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, 12 insertions, 7 deletions

diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 9a6603f8e409..91bd1e129379 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -361,9 +361,9 @@ static ia64_state_log_t ia64_state_log[IA64_MAX_LOG_TYPES];
 
 #define IA64_LOG_ALLOCATE(it, size) \
 	{ia64_state_log[it].isl_log[IA64_LOG_CURR_INDEX(it)] = \
-		(ia64_err_rec_t *)memblock_alloc(size, 0); \
+		(ia64_err_rec_t *)memblock_alloc(size, SMP_CACHE_BYTES); \
 	ia64_state_log[it].isl_log[IA64_LOG_NEXT_INDEX(it)] = \
-		(ia64_err_rec_t *)memblock_alloc(size, 0);}
+		(ia64_err_rec_t *)memblock_alloc(size, SMP_CACHE_BYTES);}
 #define IA64_LOG_LOCK_INIT(it) spin_lock_init(&ia64_state_log[it].isl_lock)
 #define IA64_LOG_LOCK(it)      spin_lock_irqsave(&ia64_state_log[it].isl_lock, s)
 #define IA64_LOG_UNLOCK(it)    spin_unlock_irqrestore(&ia64_state_log[it].isl_lock,s)
diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c
index ab545daff7c3..9340bcb4f29c 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -59,8 +59,10 @@ struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
 void __init
 mmu_context_init (void)
 {
-	ia64_ctx.bitmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3, 0);
-	ia64_ctx.flushmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3, 0);
+	ia64_ctx.bitmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3,
+					 SMP_CACHE_BYTES);
+	ia64_ctx.flushmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3,
+					   SMP_CACHE_BYTES);
 }
 
 /*
diff --git a/arch/ia64/sn/kernel/io_common.c b/arch/ia64/sn/kernel/io_common.c
index 98f55220c67d..8df13d0d96fa 100644
--- a/arch/ia64/sn/kernel/io_common.c
+++ b/arch/ia64/sn/kernel/io_common.c
@@ -391,7 +391,9 @@ void __init hubdev_init_node(nodepda_t * npda, cnodeid_t node)
 	if (node >= num_online_nodes())	/* Headless/memless IO nodes */
 		node = 0;
 
-	hubdev_info = (struct hubdev_info *)memblock_alloc_node(size, 0, node);
+	hubdev_info = (struct hubdev_info *)memblock_alloc_node(size,
+								SMP_CACHE_BYTES,
+								node);
 
 	npda->pdinfo = (void *)hubdev_info;
 }
diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c
index 71ad6b0ccab4..a6d40a2c5bff 100644
--- a/arch/ia64/sn/kernel/setup.c
+++ b/arch/ia64/sn/kernel/setup.c
@@ -511,7 +511,8 @@ static void __init sn_init_pdas(char **cmdline_p)
 	 */
 	for_each_online_node(cnode) {
 		nodepdaindr[cnode] =
-		    memblock_alloc_node(sizeof(nodepda_t), 0, cnode);
+		    memblock_alloc_node(sizeof(nodepda_t), SMP_CACHE_BYTES,
+					cnode);
 		memset(nodepdaindr[cnode]->phys_cpuid, -1,
 		    sizeof(nodepdaindr[cnode]->phys_cpuid));
 		spin_lock_init(&nodepdaindr[cnode]->ptc_lock);
@@ -522,7 +523,7 @@ static void __init sn_init_pdas(char **cmdline_p)
 	 */
 	for (cnode = num_online_nodes(); cnode < num_cnodes; cnode++)
 		nodepdaindr[cnode] =
-		    memblock_alloc_node(sizeof(nodepda_t), 0, 0);
+		    memblock_alloc_node(sizeof(nodepda_t), SMP_CACHE_BYTES, 0);
 
 	/*
 	 * Now copy the array of nodepda pointers to each nodepda.