Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM updates from Russell King:
 "This contains the usual updates from other people (listed below) and
  the usual random muddle of miscellaneous ARM updates which cover some
  low priority bug fixes and performance improvements.

  I've started to put the pull request wording into the merge commits,
  which are:

   - NoMMU stuff:

     This includes the following series sent earlier to the list:
      - nommu-fixes
      - R7 Support
      - MPU support

     I've left out the ARCH_MULTIPLATFORM/!MMU stuff that Arnd and I
     were discussing today until we've reached a conclusion/that's had
     some more review.

     This is rebased (and re-tested) on your devel-stable branch because
     otherwise there were going to be conflicts with Uwe's V7M work now
     that you've merged that.  I've included the fix for limiting MPU to
     CPU_V7.

   - Huge page support

     These changes bring both HugeTLB support and Transparent HugePage
     (THP) support to ARM.  Only long descriptors (LPAE) are supported
     in this series.

     The code has been tested on an Arndale board (Exynos 5250).

   - LPAE updates

     Please pull these miscellaneous LPAE fixes I've been collecting for
     a while now for 3.11.  They've been tested and reviewed by quite a
     few people, and most of the patches are pretty trivial.  -- Will Deacon.

   - arch_timer cleanups

     Please pull these arch_timer cleanups I've been holding onto for a
     while.  They're the same as my last posting, but have been rebased
     to v3.10-rc3.

   - mpidr linearisation (multiprocessor id register - identifies which
     CPU number we are in the system)

     This patch series that implements MPIDR linearization through a
     simple hashing algorithm and updates current cpu_{suspend}/{resume}
     code to use the newly created hash structures to retrieve context
     pointers.  It represents a stepping stone for the implementation of
     power management code on forthcoming multi-cluster ARM systems.

     It has been tested on TC2 (dual cluster A15xA7 system), iMX6q,
     OMAP4 and Tegra, with processors hitting low-power states requiring
     warm-boot resume through the cpu_resume code path"

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (77 commits)
  ARM: 7775/1: mm: Remove do_sect_fault from LPAE code
  ARM: 7777/1: Avoid extra calls to the C compiler
  ARM: 7774/1: Fix dtb dependency to use order-only prerequisites
  ARM: 7770/1: remove residual ARMv2 support from decompressor
  ARM: 7769/1: Cortex-A15: fix erratum 798181 implementation
  ARM: 7768/1: prevent risks of out-of-bound access in ASID allocator
  ARM: 7767/1: let the ASID allocator handle suspended animation
  ARM: 7766/1: versatile: don't mark pen as __INIT
  ARM: 7765/1: perf: Record the user-mode PC in the call chain.
  ARM: 7735/2: Preserve the user r/w register TPIDRURW on context switch and fork
  ARM: kernel: implement stack pointer save array through MPIDR hashing
  ARM: kernel: build MPIDR hash function data structure
  ARM: mpu: Ensure that MPU depends on CPU_V7
  ARM: mpu: protect the vectors page with an MPU region
  ARM: mpu: Allow enabling of the MPU via kconfig
  ARM: 7758/1: introduce config HAS_BANDGAP
  ARM: 7757/1: mm: don't flush icache in switch_mm with hardware broadcasting
  ARM: 7751/1: zImage: don't overwrite ourself with a page table
  ARM: 7749/1: spinlock: retry trylock operation if strex fails on free lock
  ARM: 7748/1: oabi: handle faults when loading swi instruction from userspace
  ...

3 files changed, 135 insertions, 57 deletions

diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index a2b254189782..053d846ab5b1 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -186,27 +186,19 @@ u32 arch_timer_get_rate(void)
 	return arch_timer_rate;
 }
 
-/*
- * Some external users of arch_timer_read_counter (e.g. sched_clock) may try to
- * call it before it has been initialised. Rather than incur a performance
- * penalty checking for initialisation, provide a default implementation that
- * won't lead to time appearing to jump backwards.
- */
-static u64 arch_timer_read_zero(void)
+u64 arch_timer_read_counter(void)
 {
-	return 0;
+	return arch_counter_get_cntvct();
 }
 
