Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/hskinnemoen/atmel-mci-2.6.28

70 files changed, 1112 insertions, 657 deletions

diff --git a/arch/arm/include/asm/cnt32_to_63.h b/arch/arm/include/asm/cnt32_to_63.h
deleted file mode 100644
index 480c873fa74..00000000000
--- a/arch/arm/include/asm/cnt32_to_63.h
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- *  include/asm/cnt32_to_63.h -- extend a 32-bit counter to 63 bits
- *
- *  Author:	Nicolas Pitre
- *  Created:	December 3, 2006
- *  Copyright:	MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- */
-
-#ifndef __INCLUDE_CNT32_TO_63_H__
-#define __INCLUDE_CNT32_TO_63_H__
-
-#include <linux/compiler.h>
-#include <asm/types.h>
-#include <asm/byteorder.h>
-
-/*
- * Prototype: u64 cnt32_to_63(u32 cnt)
- * Many hardware clock counters are only 32 bits wide and therefore have
- * a relatively short period making wrap-arounds rather frequent.  This
- * is a problem when implementing sched_clock() for example, where a 64-bit
- * non-wrapping monotonic value is expected to be returned.
- *
- * To overcome that limitation, let's extend a 32-bit counter to 63 bits
- * in a completely lock free fashion. Bits 0 to 31 of the clock are provided
- * by the hardware while bits 32 to 62 are stored in memory.  The top bit in
- * memory is used to synchronize with the hardware clock half-period.  When
- * the top bit of both counters (hardware and in memory) differ then the
- * memory is updated with a new value, incrementing it when the hardware
- * counter wraps around.
- *
- * Because a word store in memory is atomic then the incremented value will
- * always be in synch with the top bit indicating to any potential concurrent
- * reader if the value in memory is up to date or not with regards to the
- * needed increment.  And any race in updating the value in memory is harmless
- * as the same value would simply be stored more than once.
- *
- * The only restriction for the algorithm to work properly is that this
- * code must be executed at least once per each half period of the 32-bit
- * counter to properly update the state bit in memory. This is usually not a
- * problem in practice, but if it is then a kernel timer could be scheduled
- * to manage for this code to be executed often enough.
- *
- * Note that the top bit (bit 63) in the returned value should be considered
- * as garbage.  It is not cleared here because callers are likely to use a
- * multiplier on the returned value which can get rid of the top bit
- * implicitly by making the multiplier even, therefore saving on a runtime
- * clear-bit instruction. Otherwise caller must remember to clear the top
- * bit explicitly.
- */
-
-/* this is used only to give gcc a clue about good code generation */
-typedef union {
-	struct {
-#if defined(__LITTLE_ENDIAN)
-		u32 lo, hi;
-#elif defined(__BIG_ENDIAN)
-		u32 hi, lo;
-#endif
-	};
-	u64 val;
-} cnt32_to_63_t;
-
-#define cnt32_to_63(cnt_lo) \
-({ \
-	static volatile u32 __m_cnt_hi = 0; \
-	cnt32_to_63_t __x; \
-	__x.hi = __m_cnt_hi; \
-	__x.lo = (cnt_lo); \
- 	if (unlikely((s32)(__x.hi ^ __x.lo) < 0)) \
-		__m_cnt_hi = __x.hi = (__x.hi ^ 0x80000000) + (__x.hi >> 31); \
-	__x.val; \
-})
-
-#endif
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index aaffaecffcd..ba8ccfede96 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -111,8 +111,6 @@ int kgdb_arch_handle_exception(int exception_vector, int signo,
 	case 'D':
 	case 'k':
 	case 'c':
-		kgdb_contthread = NULL;
-
 		/*
 		 * Try to read optional parameter, pc unchanged if no parm.
 		 * If this was a compiled breakpoint, we need to move
diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c
index 67e18509d7b..b0d6b32654c 100644
--- a/arch/arm/mach-pxa/time.c
+++ b/arch/arm/mach-pxa/time.c
@@ -17,9 +17,9 @@
 #include <linux/interrupt.h>
 #include <linux/clockchips.h>
 #include <linux/sched.h>
+#include <linux/cnt32_to_63.h>
 
 #include <asm/div64.h>
-#include <asm/cnt32_to_63.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
 #include <mach/pxa-regs.h>
diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
index 1362994c78a..b422526f6d8 100644
--- a/arch/arm/mach-sa1100/generic.c
+++ b/arch/arm/mach-sa1100/generic.c
@@ -18,9 +18,9 @@
 #include <linux/ioport.h>
 #include <linux/sched.h>	/* just for sched_clock() - funny that */
 #include <linux/platform_device.h>
+#include <linux/cnt32_to_63.h>
 
