Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index b8ccdb5..9e07f55 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,4 +1,5 @@
-obj-y += core.o
+# SPDX-License-Identifier: GPL-2.0-only
+obj-y += core.o probe.o
obj-y += amd/
obj-$(CONFIG_X86_LOCAL_APIC) += msr.o
obj-$(CONFIG_CPU_SUP_INTEL) += intel/
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index c84584b..64c3e70 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -1,12 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
#include <linux/perf_event.h>
#include <linux/export.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/jiffies.h>
#include <asm/apicdef.h>
+#include <asm/nmi.h>
#include "../perf_event.h"
+static DEFINE_PER_CPU(unsigned long, perf_nmi_tstamp);
+static unsigned long perf_nmi_window;
+
static __initconst const u64 amd_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -112,23 +119,144 @@
},
};
+static __initconst const u64 amd_hw_cache_event_ids_f17h
+ [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)] = 0x0040, /* Data Cache Accesses */
+ [C(RESULT_MISS)] = 0xc860, /* L2$ access from DC Miss */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches */
+ [C(RESULT_MISS)] = 0x0081, /* Instruction cache misses */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */
+ [C(RESULT_MISS)] = 0xf045, /* L2 DTLB misses (PT walks) */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+},
+[C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */
+ [C(RESULT_MISS)] = 0xff85, /* L1 ITLB misses, L2 misses */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+[C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr. */
+ [C(RESULT_MISS)] = 0x00c3, /* Retired Mispredicted BI */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+[C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+},
+};
+
/*
- * AMD Performance Monitor K7 and later.
+ * AMD Performance Monitor K7 and later, up to and including Family 16h:
*/
static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
{
- [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
- [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
- [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
- [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
- [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */
+};
+
+/*
+ * AMD Performance Monitor Family 17h and later:
+ */
+static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+ [PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
+ [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
+ [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
+ [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287,
+ [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187,
};
static u64 amd_pmu_event_map(int hw_event)
{
+ if (boot_cpu_data.x86 >= 0x17)
+ return amd_f17h_perfmon_event_map[hw_event];
+
return amd_perfmon_event_map[hw_event];
}
@@ -429,6 +557,131 @@
}
}
+/*
+ * When a PMC counter overflows, an NMI is used to process the event and
+ * reset the counter. NMI latency can result in the counter being updated
+ * before the NMI can run, which can result in what appear to be spurious
+ * NMIs. This function is intended to wait for the NMI to run and reset
+ * the counter to avoid possible unhandled NMI messages.
+ */
+#define OVERFLOW_WAIT_COUNT 50
+
+static void amd_pmu_wait_on_overflow(int idx)
+{
+ unsigned int i;
+ u64 counter;
+
+ /*
+ * Wait for the counter to be reset if it has overflowed. This loop
+ * should exit very, very quickly, but just in case, don't wait
+ * forever...
+ */
+ for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) {
+ rdmsrl(x86_pmu_event_addr(idx), counter);
+ if (counter & (1ULL << (x86_pmu.cntval_bits - 1)))
+ break;
+
+ /* Might be in IRQ context, so can't sleep */
+ udelay(1);
+ }
+}
+
+static void amd_pmu_disable_all(void)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int idx;
+
+ x86_pmu_disable_all();
+
+ /*
+ * This shouldn't be called from NMI context, but add a safeguard here
+ * to return, since if we're in NMI context we can't wait for an NMI
+ * to reset an overflowed counter value.
+ */
+ if (in_nmi())
+ return;
+
+ /*
+ * Check each counter for overflow and wait for it to be reset by the
+ * NMI if it has overflowed. This relies on the fact that all active
+ * counters are always enabled when this function is caled and
+ * ARCH_PERFMON_EVENTSEL_INT is always set.
+ */
+ for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+ amd_pmu_wait_on_overflow(idx);
+ }
+}
+
+static void amd_pmu_disable_event(struct perf_event *event)
+{
+ x86_pmu_disable_event(event);
+
+ /*
+ * This can be called from NMI context (via x86_pmu_stop). The counter
+ * may have overflowed, but either way, we'll never see it get reset
+ * by the NMI if we're already in the NMI. And the NMI latency support
+ * below will take care of any pending NMI that might have been
+ * generated by the overflow.
+ */
+ if (in_nmi())
+ return;
+
+ amd_pmu_wait_on_overflow(event->hw.idx);
+}
+
+/*
+ * Because of NMI latency, if multiple PMC counters are active or other sources
+ * of NMIs are received, the perf NMI handler can handle one or more overflowed
+ * PMC counters outside of the NMI associated with the PMC overflow. If the NMI
+ * doesn't arrive at the LAPIC in time to become a pending NMI, then the kernel
+ * back-to-back NMI support won't be active. This PMC handler needs to take into
+ * account that this can occur, otherwise this could result in unknown NMI
+ * messages being issued. Examples of this is PMC overflow while in the NMI
+ * handler when multiple PMCs are active or PMC overflow while handling some
+ * other source of an NMI.
+ *
+ * Attempt to mitigate this by creating an NMI window in which un-handled NMIs
+ * received during this window will be claimed. This prevents extending the
+ * window past when it is possible that latent NMIs should be received. The
+ * per-CPU perf_nmi_tstamp will be set to the window end time whenever perf has
+ * handled a counter. When an un-handled NMI is received, it will be claimed
+ * only if arriving within that window.
+ */
+static int amd_pmu_handle_irq(struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int active, handled;
+
+ /*
+ * Obtain the active count before calling x86_pmu_handle_irq() since
+ * it is possible that x86_pmu_handle_irq() may make a counter
+ * inactive (through x86_pmu_stop).
+ */
+ active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX);
+
+ /* Process any counter overflows */
+ handled = x86_pmu_handle_irq(regs);
+
+ /*
+ * If a counter was handled, record a timestamp such that un-handled
+ * NMIs will be claimed if arriving within that window.
+ */
+ if (handled) {
+ this_cpu_write(perf_nmi_tstamp,
+ jiffies + perf_nmi_window);
+
+ return handled;
+ }
+
+ if (time_after(jiffies, this_cpu_read(perf_nmi_tstamp)))
+ return NMI_DONE;
+
+ return NMI_HANDLED;
+}
+
static struct event_constraint *
amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
@@ -621,11 +874,11 @@
static __initconst const struct x86_pmu amd_pmu = {
.name = "AMD",
- .handle_irq = x86_pmu_handle_irq,
- .disable_all = x86_pmu_disable_all,
+ .handle_irq = amd_pmu_handle_irq,
+ .disable_all = amd_pmu_disable_all,
.enable_all = x86_pmu_enable_all,
.enable = x86_pmu_enable_event,
- .disable = x86_pmu_disable_event,
+ .disable = amd_pmu_disable_event,
.hw_config = amd_pmu_hw_config,
.schedule_events = x86_schedule_events,
.eventsel = MSR_K7_EVNTSEL0,
@@ -657,6 +910,9 @@
if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
return 0;
+ /* Avoid calulating the value each time in the NMI handler */
+ perf_nmi_window = msecs_to_jiffies(100);
+
switch (boot_cpu_data.x86) {
case 0x15:
pr_cont("Fam15h ");
@@ -669,6 +925,10 @@
* We fallback to using default amd_get_event_constraints.
*/
break;
+ case 0x18:
+ pr_cont("Fam18h ");
+ /* Using default amd_get_event_constraints. */
+ break;
default:
pr_err("core perfctr but no constraints; unknown hardware!\n");
return -ENODEV;
@@ -714,9 +974,10 @@
x86_pmu.amd_nb_constraints = 0;
}
- /* Events are common for all AMDs */
- memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
- sizeof(hw_cache_event_ids));
+ if (boot_cpu_data.x86 >= 0x17)
+ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids));
+ else
+ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids));
return 0;
}
@@ -728,7 +989,7 @@
cpuc->perf_ctr_virt_mask = 0;
/* Reload all events */
- x86_pmu_disable_all();
+ amd_pmu_disable_all();
x86_pmu_enable_all(0);
}
EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
@@ -746,7 +1007,7 @@
cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
/* Reload all events */
- x86_pmu_disable_all();
+ amd_pmu_disable_all();
x86_pmu_enable_all(0);
}
EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index d50bb4d..26c3635 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -253,15 +253,6 @@
return -EOPNOTSUPP;
}
-static const struct perf_event_attr ibs_notsupp = {
- .exclude_user = 1,
- .exclude_kernel = 1,
- .exclude_hv = 1,
- .exclude_idle = 1,
- .exclude_host = 1,
- .exclude_guest = 1,
-};
-
static int perf_ibs_init(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
@@ -282,9 +273,6 @@
if (event->pmu != &perf_ibs->pmu)
return -ENOENT;
- if (perf_flags(&event->attr) & perf_flags(&ibs_notsupp))
- return -EINVAL;
-
if (config & ~perf_ibs->config_mask)
return -EINVAL;
@@ -389,7 +377,8 @@
struct hw_perf_event *hwc, u64 config)
{
config &= ~perf_ibs->cnt_mask;
- wrmsrl(hwc->config_base, config);
+ if (boot_cpu_data.x86 == 0x10)
+ wrmsrl(hwc->config_base, config);
config &= ~perf_ibs->enable_mask;
wrmsrl(hwc->config_base, config);
}
@@ -537,6 +526,7 @@
.start = perf_ibs_start,
.stop = perf_ibs_stop,
.read = perf_ibs_read,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
},
.msr = MSR_AMD64_IBSFETCHCTL,
.config_mask = IBS_FETCH_CONFIG_MASK,
@@ -564,7 +554,8 @@
},
.msr = MSR_AMD64_IBSOPCTL,
.config_mask = IBS_OP_CONFIG_MASK,
- .cnt_mask = IBS_OP_MAX_CNT,
+ .cnt_mask = IBS_OP_MAX_CNT | IBS_OP_CUR_CNT |
+ IBS_OP_CUR_CNT_RAND,
.enable_mask = IBS_OP_ENABLE,
.valid_mask = IBS_OP_VAL,
.max_period = IBS_OP_MAX_CNT << 4,
@@ -625,7 +616,7 @@
if (event->attr.sample_type & PERF_SAMPLE_RAW)
offset_max = perf_ibs->offset_max;
else if (check_rip)
- offset_max = 2;
+ offset_max = 3;
else
offset_max = 1;
do {
@@ -672,10 +663,17 @@
throttle = perf_event_overflow(event, &data, ®s);
out:
- if (throttle)
+ if (throttle) {
perf_ibs_stop(event, 0);
- else
- perf_ibs_enable_event(perf_ibs, hwc, period >> 4);
+ } else {
+ period >>= 4;
+
+ if ((ibs_caps & IBS_CAPS_RDWROPCNT) &&
+ (*config & IBS_OP_CNT_CTL))
+ period |= *config & IBS_OP_CUR_CNT_RAND;
+
+ perf_ibs_enable_event(perf_ibs, hwc, period);
+ }
perf_event_update_userpage(event);
diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index 3210fee..fb61620 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2013 Advanced Micro Devices, Inc.
*
@@ -5,10 +6,6 @@
* Author: Suravee Suthikulpanit <Suraveee.Suthikulpanit@amd.com>
*
* Perf: amd_iommu - AMD IOMMU Performance Counter PMU implementation
- *
- * 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.
*/
#define pr_fmt(fmt) "perf/amd_iommu: " fmt
@@ -223,11 +220,6 @@
if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
return -EINVAL;
- /* IOMMU counters do not have usr/os/guest/host bits */
- if (event->attr.exclude_user || event->attr.exclude_kernel ||
- event->attr.exclude_host || event->attr.exclude_guest)
- return -EINVAL;
-
if (event->cpu < 0)
return -EINVAL;
@@ -398,7 +390,7 @@
return 0;
}
-const struct attribute_group *amd_iommu_attr_groups[] = {
+static const struct attribute_group *amd_iommu_attr_groups[] = {
&amd_iommu_format_group,
&amd_iommu_cpumask_group,
&amd_iommu_events_group,
@@ -414,6 +406,7 @@
.read = perf_iommu_read,
.task_ctx_nr = perf_invalid_context,
.attr_groups = amd_iommu_attr_groups,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
static __init int init_one_iommu(unsigned int idx)
diff --git a/arch/x86/events/amd/iommu.h b/arch/x86/events/amd/iommu.h
index 62e0702..0e5c036 100644
--- a/arch/x86/events/amd/iommu.h
+++ b/arch/x86/events/amd/iommu.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2013 Advanced Micro Devices, Inc.
*
* Author: Steven Kinney <Steven.Kinney@amd.com>
* Author: Suravee Suthikulpanit <Suraveee.Suthikulpanit@amd.com>
- *
- * 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 _PERF_EVENT_AMD_IOMMU_H_
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index 2aefacf..abef513 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Performance events - AMD Processor Power Reporting Mechanism
*
* Copyright (C) 2016 Advanced Micro Devices, Inc.
*
* Author: Huang Rui <ray.huang@amd.com>
- *
- * 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.
*/
#include <linux/module.h>
@@ -136,14 +133,7 @@
return -ENOENT;
/* Unsupported modes and filters. */
- if (event->attr.exclude_user ||
- event->attr.exclude_kernel ||
- event->attr.exclude_hv ||
- event->attr.exclude_idle ||
- event->attr.exclude_host ||
- event->attr.exclude_guest ||
- /* no sampling */
- event->attr.sample_period)
+ if (event->attr.sample_period)
return -EINVAL;
if (cfg != AMD_POWER_EVENTSEL_PKG)
@@ -226,6 +216,7 @@
.start = pmu_event_start,
.stop = pmu_event_stop,
.read = pmu_event_read,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
static int power_cpu_exit(unsigned int cpu)
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 8671de1..a6ea07f 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2013 Advanced Micro Devices, Inc.
*
* Author: Jacob Shin <jacob.shin@amd.com>
- *
- * 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.
*/
#include <linux/perf_event.h>
@@ -201,24 +198,26 @@
if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
return -EINVAL;
- /* NB and Last level cache counters do not have usr/os/guest/host bits */
- if (event->attr.exclude_user || event->attr.exclude_kernel ||
- event->attr.exclude_host || event->attr.exclude_guest)
- return -EINVAL;
-
/* and we do not enable counter overflow interrupts */
hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
hwc->idx = -1;
+ if (event->cpu < 0)
+ return -EINVAL;
+
/*
* SliceMask and ThreadMask need to be set for certain L3 events in
* Family 17h. For other events, the two fields do not affect the count.
*/
- if (l3_mask)
- hwc->config |= (AMD64_L3_SLICE_MASK | AMD64_L3_THREAD_MASK);
+ if (l3_mask && is_llc_event(event)) {
+ int thread = 2 * (cpu_data(event->cpu).cpu_core_id % 4);
- if (event->cpu < 0)
- return -EINVAL;
+ if (smp_num_siblings > 1)
+ thread += cpu_data(event->cpu).apicid & 1;
+
+ hwc->config |= (1ULL << (AMD64_L3_THREAD_SHIFT + thread) &
+ AMD64_L3_THREAD_MASK) | AMD64_L3_SLICE_MASK;
+ }
uncore = event_to_amd_uncore(event);
if (!uncore)
@@ -307,6 +306,7 @@
.start = amd_uncore_start,
.stop = amd_uncore_stop,
.read = amd_uncore_read,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
static struct pmu amd_llc_pmu = {
@@ -317,6 +317,7 @@
.start = amd_uncore_start,
.stop = amd_uncore_stop,
.read = amd_uncore_read,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
@@ -515,17 +516,19 @@
{
int ret = -ENODEV;
- if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+ boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
return -ENODEV;
if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
return -ENODEV;
- if (boot_cpu_data.x86 == 0x17) {
+ if (boot_cpu_data.x86 == 0x17 || boot_cpu_data.x86 == 0x18) {
/*
- * For F17h, the Northbridge counters are repurposed as Data
- * Fabric counters. Also, L3 counters are supported too. The PMUs
- * are exported based on family as either L2 or L3 and NB or DF.
+ * For F17h or F18h, the Northbridge counters are
+ * repurposed as Data Fabric counters. Also, L3
+ * counters are supported too. The PMUs are exported
+ * based on family as either L2 or L3 and NB or DF.
*/
num_counters_nb = NUM_COUNTERS_NB;
num_counters_llc = NUM_COUNTERS_L3;
@@ -557,7 +560,9 @@
if (ret)
goto fail_nb;
- pr_info("AMD NB counters detected\n");
+ pr_info("%s NB counters detected\n",
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?
+ "HYGON" : "AMD");
ret = 0;
}
@@ -571,7 +576,9 @@
if (ret)
goto fail_llc;
- pr_info("AMD LLC counters detected\n");
+ pr_info("%s LLC counters detected\n",
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?
+ "HYGON" : "AMD");
ret = 0;
}
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index c8d08da..7b21455 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -560,6 +560,21 @@
return -EINVAL;
}
+ /* sample_regs_user never support XMM registers */
+ if (unlikely(event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK))
+ return -EINVAL;
+ /*
+ * Besides the general purpose registers, XMM registers may
+ * be collected in PEBS on some platforms, e.g. Icelake
+ */
+ if (unlikely(event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK)) {
+ if (!(event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS))
+ return -EINVAL;
+
+ if (!event->attr.precise_ip)
+ return -EINVAL;
+ }
+
return x86_setup_perfctr(event);
}
@@ -661,6 +676,10 @@
return event->pmu == &pmu;
}
+struct pmu *x86_get_pmu(void)
+{
+ return &pmu;
+}
/*
* Event scheduler state:
*
@@ -849,18 +868,43 @@
struct event_constraint *c;
unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
struct perf_event *e;
- int i, wmin, wmax, unsched = 0;
+ int n0, i, wmin, wmax, unsched = 0;
struct hw_perf_event *hwc;
bitmap_zero(used_mask, X86_PMC_IDX_MAX);
+ /*
+ * Compute the number of events already present; see x86_pmu_add(),
+ * validate_group() and x86_pmu_commit_txn(). For the former two
+ * cpuc->n_events hasn't been updated yet, while for the latter
+ * cpuc->n_txn contains the number of events added in the current
+ * transaction.
+ */
+ n0 = cpuc->n_events;
+ if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
+ n0 -= cpuc->n_txn;
+
if (x86_pmu.start_scheduling)
x86_pmu.start_scheduling(cpuc);
for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
- cpuc->event_constraint[i] = NULL;
- c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
- cpuc->event_constraint[i] = c;
+ c = cpuc->event_constraint[i];
+
+ /*
+ * Previously scheduled events should have a cached constraint,
+ * while new events should not have one.
+ */
+ WARN_ON_ONCE((c && i >= n0) || (!c && i < n0));
+
+ /*
+ * Request constraints for new events; or for those events that
+ * have a dynamic constraint -- for those the constraint can
+ * change due to external factors (sibling state, allow_tfa).
+ */
+ if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) {
+ c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
+ cpuc->event_constraint[i] = c;
+ }
wmin = min(wmin, c->weight);
wmax = max(wmax, c->weight);
@@ -925,25 +969,20 @@
if (!unsched && assign) {
for (i = 0; i < n; i++) {
e = cpuc->event_list[i];
- e->hw.flags |= PERF_X86_EVENT_COMMITTED;
if (x86_pmu.commit_scheduling)
x86_pmu.commit_scheduling(cpuc, i, assign[i]);
}
} else {
- for (i = 0; i < n; i++) {
+ for (i = n0; i < n; i++) {
e = cpuc->event_list[i];
- /*
- * do not put_constraint() on comitted events,
- * because they are good to go
- */
- if ((e->hw.flags & PERF_X86_EVENT_COMMITTED))
- continue;
/*
* release events that failed scheduling
*/
if (x86_pmu.put_event_constraints)
x86_pmu.put_event_constraints(cpuc, e);
+
+ cpuc->event_constraint[i] = NULL;
}
}
@@ -966,6 +1005,27 @@
/* current number of events already accepted */
n = cpuc->n_events;
+ if (!cpuc->n_events)
+ cpuc->pebs_output = 0;
+
+ if (!cpuc->is_fake && leader->attr.precise_ip) {
+ /*
+ * For PEBS->PT, if !aux_event, the group leader (PT) went
+ * away, the group was broken down and this singleton event
+ * can't schedule any more.
+ */
+ if (is_pebs_pt(leader) && !leader->aux_event)
+ return -EINVAL;
+
+ /*
+ * pebs_output: 0: no PEBS so far, 1: PT, 2: DS
+ */
+ if (cpuc->pebs_output &&
+ cpuc->pebs_output != is_pebs_pt(leader) + 1)
+ return -EINVAL;
+
+ cpuc->pebs_output = is_pebs_pt(leader) + 1;
+ }
if (is_x86_event(leader)) {
if (n >= max_count)
@@ -1013,6 +1073,27 @@
}
}
+/**
+ * x86_perf_rdpmc_index - Return PMC counter used for event
+ * @event: the perf_event to which the PMC counter was assigned
+ *
+ * The counter assigned to this performance event may change if interrupts
+ * are enabled. This counter should thus never be used while interrupts are
+ * enabled. Before this function is used to obtain the assigned counter the
+ * event should be checked for validity using, for example,
+ * perf_event_read_local(), within the same interrupt disabled section in
+ * which this counter is planned to be used.
+ *
+ * Return: The index of the performance monitoring counter assigned to
+ * @perf_event.
+ */
+int x86_perf_rdpmc_index(struct perf_event *event)
+{
+ lockdep_assert_irqs_disabled();
+
+ return event->hw.event_base_rdpmc;
+}
+
static inline int match_prev_assignment(struct hw_perf_event *hwc,
struct cpu_hw_events *cpuc,
int i)
@@ -1176,7 +1257,7 @@
* Add a single event to the PMU.
*
* The event is added to the group of enabled events
- * but only if it can be scehduled with existing events.
+ * but only if it can be scheduled with existing events.
*/
static int x86_pmu_add(struct perf_event *event, int flags)
{
@@ -1328,8 +1409,9 @@
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
- if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+ if (test_bit(hwc->idx, cpuc->active_mask)) {
x86_pmu.disable(event);
+ __clear_bit(hwc->idx, cpuc->active_mask);
cpuc->events[hwc->idx] = NULL;
WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
hwc->state |= PERF_HES_STOPPED;
@@ -1351,11 +1433,6 @@
int i;
/*
- * event is descheduled
- */
- event->hw.flags &= ~PERF_X86_EVENT_COMMITTED;
-
- /*
* If we're called during a txn, we only need to undo x86_pmu.add.
* The events never got scheduled and ->cancel_txn will truncate
* the event_list.
@@ -1391,6 +1468,7 @@
cpuc->event_list[i-1] = cpuc->event_list[i];
cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
}
+ cpuc->event_constraint[i-1] = NULL;
--cpuc->n_events;
perf_event_update_userpage(event);
@@ -1426,16 +1504,8 @@
apic_write(APIC_LVTPC, APIC_DM_NMI);
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- if (!test_bit(idx, cpuc->active_mask)) {
- /*
- * Though we deactivated the counter some cpus
- * might still deliver spurious interrupts still
- * in flight. Catch them:
- */
- if (__test_and_clear_bit(idx, cpuc->running))
- handled++;
+ if (!test_bit(idx, cpuc->active_mask))
continue;
- }
event = cpuc->events[idx];
@@ -1564,73 +1634,11 @@
}
-static struct attribute_group x86_pmu_format_group = {
+static struct attribute_group x86_pmu_format_group __ro_after_init = {
.name = "format",
.attrs = NULL,
};
-/*
- * Remove all undefined events (x86_pmu.event_map(id) == 0)
- * out of events_attr attributes.
- */
-static void __init filter_events(struct attribute **attrs)
-{
- struct device_attribute *d;
- struct perf_pmu_events_attr *pmu_attr;
- int offset = 0;
- int i, j;
-
- for (i = 0; attrs[i]; i++) {
- d = (struct device_attribute *)attrs[i];
- pmu_attr = container_of(d, struct perf_pmu_events_attr, attr);
- /* str trumps id */
- if (pmu_attr->event_str)
- continue;
- if (x86_pmu.event_map(i + offset))
- continue;
-
- for (j = i; attrs[j]; j++)
- attrs[j] = attrs[j + 1];
-
- /* Check the shifted attr. */
- i--;
-
- /*
- * event_map() is index based, the attrs array is organized
- * by increasing event index. If we shift the events, then
- * we need to compensate for the event_map(), otherwise
- * we are looking up the wrong event in the map
- */
- offset++;
- }
-}
-
-/* Merge two pointer arrays */
-__init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
-{
- struct attribute **new;
- int j, i;
-
- for (j = 0; a[j]; j++)
- ;
- for (i = 0; b[i]; i++)
- j++;
- j++;
-
- new = kmalloc_array(j, sizeof(struct attribute *), GFP_KERNEL);
- if (!new)
- return NULL;
-
- j = 0;
- for (i = 0; a[i]; i++)
- new[j++] = a[i];
- for (i = 0; b[i]; i++)
- new[j++] = b[i];
- new[j] = NULL;
-
- return new;
-}
-
ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page)
{
struct perf_pmu_events_attr *pmu_attr = \
@@ -1695,9 +1703,24 @@
NULL,
};
-static struct attribute_group x86_pmu_events_group = {
+/*
+ * Remove all undefined events (x86_pmu.event_map(id) == 0)
+ * out of events_attr attributes.
