| Age | Commit message (Collapse) | Author |
|---|
|
git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core & protocols:
- Support HW queue leasing, allowing containers to be granted access
to HW queues for zero-copy operations and AF_XDP
- Number of code moves to help the compiler with inlining. Avoid
output arguments for returning drop reason where possible
- Rework drop handling within qdiscs to include more metadata about
the reason and dropping qdisc in the tracepoints
- Remove the rtnl_lock use from IP Multicast Routing
- Pack size information into the Rx Flow Steering table pointer
itself. This allows making the table itself a flat array of u32s,
thus making the table allocation size a power of two
- Report TCP delayed ack timer information via socket diag
- Add ip_local_port_step_width sysctl to allow distributing the
randomly selected ports more evenly throughout the allowed space
- Add support for per-route tunsrc in IPv6 segment routing
- Start work of switching sockopt handling to iov_iter
- Improve dynamic recvbuf sizing in MPTCP, limit burstiness and avoid
buffer size drifting up
- Support MSG_EOR in MPTCP
- Add stp_mode attribute to the bridge driver for STP mode selection.
This addresses concerns about call_usermodehelper() usage
- Remove UDP-Lite support (as announced in 2023)
- Remove support for building IPv6 as a module. Remove the now
unnecessary function calling indirection
Cross-tree stuff:
- Move Michael MIC code from generic crypto into wireless, it's
considered insecure but some WiFi networks still need it
Netfilter:
- Switch nft_fib_ipv6 module to no longer need temporary dst_entry
object allocations by using fib6_lookup() + RCU.
Florian W reports this gets us ~13% higher packet rate
- Convert IPVS's global __ip_vs_mutex to per-net service_mutex and
switch the service tables to be per-net. Convert some code that
walks the service lists to use RCU instead of the service_mutex
- Add more opinionated input validation to lower security exposure
- Make IPVS hash tables to be per-netns and resizable
Wireless:
- Finished assoc frame encryption/EPPKE/802.1X-over-auth
- Radar detection improvements
- Add 6 GHz incumbent signal detection APIs
- Multi-link support for FILS, probe response templates and client
probing
- New APIs and mac80211 support for NAN (Neighbor Aware Networking,
aka Wi-Fi Aware) so less work must be in firmware
Driver API:
- Add numerical ID for devlink instances (to avoid having to create
fake bus/device pairs just to have an ID). Support shared devlink
instances which span multiple PFs
- Add standard counters for reporting pause storm events (implement
in mlx5 and fbnic)
- Add configuration API for completion writeback buffering (implement
in mana)
- Support driver-initiated change of RSS context sizes
- Support DPLL monitoring input frequency (implement in zl3073x)
- Support per-port resources in devlink (implement in mlx5)
Misc:
- Expand the YAML spec for Netfilter
Drivers
- Software:
- macvlan: support multicast rx for bridge ports with shared
source MAC address
- team: decouple receive and transmit enablement for IEEE 802.3ad
LACP "independent control"
- Ethernet high-speed NICs:
- nVidia/Mellanox:
- support high order pages in zero-copy mode (for payload
coalescing)
- support multiple packets in a page (for systems with 64kB
pages)
- Broadcom 25-400GE (bnxt):
- implement XDP RSS hash metadata extraction
- add software fallback for UDP GSO, lowering the IOMMU cost
- Broadcom 800GE (bnge):
- add link status and configuration handling
- add various HW and SW statistics
- Marvell/Cavium:
- NPC HW block support for cn20k
- Huawei (hinic3):
- add mailbox / control queue
- add rx VLAN offload
- add driver info and link management
- Ethernet NICs:
- Marvell/Aquantia:
- support reading SFP module info on some AQC100 cards
- Realtek PCI (r8169):
- add support for RTL8125cp
- Realtek USB (r8152):
- support for the RTL8157 5Gbit chip
- add 2500baseT EEE status/configuration support
- Ethernet NICs embedded and off-the-shelf IP:
- Synopsys (stmmac):
- cleanup and reorganize SerDes handling and PCS support
- cleanup descriptor handling and per-platform data
- cleanup and consolidate MDIO defines and handling
- shrink driver memory use for internal structures
- improve Tx IRQ coalescing
- improve TCP segmentation handling
- add support for Spacemit K3
- Cadence (macb):
- support PHYs that have inband autoneg disabled with GEM
- support IEEE 802.3az EEE
- rework usrio capabilities and handling
- AMD (xgbe):
- improve power management for S0i3
- improve TX resilience for link-down handling
- Virtual:
- Google cloud vNIC:
- support larger ring sizes in DQO-QPL mode
- improve HW-GRO handling
- support UDP GSO for DQO format
- PCIe NTB:
- support queue count configuration
- Ethernet PHYs:
- automatically disable PHY autonomous EEE if MAC is in charge
- Broadcom:
- add BCM84891/BCM84892 support
- Micrel:
- support for LAN9645X internal PHY
- Realtek:
- add RTL8224 pair order support
- support PHY LEDs on RTL8211F-VD
- support spread spectrum clocking (SSC)
- Maxlinear:
- add PHY-level statistics via ethtool
- Ethernet switches:
- Maxlinear (mxl862xx):
- support for bridge offloading
- support for VLANs
- support driver statistics
- Bluetooth:
- large number of fixes and new device IDs
- Mediatek:
- support MT6639 (MT7927)
- support MT7902 SDIO
- WiFi:
- Intel (iwlwifi):
- UNII-9 and continuing UHR work
- MediaTek (mt76):
- mt7996/mt7925 MLO fixes/improvements
- mt7996 NPU support (HW eth/wifi traffic offload)
- Qualcomm (ath12k):
- monitor mode support on IPQ5332
- basic hwmon temperature reporting
- support IPQ5424
- Realtek:
- add USB RX aggregation to improve performance
- add USB TX flow control by tracking in-flight URBs
- Cellular:
- IPA v5.2 support"
* tag 'net-next-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1561 commits)
net: pse-pd: fix kernel-doc function name for pse_control_find_by_id()
wireguard: device: use exit_rtnl callback instead of manual rtnl_lock in pre_exit
wireguard: allowedips: remove redundant space
tools: ynl: add sample for wireguard
wireguard: allowedips: Use kfree_rcu() instead of call_rcu()
MAINTAINERS: Add netkit selftest files
selftests/net: Add additional test coverage in nk_qlease
selftests/net: Split netdevsim tests from HW tests in nk_qlease
tools/ynl: Make YnlFamily closeable as a context manager
net: airoha: Add missing PPE configurations in airoha_ppe_hw_init()
net: airoha: Fix VIP configuration for AN7583 SoC
net: caif: clear client service pointer on teardown
net: strparser: fix skb_head leak in strp_abort_strp()
net: usb: cdc-phonet: fix skb frags[] overflow in rx_complete()
selftests/bpf: add test for xdp_master_redirect with bond not up
net, bpf: fix null-ptr-deref in xdp_master_redirect() for down master
net: airoha: Remove PCE_MC_EN_MASK bit in REG_FE_PCE_CFG configuration
sctp: disable BH before calling udp_tunnel_xmit_skb()
sctp: fix missing encap_port propagation for GSO fragments
net: airoha: Rely on net_device pointer in ETS callbacks
...
