Jakub Sitnicki says:
====================
This is a follow-up to discussion around the idea of making dst_port in struct
bpf_sock a 16-bit field that happened in [1].
v2:
- use an anonymous field for zero padding (Alexei)
v1:
- keep dst_field offset unchanged to prevent existing BPF program breakage
(Martin)
- allow 8-bit loads from dst_port[0] and [1]
- add test coverage for the verifier and the context access converter
[1] https://lore.kernel.org/bpf/87sftbobys.fsf@cloudflare.com/
====================
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add coverage to the verifier tests and tests for reading bpf_sock fields to
ensure that 32-bit, 16-bit, and 8-bit loads from dst_port field are allowed
only at intended offsets and produce expected values.
While 16-bit and 8-bit access to dst_port field is straight-forward, 32-bit
wide loads need be allowed and produce a zero-padded 16-bit value for
backward compatibility.
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/r/20220130115518.213259-3-jakub@cloudflare.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Menglong Dong reports that the documentation for the dst_port field in
struct bpf_sock is inaccurate and confusing. From the BPF program PoV, the
field is a zero-padded 16-bit integer in network byte order. The value
appears to the BPF user as if laid out in memory as so:
offsetof(struct bpf_sock, dst_port) + 0 <port MSB>
+ 8 <port LSB>
+16 0x00
+24 0x00
32-, 16-, and 8-bit wide loads from the field are all allowed, but only if
the offset into the field is 0.
32-bit wide loads from dst_port are especially confusing. The loaded value,
after converting to host byte order with bpf_ntohl(dst_port), contains the
port number in the upper 16-bits.
Remove the confusion by splitting the field into two 16-bit fields. For
backward compatibility, allow 32-bit wide loads from offsetof(struct
bpf_sock, dst_port).
While at it, allow loads 8-bit loads at offset [0] and [1] from dst_port.
Reported-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/r/20220130115518.213259-2-jakub@cloudflare.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
For now, if the XDP prog returns XDP_PASS on XSK, the metadata
will be lost as it doesn't get copied to the skb.
Copy it along with the frame headers. Account its size on skb
allocation, and when copying just treat it as a part of the frame
and do a pull after to "move" it to the "reserved" zone.
net_prefetch() xdp->data_meta and align the copy size to speed-up
memcpy() a little and better match ixgbe_construct_skb().
Fixes: d0bcacd0a1 ("ixgbe: add AF_XDP zero-copy Rx support")
Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Sandeep Penigalapati <sandeep.penigalapati@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
{__,}napi_alloc_skb() allocates and reserves additional NET_SKB_PAD
+ NET_IP_ALIGN for any skb.
OTOH, ixgbe_construct_skb_zc() currently allocates and reserves
additional `xdp->data - xdp->data_hard_start`, which is
XDP_PACKET_HEADROOM for XSK frames.
There's no need for that at all as the frame is post-XDP and will
go only to the networking stack core.
Pass the size of the actual data only to __napi_alloc_skb() and
don't reserve anything. This will give enough headroom for stack
processing.
Fixes: d0bcacd0a1 ("ixgbe: add AF_XDP zero-copy Rx support")
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Sandeep Penigalapati <sandeep.penigalapati@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
To not dereference bi->xdp each time in ixgbe_construct_skb_zc(),
pass bi->xdp as an argument instead of bi. We can also call
xsk_buff_free() outside of the function as well as assign bi->xdp
to NULL, which seems to make it closer to its name.
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Tested-by: Sandeep Penigalapati <sandeep.penigalapati@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
{__,}napi_alloc_skb() allocates and reserves additional NET_SKB_PAD
+ NET_IP_ALIGN for any skb.
OTOH, igc_construct_skb_zc() currently allocates and reserves
additional `xdp->data_meta - xdp->data_hard_start`, which is about
XDP_PACKET_HEADROOM for XSK frames.
There's no need for that at all as the frame is post-XDP and will
go only to the networking stack core.
Pass the size of the actual data only (+ meta) to
__napi_alloc_skb() and don't reserve anything. This will give
enough headroom for stack processing.
Also, net_prefetch() xdp->data_meta and align the copy size to
speed-up memcpy() a little and better match igc_construct_skb().
Fixes: fc9df2a0b5 ("igc: Enable RX via AF_XDP zero-copy")
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Nechama Kraus <nechamax.kraus@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
For now, if the XDP prog returns XDP_PASS on XSK, the metadata will
be lost as it doesn't get copied to the skb.