+ */
+static umode_t
+is_visible(struct kobject *kobj, struct attribute *attr, int idx)
+{
+ struct perf_pmu_events_attr *pmu_attr;
+
+ pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
+ /* str trumps id */
+ return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0;
+}
+
+static struct attribute_group x86_pmu_events_group __ro_after_init = {
.name = "events",
.attrs = events_attr,
+ .is_visible = is_visible,
};
ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event)
@@ -1756,6 +1779,10 @@
case X86_VENDOR_AMD:
err = amd_pmu_init();
break;
+ case X86_VENDOR_HYGON:
+ err = amd_pmu_init();
+ x86_pmu.name = "HYGON";
+ break;
default:
err = -ENOTSUPP;
}
@@ -1789,37 +1816,10 @@
x86_pmu_format_group.attrs = x86_pmu.format_attrs;
- if (x86_pmu.caps_attrs) {
- struct attribute **tmp;
-
- tmp = merge_attr(x86_pmu_caps_group.attrs, x86_pmu.caps_attrs);
- if (!WARN_ON(!tmp))
- x86_pmu_caps_group.attrs = tmp;
- }
-
- if (x86_pmu.event_attrs)
- x86_pmu_events_group.attrs = x86_pmu.event_attrs;
-
if (!x86_pmu.events_sysfs_show)
x86_pmu_events_group.attrs = &empty_attrs;
- else
- filter_events(x86_pmu_events_group.attrs);
- if (x86_pmu.cpu_events) {
- struct attribute **tmp;
-
- tmp = merge_attr(x86_pmu_events_group.attrs, x86_pmu.cpu_events);
- if (!WARN_ON(!tmp))
- x86_pmu_events_group.attrs = tmp;
- }
-
- if (x86_pmu.attrs) {
- struct attribute **tmp;
-
- tmp = merge_attr(x86_pmu_attr_group.attrs, x86_pmu.attrs);
- if (!WARN_ON(!tmp))
- x86_pmu_attr_group.attrs = tmp;
- }
+ pmu.attr_update = x86_pmu.attr_update;
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
@@ -1970,7 +1970,7 @@
*/
static void free_fake_cpuc(struct cpu_hw_events *cpuc)
{
- kfree(cpuc->shared_regs);
+ intel_cpuc_finish(cpuc);
kfree(cpuc);
}
@@ -1982,14 +1982,11 @@
cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL);
if (!cpuc)
return ERR_PTR(-ENOMEM);
-
- /* only needed, if we have extra_regs */
- if (x86_pmu.extra_regs) {
- cpuc->shared_regs = allocate_shared_regs(cpu);
- if (!cpuc->shared_regs)
- goto error;
- }
cpuc->is_fake = 1;
+
+ if (intel_cpuc_prepare(cpuc, cpu))
+ goto error;
+
return cpuc;
error:
free_fake_cpuc(cpuc);
@@ -2009,7 +2006,7 @@
if (IS_ERR(fake_cpuc))
return PTR_ERR(fake_cpuc);
- c = x86_pmu.get_event_constraints(fake_cpuc, -1, event);
+ c = x86_pmu.get_event_constraints(fake_cpuc, 0, event);
if (!c || !c->weight)
ret = -EINVAL;
@@ -2057,8 +2054,7 @@
if (n < 0)
goto out;
- fake_cpuc->n_events = n;
-
+ fake_cpuc->n_events = 0;
ret = x86_pmu.schedule_events(fake_cpuc, n, NULL);
out:
@@ -2112,7 +2108,7 @@
static void refresh_pce(void *ignored)
{
- load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm));
+ load_mm_cr4_irqsoff(this_cpu_read(cpu_tlbstate.loaded_mm));
}
static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
@@ -2130,7 +2126,7 @@
* For now, this can't happen because all callers hold mmap_sem
* for write. If this changes, we'll need a different solution.
*/
- lockdep_assert_held_exclusive(&mm->mmap_sem);
+ lockdep_assert_held_write(&mm->mmap_sem);
if (atomic_inc_return(&mm->context.perf_rdpmc_allowed) == 1)
on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1);
@@ -2210,7 +2206,7 @@
NULL,
};
-static struct attribute_group x86_pmu_attr_group = {
+static struct attribute_group x86_pmu_attr_group __ro_after_init = {
.attrs = x86_pmu_attrs,
};
@@ -2228,7 +2224,7 @@
NULL
};
-static struct attribute_group x86_pmu_caps_group = {
+static struct attribute_group x86_pmu_caps_group __ro_after_init = {
.name = "caps",
.attrs = x86_pmu_caps_attrs,
};
@@ -2253,6 +2249,30 @@
x86_pmu.check_microcode();
}
+static int x86_pmu_check_period(struct perf_event *event, u64 value)
+{
+ if (x86_pmu.check_period && x86_pmu.check_period(event, value))
+ return -EINVAL;
+
+ if (value && x86_pmu.limit_period) {
+ if (x86_pmu.limit_period(event, value) > value)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int x86_pmu_aux_output_match(struct perf_event *event)
+{
+ if (!(pmu.capabilities & PERF_PMU_CAP_AUX_OUTPUT))
+ return 0;
+
+ if (x86_pmu.aux_output_match)
+ return x86_pmu.aux_output_match(event);
+
+ return 0;
+}
+
static struct pmu pmu = {
.pmu_enable = x86_pmu_enable,
.pmu_disable = x86_pmu_disable,
@@ -2277,6 +2297,9 @@
.event_idx = x86_pmu_event_idx,
.sched_task = x86_pmu_sched_task,
.task_ctx_size = sizeof(struct x86_perf_task_context),
+ .check_period = x86_pmu_check_period,
+
+ .aux_output_match = x86_pmu_aux_output_match,
};
void arch_perf_update_userpage(struct perf_event *event,
@@ -2319,6 +2342,15 @@
cyc2ns_read_end();
}
+/*
+ * Determine whether the regs were taken from an irq/exception handler rather
+ * than from perf_arch_fetch_caller_regs().
+ */
+static bool perf_hw_regs(struct pt_regs *regs)
+{
+ return regs->flags & X86_EFLAGS_FIXED;
+}
+
void
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
@@ -2333,8 +2365,12 @@
if (perf_callchain_store(entry, regs->ip))
return;
- for (unwind_start(&state, current, regs, NULL); !unwind_done(&state);
- unwind_next_frame(&state)) {
+ if (perf_hw_regs(regs))
+ unwind_start(&state, current, regs, NULL);
+ else
+ unwind_start(&state, current, NULL, (void *)regs->sp);
+
+ for (; !unwind_done(&state); unwind_next_frame(&state)) {
addr = unwind_get_return_address(&state);
if (!addr || perf_callchain_store(entry, addr))
return;
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 24ffa1e..5ee3fed 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -1,15 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* BTS PMU driver for perf
* Copyright (c) 2013-2014, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
*/
#undef DEBUG
@@ -23,7 +15,7 @@
#include <linux/device.h>
#include <linux/coredump.h>
-#include <asm-generic/sizes.h>
+#include <linux/sizes.h>
#include <asm/perf_event.h>
#include "../perf_event.h"
@@ -77,10 +69,12 @@
}
static void *
-bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite)
+bts_buffer_setup_aux(struct perf_event *event, void **pages,
+ int nr_pages, bool overwrite)
{
struct bts_buffer *buf;
struct page *page;
+ int cpu = event->cpu;
int node = (cpu == -1) ? cpu : cpu_to_node(cpu);
unsigned long offset;
size_t size = nr_pages << PAGE_SHIFT;
@@ -589,7 +583,7 @@
* the AUX buffer.
*
* However, since this driver supports per-CPU and per-task inherit
- * we cannot use the user mapping since it will not be availble
+ * we cannot use the user mapping since it will not be available
* if we're not running the owning process.
*
* With PTI we can't use the kernal map either, because its not
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 155fa4b..fcef678 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Per core/cpu state
*
@@ -17,7 +18,9 @@
#include <asm/cpufeature.h>
#include <asm/hardirq.h>
#include <asm/intel-family.h>
+#include <asm/intel_pt.h>
#include <asm/apic.h>
+#include <asm/cpu_device_id.h>
#include "../perf_event.h"
@@ -238,11 +241,40 @@
EVENT_EXTRA_END
};
+static struct event_constraint intel_icl_event_constraints[] = {
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ INTEL_UEVENT_CONSTRAINT(0x1c0, 0), /* INST_RETIRED.PREC_DIST */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf),
+ INTEL_EVENT_CONSTRAINT(0x32, 0xf), /* SW_PREFETCH_ACCESS.* */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf),
+ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff), /* CYCLE_ACTIVITY.STALLS_TOTAL */
+ INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff), /* CYCLE_ACTIVITY.STALLS_MEM_ANY */
+ INTEL_EVENT_CONSTRAINT(0xa3, 0xf), /* CYCLE_ACTIVITY.* */
+ INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf),
+ EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffbfffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffffbfffull, RSP_1),
+ INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+ INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
+ EVENT_EXTRA_END
+};
+
EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
-static struct attribute *nhm_events_attrs[] = {
+static struct attribute *nhm_mem_events_attrs[] = {
EVENT_PTR(mem_ld_nhm),
NULL,
};
@@ -278,8 +310,6 @@
"4", "2");
static struct attribute *snb_events_attrs[] = {
- EVENT_PTR(mem_ld_snb),
- EVENT_PTR(mem_st_snb),
EVENT_PTR(td_slots_issued),
EVENT_PTR(td_slots_retired),
EVENT_PTR(td_fetch_bubbles),
@@ -290,6 +320,12 @@
NULL,
};
+static struct attribute *snb_mem_events_attrs[] = {
+ EVENT_PTR(mem_ld_snb),
+ EVENT_PTR(mem_st_snb),
+ NULL,
+};
+
static struct event_constraint intel_hsw_event_constraints[] = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -1822,6 +1858,45 @@
},
};
+#define TNT_LOCAL_DRAM BIT_ULL(26)
+#define TNT_DEMAND_READ GLM_DEMAND_DATA_RD
+#define TNT_DEMAND_WRITE GLM_DEMAND_RFO
+#define TNT_LLC_ACCESS GLM_ANY_RESPONSE
+#define TNT_SNP_ANY (SNB_SNP_NOT_NEEDED|SNB_SNP_MISS| \
+ SNB_NO_FWD|SNB_SNP_FWD|SNB_HITM)
+#define TNT_LLC_MISS (TNT_SNP_ANY|SNB_NON_DRAM|TNT_LOCAL_DRAM)
+
+static __initconst const u64 tnt_hw_cache_extra_regs
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = TNT_DEMAND_READ|
+ TNT_LLC_ACCESS,
+ [C(RESULT_MISS)] = TNT_DEMAND_READ|
+ TNT_LLC_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = TNT_DEMAND_WRITE|
+ TNT_LLC_ACCESS,
+ [C(RESULT_MISS)] = TNT_DEMAND_WRITE|
+ TNT_LLC_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0x0,
+ [C(RESULT_MISS)] = 0x0,
+ },
+ },
+};
+
+static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
+ /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1),
+ EVENT_EXTRA_END
+};
+
#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */
#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */
#define KNL_MCDRAM_LOCAL BIT_ULL(21)
@@ -1926,7 +2001,7 @@
* in sequence on the same PMC or on different PMCs.
*
* In practise it appears some of these events do in fact count, and
- * we need to programm all 4 events.
+ * we need to program all 4 events.
*/
static void intel_pmu_nhm_workaround(void)
{
@@ -1995,6 +2070,51 @@
intel_pmu_enable_all(added);
}
+static void intel_set_tfa(struct cpu_hw_events *cpuc, bool on)
+{
+ u64 val = on ? MSR_TFA_RTM_FORCE_ABORT : 0;
+
+ if (cpuc->tfa_shadow != val) {
+ cpuc->tfa_shadow = val;
+ wrmsrl(MSR_TSX_FORCE_ABORT, val);
+ }
+}
+
+static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
+{
+ /*
+ * We're going to use PMC3, make sure TFA is set before we touch it.
+ */
+ if (cntr == 3)
+ intel_set_tfa(cpuc, true);
+}
+
+static void intel_tfa_pmu_enable_all(int added)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ /*
+ * If we find PMC3 is no longer used when we enable the PMU, we can
+ * clear TFA.
+ */
+ if (!test_bit(3, cpuc->active_mask))
+ intel_set_tfa(cpuc, false);
+
+ intel_pmu_enable_all(added);
+}
+
+static void enable_counter_freeze(void)
+{
+ update_debugctlmsr(get_debugctlmsr() |
+ DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI);
+}
+
+static void disable_counter_freeze(void)
+{
+ update_debugctlmsr(get_debugctlmsr() &
+ ~DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI);
+}
+
static inline u64 intel_pmu_get_status(void)
{
u64 status;
@@ -2041,15 +2161,17 @@
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
cpuc->intel_cp_status &= ~(1ull << hwc->idx);
+ if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL))
+ intel_pmu_disable_fixed(hwc);
+ else
+ x86_pmu_disable_event(event);
+
+ /*
+ * Needs to be called after x86_pmu_disable_event,
+ * so we don't trigger the event without PEBS bit set.
+ */
if (unlikely(event->attr.precise_ip))
intel_pmu_pebs_disable(event);
-
- if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
- intel_pmu_disable_fixed(hwc);
- return;
- }
-
- x86_pmu_disable_event(event);
}
static void intel_pmu_del_event(struct perf_event *event)
@@ -2095,6 +2217,11 @@
bits <<= (idx * 4);
mask = 0xfULL << (idx * 4);
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) {
+ bits |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+ mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+ }
+
rdmsrl(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
ctrl_val |= bits;
@@ -2200,59 +2327,15 @@
local_irq_restore(flags);
}
-/*
- * This handler is triggered by the local APIC, so the APIC IRQ handling
- * rules apply:
- */
-static int intel_pmu_handle_irq(struct pt_regs *regs)
+static int handle_pmi_common(struct pt_regs *regs, u64 status)
{
struct perf_sample_data data;
- struct cpu_hw_events *cpuc;
- int bit, loops;
- u64 status;
- int handled;
- int pmu_enabled;
-
- cpuc = this_cpu_ptr(&cpu_hw_events);
-
- /*
- * Save the PMU state.
- * It needs to be restored when leaving the handler.
- */
- pmu_enabled = cpuc->enabled;
- /*
- * No known reason to not always do late ACK,
- * but just in case do it opt-in.
- */
- if (!x86_pmu.late_ack)
- apic_write(APIC_LVTPC, APIC_DM_NMI);
- intel_bts_disable_local();
- cpuc->enabled = 0;
- __intel_pmu_disable_all();
- handled = intel_pmu_drain_bts_buffer();
- handled += intel_bts_interrupt();
- status = intel_pmu_get_status();
- if (!status)
- goto done;
-
- loops = 0;
-again:
- intel_pmu_lbr_read();
- intel_pmu_ack_status(status);
- if (++loops > 100) {
- static bool warned = false;
- if (!warned) {
- WARN(1, "perfevents: irq loop stuck!\n");
- perf_event_print_debug();
- warned = true;
- }
- intel_pmu_reset();
- goto done;
- }
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int bit;
+ int handled = 0;
inc_irq_stat(apic_perf_irqs);
-
/*
* Ignore a range of extra bits in status that do not indicate
* overflow by themselves.
@@ -2261,7 +2344,7 @@
GLOBAL_STATUS_ASIF |
GLOBAL_STATUS_LBRS_FROZEN);
if (!status)
- goto done;
+ return 0;
/*
* In case multiple PEBS events are sampled at the same time,
* it is possible to have GLOBAL_STATUS bit 62 set indicating
@@ -2301,7 +2384,11 @@
*/
if (__test_and_clear_bit(55, (unsigned long *)&status)) {
handled++;
- intel_pt_interrupt();
+ if (unlikely(perf_guest_cbs && perf_guest_cbs->is_in_guest() &&
+ perf_guest_cbs->handle_intel_pt_intr))
+ perf_guest_cbs->handle_intel_pt_intr();
+ else
+ intel_pt_interrupt();
}
/*
@@ -2331,6 +2418,150 @@
x86_pmu_stop(event, 0);
}
+ return handled;
+}
+
+static bool disable_counter_freezing = true;
+static int __init intel_perf_counter_freezing_setup(char *s)
+{
+ bool res;
+
+ if (kstrtobool(s, &res))
+ return -EINVAL;
+
+ disable_counter_freezing = !res;
+ return 1;
+}
+__setup("perf_v4_pmi=", intel_perf_counter_freezing_setup);
+
+/*
+ * Simplified handler for Arch Perfmon v4:
+ * - We rely on counter freezing/unfreezing to enable/disable the PMU.
+ * This is done automatically on PMU ack.
+ * - Ack the PMU only after the APIC.
+ */
+
+static int intel_pmu_handle_irq_v4(struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int handled = 0;
+ bool bts = false;
+ u64 status;
+ int pmu_enabled = cpuc->enabled;
+ int loops = 0;
+
+ /* PMU has been disabled because of counter freezing */
+ cpuc->enabled = 0;
+ if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
+ bts = true;
+ intel_bts_disable_local();
+ handled = intel_pmu_drain_bts_buffer();
+ handled += intel_bts_interrupt();
+ }
+ status = intel_pmu_get_status();
+ if (!status)
+ goto done;
+again:
+ intel_pmu_lbr_read();
+ if (++loops > 100) {
+ static bool warned;
+
+ if (!warned) {
+ WARN(1, "perfevents: irq loop stuck!\n");
+ perf_event_print_debug();
+ warned = true;
+ }
+ intel_pmu_reset();
+ goto done;
+ }
+
+
+ handled += handle_pmi_common(regs, status);
+done:
+ /* Ack the PMI in the APIC */
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
+
+ /*
+ * The counters start counting immediately while ack the status.
+ * Make it as close as possible to IRET. This avoids bogus
+ * freezing on Skylake CPUs.
+ */
+ if (status) {
+ intel_pmu_ack_status(status);
+ } else {
+ /*
+ * CPU may issues two PMIs very close to each other.
+ * When the PMI handler services the first one, the
+ * GLOBAL_STATUS is already updated to reflect both.
+ * When it IRETs, the second PMI is immediately
+ * handled and it sees clear status. At the meantime,
+ * there may be a third PMI, because the freezing bit
+ * isn't set since the ack in first PMI handlers.
+ * Double check if there is more work to be done.
+ */
+ status = intel_pmu_get_status();
+ if (status)
+ goto again;
+ }
+
+ if (bts)
+ intel_bts_enable_local();
+ cpuc->enabled = pmu_enabled;
+ return handled;
+}
+
+/*
+ * This handler is triggered by the local APIC, so the APIC IRQ handling
+ * rules apply:
+ */
+static int intel_pmu_handle_irq(struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc;
+ int loops;
+ u64 status;
+ int handled;
+ int pmu_enabled;
+
+ cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ /*
+ * Save the PMU state.
+ * It needs to be restored when leaving the handler.
+ */
+ pmu_enabled = cpuc->enabled;
+ /*
+ * No known reason to not always do late ACK,
+ * but just in case do it opt-in.
+ */
+ if (!x86_pmu.late_ack)
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
+ intel_bts_disable_local();
+ cpuc->enabled = 0;
+ __intel_pmu_disable_all();
+ handled = intel_pmu_drain_bts_buffer();
+ handled += intel_bts_interrupt();
+ status = intel_pmu_get_status();
+ if (!status)
+ goto done;
+
+ loops = 0;
+again:
+ intel_pmu_lbr_read();
+ intel_pmu_ack_status(status);
+ if (++loops > 100) {
+ static bool warned;
+
+ if (!warned) {
+ WARN(1, "perfevents: irq loop stuck!\n");
+ perf_event_print_debug();
+ warned = true;
+ }
+ intel_pmu_reset();
+ goto done;
+ }
+
+ handled += handle_pmi_common(regs, status);
+
/*
* Repeat if there is more work to be done:
*/
@@ -2538,7 +2769,7 @@
if (x86_pmu.event_constraints) {
for_each_event_constraint(c, x86_pmu.event_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
@@ -2653,13 +2884,42 @@
}
static struct event_constraint *
+dyn_constraint(struct cpu_hw_events *cpuc, struct event_constraint *c, int idx)
+{
+ WARN_ON_ONCE(!cpuc->constraint_list);
+
+ if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
+ struct event_constraint *cx;
+
+ /*
+ * grab pre-allocated constraint entry
+ */
+ cx = &cpuc->constraint_list[idx];
+
+ /*
+ * initialize dynamic constraint
+ * with static constraint
+ */
+ *cx = *c;
+
+ /*
+ * mark constraint as dynamic
+ */
+ cx->flags |= PERF_X86_EVENT_DYNAMIC;
+ c = cx;
+ }
+
+ return c;
+}
+
+static struct event_constraint *
intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
int idx, struct event_constraint *c)
{
struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
struct intel_excl_states *xlo;
int tid = cpuc->excl_thread_id;
- int is_excl, i;
+ int is_excl, i, w;
/*
* validating a group does not require
@@ -2682,27 +2942,7 @@
* only needed when constraint has not yet
* been cloned (marked dynamic)
*/
- if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
- struct event_constraint *cx;
-
- /*
- * grab pre-allocated constraint entry
- */
- cx = &cpuc->constraint_list[idx];
-
- /*
- * initialize dynamic constraint
- * with static constraint
- */
- *cx = *c;
-
- /*
- * mark constraint as dynamic, so we
- * can free it later on
- */
- cx->flags |= PERF_X86_EVENT_DYNAMIC;
- c = cx;
- }
+ c = dyn_constraint(cpuc, c, idx);
/*
* From here on, the constraint is dynamic.
@@ -2735,36 +2975,40 @@
* SHARED : sibling counter measuring non-exclusive event
* UNUSED : sibling counter unused
*/
+ w = c->weight;
for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
/*
* exclusive event in sibling counter
* our corresponding counter cannot be used
* regardless of our event
*/
- if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+ if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) {
__clear_bit(i, c->idxmsk);
+ w--;
+ continue;
+ }
/*
* if measuring an exclusive event, sibling
* measuring non-exclusive, then counter cannot
* be used
*/
- if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+ if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) {
__clear_bit(i, c->idxmsk);
+ w--;
+ continue;
+ }
}
/*
- * recompute actual bit weight for scheduling algorithm
- */
- c->weight = hweight64(c->idxmsk64);
-
- /*
* if we return an empty mask, then switch
* back to static empty constraint to avoid
* the cost of freeing later on
*/
- if (c->weight == 0)
+ if (!w)
c = &emptyconstraint;
+ c->weight = w;
+
return c;
}
@@ -2772,11 +3016,9 @@
intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
{
- struct event_constraint *c1 = NULL;
- struct event_constraint *c2;
+ struct event_constraint *c1, *c2;
- if (idx >= 0) /* fake does < 0 */
- c1 = cpuc->event_constraint[idx];
+ c1 = cpuc->event_constraint[idx];
/*
* first time only
@@ -2784,7 +3026,8 @@
* - dynamic constraint: handled by intel_get_excl_constraints()
*/
c2 = __intel_get_event_constraints(cpuc, idx, event);
- if (c1 && (c1->flags & PERF_X86_EVENT_DYNAMIC)) {
+ if (c1) {
+ WARN_ON_ONCE(!(c1->flags & PERF_X86_EVENT_DYNAMIC));
bitmap_copy(c1->idxmsk, c2->idxmsk, X86_PMC_IDX_MAX);
c1->weight = c2->weight;
c2 = c1;
@@ -2972,7 +3215,7 @@
flags &= ~PERF_SAMPLE_TIME;
if (!event->attr.exclude_kernel)
flags &= ~PERF_SAMPLE_REGS_USER;
- if (event->attr.sample_regs_user & ~PEBS_REGS)
+ if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
return flags;
}
@@ -3026,7 +3269,7 @@
return ret;
if (event->attr.precise_ip) {
- if (!event->attr.freq) {
+ if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
if (!(event->attr.sample_type &
~intel_pmu_large_pebs_flags(event)))
@@ -3056,6 +3299,13 @@
}
}
+ if (event->attr.aux_output) {
+ if (!event->attr.precise_ip)
+ return -EINVAL;
+
+ event->hw.flags |= PERF_X86_EVENT_PEBS_VIA_PT;
+ }
+
if (event->attr.type != PERF_TYPE_RAW)
return 0;
@@ -3090,16 +3340,27 @@
arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask;
- /*
- * If PMU counter has PEBS enabled it is not enough to disable counter
- * on a guest entry since PEBS memory write can overshoot guest entry
- * and corrupt guest memory. Disabling PEBS solves the problem.
- */
- arr[1].msr = MSR_IA32_PEBS_ENABLE;
- arr[1].host = cpuc->pebs_enabled;
- arr[1].guest = 0;
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+ arr[0].guest &= ~cpuc->pebs_enabled;
+ else
+ arr[0].guest &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+ *nr = 1;
- *nr = 2;
+ if (x86_pmu.pebs && x86_pmu.pebs_no_isolation) {
+ /*
+ * If PMU counter has PEBS enabled it is not enough to
+ * disable counter on a guest entry since PEBS memory
+ * write can overshoot guest entry and corrupt guest
+ * memory. Disabling PEBS solves the problem.
+ *
+ * Don't do this if the CPU already enforces it.
+ */
+ arr[1].msr = MSR_IA32_PEBS_ENABLE;
+ arr[1].host = cpuc->pebs_enabled;
+ arr[1].guest = 0;
+ *nr = 2;
+ }
+
return arr;
}
@@ -3196,6 +3457,12 @@
static struct event_constraint counter2_constraint =
EVENT_CONSTRAINT(0, 0x4, 0);
+static struct event_constraint fixed0_constraint =
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0);
+
+static struct event_constraint fixed0_counter0_constraint =
+ INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000001ULL);
+
static struct event_constraint *
hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
@@ -3215,6 +3482,21 @@
}
static struct event_constraint *
+icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+ struct perf_event *event)
+{
+ /*
+ * Fixed counter 0 has less skid.
+ * Force instruction:ppp in Fixed counter 0
+ */
+ if ((event->attr.precise_ip == 3) &&
+ constraint_match(&fixed0_constraint, event->hw.config))
+ return &fixed0_constraint;
+
+ return hsw_get_event_constraints(cpuc, idx, event);
+}
+
+static struct event_constraint *
glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
{
@@ -3229,6 +3511,49 @@
return c;
}
+static struct event_constraint *
+tnt_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+ struct perf_event *event)
+{
+ struct event_constraint *c;
+
+ /*
+ * :ppp means to do reduced skid PEBS,
+ * which is available on PMC0 and fixed counter 0.
+ */
+ if (event->attr.precise_ip == 3) {
+ /* Force instruction:ppp on PMC0 and Fixed counter 0 */
+ if (constraint_match(&fixed0_constraint, event->hw.config))
+ return &fixed0_counter0_constraint;
+
+ return &counter0_constraint;
+ }
+
+ c = intel_get_event_constraints(cpuc, idx, event);
+
+ return c;
+}
+
+static bool allow_tsx_force_abort = true;
+
+static struct event_constraint *
+tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+ struct perf_event *event)
+{
+ struct event_constraint *c = hsw_get_event_constraints(cpuc, idx, event);
+
+ /*
+ * Without TFA we must not use PMC3.
