Wei Yongjun [Tue, 15 Jun 2021 17:21:55 +0000 (17:21 +0000)]
net: stmmac: Fix error return code in ingenic_mac_probe()
Fix to return a negative error code from the error handling
case instead of 0, as done elsewhere in this function.
Fixes:
2bb4b98b60d7 ("net: stmmac: Add Ingenic SoCs MAC support.")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yang Yingliang [Wed, 16 Jun 2021 06:43:18 +0000 (14:43 +0800)]
net: chelsio: cxgb4: use eth_zero_addr() to assign zero address
Using eth_zero_addr() to assign zero address insetad of
inefficient copy from an array.
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Wed, 16 Jun 2021 07:52:34 +0000 (00:52 -0700)]
Merge branch 'cosa-cleanups'
Peng Li says:
====================
net: cosa: clean up some code style issues
This patchset clean up some code style issues.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:41 +0000 (15:23 +0800)]
net: cosa: remove redundant spaces
According to the chackpatch.pl,
no spaces is necessary at the start of a line,
no space is necessary after a cast.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:40 +0000 (15:23 +0800)]
net: cosa: remove trailing whitespaces
This patch removes trailing whitespaces.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:39 +0000 (15:23 +0800)]
net: cosa: add some required spaces
Add space required before the open parenthesis '(' and '{'.
Add space required after that close brace '}' and ','
Add spaces required around that '=' , '&', '*', '|', '+', '/' and '-'.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:38 +0000 (15:23 +0800)]
net: cosa: fix the code style issue about trailing statements
Trailing statements should be on next line.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:37 +0000 (15:23 +0800)]
net: cosa: fix the alignment issue
Alignment should match open parenthesis.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:36 +0000 (15:23 +0800)]
net: cosa: use BIT macro
This patch uses the BIT macro for setting individual bits,
to fix the following checkpatch.pl issue:
CHECK: Prefer using the BIT macro.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:35 +0000 (15:23 +0800)]
net: cosa: add necessary () to macro argument
Macro argument 'cosa' may be better as '(cosa)' to avoid
precedence issues.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:34 +0000 (15:23 +0800)]
net: cosa: remove redundant braces {}
This patch removes redundant braces {}, to fix the
checkpatch.pl warning:
"braces {} are not necessary for single statement blocks".
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:33 +0000 (15:23 +0800)]
net: cosa: add braces {} to all arms of the statement
Braces {} should be used on all arms of this statement.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:32 +0000 (15:23 +0800)]
net: cosa: fix the comments style issue
Networking block comments don't use an empty /* line,
use /* Comment...
Block comments use * on subsequent lines.
Block comments use a trailing */ on a separate line.
This patch fixes the comments style issues.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:31 +0000 (15:23 +0800)]
net: cosa: move out assignment in if condition
Should not use assignment in if condition.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:30 +0000 (15:23 +0800)]
net: cosa: replace comparison to NULL with "!chan->rx_skb"
According to the chackpatch.pl, comparison to NULL could
be written "!chan->rx_skb".
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:29 +0000 (15:23 +0800)]
net: cosa: fix the code style issue about "foo* bar"
Fix the checkpatch error as "foo* bar" should be "foo *bar".
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:28 +0000 (15:23 +0800)]
net: cosa: add blank line after declarations
This patch fixes the checkpatch error about missing a blank line
after declarations.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Wed, 16 Jun 2021 07:23:27 +0000 (15:23 +0800)]
net: cosa: remove redundant blank lines
This patch removes some redundant blank lines.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Zou Wei [Wed, 16 Jun 2021 04:07:27 +0000 (12:07 +0800)]
net: iosm: add missing MODULE_DEVICE_TABLE
This patch adds missing MODULE_DEVICE_TABLE definition which generates
correct modalias for automatic loading of this driver when it is built
as an external module.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zou Wei <zou_wei@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Wang Hai [Wed, 16 Jun 2021 04:21:06 +0000 (12:21 +0800)]
qlcnic: Use list_for_each_entry() to simplify code in qlcnic_main.c
Convert list_for_each() to list_for_each_entry() where
applicable. This simplifies the code.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Wed, 16 Jun 2021 03:33:38 +0000 (20:33 -0700)]
ethtool: add a stricter length check
There has been a few errors in the ethtool reply size calculations,
most of those are hard to trigger during basic testing because of
skb size rounding up and netdev names being shorter than max.
Add a more precise check.
This change will affect the value of payload length displayed in
case of -EMSGSIZE but that should be okay, "payload length" isn't
a well defined term here.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Maciej Żenczykowski [Wed, 16 Jun 2021 06:06:04 +0000 (23:06 -0700)]
inet_diag: add support for tw_mark
Timewait sockets have included mark since approx 4.18.
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jon Maxwell <jmaxwell37@gmail.com>
Fixes:
00483690552c ("tcp: Add mark for TIMEWAIT sockets")
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jon Maxwell <jmaxwell37@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jiapeng Chong [Wed, 16 Jun 2021 05:53:09 +0000 (13:53 +0800)]
net: mhi_net: make mhi_wwan_ops static
This symbol is not used outside of net.c, so marks it static.
Fix the following sparse warning:
drivers/net/mhi/net.c:385:23: warning: symbol 'mhi_wwan_ops' was not
declared. Should it be static?
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Wed, 16 Jun 2021 07:36:07 +0000 (00:36 -0700)]
Merge branch 'hns3-next'
Guangbin Huang says:
====================
net: hns3: updates for -next
This series includes some optimization in IO path for the HNS3 ethernet
driver.
====================
Cc: Loic Poulain <loic.poulain@linaro.org>
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Stephan Gerhold <stephan@gerhold.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yunsheng Lin [Wed, 16 Jun 2021 06:36:17 +0000 (14:36 +0800)]
net: hns3: use bounce buffer when rx page can not be reused
Currently rx page will be reused to receive future packet when
the stack releases the previous skb quickly. If the old page
can not be reused, a new page will be allocated and mapped,
which comsumes a lot of cpu when IOMMU is in the strict mode,
especially when the application and irq/NAPI happens to run on
the same cpu.
So allocate a new frag to memcpy the data to avoid the costly
IOMMU unmapping/mapping operation, and add "frag_alloc_err"
and "frag_alloc" stats in "ethtool -S ethX" cmd.
The throughput improves above 50% when running single thread of
iperf using TCP when IOMMU is in strict mode and iperf shares the
same cpu with irq/NAPI(rx_copybreak = 2048 and mtu = 1500).
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yunsheng Lin [Wed, 16 Jun 2021 06:36:16 +0000 (14:36 +0800)]
net: hns3: optimize the rx page reuse handling process
Current rx page offset only reset to zero when all the below
conditions are satisfied:
1. rx page is only owned by driver.
