Merge branch 'cluster-boot-protocol' of git://linux-arm.org/linux-2.6-lp into devel-stable

8 files changed, 256 insertions, 48 deletions

diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt
new file mode 100644
index 000000000000..f32494dbfe19
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/cpus.txt
@@ -0,0 +1,77 @@
+* ARM CPUs binding description
+
+The device tree allows to describe the layout of CPUs in a system through
+the "cpus" node, which in turn contains a number of subnodes (ie "cpu")
+defining properties for every cpu.
+
+Bindings for CPU nodes follow the ePAPR standard, available from:
+
+http://devicetree.org
+
+For the ARM architecture every CPU node must contain the following properties:
+
+- device_type:  must be "cpu"
+- reg:          property matching the CPU MPIDR[23:0] register bits
+                reg[31:24] bits must be set to 0
+- compatible:   should be one of:
+                "arm,arm1020"
+                "arm,arm1020e"
+                "arm,arm1022"
+                "arm,arm1026"
+                "arm,arm720"
+                "arm,arm740"
+                "arm,arm7tdmi"
+                "arm,arm920"
+                "arm,arm922"
+                "arm,arm925"
+                "arm,arm926"
+                "arm,arm940"
+                "arm,arm946"
+                "arm,arm9tdmi"
+                "arm,cortex-a5"
+                "arm,cortex-a7"
+                "arm,cortex-a8"
+                "arm,cortex-a9"
+                "arm,cortex-a15"
+                "arm,arm1136"
+                "arm,arm1156"
+                "arm,arm1176"
+                "arm,arm11mpcore"
+                "faraday,fa526"
+                "intel,sa110"
+                "intel,sa1100"
+                "marvell,feroceon"
+                "marvell,mohawk"
+                "marvell,xsc3"
+                "marvell,xscale"
+
+Example:
+
+        cpus {
+                #size-cells = <0>;
+                #address-cells = <1>;
+
+                CPU0: cpu@0 {
+                        device_type = "cpu";
+                        compatible = "arm,cortex-a15";
+                        reg = <0x0>;
+                };
+
+                CPU1: cpu@1 {
+                        device_type = "cpu";
+                        compatible = "arm,cortex-a15";
+                        reg = <0x1>;
+                };
+
+                CPU2: cpu@100 {
+                        device_type = "cpu";
+                        compatible = "arm,cortex-a7";
+                        reg = <0x100>;
+                };
+
+                CPU3: cpu@101 {
+                        device_type = "cpu";
+                        compatible = "arm,cortex-a7";
+                        reg = <0x101>;
+                };
+        };
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index aa5269984187..36ae03a3f5d1 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -70,6 +70,14 @@ struct gic_chip_data {
 static DEFINE_RAW_SPINLOCK(irq_controller_lock);
 
 /*
+ * The GIC mapping of CPU interfaces does not necessarily match
+ * the logical CPU numbering.  Let's use a mapping as returned
+ * by the GIC itself.
+ */
+#define NR_GIC_CPU_IF 8
+static u8 gic_cpu_map[NR_GIC_CPU_IF] __read_mostly;
+
+/*
  * Supported arch specific GIC irq extension.
  * Default make them NULL.
  */
@@ -238,11 +246,11 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
         unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
         u32 val, mask, bit;
 
-        if (cpu >= 8 || cpu >= nr_cpu_ids)
+        if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
                 return -EINVAL;
 
         mask = 0xff << shift;
-        bit = 1 << (cpu_logical_map(cpu) + shift);
+        bit = gic_cpu_map[cpu] << shift;
 
         raw_spin_lock(&irq_controller_lock);
         val = readl_relaxed(reg) & ~mask;
@@ -349,11 +357,6 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
         u32 cpumask;
         unsigned int gic_irqs = gic->gic_irqs;
         void __iomem *base = gic_data_dist_base(gic);
-        u32 cpu = cpu_logical_map(smp_processor_id());
-
-        cpumask = 1 << cpu;
-        cpumask |= cpumask << 8;
-        cpumask |= cpumask << 16;
 
         writel_relaxed(0, base + GIC_DIST_CTRL);
 
