linux.git/net/smc, branch v6.5

net/smc: Use correct buffer sizes when switching between TCP and SMC

2023-08-09T10:20:29+00:00

Tuning of the effective buffer size through setsockopts was working for
SMC traffic only but not for TCP fall-back connections even before
commit 0227f058aa29 ("net/smc: Unbind r/w buffer size from clcsock and
make them tunable"). That change made it apparent that TCP fall-back
connections would use net.smc.[rw]mem as buffer size instead of
net.ipv4_tcp_[rw]mem.

Amend the code that copies attributes between the (TCP) clcsock and the
SMC socket and adjust buffer sizes appropriately:
- Copy over sk_userlocks so that both sockets agree on whether tuning
  via setsockopt is active.
- When falling back to TCP use sk_sndbuf or sk_rcvbuf as specified with
  setsockopt. Otherwise, use the sysctl value for TCP/IPv4.
- Likewise, use either values from setsockopt or from sysctl for SMC
  (duplicated) on successful SMC connect.

In smc_tcp_listen_work() drop the explicit copy of buffer sizes as that
is taken care of by the attribute copy.

Fixes: 0227f058aa29 ("net/smc: Unbind r/w buffer size from clcsock and make them tunable")
Reviewed-by: Wenjia Zhang 
Reviewed-by: Tony Lu 
Signed-off-by: Gerd Bayer 
Signed-off-by: David S. Miller

net/smc: Fix setsockopt and sysctl to specify same buffer size again

2023-08-09T10:20:28+00:00

Commit 0227f058aa29 ("net/smc: Unbind r/w buffer size from clcsock
and make them tunable") introduced the net.smc.rmem and net.smc.wmem
sysctls to specify the size of buffers to be used for SMC type
connections. This created a regression for users that specified the
buffer size via setsockopt() as the effective buffer size was now
doubled.

Re-introduce the division by 2 in the SMC buffer create code and level
this out by duplicating the net.smc.[rw]mem values used for initializing
sk_rcvbuf/sk_sndbuf at socket creation time. This gives users of both
methods (setsockopt or sysctl) the effective buffer size that they
expect.

Initialize net.smc.[rw]mem from its own constant of 64kB, respectively.
Internal performance tests show that this value is a good compromise
between throughput/latency and memory consumption. Also, this decouples
it from any tuning that was done to net.ipv4.tcp_[rw]mem[1] before the
module for SMC protocol was loaded. Check that no more than INT_MAX / 2
is assigned to net.smc.[rw]mem, in order to avoid any overflow condition
when that is doubled for use in sk_sndbuf or sk_rcvbuf.

While at it, drop the confusing sk_buf_size variable from
__smc_buf_create and name "compressed" buffer size variables more
consistently.

Background:

Before the commit mentioned above, SMC's buffer allocator in
__smc_buf_create() always used half of the sockets' sk_rcvbuf/sk_sndbuf
value as initial value to search for appropriate buffers. If the search
resorted to using a bigger buffer when all buffers of the specified
size were busy, the duplicate of the used effective buffer size is
stored back to sk_rcvbuf/sk_sndbuf.

When available, buffers of exactly the size that a user had specified as
input to setsockopt() were used, despite setsockopt()'s documentation in
"man 7 socket" talking of a mandatory duplication:

[...]
SO_SNDBUF
Sets or gets the maximum socket send buffer in bytes.
The kernel doubles this value (to allow space for book‐
keeping overhead) when it is set using setsockopt(2),
and this doubled value is returned by getsockopt(2).
The default value is set by the
/proc/sys/net/core/wmem_default file and the maximum
allowed value is set by the /proc/sys/net/core/wmem_max
file. The minimum (doubled) value for this option is
2048.
[...]

Fixes: 0227f058aa29 ("net/smc: Unbind r/w buffer size from clcsock and make them tunable")
Co-developed-by: Jan Karcher
Signed-off-by: Jan Karcher
Reviewed-by: Wenjia Zhang
Reviewed-by: Tony Lu
Signed-off-by: Gerd Bayer
Signed-off-by: David S. Miller

net: annotate data-races around sk->sk_mark

2023-07-29T17:13:41+00:00

sk->sk_mark is often read while another thread could change the value.

Fixes: 4a19ec5800fc ("[NET]: Introducing socket mark socket option.")
Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

smc: Drop smc_sendpage() in favour of smc_sendmsg() + MSG_SPLICE_PAGES

2023-06-24T22:50:12+00:00

Drop the smc_sendpage() code as smc_sendmsg() just passes the call down to
the underlying TCP socket and smc_tx_sendpage() is just a wrapper around
its sendmsg implementation.