2. rx page is reusable.
3. the page offset that is above to be given to the stack has
reached the end of the page.
If the page offset is over the hns3_buf_size(), it means the
buffer below the offset of the page is usable when the above
condition 1 & 2 are satisfied, so page offset can be reset to
zero instead of increasing the offset. We may be able to always
reuse the first 4K buffer of a 64K page, which means we can
limit the hot buffer size as much as possible.
The above optimization is a side effect when refacting the
rx page reuse handling in order to support the rx copybreak.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yunsheng Lin [Wed, 16 Jun 2021 06:36:15 +0000 (14:36 +0800)]
net: hns3: support dma_map_sg() for multi frags skb
Using the queue based tx buffer, it is also possible to allocate a
sgl buffer, and use skb_to_sgvec() to convert the skb to the sgvec
in order to support the dma_map_sg() to decreases the overhead of
IOMMU mapping and unmapping.
Firstly, it reduces the number of buffers. For example, a tcp skb
may have a 66-byte header and 3 fragments of 4328, 32768, and 28064
bytes. With this patch, dma_map_sg() will combine them into two
buffers, 66-bytes header and one 65160-bytes fragment by using IOMMU.
Secondly, it reduces the number of dma mapping and unmapping. All the
original 4 buffers are mapped only once rather than 4 times.
The throughput improves above 10% when running single thread of iperf
using TCP when IOMMU is in strict mode.
Suggested-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Huazhong Tan [Wed, 16 Jun 2021 06:36:14 +0000 (14:36 +0800)]
net: hns3: add support to query tx spare buffer size for pf
Add support to query tx spare buffer size from configuration
file, and use this info to do spare buffer initialization when
the module parameter 'tx_spare_buf_size' is not specified.
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yunsheng Lin [Wed, 16 Jun 2021 06:36:13 +0000 (14:36 +0800)]
net: hns3: use tx bounce buffer for small packets
when the packet or frag size is small, it causes both security and
performance issue. As dma can't map sub-page, this means some extra
kernel data is visible to devices. On the other hand, the overhead
of dma map and unmap is huge when IOMMU is on.
So add a queue based tx shared bounce buffer to memcpy the small
packet when the len of the xmitted skb is below tx_copybreak.
Add tx_spare_buf_size module param to set the size of tx spare
buffer, and add set/get_tunable to set or query the tx_copybreak.
The throughtput improves from 30 Gbps to 90+ Gbps when running 16
netperf threads with 32KB UDP message size when IOMMU is in the
strict mode(tx_copybreak = 2000 and mtu = 1500).
Suggested-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yunsheng Lin [Wed, 16 Jun 2021 06:36:12 +0000 (14:36 +0800)]
net: hns3: refactor for hns3_fill_desc() function
Factor out hns3_fill_desc() so that it can be reused in the
tx bounce supporting.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Yunsheng Lin [Wed, 16 Jun 2021 06:36:11 +0000 (14:36 +0800)]
net: hns3: minor refactor related to desc_cb handling
desc_cb is used to store mapping and freeing info for the
corresponding desc, which is used in the cleaning process.
There will be more desc_cb type coming up when supporting the
tx bounce buffer, change desc_cb type to bit-wise value in order
to reduce the desc_cb type checking operation in the data path.
Also move the desc_cb type definition to hns3_enet.h because it
is only used in hns3_enet.c, and declare a local variable desc_cb
in hns3_clear_desc() to reduce lines of code.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Lorenzo Bianconi [Tue, 15 Jun 2021 13:27:41 +0000 (15:27 +0200)]
net: ti: add pp skb recycling support
As already done for mvneta and mvpp2, enable skb recycling for ti
ethernet drivers
ti driver on net-next:
----------------------
[perf top]
47.15% [kernel] [k] _raw_spin_unlock_irqrestore
11.77% [kernel] [k] __cpdma_chan_free
3.16% [kernel] [k] ___bpf_prog_run
2.52% [kernel] [k] cpsw_rx_vlan_encap
2.34% [kernel] [k] __netif_receive_skb_core
2.27% [kernel] [k] free_unref_page
2.26% [kernel] [k] kmem_cache_free
2.24% [kernel] [k] kmem_cache_alloc
1.69% [kernel] [k] __softirqentry_text_start
1.61% [kernel] [k] cpsw_rx_handler
1.19% [kernel] [k] page_pool_release_page
1.19% [kernel] [k] clear_bits_ll
1.15% [kernel] [k] page_frag_free
1.06% [kernel] [k] __dma_page_dev_to_cpu
0.99% [kernel] [k] memset
0.94% [kernel] [k] __alloc_pages_bulk
0.92% [kernel] [k] kfree_skb
0.85% [kernel] [k] packet_rcv
0.78% [kernel] [k] page_address
0.75% [kernel] [k] v7_dma_inv_range
0.71% [kernel] [k] __lock_text_start
[iperf3 tcp]
[ 5] 0.00-10.00 sec 873 MBytes 732 Mbits/sec 0 sender
[ 5] 0.00-10.01 sec 866 MBytes 726 Mbits/sec receiver
ti + skb recycling:
-------------------
[perf top]
40.58% [kernel] [k] _raw_spin_unlock_irqrestore
16.18% [kernel] [k] __softirqentry_text_start
10.33% [kernel] [k] __cpdma_chan_free
2.62% [kernel] [k] ___bpf_prog_run
2.05% [kernel] [k] cpsw_rx_vlan_encap
2.00% [kernel] [k] kmem_cache_alloc
1.86% [kernel] [k] __netif_receive_skb_core
1.80% [kernel] [k] kmem_cache_free
1.63% [kernel] [k] cpsw_rx_handler
1.12% [kernel] [k] cpsw_rx_mq_poll
1.11% [kernel] [k] page_pool_put_page
1.04% [kernel] [k] _raw_spin_unlock
0.97% [kernel] [k] clear_bits_ll
0.90% [kernel] [k] packet_rcv
0.88% [kernel] [k] __dma_page_dev_to_cpu
0.85% [kernel] [k] kfree_skb
0.80% [kernel] [k] memset
0.71% [kernel] [k] __lock_text_start
0.66% [kernel] [k] v7_dma_inv_range
0.64% [kernel] [k] gen_pool_free_owner
[iperf3 tcp]
[ 5] 0.00-10.00 sec 884 MBytes 742 Mbits/sec 0 sender
[ 5] 0.00-10.01 sec 878 MBytes 735 Mbits/sec receiver
Tested-by: Grygorii Strashko <grygorii.strashko@ti.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
M Chetan Kumar [Tue, 15 Jun 2021 13:08:22 +0000 (18:38 +0530)]
net: wwan: iosm: Fix htmldocs warnings
Fixes .rst file warnings seen on linux-next build.
