Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 75 insertions, 47 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0fe77738d9..a1bf9aa15c 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -509,8 +509,8 @@ static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk)
 		qp->nr_failed++;
 		return;
 	}
-	folio = pfn_folio(pmd_pfn(*pmd));
-	if (is_huge_zero_page(&folio->page)) {
+	folio = pmd_folio(*pmd);
+	if (is_huge_zero_folio(folio)) {
 		walk->action = ACTION_CONTINUE;
 		return;
 	}
@@ -642,12 +642,11 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
 	 * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio.
 	 * Choosing not to migrate a shared folio is not counted as a failure.
 	 *
-	 * To check if the folio is shared, ideally we want to make sure
-	 * every page is mapped to the same process. Doing that is very
-	 * expensive, so check the estimated sharers of the folio instead.
+	 * See folio_likely_mapped_shared() on possible imprecision when we
+	 * cannot easily detect if a folio is shared.
 	 */
 	if ((flags & MPOL_MF_MOVE_ALL) ||
-	    (folio_estimated_sharers(folio) == 1 && !hugetlb_pmd_shared(pte)))
+	    (!folio_likely_mapped_shared(folio) && !hugetlb_pmd_shared(pte)))
 		if (!isolate_hugetlb(folio, qp->pagelist))
 			qp->nr_failed++;
 unlock:
@@ -1032,11 +1031,10 @@ static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist,
 	 * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio.
 	 * Choosing not to migrate a shared folio is not counted as a failure.
 	 *
-	 * To check if the folio is shared, ideally we want to make sure
-	 * every page is mapped to the same process. Doing that is very
-	 * expensive, so check the estimated sharers of the folio instead.
+	 * See folio_likely_mapped_shared() on possible imprecision when we
+	 * cannot easily detect if a folio is shared.
 	 */
-	if ((flags & MPOL_MF_MOVE_ALL) || folio_estimated_sharers(folio) == 1) {
+	if ((flags & MPOL_MF_MOVE_ALL) || !folio_likely_mapped_shared(folio)) {
 		if (folio_isolate_lru(folio)) {
 			list_add_tail(&folio->lru, foliolist);
 			node_stat_mod_folio(folio,
@@ -1070,6 +1068,7 @@ static long migrate_to_node(struct mm_struct *mm, int source, int dest,
 	struct migration_target_control mtc = {
 		.nid = dest,
 		.gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE,
+		.reason = MR_SYSCALL,
 	};
 
 	nodes_clear(nmask);
@@ -1227,7 +1226,8 @@ static struct folio *alloc_migration_target_by_mpol(struct folio *src,
 		h = folio_hstate(src);
 		gfp = htlb_alloc_mask(h);
 		nodemask = policy_nodemask(gfp, pol, ilx, &nid);
-		return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp);
+		return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp,
+				htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND));
 	}
 
 	if (folio_test_large(src))
@@ -1504,9 +1504,10 @@ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags)
 	if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES))
 		return -EINVAL;
 	if (*flags & MPOL_F_NUMA_BALANCING) {
-		if (*mode != MPOL_BIND)
+		if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY)
+			*flags |= (MPOL_F_MOF | MPOL_F_MORON);
+		else
 			return -EINVAL;
-		*flags |= (MPOL_F_MOF | MPOL_F_MORON);
 	}
 	return 0;
 }
@@ -2200,9 +2201,9 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
 	 */
 	preferred_gfp = gfp | __GFP_NOWARN;
 	preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
-	page = __alloc_pages(preferred_gfp, order, nid, nodemask);
+	page = __alloc_pages_noprof(preferred_gfp, order, nid, nodemask);
 	if (!page)
-		page = __alloc_pages(gfp, order, nid, NULL);
+		page = __alloc_pages_noprof(gfp, order, nid, NULL);
 