-u64 (*arch_timer_read_counter)(void) = arch_timer_read_zero;
-
 static cycle_t arch_counter_read(struct clocksource *cs)
 {
-	return arch_timer_read_counter();
+	return arch_counter_get_cntvct();
 }
 
 static cycle_t arch_counter_read_cc(const struct cyclecounter *cc)
 {
-	return arch_timer_read_counter();
+	return arch_counter_get_cntvct();
 }
 
 static struct clocksource clocksource_counter = {
@@ -287,7 +279,7 @@ static int __init arch_timer_register(void)
 	cyclecounter.mult = clocksource_counter.mult;
 	cyclecounter.shift = clocksource_counter.shift;
 	timecounter_init(&timecounter, &cyclecounter,
-			 arch_counter_get_cntpct());
+			 arch_counter_get_cntvct());
 
 	if (arch_timer_use_virtual) {
 		ppi = arch_timer_ppi[VIRT_PPI];
@@ -376,11 +368,6 @@ static void __init arch_timer_init(struct device_node *np)
 		}
 	}
 
-	if (arch_timer_use_virtual)
-		arch_timer_read_counter = arch_counter_get_cntvct;
-	else
-		arch_timer_read_counter = arch_counter_get_cntpct;
-
 	arch_timer_register();
 	arch_timer_arch_init();
 }
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index f4f3038c1df0..c3785edc0e92 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -61,6 +61,7 @@ static unsigned int fmax = 515633;
  * @pwrreg_powerup: power up value for MMCIPOWER register
  * @signal_direction: input/out direction of bus signals can be indicated
  * @pwrreg_clkgate: MMCIPOWER register must be used to gate the clock
+ * @busy_detect: true if busy detection on dat0 is supported
  */
 struct variant_data {
 	unsigned int		clkreg;
@@ -74,6 +75,7 @@ struct variant_data {
 	u32			pwrreg_powerup;
 	bool			signal_direction;
 	bool			pwrreg_clkgate;
+	bool			busy_detect;
 };
 
 static struct variant_data variant_arm = {
@@ -132,6 +134,7 @@ static struct variant_data variant_ux500 = {
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
+	.busy_detect		= true,
 };
 
 static struct variant_data variant_ux500v2 = {
@@ -146,8 +149,28 @@ static struct variant_data variant_ux500v2 = {
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
+	.busy_detect		= true,
 };
 
+static int mmci_card_busy(struct mmc_host *mmc)
+{
+	struct mmci_host *host = mmc_priv(mmc);
+	unsigned long flags;
+	int busy = 0;
+
+	pm_runtime_get_sync(mmc_dev(mmc));
+
+	spin_lock_irqsave(&host->lock, flags);
+	if (readl(host->base + MMCISTATUS) & MCI_ST_CARDBUSY)
+		busy = 1;
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	pm_runtime_mark_last_busy(mmc_dev(mmc));
+	pm_runtime_put_autosuspend(mmc_dev(mmc));
+
+	return busy;
+}
+
 /*
  * Validate mmc prerequisites
  */
@@ -191,11 +214,28 @@ static void mmci_write_pwrreg(struct mmci_host *host, u32 pwr)
 /*
  * This must be called with host->lock held
  */
+static void mmci_write_datactrlreg(struct mmci_host *host, u32 datactrl)
+{
+	/* Keep ST Micro busy mode if enabled */
+	datactrl |= host->datactrl_reg & MCI_ST_DPSM_BUSYMODE;
+
+	if (host->datactrl_reg != datactrl) {
+		host->datactrl_reg = datactrl;
+		writel(datactrl, host->base + MMCIDATACTRL);
+	}
+}
+
+/*
+ * This must be called with host->lock held
+ */
 static void mmci_set_clkreg(struct mmci_host *host, unsigned int desired)
 {
 	struct variant_data *variant = host->variant;
 	u32 clk = variant->clkreg;
 
+	/* Make sure cclk reflects the current calculated clock */
+	host->cclk = 0;
+
 	if (desired) {
 		if (desired >= host->mclk) {
 			clk = MCI_CLK_BYPASS;
@@ -230,6 +270,9 @@ static void mmci_set_clkreg(struct mmci_host *host, unsigned int desired)
 		/* clk |= MCI_CLK_PWRSAVE; */
 	}
 
