Merge commit 'arm/devel'

Documentation/arm/tcm.txt

+ARM TCM (Tightly-Coupled Memory) handling in Linux
+----
+Written by Linus Walleij <linus.walleij@stericsson.com>
+
+Some ARM SoC:s have a so-called TCM (Tightly-Coupled Memory).
+This is usually just a few (4-64) KiB of RAM inside the ARM
+processor.
+
+Due to being embedded inside the CPU The TCM has a
+Harvard-architecture, so there is an ITCM (instruction TCM)
+and a DTCM (data TCM). The DTCM can not contain any
+instructions, but the ITCM can actually contain data.
+The size of DTCM or ITCM is minimum 4KiB so the typical
+minimum configuration is 4KiB ITCM and 4KiB DTCM.
+
+ARM CPU:s have special registers to read out status, physical
+location and size of TCM memories. arch/arm/include/asm/cputype.h
+defines a CPUID_TCM register that you can read out from the
+system control coprocessor. Documentation from ARM can be found
+at http://infocenter.arm.com, search for "TCM Status Register"
+to see documents for all CPUs. Reading this register you can
+determine if ITCM (bit 0) and/or DTCM (bit 16) is present in the
+machine.
+
+There is further a TCM region register (search for "TCM Region
+Registers" at the ARM site) that can report and modify the location
+size of TCM memories at runtime. This is used to read out and modify
+TCM location and size. Notice that this is not a MMU table: you
+actually move the physical location of the TCM around. At the
+place you put it, it will mask any underlying RAM from the
+CPU so it is usually wise not to overlap any physical RAM with
+the TCM. The TCM memory exists totally outside the MMU and will
+override any MMU mappings.
+
+Code executing inside the ITCM does not "see" any MMU mappings
+and e.g. register accesses must be made to physical addresses.
+
+TCM is used for a few things:
+
+- FIQ and other interrupt handlers that need deterministic
+  timing and cannot wait for cache misses.
+
+- Idle loops where all external RAM is set to self-refresh
+  retention mode, so only on-chip RAM is accessible by
+  the CPU and then we hang inside ITCM waiting for an
+  interrupt.
+
+- Other operations which implies shutting off or reconfiguring
+  the external RAM controller.
+
+There is an interface for using TCM on the ARM architecture
+in <asm/tcm.h>. Using this interface it is possible to:
+
+- Define the physical address and size of ITCM and DTCM.
+
+- Tag functions to be compiled into ITCM.
+
+- Tag data and constants to be allocated to DTCM and ITCM.
+
+- Have the remaining TCM RAM added to a special
+  allocation pool with gen_pool_create() and gen_pool_add()
+  and provice tcm_alloc() and tcm_free() for this
+  memory. Such a heap is great for things like saving
+  device state when shutting off device power domains.
+
+A machine that has TCM memory shall select HAVE_TCM in
+arch/arm/Kconfig for itself, and then the
+rest of the functionality will depend on the physical
+location and size of ITCM and DTCM to be defined in
+mach/memory.h for the machine. Code that needs to use
+TCM shall #include <asm/tcm.h> If the TCM is not located
+at the place given in memory.h it will be moved using
+the TCM Region registers.
+
+Functions to go into itcm can be tagged like this:
+int __tcmfunc foo(int bar);
+
+Variables to go into dtcm can be tagged like this:
+int __tcmdata foo;
+
+Constants can be tagged like this:
+int __tcmconst foo;
+
+To put assembler into TCM just use
+.section ".tcm.text" or .section ".tcm.data"
+respectively.
+
+Example code:
+
+#include <asm/tcm.h>
+
+/* Uninitialized data */
+static u32 __tcmdata tcmvar;
+/* Initialized data */
+static u32 __tcmdata tcmassigned = 0x2BADBABEU;
+/* Constant */
+static const u32 __tcmconst tcmconst = 0xCAFEBABEU;
+
+static void __tcmlocalfunc tcm_to_tcm(void)
+{
+	int i;
+	for (i = 0; i < 100; i++)
+		tcmvar ++;
+}
+
+static void __tcmfunc hello_tcm(void)
+{
+	/* Some abstract code that runs in ITCM */
+	int i;
+	for (i = 0; i < 100; i++) {
+		tcmvar ++;
+	}
+	tcm_to_tcm();
+}
+
+static void __init test_tcm(void)
+{
+	u32 *tcmem;
+	int i;
+
+	hello_tcm();
+	printk("Hello TCM executed from ITCM RAM\n");
+
+	printk("TCM variable from testrun: %u @ %p\n", tcmvar, &tcmvar);
+	tcmvar = 0xDEADBEEFU;
+	printk("TCM variable: 0x%x @ %p\n", tcmvar, &tcmvar);
+
+	printk("TCM assigned variable: 0x%x @ %p\n", tcmassigned, &tcmassigned);
+
+	printk("TCM constant: 0x%x @ %p\n", tcmconst, &tcmconst);
+
+	/* Allocate some TCM memory from the pool */
+	tcmem = tcm_alloc(20);
+	if (tcmem) {
+		printk("TCM Allocated 20 bytes of TCM @ %p\n", tcmem);
+		tcmem[0] = 0xDEADBEEFU;
+		tcmem[1] = 0x2BADBABEU;
+		tcmem[2] = 0xCAFEBABEU;
+		tcmem[3] = 0xDEADBEEFU;
+		tcmem[4] = 0x2BADBABEU;
+		for (i = 0; i < 5; i++)
+			printk("TCM tcmem[%d] = %08x\n", i, tcmem[i]);
+		tcm_free(tcmem, 20);
+	}
+}

