mm: discard memblock data later

commit 3010f876 upstream.

There is existing use after free bug when deferred struct pages are
enabled:

The memblock_add() allocates memory for the memory array if more than
128 entries are needed.  See comment in e820__memblock_setup():

  * The bootstrap memblock region count maximum is 128 entries
  * (INIT_MEMBLOCK_REGIONS), but EFI might pass us more E820 entries
  * than that - so allow memblock resizing.

This memblock memory is freed here:
        free_low_memory_core_early()

We access the freed memblock.memory later in boot when deferred pages
are initialized in this path:

        deferred_init_memmap()
                for_each_mem_pfn_range()
                  __next_mem_pfn_range()
                    type = &memblock.memory;

One possible explanation for why this use-after-free hasn't been hit
before is that the limit of INIT_MEMBLOCK_REGIONS has never been
exceeded at least on systems where deferred struct pages were enabled.

Tested by reducing INIT_MEMBLOCK_REGIONS down to 4 from the current 128,
and verifying in qemu that this code is getting excuted and that the
freed pages are sane.

Link: http://lkml.kernel.org/r/1502485554-318703-2-git-send-email-pasha.tatashin@oracle.com
Fixes: 7e18adb4 ("mm: meminit: initialise remaining struct pages in parallel with kswapd")
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Reviewed-by: Steven Sistare <steven.sistare@oracle.com>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Reviewed-by: Bob Picco <bob.picco@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

include/linux/memblock.h

@@ -65,6 +65,7 @@ extern bool movable_node_enabled;
 #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
 #define __init_memblock __meminit
 #define __initdata_memblock __meminitdata
+void memblock_discard(void);
 #else
 #define __init_memblock
 #define __initdata_memblock
@@ -78,8 +79,6 @@ phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align,
 					int nid, ulong flags);
 phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
 				   phys_addr_t size, phys_addr_t align);
-phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr);
-phys_addr_t get_allocated_memblock_memory_regions_info(phys_addr_t *addr);
 void memblock_allow_resize(void);
 int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid);
 int memblock_add(phys_addr_t base, phys_addr_t size);
@@ -114,6 +113,9 @@ void __next_mem_range_rev(u64 *idx, int nid, ulong flags,
 void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start,
 				phys_addr_t *out_end);
 
+void __memblock_free_early(phys_addr_t base, phys_addr_t size);
+void __memblock_free_late(phys_addr_t base, phys_addr_t size);
+
 /**
  * for_each_mem_range - iterate through memblock areas from type_a and not
  * included in type_b. Or just type_a if type_b is NULL.

mm/memblock.c

@@ -288,31 +288,27 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
 }
 
 #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
-
-phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info(
-					phys_addr_t *addr)
+/**
+ * Discard memory and reserved arrays if they were allocated
+ */
+void __init memblock_discard(void)
 {
-	if (memblock.reserved.regions == memblock_reserved_init_regions)
-		return 0;
+	phys_addr_t addr, size;
 
-	*addr = __pa(memblock.reserved.regions);
-
-	return PAGE_ALIGN(sizeof(struct memblock_region) *
+	if (memblock.reserved.regions != memblock_reserved_init_regions) {
+		addr = __pa(memblock.reserved.regions);
+		size = PAGE_ALIGN(sizeof(struct memblock_region) *
 				  memblock.reserved.max);
-}
-
-phys_addr_t __init_memblock get_allocated_memblock_memory_regions_info(
-					phys_addr_t *addr)
-{
-	if (memblock.memory.regions == memblock_memory_init_regions)
-		return 0;
-
-	*addr = __pa(memblock.memory.regions);
+		__memblock_free_late(addr, size);
+	}
 
-	return PAGE_ALIGN(sizeof(struct memblock_region) *
+	if (memblock.memory.regions == memblock_memory_init_regions) {
+		addr = __pa(memblock.memory.regions);
+		size = PAGE_ALIGN(sizeof(struct memblock_region) *
 				  memblock.memory.max);
+		__memblock_free_late(addr, size);
+	}
 }
-
 #endif
 
 /**

mm/nobootmem.c

@@ -146,22 +146,6 @@ static unsigned long __init free_low_memory_core_early(void)
 				NULL)
 		count += __free_memory_core(start, end);
 
-#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
-	{
-		phys_addr_t size;
-
-		/* Free memblock.reserved array if it was allocated */
-		size = get_allocated_memblock_reserved_regions_info(&start);
-		if (size)
-			count += __free_memory_core(start, start + size);
-
-		/* Free memblock.memory array if it was allocated */
-		size = get_allocated_memblock_memory_regions_info(&start);
-		if (size)
-			count += __free_memory_core(start, start + size);
-	}
-#endif
-
 	return count;
 }
 

mm/page_alloc.c

@@ -1582,6 +1582,10 @@ void __init page_alloc_init_late(void)
 	/* Reinit limits that are based on free pages after the kernel is up */
 	files_maxfiles_init();
 #endif
+#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+	/* Discard memblock private memory */
+	memblock_discard();
+#endif
 
 	for_each_populated_zone(zone)
 		set_zone_contiguous(zone);