The patch titled
Subject: mm, swap_slots: remove slot cache for freeing path
has been added to the -mm mm-unstable branch. Its filename is
mm-swap_slots-remove-slot-cache-for-freeing-path.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-swap_slots-remove-slot-cache-for-freeing-path.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Kairui Song <kasong@xxxxxxxxxxx>
Subject: mm, swap_slots: remove slot cache for freeing path
Date: Tue, 14 Jan 2025 01:57:32 +0800
The slot cache for freeing path is mostly for reducing the overhead of
si->lock. As we have basically eliminated the si->lock usage for freeing
path, it can be removed.
This helps simplify the code, and avoids swap entries from being hold in
cache upon freeing. The delayed freeing of entries have been causing
trouble for further optimizations for zswap [1] and in theory will also
cause more fragmentation, and extra overhead.
Test with build linux kernel showed both performance and fragmentation is
better without the cache:
tiem make -j96 / 768M memcg, 4K pages, 10G ZRAM, avg of 4 test run::
Before:
Sys time: 36047.78, Real time: 472.43
After: (-7.6% sys time, -7.3% real time)
Sys time: 33314.76, Real time: 437.67
time make -j96 / 1152M memcg, 64K mTHP, 10G ZRAM, avg of 4 test run:
Before:
Sys time: 46859.04, Real time: 562.63
hugepages-64kB/stats/swpout: 1783392
hugepages-64kB/stats/swpout_fallback: 240875
After: (-23.3% sys time, -21.3% real time)
Sys time: 35958.87, Real time: 442.69
hugepages-64kB/stats/swpout: 1866267
hugepages-64kB/stats/swpout_fallback: 158330
Sequential SWAP should be also slightly faster, tests didn't show a
measurable difference though, at least no regression:
Swapin 4G zero page on ZRAM (time in us):
Before (avg. 1923756)
1912391 1927023 1927957 1916527 1918263 1914284 1934753 1940813 1921791
After (avg. 1922290):
1919101 1925743 1916810 1917007 1923930 1935152 1917403 1923549 1921913
Link: https://lore.kernel.org/all/CAMgjq7ACohT_uerSz8E_994ZZCv709Zor+43hdmesW_59W1BWw@xxxxxxxxxxxxxx/[1]
Link: https://lkml.kernel.org/r/20250113175732.48099-14-ryncsn@xxxxxxxxx
Signed-off-by: Kairui Song <kasong@xxxxxxxxxxx>
Suggested-by: Chris Li <chrisl@xxxxxxxxxx>
Cc: Baoquan He <bhe@xxxxxxxxxx>
Cc: Barry Song <v-songbaohua@xxxxxxxx>
Cc: "Huang, Ying" <ying.huang@xxxxxxxxxxxxxxxxx>
Cc: Hugh Dickens <hughd@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Kalesh Singh <kaleshsingh@xxxxxxxxxx>
Cc: Nhat Pham <nphamcs@xxxxxxxxx>
Cc: Ryan Roberts <ryan.roberts@xxxxxxx>
Cc: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/swap_slots.h | 3 -
mm/swap_slots.c | 78 +++---------------------------
mm/swapfile.c | 89 +++++++++++++----------------------
3 files changed, 44 insertions(+), 126 deletions(-)
--- a/include/linux/swap_slots.h~mm-swap_slots-remove-slot-cache-for-freeing-path
+++ a/include/linux/swap_slots.h
@@ -16,15 +16,12 @@ struct swap_slots_cache {
swp_entry_t *slots;
int nr;
int cur;
- spinlock_t free_lock; /* protects slots_ret, n_ret */
- swp_entry_t *slots_ret;
int n_ret;
};
void disable_swap_slots_cache_lock(void);
void reenable_swap_slots_cache_unlock(void);
void enable_swap_slots_cache(void);
-void free_swap_slot(swp_entry_t entry);
extern bool swap_slot_cache_enabled;
--- a/mm/swapfile.c~mm-swap_slots-remove-slot-cache-for-freeing-path
+++ a/mm/swapfile.c
@@ -53,14 +53,15 @@
static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
unsigned char);
static void free_swap_count_continuations(struct swap_info_struct *);
-static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry,
- unsigned int nr_pages);
+static void swap_entry_range_free(struct swap_info_struct *si,
+ struct swap_cluster_info *ci,
+ swp_entry_t entry, unsigned int nr_pages);
static void swap_range_alloc(struct swap_info_struct *si,
unsigned int nr_entries);
static bool folio_swapcache_freeable(struct folio *folio);
static struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
unsigned long offset);
-static void unlock_cluster(struct swap_cluster_info *ci);
+static inline void unlock_cluster(struct swap_cluster_info *ci);
static DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
@@ -261,10 +262,9 @@ static int __try_to_reclaim_swap(struct
folio_ref_sub(folio, nr_pages);
folio_set_dirty(folio);
- /* Only sinple page folio can be backed by zswap */
- if (nr_pages == 1)
- zswap_invalidate(entry);
- swap_entry_range_free(si, entry, nr_pages);
+ ci = lock_cluster(si, offset);
+ swap_entry_range_free(si, ci, entry, nr_pages);
+ unlock_cluster(ci);
ret = nr_pages;
out_unlock:
folio_unlock(folio);
@@ -1128,8 +1128,10 @@ static void swap_range_free(struct swap_
* Use atomic clear_bit operations only on zeromap instead of non-atomic
* bitmap_clear to prevent adjacent bits corruption due to simultaneous writes.
