Move ALLOC_CACHE_ALIGN_BUFFER() to the new memalign.h header

Now that we have a new header file for cache-aligned allocation, we should
move the stack-based allocation macro there also.

Signed-off-by: Simon Glass <sjg@chromium.org>

board/raspberrypi/rpi/rpi.c

@@ -10,6 +10,7 @@
 #include <fdt_support.h>
 #include <fdt_simplefb.h>
 #include <lcd.h>
+#include <memalign.h>
 #include <mmc.h>
 #include <asm/gpio.h>
 #include <asm/arch/mbox.h>

board/samsung/common/misc.c

@@ -12,6 +12,7 @@
 #include <errno.h>
 #include <version.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <linux/sizes.h>
 #include <asm/arch/cpu.h>
 #include <asm/gpio.h>

common/cmd_usb.c

@@ -14,6 +14,7 @@
 #include <common.h>
 #include <command.h>
 #include <dm.h>
+#include <memalign.h>
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 #include <part.h>

common/env_fat.c

@@ -13,6 +13,7 @@
 #include <environment.h>
 #include <linux/stddef.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <search.h>
 #include <errno.h>
 #include <fat.h>

common/env_mmc.c

@@ -12,6 +12,7 @@
 #include <environment.h>
 #include <linux/stddef.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <mmc.h>
 #include <search.h>
 #include <errno.h>

common/env_nand.c

@@ -19,6 +19,7 @@
 #include <environment.h>
 #include <linux/stddef.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <nand.h>
 #include <search.h>
 #include <errno.h>

common/env_ubi.c

@@ -11,6 +11,7 @@
 #include <environment.h>
 #include <errno.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <search.h>
 #include <ubi_uboot.h>
 #undef crc32

common/usb.c

@@ -29,6 +29,7 @@
 #include <common.h>
 #include <command.h>
 #include <dm.h>
+#include <memalign.h>
 #include <asm/processor.h>
 #include <linux/compiler.h>
 #include <linux/ctype.h>

common/usb_hub.c

@@ -26,6 +26,7 @@
 #include <command.h>
 #include <dm.h>
 #include <errno.h>
+#include <memalign.h>
 #include <asm/processor.h>
 #include <asm/unaligned.h>
 #include <linux/ctype.h>

common/usb_kbd.c

@@ -11,6 +11,7 @@
 #include <dm.h>
 #include <errno.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <stdio_dev.h>
 #include <asm/byteorder.h>
 

common/usb_storage.c

@@ -39,6 +39,7 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <mapmem.h>
+#include <memalign.h>
 #include <asm/byteorder.h>
 #include <asm/processor.h>
 #include <dm/device-internal.h>

disk/part_dos.c

@@ -17,6 +17,7 @@
 #include <common.h>
 #include <command.h>
 #include <ide.h>
+#include <memalign.h>
 #include "part_dos.h"
 
 #ifdef HAVE_BLOCK_DEVICE

disk/part_efi.c

@@ -16,6 +16,7 @@
 #include <ide.h>
 #include <inttypes.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <part_efi.h>
 #include <linux/ctype.h>
 

disk/part_mac.c

@@ -15,6 +15,7 @@
 
 #include <common.h>
 #include <command.h>
+#include <memalign.h>
 #include <ide.h>
 #include "part_mac.h"
 

drivers/block/ahci.c

@@ -15,6 +15,7 @@
 #include <asm/errno.h>
 #include <asm/io.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <scsi.h>
 #include <libata.h>
 #include <linux/ctype.h>

drivers/mmc/dw_mmc.c

@@ -10,6 +10,7 @@
 #include <common.h>
 #include <errno.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <mmc.h>
 #include <dwmmc.h>
 #include <asm-generic/errno.h>

drivers/mmc/mmc.c

@@ -16,6 +16,7 @@
 #include <mmc.h>
 #include <part.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <linux/list.h>
 #include <div64.h>
 #include "mmc_private.h"

drivers/mmc/rpmb.c

@@ -10,6 +10,7 @@
 
 #include <config.h>
 #include <common.h>
+#include <memalign.h>
 #include <mmc.h>
 #include <u-boot/sha256.h>
 #include "mmc_private.h"

drivers/mtd/nand/tegra_nand.c

@@ -9,6 +9,7 @@
 
 #include <common.h>
 #include <asm/io.h>
+#include <memalign.h>
 #include <nand.h>
 #include <asm/arch/clock.h>
 #include <asm/arch/funcmux.h>

