The quilt patch titled
Subject: mm: swap: allow storage of all mTHP orders
has been removed from the -mm tree. Its filename was
mm-swap-allow-storage-of-all-mthp-orders.patch
This patch was dropped because it was merged into the mm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Ryan Roberts <ryan.roberts@xxxxxxx>
Subject: mm: swap: allow storage of all mTHP orders
Date: Mon, 8 Apr 2024 19:39:44 +0100
Multi-size THP enables performance improvements by allocating large,
pte-mapped folios for anonymous memory. However I've observed that on an
arm64 system running a parallel workload (e.g. kernel compilation) across
many cores, under high memory pressure, the speed regresses. This is due
to bottlenecking on the increased number of TLBIs added due to all the
extra folio splitting when the large folios are swapped out.
Therefore, solve this regression by adding support for swapping out mTHP
without needing to split the folio, just like is already done for
PMD-sized THP. This change only applies when CONFIG_THP_SWAP is enabled,
and when the swap backing store is a non-rotating block device. These are
the same constraints as for the existing PMD-sized THP swap-out support.
Note that no attempt is made to swap-in (m)THP here - this is still done
page-by-page, like for PMD-sized THP. But swapping-out mTHP is a
prerequisite for swapping-in mTHP.
The main change here is to improve the swap entry allocator so that it can
allocate any power-of-2 number of contiguous entries between [1, (1 <<
PMD_ORDER)]. This is done by allocating a cluster for each distinct order
and allocating sequentially from it until the cluster is full. This
ensures that we don't need to search the map and we get no fragmentation
due to alignment padding for different orders in the cluster. If there is
no current cluster for a given order, we attempt to allocate a free
cluster from the list. If there are no free clusters, we fail the
allocation and the caller can fall back to splitting the folio and
allocates individual entries (as per existing PMD-sized THP fallback).
The per-order current clusters are maintained per-cpu using the existing
infrastructure. This is done to avoid interleving pages from different
tasks, which would prevent IO being batched. This is already done for the
order-0 allocations so we follow the same pattern.
As is done for order-0 per-cpu clusters, the scanner now can steal order-0
entries from any per-cpu-per-order reserved cluster. This ensures that
when the swap file is getting full, space doesn't get tied up in the
per-cpu reserves.
This change only modifies swap to be able to accept any order mTHP. It
doesn't change the callers to elide doing the actual split. That will be
done in separate changes.
Link: https://lkml.kernel.org/r/20240408183946.2991168-6-ryan.roberts@xxxxxxx
Signed-off-by: Ryan Roberts <ryan.roberts@xxxxxxx>
Reviewed-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: Barry Song <21cnbao@xxxxxxxxx>
Cc: Barry Song <v-songbaohua@xxxxxxxx>
Cc: Chris Li <chrisl@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Gao Xiang <xiang@xxxxxxxxxx>
Cc: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
Cc: Lance Yang <ioworker0@xxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Yang Shi <shy828301@xxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/swap.h | 8 +-
mm/swapfile.c | 162 +++++++++++++++++++++++------------------
2 files changed, 98 insertions(+), 72 deletions(-)
--- a/include/linux/swap.h~mm-swap-allow-storage-of-all-mthp-orders
+++ a/include/linux/swap.h
@@ -268,13 +268,19 @@ struct swap_cluster_info {
*/
#define SWAP_NEXT_INVALID 0
+#ifdef CONFIG_THP_SWAP
+#define SWAP_NR_ORDERS (PMD_ORDER + 1)
+#else
+#define SWAP_NR_ORDERS 1
+#endif
+
/*
* We assign a cluster to each CPU, so each CPU can allocate swap entry from
* its own cluster and swapout sequentially. The purpose is to optimize swapout
* throughput.
*/
struct percpu_cluster {
- unsigned int next; /* Likely next allocation offset */
+ unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
};
struct swap_cluster_list {
--- a/mm/swapfile.c~mm-swap-allow-storage-of-all-mthp-orders
+++ a/mm/swapfile.c
@@ -551,10 +551,12 @@ static void free_cluster(struct swap_inf
/*
* The cluster corresponding to page_nr will be used. The cluster will be
- * removed from free cluster list and its usage counter will be increased.
+ * removed from free cluster list and its usage counter will be increased by
+ * count.
*/
-static void inc_cluster_info_page(struct swap_info_struct *p,
- struct swap_cluster_info *cluster_info, unsigned long page_nr)
+static void add_cluster_info_page(struct swap_info_struct *p,
+ struct swap_cluster_info *cluster_info, unsigned long page_nr,
+ unsigned long count)
{
unsigned long idx = page_nr / SWAPFILE_CLUSTER;
@@ -563,9 +565,19 @@ static void inc_cluster_info_page(struct
if (cluster_is_free(&cluster_info[idx]))
alloc_cluster(p, idx);
- VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER);
+ VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER);
cluster_set_count(&cluster_info[idx],
- cluster_count(&cluster_info[idx]) + 1);
+ cluster_count(&cluster_info[idx]) + count);
+}
+
+/*
+ * The cluster corresponding to page_nr will be used. The cluster will be
+ * removed from free cluster list and its usage counter will be increased by 1.
