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

Pull ARM updates from Russell King:
 "Included in this series are:

   1. BE8 (modern big endian) changes for ARM from Ben Dooks
   2. big.Little support from Nicolas Pitre and Dave Martin
   3. support for LPAE systems with all system memory above 4GB
   4. Perf updates from Will Deacon
   5. Additional prefetching and other performance improvements from Will.
   6. Neon-optimised AES implementation fro Ard.
   7. A number of smaller fixes scattered around the place.

  There is a rather horrid merge conflict in tools/perf - I was never
  notified of the conflict because it originally occurred between Will's
  tree and other stuff.  Consequently I have a resolution which Will
  forwarded me, which I'll forward on immediately after sending this
  mail.

  The other notable thing is I'm expecting some build breakage in the
  crypto stuff on ARM only with Ard's AES patches.  These were merged
  into a stable git branch which others had already pulled, so there's
  little I can do about this.  The problem is caused because these
  patches have a dependency on some code in the crypto git tree - I
  tried requesting a branch I can pull to resolve these, and all I got
  each time from the crypto people was "we'll revert our patches then"
  which would only make things worse since I still don't have the
  dependent patches.  I've no idea what's going on there or how to
  resolve that, and since I can't split these patches from the rest of
  this pull request, I'm rather stuck with pushing this as-is or
  reverting Ard's patches.

  Since it should "come out in the wash" I've left them in - the only
  build problems they seem to cause at the moment are with randconfigs,
  and since it's a new feature anyway.  However, if by -rc1 the
  dependencies aren't in, I think it'd be best to revert Ard's patches"

I resolved the perf conflict roughly as per the patch sent by Russell,
but there may be some differences.  Any errors are likely mine.  Let's
see how the crypto issues work out..

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (110 commits)
  ARM: 7868/1: arm/arm64: remove atomic_clear_mask() in "include/asm/atomic.h"
  ARM: 7867/1: include: asm: use 'int' instead of 'unsigned long' for 'oldval' in atomic_cmpxchg().
  ARM: 7866/1: include: asm: use 'long long' instead of 'u64' within atomic.h
  ARM: 7871/1: amba: Extend number of IRQS
  ARM: 7887/1: Don't smp_cross_call() on UP devices in arch_irq_work_raise()
  ARM: 7872/1: Support arch_irq_work_raise() via self IPIs
  ARM: 7880/1: Clear the IT state independent of the Thumb-2 mode
  ARM: 7878/1: nommu: Implement dummy early_paging_init()
  ARM: 7876/1: clear Thumb-2 IT state on exception handling
  ARM: 7874/2: bL_switcher: Remove cpu_hotplug_driver_{lock,unlock}()
  ARM: footbridge: fix build warnings for netwinder
  ARM: 7873/1: vfp: clear vfp_current_hw_state for dying cpu
  ARM: fix misplaced arch_virt_to_idmap()
  ARM: 7848/1: mcpm: Implement cpu_kill() to synchronise on powerdown
  ARM: 7847/1: mcpm: Factor out logical-to-physical CPU translation
  ARM: 7869/1: remove unused XSCALE_PMU Kconfig param
  ARM: 7864/1: Handle 64-bit memory in case of 32-bit phys_addr_t
  ARM: 7863/1: Let arm_add_memory() always use 64-bit arguments
  ARM: 7862/1: pcpu: replace __get_cpu_var_uses
  ARM: 7861/1: cacheflush: consolidate single-CPU ARMv7 cache disabling code
  ...

5 files changed, 214 insertions, 27 deletions

diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index bb5b90e8e768..b6739cb78e32 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -852,7 +852,7 @@ asmlinkage void __naked cci_enable_port_for_self(void)
 
 	/* Enable the CCI port */
 "	ldr	r0, [r0, %[offsetof_port_phys]] \n"
-"	mov	r3, #"__stringify(CCI_ENABLE_REQ)" \n"
+"	mov	r3, %[cci_enable_req]\n"		   
 "	str	r3, [r0, #"__stringify(CCI_PORT_CTRL)"] \n"
 
 	/* poll the status reg for completion */
@@ -860,7 +860,7 @@ asmlinkage void __naked cci_enable_port_for_self(void)
 "	ldr	r0, [r1] \n"
 "	ldr	r0, [r0, r1]		@ cci_ctrl_base \n"
 "4:	ldr	r1, [r0, #"__stringify(CCI_CTRL_STATUS)"] \n"
-"	tst	r1, #1 \n"
+"	tst	r1, %[cci_control_status_bits] \n"			
 "	bne	4b \n"
 
