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>
diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S
index 68c9903..7d729bd 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 @@
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 @@
.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()