 	return page;
 }
@@ -2217,7 +2218,7 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
  *
  * Return: The page on success or NULL if allocation fails.
  */
-struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order,
+struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order,
 		struct mempolicy *pol, pgoff_t ilx, int nid)
 {
 	nodemask_t *nodemask;
@@ -2248,7 +2249,7 @@ struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order,
 			 * First, try to allocate THP only on local node, but
 			 * don't reclaim unnecessarily, just compact.
 			 */
-			page = __alloc_pages_node(nid,
+			page = __alloc_pages_node_noprof(nid,
 				gfp | __GFP_THISNODE | __GFP_NORETRY, order);
 			if (page || !(gfp & __GFP_DIRECT_RECLAIM))
 				return page;
@@ -2261,7 +2262,7 @@ struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order,
 		}
 	}
 
-	page = __alloc_pages(gfp, order, nid, nodemask);
+	page = __alloc_pages_noprof(gfp, order, nid, nodemask);
 
 	if (unlikely(pol->mode == MPOL_INTERLEAVE) && page) {
 		/* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */
@@ -2292,7 +2293,7 @@ struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order,
  *
  * Return: The folio on success or NULL if allocation fails.
  */
-struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
+struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma,
 		unsigned long addr, bool hugepage)
 {
 	struct mempolicy *pol;
@@ -2300,12 +2301,12 @@ struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
 	struct page *page;
 
 	pol = get_vma_policy(vma, addr, order, &ilx);
-	page = alloc_pages_mpol(gfp | __GFP_COMP, order,
-				pol, ilx, numa_node_id());
+	page = alloc_pages_mpol_noprof(gfp | __GFP_COMP, order,
+				       pol, ilx, numa_node_id());
 	mpol_cond_put(pol);
 	return page_rmappable_folio(page);
 }
-EXPORT_SYMBOL(vma_alloc_folio);
+EXPORT_SYMBOL(vma_alloc_folio_noprof);
 
 /**
  * alloc_pages - Allocate pages.
@@ -2321,7 +2322,7 @@ EXPORT_SYMBOL(vma_alloc_folio);
  * flags are used.
  * Return: The page on success or NULL if allocation fails.
  */
-struct page *alloc_pages(gfp_t gfp, unsigned int order)
+struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order)
 {
 	struct mempolicy *pol = &default_policy;
 
@@ -2332,16 +2333,16 @@ struct page *alloc_pages(gfp_t gfp, unsigned int order)
 	if (!in_interrupt() && !(gfp & __GFP_THISNODE))
 		pol = get_task_policy(current);
 
-	return alloc_pages_mpol(gfp, order,
-				pol, NO_INTERLEAVE_INDEX, numa_node_id());
+	return alloc_pages_mpol_noprof(gfp, order, pol, NO_INTERLEAVE_INDEX,
+				       numa_node_id());
 }
-EXPORT_SYMBOL(alloc_pages);
+EXPORT_SYMBOL(alloc_pages_noprof);
 
-struct folio *folio_alloc(gfp_t gfp, unsigned int order)
+struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order)
 {
-	return page_rmappable_folio(alloc_pages(gfp | __GFP_COMP, order));
+	return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order));
 }
-EXPORT_SYMBOL(folio_alloc);
+EXPORT_SYMBOL(folio_alloc_noprof);
 
 static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp,
 		struct mempolicy *pol, unsigned long nr_pages,
@@ -2360,13 +2361,13 @@ static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp,
 
 	for (i = 0; i < nodes; i++) {
 		if (delta) {
-			nr_allocated = __alloc_pages_bulk(gfp,
+			nr_allocated = alloc_pages_bulk_noprof(gfp,
 					interleave_nodes(pol), NULL,
 					nr_pages_per_node + 1, NULL,
 					page_array);
 			delta--;
 		} else {
-			nr_allocated = __alloc_pages_bulk(gfp,
+			nr_allocated = alloc_pages_bulk_noprof(gfp,
 					interleave_nodes(pol), NULL,
 					nr_pages_per_node, NULL, page_array);
 		}
@@ -2503,11 +2504,11 @@ static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
 	preferred_gfp = gfp | __GFP_NOWARN;
 	preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
 
