Merge branch 'devel-stable' into for-next

Conflicts:
	arch/arm/kernel/perf_event_cpu.c
This commit is contained in:
Russell King 2014-08-05 10:27:25 +01:00
commit f15bdfe4fb
10 changed files with 362 additions and 1107 deletions

View File

@ -91,9 +91,7 @@
* of this define that was meant to.
* Fortunately, there is no reference for this in noMMU mode, for now.
*/
#ifndef TASK_SIZE
#define TASK_SIZE (CONFIG_DRAM_SIZE)
#endif
#define TASK_SIZE UL(0xffffffff)
#ifndef TASK_UNMAPPED_BASE
#define TASK_UNMAPPED_BASE UL(0x00000000)

View File

@ -12,15 +12,6 @@
#ifndef __ARM_PERF_EVENT_H__
#define __ARM_PERF_EVENT_H__
/*
* The ARMv7 CPU PMU supports up to 32 event counters.
*/
#define ARMPMU_MAX_HWEVENTS 32
#define HW_OP_UNSUPPORTED 0xFFFF
#define C(_x) PERF_COUNT_HW_CACHE_##_x
#define CACHE_OP_UNSUPPORTED 0xFFFF
#ifdef CONFIG_HW_PERF_EVENTS
struct pt_regs;
extern unsigned long perf_instruction_pointer(struct pt_regs *regs);

View File

@ -42,6 +42,25 @@ struct arm_pmu_platdata {
#ifdef CONFIG_HW_PERF_EVENTS
/*
* The ARMv7 CPU PMU supports up to 32 event counters.
*/
#define ARMPMU_MAX_HWEVENTS 32
#define HW_OP_UNSUPPORTED 0xFFFF
#define C(_x) PERF_COUNT_HW_CACHE_##_x
#define CACHE_OP_UNSUPPORTED 0xFFFF
#define PERF_MAP_ALL_UNSUPPORTED \
[0 ... PERF_COUNT_HW_MAX - 1] = HW_OP_UNSUPPORTED
#define PERF_CACHE_MAP_ALL_UNSUPPORTED \
[0 ... C(MAX) - 1] = { \
[0 ... C(OP_MAX) - 1] = { \
[0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED, \
}, \
}
/* The events for a given PMU register set. */
struct pmu_hw_events {
/*

View File

@ -242,7 +242,7 @@ static inline void set_fs(mm_segment_t fs)
#define access_ok(type,addr,size) (__range_ok(addr,size) == 0)
#define user_addr_max() \
(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
(segment_eq(get_fs(), KERNEL_DS) ? ~0UL : get_fs())
/*
* The "__xxx" versions of the user access functions do not verify the

View File

@ -560,11 +560,16 @@ user_backtrace(struct frame_tail __user *tail,
struct perf_callchain_entry *entry)
{
struct frame_tail buftail;
unsigned long err;
/* Also check accessibility of one struct frame_tail beyond */
if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
return NULL;
if (__copy_from_user_inatomic(&buftail, tail, sizeof(buftail)))
pagefault_disable();
err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
pagefault_enable();
if (err)
return NULL;
perf_callchain_store(entry, buftail.lr);
@ -590,6 +595,10 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
}
perf_callchain_store(entry, regs->ARM_pc);
if (!current->mm)
return;
tail = (struct frame_tail __user *)regs->ARM_fp - 1;
while ((entry->nr < PERF_MAX_STACK_DEPTH) &&

View File

@ -233,14 +233,17 @@ static struct of_device_id cpu_pmu_of_device_ids[] = {
{.compatible = "arm,cortex-a7-pmu", .data = armv7_a7_pmu_init},
{.compatible = "arm,cortex-a5-pmu", .data = armv7_a5_pmu_init},
{.compatible = "arm,arm11mpcore-pmu", .data = armv6mpcore_pmu_init},
{.compatible = "arm,arm1176-pmu", .data = armv6pmu_init},
{.compatible = "arm,arm1136-pmu", .data = armv6pmu_init},
{.compatible = "arm,arm1176-pmu", .data = armv6_1176_pmu_init},
{.compatible = "arm,arm1136-pmu", .data = armv6_1136_pmu_init},
{.compatible = "qcom,krait-pmu", .data = krait_pmu_init},
{},
};
static struct platform_device_id cpu_pmu_plat_device_ids[] = {
{.name = "arm-pmu"},
{.name = "armv6-pmu"},
{.name = "armv7-pmu"},
{.name = "xscale-pmu"},
{},
};
@ -257,9 +260,13 @@ static int probe_current_pmu(struct arm_pmu *pmu)
switch (read_cpuid_part()) {
/* ARM Ltd CPUs. */
case ARM_CPU_PART_ARM1136:
ret = armv6_1136_pmu_init(pmu);
break;
case ARM_CPU_PART_ARM1156:
ret = armv6_1156_pmu_init(pmu);
break;
case ARM_CPU_PART_ARM1176:
ret = armv6pmu_init(pmu);
ret = armv6_1176_pmu_init(pmu);
break;
case ARM_CPU_PART_ARM11MPCORE:
ret = armv6mpcore_pmu_init(pmu);

