Merge tag 'memblock-v6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock

Pull memblock updates from Mike Rapoport:

 - 'reserve_mem' command line parameter to allow creation of named
   memory reservation at boot time.

   The driving use-case is to improve the ability of pstore to retain
   ramoops data across reboots.

 - cleanups and small improvements in memblock and mm_init

 - new tests cases in memblock test suite

* tag 'memblock-v6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock:
  memblock tests: fix implicit declaration of function 'numa_valid_node'
  memblock: Move late alloc warning down to phys alloc
  pstore/ramoops: Add ramoops.mem_name= command line option
  mm/memblock: Add "reserve_mem" to reserved named memory at boot up
  mm/mm_init.c: don't initialize page->lru again
  mm/mm_init.c: not always search next deferred_init_pfn from very beginning
  mm/mm_init.c: use deferred_init_mem_pfn_range_in_zone() to decide loop condition
  mm/mm_init.c: get the highest zone directly
  mm/mm_init.c: move nr_initialised reset down a bit
  mm/memblock: fix a typo in description of for_each_mem_region()
  mm/mm_init.c: use memblock_region_memory_base_pfn() to get startpfn
  mm/memblock: use PAGE_ALIGN_DOWN to get pgend in free_memmap
  mm/memblock: return true directly on finding overlap region
  memblock tests: add memblock_overlaps_region_checks
  mm/memblock: fix comment for memblock_isolate_range()
  memblock tests: add memblock_reserve_many_may_conflict_check()
  memblock tests: add memblock_reserve_all_locations_check()
  mm/memblock: remove empty dummy entry

2 files changed, 166 insertions, 54 deletions

diff --git a/mm/memblock.c b/mm/memblock.c
index e81fb68f7f88..3b9dc2d89b8a 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -114,12 +114,10 @@ static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS
 
 struct memblock memblock __initdata_memblock = {
 	.memory.regions		= memblock_memory_init_regions,
-	.memory.cnt		= 1,	/* empty dummy entry */
 	.memory.max		= INIT_MEMBLOCK_MEMORY_REGIONS,
 	.memory.name		= "memory",
 
 	.reserved.regions	= memblock_reserved_init_regions,
-	.reserved.cnt		= 1,	/* empty dummy entry */
 	.reserved.max		= INIT_MEMBLOCK_RESERVED_REGIONS,
 	.reserved.name		= "reserved",
 
@@ -130,7 +128,6 @@ struct memblock memblock __initdata_memblock = {
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
 struct memblock_type physmem = {
 	.regions		= memblock_physmem_init_regions,
-	.cnt			= 1,	/* empty dummy entry */
 	.max			= INIT_PHYSMEM_REGIONS,
 	.name			= "physmem",
 };
@@ -197,8 +194,8 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
 	for (i = 0; i < type->cnt; i++)
 		if (memblock_addrs_overlap(base, size, type->regions[i].base,
 					   type->regions[i].size))
-			break;
-	return i < type->cnt;
+			return true;
+	return false;
 }
 
 /**
@@ -356,7 +353,6 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
 	/* Special case for empty arrays */
 	if (type->cnt == 0) {
 		WARN_ON(type->total_size != 0);
-		type->cnt = 1;
 		type->regions[0].base = 0;
 		type->regions[0].size = 0;
 		type->regions[0].flags = 0;
@@ -600,12 +596,13 @@ static int __init_memblock memblock_add_range(struct memblock_type *type,
 
 	/* special case for empty array */
 	if (type->regions[0].size == 0) {
-		WARN_ON(type->cnt != 1 || type->total_size);
+		WARN_ON(type->cnt != 0 || type->total_size);
 		type->regions[0].base = base;
 		type->regions[0].size = size;
 		type->regions[0].flags = flags;
 		memblock_set_region_node(&type->regions[0], nid);
 		type->total_size = size;
+		type->cnt = 1;
 		return 0;
 	}
 
@@ -780,7 +777,8 @@ bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_byt
  * Walk @type and ensure that regions don't cross the boundaries defined by
  * [@base, @base + @size).  Crossing regions are split at the boundaries,
  * which may create at most two more regions.  The index of the first
- * region inside the range is returned in *@start_rgn and end in *@end_rgn.
+ * region inside the range is returned in *@start_rgn and the index of the
+ * first region after the range is returned in *@end_rgn.
  *
  * Return:
  * 0 on success, -errno on failure.
@@ -1441,6 +1439,17 @@ phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
 	enum memblock_flags flags = choose_memblock_flags();
 	phys_addr_t found;
 
+	/*
+	 * Detect any accidental use of these APIs after slab is ready, as at
+	 * this moment memblock may be deinitialized already and its
+	 * internal data may be destroyed (after execution of memblock_free_all)
+	 */
+	if (WARN_ON_ONCE(slab_is_available())) {
+		void *vaddr = kzalloc_node(size, GFP_NOWAIT, nid);
+
+		return vaddr ? virt_to_phys(vaddr) : 0;
+	}
+
 	if (!align) {
 		/* Can't use WARNs this early in boot on powerpc */
 		dump_stack();
@@ -1566,13 +1575,6 @@ static void * __init memblock_alloc_internal(
 {
 	phys_addr_t alloc;
 
-	/*
-	 * Detect any accidental use of these APIs after slab is ready, as at
-	 * this moment memblock may be deinitialized already and its
-	 * internal data may be destroyed (after execution of memblock_free_all)
-	 */
-	if (WARN_ON_ONCE(slab_is_available()))
-		return kzalloc_node(size, GFP_NOWAIT, nid);
 
 	if (max_addr > memblock.current_limit)
 		max_addr = memblock.current_limit;
@@ -2031,7 +2033,7 @@ static void __init free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 	 * downwards.
 	 */
 	pg = PAGE_ALIGN(__pa(start_pg));
-	pgend = __pa(end_pg) & PAGE_MASK;
+	pgend = PAGE_ALIGN_DOWN(__pa(end_pg));
 
 	/*
 	 * If there are free pages between these, free the section of the
@@ -2234,6 +2236,123 @@ void __init memblock_free_all(void)
 	totalram_pages_add(pages);
 }
 
