@@ -18,6 +18,8 @@
#define INVALID_HWID ULONG_MAX
+#define MPIDR_UP_BITMASK (0x1 << 30)
+#define MPIDR_MT_BITMASK (0x1 << 24)
#define MPIDR_HWID_BITMASK 0xff00ffffff
#define MPIDR_LEVEL_BITS_SHIFT 3
@@ -30,6 +32,9 @@
#define MPIDR_AFFINITY_LEVEL(mpidr, level) \
((mpidr >> MPIDR_LEVEL_SHIFT(level)) & MPIDR_LEVEL_MASK)
+#define MPIDR_AFF_MASK(level) \
+ ((u64)MPIDR_LEVEL_MASK << MPIDR_LEVEL_SHIFT(level))
+
#define read_cpuid(reg) ({ \
u64 __val; \
asm("mrs %0, " #reg : "=r" (__val)); \
@@ -21,6 +21,8 @@
#include <linux/sched.h>
#include <linux/slab.h>
+#include <asm/cputype.h>
+#include <asm/smp_plat.h>
#include <asm/topology.h>
/*
@@ -362,9 +364,7 @@ static void update_siblings_masks(unsigned int cpuid)
int cpu;
if (cpuid_topo->cluster_id == -1) {
- /*
- * DT does not contain topology information for this cpu.
- */
+ /* No topology information for this cpu ?! */
pr_debug("CPU%u: No topology information configured\n", cpuid);
return;
}
@@ -391,6 +391,44 @@ static void update_siblings_masks(unsigned int cpuid)
void store_cpu_topology(unsigned int cpuid)
{
+ struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
+ u64 mpidr;
+
+ if (cpuid_topo->cluster_id != -1)
+ goto topology_populated;
+
+ mpidr = read_cpuid_mpidr();
+
+ /* Create cpu topology mapping based on MPIDR. */
+ if (mpidr & MPIDR_UP_BITMASK) {
+ /* Uniprocessor system */
+ cpuid_topo->thread_id = -1;
+ cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cpuid_topo->cluster_id = 0;
+ } else if (mpidr & MPIDR_MT_BITMASK) {
+ /* Multiprocessor system : Multi-threads per core */
+ cpuid_topo->thread_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+ cpuid_topo->cluster_id =
+ ((mpidr & MPIDR_AFF_MASK(2)) >> mpidr_hash.shift_aff[2] |
+ (mpidr & MPIDR_AFF_MASK(3)) >> mpidr_hash.shift_aff[3])
+ >> mpidr_hash.shift_aff[1] >> mpidr_hash.shift_aff[0];
+ } else {
+ /* Multiprocessor system : Single-thread per core */
+ cpuid_topo->thread_id = -1;
+ cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cpuid_topo->cluster_id =
+ ((mpidr & MPIDR_AFF_MASK(1)) >> mpidr_hash.shift_aff[1] |
+ (mpidr & MPIDR_AFF_MASK(2)) >> mpidr_hash.shift_aff[2] |
+ (mpidr & MPIDR_AFF_MASK(3)) >> mpidr_hash.shift_aff[3])
+ >> mpidr_hash.shift_aff[0];
+ }
+
+ pr_debug("CPU%u: cluster %d core %d thread %d mpidr %llx\n",
+ cpuid, cpuid_topo->cluster_id, cpuid_topo->core_id,
+ cpuid_topo->thread_id, mpidr);
+
+topology_populated:
update_siblings_masks(cpuid);
update_cpu_power(cpuid);
}
Create cpu topology based on MPIDR. When hardware sets MPIDR to sane values, this method will always work. Therefore it should also work well as the fallback method. [1] When we have multiple processing elements in the system, we create the cpu topology by mapping each affinity level (from lowest to highest) to threads (if they exist), cores, and clusters. We combine data from all higher affinity levels into cluster_id so we don't lose any information from MPIDR. [2] [1] http://www.spinics.net/lists/arm-kernel/msg317445.html [2] https://lkml.org/lkml/2014/4/23/703 Signed-off-by: Zi Shen Lim <zlim@broadcom.com> --- v1->v2: Addressed comments from Mark Brown. - Reduce noise. Use pr_debug instead of pr_info. - Don't ignore higher affinity levels. v2->v3: Addressed comments from Lorenzo Pieralisi. - Rebased on top of Mark Brown's DT topology series. - Make MPIDR fallback option. - Fixed usage of mpidr_hash.shift_aff. Please review :) Tested on my multi-core multi-thread model. arch/arm64/include/asm/cputype.h | 5 +++++ arch/arm64/kernel/topology.c | 44 +++++++++++++++++++++++++++++++++++++--- 2 files changed, 46 insertions(+), 3 deletions(-)