*/
- for (i = 0; i < nr_entries; i++)
+ for (i = 0; i < nr_entries; i++) {
clear_bit(offset + i, si->zeromap);
+ zswap_invalidate(swp_entry(si->type, offset + i));
+ }
if (si->flags & SWP_BLKDEV)
swap_slot_free_notify =
@@ -1434,9 +1436,9 @@ static unsigned char __swap_entry_free(s
ci = lock_cluster(si, offset);
usage = __swap_entry_free_locked(si, offset, 1);
- unlock_cluster(ci);
if (!usage)
- free_swap_slot(entry);
+ swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1);
+ unlock_cluster(ci);
return usage;
}
@@ -1464,13 +1466,10 @@ static bool __swap_entries_free(struct s
}
for (i = 0; i < nr; i++)
WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE);
+ if (!has_cache)
+ swap_entry_range_free(si, ci, entry, nr);
unlock_cluster(ci);
- if (!has_cache) {
- for (i = 0; i < nr; i++)
- zswap_invalidate(swp_entry(si->type, offset + i));
- swap_entry_range_free(si, entry, nr);
- }
return has_cache;
fallback:
@@ -1490,15 +1489,13 @@ fallback:
* Drop the last HAS_CACHE flag of swap entries, caller have to
* ensure all entries belong to the same cgroup.
*/
-static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry,
- unsigned int nr_pages)
+static void swap_entry_range_free(struct swap_info_struct *si,
+ struct swap_cluster_info *ci,
+ swp_entry_t entry, unsigned int nr_pages)
{
unsigned long offset = swp_offset(entry);
unsigned char *map = si->swap_map + offset;
unsigned char *map_end = map + nr_pages;
- struct swap_cluster_info *ci;
-
- ci = lock_cluster(si, offset);
/* It should never free entries across different clusters */
VM_BUG_ON(ci != offset_to_cluster(si, offset + nr_pages - 1));
@@ -1518,7 +1515,6 @@ static void swap_entry_range_free(struct
free_cluster(si, ci);
else
partial_free_cluster(si, ci);
- unlock_cluster(ci);
}
static void cluster_swap_free_nr(struct swap_info_struct *si,
@@ -1526,28 +1522,13 @@ static void cluster_swap_free_nr(struct
unsigned char usage)
{
struct swap_cluster_info *ci;
- DECLARE_BITMAP(to_free, BITS_PER_LONG) = { 0 };
- int i, nr;
+ unsigned long end = offset + nr_pages;
ci = lock_cluster(si, offset);
- while (nr_pages) {
- nr = min(BITS_PER_LONG, nr_pages);
- for (i = 0; i < nr; i++) {
- if (!__swap_entry_free_locked(si, offset + i, usage))
- bitmap_set(to_free, i, 1);
- }
- if (!bitmap_empty(to_free, BITS_PER_LONG)) {
- unlock_cluster(ci);
- for_each_set_bit(i, to_free, BITS_PER_LONG)
- free_swap_slot(swp_entry(si->type, offset + i));
- if (nr == nr_pages)
- return;
- bitmap_clear(to_free, 0, BITS_PER_LONG);
- ci = lock_cluster(si, offset);
- }
- offset += nr;
- nr_pages -= nr;
- }
+ do {
+ if (!__swap_entry_free_locked(si, offset, usage))
+ swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1);
+ } while (++offset < end);
unlock_cluster(ci);
}
@@ -1588,18 +1569,12 @@ void put_swap_folio(struct folio *folio,
return;
ci = lock_cluster(si, offset);
- if (size > 1 && swap_is_has_cache(si, offset, size)) {
- unlock_cluster(ci);
- swap_entry_range_free(si, entry, size);
- return;
- }
- for (int i = 0; i < size; i++, entry.val++) {
- if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) {
- unlock_cluster(ci);
- free_swap_slot(entry);
- if (i == size - 1)
- return;
- lock_cluster(si, offset);
+ if (swap_is_has_cache(si, offset, size))
+ swap_entry_range_free(si, ci, entry, size);
+ else {
+ for (int i = 0; i < size; i++, entry.val++) {
+ if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE))
+ swap_entry_range_free(si, ci, entry, 1);
}
}
unlock_cluster(ci);
@@ -1608,6 +1583,7 @@ void put_swap_folio(struct folio *folio,
void swapcache_free_entries(swp_entry_t *entries, int n)
