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:
 "This branch contains mostly additions and changes to platform
  enablement and SoC-level drivers.  Since there's sometimes a
  dependency on device-tree changes, there's also a fair amount of
  those in this branch.

  Pieces worth mentioning are:

   - Mbus driver for Marvell platforms, allowing kernel configuration
     and resource allocation of on-chip peripherals.
   - Enablement of the mbus infrastructure from Marvell PCI-e drivers.
   - Preparation of MSI support for Marvell platforms.
   - Addition of new PCI-e host controller driver for Tegra platforms
   - Some churn caused by sharing of macro names between i.MX 6Q and 6DL
     platforms in the device tree sources and header files.
   - Various suspend/PM updates for Tegra, including LP1 support.
   - Versatile Express support for MCPM, part of big little support.
   - Allwinner platform support for A20 and A31 SoCs (dual and quad
     Cortex-A7)
   - OMAP2+ support for DRA7, a new Cortex-A15-based SoC.

  The code that touches other architectures are patches moving MSI
  arch-specific functions over to weak symbols and removal of
  ARCH_SUPPORTS_MSI, acked by PCI maintainers"

* tag 'soc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (266 commits)
  tegra-cpuidle: provide stub when !CONFIG_CPU_IDLE
  PCI: tegra: replace devm_request_and_ioremap by devm_ioremap_resource
  ARM: tegra: Drop ARCH_SUPPORTS_MSI and sort list
  ARM: dts: vf610-twr: enable i2c0 device
  ARM: dts: i.MX51: Add one more I2C2 pinmux entry
  ARM: dts: i.MX51: Move pins configuration under "iomuxc" label
  ARM: dtsi: imx6qdl-sabresd: Add USB OTG vbus pin to pinctrl_hog
  ARM: dtsi: imx6qdl-sabresd: Add USB host 1 VBUS regulator
  ARM: dts: imx27-phytec-phycore-som: Enable AUDMUX
  ARM: dts: i.MX27: Disable AUDMUX in the template
  ARM: dts: wandboard: Add support for SDIO bcm4329
  ARM: i.MX5 clocks: Remove optional clock setup (CKIH1) from i.MX51 template
  ARM: dts: imx53-qsb: Make USBH1 functional
  ARM i.MX6Q: dts: Enable I2C1 with EEPROM and PMIC on Phytec phyFLEX-i.MX6 Ouad module
  ARM i.MX6Q: dts: Enable SPI NOR flash on Phytec phyFLEX-i.MX6 Ouad module
  ARM: dts: imx6qdl-sabresd: Add touchscreen support
  ARM: imx: add ocram clock for imx53
  ARM: dts: imx: ocram size is different between imx6q and imx6dl
  ARM: dts: imx27-phytec-phycore-som: Fix regulator settings
  ARM: dts: i.MX27: Remove clock name from CPU node
  ...

1 files changed, 191 insertions, 8 deletions

diff --git a/arch/arm/mach-shmobile/clock-r8a73a4.c b/arch/arm/mach-shmobile/clock-r8a73a4.c
index 5f7fe628b8a1..8ea5ef6c79cc 100644
--- a/arch/arm/mach-shmobile/clock-r8a73a4.c
+++ b/arch/arm/mach-shmobile/clock-r8a73a4.c
@@ -30,10 +30,12 @@
 
 #define SMSTPCR2 0xe6150138
 #define SMSTPCR3 0xe615013c
+#define SMSTPCR4 0xe6150140
 #define SMSTPCR5 0xe6150144
 
 #define FRQCRA		0xE6150000
 #define FRQCRB		0xE6150004
+#define FRQCRC		0xE61500E0
 #define VCLKCR1		0xE6150008
 #define VCLKCR2		0xE615000C
 #define VCLKCR3		0xE615001C
@@ -52,6 +54,7 @@
 #define HSICKCR		0xE615026C
 #define M4CKCR		0xE6150098
 #define PLLECR		0xE61500D0
+#define PLL0CR		0xE61500D8
 #define PLL1CR		0xE6150028
 #define PLL2CR		0xE615002C
 #define PLL2SCR		0xE61501F4
@@ -177,6 +180,7 @@ static struct sh_clk_ops pll_clk_ops = {
 		.mapping	= &cpg_mapping,		\
 	}
 
