Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 673 insertions, 0 deletions

diff --git a/io_uring/opdef.c b/io_uring/opdef.c
new file mode 100644
index 000000000..cca7c5b55
--- /dev/null
+++ b/io_uring/opdef.c
@@ -0,0 +1,673 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * io_uring opcode handling table
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/io_uring.h>
+
+#include "io_uring.h"
+#include "opdef.h"
+#include "refs.h"
+#include "tctx.h"
+#include "sqpoll.h"
+#include "fdinfo.h"
+#include "kbuf.h"
+#include "rsrc.h"
+
+#include "xattr.h"
+#include "nop.h"
+#include "fs.h"
+#include "splice.h"
+#include "sync.h"
+#include "advise.h"
+#include "openclose.h"
+#include "uring_cmd.h"
+#include "epoll.h"
+#include "statx.h"
+#include "net.h"
+#include "msg_ring.h"
+#include "timeout.h"
+#include "poll.h"
+#include "cancel.h"
+#include "rw.h"
+
+static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags)
+{
+	WARN_ON_ONCE(1);
+	return -ECANCELED;
+}
+
+static __maybe_unused int io_eopnotsupp_prep(struct io_kiocb *kiocb,
+					     const struct io_uring_sqe *sqe)
+{
+	return -EOPNOTSUPP;
+}
+
+const struct io_issue_def io_issue_defs[] = {
+	[IORING_OP_NOP] = {
+		.audit_skip		= 1,
+		.iopoll			= 1,
+		.prep			= io_nop_prep,
+		.issue			= io_nop,
+	},
+	[IORING_OP_READV] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.buffer_select		= 1,
+		.plug			= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+		.iopoll			= 1,
+		.iopoll_queue		= 1,
+		.prep			= io_prep_rw,
+		.issue			= io_read,
+	},
+	[IORING_OP_WRITEV] = {
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
+		.plug			= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+		.iopoll			= 1,
+		.iopoll_queue		= 1,
+		.prep			= io_prep_rw,
+		.issue			= io_write,
+	},
+	[IORING_OP_FSYNC] = {
+		.needs_file		= 1,
+		.audit_skip		= 1,
+		.prep			= io_fsync_prep,
+		.issue			= io_fsync,
+	},
+	[IORING_OP_READ_FIXED] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.plug			= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+		.iopoll			= 1,
+		.iopoll_queue		= 1,
+		.prep			= io_prep_rw,
+		.issue			= io_read,
+	},
+	[IORING_OP_WRITE_FIXED] = {
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
+		.plug			= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+		.iopoll			= 1,
+		.iopoll_queue		= 1,
+		.prep			= io_prep_rw,
+		.issue			= io_write,
+	},
+	[IORING_OP_POLL_ADD] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.audit_skip		= 1,
+		.prep			= io_poll_add_prep,
+		.issue			= io_poll_add,
+	},
+	[IORING_OP_POLL_REMOVE] = {
+		.audit_skip		= 1,
+		.prep			= io_poll_remove_prep,
+		.issue			= io_poll_remove,
+	},
+	[IORING_OP_SYNC_FILE_RANGE] = {
+		.needs_file		= 1,
+		.audit_skip		= 1,
+		.prep			= io_sfr_prep,
+		.issue			= io_sync_file_range,
+	},
+	[IORING_OP_SENDMSG] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
+		.ioprio			= 1,
+		.manual_alloc		= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_sendmsg_prep,
