0x1a5/0x2e0 mm/util.c:419
 kvmalloc include/linux/mm.h:541 [inline]
 vhost_net_open+0x64/0x5f0 drivers/vhost/net.c:921
 misc_open+0x7b5/0x8b0 drivers/char/misc.c:154
 chrdev_open+0xc28/0xd90 fs/char_dev.c:417
 do_dentry_open+0xccb/0x1430 fs/open.c:752
 vfs_open+0x272/0x2e0 fs/open.c:866
 do_last fs/namei.c:3378 [inline]
 path_openat+0x49ad/0x6580 fs/namei.c:3519
 do_filp_open+0x267/0x640 fs/namei.c:3553
 do_sys_open+0x6ad/0x9c0 fs/open.c:1059
 SYSC_openat+0xc7/0xe0 fs/open.c:1086
 SyS_openat+0x63/0x90 fs/open.c:1080
 do_syscall_64+0x2f1/0x450 arch/x86/entry/common.c:287
==================================================================

Fixes: c67df11f ("vhost_net: try batch dequing from skb array")
Signed-off-by: NAlexander Potapenko <glider@google.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      ab7e34b3
  21. 13 2月, 2018 1 次提交
    • D
      net: make getname() functions return length rather than use int* parameter · 9b2c45d4
      由 Denys Vlasenko 提交于 
      Changes since v1:
Added changes in these files:
    drivers/infiniband/hw/usnic/usnic_transport.c
    drivers/staging/lustre/lnet/lnet/lib-socket.c
    drivers/target/iscsi/iscsi_target_login.c
    drivers/vhost/net.c
    fs/dlm/lowcomms.c
    fs/ocfs2/cluster/tcp.c
    security/tomoyo/network.c

Before:
All these functions either return a negative error indicator,
or store length of sockaddr into "int *socklen" parameter
and return zero on success.

"int *socklen" parameter is awkward. For example, if caller does not
care, it still needs to provide on-stack storage for the value
it does not need.

None of the many FOO_getname() functions of various protocols
ever used old value of *socklen. They always just overwrite it.

This change drops this parameter, and makes all these functions, on success,
return length of sockaddr. It's always >= 0 and can be differentiated
from an error.

Tests in callers are changed from "if (err)" to "if (err < 0)", where needed.

rpc_sockname() lost "int buflen" parameter, since its only use was
to be passed to kernel_getsockname() as &buflen and subsequently
not used in any way.

Userspace API is not changed.

    text    data     bss      dec     hex filename
30108430 2633624  873672 33615726 200ef6e vmlinux.before.o
30108109 2633612  873672 33615393 200ee21 vmlinux.o
Signed-off-by: NDenys Vlasenko <dvlasenk@redhat.com>
CC: David S. Miller <davem@davemloft.net>
CC: linux-kernel@vger.kernel.org
CC: netdev@vger.kernel.org
CC: linux-bluetooth@vger.kernel.org
CC: linux-decnet-user@lists.sourceforge.net
CC: linux-wireless@vger.kernel.org
CC: linux-rdma@vger.kernel.org
CC: linux-sctp@vger.kernel.org
CC: linux-nfs@vger.kernel.org
CC: linux-x25@vger.kernel.org
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      9b2c45d4
  23. 12 2月, 2018 1 次提交
    • L
      vfs: do bulk POLL* -> EPOLL* replacement · a9a08845
      由 Linus Torvalds 提交于 
      This is the mindless scripted replacement of kernel use of POLL*
variables as described by Al, done by this script:

    for V in IN OUT PRI ERR RDNORM RDBAND WRNORM WRBAND HUP RDHUP NVAL MSG; do
        L=`git grep -l -w POLL$V | grep -v '^t' | grep -v /um/ | grep -v '^sa' | grep -v '/poll.h$'|grep -v '^D'`
        for f in $L; do sed -i "-es/^\([^\"]*\)\(\<POLL$V\>\)/\\1E\\2/" $f; done
    done

with de-mangling cleanups yet to come.

NOTE! On almost all architectures, the EPOLL* constants have the same
values as the POLL* constants do.  But they keyword here is "almost".
For various bad reasons they aren't the same, and epoll() doesn't
actually work quite correctly in some cases due to this on Sparc et al.