 "	mov	r0, #0 \n"
@@ -873,6 +873,8 @@ asmlinkage void __naked cci_enable_port_for_self(void)
 "7:	.word	cci_ctrl_phys - . \n"
 	: :
 	[sizeof_cpu_port] "i" (sizeof(cpu_port)),
+	[cci_enable_req] "i" cpu_to_le32(CCI_ENABLE_REQ),
+	[cci_control_status_bits] "i" cpu_to_le32(1),
 #ifndef __ARMEB__
 	[offsetof_cpu_port_mpidr_lsb] "i" (offsetof(struct cpu_port, mpidr)),
 #else
diff --git a/drivers/gpio/gpio-sa1100.c b/drivers/gpio/gpio-sa1100.c
index 8ea3b33d4b40..a90be34e4d5c 100644
--- a/drivers/gpio/gpio-sa1100.c
+++ b/drivers/gpio/gpio-sa1100.c
@@ -10,7 +10,7 @@
 #include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/module.h>
-
+#include <linux/io.h>
 #include <mach/hardware.h>
 #include <mach/irqs.h>
 
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index d0e948084eaf..9031171c141b 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -253,10 +253,9 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
+	raw_spin_lock(&irq_controller_lock);
 	mask = 0xff << shift;
 	bit = gic_cpu_map[cpu] << shift;
-
-	raw_spin_lock(&irq_controller_lock);
 	val = readl_relaxed(reg) & ~mask;
 	writel_relaxed(val | bit, reg);
 	raw_spin_unlock(&irq_controller_lock);
@@ -652,7 +651,9 @@ static void __init gic_pm_init(struct gic_chip_data *gic)
 void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
 	int cpu;
-	unsigned long map = 0;
+	unsigned long flags, map = 0;
+
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
 
 	/* Convert our logical CPU mask into a physical one. */
 	for_each_cpu(cpu, mask)
@@ -666,7 +667,149 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 
 	/* this always happens on GIC0 */
 	writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
+}
+#endif
+
+#ifdef CONFIG_BL_SWITCHER
+/*
+ * gic_send_sgi - send a SGI directly to given CPU interface number
+ *
+ * cpu_id: the ID for the destination CPU interface
+ * irq: the IPI number to send a SGI for
+ */
+void gic_send_sgi(unsigned int cpu_id, unsigned int irq)
+{
+	BUG_ON(cpu_id >= NR_GIC_CPU_IF);
+	cpu_id = 1 << cpu_id;
+	/* this always happens on GIC0 */
+	writel_relaxed((cpu_id << 16) | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+}
+
+/*
+ * gic_get_cpu_id - get the CPU interface ID for the specified CPU
+ *
+ * @cpu: the logical CPU number to get the GIC ID for.
+ *
+ * Return the CPU interface ID for the given logical CPU number,
+ * or -1 if the CPU number is too large or the interface ID is
+ * unknown (more than one bit set).
+ */
+int gic_get_cpu_id(unsigned int cpu)
+{
+	unsigned int cpu_bit;
+
+	if (cpu >= NR_GIC_CPU_IF)
+		return -1;
+	cpu_bit = gic_cpu_map[cpu];
+	if (cpu_bit & (cpu_bit - 1))
+		return -1;
+	return __ffs(cpu_bit);
 }
+
+/*
+ * gic_migrate_target - migrate IRQs to another CPU interface
+ *
+ * @new_cpu_id: the CPU target ID to migrate IRQs to
+ *
+ * Migrate all peripheral interrupts with a target matching the current CPU
+ * to the interface corresponding to @new_cpu_id.  The CPU interface mapping
+ * is also updated.  Targets to other CPU interfaces are unchanged.
+ * This must be called with IRQs locally disabled.
+ */
+void gic_migrate_target(unsigned int new_cpu_id)
+{
+	unsigned int cur_cpu_id, gic_irqs, gic_nr = 0;
+	void __iomem *dist_base;
+	int i, ror_val, cpu = smp_processor_id();
+	u32 val, cur_target_mask, active_mask;
+
+	if (gic_nr >= MAX_GIC_NR)
+		BUG();
+
+	dist_base = gic_data_dist_base(&gic_data[gic_nr]);
+	if (!dist_base)
+		return;
+	gic_irqs = gic_data[gic_nr].gic_irqs;
+
+	cur_cpu_id = __ffs(gic_cpu_map[cpu]);
+	cur_target_mask = 0x01010101 << cur_cpu_id;
+	ror_val = (cur_cpu_id - new_cpu_id) & 31;
+
+	raw_spin_lock(&irq_controller_lock);
+
+	/* Update the target interface for this logical CPU */
+	gic_cpu_map[cpu] = 1 << new_cpu_id;
+
+	/*
+	 * Find all the peripheral interrupts targetting the current
+	 * CPU interface and migrate them to the new CPU interface.
+	 * We skip DIST_TARGET 0 to 7 as they are read-only.
+	 */
+	for (i = 8; i < DIV_ROUND_UP(gic_irqs, 4); i++) {
+		val = readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
+		active_mask = val & cur_target_mask;
+		if (active_mask) {
+			val &= ~active_mask;
+			val |= ror32(active_mask, ror_val);
+			writel_relaxed(val, dist_base + GIC_DIST_TARGET + i*4);
+		}
+	}
+
+	raw_spin_unlock(&irq_controller_lock);
+
+	/*
+	 * Now let's migrate and clear any potential SGIs that might be
+	 * pending for us (cur_cpu_id).  Since GIC_DIST_SGI_PENDING_SET
+	 * is a banked register, we can only forward the SGI using
+	 * GIC_DIST_SOFTINT.  The original SGI source is lost but Linux
+	 * doesn't use that information anyway.
+	 *
+	 * For the same reason we do not adjust SGI source information
+	 * for previously sent SGIs by us to other CPUs either.
+	 */
+	for (i = 0; i < 16; i += 4) {
+		int j;
+		val = readl_relaxed(dist_base + GIC_DIST_SGI_PENDING_SET + i);
+		if (!val)
+			continue;
+		writel_relaxed(val, dist_base + GIC_DIST_SGI_PENDING_CLEAR + i);
+		for (j = i; j < i + 4; j++) {
+			if (val & 0xff)
+				writel_relaxed((1 << (new_cpu_id + 16)) | j,
+						dist_base + GIC_DIST_SOFTINT);
+			val >>= 8;
+		}
+	}
+}
+
+/*
+ * gic_get_sgir_physaddr - get the physical address for the SGI register
+ *
+ * REturn the physical address of the SGI register to be used
+ * by some early assembly code when the kernel is not yet available.
+ */
+static unsigned long gic_dist_physaddr;
+
+unsigned long gic_get_sgir_physaddr(void)
+{
+	if (!gic_dist_physaddr)
+		return 0;
+	return gic_dist_physaddr + GIC_DIST_SOFTINT;
+}
+
+void __init gic_init_physaddr(struct device_node *node)
+{
+	struct resource res;
+	if (of_address_to_resource(node, 0, &res) == 0) {
+		gic_dist_physaddr = res.start;
+		pr_info("GIC physical location is %#lx\n", gic_dist_physaddr);
+	}
+}
+
+#else
+#define gic_init_physaddr(node)  do { } while (0)
 #endif
 
