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

12 files changed, 542 insertions, 82 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 740ca2bc2822..0ca8452ea1ad 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5674,6 +5674,28 @@
 			them.  If <base> is less than 0x10000, the region
 			is assumed to be I/O ports; otherwise it is memory.
 
+	reserve_mem=	[RAM]
+			Format: nn[KNG]:<align>:<label>
+			Reserve physical memory and label it with a name that
+			other subsystems can use to access it. This is typically
+			used for systems that do not wipe the RAM, and this command
+			line will try to reserve the same physical memory on
+			soft reboots. Note, it is not guaranteed to be the same
+			location. For example, if anything about the system changes
+			or if booting a different kernel. It can also fail if KASLR
+			places the kernel at the location of where the RAM reservation
+			was from a previous boot, the new reservation will be at a
+			different location.
+			Any subsystem using this feature must add a way to verify
+			that the contents of the physical memory is from a previous
+			boot, as there may be cases where the memory will not be
+			located at the same location.
+
+			The format is size:align:label for example, to request
+			12 megabytes of 4096 alignment for ramoops:
+
+			reserve_mem=12M:4096:oops ramoops.mem_name=oops
+
 	reservetop=	[X86-32,EARLY]
 			Format: nn[KMG]
 			Reserves a hole at the top of the kernel virtual
diff --git a/Documentation/admin-guide/ramoops.rst b/Documentation/admin-guide/ramoops.rst
index e9f85142182d..6f534a707b2a 100644
--- a/Documentation/admin-guide/ramoops.rst
+++ b/Documentation/admin-guide/ramoops.rst
@@ -23,6 +23,8 @@ and type of the memory area are set using three variables:
   * ``mem_size`` for the size. The memory size will be rounded down to a
     power of two.
   * ``mem_type`` to specify if the memory type (default is pgprot_writecombine).
+  * ``mem_name`` to specify a memory region defined by ``reserve_mem`` command
+    line parameter.
 
 Typically the default value of ``mem_type=0`` should be used as that sets the pstore
 mapping to pgprot_writecombine. Setting ``mem_type=1`` attempts to use
@@ -118,6 +120,17 @@ Setting the ramoops parameters can be done in several different manners:
 	return ret;
   }
 
+ D. Using a region of memory reserved via ``reserve_mem`` command line
+    parameter. The address and size will be defined by the ``reserve_mem``
+    parameter. Note, that ``reserve_mem`` may not always allocate memory
+    in the same location, and cannot be relied upon. Testing will need
+    to be done, and it may not work on every machine, nor every kernel.
+    Consider this a "best effort" approach. The ``reserve_mem`` option
+    takes a size, alignment and name as arguments. The name is used
+    to map the memory to a label that can be retrieved by ramoops.
+
+	reserver_mem=2M:4096:oops  ramoops.mem_name=oops
+
 You can specify either RAM memory or peripheral devices' memory. However, when
 specifying RAM, be sure to reserve the memory by issuing memblock_reserve()
 very early in the architecture code, e.g.::
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index b1a455f42e93..4311fcbc84f2 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -50,6 +50,10 @@ module_param_hw(mem_address, ullong, other, 0400);
 MODULE_PARM_DESC(mem_address,
 		"start of reserved RAM used to store oops/panic logs");
 
+static char *mem_name;
+module_param_named(mem_name, mem_name, charp, 0400);
+MODULE_PARM_DESC(mem_name, "name of kernel param that holds addr");
+
 static ulong mem_size;
 module_param(mem_size, ulong, 0400);
 MODULE_PARM_DESC(mem_size,
@@ -914,6 +918,16 @@ static void __init ramoops_register_dummy(void)
 {
 	struct ramoops_platform_data pdata;
 
+	if (mem_name) {
+		phys_addr_t start;
+		phys_addr_t size;
+
+		if (reserve_mem_find_by_name(mem_name, &start, &size)) {
+			mem_address = start;
+			mem_size = size;
+		}
+	}
+
 	/*
 	 * Prepare a dummy platform data structure to carry the module
 	 * parameters. If mem_size isn't set, then there are no module
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index e2082240586d..45cac33334c8 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -299,25 +299,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
 				  unsigned long *out_spfn,
 				  unsigned long *out_epfn);
-/**
- * for_each_free_mem_pfn_range_in_zone - iterate through zone specific free
- * memblock areas
- * @i: u64 used as loop variable
- * @zone: zone in which all of the memory blocks reside
- * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
- * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
- *
- * Walks over free (memory && !reserved) areas of memblock in a specific
- * zone. Available once memblock and an empty zone is initialized. The main
- * assumption is that the zone start, end, and pgdat have been associated.
- * This way we can use the zone to determine NUMA node, and if a given part
- * of the memblock is valid for the zone.
- */
-#define for_each_free_mem_pfn_range_in_zone(i, zone, p_start, p_end)	\
-	for (i = 0,							\
-	     __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end);	\
-	     i != U64_MAX;					\
-	     __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end))
 