Fixes:
f7af616c632e ("net: iosm: infrastructure")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: M Chetan Kumar <m.chetan.kumar@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Colin Ian King [Tue, 15 Jun 2021 10:14:57 +0000 (11:14 +0100)]
octeontx2-pf: Fix spelling mistake "morethan" -> "more than"
There is a spelling mistake in a dev_err message. Fix it.
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Colin Ian King [Tue, 15 Jun 2021 09:05:16 +0000 (10:05 +0100)]
net: dsa: b53: remove redundant null check on dev
The pointer dev can never be null, the null check is redundant
and can be removed. Cleans up a static analysis warning that
pointer priv is dereferencing dev before dev is being null
checked.
Addresses-Coverity: ("Dereference before null check")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jussi Maki [Tue, 15 Jun 2021 08:54:15 +0000 (08:54 +0000)]
net: bonding: Use per-cpu rr_tx_counter
The round-robin rr_tx_counter was shared across CPUs leading to
significant cache thrashing at high packet rates. This patch switches
the round-robin packet counter to use a per-cpu variable to decide
the destination slave.
On a test with 2x100Gbit ICE nic with pktgen_sample_04_many_flows.sh
(-s 64 -t 32) the tx rate was 19.6Mpps before and 22.3Mpps after
this patch.
"perf top -e cache_misses" before:
12.31% [bonding] [k] bond_xmit_roundrobin_slave_get
10.59% [sch_fq_codel] [k] fq_codel_dequeue
9.34% [kernel] [k] skb_release_data
after:
15.42% [sch_fq_codel] [k] fq_codel_dequeue
10.06% [kernel] [k] __memset
9.12% [kernel] [k] skb_release_data
Signed-off-by: Jussi Maki <joamaki@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Liu Shixin [Tue, 15 Jun 2021 02:14:44 +0000 (10:14 +0800)]
netlabel: Fix memory leak in netlbl_mgmt_add_common
Hulk Robot reported memory leak in netlbl_mgmt_add_common.
The problem is non-freed map in case of netlbl_domhsh_add() failed.
BUG: memory leak
unreferenced object 0xffff888100ab7080 (size 96):
comm "syz-executor537", pid 360, jiffies
4294862456 (age 22.678s)
hex dump (first 32 bytes):
05 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
fe 00 00 00 00 00 00 00 00 00 00 00 00 00 00 01 ................
backtrace:
[<
0000000008b40026>] netlbl_mgmt_add_common.isra.0+0xb2a/0x1b40
[<
000000003be10950>] netlbl_mgmt_add+0x271/0x3c0
[<
00000000c70487ed>] genl_family_rcv_msg_doit.isra.0+0x20e/0x320
[<
000000001f2ff614>] genl_rcv_msg+0x2bf/0x4f0
[<
0000000089045792>] netlink_rcv_skb+0x134/0x3d0
[<
0000000020e96fdd>] genl_rcv+0x24/0x40
[<
0000000042810c66>] netlink_unicast+0x4a0/0x6a0
[<
000000002e1659f0>] netlink_sendmsg+0x789/0xc70
[<
000000006e43415f>] sock_sendmsg+0x139/0x170
[<
00000000680a73d7>] ____sys_sendmsg+0x658/0x7d0
[<
0000000065cbb8af>] ___sys_sendmsg+0xf8/0x170
[<
0000000019932b6c>] __sys_sendmsg+0xd3/0x190
[<
00000000643ac172>] do_syscall_64+0x37/0x90
[<
000000009b79d6dc>] entry_SYSCALL_64_after_hwframe+0x44/0xae
Fixes:
63c416887437 ("netlabel: Add network address selectors to the NetLabel/LSM domain mapping")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Liu Shixin <liushixin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 15 Jun 2021 18:14:21 +0000 (11:14 -0700)]
Merge tag 'mlx5-updates-2021-06-14' of git://git./linux/kernel/git/saeed/linux
Saeed Mahameed says:
====================
mlx5-updates-2021-06-14
1) Trivial Lag refactroing in preparation for upcomming Single FDB lag feature
- First 3 patches
2) Scalable IRQ distriburion for Sub-functions
A subfunction (SF) is a lightweight function that has a parent PCI
function (PF) on which it is deployed.
Currently, mlx5 subfunction is sharing the IRQs (MSI-X) with their
parent PCI function.
Before this series the PF allocates enough IRQs to cover
all the cores in a system, Newly created SFs will re-use all the IRQs
that the PF has allocated for itself.
Hence, the more SFs are created, there are more EQs per IRQs. Therefore,
whenever we handle an interrupt, we need to pull all SFs EQs and PF EQs
instead of PF EQs without SFs on the system. This leads to a hard impact
on the performance of SFs and PF.
For example, on machine with:
Intel(R) Xeon(R) CPU E5-2697 v3 @ 2.60GHz with 56 cores.
PCI Express 3 with BW of 126 Gb/s.
ConnectX-5 Ex; EDR IB (100Gb/s) and 100GbE; dual-port QSFP28; PCIe4.0 x16.
test case: iperf TX BW single CPU, affinity of app and IRQ are the same.
PF only: no SFs on the system, 56 IRQs.
SF (before), 250 SFs Sharing the same 56 IRQs .
SF (now), 250 SFs + 255 avaiable IRQs for the NIC. (please see IRQ spread scheme below).
application SF-IRQ channel BW(Gb/sec) interrupts/sec
iperf TX affinity
PF only cpu={0} cpu={0} cpu={0} 79 8200
SF (before) cpu={0} cpu={0} cpu={0} 51.3 (-35%) 9500
SF (now) cpu={0} cpu={0} cpu={0} 78 (-2%) 8200
command:
$ taskset -c 0 iperf -c 11.1.1.1 -P 3 -i 6 -t 30 | grep SUM
The different between the SF examples is that before this series we
allocate num_cpus (56) IRQs, and all of them were shared among the PF
and the SFs. And after this series, we allocate 255 IRQs, and we spread
the SFs among the above IRQs. This have significantly decreased the load
on each IRQ and the number of EQs per IRQ is down by 95% (251->11).
In this patchset the solution proposed is to have a dedicated IRQ pool
for SFs to use. the pool will allocate a large number of IRQs
for SFs to grab from in order to minimize irq sharing between the
different SFs.
IRQs will not be requested from the OS until they are 1st requested by
an SF consumer, and will be eventually released when the last SF consumer
releases them.