arch/arm/Kconfig

@@ -46,6 +46,10 @@ config GENERIC_CLOCKEVENTS_BROADCAST
 	depends on GENERIC_CLOCKEVENTS
 	default y if SMP && !LOCAL_TIMERS
 
+config HAVE_TCM
+	bool
+	select GENERIC_ALLOCATOR
+
 config NO_IOPORT
 	bool
 
@@ -649,6 +653,7 @@ config ARCH_U300
 	bool "ST-Ericsson U300 Series"
 	depends on MMU
 	select CPU_ARM926T
+	select HAVE_TCM
 	select ARM_AMBA
 	select ARM_VIC
 	select GENERIC_TIME

arch/arm/include/asm/cputype.h

@@ -63,6 +63,11 @@ static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
 	return read_cpuid(CPUID_CACHETYPE);
 }
 
+static inline unsigned int __attribute_const__ read_cpuid_tcmstatus(void)
+{
+	return read_cpuid(CPUID_TCM);
+}
+
 /*
  * Intel's XScale3 core supports some v6 features (supersections, L2)
  * but advertises itself as v5 as it does not support the v6 ISA.  For

arch/arm/include/asm/tcm.h

+/*
+ *
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ *
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ *
+ */
+#ifndef __ASMARM_TCM_H
+#define __ASMARM_TCM_H
+
+#ifndef CONFIG_HAVE_TCM
+#error "You should not be including tcm.h unless you have a TCM!"
+#endif
+
+#include <linux/compiler.h>
+
+/* Tag variables with this */
+#define __tcmdata __section(.tcm.data)
+/* Tag constants with this */
+#define __tcmconst __section(.tcm.rodata)
+/* Tag functions inside TCM called from outside TCM with this */
+#define __tcmfunc __attribute__((long_call)) __section(.tcm.text) noinline
+/* Tag function inside TCM called from inside TCM  with this */
+#define __tcmlocalfunc __section(.tcm.text)
+
+void *tcm_alloc(size_t len);
+void tcm_free(void *addr, size_t len);
+
+#endif

arch/arm/kernel/Makefile

@@ -34,6 +34,7 @@ obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
 obj-$(CONFIG_ARM_THUMBEE)	+= thumbee.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_ARM_UNWIND)	+= unwind.o
+obj-$(CONFIG_HAVE_TCM)		+= tcm.o
 
 obj-$(CONFIG_CRUNCH)		+= crunch.o crunch-bits.o
 AFLAGS_crunch-bits.o		:= -Wa,-mcpu=ep9312

arch/arm/kernel/setup.c

@@ -45,6 +45,7 @@
 
 #include "compat.h"
 #include "atags.h"
+#include "tcm.h"
 
 #ifndef MEM_SIZE
 #define MEM_SIZE	(16*1024*1024)
@@ -749,6 +750,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	cpu_init();
+	tcm_init();
 
 	/*
 	 * Set up various architecture-specific pointers

arch/arm/kernel/tcm.c

+/*
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ * TCM memory handling for ARM systems
+ *
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/stddef.h>
+#include <linux/ioport.h>
+#include <linux/genalloc.h>
+#include <linux/string.h> /* memcpy */
+#include <asm/page.h> /* PAGE_SHIFT */
+#include <asm/cputype.h>
+#include <asm/mach/map.h>
+#include <mach/memory.h>
+#include "tcm.h"
+
+/* Scream and warn about misuse */
+#if !defined(ITCM_OFFSET) || !defined(ITCM_END) || \
+    !defined(DTCM_OFFSET) || !defined(DTCM_END)
+#error "TCM support selected but offsets not defined!"
+#endif
+
+static struct gen_pool *tcm_pool;
+
+/* TCM section definitions from the linker */
+extern char __itcm_start, __sitcm_text, __eitcm_text;
+extern char __dtcm_start, __sdtcm_data, __edtcm_data;
+
+/*
+ * TCM memory resources
+ */
+static struct resource dtcm_res = {
+	.name = "DTCM RAM",
+	.start = DTCM_OFFSET,
+	.end = DTCM_END,
+	.flags = IORESOURCE_MEM
+};
+
+static struct resource itcm_res = {
+	.name = "ITCM RAM",
+	.start = ITCM_OFFSET,
+	.end = ITCM_END,
+	.flags = IORESOURCE_MEM
+};
+
+static struct map_desc dtcm_iomap[] __initdata = {
+	{
+		.virtual	= DTCM_OFFSET,
+		.pfn		= __phys_to_pfn(DTCM_OFFSET),
+		.length		= (DTCM_END - DTCM_OFFSET + 1),
+		.type		= MT_UNCACHED
+	}
+};
+
+static struct map_desc itcm_iomap[] __initdata = {
+	{
+		.virtual	= ITCM_OFFSET,
+		.pfn		= __phys_to_pfn(ITCM_OFFSET),
+		.length		= (ITCM_END - ITCM_OFFSET + 1),
+		.type		= MT_UNCACHED
+	}
+};
+
+/*
+ * Allocate a chunk of TCM memory
+ */
+void *tcm_alloc(size_t len)
+{
+	unsigned long vaddr;
+
+	if (!tcm_pool)
+		return NULL;
+
+	vaddr = gen_pool_alloc(tcm_pool, len);
+	if (!vaddr)
+		return NULL;
+
+	return (void *) vaddr;
+}
+EXPORT_SYMBOL(tcm_alloc);
+
+/*
+ * Free a chunk of TCM memory
+ */
+void tcm_free(void *addr, size_t len)
+{
+	gen_pool_free(tcm_pool, (unsigned long) addr, len);
+}
+EXPORT_SYMBOL(tcm_free);
+
+
+static void __init setup_tcm_bank(u8 type, u32 offset, u32 expected_size)
+{
+	const int tcm_sizes[16] = { 0, -1, -1, 4, 8, 16, 32, 64, 128,
+				    256, 512, 1024, -1, -1, -1, -1 };
+	u32 tcm_region;
+	int tcm_size;
+
+	/* Read the special TCM region register c9, 0 */
+	if (!type)
+		asm("mrc	p15, 0, %0, c9, c1, 0"
+		    : "=r" (tcm_region));
+	else
+		asm("mrc	p15, 0, %0, c9, c1, 1"
+		    : "=r" (tcm_region));
+
+	tcm_size = tcm_sizes[(tcm_region >> 2) & 0x0f];
+	if (tcm_size < 0) {
+		pr_err("CPU: %sTCM of unknown size!\n",
+			type ? "I" : "D");
+	} else {
+		pr_info("CPU: found %sTCM %dk @ %08x, %senabled\n",
+			type ? "I" : "D",
+			tcm_size,
+			(tcm_region & 0xfffff000U),
+			(tcm_region & 1) ? "" : "not ");
+	}
+
+	if (tcm_size != expected_size) {
+		pr_crit("CPU: %sTCM was detected %dk but expected %dk!\n",
+		       type ? "I" : "D",
+		       tcm_size,
+		       expected_size);
+		/* Adjust to the expected size? what can we do... */
+	}
+
+	/* Force move the TCM bank to where we want it, enable */
+	tcm_region = offset | (tcm_region & 0x00000ffeU) | 1;