 #include <asm/div64.h>
-#include <asm/cnt32_to_63.h>
 #include <mach/hardware.h>
 #include <asm/system.h>
 #include <asm/pgtable.h>
diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index d75e795c893..b638f10411e 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -28,8 +28,8 @@
 #include <linux/amba/clcd.h>
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
+#include <linux/cnt32_to_63.h>
 
-#include <asm/cnt32_to_63.h>
 #include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/io.h>
diff --git a/arch/avr32/boards/atngw100/setup.c b/arch/avr32/boards/atngw100/setup.c
index abcb0d9559b..65db3d26696 100644
--- a/arch/avr32/boards/atngw100/setup.c
+++ b/arch/avr32/boards/atngw100/setup.c
@@ -54,8 +54,11 @@ static struct spi_board_info spi0_board_info[] __initdata = {
 };
 
 static struct mci_platform_data __initdata mci0_data = {
-	.detect_pin	= GPIO_PIN_PC(25),
-	.wp_pin		= GPIO_PIN_PE(0),
+	.slot[0] = {
+		.bus_width	= 4,
+		.detect_pin	= GPIO_PIN_PC(25),
+		.wp_pin		= GPIO_PIN_PE(0),
+	},
 };
 
 /*
diff --git a/arch/avr32/boards/atstk1000/atstk1002.c b/arch/avr32/boards/atstk1000/atstk1002.c
index cccca241fae..32aceec0ae7 100644
--- a/arch/avr32/boards/atstk1000/atstk1002.c
+++ b/arch/avr32/boards/atstk1000/atstk1002.c
@@ -264,16 +264,20 @@ void __init setup_board(void)
 
 #ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
 
+static struct mci_platform_data __initdata mci0_data = {
+	.slot[0] = {
+		.bus_width	= 4,
+
 /* MMC card detect requires MACB0 *NOT* be used */
 #ifdef CONFIG_BOARD_ATSTK1002_SW6_CUSTOM
-static struct mci_platform_data __initdata mci0_data = {
-	.detect_pin	= GPIO_PIN_PC(14),	/* gpio30/sdcd */
-	.wp_pin		= GPIO_PIN_PC(15),	/* gpio31/sdwp */
-};
-#define MCI_PDATA	&mci0_data
+		.detect_pin	= GPIO_PIN_PC(14), /* gpio30/sdcd */
+		.wp_pin		= GPIO_PIN_PC(15), /* gpio31/sdwp */
 #else
-#define MCI_PDATA	NULL
+		.detect_pin	= -ENODEV,
+		.wp_pin		= -ENODEV,
 #endif	/* SW6 for sd{cd,wp} routing */
+	},
+};
 
 #endif	/* SW2 for MMC signal routing */
 
@@ -326,7 +330,7 @@ static int __init atstk1002_init(void)
 	at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
 #endif
 #ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_add_device_mci(0, MCI_PDATA);
+	at32_add_device_mci(0, &mci0_pdata);
 #endif
 #ifdef CONFIG_BOARD_ATSTK1002_SW5_CUSTOM
 	set_hw_addr(at32_add_device_eth(1, &eth_data[1]));
diff --git a/arch/avr32/boards/atstk1000/atstk1003.c b/arch/avr32/boards/atstk1000/atstk1003.c
index 0cf664174c1..acc61235b89 100644
--- a/arch/avr32/boards/atstk1000/atstk1003.c
+++ b/arch/avr32/boards/atstk1000/atstk1003.c
@@ -66,6 +66,16 @@ static struct spi_board_info spi1_board_info[] __initdata = { {
 } };
 #endif
 
+#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
+static struct mci_platform_data __initdata mci0_data = {
+	.slot[0] = {
+		.bus_width	= 4,
+		.detect_pin	= -ENODEV,
+		.wp_pin		= -ENODEV,
+	},
+};
+#endif
+
 #ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
 static void __init atstk1003_setup_extdac(void)
 {
@@ -154,7 +164,7 @@ static int __init atstk1003_init(void)
 	at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
 #endif
 #ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_add_device_mci(0, NULL);
+	at32_add_device_mci(0, &mci0_data);
 #endif
 	at32_add_device_usba(0, NULL);
 #ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM
diff --git a/arch/avr32/boards/atstk1000/atstk1004.c b/arch/avr32/boards/atstk1000/atstk1004.c
index 2c072cd0c22..949c13ec51e 100644
--- a/arch/avr32/boards/atstk1000/atstk1004.c
+++ b/arch/avr32/boards/atstk1000/atstk1004.c
@@ -71,6 +71,16 @@ static struct spi_board_info spi1_board_info[] __initdata = { {
 } };
 #endif
 
