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>

37 files changed, 75 insertions, 55 deletions

diff --git a/arch/alpha/kernel/core_apecs.c b/arch/alpha/kernel/core_apecs.c
index 1bf3eef34c22..6df765ff2b10 100644
--- a/arch/alpha/kernel/core_apecs.c
+++ b/arch/alpha/kernel/core_apecs.c
@@ -346,7 +346,8 @@ apecs_init_arch(void)
 	 * Window 1 is direct access 1GB at 1GB
 	 * Window 2 is scatter-gather 8MB at 8MB (for isa)
 	 */
-	hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0);
+	hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000,
+				       SMP_CACHE_BYTES);
 	hose->sg_pci = NULL;
 	__direct_map_base = 0x40000000;
 	__direct_map_size = 0x40000000;
diff --git a/arch/alpha/kernel/core_lca.c b/arch/alpha/kernel/core_lca.c
index 81c0c43635b0..57e0750419f2 100644
--- a/arch/alpha/kernel/core_lca.c
+++ b/arch/alpha/kernel/core_lca.c
@@ -275,7 +275,8 @@ lca_init_arch(void)
 	 * Note that we do not try to save any of the DMA window CSRs
 	 * before setting them, since we cannot read those CSRs on LCA.
 	 */
-	hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0);
+	hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000,
+				       SMP_CACHE_BYTES);
 	hose->sg_pci = NULL;
 	__direct_map_base = 0x40000000;
 	__direct_map_size = 0x40000000;
diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c
index 8a568c4d8e81..c1d0c18c71ca 100644
--- a/arch/alpha/kernel/core_marvel.c
+++ b/arch/alpha/kernel/core_marvel.c
@@ -82,7 +82,7 @@ mk_resource_name(int pe, int port, char *str)
 	char *name;
 	
 	sprintf(tmp, "PCI %s PE %d PORT %d", str, pe, port);
-	name = memblock_alloc(strlen(tmp) + 1, 0);
+	name = memblock_alloc(strlen(tmp) + 1, SMP_CACHE_BYTES);
 	strcpy(name, tmp);
 
 	return name;
@@ -117,7 +117,7 @@ alloc_io7(unsigned int pe)
 		return NULL;
 	}
 
-	io7 = memblock_alloc(sizeof(*io7), 0);
+	io7 = memblock_alloc(sizeof(*io7), SMP_CACHE_BYTES);
 	io7->pe = pe;
 	raw_spin_lock_init(&io7->irq_lock);
 
diff --git a/arch/alpha/kernel/core_mcpcia.c b/arch/alpha/kernel/core_mcpcia.c
index b1549db54260..74b1d018124c 100644
--- a/arch/alpha/kernel/core_mcpcia.c
+++ b/arch/alpha/kernel/core_mcpcia.c
@@ -364,9 +364,11 @@ mcpcia_startup_hose(struct pci_controller *hose)
 	 * Window 1 is scatter-gather (up to) 1GB at 1GB (for pci)
 	 * Window 2 is direct access 2GB at 2GB
 	 */
-	hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0);
+	hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000,
+				       SMP_CACHE_BYTES);
 	hose->sg_pci = iommu_arena_new(hose, 0x40000000,
-				       size_for_memory(0x40000000), 0);
+				       size_for_memory(0x40000000),
+				       SMP_CACHE_BYTES);
 
 	__direct_map_base = 0x80000000;
 	__direct_map_size = 0x80000000;
diff --git a/arch/alpha/kernel/core_t2.c b/arch/alpha/kernel/core_t2.c
index 2c00b61ca379..98d5b6ff8a76 100644
--- a/arch/alpha/kernel/core_t2.c
+++ b/arch/alpha/kernel/core_t2.c
@@ -351,7 +351,7 @@ t2_sg_map_window2(struct pci_controller *hose,
 
 	/* Note we can only do 1 SG window, as the other is for direct, so
 	   do an ISA SG area, especially for the floppy. */
-	hose->sg_isa = iommu_arena_new(hose, base, length, 0);
+	hose->sg_isa = iommu_arena_new(hose, base, length, SMP_CACHE_BYTES);
 	hose->sg_pci = NULL;
 
 	temp = (base & 0xfff00000UL) | ((base + length - 1) >> 20);
diff --git a/arch/alpha/kernel/core_titan.c b/arch/alpha/kernel/core_titan.c
index 97551597581b..2a2820fb1be6 100644
--- a/arch/alpha/kernel/core_titan.c
+++ b/arch/alpha/kernel/core_titan.c
@@ -316,10 +316,12 @@ titan_init_one_pachip_port(titan_pachip_port *port, int index)
 	 * Window 1 is direct access 1GB at 2GB
 	 * Window 2 is scatter-gather 1GB at 3GB
 	 */
-	hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0);
+	hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000,
+				       SMP_CACHE_BYTES);
 	hose->sg_isa->align_entry = 8; /* 64KB for ISA */
 
