GCC seems to incorrectly fail to evaluate skb_ext_total_length() at
compile time under certain conditions.
The issue even occurs if all values in skb_ext_type_len[] are "0",
ruling out the possibility of an actual overflow.
As the patch has been in mainline since v6.6 without triggering the
problem it seems to be a very uncommon occurrence.
As the issue only occurs when -fno-tree-loop-im is specified as part of
CFLAGS_GCOV, disable the BUILD_BUG_ON() only when building with coverage
reporting enabled.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312171924.4FozI5FG-lkp@intel.com/
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/lkml/487cfd35-fe68-416f-9bfd-6bb417f98304@app.fastmail.com/
Fixes: 5d21d0a65b ("net: generalize calculation of skb extensions length")
Cc: <stable@vger.kernel.org>
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20231218-net-skbuff-build-bug-v1-1-eefc2fb0a7d3@weissschuh.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
In order to address the issues encountered with commit 1effe8ca4e
("skbuff: fix coalescing for page_pool fragment recycling"), the
combination of the following condition was excluded from skb coalescing:
from->pp_recycle = 1
from->cloned = 1
to->pp_recycle = 1
However, with page pool environments, the aforementioned combination can
be quite common(ex. NetworkMananger may lead to the additional
packet_type being registered, thus the cloning). In scenarios with a
higher number of small packets, it can significantly affect the success
rate of coalescing. For example, considering packets of 256 bytes size,
our comparison of coalescing success rate is as follows:
Without page pool: 70%
With page pool: 13%
Consequently, this has an impact on performance:
Without page pool: 2.57 Gbits/sec
With page pool: 2.26 Gbits/sec
Therefore, it seems worthwhile to optimize this scenario and enable
coalescing of this particular combination. To achieve this, we need to
ensure the correct increment of the "from" SKB page's page pool
reference count (pp_ref_count).
Following this optimization, the success rate of coalescing measured in
our environment has improved as follows:
With page pool: 60%
This success rate is approaching the rate achieved without using page
pool, and the performance has also been improved:
With page pool: 2.52 Gbits/sec
Below is the performance comparison for small packets before and after
this optimization. We observe no impact to packets larger than 4K.
packet size before after improved
(bytes) (Gbits/sec) (Gbits/sec)
128 1.19 1.27 7.13%
256 2.26 2.52 11.75%
512 4.13 4.81 16.50%
1024 6.17 6.73 9.05%
2048 14.54 15.47 6.45%
4096 25.44 27.87 9.52%
Signed-off-by: Liang Chen <liangchen.linux@gmail.com>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Wrap code for checking if a page is a page_pool page into a
function for better readability and ease of reuse.
Signed-off-by: Liang Chen <liangchen.linux@gmail.com>
Reviewed-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Mina Almasry <almarsymina@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Core & protocols
----------------
- Support usec resolution of TCP timestamps, enabled selectively by
a route attribute.
- Defer regular TCP ACK while processing socket backlog, try to send
a cumulative ACK at the end. Increase single TCP flow performance
on a 200Gbit NIC by 20% (100Gbit -> 120Gbit).
- The Fair Queuing (FQ) packet scheduler:
- add built-in 3 band prio / WRR scheduling
- support bypass if the qdisc is mostly idle (5% speed up for TCP RR)
- improve inactive flow reporting
- optimize the layout of structures for better cache locality
- Support TCP Authentication Option (RFC 5925, TCP-AO), a more modern
replacement for the old MD5 option.
- Add more retransmission timeout (RTO) related statistics to TCP_INFO.
- Support sending fragmented skbs over vsock sockets.
- Make sure we send SIGPIPE for vsock sockets if socket was shutdown().
- Add sysctl for ignoring lower limit on lifetime in Router
Advertisement PIO, based on an in-progress IETF draft.
- Add sysctl to control activation of TCP ping-pong mode.
- Add sysctl to make connection timeout in MPTCP configurable.
- Support rcvlowat and notsent_lowat on MPTCP sockets, to help apps
limit the number of wakeups.
- Support netlink GET for MDB (multicast forwarding), allowing user
space to request a single MDB entry instead of dumping the entire
table.
- Support selective FDB flushing in the VXLAN tunnel driver.
- Allow limiting learned FDB entries in bridges, prevent OOM attacks.
- Allow controlling via configfs netconsole targets which were created
via the kernel cmdline at boot, rather than via configfs at runtime.
- Support multiple PTP timestamp event queue readers with different
filters.
- MCTP over I3C.
BPF
---
- Add new veth-like netdevice where BPF program defines the logic
of the xmit routine. It can operate in L3 and L2 mode.
- Support exceptions - allow asserting conditions which should
never be true but are hard for the verifier to infer.
With some extra flexibility around handling of the exit / failure.
https://lwn.net/Articles/938435/
- Add support for local per-cpu kptr, allow allocating and storing
per-cpu objects in maps. Access to those objects operates on
the value for the current CPU. This allows to deprecate local
one-off implementations of per-CPU storage like
BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE maps.
- Extend cgroup BPF sockaddr hooks for UNIX sockets. The use case is
for systemd to re-implement the LogNamespace feature which allows
running multiple instances of systemd-journald to process the logs
of different services.
- Enable open-coded task_vma iteration, after maple tree conversion
made it hard to directly walk VMAs in tracing programs.
- Add open-coded task, css_task and css iterator support.
One of the use cases is customizable OOM victim selection via BPF.
- Allow source address selection with bpf_*_fib_lookup().
- Add ability to pin BPF timer to the current CPU.
- Prevent creation of infinite loops by combining tail calls and
fentry/fexit programs.
- Add missed stats for kprobes to retrieve the number of missed kprobe
executions and subsequent executions of BPF programs.
- Inherit system settings for CPU security mitigations.
- Add BPF v4 CPU instruction support for arm32 and s390x.
Changes to common code
----------------------
- overflow: add DEFINE_FLEX() for on-stack definition of structs
with flexible array members.
- Process doc update with more guidance for reviewers.
Driver API
----------
- Simplify locking in WiFi (cfg80211 and mac80211 layers), use wiphy
mutex in most places and remove a lot of smaller locks.
- Create a common DPLL configuration API. Allow configuring
and querying state of PLL circuits used for clock syntonization,
in network time distribution.
- Unify fragmented and full page allocation APIs in page pool code.
Let drivers be ignorant of PAGE_SIZE.
- Rework PHY state machine to avoid races with calls to phy_stop().
- Notify DSA drivers of MAC address changes on user ports, improve
correctness of offloads which depend on matching port MAC addresses.
- Allow antenna control on injected WiFi frames.
- Reduce the number of variants of napi_schedule().
- Simplify error handling when composing devlink health messages.
Misc
----
- A lot of KCSAN data race "fixes", from Eric.
- A lot of __counted_by() annotations, from Kees.
- A lot of strncpy -> strscpy and printf format fixes.
- Replace master/slave terminology with conduit/user in DSA drivers.
- Handful of KUnit tests for netdev and WiFi core.
Removed
-------
- AppleTalk COPS.
- AppleTalk ipddp.
- TI AR7 CPMAC Ethernet driver.
Drivers
-------
- Ethernet high-speed NICs:
- Intel (100G, ice, idpf):
- add a driver for the Intel E2000 IPUs
- make CRC/FCS stripping configurable
- cross-timestamping for E823 devices
- basic support for E830 devices
- use aux-bus for managing client drivers
- i40e: report firmware versions via devlink
- nVidia/Mellanox:
- support 4-port NICs
- increase max number of channels to 256
- optimize / parallelize SF creation flow
- Broadcom (bnxt):
- enhance NIC temperature reporting
- support PAM4 speeds and lane configuration
- Marvell OcteonTX2:
- PTP pulse-per-second output support
- enable hardware timestamping for VFs
- Solarflare/AMD:
- conntrack NAT offload and offload for tunnels
- Wangxun (ngbe/txgbe):
- expose HW statistics
- Pensando/AMD:
- support PCI level reset
- narrow down the condition under which skbs are linearized
- Netronome/Corigine (nfp):
- support CHACHA20-POLY1305 crypto in IPsec offload
- Ethernet NICs embedded, slower, virtual:
- Synopsys (stmmac):
- add Loongson-1 SoC support
- enable use of HW queues with no offload capabilities
- enable PPS input support on all 5 channels
- increase TX coalesce timer to 5ms
- RealTek USB (r8152): improve efficiency of Rx by using GRO frags
- xen: support SW packet timestamping
- add drivers for implementations based on TI's PRUSS (AM64x EVM)
- nVidia/Mellanox Ethernet datacenter switches:
- avoid poor HW resource use on Spectrum-4 by better block selection
for IPv6 multicast forwarding and ordering of blocks in ACL region
- Ethernet embedded switches:
- Microchip:
- support configuring the drive strength for EMI compliance
- ksz9477: partial ACL support
- ksz9477: HSR offload
- ksz9477: Wake on LAN
- Realtek:
- rtl8366rb: respect device tree config of the CPU port
- Ethernet PHYs:
- support Broadcom BCM5221 PHYs
- TI dp83867: support hardware LED blinking
- CAN:
- add support for Linux-PHY based CAN transceivers
- at91_can: clean up and use rx-offload helpers
- WiFi:
- MediaTek (mt76):
- new sub-driver for mt7925 USB/PCIe devices
- HW wireless <> Ethernet bridging in MT7988 chips
- mt7603/mt7628 stability improvements
- Qualcomm (ath12k):
- WCN7850:
- enable 320 MHz channels in 6 GHz band
- hardware rfkill support
- enable IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS
to make scan faster
- read board data variant name from SMBIOS
- QCN9274: mesh support
- RealTek (rtw89):
- TDMA-based multi-channel concurrency (MCC)
- Silicon Labs (wfx):
- Remain-On-Channel (ROC) support
- Bluetooth:
- ISO: many improvements for broadcast support
- mark BCM4378/BCM4387 as BROKEN_LE_CODED
- add support for QCA2066
- btmtksdio: enable Bluetooth wakeup from suspend
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----
iQIzBAABCAAdFiEE6jPA+I1ugmIBA4hXMUZtbf5SIrsFAmU8XsYACgkQMUZtbf5S
Irv19RAAnud/24OOF5XMEJkIcYlnfqximh4XO6PujRSYkSkOUJdZTF6iJPgf3pSP
YpwoHYbYKHYfeOf8+3bTNESiQNSnoVmvmvwiS6/7lZ3behHUrGLQzW9Htc3EZyWH
2h6QkDZ5OOjfg0bwYSfp3vXkmMH2k8WE9Y0NvCkhcohqZi13Rmp14RnyPmNb2d1V
yZRYDMSM133KqE6gnBr1Ct65IEvnKeGlCUN2mTGqOJgdn6DZMsyxvtt0y4rmN7Ab
41+CgPU5SfxfbYpW+Dl2HJpgfte3WrC57KC6AM0PAPJzPmQWgeB/m9mjz/apj6Bg
bhsEIo7FdvbCnQm3yWPhK2OgCAcSwLr8jfGMU+Q+W4VnL5SRRR3Rm0zjsze+kHNP
OfqJgxzl3DpvoJqVBy1h5FGcZt0XHwhksm4cTxWqIahsF+veY0ECBXbuBBQx9XTF
Y7INfI8ulg7wISJs+CJfIClYkgOibTw2u8taBS5ikbtgxNqp5D4QqODn7UefQap1
PR/IDYODF+zRgmMJLeBqSa6fij6BkfOEDiOWak5kggBoZdtbtmeKI6tzze06CNdW
lWv1WEhRufxnwK+IuWsEkjhiMbs2WGLvkJ5JbgQV9BfqHfIfiqBCrcWtT/WbQnGt
lmU46CXh1t/FZEqbmK9h+8vsIIfrcDl6jb5npEiKPRG00vDKRTM=
=46nS
-----END PGP SIGNATURE-----
Merge tag 'net-next-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core & protocols:
- Support usec resolution of TCP timestamps, enabled selectively by a
route attribute.