The next patch from Al will sort out the final differences, and we
should be all done.
Scripted-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      a9a08845
  25. 01 2月, 2018 1 次提交
  27. 30 1月, 2018 1 次提交
  29. 11 1月, 2018 1 次提交
    • J
      vhost_net: batch used ring update in rx · e2b3b35e
      由 Jason Wang 提交于 
      This patch tries to batched used ring update during RX. This is pretty
fit for the case when guest is much faster (e.g dpdk based
backend). In this case, used ring is almost empty:

- we may get serious cache line misses/contending on both used ring
  and used idx.
- at most 1 packet could be dequeued at one time, batching in guest
  does not make much effect.

Update used ring in a batch can help since guest won't access the used
ring until used idx was advanced for several descriptors and since we
advance used ring for every N packets, guest will only need to access
used idx for every N packet since it can cache the used idx. To have a
better interaction for both batch dequeuing and dpdk batching,
VHOST_RX_BATCH was used as the maximum number of descriptors that
could be batched.

Test were done between two machines with 2.40GHz Intel(R) Xeon(R) CPU
E5-2630 connected back to back through ixgbe. Traffic were generated
on one remote ixgbe through MoonGen and measure the RX pps through
testpmd in guest when do xdp_redirect_map from local ixgbe to
tap. RX pps were increased from 3.05 Mpps to 4.00 Mpps (about 31%
improvement).

One possible concern for this is the implications for TCP (especially
latency sensitive workload). Result[1] does not show obvious changes
for most of the netperf test (RR, TX, and RX). And we do get some
improvements for RX on some specific size.

Guest RX:

size/sessions/+thu%/+normalize%
   64/     1/   +2%/   +2%
   64/     2/   +2%/   -1%
   64/     4/   +1%/   +1%
   64/     8/    0%/    0%
  256/     1/   +6%/   -3%
  256/     2/   -3%/   +2%
  256/     4/  +11%/  +11%
  256/     8/    0%/    0%
  512/     1/   +4%/    0%
  512/     2/   +2%/   +2%
  512/     4/    0%/   -1%
  512/     8/   -8%/   -8%
 1024/     1/   -7%/  -17%
 1024/     2/   -8%/   -7%
 1024/     4/   +1%/    0%
 1024/     8/    0%/    0%
 2048/     1/  +30%/  +14%
 2048/     2/  +46%/  +40%
 2048/     4/    0%/    0%
 2048/     8/    0%/    0%
 4096/     1/  +23%/  +22%
 4096/     2/  +26%/  +23%
 4096/     4/    0%/   +1%
 4096/     8/    0%/    0%
16384/     1/   -2%/   -3%
16384/     2/   +1%/   -4%
16384/     4/   -1%/   -3%
16384/     8/    0%/   -1%
65535/     1/  +15%/   +7%
65535/     2/   +4%/   +7%
65535/     4/    0%/   +1%
65535/     8/    0%/    0%

TCP_RR:

size/sessions/+thu%/+normalize%
    1/     1/    0%/   +1%
    1/    25/   +2%/   +1%
    1/    50/   +4%/   +1%
   64/     1/    0%/   -4%
   64/    25/   +2%/   +1%
   64/    50/    0%/   -1%
  256/     1/    0%/    0%
  256/    25/    0%/    0%
  256/    50/   +4%/   +2%

Guest TX:

size/sessions/+thu%/+normalize%
   64/     1/   +4%/   -2%
   64/     2/   -6%/   -5%
   64/     4/   +3%/   +6%
   64/     8/    0%/   +3%
  256/     1/  +15%/  +16%
  256/     2/  +11%/  +12%
  256/     4/   +1%/    0%
  256/     8/   +5%/   +5%
  512/     1/   -1%/   -6%
  512/     2/    0%/   -8%
  512/     4/   -2%/   +4%
  512/     8/   +6%/   +9%
 1024/     1/   +3%/   +1%
 1024/     2/   +3%/   +9%
 1024/     4/    0%/   +7%
 1024/     8/    0%/   +7%
 2048/     1/   +8%/   +2%
 2048/     2/   +3%/   -1%
 2048/     4/   -1%/  +11%
 2048/     8/   +3%/   +9%
 4096/     1/   +8%/   +8%
 4096/     2/    0%/   -7%
 4096/     4/   +4%/   +4%
 4096/     8/   +2%/   +5%
16384/     1/   -3%/   +1%
16384/     2/   -1%/  -12%
16384/     4/   -1%/   +5%
16384/     8/    0%/   +1%
65535/     1/    0%/   -3%
65535/     2/   +5%/  +16%
65535/     4/   +1%/   +2%
65535/     8/   +1%/   -1%
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      e2b3b35e
  31. 09 1月, 2018 2 次提交
    • J
      tuntap: XDP transmission · fc72d1d5
      由 Jason Wang 提交于 
      This patch implements XDP transmission for TAP. Since we can't create
new queues for TAP during XDP set, exist ptr_ring was reused for
queuing XDP buffers. To differ xdp_buff from sk_buff, TUN_XDP_FLAG
(0x1UL) was encoded into lowest bit of xpd_buff pointer during
ptr_ring_produce, and was decoded during consuming. XDP metadata was
stored in the headroom of the packet which should work in most of
cases since driver usually reserve enough headroom. Very minor changes
were done for vhost_net: it just need to peek the length depends on
the type of pointer.

