*
* See ../COPYING for licensing terms.
*/
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/backing-dev.h>
#include <linux/uio.h>
-#define DEBUG 0
-
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <asm/kmap_types.h>
#include <asm/uaccess.h>
-#if DEBUG > 1
-#define dprintk printk
-#else
-#define dprintk(x...) do { ; } while (0)
-#endif
-
#define AIO_RING_MAGIC 0xa10a10a1
#define AIO_RING_COMPAT_FEATURES 1
#define AIO_RING_INCOMPAT_FEATURES 0
}; /* 128 bytes + ring size */
#define AIO_RING_PAGES 8
-struct aio_ring_info {
- unsigned long mmap_base;
- unsigned long mmap_size;
-
- struct page **ring_pages;
- spinlock_t ring_lock;
- long nr_pages;
-
- unsigned nr, tail;
-
- struct page *internal_pages[AIO_RING_PAGES];
-};
-
-static inline unsigned aio_ring_avail(struct aio_ring_info *info,
- struct aio_ring *ring)
-{
- return (ring->head + info->nr - 1 - ring->tail) % info->nr;
-}
struct kioctx {
atomic_t users;
- int dead;
+ atomic_t dead;
/* This needs improving */
unsigned long user_id;
struct hlist_node list;
- wait_queue_head_t wait;
-
- spinlock_t ctx_lock;
+ /*
+ * This is what userspace passed to io_setup(), it's not used for
+ * anything but counting against the global max_reqs quota.
+ *
+ * The real limit is nr_events - 1, which will be larger (see
+ * aio_setup_ring())
+ */
+ unsigned max_reqs;
- int reqs_active;
- struct list_head active_reqs; /* used for cancellation */
+ /* Size of ringbuffer, in units of struct io_event */
+ unsigned nr_events;
- /* sys_io_setup currently limits this to an unsigned int */
- unsigned max_reqs;
+ unsigned long mmap_base;
+ unsigned long mmap_size;
- struct aio_ring_info ring_info;
+ struct page **ring_pages;
+ long nr_pages;
struct rcu_head rcu_head;
+ struct work_struct rcu_work;
+
+ struct {
+ atomic_t reqs_active;
+ } ____cacheline_aligned_in_smp;
+
+ struct {
+ spinlock_t ctx_lock;
+ struct list_head active_reqs; /* used for cancellation */
+ } ____cacheline_aligned_in_smp;
+
+ struct {
+ struct mutex ring_lock;
+ wait_queue_head_t wait;
+ } ____cacheline_aligned_in_smp;
+
+ struct {
+ unsigned tail;
+ spinlock_t completion_lock;
+ } ____cacheline_aligned_in_smp;
+
+ struct page *internal_pages[AIO_RING_PAGES];
};
/*------ sysctl variables----*/
kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
- pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page));
+ pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page));
return 0;
}
static void aio_free_ring(struct kioctx *ctx)
{
- struct aio_ring_info *info = &ctx->ring_info;
long i;
- for (i=0; i<info->nr_pages; i++)
- put_page(info->ring_pages[i]);
+ for (i = 0; i < ctx->nr_pages; i++)
+ put_page(ctx->ring_pages[i]);
- if (info->mmap_size) {
- vm_munmap(info->mmap_base, info->mmap_size);
- }
+ if (ctx->mmap_size)
+ vm_munmap(ctx->mmap_base, ctx->mmap_size);
- if (info->ring_pages && info->ring_pages != info->internal_pages)
- kfree(info->ring_pages);
- info->ring_pages = NULL;
- info->nr = 0;
+ if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages)
+ kfree(ctx->ring_pages);
}
static int aio_setup_ring(struct kioctx *ctx)
{
struct aio_ring *ring;
- struct aio_ring_info *info = &ctx->ring_info;
unsigned nr_events = ctx->max_reqs;
struct mm_struct *mm = current->mm;
unsigned long size, populate;
nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) / sizeof(struct io_event);
- info->nr = 0;
- info->ring_pages = info->internal_pages;
+ ctx->nr_events = 0;
+ ctx->ring_pages = ctx->internal_pages;
if (nr_pages > AIO_RING_PAGES) {
- info->ring_pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
- if (!info->ring_pages)
+ ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
+ GFP_KERNEL);
+ if (!ctx->ring_pages)
return -ENOMEM;
}
- info->mmap_size = nr_pages * PAGE_SIZE;
- dprintk("attempting mmap of %lu bytes\n", info->mmap_size);
+ ctx->mmap_size = nr_pages * PAGE_SIZE;
+ pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size);
down_write(&mm->mmap_sem);
- info->mmap_base = do_mmap_pgoff(NULL, 0, info->mmap_size,
- PROT_READ|PROT_WRITE,
- MAP_ANONYMOUS|MAP_PRIVATE, 0,
- &populate);
- if (IS_ERR((void *)info->mmap_base)) {
+ ctx->mmap_base = do_mmap_pgoff(NULL, 0, ctx->mmap_size,
+ PROT_READ|PROT_WRITE,
+ MAP_ANONYMOUS|MAP_PRIVATE, 0, &populate);
+ if (IS_ERR((void *)ctx->mmap_base)) {
up_write(&mm->mmap_sem);
- info->mmap_size = 0;
+ ctx->mmap_size = 0;
aio_free_ring(ctx);
return -EAGAIN;
}
- dprintk("mmap address: 0x%08lx\n", info->mmap_base);
- info->nr_pages = get_user_pages(current, mm, info->mmap_base, nr_pages,
- 1, 0, info->ring_pages, NULL);
+ pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
+ ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages,
+ 1, 0, ctx->ring_pages, NULL);
up_write(&mm->mmap_sem);
- if (unlikely(info->nr_pages != nr_pages)) {
+ if (unlikely(ctx->nr_pages != nr_pages)) {
aio_free_ring(ctx);
return -EAGAIN;
}
if (populate)
- mm_populate(info->mmap_base, populate);
+ mm_populate(ctx->mmap_base, populate);
- ctx->user_id = info->mmap_base;
+ ctx->user_id = ctx->mmap_base;
+ ctx->nr_events = nr_events; /* trusted copy */
- info->nr = nr_events; /* trusted copy */
-
- ring = kmap_atomic(info->ring_pages[0]);
+ ring = kmap_atomic(ctx->ring_pages[0]);
ring->nr = nr_events; /* user copy */
ring->id = ctx->user_id;
ring->head = ring->tail = 0;
ring->incompat_features = AIO_RING_INCOMPAT_FEATURES;
ring->header_length = sizeof(struct aio_ring);
kunmap_atomic(ring);
+ flush_dcache_page(ctx->ring_pages[0]);
return 0;
}
-
-/* aio_ring_event: returns a pointer to the event at the given index from
- * kmap_atomic(). Release the pointer with put_aio_ring_event();
- */
#define AIO_EVENTS_PER_PAGE (PAGE_SIZE / sizeof(struct io_event))
#define AIO_EVENTS_FIRST_PAGE ((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event))
#define AIO_EVENTS_OFFSET (AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE)
-#define aio_ring_event(info, nr) ({ \
- unsigned pos = (nr) + AIO_EVENTS_OFFSET; \
- struct io_event *__event; \
- __event = kmap_atomic( \
- (info)->ring_pages[pos / AIO_EVENTS_PER_PAGE]); \
- __event += pos % AIO_EVENTS_PER_PAGE; \
- __event; \
-})
-
-#define put_aio_ring_event(event) do { \
- struct io_event *__event = (event); \
- (void)__event; \
- kunmap_atomic((void *)((unsigned long)__event & PAGE_MASK)); \
-} while(0)
-
-static void ctx_rcu_free(struct rcu_head *head)
+void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel)
{
- struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
- kmem_cache_free(kioctx_cachep, ctx);
-}
+ struct kioctx *ctx = req->ki_ctx;
+ unsigned long flags;
-/* __put_ioctx
- * Called when the last user of an aio context has gone away,
- * and the struct needs to be freed.
