| Age | Commit message (Collapse) | Author |
|---|
|
Export the network selftest packet creation infrastructure to allow
network drivers to reuse the existing selftest framework instead of
duplicating packet creation code.
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20251031111811.775434-1-Raju.Rangoju@amd.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
One GRO-cell device's NAPI callback can nest into the GRO-cell of
another device if the underlying device is also using GRO-cell.
This is the case for IPsec over vxlan.
These two GRO-cells are separate devices. From lockdep's point of view
it is the same because each device is sharing the same lock class and so
it reports a possible deadlock assuming one device is nesting into
itself.
Hold the bh_lock only while accessing gro_cell::napi_skbs in
gro_cell_poll(). This reduces the locking scope and avoids acquiring the
same lock class multiple times.
Fixes: 25718fdcbdd2 ("net: gro_cells: Use nested-BH locking for gro_cell")
Reported-by: Gal Pressman <gal@nvidia.com>
Closes: https://lore.kernel.org/all/66664116-edb8-48dc-ad72-d5223696dd19@nvidia.com/
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20251104153435.ty88xDQt@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Fix a AA deadlock in refill_skbs() where memory allocation while holding
skb_pool->lock can trigger a recursive lock acquisition attempt.
The deadlock scenario occurs when the system is under severe memory
pressure:
1. refill_skbs() acquires skb_pool->lock (spinlock)
2. alloc_skb() is called while holding the lock
3. Memory allocator fails and calls slab_out_of_memory()
4. This triggers printk() for the OOM warning
5. The console output path calls netpoll_send_udp()
6. netpoll_send_udp() attempts to acquire the same skb_pool->lock
7. Deadlock: the lock is already held by the same CPU
Call stack:
refill_skbs()
spin_lock_irqsave(&skb_pool->lock) <- lock acquired
__alloc_skb()
kmem_cache_alloc_node_noprof()
slab_out_of_memory()
printk()
console_flush_all()
netpoll_send_udp()
skb_dequeue()
spin_lock_irqsave(&skb_pool->lock) <- deadlock attempt
This bug was exposed by commit 248f6571fd4c51 ("netpoll: Optimize skb
refilling on critical path") which removed refill_skbs() from the
critical path (where nested printk was being deferred), letting nested
printk being called from inside refill_skbs()
Refactor refill_skbs() to never allocate memory while holding
the spinlock.
Another possible solution to fix this problem is protecting the
refill_skbs() from nested printks, basically calling
printk_deferred_{enter,exit}() in refill_skbs(), then, any nested
pr_warn() would be deferred.
I prefer this approach, given I _think_ it might be a good idea to move
the alloc_skb() from GFP_ATOMIC to GFP_KERNEL in the future, so, having
the alloc_skb() outside of the lock will be necessary step.
There is a possible TOCTOU issue when checking for the pool length, and
queueing the new allocated skb, but, this is not an issue, given that
an extra SKB in the pool is harmless and it will be eventually used.
Signed-off-by: Breno Leitao <leitao@debian.org>
Fixes: 248f6571fd4c51 ("netpoll: Optimize skb refilling on critical path")
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20251103-fix_netpoll_aa-v4-1-4cfecdf6da7c@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Revert struct sockaddr from flexible array to fixed 14-byte "sa_data",
to solve over 36,000 -Wflex-array-member-not-at-end warnings, since
struct sockaddr is embedded within many network structs.
With socket/proto sockaddr-based internal APIs switched to use struct
sockaddr_unsized, there should be no more uses of struct sockaddr that
depend on reading beyond the end of struct sockaddr::sa_data that might
trigger bounds checking.
Comparing an x86_64 "allyesconfig" vmlinux build before and after this
patch showed no new "ud1" instructions from CONFIG_UBSAN_BOUNDS nor any
new "field-spanning" memcpy CONFIG_FORTIFY_SOURCE instrumentations.
Cc: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20251104002617.2752303-8-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Convert struct proto pre_connect(), connect(), bind(), and bind_add()
callback function prototypes from struct sockaddr to struct sockaddr_unsized.
This does not change per-implementation use of sockaddr for passing around
an arbitrarily sized sockaddr struct. Those will be addressed in future
patches.
Additionally removes the no longer referenced struct sockaddr from
include/net/inet_common.h.
No binary changes expected.
Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20251104002617.2752303-5-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Update all struct proto_ops connect() callback function prototypes from
"struct sockaddr *" to "struct sockaddr_unsized *" to avoid lying to the
compiler about object sizes. Calls into struct proto handlers gain casts
that will be removed in the struct proto conversion patch.
No binary changes expected.
Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20251104002617.2752303-3-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Update all struct proto_ops bind() callback function prototypes from
"struct sockaddr *" to "struct sockaddr_unsized *" to avoid lying to the
compiler about object sizes. Calls into struct proto handlers gain casts
that will be removed in the struct proto conversion patch.
No binary changes expected.
Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20251104002617.2752303-2-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Commit bd61848900bf ("net: devmem: Implement TX path") declared this
but never implemented it.
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20251103072046.1670574-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
deliver_skb() should not be inlined as is it not called
in the fast path.
Add unlikely() clauses giving hints to the compiler about this fact.
Before this patch:
size net/core/dev.o
text data bss dec hex filename
121794 13330 176 135300 21084 net/core/dev.o
__netif_receive_skb_core() size on x86_64 : 4080 bytes.
After:
size net/core/dev.o
text data bss dec hex filenamee
120330 13338 176 133844 20ad4 net/core/dev.o
__netif_receive_skb_core() size on x86_64 : 2781 bytes.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251103165256.1712169-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Gathering interface statistics can be a relatively expensive operation
on certain systems as it requires iterating over all the cpus.
RTEXT_FILTER_SKIP_STATS was first introduced [1] to skip AF_INET6
statistics from interface dumps and it was then extended [2] to
also exclude IFLA_VF_INFO.
The semantics of the flag does not seem to be limited to AF_INET
or VF statistics and having a way to query the interface status
(e.g: carrier, address) without retrieving its statistics seems
reasonable. So this patch extends the use RTEXT_FILTER_SKIP_STATS
to also affect IFLA_STATS.
