We found a data corruption issue during testing of SMC-R on Redis
applications.
The benchmark has a low probability of reporting a strange error as
shown below.
"Error: Protocol error, got "\xe2" as reply type byte"
Finally, we found that the retrieved error data was as follows:
0xE2 0xD4 0xC3 0xD9 0x04 0x00 0x2C 0x20 0xA6 0x56 0x00 0x16 0x3E 0x0C
0xCB 0x04 0x02 0x01 0x00 0x00 0x20 0x00 0x00 0x00 0x00 0x00 0x00 0x00
0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0xE2
It is quite obvious that this is a SMC DECLINE message, which means that
the applications received SMC protocol message.
We found that this was caused by the following situations:
client server
¦ clc proposal
------------->
¦ clc accept
<-------------
¦ clc confirm
------------->
wait llc confirm
send llc confirm
¦failed llc confirm
¦ x------
(after 2s)timeout
wait llc confirm rsp
wait decline
(after 1s) timeout
(after 2s) timeout
¦ decline
-------------->
¦ decline
<--------------
As a result, a decline message was sent in the implementation, and this
message was read from TCP by the already-fallback connection.
This patch double the client timeout as 2x of the server value,
With this simple change, the Decline messages should never cross or
collide (during Confirm link timeout).
This issue requires an immediate solution, since the protocol updates
involve a more long-term solution.
Fixes: 0fb0b02bd6 ("net/smc: adapt SMC client code to use the LLC flow")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
W=1 builds now warn if module is built without a MODULE_DESCRIPTION().
Add descriptions to all the sock diag modules in one fell swoop.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Note that we always hold a reference to sock when attempting
to submit close_work. Therefore, if we have successfully
canceled close_work from pending, we MUST release that reference
to avoid potential leaks.
Fixes: 42bfba9eaa ("net/smc: immediate termination for SMCD link groups")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch re-fix the issues mentioned by commit 22a825c541
("net/smc: fix NULL sndbuf_desc in smc_cdc_tx_handler()").
Blocking sending message do solve the issues though, but it also
prevents the peer to receive the final message. Besides, in logic,
whether the sndbuf_desc is NULL or not have no impact on the processing
of cdc message sending.
Hence that, this patch allows the cdc message sending but to check the
sndbuf_desc with care in smc_cdc_tx_handler().
Fixes: 22a825c541 ("net/smc: fix NULL sndbuf_desc in smc_cdc_tx_handler()")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Considering scenario:
smc_cdc_rx_handler
__smc_release
sock_set_flag
smc_close_active()
sock_set_flag
__set_bit(DEAD) __set_bit(DONE)
Dues to __set_bit is not atomic, the DEAD or DONE might be lost.
if the DEAD flag lost, the state SMC_CLOSED will be never be reached
in smc_close_passive_work:
if (sock_flag(sk, SOCK_DEAD) &&
smc_close_sent_any_close(conn)) {
sk->sk_state = SMC_CLOSED;
} else {
/* just shutdown, but not yet closed locally */
sk->sk_state = SMC_APPFINCLOSEWAIT;
}
Replace sock_set_flags or __set_bit to set_bit will fix this problem.
Since set_bit is atomic.
Fixes: b38d732477 ("smc: socket closing and linkgroup cleanup")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the smc_listen_work(), if smc_listen_prfx_check() failed,
the real reason: SMC_CLC_DECL_DIFFPREFIX was dropped, and
SMC_CLC_DECL_NOSMCDEV was returned.
Althrough this is also kind of SMC_CLC_DECL_NOSMCDEV, but return
the real reason is much friendly for debugging.
Fixes: e49300a6bf ("net/smc: add listen processing for SMC-Rv2")
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Link: https://lore.kernel.org/r/20231012123729.29307-1-dust.li@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
If the netdevice is within a container and communicates externally
through network technologies such as VxLAN, we won't be able to find
routing information in the init_net namespace. To address this issue,
we need to add a struct net parameter to the smc_ib_find_route function.
This allow us to locate the routing information within the corresponding
net namespace, ensuring the correct completion of the SMC CLC interaction.
Fixes: e5c4744cfb ("net/smc: add SMC-Rv2 connection establishment")
Signed-off-by: Albert Huang <huangjie.albert@bytedance.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Link: https://lore.kernel.org/r/20231011074851.95280-1-huangjie.albert@bytedance.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Cross-merge networking fixes after downstream PR.
No conflicts.
Adjacent changes:
kernel/bpf/verifier.c
829955981c ("bpf: Fix verifier log for async callback return values")
a923819fb2 ("bpf: Treat first argument as return value for bpf_throw")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
SMC_STAT_PAYLOAD_SUB(_smc_stats, _tech, key, _len, _rc) will calculate
wrong bucket positions for payloads of exactly 4096 bytes and
(1 << (m + 12)) bytes, with m == SMC_BUF_MAX - 1.
Intended bucket distribution:
Assume l == size of payload, m == SMC_BUF_MAX - 1.
Bucket 0 : 0 < l <= 2^13
Bucket n, 1 <= n <= m-1 : 2^(n+12) < l <= 2^(n+13)
Bucket m : l > 2^(m+12)
Current solution:
_pos = fls64((l) >> 13)
[...]
_pos = (_pos < m) ? ((l == 1 << (_pos + 12)) ? _pos - 1 : _pos) : m
For l == 4096, _pos == -1, but should be _pos == 0.
For l == (1 << (m + 12)), _pos == m, but should be _pos == m - 1.
In order to avoid special treatment of these corner cases, the
calculation is adjusted. The new solution first subtracts the length by
one, and then calculates the correct bucket by shifting accordingly,
i.e. _pos = fls64((l - 1) >> 13), l > 0.
This not only fixes the issues named above, but also makes the whole
bucket assignment easier to follow.
Same is done for SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _len),
where the calculation of the bucket position is similar to the one
named above.
Fixes: e0e4b8fa53 ("net/smc: Add SMC statistics support")
Suggested-by: Halil Pasic <pasic@linux.ibm.com>
Signed-off-by: Nils Hoppmann <niho@linux.ibm.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When the SMC protocol is built into the kernel proper while ISM is
configured to be built as module, linking the kernel fails due to
unresolved dependencies out of net/smc/smc_ism.o to
ism_get_smcd_ops, ism_register_client, and ism_unregister_client
as reported via the linux-next test automation (see link).
This however is a bug introduced a while ago.
Correct the dependency list in ISM's and SMC's Kconfig to reflect the
dependencies that are actually inverted. With this you cannot build a
kernel with CONFIG_SMC=y and CONFIG_ISM=m. Either ISM needs to be 'y',
too - or a 'n'. That way, SMC can still be configured on non-s390
architectures that do not have (nor need) an ISM driver.
Fixes: 89e7d2ba61 ("net/ism: Add new API for client registration")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Closes: https://lore.kernel.org/linux-next/d53b5b50-d894-4df8-8969-fd39e63440ae@infradead.org/
Co-developed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: Gerd Bayer <gbayer@linux.ibm.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Simon Horman <horms@kernel.org> # build-tested
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Link: https://lore.kernel.org/r/20231006125847.1517840-1-gbayer@linux.ibm.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This is a followup of 8bf43be799 ("net: annotate data-races
around sk->sk_priority").
sk->sk_priority can be read and written without holding the socket lock.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the macro SMC_STAT_SERV_SUCC_INC, the smcd_version is used
to determin whether to increase the v1 statistic or the v2
statistic. It is correct for SMCD. But for SMCR, smcr_version
should be used.