- */
-static void __put_ioctx(struct kioctx *ctx)
-{
- unsigned nr_events = ctx->max_reqs;
- BUG_ON(ctx->reqs_active);
+ spin_lock_irqsave(&ctx->ctx_lock, flags);
- aio_free_ring(ctx);
- if (nr_events) {
- spin_lock(&aio_nr_lock);
- BUG_ON(aio_nr - nr_events > aio_nr);
- aio_nr -= nr_events;
- spin_unlock(&aio_nr_lock);
- }
- pr_debug("__put_ioctx: freeing %p\n", ctx);
- call_rcu(&ctx->rcu_head, ctx_rcu_free);
+ if (!req->ki_list.next)
+ list_add(&req->ki_list, &ctx->active_reqs);
+
+ req->ki_cancel = cancel;
+
+ spin_unlock_irqrestore(&ctx->ctx_lock, flags);
}
+EXPORT_SYMBOL(kiocb_set_cancel_fn);
-static inline int try_get_ioctx(struct kioctx *kioctx)
+static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb,
+ struct io_event *res)
{
- return atomic_inc_not_zero(&kioctx->users);
+ kiocb_cancel_fn *old, *cancel;
+ int ret = -EINVAL;
+
+ /*
+ * Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it
+ * actually has a cancel function, hence the cmpxchg()
+ */
+
+ cancel = ACCESS_ONCE(kiocb->ki_cancel);
+ do {
+ if (!cancel || cancel == KIOCB_CANCELLED)
+ return ret;
+
+ old = cancel;
+ cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
+ } while (cancel != old);
+
+ atomic_inc(&kiocb->ki_users);
+ spin_unlock_irq(&ctx->ctx_lock);
+
+ memset(res, 0, sizeof(*res));
+ res->obj = (u64)(unsigned long)kiocb->ki_obj.user;
+ res->data = kiocb->ki_user_data;
+ ret = cancel(kiocb, res);
+
+ spin_lock_irq(&ctx->ctx_lock);
+
+ return ret;
}
-static inline void put_ioctx(struct kioctx *kioctx)
+static void free_ioctx_rcu(struct rcu_head *head)
{
- BUG_ON(atomic_read(&kioctx->users) <= 0);
- if (unlikely(atomic_dec_and_test(&kioctx->users)))
- __put_ioctx(kioctx);
+ struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
+ kmem_cache_free(kioctx_cachep, ctx);
}
-static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb,
- struct io_event *res)
+/*
+ * When this function runs, the kioctx has been removed from the "hash table"
+ * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted -
+ * now it's safe to cancel any that need to be.
+ */
+static void free_ioctx(struct kioctx *ctx)
{
- int (*cancel)(struct kiocb *, struct io_event *);
- int ret = -EINVAL;
+ struct aio_ring *ring;
+ struct io_event res;
+ struct kiocb *req;
+ unsigned head, avail;
- cancel = kiocb->ki_cancel;
- kiocbSetCancelled(kiocb);
- if (cancel) {
- kiocb->ki_users++;
- spin_unlock_irq(&ctx->ctx_lock);
+ spin_lock_irq(&ctx->ctx_lock);
- memset(res, 0, sizeof(*res));
- res->obj = (u64)(unsigned long)kiocb->ki_obj.user;
- res->data = kiocb->ki_user_data;
- ret = cancel(kiocb, res);
+ while (!list_empty(&ctx->active_reqs)) {
+ req = list_first_entry(&ctx->active_reqs,
+ struct kiocb, ki_list);
- spin_lock_irq(&ctx->ctx_lock);
+ list_del_init(&req->ki_list);
+ kiocb_cancel(ctx, req, &res);
}
- return ret;
+ spin_unlock_irq(&ctx->ctx_lock);
+
+ ring = kmap_atomic(ctx->ring_pages[0]);
+ head = ring->head;
+ kunmap_atomic(ring);
+
+ while (atomic_read(&ctx->reqs_active) > 0) {
+ wait_event(ctx->wait, head != ctx->tail);
+
+ avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head;
+
+ atomic_sub(avail, &ctx->reqs_active);
+ head += avail;
+ head %= ctx->nr_events;
+ }
+
+ WARN_ON(atomic_read(&ctx->reqs_active) < 0);
+
+ aio_free_ring(ctx);
+
+ spin_lock(&aio_nr_lock);
+ BUG_ON(aio_nr - ctx->max_reqs > aio_nr);
+ aio_nr -= ctx->max_reqs;
+ spin_unlock(&aio_nr_lock);
+
+ pr_debug("freeing %p\n", ctx);
+
+ /*
+ * Here the call_rcu() is between the wait_event() for reqs_active to
+ * hit 0, and freeing the ioctx.
+ *
+ * aio_complete() decrements reqs_active, but it has to touch the ioctx
+ * after to issue a wakeup so we use rcu.
+ */
+ call_rcu(&ctx->rcu_head, free_ioctx_rcu);
+}
+
+static void put_ioctx(struct kioctx *ctx)
+{
+ if (unlikely(atomic_dec_and_test(&ctx->users)))
+ free_ioctx(ctx);
}
/* ioctx_alloc
ctx->max_reqs = nr_events;
atomic_set(&ctx->users, 2);
+ atomic_set(&ctx->dead, 0);
spin_lock_init(&ctx->ctx_lock);
- spin_lock_init(&ctx->ring_info.ring_lock);
+ spin_lock_init(&ctx->completion_lock);
+ mutex_init(&ctx->ring_lock);
init_waitqueue_head(&ctx->wait);
INIT_LIST_HEAD(&ctx->active_reqs);
hlist_add_head_rcu(&ctx->list, &mm->ioctx_list);
spin_unlock(&mm->ioctx_lock);
- dprintk("aio: allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
- ctx, ctx->user_id, mm, ctx->ring_info.nr);
+ pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
+ ctx, ctx->user_id, mm, ctx->nr_events);
return ctx;
out_cleanup:
aio_free_ring(ctx);
out_freectx:
kmem_cache_free(kioctx_cachep, ctx);
- dprintk("aio: error allocating ioctx %d\n", err);
+ pr_debug("error allocating ioctx %d\n", err);
return ERR_PTR(err);
}
-/* kill_ctx
- * Cancels all outstanding aio requests on an aio context. Used
- * when the processes owning a context have all exited to encourage
- * the rapid destruction of the kioctx.
