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

Pull ARM SoC specific changes from Arnd Bergmann:
 "These changes are all to SoC-specific code, a total of 33 branches on
  17 platforms were pulled into this.  Like last time, Renesas sh-mobile
  is now the platform with the most changes, followed by OMAP and
  EXYNOS.

  Two new platforms, TI Keystone and Rockchips RK3xxx are added in this
  branch, both containing almost no platform specific code at all, since
  they are using generic subsystem interfaces for clocks, pinctrl,
  interrupts etc.  The device drivers are getting merged through the
  respective subsystem maintainer trees.

  One more SoC (u300) is now multiplatform capable and several others
  (shmobile, exynos, msm, integrator, kirkwood, clps711x) are moving
  towards that goal with this series but need more work.

  Also noteworthy is the work on PCI here, which is traditionally part
  of the SoC specific code.  With the changes done by Thomas Petazzoni,
  we can now more easily have PCI host controller drivers as loadable
  modules and keep them separate from the platform code in
  drivers/pci/host.  This has already led to the discovery that three
  platforms (exynos, spear and imx) are actually using an identical PCIe
  host controller and will be able to share a driver once support for
  spear and imx is added."

* tag 'soc-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc: (480 commits)
  ARM: integrator: let pciv3 use mem/premem from device tree
  ARM: integrator: set local side PCI addresses right
  ARM: dts: Add pcie controller node for exynos5440-ssdk5440
  ARM: dts: Add pcie controller node for Samsung EXYNOS5440 SoC
  ARM: EXYNOS: Enable PCIe support for Exynos5440
  pci: Add PCIe driver for Samsung Exynos
  ARM: OMAP5: voltagedomain data: remove temporary OMAP4 voltage data
  ARM: keystone: Move CPU bringup code to dedicated asm file
  ARM: multiplatform: always pick one CPU type
  ARM: imx: select syscon for IMX6SL
  ARM: keystone: select ARM_ERRATA_798181 only for SMP
  ARM: imx: Synertronixx scb9328 needs to select SOC_IMX1
  ARM: OMAP2+: AM43x: resolve SMP related build error
  dmaengine: edma: enable build for AM33XX
  ARM: edma: Add EDMA crossbar event mux support
  ARM: edma: Add DT and runtime PM support to the private EDMA API
  dmaengine: edma: Add TI EDMA device tree binding
  arm: add basic support for Rockchip RK3066a boards
  arm: add debug uarts for rockchip rk29xx and rk3xxx series
  arm: Add basic clocks for Rockchip rk3066a SoCs
  ...

7 files changed, 324 insertions, 0 deletions

diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 5907e10c37fd..b8bbabec6310 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -57,4 +57,13 @@ config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
 config ARCH_VEXPRESS_CA9X4
 	bool "Versatile Express Cortex-A9x4 tile"
 
+config ARCH_VEXPRESS_DCSCB
+	bool "Dual Cluster System Control Block (DCSCB) support"
+	depends on MCPM
+	select ARM_CCI
+	help
+	  Support for the Dual Cluster System Configuration Block (DCSCB).
+	  This is needed to provide CPU and cluster power management
+	  on RTSM implementing big.LITTLE.
+
 endmenu
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index 42703e8b4d3b..48ba89a8149f 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -6,5 +6,6 @@ ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
 
 obj-y					:= v2m.o
 obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
+obj-$(CONFIG_ARCH_VEXPRESS_DCSCB)	+= dcscb.o	dcscb_setup.o
 obj-$(CONFIG_SMP)			+= platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)		+= hotplug.o
diff --git a/arch/arm/mach-vexpress/core.h b/arch/arm/mach-vexpress/core.h
index f134cd4a85f1..bde4374ab6d5 100644
--- a/arch/arm/mach-vexpress/core.h
+++ b/arch/arm/mach-vexpress/core.h
@@ -6,6 +6,8 @@
 
 void vexpress_dt_smp_map_io(void);
 
+bool vexpress_smp_init_ops(void);
+
 extern struct smp_operations	vexpress_smp_ops;
 