Copy it along with the frame headers. Account its size on skb
allocation, and when copying just treat it as a part of the frame
and do a pull after to "move" it to the "reserved" zone.
net_prefetch() xdp->data_meta and align the copy size to speed-up
memcpy() a little and better match ice_construct_skb().
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
{__,}napi_alloc_skb() allocates and reserves additional NET_SKB_PAD
+ NET_IP_ALIGN for any skb.
OTOH, ice_construct_skb_zc() currently allocates and reserves
additional `xdp->data - xdp->data_hard_start`, which is
XDP_PACKET_HEADROOM for XSK frames.
There's no need for that at all as the frame is post-XDP and will
go only to the networking stack core.
Pass the size of the actual data only to __napi_alloc_skb() and
don't reserve anything. This will give enough headroom for stack
processing.
Fixes: 2d4238f556 ("ice: Add support for AF_XDP")
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
In "legacy-rx" mode represented by ice_construct_skb(), we can
still use XDP (and XDP metadata), but after XDP_PASS the metadata
will be lost as it doesn't get copied to the skb.
Copy it along with the frame headers. Account its size on skb
allocation, and when copying just treat it as a part of the frame
and do a pull after to "move" it to the "reserved" zone.
Point net_prefetch() to xdp->data_meta instead of data. This won't
change anything when the meta is not here, but will save some cache
misses otherwise.
Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
For now, if the XDP prog returns XDP_PASS on XSK, the metadata will
be lost as it doesn't get copied to the skb.
Copy it along with the frame headers. Account its size on skb
allocation, and when copying just treat it as a part of the frame
and do a pull after to "move" it to the "reserved" zone.
net_prefetch() xdp->data_meta and align the copy size to speed-up
memcpy() a little and better match i40e_construct_skb().
Fixes: 0a714186d3 ("i40e: add AF_XDP zero-copy Rx support")
Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
{__,}napi_alloc_skb() allocates and reserves additional NET_SKB_PAD
+ NET_IP_ALIGN for any skb.
OTOH, i40e_construct_skb_zc() currently allocates and reserves
additional `xdp->data - xdp->data_hard_start`, which is
XDP_PACKET_HEADROOM for XSK frames.
There's no need for that at all as the frame is post-XDP and will
go only to the networking stack core.
Pass the size of the actual data only to __napi_alloc_skb() and
don't reserve anything. This will give enough headroom for stack
processing.
Fixes: 0a714186d3 ("i40e: add AF_XDP zero-copy Rx support")
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
vdso_test_abi contains a batch of tests that verify the validity of the
vDSO ABI.
When a vDSO symbol is not found the relevant test is skipped reporting
KSFT_SKIP. All the tests return values are then added in a single
variable which is checked to verify failures. This approach can have
side effects which result in reporting the wrong kselftest exit status.
Fix vdso_test_abi verifying the return code of each test separately.
Cc: Shuah Khan <shuah@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Reuse the dropped page in RX path to save page allocation
overhead.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This counter will show up in ethtool stat. It is the
number of packets received and forwarded by XDP program.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tony Lu says:
====================
net/smc: Improvements for TCP_CORK and sendfile()
Currently, SMC use default implement for syscall sendfile() [1], which
is wildly used in nginx and big data sences. Usually, applications use
sendfile() with TCP_CORK:
fstat(20, {st_mode=S_IFREG|0644, st_size=4096, ...}) = 0
setsockopt(19, SOL_TCP, TCP_CORK, [1], 4) = 0
writev(19, [{iov_base="HTTP/1.1 200 OK\r\nServer: nginx/1"..., iov_len=240}], 1) = 240
sendfile(19, 20, [0] => [4096], 4096) = 4096
close(20) = 0
setsockopt(19, SOL_TCP, TCP_CORK, [0], 4) = 0
The above is an example of Nginx, when sendfile() on, Nginx first
enables TCP_CORK, write headers, the data will not be sent. Then call
sendfile(), it reads file and write to sndbuf. When TCP_CORK is cleared,
all pending data is sent out.
The performance of the default implement of sendfile is lower than when
it is off. After investigation, it shows two parts to improve:
- unnecessary lock contention of delayed work
- less data per send than when sendfile off
Patch #1 tries to reduce lock_sock() contention in smc_tx_work().
