From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- io_uring/sqpoll.c | 564 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 564 insertions(+) create mode 100644 io_uring/sqpoll.c (limited to 'io_uring/sqpoll.c') diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c new file mode 100644 index 000000000..ad42e8eb1 --- /dev/null +++ b/io_uring/sqpoll.c @@ -0,0 +1,564 @@ +// 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "io_uring.h" +#include "tctx.h" +#include "napi.h" +#include "cancel.h" +#include "sqpoll.h" + +#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 +#define IORING_TW_CAP_ENTRIES_VALUE 32 + +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(sqpoll_task_locked(sqd) == 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); + wake_up(&sqd->wait); +} + +void io_sq_thread_park(struct io_sq_data *sqd) + __acquires(&sqd->lock) +{ + struct task_struct *tsk; + + atomic_inc(&sqd->park_pending); + set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + mutex_lock(&sqd->lock); + + tsk = sqpoll_task_locked(sqd); + if (tsk) { + WARN_ON_ONCE(tsk == current); + wake_up_process(tsk); + } +} + +void io_sq_thread_stop(struct io_sq_data *sqd) +{ + struct task_struct *tsk; + + 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); + tsk = sqpoll_task_locked(sqd); + if (tsk) { + WARN_ON_ONCE(tsk == current); + wake_up_process(tsk); + } + 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; + CLASS(fd, f)(p->wq_fd); + + if (fd_empty(f)) + return ERR_PTR(-ENXIO); + if (!io_is_uring_fops(fd_file(f))) + return ERR_PTR(-EINVAL); + + ctx_attach = fd_file(f)->private_data; + sqd = ctx_attach->sq_data; + if (!sqd) + return ERR_PTR(-EINVAL); + if (sqd->task_tgid != current->tgid) + return ERR_PTR(-EPERM); + + refcount_inc(&sqd->refs); + 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_obj(*sqd); + 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); +} + +struct io_sq_time { + bool started; + u64 usec; +}; + +u64 io_sq_cpu_usec(struct task_struct *tsk) +{ + u64 utime, stime; + + task_cputime_adjusted(tsk, &utime, &stime); + do_div(stime, 1000); + return stime; +} + +static void io_sq_update_worktime(struct io_sq_data *sqd, struct io_sq_time *ist) +{ + if (!ist->started) + return; + ist->started = false; + sqd->work_time += io_sq_cpu_usec(current) - ist->usec; +} + +static void io_sq_start_worktime(struct io_sq_time *ist) +{ + if (ist->started) + return; + ist->started = true; + ist->usec = io_sq_cpu_usec(current); +} + +static int __io_sq_thread(struct io_ring_ctx *ctx, struct io_sq_data *sqd, + bool cap_entries, struct io_sq_time *ist) +{ + 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 (to_submit || !list_empty(&ctx->iopoll_list)) { + const struct cred *creds = NULL; + + io_sq_start_worktime(ist); + + if (ctx->sq_creds != current_cred()) + creds = override_creds(ctx->sq_creds); + + mutex_lock(&ctx->uring_lock); + if (!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); + wait_event(sqd->wait, !atomic_read(&sqd->park_pending)); + mutex_lock(&sqd->lock); + sqd->sq_cpu = raw_smp_processor_id(); + } + return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); +} + +/* + * Run task_work, processing no more than max_entries at a time. If more + * than that is pending, it simply stays on the queue for the next run. + */ +static unsigned int io_sq_tw(int max_entries) +{ + struct io_uring_task *tctx = current->io_uring; + unsigned int count = 0; + + tctx_task_work_run(tctx, max_entries, &count); + if (task_work_pending(current)) + task_work_run(); + return count; +} + +static bool io_sq_tw_pending(void) +{ + struct io_uring_task *tctx = current->io_uring; + + return !mpscq_empty(&tctx->task_list); +} + +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); + + /* offload context creation failed, just exit */ + if (!current->io_uring) { + mutex_lock(&sqd->lock); + rcu_assign_pointer(sqd->thread, NULL); + put_task_struct(current); + mutex_unlock(&sqd->lock); + goto err_out; + } + + snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); + set_task_comm(current, buf); + + /* reset to our pid after we've set task_comm, for fdinfo */ + sqd->task_pid = current->pid; + + if (sqd->sq_cpu != -1) { + set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu)); + } else { + set_cpus_allowed_ptr(current, cpu_online_mask); + sqd->sq_cpu = raw_smp_processor_id(); + } + + /* + * Force audit context to get setup, in case we do prep side async + * operations that would trigger an audit call before any issue side + * audit has been done. + */ + audit_uring_entry(IORING_OP_NOP); + audit_uring_exit(true, 0); + + mutex_lock(&sqd->lock); + while (1) { + bool cap_entries, sqt_spin = false; + struct io_sq_time ist = { }; + + 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; + + kcov_remote_start_common(ctx->kcov_handle); + ret = __io_sq_thread(ctx, sqd, cap_entries, &ist); + + if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list))) + sqt_spin = true; + kcov_remote_stop(); + } + if (io_sq_tw(IORING_TW_CAP_ENTRIES_VALUE)) + sqt_spin = true; + + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { + if (io_napi(ctx)) { + io_sq_start_worktime(&ist); + io_napi_sqpoll_busy_poll(ctx); + } + } + + io_sq_update_worktime(sqd, &ist); + + if (sqt_spin || !time_after(jiffies, timeout)) { + if (sqt_spin) + timeout = jiffies + sqd->sq_thread_idle; + if (unlikely(need_resched())) { + mutex_unlock(&sqd->lock); + cond_resched(); + mutex_lock(&sqd->lock); + sqd->sq_cpu = raw_smp_processor_id(); + } + continue; + } + + prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE); + if (!io_sqd_events_pending(sqd) && !io_sq_tw_pending()) { + 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) && + !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); + sqd->sq_cpu = raw_smp_processor_id(); + } + 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; + } + + if (io_sq_tw_pending()) + io_sq_tw(UINT_MAX); + + io_uring_cancel_generic(true, sqd); + rcu_assign_pointer(sqd->thread, NULL); + put_task_struct(current); + 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); +err_out: + 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) { + CLASS(fd, f)(p->wq_fd); + if (fd_empty(f)) + return -ENXIO; + if (!io_is_uring_fops(fd_file(f))) + return -EINVAL; + } + if (ctx->flags & IORING_SETUP_SQPOLL) { + struct io_uring_task *tctx; + 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) { + cpumask_var_t allowed_mask; + int cpu = p->sq_thread_cpu; + + ret = -EINVAL; + if (cpu >= nr_cpu_ids || !cpu_online(cpu)) + goto err_sqpoll; + ret = -ENOMEM; + if (!alloc_cpumask_var(&allowed_mask, GFP_KERNEL)) + goto err_sqpoll; + ret = -EINVAL; + cpuset_cpus_allowed(current, allowed_mask); + if (!cpumask_test_cpu(cpu, allowed_mask)) { + free_cpumask_var(allowed_mask); + goto err_sqpoll; + } + free_cpumask_var(allowed_mask); + 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; + } + + mutex_lock(&sqd->lock); + rcu_assign_pointer(sqd->thread, tsk); + mutex_unlock(&sqd->lock); + + ret = 0; + get_task_struct(tsk); + tctx = io_uring_alloc_task_context(tsk, ctx); + if (!IS_ERR(tctx)) + tsk->io_uring = tctx; + else + ret = PTR_ERR(tctx); + 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; +} + +__cold int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx, + cpumask_var_t mask) +{ + struct io_sq_data *sqd = ctx->sq_data; + int ret = -EINVAL; + + if (sqd) { + struct task_struct *tsk; + + io_sq_thread_park(sqd); + /* Don't set affinity for a dying thread */ + tsk = sqpoll_task_locked(sqd); + if (tsk) + ret = io_wq_cpu_affinity(tsk->io_uring, mask); + io_sq_thread_unpark(sqd); + } + + return ret; +} -- cgit v1.3.1