- Defer regular TCP ACK while processing socket backlog, try to send
a cumulative ACK at the end. Increase single TCP flow performance
on a 200Gbit NIC by 20% (100Gbit -> 120Gbit).
- The Fair Queuing (FQ) packet scheduler:
- add built-in 3 band prio / WRR scheduling
- support bypass if the qdisc is mostly idle (5% speed up for TCP RR)
- improve inactive flow reporting
- optimize the layout of structures for better cache locality
- Support TCP Authentication Option (RFC 5925, TCP-AO), a more modern
replacement for the old MD5 option.
- Add more retransmission timeout (RTO) related statistics to
TCP_INFO.
- Support sending fragmented skbs over vsock sockets.
- Make sure we send SIGPIPE for vsock sockets if socket was
shutdown().
- Add sysctl for ignoring lower limit on lifetime in Router
Advertisement PIO, based on an in-progress IETF draft.
- Add sysctl to control activation of TCP ping-pong mode.
- Add sysctl to make connection timeout in MPTCP configurable.
- Support rcvlowat and notsent_lowat on MPTCP sockets, to help apps
limit the number of wakeups.
- Support netlink GET for MDB (multicast forwarding), allowing user
space to request a single MDB entry instead of dumping the entire
table.
- Support selective FDB flushing in the VXLAN tunnel driver.
- Allow limiting learned FDB entries in bridges, prevent OOM attacks.
- Allow controlling via configfs netconsole targets which were
created via the kernel cmdline at boot, rather than via configfs at
runtime.
- Support multiple PTP timestamp event queue readers with different
filters.
- MCTP over I3C.
BPF:
- Add new veth-like netdevice where BPF program defines the logic of
the xmit routine. It can operate in L3 and L2 mode.
- Support exceptions - allow asserting conditions which should never
be true but are hard for the verifier to infer. With some extra
flexibility around handling of the exit / failure:
https://lwn.net/Articles/938435/
- Add support for local per-cpu kptr, allow allocating and storing
per-cpu objects in maps. Access to those objects operates on the
value for the current CPU.
This allows to deprecate local one-off implementations of per-CPU
storage like BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE maps.
- Extend cgroup BPF sockaddr hooks for UNIX sockets. The use case is
for systemd to re-implement the LogNamespace feature which allows
running multiple instances of systemd-journald to process the logs
of different services.
- Enable open-coded task_vma iteration, after maple tree conversion
made it hard to directly walk VMAs in tracing programs.
- Add open-coded task, css_task and css iterator support. One of the
use cases is customizable OOM victim selection via BPF.
- Allow source address selection with bpf_*_fib_lookup().
- Add ability to pin BPF timer to the current CPU.
- Prevent creation of infinite loops by combining tail calls and
fentry/fexit programs.
- Add missed stats for kprobes to retrieve the number of missed
kprobe executions and subsequent executions of BPF programs.
- Inherit system settings for CPU security mitigations.
- Add BPF v4 CPU instruction support for arm32 and s390x.
Changes to common code:
- overflow: add DEFINE_FLEX() for on-stack definition of structs with
flexible array members.
- Process doc update with more guidance for reviewers.
Driver API:
- Simplify locking in WiFi (cfg80211 and mac80211 layers), use wiphy
mutex in most places and remove a lot of smaller locks.
- Create a common DPLL configuration API. Allow configuring and
querying state of PLL circuits used for clock syntonization, in
network time distribution.
- Unify fragmented and full page allocation APIs in page pool code.
Let drivers be ignorant of PAGE_SIZE.
- Rework PHY state machine to avoid races with calls to phy_stop().
- Notify DSA drivers of MAC address changes on user ports, improve
correctness of offloads which depend on matching port MAC
addresses.
- Allow antenna control on injected WiFi frames.
- Reduce the number of variants of napi_schedule().
- Simplify error handling when composing devlink health messages.
Misc:
- A lot of KCSAN data race "fixes", from Eric.
- A lot of __counted_by() annotations, from Kees.
- A lot of strncpy -> strscpy and printf format fixes.
- Replace master/slave terminology with conduit/user in DSA drivers.
- Handful of KUnit tests for netdev and WiFi core.
Removed:
- AppleTalk COPS.
- AppleTalk ipddp.
- TI AR7 CPMAC Ethernet driver.
Drivers:
- Ethernet high-speed NICs:
- Intel (100G, ice, idpf):
- add a driver for the Intel E2000 IPUs
- make CRC/FCS stripping configurable
- cross-timestamping for E823 devices
- basic support for E830 devices
- use aux-bus for managing client drivers
- i40e: report firmware versions via devlink
- nVidia/Mellanox:
- support 4-port NICs
- increase max number of channels to 256
- optimize / parallelize SF creation flow
- Broadcom (bnxt):
- enhance NIC temperature reporting
- support PAM4 speeds and lane configuration
- Marvell OcteonTX2:
- PTP pulse-per-second output support
- enable hardware timestamping for VFs
- Solarflare/AMD:
- conntrack NAT offload and offload for tunnels
- Wangxun (ngbe/txgbe):
- expose HW statistics
- Pensando/AMD:
- support PCI level reset
- narrow down the condition under which skbs are linearized
- Netronome/Corigine (nfp):
- support CHACHA20-POLY1305 crypto in IPsec offload
- Ethernet NICs embedded, slower, virtual:
- Synopsys (stmmac):
- add Loongson-1 SoC support
- enable use of HW queues with no offload capabilities
- enable PPS input support on all 5 channels
- increase TX coalesce timer to 5ms
- RealTek USB (r8152): improve efficiency of Rx by using GRO frags
- xen: support SW packet timestamping
- add drivers for implementations based on TI's PRUSS (AM64x EVM)
- nVidia/Mellanox Ethernet datacenter switches:
- avoid poor HW resource use on Spectrum-4 by better block
selection for IPv6 multicast forwarding and ordering of blocks
in ACL region
- Ethernet embedded switches:
- Microchip:
- support configuring the drive strength for EMI compliance
- ksz9477: partial ACL support
- ksz9477: HSR offload
- ksz9477: Wake on LAN
- Realtek:
- rtl8366rb: respect device tree config of the CPU port
- Ethernet PHYs:
- support Broadcom BCM5221 PHYs
- TI dp83867: support hardware LED blinking
- CAN:
- add support for Linux-PHY based CAN transceivers
- at91_can: clean up and use rx-offload helpers
- WiFi:
- MediaTek (mt76):
- new sub-driver for mt7925 USB/PCIe devices
- HW wireless <> Ethernet bridging in MT7988 chips
- mt7603/mt7628 stability improvements
- Qualcomm (ath12k):
- WCN7850:
- enable 320 MHz channels in 6 GHz band
- hardware rfkill support
- enable IEEE80211_HW_SINGLE_SCAN_ON_ALL_BANDS to
make scan faster
- read board data variant name from SMBIOS
- QCN9274: mesh support
- RealTek (rtw89):
- TDMA-based multi-channel concurrency (MCC)
- Silicon Labs (wfx):
- Remain-On-Channel (ROC) support
- Bluetooth:
- ISO: many improvements for broadcast support
- mark BCM4378/BCM4387 as BROKEN_LE_CODED
- add support for QCA2066
- btmtksdio: enable Bluetooth wakeup from suspend"
* tag 'net-next-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1816 commits)
net: pcs: xpcs: Add 2500BASE-X case in get state for XPCS drivers
net: bpf: Use sockopt_lock_sock() in ip_sock_set_tos()
net: mana: Use xdp_set_features_flag instead of direct assignment
vxlan: Cleanup IFLA_VXLAN_PORT_RANGE entry in vxlan_get_size()
iavf: delete the iavf client interface
iavf: add a common function for undoing the interrupt scheme
iavf: use unregister_netdev
iavf: rely on netdev's own registered state
iavf: fix the waiting time for initial reset
iavf: in iavf_down, don't queue watchdog_task if comms failed
iavf: simplify mutex_trylock+sleep loops
iavf: fix comments about old bit locks
doc/netlink: Update schema to support cmd-cnt-name and cmd-max-name
tools: ynl: introduce option to process unknown attributes or types
ipvlan: properly track tx_errors
netdevsim: Block until all devices are released
nfp: using napi_build_skb() to replace build_skb()
net: dsa: microchip: ksz9477: Fix spelling mistake "Enery" -> "Energy"
net: dsa: microchip: Ensure Stable PME Pin State for Wake-on-LAN
net: dsa: microchip: Refactor switch shutdown routine for WoL preparation
...
PP_FLAG_PAGE_FRAG is not really needed after pp_frag_count
handling is unified and page_pool_alloc_frag() is supported
in 32-bit arch with 64-bit DMA, so remove it.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
CC: Lorenzo Bianconi <lorenzo@kernel.org>
CC: Alexander Duyck <alexander.duyck@gmail.com>
CC: Liang Chen <liangchen.linux@gmail.com>
CC: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://lore.kernel.org/r/20231020095952.11055-3-linyunsheng@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Assume that caller's 'to' offset really represents an upper boundary for
the pattern search, so patterns extending past this offset are to be
rejected.
The old behaviour also was kind of inconsistent when it comes to
fragmentation (or otherwise non-linear skbs): If the pattern started in
between 'to' and 'from' offsets but extended to the next fragment, it
was not found if 'to' offset was still within the current fragment.
Test the new behaviour in a kselftest using iptables' string match.
Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org>
Fixes: f72b948dcb ("[NET]: skb_find_text ignores to argument")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Reviewed-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move csum_and_copy_from_iter_full() out of line and then merge
csum_and_copy_from_iter() into its only caller.