Patch #2 removes timed work for corking, and let applications control
it. See TCP_CORK [2] MSG_MORE [3].
Patch #3 adds MSG_SENDPAGE_NOTLAST for corking more data when
sendfile().
Test environments:
- CPU Intel Xeon Platinum 8 core, mem 32 GiB, nic Mellanox CX4
- socket sndbuf / rcvbuf: 16384 / 131072 bytes
- server: smc_run nginx
- client: smc_run ./wrk -c 100 -t 2 -d 30 http://192.168.100.1:8080/4k.html
- payload: 4KB local disk file
Items QPS
sendfile off 272477.10
sendfile on (orig) 223622.79
sendfile on (this) 395847.21
This benchmark shows +45.28% improvement compared with sendfile off, and
+77.02% compared with original sendfile implement.
[1] https://man7.org/linux/man-pages/man2/sendfile.2.html
[2] https://linux.die.net/man/7/tcp
[3] https://man7.org/linux/man-pages/man2/send.2.html
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This introduces a new corked flag, MSG_SENDPAGE_NOTLAST, which is
involved in syscall sendfile() [1], it indicates this is not the last
page. So we can cork the data until the page is not specify this flag.
It has the same effect as MSG_MORE, but existed in sendfile() only.
This patch adds a option MSG_SENDPAGE_NOTLAST for corking data, try to
cork more data before sending when using sendfile(), which acts like
TCP's behaviour. Also, this reimplements the default sendpage to inform
that it is supported to some extent.
[1] https://man7.org/linux/man-pages/man2/sendfile.2.html
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Based on the manual of TCP_CORK [1] and MSG_MORE [2], these two options
have the same effect. Applications can set these options and informs the
kernel to pend the data, and send them out only when the socket or
syscall does not specify this flag. In other words, there's no need to
send data out by a delayed work, which will queue a lot of work.
This removes corked delayed work with SMC_TX_CORK_DELAY (250ms), and the
applications control how/when to send them out. It improves the
performance for sendfile and throughput, and remove unnecessary race of
lock_sock(). This also unlocks the limitation of sndbuf, and try to fill
it up before sending.
[1] https://linux.die.net/man/7/tcp
[2] https://man7.org/linux/man-pages/man2/send.2.html
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
According to the man page of TCP_CORK [1], if set, don't send out
partial frames. All queued partial frames are sent when option is
cleared again.
When applications call setsockopt to disable TCP_CORK, this call is
protected by lock_sock(), and tries to mod_delayed_work() to 0, in order
to send pending data right now. However, the delayed work smc_tx_work is
also protected by lock_sock(). There introduces lock contention for
sending data.
To fix it, send pending data directly which acts like TCP, without
lock_sock() protected in the context of setsockopt (already lock_sock()ed),
and cancel unnecessary dealyed work, which is protected by lock.
[1] https://linux.die.net/man/7/tcp
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Akhmat Karakotov says:
====================
Make hash rethink configurable
As it was shown in the report by Alexander Azimov, hash rethink at the
client-side may lead to connection timeout toward stateful anycast
services. Tom Herbert created a patchset to address this issue by applying
hash rethink only after a negative routing event (3RTOs) [1]. This change
also affects server-side behavior, which we found undesirable. This
patchset changes defaults in a way to make them safe: hash rethink at the
client-side is disabled and enabled at the server-side upon each RTO
event or in case of duplicate acknowledgments.
This patchset provides two options to change default behaviour. The hash
rethink may be disabled at the server-side by the new sysctl option.
Changes in the sysctl option don't affect default behavior at the
client-side.
Hash rethink can also be enabled/disabled with socket option or bpf
syscalls which ovewrite both default and sysctl settings. This socket
option is available on both client and server-side. This should provide
mechanics to enable hash rethink inside administrative domain, such as DC,
where hash rethink at the client-side can be desirable.
[1] https://lore.kernel.org/netdev/20210809185314.38187-1-tom@herbertland.com/
v2:
- Changed sysctl default to ENABLED in all patches. Reduced sysctl
and socket option size to u8. Fixed netns bug reported by kernel
test robot.
v3:
- Fixed bug with bad u8 comparison. Moved sk_txrehash to use less
bytes in struct. Added WRITE_ONCE() in setsockopt in and
READ_ONCE() in tcp_rtx_synack.
v4:
- Rebase and add documentation for sysctl option.
v5:
- Move sk_txrehash out of busy poll ifdef.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Disabling rehash behavior did not affect SYN ACK retransmits because hash
was forcefully changed bypassing the sk_rethink_hash function. This patch
adds a condition which checks for rehash mode before resetting hash.