For the detailed IRQ spread and allocation scheme please see last patch:
("net/mlx5: Round-Robin EQs over IRQs")
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 15 Jun 2021 18:11:05 +0000 (11:11 -0700)]
Merge branch 'occteontx2-rate-limit-offload'
Subbaraya Sundeep says:
====================
octeontx2: Add ingress ratelimit offload
This patchset adds ingress rate limiting hardware
offload support for CN10K silicons. Police actions
are added for TC matchall and flower filters.
CN10K has ingress rate limiting feature where
a receive queue is mapped to bandwidth profile
and the profile is configured with rate and burst
parameters by software. CN10K hardware supports
three levels of ingress policing or ratelimiting.
Multiple leaf profiles can point to a single mid
level profile and multiple mid level profile can
point to a single top level one. Only leaf level
profiles are used for configuring rate limiting.
Patch 1 adds the new bandwidth profile contexts
in AF driver similar to other hardware contexts
Patch 2 adds the debugfs changes to dump bandwidth
profile contexts
Patch 3 adds support for police action with TC matchall filter
Patch 4 uses NL_SET_ERR_MSG_MOD for tc code
Patch 5 adds support for police action with TC flower filter
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Subbaraya Sundeep [Tue, 15 Jun 2021 11:34:31 +0000 (17:04 +0530)]
octeontx2-pf: Add police action for TC flower
Added police action for ingress TC flower
hardware offload. With this rate limiting can be
done per flow. Since rate limiting is tied to
RQs in hardware the number of TC flower filters
with action as police is limited to number
of receive queues of the interface. Both bps
and pps modes are supported.
Examples to rate limit a flow:
$ ethtool -K eth0 hw-tc-offload on
$ tc qdisc add dev eth0 ingress
$ tc filter add dev eth0 parent ffff: protocol ip \
flower ip_proto udp dst_port 80 action \
police rate 100Mbit burst 32Kbit
$ tc filter add dev eth0 parent ffff: \
protocol ip flower dst_mac 5e:b2:34:ee:29:49 \
action police pkts_rate 5000 pkts_burst 2048
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Subbaraya Sundeep [Tue, 15 Jun 2021 11:34:30 +0000 (17:04 +0530)]
octeontx2-pf: Use NL_SET_ERR_MSG_MOD for TC
This patch modifies all netdev_err messages in
tc code to NL_SET_ERR_MSG_MOD. NL_SET_ERR_MSG_MOD
does not support format specifiers yet hence
netdev_err messages with only strings are modified.
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sunil Goutham [Tue, 15 Jun 2021 11:34:29 +0000 (17:04 +0530)]
octeontx2-pf: TC_MATCHALL ingress ratelimiting offload
Add TC_MATCHALL ingress ratelimiting offload support with POLICE
action for entire traffic coming into the interface.
Eg: To ratelimit ingress traffic to 100Mbps
$ ethtool -K eth0 hw-tc-offload on
$ tc qdisc add dev eth0 clsact
$ tc filter add dev eth0 ingress matchall skip_sw \
action police rate 100Mbit burst 32Kbit
To support this, a leaf level bandwidth profile is allocated and all
RQs' contexts used by this interface are updated to point to it.
And the leaf level bandwidth profile is configured with user specified
rate and burst sizes.
Co-developed-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sunil Goutham [Tue, 15 Jun 2021 11:34:28 +0000 (17:04 +0530)]
octeontx2-af: cn10k: Debugfs support for bandwidth profiles
Added support for dumping current resource status of bandwidth
profiles and contexts of allocated profiles via debugfs.
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sunil Goutham [Tue, 15 Jun 2021 11:34:27 +0000 (17:04 +0530)]
octeontx2-af: cn10k: Bandwidth profiles config support
CN10K silicons supports hierarchial ingress packet ratelimiting.
There are 3 levels of profilers supported leaf, mid and top.
Ratelimiting is done after packet forwarding decision is taken
and a NIXLF's RQ is identified to DMA the packet. RQ's context
points to a leaf bandwidth profile which can be configured
to achieve desired ratelimit.
This patch adds logic for management of these bandwidth profiles
ie profile alloc, free, context update etc.
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 15 Jun 2021 18:03:17 +0000 (11:03 -0700)]
Merge branch 'pci200syn-cleanups'
Peng Li says:
====================
net: pci200syn: clean up some code style issues
This patchset clean up some code style issues.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 13:54:23 +0000 (21:54 +0800)]
net: pci200syn: fix the comments style issue
Networking block comments don't use an empty /* line,
use /* Comment...
This patch fixes the comments style issues.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 13:54:22 +0000 (21:54 +0800)]
net: pci200syn: add necessary () to macro argument
Macro argument 'card' may be better as '(card)' to
avoid precedence issues.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 13:54:21 +0000 (21:54 +0800)]
net: pci200syn: add some required spaces
Add spaces required after that close brace '}'.
Add spaces required before the open parenthesis '('.
Add spaces required after that ','.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 13:54:20 +0000 (21:54 +0800)]
net: pci200syn: replace comparison to NULL with "!card"
According to the chackpatch.pl, comparison to NULL could
be written "!card".
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 13:54:19 +0000 (21:54 +0800)]
net: pci200syn: add blank line after declarations
This patch fixes the checkpatch error about missing a blank line
after declarations.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 13:54:18 +0000 (21:54 +0800)]
net: pci200syn: remove redundant blank lines
This patch removes some redundant blank lines.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 15 Jun 2021 17:55:18 +0000 (10:55 -0700)]
Merge branch 'z85230-cleanups'
Peng Li says:
====================
net: z85230: clean up some code style issues
This patchset clean up some code style issues.
---
Change Log:
V1 -> V2:
1, fix the comments from Andrew, add commit message to [patch 04/11]
about remove volatile.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 02:43:45 +0000 (10:43 +0800)]
net: z85230: remove unnecessary out of memory message
This patch removes unnecessary out of memory message,
to fix the following checkpatch.pl warning:
"WARNING: Possible unnecessary 'out of memory' message"
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 02:43:44 +0000 (10:43 +0800)]
net: z85230: fix the code style issue about open brace {
This patch fixes the code style issue according to checkpatch.pl error:
"ERROR: that open brace { should be on the previous line".
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 02:43:43 +0000 (10:43 +0800)]
net: z85230: add some required spaces
Add space required before the open parenthesis '(' and '{'.
Add space required after that close brace '}' and ','
Add spaces required around that '=' , '&', '*', '|', '+', '/' and '-'.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 02:43:42 +0000 (10:43 +0800)]
net: z85230: remove trailing whitespaces
This patch removes trailing whitespaces.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 02:43:41 +0000 (10:43 +0800)]
net: z85230: fix the code style issue about "if..else.."
