blob: 3942db160f18ef3bc09c6f666724263a4117635d [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0
/*
* Shared application/kernel submission and completion ring pairs, for
* supporting fast/efficient IO.
*
* A note on the read/write ordering memory barriers that are matched between
* the application and kernel side.
*
* After the application reads the CQ ring tail, it must use an
* appropriate smp_rmb() to pair with the smp_wmb() the kernel uses
* before writing the tail (using smp_load_acquire to read the tail will
* do). It also needs a smp_mb() before updating CQ head (ordering the
* entry load(s) with the head store), pairing with an implicit barrier
* through a control-dependency in io_get_cqe (smp_store_release to
* store head will do). Failure to do so could lead to reading invalid
* CQ entries.
*
* Likewise, the application must use an appropriate smp_wmb() before
* writing the SQ tail (ordering SQ entry stores with the tail store),
* which pairs with smp_load_acquire in io_get_sqring (smp_store_release
* to store the tail will do). And it needs a barrier ordering the SQ
* head load before writing new SQ entries (smp_load_acquire to read
* head will do).
*
* When using the SQ poll thread (IORING_SETUP_SQPOLL), the application
* needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after*
* updating the SQ tail; a full memory barrier smp_mb() is needed
* between.
*
* Also see the examples in the liburing library:
*
* git://git.kernel.dk/liburing
*
* io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens
* from data shared between the kernel and application. This is done both
* for ordering purposes, but also to ensure that once a value is loaded from
* data that the application could potentially modify, it remains stable.
*
* Copyright (C) 2018-2019 Jens Axboe
* Copyright (c) 2018-2019 Christoph Hellwig
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/syscalls.h>
#include <net/compat.h>
#include <linux/refcount.h>
#include <linux/uio.h>
#include <linux/bits.h>
#include <linux/sched/signal.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/bvec.h>
#include <linux/net.h>
#include <net/sock.h>
#include <linux/anon_inodes.h>
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
#include <linux/nospec.h>
#include <linux/fsnotify.h>
#include <linux/fadvise.h>
#include <linux/task_work.h>
#include <linux/io_uring.h>
#include <linux/io_uring/cmd.h>
#include <linux/audit.h>
#include <linux/security.h>
#include <asm/shmparam.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
#include <uapi/linux/io_uring.h>
#include "io-wq.h"
#include "io_uring.h"
#include "opdef.h"
#include "refs.h"
#include "tctx.h"
#include "register.h"
#include "sqpoll.h"
#include "fdinfo.h"
#include "kbuf.h"
#include "rsrc.h"
#include "cancel.h"
#include "net.h"
#include "notif.h"
#include "waitid.h"
#include "futex.h"
#include "napi.h"
#include "uring_cmd.h"
#include "msg_ring.h"
#include "memmap.h"
#include "timeout.h"
#include "poll.h"
#include "rw.h"
#include "alloc_cache.h"
#include "eventfd.h"
#define IORING_MAX_ENTRIES 32768
#define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES)
#define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \
IOSQE_IO_HARDLINK | IOSQE_ASYNC)
#define SQE_VALID_FLAGS (SQE_COMMON_FLAGS | IOSQE_BUFFER_SELECT | \
IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)
#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
REQ_F_ASYNC_DATA)
#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\
IO_REQ_CLEAN_FLAGS)
#define IO_TCTX_REFS_CACHE_NR (1U << 10)
#define IO_COMPL_BATCH 32
#define IO_REQ_ALLOC_BATCH 8
struct io_defer_entry {
struct list_head list;
struct io_kiocb *req;
u32 seq;
};
/* requests with any of those set should undergo io_disarm_next() */
#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL)
#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK)
/*
* No waiters. It's larger than any valid value of the tw counter
* so that tests against ->cq_wait_nr would fail and skip wake_up().
*/
#define IO_CQ_WAKE_INIT (-1U)
/* Forced wake up if there is a waiter regardless of ->cq_wait_nr */
#define IO_CQ_WAKE_FORCE (IO_CQ_WAKE_INIT >> 1)
static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
struct task_struct *task,
bool cancel_all);
static void io_queue_sqe(struct io_kiocb *req);
struct kmem_cache *req_cachep;
static struct workqueue_struct *iou_wq __ro_after_init;
static int __read_mostly sysctl_io_uring_disabled;
static int __read_mostly sysctl_io_uring_group = -1;
#ifdef CONFIG_SYSCTL
static struct ctl_table kernel_io_uring_disabled_table[] = {
{
.procname = "io_uring_disabled",
.data = &sysctl_io_uring_disabled,
.maxlen = sizeof(sysctl_io_uring_disabled),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
{
.procname = "io_uring_group",
.data = &sysctl_io_uring_group,
.maxlen = sizeof(gid_t),
.mode = 0644,
.proc_handler = proc_dointvec,
},
};
#endif
static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx)
{
return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head);
}
static inline unsigned int __io_cqring_events_user(struct io_ring_ctx *ctx)
{
return READ_ONCE(ctx->rings->cq.tail) - READ_ONCE(ctx->rings->cq.head);
}
static bool io_match_linked(struct io_kiocb *head)
{
struct io_kiocb *req;
io_for_each_link(req, head) {
if (req->flags & REQ_F_INFLIGHT)
return true;
}
return false;
}
/*
* As io_match_task() but protected against racing with linked timeouts.
* User must not hold timeout_lock.
*/
bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
bool cancel_all)
{
bool matched;
if (task && head->task != task)
return false;
if (cancel_all)
return true;
if (head->flags & REQ_F_LINK_TIMEOUT) {
struct io_ring_ctx *ctx = head->ctx;
/* protect against races with linked timeouts */
spin_lock_irq(&ctx->timeout_lock);
matched = io_match_linked(head);
spin_unlock_irq(&ctx->timeout_lock);
} else {
matched = io_match_linked(head);
}
return matched;
}
static inline void req_fail_link_node(struct io_kiocb *req, int res)
{
req_set_fail(req);
io_req_set_res(req, res, 0);
}
static inline void io_req_add_to_cache(struct io_kiocb *req, struct io_ring_ctx *ctx)
{
wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
}
static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref)
{
struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);
complete(&ctx->ref_comp);
}
static __cold void io_fallback_req_func(struct work_struct *work)
{
struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx,
fallback_work.work);
struct llist_node *node = llist_del_all(&ctx->fallback_llist);
struct io_kiocb *req, *tmp;
struct io_tw_state ts = {};
percpu_ref_get(&ctx->refs);
mutex_lock(&ctx->uring_lock);
llist_for_each_entry_safe(req, tmp, node, io_task_work.node)
req->io_task_work.func(req, &ts);
io_submit_flush_completions(ctx);
mutex_unlock(&ctx->uring_lock);
percpu_ref_put(&ctx->refs);
}
static int io_alloc_hash_table(struct io_hash_table *table, unsigned bits)
{
unsigned hash_buckets = 1U << bits;
size_t hash_size = hash_buckets * sizeof(table->hbs[0]);
table->hbs = kmalloc(hash_size, GFP_KERNEL);
if (!table->hbs)
return -ENOMEM;
table->hash_bits = bits;
init_hash_table(table, hash_buckets);
return 0;
}
static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
{
struct io_ring_ctx *ctx;
int hash_bits;
bool ret;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return NULL;
xa_init(&ctx->io_bl_xa);
/*
* Use 5 bits less than the max cq entries, that should give us around
* 32 entries per hash list if totally full and uniformly spread, but
* don't keep too many buckets to not overconsume memory.
*/
hash_bits = ilog2(p->cq_entries) - 5;
hash_bits = clamp(hash_bits, 1, 8);
if (io_alloc_hash_table(&ctx->cancel_table, hash_bits))
goto err;
if (io_alloc_hash_table(&ctx->cancel_table_locked, hash_bits))
goto err;
if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free,
0, GFP_KERNEL))
goto err;
ctx->flags = p->flags;
atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT);
init_waitqueue_head(&ctx->sqo_sq_wait);
INIT_LIST_HEAD(&ctx->sqd_list);
INIT_LIST_HEAD(&ctx->cq_overflow_list);
INIT_LIST_HEAD(&ctx->io_buffers_cache);
ret = io_alloc_cache_init(&ctx->rsrc_node_cache, IO_NODE_ALLOC_CACHE_MAX,
sizeof(struct io_rsrc_node));
ret |= io_alloc_cache_init(&ctx->apoll_cache, IO_POLL_ALLOC_CACHE_MAX,
sizeof(struct async_poll));
ret |= io_alloc_cache_init(&ctx->netmsg_cache, IO_ALLOC_CACHE_MAX,
sizeof(struct io_async_msghdr));
ret |= io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX,
sizeof(struct io_async_rw));
ret |= io_alloc_cache_init(&ctx->uring_cache, IO_ALLOC_CACHE_MAX,
sizeof(struct uring_cache));
spin_lock_init(&ctx->msg_lock);
ret |= io_alloc_cache_init(&ctx->msg_cache, IO_ALLOC_CACHE_MAX,
sizeof(struct io_kiocb));
ret |= io_futex_cache_init(ctx);
if (ret)
goto err;
init_completion(&ctx->ref_comp);
xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->cq_wait);
init_waitqueue_head(&ctx->poll_wq);
init_waitqueue_head(&ctx->rsrc_quiesce_wq);
spin_lock_init(&ctx->completion_lock);
spin_lock_init(&ctx->timeout_lock);
INIT_WQ_LIST(&ctx->iopoll_list);
INIT_LIST_HEAD(&ctx->io_buffers_comp);
INIT_LIST_HEAD(&ctx->defer_list);
INIT_LIST_HEAD(&ctx->timeout_list);
INIT_LIST_HEAD(&ctx->ltimeout_list);
INIT_LIST_HEAD(&ctx->rsrc_ref_list);
init_llist_head(&ctx->work_llist);
INIT_LIST_HEAD(&ctx->tctx_list);
ctx->submit_state.free_list.next = NULL;
INIT_HLIST_HEAD(&ctx->waitid_list);
#ifdef CONFIG_FUTEX
INIT_HLIST_HEAD(&ctx->futex_list);
#endif
INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
INIT_HLIST_HEAD(&ctx->cancelable_uring_cmd);
io_napi_init(ctx);
return ctx;
err:
io_alloc_cache_free(&ctx->rsrc_node_cache, kfree);
io_alloc_cache_free(&ctx->apoll_cache, kfree);
io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free);
io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free);
io_alloc_cache_free(&ctx->uring_cache, kfree);
io_alloc_cache_free(&ctx->msg_cache, io_msg_cache_free);