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/20230925120309.1731676-12-dhowells@redhat.com
cc: Alexander Viro <viro@zeniv.linux.org.uk>
cc: Jens Axboe <axboe@kernel.dk>
cc: Christoph Hellwig <hch@lst.de>
cc: Christian Brauner <christian@brauner.io>
cc: Matthew Wilcox <willy@infradead.org>
cc: Linus Torvalds <torvalds@linux-foundation.org>
cc: David Laight <David.Laight@ACULAB.COM>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-block@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
cc: netdev@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Fold csum_and_memcpy() in to its callers.
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/20230925120309.1731676-11-dhowells@redhat.com
cc: Alexander Viro <viro@zeniv.linux.org.uk>
cc: Jens Axboe <axboe@kernel.dk>
cc: Christoph Hellwig <hch@lst.de>
cc: Christian Brauner <christian@brauner.io>
cc: Matthew Wilcox <willy@infradead.org>
cc: Linus Torvalds <torvalds@linux-foundation.org>
cc: David Laight <David.Laight@ACULAB.COM>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-block@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
cc: netdev@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Move csum_and_copy_to/from_iter() to net code now that the iteration
framework can be #included.
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/20230925120309.1731676-10-dhowells@redhat.com
cc: Alexander Viro <viro@zeniv.linux.org.uk>
cc: Jens Axboe <axboe@kernel.dk>
cc: Christoph Hellwig <hch@lst.de>
cc: Christian Brauner <christian@brauner.io>
cc: Matthew Wilcox <willy@infradead.org>
cc: Linus Torvalds <torvalds@linux-foundation.org>
cc: David Laight <David.Laight@ACULAB.COM>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-block@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
cc: netdev@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Exit early if the list is empty.
Some applications using TCP zerocopy are calling
recvmsg( ... MSG_ERRQUEUE) and hit this case quite often,
probably because busy polling only deals with sk_receive_queue.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231005114504.642589-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
1) Exit early if the list is empty.
2) splice the list into a local list,
so that we block hard irqs only once.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20231003181920.3280453-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
It can be time consuming to track driver bugs, that might be detected
too late from this confusing warning in skb_try_coalesce()
WARN_ON_ONCE(delta < len);
Add sanity check in skb_add_rx_frag() and skb_coalesce_rx_frag()
to better track bug origin for CONFIG_DEBUG_NET=y builds.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Blamed commit changed:
ptr = kmalloc(size);
if (ptr)
size = ksize(ptr);
to:
size = kmalloc_size_roundup(size);
ptr = kmalloc(size);
This allowed various crash as reported by syzbot [1]
and Kyle Zeng.
Problem is that if @size is bigger than 0x80000001,
kmalloc_size_roundup(size) returns 2^32.
kmalloc_reserve() uses a 32bit variable (obj_size),
so 2^32 is truncated to 0.
kmalloc(0) returns ZERO_SIZE_PTR which is not handled by
skb allocations.
Following trace can be triggered if a netdev->mtu is set
close to 0x7fffffff
We might in the future limit netdev->mtu to more sensible
limit (like KMALLOC_MAX_SIZE).
This patch is based on a syzbot report, and also a report
and tentative fix from Kyle Zeng.
[1]
BUG: KASAN: user-memory-access in __build_skb_around net/core/skbuff.c:294 [inline]
BUG: KASAN: user-memory-access in __alloc_skb+0x3c4/0x6e8 net/core/skbuff.c:527
Write of size 32 at addr 00000000fffffd10 by task syz-executor.4/22554
CPU: 1 PID: 22554 Comm: syz-executor.4 Not tainted 6.1.39-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/03/2023
Call trace:
dump_backtrace+0x1c8/0x1f4 arch/arm64/kernel/stacktrace.c:279
show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:286
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0x120/0x1a0 lib/dump_stack.c:106
print_report+0xe4/0x4b4 mm/kasan/report.c:398
kasan_report+0x150/0x1ac mm/kasan/report.c:495
kasan_check_range+0x264/0x2a4 mm/kasan/generic.c:189
memset+0x40/0x70 mm/kasan/shadow.c:44
__build_skb_around net/core/skbuff.c:294 [inline]
__alloc_skb+0x3c4/0x6e8 net/core/skbuff.c:527
alloc_skb include/linux/skbuff.h:1316 [inline]
igmpv3_newpack+0x104/0x1088 net/ipv4/igmp.c:359
add_grec+0x81c/0x1124 net/ipv4/igmp.c:534
igmpv3_send_cr net/ipv4/igmp.c:667 [inline]
igmp_ifc_timer_expire+0x1b0/0x1008 net/ipv4/igmp.c:810
call_timer_fn+0x1c0/0x9f0 kernel/time/timer.c:1474
expire_timers kernel/time/timer.c:1519 [inline]
__run_timers+0x54c/0x710 kernel/time/timer.c:1790
run_timer_softirq+0x28/0x4c kernel/time/timer.c:1803
_stext+0x380/0xfbc
____do_softirq+0x14/0x20 arch/arm64/kernel/irq.c:79
call_on_irq_stack+0x24/0x4c arch/arm64/kernel/entry.S:891
do_softirq_own_stack+0x20/0x2c arch/arm64/kernel/irq.c:84
invoke_softirq kernel/softirq.c:437 [inline]
__irq_exit_rcu+0x1c0/0x4cc kernel/softirq.c:683
irq_exit_rcu+0x14/0x78 kernel/softirq.c:695
el0_interrupt+0x7c/0x2e0 arch/arm64/kernel/entry-common.c:717
__el0_irq_handler_common+0x18/0x24 arch/arm64/kernel/entry-common.c:724
el0t_64_irq_handler+0x10/0x1c arch/arm64/kernel/entry-common.c:729
el0t_64_irq+0x1a0/0x1a4 arch/arm64/kernel/entry.S:584
Fixes: 12d6c1d3a2 ("skbuff: Proactively round up to kmalloc bucket size")
Reported-by: syzbot <syzkaller@googlegroups.com>
Reported-by: Kyle Zeng <zengyhkyle@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit bf5c25d608 ("skbuff: in skb_segment, call zerocopy functions
once per nskb") added the call to zero copy functions in skb_segment().
The change introduced a bug in skb_segment() because skb_orphan_frags()
may possibly change the number of fragments or allocate new fragments
altogether leaving nrfrags and frag to point to the old values. This can
cause a panic with stacktrace like the one below.
[ 193.894380] BUG: kernel NULL pointer dereference, address: 00000000000000bc
[ 193.895273] CPU: 13 PID: 18164 Comm: vh-net-17428 Kdump: loaded Tainted: G O 5.15.123+ #26
[ 193.903919] RIP: 0010:skb_segment+0xb0e/0x12f0
[ 194.021892] Call Trace:
[ 194.027422] <TASK>
[ 194.072861] tcp_gso_segment+0x107/0x540
[ 194.082031] inet_gso_segment+0x15c/0x3d0
[ 194.090783] skb_mac_gso_segment+0x9f/0x110
[ 194.095016] __skb_gso_segment+0xc1/0x190
[ 194.103131] netem_enqueue+0x290/0xb10 [sch_netem]
[ 194.107071] dev_qdisc_enqueue+0x16/0x70
[ 194.110884] __dev_queue_xmit+0x63b/0xb30
[ 194.121670] bond_start_xmit+0x159/0x380 [bonding]
[ 194.128506] dev_hard_start_xmit+0xc3/0x1e0
[ 194.131787] __dev_queue_xmit+0x8a0/0xb30
[ 194.138225] macvlan_start_xmit+0x4f/0x100 [macvlan]
[ 194.141477] dev_hard_start_xmit+0xc3/0x1e0
[ 194.144622] sch_direct_xmit+0xe3/0x280
[ 194.147748] __dev_queue_xmit+0x54a/0xb30
[ 194.154131] tap_get_user+0x2a8/0x9c0 [tap]
[ 194.157358] tap_sendmsg+0x52/0x8e0 [tap]
[ 194.167049] handle_tx_zerocopy+0x14e/0x4c0 [vhost_net]
[ 194.173631] handle_tx+0xcd/0xe0 [vhost_net]
[ 194.176959] vhost_worker+0x76/0xb0 [vhost]
[ 194.183667] kthread+0x118/0x140
[ 194.190358] ret_from_fork+0x1f/0x30
[ 194.193670] </TASK>
In this case calling skb_orphan_frags() updated nr_frags leaving nrfrags
local variable in skb_segment() stale. This resulted in the code hitting
i >= nrfrags prematurely and trying to move to next frag_skb using
list_skb pointer, which was NULL, and caused kernel panic. Move the call
to zero copy functions before using frags and nr_frags.
Fixes: bf5c25d608 ("skbuff: in skb_segment, call zerocopy functions once per nskb")
Signed-off-by: Mohamed Khalfella <mkhalfella@purestorage.com>
Reported-by: Amit Goyal <agoyal@purestorage.com>
Cc: stable@vger.kernel.org
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
sk->sk_tsflags can be read locklessly, add corresponding annotations.
Fixes: b9f40e21ef ("net-timestamp: move timestamp flags out of sk_flags")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove the necessity to modify skb_ext_total_length() when new extension
types are added.
Also reduces the line count a bit.
With optimizations enabled the function is folded down to the same
constant value as before during compilation.
This has been validated on x86 with GCC 6.5.0 and 13.2.1.
Also a similar construct has been validated on godbolt.org with GCC 5.1.
In any case the compiler has to be able to evaluate the construct at
compile-time for the BUILD_BUG_ON() in skb_extensions_init().
Even if not evaluated at compile-time this function would only ever
be executed once at run-time, so the overhead would be very minuscule.
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20230823-skb_ext-simplify-v2-1-66e26cd66860@weissschuh.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Setting IP_RECVERR and IPV6_RECVERR options to zero currently
purges the socket error queue, which was probably not expected
for zerocopy and tx_timestamp users.
I discovered this issue while preparing commit 6b5f43ea08
("inet: move inet->recverr to inet->inet_flags"), I presume this
change does not need to be backported to stable kernels.
Add skb_errqueue_purge() helper to purge error messages only.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb_queue_purge() and __skb_queue_purge() become wrappers
around the new generic functions.
New SKB_DROP_REASON_QUEUE_PURGE drop reason is added,
but users can start adding more specific reasons.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since v6.5-rc1 MM-tree is merged and contains a new flag SLAB_NO_MERGE
in commit d0bf7d5759 ("mm/slab: introduce kmem_cache flag SLAB_NO_MERGE")
now is the time to use this flag for networking as proposed
earlier see link.
The SKB (sk_buff) kmem_cache slab is critical for network performance.