[1] https://lore.kernel.org/all/20150911204848.GC9687@oracle.com/
[2] https://lore.kernel.org/all/20230611105108.122586-1-gal@nvidia.com/
Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Link: https://patch.msgid.link/20251103154006.1189707-1-amorenoz@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Add a new state NAPI_STATE_THREADED_BUSY_POLL to the NAPI state enum to
enable and disable threaded busy polling.
When threaded busy polling is enabled for a NAPI, enable
NAPI_STATE_THREADED also.
When the threaded NAPI is scheduled, set NAPI_STATE_IN_BUSY_POLL to
signal napi_complete_done not to rearm interrupts.
Whenever NAPI_STATE_THREADED_BUSY_POLL is unset, the
NAPI_STATE_IN_BUSY_POLL will be unset, napi_complete_done unsets the
NAPI_STATE_SCHED_THREADED bit also, which in turn will make the kthread
go to sleep.
Signed-off-by: Samiullah Khawaja <skhawaja@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Martin Karsten <mkarsten@uwaterloo.ca>
Tested-by: Martin Karsten <mkarsten@uwaterloo.ca>
Link: https://patch.msgid.link/20251028203007.575686-2-skhawaja@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Cross-merge BPF and other fixes after downstream PR.
No conflicts.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
The initial set of namespace comes with fixed inode numbers making it
easy for userspace to identify them solely based on that information.
This has long preceeded anything here.
Similarly, let's assign fixed namespace ids for the initial namespaces.
Kill the cookie and use a sequentially increasing number. This has the
nice side-effect that the owning user namespace will always have a
namespace id that is smaller than any of it's descendant namespaces.
Link: https://patch.msgid.link/20251029-work-namespace-nstree-listns-v4-15-2e6f823ebdc0@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
|
|
Pull bpf fixes from Alexei Starovoitov:
- Mark migrate_disable/enable() as always_inline to avoid issues with
partial inlining (Yonghong Song)
- Fix powerpc stack register definition in libbpf bpf_tracing.h (Andrii
Nakryiko)
- Reject negative head_room in __bpf_skb_change_head (Daniel Borkmann)
- Conditionally include dynptr copy kfuncs (Malin Jonsson)
- Sync pending IRQ work before freeing BPF ring buffer (Noorain Eqbal)
- Do not audit capability check in x86 do_jit() (Ondrej Mosnacek)
- Fix arm64 JIT of BPF_ST insn when it writes into arena memory
(Puranjay Mohan)
* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
bpf/arm64: Fix BPF_ST into arena memory
bpf: Make migrate_disable always inline to avoid partial inlining
bpf: Reject negative head_room in __bpf_skb_change_head
bpf: Conditionally include dynptr copy kfuncs
libbpf: Fix powerpc's stack register definition in bpf_tracing.h
bpf: Do not audit capability check in do_jit()
bpf: Sync pending IRQ work before freeing ring buffer
|
|
Cross-merge networking fixes after downstream PR (net-6.18-rc4).
No conflicts, adjacent changes:
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
ded9813d17d3 ("net: stmmac: Consider Tx VLAN offload tag length for maxSDU")
26ab9830beab ("net: stmmac: replace has_xxxx with core_type")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The zero-copy Device Memory (Devmem) transmit path
relies on the socket's route cache (`dst_entry`) to
validate that the packet is being sent via the network
device to which the DMA buffer was bound.
However, this check incorrectly fails and returns `-ENODEV`
if the socket's route cache entry (`dst`) is merely missing
or expired (`dst == NULL`). This scenario is observed during
network events, such as when flow steering rules are deleted,
leading to a temporary route cache invalidation.
This patch fixes -ENODEV error for `net_devmem_get_binding()`
by doing the following:
1. It attempts to rebuild the route via `rebuild_header()`
if the route is initially missing (`dst == NULL`). This
allows the TCP/IP stack to recover from transient route
cache misses.
2. It uses `rcu_read_lock()` and `dst_dev_rcu()` to safely
access the network device pointer (`dst_dev`) from the
route, preventing use-after-free conditions if the
device is concurrently removed.
3. It maintains the critical safety check by validating
that the retrieved destination device (`dst_dev`) is
exactly the device registered in the Devmem binding
(`binding->dev`).
These changes prevent unnecessary ENODEV failures while
maintaining the critical safety requirement that the
Devmem resources are only used on the bound network device.
Reviewed-by: Bobby Eshleman <bobbyeshleman@meta.com>
Reported-by: Eric Dumazet <edumazet@google.com>
Reported-by: Vedant Mathur <vedantmathur@google.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Fixes: bd61848900bf ("net: devmem: Implement TX path")
Signed-off-by: Shivaji Kant <shivajikant@google.com>
Link: https://patch.msgid.link/20251029065420.3489943-1-shivajikant@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Add the ability to append the incoming IP interface information to
ICMPv6 error messages in accordance with RFC 5837 and RFC 4884. This is
required for more meaningful traceroute results in unnumbered networks.
The feature is disabled by default and controlled via a new sysctl
("net.ipv6.icmp.errors_extension_mask") which accepts a bitmask of ICMP
extensions to append to ICMP error messages. Currently, only a single
value is supported, but the interface and the implementation should be
able to support more extensions, if needed.
Clone the skb and copy the relevant data portions before modifying the
skb as the caller of icmp6_send() still owns the skb after the function
returns. This should be fine since by default ICMP error messages are
rate limited to 1000 per second and no more than 1 per second per
specific host.
Trim or pad the packet to 128 bytes before appending the ICMP extension
structure in order to be compatible with legacy applications that assume
that the ICMP extension structure always starts at this offset (the
minimum length specified by RFC 4884).
Since commit 20e1954fe238 ("ipv6: RFC 4884 partial support for SIT/GRE
tunnels") it is possible for icmp6_send() to be called with an skb that
already contains ICMP extensions. This can happen when we receive an
ICMPv4 message with extensions from a tunnel and translate it to an
ICMPv6 message towards an IPv6 host in the overlay network. I could not
find an RFC that supports this behavior, but it makes sense to not
overwrite the original extensions that were appended to the packet.
Therefore, avoid appending extensions if the length field in the
provided ICMPv6 header is already filled.
Export netdev_copy_name() using EXPORT_IPV6_MOD_GPL() to make it
available to IPv6 when it is built as a module.
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251027082232.232571-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Add likely() and unlikely() clauses for the common cases:
Device is running.
Queue is not full.
Queue is less than half capacity.