+ */
+ if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) {
+ c = dyn_constraint(cpuc, c, idx);
+ c->idxmsk64 &= ~(1ULL << 3);
+ c->weight--;
+ }
+
+ return c;
+}
+
/*
* Broadwell:
*
@@ -3255,6 +3580,11 @@
return left;
}
+static u64 nhm_limit_period(struct perf_event *event, u64 left)
+{
+ return max(left, 32ULL);
+}
+
PMU_FORMAT_ATTR(event, "config:0-7" );
PMU_FORMAT_ATTR(umask, "config:8-15" );
PMU_FORMAT_ATTR(edge, "config:18" );
@@ -3282,7 +3612,7 @@
return x86_event_sysfs_show(page, config, event);
}
-struct intel_shared_regs *allocate_shared_regs(int cpu)
+static struct intel_shared_regs *allocate_shared_regs(int cpu)
{
struct intel_shared_regs *regs;
int i;
@@ -3314,9 +3644,10 @@
return c;
}
-static int intel_pmu_cpu_prepare(int cpu)
+
+int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
{
- struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+ cpuc->pebs_record_size = x86_pmu.pebs_record_size;
if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
cpuc->shared_regs = allocate_shared_regs(cpu);
@@ -3324,13 +3655,15 @@
goto err;
}
- if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
+ if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA)) {
size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);
- cpuc->constraint_list = kzalloc(sz, GFP_KERNEL);
+ cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
if (!cpuc->constraint_list)
goto err_shared_regs;
+ }
+ if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
cpuc->excl_cntrs = allocate_excl_cntrs(cpu);
if (!cpuc->excl_cntrs)
goto err_constraint_list;
@@ -3352,6 +3685,11 @@
return -ENOMEM;
}
+static int intel_pmu_cpu_prepare(int cpu)
+{
+ return intel_cpuc_prepare(&per_cpu(cpu_hw_events, cpu), cpu);
+}
+
static void flip_smm_bit(void *data)
{
unsigned long set = *(unsigned long *)data;
@@ -3379,9 +3717,18 @@
cpuc->lbr_sel = NULL;
+ if (x86_pmu.flags & PMU_FL_TFA) {
+ WARN_ON_ONCE(cpuc->tfa_shadow);
+ cpuc->tfa_shadow = ~0ULL;
+ intel_set_tfa(cpuc, false);
+ }
+
if (x86_pmu.version > 1)
flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
+ if (x86_pmu.counter_freezing)
+ enable_counter_freeze();
+
if (!cpuc->shared_regs)
return;
@@ -3423,9 +3770,8 @@
}
}
-static void free_excl_cntrs(int cpu)
+static void free_excl_cntrs(struct cpu_hw_events *cpuc)
{
- struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
struct intel_excl_cntrs *c;
c = cpuc->excl_cntrs;
@@ -3433,14 +3779,22 @@
if (c->core_id == -1 || --c->refcnt == 0)
kfree(c);
cpuc->excl_cntrs = NULL;
- kfree(cpuc->constraint_list);
- cpuc->constraint_list = NULL;
}
+
+ kfree(cpuc->constraint_list);
+ cpuc->constraint_list = NULL;
}
static void intel_pmu_cpu_dying(int cpu)
{
- struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+ fini_debug_store_on_cpu(cpu);
+
+ if (x86_pmu.counter_freezing)
+ disable_counter_freeze();
+}
+
+void intel_cpuc_finish(struct cpu_hw_events *cpuc)
+{
struct intel_shared_regs *pc;
pc = cpuc->shared_regs;
@@ -3450,9 +3804,12 @@
cpuc->shared_regs = NULL;
}
- free_excl_cntrs(cpu);
+ free_excl_cntrs(cpuc);
+}
- fini_debug_store_on_cpu(cpu);
+static void intel_pmu_cpu_dead(int cpu)
+{
+ intel_cpuc_finish(&per_cpu(cpu_hw_events, cpu));
}
static void intel_pmu_sched_task(struct perf_event_context *ctx,
@@ -3462,6 +3819,19 @@
intel_pmu_lbr_sched_task(ctx, sched_in);
}
+static int intel_pmu_check_period(struct perf_event *event, u64 value)
+{
+ return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
+}
+
+static int intel_pmu_aux_output_match(struct perf_event *event)
+{
+ if (!x86_pmu.intel_cap.pebs_output_pt_available)
+ return 0;
+
+ return is_intel_pt_event(event);
+}
+
PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -3541,9 +3911,10 @@
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
-};
+ .cpu_dead = intel_pmu_cpu_dead,
-static struct attribute *intel_pmu_attrs[];
+ .check_period = intel_pmu_check_period,
+};
static __initconst const struct x86_pmu intel_pmu = {
.name = "Intel",
@@ -3576,13 +3947,17 @@
.format_attrs = intel_arch3_formats_attr,
.events_sysfs_show = intel_event_sysfs_show,
- .attrs = intel_pmu_attrs,
-
.cpu_prepare = intel_pmu_cpu_prepare,
.cpu_starting = intel_pmu_cpu_starting,
.cpu_dying = intel_pmu_cpu_dying,
+ .cpu_dead = intel_pmu_cpu_dead,
+
.guest_get_msrs = intel_guest_get_msrs,
.sched_task = intel_pmu_sched_task,
+
+ .check_period = intel_pmu_check_period,
+
+ .aux_output_match = intel_pmu_aux_output_match,
};
static __init void intel_clovertown_quirk(void)
@@ -3611,36 +3986,62 @@
x86_pmu.pebs_constraints = NULL;
}
-static int intel_snb_pebs_broken(int cpu)
+static const struct x86_cpu_desc isolation_ucodes[] = {
+ INTEL_CPU_DESC(INTEL_FAM6_HASWELL, 3, 0x0000001f),
+ INTEL_CPU_DESC(INTEL_FAM6_HASWELL_L, 1, 0x0000001e),
+ INTEL_CPU_DESC(INTEL_FAM6_HASWELL_G, 1, 0x00000015),
+ INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X, 2, 0x00000037),
+ INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X, 4, 0x0000000a),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL, 4, 0x00000023),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_G, 1, 0x00000014),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 2, 0x00000010),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 3, 0x07000009),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 4, 0x0f000009),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 5, 0x0e000002),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X, 2, 0x0b000014),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 3, 0x00000021),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 4, 0x00000000),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 9, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 10, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 11, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_L, 12, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 10, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 11, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 12, 0x0000004e),
+ INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 13, 0x0000004e),
+ {}
+};
+
+static void intel_check_pebs_isolation(void)
{
- u32 rev = UINT_MAX; /* default to broken for unknown models */
+ x86_pmu.pebs_no_isolation = !x86_cpu_has_min_microcode_rev(isolation_ucodes);
+}
- switch (cpu_data(cpu).x86_model) {
- case INTEL_FAM6_SANDYBRIDGE:
- rev = 0x28;
- break;
+static __init void intel_pebs_isolation_quirk(void)
+{
+ WARN_ON_ONCE(x86_pmu.check_microcode);
+ x86_pmu.check_microcode = intel_check_pebs_isolation;
+ intel_check_pebs_isolation();
+}
- case INTEL_FAM6_SANDYBRIDGE_X:
- switch (cpu_data(cpu).x86_stepping) {
- case 6: rev = 0x618; break;
- case 7: rev = 0x70c; break;
- }
- }
+static const struct x86_cpu_desc pebs_ucodes[] = {
+ INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE, 7, 0x00000028),
+ INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X, 6, 0x00000618),
+ INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X, 7, 0x0000070c),
+ {}
+};
- return (cpu_data(cpu).microcode < rev);
+static bool intel_snb_pebs_broken(void)
+{
+ return !x86_cpu_has_min_microcode_rev(pebs_ucodes);
}
static void intel_snb_check_microcode(void)
{
- int pebs_broken = 0;
- int cpu;
-
- for_each_online_cpu(cpu) {
- if ((pebs_broken = intel_snb_pebs_broken(cpu)))
- break;
- }
-
- if (pebs_broken == x86_pmu.pebs_broken)
+ if (intel_snb_pebs_broken() == x86_pmu.pebs_broken)
return;
/*
@@ -3671,6 +4072,13 @@
u64 val_old, val_new, val_tmp;
/*
+ * Disable the check for real HW, so we don't
+ * mess with potentionaly enabled registers:
+ */
+ if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ return true;
+
+ /*
* Read the current value, change it and read it back to see if it
* matches, this is needed to detect certain hardware emulators
* (qemu/kvm) that don't trap on the MSR access and always return 0s.
@@ -3757,6 +4165,39 @@
}
}
+static const struct x86_cpu_desc counter_freezing_ucodes[] = {
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 2, 0x0000000e),
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 9, 0x0000002e),
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT, 10, 0x00000008),
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_D, 1, 0x00000028),
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS, 1, 0x00000028),
+ INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS, 8, 0x00000006),
+ {}
+};
+
+static bool intel_counter_freezing_broken(void)
+{
+ return !x86_cpu_has_min_microcode_rev(counter_freezing_ucodes);
+}
+
+static __init void intel_counter_freezing_quirk(void)
+{
+ /* Check if it's already disabled */
+ if (disable_counter_freezing)
+ return;
+
+ /*
+ * If the system starts with the wrong ucode, leave the
+ * counter-freezing feature permanently disabled.
+ */
+ if (intel_counter_freezing_broken()) {
+ pr_info("PMU counter freezing disabled due to CPU errata,"
+ "please upgrade microcode\n");
+ x86_pmu.counter_freezing = false;
+ x86_pmu.handle_irq = intel_pmu_handle_irq;
+ }
+}
+
/*
* enable software workaround for errata:
* SNB: BJ122
@@ -3796,8 +4237,6 @@
EVENT_ATTR_STR(cycles-ct, cycles_ct, "event=0x3c,in_tx=1,in_tx_cp=1");
static struct attribute *hsw_events_attrs[] = {
- EVENT_PTR(mem_ld_hsw),
- EVENT_PTR(mem_st_hsw),
EVENT_PTR(td_slots_issued),
EVENT_PTR(td_slots_retired),
EVENT_PTR(td_fetch_bubbles),
@@ -3808,6 +4247,12 @@
NULL
};
+static struct attribute *hsw_mem_events_attrs[] = {
+ EVENT_PTR(mem_ld_hsw),
+ EVENT_PTR(mem_st_hsw),
+ NULL,
+};
+
static struct attribute *hsw_tsx_events_attrs[] = {
EVENT_PTR(tx_start),
EVENT_PTR(tx_commit),
@@ -3824,12 +4269,34 @@
NULL
};
-static __init struct attribute **get_hsw_events_attrs(void)
-{
- return boot_cpu_has(X86_FEATURE_RTM) ?
- merge_attr(hsw_events_attrs, hsw_tsx_events_attrs) :
- hsw_events_attrs;
-}
+EVENT_ATTR_STR(tx-capacity-read, tx_capacity_read, "event=0x54,umask=0x80");
+EVENT_ATTR_STR(tx-capacity-write, tx_capacity_write, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(el-capacity-read, el_capacity_read, "event=0x54,umask=0x80");
+EVENT_ATTR_STR(el-capacity-write, el_capacity_write, "event=0x54,umask=0x2");
+
+static struct attribute *icl_events_attrs[] = {
+ EVENT_PTR(mem_ld_hsw),
+ EVENT_PTR(mem_st_hsw),
+ NULL,
+};
+
+static struct attribute *icl_tsx_events_attrs[] = {
+ EVENT_PTR(tx_start),
+ EVENT_PTR(tx_abort),
+ EVENT_PTR(tx_commit),
+ EVENT_PTR(tx_capacity_read),
+ EVENT_PTR(tx_capacity_write),
+ EVENT_PTR(tx_conflict),
+ EVENT_PTR(el_start),
+ EVENT_PTR(el_abort),
+ EVENT_PTR(el_commit),
+ EVENT_PTR(el_capacity_read),
+ EVENT_PTR(el_capacity_write),
+ EVENT_PTR(el_conflict),
+ EVENT_PTR(cycles_t),
+ EVENT_PTR(cycles_ct),
+ NULL,
+};
static ssize_t freeze_on_smi_show(struct device *cdev,
struct device_attribute *attr,
@@ -3870,6 +4337,50 @@
return count;
}
+static void update_tfa_sched(void *ignored)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ /*
+ * check if PMC3 is used
+ * and if so force schedule out for all event types all contexts
+ */
+ if (test_bit(3, cpuc->active_mask))
+ perf_pmu_resched(x86_get_pmu());
+}
+
+static ssize_t show_sysctl_tfa(struct device *cdev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, 40, "%d\n", allow_tsx_force_abort);
+}
+
+static ssize_t set_sysctl_tfa(struct device *cdev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ bool val;
+ ssize_t ret;
+
+ ret = kstrtobool(buf, &val);
+ if (ret)
+ return ret;
+
+ /* no change */
+ if (val == allow_tsx_force_abort)
+ return count;
+
+ allow_tsx_force_abort = val;
+
+ get_online_cpus();
+ on_each_cpu(update_tfa_sched, NULL, 1);
+ put_online_cpus();
+
+ return count;
+}
+
+
static DEVICE_ATTR_RW(freeze_on_smi);
static ssize_t branches_show(struct device *cdev,
@@ -3902,21 +4413,117 @@
NULL
};
+static DEVICE_ATTR(allow_tsx_force_abort, 0644,
+ show_sysctl_tfa,
+ set_sysctl_tfa);
+
static struct attribute *intel_pmu_attrs[] = {
&dev_attr_freeze_on_smi.attr,
+ &dev_attr_allow_tsx_force_abort.attr,
NULL,
};
+static umode_t
+tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return boot_cpu_has(X86_FEATURE_RTM) ? attr->mode : 0;
+}
+
+static umode_t
+pebs_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.pebs ? attr->mode : 0;
+}
+
+static umode_t
+lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.lbr_nr ? attr->mode : 0;
+}
+
+static umode_t
+exra_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return x86_pmu.version >= 2 ? attr->mode : 0;
+}
+
+static umode_t
+default_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ if (attr == &dev_attr_allow_tsx_force_abort.attr)
+ return x86_pmu.flags & PMU_FL_TFA ? attr->mode : 0;
+
+ return attr->mode;
+}
+
+static struct attribute_group group_events_td = {
+ .name = "events",
+};
+
+static struct attribute_group group_events_mem = {
+ .name = "events",
+ .is_visible = pebs_is_visible,
+};
+
+static struct attribute_group group_events_tsx = {
+ .name = "events",
+ .is_visible = tsx_is_visible,
+};
+
+static struct attribute_group group_caps_gen = {
+ .name = "caps",
+ .attrs = intel_pmu_caps_attrs,
+};
+
+static struct attribute_group group_caps_lbr = {
+ .name = "caps",
+ .attrs = lbr_attrs,
+ .is_visible = lbr_is_visible,
+};
+
+static struct attribute_group group_format_extra = {
+ .name = "format",
+ .is_visible = exra_is_visible,
+};
+
+static struct attribute_group group_format_extra_skl = {
+ .name = "format",
+ .is_visible = exra_is_visible,
+};
+
+static struct attribute_group group_default = {
+ .attrs = intel_pmu_attrs,
+ .is_visible = default_is_visible,
+};
+
+static const struct attribute_group *attr_update[] = {
+ &group_events_td,
+ &group_events_mem,
+ &group_events_tsx,
+ &group_caps_gen,
+ &group_caps_lbr,
+ &group_format_extra,
+ &group_format_extra_skl,
+ &group_default,
+ NULL,
+};
+
+static struct attribute *empty_attrs;
+
__init int intel_pmu_init(void)
{
- struct attribute **extra_attr = NULL;
- struct attribute **to_free = NULL;
+ struct attribute **extra_skl_attr = &empty_attrs;
+ struct attribute **extra_attr = &empty_attrs;
+ struct attribute **td_attr = &empty_attrs;
+ struct attribute **mem_attr = &empty_attrs;
+ struct attribute **tsx_attr = &empty_attrs;
union cpuid10_edx edx;
union cpuid10_eax eax;
union cpuid10_ebx ebx;
struct event_constraint *c;
unsigned int unused;
struct extra_reg *er;
+ bool pmem = false;
int version, i;
char *name;
@@ -3967,6 +4574,9 @@
max((int)edx.split.num_counters_fixed, assume);
}
+ if (version >= 4)
+ x86_pmu.counter_freezing = !disable_counter_freezing;
+
if (boot_cpu_has(X86_FEATURE_PDCM)) {
u64 capabilities;
@@ -3989,6 +4599,8 @@
case INTEL_FAM6_CORE2_MEROM:
x86_add_quirk(intel_clovertown_quirk);
+ /* fall through */
+
case INTEL_FAM6_CORE2_MEROM_L:
case INTEL_FAM6_CORE2_PENRYN:
case INTEL_FAM6_CORE2_DUNNINGTON:
@@ -4017,8 +4629,9 @@
x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints;
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
x86_pmu.extra_regs = intel_nehalem_extra_regs;
+ x86_pmu.limit_period = nhm_limit_period;
- x86_pmu.cpu_events = nhm_events_attrs;
+ mem_attr = nhm_mem_events_attrs;
/* UOPS_ISSUED.STALLED_CYCLES */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4036,11 +4649,11 @@
name = "nehalem";
break;
- case INTEL_FAM6_ATOM_PINEVIEW:
- case INTEL_FAM6_ATOM_LINCROFT:
- case INTEL_FAM6_ATOM_PENWELL:
- case INTEL_FAM6_ATOM_CLOVERVIEW:
- case INTEL_FAM6_ATOM_CEDARVIEW:
+ case INTEL_FAM6_ATOM_BONNELL:
+ case INTEL_FAM6_ATOM_BONNELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL:
+ case INTEL_FAM6_ATOM_SALTWELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL_TABLET:
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -4053,9 +4666,11 @@
name = "bonnell";
break;
- case INTEL_FAM6_ATOM_SILVERMONT1:
- case INTEL_FAM6_ATOM_SILVERMONT2:
+ case INTEL_FAM6_ATOM_SILVERMONT:
+ case INTEL_FAM6_ATOM_SILVERMONT_D:
+ case INTEL_FAM6_ATOM_SILVERMONT_MID:
case INTEL_FAM6_ATOM_AIRMONT:
+ case INTEL_FAM6_ATOM_AIRMONT_MID:
memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -4067,14 +4682,15 @@
x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
x86_pmu.extra_regs = intel_slm_extra_regs;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.cpu_events = slm_events_attrs;
+ td_attr = slm_events_attrs;
extra_attr = slm_format_attr;
pr_cont("Silvermont events, ");
name = "silvermont";
break;
case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_DENVERTON:
+ case INTEL_FAM6_ATOM_GOLDMONT_D:
+ x86_add_quirk(intel_counter_freezing_quirk);
memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
@@ -4094,13 +4710,14 @@
x86_pmu.pebs_prec_dist = true;
x86_pmu.lbr_pt_coexist = true;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.cpu_events = glm_events_attrs;
+ td_attr = glm_events_attrs;
extra_attr = slm_format_attr;
pr_cont("Goldmont events, ");
name = "goldmont";
break;
- case INTEL_FAM6_ATOM_GEMINI_LAKE:
+ case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ x86_add_quirk(intel_counter_freezing_quirk);
memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
@@ -4120,7 +4737,7 @@
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_PEBS_ALL;
x86_pmu.get_event_constraints = glp_get_event_constraints;
- x86_pmu.cpu_events = glm_events_attrs;
+ td_attr = glm_events_attrs;
/* Goldmont Plus has 4-wide pipeline */
event_attr_td_total_slots_scale_glm.event_str = "4";
extra_attr = slm_format_attr;
@@ -4128,6 +4745,32 @@
name = "goldmont_plus";
break;
+ case INTEL_FAM6_ATOM_TREMONT_D:
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
+ hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+
+ intel_pmu_lbr_init_skl();
+
+ x86_pmu.event_constraints = intel_slm_event_constraints;
+ x86_pmu.extra_regs = intel_tnt_extra_regs;
+ /*
+ * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
+ * for precise cycles.
+ */
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.lbr_pt_coexist = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.get_event_constraints = tnt_get_event_constraints;
+ extra_attr = slm_format_attr;
+ pr_cont("Tremont events, ");
+ name = "Tremont";
+ break;
+
case INTEL_FAM6_WESTMERE:
case INTEL_FAM6_WESTMERE_EP:
case INTEL_FAM6_WESTMERE_EX:
@@ -4144,7 +4787,7 @@
x86_pmu.extra_regs = intel_westmere_extra_regs;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.cpu_events = nhm_events_attrs;
+ mem_attr = nhm_mem_events_attrs;
/* UOPS_ISSUED.STALLED_CYCLES */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4183,7 +4826,8 @@
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.cpu_events = snb_events_attrs;
+ td_attr = snb_events_attrs;
+ mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4223,7 +4867,8 @@
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.cpu_events = snb_events_attrs;
+ td_attr = snb_events_attrs;
+ mem_attr = snb_mem_events_attrs;
/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
@@ -4236,11 +4881,12 @@
break;
- case INTEL_FAM6_HASWELL_CORE:
+ case INTEL_FAM6_HASWELL:
case INTEL_FAM6_HASWELL_X:
- case INTEL_FAM6_HASWELL_ULT:
- case INTEL_FAM6_HASWELL_GT3E:
+ case INTEL_FAM6_HASWELL_L:
+ case INTEL_FAM6_HASWELL_G:
x86_add_quirk(intel_ht_bug);
+ x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4258,18 +4904,21 @@
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = get_hsw_events_attrs();
x86_pmu.lbr_double_abort = true;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
+ td_attr = hsw_events_attrs;
+ mem_attr = hsw_mem_events_attrs;
+ tsx_attr = hsw_tsx_events_attrs;
pr_cont("Haswell events, ");
name = "haswell";
break;
- case INTEL_FAM6_BROADWELL_CORE:
- case INTEL_FAM6_BROADWELL_XEON_D:
- case INTEL_FAM6_BROADWELL_GT3E:
+ case INTEL_FAM6_BROADWELL:
+ case INTEL_FAM6_BROADWELL_D:
+ case INTEL_FAM6_BROADWELL_G:
case INTEL_FAM6_BROADWELL_X:
+ x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4297,10 +4946,12 @@
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
- x86_pmu.cpu_events = get_hsw_events_attrs();
x86_pmu.limit_period = bdw_limit_period;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
+ td_attr = hsw_events_attrs;
+ mem_attr = hsw_mem_events_attrs;
+ tsx_attr = hsw_tsx_events_attrs;
pr_cont("Broadwell events, ");
name = "broadwell";
break;
@@ -4325,11 +4976,16 @@
name = "knights-landing";
break;
- case INTEL_FAM6_SKYLAKE_MOBILE:
- case INTEL_FAM6_SKYLAKE_DESKTOP:
case INTEL_FAM6_SKYLAKE_X:
- case INTEL_FAM6_KABYLAKE_MOBILE:
- case INTEL_FAM6_KABYLAKE_DESKTOP:
+ pmem = true;
+ /* fall through */
+ case INTEL_FAM6_SKYLAKE_L:
+ case INTEL_FAM6_SKYLAKE:
+ case INTEL_FAM6_KABYLAKE_L:
+ case INTEL_FAM6_KABYLAKE:
+ case INTEL_FAM6_COMETLAKE_L:
+ case INTEL_FAM6_COMETLAKE:
+ x86_add_quirk(intel_pebs_isolation_quirk);
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4354,15 +5010,59 @@
x86_pmu.get_event_constraints = hsw_get_event_constraints;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
- extra_attr = merge_attr(extra_attr, skl_format_attr);
- to_free = extra_attr;
- x86_pmu.cpu_events = get_hsw_events_attrs();
- intel_pmu_pebs_data_source_skl(
- boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
+ extra_skl_attr = skl_format_attr;
+ td_attr = hsw_events_attrs;
+ mem_attr = hsw_mem_events_attrs;
+ tsx_attr = hsw_tsx_events_attrs;
+ intel_pmu_pebs_data_source_skl(pmem);
+
+ if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
+ x86_pmu.flags |= PMU_FL_TFA;
+ x86_pmu.get_event_constraints = tfa_get_event_constraints;
+ x86_pmu.enable_all = intel_tfa_pmu_enable_all;
+ x86_pmu.commit_scheduling = intel_tfa_commit_scheduling;
+ }
+
pr_cont("Skylake events, ");
name = "skylake";
break;
+ case INTEL_FAM6_ICELAKE_X:
+ case INTEL_FAM6_ICELAKE_D:
+ pmem = true;
+ /* fall through */
+ case INTEL_FAM6_ICELAKE_L:
+ case INTEL_FAM6_ICELAKE:
+ case INTEL_FAM6_TIGERLAKE_L:
+ case INTEL_FAM6_TIGERLAKE:
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+ hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+ intel_pmu_lbr_init_skl();
+
+ x86_pmu.event_constraints = intel_icl_event_constraints;
+ x86_pmu.pebs_constraints = intel_icl_pebs_event_constraints;
+ x86_pmu.extra_regs = intel_icl_extra_regs;
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+
+ x86_pmu.hw_config = hsw_hw_config;
+ x86_pmu.get_event_constraints = icl_get_event_constraints;
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ hsw_format_attr : nhm_format_attr;
+ extra_skl_attr = skl_format_attr;
+ mem_attr = icl_events_attrs;
+ tsx_attr = icl_tsx_events_attrs;
+ x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
+ x86_pmu.lbr_pt_coexist = true;
+ intel_pmu_pebs_data_source_skl(pmem);
+ pr_cont("Icelake events, ");
+ name = "icelake";
+ break;
+
default:
switch (x86_pmu.version) {
case 1:
@@ -4381,13 +5081,16 @@
}
}
- snprintf(pmu_name_str, sizeof pmu_name_str, "%s", name);
+ snprintf(pmu_name_str, sizeof(pmu_name_str), "%s", name);
- if (version >= 2 && extra_attr) {
- x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
- extra_attr);
- WARN_ON(!x86_pmu.format_attrs);
- }
+
+ group_events_td.attrs = td_attr;
+ group_events_mem.attrs = mem_attr;
+ group_events_tsx.attrs = tsx_attr;
+ group_format_extra.attrs = extra_attr;
+ group_format_extra_skl.attrs = extra_skl_attr;
+
+ x86_pmu.attr_update = attr_update;
if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) {
WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
@@ -4435,12 +5138,8 @@
x86_pmu.lbr_nr = 0;
}
- x86_pmu.caps_attrs = intel_pmu_caps_attrs;
-
- if (x86_pmu.lbr_nr) {
- x86_pmu.caps_attrs = merge_attr(x86_pmu.caps_attrs, lbr_attrs);
+ if (x86_pmu.lbr_nr)
pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr);
- }
/*
* Access extra MSR may cause #GP under certain circumstances.