Signed-off-by: Akhmat Karakotov <hmukos@yandex-team.ru>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Update Documentation/admin-guide/sysctl/net.rst with txrehash usage
description.
Signed-off-by: Akhmat Karakotov <hmukos@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add the SO_TXREHASH socket option to control hash rethink behavior per socket.
When default mode is set, sockets disable rehash at initialization and use
sysctl option when entering listen state. setsockopt() overrides default
behavior.
Signed-off-by: Akhmat Karakotov <hmukos@yandex-team.ru>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a per ns sysctl that controls the txhash rethink behavior:
net.core.txrehash. When enabled, the same behavior is retained,
when disabled, rethink is not performed. Sysctl is enabled by default.
Signed-off-by: Akhmat Karakotov <hmukos@yandex-team.ru>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
timestamping checks socket options during initialisation. For the field
bind_phc of the socket option SO_TIMESTAMPING it expects the value -1 if
PHC is not bound. Actually the value of bind_phc is 0 if PHC is not
bound. This results in the following output:
SIOCSHWTSTAMP: tx_type 0 requested, got 0; rx_filter 0 requested, got 0
SO_TIMESTAMP 0
SO_TIMESTAMPNS 0
SO_TIMESTAMPING flags 0, bind phc 0
not expected, flags 0, bind phc -1
This is fixed by setting default value and expected value of bind_phc to
0.
Fixes: 2214d70324 ("selftests/net: timestamping: support binding PHC")
Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sergey Shtylyov says:
====================
Remove some dead code in the Renesas Ethernet drivers
Here are 2 patches against DaveM's 'net-next.git' repo. The Renesas drivers
call their ndo_stop() methods directly and they always return 0, making the
result checks pointless, hence remove them...
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
sh_eth_close() always returns 0, hence the check in sh_eth_wol_restore()
is pointless (however we cannot change the prototype of sh_eth_close() as
it implements the driver's ndo_stop() method).
Found by Linux Verification Center (linuxtesting.org) with the SVACE static
analysis tool.
Signed-off-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
ravb_close() always returns 0, hence the check in ravb_wol_restore() is
pointless (however, we cannot change the prototype of ravb_close() as it
implements the driver's ndo_stop() method).
Found by Linux Verification Center (linuxtesting.org) with the SVACE static
analysis tool.
Signed-off-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
In case of error, the function devm_ioremap() returns NULL pointer
not ERR_PTR(). The IS_ERR() test in the return value check should
be replaced with NULL test.
Fixes: 1d14eb15dc ("net/fsl: xgmac_mdio: Use managed device resources")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Tobias Waldekranz <tobias@waldekranz.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add rtl_disable_exit_l1() for ensuring that the chip doesn't
inadvertently exit ASPM L1 when being in a low-power mode.
The new function is called from rtl_prepare_power_down() which
has to be moved in the code to avoid a forward declaration.
According to Realtek OCP register 0xc0ac shadows ERI register 0xd4
on RTL8168 versions from RTL8168g. This allows to simplify the
code a little.
v2:
- call rtl_disable_exit_l1() also if DASH or WoL are enabled
Suggested-by: Chun-Hao Lin <hau@realtek.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After following the call tree of phy_set_max_speed(), it became clear
that this function never returns anything but 0, so we can change its
result type to *void* and drop the result checks from the three drivers
that actually bothered to do it...
Found by Linux Verification Center (linuxtesting.org) with the SVACE static
analysis tool.
Signed-off-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tobias Waldekranz says:
====================
net: dsa: mv88e6xxx: Improve indirect addressing performance
The individual patches have all the details. This work was triggered
by recent work on a platform that took 16s (sic) to load the mv88e6xxx
module.
The first patch gets rid of most of that time by replacing a very long
delay with a tighter poll loop to wait for the busy bit to clear.
