memblock: stop using implicit alignment to SMP_CACHE_BYTES

When a memblock allocation APIs are called with align = 0, the alignment
is implicitly set to SMP_CACHE_BYTES.

Implicit alignment is done deep in the memblock allocator and it can
come as a surprise.  Not that such an alignment would be wrong even
when used incorrectly but it is better to be explicit for the sake of
clarity and the prinicple of the least surprise.

Replace all such uses of memblock APIs with the 'align' parameter
explicitly set to SMP_CACHE_BYTES and stop implicit alignment assignment
in the memblock internal allocation functions.

For the case when memblock APIs are used via helper functions, e.g.  like
iommu_arena_new_node() in Alpha, the helper functions were detected with
Coccinelle's help and then manually examined and updated where
appropriate.

The direct memblock APIs users were updated using the semantic patch below:

@@
expression size, min_addr, max_addr, nid;
@@
(
|
- memblock_alloc_try_nid_raw(size, 0, min_addr, max_addr, nid)
+ memblock_alloc_try_nid_raw(size, SMP_CACHE_BYTES, min_addr, max_addr,
nid)
|
- memblock_alloc_try_nid_nopanic(size, 0, min_addr, max_addr, nid)
+ memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, min_addr, max_addr,
nid)
|
- memblock_alloc_try_nid(size, 0, min_addr, max_addr, nid)
+ memblock_alloc_try_nid(size, SMP_CACHE_BYTES, min_addr, max_addr, nid)
|
- memblock_alloc(size, 0)
+ memblock_alloc(size, SMP_CACHE_BYTES)
|
- memblock_alloc_raw(size, 0)
+ memblock_alloc_raw(size, SMP_CACHE_BYTES)
|
- memblock_alloc_from(size, 0, min_addr)
+ memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr)
|
- memblock_alloc_nopanic(size, 0)
+ memblock_alloc_nopanic(size, SMP_CACHE_BYTES)
|
- memblock_alloc_low(size, 0)
+ memblock_alloc_low(size, SMP_CACHE_BYTES)
|
- memblock_alloc_low_nopanic(size, 0)
+ memblock_alloc_low_nopanic(size, SMP_CACHE_BYTES)
|
- memblock_alloc_from_nopanic(size, 0, min_addr)
+ memblock_alloc_from_nopanic(size, SMP_CACHE_BYTES, min_addr)
|
- memblock_alloc_node(size, 0, nid)
+ memblock_alloc_node(size, SMP_CACHE_BYTES, nid)
)

[mhocko@suse.com: changelog update]
[akpm@linux-foundation.org: coding-style fixes]
[rppt@linux.ibm.com: fix missed uses of implicit alignment]
  Link: http://lkml.kernel.org/r/20181016133656.GA10925@rapoport-lnx
Link: http://lkml.kernel.org/r/1538687224-17535-1-git-send-email-rppt@linux.vnet.ibm.com
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Suggested-by: Michal Hocko <mhocko@suse.com>
Acked-by: Paul Burton <paul.burton@mips.com>	[MIPS]
Acked-by: Michael Ellerman <mpe@ellerman.id.au>	[powerpc]
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Guan Xuetao <gxt@pku.edu.cn>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Richard Weinberger <richard@nod.at>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 26 insertions, 29 deletions

diff --git a/mm/memblock.c b/mm/memblock.c
index c655342569f8..839531133816 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1247,9 +1247,6 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
 {
 	phys_addr_t found;
 
-	if (!align)
-		align = SMP_CACHE_BYTES;
-
 	found = memblock_find_in_range_node(size, align, start, end, nid,
 					    flags);
 	if (found && !memblock_reserve(found, size)) {
@@ -1343,8 +1340,6 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali
  * The allocation is performed from memory region limited by
  * memblock.current_limit if @max_addr == %MEMBLOCK_ALLOC_ACCESSIBLE.
  *
- * The memory block is aligned on %SMP_CACHE_BYTES if @align == 0.
- *
  * The phys address of allocated boot memory block is converted to virtual and
  * allocated memory is reset to 0.
  *
@@ -1374,9 +1369,6 @@ static void * __init memblock_alloc_internal(
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, nid);
 