+	/* Set actual clock for debug */
+	host->mmc->actual_clock = host->cclk;
+
 	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_4)
 		clk |= MCI_4BIT_BUS;
 	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_8)
@@ -275,7 +318,7 @@ static void mmci_set_mask1(struct mmci_host *host, unsigned int mask)
 
 static void mmci_stop_data(struct mmci_host *host)
 {
-	writel(0, host->base + MMCIDATACTRL);
+	mmci_write_datactrlreg(host, 0);
 	mmci_set_mask1(host, 0);
 	host->data = NULL;
 }
@@ -304,10 +347,8 @@ static void mmci_dma_setup(struct mmci_host *host)
 	const char *rxname, *txname;
 	dma_cap_mask_t mask;
 
-	if (!plat || !plat->dma_filter) {
-		dev_info(mmc_dev(host->mmc), "no DMA platform data\n");
-		return;
-	}
+	host->dma_rx_channel = dma_request_slave_channel(mmc_dev(host->mmc), "rx");
+	host->dma_tx_channel = dma_request_slave_channel(mmc_dev(host->mmc), "tx");
 
 	/* initialize pre request cookie */
 	host->next_data.cookie = 1;
@@ -316,30 +357,33 @@ static void mmci_dma_setup(struct mmci_host *host)
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
 
-	/*
-	 * If only an RX channel is specified, the driver will
-	 * attempt to use it bidirectionally, however if it is
-	 * is specified but cannot be located, DMA will be disabled.
-	 */
-	if (plat->dma_rx_param) {
-		host->dma_rx_channel = dma_request_channel(mask,
+	if (plat && plat->dma_filter) {
+		if (!host->dma_rx_channel && plat->dma_rx_param) {
+			host->dma_rx_channel = dma_request_channel(mask,
 							   plat->dma_filter,
 							   plat->dma_rx_param);
-		/* E.g if no DMA hardware is present */
-		if (!host->dma_rx_channel)
-			dev_err(mmc_dev(host->mmc), "no RX DMA channel\n");
-	}
+			/* E.g if no DMA hardware is present */
+			if (!host->dma_rx_channel)
+				dev_err(mmc_dev(host->mmc), "no RX DMA channel\n");
+		}
 
-	if (plat->dma_tx_param) {
-		host->dma_tx_channel = dma_request_channel(mask,
+		if (!host->dma_tx_channel && plat->dma_tx_param) {
+			host->dma_tx_channel = dma_request_channel(mask,
 							   plat->dma_filter,
 							   plat->dma_tx_param);
-		if (!host->dma_tx_channel)
-			dev_warn(mmc_dev(host->mmc), "no TX DMA channel\n");
-	} else {
-		host->dma_tx_channel = host->dma_rx_channel;
+			if (!host->dma_tx_channel)
+				dev_warn(mmc_dev(host->mmc), "no TX DMA channel\n");
+		}
 	}
 
+	/*
+	 * If only an RX channel is specified, the driver will
+	 * attempt to use it bidirectionally, however if it is
+	 * is specified but cannot be located, DMA will be disabled.
+	 */
+	if (host->dma_rx_channel && !host->dma_tx_channel)
+		host->dma_tx_channel = host->dma_rx_channel;
+
 	if (host->dma_rx_channel)
 		rxname = dma_chan_name(host->dma_rx_channel);
 	else
@@ -552,7 +596,7 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
 	datactrl |= MCI_DPSM_DMAENABLE;
 
 	/* Trigger the DMA transfer */
-	writel(datactrl, host->base + MMCIDATACTRL);
+	mmci_write_datactrlreg(host, datactrl);
 
 	/*
 	 * Let the MMCI say when the data is ended and it's time
@@ -750,7 +794,7 @@ static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
 		irqmask = MCI_TXFIFOHALFEMPTYMASK;
 	}
 