 /**
  * for_each_free_mem_pfn_range_in_zone_from - iterate through zone specific
@@ -565,7 +546,7 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
 }
 
 /**
- * for_each_mem_region - itereate over memory regions
+ * for_each_mem_region - iterate over memory regions
  * @region: loop variable
  */
 #define for_each_mem_region(region)					\
diff --git a/include/linux/mm.h b/include/linux/mm.h
index eb7c96d24ac0..fe49d432700e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4261,4 +4261,6 @@ static inline bool pfn_is_unaccepted_memory(unsigned long pfn)
 void vma_pgtable_walk_begin(struct vm_area_struct *vma);
 void vma_pgtable_walk_end(struct vm_area_struct *vma);
 
+int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size);
+
 #endif /* _LINUX_MM_H */
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))
diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h
index dc0fc7125bc3..cad4f2927983 100644
--- a/tools/include/linux/mm.h
+++ b/tools/include/linux/mm.h
@@ -12,6 +12,7 @@
 #define PHYS_ADDR_MAX	(~(phys_addr_t)0)
 
 #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
+#define PAGE_ALIGN_DOWN(addr) ALIGN_DOWN(addr, PAGE_SIZE)
 
 #define __va(x) ((void *)((unsigned long)(x)))
 #define __pa(x) ((unsigned long)(x))
diff --git a/tools/include/linux/numa.h b/tools/include/linux/numa.h
index 110b0e5d0fb0..c8b9369335e0 100644
--- a/tools/include/linux/numa.h
+++ b/tools/include/linux/numa.h
@@ -13,4 +13,9 @@
 
 #define	NUMA_NO_NODE	(-1)
 
+static inline bool numa_valid_node(int nid)
+{
+	return nid >= 0 && nid < MAX_NUMNODES;
+}
+
 #endif /* _LINUX_NUMA_H */
diff --git a/tools/testing/memblock/tests/basic_api.c b/tools/testing/memblock/tests/basic_api.c
index 57bf2688edfd..67503089e6a0 100644
--- a/tools/testing/memblock/tests/basic_api.c
+++ b/tools/testing/memblock/tests/basic_api.c
@@ -15,12 +15,12 @@ static int memblock_initialization_check(void)
 	PREFIX_PUSH();
 
 	ASSERT_NE(memblock.memory.regions, NULL);
-	ASSERT_EQ(memblock.memory.cnt, 1);
+	ASSERT_EQ(memblock.memory.cnt, 0);
 	ASSERT_EQ(memblock.memory.max, EXPECTED_MEMBLOCK_REGIONS);
 	ASSERT_EQ(strcmp(memblock.memory.name, "memory"), 0);
 
 	ASSERT_NE(memblock.reserved.regions, NULL);
-	ASSERT_EQ(memblock.reserved.cnt, 1);
+	ASSERT_EQ(memblock.reserved.cnt, 0);
 	ASSERT_EQ(memblock.memory.max, EXPECTED_MEMBLOCK_REGIONS);
 	ASSERT_EQ(strcmp(memblock.reserved.name, "reserved"), 0);
 
@@ -982,6 +982,262 @@ static int memblock_reserve_many_check(void)
 	return 0;
 }
 
