From: Kairui Song <kasong@xxxxxxxxxxx>
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 `cluster_isolate_lock`.
- 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@xxxxxxxxxx>
Signed-off-by: Kairui Song <kasong@xxxxxxxxxxx>
---
include/linux/swap.h | 3 +-
mm/swapfile.c | 435 ++++++++++++++++++++++++-------------------
2 files changed, 246 insertions(+), 192 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 be2c719a51bb..bb1ef9192d99 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);
@@ -403,7 +401,21 @@ 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->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)
+{
+ if (unlikely(ci->flags > CLUSTER_FLAG_USABLE))
+ return false;
+ if (!order)
+ return true;
+ return cluster_is_free(ci) || order == ci->order;
}
static inline unsigned int cluster_index(struct swap_info_struct *si,
@@ -440,19 +452,20 @@ static void cluster_move(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 */
@@ -475,39 +488,90 @@ 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);
cluster_move(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 *cluster_isolate_lock(
+ 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 but don't clear its flags until
+ * discard is done, so isolation and relocation will skip it.
+ */
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 now 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)
@@ -516,9 +580,7 @@ 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)
@@ -529,10 +591,14 @@ 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);
/*
@@ -549,6 +615,48 @@ 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)
+ cluster_move(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)
+ cluster_move(si, ci, &si->frag_clusters[ci->order],
+ CLUSTER_FLAG_FRAG);
+ } else {
+ if (ci->flags != CLUSTER_FLAG_FULL)
+ cluster_move(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.
@@ -567,30 +675,6 @@ 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)
- cluster_move(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)
@@ -600,8 +684,6 @@ 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:
@@ -619,9 +701,7 @@ 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.
@@ -635,11 +715,11 @@ 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])) {
@@ -648,16 +728,13 @@ 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;
}
@@ -672,23 +749,13 @@ 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)
- cluster_move(si, ci, &si->nonfull_clusters[order],
- CLUSTER_FLAG_NONFULL);
+ if (cluster_is_free(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)
- cluster_move(si, ci, &si->full_clusters, CLUSTER_FLAG_FULL);
-
return true;
}
@@ -699,37 +766,55 @@ 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_free(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;
}
@@ -746,18 +831,17 @@ 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 = cluster_isolate_lock(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;
@@ -765,8 +849,8 @@ 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;
}
@@ -778,9 +862,7 @@ 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);
}
/*
@@ -791,29 +873,34 @@ 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_free(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 = cluster_isolate_lock(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 */
@@ -821,49 +908,45 @@ 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);
- cluster_move(si, ci, &si->frag_clusters[order], CLUSTER_FLAG_FRAG);
+ while ((ci = cluster_isolate_lock(si, &si->nonfull_clusters[order]))) {
offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
&found, order, usage);
- frags++;
+ /*
+ * With `fragmenting` set to true, it will surely take
+ * the cluster off nonfull list
+ */
if (found)
goto done;
+ 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 = cluster_isolate_lock(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;
@@ -874,26 +957,25 @@ 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 = cluster_isolate_lock(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 = cluster_isolate_lock(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;
}
@@ -1153,14 +1235,11 @@ 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);
@@ -1373,9 +1452,7 @@ 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;
@@ -1404,16 +1481,27 @@ 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_free(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,
@@ -1485,9 +1573,7 @@ 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++) {
@@ -1502,46 +1588,19 @@ 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)
@@ -1793,13 +1852,8 @@ swp_entry_t get_swap_page_of_type(int type)
goto fail;
/* 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);
- }
+ if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0))
+ atomic_long_dec(&nr_swap_pages);
fail:
return entry;
}
@@ -3137,6 +3191,7 @@ 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);
}
/*
@@ -3160,7 +3215,7 @@ 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);
}
/*
@@ -3642,7 +3697,6 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
*/
goto outer;
}
- spin_lock(&si->lock);
offset = swp_offset(entry);
@@ -3707,7 +3761,6 @@ 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
