Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/upstream-linus

* 'upstream' of git://git.linux-mips.org/pub/scm/upstream-linus: (46 commits)
  ftrace/MIPS: Enable C Version of recordmcount
  ftrace/MIPS: Add module support for C version of recordmcount
  ftrace/MIPS: Add MIPS64 support for C version of recordmcount
  MIPS: Make TASK_SIZE reflect proper size for both 32 and 64 bit processes.
  MIPS: Allow UserLocal on MIPS_R1 processors
  MIPS: Honor L2 bypass bit
  MIPS: Add BMIPS CP0 register definitions
  MIPS: Add BMIPS processor types to Kconfig
  MIPS: Decouple BMIPS CPU support from bcm47xx/bcm63xx SoC code
  MIPS: Add support for hardware performance events (mipsxx)
  MIPS: Perf-events: Add callchain support
  MIPS: add support for hardware performance events (skeleton)
  MIPS: add support for software performance events
  MIPS: define local_xchg from xchg_local to atomic_long_xchg
  MIPS: AR7: Add support for Titan (TNETV10xx) SoC variant
  MIPS: AR7: Initialize GPIO earlier
  MIPS: Add platform device and Kconfig for Octeon USB EHCI / OHCI
  USB: Add EHCI and OHCH glue for OCTEON II SOCs.
  MIPS: Octeon: Add register definitions for EHCI / OHCI USB glue logic.
  MIPS: Octeon: Apply CN63XXP1 errata workarounds.
  ...

arch/mips/Kconfig

@@ -4,16 +4,21 @@ config MIPS
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_IDE
 	select HAVE_OPROFILE
+	select HAVE_PERF_EVENTS
+	select PERF_USE_VMALLOC
 	select HAVE_ARCH_KGDB
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_C_RECORDMCOUNT
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
 	select RTC_LIB if !MACH_LOONGSON
 	select GENERIC_ATOMIC64 if !64BIT
+	select HAVE_DMA_ATTRS
+	select HAVE_DMA_API_DEBUG
 
 menu "Machine selection"
 
@@ -691,6 +696,9 @@ config CAVIUM_OCTEON_REFERENCE_BOARD
 	select SWAP_IO_SPACE
 	select HW_HAS_PCI
 	select ARCH_SUPPORTS_MSI
+	select ZONE_DMA32
+	select USB_ARCH_HAS_OHCI
+	select USB_ARCH_HAS_EHCI
 	help
 	  This option supports all of the Octeon reference boards from Cavium
 	  Networks. It builds a kernel that dynamically determines the Octeon
@@ -1334,6 +1342,57 @@ config CPU_CAVIUM_OCTEON
 	  can have up to 16 Mips64v2 cores and 8 integrated gigabit ethernets.
 	  Full details can be found at http://www.caviumnetworks.com.
 
+config CPU_BMIPS3300
+	bool "BMIPS3300"
+	depends on SYS_HAS_CPU_BMIPS3300
+	select DMA_NONCOHERENT
+	select IRQ_CPU
+	select SWAP_IO_SPACE
+	select SYS_SUPPORTS_32BIT_KERNEL
+	select WEAK_ORDERING
+	help
+	  Broadcom BMIPS3300 processors.
+
+config CPU_BMIPS4350
+	bool "BMIPS4350"
+	depends on SYS_HAS_CPU_BMIPS4350
+	select CPU_SUPPORTS_32BIT_KERNEL
+	select DMA_NONCOHERENT
+	select IRQ_CPU
+	select SWAP_IO_SPACE
+	select SYS_SUPPORTS_SMP
+	select SYS_SUPPORTS_HOTPLUG_CPU
+	select WEAK_ORDERING
+	help
+	  Broadcom BMIPS4350 ("VIPER") processors.
+
+config CPU_BMIPS4380
+	bool "BMIPS4380"
+	depends on SYS_HAS_CPU_BMIPS4380
+	select CPU_SUPPORTS_32BIT_KERNEL
+	select DMA_NONCOHERENT
+	select IRQ_CPU
+	select SWAP_IO_SPACE
+	select SYS_SUPPORTS_SMP
+	select SYS_SUPPORTS_HOTPLUG_CPU
+	select WEAK_ORDERING
+	help
+	  Broadcom BMIPS4380 processors.
+
+config CPU_BMIPS5000
+	bool "BMIPS5000"
+	depends on SYS_HAS_CPU_BMIPS5000
+	select CPU_SUPPORTS_32BIT_KERNEL
+	select CPU_SUPPORTS_HIGHMEM
+	select DMA_NONCOHERENT
+	select IRQ_CPU
+	select SWAP_IO_SPACE
+	select SYS_SUPPORTS_SMP
+	select SYS_SUPPORTS_HOTPLUG_CPU
+	select WEAK_ORDERING
+	help
+	  Broadcom BMIPS5000 processors.
+
 endchoice
 
 if CPU_LOONGSON2F
@@ -1452,6 +1511,18 @@ config SYS_HAS_CPU_SB1
 config SYS_HAS_CPU_CAVIUM_OCTEON
 	bool
 
+config SYS_HAS_CPU_BMIPS3300
+	bool
+
+config SYS_HAS_CPU_BMIPS4350
+	bool
+
+config SYS_HAS_CPU_BMIPS4380
+	bool
+
+config SYS_HAS_CPU_BMIPS5000
+	bool
+
 #
 # CPU may reorder R->R, R->W, W->R, W->W
 # Reordering beyond LL and SC is handled in WEAK_REORDERING_BEYOND_LLSC
@@ -1928,6 +1999,14 @@ config NODES_SHIFT
 	default "6"
 	depends on NEED_MULTIPLE_NODES
 
+config HW_PERF_EVENTS
+	bool "Enable hardware performance counter support for perf events"
+	depends on PERF_EVENTS && !MIPS_MT_SMTC && OPROFILE=n && CPU_MIPS32
+	default y
+	help
+	  Enable hardware performance counter support for perf events. If
+	  disabled, perf events will use software events only.
+
 source "mm/Kconfig"
 
 config SMP

arch/mips/Kconfig.debug

@@ -67,6 +67,15 @@ config CMDLINE_OVERRIDE
 
 	  Normally, you will choose 'N' here.
 
+config DEBUG_STACKOVERFLOW
+	bool "Check for stack overflows"
+	depends on DEBUG_KERNEL
+	help
+	  This option will cause messages to be printed if free stack space
+	  drops below a certain limit(2GB on MIPS). The debugging option
+	  provides another way to check stack overflow happened on kernel mode
+	  stack usually caused by nested interruption.
+
 config DEBUG_STACK_USAGE
 	bool "Enable stack utilization instrumentation"
 	depends on DEBUG_KERNEL

arch/mips/Makefile

@@ -48,9 +48,6 @@ ifneq ($(SUBARCH),$(ARCH))
   endif
 endif
 
-ifndef CONFIG_FUNCTION_TRACER
-cflags-y := -ffunction-sections
-endif
 ifdef CONFIG_FUNCTION_GRAPH_TRACER
   ifndef KBUILD_MCOUNT_RA_ADDRESS
     ifeq ($(call cc-option-yn,-mmcount-ra-address), y)
@@ -159,6 +156,7 @@ cflags-$(CONFIG_CPU_CAVIUM_OCTEON) += $(call cc-option,-march=octeon) -Wa,--trap
 ifeq (,$(findstring march=octeon, $(cflags-$(CONFIG_CPU_CAVIUM_OCTEON))))
 cflags-$(CONFIG_CPU_CAVIUM_OCTEON) += -Wa,-march=octeon
 endif
+cflags-$(CONFIG_CAVIUM_CN63XXP1) += -Wa,-mfix-cn63xxp1
 
 cflags-$(CONFIG_CPU_R4000_WORKAROUNDS)	+= $(call cc-option,-mfix-r4000,)
 cflags-$(CONFIG_CPU_R4400_WORKAROUNDS)	+= $(call cc-option,-mfix-r4400,)

arch/mips/ar7/gpio.c

 /*
  * Copyright (C) 2007 Felix Fietkau <nbd@openwrt.org>
  * Copyright (C) 2007 Eugene Konev <ejka@openwrt.org>
- * Copyright (C) 2009 Florian Fainelli <florian@openwrt.org>
+ * Copyright (C) 2009-2010 Florian Fainelli <florian@openwrt.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -37,6 +37,16 @@ static int ar7_gpio_get_value(struct gpio_chip *chip, unsigned gpio)
 	return readl(gpio_in) & (1 << gpio);
 }
 
+static int titan_gpio_get_value(struct gpio_chip *chip, unsigned gpio)
+{
+	struct ar7_gpio_chip *gpch =
+				container_of(chip, struct ar7_gpio_chip, chip);
+	void __iomem *gpio_in0 = gpch->regs + TITAN_GPIO_INPUT_0;
+	void __iomem *gpio_in1 = gpch->regs + TITAN_GPIO_INPUT_1;
+
+	return readl(gpio >> 5 ? gpio_in1 : gpio_in0) & (1 << (gpio & 0x1f));
+}
+
 static void ar7_gpio_set_value(struct gpio_chip *chip,
 				unsigned gpio, int value)
 {
@@ -51,6 +61,21 @@ static void ar7_gpio_set_value(struct gpio_chip *chip,
 	writel(tmp, gpio_out);
 }
 
+static void titan_gpio_set_value(struct gpio_chip *chip,
+				unsigned gpio, int value)
+{
+	struct ar7_gpio_chip *gpch =
+				container_of(chip, struct ar7_gpio_chip, chip);
+	void __iomem *gpio_out0 = gpch->regs + TITAN_GPIO_OUTPUT_0;
+	void __iomem *gpio_out1 = gpch->regs + TITAN_GPIO_OUTPUT_1;
+	unsigned tmp;
+
+	tmp = readl(gpio >> 5 ? gpio_out1 : gpio_out0) & ~(1 << (gpio & 0x1f));
+	if (value)
+		tmp |= 1 << (gpio & 0x1f);
+	writel(tmp, gpio >> 5 ? gpio_out1 : gpio_out0);
+}
+
 static int ar7_gpio_direction_input(struct gpio_chip *chip, unsigned gpio)
 {
 	struct ar7_gpio_chip *gpch =
@@ -62,6 +87,21 @@ static int ar7_gpio_direction_input(struct gpio_chip *chip, unsigned gpio)
 	return 0;
 }
 
+static int titan_gpio_direction_input(struct gpio_chip *chip, unsigned gpio)
+{
+	struct ar7_gpio_chip *gpch =
+				container_of(chip, struct ar7_gpio_chip, chip);
+	void __iomem *gpio_dir0 = gpch->regs + TITAN_GPIO_DIR_0;
+	void __iomem *gpio_dir1 = gpch->regs + TITAN_GPIO_DIR_1;
+
+	if (gpio >= TITAN_GPIO_MAX)
+		return -EINVAL;
+
+	writel(readl(gpio >> 5 ? gpio_dir1 : gpio_dir0) | (1 << (gpio & 0x1f)),
+			gpio >> 5 ? gpio_dir1 : gpio_dir0);
+	return 0;
+}
+
 static int ar7_gpio_direction_output(struct gpio_chip *chip,
 					unsigned gpio, int value)
 {
@@ -75,6 +115,24 @@ static int ar7_gpio_direction_output(struct gpio_chip *chip,
 	return 0;
 }
 
+static int titan_gpio_direction_output(struct gpio_chip *chip,
+					unsigned gpio, int value)
+{
+	struct ar7_gpio_chip *gpch =
+				container_of(chip, struct ar7_gpio_chip, chip);
+	void __iomem *gpio_dir0 = gpch->regs + TITAN_GPIO_DIR_0;
+	void __iomem *gpio_dir1 = gpch->regs + TITAN_GPIO_DIR_1;
+
+	if (gpio >= TITAN_GPIO_MAX)
+		return -EINVAL;
+
+	titan_gpio_set_value(chip, gpio, value);
+	writel(readl(gpio >> 5 ? gpio_dir1 : gpio_dir0) & ~(1 <<
+		(gpio & 0x1f)), gpio >> 5 ? gpio_dir1 : gpio_dir0);
+
+	return 0;
+}
+
 static struct ar7_gpio_chip ar7_gpio_chip = {
 	.chip = {
 		.label			= "ar7-gpio",
@@ -87,7 +145,19 @@ static struct ar7_gpio_chip ar7_gpio_chip = {
 	}
 };
 
