[ Upstream commit 5a159128faff151b7fe5f4eb0f310b1e0a2d56bf ]
We try using cancel_delayed_work_sync() to prevent the work from
enabling NAPI. This is insufficient since we don't disable the source
of the refill work scheduling. This means an NAPI poll callback after
cancel_delayed_work_sync() can schedule the refill work then can
re-enable the NAPI that leads to use-after-free [1].
Since the work can enable NAPI, we can't simply disable NAPI before
calling cancel_delayed_work_sync(). So fix this by introducing a
dedicated boolean to control whether or not the work could be
scheduled from NAPI.
[1]
==================================================================
BUG: KASAN: use-after-free in refill_work+0x43/0xd4
Read of size 2 at addr ffff88810562c92e by task kworker/2:1/42
CPU: 2 PID: 42 Comm: kworker/2:1 Not tainted 5.19.0-rc1+ #480
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
Workqueue: events refill_work
Call Trace:
<TASK>
dump_stack_lvl+0x34/0x44
print_report.cold+0xbb/0x6ac
? _printk+0xad/0xde
? refill_work+0x43/0xd4
kasan_report+0xa8/0x130
? refill_work+0x43/0xd4
refill_work+0x43/0xd4
process_one_work+0x43d/0x780
worker_thread+0x2a0/0x6f0
? process_one_work+0x780/0x780
kthread+0x167/0x1a0
? kthread_exit+0x50/0x50
ret_from_fork+0x22/0x30
</TASK>
...
Fixes: b2baed69e6 ("virtio_net: set/cancel work on ndo_open/ndo_stop")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 50c0ada627f56c92f5953a8bf9158b045ad026a1 upstream.
We currently call virtio_device_ready() after netdev
registration. Since ndo_open() can be called immediately
after register_netdev, this means there exists a race between
ndo_open() and virtio_device_ready(): the driver may start to use the
device before DRIVER_OK which violates the spec.
Fix this by switching to use register_netdevice() and protect the
virtio_device_ready() with rtnl_lock() to make sure ndo_open() can
only be called after virtio_device_ready().
Fixes: 4baf1e33d0 ("virtio_net: enable VQs early")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20220617072949.30734-1-jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 8af52fe9fd3bf5e7478da99193c0632276e1dfce ]
The following sequence currently causes a driver bug warning
when using virtio_net:
# ip link set eth0 up
# echo mem > /sys/power/state (or e.g. # rtcwake -s 10 -m mem)
<resume>
# ip link set eth0 down
Missing register, driver bug
WARNING: CPU: 0 PID: 375 at net/core/xdp.c:138 xdp_rxq_info_unreg+0x58/0x60
Call trace:
xdp_rxq_info_unreg+0x58/0x60
virtnet_close+0x58/0xac
__dev_close_many+0xac/0x140
__dev_change_flags+0xd8/0x210
dev_change_flags+0x24/0x64
do_setlink+0x230/0xdd0
...
This happens because virtnet_freeze() frees the receive_queue
completely (including struct xdp_rxq_info) but does not call
xdp_rxq_info_unreg(). Similarly, virtnet_restore() sets up the
receive_queue again but does not call xdp_rxq_info_reg().
Actually, parts of virtnet_freeze_down() and virtnet_restore_up()
are almost identical to virtnet_close() and virtnet_open(): only
the calls to xdp_rxq_info_(un)reg() are missing. This means that
we can fix this easily and avoid such problems in the future by
just calling virtnet_close()/open() from the freeze/restore handlers.
Aside from adding the missing xdp_rxq_info calls the only difference
is that the refill work is only cancelled if netif_running(). However,
this should not make any functional difference since the refill work
should only be active if the network interface is actually up.
Fixes: 754b8a21a9 ("virtio_net: setup xdp_rxq_info")
Signed-off-by: Stephan Gerhold <stephan.gerhold@kernkonzept.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20220621114845.3650258-1-stephan.gerhold@kernkonzept.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit acb16b395c3f3d7502443e0c799c2b42df645642 upstream.
We received a report[1] of kernel crashes when Cilium is used in XDP
mode with virtio_net after updating to newer kernels. After
investigating the reason it turned out that when using mergeable bufs
with an XDP program which adjusts xdp.data or xdp.data_meta page_to_buf()
calculates the build_skb address wrong because the offset can become less
than the headroom so it gets the address of the previous page (-X bytes
depending on how lower offset is):
page_to_skb: page addr ffff9eb2923e2000 buf ffff9eb2923e1ffc offset 252 headroom 256
This is a pr_err() I added in the beginning of page_to_skb which clearly
shows offset that is less than headroom by adding 4 bytes of metadata
via an xdp prog. The calculations done are:
receive_mergeable():
headroom = VIRTIO_XDP_HEADROOM; // VIRTIO_XDP_HEADROOM == 256 bytes
offset = xdp.data - page_address(xdp_page) -
vi->hdr_len - metasize;
page_to_skb():
p = page_address(page) + offset;
...
buf = p - headroom;
Now buf goes -4 bytes from the page's starting address as can be seen
above which is set as skb->head and skb->data by build_skb later. Depending
on what's done with the skb (when it's freed most often) we get all kinds
of corruptions and BUG_ON() triggers in mm[2]. We have to recalculate
the new headroom after the xdp program has run, similar to how offset
and len are recalculated. Headroom is directly related to
data_hard_start, data and data_meta, so we use them to get the new size.
