netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [RFC,net-next] tcp: add support for read with offset when using MSG_PEEK
@ 2024-01-15 21:51 Martin Zaharinov
  2024-01-15 22:41 ` Jon Maloy
  0 siblings, 1 reply; 13+ messages in thread
From: Martin Zaharinov @ 2024-01-15 21:51 UTC (permalink / raw)
  To: jmaloy; +Cc: netdev

Hi Jon

After apply the patch on kernel 6.7.0 system hang with this bug report : 


Jan 15 22:27:39 6.7.0,1,863,194879739,-,caller=T3523;BUG: unable to handle page fault for address: 00007fff333174e0
Jan 15 22:27:39 6.7.0,1,864,194879876,-,caller=T3523;#PF: supervisor read access in kernel mode
Jan 15 22:27:39 6.7.0,1,865,194879976,-,caller=T3523;#PF: error_code(0x0001) - permissions violation
Jan 15 22:27:39 6.7.0,6,866,194880075,-,caller=T3523;PGD 107cbd067 P4D 107cbd067 PUD 22055d067 PMD 10a384067 PTE 8000000228b00067
Jan 15 22:27:39 6.7.0,4,867,194880202,-,caller=T3523;Oops: 0001 [#1] SMP
Jan 15 22:27:39 6.7.0,4,868,194880297,-,caller=T3523;CPU: 12 PID: 3523 Comm: server-nft Tainted: G           O       6.7.0 #1
Jan 15 22:27:39 6.7.0,4,869,194880420,-,caller=T3523;Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./EP2C612D8, BIOS P2.30 04/30/2018
Jan 15 22:27:39 6.7.0,4,870,194880547,-,caller=T3523;RIP: 0010:tcp_recvmsg_locked+0x498/0xea0
Jan 15 22:27:39 6.7.0,4,871,194880709,-,caller=T3523;Code: a3 07 00 00 80 fa 02 0f 84 88 07 00 00 84 d2 0f 84 f1 04 00 00 41 8b 8c 24 d8 05 00 00 49 8b 53 20 4c 8d 7c 24 44 89 4c 24 44 <48> 83 3a 00 0f 85 e5 fb ff ff 49 8b 73 30 48 83 fe 01 0f 86 c4 04
Jan 15 22:27:39 6.7.0,4,872,194880876,-,caller=T3523;RSP: 0018:ffffa47b01307d00 EFLAGS: 00010202
Jan 15 22:27:39 6.7.0,4,873,194880975,-,caller=T3523;RAX: 0000000000000002 RBX: ffff8cf8c3209800 RCX: 00000000a87ac03c
Jan 15 22:27:39 6.7.0,4,874,194881096,-,caller=T3523;RDX: 00007fff333174e0 RSI: ffffa47b01307e18 RDI: ffff8cf8c3209800
Jan 15 22:27:39 6.7.0,4,875,194881217,-,caller=T3523;RBP: ffffa47b01307d78 R08: ffffa47b01307d90 R09: ffffa47b01307d8c
Jan 15 22:27:39 6.7.0,4,876,194881338,-,caller=T3523;R10: 0000000000000002 R11: ffffa47b01307e18 R12: ffff8cf8c3209800
Jan 15 22:27:39 6.7.0,4,877,194881458,-,caller=T3523;R13: 0000000000000000 R14: 0000000000000000 R15: ffffa47b01307d44
Jan 15 22:27:39 6.7.0,4,878,194881579,-,caller=T3523;FS:  00007f4941b0ad80(0000) GS:ffff8d001f900000(0000) knlGS:0000000000000000
Jan 15 22:27:39 6.7.0,4,879,194881703,-,caller=T3523;CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Jan 15 22:27:39 6.7.0,4,880,194881802,-,caller=T3523;CR2: 00007fff333174e0 CR3: 000000010df04002 CR4: 00000000003706f0
Jan 15 22:27:39 6.7.0,4,881,194881922,-,caller=T3523;DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