io_futex_cache_free(ctx);
kfree(ctx->cancel_table.hbs);
kfree(ctx->cancel_table_locked.hbs);
xa_destroy(&ctx->io_bl_xa);
kfree(ctx);
return NULL;
}
static void io_account_cq_overflow(struct io_ring_ctx *ctx)
{
struct io_rings *r = ctx->rings;
WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1);
ctx->cq_extra--;
}
static bool req_need_defer(struct io_kiocb *req, u32 seq)
{
if (unlikely(req->flags & REQ_F_IO_DRAIN)) {
struct io_ring_ctx *ctx = req->ctx;
return seq + READ_ONCE(ctx->cq_extra) != ctx->cached_cq_tail;
}
return false;
}
static void io_clean_op(struct io_kiocb *req)
{
if (req->flags & REQ_F_BUFFER_SELECTED) {
spin_lock(&req->ctx->completion_lock);
io_kbuf_drop(req);
spin_unlock(&req->ctx->completion_lock);
}
if (req->flags & REQ_F_NEED_CLEANUP) {
const struct io_cold_def *def = &io_cold_defs[req->opcode];
if (def->cleanup)
def->cleanup(req);
}
if ((req->flags & REQ_F_POLLED) && req->apoll) {
kfree(req->apoll->double_poll);
kfree(req->apoll);
req->apoll = NULL;
}
if (req->flags & REQ_F_INFLIGHT) {
struct io_uring_task *tctx = req->task->io_uring;
atomic_dec(&tctx->inflight_tracked);
}
if (req->flags & REQ_F_CREDS)
put_cred(req->creds);
if (req->flags & REQ_F_ASYNC_DATA) {
kfree(req->async_data);
req->async_data = NULL;
}
req->flags &= ~IO_REQ_CLEAN_FLAGS;
}
static inline void io_req_track_inflight(struct io_kiocb *req)
{
if (!(req->flags & REQ_F_INFLIGHT)) {
req->flags |= REQ_F_INFLIGHT;
atomic_inc(&req->task->io_uring->inflight_tracked);
}
}
static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
{
if (WARN_ON_ONCE(!req->link))
return NULL;
req->flags &= ~REQ_F_ARM_LTIMEOUT;
req->flags |= REQ_F_LINK_TIMEOUT;
/* linked timeouts should have two refs once prep'ed */
io_req_set_refcount(req);
__io_req_set_refcount(req->link, 2);
return req->link;
}
static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
{
if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT)))
return NULL;
return __io_prep_linked_timeout(req);
}
static noinline void __io_arm_ltimeout(struct io_kiocb *req)
{
io_queue_linked_timeout(__io_prep_linked_timeout(req));
}
static inline void io_arm_ltimeout(struct io_kiocb *req)
{
if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT))
__io_arm_ltimeout(req);
}
static void io_prep_async_work(struct io_kiocb *req)
{
const struct io_issue_def *def = &io_issue_defs[req->opcode];
struct io_ring_ctx *ctx = req->ctx;
if (!(req->flags & REQ_F_CREDS)) {
req->flags |= REQ_F_CREDS;
req->creds = get_current_cred();
}
req->work.list.next = NULL;
atomic_set(&req->work.flags, 0);
if (req->flags & REQ_F_FORCE_ASYNC)
atomic_or(IO_WQ_WORK_CONCURRENT, &req->work.flags);
if (req->file && !(req->flags & REQ_F_FIXED_FILE))
req->flags |= io_file_get_flags(req->file);
if (req->file && (req->flags & REQ_F_ISREG)) {
bool should_hash = def->hash_reg_file;
/* don't serialize this request if the fs doesn't need it */
if (should_hash && (req->file->f_flags & O_DIRECT) &&
(req->file->f_op->fop_flags & FOP_DIO_PARALLEL_WRITE))
should_hash = false;
if (should_hash || (ctx->flags & IORING_SETUP_IOPOLL))
io_wq_hash_work(&req->work, file_inode(req->file));
} else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) {
if (def->unbound_nonreg_file)
atomic_or(IO_WQ_WORK_UNBOUND, &req->work.flags);
}
}
static void io_prep_async_link(struct io_kiocb *req)
{
struct io_kiocb *cur;
if (req->flags & REQ_F_LINK_TIMEOUT) {
struct io_ring_ctx *ctx = req->ctx;
spin_lock_irq(&ctx->timeout_lock);
io_for_each_link(cur, req)
io_prep_async_work(cur);
spin_unlock_irq(&ctx->timeout_lock);
} else {
io_for_each_link(cur, req)
io_prep_async_work(cur);
}
}
static void io_queue_iowq(struct io_kiocb *req)
{
struct io_kiocb *link = io_prep_linked_timeout(req);
struct io_uring_task *tctx = req->task->io_uring;
BUG_ON(!tctx);
BUG_ON(!tctx->io_wq);
/* init ->work of the whole link before punting */
io_prep_async_link(req);
/*
* Not expected to happen, but if we do have a bug where this _can_
* happen, catch it here and ensure the request is marked as
* canceled. That will make io-wq go through the usual work cancel
* procedure rather than attempt to run this request (or create a new
* worker for it).
*/
if (WARN_ON_ONCE(!same_thread_group(req->task, current)))
atomic_or(IO_WQ_WORK_CANCEL, &req->work.flags);
trace_io_uring_queue_async_work(req, io_wq_is_hashed(&req->work));
io_wq_enqueue(tctx->io_wq, &req->work);
if (link)
io_queue_linked_timeout(link);
}
static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
{
while (!list_empty(&ctx->defer_list)) {
struct io_defer_entry *de = list_first_entry(&ctx->defer_list,
struct io_defer_entry, list);
if (req_need_defer(de->req, de->seq))
break;
list_del_init(&de->list);
io_req_task_queue(de->req);
kfree(de);
}
}
void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
{
if (ctx->poll_activated)
io_poll_wq_wake(ctx);
if (ctx->off_timeout_used)
io_flush_timeouts(ctx);
if (ctx->drain_active) {
spin_lock(&ctx->completion_lock);
io_queue_deferred(ctx);
spin_unlock(&ctx->completion_lock);
}
if (ctx->has_evfd)
io_eventfd_flush_signal(ctx);
}
static inline void __io_cq_lock(struct io_ring_ctx *ctx)
{
if (!ctx->lockless_cq)
spin_lock(&ctx->completion_lock);
}
static inline void io_cq_lock(struct io_ring_ctx *ctx)
__acquires(ctx->completion_lock)
{
spin_lock(&ctx->completion_lock);
}
static inline void __io_cq_unlock_post(struct io_ring_ctx *ctx)
{
io_commit_cqring(ctx);
if (!ctx->task_complete) {
if (!ctx->lockless_cq)
spin_unlock(&ctx->completion_lock);
/* IOPOLL rings only need to wake up if it's also SQPOLL */
if (!ctx->syscall_iopoll)
io_cqring_wake(ctx);
}
io_commit_cqring_flush(ctx);
}
static void io_cq_unlock_post(struct io_ring_ctx *ctx)
__releases(ctx->completion_lock)
{
io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
io_cqring_wake(ctx);
io_commit_cqring_flush(ctx);
}
static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool dying)
{
size_t cqe_size = sizeof(struct io_uring_cqe);
lockdep_assert_held(&ctx->uring_lock);
/* don't abort if we're dying, entries must get freed */
if (!dying && __io_cqring_events(ctx) == ctx->cq_entries)
return;
if (ctx->flags & IORING_SETUP_CQE32)
cqe_size <<= 1;
io_cq_lock(ctx);
while (!list_empty(&ctx->cq_overflow_list)) {
struct io_uring_cqe *cqe;
struct io_overflow_cqe *ocqe;
ocqe = list_first_entry(&ctx->cq_overflow_list,
struct io_overflow_cqe, list);
if (!dying) {
if (!io_get_cqe_overflow(ctx, &cqe, true))
break;
memcpy(cqe, &ocqe->cqe, cqe_size);
}
list_del(&ocqe->list);
kfree(ocqe);
}
if (list_empty(&ctx->cq_overflow_list)) {
clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
atomic_andnot(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags);
}
io_cq_unlock_post(ctx);
}
static void io_cqring_overflow_kill(struct io_ring_ctx *ctx)
{
if (ctx->rings)
__io_cqring_overflow_flush(ctx, true);
}
static void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx)
{
mutex_lock(&ctx->uring_lock);
__io_cqring_overflow_flush(ctx, false);
mutex_unlock(&ctx->uring_lock);
}
/* can be called by any task */
static void io_put_task_remote(struct task_struct *task)
{
struct io_uring_task *tctx = task->io_uring;
percpu_counter_sub(&tctx->inflight, 1);
if (unlikely(atomic_read(&tctx->in_cancel)))
wake_up(&tctx->wait);
put_task_struct(task);
}
/* used by a task to put its own references */
static void io_put_task_local(struct task_struct *task)
{
task->io_uring->cached_refs++;
}
/* must to be called somewhat shortly after putting a request */
static inline void io_put_task(struct task_struct *task)
{
if (likely(task == current))
io_put_task_local(task);
else
io_put_task_remote(task);
}
void io_task_refs_refill(struct io_uring_task *tctx)
{
unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR;
percpu_counter_add(&tctx->inflight, refill);
refcount_add(refill, &current->usage);
tctx->cached_refs += refill;
}
static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
{
struct io_uring_task *tctx = task->io_uring;
unsigned int refs = tctx->cached_refs;
if (refs) {
tctx->cached_refs = 0;
percpu_counter_sub(&tctx->inflight, refs);
put_task_struct_many(task, refs);
}
}
static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
s32 res, u32 cflags, u64 extra1, u64 extra2)
{
struct io_overflow_cqe *ocqe;
size_t ocq_size = sizeof(struct io_overflow_cqe);
bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
lockdep_assert_held(&ctx->completion_lock);
if (is_cqe32)
ocq_size += sizeof(struct io_uring_cqe);
ocqe = kmalloc(ocq_size, GFP_ATOMIC | __GFP_ACCOUNT);
trace_io_uring_cqe_overflow(ctx, user_data, res, cflags, ocqe);
if (!ocqe) {
/*
* If we're in ring overflow flush mode, or in task cancel mode,
* or cannot allocate an overflow entry, then we need to drop it
* on the floor.
*/
io_account_cq_overflow(ctx);
set_bit(IO_CHECK_CQ_DROPPED_BIT, &ctx->check_cq);
return false;
}
if (list_empty(&ctx->cq_overflow_list)) {
set_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
atomic_or(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags);
}
ocqe->cqe.user_data = user_data;
ocqe->cqe.res = res;
ocqe->cqe.flags = cflags;
if (is_cqe32) {
ocqe->cqe.big_cqe[0] = extra1;
ocqe->cqe.big_cqe[1] = extra2;
}
list_add_tail(&ocqe->list, &ctx->cq_overflow_list);
return true;
}
static void io_req_cqe_overflow(struct io_kiocb *req)
{
io_cqring_event_overflow(req->ctx, req->cqe.user_data,
req->cqe.res, req->cqe.flags,
req->big_cqe.extra1, req->big_cqe.extra2);
memset(&req->big_cqe, 0, sizeof(req->big_cqe));
}
/*
* writes to the cq entry need to come after reading head; the
* control dependency is enough as we're using WRITE_ONCE to
* fill the cq entry
*/
bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow)
{
struct io_rings *rings = ctx->rings;
unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1);
unsigned int free, queued, len;
/*
* Posting into the CQ when there are pending overflowed CQEs may break
* ordering guarantees, which will affect links, F_MORE users and more.
* Force overflow the completion.
*/
if (!overflow && (ctx->check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)))
return false;
/* userspace may cheat modifying the tail, be safe and do min */
queued = min(__io_cqring_events(ctx), ctx->cq_entries);
free = ctx->cq_entries - queued;
/* we need a contiguous range, limit based on the current array offset */
len = min(free, ctx->cq_entries - off);
if (!len)
return false;
if (ctx->flags & IORING_SETUP_CQE32) {
off <<= 1;
len <<= 1;
}
ctx->cqe_cached = &rings->cqes[off];
ctx->cqe_sentinel = ctx->cqe_cached + len;
return true;
}
static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res,
u32 cflags)
{
struct io_uring_cqe *cqe;
ctx->cq_extra++;
/*
* If we can't get a cq entry, userspace overflowed the
* submission (by quite a lot). Increment the overflow count in
* the ring.
*/
if (likely(io_get_cqe(ctx, &cqe))) {
trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0);
WRITE_ONCE(cqe->user_data, user_data);
WRITE_ONCE(cqe->res, res);
WRITE_ONCE(cqe->flags, cflags);
if (ctx->flags & IORING_SETUP_CQE32) {
WRITE_ONCE(cqe->big_cqe[0], 0);
WRITE_ONCE(cqe->big_cqe[1], 0);
}
return true;
}
return false;
}
static bool __io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res,
u32 cflags)
{
bool filled;
filled = io_fill_cqe_aux(ctx, user_data, res, cflags);
if (!filled)
filled = io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
return filled;
}
bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags)
{
bool filled;
io_cq_lock(ctx);
filled = __io_post_aux_cqe(ctx, user_data, res, cflags);
io_cq_unlock_post(ctx);
return filled;
}
/*
* Must be called from inline task_work so we now a flush will happen later,
* and obviously with ctx->uring_lock held (tw always has that).
*/
void io_add_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags)
{
if (!io_fill_cqe_aux(ctx, user_data, res, cflags)) {
spin_lock(&ctx->completion_lock);
io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
spin_unlock(&ctx->completion_lock);
}
ctx->submit_state.cq_flush = true;
}
/*
* A helper for multishot requests posting additional CQEs.
* Should only be used from a task_work including IO_URING_F_MULTISHOT.
*/
bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags)
{
struct io_ring_ctx *ctx = req->ctx;
bool posted;
lockdep_assert(!io_wq_current_is_worker());
lockdep_assert_held(&ctx->uring_lock);
__io_cq_lock(ctx);
posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
ctx->submit_state.cq_flush = true;
__io_cq_unlock_post(ctx);
return posted;
}
static void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
/*
* All execution paths but io-wq use the deferred completions by
* passing IO_URING_F_COMPLETE_DEFER and thus should not end up here.
*/
if (WARN_ON_ONCE(!(issue_flags & IO_URING_F_IOWQ)))
return;
/*
* Handle special CQ sync cases via task_work. DEFER_TASKRUN requires
* the submitter task context, IOPOLL protects with uring_lock.
*/
if (ctx->task_complete || (ctx->flags & IORING_SETUP_IOPOLL)) {
req->io_task_work.func = io_req_task_complete;
io_req_task_work_add(req);
return;
}
io_cq_lock(ctx);
if (!(req->flags & REQ_F_CQE_SKIP)) {
if (!io_fill_cqe_req(ctx, req))
io_req_cqe_overflow(req);
}
io_cq_unlock_post(ctx);
/*
* We don't free the request here because we know it's called from
* io-wq only, which holds a reference, so it cannot be the last put.
*/
req_ref_put(req);
}
void io_req_defer_failed(struct io_kiocb *req, s32 res)
__must_hold(&ctx->uring_lock)
{
const struct io_cold_def *def = &io_cold_defs[req->opcode];
lockdep_assert_held(&req->ctx->uring_lock);
req_set_fail(req);
io_req_set_res(req, res, io_put_kbuf(req, IO_URING_F_UNLOCKED));
if (def->fail)
def->fail(req);
io_req_complete_defer(req);
}
/*
* Don't initialise the fields below on every allocation, but do that in
* advance and keep them valid across allocations.
*/
static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx)
{
req->ctx = ctx;
req->link = NULL;
req->async_data = NULL;
/* not necessary, but safer to zero */
memset(&req->cqe, 0, sizeof(req->cqe));
memset(&req->big_cqe, 0, sizeof(req->big_cqe));
}
/*
* A request might get retired back into the request caches even before opcode
* handlers and io_issue_sqe() are done with it, e.g. inline completion path.
* Because of that, io_alloc_req() should be called only under ->uring_lock
* and with extra caution to not get a request that is still worked on.
*/
__cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
void *reqs[IO_REQ_ALLOC_BATCH];
int ret;
ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), reqs);
/*
* Bulk alloc is all-or-nothing. If we fail to get a batch,
* retry single alloc to be on the safe side.
*/
if (unlikely(ret <= 0)) {
reqs[0] = kmem_cache_alloc(req_cachep, gfp);
if (!reqs[0])
return false;
ret = 1;
}
percpu_ref_get_many(&ctx->refs, ret);
while (ret--) {
struct io_kiocb *req = reqs[ret];
io_preinit_req(req, ctx);
io_req_add_to_cache(req, ctx);
}
return true;
}
__cold void io_free_req(struct io_kiocb *req)
{
/* refs were already put, restore them for io_req_task_complete() */
req->flags &= ~REQ_F_REFCOUNT;
/* we only want to free it, don't post CQEs */
req->flags |= REQ_F_CQE_SKIP;
req->io_task_work.func = io_req_task_complete;
io_req_task_work_add(req);
}
static void __io_req_find_next_prep(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
spin_lock(&ctx->completion_lock);
io_disarm_next(req);
spin_unlock(&ctx->completion_lock);
}
static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req)
{
struct io_kiocb *nxt;
/*
* If LINK is set, we have dependent requests in this chain. If we
* didn't fail this request, queue the first one up, moving any other
* dependencies to the next request. In case of failure, fail the rest
* of the chain.
*/
if (unlikely(req->flags & IO_DISARM_MASK))
__io_req_find_next_prep(req);
nxt = req->link;
req->link = NULL;
return nxt;
}
static void ctx_flush_and_put(struct io_ring_ctx *ctx, struct io_tw_state *ts)
{
if (!ctx)
return;
if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
io_submit_flush_completions(ctx);
mutex_unlock(&ctx->uring_lock);
percpu_ref_put(&ctx->refs);
}
/*
* Run queued task_work, returning the number of entries processed in *count.
* If more entries than max_entries are available, stop processing once this
* is reached and return the rest of the list.
*/
struct llist_node *io_handle_tw_list(struct llist_node *node,
unsigned int *count,
unsigned int max_entries)
{
struct io_ring_ctx *ctx = NULL;
struct io_tw_state ts = { };
do {
struct llist_node *next = node->next;
struct io_kiocb *req = container_of(node, struct io_kiocb,
io_task_work.node);
if (req->ctx != ctx) {
ctx_flush_and_put(ctx, &ts);
ctx = req->ctx;
mutex_lock(&ctx->uring_lock);
percpu_ref_get(&ctx->refs);
}
INDIRECT_CALL_2(req->io_task_work.func,
io_poll_task_func, io_req_rw_complete,
req, &ts);
node = next;
(*count)++;
if (unlikely(need_resched())) {
ctx_flush_and_put(ctx, &ts);
ctx = NULL;
cond_resched();
}
} while (node && *count < max_entries);
ctx_flush_and_put(ctx, &ts);
return node;
}
/**
* io_llist_xchg - swap all entries in a lock-less list
* @head: the head of lock-less list to delete all entries
* @new: new entry as the head of the list
*
* If list is empty, return NULL, otherwise, return the pointer to the first entry.
* The order of entries returned is from the newest to the oldest added one.
*/
static inline struct llist_node *io_llist_xchg(struct llist_head *head,
struct llist_node *new)
{
return xchg(&head->first, new);
}
static __cold void io_fallback_tw(struct io_uring_task *tctx, bool sync)
{
struct llist_node *node = llist_del_all(&tctx->task_list);
struct io_ring_ctx *last_ctx = NULL;
struct io_kiocb *req;
while (node) {
req = container_of(node, struct io_kiocb, io_task_work.node);
node = node->next;
if (sync && last_ctx != req->ctx) {
if (last_ctx) {
flush_delayed_work(&last_ctx->fallback_work);
percpu_ref_put(&last_ctx->refs);
}
last_ctx = req->ctx;
percpu_ref_get(&last_ctx->refs);
}
if (llist_add(&req->io_task_work.node,
&req->ctx->fallback_llist))
schedule_delayed_work(&req->ctx->fallback_work, 1);
}
if (last_ctx) {
flush_delayed_work(&last_ctx->fallback_work);
percpu_ref_put(&last_ctx->refs);
}
}
struct llist_node *tctx_task_work_run(struct io_uring_task *tctx,
unsigned int max_entries,
unsigned int *count)
{
struct llist_node *node;
if (unlikely(current->flags & PF_EXITING)) {
io_fallback_tw(tctx, true);
return NULL;
}
node = llist_del_all(&tctx->task_list);
if (node) {
node = llist_reverse_order(node);
node = io_handle_tw_list(node, count, max_entries);
}
/* relaxed read is enough as only the task itself sets ->in_cancel */
if (unlikely(atomic_read(&tctx->in_cancel)))
io_uring_drop_tctx_refs(current);
trace_io_uring_task_work_run(tctx, *count);
return node;
}
void tctx_task_work(struct callback_head *cb)
{
struct io_uring_task *tctx;
struct llist_node *ret;
unsigned int count = 0;
tctx = container_of(cb, struct io_uring_task, task_work);
ret = tctx_task_work_run(tctx, UINT_MAX, &count);
/* can't happen */
WARN_ON_ONCE(ret);
}
static inline void io_req_local_work_add(struct io_kiocb *req,
struct io_ring_ctx *ctx,
unsigned flags)
{
unsigned nr_wait, nr_tw, nr_tw_prev;
struct llist_node *head;
/* See comment above IO_CQ_WAKE_INIT */
BUILD_BUG_ON(IO_CQ_WAKE_FORCE <= IORING_MAX_CQ_ENTRIES);
/*
* We don't know how many reuqests is there in the link and whether
* they can even be queued lazily, fall back to non-lazy.
