* [PATCH v4 01/13] mm, swap: minor clean up for swap entry allocation
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 02/13] mm, swap: fold swap_info_get_cont in the only caller Kairui Song
` (11 subsequent siblings)
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
Direct reclaim can skip the whole folio after reclaimed a set of
folio based slots. Also simplify the code for allocation, reduce
indention.
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
---
mm/swapfile.c | 59 +++++++++++++++++++++++++--------------------------
1 file changed, 29 insertions(+), 30 deletions(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b0a9071cfe1d..f8002f110104 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -604,23 +604,28 @@ static bool cluster_reclaim_range(struct swap_info_struct *si,
unsigned long start, unsigned long end)
{
unsigned char *map = si->swap_map;
- unsigned long offset;
+ unsigned long offset = start;
+ int nr_reclaim;
spin_unlock(&ci->lock);
spin_unlock(&si->lock);
- for (offset = start; offset < end; offset++) {
+ do {
switch (READ_ONCE(map[offset])) {
case 0:
- continue;
+ offset++;
+ break;
case SWAP_HAS_CACHE:
- if (__try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT) > 0)
- continue;
- goto out;
+ nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT);
+ if (nr_reclaim > 0)
+ offset += nr_reclaim;
+ else
+ goto out;
+ break;
default:
goto out;
}
- }
+ } while (offset < end);
out:
spin_lock(&si->lock);
spin_lock(&ci->lock);
@@ -838,35 +843,30 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
&found, order, usage);
frags++;
if (found)
- break;
+ goto done;
}
- if (!found) {
+ /*
+ * Nonfull clusters are moved to frag tail if we reached
+ * here, count them too, don't over scan the frag list.
+ */
+ while (frags < si->frag_cluster_nr[order]) {
+ ci = list_first_entry(&si->frag_clusters[order],
+ struct swap_cluster_info, list);
/*
- * Nonfull clusters are moved to frag tail if we reached
- * here, count them too, don't over scan the frag list.
+ * Rotate the frag list to iterate, they were all failing
+ * high order allocation or moved here due to per-CPU usage,
+ * this help keeping usable cluster ahead.
*/
- while (frags < si->frag_cluster_nr[order]) {
- ci = list_first_entry(&si->frag_clusters[order],
- struct swap_cluster_info, list);
- /*
- * Rotate the frag list to iterate, they were all failing
- * high order allocation or moved here due to per-CPU usage,
- * this help keeping usable cluster ahead.
- */
- list_move_tail(&ci->list, &si->frag_clusters[order]);
- offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
- &found, order, usage);
- frags++;
- if (found)
- break;
- }
+ list_move_tail(&ci->list, &si->frag_clusters[order]);
+ offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
+ &found, order, usage);
+ frags++;
+ if (found)
+ goto done;
}
}
- if (found)
- goto done;
-
if (!list_empty(&si->discard_clusters)) {
/*
* we don't have free cluster but have some clusters in
@@ -904,7 +904,6 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
goto done;
}
}
-
done:
cluster->next[order] = offset;
return found;
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* [PATCH v4 02/13] mm, swap: fold swap_info_get_cont in the only caller
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
2025-01-13 17:57 ` [PATCH v4 01/13] mm, swap: minor clean up for swap entry allocation Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 03/13] mm, swap: remove old allocation path for HDD Kairui Song
` (10 subsequent siblings)
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
The name of the function is confusing, and the code is much easier to
follow after folding, also rename the confusing naming "p" to more
meaningful "si".
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
---
mm/swapfile.c | 39 +++++++++++++++------------------------
1 file changed, 15 insertions(+), 24 deletions(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index f8002f110104..574059158627 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1375,22 +1375,6 @@ static struct swap_info_struct *_swap_info_get(swp_entry_t entry)
return NULL;
}
-static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry,
- struct swap_info_struct *q)
-{
- struct swap_info_struct *p;
-
- p = _swap_info_get(entry);
-
- if (p != q) {
- if (q != NULL)
- spin_unlock(&q->lock);
- if (p != NULL)
- spin_lock(&p->lock);
- }
- return p;
-}
-
static unsigned char __swap_entry_free_locked(struct swap_info_struct *si,
unsigned long offset,
unsigned char usage)
@@ -1687,14 +1671,14 @@ static int swp_entry_cmp(const void *ent1, const void *ent2)
void swapcache_free_entries(swp_entry_t *entries, int n)
{
- struct swap_info_struct *p, *prev;
+ struct swap_info_struct *si, *prev;
int i;
if (n <= 0)
return;
prev = NULL;
- p = NULL;
+ si = NULL;
/*
* Sort swap entries by swap device, so each lock is only taken once.
@@ -1704,13 +1688,20 @@ void swapcache_free_entries(swp_entry_t *entries, int n)
if (nr_swapfiles > 1)
sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL);
for (i = 0; i < n; ++i) {
- p = swap_info_get_cont(entries[i], prev);
- if (p)
- swap_entry_range_free(p, entries[i], 1);
- prev = p;
+ si = _swap_info_get(entries[i]);
+
+ if (si != prev) {
+ if (prev != NULL)
+ spin_unlock(&prev->lock);
+ if (si != NULL)
+ spin_lock(&si->lock);
+ }
+ if (si)
+ swap_entry_range_free(si, entries[i], 1);
+ prev = si;
}
- if (p)
- spin_unlock(&p->lock);
+ if (si)
+ spin_unlock(&si->lock);
}
int __swap_count(swp_entry_t entry)
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* [PATCH v4 03/13] mm, swap: remove old allocation path for HDD
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
2025-01-13 17:57 ` [PATCH v4 01/13] mm, swap: minor clean up for swap entry allocation Kairui Song
2025-01-13 17:57 ` [PATCH v4 02/13] mm, swap: fold swap_info_get_cont in the only caller Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 04/13] mm, swap: use cluster lock " Kairui Song
` (9 subsequent siblings)
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
We are currently using different swap allocation algorithm for HDD and
non-HDD. This leads to the existence of a different set of locks, and
the code path is heavily bloated, causing difficulties for further
optimization and maintenance.
This commit removes all HDD swap allocation and related dead code,
and uses the cluster allocation algorithm instead.
The performance may drop temporarily, but this should be negligible:
The main advantage of the legacy HDD allocation algorithm is that it
tends to use continuous slots, but swap device gets fragmented quickly
anyway, and the attempt to use continuous slots will fail easily.
This commit also enables mTHP swap on HDD, which is expected to be
beneficial, and following commits will adapt and optimize the cluster
allocator for HDD.
Suggested-by: Chris Li <chrisl@kernel.org>
Suggested-by: "Huang, Ying" <ying.huang@linux.alibaba.com>
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
---
include/linux/swap.h | 3 -
mm/swapfile.c | 235 ++-----------------------------------------
2 files changed, 9 insertions(+), 229 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 187715eec3cb..0c681aa5cb98 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -310,9 +310,6 @@ struct swap_info_struct {
unsigned int highest_bit; /* index of last free in swap_map */
unsigned int pages; /* total of usable pages of swap */
unsigned int inuse_pages; /* number of those currently in use */
- unsigned int cluster_next; /* likely index for next allocation */
- unsigned int cluster_nr; /* countdown to next cluster search */
- unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */
struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
struct rb_root swap_extent_root;/* root of the swap extent rbtree */
struct block_device *bdev; /* swap device or bdev of swap file */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 574059158627..fca58d43b836 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1001,49 +1001,6 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries);
}
-static void set_cluster_next(struct swap_info_struct *si, unsigned long next)
-{
- unsigned long prev;
-
- if (!(si->flags & SWP_SOLIDSTATE)) {
- si->cluster_next = next;
- return;
- }
-
- prev = this_cpu_read(*si->cluster_next_cpu);
- /*
- * Cross the swap address space size aligned trunk, choose
- * another trunk randomly to avoid lock contention on swap
- * address space if possible.
- */
- if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) !=
- (next >> SWAP_ADDRESS_SPACE_SHIFT)) {
- /* No free swap slots available */
- if (si->highest_bit <= si->lowest_bit)
- return;
- next = get_random_u32_inclusive(si->lowest_bit, si->highest_bit);
- next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES);
- next = max_t(unsigned int, next, si->lowest_bit);
- }
- this_cpu_write(*si->cluster_next_cpu, next);
-}
-
-static bool swap_offset_available_and_locked(struct swap_info_struct *si,
- unsigned long offset)
-{
- if (data_race(!si->swap_map[offset])) {
- spin_lock(&si->lock);
- return true;
- }
-
- if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) {
- spin_lock(&si->lock);
- return true;
- }
-
- return false;
-}
-
static int cluster_alloc_swap(struct swap_info_struct *si,
unsigned char usage, int nr,
swp_entry_t slots[], int order)
@@ -1071,13 +1028,7 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
unsigned char usage, int nr,
swp_entry_t slots[], int order)
{
- unsigned long offset;
- unsigned long scan_base;
- unsigned long last_in_cluster = 0;
- int latency_ration = LATENCY_LIMIT;
unsigned int nr_pages = 1 << order;
- int n_ret = 0;
- bool scanned_many = false;
/*
* We try to cluster swap pages by allocating them sequentially
@@ -1089,7 +1040,6 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
* But we do now try to find an empty cluster. -Andrea
* And we let swap pages go all over an SSD partition. Hugh
*/
-
if (order > 0) {
/*
* Should not even be attempting large allocations when huge
@@ -1109,158 +1059,7 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
return 0;
}
- if (si->cluster_info)
- return cluster_alloc_swap(si, usage, nr, slots, order);
-
- si->flags += SWP_SCANNING;
-
- /* For HDD, sequential access is more important. */
- scan_base = si->cluster_next;
- offset = scan_base;
-
- if (unlikely(!si->cluster_nr--)) {
- if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
- si->cluster_nr = SWAPFILE_CLUSTER - 1;
- goto checks;
- }
-
- spin_unlock(&si->lock);
-
- /*
- * If seek is expensive, start searching for new cluster from
- * start of partition, to minimize the span of allocated swap.
- */
- scan_base = offset = si->lowest_bit;
- last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
-
- /* Locate the first empty (unaligned) cluster */
- for (; last_in_cluster <= READ_ONCE(si->highest_bit); offset++) {
- if (si->swap_map[offset])
- last_in_cluster = offset + SWAPFILE_CLUSTER;
- else if (offset == last_in_cluster) {
- spin_lock(&si->lock);
- offset -= SWAPFILE_CLUSTER - 1;
- si->cluster_next = offset;
- si->cluster_nr = SWAPFILE_CLUSTER - 1;
- goto checks;
- }
- if (unlikely(--latency_ration < 0)) {
- cond_resched();
- latency_ration = LATENCY_LIMIT;
- }
- }
-
- offset = scan_base;
- spin_lock(&si->lock);
- si->cluster_nr = SWAPFILE_CLUSTER - 1;
- }
-
-checks:
- if (!(si->flags & SWP_WRITEOK))
- goto no_page;
- if (!si->highest_bit)
- goto no_page;
- if (offset > si->highest_bit)
- scan_base = offset = si->lowest_bit;
-
- /* reuse swap entry of cache-only swap if not busy. */
- if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
- int swap_was_freed;
- spin_unlock(&si->lock);
- swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT);
- spin_lock(&si->lock);
- /* entry was freed successfully, try to use this again */
- if (swap_was_freed > 0)
- goto checks;
- goto scan; /* check next one */
- }
-
- if (si->swap_map[offset]) {
- if (!n_ret)
- goto scan;
- else
- goto done;
- }
- memset(si->swap_map + offset, usage, nr_pages);
-
- swap_range_alloc(si, offset, nr_pages);
- slots[n_ret++] = swp_entry(si->type, offset);
-
- /* got enough slots or reach max slots? */
- if ((n_ret == nr) || (offset >= si->highest_bit))
- goto done;
-
- /* search for next available slot */
-
- /* time to take a break? */
- if (unlikely(--latency_ration < 0)) {
- if (n_ret)
- goto done;
- spin_unlock(&si->lock);
- cond_resched();
- spin_lock(&si->lock);
- latency_ration = LATENCY_LIMIT;
- }
-
- if (si->cluster_nr && !si->swap_map[++offset]) {
- /* non-ssd case, still more slots in cluster? */
- --si->cluster_nr;
- goto checks;
- }
-
- /*
- * Even if there's no free clusters available (fragmented),
- * try to scan a little more quickly with lock held unless we
- * have scanned too many slots already.
- */
- if (!scanned_many) {
- unsigned long scan_limit;
-
- if (offset < scan_base)
- scan_limit = scan_base;
- else
- scan_limit = si->highest_bit;
- for (; offset <= scan_limit && --latency_ration > 0;
- offset++) {
- if (!si->swap_map[offset])
- goto checks;
- }
- }
-
-done:
- if (order == 0)
- set_cluster_next(si, offset + 1);
- si->flags -= SWP_SCANNING;
- return n_ret;
-
-scan:
- VM_WARN_ON(order > 0);
- spin_unlock(&si->lock);
- while (++offset <= READ_ONCE(si->highest_bit)) {
- if (unlikely(--latency_ration < 0)) {
- cond_resched();
- latency_ration = LATENCY_LIMIT;
- scanned_many = true;
- }
- if (swap_offset_available_and_locked(si, offset))
- goto checks;
- }
- offset = si->lowest_bit;
- while (offset < scan_base) {
- if (unlikely(--latency_ration < 0)) {
- cond_resched();
- latency_ration = LATENCY_LIMIT;
- scanned_many = true;
- }
- if (swap_offset_available_and_locked(si, offset))
- goto checks;
- offset++;
- }
- spin_lock(&si->lock);
-
-no_page:
- si->flags -= SWP_SCANNING;
- return n_ret;
+ return cluster_alloc_swap(si, usage, nr, slots, order);
}
int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
@@ -2871,8 +2670,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
mutex_unlock(&swapon_mutex);
free_percpu(p->percpu_cluster);
p->percpu_cluster = NULL;
- free_percpu(p->cluster_next_cpu);
- p->cluster_next_cpu = NULL;
vfree(swap_map);
kvfree(zeromap);
kvfree(cluster_info);
@@ -3184,8 +2981,6 @@ static unsigned long read_swap_header(struct swap_info_struct *si,
}
si->lowest_bit = 1;
- si->cluster_next = 1;
- si->cluster_nr = 0;
maxpages = swapfile_maximum_size;
last_page = swap_header->info.last_page;
@@ -3271,7 +3066,6 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
unsigned long maxpages)
{
unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER);
- unsigned long col = si->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS;
struct swap_cluster_info *cluster_info;
unsigned long i, j, k, idx;
int cpu, err = -ENOMEM;
@@ -3283,15 +3077,6 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
for (i = 0; i < nr_clusters; i++)
spin_lock_init(&cluster_info[i].lock);
- si->cluster_next_cpu = alloc_percpu(unsigned int);
- if (!si->cluster_next_cpu)
- goto err_free;
-
- /* Random start position to help with wear leveling */
- for_each_possible_cpu(cpu)
- per_cpu(*si->cluster_next_cpu, cpu) =
- get_random_u32_inclusive(1, si->highest_bit);
-
si->percpu_cluster = alloc_percpu(struct percpu_cluster);
if (!si->percpu_cluster)
goto err_free;
@@ -3333,7 +3118,7 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
* sharing same address space.
