Merge branch 'mcpm' of git://git.linaro.org/people/nico/linux into devel-stable

7 files changed, 322 insertions, 33 deletions

diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index e1489c54cd12..bff71388e72a 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -363,4 +363,79 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 		flush_cache_all();
 }
 
+/*
+ * Memory synchronization helpers for mixed cached vs non cached accesses.
+ *
+ * Some synchronization algorithms have to set states in memory with the
+ * cache enabled or disabled depending on the code path.  It is crucial
+ * to always ensure proper cache maintenance to update main memory right
+ * away in that case.
+ *
+ * Any cached write must be followed by a cache clean operation.
+ * Any cached read must be preceded by a cache invalidate operation.
+ * Yet, in the read case, a cache flush i.e. atomic clean+invalidate
+ * operation is needed to avoid discarding possible concurrent writes to the
+ * accessed memory.
+ *
+ * Also, in order to prevent a cached writer from interfering with an
+ * adjacent non-cached writer, each state variable must be located to
+ * a separate cache line.
+ */
+
+/*
+ * This needs to be >= the max cache writeback size of all
+ * supported platforms included in the current kernel configuration.
+ * This is used to align state variables to their own cache lines.
+ */
+#define __CACHE_WRITEBACK_ORDER 6  /* guessed from existing platforms */
+#define __CACHE_WRITEBACK_GRANULE (1 << __CACHE_WRITEBACK_ORDER)
+
+/*
+ * There is no __cpuc_clean_dcache_area but we use it anyway for
+ * code intent clarity, and alias it to __cpuc_flush_dcache_area.
+ */
+#define __cpuc_clean_dcache_area __cpuc_flush_dcache_area
+
+/*
+ * Ensure preceding writes to *p by this CPU are visible to
+ * subsequent reads by other CPUs:
+ */
+static inline void __sync_cache_range_w(volatile void *p, size_t size)
+{
+	char *_p = (char *)p;
+
+	__cpuc_clean_dcache_area(_p, size);
+	outer_clean_range(__pa(_p), __pa(_p + size));
+}
+
+/*
+ * Ensure preceding writes to *p by other CPUs are visible to
+ * subsequent reads by this CPU.  We must be careful not to
+ * discard data simultaneously written by another CPU, hence the
+ * usage of flush rather than invalidate operations.
+ */
+static inline void __sync_cache_range_r(volatile void *p, size_t size)
+{
+	char *_p = (char *)p;
+
+#ifdef CONFIG_OUTER_CACHE
+	if (outer_cache.flush_range) {
+		/*
+		 * Ensure dirty data migrated from other CPUs into our cache
+		 * are cleaned out safely before the outer cache is cleaned:
+		 */
+		__cpuc_clean_dcache_area(_p, size);
+
+		/* Clean and invalidate stale data for *p from outer ... */
+		outer_flush_range(__pa(_p), __pa(_p + size));
+	}
+#endif
+
+	/* ... and inner cache: */
+	__cpuc_flush_dcache_area(_p, size);
+}
+
+#define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr))
+#define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr))
+
 #endif
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
new file mode 100644
index 000000000000..0f7b7620e9a5
--- /dev/null
+++ b/arch/arm/include/asm/mcpm.h
@@ -0,0 +1,209 @@
+/*
+ * arch/arm/include/asm/mcpm.h
+ *
+ * Created by:  Nicolas Pitre, April 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.
+ */
+
+#ifndef MCPM_H
+#define MCPM_H
+
+/*
+ * Maximum number of possible clusters / CPUs per cluster.
+ *
+ * This should be sufficient for quite a while, while keeping the
+ * (assembly) code simpler.  When this starts to grow then we'll have
+ * to consider dynamic allocation.
+ */
+#define MAX_CPUS_PER_CLUSTER	4
+#define MAX_NR_CLUSTERS		2
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Platform specific code should use this symbol to set up secondary
+ * entry location for processors to use when released from reset.
+ */
+extern void mcpm_entry_point(void);
+
+/*
+ * This is used to indicate where the given CPU from given cluster should
+ * branch once it is ready to re-enter the kernel using ptr, or NULL if it
+ * should be gated.  A gated CPU is held in a WFE loop until its vector
+ * becomes non NULL.
+ */
+void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr);
+
+/*
+ * CPU/cluster power operations API for higher subsystems to use.
+ */
+
+/**
+ * mcpm_cpu_power_up - make given CPU in given cluster runable
+ *
+ * @cpu: CPU number within given cluster
+ * @cluster: cluster number for the CPU
+ *
+ * The identified CPU is brought out of reset.  If the cluster was powered
+ * down then it is brought up as well, taking care not to let the other CPUs
+ * in the cluster run, and ensuring appropriate cluster setup.
+ *
+ * Caller must ensure the appropriate entry vector is initialized with
+ * mcpm_set_entry_vector() prior to calling this.
+ *
+ * This must be called in a sleepable context.  However, the implementation
+ * is strongly encouraged to return early and let the operation happen
