From: Miaohe Lin <linmiaohe@huawei.com>
To: <akpm@linux-foundation.org>
Cc: <ying.huang@intel.com>, <dennis@kernel.org>,
<tim.c.chen@linux.intel.com>, <hughd@google.com>,
<hannes@cmpxchg.org>, <mhocko@suse.com>, <iamjoonsoo.kim@lge.com>,
<alexs@kernel.org>, <willy@infradead.org>, <minchan@kernel.org>,
<richard.weiyang@gmail.com>, <shy828301@gmail.com>,
<david@redhat.com>, <linux-kernel@vger.kernel.org>,
<linux-mm@kvack.org>, <linmiaohe@huawei.com>
Subject: [PATCH v5 1/4] mm/swapfile: use percpu_ref to serialize against concurrent swapoff
Date: Sun, 25 Apr 2021 17:54:16 +0800 [thread overview]
Message-ID: <20210425095419.3830298-2-linmiaohe@huawei.com> (raw)
In-Reply-To: <20210425095419.3830298-1-linmiaohe@huawei.com>
Using current get/put_swap_device() to guard against concurrent swapoff
for some swap ops, e.g. swap_readpage(), looks terrible because they
might take really long time. This patch adds the percpu_ref support to
serialize against concurrent swapoff(as suggested by Huang, Ying). Also
we remove the SWP_VALID flag because it's used together with RCU solution.
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
---
include/linux/swap.h | 5 +--
mm/swapfile.c | 79 +++++++++++++++++++++++++++-----------------
2 files changed, 52 insertions(+), 32 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 144727041e78..c9e7fea10b83 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -177,7 +177,6 @@ enum {
SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */
SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */
SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */
- SWP_VALID = (1 << 13), /* swap is valid to be operated on? */
/* add others here before... */
SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */
};
@@ -240,6 +239,7 @@ struct swap_cluster_list {
* The in-memory structure used to track swap areas.
*/
struct swap_info_struct {
+ struct percpu_ref users; /* indicate and keep swap device valid. */
unsigned long flags; /* SWP_USED etc: see above */
signed short prio; /* swap priority of this type */
struct plist_node list; /* entry in swap_active_head */
@@ -260,6 +260,7 @@ struct swap_info_struct {
struct block_device *bdev; /* swap device or bdev of swap file */
struct file *swap_file; /* seldom referenced */
unsigned int old_block_size; /* seldom referenced */
+ struct completion comp; /* seldom referenced */
#ifdef CONFIG_FRONTSWAP
unsigned long *frontswap_map; /* frontswap in-use, one bit per page */
atomic_t frontswap_pages; /* frontswap pages in-use counter */
@@ -511,7 +512,7 @@ sector_t swap_page_sector(struct page *page);
static inline void put_swap_device(struct swap_info_struct *si)
{
- rcu_read_unlock();
+ percpu_ref_put(&si->users);
}
#else /* CONFIG_SWAP */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 149e77454e3c..2aad85751991 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -39,6 +39,7 @@
#include <linux/export.h>
#include <linux/swap_slots.h>
#include <linux/sort.h>
+#include <linux/completion.h>
#include <asm/tlbflush.h>
#include <linux/swapops.h>
@@ -511,6 +512,14 @@ static void swap_discard_work(struct work_struct *work)
spin_unlock(&si->lock);
}
+static void swap_users_ref_free(struct percpu_ref *ref)
+{
+ struct swap_info_struct *si;
+
+ si = container_of(ref, struct swap_info_struct, users);
+ complete(&si->comp);
+}
+
static void alloc_cluster(struct swap_info_struct *si, unsigned long idx)
{
struct swap_cluster_info *ci = si->cluster_info;
@@ -1270,18 +1279,12 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p,
* via preventing the swap device from being swapoff, until
* put_swap_device() is called. Otherwise return NULL.
*
- * The entirety of the RCU read critical section must come before the
- * return from or after the call to synchronize_rcu() in
- * enable_swap_info() or swapoff(). So if "si->flags & SWP_VALID" is
- * true, the si->map, si->cluster_info, etc. must be valid in the
- * critical section.
- *
* Notice that swapoff or swapoff+swapon can still happen before the
- * rcu_read_lock() in get_swap_device() or after the rcu_read_unlock()
- * in put_swap_device() if there isn't any other way to prevent
- * swapoff, such as page lock, page table lock, etc. The caller must
- * be prepared for that. For example, the following situation is
- * possible.
+ * percpu_ref_tryget_live() in get_swap_device() or after the
+ * percpu_ref_put() in put_swap_device() if there isn't any other way
+ * to prevent swapoff, such as page lock, page table lock, etc. The
+ * caller must be prepared for that. For example, the following
+ * situation is possible.
*
* CPU1 CPU2
* do_swap_page()
@@ -1309,21 +1312,27 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry)
si = swp_swap_info(entry);
if (!si)
goto bad_nofile;
-
- rcu_read_lock();
- if (data_race(!(si->flags & SWP_VALID)))
- goto unlock_out;
+ if (!percpu_ref_tryget_live(&si->users))
+ goto out;
+ /*
+ * Guarantee the si->users are checked before accessing other
+ * fields of swap_info_struct.
