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, 451 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c
new file mode 100644
index 000000000..ce52b8749
--- /dev/null
+++ b/arch/powerpc/platforms/cell/spufs/run.c
@@ -0,0 +1,451 @@
+// SPDX-License-Identifier: GPL-2.0
+#define DEBUG
+
+#include <linux/wait.h>
+#include <linux/ptrace.h>
+
+#include <asm/spu.h>
+#include <asm/spu_priv1.h>
+#include <asm/io.h>
+#include <asm/unistd.h>
+
+#include "spufs.h"
+
+/* interrupt-level stop callback function. */
+void spufs_stop_callback(struct spu *spu, int irq)
+{
+	struct spu_context *ctx = spu->ctx;
+
+	/*
+	 * It should be impossible to preempt a context while an exception
+	 * is being processed, since the context switch code is specially
+	 * coded to deal with interrupts ... But, just in case, sanity check
+	 * the context pointer.  It is OK to return doing nothing since
+	 * the exception will be regenerated when the context is resumed.
+	 */
+	if (ctx) {
+		/* Copy exception arguments into module specific structure */
+		switch(irq) {
+		case 0 :
+			ctx->csa.class_0_pending = spu->class_0_pending;
+			ctx->csa.class_0_dar = spu->class_0_dar;
+			break;
+		case 1 :
+			ctx->csa.class_1_dsisr = spu->class_1_dsisr;
+			ctx->csa.class_1_dar = spu->class_1_dar;
+			break;
+		case 2 :
+			break;
+		}
+
+		/* ensure that the exception status has hit memory before a
+		 * thread waiting on the context's stop queue is woken */
+		smp_wmb();
+
+		wake_up_all(&ctx->stop_wq);
+	}
+}
+
+int spu_stopped(struct spu_context *ctx, u32 *stat)
+{
+	u64 dsisr;
+	u32 stopped;
+
+	stopped = SPU_STATUS_INVALID_INSTR | SPU_STATUS_SINGLE_STEP |
+		SPU_STATUS_STOPPED_BY_HALT | SPU_STATUS_STOPPED_BY_STOP;
+
+top:
+	*stat = ctx->ops->status_read(ctx);
+	if (*stat & stopped) {
+		/*
+		 * If the spu hasn't finished stopping, we need to
+		 * re-read the register to get the stopped value.
+		 */
+		if (*stat & SPU_STATUS_RUNNING)
+			goto top;
+		return 1;
+	}
+
+	if (test_bit(SPU_SCHED_NOTIFY_ACTIVE, &ctx->sched_flags))
+		return 1;
+
+	dsisr = ctx->csa.class_1_dsisr;
+	if (dsisr & (MFC_DSISR_PTE_NOT_FOUND | MFC_DSISR_ACCESS_DENIED))
+		return 1;
+
+	if (ctx->csa.class_0_pending)
+		return 1;
+
+	return 0;
+}
+
+static int spu_setup_isolated(struct spu_context *ctx)
+{
+	int ret;
+	u64 __iomem *mfc_cntl;
+	u64 sr1;
+	u32 status;
+	unsigned long timeout;
+	const u32 status_loading = SPU_STATUS_RUNNING
+		| SPU_STATUS_ISOLATED_STATE | SPU_STATUS_ISOLATED_LOAD_STATUS;
+
+	ret = -ENODEV;
+	if (!isolated_loader)
+		goto out;
+
+	/*
+	 * We need to exclude userspace access to the context.
+	 *
+	 * To protect against memory access we invalidate all ptes
+	 * and make sure the pagefault handlers block on the mutex.