+ * asynchronously, especially when significant delays are expected.
+ *
+ * If the operation cannot be performed then an error code is returned.
+ */
+int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster);
+
+/**
+ * mcpm_cpu_power_down - power the calling CPU down
+ *
+ * The calling CPU is powered down.
+ *
+ * If this CPU is found to be the "last man standing" in the cluster
+ * then the cluster is prepared for power-down too.
+ *
+ * This must be called with interrupts disabled.
+ *
+ * This does not return.  Re-entry in the kernel is expected via
+ * mcpm_entry_point.
+ */
+void mcpm_cpu_power_down(void);
+
+/**
+ * mcpm_cpu_suspend - bring the calling CPU in a suspended state
+ *
+ * @expected_residency: duration in microseconds the CPU is expected
+ *			to remain suspended, or 0 if unknown/infinity.
+ *
+ * The calling CPU is suspended.  The expected residency argument is used
+ * as a hint by the platform specific backend to implement the appropriate
+ * sleep state level according to the knowledge it has on wake-up latency
+ * for the given hardware.
+ *
+ * If this CPU is found to be the "last man standing" in the cluster
+ * then the cluster may be prepared for power-down too, if the expected
+ * residency makes it worthwhile.
+ *
+ * This must be called with interrupts disabled.
+ *
+ * This does not return.  Re-entry in the kernel is expected via
+ * mcpm_entry_point.
+ */
+void mcpm_cpu_suspend(u64 expected_residency);
+
+/**
+ * mcpm_cpu_powered_up - housekeeping workafter a CPU has been powered up
+ *
+ * This lets the platform specific backend code perform needed housekeeping
+ * work.  This must be called by the newly activated CPU as soon as it is
+ * fully operational in kernel space, before it enables interrupts.
+ *
+ * If the operation cannot be performed then an error code is returned.
+ */
+int mcpm_cpu_powered_up(void);
+
+/*
+ * Platform specific methods used in the implementation of the above API.
+ */
+struct mcpm_platform_ops {
+	int (*power_up)(unsigned int cpu, unsigned int cluster);
+	void (*power_down)(void);
+	void (*suspend)(u64);
+	void (*powered_up)(void);
+};
+
+/**
+ * mcpm_platform_register - register platform specific power methods
+ *
+ * @ops: mcpm_platform_ops structure to register
+ *
+ * An error is returned if the registration has been done previously.
+ */
+int __init mcpm_platform_register(const struct mcpm_platform_ops *ops);
+
+/* Synchronisation structures for coordinating safe cluster setup/teardown: */
+
+/*
+ * When modifying this structure, make sure you update the MCPM_SYNC_ defines
+ * to match.
+ */
+struct mcpm_sync_struct {
+	/* individual CPU states */
+	struct {
+		s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE);
+	} cpus[MAX_CPUS_PER_CLUSTER];
+
+	/* cluster state */
+	s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE);
+
+	/* inbound-side state */
+	s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE);
+};
+
+struct sync_struct {
+	struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS];
+};
+
+extern unsigned long sync_phys;	/* physical address of *mcpm_sync */
+
+void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster);
+void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster);
+void __mcpm_outbound_leave_critical(unsigned int cluster, int state);
+bool __mcpm_outbound_enter_critical(unsigned int this_cpu, unsigned int cluster);
+int __mcpm_cluster_state(unsigned int cluster);
+
+int __init mcpm_sync_init(
+	void (*power_up_setup)(unsigned int affinity_level));
+
+void __init mcpm_smp_set_ops(void);
+
+#else
+
+/* 
+ * asm-offsets.h causes trouble when included in .c files, and cacheflush.h
+ * cannot be included in asm files.  Let's work around the conflict like this.
+ */
+#include <asm/asm-offsets.h>
+#define __CACHE_WRITEBACK_GRANULE CACHE_WRITEBACK_GRANULE
+
+#endif /* ! __ASSEMBLY__ */
+
+/* Definitions for mcpm_sync_struct */
+#define CPU_DOWN		0x11
+#define CPU_COMING_UP		0x12
+#define CPU_UP			0x13
+#define CPU_GOING_DOWN		0x14
+
+#define CLUSTER_DOWN		0x21
+#define CLUSTER_UP		0x22
+#define CLUSTER_GOING_DOWN	0x23
+
+#define INBOUND_NOT_COMING_UP	0x31
+#define INBOUND_COMING_UP	0x32
+
+/*
+ * Offsets for the mcpm_sync_struct members, for use in asm.
+ * We don't want to make them global to the kernel via asm-offsets.c.
+ */
+#define MCPM_SYNC_CLUSTER_CPUS	0
+#define MCPM_SYNC_CPU_SIZE	__CACHE_WRITEBACK_GRANULE
+#define MCPM_SYNC_CLUSTER_CLUSTER \
+	(MCPM_SYNC_CLUSTER_CPUS + MCPM_SYNC_CPU_SIZE * MAX_CPUS_PER_CLUSTER)
+#define MCPM_SYNC_CLUSTER_INBOUND \
+	(MCPM_SYNC_CLUSTER_CLUSTER + __CACHE_WRITEBACK_GRANULE)
+#define MCPM_SYNC_CLUSTER_SIZE \
+	(MCPM_SYNC_CLUSTER_INBOUND + __CACHE_WRITEBACK_GRANULE)
+
+#endif
diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
index 9f77e7804f3b..e3d55547e755 100644
--- a/arch/arm/include/asm/mmu.h
+++ b/arch/arm/include/asm/mmu.h
@@ -5,15 +5,15 @@
 