The second patch shaves off some more time by avoiding redundant
busy-bit-checks, saving 1 out of 4 MDIO operations for every register
read/write in the optimal case.
v1 -> v2:
- Make sure that we always poll the busy bit at least twice, in the
unlikely event that the first one is quick to query the hardware,
but is then scheduled out for a long time before the timeout is
checked.
v2 -> v3:
- Fallback to the longer sleeps after the initial two poll attempts.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Before this change, both the read and write callback would start out
by asserting that the chip's busy flag was cleared. However, both
callbacks also made sure to wait for the clearing of the busy bit
before returning - making the initial check superfluous. The only
time that would ever have an effect was if the busy bit was initially
set for some reason.
With that in mind, make sure to perform an initial check of the busy
bit, after which both read and write can rely the previous operation
to have waited for the bit to clear.
This cuts the number of operations on the underlying MDIO bus by 25%
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Avoid a long delay when a busy bit is still set and has to be polled
again.
Measurements on a system with 2 Opals (6097F) and one Agate (6352)
show that even with this much tighter loop, we have about a 50% chance
of the bit being cleared on the first poll, all other accesses see the
bit being cleared on the second poll.
On a standard MDIO bus running MDC at 2.5MHz, a single access with 32
bits of preamble plus 32 bits of data takes 64*(1/2.5MHz) = 25.6us.
This means that mv88e6xxx_smi_direct_wait took 26us + CPU overhead in
the fast scenario, but 26us + 1500us + 26us + CPU overhead in the slow
case - bringing the average close to 1ms.
With this change in place, the slow case is closer to 2*26us + CPU
overhead, with the average well below 100us - a 10x improvement.
This translates to real-world winnings. On a 3-chip 20-port system,
the modprobe time drops by 88%:
Before:
root@coronet:~# time modprobe mv88e6xxx
real 0m 15.99s
user 0m 0.00s
sys 0m 1.52s
After:
root@coronet:~# time modprobe mv88e6xxx
real 0m 2.21s
user 0m 0.00s
sys 0m 1.54s
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since ipv6 neighbor solicitation and advertisement messages
isn't handled gracefully in bond6 driver, we can see packet
drop due to inconsistency between mac address in the option
message and source MAC .
Another examples is ipv6 neighbor solicitation and advertisement
messages from VM via tap attached to host bridge, the src mac
might be changed through balance-alb mode, but it is not synced
with Link-layer address in the option message.
The patch implements bond6's tx handle for ipv6 neighbor
solicitation and advertisement messages.
Suggested-by: Hu Yadi <huyd12@chinatelecom.cn>
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: Sun Shouxin <sunshouxin@chinatelecom.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
When we replace TCP with SMC and a fallback occurs, there may be
some socket waitqueue entries remaining in smc socket->wq, such
as eppoll_entries inserted by userspace applications.
After the fallback, data flows over TCP/IP and only clcsocket->wq
will be woken up. Applications can't be notified by the entries
which were inserted in smc socket->wq before fallback. So we need
a mechanism to wake up smc socket->wq at the same time if some
entries remaining in it.
The current workaround is to transfer the entries from smc socket->wq
to clcsock->wq during the fallback. But this may cause a crash
like this:
general protection fault, probably for non-canonical address 0xdead000000000100: 0000 [#1] PREEMPT SMP PTI
CPU: 3 PID: 0 Comm: swapper/3 Kdump: loaded Tainted: G E 5.16.0+ #107
RIP: 0010:__wake_up_common+0x65/0x170
Call Trace:
<IRQ>
__wake_up_common_lock+0x7a/0xc0
sock_def_readable+0x3c/0x70
tcp_data_queue+0x4a7/0xc40
tcp_rcv_established+0x32f/0x660
? sk_filter_trim_cap+0xcb/0x2e0
tcp_v4_do_rcv+0x10b/0x260
tcp_v4_rcv+0xd2a/0xde0
ip_protocol_deliver_rcu+0x3b/0x1d0
ip_local_deliver_finish+0x54/0x60
ip_local_deliver+0x6a/0x110
? tcp_v4_early_demux+0xa2/0x140
? tcp_v4_early_demux+0x10d/0x140
ip_sublist_rcv_finish+0x49/0x60
ip_sublist_rcv+0x19d/0x230
ip_list_rcv+0x13e/0x170
__netif_receive_skb_list_core+0x1c2/0x240
netif_receive_skb_list_internal+0x1e6/0x320
napi_complete_done+0x11d/0x190
mlx5e_napi_poll+0x163/0x6b0 [mlx5_core]
__napi_poll+0x3c/0x1b0
net_rx_action+0x27c/0x300
__do_softirq+0x114/0x2d2
irq_exit_rcu+0xb4/0xe0
common_interrupt+0xba/0xe0
</IRQ>
<TASK>
The crash is caused by privately transferring waitqueue entries from
smc socket->wq to clcsock->wq. The owners of these entries, such as
epoll, have no idea that the entries have been transferred to a
different socket wait queue and still use original waitqueue spinlock
(smc socket->wq.wait.lock) to make the entries operation exclusive,
but it doesn't work. The operations to the entries, such as removing
from the waitqueue (now is clcsock->wq after fallback), may cause a
crash when clcsock waitqueue is being iterated over at the moment.