View File

@ -65,13 +65,11 @@ enum armv6_counters {
* accesses/misses in hardware.
*/
static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
PERF_MAP_ALL_UNSUPPORTED,
[PERF_COUNT_HW_CPU_CYCLES] = ARMV6_PERFCTR_CPU_CYCLES,
[PERF_COUNT_HW_INSTRUCTIONS] = ARMV6_PERFCTR_INSTR_EXEC,
[PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC,
[PERF_COUNT_HW_BRANCH_MISSES] = ARMV6_PERFCTR_BR_MISPREDICT,
[PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV6_PERFCTR_IBUF_STALL,
[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV6_PERFCTR_LSU_FULL_STALL,
};
@ -79,116 +77,31 @@ static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
[C(L1D)] = {
/*
* The performance counters don't differentiate between read
* and write accesses/misses so this isn't strictly correct,
* but it's the best we can do. Writes and reads get
* combined.
*/
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
[C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
[C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(L1I)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(LL)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(DTLB)] = {
/*
* The ARM performance counters can count micro DTLB misses,
* micro ITLB misses and main TLB misses. There isn't an event
* for TLB misses, so use the micro misses here and if users
* want the main TLB misses they can use a raw counter.
*/
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(ITLB)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(BPU)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(NODE)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
PERF_CACHE_MAP_ALL_UNSUPPORTED,
/*
* The performance counters don't differentiate between read and write
* accesses/misses so this isn't strictly correct, but it's the best we
* can do. Writes and reads get combined.
*/
[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
[C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS,
[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS,
[C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS,
/*
* The ARM performance counters can count micro DTLB misses, micro ITLB
* misses and main TLB misses. There isn't an event for TLB misses, so
* use the micro misses here and if users want the main TLB misses they
* can use a raw counter.
*/
[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS,
[C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS,
};
enum armv6mpcore_perf_types {
@ -220,13 +133,11 @@ enum armv6mpcore_perf_types {
* accesses/misses in hardware.
*/
static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
PERF_MAP_ALL_UNSUPPORTED,
[PERF_COUNT_HW_CPU_CYCLES] = ARMV6MPCORE_PERFCTR_CPU_CYCLES,
[PERF_COUNT_HW_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_INSTR_EXEC,
[PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC,
[PERF_COUNT_HW_BRANCH_MISSES] = ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
[PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV6MPCORE_PERFCTR_IBUF_STALL,
[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV6MPCORE_PERFCTR_LSU_FULL_STALL,
};
@ -234,114 +145,26 @@ static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
[C(L1D)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] =
ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
[C(RESULT_MISS)] =
ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] =
ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
[C(RESULT_MISS)] =
ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(L1I)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(LL)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(DTLB)] = {
/*
* The ARM performance counters can count micro DTLB misses,
* micro ITLB misses and main TLB misses. There isn't an event
* for TLB misses, so use the micro misses here and if users
* want the main TLB misses they can use a raw counter.
*/
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(ITLB)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(BPU)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(NODE)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
PERF_CACHE_MAP_ALL_UNSUPPORTED,
[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
[C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
[C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
/*
* The ARM performance counters can count micro DTLB misses, micro ITLB
* misses and main TLB misses. There isn't an event for TLB misses, so
* use the micro misses here and if users want the main TLB misses they
* can use a raw counter.
*/
[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS,
[C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS,
};
static inline unsigned long
@ -653,9 +476,8 @@ static int armv6_map_event(struct perf_event *event)
&armv6_perf_cache_map, 0xFF);
}
static int armv6pmu_init(struct arm_pmu *cpu_pmu)
static void armv6pmu_init(struct arm_pmu *cpu_pmu)
{
cpu_pmu->name = "v6";
cpu_pmu->handle_irq = armv6pmu_handle_irq;
cpu_pmu->enable = armv6pmu_enable_event;
cpu_pmu->disable = armv6pmu_disable_event;
@ -667,7 +489,26 @@ static int armv6pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->map_event = armv6_map_event;
cpu_pmu->num_events = 3;
cpu_pmu->max_period = (1LLU << 32) - 1;
}
static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
{
armv6pmu_init(cpu_pmu);
cpu_pmu->name = "armv6_1136";
return 0;
}
static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu)
{
armv6pmu_init(cpu_pmu);
cpu_pmu->name = "armv6_1156";
return 0;
}
static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
{
armv6pmu_init(cpu_pmu);
cpu_pmu->name = "armv6_1176";
return 0;
}
@ -687,7 +528,7 @@ static int armv6mpcore_map_event(struct perf_event *event)
static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
{
cpu_pmu->name = "v6mpcore";
cpu_pmu->name = "armv6_11mpcore";
cpu_pmu->handle_irq = armv6pmu_handle_irq;
cpu_pmu->enable = armv6pmu_enable_event;
cpu_pmu->disable = armv6mpcore_pmu_disable_event;
@ -703,7 +544,17 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
return 0;
}
#else
static int armv6pmu_init(struct arm_pmu *cpu_pmu)
static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
{
return -ENODEV;
}
static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu)
{
return -ENODEV;
}
static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
{
return -ENODEV;
}

File diff suppressed because it is too large Load Diff

View File

@ -48,118 +48,31 @@ enum xscale_counters {
};
static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
PERF_MAP_ALL_UNSUPPORTED,
[PERF_COUNT_HW_CPU_CYCLES] = XSCALE_PERFCTR_CCNT,
[PERF_COUNT_HW_INSTRUCTIONS] = XSCALE_PERFCTR_INSTRUCTION,
[PERF_COUNT_HW_CACHE_REFERENCES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_CACHE_MISSES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = XSCALE_PERFCTR_BRANCH,
[PERF_COUNT_HW_BRANCH_MISSES] = XSCALE_PERFCTR_BRANCH_MISS,
[PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED,
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = XSCALE_PERFCTR_ICACHE_NO_DELIVER,
[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = HW_OP_UNSUPPORTED,
};
static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
[C(L1D)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS,
[C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS,
[C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(L1I)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = XSCALE_PERFCTR_ICACHE_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(LL)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(DTLB)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(ITLB)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(BPU)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
[C(NODE)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_WRITE)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
[C(OP_PREFETCH)] = {
[C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
PERF_CACHE_MAP_ALL_UNSUPPORTED,
[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS,
[C(L1D)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS,
[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS,
[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS,
[C(L1I)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_ICACHE_MISS,
[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS,
[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS,
[C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS,
[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS,
};
#define XSCALE_PMU_ENABLE 0x001
@ -442,7 +355,7 @@ static int xscale_map_event(struct perf_event *event)
static int xscale1pmu_init(struct arm_pmu *cpu_pmu)
{
cpu_pmu->name = "xscale1";
cpu_pmu->name = "armv5_xscale1";
cpu_pmu->handle_irq = xscale1pmu_handle_irq;
cpu_pmu->enable = xscale1pmu_enable_event;
cpu_pmu->disable = xscale1pmu_disable_event;
@ -812,7 +725,7 @@ static inline void xscale2pmu_write_counter(struct perf_event *event, u32 val)
static int xscale2pmu_init(struct arm_pmu *cpu_pmu)
{
cpu_pmu->name = "xscale2";
cpu_pmu->name = "armv5_xscale2";
cpu_pmu->handle_irq = xscale2pmu_handle_irq;
cpu_pmu->enable = xscale2pmu_enable_event;
cpu_pmu->disable = xscale2pmu_disable_event;

View File

@ -33,12 +33,14 @@ static struct op_perf_name {
char *perf_name;
char *op_name;
} op_perf_name_map[] = {
{ "xscale1", "arm/xscale1" },
{ "xscale1", "arm/xscale2" },
{ "v6", "arm/armv6" },
{ "v6mpcore", "arm/mpcore" },
{ "ARMv7 Cortex-A8", "arm/armv7" },
{ "ARMv7 Cortex-A9", "arm/armv7-ca9" },
{ "armv5_xscale1", "arm/xscale1" },
{ "armv5_xscale2", "arm/xscale2" },
{ "armv6_1136", "arm/armv6" },
{ "armv6_1156", "arm/armv6" },
{ "armv6_1176", "arm/armv6" },
{ "armv6_11mpcore", "arm/mpcore" },
{ "armv7_cortex_a8", "arm/armv7" },
{ "armv7_cortex_a9", "arm/armv7-ca9" },
};
char *op_name_from_perf_id(void)