-	hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x40000000, 0);
+	hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x40000000,
+				       SMP_CACHE_BYTES);
 	hose->sg_pci->align_entry = 4; /* Titan caches 4 PTEs at a time */
 
 	port->wsba[0].csr = hose->sg_isa->dma_base | 3;
diff --git a/arch/alpha/kernel/core_tsunami.c b/arch/alpha/kernel/core_tsunami.c
index f334b8928d72..fc1ab73f23de 100644
--- a/arch/alpha/kernel/core_tsunami.c
+++ b/arch/alpha/kernel/core_tsunami.c
@@ -319,12 +319,14 @@ tsunami_init_one_pchip(tsunami_pchip *pchip, int index)
 	 * NOTE: we need the align_entry settings for Acer devices on ES40,
 	 * specifically floppy and IDE when memory is larger than 2GB.
 	 */
-	hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0);
+	hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000,
+				       SMP_CACHE_BYTES);
 	/* Initially set for 4 PTEs, but will be overridden to 64K for ISA. */
         hose->sg_isa->align_entry = 4;
 
 	hose->sg_pci = iommu_arena_new(hose, 0x40000000,
-				       size_for_memory(0x40000000), 0);
+				       size_for_memory(0x40000000),
+				       SMP_CACHE_BYTES);
         hose->sg_pci->align_entry = 4; /* Tsunami caches 4 PTEs at a time */
 
 	__direct_map_base = 0x80000000;
diff --git a/arch/alpha/kernel/core_wildfire.c b/arch/alpha/kernel/core_wildfire.c
index cad36fc6ed7d..353c03d15442 100644
--- a/arch/alpha/kernel/core_wildfire.c
+++ b/arch/alpha/kernel/core_wildfire.c
@@ -111,8 +111,10 @@ wildfire_init_hose(int qbbno, int hoseno)
          * ??? We ought to scale window 3 memory.
          *
          */
-        hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0);
-        hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x08000000, 0);
+	hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000,
+				       SMP_CACHE_BYTES);
+	hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x08000000,
+				       SMP_CACHE_BYTES);
 
 	pci = WILDFIRE_pci(qbbno, hoseno);
 
diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c
index a9378ee0c2f1..091cff3c68fd 100644
--- a/arch/alpha/kernel/pci-noop.c
+++ b/arch/alpha/kernel/pci-noop.c
@@ -33,7 +33,7 @@ alloc_pci_controller(void)
 {
 	struct pci_controller *hose;
 
-	hose = memblock_alloc(sizeof(*hose), 0);
+	hose = memblock_alloc(sizeof(*hose), SMP_CACHE_BYTES);
 
 	*hose_tail = hose;
 	hose_tail = &hose->next;
@@ -44,7 +44,7 @@ alloc_pci_controller(void)
 struct resource * __init
 alloc_resource(void)
 {
-	return memblock_alloc(sizeof(struct resource), 0);
+	return memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
 }
 
 SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, bus,
diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c
index 13937e72d875..97098127df83 100644
--- a/arch/alpha/kernel/pci.c
+++ b/arch/alpha/kernel/pci.c
@@ -392,7 +392,7 @@ alloc_pci_controller(void)
 {
 	struct pci_controller *hose;
 
-	hose = memblock_alloc(sizeof(*hose), 0);
+	hose = memblock_alloc(sizeof(*hose), SMP_CACHE_BYTES);
 
 	*hose_tail = hose;
 	hose_tail = &hose->next;
@@ -403,7 +403,7 @@ alloc_pci_controller(void)
 struct resource * __init
 alloc_resource(void)
 {
-	return memblock_alloc(sizeof(struct resource), 0);
+	return memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
 }
 
