Merge branch 'VExpress_DCSCB' of git://git.linaro.org/people/nico/linux into next/soc

From Nicolas Pitre:

This is the first MCPM backend submission for VExpress running on RTSM
aka Fast Models implementing the big.LITTLE system architecture.  This
enables SMP secondary boot as well as CPU hotplug on this platform.

A big prerequisite for this support is the CCI driver from Lorenzo
included in this pull request.

Also included is Rob Herring's set_auxcr/get_auxcr allowing nicer code.

Signed-off-by: Olof Johansson <olof@lixom.net>

* 'VExpress_DCSCB' of git://git.linaro.org/people/nico/linux:
  ARM: vexpress: Select multi-cluster SMP operation if required
  ARM: vexpress/dcscb: handle platform coherency exit/setup and CCI
  ARM: vexpress/dcscb: do not hardcode number of CPUs per cluster
  ARM: vexpress/dcscb: add CPU use counts to the power up/down API implementation
  ARM: vexpress: introduce DCSCB support
  ARM: introduce common set_auxcr/get_auxcr functions
  drivers/bus: arm-cci: function to enable CCI ports from early boot code
  drivers: bus: add ARM CCI support

8 files changed, 338 insertions, 0 deletions

diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 1f3262e99d8..cedd3721318 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -61,6 +61,20 @@ static inline void set_cr(unsigned int val)
 	isb();
 }
 
+static inline unsigned int get_auxcr(void)
+{
+	unsigned int val;
+	asm("mrc p15, 0, %0, c1, c0, 1	@ get AUXCR" : "=r" (val));
+	return val;
+}
+
+static inline void set_auxcr(unsigned int val)
+{
+	asm volatile("mcr p15, 0, %0, c1, c0, 1	@ set AUXCR"
+	  : : "r" (val));
+	isb();
+}
+
 #ifndef CONFIG_SMP
 extern void adjust_cr(unsigned long mask, unsigned long set);
 #endif
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 5907e10c37f..b8bbabec631 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 42703e8b4d3..48ba89a8149 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 f134cd4a85f..bde4374ab6d 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 00000000000..16d57a8a9d5
--- /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 00000000000..4bb7fbe0f62
--- /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 dc1ace55d55..993c9ae5dc5 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 8802030df98..b0eccf7e06e 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -456,6 +456,7 @@ 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_irq	= irqchip_init,