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Long ago we set out to remove the kitchen sink on kernel/sysctl.c arrays and
placings sysctls to their own sybsystem or file to help avoid merge conflicts.
Matthew Wilcox pointed out though that if we're going to do that we might as
well also *save* space while at it and try to remove the extra last sysctl
entry added at the end of each array, a sentintel, instead of bloating the
kernel by adding a new sentinel with each array moved.
Doing that was not so trivial, and has required slowing down the moves of
kernel/sysctl.c arrays and measuring the impact on size by each new move.
The complex part of the effort to help reduce the size of each sysctl is being
done by the patient work of el señor Don Joel Granados. A lot of this is truly
painful code refactoring and testing and then trying to measure the savings of
each move and removing the sentinels. Although Joel already has code which does
most of this work, experience with sysctl moves in the past shows is we need to
be careful due to the slew of odd build failures that are possible due to the
amount of random Kconfig options sysctls use.
To that end Joel's work is split by first addressing the major housekeeping
needed to remove the sentinels, which is part of this merge request. The rest
of the work to actually remove the sentinels will be done later in future
kernel releases.
At first I was only going to send his first 7 patches of his patch series,
posted 1 month ago, but in retrospect due to the testing the changes have
received in linux-next and the minor changes they make this goes with the
entire set of patches Joel had planned: just sysctl house keeping. There are
networking changes but these are part of the house keeping too.
The preliminary math is showing this will all help reduce the overall build
time size of the kernel and run time memory consumed by the kernel by about
~64 bytes per array where we are able to remove each sentinel in the future.
That also means there is no more bloating the kernel with the extra ~64 bytes
per array moved as no new sentinels are created.
Most of this has been in linux-next for about a month, the last 7 patches took
a minor refresh 2 week ago based on feedback.
-----BEGIN PGP SIGNATURE-----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=sq2p
-----END PGP SIGNATURE-----
Merge tag 'sysctl-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux
Pull sysctl updates from Luis Chamberlain:
"Long ago we set out to remove the kitchen sink on kernel/sysctl.c
arrays and placings sysctls to their own sybsystem or file to help
avoid merge conflicts. Matthew Wilcox pointed out though that if we're
going to do that we might as well also *save* space while at it and
try to remove the extra last sysctl entry added at the end of each
array, a sentintel, instead of bloating the kernel by adding a new
sentinel with each array moved.
Doing that was not so trivial, and has required slowing down the moves
of kernel/sysctl.c arrays and measuring the impact on size by each new
move.
The complex part of the effort to help reduce the size of each sysctl
is being done by the patient work of el señor Don Joel Granados. A lot
of this is truly painful code refactoring and testing and then trying
to measure the savings of each move and removing the sentinels.
Although Joel already has code which does most of this work,
experience with sysctl moves in the past shows is we need to be
careful due to the slew of odd build failures that are possible due to
the amount of random Kconfig options sysctls use.
To that end Joel's work is split by first addressing the major
housekeeping needed to remove the sentinels, which is part of this
merge request. The rest of the work to actually remove the sentinels
will be done later in future kernel releases.
The preliminary math is showing this will all help reduce the overall
build time size of the kernel and run time memory consumed by the
kernel by about ~64 bytes per array where we are able to remove each
sentinel in the future. That also means there is no more bloating the
kernel with the extra ~64 bytes per array moved as no new sentinels
are created"
* tag 'sysctl-6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux:
sysctl: Use ctl_table_size as stopping criteria for list macro
sysctl: SIZE_MAX->ARRAY_SIZE in register_net_sysctl
vrf: Update to register_net_sysctl_sz
networking: Update to register_net_sysctl_sz
netfilter: Update to register_net_sysctl_sz
ax.25: Update to register_net_sysctl_sz
sysctl: Add size to register_net_sysctl function
sysctl: Add size arg to __register_sysctl_init
sysctl: Add size to register_sysctl
sysctl: Add a size arg to __register_sysctl_table
sysctl: Add size argument to init_header
sysctl: Add ctl_table_size to ctl_table_header
sysctl: Use ctl_table_header in list_for_each_table_entry
sysctl: Prefer ctl_table_header in proc_sysctl
sk_getsockopt() runs locklessly. This means sk->sk_lingertime
can be read while other threads are changing its value.
Other reads also happen without socket lock being held,
and must be annotated.
Remove preprocessor logic using BITS_PER_LONG, compilers
are smart enough to figure this by themselves.
v2: fixed a clang W=1 (-Wtautological-constant-out-of-range-compare) warning
(Jakub)
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add SMC_NLA_LGR_R_V2_MAX_CONNS and SMC_NLA_LGR_R_V2_MAX_LINKS
to SMCR v2 linkgroup netlink attribute SMC_NLA_LGR_R_V2 for
linkgroup's detail info showing.
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Support max links per lgr negotiation in clc handshake for SMCR v2.1,
which is one of smc v2.1 features. Server makes decision for the final
value of max links based on the client preferred max links and
self-preferred max links. Here use the minimum value of the client
preferred max links and server preferred max links.
Client Server
Proposal(max links(client preferred))
-------------------------------------->
Accept(max links(accepted value))
accepted value=min(client preferred, server preferred)
<-------------------------------------
Confirm(max links(accepted value))
------------------------------------->
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Support max connections per lgr negotiation for SMCR v2.1,
which is one of smc v2.1 features. Server makes decision for
the final value of max conns based on the client preferred
max conns and self-preferred max conns. Here use the minimum
value of client preferred max conns and server preferred max
conns.
Client Server
Proposal(max conns(client preferred))
------------------------------------>
Accept(max conns(accepted value))
accepted value=min(client preferred, server preferred)
<-----------------------------------
Confirm(max conns(accepted value))
----------------------------------->
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Support SMC v2.x features validate for SMC v2.1. This is the frame
code for SMC v2.x features validate, and will take effects only when
the negotiated release version is v2.1 or later.
For Server, v2.x features' validation should be done in smc_clc_srv_
v2x_features_validate when receiving v2.1 or later CLC Proposal Message,
such as max conns, max links negotiation, the decision of the final
value of max conns and max links should be made in this function.
And final check for server when receiving v2.1 or later CLC Confirm
Message should be done in smc_clc_v2x_features_confirm_check.
For client, v2.x features' validation should be done in smc_clc_clnt_
v2x_features_validate when receiving v2.1 or later CLC Accept Message,
for example, the decision to accpt the accepted value or to decline
should be made in this function.
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add vendor unique experimental options area in clc handshake. In clc
accept and confirm msg, vendor unique experimental options use the
16-Bytes reserved field, which defined in struct smc_clc_fce_gid_ext
in previous version. Because of the struct smc_clc_first_contact_ext
is widely used and limit the scope of modification, this patch moves
the 16-Bytes reserved field out of struct smc_clc_fce_gid_ext, and
followed with the struct smc_clc_first_contact_ext in a new struct
names struct smc_clc_first_contact_ext_v2x.
For SMC-R first connection, in previous version, the struct smc_clc_
first_contact_ext and the 16-Bytes reserved field has already been
included in clc accept and confirm msg. Thus, this patch use struct
smc_clc_first_contact_ext_v2x instead of the struct smc_clc_first_
contact_ext and the 16-Bytes reserved field in SMC-R clc accept and
confirm msg is compatible with previous version.