*/
if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK))
flags &= ~IOU_F_TWQ_LAZY_WAKE;
guard(rcu)();
head = READ_ONCE(ctx->work_llist.first);
do {
nr_tw_prev = 0;
if (head) {
struct io_kiocb *first_req = container_of(head,
struct io_kiocb,
io_task_work.node);
/*
* Might be executed at any moment, rely on
* SLAB_TYPESAFE_BY_RCU to keep it alive.
*/
nr_tw_prev = READ_ONCE(first_req->nr_tw);
}
/*
* Theoretically, it can overflow, but that's fine as one of
* previous adds should've tried to wake the task.
*/
nr_tw = nr_tw_prev + 1;
if (!(flags & IOU_F_TWQ_LAZY_WAKE))
nr_tw = IO_CQ_WAKE_FORCE;
req->nr_tw = nr_tw;
req->io_task_work.node.next = head;
} while (!try_cmpxchg(&ctx->work_llist.first, &head,
&req->io_task_work.node));
/*
* cmpxchg implies a full barrier, which pairs with the barrier
* in set_current_state() on the io_cqring_wait() side. It's used
* to ensure that either we see updated ->cq_wait_nr, or waiters
* going to sleep will observe the work added to the list, which
* is similar to the wait/wawke task state sync.
*/
if (!head) {
if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
if (ctx->has_evfd)
io_eventfd_signal(ctx);
}
nr_wait = atomic_read(&ctx->cq_wait_nr);
/* not enough or no one is waiting */
if (nr_tw < nr_wait)
return;
/* the previous add has already woken it up */
if (nr_tw_prev >= nr_wait)
return;
wake_up_state(ctx->submitter_task, TASK_INTERRUPTIBLE);
}
static void io_req_normal_work_add(struct io_kiocb *req)
{
struct io_uring_task *tctx = req->task->io_uring;
struct io_ring_ctx *ctx = req->ctx;
/* task_work already pending, we're done */
if (!llist_add(&req->io_task_work.node, &tctx->task_list))
return;
if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
/* SQPOLL doesn't need the task_work added, it'll run it itself */
if (ctx->flags & IORING_SETUP_SQPOLL) {
struct io_sq_data *sqd = ctx->sq_data;
if (sqd->thread)
__set_notify_signal(sqd->thread);
return;
}
if (likely(!task_work_add(req->task, &tctx->task_work, ctx->notify_method)))
return;
io_fallback_tw(tctx, false);
}
void __io_req_task_work_add(struct io_kiocb *req, unsigned flags)
{
if (req->ctx->flags & IORING_SETUP_DEFER_TASKRUN)
io_req_local_work_add(req, req->ctx, flags);
else
io_req_normal_work_add(req);
}
void io_req_task_work_add_remote(struct io_kiocb *req, struct io_ring_ctx *ctx,
unsigned flags)
{
if (WARN_ON_ONCE(!(ctx->flags & IORING_SETUP_DEFER_TASKRUN)))
return;
io_req_local_work_add(req, ctx, flags);
}
static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx)
{
struct llist_node *node;
node = llist_del_all(&ctx->work_llist);
while (node) {
struct io_kiocb *req = container_of(node, struct io_kiocb,
io_task_work.node);
node = node->next;
io_req_normal_work_add(req);
}
}
static bool io_run_local_work_continue(struct io_ring_ctx *ctx, int events,
int min_events)
{
if (llist_empty(&ctx->work_llist))
return false;
if (events < min_events)
return true;
if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
return false;
}
static int __io_run_local_work(struct io_ring_ctx *ctx, struct io_tw_state *ts,
int min_events)
{
struct llist_node *node;
unsigned int loops = 0;
int ret = 0;
if (WARN_ON_ONCE(ctx->submitter_task != current))
return -EEXIST;
if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
again:
/*
* llists are in reverse order, flip it back the right way before
* running the pending items.
*/
node = llist_reverse_order(io_llist_xchg(&ctx->work_llist, NULL));
while (node) {
struct llist_node *next = node->next;
struct io_kiocb *req = container_of(node, struct io_kiocb,
io_task_work.node);
INDIRECT_CALL_2(req->io_task_work.func,
io_poll_task_func, io_req_rw_complete,
req, ts);
ret++;
node = next;
}
loops++;
if (io_run_local_work_continue(ctx, ret, min_events))
goto again;
io_submit_flush_completions(ctx);
if (io_run_local_work_continue(ctx, ret, min_events))
goto again;
trace_io_uring_local_work_run(ctx, ret, loops);
return ret;
}
static inline int io_run_local_work_locked(struct io_ring_ctx *ctx,
int min_events)
{
struct io_tw_state ts = {};
if (llist_empty(&ctx->work_llist))
return 0;
return __io_run_local_work(ctx, &ts, min_events);
}
static int io_run_local_work(struct io_ring_ctx *ctx, int min_events)
{
struct io_tw_state ts = {};
int ret;
mutex_lock(&ctx->uring_lock);
ret = __io_run_local_work(ctx, &ts, min_events);
mutex_unlock(&ctx->uring_lock);
return ret;
}
static void io_req_task_cancel(struct io_kiocb *req, struct io_tw_state *ts)
{
io_tw_lock(req->ctx, ts);
io_req_defer_failed(req, req->cqe.res);
}
void io_req_task_submit(struct io_kiocb *req, struct io_tw_state *ts)
{
io_tw_lock(req->ctx, ts);
/* req->task == current here, checking PF_EXITING is safe */
if (unlikely(req->task->flags & PF_EXITING))
io_req_defer_failed(req, -EFAULT);
else if (req->flags & REQ_F_FORCE_ASYNC)
io_queue_iowq(req);
else
io_queue_sqe(req);
}
void io_req_task_queue_fail(struct io_kiocb *req, int ret)
{
io_req_set_res(req, ret, 0);
req->io_task_work.func = io_req_task_cancel;
io_req_task_work_add(req);
}
void io_req_task_queue(struct io_kiocb *req)
{
req->io_task_work.func = io_req_task_submit;
io_req_task_work_add(req);
}
void io_queue_next(struct io_kiocb *req)
{
struct io_kiocb *nxt = io_req_find_next(req);
if (nxt)
io_req_task_queue(nxt);
}
static void io_free_batch_list(struct io_ring_ctx *ctx,
struct io_wq_work_node *node)
__must_hold(&ctx->uring_lock)
{
do {
struct io_kiocb *req = container_of(node, struct io_kiocb,
comp_list);
if (unlikely(req->flags & IO_REQ_CLEAN_SLOW_FLAGS)) {
if (req->flags & REQ_F_REFCOUNT) {
node = req->comp_list.next;
if (!req_ref_put_and_test(req))
continue;
}
if ((req->flags & REQ_F_POLLED) && req->apoll) {
struct async_poll *apoll = req->apoll;
if (apoll->double_poll)
kfree(apoll->double_poll);
if (!io_alloc_cache_put(&ctx->apoll_cache, apoll))
kfree(apoll);
req->flags &= ~REQ_F_POLLED;
}
if (req->flags & IO_REQ_LINK_FLAGS)
io_queue_next(req);
if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS))
io_clean_op(req);
}
io_put_file(req);
io_put_rsrc_node(ctx, req->rsrc_node);
io_put_task(req->task);
node = req->comp_list.next;
io_req_add_to_cache(req, ctx);
} while (node);
}
void __io_submit_flush_completions(struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
struct io_submit_state *state = &ctx->submit_state;
struct io_wq_work_node *node;
__io_cq_lock(ctx);
__wq_list_for_each(node, &state->compl_reqs) {
struct io_kiocb *req = container_of(node, struct io_kiocb,
comp_list);
if (!(req->flags & REQ_F_CQE_SKIP) &&
unlikely(!io_fill_cqe_req(ctx, req))) {
if (ctx->lockless_cq) {
spin_lock(&ctx->completion_lock);
io_req_cqe_overflow(req);
spin_unlock(&ctx->completion_lock);
} else {
io_req_cqe_overflow(req);
}
}
}
__io_cq_unlock_post(ctx);
if (!wq_list_empty(&state->compl_reqs)) {
io_free_batch_list(ctx, state->compl_reqs.first);
INIT_WQ_LIST(&state->compl_reqs);
}
ctx->submit_state.cq_flush = false;
}
static unsigned io_cqring_events(struct io_ring_ctx *ctx)
{
/* See comment at the top of this file */
smp_rmb();
return __io_cqring_events(ctx);
}
/*
* We can't just wait for polled events to come to us, we have to actively
* find and complete them.
*/
static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
{
if (!(ctx->flags & IORING_SETUP_IOPOLL))
return;
mutex_lock(&ctx->uring_lock);
while (!wq_list_empty(&ctx->iopoll_list)) {
/* let it sleep and repeat later if can't complete a request */
if (io_do_iopoll(ctx, true) == 0)
break;
/*
* Ensure we allow local-to-the-cpu processing to take place,
* in this case we need to ensure that we reap all events.
* Also let task_work, etc. to progress by releasing the mutex
*/
if (need_resched()) {
mutex_unlock(&ctx->uring_lock);
cond_resched();
mutex_lock(&ctx->uring_lock);
}
}
mutex_unlock(&ctx->uring_lock);
}
static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
{
unsigned int nr_events = 0;
unsigned long check_cq;
lockdep_assert_held(&ctx->uring_lock);
if (!io_allowed_run_tw(ctx))
return -EEXIST;
check_cq = READ_ONCE(ctx->check_cq);
if (unlikely(check_cq)) {
if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
__io_cqring_overflow_flush(ctx, false);
/*
* Similarly do not spin if we have not informed the user of any
* dropped CQE.
*/
if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))
return -EBADR;
}
/*
* Don't enter poll loop if we already have events pending.
* If we do, we can potentially be spinning for commands that
* already triggered a CQE (eg in error).
*/
if (io_cqring_events(ctx))
return 0;
do {
int ret = 0;
/*
* If a submit got punted to a workqueue, we can have the
* application entering polling for a command before it gets
* issued. That app will hold the uring_lock for the duration
* of the poll right here, so we need to take a breather every
* now and then to ensure that the issue has a chance to add
* the poll to the issued list. Otherwise we can spin here
* forever, while the workqueue is stuck trying to acquire the
* very same mutex.
*/
if (wq_list_empty(&ctx->iopoll_list) ||
io_task_work_pending(ctx)) {
u32 tail = ctx->cached_cq_tail;
(void) io_run_local_work_locked(ctx, min);
if (task_work_pending(current) ||
wq_list_empty(&ctx->iopoll_list)) {
mutex_unlock(&ctx->uring_lock);
io_run_task_work();
mutex_lock(&ctx->uring_lock);
}
/* some requests don't go through iopoll_list */
if (tail != ctx->cached_cq_tail ||
wq_list_empty(&ctx->iopoll_list))
break;
}
ret = io_do_iopoll(ctx, !min);
if (unlikely(ret < 0))
return ret;
if (task_sigpending(current))
return -EINTR;
if (need_resched())
break;
nr_events += ret;
} while (nr_events < min);
return 0;
}
void io_req_task_complete(struct io_kiocb *req, struct io_tw_state *ts)
{
io_req_complete_defer(req);
}
/*
* After the iocb has been issued, it's safe to be found on the poll list.