@@ -366,6 +369,7 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
         /*
          * Set all global interrupts to this CPU only.
          */
+        cpumask = readl_relaxed(base + GIC_DIST_TARGET + 0);
         for (i = 32; i < gic_irqs; i += 4)
                 writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
 
@@ -389,9 +393,25 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 {
         void __iomem *dist_base = gic_data_dist_base(gic);
         void __iomem *base = gic_data_cpu_base(gic);
+        unsigned int cpu_mask, cpu = smp_processor_id();
         int i;
 
         /*
+         * Get what the GIC says our CPU mask is.
+         */
+        BUG_ON(cpu >= NR_GIC_CPU_IF);
+        cpu_mask = readl_relaxed(dist_base + GIC_DIST_TARGET + 0);
+        gic_cpu_map[cpu] = cpu_mask;
+
+        /*
+         * Clear our mask from the other map entries in case they're
+         * still undefined.
+         */
+        for (i = 0; i < NR_GIC_CPU_IF; i++)
+                if (i != cpu)
+                        gic_cpu_map[i] &= ~cpu_mask;
+
+        /*
          * Deal with the banked PPI and SGI interrupts - disable all
          * PPI interrupts, ensure all SGI interrupts are enabled.
          */
@@ -646,7 +666,7 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 {
         irq_hw_number_t hwirq_base;
         struct gic_chip_data *gic;
-        int gic_irqs, irq_base;
+        int gic_irqs, irq_base, i;
 
         BUG_ON(gic_nr >= MAX_GIC_NR);
 
@@ -683,6 +703,13 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
         }
 
         /*
+         * Initialize the CPU interface map to all CPUs.
+         * It will be refined as each CPU probes its ID.
+         */
+        for (i = 0; i < NR_GIC_CPU_IF; i++)
+                gic_cpu_map[i] = 0xff;
+
+        /*
          * For primary GICs, skip over SGIs.
          * For secondary GICs, skip over PPIs, too.
          */
@@ -737,7 +764,7 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 
         /* Convert our logical CPU mask into a physical one. */
         for_each_cpu(cpu, mask)
-                map |= 1 << cpu_logical_map(cpu);
+                map |= gic_cpu_map[cpu];
 
         /*
          * Ensure that stores to Normal memory are visible to the
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index cb47d28cbe1f..a59dcb5ab5fc 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -25,6 +25,19 @@
 #define CPUID_EXT_ISAR4 "c2, 4"
 #define CPUID_EXT_ISAR5 "c2, 5"
 
+#define MPIDR_SMP_BITMASK (0x3 << 30)
+#define MPIDR_SMP_VALUE (0x2 << 30)
+
+#define MPIDR_MT_BITMASK (0x1 << 24)
+
+#define MPIDR_HWID_BITMASK 0xFFFFFF
+
+#define MPIDR_LEVEL_BITS 8
+#define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1)
+
+#define MPIDR_AFFINITY_LEVEL(mpidr, level) \
+        ((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK)
+
 extern unsigned int processor_id;
 
 #ifdef CONFIG_CPU_CP15
diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h
index aeae9c609df4..8dd51dc1a367 100644
--- a/arch/arm/include/asm/prom.h
+++ b/arch/arm/include/asm/prom.h
@@ -15,6 +15,7 @@
 
 extern struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
 extern void arm_dt_memblock_reserve(void);
+extern void __init arm_dt_init_cpu_maps(void);
 
 #else /* CONFIG_OF */
 
@@ -24,6 +25,7 @@ static inline struct machine_desc *setup_machine_fdt(unsigned int dt_phys)
 }
 
 static inline void arm_dt_memblock_reserve(void) { }
+static inline void arm_dt_init_cpu_maps(void) { }
 
 #endif /* CONFIG_OF */
 #endif /* ASMARM_PROM_H */
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index 558d6c80aca9..aaa61b6f50ff 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -5,6 +5,9 @@
 #ifndef __ASMARM_SMP_PLAT_H
 #define __ASMARM_SMP_PLAT_H
 
