linux-kernel - [PATCH -mm -v3 6/6] mm, swap: Don't use VMA based swap readahead if HDD is used as swap

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

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20170725015151.19502-7-ying.huang@intel.com>
Date:   Tue, 25 Jul 2017 09:51:51 +0800
From:   "Huang, Ying" <ying.huang@...el.com>
To:     Andrew Morton <akpm@...ux-foundation.org>
Cc:     linux-mm@...ck.org, linux-kernel@...r.kernel.org,
        Huang Ying <ying.huang@...el.com>,
        Johannes Weiner <hannes@...xchg.org>,
        Minchan Kim <minchan@...nel.org>,
        Rik van Riel <riel@...hat.com>, Shaohua Li <shli@...nel.org>,
        Hugh Dickins <hughd@...gle.com>,
        Fengguang Wu <fengguang.wu@...el.com>,
        Tim Chen <tim.c.chen@...el.com>,
        Dave Hansen <dave.hansen@...el.com>
Subject: [PATCH -mm -v3 6/6] mm, swap: Don't use VMA based swap readahead if HDD is used as swap

From: Huang Ying <ying.huang@...el.com>

VMA based swap readahead will readahead the virtual pages that is
continuous in the virtual address space.  While the original swap
readahead will readahead the swap slots that is continuous in the swap
device.  Although VMA based swap readahead is more correct for the
swap slots to be readahead, it will trigger more small random
readings, which may cause the performance of HDD (hard disk) to
degrade heavily, and may finally exceed the benefit.

To avoid the issue, in this patch, if the HDD is used as swap, the VMA
based swap readahead will be disabled, and the original swap readahead
will be used instead.

Signed-off-by: "Huang, Ying" <ying.huang@...el.com>
Cc: Johannes Weiner <hannes@...xchg.org>
Cc: Minchan Kim <minchan@...nel.org>
Cc: Rik van Riel <riel@...hat.com>
Cc: Shaohua Li <shli@...nel.org>
Cc: Hugh Dickins <hughd@...gle.com>
Cc: Fengguang Wu <fengguang.wu@...el.com>
Cc: Tim Chen <tim.c.chen@...el.com>
Cc: Dave Hansen <dave.hansen@...el.com>
---
 include/linux/swap.h | 11 ++++++-----
 mm/swapfile.c        |  8 +++++++-
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 9e5cfb64b5e8..633bf6c5bac8 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -399,16 +399,17 @@ extern struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 					   struct vm_fault *vmf,
 					   struct vma_swap_readahead *swap_ra);
 
-static inline bool swap_use_vma_readahead(void)
-{
-	return READ_ONCE(swap_vma_readahead);
-}
-
 /* linux/mm/swapfile.c */
 extern atomic_long_t nr_swap_pages;
 extern long total_swap_pages;
+extern atomic_t nr_rotate_swap;
 extern bool has_usable_swap(void);
 
+static inline bool swap_use_vma_readahead(void)
+{
+	return READ_ONCE(swap_vma_readahead) && !atomic_read(&nr_rotate_swap);
+}
+
 /* Swap 50% full? Release swapcache more aggressively.. */
 static inline bool vm_swap_full(void)
 {
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6ba4aab2db0b..2685b9951cc1 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -96,6 +96,8 @@ static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait);
 /* Activity counter to indicate that a swapon or swapoff has occurred */
 static atomic_t proc_poll_event = ATOMIC_INIT(0);
 
+atomic_t nr_rotate_swap = ATOMIC_INIT(0);
+
 static inline unsigned char swap_count(unsigned char ent)
 {
 	return ent & ~SWAP_HAS_CACHE;	/* may include SWAP_HAS_CONT flag */
@@ -2387,6 +2389,9 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	if (p->flags & SWP_CONTINUED)
 		free_swap_count_continuations(p);
 
+	if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev)))
+		atomic_dec(&nr_rotate_swap);
+
 	mutex_lock(&swapon_mutex);
 	spin_lock(&swap_lock);
 	spin_lock(&p->lock);
@@ -2963,7 +2968,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 			cluster = per_cpu_ptr(p->percpu_cluster, cpu);
 			cluster_set_null(&cluster->index);
 		}
-	}
+	} else
+		atomic_inc(&nr_rotate_swap);
 
 	error = swap_cgroup_swapon(p->type, maxpages);
 	if (error)
-- 
2.13.2