drivers/net/e1000.c

@@ -32,6 +32,7 @@ tested on both gig copper and gig fiber boards
 #include <common.h>
 #include <dm.h>
 #include <errno.h>
+#include <memalign.h>
 #include <pci.h>
 #include "e1000.h"
 

drivers/net/fec_mxc.c

@@ -10,6 +10,7 @@
 
 #include <common.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <net.h>
 #include <netdev.h>
 #include <miiphy.h>

drivers/net/rtl8169.c

@@ -44,6 +44,7 @@
 #include <dm.h>
 #include <errno.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <net.h>
 #ifndef CONFIG_DM_ETH
 #include <netdev.h>

drivers/spi/mxs_spi.c

@@ -12,6 +12,7 @@
 
 #include <common.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <spi.h>
 #include <asm/errno.h>
 #include <asm/io.h>

drivers/usb/eth/asix.c

@@ -10,6 +10,7 @@
 #include <dm.h>
 #include <usb.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <linux/mii.h>
 #include "usb_ether.h"
 

drivers/usb/eth/asix88179.c

@@ -12,6 +12,7 @@
 #include <linux/mii.h>
 #include "usb_ether.h"
 #include <malloc.h>
+#include <memalign.h>
 #include <errno.h>
 
 /* ASIX AX88179 based USB 3.0 Ethernet Devices */

drivers/usb/eth/mcs7830.c

@@ -14,6 +14,7 @@
 #include <errno.h>
 #include <linux/mii.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <usb.h>
 
 #include "usb_ether.h"

drivers/usb/eth/smsc95xx.c

@@ -11,6 +11,7 @@
 #include <dm.h>
 #include <errno.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <usb.h>
 #include <asm/unaligned.h>
 #include <linux/mii.h>

drivers/usb/gadget/ether.c

@@ -17,6 +17,7 @@
 #include <net.h>
 #include <usb.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <linux/ctype.h>
 
 #include "gadget_chips.h"

drivers/usb/gadget/f_thor.c

@@ -18,6 +18,7 @@
 #include <errno.h>
 #include <common.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <version.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>

drivers/usb/host/dwc2.c

@@ -10,6 +10,7 @@
 #include <errno.h>
 #include <usb.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <phys2bus.h>
 #include <usbroothubdes.h>
 #include <asm/io.h>

drivers/usb/host/ehci-hcd.c

@@ -15,6 +15,7 @@
 #include <usb.h>
 #include <asm/io.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <watchdog.h>
 #include <linux/compiler.h>
 

drivers/usb/host/ohci-hcd.c

@@ -41,6 +41,7 @@
 #endif
 
 #include <malloc.h>
+#include <memalign.h>
 #include <usb.h>
 
 #include "ohci.h"

drivers/usb/host/usb-uclass.c

@@ -10,6 +10,7 @@
 #include <common.h>
 #include <dm.h>
 #include <errno.h>
+#include <memalign.h>
 #include <usb.h>
 #include <dm/device-internal.h>
 #include <dm/lists.h>

drivers/video/bcm2835.c

@@ -6,6 +6,7 @@
 
 #include <common.h>
 #include <lcd.h>
+#include <memalign.h>
 #include <asm/arch/mbox.h>
 #include <asm/global_data.h>
 

fs/ext4/dev.c

@@ -25,6 +25,7 @@
 
 #include <common.h>
 #include <config.h>
+#include <memalign.h>
 #include <ext4fs.h>
 #include <ext_common.h>
 #include "ext4_common.h"

fs/ext4/ext4_common.c

@@ -24,6 +24,7 @@
 #include <ext4fs.h>
 #include <inttypes.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <stddef.h>
 #include <linux/stat.h>
 #include <linux/time.h>

fs/ext4/ext4_write.c

@@ -23,6 +23,7 @@
 
 
 #include <common.h>
+#include <memalign.h>
 #include <linux/stat.h>
 #include <div64.h>
 #include "ext4_common.h"

fs/fat/fat.c

@@ -16,6 +16,7 @@
 #include <asm/byteorder.h>
 #include <part.h>
 #include <malloc.h>
+#include <memalign.h>
 #include <linux/compiler.h>
 #include <linux/ctype.h>
 

include/common.h

@@ -973,93 +973,6 @@ int cpu_release(int nr, int argc, char * const argv[]);
 
 #define ROUND(a,b)		(((a) + (b) - 1) & ~((b) - 1))
 