+PLL_CLOCK(pll0_clk,  &main_clk,      pll_parent_main,      1, 20, PLL0CR,  0);
 PLL_CLOCK(pll1_clk,  &main_clk,      pll_parent_main,       1, 7, PLL1CR,  1);
 PLL_CLOCK(pll2_clk,  &main_div2_clk, pll_parent_main_extal, 3, 5, PLL2CR,  2);
 PLL_CLOCK(pll2s_clk, &main_div2_clk, pll_parent_main_extal, 3, 5, PLL2SCR, 4);
@@ -184,6 +188,157 @@ PLL_CLOCK(pll2h_clk, &main_div2_clk, pll_parent_main_extal, 3, 5, PLL2HCR, 5);
 
 SH_FIXED_RATIO_CLK(pll1_div2_clk,	pll1_clk,	div2);
 
+static atomic_t frqcr_lock;
+
+/* Several clocks need to access FRQCRB, have to lock */
+static bool frqcr_kick_check(struct clk *clk)
+{
+	return !(ioread32(CPG_MAP(FRQCRB)) & BIT(31));
+}
+
+static int frqcr_kick_do(struct clk *clk)
+{
+	int i;
+
+	/* set KICK bit in FRQCRB to update hardware setting, check success */
+	iowrite32(ioread32(CPG_MAP(FRQCRB)) | BIT(31), CPG_MAP(FRQCRB));
+	for (i = 1000; i; i--)
+		if (ioread32(CPG_MAP(FRQCRB)) & BIT(31))
+			cpu_relax();
+		else
+			return 0;
+
+	return -ETIMEDOUT;
+}
+
+static int zclk_set_rate(struct clk *clk, unsigned long rate)
+{
+	void __iomem *frqcrc;
+	int ret;
+	unsigned long step, p_rate;
+	u32 val;
+
+	if (!clk->parent || !__clk_get(clk->parent))
+		return -ENODEV;
+
+	if (!atomic_inc_and_test(&frqcr_lock) || !frqcr_kick_check(clk)) {
+		ret = -EBUSY;
+		goto done;
+	}
+
+	/*
+	 * Users are supposed to first call clk_set_rate() only with
+	 * clk_round_rate() results. So, we don't fix wrong rates here, but
+	 * guard against them anyway
+	 */
+
+	p_rate = clk_get_rate(clk->parent);
+	if (rate == p_rate) {
+		val = 0;
+	} else {
+		step = DIV_ROUND_CLOSEST(p_rate, 32);
+
+		if (rate > p_rate || rate < step) {
+			ret = -EINVAL;
+			goto done;
+		}
+
+		val = 32 - rate / step;
+	}
+
+	frqcrc = clk->mapped_reg + (FRQCRC - (u32)clk->enable_reg);
+
+	iowrite32((ioread32(frqcrc) & ~(clk->div_mask << clk->enable_bit)) |
+		  (val << clk->enable_bit), frqcrc);
+
+	ret = frqcr_kick_do(clk);
+
+done:
+	atomic_dec(&frqcr_lock);
+	__clk_put(clk->parent);
+	return ret;
+}
+
+static long zclk_round_rate(struct clk *clk, unsigned long rate)
+{
+	/*
+	 * theoretical rate = parent rate * multiplier / 32,
+	 * where 1 <= multiplier <= 32. Therefore we should do
+	 * multiplier = rate * 32 / parent rate
+	 * rounded rate = parent rate * multiplier / 32.
+	 * However, multiplication before division won't fit in 32 bits, so
+	 * we sacrifice some precision by first dividing and then multiplying.
+	 * To find the nearest divisor we calculate both and pick up the best
+	 * one. This avoids 64-bit arithmetics.
+	 */
+	unsigned long step, mul_min, mul_max, rate_min, rate_max;
+
+	rate_max = clk_get_rate(clk->parent);
+
+	/* output freq <= parent */
+	if (rate >= rate_max)
+		return rate_max;
+
+	step = DIV_ROUND_CLOSEST(rate_max, 32);
+	/* output freq >= parent / 32 */
+	if (step >= rate)
+		return step;
+
+	mul_min = rate / step;
+	mul_max = DIV_ROUND_UP(rate, step);
+	rate_min = step * mul_min;
+	if (mul_max == mul_min)
+		return rate_min;
+
+	rate_max = step * mul_max;
+
+	if (rate_max - rate <  rate - rate_min)
+		return rate_max;
+
+	return rate_min;
+}
+
+static unsigned long zclk_recalc(struct clk *clk)
+{
+	void __iomem *frqcrc = FRQCRC - (u32)clk->enable_reg + clk->mapped_reg;
+	unsigned int max = clk->div_mask + 1;
+	unsigned long val = ((ioread32(frqcrc) >> clk->enable_bit) &
+			     clk->div_mask);
+
+	return DIV_ROUND_CLOSEST(clk_get_rate(clk->parent), max) *
+		(max - val);
+}
+
+static struct sh_clk_ops zclk_ops = {
+	.recalc = zclk_recalc,
+	.set_rate = zclk_set_rate,
+	.round_rate = zclk_round_rate,
+};
+
+static struct clk z_clk = {
+	.parent = &pll0_clk,
+	.div_mask = 0x1f,
+	.enable_bit = 8,
+	/* We'll need to access FRQCRB and FRQCRC */
+	.enable_reg = (void __iomem *)FRQCRB,
+	.ops = &zclk_ops,
+};
+
+/*
+ * It seems only 1/2 divider is usable in manual mode. 1/2 / 2/3
+ * switching is only available in auto-DVFS mode
+ */
+SH_FIXED_RATIO_CLK(pll0_div2_clk,	pll0_clk,		div2);
+
+static struct clk z2_clk = {
+	.parent = &pll0_div2_clk,
+	.div_mask = 0x1f,
+	.enable_bit = 0,
+	/* We'll need to access FRQCRB and FRQCRC */
+	.enable_reg = (void __iomem *)FRQCRB,
+	.ops = &zclk_ops,
+};
+
 static struct clk *main_clks[] = {
 	&extalr_clk,
 	&extal1_clk,
@@ -195,22 +350,23 @@ static struct clk *main_clks[] = {
 	&main_div2_clk,
 	&fsiack_clk,
 	&fsibck_clk,
+	&pll0_clk,
 	&pll1_clk,
 	&pll1_div2_clk,
 	&pll2_clk,
 	&pll2s_clk,
 	&pll2h_clk,
+	&z_clk,
+	&pll0_div2_clk,
+	&z2_clk,
 };
 