- */
-static void kill_ctx(struct kioctx *ctx)
+static void kill_ioctx_work(struct work_struct *work)
{
- struct task_struct *tsk = current;
- DECLARE_WAITQUEUE(wait, tsk);
- struct io_event res;
- struct kiocb *req;
+ struct kioctx *ctx = container_of(work, struct kioctx, rcu_work);
- spin_lock_irq(&ctx->ctx_lock);
- ctx->dead = 1;
- while (!list_empty(&ctx->active_reqs)) {
- req = list_first_entry(&ctx->active_reqs,
- struct kiocb, ki_list);
+ wake_up_all(&ctx->wait);
+ put_ioctx(ctx);
+}
- list_del_init(&req->ki_list);
- kiocb_cancel(ctx, req, &res);
- }
+static void kill_ioctx_rcu(struct rcu_head *head)
+{
+ struct kioctx *ctx = container_of(head, struct kioctx, rcu_head);
- if (!ctx->reqs_active)
- goto out;
+ INIT_WORK(&ctx->rcu_work, kill_ioctx_work);
+ schedule_work(&ctx->rcu_work);
+}
- add_wait_queue(&ctx->wait, &wait);
- set_task_state(tsk, TASK_UNINTERRUPTIBLE);
- while (ctx->reqs_active) {
- spin_unlock_irq(&ctx->ctx_lock);
- io_schedule();
- set_task_state(tsk, TASK_UNINTERRUPTIBLE);
- spin_lock_irq(&ctx->ctx_lock);
- }
- __set_task_state(tsk, TASK_RUNNING);
- remove_wait_queue(&ctx->wait, &wait);
+/* kill_ioctx
+ * Cancels all outstanding aio requests on an aio context. Used
+ * when the processes owning a context have all exited to encourage
+ * the rapid destruction of the kioctx.
+ */
+static void kill_ioctx(struct kioctx *ctx)
+{
+ if (!atomic_xchg(&ctx->dead, 1)) {
+ hlist_del_rcu(&ctx->list);
+ /* Between hlist_del_rcu() and dropping the initial ref */
+ synchronize_rcu();
-out:
- spin_unlock_irq(&ctx->ctx_lock);
+ /*
+ * We can't punt to workqueue here because put_ioctx() ->
+ * free_ioctx() will unmap the ringbuffer, and that has to be
+ * done in the original process's context. kill_ioctx_rcu/work()
+ * exist for exit_aio(), as in that path free_ioctx() won't do
+ * the unmap.
+ */
+ kill_ioctx_work(&ctx->rcu_work);
+ }
}
/* wait_on_sync_kiocb:
*/
ssize_t wait_on_sync_kiocb(struct kiocb *iocb)
{
- while (iocb->ki_users) {
+ while (atomic_read(&iocb->ki_users)) {
set_current_state(TASK_UNINTERRUPTIBLE);
- if (!iocb->ki_users)
+ if (!atomic_read(&iocb->ki_users))
break;
io_schedule();
}
}
EXPORT_SYMBOL(wait_on_sync_kiocb);
-/* exit_aio: called when the last user of mm goes away. At this point,
- * there is no way for any new requests to be submited or any of the
- * io_* syscalls to be called on the context. However, there may be
- * outstanding requests which hold references to the context; as they
- * go away, they will call put_ioctx and release any pinned memory
- * associated with the request (held via struct page * references).
+/*
+ * exit_aio: called when the last user of mm goes away. At this point, there is
+ * no way for any new requests to be submited or any of the io_* syscalls to be
+ * called on the context.
+ *
+ * There may be outstanding kiocbs, but free_ioctx() will explicitly wait on
+ * them.
*/
void exit_aio(struct mm_struct *mm)
{
struct kioctx *ctx;
+ struct hlist_node *n;
- while (!hlist_empty(&mm->ioctx_list)) {
- ctx = hlist_entry(mm->ioctx_list.first, struct kioctx, list);
- hlist_del_rcu(&ctx->list);
-
- kill_ctx(ctx);
-
+ hlist_for_each_entry_safe(ctx, n, &mm->ioctx_list, list) {
if (1 != atomic_read(&ctx->users))
printk(KERN_DEBUG
"exit_aio:ioctx still alive: %d %d %d\n",
- atomic_read(&ctx->users), ctx->dead,
- ctx->reqs_active);
+ atomic_read(&ctx->users),
+ atomic_read(&ctx->dead),
+ atomic_read(&ctx->reqs_active));
/*
* We don't need to bother with munmap() here -
* exit_mmap(mm) is coming and it'll unmap everything.
* just set it to 0; aio_free_ring() is the only
* place that uses ->mmap_size, so it's safe.
*/
- ctx->ring_info.mmap_size = 0;
- put_ioctx(ctx);
+ ctx->mmap_size = 0;
+
+ if (!atomic_xchg(&ctx->dead, 1)) {
+ hlist_del_rcu(&ctx->list);
+ call_rcu(&ctx->rcu_head, kill_ioctx_rcu);
+ }
}
}
/* aio_get_req
- * Allocate a slot for an aio request. Increments the users count
+ * Allocate a slot for an aio request. Increments the ki_users count
* of the kioctx so that the kioctx stays around until all requests are
* complete. Returns NULL if no requests are free.
*
- * Returns with kiocb->users set to 2. The io submit code path holds
+ * Returns with kiocb->ki_users set to 2. The io submit code path holds
* an extra reference while submitting the i/o.
* This prevents races between the aio code path referencing the
* req (after submitting it) and aio_complete() freeing the req.
*/
-static struct kiocb *__aio_get_req(struct kioctx *ctx)
+static inline struct kiocb *aio_get_req(struct kioctx *ctx)
{
- struct kiocb *req = NULL;
+ struct kiocb *req;
- req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL);
- if (unlikely(!req))
+ if (atomic_read(&ctx->reqs_active) >= ctx->nr_events)
return NULL;
- req->ki_flags = 0;
- req->ki_users = 2;
- req->ki_key = 0;
- req->ki_ctx = ctx;
- req->ki_cancel = NULL;
- req->ki_retry = NULL;
- req->ki_dtor = NULL;
- req->private = NULL;
- req->ki_iovec = NULL;
- req->ki_eventfd = NULL;
-
- return req;
-}
-
-/*
- * struct kiocb's are allocated in batches to reduce the number of
- * times the ctx lock is acquired and released.