@@ -4463,7 +5162,13 @@
pr_cont("full-width counters, ");
}
- kfree(to_free);
+ /*
+ * For arch perfmon 4 use counter freezing to avoid
+ * several MSR accesses in the PMI.
+ */
+ if (x86_pmu.counter_freezing)
+ x86_pmu.handle_irq = intel_pmu_handle_irq_v4;
+
return 0;
}
@@ -4500,7 +5205,7 @@
hardlockup_detector_perf_restart();
for_each_online_cpu(c)
- free_excl_cntrs(c);
+ free_excl_cntrs(&per_cpu(cpu_hw_events, c));
cpus_read_unlock();
pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n");
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9f8084f..e1daf41 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -45,46 +45,49 @@
* MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
* perf code: 0x01
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM,
- CNL
+ * CNL,KBL,CML
* Scope: Core
* MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
* perf code: 0x02
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- * SKL,KNL,GLM,CNL
+ * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
* Scope: Core
* MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
* perf code: 0x03
- * Available model: SNB,IVB,HSW,BDW,SKL,CNL
+ * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
+ * ICL,TGL
* Scope: Core
* MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter.
* perf code: 0x00
- * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL
+ * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
+ * KBL,CML,ICL,TGL
* Scope: Package (physical package)
* MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter.
* perf code: 0x01
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
- * GLM,CNL
+ * GLM,CNL,KBL,CML,ICL,TGL
* Scope: Package (physical package)
* MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter.
* perf code: 0x02
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- * SKL,KNL,GLM,CNL
+ * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
* Scope: Package (physical package)
* MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
* perf code: 0x03
- * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL
+ * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
+ * KBL,CML,ICL,TGL
* Scope: Package (physical package)
* MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
* perf code: 0x04
- * Available model: HSW ULT,CNL
+ * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL
* Scope: Package (physical package)
* MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
* perf code: 0x05
- * Available model: HSW ULT,CNL
+ * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
- * Available model: HSW ULT,GLM,CNL
+ * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL
* Scope: Package (physical package)
*
*/
@@ -96,6 +99,7 @@
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "../perf_event.h"
+#include "../probe.h"
MODULE_LICENSE("GPL");
@@ -144,25 +148,42 @@
PERF_CSTATE_CORE_EVENT_MAX,
};
-PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00");
-PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01");
-PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02");
-PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03");
+PMU_EVENT_ATTR_STRING(c1-residency, attr_cstate_core_c1, "event=0x00");
+PMU_EVENT_ATTR_STRING(c3-residency, attr_cstate_core_c3, "event=0x01");
+PMU_EVENT_ATTR_STRING(c6-residency, attr_cstate_core_c6, "event=0x02");
+PMU_EVENT_ATTR_STRING(c7-residency, attr_cstate_core_c7, "event=0x03");
-static struct perf_cstate_msr core_msr[] = {
- [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1 },
- [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3 },
- [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6 },
- [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7 },
+static unsigned long core_msr_mask;
+
+PMU_EVENT_GROUP(events, cstate_core_c1);
+PMU_EVENT_GROUP(events, cstate_core_c3);
+PMU_EVENT_GROUP(events, cstate_core_c6);
+PMU_EVENT_GROUP(events, cstate_core_c7);
+
+static bool test_msr(int idx, void *data)
+{
+ return test_bit(idx, (unsigned long *) data);
+}
+
+static struct perf_msr core_msr[] = {
+ [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &group_cstate_core_c1, test_msr },
+ [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &group_cstate_core_c3, test_msr },
+ [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &group_cstate_core_c6, test_msr },
+ [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &group_cstate_core_c7, test_msr },
};
-static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = {
+static struct attribute *attrs_empty[] = {
NULL,
};
+/*
+ * There are no default events, but we need to create
+ * "events" group (with empty attrs) before updating
+ * it with detected events.
+ */
static struct attribute_group core_events_attr_group = {
.name = "events",
- .attrs = core_events_attrs,
+ .attrs = attrs_empty,
};
DEFINE_CSTATE_FORMAT_ATTR(core_event, event, "config:0-63");
@@ -211,31 +232,37 @@
PERF_CSTATE_PKG_EVENT_MAX,
};
-PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00");
-PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01");
-PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02");
-PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_pkg_c7, "event=0x03");
-PMU_EVENT_ATTR_STRING(c8-residency, evattr_cstate_pkg_c8, "event=0x04");
-PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05");
-PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06");
+PMU_EVENT_ATTR_STRING(c2-residency, attr_cstate_pkg_c2, "event=0x00");
+PMU_EVENT_ATTR_STRING(c3-residency, attr_cstate_pkg_c3, "event=0x01");
+PMU_EVENT_ATTR_STRING(c6-residency, attr_cstate_pkg_c6, "event=0x02");
+PMU_EVENT_ATTR_STRING(c7-residency, attr_cstate_pkg_c7, "event=0x03");
+PMU_EVENT_ATTR_STRING(c8-residency, attr_cstate_pkg_c8, "event=0x04");
+PMU_EVENT_ATTR_STRING(c9-residency, attr_cstate_pkg_c9, "event=0x05");
+PMU_EVENT_ATTR_STRING(c10-residency, attr_cstate_pkg_c10, "event=0x06");
-static struct perf_cstate_msr pkg_msr[] = {
- [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2 },
- [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3 },
- [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6 },
- [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7 },
- [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8 },
- [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9 },
- [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10 },
-};
+static unsigned long pkg_msr_mask;
-static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = {
- NULL,
+PMU_EVENT_GROUP(events, cstate_pkg_c2);
+PMU_EVENT_GROUP(events, cstate_pkg_c3);
+PMU_EVENT_GROUP(events, cstate_pkg_c6);
+PMU_EVENT_GROUP(events, cstate_pkg_c7);
+PMU_EVENT_GROUP(events, cstate_pkg_c8);
+PMU_EVENT_GROUP(events, cstate_pkg_c9);
+PMU_EVENT_GROUP(events, cstate_pkg_c10);
+
+static struct perf_msr pkg_msr[] = {
+ [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &group_cstate_pkg_c2, test_msr },
+ [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &group_cstate_pkg_c3, test_msr },
+ [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &group_cstate_pkg_c6, test_msr },
+ [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &group_cstate_pkg_c7, test_msr },
+ [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &group_cstate_pkg_c8, test_msr },
+ [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &group_cstate_pkg_c9, test_msr },
+ [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &group_cstate_pkg_c10, test_msr },
};
static struct attribute_group pkg_events_attr_group = {
.name = "events",
- .attrs = pkg_events_attrs,
+ .attrs = attrs_empty,
};
DEFINE_CSTATE_FORMAT_ATTR(pkg_event, event, "config:0-63");
@@ -280,13 +307,7 @@
return -ENOENT;
/* unsupported modes and filters */
- if (event->attr.exclude_user ||
- event->attr.exclude_kernel ||
- event->attr.exclude_hv ||
- event->attr.exclude_idle ||
- event->attr.exclude_host ||
- event->attr.exclude_guest ||
- event->attr.sample_period) /* no sampling */
+ if (event->attr.sample_period) /* no sampling */
return -EINVAL;
if (event->cpu < 0)
@@ -295,7 +316,8 @@
if (event->pmu == &cstate_core_pmu) {
if (cfg >= PERF_CSTATE_CORE_EVENT_MAX)
return -EINVAL;
- if (!core_msr[cfg].attr)
+ cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_CORE_EVENT_MAX);
+ if (!(core_msr_mask & (1 << cfg)))
return -EINVAL;
event->hw.event_base = core_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_core_cpu_mask,
@@ -304,11 +326,11 @@
if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
return -EINVAL;
cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX);
- if (!pkg_msr[cfg].attr)
+ if (!(pkg_msr_mask & (1 << cfg)))
return -EINVAL;
event->hw.event_base = pkg_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
- topology_core_cpumask(event->cpu));
+ topology_die_cpumask(event->cpu));
} else {
return -ENOENT;
}
@@ -391,7 +413,7 @@
if (has_cstate_pkg &&
cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) {
- target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+ target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
/* Migrate events if there is a valid target */
if (target < nr_cpu_ids) {
cpumask_set_cpu(target, &cstate_pkg_cpu_mask);
@@ -420,15 +442,35 @@
* in the package cpu mask as the designated reader.
*/
target = cpumask_any_and(&cstate_pkg_cpu_mask,
- topology_core_cpumask(cpu));
+ topology_die_cpumask(cpu));
if (has_cstate_pkg && target >= nr_cpu_ids)
cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
return 0;
}
+static const struct attribute_group *core_attr_update[] = {
+ &group_cstate_core_c1,
+ &group_cstate_core_c3,
+ &group_cstate_core_c6,
+ &group_cstate_core_c7,
+ NULL,
+};
+
+static const struct attribute_group *pkg_attr_update[] = {
+ &group_cstate_pkg_c2,
+ &group_cstate_pkg_c3,
+ &group_cstate_pkg_c6,
+ &group_cstate_pkg_c7,
+ &group_cstate_pkg_c8,
+ &group_cstate_pkg_c9,
+ &group_cstate_pkg_c10,
+ NULL,
+};
+
static struct pmu cstate_core_pmu = {
.attr_groups = core_attr_groups,
+ .attr_update = core_attr_update,
.name = "cstate_core",
.task_ctx_nr = perf_invalid_context,
.event_init = cstate_pmu_event_init,
@@ -437,12 +479,13 @@
.start = cstate_pmu_event_start,
.stop = cstate_pmu_event_stop,
.read = cstate_pmu_event_update,
- .capabilities = PERF_PMU_CAP_NO_INTERRUPT,
+ .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
.module = THIS_MODULE,
};
static struct pmu cstate_pkg_pmu = {
.attr_groups = pkg_attr_groups,
+ .attr_update = pkg_attr_update,
.name = "cstate_pkg",
.task_ctx_nr = perf_invalid_context,
.event_init = cstate_pmu_event_init,
@@ -451,7 +494,7 @@
.start = cstate_pmu_event_start,
.stop = cstate_pmu_event_stop,
.read = cstate_pmu_event_update,
- .capabilities = PERF_PMU_CAP_NO_INTERRUPT,
+ .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
.module = THIS_MODULE,
};
@@ -504,6 +547,19 @@
BIT(PERF_CSTATE_PKG_C10_RES),
};
+static const struct cstate_model icl_cstates __initconst = {
+ .core_events = BIT(PERF_CSTATE_CORE_C6_RES) |
+ BIT(PERF_CSTATE_CORE_C7_RES),
+
+ .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) |
+ BIT(PERF_CSTATE_PKG_C3_RES) |
+ BIT(PERF_CSTATE_PKG_C6_RES) |
+ BIT(PERF_CSTATE_PKG_C7_RES) |
+ BIT(PERF_CSTATE_PKG_C8_RES) |
+ BIT(PERF_CSTATE_PKG_C9_RES) |
+ BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
static const struct cstate_model slm_cstates __initconst = {
.core_events = BIT(PERF_CSTATE_CORE_C1_RES) |
BIT(PERF_CSTATE_CORE_C6_RES),
@@ -553,66 +609,48 @@
X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE_X, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_CORE, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_X, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_GT3E, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_HASWELL, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_X, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_G, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_ULT, hswult_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_L, hswult_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT1, slm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT2, slm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT, slm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT, slm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT_D, slm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT, slm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_CORE, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_XEON_D, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_GT3E, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_X, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_D, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_G, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_X, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_L, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_L, hswult_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE, hswult_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE_L, hswult_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE, hswult_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_L, cnl_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+
+ X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE, icl_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE_L, icl_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE, icl_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
-/*
- * Probe the cstate events and insert the available one into sysfs attrs
- * Return false if there are no available events.
- */
-static bool __init cstate_probe_msr(const unsigned long evmsk, int max,
- struct perf_cstate_msr *msr,
- struct attribute **attrs)
-{
- bool found = false;
- unsigned int bit;
- u64 val;
-
- for (bit = 0; bit < max; bit++) {
- if (test_bit(bit, &evmsk) && !rdmsrl_safe(msr[bit].msr, &val)) {
- *attrs++ = &msr[bit].attr->attr.attr;
- found = true;
- } else {
- msr[bit].attr = NULL;
- }
- }
- *attrs = NULL;
-
- return found;
-}
-
static int __init cstate_probe(const struct cstate_model *cm)
{
/* SLM has different MSR for PKG C6 */
@@ -624,13 +662,14 @@
pkg_msr[PERF_CSTATE_CORE_C6_RES].msr = MSR_KNL_CORE_C6_RESIDENCY;
- has_cstate_core = cstate_probe_msr(cm->core_events,
- PERF_CSTATE_CORE_EVENT_MAX,
- core_msr, core_events_attrs);
+ core_msr_mask = perf_msr_probe(core_msr, PERF_CSTATE_CORE_EVENT_MAX,
+ true, (void *) &cm->core_events);
- has_cstate_pkg = cstate_probe_msr(cm->pkg_events,
- PERF_CSTATE_PKG_EVENT_MAX,
- pkg_msr, pkg_events_attrs);
+ pkg_msr_mask = perf_msr_probe(pkg_msr, PERF_CSTATE_PKG_EVENT_MAX,
+ true, (void *) &cm->pkg_events);
+
+ has_cstate_core = !!core_msr_mask;
+ has_cstate_pkg = !!pkg_msr_mask;
return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV;
}
@@ -667,7 +706,13 @@
}
if (has_cstate_pkg) {
- err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1);
+ if (topology_max_die_per_package() > 1) {
+ err = perf_pmu_register(&cstate_pkg_pmu,
+ "cstate_die", -1);
+ } else {
+ err = perf_pmu_register(&cstate_pkg_pmu,
+ cstate_pkg_pmu.name, -1);
+ }
if (err) {
has_cstate_pkg = false;
pr_info("Failed to register cstate pkg pmu\n");
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index b7b01d7..ce83950 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -337,7 +337,7 @@
struct debug_store *ds = hwev->ds;
size_t bsiz = x86_pmu.pebs_buffer_size;
int max, node = cpu_to_node(cpu);
- void *buffer, *ibuffer, *cea;
+ void *buffer, *insn_buff, *cea;
if (!x86_pmu.pebs)
return 0;
@@ -351,12 +351,12 @@
* buffer then.
*/
if (x86_pmu.intel_cap.pebs_format < 2) {
- ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
- if (!ibuffer) {
+ insn_buff = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
+ if (!insn_buff) {
dsfree_pages(buffer, bsiz);
return -ENOMEM;
}
- per_cpu(insn_buffer, cpu) = ibuffer;
+ per_cpu(insn_buffer, cpu) = insn_buff;
}
hwev->ds_pebs_vaddr = buffer;
/* Update the cpu entry area mapping */
@@ -684,7 +684,7 @@
INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01),
EVENT_CONSTRAINT_END
};
@@ -693,7 +693,7 @@
INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01),
/* Allow all events as PEBS with no flags */
INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
EVENT_CONSTRAINT_END
@@ -701,7 +701,7 @@
struct event_constraint intel_slm_pebs_event_constraints[] = {
/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x1),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x1),
/* Allow all events as PEBS with no flags */
INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
EVENT_CONSTRAINT_END
@@ -726,7 +726,7 @@
INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
EVENT_CONSTRAINT_END
};
@@ -743,7 +743,7 @@
INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
EVENT_CONSTRAINT_END
};
@@ -752,7 +752,7 @@
INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */
/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -767,9 +767,9 @@
INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */
/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -783,9 +783,9 @@
INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */
/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
@@ -806,9 +806,9 @@
INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */
/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
@@ -829,9 +829,9 @@
struct event_constraint intel_skl_pebs_event_constraints[] = {
INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */
/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
/* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */
- INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
INTEL_PLD_CONSTRAINT(0x1cd, 0xf), /* MEM_TRANS_RETIRED.* */
INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
@@ -849,6 +849,26 @@
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_icl_pebs_event_constraints[] = {
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */
+
+ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */
+
+ /*
+ * Everything else is handled by PMU_FL_PEBS_ALL, because we
+ * need the full constraints from the main table.
+ */
+
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event)
{
struct event_constraint *c;
@@ -858,7 +878,7 @@
if (x86_pmu.pebs_constraints) {
for_each_event_constraint(c, x86_pmu.pebs_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
@@ -882,6 +902,9 @@
*/
static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc)
{
+ if (cpuc->n_pebs == cpuc->n_pebs_via_pt)
+ return false;
+
return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs);
}
@@ -899,6 +922,9 @@
u64 threshold;
int reserved;
+ if (cpuc->n_pebs_via_pt)
+ return;
+
if (x86_pmu.flags & PMU_FL_PEBS_ALL)
reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed;
else
@@ -906,17 +932,87 @@
if (cpuc->n_pebs == cpuc->n_large_pebs) {
threshold = ds->pebs_absolute_maximum -
- reserved * x86_pmu.pebs_record_size;
+ reserved * cpuc->pebs_record_size;
} else {
- threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+ threshold = ds->pebs_buffer_base + cpuc->pebs_record_size;
}
ds->pebs_interrupt_threshold = threshold;
}
-static void
-pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
+static void adaptive_pebs_record_size_update(void)
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ u64 pebs_data_cfg = cpuc->pebs_data_cfg;
+ int sz = sizeof(struct pebs_basic);
+
+ if (pebs_data_cfg & PEBS_DATACFG_MEMINFO)
+ sz += sizeof(struct pebs_meminfo);
+ if (pebs_data_cfg & PEBS_DATACFG_GP)
+ sz += sizeof(struct pebs_gprs);
+ if (pebs_data_cfg & PEBS_DATACFG_XMMS)
+ sz += sizeof(struct pebs_xmm);
+ if (pebs_data_cfg & PEBS_DATACFG_LBRS)
+ sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+
+ cpuc->pebs_record_size = sz;
+}
+
+#define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \
+ PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \
+ PERF_SAMPLE_TRANSACTION)
+
+static u64 pebs_update_adaptive_cfg(struct perf_event *event)
+{
+ struct perf_event_attr *attr = &event->attr;
+ u64 sample_type = attr->sample_type;
+ u64 pebs_data_cfg = 0;
+ bool gprs, tsx_weight;
+
+ if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
+ attr->precise_ip > 1)
+ return pebs_data_cfg;
+
+ if (sample_type & PERF_PEBS_MEMINFO_TYPE)
+ pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
+
+ /*
+ * We need GPRs when:
+ * + user requested them
+ * + precise_ip < 2 for the non event IP
+ * + For RTM TSX weight we need GPRs for the abort code.
+ */
+ gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_GP_REGS);
+
+ tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
+ ((attr->config & INTEL_ARCH_EVENT_MASK) ==
+ x86_pmu.rtm_abort_event);
+
+ if (gprs || (attr->precise_ip < 2) || tsx_weight)
+ pebs_data_cfg |= PEBS_DATACFG_GP;
+
+ if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PERF_REG_EXTENDED_MASK))
+ pebs_data_cfg |= PEBS_DATACFG_XMMS;
+
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ /*
+ * For now always log all LBRs. Could configure this
+ * later.
+ */
+ pebs_data_cfg |= PEBS_DATACFG_LBRS |
+ ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
+ }
+
+ return pebs_data_cfg;
+}
+
+static void
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
+ struct perf_event *event, bool add)
+{
+ struct pmu *pmu = event->ctx->pmu;
/*
* Make sure we get updated with the first PEBS
* event. It will trigger also during removal, but
@@ -933,6 +1029,29 @@
update = true;
}
+ /*
+ * The PEBS record doesn't shrink on pmu::del(). Doing so would require
+ * iterating all remaining PEBS events to reconstruct the config.
+ */
+ if (x86_pmu.intel_cap.pebs_baseline && add) {
+ u64 pebs_data_cfg;
+
+ /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
+ if (cpuc->n_pebs == 1) {
+ cpuc->pebs_data_cfg = 0;
+ cpuc->pebs_record_size = sizeof(struct pebs_basic);
+ }
+
+ pebs_data_cfg = pebs_update_adaptive_cfg(event);
+
+ /* Update pebs_record_size if new event requires more data. */
+ if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
+ cpuc->pebs_data_cfg |= pebs_data_cfg;
+ adaptive_pebs_record_size_update();
+ update = true;
+ }
+ }
+
if (update)
pebs_update_threshold(cpuc);
}
@@ -946,8 +1065,38 @@
cpuc->n_pebs++;
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs++;
+ if (hwc->flags & PERF_X86_EVENT_PEBS_VIA_PT)
+ cpuc->n_pebs_via_pt++;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, true);
+}
+
+static void intel_pmu_pebs_via_pt_disable(struct perf_event *event)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ if (!is_pebs_pt(event))
+ return;
+
+ if (!(cpuc->pebs_enabled & ~PEBS_VIA_PT_MASK))
+ cpuc->pebs_enabled &= ~PEBS_VIA_PT_MASK;
+}
+
+static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct hw_perf_event *hwc = &event->hw;
+ struct debug_store *ds = cpuc->ds;
+
+ if (!is_pebs_pt(event))
+ return;
+
+ if (!(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS))
+ cpuc->pebs_enabled |= PEBS_PMI_AFTER_EACH_RECORD;
+
+ cpuc->pebs_enabled |= PEBS_OUTPUT_PT;
+
+ wrmsrl(MSR_RELOAD_PMC0 + hwc->idx, ds->pebs_event_reset[hwc->idx]);
}
void intel_pmu_pebs_enable(struct perf_event *event)
@@ -960,11 +1109,19 @@
cpuc->pebs_enabled |= 1ULL << hwc->idx;
- if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5))
cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63;
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ hwc->config |= ICL_EVENTSEL_ADAPTIVE;
+ if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
+ wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
+ cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
+ }
+ }
+
/*
* Use auto-reload if possible to save a MSR write in the PMI.
* This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
@@ -979,6 +1136,8 @@
} else {
ds->pebs_event_reset[hwc->idx] = 0;
}
+
+ intel_pmu_pebs_via_pt_enable(event);
}
void intel_pmu_pebs_del(struct perf_event *event)
@@ -990,8 +1149,10 @@
cpuc->n_pebs--;
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs--;
+ if (hwc->flags & PERF_X86_EVENT_PEBS_VIA_PT)
+ cpuc->n_pebs_via_pt--;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, false);
}
void intel_pmu_pebs_disable(struct perf_event *event)
@@ -999,16 +1160,20 @@
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
- if (cpuc->n_pebs == cpuc->n_large_pebs)
+ if (cpuc->n_pebs == cpuc->n_large_pebs &&
+ cpuc->n_pebs != cpuc->n_pebs_via_pt)
intel_pmu_drain_pebs_buffer();
cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
- if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
+ (x86_pmu.version < 5))
cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled &= ~(1ULL << 63);
+ intel_pmu_pebs_via_pt_disable(event);
+
if (cpuc->enabled)
wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
@@ -1125,34 +1290,57 @@
return 0;
}
-static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_weight(u64 tsx_tuning)
{
- if (pebs->tsx_tuning) {
- union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
+ if (tsx_tuning) {
+ union hsw_tsx_tuning tsx = { .value = tsx_tuning };
return tsx.cycles_last_block;
}
return 0;
}
-static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
{
- u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
+ u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
/* For RTM XABORTs also log the abort code from AX */
- if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1))
- txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+ if ((txn & PERF_TXN_TRANSACTION) && (ax & 1))
+ txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
return txn;
}
-static void setup_pebs_sample_data(struct perf_event *event,
- struct pt_regs *iregs, void *__pebs,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+static inline u64 get_pebs_status(void *n)
{
+ if (x86_pmu.intel_cap.pebs_format < 4)
+ return ((struct pebs_record_nhm *)n)->status;
+ return ((struct pebs_basic *)n)->applicable_counters;
+}
+
#define PERF_X86_EVENT_PEBS_HSW_PREC \
(PERF_X86_EVENT_PEBS_ST_HSW | \
PERF_X86_EVENT_PEBS_LD_HSW | \
PERF_X86_EVENT_PEBS_NA_HSW)
+
+static u64 get_data_src(struct perf_event *event, u64 aux)
+{
+ u64 val = PERF_MEM_NA;
+ int fl = event->hw.flags;
+ bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+
+ if (fl & PERF_X86_EVENT_PEBS_LDLAT)
+ val = load_latency_data(aux);
+ else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
+ val = precise_datala_hsw(event, aux);
+ else if (fst)
+ val = precise_store_data(aux);
+ return val;
+}
+
+static void setup_pebs_fixed_sample_data(struct perf_event *event,
+ struct pt_regs *iregs, void *__pebs,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
/*
* We cast to the biggest pebs_record but are careful not to
* unconditionally access the 'extra' entries.
@@ -1160,17 +1348,13 @@
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct pebs_record_skl *pebs = __pebs;
u64 sample_type;
- int fll, fst, dsrc;
- int fl = event->hw.flags;
+ int fll;
if (pebs == NULL)
return;
sample_type = event->attr.sample_type;
- dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
-
- fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
- fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+ fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
perf_sample_data_init(data, 0, event->hw.last_period);
@@ -1185,21 +1369,13 @@
/*
* data.data_src encodes the data source
*/
- if (dsrc) {
- u64 val = PERF_MEM_NA;
- if (fll)
- val = load_latency_data(pebs->dse);
- else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
- val = precise_datala_hsw(event, pebs->dse);
- else if (fst)
- val = precise_store_data(pebs->dse);
- data->data_src.val = val;
- }
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, pebs->dse);
/*
* We must however always use iregs for the unwinder to stay sane; the
* record BP,SP,IP can point into thin air when the record is from a
- * previous PMI context or an (I)RET happend between the record and
+ * previous PMI context or an (I)RET happened between the record and
* PMI.