+ */
+static void inc_cluster_info_page(struct swap_info_struct *p,
+ struct swap_cluster_info *cluster_info, unsigned long page_nr)
+{
+ add_cluster_info_page(p, cluster_info, page_nr, 1);
}
/*
@@ -595,7 +607,7 @@ static void dec_cluster_info_page(struct
*/
static bool
scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
- unsigned long offset)
+ unsigned long offset, int order)
{
struct percpu_cluster *percpu_cluster;
bool conflict;
@@ -609,24 +621,39 @@ scan_swap_map_ssd_cluster_conflict(struc
return false;
percpu_cluster = this_cpu_ptr(si->percpu_cluster);
- percpu_cluster->next = SWAP_NEXT_INVALID;
+ percpu_cluster->next[order] = SWAP_NEXT_INVALID;
+ return true;
+}
+
+static inline bool swap_range_empty(char *swap_map, unsigned int start,
+ unsigned int nr_pages)
+{
+ unsigned int i;
+
+ for (i = 0; i < nr_pages; i++) {
+ if (swap_map[start + i])
+ return false;
+ }
+
return true;
}
/*
- * Try to get a swap entry from current cpu's swap entry pool (a cluster). This
- * might involve allocating a new cluster for current CPU too.
+ * Try to get swap entries with specified order from current cpu's swap entry
+ * pool (a cluster). This might involve allocating a new cluster for current CPU
+ * too.
*/
static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
- unsigned long *offset, unsigned long *scan_base)
+ unsigned long *offset, unsigned long *scan_base, int order)
{
+ unsigned int nr_pages = 1 << order;
struct percpu_cluster *cluster;
struct swap_cluster_info *ci;
unsigned int tmp, max;
new_cluster:
cluster = this_cpu_ptr(si->percpu_cluster);
- tmp = cluster->next;
+ tmp = cluster->next[order];
if (tmp == SWAP_NEXT_INVALID) {
if (!cluster_list_empty(&si->free_clusters)) {
tmp = cluster_next(&si->free_clusters.head) *
@@ -647,26 +674,27 @@ new_cluster:
/*
* Other CPUs can use our cluster if they can't find a free cluster,
- * check if there is still free entry in the cluster
+ * check if there is still free entry in the cluster, maintaining
+ * natural alignment.
*/
max = min_t(unsigned long, si->max, ALIGN(tmp + 1, SWAPFILE_CLUSTER));
if (tmp < max) {
ci = lock_cluster(si, tmp);
while (tmp < max) {
- if (!si->swap_map[tmp])
+ if (swap_range_empty(si->swap_map, tmp, nr_pages))
break;
- tmp++;
+ tmp += nr_pages;
}
unlock_cluster(ci);
}
if (tmp >= max) {
- cluster->next = SWAP_NEXT_INVALID;
+ cluster->next[order] = SWAP_NEXT_INVALID;
goto new_cluster;
}
*offset = tmp;
*scan_base = tmp;
- tmp += 1;
- cluster->next = tmp < max ? tmp : SWAP_NEXT_INVALID;
+ tmp += nr_pages;
+ cluster->next[order] = tmp < max ? tmp : SWAP_NEXT_INVALID;
return true;
}
@@ -796,13 +824,14 @@ static bool swap_offset_available_and_lo
static int scan_swap_map_slots(struct swap_info_struct *si,
unsigned char usage, int nr,
- swp_entry_t slots[])
+ swp_entry_t slots[], int order)
{
struct swap_cluster_info *ci;
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;
@@ -817,6 +846,25 @@ static int scan_swap_map_slots(struct sw
* And we let swap pages go all over an SSD partition. Hugh
*/
+ if (order > 0) {
+ /*
+ * Should not even be attempting large allocations when huge
+ * page swap is disabled. Warn and fail the allocation.
+ */
+ if (!IS_ENABLED(CONFIG_THP_SWAP) ||
+ nr_pages > SWAPFILE_CLUSTER) {
+ VM_WARN_ON_ONCE(1);
+ return 0;
+ }
+
+ /*
+ * Swapfile is not block device or not using clusters so unable
+ * to allocate large entries.