Signed-off-by: David Howells 
cc: Karsten Graul 
cc: Wenjia Zhang 
cc: Jan Karcher 
cc: "D. Wythe" 
cc: Tony Lu 
cc: Wen Gu 
cc: Jens Axboe 
cc: Matthew Wilcox 
Link: https://lore.kernel.org/r/20230623225513.2732256-10-dhowells@redhat.com
Signed-off-by: Jakub Kicinski

tcp_bpf, smc, tls, espintcp, siw: Reduce MSG_SENDPAGE_NOTLAST usage

2023-06-24T22:50:12+00:00

As MSG_SENDPAGE_NOTLAST is being phased out along with sendpage(), don't
use it further in than the sendpage methods, but rather translate it to
MSG_MORE and use that instead.

Signed-off-by: David Howells 
cc: Willem de Bruijn 
cc: Bernard Metzler 
cc: Jason Gunthorpe 
cc: Leon Romanovsky 
cc: John Fastabend 
cc: Jakub Sitnicki 
cc: David Ahern 
cc: Karsten Graul 
cc: Wenjia Zhang 
cc: Jan Karcher 
cc: "D. Wythe" 
cc: Tony Lu 
cc: Wen Gu 
cc: Boris Pismenny 
cc: Steffen Klassert 
cc: Herbert Xu 
Link: https://lore.kernel.org/r/20230623225513.2732256-2-dhowells@redhat.com
Signed-off-by: Jakub Kicinski

net/smc: Avoid to access invalid RMBs' MRs in SMCRv1 ADD LINK CONT

2023-06-03T19:51:04+00:00

SMCRv1 has a similar issue to SMCRv2 (see link below) that may access
invalid MRs of RMBs when construct LLC ADD LINK CONT messages.

 BUG: kernel NULL pointer dereference, address: 0000000000000014
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: 0000 [#1] PREEMPT SMP PTI
 CPU: 5 PID: 48 Comm: kworker/5:0 Kdump: loaded Tainted: G W   E      6.4.0-rc3+ #49
 Workqueue: events smc_llc_add_link_work [smc]
 RIP: 0010:smc_llc_add_link_cont+0x160/0x270 [smc]
 RSP: 0018:ffffa737801d3d50 EFLAGS: 00010286
 RAX: ffff964f82144000 RBX: ffffa737801d3dd8 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff964f81370c30
 RBP: ffffa737801d3dd4 R08: ffff964f81370000 R09: ffffa737801d3db0
 R10: 0000000000000001 R11: 0000000000000060 R12: ffff964f82e70000
 R13: ffff964f81370c38 R14: ffffa737801d3dd3 R15: 0000000000000001
 FS:  0000000000000000(0000) GS:ffff9652bfd40000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000014 CR3: 000000008fa20004 CR4: 00000000003706e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 Call Trace:
  
  smc_llc_srv_rkey_exchange+0xa7/0x190 [smc]
  smc_llc_srv_add_link+0x3ae/0x5a0 [smc]
  smc_llc_add_link_work+0xb8/0x140 [smc]
  process_one_work+0x1e5/0x3f0
  worker_thread+0x4d/0x2f0
  ? __pfx_worker_thread+0x10/0x10
  kthread+0xe5/0x120
  ? __pfx_kthread+0x10/0x10
  ret_from_fork+0x2c/0x50
  

When an alernate RNIC is available in system, SMC will try to add a new
link based on the RNIC for resilience. All the RMBs in use will be mapped
to the new link. Then the RMBs' MRs corresponding to the new link will
be filled into LLC messages. For SMCRv1, they are ADD LINK CONT messages.

However smc_llc_add_link_cont() may mistakenly access to unused RMBs which
haven't been mapped to the new link and have no valid MRs, thus causing a
crash. So this patch fixes it.

Fixes: 87f88cda2128 ("net/smc: rkey processing for a new link as SMC client")
Link: https://lore.kernel.org/r/1685101741-74826-3-git-send-email-guwen@linux.alibaba.com
Signed-off-by: Wen Gu 
Reviewed-by: Wenjia Zhang 
Reviewed-by: Tony Lu 
Signed-off-by: David S. Miller

net/smc: Don't use RMBs not mapped to new link in SMCRv2 ADD LINK

2023-05-30T09:26:32+00:00

We encountered a crash when using SMCRv2. It is caused by a logical
error in smc_llc_fill_ext_v2().