The result is correct (similar pr_err() in page_to_skb, one case of
xdp_page and one case of virtnet buf):
a) Case with 4 bytes of metadata
[ 115.949641] page_to_skb: page addr ffff8b4dcfad2000 offset 252 headroom 252
[ 121.084105] page_to_skb: page addr ffff8b4dcf018000 offset 20732 headroom 252
b) Case of pushing data +32 bytes
[ 153.181401] page_to_skb: page addr ffff8b4dd0c4d000 offset 288 headroom 288
[ 158.480421] page_to_skb: page addr ffff8b4dd00b0000 offset 24864 headroom 288
c) Case of pushing data -33 bytes
[ 835.906830] page_to_skb: page addr ffff8b4dd3270000 offset 223 headroom 223
[ 840.839910] page_to_skb: page addr ffff8b4dcdd68000 offset 12511 headroom 223
Offset and headroom are equal because offset points to the start of
reserved bytes for the virtio_net header which are at buf start +
headroom, while data points at buf start + vnet hdr size + headroom so
when data or data_meta are adjusted by the xdp prog both the headroom size
and the offset change equally. We can use data_hard_start to compute the
new headroom after the xdp prog (linearized / page start case, the
virtnet buf case is similar just with bigger base offset):
xdp.data_hard_start = page_address + vnet_hdr
xdp.data = page_address + vnet_hdr + headroom
new headroom after xdp prog = xdp.data - xdp.data_hard_start - metasize
An example reproducer xdp prog[3] is below.
[1] https://github.com/cilium/cilium/issues/19453
[2] Two of the many traces:
[ 40.437400] BUG: Bad page state in process swapper/0 pfn:14940
[ 40.916726] BUG: Bad page state in process systemd-resolve pfn:053b7
[ 41.300891] kernel BUG at include/linux/mm.h:720!
[ 41.301801] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
[ 41.302784] CPU: 1 PID: 1181 Comm: kubelet Kdump: loaded Tainted: G B W 5.18.0-rc1+ #37
[ 41.304458] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1.fc35 04/01/2014
[ 41.306018] RIP: 0010:page_frag_free+0x79/0xe0
[ 41.306836] Code: 00 00 75 ea 48 8b 07 a9 00 00 01 00 74 e0 48 8b 47 48 48 8d 50 ff a8 01 48 0f 45 fa eb d0 48 c7 c6 18 b8 30 a6 e8 d7 f8 fc ff <0f> 0b 48 8d 78 ff eb bc 48 8b 07 a9 00 00 01 00 74 3a 66 90 0f b6
[ 41.310235] RSP: 0018:ffffac05c2a6bc78 EFLAGS: 00010292
[ 41.311201] RAX: 000000000000003e RBX: 0000000000000000 RCX: 0000000000000000
[ 41.312502] RDX: 0000000000000001 RSI: ffffffffa6423004 RDI: 00000000ffffffff
[ 41.313794] RBP: ffff993c98823600 R08: 0000000000000000 R09: 00000000ffffdfff
[ 41.315089] R10: ffffac05c2a6ba68 R11: ffffffffa698ca28 R12: ffff993c98823600
[ 41.316398] R13: ffff993c86311ebc R14: 0000000000000000 R15: 000000000000005c
[ 41.317700] FS: 00007fe13fc56740(0000) GS:ffff993cdd900000(0000) knlGS:0000000000000000
[ 41.319150] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 41.320152] CR2: 000000c00008a000 CR3: 0000000014908000 CR4: 0000000000350ee0
[ 41.321387] Call Trace:
[ 41.321819] <TASK>
[ 41.322193] skb_release_data+0x13f/0x1c0
[ 41.322902] __kfree_skb+0x20/0x30
[ 41.343870] tcp_recvmsg_locked+0x671/0x880
[ 41.363764] tcp_recvmsg+0x5e/0x1c0
[ 41.384102] inet_recvmsg+0x42/0x100
[ 41.406783] ? sock_recvmsg+0x1d/0x70
[ 41.428201] sock_read_iter+0x84/0xd0
[ 41.445592] ? 0xffffffffa3000000
[ 41.462442] new_sync_read+0x148/0x160
[ 41.479314] ? 0xffffffffa3000000
[ 41.496937] vfs_read+0x138/0x190
[ 41.517198] ksys_read+0x87/0xc0
[ 41.535336] do_syscall_64+0x3b/0x90
[ 41.551637] entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 41.568050] RIP: 0033:0x48765b
[ 41.583955] Code: e8 4a 35 fe ff eb 88 cc cc cc cc cc cc cc cc e8 fb 7a fe ff 48 8b 7c 24 10 48 8b 74 24 18 48 8b 54 24 20 48 8b 44 24 08 0f 05 <48> 3d 01 f0 ff ff 76 20 48 c7 44 24 28 ff ff ff ff 48 c7 44 24 30
