Merge branch 'master' into mm-hotfixes-stable

8 files changed, 46 insertions, 29 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 1902cfe4cc4f..ffc3a2ba3a8c 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1258,6 +1258,9 @@ config LOCK_MM_AND_FIND_VMA
 	bool
 	depends on !STACK_GROWSUP
 
+config IOMMU_MM_DATA
+	bool
+
 source "mm/damon/Kconfig"
 
 endmenu
diff --git a/mm/compaction.c b/mm/compaction.c
index 27ada42924d5..4add68d40e8d 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -882,6 +882,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 
 	/* Time to isolate some pages for migration */
 	for (; low_pfn < end_pfn; low_pfn++) {
+		bool is_dirty, is_unevictable;
 
 		if (skip_on_failure && low_pfn >= next_skip_pfn) {
 			/*
@@ -1079,8 +1080,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!folio_test_lru(folio))
 			goto isolate_fail_put;
 
+		is_unevictable = folio_test_unevictable(folio);
+
 		/* Compaction might skip unevictable pages but CMA takes them */
-		if (!(mode & ISOLATE_UNEVICTABLE) && folio_test_unevictable(folio))
+		if (!(mode & ISOLATE_UNEVICTABLE) && is_unevictable)
 			goto isolate_fail_put;
 
 		/*
@@ -1092,26 +1095,42 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_writeback(folio))
 			goto isolate_fail_put;
 
-		if ((mode & ISOLATE_ASYNC_MIGRATE) && folio_test_dirty(folio)) {
-			bool migrate_dirty;
+		is_dirty = folio_test_dirty(folio);
+
+		if (((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) ||
+		    (mapping && is_unevictable)) {
+			bool migrate_dirty = true;
+			bool is_unmovable;
 
 			/*
 			 * Only folios without mappings or that have
-			 * a ->migrate_folio callback are possible to
-			 * migrate without blocking.  However, we may
-			 * be racing with truncation, which can free
-			 * the mapping.  Truncation holds the folio lock
-			 * until after the folio is removed from the page
-			 * cache so holding it ourselves is sufficient.
+			 * a ->migrate_folio callback are possible to migrate
+			 * without blocking.
+			 *
+			 * Folios from unmovable mappings are not migratable.
+			 *
+			 * However, we can be racing with truncation, which can
+			 * free the mapping that we need to check. Truncation
+			 * holds the folio lock until after the folio is removed
+			 * from the page so holding it ourselves is sufficient.
+			 *
+			 * To avoid locking the folio just to check unmovable,
+			 * assume every unmovable folio is also unevictable,
+			 * which is a cheaper test.  If our assumption goes
+			 * wrong, it's not a correctness bug, just potentially
+			 * wasted cycles.
 			 */
 			if (!folio_trylock(folio))
 				goto isolate_fail_put;
 
 			mapping = folio_mapping(folio);
-			migrate_dirty = !mapping ||
-					mapping->a_ops->migrate_folio;
+			if ((mode & ISOLATE_ASYNC_MIGRATE) && is_dirty) {
+				migrate_dirty = !mapping ||
+						mapping->a_ops->migrate_folio;
+			}
+			is_unmovable = mapping && mapping_unmovable(mapping);
 			folio_unlock(folio);
-			if (!migrate_dirty)
+			if (!migrate_dirty || is_unmovable)
 				goto isolate_fail_put;
 		}
 
diff --git a/mm/filemap.c b/mm/filemap.c
index ea49677c6338..750e779c23db 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2688,6 +2688,7 @@ int kiocb_write_and_wait(struct kiocb *iocb, size_t count)
 
 	return filemap_write_and_wait_range(mapping, pos, end);
 }
+EXPORT_SYMBOL_GPL(kiocb_write_and_wait);
 
 int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
 {
@@ -2715,6 +2716,7 @@ int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
 	return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
 					     end >> PAGE_SHIFT);
 }
+EXPORT_SYMBOL_GPL(kiocb_invalidate_pages);
 
 /**
  * generic_file_read_iter - generic filesystem read routine
diff --git a/mm/init-mm.c b/mm/init-mm.c
index cfd367822cdd..24c809379274 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -44,9 +44,6 @@ struct mm_struct init_mm = {
 #endif
 	.user_ns	= &init_user_ns,
 	.cpu_bitmap	= CPU_BITS_NONE,
-#ifdef CONFIG_IOMMU_SVA
-	.pasid		= IOMMU_PASID_INVALID,
-#endif
 	INIT_MM_CONTEXT(init_mm)
 };
 
diff --git a/mm/memblock.c b/mm/memblock.c
index 8c194d8afeec..abd92869874d 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1885,7 +1885,7 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
 	int mid = memblock_search(type, PFN_PHYS(pfn));
 
 	if (mid == -1)
-		return -1;
+		return NUMA_NO_NODE;
 
 	*start_pfn = PFN_DOWN(type->regions[mid].base);
 	*end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size);
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 8d5291add2bc..5462d9e3c84c 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -109,7 +109,7 @@ static struct demotion_nodes *node_demotion __read_mostly;
 static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms);
 
 static bool default_dram_perf_error;
-static struct node_hmem_attrs default_dram_perf;
+static struct access_coordinate default_dram_perf;
 static int default_dram_perf_ref_nid = NUMA_NO_NODE;
 static const char *default_dram_perf_ref_source;
 
@@ -601,15 +601,15 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype)
 }
 EXPORT_SYMBOL_GPL(clear_node_memory_type);
 
-static void dump_hmem_attrs(struct node_hmem_attrs *attrs, const char *prefix)
+static void dump_hmem_attrs(struct access_coordinate *coord, const char *prefix)
 {
 	pr_info(
 "%sread_latency: %u, write_latency: %u, read_bandwidth: %u, write_bandwidth: %u\n",
-		prefix, attrs->read_latency, attrs->write_latency,
-		attrs->read_bandwidth, attrs->write_bandwidth);
+		prefix, coord->read_latency, coord->write_latency,
+		coord->read_bandwidth, coord->write_bandwidth);
 }
 
-int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
+int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
 			     const char *source)
 {
 	int rc = 0;
@@ -666,7 +666,7 @@ out:
 	return rc;
 }
 
-int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist)
+int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
 {
 	if (default_dram_perf_error)
 		return -EIO;
diff --git a/mm/migrate.c b/mm/migrate.c
index bde8273cf15b..cc9f2bcd73b4 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -962,6 +962,8 @@ static int move_to_new_folio(struct folio *dst, struct folio *src,
 
 		if (!mapping)
 			rc = migrate_folio(mapping, dst, src, mode);
+		else if (mapping_unmovable(mapping))
+			rc = -EOPNOTSUPP;
 		else if (mapping->a_ops->migrate_folio)
 			/*
 			 * Most folios have a mapping and most filesystems
diff --git a/mm/percpu.c b/mm/percpu.c
index 7b97d31df767..4e11fc1e6def 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -3333,13 +3333,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
 		if (rc < 0)
 			panic("failed to map percpu area, err=%d\n", rc);
 
-		/*
-		 * FIXME: Archs with virtual cache should flush local
-		 * cache for the linear mapping here - something
-		 * equivalent to flush_cache_vmap() on the local cpu.
-		 * flush_cache_vmap() can't be used as most supporting
-		 * data structures are not set up yet.
-		 */
+		flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size);
 
 		/* copy static data */
 		memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);