*/
for (k = 0; k < SWAP_CLUSTER_COLS; k++) {
- j = (k + col) % SWAP_CLUSTER_COLS;
+ j = k % SWAP_CLUSTER_COLS;
for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) {
struct swap_cluster_info *ci;
idx = i * SWAP_CLUSTER_COLS + j;
@@ -3483,18 +3268,18 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
if (si->bdev && bdev_nonrot(si->bdev)) {
si->flags |= SWP_SOLIDSTATE;
-
- cluster_info = setup_clusters(si, swap_header, maxpages);
- if (IS_ERR(cluster_info)) {
- error = PTR_ERR(cluster_info);
- cluster_info = NULL;
- goto bad_swap_unlock_inode;
- }
} else {
atomic_inc(&nr_rotate_swap);
inced_nr_rotate_swap = true;
}
+ cluster_info = setup_clusters(si, swap_header, maxpages);
+ if (IS_ERR(cluster_info)) {
+ error = PTR_ERR(cluster_info);
+ cluster_info = NULL;
+ goto bad_swap_unlock_inode;
+ }
+
if ((swap_flags & SWAP_FLAG_DISCARD) &&
si->bdev && bdev_max_discard_sectors(si->bdev)) {
/*
@@ -3575,8 +3360,6 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
bad_swap:
free_percpu(si->percpu_cluster);
si->percpu_cluster = NULL;
- free_percpu(si->cluster_next_cpu);
- si->cluster_next_cpu = NULL;
inode = NULL;
destroy_swap_extents(si);
swap_cgroup_swapoff(si->type);
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* [PATCH v4 04/13] mm, swap: use cluster lock for HDD
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
` (2 preceding siblings ...)
2025-01-13 17:57 ` [PATCH v4 03/13] mm, swap: remove old allocation path for HDD Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 05/13] mm, swap: clean up device availability check Kairui Song
` (8 subsequent siblings)
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
Cluster lock (ci->lock) was introduced to reduce contention for certain
operations. Using cluster lock for HDD is not helpful as HDD have a poor
performance, so locking isn't the bottleneck. But having different set
of locks for HDD / non-HDD prevents further rework of device lock
(si->lock).
This commit just changed all lock_cluster_or_swap_info to lock_cluster,
which is a safe and straight conversion since cluster info is always
allocated now, also removed all cluster_info related checks.
Suggested-by: Chris Li <chrisl@kernel.org>
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
---
mm/swapfile.c | 109 ++++++++++++++++----------------------------------
1 file changed, 35 insertions(+), 74 deletions(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index fca58d43b836..83ebc24cc94b 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -58,10 +58,9 @@ static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry
static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
unsigned int nr_entries);
static bool folio_swapcache_freeable(struct folio *folio);
-static struct swap_cluster_info *lock_cluster_or_swap_info(
- struct swap_info_struct *si, unsigned long offset);
-static void unlock_cluster_or_swap_info(struct swap_info_struct *si,
- struct swap_cluster_info *ci);
+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 DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
@@ -222,9 +221,9 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si,
* swap_map is HAS_CACHE only, which means the slots have no page table
* reference or pending writeback, and can't be allocated to others.
*/
- ci = lock_cluster_or_swap_info(si, offset);
+ ci = lock_cluster(si, offset);
need_reclaim = swap_is_has_cache(si, offset, nr_pages);
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
if (!need_reclaim)
goto out_unlock;
@@ -404,45 +403,15 @@ static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si
{
struct swap_cluster_info *ci;
- ci = si->cluster_info;
- if (ci) {
- ci += offset / SWAPFILE_CLUSTER;
- spin_lock(&ci->lock);
- }
- return ci;
-}
-
-static inline void unlock_cluster(struct swap_cluster_info *ci)
-{
- if (ci)
- spin_unlock(&ci->lock);
-}
-
-/*
- * Determine the locking method in use for this device. Return
- * swap_cluster_info if SSD-style cluster-based locking is in place.
- */
-static inline struct swap_cluster_info *lock_cluster_or_swap_info(
- struct swap_info_struct *si, unsigned long offset)
-{
- struct swap_cluster_info *ci;
-
- /* Try to use fine-grained SSD-style locking if available: */
- ci = lock_cluster(si, offset);
- /* Otherwise, fall back to traditional, coarse locking: */
- if (!ci)
- spin_lock(&si->lock);
+ ci = &si->cluster_info[offset / SWAPFILE_CLUSTER];
+ spin_lock(&ci->lock);
return ci;
}
-static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si,
- struct swap_cluster_info *ci)
+static inline void unlock_cluster(struct swap_cluster_info *ci)
{
- if (ci)
- unlock_cluster(ci);
- else
- spin_unlock(&si->lock);
+ spin_unlock(&ci->lock);
}
/* Add a cluster to discard list and schedule it to do discard */
@@ -558,9 +527,6 @@ static void inc_cluster_info_page(struct swap_info_struct *si,
unsigned long idx = page_nr / SWAPFILE_CLUSTER;
struct swap_cluster_info *ci;
- if (!cluster_info)
- return;
-
ci = cluster_info + idx;
ci->count++;
@@ -576,9 +542,6 @@ static void inc_cluster_info_page(struct swap_info_struct *si,
static void dec_cluster_info_page(struct swap_info_struct *si,
struct swap_cluster_info *ci, int nr_pages)
{
- if (!si->cluster_info)
- return;
-
VM_BUG_ON(ci->count < nr_pages);
VM_BUG_ON(cluster_is_free(ci));
lockdep_assert_held(&si->lock);
@@ -940,7 +903,7 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
si->highest_bit = 0;
del_from_avail_list(si);
- if (si->cluster_info && vm_swap_full())
+ if (vm_swap_full())
schedule_work(&si->reclaim_work);
}
}
@@ -1007,8 +970,6 @@ static int cluster_alloc_swap(struct swap_info_struct *si,
{
int n_ret = 0;
- VM_BUG_ON(!si->cluster_info);
-
si->flags += SWP_SCANNING;
while (n_ret < nr) {
@@ -1052,10 +1013,10 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
}
/*
- * Swapfile is not block device or not using clusters so unable
+ * Swapfile is not block device so unable
* to allocate large entries.
*/
- if (!(si->flags & SWP_BLKDEV) || !si->cluster_info)
+ if (!(si->flags & SWP_BLKDEV))
return 0;
}
@@ -1295,9 +1256,9 @@ static unsigned char __swap_entry_free(struct swap_info_struct *si,
unsigned long offset = swp_offset(entry);
unsigned char usage;
- ci = lock_cluster_or_swap_info(si, offset);
+ ci = lock_cluster(si, offset);
usage = __swap_entry_free_locked(si, offset, 1);
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
if (!usage)
free_swap_slot(entry);
@@ -1320,14 +1281,14 @@ static bool __swap_entries_free(struct swap_info_struct *si,
if (nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER)
goto fallback;
- ci = lock_cluster_or_swap_info(si, offset);
+ ci = lock_cluster(si, offset);
if (!swap_is_last_map(si, offset, nr, &has_cache)) {
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
goto fallback;
}
for (i = 0; i < nr; i++)
WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE);
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
if (!has_cache) {
for (i = 0; i < nr; i++)
@@ -1383,7 +1344,7 @@ static void cluster_swap_free_nr(struct swap_info_struct *si,
DECLARE_BITMAP(to_free, BITS_PER_LONG) = { 0 };
int i, nr;
- ci = lock_cluster_or_swap_info(si, offset);
+ ci = lock_cluster(si, offset);
while (nr_pages) {
nr = min(BITS_PER_LONG, nr_pages);
for (i = 0; i < nr; i++) {
@@ -1391,18 +1352,18 @@ static void cluster_swap_free_nr(struct swap_info_struct *si,
bitmap_set(to_free, i, 1);
}
if (!bitmap_empty(to_free, BITS_PER_LONG)) {
- unlock_cluster_or_swap_info(si, ci);
+ 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_or_swap_info(si, offset);
+ ci = lock_cluster(si, offset);
}
offset += nr;
nr_pages -= nr;
}
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
}
/*
@@ -1441,9 +1402,9 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
if (!si)
return;
- ci = lock_cluster_or_swap_info(si, offset);
+ ci = lock_cluster(si, offset);
if (size > 1 && swap_is_has_cache(si, offset, size)) {
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
spin_lock(&si->lock);
swap_entry_range_free(si, entry, size);
spin_unlock(&si->lock);
@@ -1451,14 +1412,14 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
}
for (int i = 0; i < size; i++, entry.val++) {
if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) {
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
free_swap_slot(entry);
if (i == size - 1)
return;
- lock_cluster_or_swap_info(si, offset);
+ lock_cluster(si, offset);
}
}
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
}
static int swp_entry_cmp(const void *ent1, const void *ent2)
@@ -1522,9 +1483,9 @@ int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry)
struct swap_cluster_info *ci;
int count;
- ci = lock_cluster_or_swap_info(si, offset);
+ ci = lock_cluster(si, offset);
count = swap_count(si->swap_map[offset]);
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
return count;
}
@@ -1547,7 +1508,7 @@ int swp_swapcount(swp_entry_t entry)
offset = swp_offset(entry);
- ci = lock_cluster_or_swap_info(si, offset);
+ ci = lock_cluster(si, offset);
count = swap_count(si->swap_map[offset]);
if (!(count & COUNT_CONTINUED))
@@ -1570,7 +1531,7 @@ int swp_swapcount(swp_entry_t entry)
n *= (SWAP_CONT_MAX + 1);
} while (tmp_count & COUNT_CONTINUED);
out:
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
return count;
}
@@ -1585,8 +1546,8 @@ static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
int i;
bool ret = false;
- ci = lock_cluster_or_swap_info(si, offset);
- if (!ci || nr_pages == 1) {
+ ci = lock_cluster(si, offset);
+ if (nr_pages == 1) {
if (swap_count(map[roffset]))
ret = true;
goto unlock_out;
@@ -1598,7 +1559,7 @@ static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
}
}
unlock_out:
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
return ret;
}
@@ -3428,7 +3389,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr)
offset = swp_offset(entry);
VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);
VM_WARN_ON(usage == 1 && nr > 1);
- ci = lock_cluster_or_swap_info(si, offset);
+ ci = lock_cluster(si, offset);
err = 0;
for (i = 0; i < nr; i++) {
@@ -3483,7 +3444,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr)
}
unlock_out:
- unlock_cluster_or_swap_info(si, ci);
+ unlock_cluster(ci);
return err;
}
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* [PATCH v4 05/13] mm, swap: clean up device availability check
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
` (3 preceding siblings ...)
2025-01-13 17:57 ` [PATCH v4 04/13] mm, swap: use cluster lock " Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 06/13] mm, swap: clean up plist removal and adding Kairui Song
` (7 subsequent siblings)
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
Remove highest_bit and lowest_bit. After the HDD allocation path
has been removed, the only purpose of these two fields is to determine
whether the device is full or not, which can instead be determined
by checking the inuse_pages.
