Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linuxgrafted

Pull io_uring fixes from Jens Axboe:

 - Fix a task_work add use-after-free with SQPOLL.

   The sqpoll thread could pop and complete the last request while
   io_req_normal_work_add() was still looking at them after the mpscq
   push.

   Use the same approach as DEFER_TASKRUN to protect from that, holding
   an RCU read lock across the add, and have exit wait for an RCU grace
   period for SQPOLL rings as well.

 - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the
   big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED
   rings

 - Mark the source filter table as COW when cloning bpf filters, so
   registering another filter on the source doesn't modify the shared
   table in place

 - Initialize the task context before running the BPF loop

 - Requeue zcrx multishot receives stopped by a local resource

 - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit)

* tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring: fix task_work add use-after-free with SQPOLL
  io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full
  io_uring/zcrx: requeue multishot receives stopped by a local resource
  io_uring: initialize task context before running the BPF loop
  io_uring: zero big_cqe for aux CQEs on CQE32 rings
  io_uring: fix free entry check for 32b CQEs on CQE32 rings
  io_uring: only post the dummy skip CQE on CQE_MIXED rings
  io_uring/bpf_filter: mark source as COW when cloning filters

1 files changed, 166 insertions, 0 deletions

diff --git a/include/xen/interface/sched.h b/include/xen/interface/sched.h
new file mode 100644
index 000000000..4dac0634f
--- /dev/null
+++ b/include/xen/interface/sched.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: MIT */
+/******************************************************************************
+ * sched.h
+ *
+ * Scheduler state interactions
+ *
+ * Copyright (c) 2005, Keir Fraser <keir@xensource.com>
+ */
+
+#ifndef __XEN_PUBLIC_SCHED_H__
+#define __XEN_PUBLIC_SCHED_H__
+
+#include <xen/interface/event_channel.h>
+
+/*
+ * Guest Scheduler Operations
+ *
+ * The SCHEDOP interface provides mechanisms for a guest to interact
+ * with the scheduler, including yield, blocking and shutting itself
+ * down.
+ */
+
+/*
+ * The prototype for this hypercall is:
+ * long HYPERVISOR_sched_op(enum sched_op cmd, void *arg, ...)
+ *
+ * @cmd == SCHEDOP_??? (scheduler operation).
+ * @arg == Operation-specific extra argument(s), as described below.
+ * ...  == Additional Operation-specific extra arguments, described below.
+ *
+ * Versions of Xen prior to 3.0.2 provided only the following legacy version
+ * of this hypercall, supporting only the commands yield, block and shutdown:
+ *  long sched_op(int cmd, unsigned long arg)
+ * @cmd == SCHEDOP_??? (scheduler operation).
+ * @arg == 0               (SCHEDOP_yield and SCHEDOP_block)
+ *      == SHUTDOWN_* code (SCHEDOP_shutdown)
+ *
+ * This legacy version is available to new guests as:
+ * long HYPERVISOR_sched_op_compat(enum sched_op cmd, unsigned long arg)
+ */
+
+/*
+ * Voluntarily yield the CPU.
+ * @arg == NULL.
+ */
+#define SCHEDOP_yield       0
+
+/*
+ * Block execution of this VCPU until an event is received for processing.
+ * If called with event upcalls masked, this operation will atomically
+ * reenable event delivery and check for pending events before blocking the
+ * VCPU. This avoids a "wakeup waiting" race.
+ * @arg == NULL.
+ */
+#define SCHEDOP_block       1
+
+/*
+ * Halt execution of this domain (all VCPUs) and notify the system controller.
+ * @arg == pointer to sched_shutdown structure.
+ *
+ * If the sched_shutdown_t reason is SHUTDOWN_suspend then
+ * x86 PV guests must also set RDX (EDX for 32-bit guests) to the MFN
