ARM: mcpm: introduce helpers for platform coherency exit/setup

This provides helper methods to coordinate between CPUs coming down
and CPUs going up, as well as documentation on the used algorithms,
so that cluster teardown and setup
operations are not done for a cluster simultaneously.

For use in the power_down() implementation:
  * __mcpm_cpu_going_down(unsigned int cluster, unsigned int cpu)
  * __mcpm_outbound_enter_critical(unsigned int cluster)
  * __mcpm_outbound_leave_critical(unsigned int cluster)
  * __mcpm_cpu_down(unsigned int cluster, unsigned int cpu)

The power_up_setup() helper should do platform-specific setup in
preparation for turning the CPU on, such as invalidating local caches
or entering coherency.  It must be assembler for now, since it must
run before the MMU can be switched on.  It is passed the affinity level
for which initialization should be performed.

Because the mcpm_sync_struct content is looked-up and modified
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.  The sync_cache_*() helpers are used to that end.

Also, in order to prevent a cached writer from interfering with an
adjacent non-cached writer, we ensure each state variable is located to
a separate cache line.

Thanks to Nicolas Pitre and Achin Gupta for the help with this
patch.

Signed-off-by: Dave Martin <dave.martin@linaro.org>
Signed-off-by: Nicolas Pitre <nico@linaro.org>
Reviewed-by: Will Deacon <will.deacon@arm.com>

4 files changed, 330 insertions, 2 deletions

diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index 5d72889a58a..370236dd1a0 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -16,6 +16,7 @@
 #include <asm/mcpm.h>
 #include <asm/cacheflush.h>
 #include <asm/idmap.h>
+#include <asm/cputype.h>
 
 extern unsigned long mcpm_entry_vectors[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER];
 