Network stack uses kmem_cache_{alloc,free}_bulk APIs to gain
performance by amortising the alloc/free cost.
For the bulk API to perform efficiently the slub fragmentation need to
be low. Especially for the SLUB allocator, the efficiency of bulk free
API depend on objects belonging to the same slab (page).
When running different network performance microbenchmarks, I started
to notice that performance was reduced (slightly) when machines had
longer uptimes. I believe the cause was 'skbuff_head_cache' got
aliased/merged into the general slub for 256 bytes sized objects (with
my kernel config, without CONFIG_HARDENED_USERCOPY).
For SKB kmem_cache network stack have other various reasons for
not merging, but it varies depending on kernel config (e.g.
CONFIG_HARDENED_USERCOPY). We want to explicitly set SLAB_NO_MERGE
for this kmem_cache to get most out of kmem_cache_{alloc,free}_bulk APIs.
When CONFIG_SLUB_TINY is configured the bulk APIs are essentially
disabled. Thus, for this case drop the SLAB_NO_MERGE flag.
Link: https://lore.kernel.org/all/167396280045.539803.7540459812377220500.stgit@firesoul/
Signed-off-by: Jesper Dangaard Brouer <hawk@kernel.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/r/169211265663.1491038.8580163757548985946.stgit@firesoul
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit 8c48eea3ad ("page_pool: allow caching from safely localized
NAPI") allowed direct recycling of skb pages to their PP for some cases,
but unfortunately missed a couple of other majors.
For example, %XDP_DROP in skb mode. The netstack just calls kfree_skb(),
which unconditionally passes `false` as @napi_safe. Thus, all pages go
through ptr_ring and locks, although most of time we're actually inside
the NAPI polling this PP is linked with, so that it would be perfectly
safe to recycle pages directly.
Let's address such. If @napi_safe is true, we're fine, don't change
anything for this path. But if it's false, check whether we are in the
softirq context. It will most likely be so and then if ->list_owner
is our current CPU, we're good to use direct recycling, even though
@napi_safe is false -- concurrent access is excluded. in_softirq()
protection is needed mostly due to we can hit this place in the
process context (not the hardirq though).
For the mentioned xdp-drop-skb-mode case, the improvement I got is
3-4% in Mpps. As for page_pool stats, recycle_ring is now 0 and
alloc_slow counter doesn't change most of time, which means the
MM layer is not even called to allocate any new pages.
Suggested-by: Jakub Kicinski <kuba@kernel.org> # in_softirq()
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-7-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently, pp->p.napi is always read, but the actual variable it gets
assigned to is read-only when @napi_safe is true. For the !napi_safe
cases, which yet is still a pack, it's an unneeded operation.
Moreover, it can lead to premature or even redundant page_pool
cacheline access. For example, when page_pool_is_last_frag() returns
false (with the recent frag improvements).
Thus, read it only when @napi_safe is true. This also allows moving
@napi inside the condition block itself. Constify it while we are
here, because why not.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-5-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently, touching <net/page_pool/types.h> triggers a rebuild of more
than half of the kernel. That's because it's included in
<linux/skbuff.h>. And each new include to page_pool/types.h adds more
[useless] data for the toolchain to process per each source file from
that pile.
In commit 6a5bcd84e8 ("page_pool: Allow drivers to hint on SKB
recycling"), Matteo included it to be able to call a couple of functions
defined there. Then, in commit 57f05bc2ab ("page_pool: keep pp info as
long as page pool owns the page") one of the calls was removed, so only
one was left. It's the call to page_pool_return_skb_page() in
napi_frag_unref(). The function is external and doesn't have any
dependencies. Having very niche page_pool_types.h included only for that
looks like an overkill.
As %PP_SIGNATURE is not local to page_pool.c (was only in the
early submissions), nothing holds this function there. Teleport
page_pool_return_skb_page() to skbuff.c, just next to the main consumer,
skb_pp_recycle(), and rename it to napi_pp_put_page(), as it doesn't
work with skbs at all and the former name tells nothing. The #if guards
here are only to not compile and have it in the vmlinux when not needed
-- both call sites are already guarded.
Now, touching page_pool_types.h only triggers rebuilding of the drivers
using it and a couple of core networking files.
Suggested-by: Jakub Kicinski <kuba@kernel.org> # make skbuff.h less heavy
Suggested-by: Alexander Duyck <alexanderduyck@fb.com> # move to skbuff.c
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-3-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Split types and pure function declarations from page_pool.h
and add them in page_page/types.h, so that C sources can
include page_pool.h and headers should generally only include
page_pool/types.h as suggested by jakub.
Rename page_pool.h to page_pool/helpers.h to have both in
one place.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230804180529.2483231-2-aleksander.lobakin@intel.com
[Jakub: change microsoft/mana, fix kdoc paths in Documentation]
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Use sendmsg() with MSG_SPLICE_PAGES rather than sendpage in
skb_send_sock(). This causes pages to be spliced from the source iterator
if possible.
This allows ->sendpage() to be replaced by something that can handle
multiple multipage folios in a single transaction.
Note that this could perhaps be improved to fill out a bvec array with all
the frags and then make a single sendmsg call, possibly sticking the header
on the front also.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
Link: https://lore.kernel.org/r/20230623225513.2732256-3-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Move declarations into include/net/gso.h and code into net/core/gso.c
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230608191738.3947077-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The "len" variable needs to be signed for the error handling to work
correctly.
Fixes: 2e910b9532 ("net: Add a function to splice pages into an skbuff for MSG_SPLICE_PAGES")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/366861a7-87c8-4bbf-9101-69dd41021d07@kili.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit 50749f2dd6 ("tcp/udp: Fix memleaks of sk and zerocopy skbs with
TX timestamp.") added a call to skb_orphan_frags_rx() to fix leaks with
zerocopy skbs. But it ended up adding a leak of its own. When
skb_orphan_frags_rx() fails, the function just returns, leaking the skb
it just cloned. Free it before returning.
This bug was discovered and resolved using Coverity Static Analysis
Security Testing (SAST) by Synopsys, Inc.
Fixes: 50749f2dd6 ("tcp/udp: Fix memleaks of sk and zerocopy skbs with TX timestamp.")
Signed-off-by: Pratyush Yadav <ptyadav@amazon.de>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20230522153020.32422-1-ptyadav@amazon.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add a function to handle MSG_SPLICE_PAGES being passed internally to
sendmsg(). Pages are spliced into the given socket buffer if possible and
copied in if not (e.g. they're slab pages or have a zero refcount).
Signed-off-by: David Howells <dhowells@redhat.com>
cc: David Ahern <dsahern@kernel.org>
cc: Al Viro <viro@zeniv.linux.org.uk>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Pass the maximum number of fragments into skb_append_pagefrags() rather
than using MAX_SKB_FRAGS so that it can be used from code that wants to
specify sysctl_max_skb_frags.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: David Ahern <dsahern@kernel.org>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Most users use __skb_frag_set_page()/skb_frag_off_set()/
skb_frag_size_set() to fill the page desc for a skb frag.
Introduce skb_frag_fill_page_desc() to do that.
net/bpf/test_run.c does not call skb_frag_off_set() to
set the offset, "copy_from_user(page_address(page), ...)"
and 'shinfo' being part of the 'data' kzalloced in
bpf_test_init() suggest that it is assuming offset to be
initialized as zero, so call skb_frag_fill_page_desc()
with offset being zero for this case.
Also, skb_frag_set_page() is not used anymore, so remove
it.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit c9929f0e34 ("mm/slob: remove CONFIG_SLOB") removes CONFIG_SLOB.
Now, we can also remove special handling for socket buffers with the SLOB
allocator. The code with HAVE_SKB_SMALL_HEAD_CACHE=1 is now the default
behavior for all allocators.
Remove an unnecessary distinction between SLOB and SLAB/SLUB allocator
after the SLOB allocator is gone.
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230509071207.28942-1-lukas.bulwahn@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
David Ahern reported crashes in skb_copy_ubufs() caused by TCP tx zerocopy
using hugepages, and skb length bigger than ~68 KB.
skb_copy_ubufs() assumed it could copy all payload using up to
MAX_SKB_FRAGS order-0 pages.
This assumption broke when BIG TCP was able to put up to 512 KB per skb.
We did not hit this bug at Google because we use CONFIG_MAX_SKB_FRAGS=45
and limit gso_max_size to 180000.
A solution is to use higher order pages if needed.
v2: add missing __GFP_COMP, or we leak memory.
Fixes: 7c4e983c4f ("net: allow gso_max_size to exceed 65536")
Reported-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/netdev/c70000f6-baa4-4a05-46d0-4b3e0dc1ccc8@gmail.com/T/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Xin Long <lucien.xin@gmail.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Coco Li <lixiaoyan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
syzkaller reported [0] memory leaks of an UDP socket and ZEROCOPY
skbs. We can reproduce the problem with these sequences:
sk = socket(AF_INET, SOCK_DGRAM, 0)
sk.setsockopt(SOL_SOCKET, SO_TIMESTAMPING, SOF_TIMESTAMPING_TX_SOFTWARE)
sk.setsockopt(SOL_SOCKET, SO_ZEROCOPY, 1)
sk.sendto(b'', MSG_ZEROCOPY, ('127.0.0.1', 53))
sk.close()
sendmsg() calls msg_zerocopy_alloc(), which allocates a skb, sets
skb->cb->ubuf.refcnt to 1, and calls sock_hold(). Here, struct
ubuf_info_msgzc indirectly holds a refcnt of the socket. When the
skb is sent, __skb_tstamp_tx() clones it and puts the clone into
the socket's error queue with the TX timestamp.
When the original skb is received locally, skb_copy_ubufs() calls
skb_unclone(), and pskb_expand_head() increments skb->cb->ubuf.refcnt.
This additional count is decremented while freeing the skb, but struct
ubuf_info_msgzc still has a refcnt, so __msg_zerocopy_callback() is
not called.
The last refcnt is not released unless we retrieve the TX timestamped
skb by recvmsg(). Since we clear the error queue in inet_sock_destruct()
after the socket's refcnt reaches 0, there is a circular dependency.
If we close() the socket holding such skbs, we never call sock_put()
and leak the count, sk, and skb.
TCP has the same problem, and commit e0c8bccd40 ("net: stream:
purge sk_error_queue in sk_stream_kill_queues()") tried to fix it
by calling skb_queue_purge() during close(). However, there is a
small chance that skb queued in a qdisc or device could be put
into the error queue after the skb_queue_purge() call.
In __skb_tstamp_tx(), the cloned skb should not have a reference
to the ubuf to remove the circular dependency, but skb_clone() does
not call skb_copy_ubufs() for zerocopy skb. So, we need to call
skb_orphan_frags_rx() for the cloned skb to call skb_copy_ubufs().
[0]:
BUG: memory leak
unreferenced object 0xffff88800c6d2d00 (size 1152):
comm "syz-executor392", pid 264, jiffies 4294785440 (age 13.044s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 cd af e8 81 00 00 00 00 ................
02 00 07 40 00 00 00 00 00 00 00 00 00 00 00 00 ...@............
backtrace:
[<0000000055636812>] sk_prot_alloc+0x64/0x2a0 net/core/sock.c:2024
[<0000000054d77b7a>] sk_alloc+0x3b/0x800 net/core/sock.c:2083
[<0000000066f3c7e0>] inet_create net/ipv4/af_inet.c:319 [inline]
[<0000000066f3c7e0>] inet_create+0x31e/0xe40 net/ipv4/af_inet.c:245
[<000000009b83af97>] __sock_create+0x2ab/0x550 net/socket.c:1515
[<00000000b9b11231>] sock_create net/socket.c:1566 [inline]
[<00000000b9b11231>] __sys_socket_create net/socket.c:1603 [inline]
[<00000000b9b11231>] __sys_socket_create net/socket.c:1588 [inline]
[<00000000b9b11231>] __sys_socket+0x138/0x250 net/socket.c:1636
[<000000004fb45142>] __do_sys_socket net/socket.c:1649 [inline]
[<000000004fb45142>] __se_sys_socket net/socket.c:1647 [inline]
[<000000004fb45142>] __x64_sys_socket+0x73/0xb0 net/socket.c:1647
[<0000000066999e0e>] do_syscall_x64 arch/x86/entry/common.c:50 [inline]
[<0000000066999e0e>] do_syscall_64+0x38/0x90 arch/x86/entry/common.c:80
[<0000000017f238c1>] entry_SYSCALL_64_after_hwframe+0x63/0xcd
BUG: memory leak
unreferenced object 0xffff888017633a00 (size 240):
comm "syz-executor392", pid 264, jiffies 4294785440 (age 13.044s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 00 2d 6d 0c 80 88 ff ff .........-m.....
backtrace:
[<000000002b1c4368>] __alloc_skb+0x229/0x320 net/core/skbuff.c:497
[<00000000143579a6>] alloc_skb include/linux/skbuff.h:1265 [inline]
[<00000000143579a6>] sock_omalloc+0xaa/0x190 net/core/sock.c:2596
[<00000000be626478>] msg_zerocopy_alloc net/core/skbuff.c:1294 [inline]
[<00000000be626478>] msg_zerocopy_realloc+0x1ce/0x7f0 net/core/skbuff.c:1370
[<00000000cbfc9870>] __ip_append_data+0x2adf/0x3b30 net/ipv4/ip_output.c:1037
[<0000000089869146>] ip_make_skb+0x26c/0x2e0 net/ipv4/ip_output.c:1652
[<00000000098015c2>] udp_sendmsg+0x1bac/0x2390 net/ipv4/udp.c:1253
[<0000000045e0e95e>] inet_sendmsg+0x10a/0x150 net/ipv4/af_inet.c:819
[<000000008d31bfde>] sock_sendmsg_nosec net/socket.c:714 [inline]
[<000000008d31bfde>] sock_sendmsg+0x141/0x190 net/socket.c:734
[<0000000021e21aa4>] __sys_sendto+0x243/0x360 net/socket.c:2117
[<00000000ac0af00c>] __do_sys_sendto net/socket.c:2129 [inline]
[<00000000ac0af00c>] __se_sys_sendto net/socket.c:2125 [inline]
[<00000000ac0af00c>] __x64_sys_sendto+0xe1/0x1c0 net/socket.c:2125
[<0000000066999e0e>] do_syscall_x64 arch/x86/entry/common.c:50 [inline]
[<0000000066999e0e>] do_syscall_64+0x38/0x90 arch/x86/entry/common.c:80
[<0000000017f238c1>] entry_SYSCALL_64_after_hwframe+0x63/0xcd
Fixes: f214f915e7 ("tcp: enable MSG_ZEROCOPY")
Fixes: b5947e5d1e ("udp: msg_zerocopy")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ocelot_xmit_get_vlan_info() calls __skb_vlan_pop() as the most
appropriate helper I could find which strips away a VLAN header.
That's all I need it to do, but __skb_vlan_pop() has more logic, which
will become incompatible with the future revert of commit 6d1ccff627
("net: reset mac header in dev_start_xmit()").
Namely, it performs a sanity check on skb_mac_header(), which will stop
being set after the above revert, so it will return an error instead of
removing the VLAN tag.
ocelot_xmit_get_vlan_info() gets called in 2 circumstances:
(1) the port is under a VLAN-aware bridge and the bridge sends
VLAN-tagged packets
(2) the port is under a VLAN-aware bridge and somebody else (an 8021q
upper) sends VLAN-tagged packets (using a VID that isn't in the
bridge vlan tables)
In case (1), there is actually no bug to defend against, because
br_dev_xmit() calls skb_reset_mac_header() and things continue to work.
However, in case (2), illustrated using the commands below, it can be
seen that our intervention is needed, since __skb_vlan_pop() complains:
$ ip link add br0 type bridge vlan_filtering 1 && ip link set br0 up
$ ip link set $eth master br0 && ip link set $eth up
$ ip link add link $eth name $eth.100 type vlan id 100 && ip link set $eth.100 up
$ ip addr add 192.168.100.1/24 dev $eth.100
I could fend off the checks in __skb_vlan_pop() with some
skb_mac_header_was_set() calls, but seeing how few callers of
__skb_vlan_pop() there are from TX paths, that seems rather
unproductive.
As an alternative solution, extract the bare minimum logic to strip a
VLAN header, and move it to a new helper named vlan_remove_tag(), close
to the definition of vlan_insert_tag(). Document it appropriately and
make ocelot_xmit_get_vlan_info() call this smaller helper instead.
Seeing that it doesn't appear illegal to test skb->protocol in the TX
path, I guess it would be a good for vlan_remove_tag() to also absorb
the vlan_set_encap_proto() function call.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
kfree_skb() can be called from hard irq handlers,
but skb_attempt_defer_free() is meant to be used
from process or BH contexts, and skb_defer_free_flush()
is meant to be called from BH contexts.
Not having to mask hard irq can save some cycles.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Extend drop reasons to make them usable by subsystems
other than core by reserving the high 16 bits for a
new subsystem ID, of which 0 of course is used for the
existing reasons immediately.
To still be able to have string reasons, restructure
that code a bit to make the loopup under RCU, the only
user of this (right now) is drop_monitor.
Link: https://lore.kernel.org/netdev/00659771ed54353f92027702c5bbb84702da62ce.camel@sipsolutions.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
__kfree_skb_defer() uses the old naming where "defer" meant
slab bulk free/alloc APIs. In the meantime we also made
__kfree_skb_defer() feed the per-NAPI skb cache, which
implies bulk APIs. So take away the 'defer' and add 'napi'.
While at it add a drop reason. This only matters on the
tx_action path, if the skb has a frag_list. But getting
rid of a SKB_DROP_REASON_NOT_SPECIFIED seems like a net
benefit so why not.
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://lore.kernel.org/r/20230420020005.815854-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Datacenter kernel builds will very likely not include WIRELESS,
so let them shave 2 bits off the skb by hiding the wifi fields.
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Recent patches to mlx5 mentioned a regression when moving from
driver local page pool to only using the generic page pool code.
Page pool has two recycling paths (1) direct one, which runs in
safe NAPI context (basically consumer context, so producing
can be lockless); and (2) via a ptr_ring, which takes a spin
lock because the freeing can happen from any CPU; producer
and consumer may run concurrently.
Since the page pool code was added, Eric introduced a revised version
of deferred skb freeing. TCP skbs are now usually returned to the CPU
which allocated them, and freed in softirq context. This places the
freeing (producing of pages back to the pool) enticingly close to
the allocation (consumer).
If we can prove that we're freeing in the same softirq context in which
the consumer NAPI will run - lockless use of the cache is perfectly fine,
no need for the lock.
Let drivers link the page pool to a NAPI instance. If the NAPI instance
is scheduled on the same CPU on which we're freeing - place the pages
in the direct cache.
With that and patched bnxt (XDP enabled to engage the page pool, sigh,
bnxt really needs page pool work :() I see a 2.6% perf boost with
a TCP stream test (app on a different physical core than softirq).
The CPU use of relevant functions decreases as expected:
page_pool_refill_alloc_cache 1.17% -> 0%
_raw_spin_lock 2.41% -> 0.98%
Only consider lockless path to be safe when NAPI is scheduled
- in practice this should cover majority if not all of steady state
workloads. It's usually the NAPI kicking in that causes the skb flush.
The main case we'll miss out on is when application runs on the same
CPU as NAPI. In that case we don't use the deferred skb free path.
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We maintain a NAPI-local cache of skbs which is fed by napi_consume_skb().
Going forward we will also try to cache head and data pages.
Plumb the "are we in a normal NAPI context" information thru
deeper into the freeing path, up to skb_release_data() and
skb_free_head()/skb_pp_recycle(). The "not normal NAPI context"
comes from netpoll which passes budget of 0 to try to reap
the Tx completions but not perform any Rx.
Use "bool napi_safe" rather than bare "int budget",
the further we get from NAPI the more confusing the budget
argument may seem (particularly whether 0 or MAX is the
correct value to pass in when not in NAPI).
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Tested-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit 1effe8ca4e ("skbuff: fix coalescing for page_pool fragment
recycling") allowed coalescing to proceed with non page pool page and page
pool page when @from is cloned, i.e.
to->pp_recycle --> false
from->pp_recycle --> true
skb_cloned(from) --> true
However, it actually requires skb_cloned(@from) to hold true until
coalescing finishes in this situation. If the other cloned SKB is
released while the merging is in process, from_shinfo->nr_frags will be
set to 0 toward the end of the function, causing the increment of frag
page _refcount to be unexpectedly skipped resulting in inconsistent
reference counts. Later when SKB(@to) is released, it frees the page
directly even though the page pool page is still in use, leading to
use-after-free or double-free errors. So it should be prohibited.
