Received-SPF: pass (google.com: domain of linux-kernel+bounces-117249-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
From: Donet Tom <donettom@linux.ibm.com>
To: Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Cc: Aneesh Kumar <aneesh.kumar@kernel.org>, Huang Ying <ying.huang@intel.com>,
        Michal Hocko <mhocko@kernel.org>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Mel Gorman <mgorman@suse.de>, Feng Tang <feng.tang@intel.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>,
        Rik van Riel <riel@surriel.com>, Johannes Weiner <hannes@cmpxchg.org>,
        Matthew Wilcox <willy@infradead.org>, Vlastimil Babka <vbabka@suse.cz>,
        Dan Williams <dan.j.williams@intel.com>,
        Hugh Dickins <hughd@google.com>,
        Kefeng Wang <wangkefeng.wang@huawei.com>,
        Suren Baghdasaryan <surenb@google.com>,
        Donet Tom <donettom@linux.ibm.com>
Subject: [PATCH v4 1/2] mm/mempolicy: Use numa_node_id() instead of cpu_to_node()
Date: Mon, 25 Mar 2024 09:24:13 -0500
Message-Id: <6059f034f436734b472d066db69676fb3a459864.1711373653.git.donettom@linux.ibm.com>
In-Reply-To: <cover.1711373653.git.donettom@linux.ibm.com>
References: <cover.1711373653.git.donettom@linux.ibm.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

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.

Signed-off-by: Aneesh Kumar K.V (IBM) <aneesh.kumar@kernel.org>
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
---
 include/linux/mempolicy.h |  5 +++--
 mm/huge_memory.c          |  2 +-
 mm/internal.h             |  2 +-
 mm/memory.c               |  8 +++++---
 mm/mempolicy.c            | 14 ++++++++++----
 5 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 931b118336f4..1add16f21612 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -167,7 +167,8 @@ extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol);
 /* 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)
@@ -282,7 +283,7 @@ static inline int mpol_parse_str(char *str, struct mempolicy **mpol)
 #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 */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9859aa4f7553..b40bd9f3ead5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1754,7 +1754,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 	 */
 	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;
diff --git a/mm/internal.h b/mm/internal.h
index 7e486f2c502c..e0001c681c56 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1088,7 +1088,7 @@ void vunmap_range_noflush(unsigned long start, unsigned long end);
 
 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);
diff --git a/mm/memory.c b/mm/memory.c
index f2bc6dd15eb8..29e240978f45 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5033,9 +5033,11 @@ static vm_fault_t do_fault(struct vm_fault *vmf)
 	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 */
@@ -5047,7 +5049,7 @@ int numa_migrate_prep(struct folio *folio, struct vm_area_struct *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)
@@ -5121,7 +5123,7 @@ 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;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0fe77738d971..aa48376e2d34 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2718,7 +2718,7 @@ static void sp_free(struct sp_node *n)
  * 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
@@ -2728,18 +2728,24 @@ static void sp_free(struct sp_node *n)
  * 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;
@@ -2781,7 +2787,7 @@ int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma,
 		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);
-- 
2.39.3