patches/old/mm-swap-reduce-swap-cache-search-space.patch

From: Kairui Song <kasong@tencent.com>
Subject: mm/swap: reduce swap cache search space
Date: Wed, 22 May 2024 01:58:53 +0800

Currently we use one swap_address_space for every 64M chunk to reduce lock
contention, this is like having a set of smaller swap files inside one
swap device.  But when doing swap cache look up or insert, we are still
using the offset of the whole large swap device.  This is OK for
correctness, as the offset (key) is unique.

But Xarray is specially optimized for small indexes, it creates the radix
tree levels lazily to be just enough to fit the largest key stored in one
Xarray.  So we are wasting tree nodes unnecessarily.

For 64M chunk it should only take at most 3 levels to contain everything. 
But if we are using the offset from the whole swap device, the offset
(key) value will be way beyond 64M, and so will the tree level.

Optimize this by using a new helper swap_cache_index to get a swap entry's
unique offset in its own 64M swap_address_space.

I see a ~1% performance gain in benchmark and actual workload with high
memory pressure.

Test with `time memhog 128G` inside a 8G memcg using 128G swap (ramdisk
with SWP_SYNCHRONOUS_IO dropped, tested 3 times, results are stable.  The
test result is similar but the improvement is smaller if
SWP_SYNCHRONOUS_IO is enabled, as swap out path can never skip swap
cache):

Before:
6.07user 250.74system 4:17.26elapsed 99%CPU (0avgtext+0avgdata 8373376maxresident)k
0inputs+0outputs (55major+33555018minor)pagefaults 0swaps

After (1.8% faster):
6.08user 246.09system 4:12.58elapsed 99%CPU (0avgtext+0avgdata 8373248maxresident)k
0inputs+0outputs (54major+33555027minor)pagefaults 0swaps

Similar result with MySQL and sysbench using swap:
Before:
94055.61 qps

After (0.8% faster):
94834.91 qps

Radix tree slab usage is also very slightly lower.

Link: https://lkml.kernel.org/r/20240521175854.96038-12-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Anna Schumaker <anna@kernel.org>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: Chao Yu <chao@kernel.org>
Cc: Chris Li <chrisl@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Marc Dionne <marc.dionne@auristor.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: NeilBrown <neilb@suse.de>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Xiubo Li <xiubli@redhat.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/huge_memory.c |    2 +-
 mm/memcontrol.c  |    2 +-
 mm/mincore.c     |    2 +-
 mm/shmem.c       |    2 +-
 mm/swap.h        |   15 +++++++++++++++
 mm/swap_state.c  |   17 +++++++++--------
 mm/swapfile.c    |    6 +++---
 7 files changed, 31 insertions(+), 15 deletions(-)

--- a/mm/huge_memory.c~mm-swap-reduce-swap-cache-search-space
+++ a/mm/huge_memory.c
@@ -2838,7 +2838,7 @@ static void __split_huge_page(struct pag
 	split_page_memcg(head, order, new_order);
 
 	if (folio_test_anon(folio) && folio_test_swapcache(folio)) {
-		offset = swp_offset(folio->swap);
+		offset = swap_cache_index(folio->swap);
 		swap_cache = swap_address_space(folio->swap);
 		xa_lock(&swap_cache->i_pages);
 	}
--- a/mm/memcontrol.c~mm-swap-reduce-swap-cache-search-space
+++ a/mm/memcontrol.c
@@ -6146,7 +6146,7 @@ static struct page *mc_handle_swap_pte(s
 	 * Because swap_cache_get_folio() updates some statistics counter,
 	 * we call find_get_page() with swapper_space directly.
 	 */
-	page = find_get_page(swap_address_space(ent), swp_offset(ent));
+	page = find_get_page(swap_address_space(ent), swap_cache_index(ent));
 	entry->val = ent.val;
 
 	return page;
--- a/mm/mincore.c~mm-swap-reduce-swap-cache-search-space
+++ a/mm/mincore.c
@@ -139,7 +139,7 @@ static int mincore_pte_range(pmd_t *pmd,
 			} else {
 #ifdef CONFIG_SWAP
 				*vec = mincore_page(swap_address_space(entry),
-						    swp_offset(entry));
+						    swap_cache_index(entry));
 #else
 				WARN_ON(1);
 				*vec = 1;
--- a/mm/shmem.c~mm-swap-reduce-swap-cache-search-space
+++ a/mm/shmem.c
@@ -1742,7 +1742,7 @@ static int shmem_replace_folio(struct fo
 
 	old = *foliop;
 	entry = old->swap;
-	swap_index = swp_offset(entry);
+	swap_index = swap_cache_index(entry);
 	swap_mapping = swap_address_space(entry);
 
 	/*
--- a/mm/swapfile.c~mm-swap-reduce-swap-cache-search-space
+++ a/mm/swapfile.c
@@ -142,7 +142,7 @@ static int __try_to_reclaim_swap(struct
 	struct folio *folio;
 	int ret = 0;
 
-	folio = filemap_get_folio(swap_address_space(entry), offset);
+	folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry));
 	if (IS_ERR(folio))
 		return 0;
 	/*
@@ -2158,7 +2158,7 @@ retry:
 	       (i = find_next_to_unuse(si, i)) != 0) {
 
 		entry = swp_entry(type, i);
-		folio = filemap_get_folio(swap_address_space(entry), i);
+		folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry));
 		if (IS_ERR(folio))
 			continue;
 