According to the chackpatch.pl, else should follow close brace '}',
braces {} should be used on all arms of this statement.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 02:43:40 +0000 (10:43 +0800)]
net: z85230: fix the comments style issue
Networking block comments don't use an empty /* line,
use /* Comment...
Block comments use * on subsequent lines.
Block comments use a trailing */ on a separate line.
This patch fixes the comments style issues.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 02:43:39 +0000 (10:43 +0800)]
net: z85230: replace comparison to NULL with "!skb"
According to the chackpatch.pl, comparison to NULL could
be written "!skb".
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 02:43:38 +0000 (10:43 +0800)]
net: z85230: fix the code style issue about EXPORT_SYMBOL(foo)
According to the chackpatch.pl,
EXPORT_SYMBOL(foo); should immediately follow its function/variable.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 02:43:37 +0000 (10:43 +0800)]
net: z85230: add blank line after declarations
This patch fixes the checkpatch error about missing a blank line
after declarations.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Peng Li [Tue, 15 Jun 2021 02:43:36 +0000 (10:43 +0800)]
net: z85230: remove redundant blank lines
This patch removes some redundant blank lines.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Boris Sukholitko [Mon, 14 Jun 2021 11:13:22 +0000 (14:13 +0300)]
net/sched: cls_flower: Remove match on n_proto
The following flower filters fail to match packets:
tc filter add dev eth0 ingress protocol 0x8864 flower \
action simple sdata hi64
tc filter add dev eth0 ingress protocol 802.1q flower \
vlan_ethtype 0x8864 action simple sdata "hi vlan"
The protocol 0x8864 (ETH_P_PPP_SES) is a tunnel protocol. As such, it is
being dissected by __skb_flow_dissect and it's internal protocol is
being set as key->basic.n_proto. IOW, the existence of ETH_P_PPP_SES
tunnel is transparent to the callers of __skb_flow_dissect.
OTOH, in the filters above, cls_flower configures its key->basic.n_proto
to the ETH_P_PPP_SES value configured by the user. Matching on this key
fails because of __skb_flow_dissect "transparency" mentioned above.
In the following, I would argue that the problem lies with cls_flower,
unnessary attempting key->basic.n_proto match.
There are 3 close places in fl_set_key in cls_flower setting up
mask->basic.n_proto. They are (in reverse order of appearance in the
code) due to:
(a) No vlan is given: use TCA_FLOWER_KEY_ETH_TYPE parameter
(b) One vlan tag is given: use TCA_FLOWER_KEY_VLAN_ETH_TYPE
(c) Two vlans are given: use TCA_FLOWER_KEY_CVLAN_ETH_TYPE
The match in case (a) is unneeded because flower has no its own
eth_type parameter. It was removed by Jamal Hadi Salim in commit
488b41d020fb06428b90289f70a41210718f52b7 in iproute2. For
TCA_FLOWER_KEY_ETH_TYPE the userspace uses the generic tc filter
protocol field. Therefore the match for the case (a) is done by tc
itself.
The matches in cases (b), (c) are unneeded because the protocol will
appear in and will be matched by flow_dissector_key_vlan.vlan_tpid.
Therefore in the best case, key->basic.n_proto will try to repeat vlan
key match again.
The below patch removes mask->basic.n_proto setting and resets it to 0
in case (c).
Signed-off-by: Boris Sukholitko <boris.sukholitko@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Matteo Croce [Mon, 14 Jun 2021 02:25:04 +0000 (04:25 +0200)]
stmmac: align RX buffers
On RX an SKB is allocated and the received buffer is copied into it.
But on some architectures, the memcpy() needs the source and destination
buffers to have the same alignment to be efficient.
This is not our case, because SKB data pointer is misaligned by two bytes
to compensate the ethernet header.
Align the RX buffer the same way as the SKB one, so the copy is faster.
An iperf3 RX test gives a decent improvement on a RISC-V machine:
before:
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.00 sec 733 MBytes 615 Mbits/sec 88 sender
[ 5] 0.00-10.01 sec 730 MBytes 612 Mbits/sec receiver
after:
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.00 sec 1.10 GBytes 942 Mbits/sec 0 sender
[ 5] 0.00-10.00 sec 1.09 GBytes 940 Mbits/sec receiver
And the memcpy() overhead during the RX drops dramatically.
before:
Overhead Shared O Symbol
43.35% [kernel] [k] memcpy
33.77% [kernel] [k] __asm_copy_to_user
3.64% [kernel] [k] sifive_l2_flush64_range
after:
Overhead Shared O Symbol
45.40% [kernel] [k] __asm_copy_to_user
28.09% [kernel] [k] memcpy
4.27% [kernel] [k] sifive_l2_flush64_range
Signed-off-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Shay Drory [Tue, 23 Feb 2021 09:57:32 +0000 (11:57 +0200)]
net/mlx5: Round-Robin EQs over IRQs
Whenever users provided affinity for an EQ creation request, map the
EQ to a matching IRQ.
Matching IRQ=IRQ with the same affinity and type (completion/control) of
the EQ created.
This mapping is being done in agressive dedicated IRQ allocation scheme,
which described bellow.
First, we check whether there is a matching IRQ that his min threshold
is not exhausted.
- min_eqs_threshold = 3 for control EQ.
- min_eqs_threshold = 1 for completion EQ.
In case no matching IRQ was found, try to request a new IRQ.
In case we can't request a new IRQ, reuse least-used matching IRQ.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Shay Drory [Tue, 11 May 2021 15:48:30 +0000 (18:48 +0300)]
net/mlx5: Separate between public and private API of sf.h
Move mlx5_sf_max_functions() and friends from the privete sf/sf.h
to the public lib/sf.h. This is done in order to have one direction
include paths.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Shay Drory [Mon, 10 May 2021 06:10:43 +0000 (09:10 +0300)]
net/mlx5: Enlarge interrupt field in CREATE_EQ
FW is now supporting more than 256 MSI-X per PF (up to 2K).
Hence, enlarge interrupt field in CREATE_EQ to make use of the new
MSI-X's.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Shay Drory [Tue, 23 Feb 2021 09:48:17 +0000 (11:48 +0200)]
net/mlx5: Allocating a pool of MSI-X vectors for SFs
SFs (Sub Functions) currently use IRQs from the global IRQ table their
parent Physical Function have. In order to better scale, we need to
allocate more IRQs and share them between different SFs.