+/* Keep a table to reserve named memory */
+#define RESERVE_MEM_MAX_ENTRIES		8
+#define RESERVE_MEM_NAME_SIZE		16
+struct reserve_mem_table {
+	char			name[RESERVE_MEM_NAME_SIZE];
+	phys_addr_t		start;
+	phys_addr_t		size;
+};
+static struct reserve_mem_table reserved_mem_table[RESERVE_MEM_MAX_ENTRIES];
+static int reserved_mem_count;
+
+/* Add wildcard region with a lookup name */
+static void __init reserved_mem_add(phys_addr_t start, phys_addr_t size,
+				   const char *name)
+{
+	struct reserve_mem_table *map;
+
+	map = &reserved_mem_table[reserved_mem_count++];
+	map->start = start;
+	map->size = size;
+	strscpy(map->name, name);
+}
+
+/**
+ * reserve_mem_find_by_name - Find reserved memory region with a given name
+ * @name: The name that is attached to a reserved memory region
+ * @start: If found, holds the start address
+ * @size: If found, holds the size of the address.
+ *
+ * @start and @size are only updated if @name is found.
+ *
+ * Returns: 1 if found or 0 if not found.
+ */
+int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size)
+{
+	struct reserve_mem_table *map;
+	int i;
+
+	for (i = 0; i < reserved_mem_count; i++) {
+		map = &reserved_mem_table[i];
+		if (!map->size)
+			continue;
+		if (strcmp(name, map->name) == 0) {
+			*start = map->start;
+			*size = map->size;
+			return 1;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(reserve_mem_find_by_name);
+
+/*
+ * Parse reserve_mem=nn:align:name
+ */
+static int __init reserve_mem(char *p)
+{
+	phys_addr_t start, size, align, tmp;
+	char *name;
+	char *oldp;
+	int len;
+
+	if (!p)
+		return -EINVAL;
+
+	/* Check if there's room for more reserved memory */
+	if (reserved_mem_count >= RESERVE_MEM_MAX_ENTRIES)
+		return -EBUSY;
+
+	oldp = p;
+	size = memparse(p, &p);
+	if (!size || p == oldp)
+		return -EINVAL;
+
+	if (*p != ':')
+		return -EINVAL;
+
+	align = memparse(p+1, &p);
+	if (*p != ':')
+		return -EINVAL;
+
+	/*
+	 * memblock_phys_alloc() doesn't like a zero size align,
+	 * but it is OK for this command to have it.
+	 */
+	if (align < SMP_CACHE_BYTES)
+		align = SMP_CACHE_BYTES;
+
+	name = p + 1;
+	len = strlen(name);
+
+	/* name needs to have length but not too big */
+	if (!len || len >= RESERVE_MEM_NAME_SIZE)
+		return -EINVAL;
+
+	/* Make sure that name has text */
+	for (p = name; *p; p++) {
+		if (!isspace(*p))
+			break;
+	}
+	if (!*p)
+		return -EINVAL;
+
+	/* Make sure the name is not already used */
+	if (reserve_mem_find_by_name(name, &start, &tmp))
+		return -EBUSY;
+
+	start = memblock_phys_alloc(size, align);
+	if (!start)
+		return -ENOMEM;
+
+	reserved_mem_add(start, size, name);
+
+	return 1;
+}
+__setup("reserve_mem=", reserve_mem);
+
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_ARCH_KEEP_MEMBLOCK)
 static const char * const flagname[] = {
 	[ilog2(MEMBLOCK_HOTPLUG)] = "HOTPLUG",
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 3ec04933f7fd..804df0309257 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -363,7 +363,7 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 
 			nid = memblock_get_region_node(r);
 
-			usable_startpfn = PFN_DOWN(r->base);
+			usable_startpfn = memblock_region_memory_base_pfn(r);
 			zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
 				min(usable_startpfn, zone_movable_pfn[nid]) :
 				usable_startpfn;
@@ -676,6 +676,14 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 
 	if (early_page_ext_enabled())
 		return false;
+
+	/* Always populate low zones for address-constrained allocations */
+	if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
+		return false;
+
+	if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX)
+		return true;
+
 	/*
 	 * prev_end_pfn static that contains the end of previous zone
 	 * No need to protect because called very early in boot before smp_init.
@@ -685,12 +693,6 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 		nr_initialised = 0;
 	}
 
-	/* Always populate low zones for address-constrained allocations */
-	if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
-		return false;
-
-	if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX)
-		return true;
 	/*
 	 * We start only with one section of pages, more pages are added as
 	 * needed until the rest of deferred pages are initialized.
@@ -758,9 +760,6 @@ void __meminit reserve_bootmem_region(phys_addr_t start,
 
 			init_reserved_page(start_pfn, nid);
 
-			/* Avoid false-positive PageTail() */
-			INIT_LIST_HEAD(&page->lru);
-
 			/*
 			 * no need for atomic set_bit because the struct
 			 * page is not visible yet so nobody should
@@ -2019,24 +2018,29 @@ static unsigned long  __init deferred_init_pages(struct zone *zone,
 }
 
