struct aio_ring_info was kind of odd, the only place it's used is where
it's embedded in struct kioctx - there's no real need for it.
The next patch rearranges struct kioctx and puts various things on their
own cachelines - getting rid of struct aio_ring_info now makes that
reordering a bit clearer.
Signed-off-by: Kent Overstreet <koverstr...@google.com>
---
fs/aio.c | 142 ++++++++++++++++++++++++++++++---------------------------------
1 file changed, 68 insertions(+), 74 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index f2d616e..1ff4d3b 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -58,18 +58,6 @@ struct aio_ring {
}; /* 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;
- struct mutex ring_lock;
- long nr_pages;
-
- unsigned nr, tail;
-
- struct page *internal_pages[AIO_RING_PAGES];
-};
struct kioctx {
atomic_t users;
@@ -86,12 +74,28 @@ struct kioctx {
atomic_t reqs_active;
struct list_head active_reqs; /* used for cancellation */
+ unsigned nr;
+
/* sys_io_setup currently limits this to an unsigned int */
unsigned max_reqs;
- struct aio_ring_info ring_info;
+ unsigned long mmap_base;
+ unsigned long mmap_size;
+
+ struct page **ring_pages;
+ long nr_pages;
+
+ struct {
+ struct mutex ring_lock;
+ } ____cacheline_aligned;
+
+ struct {
+ unsigned tail;
+ spinlock_t completion_lock;
+ } ____cacheline_aligned;
+
+ struct page *internal_pages[AIO_RING_PAGES];
- spinlock_t completion_lock;
};
/*------ sysctl variables----*/
@@ -120,26 +124,21 @@ __initcall(aio_setup);
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;
@@ -157,42 +156,42 @@ static int aio_setup_ring(struct kioctx *ctx)
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 = 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;
- pr_debug("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);
- 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);
+ 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;
}
- pr_debug("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;
}
- ctx->user_id = info->mmap_base;
+ ctx->user_id = ctx->mmap_base;
- info->nr = nr_events; /* trusted copy */
+ ctx->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;
@@ -213,11 +212,11 @@ static int aio_setup_ring(struct kioctx *ctx)
#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) ({ \
+#define aio_ring_event(ctx, nr) ({ \
unsigned pos = (nr) + AIO_EVENTS_OFFSET; \
struct io_event *__event; \
__event = kmap_atomic( \
- (info)->ring_pages[pos / AIO_EVENTS_PER_PAGE]); \
+ (ctx)->ring_pages[pos / AIO_EVENTS_PER_PAGE]); \
__event += pos % AIO_EVENTS_PER_PAGE; \
__event; \
})
@@ -276,7 +275,6 @@ static int kiocb_cancel(struct kioctx *ctx, struct kiocb
*kiocb,
*/
static void free_ioctx(struct kioctx *ctx)
{
- struct aio_ring_info *info = &ctx->ring_info;
struct aio_ring *ring;
struct io_event res;
unsigned head, avail;
@@ -293,18 +291,18 @@ static void free_ioctx(struct kioctx *ctx)
spin_unlock_irq(&ctx->ctx_lock);
- ring = kmap_atomic(info->ring_pages[0]);
+ 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 != info->tail);
+ wait_event(ctx->wait, head != ctx->tail);
- avail = (head < info->tail ? info->tail : info->nr) - head;
+ avail = (head < ctx->tail ? ctx->tail : ctx->nr) - head;
atomic_sub(avail, &ctx->reqs_active);
head += avail;
- head %= info->nr;
+ head %= ctx->nr;
}
WARN_ON(atomic_read(&ctx->reqs_active) < 0);
@@ -356,7 +354,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
atomic_set(&ctx->users, 2);
spin_lock_init(&ctx->ctx_lock);
spin_lock_init(&ctx->completion_lock);
- mutex_init(&ctx->ring_info.ring_lock);
+ mutex_init(&ctx->ring_lock);
init_waitqueue_head(&ctx->wait);
INIT_LIST_HEAD(&ctx->active_reqs);
@@ -380,7 +378,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
spin_unlock(&mm->ioctx_lock);
pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
- ctx, ctx->user_id, mm, ctx->ring_info.nr);
+ ctx, ctx->user_id, mm, ctx->nr);
return ctx;
out_cleanup:
@@ -453,7 +451,7 @@ void exit_aio(struct mm_struct *mm)
* 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;
+ ctx->mmap_size = 0;
kill_ioctx(ctx);
}
}
@@ -472,10 +470,10 @@ static inline struct kiocb *aio_get_req(struct kioctx
*ctx)
{
struct kiocb *req;
- if (atomic_read(&ctx->reqs_active) >= ctx->ring_info.nr)
+ if (atomic_read(&ctx->reqs_active) >= ctx->nr)
return NULL;
- if (atomic_inc_return(&ctx->reqs_active) > ctx->ring_info.nr)
+ if (atomic_inc_return(&ctx->reqs_active) > ctx->nr)
goto out_put;
req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO);
@@ -539,7 +537,6 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
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;
unsigned long flags;
@@ -560,8 +557,6 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
return;
}
- info = &ctx->ring_info;
-
/*
* Take rcu_read_lock() in case the kioctx is being destroyed, as we
* need to issue a wakeup after decrementing reqs_active.