Add max_backlog parameter to skb_flow_limit() to avoid
a second READ_ONCE(net_hotdata.max_backlog).
skb_flow_limit() does not need the backlog_lock protection,
and can be called before we acquire the lock, for even better
resistance to attacks.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251024090517.3289181-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Yinhao et al. recently reported:
Our fuzzing tool was able to create a BPF program which triggered
the below BUG condition inside pskb_expand_head.
[ 23.016047][T10006] kernel BUG at net/core/skbuff.c:2232!
[...]
[ 23.017301][T10006] RIP: 0010:pskb_expand_head+0x1519/0x1530
[...]
[ 23.021249][T10006] Call Trace:
[ 23.021387][T10006] <TASK>
[ 23.021507][T10006] ? __pfx_pskb_expand_head+0x10/0x10
[ 23.021725][T10006] __bpf_skb_change_head+0x22a/0x520
[ 23.021939][T10006] bpf_skb_change_head+0x34/0x1b0
[ 23.022143][T10006] ___bpf_prog_run+0xf70/0xb670
[ 23.022342][T10006] __bpf_prog_run32+0xed/0x140
[...]
The problem is that in __bpf_skb_change_head() we need to reject a
negative head_room as otherwise this propagates all the way to the
pskb_expand_head() from skb_cow(). For example, if the BPF test infra
passes a skb with gso_skb:1 to the BPF helper with a negative head_room
of -22, then this gets passed into skb_cow(). __skb_cow() in this
example calculates a delta of -86 which gets aligned to -64, and then
triggers BUG_ON(nhead < 0). Thus, reject malformed negative input.
Fixes: 3a0af8fd61f9 ("bpf: BPF for lightweight tunnel infrastructure")
Reported-by: Yinhao Hu <dddddd@hust.edu.cn>
Reported-by: Kaiyan Mei <M202472210@hust.edu.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Dongliang Mu <dzm91@hust.edu.cn>
Link: https://patch.msgid.link/20251023125532.182262-1-daniel@iogearbox.net
|
|
sctp_accept() will use sk_clone_lock(), but it will be called
with the parent socket locked, and sctp_migrate() acquires the
child lock later.
Let's add no lock version of sk_clone_lock().
Note that lockdep complains if we simply use bh_lock_sock_nested().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Link: https://patch.msgid.link/20251023231751.4168390-5-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Only neigh_for_each() and neigh_seq_start/stop() are on the
reader side of neigh_table.lock.
Let's convert rwlock to the plain spinlock.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251022054004.2514876-6-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
neightbl_set() fetches neigh_tables[] and updates attributes under
write_lock_bh(&tbl->lock), so RTNL is not needed.
neigh_table_clear() synchronises RCU only, and rcu_dereference_rtnl()
protects nothing here.
If we released RCU after fetching neigh_tables[], there would be no
synchronisation to block neigh_table_clear() further, so RCU is held
until the end of the function.
Another option would be to protect neigh_tables[] user with SRCU
and add synchronize_srcu() in neigh_table_clear().
But, holding RCU should be fine as we hold write_lock_bh() for the
rest of neightbl_set() anyway.
Let's perform RTM_SETNEIGHTBL under RCU and drop RTNL.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251022054004.2514876-5-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
neightbl_dump_info() calls these functions for each neigh_tables[]
entry:
1. neightbl_fill_info() for tbl->parms
2. neightbl_fill_param_info() for tbl->parms_list (except tbl->parms)
Both functions rely on the table lock (read_lock_bh(&tbl->lock))
and RTNL is not needed.
Let's fetch the table under RCU and convert RTM_GETNEIGHTBL to RCU.
Note that the first entry of tbl->parms_list is tbl->parms.list and
embedded in neigh_table, so list_next_entry() is safe.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251022054004.2514876-4-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
NEIGH_VAR() is read locklessly in the fast path, and IPv6 ndisc uses
NEIGH_VAR_SET() locklessly.
The next patch will convert neightbl_dump_info() to RCU.
Let's annotate accesses to neigh_param with READ_ONCE() and WRITE_ONCE().
Note that ndisc_ifinfo_sysctl_change() uses &NEIGH_VAR() and we cannot
use '&' with READ_ONCE(), so NEIGH_VAR_PTR() is introduced.
Note also that NEIGH_VAR_INIT() does not need WRITE_ONCE() as it is before
parms is published. Also, the only user hippi_neigh_setup_dev() is no
longer called since commit e3804cbebb67 ("net: remove COMPAT_NET_DEV_OPS"),
which looks wrong, but probably no one uses HIPPI and RoadRunner.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251022054004.2514876-3-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
We will convert RTM_GETNEIGHTBL to RCU soon, where we traverse
tbl->parms_list under RCU in neightbl_dump_info().
Let's use RCU list helper for neigh_parms in neigh_parms_alloc()
and neigh_parms_release().
neigh_table_init() uses the plain list_add() for the default
neigh_parm that is embedded in the table and not yet published.
Note that neigh_parms_release() already uses call_rcu() to free
neigh_parms.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20251022054004.2514876-2-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Cross-merge networking fixes after downstream PR (net-6.18-rc3).
No conflicts or adjacent changes.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Some protocols using TCP encapsulation (e.g., espintcp, openvpn) deliver
userspace-bound packets through a custom skb queue rather than the
standard sk_receive_queue.
Introduce datagram_poll_queue that accepts an explicit receive queue,
and convert datagram_poll into a wrapper around datagram_poll_queue.
This allows protocols with custom skb queues to reuse the core polling
logic without relying on sk_receive_queue.
Cc: Sabrina Dubroca <sd@queasysnail.net>
Cc: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: Ralf Lici <ralf@mandelbit.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Antonio Quartulli <antonio@openvpn.net>
Link: https://patch.msgid.link/20251021100942.195010-2-ralf@mandelbit.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Some high level software drivers need to compute features from lower
devices. But each has their own implementations and may lost some
feature compute. Let's use one common function to compute features
for kinds of these devices.
The new helper uses the current bond implementation as the reference
one, as the latter already handles all the relevant aspects: netdev
features, TSO limits and dst retention.
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://patch.msgid.link/20251017034155.61990-2-liuhangbin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
syzbot found that the local_unlock_nested_bh() call was
missing in some cases.