+
+	if (!type)
+		asm("mcr	p15, 0, %0, c9, c1, 0"
+		    : /* No output operands */
+		    : "r" (tcm_region));
+	else
+		asm("mcr	p15, 0, %0, c9, c1, 1"
+		    : /* No output operands */
+		    : "r" (tcm_region));
+
+	pr_debug("CPU: moved %sTCM %dk to %08x, enabled\n",
+		 type ? "I" : "D",
+		 tcm_size,
+		 (tcm_region & 0xfffff000U));
+}
+
+/*
+ * This initializes the TCM memory
+ */
+void __init tcm_init(void)
+{
+	u32 tcm_status = read_cpuid_tcmstatus();
+	char *start;
+	char *end;
+	char *ram;
+
+	/* Setup DTCM if present */
+	if (tcm_status & (1 << 16)) {
+		setup_tcm_bank(0, DTCM_OFFSET,
+			       (DTCM_END - DTCM_OFFSET + 1) >> 10);
+		request_resource(&iomem_resource, &dtcm_res);
+		iotable_init(dtcm_iomap, 1);
+		/* Copy data from RAM to DTCM */
+		start = &__sdtcm_data;
+		end   = &__edtcm_data;
+		ram   = &__dtcm_start;
+		memcpy(start, ram, (end-start));
+		pr_debug("CPU DTCM: copied data from %p - %p\n", start, end);
+	}
+
+	/* Setup ITCM if present */
+	if (tcm_status & 1) {
+		setup_tcm_bank(1, ITCM_OFFSET,
+			       (ITCM_END - ITCM_OFFSET + 1) >> 10);
+		request_resource(&iomem_resource, &itcm_res);
+		iotable_init(itcm_iomap, 1);
+		/* Copy code from RAM to ITCM */
+		start = &__sitcm_text;
+		end   = &__eitcm_text;
+		ram   = &__itcm_start;
+		memcpy(start, ram, (end-start));
+		pr_debug("CPU ITCM: copied code from %p - %p\n", start, end);
+	}
+}
+
+/*
+ * This creates the TCM memory pool and has to be done later,
+ * during the core_initicalls, since the allocator is not yet
+ * up and running when the first initialization runs.
+ */
+static int __init setup_tcm_pool(void)
+{
+	u32 tcm_status = read_cpuid_tcmstatus();
+	u32 dtcm_pool_start = (u32) &__edtcm_data;
+	u32 itcm_pool_start = (u32) &__eitcm_text;
+	int ret;
+
+	/*
+	 * Set up malloc pool, 2^2 = 4 bytes granularity since
+	 * the TCM is sometimes just 4 KiB. NB: pages and cache
+	 * line alignments does not matter in TCM!
+	 */
+	tcm_pool = gen_pool_create(2, -1);
+
+	pr_debug("Setting up TCM memory pool\n");
+
+	/* Add the rest of DTCM to the TCM pool */
+	if (tcm_status & (1 << 16)) {
+		if (dtcm_pool_start < DTCM_END) {
+			ret = gen_pool_add(tcm_pool, dtcm_pool_start,
+					   DTCM_END - dtcm_pool_start + 1, -1);
+			if (ret) {
+				pr_err("CPU DTCM: could not add DTCM " \
+				       "remainder to pool!\n");
+				return ret;
+			}
+			pr_debug("CPU DTCM: Added %08x bytes @ %08x to " \
+				 "the TCM memory pool\n",
+				 DTCM_END - dtcm_pool_start + 1,
+				 dtcm_pool_start);
+		}
+	}
+
+	/* Add the rest of ITCM to the TCM pool */
+	if (tcm_status & 1) {
+		if (itcm_pool_start < ITCM_END) {
+			ret = gen_pool_add(tcm_pool, itcm_pool_start,
+					   ITCM_END - itcm_pool_start + 1, -1);
+			if (ret) {
+				pr_err("CPU ITCM: could not add ITCM " \
+				       "remainder to pool!\n");
+				return ret;
+			}
+			pr_debug("CPU ITCM: Added %08x bytes @ %08x to " \
+				 "the TCM memory pool\n",
+				 ITCM_END - itcm_pool_start + 1,
+				 itcm_pool_start);
+		}
+	}
+	return 0;
+}
+
+core_initcall(setup_tcm_pool);