-	writel(datactrl, base + MMCIDATACTRL);
+	mmci_write_datactrlreg(host, datactrl);
 	writel(readl(base + MMCIMASK0) & ~MCI_DATAENDMASK, base + MMCIMASK0);
 	mmci_set_mask1(host, irqmask);
 }
@@ -842,7 +886,7 @@ mmci_data_irq(struct mmci_host *host, struct mmc_data *data,
 			/* The error clause is handled above, success! */
 			data->bytes_xfered = data->blksz * data->blocks;
 
-		if (!data->stop) {
+		if (!data->stop || host->mrq->sbc) {
 			mmci_request_end(host, data->mrq);
 		} else {
 			mmci_start_command(host, data->stop, 0);
@@ -855,6 +899,7 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
 	     unsigned int status)
 {
 	void __iomem *base = host->base;
+	bool sbc = (cmd == host->mrq->sbc);
 
 	host->cmd = NULL;
 
@@ -869,7 +914,7 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
 		cmd->resp[3] = readl(base + MMCIRESPONSE3);
 	}
 
-	if (!cmd->data || cmd->error) {
+	if ((!sbc && !cmd->data) || cmd->error) {
 		if (host->data) {
 			/* Terminate the DMA transfer */
 			if (dma_inprogress(host)) {
@@ -878,7 +923,9 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
 			}
 			mmci_stop_data(host);
 		}
-		mmci_request_end(host, cmd->mrq);
+		mmci_request_end(host, host->mrq);
+	} else if (sbc) {
+		mmci_start_command(host, host->mrq->cmd, 0);
 	} else if (!(cmd->data->flags & MMC_DATA_READ)) {
 		mmci_start_data(host, cmd->data);
 	}
@@ -1119,7 +1166,10 @@ static void mmci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	if (mrq->data && mrq->data->flags & MMC_DATA_READ)
 		mmci_start_data(host, mrq->data);
 
-	mmci_start_command(host, mrq->cmd, 0);
+	if (mrq->sbc)
+		mmci_start_command(host, mrq->sbc, 0);
+	else
+		mmci_start_command(host, mrq->cmd, 0);
 
 	spin_unlock_irqrestore(&host->lock, flags);
 }
@@ -1143,9 +1193,10 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		if (!IS_ERR(mmc->supply.vmmc))
 			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
 
-		if (!IS_ERR(mmc->supply.vqmmc) &&
-		    regulator_is_enabled(mmc->supply.vqmmc))
+		if (!IS_ERR(mmc->supply.vqmmc) && host->vqmmc_enabled) {
 			regulator_disable(mmc->supply.vqmmc);
+			host->vqmmc_enabled = false;
+		}
 
 		break;
 	case MMC_POWER_UP:
@@ -1161,12 +1212,13 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 		break;
 	case MMC_POWER_ON:
-		if (!IS_ERR(mmc->supply.vqmmc) &&
-		    !regulator_is_enabled(mmc->supply.vqmmc)) {
+		if (!IS_ERR(mmc->supply.vqmmc) && !host->vqmmc_enabled) {
 			ret = regulator_enable(mmc->supply.vqmmc);
 			if (ret < 0)
 				dev_err(mmc_dev(mmc),
 					"failed to enable vqmmc regulator\n");
+			else
+				host->vqmmc_enabled = true;
 		}
 
 		pwr |= MCI_PWR_ON;
@@ -1251,6 +1303,39 @@ static int mmci_get_cd(struct mmc_host *mmc)
 	return status;
 }
 