For SMC-D first connection, in previous version, only the struct smc_
clc_first_contact_ext is included in clc accept and confirm msg, and
the 16-Bytes reserved field is not included. Thus, when the negotiated
smc release version is the version before v2.1, we still use struct
smc_clc_first_contact_ext for compatible consideration. If the negotiated
smc release version is v2.1 or later, use struct smc_clc_first_contact_
ext_v2x instead.
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Support smc release version negotiation in clc handshake based on
SMC v2, where no negotiation process for different releases, but
for different versions. The latest smc release version was updated
to v2.1. And currently there are two release versions of SMCv2, v2.0
and v2.1. In the release version negotiation, client sends the preferred
release version by CLC Proposal Message, server makes decision for which
release version to use based on the client preferred release version and
self-supported release version (here choose the minimum release version
of the client preferred and server latest supported), then the decision
returns to client by CLC Accept Message. Client confirms the decision by
CLC Confirm Message.
Client Server
Proposal(preferred release version)
------------------------------------>
Accept(accpeted release version)
min(client preferred, server latest supported)
<------------------------------------
Confirm(accpeted release version)
------------------------------------>
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move from register_net_sysctl to register_net_sysctl_sz for all the
networking related files. Do this while making sure to mirror the NULL
assignments with a table_size of zero for the unprivileged users.
We need to move to the new function in preparation for when we change
SIZE_MAX to ARRAY_SIZE() in the register_net_sysctl macro. Failing to do
so would erroneously allow ARRAY_SIZE() to be called on a pointer. We
hold off the SIZE_MAX to ARRAY_SIZE change until we have migrated all
the relevant net sysctl registering functions to register_net_sysctl_sz
in subsequent commits.
An additional size function was added to the following files in order to
calculate the size of an array that is defined in another file:
include/net/ipv6.h
net/ipv6/icmp.c
net/ipv6/route.c
net/ipv6/sysctl_net_ipv6.c
Signed-off-by: Joel Granados <j.granados@samsung.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Tuning of the effective buffer size through setsockopts was working for
SMC traffic only but not for TCP fall-back connections even before
commit 0227f058aa ("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: 0227f058aa ("net/smc: Unbind r/w buffer size from clcsock and make them tunable")
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: Gerd Bayer <gbayer@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 0227f058aa ("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: 0227f058aa ("net/smc: Unbind r/w buffer size from clcsock and make them tunable")
Co-developed-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: Jan Karcher <jaka@linux.ibm.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: Gerd Bayer <gbayer@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
commit f9aab6f2ce ("net/smc: immediate freeing in smc_lgr_cleanup_early()")
left behind smc_lgr_schedule_free_work_fast() declaration.
And since commit 349d43127d ("net/smc: fix kernel panic caused by race of smc_sock")
smc_ib_modify_qp_reset() is not used anymore.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Link: https://lore.kernel.org/r/20230729121929.17180-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
sk->sk_mark is often read while another thread could change the value.
Fixes: 4a19ec5800 ("[NET]: Introducing socket mark socket option.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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 <dhowells@redhat.com>
cc: Karsten Graul <kgraul@linux.ibm.com>
cc: Wenjia Zhang <wenjia@linux.ibm.com>
cc: Jan Karcher <jaka@linux.ibm.com>
cc: "D. Wythe" <alibuda@linux.alibaba.com>
cc: Tony Lu <tonylu@linux.alibaba.com>
cc: Wen Gu <guwen@linux.alibaba.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
Link: https://lore.kernel.org/r/20230623225513.2732256-10-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
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 <dhowells@redhat.com>
cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
cc: Bernard Metzler <bmt@zurich.ibm.com>
cc: Jason Gunthorpe <jgg@ziepe.ca>
cc: Leon Romanovsky <leon@kernel.org>
cc: John Fastabend <john.fastabend@gmail.com>
cc: Jakub Sitnicki <jakub@cloudflare.com>
cc: David Ahern <dsahern@kernel.org>
cc: Karsten Graul <kgraul@linux.ibm.com>
cc: Wenjia Zhang <wenjia@linux.ibm.com>
cc: Jan Karcher <jaka@linux.ibm.com>
cc: "D. Wythe" <alibuda@linux.alibaba.com>
cc: Tony Lu <tonylu@linux.alibaba.com>
cc: Wen Gu <guwen@linux.alibaba.com>
cc: Boris Pismenny <borisp@nvidia.com>
cc: Steffen Klassert <steffen.klassert@secunet.com>
cc: Herbert Xu <herbert@gondor.apana.org.au>
Link: https://lore.kernel.org/r/20230623225513.2732256-2-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
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:
<TASK>
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
</TASK>
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: 87f88cda21 ("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 <guwen@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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:
<TASK>
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
</TASK>
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: b4ba4652b3 ("net/smc: extend LLC layer for SMC-Rv2")
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
When finding the first RMB of link group, it should start from the
current RMB list whose index is 0. So fix it.
Fixes: b4ba4652b3 ("net/smc: extend LLC layer for SMC-Rv2")
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
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://<ip>:<port>
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:
<TASK>
? 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
</TASK>
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: e49300a6bf ("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 <guwen@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
__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: 1da177e4c3 ("Linux-2.6.12-rc2")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
switching from a user process to a kernel thread.
- More folio conversions from Kefeng Wang, Zhang Peng and Pankaj Raghav.
- zsmalloc performance improvements from Sergey Senozhatsky.
- Yue Zhao has found and fixed some data race issues around the
alteration of memcg userspace tunables.
- VFS rationalizations from Christoph Hellwig:
- removal of most of the callers of write_one_page().
- make __filemap_get_folio()'s return value more useful
- Luis Chamberlain has changed tmpfs so it no longer requires swap
backing. Use `mount -o noswap'.
- Qi Zheng has made the slab shrinkers operate locklessly, providing
some scalability benefits.
- Keith Busch has improved dmapool's performance, making part of its
operations O(1) rather than O(n).
- Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
permitting userspace to wr-protect anon memory unpopulated ptes.
- Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive rather
than exclusive, and has fixed a bunch of errors which were caused by its
unintuitive meaning.
- Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
which causes minor faults to install a write-protected pte.
- Vlastimil Babka has done some maintenance work on vma_merge():
cleanups to the kernel code and improvements to our userspace test
harness.
- Cleanups to do_fault_around() by Lorenzo Stoakes.
- Mike Rapoport has moved a lot of initialization code out of various
mm/ files and into mm/mm_init.c.
- Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
DRM, but DRM doesn't use it any more.
- Lorenzo has also coverted read_kcore() and vread() to use iterators
and has thereby removed the use of bounce buffers in some cases.
- Lorenzo has also contributed further cleanups of vma_merge().
- Chaitanya Prakash provides some fixes to the mmap selftesting code.
- Matthew Wilcox changes xfs and afs so they no longer take sleeping
locks in ->map_page(), a step towards RCUification of pagefaults.
- Suren Baghdasaryan has improved mmap_lock scalability by switching to
per-VMA locking.
- Frederic Weisbecker has reworked the percpu cache draining so that it
no longer causes latency glitches on cpu isolated workloads.
- Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
logic.
- Liu Shixin has changed zswap's initialization so we no longer waste a
chunk of memory if zswap is not being used.
- Yosry Ahmed has improved the performance of memcg statistics flushing.