 typedef struct {
 #ifdef CONFIG_CPU_HAS_ASID
-	u64 id;
+	atomic64_t	id;
 #endif
-	unsigned int vmalloc_seq;
+	unsigned int	vmalloc_seq;
 } mm_context_t;
 
 #ifdef CONFIG_CPU_HAS_ASID
 #define ASID_BITS	8
 #define ASID_MASK	((~0ULL) << ASID_BITS)
-#define ASID(mm)	((mm)->context.id & ~ASID_MASK)
+#define ASID(mm)	((mm)->context.id.counter & ~ASID_MASK)
 #else
 #define ASID(mm)	(0)
 #endif
@@ -26,7 +26,7 @@ typedef struct {
  *  modified for 2.6 by Hyok S. Choi <hyok.choi@samsung.com>
  */
 typedef struct {
-	unsigned long		end_brk;
+	unsigned long	end_brk;
 } mm_context_t;
 
 #endif
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index e1f644bc7cc5..863a6611323c 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -25,7 +25,7 @@ void __check_vmalloc_seq(struct mm_struct *mm);
 #ifdef CONFIG_CPU_HAS_ASID
 
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk);
-#define init_new_context(tsk,mm)	({ mm->context.id = 0; })
+#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
 
 #else	/* !CONFIG_CPU_HAS_ASID */
 
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 6e924d3a77eb..4db8c8820f0d 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -34,10 +34,13 @@
 #define TLB_V6_D_ASID	(1 << 17)
 #define TLB_V6_I_ASID	(1 << 18)
 
+#define TLB_V6_BP	(1 << 19)
+
 /* Unified Inner Shareable TLB operations (ARMv7 MP extensions) */
-#define TLB_V7_UIS_PAGE	(1 << 19)
-#define TLB_V7_UIS_FULL (1 << 20)
-#define TLB_V7_UIS_ASID (1 << 21)
+#define TLB_V7_UIS_PAGE	(1 << 20)
+#define TLB_V7_UIS_FULL (1 << 21)
+#define TLB_V7_UIS_ASID (1 << 22)
+#define TLB_V7_UIS_BP	(1 << 23)
 
 #define TLB_BARRIER	(1 << 28)
 #define TLB_L2CLEAN_FR	(1 << 29)		/* Feroceon */
@@ -150,7 +153,8 @@
 #define v6wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
 			 TLB_V6_I_FULL | TLB_V6_D_FULL | \
 			 TLB_V6_I_PAGE | TLB_V6_D_PAGE | \
-			 TLB_V6_I_ASID | TLB_V6_D_ASID)
+			 TLB_V6_I_ASID | TLB_V6_D_ASID | \
+			 TLB_V6_BP)
 