 extern void vexpress_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
new file mode 100644
index 000000000000..16d57a8a9d5a
--- /dev/null
+++ b/arch/arm/mach-vexpress/dcscb.c
@@ -0,0 +1,253 @@
+/*
+ * arch/arm/mach-vexpress/dcscb.c - Dual Cluster System Configuration Block
+ *
+ * Created by:	Nicolas Pitre, May 2012
+ * Copyright:	(C) 2012-2013  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/of_address.h>
+#include <linux/vexpress.h>
+#include <linux/arm-cci.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+
+
+#define RST_HOLD0	0x0
+#define RST_HOLD1	0x4
+#define SYS_SWRESET	0x8
+#define RST_STAT0	0xc
+#define RST_STAT1	0x10
+#define EAG_CFG_R	0x20
+#define EAG_CFG_W	0x24
+#define KFC_CFG_R	0x28
+#define KFC_CFG_W	0x2c
+#define DCS_CFG_R	0x30
+
+/*
+ * We can't use regular spinlocks. In the switcher case, it is possible
+ * for an outbound CPU to call power_down() while its inbound counterpart
+ * is already live using the same logical CPU number which trips lockdep
+ * debugging.
+ */
+static arch_spinlock_t dcscb_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+static void __iomem *dcscb_base;
+static int dcscb_use_count[4][2];
+static int dcscb_allcpus_mask[2];
+
+static int dcscb_power_up(unsigned int cpu, unsigned int cluster)
+{
+	unsigned int rst_hold, cpumask = (1 << cpu);
+	unsigned int all_mask = dcscb_allcpus_mask[cluster];
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	if (cpu >= 4 || cluster >= 2)
+		return -EINVAL;
+
+	/*
+	 * Since this is called with IRQs enabled, and no arch_spin_lock_irq
+	 * variant exists, we need to disable IRQs manually here.
+	 */
+	local_irq_disable();
+	arch_spin_lock(&dcscb_lock);
+
+	dcscb_use_count[cpu][cluster]++;
+	if (dcscb_use_count[cpu][cluster] == 1) {
+		rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+		if (rst_hold & (1 << 8)) {
+			/* remove cluster reset and add individual CPU's reset */
+			rst_hold &= ~(1 << 8);
+			rst_hold |= all_mask;
+		}
+		rst_hold &= ~(cpumask | (cpumask << 4));
+		writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
+	} else if (dcscb_use_count[cpu][cluster] != 2) {
+		/*
+		 * The only possible values are:
+		 * 0 = CPU down
+		 * 1 = CPU (still) up
+		 * 2 = CPU requested to be up before it had a chance
+		 *     to actually make itself down.
+		 * Any other value is a bug.
+		 */
+		BUG();
+	}
+
+	arch_spin_unlock(&dcscb_lock);
+	local_irq_enable();
+
+	return 0;
+}
+
+static void dcscb_power_down(void)
+{
+	unsigned int mpidr, cpu, cluster, rst_hold, cpumask, all_mask;
+	bool last_man = false, skip_wfi = false;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	cpumask = (1 << cpu);
+	all_mask = dcscb_allcpus_mask[cluster];
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cpu >= 4 || cluster >= 2);
+
+	__mcpm_cpu_going_down(cpu, cluster);
+
+	arch_spin_lock(&dcscb_lock);
+	BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+	dcscb_use_count[cpu][cluster]--;
+	if (dcscb_use_count[cpu][cluster] == 0) {
+		rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+		rst_hold |= cpumask;
+		if (((rst_hold | (rst_hold >> 4)) & all_mask) == all_mask) {
+			rst_hold |= (1 << 8);
+			last_man = true;
+		}
+		writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
+	} else if (dcscb_use_count[cpu][cluster] == 1) {
+		/*
+		 * A power_up request went ahead of us.
+		 * Even if we do not want to shut this CPU down,
+		 * the caller expects a certain state as if the WFI
+		 * was aborted.  So let's continue with cache cleaning.
+		 */
+		skip_wfi = true;
+	} else
+		BUG();
+
+	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
+		arch_spin_unlock(&dcscb_lock);
+
+		/*
+		 * Flush all cache levels for this cluster.
+		 *
+		 * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need
+		 * a preliminary flush here for those CPUs.  At least, that's
+		 * the theory -- without the extra flush, Linux explodes on
+		 * RTSM (to be investigated).
+		 */
+		flush_cache_all();
+		set_cr(get_cr() & ~CR_C);
+		flush_cache_all();
+
+		/*
+		 * This is a harmless no-op.  On platforms with a real
+		 * outer cache this might either be needed or not,
+		 * depending on where the outer cache sits.
+		 */
+		outer_flush_all();
+
+		/* Disable local coherency by clearing the ACTLR "SMP" bit: */
+		set_auxcr(get_auxcr() & ~(1 << 6));
+
+		/*
+		 * Disable cluster-level coherency by masking
+		 * incoming snoops and DVM messages:
+		 */
+		cci_disable_port_by_cpu(mpidr);
+
+		__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+	} else {
+		arch_spin_unlock(&dcscb_lock);
+
+		/*
+		 * Flush the local CPU cache.
+		 *
+		 * A15/A7 can hit in the cache with SCTLR.C=0, so we don't need
+		 * a preliminary flush here for those CPUs.  At least, that's
+		 * the theory -- without the extra flush, Linux explodes on
+		 * RTSM (to be investigated).
+		 */
+		flush_cache_louis();
+		set_cr(get_cr() & ~CR_C);
+		flush_cache_louis();
+
+		/* Disable local coherency by clearing the ACTLR "SMP" bit: */
+		set_auxcr(get_auxcr() & ~(1 << 6));
+	}
+
+	__mcpm_cpu_down(cpu, cluster);
+
+	/* Now we are prepared for power-down, do it: */
+	dsb();
+	if (!skip_wfi)
+		wfi();
+
+	/* Not dead at this point?  Let our caller cope. */
+}
+
+static const struct mcpm_platform_ops dcscb_power_ops = {
+	.power_up	= dcscb_power_up,
+	.power_down	= dcscb_power_down,
+};
+
+static void __init dcscb_usage_count_init(void)
+{
+	unsigned int mpidr, cpu, cluster;
+
+	mpidr = read_cpuid_mpidr();
+	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+	BUG_ON(cpu >= 4 || cluster >= 2);
+	dcscb_use_count[cpu][cluster] = 1;
+}
+
+extern void dcscb_power_up_setup(unsigned int affinity_level);
+
+static int __init dcscb_init(void)
+{
+	struct device_node *node;
+	unsigned int cfg;
+	int ret;
+
+	if (!cci_probed())
+		return -ENODEV;
+
+	node = of_find_compatible_node(NULL, NULL, "arm,rtsm,dcscb");
+	if (!node)
+		return -ENODEV;
+	dcscb_base = of_iomap(node, 0);
+	if (!dcscb_base)
+		return -EADDRNOTAVAIL;
+	cfg = readl_relaxed(dcscb_base + DCS_CFG_R);
+	dcscb_allcpus_mask[0] = (1 << (((cfg >> 16) >> (0 << 2)) & 0xf)) - 1;
+	dcscb_allcpus_mask[1] = (1 << (((cfg >> 16) >> (1 << 2)) & 0xf)) - 1;
+	dcscb_usage_count_init();
+
+	ret = mcpm_platform_register(&dcscb_power_ops);
+	if (!ret)
+		ret = mcpm_sync_init(dcscb_power_up_setup);
+	if (ret) {
+		iounmap(dcscb_base);
+		return ret;
+	}
+
+	pr_info("VExpress DCSCB support installed\n");
+
+	/*
+	 * Future entries into the kernel can now go
+	 * through the cluster entry vectors.
+	 */
+	vexpress_flags_set(virt_to_phys(mcpm_entry_point));
+
+	return 0;
+}
+
+early_initcall(dcscb_init);
diff --git a/arch/arm/mach-vexpress/dcscb_setup.S b/arch/arm/mach-vexpress/dcscb_setup.S
new file mode 100644
index 000000000000..4bb7fbe0f621
--- /dev/null
+++ b/arch/arm/mach-vexpress/dcscb_setup.S
@@ -0,0 +1,38 @@
+/*
+ * arch/arm/include/asm/dcscb_setup.S
+ *
+ * Created by:  Dave Martin, 2012-06-22
+ * Copyright:   (C) 2012-2013  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+
+ENTRY(dcscb_power_up_setup)
+
+	cmp	r0, #0			@ check affinity level
+	beq	2f
+
+/*
+ * Enable cluster-level coherency, in preparation for turning on the MMU.
+ * The ACTLR SMP bit does not need to be set here, because cpu_resume()
+ * already restores that.
+ *
+ * A15/A7 may not require explicit L2 invalidation on reset, dependent
+ * on hardware integration decisions.
+ * For now, this code assumes that L2 is either already invalidated,
+ * or invalidation is not required.
+ */
+
+	b	cci_enable_port_for_self
+
+2:	@ Implementation-specific local CPU setup operations should go here,
+	@ if any.  In this case, there is nothing to do.
+
+	bx	lr
+
+ENDPROC(dcscb_power_up_setup)
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
index dc1ace55d557..993c9ae5dc5e 100644
--- a/arch/arm/mach-vexpress/platsmp.c
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -12,9 +12,11 @@
 #include <linux/errno.h>
 #include <linux/smp.h>
 #include <linux/io.h>
+#include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/vexpress.h>
 