+ *
+ * Paired with the spin_unlock() after setup_swap_info() in
+ * enable_swap_info().
+ */
+ smp_rmb();
offset = swp_offset(entry);
if (offset >= si->max)
- goto unlock_out;
+ goto put_out;
return si;
bad_nofile:
pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val);
out:
return NULL;
-unlock_out:
- rcu_read_unlock();
+put_out:
+ percpu_ref_put(&si->users);
return NULL;
}
@@ -2466,7 +2475,7 @@ static void setup_swap_info(struct swap_info_struct *p, int prio,
static void _enable_swap_info(struct swap_info_struct *p)
{
- p->flags |= SWP_WRITEOK | SWP_VALID;
+ p->flags |= SWP_WRITEOK;
atomic_long_add(p->pages, &nr_swap_pages);
total_swap_pages += p->pages;
@@ -2497,10 +2506,9 @@ static void enable_swap_info(struct swap_info_struct *p, int prio,
spin_unlock(&p->lock);
spin_unlock(&swap_lock);
/*
- * Guarantee swap_map, cluster_info, etc. fields are valid
- * between get/put_swap_device() if SWP_VALID bit is set
+ * Finished initializing swap device, now it's safe to reference it.
*/
- synchronize_rcu();
+ percpu_ref_resurrect(&p->users);
spin_lock(&swap_lock);
spin_lock(&p->lock);
_enable_swap_info(p);
@@ -2616,16 +2624,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
reenable_swap_slots_cache_unlock();
- spin_lock(&swap_lock);
- spin_lock(&p->lock);
- p->flags &= ~SWP_VALID; /* mark swap device as invalid */
- spin_unlock(&p->lock);
- spin_unlock(&swap_lock);
/*
- * wait for swap operations protected by get/put_swap_device()
- * to complete
+ * Wait for swap operations protected by get/put_swap_device()
+ * to complete.
+ *
+ * We need synchronize_rcu() here to protect the accessing to
+ * the swap cache data structure.
*/
+ percpu_ref_kill(&p->users);
synchronize_rcu();
+ wait_for_completion(&p->comp);
flush_work(&p->discard_work);
@@ -2857,6 +2865,12 @@ static struct swap_info_struct *alloc_swap_info(void)
if (!p)
return ERR_PTR(-ENOMEM);
+ if (percpu_ref_init(&p->users, swap_users_ref_free,
+ PERCPU_REF_INIT_DEAD, GFP_KERNEL)) {
+ kvfree(p);
+ return ERR_PTR(-ENOMEM);
+ }
+
spin_lock(&swap_lock);
for (type = 0; type < nr_swapfiles; type++) {
if (!(swap_info[type]->flags & SWP_USED))
@@ -2864,6 +2878,7 @@ static struct swap_info_struct *alloc_swap_info(void)
}
if (type >= MAX_SWAPFILES) {
spin_unlock(&swap_lock);
+ percpu_ref_exit(&p->users);
kvfree(p);
return ERR_PTR(-EPERM);
}
@@ -2891,9 +2906,13 @@ static struct swap_info_struct *alloc_swap_info(void)
plist_node_init(&p->avail_lists[i], 0);
p->flags = SWP_USED;
spin_unlock(&swap_lock);
- kvfree(defer);
+ if (defer) {
+ percpu_ref_exit(&defer->users);
+ kvfree(defer);
+ }
spin_lock_init(&p->lock);
spin_lock_init(&p->cont_lock);
+ init_completion(&p->comp);
return p;
}
--
2.23.0
next prev parent reply other threads:[~2021-04-25 9:54 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-25 9:54 [PATCH v5 0/4] close various race windows for swap Miaohe Lin
2021-04-25 9:54 ` Miaohe Lin [this message]
2021-04-25 9:54 ` [PATCH v5 2/4] swap: fix do_swap_page() race with swapoff Miaohe Lin
2021-04-25 9:54 ` [PATCH v5 3/4] mm/swap: remove confusing checking for non_swap_entry() in swap_ra_info() Miaohe Lin
2021-04-25 9:54 ` [PATCH v5 4/4] mm/shmem: fix shmem_swapin() race with swapoff Miaohe Lin
2021-04-26 0:56 ` Huang, Ying
2021-04-26 6:53 ` Yu Zhao
2021-04-26 7:05 ` Miaohe Lin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210425095419.3830298-2-linmiaohe@huawei.com \
--to=linmiaohe@huawei.com \
--cc=akpm@linux-foundation.org \
--cc=alexs@kernel.org \
--cc=david@redhat.com \
--cc=dennis@kernel.org \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=minchan@kernel.org \
--cc=richard.weiyang@gmail.com \
--cc=shy828301@gmail.com \
--cc=tim.c.chen@linux.intel.com \
--cc=willy@infradead.org \
--cc=ying.huang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).