1 files changed, 90 insertions, 126 deletions

diff --git a/mm/mm_init.c b/mm/mm_init.c
index b6a1fcf6e13a..f72b852bd5b8 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -24,6 +24,7 @@
 #include <linux/page_ext.h>
 #include <linux/pti.h>
 #include <linux/pgtable.h>
+#include <linux/stackdepot.h>
 #include <linux/swap.h>
 #include <linux/cma.h>
 #include <linux/crash_dump.h>
@@ -227,7 +228,6 @@ static unsigned long required_movablecore_percent __initdata;
 
 static unsigned long nr_kernel_pages __initdata;
 static unsigned long nr_all_pages __initdata;
-static unsigned long dma_reserve __initdata;
 
 static bool deferred_struct_pages __meminitdata;
 
@@ -1145,7 +1145,7 @@ static void __init adjust_zone_range_for_zone_movable(int nid,
  * Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
  * then all holes in the requested range will be accounted for.
  */
-unsigned long __init __absent_pages_in_range(int nid,
+static unsigned long __init __absent_pages_in_range(int nid,
 				unsigned long range_start_pfn,
 				unsigned long range_end_pfn)
 {
@@ -1266,6 +1266,30 @@ static void __init reset_memoryless_node_totalpages(struct pglist_data *pgdat)
 	pr_debug("On node %d totalpages: 0\n", pgdat->node_id);
 }
 
+static void __init calc_nr_kernel_pages(void)
+{
+	unsigned long start_pfn, end_pfn;
+	phys_addr_t start_addr, end_addr;
+	u64 u;
+#ifdef CONFIG_HIGHMEM
+	unsigned long high_zone_low = arch_zone_lowest_possible_pfn[ZONE_HIGHMEM];
+#endif
+
+	for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) {
+		start_pfn = PFN_UP(start_addr);
+		end_pfn   = PFN_DOWN(end_addr);
+
+		if (start_pfn < end_pfn) {
+			nr_all_pages += end_pfn - start_pfn;
+#ifdef CONFIG_HIGHMEM
+			start_pfn = clamp(start_pfn, 0, high_zone_low);
+			end_pfn = clamp(end_pfn, 0, high_zone_low);
+#endif
+			nr_kernel_pages += end_pfn - start_pfn;
+		}
+	}
+}
+
 static void __init calculate_node_totalpages(struct pglist_data *pgdat,
 						unsigned long node_start_pfn,
 						unsigned long node_end_pfn)
@@ -1309,26 +1333,6 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat,
 	pr_debug("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages);
 }
 
-static unsigned long __init calc_memmap_size(unsigned long spanned_pages,
-						unsigned long present_pages)
-{
-	unsigned long pages = spanned_pages;
-
-	/*
-	 * Provide a more accurate estimation if there are holes within
-	 * the zone and SPARSEMEM is in use. If there are holes within the
-	 * zone, each populated memory region may cost us one or two extra
-	 * memmap pages due to alignment because memmap pages for each
-	 * populated regions may not be naturally aligned on page boundary.
-	 * So the (present_pages >> 4) heuristic is a tradeoff for that.
-	 */
-	if (spanned_pages > present_pages + (present_pages >> 4) &&
-	    IS_ENABLED(CONFIG_SPARSEMEM))
-		pages = present_pages;
-
-	return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT;
-}
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static void pgdat_init_split_queue(struct pglist_data *pgdat)
 {
@@ -1543,15 +1547,6 @@ void __ref free_area_init_core_hotplug(struct pglist_data *pgdat)
 }
 #endif
 
-/*
- * Set up the zone data structures:
- *   - mark all pages reserved
- *   - mark all memory queues empty
- *   - clear the memory bitmaps
- *
- * NOTE: pgdat should get zeroed by caller.
- * NOTE: this function is only called during early init.
- */
 static void __init free_area_init_core(struct pglist_data *pgdat)
 {
 	enum zone_type j;
@@ -1562,47 +1557,13 @@ static void __init free_area_init_core(struct pglist_data *pgdat)
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
-		unsigned long size, freesize, memmap_pages;
-
-		size = zone->spanned_pages;
-		freesize = zone->present_pages;
-
-		/*
-		 * Adjust freesize so that it accounts for how much memory
-		 * is used by this zone for memmap. This affects the watermark
-		 * and per-cpu initialisations
-		 */
-		memmap_pages = calc_memmap_size(size, freesize);
-		if (!is_highmem_idx(j)) {
-			if (freesize >= memmap_pages) {
-				freesize -= memmap_pages;
-				if (memmap_pages)
-					pr_debug("  %s zone: %lu pages used for memmap\n",
-						 zone_names[j], memmap_pages);
-			} else
-				pr_warn("  %s zone: %lu memmap pages exceeds freesize %lu\n",
-					zone_names[j], memmap_pages, freesize);
-		}
-
-		/* Account for reserved pages */
-		if (j == 0 && freesize > dma_reserve) {
-			freesize -= dma_reserve;
-			pr_debug("  %s zone: %lu pages reserved\n", zone_names[0], dma_reserve);
-		}
-
-		if (!is_highmem_idx(j))
-			nr_kernel_pages += freesize;
-		/* Charge for highmem memmap if there are enough kernel pages */
-		else if (nr_kernel_pages > memmap_pages * 2)
-			nr_kernel_pages -= memmap_pages;
-		nr_all_pages += freesize;
+		unsigned long size = zone->spanned_pages;
 