+		.issue			= io_sendmsg,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+	[IORING_OP_RECVMSG] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.buffer_select		= 1,
+		.ioprio			= 1,
+		.manual_alloc		= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_recvmsg_prep,
+		.issue			= io_recvmsg,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+	[IORING_OP_TIMEOUT] = {
+		.audit_skip		= 1,
+		.prep			= io_timeout_prep,
+		.issue			= io_timeout,
+	},
+	[IORING_OP_TIMEOUT_REMOVE] = {
+		/* used by timeout updates' prep() */
+		.audit_skip		= 1,
+		.prep			= io_timeout_remove_prep,
+		.issue			= io_timeout_remove,
+	},
+	[IORING_OP_ACCEPT] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.poll_exclusive		= 1,
+		.ioprio			= 1,	/* used for flags */
+#if defined(CONFIG_NET)
+		.prep			= io_accept_prep,
+		.issue			= io_accept,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+	[IORING_OP_ASYNC_CANCEL] = {
+		.audit_skip		= 1,
+		.prep			= io_async_cancel_prep,
+		.issue			= io_async_cancel,
+	},
+	[IORING_OP_LINK_TIMEOUT] = {
+		.audit_skip		= 1,
+		.prep			= io_link_timeout_prep,
+		.issue			= io_no_issue,
+	},
+	[IORING_OP_CONNECT] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_connect_prep,
+		.issue			= io_connect,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+	[IORING_OP_FALLOCATE] = {
+		.needs_file		= 1,
+		.prep			= io_fallocate_prep,
+		.issue			= io_fallocate,
+	},
+	[IORING_OP_OPENAT] = {
+		.prep			= io_openat_prep,
+		.issue			= io_openat,
+	},
+	[IORING_OP_CLOSE] = {
+		.prep			= io_close_prep,
+		.issue			= io_close,
+	},
+	[IORING_OP_FILES_UPDATE] = {
+		.audit_skip		= 1,
+		.iopoll			= 1,
+		.prep			= io_files_update_prep,
+		.issue			= io_files_update,
+	},
+	[IORING_OP_STATX] = {
+		.audit_skip		= 1,
+		.prep			= io_statx_prep,
+		.issue			= io_statx,
+	},
+	[IORING_OP_READ] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.buffer_select		= 1,
+		.plug			= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+		.iopoll			= 1,
+		.iopoll_queue		= 1,
+		.prep			= io_prep_rw,
+		.issue			= io_read,
+	},
+	[IORING_OP_WRITE] = {
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
+		.plug			= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+		.iopoll			= 1,
+		.iopoll_queue		= 1,
+		.prep			= io_prep_rw,
+		.issue			= io_write,
+	},
+	[IORING_OP_FADVISE] = {
+		.needs_file		= 1,
+		.audit_skip		= 1,
+		.prep			= io_fadvise_prep,
+		.issue			= io_fadvise,
+	},
+	[IORING_OP_MADVISE] = {
+		.audit_skip		= 1,
+		.prep			= io_madvise_prep,
+		.issue			= io_madvise,
+	},
+	[IORING_OP_SEND] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+		.manual_alloc		= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_sendmsg_prep,
+		.issue			= io_send,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+	[IORING_OP_RECV] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.buffer_select		= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_recvmsg_prep,