 /* DIV4 */
 static void div4_kick(struct clk *clk)
 {
-	unsigned long value;
-
-	/* set KICK bit in FRQCRB to update hardware setting */
-	value = ioread32(CPG_MAP(FRQCRB));
-	value |= (1 << 31);
-	iowrite32(value, CPG_MAP(FRQCRB));
+	if (!WARN(!atomic_inc_and_test(&frqcr_lock), "FRQCR* lock broken!\n"))
+		frqcr_kick_do(clk);
+	atomic_dec(&frqcr_lock);
 }
 
 static int divisors[] = { 2, 3, 4, 6, 8, 12, 16, 18, 24, 0, 36, 48, 10};
@@ -349,8 +505,10 @@ static struct clk div6_clks[DIV6_NR] = {
 /* MSTP */
 enum {
 	MSTP217, MSTP216, MSTP207, MSTP206, MSTP204, MSTP203,
-	MSTP315, MSTP314, MSTP313, MSTP312, MSTP305,
-	MSTP522,
+	MSTP329, MSTP323, MSTP318, MSTP317, MSTP316,
+	MSTP315, MSTP314, MSTP313, MSTP312, MSTP305, MSTP300,
+	MSTP411, MSTP410, MSTP409,
+	MSTP522, MSTP515,
 	MSTP_NR
 };
 