arch/arm/kernel/tcm.h

+/*
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ * TCM memory handling for ARM systems
+ *
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ */
+
+#ifdef CONFIG_HAVE_TCM
+void __init tcm_init(void);
+#else
+/* No TCM support, just blank inlines to be optimized out */
+inline void tcm_init(void)
+{
+}
+#endif

arch/arm/kernel/vmlinux.lds.S

@@ -199,6 +199,63 @@ SECTIONS
 	}
 	_edata_loc = __data_loc + SIZEOF(.data);
 
+#ifdef CONFIG_HAVE_TCM
+        /*
+	 * We align everything to a page boundary so we can
+	 * free it after init has commenced and TCM contents have
+	 * been copied to its destination.
+	 */
+	.tcm_start : {
+		. = ALIGN(PAGE_SIZE);
+		__tcm_start = .;
+		__itcm_start = .;
+	}
+
+	/*
+	 * Link these to the ITCM RAM
+	 * Put VMA to the TCM address and LMA to the common RAM
+	 * and we'll upload the contents from RAM to TCM and free
+	 * the used RAM after that.
+	 */
+	.text_itcm ITCM_OFFSET : AT(__itcm_start)
+	{
+		__sitcm_text = .;
+		*(.tcm.text)
+		*(.tcm.rodata)
+		. = ALIGN(4);
+		__eitcm_text = .;
+	}
+
+	/*
+	 * Reset the dot pointer, this is needed to create the
+	 * relative __dtcm_start below (to be used as extern in code).
+	 */
+	. = ADDR(.tcm_start) + SIZEOF(.tcm_start) + SIZEOF(.text_itcm);
+
+	.dtcm_start : {
+		__dtcm_start = .;
+	}
+
+	/* TODO: add remainder of ITCM as well, that can be used for data! */
+	.data_dtcm DTCM_OFFSET : AT(__dtcm_start)
+	{
+		. = ALIGN(4);
+		__sdtcm_data = .;
+		*(.tcm.data)
+		. = ALIGN(4);
+		__edtcm_data = .;
+	}
+
+	/* Reset the dot pointer or the linker gets confused */
+	. = ADDR(.dtcm_start) + SIZEOF(.data_dtcm);
+
+	/* End marker for freeing TCM copy in linked object */
+	.tcm_end : AT(ADDR(.dtcm_start) + SIZEOF(.data_dtcm)){
+		. = ALIGN(PAGE_SIZE);
+		__tcm_end = .;
+	}
+#endif
+
 	.bss : {
 		__bss_start = .;	/* BSS				*/
 		*(.bss)

arch/arm/mach-at91/at91sam9g45_devices.c

@@ -24,10 +24,58 @@
 #include <mach/at91sam9g45.h>
 #include <mach/at91sam9g45_matrix.h>
 #include <mach/at91sam9_smc.h>
+#include <mach/at_hdmac.h>
 
 #include "generic.h"
 
 
+/* --------------------------------------------------------------------
+ *  HDMAC - AHB DMA Controller
+ * -------------------------------------------------------------------- */
+
+#if defined(CONFIG_AT_HDMAC) || defined(CONFIG_AT_HDMAC_MODULE)
+static u64 hdmac_dmamask = DMA_BIT_MASK(32);
+
+static struct at_dma_platform_data atdma_pdata = {
+	.nr_channels	= 8,
+};
+
+static struct resource hdmac_resources[] = {
+	[0] = {
+		.start	= AT91_BASE_SYS + AT91_DMA,
+		.end	= AT91_BASE_SYS + AT91_DMA + SZ_512 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[2] = {
+		.start	= AT91SAM9G45_ID_DMA,
+		.end	= AT91SAM9G45_ID_DMA,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device at_hdmac_device = {
+	.name		= "at_hdmac",
+	.id		= -1,
+	.dev		= {
+				.dma_mask		= &hdmac_dmamask,
+				.coherent_dma_mask	= DMA_BIT_MASK(32),
+				.platform_data		= &atdma_pdata,
+	},
+	.resource	= hdmac_resources,
+	.num_resources	= ARRAY_SIZE(hdmac_resources),
+};
+
+void __init at91_add_device_hdmac(void)
+{
+	dma_cap_set(DMA_MEMCPY, atdma_pdata.cap_mask);
+	dma_cap_set(DMA_SLAVE, atdma_pdata.cap_mask);
+	platform_device_register(&at_hdmac_device);
+}
+#else
+void __init at91_add_device_hdmac(void) {}
+#endif
+
+
 /* --------------------------------------------------------------------
  *  USB Host (OHCI)
  * -------------------------------------------------------------------- */
@@ -1220,6 +1268,7 @@ void __init at91_add_device_serial(void) {}
  */
 static int __init at91_add_standard_devices(void)
 {
+	at91_add_device_hdmac();
 	at91_add_device_rtc();
 	at91_add_device_rtt();
 	at91_add_device_watchdog();

arch/arm/mach-at91/at91sam9rl_devices.c

@@ -21,10 +21,56 @@
 #include <mach/at91sam9rl.h>
 #include <mach/at91sam9rl_matrix.h>
 #include <mach/at91sam9_smc.h>
+#include <mach/at_hdmac.h>
 
 #include "generic.h"
 
