Merge v6.18.40linux-rolling-lts

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

7 files changed, 103 insertions, 47 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 1e8f8eca318c..6769a9d6f16a 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1858,15 +1858,14 @@ static void compaction_free(struct folio *dst, unsigned long data)
 	int order = folio_order(dst);
 	struct page *page = &dst->page;
 
-	if (folio_put_testzero(dst)) {
-		free_pages_prepare(page, order);
+	if (folio_put_testzero(dst) && free_pages_prepare(page, order)) {
 		list_add(&dst->lru, &cc->freepages[order]);
 		cc->nr_freepages += 1 << order;
 	}
 	cc->nr_migratepages += 1 << order;
 	/*
-	 * someone else has referenced the page, we cannot take it back to our
-	 * free list.
+	 * someone else has referenced the page or free_pages_prepare() fails,
+	 * we cannot take it back to our free list.
 	 */
 }
 
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 00c80b7c8c3f..3e221c888e30 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1173,10 +1173,36 @@ static int damon_commit_target(
 	return 0;
 }
 
+/*
+ * damon_revert_target_commits() - revert unsuccessful target commits.
+ * @dst:	Commit destination context
+ * @failed:	Commit failed destination target
+ * @src:	Commit source context
+ *
+ * Revert target states that changed by damon_commit_target(), and cannot be
+ * cleaned up by the destination context's ops.cleanup_target().
+ */
+static void damon_revert_target_commits(struct damon_ctx *dst,
+		struct damon_target *failed, struct damon_ctx *src)
+{
+	struct damon_target *target;
+
+	if (!damon_target_has_pid(src))
+		return;
+	if (dst->ops.cleanup_target)
+		return;
+	damon_for_each_target(target, dst) {
+		if (target == failed)
+			return;
+		put_pid(target->pid);
+	}
+}
+
 static int damon_commit_targets(
 		struct damon_ctx *dst, struct damon_ctx *src)
 {
 	struct damon_target *dst_target, *next, *src_target, *new_target;
+	struct damon_target *failed;
 	int i = 0, j = 0, err;
 
 	damon_for_each_target_safe(dst_target, next, dst) {
@@ -1186,8 +1212,10 @@ static int damon_commit_targets(
 					dst_target, damon_target_has_pid(dst),
 					src_target, damon_target_has_pid(src),
 					src->min_sz_region);
-			if (err)
-				return err;
+			if (err) {
+				failed = dst_target;
+				goto out;
+			}
 		} else {
 			struct damos *s;
 
@@ -1201,22 +1229,29 @@ static int damon_commit_targets(
 		}
 	}
 
+	failed = NULL;
 	damon_for_each_target_safe(src_target, next, src) {
 		if (j++ < i)
 			continue;
 		new_target = damon_new_target();
-		if (!new_target)
-			return -ENOMEM;
+		if (!new_target) {
+			err = -ENOMEM;
+			goto out;
+		}
 		err = damon_commit_target(new_target, false,
 				src_target, damon_target_has_pid(src),
 				src->min_sz_region);
 		if (err) {
 			damon_destroy_target(new_target, NULL);
-			return err;
+			goto out;
 		}
 		damon_add_target(dst, new_target);
 	}
 	return 0;
+
+out:
+	damon_revert_target_commits(dst, failed, src);
+	return err;
 }
 
 /**
@@ -1255,8 +1290,10 @@ int damon_commit_ctx(struct damon_ctx *dst, struct damon_ctx *src)
 	 */
 	if (!damon_attrs_equals(&dst->attrs, &src->attrs)) {
 		err = damon_set_attrs(dst, &src->attrs);
-		if (err)
+		if (err) {
+			damon_revert_target_commits(dst, NULL, src);
 			return err;
+		}
 	}
 	dst->ops = src->ops;
 	dst->addr_unit = src->addr_unit;
@@ -1950,7 +1987,7 @@ static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t,
 		quota->charged_sz += sz;
 		if (quota->esz && quota->charged_sz >= quota->esz) {
 			quota->charge_target_from = t;
-			quota->charge_addr_from = r->ar.end + 1;
+			quota->charge_addr_from = r->ar.end;
 		}
 	}
 	if (s->action != DAMOS_STAT)
@@ -2200,6 +2237,8 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s)
 	if (!quota->total_charged_sz && !quota->charged_from) {
 		quota->charged_from = jiffies;
 		damos_set_effective_quota(quota, c);
+		if (trace_damos_esz_enabled())
+			damos_trace_esz(c, s, quota);
 	}
 