{
int i;
+ struct swap_cluster_info *ci;
struct swap_info_struct *si = NULL;
if (n <= 0)
@@ -1615,8 +1591,11 @@ void swapcache_free_entries(swp_entry_t
for (i = 0; i < n; ++i) {
si = _swap_info_get(entries[i]);
- if (si)
- swap_entry_range_free(si, entries[i], 1);
+ if (si) {
+ ci = lock_cluster(si, swp_offset(entries[i]));
+ swap_entry_range_free(si, ci, entries[i], 1);
+ unlock_cluster(ci);
+ }
}
}
--- a/mm/swap_slots.c~mm-swap_slots-remove-slot-cache-for-freeing-path
+++ a/mm/swap_slots.c
@@ -43,17 +43,15 @@ static DEFINE_MUTEX(swap_slots_cache_mut
/* Serialize swap slots cache enable/disable operations */
static DEFINE_MUTEX(swap_slots_cache_enable_mutex);
-static void __drain_swap_slots_cache(unsigned int type);
+static void __drain_swap_slots_cache(void);
#define use_swap_slot_cache (swap_slot_cache_active && swap_slot_cache_enabled)
-#define SLOTS_CACHE 0x1
-#define SLOTS_CACHE_RET 0x2
static void deactivate_swap_slots_cache(void)
{
mutex_lock(&swap_slots_cache_mutex);
swap_slot_cache_active = false;
- __drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET);
+ __drain_swap_slots_cache();
mutex_unlock(&swap_slots_cache_mutex);
}
@@ -72,7 +70,7 @@ void disable_swap_slots_cache_lock(void)
if (swap_slot_cache_initialized) {
/* serialize with cpu hotplug operations */
cpus_read_lock();
- __drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET);
+ __drain_swap_slots_cache();
cpus_read_unlock();
}
}
@@ -113,7 +111,7 @@ out:
static int alloc_swap_slot_cache(unsigned int cpu)
{
struct swap_slots_cache *cache;
- swp_entry_t *slots, *slots_ret;
+ swp_entry_t *slots;
/*
* Do allocation outside swap_slots_cache_mutex
@@ -125,28 +123,19 @@ static int alloc_swap_slot_cache(unsigne
if (!slots)
return -ENOMEM;
- slots_ret = kvcalloc(SWAP_SLOTS_CACHE_SIZE, sizeof(swp_entry_t),
- GFP_KERNEL);
- if (!slots_ret) {
- kvfree(slots);
- return -ENOMEM;
- }
-
mutex_lock(&swap_slots_cache_mutex);
cache = &per_cpu(swp_slots, cpu);
- if (cache->slots || cache->slots_ret) {
+ if (cache->slots) {
/* cache already allocated */
mutex_unlock(&swap_slots_cache_mutex);
kvfree(slots);
- kvfree(slots_ret);
return 0;
}
if (!cache->lock_initialized) {
mutex_init(&cache->alloc_lock);
- spin_lock_init(&cache->free_lock);
cache->lock_initialized = true;
}
cache->nr = 0;
@@ -160,19 +149,16 @@ static int alloc_swap_slot_cache(unsigne
*/
mb();
cache->slots = slots;
- cache->slots_ret = slots_ret;
mutex_unlock(&swap_slots_cache_mutex);
return 0;
}
-static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type,
- bool free_slots)
+static void drain_slots_cache_cpu(unsigned int cpu, bool free_slots)
{
struct swap_slots_cache *cache;
- swp_entry_t *slots = NULL;
cache = &per_cpu(swp_slots, cpu);
- if ((type & SLOTS_CACHE) && cache->slots) {
+ if (cache->slots) {
mutex_lock(&cache->alloc_lock);
swapcache_free_entries(cache->slots + cache->cur, cache->nr);
cache->cur = 0;
@@ -183,20 +169,9 @@ static void drain_slots_cache_cpu(unsign
}
mutex_unlock(&cache->alloc_lock);
}
- if ((type & SLOTS_CACHE_RET) && cache->slots_ret) {
- spin_lock_irq(&cache->free_lock);
- swapcache_free_entries(cache->slots_ret, cache->n_ret);
- cache->n_ret = 0;
- if (free_slots && cache->slots_ret) {
- slots = cache->slots_ret;
- cache->slots_ret = NULL;
- }
- spin_unlock_irq(&cache->free_lock);
- kvfree(slots);
- }
}
-static void __drain_swap_slots_cache(unsigned int type)
+static void __drain_swap_slots_cache(void)
{
unsigned int cpu;
@@ -224,13 +199,13 @@ static void __drain_swap_slots_cache(uns
* There are no slots on such cpu that need to be drained.