 
+/* --------------------------------------------------------------------
+ *  HDMAC - AHB DMA Controller
+ * -------------------------------------------------------------------- */
+
+#if defined(CONFIG_AT_HDMAC) || defined(CONFIG_AT_HDMAC_MODULE)
+static u64 hdmac_dmamask = DMA_BIT_MASK(32);
+
+static struct at_dma_platform_data atdma_pdata = {
+	.nr_channels	= 2,
+};
+
+static struct resource hdmac_resources[] = {
+	[0] = {
+		.start	= AT91_BASE_SYS + AT91_DMA,
+		.end	= AT91_BASE_SYS + AT91_DMA + SZ_512 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[2] = {
+		.start	= AT91SAM9RL_ID_DMA,
+		.end	= AT91SAM9RL_ID_DMA,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device at_hdmac_device = {
+	.name		= "at_hdmac",
+	.id		= -1,
+	.dev		= {
+				.dma_mask		= &hdmac_dmamask,
+				.coherent_dma_mask	= DMA_BIT_MASK(32),
+				.platform_data		= &atdma_pdata,
+	},
+	.resource	= hdmac_resources,
+	.num_resources	= ARRAY_SIZE(hdmac_resources),
+};
+
+void __init at91_add_device_hdmac(void)
+{
+	dma_cap_set(DMA_MEMCPY, atdma_pdata.cap_mask);
+	platform_device_register(&at_hdmac_device);
+}
+#else
+void __init at91_add_device_hdmac(void) {}
+#endif
+
 /* --------------------------------------------------------------------
  *  USB HS Device (Gadget)
  * -------------------------------------------------------------------- */
@@ -1103,6 +1149,7 @@ void __init at91_add_device_serial(void) {}
  */
 static int __init at91_add_standard_devices(void)
 {
+	at91_add_device_hdmac();
 	at91_add_device_rtc();
 	at91_add_device_rtt();
 	at91_add_device_watchdog();

arch/arm/mach-integrator/integrator_cp.c

@@ -19,6 +19,7 @@
 #include <linux/amba/bus.h>
 #include <linux/amba/kmi.h>
 #include <linux/amba/clcd.h>
+#include <linux/amba/mmci.h>
 #include <linux/io.h>
 
 #include <asm/clkdev.h>
@@ -35,7 +36,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/irq.h>
-#include <asm/mach/mmc.h>
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
 
@@ -400,7 +400,7 @@ static unsigned int mmc_status(struct device *dev)
 	return status & 8;
 }
 
-static struct mmc_platform_data mmc_data = {
+static struct mmci_platform_data mmc_data = {
 	.ocr_mask	= MMC_VDD_32_33|MMC_VDD_33_34,
 	.status		= mmc_status,
 	.gpio_wp	= -1,

arch/arm/mach-realview/core.c

@@ -30,6 +30,7 @@
 #include <linux/io.h>
 #include <linux/smsc911x.h>
 #include <linux/ata_platform.h>
+#include <linux/amba/mmci.h>
 
 #include <asm/clkdev.h>
 #include <asm/system.h>
@@ -44,7 +45,6 @@
 #include <asm/mach/flash.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/map.h>
-#include <asm/mach/mmc.h>
 
 #include <asm/hardware/gic.h>
 
@@ -237,14 +237,14 @@ static unsigned int realview_mmc_status(struct device *dev)
 	return readl(REALVIEW_SYSMCI) & mask;
 }
 
-struct mmc_platform_data realview_mmc0_plat_data = {
+struct mmci_platform_data realview_mmc0_plat_data = {
 	.ocr_mask	= MMC_VDD_32_33|MMC_VDD_33_34,
 	.status		= realview_mmc_status,
 	.gpio_wp	= 17,
 	.gpio_cd	= 16,
 };
 
-struct mmc_platform_data realview_mmc1_plat_data = {
+struct mmci_platform_data realview_mmc1_plat_data = {
 	.ocr_mask	= MMC_VDD_32_33|MMC_VDD_33_34,
 	.status		= realview_mmc_status,
 	.gpio_wp	= 19,

arch/arm/mach-realview/core.h

@@ -47,8 +47,8 @@ static struct amba_device name##_device = {			\
 extern struct platform_device realview_flash_device;
 extern struct platform_device realview_cf_device;
 extern struct platform_device realview_i2c_device;
-extern struct mmc_platform_data realview_mmc0_plat_data;
-extern struct mmc_platform_data realview_mmc1_plat_data;
+extern struct mmci_platform_data realview_mmc0_plat_data;
+extern struct mmci_platform_data realview_mmc1_plat_data;
 extern struct clcd_board clcd_plat_data;
 extern void __iomem *gic_cpu_base_addr;
 extern void __iomem *timer0_va_base;

arch/arm/mach-u300/include/mach/memory.h

@@ -34,6 +34,14 @@
 	    (CONFIG_MACH_U300_ACCESS_MEM_SIZE & 1))*1024*1024 + 0x100)
 #endif
 