+	 */
+	spu_unmap_mappings(ctx);
+
+	mfc_cntl = &ctx->spu->priv2->mfc_control_RW;
+
+	/* purge the MFC DMA queue to ensure no spurious accesses before we
+	 * enter kernel mode */
+	timeout = jiffies + HZ;
+	out_be64(mfc_cntl, MFC_CNTL_PURGE_DMA_REQUEST);
+	while ((in_be64(mfc_cntl) & MFC_CNTL_PURGE_DMA_STATUS_MASK)
+			!= MFC_CNTL_PURGE_DMA_COMPLETE) {
+		if (time_after(jiffies, timeout)) {
+			printk(KERN_ERR "%s: timeout flushing MFC DMA queue\n",
+					__func__);
+			ret = -EIO;
+			goto out;
+		}
+		cond_resched();
+	}
+
+	/* clear purge status */
+	out_be64(mfc_cntl, 0);
+
+	/* put the SPE in kernel mode to allow access to the loader */
+	sr1 = spu_mfc_sr1_get(ctx->spu);
+	sr1 &= ~MFC_STATE1_PROBLEM_STATE_MASK;
+	spu_mfc_sr1_set(ctx->spu, sr1);
+
+	/* start the loader */
+	ctx->ops->signal1_write(ctx, (unsigned long)isolated_loader >> 32);
+	ctx->ops->signal2_write(ctx,
+			(unsigned long)isolated_loader & 0xffffffff);
+
+	ctx->ops->runcntl_write(ctx,
+			SPU_RUNCNTL_RUNNABLE | SPU_RUNCNTL_ISOLATE);
+
+	ret = 0;
+	timeout = jiffies + HZ;
+	while (((status = ctx->ops->status_read(ctx)) & status_loading) ==
+				status_loading) {
+		if (time_after(jiffies, timeout)) {
+			printk(KERN_ERR "%s: timeout waiting for loader\n",
+					__func__);
+			ret = -EIO;
+			goto out_drop_priv;
+		}
+		cond_resched();
+	}
+
+	if (!(status & SPU_STATUS_RUNNING)) {
+		/* If isolated LOAD has failed: run SPU, we will get a stop-and
+		 * signal later. */
+		pr_debug("%s: isolated LOAD failed\n", __func__);
+		ctx->ops->runcntl_write(ctx, SPU_RUNCNTL_RUNNABLE);
+		ret = -EACCES;
+		goto out_drop_priv;
+	}
+
+	if (!(status & SPU_STATUS_ISOLATED_STATE)) {
+		/* This isn't allowed by the CBEA, but check anyway */
+		pr_debug("%s: SPU fell out of isolated mode?\n", __func__);
+		ctx->ops->runcntl_write(ctx, SPU_RUNCNTL_STOP);
+		ret = -EINVAL;
+		goto out_drop_priv;
+	}
+
+out_drop_priv:
+	/* Finished accessing the loader. Drop kernel mode */
+	sr1 |= MFC_STATE1_PROBLEM_STATE_MASK;
+	spu_mfc_sr1_set(ctx->spu, sr1);
+
+out:
+	return ret;
+}
+
+static int spu_run_init(struct spu_context *ctx, u32 *npc)
+{
+	unsigned long runcntl = SPU_RUNCNTL_RUNNABLE;
+	int ret;
+
+	spuctx_switch_state(ctx, SPU_UTIL_SYSTEM);
+
+	/*
+	 * NOSCHED is synchronous scheduling with respect to the caller.
+	 * The caller waits for the context to be loaded.
+	 */
+	if (ctx->flags & SPU_CREATE_NOSCHED) {
+		if (ctx->state == SPU_STATE_SAVED) {
+			ret = spu_activate(ctx, 0);
+			if (ret)
+				return ret;
+		}
+	}
+
+	/*
+	 * Apply special setup as required.