- */
-#define KIOCB_BATCH_SIZE 32L
-struct kiocb_batch {
- struct list_head head;
- long count; /* number of requests left to allocate */
-};
-
-static void kiocb_batch_init(struct kiocb_batch *batch, long total)
-{
- INIT_LIST_HEAD(&batch->head);
- batch->count = total;
-}
-
-static void kiocb_batch_free(struct kioctx *ctx, struct kiocb_batch *batch)
-{
- struct kiocb *req, *n;
-
- if (list_empty(&batch->head))
- return;
-
- spin_lock_irq(&ctx->ctx_lock);
- list_for_each_entry_safe(req, n, &batch->head, ki_batch) {
- list_del(&req->ki_batch);
- list_del(&req->ki_list);
- kmem_cache_free(kiocb_cachep, req);
- ctx->reqs_active--;
- }
- if (unlikely(!ctx->reqs_active && ctx->dead))
- wake_up_all(&ctx->wait);
- spin_unlock_irq(&ctx->ctx_lock);
-}
-
-/*
- * Allocate a batch of kiocbs. This avoids taking and dropping the
- * context lock a lot during setup.
- */
-static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch)
-{
- unsigned short allocated, to_alloc;
- long avail;
- struct kiocb *req, *n;
- struct aio_ring *ring;
-
- to_alloc = min(batch->count, KIOCB_BATCH_SIZE);
- for (allocated = 0; allocated < to_alloc; allocated++) {
- req = __aio_get_req(ctx);
- if (!req)
- /* allocation failed, go with what we've got */
- break;
- list_add(&req->ki_batch, &batch->head);
- }
-
- if (allocated == 0)
- goto out;
-
- spin_lock_irq(&ctx->ctx_lock);
- ring = kmap_atomic(ctx->ring_info.ring_pages[0]);
-
- avail = aio_ring_avail(&ctx->ring_info, ring) - ctx->reqs_active;
- BUG_ON(avail < 0);
- if (avail < allocated) {
- /* Trim back the number of requests. */
- list_for_each_entry_safe(req, n, &batch->head, ki_batch) {
- list_del(&req->ki_batch);
- kmem_cache_free(kiocb_cachep, req);
- if (--allocated <= avail)
- break;
- }
- }
-
- batch->count -= allocated;
- list_for_each_entry(req, &batch->head, ki_batch) {
- list_add(&req->ki_list, &ctx->active_reqs);
- ctx->reqs_active++;
- }
+ if (atomic_inc_return(&ctx->reqs_active) > ctx->nr_events - 1)
+ goto out_put;
- kunmap_atomic(ring);
- spin_unlock_irq(&ctx->ctx_lock);
-
-out:
- return allocated;
-}
+ req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO);
+ if (unlikely(!req))
+ goto out_put;
-static inline struct kiocb *aio_get_req(struct kioctx *ctx,
- struct kiocb_batch *batch)
-{
- struct kiocb *req;
+ atomic_set(&req->ki_users, 2);
+ req->ki_ctx = ctx;
- if (list_empty(&batch->head))
- if (kiocb_batch_refill(ctx, batch) == 0)
- return NULL;
- req = list_first_entry(&batch->head, struct kiocb, ki_batch);
- list_del(&req->ki_batch);
return req;
+out_put:
+ atomic_dec(&ctx->reqs_active);
+ return NULL;
}
-static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
+static void kiocb_free(struct kiocb *req)
{
- assert_spin_locked(&ctx->ctx_lock);
-
+ if (req->ki_filp)
+ fput(req->ki_filp);
if (req->ki_eventfd != NULL)
eventfd_ctx_put(req->ki_eventfd);
if (req->ki_dtor)
if (req->ki_iovec != &req->ki_inline_vec)
kfree(req->ki_iovec);
kmem_cache_free(kiocb_cachep, req);
- ctx->reqs_active--;
-
- if (unlikely(!ctx->reqs_active && ctx->dead))
- wake_up_all(&ctx->wait);
}
-/* __aio_put_req
- * Returns true if this put was the last user of the request.
- */
-static void __aio_put_req(struct kioctx *ctx, struct kiocb *req)
-{
- dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n",
- req, atomic_long_read(&req->ki_filp->f_count));
-
- assert_spin_locked(&ctx->ctx_lock);
-
- req->ki_users--;
- BUG_ON(req->ki_users < 0);
- if (likely(req->ki_users))
- return;
- list_del(&req->ki_list); /* remove from active_reqs */
- req->ki_cancel = NULL;
- req->ki_retry = NULL;
-
- fput(req->ki_filp);
- req->ki_filp = NULL;
- really_put_req(ctx, req);
-}
-
-/* aio_put_req
- * Returns true if this put was the last user of the kiocb,
- * false if the request is still in use.
- */
void aio_put_req(struct kiocb *req)
{
- struct kioctx *ctx = req->ki_ctx;
- spin_lock_irq(&ctx->ctx_lock);
- __aio_put_req(ctx, req);
- spin_unlock_irq(&ctx->ctx_lock);
+ if (atomic_dec_and_test(&req->ki_users))
+ kiocb_free(req);
}
EXPORT_SYMBOL(aio_put_req);
rcu_read_lock();
hlist_for_each_entry_rcu(ctx, &mm->ioctx_list, list) {
- /*
- * RCU protects us against accessing freed memory but
- * we have to be careful not to get a reference when the
- * reference count already dropped to 0 (ctx->dead test
- * is unreliable because of races).
- */
- if (ctx->user_id == ctx_id && !ctx->dead && try_get_ioctx(ctx)){
+ if (ctx->user_id == ctx_id) {
+ atomic_inc(&ctx->users);
ret = ctx;
break;
}
void aio_complete(struct kiocb *iocb, long res, long res2)
{
struct kioctx *ctx = iocb->ki_ctx;
- struct aio_ring_info *info;
struct aio_ring *ring;
- struct io_event *event;
+ struct io_event *ev_page, *event;
unsigned long flags;
- unsigned long tail;
+ unsigned tail, pos;
/*
* Special case handling for sync iocbs:
* - the sync task helpfully left a reference to itself in the iocb
*/
if (is_sync_kiocb(iocb)) {
- BUG_ON(iocb->ki_users != 1);
+ BUG_ON(atomic_read(&iocb->ki_users) != 1);
iocb->ki_user_data = res;
- iocb->ki_users = 0;
+ atomic_set(&iocb->ki_users, 0);
wake_up_process(iocb->ki_obj.tsk);
return;
}
- info = &ctx->ring_info;
-
- /* add a completion event to the ring buffer.
- * must be done holding ctx->ctx_lock to prevent
- * other code from messing with the tail
- * pointer since we might be called from irq
- * context.
+ /*
+ * Take rcu_read_lock() in case the kioctx is being destroyed, as we
+ * need to issue a wakeup after decrementing reqs_active.
*/
- spin_lock_irqsave(&ctx->ctx_lock, flags);
+ rcu_read_lock();
+
+ if (iocb->ki_list.next) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->ctx_lock, flags);
+ list_del(&iocb->ki_list);
+ spin_unlock_irqrestore(&ctx->ctx_lock, flags);
+ }
/*
* cancelled requests don't get events, userland was given one
* when the event got cancelled.
*/
- if (kiocbIsCancelled(iocb))
+ if (unlikely(xchg(&iocb->ki_cancel,
+ KIOCB_CANCELLED) == KIOCB_CANCELLED)) {
+ atomic_dec(&ctx->reqs_active);
+ /* Still need the wake_up in case free_ioctx is waiting */
goto put_rq;
+ }
- ring = kmap_atomic(info->ring_pages[0]);
+ /*
+ * Add a completion event to the ring buffer. Must be done holding
+ * ctx->ctx_lock to prevent other code from messing with the tail
+ * pointer since we might be called from irq context.
+ */
+ spin_lock_irqsave(&ctx->completion_lock, flags);
- tail = info->tail;
- event = aio_ring_event(info, tail);
- if (++tail >= info->nr)
+ tail = ctx->tail;
+ pos = tail + AIO_EVENTS_OFFSET;
+
+ if (++tail >= ctx->nr_events)
tail = 0;
+ ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
+ event = ev_page + pos % AIO_EVENTS_PER_PAGE;
+
event->obj = (u64)(unsigned long)iocb->ki_obj.user;
event->data = iocb->ki_user_data;
event->res = res;
event->res2 = res2;
- dprintk("aio_complete: %p[%lu]: %p: %p %Lx %lx %lx\n",
- ctx, tail, iocb, iocb->ki_obj.user, iocb->ki_user_data,
- res, res2);
+ kunmap_atomic(ev_page);
+ flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
+
+ pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n",
+ ctx, tail, iocb, iocb->ki_obj.user, iocb->ki_user_data,
+ res, res2);
/* after flagging the request as done, we
* must never even look at it again
*/
smp_wmb(); /* make event visible before updating tail */
- info->tail = tail;
- ring->tail = tail;
+ ctx->tail = tail;
- put_aio_ring_event(event);
+ ring = kmap_atomic(ctx->ring_pages[0]);
+ ring->tail = tail;
kunmap_atomic(ring);
+ flush_dcache_page(ctx->ring_pages[0]);
+
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
- pr_debug("added to ring %p at [%lu]\n", iocb, tail);
+ pr_debug("added to ring %p at [%u]\n", iocb, tail);
/*
* Check if the user asked us to deliver the result through an
put_rq:
/* everything turned out well, dispose of the aiocb. */
- __aio_put_req(ctx, iocb);
+ aio_put_req(iocb);
/*
* We have to order our ring_info tail store above and test
if (waitqueue_active(&ctx->wait))
wake_up(&ctx->wait);
- spin_unlock_irqrestore(&ctx->ctx_lock, flags);
+ rcu_read_unlock();
}
EXPORT_SYMBOL(aio_complete);
-/* aio_read_evt
- * Pull an event off of the ioctx's event ring. Returns the number of
- * events fetched (0 or 1 ;-)
- * FIXME: make this use cmpxchg.
- * TODO: make the ringbuffer user mmap()able (requires FIXME).
+/* aio_read_events
+ * Pull an event off of the ioctx's event ring. Returns the number of
+ * events fetched
*/
-static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent)
+static long aio_read_events_ring(struct kioctx *ctx,
+ struct io_event __user *event, long nr)
{
- struct aio_ring_info *info = &ioctx->ring_info;
struct aio_ring *ring;
- unsigned long head;
- int ret = 0;
-
- ring = kmap_atomic(info->ring_pages[0]);
- dprintk("in aio_read_evt h%lu t%lu m%lu\n",
- (unsigned long)ring->head, (unsigned long)ring->tail,
- (unsigned long)ring->nr);
-
- if (ring->head == ring->tail)
- goto out;
+ unsigned head, pos;
+ long ret = 0;
+ int copy_ret;
- spin_lock(&info->ring_lock);
-
- head = ring->head % info->nr;
- if (head != ring->tail) {
- struct io_event *evp = aio_ring_event(info, head);
- *ent = *evp;
- head = (head + 1) % info->nr;
- smp_mb(); /* finish reading the event before updatng the head */
- ring->head = head;
- ret = 1;
- put_aio_ring_event(evp);
- }
- spin_unlock(&info->ring_lock);
+ mutex_lock(&ctx->ring_lock);
-out:
- dprintk("leaving aio_read_evt: %d h%lu t%lu\n", ret,
- (unsigned long)ring->head, (unsigned long)ring->tail);
+ ring = kmap_atomic(ctx->ring_pages[0]);
+ head = ring->head;
kunmap_atomic(ring);
- return ret;
-}
-struct aio_timeout {
- struct timer_list timer;
- int timed_out;
- struct task_struct *p;
-};
-
-static void timeout_func(unsigned long data)
-{
- struct aio_timeout *to = (struct aio_timeout *)data;
+ pr_debug("h%u t%u m%u\n", head, ctx->tail, ctx->nr_events);
- to->timed_out = 1;
- wake_up_process(to->p);
-}
+ if (head == ctx->tail)
+ goto out;
-static inline void init_timeout(struct aio_timeout *to)
-{
- setup_timer_on_stack(&to->timer, timeout_func, (unsigned long) to);
- to->timed_out = 0;
- to->p = current;
-}
+ while (ret < nr) {
+ long avail;
+ struct io_event *ev;
+ struct page *page;
-static inline void set_timeout(long start_jiffies, struct aio_timeout *to,
- const struct timespec *ts)
-{
- to->timer.expires = start_jiffies + timespec_to_jiffies(ts);
- if (time_after(to->timer.expires, jiffies))
- add_timer(&to->timer);
- else
- to->timed_out = 1;
-}
+ avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head;
+ if (head == ctx->tail)
+ break;
-static inline void clear_timeout(struct aio_timeout *to)
-{
- del_singleshot_timer_sync(&to->timer);
-}
+ avail = min(avail, nr - ret);
+ avail = min_t(long, avail, AIO_EVENTS_PER_PAGE -
+ ((head + AIO_EVENTS_OFFSET) % AIO_EVENTS_PER_PAGE));
-static int read_events(struct kioctx *ctx,
- long min_nr, long nr,
- struct io_event __user *event,
- struct timespec __user *timeout)
-{
- long start_jiffies = jiffies;
- struct task_struct *tsk = current;
- DECLARE_WAITQUEUE(wait, tsk);
- int ret;
- int i = 0;
- struct io_event ent;
- struct aio_timeout to;
-
- /* needed to zero any padding within an entry (there shouldn't be
- * any, but C is fun!
- */
- memset(&ent, 0, sizeof(ent));
- ret = 0;
- while (likely(i < nr)) {
- ret = aio_read_evt(ctx, &ent);
- if (unlikely(ret <= 0))
- break;
+ pos = head + AIO_EVENTS_OFFSET;
+ page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE];
+ pos %= AIO_EVENTS_PER_PAGE;
- dprintk("read event: %Lx %Lx %Lx %Lx\n",
- ent.data, ent.obj, ent.res, ent.res2);
+ ev = kmap(page);
+ copy_ret = copy_to_user(event + ret, ev + pos,
+ sizeof(*ev) * avail);
+ kunmap(page);
- /* Could we split the check in two? */
- ret = -EFAULT;
- if (unlikely(copy_to_user(event, &ent, sizeof(ent)))) {
- dprintk("aio: lost an event due to EFAULT.\n");
- break;
+ if (unlikely(copy_ret)) {
+ ret = -EFAULT;
+ goto out;
}
- ret = 0;
- /* Good, event copied to userland, update counts. */
- event ++;
- i ++;
+ ret += avail;
+ head += avail;
+ head %= ctx->nr_events;
}
- if (min_nr <= i)
- return i;
- if (ret)
- return ret;
+ ring = kmap_atomic(ctx->ring_pages[0]);
+ ring->head = head;
+ kunmap_atomic(ring);
+ flush_dcache_page(ctx->ring_pages[0]);
- /* End fast path */
+ pr_debug("%li h%u t%u\n", ret, head, ctx->tail);
- init_timeout(&to);
- if (timeout) {
- struct timespec ts;
- ret = -EFAULT;
- if (unlikely(copy_from_user(&ts, timeout, sizeof(ts))))
- goto out;
+ atomic_sub(ret, &ctx->reqs_active);
+out:
+ mutex_unlock(&ctx->ring_lock);
- set_timeout(start_jiffies, &to, &ts);
- }
+ return ret;
+}
- while (likely(i < nr)) {
- add_wait_queue_exclusive(&ctx->wait, &wait);
- do {
- set_task_state(tsk, TASK_INTERRUPTIBLE);
- ret = aio_read_evt(ctx, &ent);
- if (ret)
- break;
- if (min_nr <= i)
- break;
- if (unlikely(ctx->dead)) {
- ret = -EINVAL;
- break;
- }
- if (to.timed_out) /* Only check after read evt */
- break;
- /* Try to only show up in io wait if there are ops
- * in flight */
- if (ctx->reqs_active)
- io_schedule();
- else
- schedule();
- if (signal_pending(tsk)) {
- ret = -EINTR;
- break;
- }
- /*ret = aio_read_evt(ctx, &ent);*/
- } while (1) ;
-
- set_task_state(tsk, TASK_RUNNING);
- remove_wait_queue(&ctx->wait, &wait);
-
- if (unlikely(ret <= 0))
- break;
+static bool aio_read_events(struct kioctx *ctx, long min_nr, long nr,
+ struct io_event __user *event, long *i)
+{
+ long ret = aio_read_events_ring(ctx, event + *i, nr - *i);
- ret = -EFAULT;
- if (unlikely(copy_to_user(event, &ent, sizeof(ent)))) {
- dprintk("aio: lost an event due to EFAULT.\n");
- break;
- }
+ if (ret > 0)
+ *i += ret;
- /* Good, event copied to userland, update counts. */
- event ++;
- i ++;
- }
+ if (unlikely(atomic_read(&ctx->dead)))
+ ret = -EINVAL;
- if (timeout)
- clear_timeout(&to);
-out:
- destroy_timer_on_stack(&to.timer);
- return i ? i : ret;
+ if (!*i)
+ *i = ret;
+
+ return ret < 0 || *i >= min_nr;
}
-/* Take an ioctx and remove it from the list of ioctx's. Protects
- * against races with itself via ->dead.
- */
-static void io_destroy(struct kioctx *ioctx)
+static long read_events(struct kioctx *ctx, long min_nr, long nr,
+ struct io_event __user *event,
+ struct timespec __user *timeout)
{
- struct mm_struct *mm = current->mm;
- int was_dead;
+ ktime_t until = { .tv64 = KTIME_MAX };
+ long ret = 0;
- /* delete the entry from the list is someone else hasn't already */
- spin_lock(&mm->ioctx_lock);
- was_dead = ioctx->dead;
- ioctx->dead = 1;
- hlist_del_rcu(&ioctx->list);
- spin_unlock(&mm->ioctx_lock);
+ if (timeout) {
+ struct timespec ts;
- dprintk("aio_release(%p)\n", ioctx);
- if (likely(!was_dead))
- put_ioctx(ioctx); /* twice for the list */
+ if (unlikely(copy_from_user(&ts, timeout, sizeof(ts))))
+ return -EFAULT;
- kill_ctx(ioctx);
+ until = timespec_to_ktime(ts);
+ }
/*
- * Wake up any waiters. The setting of ctx->dead must be seen
- * by other CPUs at this point. Right now, we rely on the
- * locking done by the above calls to ensure this consistency.
+ * Note that aio_read_events() is being called as the conditional - i.e.
+ * we're calling it after prepare_to_wait() has set task state to
+ * TASK_INTERRUPTIBLE.
+ *
+ * But aio_read_events() can block, and if it blocks it's going to flip
+ * the task state back to TASK_RUNNING.
+ *
+ * This should be ok, provided it doesn't flip the state back to
+ * TASK_RUNNING and return 0 too much - that causes us to spin. That
+ * will only happen if the mutex_lock() call blocks, and we then find
+ * the ringbuffer empty. So in practice we should be ok, but it's
+ * something to be aware of when touching this code.
*/
- wake_up_all(&ioctx->wait);
+ wait_event_interruptible_hrtimeout(ctx->wait,
+ aio_read_events(ctx, min_nr, nr, event, &ret), until);
+
+ if (!ret && signal_pending(current))
+ ret = -EINTR;
+
+ return ret;
}
/* sys_io_setup:
if (!IS_ERR(ioctx)) {
ret = put_user(ioctx->user_id, ctxp);
if (ret)
- io_destroy(ioctx);
+ kill_ioctx(ioctx);
put_ioctx(ioctx);
}
{
struct kioctx *ioctx = lookup_ioctx(ctx);
if (likely(NULL != ioctx)) {
- io_destroy(ioctx);
+ kill_ioctx(ioctx);
put_ioctx(ioctx);
return 0;
}
BUG_ON(ret > 0 && iocb->ki_left == 0);
}
-static ssize_t aio_rw_vect_retry(struct kiocb *iocb)
+typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *,
+ unsigned long, loff_t);
+
+static ssize_t aio_rw_vect_retry(struct kiocb *iocb, int rw, aio_rw_op *rw_op)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
- ssize_t (*rw_op)(struct kiocb *, const struct iovec *,
- unsigned long, loff_t);
ssize_t ret = 0;
- unsigned short opcode;
-
- if ((iocb->ki_opcode == IOCB_CMD_PREADV) ||
- (iocb->ki_opcode == IOCB_CMD_PREAD)) {
- rw_op = file->f_op->aio_read;
- opcode = IOCB_CMD_PREADV;
- } else {
- rw_op = file->f_op->aio_write;
- opcode = IOCB_CMD_PWRITEV;
- }
/* This matches the pread()/pwrite() logic */
if (iocb->ki_pos < 0)
return -EINVAL;
- if (opcode == IOCB_CMD_PWRITEV)
+ if (rw == WRITE)
file_start_write(file);
do {
ret = rw_op(iocb, &iocb->ki_iovec[iocb->ki_cur_seg],
/* retry all partial writes. retry partial reads as long as its a
* regular file. */
} while (ret > 0 && iocb->ki_left > 0 &&
- (opcode == IOCB_CMD_PWRITEV ||
+ (rw == WRITE ||
(!S_ISFIFO(inode->i_mode) && !S_ISSOCK(inode->i_mode))));
- if (opcode == IOCB_CMD_PWRITEV)
+ if (rw == WRITE)
file_end_write(file);
/* This means we must have transferred all that we could */
/* If we managed to write some out we return that, rather than
* the eventual error. */
- if (opcode == IOCB_CMD_PWRITEV
+ if (rw == WRITE
&& ret < 0 && ret != -EIOCBQUEUED
&& iocb->ki_nbytes - iocb->ki_left)
ret = iocb->ki_nbytes - iocb->ki_left;
return ret;
}
-static ssize_t aio_fdsync(struct kiocb *iocb)
-{
- struct file *file = iocb->ki_filp;
- ssize_t ret = -EINVAL;
-
- if (file->f_op->aio_fsync)
- ret = file->f_op->aio_fsync(iocb, 1);
- return ret;
-}
-
-static ssize_t aio_fsync(struct kiocb *iocb)
-{
- struct file *file = iocb->ki_filp;
- ssize_t ret = -EINVAL;
-
- if (file->f_op->aio_fsync)
- ret = file->f_op->aio_fsync(iocb, 0);
- return ret;
-}
-
-static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat)
+static ssize_t aio_setup_vectored_rw(int rw, struct kiocb *kiocb, bool compat)
{
ssize_t ret;
+ kiocb->ki_nr_segs = kiocb->ki_nbytes;
+
#ifdef CONFIG_COMPAT
if (compat)
- ret = compat_rw_copy_check_uvector(type,
+ ret = compat_rw_copy_check_uvector(rw,
(struct compat_iovec __user *)kiocb->ki_buf,
- kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
+ kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec,
&kiocb->ki_iovec);
else
#endif
- ret = rw_copy_check_uvector(type,
+ ret = rw_copy_check_uvector(rw,
(struct iovec __user *)kiocb->ki_buf,
- kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
+ kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec,
&kiocb->ki_iovec);
if (ret < 0)
- goto out;
-
- ret = rw_verify_area(type, kiocb->ki_filp, &kiocb->ki_pos, ret);
- if (ret < 0)
- goto out;
+ return ret;
- kiocb->ki_nr_segs = kiocb->ki_nbytes;
- kiocb->ki_cur_seg = 0;
- /* ki_nbytes/left now reflect bytes instead of segs */
+ /* ki_nbytes now reflect bytes instead of segs */
kiocb->ki_nbytes = ret;
- kiocb->ki_left = ret;
-
- ret = 0;
-out:
- return ret;
+ return 0;
}
-static ssize_t aio_setup_single_vector(int type, struct file * file, struct kiocb *kiocb)
+static ssize_t aio_setup_single_vector(int rw, struct kiocb *kiocb)
{
- int bytes;
-
- bytes = rw_verify_area(type, file, &kiocb->ki_pos, kiocb->ki_left);
- if (bytes < 0)
- return bytes;
+ if (unlikely(!access_ok(!rw, kiocb->ki_buf, kiocb->ki_nbytes)))
+ return -EFAULT;
kiocb->ki_iovec = &kiocb->ki_inline_vec;
kiocb->ki_iovec->iov_base = kiocb->ki_buf;
- kiocb->ki_iovec->iov_len = bytes;
+ kiocb->ki_iovec->iov_len = kiocb->ki_nbytes;
kiocb->ki_nr_segs = 1;
- kiocb->ki_cur_seg = 0;
return 0;
}
* Performs the initial checks and aio retry method
* setup for the kiocb at the time of io submission.
*/
-static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
+static ssize_t aio_run_iocb(struct kiocb *req, bool compat)
{
- struct file *file = kiocb->ki_filp;
- ssize_t ret = 0;
+ struct file *file = req->ki_filp;
+ ssize_t ret;
+ int rw;
+ fmode_t mode;
+ aio_rw_op *rw_op;
- switch (kiocb->ki_opcode) {
+ switch (req->ki_opcode) {
case IOCB_CMD_PREAD:
- ret = -EBADF;
- if (unlikely(!(file->f_mode & FMODE_READ)))
- break;
- ret = -EFAULT;
- if (unlikely(!access_ok(VERIFY_WRITE, kiocb->ki_buf,
- kiocb->ki_left)))
- break;
- ret = aio_setup_single_vector(READ, file, kiocb);
- if (ret)
- break;
- ret = -EINVAL;
- if (file->f_op->aio_read)
- kiocb->ki_retry = aio_rw_vect_retry;
- break;
- case IOCB_CMD_PWRITE:
- ret = -EBADF;
- if (unlikely(!(file->f_mode & FMODE_WRITE)))
- break;
- ret = -EFAULT;
- if (unlikely(!access_ok(VERIFY_READ, kiocb->ki_buf,
- kiocb->ki_left)))
- break;
- ret = aio_setup_single_vector(WRITE, file, kiocb);
- if (ret)
- break;
- ret = -EINVAL;
- if (file->f_op->aio_write)
- kiocb->ki_retry = aio_rw_vect_retry;
- break;
case IOCB_CMD_PREADV:
- ret = -EBADF;
- if (unlikely(!(file->f_mode & FMODE_READ)))
- break;
- ret = aio_setup_vectored_rw(READ, kiocb, compat);
- if (ret)
- break;
- ret = -EINVAL;
- if (file->f_op->aio_read)
- kiocb->ki_retry = aio_rw_vect_retry;
- break;
+ mode = FMODE_READ;
+ rw = READ;
+ rw_op = file->f_op->aio_read;
+ goto rw_common;
+
+ case IOCB_CMD_PWRITE:
case IOCB_CMD_PWRITEV:
- ret = -EBADF;
- if (unlikely(!(file->f_mode & FMODE_WRITE)))
- break;
- ret = aio_setup_vectored_rw(WRITE, kiocb, compat);
+ mode = FMODE_WRITE;
+ rw = WRITE;
+ rw_op = file->f_op->aio_write;
+ goto rw_common;
+rw_common:
+ if (unlikely(!(file->f_mode & mode)))
+ return -EBADF;
+
+ if (!rw_op)
+ return -EINVAL;
+
+ ret = (req->ki_opcode == IOCB_CMD_PREADV ||
+ req->ki_opcode == IOCB_CMD_PWRITEV)
+ ? aio_setup_vectored_rw(rw, req, compat)
+ : aio_setup_single_vector(rw, req);
if (ret)
- break;
- ret = -EINVAL;
- if (file->f_op->aio_write)
- kiocb->ki_retry = aio_rw_vect_retry;
+ return ret;
+
+ ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
+ if (ret < 0)
+ return ret;
+
+ req->ki_nbytes = ret;
+ req->ki_left = ret;
+
+ ret = aio_rw_vect_retry(req, rw, rw_op);
break;
+
case IOCB_CMD_FDSYNC:
- ret = -EINVAL;
- if (file->f_op->aio_fsync)
- kiocb->ki_retry = aio_fdsync;
+ if (!file->f_op->aio_fsync)
+ return -EINVAL;
+
+ ret = file->f_op->aio_fsync(req, 1);
break;
+
case IOCB_CMD_FSYNC:
- ret = -EINVAL;
- if (file->f_op->aio_fsync)
- kiocb->ki_retry = aio_fsync;
+ if (!file->f_op->aio_fsync)
+ return -EINVAL;
+
+ ret = file->f_op->aio_fsync(req, 0);
break;
+
default:
- dprintk("EINVAL: io_submit: no operation provided\n");
- ret = -EINVAL;
+ pr_debug("EINVAL: no operation provided\n");
+ return -EINVAL;
}
- if (!kiocb->ki_retry)
- return ret;
+ if (ret != -EIOCBQUEUED) {
+ /*
+ * There's no easy way to restart the syscall since other AIO's
+ * may be already running. Just fail this IO with EINTR.
+ */
+ if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
+ ret == -ERESTARTNOHAND ||
+ ret == -ERESTART_RESTARTBLOCK))
+ ret = -EINTR;
+ aio_complete(req, ret, 0);
+ }
return 0;
}
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
- struct iocb *iocb, struct kiocb_batch *batch,
- bool compat)
+ struct iocb *iocb, bool compat)
{
struct kiocb *req;
- struct file *file;
ssize_t ret;
/* enforce forwards compatibility on users */
if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2)) {
- pr_debug("EINVAL: io_submit: reserve field set\n");
+ pr_debug("EINVAL: reserve field set\n");
return -EINVAL;
}
return -EINVAL;
}
- file = fget(iocb->aio_fildes);
- if (unlikely(!file))
- return -EBADF;
-
- req = aio_get_req(ctx, batch); /* returns with 2 references to req */
- if (unlikely(!req)) {
- fput(file);
+ req = aio_get_req(ctx);
+ if (unlikely(!req))
return -EAGAIN;
+
+ req->ki_filp = fget(iocb->aio_fildes);
+ if (unlikely(!req->ki_filp)) {
+ ret = -EBADF;
+ goto out_put_req;
}
- req->ki_filp = file;
+
if (iocb->aio_flags & IOCB_FLAG_RESFD) {
/*
* If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
}
}
- ret = put_user(req->ki_key, &user_iocb->aio_key);
+ ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
if (unlikely(ret)) {
- dprintk("EFAULT: aio_key\n");
+ pr_debug("EFAULT: aio_key\n");
goto out_put_req;
}
req->ki_left = req->ki_nbytes = iocb->aio_nbytes;
req->ki_opcode = iocb->aio_lio_opcode;
- ret = aio_setup_iocb(req, compat);
-
- if (ret)
- goto out_put_req;
-
- spin_lock_irq(&ctx->ctx_lock);
- /*
- * We could have raced with io_destroy() and are currently holding a
- * reference to ctx which should be destroyed. We cannot submit IO
- * since ctx gets freed as soon as io_submit() puts its reference. The
- * check here is reliable: io_destroy() sets ctx->dead before waiting
- * for outstanding IO and the barrier between these two is realized by
- * unlock of mm->ioctx_lock and lock of ctx->ctx_lock. Analogously we
- * increment ctx->reqs_active before checking for ctx->dead and the
- * barrier is realized by unlock and lock of ctx->ctx_lock. Thus if we
- * don't see ctx->dead set here, io_destroy() waits for our IO to
- * finish.
- */
- if (ctx->dead)
- ret = -EINVAL;
- spin_unlock_irq(&ctx->ctx_lock);
+ ret = aio_run_iocb(req, compat);
if (ret)
goto out_put_req;
- if (unlikely(kiocbIsCancelled(req)))
- ret = -EINTR;
- else
- ret = req->ki_retry(req);
-
- if (ret != -EIOCBQUEUED) {
- /*
- * There's no easy way to restart the syscall since other AIO's
- * may be already running. Just fail this IO with EINTR.
- */
- if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
- ret == -ERESTARTNOHAND ||
- ret == -ERESTART_RESTARTBLOCK))
- ret = -EINTR;
- aio_complete(req, ret, 0);
- }
-
aio_put_req(req); /* drop extra ref to req */
return 0;
-
out_put_req:
+ atomic_dec(&ctx->reqs_active);
aio_put_req(req); /* drop extra ref to req */
aio_put_req(req); /* drop i/o ref to req */
return ret;
long ret = 0;
int i = 0;
struct blk_plug plug;
- struct kiocb_batch batch;
if (unlikely(nr < 0))
return -EINVAL;
ctx = lookup_ioctx(ctx_id);
if (unlikely(!ctx)) {
- pr_debug("EINVAL: io_submit: invalid context id\n");
+ pr_debug("EINVAL: invalid context id\n");
return -EINVAL;
}
- kiocb_batch_init(&batch, nr);
-
blk_start_plug(&plug);
/*
break;
}
- ret = io_submit_one(ctx, user_iocb, &tmp, &batch, compat);
+ ret = io_submit_one(ctx, user_iocb, &tmp, compat);
if (ret)
break;
}
blk_finish_plug(&plug);
- kiocb_batch_free(ctx, &batch);
put_ioctx(ctx);
return i ? i : ret;
}
assert_spin_locked(&ctx->ctx_lock);
+ if (key != KIOCB_KEY)
+ return NULL;
+
/* TODO: use a hash or array, this sucks. */
list_for_each(pos, &ctx->active_reqs) {
struct kiocb *kiocb = list_kiocb(pos);
- if (kiocb->ki_obj.user == iocb && kiocb->ki_key == key)
+ if (kiocb->ki_obj.user == iocb)
return kiocb;
}
return NULL;
* < min_nr if the timeout specified by timeout has elapsed
* before sufficient events are available, where timeout == NULL
* specifies an infinite timeout. Note that the timeout pointed to by
- * timeout is relative and will be updated if not NULL and the
- * operation blocks. Will fail with -ENOSYS if not implemented.
+ * timeout is relative. Will fail with -ENOSYS if not implemented.
*/
SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
long, min_nr,
projects / linux-2.6-block.git / blobdiff