 /*
- * This function is meant to pre-load the iterator for the zone init.
- * Specifically it walks through the ranges until we are caught up to the
- * first_init_pfn value and exits there. If we never encounter the value we
- * return false indicating there are no valid ranges left.
+ * This function is meant to pre-load the iterator for the zone init from
+ * a given point.
+ * Specifically it walks through the ranges starting with initial index
+ * passed to it until we are caught up to the first_init_pfn value and
+ * exits there. If we never encounter the value we return false indicating
+ * there are no valid ranges left.
  */
 static bool __init
 deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone,
 				    unsigned long *spfn, unsigned long *epfn,
 				    unsigned long first_init_pfn)
 {
-	u64 j;
+	u64 j = *i;
+
+	if (j == 0)
+		__next_mem_pfn_range_in_zone(&j, zone, spfn, epfn);
 
 	/*
 	 * Start out by walking through the ranges in this zone that have
 	 * already been initialized. We don't need to do anything with them
 	 * so we just need to flush them out of the system.
 	 */
-	for_each_free_mem_pfn_range_in_zone(j, zone, spfn, epfn) {
+	for_each_free_mem_pfn_range_in_zone_from(j, zone, spfn, epfn) {
 		if (*epfn <= first_init_pfn)
 			continue;
 		if (*spfn < first_init_pfn)
@@ -2108,7 +2112,7 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
 {
 	unsigned long spfn, epfn;
 	struct zone *zone = arg;
-	u64 i;
+	u64 i = 0;
 
 	deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn);
 
@@ -2138,8 +2142,8 @@ static int __init deferred_init_memmap(void *data)
 	unsigned long first_init_pfn, flags;
 	unsigned long start = jiffies;
 	struct zone *zone;
-	int zid, max_threads;
-	u64 i;
+	int max_threads;
+	u64 i = 0;
 
 	/* Bind memory initialisation thread to a local node if possible */
 	if (!cpumask_empty(cpumask))
@@ -2165,27 +2169,18 @@ static int __init deferred_init_memmap(void *data)
 	 */
 	pgdat_resize_unlock(pgdat, &flags);
 
-	/* Only the highest zone is deferred so find it */
-	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-		zone = pgdat->node_zones + zid;
-		if (first_init_pfn < zone_end_pfn(zone))
-			break;
-	}
-
-	/* If the zone is empty somebody else may have cleared out the zone */
-	if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
-						 first_init_pfn))
-		goto zone_empty;
+	/* Only the highest zone is deferred */
+	zone = pgdat->node_zones + pgdat->nr_zones - 1;
 
 	max_threads = deferred_page_init_max_threads(cpumask);
 
-	while (spfn < epfn) {
-		unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION);
+	while (deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, first_init_pfn)) {
+		first_init_pfn = ALIGN(epfn, PAGES_PER_SECTION);
 		struct padata_mt_job job = {
 			.thread_fn   = deferred_init_memmap_chunk,
 			.fn_arg      = zone,
 			.start       = spfn,
-			.size        = epfn_align - spfn,
+			.size        = first_init_pfn - spfn,
 			.align       = PAGES_PER_SECTION,
 			.min_chunk   = PAGES_PER_SECTION,
 			.max_threads = max_threads,
@@ -2193,12 +2188,10 @@ static int __init deferred_init_memmap(void *data)
 		};
 
 		padata_do_multithreaded(&job);
-		deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
-						    epfn_align);
 	}
-zone_empty:
+
 	/* Sanity check that the next zone really is unpopulated */
-	WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
+	WARN_ON(pgdat->nr_zones < MAX_NR_ZONES && populated_zone(++zone));
 
 	pr_info("node %d deferred pages initialised in %ums\n",
 		pgdat->node_id, jiffies_to_msecs(jiffies - start));
@@ -2225,7 +2218,7 @@ bool __init deferred_grow_zone(struct zone *zone, unsigned int order)
 	unsigned long first_deferred_pfn = pgdat->first_deferred_pfn;
 	unsigned long spfn, epfn, flags;
 	unsigned long nr_pages = 0;
-	u64 i;
+	u64 i = 0;
 
 	/* Only the last zone may have deferred pages */
 	if (zone_end_pfn(zone) != pgdat_end_pfn(pgdat))