+	 */
+	if (ctx->flags & SPU_CREATE_ISOLATE) {
+		if (!(ctx->ops->status_read(ctx) & SPU_STATUS_ISOLATED_STATE)) {
+			ret = spu_setup_isolated(ctx);
+			if (ret)
+				return ret;
+		}
+
+		/*
+		 * If userspace has set the runcntrl register (eg, to
+		 * issue an isolated exit), we need to re-set it here
+		 */
+		runcntl = ctx->ops->runcntl_read(ctx) &
+			(SPU_RUNCNTL_RUNNABLE | SPU_RUNCNTL_ISOLATE);
+		if (runcntl == 0)
+			runcntl = SPU_RUNCNTL_RUNNABLE;
+	} else {
+		unsigned long privcntl;
+
+		if (test_thread_flag(TIF_SINGLESTEP))
+			privcntl = SPU_PRIVCNTL_MODE_SINGLE_STEP;
+		else
+			privcntl = SPU_PRIVCNTL_MODE_NORMAL;
+
+		ctx->ops->privcntl_write(ctx, privcntl);
+		ctx->ops->npc_write(ctx, *npc);
+	}
+
+	ctx->ops->runcntl_write(ctx, runcntl);
+
+	if (ctx->flags & SPU_CREATE_NOSCHED) {
+		spuctx_switch_state(ctx, SPU_UTIL_USER);
+	} else {
+
+		if (ctx->state == SPU_STATE_SAVED) {
+			ret = spu_activate(ctx, 0);
+			if (ret)
+				return ret;
+		} else {
+			spuctx_switch_state(ctx, SPU_UTIL_USER);
+		}
+	}
+
+	set_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags);
+	return 0;
+}
+
+static int spu_run_fini(struct spu_context *ctx, u32 *npc,
+			       u32 *status)
+{
+	int ret = 0;
+
+	spu_del_from_rq(ctx);
+
+	*status = ctx->ops->status_read(ctx);
+	*npc = ctx->ops->npc_read(ctx);
+
+	spuctx_switch_state(ctx, SPU_UTIL_IDLE_LOADED);
+	clear_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags);
+	spu_switch_log_notify(NULL, ctx, SWITCH_LOG_EXIT, *status);
+	spu_release(ctx);
+
+	if (signal_pending(current))
+		ret = -ERESTARTSYS;
+
+	return ret;
+}
+
+/*
+ * SPU syscall restarting is tricky because we violate the basic
+ * assumption that the signal handler is running on the interrupted
+ * thread. Here instead, the handler runs on PowerPC user space code,
+ * while the syscall was called from the SPU.
+ * This means we can only do a very rough approximation of POSIX
+ * signal semantics.
+ */
+static int spu_handle_restartsys(struct spu_context *ctx, long *spu_ret,
+			  unsigned int *npc)
+{
+	int ret;
+
+	switch (*spu_ret) {
+	case -ERESTARTSYS:
+	case -ERESTARTNOINTR:
+		/*
+		 * Enter the regular syscall restarting for
+		 * sys_spu_run, then restart the SPU syscall
+		 * callback.
+		 */
+		*npc -= 8;
+		ret = -ERESTARTSYS;
+		break;
+	case -ERESTARTNOHAND:
+	case -ERESTART_RESTARTBLOCK:
+		/*
+		 * Restart block is too hard for now, just return -EINTR
+		 * to the SPU.
+		 * ERESTARTNOHAND comes from sys_pause, we also return
+		 * -EINTR from there.
+		 * Assume that we need to be restarted ourselves though.
+		 */
+		*spu_ret = -EINTR;
+		ret = -ERESTARTSYS;
+		break;
+	default:
+		printk(KERN_WARNING "%s: unexpected return code %ld\n",
+			__func__, *spu_ret);
+		ret = 0;
+	}
+	return ret;
+}
+
+static int spu_process_callback(struct spu_context *ctx)
+{
+	struct spu_syscall_block s;
+	u32 ls_pointer, npc;
+	void __iomem *ls;
+	long spu_ret;
+	int ret;
+
+	/* get syscall block from local store */
+	npc = ctx->ops->npc_read(ctx) & ~3;
+	ls = (void __iomem *)ctx->ops->get_ls(ctx);
+	ls_pointer = in_be32(ls + npc);
+	if (ls_pointer > (LS_SIZE - sizeof(s)))
+		return -EFAULT;
+	memcpy_fromio(&s, ls + ls_pointer, sizeof(s));
+
+	/* do actual syscall without pinning the spu */
+	ret = 0;
+	spu_ret = -ENOSYS;
+	npc += 4;
+
+	if (s.nr_ret < NR_syscalls) {
+		spu_release(ctx);
+		/* do actual system call from here */
+		spu_ret = spu_sys_callback(&s);
+		if (spu_ret <= -ERESTARTSYS) {
+			ret = spu_handle_restartsys(ctx, &spu_ret, &npc);
+		}
+		mutex_lock(&ctx->state_mutex);
+		if (ret == -ERESTARTSYS)
+			return ret;
+	}
+
+	/* need to re-get the ls, as it may have changed when we released the
+	 * spu */
+	ls = (void __iomem *)ctx->ops->get_ls(ctx);
+
+	/* write result, jump over indirect pointer */
+	memcpy_toio(ls + ls_pointer, &spu_ret, sizeof(spu_ret));
+	ctx->ops->npc_write(ctx, npc);
+	ctx->ops->runcntl_write(ctx, SPU_RUNCNTL_RUNNABLE);
+	return ret;
+}
+
+long spufs_run_spu(struct spu_context *ctx, u32 *npc, u32 *event)
+{
+	int ret;
+	u32 status;
+
+	if (mutex_lock_interruptible(&ctx->run_mutex))
+		return -ERESTARTSYS;
+
+	ctx->event_return = 0;
+
+	ret = spu_acquire(ctx);
+	if (ret)
+		goto out_unlock;
+
+	spu_enable_spu(ctx);
+
+	spu_update_sched_info(ctx);
+
+	ret = spu_run_init(ctx, npc);
+	if (ret) {
+		spu_release(ctx);
+		goto out;
+	}
+
+	do {
+		ret = spufs_wait(ctx->stop_wq, spu_stopped(ctx, &status));
+		if (unlikely(ret)) {
+			/*
+			 * This is nasty: we need the state_mutex for all the
+			 * bookkeeping even if the syscall was interrupted by
+			 * a signal. ewww.
+			 */
+			mutex_lock(&ctx->state_mutex);
+			break;
+		}
+		if (unlikely(test_and_clear_bit(SPU_SCHED_NOTIFY_ACTIVE,
+						&ctx->sched_flags))) {
+			if (!(status & SPU_STATUS_STOPPED_BY_STOP))
+				continue;
+		}
+
+		spuctx_switch_state(ctx, SPU_UTIL_SYSTEM);
+
+		if ((status & SPU_STATUS_STOPPED_BY_STOP) &&
+		    (status >> SPU_STOP_STATUS_SHIFT == 0x2104)) {
+			ret = spu_process_callback(ctx);
+			if (ret)
+				break;
+			status &= ~SPU_STATUS_STOPPED_BY_STOP;
+		}
+		ret = spufs_handle_class1(ctx);
+		if (ret)
+			break;
+
+		ret = spufs_handle_class0(ctx);
+		if (ret)
+			break;
+
+		if (signal_pending(current))
+			ret = -ERESTARTSYS;
+	} while (!ret && !(status & (SPU_STATUS_STOPPED_BY_STOP |
+				      SPU_STATUS_STOPPED_BY_HALT |
+				       SPU_STATUS_SINGLE_STEP)));
+
+	spu_disable_spu(ctx);
+	ret = spu_run_fini(ctx, npc, &status);
+	spu_yield(ctx);
+
+	if ((status & SPU_STATUS_STOPPED_BY_STOP) &&
+	    (((status >> SPU_STOP_STATUS_SHIFT) & 0x3f00) == 0x2100))
+		ctx->stats.libassist++;
+
+	if ((ret == 0) ||
+	    ((ret == -ERESTARTSYS) &&
+	     ((status & SPU_STATUS_STOPPED_BY_HALT) ||
+	      (status & SPU_STATUS_SINGLE_STEP) ||
+	      ((status & SPU_STATUS_STOPPED_BY_STOP) &&
+	       (status >> SPU_STOP_STATUS_SHIFT != 0x2104)))))
+		ret = status;
+
+	/* Note: we don't need to force_sig SIGTRAP on single-step
+	 * since we have TIF_SINGLESTEP set, thus the kernel will do
+	 * it upon return from the syscall anyway.
+	 */
+	if (unlikely(status & SPU_STATUS_SINGLE_STEP))
+		ret = -ERESTARTSYS;
+
+	else if (unlikely((status & SPU_STATUS_STOPPED_BY_STOP)
+	    && (status >> SPU_STOP_STATUS_SHIFT) == 0x3fff)) {
+		force_sig(SIGTRAP);
+		ret = -ERESTARTSYS;
+	}
+
+out:
+	*event = ctx->event_return;
+out_unlock:
+	mutex_unlock(&ctx->run_mutex);
+	return ret;
+}