 BUG: kernel NULL pointer dereference, address: 0000000000000014
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: 0000 [#1] PREEMPT SMP PTI
 CPU: 7 PID: 453 Comm: kworker/7:4 Kdump: loaded Tainted: G        W   E      6.4.0-rc3+ #44
 Workqueue: events smc_llc_add_link_work [smc]
 RIP: 0010:smc_llc_fill_ext_v2+0x117/0x280 [smc]
 RSP: 0018:ffffacb5c064bd88 EFLAGS: 00010282
 RAX: ffff9a6bc1c3c02c RBX: ffff9a6be3558000 RCX: 0000000000000000
 RDX: 0000000000000002 RSI: 0000000000000002 RDI: 000000000000000a
 RBP: ffffacb5c064bdb8 R08: 0000000000000040 R09: 000000000000000c
 R10: ffff9a6bc0910300 R11: 0000000000000002 R12: 0000000000000000
 R13: 0000000000000002 R14: ffff9a6bc1c3c02c R15: ffff9a6be3558250
 FS:  0000000000000000(0000) GS:ffff9a6eefdc0000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000014 CR3: 000000010b078003 CR4: 00000000003706e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 Call Trace:
  
  smc_llc_send_add_link+0x1ae/0x2f0 [smc]
  smc_llc_srv_add_link+0x2c9/0x5a0 [smc]
  ? cc_mkenc+0x40/0x60
  smc_llc_add_link_work+0xb8/0x140 [smc]
  process_one_work+0x1e5/0x3f0
  worker_thread+0x4d/0x2f0
  ? __pfx_worker_thread+0x10/0x10
  kthread+0xe5/0x120
  ? __pfx_kthread+0x10/0x10
  ret_from_fork+0x2c/0x50
  

When an alernate RNIC is available in system, SMC will try to add a new
link based on the RNIC for resilience. All the RMBs in use will be mapped
to the new link. Then the RMBs' MRs corresponding to the new link will be
filled into SMCRv2 LLC ADD LINK messages.

However, smc_llc_fill_ext_v2() mistakenly accesses to unused RMBs which
haven't been mapped to the new link and have no valid MRs, thus causing
a crash. So this patch fixes the logic.

Fixes: b4ba4652b3f8 ("net/smc: extend LLC layer for SMC-Rv2")
Signed-off-by: Wen Gu 
Signed-off-by: Paolo Abeni

net/smc: Scan from current RMB list when no position specified

2023-05-30T09:26:32+00:00

When finding the first RMB of link group, it should start from the
current RMB list whose index is 0. So fix it.

Fixes: b4ba4652b3f8 ("net/smc: extend LLC layer for SMC-Rv2")
Signed-off-by: Wen Gu 
Signed-off-by: Paolo Abeni

net/smc: Reset connection when trying to use SMCRv2 fails.

2023-05-19T07:54:04+00:00

We found a crash when using SMCRv2 with 2 Mellanox ConnectX-4. It
can be reproduced by:

- smc_run nginx
- smc_run wrk -t 32 -c 500 -d 30 http://:

 BUG: kernel NULL pointer dereference, address: 0000000000000014
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 8000000108713067 P4D 8000000108713067 PUD 151127067 PMD 0
 Oops: 0000 [#1] PREEMPT SMP PTI
 CPU: 4 PID: 2441 Comm: kworker/4:249 Kdump: loaded Tainted: G        W   E      6.4.0-rc1+ #42
 Workqueue: smc_hs_wq smc_listen_work [smc]
 RIP: 0010:smc_clc_send_confirm_accept+0x284/0x580 [smc]
 RSP: 0018:ffffb8294b2d7c78 EFLAGS: 00010a06
 RAX: ffff8f1873238880 RBX: ffffb8294b2d7dc8 RCX: 0000000000000000
 RDX: 00000000000000b4 RSI: 0000000000000001 RDI: 0000000000b40c00
 RBP: ffffb8294b2d7db8 R08: ffff8f1815c5860c R09: 0000000000000000
 R10: 0000000000000400 R11: 0000000000000000 R12: ffff8f1846f56180
 R13: ffff8f1815c5860c R14: 0000000000000001 R15: 0000000000000001
 FS:  0000000000000000(0000) GS:ffff8f1aefd00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000014 CR3: 00000001027a0001 CR4: 00000000003706e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 Call Trace:
  
  ? mlx5_ib_map_mr_sg+0xa1/0xd0 [mlx5_ib]
  ? smcr_buf_map_link+0x24b/0x290 [smc]
  ? __smc_buf_create+0x4ee/0x9b0 [smc]
  smc_clc_send_accept+0x4c/0xb0 [smc]
  smc_listen_work+0x346/0x650 [smc]
  ? __schedule+0x279/0x820
  process_one_work+0x1e5/0x3f0
  worker_thread+0x4d/0x2f0
  ? __pfx_worker_thread+0x10/0x10
  kthread+0xe5/0x120
  ? __pfx_kthread+0x10/0x10
  ret_from_fork+0x2c/0x50
  

During the CLC handshake, server sequentially tries available SMCRv2
and SMCRv1 devices in smc_listen_work().