- David Stevens has fixed several issues involving khugepaged,
userfaultfd and shmem.
- Christoph Hellwig has provided some cleanup work to zram's IO-related
code paths.
- David Hildenbrand has fixed up some issues in the selftest code's
testing of our pte state changing.
- Pankaj Raghav has made page_endio() unneeded and has removed it.
- Peter Xu contributed some rationalizations of the userfaultfd
selftests.
- Yosry Ahmed has fixed an issue around memcg's page recalim accounting.
- Chaitanya Prakash has fixed some arm-related issues in the
selftests/mm code.
- Longlong Xia has improved the way in which KSM handles hwpoisoned
pages.
- Peter Xu fixes a few issues with uffd-wp at fork() time.
- Stefan Roesch has changed KSM so that it may now be used on a
per-process and per-cgroup basis.
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZEr3zQAKCRDdBJ7gKXxA
jlLoAP0fpQBipwFxED0Us4SKQfupV6z4caXNJGPeay7Aj11/kQD/aMRC2uPfgr96
eMG3kwn2pqkB9ST2QpkaRbxA//eMbQY=
=J+Dj
-----END PGP SIGNATURE-----
Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
- Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
switching from a user process to a kernel thread.
- More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
Raghav.
- zsmalloc performance improvements from Sergey Senozhatsky.
- Yue Zhao has found and fixed some data race issues around the
alteration of memcg userspace tunables.
- VFS rationalizations from Christoph Hellwig:
- removal of most of the callers of write_one_page()
- make __filemap_get_folio()'s return value more useful
- Luis Chamberlain has changed tmpfs so it no longer requires swap
backing. Use `mount -o noswap'.
- Qi Zheng has made the slab shrinkers operate locklessly, providing
some scalability benefits.
- Keith Busch has improved dmapool's performance, making part of its
operations O(1) rather than O(n).
- Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
permitting userspace to wr-protect anon memory unpopulated ptes.
- Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
rather than exclusive, and has fixed a bunch of errors which were
caused by its unintuitive meaning.
- Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
which causes minor faults to install a write-protected pte.
- Vlastimil Babka has done some maintenance work on vma_merge():
cleanups to the kernel code and improvements to our userspace test
harness.
- Cleanups to do_fault_around() by Lorenzo Stoakes.
- Mike Rapoport has moved a lot of initialization code out of various
mm/ files and into mm/mm_init.c.
- Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
DRM, but DRM doesn't use it any more.
- Lorenzo has also coverted read_kcore() and vread() to use iterators
and has thereby removed the use of bounce buffers in some cases.
- Lorenzo has also contributed further cleanups of vma_merge().
- Chaitanya Prakash provides some fixes to the mmap selftesting code.
- Matthew Wilcox changes xfs and afs so they no longer take sleeping
locks in ->map_page(), a step towards RCUification of pagefaults.
- Suren Baghdasaryan has improved mmap_lock scalability by switching to
per-VMA locking.
- Frederic Weisbecker has reworked the percpu cache draining so that it
no longer causes latency glitches on cpu isolated workloads.
- Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
logic.
- Liu Shixin has changed zswap's initialization so we no longer waste a
chunk of memory if zswap is not being used.
- Yosry Ahmed has improved the performance of memcg statistics
flushing.
- David Stevens has fixed several issues involving khugepaged,
userfaultfd and shmem.
- Christoph Hellwig has provided some cleanup work to zram's IO-related
code paths.
- David Hildenbrand has fixed up some issues in the selftest code's
testing of our pte state changing.
- Pankaj Raghav has made page_endio() unneeded and has removed it.
- Peter Xu contributed some rationalizations of the userfaultfd
selftests.
- Yosry Ahmed has fixed an issue around memcg's page recalim
accounting.
- Chaitanya Prakash has fixed some arm-related issues in the
selftests/mm code.
- Longlong Xia has improved the way in which KSM handles hwpoisoned
pages.
- Peter Xu fixes a few issues with uffd-wp at fork() time.
- Stefan Roesch has changed KSM so that it may now be used on a
per-process and per-cgroup basis.
* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
shmem: restrict noswap option to initial user namespace
mm/khugepaged: fix conflicting mods to collapse_file()
sparse: remove unnecessary 0 values from rc
mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
maple_tree: fix allocation in mas_sparse_area()
mm: do not increment pgfault stats when page fault handler retries
zsmalloc: allow only one active pool compaction context
selftests/mm: add new selftests for KSM
mm: add new KSM process and sysfs knobs
mm: add new api to enable ksm per process
mm: shrinkers: fix debugfs file permissions
mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
migrate_pages_batch: fix statistics for longterm pin retry
userfaultfd: use helper function range_in_vma()
lib/show_mem.c: use for_each_populated_zone() simplify code
mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
fs/buffer: convert create_page_buffers to folio_create_buffers
fs/buffer: add folio_create_empty_buffers helper
...
With Eric's ref tracker, syzbot finally found a repro for
use-after-free in tcp_write_timer_handler() by kernel TCP
sockets. [0]
If SMC creates a kernel socket in __smc_create(), the kernel
socket is supposed to be freed in smc_clcsock_release() by
calling sock_release() when we close() the parent SMC socket.
However, at the end of smc_clcsock_release(), the kernel
socket's sk_state might not be TCP_CLOSE. This means that
we have not called inet_csk_destroy_sock() in __tcp_close()
and have not stopped the TCP timers.
The kernel socket's TCP timers can be fired later, so we
need to hold a refcnt for net as we do for MPTCP subflows
in mptcp_subflow_create_socket().
[0]:
leaked reference.
sk_alloc (./include/net/net_namespace.h:335 net/core/sock.c:2108)
inet_create (net/ipv4/af_inet.c:319 net/ipv4/af_inet.c:244)
__sock_create (net/socket.c:1546)
smc_create (net/smc/af_smc.c:3269 net/smc/af_smc.c:3284)
__sock_create (net/socket.c:1546)
__sys_socket (net/socket.c:1634 net/socket.c:1618 net/socket.c:1661)
__x64_sys_socket (net/socket.c:1672)
do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120)
==================================================================
BUG: KASAN: slab-use-after-free in tcp_write_timer_handler (net/ipv4/tcp_timer.c:378 net/ipv4/tcp_timer.c:624 net/ipv4/tcp_timer.c:594)
Read of size 1 at addr ffff888052b65e0d by task syzrepro/18091
CPU: 0 PID: 18091 Comm: syzrepro Tainted: G W 6.3.0-rc4-01174-gb5d54eb5899a #7
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014
Call Trace:
<IRQ>
dump_stack_lvl (lib/dump_stack.c:107)
print_report (mm/kasan/report.c:320 mm/kasan/report.c:430)
kasan_report (mm/kasan/report.c:538)
tcp_write_timer_handler (net/ipv4/tcp_timer.c:378 net/ipv4/tcp_timer.c:624 net/ipv4/tcp_timer.c:594)
tcp_write_timer (./include/linux/spinlock.h:390 net/ipv4/tcp_timer.c:643)
call_timer_fn (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/timer.h:127 kernel/time/timer.c:1701)
__run_timers.part.0 (kernel/time/timer.c:1752 kernel/time/timer.c:2022)
run_timer_softirq (kernel/time/timer.c:2037)
__do_softirq (./arch/x86/include/asm/jump_label.h:27 ./include/linux/jump_label.h:207 ./include/trace/events/irq.h:142 kernel/softirq.c:572)
__irq_exit_rcu (kernel/softirq.c:445 kernel/softirq.c:650)
irq_exit_rcu (kernel/softirq.c:664)
sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1107 (discriminator 14))
</IRQ>
Fixes: ac7138746e ("smc: establish new socket family")
Reported-by: syzbot+7e1e1bdb852961150198@syzkaller.appspotmail.com
Link: https://lore.kernel.org/netdev/000000000000a3f51805f8bcc43a@google.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can change smc_sk() to propagate its argument const qualifier,
thanks to container_of_const().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Karsten Graul <kgraul@linux.ibm.com>
Cc: Wenjia Zhang <wenjia@linux.ibm.com>
Cc: Jan Karcher <jaka@linux.ibm.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The refcount wr_tx_refcnt may cause cache thrashing problems among
cores and we can use percpu ref to mitigate this issue here. We
gain some performance improvement with percpu ref here on our
customized smc-r verion. Applying cache alignment may also mitigate
this problem but it seem more reasonable to use percpu ref here.