-int ar7_gpio_enable(unsigned gpio)
+static struct ar7_gpio_chip titan_gpio_chip = {
+	.chip = {
+		.label			= "titan-gpio",
+		.direction_input	= titan_gpio_direction_input,
+		.direction_output	= titan_gpio_direction_output,
+		.set			= titan_gpio_set_value,
+		.get			= titan_gpio_get_value,
+		.base			= 0,
+		.ngpio			= TITAN_GPIO_MAX,
+	}
+};
+
+static inline int ar7_gpio_enable_ar7(unsigned gpio)
 {
 	void __iomem *gpio_en = ar7_gpio_chip.regs + AR7_GPIO_ENABLE;
 
@@ -95,9 +165,26 @@ int ar7_gpio_enable(unsigned gpio)
 
 	return 0;
 }
+
+static inline int ar7_gpio_enable_titan(unsigned gpio)
+{
+	void __iomem *gpio_en0 = titan_gpio_chip.regs  + TITAN_GPIO_ENBL_0;
+	void __iomem *gpio_en1 = titan_gpio_chip.regs  + TITAN_GPIO_ENBL_1;
+
+	writel(readl(gpio >> 5 ? gpio_en1 : gpio_en0) | (1 << (gpio & 0x1f)),
+		gpio >> 5 ? gpio_en1 : gpio_en0);
+
+	return 0;
+}
+
+int ar7_gpio_enable(unsigned gpio)
+{
+	return ar7_is_titan() ? ar7_gpio_enable_titan(gpio) :
+				ar7_gpio_enable_ar7(gpio);
+}
 EXPORT_SYMBOL(ar7_gpio_enable);
 
-int ar7_gpio_disable(unsigned gpio)
+static inline int ar7_gpio_disable_ar7(unsigned gpio)
 {
 	void __iomem *gpio_en = ar7_gpio_chip.regs + AR7_GPIO_ENABLE;
 
@@ -105,27 +192,159 @@ int ar7_gpio_disable(unsigned gpio)
 
 	return 0;
 }
+
+static inline int ar7_gpio_disable_titan(unsigned gpio)
+{
+	void __iomem *gpio_en0 = titan_gpio_chip.regs + TITAN_GPIO_ENBL_0;
+	void __iomem *gpio_en1 = titan_gpio_chip.regs + TITAN_GPIO_ENBL_1;
+
+	writel(readl(gpio >> 5 ? gpio_en1 : gpio_en0) & ~(1 << (gpio & 0x1f)),
+			gpio >> 5 ? gpio_en1 : gpio_en0);
+
+	return 0;
+}
+
+int ar7_gpio_disable(unsigned gpio)
+{
+	return ar7_is_titan() ? ar7_gpio_disable_titan(gpio) :
+				ar7_gpio_disable_ar7(gpio);
+}
 EXPORT_SYMBOL(ar7_gpio_disable);
 
-static int __init ar7_gpio_init(void)
+struct titan_gpio_cfg {
+	u32 reg;
+	u32 shift;
+	u32 func;
+};
+
+static struct titan_gpio_cfg titan_gpio_table[] = {
+	/* reg, start bit, mux value */
+	{4, 24, 1},
+	{4, 26, 1},
+	{4, 28, 1},
+	{4, 30, 1},
+	{5, 6, 1},
+	{5, 8, 1},
+	{5, 10, 1},
+	{5, 12, 1},
+	{7, 14, 3},
+	{7, 16, 3},
+	{7, 18, 3},
+	{7, 20, 3},
+	{7, 22, 3},
+	{7, 26, 3},
+	{7, 28, 3},
+	{7, 30, 3},
+	{8, 0, 3},
+	{8, 2, 3},
+	{8, 4, 3},
+	{8, 10, 3},
+	{8, 14, 3},
+	{8, 16, 3},
+	{8, 18, 3},
+	{8, 20, 3},
+	{9, 8, 3},
+	{9, 10, 3},
+	{9, 12, 3},
+	{9, 14, 3},
+	{9, 18, 3},
+	{9, 20, 3},
+	{9, 24, 3},
+	{9, 26, 3},
+	{9, 28, 3},
+	{9, 30, 3},
+	{10, 0, 3},
+	{10, 2, 3},
+	{10, 8, 3},
+	{10, 10, 3},
+	{10, 12, 3},
+	{10, 14, 3},
+	{13, 12, 3},
+	{13, 14, 3},
+	{13, 16, 3},
+	{13, 18, 3},
+	{13, 24, 3},
+	{13, 26, 3},
+	{13, 28, 3},
+	{13, 30, 3},
+	{14, 2, 3},
+	{14, 6, 3},
+	{14, 8, 3},
+	{14, 12, 3}
+};
+
+static int titan_gpio_pinsel(unsigned gpio)
+{
+	struct titan_gpio_cfg gpio_cfg;
+	u32 mux_status, pin_sel_reg, tmp;
+	void __iomem *pin_sel = (void __iomem *)KSEG1ADDR(AR7_REGS_PINSEL);
+
+	if (gpio >= ARRAY_SIZE(titan_gpio_table))
+		return -EINVAL;
+
+	gpio_cfg = titan_gpio_table[gpio];
+	pin_sel_reg = gpio_cfg.reg - 1;
+
+	mux_status = (readl(pin_sel + pin_sel_reg) >> gpio_cfg.shift) & 0x3;
+
+	/* Check the mux status */
+	if (!((mux_status == 0) || (mux_status == gpio_cfg.func)))
+		return 0;
+
+	/* Set the pin sel value */
+	tmp = readl(pin_sel + pin_sel_reg);
+	tmp |= ((gpio_cfg.func & 0x3) << gpio_cfg.shift);
+	writel(tmp, pin_sel + pin_sel_reg);
+
+	return 0;
+}
+
+/* Perform minimal Titan GPIO configuration */
+static void titan_gpio_init(void)
+{
+	unsigned i;
+
+	for (i = 44; i < 48; i++) {
+		titan_gpio_pinsel(i);
+		ar7_gpio_enable_titan(i);
+		titan_gpio_direction_input(&titan_gpio_chip.chip, i);
+	}
+}
+
+int __init ar7_gpio_init(void)
 {
 	int ret;
+	struct ar7_gpio_chip *gpch;
+	unsigned size;
+
+	if (!ar7_is_titan()) {
+		gpch = &ar7_gpio_chip;
+		size = 0x10;
+	} else {
+		gpch = &titan_gpio_chip;
+		size = 0x1f;
+	}
 
-	ar7_gpio_chip.regs = ioremap_nocache(AR7_REGS_GPIO,
+	gpch->regs = ioremap_nocache(AR7_REGS_GPIO,
 					AR7_REGS_GPIO + 0x10);
 
-	if (!ar7_gpio_chip.regs) {
-		printk(KERN_ERR "ar7-gpio: failed to ioremap regs\n");
+	if (!gpch->regs) {
+		printk(KERN_ERR "%s: failed to ioremap regs\n",
+					gpch->chip.label);
 		return -ENOMEM;
 	}
 
-	ret = gpiochip_add(&ar7_gpio_chip.chip);
+	ret = gpiochip_add(&gpch->chip);
 	if (ret) {
-		printk(KERN_ERR "ar7-gpio: failed to add gpiochip\n");
+		printk(KERN_ERR "%s: failed to add gpiochip\n",
+					gpch->chip.label);
 		return ret;
 	}
-	printk(KERN_INFO "ar7-gpio: registered %d GPIOs\n",
-				ar7_gpio_chip.chip.ngpio);
+	printk(KERN_INFO "%s: registered %d GPIOs\n",
+				gpch->chip.label, gpch->chip.ngpio);
+
+	if (ar7_is_titan())
+		titan_gpio_init();
+
 	return ret;
 }
-arch_initcall(ar7_gpio_init);

arch/mips/ar7/platform.c

@@ -357,6 +357,11 @@ static struct gpio_led default_leds[] = {
 	},
 };
 
+static struct gpio_led titan_leds[] = {
+	{ .name = "status", .gpio = 8, .active_low = 1, },
+	{ .name = "wifi", .gpio = 13, .active_low = 1, },
+};
+
 static struct gpio_led dsl502t_leds[] = {
 	{
 		.name			= "status",
@@ -495,6 +500,9 @@ static void __init detect_leds(void)
 	} else if (strstr(prid, "DG834")) {
 		ar7_led_data.num_leds = ARRAY_SIZE(dg834g_leds);
 		ar7_led_data.leds = dg834g_leds;
+	} else if (strstr(prid, "CYWM") || strstr(prid, "CYWL")) {
+		ar7_led_data.num_leds = ARRAY_SIZE(titan_leds);
+		ar7_led_data.leds = titan_leds;
 	}
 }
 
@@ -560,6 +568,51 @@ static int __init ar7_register_uarts(void)
 	return 0;
 }
 
+static void __init titan_fixup_devices(void)
+{
+	/* Set vlynq0 data */
+	vlynq_low_data.reset_bit = 15;
+	vlynq_low_data.gpio_bit = 14;
+
+	/* Set vlynq1 data */
+	vlynq_high_data.reset_bit = 16;
+	vlynq_high_data.gpio_bit = 7;
+
+	/* Set vlynq0 resources */
+	vlynq_low_res[0].start = TITAN_REGS_VLYNQ0;
+	vlynq_low_res[0].end = TITAN_REGS_VLYNQ0 + 0xff;
+	vlynq_low_res[1].start = 33;
+	vlynq_low_res[1].end = 33;
+	vlynq_low_res[2].start = 0x0c000000;
+	vlynq_low_res[2].end = 0x0fffffff;
+	vlynq_low_res[3].start = 80;
+	vlynq_low_res[3].end = 111;
+
+	/* Set vlynq1 resources */
+	vlynq_high_res[0].start = TITAN_REGS_VLYNQ1;
+	vlynq_high_res[0].end = TITAN_REGS_VLYNQ1 + 0xff;
+	vlynq_high_res[1].start = 34;
+	vlynq_high_res[1].end = 34;
+	vlynq_high_res[2].start = 0x40000000;
+	vlynq_high_res[2].end = 0x43ffffff;
+	vlynq_high_res[3].start = 112;
+	vlynq_high_res[3].end = 143;
+
+	/* Set cpmac0 data */
+	cpmac_low_data.phy_mask = 0x40000000;
+
+	/* Set cpmac1 data */
+	cpmac_high_data.phy_mask = 0x80000000;
+
+	/* Set cpmac0 resources */
+	cpmac_low_res[0].start = TITAN_REGS_MAC0;
+	cpmac_low_res[0].end = TITAN_REGS_MAC0 + 0x7ff;
+
+	/* Set cpmac1 resources */
+	cpmac_high_res[0].start = TITAN_REGS_MAC1;
+	cpmac_high_res[0].end = TITAN_REGS_MAC1 + 0x7ff;
+}
+
 static int __init ar7_register_devices(void)
 {
 	void __iomem *bootcr;
@@ -574,6 +627,9 @@ static int __init ar7_register_devices(void)
 	if (res)
 		pr_warning("unable to register physmap-flash: %d\n", res);
 
+	if (ar7_is_titan())
+		titan_fixup_devices();
+
 	ar7_device_disable(vlynq_low_data.reset_bit);
 	res = platform_device_register(&vlynq_low);
 	if (res)

arch/mips/ar7/prom.c

@@ -246,6 +246,8 @@ void __init prom_init(void)
 	ar7_init_cmdline(fw_arg0, (char **)fw_arg1);
 	ar7_init_env((struct env_var *)fw_arg2);
 	console_config();
+
+	ar7_gpio_init();
 }
 