*/
if (sample_type & PERF_SAMPLE_CALLCHAIN)
@@ -1281,10 +1457,11 @@
if (x86_pmu.intel_cap.pebs_format >= 2) {
/* Only set the TSX weight when no memory weight. */
if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
- data->weight = intel_hsw_weight(pebs);
+ data->weight = intel_get_tsx_weight(pebs->tsx_tuning);
if (sample_type & PERF_SAMPLE_TRANSACTION)
- data->txn = intel_hsw_transaction(pebs);
+ data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
+ pebs->ax);
}
/*
@@ -1301,6 +1478,140 @@
data->br_stack = &cpuc->lbr_stack;
}
+static void adaptive_pebs_save_regs(struct pt_regs *regs,
+ struct pebs_gprs *gprs)
+{
+ regs->ax = gprs->ax;
+ regs->bx = gprs->bx;
+ regs->cx = gprs->cx;
+ regs->dx = gprs->dx;
+ regs->si = gprs->si;
+ regs->di = gprs->di;
+ regs->bp = gprs->bp;
+ regs->sp = gprs->sp;
+#ifndef CONFIG_X86_32
+ regs->r8 = gprs->r8;
+ regs->r9 = gprs->r9;
+ regs->r10 = gprs->r10;
+ regs->r11 = gprs->r11;
+ regs->r12 = gprs->r12;
+ regs->r13 = gprs->r13;
+ regs->r14 = gprs->r14;
+ regs->r15 = gprs->r15;
+#endif
+}
+
+/*
+ * With adaptive PEBS the layout depends on what fields are configured.
+ */
+
+static void setup_pebs_adaptive_sample_data(struct perf_event *event,
+ struct pt_regs *iregs, void *__pebs,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct pebs_basic *basic = __pebs;
+ void *next_record = basic + 1;
+ u64 sample_type;
+ u64 format_size;
+ struct pebs_meminfo *meminfo = NULL;
+ struct pebs_gprs *gprs = NULL;
+ struct x86_perf_regs *perf_regs;
+
+ if (basic == NULL)
+ return;
+
+ perf_regs = container_of(regs, struct x86_perf_regs, regs);
+ perf_regs->xmm_regs = NULL;
+
+ sample_type = event->attr.sample_type;
+ format_size = basic->format_size;
+ perf_sample_data_init(data, 0, event->hw.last_period);
+ data->period = event->hw.last_period;
+
+ if (event->attr.use_clockid == 0)
+ data->time = native_sched_clock_from_tsc(basic->tsc);
+
+ /*
+ * We must however always use iregs for the unwinder to stay sane; the
+ * record BP,SP,IP can point into thin air when the record is from a
+ * previous PMI context or an (I)RET happened between the record and
+ * PMI.
+ */
+ if (sample_type & PERF_SAMPLE_CALLCHAIN)
+ data->callchain = perf_callchain(event, iregs);
+
+ *regs = *iregs;
+ /* The ip in basic is EventingIP */
+ set_linear_ip(regs, basic->ip);
+ regs->flags = PERF_EFLAGS_EXACT;
+
+ /*
+ * The record for MEMINFO is in front of GP
+ * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
+ * Save the pointer here but process later.
+ */
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ meminfo = next_record;
+ next_record = meminfo + 1;
+ }
+
+ if (format_size & PEBS_DATACFG_GP) {
+ gprs = next_record;
+ next_record = gprs + 1;
+
+ if (event->attr.precise_ip < 2) {
+ set_linear_ip(regs, gprs->ip);
+ regs->flags &= ~PERF_EFLAGS_EXACT;
+ }
+
+ if (sample_type & PERF_SAMPLE_REGS_INTR)
+ adaptive_pebs_save_regs(regs, gprs);
+ }
+
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ if (sample_type & PERF_SAMPLE_WEIGHT)
+ data->weight = meminfo->latency ?:
+ intel_get_tsx_weight(meminfo->tsx_tuning);
+
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, meminfo->aux);
+
+ if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
+ data->addr = meminfo->address;
+
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
+ data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning,
+ gprs ? gprs->ax : 0);
+ }
+
+ if (format_size & PEBS_DATACFG_XMMS) {
+ struct pebs_xmm *xmm = next_record;
+
+ next_record = xmm + 1;
+ perf_regs->xmm_regs = xmm->xmm;
+ }
+
+ if (format_size & PEBS_DATACFG_LBRS) {
+ struct pebs_lbr *lbr = next_record;
+ int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+ & 0xff) + 1;
+ next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+
+ if (has_branch_stack(event)) {
+ intel_pmu_store_pebs_lbrs(lbr);
+ data->br_stack = &cpuc->lbr_stack;
+ }
+ }
+
+ WARN_ONCE(next_record != __pebs + (format_size >> 48),
+ "PEBS record size %llu, expected %llu, config %llx\n",
+ format_size >> 48,
+ (u64)(next_record - __pebs),
+ basic->format_size);
+}
+
static inline void *
get_next_pebs_record_by_bit(void *base, void *top, int bit)
{
@@ -1318,19 +1629,19 @@
if (base == NULL)
return NULL;
- for (at = base; at < top; at += x86_pmu.pebs_record_size) {
- struct pebs_record_nhm *p = at;
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ unsigned long status = get_pebs_status(at);
- if (test_bit(bit, (unsigned long *)&p->status)) {
+ if (test_bit(bit, (unsigned long *)&status)) {
/* PEBS v3 has accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3)
return at;
- if (p->status == (1 << bit))
+ if (status == (1 << bit))
return at;
/* clear non-PEBS bit and re-check */
- pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status = status & cpuc->pebs_enabled;
pebs_status &= PEBS_COUNTER_MASK;
if (pebs_status == (1 << bit))
return at;
@@ -1410,11 +1721,18 @@
static void __intel_pmu_pebs_event(struct perf_event *event,
struct pt_regs *iregs,
void *base, void *top,
- int bit, int count)
+ int bit, int count,
+ void (*setup_sample)(struct perf_event *,
+ struct pt_regs *,
+ void *,
+ struct perf_sample_data *,
+ struct pt_regs *))
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
struct perf_sample_data data;
- struct pt_regs regs;
+ struct x86_perf_regs perf_regs;
+ struct pt_regs *regs = &perf_regs.regs;
void *at = get_next_pebs_record_by_bit(base, top, bit);
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
@@ -1429,20 +1747,20 @@
return;
while (count > 1) {
- setup_pebs_sample_data(event, iregs, at, &data, ®s);
- perf_event_output(event, &data, ®s);
- at += x86_pmu.pebs_record_size;
+ setup_sample(event, iregs, at, &data, regs);
+ perf_event_output(event, &data, regs);
+ at += cpuc->pebs_record_size;
at = get_next_pebs_record_by_bit(at, top, bit);
count--;
}
- setup_pebs_sample_data(event, iregs, at, &data, ®s);
+ setup_sample(event, iregs, at, &data, regs);
/*
* All but the last records are processed.
* The last one is left to be able to call the overflow handler.
*/
- if (perf_event_overflow(event, &data, ®s)) {
+ if (perf_event_overflow(event, &data, regs)) {
x86_pmu_stop(event, 0);
return;
}
@@ -1483,7 +1801,27 @@
return;
}
- __intel_pmu_pebs_event(event, iregs, at, top, 0, n);
+ __intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+ setup_pebs_fixed_sample_data);
+}
+
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
+{
+ struct perf_event *event;
+ int bit;
+
+ /*
+ * The drain_pebs() could be called twice in a short period
+ * for auto-reload event in pmu::read(). There are no
+ * overflows have happened in between.
+ * It needs to call intel_pmu_save_and_restart_reload() to
+ * update the event->count for this case.
+ */
+ for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
+ event = cpuc->events[bit];
+ if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+ intel_pmu_save_and_restart_reload(event, 0);
+ }
}
static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
@@ -1513,19 +1851,7 @@
}
if (unlikely(base >= top)) {
- /*
- * The drain_pebs() could be called twice in a short period
- * for auto-reload event in pmu::read(). There are no
- * overflows have happened in between.
- * It needs to call intel_pmu_save_and_restart_reload() to
- * update the event->count for this case.
- */
- for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
- size) {
- event = cpuc->events[bit];
- if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
- intel_pmu_save_and_restart_reload(event, 0);
- }
+ intel_pmu_pebs_event_update_no_drain(cpuc, size);
return;
}
@@ -1538,8 +1864,7 @@
/* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
- for_each_set_bit(bit, (unsigned long *)&pebs_status,
- size)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
counts[bit]++;
continue;
@@ -1578,8 +1903,7 @@
* If collision happened, the record will be dropped.
*/
if (p->status != (1ULL << bit)) {
- for_each_set_bit(i, (unsigned long *)&pebs_status,
- x86_pmu.max_pebs_events)
+ for_each_set_bit(i, (unsigned long *)&pebs_status, size)
error[i]++;
continue;
}
@@ -1587,7 +1911,7 @@
counts[bit]++;
}
- for (bit = 0; bit < size; bit++) {
+ for_each_set_bit(bit, (unsigned long *)&mask, size) {
if ((counts[bit] == 0) && (error[bit] == 0))
continue;
@@ -1608,11 +1932,66 @@
if (counts[bit]) {
__intel_pmu_pebs_event(event, iregs, base,
- top, bit, counts[bit]);
+ top, bit, counts[bit],
+ setup_pebs_fixed_sample_data);
}
}
}
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+{
+ short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct debug_store *ds = cpuc->ds;
+ struct perf_event *event;
+ void *base, *at, *top;
+ int bit, size;
+ u64 mask;
+
+ if (!x86_pmu.pebs_active)
+ return;
+
+ base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base;
+ top = (struct pebs_basic *)(unsigned long)ds->pebs_index;
+
+ ds->pebs_index = ds->pebs_buffer_base;
+
+ mask = ((1ULL << x86_pmu.max_pebs_events) - 1) |
+ (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
+ size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+
+ if (unlikely(base >= top)) {
+ intel_pmu_pebs_event_update_no_drain(cpuc, size);
+ return;
+ }
+
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ u64 pebs_status;
+
+ pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
+ pebs_status &= mask;
+
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+ counts[bit]++;
+ }
+
+ for_each_set_bit(bit, (unsigned long *)&mask, size) {
+ if (counts[bit] == 0)
+ continue;
+
+ event = cpuc->events[bit];
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ if (WARN_ON_ONCE(!event->attr.precise_ip))
+ continue;
+
+ __intel_pmu_pebs_event(event, iregs, base,
+ top, bit, counts[bit],
+ setup_pebs_adaptive_sample_data);
+ }
+}
+
/*
* BTS, PEBS probe and setup
*/
@@ -1628,10 +2007,17 @@
x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS);
x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
+ if (x86_pmu.version <= 4)
+ x86_pmu.pebs_no_isolation = 1;
+
if (x86_pmu.pebs) {
char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
+ char *pebs_qual = "";
int format = x86_pmu.intel_cap.pebs_format;
+ if (format < 4)
+ x86_pmu.intel_cap.pebs_baseline = 0;
+
switch (format) {
case 0:
pr_cont("PEBS fmt0%c, ", pebs_type);
@@ -1667,6 +2053,35 @@
x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
break;
+ case 4:
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl;
+ x86_pmu.pebs_record_size = sizeof(struct pebs_basic);
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ x86_pmu.large_pebs_flags |=
+ PERF_SAMPLE_BRANCH_STACK |
+ PERF_SAMPLE_TIME;
+ x86_pmu.flags |= PMU_FL_PEBS_ALL;
+ pebs_qual = "-baseline";
+ x86_get_pmu()->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
+ } else {
+ /* Only basic record supported */
+ x86_pmu.large_pebs_flags &=
+ ~(PERF_SAMPLE_ADDR |
+ PERF_SAMPLE_TIME |
+ PERF_SAMPLE_DATA_SRC |
+ PERF_SAMPLE_TRANSACTION |
+ PERF_SAMPLE_REGS_USER |
+ PERF_SAMPLE_REGS_INTR);
+ }
+ pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+
+ if (x86_pmu.intel_cap.pebs_output_pt_available) {
+ pr_cont("PEBS-via-PT, ");
+ x86_get_pmu()->capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
+ }
+
+ break;
+
default:
pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
x86_pmu.pebs = 0;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index c88ed39..ea54634 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -273,7 +273,7 @@
return !tsx_support && (lbr_desc[lbr_format] & LBR_TSX);
}
-DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key);
+static DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key);
/* If quirk is enabled, ensure sign extension is 63 bits: */
inline u64 lbr_from_signext_quirk_wr(u64 val)
@@ -488,6 +488,8 @@
* be 'new'. Conversely, a new event can get installed through the
* context switch path for the first time.
*/
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+ cpuc->lbr_pebs_users++;
perf_sched_cb_inc(event->ctx->pmu);
if (!cpuc->lbr_users++ && !event->total_time_running)
intel_pmu_lbr_reset();
@@ -507,8 +509,11 @@
task_ctx->lbr_callstack_users--;
}
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+ cpuc->lbr_pebs_users--;
cpuc->lbr_users--;
WARN_ON_ONCE(cpuc->lbr_users < 0);
+ WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
perf_sched_cb_dec(event->ctx->pmu);
}
@@ -658,7 +663,13 @@
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- if (!cpuc->lbr_users)
+ /*
+ * Don't read when all LBRs users are using adaptive PEBS.
+ *
+ * This could be smarter and actually check the event,
+ * but this simple approach seems to work for now.
+ */
+ if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
return;
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
@@ -931,6 +942,7 @@
ret = X86_BR_ZERO_CALL;
break;
}
+ /* fall through */
case 0x9a: /* call far absolute */
ret = X86_BR_CALL;
break;
@@ -1079,6 +1091,28 @@
}
}
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int i;
+
+ cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
+ for (i = 0; i < x86_pmu.lbr_nr; i++) {
+ u64 info = lbr->lbr[i].info;
+ struct perf_branch_entry *e = &cpuc->lbr_entries[i];
+
+ e->from = lbr->lbr[i].from;
+ e->to = lbr->lbr[i].to;
+ e->mispred = !!(info & LBR_INFO_MISPRED);
+ e->predicted = !(info & LBR_INFO_MISPRED);
+ e->in_tx = !!(info & LBR_INFO_IN_TX);
+ e->abort = !!(info & LBR_INFO_ABORT);
+ e->cycles = info & LBR_INFO_CYCLES;
+ e->reserved = 0;
+ }
+ intel_pmu_lbr_filter(cpuc);
+}
+
/*
* Map interface branch filters onto LBR filters
*/
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index d32c0ee..dee579e 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -1259,7 +1259,7 @@
}
/*
* Perf does test runs to see if a whole group can be assigned
- * together succesfully. There can be multiple rounds of this.
+ * together successfully. There can be multiple rounds of this.
* Unfortunately, p4_pmu_swap_config_ts touches the hwc->config
* bits, such that the next round of group assignments will
* cause the above p4_should_swap_ts to pass instead of fail.
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 8d016ce..05e43d0 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1,16 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Intel(R) Processor Trace PMU driver for perf
* Copyright (c) 2013-2014, Intel Corporation.
*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
* Intel PT is specified in the Intel Architecture Instruction Set Extensions
* Programming Reference:
* http://software.intel.com/en-us/intel-isa-extensions
@@ -68,6 +60,7 @@
PT_CAP(topa_output, 0, CPUID_ECX, BIT(0)),
PT_CAP(topa_multiple_entries, 0, CPUID_ECX, BIT(1)),
PT_CAP(single_range_output, 0, CPUID_ECX, BIT(2)),
+ PT_CAP(output_subsys, 0, CPUID_ECX, BIT(3)),
PT_CAP(payloads_lip, 0, CPUID_ECX, BIT(31)),
PT_CAP(num_address_ranges, 1, CPUID_EAX, 0x3),
PT_CAP(mtc_periods, 1, CPUID_EAX, 0xffff0000),
@@ -75,14 +68,21 @@
PT_CAP(psb_periods, 1, CPUID_EBX, 0xffff0000),
};
-static u32 pt_cap_get(enum pt_capabilities cap)
+u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities capability)
{
- struct pt_cap_desc *cd = &pt_caps[cap];
- u32 c = pt_pmu.caps[cd->leaf * PT_CPUID_REGS_NUM + cd->reg];
+ struct pt_cap_desc *cd = &pt_caps[capability];
+ u32 c = caps[cd->leaf * PT_CPUID_REGS_NUM + cd->reg];
unsigned int shift = __ffs(cd->mask);
return (c & cd->mask) >> shift;
}
+EXPORT_SYMBOL_GPL(intel_pt_validate_cap);
+
+u32 intel_pt_validate_hw_cap(enum pt_capabilities cap)
+{
+ return intel_pt_validate_cap(pt_pmu.caps, cap);
+}
+EXPORT_SYMBOL_GPL(intel_pt_validate_hw_cap);
static ssize_t pt_cap_show(struct device *cdev,
struct device_attribute *attr,
@@ -92,10 +92,10 @@
container_of(attr, struct dev_ext_attribute, attr);
enum pt_capabilities cap = (long)ea->var;
- return snprintf(buf, PAGE_SIZE, "%x\n", pt_cap_get(cap));
+ return snprintf(buf, PAGE_SIZE, "%x\n", intel_pt_validate_hw_cap(cap));
}
-static struct attribute_group pt_cap_group = {
+static struct attribute_group pt_cap_group __ro_after_init = {
.name = "caps",
};
@@ -204,9 +204,9 @@
/* model-specific quirks */
switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_BROADWELL_CORE:
- case INTEL_FAM6_BROADWELL_XEON_D:
- case INTEL_FAM6_BROADWELL_GT3E:
+ case INTEL_FAM6_BROADWELL:
+ case INTEL_FAM6_BROADWELL_D:
+ case INTEL_FAM6_BROADWELL_G:
case INTEL_FAM6_BROADWELL_X:
/* not setting BRANCH_EN will #GP, erratum BDM106 */
pt_pmu.branch_en_always_on = true;
@@ -310,16 +310,16 @@
return false;
if (config & RTIT_CTL_CYC_PSB) {
- if (!pt_cap_get(PT_CAP_psb_cyc))
+ if (!intel_pt_validate_hw_cap(PT_CAP_psb_cyc))
return false;
- allowed = pt_cap_get(PT_CAP_psb_periods);
+ allowed = intel_pt_validate_hw_cap(PT_CAP_psb_periods);
requested = (config & RTIT_CTL_PSB_FREQ) >>
RTIT_CTL_PSB_FREQ_OFFSET;
if (requested && (!(allowed & BIT(requested))))
return false;
- allowed = pt_cap_get(PT_CAP_cycle_thresholds);
+ allowed = intel_pt_validate_hw_cap(PT_CAP_cycle_thresholds);
requested = (config & RTIT_CTL_CYC_THRESH) >>
RTIT_CTL_CYC_THRESH_OFFSET;
if (requested && (!(allowed & BIT(requested))))
@@ -334,10 +334,10 @@
* Spec says that setting mtc period bits while mtc bit in
* CPUID is 0 will #GP, so better safe than sorry.
*/
- if (!pt_cap_get(PT_CAP_mtc))
+ if (!intel_pt_validate_hw_cap(PT_CAP_mtc))
return false;
- allowed = pt_cap_get(PT_CAP_mtc_periods);
+ allowed = intel_pt_validate_hw_cap(PT_CAP_mtc_periods);
if (!allowed)
return false;
@@ -349,11 +349,11 @@
}
if (config & RTIT_CTL_PWR_EVT_EN &&
- !pt_cap_get(PT_CAP_power_event_trace))
+ !intel_pt_validate_hw_cap(PT_CAP_power_event_trace))
return false;
if (config & RTIT_CTL_PTW) {
- if (!pt_cap_get(PT_CAP_ptwrite))
+ if (!intel_pt_validate_hw_cap(PT_CAP_ptwrite))
return false;
/* FUPonPTW without PTW doesn't make sense */
@@ -545,33 +545,62 @@
wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, reg);
}
+/**
+ * struct topa - ToPA metadata
+ * @list: linkage to struct pt_buffer's list of tables
+ * @offset: offset of the first entry in this table in the buffer
+ * @size: total size of all entries in this table
+ * @last: index of the last initialized entry in this table
+ * @z_count: how many times the first entry repeats
+ */
+struct topa {
+ struct list_head list;
+ u64 offset;
+ size_t size;
+ int last;
+ unsigned int z_count;
+};
+
/*
* Keep ToPA table-related metadata on the same page as the actual table,
* taking up a few words from the top
*/
-#define TENTS_PER_PAGE (((PAGE_SIZE - 40) / sizeof(struct topa_entry)) - 1)
+#define TENTS_PER_PAGE \
+ ((PAGE_SIZE - sizeof(struct topa)) / sizeof(struct topa_entry))
/**
- * struct topa - page-sized ToPA table with metadata at the top
+ * struct topa_page - page-sized ToPA table with metadata at the top
* @table: actual ToPA table entries, as understood by PT hardware
- * @list: linkage to struct pt_buffer's list of tables
- * @phys: physical address of this page
- * @offset: offset of the first entry in this table in the buffer
- * @size: total size of all entries in this table
- * @last: index of the last initialized entry in this table
+ * @topa: metadata
*/
-struct topa {
+struct topa_page {
struct topa_entry table[TENTS_PER_PAGE];
- struct list_head list;
- u64 phys;
- u64 offset;
- size_t size;
- int last;
+ struct topa topa;
};
+static inline struct topa_page *topa_to_page(struct topa *topa)
+{
+ return container_of(topa, struct topa_page, topa);
+}
+
+static inline struct topa_page *topa_entry_to_page(struct topa_entry *te)
+{
+ return (struct topa_page *)((unsigned long)te & PAGE_MASK);
+}
+
+static inline phys_addr_t topa_pfn(struct topa *topa)
+{
+ return PFN_DOWN(virt_to_phys(topa_to_page(topa)));
+}
+
/* make -1 stand for the last table entry */
-#define TOPA_ENTRY(t, i) ((i) == -1 ? &(t)->table[(t)->last] : &(t)->table[(i)])
+#define TOPA_ENTRY(t, i) \
+ ((i) == -1 \
+ ? &topa_to_page(t)->table[(t)->last] \
+ : &topa_to_page(t)->table[(i)])
+#define TOPA_ENTRY_SIZE(t, i) (sizes(TOPA_ENTRY((t), (i))->size))
+#define TOPA_ENTRY_PAGES(t, i) (1 << TOPA_ENTRY((t), (i))->size)
/**
* topa_alloc() - allocate page-sized ToPA table
@@ -583,27 +612,26 @@
static struct topa *topa_alloc(int cpu, gfp_t gfp)
{
int node = cpu_to_node(cpu);
- struct topa *topa;
+ struct topa_page *tp;
struct page *p;
p = alloc_pages_node(node, gfp | __GFP_ZERO, 0);
if (!p)
return NULL;
- topa = page_address(p);
- topa->last = 0;
- topa->phys = page_to_phys(p);
+ tp = page_address(p);
+ tp->topa.last = 0;
/*
* In case of singe-entry ToPA, always put the self-referencing END
* link as the 2nd entry in the table
*/
- if (!pt_cap_get(PT_CAP_topa_multiple_entries)) {
- TOPA_ENTRY(topa, 1)->base = topa->phys >> TOPA_SHIFT;
- TOPA_ENTRY(topa, 1)->end = 1;
+ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) {
+ TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p) >> TOPA_SHIFT;
+ TOPA_ENTRY(&tp->topa, 1)->end = 1;
}
- return topa;
+ return &tp->topa;
}
/**
@@ -638,12 +666,12 @@
topa->offset = last->offset + last->size;
buf->last = topa;
- if (!pt_cap_get(PT_CAP_topa_multiple_entries))
+ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
return;
BUG_ON(last->last != TENTS_PER_PAGE - 1);
- TOPA_ENTRY(last, -1)->base = topa->phys >> TOPA_SHIFT;
+ TOPA_ENTRY(last, -1)->base = topa_pfn(topa);
TOPA_ENTRY(last, -1)->end = 1;
}
@@ -654,7 +682,7 @@
static bool topa_table_full(struct topa *topa)
{
/* single-entry ToPA is a special case */
- if (!pt_cap_get(PT_CAP_topa_multiple_entries))
+ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
return !!topa->last;
return topa->last == TENTS_PER_PAGE - 1;
@@ -670,7 +698,7 @@
*
* Return: 0 on success or error code.
*/
-static int topa_insert_pages(struct pt_buffer *buf, gfp_t gfp)
+static int topa_insert_pages(struct pt_buffer *buf, int cpu, gfp_t gfp)
{
struct topa *topa = buf->last;
int order = 0;
@@ -681,16 +709,22 @@
order = page_private(p);
if (topa_table_full(topa)) {
- topa = topa_alloc(buf->cpu, gfp);
+ topa = topa_alloc(cpu, gfp);
if (!topa)
return -ENOMEM;
topa_insert_table(buf, topa);
}
+ if (topa->z_count == topa->last - 1) {
+ if (order == TOPA_ENTRY(topa, topa->last - 1)->size)
+ topa->z_count++;
+ }
+
TOPA_ENTRY(topa, -1)->base = page_to_phys(p) >> TOPA_SHIFT;
TOPA_ENTRY(topa, -1)->size = order;
- if (!buf->snapshot && !pt_cap_get(PT_CAP_topa_multiple_entries)) {
+ if (!buf->snapshot &&
+ !intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) {
TOPA_ENTRY(topa, -1)->intr = 1;
TOPA_ENTRY(topa, -1)->stop = 1;
}
@@ -712,23 +746,26 @@
struct topa *topa;
list_for_each_entry(topa, &buf->tables, list) {
+ struct topa_page *tp = topa_to_page(topa);
int i;
- pr_debug("# table @%p (%016Lx), off %llx size %zx\n", topa->table,
- topa->phys, topa->offset, topa->size);
+ pr_debug("# table @%p, off %llx size %zx\n", tp->table,
+ topa->offset, topa->size);
for (i = 0; i < TENTS_PER_PAGE; i++) {
pr_debug("# entry @%p (%lx sz %u %c%c%c) raw=%16llx\n",
- &topa->table[i],
- (unsigned long)topa->table[i].base << TOPA_SHIFT,
- sizes(topa->table[i].size),
- topa->table[i].end ? 'E' : ' ',
- topa->table[i].intr ? 'I' : ' ',
- topa->table[i].stop ? 'S' : ' ',
- *(u64 *)&topa->table[i]);
- if ((pt_cap_get(PT_CAP_topa_multiple_entries) &&
- topa->table[i].stop) ||
- topa->table[i].end)
+ &tp->table[i],
+ (unsigned long)tp->table[i].base << TOPA_SHIFT,
+ sizes(tp->table[i].size),
+ tp->table[i].end ? 'E' : ' ',
+ tp->table[i].intr ? 'I' : ' ',
+ tp->table[i].stop ? 'S' : ' ',
+ *(u64 *)&tp->table[i]);
+ if ((intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries) &&
+ tp->table[i].stop) ||
+ tp->table[i].end)
break;
+ if (!i && topa->z_count)
+ i += topa->z_count;
}
}
}
@@ -770,7 +807,7 @@
/* offset of the current output region within this table */
for (topa_idx = 0; topa_idx < buf->cur_idx; topa_idx++)
- base += sizes(buf->cur->table[topa_idx].size);
+ base += TOPA_ENTRY_SIZE(buf->cur, topa_idx);
if (buf->snapshot) {
local_set(&buf->data_size, base);
@@ -790,7 +827,7 @@
*/
static void *pt_buffer_region(struct pt_buffer *buf)
{
- return phys_to_virt(buf->cur->table[buf->cur_idx].base << TOPA_SHIFT);
+ return phys_to_virt(TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT);
}
/**
@@ -799,7 +836,7 @@
*/
static size_t pt_buffer_region_size(struct pt_buffer *buf)
{
- return sizes(buf->cur->table[buf->cur_idx].size);
+ return TOPA_ENTRY_SIZE(buf->cur, buf->cur_idx);
}
/**
@@ -828,8 +865,8 @@
* means we are already losing data; need to let the decoder
* know.