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Pull bpf updates from Alexei Starovoitov:
- Welcome new BPF maintainers: Kumar Kartikeya Dwivedi, Eduard
Zingerman while Martin KaFai Lau reduced his load to Reviwer.
- Lots of fixes everywhere from many first time contributors. Thank you
All.
- Diff stat is dominated by mechanical split of verifier.c into
multiple components:
- backtrack.c: backtracking logic and jump history
- states.c: state equivalence
- cfg.c: control flow graph, postorder, strongly connected
components
- liveness.c: register and stack liveness
- fixups.c: post-verification passes: instruction patching, dead
code removal, bpf_loop inlining, finalize fastcall
8k line were moved. verifier.c still stands at 20k lines.
Further refactoring is planned for the next release.
- Replace dynamic stack liveness with static stack liveness based on
data flow analysis.
This improved the verification time by 2x for some programs and
equally reduced memory consumption. New logic is in liveness.c and
supported by constant folding in const_fold.c (Eduard Zingerman,
Alexei Starovoitov)
- Introduce BTF layout to ease addition of new BTF kinds (Alan Maguire)
- Use kmalloc_nolock() universally in BPF local storage (Amery Hung)
- Fix several bugs in linked registers delta tracking (Daniel Borkmann)
- Improve verifier support of arena pointers (Emil Tsalapatis)
- Improve verifier tracking of register bounds in min/max and tnum
domains (Harishankar Vishwanathan, Paul Chaignon, Hao Sun)
- Further extend support for implicit arguments in the verifier (Ihor
Solodrai)
- Add support for nop,nop5 instruction combo for USDT probes in libbpf
(Jiri Olsa)
- Support merging multiple module BTFs (Josef Bacik)
- Extend applicability of bpf_kptr_xchg (Kaitao Cheng)
- Retire rcu_trace_implies_rcu_gp() (Kumar Kartikeya Dwivedi)
- Support variable offset context access for 'syscall' programs (Kumar
Kartikeya Dwivedi)
- Migrate bpf_task_work and dynptr to kmalloc_nolock() (Mykyta
Yatsenko)
- Fix UAF in in open-coded task_vma iterator (Puranjay Mohan)
* tag 'bpf-next-7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (241 commits)
selftests/bpf: cover short IPv4/IPv6 inputs with adjust_room
bpf: reject short IPv4/IPv6 inputs in bpf_prog_test_run_skb
selftests/bpf: Use memfd_create instead of shm_open in cgroup_iter_memcg
selftests/bpf: Add test for cgroup storage OOB read
bpf: Fix OOB in pcpu_init_value
selftests/bpf: Fix reg_bounds to match new tnum-based refinement
selftests/bpf: Add tests for non-arena/arena operations
bpf: Allow instructions with arena source and non-arena dest registers
bpftool: add missing fsession to the usage and docs of bpftool
docs/bpf: add missing fsession attach type to docs
bpf: add missing fsession to the verifier log
bpf: Move BTF checking logic into check_btf.c
bpf: Move backtracking logic to backtrack.c
bpf: Move state equivalence logic to states.c
bpf: Move check_cfg() into cfg.c
bpf: Move compute_insn_live_regs() into liveness.c
bpf: Move fixup/post-processing logic from verifier.c into fixups.c
bpf: Simplify do_check_insn()
bpf: Move checks for reserved fields out of the main pass
bpf: Delete unused variable
...
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull vfs i_ino updates from Christian Brauner:
"For historical reasons, the inode->i_ino field is an unsigned long,
which means that it's 32 bits on 32 bit architectures. This has caused
a number of filesystems to implement hacks to hash a 64-bit identifier
into a 32-bit field, and deprives us of a universal identifier field
for an inode.
This changes the inode->i_ino field from an unsigned long to a u64.
This shouldn't make any material difference on 64-bit hosts, but
32-bit hosts will see struct inode grow by at least 4 bytes. This
could have effects on slabcache sizes and field alignment.
The bulk of the changes are to format strings and tracepoints, since
the kernel itself doesn't care that much about the i_ino field. The
first patch changes some vfs function arguments, so check that one out
carefully.