Driver will maintain 3 separated irq pools:
1. A pool that serve the PF consumer (PF's netdev, rdma stacks), similar
to what the driver had before this patch. i.e, this pool will share irqs
between rdma and netev, and will keep the irq indexes and allocation
order. The last is important for PF netdev rmap (aRFS).
2. A pool of control IRQs for SFs. The size of this pool is the number
of SFs that can be created divided by SFS_PER_IRQ. This pool will serve
the control path EQs of the SFs.
3. A pool of completion data path IRQs for SFs transport queues. The
size of this pool is:
num_irqs_allocated - pf_pool_size - sf_ctrl_pool_size.
This pool will served netdev and rdma stacks. Moreover, rmap is not
supported on SFs.
Sharing methodology of the SFs pools is explained in the next patch.
Important note: rmap is not supported on SFs because rmap mapping cannot
function correctly for IRQs that are shared for different core/netdev RX
rings.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Shay Drory [Tue, 23 Feb 2021 09:38:52 +0000 (11:38 +0200)]
net/mlx5: Change IRQ storage logic from static to dynamic
Store newly created IRQs in the xarray DB instead of a static array,
so we will be able to store only IRQs which are being used.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Shay Drory [Tue, 23 Feb 2021 09:24:47 +0000 (11:24 +0200)]
net/mlx5: Moving rmap logic to EQs
IRQs are being simplified in order to ease their sharing and any feature
specific object will be moved to upper layer.
Hence we move rmap object into eq_table.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Shay Drory [Tue, 23 Feb 2021 09:15:43 +0000 (11:15 +0200)]
net/mlx5: Extend mlx5_irq_request to request IRQ from the kernel
Extend mlx5_irq_request so that IRQs will be requested upon EQ creation,
and not on driver boot.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Shay Drory [Tue, 23 Feb 2021 09:08:26 +0000 (11:08 +0200)]
net/mlx5: Removing rmap per IRQ
In next patches, IRQs will be requested according to demand, instead of
statically on driver boot.
Also, currently, rmap is managed by the IRQ layer. rmap management will
move out from the IRQ layer in future patches.
Therefore, we want to remove the IRQ from the rmap, when IRQ is destroyed,
instead of removing all the IRQs from the rmap when irq_table is destroyed.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Leon Romanovsky [Thu, 14 Jan 2021 13:19:40 +0000 (15:19 +0200)]
net/mlx5: Clean license text in eq.[c|h] files
The eq.[c|h] files are under major rewrite. so use this opportunity and
update their copyright and license texts.
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Leon Romanovsky [Tue, 23 Feb 2021 08:37:05 +0000 (10:37 +0200)]
net/mlx5: Provide cpumask at EQ creation phase
The users of EQ are running their code on different CPUs and with
various affinity patterns. Move the cpumask setting close to their
actual usage.
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Shay Drory [Tue, 6 Apr 2021 18:42:17 +0000 (21:42 +0300)]
net/mlx5: Introduce API for request and release IRQs
Introduce new API that will allow IRQs users to hold a pointer to
mlx5_irq.
In the end of this series, IRQs will be allocated on demand. Hence,
this will allow us to properly manage and use IRQs.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Leon Romanovsky [Tue, 23 Feb 2021 07:32:21 +0000 (09:32 +0200)]
net/mlx5: Delay IRQ destruction till all users are gone
Shared IRQ are consumed by multiple EQ users and in order to properly
initialize and later release such IRQs, we add kref counting of IRQ
structure.
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Mark Bloch [Wed, 14 Apr 2021 08:18:09 +0000 (08:18 +0000)]
net/mlx5: Change ownership model for lag
Lag is used to combine two PCI functions of the same HCA into a single
logical unit. This is a core functionality and as such should be managed by
the core driver. Currently this isn't the case. While we store the lag
software structure inside the lower device, its lifetime (creation /
destruction) is dictated by the mlx5e part. Change the ownership model so
lag is tied to the lifetime of the lower level driver instead to the
mlx5e part.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Mark Bloch [Wed, 14 Apr 2021 07:28:19 +0000 (07:28 +0000)]
net/mlx5: Lag, Don't rescan if the device is going down
If MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV is set it means the device is going
down and mlx5_rescan_drivers_locked() shouldn't be called.
With this patch and the previous one in the series, unbinding a PCI
function when its netdev is part of a bond works and leaves the system in a
working state.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Mark Bloch [Wed, 14 Apr 2021 07:16:40 +0000 (07:16 +0000)]
net/mlx5: Lag, refactor disable flow
When a net device is removed (can happen if the PCI function is unbound
from the system) it's not enough to destroy the hardware lag. The system
should recreate the original devices that were present before the lag.
As the same flow is done when a net device is removed from the bond
refactor and reuse the code.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Loic Poulain [Mon, 14 Jun 2021 16:56:36 +0000 (18:56 +0200)]
net: wwan: Fix WWAN config symbols
There is not strong reason to have both WWAN and WWAN_CORE symbols,
Let's build the WWAN core framework when WWAN is selected, in the
same way as for other subsystems.
This fixes issue with mhi_net selecting WWAN_CORE without WWAN and
reported by kernel test robot:
Kconfig warnings: (for reference only)
WARNING: unmet direct dependencies detected for WWAN_CORE
Depends on NETDEVICES && WWAN
Selected by
- MHI_NET && NETDEVICES && NET_CORE && MHI_BUS
Fixes:
9a44c1cc6388 ("net: Add a WWAN subsystem")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean [Mon, 14 Jun 2021 13:58:19 +0000 (16:58 +0300)]
net: flow_dissector: fix RPS on DSA masters
After the blamed patch, __skb_flow_dissect() on the DSA master stopped
adjusting for the length of the DSA headers. This is because it was told
to adjust only if the needed_headroom is zero, aka if there is no DSA
header. Of course, the adjustment should be done only if there _is_ a
DSA header.
Modify the comment too so it is clearer.
Fixes:
4e50025129ef ("net: dsa: generalize overhead for taggers that use both headers and trailers")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean [Mon, 14 Jun 2021 13:50:50 +0000 (16:50 +0300)]
net: dsa: sja1105: constify the sja1105_regs structures
The struct sja1105_regs tables are not modified during the runtime of
the driver, so they can be made constant. In fact, struct sja1105_info
already holds a const pointer to these.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 14 Jun 2021 20:12:59 +0000 (13:12 -0700)]
Merge branch 'tja1103-improvewmentsa'
Vladimir Oltean says:
====================
Fixes and improvements to TJA1103 PHY driver
This series contains:
- an erratum workaround for the TJA1103 PHY integrated in SJA1110
- an adaptation of the driver so it prints less unnecessary information
when probing on SJA1110
- a PTP RX timestamping bug fix and a clarification patch
Targeting net-next since the PHY support is currently in net-next only.