+/*
+ * TCM memory whereabouts
+ */
+#define ITCM_OFFSET	0xffff2000
+#define ITCM_END	0xffff3fff
+#define DTCM_OFFSET	0xffff4000
+#define DTCM_END	0xffff5fff
+
 /*
  * We enable a real big DMA buffer if need be.
  */

arch/arm/mach-u300/mmc.c

@@ -20,14 +20,14 @@
 #include <linux/regulator/machine.h>
 #include <linux/gpio.h>
 
-#include <asm/mach/mmc.h>
+#include <linux/amba/mmci.h>
 #include "mmc.h"
 
 struct mmci_card_event {
 	struct input_dev *mmc_input;
 	int mmc_inserted;
 	struct work_struct workq;
-	struct mmc_platform_data mmc0_plat_data;
+	struct mmci_platform_data mmc0_plat_data;
 };
 
 static unsigned int mmc_status(struct device *dev)
@@ -158,6 +158,8 @@ int __devinit mmc_init(struct amba_device *adev)
 	mmci_card->mmc0_plat_data.status = mmc_status;
 	mmci_card->mmc0_plat_data.gpio_wp = -1;
 	mmci_card->mmc0_plat_data.gpio_cd = -1;
+	mmci_card->mmc0_plat_data.capabilities = MMC_CAP_MMC_HIGHSPEED |
+		MMC_CAP_SD_HIGHSPEED | MMC_CAP_4_BIT_DATA;
 
 	mmcsd_device->platform_data = (void *) &mmci_card->mmc0_plat_data;
 

arch/arm/mach-versatile/core.c

@@ -27,6 +27,7 @@
 #include <linux/amba/bus.h>
 #include <linux/amba/clcd.h>
 #include <linux/amba/pl061.h>
+#include <linux/amba/mmci.h>
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/cnt32_to_63.h>
@@ -47,7 +48,6 @@
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
 #include <asm/mach/map.h>
-#include <asm/mach/mmc.h>
 
 #include "core.h"
 #include "clock.h"

arch/arm/mach-versatile/versatile_pb.c

@@ -24,6 +24,7 @@
 #include <linux/sysdev.h>
 #include <linux/amba/bus.h>
 #include <linux/amba/pl061.h>
+#include <linux/amba/mmci.h>
 #include <linux/io.h>
 
 #include <mach/hardware.h>
@@ -31,7 +32,6 @@
 #include <asm/mach-types.h>
 
 #include <asm/mach/arch.h>
-#include <asm/mach/mmc.h>
 
 #include "core.h"
 
@@ -41,7 +41,7 @@
 #define IRQ_MMCI1A	IRQ_SIC_MMCI1A
 #endif
 
-static struct mmc_platform_data mmc1_plat_data = {
+static struct mmci_platform_data mmc1_plat_data = {
 	.ocr_mask	= MMC_VDD_32_33|MMC_VDD_33_34,
 	.status		= mmc_status,
 	.gpio_wp	= -1,

arch/arm/mm/init.c

@@ -613,6 +613,14 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
+#ifdef CONFIG_HAVE_TCM
+	extern char *__tcm_start, *__tcm_end;
+
+	totalram_pages += free_area(__phys_to_pfn(__pa(__tcm_start)),
+				    __phys_to_pfn(__pa(__tcm_end)),
+				    "TCM link");
+#endif
+
 	if (!machine_is_integrator() && !machine_is_cintegrator())
 		totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)),
 					    __phys_to_pfn(__pa(__init_end)),

drivers/mmc/host/mmci.c

@@ -22,12 +22,12 @@
 #include <linux/clk.h>
 #include <linux/scatterlist.h>
 #include <linux/gpio.h>
+#include <linux/amba/mmci.h>
 
 #include <asm/cacheflush.h>
 #include <asm/div64.h>
 #include <asm/io.h>
 #include <asm/sizes.h>
-#include <asm/mach/mmc.h>
 
 #include "mmci.h"
 
@@ -38,6 +38,36 @@
 
 static unsigned int fmax = 515633;
 