[ 41.632818] RSP: 002b:000000c000a2f5b8 EFLAGS: 00000212 ORIG_RAX: 0000000000000000
[ 41.664588] RAX: ffffffffffffffda RBX: 000000c000062000 RCX: 000000000048765b
[ 41.681205] RDX: 0000000000005e54 RSI: 000000c000e66000 RDI: 0000000000000016
[ 41.697164] RBP: 000000c000a2f608 R08: 0000000000000001 R09: 00000000000001b4
[ 41.713034] R10: 00000000000000b6 R11: 0000000000000212 R12: 00000000000000e9
[ 41.728755] R13: 0000000000000001 R14: 000000c000a92000 R15: ffffffffffffffff
[ 41.744254] </TASK>
[ 41.758585] Modules linked in: br_netfilter bridge veth netconsole virtio_net
and
[ 33.524802] BUG: Bad page state in process systemd-network pfn:11e60
[ 33.528617] page ffffe05dc0147b00 ffffe05dc04e7a00 ffff8ae9851ec000 (1) len 82 offset 252 metasize 4 hroom 0 hdr_len 12 data ffff8ae9851ec10c data_meta ffff8ae9851ec108 data_end ffff8ae9851ec14e
[ 33.529764] page:000000003792b5ba refcount:0 mapcount:-512 mapping:0000000000000000 index:0x0 pfn:0x11e60
[ 33.532463] flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff)
[ 33.532468] raw: 000fffffc0000000 0000000000000000 dead000000000122 0000000000000000
[ 33.532470] raw: 0000000000000000 0000000000000000 00000000fffffdff 0000000000000000
[ 33.532471] page dumped because: nonzero mapcount
[ 33.532472] Modules linked in: br_netfilter bridge veth netconsole virtio_net
[ 33.532479] CPU: 0 PID: 791 Comm: systemd-network Kdump: loaded Not tainted 5.18.0-rc1+ #37
[ 33.532482] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1.fc35 04/01/2014
[ 33.532484] Call Trace:
[ 33.532496] <TASK>
[ 33.532500] dump_stack_lvl+0x45/0x5a
[ 33.532506] bad_page.cold+0x63/0x94
[ 33.532510] free_pcp_prepare+0x290/0x420
[ 33.532515] free_unref_page+0x1b/0x100
[ 33.532518] skb_release_data+0x13f/0x1c0
[ 33.532524] kfree_skb_reason+0x3e/0xc0
[ 33.532527] ip6_mc_input+0x23c/0x2b0
[ 33.532531] ip6_sublist_rcv_finish+0x83/0x90
[ 33.532534] ip6_sublist_rcv+0x22b/0x2b0
[3] XDP program to reproduce(xdp_pass.c):
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
SEC("xdp_pass")
int xdp_pkt_pass(struct xdp_md *ctx)
{
bpf_xdp_adjust_head(ctx, -(int)32);
return XDP_PASS;
}
char _license[] SEC("license") = "GPL";
compile: clang -O2 -g -Wall -target bpf -c xdp_pass.c -o xdp_pass.o
load on virtio_net: ip link set enp1s0 xdpdrv obj xdp_pass.o sec xdp_pass
CC: stable@vger.kernel.org
CC: Jason Wang <jasowang@redhat.com>
CC: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
CC: Daniel Borkmann <daniel@iogearbox.net>
CC: "Michael S. Tsirkin" <mst@redhat.com>
CC: virtualization@lists.linux-foundation.org
Fixes: 8fb7da9e99 ("virtio_net: get build_skb() buf by data ptr")
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20220425103703.3067292-1-razor@blackwall.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 126285651b ("Merge ra.kernel.org:/pub/scm/linux/kernel/git/netdev/net")
accidentally reverted the effect of
commit 1a8024239d ("virtio-net: fix for skb_over_panic inside big mode")
on drivers/net/virtio_net.c
As a result, users of crosvm (which is using large packet mode)
are experiencing crashes with 5.14-rc1 and above that do not
occur with 5.13.
Crash trace:
[ 61.346677] skbuff: skb_over_panic: text:ffffffff881ae2c7 len:3762 put:3762 head:ffff8a5ec8c22000 data:ffff8a5ec8c22010 tail:0xec2 end:0xec0 dev:<NULL>
[ 61.369192] kernel BUG at net/core/skbuff.c:111!
[ 61.372840] invalid opcode: 0000 [#1] SMP PTI
[ 61.374892] CPU: 5 PID: 0 Comm: swapper/5 Not tainted 5.14.0-rc1 linux-v5.14-rc1-for-mesa-ci.tar.bz2 #1
[ 61.376450] Hardware name: ChromiumOS crosvm, BIOS 0
..
