mm, pcp: reduce detecting time of consecutive high order page freeing

[ Upstream commit 6ccdcb6 ]
Conflict: none

In current PCP auto-tuning design, if the number of pages allocated is
much more than that of pages freed on a CPU, the PCP high may become the
maximal value even if the allocating/freeing depth is small, for example,
in the sender of network workloads.  If a CPU was used as sender
originally, then it is used as receiver after context switching, we need
to fill the whole PCP with maximal high before triggering PCP draining for
consecutive high order freeing.  This will hurt the performance of some
network workloads.

To solve the issue, in this patch, we will track the consecutive page
freeing with a counter in stead of relying on PCP draining.  So, we can
detect consecutive page freeing much earlier.

On a 2-socket Intel server with 128 logical CPU, we tested
SCTP_STREAM_MANY test case of netperf test suite with 64-pair processes.
With the patch, the network bandwidth improves 5.0%.  This restores the
performance drop caused by PCP auto-tuning.

Intel-SIG: commit 6ccdcb6 mm, pcp: reduce detecting time of consecutive high order page freeing.
Backport Auto-tune per-CPU pageset size.

Link: https://lkml.kernel.org/r/20231016053002.756205-10-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
[ Aubrey Li: amend commit log ]
Signed-off-by: Aubrey Li <aubrey.li@linux.intel.com>

Author: yhuang-intel

include/linux/mmzone.h

@@ -710,10 +710,10 @@ struct per_cpu_pages {
 	int batch;		/* chunk size for buddy add/remove */
 	u8 flags;		/* protected by pcp->lock */
 	u8 alloc_factor;	/* batch scaling factor during allocate */
-	u8 free_factor;		/* batch scaling factor during free */
 #ifdef CONFIG_NUMA
 	u8 expire;		/* When 0, remote pagesets are drained */
 #endif
+	short free_count;	/* consecutive free count */
 
 	/* Lists of pages, one per migrate type stored on the pcp-lists */
 	struct list_head lists[NR_PCP_LISTS];

mm/page_alloc.c

@@ -2394,13 +2394,10 @@ static int nr_pcp_free(struct per_cpu_pages *pcp, int batch, int high, bool free
 	max_nr_free = high - batch;
 
 	/*
-	 * Double the number of pages freed each time there is subsequent
-	 * freeing of pages without any allocation.
+	 * Increase the batch number to the number of the consecutive
+	 * freed pages to reduce zone lock contention.
 	 */
-	batch <<= pcp->free_factor;
-	if (batch <= max_nr_free && pcp->free_factor < CONFIG_PCP_BATCH_SCALE_MAX)
-		pcp->free_factor++;
-	batch = clamp(batch, min_nr_free, max_nr_free);
+	batch = clamp_t(int, pcp->free_count, min_nr_free, max_nr_free);
 
 	return batch;
 }
@@ -2428,18 +2425,22 @@ static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone,
 	 * stored on pcp lists
 	 */
 	if (test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags)) {
-		pcp->high = max(high - (batch << pcp->free_factor), high_min);
+		int free_count = max_t(int, pcp->free_count, batch);
+
+		pcp->high = max(high - free_count, high_min);
 		return min(batch << 2, pcp->high);
 	}
 
 	if (high_min == high_max)
 		return high;
 
 	if (test_bit(ZONE_BELOW_HIGH, &zone->flags)) {
-		pcp->high = max(high - (batch << pcp->free_factor), high_min);
+		int free_count = max_t(int, pcp->free_count, batch);
+
+		pcp->high = max(high - free_count, high_min);
 		high = max(pcp->count, high_min);
 	} else if (pcp->count >= high) {
-		int need_high = (batch << pcp->free_factor) + batch;
+		int need_high = pcp->free_count + batch;
 
 		/* pcp->high should be large enough to hold batch freed pages */
 		if (pcp->high < need_high)
@@ -2476,14 +2477,16 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp,
 	 * stops will be drained from vmstat refresh context.
 	 */
 	if (order && order <= PAGE_ALLOC_COSTLY_ORDER) {
-		free_high = (pcp->free_factor &&
+		free_high = (pcp->free_count >= batch &&
 			     (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) &&
 			     (!(pcp->flags & PCPF_FREE_HIGH_BATCH) ||
 			      pcp->count >= READ_ONCE(batch)));
 		pcp->flags |= PCPF_PREV_FREE_HIGH_ORDER;
 	} else if (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) {
 		pcp->flags &= ~PCPF_PREV_FREE_HIGH_ORDER;
 	}
+	if (pcp->free_count < (batch << CONFIG_PCP_BATCH_SCALE_MAX))
+		pcp->free_count += (1 << order);
 	high = nr_pcp_high(pcp, zone, batch, free_high);
 	if (pcp->count >= high) {
 		free_pcppages_bulk(zone, nr_pcp_free(pcp, batch, high, free_high),
@@ -2880,7 +2883,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
 	 * See nr_pcp_free() where free_factor is increased for subsequent
 	 * frees.
 	 */
-	pcp->free_factor >>= 1;
+	pcp->free_count >>= 1;
 	list = &pcp->lists[order_to_pindex(migratetype, order)];
 	page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list);
 	pcp_spin_unlock(pcp);
@@ -5508,7 +5511,7 @@ static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonesta
 	pcp->high_min = BOOT_PAGESET_HIGH;
 	pcp->high_max = BOOT_PAGESET_HIGH;
 	pcp->batch = BOOT_PAGESET_BATCH;
-	pcp->free_factor = 0;
+	pcp->free_count = 0;
 }
 
 static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long high_min,