 		/*
-		 * Set an approximate value for lowmem here, it will be adjusted
-		 * when the bootmem allocator frees pages into the buddy system.
-		 * And all highmem pages will be managed by the buddy system.
+		 * Initialize zone->managed_pages as 0 , it will be reset
+		 * when memblock allocator frees pages into buddy system.
 		 */
-		zone_init_internals(zone, j, nid, freesize);
+		zone_init_internals(zone, j, nid, zone->present_pages);
 
 		if (!size)
 			continue;
@@ -1875,30 +1836,26 @@ void __init free_area_init(unsigned long *max_zone_pfn)
 				panic("Cannot allocate %zuB for node %d.\n",
 				       sizeof(*pgdat), nid);
 			arch_refresh_nodedata(nid, pgdat);
-			free_area_init_node(nid);
-
-			/*
-			 * We do not want to confuse userspace by sysfs
-			 * files/directories for node without any memory
-			 * attached to it, so this node is not marked as
-			 * N_MEMORY and not marked online so that no sysfs
-			 * hierarchy will be created via register_one_node for
-			 * it. The pgdat will get fully initialized by
-			 * hotadd_init_pgdat() when memory is hotplugged into
-			 * this node.
-			 */
-			continue;
 		}
 
 		pgdat = NODE_DATA(nid);
 		free_area_init_node(nid);
 
-		/* Any memory on that node */
-		if (pgdat->node_present_pages)
+		/*
+		 * No sysfs hierarcy will be created via register_one_node()
+		 *for memory-less node because here it's not marked as N_MEMORY
+		 *and won't be set online later. The benefit is userspace
+		 *program won't be confused by sysfs files/directories of
+		 *memory-less node. The pgdat will get fully initialized by
+		 *hotadd_init_pgdat() when memory is hotplugged into this node.
+		 */
+		if (pgdat->node_present_pages) {
 			node_set_state(nid, N_MEMORY);
-		check_for_memory(pgdat);
+			check_for_memory(pgdat);
+		}
 	}
 
+	calc_nr_kernel_pages();
 	memmap_init();
 
 	/* disable hash distribution for systems with a single node */
@@ -2058,7 +2015,7 @@ static unsigned long  __init deferred_init_pages(struct zone *zone,
 		__init_single_page(page, pfn, zid, nid);
 		nr_pages++;
 	}
-	return (nr_pages);
+	return nr_pages;
 }
 
 /*
@@ -2260,10 +2217,6 @@ zone_empty:
  * Return true when zone was grown, otherwise return false. We return true even
  * when we grow less than requested, to let the caller decide if there are
  * enough pages to satisfy the allocation.
- *
- * Note: We use noinline because this function is needed only during boot, and
- * it is called from a __ref function _deferred_grow_zone. This way we are
- * making sure that it is not inlined into permanent text section.
  */
 bool __init deferred_grow_zone(struct zone *zone, unsigned int order)
 {
@@ -2413,17 +2366,6 @@ void __init page_alloc_init_late(void)
 	page_alloc_sysctl_init();
 }
 
-#ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES
-/*
- * Returns the number of pages that arch has reserved but
- * is not known to alloc_large_system_hash().
- */
-static unsigned long __init arch_reserved_kernel_pages(void)
-{
-	return 0;
-}
-#endif
-
 /*
  * Adaptive scale is meant to reduce sizes of hash tables on large memory
  * machines. As memory size is increased the scale is also increased but at
@@ -2466,7 +2408,6 @@ void *__init alloc_large_system_hash(const char *tablename,
 	if (!numentries) {
 		/* round applicable memory size up to nearest megabyte */
 		numentries = nr_kernel_pages;
-		numentries -= arch_reserved_kernel_pages();
 
 		/* It isn't necessary when PAGE_SIZE >= 1MB */
 		if (PAGE_SIZE < SZ_1M)
@@ -2548,26 +2489,9 @@ void *__init alloc_large_system_hash(const char *tablename,
 	return table;
 }
 
