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, 420 insertions, 0 deletions

diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
new file mode 100644
index 000000000..0119d3f1a
--- /dev/null
+++ b/io_uring/sqpoll.c
@@ -0,0 +1,420 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Contains the core associated with submission side polling of the SQ
+ * ring, offloading submissions from the application to a kernel thread.
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/audit.h>
+#include <linux/security.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "sqpoll.h"
+
+#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
+
+enum {
+	IO_SQ_THREAD_SHOULD_STOP = 0,
+	IO_SQ_THREAD_SHOULD_PARK,
+};
+
+void io_sq_thread_unpark(struct io_sq_data *sqd)
+	__releases(&sqd->lock)
+{
+	WARN_ON_ONCE(sqd->thread == current);
+
+	/*
+	 * Do the dance but not conditional clear_bit() because it'd race with
+	 * other threads incrementing park_pending and setting the bit.
+	 */
+	clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
+	if (atomic_dec_return(&sqd->park_pending))
+		set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
+	mutex_unlock(&sqd->lock);
+}
+
+void io_sq_thread_park(struct io_sq_data *sqd)
+	__acquires(&sqd->lock)
+{
+	WARN_ON_ONCE(sqd->thread == current);
+
+	atomic_inc(&sqd->park_pending);
+	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
+	mutex_lock(&sqd->lock);
+	if (sqd->thread)
+		wake_up_process(sqd->thread);
+}
+
+void io_sq_thread_stop(struct io_sq_data *sqd)
+{
+	WARN_ON_ONCE(sqd->thread == current);
+	WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state));
+
+	set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
+	mutex_lock(&sqd->lock);
+	if (sqd->thread)
+		wake_up_process(sqd->thread);
+	mutex_unlock(&sqd->lock);
+	wait_for_completion(&sqd->exited);
+}
+
+void io_put_sq_data(struct io_sq_data *sqd)
+{
+	if (refcount_dec_and_test(&sqd->refs)) {
+		WARN_ON_ONCE(atomic_read(&sqd->park_pending));
+
+		io_sq_thread_stop(sqd);
+		kfree(sqd);
+	}
+}
+
+static __cold void io_sqd_update_thread_idle(struct io_sq_data *sqd)
+{
+	struct io_ring_ctx *ctx;
+	unsigned sq_thread_idle = 0;
+
+	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
+		sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle);
+	sqd->sq_thread_idle = sq_thread_idle;
+}
+
+void io_sq_thread_finish(struct io_ring_ctx *ctx)
+{
+	struct io_sq_data *sqd = ctx->sq_data;
+
+	if (sqd) {
+		io_sq_thread_park(sqd);
+		list_del_init(&ctx->sqd_list);
+		io_sqd_update_thread_idle(sqd);
+		io_sq_thread_unpark(sqd);
+
+		io_put_sq_data(sqd);
+		ctx->sq_data = NULL;
+	}
+}
+
+static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p)
+{
+	struct io_ring_ctx *ctx_attach;
+	struct io_sq_data *sqd;
+	struct fd f;
+
+	f = fdget(p->wq_fd);
+	if (!f.file)
+		return ERR_PTR(-ENXIO);
+	if (!io_is_uring_fops(f.file)) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+
+	ctx_attach = f.file->private_data;
+	sqd = ctx_attach->sq_data;
+	if (!sqd) {
+		fdput(f);
+		return ERR_PTR(-EINVAL);
+	}
+	if (sqd->task_tgid != current->tgid) {
+		fdput(f);
+		return ERR_PTR(-EPERM);
+	}
+
+	refcount_inc(&sqd->refs);
+	fdput(f);
+	return sqd;
+}
+
+static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
+					 bool *attached)
+{
+	struct io_sq_data *sqd;
+
+	*attached = false;
+	if (p->flags & IORING_SETUP_ATTACH_WQ) {
+		sqd = io_attach_sq_data(p);
+		if (!IS_ERR(sqd)) {
+			*attached = true;
+			return sqd;
+		}
+		/* fall through for EPERM case, setup new sqd/task */
+		if (PTR_ERR(sqd) != -EPERM)
+			return sqd;
+	}
+
+	sqd = kzalloc(sizeof(*sqd), GFP_KERNEL);
+	if (!sqd)
+		return ERR_PTR(-ENOMEM);
+
+	atomic_set(&sqd->park_pending, 0);
+	refcount_set(&sqd->refs, 1);
+	INIT_LIST_HEAD(&sqd->ctx_list);
+	mutex_init(&sqd->lock);
+	init_waitqueue_head(&sqd->wait);
+	init_completion(&sqd->exited);
+	return sqd;
+}
+
+static inline bool io_sqd_events_pending(struct io_sq_data *sqd)
+{
+	return READ_ONCE(sqd->state);
+}
+
+static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
+{
+	unsigned int to_submit;
+	int ret = 0;
+
+	to_submit = io_sqring_entries(ctx);
+	/* if we're handling multiple rings, cap submit size for fairness */
+	if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE)
+		to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE;
+
+	if (!wq_list_empty(&ctx->iopoll_list) || to_submit) {
+		const struct cred *creds = NULL;
+
+		if (ctx->sq_creds != current_cred())
+			creds = override_creds(ctx->sq_creds);
+
+		mutex_lock(&ctx->uring_lock);
+		if (!wq_list_empty(&ctx->iopoll_list))
+			io_do_iopoll(ctx, true);
+
+		/*
+		 * Don't submit if refs are dying, good for io_uring_register(),
+		 * but also it is relied upon by io_ring_exit_work()
+		 */
+		if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) &&
+		    !(ctx->flags & IORING_SETUP_R_DISABLED))
+			ret = io_submit_sqes(ctx, to_submit);
+		mutex_unlock(&ctx->uring_lock);
+
+		if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
+			wake_up(&ctx->sqo_sq_wait);
+		if (creds)
+			revert_creds(creds);
+	}
+
+	return ret;
+}
+
+static bool io_sqd_handle_event(struct io_sq_data *sqd)
+{
+	bool did_sig = false;
+	struct ksignal ksig;
+
+	if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) ||
+	    signal_pending(current)) {
+		mutex_unlock(&sqd->lock);
+		if (signal_pending(current))
+			did_sig = get_signal(&ksig);
+		cond_resched();
+		mutex_lock(&sqd->lock);
+	}
+	return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
+}
+
+static int io_sq_thread(void *data)
+{
+	struct io_sq_data *sqd = data;
+	struct io_ring_ctx *ctx;
+	unsigned long timeout = 0;
+	char buf[TASK_COMM_LEN];
+	DEFINE_WAIT(wait);
+
+	snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
+	set_task_comm(current, buf);
+
+	if (sqd->sq_cpu != -1)
+		set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
+	else
+		set_cpus_allowed_ptr(current, cpu_online_mask);
+	current->flags |= PF_NO_SETAFFINITY;
+
+	mutex_lock(&sqd->lock);
+	while (1) {
+		bool cap_entries, sqt_spin = false;
+
+		if (io_sqd_events_pending(sqd) || signal_pending(current)) {
+			if (io_sqd_handle_event(sqd))
+				break;
+			timeout = jiffies + sqd->sq_thread_idle;
+		}
+
+		cap_entries = !list_is_singular(&sqd->ctx_list);
+		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
+			int ret = __io_sq_thread(ctx, cap_entries);
+
+			if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
+				sqt_spin = true;
+		}
+		if (io_run_task_work())
+			sqt_spin = true;
+
+		if (sqt_spin || !time_after(jiffies, timeout)) {
+			cond_resched();
+			if (sqt_spin)
+				timeout = jiffies + sqd->sq_thread_idle;
+			continue;
+		}
+
+		prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE);
+		if (!io_sqd_events_pending(sqd) && !task_work_pending(current)) {
+			bool needs_sched = true;
+
+			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