[ 61.393635] Call Trace:
[ 61.394127] <IRQ>
[ 61.394488] skb_put.cold+0x10/0x10
[ 61.395095] page_to_skb+0xf7/0x410
[ 61.395689] receive_buf+0x81/0x1660
[ 61.396228] ? netif_receive_skb_list_internal+0x1ad/0x2b0
[ 61.397180] ? napi_gro_flush+0x97/0xe0
[ 61.397896] ? detach_buf_split+0x67/0x120
[ 61.398573] virtnet_poll+0x2cf/0x420
[ 61.399197] __napi_poll+0x25/0x150
[ 61.399764] net_rx_action+0x22f/0x280
[ 61.400394] __do_softirq+0xba/0x257
[ 61.401012] irq_exit_rcu+0x8e/0xb0
[ 61.401618] common_interrupt+0x7b/0xa0
[ 61.402270] </IRQ>
See
https://lore.kernel.org/r/5edaa2b7c2fe4abd0347b8454b2ac032b6694e2c.camel%40collabora.com
for the report.
Apply the original 1a8024239d ("virtio-net: fix for skb_over_panic inside big mode")
again, the original logic still holds:
In virtio-net's large packet mode, there is a hole in the space behind
buf.
hdr_padded_len - hdr_len
We must take this into account when calculating tailroom.
Cc: Greg KH <gregkh@linuxfoundation.org>
Fixes: fb32856b16 ("virtio-net: page_to_skb() use build_skb when there's sufficient tailroom")
Fixes: 126285651b ("Merge ra.kernel.org:/pub/scm/linux/kernel/git/netdev/net")
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Reported-by: Corentin Noël <corentin.noel@collabora.com>
Tested-by: Corentin Noël <corentin.noel@collabora.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We try to use build_skb() if we had sufficient tailroom. But we forget
to release the unused pages chained via private in big mode which will
leak pages. Fixing this by release the pages after building the skb in
big mode.
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Fixes: fb32856b16 ("virtio-net: page_to_skb() use build_skb when there's sufficient tailroom")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
smp_processor_id()/raw* will be called once each when not
more queues in virtnet_xdp_get_sq() which is called in
non-preemptible context, so it's safe to call the function
smp_processor_id() once.
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to support more coalesce parameters through netlink,
add two new parameter kernel_coal and extack for .set_coalesce
and .get_coalesce, then some extra info can return to user with
the netlink API.
Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit a02e8964ea ("virtio-net: ethtool configurable LRO")
maps LRO to virtio guest offloading features and allows the
administrator to enable and disable those features via ethtool.
This leads to several issues:
- For a device that doesn't support control guest offloads, the "LRO"
can't be disabled triggering WARN in dev_disable_lro() when turning
off LRO or when enabling forwarding bridging etc.
- For a device that supports control guest offloads, the guest
offloads are disabled in cases of bridging, forwarding etc slowing
down the traffic.
Fix this by using NETIF_F_GRO_HW instead. Though the spec does not
guarantee packets to be re-segmented as the original ones,
we can add that to the spec, possibly with a flag for devices to
differentiate between GRO and LRO.
Further, we never advertised LRO historically before a02e8964ea
("virtio-net: ethtool configurable LRO") and so bridged/forwarded
configs effectively always relied on virtio receive offloads behaving
like GRO - thus even if this breaks any configs it is at least not
a regression.
Fixes: a02e8964ea ("virtio-net: ethtool configurable LRO")
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reported-by: Ivan <ivan@prestigetransportation.com>
Tested-by: Ivan <ivan@prestigetransportation.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The functions get_online_cpus() and put_online_cpus() have been
deprecated during the CPU hotplug rework. They map directly to
cpus_read_lock() and cpus_read_unlock().
Replace deprecated CPU-hotplug functions with the official version.
The behavior remains unchanged.
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We ended up merging two versions of the same patch set:
commit 8fb7da9e99 ("virtio_net: get build_skb() buf by data ptr")
commit 5c37711d9f ("virtio-net: fix for unable to handle page fault for address")
into net, and
commit 7bf64460e3 ("virtio-net: get build_skb() buf by data ptr")
commit 6c66c147b9 ("virtio-net: fix for unable to handle page fault for address")
into net-next. Redo the merge from commit 126285651b ("Merge
ra.kernel.org:/pub/scm/linux/kernel/git/netdev/net"), so that
the most recent code remains.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking fixes from Jakub Kicinski.
"Including fixes from bpf and netfilter.