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
---
fs/btrfs/inode.c | 1 -
fs/f2fs/data.c | 1 -
fs/iomap/swapfile.c | 1 -
include/linux/swap.h | 2 --
mm/page_io.c | 1 -
mm/swapfile.c | 38 ++++++++------------------------------
6 files changed, 8 insertions(+), 36 deletions(-)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 27b2fe7f735d..3b99b1e19371 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10110,7 +10110,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
*span = bsi.highest_ppage - bsi.lowest_ppage + 1;
sis->max = bsi.nr_pages;
sis->pages = bsi.nr_pages - 1;
- sis->highest_bit = bsi.nr_pages - 1;
return bsi.nr_extents;
}
#else
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index a2478c2afb3a..a9eddd782dbc 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -4043,7 +4043,6 @@ static int check_swap_activate(struct swap_info_struct *sis,
cur_lblock = 1; /* force Empty message */
sis->max = cur_lblock;
sis->pages = cur_lblock - 1;
- sis->highest_bit = cur_lblock - 1;
out:
if (not_aligned)
f2fs_warn(sbi, "Swapfile (%u) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(%lu * N)",
diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c
index 5fc0ac36dee3..b90d0eda9e51 100644
--- a/fs/iomap/swapfile.c
+++ b/fs/iomap/swapfile.c
@@ -189,7 +189,6 @@ int iomap_swapfile_activate(struct swap_info_struct *sis,
*pagespan = 1 + isi.highest_ppage - isi.lowest_ppage;
sis->max = isi.nr_pages;
sis->pages = isi.nr_pages - 1;
- sis->highest_bit = isi.nr_pages - 1;
return isi.nr_extents;
}
EXPORT_SYMBOL_GPL(iomap_swapfile_activate);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 0c681aa5cb98..0c222017b5c6 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -306,8 +306,6 @@ struct swap_info_struct {
struct list_head frag_clusters[SWAP_NR_ORDERS];
/* list of cluster that are fragmented or contented */
unsigned int frag_cluster_nr[SWAP_NR_ORDERS];
- unsigned int lowest_bit; /* index of first free in swap_map */
- unsigned int highest_bit; /* index of last free in swap_map */
unsigned int pages; /* total of usable pages of swap */
unsigned int inuse_pages; /* number of those currently in use */
struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
diff --git a/mm/page_io.c b/mm/page_io.c
index 4b4ea8e49cf6..9b983de351f9 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -163,7 +163,6 @@ int generic_swapfile_activate(struct swap_info_struct *sis,
page_no = 1; /* force Empty message */
sis->max = page_no;
sis->pages = page_no - 1;
- sis->highest_bit = page_no - 1;
out:
return ret;
bad_bmap:
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 83ebc24cc94b..2686032d3510 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -55,7 +55,7 @@ static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
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_range_alloc(struct swap_info_struct *si, unsigned long offset,
+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,
@@ -650,7 +650,7 @@ static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster
}
memset(si->swap_map + start, usage, nr_pages);
- swap_range_alloc(si, start, nr_pages);
+ swap_range_alloc(si, nr_pages);
ci->count += nr_pages;
if (ci->count == SWAPFILE_CLUSTER) {
@@ -888,19 +888,11 @@ static void del_from_avail_list(struct swap_info_struct *si)
spin_unlock(&swap_avail_lock);
}
-static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
+static void swap_range_alloc(struct swap_info_struct *si,
unsigned int nr_entries)
{
- unsigned int end = offset + nr_entries - 1;
-
- if (offset == si->lowest_bit)
- si->lowest_bit += nr_entries;
- if (end == si->highest_bit)
- WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries);
WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries);
if (si->inuse_pages == si->pages) {
- si->lowest_bit = si->max;
- si->highest_bit = 0;
del_from_avail_list(si);
if (vm_swap_full())
@@ -933,15 +925,8 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
for (i = 0; i < nr_entries; i++)
clear_bit(offset + i, si->zeromap);
- if (offset < si->lowest_bit)
- si->lowest_bit = offset;
- if (end > si->highest_bit) {
- bool was_full = !si->highest_bit;
-
- WRITE_ONCE(si->highest_bit, end);
- if (was_full && (si->flags & SWP_WRITEOK))
- add_to_avail_list(si);
- }
+ if (si->inuse_pages == si->pages)
+ add_to_avail_list(si);
if (si->flags & SWP_BLKDEV)
swap_slot_free_notify =
si->bdev->bd_disk->fops->swap_slot_free_notify;
@@ -1051,15 +1036,12 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]);
spin_unlock(&swap_avail_lock);
spin_lock(&si->lock);
- if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) {
+ if ((si->inuse_pages == si->pages) || !(si->flags & SWP_WRITEOK)) {
spin_lock(&swap_avail_lock);
if (plist_node_empty(&si->avail_lists[node])) {
spin_unlock(&si->lock);
goto nextsi;
}
- WARN(!si->highest_bit,
- "swap_info %d in list but !highest_bit\n",
- si->type);
WARN(!(si->flags & SWP_WRITEOK),
"swap_info %d in list but !SWP_WRITEOK\n",
si->type);
@@ -2441,8 +2423,8 @@ static void _enable_swap_info(struct swap_info_struct *si)
*/
plist_add(&si->list, &swap_active_head);
- /* add to available list iff swap device is not full */
- if (si->highest_bit)
+ /* add to available list if swap device is not full */
+ if (si->inuse_pages < si->pages)
add_to_avail_list(si);
}
@@ -2606,7 +2588,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
drain_mmlist();
/* wait for anyone still in scan_swap_map_slots */
- p->highest_bit = 0; /* cuts scans short */
while (p->flags >= SWP_SCANNING) {
spin_unlock(&p->lock);
spin_unlock(&swap_lock);
@@ -2941,8 +2922,6 @@ static unsigned long read_swap_header(struct swap_info_struct *si,
return 0;
}
- si->lowest_bit = 1;
-
maxpages = swapfile_maximum_size;
last_page = swap_header->info.last_page;
if (!last_page) {
@@ -2959,7 +2938,6 @@ static unsigned long read_swap_header(struct swap_info_struct *si,
if ((unsigned int)maxpages == 0)
maxpages = UINT_MAX;
}
- si->highest_bit = maxpages - 1;
if (!maxpages)
return 0;
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* [PATCH v4 06/13] mm, swap: clean up plist removal and adding
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
` (4 preceding siblings ...)
2025-01-13 17:57 ` [PATCH v4 05/13] mm, swap: clean up device availability check Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 07/13] mm, swap: hold a reference during scan and cleanup flag usage Kairui Song
` (6 subsequent siblings)
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
When the swap device is full (inuse_pages == pages), it should be
removed from the allocation available plist. If any slot is freed,
the swap device should be added back to the plist. Additionally,
during swapon or swapoff, the swap device is forcefully added
or removed.
Currently, the condition (inuse_pages == pages) is checked after
every counter update, then remove or add the device accordingly.
This is serialized by si->lock.
This commit decouples it from the protection of si->lock and reworked
plist removal and adding, making it possible to get rid of the hard
dependency on si->lock in allocation path in later commits.
To achieve this, simply using another lock is not an optimal approach,
as the overhead is observable for a hot counter, and may cause complex
locking issues. Thus, this commit manages to make it a lock-free
atomic operation, by embedding the plist state into the second highest
bit of the atomic counter.
Simply making the counter an atomic will not work, if the update
and plist status check are not performed atomically, we may miss an
addition or removal. With the embedded info we can update the counter
and check the plist status with single atomic operations, and avoid
any extra overheads:
If the counter is full (inuse_pages == pages) and the off-list bit
is unset, we attempt to remove it from the plist. If the counter is
not full (inuse_pages != pages) and the off-list bit is set, we
attempt to add it to the plist. Removing, adding and bit update
is serialized with a lock, which is a cold path. Ordinary counter
updates will be lock-free.
Signed-off-by: Kairui Song <kasong@tencent.com>
---
include/linux/swap.h | 2 +-
mm/swapfile.c | 186 +++++++++++++++++++++++++++++++------------
2 files changed, 138 insertions(+), 50 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 0c222017b5c6..e1eeea6307cd 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -307,7 +307,7 @@ struct swap_info_struct {
/* list of cluster that are fragmented or contented */
unsigned int frag_cluster_nr[SWAP_NR_ORDERS];
unsigned int pages; /* total of usable pages of swap */
- unsigned int inuse_pages; /* number of those currently in use */
+ atomic_long_t inuse_pages; /* number of those currently in use */
struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
struct rb_root swap_extent_root;/* root of the swap extent rbtree */
struct block_device *bdev; /* swap device or bdev of swap file */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2686032d3510..91faf2073006 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -128,6 +128,26 @@ static inline unsigned char swap_count(unsigned char ent)
return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */
}
+/*
+ * Use the second highest bit of inuse_pages counter as the indicator
+ * if one swap device is on the available plist, so the atomic can
+ * still be updated arithmetically while having special data embedded.
+ *
+ * inuse_pages counter is the only thing indicating if a device should
+ * be on avail_lists or not (except swapon / swapoff). By embedding the
+ * off-list bit in the atomic counter, updates no longer need any lock
+ * to check the list status.
+ *
+ * This bit will be set if the device is not on the plist and not
+ * usable, will be cleared if the device is on the plist.
+ */
+#define SWAP_USAGE_OFFLIST_BIT (1UL << (BITS_PER_TYPE(atomic_t) - 2))
+#define SWAP_USAGE_COUNTER_MASK (~SWAP_USAGE_OFFLIST_BIT)
+static long swap_usage_in_pages(struct swap_info_struct *si)
+{
+ return atomic_long_read(&si->inuse_pages) & SWAP_USAGE_COUNTER_MASK;
+}
+
/* Reclaim the swap entry anyway if possible */
#define TTRS_ANYWAY 0x1
/*
@@ -717,7 +737,7 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
int nr_reclaim;
if (force)
- to_scan = si->inuse_pages / SWAPFILE_CLUSTER;
+ to_scan = swap_usage_in_pages(si) / SWAPFILE_CLUSTER;
while (!list_empty(&si->full_clusters)) {
ci = list_first_entry(&si->full_clusters, struct swap_cluster_info, list);
@@ -872,42 +892,128 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
return found;
}
-static void __del_from_avail_list(struct swap_info_struct *si)
+/* SWAP_USAGE_OFFLIST_BIT can only be set by this helper. */
+static void del_from_avail_list(struct swap_info_struct *si, bool swapoff)
{
int nid;
+ unsigned long pages;
+
+ spin_lock(&swap_avail_lock);
+
+ if (swapoff) {
+ /*
+ * Forcefully remove it. Clear the SWP_WRITEOK flags for
+ * swapoff here so it's synchronized by both si->lock and
+ * swap_avail_lock, to ensure the result can be seen by
+ * add_to_avail_list.
+ */
+ lockdep_assert_held(&si->lock);
+ si->flags &= ~SWP_WRITEOK;
+ atomic_long_or(SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages);
+ } else {
+ /*
+ * If not called by swapoff, take it off-list only if it's
+ * full and SWAP_USAGE_OFFLIST_BIT is not set (strictly
+ * si->inuse_pages == pages), any concurrent slot freeing,
+ * or device already removed from plist by someone else
+ * will make this return false.
+ */
+ pages = si->pages;
+ if (!atomic_long_try_cmpxchg(&si->inuse_pages, &pages,
+ pages | SWAP_USAGE_OFFLIST_BIT))
+ goto skip;
+ }
- assert_spin_locked(&si->lock);
for_each_node(nid)
plist_del(&si->avail_lists[nid], &swap_avail_heads[nid]);
+
+skip:
+ spin_unlock(&swap_avail_lock);
}
-static void del_from_avail_list(struct swap_info_struct *si)
+/* SWAP_USAGE_OFFLIST_BIT can only be cleared by this helper. */
+static void add_to_avail_list(struct swap_info_struct *si, bool swapon)
{
+ int nid;
+ long val;
+ unsigned long pages;
+
spin_lock(&swap_avail_lock);
- __del_from_avail_list(si);
+
+ /* Corresponding to SWP_WRITEOK clearing in del_from_avail_list */
+ if (swapon) {
+ lockdep_assert_held(&si->lock);
+ si->flags |= SWP_WRITEOK;
+ } else {
+ if (!(READ_ONCE(si->flags) & SWP_WRITEOK))
+ goto skip;
+ }
+
+ if (!(atomic_long_read(&si->inuse_pages) & SWAP_USAGE_OFFLIST_BIT))
+ goto skip;
+
+ val = atomic_long_fetch_and_relaxed(~SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages);
+
+ /*
+ * When device is full and device is on the plist, only one updater will
+ * see (inuse_pages == si->pages) and will call del_from_avail_list. If
+ * that updater happen to be here, just skip adding.
+ */
+ pages = si->pages;
+ if (val == pages) {
+ /* Just like the cmpxchg in del_from_avail_list */
+ if (atomic_long_try_cmpxchg(&si->inuse_pages, &pages,
+ pages | SWAP_USAGE_OFFLIST_BIT))
+ goto skip;
+ }
+
+ for_each_node(nid)
+ plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]);
+
+skip:
spin_unlock(&swap_avail_lock);
}
-static void swap_range_alloc(struct swap_info_struct *si,
- unsigned int nr_entries)
+/*
+ * swap_usage_add / swap_usage_sub of each slot are serialized by ci->lock
+ * within each cluster, so the total contribution to the global counter should
+ * always be positive and cannot exceed the total number of usable slots.
+ */
+static bool swap_usage_add(struct swap_info_struct *si, unsigned int nr_entries)
{
- WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries);
- if (si->inuse_pages == si->pages) {
- del_from_avail_list(si);
+ long val = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages);
- if (vm_swap_full())
- schedule_work(&si->reclaim_work);
+ /*
+ * If device is full, and SWAP_USAGE_OFFLIST_BIT is not set,
+ * remove it from the plist.
+ */
+ if (unlikely(val == si->pages)) {
+ del_from_avail_list(si, false);
+ return true;
}
+
+ return false;
}
-static void add_to_avail_list(struct swap_info_struct *si)
+static void swap_usage_sub(struct swap_info_struct *si, unsigned int nr_entries)
{
- int nid;
+ long val = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages);
- spin_lock(&swap_avail_lock);
- for_each_node(nid)
- plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]);
- spin_unlock(&swap_avail_lock);
+ /*
+ * If device is not full, and SWAP_USAGE_OFFLIST_BIT is set,
+ * remove it from the plist.
+ */
+ if (unlikely(val & SWAP_USAGE_OFFLIST_BIT))
+ add_to_avail_list(si, false);
+}
+
+static void swap_range_alloc(struct swap_info_struct *si,
+ unsigned int nr_entries)
+{
+ if (swap_usage_add(si, nr_entries)) {
+ if (vm_swap_full())
+ schedule_work(&si->reclaim_work);
+ }
}
static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
@@ -925,8 +1031,6 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
for (i = 0; i < nr_entries; i++)
clear_bit(offset + i, si->zeromap);
- if (si->inuse_pages == si->pages)
- add_to_avail_list(si);
if (si->flags & SWP_BLKDEV)
swap_slot_free_notify =
si->bdev->bd_disk->fops->swap_slot_free_notify;
@@ -946,7 +1050,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
*/
smp_wmb();
atomic_long_add(nr_entries, &nr_swap_pages);
- WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries);
+ swap_usage_sub(si, nr_entries);
}
static int cluster_alloc_swap(struct swap_info_struct *si,
@@ -1036,19 +1140,6 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]);
spin_unlock(&swap_avail_lock);
spin_lock(&si->lock);
- if ((si->inuse_pages == si->pages) || !(si->flags & SWP_WRITEOK)) {
- spin_lock(&swap_avail_lock);
- if (plist_node_empty(&si->avail_lists[node])) {
- spin_unlock(&si->lock);
- goto nextsi;
- }
- WARN(!(si->flags & SWP_WRITEOK),
- "swap_info %d in list but !SWP_WRITEOK\n",
- si->type);
- __del_from_avail_list(si);
- spin_unlock(&si->lock);
- goto nextsi;
- }
n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
n_goal, swp_entries, order);
spin_unlock(&si->lock);
@@ -1057,7 +1148,6 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
cond_resched();
spin_lock(&swap_avail_lock);
-nextsi:
/*
* if we got here, it's likely that si was almost full before,
* and since scan_swap_map_slots() can drop the si->lock,
@@ -1789,7 +1879,7 @@ unsigned int count_swap_pages(int type, int free)
if (sis->flags & SWP_WRITEOK) {
n = sis->pages;
if (free)
- n -= sis->inuse_pages;
+ n -= swap_usage_in_pages(sis);
}
spin_unlock(&sis->lock);
}
@@ -2124,7 +2214,7 @@ static int try_to_unuse(unsigned int type)
swp_entry_t entry;
unsigned int i;
- if (!READ_ONCE(si->inuse_pages))
+ if (!swap_usage_in_pages(si))
goto success;
retry:
@@ -2137,7 +2227,7 @@ static int try_to_unuse(unsigned int type)
spin_lock(&mmlist_lock);
p = &init_mm.mmlist;
- while (READ_ONCE(si->inuse_pages) &&
+ while (swap_usage_in_pages(si) &&
!signal_pending(current) &&
(p = p->next) != &init_mm.mmlist) {
@@ -2165,7 +2255,7 @@ static int try_to_unuse(unsigned int type)
mmput(prev_mm);
i = 0;
- while (READ_ONCE(si->inuse_pages) &&
+ while (swap_usage_in_pages(si) &&
!signal_pending(current) &&
(i = find_next_to_unuse(si, i)) != 0) {
@@ -2200,7 +2290,7 @@ static int try_to_unuse(unsigned int type)
* folio_alloc_swap(), temporarily hiding that swap. It's easy
* and robust (though cpu-intensive) just to keep retrying.