 #define PORT(offset) (KSEG1ADDR(AR7_REGS_UART0 + (offset * 4)))

arch/mips/ar7/setup.c

@@ -23,6 +23,7 @@
 #include <asm/reboot.h>
 #include <asm/mach-ar7/ar7.h>
 #include <asm/mach-ar7/prom.h>
+#include <asm/mach-ar7/gpio.h>
 
 static void ar7_machine_restart(char *command)
 {
@@ -49,6 +50,8 @@ static void ar7_machine_power_off(void)
 const char *get_system_type(void)
 {
 	u16 chip_id = ar7_chip_id();
+	u16 titan_variant_id = titan_chip_id();
+
 	switch (chip_id) {
 	case AR7_CHIP_7100:
 		return "TI AR7 (TNETD7100)";
@@ -56,6 +59,17 @@ const char *get_system_type(void)
 		return "TI AR7 (TNETD7200)";
 	case AR7_CHIP_7300:
 		return "TI AR7 (TNETD7300)";
+	case AR7_CHIP_TITAN:
+		switch (titan_variant_id) {
+		case TITAN_CHIP_1050:
+			return "TI AR7 (TNETV1050)";
+		case TITAN_CHIP_1055:
+			return "TI AR7 (TNETV1055)";
+		case TITAN_CHIP_1056:
+			return "TI AR7 (TNETV1056)";
+		case TITAN_CHIP_1060:
+			return "TI AR7 (TNETV1060)";
+		}
 	default:
 		return "TI AR7 (unknown)";
 	}

arch/mips/bcm63xx/cpu.c

@@ -10,7 +10,9 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/cpu.h>
+#include <asm/cpu.h>
 #include <asm/cpu-info.h>
+#include <asm/mipsregs.h>
 #include <bcm63xx_cpu.h>
 #include <bcm63xx_regs.h>
 #include <bcm63xx_io.h>
@@ -296,26 +298,24 @@ void __init bcm63xx_cpu_init(void)
 	expected_cpu_id = 0;
 
 	switch (c->cputype) {
-	/*
-	 * BCM6338 as the same PrId as BCM3302 see arch/mips/kernel/cpu-probe.c
-	 */
-	case CPU_BCM3302:
-		__cpu_name[cpu] = "Broadcom BCM6338";
-		expected_cpu_id = BCM6338_CPU_ID;
-		bcm63xx_regs_base = bcm96338_regs_base;
-		bcm63xx_irqs = bcm96338_irqs;
+	case CPU_BMIPS3300:
+		if ((read_c0_prid() & 0xff00) == PRID_IMP_BMIPS3300_ALT) {
+			expected_cpu_id = BCM6348_CPU_ID;
+			bcm63xx_regs_base = bcm96348_regs_base;
+			bcm63xx_irqs = bcm96348_irqs;
+		} else {
+			__cpu_name[cpu] = "Broadcom BCM6338";
+			expected_cpu_id = BCM6338_CPU_ID;
+			bcm63xx_regs_base = bcm96338_regs_base;
+			bcm63xx_irqs = bcm96338_irqs;
+		}
 		break;
-	case CPU_BCM6345:
+	case CPU_BMIPS32:
 		expected_cpu_id = BCM6345_CPU_ID;
 		bcm63xx_regs_base = bcm96345_regs_base;
 		bcm63xx_irqs = bcm96345_irqs;
 		break;
-	case CPU_BCM6348:
-		expected_cpu_id = BCM6348_CPU_ID;
-		bcm63xx_regs_base = bcm96348_regs_base;
-		bcm63xx_irqs = bcm96348_irqs;
-		break;
-	case CPU_BCM6358:
+	case CPU_BMIPS4350:
 		expected_cpu_id = BCM6358_CPU_ID;
 		bcm63xx_regs_base = bcm96358_regs_base;
 		bcm63xx_irqs = bcm96358_irqs;

arch/mips/cavium-octeon/Kconfig

@@ -3,6 +3,17 @@ config CAVIUM_OCTEON_SPECIFIC_OPTIONS
 	depends on CPU_CAVIUM_OCTEON
 	default "y"
 
+config CAVIUM_CN63XXP1
+	bool "Enable CN63XXP1 errata worarounds"
+	depends on CAVIUM_OCTEON_SPECIFIC_OPTIONS
+	default "n"
+	help
+	  The CN63XXP1 chip requires build time workarounds to
+	  function reliably, select this option to enable them.  These
+	  workarounds will cause a slight decrease in performance on
+	  non-CN63XXP1 hardware, so it is recommended to select "n"
+	  unless it is known the workarounds are needed.
+
 config CAVIUM_OCTEON_2ND_KERNEL
 	bool "Build the kernel to be used as a 2nd kernel on the same chip"
 	depends on CAVIUM_OCTEON_SPECIFIC_OPTIONS
@@ -87,3 +98,15 @@ config ARCH_SPARSEMEM_ENABLE
 config CAVIUM_OCTEON_HELPER
 	def_bool y
 	depends on OCTEON_ETHERNET || PCI
+
+config IOMMU_HELPER
+	bool
+
+config NEED_SG_DMA_LENGTH
+	bool
+
+config SWIOTLB
+	def_bool y
+	depends on CPU_CAVIUM_OCTEON
+	select IOMMU_HELPER
+	select NEED_SG_DMA_LENGTH

arch/mips/cavium-octeon/csrc-octeon.c

@@ -4,14 +4,18 @@
  * for more details.
  *
  * Copyright (C) 2007 by Ralf Baechle
+ * Copyright (C) 2009, 2010 Cavium Networks, Inc.
  */
 #include <linux/clocksource.h>
 #include <linux/init.h>
+#include <linux/smp.h>
 
+#include <asm/cpu-info.h>
 #include <asm/time.h>
 
 #include <asm/octeon/octeon.h>
 #include <asm/octeon/cvmx-ipd-defs.h>
+#include <asm/octeon/cvmx-mio-defs.h>
 
 /*
  * Set the current core's cvmcount counter to the value of the
@@ -19,11 +23,23 @@
  * on-line.  This allows for a read from a local cpu register to
  * access a synchronized counter.
  *
+ * On CPU_CAVIUM_OCTEON2 the IPD_CLK_COUNT is scaled by rdiv/sdiv.
  */
 void octeon_init_cvmcount(void)
 {
 	unsigned long flags;
 	unsigned loops = 2;
+	u64 f = 0;
+	u64 rdiv = 0;
+	u64 sdiv = 0;
+	if (current_cpu_type() == CPU_CAVIUM_OCTEON2) {
+		union cvmx_mio_rst_boot rst_boot;
+		rst_boot.u64 = cvmx_read_csr(CVMX_MIO_RST_BOOT);
+		rdiv = rst_boot.s.c_mul;	/* CPU clock */
+		sdiv = rst_boot.s.pnr_mul;	/* I/O clock */
+		f = (0x8000000000000000ull / sdiv) * 2;
+	}
+
 
 	/* Clobber loops so GCC will not unroll the following while loop. */
 	asm("" : "+r" (loops));
@@ -33,8 +49,20 @@ void octeon_init_cvmcount(void)
 	 * Loop several times so we are executing from the cache,
 	 * which should give more deterministic timing.
 	 */
-	while (loops--)
-		write_c0_cvmcount(cvmx_read_csr(CVMX_IPD_CLK_COUNT));
+	while (loops--) {
+		u64 ipd_clk_count = cvmx_read_csr(CVMX_IPD_CLK_COUNT);
+		if (rdiv != 0) {
+			ipd_clk_count *= rdiv;
+			if (f != 0) {
+				asm("dmultu\t%[cnt],%[f]\n\t"
+				    "mfhi\t%[cnt]"
+				    : [cnt] "+r" (ipd_clk_count),
+				      [f] "=r" (f)
+				    : : "hi", "lo");
+			}
+		}
+		write_c0_cvmcount(ipd_clk_count);
+	}
 	local_irq_restore(flags);
 }
 
@@ -77,7 +105,7 @@ unsigned long long notrace sched_clock(void)
 void __init plat_time_init(void)
 {
 	clocksource_mips.rating = 300;
-	clocksource_set_clock(&clocksource_mips, mips_hpt_frequency);
+	clocksource_set_clock(&clocksource_mips, octeon_get_clock_rate());
 	clocksource_register(&clocksource_mips);
 }
 

arch/mips/cavium-octeon/octeon-platform.c

@@ -3,13 +3,15 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 2004-2009 Cavium Networks
+ * Copyright (C) 2004-2010 Cavium Networks
  * Copyright (C) 2008 Wind River Systems
  */
 
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/i2c.h>
+#include <linux/usb.h>
+#include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 
@@ -198,7 +200,7 @@ static int __init octeon_i2c_device_init(void)
 		num_ports = 1;
 
 	for (port = 0; port < num_ports; port++) {
-		octeon_i2c_data[port].sys_freq = octeon_get_clock_rate();
+		octeon_i2c_data[port].sys_freq = octeon_get_io_clock_rate();
 		/*FIXME: should be examined. At the moment is set for 100Khz */
 		octeon_i2c_data[port].i2c_freq = 100000;
 
@@ -301,6 +303,10 @@ static int __init octeon_mgmt_device_init(void)
 			ret = -ENOMEM;
 			goto out;
 		}
+		/* No DMA restrictions */
+		pd->dev.coherent_dma_mask = DMA_BIT_MASK(64);
+		pd->dev.dma_mask = &pd->dev.coherent_dma_mask;
+
 		switch (port) {
 		case 0:
 			mgmt_port_resource.start = OCTEON_IRQ_MII0;
@@ -332,6 +338,108 @@ static int __init octeon_mgmt_device_init(void)
 }
 device_initcall(octeon_mgmt_device_init);
 
+#ifdef CONFIG_USB
+
+static int __init octeon_ehci_device_init(void)
+{
+	struct platform_device *pd;
+	int ret = 0;
+
+	struct resource usb_resources[] = {
+		{
+			.flags	= IORESOURCE_MEM,
+		}, {
+			.flags	= IORESOURCE_IRQ,
+		}
+	};
+
+	/* Only Octeon2 has ehci/ohci */
+	if (!OCTEON_IS_MODEL(OCTEON_CN63XX))
+		return 0;
+
+	if (octeon_is_simulation() || usb_disabled())
+		return 0; /* No USB in the simulator. */
+
+	pd = platform_device_alloc("octeon-ehci", 0);
+	if (!pd) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	usb_resources[0].start = 0x00016F0000000000ULL;
+	usb_resources[0].end = usb_resources[0].start + 0x100;
+
+	usb_resources[1].start = OCTEON_IRQ_USB0;
+	usb_resources[1].end = OCTEON_IRQ_USB0;
+
+	ret = platform_device_add_resources(pd, usb_resources,
+					    ARRAY_SIZE(usb_resources));
+	if (ret)
+		goto fail;
+
+	ret = platform_device_add(pd);
+	if (ret)
+		goto fail;
+
+	return ret;
+fail:
+	platform_device_put(pd);
+out:
+	return ret;
+}
+device_initcall(octeon_ehci_device_init);
+
+static int __init octeon_ohci_device_init(void)
+{
+	struct platform_device *pd;
+	int ret = 0;
+
+	struct resource usb_resources[] = {
+		{
+			.flags	= IORESOURCE_MEM,
+		}, {
+			.flags	= IORESOURCE_IRQ,
+		}
+	};
+
+	/* Only Octeon2 has ehci/ohci */
+	if (!OCTEON_IS_MODEL(OCTEON_CN63XX))
+		return 0;
+
+	if (octeon_is_simulation() || usb_disabled())
+		return 0; /* No USB in the simulator. */
+
+	pd = platform_device_alloc("octeon-ohci", 0);
+	if (!pd) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	usb_resources[0].start = 0x00016F0000000400ULL;
+	usb_resources[0].end = usb_resources[0].start + 0x100;
+
+	usb_resources[1].start = OCTEON_IRQ_USB0;
+	usb_resources[1].end = OCTEON_IRQ_USB0;
+
+	ret = platform_device_add_resources(pd, usb_resources,
+					    ARRAY_SIZE(usb_resources));
+	if (ret)
+		goto fail;
+
+	ret = platform_device_add(pd);
+	if (ret)
+		goto fail;
+
+	return ret;
+fail:
+	platform_device_put(pd);
+out:
+	return ret;
+}
+device_initcall(octeon_ohci_device_init);
+
+#endif /* CONFIG_USB */
+
 MODULE_AUTHOR("David Daney <ddaney@caviumnetworks.com>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Platform driver for Octeon SOC");

arch/mips/cavium-octeon/serial.c

@@ -66,7 +66,7 @@ static void __init octeon_uart_set_common(struct plat_serial8250_port *p)
 		/* Make simulator output fast*/
 		p->uartclk = 115200 * 16;
 	else
-		p->uartclk = mips_hpt_frequency;
+		p->uartclk = octeon_get_io_clock_rate();
 	p->serial_in = octeon_serial_in;
 	p->serial_out = octeon_serial_out;
 }

arch/mips/cavium-octeon/setup.c

@@ -33,6 +33,7 @@
 
 #include <asm/octeon/octeon.h>
 #include <asm/octeon/pci-octeon.h>
+#include <asm/octeon/cvmx-mio-defs.h>
 