Current release - regressions:
- sock: fix parameter order in sock_setsockopt()
Current release - new code bugs:
- netfilter: nft_last:
- fix incorrect arithmetic when restoring last used
- honor NFTA_LAST_SET on restoration
Previous releases - regressions:
- udp: properly flush normal packet at GRO time
- sfc: ensure correct number of XDP queues; don't allow enabling the
feature if there isn't sufficient resources to Tx from any CPU
- dsa: sja1105: fix address learning getting disabled on the CPU port
- mptcp: addresses a rmem accounting issue that could keep packets in
subflow receive buffers longer than necessary, delaying MPTCP-level
ACKs
- ip_tunnel: fix mtu calculation for ETHER tunnel devices
- do not reuse skbs allocated from skbuff_fclone_cache in the napi
skb cache, we'd try to return them to the wrong slab cache
- tcp: consistently disable header prediction for mptcp
Previous releases - always broken:
- bpf: fix subprog poke descriptor tracking use-after-free
- ipv6:
- allocate enough headroom in ip6_finish_output2() in case
iptables TEE is used
- tcp: drop silly ICMPv6 packet too big messages to avoid
expensive and pointless lookups (which may serve as a DDOS
vector)
- make sure fwmark is copied in SYNACK packets
- fix 'disable_policy' for forwarded packets (align with IPv4)
- netfilter: conntrack:
- do not renew entry stuck in tcp SYN_SENT state
- do not mark RST in the reply direction coming after SYN packet
for an out-of-sync entry
- mptcp: cleanly handle error conditions with MP_JOIN and syncookies
- mptcp: fix double free when rejecting a join due to port mismatch
- validate lwtstate->data before returning from skb_tunnel_info()
- tcp: call sk_wmem_schedule before sk_mem_charge in zerocopy path
- mt76: mt7921: continue to probe driver when fw already downloaded
- bonding: fix multiple issues with offloading IPsec to (thru?) bond
- stmmac: ptp: fix issues around Qbv support and setting time back
- bcmgenet: always clear wake-up based on energy detection
Misc:
- sctp: move 198 addresses from unusable to private scope
- ptp: support virtual clocks and timestamping
- openvswitch: optimize operation for key comparison"
* tag 'net-5.14-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (158 commits)
net: dsa: properly check for the bridge_leave methods in dsa_switch_bridge_leave()
sfc: add logs explaining XDP_TX/REDIRECT is not available
sfc: ensure correct number of XDP queues
sfc: fix lack of XDP TX queues - error XDP TX failed (-22)
net: fddi: fix UAF in fza_probe
net: dsa: sja1105: fix address learning getting disabled on the CPU port
net: ocelot: fix switchdev objects synced for wrong netdev with LAG offload
net: Use nlmsg_unicast() instead of netlink_unicast()
octeontx2-pf: Fix uninitialized boolean variable pps
ipv6: allocate enough headroom in ip6_finish_output2()
net: hdlc: rename 'mod_init' & 'mod_exit' functions to be module-specific
net: bridge: multicast: fix MRD advertisement router port marking race
net: bridge: multicast: fix PIM hello router port marking race
net: phy: marvell10g: fix differentiation of 88X3310 from 88X3340
dsa: fix for_each_child.cocci warnings
virtio_net: check virtqueue_add_sgs() return value
mptcp: properly account bulk freed memory
selftests: mptcp: fix case multiple subflows limited by server
mptcp: avoid processing packet if a subflow reset
mptcp: fix syncookie process if mptcp can not_accept new subflow
...
As virtqueue_add_sgs() can fail, we should check the return value.
Addresses-Coverity-ID: 1464439 ("Unchecked return value")
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are currently two cases where we poll TX vq not in response to a
callback: start xmit and rx napi. We currently do this with callbacks
enabled which can cause extra interrupts from the card. Used not to be
a big issue as we run with interrupts disabled but that is no longer the
case, and in some cases the rate of spurious interrupts is so high
linux detects this and actually kills the interrupt.
Fix up by disabling the callbacks before polling the tx vq.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
We currently check num_free outside tx q lock
which is unsafe: new packets can arrive meanwhile
and there won't be space in the queue.
Thus a spurious queue wakeup causing overhead
and even packet drops.
Move the check under the lock to fix that.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
It's unsafe to operate a vq from multiple threads.
Unfortunately this is exactly what we do when invoking
clean tx poll from rx napi.
Same happens with napi-tx even without the
opportunistic cleaning from the receive interrupt: that races
with processing the vq in start_xmit.
As a fix move everything that deals with the vq to under tx lock.
Fixes: b92f1e6751 ("virtio-net: transmit napi")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
We should not directly BUG() when there is hdr error, it is
better to output a print when such error happens. Currently,
the caller of xmit_skb() already did it.
Signed-off-by: Xianting Tian <xianting.tian@linux.alibaba.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the case of merge, the page passed into page_to_skb() may be a head
page, not the page where the current data is located. So when trying to
get the buf where the data is located, we should get buf based on
headroom instead of offset.
This patch solves this problem. But if you don't use this patch, the
original code can also run, because if the page is not the page of the
current data, the calculated tailroom will be less than 0, and will not
enter the logic of build_skb() . The significance of this patch is to
modify this logical problem, allowing more situations to use
build_skb().
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the case of merge, the page passed into page_to_skb() may be a head
page, not the page where the current data is located. So when trying to
get the buf where the data is located, you should directly use the
pointer(p) to get the address corresponding to the page.
At the same time, the offset of the data in the page should also be
obtained using offset_in_page().
This patch solves this problem. But if you don’t use this patch, the
original code can also run, because if the page is not the page of the
current data, the calculated tailroom will be less than 0, and will not
enter the logic of build_skb() . The significance of this patch is to
modify this logical problem, allowing more situations to use
build_skb().