+#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
+static struct mci_platform_data __initdata mci0_data = {
+	.slot[0] = {
+		.bus_width	= 4,
+		.detect_pin	= -ENODEV,
+		.wp_pin		= -ENODEV,
+	},
+};
+#endif
+
 #ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
 static void __init atstk1004_setup_extdac(void)
 {
@@ -137,7 +147,7 @@ static int __init atstk1004_init(void)
 	at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
 #endif
 #ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-	at32_add_device_mci(0, NULL);
+	at32_add_device_mci(0, &mci0_data);
 #endif
 	at32_add_device_lcdc(0, &atstk1000_lcdc_data,
 			     fbmem_start, fbmem_size,
diff --git a/arch/avr32/include/asm/atmel-mci.h b/arch/avr32/include/asm/atmel-mci.h
index c2ea6e1c9aa..59f3fadd0b6 100644
--- a/arch/avr32/include/asm/atmel-mci.h
+++ b/arch/avr32/include/asm/atmel-mci.h
@@ -1,9 +1,39 @@
 #ifndef __ASM_AVR32_ATMEL_MCI_H
 #define __ASM_AVR32_ATMEL_MCI_H
 
-struct mci_platform_data {
+#define ATMEL_MCI_MAX_NR_SLOTS	2
+
+struct dma_slave;
+
+/**
+ * struct mci_slot_pdata - board-specific per-slot configuration
+ * @bus_width: Number of data lines wired up the slot
+ * @detect_pin: GPIO pin wired to the card detect switch
+ * @wp_pin: GPIO pin wired to the write protect sensor
+ *
+ * If a given slot is not present on the board, @bus_width should be
+ * set to 0. The other fields are ignored in this case.
+ *
+ * Any pins that aren't available should be set to a negative value.
+ *
+ * Note that support for multiple slots is experimental -- some cards
+ * might get upset if we don't get the clock management exactly right.
+ * But in most cases, it should work just fine.
+ */
+struct mci_slot_pdata {
+	unsigned int		bus_width;
 	int			detect_pin;
 	int			wp_pin;
 };
 
+/**
+ * struct mci_platform_data - board-specific MMC/SDcard configuration
+ * @dma_slave: DMA slave interface to use in data transfers, or NULL.
+ * @slot: Per-slot configuration data.
+ */
+struct mci_platform_data {
+	struct dma_slave	*dma_slave;
+	struct mci_slot_pdata	slot[ATMEL_MCI_MAX_NR_SLOTS];
+};
+
 #endif /* __ASM_AVR32_ATMEL_MCI_H */
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index fd306c49194..5d00bb8d3cc 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -1272,10 +1272,14 @@ static struct clk atmel_mci0_pclk = {
 struct platform_device *__init
 at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
 {
-	struct mci_platform_data	_data;
 	struct platform_device		*pdev;
+	struct dw_dma_slave		*dws;
 
-	if (id != 0)
+	if (id != 0 || !data)
+		return NULL;
+
+	/* Must have at least one usable slot */
+	if (!data->slot[0].bus_width && !data->slot[1].bus_width)
 		return NULL;
 
 	pdev = platform_device_alloc("atmel_mci", id);
@@ -1286,28 +1290,76 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
 				ARRAY_SIZE(atmel_mci0_resource)))
 		goto fail;
 
-	if (!data) {
-		data = &_data;
-		memset(data, -1, sizeof(struct mci_platform_data));
-		data->detect_pin = GPIO_PIN_NONE;
-		data->wp_pin = GPIO_PIN_NONE;
-	}
+	if (data->dma_slave)
+		dws = kmemdup(to_dw_dma_slave(data->dma_slave),
+				sizeof(struct dw_dma_slave), GFP_KERNEL);
+	else
+		dws = kzalloc(sizeof(struct dw_dma_slave), GFP_KERNEL);
+
+	dws->slave.dev = &pdev->dev;
+	dws->slave.dma_dev = &dw_dmac0_device.dev;
+	dws->slave.reg_width = DMA_SLAVE_WIDTH_32BIT;
+	dws->cfg_hi = (DWC_CFGH_SRC_PER(0)
+				| DWC_CFGH_DST_PER(1));
+	dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL
+				| DWC_CFGL_HS_SRC_POL);
+
+	data->dma_slave = &dws->slave;
 
 	if (platform_device_add_data(pdev, data,
 				sizeof(struct mci_platform_data)))
 		goto fail;
 
-	select_peripheral(PA(10), PERIPH_A, 0);	/* CLK	 */
-	select_peripheral(PA(11), PERIPH_A, 0);	/* CMD	 */
-	select_peripheral(PA(12), PERIPH_A, 0);	/* DATA0 */
-	select_peripheral(PA(13), PERIPH_A, 0);	/* DATA1 */
-	select_peripheral(PA(14), PERIPH_A, 0);	/* DATA2 */
-	select_peripheral(PA(15), PERIPH_A, 0);	/* DATA3 */
+	/* CLK line is common to both slots */
+	select_peripheral(PA(10), PERIPH_A, 0);
 