+
+/*
+ * A test that trying to reserve the 129th memory block at all locations.
+ * Expect to trigger memblock_double_array() to double the
+ * memblock.memory.max, find a new valid memory as reserved.regions.
+ *
+ *  0               1               2                 128
+ *  +-------+       +-------+       +-------+         +-------+
+ *  |  32K  |       |  32K  |       |  32K  |   ...   |  32K  |
+ *  +-------+-------+-------+-------+-------+         +-------+
+ *          |<-32K->|       |<-32K->|
+ *
+ */
+/* Keep the gap so these memory region will not be merged. */
+#define MEMORY_BASE(idx) (SZ_128K + (MEM_SIZE * 2) * (idx))
+static int memblock_reserve_all_locations_check(void)
+{
+	int i, skip;
+	void *orig_region;
+	struct region r = {
+		.base = SZ_16K,
+		.size = SZ_16K,
+	};
+	phys_addr_t new_reserved_regions_size;
+
+	PREFIX_PUSH();
+
+	/* Reserve the 129th memory block for all possible positions*/
+	for (skip = 0; skip < INIT_MEMBLOCK_REGIONS + 1; skip++) {
+		reset_memblock_regions();
+		memblock_allow_resize();
+
+		/* Add a valid memory region used by double_array(). */
+		dummy_physical_memory_init();
+		memblock_add(dummy_physical_memory_base(), MEM_SIZE);
+
+		for (i = 0; i < INIT_MEMBLOCK_REGIONS + 1; i++) {
+			if (i == skip)
+				continue;
+
+			/* Reserve some fakes memory region to fulfill the memblock. */
+			memblock_reserve(MEMORY_BASE(i), MEM_SIZE);
+
+			if (i < skip) {
+				ASSERT_EQ(memblock.reserved.cnt, i + 1);
+				ASSERT_EQ(memblock.reserved.total_size, (i + 1) * MEM_SIZE);
+			} else {
+				ASSERT_EQ(memblock.reserved.cnt, i);
+				ASSERT_EQ(memblock.reserved.total_size, i * MEM_SIZE);
+			}
+		}
+
+		orig_region = memblock.reserved.regions;
+
+		/* This reserve the 129 memory_region, and makes it double array. */
+		memblock_reserve(MEMORY_BASE(skip), MEM_SIZE);
+
+		/*
+		 * This is the memory region size used by the doubled reserved.regions,
+		 * and it has been reserved due to it has been used. The size is used to
+		 * calculate the total_size that the memblock.reserved have now.
+		 */
+		new_reserved_regions_size = PAGE_ALIGN((INIT_MEMBLOCK_REGIONS * 2) *
+						sizeof(struct memblock_region));
+		/*
+		 * The double_array() will find a free memory region as the new
+		 * reserved.regions, and the used memory region will be reserved, so
+		 * there will be one more region exist in the reserved memblock. And the
+		 * one more reserved region's size is new_reserved_regions_size.
+		 */
+		ASSERT_EQ(memblock.reserved.cnt, INIT_MEMBLOCK_REGIONS + 2);
+		ASSERT_EQ(memblock.reserved.total_size, (INIT_MEMBLOCK_REGIONS + 1) * MEM_SIZE +
+							new_reserved_regions_size);
+		ASSERT_EQ(memblock.reserved.max, INIT_MEMBLOCK_REGIONS * 2);
+
+		/*
+		 * Now memblock_double_array() works fine. Let's check after the
+		 * double_array(), the memblock_reserve() still works as normal.
+		 */
+		memblock_reserve(r.base, r.size);
+		ASSERT_EQ(memblock.reserved.regions[0].base, r.base);
+		ASSERT_EQ(memblock.reserved.regions[0].size, r.size);
+
+		ASSERT_EQ(memblock.reserved.cnt, INIT_MEMBLOCK_REGIONS + 3);
+		ASSERT_EQ(memblock.reserved.total_size, (INIT_MEMBLOCK_REGIONS + 1) * MEM_SIZE +
+							new_reserved_regions_size +
+							r.size);
+		ASSERT_EQ(memblock.reserved.max, INIT_MEMBLOCK_REGIONS * 2);
+
+		dummy_physical_memory_cleanup();
+
+		/*