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull virtio updates from Michael Tsirkin:
"A bunch of new drivers including vdpa support for block and
virtio-vdpa.
Beginning of vq kick (aka doorbell) mapping support.
Misc fixes"
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (40 commits)
virtio_pci_modern: correct sparse tags for notify
virtio_pci_modern: __force cast the notify mapping
vDPA/ifcvf: get_config_size should return dev specific config size
vDPA/ifcvf: enable Intel C5000X-PL virtio-block for vDPA
vDPA/ifcvf: deduce VIRTIO device ID when probe
vdpa_sim_blk: add support for vdpa management tool
vdpa_sim_blk: handle VIRTIO_BLK_T_GET_ID
vdpa_sim_blk: implement ramdisk behaviour
vdpa: add vdpa simulator for block device
vhost/vdpa: Remove the restriction that only supports virtio-net devices
vhost/vdpa: use get_config_size callback in vhost_vdpa_config_validate()
vdpa: add get_config_size callback in vdpa_config_ops
vdpa_sim: cleanup kiovs in vdpasim_free()
vringh: add vringh_kiov_length() helper
vringh: implement vringh_kiov_advance()
vringh: explain more about cleaning riov and wiov
vringh: reset kiov 'consumed' field in __vringh_iov()
vringh: add 'iotlb_lock' to synchronize iotlb accesses
vdpa_sim: use iova module to allocate IOVA addresses
vDPA/ifcvf: deduce VIRTIO device ID from pdev ids
...
build_skb() is supposed to be followed by
skb_reserve(skb, NET_IP_ALIGN), so that IP headers are word-aligned.
(Best practice is to reserve NET_IP_ALIGN+NET_SKB_PAD, but the NET_SKB_PAD
part is only a performance optimization if tunnel encaps are added.)
Unfortunately virtio_net has not provisioned this reserve.
We can only use build_skb() for arches where NET_IP_ALIGN == 0
We might refine this later, with enough testing.
Fixes: fb32856b16 ("virtio-net: page_to_skb() use build_skb when there's sufficient tailroom")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: David S. Miller <davem@davemloft.net>
In page_to_skb(), if we have enough tailroom to save skb_shared_info, we
can use build_skb to create skb directly. No need to alloc for
additional space. And it can save a 'frags slot', which is very friendly
to GRO.
Here, if the payload of the received package is too small (less than
GOOD_COPY_LEN), we still choose to copy it directly to the space got by
napi_alloc_skb. So we can reuse these pages.
Testing Machine:
The four queues of the network card are bound to the cpu1.
Test command:
for ((i=0;i<5;++i)); do sockperf tp --ip 192.168.122.64 -m 1000 -t 150& done
The size of the udp package is 1000, so in the case of this patch, there
will always be enough tailroom to use build_skb. The sent udp packet
will be discarded because there is no port to receive it. The irqsoftd
of the machine is 100%, we observe the received quantity displayed by
sar -n DEV 1:
no build_skb: 956864.00 rxpck/s
build_skb: 1158465.00 rxpck/s
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
MAINTAINERS
- keep Chandrasekar
drivers/net/ethernet/mellanox/mlx5/core/en_main.c
- simple fix + trust the code re-added to param.c in -next is fine
include/linux/bpf.h
- trivial
include/linux/ethtool.h
- trivial, fix kdoc while at it
include/linux/skmsg.h
- move to relevant place in tcp.c, comment re-wrapped
net/core/skmsg.c
- add the sk = sk // sk = NULL around calls
net/tipc/crypto.c
- trivial
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Xuan Zhuo reported that commit 3226b158e6 ("net: avoid 32 x truesize
under-estimation for tiny skbs") brought a ~10% performance drop.
The reason for the performance drop was that GRO was forced
to chain sk_buff (using skb_shinfo(skb)->frag_list), which
uses more memory but also cause packet consumers to go over
a lot of overhead handling all the tiny skbs.
It turns out that virtio_net page_to_skb() has a wrong strategy :
It allocates skbs with GOOD_COPY_LEN (128) bytes in skb->head, then
copies 128 bytes from the page, before feeding the packet to GRO stack.
This was suboptimal before commit 3226b158e6 ("net: avoid 32 x truesize
under-estimation for tiny skbs") because GRO was using 2 frags per MSS,
meaning we were not packing MSS with 100% efficiency.
Fix is to pull only the ethernet header in page_to_skb()
Then, we change virtio_net_hdr_to_skb() to pull the missing
headers, instead of assuming they were already pulled by callers.
This fixes the performance regression, but could also allow virtio_net
to accept packets with more than 128bytes of headers.
Many thanks to Xuan Zhuo for his report, and his tests/help.
Fixes: 3226b158e6 ("net: avoid 32 x truesize under-estimation for tiny skbs")
Reported-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Link: https://www.spinics.net/lists/netdev/msg731397.html
Co-Developed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexei Starovoitov says:
====================
pull-request: bpf-next 2021-03-24
The following pull-request contains BPF updates for your *net-next* tree.