Jan 15 22:27:39 6.7.0,4,882,194882043,-,caller=T3523;DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Jan 15 22:27:39 6.7.0,4,883,194882164,-,caller=T3523;Call Trace:
Jan 15 22:27:39 6.7.0,4,884,194882257,-,caller=T3523; <TASK>
Jan 15 22:27:39 6.7.0,4,885,194882347,-,caller=T3523; ? __die+0xe4/0xf0
Jan 15 22:27:39 6.7.0,4,886,194882442,-,caller=T3523; ? page_fault_oops+0x144/0x3e0
Jan 15 22:27:39 6.7.0,4,887,194882539,-,caller=T3523; ? zap_pte_range+0x6a4/0xdc0
Jan 15 22:27:39 6.7.0,4,888,194882638,-,caller=T3523; ? exc_page_fault+0x5d/0xa0
Jan 15 22:27:39 6.7.0,4,889,194882736,-,caller=T3523; ? asm_exc_page_fault+0x22/0x30
Jan 15 22:27:39 6.7.0,4,890,194882834,-,caller=T3523; ? tcp_recvmsg_locked+0x498/0xea0
Jan 15 22:27:39 6.7.0,4,891,194882931,-,caller=T3523; ? __call_rcu_common.constprop.0+0xbc/0x770
Jan 15 22:27:39 6.7.0,4,892,194883031,-,caller=T3523; ? rcu_nocb_flush_bypass.part.0+0xec/0x120
Jan 15 22:27:39 6.7.0,4,893,194883133,-,caller=T3523; tcp_recvmsg+0x5c/0x1e0
Jan 15 22:27:39 6.7.0,4,894,194883228,-,caller=T3523; inet_recvmsg+0x2a/0x90
Jan 15 22:27:39 6.7.0,4,895,194883325,-,caller=T3523; __sys_recvfrom+0x15e/0x200
Jan 15 22:27:39 6.7.0,4,896,194883423,-,caller=T3523; ? wait_task_zombie+0xee/0x410
Jan 15 22:27:39 6.7.0,4,897,194883539,-,caller=T3523; ? remove_wait_queue+0x1b/0x60
Jan 15 22:27:39 6.7.0,4,898,194883635,-,caller=T3523; ? do_wait+0x93/0xa0
Jan 15 22:27:39 6.7.0,4,899,194883729,-,caller=T3523; ? __x64_sys_poll+0xa7/0x170
Jan 15 22:27:39 6.7.0,4,900,194883825,-,caller=T3523; __x64_sys_recvfrom+0x1b/0x20
Jan 15 22:27:39 6.7.0,4,901,194883921,-,caller=T3523; do_syscall_64+0x2c/0xa0
Jan 15 22:27:39 6.7.0,4,902,194884018,-,caller=T3523; entry_SYSCALL_64_after_hwframe+0x46/0x4e
Jan 15 22:27:39 6.7.0,4,903,194884116,-,caller=T3523;RIP: 0033:0x7f4941fe92a9
Jan 15 22:27:39 6.7.0,4,904,194884210,-,caller=T3523;Code: 0c 00 64 c7 02 02 00 00 00 eb bf 66 0f 1f 44 00 00 80 3d a9 e0 0c 00 00 41 89 ca 74 1c 45 31 c9 45 31 c0 b8 2d 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 67 c3 66 0f 1f 44 00 00 55 48 83 ec 20 48 89
Jan 15 22:27:39 6.7.0,4,905,194884377,-,caller=T3523;RSP: 002b:00007fff33317468 EFLAGS: 00000246 ORIG_RAX: 000000000000002d
Jan 15 22:27:39 6.7.0,4,906,194884499,-,caller=T3523;RAX: ffffffffffffffda RBX: 00007fff333174e0 RCX: 00007f4941fe92a9
Jan 15 22:27:39 6.7.0,4,907,194884620,-,caller=T3523;RDX: 0000000000000001 RSI: 00007fff333174e0 RDI: 0000000000000005
Jan 15 22:27:39 6.7.0,4,908,194884740,-,caller=T3523;RBP: 00007fff33317550 R08: 0000000000000000 R09: 0000000000000000
Jan 15 22:27:39 6.7.0,4,909,194884860,-,caller=T3523;R10: 0000000000000002 R11: 0000000000000246 R12: 0000000000000000