With this change, we may be able to shrink some inode structures. For
instance, struct nfs_inode has a fileid field that holds the 64-bit
inode number. With this set of changes, that field could be
eliminated. I'd rather leave that sort of cleanups for later just to
keep this simple"
* tag 'vfs-7.1-rc1.kino' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
nilfs2: fix 64-bit division operations in nilfs_bmap_find_target_in_group()
EVM: add comment describing why ino field is still unsigned long
vfs: remove externs from fs.h on functions modified by i_ino widening
treewide: fix missed i_ino format specifier conversions
ext4: fix signed format specifier in ext4_load_inode trace event
treewide: change inode->i_ino from unsigned long to u64
nilfs2: widen trace event i_ino fields to u64
f2fs: widen trace event i_ino fields to u64
ext4: widen trace event i_ino fields to u64
zonefs: widen trace event i_ino fields to u64
hugetlbfs: widen trace event i_ino fields to u64
ext2: widen trace event i_ino fields to u64
cachefiles: widen trace event i_ino fields to u64
vfs: widen trace event i_ino fields to u64
net: change sock.sk_ino and sock_i_ino() to u64
audit: widen ino fields to u64
vfs: widen inode hash/lookup functions to u64
|
|
The netif_get_rx_queue_lease_locked() API hides the locking
and the descend onto the leased queue. Making the code
harder to follow (at least to me). Remove the API and open
code the descend a bit. Most of the code now looks like:
if (!leased)
return __helper(x);
hw_rxq = ..
netdev_lock(hw_rxq->dev);
ret = __helper(x);
netdev_unlock(hw_rxq->dev);
return ret;
Of course if we have more code paths that need the wrapping
we may need to revisit. For now, IMHO, having to know what
netif_get_rx_queue_lease_locked() does is not worth the 20LoC
it saves.
Link: https://patch.msgid.link/20260408151251.72bd2482@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Daniel Borkmann says:
====================
netkit: Support for io_uring zero-copy and AF_XDP
Containers use virtual netdevs to route traffic from a physical netdev
in the host namespace. They do not have access to the physical netdev
in the host and thus can't use memory providers or AF_XDP that require
reconfiguring/restarting queues in the physical netdev.
This patchset adds the concept of queue leasing to virtual netdevs that
allow containers to use memory providers and AF_XDP at native speed.
Leased queues are bound to a real queue in a physical netdev and act
as a proxy.
Memory providers and AF_XDP operations take an ifindex and queue id,
so containers would pass in an ifindex for a virtual netdev and a queue
id of a leased queue, which then gets proxied to the underlying real
queue.
We have implemented support for this concept in netkit and tested the
latter against Nvidia ConnectX-6 (mlx5) as well as Broadcom BCM957504
(bnxt_en) 100G NICs. For more details see the individual patches.
====================
Link: https://patch.msgid.link/20260402231031.447597-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Similarly to the netif_mp_{open,close}_rxq handling for leased queues, proxy
the xsk_{reg,clear}_pool_at_qid via netif_get_rx_queue_lease_locked such
that in case a virtual netdev picked a leased rxq, the request gets through
to the real rxq in the physical netdev. The proxying is only relevant for
queue_id < dev->real_num_rx_queues since right now it's only supported for
rxqs.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260402231031.447597-10-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
xsk_rcv_check tests for inbound packets to see whether they match
the bound AF_XDP socket. Refactor the test into a small helper
xsk_dev_queue_valid and move the validation against xs->dev and
xs->queue_id there.
The fast-path case stays in place and allows for quick return in
xsk_dev_queue_valid. If it fails, the validation is extended to
check whether the AF_XDP socket is bound against a leased queue,
and if so, the test is redone.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260402231031.447597-9-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Cross-merge networking fixes after downstream PR (net-7.0-rc8).
Conflicts:
net/ipv6/seg6_iptunnel.c
c3812651b522f ("seg6: separate dst_cache for input and output paths in seg6 lwtunnel")
78723a62b969a ("seg6: add per-route tunnel source address")
https://lore.kernel.org/adZhwtOYfo-0ImSa@sirena.org.uk
net/ipv4/icmp.c
fde29fd934932 ("ipv4: icmp: fix null-ptr-deref in icmp_build_probe()")
d98adfbdd5c01 ("ipv4: drop ipv6_stub usage and use direct function calls")
https://lore.kernel.org/adO3dccqnr6j-BL9@sirena.org.uk
Adjacent changes:
drivers/net/ethernet/stmicro/stmmac/chain_mode.c
51f4e090b9f8 ("net: stmmac: fix integer underflow in chain mode")
6b4286e05508 ("net: stmmac: rename STMMAC_GET_ENTRY() -> STMMAC_NEXT_ENTRY()")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
AF_XDP bind currently accepts zero-copy pool configurations without
verifying that the device MTU fits into the usable frame space provided
by the UMEM chunk.
This becomes a problem since we started to respect tailroom which is
subtracted from chunk_size (among with headroom). 2k chunk size might
not provide enough space for standard 1500 MTU, so let us catch such
settings at bind time. Furthermore, validate whether underlying HW will
be able to satisfy configured MTU wrt XSK's frame size multiplied by
supported Rx buffer chain length (that is exposed via
net_device::xdp_zc_max_segs).
Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Reviewed-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-5-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Currently xp_assign_dev_shared() is missing XDP_USE_SG being propagated
to flags so set it in order to preserve mtu check that is supposed to be
done only when no multi-buffer setup is in picture.
Also, this flag has the same value as XDP_UMEM_TX_SW_CSUM so we could
get unexpected SG setups for software Tx checksums. Since csum flag is
UAPI, modify value of XDP_UMEM_SG_FLAG.
Fixes: d609f3d228a8 ("xsk: add multi-buffer support for sockets sharing umem")
Reviewed-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-4-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Multi-buffer XDP stores information about frags in skb_shared_info that
sits at the tailroom of a packet. The storage space is reserved via
xdp_data_hard_end():
((xdp)->data_hard_start + (xdp)->frame_sz - \
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
and then we refer to it via macro below:
static inline struct skb_shared_info *
xdp_get_shared_info_from_buff(const struct xdp_buff *xdp)
{
return (struct skb_shared_info *)xdp_data_hard_end(xdp);
}
Currently we do not respect this tailroom space in multi-buffer AF_XDP
ZC scenario. To address this, introduce xsk_pool_get_tailroom() and use
it within xsk_pool_get_rx_frame_size() which is used in ZC drivers to
configure length of HW Rx buffer.
Typically drivers on Rx Hw buffers side work on 128 byte alignment so
let us align the value returned by xsk_pool_get_rx_frame_size() in order
to avoid addressing this on driver's side. This addresses the fact that
idpf uses mentioned function *before* pool->dev being set so we were at
risk that after subtracting tailroom we would not provide 128-byte
aligned value to HW.