+		 * The current reserved.regions is occupying a range of memory that
+		 * allocated from dummy_physical_memory_init(). After free the memory,
+		 * we must not use it. So restore the origin memory region to make sure
+		 * the tests can run as normal and not affected by the double array.
+		 */
+		memblock.reserved.regions = orig_region;
+		memblock.reserved.cnt = INIT_MEMBLOCK_RESERVED_REGIONS;
+	}
+
+	test_pass_pop();
+
+	return 0;
+}
+
+/*
+ * A test that trying to reserve the 129th memory block at all locations.
+ * Expect to trigger memblock_double_array() to double the
+ * memblock.memory.max, find a new valid memory as reserved.regions. And make
+ * sure it doesn't conflict with the range we want to reserve.
+ *
+ * For example, we have 128 regions in reserved and now want to reserve
+ * the skipped one. Since reserved is full, memblock_double_array() would find
+ * an available range in memory for the new array. We intended to put two
+ * ranges in memory with one is the exact range of the skipped one. Before
+ * commit 48c3b583bbdd ("mm/memblock: fix overlapping allocation when doubling
+ * reserved array"), the new array would sits in the skipped range which is a
+ * conflict. The expected new array should be allocated from memory.regions[0].
+ *
+ *           0                               1
+ * memory    +-------+                       +-------+
+ *           |  32K  |                       |  32K  |
+ *           +-------+ ------+-------+-------+-------+
+ *                   |<-32K->|<-32K->|<-32K->|
+ *
+ *                           0               skipped           127
+ * reserved                  +-------+       .........         +-------+
+ *                           |  32K  |       .  32K  .   ...   |  32K  |
+ *                           +-------+-------+-------+         +-------+
+ *                                   |<-32K->|
+ *                                           ^
+ *                                           |
+ *                                           |
+ *                                           skipped one
+ */
+/* Keep the gap so these memory region will not be merged. */
+#define MEMORY_BASE_OFFSET(idx, offset) ((offset) + (MEM_SIZE * 2) * (idx))
+static int memblock_reserve_many_may_conflict_check(void)
+{
+	int i, skip;
+	void *orig_region;
+	struct region r = {
+		.base = SZ_16K,
+		.size = SZ_16K,
+	};
+	phys_addr_t new_reserved_regions_size;
+
+	/*
+	 *  0        1          129
+	 *  +---+    +---+      +---+
+	 *  |32K|    |32K|  ..  |32K|
+	 *  +---+    +---+      +---+
+	 *
+	 * Pre-allocate the range for 129 memory block + one range for double
+	 * memblock.reserved.regions at idx 0.
+	 */
+	dummy_physical_memory_init();
+	phys_addr_t memory_base = dummy_physical_memory_base();
+	phys_addr_t offset = PAGE_ALIGN(memory_base);
+
+	PREFIX_PUSH();
+
+	/* Reserve the 129th memory block for all possible positions*/
+	for (skip = 1; skip <= INIT_MEMBLOCK_REGIONS + 1; skip++) {
+		reset_memblock_regions();
+		memblock_allow_resize();
+
+		reset_memblock_attributes();
+		/* Add a valid memory region used by double_array(). */
+		memblock_add(MEMORY_BASE_OFFSET(0, offset), MEM_SIZE);
+		/*
+		 * Add a memory region which will be reserved as 129th memory
+		 * region. This is not expected to be used by double_array().
+		 */
+		memblock_add(MEMORY_BASE_OFFSET(skip, offset), MEM_SIZE);