We can also replace wr_reg_refcnt with one percpu reference like
wr_tx_refcnt.
redis-benchmark on smc-r with atomic wr_tx_refcnt:
SET: 525707.06 requests per second, p50=0.087 msec
GET: 554877.38 requests per second, p50=0.087 msec
redis-benchmark on the percpu_ref version:
SET: 540482.06 requests per second, p50=0.087 msec
GET: 570711.12 requests per second, p50=0.079 msec
Cases are like "redis-benchmark -h x.x.x.x -q -t set,get -P 1 -n
5000000 -c 50 -d 10 --threads 4".
Signed-off-by: Kai Shen <KaiShen@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously, v2 support was derived from a very specific format of the SEID
as part of the SMC-D codebase. Make this part of the SMC-D device API, so
implementers do not need to adhere to a specific SEID format.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Reviewed-and-tested-by: Jan Karcher <jaka@linux.ibm.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
CLC message initialization was not properly reversed in error handling path.
Reported-and-suggested-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When performing a stress test on SMC-R by rmmod mlx5_ib driver
during the wrk/nginx test, we found that there is a probability
of triggering a panic while terminating all link groups.
This issue dues to the race between smc_smcr_terminate_all()
and smc_buf_create().
smc_smcr_terminate_all
smc_buf_create
/* init */
conn->sndbuf_desc = NULL;
...
__smc_lgr_terminate
smc_conn_kill
smc_close_abort
smc_cdc_get_slot_and_msg_send
__softirqentry_text_start
smc_wr_tx_process_cqe
smc_cdc_tx_handler
READ(conn->sndbuf_desc->len);
/* panic dues to NULL sndbuf_desc */
conn->sndbuf_desc = xxx;
This patch tries to fix the issue by always to check the sndbuf_desc
before send any cdc msg, to make sure that no null pointer is
seen during cqe processing.
Fixes: 0b29ec6436 ("net/smc: immediate termination for SMCR link groups")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Link: https://lore.kernel.org/r/1678263432-17329-1-git-send-email-alibuda@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Before determining whether the msg has unsupported options, it has been
prematurely terminated by the wrong status check.
For the application, the general usages of MSG_FASTOPEN likes
fd = socket(...)
/* rather than connect */
sendto(fd, data, len, MSG_FASTOPEN)
Hence, We need to check the flag before state check, because the sock
state here is always SMC_INIT when applications tries MSG_FASTOPEN.
Once we found unsupported options, fallback it to TCP.
Fixes: ee9dfbef02 ("net/smc: handle sockopts forcing fallback")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: Simon Horman <simon.horman@corigine.com>
v2 -> v1: Optimize code style
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a certain probability that following
exceptions will occur in the wrk benchmark test:
Running 10s test @ http://11.213.45.6:80
8 threads and 64 connections
Thread Stats Avg Stdev Max +/- Stdev
Latency 3.72ms 13.94ms 245.33ms 94.17%
Req/Sec 1.96k 713.67 5.41k 75.16%
155262 requests in 10.10s, 23.10MB read
Non-2xx or 3xx responses: 3
We will find that the error is HTTP 400 error, which is a serious
exception in our test, which means the application data was
corrupted.
Consider the following scenarios:
CPU0 CPU1
buf_desc->used = 0;
cmpxchg(buf_desc->used, 0, 1)
deal_with(buf_desc)
memset(buf_desc->cpu_addr,0);
This will cause the data received by a victim connection to be cleared,
thus triggering an HTTP 400 error in the server.
This patch exchange the order between clear used and memset, add
barrier to ensure memory consistency.
Fixes: 1c5526968e ("net/smc: Clear memory when release and reuse buffer")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a certain chance to trigger the following panic:
PID: 5900 TASK: ffff88c1c8af4100 CPU: 1 COMMAND: "kworker/1:48"
#0 [ffff9456c1cc79a0] machine_kexec at ffffffff870665b7
#1 [ffff9456c1cc79f0] __crash_kexec at ffffffff871b4c7a
#2 [ffff9456c1cc7ab0] crash_kexec at ffffffff871b5b60
#3 [ffff9456c1cc7ac0] oops_end at ffffffff87026ce7
#4 [ffff9456c1cc7ae0] page_fault_oops at ffffffff87075715
#5 [ffff9456c1cc7b58] exc_page_fault at ffffffff87ad0654
#6 [ffff9456c1cc7b80] asm_exc_page_fault at ffffffff87c00b62
[exception RIP: ib_alloc_mr+19]
RIP: ffffffffc0c9cce3 RSP: ffff9456c1cc7c38 RFLAGS: 00010202
RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000004
RDX: 0000000000000010 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffff88c1ea281d00 R8: 000000020a34ffff R9: ffff88c1350bbb20
R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000
R13: 0000000000000010 R14: ffff88c1ab040a50 R15: ffff88c1ea281d00
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
#7 [ffff9456c1cc7c60] smc_ib_get_memory_region at ffffffffc0aff6df [smc]
#8 [ffff9456c1cc7c88] smcr_buf_map_link at ffffffffc0b0278c [smc]
#9 [ffff9456c1cc7ce0] __smc_buf_create at ffffffffc0b03586 [smc]
The reason here is that when the server tries to create a second link,
smc_llc_srv_add_link() has no protection and may add a new link to
link group. This breaks the security environment protected by
llc_conf_mutex.
Fixes: 2d2209f201 ("net/smc: first part of add link processing as SMC server")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit e48c414ee6 ("[INET]: Generalise the TCP sock ID lookup routines")
commented out the definition of SOCK_REFCNT_DEBUG in 2005 and later another
commit 463c84b97f ("[NET]: Introduce inet_connection_sock") removed it.
Since we could track all of them through bpf and kprobe related tools
and the feature could print loads of information which might not be
that helpful even under a little bit pressure, the whole feature which
has been inactive for many years is no longer supported.
Link: https://lore.kernel.org/lkml/20230211065153.54116-1-kerneljasonxing@gmail.com/
Suggested-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
It's clear that rmbs_lock and sndbufs_lock are aims to protect the
rmbs list or the sndbufs list.
During connection establieshment, smc_buf_get_slot() will always
be invoked, and it only performs read semantics in rmbs list and
sndbufs list.
Based on the above considerations, we replace mutex with rw_semaphore.