Since xsk_pool_get_rx_frame_size() is actively used in xsk_rcv_check()
and __xsk_rcv(), add a variant of this routine that will not include 128
byte alignment and therefore old behavior is preserved.
Reviewed-by: Björn Töpel <bjorn@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-3-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
The current headroom validation in xdp_umem_reg() could leave us with
insufficient space dedicated to even receive minimum-sized ethernet
frame. Furthermore if multi-buffer would come to play then
skb_shared_info stored at the end of XSK frame would be corrupted.
HW typically works with 128-aligned sizes so let us provide this value
as bare minimum.
Multi-buffer setting is known later in the configuration process so
besides accounting for 128 bytes, let us also take care of tailroom space
upfront.
Reviewed-by: Björn Töpel <bjorn@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Fixes: 99e3a236dd43 ("xsk: Add missing check on user supplied headroom size")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20260402154958.562179-2-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Commit f620af11c27b ("xsk: avoid double checking against rx queue being
full") addressed a case in copy mode, when working with multi-buffer
xdp_buff, where we were peeking onto XSK Rx queue twice, to find out if
there is a space to produce descriptors.
Adjust ZC path to follow the same principle.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/r/20260316140557.461288-1-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
Seems we have been carrying around repeated defines for unaligned mode
logic. Remove redundant ones.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20260313111931.438911-1-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Cross-merge BPF and other fixes after downstream PR.
No conflicts.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
inode->i_ino is being converted to a u64. sock.sk_ino (which caches the
inode number) must also be widened to avoid truncation on 32-bit
architectures where unsigned long is only 32 bits.
Change sk_ino from unsigned long to u64, and update the return type
of sock_i_ino() to match. Fix all format strings that print the
result of sock_i_ino() (%lu -> %llu), and widen the intermediate
variables and function parameters in the diag modules that were
using int to hold the inode number.
Note that the UAPI socket diag structures (inet_diag_msg.idiag_inode,
unix_diag_msg.udiag_ino, etc.) are all __u32 and cannot be changed
without breaking the ABI. The assignments to those fields will
silently truncate, which is the existing behavior.
Acked-by: Marc Kleine-Budde <mkl@pengutronix.de> # for net/can
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20260304-iino-u64-v3-3-2257ad83d372@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
|
|
AF_XDP should ensure that only a complete packet is sent to application.
In the zero-copy case, if the Rx queue gets full as fragments are being
enqueued, the remaining fragments are dropped.
For the multi-buffer case, add a check to ensure that the Rx queue has
enough space for all fragments of a packet before starting to enqueue
them.
Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Signed-off-by: Nikhil P. Rao <nikhil.rao@amd.com>
Link: https://patch.msgid.link/20260225000456.107806-3-nikhil.rao@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
After commit b692bf9a7543 ("xsk: Get rid of xdp_buff_xsk::xskb_list_node"),
the list_node field is reused for both the xskb pool list and the buffer
free list, this causes a buffer leak as described below.
xp_free() checks if a buffer is already on the free list using
list_empty(&xskb->list_node). When list_del() is used to remove a node
from the xskb pool list, it doesn't reinitialize the node pointers.
This means list_empty() will return false even after the node has been
removed, causing xp_free() to incorrectly skip adding the buffer to the
free list.
Fix this by using list_del_init() instead of list_del() in all fragment
handling paths, this ensures the list node is reinitialized after removal,
allowing the list_empty() to work correctly.
Fixes: b692bf9a7543 ("xsk: Get rid of xdp_buff_xsk::xskb_list_node")
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Nikhil P. Rao <nikhil.rao@amd.com>
Link: https://patch.msgid.link/20260225000456.107806-2-nikhil.rao@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Currently non-zc xsk rx path for multi-buffer case checks twice if xsk
rx queue has enough space for producing descriptors:
1.
if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) {
xs->rx_queue_full++;
return -ENOBUFS;
}
2.
__xsk_rcv_zc(xs, xskb, copied - meta_len, rem ? XDP_PKT_CONTD : 0);
-> err = xskq_prod_reserve_desc(xs->rx, addr, len, flags);
-> if (xskq_prod_is_full(q))
Second part is redundant as in 1. we already peeked onto rx queue and
checked that there is enough space to produce given amount of
descriptors.
Provide helper functions that will skip it and therefore optimize code.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/r/20260218150000.301176-1-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
Conversion performed via this Coccinelle script:
// SPDX-License-Identifier: GPL-2.0-only
// Options: --include-headers-for-types --all-includes --include-headers --keep-comments
virtual patch
@gfp depends on patch && !(file in "tools") && !(file in "samples")@
identifier ALLOC = {kmalloc_obj,kmalloc_objs,kmalloc_flex,
kzalloc_obj,kzalloc_objs,kzalloc_flex,
kvmalloc_obj,kvmalloc_objs,kvmalloc_flex,
kvzalloc_obj,kvzalloc_objs,kvzalloc_flex};
@@
ALLOC(...
- , GFP_KERNEL
)
$ make coccicheck MODE=patch COCCI=gfp.cocci
Build and boot tested x86_64 with Fedora 42's GCC and Clang:
Linux version 6.19.0+ (user@host) (gcc (GCC) 15.2.1 20260123 (Red Hat 15.2.1-7), GNU ld version 2.44-12.fc42) #1 SMP PREEMPT_DYNAMIC 1970-01-01
Linux version 6.19.0+ (user@host) (clang version 20.1.8 (Fedora 20.1.8-4.fc42), LLD 20.1.8) #1 SMP PREEMPT_DYNAMIC 1970-01-01
Signed-off-by: Kees Cook <kees@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
This converts some of the visually simpler cases that have been split
over multiple lines. I only did the ones that are easy to verify the
resulting diff by having just that final GFP_KERNEL argument on the next
line.
Somebody should probably do a proper coccinelle script for this, but for
me the trivial script actually resulted in an assertion failure in the
middle of the script. I probably had made it a bit _too_ trivial.
So after fighting that far a while I decided to just do some of the
syntactically simpler cases with variations of the previous 'sed'
scripts.
The more syntactically complex multi-line cases would mostly really want
whitespace cleanup anyway.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
This is the exact same thing as the 'alloc_obj()' version, only much
smaller because there are a lot fewer users of the *alloc_flex()
interface.