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
@@ -850,6 +993,8 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent)
 		percpu_offset = 0;
 
 	gic_init_bases(gic_cnt, -1, dist_base, cpu_base, percpu_offset, node);
+	if (!gic_cnt)
+		gic_init_physaddr(node);
 
 	if (parent) {
 		irq = irq_of_parse_and_map(node, 0);
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index c3785edc0e92..d135c76c4855 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -62,6 +62,7 @@ static unsigned int fmax = 515633;
  * @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
+ * @pwrreg_nopower: bits in MMCIPOWER don't controls ext. power supply
  */
 struct variant_data {
 	unsigned int		clkreg;
@@ -76,6 +77,7 @@ struct variant_data {
 	bool			signal_direction;
 	bool			pwrreg_clkgate;
 	bool			busy_detect;
+	bool			pwrreg_nopower;
 };
 
 static struct variant_data variant_arm = {
@@ -109,6 +111,7 @@ static struct variant_data variant_u300 = {
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
+	.pwrreg_nopower		= true,
 };
 
 static struct variant_data variant_nomadik = {
@@ -121,6 +124,7 @@ static struct variant_data variant_nomadik = {
 	.pwrreg_powerup		= MCI_PWR_ON,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
+	.pwrreg_nopower		= true,
 };
 
 static struct variant_data variant_ux500 = {
@@ -135,6 +139,7 @@ static struct variant_data variant_ux500 = {
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
 	.busy_detect		= true,
+	.pwrreg_nopower		= true,
 };
 
 static struct variant_data variant_ux500v2 = {
@@ -150,6 +155,7 @@ static struct variant_data variant_ux500v2 = {
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
 	.busy_detect		= true,
+	.pwrreg_nopower		= true,
 };
 
 static int mmci_card_busy(struct mmc_host *mmc)
@@ -189,6 +195,21 @@ static int mmci_validate_data(struct mmci_host *host,
 	return 0;
 }
 