*/
- if (READ_ONCE(si->inuse_pages)) {
+ if (swap_usage_in_pages(si)) {
if (!signal_pending(current))
goto retry;
return -EINTR;
@@ -2227,7 +2317,7 @@ static void drain_mmlist(void)
unsigned int type;
for (type = 0; type < nr_swapfiles; type++)
- if (swap_info[type]->inuse_pages)
+ if (swap_usage_in_pages(swap_info[type]))
return;
spin_lock(&mmlist_lock);
list_for_each_safe(p, next, &init_mm.mmlist)
@@ -2406,7 +2496,6 @@ static void setup_swap_info(struct swap_info_struct *si, int prio,
static void _enable_swap_info(struct swap_info_struct *si)
{
- si->flags |= SWP_WRITEOK;
atomic_long_add(si->pages, &nr_swap_pages);
total_swap_pages += si->pages;
@@ -2423,9 +2512,8 @@ static void _enable_swap_info(struct swap_info_struct *si)
*/
plist_add(&si->list, &swap_active_head);
- /* add to available list if swap device is not full */
- if (si->inuse_pages < si->pages)
- add_to_avail_list(si);
+ /* Add back to available list */
+ add_to_avail_list(si, true);
}
static void enable_swap_info(struct swap_info_struct *si, int prio,
@@ -2523,7 +2611,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
goto out_dput;
}
spin_lock(&p->lock);
- del_from_avail_list(p);
+ del_from_avail_list(p, true);
if (p->prio < 0) {
struct swap_info_struct *si = p;
int nid;
@@ -2541,7 +2629,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
plist_del(&p->list, &swap_active_head);
atomic_long_sub(p->pages, &nr_swap_pages);
total_swap_pages -= p->pages;
- p->flags &= ~SWP_WRITEOK;
spin_unlock(&p->lock);
spin_unlock(&swap_lock);
@@ -2721,7 +2808,7 @@ static int swap_show(struct seq_file *swap, void *v)
}
bytes = K(si->pages);
- inuse = K(READ_ONCE(si->inuse_pages));
+ inuse = K(swap_usage_in_pages(si));
file = si->swap_file;
len = seq_file_path(swap, file, " \t\n\\");
@@ -2838,6 +2925,7 @@ static struct swap_info_struct *alloc_swap_info(void)
}
spin_lock_init(&p->lock);
spin_lock_init(&p->cont_lock);
+ atomic_long_set(&p->inuse_pages, SWAP_USAGE_OFFLIST_BIT);
init_completion(&p->comp);
return p;
@@ -3335,7 +3423,7 @@ void si_swapinfo(struct sysinfo *val)
struct swap_info_struct *si = swap_info[type];
if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK))
- nr_to_be_unused += READ_ONCE(si->inuse_pages);
+ nr_to_be_unused += swap_usage_in_pages(si);
}
val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused;
val->totalswap = total_swap_pages + nr_to_be_unused;
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* [PATCH v4 07/13] mm, swap: hold a reference during scan and cleanup flag usage
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
` (5 preceding siblings ...)
2025-01-13 17:57 ` [PATCH v4 06/13] mm, swap: clean up plist removal and adding Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 08/13] mm, swap: use an enum to define all cluster flags and wrap flags changes Kairui Song
` (5 subsequent siblings)
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
The flag SWP_SCANNING was used as an indicator of whether a device
is being scanned for allocation, and prevents swapoff. Combined with
SWP_WRITEOK, they work as a set of barriers for a clean swapoff:
1. Swapoff clears SWP_WRITEOK, allocation requests will see
~SWP_WRITEOK and abort as it's serialized by si->lock.
2. Swapoff unuses all allocated entries.
3. Swapoff waits for SWP_SCANNING flag to be cleared, so ongoing
allocations will stop, preventing UAF.
4. Now swapoff can free everything safely.
This will make the allocation path have a hard dependency on
si->lock. Allocation always have to acquire si->lock first for
setting SWP_SCANNING and checking SWP_WRITEOK.
This commit removes this flag, and just uses the existing per-CPU
refcount instead to prevent UAF in step 3, which serves well for
such usage without dependency on si->lock, and scales very well too.
Just hold a reference during the whole scan and allocation process.
Swapoff will kill and wait for the counter.
And for preventing any allocation from happening after step 1 so the
unuse in step 2 can ensure all slots are free, swapoff will acquire
the ci->lock of each cluster one by one to ensure all allocations
see ~SWP_WRITEOK and abort.
This way these dependences on si->lock are gone. And worth noting we
can't kill the refcount as the first step for swapoff as the unuse
process have to acquire the refcount.
Signed-off-by: Kairui Song <kasong@tencent.com>
---
include/linux/swap.h | 1 -
mm/swapfile.c | 90 ++++++++++++++++++++++++++++----------------
2 files changed, 57 insertions(+), 34 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index e1eeea6307cd..02120f1005d5 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -219,7 +219,6 @@ enum {
SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */
SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */
/* add others here before... */
- SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */
};
#define SWAP_CLUSTER_MAX 32UL
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 91faf2073006..3898576f947a 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -658,6 +658,8 @@ static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster
{
unsigned int nr_pages = 1 << order;
+ lockdep_assert_held(&ci->lock);
+
if (!(si->flags & SWP_WRITEOK))
return false;
@@ -1059,8 +1061,6 @@ static int cluster_alloc_swap(struct swap_info_struct *si,
{
int n_ret = 0;
- si->flags += SWP_SCANNING;
-
while (n_ret < nr) {
unsigned long offset = cluster_alloc_swap_entry(si, order, usage);
@@ -1069,8 +1069,6 @@ static int cluster_alloc_swap(struct swap_info_struct *si,
slots[n_ret++] = swp_entry(si->type, offset);
}
- si->flags -= SWP_SCANNING;
-
return n_ret;
}
@@ -1112,6 +1110,22 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
return cluster_alloc_swap(si, usage, nr, slots, order);
}
+static bool get_swap_device_info(struct swap_info_struct *si)
+{
+ if (!percpu_ref_tryget_live(&si->users))
+ return false;
+ /*
+ * Guarantee the si->users are checked before accessing other
+ * fields of swap_info_struct, and si->flags (SWP_WRITEOK) is
+ * up to dated.
+ *
+ * Paired with the spin_unlock() after setup_swap_info() in
+ * enable_swap_info(), and smp_wmb() in swapoff.
+ */
+ smp_rmb();
+ return true;
+}
+
int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
{
int order = swap_entry_order(entry_order);
@@ -1139,13 +1153,16 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
/* requeue si to after same-priority siblings */
plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]);
spin_unlock(&swap_avail_lock);
- spin_lock(&si->lock);
- n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
- n_goal, swp_entries, order);
- spin_unlock(&si->lock);
- if (n_ret || size > 1)
- goto check_out;
- cond_resched();
+ if (get_swap_device_info(si)) {
+ spin_lock(&si->lock);
+ n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
+ n_goal, swp_entries, order);
+ spin_unlock(&si->lock);
+ put_swap_device(si);
+ if (n_ret || size > 1)
+ goto check_out;
+ cond_resched();
+ }
spin_lock(&swap_avail_lock);
/*
@@ -1296,16 +1313,8 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry)
si = swp_swap_info(entry);
if (!si)
goto bad_nofile;
- if (!percpu_ref_tryget_live(&si->users))
+ if (!get_swap_device_info(si))
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 put_out;
@@ -1785,10 +1794,13 @@ swp_entry_t get_swap_page_of_type(int type)
goto fail;
/* This is called for allocating swap entry, not cache */
- spin_lock(&si->lock);
- if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0))
- atomic_long_dec(&nr_swap_pages);
- spin_unlock(&si->lock);
+ if (get_swap_device_info(si)) {
+ spin_lock(&si->lock);
+ if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0))
+ atomic_long_dec(&nr_swap_pages);
+ spin_unlock(&si->lock);
+ put_swap_device(si);
+ }
fail:
return entry;
}
@@ -2562,6 +2574,25 @@ bool has_usable_swap(void)
return ret;
}
+/*
+ * Called after clearing SWP_WRITEOK, ensures cluster_alloc_range
+ * see the updated flags, so there will be no more allocations.
+ */
+static void wait_for_allocation(struct swap_info_struct *si)
+{
+ unsigned long offset;
+ unsigned long end = ALIGN(si->max, SWAPFILE_CLUSTER);
+ struct swap_cluster_info *ci;
+
+ BUG_ON(si->flags & SWP_WRITEOK);
+
+ for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) {
+ ci = lock_cluster(si, offset);
+ unlock_cluster(ci);
+ offset += SWAPFILE_CLUSTER;
+ }
+}
+
SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
{
struct swap_info_struct *p = NULL;
@@ -2632,6 +2663,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
spin_unlock(&p->lock);
spin_unlock(&swap_lock);
+ wait_for_allocation(p);
+
disable_swap_slots_cache_lock();
set_current_oom_origin();
@@ -2674,15 +2707,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
spin_lock(&p->lock);
drain_mmlist();
- /* wait for anyone still in scan_swap_map_slots */
- while (p->flags >= SWP_SCANNING) {
- spin_unlock(&p->lock);
- spin_unlock(&swap_lock);
- schedule_timeout_uninterruptible(1);
- spin_lock(&swap_lock);
- spin_lock(&p->lock);
- }
-
swap_file = p->swap_file;
p->swap_file = NULL;
p->max = 0;
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* [PATCH v4 08/13] mm, swap: use an enum to define all cluster flags and wrap flags changes
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
` (6 preceding siblings ...)
2025-01-13 17:57 ` [PATCH v4 07/13] mm, swap: hold a reference during scan and cleanup flag usage Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 09/13] mm, swap: reduce contention on device lock Kairui Song
` (4 subsequent siblings)
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
Currently, we are only using flags to indicate which list the cluster
is on. Using one bit for each list type might be a waste, as the list
type grows, we will consume too many bits. Additionally, the current
mixed usage of '&' and '==' is a bit confusing.
Make it clean by using an enum to define all possible cluster
statuses. Only an off-list cluster will have the NONE (0) flag.
And use a wrapper to annotate and sanitize all flag settings
and list movements.