As with alloc_obj() version, this was done entirely with mindless brute
force, using the same script, except using 'flex' in the pattern rather
than 'objs*'.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
This was done entirely with mindless brute force, using
git grep -l '\<k[vmz]*alloc_objs*(.*, GFP_KERNEL)' |
xargs sed -i 's/\(alloc_objs*(.*\), GFP_KERNEL)/\1)/'
to convert the new alloc_obj() users that had a simple GFP_KERNEL
argument to just drop that argument.
Note that due to the extreme simplicity of the scripting, any slightly
more complex cases spread over multiple lines would not be triggered:
they definitely exist, but this covers the vast bulk of the cases, and
the resulting diff is also then easier to check automatically.
For the same reason the 'flex' versions will be done as a separate
conversion.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
This is the result of running the Coccinelle script from
scripts/coccinelle/api/kmalloc_objs.cocci. The script is designed to
avoid scalar types (which need careful case-by-case checking), and
instead replace kmalloc-family calls that allocate struct or union
object instances:
Single allocations: kmalloc(sizeof(TYPE), ...)
are replaced with: kmalloc_obj(TYPE, ...)
Array allocations: kmalloc_array(COUNT, sizeof(TYPE), ...)
are replaced with: kmalloc_objs(TYPE, COUNT, ...)
Flex array allocations: kmalloc(struct_size(PTR, FAM, COUNT), ...)
are replaced with: kmalloc_flex(*PTR, FAM, COUNT, ...)
(where TYPE may also be *VAR)
The resulting allocations no longer return "void *", instead returning
"TYPE *".
Signed-off-by: Kees Cook <kees@kernel.org>
|
|
This reverts commit 77b9c4a438fc66e2ab004c411056b3fb71a54f2c, reversing
changes made to 4515ec4ad58a37e70a9e1256c0b993958c9b7497:
931420a2fc36 ("selftests/net: Add netkit container tests")
ab771c938d9a ("selftests/net: Make NetDrvContEnv support queue leasing")
6be87fbb2776 ("selftests/net: Add env for container based tests")
61d99ce3dfc2 ("selftests/net: Add bpf skb forwarding program")
920da3634194 ("netkit: Add xsk support for af_xdp applications")
eef51113f8af ("netkit: Add netkit notifier to check for unregistering devices")
b5ef109d22d4 ("netkit: Implement rtnl_link_ops->alloc and ndo_queue_create")
b5c3fa4a0b16 ("netkit: Add single device mode for netkit")
0073d2fd679d ("xsk: Proxy pool management for leased queues")
1ecea95dd3b5 ("xsk: Extend xsk_rcv_check validation")
804bf334d08a ("net: Proxy netdev_queue_get_dma_dev for leased queues")
0caa9a8ddec3 ("net: Proxy net_mp_{open,close}_rxq for leased queues")
ff8889ff9107 ("net, ethtool: Disallow leased real rxqs to be resized")
9e2103f36110 ("net: Add lease info to queue-get response")
31127deddef4 ("net: Implement netdev_nl_queue_create_doit")
a5546e18f77c ("net: Add queue-create operation")
The series will conflict with io_uring work, and the code needs more
polish.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Similarly to the net_mp_{open,close}_rxq handling for leased queues, proxy
the xsk_{reg,clear}_pool_at_qid via netif_get_rx_queue_lease_locked such
that in case a virtual netdev picked a leased rxq, the request gets through
to the real rxq in the physical netdev. The proxying is only relevant for
queue_id < dev->real_num_rx_queues since right now its only supported for
rxqs.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260115082603.219152-9-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
xsk_rcv_check tests for inbound packets to see whether they match
the bound AF_XDP socket. Refactor the test into a small helper
xsk_dev_queue_valid and move the validation against xs->dev and
xs->queue_id there.
The fast-path case stays in place and allows for quick return in
xsk_dev_queue_valid. If it fails, the validation is extended to
check whether the AF_XDP socket is bound against a leased queue,
and if the case then the test is redone.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260115082603.219152-8-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Implement netdev_nl_queue_create_doit which creates a new rx queue in a
virtual netdev and then leases it to a rx queue in a physical netdev.
Example with ynl client:
# ./pyynl/cli.py \
--spec ~/netlink/specs/netdev.yaml \
--do queue-create \
--json '{"ifindex": 8, "type": "rx", "lease": {"ifindex": 4, "queue": {"type": "rx", "id": 15}}}'
{'id': 1}
Note that the netdevice locking order is always from the virtual to
the physical device.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20260115082603.219152-3-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
We (Paolo and I) noticed that in the sending path touching an extra
cacheline due to cq_cached_prod_lock will impact the performance. After
moving the lock from struct xsk_buff_pool to struct xsk_queue, the
performance is increased by ~5% which can be observed by xdpsock.
An alternative approach [1] can be using atomic_try_cmpxchg() to have the
same effect. But unfortunately I don't have evident performance numbers to
prove the atomic approach is better than the current patch. The advantage
is to save the contention time among multiple xsks sharing the same pool
while the disadvantage is losing good maintenance. The full discussion can
be found at the following link.
[1]: https://lore.kernel.org/all/20251128134601.54678-1-kerneljasonxing@gmail.com/
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Link: https://patch.msgid.link/20260104012125.44003-3-kerneljasonxing@gmail.com
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
In the shared umem mode with different queues or devices, either
uninitialized cq or fq is not allowed which was previously done in
xp_assign_dev_shared(). The patch advances the check at the beginning
so that 1) we can avoid a few memory allocation and stuff if cq or fq
is NULL, 2) it can be regarded as preparation for the next patch in
the series.