WARNING: possible recursive locking detected
syzkaller #0 Not tainted
--------------------------------------------
syz.2.329/7421 is trying to acquire lock:
ffffe8ffffd48888 ((&cell->bh_lock)){+...}-{3:3}, at: spin_lock include/linux/spinlock_rt.h:44 [inline]
ffffe8ffffd48888 ((&cell->bh_lock)){+...}-{3:3}, at: gro_cells_receive+0x404/0x790 net/core/gro_cells.c:30
but task is already holding lock:
ffffe8ffffd48888 ((&cell->bh_lock)){+...}-{3:3}, at: spin_lock include/linux/spinlock_rt.h:44 [inline]
ffffe8ffffd48888 ((&cell->bh_lock)){+...}-{3:3}, at: gro_cells_receive+0x404/0x790 net/core/gro_cells.c:30
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock((&cell->bh_lock));
lock((&cell->bh_lock));
*** DEADLOCK ***
Given the introduction of @have_bh_lock variable, it seems the author
intent was to have the local_unlock_nested_bh() after the @unlock label.
Fixes: 25718fdcbdd2 ("net: gro_cells: Use nested-BH locking for gro_cell")
Reported-by: syzbot+f9651b9a8212e1c8906f@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68f65eb9.a70a0220.205af.0034.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20251020161114.1891141-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
UDP TX packets destructor is sock_wfree().
It suffers from a cache line bouncing in sock_def_write_space_wfree().
Instead of reading sk->sk_wmem_alloc after we just did an atomic RMW
on it, use __refcount_sub_and_test() to get the old value for free,
and pass the new value to sock_def_write_space_wfree().
Add __sock_writeable() helper.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251017133712.2842665-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Following loop in napi_skb_cache_put() is unrolled by the compiler
even if CONFIG_KASAN is not enabled:
for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++)
kasan_mempool_unpoison_object(nc->skb_cache[i],
kmem_cache_size(net_hotdata.skbuff_cache));
We have 32 times this sequence, for a total of 384 bytes.
48 8b 3d 00 00 00 00 net_hotdata.skbuff_cache,%rdi
e8 00 00 00 00 call kmem_cache_size
This is because kmem_cache_size() is not an inline and not const,
and kasan_unpoison_object_data() is an inline function.
Cache kmem_cache_size() result in a variable, so that
the compiler can remove dead code (and variable) when/if
CONFIG_KASAN is unset.
After this patch, napi_skb_cache_put() is inlined in its callers,
and we avoid one kmem_cache_size() call in napi_skb_cache_get()
and napi_skb_cache_get_bulk().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/20251016182911.1132792-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Cpus serving NIC interrupts and specifically TX completions are often
trapped in also restarting a busy qdisc (because qdisc was stopped by BQL
or the driver's own flow control).
When they call netdev_tx_completed_queue() or netif_tx_wake_queue(),
they call __netif_schedule() so that the queue can be run
later from net_tx_action() (involving NET_TX_SOFTIRQ)
Quite often, by the time the cpu reaches net_tx_action(), another cpu
grabbed the qdisc spinlock from __dev_xmit_skb(), and we spend too much
time spinning on this lock.
We can detect in __netif_schedule() if a cpu is already at a specific
point in __dev_xmit_skb() where we have the guarantee the queue will
be run.
This patch gives a 13 % increase of throughput on an IDPF NIC (200Gbit),
32 TX qeues, sending UDP packets of 120 bytes.
This also helps __qdisc_run() to not force a NET_TX_SOFTIRQ
if another thread is waiting in __dev_xmit_skb()
Before:
sar -n DEV 5 5|grep eth1|grep Average
Average: eth1 1496.44 52191462.56 210.00 13369396.90 0.00 0.00 0.00 54.76
After:
sar -n DEV 5 5|grep eth1|grep Average
Average: eth1 1457.88 59363099.96 205.08 15206384.35 0.00 0.00 0.00 62.29
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251017145334.3016097-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Yinhao et al. reported that their fuzzer tool was able to trigger a
skb_warn_bad_offload() from netif_skb_features() -> gso_features_check().
When a BPF program - triggered via BPF test infra - pushes the packet
to the loopback device via bpf_clone_redirect() then mentioned offload
warning can be seen. GSO-related features are then rightfully disabled.
We get into this situation due to convert___skb_to_skb() setting
gso_segs and gso_size but not gso_type. Technically, it makes sense
that this warning triggers since the GSO properties are malformed due
to the gso_type. Potentially, the gso_type could be marked non-trustworthy
through setting it at least to SKB_GSO_DODGY without any other specific
assumptions, but that also feels wrong given we should not go further
into the GSO engine in the first place.
The checks were added in 121d57af308d ("gso: validate gso_type in GSO
handlers") because there were malicious (syzbot) senders that combine
a protocol with a non-matching gso_type. If we would want to drop such
packets, gso_features_check() currently only returns feature flags via
netif_skb_features(), so one location for potentially dropping such skbs
could be validate_xmit_unreadable_skb(), but then otoh it would be
an additional check in the fast-path for a very corner case. Given
bpf_clone_redirect() is the only place where BPF test infra could emit
such packets, lets reject them right there.
Fixes: 850a88cc4096 ("bpf: Expose __sk_buff wire_len/gso_segs to BPF_PROG_TEST_RUN")
Fixes: cf62089b0edd ("bpf: Add gso_size to __sk_buff")
Reported-by: Yinhao Hu <dddddd@hust.edu.cn>
Reported-by: Kaiyan Mei <M202472210@hust.edu.cn>
Reported-by: Dongliang Mu <dzm91@hust.edu.cn>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20251020075441.127980-1-daniel@iogearbox.net
|
|
Cross-merge BPF and other fixes after downstream PR.
No conflicts.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Martin KaFai Lau says:
====================
pull-request: bpf-next 2025-10-16
We've added 6 non-merge commits during the last 1 day(s) which contain
a total of 18 files changed, 577 insertions(+), 38 deletions(-).
The main changes are:
1) Bypass the global per-protocol memory accounting either by setting
a netns sysctl or using bpf_setsockopt in a bpf program,
from Kuniyuki Iwashima.
* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next:
selftests/bpf: Add test for sk->sk_bypass_prot_mem.
bpf: Introduce SK_BPF_BYPASS_PROT_MEM.
bpf: Support bpf_setsockopt() for BPF_CGROUP_INET_SOCK_CREATE.
net: Introduce net.core.bypass_prot_mem sysctl.
net: Allow opt-out from global protocol memory accounting.
tcp: Save lock_sock() for memcg in inet_csk_accept().