Changes in v3:
Added one more patch which improves the readability of
nxp_c45_reconstruct_ts.
Changes in v2:
Added a comment to the hardware workaround procedure.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean [Mon, 14 Jun 2021 13:44:41 +0000 (16:44 +0300)]
net: phy: nxp-c45-tja11xx: enable MDIO write access to the master/slave registers
The SJA1110 switch integrates TJA1103 PHYs, but in SJA1110 switch rev B
silicon, there is a bug in that the registers for selecting the 100base-T1
autoneg master/slave roles are not writable.
To enable write access to the master/slave registers, these additional
PHY writes are necessary during initialization.
The issue has been corrected in later SJA1110 silicon versions and is
not present in the standalone PHY variants, but applying the workaround
unconditionally in the driver should not do any harm.
Suggested-by: Radu Pirea (NXP OSS) <radu-nicolae.pirea@oss.nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean [Mon, 14 Jun 2021 13:44:40 +0000 (16:44 +0300)]
net: phy: nxp-c45-tja11xx: fix potential RX timestamp wraparound
The reconstruction procedure for partial timestamps reads the current
PTP time and fills in the low 2 bits of the second portion, as well as
the nanoseconds portion, from the actual hardware packet timestamp.
Critically, the reconstruction procedure works because it assumes that
the current PTP time is strictly larger than the hardware timestamp was:
it detects a 2-bit wraparound of the 'seconds' portion by checking whether
the 'seconds' portion of the partial hardware timestamp is larger than
the 'seconds' portion of the current time. That can only happen if the
hardware timestamp was captured by the PHY during the last phase of a
'modulo 4 seconds' interval, and the current PTP time was read by the
driver during the initial phase of the next 'modulo 4 seconds' interval.
The partial RX timestamps are added to priv->rx_queue in
nxp_c45_rxtstamp() and they are processed potentially in parallel by the
aux worker thread in nxp_c45_do_aux_work(). This means that it is
possible for nxp_c45_do_aux_work() to process more than one RX timestamp
during the same schedule.
There is one premature optimization that will cause issues: for RX
timestamping, the driver reads the current time only once, and it uses
that to reconstruct all PTP RX timestamps in the queue. For the second
and later timestamps, this will be an issue if we are processing two RX
timestamps which are to the left and to the right, respectively, of a
4-bit wraparound of the 'seconds' portion of the PTP time, and the
current PTP time is also pre-wraparound.
0.
000000000 4.
000000000 8.
000000000 12.
000000000
|..................|..................|..................|............>
^ ^ ^ ^ time
| | | |
| | | process hwts 1 and hwts 2
| | |
| | hwts 2
| |
| read current PTP time
|
hwts 1
What will happen in that case is that hwts 2 (post-wraparound) will use
a stale current PTP time that is pre-wraparound.
But nxp_c45_reconstruct_ts will not detect this condition, because it is
not coded up for it, so it will reconstruct hwts 2 with a current time
from the previous 4 second interval (i.e. 0.something instead of
4.something).
This is solvable by making sure that the full 64-bit current time is
always read after the PHY has taken the partial RX timestamp. We do this
by reading the current PTP time for every timestamp in the RX queue.
Fixes:
514def5dd339 ("phy: nxp-c45-tja11xx: add timestamping support")
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean [Mon, 14 Jun 2021 13:44:39 +0000 (16:44 +0300)]
net: phy: nxp-c45-tja11xx: express timestamp wraparound interval in terms of TS_SEC_MASK
nxp_c45_reconstruct_ts() takes a partial hardware timestamp in @hwts,
with 2 bits of the 'seconds' portion, and a full PTP time in @ts.
It patches in the lower bits of @hwts into @ts, and to ensure that the
reconstructed timestamp is correct, it checks whether the lower 2 bits
of @hwts are not in fact higher than the lower 2 bits of @ts. This is
not logically possible because, according to the calling convention, @ts
was collected later in time than @hwts, but due to two's complement
arithmetic it can actually happen, because the current PTP time might
have wrapped around between when @hwts was collected and when @ts was,
yielding the lower 2 bits of @ts smaller than those of @hwts.
To correct for that situation which is expected to happen under normal
conditions, the driver subtracts exactly one wraparound interval from
the reconstructed timestamp, since the upper bits of that need to
correspond to what the upper bits of @hwts were, not to what the upper
bits of @ts were.
Readers might be confused because the driver denotes the amount of bits
that the partial hardware timestamp has to offer as TS_SEC_MASK
(timestamp mask for seconds). But it subtracts a seemingly unrelated
BIT(2), which is in fact more subtle: if the hardware timestamp provides
2 bits of partial 'seconds' timestamp, then the wraparound interval is
2^2 == BIT(2).
But nonetheless, it is better to express the wraparound interval in
terms of a definition we already have, so replace BIT(2) with
1 + GENMASK(1, 0) which produces the same result but is clearer.
Suggested-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean [Mon, 14 Jun 2021 13:44:38 +0000 (16:44 +0300)]
net: phy: nxp-c45-tja11xx: demote the "no PTP support" message to debug
The SJA1110 switch integrates these PHYs, and they do not have support
for timestamping. This message becomes quite overwhelming:
[ 10.056596] NXP C45 TJA1103 spi1.0-base-t1:01: the phy does not support PTP
[ 10.112625] NXP C45 TJA1103 spi1.0-base-t1:02: the phy does not support PTP
[ 10.167461] NXP C45 TJA1103 spi1.0-base-t1:03: the phy does not support PTP
[ 10.223510] NXP C45 TJA1103 spi1.0-base-t1:04: the phy does not support PTP
[ 10.278239] NXP C45 TJA1103 spi1.0-base-t1:05: the phy does not support PTP
[ 10.332663] NXP C45 TJA1103 spi1.0-base-t1:06: the phy does not support PTP
[ 15.390828] NXP C45 TJA1103 spi1.2-base-t1:01: the phy does not support PTP
[ 15.445224] NXP C45 TJA1103 spi1.2-base-t1:02: the phy does not support PTP
[ 15.499673] NXP C45 TJA1103 spi1.2-base-t1:03: the phy does not support PTP
[ 15.554074] NXP C45 TJA1103 spi1.2-base-t1:04: the phy does not support PTP
[ 15.608516] NXP C45 TJA1103 spi1.2-base-t1:05: the phy does not support PTP
[ 15.662996] NXP C45 TJA1103 spi1.2-base-t1:06: the phy does not support PTP
So reduce its log level to debug.