+		.issue			= io_recv,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+	[IORING_OP_OPENAT2] = {
+		.prep			= io_openat2_prep,
+		.issue			= io_openat2,
+	},
+	[IORING_OP_EPOLL_CTL] = {
+		.unbound_nonreg_file	= 1,
+		.audit_skip		= 1,
+#if defined(CONFIG_EPOLL)
+		.prep			= io_epoll_ctl_prep,
+		.issue			= io_epoll_ctl,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+	[IORING_OP_SPLICE] = {
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.audit_skip		= 1,
+		.prep			= io_splice_prep,
+		.issue			= io_splice,
+	},
+	[IORING_OP_PROVIDE_BUFFERS] = {
+		.audit_skip		= 1,
+		.iopoll			= 1,
+		.prep			= io_provide_buffers_prep,
+		.issue			= io_provide_buffers,
+	},
+	[IORING_OP_REMOVE_BUFFERS] = {
+		.audit_skip		= 1,
+		.iopoll			= 1,
+		.prep			= io_remove_buffers_prep,
+		.issue			= io_remove_buffers,
+	},
+	[IORING_OP_TEE] = {
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.audit_skip		= 1,
+		.prep			= io_tee_prep,
+		.issue			= io_tee,
+	},
+	[IORING_OP_SHUTDOWN] = {
+		.needs_file		= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_shutdown_prep,
+		.issue			= io_shutdown,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+	[IORING_OP_RENAMEAT] = {
+		.prep			= io_renameat_prep,
+		.issue			= io_renameat,
+	},
+	[IORING_OP_UNLINKAT] = {
+		.prep			= io_unlinkat_prep,
+		.issue			= io_unlinkat,
+	},
+	[IORING_OP_MKDIRAT] = {
+		.prep			= io_mkdirat_prep,
+		.issue			= io_mkdirat,
+	},
+	[IORING_OP_SYMLINKAT] = {
+		.prep			= io_symlinkat_prep,
+		.issue			= io_symlinkat,
+	},
+	[IORING_OP_LINKAT] = {
+		.prep			= io_linkat_prep,
+		.issue			= io_linkat,
+	},
+	[IORING_OP_MSG_RING] = {
+		.needs_file		= 1,
+		.iopoll			= 1,
+		.prep			= io_msg_ring_prep,
+		.issue			= io_msg_ring,
+	},
+	[IORING_OP_FSETXATTR] = {
+		.needs_file = 1,
+		.prep			= io_fsetxattr_prep,
+		.issue			= io_fsetxattr,
+	},
+	[IORING_OP_SETXATTR] = {
+		.prep			= io_setxattr_prep,
+		.issue			= io_setxattr,
+	},
+	[IORING_OP_FGETXATTR] = {
+		.needs_file = 1,
+		.prep			= io_fgetxattr_prep,
+		.issue			= io_fgetxattr,
+	},
+	[IORING_OP_GETXATTR] = {
+		.prep			= io_getxattr_prep,
+		.issue			= io_getxattr,
+	},
+	[IORING_OP_SOCKET] = {
+		.audit_skip		= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_socket_prep,
+		.issue			= io_socket,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+	[IORING_OP_URING_CMD] = {
+		.needs_file		= 1,
+		.plug			= 1,
+		.iopoll			= 1,
+		.iopoll_queue		= 1,
+		.prep			= io_uring_cmd_prep,
+		.issue			= io_uring_cmd,
+	},
+	[IORING_OP_SEND_ZC] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
+		.audit_skip		= 1,
+		.ioprio			= 1,
+		.manual_alloc		= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_send_zc_prep,
+		.issue			= io_send_zc,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+	[IORING_OP_SENDMSG_ZC] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollout		= 1,
+		.ioprio			= 1,