Only smc_buf_get_slot() use down_read() to allow smc_buf_get_slot()
run concurrently, other part use down_write() to keep exclusive
semantics.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Unlike smc_buf_create() and smcr_buf_unuse(), smcr_lgr_reg_rmbs() is
exclusive when assigned rmb_desc was not registered, although it can be
executed in parallel when assigned rmb_desc was registered already
and only performs read semtamics on it. Hence, we can not simply replace
it with read semaphore.
The idea here is that if the assigned rmb_desc was registered already,
use read semaphore to protect the critical section, once the assigned
rmb_desc was not registered, keep using keep write semaphore still
to keep its exclusivity.
Thanks to the reusable features of rmb_desc, which allows us to execute
in parallel in most cases.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Following is part of Off-CPU graph during frequent SMC-R short-lived
processing:
process_one_work (51.19%)
smc_close_passive_work (28.36%)
smcr_buf_unuse (28.34%)
rwsem_down_write_slowpath (28.22%)
smc_listen_work (22.83%)
smc_clc_wait_msg (1.84%)
smc_buf_create (20.45%)
smcr_buf_map_usable_links
rwsem_down_write_slowpath (20.43%)
smcr_lgr_reg_rmbs (0.53%)
rwsem_down_write_slowpath (0.43%)
smc_llc_do_confirm_rkey (0.08%)
We can clearly see that during the connection establishment time,
waiting time of connections is not on IO, but on llc_conf_mutex.
What is more important, the core critical area (smcr_buf_unuse() &
smc_buf_create()) only perfroms read semantics on links, we can
easily replace it with read semaphore.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
llc_conf_mutex was used to protect links and link related configurations
in the same link group, for example, add or delete links. However,
in most cases, the protected critical area has only read semantics and
with no write semantics at all, such as obtaining a usable link or an
available rmb_desc.
This patch do simply code refactoring, replace mutex with rw_semaphore,
replace mutex_lock with down_write and replace mutex_unlock with
up_write.
Theoretically, this replacement is equivalent, but after this patch,
we can distinguish lock granularity according to different semantics
of critical areas.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Number of files depend on linux/splice.h getting included
by linux/skbuff.h which soon will no longer be the case.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The struct device for ISM devices was part of struct smcd_dev. Move to
struct ism_dev, provide a new API call in struct smcd_ops, and convert
existing SMCD code accordingly.
Furthermore, remove struct smcd_dev from struct ism_dev.
This is the final part of a bigger overhaul of the interfaces between SMC
and ISM.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ism module had SMC-D-specific code sprinkled across the entire module.
We are now consolidating the SMC-D-specific parts into the latter parts
of the module, so it becomes more clear what code is intended for use with
ISM, and which parts are glue code for usage in the context of SMC-D.
This is the fourth part of a bigger overhaul of the interfaces between SMC
and ISM.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We separate the code implementing the struct smcd_ops API in the ISM
device driver from the functions that may be used by other exploiters of
ISM devices.
Note: We start out small, and don't offer the whole breadth of the ISM
device for public use, as many functions are specific to or likely only
ever used in the context of SMC-D.
This is the third part of a bigger overhaul of the interfaces between SMC
and ISM.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Register the smc module with the new ism device driver API.
This is the second part of a bigger overhaul of the interfaces between SMC
and ISM.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a new API that allows other drivers to concurrently access ISM devices.
To do so, we introduce a new API that allows other modules to register for
ISM device usage. Furthermore, we move the GID to struct ism, where it
belongs conceptually, and rename and relocate struct smcd_event to struct
ism_event.
This is the first part of a bigger overhaul of the interfaces between SMC
and ISM.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Removing an ISM device prior to terminating its associated connections
doesn't end well.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Jan Karcher <jaka@linux.ibm.com>
Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As suggested by Cong, introduce a tracepoint for all ->sk_data_ready()
callback implementations. For example:
<...>
iperf-609 [002] ..... 70.660425: sk_data_ready: family=2 protocol=6 func=sock_def_readable
iperf-609 [002] ..... 70.660436: sk_data_ready: family=2 protocol=6 func=sock_def_readable
<...>
Suggested-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Peilin Ye <peilin.ye@bytedance.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
READ/WRITE proved to be actively confusing - the meanings are
"data destination, as used with read(2)" and "data source, as
used with write(2)", but people keep interpreting those as
"we read data from it" and "we write data to it", i.e. exactly
the wrong way.
Call them ITER_DEST and ITER_SOURCE - at least that is harder
to misinterpret...
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
In smc_init(), register_pernet_subsys(&smc_net_stat_ops) is called
without any error handling.
If it fails, registering of &smc_net_ops won't be reverted.
And if smc_nl_init() fails, &smc_net_stat_ops itself won't be reverted.
This leaves wild ops in subsystem linkedlist and when another module
tries to call register_pernet_operations() it triggers page fault:
BUG: unable to handle page fault for address: fffffbfff81b964c
RIP: 0010:register_pernet_operations+0x1b9/0x5f0
Call Trace:
<TASK>
register_pernet_subsys+0x29/0x40
ebtables_init+0x58/0x1000 [ebtables]
...
Fixes: 194730a9be ("net/smc: Make SMC statistics network namespace aware")
Signed-off-by: Chen Zhongjin <chenzhongjin@huawei.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Link: https://lore.kernel.org/r/20221101093722.127223-1-chenzhongjin@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
If smc_wr_alloc_lgr_mem() fails then return an error code. Don't return
success.
Fixes: 8799e310fb ("net/smc: add v2 support to the work request layer")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, SMC uses smc->sk.sk_{rcv|snd}buf to create buffers for
send buffer and RMB. And the values of buffer size are from tcp_{w|r}mem
in clcsock.
The buffer size from TCP socket doesn't fit SMC well. Generally, buffers
are usually larger than TCP for SMC-R/-D to get higher performance, for
they are different underlay devices and paths.
So this patch unbinds buffer size from TCP, and introduces two sysctl
knobs to tune them independently. Also, these knobs are per net
namespace and work for containers.
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
SMC-R tests the viability of link by sending out TEST_LINK LLC
messages over RoCE fabric when connections on link have been
idle for a time longer than keepalive interval (testlink time).
But using tcp_keepalive_time as testlink time maybe not quite
suitable because it is default no less than two hours[1], which
is too long for single link to find peer dead. The active host
will still use peer-dead link (QP) sending messages, and can't
find out until get IB_WC_RETRY_EXC_ERR error CQEs, which takes
more time than TEST_LINK timeout (SMC_LLC_WAIT_TIME) normally.
So this patch introduces a independent sysctl for SMC-R to set
link keepalive time, in order to detect link down in time. The
default value is 30 seconds.
[1] https://www.rfc-editor.org/rfc/rfc1122#page-101
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
There might be a potential race between SMC-R buffer map and
link group termination.
smc_smcr_terminate_all() | smc_connect_rdma()
--------------------------------------------------------------
| smc_conn_create()
for links in smcibdev |
schedule links down |
| smc_buf_create()
| \- smcr_buf_map_usable_links()
| \- no usable links found,
| (rmb->mr = NULL)
|
| smc_clc_send_confirm()
| \- access conn->rmb_desc->mr[]->rkey
| (panic)
During reboot and IB device module remove, all links will be set
down and no usable links remain in link groups. In such situation
smcr_buf_map_usable_links() should return an error and stop the
CLC flow accessing to uninitialized mr.