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Link: https://patch.msgid.link/20260104012125.44003-2-kerneljasonxing@gmail.com
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Conflicts:
net/xdp/xsk.c
0ebc27a4c67d ("xsk: avoid data corruption on cq descriptor number")
8da7bea7db69 ("xsk: add indirect call for xsk_destruct_skb")
30ed05adca4a ("xsk: use a smaller new lock for shared pool case")
https://lore.kernel.org/20251127105450.4a1665ec@canb.auug.org.au
https://lore.kernel.org/eb4eee14-7e24-4d1b-b312-e9ea738fefee@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Since commit 30f241fcf52a ("xsk: Fix immature cq descriptor
production"), the descriptor number is stored in skb control block and
xsk_cq_submit_addr_locked() relies on it to put the umem addrs onto
pool's completion queue.
skb control block shouldn't be used for this purpose as after transmit
xsk doesn't have control over it and other subsystems could use it. This
leads to the following kernel panic due to a NULL pointer dereference.
BUG: kernel NULL pointer dereference, address: 0000000000000000
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 0 P4D 0
Oops: Oops: 0000 [#1] SMP NOPTI
CPU: 2 UID: 1 PID: 927 Comm: p4xsk.bin Not tainted 6.16.12+deb14-cloud-amd64 #1 PREEMPT(lazy) Debian 6.16.12-1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
RIP: 0010:xsk_destruct_skb+0xd0/0x180
[...]
Call Trace:
<IRQ>
? napi_complete_done+0x7a/0x1a0
ip_rcv_core+0x1bb/0x340
ip_rcv+0x30/0x1f0
__netif_receive_skb_one_core+0x85/0xa0
process_backlog+0x87/0x130
__napi_poll+0x28/0x180
net_rx_action+0x339/0x420
handle_softirqs+0xdc/0x320
? handle_edge_irq+0x90/0x1e0
do_softirq.part.0+0x3b/0x60
</IRQ>
<TASK>
__local_bh_enable_ip+0x60/0x70
__dev_direct_xmit+0x14e/0x1f0
__xsk_generic_xmit+0x482/0xb70
? __remove_hrtimer+0x41/0xa0
? __xsk_generic_xmit+0x51/0xb70
? _raw_spin_unlock_irqrestore+0xe/0x40
xsk_sendmsg+0xda/0x1c0
__sys_sendto+0x1ee/0x200
__x64_sys_sendto+0x24/0x30
do_syscall_64+0x84/0x2f0
? __pfx_pollwake+0x10/0x10
? __rseq_handle_notify_resume+0xad/0x4c0
? restore_fpregs_from_fpstate+0x3c/0x90
? switch_fpu_return+0x5b/0xe0
? do_syscall_64+0x204/0x2f0
? do_syscall_64+0x204/0x2f0
? do_syscall_64+0x204/0x2f0
entry_SYSCALL_64_after_hwframe+0x76/0x7e
</TASK>
[...]
Kernel panic - not syncing: Fatal exception in interrupt
Kernel Offset: 0x1c000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
Instead use the skb destructor_arg pointer along with pointer tagging.
As pointers are always aligned to 8B, use the bottom bit to indicate
whether this a single address or an allocated struct containing several
addresses.
Fixes: 30f241fcf52a ("xsk: Fix immature cq descriptor production")
Closes: https://lore.kernel.org/netdev/0435b904-f44f-48f8-afb0-68868474bf1c@nop.hu/
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Fernando Fernandez Mancera <fmancera@suse.de>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20251124171409.3845-1-fmancera@suse.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Since Eric proposed an idea about adding indirect call wrappers for
UDP and managed to see a huge improvement[1], the same situation can
also be applied in xsk scenario.
This patch adds an indirect call for xsk and helps current copy mode
improve the performance by around 1% stably which was observed with
IXGBE at 10Gb/sec loaded. If the throughput grows, the positive effect
will be magnified. I applied this patch on top of batch xmit series[2],
and was able to see <5% improvement from our internal application
which is a little bit unstable though.
Use INDIRECT wrappers to keep xsk_destruct_skb static as it used to
be when the mitigation config is off.
Be aware of the freeing path that can be very hot since the frequency
can reach around 2,000,000 times per second with the xdpsock test.
[1]: https://lore.kernel.org/netdev/20251006193103.2684156-2-edumazet@google.com/
[2]: https://lore.kernel.org/all/20251021131209.41491-1-kerneljasonxing@gmail.com/
Suggested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/20251031103328.95468-1-kerneljasonxing@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Move NETDEV_XDP_ACT_ZC into xdp_sock_drv.h header such that external code
can reuse it, and rename it into more generic NETDEV_XDP_ACT_XSK.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Co-developed-by: David Wei <dw@davidwei.uk>
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20251031212103.310683-7-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Update all struct proto_ops bind() callback function prototypes from
"struct sockaddr *" to "struct sockaddr_unsized *" to avoid lying to the
compiler about object sizes. Calls into struct proto handlers gain casts
that will be removed in the struct proto conversion patch.
No binary changes expected.
Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20251104002617.2752303-2-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
- Split cq_lock into two smaller locks: cq_prod_lock and
cq_cached_prod_lock
- Avoid disabling/enabling interrupts in the hot xmit path
In either xsk_cq_cancel_locked() or xsk_cq_reserve_locked() function,
the race condition is only between multiple xsks sharing the same
pool. They are all in the process context rather than interrupt context,
so now the small lock named cq_cached_prod_lock can be used without
handling interrupts.
While cq_cached_prod_lock ensures the exclusive modification of
@cached_prod, cq_prod_lock in xsk_cq_submit_addr_locked() only cares
about @producer and corresponding @desc. Both of them don't necessarily
be consistent with @cached_prod protected by cq_cached_prod_lock.
That's the reason why the previous big lock can be split into two
smaller ones. Please note that SPSC rule is all about the global state
of producer and consumer that can affect both layers instead of local
or cached ones.
Frequently disabling and enabling interrupt are very time consuming
in some cases, especially in a per-descriptor granularity, which now
can be avoided after this optimization, even when the pool is shared by
multiple xsks.
With this patch, the performance number[1] could go from 1,872,565 pps
to 1,961,009 pps. It's a minor rise of around 5%.