Suggested-by: Chris Li <chrisl@kernel.org>
Signed-off-by: Kairui Song <kasong@tencent.com>
---
include/linux/swap.h | 17 +++++++---
mm/swapfile.c | 76 +++++++++++++++++++++++---------------------
2 files changed, 53 insertions(+), 40 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 02120f1005d5..339d7f0192ff 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -257,10 +257,19 @@ struct swap_cluster_info {
u8 order;
struct list_head list;
};
-#define CLUSTER_FLAG_FREE 1 /* This cluster is free */
-#define CLUSTER_FLAG_NONFULL 2 /* This cluster is on nonfull list */
-#define CLUSTER_FLAG_FRAG 4 /* This cluster is on nonfull list */
-#define CLUSTER_FLAG_FULL 8 /* This cluster is on full list */
+
+/* All on-list cluster must have a non-zero flag. */
+enum swap_cluster_flags {
+ CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */
+ CLUSTER_FLAG_FREE,
+ CLUSTER_FLAG_NONFULL,
+ CLUSTER_FLAG_FRAG,
+ /* Clusters with flags above are allocatable */
+ CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG,
+ CLUSTER_FLAG_FULL,
+ CLUSTER_FLAG_DISCARD,
+ CLUSTER_FLAG_MAX,
+};
/*
* The first page in the swap file is the swap header, which is always marked
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 3898576f947a..b754c9e16c3b 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -403,7 +403,7 @@ static void discard_swap_cluster(struct swap_info_struct *si,
static inline bool cluster_is_free(struct swap_cluster_info *info)
{
- return info->flags & CLUSTER_FLAG_FREE;
+ return info->flags == CLUSTER_FLAG_FREE;
}
static inline unsigned int cluster_index(struct swap_info_struct *si,
@@ -434,6 +434,28 @@ static inline void unlock_cluster(struct swap_cluster_info *ci)
spin_unlock(&ci->lock);
}
+static void move_cluster(struct swap_info_struct *si,
+ struct swap_cluster_info *ci, struct list_head *list,
+ enum swap_cluster_flags new_flags)
+{
+ VM_WARN_ON(ci->flags == new_flags);
+
+ BUILD_BUG_ON(1 << sizeof(ci->flags) * BITS_PER_BYTE < CLUSTER_FLAG_MAX);
+
+ if (ci->flags == CLUSTER_FLAG_NONE) {
+ list_add_tail(&ci->list, list);
+ } else {
+ if (ci->flags == CLUSTER_FLAG_FRAG) {
+ VM_WARN_ON(!si->frag_cluster_nr[ci->order]);
+ si->frag_cluster_nr[ci->order]--;
+ }
+ list_move_tail(&ci->list, list);
+ }
+ ci->flags = new_flags;
+ if (new_flags == CLUSTER_FLAG_FRAG)
+ si->frag_cluster_nr[ci->order]++;
+}
+
/* Add a cluster to discard list and schedule it to do discard */
static void swap_cluster_schedule_discard(struct swap_info_struct *si,
struct swap_cluster_info *ci)
@@ -447,10 +469,8 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si,
*/
memset(si->swap_map + idx * SWAPFILE_CLUSTER,
SWAP_MAP_BAD, SWAPFILE_CLUSTER);
-
- VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE);
- list_move_tail(&ci->list, &si->discard_clusters);
- ci->flags = 0;
+ VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE);
+ move_cluster(si, ci, &si->discard_clusters, CLUSTER_FLAG_DISCARD);
schedule_work(&si->discard_work);
}
@@ -458,12 +478,7 @@ static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info
{
lockdep_assert_held(&si->lock);
lockdep_assert_held(&ci->lock);
-
- if (ci->flags)
- list_move_tail(&ci->list, &si->free_clusters);
- else
- list_add_tail(&ci->list, &si->free_clusters);
- ci->flags = CLUSTER_FLAG_FREE;
+ move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE);
ci->order = 0;
}
@@ -479,6 +494,8 @@ static void swap_do_scheduled_discard(struct swap_info_struct *si)
while (!list_empty(&si->discard_clusters)) {
ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list);
list_del(&ci->list);
+ /* Must clear flag when taking a cluster off-list */
+ ci->flags = CLUSTER_FLAG_NONE;
idx = cluster_index(si, ci);
spin_unlock(&si->lock);
@@ -519,9 +536,6 @@ static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *
lockdep_assert_held(&si->lock);
lockdep_assert_held(&ci->lock);
- if (ci->flags & CLUSTER_FLAG_FRAG)
- si->frag_cluster_nr[ci->order]--;
-
/*
* If the swap is discardable, prepare discard the cluster
* instead of free it immediately. The cluster will be freed
@@ -573,13 +587,9 @@ static void dec_cluster_info_page(struct swap_info_struct *si,
return;
}
- if (!(ci->flags & CLUSTER_FLAG_NONFULL)) {
- VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE);
- if (ci->flags & CLUSTER_FLAG_FRAG)
- si->frag_cluster_nr[ci->order]--;
- list_move_tail(&ci->list, &si->nonfull_clusters[ci->order]);
- ci->flags = CLUSTER_FLAG_NONFULL;
- }
+ if (ci->flags != CLUSTER_FLAG_NONFULL)
+ move_cluster(si, ci, &si->nonfull_clusters[ci->order],
+ CLUSTER_FLAG_NONFULL);
}
static bool cluster_reclaim_range(struct swap_info_struct *si,
@@ -663,11 +673,13 @@ static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster
if (!(si->flags & SWP_WRITEOK))
return false;
+ VM_BUG_ON(ci->flags == CLUSTER_FLAG_NONE);
+ VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE);
+
if (cluster_is_free(ci)) {
- if (nr_pages < SWAPFILE_CLUSTER) {
- list_move_tail(&ci->list, &si->nonfull_clusters[order]);
- ci->flags = CLUSTER_FLAG_NONFULL;
- }
+ if (nr_pages < SWAPFILE_CLUSTER)
+ move_cluster(si, ci, &si->nonfull_clusters[order],
+ CLUSTER_FLAG_NONFULL);
ci->order = order;
}
@@ -675,14 +687,8 @@ static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster
swap_range_alloc(si, nr_pages);
ci->count += nr_pages;
- if (ci->count == SWAPFILE_CLUSTER) {
- VM_BUG_ON(!(ci->flags &
- (CLUSTER_FLAG_FREE | CLUSTER_FLAG_NONFULL | CLUSTER_FLAG_FRAG)));
- if (ci->flags & CLUSTER_FLAG_FRAG)
- si->frag_cluster_nr[ci->order]--;
- list_move_tail(&ci->list, &si->full_clusters);
- ci->flags = CLUSTER_FLAG_FULL;
- }
+ if (ci->count == SWAPFILE_CLUSTER)
+ move_cluster(si, ci, &si->full_clusters, CLUSTER_FLAG_FULL);
return true;
}
@@ -821,9 +827,7 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
while (!list_empty(&si->nonfull_clusters[order])) {
ci = list_first_entry(&si->nonfull_clusters[order],
struct swap_cluster_info, list);
- list_move_tail(&ci->list, &si->frag_clusters[order]);
- ci->flags = CLUSTER_FLAG_FRAG;
- si->frag_cluster_nr[order]++;
+ move_cluster(si, ci, &si->frag_clusters[order], CLUSTER_FLAG_FRAG);
offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
&found, order, usage);
frags++;
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* [PATCH v4 09/13] mm, swap: reduce contention on device lock
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
` (7 preceding siblings ...)
2025-01-13 17:57 ` [PATCH v4 08/13] mm, swap: use an enum to define all cluster flags and wrap flags changes Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 10/13] mm, swap: simplify percpu cluster updating Kairui Song
` (3 subsequent siblings)
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
Currently, swap locking is mainly composed of two locks: the cluster
lock (ci->lock) and the device lock (si->lock).
The cluster lock is much more fine-grained, so it is best to use
ci->lock instead of si->lock as much as possible.
We have cleaned up other hard dependencies on si->lock. Following the
new cluster allocator design, most operations don't need to touch
si->lock at all. In practice, we only need to take si->lock when
moving clusters between lists.
To achieve this, this commit reworks the locking pattern of all
si->lock and ci->lock users, eliminates all usage of ci->lock inside
si->lock, and introduces a new design to avoid touching si->lock
unless needed.
For minimal contention and easier understanding of the system, two
ideas are introduced with the corresponding helpers: isolation and
relocation.
- Clusters will be `isolated` from the list when iterating the list
to search for an allocatable cluster.
This ensures other CPUs won't walk into the same cluster easily,
and it releases si->lock after acquiring ci->lock, providing the
only place that handles the inversion of two locks, and avoids
contention.
Iterating the cluster list almost always moves the cluster
(free -> nonfull, nonfull -> frag, frag -> frag tail), but it
doesn't know where the cluster should be moved to until scanning
is done. So keeping the cluster off-list is a good option with
low overhead.
The off-list time window of a cluster is also minimal. In the worst
case, one CPU will return the cluster after scanning the 512 entries
on it, which we used to busy wait with a spin lock.
This is done with the new helper `isolate_lock_cluster`.
- Clusters will be `relocated` after allocation or freeing, according
to their usage count and status.
Allocations no longer hold si->lock now, and may drop ci->lock for
reclaim, so the cluster could be moved to any location while no lock
is held. Besides, isolation clears all flags when it takes the
cluster off the list (the flags must be in sync with the list status,
so cluster users don't need to touch si->lock for checking its list
status). So the cluster has to be relocated to the right list
according to its usage after allocation or freeing.
Relocation is optional, if the cluster flags indicate it's already
on the right list, it will skip touching the list or si->lock.
This is done with `relocate_cluster` after allocation or with
`[partial_]free_cluster` after freeing.
This handled usage of all kinds of clusters in a clean way.
Scanning and allocation by iterating the cluster list is handled by
"isolate - <scan / allocate> - relocate".
Scanning and allocation of per-CPU clusters will only involve
"<scan / allocate> - relocate", as it knows which cluster to lock
and use.
Freeing will only involve "relocate".
Each CPU will keep using its per-CPU cluster until the 512 entries
are all consumed. Freeing also has to free 512 entries to trigger
cluster movement in the best case, so si->lock is rarely touched.
Testing with building the Linux kernel with defconfig showed huge
improvement:
tiem make -j96 / 768M memcg, 4K pages, 10G ZRAM, on Intel 8255C:
Before:
Sys time: 73578.30, Real time: 864.05
After: (-50.7% sys time, -44.8% real time)
Sys time: 36227.49, Real time: 476.66
time make -j96 / 1152M memcg, 64K mTHP, 10G ZRAM, on Intel 8255C:
(avg of 4 test run)
Before:
Sys time: 74044.85, Real time: 846.51
hugepages-64kB/stats/swpout: 1735216
hugepages-64kB/stats/swpout_fallback: 430333
After: (-40.4% sys time, -37.1% real time)
Sys time: 44160.56, Real time: 532.07
hugepages-64kB/stats/swpout: 1786288
hugepages-64kB/stats/swpout_fallback: 243384
time make -j32 / 512M memcg, 4K pages, 5G ZRAM, on AMD 7K62:
Before:
Sys time: 8098.21, Real time: 401.3
After: (-22.6% sys time, -12.8% real time )
Sys time: 6265.02, Real time: 349.83
The allocation success rate also slightly improved as we sanitized the
usage of clusters with new defined helpers, previously dropping
si->lock or ci->lock during scan will cause cluster order shuffle.
Suggested-by: Chris Li <chrisl@kernel.org>
Signed-off-by: Kairui Song <kasong@tencent.com>
---
include/linux/swap.h | 3 +-
mm/swapfile.c | 432 ++++++++++++++++++++++++-------------------
2 files changed, 247 insertions(+), 188 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 339d7f0192ff..c4ff31cb6bde 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -291,6 +291,7 @@ enum swap_cluster_flags {
* throughput.
*/
struct percpu_cluster {
+ local_lock_t lock; /* Protect the percpu_cluster above */
unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
};
@@ -313,7 +314,7 @@ struct swap_info_struct {
/* list of cluster that contains at least one free slot */
struct list_head frag_clusters[SWAP_NR_ORDERS];
/* list of cluster that are fragmented or contented */
- unsigned int frag_cluster_nr[SWAP_NR_ORDERS];
+ atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS];
unsigned int pages; /* total of usable pages of swap */
atomic_long_t inuse_pages; /* number of those currently in use */
struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b754c9e16c3b..489ac6997a0c 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -261,12 +261,10 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si,
folio_ref_sub(folio, nr_pages);
folio_set_dirty(folio);
- spin_lock(&si->lock);
/* Only sinple page folio can be backed by zswap */
if (nr_pages == 1)
zswap_invalidate(entry);
swap_entry_range_free(si, entry, nr_pages);
- spin_unlock(&si->lock);
ret = nr_pages;
out_unlock:
folio_unlock(folio);
@@ -401,9 +399,23 @@ static void discard_swap_cluster(struct swap_info_struct *si,
#endif
#define LATENCY_LIMIT 256
-static inline bool cluster_is_free(struct swap_cluster_info *info)
+static inline bool cluster_is_empty(struct swap_cluster_info *info)
+{
+ return info->count == 0;
+}
+
+static inline bool cluster_is_discard(struct swap_cluster_info *info)
+{
+ return info->flags == CLUSTER_FLAG_DISCARD;
+}
+
+static inline bool cluster_is_usable(struct swap_cluster_info *ci, int order)
{
- return info->flags == CLUSTER_FLAG_FREE;
+ if (unlikely(ci->flags > CLUSTER_FLAG_USABLE))
+ return false;
+ if (!order)
+ return true;
+ return cluster_is_empty(ci) || order == ci->order;
}
static inline unsigned int cluster_index(struct swap_info_struct *si,
@@ -441,19 +453,20 @@ static void move_cluster(struct swap_info_struct *si,
VM_WARN_ON(ci->flags == new_flags);
BUILD_BUG_ON(1 << sizeof(ci->flags) * BITS_PER_BYTE < CLUSTER_FLAG_MAX);
+ lockdep_assert_held(&ci->lock);
- if (ci->flags == CLUSTER_FLAG_NONE) {
+ spin_lock(&si->lock);
+ if (ci->flags == CLUSTER_FLAG_NONE)
list_add_tail(&ci->list, list);
- } else {
- if (ci->flags == CLUSTER_FLAG_FRAG) {
- VM_WARN_ON(!si->frag_cluster_nr[ci->order]);
- si->frag_cluster_nr[ci->order]--;
- }
+ else
list_move_tail(&ci->list, list);
- }
+ spin_unlock(&si->lock);
+
+ if (ci->flags == CLUSTER_FLAG_FRAG)
+ atomic_long_dec(&si->frag_cluster_nr[ci->order]);
+ else if (new_flags == CLUSTER_FLAG_FRAG)
+ atomic_long_inc(&si->frag_cluster_nr[ci->order]);
ci->flags = new_flags;
- if (new_flags == CLUSTER_FLAG_FRAG)
- si->frag_cluster_nr[ci->order]++;
}
/* Add a cluster to discard list and schedule it to do discard */
@@ -476,39 +489,91 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si,
static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
{
- lockdep_assert_held(&si->lock);
lockdep_assert_held(&ci->lock);
move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE);
ci->order = 0;
}
+/*
+ * Isolate and lock the first cluster that is not contented on a list,
+ * clean its flag before taken off-list. Cluster flag must be in sync
+ * with list status, so cluster updaters can always know the cluster
+ * list status without touching si lock.
+ *
+ * Note it's possible that all clusters on a list are contented so
+ * this returns NULL for an non-empty list.
+ */
+static struct swap_cluster_info *isolate_lock_cluster(
+ struct swap_info_struct *si, struct list_head *list)
+{
+ struct swap_cluster_info *ci, *ret = NULL;
+
+ spin_lock(&si->lock);
+
+ if (unlikely(!(si->flags & SWP_WRITEOK)))
+ goto out;
+
+ list_for_each_entry(ci, list, list) {
+ if (!spin_trylock(&ci->lock))
+ continue;
+
+ /* We may only isolate and clear flags of following lists */
+ VM_BUG_ON(!ci->flags);
+ VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE &&
+ ci->flags != CLUSTER_FLAG_FULL);
+
+ list_del(&ci->list);
+ ci->flags = CLUSTER_FLAG_NONE;
+ ret = ci;
+ break;
+ }
+out:
+ spin_unlock(&si->lock);
+
+ return ret;
+}
+
/*
* Doing discard actually. After a cluster discard is finished, the cluster
- * will be added to free cluster list. caller should hold si->lock.
-*/
-static void swap_do_scheduled_discard(struct swap_info_struct *si)
+ * will be added to free cluster list. Discard cluster is a bit special as
+ * they don't participate in allocation or reclaim, so clusters marked as
+ * CLUSTER_FLAG_DISCARD must remain off-list or on discard list.
+ */
+static bool swap_do_scheduled_discard(struct swap_info_struct *si)
{
struct swap_cluster_info *ci;
+ bool ret = false;
unsigned int idx;
+ spin_lock(&si->lock);
while (!list_empty(&si->discard_clusters)) {
ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list);
+ /*
+ * Delete the cluster from list to prepare for discard, but keep
+ * the CLUSTER_FLAG_DISCARD flag, there could be percpu_cluster
+ * pointing to it, or ran into by relocate_cluster.
+ */
list_del(&ci->list);
- /* Must clear flag when taking a cluster off-list */
- ci->flags = CLUSTER_FLAG_NONE;
idx = cluster_index(si, ci);
spin_unlock(&si->lock);
-
discard_swap_cluster(si, idx * SWAPFILE_CLUSTER,
SWAPFILE_CLUSTER);
- spin_lock(&si->lock);
spin_lock(&ci->lock);
- __free_cluster(si, ci);
+ /*
+ * Discard is done, clear its flags as it's off-list, then
+ * return the cluster to allocation list.