====================
Link: https://patch.msgid.link/20251016204539.773707-1-martin.lau@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Remove busylock spinlock and use a lockless list (llist)
to reduce spinlock contention to the minimum.
Idea is that only one cpu might spin on the qdisc spinlock,
while others simply add their skb in the llist.
After this patch, we get a 300 % improvement on heavy TX workloads.
- Sending twice the number of packets per second.
- While consuming 50 % less cycles.
Note that this also allows in the future to submit batches
to various qdisc->enqueue() methods.
Tested:
- Dual Intel(R) Xeon(R) 6985P-C (480 hyper threads).
- 100Gbit NIC, 30 TX queues with FQ packet scheduler.
- echo 64 >/sys/kernel/slab/skbuff_small_head/cpu_partial (avoid contention in mm)
- 240 concurrent "netperf -t UDP_STREAM -- -m 120 -n"
Before:
16 Mpps (41 Mpps if each thread is pinned to a different cpu)
vmstat 2 5
procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu-----
r b swpd free buff cache si so bi bo in cs us sy id wa st
243 0 0 2368988672 51036 1100852 0 0 146 1 242 60 0 9 91 0 0
244 0 0 2368988672 51036 1100852 0 0 536 10 487745 14718 0 52 48 0 0
244 0 0 2368988672 51036 1100852 0 0 512 0 503067 46033 0 52 48 0 0
244 0 0 2368988672 51036 1100852 0 0 512 0 494807 12107 0 52 48 0 0
244 0 0 2368988672 51036 1100852 0 0 702 26 492845 10110 0 52 48 0 0
Lock contention (1 second sample taken on 8 cores)
perf lock record -C0-7 sleep 1; perf lock contention
contended total wait max wait avg wait type caller
442111 6.79 s 162.47 ms 15.35 us spinlock dev_hard_start_xmit+0xcd
5961 9.57 ms 8.12 us 1.60 us spinlock __dev_queue_xmit+0x3a0
244 560.63 us 7.63 us 2.30 us spinlock do_softirq+0x5b
13 25.09 us 3.21 us 1.93 us spinlock net_tx_action+0xf8
If netperf threads are pinned, spinlock stress is very high.
perf lock record -C0-7 sleep 1; perf lock contention
contended total wait max wait avg wait type caller
964508 7.10 s 147.25 ms 7.36 us spinlock dev_hard_start_xmit+0xcd
201 268.05 us 4.65 us 1.33 us spinlock __dev_queue_xmit+0x3a0
12 26.05 us 3.84 us 2.17 us spinlock do_softirq+0x5b
@__dev_queue_xmit_ns:
[256, 512) 21 | |
[512, 1K) 631 | |
[1K, 2K) 27328 |@ |
[2K, 4K) 265392 |@@@@@@@@@@@@@@@@ |
[4K, 8K) 417543 |@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[8K, 16K) 826292 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[16K, 32K) 733822 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[32K, 64K) 19055 |@ |
[64K, 128K) 17240 |@ |
[128K, 256K) 25633 |@ |
[256K, 512K) 4 | |
After:
29 Mpps (57 Mpps if each thread is pinned to a different cpu)
vmstat 2 5
procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu-----
r b swpd free buff cache si so bi bo in cs us sy id wa st
78 0 0 2369573632 32896 1350988 0 0 22 0 331 254 0 8 92 0 0
75 0 0 2369573632 32896 1350988 0 0 22 50 425713 280199 0 23 76 0 0
104 0 0 2369573632 32896 1350988 0 0 290 0 430238 298247 0 23 76 0 0
86 0 0 2369573632 32896 1350988 0 0 132 0 428019 291865 0 24 76 0 0
90 0 0 2369573632 32896 1350988 0 0 502 0 422498 278672 0 23 76 0 0
perf lock record -C0-7 sleep 1; perf lock contention
contended total wait max wait avg wait type caller
2524 116.15 ms 486.61 us 46.02 us spinlock __dev_queue_xmit+0x55b
5821 107.18 ms 371.67 us 18.41 us spinlock dev_hard_start_xmit+0xcd
2377 9.73 ms 35.86 us 4.09 us spinlock ___slab_alloc+0x4e0
923 5.74 ms 20.91 us 6.22 us spinlock ___slab_alloc+0x5c9
121 3.42 ms 193.05 us 28.24 us spinlock net_tx_action+0xf8
6 564.33 us 167.60 us 94.05 us spinlock do_softirq+0x5b
If netperf threads are pinned (~54 Mpps)
perf lock record -C0-7 sleep 1; perf lock contention
32907 316.98 ms 195.98 us 9.63 us spinlock dev_hard_start_xmit+0xcd
4507 61.83 ms 212.73 us 13.72 us spinlock __dev_queue_xmit+0x554
2781 23.53 ms 40.03 us 8.46 us spinlock ___slab_alloc+0x5c9
3554 18.94 ms 34.69 us 5.33 us spinlock ___slab_alloc+0x4e0
233 9.09 ms 215.70 us 38.99 us spinlock do_softirq+0x5b
153 930.66 us 48.67 us 6.08 us spinlock net_tx_action+0xfd
84 331.10 us 14.22 us 3.94 us spinlock ___slab_alloc+0x5c9
140 323.71 us 9.94 us 2.31 us spinlock ___slab_alloc+0x4e0
@__dev_queue_xmit_ns:
[128, 256) 1539830 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[256, 512) 2299558 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[512, 1K) 483936 |@@@@@@@@@@ |
[1K, 2K) 265345 |@@@@@@ |
[2K, 4K) 145463 |@@@ |
[4K, 8K) 54571 |@ |
[8K, 16K) 10270 | |
[16K, 32K) 9385 | |
[32K, 64K) 7749 | |
[64K, 128K) 26799 | |
[128K, 256K) 2665 | |
[256K, 512K) 665 | |
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Tested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20251014171907.3554413-7-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
This reverts commits 0f022d32c3eca477fbf79a205243a6123ed0fe11
and 44180feaccf266d9b0b28cc4ceaac019817deb5c.
Prior patch in this series implemented loop detection
in act_mirred, we can remove q->owner to save some cycles
in the fast path.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Victor Nogueira <victor@mojatatu.com>
Tested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20251014171907.3554413-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
While stress testing UDP senders on a host with expensive indirect
calls, I found cpus processing TX completions where showing
a very high cost (20%) in sock_wfree() due to
CONFIG_MITIGATION_RETPOLINE=y.
Take care of TCP and UDP TX destructors and use INDIRECT_CALL_3() macro.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Tested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20251014171907.3554413-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Creating FDB entries is possible from a non-initial user namespace when
having CAP_NET_ADMIN, yet, when deleting FDB entries, processes receive
an EPERM because the capability is always checked against the initial
user namespace. This restricts the FDB management from unprivileged
containers.
Drop the netlink_capable check in rtnl_fdb_del as it was originally
dropped in c5c351088ae7 and reintroduced in 1690be63a27b without
intention.
This patch was tested using a container on GyroidOS, where it was
possible to delete FDB entries from an unprivileged user namespace and
private network namespace.
Fixes: 1690be63a27b ("bridge: Add vlan support to static neighbors")
Reviewed-by: Michael Weiß <michael.weiss@aisec.fraunhofer.de>
Tested-by: Harshal Gohel <hg@simonwunderlich.de>
Signed-off-by: Johannes Wiesböck <johannes.wiesboeck@aisec.fraunhofer.de>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20251015201548.319871-1-johannes.wiesboeck@aisec.fraunhofer.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Some network drivers assume this field is zero after napi_get_frags().
We must clear it in napi_reuse_skb() otherwise the following can happen:
1) A packet is received, and skb_shinfo(skb)->hwtstamps is populated
because a bit in the receive descriptor announced hwtstamp
availability for this packet.
2) Packet is given to gro layer via napi_gro_frags().
3) Packet is merged to a prior one held in GRO queues.
4) skb is saved after some cleanup in napi->skb via a call
to napi_reuse_skb().
5) Next packet is received 10 seconds later, gets the recycled skb
from napi_get_frags().
6) The receive descriptor does not announce hwtstamp availability.
Driver does not clear shinfo->hwtstamps.
7) We have in shinfo->hwtstamps an old timestamp.
Fixes: ac45f602ee3d ("net: infrastructure for hardware time stamping")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/20251015063221.4171986-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
If a socket has sk->sk_bypass_prot_mem flagged, the socket opts out
of the global protocol memory accounting.
This is easily controlled by net.core.bypass_prot_mem sysctl, but it
lacks flexibility.
Let's support flagging (and clearing) sk->sk_bypass_prot_mem via
bpf_setsockopt() at the BPF_CGROUP_INET_SOCK_CREATE hook.
int val = 1;
bpf_setsockopt(ctx, SOL_SOCKET, SK_BPF_BYPASS_PROT_MEM,
&val, sizeof(val));
As with net.core.bypass_prot_mem, this is inherited to child sockets,
and BPF always takes precedence over sysctl at socket(2) and accept(2).
SK_BPF_BYPASS_PROT_MEM is only supported at BPF_CGROUP_INET_SOCK_CREATE
and not supported on other hooks for some reasons:
1. UDP charges memory under sk->sk_receive_queue.lock instead
of lock_sock()
2. Modifying the flag after skb is charged to sk requires such
adjustment during bpf_setsockopt() and complicates the logic
unnecessarily
We can support other hooks later if a real use case justifies that.
Most changes are inline and hard to trace, but a microbenchmark on
__sk_mem_raise_allocated() during neper/tcp_stream showed that more
samples completed faster with sk->sk_bypass_prot_mem == 1. This will
be more visible under tcp_mem pressure (but it's not a fair comparison).
# bpftrace -e 'kprobe:__sk_mem_raise_allocated { @start[tid] = nsecs; }
kretprobe:__sk_mem_raise_allocated /@start[tid]/
{ @end[tid] = nsecs - @start[tid]; @times = hist(@end[tid]); delete(@start[tid]); }'
# tcp_stream -6 -F 1000 -N -T 256
Without bpf prog:
[128, 256) 3846 | |
[256, 512) 1505326 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[512, 1K) 1371006 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[1K, 2K) 198207 |@@@@@@ |
[2K, 4K) 31199 |@ |
With bpf prog in the next patch:
(must be attached before tcp_stream)
# bpftool prog load sk_bypass_prot_mem.bpf.o /sys/fs/bpf/test type cgroup/sock_create
# bpftool cgroup attach /sys/fs/cgroup/test cgroup_inet_sock_create pinned /sys/fs/bpf/test
[128, 256) 6413 | |
[256, 512) 1868425 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[512, 1K) 1101697 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[1K, 2K) 117031 |@@@@ |
[2K, 4K) 11773 | |
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-6-kuniyu@google.com
|
|
We will support flagging sk->sk_bypass_prot_mem via bpf_setsockopt()
at the BPF_CGROUP_INET_SOCK_CREATE hook.
BPF_CGROUP_INET_SOCK_CREATE is invoked by __cgroup_bpf_run_filter_sk()
that passes a pointer to struct sock to the bpf prog as void *ctx.
But there are no bpf_func_proto for bpf_setsockopt() that receives
the ctx as a pointer to struct sock.
Also, bpf_getsockopt() will be necessary for a cgroup with multiple
bpf progs running.
Let's add new bpf_setsockopt() and bpf_getsockopt() variants for
BPF_CGROUP_INET_SOCK_CREATE.
Note that inet_create() is not under lock_sock() and has the same
semantics with bpf_lsm_unlocked_sockopt_hooks.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-5-kuniyu@google.com
|
|
If a socket has sk->sk_bypass_prot_mem flagged, the socket opts out
of the global protocol memory accounting.
Let's control the flag by a new sysctl knob.
The flag is written once during socket(2) and is inherited to child
sockets.
Tested with a script that creates local socket pairs and send()s a
bunch of data without recv()ing.