-	nr_allocated  = __alloc_pages_bulk(preferred_gfp, nid, &pol->nodes,
+	nr_allocated  = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes,
 					   nr_pages, NULL, page_array);
 
 	if (nr_allocated < nr_pages)
-		nr_allocated += __alloc_pages_bulk(gfp, numa_node_id(), NULL,
+		nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL,
 				nr_pages - nr_allocated, NULL,
 				page_array + nr_allocated);
 	return nr_allocated;
@@ -2519,7 +2520,7 @@ static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
  * It can accelerate memory allocation especially interleaving
  * allocate memory.
  */
-unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp,
+unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp,
 		unsigned long nr_pages, struct page **page_array)
 {
 	struct mempolicy *pol = &default_policy;
@@ -2543,8 +2544,8 @@ unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp,
 
 	nid = numa_node_id();
 	nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid);
-	return __alloc_pages_bulk(gfp, nid, nodemask,
-				  nr_pages, NULL, page_array);
+	return alloc_pages_bulk_noprof(gfp, nid, nodemask,
+				       nr_pages, NULL, page_array);
 }
 
 int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
@@ -2718,7 +2719,7 @@ 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 +2729,24 @@ 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;
@@ -2764,15 +2771,26 @@ int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma,
 		break;
 
 	case MPOL_BIND:
-		/* Optimize placement among multiple nodes via NUMA balancing */
+	case MPOL_PREFERRED_MANY:
+		/*
+		 * Even though MPOL_PREFERRED_MANY can allocate pages outside
+		 * policy nodemask we don't allow numa migration to nodes
+		 * outside policy nodemask for now. This is done so that if we
+		 * want demotion to slow memory to happen, before allocating
+		 * from some DRAM node say 'x', we will end up using a
+		 * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario
+		 * we should not promote to node 'x' from slow memory node.
+		 */
 		if (pol->flags & MPOL_F_MORON) {
+			/*
+			 * Optimize placement among multiple nodes
+			 * via NUMA balancing
+			 */
 			if (node_isset(thisnid, pol->nodes))
 				break;
 			goto out;
 		}
-		fallthrough;
 
-	case MPOL_PREFERRED_MANY:
 		/*
 		 * use current page if in policy nodemask,
 		 * else select nearest allowed node, if any.
@@ -2781,7 +2799,7 @@ 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);
@@ -3275,8 +3293,9 @@ out:
  * @pol:  pointer to mempolicy to be formatted
  *
  * Convert @pol into a string.  If @buffer is too short, truncate the string.
- * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the
- * longest flag, "relative", and to display at least a few node ids.
+ * Recommend a @maxlen of at least 51 for the longest mode, "weighted
+ * interleave", plus the longest flag flags, "relative|balancing", and to
+ * display at least a few node ids.
  */
 void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 {
@@ -3285,7 +3304,10 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 	unsigned short mode = MPOL_DEFAULT;
 	unsigned short flags = 0;
 
-	if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) {
+	if (pol &&
+	    pol != &default_policy &&
+	    !(pol >= &preferred_node_policy[0] &&
+	      pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) {
 		mode = pol->mode;
 		flags = pol->flags;
 	}
@@ -3313,12 +3335,18 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
 		p += snprintf(p, buffer + maxlen - p, "=");
 
 		/*
-		 * Currently, the only defined flags are mutually exclusive
+		 * Static and relative are mutually exclusive.
 		 */
 		if (flags & MPOL_F_STATIC_NODES)
 			p += snprintf(p, buffer + maxlen - p, "static");
 		else if (flags & MPOL_F_RELATIVE_NODES)
 			p += snprintf(p, buffer + maxlen - p, "relative");
+
+		if (flags & MPOL_F_NUMA_BALANCING) {
+			if (!is_power_of_2(flags & MPOL_MODE_FLAGS))
+				p += snprintf(p, buffer + maxlen - p, "|");
+			p += snprintf(p, buffer + maxlen - p, "balancing");
+		}
 	}
 
 	if (!nodes_empty(nodes))