+ */
+ ci->flags = CLUSTER_FLAG_NONE;
memset(si->swap_map + idx * SWAPFILE_CLUSTER,
0, SWAPFILE_CLUSTER);
+ __free_cluster(si, ci);
spin_unlock(&ci->lock);
+ ret = true;
+ spin_lock(&si->lock);
}
+ spin_unlock(&si->lock);
+ return ret;
}
static void swap_discard_work(struct work_struct *work)
@@ -517,9 +582,7 @@ static void swap_discard_work(struct work_struct *work)
si = container_of(work, struct swap_info_struct, discard_work);
- spin_lock(&si->lock);
swap_do_scheduled_discard(si);
- spin_unlock(&si->lock);
}
static void swap_users_ref_free(struct percpu_ref *ref)
@@ -530,10 +593,14 @@ static void swap_users_ref_free(struct percpu_ref *ref)
complete(&si->comp);
}
+/*
+ * Must be called after freeing if ci->count == 0, moves the cluster to free
+ * or discard list.
+ */
static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
{
VM_BUG_ON(ci->count != 0);
- lockdep_assert_held(&si->lock);
+ VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE);
lockdep_assert_held(&ci->lock);
/*
@@ -550,6 +617,48 @@ static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *
__free_cluster(si, ci);
}
+/*
+ * Must be called after freeing if ci->count != 0, moves the cluster to
+ * nonfull list.
+ */
+static void partial_free_cluster(struct swap_info_struct *si,
+ struct swap_cluster_info *ci)
+{
+ VM_BUG_ON(!ci->count || ci->count == SWAPFILE_CLUSTER);
+ lockdep_assert_held(&ci->lock);
+
+ if (ci->flags != CLUSTER_FLAG_NONFULL)
+ move_cluster(si, ci, &si->nonfull_clusters[ci->order],
+ CLUSTER_FLAG_NONFULL);
+}
+
+/*
+ * Must be called after allocation, moves the cluster to full or frag list.
+ * Note: allocation doesn't acquire si lock, and may drop the ci lock for
+ * reclaim, so the cluster could be any where when called.
+ */
+static void relocate_cluster(struct swap_info_struct *si,
+ struct swap_cluster_info *ci)
+{
+ lockdep_assert_held(&ci->lock);
+
+ /* Discard cluster must remain off-list or on discard list */
+ if (cluster_is_discard(ci))
+ return;
+
+ if (!ci->count) {
+ free_cluster(si, ci);
+ } else if (ci->count != SWAPFILE_CLUSTER) {
+ if (ci->flags != CLUSTER_FLAG_FRAG)
+ move_cluster(si, ci, &si->frag_clusters[ci->order],
+ CLUSTER_FLAG_FRAG);
+ } else {
+ if (ci->flags != CLUSTER_FLAG_FULL)
+ move_cluster(si, ci, &si->full_clusters,
+ CLUSTER_FLAG_FULL);
+ }
+}
+
/*
* The cluster corresponding to page_nr will be used. The cluster will not be
* added to free cluster list and its usage counter will be increased by 1.
@@ -568,30 +677,6 @@ static void inc_cluster_info_page(struct swap_info_struct *si,
VM_BUG_ON(ci->flags);
}
-/*
- * The cluster ci decreases @nr_pages usage. If the usage counter becomes 0,
- * which means no page in the cluster is in use, we can optionally discard
- * the cluster and add it to free cluster list.
- */
-static void dec_cluster_info_page(struct swap_info_struct *si,
- struct swap_cluster_info *ci, int nr_pages)
-{
- VM_BUG_ON(ci->count < nr_pages);
- VM_BUG_ON(cluster_is_free(ci));
- lockdep_assert_held(&si->lock);
- lockdep_assert_held(&ci->lock);
- ci->count -= nr_pages;
-
- if (!ci->count) {
- free_cluster(si, ci);
- return;
- }
-
- if (ci->flags != CLUSTER_FLAG_NONFULL)
- move_cluster(si, ci, &si->nonfull_clusters[ci->order],
- CLUSTER_FLAG_NONFULL);
-}
-
static bool cluster_reclaim_range(struct swap_info_struct *si,
struct swap_cluster_info *ci,
unsigned long start, unsigned long end)
@@ -601,8 +686,6 @@ static bool cluster_reclaim_range(struct swap_info_struct *si,
int nr_reclaim;
spin_unlock(&ci->lock);
- spin_unlock(&si->lock);
-
do {
switch (READ_ONCE(map[offset])) {
case 0:
@@ -620,9 +703,7 @@ static bool cluster_reclaim_range(struct swap_info_struct *si,
}
} while (offset < end);
out:
- spin_lock(&si->lock);
spin_lock(&ci->lock);
-
/*
* Recheck the range no matter reclaim succeeded or not, the slot
* could have been be freed while we are not holding the lock.
@@ -636,11 +717,11 @@ static bool cluster_reclaim_range(struct swap_info_struct *si,
static bool cluster_scan_range(struct swap_info_struct *si,
struct swap_cluster_info *ci,
- unsigned long start, unsigned int nr_pages)
+ unsigned long start, unsigned int nr_pages,
+ bool *need_reclaim)
{
unsigned long offset, end = start + nr_pages;
unsigned char *map = si->swap_map;
- bool need_reclaim = false;
for (offset = start; offset < end; offset++) {
switch (READ_ONCE(map[offset])) {
@@ -649,16 +730,13 @@ static bool cluster_scan_range(struct swap_info_struct *si,
case SWAP_HAS_CACHE:
if (!vm_swap_full())
return false;
- need_reclaim = true;
+ *need_reclaim = true;
continue;
default:
return false;
}
}
- if (need_reclaim)
- return cluster_reclaim_range(si, ci, start, end);
-
return true;
}
@@ -673,23 +751,17 @@ static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster
if (!(si->flags & SWP_WRITEOK))
return false;
- VM_BUG_ON(ci->flags == CLUSTER_FLAG_NONE);
- VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE);
-
- if (cluster_is_free(ci)) {
- if (nr_pages < SWAPFILE_CLUSTER)
- move_cluster(si, ci, &si->nonfull_clusters[order],
- CLUSTER_FLAG_NONFULL);
+ /*
+ * The first allocation in a cluster makes the
+ * cluster exclusive to this order
+ */
+ if (cluster_is_empty(ci))
ci->order = order;
- }
memset(si->swap_map + start, usage, nr_pages);
swap_range_alloc(si, nr_pages);
ci->count += nr_pages;
- if (ci->count == SWAPFILE_CLUSTER)
- move_cluster(si, ci, &si->full_clusters, CLUSTER_FLAG_FULL);
-
return true;
}
@@ -700,37 +772,55 @@ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigne
unsigned long start = offset & ~(SWAPFILE_CLUSTER - 1);
unsigned long end = min(start + SWAPFILE_CLUSTER, si->max);
unsigned int nr_pages = 1 << order;
+ bool need_reclaim, ret;
struct swap_cluster_info *ci;
- if (end < nr_pages)
- return SWAP_NEXT_INVALID;
- end -= nr_pages;
+ ci = &si->cluster_info[offset / SWAPFILE_CLUSTER];
+ lockdep_assert_held(&ci->lock);
- ci = lock_cluster(si, offset);
- if (ci->count + nr_pages > SWAPFILE_CLUSTER) {
+ if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER) {
offset = SWAP_NEXT_INVALID;
- goto done;
+ goto out;
}
- while (offset <= end) {
- if (cluster_scan_range(si, ci, offset, nr_pages)) {
- if (!cluster_alloc_range(si, ci, offset, usage, order)) {
- offset = SWAP_NEXT_INVALID;
- goto done;
- }
- *foundp = offset;
- if (ci->count == SWAPFILE_CLUSTER) {
+ for (end -= nr_pages; offset <= end; offset += nr_pages) {
+ need_reclaim = false;
+ if (!cluster_scan_range(si, ci, offset, nr_pages, &need_reclaim))
+ continue;
+ if (need_reclaim) {
+ ret = cluster_reclaim_range(si, ci, start, end);
+ /*
+ * Reclaim drops ci->lock and cluster could be used
+ * by another order. Not checking flag as off-list
+ * cluster has no flag set, and change of list
+ * won't cause fragmentation.
+ */
+ if (!cluster_is_usable(ci, order)) {
offset = SWAP_NEXT_INVALID;
- goto done;
+ goto out;
}
- offset += nr_pages;
- break;
+ if (cluster_is_empty(ci))
+ offset = start;
+ /* Reclaim failed but cluster is usable, try next */
+ if (!ret)
+ continue;
+ }
+ if (!cluster_alloc_range(si, ci, offset, usage, order)) {
+ offset = SWAP_NEXT_INVALID;
+ goto out;
+ }
+ *foundp = offset;
+ if (ci->count == SWAPFILE_CLUSTER) {
+ offset = SWAP_NEXT_INVALID;
+ goto out;
}
offset += nr_pages;
+ break;
}
if (offset > end)
offset = SWAP_NEXT_INVALID;
-done:
+out:
+ relocate_cluster(si, ci);
unlock_cluster(ci);
return offset;
}
@@ -747,18 +837,17 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
if (force)
to_scan = swap_usage_in_pages(si) / SWAPFILE_CLUSTER;
- while (!list_empty(&si->full_clusters)) {
- ci = list_first_entry(&si->full_clusters, struct swap_cluster_info, list);
- list_move_tail(&ci->list, &si->full_clusters);
+ while ((ci = isolate_lock_cluster(si, &si->full_clusters))) {
offset = cluster_offset(si, ci);
end = min(si->max, offset + SWAPFILE_CLUSTER);
to_scan--;
- spin_unlock(&si->lock);
while (offset < end) {
if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) {
+ spin_unlock(&ci->lock);
nr_reclaim = __try_to_reclaim_swap(si, offset,
TTRS_ANYWAY | TTRS_DIRECT);
+ spin_lock(&ci->lock);
if (nr_reclaim) {
offset += abs(nr_reclaim);
continue;
@@ -766,8 +855,8 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
}
offset++;
}
- spin_lock(&si->lock);
+ unlock_cluster(ci);
if (to_scan <= 0)
break;
}
@@ -779,9 +868,7 @@ static void swap_reclaim_work(struct work_struct *work)
si = container_of(work, struct swap_info_struct, reclaim_work);
- spin_lock(&si->lock);
swap_reclaim_full_clusters(si, true);
- spin_unlock(&si->lock);
}
/*
@@ -792,29 +879,34 @@ static void swap_reclaim_work(struct work_struct *work)
static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order,
unsigned char usage)
{
- struct percpu_cluster *cluster;
struct swap_cluster_info *ci;
unsigned int offset, found = 0;
-new_cluster:
- lockdep_assert_held(&si->lock);
- cluster = this_cpu_ptr(si->percpu_cluster);
- offset = cluster->next[order];
+ /* Fast path using per CPU cluster */
+ local_lock(&si->percpu_cluster->lock);
+ offset = __this_cpu_read(si->percpu_cluster->next[order]);
if (offset) {
- offset = alloc_swap_scan_cluster(si, offset, &found, order, usage);
+ ci = lock_cluster(si, offset);
+ /* Cluster could have been used by another order */
+ if (cluster_is_usable(ci, order)) {
+ if (cluster_is_empty(ci))
+ offset = cluster_offset(si, ci);
+ offset = alloc_swap_scan_cluster(si, offset, &found,
+ order, usage);
+ } else {
+ unlock_cluster(ci);
+ }
if (found)
goto done;
}
- if (!list_empty(&si->free_clusters)) {
- ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
- offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage);
- /*
- * Either we didn't touch the cluster due to swapoff,
- * or the allocation must success.
- */
- VM_BUG_ON((si->flags & SWP_WRITEOK) && !found);
- goto done;
+new_cluster:
+ ci = isolate_lock_cluster(si, &si->free_clusters);
+ if (ci) {
+ offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
+ &found, order, usage);
+ if (found)
+ goto done;
}
/* Try reclaim from full clusters if free clusters list is drained */
@@ -822,49 +914,42 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
swap_reclaim_full_clusters(si, false);
if (order < PMD_ORDER) {
- unsigned int frags = 0;
+ unsigned int frags = 0, frags_existing;
- while (!list_empty(&si->nonfull_clusters[order])) {
- ci = list_first_entry(&si->nonfull_clusters[order],
- struct swap_cluster_info, list);
- move_cluster(si, ci, &si->frag_clusters[order], CLUSTER_FLAG_FRAG);
+ while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[order]))) {
offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
&found, order, usage);
- frags++;
if (found)
goto done;
+ /* Clusters failed to allocate are moved to frag_clusters */
+ frags++;
}
- /*
- * Nonfull clusters are moved to frag tail if we reached
- * here, count them too, don't over scan the frag list.
- */
- while (frags < si->frag_cluster_nr[order]) {
- ci = list_first_entry(&si->frag_clusters[order],
- struct swap_cluster_info, list);
+ frags_existing = atomic_long_read(&si->frag_cluster_nr[order]);
+ while (frags < frags_existing &&
+ (ci = isolate_lock_cluster(si, &si->frag_clusters[order]))) {
+ atomic_long_dec(&si->frag_cluster_nr[order]);
/*
- * Rotate the frag list to iterate, they were all failing
- * high order allocation or moved here due to per-CPU usage,
- * this help keeping usable cluster ahead.
+ * Rotate the frag list to iterate, they were all
+ * failing high order allocation or moved here due to
+ * per-CPU usage, but they could contain newly released
+ * reclaimable (eg. lazy-freed swap cache) slots.
*/
- list_move_tail(&ci->list, &si->frag_clusters[order]);
offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
&found, order, usage);
- frags++;
if (found)
goto done;
+ frags++;
}
}
- if (!list_empty(&si->discard_clusters)) {
- /*
- * we don't have free cluster but have some clusters in
- * discarding, do discard now and reclaim them, then
- * reread cluster_next_cpu since we dropped si->lock
- */
- swap_do_scheduled_discard(si);
+ /*
+ * We don't have free cluster but have some clusters in
+ * discarding, do discard now and reclaim them, then
+ * reread cluster_next_cpu since we dropped si->lock
+ */
+ if ((si->flags & SWP_PAGE_DISCARD) && swap_do_scheduled_discard(si))
goto new_cluster;
- }
if (order)
goto done;
@@ -875,26 +960,25 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
* Clusters here have at least one usable slots and can't fail order 0
* allocation, but reclaim may drop si->lock and race with another user.
