mm/swap: split swap cache into 64MB trunks

The patch is to improve the scalability of the swap out/in via using
fine grained locks for the swap cache.  In current kernel, one address
space will be used for each swap device.  And in the common
configuration, the number of the swap device is very small (one is
typical).  This causes the heavy lock contention on the radix tree of
the address space if multiple tasks swap out/in concurrently.

But in fact, there is no dependency between pages in the swap cache.  So
that, we can split the one shared address space for each swap device
into several address spaces to reduce the lock contention.  In the
patch, the shared address space is split into 64MB trunks.  64MB is
chosen to balance the memory space usage and effect of lock contention
reduction.

The size of struct address_space on x86_64 architecture is 408B, so with
the patch, 6528B more memory will be used for every 1GB swap space on
x86_64 architecture.

One address space is still shared for the swap entries in the same 64M
trunks.  To avoid lock contention for the first round of swap space
allocation, the order of the swap clusters in the initial free clusters
list is changed.  The swap space distance between the consecutive swap
clusters in the free cluster list is at least 64M.  After the first
round of allocation, the swap clusters are expected to be freed
randomly, so the lock contention should be reduced effectively.

Link: http://lkml.kernel.org/r/735bab895e64c930581ffb0a05b661e01da82bc5.1484082593.git.tim.c.chen@linux.intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net> escreveu:
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 70 insertions, 20 deletions

diff --git a/mm/swap.c b/mm/swap.c
index 844baedd2429..aabf2e90fe32 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -971,12 +971,6 @@ EXPORT_SYMBOL(pagevec_lookup_tag);
 void __init swap_setup(void)
 {
 	unsigned long megs = totalram_pages >> (20 - PAGE_SHIFT);
-#ifdef CONFIG_SWAP
-	int i;
-
-	for (i = 0; i < MAX_SWAPFILES; i++)
-		spin_lock_init(&swapper_spaces[i].tree_lock);
-#endif
 
 	/* Use a smaller cluster for small-memory machines */
 	if (megs < 16)
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 35d7e0ee1c77..3863acd6189c 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -17,6 +17,7 @@
 #include <linux/blkdev.h>
 #include <linux/pagevec.h>
 #include <linux/migrate.h>
+#include <linux/vmalloc.h>
 
 #include <asm/pgtable.h>
 
@@ -32,15 +33,8 @@ static const struct address_space_operations swap_aops = {
 #endif
 };
 
-struct address_space swapper_spaces[MAX_SWAPFILES] = {
-	[0 ... MAX_SWAPFILES - 1] = {
-		.page_tree	= RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
-		.i_mmap_writable = ATOMIC_INIT(0),
-		.a_ops		= &swap_aops,
-		/* swap cache doesn't use writeback related tags */
-		.flags		= 1 << AS_NO_WRITEBACK_TAGS,
-	}
-};
+struct address_space *swapper_spaces[MAX_SWAPFILES];
+static unsigned int nr_swapper_spaces[MAX_SWAPFILES];
 
 #define INC_CACHE_INFO(x)	do { swap_cache_info.x++; } while (0)
 
@@ -53,11 +47,26 @@ static struct {
 
 unsigned long total_swapcache_pages(void)
 {
-	int i;
+	unsigned int i, j, nr;
 	unsigned long ret = 0;
+	struct address_space *spaces;
 
-	for (i = 0; i < MAX_SWAPFILES; i++)
-		ret += swapper_spaces[i].nrpages;
+	rcu_read_lock();
+	for (i = 0; i < MAX_SWAPFILES; i++) {
+		/*
+		 * The corresponding entries in nr_swapper_spaces and
+		 * swapper_spaces will be reused only after at least
+		 * one grace period.  So it is impossible for them
+		 * belongs to different usage.
+		 */
+		nr = nr_swapper_spaces[i];
+		spaces = rcu_dereference(swapper_spaces[i]);
+		if (!nr || !spaces)
+			continue;
+		for (j = 0; j < nr; j++)
+			ret += spaces[j].nrpages;
+	}
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -505,3 +514,38 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 skip:
 	return read_swap_cache_async(entry, gfp_mask, vma, addr);
 }
+
+int init_swap_address_space(unsigned int type, unsigned long nr_pages)
+{
+	struct address_space *spaces, *space;
+	unsigned int i, nr;
+
+	nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES);
+	spaces = vzalloc(sizeof(struct address_space) * nr);
+	if (!spaces)
+		return -ENOMEM;
+	for (i = 0; i < nr; i++) {
+		space = spaces + i;
+		INIT_RADIX_TREE(&space->page_tree, GFP_ATOMIC|__GFP_NOWARN);
+		atomic_set(&space->i_mmap_writable, 0);
+		space->a_ops = &swap_aops;
+		/* swap cache doesn't use writeback related tags */
+		mapping_set_no_writeback_tags(space);
+		spin_lock_init(&space->tree_lock);
+	}
+	nr_swapper_spaces[type] = nr;
+	rcu_assign_pointer(swapper_spaces[type], spaces);
+
+	return 0;
+}
+
+void exit_swap_address_space(unsigned int type)
+{
+	struct address_space *spaces;
+
+	spaces = swapper_spaces[type];
+	nr_swapper_spaces[type] = 0;
+	rcu_assign_pointer(swapper_spaces[type], NULL);
+	synchronize_rcu();
+	kvfree(spaces);
+}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index eb71b5d9430b..66e95eb73040 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2084,6 +2084,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	vfree(frontswap_map);
 	/* Destroy swap account information */
 	swap_cgroup_swapoff(p->type);
+	exit_swap_address_space(p->type);
 
 	inode = mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
@@ -2407,8 +2408,12 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
 	return maxpages;
 }
 
-#define SWAP_CLUSTER_COLS						\
+#define SWAP_CLUSTER_INFO_COLS						\
 	DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info))
+#define SWAP_CLUSTER_SPACE_COLS						\
+	DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER)
+#define SWAP_CLUSTER_COLS						\
+	max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS)
 
 static int setup_swap_map_and_extents(struct swap_info_struct *p,
 					union swap_header *swap_header,
@@ -2471,7 +2476,10 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p,
 		return nr_extents;
 
 
-	/* Reduce false cache line sharing between cluster_info */
+	/*
+	 * Reduce false cache line sharing between cluster_info and
+	 * sharing same address space.
+	 */
 	for (k = 0; k < SWAP_CLUSTER_COLS; k++) {
 		j = (k + col) % SWAP_CLUSTER_COLS;
 		for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) {
@@ -2661,6 +2669,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		}
 	}
 
+	error = init_swap_address_space(p->type, maxpages);
+	if (error)
+		goto bad_swap;
+
 	mutex_lock(&swapon_mutex);
 	prio = -1;
 	if (swap_flags & SWAP_FLAG_PREFER)