The double-free error message below prompted us to investigate:
BUG: Bad page state in process swapper/1 pfn:0e0d1
page:00000000c6548b28 refcount:-1 mapcount:0 mapping:0000000000000000
index:0x2 pfn:0xe0d1
flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff)
raw: 000fffffc0000000 0000000000000000 ffffffff00000101 0000000000000000
raw: 0000000000000002 0000000000000000 ffffffffffffffff 0000000000000000
page dumped because: nonzero _refcount
CPU: 1 PID: 0 Comm: swapper/1 Tainted: G E 6.2.0+
Call Trace:
<IRQ>
dump_stack_lvl+0x32/0x50
bad_page+0x69/0xf0
free_pcp_prepare+0x260/0x2f0
free_unref_page+0x20/0x1c0
skb_release_data+0x10b/0x1a0
napi_consume_skb+0x56/0x150
net_rx_action+0xf0/0x350
? __napi_schedule+0x79/0x90
__do_softirq+0xc8/0x2b1
__irq_exit_rcu+0xb9/0xf0
common_interrupt+0x82/0xa0
</IRQ>
<TASK>
asm_common_interrupt+0x22/0x40
RIP: 0010:default_idle+0xb/0x20
Fixes: 53e0961da1 ("page_pool: add frag page recycling support in page pool")
Signed-off-by: Liang Chen <liangchen.linux@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230413090353.14448-1-liangchen.linux@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Similarly to napi_build_skb(), it is likely the skb allocation in
build_skb() succeeded. frag_size != 0 is also likely, as stated in
__build_skb_around().
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Use skb_propagate_pfmemalloc() in build_skb()/build_skb_around() instead
of open-coding it.
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
MSG_ZEROCOPY ensures that pinned user pages do not exceed the limit.
If no limit is set, skip this accounting as otherwise expensive
atomic_long operations are called for no reason.
This accounting is already skipped for privileged (CAP_IPC_LOCK)
users. Rely on the same mechanism: if no mmp->user is set,
mm_unaccount_pinned_pages does not decrement either.
Tested by running tools/testing/selftests/net/msg_zerocopy.sh with
an unprivileged user for the TXMODE binary:
ip netns exec "${NS1}" sudo -u "{$USER}" "${BIN}" "-${IP}" ...
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230214155740.3448763-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
skbuff_head_cache is misnamed (perhaps for historical reasons?)
because it does not hold heads. Head is the buffer which skb->data
points to, and also where shinfo lives. struct sk_buff is a metadata
structure, not the head.
Eric recently added skb_small_head_cache (which allocates actual
head buffers), let that serve as an excuse to finally clean this up :)
Leave the user-space visible name intact, it could possibly be uAPI.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Recent removal of ksize() in alloc_skb() increased
performance because we no longer read
the associated struct page.
We have an equivalent cost at kfree_skb() time.
kfree(skb->head) has to access a struct page,
often cold in cpu caches to get the owning
struct kmem_cache.
Considering that many allocations are small (at least for TCP ones)
we can have our own kmem_cache to avoid the cache line miss.
This also saves memory because these small heads
are no longer padded to 1024 bytes.
CONFIG_SLUB=y
$ grep skbuff_small_head /proc/slabinfo
skbuff_small_head 2907 2907 640 51 8 : tunables 0 0 0 : slabdata 57 57 0
CONFIG_SLAB=y
$ grep skbuff_small_head /proc/slabinfo
skbuff_small_head 607 624 640 6 1 : tunables 54 27 8 : slabdata 104 104 5
Notes:
- After Kees Cook patches and this one, we might
be able to revert commit
dbae2b0628 ("net: skb: introduce and use a single page frag cache")
because GRO_MAX_HEAD is also small.
- This patch is a NOP for CONFIG_SLOB=y builds.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
All kmalloc_reserve() callers have to make the same computation,
we can factorize them, to prepare following patch in the series.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This is a cleanup patch, to prepare following change.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We have many places using this expression:
SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
Use of SKB_HEAD_ALIGN() will allow to clean them.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
First user of skb_poison_list is in kfree_skb_list_reason, to catch bugs
earlier like introduced in commit eedade12f4 ("net: kfree_skb_list use
kmem_cache_free_bulk"). For completeness mentioned bug have been fixed in
commit f72ff8b81e ("net: fix kfree_skb_list use of skb_mark_not_on_list").
In case of a bug like mentioned commit we would have seen OOPS with:
general protection fault, probably for non-canonical address 0xdead000000000870
And content of one the registers e.g. R13: dead000000000800
In this case skb->len is at offset 112 bytes (0x70) why fault happens at
0x800+0x70 = 0x870
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This include was added for skb_find_text() but all we need there
is a forward declaration of struct ts_config.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
A bug was introduced by commit eedade12f4 ("net: kfree_skb_list use
kmem_cache_free_bulk"). It unconditionally unlinked the SKB list via
invoking skb_mark_not_on_list().
In this patch we choose to remove the skb_mark_not_on_list() call as it
isn't necessary. It would be possible and correct to call
skb_mark_not_on_list() only when __kfree_skb_reason() returns true,
meaning the SKB is ready to be free'ed, as it calls/check skb_unref().
This fix is needed as kfree_skb_list() is also invoked on skb_shared_info
frag_list (skb_drop_fraglist() calling kfree_skb_list()). A frag_list can
have SKBs with elevated refcnt due to cloning via skb_clone_fraglist(),
which takes a reference on all SKBs in the list. This implies the
invariant that all SKBs in the list must have the same refcnt, when using
kfree_skb_list().
Reported-by: syzbot+c8a2e66e37eee553c4fd@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+c8a2e66e37eee553c4fd@syzkaller.appspotmail.com
Fixes: eedade12f4 ("net: kfree_skb_list use kmem_cache_free_bulk")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/167421088417.1125894.9761158218878962159.stgit@firesoul
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The kfree_skb_list function walks SKB (via skb->next) and frees them
individually to the SLUB/SLAB allocator (kmem_cache). It is more
efficient to bulk free them via the kmem_cache_free_bulk API.
This patches create a stack local array with SKBs to bulk free while
walking the list. Bulk array size is limited to 16 SKBs to trade off
stack usage and efficiency. The SLUB kmem_cache "skbuff_head_cache"
uses objsize 256 bytes usually in an order-1 page 8192 bytes that is
32 objects per slab (can vary on archs and due to SLUB sharing). Thus,
for SLUB the optimal bulk free case is 32 objects belonging to same
slab, but runtime this isn't likely to occur.
The expected gain from using kmem_cache bulk alloc and free API
have been assessed via a microbencmark kernel module[1].
The module 'slab_bulk_test01' results at bulk 16 element:
kmem-in-loop Per elem: 109 cycles(tsc) 30.532 ns (step:16)
kmem-bulk Per elem: 64 cycles(tsc) 17.905 ns (step:16)
More detailed description of benchmarks avail in [2].
[1] https://github.com/netoptimizer/prototype-kernel/tree/master/kernel/mm
[2] https://github.com/xdp-project/xdp-project/blob/master/areas/mem/kfree_skb_list01.org
V2: rename function to kfree_skb_add_bulk.
Reviewed-by: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The SKB drop reason uses __builtin_return_address(0) to give the call
"location" to trace_kfree_skb() tracepoint skb:kfree_skb.
To keep this stable for compilers kfree_skb_reason() is annotated with
__fix_address (noinline __noclone) as fixed in commit c205cc7534
("net: skb: prevent the split of kfree_skb_reason() by gcc").
The function kfree_skb_list_reason() invoke kfree_skb_reason(), which
cause the __builtin_return_address(0) "location" to report the
unexpected address of kfree_skb_list_reason.
Example output from 'perf script':
kpktgend_0 1337 [000] 81.002597: skb:kfree_skb: skbaddr=0xffff888144824700 protocol=2048 location=kfree_skb_list_reason+0x1e reason: QDISC_DROP
Patch creates an __always_inline __kfree_skb_reason() helper call that
is called from both kfree_skb_list() and kfree_skb_list_reason().
Suggestions for solutions that shares code better are welcome.
As preparation for next patch move __kfree_skb() invocation out of
this helper function.
Reviewed-by: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Since commit ce098da149 ("skbuff: Introduce slab_build_skb()")
drivers trying to build skb around slab-backed buffers should
go via slab_build_skb() rather than passing frag_size = 0 to
the main build_skb().
Remove the copy'n'pasted comments about 0 meaning slab.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Extending the tail can have some unexpected side effects if a program uses
a helper like BPF_FUNC_skb_pull_data to read partial content beyond the
head skb headlen when all the skbs in the gso frag_list are linear with no
head_frag -
kernel BUG at net/core/skbuff.c:4219!
pc : skb_segment+0xcf4/0xd2c
lr : skb_segment+0x63c/0xd2c
Call trace:
skb_segment+0xcf4/0xd2c
__udp_gso_segment+0xa4/0x544
udp4_ufo_fragment+0x184/0x1c0
inet_gso_segment+0x16c/0x3a4
skb_mac_gso_segment+0xd4/0x1b0
__skb_gso_segment+0xcc/0x12c
udp_rcv_segment+0x54/0x16c
udp_queue_rcv_skb+0x78/0x144
udp_unicast_rcv_skb+0x8c/0xa4
__udp4_lib_rcv+0x490/0x68c
udp_rcv+0x20/0x30
ip_protocol_deliver_rcu+0x1b0/0x33c
ip_local_deliver+0xd8/0x1f0
ip_rcv+0x98/0x1a4
deliver_ptype_list_skb+0x98/0x1ec
__netif_receive_skb_core+0x978/0xc60
Fix this by marking these skbs as GSO_DODGY so segmentation can handle
the tail updates accordingly.
Fixes: 3dcbdb134f ("net: gso: Fix skb_segment splat when splitting gso_size mangled skb having linear-headed frag_list")
Signed-off-by: Sean Tranchetti <quic_stranche@quicinc.com>
Signed-off-by: Subash Abhinov Kasiviswanathan <quic_subashab@quicinc.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/1671084718-24796-1-git-send-email-quic_subashab@quicinc.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
syzkaller reported:
BUG: KASAN: slab-out-of-bounds in __build_skb_around+0x235/0x340 net/core/skbuff.c:294
Write of size 32 at addr ffff88802aa172c0 by task syz-executor413/5295
For bpf_prog_test_run_skb(), which uses a kmalloc()ed buffer passed to
build_skb().
When build_skb() is passed a frag_size of 0, it means the buffer came
from kmalloc. In these cases, ksize() is used to find its actual size,
but since the allocation may not have been made to that size, actually
perform the krealloc() call so that all the associated buffer size
checking will be correctly notified (and use the "new" pointer so that
compiler hinting works correctly). Split this logic out into a new
interface, slab_build_skb(), but leave the original 0 checking for now
to catch any stragglers.