 #ifdef CONFIG_CAVIUM_DECODE_RSL
 extern void cvmx_interrupt_rsl_decode(void);
@@ -96,12 +97,21 @@ int octeon_is_pci_host(void)
  */
 uint64_t octeon_get_clock_rate(void)
 {
-	if (octeon_is_simulation())
-		octeon_bootinfo->eclock_hz = 6000000;
-	return octeon_bootinfo->eclock_hz;
+	struct cvmx_sysinfo *sysinfo = cvmx_sysinfo_get();
+
+	return sysinfo->cpu_clock_hz;
 }
 EXPORT_SYMBOL(octeon_get_clock_rate);
 
+static u64 octeon_io_clock_rate;
+
+u64 octeon_get_io_clock_rate(void)
+{
+	return octeon_io_clock_rate;
+}
+EXPORT_SYMBOL(octeon_get_io_clock_rate);
+
+
 /**
  * Write to the LCD display connected to the bootbus. This display
  * exists on most Cavium evaluation boards. If it doesn't exist, then
@@ -346,8 +356,18 @@ void octeon_user_io_init(void)
 	cvmmemctl.s.wbfltime = 0;
 	/* R/W If set, do not put Istream in the L2 cache. */
 	cvmmemctl.s.istrnol2 = 0;
-	/* R/W The write buffer threshold. */
-	cvmmemctl.s.wbthresh = 10;
+
+	/*
+	 * R/W The write buffer threshold. As per erratum Core-14752
+	 * for CN63XX, a sc/scd might fail if the write buffer is
+	 * full.  Lowering WBTHRESH greatly lowers the chances of the
+	 * write buffer ever being full and triggering the erratum.
+	 */
+	if (OCTEON_IS_MODEL(OCTEON_CN63XX_PASS1_X))
+		cvmmemctl.s.wbthresh = 4;
+	else
+		cvmmemctl.s.wbthresh = 10;
+
 	/* R/W If set, CVMSEG is available for loads/stores in
 	 * kernel/debug mode. */
 #if CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0
@@ -365,14 +385,13 @@ void octeon_user_io_init(void)
 	 * is max legal value. */
 	cvmmemctl.s.lmemsz = CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE;
 
+	write_c0_cvmmemctl(cvmmemctl.u64);
 
 	if (smp_processor_id() == 0)
 		pr_notice("CVMSEG size: %d cache lines (%d bytes)\n",
 			  CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE,
 			  CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE * 128);
 
-	write_c0_cvmmemctl(cvmmemctl.u64);
-
 	/* Move the performance counter interrupts to IRQ 6 */
 	cvmctl = read_c0_cvmctl();
 	cvmctl &= ~(7 << 7);
@@ -416,6 +435,41 @@ void __init prom_init(void)
 		cvmx_phys_to_ptr(octeon_boot_desc_ptr->cvmx_desc_vaddr);
 	cvmx_bootmem_init(cvmx_phys_to_ptr(octeon_bootinfo->phy_mem_desc_addr));
 
+	sysinfo = cvmx_sysinfo_get();
+	memset(sysinfo, 0, sizeof(*sysinfo));
+	sysinfo->system_dram_size = octeon_bootinfo->dram_size << 20;
+	sysinfo->phy_mem_desc_ptr =
+		cvmx_phys_to_ptr(octeon_bootinfo->phy_mem_desc_addr);
+	sysinfo->core_mask = octeon_bootinfo->core_mask;
+	sysinfo->exception_base_addr = octeon_bootinfo->exception_base_addr;
+	sysinfo->cpu_clock_hz = octeon_bootinfo->eclock_hz;
+	sysinfo->dram_data_rate_hz = octeon_bootinfo->dclock_hz * 2;
+	sysinfo->board_type = octeon_bootinfo->board_type;
+	sysinfo->board_rev_major = octeon_bootinfo->board_rev_major;
+	sysinfo->board_rev_minor = octeon_bootinfo->board_rev_minor;
+	memcpy(sysinfo->mac_addr_base, octeon_bootinfo->mac_addr_base,
+	       sizeof(sysinfo->mac_addr_base));
+	sysinfo->mac_addr_count = octeon_bootinfo->mac_addr_count;
+	memcpy(sysinfo->board_serial_number,
+	       octeon_bootinfo->board_serial_number,
+	       sizeof(sysinfo->board_serial_number));
+	sysinfo->compact_flash_common_base_addr =
+		octeon_bootinfo->compact_flash_common_base_addr;
+	sysinfo->compact_flash_attribute_base_addr =
+		octeon_bootinfo->compact_flash_attribute_base_addr;
+	sysinfo->led_display_base_addr = octeon_bootinfo->led_display_base_addr;
+	sysinfo->dfa_ref_clock_hz = octeon_bootinfo->dfa_ref_clock_hz;
+	sysinfo->bootloader_config_flags = octeon_bootinfo->config_flags;
+
+	if (OCTEON_IS_MODEL(OCTEON_CN6XXX)) {
+		/* I/O clock runs at a different rate than the CPU. */
+		union cvmx_mio_rst_boot rst_boot;
+		rst_boot.u64 = cvmx_read_csr(CVMX_MIO_RST_BOOT);
+		octeon_io_clock_rate = 50000000 * rst_boot.s.pnr_mul;
+	} else {
+		octeon_io_clock_rate = sysinfo->cpu_clock_hz;
+	}
+
 	/*
 	 * Only enable the LED controller if we're running on a CN38XX, CN58XX,
 	 * or CN56XX. The CN30XX and CN31XX don't have an LED controller.
@@ -479,33 +533,6 @@ void __init prom_init(void)
 	}
 #endif
 
-	sysinfo = cvmx_sysinfo_get();
-	memset(sysinfo, 0, sizeof(*sysinfo));
-	sysinfo->system_dram_size = octeon_bootinfo->dram_size << 20;
-	sysinfo->phy_mem_desc_ptr =
-		cvmx_phys_to_ptr(octeon_bootinfo->phy_mem_desc_addr);
-	sysinfo->core_mask = octeon_bootinfo->core_mask;
-	sysinfo->exception_base_addr = octeon_bootinfo->exception_base_addr;
-	sysinfo->cpu_clock_hz = octeon_bootinfo->eclock_hz;
-	sysinfo->dram_data_rate_hz = octeon_bootinfo->dclock_hz * 2;
-	sysinfo->board_type = octeon_bootinfo->board_type;
-	sysinfo->board_rev_major = octeon_bootinfo->board_rev_major;
-	sysinfo->board_rev_minor = octeon_bootinfo->board_rev_minor;
-	memcpy(sysinfo->mac_addr_base, octeon_bootinfo->mac_addr_base,
-	       sizeof(sysinfo->mac_addr_base));
-	sysinfo->mac_addr_count = octeon_bootinfo->mac_addr_count;
-	memcpy(sysinfo->board_serial_number,
-	       octeon_bootinfo->board_serial_number,
-	       sizeof(sysinfo->board_serial_number));
-	sysinfo->compact_flash_common_base_addr =
-		octeon_bootinfo->compact_flash_common_base_addr;
-	sysinfo->compact_flash_attribute_base_addr =
-		octeon_bootinfo->compact_flash_attribute_base_addr;
-	sysinfo->led_display_base_addr = octeon_bootinfo->led_display_base_addr;
-	sysinfo->dfa_ref_clock_hz = octeon_bootinfo->dfa_ref_clock_hz;
-	sysinfo->bootloader_config_flags = octeon_bootinfo->config_flags;
-
-
 	octeon_check_cpu_bist();
 
 	octeon_uart = octeon_get_boot_uart();
@@ -740,6 +767,31 @@ EXPORT_SYMBOL(prom_putchar);
 
 void prom_free_prom_memory(void)
 {
+	if (OCTEON_IS_MODEL(OCTEON_CN63XX_PASS1_X)) {
+		/* Check for presence of Core-14449 fix.  */
+		u32 insn;
+		u32 *foo;
+
+		foo = &insn;
+
+		asm volatile("# before" : : : "memory");
+		prefetch(foo);
+		asm volatile(
+			".set push\n\t"
+			".set noreorder\n\t"
+			"bal 1f\n\t"
+			"nop\n"
+			"1:\tlw %0,-12($31)\n\t"
+			".set pop\n\t"
+			: "=r" (insn) : : "$31", "memory");
+
+		if ((insn >> 26) != 0x33)
+			panic("No PREF instruction at Core-14449 probe point.\n");
+
+		if (((insn >> 16) & 0x1f) != 28)
+			panic("Core-14449 WAR not in place (%04x).\n"
+			      "Please build kernel with proper options (CONFIG_CAVIUM_CN63XXP1).\n", insn);
+	}
 #ifdef CONFIG_CAVIUM_DECODE_RSL
 	cvmx_interrupt_rsl_enable();
 

arch/mips/include/asm/atomic.h

@@ -64,18 +64,16 @@ static __inline__ void atomic_add(int i, atomic_t * v)
 	} else if (kernel_uses_llsc) {
 		int temp;
 
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	ll	%0, %1		# atomic_add		\n"
-		"	addu	%0, %2					\n"
-		"	sc	%0, %1					\n"
-		"	beqz	%0, 2f					\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	mips0					\n"
-		: "=&r" (temp), "=m" (v->counter)
-		: "Ir" (i), "m" (v->counter));
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	ll	%0, %1		# atomic_add	\n"
+			"	addu	%0, %2				\n"
+			"	sc	%0, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (temp), "=m" (v->counter)
+			: "Ir" (i), "m" (v->counter));
+		} while (unlikely(!temp));
 	} else {
 		unsigned long flags;
 
@@ -109,18 +107,16 @@ static __inline__ void atomic_sub(int i, atomic_t * v)
 	} else if (kernel_uses_llsc) {
 		int temp;
 
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	ll	%0, %1		# atomic_sub		\n"
-		"	subu	%0, %2					\n"
-		"	sc	%0, %1					\n"
-		"	beqz	%0, 2f					\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	mips0					\n"
-		: "=&r" (temp), "=m" (v->counter)
-		: "Ir" (i), "m" (v->counter));
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	ll	%0, %1		# atomic_sub	\n"
+			"	subu	%0, %2				\n"
+			"	sc	%0, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (temp), "=m" (v->counter)
+			: "Ir" (i), "m" (v->counter));
+		} while (unlikely(!temp));
 	} else {
 		unsigned long flags;
 
@@ -156,20 +152,19 @@ static __inline__ int atomic_add_return(int i, atomic_t * v)
 	} else if (kernel_uses_llsc) {
 		int temp;
 
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	ll	%1, %2		# atomic_add_return	\n"
-		"	addu	%0, %1, %3				\n"
-		"	sc	%0, %2					\n"
-		"	beqz	%0, 2f					\n"
-		"	addu	%0, %1, %3				\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
-		: "Ir" (i), "m" (v->counter)
-		: "memory");
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	ll	%1, %2	# atomic_add_return	\n"
+			"	addu	%0, %1, %3			\n"
+			"	sc	%0, %2				\n"
+			"	.set	mips0				\n"
+			: "=&r" (result), "=&r" (temp), "=m" (v->counter)
+			: "Ir" (i), "m" (v->counter)
+			: "memory");
+		} while (unlikely(!result));
+
+		result = temp + i;
 	} else {
 		unsigned long flags;
 
@@ -205,23 +200,24 @@ static __inline__ int atomic_sub_return(int i, atomic_t * v)
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
 		: "Ir" (i), "m" (v->counter)
 		: "memory");
+
+		result = temp - i;
 	} else if (kernel_uses_llsc) {
 		int temp;
 