@@ -593,11 +588,11 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
*/
spin_lock_irqsave(&ctx->completion_lock, flags);
- ring = kmap_atomic(info->ring_pages[0]);
+ ring = kmap_atomic(ctx->ring_pages[0]);
- tail = info->tail;
- event = aio_ring_event(info, tail);
- if (++tail >= info->nr)
+ tail = ctx->tail;
+ event = aio_ring_event(ctx, tail);
+ if (++tail >= ctx->nr)
tail = 0;
event->obj = (u64)(unsigned long)iocb->ki_obj.user;
@@ -614,7 +609,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
*/
smp_wmb(); /* make event visible before updating tail */
- info->tail = tail;
+ ctx->tail = tail;
ring->tail = tail;
put_aio_ring_event(event);
@@ -658,25 +653,24 @@ EXPORT_SYMBOL(aio_complete);
static int aio_read_events(struct kioctx *ctx, struct io_event __user *event,
long nr)
{
- struct aio_ring_info *info = &ctx->ring_info;
struct aio_ring *ring;
unsigned head, pos;
int ret = 0, copy_ret;
- mutex_lock(&info->ring_lock);
+ mutex_lock(&ctx->ring_lock);
- ring = kmap_atomic(info->ring_pages[0]);
+ ring = kmap_atomic(ctx->ring_pages[0]);
head = ring->head;
kunmap_atomic(ring);
- pr_debug("h%u t%u m%u\n", head, info->tail, info->nr);
+ pr_debug("h%u t%u m%u\n", head, ctx->tail, ctx->nr);
while (ret < nr) {
- unsigned i = (head < info->tail ? info->tail : info->nr) - head;
+ unsigned i = (head < ctx->tail ? ctx->tail : ctx->nr) - head;
struct io_event *ev;
struct page *page;
- if (head == info->tail)
+ if (head == ctx->tail)
break;
i = min_t(int, i, nr - ret);
@@ -684,7 +678,7 @@ static int aio_read_events(struct kioctx *ctx, struct
io_event __user *event,
((head + AIO_EVENTS_OFFSET) % AIO_EVENTS_PER_PAGE));
pos = head + AIO_EVENTS_OFFSET;
- page = info->ring_pages[pos / AIO_EVENTS_PER_PAGE];
+ page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE];
pos %= AIO_EVENTS_PER_PAGE;
ev = kmap(page);
@@ -698,20 +692,20 @@ static int aio_read_events(struct kioctx *ctx, struct
io_event __user *event,
ret += i;
head += i;
- head %= info->nr;
+ head %= ctx->nr;
}
smp_mb(); /* finish reading the event before updatng the head */
- ring = kmap_atomic(info->ring_pages[0]);
+ ring = kmap_atomic(ctx->ring_pages[0]);
ring->head = head;
kunmap_atomic(ring);
atomic_sub(ret, &ctx->reqs_active);
- pr_debug("%d h%u t%u\n", ret, head, info->tail);
+ pr_debug("%d h%u t%u\n", ret, head, ctx->tail);
out:
- mutex_unlock(&info->ring_lock);
+ mutex_unlock(&ctx->ring_lock);
return ret;
}
--
1.7.12
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