+
+		for (i = 1; i <= INIT_MEMBLOCK_REGIONS + 1; i++) {
+			if (i == skip)
+				continue;
+
+			/* Reserve some fakes memory region to fulfill the memblock. */
+			memblock_reserve(MEMORY_BASE_OFFSET(i, offset), MEM_SIZE);
+
+			if (i < skip) {
+				ASSERT_EQ(memblock.reserved.cnt, i);
+				ASSERT_EQ(memblock.reserved.total_size, i * MEM_SIZE);
+			} else {
+				ASSERT_EQ(memblock.reserved.cnt, i - 1);
+				ASSERT_EQ(memblock.reserved.total_size, (i - 1) * MEM_SIZE);
+			}
+		}
+
+		orig_region = memblock.reserved.regions;
+
+		/* This reserve the 129 memory_region, and makes it double array. */
+		memblock_reserve(MEMORY_BASE_OFFSET(skip, offset), MEM_SIZE);
+
+		/*
+		 * This is the memory region size used by the doubled reserved.regions,
+		 * and it has been reserved due to it has been used. The size is used to
+		 * calculate the total_size that the memblock.reserved have now.
+		 */
+		new_reserved_regions_size = PAGE_ALIGN((INIT_MEMBLOCK_REGIONS * 2) *
+						sizeof(struct memblock_region));
+		/*
+		 * The double_array() will find a free memory region as the new
+		 * reserved.regions, and the used memory region will be reserved, so
+		 * there will be one more region exist in the reserved memblock. And the
+		 * one more reserved region's size is new_reserved_regions_size.
+		 */
+		ASSERT_EQ(memblock.reserved.cnt, INIT_MEMBLOCK_REGIONS + 2);
+		ASSERT_EQ(memblock.reserved.total_size, (INIT_MEMBLOCK_REGIONS + 1) * MEM_SIZE +
+							new_reserved_regions_size);
+		ASSERT_EQ(memblock.reserved.max, INIT_MEMBLOCK_REGIONS * 2);
+
+		/*
+		 * The first reserved region is allocated for double array
+		 * with the size of new_reserved_regions_size and the base to be
+		 * MEMORY_BASE_OFFSET(0, offset) + SZ_32K - new_reserved_regions_size
+		 */
+		ASSERT_EQ(memblock.reserved.regions[0].base + memblock.reserved.regions[0].size,
+			  MEMORY_BASE_OFFSET(0, offset) + SZ_32K);
+		ASSERT_EQ(memblock.reserved.regions[0].size, new_reserved_regions_size);
+
+		/*
+		 * Now memblock_double_array() works fine. Let's check after the
+		 * double_array(), the memblock_reserve() still works as normal.
+		 */
+		memblock_reserve(r.base, r.size);
+		ASSERT_EQ(memblock.reserved.regions[0].base, r.base);
+		ASSERT_EQ(memblock.reserved.regions[0].size, r.size);
+
+		ASSERT_EQ(memblock.reserved.cnt, INIT_MEMBLOCK_REGIONS + 3);
+		ASSERT_EQ(memblock.reserved.total_size, (INIT_MEMBLOCK_REGIONS + 1) * MEM_SIZE +
+							new_reserved_regions_size +
+							r.size);
+		ASSERT_EQ(memblock.reserved.max, INIT_MEMBLOCK_REGIONS * 2);
+
+		/*
+		 * The current reserved.regions is occupying a range of memory that
+		 * allocated from dummy_physical_memory_init(). After free the memory,
+		 * we must not use it. So restore the origin memory region to make sure
+		 * the tests can run as normal and not affected by the double array.
+		 */
+		memblock.reserved.regions = orig_region;
+		memblock.reserved.cnt = INIT_MEMBLOCK_RESERVED_REGIONS;
+	}
+
+	dummy_physical_memory_cleanup();
+
+	test_pass_pop();
+
+	return 0;
+}
+
 static int memblock_reserve_checks(void)
 {
 	prefix_reset();
@@ -997,6 +1253,8 @@ static int memblock_reserve_checks(void)
 	memblock_reserve_between_check();
 	memblock_reserve_near_max_check();
 	memblock_reserve_many_check();
+	memblock_reserve_all_locations_check();
+	memblock_reserve_many_may_conflict_check();
 