This patch tries to fix this by no longer transferring wait queue
entries privately, but introducing own implementations of clcsock's
callback functions in fallback situation. The callback functions will
forward the wakeup to smc socket->wq if clcsock->wq is actually woken
up and smc socket->wq has remaining entries.
Fixes: 2153bd1e3d ("net/smc: Transfer remaining wait queue entries during fallback")
Suggested-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Acked-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull irq fixes from Borislav Petkov:
- Drop an unused private data field in the AIC driver
- Various fixes to the realtek-rtl driver
- Make the GICv3 ITS driver compile again in !SMP configurations
- Force reset of the GICv3 ITSs at probe time to avoid issues during kexec
- Yet another kfree/bitmap_free conversion
- Various DT updates (Renesas, SiFive)
* tag 'irq_urgent_for_v5.17_rc2_p2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
dt-bindings: interrupt-controller: sifive,plic: Group interrupt tuples
dt-bindings: interrupt-controller: sifive,plic: Fix number of interrupts
dt-bindings: irqchip: renesas-irqc: Add R-Car V3U support
irqchip/gic-v3-its: Reset each ITS's BASERn register before probe
irqchip/gic-v3-its: Fix build for !SMP
irqchip/loongson-pch-ms: Use bitmap_free() to free bitmap
irqchip/realtek-rtl: Service all pending interrupts
irqchip/realtek-rtl: Fix off-by-one in routing
irqchip/realtek-rtl: Map control data to virq
irqchip/apple-aic: Drop unused ipi_hwirq field
Pull perf fixes from Borislav Petkov:
- Prevent accesses to the per-CPU cgroup context list from another CPU
except the one it belongs to, to avoid list corruption
- Make sure parent events are always woken up to avoid indefinite hangs
in the traced workload
* tag 'perf_urgent_for_v5.17_rc2_p2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/core: Fix cgroup event list management
perf: Always wake the parent event
Pull scheduler fix from Borislav Petkov:
"Make sure the membarrier-rseq fence commands are part of the reported
set when querying membarrier(2) commands through MEMBARRIER_CMD_QUERY"
* tag 'sched_urgent_for_v5.17_rc2_p2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/membarrier: Fix membarrier-rseq fence command missing from query bitmask
Pull x86 fixes from Borislav Petkov:
- Add another Intel CPU model to the list of CPUs supporting the
processor inventory unique number
- Allow writing to MCE thresholding sysfs files again - a previous
change had accidentally disabled it and no one noticed. Goes to show
how much is this stuff used
* tag 'x86_urgent_for_v5.17_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/cpu: Add Xeon Icelake-D to list of CPUs that support PPIN
x86/MCE/AMD: Allow thresholding interface updates after init
Merge misc fixes from Andrew Morton:
"12 patches.
Subsystems affected by this patch series: sysctl, binfmt, ia64, mm
(memory-failure, folios, kasan, and psi), selftests, and ocfs2"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
ocfs2: fix a deadlock when commit trans
jbd2: export jbd2_journal_[grab|put]_journal_head
psi: fix "defined but not used" warnings when CONFIG_PROC_FS=n
psi: fix "no previous prototype" warnings when CONFIG_CGROUPS=n
mm, kasan: use compare-exchange operation to set KASAN page tag
kasan: test: fix compatibility with FORTIFY_SOURCE
tools/testing/scatterlist: add missing defines
mm: page->mapping folio->mapping should have the same offset
memory-failure: fetch compound_head after pgmap_pfn_valid()
ia64: make IA64_MCA_RECOVERY bool instead of tristate
binfmt_misc: fix crash when load/unload module
include/linux/sysctl.h: fix register_sysctl_mount_point() return type