@@ -3451,7 +3451,7 @@ EXPORT_SYMBOL_GPL(swapcache_mapping);
 
 pgoff_t __folio_swap_cache_index(struct folio *folio)
 {
-	return swp_offset(folio->swap);
+	return swap_cache_index(folio->swap);
 }
 EXPORT_SYMBOL_GPL(__folio_swap_cache_index);
 
--- a/mm/swap.h~mm-swap-reduce-swap-cache-search-space
+++ a/mm/swap.h
@@ -27,6 +27,7 @@ void __swap_writepage(struct folio *foli
 /* One swap address space for each 64M swap space */
 #define SWAP_ADDRESS_SPACE_SHIFT	14
 #define SWAP_ADDRESS_SPACE_PAGES	(1 << SWAP_ADDRESS_SPACE_SHIFT)
+#define SWAP_ADDRESS_SPACE_MASK		(SWAP_ADDRESS_SPACE_PAGES - 1)
 extern struct address_space *swapper_spaces[];
 #define swap_address_space(entry)			    \
 	(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
@@ -40,6 +41,15 @@ static inline loff_t swap_dev_pos(swp_en
 	return ((loff_t)swp_offset(entry)) << PAGE_SHIFT;
 }
 
+/*
+ * Return the swap cache index of the swap entry.
+ */
+static inline pgoff_t swap_cache_index(swp_entry_t entry)
+{
+	BUILD_BUG_ON((SWP_OFFSET_MASK | SWAP_ADDRESS_SPACE_MASK) != SWP_OFFSET_MASK);
+	return swp_offset(entry) & SWAP_ADDRESS_SPACE_MASK;
+}
+
 void show_swap_cache_info(void);
 bool add_to_swap(struct folio *folio);
 void *get_shadow_from_swap_cache(swp_entry_t entry);
@@ -86,6 +96,11 @@ static inline struct address_space *swap
 	return NULL;
 }
 
+static inline pgoff_t swap_cache_index(swp_entry_t entry)
+{
+	return 0;
+}
+
 static inline void show_swap_cache_info(void)
 {
 }
--- a/mm/swap_state.c~mm-swap-reduce-swap-cache-search-space
+++ a/mm/swap_state.c
@@ -72,7 +72,7 @@ void show_swap_cache_info(void)
 void *get_shadow_from_swap_cache(swp_entry_t entry)
 {
 	struct address_space *address_space = swap_address_space(entry);
-	pgoff_t idx = swp_offset(entry);
+	pgoff_t idx = swap_cache_index(entry);
 	void *shadow;
 
 	shadow = xa_load(&address_space->i_pages, idx);
@@ -89,7 +89,7 @@ int add_to_swap_cache(struct folio *foli
 			gfp_t gfp, void **shadowp)
 {
 	struct address_space *address_space = swap_address_space(entry);
-	pgoff_t idx = swp_offset(entry);
+	pgoff_t idx = swap_cache_index(entry);
 	XA_STATE_ORDER(xas, &address_space->i_pages, idx, folio_order(folio));
 	unsigned long i, nr = folio_nr_pages(folio);
 	void *old;
@@ -144,7 +144,7 @@ void __delete_from_swap_cache(struct fol
 	struct address_space *address_space = swap_address_space(entry);
 	int i;
 	long nr = folio_nr_pages(folio);
-	pgoff_t idx = swp_offset(entry);
+	pgoff_t idx = swap_cache_index(entry);
 	XA_STATE(xas, &address_space->i_pages, idx);
 
 	xas_set_update(&xas, workingset_update_node);
@@ -253,13 +253,14 @@ void clear_shadow_from_swap_cache(int ty
 
 	for (;;) {
 		swp_entry_t entry = swp_entry(type, curr);
+		unsigned long index = curr & SWAP_ADDRESS_SPACE_MASK;
 		struct address_space *address_space = swap_address_space(entry);
-		XA_STATE(xas, &address_space->i_pages, curr);
+		XA_STATE(xas, &address_space->i_pages, index);
 
 		xas_set_update(&xas, workingset_update_node);
 
 		xa_lock_irq(&address_space->i_pages);
-		xas_for_each(&xas, old, end) {
+		xas_for_each(&xas, old, min(index + (end - curr), SWAP_ADDRESS_SPACE_PAGES)) {
 			if (!xa_is_value(old))
 				continue;
 			xas_store(&xas, NULL);
@@ -350,7 +351,7 @@ struct folio *swap_cache_get_folio(swp_e
 {
 	struct folio *folio;
 
-	folio = filemap_get_folio(swap_address_space(entry), swp_offset(entry));
+	folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry));
 	if (!IS_ERR(folio)) {
 		bool vma_ra = swap_use_vma_readahead();
 		bool readahead;
@@ -420,7 +421,7 @@ struct folio *filemap_get_incore_folio(s
 	si = get_swap_device(swp);
 	if (!si)
 		return ERR_PTR(-ENOENT);
-	index = swp_offset(swp);
+	index = swap_cache_index(swp);
 	folio = filemap_get_folio(swap_address_space(swp), index);
 	put_swap_device(si);
 	return folio;
@@ -447,7 +448,7 @@ struct folio *__read_swap_cache_async(sw
 		 * that would confuse statistics.
 		 */
 		folio = filemap_get_folio(swap_address_space(entry),
-						swp_offset(entry));
+					  swap_cache_index(entry));
 		if (!IS_ERR(folio))
 			goto got_folio;
 
_