+#include <linux/cpumask.h>
+#include <linux/err.h>
+
 #include <asm/cputype.h>
 
 /*
@@ -48,5 +51,19 @@ static inline int cache_ops_need_broadcast(void)
  */
 extern int __cpu_logical_map[];
 #define cpu_logical_map(cpu)    __cpu_logical_map[cpu]
+/*
+ * Retrieve logical cpu index corresponding to a given MPIDR[23:0]
+ *  - mpidr: MPIDR[23:0] to be used for the look-up
+ *
+ * Returns the cpu logical index or -EINVAL on look-up error
+ */
+static inline int get_logical_index(u32 mpidr)
+{
+        int cpu;
+        for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+                if (cpu_logical_map(cpu) == mpidr)
+                        return cpu;
+        return -EINVAL;
+}
 
 #endif
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index bee7f9d47f02..aaf9add497fe 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -19,8 +19,10 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 
+#include <asm/cputype.h>
 #include <asm/setup.h>
 #include <asm/page.h>
+#include <asm/smp_plat.h>
 #include <asm/mach/arch.h>
 #include <asm/mach-types.h>
 
@@ -61,6 +63,104 @@ void __init arm_dt_memblock_reserve(void)
         }
 }
 
+/*
+ * arm_dt_init_cpu_maps - Function retrieves cpu nodes from the device tree
+ * and builds the cpu logical map array containing MPIDR values related to
+ * logical cpus
+ *
+ * Updates the cpu possible mask with the number of parsed cpu nodes
+ */
+void __init arm_dt_init_cpu_maps(void)
+{
+        /*
+         * Temp logical map is initialized with UINT_MAX values that are
+         * considered invalid logical map entries since the logical map must
+         * contain a list of MPIDR[23:0] values where MPIDR[31:24] must
+         * read as 0.
+         */
+        struct device_node *cpu, *cpus;
+        u32 i, j, cpuidx = 1;
+        u32 mpidr = is_smp() ? read_cpuid_mpidr() & MPIDR_HWID_BITMASK : 0;
+
+        u32 tmp_map[NR_CPUS] = { [0 ... NR_CPUS-1] = UINT_MAX };
+        bool bootcpu_valid = false;
+        cpus = of_find_node_by_path("/cpus");
+
+        if (!cpus)
+                return;
+
+        for_each_child_of_node(cpus, cpu) {
+                u32 hwid;
+
+                pr_debug(" * %s...\n", cpu->full_name);
+                /*
+                 * A device tree containing CPU nodes with missing "reg"
+                 * properties is considered invalid to build the
+                 * cpu_logical_map.
+                 */
+                if (of_property_read_u32(cpu, "reg", &hwid)) {
+                        pr_debug(" * %s missing reg property\n",
+                                     cpu->full_name);
+                        return;
+                }
+
+                /*
+                 * 8 MSBs must be set to 0 in the DT since the reg property
+                 * defines the MPIDR[23:0].
+                 */
+                if (hwid & ~MPIDR_HWID_BITMASK)
+                        return;
+
+                /*
+                 * Duplicate MPIDRs are a recipe for disaster.
+                 * Scan all initialized entries and check for
+                 * duplicates. If any is found just bail out.
+                 * temp values were initialized to UINT_MAX
+                 * to avoid matching valid MPIDR[23:0] values.
+                 */
+                for (j = 0; j < cpuidx; j++)
+                        if (WARN(tmp_map[j] == hwid, "Duplicate /cpu reg "
+                                                     "properties in the DT\n"))
+                                return;
+
+                /*
+                 * Build a stashed array of MPIDR values. Numbering scheme
+                 * requires that if detected the boot CPU must be assigned
+                 * logical id 0. Other CPUs get sequential indexes starting
+                 * from 1. If a CPU node with a reg property matching the
+                 * boot CPU MPIDR is detected, this is recorded so that the
+                 * logical map built from DT is validated and can be used
+                 * to override the map created in smp_setup_processor_id().
+                 */
+                if (hwid == mpidr) {
+                        i = 0;
+                        bootcpu_valid = true;
+                } else {
+                        i = cpuidx++;
+                }
+
+                tmp_map[i] = hwid;
+
+                if (cpuidx > nr_cpu_ids)
+                        break;
+        }
+
+        if (WARN(!bootcpu_valid, "DT missing boot CPU MPIDR[23:0], "
+                                 "fall back to default cpu_logical_map\n"))
+                return;
+
+        /*
+         * Since the boot CPU node contains proper data, and all nodes have
+         * a reg property, the DT CPU list can be considered valid and the
+         * logical map created in smp_setup_processor_id() can be overridden
+         */
+        for (i = 0; i < cpuidx; i++) {
+                set_cpu_possible(i, true);
+                cpu_logical_map(i) = tmp_map[i];
+                pr_debug("cpu logical map 0x%x\n", cpu_logical_map(i));
+        }
+}
+
 /**
  * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
  * @dt_phys: physical address of dt blob
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index da1d1aa20ad9..d15f1c503f3d 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -426,13 +426,14 @@ int __cpu_logical_map[NR_CPUS];
 void __init smp_setup_processor_id(void)
 {
         int i;
-        u32 cpu = is_smp() ? read_cpuid_mpidr() & 0xff : 0;
+        u32 mpidr = is_smp() ? read_cpuid_mpidr() & MPIDR_HWID_BITMASK : 0;
+        u32 cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 
         cpu_logical_map(0) = cpu;
-        for (i = 1; i < NR_CPUS; ++i)
+        for (i = 1; i < nr_cpu_ids; ++i)
                 cpu_logical_map(i) = i == cpu ? 0 : i;
 