-	if (gpio_is_valid(data->detect_pin))
-		at32_select_gpio(data->detect_pin, 0);
-	if (gpio_is_valid(data->wp_pin))
-		at32_select_gpio(data->wp_pin, 0);
+	switch (data->slot[0].bus_width) {
+	case 4:
+		select_peripheral(PA(13), PERIPH_A, 0);	/* DATA1 */
+		select_peripheral(PA(14), PERIPH_A, 0);	/* DATA2 */
+		select_peripheral(PA(15), PERIPH_A, 0);	/* DATA3 */
+		/* fall through */
+	case 1:
+		select_peripheral(PA(11), PERIPH_A, 0);	/* CMD	 */
+		select_peripheral(PA(12), PERIPH_A, 0);	/* DATA0 */
+
+		if (gpio_is_valid(data->slot[0].detect_pin))
+			at32_select_gpio(data->slot[0].detect_pin, 0);
+		if (gpio_is_valid(data->slot[0].wp_pin))
+			at32_select_gpio(data->slot[0].wp_pin, 0);
+		break;
+	case 0:
+		/* Slot is unused */
+		break;
+	default:
+		goto fail;
+	}
+
+	switch (data->slot[1].bus_width) {
+	case 4:
+		select_peripheral(PB(8),  PERIPH_B, 0);	/* DATA1 */
+		select_peripheral(PB(9),  PERIPH_B, 0);	/* DATA2 */
+		select_peripheral(PB(10), PERIPH_B, 0);	/* DATA3 */
+		/* fall through */
+	case 1:
+		select_peripheral(PB(6),  PERIPH_B, 0); /* CMD	 */
+		select_peripheral(PB(7),  PERIPH_B, 0); /* DATA0 */
+
+		if (gpio_is_valid(data->slot[1].detect_pin))
+			at32_select_gpio(data->slot[1].detect_pin, 0);
+		if (gpio_is_valid(data->slot[1].wp_pin))
+			at32_select_gpio(data->slot[1].wp_pin, 0);
+		break;
+	case 0:
+		/* Slot is unused */
+		break;
+	default:
+		if (!data->slot[0].bus_width)
+			goto fail;
+
+		data->slot[1].bus_width = 0;
+		break;
+	}
 
 	atmel_mci0_pclk.dev = &pdev->dev;
 
diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h
index f6679989103..1a873b36a4a 100644
--- a/arch/ia64/include/asm/sections.h
+++ b/arch/ia64/include/asm/sections.h
@@ -11,6 +11,9 @@
 #include <asm-generic/sections.h>
 
 extern char __per_cpu_start[], __per_cpu_end[], __phys_per_cpu_start[];
+#ifdef	CONFIG_SMP
+extern char __cpu0_per_cpu[];
+#endif
 extern char __start___vtop_patchlist[], __end___vtop_patchlist[];
 extern char __start___rse_patchlist[], __end___rse_patchlist[];
 extern char __start___mckinley_e9_bundles[], __end___mckinley_e9_bundles[];
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index d45f215bc8f..51b75cea701 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -1232,9 +1232,10 @@ efi_initialize_iomem_resources(struct resource *code_resource,
 				if (md->attribute & EFI_MEMORY_WP) {
 					name = "System ROM";
 					flags |= IORESOURCE_READONLY;
-				} else {
+				} else if (md->attribute == EFI_MEMORY_UC)
+					name = "Uncached RAM";
+				else
 					name = "System RAM";
-				}
 				break;
 
 			case EFI_ACPI_MEMORY_NVS:
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index 8bdea8eb62e..66e491d8baa 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -367,16 +367,17 @@ start_ap:
 	;;
 #else
 (isAP)	br.few 2f
-	mov r20=r19
-	sub r19=r19,r18
+	movl r20=__cpu0_per_cpu
 	;;
 	shr.u r18=r18,3
 1:
-	ld8 r21=[r20],8;;
-	st8[r19]=r21,8
+	ld8 r21=[r19],8;;
+	st8[r20]=r21,8
 	adds r18=-1,r18;;
 	cmp4.lt p7,p6=0,r18
 (p7)	br.cond.dptk.few 1b
+	mov r19=r20
+	;;
 2:
 #endif
 	tpa r19=r19
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index c27d5b2c182..de636b21567 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -616,7 +616,9 @@ setup_arch (char **cmdline_p)
 		ia64_mca_init();
 
 	platform_setup(cmdline_p);
+#ifndef CONFIG_IA64_HP_SIM
 	check_sal_cache_flush();
+#endif
 	paging_init();
 }
 <