Jan 15 22:27:39 6.7.0,4,910,194884980,-,caller=T3523;R13: 0000000000000000 R14: 0000000000000000 R15: 00007f49418850a0
Jan 15 22:27:39 6.7.0,4,911,194885101,-,caller=T3523; </TASK>
Jan 15 22:27:39 6.7.0,4,912,194885191,-,caller=T3523;Modules linked in: nft_limit pppoe pppox ppp_generic slhc nft_ct nft_nat nft_chain_nat nf_tables netconsole coretemp bonding igb i2c_algo_bit i40e ixgbe mdio nf_nat_sip nf_conntrack_sip nf_nat_pptp nf_conntrack_pptp nf_nat_tftp nf_conntrack_tftp nf_nat_ftp nf_conntrack_ftp nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ipmi_si ipmi_devintf ipmi_msghandler rtc_cmos aesni_intel crypto_simd cryptd
Jan 15 22:27:39 6.7.0,4,913,194885507,-,caller=T3523;CR2: 00007fff333174e0
Jan 15 22:27:39 6.7.0,4,914,194885602,-,caller=T3523;---[ end trace 0000000000000000 ]---
Jan 15 22:27:39 6.7.0,4,915,194885698,-,caller=T3523;RIP: 0010:tcp_recvmsg_locked+0x498/0xea0
Jan 15 22:27:39 6.7.0,4,916,194885797,-,caller=T3523;Code: a3 07 00 00 80 fa 02 0f 84 88 07 00 00 84 d2 0f 84 f1 04 00 00 41 8b 8c 24 d8 05 00 00 49 8b 53 20 4c 8d 7c 24 44 89 4c 24 44 <48> 83 3a 00 0f 85 e5 fb ff ff 49 8b 73 30 48 83 fe 01 0f 86 c4 04
Jan 15 22:27:39 6.7.0,4,917,194887079,-,caller=T3523;RSP: 0018:ffffa47b01307d00 EFLAGS: 00010202
Jan 15 22:27:39 6.7.0,4,918,194887177,-,caller=T3523;RAX: 0000000000000002 RBX: ffff8cf8c3209800 RCX: 00000000a87ac03c
Jan 15 22:27:39 6.7.0,4,919,194887298,-,caller=T3523;RDX: 00007fff333174e0 RSI: ffffa47b01307e18 RDI: ffff8cf8c3209800
Jan 15 22:27:39 6.7.0,4,920,194887418,-,caller=T3523;RBP: ffffa47b01307d78 R08: ffffa47b01307d90 R09: ffffa47b01307d8c
Jan 15 22:27:39 6.7.0,4,921,194887538,-,caller=T3523;R10: 0000000000000002 R11: ffffa47b01307e18 R12: ffff8cf8c3209800
Jan 15 22:27:39 6.7.0,4,922,194887658,-,caller=T3523;R13: 0000000000000000 R14: 0000000000000000 R15: ffffa47b01307d44
Jan 15 22:27:39 6.7.0,4,923,194887779,-,caller=T3523;FS:  00007f4941b0ad80(0000) GS:ffff8d001f900000(0000) knlGS:0000000000000000
Jan 15 22:27:39 6.7.0,4,924,194887901,-,caller=T3523;CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Jan 15 22:27:39 6.7.0,4,925,194888000,-,caller=T3523;CR2: 00007fff333174e0 CR3: 000000010df04002 CR4: 00000000003706f0
Jan 15 22:27:39 6.7.0,4,926,194888120,-,caller=T3523;DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
Jan 15 22:27:39 6.7.0,4,927,194888240,-,caller=T3523;DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Jan 15 22:27:39 6.7.0,0,928,194888360,-,caller=T3523;Kernel panic - not syncing: Fatal exception
Jan 15 22:27:40 6.7.0,0,929,195391096,-,caller=T3523;Kernel Offset: 0x1f000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
Jan 15 22:27:40 6.7.0,0,930,195391224,-,caller=T3523;Rebooting in 10 seconds..



