#define AIO_RING_PAGES 8
+struct kioctx_table {
+ struct rcu_head rcu;
+ unsigned nr;
+ struct kioctx *table[];
+};
+
struct kioctx_cpu {
unsigned reqs_available;
};
struct percpu_ref users;
atomic_t dead;
- /* This needs improving */
unsigned long user_id;
- struct hlist_node list;
struct __percpu kioctx_cpu *cpu;
struct page *internal_pages[AIO_RING_PAGES];
struct file *aio_ring_file;
+
+ unsigned id;
};
/*------ sysctl variables----*/
if (aio_ring_file) {
truncate_setsize(aio_ring_file->f_inode, 0);
- pr_debug("pid(%d) i_nlink=%u d_count=%d d_unhashed=%d i_count=%d\n",
- current->pid, aio_ring_file->f_inode->i_nlink,
- aio_ring_file->f_path.dentry->d_count,
- d_unhashed(aio_ring_file->f_path.dentry),
- atomic_read(&aio_ring_file->f_inode->i_count));
fput(aio_ring_file);
ctx->aio_ring_file = NULL;
}
aio_free_ring(ctx);
return -EAGAIN;
}
- up_write(&mm->mmap_sem);
-
- mm_populate(ctx->mmap_base, populate);
pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
+
+ /* We must do this while still holding mmap_sem for write, as we
+ * need to be protected against userspace attempting to mremap()
+ * or munmap() the ring buffer.
+ */
ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages,
1, 0, ctx->ring_pages, NULL);
+
+ /* Dropping the reference here is safe as the page cache will hold
+ * onto the pages for us. It is also required so that page migration
+ * can unmap the pages and get the right reference count.
+ */
for (i = 0; i < ctx->nr_pages; i++)
put_page(ctx->ring_pages[i]);
+ up_write(&mm->mmap_sem);
+
if (unlikely(ctx->nr_pages != nr_pages)) {
aio_free_ring(ctx);
return -EAGAIN;
ring = kmap_atomic(ctx->ring_pages[0]);
ring->nr = nr_events; /* user copy */
- ring->id = ctx->user_id;
+ ring->id = ~0U;
ring->head = ring->tail = 0;
ring->magic = AIO_RING_MAGIC;
ring->compat_features = AIO_RING_COMPAT_FEATURES;
static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb)
{
kiocb_cancel_fn *old, *cancel;
- int ret = -EINVAL;
/*
* Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it
cancel = ACCESS_ONCE(kiocb->ki_cancel);
do {
if (!cancel || cancel == KIOCB_CANCELLED)
- return ret;
+ return -EINVAL;
old = cancel;
cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
} while (cancel != old);
- atomic_inc(&kiocb->ki_users);
- spin_unlock_irq(&ctx->ctx_lock);
-
- ret = cancel(kiocb);
-
- spin_lock_irq(&ctx->ctx_lock);
- aio_put_req(kiocb);
-
- return ret;
+ return cancel(kiocb);
}
static void free_ioctx_rcu(struct rcu_head *head)
schedule_work(&ctx->free_work);
}
+static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
+{
+ unsigned i, new_nr;
+ struct kioctx_table *table, *old;
+ struct aio_ring *ring;
+
+ spin_lock(&mm->ioctx_lock);
+ rcu_read_lock();
+ table = rcu_dereference(mm->ioctx_table);
+
+ while (1) {
+ if (table)
+ for (i = 0; i < table->nr; i++)
+ if (!table->table[i]) {
+ ctx->id = i;
+ table->table[i] = ctx;
+ rcu_read_unlock();
+ spin_unlock(&mm->ioctx_lock);
+
+ ring = kmap_atomic(ctx->ring_pages[0]);
+ ring->id = ctx->id;
+ kunmap_atomic(ring);
+ return 0;
+ }
+
+ new_nr = (table ? table->nr : 1) * 4;
+
+ rcu_read_unlock();
+ spin_unlock(&mm->ioctx_lock);
+
+ table = kzalloc(sizeof(*table) + sizeof(struct kioctx *) *
+ new_nr, GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+
+ table->nr = new_nr;
+
+ spin_lock(&mm->ioctx_lock);
+ rcu_read_lock();
+ old = rcu_dereference(mm->ioctx_table);
+
+ if (!old) {
+ rcu_assign_pointer(mm->ioctx_table, table);
+ } else if (table->nr > old->nr) {
+ memcpy(table->table, old->table,
+ old->nr * sizeof(struct kioctx *));
+
+ rcu_assign_pointer(mm->ioctx_table, table);
+ kfree_rcu(old, rcu);
+ } else {
+ kfree(table);
+ table = old;
+ }
+ }
+}
+
/* ioctx_alloc
* Allocates and initializes an ioctx. Returns an ERR_PTR if it failed.
*/
return ERR_PTR(-EINVAL);
}
- if (!nr_events || (unsigned long)nr_events > aio_max_nr)
+ if (!nr_events || (unsigned long)nr_events > (aio_max_nr * 2UL))
return ERR_PTR(-EAGAIN);
ctx = kmem_cache_zalloc(kioctx_cachep, GFP_KERNEL);
atomic_set(&ctx->reqs_available, ctx->nr_events - 1);
ctx->req_batch = (ctx->nr_events - 1) / (num_possible_cpus() * 4);
- BUG_ON(!ctx->req_batch);
+ if (ctx->req_batch < 1)
+ ctx->req_batch = 1;
/* limit the number of system wide aios */
spin_lock(&aio_nr_lock);
- if (aio_nr + nr_events > aio_max_nr ||
+ if (aio_nr + nr_events > (aio_max_nr * 2UL) ||
aio_nr + nr_events < aio_nr) {
spin_unlock(&aio_nr_lock);
goto out_cleanup;
percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */
- /* now link into global list. */
- spin_lock(&mm->ioctx_lock);
- hlist_add_head_rcu(&ctx->list, &mm->ioctx_list);
- spin_unlock(&mm->ioctx_lock);
+ err = ioctx_add_table(ctx, mm);
+ if (err)
+ goto out_cleanup_put;
pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
ctx, ctx->user_id, mm, ctx->nr_events);
return ctx;
+out_cleanup_put:
+ percpu_ref_put(&ctx->users);
out_cleanup:
err = -EAGAIN;
aio_free_ring(ctx);
* when the processes owning a context have all exited to encourage
* the rapid destruction of the kioctx.
*/
-static void kill_ioctx(struct kioctx *ctx)
+static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx)
{
if (!atomic_xchg(&ctx->dead, 1)) {
- hlist_del_rcu(&ctx->list);
+ struct kioctx_table *table;
+
+ spin_lock(&mm->ioctx_lock);
+ rcu_read_lock();
+ table = rcu_dereference(mm->ioctx_table);
+
+ WARN_ON(ctx != table->table[ctx->id]);
+ table->table[ctx->id] = NULL;
+ rcu_read_unlock();
+ spin_unlock(&mm->ioctx_lock);
+
/* percpu_ref_kill() will do the necessary call_rcu() */
wake_up_all(&ctx->wait);
/* wait_on_sync_kiocb:
* Waits on the given sync kiocb to complete.
*/
-ssize_t wait_on_sync_kiocb(struct kiocb *iocb)
+ssize_t wait_on_sync_kiocb(struct kiocb *req)
{
- while (atomic_read(&iocb->ki_users)) {
+ while (!req->ki_ctx) {
set_current_state(TASK_UNINTERRUPTIBLE);
- if (!atomic_read(&iocb->ki_users))
+ if (req->ki_ctx)
break;
io_schedule();
}
__set_current_state(TASK_RUNNING);
- return iocb->ki_user_data;
+ return req->ki_user_data;
}
EXPORT_SYMBOL(wait_on_sync_kiocb);
*/
void exit_aio(struct mm_struct *mm)
{
+ struct kioctx_table *table;
struct kioctx *ctx;
- struct hlist_node *n;
+ unsigned i = 0;
+
+ while (1) {
+ rcu_read_lock();
+ table = rcu_dereference(mm->ioctx_table);
+
+ do {
+ if (!table || i >= table->nr) {
+ rcu_read_unlock();
+ rcu_assign_pointer(mm->ioctx_table, NULL);
+ if (table)
+ kfree(table);
+ return;
+ }
+
+ ctx = table->table[i++];
+ } while (!ctx);
+
+ rcu_read_unlock();
- hlist_for_each_entry_safe(ctx, n, &mm->ioctx_list, list) {
/*
* We don't need to bother with munmap() here -
* exit_mmap(mm) is coming and it'll unmap everything.
*/
ctx->mmap_size = 0;
- kill_ioctx(ctx);
+ kill_ioctx(mm, ctx);
}
}
}
/* aio_get_req
- * 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->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.
+ * Allocate a slot for an aio request.
+ * Returns NULL if no requests are free.
*/
static inline struct kiocb *aio_get_req(struct kioctx *ctx)
{
if (unlikely(!req))
goto out_put;
- atomic_set(&req->ki_users, 1);
req->ki_ctx = ctx;
return req;
out_put:
fput(req->ki_filp);
if (req->ki_eventfd != NULL)
eventfd_ctx_put(req->ki_eventfd);
- if (req->ki_dtor)
- req->ki_dtor(req);
- if (req->ki_iovec != &req->ki_inline_vec)
- kfree(req->ki_iovec);
kmem_cache_free(kiocb_cachep, req);
}
-void aio_put_req(struct kiocb *req)
-{
- if (atomic_dec_and_test(&req->ki_users))
- kiocb_free(req);
-}
-EXPORT_SYMBOL(aio_put_req);
-
static struct kioctx *lookup_ioctx(unsigned long ctx_id)
{
+ struct aio_ring __user *ring = (void __user *)ctx_id;
struct mm_struct *mm = current->mm;
struct kioctx *ctx, *ret = NULL;
+ struct kioctx_table *table;
+ unsigned id;
+
+ if (get_user(id, &ring->id))
+ return NULL;
rcu_read_lock();
+ table = rcu_dereference(mm->ioctx_table);
- hlist_for_each_entry_rcu(ctx, &mm->ioctx_list, list) {
- if (ctx->user_id == ctx_id) {
- percpu_ref_get(&ctx->users);
- ret = ctx;
- break;
- }
- }
+ if (!table || id >= table->nr)
+ goto out;
+ ctx = table->table[id];
+ if (ctx && ctx->user_id == ctx_id) {
+ percpu_ref_get(&ctx->users);
+ ret = ctx;
+ }
+out:
rcu_read_unlock();
return ret;
}
* - the sync task helpfully left a reference to itself in the iocb
*/
if (is_sync_kiocb(iocb)) {
- BUG_ON(atomic_read(&iocb->ki_users) != 1);
iocb->ki_user_data = res;
- atomic_set(&iocb->ki_users, 0);
+ smp_wmb();
+ iocb->ki_ctx = ERR_PTR(-EXDEV);
wake_up_process(iocb->ki_obj.tsk);
return;
}
eventfd_signal(iocb->ki_eventfd, 1);
/* everything turned out well, dispose of the aiocb. */
- aio_put_req(iocb);
+ kiocb_free(iocb);
/*
* We have to order our ring_info tail store above and test
if (!IS_ERR(ioctx)) {
ret = put_user(ioctx->user_id, ctxp);
if (ret)
- kill_ioctx(ioctx);
+ kill_ioctx(current->mm, ioctx);
percpu_ref_put(&ioctx->users);
}
{
struct kioctx *ioctx = lookup_ioctx(ctx);
if (likely(NULL != ioctx)) {
- kill_ioctx(ioctx);
+ kill_ioctx(current->mm, ioctx);
percpu_ref_put(&ioctx->users);
return 0;
}
typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *,
unsigned long, loff_t);
-static ssize_t aio_setup_vectored_rw(int rw, struct kiocb *kiocb, bool compat)
+static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb,
+ int rw, char __user *buf,
+ unsigned long *nr_segs,
+ struct iovec **iovec,
+ bool compat)
{
ssize_t ret;
- kiocb->ki_nr_segs = kiocb->ki_nbytes;
+ *nr_segs = kiocb->ki_nbytes;
#ifdef CONFIG_COMPAT
if (compat)
ret = compat_rw_copy_check_uvector(rw,
- (struct compat_iovec __user *)kiocb->ki_buf,
- kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec,
- &kiocb->ki_iovec);
+ (struct compat_iovec __user *)buf,
+ *nr_segs, 1, *iovec, iovec);
else
#endif
ret = rw_copy_check_uvector(rw,
- (struct iovec __user *)kiocb->ki_buf,
- kiocb->ki_nr_segs, 1, &kiocb->ki_inline_vec,
- &kiocb->ki_iovec);
+ (struct iovec __user *)buf,
+ *nr_segs, 1, *iovec, iovec);
if (ret < 0)
return ret;
return 0;
}
-static ssize_t aio_setup_single_vector(int rw, struct kiocb *kiocb)
+static ssize_t aio_setup_single_vector(struct kiocb *kiocb,
+ int rw, char __user *buf,
+ unsigned long *nr_segs,
+ struct iovec *iovec)
{
- if (unlikely(!access_ok(!rw, kiocb->ki_buf, kiocb->ki_nbytes)))
+ if (unlikely(!access_ok(!rw, 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 = kiocb->ki_nbytes;
- kiocb->ki_nr_segs = 1;
+ iovec->iov_base = buf;
+ iovec->iov_len = kiocb->ki_nbytes;
+ *nr_segs = 1;
return 0;
}
* Performs the initial checks and aio retry method
* setup for the kiocb at the time of io submission.
*/
-static ssize_t aio_run_iocb(struct kiocb *req, bool compat)
+static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
+ char __user *buf, bool compat)
{
struct file *file = req->ki_filp;
ssize_t ret;
+ unsigned long nr_segs;
int rw;
fmode_t mode;
aio_rw_op *rw_op;
+ struct iovec inline_vec, *iovec = &inline_vec;
- switch (req->ki_opcode) {
+ switch (opcode) {
case IOCB_CMD_PREAD:
case IOCB_CMD_PREADV:
mode = FMODE_READ;
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);
+ ret = (opcode == IOCB_CMD_PREADV ||
+ opcode == IOCB_CMD_PWRITEV)
+ ? aio_setup_vectored_rw(req, rw, buf, &nr_segs,
+ &iovec, compat)
+ : aio_setup_single_vector(req, rw, buf, &nr_segs,
+ iovec);
if (ret)
return ret;
ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
- if (ret < 0)
+ if (ret < 0) {
+ if (iovec != &inline_vec)
+ kfree(iovec);
return ret;
+ }
req->ki_nbytes = ret;
if (rw == WRITE)
file_start_write(file);
- ret = rw_op(req, req->ki_iovec,
- req->ki_nr_segs, req->ki_pos);
+ ret = rw_op(req, iovec, nr_segs, req->ki_pos);
if (rw == WRITE)
file_end_write(file);
return -EINVAL;
}
+ if (iovec != &inline_vec)
+ kfree(iovec);
+
if (ret != -EIOCBQUEUED) {
/*
* There's no easy way to restart the syscall since other AIO's
req->ki_obj.user = user_iocb;
req->ki_user_data = iocb->aio_data;
req->ki_pos = iocb->aio_offset;
-
- req->ki_buf = (char __user *)(unsigned long)iocb->aio_buf;
req->ki_nbytes = iocb->aio_nbytes;
- req->ki_opcode = iocb->aio_lio_opcode;
- ret = aio_run_iocb(req, compat);
+ ret = aio_run_iocb(req, iocb->aio_lio_opcode,
+ (char __user *)(unsigned long)iocb->aio_buf,
+ compat);
if (ret)
goto out_put_req;
return 0;
out_put_req:
put_reqs_available(ctx, 1);
- aio_put_req(req);
+ kiocb_free(req);
return ret;
}