 	prefix_pop();
 
@@ -1295,7 +1553,7 @@ static int memblock_remove_only_region_check(void)
 	ASSERT_EQ(rgn->base, 0);
 	ASSERT_EQ(rgn->size, 0);
 
-	ASSERT_EQ(memblock.memory.cnt, 1);
+	ASSERT_EQ(memblock.memory.cnt, 0);
 	ASSERT_EQ(memblock.memory.total_size, 0);
 
 	test_pass_pop();
@@ -1723,7 +1981,7 @@ static int memblock_free_only_region_check(void)
 	ASSERT_EQ(rgn->base, 0);
 	ASSERT_EQ(rgn->size, 0);
 
-	ASSERT_EQ(memblock.reserved.cnt, 1);
+	ASSERT_EQ(memblock.reserved.cnt, 0);
 	ASSERT_EQ(memblock.reserved.total_size, 0);
 
 	test_pass_pop();
@@ -2129,6 +2387,53 @@ static int memblock_trim_memory_checks(void)
 	return 0;
 }
 
+static int memblock_overlaps_region_check(void)
+{
+	struct region r = {
+		.base = SZ_1G,
+		.size = SZ_4M
+	};
+
+	PREFIX_PUSH();
+
+	reset_memblock_regions();
+	memblock_add(r.base, r.size);
+
+	/* Far Away */
+	ASSERT_FALSE(memblock_overlaps_region(&memblock.memory, SZ_1M, SZ_1M));
+	ASSERT_FALSE(memblock_overlaps_region(&memblock.memory, SZ_2G, SZ_1M));
+
+	/* Neighbor */
+	ASSERT_FALSE(memblock_overlaps_region(&memblock.memory, SZ_1G - SZ_1M, SZ_1M));
+	ASSERT_FALSE(memblock_overlaps_region(&memblock.memory, SZ_1G + SZ_4M, SZ_1M));
+
+	/* Partial Overlap */
+	ASSERT_TRUE(memblock_overlaps_region(&memblock.memory, SZ_1G - SZ_1M, SZ_2M));
+	ASSERT_TRUE(memblock_overlaps_region(&memblock.memory, SZ_1G + SZ_2M, SZ_2M));
+
+	/* Totally Overlap */
+	ASSERT_TRUE(memblock_overlaps_region(&memblock.memory, SZ_1G, SZ_4M));
+	ASSERT_TRUE(memblock_overlaps_region(&memblock.memory, SZ_1G - SZ_2M, SZ_8M));
+	ASSERT_TRUE(memblock_overlaps_region(&memblock.memory, SZ_1G + SZ_1M, SZ_1M));
+
+	test_pass_pop();
+
+	return 0;
+}
+
+static int memblock_overlaps_region_checks(void)
+{
+	prefix_reset();
+	prefix_push("memblock_overlaps_region");
+	test_print("Running memblock_overlaps_region tests...\n");
+
+	memblock_overlaps_region_check();
+
+	prefix_pop();
+
+	return 0;
+}
+
 int memblock_basic_checks(void)
 {
 	memblock_initialization_check();
@@ -2138,6 +2443,7 @@ int memblock_basic_checks(void)
 	memblock_free_checks();
 	memblock_bottom_up_checks();
 	memblock_trim_memory_checks();
+	memblock_overlaps_region_checks();
 
 	return 0;
 }
diff --git a/tools/testing/memblock/tests/common.c b/tools/testing/memblock/tests/common.c
index f43b6f414983..3250c8e5124b 100644
--- a/tools/testing/memblock/tests/common.c
+++ b/tools/testing/memblock/tests/common.c
@@ -40,13 +40,13 @@ void reset_memblock_regions(void)
 {
 	memset(memblock.memory.regions, 0,
 	       memblock.memory.cnt * sizeof(struct memblock_region));
-	memblock.memory.cnt	= 1;
+	memblock.memory.cnt     = 0;
 	memblock.memory.max	= INIT_MEMBLOCK_REGIONS;
 	memblock.memory.total_size = 0;
 
 	memset(memblock.reserved.regions, 0,
 	       memblock.reserved.cnt * sizeof(struct memblock_region));
-	memblock.reserved.cnt	= 1;
+	memblock.reserved.cnt   = 0;
 	memblock.reserved.max	= INIT_MEMBLOCK_RESERVED_REGIONS;
 	memblock.reserved.total_size = 0;
 }
@@ -61,7 +61,7 @@ void reset_memblock_attributes(void)
 
 static inline void fill_memblock(void)
 {
-	memset(memory_block.base, 1, MEM_SIZE);
+	memset(memory_block.base, 1, PHYS_MEM_SIZE);
 }
 
 void setup_memblock(void)
@@ -103,7 +103,7 @@ void setup_numa_memblock(const unsigned int node_fracs[])
 
 void dummy_physical_memory_init(void)
 {
-	memory_block.base = malloc(MEM_SIZE);
+	memory_block.base = malloc(PHYS_MEM_SIZE);
 	assert(memory_block.base);
 	fill_memblock();
 }
diff --git a/tools/testing/memblock/tests/common.h b/tools/testing/memblock/tests/common.h
index b5ec59aa62d7..e1138e06c903 100644
--- a/tools/testing/memblock/tests/common.h
+++ b/tools/testing/memblock/tests/common.h
@@ -12,6 +12,7 @@
 #include <../selftests/kselftest.h>
 
 #define MEM_SIZE		SZ_32K
+#define PHYS_MEM_SIZE		SZ_16M
 #define NUMA_NODES		8
 
 #define INIT_MEMBLOCK_REGIONS			128
@@ -39,6 +40,9 @@ enum test_flags {
 	assert((_expected) == (_seen)); \
 } while (0)
 
+#define ASSERT_TRUE(_seen) ASSERT_EQ(true, _seen)
+#define ASSERT_FALSE(_seen) ASSERT_EQ(false, _seen)
+
 /**
  * ASSERT_NE():
  * Check the condition