Tests were done on two Intel E5-2630 2.40GHz machines connected back
to back through two 82599ES. Traffic were generated/received through
MoonGen/testpmd(rxonly). It reports ~20% improvements when
xdp_redirect_map is doing redirection from ixgbe to TAP (from 2.50Mpps
to 3.05Mpps)

Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      fc72d1d5
    • J
      tun/tap: use ptr_ring instead of skb_array · 5990a305
      由 Jason Wang 提交于 
      This patch switches to use ptr_ring instead of skb_array. This will be
used to enqueue different types of pointers by encoding type into
lower bits.
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      5990a305
  33. 03 12月, 2017 1 次提交
  35. 29 11月, 2017 1 次提交
  37. 15 11月, 2017 1 次提交
    • J
      vhost_net: conditionally enable tx polling · feb8892c
      由 Jason Wang 提交于 
      We always poll tx for socket, this is sub optimal since this will
slightly increase the waitqueue traversing time and more important,
vhost could not benefit from commit 9e641bdc ("net-tun:
restructure tun_do_read for better sleep/wakeup efficiency") even if
we've stopped rx polling during handle_rx(), tx poll were still left
in the waitqueue.

Pktgen from a remote host to VM over mlx4 on two 2.00GHz Xeon E5-2650
shows 11.7% improvements on rx PPS. (from 1.28Mpps to 1.44Mpps)

Cc: Wei Xu <wexu@redhat.com>
Cc: Matthew Rosato <mjrosato@linux.vnet.ibm.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      feb8892c
  39. 10 10月, 2017 1 次提交
    • W
      vhost_net: do not stall on zerocopy depletion · 1e6f7453
      由 Willem de Bruijn 提交于 
      Vhost-net has a hard limit on the number of zerocopy skbs in flight.
When reached, transmission stalls. Stalls cause latency, as well as
head-of-line blocking of other flows that do not use zerocopy.

Instead of stalling, revert to copy-based transmission.

Tested by sending two udp flows from guest to host, one with payload
of VHOST_GOODCOPY_LEN, the other too small for zerocopy (1B). The
large flow is redirected to a netem instance with 1MBps rate limit
and deep 1000 entry queue.

  modprobe ifb
  ip link set dev ifb0 up
  tc qdisc add dev ifb0 root netem limit 1000 rate 1MBit

  tc qdisc add dev tap0 ingress
  tc filter add dev tap0 parent ffff: protocol ip \
      u32 match ip dport 8000 0xffff \
      action mirred egress redirect dev ifb0

Before the delay, both flows process around 80K pps. With the delay,
before this patch, both process around 400. After this patch, the
large flow is still rate limited, while the small reverts to its
original rate. See also discussion in the first link, below.

Without rate limiting, {1, 10, 100}x TCP_STREAM tests continued to
send at 100% zerocopy.

The limit in vhost_exceeds_maxpend must be carefully chosen. With
vq->num >> 1, the flows remain correlated. This value happens to
correspond to VHOST_MAX_PENDING for vq->num == 256. Allow smaller
fractions and ensure correctness also for much smaller values of
vq->num, by testing the min() of both explicitly. See also the
discussion in the second link below.

Changes
  v1 -> v2
    - replaced min with typed min_t
    - avoid unnecessary whitespace change

Link:http://lkml.kernel.org/r/CAF=yD-+Wk9sc9dXMUq1+x_hh=3ThTXa6BnZkygP3tgVpjbp93g@mail.gmail.com
Link:http://lkml.kernel.org/r/20170819064129.27272-1-den@klaipeden.comSigned-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      1e6f7453
  41. 06 9月, 2017 1 次提交
    • J
      vhost_net: correctly check tx avail during rx busy polling · 8b949bef
      由 Jason Wang 提交于 
      We check tx avail through vhost_enable_notify() in the past which is
wrong since it only checks whether or not guest has filled more
available buffer since last avail idx synchronization which was just
done by vhost_vq_avail_empty() before. What we really want is checking
pending buffers in the avail ring. Fix this by calling
vhost_vq_avail_empty() instead.