Fixes: b9247544c1 ("net/smc: convert static link ID instances to support multiple links")
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Link: https://lore.kernel.org/r/1663656189-32090-1-git-send-email-guwen@linux.alibaba.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
drivers/net/ethernet/freescale/fec.h
7d650df99d ("net: fec: add pm_qos support on imx6q platform")
40c79ce13b ("net: fec: add stop mode support for imx8 platform")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
For passive connections, the refcount increment has been done in
smc_clcsock_accept()-->smc_sock_alloc().
Fixes: 3b2dec2603 ("net/smc: restructure client and server code in af_smc")
Signed-off-by: Yacan Liu <liuyacan@corp.netease.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Link: https://lore.kernel.org/r/20220830152314.838736-1-liuyacan@corp.netease.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
We had historically not checked that genlmsghdr.reserved
is 0 on input which prevents us from using those precious
bytes in the future.
One use case would be to extend the cmd field, which is
currently just 8 bits wide and 256 is not a lot of commands
for some core families.
To make sure that new families do the right thing by default
put the onus of opting out of validation on existing families.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Paul Moore <paul@paul-moore.com> (NetLabel)
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously, the smc and smc_diag modules were automatically loaded as
dependencies of the ism module whenever an ISM device was present.
With the pending rework of the ISM API, the smc module will no longer
automatically be loaded in presence of an ISM device. Usage of an AF_SMC
socket will still trigger loading of the smc modules, but usage of a
netlink socket will not.
This is addressed by setting the correct module aliases.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Wenjia Zhang < wenjia@linux.ibm.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make the DMBE bits, which are passed on individually in ism_move() as
parameter idx, available to the receiver.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Wenjia Zhang < wenjia@linux.ibm.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reworked signature of the function to retrieve the system EID: No plausible
reason to use a double pointer. And neither to pass in the device as an
argument, as this identifier is by definition per system, not per device.
Plus some minor consistency edits.
Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Wenjia Zhang < wenjia@linux.ibm.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This struct is used in a single place only, and its usage generates
inefficient code. Time to clean up!
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-and-tested-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Wenjia Zhang < wenjia@linux.ibm.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While reading sysctl_tcp_keepalive_(time|probes|intvl), they can be changed
concurrently. Thus, we need to add READ_ONCE() to their readers.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Extend SMC-R link group netlink attribute SMC_GEN_LGR_SMCR.
Introduce SMC_NLA_LGR_R_BUF_TYPE to show the buffer type of
SMC-R link group.
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
On long-running enterprise production servers, high-order contiguous
memory pages are usually very rare and in most cases we can only get
fragmented pages.
When replacing TCP with SMC-R in such production scenarios, attempting
to allocate high-order physically contiguous sndbufs and RMBs may result
in frequent memory compaction, which will cause unexpected hung issue
and further stability risks.
So this patch is aimed to allow SMC-R link group to use virtually
contiguous sndbufs and RMBs to avoid potential issues mentioned above.
Whether to use physically or virtually contiguous buffers can be set
by sysctl smcr_buf_type.
Note that using virtually contiguous buffers will bring an acceptable
performance regression, which can be mainly divided into two parts:
1) regression in data path, which is brought by additional address
translation of sndbuf by RNIC in Tx. But in general, translating
address through MTT is fast.
Taking 256KB sndbuf and RMB as an example, the comparisons in qperf
latency and bandwidth test with physically and virtually contiguous
buffers are as follows:
- client:
smc_run taskset -c <cpu> qperf <server> -oo msg_size:1:64K:*2\
-t 5 -vu tcp_{bw|lat}
- server:
smc_run taskset -c <cpu> qperf
[latency]
msgsize tcp smcr smcr-use-virt-buf
1 11.17 us 7.56 us 7.51 us (-0.67%)
2 10.65 us 7.74 us 7.56 us (-2.31%)
4 11.11 us 7.52 us 7.59 us ( 0.84%)
8 10.83 us 7.55 us 7.51 us (-0.48%)
16 11.21 us 7.46 us 7.51 us ( 0.71%)
32 10.65 us 7.53 us 7.58 us ( 0.61%)
64 10.95 us 7.74 us 7.80 us ( 0.76%)
128 11.14 us 7.83 us 7.87 us ( 0.47%)
256 10.97 us 7.94 us 7.92 us (-0.28%)
512 11.23 us 7.94 us 8.20 us ( 3.25%)
1024 11.60 us 8.12 us 8.20 us ( 0.96%)
2048 14.04 us 8.30 us 8.51 us ( 2.49%)
4096 16.88 us 9.13 us 9.07 us (-0.64%)
8192 22.50 us 10.56 us 11.22 us ( 6.26%)
16384 28.99 us 12.88 us 13.83 us ( 7.37%)
32768 40.13 us 16.76 us 16.95 us ( 1.16%)
65536 68.70 us 24.68 us 24.85 us ( 0.68%)
[bandwidth]
msgsize tcp smcr smcr-use-virt-buf
1 1.65 MB/s 1.59 MB/s 1.53 MB/s (-3.88%)
2 3.32 MB/s 3.17 MB/s 3.08 MB/s (-2.67%)
4 6.66 MB/s 6.33 MB/s 6.09 MB/s (-3.85%)
8 13.67 MB/s 13.45 MB/s 11.97 MB/s (-10.99%)
16 25.36 MB/s 27.15 MB/s 24.16 MB/s (-11.01%)
32 48.22 MB/s 54.24 MB/s 49.41 MB/s (-8.89%)
64 106.79 MB/s 107.32 MB/s 99.05 MB/s (-7.71%)
128 210.21 MB/s 202.46 MB/s 201.02 MB/s (-0.71%)
256 400.81 MB/s 416.81 MB/s 393.52 MB/s (-5.59%)
512 746.49 MB/s 834.12 MB/s 809.99 MB/s (-2.89%)
1024 1292.33 MB/s 1641.96 MB/s 1571.82 MB/s (-4.27%)
2048 2007.64 MB/s 2760.44 MB/s 2717.68 MB/s (-1.55%)
4096 2665.17 MB/s 4157.44 MB/s 4070.76 MB/s (-2.09%)
8192 3159.72 MB/s 4361.57 MB/s 4270.65 MB/s (-2.08%)
16384 4186.70 MB/s 4574.13 MB/s 4501.17 MB/s (-1.60%)
32768 4093.21 MB/s 4487.42 MB/s 4322.43 MB/s (-3.68%)
65536 4057.14 MB/s 4735.61 MB/s 4555.17 MB/s (-3.81%)
2) regression in buffer initialization and destruction path, which is
brought by additional MR operations of sndbufs. But thanks to link
group buffer reuse mechanism, the impact of this kind of regression
decreases as times of buffer reuse increases.
Taking 256KB sndbuf and RMB as an example, latency of some key SMC-R
buffer-related function obtained by bpftrace are as follows:
Function Phys-bufs Virt-bufs
smcr_new_buf_create() 67154 ns 79164 ns
smc_ib_buf_map_sg() 525 ns 928 ns
smc_ib_get_memory_region() 162294 ns 161191 ns
smc_wr_reg_send() 9957 ns 9635 ns
smc_ib_put_memory_region() 203548 ns 198374 ns
smc_ib_buf_unmap_sg() 508 ns 1158 ns
------------
Test environment notes:
1. Above tests run on 2 VMs within the same Host.
2. The NIC is ConnectX-4Lx, using SRIOV and passing through 2 VFs to
the each VM respectively.