+static void mmci_reg_delay(struct mmci_host *host)
+{
+	/*
+	 * According to the spec, at least three feedback clock cycles
+	 * of max 52 MHz must pass between two writes to the MMCICLOCK reg.
+	 * Three MCLK clock cycles must pass between two MMCIPOWER reg writes.
+	 * Worst delay time during card init is at 100 kHz => 30 us.
+	 * Worst delay time when up and running is at 25 MHz => 120 ns.
+	 */
+	if (host->cclk < 25000000)
+		udelay(30);
+	else
+		ndelay(120);
+}
+
 /*
  * This must be called with host->lock held
  */
@@ -1264,6 +1285,7 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 	mmci_set_clkreg(host, ios->clock);
 	mmci_write_pwrreg(host, pwr);
+	mmci_reg_delay(host);
 
 	spin_unlock_irqrestore(&host->lock, flags);
 
@@ -1510,23 +1532,6 @@ static int mmci_probe(struct amba_device *dev,
 		mmc->f_max = min(host->mclk, fmax);
 	dev_dbg(mmc_dev(mmc), "clocking block at %u Hz\n", mmc->f_max);
 
-	host->pinctrl = devm_pinctrl_get(&dev->dev);
-	if (IS_ERR(host->pinctrl)) {
-		ret = PTR_ERR(host->pinctrl);
-		goto clk_disable;
-	}
-
-	host->pins_default = pinctrl_lookup_state(host->pinctrl,
-			PINCTRL_STATE_DEFAULT);
-
-	/* enable pins to be muxed in and configured */
-	if (!IS_ERR(host->pins_default)) {
-		ret = pinctrl_select_state(host->pinctrl, host->pins_default);
-		if (ret)
-			dev_warn(&dev->dev, "could not set default pins\n");
-	} else
-		dev_warn(&dev->dev, "could not get default pinstate\n");
-
 	/* Get regulators and the supported OCR mask */
 	mmc_regulator_get_supply(mmc);
 	if (!mmc->ocr_avail)
@@ -1760,6 +1765,41 @@ static int mmci_resume(struct device *dev)
 #endif
 
 #ifdef CONFIG_PM_RUNTIME
+static void mmci_save(struct mmci_host *host)
+{
+	unsigned long flags;
+
+	if (host->variant->pwrreg_nopower) {
+		spin_lock_irqsave(&host->lock, flags);
+
+		writel(0, host->base + MMCIMASK0);
+		writel(0, host->base + MMCIDATACTRL);
+		writel(0, host->base + MMCIPOWER);
+		writel(0, host->base + MMCICLOCK);
+		mmci_reg_delay(host);
+
+		spin_unlock_irqrestore(&host->lock, flags);
+	}
+
+}
+
+static void mmci_restore(struct mmci_host *host)
+{
+	unsigned long flags;
+
+	if (host->variant->pwrreg_nopower) {
+		spin_lock_irqsave(&host->lock, flags);
+
+		writel(host->clk_reg, host->base + MMCICLOCK);
+		writel(host->datactrl_reg, host->base + MMCIDATACTRL);
+		writel(host->pwr_reg, host->base + MMCIPOWER);
+		writel(MCI_IRQENABLE, host->base + MMCIMASK0);
+		mmci_reg_delay(host);
+
+		spin_unlock_irqrestore(&host->lock, flags);
+	}
+}
+
 static int mmci_runtime_suspend(struct device *dev)
 {
 	struct amba_device *adev = to_amba_device(dev);
@@ -1767,6 +1807,8 @@ static int mmci_runtime_suspend(struct device *dev)
 
 	if (mmc) {
 		struct mmci_host *host = mmc_priv(mmc);
+		pinctrl_pm_select_sleep_state(dev);
+		mmci_save(host);
 		clk_disable_unprepare(host->clk);
 	}
 
@@ -1781,6 +1823,8 @@ static int mmci_runtime_resume(struct device *dev)
 	if (mmc) {
 		struct mmci_host *host = mmc_priv(mmc);
 		clk_prepare_enable(host->clk);
+		mmci_restore(host);
+		pinctrl_pm_select_default_state(dev);
 	}
 
 	return 0;
diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h
index 69080fab6375..168bc72f7a94 100644
--- a/drivers/mmc/host/mmci.h
+++ b/drivers/mmc/host/mmci.h
@@ -200,10 +200,6 @@ struct mmci_host {
 	struct sg_mapping_iter	sg_miter;
 	unsigned int		size;
 
-	/* pinctrl handles */
-	struct pinctrl		*pinctrl;
-	struct pinctrl_state	*pins_default;
-
 #ifdef CONFIG_DMA_ENGINE
 	/* DMA stuff */
 	struct dma_chan		*dma_current;