Merge branch 'devel-stable' into for-next

Conflicts:
	arch/arm/Makefile
	arch/arm/include/asm/glue-proc.h

1 files changed, 97 insertions, 4 deletions

diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 0cde326f5542..9b653278c9e8 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -37,6 +37,7 @@
 #include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/procinfo.h>
+#include <asm/psci.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
@@ -128,7 +129,9 @@ struct stack {
 	u32 und[3];
 } ____cacheline_aligned;
 
+#ifndef CONFIG_CPU_V7M
 static struct stack stacks[NR_CPUS];
+#endif
 
 char elf_platform[ELF_PLATFORM_SIZE];
 EXPORT_SYMBOL(elf_platform);
@@ -207,7 +210,7 @@ static const char *proc_arch[] = {
 	"5TEJ",
 	"6TEJ",
 	"7",
-	"?(11)",
+	"7M",
 	"?(12)",
 	"?(13)",
 	"?(14)",
@@ -216,6 +219,12 @@ static const char *proc_arch[] = {
 	"?(17)",
 };
 
+#ifdef CONFIG_CPU_V7M
+static int __get_cpu_architecture(void)
+{
+	return CPU_ARCH_ARMv7M;
+}
+#else
 static int __get_cpu_architecture(void)
 {
 	int cpu_arch;
@@ -248,6 +257,7 @@ static int __get_cpu_architecture(void)
 
 	return cpu_arch;
 }
+#endif
 
 int __pure cpu_architecture(void)
 {
@@ -293,7 +303,9 @@ static void __init cacheid_init(void)
 {
 	unsigned int arch = cpu_architecture();
 
-	if (arch >= CPU_ARCH_ARMv6) {
+	if (arch == CPU_ARCH_ARMv7M) {
+		cacheid = 0;
+	} else if (arch >= CPU_ARCH_ARMv6) {
 		unsigned int cachetype = read_cpuid_cachetype();
 		if ((cachetype & (7 << 29)) == 4 << 29) {
 			/* ARMv7 register format */
@@ -355,7 +367,7 @@ void __init early_print(const char *str, ...)
 
 static void __init cpuid_init_hwcaps(void)
 {
-	unsigned int divide_instrs;
+	unsigned int divide_instrs, vmsa;
 
 	if (cpu_architecture() < CPU_ARCH_ARMv7)
 		return;
@@ -368,6 +380,11 @@ static void __init cpuid_init_hwcaps(void)
 	case 1:
 		elf_hwcap |= HWCAP_IDIVT;
 	}
+
+	/* LPAE implies atomic ldrd/strd instructions */
+	vmsa = (read_cpuid_ext(CPUID_EXT_MMFR0) & 0xf) >> 0;
+	if (vmsa >= 5)
+		elf_hwcap |= HWCAP_LPAE;
 }
 
 static void __init feat_v6_fixup(void)
@@ -392,6 +409,7 @@ static void __init feat_v6_fixup(void)
  */
 void notrace cpu_init(void)
 {
+#ifndef CONFIG_CPU_V7M
 	unsigned int cpu = smp_processor_id();
 	struct stack *stk = &stacks[cpu];
 
@@ -442,6 +460,7 @@ void notrace cpu_init(void)
 	      "I" (offsetof(struct stack, und[0])),
 	      PLC (PSR_F_BIT | PSR_I_BIT | SVC_MODE)
 	    : "r14");
+#endif
 }
 
 u32 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = MPIDR_INVALID };
@@ -466,6 +485,72 @@ void __init smp_setup_processor_id(void)
 	printk(KERN_INFO "Booting Linux on physical CPU 0x%x\n", mpidr);
 }
 
+struct mpidr_hash mpidr_hash;
+#ifdef CONFIG_SMP
+/**
+ * smp_build_mpidr_hash - Pre-compute shifts required at each affinity
+ *			  level in order to build a linear index from an
+ *			  MPIDR value. Resulting algorithm is a collision
+ *			  free hash carried out through shifting and ORing
+ */
+static void __init smp_build_mpidr_hash(void)
+{
+	u32 i, affinity;
+	u32 fs[3], bits[3], ls, mask = 0;
+	/*
+	 * Pre-scan the list of MPIDRS and filter out bits that do
+	 * not contribute to affinity levels, ie they never toggle.
+	 */
+	for_each_possible_cpu(i)
+		mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
+	pr_debug("mask of set bits 0x%x\n", mask);
+	/*
+	 * Find and stash the last and first bit set at all affinity levels to
+	 * check how many bits are required to represent them.
+	 */
+	for (i = 0; i < 3; i++) {
+		affinity = MPIDR_AFFINITY_LEVEL(mask, i);
+		/*
+		 * Find the MSB bit and LSB bits position
+		 * to determine how many bits are required
+		 * to express the affinity level.
+		 */
+		ls = fls(affinity);
+		fs[i] = affinity ? ffs(affinity) - 1 : 0;
+		bits[i] = ls - fs[i];
+	}
+	/*
+	 * An index can be created from the MPIDR by isolating the
+	 * significant bits at each affinity level and by shifting
+	 * them in order to compress the 24 bits values space to a
+	 * compressed set of values. This is equivalent to hashing
+	 * the MPIDR through shifting and ORing. It is a collision free
+	 * hash though not minimal since some levels might contain a number
+	 * of CPUs that is not an exact power of 2 and their bit
+	 * representation might contain holes, eg MPIDR[7:0] = {0x2, 0x80}.
+	 */
+	mpidr_hash.shift_aff[0] = fs[0];
+	mpidr_hash.shift_aff[1] = MPIDR_LEVEL_BITS + fs[1] - bits[0];
+	mpidr_hash.shift_aff[2] = 2*MPIDR_LEVEL_BITS + fs[2] -
+						(bits[1] + bits[0]);
+	mpidr_hash.mask = mask;
+	mpidr_hash.bits = bits[2] + bits[1] + bits[0];
+	pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] mask[0x%x] bits[%u]\n",
+				mpidr_hash.shift_aff[0],
+				mpidr_hash.shift_aff[1],
+				mpidr_hash.shift_aff[2],
+				mpidr_hash.mask,
+				mpidr_hash.bits);
+	/*
+	 * 4x is an arbitrary value used to warn on a hash table much bigger
+	 * than expected on most systems.
+	 */
+	if (mpidr_hash_size() > 4 * num_possible_cpus())
+		pr_warn("Large number of MPIDR hash buckets detected\n");
+	sync_cache_w(&mpidr_hash);
+}
+#endif
+
 static void __init setup_processor(void)
 {
 	struct proc_info_list *list;
@@ -803,10 +888,17 @@ void __init setup_arch(char **cmdline_p)
 	unflatten_device_tree();
 
 	arm_dt_init_cpu_maps();
+	psci_init();
 #ifdef CONFIG_SMP
 	if (is_smp()) {
-		smp_set_ops(mdesc->smp);
+		if (!mdesc->smp_init || !mdesc->smp_init()) {
+			if (psci_smp_available())
+				smp_set_ops(&psci_smp_ops);
+			else if (mdesc->smp)
+				smp_set_ops(mdesc->smp);
+		}
 		smp_init_cpus();
+		smp_build_mpidr_hash();
 	}
 #endif
 
@@ -879,6 +971,7 @@ static const char *hwcap_str[] = {
 	"vfpv4",
 	"idiva",
 	"idivt",
+	"lpae",
 	NULL
 };