Merge tag 'memblock-v5.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock

Pull memblock updates from Mike Rapoport:
 "Fix arm crashes caused by holes in the memory map.

  The coordination between freeing of unused memory map, pfn_valid() and
  core mm assumptions about validity of the memory map in various ranges
  was not designed for complex layouts of the physical memory with a lot
  of holes all over the place.

  Kefen Wang reported crashes in move_freepages() on a system with the
  following memory layout [1]:

	node 0: [mem 0x0000000080a00000-0x00000000855fffff]
	node 0: [mem 0x0000000086a00000-0x0000000087dfffff]
	node 0: [mem 0x000000008bd00000-0x000000008c4fffff]
	node 0: [mem 0x000000008e300000-0x000000008ecfffff]
	node 0: [mem 0x0000000090d00000-0x00000000bfffffff]
	node 0: [mem 0x00000000cc000000-0x00000000dc9fffff]
	node 0: [mem 0x00000000de700000-0x00000000de9fffff]
	node 0: [mem 0x00000000e0800000-0x00000000e0bfffff]
	node 0: [mem 0x00000000f4b00000-0x00000000f6ffffff]
	node 0: [mem 0x00000000fda00000-0x00000000ffffefff]

  These crashes can be mitigated by enabling CONFIG_HOLES_IN_ZONE on ARM
  and essentially turning pfn_valid_within() to pfn_valid() instead of
  having it hardwired to 1 on that architecture, but this would require
  to keep CONFIG_HOLES_IN_ZONE solely for this purpose.

  A cleaner approach is to update ARM's implementation of pfn_valid() to
  take into accounting rounding of the freed memory map to pageblock
  boundaries and make sure it returns true for PFNs that have memory map
  entries even if there is no physical memory backing those PFNs"

Link: https://lore.kernel.org/lkml/2a1592ad-bc9d-4664-fd19-f7448a37edc0@huawei.com [1]

* tag 'memblock-v5.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock:
  arm: extend pfn_valid to take into account freed memory map alignment
  memblock: ensure there is no overflow in memblock_overlaps_region()
  memblock: align freed memory map on pageblock boundaries with SPARSEMEM
  memblock: free_unused_memmap: use pageblock units instead of MAX_ORDER

2 files changed, 26 insertions, 13 deletions

diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 9d4744a632c6..6162a070a410 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -125,11 +125,22 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max_low,
 int pfn_valid(unsigned long pfn)
 {
 	phys_addr_t addr = __pfn_to_phys(pfn);
+	unsigned long pageblock_size = PAGE_SIZE * pageblock_nr_pages;
 
 	if (__phys_to_pfn(addr) != pfn)
 		return 0;
 
-	return memblock_is_map_memory(addr);
+	/*
+	 * If address less than pageblock_size bytes away from a present
+	 * memory chunk there still will be a memory map entry for it
+	 * because we round freed memory map to the pageblock boundaries.
+	 */
+	if (memblock_overlaps_region(&memblock.memory,
+				     ALIGN_DOWN(addr, pageblock_size),
+				     pageblock_size))
+		return 1;
+
+	return 0;
 }
 EXPORT_SYMBOL(pfn_valid);
 #endif
diff --git a/mm/memblock.c b/mm/memblock.c
index 3e4acbf03ab7..0041ff62c584 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -182,6 +182,8 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
 {
 	unsigned long i;
 
+	memblock_cap_size(base, &size);
+
 	for (i = 0; i < type->cnt; i++)
 		if (memblock_addrs_overlap(base, size, type->regions[i].base,
 					   type->regions[i].size))
@@ -1799,7 +1801,6 @@ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t siz
  */
 bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
 {
-	memblock_cap_size(base, &size);
 	return memblock_overlaps_region(&memblock.reserved, base, size);
 }
 
@@ -1946,14 +1947,13 @@ static void __init free_unused_memmap(void)
 		 * due to SPARSEMEM sections which aren't present.
 		 */
 		start = min(start, ALIGN(prev_end, PAGES_PER_SECTION));
-#else
+#endif
 		/*
-		 * Align down here since the VM subsystem insists that the
-		 * memmap entries are valid from the bank start aligned to
-		 * MAX_ORDER_NR_PAGES.
+		 * Align down here since many operations in VM subsystem
+		 * presume that there are no holes in the memory map inside
+		 * a pageblock
 		 */
-		start = round_down(start, MAX_ORDER_NR_PAGES);
-#endif
+		start = round_down(start, pageblock_nr_pages);
 
 		/*
 		 * If we had a previous bank, and there is a space
@@ -1963,16 +1963,18 @@ static void __init free_unused_memmap(void)
 			free_memmap(prev_end, start);
 
 		/*
-		 * Align up here since the VM subsystem insists that the
-		 * memmap entries are valid from the bank end aligned to
-		 * MAX_ORDER_NR_PAGES.
+		 * Align up here since many operations in VM subsystem
+		 * presume that there are no holes in the memory map inside
+		 * a pageblock
 		 */
-		prev_end = ALIGN(end, MAX_ORDER_NR_PAGES);
+		prev_end = ALIGN(end, pageblock_nr_pages);
 	}
 
 #ifdef CONFIG_SPARSEMEM
-	if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION))
+	if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) {
+		prev_end = ALIGN(end, pageblock_nr_pages);
 		free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION));
+	}
 #endif
 }