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

1 files changed, 31 insertions, 38 deletions

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))