 #ifdef CONFIG_CPU_TLB_V6
 # define v6wbi_possible_flags	v6wbi_tlb_flags
@@ -166,9 +170,11 @@
 #endif
 
 #define v7wbi_tlb_flags_smp	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
-			 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | TLB_V7_UIS_ASID)
+				 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | \
+				 TLB_V7_UIS_ASID | TLB_V7_UIS_BP)
 #define v7wbi_tlb_flags_up	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
-			 TLB_V6_U_FULL | TLB_V6_U_PAGE | TLB_V6_U_ASID)
+				 TLB_V6_U_FULL | TLB_V6_U_PAGE | \
+				 TLB_V6_U_ASID | TLB_V6_BP)
 
 #ifdef CONFIG_CPU_TLB_V7
 
@@ -430,6 +436,20 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 	}
 }
 
+static inline void local_flush_bp_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_V7_UIS_BP))
+		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero));
+	else if (tlb_flag(TLB_V6_BP))
+		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero));
+
+	if (tlb_flag(TLB_BARRIER))
+		isb();
+}
+
 /*
  *	flush_pmd_entry
  *
@@ -480,6 +500,7 @@ static inline void clean_pmd_entry(void *pmd)
 #define flush_tlb_kernel_page	local_flush_tlb_kernel_page
 #define flush_tlb_range		local_flush_tlb_range
 #define flush_tlb_kernel_range	local_flush_tlb_kernel_range
+#define flush_bp_all		local_flush_bp_all
 #else
 extern void flush_tlb_all(void);
 extern void flush_tlb_mm(struct mm_struct *mm);
@@ -487,6 +508,7 @@ extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr);
 extern void flush_tlb_kernel_page(unsigned long kaddr);
 extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void flush_bp_all(void);
 #endif
 
 /*
diff --git a/arch/arm/include/asm/xen/events.h b/arch/arm/include/asm/xen/events.h
index 5c27696de14f..8b1f37bfeeec 100644
--- a/arch/arm/include/asm/xen/events.h
+++ b/arch/arm/include/asm/xen/events.h
@@ -2,6 +2,7 @@
 #define _ASM_ARM_XEN_EVENTS_H
 
 #include <asm/ptrace.h>
+#include <asm/atomic.h>
 
 enum ipi_vector {
 	XEN_PLACEHOLDER_VECTOR,
@@ -15,26 +16,8 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
 	return raw_irqs_disabled_flags(regs->ARM_cpsr);
 }
 
-/*
- * We cannot use xchg because it does not support 8-byte
- * values. However it is safe to use {ldr,dtd}exd directly because all
- * platforms which Xen can run on support those instructions.
- */
-static inline xen_ulong_t xchg_xen_ulong(xen_ulong_t *ptr, xen_ulong_t val)
-{
-	xen_ulong_t oldval;
-	unsigned int tmp;
-
-	wmb();
-	asm volatile("@ xchg_xen_ulong\n"
-		"1:     ldrexd  %0, %H0, [%3]\n"
-		"       strexd  %1, %2, %H2, [%3]\n"
-		"       teq     %1, #0\n"
-		"       bne     1b"
-		: "=&r" (oldval), "=&r" (tmp)
-		: "r" (val), "r" (ptr)
-		: "memory", "cc");
-	return oldval;
-}
+#define xchg_xen_ulong(ptr, val) atomic64_xchg(container_of((ptr),	\
+							    atomic64_t,	\
+							    counter), (val))
 
 #endif /* _ASM_ARM_XEN_EVENTS_H */
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 4da7cde70b5d..af33b44990ed 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -404,7 +404,7 @@
 #define __NR_setns			(__NR_SYSCALL_BASE+375)
 #define __NR_process_vm_readv		(__NR_SYSCALL_BASE+376)
 #define __NR_process_vm_writev		(__NR_SYSCALL_BASE+377)
-					/* 378 for kcmp */
+#define __NR_kcmp			(__NR_SYSCALL_BASE+378)
 #define __NR_finit_module		(__NR_SYSCALL_BASE+379)
 
 /*