*/
for_each_online_cpu(cpu)
- drain_slots_cache_cpu(cpu, type, false);
+ drain_slots_cache_cpu(cpu, false);
}
static int free_slot_cache(unsigned int cpu)
{
mutex_lock(&swap_slots_cache_mutex);
- drain_slots_cache_cpu(cpu, SLOTS_CACHE | SLOTS_CACHE_RET, true);
+ drain_slots_cache_cpu(cpu, true);
mutex_unlock(&swap_slots_cache_mutex);
return 0;
}
@@ -269,39 +244,6 @@ static int refill_swap_slots_cache(struc
return cache->nr;
}
-void free_swap_slot(swp_entry_t entry)
-{
- struct swap_slots_cache *cache;
-
- /* Large folio swap slot is not covered. */
- zswap_invalidate(entry);
-
- cache = raw_cpu_ptr(&swp_slots);
- if (likely(use_swap_slot_cache && cache->slots_ret)) {
- spin_lock_irq(&cache->free_lock);
- /* Swap slots cache may be deactivated before acquiring lock */
- if (!use_swap_slot_cache || !cache->slots_ret) {
- spin_unlock_irq(&cache->free_lock);
- goto direct_free;
- }
- if (cache->n_ret >= SWAP_SLOTS_CACHE_SIZE) {
- /*
- * Return slots to global pool.
- * The current swap_map value is SWAP_HAS_CACHE.
- * Set it to 0 to indicate it is available for
- * allocation in global pool
- */
- swapcache_free_entries(cache->slots_ret, cache->n_ret);
- cache->n_ret = 0;
- }
- cache->slots_ret[cache->n_ret++] = entry;
- spin_unlock_irq(&cache->free_lock);
- } else {
-direct_free:
- swapcache_free_entries(&entry, 1);
- }
-}
-
swp_entry_t folio_alloc_swap(struct folio *folio)
{
swp_entry_t entry;
_
Patches currently in -mm which might be from kasong@xxxxxxxxxxx are
mm-memcontrol-avoid-duplicated-memcg-enable-check.patch
mm-swap_cgroup-remove-swap_cgroup_cmpxchg.patch
mm-swap_cgroup-remove-global-swap-cgroup-lock.patch
mm-swap_cgroup-decouple-swap-cgroup-recording-and-clearing.patch
mm-swap-minor-clean-up-for-swap-entry-allocation.patch
mm-swap-fold-swap_info_get_cont-in-the-only-caller.patch
mm-swap-remove-old-allocation-path-for-hdd.patch
mm-swap-use-cluster-lock-for-hdd.patch
mm-swap-clean-up-device-availability-check.patch
mm-swap-clean-up-plist-removal-and-adding.patch
mm-swap-hold-a-reference-during-scan-and-cleanup-flag-usage.patch
mm-swap-use-an-enum-to-define-all-cluster-flags-and-wrap-flags-changes.patch
mm-swap-reduce-contention-on-device-lock.patch
mm-swap-simplify-percpu-cluster-updating.patch
mm-swap-introduce-a-helper-for-retrieving-cluster-from-offset.patch
mm-swap-use-a-global-swap-cluster-for-non-rotation-devices.patch
mm-swap_slots-remove-slot-cache-for-freeing-path.patch