+ * of the guest's start info page.  RDX/EDX is the third hypercall
+ * argument.
+ *
+ * In addition, which reason is SHUTDOWN_suspend this hypercall
+ * returns 1 if suspend was cancelled or the domain was merely
+ * checkpointed, and 0 if it is resuming in a new domain.
+ */
+#define SCHEDOP_shutdown    2
+
+/*
+ * Poll a set of event-channel ports. Return when one or more are pending. An
+ * optional timeout may be specified.
+ * @arg == pointer to sched_poll structure.
+ */
+#define SCHEDOP_poll        3
+
+/*
+ * Declare a shutdown for another domain. The main use of this function is
+ * in interpreting shutdown requests and reasons for fully-virtualized
+ * domains.  A para-virtualized domain may use SCHEDOP_shutdown directly.
+ * @arg == pointer to sched_remote_shutdown structure.
+ */
+#define SCHEDOP_remote_shutdown        4
+
+/*
+ * Latch a shutdown code, so that when the domain later shuts down it
+ * reports this code to the control tools.
+ * @arg == sched_shutdown, as for SCHEDOP_shutdown.
+ */
+#define SCHEDOP_shutdown_code 5
+
+/*
+ * Setup, poke and destroy a domain watchdog timer.
+ * @arg == pointer to sched_watchdog structure.
+ * With id == 0, setup a domain watchdog timer to cause domain shutdown
+ *               after timeout, returns watchdog id.
+ * With id != 0 and timeout == 0, destroy domain watchdog timer.
+ * With id != 0 and timeout != 0, poke watchdog timer and set new timeout.
+ */
+#define SCHEDOP_watchdog    6
+
+/*
+ * Override the current vcpu affinity by pinning it to one physical cpu or
+ * undo this override restoring the previous affinity.
+ * @arg == pointer to sched_pin_override structure.
+ *
+ * A negative pcpu value will undo a previous pin override and restore the
+ * previous cpu affinity.
+ * This call is allowed for the hardware domain only and requires the cpu
+ * to be part of the domain's cpupool.
+ */
+#define SCHEDOP_pin_override 7
+
+struct sched_shutdown {
+    unsigned int reason; /* SHUTDOWN_* => shutdown reason */
+};
+DEFINE_GUEST_HANDLE_STRUCT(sched_shutdown);
+
+struct sched_poll {
+    GUEST_HANDLE(evtchn_port_t) ports;
+    unsigned int nr_ports;
+    uint64_t timeout;
+};
+DEFINE_GUEST_HANDLE_STRUCT(sched_poll);
+
+struct sched_remote_shutdown {
+    domid_t domain_id;         /* Remote domain ID */
+    unsigned int reason;       /* SHUTDOWN_* => shutdown reason */
+};
+DEFINE_GUEST_HANDLE_STRUCT(sched_remote_shutdown);
+
+struct sched_watchdog {
+    uint32_t id;                /* watchdog ID */
+    uint32_t timeout;           /* timeout */
+};
+DEFINE_GUEST_HANDLE_STRUCT(sched_watchdog);
+
+struct sched_pin_override {
+    int32_t pcpu;
+};
+DEFINE_GUEST_HANDLE_STRUCT(sched_pin_override);
+
+/*
+ * Reason codes for SCHEDOP_shutdown. These may be interpreted by control
+ * software to determine the appropriate action. For the most part, Xen does
+ * not care about the shutdown code.
+ */
+#define SHUTDOWN_poweroff   0  /* Domain exited normally. Clean up and kill. */
+#define SHUTDOWN_reboot     1  /* Clean up, kill, and then restart.          */
+#define SHUTDOWN_suspend    2  /* Clean up, save suspend info, kill.         */
+#define SHUTDOWN_crash      3  /* Tell controller we've crashed.             */
+#define SHUTDOWN_watchdog   4  /* Restart because watchdog time expired.     */
+
+/*
+ * Domain asked to perform 'soft reset' for it. The expected behavior is to
+ * reset internal Xen state for the domain returning it to the point where it
+ * was created but leaving the domain's memory contents and vCPU contexts
+ * intact. This will allow the domain to start over and set up all Xen specific
+ * interfaces again.
+ */
+#define SHUTDOWN_soft_reset 5
+#define SHUTDOWN_MAX        5  /* Maximum valid shutdown reason.             */
+
+#endif /* __XEN_PUBLIC_SCHED_H__ */