Reported-by: syzbot+fda18eaa8c12534ccb3b@syzkaller.appspotmail.com
Link: https://groups.google.com/g/syzkaller-bugs/c/UnIKxTtU5-0/m/-wbXinkgAQAJ
Fixes: 38931d8989 ("mm: Make ksize() a reporting-only function")
Cc: Pavel Begunkov <asml.silence@gmail.com>
Cc: pepsipu <soopthegoop@gmail.com>
Cc: syzbot+fda18eaa8c12534ccb3b@syzkaller.appspotmail.com
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: kasan-dev <kasan-dev@googlegroups.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: ast@kernel.org
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Hao Luo <haoluo@google.com>
Cc: Jesper Dangaard Brouer <hawk@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: jolsa@kernel.org
Cc: KP Singh <kpsingh@kernel.org>
Cc: martin.lau@linux.dev
Cc: Stanislav Fomichev <sdf@google.com>
Cc: song@kernel.org
Cc: Yonghong Song <yhs@fb.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20221208060256.give.994-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Adopt atomic_long_try_cmpxchg() in mm_account_pinned_pages()
as it is slightly more efficient.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-----BEGIN PGP SIGNATURE-----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=q04p
-----END PGP SIGNATURE-----
Merge tag 'rxrpc-next-20221108' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs
rxrpc changes
David Howells says:
====================
rxrpc: Increasing SACK size and moving away from softirq, part 1
AF_RXRPC has some issues that need addressing:
(1) The SACK table has a maximum capacity of 255, but for modern networks
that isn't sufficient. This is hard to increase in the upstream code
because of the way the application thread is coupled to the softirq
and retransmission side through a ring buffer. Adjustments to the rx
protocol allows a capacity of up to 8192, and having a ring
sufficiently large to accommodate that would use an excessive amount
of memory as this is per-call.
(2) Processing ACKs in softirq mode causes the ACKs get conflated, with
only the most recent being considered. Whilst this has the upside
that the retransmission algorithm only needs to deal with the most
recent ACK, it causes DATA transmission for a call to be very bursty
because DATA packets cannot be transmitted in softirq mode. Rather
transmission must be delegated to either the application thread or a
workqueue, so there tend to be sudden bursts of traffic for any
particular call due to scheduling delays.
(3) All crypto in a single call is done in series; however, each DATA
packet is individually encrypted so encryption and decryption of large
calls could be parallelised if spare CPU resources are available.
This is the first of a number of sets of patches that try and address them.
The overall aims of these changes include:
(1) To get rid of the TxRx ring and instead pass the packets round in
queues (eg. sk_buff_head). On the Tx side, each ACK packet comes with
a SACK table that can be parsed as-is, so there's no particular need
to maintain our own; we just have to refer to the ACK.
On the Rx side, we do need to maintain a SACK table with one bit per
entry - but only if packets go missing - and we don't want to have to
perform a complex transformation to get the information into an ACK
packet.
(2) To try and move almost all processing of received packets out of the
softirq handler and into a high-priority kernel I/O thread. Only the
transferral of packets would be left there. I would still use the
encap_rcv hook to receive packets as there's a noticeable performance
drop from letting the UDP socket put the packets into its own queue
and then getting them out of there.
(3) To make the I/O thread also do all the transmission. The app thread
would be responsible for packaging the data into packets and then
buffering them for the I/O thread to transmit. This would make it
easier for the app thread to run ahead of the I/O thread, and would
mean the I/O thread is less likely to have to wait around for a new
packet to come available for transmission.
(4) To logically partition the socket/UAPI/KAPI side of things from the
I/O side of things. The local endpoint, connection, peer and call
objects would belong to the I/O side. The socket side would not then
touch the private internals of calls and suchlike and would not change
their states. It would only look at the send queue, receive queue and
a way to pass a message to cause an abort.
(5) To remove as much locking, synchronisation, barriering and atomic ops
as possible from the I/O side. Exclusion would be achieved by
limiting modification of state to the I/O thread only. Locks would
still need to be used in communication with the UDP socket and the
AF_RXRPC socket API.
(6) To provide crypto offload kernel threads that, when there's slack in
the system, can see packets that need crypting and provide
parallelisation in dealing with them.
(7) To remove the use of system timers. Since each timer would then send
a poke to the I/O thread, which would then deal with it when it had
the opportunity, there seems no point in using system timers if,
instead, a list of timeouts can be sensibly consulted. An I/O thread
only then needs to schedule with a timeout when it is idle.
(8) To use zero-copy sendmsg to send packets. This would make use of the
I/O thread being the sole transmitter on the socket to manage the
dead-reckoning sequencing of the completion notifications. There is a
problem with zero-copy, though: the UDP socket doesn't handle running
out of option memory very gracefully.
With regard to this first patchset, the changes made include:
(1) Some fixes, including a fallback for proc_create_net_single_write(),
setting ack.bufferSize to 0 in ACK packets and a fix for rxrpc
congestion management, which shouldn't be saving the cwnd value
between calls.
(2) Improvements in rxrpc tracepoints, including splitting the timer
tracepoint into a set-timer and a timer-expired trace.
(3) Addition of a new proc file to display some stats.
(4) Some code cleanups, including removing some unused bits and
unnecessary header inclusions.
(5) A change to the recently added UDP encap_err_rcv hook so that it has
the same signature as {ip,ipv6}_icmp_error(), and then just have rxrpc
point its UDP socket's hook directly at those.
(6) Definition of a new struct, rxrpc_txbuf, that is used to hold
transmissible packets of DATA and ACK type in a single 2KiB block
rather than using an sk_buff. This allows the buffer to be on a
number of queues simultaneously more easily, and also guarantees that
the entire block is in a single unit for zerocopy purposes and that
the data payload is aligned for in-place crypto purposes.
(7) ACK txbufs are allocated at proposal and queued for later transmission
rather than being stored in a single place in the rxrpc_call struct,
which means only a single ACK can be pending transmission at a time.
The queue is then drained at various points. This allows the ACK
generation code to be simplified.
(8) The Rx ring buffer is removed. When a jumbo packet is received (which
comprises a number of ordinary DATA packets glued together), it used
to be pointed to by the ring multiple times, with an annotation in a
side ring indicating which subpacket was in that slot - but this is no
longer possible. Instead, the packet is cloned once for each
subpacket, barring the last, and the range of data is set in the skb
private area. This makes it easier for the subpackets in a jumbo
packet to be decrypted in parallel.
(9) The Tx ring buffer is removed. The side annotation ring that held the
SACK information is also removed. Instead, in the event of packet
loss, the SACK data attached an ACK packet is parsed.
(10) Allocate an skcipher request when needed in the rxkad security class
rather than caching one in the rxrpc_call struct. This deals with a
race between externally-driven call disconnection getting rid of the
skcipher request and sendmsg/recvmsg trying to use it because they
haven't seen the completion yet. This is also needed to support
parallelisation as the skcipher request cannot be used by two or more
threads simultaneously.
(11) Call udp_sendmsg() and udpv6_sendmsg() directly rather than going
through kernel_sendmsg() so that we can provide our own iterator
(zerocopy explicitly doesn't work with a KVEC iterator). This also
lets us avoid the overhead of the security hook.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Improve the tracking of which packets need to be transmitted by saving the
last ACK packet that we receive that has a populated soft-ACK table rather
than marking packets. Then we can step through the soft-ACK table and look
at the packets we've transmitted beyond that to determine which packets we
might want to retransmit.
We also look at the highest serial number that has been acked to try and
guess which packets we've transmitted the peer is likely to have seen. If
necessary, we send a ping to retrieve that number.
One downside that might be a problem is that we can't then compare the
previous acked/unacked state so easily in rxrpc_input_soft_acks() - which
is a potential problem for the slow-start algorithm.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
Since commit 3dcbdb134f ("net: gso: Fix skb_segment splat when
splitting gso_size mangled skb having linear-headed frag_list"), it is
allowed to change gso_size of a GRO packet. However, that commit assumes
that "checking the first list_skb member suffices; i.e if either of the
list_skb members have non head_frag head, then the first one has too".
It turns out this assumption does not hold. We've seen BUG_ON being hit
in skb_segment when skbs on the frag_list had differing head_frag with
the vmxnet3 driver. This happens because __netdev_alloc_skb and
__napi_alloc_skb can return a skb that is page backed or kmalloced
depending on the requested size. As the result, the last small skb in
the GRO packet can be kmalloced.
There are three different locations where this can be fixed:
(1) We could check head_frag in GRO and not allow GROing skbs with
different head_frag. However, that would lead to performance
regression on normal forward paths with unmodified gso_size, where
!head_frag in the last packet is not a problem.
(2) Set a flag in bpf_skb_net_grow and bpf_skb_net_shrink indicating
that NETIF_F_SG is undesirable. That would need to eat a bit in
sk_buff. Furthermore, that flag can be unset when all skbs on the
frag_list are page backed. To retain good performance,
bpf_skb_net_grow/shrink would have to walk the frag_list.
(3) Walk the frag_list in skb_segment when determining whether
NETIF_F_SG should be cleared. This of course slows things down.
This patch implements (3). To limit the performance impact in
skb_segment, the list is walked only for skbs with SKB_GSO_DODGY set
that have gso_size changed. Normal paths thus will not hit it.
We could check only the last skb but since we need to walk the whole
list anyway, let's stay on the safe side.
Fixes: 3dcbdb134f ("net: gso: Fix skb_segment splat when splitting gso_size mangled skb having linear-headed frag_list")
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/e04426a6a91baf4d1081e1b478c82b5de25fdf21.1667407944.git.jbenc@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When an skb with a frag list is consumed, we currently
pretend all skbs in the frag list were dropped.
In order to fix this, add a @reason argument to skb_release_data()
and skb_release_all().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This will allow to simply use in the future:
kfree_skb_reason(skb, reason);
Instead of repeating sequences like:
if (dropped)
kfree_skb_reason(skb, reason);
else
consume_skb(skb);
For instance, following patch in the series is adding
@reason to skb_release_data() and skb_release_all(),
so that we can propagate a meaningful @reason whenever
consume_skb()/kfree_skb() have to take care of a potential frag_list.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
2871edb32f ("can: kvaser_usb: Fix possible completions during init_completion")
abb8670938 ("can: kvaser_usb_leaf: Ignore stale bus-off after start")
8d21f5927a ("can: kvaser_usb_leaf: Fix improved state not being reported")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Instead of discovering the kmalloc bucket size _after_ allocation, round
up proactively so the allocation is explicitly made for the full size,
allowing the compiler to correctly reason about the resulting size of
the buffer through the existing __alloc_size() hint.
This will allow for kernels built with CONFIG_UBSAN_BOUNDS or the
coming dynamic bounds checking under CONFIG_FORTIFY_SOURCE to gain
back the __alloc_size() hints that were temporarily reverted in commit
93dd04ab0b ("slab: remove __alloc_size attribute from __kmalloc_track_caller")
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: netdev@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: David Rientjes <rientjes@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://patchwork.kernel.org/project/netdevbpf/patch/20221021234713.you.031-kees@kernel.org/
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20221025223811.up.360-kees@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
skb_pp_recycle() is only used by skb_free_head() in
skbuff.c, so move it to skbuff.c.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit 3226b158e6 ("net: avoid 32 x truesize under-estimation
for tiny skbs") we are observing 10-20% regressions in performance
tests with small packets. The perf trace points to high pressure on
the slab allocator.