m.

^ permalink raw reply	[flat|nested] 13+ messages in thread
* [RFC net-next] tcp: add support for read with offset when using MSG_PEEK
@ 2024-01-11 23:00 jmaloy
  2024-01-16 10:49 ` Paolo Abeni
  0 siblings, 1 reply; 13+ messages in thread
From: jmaloy @ 2024-01-11 23:00 UTC (permalink / raw)
  To: netdev, davem; +Cc: kuba, passt-dev, jmaloy, sbrivio, lvivier, dgibson

From: Jon Maloy <jmaloy@redhat.com>

When reading received messages from a socket with MSG_PEEK, we may want
to read the contents with an offset, like we can do with pread/preadv()
when reading files. Currently, it is not possible to do that.

In this commit, we allow the user to set iovec.iov_base in the first
vector entry to NULL. This tells the socket to skip the first entry,
hence letting the iov_len field of that entry indicate the offset value.
This way, there is no need to add any new arguments or flags.

In the iperf3 log examples shown below, we can observe a throughput
improvement of ~15 % in the direction host->namespace when using the
protocol splicer 'pasta' (https://passt.top).
This is a consistent result.

pasta(1) and passt(1) implement user-mode networking for network
namespaces (containers) and virtual machines by means of a translation
layer between Layer-2 network interface and native Layer-4 sockets
(TCP, UDP, ICMP/ICMPv6 echo).

Received, pending TCP data to the container/guest is kept in kernel
buffers until acknowledged, so the tool routinely needs to fetch new
data from socket, skipping data that was already sent.

At the moment this is implemented using a dummy buffer passed to
recvmsg(). With this change, we don't need a dummy buffer and the
related buffer copy (copy_to_user()) anymore.

passt and pasta are supported in KubeVirt and libvirt/qemu.

jmaloy@freyr:~/passt$ perf record -g ./pasta --config-net -f
MSG_PEEK with offset not supported by kernel.

jmaloy@freyr:~/passt# iperf3 -s
-----------------------------------------------------------
Server listening on 5201 (test #1)
-----------------------------------------------------------
Accepted connection from 192.168.122.1, port 44822
[  5] local 192.168.122.180 port 5201 connected to 192.168.122.1 port 44832
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-1.00   sec  1.02 GBytes  8.78 Gbits/sec
[  5]   1.00-2.00   sec  1.06 GBytes  9.08 Gbits/sec
[  5]   2.00-3.00   sec  1.07 GBytes  9.15 Gbits/sec
[  5]   3.00-4.00   sec  1.10 GBytes  9.46 Gbits/sec
[  5]   4.00-5.00   sec  1.03 GBytes  8.85 Gbits/sec
[  5]   5.00-6.00   sec  1.10 GBytes  9.44 Gbits/sec
[  5]   6.00-7.00   sec  1.11 GBytes  9.56 Gbits/sec
[  5]   7.00-8.00   sec  1.07 GBytes  9.20 Gbits/sec
[  5]   8.00-9.00   sec   667 MBytes  5.59 Gbits/sec
[  5]   9.00-10.00  sec  1.03 GBytes  8.83 Gbits/sec
[  5]  10.00-10.04  sec  30.1 MBytes  6.36 Gbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-10.04  sec  10.3 GBytes  8.78 Gbits/sec   receiver
-----------------------------------------------------------
Server listening on 5201 (test #2)
-----------------------------------------------------------
^Ciperf3: interrupt - the server has terminated
jmaloy@freyr:~/passt#
logout
[ perf record: Woken up 23 times to write data ]
[ perf record: Captured and wrote 5.696 MB perf.data (35580 samples) ]
jmaloy@freyr:~/passt$

jmaloy@freyr:~/passt$ perf record -g ./pasta --config-net -f
MSG_PEEK with offset supported by kernel.

jmaloy@freyr:~/passt# iperf3 -s
-----------------------------------------------------------
Server listening on 5201 (test #1)
-----------------------------------------------------------
Accepted connection from 192.168.122.1, port 40854
[  5] local 192.168.122.180 port 5201 connected to 192.168.122.1 port 40862
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-1.00   sec  1.22 GBytes  10.5 Gbits/sec
[  5]   1.00-2.00   sec  1.19 GBytes  10.2 Gbits/sec
[  5]   2.00-3.00   sec  1.22 GBytes  10.5 Gbits/sec
[  5]   3.00-4.00   sec  1.11 GBytes  9.56 Gbits/sec
[  5]   4.00-5.00   sec  1.20 GBytes  10.3 Gbits/sec
[  5]   5.00-6.00   sec  1.14 GBytes  9.80 Gbits/sec
[  5]   6.00-7.00   sec  1.17 GBytes  10.0 Gbits/sec
[  5]   7.00-8.00   sec  1.12 GBytes  9.61 Gbits/sec
[  5]   8.00-9.00   sec  1.13 GBytes  9.74 Gbits/sec
[  5]   9.00-10.00  sec  1.26 GBytes  10.8 Gbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-10.04  sec  11.8 GBytes  10.1 Gbits/sec   receiver
-----------------------------------------------------------
Server listening on 5201 (test #2)
-----------------------------------------------------------
^Ciperf3: interrupt - the server has terminated
logout
[ perf record: Woken up 20 times to write data ]
[ perf record: Captured and wrote 5.040 MB perf.data (33411 samples) ]
jmaloy@freyr:~/passt$