-	if (!align)
-		align = SMP_CACHE_BYTES;
-
 	if (max_addr > memblock.current_limit)
 		max_addr = memblock.current_limit;
 again:
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ef289fadec0e..a919ba5cb3c8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7710,9 +7710,11 @@ void *__init alloc_large_system_hash(const char *tablename,
 		size = bucketsize << log2qty;
 		if (flags & HASH_EARLY) {
 			if (flags & HASH_ZERO)
-				table = memblock_alloc_nopanic(size, 0);
+				table = memblock_alloc_nopanic(size,
+							       SMP_CACHE_BYTES);
 			else
-				table = memblock_alloc_raw(size, 0);
+				table = memblock_alloc_raw(size,
+							   SMP_CACHE_BYTES);
 		} else if (hashdist) {
 			table = __vmalloc(size, gfp_flags, PAGE_KERNEL);
 		} else {
diff --git a/mm/percpu.c b/mm/percpu.c
index 61cdbb3b3736..a6b74c6fe0be 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1102,8 +1102,8 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 
 	/* allocate chunk */
 	chunk = memblock_alloc(sizeof(struct pcpu_chunk) +
-				    BITS_TO_LONGS(region_size >> PAGE_SHIFT),
-				    0);
+			       BITS_TO_LONGS(region_size >> PAGE_SHIFT),
+			       SMP_CACHE_BYTES);
 
 	INIT_LIST_HEAD(&chunk->list);
 
@@ -1114,12 +1114,12 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 	chunk->nr_pages = region_size >> PAGE_SHIFT;
 	region_bits = pcpu_chunk_map_bits(chunk);
 
-	chunk->alloc_map = memblock_alloc(BITS_TO_LONGS(region_bits) *
-					       sizeof(chunk->alloc_map[0]), 0);
-	chunk->bound_map = memblock_alloc(BITS_TO_LONGS(region_bits + 1) *
-					       sizeof(chunk->bound_map[0]), 0);
-	chunk->md_blocks = memblock_alloc(pcpu_chunk_nr_blocks(chunk) *
-					       sizeof(chunk->md_blocks[0]), 0);
+	chunk->alloc_map = memblock_alloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]),
+					  SMP_CACHE_BYTES);
+	chunk->bound_map = memblock_alloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]),
+					  SMP_CACHE_BYTES);
+	chunk->md_blocks = memblock_alloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]),
+					  SMP_CACHE_BYTES);
 	pcpu_init_md_blocks(chunk);
 
 	/* manage populated page bitmap */
@@ -2075,12 +2075,14 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);
 
 	/* process group information and build config tables accordingly */
-	group_offsets = memblock_alloc(ai->nr_groups *
-					     sizeof(group_offsets[0]), 0);
-	group_sizes = memblock_alloc(ai->nr_groups *
-					   sizeof(group_sizes[0]), 0);
-	unit_map = memblock_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0);
-	unit_off = memblock_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0);
+	group_offsets = memblock_alloc(ai->nr_groups * sizeof(group_offsets[0]),
+				       SMP_CACHE_BYTES);
+	group_sizes = memblock_alloc(ai->nr_groups * sizeof(group_sizes[0]),
+				     SMP_CACHE_BYTES);
+	unit_map = memblock_alloc(nr_cpu_ids * sizeof(unit_map[0]),
+				  SMP_CACHE_BYTES);
+	unit_off = memblock_alloc(nr_cpu_ids * sizeof(unit_off[0]),
+				  SMP_CACHE_BYTES);
 
 	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
 		unit_map[cpu] = UINT_MAX;
@@ -2144,8 +2146,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	 * empty chunks.
 	 */
 	pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
-	pcpu_slot = memblock_alloc(
-			pcpu_nr_slots * sizeof(pcpu_slot[0]), 0);
+	pcpu_slot = memblock_alloc(pcpu_nr_slots * sizeof(pcpu_slot[0]),
+				   SMP_CACHE_BYTES);
 	for (i = 0; i < pcpu_nr_slots; i++)
 		INIT_LIST_HEAD(&pcpu_slot[i]);
 
@@ -2458,7 +2460,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 	size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
 	areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *));
 
-	areas = memblock_alloc_nopanic(areas_size, 0);
+	areas = memblock_alloc_nopanic(areas_size, SMP_CACHE_BYTES);
 	if (!areas) {
 		rc = -ENOMEM;
 		goto out_free;
@@ -2599,7 +2601,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
 	/* unaligned allocations can't be freed, round up to page size */
 	pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() *
 			       sizeof(pages[0]));
-	pages = memblock_alloc(pages_size, 0);
+	pages = memblock_alloc(pages_size, SMP_CACHE_BYTES);
 
 	/* allocate pages */
 	j = 0;
diff --git a/mm/sparse.c b/mm/sparse.c
index ab2ac45e0440..33307fc05c4d 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -68,7 +68,8 @@ static noinline struct mem_section __ref *sparse_index_alloc(int nid)
 	if (slab_is_available())
 		section = kzalloc_node(array_size, GFP_KERNEL, nid);
 	else
-		section = memblock_alloc_node(array_size, 0, nid);
+		section = memblock_alloc_node(array_size, SMP_CACHE_BYTES,
+					      nid);
 
 	return section;
 }