 
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 82cf950bda2a..46e08e0d9181 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -79,7 +79,7 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base,
 		printk("%s: couldn't allocate arena from node %d\n"
 		       "    falling back to system-wide allocation\n",
 		       __func__, nid);
-		arena = memblock_alloc(sizeof(*arena), 0);
+		arena = memblock_alloc(sizeof(*arena), SMP_CACHE_BYTES);
 	}
 
 	arena->ptes = memblock_alloc_node(sizeof(*arena), align, nid);
@@ -92,7 +92,7 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base,
 
 #else /* CONFIG_DISCONTIGMEM */
 
-	arena = memblock_alloc(sizeof(*arena), 0);
+	arena = memblock_alloc(sizeof(*arena), SMP_CACHE_BYTES);
 	arena->ptes = memblock_alloc_from(mem_size, align, 0);
 
 #endif /* CONFIG_DISCONTIGMEM */
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 840a4adc69fc..ac7e08886863 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -856,7 +856,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 		 */
 		boot_alias_start = phys_to_idmap(start);
 		if (arm_has_idmap_alias() && boot_alias_start != IDMAP_INVALID_ADDR) {
-			res = memblock_alloc(sizeof(*res), 0);
+			res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES);
 			res->name = "System RAM (boot alias)";
 			res->start = boot_alias_start;
 			res->end = phys_to_idmap(end);
@@ -864,7 +864,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 			request_resource(&iomem_resource, res);
 		}
 
-		res = memblock_alloc(sizeof(*res), 0);
+		res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES);
 		res->name  = "System RAM";
 		res->start = start;
 		res->end = end;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index cd5732ab0cdf..083dcd9942ce 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -726,7 +726,7 @@ static int __init _setup_clkctrl_provider(struct device_node *np)
 	u64 size;
 	int i;
 
-	provider = memblock_alloc(sizeof(*provider), 0);
+	provider = memblock_alloc(sizeof(*provider), SMP_CACHE_BYTES);
 	if (!provider)
 		return -ENOMEM;
 
@@ -736,12 +736,14 @@ static int __init _setup_clkctrl_provider(struct device_node *np)
 		of_property_count_elems_of_size(np, "reg", sizeof(u32)) / 2;
 
 	provider->addr =
-		memblock_alloc(sizeof(void *) * provider->num_addrs, 0);
+		memblock_alloc(sizeof(void *) * provider->num_addrs,
+			       SMP_CACHE_BYTES);
 	if (!provider->addr)
 		return -ENOMEM;
 
 	provider->size =
-		memblock_alloc(sizeof(u32) * provider->num_addrs, 0);
+		memblock_alloc(sizeof(u32) * provider->num_addrs,
+			       SMP_CACHE_BYTES);
 	if (!provider->size)
 		return -ENOMEM;
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 7ce7306f1d75..953e316521fc 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -218,7 +218,7 @@ static void __init request_standard_resources(void)
 	num_standard_resources = memblock.memory.cnt;
 	standard_resources = memblock_alloc_low(num_standard_resources *
 					        sizeof(*standard_resources),
-					        0);
+					        SMP_CACHE_BYTES);
 
 	for_each_memblock(memory, region) {
 		res = &standard_resources[i++];
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.
diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c
index 8be8b750c629..4d64711d3d47 100644
--- a/arch/m68k/sun3/sun3dvma.c
+++ b/arch/m68k/sun3/sun3dvma.c
@@ -268,7 +268,7 @@ void __init dvma_init(void)
 	list_add(&(hole->list), &hole_list);
 
 	iommu_use = memblock_alloc(IOMMU_TOTAL_ENTRIES * sizeof(unsigned long),
-				   0);
+				   SMP_CACHE_BYTES);
 
 	dvma_unmap_iommu(DVMA_START, DVMA_SIZE);
 
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 8c14988f52f2..b17fd8aafd64 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -376,7 +376,7 @@ void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask)
 	if (mem_init_done)
 		p = kzalloc(size, mask);
 	else {
-		p = memblock_alloc(size, 0);
+		p = memblock_alloc(size, SMP_CACHE_BYTES);
 		if (p)
 			memset(p, 0, size);
 	}
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 41c1683761bb..ea09ed6a80a9 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -916,7 +916,7 @@ static void __init resource_init(void)
 		if (end >= HIGHMEM_START)
 			end = HIGHMEM_START - 1;
 