The perf record confirms this result. Below, we can observe that the
CPU spends significantly less time in the function ____sys_recvmsg()
when we have offset support.

Without offset support:
----------------------
jmaloy@freyr:~/passt$ perf report -q --symbol-filter=do_syscall_64 -p ____sys_recvmsg -x --stdio -i  perf.data | head -1
    46.32%     0.00%  passt.avx2  [kernel.vmlinux]  [k] do_syscall_64  ____sys_recvmsg

With offset support:
----------------------
jmaloy@freyr:~/passt$ perf report -q --symbol-filter=do_syscall_64 -p ____sys_recvmsg -x --stdio -i  perf.data | head -1
   27.24%     0.00%  passt.avx2  [kernel.vmlinux]  [k] do_syscall_64  ____sys_recvmsg

Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
 net/ipv4/tcp.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1baa484d2190..82e1da3f0f98 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2351,6 +2351,20 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	if (flags & MSG_PEEK) {
 		peek_seq = tp->copied_seq;
 		seq = &peek_seq;
+		if (!msg->msg_iter.__iov[0].iov_base) {
+			size_t peek_offset;
+
+			if (msg->msg_iter.nr_segs < 2) {
+				err = -EINVAL;
+				goto out;
+			}
+			peek_offset = msg->msg_iter.__iov[0].iov_len;
+			msg->msg_iter.__iov = &msg->msg_iter.__iov[1];
+			msg->msg_iter.nr_segs -= 1;
+			msg->msg_iter.count -= peek_offset;
+			len -= peek_offset;
+			*seq += peek_offset;
+		}
 	}
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
-- 
2.42.0


^ permalink raw reply related	[flat|nested] 13+ messages in thread
* [RFC net-next] tcp: add support for read with offset when using MSG_PEEK
@ 2024-01-11 22:22 jmaloy
  0 siblings, 0 replies; 13+ messages in thread
From: jmaloy @ 2024-01-11 22:22 UTC (permalink / raw)
  To: netdev, davem; +Cc: kuba, passt-dev, jmaloy, sbrivio, lvivier, dgibson

From: Jon Maloy <jmaloy@redhat.com>

When reading received messages with MSG_PEEK, we sometines have to read
the leading bytes of the stream several times, only to reach the bytes
we really want. This is clearly non-optimal.

What we would want is something similar to pread/preadv(), but working
even for tcp sockets. At the same time, we don't want to add any new
arguments to the recv/recvmsg() calls.

In this commit, we allow the user to set iovec.iov_base in the first
vector entry to NULL. This tells the socket to skip the first entry,
hence letting the iov_len field of that entry indicate the offset value.
This way, there is no need to add any new arguments or flags.

In the iperf3 logs examples shown below, we can observe a throughput
improvement of ~20 % in the direction host->namespace when using the
protocol splicer 'passt'. This is a consistent result.

$ ./passt/passt/pasta --config-net  -f
MSG_PEEK with offset not supported.
[root@fedora37 ~]# perf record iperf3 -s
-----------------------------------------------------------
Server listening on 5201 (test #1)
-----------------------------------------------------------
Accepted connection from 192.168.122.1, port 60344
[  6] local 192.168.122.163 port 5201 connected to 192.168.122.1 port 60360
[ ID] Interval           Transfer     Bitrate
{...]
[  6]  13.00-14.00  sec  2.54 GBytes  21.8 Gbits/sec
[  6]  14.00-15.00  sec  2.52 GBytes  21.7 Gbits/sec
[  6]  15.00-16.00  sec  2.50 GBytes  21.5 Gbits/sec
[  6]  16.00-17.00  sec  2.49 GBytes  21.4 Gbits/sec
[  6]  17.00-18.00  sec  2.51 GBytes  21.6 Gbits/sec
[  6]  18.00-19.00  sec  2.48 GBytes  21.3 Gbits/sec
[  6]  19.00-20.00  sec  2.49 GBytes  21.4 Gbits/sec
[  6]  20.00-20.04  sec  87.4 MBytes  19.2 Gbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate
[  6]   0.00-20.04  sec  48.9 GBytes  21.0 Gbits/sec receiver
-----------------------------------------------------------