@@ -111,3 +112,152 @@ int mcpm_cpu_powered_up(void)
 		platform_ops->powered_up();
 	return 0;
 }
+
+struct sync_struct mcpm_sync;
+
+/*
+ * __mcpm_cpu_going_down: Indicates that the cpu is being torn down.
+ *    This must be called at the point of committing to teardown of a CPU.
+ *    The CPU cache (SCTRL.C bit) is expected to still be active.
+ */
+void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster)
+{
+	mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_GOING_DOWN;
+	sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu);
+}
+
+/*
+ * __mcpm_cpu_down: Indicates that cpu teardown is complete and that the
+ *    cluster can be torn down without disrupting this CPU.
+ *    To avoid deadlocks, this must be called before a CPU is powered down.
+ *    The CPU cache (SCTRL.C bit) is expected to be off.
+ *    However L2 cache might or might not be active.
+ */
+void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster)
+{
+	dmb();
+	mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_DOWN;
+	sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu);
+	dsb_sev();
+}
+
+/*
+ * __mcpm_outbound_leave_critical: Leave the cluster teardown critical section.
+ * @state: the final state of the cluster:
+ *     CLUSTER_UP: no destructive teardown was done and the cluster has been
+ *         restored to the previous state (CPU cache still active); or
+ *     CLUSTER_DOWN: the cluster has been torn-down, ready for power-off
+ *         (CPU cache disabled, L2 cache either enabled or disabled).
+ */
+void __mcpm_outbound_leave_critical(unsigned int cluster, int state)
+{
+	dmb();
+	mcpm_sync.clusters[cluster].cluster = state;
+	sync_cache_w(&mcpm_sync.clusters[cluster].cluster);
+	dsb_sev();
+}
+
+/*
+ * __mcpm_outbound_enter_critical: Enter the cluster teardown critical section.
+ * This function should be called by the last man, after local CPU teardown
+ * is complete.  CPU cache expected to be active.
+ *
+ * Returns:
+ *     false: the critical section was not entered because an inbound CPU was
+ *         observed, or the cluster is already being set up;
+ *     true: the critical section was entered: it is now safe to tear down the
+ *         cluster.
+ */
+bool __mcpm_outbound_enter_critical(unsigned int cpu, unsigned int cluster)
+{
+	unsigned int i;
+	struct mcpm_sync_struct *c = &mcpm_sync.clusters[cluster];
+
+	/* Warn inbound CPUs that the cluster is being torn down: */
+	c->cluster = CLUSTER_GOING_DOWN;
+	sync_cache_w(&c->cluster);
+
+	/* Back out if the inbound cluster is already in the critical region: */
+	sync_cache_r(&c->inbound);
+	if (c->inbound == INBOUND_COMING_UP)
+		goto abort;
+
+	/*
+	 * Wait for all CPUs to get out of the GOING_DOWN state, so that local
+	 * teardown is complete on each CPU before tearing down the cluster.
+	 *
+	 * If any CPU has been woken up again from the DOWN state, then we
+	 * shouldn't be taking the cluster down at all: abort in that case.
+	 */
+	sync_cache_r(&c->cpus);
+	for (i = 0; i < MAX_CPUS_PER_CLUSTER; i++) {
+		int cpustate;
+
+		if (i == cpu)
+			continue;
+
+		while (1) {
+			cpustate = c->cpus[i].cpu;
+			if (cpustate != CPU_GOING_DOWN)
+				break;
+
+			wfe();
+			sync_cache_r(&c->cpus[i].cpu);
+		}
+
+		switch (cpustate) {
+		case CPU_DOWN:
+			continue;
+
+		default:
+			goto abort;
+		}
+	}
+
+	return true;
+
+abort:
+	__mcpm_outbound_leave_critical(cluster, CLUSTER_UP);
+	return false;
+}
+
+int __mcpm_cluster_state(unsigned int cluster)
+{
+	sync_cache_r(&mcpm_sync.clusters[cluster].cluster);
+	return mcpm_sync.clusters[cluster].cluster;
+}
+
+extern unsigned long mcpm_power_up_setup_phys;
+
+int __init mcpm_sync_init(
+	void (*power_up_setup)(unsigned int affinity_level))
+{
+	unsigned int i, j, mpidr, this_cluster;
+
+	BUILD_BUG_ON(MCPM_SYNC_CLUSTER_SIZE * MAX_NR_CLUSTERS != sizeof mcpm_sync);
+	BUG_ON((unsigned long)&mcpm_sync & (__CACHE_WRITEBACK_GRANULE - 1));
+
+	/*
+	 * Set initial CPU and cluster states.
+	 * Only one cluster is assumed to be active at this point.
+	 */
+	for (i = 0; i < MAX_NR_CLUSTERS; i++) {
+		mcpm_sync.clusters[i].cluster = CLUSTER_DOWN;
+		mcpm_sync.clusters[i].inbound = INBOUND_NOT_COMING_UP;
+		for (j = 0; j < MAX_CPUS_PER_CLUSTER; j++)
+			mcpm_sync.clusters[i].cpus[j].cpu = CPU_DOWN;
+	}
+	mpidr = read_cpuid_mpidr();
+	this_cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	for_each_online_cpu(i)
+		mcpm_sync.clusters[this_cluster].cpus[i].cpu = CPU_UP;
+	mcpm_sync.clusters[this_cluster].cluster = CLUSTER_UP;
+	sync_cache_w(&mcpm_sync);
+
+	if (power_up_setup) {
+		mcpm_power_up_setup_phys = virt_to_phys(power_up_setup);
+		sync_cache_w(&mcpm_power_up_setup_phys);
+	}
+
+	return 0;
+}
diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S
index 68c9903075a..7d729bd7267 100644
--- a/arch/arm/common/mcpm_head.S
+++ b/arch/arm/common/mcpm_head.S
@@ -7,11 +7,19 @@
  * 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.
+ *
+ *
+ * Refer to Documentation/arm/cluster-pm-race-avoidance.txt
+ * for details of the synchronisation algorithms used here.
  */
 
 #include <linux/linkage.h>
 #include <asm/mcpm.h>
 
+.if MCPM_SYNC_CLUSTER_CPUS
+.error "cpus must be the first member of struct mcpm_sync_struct"
+.endif
+
 	.macro	pr_dbg	string
 #if defined(CONFIG_DEBUG_LL) && defined(DEBUG)
 	b	1901f
@@ -57,24 +65,114 @@ ENTRY(mcpm_entry_point)
 2:	pr_dbg	"kernel mcpm_entry_point\n"
 