 	/* New charge window starts */
diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 4a432a07c5c3..adf60f672b8b 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -1615,22 +1615,19 @@ static int damon_sysfs_access_pattern_add_dirs(
 	err = damon_sysfs_access_pattern_add_range_dir(access_pattern,
 			&access_pattern->sz, "sz");
 	if (err)
-		goto put_sz_out;
+		return err;
 
 	err = damon_sysfs_access_pattern_add_range_dir(access_pattern,
 			&access_pattern->nr_accesses, "nr_accesses");
 	if (err)
-		goto put_nr_accesses_sz_out;
+		goto put_sz_out;
 
 	err = damon_sysfs_access_pattern_add_range_dir(access_pattern,
 			&access_pattern->age, "age");
 	if (err)
-		goto put_age_nr_accesses_sz_out;
+		goto put_nr_accesses_sz_out;
 	return 0;
 
-put_age_nr_accesses_sz_out:
-	kobject_put(&access_pattern->age->kobj);
-	access_pattern->age = NULL;
 put_nr_accesses_sz_out:
 	kobject_put(&access_pattern->nr_accesses->kobj);
 	access_pattern->nr_accesses = NULL;
@@ -2135,12 +2132,12 @@ static int damon_sysfs_scheme_add_dirs(struct damon_sysfs_scheme *scheme)
 		goto put_filters_watermarks_quotas_access_pattern_out;
 	err = damon_sysfs_scheme_set_tried_regions(scheme);
 	if (err)
-		goto put_tried_regions_out;
+		goto put_stats_out;
 	return 0;
 
-put_tried_regions_out:
-	kobject_put(&scheme->tried_regions->kobj);
-	scheme->tried_regions = NULL;
+put_stats_out:
+	kobject_put(&scheme->stats->kobj);
+	scheme->stats = NULL;
 put_filters_watermarks_quotas_access_pattern_out:
 	kobject_put(&scheme->ops_filters->kobj);
 	scheme->ops_filters = NULL;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9ac5df16b1a9..e0b36a634eb6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2959,6 +2959,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	map_chg_state map_chg;
 	int ret, idx;
 	struct hugetlb_cgroup *h_cg = NULL;
+	struct hugetlb_cgroup *h_cg_rsvd = NULL;
 	gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL;
 
 	idx = hstate_index(h);
@@ -3009,7 +3010,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	 */
 	if (map_chg) {
 		ret = hugetlb_cgroup_charge_cgroup_rsvd(
-			idx, pages_per_huge_page(h), &h_cg);
+			idx, pages_per_huge_page(h), &h_cg_rsvd);
 		if (ret)
 			goto out_subpool_put;
 	}
@@ -3051,7 +3052,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	 */
 	if (map_chg) {
 		hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h),
-						  h_cg, folio);
+						  h_cg_rsvd, folio);
 	}
 
 	spin_unlock_irq(&hugetlb_lock);
@@ -3106,7 +3107,7 @@ out_uncharge_cgroup:
 out_uncharge_cgroup_reservation:
 	if (map_chg)
 		hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h),
-						    h_cg);
+						    h_cg_rsvd);
 out_subpool_put:
 	/*
 	 * put page to subpool iff the quota of subpool's rsv_hpages is used
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 6a7714179c20..b7030bcd9b03 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1489,7 +1489,7 @@ static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group,
 		ret = create_memory_block_devices(cur_start, memblock_size, nid,
 						  params.altmap, group);
 		if (ret) {
-			arch_remove_memory(cur_start, memblock_size, NULL);
+			arch_remove_memory(cur_start, memblock_size, params.altmap);
 			kfree(params.altmap);
 			goto out;
 		}
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 7712d887b696..1b977fa9e8be 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -666,6 +666,20 @@ static inline void fixup_hashdist(void)
 static inline void fixup_hashdist(void) {}
 #endif /* CONFIG_NUMA */
 