Setup:
# mkdir /sys/fs/cgroup/test
# echo $$ >> /sys/fs/cgroup/test/cgroup.procs
# sysctl -q net.ipv4.tcp_mem="1000 1000 1000"
# ulimit -n 524288
Without net.core.bypass_prot_mem, charged to tcp_mem & memcg
# python3 pressure.py &
# cat /sys/fs/cgroup/test/memory.stat | grep sock
sock 22642688 <-------------------------------------- charged to memcg
# cat /proc/net/sockstat| grep TCP
TCP: inuse 2006 orphan 0 tw 0 alloc 2008 mem 5376 <-- charged to tcp_mem
# ss -tn | head -n 5
State Recv-Q Send-Q Local Address:Port Peer Address:Port
ESTAB 2000 0 127.0.0.1:34479 127.0.0.1:53188
ESTAB 2000 0 127.0.0.1:34479 127.0.0.1:49972
ESTAB 2000 0 127.0.0.1:34479 127.0.0.1:53868
ESTAB 2000 0 127.0.0.1:34479 127.0.0.1:53554
# nstat | grep Pressure || echo no pressure
TcpExtTCPMemoryPressures 1 0.0
With net.core.bypass_prot_mem=1, charged to memcg only:
# sysctl -q net.core.bypass_prot_mem=1
# python3 pressure.py &
# cat /sys/fs/cgroup/test/memory.stat | grep sock
sock 2757468160 <------------------------------------ charged to memcg
# cat /proc/net/sockstat | grep TCP
TCP: inuse 2006 orphan 0 tw 0 alloc 2008 mem 0 <- NOT charged to tcp_mem
# ss -tn | head -n 5
State Recv-Q Send-Q Local Address:Port Peer Address:Port
ESTAB 111000 0 127.0.0.1:36019 127.0.0.1:49026
ESTAB 110000 0 127.0.0.1:36019 127.0.0.1:45630
ESTAB 110000 0 127.0.0.1:36019 127.0.0.1:44870
ESTAB 111000 0 127.0.0.1:36019 127.0.0.1:45274
# nstat | grep Pressure || echo no pressure
no pressure
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-4-kuniyu@google.com
|
|
Some protocols (e.g., TCP, UDP) implement memory accounting for socket
buffers and charge memory to per-protocol global counters pointed to by
sk->sk_proto->memory_allocated.
Sometimes, system processes do not want that limitation. For a similar
purpose, there is SO_RESERVE_MEM for sockets under memcg.
Also, by opting out of the per-protocol accounting, sockets under memcg
can avoid paying costs for two orthogonal memory accounting mechanisms.
A microbenchmark result is in the subsequent bpf patch.
Let's allow opt-out from the per-protocol memory accounting if
sk->sk_bypass_prot_mem is true.
sk->sk_bypass_prot_mem and sk->sk_prot are placed in the same cache
line, and sk_has_account() always fetches sk->sk_prot before accessing
sk->sk_bypass_prot_mem, so there is no extra cache miss for this patch.
The following patches will set sk->sk_bypass_prot_mem to true, and
then, the per-protocol memory accounting will be skipped.
Note that this does NOT disable memcg, but rather the per-protocol one.
Another option not to use the hole in struct sock_common is create
sk_prot variants like tcp_prot_bypass, but this would complicate
SOCKMAP logic, tcp_bpf_prots etc.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://patch.msgid.link/20251014235604.3057003-3-kuniyu@google.com
|
|
Cross-merge networking fixes after downstream PR (net-6.18-rc2).
No conflicts or adjacent changes.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from CAN
Current release - regressions:
- udp: do not use skb_release_head_state() before
skb_attempt_defer_free()
- gro_cells: use nested-BH locking for gro_cell
- dpll: zl3073x: increase maximum size of flash utility
Previous releases - regressions:
- core: fix lockdep splat on device unregister
- tcp: fix tcp_tso_should_defer() vs large RTT
- tls:
- don't rely on tx_work during send()
- wait for pending async decryptions if tls_strp_msg_hold fails
- can: j1939: add missing calls in NETDEV_UNREGISTER notification
handler
- eth: lan78xx: fix lost EEPROM write timeout in
lan78xx_write_raw_eeprom
Previous releases - always broken:
- ip6_tunnel: prevent perpetual tunnel growth
- dpll: zl3073x: handle missing or corrupted flash configuration
- can: m_can: fix pm_runtime and CAN state handling
- eth:
- ixgbe: fix too early devlink_free() in ixgbe_remove()
- ixgbevf: fix mailbox API compatibility
- gve: Check valid ts bit on RX descriptor before hw timestamping
- idpf: cleanup remaining SKBs in PTP flows
- r8169: fix packet truncation after S4 resume on RTL8168H/RTL8111H"
* tag 'net-6.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (50 commits)
udp: do not use skb_release_head_state() before skb_attempt_defer_free()
net: usb: lan78xx: fix use of improperly initialized dev->chipid in lan78xx_reset
netdevsim: set the carrier when the device goes up
selftests: tls: add test for short splice due to full skmsg
selftests: net: tls: add tests for cmsg vs MSG_MORE
tls: don't rely on tx_work during send()
tls: wait for pending async decryptions if tls_strp_msg_hold fails
tls: always set record_type in tls_process_cmsg
tls: wait for async encrypt in case of error during latter iterations of sendmsg
tls: trim encrypted message to match the plaintext on short splice
tg3: prevent use of uninitialized remote_adv and local_adv variables
MAINTAINERS: new entry for IPv6 IOAM
gve: Check valid ts bit on RX descriptor before hw timestamping
net: core: fix lockdep splat on device unregister
MAINTAINERS: add myself as maintainer for b53
selftests: net: check jq command is supported
net: airoha: Take into account out-of-order tx completions in airoha_dev_xmit()
tcp: fix tcp_tso_should_defer() vs large RTT
r8152: add error handling in rtl8152_driver_init
usbnet: Fix using smp_processor_id() in preemptible code warnings
...
|
|
Michal reported and bisected an issue after recent adoption
of skb_attempt_defer_free() in UDP.
The issue here is that skb_release_head_state() is called twice per skb,
one time from skb_consume_udp(), then a second time from skb_defer_free_flush()
and napi_consume_skb().
As Sabrina suggested, remove skb_release_head_state() call from
skb_consume_udp().
Add a DEBUG_NET_WARN_ON_ONCE(skb_nfct(skb)) in skb_attempt_defer_free()
Many thanks to Michal, Sabrina, Paolo and Florian for their help.