+#include <asm/mcpm.h>
 #include <asm/smp_scu.h>
 #include <asm/mach/map.h>
 
@@ -203,3 +205,21 @@ struct smp_operations __initdata vexpress_smp_ops = {
 	.cpu_die		= vexpress_cpu_die,
 #endif
 };
+
+bool __init vexpress_smp_init_ops(void)
+{
+#ifdef CONFIG_MCPM
+	/*
+	 * The best way to detect a multi-cluster configuration at the moment
+	 * is to look for the presence of a CCI in the system.
+	 * Override the default vexpress_smp_ops if so.
+	 */
+	struct device_node *node;
+	node = of_find_compatible_node(NULL, NULL, "arm,cci-400");
+	if (node && of_device_is_available(node)) {
+		mcpm_smp_set_ops();
+		return true;
+	}
+#endif
+	return false;
+}
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index d6016970e2fe..95a469e23e37 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -455,6 +455,7 @@ static const char * const v2m_dt_match[] __initconst = {
 DT_MACHINE_START(VEXPRESS_DT, "ARM-Versatile Express")
 	.dt_compat	= v2m_dt_match,
 	.smp		= smp_ops(vexpress_smp_ops),
+	.smp_init	= smp_init_ops(vexpress_smp_init_ops),
 	.map_io		= v2m_dt_map_io,
 	.init_early	= v2m_dt_init_early,
 	.init_time	= v2m_dt_timer_init,