*/
- if (!pt_cap_get(PT_CAP_topa_multiple_entries) ||
- buf->output_off == sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) {
+ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries) ||
+ buf->output_off == pt_buffer_region_size(buf)) {
perf_aux_output_flag(&pt->handle,
PERF_AUX_FLAG_TRUNCATED);
advance++;
@@ -840,7 +877,8 @@
* Also on single-entry ToPA implementations, interrupt will come
* before the output reaches its output region's boundary.
*/
- if (!pt_cap_get(PT_CAP_topa_multiple_entries) && !buf->snapshot &&
+ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries) &&
+ !buf->snapshot &&
pt_buffer_region_size(buf) - buf->output_off <= TOPA_PMI_MARGIN) {
void *head = pt_buffer_region(buf);
@@ -866,9 +904,11 @@
static void pt_read_offset(struct pt_buffer *buf)
{
u64 offset, base_topa;
+ struct topa_page *tp;
rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, base_topa);
- buf->cur = phys_to_virt(base_topa);
+ tp = phys_to_virt(base_topa);
+ buf->cur = &tp->topa;
rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, offset);
/* offset within current output region */
@@ -877,29 +917,97 @@
buf->cur_idx = (offset & 0xffffff80) >> 7;
}
-/**
- * pt_topa_next_entry() - obtain index of the first page in the next ToPA entry
- * @buf: PT buffer.
- * @pg: Page offset in the buffer.
- *
- * When advancing to the next output region (ToPA entry), given a page offset
- * into the buffer, we need to find the offset of the first page in the next
- * region.
- */
-static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg)
+static struct topa_entry *
+pt_topa_entry_for_page(struct pt_buffer *buf, unsigned int pg)
{
- struct topa_entry *te = buf->topa_index[pg];
+ struct topa_page *tp;
+ struct topa *topa;
+ unsigned int idx, cur_pg = 0, z_pg = 0, start_idx = 0;
- /* one region */
- if (buf->first == buf->last && buf->first->last == 1)
- return pg;
+ /*
+ * Indicates a bug in the caller.
+ */
+ if (WARN_ON_ONCE(pg >= buf->nr_pages))
+ return NULL;
- do {
- pg++;
- pg &= buf->nr_pages - 1;
- } while (buf->topa_index[pg] == te);
+ /*
+ * First, find the ToPA table where @pg fits. With high
+ * order allocations, there shouldn't be many of these.
+ */
+ list_for_each_entry(topa, &buf->tables, list) {
+ if (topa->offset + topa->size > pg << PAGE_SHIFT)
+ goto found;
+ }
- return pg;
+ /*
+ * Hitting this means we have a problem in the ToPA
+ * allocation code.
+ */
+ WARN_ON_ONCE(1);
+
+ return NULL;
+
+found:
+ /*
+ * Indicates a problem in the ToPA allocation code.
+ */
+ if (WARN_ON_ONCE(topa->last == -1))
+ return NULL;
+
+ tp = topa_to_page(topa);
+ cur_pg = PFN_DOWN(topa->offset);
+ if (topa->z_count) {
+ z_pg = TOPA_ENTRY_PAGES(topa, 0) * (topa->z_count + 1);
+ start_idx = topa->z_count + 1;
+ }
+
+ /*
+ * Multiple entries at the beginning of the table have the same size,
+ * ideally all of them; if @pg falls there, the search is done.
+ */
+ if (pg >= cur_pg && pg < cur_pg + z_pg) {
+ idx = (pg - cur_pg) / TOPA_ENTRY_PAGES(topa, 0);
+ return &tp->table[idx];
+ }
+
+ /*
+ * Otherwise, slow path: iterate through the remaining entries.
+ */
+ for (idx = start_idx, cur_pg += z_pg; idx < topa->last; idx++) {
+ if (cur_pg + TOPA_ENTRY_PAGES(topa, idx) > pg)
+ return &tp->table[idx];
+
+ cur_pg += TOPA_ENTRY_PAGES(topa, idx);
+ }
+
+ /*
+ * Means we couldn't find a ToPA entry in the table that does match.
+ */
+ WARN_ON_ONCE(1);
+
+ return NULL;
+}
+
+static struct topa_entry *
+pt_topa_prev_entry(struct pt_buffer *buf, struct topa_entry *te)
+{
+ unsigned long table = (unsigned long)te & ~(PAGE_SIZE - 1);
+ struct topa_page *tp;
+ struct topa *topa;
+
+ tp = (struct topa_page *)table;
+ if (tp->table != te)
+ return --te;
+
+ topa = &tp->topa;
+ if (topa == buf->first)
+ topa = buf->last;
+ else
+ topa = list_prev_entry(topa, list);
+
+ tp = topa_to_page(topa);
+
+ return &tp->table[topa->last - 1];
}
/**
@@ -923,21 +1031,24 @@
unsigned long idx, npages, wakeup;
/* can't stop in the middle of an output region */
- if (buf->output_off + handle->size + 1 <
- sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) {
+ if (buf->output_off + handle->size + 1 < pt_buffer_region_size(buf)) {
perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
return -EINVAL;
}
/* single entry ToPA is handled by marking all regions STOP=1 INT=1 */
- if (!pt_cap_get(PT_CAP_topa_multiple_entries))
+ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
return 0;
/* clear STOP and INT from current entry */
- buf->topa_index[buf->stop_pos]->stop = 0;
- buf->topa_index[buf->stop_pos]->intr = 0;
- buf->topa_index[buf->intr_pos]->intr = 0;
+ if (buf->stop_te) {
+ buf->stop_te->stop = 0;
+ buf->stop_te->intr = 0;
+ }
+
+ if (buf->intr_te)
+ buf->intr_te->intr = 0;
/* how many pages till the STOP marker */
npages = handle->size >> PAGE_SHIFT;
@@ -948,7 +1059,12 @@
idx = (head >> PAGE_SHIFT) + npages;
idx &= buf->nr_pages - 1;
- buf->stop_pos = idx;
+
+ if (idx != buf->stop_pos) {
+ buf->stop_pos = idx;
+ buf->stop_te = pt_topa_entry_for_page(buf, idx);
+ buf->stop_te = pt_topa_prev_entry(buf, buf->stop_te);
+ }
wakeup = handle->wakeup >> PAGE_SHIFT;
@@ -958,48 +1074,17 @@
idx = wakeup;
idx &= buf->nr_pages - 1;
- buf->intr_pos = idx;
-
- buf->topa_index[buf->stop_pos]->stop = 1;
- buf->topa_index[buf->stop_pos]->intr = 1;
- buf->topa_index[buf->intr_pos]->intr = 1;
-
- return 0;
-}
-
-/**
- * pt_buffer_setup_topa_index() - build topa_index[] table of regions
- * @buf: PT buffer.
- *
- * topa_index[] references output regions indexed by offset into the
- * buffer for purposes of quick reverse lookup.
- */
-static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
-{
- struct topa *cur = buf->first, *prev = buf->last;
- struct topa_entry *te_cur = TOPA_ENTRY(cur, 0),
- *te_prev = TOPA_ENTRY(prev, prev->last - 1);
- int pg = 0, idx = 0;
-
- while (pg < buf->nr_pages) {
- int tidx;
-
- /* pages within one topa entry */
- for (tidx = 0; tidx < 1 << te_cur->size; tidx++, pg++)
- buf->topa_index[pg] = te_prev;
-
- te_prev = te_cur;
-
- if (idx == cur->last - 1) {
- /* advance to next topa table */
- idx = 0;
- cur = list_entry(cur->list.next, struct topa, list);
- } else {
- idx++;
- }
- te_cur = TOPA_ENTRY(cur, idx);
+ if (idx != buf->intr_pos) {
+ buf->intr_pos = idx;
+ buf->intr_te = pt_topa_entry_for_page(buf, idx);
+ buf->intr_te = pt_topa_prev_entry(buf, buf->intr_te);
}
+ buf->stop_te->stop = 1;
+ buf->stop_te->intr = 1;
+ buf->intr_te->intr = 1;
+
+ return 0;
}
/**
@@ -1019,18 +1104,20 @@
*/
static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head)
{
+ struct topa_page *cur_tp;
+ struct topa_entry *te;
int pg;
if (buf->snapshot)
head &= (buf->nr_pages << PAGE_SHIFT) - 1;
pg = (head >> PAGE_SHIFT) & (buf->nr_pages - 1);
- pg = pt_topa_next_entry(buf, pg);
+ te = pt_topa_entry_for_page(buf, pg);
- buf->cur = (struct topa *)((unsigned long)buf->topa_index[pg] & PAGE_MASK);
- buf->cur_idx = ((unsigned long)buf->topa_index[pg] -
- (unsigned long)buf->cur) / sizeof(struct topa_entry);
- buf->output_off = head & (sizes(buf->cur->table[buf->cur_idx].size) - 1);
+ cur_tp = topa_entry_to_page(te);
+ buf->cur = &cur_tp->topa;
+ buf->cur_idx = te - TOPA_ENTRY(buf->cur, 0);
+ buf->output_off = head & (pt_buffer_region_size(buf) - 1);
local64_set(&buf->head, head);
local_set(&buf->data_size, 0);
@@ -1059,31 +1146,29 @@
* @size: Total size of all regions within this ToPA.
* @gfp: Allocation flags.
*/
-static int pt_buffer_init_topa(struct pt_buffer *buf, unsigned long nr_pages,
- gfp_t gfp)
+static int pt_buffer_init_topa(struct pt_buffer *buf, int cpu,
+ unsigned long nr_pages, gfp_t gfp)
{
struct topa *topa;
int err;
- topa = topa_alloc(buf->cpu, gfp);
+ topa = topa_alloc(cpu, gfp);
if (!topa)
return -ENOMEM;
topa_insert_table(buf, topa);
while (buf->nr_pages < nr_pages) {
- err = topa_insert_pages(buf, gfp);
+ err = topa_insert_pages(buf, cpu, gfp);
if (err) {
pt_buffer_fini_topa(buf);
return -ENOMEM;
}
}
- pt_buffer_setup_topa_index(buf);
-
/* link last table to the first one, unless we're double buffering */
- if (pt_cap_get(PT_CAP_topa_multiple_entries)) {
- TOPA_ENTRY(buf->last, -1)->base = buf->first->phys >> TOPA_SHIFT;
+ if (intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) {
+ TOPA_ENTRY(buf->last, -1)->base = topa_pfn(buf->first);
TOPA_ENTRY(buf->last, -1)->end = 1;
}
@@ -1104,10 +1189,11 @@
* Return: Our private PT buffer structure.
*/
static void *
-pt_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool snapshot)
+pt_buffer_setup_aux(struct perf_event *event, void **pages,
+ int nr_pages, bool snapshot)
{
struct pt_buffer *buf;
- int node, ret;
+ int node, ret, cpu = event->cpu;
if (!nr_pages)
return NULL;
@@ -1116,18 +1202,18 @@
cpu = raw_smp_processor_id();
node = cpu_to_node(cpu);
- buf = kzalloc_node(offsetof(struct pt_buffer, topa_index[nr_pages]),
- GFP_KERNEL, node);
+ buf = kzalloc_node(sizeof(struct pt_buffer), GFP_KERNEL, node);
if (!buf)
return NULL;
- buf->cpu = cpu;
buf->snapshot = snapshot;
buf->data_pages = pages;
+ buf->stop_pos = -1;
+ buf->intr_pos = -1;
INIT_LIST_HEAD(&buf->tables);
- ret = pt_buffer_init_topa(buf, nr_pages, GFP_KERNEL);
+ ret = pt_buffer_init_topa(buf, cpu, nr_pages, GFP_KERNEL);
if (ret) {
kfree(buf);
return NULL;
@@ -1153,7 +1239,7 @@
struct pt_filters *filters;
int node = event->cpu == -1 ? -1 : cpu_to_node(event->cpu);
- if (!pt_cap_get(PT_CAP_num_address_ranges))
+ if (!intel_pt_validate_hw_cap(PT_CAP_num_address_ranges))
return 0;
filters = kzalloc_node(sizeof(struct pt_filters), GFP_KERNEL, node);
@@ -1202,7 +1288,7 @@
return -EINVAL;
}
- if (++range > pt_cap_get(PT_CAP_num_address_ranges))
+ if (++range > intel_pt_validate_hw_cap(PT_CAP_num_address_ranges))
return -EOPNOTSUPP;
}
@@ -1212,7 +1298,8 @@
static void pt_event_addr_filters_sync(struct perf_event *event)
{
struct perf_addr_filters_head *head = perf_event_addr_filters(event);
- unsigned long msr_a, msr_b, *offs = event->addr_filters_offs;
+ unsigned long msr_a, msr_b;
+ struct perf_addr_filter_range *fr = event->addr_filter_ranges;
struct pt_filters *filters = event->hw.addr_filters;
struct perf_addr_filter *filter;
int range = 0;
@@ -1221,12 +1308,12 @@
return;
list_for_each_entry(filter, &head->list, entry) {
- if (filter->path.dentry && !offs[range]) {
+ if (filter->path.dentry && !fr[range].start) {
msr_a = msr_b = 0;
} else {
/* apply the offset */
- msr_a = filter->offset + offs[range];
- msr_b = filter->size + msr_a - 1;
+ msr_a = fr[range].start;
+ msr_b = msr_a + fr[range].size - 1;
}
filters->filter[range].msr_a = msr_a;
@@ -1292,7 +1379,7 @@
return;
}
- pt_config_buffer(buf->cur->table, buf->cur_idx,
+ pt_config_buffer(topa_to_page(buf->cur)->table, buf->cur_idx,
buf->output_off);
pt_config(event);
}
@@ -1357,7 +1444,7 @@
WRITE_ONCE(pt->handle_nmi, 1);
hwc->state = 0;
- pt_config_buffer(buf->cur->table, buf->cur_idx,
+ pt_config_buffer(topa_to_page(buf->cur)->table, buf->cur_idx,
buf->output_off);
pt_config(event);
@@ -1477,6 +1564,11 @@
pt_event_stop(pt->handle.event, PERF_EF_UPDATE);
}
+int is_intel_pt_event(struct perf_event *event)
+{
+ return event->pmu == &pt_pmu.pmu;
+}
+
static __init int pt_init(void)
{
int ret, cpu, prior_warn = 0;
@@ -1507,14 +1599,13 @@
if (ret)
return ret;
- if (!pt_cap_get(PT_CAP_topa_output)) {
+ if (!intel_pt_validate_hw_cap(PT_CAP_topa_output)) {
pr_warn("ToPA output is not supported on this CPU\n");
return -ENODEV;
}
- if (!pt_cap_get(PT_CAP_topa_multiple_entries))
- pt_pmu.pmu.capabilities =
- PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF;
+ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
+ pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
pt_pmu.pmu.attr_groups = pt_attr_groups;
@@ -1530,7 +1621,7 @@
pt_pmu.pmu.addr_filters_sync = pt_event_addr_filters_sync;
pt_pmu.pmu.addr_filters_validate = pt_event_addr_filters_validate;
pt_pmu.pmu.nr_addr_filters =
- pt_cap_get(PT_CAP_num_address_ranges);
+ intel_pt_validate_hw_cap(PT_CAP_num_address_ranges);
ret = perf_pmu_register(&pt_pmu.pmu, "intel_pt", -1);
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index 0eb41d0..1d2bb75 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -1,16 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Intel(R) Processor Trace PMU driver for perf
* Copyright (c) 2013-2014, Intel Corporation.
*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
* Intel PT is specified in the Intel Architecture Instruction Set Extensions
* Programming Reference:
* http://software.intel.com/en-us/intel-isa-extensions
@@ -20,43 +12,6 @@
#define __INTEL_PT_H__
/*
- * PT MSR bit definitions
- */
-#define RTIT_CTL_TRACEEN BIT(0)
-#define RTIT_CTL_CYCLEACC BIT(1)
-#define RTIT_CTL_OS BIT(2)
-#define RTIT_CTL_USR BIT(3)
-#define RTIT_CTL_PWR_EVT_EN BIT(4)
-#define RTIT_CTL_FUP_ON_PTW BIT(5)
-#define RTIT_CTL_CR3EN BIT(7)
-#define RTIT_CTL_TOPA BIT(8)
-#define RTIT_CTL_MTC_EN BIT(9)
-#define RTIT_CTL_TSC_EN BIT(10)
-#define RTIT_CTL_DISRETC BIT(11)
-#define RTIT_CTL_PTW_EN BIT(12)
-#define RTIT_CTL_BRANCH_EN BIT(13)
-#define RTIT_CTL_MTC_RANGE_OFFSET 14
-#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
-#define RTIT_CTL_CYC_THRESH_OFFSET 19
-#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET)
-#define RTIT_CTL_PSB_FREQ_OFFSET 24
-#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET)
-#define RTIT_CTL_ADDR0_OFFSET 32
-#define RTIT_CTL_ADDR0 (0x0full << RTIT_CTL_ADDR0_OFFSET)
-#define RTIT_CTL_ADDR1_OFFSET 36
-#define RTIT_CTL_ADDR1 (0x0full << RTIT_CTL_ADDR1_OFFSET)
-#define RTIT_CTL_ADDR2_OFFSET 40
-#define RTIT_CTL_ADDR2 (0x0full << RTIT_CTL_ADDR2_OFFSET)
-#define RTIT_CTL_ADDR3_OFFSET 44
-#define RTIT_CTL_ADDR3 (0x0full << RTIT_CTL_ADDR3_OFFSET)
-#define RTIT_STATUS_FILTEREN BIT(0)
-#define RTIT_STATUS_CONTEXTEN BIT(1)
-#define RTIT_STATUS_TRIGGEREN BIT(2)
-#define RTIT_STATUS_BUFFOVF BIT(3)
-#define RTIT_STATUS_ERROR BIT(4)
-#define RTIT_STATUS_STOPPED BIT(5)
-
-/*
* Single-entry ToPA: when this close to region boundary, switch
* buffers to avoid losing data.
*/
@@ -82,30 +37,9 @@
u64 rsvd4 : 16;
};
-#define PT_CPUID_LEAVES 2
-#define PT_CPUID_REGS_NUM 4 /* number of regsters (eax, ebx, ecx, edx) */
-
/* TSC to Core Crystal Clock Ratio */
#define CPUID_TSC_LEAF 0x15
-enum pt_capabilities {
- PT_CAP_max_subleaf = 0,
- PT_CAP_cr3_filtering,
- PT_CAP_psb_cyc,
- PT_CAP_ip_filtering,
- PT_CAP_mtc,
- PT_CAP_ptwrite,
- PT_CAP_power_event_trace,
- PT_CAP_topa_output,
- PT_CAP_topa_multiple_entries,
- PT_CAP_single_range_output,
- PT_CAP_payloads_lip,
- PT_CAP_num_address_ranges,
- PT_CAP_mtc_periods,
- PT_CAP_cycle_thresholds,
- PT_CAP_psb_periods,
-};
-
struct pt_pmu {
struct pmu pmu;
u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
@@ -119,7 +53,6 @@
/**
* struct pt_buffer - buffer configuration; one buffer per task_struct or
* cpu, depending on perf event configuration
- * @cpu: cpu for per-cpu allocation
* @tables: list of ToPA tables in this buffer
* @first: shorthand for first topa table
* @last: shorthand for last topa table
@@ -131,13 +64,14 @@
* @lost: if data was lost/truncated
* @head: logical write offset inside the buffer
* @snapshot: if this is for a snapshot/overwrite counter
- * @stop_pos: STOP topa entry in the buffer
- * @intr_pos: INT topa entry in the buffer
+ * @stop_pos: STOP topa entry index
+ * @intr_pos: INT topa entry index
+ * @stop_te: STOP topa entry pointer
+ * @intr_te: INT topa entry pointer
* @data_pages: array of pages from perf
* @topa_index: table of topa entries indexed by page offset
*/
struct pt_buffer {
- int cpu;
struct list_head tables;
struct topa *first, *last, *cur;
unsigned int cur_idx;
@@ -146,9 +80,9 @@
local_t data_size;
local64_t head;
bool snapshot;
- unsigned long stop_pos, intr_pos;
+ long stop_pos, intr_pos;
+ struct topa_entry *stop_te, *intr_te;
void **data_pages;
- struct topa_entry *topa_index[0];
};
#define PT_FILTERS_NUM 4
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 32f3e94..5053a40 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Support Intel RAPL energy consumption counters
* Copyright (C) 2013 Google, Inc., Stephane Eranian
@@ -54,27 +55,28 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
+#include <linux/nospec.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include "../perf_event.h"
+#include "../probe.h"
MODULE_LICENSE("GPL");
/*
* RAPL energy status counters
*/
-#define RAPL_IDX_PP0_NRG_STAT 0 /* all cores */
-#define INTEL_RAPL_PP0 0x1 /* pseudo-encoding */
-#define RAPL_IDX_PKG_NRG_STAT 1 /* entire package */
-#define INTEL_RAPL_PKG 0x2 /* pseudo-encoding */
-#define RAPL_IDX_RAM_NRG_STAT 2 /* DRAM */
-#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */
-#define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */
-#define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */
-#define RAPL_IDX_PSYS_NRG_STAT 4 /* psys */
-#define INTEL_RAPL_PSYS 0x5 /* pseudo-encoding */
+enum perf_rapl_events {
+ PERF_RAPL_PP0 = 0, /* all cores */
+ PERF_RAPL_PKG, /* entire package */
+ PERF_RAPL_RAM, /* DRAM */
+ PERF_RAPL_PP1, /* gpu */
+ PERF_RAPL_PSYS, /* psys */
-#define NR_RAPL_DOMAINS 0x5
+ PERF_RAPL_MAX,
+ NR_RAPL_DOMAINS = PERF_RAPL_MAX,
+};
+
static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
"pp0-core",
"package",
@@ -83,33 +85,6 @@
"psys",
};
-/* Clients have PP0, PKG */
-#define RAPL_IDX_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_PP1_NRG_STAT)
-
-/* Servers have PP0, PKG, RAM */
-#define RAPL_IDX_SRV (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT)
-
-/* Servers have PP0, PKG, RAM, PP1 */
-#define RAPL_IDX_HSW (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT|\
- 1<<RAPL_IDX_PP1_NRG_STAT)
-
-/* SKL clients have PP0, PKG, RAM, PP1, PSYS */
-#define RAPL_IDX_SKL_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
- 1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT|\
- 1<<RAPL_IDX_PP1_NRG_STAT|\
- 1<<RAPL_IDX_PSYS_NRG_STAT)
-
-/* Knights Landing has PKG, RAM */
-#define RAPL_IDX_KNL (1<<RAPL_IDX_PKG_NRG_STAT|\
- 1<<RAPL_IDX_RAM_NRG_STAT)
-
/*
* event code: LSB 8 bits, passed in attr->config
* any other bit is reserved
@@ -148,26 +123,32 @@
struct rapl_pmus {
struct pmu pmu;
- unsigned int maxpkg;
+ unsigned int maxdie;
struct rapl_pmu *pmus[];
};
+struct rapl_model {
+ unsigned long events;
+ bool apply_quirk;
+};
+
/* 1/2^hw_unit Joule */
static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;
static struct rapl_pmus *rapl_pmus;
static cpumask_t rapl_cpu_mask;
static unsigned int rapl_cntr_mask;
static u64 rapl_timer_ms;
+static struct perf_msr rapl_msrs[];
static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
{
- unsigned int pkgid = topology_logical_package_id(cpu);
+ unsigned int dieid = topology_logical_die_id(cpu);
/*
* The unsigned check also catches the '-1' return value for non
* existent mappings in the topology map.