*/
- while (!list_empty(&si->frag_clusters[o])) {
- ci = list_first_entry(&si->frag_clusters[o],
- struct swap_cluster_info, list);
+ while ((ci = isolate_lock_cluster(si, &si->frag_clusters[o]))) {
+ atomic_long_dec(&si->frag_cluster_nr[o]);
offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
- &found, 0, usage);
+ &found, order, usage);
if (found)
goto done;
}
- while (!list_empty(&si->nonfull_clusters[o])) {
- ci = list_first_entry(&si->nonfull_clusters[o],
- struct swap_cluster_info, list);
+ while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[o]))) {
offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
- &found, 0, usage);
+ &found, order, usage);
if (found)
goto done;
}
}
done:
- cluster->next[order] = offset;
+ __this_cpu_write(si->percpu_cluster->next[order], offset);
+ local_unlock(&si->percpu_cluster->lock);
+
return found;
}
@@ -1158,14 +1242,11 @@ int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]);
spin_unlock(&swap_avail_lock);
if (get_swap_device_info(si)) {
- spin_lock(&si->lock);
n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
n_goal, swp_entries, order);
- spin_unlock(&si->lock);
put_swap_device(si);
if (n_ret || size > 1)
goto check_out;
- cond_resched();
}
spin_lock(&swap_avail_lock);
@@ -1378,9 +1459,7 @@ static bool __swap_entries_free(struct swap_info_struct *si,
if (!has_cache) {
for (i = 0; i < nr; i++)
zswap_invalidate(swp_entry(si->type, offset + i));
- spin_lock(&si->lock);
swap_entry_range_free(si, entry, nr);
- spin_unlock(&si->lock);
}
return has_cache;
@@ -1409,16 +1488,27 @@ static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry
unsigned char *map_end = map + nr_pages;
struct swap_cluster_info *ci;
+ /* It should never free entries across different clusters */
+ VM_BUG_ON((offset / SWAPFILE_CLUSTER) != ((offset + nr_pages - 1) / SWAPFILE_CLUSTER));
+
ci = lock_cluster(si, offset);
+ VM_BUG_ON(cluster_is_empty(ci));
+ VM_BUG_ON(ci->count < nr_pages);
+
+ ci->count -= nr_pages;
do {
VM_BUG_ON(*map != SWAP_HAS_CACHE);
*map = 0;
} while (++map < map_end);
- dec_cluster_info_page(si, ci, nr_pages);
- unlock_cluster(ci);
mem_cgroup_uncharge_swap(entry, nr_pages);
swap_range_free(si, offset, nr_pages);
+
+ if (!ci->count)
+ free_cluster(si, ci);
+ else
+ partial_free_cluster(si, ci);
+ unlock_cluster(ci);
}
static void cluster_swap_free_nr(struct swap_info_struct *si,
@@ -1490,9 +1580,7 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
ci = lock_cluster(si, offset);
if (size > 1 && swap_is_has_cache(si, offset, size)) {
unlock_cluster(ci);
- spin_lock(&si->lock);
swap_entry_range_free(si, entry, size);
- spin_unlock(&si->lock);
return;
}
for (int i = 0; i < size; i++, entry.val++) {
@@ -1507,46 +1595,19 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
unlock_cluster(ci);
}
-static int swp_entry_cmp(const void *ent1, const void *ent2)
-{
- const swp_entry_t *e1 = ent1, *e2 = ent2;
-
- return (int)swp_type(*e1) - (int)swp_type(*e2);
-}
-
void swapcache_free_entries(swp_entry_t *entries, int n)
{
- struct swap_info_struct *si, *prev;
int i;
+ struct swap_info_struct *si = NULL;
if (n <= 0)
return;
- prev = NULL;
- si = NULL;
-
- /*
- * Sort swap entries by swap device, so each lock is only taken once.
- * nr_swapfiles isn't absolutely correct, but the overhead of sort() is
- * so low that it isn't necessary to optimize further.
- */
- if (nr_swapfiles > 1)
- sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL);
for (i = 0; i < n; ++i) {
si = _swap_info_get(entries[i]);
-
- if (si != prev) {
- if (prev != NULL)
- spin_unlock(&prev->lock);
- if (si != NULL)
- spin_lock(&si->lock);
- }
if (si)
swap_entry_range_free(si, entries[i], 1);
- prev = si;
}
- if (si)
- spin_unlock(&si->lock);
}
int __swap_count(swp_entry_t entry)
@@ -1799,10 +1860,8 @@ swp_entry_t get_swap_page_of_type(int type)
/* This is called for allocating swap entry, not cache */
if (get_swap_device_info(si)) {
- spin_lock(&si->lock);
if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0))
atomic_long_dec(&nr_swap_pages);
- spin_unlock(&si->lock);
put_swap_device(si);
}
fail:
@@ -3142,6 +3201,7 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
cluster = per_cpu_ptr(si->percpu_cluster, cpu);
for (i = 0; i < SWAP_NR_ORDERS; i++)
cluster->next[i] = SWAP_NEXT_INVALID;
+ local_lock_init(&cluster->lock);
}
/*
@@ -3165,7 +3225,7 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
for (i = 0; i < SWAP_NR_ORDERS; i++) {
INIT_LIST_HEAD(&si->nonfull_clusters[i]);
INIT_LIST_HEAD(&si->frag_clusters[i]);
- si->frag_cluster_nr[i] = 0;
+ atomic_long_set(&si->frag_cluster_nr[i], 0);
}
/*
@@ -3647,7 +3707,6 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
*/
goto outer;
}
- spin_lock(&si->lock);
offset = swp_offset(entry);
@@ -3712,7 +3771,6 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
spin_unlock(&si->cont_lock);
out:
unlock_cluster(ci);
- spin_unlock(&si->lock);
put_swap_device(si);
outer:
if (page)
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* [PATCH v4 10/13] mm, swap: simplify percpu cluster updating
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
` (8 preceding siblings ...)
2025-01-13 17:57 ` [PATCH v4 09/13] mm, swap: reduce contention on device lock Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 11/13] mm, swap: introduce a helper for retrieving cluster from offset Kairui Song
` (2 subsequent siblings)
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
Instead of using a returning argument, we can simply store the next
cluster offset to the fixed percpu location, which reduce the stack
usage and simplify the function:
Object size:
./scripts/bloat-o-meter mm/swapfile.o mm/swapfile.o.new
add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-271 (-271)
Function old new delta
get_swap_pages 2847 2733 -114
alloc_swap_scan_cluster 894 737 -157
Total: Before=30833, After=30562, chg -0.88%
Stack usage:
Before:
swapfile.c:1190:5:get_swap_pages 240 static
After:
swapfile.c:1185:5:get_swap_pages 216 static
Signed-off-by: Kairui Song <kasong@tencent.com>
---
include/linux/swap.h | 4 +--
mm/swapfile.c | 66 +++++++++++++++++++-------------------------
2 files changed, 31 insertions(+), 39 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c4ff31cb6bde..4c1d2e69689f 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -275,9 +275,9 @@ enum swap_cluster_flags {
* The first page in the swap file is the swap header, which is always marked
* bad to prevent it from being allocated as an entry. This also prevents the
* cluster to which it belongs being marked free. Therefore 0 is safe to use as
- * a sentinel to indicate next is not valid in percpu_cluster.
+ * a sentinel to indicate an entry is not valid.
*/
-#define SWAP_NEXT_INVALID 0
+#define SWAP_ENTRY_INVALID 0
#ifdef CONFIG_THP_SWAP
#define SWAP_NR_ORDERS (PMD_ORDER + 1)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 489ac6997a0c..6da2f3aa55fb 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -765,23 +765,23 @@ static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster
return true;
}
-static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigned long offset,
- unsigned int *foundp, unsigned int order,
+/* Try use a new cluster for current CPU and allocate from it. */
+static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si,
+ struct swap_cluster_info *ci,
+ unsigned long offset,
+ unsigned int order,
unsigned char usage)
{
- unsigned long start = offset & ~(SWAPFILE_CLUSTER - 1);
+ unsigned int next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID;
+ unsigned long start = ALIGN_DOWN(offset, SWAPFILE_CLUSTER);
unsigned long end = min(start + SWAPFILE_CLUSTER, si->max);
unsigned int nr_pages = 1 << order;
bool need_reclaim, ret;
- struct swap_cluster_info *ci;
- ci = &si->cluster_info[offset / SWAPFILE_CLUSTER];
lockdep_assert_held(&ci->lock);
- if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER) {
- offset = SWAP_NEXT_INVALID;
+ if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER)
goto out;
- }
for (end -= nr_pages; offset <= end; offset += nr_pages) {
need_reclaim = false;
@@ -795,34 +795,27 @@ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigne
* cluster has no flag set, and change of list
* won't cause fragmentation.
*/
- if (!cluster_is_usable(ci, order)) {
- offset = SWAP_NEXT_INVALID;
+ if (!cluster_is_usable(ci, order))
goto out;
- }
if (cluster_is_empty(ci))
offset = start;
/* Reclaim failed but cluster is usable, try next */
if (!ret)
continue;
}
- if (!cluster_alloc_range(si, ci, offset, usage, order)) {
- offset = SWAP_NEXT_INVALID;
- goto out;
- }
- *foundp = offset;
- if (ci->count == SWAPFILE_CLUSTER) {
- offset = SWAP_NEXT_INVALID;
- goto out;
- }
+ if (!cluster_alloc_range(si, ci, offset, usage, order))
+ break;
+ found = offset;
offset += nr_pages;
+ if (ci->count < SWAPFILE_CLUSTER && offset <= end)
+ next = offset;
break;
}
- if (offset > end)
- offset = SWAP_NEXT_INVALID;
out:
relocate_cluster(si, ci);
unlock_cluster(ci);
- return offset;
+ __this_cpu_write(si->percpu_cluster->next[order], next);
+ return found;
}
/* Return true if reclaimed a whole cluster */
@@ -891,8 +884,8 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
if (cluster_is_usable(ci, order)) {
if (cluster_is_empty(ci))
offset = cluster_offset(si, ci);
- offset = alloc_swap_scan_cluster(si, offset, &found,
- order, usage);
+ found = alloc_swap_scan_cluster(si, ci, offset,
+ order, usage);
} else {
unlock_cluster(ci);
}
@@ -903,8 +896,8 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
new_cluster:
ci = isolate_lock_cluster(si, &si->free_clusters);
if (ci) {
- offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
- &found, order, usage);
+ found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
+ order, usage);
if (found)
goto done;
}
@@ -917,8 +910,8 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
unsigned int frags = 0, frags_existing;
while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[order]))) {
- offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
- &found, order, usage);
+ found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
+ order, usage);
if (found)
goto done;
/* Clusters failed to allocate are moved to frag_clusters */
@@ -935,8 +928,8 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
* per-CPU usage, but they could contain newly released
* reclaimable (eg. lazy-freed swap cache) slots.
*/
- offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
- &found, order, usage);
+ found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
+ order, usage);
if (found)
goto done;
frags++;
@@ -962,21 +955,20 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
*/
while ((ci = isolate_lock_cluster(si, &si->frag_clusters[o]))) {
atomic_long_dec(&si->frag_cluster_nr[o]);
- offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
- &found, order, usage);
+ found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
+ 0, usage);
if (found)
goto done;
}
while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[o]))) {
- offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
- &found, order, usage);
+ found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
+ 0, usage);
if (found)
goto done;
}
}
done:
- __this_cpu_write(si->percpu_cluster->next[order], offset);
local_unlock(&si->percpu_cluster->lock);
return found;
@@ -3200,7 +3192,7 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
cluster = per_cpu_ptr(si->percpu_cluster, cpu);
for (i = 0; i < SWAP_NR_ORDERS; i++)
- cluster->next[i] = SWAP_NEXT_INVALID;
+ cluster->next[i] = SWAP_ENTRY_INVALID;
local_lock_init(&cluster->lock);
}
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* [PATCH v4 11/13] mm, swap: introduce a helper for retrieving cluster from offset
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
` (9 preceding siblings ...)
2025-01-13 17:57 ` [PATCH v4 10/13] mm, swap: simplify percpu cluster updating Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 12/13] mm, swap: use a global swap cluster for non-rotation devices Kairui Song
2025-01-13 17:57 ` [PATCH v4 13/13] mm, swap_slots: remove slot cache for freeing path Kairui Song
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
It's a common operation to retrieve the cluster info from offset,
introduce a helper for this.
Suggested-by: Chris Li <chrisl@kernel.org>
Signed-off-by: Kairui Song <kasong@tencent.com>
---
mm/swapfile.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6da2f3aa55fb..37d540fa0310 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -424,6 +424,12 @@ static inline unsigned int cluster_index(struct swap_info_struct *si,
return ci - si->cluster_info;
}
+static inline struct swap_cluster_info *offset_to_cluster(struct swap_info_struct *si,
+ unsigned long offset)
+{
+ return &si->cluster_info[offset / SWAPFILE_CLUSTER];
+}
+
static inline unsigned int cluster_offset(struct swap_info_struct *si,
struct swap_cluster_info *ci)
{
@@ -435,7 +441,7 @@ static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si
{
struct swap_cluster_info *ci;
- ci = &si->cluster_info[offset / SWAPFILE_CLUSTER];
+ ci = offset_to_cluster(si, offset);
spin_lock(&ci->lock);
return ci;
@@ -1480,10 +1486,10 @@ static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry
unsigned char *map_end = map + nr_pages;
struct swap_cluster_info *ci;
- /* It should never free entries across different clusters */
- VM_BUG_ON((offset / SWAPFILE_CLUSTER) != ((offset + nr_pages - 1) / SWAPFILE_CLUSTER));
-
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));
VM_BUG_ON(cluster_is_empty(ci));
VM_BUG_ON(ci->count < nr_pages);
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* [PATCH v4 12/13] mm, swap: use a global swap cluster for non-rotation devices
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
` (10 preceding siblings ...)
2025-01-13 17:57 ` [PATCH v4 11/13] mm, swap: introduce a helper for retrieving cluster from offset Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
2025-01-15 10:51 ` Kairui Song
2025-01-13 17:57 ` [PATCH v4 13/13] mm, swap_slots: remove slot cache for freeing path Kairui Song
12 siblings, 1 reply; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
Non-rotational devices (SSD / ZRAM) can tolerate fragmentation, so the
goal of the SWAP allocator is to avoid contention for clusters. It uses
a per-CPU cluster design, and each CPU will use a different cluster as
much as possible.