+/*
+ * This must be called with host->lock held
+ */
+static void mmci_set_clkreg(struct mmci_host *host, unsigned int desired)
+{
+	u32 clk = 0;
+
+	if (desired) {
+		if (desired >= host->mclk) {
+			clk = MCI_CLK_BYPASS;
+			host->cclk = host->mclk;
+		} else {
+			clk = host->mclk / (2 * desired) - 1;
+			if (clk >= 256)
+				clk = 255;
+			host->cclk = host->mclk / (2 * (clk + 1));
+		}
+		if (host->hw_designer == 0x80)
+			clk |= MCI_FCEN; /* Bug fix in ST IP block */
+		clk |= MCI_CLK_ENABLE;
+		/* This hasn't proven to be worthwhile */
+		/* clk |= MCI_CLK_PWRSAVE; */
+	}
+
+	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_4)
+		clk |= MCI_WIDE_BUS;
+
+	writel(clk, host->base + MMCICLOCK);
+}
+
 static void
 mmci_request_end(struct mmci_host *host, struct mmc_request *mrq)
 {
@@ -419,22 +449,8 @@ static void mmci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct mmci_host *host = mmc_priv(mmc);
-	u32 clk = 0, pwr = 0;
-
-	if (ios->clock) {
-		if (ios->clock >= host->mclk) {
-			clk = MCI_CLK_BYPASS;
-			host->cclk = host->mclk;
-		} else {
-			clk = host->mclk / (2 * ios->clock) - 1;
-			if (clk >= 256)
-				clk = 255;
-			host->cclk = host->mclk / (2 * (clk + 1));
-		}
-		if (host->hw_designer == AMBA_VENDOR_ST)
-			clk |= MCI_FCEN; /* Bug fix in ST IP block */
-		clk |= MCI_CLK_ENABLE;
-	}
+	u32 pwr = 0;
+	unsigned long flags;
 
 	if (host->plat->translate_vdd)
 		pwr |= host->plat->translate_vdd(mmc_dev(mmc), ios->vdd);
@@ -465,12 +481,16 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		}
 	}
 
-	writel(clk, host->base + MMCICLOCK);
+	spin_lock_irqsave(&host->lock, flags);
+
+	mmci_set_clkreg(host, ios->clock);
 
 	if (host->pwr != pwr) {
 		host->pwr = pwr;
 		writel(pwr, host->base + MMCIPOWER);
 	}
+
+	spin_unlock_irqrestore(&host->lock, flags);
 }
 
 static int mmci_get_ro(struct mmc_host *mmc)
@@ -517,7 +537,7 @@ static void mmci_check_status(unsigned long data)
 
 static int __devinit mmci_probe(struct amba_device *dev, struct amba_id *id)
 {
-	struct mmc_platform_data *plat = dev->dev.platform_data;
+	struct mmci_platform_data *plat = dev->dev.platform_data;
 	struct mmci_host *host;
 	struct mmc_host *mmc;
 	int ret;
@@ -584,6 +604,7 @@ static int __devinit mmci_probe(struct amba_device *dev, struct amba_id *id)
 	mmc->f_min = (host->mclk + 511) / 512;
 	mmc->f_max = min(host->mclk, fmax);
 	mmc->ocr_avail = plat->ocr_mask;
+	mmc->caps = plat->capabilities;
 
 	/*
 	 * We can do SGIO

drivers/mmc/host/mmci.h

@@ -161,7 +161,7 @@ struct mmci_host {
 	unsigned int		mclk;
 	unsigned int		cclk;
 	u32			pwr;
-	struct mmc_platform_data *plat;
+	struct mmci_platform_data *plat;
 
 	u8			hw_designer;
 	u8			hw_revision:4;

arch/arm/include/asm/mach/mmc.h → include/linux/amba/mmci.h

 /*
- *  arch/arm/include/asm/mach/mmc.h
+ *  include/linux/amba/mmci.h
  */
-#ifndef ASMARM_MACH_MMC_H
-#define ASMARM_MACH_MMC_H
+#ifndef AMBA_MMCI_H
+#define AMBA_MMCI_H
 
 #include <linux/mmc/host.h>
 
-struct mmc_platform_data {
+struct mmci_platform_data {
 	unsigned int ocr_mask;			/* available voltages */
 	u32 (*translate_vdd)(struct device *, unsigned int);
 	unsigned int (*status)(struct device *);
 	int	gpio_wp;
 	int	gpio_cd;
+	unsigned long capabilities;
 };
 
 #endif