[1]: taskset -c 1 ./xdpsock -i enp2s0f1 -q 0 -t -S -s 64
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20251030000646.18859-3-kerneljasonxing@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
The commit ac98d8aab61b ("xsk: wire upp Tx zero-copy functions")
originally introducing this lock put the deletion process in the
sk_destruct which can run in irq context obviously, so the
xxx_irqsave()/xxx_irqrestore() pair was used. But later another
commit 541d7fdd7694 ("xsk: proper AF_XDP socket teardown ordering")
moved the deletion into xsk_release() that only happens in process
context. It means that since this commit, it doesn't necessarily
need that pair.
Now, there are two places that use this xsk_tx_list_lock and only
run in the process context. So avoid manipulating the irq then.
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20251030000646.18859-2-kerneljasonxing@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
Turned out certain clearly invalid values passed in xdp_desc from
userspace can pass xp_{,un}aligned_validate_desc() and then lead
to UBs or just invalid frames to be queued for xmit.
desc->len close to ``U32_MAX`` with a non-zero pool->tx_metadata_len
can cause positive integer overflow and wraparound, the same way low
enough desc->addr with a non-zero pool->tx_metadata_len can cause
negative integer overflow. Both scenarios can then pass the
validation successfully.
This doesn't happen with valid XSk applications, but can be used
to perform attacks.
Always promote desc->len to ``u64`` first to exclude positive
overflows of it. Use explicit check_{add,sub}_overflow() when
validating desc->addr (which is ``u64`` already).
bloat-o-meter reports a little growth of the code size:
add/remove: 0/0 grow/shrink: 2/1 up/down: 60/-16 (44)
Function old new delta
xskq_cons_peek_desc 299 330 +31
xsk_tx_peek_release_desc_batch 973 1002 +29
xsk_generic_xmit 3148 3132 -16
but hopefully this doesn't hurt the performance much.
Fixes: 341ac980eab9 ("xsk: Support tx_metadata_len")
Cc: stable@vger.kernel.org # 6.8+
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20251008165659.4141318-1-aleksander.lobakin@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
xsk_build_skb() has gone wild with its size and one of the things we can
do about it is to pull out a branch that takes care of metadata handling
and make it a separate function.
While at it, let us add metadata SW support for devices supporting
IFF_TX_SKB_NO_LINEAR flag, that happen to have separate logic for
building skb in xsk's generic xmit path.
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250925160009.2474816-4-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Instead of using auxiliary boolean that tracks if we are at first frag
when gathering all elements of skb, same functionality can be achieved
with checking if skb_shared_info::nr_frags is 0.
Remove @first_frag but be careful around xsk_build_skb_zerocopy() and
NULL the skb pointer when it failed so that common error path does not
incorrectly interpret it during decision whether to call kfree_skb().
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250925160009.2474816-3-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
We are unnecessarily setting a bunch of skb fields per each processed
descriptor, which is redundant for fragmented frames.
Let us set these respective members for first fragment only. To address
both paths that we have within xsk_build_skb(), move assignments onto
xsk_set_destructor_arg() and rename it to xsk_skb_init_misc().
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250925160009.2474816-2-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Eryk reported an issue that I have put under Closes: tag, related to
umem addrs being prematurely produced onto pool's completion queue.
Let us make the skb's destructor responsible for producing all addrs
that given skb used.
Commit from fixes tag introduced the buggy behavior, it was not broken
from day 1, but rather when xsk multi-buffer got introduced.
In order to mitigate performance impact as much as possible, mimic the
linear and frag parts within skb by storing the first address from XSK
descriptor at sk_buff::destructor_arg. For fragments, store them at ::cb
via list. The nodes that will go onto list will be allocated via
kmem_cache. xsk_destruct_skb() will consume address stored at
::destructor_arg and optionally go through list from ::cb, if count of
descriptors associated with this particular skb is bigger than 1.
Previous approach where whole array for storing UMEM addresses from XSK
descriptors was pre-allocated during first fragment processing yielded
too big performance regression for 64b traffic. In current approach
impact is much reduced on my tests and for jumbo frames I observed
traffic being slower by at most 9%.
Magnus suggested to have this way of processing special cased for
XDP_SHARED_UMEM, so we would identify this during bind and set different
hooks for 'backpressure mechanism' on CQ and for skb destructor, but
given that results looked promising on my side I decided to have a
single data path for XSK generic Tx. I suppose other auxiliary stuff
would have to land as well in order to make it work.
Fixes: b7f72a30e9ac ("xsk: introduce wrappers and helpers for supporting multi-buffer in Tx path")
Reported-by: Eryk Kubanski <e.kubanski@partner.samsung.com>
Closes: https://lore.kernel.org/netdev/20250530103456.53564-1-e.kubanski@partner.samsung.com/
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/r/20250904194907.2342177-1-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
This patch provides a setsockopt method to let applications leverage to
adjust how many descs to be handled at most in one send syscall. It
mitigates the situation where the default value (32) that is too small
leads to higher frequency of triggering send syscall.
Considering the prosperity/complexity the applications have, there is no
absolutely ideal suggestion fitting all cases. So keep 32 as its default
value like before.
The patch does the following things:
- Add XDP_MAX_TX_SKB_BUDGET socket option.
- Set max_tx_budget to 32 by default in the initialization phase as a
per-socket granular control.
- Set the range of max_tx_budget as [32, xs->tx->nentries].
The idea behind this comes out of real workloads in production. We use a
user-level stack with xsk support to accelerate sending packets and
minimize triggering syscalls. When the packets are aggregated, it's not
hard to hit the upper bound (namely, 32). The moment user-space stack
fetches the -EAGAIN error number passed from sendto(), it will loop to try
again until all the expected descs from tx ring are sent out to the driver.
Enlarging the XDP_MAX_TX_SKB_BUDGET value contributes to less frequency of
sendto() and higher throughput/PPS.