* Adding the kiocb to the list AFTER submission ensures that we don't
* find it from a io_do_iopoll() thread before the issuer is done
* accessing the kiocb cookie.
*/
static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
const bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
/* workqueue context doesn't hold uring_lock, grab it now */
if (unlikely(needs_lock))
mutex_lock(&ctx->uring_lock);
/*
* Track whether we have multiple files in our lists. This will impact
* how we do polling eventually, not spinning if we're on potentially
* different devices.
*/
if (wq_list_empty(&ctx->iopoll_list)) {
ctx->poll_multi_queue = false;
} else if (!ctx->poll_multi_queue) {
struct io_kiocb *list_req;
list_req = container_of(ctx->iopoll_list.first, struct io_kiocb,
comp_list);
if (list_req->file != req->file)
ctx->poll_multi_queue = true;
}
/*
* For fast devices, IO may have already completed. If it has, add
* it to the front so we find it first.
*/
if (READ_ONCE(req->iopoll_completed))
wq_list_add_head(&req->comp_list, &ctx->iopoll_list);
else
wq_list_add_tail(&req->comp_list, &ctx->iopoll_list);
if (unlikely(needs_lock)) {
/*
* If IORING_SETUP_SQPOLL is enabled, sqes are either handle
* in sq thread task context or in io worker task context. If
* current task context is sq thread, we don't need to check
* whether should wake up sq thread.
*/
if ((ctx->flags & IORING_SETUP_SQPOLL) &&
wq_has_sleeper(&ctx->sq_data->wait))
wake_up(&ctx->sq_data->wait);
mutex_unlock(&ctx->uring_lock);
}
}
io_req_flags_t io_file_get_flags(struct file *file)
{
io_req_flags_t res = 0;
if (S_ISREG(file_inode(file)->i_mode))
res |= REQ_F_ISREG;
if ((file->f_flags & O_NONBLOCK) || (file->f_mode & FMODE_NOWAIT))
res |= REQ_F_SUPPORT_NOWAIT;
return res;
}
bool io_alloc_async_data(struct io_kiocb *req)
{
const struct io_issue_def *def = &io_issue_defs[req->opcode];
WARN_ON_ONCE(!def->async_size);
req->async_data = kmalloc(def->async_size, GFP_KERNEL);
if (req->async_data) {
req->flags |= REQ_F_ASYNC_DATA;
return false;
}
return true;
}
static u32 io_get_sequence(struct io_kiocb *req)
{
u32 seq = req->ctx->cached_sq_head;
struct io_kiocb *cur;
/* need original cached_sq_head, but it was increased for each req */
io_for_each_link(cur, req)
seq--;
return seq;
}
static __cold void io_drain_req(struct io_kiocb *req)
__must_hold(&ctx->uring_lock)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_defer_entry *de;
int ret;
u32 seq = io_get_sequence(req);
/* Still need defer if there is pending req in defer list. */
spin_lock(&ctx->completion_lock);
if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) {
spin_unlock(&ctx->completion_lock);
queue:
ctx->drain_active = false;
io_req_task_queue(req);
return;
}
spin_unlock(&ctx->completion_lock);
io_prep_async_link(req);
de = kmalloc(sizeof(*de), GFP_KERNEL);
if (!de) {
ret = -ENOMEM;
io_req_defer_failed(req, ret);
return;
}
spin_lock(&ctx->completion_lock);
if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) {
spin_unlock(&ctx->completion_lock);
kfree(de);
goto queue;
}
trace_io_uring_defer(req);
de->req = req;
de->seq = seq;
list_add_tail(&de->list, &ctx->defer_list);
spin_unlock(&ctx->completion_lock);
}
static bool io_assign_file(struct io_kiocb *req, const struct io_issue_def *def,
unsigned int issue_flags)
{
if (req->file || !def->needs_file)
return true;
if (req->flags & REQ_F_FIXED_FILE)
req->file = io_file_get_fixed(req, req->cqe.fd, issue_flags);
else
req->file = io_file_get_normal(req, req->cqe.fd);
return !!req->file;
}
static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
{
const struct io_issue_def *def = &io_issue_defs[req->opcode];
const struct cred *creds = NULL;
int ret;
if (unlikely(!io_assign_file(req, def, issue_flags)))
return -EBADF;
if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred()))
creds = override_creds(req->creds);
if (!def->audit_skip)
audit_uring_entry(req->opcode);
ret = def->issue(req, issue_flags);
if (!def->audit_skip)
audit_uring_exit(!ret, ret);
if (creds)
revert_creds(creds);
if (ret == IOU_OK) {
if (issue_flags & IO_URING_F_COMPLETE_DEFER)
io_req_complete_defer(req);
else
io_req_complete_post(req, issue_flags);
return 0;
}
if (ret == IOU_ISSUE_SKIP_COMPLETE) {
ret = 0;
io_arm_ltimeout(req);
/* If the op doesn't have a file, we're not polling for it */
if ((req->ctx->flags & IORING_SETUP_IOPOLL) && def->iopoll_queue)
io_iopoll_req_issued(req, issue_flags);
}
return ret;
}
int io_poll_issue(struct io_kiocb *req, struct io_tw_state *ts)
{
io_tw_lock(req->ctx, ts);
return io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_MULTISHOT|
IO_URING_F_COMPLETE_DEFER);
}
struct io_wq_work *io_wq_free_work(struct io_wq_work *work)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
struct io_kiocb *nxt = NULL;
if (req_ref_put_and_test(req)) {
if (req->flags & IO_REQ_LINK_FLAGS)
nxt = io_req_find_next(req);
io_free_req(req);
}
return nxt ? &nxt->work : NULL;
}
void io_wq_submit_work(struct io_wq_work *work)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
const struct io_issue_def *def = &io_issue_defs[req->opcode];
unsigned int issue_flags = IO_URING_F_UNLOCKED | IO_URING_F_IOWQ;
bool needs_poll = false;
int ret = 0, err = -ECANCELED;
/* one will be dropped by ->io_wq_free_work() after returning to io-wq */
if (!(req->flags & REQ_F_REFCOUNT))
__io_req_set_refcount(req, 2);
else
req_ref_get(req);
io_arm_ltimeout(req);
/* either cancelled or io-wq is dying, so don't touch tctx->iowq */
if (atomic_read(&work->flags) & IO_WQ_WORK_CANCEL) {
fail:
io_req_task_queue_fail(req, err);
return;
}
if (!io_assign_file(req, def, issue_flags)) {
err = -EBADF;
atomic_or(IO_WQ_WORK_CANCEL, &work->flags);
goto fail;
}
/*
* If DEFER_TASKRUN is set, it's only allowed to post CQEs from the
* submitter task context. Final request completions are handed to the
* right context, however this is not the case of auxiliary CQEs,
* which is the main mean of operation for multishot requests.
* Don't allow any multishot execution from io-wq. It's more restrictive
* than necessary and also cleaner.
*/
if (req->flags & REQ_F_APOLL_MULTISHOT) {
err = -EBADFD;
if (!io_file_can_poll(req))
goto fail;
if (req->file->f_flags & O_NONBLOCK ||
req->file->f_mode & FMODE_NOWAIT) {
err = -ECANCELED;
if (io_arm_poll_handler(req, issue_flags) != IO_APOLL_OK)
goto fail;
return;
} else {
req->flags &= ~REQ_F_APOLL_MULTISHOT;
}
}
if (req->flags & REQ_F_FORCE_ASYNC) {
bool opcode_poll = def->pollin || def->pollout;
if (opcode_poll && io_file_can_poll(req)) {
needs_poll = true;
issue_flags |= IO_URING_F_NONBLOCK;
}
}
do {
ret = io_issue_sqe(req, issue_flags);
if (ret != -EAGAIN)
break;
/*
* If REQ_F_NOWAIT is set, then don't wait or retry with
* poll. -EAGAIN is final for that case.
*/
if (req->flags & REQ_F_NOWAIT)
break;
/*
* We can get EAGAIN for iopolled IO even though we're
* forcing a sync submission from here, since we can't
* wait for request slots on the block side.
*/
if (!needs_poll) {
if (!(req->ctx->flags & IORING_SETUP_IOPOLL))
break;
if (io_wq_worker_stopped())
break;
cond_resched();
continue;
}
if (io_arm_poll_handler(req, issue_flags) == IO_APOLL_OK)
return;
/* aborted or ready, in either case retry blocking */
needs_poll = false;
issue_flags &= ~IO_URING_F_NONBLOCK;
} while (1);
/* avoid locking problems by failing it from a clean context */
if (ret)
io_req_task_queue_fail(req, ret);
}
inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_fixed_file *slot;
struct file *file = NULL;
io_ring_submit_lock(ctx, issue_flags);
if (unlikely((unsigned int)fd >= ctx->nr_user_files))
goto out;
fd = array_index_nospec(fd, ctx->nr_user_files);
slot = io_fixed_file_slot(&ctx->file_table, fd);
if (!req->rsrc_node)
__io_req_set_rsrc_node(req, ctx);
req->flags |= io_slot_flags(slot);
file = io_slot_file(slot);
out:
io_ring_submit_unlock(ctx, issue_flags);
return file;
}
struct file *io_file_get_normal(struct io_kiocb *req, int fd)
{
struct file *file = fget(fd);
trace_io_uring_file_get(req, fd);
/* we don't allow fixed io_uring files */
if (file && io_is_uring_fops(file))
io_req_track_inflight(req);
return file;
}
static void io_queue_async(struct io_kiocb *req, int ret)
__must_hold(&req->ctx->uring_lock)
{
struct io_kiocb *linked_timeout;
if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) {
io_req_defer_failed(req, ret);
return;
}
linked_timeout = io_prep_linked_timeout(req);
switch (io_arm_poll_handler(req, 0)) {
case IO_APOLL_READY:
io_kbuf_recycle(req, 0);
io_req_task_queue(req);
break;
case IO_APOLL_ABORTED:
io_kbuf_recycle(req, 0);
io_queue_iowq(req);
break;
case IO_APOLL_OK:
break;
}
if (linked_timeout)
io_queue_linked_timeout(linked_timeout);
}
static inline void io_queue_sqe(struct io_kiocb *req)
__must_hold(&req->ctx->uring_lock)
{
int ret;
ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER);
/*
* We async punt it if the file wasn't marked NOWAIT, or if the file
* doesn't support non-blocking read/write attempts
*/
if (unlikely(ret))
io_queue_async(req, ret);
}
static void io_queue_sqe_fallback(struct io_kiocb *req)
__must_hold(&req->ctx->uring_lock)
{
if (unlikely(req->flags & REQ_F_FAIL)) {
/*
* We don't submit, fail them all, for that replace hardlinks
* with normal links. Extra REQ_F_LINK is tolerated.
*/
req->flags &= ~REQ_F_HARDLINK;
req->flags |= REQ_F_LINK;
io_req_defer_failed(req, req->cqe.res);
} else {
if (unlikely(req->ctx->drain_active))
io_drain_req(req);
else
io_queue_iowq(req);
}
}
/*
* Check SQE restrictions (opcode and flags).
*
* Returns 'true' if SQE is allowed, 'false' otherwise.
*/
static inline bool io_check_restriction(struct io_ring_ctx *ctx,
struct io_kiocb *req,
unsigned int sqe_flags)
{
if (!test_bit(req->opcode, ctx->restrictions.sqe_op))
return false;
if ((sqe_flags & ctx->restrictions.sqe_flags_required) !=
ctx->restrictions.sqe_flags_required)
return false;
if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed |
ctx->restrictions.sqe_flags_required))
return false;
return true;
}
static void io_init_req_drain(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_kiocb *head = ctx->submit_state.link.head;
ctx->drain_active = true;
if (head) {
/*
* If we need to drain a request in the middle of a link, drain
* the head request and the next request/link after the current
* link. Considering sequential execution of links,
* REQ_F_IO_DRAIN will be maintained for every request of our
* link.
*/
head->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC;
ctx->drain_next = true;
}
}
static __cold int io_init_fail_req(struct io_kiocb *req, int err)
{
/* ensure per-opcode data is cleared if we fail before prep */
memset(&req->cmd.data, 0, sizeof(req->cmd.data));
return err;
}
static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
const struct io_uring_sqe *sqe)
__must_hold(&ctx->uring_lock)
{
const struct io_issue_def *def;
unsigned int sqe_flags;
int personality;
u8 opcode;
/* req is partially pre-initialised, see io_preinit_req() */
req->opcode = opcode = READ_ONCE(sqe->opcode);
/* same numerical values with corresponding REQ_F_*, safe to copy */
sqe_flags = READ_ONCE(sqe->flags);
req->flags = (io_req_flags_t) sqe_flags;
req->cqe.user_data = READ_ONCE(sqe->user_data);
req->file = NULL;
req->rsrc_node = NULL;
req->task = current;
req->cancel_seq_set = false;
if (unlikely(opcode >= IORING_OP_LAST)) {
req->opcode = 0;
return io_init_fail_req(req, -EINVAL);
}
def = &io_issue_defs[opcode];
if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) {
/* enforce forwards compatibility on users */
if (sqe_flags & ~SQE_VALID_FLAGS)
return io_init_fail_req(req, -EINVAL);
if (sqe_flags & IOSQE_BUFFER_SELECT) {
if (!def->buffer_select)
return io_init_fail_req(req, -EOPNOTSUPP);
req->buf_index = READ_ONCE(sqe->buf_group);
}
if (sqe_flags & IOSQE_CQE_SKIP_SUCCESS)
ctx->drain_disabled = true;
if (sqe_flags & IOSQE_IO_DRAIN) {
if (ctx->drain_disabled)
return io_init_fail_req(req, -EOPNOTSUPP);
io_init_req_drain(req);
}
}
if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) {
if (ctx->restricted && !io_check_restriction(ctx, req, sqe_flags))
return io_init_fail_req(req, -EACCES);
/* knock it to the slow queue path, will be drained there */
if (ctx->drain_active)
req->flags |= REQ_F_FORCE_ASYNC;
/* if there is no link, we're at "next" request and need to drain */
if (unlikely(ctx->drain_next) && !ctx->submit_state.link.head) {
ctx->drain_next = false;
ctx->drain_active = true;
req->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC;
}
}
if (!def->ioprio && sqe->ioprio)
return io_init_fail_req(req, -EINVAL);
if (!def->iopoll && (ctx->flags & IORING_SETUP_IOPOLL))
return io_init_fail_req(req, -EINVAL);
if (def->needs_file) {
struct io_submit_state *state = &ctx->submit_state;
req->cqe.fd = READ_ONCE(sqe->fd);
/*
* Plug now if we have more than 2 IO left after this, and the
* target is potentially a read/write to block based storage.
*/
if (state->need_plug && def->plug) {
state->plug_started = true;
state->need_plug = false;
blk_start_plug_nr_ios(&state->plug, state->submit_nr);
}
}
personality = READ_ONCE(sqe->personality);
if (personality) {
int ret;
req->creds = xa_load(&ctx->personalities, personality);
if (!req->creds)
return io_init_fail_req(req, -EINVAL);
get_cred(req->creds);
ret = security_uring_override_creds(req->creds);
if (ret) {
put_cred(req->creds);
return io_init_fail_req(req, ret);
}
req->flags |= REQ_F_CREDS;
}
return def->prep(req, sqe);
}
static __cold int io_submit_fail_init(const struct io_uring_sqe *sqe,
struct io_kiocb *req, int ret)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_submit_link *link = &ctx->submit_state.link;
struct io_kiocb *head = link->head;
trace_io_uring_req_failed(sqe, req, ret);
/*
* Avoid breaking links in the middle as it renders links with SQPOLL
* unusable. Instead of failing eagerly, continue assembling the link if
* applicable and mark the head with REQ_F_FAIL. The link flushing code
* should find the flag and handle the rest.
*/
req_fail_link_node(req, ret);
if (head && !(head->flags & REQ_F_FAIL))
req_fail_link_node(head, -ECANCELED);
if (!(req->flags & IO_REQ_LINK_FLAGS)) {
if (head) {
link->last->link = req;
link->head = NULL;
req = head;
}
io_queue_sqe_fallback(req);
return ret;
}
if (head)
link->last->link = req;
else
link->head = req;
link->last = req;
return 0;
}
static inline int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
const struct io_uring_sqe *sqe)
__must_hold(&ctx->uring_lock)
{
struct io_submit_link *link = &ctx->submit_state.link;
int ret;
ret = io_init_req(ctx, req, sqe);
if (unlikely(ret))
return io_submit_fail_init(sqe, req, ret);
trace_io_uring_submit_req(req);
/*
* If we already have a head request, queue this one for async
* submittal once the head completes. If we don't have a head but
* IOSQE_IO_LINK is set in the sqe, start a new head. This one will be
* submitted sync once the chain is complete. If none of those
* conditions are true (normal request), then just queue it.
*/
if (unlikely(link->head)) {
trace_io_uring_link(req, link->head);
link->last->link = req;
link->last = req;
if (req->flags & IO_REQ_LINK_FLAGS)
return 0;
/* last request of the link, flush it */
req = link->head;
link->head = NULL;
if (req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL))
goto fallback;
} else if (unlikely(req->flags & (IO_REQ_LINK_FLAGS |
REQ_F_FORCE_ASYNC | REQ_F_FAIL))) {
if (req->flags & IO_REQ_LINK_FLAGS) {
link->head = req;
link->last = req;
} else {
fallback:
io_queue_sqe_fallback(req);
}
return 0;
}
io_queue_sqe(req);
return 0;
}
/*
* Batched submission is done, ensure local IO is flushed out.
*/
static void io_submit_state_end(struct io_ring_ctx *ctx)
{
struct io_submit_state *state = &ctx->submit_state;
if (unlikely(state->link.head))
io_queue_sqe_fallback(state->link.head);
/* flush only after queuing links as they can generate completions */
io_submit_flush_completions(ctx);
if (state->plug_started)
blk_finish_plug(&state->plug);
}
/*
* Start submission side cache.
*/
static void io_submit_state_start(struct io_submit_state *state,
unsigned int max_ios)
{
state->plug_started = false;
state->need_plug = max_ios > 2;
state->submit_nr = max_ios;
/* set only head, no need to init link_last in advance */
state->link.head = NULL;
}
static void io_commit_sqring(struct io_ring_ctx *ctx)
{
struct io_rings *rings = ctx->rings;
/*
* Ensure any loads from the SQEs are done at this point,
* since once we write the new head, the application could
* write new data to them.
*/
smp_store_release(&rings->sq.head, ctx->cached_sq_head);
}
/*
* Fetch an sqe, if one is available. Note this returns a pointer to memory
* that is mapped by userspace. This means that care needs to be taken to
* ensure that reads are stable, as we cannot rely on userspace always
* being a good citizen. If members of the sqe are validated and then later
* used, it's important that those reads are done through READ_ONCE() to
* prevent a re-load down the line.
*/
static bool io_get_sqe(struct io_ring_ctx *ctx, const struct io_uring_sqe **sqe)
{
unsigned mask = ctx->sq_entries - 1;
unsigned head = ctx->cached_sq_head++ & mask;
if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) {
head = READ_ONCE(ctx->sq_array[head]);
if (unlikely(head >= ctx->sq_entries)) {
/* drop invalid entries */
spin_lock(&ctx->completion_lock);
ctx->cq_extra--;
spin_unlock(&ctx->completion_lock);
WRITE_ONCE(ctx->rings->sq_dropped,
READ_ONCE(ctx->rings->sq_dropped) + 1);
return false;
}
}
/*
* The cached sq head (or cq tail) serves two purposes:
*
* 1) allows us to batch the cost of updating the user visible
* head updates.
* 2) allows the kernel side to track the head on its own, even
* though the application is the one updating it.
*/
/* double index for 128-byte SQEs, twice as long */
if (ctx->flags & IORING_SETUP_SQE128)
head <<= 1;
*sqe = &ctx->sq_sqes[head];
return true;
}
int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
__must_hold(&ctx->uring_lock)
{
unsigned int entries = io_sqring_entries(ctx);
unsigned int left;
int ret;
if (unlikely(!entries))
return 0;
/* make sure SQ entry isn't read before tail */
ret = left = min(nr, entries);
io_get_task_refs(left);
io_submit_state_start(&ctx->submit_state, left);
do {
const struct io_uring_sqe *sqe;
struct io_kiocb *req;
if (unlikely(!io_alloc_req(ctx, &req)))
break;
if (unlikely(!io_get_sqe(ctx, &sqe))) {
io_req_add_to_cache(req, ctx);
break;
}
/*
* Continue submitting even for sqe failure if the
* ring was setup with IORING_SETUP_SUBMIT_ALL
*/
if (unlikely(io_submit_sqe(ctx, req, sqe)) &&
!(ctx->flags & IORING_SETUP_SUBMIT_ALL)) {
left--;
break;
}
} while (--left);
if (unlikely(left)) {
ret -= left;
/* try again if it submitted nothing and can't allocate a req */
if (!ret && io_req_cache_empty(ctx))
ret = -EAGAIN;
current->io_uring->cached_refs += left;
}
io_submit_state_end(ctx);
/* Commit SQ ring head once we've consumed and submitted all SQEs */
io_commit_sqring(ctx);
return ret;
}
static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
int wake_flags, void *key)
{
struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue, wq);
/*
* Cannot safely flush overflowed CQEs from here, ensure we wake up
* the task, and the next invocation will do it.
*/
if (io_should_wake(iowq) || io_has_work(iowq->ctx))
return autoremove_wake_function(curr, mode, wake_flags, key);
return -1;
}
int io_run_task_work_sig(struct io_ring_ctx *ctx)
{
if (!llist_empty(&ctx->work_llist)) {
__set_current_state(TASK_RUNNING);
if (io_run_local_work(ctx, INT_MAX) > 0)
return 0;
}
if (io_run_task_work() > 0)
return 0;
if (task_sigpending(current))
return -EINTR;
return 0;
}
static bool current_pending_io(void)
{
struct io_uring_task *tctx = current->io_uring;
if (!tctx)
return false;
return percpu_counter_read_positive(&tctx->inflight);
}
/* when returns >0, the caller should retry */
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq)
{
int ret;
if (unlikely(READ_ONCE(ctx->check_cq)))
return 1;
if (unlikely(!llist_empty(&ctx->work_llist)))
return 1;
if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL)))
return 1;
if (unlikely(task_sigpending(current)))
return -EINTR;
if (unlikely(io_should_wake(iowq)))
return 0;
/*
* Mark us as being in io_wait if we have pending requests, so cpufreq
* can take into account that the task is waiting for IO - turns out
* to be important for low QD IO.
*/
if (current_pending_io())
current->in_iowait = 1;
ret = 0;
if (iowq->timeout == KTIME_MAX)
schedule();
else if (!schedule_hrtimeout(&iowq->timeout, HRTIMER_MODE_ABS))
ret = -ETIME;
current->in_iowait = 0;
return ret;
}
/*
* Wait until events become available, if we don't already have some. The
* application must reap them itself, as they reside on the shared cq ring.
*/
static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
const sigset_t __user *sig, size_t sigsz,
struct __kernel_timespec __user *uts)
{
struct io_wait_queue iowq;
struct io_rings *rings = ctx->rings;
int ret;
if (!io_allowed_run_tw(ctx))
return -EEXIST;
if (!llist_empty(&ctx->work_llist))
io_run_local_work(ctx, min_events);
io_run_task_work();
if (unlikely(test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)))
io_cqring_do_overflow_flush(ctx);
if (__io_cqring_events_user(ctx) >= min_events)
return 0;
init_waitqueue_func_entry(&iowq.wq, io_wake_function);
iowq.wq.private = current;
INIT_LIST_HEAD(&iowq.wq.entry);
iowq.ctx = ctx;
iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events;
iowq.timeout = KTIME_MAX;
if (uts) {
struct timespec64 ts;
ktime_t dt;
if (get_timespec64(&ts, uts))
return -EFAULT;
dt = timespec64_to_ktime(ts);
iowq.timeout = ktime_add(dt, ktime_get());
io_napi_adjust_timeout(ctx, &iowq, dt);
}
if (sig) {
#ifdef CONFIG_COMPAT
if (in_compat_syscall())
ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig,
sigsz);
else
#endif
ret = set_user_sigmask(sig, sigsz);
if (ret)
return ret;
}
io_napi_busy_loop(ctx, &iowq);
trace_io_uring_cqring_wait(ctx, min_events);
do {
int nr_wait = (int) iowq.cq_tail - READ_ONCE(ctx->rings->cq.tail);
unsigned long check_cq;
if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) {
atomic_set(&ctx->cq_wait_nr, nr_wait);
set_current_state(TASK_INTERRUPTIBLE);
} else {
prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
TASK_INTERRUPTIBLE);
}
ret = io_cqring_wait_schedule(ctx, &iowq);
__set_current_state(TASK_RUNNING);
atomic_set(&ctx->cq_wait_nr, IO_CQ_WAKE_INIT);
/*
* Run task_work after scheduling and before io_should_wake().
* If we got woken because of task_work being processed, run it
* now rather than let the caller do another wait loop.
*/
io_run_task_work();
if (!llist_empty(&ctx->work_llist))
io_run_local_work(ctx, nr_wait);
/*
* Non-local task_work will be run on exit to userspace, but
* if we're using DEFER_TASKRUN, then we could have waited
* with a timeout for a number of requests. If the timeout
* hits, we could have some requests ready to process. Ensure
* this break is _after_ we have run task_work, to avoid
* deferring running potentially pending requests until the
* next time we wait for events.
*/
if (ret < 0)
break;
check_cq = READ_ONCE(ctx->check_cq);
if (unlikely(check_cq)) {
/* let the caller flush overflows, retry */
if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
io_cqring_do_overflow_flush(ctx);
if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)) {
ret = -EBADR;
break;
}
}
if (io_should_wake(&iowq)) {
ret = 0;
break;
}
cond_resched();
} while (1);
if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN))
finish_wait(&ctx->cq_wait, &iowq.wq);
restore_saved_sigmask_unless(ret == -EINTR);
return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0;
}
static void *io_rings_map(struct io_ring_ctx *ctx, unsigned long uaddr,
size_t size)
{
return __io_uaddr_map(&ctx->ring_pages, &ctx->n_ring_pages, uaddr,
size);
}
static void *io_sqes_map(struct io_ring_ctx *ctx, unsigned long uaddr,
size_t size)
{
return __io_uaddr_map(&ctx->sqe_pages, &ctx->n_sqe_pages, uaddr,
size);
}
static void io_rings_free(struct io_ring_ctx *ctx)
{
if (!(ctx->flags & IORING_SETUP_NO_MMAP)) {
io_pages_unmap(ctx->rings, &ctx->ring_pages, &ctx->n_ring_pages,
true);
io_pages_unmap(ctx->sq_sqes, &ctx->sqe_pages, &ctx->n_sqe_pages,
true);
} else {
io_pages_free(&ctx->ring_pages, ctx->n_ring_pages);
ctx->n_ring_pages = 0;
io_pages_free(&ctx->sqe_pages, ctx->n_sqe_pages);
ctx->n_sqe_pages = 0;
vunmap(ctx->rings);
vunmap(ctx->sq_sqes);
}
ctx->rings = NULL;
ctx->sq_sqes = NULL;
}
static unsigned long rings_size(struct io_ring_ctx *ctx, unsigned int sq_entries,
unsigned int cq_entries, size_t *sq_offset)
{
struct io_rings *rings;
size_t off, sq_array_size;
off = struct_size(rings, cqes, cq_entries);
if (off == SIZE_MAX)
return SIZE_MAX;
if (ctx->flags & IORING_SETUP_CQE32) {
if (check_shl_overflow(off, 1, &off))
return SIZE_MAX;
}
#ifdef CONFIG_SMP
off = ALIGN(off, SMP_CACHE_BYTES);
if (off == 0)
return SIZE_MAX;
#endif
if (ctx->flags & IORING_SETUP_NO_SQARRAY) {
*sq_offset = SIZE_MAX;
return off;
}
*sq_offset = off;
sq_array_size = array_size(sizeof(u32), sq_entries);
if (sq_array_size == SIZE_MAX)
return SIZE_MAX;
if (check_add_overflow(off, sq_array_size, &off))
return SIZE_MAX;
return off;
}
static void io_req_caches_free(struct io_ring_ctx *ctx)
{
struct io_kiocb *req;
int nr = 0;
mutex_lock(&ctx->uring_lock);
while (!io_req_cache_empty(ctx)) {
req = io_extract_req(ctx);
kmem_cache_free(req_cachep, req);
nr++;
}
if (nr)
percpu_ref_put_many(&ctx->refs, nr);
mutex_unlock(&ctx->uring_lock);
}
static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
{
io_sq_thread_finish(ctx);
/* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */
if (WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)))
return;
mutex_lock(&ctx->uring_lock);
if (ctx->buf_data)
__io_sqe_buffers_unregister(ctx);
if (ctx->file_data)
__io_sqe_files_unregister(ctx);
io_cqring_overflow_kill(ctx);
io_eventfd_unregister(ctx);
io_alloc_cache_free(&ctx->apoll_cache, kfree);
io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free);
io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free);
io_alloc_cache_free(&ctx->uring_cache, kfree);
io_alloc_cache_free(&ctx->msg_cache, io_msg_cache_free);
io_futex_cache_free(ctx);
io_destroy_buffers(ctx);
mutex_unlock(&ctx->uring_lock);
if (ctx->sq_creds)
put_cred(ctx->sq_creds);
if (ctx->submitter_task)
put_task_struct(ctx->submitter_task);
/* there are no registered resources left, nobody uses it */
if (ctx->rsrc_node)
io_rsrc_node_destroy(ctx, ctx->rsrc_node);
WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list));
WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list));
io_alloc_cache_free(&ctx->rsrc_node_cache, kfree);
if (ctx->mm_account) {
mmdrop(ctx->mm_account);
ctx->mm_account = NULL;
}
io_rings_free(ctx);
percpu_ref_exit(&ctx->refs);
free_uid(ctx->user);
io_req_caches_free(ctx);
if (ctx->hash_map)
io_wq_put_hash(ctx->hash_map);
io_napi_free(ctx);
kfree(ctx->cancel_table.hbs);
kfree(ctx->cancel_table_locked.hbs);
xa_destroy(&ctx->io_bl_xa);
kfree(ctx);
}
static __cold void io_activate_pollwq_cb(struct callback_head *cb)
{
struct io_ring_ctx *ctx = container_of(cb, struct io_ring_ctx,
poll_wq_task_work);
mutex_lock(&ctx->uring_lock);
ctx->poll_activated = true;
mutex_unlock(&ctx->uring_lock);
/*
* Wake ups for some events between start of polling and activation
* might've been lost due to loose synchronisation.
*/
wake_up_all(&ctx->poll_wq);
percpu_ref_put(&ctx->refs);
}
__cold void io_activate_pollwq(struct io_ring_ctx *ctx)
{
spin_lock(&ctx->completion_lock);
/* already activated or in progress */
if (ctx->poll_activated || ctx->poll_wq_task_work.func)
goto out;
if (WARN_ON_ONCE(!ctx->task_complete))
goto out;
if (!ctx->submitter_task)
goto out;
/*
* with ->submitter_task only the submitter task completes requests, we
* only need to sync with it, which is done by injecting a tw
*/
init_task_work(&ctx->poll_wq_task_work, io_activate_pollwq_cb);
percpu_ref_get(&ctx->refs);
if (task_work_add(ctx->submitter_task, &ctx->poll_wq_task_work, TWA_SIGNAL))
percpu_ref_put(&ctx->refs);
out:
spin_unlock(&ctx->completion_lock);
}
static __poll_t io_uring_poll(struct file *file, poll_table *wait)
{
struct io_ring_ctx *ctx = file->private_data;
__poll_t mask = 0;
if (unlikely(!ctx->poll_activated))
io_activate_pollwq(ctx);
poll_wait(file, &ctx->poll_wq, wait);
/*
* synchronizes with barrier from wq_has_sleeper call in
* io_commit_cqring
*/
smp_rmb();
if (!io_sqring_full(ctx))
mask |= EPOLLOUT | EPOLLWRNORM;
/*
* Don't flush cqring overflow list here, just do a simple check.
* Otherwise there could possible be ABBA deadlock:
* CPU0 CPU1
* ---- ----
* lock(&ctx->uring_lock);
* lock(&ep->mtx);
* lock(&ctx->uring_lock);
* lock(&ep->mtx);
*
* Users may get EPOLLIN meanwhile seeing nothing in cqring, this
* pushes them to do the flush.
*/
if (__io_cqring_events_user(ctx) || io_has_work(ctx))
mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
struct io_tctx_exit {
struct callback_head task_work;
struct completion completion;
struct io_ring_ctx *ctx;
};
static __cold void io_tctx_exit_cb(struct callback_head *cb)
{
struct io_uring_task *tctx = current->io_uring;
struct io_tctx_exit *work;
work = container_of(cb, struct io_tctx_exit, task_work);
/*
* When @in_cancel, we're in cancellation and it's racy to remove the
* node. It'll be removed by the end of cancellation, just ignore it.
* tctx can be NULL if the queueing of this task_work raced with
* work cancelation off the exec path.
*/
if (tctx && !atomic_read(&tctx->in_cancel))
io_uring_del_tctx_node((unsigned long)work->ctx);
complete(&work->completion);
}
static __cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
return req->ctx == data;
}
static __cold void io_ring_exit_work(struct work_struct *work)
{
struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work);
unsigned long timeout = jiffies + HZ * 60 * 5;
unsigned long interval = HZ / 20;
struct io_tctx_exit exit;
struct io_tctx_node *node;
int ret;
/*
* If we're doing polled IO and end up having requests being
* submitted async (out-of-line), then completions can come in while
* we're waiting for refs to drop. We need to reap these manually,
* as nobody else will be looking for them.
*/
do {
if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
mutex_lock(&ctx->uring_lock);
io_cqring_overflow_kill(ctx);
mutex_unlock(&ctx->uring_lock);
}
if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
io_move_task_work_from_local(ctx);
while (io_uring_try_cancel_requests(ctx, NULL, true))
cond_resched();
if (ctx->sq_data) {
struct io_sq_data *sqd = ctx->sq_data;
struct task_struct *tsk;
io_sq_thread_park(sqd);
tsk = sqd->thread;
if (tsk && tsk->io_uring && tsk->io_uring->io_wq)
io_wq_cancel_cb(tsk->io_uring->io_wq,
io_cancel_ctx_cb, ctx, true);
io_sq_thread_unpark(sqd);
}
io_req_caches_free(ctx);
if (WARN_ON_ONCE(time_after(jiffies, timeout))) {
/* there is little hope left, don't run it too often */
interval = HZ * 60;
}
/*
* This is really an uninterruptible wait, as it has to be
* complete. But it's also run from a kworker, which doesn't
* take signals, so it's fine to make it interruptible. This
* avoids scenarios where we knowingly can wait much longer
* on completions, for example if someone does a SIGSTOP on
* a task that needs to finish task_work to make this loop
* complete. That's a synthetic situation that should not
* cause a stuck task backtrace, and hence a potential panic
* on stuck tasks if that is enabled.
*/
} while (!wait_for_completion_interruptible_timeout(&ctx->ref_comp, interval));
init_completion(&exit.completion);
init_task_work(&exit.task_work, io_tctx_exit_cb);
exit.ctx = ctx;
mutex_lock(&ctx->uring_lock);
while (!list_empty(&ctx->tctx_list)) {
WARN_ON_ONCE(time_after(jiffies, timeout));
node = list_first_entry(&ctx->tctx_list, struct io_tctx_node,
ctx_node);
/* don't spin on a single task if cancellation failed */
list_rotate_left(&ctx->tctx_list);
ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL);
if (WARN_ON_ONCE(ret))
continue;
mutex_unlock(&ctx->uring_lock);
/*
* See comment above for
* wait_for_completion_interruptible_timeout() on why this
* wait is marked as interruptible.
*/
wait_for_completion_interruptible(&exit.completion);
mutex_lock(&ctx->uring_lock);
}
mutex_unlock(&ctx->uring_lock);
spin_lock(&ctx->completion_lock);
spin_unlock(&ctx->completion_lock);
/* pairs with RCU read section in io_req_local_work_add() */
if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
synchronize_rcu();
io_ring_ctx_free(ctx);
}
static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
{
unsigned long index;
struct creds *creds;
mutex_lock(&ctx->uring_lock);
percpu_ref_kill(&ctx->refs);
xa_for_each(&ctx->personalities, index, creds)
io_unregister_personality(ctx, index);
mutex_unlock(&ctx->uring_lock);
flush_delayed_work(&ctx->fallback_work);
INIT_WORK(&ctx->exit_work, io_ring_exit_work);
/*
* Use system_unbound_wq to avoid spawning tons of event kworkers
* if we're exiting a ton of rings at the same time. It just adds
* noise and overhead, there's no discernable change in runtime
* over using system_wq.
*/
queue_work(iou_wq, &ctx->exit_work);
}
static int io_uring_release(struct inode *inode, struct file *file)
{
struct io_ring_ctx *ctx = file->private_data;
file->private_data = NULL;
io_ring_ctx_wait_and_kill(ctx);
return 0;
}
struct io_task_cancel {
struct task_struct *task;
bool all;
};
static bool io_cancel_task_cb(struct io_wq_work *work, void *data)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
struct io_task_cancel *cancel = data;
return io_match_task_safe(req, cancel->task, cancel->all);
}
static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx,
struct task_struct *task,
bool cancel_all)
{
struct io_defer_entry *de;
LIST_HEAD(list);
spin_lock(&ctx->completion_lock);
list_for_each_entry_reverse(de, &ctx->defer_list, list) {
if (io_match_task_safe(de->req, task, cancel_all)) {
list_cut_position(&list, &ctx->defer_list, &de->list);
break;
}
}
spin_unlock(&ctx->completion_lock);
if (list_empty(&list))
return false;
while (!list_empty(&list)) {
de = list_first_entry(&list, struct io_defer_entry, list);
list_del_init(&de->list);
io_req_task_queue_fail(de->req, -ECANCELED);
kfree(de);
}
return true;
}
static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
{
struct io_tctx_node *node;
enum io_wq_cancel cret;
bool ret = false;
mutex_lock(&ctx->uring_lock);
list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
struct io_uring_task *tctx = node->task->io_uring;
/*
* io_wq will stay alive while we hold uring_lock, because it's
* killed after ctx nodes, which requires to take the lock.
*/
if (!tctx || !tctx->io_wq)
continue;
cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true);
ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
}
mutex_unlock(&ctx->uring_lock);
return ret;
}
static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
struct task_struct *task,
bool cancel_all)
{
struct io_task_cancel cancel = { .task = task, .all = cancel_all, };
struct io_uring_task *tctx = task ? task->io_uring : NULL;
enum io_wq_cancel cret;
bool ret = false;
/* set it so io_req_local_work_add() would wake us up */
if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) {
atomic_set(&ctx->cq_wait_nr, 1);
smp_mb();
}
/* failed during ring init, it couldn't have issued any requests */
if (!ctx->rings)
return false;
if (!task) {
ret |= io_uring_try_cancel_iowq(ctx);
} else if (tctx && tctx->io_wq) {
/*
* Cancels requests of all rings, not only @ctx, but
* it's fine as the task is in exit/exec.
*/
cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb,
&cancel, true);
ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
}
/* SQPOLL thread does its own polling */
if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) ||
(ctx->sq_data && ctx->sq_data->thread == current)) {
while (!wq_list_empty(&ctx->iopoll_list)) {
io_iopoll_try_reap_events(ctx);
ret = true;
cond_resched();
}
}
if ((ctx->flags & IORING_SETUP_DEFER_TASKRUN) &&
io_allowed_defer_tw_run(ctx))
ret |= io_run_local_work(ctx, INT_MAX) > 0;
ret |= io_cancel_defer_files(ctx, task, cancel_all);
mutex_lock(&ctx->uring_lock);
ret |= io_poll_remove_all(ctx, task, cancel_all);
ret |= io_waitid_remove_all(ctx, task, cancel_all);
ret |= io_futex_remove_all(ctx, task, cancel_all);
ret |= io_uring_try_cancel_uring_cmd(ctx, task, cancel_all);
mutex_unlock(&ctx->uring_lock);
ret |= io_kill_timeouts(ctx, task, cancel_all);
if (task)
ret |= io_run_task_work() > 0;
else
ret |= flush_delayed_work(&ctx->fallback_work);
return ret;
}
static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
{
if (tracked)
return atomic_read(&tctx->inflight_tracked);
return percpu_counter_sum(&tctx->inflight);
}
/*
* Find any io_uring ctx that this task has registered or done IO on, and cancel
* requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation.
*/
__cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
{
struct io_uring_task *tctx = current->io_uring;
struct io_ring_ctx *ctx;
struct io_tctx_node *node;
unsigned long index;
s64 inflight;
DEFINE_WAIT(wait);
WARN_ON_ONCE(sqd && sqd->thread != current);
if (!current->io_uring)
return;
if (tctx->io_wq)
io_wq_exit_start(tctx->io_wq);
atomic_inc(&tctx->in_cancel);
do {
bool loop = false;
io_uring_drop_tctx_refs(current);
if (!tctx_inflight(tctx, !cancel_all))
break;
/* read completions before cancelations */
inflight = tctx_inflight(tctx, false);
if (!inflight)
break;
if (!sqd) {
xa_for_each(&tctx->xa, index, node) {
/* sqpoll task will cancel all its requests */
if (node->ctx->sq_data)
continue;
loop |= io_uring_try_cancel_requests(node->ctx,
current, cancel_all);
}
} else {
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
loop |= io_uring_try_cancel_requests(ctx,
current,
cancel_all);
}
if (loop) {
cond_resched();
continue;
}
prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE);
io_run_task_work();
io_uring_drop_tctx_refs(current);
xa_for_each(&tctx->xa, index, node) {
if (!llist_empty(&node->ctx->work_llist)) {
WARN_ON_ONCE(node->ctx->submitter_task &&
node->ctx->submitter_task != current);
goto end_wait;
}
}
/*
* If we've seen completions, retry without waiting. This
* avoids a race where a completion comes in before we did
* prepare_to_wait().
*/
if (inflight == tctx_inflight(tctx, !cancel_all))
schedule();
end_wait:
finish_wait(&tctx->wait, &wait);
} while (1);