@@ -361,12 +519,22 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP207] = SH_CLK_MSTP32(&div6_clks[DIV6_MP],	SMSTPCR2, 7, 0), /* SCIFB1 */
 	[MSTP216] = SH_CLK_MSTP32(&div6_clks[DIV6_MP],	SMSTPCR2, 16, 0), /* SCIFB2 */
 	[MSTP217] = SH_CLK_MSTP32(&div6_clks[DIV6_MP],	SMSTPCR2, 17, 0), /* SCIFB3 */
+	[MSTP300] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 0, 0), /* IIC2 */
 	[MSTP305] = SH_CLK_MSTP32(&div6_clks[DIV6_MMC1],SMSTPCR3, 5, 0), /* MMCIF1 */
 	[MSTP312] = SH_CLK_MSTP32(&div6_clks[DIV6_SDHI2],SMSTPCR3, 12, 0), /* SDHI2 */
 	[MSTP313] = SH_CLK_MSTP32(&div6_clks[DIV6_SDHI1],SMSTPCR3, 13, 0), /* SDHI1 */
 	[MSTP314] = SH_CLK_MSTP32(&div6_clks[DIV6_SDHI0],SMSTPCR3, 14, 0), /* SDHI0 */
 	[MSTP315] = SH_CLK_MSTP32(&div6_clks[DIV6_MMC0],SMSTPCR3, 15, 0), /* MMCIF0 */
+	[MSTP316] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 16, 0), /* IIC6 */
+	[MSTP317] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 17, 0), /* IIC7 */
+	[MSTP318] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 18, 0), /* IIC0 */
+	[MSTP323] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR3, 23, 0), /* IIC1 */
+	[MSTP329] = SH_CLK_MSTP32(&extalr_clk, SMSTPCR3, 29, 0), /* CMT10 */
+	[MSTP409] = SH_CLK_MSTP32(&main_div2_clk,	SMSTPCR4, 9, 0), /* IIC5 */
+	[MSTP410] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR4, 10, 0), /* IIC4 */
+	[MSTP411] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR4, 11, 0), /* IIC3 */
 	[MSTP522] = SH_CLK_MSTP32(&extal2_clk, SMSTPCR5, 22, 0), /* Thermal */
+	[MSTP515] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],	SMSTPCR5, 15, 0), /* IIC8 */
 };
 
 static struct clk_lookup lookups[] = {
@@ -386,6 +554,9 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_CON_ID("pll2s",			&pll2s_clk),
 	CLKDEV_CON_ID("pll2h",			&pll2h_clk),
 
+	/* CPU clock */
+	CLKDEV_DEV_ID("cpufreq-cpu0",		&z_clk),
+
 	/* DIV6 */
 	CLKDEV_CON_ID("zb",			&div6_clks[DIV6_ZB]),
 	CLKDEV_CON_ID("vck1",			&div6_clks[DIV6_VCK1]),
@@ -408,6 +579,7 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("sh-sci.4", &mstp_clks[MSTP216]),
 	CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP217]),
 	CLKDEV_DEV_ID("rcar_thermal", &mstp_clks[MSTP522]),
+	CLKDEV_DEV_ID("e6520000.i2c", &mstp_clks[MSTP300]),
 	CLKDEV_DEV_ID("sh_mmcif.1", &mstp_clks[MSTP305]),
 	CLKDEV_DEV_ID("ee220000.mmcif", &mstp_clks[MSTP305]),
 	CLKDEV_DEV_ID("sh_mobile_sdhi.2", &mstp_clks[MSTP312]),
@@ -418,6 +590,15 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("ee100000.sdhi", &mstp_clks[MSTP314]),
 	CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP315]),
 	CLKDEV_DEV_ID("ee200000.mmcif", &mstp_clks[MSTP315]),
+	CLKDEV_DEV_ID("e6550000.i2c", &mstp_clks[MSTP316]),
+	CLKDEV_DEV_ID("e6560000.i2c", &mstp_clks[MSTP317]),
+	CLKDEV_DEV_ID("e6500000.i2c", &mstp_clks[MSTP318]),
+	CLKDEV_DEV_ID("e6510000.i2c", &mstp_clks[MSTP323]),
+	CLKDEV_DEV_ID("sh_cmt.10", &mstp_clks[MSTP329]),
+	CLKDEV_DEV_ID("e60b0000.i2c", &mstp_clks[MSTP409]),
+	CLKDEV_DEV_ID("e6540000.i2c", &mstp_clks[MSTP410]),
+	CLKDEV_DEV_ID("e6530000.i2c", &mstp_clks[MSTP411]),
+	CLKDEV_DEV_ID("e6570000.i2c", &mstp_clks[MSTP515]),
 
 	/* for DT */
 	CLKDEV_DEV_ID("e61f0000.thermal", &mstp_clks[MSTP522]),
@@ -429,6 +610,8 @@ void __init r8a73a4_clock_init(void)
 	int k, ret = 0;
 	u32 ckscr;
 
+	atomic_set(&frqcr_lock, -1);
+
 	reg = ioremap_nocache(CKSCR, PAGE_SIZE);
 	BUG_ON(!reg);
 	ckscr = ioread32(reg);