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	ll	%1, %2		# atomic_sub_return	\n"
-		"	subu	%0, %1, %3				\n"
-		"	sc	%0, %2					\n"
-		"	beqz	%0, 2f					\n"
-		"	subu	%0, %1, %3				\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
-		: "Ir" (i), "m" (v->counter)
-		: "memory");
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	ll	%1, %2	# atomic_sub_return	\n"
+			"	subu	%0, %1, %3			\n"
+			"	sc	%0, %2				\n"
+			"	.set	mips0				\n"
+			: "=&r" (result), "=&r" (temp), "=m" (v->counter)
+			: "Ir" (i), "m" (v->counter)
+			: "memory");
+		} while (unlikely(!result));
+
+		result = temp - i;
 	} else {
 		unsigned long flags;
 
@@ -279,12 +275,9 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		"	bltz	%0, 1f					\n"
 		"	sc	%0, %2					\n"
 		"	.set	noreorder				\n"
-		"	beqz	%0, 2f					\n"
+		"	beqz	%0, 1b					\n"
 		"	 subu	%0, %1, %3				\n"
 		"	.set	reorder					\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
@@ -443,18 +436,16 @@ static __inline__ void atomic64_add(long i, atomic64_t * v)
 	} else if (kernel_uses_llsc) {
 		long temp;
 
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	lld	%0, %1		# atomic64_add		\n"
-		"	daddu	%0, %2					\n"
-		"	scd	%0, %1					\n"
-		"	beqz	%0, 2f					\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	mips0					\n"
-		: "=&r" (temp), "=m" (v->counter)
-		: "Ir" (i), "m" (v->counter));
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	lld	%0, %1		# atomic64_add	\n"
+			"	daddu	%0, %2				\n"
+			"	scd	%0, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (temp), "=m" (v->counter)
+			: "Ir" (i), "m" (v->counter));
+		} while (unlikely(!temp));
 	} else {
 		unsigned long flags;
 
@@ -488,18 +479,16 @@ static __inline__ void atomic64_sub(long i, atomic64_t * v)
 	} else if (kernel_uses_llsc) {
 		long temp;
 
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	lld	%0, %1		# atomic64_sub		\n"
-		"	dsubu	%0, %2					\n"
-		"	scd	%0, %1					\n"
-		"	beqz	%0, 2f					\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	mips0					\n"
-		: "=&r" (temp), "=m" (v->counter)
-		: "Ir" (i), "m" (v->counter));
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	lld	%0, %1		# atomic64_sub	\n"
+			"	dsubu	%0, %2				\n"
+			"	scd	%0, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (temp), "=m" (v->counter)
+			: "Ir" (i), "m" (v->counter));
+		} while (unlikely(!temp));
 	} else {
 		unsigned long flags;
 
@@ -535,20 +524,19 @@ static __inline__ long atomic64_add_return(long i, atomic64_t * v)
 	} else if (kernel_uses_llsc) {
 		long temp;
 
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	lld	%1, %2		# atomic64_add_return	\n"
-		"	daddu	%0, %1, %3				\n"
-		"	scd	%0, %2					\n"
-		"	beqz	%0, 2f					\n"
-		"	daddu	%0, %1, %3				\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
-		: "Ir" (i), "m" (v->counter)
-		: "memory");
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	lld	%1, %2	# atomic64_add_return	\n"
+			"	daddu	%0, %1, %3			\n"
+			"	scd	%0, %2				\n"
+			"	.set	mips0				\n"
+			: "=&r" (result), "=&r" (temp), "=m" (v->counter)
+			: "Ir" (i), "m" (v->counter)
+			: "memory");
+		} while (unlikely(!result));
+
+		result = temp + i;
 	} else {
 		unsigned long flags;
 
@@ -587,20 +575,19 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
 	} else if (kernel_uses_llsc) {
 		long temp;
 
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	lld	%1, %2		# atomic64_sub_return	\n"
-		"	dsubu	%0, %1, %3				\n"
-		"	scd	%0, %2					\n"
-		"	beqz	%0, 2f					\n"
-		"	dsubu	%0, %1, %3				\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp), "=m" (v->counter)
-		: "Ir" (i), "m" (v->counter)
-		: "memory");
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	lld	%1, %2	# atomic64_sub_return	\n"
+			"	dsubu	%0, %1, %3			\n"
+			"	scd	%0, %2				\n"
+			"	.set	mips0				\n"
+			: "=&r" (result), "=&r" (temp), "=m" (v->counter)
+			: "Ir" (i), "m" (v->counter)
+			: "memory");
+		} while (unlikely(!result));
+
+		result = temp - i;
 	} else {
 		unsigned long flags;
 
@@ -658,12 +645,9 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		"	bltz	%0, 1f					\n"
 		"	scd	%0, %2					\n"
 		"	.set	noreorder				\n"
-		"	beqz	%0, 2f					\n"
+		"	beqz	%0, 1b					\n"
 		"	 dsubu	%0, %1, %3				\n"
 		"	.set	reorder					\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp), "=m" (v->counter)

arch/mips/include/asm/bitops.h

@@ -73,30 +73,26 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 		: "ir" (1UL << bit), "m" (*m));
 #ifdef CONFIG_CPU_MIPSR2
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
-		__asm__ __volatile__(
-		"1:	" __LL "%0, %1			# set_bit	\n"
-		"	" __INS "%0, %4, %2, 1				\n"
-		"	" __SC "%0, %1					\n"
-		"	beqz	%0, 2f					\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		: "=&r" (temp), "=m" (*m)
-		: "ir" (bit), "m" (*m), "r" (~0));
+		do {
+			__asm__ __volatile__(
+			"	" __LL "%0, %1		# set_bit	\n"
+			"	" __INS "%0, %3, %2, 1			\n"
+			"	" __SC "%0, %1				\n"
+			: "=&r" (temp), "+m" (*m)
+			: "ir" (bit), "r" (~0));
+		} while (unlikely(!temp));
 #endif /* CONFIG_CPU_MIPSR2 */
 	} else if (kernel_uses_llsc) {
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	" __LL "%0, %1			# set_bit	\n"
-		"	or	%0, %2					\n"
-		"	" __SC	"%0, %1					\n"
-		"	beqz	%0, 2f					\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	mips0					\n"
-		: "=&r" (temp), "=m" (*m)
-		: "ir" (1UL << bit), "m" (*m));
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	" __LL "%0, %1		# set_bit	\n"
+			"	or	%0, %2				\n"
+			"	" __SC	"%0, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (temp), "+m" (*m)
+			: "ir" (1UL << bit));
+		} while (unlikely(!temp));
 	} else {
 		volatile unsigned long *a = addr;
 		unsigned long mask;
@@ -134,34 +130,30 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 		"	" __SC "%0, %1					\n"
 		"	beqzl	%0, 1b					\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "=m" (*m)
-		: "ir" (~(1UL << bit)), "m" (*m));
+		: "=&r" (temp), "+m" (*m)
+		: "ir" (~(1UL << bit)));
 #ifdef CONFIG_CPU_MIPSR2
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
-		__asm__ __volatile__(
-		"1:	" __LL "%0, %1			# clear_bit	\n"
-		"	" __INS "%0, $0, %2, 1				\n"
-		"	" __SC "%0, %1					\n"
-		"	beqz	%0, 2f					\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		: "=&r" (temp), "=m" (*m)
-		: "ir" (bit), "m" (*m));
+		do {
+			__asm__ __volatile__(
+			"	" __LL "%0, %1		# clear_bit	\n"
+			"	" __INS "%0, $0, %2, 1			\n"
+			"	" __SC "%0, %1				\n"
+			: "=&r" (temp), "+m" (*m)
+			: "ir" (bit));
+		} while (unlikely(!temp));
 #endif /* CONFIG_CPU_MIPSR2 */
 	} else if (kernel_uses_llsc) {
-		__asm__ __volatile__(
-		"	.set	mips3					\n"
-		"1:	" __LL "%0, %1			# clear_bit	\n"
-		"	and	%0, %2					\n"
-		"	" __SC "%0, %1					\n"
-		"	beqz	%0, 2f					\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		"	.set	mips0					\n"
-		: "=&r" (temp), "=m" (*m)
-		: "ir" (~(1UL << bit)), "m" (*m));
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	" __LL "%0, %1		# clear_bit	\n"
+			"	and	%0, %2				\n"
+			"	" __SC "%0, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (temp), "+m" (*m)
+			: "ir" (~(1UL << bit)));
+		} while (unlikely(!temp));
 	} else {
 		volatile unsigned long *a = addr;
 		unsigned long mask;
@@ -213,24 +205,22 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 		"	" __SC	"%0, %1				\n"
 		"	beqzl	%0, 1b				\n"
 		"	.set	mips0				\n"
-		: "=&r" (temp), "=m" (*m)
-		: "ir" (1UL << bit), "m" (*m));
+		: "=&r" (temp), "+m" (*m)
+		: "ir" (1UL << bit));
 	} else if (kernel_uses_llsc) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
 
-		__asm__ __volatile__(
-		"	.set	mips3				\n"
-		"1:	" __LL "%0, %1		# change_bit	\n"
-		"	xor	%0, %2				\n"
-		"	" __SC	"%0, %1				\n"
-		"	beqz	%0, 2f				\n"
-		"	.subsection 2				\n"
-		"2:	b	1b				\n"
-		"	.previous				\n"
-		"	.set	mips0				\n"
-		: "=&r" (temp), "=m" (*m)
-		: "ir" (1UL << bit), "m" (*m));
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	" __LL "%0, %1		# change_bit	\n"
+			"	xor	%0, %2				\n"
+			"	" __SC	"%0, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (temp), "+m" (*m)
+			: "ir" (1UL << bit));
+		} while (unlikely(!temp));
 	} else {
 		volatile unsigned long *a = addr;
 		unsigned long mask;
@@ -272,30 +262,26 @@ static inline int test_and_set_bit(unsigned long nr,
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "=m" (*m), "=&r" (res)
-		: "r" (1UL << bit), "m" (*m)
+		: "=&r" (temp), "+m" (*m), "=&r" (res)
+		: "r" (1UL << bit)
 		: "memory");
 	} else if (kernel_uses_llsc) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
 
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noreorder				\n"
-		"	.set	mips3					\n"
-		"1:	" __LL "%0, %1		# test_and_set_bit	\n"
-		"	or	%2, %0, %3				\n"
-		"	" __SC	"%2, %1					\n"
-		"	beqz	%2, 2f					\n"
-		"	 and	%2, %0, %3				\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	 nop						\n"
-		"	.previous					\n"
-		"	.set	pop					\n"
-		: "=&r" (temp), "=m" (*m), "=&r" (res)
-		: "r" (1UL << bit), "m" (*m)
-		: "memory");
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	" __LL "%0, %1	# test_and_set_bit	\n"
+			"	or	%2, %0, %3			\n"
+			"	" __SC	"%2, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (temp), "+m" (*m), "=&r" (res)
+			: "r" (1UL << bit)
+			: "memory");
+		} while (unlikely(!res));
+
+		res = temp & (1UL << bit);
 	} else {
 		volatile unsigned long *a = addr;
 		unsigned long mask;
@@ -340,30 +326,26 @@ static inline int test_and_set_bit_lock(unsigned long nr,
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "=m" (*m), "=&r" (res)
-		: "r" (1UL << bit), "m" (*m)
+		: "=&r" (temp), "+m" (*m), "=&r" (res)
+		: "r" (1UL << bit)
 		: "memory");
 	} else if (kernel_uses_llsc) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
 
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noreorder				\n"
-		"	.set	mips3					\n"
-		"1:	" __LL "%0, %1		# test_and_set_bit	\n"
-		"	or	%2, %0, %3				\n"
-		"	" __SC	"%2, %1					\n"
-		"	beqz	%2, 2f					\n"
-		"	 and	%2, %0, %3				\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	 nop						\n"
-		"	.previous					\n"
-		"	.set	pop					\n"
-		: "=&r" (temp), "=m" (*m), "=&r" (res)
-		: "r" (1UL << bit), "m" (*m)
-		: "memory");
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	" __LL "%0, %1	# test_and_set_bit	\n"
+			"	or	%2, %0, %3			\n"
+			"	" __SC	"%2, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (temp), "+m" (*m), "=&r" (res)
+			: "r" (1UL << bit)
+			: "memory");
+		} while (unlikely(!res));
+
+		res = temp & (1UL << bit);
 	} else {
 		volatile unsigned long *a = addr;
 		unsigned long mask;
@@ -410,49 +392,43 @@ static inline int test_and_clear_bit(unsigned long nr,
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "=m" (*m), "=&r" (res)
-		: "r" (1UL << bit), "m" (*m)
+		: "=&r" (temp), "+m" (*m), "=&r" (res)
+		: "r" (1UL << bit)
 		: "memory");
 #ifdef CONFIG_CPU_MIPSR2
 	} else if (kernel_uses_llsc && __builtin_constant_p(nr)) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
 