This issue could be noticed by doing netperf TCP_RR benchmark as
client from guest (but not host). With this fix, TCP_RR from guest to
localhost restores from 1375.91 trans per sec to 55235.28 trans per
sec on my laptop (Intel(R) Core(TM) i7-5600U CPU @ 2.60GHz).

Fixes: 03088137 ("vhost_net: basic polling support")
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      8b949bef
  43. 02 9月, 2017 1 次提交
  45. 04 8月, 2017 1 次提交
    • W
      sock: enable MSG_ZEROCOPY · 1f8b977a
      由 Willem de Bruijn 提交于 
      Prepare the datapath for refcounted ubuf_info. Clone ubuf_info with
skb_zerocopy_clone() wherever needed due to skb split, merge, resize
or clone.

Split skb_orphan_frags into two variants. The split, merge, .. paths
support reference counted zerocopy buffers, so do not do a deep copy.
Add skb_orphan_frags_rx for paths that may loop packets to receive
sockets. That is not allowed, as it may cause unbounded latency.
Deep copy all zerocopy copy buffers, ref-counted or not, in this path.

The exact locations to modify were chosen by exhaustively searching
through all code that might modify skb_frag references and/or the
the SKBTX_DEV_ZEROCOPY tx_flags bit.

The changes err on the safe side, in two ways.

(1) legacy ubuf_info paths virtio and tap are not modified. They keep
    a 1:1 ubuf_info to sk_buff relationship. Calls to skb_orphan_frags
    still call skb_copy_ubufs and thus copy frags in this case.

(2) not all copies deep in the stack are addressed yet. skb_shift,
    skb_split and skb_try_coalesce can be refined to avoid copying.
    These are not in the hot path and this patch is hairy enough as
    is, so that is left for future refinement.
Signed-off-by: NWillem de Bruijn <willemb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      1f8b977a
  47. 13 7月, 2017 1 次提交
    • M
      mm, tree wide: replace __GFP_REPEAT by __GFP_RETRY_MAYFAIL with more useful semantic · dcda9b04
      由 Michal Hocko 提交于 
      __GFP_REPEAT was designed to allow retry-but-eventually-fail semantic to
the page allocator.  This has been true but only for allocations
requests larger than PAGE_ALLOC_COSTLY_ORDER.  It has been always
ignored for smaller sizes.  This is a bit unfortunate because there is
no way to express the same semantic for those requests and they are
considered too important to fail so they might end up looping in the
page allocator for ever, similarly to GFP_NOFAIL requests.

Now that the whole tree has been cleaned up and accidental or misled
usage of __GFP_REPEAT flag has been removed for !costly requests we can
give the original flag a better name and more importantly a more useful
semantic.  Let's rename it to __GFP_RETRY_MAYFAIL which tells the user
that the allocator would try really hard but there is no promise of a
success.  This will work independent of the order and overrides the
default allocator behavior.  Page allocator users have several levels of
guarantee vs.  cost options (take GFP_KERNEL as an example)

 - GFP_KERNEL & ~__GFP_RECLAIM - optimistic allocation without _any_
   attempt to free memory at all. The most light weight mode which even
   doesn't kick the background reclaim. Should be used carefully because
   it might deplete the memory and the next user might hit the more
   aggressive reclaim

 - GFP_KERNEL & ~__GFP_DIRECT_RECLAIM (or GFP_NOWAIT)- optimistic
   allocation without any attempt to free memory from the current
   context but can wake kswapd to reclaim memory if the zone is below
   the low watermark. Can be used from either atomic contexts or when
   the request is a performance optimization and there is another
   fallback for a slow path.

 - (GFP_KERNEL|__GFP_HIGH) & ~__GFP_DIRECT_RECLAIM (aka GFP_ATOMIC) -
   non sleeping allocation with an expensive fallback so it can access
   some portion of memory reserves. Usually used from interrupt/bh
   context with an expensive slow path fallback.

 - GFP_KERNEL - both background and direct reclaim are allowed and the
   _default_ page allocator behavior is used. That means that !costly
   allocation requests are basically nofail but there is no guarantee of
   that behavior so failures have to be checked properly by callers
   (e.g. OOM killer victim is allowed to fail currently).

 - GFP_KERNEL | __GFP_NORETRY - overrides the default allocator behavior
   and all allocation requests fail early rather than cause disruptive
   reclaim (one round of reclaim in this implementation). The OOM killer
   is not invoked.