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 14 Jun 2021 20:06:53 +0000 (13:06 -0700)]
Merge branch 'Ingenic-SOC-mac-support'
Zhou Yanjie says:
====================
Add Ingenic SoCs MAC support.
v2->v3:
1.Add "ingenic,mac.yaml" for Ingenic SoCs.
2.Change tx clk delay and rx clk delay from hardware value to ps.
3.return -EINVAL when a unsupported value is encountered when
parsing the binding.
4.Simplify the code of the RGMII part of X2000 SoC according to
Andrew Lunn’s suggestion.
5.Follow the example of "dwmac-mediatek.c" to improve the code
that handles delays according to Andrew Lunn’s suggestion.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
周琰杰 (Zhou Yanjie) [Mon, 14 Jun 2021 17:15:37 +0000 (01:15 +0800)]
net: stmmac: Add Ingenic SoCs MAC support.
Add support for Ingenic SoC MAC glue layer support for the stmmac
device driver. This driver is used on for the MAC ethernet controller
found in the JZ4775 SoC, the X1000 SoC, the X1600 SoC, the X1830 SoC,
and the X2000 SoC.
Signed-off-by: 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
周琰杰 (Zhou Yanjie) [Mon, 14 Jun 2021 17:15:36 +0000 (01:15 +0800)]
dt-bindings: dwmac: Add bindings for new Ingenic SoCs.
Add the dwmac bindings for the JZ4775 SoC, the X1000 SoC,
the X1600 SoC, the X1830 SoC and the X2000 SoC from Ingenic.
Signed-off-by: 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 14 Jun 2021 20:04:26 +0000 (13:04 -0700)]
Merge branch 'marvell-prestera-devlink'
Oleksandr Mazur says:
====================
Marvell Prestera driver implementation of devlink functionality.
This patch series implement Prestera Switchdev driver devlink traps,
that are registered within the driver, as well as extend current devlink
functionality by adding new hard drop statistics counter, that could be
retrieved on-demand: the counter shows number of packets that have been
dropped by the underlying device and haven't been passed to the devlink
subsystem.
The core prestera-devlink functionality is implemented in the prestera_devlink.c.
The patch series also extends the existing devlink kernel API:
- devlink: add trap_drop_counter_get callback for driver to register - make it possible
to keep track of how many packets have been dropped (hard) by the switch device, before
the packets even made it to the devlink subsystem (e.g. dropped due to RXDMA buffer
overflow).
The core features that extend current functionality of prestera Switchdev driver:
- add logic for driver traps and drops registration (also traps with DROP action).
- add documentation for prestera driver traps and drops group.
PATCH v2:
1) Rebase whole series on top of latest mater;
2) Remove storm control-related patches, as they're out of devlink
scope;
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Oleksandr Mazur [Mon, 14 Jun 2021 13:01:18 +0000 (16:01 +0300)]
documentation: networking: devlink: add prestera switched driver Documentation
Add documentation for the devlink feature prestera switchdev driver supports:
add description for the support of the driver-specific devlink traps
(include both traps with action TRAP and action DROP);
Signed-off-by: Oleksandr Mazur <oleksandr.mazur@plvision.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Oleksandr Mazur [Mon, 14 Jun 2021 13:01:17 +0000 (16:01 +0300)]
net: marvell: prestera: devlink: add traps with DROP action
Add traps that have init_action being set to DROP.
Add 'trap_drop_counter_get' (devlink API) callback implementation,
that is used to get number of packets that have been dropped by the HW
(traps with action 'DROP').
Add new FW command CPU_CODE_COUNTERS_GET.
Signed-off-by: Oleksandr Mazur <oleksandr.mazur@plvision.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Oleksandr Mazur [Mon, 14 Jun 2021 13:01:16 +0000 (16:01 +0300)]
net: marvell: prestera: devlink: add traps/groups implementation
Add devlink traps registration (with corresponding groups) for
all the traffic types that driver traps to the CPU;
prestera_rxtx: report each packet trapped to the CPU (RX) to the
prestera_devlink;
Signed-off-by: Oleksandr Mazur <oleksandr.mazur@plvision.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Oleksandr Mazur [Mon, 14 Jun 2021 13:01:15 +0000 (16:01 +0300)]
testing: selftests: drivers: net: netdevsim: devlink: add test case for hard drop statistics
Add hard drop counter check testcase, to make sure netdevsim driver
properly handles the devlink hard drop counters get/set callbacks.
Signed-off-by: Oleksandr Mazur <oleksandr.mazur@plvision.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Oleksandr Mazur [Mon, 14 Jun 2021 13:01:14 +0000 (16:01 +0300)]
drivers: net: netdevsim: add devlink trap_drop_counter_get implementation
Whenever query statistics is issued for trap with DROP action,
devlink subsystem would also fill-in statistics 'dropped' field.
In case if device driver did't register callback for hard drop
statistics querying, 'dropped' field will be omitted and not filled.
Add trap_drop_counter_get callback implementation to the netdevsim.
Add new test cases for netdevsim, to test both the callback
functionality, as well as drop statistics alteration check.
Signed-off-by: Oleksandr Mazur <oleksandr.mazur@plvision.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Oleksandr Mazur [Mon, 14 Jun 2021 13:01:13 +0000 (16:01 +0300)]
testing: selftests: net: forwarding: add devlink-required functionality to test (hard) dropped stats field
Add devlink_trap_drop_packets_get function, as well as test that are
used to verify devlink (hard) dropped stats functionality works.
Signed-off-by: Oleksandr Mazur <oleksandr.mazur@plvision.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Oleksandr Mazur [Mon, 14 Jun 2021 13:01:12 +0000 (16:01 +0300)]
net: core: devlink: add dropped stats traps field
Whenever query statistics is issued for trap, devlink subsystem
would also fill-in statistics 'dropped' field. This field indicates
the number of packets HW dropped and failed to report to the device driver,
and thus - to the devlink subsystem itself.
In case if device driver didn't register callback for hard drop
statistics querying, 'dropped' field will be omitted and not filled.
Signed-off-by: Oleksandr Mazur <oleksandr.mazur@plvision.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Loic Poulain [Mon, 14 Jun 2021 08:16:40 +0000 (10:16 +0200)]
net: wwan: iosm: Remove DEBUG flag
Author forgot to remove that flag.
Fixes:
f7af616c632e ("net: iosm: infrastructure")
Reported-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Lijun Pan [Mon, 14 Jun 2021 05:20:45 +0000 (00:20 -0500)]
ibmvnic: fix send_request_map incompatible argument
The 3rd argument is u32 by function definition while it is __be32
by function declaration.
Signed-off-by: Lijun Pan <lijunp213@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>