mm/mempolicy: use numa_node_id() instead of cpu_to_node()

Patch series "Allow migrate on protnone reference with MPOL_PREFERRED_MANY
policy:, v4.

This patchset is to optimize the cross-socket memory access with
MPOL_PREFERRED_MANY policy.

To test this patch we ran the following test on a 3 node system.
Node 0 - 2GB - Tier 1
Node 1 - 11GB - Tier 1
Node 6 - 10GB - Tier 2

Below changes are made to memcached to set the memory policy,
It select Node0 and Node1 as preferred nodes.

#include <numaif.h>
#include <numa.h>

unsigned long nodemask;
int ret;

nodemask = 0x03;
ret = set_mempolicy(MPOL_PREFERRED_MANY | MPOL_F_NUMA_BALANCING,
&nodemask, 10);
/* If MPOL_F_NUMA_BALANCING isn't supported,
* fall back to MPOL_PREFERRED_MANY */
if (ret < 0 && errno == EINVAL){
printf("set mem policy normal\n");
ret = set_mempolicy(MPOL_PREFERRED_MANY, &nodemask, 10);
}
if (ret < 0) {
perror("Failed to call set_mempolicy");
exit(-1);
}

Test Procedure:
===============
1. Make sure memory tiring and demotion are enabled.
2. Start memcached.

# ./memcached -b 100000 -m 204800 -u root -c 1000000 -t 7
-d -s "/tmp/memcached.sock"

3. Run memtier_benchmark to store 3200000 keys.

#./memtier_benchmark -S "/tmp/memcached.sock" --protocol=memcache_binary
--threads=1 --pipeline=1 --ratio=1:0 --key-pattern=S:S --key-minimum=1
--key-maximum=3200000 -n allkeys -c 1 -R -x 1 -d 1024

4. Start a memory eater on node 0 and 1. This will demote all memcached
pages to node 6.
5. Make sure all the memcached pages got demoted to lower tier by reading
/proc/<memcaced PID>/numa_maps.

# cat /proc/2771/numa_maps
---
default anon=1009 dirty=1009 active=0 N6=1009 kernelpagesize_kB=64
default anon=1009 dirty=1009 active=0 N6=1009 kernelpagesize_kB=64
---

6. Kill memory eater.
7. Read the pgpromote_success counter.
8. Start reading the keys by running memtier_benchmark.

#./memtier_benchmark -S "/tmp/memcached.sock" --protocol=memcache_binary
--pipeline=1 --distinct-client-seed --ratio=0:3 --key-pattern=R:R
--key-minimum=1 --key-maximum=3200000 -n allkeys
--threads=64 -c 1 -R -x 6

9. Read the pgpromote_success counter.

Test Results:
=============
Without Patch
------------------
1. pgpromote_success before test
Node 0: pgpromote_success 11
Node 1: pgpromote_success 140974

pgpromote_success after test
Node 0: pgpromote_success 11
Node 1: pgpromote_success 140974

2. Memtier-benchmark result.
AGGREGATED AVERAGE RESULTS (6 runs)
==================================================================
Type Ops/sec Hits/sec Misses/sec Avg. Latency p50 Latency
------------------------------------------------------------------
Sets 0.00 --- --- --- ---
Gets 305792.03 305791.93 0.10 0.18949 0.16700
Waits 0.00 --- --- --- ---
Totals 305792.03 305791.93 0.10 0.18949 0.16700

======================================
p99 Latency p99.9 Latency KB/sec
-------------------------------------
--- --- 0.00
0.44700 1.71100 11542.69
--- --- ---
0.44700 1.71100 11542.69

With Patch
---------------
1. pgpromote_success before test
Node 0: pgpromote_success 5
Node 1: pgpromote_success 89386

pgpromote_success after test
Node 0: pgpromote_success 57895
Node 1: pgpromote_success 141463

2. Memtier-benchmark result.
AGGREGATED AVERAGE RESULTS (6 runs)
====================================================================
Type Ops/sec Hits/sec Misses/sec Avg. Latency p50 Latency
--------------------------------------------------------------------
Sets 0.00 --- --- --- ---
Gets 521942.24 521942.07 0.17 0.11459 0.10300
Waits 0.00 --- --- --- ---
Totals 521942.24 521942.07 0.17 0.11459 0.10300

=======================================
p99 Latency p99.9 Latency KB/sec
---------------------------------------
--- --- 0.00
0.23100 0.31900 19701.68
--- --- ---
0.23100 0.31900 19701.68


Test Result Analysis:
=====================
1. With patch we could observe pages are getting promoted.
2. Memtier-benchmark results shows that, with the patch,
performance has increased more than 50%.

Ops/sec without fix - 305792.03
Ops/sec with fix - 521942.24


This patch (of 2):

Instead of using 'cpu_to_node()', we use 'numa_node_id()', which is
quicker. smp_processor_id is guaranteed to be stable in the
'mpol_misplaced()' function because it is called with ptl held.
lockdep_assert_held was added to ensure that.

No functional change in this patch.