Here is what I did in production, along with some numbers as follows:
For one application I saw lately, I suggested using 128 as max_tx_budget
because I saw two limitations without changing any default configuration:
1) XDP_MAX_TX_SKB_BUDGET, 2) socket sndbuf which is 212992 decided by
net.core.wmem_default. As to XDP_MAX_TX_SKB_BUDGET, the scenario behind
this was I counted how many descs are transmitted to the driver at one
time of sendto() based on [1] patch and then I calculated the
possibility of hitting the upper bound. Finally I chose 128 as a
suitable value because 1) it covers most of the cases, 2) a higher
number would not bring evident results. After twisting the parameters,
a stable improvement of around 4% for both PPS and throughput and less
resources consumption were found to be observed by strace -c -p xxx:
1) %time was decreased by 7.8%
2) error counter was decreased from 18367 to 572
[1]: https://lore.kernel.org/all/20250619093641.70700-1-kerneljasonxing@gmail.com/
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20250704160138.48677-1-kerneljasonxing@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
|
|
For afxdp, the return value of sendto() syscall doesn't reflect how many
descs handled in the kernel. One of use cases is that when user-space
application tries to know the number of transmitted skbs and then decides
if it continues to send, say, is it stopped due to max tx budget?
The following formular can be used after sending to learn how many
skbs/descs the kernel takes care of:
tx_queue.consumers_before - tx_queue.consumers_after
Prior to the current patch, in non-zc mode, the consumer of tx queue is
not immediately updated at the end of each sendto syscall when error
occurs, which leads to the consumer value out-of-dated from the perspective
of user space. So this patch requires store operation to pass the cached
value to the shared value to handle the problem.
More than those explicit errors appearing in the while() loop in
__xsk_generic_xmit(), there are a few possible error cases that might
be neglected in the following call trace:
__xsk_generic_xmit()
xskq_cons_peek_desc()
xskq_cons_read_desc()
xskq_cons_is_valid_desc()
It will also cause the premature exit in the while() loop even if not
all the descs are consumed.
Based on the above analysis, using @sent_frame could cover all the possible
cases where it might lead to out-of-dated global state of consumer after
finishing __xsk_generic_xmit().
The patch also adds a common helper __xsk_tx_release() to keep align
with the zc mode usage in xsk_tx_release().
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250703141712.33190-2-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Difference between sock_i_uid() and sk_uid() is that
after sock_orphan(), sock_i_uid() returns GLOBAL_ROOT_UID
while sk_uid() returns the last cached sk->sk_uid value.
None of sock_i_uid() callers care about this.
Use sk_uid() which is much faster and inlined.
Note that diag/dump users are calling sock_i_ino() and
can not see the full benefit yet.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Reviewed-by: Maciej Żenczykowski <maze@google.com>
Link: https://patch.msgid.link/20250620133001.4090592-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Cross-merge networking fixes after downstream PR (net-6.15-rc8).
Conflicts:
80f2ab46c2ee ("irdma: free iwdev->rf after removing MSI-X")
4bcc063939a5 ("ice, irdma: fix an off by one in error handling code")
c24a65b6a27c ("iidc/ice/irdma: Update IDC to support multiple consumers")
https://lore.kernel.org/20250513130630.280ee6c5@canb.auug.org.au
No extra adjacent changes.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Commit 5ef44b3cb43b ("xsk: Bring back busy polling support") fixed the
busy polling support in xsk for XDP_ZEROCOPY after it was broken in
commit 86e25f40aa1e ("net: napi: Add napi_config"). The busy polling
support with XDP_COPY remained broken since the napi_id setup in
xsk_rcv_check was removed.
Bring back the setup of napi_id for XDP_COPY so socket level SO_BUSYPOLL
can be used to poll the underlying napi.
Do the setup of napi_id for XDP_COPY in xsk_bind, as it is done
currently for XDP_ZEROCOPY. The setup of napi_id for XDP_COPY in
xsk_bind is safe because xsk_rcv_check checks that the rx queue at which
the packet arrives is equal to the queue_id that was supplied in bind.
This is done for both XDP_COPY and XDP_ZEROCOPY mode.
Tested using AF_XDP support in virtio-net by running the xsk_rr AF_XDP
benchmarking tool shared here:
https://lore.kernel.org/all/20250320163523.3501305-1-skhawaja@google.com/T/
Enabled socket busy polling using following commands in qemu,
```
sudo ethtool -L eth0 combined 1
echo 400 | sudo tee /proc/sys/net/core/busy_read
echo 100 | sudo tee /sys/class/net/eth0/napi_defer_hard_irqs
echo 15000 | sudo tee /sys/class/net/eth0/gro_flush_timeout
```
Fixes: 5ef44b3cb43b ("xsk: Bring back busy polling support")
Signed-off-by: Samiullah Khawaja <skhawaja@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Cross-merge networking fixes after downstream PR (net-6.15-rc5).
No conflicts or adjacent changes.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Move rx_lock from xsk_socket to xsk_buff_pool.
Fix synchronization for shared umem mode in
generic RX path where multiple sockets share
single xsk_buff_pool.
RX queue is exclusive to xsk_socket, while FILL
queue can be shared between multiple sockets.
This could result in race condition where two
CPU cores access RX path of two different sockets
sharing the same umem.
Protect both queues by acquiring spinlock in shared
xsk_buff_pool.
Lock contention may be minimized in the future by some
per-thread FQ buffering.
It's safe and necessary to move spin_lock_bh(rx_lock)
after xsk_rcv_check():
* xs->pool and spinlock_init is synchronized by
xsk_bind() -> xsk_is_bound() memory barriers.
* xsk_rcv_check() may return true at the moment
of xsk_release() or xsk_unbind_dev(),
however this will not cause any data races or
race conditions. xsk_unbind_dev() removes xdp
socket from all maps and waits for completion
of all outstanding rx operations. Packets in
RX path will either complete safely or drop.
Signed-off-by: Eryk Kubanski <e.kubanski@partner.samsung.com>
Fixes: bf0bdd1343efb ("xdp: fix race on generic receive path")
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://patch.msgid.link/20250416101908.10919-1-e.kubanski@partner.samsung.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Read accesses go via xsk_get_pool_from_qid(), the call coming
from the core and gve look safe (other "ops locked" drivers
don't support XSK).
Write accesses go via xsk_reg_pool_at_qid() and xsk_clear_pool_at_qid().
Former is already under the ops lock, latter is not (both coming from
the workqueue via xp_clear_dev() and NETDEV_UNREGISTER via xsk_notifier()).
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250408195956.412733-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