 	/*
-	 * MMU is off so we need to get to mcpm_entry_vectors in a
+	 * MMU is off so we need to get to various variables in a
 	 * position independent way.
 	 */
 	adr	r5, 3f
-	ldr	r6, [r5]
+	ldmia	r5, {r6, r7, r8}
 	add	r6, r5, r6			@ r6 = mcpm_entry_vectors
+	ldr	r7, [r5, r7]			@ r7 = mcpm_power_up_setup_phys
+	add	r8, r5, r8			@ r8 = mcpm_sync
+
+	mov	r0, #MCPM_SYNC_CLUSTER_SIZE
+	mla	r8, r0, r10, r8			@ r8 = sync cluster base
+
+	@ Signal that this CPU is coming UP:
+	mov	r0, #CPU_COMING_UP
+	mov	r5, #MCPM_SYNC_CPU_SIZE
+	mla	r5, r9, r5, r8			@ r5 = sync cpu address
+	strb	r0, [r5]
+
+	@ At this point, the cluster cannot unexpectedly enter the GOING_DOWN
+	@ state, because there is at least one active CPU (this CPU).
+
+	@ Note: the following is racy as another CPU might be testing
+	@ the same flag at the same moment.  That'll be fixed later.
+	ldrb	r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER]
+	cmp	r0, #CLUSTER_UP			@ cluster already up?
+	bne	mcpm_setup			@ if not, set up the cluster
+
+	@ Otherwise, skip setup:
+	b	mcpm_setup_complete
+
+mcpm_setup:
+	@ Control dependency implies strb not observable before previous ldrb.
+
+	@ Signal that the cluster is being brought up:
+	mov	r0, #INBOUND_COMING_UP
+	strb	r0, [r8, #MCPM_SYNC_CLUSTER_INBOUND]
+	dmb
+
+	@ Any CPU trying to take the cluster into CLUSTER_GOING_DOWN from this
+	@ point onwards will observe INBOUND_COMING_UP and abort.
+
+	@ Wait for any previously-pending cluster teardown operations to abort
+	@ or complete:
+mcpm_teardown_wait:
+	ldrb	r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER]
+	cmp	r0, #CLUSTER_GOING_DOWN
+	bne	first_man_setup
+	wfe
+	b	mcpm_teardown_wait
+
+first_man_setup:
+	dmb
+
+	@ If the outbound gave up before teardown started, skip cluster setup:
+
+	cmp	r0, #CLUSTER_UP
+	beq	mcpm_setup_leave
+
+	@ power_up_setup is now responsible for setting up the cluster:
+
+	cmp	r7, #0
+	mov	r0, #1		@ second (cluster) affinity level
+	blxne	r7		@ Call power_up_setup if defined
+	dmb
+
+	mov	r0, #CLUSTER_UP
+	strb	r0, [r8, #MCPM_SYNC_CLUSTER_CLUSTER]
+	dmb
+
+mcpm_setup_leave:
+	@ Leave the cluster setup critical section:
+
+	mov	r0, #INBOUND_NOT_COMING_UP
+	strb	r0, [r8, #MCPM_SYNC_CLUSTER_INBOUND]
+	dsb
+	sev
+
+mcpm_setup_complete:
+	@ If a platform-specific CPU setup hook is needed, it is
+	@ called from here.
+
+	cmp	r7, #0
+	mov	r0, #0		@ first (CPU) affinity level
+	blxne	r7		@ Call power_up_setup if defined
+	dmb
+
+	@ Mark the CPU as up:
+
+	mov	r0, #CPU_UP
+	strb	r0, [r5]
+
+	@ Observability order of CPU_UP and opening of the gate does not matter.
 
 mcpm_entry_gated:
 	ldr	r5, [r6, r4, lsl #2]		@ r5 = CPU entry vector
 	cmp	r5, #0
 	wfeeq
 	beq	mcpm_entry_gated
+	dmb
+
 	pr_dbg	"released\n"
 	bx	r5
 
 	.align	2
 
 3:	.word	mcpm_entry_vectors - .
+	.word	mcpm_power_up_setup_phys - 3b
+	.word	mcpm_sync - 3b
 
 ENDPROC(mcpm_entry_point)
 
@@ -84,3 +182,7 @@ ENDPROC(mcpm_entry_point)
 	.type	mcpm_entry_vectors, #object
 ENTRY(mcpm_entry_vectors)
 	.space	4 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
+
+	.type	mcpm_power_up_setup_phys, #object
+ENTRY(mcpm_power_up_setup_phys)
+	.space  4		@ set by mcpm_sync_init()
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index 627761fce78..3046e90210c 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -24,6 +24,9 @@
 
 #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.
@@ -130,5 +133,75 @@ struct mcpm_platform_ops {
  */
 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));
+
+#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/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 923eec7105c..1bed82a0a9e 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -149,6 +149,9 @@ int main(void)
   DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
   DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
   DEFINE(DMA_FROM_DEVICE,	DMA_FROM_DEVICE);
+  BLANK();
+  DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE);
+  BLANK();
 #ifdef CONFIG_KVM_ARM_HOST
   DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
   DEFINE(VCPU_MIDR,		offsetof(struct kvm_vcpu, arch.midr));