-/**
- * set_dma_reserve - set the specified number of pages reserved in the first zone
- * @new_dma_reserve: The number of pages to mark reserved
- *
- * The per-cpu batchsize and zone watermarks are determined by managed_pages.
- * In the DMA zone, a significant percentage may be consumed by kernel image
- * and other unfreeable allocations which can skew the watermarks badly. This
- * function may optionally be used to account for unfreeable pages in the
- * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and
- * smaller per-cpu batchsize.
- */
-void __init set_dma_reserve(unsigned long new_dma_reserve)
-{
-	dma_reserve = new_dma_reserve;
-}
-
 void __init memblock_free_pages(struct page *page, unsigned long pfn,
 							unsigned int order)
 {
-
 	if (IS_ENABLED(CONFIG_DEFERRED_STRUCT_PAGE_INIT)) {
 		int nid = early_pfn_to_nid(pfn);
 
@@ -2579,6 +2503,17 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn,
 		/* KMSAN will take care of these pages. */
 		return;
 	}
+
+	/* pages were reserved and not allocated */
+	if (mem_alloc_profiling_enabled()) {
+		union codetag_ref *ref = get_page_tag_ref(page);
+
+		if (ref) {
+			set_codetag_empty(ref);
+			put_page_tag_ref(ref);
+		}
+	}
+
 	__free_pages_core(page, order);
 }
 
@@ -2588,6 +2523,9 @@ EXPORT_SYMBOL(init_on_alloc);
 DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
 EXPORT_SYMBOL(init_on_free);
 
+DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free);
+EXPORT_SYMBOL(init_mlocked_on_free);
+
 static bool _init_on_alloc_enabled_early __read_mostly
 				= IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON);
 static int __init early_init_on_alloc(char *buf)
@@ -2605,6 +2543,14 @@ static int __init early_init_on_free(char *buf)
 }
 early_param("init_on_free", early_init_on_free);
 
+static bool _init_mlocked_on_free_enabled_early __read_mostly
+				= IS_ENABLED(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON);
+static int __init early_init_mlocked_on_free(char *buf)
+{
+	return kstrtobool(buf, &_init_mlocked_on_free_enabled_early);
+}
+early_param("init_mlocked_on_free", early_init_mlocked_on_free);
+
 DEFINE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled);
 
 /*
@@ -2632,12 +2578,21 @@ static void __init mem_debugging_and_hardening_init(void)
 	}
 #endif
 
-	if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) &&
+	if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early ||
+	    _init_mlocked_on_free_enabled_early) &&
 	    page_poisoning_requested) {
 		pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
-			"will take precedence over init_on_alloc and init_on_free\n");
+			"will take precedence over init_on_alloc, init_on_free "
+			"and init_mlocked_on_free\n");
 		_init_on_alloc_enabled_early = false;
 		_init_on_free_enabled_early = false;
+		_init_mlocked_on_free_enabled_early = false;
+	}
+
+	if (_init_mlocked_on_free_enabled_early && _init_on_free_enabled_early) {
+		pr_info("mem auto-init: init_on_free is on, "
+			"will take precedence over init_mlocked_on_free\n");
+		_init_mlocked_on_free_enabled_early = false;
 	}
 
 	if (_init_on_alloc_enabled_early) {
@@ -2654,9 +2609,17 @@ static void __init mem_debugging_and_hardening_init(void)
 		static_branch_disable(&init_on_free);
 	}
 
-	if (IS_ENABLED(CONFIG_KMSAN) &&
-	    (_init_on_alloc_enabled_early || _init_on_free_enabled_early))
-		pr_info("mem auto-init: please make sure init_on_alloc and init_on_free are disabled when running KMSAN\n");
+	if (_init_mlocked_on_free_enabled_early) {
+		want_check_pages = true;
+		static_branch_enable(&init_mlocked_on_free);
+	} else {
+		static_branch_disable(&init_mlocked_on_free);
+	}
+
+	if (IS_ENABLED(CONFIG_KMSAN) && (_init_on_alloc_enabled_early ||
+	    _init_on_free_enabled_early || _init_mlocked_on_free_enabled_early))
+		pr_info("mem auto-init: please make sure init_on_alloc, init_on_free and "
+			"init_mlocked_on_free are disabled when running KMSAN\n");
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	if (debug_pagealloc_enabled()) {
@@ -2695,9 +2658,10 @@ static void __init report_meminit(void)
 	else
 		stack = "off";
 
-	pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n",
+	pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s, mlocked free:%s\n",
 		stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off",
-		want_init_on_free() ? "on" : "off");
+		want_init_on_free() ? "on" : "off",
+		want_init_mlocked_on_free() ? "on" : "off");
 	if (want_init_on_free())
 		pr_info("mem auto-init: clearing system memory may take some time...\n");
 }