Fixes: 6471658dc66c ("udp: use skb_attempt_defer_free()")
Reported-and-bisected-by: Michal Kubecek <mkubecek@suse.cz>
Closes: https://lore.kernel.org/netdev/gpjh4lrotyephiqpuldtxxizrsg6job7cvhiqrw72saz2ubs3h@g6fgbvexgl3r/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Michal Kubecek <mkubecek@suse.cz>
Cc: Sabrina Dubroca <sd@queasysnail.net>
Cc: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/20251015052715.4140493-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
This is a followup of commit 726e9e8b94b9 ("tcp: refine
skb->ooo_okay setting") and of prior commit in this series
("net: control skb->ooo_okay from skb_set_owner_w()")
skb->ooo_okay might never be set for bulk flows that always
have at least one skb in a qdisc queue of NIC queue,
especially if TX completion is delayed because of a stressed cpu.
The so-called "strange attractors" has caused many performance
issues (see for instance 9b462d02d6dd ("tcp: TCP Small Queues
and strange attractors")), we need to do better.
We have tried very hard to avoid reorders because TCP was
not dealing with them nicely a decade ago.
Use the new net.core.txq_reselection_ms sysctl to let
flows follow XPS and select a more efficient queue.
After this patch, we no longer have to make sure threads
are pinned to cpus, they now can be migrated without
adding too much spinlock/qdisc/TX completion pressure anymore.
TX completion part was problematic, because it added false sharing
on various socket fields, but also added false sharing and spinlock
contention in mm layers. Calling skb_orphan() from ndo_start_xmit()
is not an option unfortunately.
Note for later:
1) move sk->sk_tx_queue_mapping closer
to sk_tx_queue_mapping_jiffies for better cache locality.
2) Study if 9b462d02d6dd ("tcp: TCP Small Queues
and strange attractors") could be revised.
Tested:
Used a host with 32 TX queues, shared by groups of 8 cores.
XPS setup :
echo ff >/sys/class/net/eth1/queue/tx-0/xps_cpus
echo ff00 >/sys/class/net/eth1/queue/tx-1/xps_cpus
echo ff0000 >/sys/class/net/eth1/queue/tx-2/xps_cpus
echo ff000000 >/sys/class/net/eth1/queue/tx-3/xps_cpus
echo ff,00000000 >/sys/class/net/eth1/queue/tx-4/xps_cpus
echo ff00,00000000 >/sys/class/net/eth1/queue/tx-5/xps_cpus
echo ff0000,00000000 >/sys/class/net/eth1/queue/tx-6/xps_cpus
echo ff000000,00000000 >/sys/class/net/eth1/queue/tx-7/xps_cpus
...
Launched a tcp_stream with 15 threads and 1000 flows, initially affined to core 0-15
taskset -c 0-15 tcp_stream -T15 -F1000 -l1000 -c -H target_host
Checked that only queues 0 and 1 are used as instructed by XPS :
tc -s qdisc show dev eth1|grep backlog|grep -v "backlog 0b 0p"
backlog 123489410b 1890p
backlog 69809026b 1064p
backlog 52401054b 805p
Then force each thread to run on cpu 1,9,17,25,33,41,49,57,65,73,81,89,97,105,113,121
C=1;PID=`pidof tcp_stream`;for P in `ls /proc/$PID/task`; do taskset -pc $C $P; C=$(($C + 8));done
Set txq_reselection_ms to 1000
echo 1000 > /proc/sys/net/core/txq_reselection_ms
Check that the flows have migrated nicely:
tc -s qdisc show dev eth1|grep backlog|grep -v "backlog 0b 0p"
backlog 130508314b 1916p
backlog 8584380b 126p
backlog 8584380b 126p
backlog 8379990b 123p
backlog 8584380b 126p
backlog 8487484b 125p
backlog 8584380b 126p
backlog 8448120b 124p
backlog 8584380b 126p
backlog 8720640b 128p
backlog 8856900b 130p
backlog 8584380b 126p
backlog 8652510b 127p
backlog 8448120b 124p
backlog 8516250b 125p
backlog 7834950b 115p
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251013152234.842065-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Add a new sysctl to control how often a queue reselection
can happen even if a flow has a persistent queue of skbs
in a Qdisc or NIC queue.
A value of zero means the feature is disabled.
Default is 1000 (1 second).
This sysctl is used in the following patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251013152234.842065-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
15 years after Tom Herbert added skb->ooo_okay, only TCP transport
benefits from it.
We can support other transports directly from skb_set_owner_w().
If no other TX packet for this socket is in a host queue (qdisc, NIC queue)
there is no risk of self-inflicted reordering, we can set skb->ooo_okay.
This allows netdev_pick_tx() to choose a TX queue based on XPS settings,
instead of reusing the queue chosen at the time the first packet was sent
for connected sockets.
Tested:
500 concurrent UDP_RR connected UDP flows, host with 32 TX queues,
512 cpus, XPS setup.
super_netperf 500 -t UDP_RR -H <host> -l 1000 -- -r 100,100 -Nn &
This patch saves between 10% and 20% of cycles, depending on how
process scheduler migrates threads among cpus.
Using following bpftrace script, we can see the effect on Qdisc/NIC tx queues
being better used (less cache line misses).
bpftrace -e '
k:__dev_queue_xmit { @start[cpu] = nsecs; }
kr:__dev_queue_xmit {
if (@start[cpu]) {
$delay = nsecs - @start[cpu];
delete(@start[cpu]);
@__dev_queue_xmit_ns = hist($delay);
}
}
END { clear(@start); }'
Before:
@__dev_queue_xmit_ns:
[128, 256) 6 | |
[256, 512) 116283 | |
[512, 1K) 1888205 |@@@@@@@@@@@ |
[1K, 2K) 8106167 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[2K, 4K) 8699293 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[4K, 8K) 2600676 |@@@@@@@@@@@@@@@ |
[8K, 16K) 721688 |@@@@ |
[16K, 32K) 122995 | |
[32K, 64K) 10639 | |
[64K, 128K) 119 | |
[128K, 256K) 1 | |
After:
@__dev_queue_xmit_ns:
[128, 256) 3 | |
[256, 512) 651112 |@@ |
[512, 1K) 8109938 |@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[1K, 2K) 16081031 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[2K, 4K) 2411692 |@@@@@@@ |
[4K, 8K) 98994 | |
[8K, 16K) 1536 | |
[16K, 32K) 587 | |
[32K, 64K) 2 | |
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251013152234.842065-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