+ */
+ if (!(si->flags & SWP_BLKDEV) || !si->cluster_info)
+ return 0;
+ }
+
si->flags += SWP_SCANNING;
/*
* Use percpu scan base for SSD to reduce lock contention on
@@ -831,8 +879,11 @@ static int scan_swap_map_slots(struct sw
/* SSD algorithm */
if (si->cluster_info) {
- if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
+ if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order)) {
+ if (order > 0)
+ goto no_page;
goto scan;
+ }
} else if (unlikely(!si->cluster_nr--)) {
if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
si->cluster_nr = SWAPFILE_CLUSTER - 1;
@@ -874,13 +925,16 @@ static int scan_swap_map_slots(struct sw
checks:
if (si->cluster_info) {
- while (scan_swap_map_ssd_cluster_conflict(si, offset)) {
+ while (scan_swap_map_ssd_cluster_conflict(si, offset, order)) {
/* take a break if we already got some slots */
if (n_ret)
goto done;
if (!scan_swap_map_try_ssd_cluster(si, &offset,
- &scan_base))
+ &scan_base, order)) {
+ if (order > 0)
+ goto no_page;
goto scan;
+ }
}
}
if (!(si->flags & SWP_WRITEOK))
@@ -911,11 +965,11 @@ checks:
else
goto done;
}
- WRITE_ONCE(si->swap_map[offset], usage);
- inc_cluster_info_page(si, si->cluster_info, offset);
+ memset(si->swap_map + offset, usage, nr_pages);
+ add_cluster_info_page(si, si->cluster_info, offset, nr_pages);
unlock_cluster(ci);
- swap_range_alloc(si, offset, 1);
+ swap_range_alloc(si, offset, nr_pages);
slots[n_ret++] = swp_entry(si->type, offset);
/* got enough slots or reach max slots? */
@@ -936,8 +990,10 @@ checks:
/* try to get more slots in cluster */
if (si->cluster_info) {
- if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
+ if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order))
goto checks;
+ if (order > 0)
+ goto done;
} else if (si->cluster_nr && !si->swap_map[++offset]) {
/* non-ssd case, still more slots in cluster? */
--si->cluster_nr;
@@ -964,11 +1020,13 @@ checks:
}
done:
- set_cluster_next(si, offset + 1);
+ 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)) {
@@ -997,38 +1055,6 @@ no_page:
return n_ret;
}
-static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
-{
- unsigned long idx;
- struct swap_cluster_info *ci;
- unsigned long offset;
-
- /*
- * Should not even be attempting cluster allocations when huge
- * page swap is disabled. Warn and fail the allocation.
- */
- if (!IS_ENABLED(CONFIG_THP_SWAP)) {
- VM_WARN_ON_ONCE(1);
- return 0;
- }
-
- if (cluster_list_empty(&si->free_clusters))
- return 0;
-
- idx = cluster_list_first(&si->free_clusters);
- offset = idx * SWAPFILE_CLUSTER;
- ci = lock_cluster(si, offset);
- alloc_cluster(si, idx);
- cluster_set_count(ci, SWAPFILE_CLUSTER);
-
- memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER);
- unlock_cluster(ci);
- swap_range_alloc(si, offset, SWAPFILE_CLUSTER);
- *slot = swp_entry(si->type, offset);
-
- return 1;
-}
-
static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
{
unsigned long offset = idx * SWAPFILE_CLUSTER;
@@ -1051,9 +1077,6 @@ int get_swap_pages(int n_goal, swp_entry
int n_ret = 0;
int node;
- /* Only single cluster request supported */
- WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER);
-
spin_lock(&swap_avail_lock);
avail_pgs = atomic_long_read(&nr_swap_pages) / size;
@@ -1089,14 +1112,10 @@ start_over:
spin_unlock(&si->lock);
goto nextsi;
}
- if (size == SWAPFILE_CLUSTER) {
- if (si->flags & SWP_BLKDEV)
- n_ret = swap_alloc_cluster(si, swp_entries);
- } else
- n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
- n_goal, swp_entries);
+ n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
+ n_goal, swp_entries, order);
spin_unlock(&si->lock);
- if (n_ret || size == SWAPFILE_CLUSTER)
+ if (n_ret || size > 1)
goto check_out;
cond_resched();
@@ -1673,7 +1692,7 @@ swp_entry_t get_swap_page_of_type(int ty
/* 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))
+ if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0))
atomic_long_dec(&nr_swap_pages);
spin_unlock(&si->lock);
fail:
@@ -3127,7 +3146,7 @@ SYSCALL_DEFINE2(swapon, const char __use
p->flags |= SWP_SYNCHRONOUS_IO;
if (p->bdev && bdev_nonrot(p->bdev)) {
- int cpu;
+ int cpu, i;
unsigned long ci, nr_cluster;
p->flags |= SWP_SOLIDSTATE;
@@ -3165,7 +3184,8 @@ SYSCALL_DEFINE2(swapon, const char __use
struct percpu_cluster *cluster;
cluster = per_cpu_ptr(p->percpu_cluster, cpu);
- cluster->next = SWAP_NEXT_INVALID;
+ for (i = 0; i < SWAP_NR_ORDERS; i++)
+ cluster->next[i] = SWAP_NEXT_INVALID;
}
} else {
atomic_inc(&nr_rotate_swap);
_
Patches currently in -mm which might be from ryan.roberts@xxxxxxx are
selftests-mm-soft-dirty-should-fail-if-a-testcase-fails.patch
mm-fix-race-between-__split_huge_pmd_locked-and-gup-fast.patch