*/
- return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
+ return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL;
}
static inline u64 rapl_read_counter(struct perf_event *event)
@@ -349,7 +330,7 @@
static int rapl_pmu_event_init(struct perf_event *event)
{
u64 cfg = event->attr.config & RAPL_EVENT_MASK;
- int bit, msr, ret = 0;
+ int bit, ret = 0;
struct rapl_pmu *pmu;
/* only look at RAPL events */
@@ -365,45 +346,18 @@
event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
- /*
- * check event is known (determines counter)
- */
- switch (cfg) {
- case INTEL_RAPL_PP0:
- bit = RAPL_IDX_PP0_NRG_STAT;
- msr = MSR_PP0_ENERGY_STATUS;
- break;
- case INTEL_RAPL_PKG:
- bit = RAPL_IDX_PKG_NRG_STAT;
- msr = MSR_PKG_ENERGY_STATUS;
- break;
- case INTEL_RAPL_RAM:
- bit = RAPL_IDX_RAM_NRG_STAT;
- msr = MSR_DRAM_ENERGY_STATUS;
- break;
- case INTEL_RAPL_PP1:
- bit = RAPL_IDX_PP1_NRG_STAT;
- msr = MSR_PP1_ENERGY_STATUS;
- break;
- case INTEL_RAPL_PSYS:
- bit = RAPL_IDX_PSYS_NRG_STAT;
- msr = MSR_PLATFORM_ENERGY_STATUS;
- break;
- default:
+ if (!cfg || cfg >= NR_RAPL_DOMAINS + 1)
return -EINVAL;
- }
+
+ cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1);
+ bit = cfg - 1;
+
/* check event supported */
if (!(rapl_cntr_mask & (1 << bit)))
return -EINVAL;
/* unsupported modes and filters */
- if (event->attr.exclude_user ||
- event->attr.exclude_kernel ||
- event->attr.exclude_hv ||
- event->attr.exclude_idle ||
- event->attr.exclude_host ||
- event->attr.exclude_guest ||
- event->attr.sample_period) /* no sampling */
+ if (event->attr.sample_period) /* no sampling */
return -EINVAL;
/* must be done before validate_group */
@@ -412,7 +366,7 @@
return -EINVAL;
event->cpu = pmu->cpu;
event->pmu_private = pmu;
- event->hw.event_base = msr;
+ event->hw.event_base = rapl_msrs[bit].msr;
event->hw.config = cfg;
event->hw.idx = bit;
@@ -462,90 +416,18 @@
RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10");
RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10");
-static struct attribute *rapl_events_srv_attr[] = {
- EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_ram),
-
- EVENT_PTR(rapl_cores_unit),
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_ram_unit),
-
- EVENT_PTR(rapl_cores_scale),
- EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_ram_scale),
- NULL,
-};
-
-static struct attribute *rapl_events_cln_attr[] = {
- EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_gpu),
-
- EVENT_PTR(rapl_cores_unit),
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_gpu_unit),
-
- EVENT_PTR(rapl_cores_scale),
- EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_gpu_scale),
- NULL,
-};
-
-static struct attribute *rapl_events_hsw_attr[] = {
- EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_gpu),
- EVENT_PTR(rapl_ram),
-
- EVENT_PTR(rapl_cores_unit),
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_gpu_unit),
- EVENT_PTR(rapl_ram_unit),
-
- EVENT_PTR(rapl_cores_scale),
- EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_gpu_scale),
- EVENT_PTR(rapl_ram_scale),
- NULL,
-};
-
-static struct attribute *rapl_events_skl_attr[] = {
- EVENT_PTR(rapl_cores),
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_gpu),
- EVENT_PTR(rapl_ram),
- EVENT_PTR(rapl_psys),
-
- EVENT_PTR(rapl_cores_unit),
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_gpu_unit),
- EVENT_PTR(rapl_ram_unit),
- EVENT_PTR(rapl_psys_unit),
-
- EVENT_PTR(rapl_cores_scale),
- EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_gpu_scale),
- EVENT_PTR(rapl_ram_scale),
- EVENT_PTR(rapl_psys_scale),
- NULL,
-};
-
-static struct attribute *rapl_events_knl_attr[] = {
- EVENT_PTR(rapl_pkg),
- EVENT_PTR(rapl_ram),
-
- EVENT_PTR(rapl_pkg_unit),
- EVENT_PTR(rapl_ram_unit),
-
- EVENT_PTR(rapl_pkg_scale),
- EVENT_PTR(rapl_ram_scale),
+/*
+ * There are no default events, but we need to create
+ * "events" group (with empty attrs) before updating
+ * it with detected events.
+ */
+static struct attribute *attrs_empty[] = {
NULL,
};
static struct attribute_group rapl_pmu_events_group = {
.name = "events",
- .attrs = NULL, /* patched at runtime */
+ .attrs = attrs_empty,
};
DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
@@ -566,6 +448,79 @@
NULL,
};
+static struct attribute *rapl_events_cores[] = {
+ EVENT_PTR(rapl_cores),
+ EVENT_PTR(rapl_cores_unit),
+ EVENT_PTR(rapl_cores_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_cores_group = {
+ .name = "events",
+ .attrs = rapl_events_cores,
+};
+
+static struct attribute *rapl_events_pkg[] = {
+ EVENT_PTR(rapl_pkg),
+ EVENT_PTR(rapl_pkg_unit),
+ EVENT_PTR(rapl_pkg_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_pkg_group = {
+ .name = "events",
+ .attrs = rapl_events_pkg,
+};
+
+static struct attribute *rapl_events_ram[] = {
+ EVENT_PTR(rapl_ram),
+ EVENT_PTR(rapl_ram_unit),
+ EVENT_PTR(rapl_ram_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_ram_group = {
+ .name = "events",
+ .attrs = rapl_events_ram,
+};
+
+static struct attribute *rapl_events_gpu[] = {
+ EVENT_PTR(rapl_gpu),
+ EVENT_PTR(rapl_gpu_unit),
+ EVENT_PTR(rapl_gpu_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_gpu_group = {
+ .name = "events",
+ .attrs = rapl_events_gpu,
+};
+
+static struct attribute *rapl_events_psys[] = {
+ EVENT_PTR(rapl_psys),
+ EVENT_PTR(rapl_psys_unit),
+ EVENT_PTR(rapl_psys_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_events_psys_group = {
+ .name = "events",
+ .attrs = rapl_events_psys,
+};
+
+static bool test_msr(int idx, void *data)
+{
+ return test_bit(idx, (unsigned long *) data);
+}
+
+static struct perf_msr rapl_msrs[] = {
+ [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr },
+ [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr },
+ [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr },
+ [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr },
+ [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr },
+};
+
static int rapl_cpu_offline(unsigned int cpu)
{
struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
@@ -577,7 +532,7 @@
pmu->cpu = -1;
/* Find a new cpu to collect rapl events */
- target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+ target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
/* Migrate rapl events to the new target */
if (target < nr_cpu_ids) {
@@ -604,14 +559,14 @@
pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
rapl_hrtimer_init(pmu);
- rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+ rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu;
}
/*
* Check if there is an online cpu in the package which collects rapl
* events already.
*/
- target = cpumask_any_and(&rapl_cpu_mask, topology_core_cpumask(cpu));
+ target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu));
if (target < nr_cpu_ids)
return 0;
@@ -638,7 +593,7 @@
* of 2. Datasheet, September 2014, Reference Number: 330784-001 "
*/
if (apply_quirk)
- rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16;
+ rapl_hw_unit[PERF_RAPL_RAM] = 16;
/*
* Calculate the timer rate:
@@ -674,23 +629,33 @@
{
int i;
- for (i = 0; i < rapl_pmus->maxpkg; i++)
+ for (i = 0; i < rapl_pmus->maxdie; i++)
kfree(rapl_pmus->pmus[i]);
kfree(rapl_pmus);
}
+static const struct attribute_group *rapl_attr_update[] = {
+ &rapl_events_cores_group,
+ &rapl_events_pkg_group,
+ &rapl_events_ram_group,
+ &rapl_events_gpu_group,
+ &rapl_events_gpu_group,
+ NULL,
+};
+
static int __init init_rapl_pmus(void)
{
- int maxpkg = topology_max_packages();
+ int maxdie = topology_max_packages() * topology_max_die_per_package();
size_t size;
- size = sizeof(*rapl_pmus) + maxpkg * sizeof(struct rapl_pmu *);
+ size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *);
rapl_pmus = kzalloc(size, GFP_KERNEL);
if (!rapl_pmus)
return -ENOMEM;
- rapl_pmus->maxpkg = maxpkg;
+ rapl_pmus->maxdie = maxdie;
rapl_pmus->pmu.attr_groups = rapl_attr_groups;
+ rapl_pmus->pmu.attr_update = rapl_attr_update;
rapl_pmus->pmu.task_ctx_nr = perf_invalid_context;
rapl_pmus->pmu.event_init = rapl_pmu_event_init;
rapl_pmus->pmu.add = rapl_pmu_event_add;
@@ -699,109 +664,103 @@
rapl_pmus->pmu.stop = rapl_pmu_event_stop;
rapl_pmus->pmu.read = rapl_pmu_event_read;
rapl_pmus->pmu.module = THIS_MODULE;
+ rapl_pmus->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE;
return 0;
}
#define X86_RAPL_MODEL_MATCH(model, init) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
-struct intel_rapl_init_fun {
- bool apply_quirk;
- int cntr_mask;
- struct attribute **attrs;
+static struct rapl_model model_snb = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_PP1),
+ .apply_quirk = false,
};
-static const struct intel_rapl_init_fun snb_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_CLN,
- .attrs = rapl_events_cln_attr,
+static struct rapl_model model_snbep = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = false,
};
-static const struct intel_rapl_init_fun hsx_rapl_init __initconst = {
- .apply_quirk = true,
- .cntr_mask = RAPL_IDX_SRV,
- .attrs = rapl_events_srv_attr,
+static struct rapl_model model_hsw = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM) |
+ BIT(PERF_RAPL_PP1),
+ .apply_quirk = false,
};
-static const struct intel_rapl_init_fun hsw_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_HSW,
- .attrs = rapl_events_hsw_attr,
+static struct rapl_model model_hsx = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = true,
};
-static const struct intel_rapl_init_fun snbep_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_SRV,
- .attrs = rapl_events_srv_attr,
+static struct rapl_model model_knl = {
+ .events = BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM),
+ .apply_quirk = true,
};
-static const struct intel_rapl_init_fun knl_rapl_init __initconst = {
- .apply_quirk = true,
- .cntr_mask = RAPL_IDX_KNL,
- .attrs = rapl_events_knl_attr,
+static struct rapl_model model_skl = {
+ .events = BIT(PERF_RAPL_PP0) |
+ BIT(PERF_RAPL_PKG) |
+ BIT(PERF_RAPL_RAM) |
+ BIT(PERF_RAPL_PP1) |
+ BIT(PERF_RAPL_PSYS),
+ .apply_quirk = false,
};
-static const struct intel_rapl_init_fun skl_rapl_init __initconst = {
- .apply_quirk = false,
- .cntr_mask = RAPL_IDX_SKL_CLN,
- .attrs = rapl_events_skl_attr,
-};
-
-static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, snb_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, snbep_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, snb_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, snbep_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hsx_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, hsx_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsx_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, hsx_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_MOBILE, skl_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init),
-
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init),
+static const struct x86_cpu_id rapl_model_match[] __initconst = {
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, model_snb),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, model_snbep),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, model_snb),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, model_snbep),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_L, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_G, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_G, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_D, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, model_knl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, model_knl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_L, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, model_hsx),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_L, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_L, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_D, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, model_hsw),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_L, model_skl),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE, model_skl),
{},
};
-MODULE_DEVICE_TABLE(x86cpu, rapl_cpu_match);
+MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
static int __init rapl_pmu_init(void)
{
const struct x86_cpu_id *id;
- struct intel_rapl_init_fun *rapl_init;
- bool apply_quirk;
+ struct rapl_model *rm;
int ret;
- id = x86_match_cpu(rapl_cpu_match);
+ id = x86_match_cpu(rapl_model_match);
if (!id)
return -ENODEV;
- rapl_init = (struct intel_rapl_init_fun *)id->driver_data;
- apply_quirk = rapl_init->apply_quirk;
- rapl_cntr_mask = rapl_init->cntr_mask;
- rapl_pmu_events_group.attrs = rapl_init->attrs;
+ rm = (struct rapl_model *) id->driver_data;
+ rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX,
+ false, (void *) &rm->events);
- ret = rapl_check_hw_unit(apply_quirk);
+ ret = rapl_check_hw_unit(rm->apply_quirk);
if (ret)
return ret;
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 27a4614..86467f8 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
#include <linux/module.h>
#include <asm/cpu_device_id.h>
@@ -7,6 +8,7 @@
static struct intel_uncore_type *empty_uncore[] = { NULL, };
struct intel_uncore_type **uncore_msr_uncores = empty_uncore;
struct intel_uncore_type **uncore_pci_uncores = empty_uncore;
+struct intel_uncore_type **uncore_mmio_uncores = empty_uncore;
static bool pcidrv_registered;
struct pci_driver *uncore_pci_driver;
@@ -14,7 +16,7 @@
DEFINE_RAW_SPINLOCK(pci2phy_map_lock);
struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head);
struct pci_extra_dev *uncore_extra_pci_dev;
-static int max_packages;
+static int max_dies;
/* mask of cpus that collect uncore events */
static cpumask_t uncore_cpu_mask;
@@ -27,7 +29,7 @@
MODULE_LICENSE("GPL");
-static int uncore_pcibus_to_physid(struct pci_bus *bus)
+int uncore_pcibus_to_physid(struct pci_bus *bus)
{
struct pci2phy_map *map;
int phys_id = -1;
@@ -100,13 +102,13 @@
struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
{
- unsigned int pkgid = topology_logical_package_id(cpu);
+ unsigned int dieid = topology_logical_die_id(cpu);
/*
* The unsigned check also catches the '-1' return value for non
* existent mappings in the topology map.
*/
- return pkgid < max_packages ? pmu->boxes[pkgid] : NULL;
+ return dieid < max_dies ? pmu->boxes[dieid] : NULL;
}
u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
@@ -118,6 +120,21 @@
return count;
}
+void uncore_mmio_exit_box(struct intel_uncore_box *box)
+{
+ if (box->io_addr)
+ iounmap(box->io_addr);
+}
+
+u64 uncore_mmio_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ if (!box->io_addr)
+ return 0;
+
+ return readq(box->io_addr + event->hw.event_base);
+}
+
/*
* generic get constraint function for shared match/mask registers.
*/
@@ -311,7 +328,7 @@
uncore_pmu_init_hrtimer(box);
box->cpu = -1;
box->pci_phys_id = -1;
- box->pkgid = -1;
+ box->dieid = -1;
/* set default hrtimer timeout */
box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL;
@@ -485,10 +502,8 @@
local64_set(&event->hw.prev_count, uncore_read_counter(box, event));
uncore_enable_event(box, event);
- if (box->n_active == 1) {
- uncore_enable_box(box);
+ if (box->n_active == 1)
uncore_pmu_start_hrtimer(box);
- }
}
void uncore_pmu_event_stop(struct perf_event *event, int flags)
@@ -512,10 +527,8 @@
WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
hwc->state |= PERF_HES_STOPPED;
- if (box->n_active == 0) {
- uncore_disable_box(box);
+ if (box->n_active == 0)
uncore_pmu_cancel_hrtimer(box);
- }
}
if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
@@ -695,14 +708,6 @@
if (pmu->func_id < 0)
return -ENOENT;
- /*
- * Uncore PMU does measure at all privilege level all the time.
- * So it doesn't make sense to specify any exclude bits.
- */
- if (event->attr.exclude_user || event->attr.exclude_kernel ||
- event->attr.exclude_hv || event->attr.exclude_idle)
- return -EINVAL;
-
/* Sampling not supported yet */
if (hwc->sample_period)
return -EINVAL;
@@ -740,6 +745,7 @@
/* fixed counters have event field hardcoded to zero */
hwc->config = 0ULL;
} else if (is_freerunning_event(event)) {
+ hwc->config = event->attr.config;
if (!check_valid_freerunning_event(box, event))
return -EINVAL;
event->hw.idx = UNCORE_PMC_IDX_FREERUNNING;
@@ -768,6 +774,40 @@
return ret;
}
+static void uncore_pmu_enable(struct pmu *pmu)
+{
+ struct intel_uncore_pmu *uncore_pmu;
+ struct intel_uncore_box *box;
+
+ uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
+ if (!uncore_pmu)
+ return;
+
+ box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
+ if (!box)
+ return;
+
+ if (uncore_pmu->type->ops->enable_box)
+ uncore_pmu->type->ops->enable_box(box);
+}
+
+static void uncore_pmu_disable(struct pmu *pmu)
+{
+ struct intel_uncore_pmu *uncore_pmu;
+ struct intel_uncore_box *box;
+
+ uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
+ if (!uncore_pmu)
+ return;
+
+ box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
+ if (!box)
+ return;
+
+ if (uncore_pmu->type->ops->disable_box)
+ uncore_pmu->type->ops->disable_box(box);
+}
+
static ssize_t uncore_get_attr_cpumask(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -793,6 +833,8 @@
pmu->pmu = (struct pmu) {
.attr_groups = pmu->type->attr_groups,
.task_ctx_nr = perf_invalid_context,
+ .pmu_enable = uncore_pmu_enable,
+ .pmu_disable = uncore_pmu_disable,
.event_init = uncore_pmu_event_init,
.add = uncore_pmu_event_add,
.del = uncore_pmu_event_del,
@@ -800,6 +842,7 @@
.stop = uncore_pmu_event_stop,
.read = uncore_pmu_event_read,
.module = THIS_MODULE,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
} else {
pmu->pmu = *pmu->type->pmu;
@@ -832,10 +875,10 @@
static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
{
- int pkg;
+ int die;
- for (pkg = 0; pkg < max_packages; pkg++)
- kfree(pmu->boxes[pkg]);
+ for (die = 0; die < max_dies; die++)
+ kfree(pmu->boxes[die]);
kfree(pmu->boxes);
}
@@ -872,7 +915,7 @@
if (!pmus)
return -ENOMEM;
- size = max_packages * sizeof(struct intel_uncore_box *);
+ size = max_dies * sizeof(struct intel_uncore_box *);
for (i = 0; i < type->num_boxes; i++) {
pmus[i].func_id = setid ? i : -1;
@@ -942,20 +985,21 @@
struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu = NULL;
struct intel_uncore_box *box;
- int phys_id, pkg, ret;
+ int phys_id, die, ret;
phys_id = uncore_pcibus_to_physid(pdev->bus);
if (phys_id < 0)
return -ENODEV;
- pkg = topology_phys_to_logical_pkg(phys_id);
- if (pkg < 0)
+ die = (topology_max_die_per_package() > 1) ? phys_id :
+ topology_phys_to_logical_pkg(phys_id);
+ if (die < 0)
return -EINVAL;
if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
int idx = UNCORE_PCI_DEV_IDX(id->driver_data);
- uncore_extra_pci_dev[pkg].dev[idx] = pdev;
+ uncore_extra_pci_dev[die].dev[idx] = pdev;
pci_set_drvdata(pdev, NULL);
return 0;
}
@@ -994,7 +1038,7 @@
pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
}
- if (WARN_ON_ONCE(pmu->boxes[pkg] != NULL))
+ if (WARN_ON_ONCE(pmu->boxes[die] != NULL))
return -EINVAL;
box = uncore_alloc_box(type, NUMA_NO_NODE);
@@ -1008,13 +1052,13 @@
atomic_inc(&box->refcnt);
box->pci_phys_id = phys_id;
- box->pkgid = pkg;
+ box->dieid = die;
box->pci_dev = pdev;
box->pmu = pmu;
uncore_box_init(box);
pci_set_drvdata(pdev, box);
- pmu->boxes[pkg] = box;
+ pmu->boxes[die] = box;
if (atomic_inc_return(&pmu->activeboxes) > 1)
return 0;
@@ -1022,7 +1066,7 @@
ret = uncore_pmu_register(pmu);
if (ret) {
pci_set_drvdata(pdev, NULL);
- pmu->boxes[pkg] = NULL;
+ pmu->boxes[die] = NULL;
uncore_box_exit(box);
kfree(box);
}
@@ -1033,16 +1077,17 @@
{
struct intel_uncore_box *box;
struct intel_uncore_pmu *pmu;
- int i, phys_id, pkg;
+ int i, phys_id, die;
phys_id = uncore_pcibus_to_physid(pdev->bus);
box = pci_get_drvdata(pdev);
if (!box) {
- pkg = topology_phys_to_logical_pkg(phys_id);
+ die = (topology_max_die_per_package() > 1) ? phys_id :
+ topology_phys_to_logical_pkg(phys_id);
for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
- if (uncore_extra_pci_dev[pkg].dev[i] == pdev) {
- uncore_extra_pci_dev[pkg].dev[i] = NULL;
+ if (uncore_extra_pci_dev[die].dev[i] == pdev) {
+ uncore_extra_pci_dev[die].dev[i] = NULL;
break;
}
}
@@ -1055,7 +1100,7 @@
return;
pci_set_drvdata(pdev, NULL);
- pmu->boxes[box->pkgid] = NULL;
+ pmu->boxes[box->dieid] = NULL;
if (atomic_dec_return(&pmu->activeboxes) == 0)
uncore_pmu_unregister(pmu);
uncore_box_exit(box);
@@ -1067,7 +1112,7 @@
size_t size;
int ret;
- size = max_packages * sizeof(struct pci_extra_dev);
+ size = max_dies * sizeof(struct pci_extra_dev);
uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL);
if (!uncore_extra_pci_dev) {
ret = -ENOMEM;
@@ -1114,11 +1159,11 @@
{
struct intel_uncore_pmu *pmu = type->pmus;
struct intel_uncore_box *box;
- int i, pkg;
+ int i, die;
- pkg = topology_logical_package_id(old_cpu < 0 ? new_cpu : old_cpu);
+ die = topology_logical_die_id(old_cpu < 0 ? new_cpu : old_cpu);
for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
+ box = pmu->boxes[die];
if (!box)
continue;
@@ -1146,18 +1191,33 @@
uncore_change_type_ctx(*uncores, old_cpu, new_cpu);
}
-static int uncore_event_cpu_offline(unsigned int cpu)
+static void uncore_box_unref(struct intel_uncore_type **types, int id)
{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
+ struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
- int i, pkg, target;
+ int i;
+
+ for (; *types; types++) {
+ type = *types;
+ pmu = type->pmus;
+ for (i = 0; i < type->num_boxes; i++, pmu++) {
+ box = pmu->boxes[id];
+ if (box && atomic_dec_return(&box->refcnt) == 0)
+ uncore_box_exit(box);
+ }
+ }
+}
+
+static int uncore_event_cpu_offline(unsigned int cpu)
+{
+ int die, target;
/* Check if exiting cpu is used for collecting uncore events */
if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
goto unref;
/* Find a new cpu to collect uncore events */
- target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
+ target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
/* Migrate uncore events to the new target */
if (target < nr_cpu_ids)
@@ -1166,25 +1226,19 @@
target = -1;
uncore_change_context(uncore_msr_uncores, cpu, target);
+ uncore_change_context(uncore_mmio_uncores, cpu, target);
uncore_change_context(uncore_pci_uncores, cpu, target);
unref:
/* Clear the references */
- pkg = topology_logical_package_id(cpu);
- for (; *types; types++) {
- type = *types;
- pmu = type->pmus;
- for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
- if (box && atomic_dec_return(&box->refcnt) == 0)
- uncore_box_exit(box);
- }
- }
+ die = topology_logical_die_id(cpu);
+ uncore_box_unref(uncore_msr_uncores, die);
+ uncore_box_unref(uncore_mmio_uncores, die);
return 0;
}
static int allocate_boxes(struct intel_uncore_type **types,
- unsigned int pkg, unsigned int cpu)
+ unsigned int die, unsigned int cpu)
{
struct intel_uncore_box *box, *tmp;
struct intel_uncore_type *type;
@@ -1197,20 +1251,20 @@
type = *types;
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
- if (pmu->boxes[pkg])
+ if (pmu->boxes[die])
continue;
box = uncore_alloc_box(type, cpu_to_node(cpu));
if (!box)
goto cleanup;
box->pmu = pmu;
- box->pkgid = pkg;
+ box->dieid = die;
list_add(&box->active_list, &allocated);
}
}
/* Install them in the pmus */
list_for_each_entry_safe(box, tmp, &allocated, active_list) {
list_del_init(&box->active_list);
- box->pmu->boxes[pkg] = box;
+ box->pmu->boxes[die] = box;
}
return 0;
@@ -1222,15 +1276,15 @@
return -ENOMEM;
}
-static int uncore_event_cpu_online(unsigned int cpu)
+static int uncore_box_ref(struct intel_uncore_type **types,
+ int id, unsigned int cpu)
{
- struct intel_uncore_type *type, **types = uncore_msr_uncores;
+ struct intel_uncore_type *type;
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
- int i, ret, pkg, target;
+ int i, ret;
- pkg = topology_logical_package_id(cpu);
- ret = allocate_boxes(types, pkg, cpu);
+ ret = allocate_boxes(types, id, cpu);
if (ret)
return ret;
@@ -1238,23 +1292,38 @@
type = *types;
pmu = type->pmus;
for (i = 0; i < type->num_boxes; i++, pmu++) {
- box = pmu->boxes[pkg];
+ box = pmu->boxes[id];
if (box && atomic_inc_return(&box->refcnt) == 1)
uncore_box_init(box);
}
}
+ return 0;
+}
+
+static int uncore_event_cpu_online(unsigned int cpu)
+{
+ int die, target, msr_ret, mmio_ret;
+
+ die = topology_logical_die_id(cpu);
+ msr_ret = uncore_box_ref(uncore_msr_uncores, die, cpu);
+ mmio_ret = uncore_box_ref(uncore_mmio_uncores, die, cpu);
+ if (msr_ret && mmio_ret)
+ return -ENOMEM;
/*
* Check if there is an online cpu in the package
* which collects uncore events already.