-		__asm__ __volatile__(
-		"1:	" __LL	"%0, %1		# test_and_clear_bit	\n"
-		"	" __EXT "%2, %0, %3, 1				\n"
-		"	" __INS	"%0, $0, %3, 1				\n"
-		"	" __SC 	"%0, %1					\n"
-		"	beqz	%0, 2f					\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	.previous					\n"
-		: "=&r" (temp), "=m" (*m), "=&r" (res)
-		: "ir" (bit), "m" (*m)
-		: "memory");
+		do {
+			__asm__ __volatile__(
+			"	" __LL	"%0, %1	# test_and_clear_bit	\n"
+			"	" __EXT "%2, %0, %3, 1			\n"
+			"	" __INS	"%0, $0, %3, 1			\n"
+			"	" __SC 	"%0, %1				\n"
+			: "=&r" (temp), "+m" (*m), "=&r" (res)
+			: "ir" (bit)
+			: "memory");
+		} while (unlikely(!temp));
 #endif
 	} else if (kernel_uses_llsc) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
 
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noreorder				\n"
-		"	.set	mips3					\n"
-		"1:	" __LL	"%0, %1		# test_and_clear_bit	\n"
-		"	or	%2, %0, %3				\n"
-		"	xor	%2, %3					\n"
-		"	" __SC 	"%2, %1					\n"
-		"	beqz	%2, 2f					\n"
-		"	 and	%2, %0, %3				\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	 nop						\n"
-		"	.previous					\n"
-		"	.set	pop					\n"
-		: "=&r" (temp), "=m" (*m), "=&r" (res)
-		: "r" (1UL << bit), "m" (*m)
-		: "memory");
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	" __LL	"%0, %1	# test_and_clear_bit	\n"
+			"	or	%2, %0, %3			\n"
+			"	xor	%2, %3				\n"
+			"	" __SC 	"%2, %1				\n"
+			"	.set	mips0				\n"
+			: "=&r" (temp), "+m" (*m), "=&r" (res)
+			: "r" (1UL << bit)
+			: "memory");
+		} while (unlikely(!res));
+
+		res = temp & (1UL << bit);
 	} else {
 		volatile unsigned long *a = addr;
 		unsigned long mask;
@@ -499,30 +475,26 @@ static inline int test_and_change_bit(unsigned long nr,
 		"	beqzl	%2, 1b					\n"
 		"	and	%2, %0, %3				\n"
 		"	.set	mips0					\n"
-		: "=&r" (temp), "=m" (*m), "=&r" (res)
-		: "r" (1UL << bit), "m" (*m)
+		: "=&r" (temp), "+m" (*m), "=&r" (res)
+		: "r" (1UL << bit)
 		: "memory");
 	} else if (kernel_uses_llsc) {
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
 
-		__asm__ __volatile__(
-		"	.set	push					\n"
-		"	.set	noreorder				\n"
-		"	.set	mips3					\n"
-		"1:	" __LL	"%0, %1		# test_and_change_bit	\n"
-		"	xor	%2, %0, %3				\n"
-		"	" __SC	"\t%2, %1				\n"
-		"	beqz	%2, 2f					\n"
-		"	 and	%2, %0, %3				\n"
-		"	.subsection 2					\n"
-		"2:	b	1b					\n"
-		"	 nop						\n"
-		"	.previous					\n"
-		"	.set	pop					\n"
-		: "=&r" (temp), "=m" (*m), "=&r" (res)
-		: "r" (1UL << bit), "m" (*m)
-		: "memory");
+		do {
+			__asm__ __volatile__(
+			"	.set	mips3				\n"
+			"	" __LL	"%0, %1	# test_and_change_bit	\n"
+			"	xor	%2, %0, %3			\n"
+			"	" __SC	"\t%2, %1			\n"
+			"	.set	mips0				\n"
+			: "=&r" (temp), "+m" (*m), "=&r" (res)
+			: "r" (1UL << bit)
+			: "memory");
+		} while (unlikely(!res));
+
+		res = temp & (1UL << bit);
 	} else {
 		volatile unsigned long *a = addr;
 		unsigned long mask;

arch/mips/include/asm/bootinfo.h

@@ -125,4 +125,16 @@ extern unsigned long fw_arg0, fw_arg1, fw_arg2, fw_arg3;
  */
 extern void plat_mem_setup(void);
 
+#ifdef CONFIG_SWIOTLB
+/*
+ * Optional platform hook to call swiotlb_setup().
+ */
+extern void plat_swiotlb_setup(void);
+
+#else
+
+static inline void plat_swiotlb_setup(void) {}
+
+#endif /* CONFIG_SWIOTLB */
+
 #endif /* _ASM_BOOTINFO_H */

arch/mips/include/asm/cmpxchg.h

@@ -44,12 +44,9 @@
 		"	move	$1, %z4				\n"	\
 		"	.set	mips3				\n"	\
 		"	" st "	$1, %1				\n"	\
-		"	beqz	$1, 3f				\n"	\
-		"2:						\n"	\
-		"	.subsection 2				\n"	\
-		"3:	b	1b				\n"	\
-		"	.previous				\n"	\
+		"	beqz	$1, 1b				\n"	\
 		"	.set	pop				\n"	\
+		"2:						\n"	\
 		: "=&r" (__ret), "=R" (*m)				\
 		: "R" (*m), "Jr" (old), "Jr" (new)			\
 		: "memory");						\

arch/mips/include/asm/cpu.h

@@ -111,14 +111,16 @@
  * These are the PRID's for when 23:16 == PRID_COMP_BROADCOM
  */
 
-#define PRID_IMP_BCM4710	0x4000
-#define PRID_IMP_BCM3302	0x9000
-#define PRID_IMP_BCM6338	0x9000
-#define PRID_IMP_BCM6345	0x8000
-#define PRID_IMP_BCM6348	0x9100
-#define PRID_IMP_BCM4350	0xA000
-#define PRID_REV_BCM6358	0x0010
-#define PRID_REV_BCM6368	0x0030
+#define PRID_IMP_BMIPS4KC	0x4000
+#define PRID_IMP_BMIPS32	0x8000
+#define PRID_IMP_BMIPS3300	0x9000
+#define PRID_IMP_BMIPS3300_ALT	0x9100
+#define PRID_IMP_BMIPS3300_BUG	0x0000
+#define PRID_IMP_BMIPS43XX	0xa000
+#define PRID_IMP_BMIPS5000	0x5a00
+
+#define PRID_REV_BMIPS4380_LO	0x0040
+#define PRID_REV_BMIPS4380_HI	0x006f
 
 /*
  * These are the PRID's for when 23:16 == PRID_COMP_CAVIUM
@@ -131,6 +133,7 @@
 #define PRID_IMP_CAVIUM_CN56XX 0x0400
 #define PRID_IMP_CAVIUM_CN50XX 0x0600
 #define PRID_IMP_CAVIUM_CN52XX 0x0700
+#define PRID_IMP_CAVIUM_CN63XX 0x9000
 
 /*
  * These are the PRID's for when 23:16 == PRID_COMP_INGENIC
@@ -223,15 +226,14 @@ enum cpu_type_enum {
 	 * MIPS32 class processors
 	 */
 	CPU_4KC, CPU_4KEC, CPU_4KSC, CPU_24K, CPU_34K, CPU_1004K, CPU_74K,
-	CPU_ALCHEMY, CPU_PR4450, CPU_BCM3302, CPU_BCM4710,
-	CPU_BCM6338, CPU_BCM6345, CPU_BCM6348, CPU_BCM6358,
-	CPU_JZRISC,
+	CPU_ALCHEMY, CPU_PR4450, CPU_BMIPS32, CPU_BMIPS3300, CPU_BMIPS4350,
+	CPU_BMIPS4380, CPU_BMIPS5000, CPU_JZRISC,
 
 	/*
 	 * MIPS64 class processors
 	 */
 	CPU_5KC, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2,
-	CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS,
+	CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, CPU_CAVIUM_OCTEON2,
 
 	CPU_LAST
 };

arch/mips/include/asm/device.h

@@ -3,4 +3,17 @@
  *
  * This file is released under the GPLv2
  */
-#include <asm-generic/device.h>
+#ifndef _ASM_MIPS_DEVICE_H
+#define _ASM_MIPS_DEVICE_H
+
+struct dma_map_ops;
+
+struct dev_archdata {
+	/* DMA operations on that device */
+	struct dma_map_ops *dma_ops;
+};
+
+struct pdev_archdata {
+};
+
+#endif /* _ASM_MIPS_DEVICE_H*/

arch/mips/include/asm/dma-mapping.h

@@ -5,51 +5,41 @@
 #include <asm/cache.h>
 #include <asm-generic/dma-coherent.h>
 
-void *dma_alloc_noncoherent(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flag);
+#include <dma-coherence.h>
 
-void dma_free_noncoherent(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle);
+extern struct dma_map_ops *mips_dma_map_ops;
 
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flag);
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	if (dev && dev->archdata.dma_ops)
+		return dev->archdata.dma_ops;
+	else
+		return mips_dma_map_ops;
+}
 
-void dma_free_coherent(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle);
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	if (!dev->dma_mask)
+		return 0;
 
-extern dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
-	enum dma_data_direction direction);
-extern void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction);
-extern int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-	enum dma_data_direction direction);
-extern dma_addr_t dma_map_page(struct device *dev, struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction);
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-	size_t size, enum dma_data_direction direction)
+	return addr + size <= *dev->dma_mask;
+}
+
+static inline void dma_mark_clean(void *addr, size_t size) {}
+
+#include <asm-generic/dma-mapping-common.h>
+
+static inline int dma_supported(struct device *dev, u64 mask)
 {
-	dma_unmap_single(dev, dma_address, size, direction);
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	return ops->dma_supported(dev, mask);
 }
 
-extern void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-	int nhwentries, enum dma_data_direction direction);
-extern void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
-	size_t size, enum dma_data_direction direction);
-extern void dma_sync_single_for_device(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction);
-extern void dma_sync_single_range_for_cpu(struct device *dev,
-	dma_addr_t dma_handle, unsigned long offset, size_t size,
-	enum dma_data_direction direction);
-extern void dma_sync_single_range_for_device(struct device *dev,
-	dma_addr_t dma_handle, unsigned long offset, size_t size,
-	enum dma_data_direction direction);
-extern void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-	int nelems, enum dma_data_direction direction);
-extern void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-	int nelems, enum dma_data_direction direction);
-extern int dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
-extern int dma_supported(struct device *dev, u64 mask);
+static inline int dma_mapping_error(struct device *dev, u64 mask)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	return ops->mapping_error(dev, mask);
+}
 
 static inline int
 dma_set_mask(struct device *dev, u64 mask)
@@ -65,4 +55,34 @@ dma_set_mask(struct device *dev, u64 mask)
 extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	       enum dma_data_direction direction);
 
+static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t gfp)
+{
+	void *ret;
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	ret = ops->alloc_coherent(dev, size, dma_handle, gfp);
+
+	debug_dma_alloc_coherent(dev, size, *dma_handle, ret);
+
+	return ret;
+}
+
+static inline void dma_free_coherent(struct device *dev, size_t size,
+				     void *vaddr, dma_addr_t dma_handle)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	ops->free_coherent(dev, size, vaddr, dma_handle);
+
+	debug_dma_free_coherent(dev, size, vaddr, dma_handle);
+}
+
+
+void *dma_alloc_noncoherent(struct device *dev, size_t size,
+			   dma_addr_t *dma_handle, gfp_t flag);
+
+void dma_free_noncoherent(struct device *dev, size_t size,
+			 void *vaddr, dma_addr_t dma_handle);
+
 #endif /* _ASM_DMA_MAPPING_H */

arch/mips/include/asm/dma.h

@@ -91,7 +91,10 @@
 #define MAX_DMA_ADDRESS		(PAGE_OFFSET + 0x01000000)
 #endif
 #define MAX_DMA_PFN		PFN_DOWN(virt_to_phys((void *)MAX_DMA_ADDRESS))
+
+#ifndef MAX_DMA32_PFN
 #define MAX_DMA32_PFN		(1UL << (32 - PAGE_SHIFT))
+#endif
 