-		res = memblock_alloc(sizeof(struct resource), 0);
+		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
 
 		res->start = start;
 		res->end = end;
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index f331a0054b3a..913bfca09c4f 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -198,7 +198,7 @@ void __init allocate_paca_ptrs(void)
 	paca_nr_cpu_ids = nr_cpu_ids;
 
 	paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids;
-	paca_ptrs = __va(memblock_phys_alloc(paca_ptrs_size, 0));
+	paca_ptrs = __va(memblock_phys_alloc(paca_ptrs_size, SMP_CACHE_BYTES));
 	memset(paca_ptrs, 0x88, paca_ptrs_size);
 }
 
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 274bd1442dd9..d3f04f2d8249 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -203,7 +203,8 @@ pci_create_OF_bus_map(void)
 	struct property* of_prop;
 	struct device_node *dn;
 
-	of_prop = memblock_alloc(sizeof(struct property) + 256, 0);
+	of_prop = memblock_alloc(sizeof(struct property) + 256,
+				 SMP_CACHE_BYTES);
 	dn = of_find_node_by_path("/");
 	if (dn) {
 		memset(of_prop, -1, sizeof(struct property) + 256);
diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c
index 5b61704447c1..dedf88a76f58 100644
--- a/arch/powerpc/lib/alloc.c
+++ b/arch/powerpc/lib/alloc.c
@@ -14,7 +14,7 @@ void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask)
 	if (slab_is_available())
 		p = kzalloc(size, mask);
 	else {
-		p = memblock_alloc(size, 0);
+		p = memblock_alloc(size, SMP_CACHE_BYTES);
 	}
 	return p;
 }
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index 67b9d7b669a1..2faca46ad720 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -461,10 +461,11 @@ void __init mmu_context_init(void)
 	/*
 	 * Allocate the maps used by context management
 	 */
-	context_map = memblock_alloc(CTX_MAP_SIZE, 0);
-	context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1), 0);
+	context_map = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES);
+	context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1),
+				    SMP_CACHE_BYTES);
 #ifdef CONFIG_SMP
-	stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, 0);
+	stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES);
 
 	cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE,
 				  "powerpc/mmu/ctx:prepare",
diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c
index f3391be7c762..ae54d7fe68f3 100644
--- a/arch/powerpc/platforms/powermac/nvram.c
+++ b/arch/powerpc/platforms/powermac/nvram.c
@@ -513,7 +513,7 @@ static int __init core99_nvram_setup(struct device_node *dp, unsigned long addr)
 		printk(KERN_ERR "nvram: no address\n");
 		return -EINVAL;
 	}
-	nvram_image = memblock_alloc(NVRAM_SIZE, 0);
+	nvram_image = memblock_alloc(NVRAM_SIZE, SMP_CACHE_BYTES);
 	nvram_data = ioremap(addr, NVRAM_SIZE*2);
 	nvram_naddrs = 1; /* Make sure we get the correct case */
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index aba81cbf0b36..dd807446801e 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -3769,7 +3769,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	phb_id = be64_to_cpup(prop64);
 	pr_debug("  PHB-ID  : 0x%016llx\n", phb_id);
 
-	phb = memblock_alloc(sizeof(*phb), 0);
+	phb = memblock_alloc(sizeof(*phb), SMP_CACHE_BYTES);
 
 	/* Allocate PCI controller */
 	phb->hose = hose = pcibios_alloc_controller(np);
@@ -3815,7 +3815,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	else
 		phb->diag_data_size = PNV_PCI_DIAG_BUF_SIZE;
 
-	phb->diag_data = memblock_alloc(phb->diag_data_size, 0);
+	phb->diag_data = memblock_alloc(phb->diag_data_size, SMP_CACHE_BYTES);
 
 	/* Parse 32-bit and IO ranges (if any) */
 	pci_process_bridge_OF_ranges(hose, np, !hose->global_number);
@@ -3874,7 +3874,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	}
 	pemap_off = size;
 	size += phb->ioda.total_pe_num * sizeof(struct pnv_ioda_pe);
-	aux = memblock_alloc(size, 0);
+	aux = memblock_alloc(size, SMP_CACHE_BYTES);
 	phb->ioda.pe_alloc = aux;
 	phb->ioda.m64_segmap = aux + m64map_off;
 	phb->ioda.m32_segmap = aux + m32map_off;
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index 2444feda831f..d45450f6666a 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -128,7 +128,7 @@ int __ref msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count,
 	if (bmp->bitmap_from_slab)
 		bmp->bitmap = kzalloc(size, GFP_KERNEL);
 	else {
-		bmp->bitmap = memblock_alloc(size, 0);
+		bmp->bitmap = memblock_alloc(size, SMP_CACHE_BYTES);
 		/* the bitmap won't be freed from memblock allocator */
 		kmemleak_not_leak(bmp->bitmap);
 	}
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 673816880cce..624cb47cc9cd 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -650,7 +650,7 @@ static int __init eth_setup(char *str)
 		return 1;
 	}
 