+		.manual_alloc		= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_send_zc_prep,
+		.issue			= io_sendmsg_zc,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+};
+
+
+const struct io_cold_def io_cold_defs[] = {
+	[IORING_OP_NOP] = {
+		.name			= "NOP",
+	},
+	[IORING_OP_READV] = {
+		.async_size		= sizeof(struct io_async_rw),
+		.name			= "READV",
+		.prep_async		= io_readv_prep_async,
+		.cleanup		= io_readv_writev_cleanup,
+		.fail			= io_rw_fail,
+	},
+	[IORING_OP_WRITEV] = {
+		.async_size		= sizeof(struct io_async_rw),
+		.name			= "WRITEV",
+		.prep_async		= io_writev_prep_async,
+		.cleanup		= io_readv_writev_cleanup,
+		.fail			= io_rw_fail,
+	},
+	[IORING_OP_FSYNC] = {
+		.name			= "FSYNC",
+	},
+	[IORING_OP_READ_FIXED] = {
+		.async_size		= sizeof(struct io_async_rw),
+		.name			= "READ_FIXED",
+		.fail			= io_rw_fail,
+	},
+	[IORING_OP_WRITE_FIXED] = {
+		.async_size		= sizeof(struct io_async_rw),
+		.name			= "WRITE_FIXED",
+		.fail			= io_rw_fail,
+	},
+	[IORING_OP_POLL_ADD] = {
+		.name			= "POLL_ADD",
+	},
+	[IORING_OP_POLL_REMOVE] = {
+		.name			= "POLL_REMOVE",
+	},
+	[IORING_OP_SYNC_FILE_RANGE] = {
+		.name			= "SYNC_FILE_RANGE",
+	},
+	[IORING_OP_SENDMSG] = {
+		.name			= "SENDMSG",
+#if defined(CONFIG_NET)
+		.async_size		= sizeof(struct io_async_msghdr),
+		.prep_async		= io_sendmsg_prep_async,
+		.cleanup		= io_sendmsg_recvmsg_cleanup,
+		.fail			= io_sendrecv_fail,
+#endif
+	},
+	[IORING_OP_RECVMSG] = {
+		.name			= "RECVMSG",
+#if defined(CONFIG_NET)
+		.async_size		= sizeof(struct io_async_msghdr),
+		.prep_async		= io_recvmsg_prep_async,
+		.cleanup		= io_sendmsg_recvmsg_cleanup,
+		.fail			= io_sendrecv_fail,
+#endif
+	},
+	[IORING_OP_TIMEOUT] = {
+		.async_size		= sizeof(struct io_timeout_data),
+		.name			= "TIMEOUT",
+	},
+	[IORING_OP_TIMEOUT_REMOVE] = {
+		.name			= "TIMEOUT_REMOVE",
+	},
+	[IORING_OP_ACCEPT] = {
+		.name			= "ACCEPT",
+	},
+	[IORING_OP_ASYNC_CANCEL] = {
+		.name			= "ASYNC_CANCEL",
+	},
+	[IORING_OP_LINK_TIMEOUT] = {
+		.async_size		= sizeof(struct io_timeout_data),
+		.name			= "LINK_TIMEOUT",
+	},
+	[IORING_OP_CONNECT] = {
+		.name			= "CONNECT",
+#if defined(CONFIG_NET)
+		.async_size		= sizeof(struct io_async_connect),
+		.prep_async		= io_connect_prep_async,
+#endif
+	},
+	[IORING_OP_FALLOCATE] = {
+		.name			= "FALLOCATE",
+	},
+	[IORING_OP_OPENAT] = {
+		.name			= "OPENAT",
+		.cleanup		= io_open_cleanup,
+	},
+	[IORING_OP_CLOSE] = {
+		.name			= "CLOSE",
+	},
+	[IORING_OP_FILES_UPDATE] = {
+		.name			= "FILES_UPDATE",
+	},
+	[IORING_OP_STATX] = {
+		.name			= "STATX",
+		.cleanup		= io_statx_cleanup,
+	},
+	[IORING_OP_READ] = {
+		.async_size		= sizeof(struct io_async_rw),
+		.name			= "READ",
+		.fail			= io_rw_fail,
+	},
+	[IORING_OP_WRITE] = {
+		.async_size		= sizeof(struct io_async_rw),
+		.name			= "WRITE",
+		.fail			= io_rw_fail,
+	},
+	[IORING_OP_FADVISE] = {
+		.name			= "FADVISE",
+	},
+	[IORING_OP_MADVISE] = {