+static int mmci_sig_volt_switch(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	int ret = 0;
+
+	if (!IS_ERR(mmc->supply.vqmmc)) {
+
+		pm_runtime_get_sync(mmc_dev(mmc));
+
+		switch (ios->signal_voltage) {
+		case MMC_SIGNAL_VOLTAGE_330:
+			ret = regulator_set_voltage(mmc->supply.vqmmc,
+						2700000, 3600000);
+			break;
+		case MMC_SIGNAL_VOLTAGE_180:
+			ret = regulator_set_voltage(mmc->supply.vqmmc,
+						1700000, 1950000);
+			break;
+		case MMC_SIGNAL_VOLTAGE_120:
+			ret = regulator_set_voltage(mmc->supply.vqmmc,
+						1100000, 1300000);
+			break;
+		}
+
+		if (ret)
+			dev_warn(mmc_dev(mmc), "Voltage switch failed\n");
+
+		pm_runtime_mark_last_busy(mmc_dev(mmc));
+		pm_runtime_put_autosuspend(mmc_dev(mmc));
+	}
+
+	return ret;
+}
+
 static irqreturn_t mmci_cd_irq(int irq, void *dev_id)
 {
 	struct mmci_host *host = dev_id;
@@ -1260,13 +1345,14 @@ static irqreturn_t mmci_cd_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static const struct mmc_host_ops mmci_ops = {
+static struct mmc_host_ops mmci_ops = {
 	.request	= mmci_request,
 	.pre_req	= mmci_pre_request,
 	.post_req	= mmci_post_request,
 	.set_ios	= mmci_set_ios,
 	.get_ro		= mmci_get_ro,
 	.get_cd		= mmci_get_cd,
+	.start_signal_voltage_switch = mmci_sig_volt_switch,
 };
 
 #ifdef CONFIG_OF
@@ -1362,16 +1448,15 @@ static int mmci_probe(struct amba_device *dev,
 	dev_dbg(mmc_dev(mmc), "designer ID = 0x%02x\n", host->hw_designer);
 	dev_dbg(mmc_dev(mmc), "revision = 0x%01x\n", host->hw_revision);
 
-	host->clk = clk_get(&dev->dev, NULL);
+	host->clk = devm_clk_get(&dev->dev, NULL);
 	if (IS_ERR(host->clk)) {
 		ret = PTR_ERR(host->clk);
-		host->clk = NULL;
 		goto host_free;
 	}
 
 	ret = clk_prepare_enable(host->clk);
 	if (ret)
-		goto clk_free;
+		goto host_free;
 
 	host->plat = plat;
 	host->variant = variant;
@@ -1396,6 +1481,11 @@ static int mmci_probe(struct amba_device *dev,
 		goto clk_disable;
 	}
 
+	if (variant->busy_detect) {
+		mmci_ops.card_busy = mmci_card_busy;
+		mmci_write_datactrlreg(host, MCI_ST_DPSM_BUSYMODE);
+	}
+
 	mmc->ops = &mmci_ops;
 	/*
 	 * The ARM and ST versions of the block have slightly different
@@ -1576,8 +1666,6 @@ static int mmci_probe(struct amba_device *dev,
 	iounmap(host->base);
  clk_disable:
 	clk_disable_unprepare(host->clk);
- clk_free:
-	clk_put(host->clk);
  host_free:
 	mmc_free_host(mmc);
  rel_regions:
@@ -1623,7 +1711,6 @@ static int mmci_remove(struct amba_device *dev)
 
 		iounmap(host->base);
 		clk_disable_unprepare(host->clk);
-		clk_put(host->clk);
 
 		mmc_free_host(mmc);
 
diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h
index 1f33ad5333a0..69080fab6375 100644
--- a/drivers/mmc/host/mmci.h
+++ b/drivers/mmc/host/mmci.h
@@ -94,6 +94,7 @@
 /* Extended status bits for the ST Micro variants */
 #define MCI_ST_SDIOIT		(1 << 22)
 #define MCI_ST_CEATAEND		(1 << 23)
+#define MCI_ST_CARDBUSY		(1 << 24)
 
 #define MMCICLEAR		0x038
 #define MCI_CMDCRCFAILCLR	(1 << 0)
@@ -110,6 +111,7 @@
 /* Extended status bits for the ST Micro variants */
 #define MCI_ST_SDIOITC		(1 << 22)
 #define MCI_ST_CEATAENDC	(1 << 23)
+#define MCI_ST_BUSYENDC		(1 << 24)
 
 #define MMCIMASK0		0x03c
 #define MCI_CMDCRCFAILMASK	(1 << 0)
@@ -183,6 +185,8 @@ struct mmci_host {
 	unsigned int		cclk;
 	u32			pwr_reg;
 	u32			clk_reg;
+	u32			datactrl_reg;
+	bool			vqmmc_enabled;
 	struct mmci_platform_data *plat;
 	struct variant_data	*variant;