We've added 37 non-merge commits during the last 15 day(s) which contain
a total of 65 files changed, 3200 insertions(+), 738 deletions(-).
The main changes are:
1) Static linking of multiple BPF ELF files, from Andrii.
2) Move drop error path to devmap for XDP_REDIRECT, from Lorenzo.
3) Spelling fixes from various folks.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Move the xps maps (xps_cpus_map and xps_rxqs_map) to an array in
net_device. That will simplify a lot the code removing the need for lots
of if/else conditionals as the correct map will be available using its
offset in the array.
This should not modify the xps maps behaviour in any way.
Suggested-by: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
We want to change the current ndo_xdp_xmit drop semantics because it will
allow us to implement better queue overflow handling. This is working
towards the larger goal of a XDP TX queue-hook. Move XDP_REDIRECT error
path handling from each XDP ethernet driver to devmap code. According to
the new APIs, the driver running the ndo_xdp_xmit pointer, will break tx
loop whenever the hw reports a tx error and it will just return to devmap
caller the number of successfully transmitted frames. It will be devmap
responsibility to free dropped frames.
Move each XDP ndo_xdp_xmit capable driver to the new APIs:
- veth
- virtio-net
- mvneta
- mvpp2
- socionext
- amazon ena
- bnxt
- freescale (dpaa2, dpaa)
- xen-frontend
- qede
- ice
- igb
- ixgbe
- i40e
- mlx5
- ti (cpsw, cpsw-new)
- tun
- sfc
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Camelia Groza <camelia.groza@nxp.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Shay Agroskin <shayagr@amazon.com>
Link: https://lore.kernel.org/bpf/ed670de24f951cfd77590decf0229a0ad7fd12f6.1615201152.git.lorenzo@kernel.org
Update the code to replace instances of snprintf and a pointer update with
just calling ethtool_sprintf.
Also replace the char pointer with a u8 pointer to avoid having to recast
the pointer type.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The number of queues implemented by many virtio backends is limited,
especially some machines have a large number of CPUs. In this case, it
is often impossible to allocate a separate queue for
XDP_TX/XDP_REDIRECT, then xdp cannot be loaded to work, even xdp does
not use the XDP_TX/XDP_REDIRECT.
This patch allows XDP_TX/XDP_REDIRECT to run by reuse the existing SQ
with __netif_tx_lock() hold when there are not enough queues.
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexei Starovoitov says:
====================
pull-request: bpf-next 2021-03-09
The following pull-request contains BPF updates for your *net-next* tree.
We've added 90 non-merge commits during the last 17 day(s) which contain
a total of 114 files changed, 5158 insertions(+), 1288 deletions(-).
The main changes are:
1) Faster bpf_redirect_map(), from Björn.
2) skmsg cleanup, from Cong.
3) Support for floating point types in BTF, from Ilya.
4) Documentation for sys_bpf commands, from Joe.
5) Support for sk_lookup in bpf_prog_test_run, form Lorenz.
6) Enable task local storage for tracing programs, from Song.
7) bpf_for_each_map_elem() helper, from Yonghong.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull virtio updates from Michael Tsirkin:
- new vdpa features to allow creation and deletion of new devices
- virtio-blk support per-device queue depth
- fixes, cleanups all over the place
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (31 commits)
virtio-input: add multi-touch support
virtio_mmio: fix one typo
vdpa/mlx5: fix param validation in mlx5_vdpa_get_config()
virtio_net: Fix fall-through warnings for Clang
virtio_input: Prevent EV_MSC/MSC_TIMESTAMP loop storm for MT.
virtio-blk: support per-device queue depth
virtio_vdpa: don't warn when fail to disable vq
virtio-pci: introduce modern device module
virito-pci-modern: rename map_capability() to vp_modern_map_capability()
virtio-pci-modern: introduce helper to get notification offset
virtio-pci-modern: introduce helper for getting queue nums
virtio-pci-modern: introduce helper for setting/geting queue size
virtio-pci-modern: introduce helper to set/get queue_enable
virtio-pci-modern: introduce vp_modern_queue_address()
virtio-pci-modern: introduce vp_modern_set_queue_vector()
virtio-pci-modern: introduce vp_modern_generation()
virtio-pci-modern: introduce helpers for setting and getting features
virtio-pci-modern: introduce helpers for setting and getting status
virtio-pci-modern: introduce helper to set config vector
virtio-pci-modern: introduce vp_modern_remove()
...
Pull networking fixes from Jakub Kicinski:
"Networking fixes, including fixes from netfilter, wireless and bpf
trees.