+		.name			= "MADVISE",
+	},
+	[IORING_OP_SEND] = {
+		.name			= "SEND",
+#if defined(CONFIG_NET)
+		.async_size		= sizeof(struct io_async_msghdr),
+		.fail			= io_sendrecv_fail,
+		.prep_async		= io_send_prep_async,
+#endif
+	},
+	[IORING_OP_RECV] = {
+		.name			= "RECV",
+#if defined(CONFIG_NET)
+		.fail			= io_sendrecv_fail,
+#endif
+	},
+	[IORING_OP_OPENAT2] = {
+		.name			= "OPENAT2",
+		.cleanup		= io_open_cleanup,
+	},
+	[IORING_OP_EPOLL_CTL] = {
+		.name			= "EPOLL",
+	},
+	[IORING_OP_SPLICE] = {
+		.name			= "SPLICE",
+	},
+	[IORING_OP_PROVIDE_BUFFERS] = {
+		.name			= "PROVIDE_BUFFERS",
+	},
+	[IORING_OP_REMOVE_BUFFERS] = {
+		.name			= "REMOVE_BUFFERS",
+	},
+	[IORING_OP_TEE] = {
+		.name			= "TEE",
+	},
+	[IORING_OP_SHUTDOWN] = {
+		.name			= "SHUTDOWN",
+	},
+	[IORING_OP_RENAMEAT] = {
+		.name			= "RENAMEAT",
+		.cleanup		= io_renameat_cleanup,
+	},
+	[IORING_OP_UNLINKAT] = {
+		.name			= "UNLINKAT",
+		.cleanup		= io_unlinkat_cleanup,
+	},
+	[IORING_OP_MKDIRAT] = {
+		.name			= "MKDIRAT",
+		.cleanup		= io_mkdirat_cleanup,
+	},
+	[IORING_OP_SYMLINKAT] = {
+		.name			= "SYMLINKAT",
+		.cleanup		= io_link_cleanup,
+	},
+	[IORING_OP_LINKAT] = {
+		.name			= "LINKAT",
+		.cleanup		= io_link_cleanup,
+	},
+	[IORING_OP_MSG_RING] = {
+		.name			= "MSG_RING",
+		.cleanup		= io_msg_ring_cleanup,
+	},
+	[IORING_OP_FSETXATTR] = {
+		.name			= "FSETXATTR",
+		.cleanup		= io_xattr_cleanup,
+	},
+	[IORING_OP_SETXATTR] = {
+		.name			= "SETXATTR",
+		.cleanup		= io_xattr_cleanup,
+	},
+	[IORING_OP_FGETXATTR] = {
+		.name			= "FGETXATTR",
+		.cleanup		= io_xattr_cleanup,
+	},
+	[IORING_OP_GETXATTR] = {
+		.name			= "GETXATTR",
+		.cleanup		= io_xattr_cleanup,
+	},
+	[IORING_OP_SOCKET] = {
+		.name			= "SOCKET",
+	},
+	[IORING_OP_URING_CMD] = {
+		.name			= "URING_CMD",
+		.async_size		= uring_cmd_pdu_size(1),
+		.prep_async		= io_uring_cmd_prep_async,
+	},
+	[IORING_OP_SEND_ZC] = {
+		.name			= "SEND_ZC",
+#if defined(CONFIG_NET)
+		.async_size		= sizeof(struct io_async_msghdr),
+		.prep_async		= io_send_prep_async,
+		.cleanup		= io_send_zc_cleanup,
+		.fail			= io_sendrecv_fail,
+#endif
+	},
+	[IORING_OP_SENDMSG_ZC] = {
+		.name			= "SENDMSG_ZC",
+#if defined(CONFIG_NET)
+		.async_size		= sizeof(struct io_async_msghdr),
+		.prep_async		= io_sendmsg_prep_async,
+		.cleanup		= io_send_zc_cleanup,
+		.fail			= io_sendrecv_fail,
+#endif
+	},
+};
+
+const char *io_uring_get_opcode(u8 opcode)
+{
+	if (opcode < IORING_OP_LAST)
+		return io_cold_defs[opcode].name;
+	return "INVALID";
+}
+
+void __init io_uring_optable_init(void)
+{
+	int i;
+
+	BUILD_BUG_ON(ARRAY_SIZE(io_cold_defs) != IORING_OP_LAST);
+	BUILD_BUG_ON(ARRAY_SIZE(io_issue_defs) != IORING_OP_LAST);
+
+	for (i = 0; i < ARRAY_SIZE(io_issue_defs); i++) {
+		BUG_ON(!io_issue_defs[i].prep);
+		if (io_issue_defs[i].prep != io_eopnotsupp_prep)
+			BUG_ON(!io_issue_defs[i].issue);
+		WARN_ON_ONCE(!io_cold_defs[i].name);
+	}
+}