3. VMs' vCPUs are binded to different physical CPUs, and the binded
physical CPUs are isolated by `isolcpus=xxx` cmdline.
4. NICs' queue number are set to 1.
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces a new SMC-R specific element buf_type
in struct smc_link_group, for recording the value of sysctl
smcr_buf_type when link group is created.
New created link group will create and reuse buffers of the
type specified by buf_type.
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces the sysctl smcr_buf_type for setting
the type of SMC-R sndbufs and RMBs.
Valid values includes:
- SMCR_PHYS_CONT_BUFS, which means use physically contiguous
buffers for better performance and is the default value.
- SMCR_VIRT_CONT_BUFS, which means use virtually contiguous
buffers in case of physically contiguous memory is scarce.
- SMCR_MIXED_BUFS, which means first try to use physically
contiguous buffers. If not available, then use virtually
contiguous buffers.
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some CPU, such as Xeon, can guarantee DMA cache coherency.
So it is no need to use dma sync APIs to flush cache on such CPUs.
In order to avoid calling dma sync APIs on the IO path, use the
dma_need_sync to check whether smc_buf_desc needs dma sync when
creating smc_buf_desc.
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
smc_ib_sync_sg_for_cpu/device are the ops used for dma memory cache
consistency. Smc sndbufs are dma buffers, where CPU writes data to
it and PCIE device reads data from it. So for sndbufs,
smc_ib_sync_sg_for_device is needed and smc_ib_sync_sg_for_cpu is
redundant as PCIE device will not write the buffers. Smc rmbs
are dma buffers, where PCIE device write data to it and CPU read
data from it. So for rmbs, smc_ib_sync_sg_for_cpu is needed and
smc_ib_sync_sg_for_device is redundant as CPU will not write the buffers.
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Netdev reference helpers have a dev_ prefix for historic
reasons. Renaming the old helpers would be too much churn
but we can rename the tracking ones which are relatively
recent and should be the default for new code.
Rename:
dev_hold_track() -> netdev_hold()
dev_put_track() -> netdev_put()
dev_replace_track() -> netdev_ref_replace()
Link: https://lore.kernel.org/r/20220608043955.919359-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
"struct smc_cdc_tx_pend **" can not directly convert
to "struct smc_wr_tx_pend_priv *".
Fixes: 2bced6aefa ("net/smc: put slot when connection is killed")
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the process of checking whether RDMAv2 is available, the current
implementation first sets ini->smcrv2.ib_dev_v2, and then allocates
smc buf desc and register rmb, but the latter may fail. In this case,
the pointer should be reset.
Fixes: e49300a6bf ("net/smc: add listen processing for SMC-Rv2")
Signed-off-by: liuyacan <liuyacan@corp.netease.com>
Reviewed-by: Karsten Graul <kgraul@linux.ibm.com>
Link: https://lore.kernel.org/r/20220525085408.812273-1-liuyacan@corp.netease.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In the process of checking whether RDMAv2 is available, the current
implementation first sets ini->smcrv2.ib_dev_v2, and then allocates
smc buf desc, but the latter may fail. Unfortunately, the caller
will only check the former. In this case, a NULL pointer reference
will occur in smc_clc_send_confirm_accept() when accessing
conn->rmb_desc.
This patch does two things:
1. Use the return code to determine whether V2 is available.
2. If the return code is NODEV, continue to check whether V1 is
available.
Fixes: e49300a6bf ("net/smc: add listen processing for SMC-Rv2")
Signed-off-by: liuyacan <liuyacan@corp.netease.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Same trigger condition as commit 86434744. When setsockopt runs
in parallel to a connect(), and switch the socket into fallback
mode. Then the sk_refcnt is incremented in smc_connect(), but
its state stay in SMC_INIT (NOT SMC_ACTIVE). This cause the
corresponding sk_refcnt decrement in __smc_release() will not be
performed.
Fixes: 86434744fe ("net/smc: add fallback check to connect()")
Signed-off-by: liuyacan <liuyacan@corp.netease.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rdma write with inline flag when sending small packages,
whose length is shorter than the qp's max_inline_data, can
help reducing latency.
In my test environment, which are 2 VMs running on the same
physical host and whose NICs(ConnectX-4Lx) are working on
SR-IOV mode, qperf shows 0.5us-0.7us improvement in latency.
Test command:
server: smc_run taskset -c 1 qperf
client: smc_run taskset -c 1 qperf <server ip> -oo \
msg_size:1:2K:*2 -t 30 -vu tcp_lat
The results shown below:
msgsize before after
1B 11.2 us 10.6 us (-0.6 us)
2B 11.2 us 10.7 us (-0.5 us)
4B 11.3 us 10.7 us (-0.6 us)
8B 11.2 us 10.6 us (-0.6 us)
16B 11.3 us 10.7 us (-0.6 us)
32B 11.3 us 10.6 us (-0.7 us)
64B 11.2 us 11.2 us (0 us)
128B 11.2 us 11.2 us (0 us)
256B 11.2 us 11.2 us (0 us)
512B 11.4 us 11.3 us (-0.1 us)
1KB 11.4 us 11.5 us (0.1 us)
2KB 11.5 us 11.5 us (0 us)
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Tested-by: kernel test robot <lkp@intel.com>
Acked-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
As cdc msg's length is 44B, cdc msgs can be sent inline in
most rdma devices, which can help reducing sending latency.
In my test environment, which are 2 VMs running on the same
physical host and whose NICs(ConnectX-4Lx) are working on
SR-IOV mode, qperf shows 0.4us-0.7us improvement in latency.
Test command:
server: smc_run taskset -c 1 qperf
client: smc_run taskset -c 1 qperf <server ip> -oo \
msg_size:1:2K:*2 -t 30 -vu tcp_lat
The results shown below:
msgsize before after
1B 11.9 us 11.2 us (-0.7 us)
2B 11.7 us 11.2 us (-0.5 us)
4B 11.7 us 11.3 us (-0.4 us)
8B 11.6 us 11.2 us (-0.4 us)
16B 11.7 us 11.3 us (-0.4 us)
32B 11.7 us 11.3 us (-0.4 us)
64B 11.7 us 11.2 us (-0.5 us)
128B 11.6 us 11.2 us (-0.4 us)
256B 11.8 us 11.2 us (-0.6 us)
512B 11.8 us 11.4 us (-0.4 us)
1KB 11.9 us 11.4 us (-0.5 us)
2KB 12.1 us 11.5 us (-0.6 us)
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Tested-by: kernel test robot <lkp@intel.com>
Acked-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Connect with O_NONBLOCK will not be completed immediately
and returns -EINPROGRESS. It is possible to use selector/poll
for completion by selecting the socket for writing. After select
indicates writability, a second connect function call will return
0 to indicate connected successfully as TCP does, but smc returns
-EISCONN. Use socket state for smc to indicate connect state, which
can help smc aligning the connect behaviour with TCP.
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Acked-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Non blocking sendmsg will return -EAGAIN when any signal pending
and no send space left, while non blocking recvmsg return -EINTR
when signal pending and no data received. This may makes confused.
As TCP returns -EAGAIN in the conditions described above. Align the
behavior of smc with TCP.
Fixes: 846e344eb7 ("net/smc: add receive timeout check")
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Acked-by: Karsten Graul <kgraul@linux.ibm.com>
Link: https://lore.kernel.org/r/20220512030820.73848-1-guangguan.wang@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
D. Wythe