If an SMCRv2 device is found. SMCv2 based link group and link will be
assigned to the connection. Then assumed that some buffer assignment
errors happen later in the CLC handshake, such as RMB registration
failure, server will give up SMCRv2 and try SMCRv1 device instead. But
the resources assigned to the connection won't be reset.

When server tries SMCRv1 device, the connection creation process will
be executed again. Since conn->lnk has been assigned when trying SMCRv2,
it will not be set to the correct SMCRv1 link in
smcr_lgr_conn_assign_link(). So in such situation, conn->lgr points to
correct SMCRv1 link group but conn->lnk points to the SMCRv2 link
mistakenly.

Then in smc_clc_send_confirm_accept(), conn->rmb_desc->mr[link->link_idx]
will be accessed. Since the link->link_idx is not correct, the related
MR may not have been initialized, so crash happens.

 | Try SMCRv2 device first
 |     |-> conn->lgr:	assign existed SMCRv2 link group;
 |     |-> conn->link:	assign existed SMCRv2 link (link_idx may be 1 in SMC_LGR_SYMMETRIC);
 |     |-> sndbuf & RMB creation fails, quit;
 |
 | Try SMCRv1 device then
 |     |-> conn->lgr:	create SMCRv1 link group and assign;
 |     |-> conn->link:	keep SMCRv2 link mistakenly;
 |     |-> sndbuf & RMB creation succeed, only RMB->mr[link_idx = 0]
 |         initialized.
 |
 | Then smc_clc_send_confirm_accept() accesses
 | conn->rmb_desc->mr[conn->link->link_idx, which is 1], then crash.
 v

This patch tries to fix this by cleaning conn->lnk before assigning
link. In addition, it is better to reset the connection and clean the
resources assigned if trying SMCRv2 failed in buffer creation or
registration.

Fixes: e49300a6bf62 ("net/smc: add listen processing for SMC-Rv2")
Link: https://lore.kernel.org/r/20220523055056.2078994-1-liuyacan@corp.netease.com/
Signed-off-by: Wen Gu 
Reviewed-by: Tony Lu 
Signed-off-by: David S. Miller

net: deal with most data-races in sk_wait_event()

2023-05-10T09:03:32+00:00

__condition is evaluated twice in sk_wait_event() macro.

First invocation is lockless, and reads can race with writes,
as spotted by syzbot.

BUG: KCSAN: data-race in sk_stream_wait_connect / tcp_disconnect

write to 0xffff88812d83d6a0 of 4 bytes by task 9065 on cpu 1:
tcp_disconnect+0x2cd/0xdb0
inet_shutdown+0x19e/0x1f0 net/ipv4/af_inet.c:911
__sys_shutdown_sock net/socket.c:2343 [inline]
__sys_shutdown net/socket.c:2355 [inline]
__do_sys_shutdown net/socket.c:2363 [inline]
__se_sys_shutdown+0xf8/0x140 net/socket.c:2361
__x64_sys_shutdown+0x31/0x40 net/socket.c:2361
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

read to 0xffff88812d83d6a0 of 4 bytes by task 9040 on cpu 0:
sk_stream_wait_connect+0x1de/0x3a0 net/core/stream.c:75
tcp_sendmsg_locked+0x2e4/0x2120 net/ipv4/tcp.c:1266
tcp_sendmsg+0x30/0x50 net/ipv4/tcp.c:1484
inet6_sendmsg+0x63/0x80 net/ipv6/af_inet6.c:651
sock_sendmsg_nosec net/socket.c:724 [inline]
sock_sendmsg net/socket.c:747 [inline]
__sys_sendto+0x246/0x300 net/socket.c:2142
__do_sys_sendto net/socket.c:2154 [inline]
__se_sys_sendto net/socket.c:2150 [inline]
__x64_sys_sendto+0x78/0x90 net/socket.c:2150
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd

value changed: 0x00000000 -> 0x00000068

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot 
Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller