#include <linux/security.h>
#include <linux/eventfd.h>
#include <linux/blkdev.h>
-#include <linux/mempool.h>
-#include <linux/hash.h>
#include <linux/compat.h>
#include <asm/kmap_types.h>
static DEFINE_SPINLOCK(fput_lock);
static LIST_HEAD(fput_head);
-#define AIO_BATCH_HASH_BITS 3 /* allocated on-stack, so don't go crazy */
-#define AIO_BATCH_HASH_SIZE (1 << AIO_BATCH_HASH_BITS)
-struct aio_batch_entry {
- struct hlist_node list;
- struct address_space *mapping;
-};
-mempool_t *abe_pool;
-
static void aio_kick_handler(struct work_struct *);
static void aio_queue_work(struct kioctx *);
kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
- aio_wq = create_workqueue("aio");
- abe_pool = mempool_create_kmalloc_pool(1, sizeof(struct aio_batch_entry));
- BUG_ON(!abe_pool);
+ aio_wq = alloc_workqueue("aio", 0, 1); /* used to limit concurrency */
+ BUG_ON(!aio_wq);
pr_debug("aio_setup: sizeof(struct page) = %d\n", (int)sizeof(struct page));
call_rcu(&ctx->rcu_head, ctx_rcu_free);
}
-#define get_ioctx(kioctx) do { \
- BUG_ON(atomic_read(&(kioctx)->users) <= 0); \
- atomic_inc(&(kioctx)->users); \
-} while (0)
-#define put_ioctx(kioctx) do { \
- BUG_ON(atomic_read(&(kioctx)->users) <= 0); \
- if (unlikely(atomic_dec_and_test(&(kioctx)->users))) \
- __put_ioctx(kioctx); \
-} while (0)
+static inline int try_get_ioctx(struct kioctx *kioctx)
+{
+ return atomic_inc_not_zero(&kioctx->users);
+}
+
+static inline void put_ioctx(struct kioctx *kioctx)
+{
+ BUG_ON(atomic_read(&kioctx->users) <= 0);
+ if (unlikely(atomic_dec_and_test(&kioctx->users)))
+ __put_ioctx(kioctx);
+}
/* ioctx_alloc
* Allocates and initializes an ioctx. Returns an ERR_PTR if it failed.
mm = ctx->mm = current->mm;
atomic_inc(&mm->mm_count);
- atomic_set(&ctx->users, 1);
+ atomic_set(&ctx->users, 2);
spin_lock_init(&ctx->ctx_lock);
spin_lock_init(&ctx->ring_info.ring_lock);
init_waitqueue_head(&ctx->wait);
ctx->reqs_active--;
if (unlikely(!ctx->reqs_active && ctx->dead))
- wake_up(&ctx->wait);
+ wake_up_all(&ctx->wait);
}
static void aio_fput_routine(struct work_struct *data)
fput(req->ki_filp);
/* Link the iocb into the context's free list */
+ rcu_read_lock();
spin_lock_irq(&ctx->ctx_lock);
really_put_req(ctx, req);
+ /*
+ * at that point ctx might've been killed, but actual
+ * freeing is RCU'd
+ */
spin_unlock_irq(&ctx->ctx_lock);
+ rcu_read_unlock();
- put_ioctx(ctx);
spin_lock_irq(&fput_lock);
}
spin_unlock_irq(&fput_lock);
* this function will be executed w/out any aio kthread wakeup.
*/
if (unlikely(!fput_atomic(req->ki_filp))) {
- get_ioctx(ctx);
spin_lock(&fput_lock);
list_add(&req->ki_list, &fput_head);
spin_unlock(&fput_lock);
- queue_work(aio_wq, &fput_work);
+ schedule_work(&fput_work);
} else {
req->ki_filp = NULL;
really_put_req(ctx, req);
rcu_read_lock();
hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) {
- if (ctx->user_id == ctx_id && !ctx->dead) {
- get_ioctx(ctx);
+ /*
+ * 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)){
ret = ctx;
break;
}
queue_delayed_work(aio_wq, &ctx->wq, timeout);
}
-
/*
- * aio_run_iocbs:
- * Process all pending retries queued on the ioctx
- * run list.
- * Assumes it is operating within the aio issuer's mm
- * context.
- */
-static inline void aio_run_iocbs(struct kioctx *ctx)
-{
- int requeue;
-
- spin_lock_irq(&ctx->ctx_lock);
-
- requeue = __aio_run_iocbs(ctx);
- spin_unlock_irq(&ctx->ctx_lock);
- if (requeue)
- aio_queue_work(ctx);
-}
-
-/*
- * just like aio_run_iocbs, but keeps running them until
- * the list stays empty
+ * aio_run_all_iocbs:
+ * Process all pending retries queued on the ioctx
+ * run list, and keep running them until the list
+ * stays empty.
+ * Assumes it is operating within the aio issuer's mm context.
*/
static inline void aio_run_all_iocbs(struct kioctx *ctx)
{
* by other CPUs at this point. Right now, we rely on the
* locking done by the above calls to ensure this consistency.
*/
- wake_up(&ioctx->wait);
+ wake_up_all(&ioctx->wait);
put_ioctx(ioctx); /* once for the lookup */
}
ret = PTR_ERR(ioctx);
if (!IS_ERR(ioctx)) {
ret = put_user(ioctx->user_id, ctxp);
- if (!ret)
+ if (!ret) {
+ put_ioctx(ioctx);
return 0;
-
- get_ioctx(ioctx); /* io_destroy() expects us to hold a ref */
+ }
io_destroy(ioctx);
}
if (ret < 0)
goto out;
+ ret = rw_verify_area(type, kiocb->ki_filp, &kiocb->ki_pos, ret);
+ if (ret < 0)
+ goto out;
+
kiocb->ki_nr_segs = kiocb->ki_nbytes;
kiocb->ki_cur_seg = 0;
/* ki_nbytes/left now reflect bytes instead of segs */
return ret;
}
-static ssize_t aio_setup_single_vector(struct kiocb *kiocb)
+static ssize_t aio_setup_single_vector(int type, struct file * file, struct kiocb *kiocb)
{
+ int bytes;
+
+ bytes = rw_verify_area(type, file, &kiocb->ki_pos, kiocb->ki_left);
+ if (bytes < 0)
+ return bytes;
+
kiocb->ki_iovec = &kiocb->ki_inline_vec;
kiocb->ki_iovec->iov_base = kiocb->ki_buf;
- kiocb->ki_iovec->iov_len = kiocb->ki_left;
+ kiocb->ki_iovec->iov_len = bytes;
kiocb->ki_nr_segs = 1;
kiocb->ki_cur_seg = 0;
return 0;
if (unlikely(!access_ok(VERIFY_WRITE, kiocb->ki_buf,
kiocb->ki_left)))
break;
- ret = security_file_permission(file, MAY_READ);
- if (unlikely(ret))
- break;
- ret = aio_setup_single_vector(kiocb);
+ ret = aio_setup_single_vector(READ, file, kiocb);
if (ret)
break;
ret = -EINVAL;
if (unlikely(!access_ok(VERIFY_READ, kiocb->ki_buf,
kiocb->ki_left)))
break;
- ret = security_file_permission(file, MAY_WRITE);
- if (unlikely(ret))
- break;
- ret = aio_setup_single_vector(kiocb);
+ ret = aio_setup_single_vector(WRITE, file, kiocb);
if (ret)
break;
ret = -EINVAL;
ret = -EBADF;
if (unlikely(!(file->f_mode & FMODE_READ)))
break;
- ret = security_file_permission(file, MAY_READ);
- if (unlikely(ret))
- break;
ret = aio_setup_vectored_rw(READ, kiocb, compat);
if (ret)
break;
ret = -EBADF;
if (unlikely(!(file->f_mode & FMODE_WRITE)))
break;
- ret = security_file_permission(file, MAY_WRITE);
- if (unlikely(ret))
- break;
ret = aio_setup_vectored_rw(WRITE, kiocb, compat);
if (ret)
break;
return 0;
}
-static void aio_batch_add(struct address_space *mapping,
- struct hlist_head *batch_hash)
-{
- struct aio_batch_entry *abe;
- struct hlist_node *pos;
- unsigned bucket;
-
- bucket = hash_ptr(mapping, AIO_BATCH_HASH_BITS);
- hlist_for_each_entry(abe, pos, &batch_hash[bucket], list) {
- if (abe->mapping == mapping)
- return;
- }
-
- abe = mempool_alloc(abe_pool, GFP_KERNEL);
- BUG_ON(!igrab(mapping->host));
- abe->mapping = mapping;
- hlist_add_head(&abe->list, &batch_hash[bucket]);
- return;
-}
-
-static void aio_batch_free(struct hlist_head *batch_hash)
-{
- struct aio_batch_entry *abe;
- struct hlist_node *pos, *n;
- int i;
-
- for (i = 0; i < AIO_BATCH_HASH_SIZE; i++) {
- hlist_for_each_entry_safe(abe, pos, n, &batch_hash[i], list) {
- blk_run_address_space(abe->mapping);
- iput(abe->mapping->host);
- hlist_del(&abe->list);
- mempool_free(abe, abe_pool);
- }
- }
-}
-
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
- struct iocb *iocb, struct hlist_head *batch_hash,
- bool compat)
+ struct iocb *iocb, bool compat)
{
struct kiocb *req;
struct file *file;
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) {
+ spin_unlock_irq(&ctx->ctx_lock);
+ ret = -EINVAL;
+ goto out_put_req;
+ }
aio_run_iocb(req);
if (!list_empty(&ctx->run_list)) {
/* drain the run list */
;
}
spin_unlock_irq(&ctx->ctx_lock);
- if (req->ki_opcode == IOCB_CMD_PREAD ||
- req->ki_opcode == IOCB_CMD_PREADV ||
- req->ki_opcode == IOCB_CMD_PWRITE ||
- req->ki_opcode == IOCB_CMD_PWRITEV)
- aio_batch_add(file->f_mapping, batch_hash);
aio_put_req(req); /* drop extra ref to req */
return 0;
struct kioctx *ctx;
long ret = 0;
int i;
- struct hlist_head batch_hash[AIO_BATCH_HASH_SIZE] = { { 0, }, };
+ struct blk_plug plug;
if (unlikely(nr < 0))
return -EINVAL;
return -EINVAL;
}
+ blk_start_plug(&plug);
+
/*
* AKPM: should this return a partial result if some of the IOs were
* successfully submitted?
break;
}
- ret = io_submit_one(ctx, user_iocb, &tmp, batch_hash, compat);
+ ret = io_submit_one(ctx, user_iocb, &tmp, compat);
if (ret)
break;
}
- aio_batch_free(batch_hash);
+ blk_finish_plug(&plug);
put_ioctx(ctx);
return i ? i : ret;
long ret = -EINVAL;
if (likely(ioctx)) {
- if (likely(min_nr <= nr && min_nr >= 0 && nr >= 0))
+ if (likely(min_nr <= nr && min_nr >= 0))
ret = read_events(ioctx, min_nr, nr, events, timeout);
put_ioctx(ioctx);
}