Current release - regressions:
- mt76: fix NULL pointer dereference in mt76u_status_worker and
mt76s_process_tx_queue
- net: ipa: fix interconnect enable bug
Current release - always broken:
- netfilter: fixes possible oops in mtype_resize in ipset
- ath11k: fix number of coding issues found by static analysis tools
and spurious error messages
Previous releases - regressions:
- e1000e: re-enable s0ix power saving flows for systems with the
Intel i219-LM Ethernet controllers to fix power use regression
- virtio_net: fix recursive call to cpus_read_lock() to avoid a
deadlock
- ipv4: ignore ECN bits for fib lookups in fib_compute_spec_dst()
- sysfs: take the rtnl lock around XPS configuration
- xsk: fix memory leak for failed bind and rollback reservation at
NETDEV_TX_BUSY
- r8169: work around power-saving bug on some chip versions
Previous releases - always broken:
- dcb: validate netlink message in DCB handler
- tun: fix return value when the number of iovs exceeds MAX_SKB_FRAGS
to prevent unnecessary retries
- vhost_net: fix ubuf refcount when sendmsg fails
- bpf: save correct stopping point in file seq iteration
- ncsi: use real net-device for response handler
- neighbor: fix div by zero caused by a data race (TOCTOU)
- bareudp: fix use of incorrect min_headroom size and a false
positive lockdep splat from the TX lock
- mvpp2:
- clear force link UP during port init procedure in case
bootloader had set it
- add TCAM entry to drop flow control pause frames
- fix PPPoE with ipv6 packet parsing
- fix GoP Networking Complex Control config of port 3
- fix pkt coalescing IRQ-threshold configuration
- xsk: fix race in SKB mode transmit with shared cq
- ionic: account for vlan tag len in rx buffer len
- stmmac: ignore the second clock input, current clock framework does
not handle exclusive clock use well, other drivers may reconfigure
the second clock
Misc:
- ppp: change PPPIOCUNBRIDGECHAN ioctl request number to follow
existing scheme"
* tag 'net-5.11-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (99 commits)
net: dsa: lantiq_gswip: Fix GSWIP_MII_CFG(p) register access
net: dsa: lantiq_gswip: Enable GSWIP_MII_CFG_EN also for internal PHYs
net: lapb: Decrease the refcount of "struct lapb_cb" in lapb_device_event
r8169: work around power-saving bug on some chip versions
net: usb: qmi_wwan: add Quectel EM160R-GL
selftests: mlxsw: Set headroom size of correct port
net: macb: Correct usage of MACB_CAPS_CLK_HW_CHG flag
ibmvnic: fix: NULL pointer dereference.
docs: networking: packet_mmap: fix old config reference
docs: networking: packet_mmap: fix formatting for C macros
vhost_net: fix ubuf refcount incorrectly when sendmsg fails
bareudp: Fix use of incorrect min_headroom size
bareudp: set NETIF_F_LLTX flag
net: hdlc_ppp: Fix issues when mod_timer is called while timer is running
atlantic: remove architecture depends
erspan: fix version 1 check in gre_parse_header()
net: hns: fix return value check in __lb_other_process()
net: sched: prevent invalid Scell_log shift count
net: neighbor: fix a crash caused by mod zero
ipv4: Ignore ECN bits for fib lookups in fib_compute_spec_dst()
...
Pull virtio updates from Michael Tsirkin:
- vdpa sim refactoring
- virtio mem: Big Block Mode support
- misc cleanus, fixes
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (61 commits)
vdpa: Use simpler version of ida allocation
vdpa: Add missing comment for virtqueue count
uapi: virtio_ids: add missing device type IDs from OASIS spec
uapi: virtio_ids.h: consistent indentions
vhost scsi: fix error return code in vhost_scsi_set_endpoint()
virtio_ring: Fix two use after free bugs
virtio_net: Fix error code in probe()
virtio_ring: Cut and paste bugs in vring_create_virtqueue_packed()
tools/virtio: add barrier for aarch64
tools/virtio: add krealloc_array
tools/virtio: include asm/bug.h
vdpa/mlx5: Use write memory barrier after updating CQ index
vdpa: split vdpasim to core and net modules
vdpa_sim: split vdpasim_virtqueue's iov field in out_iov and in_iov
vdpa_sim: make vdpasim->buffer size configurable
vdpa_sim: use kvmalloc to allocate vdpasim->buffer
vdpa_sim: set vringh notify callback
vdpa_sim: add set_config callback in vdpasim_dev_attr
vdpa_sim: add get_config callback in vdpasim_dev_attr
vdpa_sim: make 'config' generic and usable for any device type
...
virtnet_set_channels can recursively call cpus_read_lock if CONFIG_XPS
and CONFIG_HOTPLUG are enabled.
The path is:
virtnet_set_channels - calls get_online_cpus(), which is a trivial
wrapper around cpus_read_lock()
netif_set_real_num_tx_queues
netif_reset_xps_queues_gt
netif_reset_xps_queues - calls cpus_read_lock()
This call chain and potential deadlock happens when the number of TX
queues is reduced.
This commit the removes netif_set_real_num_[tr]x_queues calls from
inside the get/put_online_cpus section, as they don't require that it
be held.
Fixes: 47be24796c ("virtio-net: fix the set affinity bug when CPU IDs are not consecutive")
Signed-off-by: Jeff Dike <jdike@akamai.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/r/20201223025421.671-1-jdike@akamai.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