 - GFP_KERNEL | __GFP_RETRY_MAYFAIL - overrides the default allocator
   behavior and all allocation requests try really hard. The request
   will fail if the reclaim cannot make any progress. The OOM killer
   won't be triggered.

 - GFP_KERNEL | __GFP_NOFAIL - overrides the default allocator behavior
   and all allocation requests will loop endlessly until they succeed.
   This might be really dangerous especially for larger orders.

Existing users of __GFP_REPEAT are changed to __GFP_RETRY_MAYFAIL
because they already had their semantic.  No new users are added.
__alloc_pages_slowpath is changed to bail out for __GFP_RETRY_MAYFAIL if
there is no progress and we have already passed the OOM point.

This means that all the reclaim opportunities have been exhausted except
the most disruptive one (the OOM killer) and a user defined fallback
behavior is more sensible than keep retrying in the page allocator.

[akpm@linux-foundation.org: fix arch/sparc/kernel/mdesc.c]
[mhocko@suse.com: semantic fix]
  Link: http://lkml.kernel.org/r/20170626123847.GM11534@dhcp22.suse.cz
[mhocko@kernel.org: address other thing spotted by Vlastimil]
  Link: http://lkml.kernel.org/r/20170626124233.GN11534@dhcp22.suse.cz
Link: http://lkml.kernel.org/r/20170623085345.11304-3-mhocko@kernel.orgSigned-off-by: NMichal Hocko <mhocko@suse.com>
Acked-by: NVlastimil Babka <vbabka@suse.cz>
Cc: Alex Belits <alex.belits@cavium.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: NeilBrown <neilb@suse.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      dcda9b04
  49. 18 5月, 2017 1 次提交
    • J
      vhost_net: try batch dequing from skb array · c67df11f
      由 Jason Wang 提交于 
      We used to dequeue one skb during recvmsg() from skb_array, this could
be inefficient because of the bad cache utilization and spinlock
touching for each packet. This patch tries to batch them by calling
batch dequeuing helpers explicitly on the exported skb array and pass
the skb back through msg_control for underlayer socket to finish the
userspace copying. Batch dequeuing is also the requirement for more
batching improvement on receive path.

Tests were done by pktgen on tap with XDP1 in guest. Host is Intel(R)
Xeon(R) CPU E5-2650 0 @ 2.00GHz.

rx batch | pps

0   2.25Mpps
1   2.33Mpps (+3.56%)
4   2.33Mpps (+3.56%)
16  2.35Mpps (+4.44%)
64  2.42Mpps (+7.56%) <- Default rx batching
128 2.40Mpps (+6.67%)
256 2.38Mpps (+5.78%)
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      c67df11f
  51. 09 5月, 2017 1 次提交
  53. 02 3月, 2017 2 次提交
  55. 12 2月, 2017 1 次提交
  57. 19 1月, 2017 1 次提交
  59. 16 11月, 2016 1 次提交
  61. 02 8月, 2016 1 次提交
    • J
      vhost: new device IOTLB API · 6b1e6cc7
      由 Jason Wang 提交于 
      This patch tries to implement an device IOTLB for vhost. This could be
used with userspace(qemu) implementation of DMA remapping
to emulate an IOMMU for the guest.

The idea is simple, cache the translation in a software device IOTLB
(which is implemented as an interval tree) in vhost and use vhost_net
file descriptor for reporting IOTLB miss and IOTLB
update/invalidation. When vhost meets an IOTLB miss, the fault
address, size and access can be read from the file. After userspace
finishes the translation, it writes the translated address to the
vhost_net file to update the device IOTLB.

When device IOTLB is enabled by setting VIRTIO_F_IOMMU_PLATFORM all vq
addresses set by ioctl are treated as iova instead of virtual address and
the accessing can only be done through IOTLB instead of direct userspace
memory access. Before each round or vq processing, all vq metadata is
prefetched in device IOTLB to make sure no translation fault happens
during vq processing.

In most cases, virtqueues are contiguous even in virtual address space.
The IOTLB translation for virtqueue itself may make it a little
slower. We might add fast path cache on top of this patch.
Signed-off-by: NJason Wang <jasowang@redhat.com>
[mst: use virtio feature bit: VHOST_F_DEVICE_IOTLB -> VIRTIO_F_IOMMU_PLATFORM ]
[mst: fix build warnings ]
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
[ weiyj.lk: missing unlock on error ]
Signed-off-by: NWei Yongjun <weiyj.lk@gmail.com>
      6b1e6cc7