-        printk(KERN_INFO "Booting Linux on physical CPU %d\n", cpu);
+        printk(KERN_INFO "Booting Linux on physical CPU 0x%x\n", mpidr);
 }
 
 static void __init setup_processor(void)
@@ -758,6 +759,7 @@ void __init setup_arch(char **cmdline_p)
 
         unflatten_device_tree();
 
+        arm_dt_init_cpu_maps();
 #ifdef CONFIG_SMP
         if (is_smp()) {
                 smp_set_ops(mdesc->smp);
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 26c12c6440fc..79282ebcd939 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -196,32 +196,7 @@ static inline void parse_dt_topology(void) {}
 static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {}
 #endif
 
-
-/*
- * cpu topology management
- */
-
-#define MPIDR_SMP_BITMASK (0x3 << 30)
-#define MPIDR_SMP_VALUE (0x2 << 30)
-
-#define MPIDR_MT_BITMASK (0x1 << 24)
-
-/*
- * These masks reflect the current use of the affinity levels.
- * The affinity level can be up to 16 bits according to ARM ARM
- */
-#define MPIDR_HWID_BITMASK 0xFFFFFF
-
-#define MPIDR_LEVEL0_MASK 0x3
-#define MPIDR_LEVEL0_SHIFT 0
-
-#define MPIDR_LEVEL1_MASK 0xF
-#define MPIDR_LEVEL1_SHIFT 8
-
-#define MPIDR_LEVEL2_MASK 0xFF
-#define MPIDR_LEVEL2_SHIFT 16
-
-/*
+ /*
  * cpu topology table
  */
 struct cputopo_arm cpu_topology[NR_CPUS];
@@ -282,19 +257,14 @@ void store_cpu_topology(unsigned int cpuid)
 
                 if (mpidr & MPIDR_MT_BITMASK) {
                         /* core performance interdependency */
-                        cpuid_topo->thread_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
-                                & MPIDR_LEVEL0_MASK;
-                        cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
-                                & MPIDR_LEVEL1_MASK;
-                        cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL2_SHIFT)
-                                & MPIDR_LEVEL2_MASK;
+                        cpuid_topo->thread_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+                        cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+                        cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
                 } else {
                         /* largely independent cores */
                         cpuid_topo->thread_id = -1;
-                        cpuid_topo->core_id = (mpidr >> MPIDR_LEVEL0_SHIFT)
-                                & MPIDR_LEVEL0_MASK;
-                        cpuid_topo->socket_id = (mpidr >> MPIDR_LEVEL1_SHIFT)
-                                & MPIDR_LEVEL1_MASK;
+                        cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+                        cpuid_topo->socket_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
                 }
         } else {
                 /*