[[e-mail]: add "* @vmf: structure describing the fault" comment]
Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Aneesh Kumar K.V (IBM) <[e-mail]>
Signed-off-by: Donet Tom <[e-mail]>
Cc: Andrea Arcangeli <[e-mail]>
Cc: Dan Williams <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Cc: Feng Tang <[e-mail]>
Cc: Huang, Ying <[e-mail]>
Cc: Hugh Dickins <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Johannes Weiner <[e-mail]>
Cc: Kefeng Wang <[e-mail]>
Cc: "Matthew Wilcox (Oracle)" <[e-mail]>
Cc: Mel Gorman <[e-mail]>
Cc: Michal Hocko <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Rik van Riel <[e-mail]>
Cc: Suren Baghdasaryan <[e-mail]>
Cc: Vlastimil Babka <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

include/linux/mempolicy.h

···
 /* Check if a vma is migratable */
 extern bool vma_migratable(struct vm_area_struct *vma);
 
-int mpol_misplaced(struct folio *, struct vm_area_struct *, unsigned long);
+int mpol_misplaced(struct folio *folio, struct vm_fault *vmf,
+					unsigned long addr);
 extern void mpol_put_task_policy(struct task_struct *);
 
 static inline bool mpol_is_preferred_many(struct mempolicy *pol)
···
 #endif
 
 static inline int mpol_misplaced(struct folio *folio,
-				 struct vm_area_struct *vma,
+				 struct vm_fault *vmf,
 				 unsigned long address)
 {
 	return -1; /* no node preference */

mm/huge_memory.c

···
 	 */
 	if (node_is_toptier(nid))
 		last_cpupid = folio_last_cpupid(folio);
-	target_nid = numa_migrate_prep(folio, vma, haddr, nid, &flags);
+	target_nid = numa_migrate_prep(folio, vmf, haddr, nid, &flags);
 	if (target_nid == NUMA_NO_NODE) {
 		folio_put(folio);
 		goto out_map;

mm/internal.h

···
 
 void __vunmap_range_noflush(unsigned long start, unsigned long end);
 
-int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma,
+int numa_migrate_prep(struct folio *folio, struct vm_fault *vmf,
 		      unsigned long addr, int page_nid, int *flags);
 
 void free_zone_device_page(struct page *page);

mm/memory.c

···
 	return ret;
 }
 
-int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma,
+int numa_migrate_prep(struct folio *folio, struct vm_fault *vmf,
 		      unsigned long addr, int page_nid, int *flags)
 {
+	struct vm_area_struct *vma = vmf->vma;
+
 	folio_get(folio);
 
 	/* Record the current PID acceesing VMA */
···
 		*flags |= TNF_FAULT_LOCAL;
 	}
 
-	return mpol_misplaced(folio, vma, addr);
+	return mpol_misplaced(folio, vmf, addr);
 }
 
 static vm_fault_t do_numa_page(struct vm_fault *vmf)
···
 		last_cpupid = (-1 & LAST_CPUPID_MASK);
 	else
 		last_cpupid = folio_last_cpupid(folio);
-	target_nid = numa_migrate_prep(folio, vma, vmf->address, nid, &flags);
+	target_nid = numa_migrate_prep(folio, vmf, vmf->address, nid, &flags);
 	if (target_nid == NUMA_NO_NODE) {
 		folio_put(folio);
 		goto out_map;

mm/mempolicy.c

···
  * mpol_misplaced - check whether current folio node is valid in policy
  *
  * @folio: folio to be checked
- * @vma: vm area where folio mapped
+ * @vmf: structure describing the fault
  * @addr: virtual address in @vma for shared policy lookup and interleave policy
  *
  * Lookup current policy node id for vma,addr and "compare to" folio's
···
  * Return: NUMA_NO_NODE if the page is in a node that is valid for this
  * policy, or a suitable node ID to allocate a replacement folio from.
  */
-int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma,
+int mpol_misplaced(struct folio *folio, struct vm_fault *vmf,
 		   unsigned long addr)
 {
 	struct mempolicy *pol;
 	pgoff_t ilx;
 	struct zoneref *z;
 	int curnid = folio_nid(folio);
+	struct vm_area_struct *vma = vmf->vma;
 	int thiscpu = raw_smp_processor_id();
-	int thisnid = cpu_to_node(thiscpu);
+	int thisnid = numa_node_id();
 	int polnid = NUMA_NO_NODE;
 	int ret = NUMA_NO_NODE;
 
+	/*
+	 * Make sure ptl is held so that we don't preempt and we
+	 * have a stable smp processor id
+	 */
+	lockdep_assert_held(vmf->ptl);
 	pol = get_vma_policy(vma, addr, folio_order(folio), &ilx);
 	if (!(pol->flags & MPOL_F_MOF))
 		goto out;
···
 		if (node_isset(curnid, pol->nodes))
 			goto out;
 		z = first_zones_zonelist(
-				node_zonelist(numa_node_id(), GFP_HIGHUSER),
+				node_zonelist(thisnid, GFP_HIGHUSER),
 				gfp_zone(GFP_HIGHUSER),
 				&pol->nodes);
 		polnid = zone_to_nid(z->zone);