+				atomic_or(IORING_SQ_NEED_WAKEUP,
+						&ctx->rings->sq_flags);
+				if ((ctx->flags & IORING_SETUP_IOPOLL) &&
+				    !wq_list_empty(&ctx->iopoll_list)) {
+					needs_sched = false;
+					break;
+				}
+
+				/*
+				 * Ensure the store of the wakeup flag is not
+				 * reordered with the load of the SQ tail
+				 */
+				smp_mb__after_atomic();
+
+				if (io_sqring_entries(ctx)) {
+					needs_sched = false;
+					break;
+				}
+			}
+
+			if (needs_sched) {
+				mutex_unlock(&sqd->lock);
+				schedule();
+				mutex_lock(&sqd->lock);
+			}
+			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
+				atomic_andnot(IORING_SQ_NEED_WAKEUP,
+						&ctx->rings->sq_flags);
+		}
+
+		finish_wait(&sqd->wait, &wait);
+		timeout = jiffies + sqd->sq_thread_idle;
+	}
+
+	io_uring_cancel_generic(true, sqd);
+	sqd->thread = NULL;
+	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
+		atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags);
+	io_run_task_work();
+	mutex_unlock(&sqd->lock);
+
+	complete(&sqd->exited);
+	do_exit(0);
+}
+
+void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
+{
+	DEFINE_WAIT(wait);
+
+	do {
+		if (!io_sqring_full(ctx))
+			break;
+		prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE);
+
+		if (!io_sqring_full(ctx))
+			break;
+		schedule();
+	} while (!signal_pending(current));
+
+	finish_wait(&ctx->sqo_sq_wait, &wait);
+}
+
+__cold int io_sq_offload_create(struct io_ring_ctx *ctx,
+				struct io_uring_params *p)
+{
+	int ret;
+
+	/* Retain compatibility with failing for an invalid attach attempt */
+	if ((ctx->flags & (IORING_SETUP_ATTACH_WQ | IORING_SETUP_SQPOLL)) ==
+				IORING_SETUP_ATTACH_WQ) {
+		struct fd f;
+
+		f = fdget(p->wq_fd);
+		if (!f.file)
+			return -ENXIO;
+		if (!io_is_uring_fops(f.file)) {
+			fdput(f);
+			return -EINVAL;
+		}
+		fdput(f);
+	}
+	if (ctx->flags & IORING_SETUP_SQPOLL) {
+		struct task_struct *tsk;
+		struct io_sq_data *sqd;
+		bool attached;
+
+		ret = security_uring_sqpoll();
+		if (ret)
+			return ret;
+
+		sqd = io_get_sq_data(p, &attached);
+		if (IS_ERR(sqd)) {
+			ret = PTR_ERR(sqd);
+			goto err;
+		}
+
+		ctx->sq_creds = get_current_cred();
+		ctx->sq_data = sqd;
+		ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
+		if (!ctx->sq_thread_idle)
+			ctx->sq_thread_idle = HZ;
+
+		io_sq_thread_park(sqd);
+		list_add(&ctx->sqd_list, &sqd->ctx_list);
+		io_sqd_update_thread_idle(sqd);
+		/* don't attach to a dying SQPOLL thread, would be racy */
+		ret = (attached && !sqd->thread) ? -ENXIO : 0;
+		io_sq_thread_unpark(sqd);
+
+		if (ret < 0)
+			goto err;
+		if (attached)
+			return 0;
+
+		if (p->flags & IORING_SETUP_SQ_AFF) {
+			int cpu = p->sq_thread_cpu;
+
+			ret = -EINVAL;
+			if (cpu >= nr_cpu_ids || !cpu_online(cpu))
+				goto err_sqpoll;
+			sqd->sq_cpu = cpu;
+		} else {
+			sqd->sq_cpu = -1;
+		}
+
+		sqd->task_pid = current->pid;
+		sqd->task_tgid = current->tgid;
+		tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE);
+		if (IS_ERR(tsk)) {
+			ret = PTR_ERR(tsk);
+			goto err_sqpoll;
+		}
+
+		sqd->thread = tsk;
+		ret = io_uring_alloc_task_context(tsk, ctx);
+		wake_up_new_task(tsk);
+		if (ret)
+			goto err;
+	} else if (p->flags & IORING_SETUP_SQ_AFF) {
+		/* Can't have SQ_AFF without SQPOLL */
+		ret = -EINVAL;
+		goto err;
+	}
+
+	return 0;
+err_sqpoll:
+	complete(&ctx->sq_data->exited);
+err:
+	io_sq_thread_finish(ctx);
+	return ret;
+}