-/*
- * ARCH_DMA_MINALIGN is defined in asm/cache.h for each architecture.  It
- * is used to align DMA buffers.
- */
-#ifndef __ASSEMBLY__
-#include <asm/cache.h>
-#endif
-
-/*
- * The ALLOC_CACHE_ALIGN_BUFFER macro is used to allocate a buffer on the
- * stack that meets the minimum architecture alignment requirements for DMA.
- * Such a buffer is useful for DMA operations where flushing and invalidating
- * the cache before and after a read and/or write operation is required for
- * correct operations.
- *
- * When called the macro creates an array on the stack that is sized such
- * that:
- *
- * 1) The beginning of the array can be advanced enough to be aligned.
- *
- * 2) The size of the aligned portion of the array is a multiple of the minimum
- *    architecture alignment required for DMA.
- *
- * 3) The aligned portion contains enough space for the original number of
- *    elements requested.
- *
- * The macro then creates a pointer to the aligned portion of this array and
- * assigns to the pointer the address of the first element in the aligned
- * portion of the array.
- *
- * Calling the macro as:
- *
- *     ALLOC_CACHE_ALIGN_BUFFER(uint32_t, buffer, 1024);
- *
- * Will result in something similar to saying:
- *
- *     uint32_t    buffer[1024];
- *
- * The following differences exist:
- *
- * 1) The resulting buffer is guaranteed to be aligned to the value of
- *    ARCH_DMA_MINALIGN.
- *
- * 2) The buffer variable created by the macro is a pointer to the specified
- *    type, and NOT an array of the specified type.  This can be very important
- *    if you want the address of the buffer, which you probably do, to pass it
- *    to the DMA hardware.  The value of &buffer is different in the two cases.
- *    In the macro case it will be the address of the pointer, not the address
- *    of the space reserved for the buffer.  However, in the second case it
- *    would be the address of the buffer.  So if you are replacing hard coded
- *    stack buffers with this macro you need to make sure you remove the & from
- *    the locations where you are taking the address of the buffer.
- *
- * Note that the size parameter is the number of array elements to allocate,
- * not the number of bytes.
- *
- * This macro can not be used outside of function scope, or for the creation
- * of a function scoped static buffer.  It can not be used to create a cache
- * line aligned global buffer.
- */
-#define PAD_COUNT(s, pad) (((s) - 1) / (pad) + 1)
-#define PAD_SIZE(s, pad) (PAD_COUNT(s, pad) * pad)
-#define ALLOC_ALIGN_BUFFER_PAD(type, name, size, align, pad)		\
-	char __##name[ROUND(PAD_SIZE((size) * sizeof(type), pad), align)  \
-		      + (align - 1)];					\
-									\
-	type *name = (type *) ALIGN((uintptr_t)__##name, align)
-#define ALLOC_ALIGN_BUFFER(type, name, size, align)		\
-	ALLOC_ALIGN_BUFFER_PAD(type, name, size, align, 1)
-#define ALLOC_CACHE_ALIGN_BUFFER_PAD(type, name, size, pad)		\
-	ALLOC_ALIGN_BUFFER_PAD(type, name, size, ARCH_DMA_MINALIGN, pad)
-#define ALLOC_CACHE_ALIGN_BUFFER(type, name, size)			\
-	ALLOC_ALIGN_BUFFER(type, name, size, ARCH_DMA_MINALIGN)
-
-/*
- * DEFINE_CACHE_ALIGN_BUFFER() is similar to ALLOC_CACHE_ALIGN_BUFFER, but it's
- * purpose is to allow allocating aligned buffers outside of function scope.
- * Usage of this macro shall be avoided or used with extreme care!
- */
-#define DEFINE_ALIGN_BUFFER(type, name, size, align)			\
-	static char __##name[ALIGN(size * sizeof(type), align)]	\
-			__aligned(align);				\
-									\
-	static type *name = (type *)__##name
-#define DEFINE_CACHE_ALIGN_BUFFER(type, name, size)			\
-	DEFINE_ALIGN_BUFFER(type, name, size, ARCH_DMA_MINALIGN)
-
 /*
  * check_member() - Check the offset of a structure member
  *

include/memalign.h

@@ -13,9 +13,100 @@
  */
 #ifndef __ASSEMBLY__
 #include <asm/cache.h>
-
 #include <malloc.h>
 