However, HDDs are very sensitive to fragmentation, contention is trivial
in comparison. Therefore, we use one global cluster instead. This ensures
that each order will be written to the same cluster as much as possible,
which helps make the I/O more continuous.
This ensures that the performance of the cluster allocator is as good as
that of the old allocator. Tests after this commit compared to those
before this series:
Tested using 'make -j32' with tinyconfig, a 1G memcg limit, and HDD swap:
make -j32 with tinyconfig, using 1G memcg limit and HDD swap:
Before this series:
114.44user 29.11system 39:42.90elapsed 6%CPU (0avgtext+0avgdata 157284maxresident)k
2901232inputs+0outputs (238877major+4227640minor)pagefaults
After this commit:
113.90user 23.81system 38:11.77elapsed 6%CPU (0avgtext+0avgdata 157260maxresident)k
2548728inputs+0outputs (235471major+4238110minor)pagefaults
Suggested-by: Chris Li <chrisl@kernel.org>
Signed-off-by: Kairui Song <kasong@tencent.com>
---
include/linux/swap.h | 2 ++
mm/swapfile.c | 51 ++++++++++++++++++++++++++++++++------------
2 files changed, 39 insertions(+), 14 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4c1d2e69689f..b13b72645db3 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -318,6 +318,8 @@ struct swap_info_struct {
unsigned int pages; /* total of usable pages of swap */
atomic_long_t inuse_pages; /* number of those currently in use */
struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
+ struct percpu_cluster *global_cluster; /* Use one global cluster for rotating device */
+ spinlock_t global_cluster_lock; /* Serialize usage of global cluster */
struct rb_root swap_extent_root;/* root of the swap extent rbtree */
struct block_device *bdev; /* swap device or bdev of swap file */
struct file *swap_file; /* seldom referenced */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 37d540fa0310..793b2fd1a2a8 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -820,7 +820,10 @@ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si,
out:
relocate_cluster(si, ci);
unlock_cluster(ci);
- __this_cpu_write(si->percpu_cluster->next[order], next);
+ if (si->flags & SWP_SOLIDSTATE)
+ __this_cpu_write(si->percpu_cluster->next[order], next);
+ else
+ si->global_cluster->next[order] = next;
return found;
}
@@ -881,9 +884,16 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
struct swap_cluster_info *ci;
unsigned int offset, found = 0;
- /* Fast path using per CPU cluster */
- local_lock(&si->percpu_cluster->lock);
- offset = __this_cpu_read(si->percpu_cluster->next[order]);
+ if (si->flags & SWP_SOLIDSTATE) {
+ /* Fast path using per CPU cluster */
+ local_lock(&si->percpu_cluster->lock);
+ offset = __this_cpu_read(si->percpu_cluster->next[order]);
+ } else {
+ /* Serialize HDD SWAP allocation for each device. */
+ spin_lock(&si->global_cluster_lock);
+ offset = si->global_cluster->next[order];
+ }
+
if (offset) {
ci = lock_cluster(si, offset);
/* Cluster could have been used by another order */
@@ -975,8 +985,10 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
}
}
done:
- local_unlock(&si->percpu_cluster->lock);
-
+ if (si->flags & SWP_SOLIDSTATE)
+ local_unlock(&si->percpu_cluster->lock);
+ else
+ spin_unlock(&si->global_cluster_lock);
return found;
}
@@ -2784,6 +2796,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
mutex_unlock(&swapon_mutex);
free_percpu(p->percpu_cluster);
p->percpu_cluster = NULL;
+ kfree(p->global_cluster);
+ p->global_cluster = NULL;
vfree(swap_map);
kvfree(zeromap);
kvfree(cluster_info);
@@ -3189,17 +3203,24 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
for (i = 0; i < nr_clusters; i++)
spin_lock_init(&cluster_info[i].lock);
- si->percpu_cluster = alloc_percpu(struct percpu_cluster);
- if (!si->percpu_cluster)
- goto err_free;
+ if (si->flags & SWP_SOLIDSTATE) {
+ si->percpu_cluster = alloc_percpu(struct percpu_cluster);
+ if (!si->percpu_cluster)
+ goto err_free;
- for_each_possible_cpu(cpu) {
- struct percpu_cluster *cluster;
+ for_each_possible_cpu(cpu) {
+ struct percpu_cluster *cluster;
- cluster = per_cpu_ptr(si->percpu_cluster, cpu);
+ cluster = per_cpu_ptr(si->percpu_cluster, cpu);
+ for (i = 0; i < SWAP_NR_ORDERS; i++)
+ cluster->next[i] = SWAP_ENTRY_INVALID;
+ local_lock_init(&cluster->lock);
+ }
+ } else {
+ si->global_cluster = kmalloc(sizeof(*si->global_cluster), GFP_KERNEL);
for (i = 0; i < SWAP_NR_ORDERS; i++)
- cluster->next[i] = SWAP_ENTRY_INVALID;
- local_lock_init(&cluster->lock);
+ si->global_cluster->next[i] = SWAP_ENTRY_INVALID;
+ spin_lock_init(&si->global_cluster_lock);
}
/*
@@ -3473,6 +3494,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
bad_swap:
free_percpu(si->percpu_cluster);
si->percpu_cluster = NULL;
+ kfree(si->global_cluster);
+ si->global_cluster = NULL;
inode = NULL;
destroy_swap_extents(si);
swap_cgroup_swapoff(si->type);
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCH v4 12/13] mm, swap: use a global swap cluster for non-rotation devices
2025-01-13 17:57 ` [PATCH v4 12/13] mm, swap: use a global swap cluster for non-rotation devices Kairui Song
@ 2025-01-15 10:51 ` Kairui Song
0 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-15 10:51 UTC (permalink / raw)
To: Andrew Morton, linux-mm
Cc: Chris Li, Barry Song, Ryan Roberts, Hugh Dickins, Yosry Ahmed,
Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel
On Tue, Jan 14, 2025 at 2:00 AM Kairui Song <ryncsn@gmail.com> wrote:
>
> From: Kairui Song <kasong@tencent.com>
>
> Non-rotational devices (SSD / ZRAM) can tolerate fragmentation, so the
> goal of the SWAP allocator is to avoid contention for clusters. It uses
> a per-CPU cluster design, and each CPU will use a different cluster as
> much as possible.
>
> However, HDDs are very sensitive to fragmentation, contention is trivial
> in comparison. Therefore, we use one global cluster instead. This ensures
> that each order will be written to the same cluster as much as possible,
> which helps make the I/O more continuous.
>
> This ensures that the performance of the cluster allocator is as good as
> that of the old allocator. Tests after this commit compared to those
> before this series:
>
> Tested using 'make -j32' with tinyconfig, a 1G memcg limit, and HDD swap:
>
> make -j32 with tinyconfig, using 1G memcg limit and HDD swap:
>
> Before this series:
> 114.44user 29.11system 39:42.90elapsed 6%CPU (0avgtext+0avgdata 157284maxresident)k
> 2901232inputs+0outputs (238877major+4227640minor)pagefaults
>
> After this commit:
> 113.90user 23.81system 38:11.77elapsed 6%CPU (0avgtext+0avgdata 157260maxresident)k
> 2548728inputs+0outputs (235471major+4238110minor)pagefaults
>
> Suggested-by: Chris Li <chrisl@kernel.org>
> Signed-off-by: Kairui Song <kasong@tencent.com>
> ---
> include/linux/swap.h | 2 ++
> mm/swapfile.c | 51 ++++++++++++++++++++++++++++++++------------
> 2 files changed, 39 insertions(+), 14 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 4c1d2e69689f..b13b72645db3 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -318,6 +318,8 @@ struct swap_info_struct {
> unsigned int pages; /* total of usable pages of swap */
> atomic_long_t inuse_pages; /* number of those currently in use */
> struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
> + struct percpu_cluster *global_cluster; /* Use one global cluster for rotating device */
> + spinlock_t global_cluster_lock; /* Serialize usage of global cluster */
> struct rb_root swap_extent_root;/* root of the swap extent rbtree */
> struct block_device *bdev; /* swap device or bdev of swap file */
> struct file *swap_file; /* seldom referenced */
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 37d540fa0310..793b2fd1a2a8 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -820,7 +820,10 @@ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si,
> out:
> relocate_cluster(si, ci);
> unlock_cluster(ci);
> - __this_cpu_write(si->percpu_cluster->next[order], next);
> + if (si->flags & SWP_SOLIDSTATE)
> + __this_cpu_write(si->percpu_cluster->next[order], next);
> + else
> + si->global_cluster->next[order] = next;
> return found;
> }
>
> @@ -881,9 +884,16 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
> struct swap_cluster_info *ci;
> unsigned int offset, found = 0;
>
> - /* Fast path using per CPU cluster */
> - local_lock(&si->percpu_cluster->lock);
> - offset = __this_cpu_read(si->percpu_cluster->next[order]);
> + if (si->flags & SWP_SOLIDSTATE) {
> + /* Fast path using per CPU cluster */
> + local_lock(&si->percpu_cluster->lock);
> + offset = __this_cpu_read(si->percpu_cluster->next[order]);
> + } else {
> + /* Serialize HDD SWAP allocation for each device. */
> + spin_lock(&si->global_cluster_lock);
> + offset = si->global_cluster->next[order];
> + }
> +
> if (offset) {
> ci = lock_cluster(si, offset);
> /* Cluster could have been used by another order */
> @@ -975,8 +985,10 @@ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int o
> }
> }
> done:
> - local_unlock(&si->percpu_cluster->lock);
> -
> + if (si->flags & SWP_SOLIDSTATE)
> + local_unlock(&si->percpu_cluster->lock);
> + else
> + spin_unlock(&si->global_cluster_lock);
> return found;
> }
>
> @@ -2784,6 +2796,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
> mutex_unlock(&swapon_mutex);
> free_percpu(p->percpu_cluster);
> p->percpu_cluster = NULL;
> + kfree(p->global_cluster);
> + p->global_cluster = NULL;
> vfree(swap_map);
> kvfree(zeromap);
> kvfree(cluster_info);
> @@ -3189,17 +3203,24 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
> for (i = 0; i < nr_clusters; i++)
> spin_lock_init(&cluster_info[i].lock);
>
> - si->percpu_cluster = alloc_percpu(struct percpu_cluster);
> - if (!si->percpu_cluster)
> - goto err_free;
> + if (si->flags & SWP_SOLIDSTATE) {
> + si->percpu_cluster = alloc_percpu(struct percpu_cluster);
> + if (!si->percpu_cluster)
> + goto err_free;
>
> - for_each_possible_cpu(cpu) {
> - struct percpu_cluster *cluster;
> + for_each_possible_cpu(cpu) {
> + struct percpu_cluster *cluster;
>
> - cluster = per_cpu_ptr(si->percpu_cluster, cpu);
> + cluster = per_cpu_ptr(si->percpu_cluster, cpu);
> + for (i = 0; i < SWAP_NR_ORDERS; i++)
> + cluster->next[i] = SWAP_ENTRY_INVALID;
> + local_lock_init(&cluster->lock);
> + }
> + } else {
> + si->global_cluster = kmalloc(sizeof(*si->global_cluster), GFP_KERNEL);
Hi Andrew,
Sorry I just found I missed this tiny fix here, can you help fold it to the
current unstable tree?
diff --git a/mm/swapfile.c b/mm/swapfile.c
index e57e5453a25b..559b8e62ff71 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3212,6 +3212,8 @@ static struct swap_cluster_info
*setup_clusters(struct swap_info_struct *si,
}
} else {
si->global_cluster =
kmalloc(sizeof(*si->global_cluster), GFP_KERNEL);
+ if (!si->global_cluster)
+ goto err_free;
for (i = 0; i < SWAP_NR_ORDERS; i++)
si->global_cluster->next[i] = SWAP_ENTRY_INVALID;
spin_lock_init(&si->global_cluster_lock);
^ permalink raw reply [flat|nested] 15+ messages in thread
* [PATCH v4 13/13] mm, swap_slots: remove slot cache for freeing path
2025-01-13 17:57 [PATCH v4 00/13] mm, swap: rework of swap allocator locks Kairui Song
` (11 preceding siblings ...)
2025-01-13 17:57 ` [PATCH v4 12/13] mm, swap: use a global swap cluster for non-rotation devices Kairui Song
@ 2025-01-13 17:57 ` Kairui Song
12 siblings, 0 replies; 15+ messages in thread
From: Kairui Song @ 2025-01-13 17:57 UTC (permalink / raw)
To: linux-mm
Cc: Andrew Morton, Chris Li, Barry Song, Ryan Roberts, Hugh Dickins,
Yosry Ahmed, Huang, Ying, Baoquan He, Nhat Pham, Johannes Weiner,
Kalesh Singh, linux-kernel, Kairui Song
From: Kairui Song <kasong@tencent.com>
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@mail.gmail.com/[1]
Suggested-by: Chris Li <chrisl@kernel.org>
Signed-off-by: Kairui Song <kasong@tencent.com>
---
include/linux/swap_slots.h | 3 --
mm/swap_slots.c | 78 +++++----------------------------
mm/swapfile.c | 89 +++++++++++++++-----------------------
3 files changed, 44 insertions(+), 126 deletions(-)
diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h
index 15adfb8c813a..840aec3523b2 100644
--- a/include/linux/swap_slots.h
+++ b/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;
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 13ab3b771409..9c7c171df7ba 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -43,17 +43,15 @@ static DEFINE_MUTEX(swap_slots_cache_mutex);
/* 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 @@ static bool check_cache_active(void)
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(unsigned int cpu)
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(unsigned int cpu)
*/
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(unsigned int cpu, unsigned int type,
}
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(unsigned int type)
* 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(struct swap_slots_cache *cache)
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;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 793b2fd1a2a8..b3154e52cb45 100644
--- a/mm/swapfile.c
+++ b/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 swap_info_struct *si,
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_info_struct *si, unsigned long offset,
* 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(struct swap_info_struct *si,
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 swap_info_struct *si,
}
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 @@ static bool __swap_entries_free(struct swap_info_struct *si,
* 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 swap_info_struct *si, swp_entry_t entry
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 swap_info_struct *si,
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, swp_entry_t entry)
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, swp_entry_t entry)
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 *entries, int n)
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);
+ }
}
}
--
2.47.1
^ permalink raw reply [flat|nested] 15+ messages in thread