This change tries to improve the allocation schema for small packets
using an idea originally suggested by Eric: a new per CPU page frag is
introduced and used in __napi_alloc_skb to cope with small allocation
requests.
To ensure that the above does not lead to excessive truesize
underestimation, the frag size for small allocation is inflated to 1K
and all the above is restricted to build with 4K page size.
Note that we need to update accordingly the run-time check introduced
with commit fd9ea57f4e ("net: add napi_get_frags_check() helper").
Alex suggested a smart page refcount schema to reduce the number
of atomic operations and deal properly with pfmemalloc pages.
Under small packet UDP flood, I measure a 15% peak tput increases.
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Suggested-by: Alexander H Duyck <alexanderduyck@fb.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/6b6f65957c59f86a353fc09a5127e83a32ab5999.1664350652.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We can benefit from a smaller struct ubuf_info, so leave only mandatory
fields and let users to decide how they want to extend it. Convert
MSG_ZEROCOPY to struct ubuf_info_msgzc and remove duplicated fields.
This reduces the size from 48 bytes to just 16.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
drivers/net/ethernet/freescale/fec.h
7d650df99d ("net: fec: add pm_qos support on imx6q platform")
40c79ce13b ("net: fec: add stop mode support for imx8 platform")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
As Eric reported, the 'reason' field is not presented when trace the
kfree_skb event by perf:
$ perf record -e skb:kfree_skb -a sleep 10
$ perf script
ip_defrag 14605 [021] 221.614303: skb:kfree_skb:
skbaddr=0xffff9d2851242700 protocol=34525 location=0xffffffffa39346b1
reason:
The cause seems to be passing kernel address directly to TP_printk(),
which is not right. As the enum 'skb_drop_reason' is not exported to
user space through TRACE_DEFINE_ENUM(), perf can't get the drop reason
string from the 'reason' field, which is a number.
Therefore, we introduce the macro DEFINE_DROP_REASON(), which is used
to define the trace enum by TRACE_DEFINE_ENUM(). With the help of
DEFINE_DROP_REASON(), now we can remove the auto-generate that we
introduced in the commit ec43908dd5
("net: skb: use auto-generation to convert skb drop reason to string"),
and define the string array 'drop_reasons'.
Hmmmm...now we come back to the situation that have to maintain drop
reasons in both enum skb_drop_reason and DEFINE_DROP_REASON. But they
are both in dropreason.h, which makes it easier.
After this commit, now the format of kfree_skb is like this:
$ cat /tracing/events/skb/kfree_skb/format
name: kfree_skb
ID: 1524
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:void * skbaddr; offset:8; size:8; signed:0;
field:void * location; offset:16; size:8; signed:0;
field:unsigned short protocol; offset:24; size:2; signed:0;
field:enum skb_drop_reason reason; offset:28; size:4; signed:0;
print fmt: "skbaddr=%p protocol=%u location=%p reason: %s", REC->skbaddr, REC->protocol, REC->location, __print_symbolic(REC->reason, { 1, "NOT_SPECIFIED" }, { 2, "NO_SOCKET" } ......
Fixes: ec43908dd5 ("net: skb: use auto-generation to convert skb drop reason to string")
Link: https://lore.kernel.org/netdev/CANn89i+bx0ybvE55iMYf5GJM48WwV1HNpdm9Q6t-HaEstqpCSA@mail.gmail.com/
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While reading sysctl_tstamp_allow_data, it can be changed
concurrently. Thus, we need to add READ_ONCE() to its reader.
Fixes: b245be1f4d ("net-timestamp: no-payload only sysctl")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb_copy_bits() could fail, which requires a check on the return
value.
Signed-off-by: Li Zhong <floridsleeves@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sometimes, gcc will optimize the function by spliting it to two or
more functions. In this case, kfree_skb_reason() is splited to
kfree_skb_reason and kfree_skb_reason.part.0. However, the
function/tracepoint trace_kfree_skb() in it needs the return address
of kfree_skb_reason().
This split makes the call chains becomes:
kfree_skb_reason() -> kfree_skb_reason.part.0 -> trace_kfree_skb()
which makes the return address that passed to trace_kfree_skb() be
kfree_skb().
Therefore, introduce '__fix_address', which is the combination of
'__noclone' and 'noinline', and apply it to kfree_skb_reason() to
prevent to from being splited or made inline.
(Is it better to simply apply '__noclone oninline' to kfree_skb_reason?
I'm thinking maybe other functions have the same problems)
Meanwhile, wrap 'skb_unref()' with 'unlikely()', as the compiler thinks
it is likely return true and splits kfree_skb_reason().
Signed-off-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pavel Begunkov says:
====================
io_uring zerocopy send
The patchset implements io_uring zerocopy send. It works with both registered
and normal buffers, mixing is allowed but not recommended. Apart from usual
request completions, just as with MSG_ZEROCOPY, io_uring separately notifies
the userspace when buffers are freed and can be reused (see API design below),
which is delivered into io_uring's Completion Queue. Those "buffer-free"
notifications are not necessarily per request, but the userspace has control
over it and should explicitly attaching a number of requests to a single
notification. The series also adds some internal optimisations when used with
registered buffers like removing page referencing.
From the kernel networking perspective there are two main changes. The first
one is passing ubuf_info into the network layer from io_uring (inside of an
in kernel struct msghdr). This allows extra optimisations, e.g. ubuf_info
caching on the io_uring side, but also helps to avoid cross-referencing
and synchronisation problems. The second part is an optional optimisation
removing page referencing for requests with registered buffers.
Benchmarking UDP with an optimised version of the selftest (see [1]), which
sends a bunch of requests, waits for completions and repeats. "+ flush" column
posts one additional "buffer-free" notification per request, and just "zc"
doesn't post buffer notifications at all.
NIC (requests / second):
IO size | non-zc | zc | zc + flush
4000 | 495134 | 606420 (+22%) | 558971 (+12%)
1500 | 551808 | 577116 (+4.5%) | 565803 (+2.5%)
1000 | 584677 | 592088 (+1.2%) | 560885 (-4%)
600 | 596292 | 598550 (+0.4%) | 555366 (-6.7%)
dummy (requests / second):
IO size | non-zc | zc | zc + flush
8000 | 1299916 | 2396600 (+84%) | 2224219 (+71%)
4000 | 1869230 | 2344146 (+25%) | 2170069 (+16%)
1200 | 2071617 | 2361960 (+14%) | 2203052 (+6%)
600 | 2106794 | 2381527 (+13%) | 2195295 (+4%)
Previously it also brought a massive performance speedup compared to the
msg_zerocopy tool (see [3]), which is probably not super interesting. There
is also an additional bunch of refcounting optimisations that was omitted from
the series for simplicity and as they don't change the picture drastically,
they will be sent as follow up, as well as flushing optimisations closing the
performance gap b/w two last columns.
For TCP on localhost (with hacks enabling localhost zerocopy) and including
additional overhead for receive:
IO size | non-zc | zc
1200 | 4174 | 4148
4096 | 7597 | 11228
Using a real NIC 1200 bytes, zc is worse than non-zc ~5-10%, maybe the
omitted optimisations will somewhat help, should look better for 4000,
but couldn't test properly because of setup problems.
Links:
liburing (benchmark + tests):
[1] https://github.com/isilence/liburing/tree/zc_v4
kernel repo:
[2] https://github.com/isilence/linux/tree/zc_v4
RFC v1:
[3] https://lore.kernel.org/io-uring/cover.1638282789.git.asml.silence@gmail.com/
RFC v2:
https://lore.kernel.org/io-uring/cover.1640029579.git.asml.silence@gmail.com/
Net patches based:
git@github.com:isilence/linux.git zc_v4-net-base
or
https://github.com/isilence/linux/tree/zc_v4-net-base
API design overview:
The series introduces an io_uring concept of notifactors. From the userspace
perspective it's an entity to which it can bind one or more requests and then
requesting to flush it. Flushing a notifier makes it impossible to attach new
requests to it, and instructs the notifier to post a completion once all
requests attached to it are completed and the kernel doesn't need the buffers
anymore.
Notifications are stored in notification slots, which should be registered as
an array in io_uring. Each slot stores only one notifier at any particular
moment. Flushing removes it from the slot and the slot automatically replaces
it with a new notifier. All operations with notifiers are done by specifying
an index of a slot it's currently in.
When registering a notification the userspace specifies a u64 tag for each
slot, which will be copied in notification completion entries as
cqe::user_data. cqe::res is 0 and cqe::flags is equal to wrap around u32
sequence number counting notifiers of a slot.
====================
Link: https://lore.kernel.org/r/cover.1657643355.git.asml.silence@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Some users like io_uring can do page pinning more efficiently, so we
want a way to delegate referencing to other subsystems. For that add
a new flag called SKBFL_MANAGED_FRAG_REFS. When set, skb doesn't hold
page references and upper layers are responsivle to managing page
lifetime.
It's allowed to convert skbs from managed to normal by calling
skb_zcopy_downgrade_managed(). The function will take all needed
page references and clear the flag. It's needed, for instance,
to avoid mixing managed modes.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add support for custom iov_iter handling to msghdr. The idea is that
in-kernel subsystems want control over how an SG is split.
Signed-off-by: David Ahern <dsahern@kernel.org>
[pavel: move callback into msghdr]
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We don't want to list every single ubuf_info callback in
skb_orphan_frags(), add a flag controlling the behaviour.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We should not append MSG_ZEROCOPY requests to skbuff with non
MSG_ZEROCOPY ubuf_info, they might be not compatible.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
TCP allocates 'fast clones' skbs for packets in tx queues.
Currently, __alloc_skb() initializes the companion fclone
field to SKB_FCLONE_CLONE, and leaves other fields untouched.
It makes sense to defer this init much later in skb_clone(),
because all fclone fields are copied and hot in cpu caches
at that time.
This removes one cache line miss in __alloc_skb(), cost seen
on an host with 256 cpus all competing on memory accesses.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move the len fields manipulation in the skbs to a helper function.
There is a comment specifically requesting this and there are several
other areas in the code displaying the same pattern which can be
refactored.
This improves code readability.
Signed-off-by: Richard Gobert <richardbgobert@gmail.com>
Link: https://lore.kernel.org/r/20220622160853.GA6478@debian
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
NAPI cache skb_count is being checked twice without condition. Change to
checking the second time only if the first check is run.
Signed-off-by: Sieng Piaw Liew <liew.s.piaw@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 6454eca81e ("net: Use lockdep_assert_in_softirq()
in napi_consume_skb()") added a check in napi_consume_skb()
which is a bit weak.
napi_consume_skb() and __napi_alloc_skb() should only
be used from BH context, not from hard irq or nmi context,
otherwise we could have races.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>