+/*
+ * The ALLOC_CACHE_ALIGN_BUFFER macro is used to allocate a buffer on the
+ * stack that meets the minimum architecture alignment requirements for DMA.
+ * Such a buffer is useful for DMA operations where flushing and invalidating
+ * the cache before and after a read and/or write operation is required for
+ * correct operations.
+ *
+ * When called the macro creates an array on the stack that is sized such
+ * that:
+ *
+ * 1) The beginning of the array can be advanced enough to be aligned.
+ *
+ * 2) The size of the aligned portion of the array is a multiple of the minimum
+ *    architecture alignment required for DMA.
+ *
+ * 3) The aligned portion contains enough space for the original number of
+ *    elements requested.
+ *
+ * The macro then creates a pointer to the aligned portion of this array and
+ * assigns to the pointer the address of the first element in the aligned
+ * portion of the array.
+ *
+ * Calling the macro as:
+ *
+ *     ALLOC_CACHE_ALIGN_BUFFER(uint32_t, buffer, 1024);
+ *
+ * Will result in something similar to saying:
+ *
+ *     uint32_t    buffer[1024];
+ *
+ * The following differences exist:
+ *
+ * 1) The resulting buffer is guaranteed to be aligned to the value of
+ *    ARCH_DMA_MINALIGN.
+ *
+ * 2) The buffer variable created by the macro is a pointer to the specified
+ *    type, and NOT an array of the specified type.  This can be very important
+ *    if you want the address of the buffer, which you probably do, to pass it
+ *    to the DMA hardware.  The value of &buffer is different in the two cases.
+ *    In the macro case it will be the address of the pointer, not the address
+ *    of the space reserved for the buffer.  However, in the second case it
+ *    would be the address of the buffer.  So if you are replacing hard coded
+ *    stack buffers with this macro you need to make sure you remove the & from
+ *    the locations where you are taking the address of the buffer.
+ *
+ * Note that the size parameter is the number of array elements to allocate,
+ * not the number of bytes.
+ *
+ * This macro can not be used outside of function scope, or for the creation
+ * of a function scoped static buffer.  It can not be used to create a cache
+ * line aligned global buffer.
+ */
+#define PAD_COUNT(s, pad) (((s) - 1) / (pad) + 1)
+#define PAD_SIZE(s, pad) (PAD_COUNT(s, pad) * pad)
+#define ALLOC_ALIGN_BUFFER_PAD(type, name, size, align, pad)		\
+	char __##name[ROUND(PAD_SIZE((size) * sizeof(type), pad), align)  \
+		      + (align - 1)];					\
+									\
+	type *name = (type *)ALIGN((uintptr_t)__##name, align)
+#define ALLOC_ALIGN_BUFFER(type, name, size, align)		\
+	ALLOC_ALIGN_BUFFER_PAD(type, name, size, align, 1)
+#define ALLOC_CACHE_ALIGN_BUFFER_PAD(type, name, size, pad)		\
+	ALLOC_ALIGN_BUFFER_PAD(type, name, size, ARCH_DMA_MINALIGN, pad)
+#define ALLOC_CACHE_ALIGN_BUFFER(type, name, size)			\
+	ALLOC_ALIGN_BUFFER(type, name, size, ARCH_DMA_MINALIGN)
+
+/*
+ * DEFINE_CACHE_ALIGN_BUFFER() is similar to ALLOC_CACHE_ALIGN_BUFFER, but it's
+ * purpose is to allow allocating aligned buffers outside of function scope.
+ * Usage of this macro shall be avoided or used with extreme care!
+ */
+#define DEFINE_ALIGN_BUFFER(type, name, size, align)			\
+	static char __##name[ALIGN(size * sizeof(type), align)]	\
+			__aligned(align);				\
+									\
+	static type *name = (type *)__##name
+#define DEFINE_CACHE_ALIGN_BUFFER(type, name, size)			\
+	DEFINE_ALIGN_BUFFER(type, name, size, ARCH_DMA_MINALIGN)
+
+/**
+ * malloc_cache_aligned() - allocate a memory region aligned to cache line size
+ *
+ * This allocates memory at a cache-line boundary. The amount allocated may
+ * be larger than requested as it is rounded up to the nearest multiple of the
+ * cache-line size. This ensured that subsequent cache operations on this
+ * memory (flush, invalidate) will not affect subsequently allocated regions.
+ *
+ * @size:	Minimum number of bytes to allocate
+ *
+ * @return pointer to new memory region, or NULL if there is no more memory
+ * available.
+ */
 static inline void *malloc_cache_aligned(size_t size)
 {
 	return memalign(ARCH_DMA_MINALIGN, ALIGN(size, ARCH_DMA_MINALIGN));