 /* 8237 DMA controllers */
 #define IO_DMA1_BASE	0x00	/* 8 bit slave DMA, channels 0..3 */

arch/mips/include/asm/local.h

@@ -117,7 +117,7 @@ static __inline__ long local_sub_return(long i, local_t * l)
 
 #define local_cmpxchg(l, o, n) \
 	((long)cmpxchg_local(&((l)->a.counter), (o), (n)))
-#define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n)))
+#define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n)))
 
 /**
  * local_add_unless - add unless the number is a given value

arch/mips/include/asm/mach-ar7/ar7.h

@@ -39,6 +39,7 @@
 #define AR7_REGS_UART0	(AR7_REGS_BASE + 0x0e00)
 #define AR7_REGS_USB	(AR7_REGS_BASE + 0x1200)
 #define AR7_REGS_RESET	(AR7_REGS_BASE + 0x1600)
+#define AR7_REGS_PINSEL (AR7_REGS_BASE + 0x160C)
 #define AR7_REGS_VLYNQ0	(AR7_REGS_BASE + 0x1800)
 #define AR7_REGS_DCL	(AR7_REGS_BASE + 0x1a00)
 #define AR7_REGS_VLYNQ1	(AR7_REGS_BASE + 0x1c00)
@@ -50,6 +51,14 @@
 #define UR8_REGS_WDT	(AR7_REGS_BASE + 0x0b00)
 #define UR8_REGS_UART1	(AR7_REGS_BASE + 0x0f00)
 
+/* Titan registers */
+#define TITAN_REGS_ESWITCH_BASE	(0x08640000)
+#define TITAN_REGS_MAC0		(TITAN_REGS_ESWITCH_BASE)
+#define TITAN_REGS_MAC1		(TITAN_REGS_ESWITCH_BASE + 0x0800)
+#define TITAN_REGS_MDIO		(TITAN_REGS_ESWITCH_BASE + 0x02000)
+#define TITAN_REGS_VLYNQ0	(AR7_REGS_BASE + 0x1c00)
+#define TITAN_REGS_VLYNQ1	(AR7_REGS_BASE + 0x1300)
+
 #define AR7_RESET_PERIPHERAL	0x0
 #define AR7_RESET_SOFTWARE	0x4
 #define AR7_RESET_STATUS	0x8
@@ -59,15 +68,30 @@
 #define AR7_RESET_BIT_MDIO	22
 #define AR7_RESET_BIT_EPHY	26
 
+#define TITAN_RESET_BIT_EPHY1	28
+
 /* GPIO control registers */
 #define AR7_GPIO_INPUT	0x0
 #define AR7_GPIO_OUTPUT	0x4
 #define AR7_GPIO_DIR	0x8
 #define AR7_GPIO_ENABLE	0xc
+#define TITAN_GPIO_INPUT_0	0x0
+#define TITAN_GPIO_INPUT_1	0x4
+#define TITAN_GPIO_OUTPUT_0	0x8
+#define TITAN_GPIO_OUTPUT_1	0xc
+#define TITAN_GPIO_DIR_0	0x10
+#define TITAN_GPIO_DIR_1	0x14
+#define TITAN_GPIO_ENBL_0	0x18
+#define TITAN_GPIO_ENBL_1	0x1c
 
 #define AR7_CHIP_7100	0x18
 #define AR7_CHIP_7200	0x2b
 #define AR7_CHIP_7300	0x05
+#define AR7_CHIP_TITAN	0x07
+#define TITAN_CHIP_1050	0x0f
+#define TITAN_CHIP_1055	0x0e
+#define TITAN_CHIP_1056	0x0d
+#define TITAN_CHIP_1060	0x07
 
 /* Interrupts */
 #define AR7_IRQ_UART0	15
@@ -95,14 +119,29 @@ struct plat_dsl_data {
 
 extern int ar7_cpu_clock, ar7_bus_clock, ar7_dsp_clock;
 
+static inline int ar7_is_titan(void)
+{
+	return (readl((void *)KSEG1ADDR(AR7_REGS_GPIO + 0x24)) & 0xffff) ==
+		AR7_CHIP_TITAN;
+}
+
 static inline u16 ar7_chip_id(void)
 {
-	return readl((void *)KSEG1ADDR(AR7_REGS_GPIO + 0x14)) & 0xffff;
+	return ar7_is_titan() ? AR7_CHIP_TITAN : (readl((void *)
+		KSEG1ADDR(AR7_REGS_GPIO + 0x14)) & 0xffff);
+}
+
+static inline u16 titan_chip_id(void)
+{
+	unsigned int val = readl((void *)KSEG1ADDR(AR7_REGS_GPIO +
+						TITAN_GPIO_INPUT_1));
+	return ((val >> 12) & 0x0f);
 }
 
 static inline u8 ar7_chip_rev(void)
 {
-	return (readl((void *)KSEG1ADDR(AR7_REGS_GPIO + 0x14)) >> 16) & 0xff;
+	return (readl((void *)KSEG1ADDR(AR7_REGS_GPIO + (ar7_is_titan() ? 0x24 :
+		0x14))) >> 16) & 0xff;
 }
 
 struct clk {
@@ -161,4 +200,8 @@ static inline void ar7_device_off(u32 bit)
 	msleep(20);
 }
 
+int __init ar7_gpio_init(void);
+
+int __init ar7_gpio_init(void);
+
 #endif /* __AR7_H__ */

arch/mips/include/asm/mach-ar7/gpio.h

@@ -22,7 +22,8 @@
 #include <asm/mach-ar7/ar7.h>
 
 #define AR7_GPIO_MAX 32
-#define NR_BUILTIN_GPIO AR7_GPIO_MAX
+#define TITAN_GPIO_MAX	51
+#define NR_BUILTIN_GPIO TITAN_GPIO_MAX
 
 #define gpio_to_irq(gpio)	-1
 

arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h

@@ -59,7 +59,7 @@
 #define cpu_has_veic		0
 #define cpu_hwrena_impl_bits	0xc0000000
 
-#define kernel_uses_smartmips_rixi (cpu_data[0].cputype == CPU_CAVIUM_OCTEON_PLUS)
+#define kernel_uses_smartmips_rixi (cpu_data[0].cputype != CPU_CAVIUM_OCTEON)
 
 #define ARCH_HAS_IRQ_PER_CPU	1
 #define ARCH_HAS_SPINLOCK_PREFETCH 1
@@ -81,4 +81,10 @@ static inline int octeon_has_saa(void)
 	return id >= 0x000d0300;
 }
 
+/*
+ * The last 256MB are reserved for device to device mappings and the
+ * BAR1 hole.
+ */
+#define MAX_DMA32_PFN (((1ULL << 32) - (1ULL << 28)) >> PAGE_SHIFT)
+
 #endif

arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h

@@ -15,41 +15,40 @@
 
 struct device;
 
-dma_addr_t octeon_map_dma_mem(struct device *, void *, size_t);
-void octeon_unmap_dma_mem(struct device *, dma_addr_t);
+extern void octeon_pci_dma_init(void);
 
 static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
 	size_t size)
 {
-	return octeon_map_dma_mem(dev, addr, size);
+	BUG();
 }
 
 static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
 	struct page *page)
 {
-	return octeon_map_dma_mem(dev, page_address(page), PAGE_SIZE);
+	BUG();
 }
 
 static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
 	dma_addr_t dma_addr)
 {
-	return dma_addr;
+	BUG();
 }
 
 static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
 	size_t size, enum dma_data_direction direction)
 {
-	octeon_unmap_dma_mem(dev, dma_addr);
+	BUG();
 }
 
 static inline int plat_dma_supported(struct device *dev, u64 mask)
 {
-	return 1;
+	BUG();
 }
 
 static inline void plat_extra_sync_for_device(struct device *dev)
 {
-	mb();
+	BUG();
 }
 
 static inline int plat_device_is_coherent(struct device *dev)
@@ -60,7 +59,14 @@ static inline int plat_device_is_coherent(struct device *dev)
 static inline int plat_dma_mapping_error(struct device *dev,
 					 dma_addr_t dma_addr)
 {
-	return dma_addr == -1;
+	BUG();
 }
 
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
+
+struct dma_map_ops;
+extern struct dma_map_ops *octeon_pci_dma_map_ops;
+extern char *octeon_swiotlb;
+
 #endif /* __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H */

arch/mips/include/asm/mach-ip27/dma-coherence.h

@@ -26,14 +26,15 @@ static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
 	return pa;
 }
 
-static dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page)
+static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
+	struct page *page)
 {
 	dma_addr_t pa = dev_to_baddr(dev, page_to_phys(page));
 
 	return pa;
 }
 
-static unsigned long plat_dma_addr_to_phys(struct device *dev,
+static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
 	dma_addr_t dma_addr)
 {
 	return dma_addr & ~(0xffUL << 56);

arch/mips/include/asm/mach-ip32/dma-coherence.h

@@ -37,7 +37,8 @@ static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
 	return pa;
 }
 
-static dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page)
+static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
+	struct page *page)
 {
 	dma_addr_t pa;
 
@@ -50,7 +51,7 @@ static dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page)
 }
 
 /* This is almost certainly wrong but it's what dma-ip32.c used to use  */
-static unsigned long plat_dma_addr_to_phys(struct device *dev,
+static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
 	dma_addr_t dma_addr)
 {
 	unsigned long addr = dma_addr & RAM_OFFSET_MASK;

arch/mips/include/asm/mach-jazz/dma-coherence.h

@@ -12,23 +12,24 @@
 
 struct device;
 
-static dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size)
+static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size)
 {
 	return vdma_alloc(virt_to_phys(addr), size);
 }
 
-static dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page)
+static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
+	struct page *page)
 {
 	return vdma_alloc(page_to_phys(page), PAGE_SIZE);
 }
 
-static unsigned long plat_dma_addr_to_phys(struct device *dev,
+static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
 	dma_addr_t dma_addr)
 {
 	return vdma_log2phys(dma_addr);
 }
 
-static void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
+static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
 	size_t size, enum dma_data_direction direction)
 {
 	vdma_free(dma_addr);

arch/mips/include/asm/mipsregs.h

@@ -1040,6 +1040,12 @@ do {									\
 #define read_c0_dtaglo()	__read_32bit_c0_register($28, 2)
 #define write_c0_dtaglo(val)	__write_32bit_c0_register($28, 2, val)
 
+#define read_c0_ddatalo()	__read_32bit_c0_register($28, 3)
+#define write_c0_ddatalo(val)	__write_32bit_c0_register($28, 3, val)
+
+#define read_c0_staglo()	__read_32bit_c0_register($28, 4)
+#define write_c0_staglo(val)	__write_32bit_c0_register($28, 4, val)
+
 #define read_c0_taghi()		__read_32bit_c0_register($29, 0)
 #define write_c0_taghi(val)	__write_32bit_c0_register($29, 0, val)
 
@@ -1082,6 +1088,51 @@ do {									\
 #define read_octeon_c0_dcacheerr()	__read_64bit_c0_register($27, 1)
 #define write_octeon_c0_dcacheerr(val)	__write_64bit_c0_register($27, 1, val)
 
+/* BMIPS3300 */
+#define read_c0_brcm_config_0()		__read_32bit_c0_register($22, 0)
+#define write_c0_brcm_config_0(val)	__write_32bit_c0_register($22, 0, val)
+
+#define read_c0_brcm_bus_pll()		__read_32bit_c0_register($22, 4)
+#define write_c0_brcm_bus_pll(val)	__write_32bit_c0_register($22, 4, val)
+
+#define read_c0_brcm_reset()		__read_32bit_c0_register($22, 5)
+#define write_c0_brcm_reset(val)	__write_32bit_c0_register($22, 5, val)
+
+/* BMIPS4380 */
+#define read_c0_brcm_cmt_intr()		__read_32bit_c0_register($22, 1)
+#define write_c0_brcm_cmt_intr(val)	__write_32bit_c0_register($22, 1, val)
+
+#define read_c0_brcm_cmt_ctrl()		__read_32bit_c0_register($22, 2)
+#define write_c0_brcm_cmt_ctrl(val)	__write_32bit_c0_register($22, 2, val)
+
+#define read_c0_brcm_cmt_local()	__read_32bit_c0_register($22, 3)
+#define write_c0_brcm_cmt_local(val)	__write_32bit_c0_register($22, 3, val)
+
+#define read_c0_brcm_config_1()		__read_32bit_c0_register($22, 5)
+#define write_c0_brcm_config_1(val)	__write_32bit_c0_register($22, 5, val)
+
+#define read_c0_brcm_cbr()		__read_32bit_c0_register($22, 6)
+#define write_c0_brcm_cbr(val)		__write_32bit_c0_register($22, 6, val)
+
+/* BMIPS5000 */
+#define read_c0_brcm_config()		__read_32bit_c0_register($22, 0)
+#define write_c0_brcm_config(val)	__write_32bit_c0_register($22, 0, val)
+
+#define read_c0_brcm_mode()		__read_32bit_c0_register($22, 1)
+#define write_c0_brcm_mode(val)		__write_32bit_c0_register($22, 1, val)
+
+#define read_c0_brcm_action()		__read_32bit_c0_register($22, 2)
+#define write_c0_brcm_action(val)	__write_32bit_c0_register($22, 2, val)
+
+#define read_c0_brcm_edsp()		__read_32bit_c0_register($22, 3)
+#define write_c0_brcm_edsp(val)		__write_32bit_c0_register($22, 3, val)
+
+#define read_c0_brcm_bootvec()		__read_32bit_c0_register($22, 4)
+#define write_c0_brcm_bootvec(val)	__write_32bit_c0_register($22, 4, val)
+
+#define read_c0_brcm_sleepcount()	__read_32bit_c0_register($22, 7)
+#define write_c0_brcm_sleepcount(val)	__write_32bit_c0_register($22, 7, val)
+
 /*
  * Macros to access the floating point coprocessor control registers
  */

arch/mips/include/asm/octeon/cvmx-asm.h

@@ -114,6 +114,17 @@
 #define CVMX_DCACHE_INVALIDATE \
 	{ CVMX_SYNC; asm volatile ("cache 9, 0($0)" : : ); }
 
+#define CVMX_CACHE(op, address, offset)					\
+	asm volatile ("cache " CVMX_TMP_STR(op) ", " CVMX_TMP_STR(offset) "(%[rbase])" \
+		: : [rbase] "d" (address) )
+/* fetch and lock the state. */
+#define CVMX_CACHE_LCKL2(address, offset) CVMX_CACHE(31, address, offset)
+/* unlock the state. */
+#define CVMX_CACHE_WBIL2(address, offset) CVMX_CACHE(23, address, offset)
+/* invalidate the cache block and clear the USED bits for the block */
+#define CVMX_CACHE_WBIL2I(address, offset) CVMX_CACHE(3, address, offset)
+/* load virtual tag and data for the L2 cache block into L2C_TAD0_TAG register */
+#define CVMX_CACHE_LTGL2I(address, offset) CVMX_CACHE(7, address, offset)
 
 #define CVMX_POP(result, input) \
 	asm ("pop %[rd],%[rs]" : [rd] "=d" (result) : [rs] "d" (input))

arch/mips/include/asm/octeon/cvmx-gpio-defs.h

@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (c) 2003-2010 Cavium Networks
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -28,29 +28,22 @@
 #ifndef __CVMX_GPIO_DEFS_H__
 #define __CVMX_GPIO_DEFS_H__
 
-#define CVMX_GPIO_BIT_CFGX(offset) \
-	 CVMX_ADD_IO_SEG(0x0001070000000800ull + (((offset) & 15) * 8))
-#define CVMX_GPIO_BOOT_ENA \
-	 CVMX_ADD_IO_SEG(0x00010700000008A8ull)
-#define CVMX_GPIO_CLK_GENX(offset) \
-	 CVMX_ADD_IO_SEG(0x00010700000008C0ull + (((offset) & 3) * 8))
-#define CVMX_GPIO_DBG_ENA \
-	 CVMX_ADD_IO_SEG(0x00010700000008A0ull)
-#define CVMX_GPIO_INT_CLR \
-	 CVMX_ADD_IO_SEG(0x0001070000000898ull)
-#define CVMX_GPIO_RX_DAT \
-	 CVMX_ADD_IO_SEG(0x0001070000000880ull)
-#define CVMX_GPIO_TX_CLR \
-	 CVMX_ADD_IO_SEG(0x0001070000000890ull)
-#define CVMX_GPIO_TX_SET \
-	 CVMX_ADD_IO_SEG(0x0001070000000888ull)
-#define CVMX_GPIO_XBIT_CFGX(offset) \
-	 CVMX_ADD_IO_SEG(0x0001070000000900ull + (((offset) & 31) * 8) - 8 * 16)
+#define CVMX_GPIO_BIT_CFGX(offset) (CVMX_ADD_IO_SEG(0x0001070000000800ull) + ((offset) & 15) * 8)
+#define CVMX_GPIO_BOOT_ENA (CVMX_ADD_IO_SEG(0x00010700000008A8ull))
+#define CVMX_GPIO_CLK_GENX(offset) (CVMX_ADD_IO_SEG(0x00010700000008C0ull) + ((offset) & 3) * 8)
+#define CVMX_GPIO_CLK_QLMX(offset) (CVMX_ADD_IO_SEG(0x00010700000008E0ull) + ((offset) & 1) * 8)
+#define CVMX_GPIO_DBG_ENA (CVMX_ADD_IO_SEG(0x00010700000008A0ull))
+#define CVMX_GPIO_INT_CLR (CVMX_ADD_IO_SEG(0x0001070000000898ull))
+#define CVMX_GPIO_RX_DAT (CVMX_ADD_IO_SEG(0x0001070000000880ull))
+#define CVMX_GPIO_TX_CLR (CVMX_ADD_IO_SEG(0x0001070000000890ull))
+#define CVMX_GPIO_TX_SET (CVMX_ADD_IO_SEG(0x0001070000000888ull))
+#define CVMX_GPIO_XBIT_CFGX(offset) (CVMX_ADD_IO_SEG(0x0001070000000900ull) + ((offset) & 31) * 8 - 8*16)
 
 union cvmx_gpio_bit_cfgx {
 	uint64_t u64;
 	struct cvmx_gpio_bit_cfgx_s {
-		uint64_t reserved_15_63:49;
+		uint64_t reserved_17_63:47;
+		uint64_t synce_sel:2;
 		uint64_t clk_gen:1;
 		uint64_t clk_sel:2;
 		uint64_t fil_sel:4;
@@ -73,12 +66,24 @@ union cvmx_gpio_bit_cfgx {
 	struct cvmx_gpio_bit_cfgx_cn30xx cn38xx;
 	struct cvmx_gpio_bit_cfgx_cn30xx cn38xxp2;
 	struct cvmx_gpio_bit_cfgx_cn30xx cn50xx;
-	struct cvmx_gpio_bit_cfgx_s cn52xx;
-	struct cvmx_gpio_bit_cfgx_s cn52xxp1;
-	struct cvmx_gpio_bit_cfgx_s cn56xx;
-	struct cvmx_gpio_bit_cfgx_s cn56xxp1;
+	struct cvmx_gpio_bit_cfgx_cn52xx {
+		uint64_t reserved_15_63:49;
+		uint64_t clk_gen:1;
+		uint64_t clk_sel:2;
+		uint64_t fil_sel:4;
+		uint64_t fil_cnt:4;
+		uint64_t int_type:1;
+		uint64_t int_en:1;
+		uint64_t rx_xor:1;
+		uint64_t tx_oe:1;
+	} cn52xx;
+	struct cvmx_gpio_bit_cfgx_cn52xx cn52xxp1;
+	struct cvmx_gpio_bit_cfgx_cn52xx cn56xx;
+	struct cvmx_gpio_bit_cfgx_cn52xx cn56xxp1;
 	struct cvmx_gpio_bit_cfgx_cn30xx cn58xx;
 	struct cvmx_gpio_bit_cfgx_cn30xx cn58xxp1;
+	struct cvmx_gpio_bit_cfgx_s cn63xx;
+	struct cvmx_gpio_bit_cfgx_s cn63xxp1;
 };
 
 union cvmx_gpio_boot_ena {
@@ -103,6 +108,19 @@ union cvmx_gpio_clk_genx {
 	struct cvmx_gpio_clk_genx_s cn52xxp1;
 	struct cvmx_gpio_clk_genx_s cn56xx;
 	struct cvmx_gpio_clk_genx_s cn56xxp1;
+	struct cvmx_gpio_clk_genx_s cn63xx;
+	struct cvmx_gpio_clk_genx_s cn63xxp1;
+};
+
+union cvmx_gpio_clk_qlmx {
+	uint64_t u64;
+	struct cvmx_gpio_clk_qlmx_s {
+		uint64_t reserved_3_63:61;
+		uint64_t div:1;
+		uint64_t lane_sel:2;
+	} s;
+	struct cvmx_gpio_clk_qlmx_s cn63xx;
+	struct cvmx_gpio_clk_qlmx_s cn63xxp1;
 };
 
 union cvmx_gpio_dbg_ena {
@@ -133,6 +151,8 @@ union cvmx_gpio_int_clr {
 	struct cvmx_gpio_int_clr_s cn56xxp1;
 	struct cvmx_gpio_int_clr_s cn58xx;
 	struct cvmx_gpio_int_clr_s cn58xxp1;
+	struct cvmx_gpio_int_clr_s cn63xx;
+	struct cvmx_gpio_int_clr_s cn63xxp1;
 };
 
 union cvmx_gpio_rx_dat {
@@ -155,6 +175,8 @@ union cvmx_gpio_rx_dat {
 	struct cvmx_gpio_rx_dat_cn38xx cn56xxp1;
 	struct cvmx_gpio_rx_dat_cn38xx cn58xx;
 	struct cvmx_gpio_rx_dat_cn38xx cn58xxp1;
+	struct cvmx_gpio_rx_dat_cn38xx cn63xx;
+	struct cvmx_gpio_rx_dat_cn38xx cn63xxp1;
 };
 
 union cvmx_gpio_tx_clr {
@@ -177,6 +199,8 @@ union cvmx_gpio_tx_clr {
 	struct cvmx_gpio_tx_clr_cn38xx cn56xxp1;
 	struct cvmx_gpio_tx_clr_cn38xx cn58xx;
 	struct cvmx_gpio_tx_clr_cn38xx cn58xxp1;
+	struct cvmx_gpio_tx_clr_cn38xx cn63xx;
+	struct cvmx_gpio_tx_clr_cn38xx cn63xxp1;
 };
 
 union cvmx_gpio_tx_set {
@@ -199,6 +223,8 @@ union cvmx_gpio_tx_set {
 	struct cvmx_gpio_tx_set_cn38xx cn56xxp1;
 	struct cvmx_gpio_tx_set_cn38xx cn58xx;
 	struct cvmx_gpio_tx_set_cn38xx cn58xxp1;
+	struct cvmx_gpio_tx_set_cn38xx cn63xx;
+	struct cvmx_gpio_tx_set_cn38xx cn63xxp1;
 };
 
 union cvmx_gpio_xbit_cfgx {

arch/mips/include/asm/octeon/octeon.h

@@ -35,6 +35,7 @@ extern int octeon_is_simulation(void);
 extern int octeon_is_pci_host(void);
 extern int octeon_usb_is_ref_clk(void);
 extern uint64_t octeon_get_clock_rate(void);
+extern u64 octeon_get_io_clock_rate(void);
 extern const char *octeon_board_type_string(void);
 extern const char *octeon_get_pci_interrupts(void);
 extern int octeon_get_southbridge_interrupt(void);

drivers/usb/host/Makefile

@@ -34,3 +34,4 @@ obj-$(CONFIG_USB_ISP1760_HCD)	+= isp1760.o
 obj-$(CONFIG_USB_HWA_HCD)	+= hwa-hc.o
 obj-$(CONFIG_USB_IMX21_HCD)	+= imx21-hcd.o
 obj-$(CONFIG_USB_FSL_MPH_DR_OF)	+= fsl-mph-dr-of.o
+obj-$(CONFIG_USB_OCTEON2_COMMON) += octeon2-common.o