[jmaloy@fedora37 ~]$ ./passt/passt/pasta --config-net  -f
MSG_PEEK with offset supported.
[root@fedora37 ~]# perf record iperf3 -s
-----------------------------------------------------------
Server listening on 5201 (test #1)
-----------------------------------------------------------
Accepted connection from 192.168.122.1, port 46362
[  6] local 192.168.122.163 port 5201 connected to 192.168.122.1 port 46374
[ ID] Interval           Transfer     Bitrate
[...]
[  6]  12.00-13.00  sec  3.18 GBytes  27.3 Gbits/sec
[  6]  13.00-14.00  sec  3.17 GBytes  27.3 Gbits/sec
[  6]  14.00-15.00  sec  3.13 GBytes  26.9 Gbits/sec
[  6]  15.00-16.00  sec  3.17 GBytes  27.3 Gbits/sec
[  6]  16.00-17.00  sec  3.17 GBytes  27.2 Gbits/sec
[  6]  17.00-18.00  sec  3.14 GBytes  27.0 Gbits/sec
[  6]  18.00-19.00  sec  3.17 GBytes  27.2 Gbits/sec
[  6]  19.00-20.00  sec  3.12 GBytes  26.8 Gbits/sec
[  6]  20.00-20.04  sec   119 MBytes  25.5 Gbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate
[  6]   0.00-20.04  sec  59.4 GBytes  25.4 Gbits/sec receiver
-----------------------------------------------------------

Passt is used to support VMs in containers, such as KubeVirt, and
is also generally supported in libvirt/QEMU since release 9.2 / 7.2.

Signed-off-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Jon Paul Maloy <jmaloy@redhat.com>
---
 net/ipv4/tcp.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 53bcc17c91e4..e9d3b5bf2f66 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2310,6 +2310,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 			      int *cmsg_flags)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	size_t peek_offset;
 	int copied = 0;
 	u32 peek_seq;
 	u32 *seq;
@@ -2353,6 +2354,20 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	if (flags & MSG_PEEK) {
 		peek_seq = tp->copied_seq;
 		seq = &peek_seq;
+		if (!msg->msg_iter.__iov[0].iov_base) {
+			peek_offset = msg->msg_iter.__iov[0].iov_len;
+			msg->msg_iter.__iov = &msg->msg_iter.__iov[1];
+			if (msg->msg_iter.nr_segs <= 1)
+				goto out;
+			msg->msg_iter.nr_segs -= 1;
+			if (msg->msg_iter.count <= peek_offset)
+				goto out;
+			msg->msg_iter.count -= peek_offset;
+			if (len <= peek_offset)
+				goto out;
+			len -= peek_offset;
+			*seq += peek_offset;
+		}
 	}
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
-- 
2.39.0


^ permalink raw reply related	[flat|nested] 13+ messages in thread
end of thread, other threads:[~2024-01-28 18:52 UTC | newest]

Thread overview: 13+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-01-15 21:51 [RFC,net-next] tcp: add support for read with offset when using MSG_PEEK Martin Zaharinov
2024-01-15 22:41 ` Jon Maloy
2024-01-16  4:59   ` Martin Zaharinov
2024-01-17 16:33     ` Jon Maloy
2024-01-17 17:11       ` Martin Zaharinov
2024-01-26 15:01       ` Martin Zaharinov
2024-01-28 18:52         ` Jon Maloy
  -- strict thread matches above, loose matches on Subject: below --
2024-01-11 23:00 [RFC net-next] " jmaloy
2024-01-16 10:49 ` Paolo Abeni
2024-01-18 22:22   ` Jon Maloy
2024-01-21 22:16     ` Stefano Brivio
2024-01-22 16:22       ` Jon Maloy
2024-01-11 22:22 jmaloy

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).