+#ifdef CONFIG_ZONE_DEVICE
+static __meminit void pageblock_migratetype_init_range(unsigned long pfn,
+		unsigned long nr_pages, int migratetype)
+{
+	const unsigned long end = pfn + nr_pages;
+
+	for (pfn = pageblock_align(pfn); pfn < end; pfn += pageblock_nr_pages) {
+		init_pageblock_migratetype(pfn_to_page(pfn), migratetype, false);
+		if (IS_ALIGNED(pfn, PAGES_PER_SECTION))
+			cond_resched();
+	}
+}
+#endif
+
 /*
  * Initialize a reserved page unconditionally, finding its zone first.
  */
@@ -1029,21 +1043,6 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn,
 	page->zone_device_data = NULL;
 
 	/*
-	 * Mark the block movable so that blocks are reserved for
-	 * movable at startup. This will force kernel allocations
-	 * to reserve their blocks rather than leaking throughout
-	 * the address space during boot when many long-lived
-	 * kernel allocations are made.
-	 *
-	 * Please note that MEMINIT_HOTPLUG path doesn't clear memmap
-	 * because this is done early in section_activate()
-	 */
-	if (pageblock_aligned(pfn)) {
-		init_pageblock_migratetype(page, MIGRATE_MOVABLE, false);
-		cond_resched();
-	}
-
-	/*
 	 * ZONE_DEVICE pages other than MEMORY_TYPE_GENERIC are released
 	 * directly to the driver page allocator which will set the page count
 	 * to 1 when allocating the page.
@@ -1073,10 +1072,17 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn,
  * of how the sparse_vmemmap internals handle compound pages in the lack
  * of an altmap. See vmemmap_populate_compound_pages().
  */
-static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap,
+static inline unsigned long compound_nr_pages(unsigned long pfn,
+					      struct vmem_altmap *altmap,
 					      struct dev_pagemap *pgmap)
 {
-	if (!vmemmap_can_optimize(altmap, pgmap))
+	/*
+	 * If DAX memory is hot-plugged into an unoccupied subsection
+	 * of an early section, the unoptimized boot memmap is reused.
+	 * See section_activate().
+	 */
+	if (early_section(__pfn_to_section(pfn)) ||
+	    !vmemmap_can_optimize(altmap, pgmap))
 		return pgmap_vmemmap_nr(pgmap);
 
 	return VMEMMAP_RESERVE_NR * (PAGE_SIZE / sizeof(struct page));
@@ -1139,13 +1145,18 @@ void __ref memmap_init_zone_device(struct zone *zone,
 
 		__init_zone_device_page(page, pfn, zone_idx, nid, pgmap);
 
+		if (IS_ALIGNED(pfn, PAGES_PER_SECTION))
+			cond_resched();
+
 		if (pfns_per_compound == 1)
 			continue;
 
 		memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
-				     compound_nr_pages(altmap, pgmap));
+				     compound_nr_pages(pfn, altmap, pgmap));
 	}
 
+	pageblock_migratetype_init_range(start_pfn, nr_pages, MIGRATE_MOVABLE);
+
 	pr_debug("%s initialised %lu pages in %ums\n", __func__,
 		nr_pages, jiffies_to_msecs(jiffies - start));
 }
diff --git a/mm/numa_emulation.c b/mm/numa_emulation.c
index 703c8fa05048..55f26b22bb0b 100644
--- a/mm/numa_emulation.c
+++ b/mm/numa_emulation.c
@@ -214,7 +214,7 @@ static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes)
  * Sets up fake nodes of `size' interleaved over physical nodes ranging from
  * `addr' to `max_addr'.
  *
- * Returns zero on success or negative on error.
+ * Returns node ID of the next node on success or negative error code.
  */
 static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei,
 					      struct numa_meminfo *pi,
@@ -398,7 +398,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	 */
 	if (strchr(emu_cmdline, 'U')) {
 		unsigned long n;
-		int nid = 0;
+		int nid = 0, nr_created;
 
 		n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
 		ret = -1;
@@ -416,9 +416,18 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 					n, &pi.blk[0], nid);
 			if (ret < 0)
 				break;
-			if (ret < n) {
+
+			/*
+			 * If no memory was found for this physical node,
+			 * skip the under-allocation check.
+			 */
+			if (ret == nid)
+				continue;
+
+			nr_created = ret - nid;
+			if (nr_created < n) {
 				pr_info("%s: phys: %d only got %d of %ld nodes, failing\n",
-						__func__, i, ret, n);
+						__func__, i, nr_created, n);
 				ret = -1;
 				break;
 			}