-	new = memblock_alloc(sizeof(*new), 0);
+	new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES);
 
 	INIT_LIST_HEAD(&new->list);
 	new->index = n;
diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c
index 2b4dded11a7a..10d8d20eb9ec 100644
--- a/arch/um/drivers/vector_kern.c
+++ b/arch/um/drivers/vector_kern.c
@@ -1580,7 +1580,7 @@ static int __init vector_setup(char *str)
 				 str, error);
 		return 1;
 	}
-	new = memblock_alloc(sizeof(*new), 0);
+	new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES);
 	INIT_LIST_HEAD(&new->list);
 	new->unit = n;
 	new->arguments = str;
diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c
index 3678f5b05e42..ce169ea87e61 100644
--- a/arch/um/kernel/initrd.c
+++ b/arch/um/kernel/initrd.c
@@ -36,7 +36,7 @@ int __init read_initrd(void)
 		return 0;
 	}
 
-	area = memblock_alloc(size, 0);
+	area = memblock_alloc(size, SMP_CACHE_BYTES);
 
 	if (load_initrd(initrd, area, size) == -1)
 		return 0;
diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c
index b2c38b32ea57..4b0cb68c355a 100644
--- a/arch/unicore32/kernel/setup.c
+++ b/arch/unicore32/kernel/setup.c
@@ -206,7 +206,7 @@ request_standard_resources(struct meminfo *mi)
 		if (mi->bank[i].size == 0)
 			continue;
 
-		res = memblock_alloc_low(sizeof(*res), 0);
+		res = memblock_alloc_low(sizeof(*res), SMP_CACHE_BYTES);
 		res->name  = "System RAM";
 		res->start = mi->bank[i].start;
 		res->end   = mi->bank[i].start + mi->bank[i].size - 1;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 7f5d212551d4..92c76bf97ad8 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -934,7 +934,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table)
 	 */
 #define HPET_RESOURCE_NAME_SIZE 9
 	hpet_res = memblock_alloc(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE,
-				  0);
+				  SMP_CACHE_BYTES);
 
 	hpet_res->name = (void *)&hpet_res[1];
 	hpet_res->flags = IORESOURCE_MEM;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 5fbc57e4b0b9..2953bbf05c08 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2578,7 +2578,7 @@ static struct resource * __init ioapic_setup_resources(void)
 	n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource);
 	n *= nr_ioapics;
 
-	mem = memblock_alloc(n, 0);
+	mem = memblock_alloc(n, SMP_CACHE_BYTES);
 	res = (void *)mem;
 
 	mem += sizeof(struct resource) * nr_ioapics;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 68ff62bffbab..50895c2f937d 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1093,7 +1093,8 @@ void __init e820__reserve_resources(void)
 	struct resource *res;
 	u64 end;
 
-	res = memblock_alloc(sizeof(*res) * e820_table->nr_entries, 0);
+	res = memblock_alloc(sizeof(*res) * e820_table->nr_entries,
+			     SMP_CACHE_BYTES);
 	e820_res = res;
 
 	for (i = 0; i < e820_table->nr_entries; i++) {
diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c
index 115c8e4173bb..24d2175a9480 100644
--- a/arch/x86/platform/olpc/olpc_dt.c
+++ b/arch/x86/platform/olpc/olpc_dt.c
@@ -141,7 +141,7 @@ void * __init prom_early_alloc(unsigned long size)
 		 * fast enough on the platforms we care about while minimizing
 		 * wasted bootmem) and hand off chunks of it to callers.
 		 */
-		res = memblock_alloc(chunk_size, 0);
+		res = memblock_alloc(chunk_size, SMP_CACHE_BYTES);
 		BUG_ON(!res);
 		prom_early_allocated += chunk_size;
 		memset(res, 0, chunk_size);
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index 190846dddc67..d052712373b6 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -646,7 +646,7 @@ static int __init iss_net_setup(char *str)
 		return 1;
 	}
 
-	new = memblock_alloc(sizeof(*new), 0);
+	new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES);
 	if (new == NULL) {
 		pr_err("Alloc_bootmem failed\n");
 		return 1;