| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 21 Mar 2013 09:35:40 -0700
From: Kent Overstreet <koverstreet@...gle.com>
To: linux-kernel@...r.kernel.org, linux-aio@...ck.org,
akpm@...ux-foundation.org
Cc: Kent Overstreet <koverstreet@...gle.com>,
Zach Brown <zab@...hat.com>, Felipe Balbi <balbi@...com>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Mark Fasheh <mfasheh@...e.com>,
Joel Becker <jlbec@...lplan.org>,
Rusty Russell <rusty@...tcorp.com.au>,
Jens Axboe <axboe@...nel.dk>,
Asai Thambi S P <asamymuthupa@...ron.com>,
Selvan Mani <smani@...ron.com>,
Sam Bradshaw <sbradshaw@...ron.com>,
Jeff Moyer <jmoyer@...hat.com>,
Al Viro <viro@...iv.linux.org.uk>,
Benjamin LaHaise <bcrl@...ck.org>,
Theodore Ts'o <tytso@....edu>
Subject: [PATCH 19/33] aio: kill struct aio_ring_info
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 <koverstreet@...gle.com>
Cc: Zach Brown <zab@...hat.com>
Cc: Felipe Balbi <balbi@...com>
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
Cc: Mark Fasheh <mfasheh@...e.com>
Cc: Joel Becker <jlbec@...lplan.org>
Cc: Rusty Russell <rusty@...tcorp.com.au>
Cc: Jens Axboe <axboe@...nel.dk>
Cc: Asai Thambi S P <asamymuthupa@...ron.com>
Cc: Selvan Mani <smani@...ron.com>
Cc: Sam Bradshaw <sbradshaw@...ron.com>
Cc: Jeff Moyer <jmoyer@...hat.com>
Cc: Al Viro <viro@...iv.linux.org.uk>
Cc: Benjamin LaHaise <bcrl@...ck.org>
Cc: Theodore Ts'o <tytso@....edu>
Signed-off-by: Andrew Morton <akpm@...ux-foundation.org>
---
fs/aio.c | 156 ++++++++++++++++++++++++++++++---------------------------------
1 file changed, 75 insertions(+), 81 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index 95fcd08..0e283ad 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;
@@ -90,14 +78,30 @@ struct kioctx {
* 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 ring->nr - 1, which will be larger (see
+ * The real limit is nr_events - 1, which will be larger (see
* aio_setup_ring())
*/
unsigned max_reqs;
- struct aio_ring_info ring_info;
+ /* Size of ringbuffer, in units of struct io_event */
+ unsigned nr_events;
- spinlock_t completion_lock;
+ 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];
struct rcu_head rcu_head;
struct work_struct rcu_work;
@@ -129,26 +133,21 @@ __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, populate;
@@ -166,45 +165,44 @@ 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_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;
- 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,
- &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;
}
- 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;
}
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;
@@ -213,7 +211,7 @@ static int aio_setup_ring(struct kioctx *ctx)
ring->incompat_features = AIO_RING_INCOMPAT_FEATURES;
ring->header_length = sizeof(struct aio_ring);
kunmap_atomic(ring);
- flush_dcache_page(info->ring_pages[0]);
+ flush_dcache_page(ctx->ring_pages[0]);
return 0;
}
@@ -284,7 +282,6 @@ static void free_ioctx_rcu(struct rcu_head *head)
*/
static void free_ioctx(struct kioctx *ctx)
{
- struct aio_ring_info *info = &ctx->ring_info;
struct aio_ring *ring;
struct io_event res;
struct kiocb *req;
@@ -302,18 +299,18 @@ 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_events) - head;
atomic_sub(avail, &ctx->reqs_active);
head += avail;
- head %= info->nr;
+ head %= ctx->nr_events;
}
WARN_ON(atomic_read(&ctx->reqs_active) < 0);
@@ -372,7 +369,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
atomic_set(&ctx->dead, 0);
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);
@@ -396,7 +393,7 @@ 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_events);
return ctx;
out_cleanup:
@@ -491,7 +488,7 @@ 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;
if (!atomic_xchg(&ctx->dead, 1)) {
hlist_del_rcu(&ctx->list);
@@ -514,10 +511,10 @@ 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_events)
return NULL;
- if (atomic_inc_return(&ctx->reqs_active) > ctx->ring_info.nr - 1)
+ if (atomic_inc_return(&ctx->reqs_active) > ctx->nr_events - 1)
goto out_put;
req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO);
@@ -578,7 +575,6 @@ 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 *ev_page, *event;
unsigned long flags;
@@ -599,8 +595,6 @@ 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.
@@ -633,13 +627,13 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
*/
spin_lock_irqsave(&ctx->completion_lock, flags);
- tail = info->tail;
+ tail = ctx->tail;
pos = tail + AIO_EVENTS_OFFSET;
- if (++tail >= info->nr)
+ if (++tail >= ctx->nr_events)
tail = 0;
- ev_page = kmap_atomic(info->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
+ 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;
@@ -648,7 +642,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
event->res2 = res2;
kunmap_atomic(ev_page);
- flush_dcache_page(info->ring_pages[pos / AIO_EVENTS_PER_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,
@@ -659,12 +653,12 @@ 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 = kmap_atomic(info->ring_pages[0]);
+ ring = kmap_atomic(ctx->ring_pages[0]);
ring->tail = tail;
kunmap_atomic(ring);
- flush_dcache_page(info->ring_pages[0]);
+ flush_dcache_page(ctx->ring_pages[0]);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
@@ -704,29 +698,29 @@ EXPORT_SYMBOL(aio_complete);
static long aio_read_events_ring(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;
long ret = 0;
int 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_events);
- if (head == info->tail)
+ if (head == ctx->tail)
goto out;
while (ret < nr) {
- long avail = (head <= info->tail ? info->tail : info->nr) - head;
+ long avail = (head <= ctx->tail
+ ? ctx->tail : ctx->nr_events) - head;
struct io_event *ev;
struct page *page;
- if (head == info->tail)
+ if (head == ctx->tail)
break;
avail = min(avail, nr - ret);
@@ -734,7 +728,7 @@ static long aio_read_events_ring(struct kioctx *ctx,
((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);
@@ -748,19 +742,19 @@ static long aio_read_events_ring(struct kioctx *ctx,
ret += avail;
head += avail;
- head %= info->nr;
+ head %= ctx->nr_events;
}
- ring = kmap_atomic(info->ring_pages[0]);
+ ring = kmap_atomic(ctx->ring_pages[0]);
ring->head = head;
kunmap_atomic(ring);
- flush_dcache_page(info->ring_pages[0]);
+ flush_dcache_page(ctx->ring_pages[0]);
- pr_debug("%li h%u t%u\n", ret, head, info->tail);
+ pr_debug("%li h%u t%u\n", ret, head, ctx->tail);
atomic_sub(ret, &ctx->reqs_active);
out:
- mutex_unlock(&info->ring_lock);
+ mutex_unlock(&ctx->ring_lock);
return ret;
}
--
1.8.1.3
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists