Merge tag 'soc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc

Pull ARM SoC platform changes from Olof Johansson:
 "New core SoC-specific changes.

  New platforms:
   * Introduction of a vendor, Hisilicon, and one of their SoCs with
     some random numerical product name.
   * Introduction of EFM32, embedded platform from Silicon Labs (ARMv7m,
     i.e. !MMU).
   * Marvell Berlin series of SoCs, which include the one in Chromecast.
   * MOXA platform support, ARM9-based platform used mostly in
     industrial products
   * Support for Freescale's i.MX50 SoC.

  Other work:
   * Renesas work for new platforms and drivers, and conversion over to
     more multiplatform-friendly device registration schemes.
   * SMP support for Allwinner sunxi platforms.
   * ... plus a bunch of other stuff across various platforms"

* tag 'soc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (201 commits)
  ARM: tegra: fix tegra_powergate_sequence_power_up() inline
  ARM: msm_defconfig: Update for multi-platform
  ARM: msm: Move MSM's DT based hardware to multi-platform support
  ARM: msm: Only build timer.c if required
  ARM: msm: Only build clock.c on proc_comm based platforms
  ARM: ux500: Enable system suspend with WFI support
  ARM: ux500: turn on PRINTK_TIME in u8500_defconfig
  ARM: shmobile: r8a7790: Fix I2C controller names
  ARM: msm: Simplify ARCH_MSM_DT config
  ARM: msm: Add support for MSM8974 SoC
  ARM: sunxi: select ARM_PSCI
  MAINTAINERS: Update Allwinner sunXi maintainer files
  ARM: sunxi: Select RESET_CONTROLLER
  ARM: imx: improve the comment of CCM lpm SW workaround
  ARM: imx: improve status check of clock gate
  ARM: imx: add necessary interface for pfd
  ARM: imx_v6_v7_defconfig: Select CONFIG_REGULATOR_PFUZE100
  ARM: imx_v6_v7_defconfig: Select MX35 and MX50 device tree support
  ARM: imx: Add cpu frequency scaling support
  ARM i.MX35: Add devicetree support.
  ...

5 files changed, 241 insertions, 14 deletions

diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index 15c0929..d1a12a4 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -65,6 +65,7 @@ config ARCH_TEGRA_124_SOC
 	bool "Enable support for Tegra124 family"
 	select ARM_L1_CACHE_SHIFT_6
 	select HAVE_ARM_ARCH_TIMER
+	select PINCTRL_TEGRA124
 	help
 	  Support for NVIDIA Tegra T124 processor family, based on the
 	  ARM CortexA15MP CPU
diff --git a/arch/arm/mach-tegra/fuse.c b/arch/arm/mach-tegra/fuse.c
index 3a9c1f1..c9ac23b 100644
--- a/arch/arm/mach-tegra/fuse.c
+++ b/arch/arm/mach-tegra/fuse.c
@@ -22,6 +22,7 @@
 #include <linux/io.h>
 #include <linux/export.h>
 #include <linux/random.h>
+#include <linux/clk.h>
 #include <linux/tegra-soc.h>
 
 #include "fuse.h"
@@ -54,6 +55,7 @@ int tegra_cpu_speedo_id;		/* only exist in Tegra30 and later */
 int tegra_soc_speedo_id;
 enum tegra_revision tegra_revision;
 
+static struct clk *fuse_clk;
 static int tegra_fuse_spare_bit;
 static void (*tegra_init_speedo_data)(void);
 
@@ -77,6 +79,22 @@ static const char *tegra_revision_name[TEGRA_REVISION_MAX] = {
 	[TEGRA_REVISION_A04]     = "A04",
 };
 
+static void tegra_fuse_enable_clk(void)
+{
+	if (IS_ERR(fuse_clk))
+		fuse_clk = clk_get_sys(NULL, "fuse");
+	if (IS_ERR(fuse_clk))
+		return;
+	clk_prepare_enable(fuse_clk);
+}
+
+static void tegra_fuse_disable_clk(void)
+{
+	if (IS_ERR(fuse_clk))
+		return;
+	clk_disable_unprepare(fuse_clk);
+}
+
 u32 tegra_fuse_readl(unsigned long offset)
 {
 	return tegra_apb_readl(TEGRA_FUSE_BASE + offset);
@@ -84,7 +102,15 @@ u32 tegra_fuse_readl(unsigned long offset)
 
 bool tegra_spare_fuse(int bit)
 {
-	return tegra_fuse_readl(tegra_fuse_spare_bit + bit * 4);
+	bool ret;
+
+	tegra_fuse_enable_clk();
+
+	ret = tegra_fuse_readl(tegra_fuse_spare_bit + bit * 4);
+
+	tegra_fuse_disable_clk();
+
+	return ret;
 }
 
 static enum tegra_revision tegra_get_revision(u32 id)
@@ -113,10 +139,14 @@ static void tegra_get_process_id(void)
 {
 	u32 reg;
 
+	tegra_fuse_enable_clk();
+
 	reg = tegra_fuse_readl(tegra_fuse_spare_bit);
 	tegra_cpu_process_id = (reg >> 6) & 3;
 	reg = tegra_fuse_readl(tegra_fuse_spare_bit);
 	tegra_core_process_id = (reg >> 12) & 3;
+
+	tegra_fuse_disable_clk();
 }
 
 u32 tegra_read_chipid(void)
@@ -159,6 +189,15 @@ void __init tegra_init_fuse(void)
 	reg |= 1 << 28;
 	writel(reg, IO_ADDRESS(TEGRA_CLK_RESET_BASE + 0x48));
 
+	/*
+	 * Enable FUSE clock. This needs to be hardcoded because the clock
+	 * subsystem is not active during early boot.
+	 */
+	reg = readl(IO_ADDRESS(TEGRA_CLK_RESET_BASE + 0x14));
+	reg |= 1 << 7;
+	writel(reg, IO_ADDRESS(TEGRA_CLK_RESET_BASE + 0x14));
+	fuse_clk = ERR_PTR(-EINVAL);
+
 	reg = tegra_fuse_readl(FUSE_SKU_INFO);
 	randomness[0] = reg;
 	tegra_sku_id = reg & 0xFF;
diff --git a/arch/arm/mach-tegra/iomap.h b/arch/arm/mach-tegra/iomap.h
index 26b1c2a..ee79808 100644
--- a/arch/arm/mach-tegra/iomap.h
+++ b/arch/arm/mach-tegra/iomap.h
@@ -19,6 +19,7 @@
 #ifndef __MACH_TEGRA_IOMAP_H
 #define __MACH_TEGRA_IOMAP_H
 
+#include <asm/pgtable.h>
 #include <asm/sizes.h>
 
 #define TEGRA_IRAM_BASE			0x40000000
@@ -115,27 +116,26 @@
  * two 256MB io windows (that actually only use about 64KB
  * at the start of each).
  *
- * We will just map the first 1MB of each window (to minimize
+ * We will just map the first MMU section of each window (to minimize
  * pt entries needed) and provide a macro to transform physical
  * io addresses to an appropriate void __iomem *.
- *
  */
 
 #define IO_IRAM_PHYS	0x40000000
 #define IO_IRAM_VIRT	IOMEM(0xFE400000)
 #define IO_IRAM_SIZE	SZ_256K
 
-#define IO_CPU_PHYS     0x50040000
-#define IO_CPU_VIRT     IOMEM(0xFE000000)
+#define IO_CPU_PHYS	0x50040000
+#define IO_CPU_VIRT	IOMEM(0xFE440000)
 #define IO_CPU_SIZE	SZ_16K
 
 #define IO_PPSB_PHYS	0x60000000
 #define IO_PPSB_VIRT	IOMEM(0xFE200000)
-#define IO_PPSB_SIZE	SZ_1M
+#define IO_PPSB_SIZE	SECTION_SIZE
 
 #define IO_APB_PHYS	0x70000000
-#define IO_APB_VIRT	IOMEM(0xFE300000)
-#define IO_APB_SIZE	SZ_1M
+#define IO_APB_VIRT	IOMEM(0xFE000000)
+#define IO_APB_SIZE	SECTION_SIZE
 
 #define IO_TO_VIRT_BETWEEN(p, st, sz)	((p) >= (st) && (p) < ((st) + (sz)))
 #define IO_TO_VIRT_XLATE(p, pst, vst)	(((p) - (pst) + (vst)))
diff --git a/arch/arm/mach-tegra/powergate.c b/arch/arm/mach-tegra/powergate.c
index f6f5b54..3d0c537 100644
--- a/arch/arm/mach-tegra/powergate.c
+++ b/arch/arm/mach-tegra/powergate.c
@@ -34,6 +34,10 @@
 #include "fuse.h"
 #include "iomap.h"
 
+#define DPD_SAMPLE		0x020
+#define  DPD_SAMPLE_ENABLE	(1 << 0)
+#define  DPD_SAMPLE_DISABLE	(0 << 0)
+
 #define PWRGATE_TOGGLE		0x30
 #define  PWRGATE_TOGGLE_START	(1 << 8)
 
@@ -41,6 +45,19 @@
 
 #define PWRGATE_STATUS		0x38
 
+#define IO_DPD_REQ		0x1b8
+#define  IO_DPD_REQ_CODE_IDLE	(0 << 30)
+#define  IO_DPD_REQ_CODE_OFF	(1 << 30)
+#define  IO_DPD_REQ_CODE_ON	(2 << 30)
+#define  IO_DPD_REQ_CODE_MASK	(3 << 30)
+
+#define IO_DPD_STATUS		0x1bc
+#define IO_DPD2_REQ		0x1c0
+#define IO_DPD2_STATUS		0x1c4
+#define SEL_DPD_TIM		0x1c8
+
+#define GPU_RG_CNTRL		0x2d4
+
 static int tegra_num_powerdomains;
 static int tegra_num_cpu_domains;
 static const u8 *tegra_cpu_domains;
@@ -59,6 +76,13 @@ static const u8 tegra114_cpu_domains[] = {
 	TEGRA_POWERGATE_CPU3,
 };
 
+static const u8 tegra124_cpu_domains[] = {
+	TEGRA_POWERGATE_CPU0,
+	TEGRA_POWERGATE_CPU1,
+	TEGRA_POWERGATE_CPU2,
+	TEGRA_POWERGATE_CPU3,
+};
+
 static DEFINE_SPINLOCK(tegra_powergate_lock);
 
 static void __iomem *pmc = IO_ADDRESS(TEGRA_PMC_BASE);
@@ -109,6 +133,7 @@ int tegra_powergate_power_off(int id)
 
 	return tegra_powergate_set(id, false);
 }
+EXPORT_SYMBOL(tegra_powergate_power_off);
 
 int tegra_powergate_is_powered(int id)
 {
@@ -129,12 +154,23 @@ int tegra_powergate_remove_clamping(int id)
 		return -EINVAL;
 
 	/*
+	 * The Tegra124 GPU has a separate register (with different semantics)
+	 * to remove clamps.
+	 */
+	if (tegra_chip_id == TEGRA124) {
+		if (id == TEGRA_POWERGATE_3D) {
+			pmc_write(0, GPU_RG_CNTRL);
+			return 0;
+		}
+	}
+
+	/*
 	 * Tegra 2 has a bug where PCIE and VDE clamping masks are
 	 * swapped relatively to the partition ids
 	 */
-	if (id ==  TEGRA_POWERGATE_VDEC)
+	if (id == TEGRA_POWERGATE_VDEC)
 		mask = (1 << TEGRA_POWERGATE_PCIE);
-	else if	(id == TEGRA_POWERGATE_PCIE)
+	else if (id == TEGRA_POWERGATE_PCIE)
 		mask = (1 << TEGRA_POWERGATE_VDEC);
 	else
 		mask = (1 << id);
@@ -143,6 +179,7 @@ int tegra_powergate_remove_clamping(int id)
 
 	return 0;
 }
+EXPORT_SYMBOL(tegra_powergate_remove_clamping);
 
 /* Must be called with clk disabled, and returns with clk enabled */
 int tegra_powergate_sequence_power_up(int id, struct clk *clk,
@@ -204,6 +241,11 @@ int __init tegra_powergate_init(void)
 		tegra_num_cpu_domains = 4;
 		tegra_cpu_domains = tegra114_cpu_domains;
 		break;
+	case TEGRA124:
+		tegra_num_powerdomains = 25;
+		tegra_num_cpu_domains = 4;
+		tegra_cpu_domains = tegra124_cpu_domains;
+		break;
 	default:
 		/* Unknown Tegra variant. Disable powergating */
 		tegra_num_powerdomains = 0;
@@ -245,12 +287,36 @@ static const char * const powergate_name_t30[] = {
 };
 
 static const char * const powergate_name_t114[] = {
-	[TEGRA_POWERGATE_CPU]	= "cpu0",
+	[TEGRA_POWERGATE_CPU]	= "crail",
+	[TEGRA_POWERGATE_3D]	= "3d",
+	[TEGRA_POWERGATE_VENC]	= "venc",
+	[TEGRA_POWERGATE_VDEC]	= "vdec",
+	[TEGRA_POWERGATE_MPE]	= "mpe",
+	[TEGRA_POWERGATE_HEG]	= "heg",
+	[TEGRA_POWERGATE_CPU1]	= "cpu1",
+	[TEGRA_POWERGATE_CPU2]	= "cpu2",
+	[TEGRA_POWERGATE_CPU3]	= "cpu3",
+	[TEGRA_POWERGATE_CELP]	= "celp",
+	[TEGRA_POWERGATE_CPU0]	= "cpu0",
+	[TEGRA_POWERGATE_C0NC]	= "c0nc",
+	[TEGRA_POWERGATE_C1NC]	= "c1nc",
+	[TEGRA_POWERGATE_DIS]	= "dis",
+	[TEGRA_POWERGATE_DISB]	= "disb",
+	[TEGRA_POWERGATE_XUSBA]	= "xusba",
+	[TEGRA_POWERGATE_XUSBB]	= "xusbb",
+	[TEGRA_POWERGATE_XUSBC]	= "xusbc",
+};
+
+static const char * const powergate_name_t124[] = {
+	[TEGRA_POWERGATE_CPU]	= "crail",
 	[TEGRA_POWERGATE_3D]	= "3d",
 	[TEGRA_POWERGATE_VENC]	= "venc",
+	[TEGRA_POWERGATE_PCIE]	= "pcie",
 	[TEGRA_POWERGATE_VDEC]	= "vdec",
+	[TEGRA_POWERGATE_L2]	= "l2",
 	[TEGRA_POWERGATE_MPE]	= "mpe",
 	[TEGRA_POWERGATE_HEG]	= "heg",
+	[TEGRA_POWERGATE_SATA]	= "sata",
 	[TEGRA_POWERGATE_CPU1]	= "cpu1",
 	[TEGRA_POWERGATE_CPU2]	= "cpu2",
 	[TEGRA_POWERGATE_CPU3]	= "cpu3",
@@ -258,11 +324,14 @@ static const char * const powergate_name_t114[] = {
 	[TEGRA_POWERGATE_CPU0]	= "cpu0",
 	[TEGRA_POWERGATE_C0NC]	= "c0nc",
 	[TEGRA_POWERGATE_C1NC]	= "c1nc",
+	[TEGRA_POWERGATE_SOR]	= "sor",
 	[TEGRA_POWERGATE_DIS]	= "dis",
 	[TEGRA_POWERGATE_DISB]	= "disb",
 	[TEGRA_POWERGATE_XUSBA]	= "xusba",
 	[TEGRA_POWERGATE_XUSBB]	= "xusbb",
 	[TEGRA_POWERGATE_XUSBC]	= "xusbc",
+	[TEGRA_POWERGATE_VIC]	= "vic",
+	[TEGRA_POWERGATE_IRAM]	= "iram",
 };
 
 static int powergate_show(struct seq_file *s, void *data)
@@ -309,6 +378,9 @@ int __init tegra_powergate_debugfs_init(void)
 	case TEGRA114:
 		powergate_name = powergate_name_t114;
 		break;
+	case TEGRA124:
+		powergate_name = powergate_name_t124;
+		break;
 	}
 
 	if (powergate_name) {
@@ -322,3 +394,120 @@ int __init tegra_powergate_debugfs_init(void)
 }
 
 #endif
+
+static int tegra_io_rail_prepare(int id, unsigned long *request,
+				 unsigned long *status, unsigned int *bit)
+{
+	unsigned long rate, value;
+	struct clk *clk;
+
+	*bit = id % 32;
+
+	/*
+	 * There are two sets of 30 bits to select IO rails, but bits 30 and
+	 * 31 are control bits rather than IO rail selection bits.
+	 */
+	if (id > 63 || *bit == 30 || *bit == 31)
+		return -EINVAL;
+
+	if (id < 32) {
+		*status = IO_DPD_STATUS;
+		*request = IO_DPD_REQ;
+	} else {
+		*status = IO_DPD2_STATUS;
+		*request = IO_DPD2_REQ;
+	}
+
+	clk = clk_get_sys(NULL, "pclk");
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	rate = clk_get_rate(clk);
+	clk_put(clk);
+
+	pmc_write(DPD_SAMPLE_ENABLE, DPD_SAMPLE);
+
+	/* must be at least 200 ns, in APB (PCLK) clock cycles */
+	value = DIV_ROUND_UP(1000000000, rate);
+	value = DIV_ROUND_UP(200, value);
+	pmc_write(value, SEL_DPD_TIM);
+
+	return 0;
+}
+
+static int tegra_io_rail_poll(unsigned long offset, unsigned long mask,
+			      unsigned long val, unsigned long timeout)
+{
+	unsigned long value;
+
+	timeout = jiffies + msecs_to_jiffies(timeout);
+
+	while (time_after(timeout, jiffies)) {
+		value = pmc_read(offset);
+		if ((value & mask) == val)
+			return 0;
+
+		usleep_range(250, 1000);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static void tegra_io_rail_unprepare(void)
+{
+	pmc_write(DPD_SAMPLE_DISABLE, DPD_SAMPLE);
+}
+
+int tegra_io_rail_power_on(int id)
+{
+	unsigned long request, status, value;
+	unsigned int bit, mask;
+	int err;
+
+	err = tegra_io_rail_prepare(id, &request, &status, &bit);
+	if (err < 0)
+		return err;
+
+	mask = 1 << bit;
+
+	value = pmc_read(request);
+	value |= mask;
+	value &= ~IO_DPD_REQ_CODE_MASK;
+	value |= IO_DPD_REQ_CODE_OFF;
+	pmc_write(value, request);
+
+	err = tegra_io_rail_poll(status, mask, 0, 250);
+	if (err < 0)
+		return err;
+
+	tegra_io_rail_unprepare();
+
+	return 0;
+}
+
+int tegra_io_rail_power_off(int id)
+{
+	unsigned long request, status, value;
+	unsigned int bit, mask;
+	int err;
+
+	err = tegra_io_rail_prepare(id, &request, &status, &bit);
+	if (err < 0)
+		return err;
+
+	mask = 1 << bit;
+
+	value = pmc_read(request);
+	value |= mask;
+	value &= ~IO_DPD_REQ_CODE_MASK;
+	value |= IO_DPD_REQ_CODE_ON;
+	pmc_write(value, request);
+
+	err = tegra_io_rail_poll(status, mask, mask, 250);
+	if (err < 0)
+		return err;
+
+	tegra_io_rail_unprepare();
+
+	return 0;
+}
diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c
index 7336817..ea14d38 100644
--- a/arch/arm/mach-tegra/tegra.c
+++ b/arch/arm/mach-tegra/tegra.c
@@ -60,15 +60,13 @@
  * kernel is loaded. The data is declared here rather than debug-macro.S so
  * that multiple inclusions of debug-macro.S point at the same data.
  */
-u32 tegra_uart_config[4] = {
+u32 tegra_uart_config[3] = {
 	/* Debug UART initialization required */
 	1,
 	/* Debug UART physical address */
 	0,
 	/* Debug UART virtual address */
 	0,
-	/* Scratch space for debug macro */
-	0,
 };
 
 static void __init tegra_init_cache(void)