*/
- target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu));
+ target = cpumask_any_and(&uncore_cpu_mask, topology_die_cpumask(cpu));
if (target < nr_cpu_ids)
return 0;
cpumask_set_cpu(cpu, &uncore_cpu_mask);
- uncore_change_context(uncore_msr_uncores, -1, cpu);
+ if (!msr_ret)
+ uncore_change_context(uncore_msr_uncores, -1, cpu);
+ if (!mmio_ret)
+ uncore_change_context(uncore_mmio_uncores, -1, cpu);
uncore_change_context(uncore_pci_uncores, -1, cpu);
return 0;
}
@@ -1302,12 +1371,35 @@
return ret;
}
+static int __init uncore_mmio_init(void)
+{
+ struct intel_uncore_type **types = uncore_mmio_uncores;
+ int ret;
+
+ ret = uncore_types_init(types, true);
+ if (ret)
+ goto err;
+
+ for (; *types; types++) {
+ ret = type_pmu_register(*types);
+ if (ret)
+ goto err;
+ }
+ return 0;
+err:
+ uncore_types_exit(uncore_mmio_uncores);
+ uncore_mmio_uncores = empty_uncore;
+ return ret;
+}
+
+
#define X86_UNCORE_MODEL_MATCH(model, init) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
struct intel_uncore_init_fun {
void (*cpu_init)(void);
int (*pci_init)(void);
+ void (*mmio_init)(void);
};
static const struct intel_uncore_init_fun nhm_uncore_init __initconst = {
@@ -1373,6 +1465,17 @@
.pci_init = skx_uncore_pci_init,
};
+static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
+ .cpu_init = icl_uncore_cpu_init,
+ .pci_init = skl_uncore_pci_init,
+};
+
+static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
+ .cpu_init = snr_uncore_cpu_init,
+ .pci_init = snr_uncore_pci_init,
+ .mmio_init = snr_uncore_mmio_init,
+};
+
static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init),
@@ -1380,25 +1483,29 @@
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EP, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE, snb_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE, ivb_uncore_init),
- X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_CORE, hsw_uncore_init),
- X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_ULT, hsw_uncore_init),
- X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_GT3E, hsw_uncore_init),
- X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, bdw_uncore_init),
- X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, bdw_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL, hsw_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_L, hsw_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_G, hsw_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL, bdw_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_G, bdw_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X, snbep_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EX, nhmex_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EX, nhmex_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X, ivbep_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_X, hswep_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, bdx_uncore_init),
- X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, bdx_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_D, bdx_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM, knl_uncore_init),
- X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
- X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_L, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init),
- X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
- X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_L, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_L, icl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_NNPI, icl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE, icl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ATOM_TREMONT_D, snr_uncore_init),
{},
};
@@ -1408,7 +1515,7 @@
{
const struct x86_cpu_id *id;
struct intel_uncore_init_fun *uncore_init;
- int pret = 0, cret = 0, ret;
+ int pret = 0, cret = 0, mret = 0, ret;
id = x86_match_cpu(intel_uncore_match);
if (!id)
@@ -1417,7 +1524,7 @@
if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
return -ENODEV;
- max_packages = topology_max_packages();
+ max_dies = topology_max_packages() * topology_max_die_per_package();
uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
if (uncore_init->pci_init) {
@@ -1431,7 +1538,12 @@
cret = uncore_cpu_init();
}
- if (cret && pret)
+ if (uncore_init->mmio_init) {
+ uncore_init->mmio_init();
+ mret = uncore_mmio_init();
+ }
+
+ if (cret && pret && mret)
return -ENODEV;
/* Install hotplug callbacks to setup the targets for each package */
@@ -1445,6 +1557,7 @@
err:
uncore_types_exit(uncore_msr_uncores);
+ uncore_types_exit(uncore_mmio_uncores);
uncore_pci_exit();
return ret;
}
@@ -1454,6 +1567,7 @@
{
cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
uncore_types_exit(uncore_msr_uncores);
+ uncore_types_exit(uncore_mmio_uncores);
uncore_pci_exit();
}
module_exit(intel_uncore_exit);
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index e17ab88..bbfdaa7 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -2,6 +2,7 @@
#include <linux/slab.h>
#include <linux/pci.h>
#include <asm/apicdef.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/perf_event.h>
#include "../perf_event.h"
@@ -56,7 +57,10 @@
unsigned fixed_ctr;
unsigned fixed_ctl;
unsigned box_ctl;
- unsigned msr_offset;
+ union {
+ unsigned msr_offset;
+ unsigned mmio_offset;
+ };
unsigned num_shared_regs:8;
unsigned single_fixed:1;
unsigned pair_ctr_ctl:1;
@@ -108,7 +112,7 @@
struct intel_uncore_box {
int pci_phys_id;
- int pkgid; /* Logical package ID */
+ int dieid; /* Logical die ID */
int n_active; /* number of active events */
int n_events;
int cpu; /* cpu to collect events */
@@ -125,12 +129,19 @@
struct hrtimer hrtimer;
struct list_head list;
struct list_head active_list;
- void *io_addr;
+ void __iomem *io_addr;
struct intel_uncore_extra_reg shared_regs[0];
};
-#define UNCORE_BOX_FLAG_INITIATED 0
-#define UNCORE_BOX_FLAG_CTL_OFFS8 1 /* event config registers are 8-byte apart */
+/* CFL uncore 8th cbox MSRs */
+#define CFL_UNC_CBO_7_PERFEVTSEL0 0xf70
+#define CFL_UNC_CBO_7_PER_CTR0 0xf76
+
+#define UNCORE_BOX_FLAG_INITIATED 0
+/* event config registers are 8-byte apart */
+#define UNCORE_BOX_FLAG_CTL_OFFS8 1
+/* CFL 8th CBOX has different MSR space */
+#define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS 2
struct uncore_event_desc {
struct kobj_attribute attr;
@@ -152,6 +163,7 @@
};
struct pci2phy_map *__find_pci2phy_map(int segment);
+int uncore_pcibus_to_physid(struct pci_bus *bus);
ssize_t uncore_event_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf);
@@ -183,6 +195,13 @@
return idx == UNCORE_PMC_IDX_FREERUNNING;
}
+static inline
+unsigned int uncore_mmio_box_ctl(struct intel_uncore_box *box)
+{
+ return box->pmu->type->box_ctl +
+ box->pmu->type->mmio_offset * box->pmu->pmu_idx;
+}
+
static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
{
return box->pmu->type->box_ctl;
@@ -285,8 +304,8 @@
unsigned int uncore_freerunning_counter(struct intel_uncore_box *box,
struct perf_event *event)
{
- unsigned int type = uncore_freerunning_type(event->attr.config);
- unsigned int idx = uncore_freerunning_idx(event->attr.config);
+ unsigned int type = uncore_freerunning_type(event->hw.config);
+ unsigned int idx = uncore_freerunning_idx(event->hw.config);
struct intel_uncore_pmu *pmu = box->pmu;
return pmu->type->freerunning[type].counter_base +
@@ -297,23 +316,33 @@
static inline
unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
{
- return box->pmu->type->event_ctl +
- (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
- uncore_msr_box_offset(box);
+ if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) {
+ return CFL_UNC_CBO_7_PERFEVTSEL0 +
+ (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx);
+ } else {
+ return box->pmu->type->event_ctl +
+ (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+ uncore_msr_box_offset(box);
+ }
}
static inline
unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
{
- return box->pmu->type->perf_ctr +
- (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
- uncore_msr_box_offset(box);
+ if (test_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags)) {
+ return CFL_UNC_CBO_7_PER_CTR0 +
+ (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx);
+ } else {
+ return box->pmu->type->perf_ctr +
+ (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
+ uncore_msr_box_offset(box);
+ }
}
static inline
unsigned uncore_fixed_ctl(struct intel_uncore_box *box)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_fixed_ctl(box);
else
return uncore_msr_fixed_ctl(box);
@@ -322,7 +351,7 @@
static inline
unsigned uncore_fixed_ctr(struct intel_uncore_box *box)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_fixed_ctr(box);
else
return uncore_msr_fixed_ctr(box);
@@ -331,7 +360,7 @@
static inline
unsigned uncore_event_ctl(struct intel_uncore_box *box, int idx)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_event_ctl(box, idx);
else
return uncore_msr_event_ctl(box, idx);
@@ -340,7 +369,7 @@
static inline
unsigned uncore_perf_ctr(struct intel_uncore_box *box, int idx)
{
- if (box->pci_dev)
+ if (box->pci_dev || box->io_addr)
return uncore_pci_perf_ctr(box, idx);
else
return uncore_msr_perf_ctr(box, idx);
@@ -360,7 +389,7 @@
unsigned int uncore_freerunning_bits(struct intel_uncore_box *box,
struct perf_event *event)
{
- unsigned int type = uncore_freerunning_type(event->attr.config);
+ unsigned int type = uncore_freerunning_type(event->hw.config);
return box->pmu->type->freerunning[type].bits;
}
@@ -368,7 +397,7 @@
static inline int uncore_num_freerunning(struct intel_uncore_box *box,
struct perf_event *event)
{
- unsigned int type = uncore_freerunning_type(event->attr.config);
+ unsigned int type = uncore_freerunning_type(event->hw.config);
return box->pmu->type->freerunning[type].num_counters;
}
@@ -382,8 +411,8 @@
static inline bool check_valid_freerunning_event(struct intel_uncore_box *box,
struct perf_event *event)
{
- unsigned int type = uncore_freerunning_type(event->attr.config);
- unsigned int idx = uncore_freerunning_idx(event->attr.config);
+ unsigned int type = uncore_freerunning_type(event->hw.config);
+ unsigned int idx = uncore_freerunning_idx(event->hw.config);
return (type < uncore_num_freerunning_types(box, event)) &&
(idx < uncore_num_freerunning(box, event));
@@ -402,16 +431,14 @@
(((cfg >> 8) & 0xff) >= UNCORE_FREERUNNING_UMASK_START);
}
-static inline void uncore_disable_box(struct intel_uncore_box *box)
+/* Check and reject invalid config */
+static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box,
+ struct perf_event *event)
{
- if (box->pmu->type->ops->disable_box)
- box->pmu->type->ops->disable_box(box);
-}
+ if (is_freerunning_event(event))
+ return 0;
-static inline void uncore_enable_box(struct intel_uncore_box *box)
-{
- if (box->pmu->type->ops->enable_box)
- box->pmu->type->ops->enable_box(box);
+ return -EINVAL;
}
static inline void uncore_disable_event(struct intel_uncore_box *box,
@@ -450,7 +477,7 @@
static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
{
- return (box->pkgid < 0);
+ return (box->dieid < 0);
}
static inline struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
@@ -465,6 +492,9 @@
struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu);
u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
+void uncore_mmio_exit_box(struct intel_uncore_box *box);
+u64 uncore_mmio_read_counter(struct intel_uncore_box *box,
+ struct perf_event *event);
void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
void uncore_pmu_event_start(struct perf_event *event, int flags);
@@ -480,6 +510,7 @@
extern struct intel_uncore_type **uncore_msr_uncores;
extern struct intel_uncore_type **uncore_pci_uncores;
+extern struct intel_uncore_type **uncore_mmio_uncores;
extern struct pci_driver *uncore_pci_driver;
extern raw_spinlock_t pci2phy_map_lock;
extern struct list_head pci2phy_map_head;
@@ -495,6 +526,7 @@
void snb_uncore_cpu_init(void);
void nhm_uncore_cpu_init(void);
void skl_uncore_cpu_init(void);
+void icl_uncore_cpu_init(void);
int snb_pci2phy_map_init(int devid);
/* uncore_snbep.c */
@@ -510,6 +542,9 @@
void knl_uncore_cpu_init(void);
int skx_uncore_pci_init(void);
void skx_uncore_cpu_init(void);
+int snr_uncore_pci_init(void);
+void snr_uncore_cpu_init(void);
+void snr_uncore_mmio_init(void);
/* uncore_nhmex.c */
void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index bfa2581..dbaa1b0 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -3,27 +3,29 @@
#include "uncore.h"
/* Uncore IMC PCI IDs */
-#define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100
-#define PCI_DEVICE_ID_INTEL_IVB_IMC 0x0154
-#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150
-#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
-#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
-#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
-#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x1904
-#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC 0x190c
-#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC 0x1900
-#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
-#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
-#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
-#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c
-#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904
-#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914
-#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC 0x590f
-#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC 0x591f
-#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC 0x3ecc
-#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC 0x3ed0
-#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC 0x3e10
-#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC 0x3ec4
+#define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100
+#define PCI_DEVICE_ID_INTEL_IVB_IMC 0x0154
+#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150
+#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
+#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
+#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
+#define PCI_DEVICE_ID_INTEL_SKL_U_IMC 0x1904
+#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC 0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC 0x1900
+#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910
+#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f
+#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f
+#define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c
+#define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904
+#define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914
+#define PCI_DEVICE_ID_INTEL_KBL_SD_IMC 0x590f
+#define PCI_DEVICE_ID_INTEL_KBL_SQ_IMC 0x591f
+#define PCI_DEVICE_ID_INTEL_KBL_HQ_IMC 0x5910
+#define PCI_DEVICE_ID_INTEL_KBL_WQ_IMC 0x5918
+#define PCI_DEVICE_ID_INTEL_CFL_2U_IMC 0x3ecc
+#define PCI_DEVICE_ID_INTEL_CFL_4U_IMC 0x3ed0
+#define PCI_DEVICE_ID_INTEL_CFL_4H_IMC 0x3e10
+#define PCI_DEVICE_ID_INTEL_CFL_6H_IMC 0x3ec4
#define PCI_DEVICE_ID_INTEL_CFL_2S_D_IMC 0x3e0f
#define PCI_DEVICE_ID_INTEL_CFL_4S_D_IMC 0x3e1f
#define PCI_DEVICE_ID_INTEL_CFL_6S_D_IMC 0x3ec2
@@ -34,6 +36,14 @@
#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33
#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca
#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32
+#define PCI_DEVICE_ID_INTEL_AML_YD_IMC 0x590c
+#define PCI_DEVICE_ID_INTEL_AML_YQ_IMC 0x590d
+#define PCI_DEVICE_ID_INTEL_WHL_UQ_IMC 0x3ed0
+#define PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC 0x3e34
+#define PCI_DEVICE_ID_INTEL_WHL_UD_IMC 0x3e35
+#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02
+#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12
+
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
@@ -93,6 +103,12 @@
#define SKL_UNC_PERF_GLOBAL_CTL 0xe01
#define SKL_UNC_GLOBAL_CTL_CORE_ALL ((1 << 5) - 1)
+/* ICL Cbo register */
+#define ICL_UNC_CBO_CONFIG 0x396
+#define ICL_UNC_NUM_CBO_MASK 0xf
+#define ICL_UNC_CBO_0_PER_CTR0 0x702
+#define ICL_UNC_CBO_MSR_OFFSET 0x8
+
DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
@@ -221,6 +237,10 @@
wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
}
+
+ /* The 8th CBOX has different MSR space */
+ if (box->pmu->pmu_idx == 7)
+ __set_bit(UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS, &box->flags);
}
static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
@@ -247,7 +267,7 @@
static struct intel_uncore_type skl_uncore_cbox = {
.name = "cbox",
.num_counters = 4,
- .num_boxes = 5,
+ .num_boxes = 8,
.perf_ctr_bits = 44,
.fixed_ctr_bits = 48,
.perf_ctr = SNB_UNC_CBO_0_PER_CTR0,
@@ -276,6 +296,70 @@
snb_uncore_arb.ops = &skl_uncore_msr_ops;
}
+static struct intel_uncore_type icl_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 4,
+ .perf_ctr_bits = 44,
+ .perf_ctr = ICL_UNC_CBO_0_PER_CTR0,
+ .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0,
+ .event_mask = SNB_UNC_RAW_EVENT_MASK,
+ .msr_offset = ICL_UNC_CBO_MSR_OFFSET,
+ .ops = &skl_uncore_msr_ops,
+ .format_group = &snb_uncore_format_group,
+};
+
+static struct uncore_event_desc icl_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff"),
+ { /* end: all zeroes */ },
+};
+
+static struct attribute *icl_uncore_clock_formats_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group icl_uncore_clock_format_group = {
+ .name = "format",
+ .attrs = icl_uncore_clock_formats_attr,
+};
+
+static struct intel_uncore_type icl_uncore_clockbox = {
+ .name = "clock",
+ .num_counters = 1,
+ .num_boxes = 1,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNB_UNC_FIXED_CTR,
+ .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL,
+ .single_fixed = 1,
+ .event_mask = SNB_UNC_CTL_EV_SEL_MASK,
+ .format_group = &icl_uncore_clock_format_group,
+ .ops = &skl_uncore_msr_ops,
+ .event_descs = icl_uncore_events,
+};
+
+static struct intel_uncore_type *icl_msr_uncores[] = {
+ &icl_uncore_cbox,
+ &snb_uncore_arb,
+ &icl_uncore_clockbox,
+ NULL,
+};
+
+static int icl_get_cbox_num(void)
+{
+ u64 num_boxes;
+
+ rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes);
+
+ return num_boxes & ICL_UNC_NUM_CBO_MASK;
+}
+
+void icl_uncore_cpu_init(void)
+{
+ uncore_msr_uncores = icl_msr_uncores;
+ icl_uncore_cbox.num_boxes = icl_get_cbox_num();
+ snb_uncore_arb.ops = &skl_uncore_msr_ops;
+}
+
enum {
SNB_PCI_UNCORE_IMC,
};
@@ -344,11 +428,6 @@
box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
}
-static void snb_uncore_imc_exit_box(struct intel_uncore_box *box)
-{
- iounmap(box->io_addr);
-}
-
static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
{}
@@ -361,13 +440,6 @@
static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
{}
-static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
-}
-
/*
* Keep the custom event_init() function compatible with old event
* encoding for free running counters.
@@ -393,13 +465,7 @@
return -EINVAL;
/* unsupported modes and filters */
- if (event->attr.exclude_user ||
- event->attr.exclude_kernel ||
- event->attr.exclude_hv ||
- event->attr.exclude_idle ||
- event->attr.exclude_host ||
- event->attr.exclude_guest ||
- event->attr.sample_period) /* no sampling */
+ if (event->attr.sample_period) /* no sampling */
return -EINVAL;
/*
@@ -444,9 +510,11 @@
/* must be done before validate_group */
event->hw.event_base = base;
- event->hw.config = cfg;
event->hw.idx = idx;
+ /* Convert to standard encoding format for freerunning counters */
+ event->hw.config = ((cfg - 1) << 8) | 0x10ff;
+
/* no group validation needed, we have free running counters */
return 0;
@@ -493,17 +561,18 @@
.start = uncore_pmu_event_start,
.stop = uncore_pmu_event_stop,
.read = uncore_pmu_event_read,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
static struct intel_uncore_ops snb_uncore_imc_ops = {
.init_box = snb_uncore_imc_init_box,
- .exit_box = snb_uncore_imc_exit_box,
+ .exit_box = uncore_mmio_exit_box,
.enable_box = snb_uncore_imc_enable_box,
.disable_box = snb_uncore_imc_disable_box,
.disable_event = snb_uncore_imc_disable_event,
.enable_event = snb_uncore_imc_enable_event,
.hw_config = snb_uncore_imc_hw_config,
- .read_counter = snb_uncore_imc_read_counter,
+ .read_counter = uncore_mmio_read_counter,
};
static struct intel_uncore_type snb_uncore_imc = {
@@ -609,6 +678,14 @@
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
{ /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_HQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_WQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_2U_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
@@ -664,6 +741,38 @@
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC),
.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
},
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YD_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AML_YQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_4_UQ_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WHL_UD_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
+static const struct pci_device_id icl_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
{ /* end: all zeroes */ },
};
@@ -692,6 +801,11 @@
.id_table = skl_uncore_pci_ids,
};
+static struct pci_driver icl_uncore_pci_driver = {
+ .name = "icl_uncore",
+ .id_table = icl_uncore_pci_ids,
+};
+
struct imc_uncore_pci_dev {
__u32 pci_id;
struct pci_driver *driver;
@@ -717,6 +831,8 @@
IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U Quad Core */
IMC_DEV(KBL_SD_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Dual Core */
IMC_DEV(KBL_SQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S Quad Core */
+ IMC_DEV(KBL_HQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core H Quad Core */
+ IMC_DEV(KBL_WQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core S 4 cores Work Station */
IMC_DEV(CFL_2U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 2 Cores */
IMC_DEV(CFL_4U_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U 4 Cores */
IMC_DEV(CFL_4H_IMC, &skl_uncore_pci_driver), /* 8th Gen Core H 4 Cores */
@@ -731,6 +847,13 @@
IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */
IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */
IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */
+ IMC_DEV(AML_YD_IMC, &skl_uncore_pci_driver), /* 8th Gen Core Y Mobile Dual Core */
+ IMC_DEV(AML_YQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core Y Mobile Quad Core */
+ IMC_DEV(WHL_UQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Quad Core */
+ IMC_DEV(WHL_4_UQ_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Quad Core */
+ IMC_DEV(WHL_UD_IMC, &skl_uncore_pci_driver), /* 8th Gen Core U Mobile Dual Core */
+ IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
+ IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
{ /* end marker */ }
};
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index c07bee3..b10a5ec 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -324,12 +324,77 @@
#define SKX_M2M_PCI_PMON_CTR0 0x200
#define SKX_M2M_PCI_PMON_BOX_CTL 0x258
+/* SNR Ubox */
+#define SNR_U_MSR_PMON_CTR0 0x1f98
+#define SNR_U_MSR_PMON_CTL0 0x1f91
+#define SNR_U_MSR_PMON_UCLK_FIXED_CTL 0x1f93
+#define SNR_U_MSR_PMON_UCLK_FIXED_CTR 0x1f94
+
+/* SNR CHA */
+#define SNR_CHA_RAW_EVENT_MASK_EXT 0x3ffffff
+#define SNR_CHA_MSR_PMON_CTL0 0x1c01
+#define SNR_CHA_MSR_PMON_CTR0 0x1c08
+#define SNR_CHA_MSR_PMON_BOX_CTL 0x1c00
+#define SNR_C0_MSR_PMON_BOX_FILTER0 0x1c05
+
+
+/* SNR IIO */
+#define SNR_IIO_MSR_PMON_CTL0 0x1e08
+#define SNR_IIO_MSR_PMON_CTR0 0x1e01
+#define SNR_IIO_MSR_PMON_BOX_CTL 0x1e00
+#define SNR_IIO_MSR_OFFSET 0x10
+#define SNR_IIO_PMON_RAW_EVENT_MASK_EXT 0x7ffff
+
+/* SNR IRP */
+#define SNR_IRP0_MSR_PMON_CTL0 0x1ea8
+#define SNR_IRP0_MSR_PMON_CTR0 0x1ea1
+#define SNR_IRP0_MSR_PMON_BOX_CTL 0x1ea0
+#define SNR_IRP_MSR_OFFSET 0x10
+
+/* SNR M2PCIE */
+#define SNR_M2PCIE_MSR_PMON_CTL0 0x1e58
+#define SNR_M2PCIE_MSR_PMON_CTR0 0x1e51
+#define SNR_M2PCIE_MSR_PMON_BOX_CTL 0x1e50
+#define SNR_M2PCIE_MSR_OFFSET 0x10
+
+/* SNR PCU */
+#define SNR_PCU_MSR_PMON_CTL0 0x1ef1
+#define SNR_PCU_MSR_PMON_CTR0 0x1ef8
+#define SNR_PCU_MSR_PMON_BOX_CTL 0x1ef0
+#define SNR_PCU_MSR_PMON_BOX_FILTER 0x1efc
+
+/* SNR M2M */
+#define SNR_M2M_PCI_PMON_CTL0 0x468
+#define SNR_M2M_PCI_PMON_CTR0 0x440
+#define SNR_M2M_PCI_PMON_BOX_CTL 0x438
+#define SNR_M2M_PCI_PMON_UMASK_EXT 0xff
+
+/* SNR PCIE3 */
+#define SNR_PCIE3_PCI_PMON_CTL0 0x508
+#define SNR_PCIE3_PCI_PMON_CTR0 0x4e8
+#define SNR_PCIE3_PCI_PMON_BOX_CTL 0x4e4
+
+/* SNR IMC */
+#define SNR_IMC_MMIO_PMON_FIXED_CTL 0x54
+#define SNR_IMC_MMIO_PMON_FIXED_CTR 0x38
+#define SNR_IMC_MMIO_PMON_CTL0 0x40
+#define SNR_IMC_MMIO_PMON_CTR0 0x8
+#define SNR_IMC_MMIO_PMON_BOX_CTL 0x22800
+#define SNR_IMC_MMIO_OFFSET 0x4000
+#define SNR_IMC_MMIO_SIZE 0x4000
+#define SNR_IMC_MMIO_BASE_OFFSET 0xd0
+#define SNR_IMC_MMIO_BASE_MASK 0x1FFFFFFF
+#define SNR_IMC_MMIO_MEM0_OFFSET 0xd8
+#define SNR_IMC_MMIO_MEM0_MASK 0x7FF
+
DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6");
DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7");
DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39");
DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
@@ -343,11 +408,14 @@
DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31");
DEFINE_UNCORE_FORMAT_ATTR(ch_mask, ch_mask, "config:36-43");
+DEFINE_UNCORE_FORMAT_ATTR(ch_mask2, ch_mask, "config:36-47");
DEFINE_UNCORE_FORMAT_ATTR(fc_mask, fc_mask, "config:44-46");
+DEFINE_UNCORE_FORMAT_ATTR(fc_mask2, fc_mask, "config:48-50");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5");
DEFINE_UNCORE_FORMAT_ATTR(filter_tid4, filter_tid, "config1:0-8");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid5, filter_tid, "config1:0-9");
DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5");
DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8");
@@ -1058,8 +1126,8 @@
if (reg1->idx != EXTRA_REG_NONE) {
int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
- int pkg = box->pkgid;
- struct pci_dev *filter_pdev = uncore_extra_pci_dev[pkg].dev[idx];
+ int die = box->dieid;
+ struct pci_dev *filter_pdev = uncore_extra_pci_dev[die].dev[idx];
if (filter_pdev) {
pci_write_config_dword(filter_pdev, reg1->reg,
@@ -1222,6 +1290,8 @@
.id_table = snbep_uncore_pci_ids,
};
+#define NODE_ID_MASK 0x7
+
/*
* build pci bus to socket mapping
*/
@@ -1243,7 +1313,7 @@
err = pci_read_config_dword(ubox_dev, nodeid_loc, &config);
if (err)
break;
- nodeid = config;
+ nodeid = config & NODE_ID_MASK;
/* get the Node ID mapping */
err = pci_read_config_dword(ubox_dev, idmap_loc, &config);
if (err)
@@ -3583,6 +3653,7 @@
static struct intel_uncore_ops skx_uncore_iio_freerunning_ops = {
.read_counter = uncore_msr_read_counter,
+ .hw_config = uncore_freerunning_hw_config,
};
static struct attribute *skx_uncore_iio_freerunning_formats_attr[] = {
@@ -3965,3 +4036,535 @@
}
/* end of SKX uncore support */
+
+/* SNR uncore support */
+
+static struct intel_uncore_type snr_uncore_ubox = {
+ .name = "ubox",
+ .num_counters = 2,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = SNR_U_MSR_PMON_CTR0,
+ .event_ctl = SNR_U_MSR_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .fixed_ctr = SNR_U_MSR_PMON_UCLK_FIXED_CTR,
+ .fixed_ctl = SNR_U_MSR_PMON_UCLK_FIXED_CTL,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+static struct attribute *snr_uncore_cha_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask_ext2.attr,
+ &format_attr_edge.attr,
+ &format_attr_tid_en.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_filter_tid5.attr,
+ NULL,
+};
+static const struct attribute_group snr_uncore_chabox_format_group = {
+ .name = "format",
+ .attrs = snr_uncore_cha_formats_attr,
+};
+
+static int snr_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+
+ reg1->reg = SNR_C0_MSR_PMON_BOX_FILTER0 +
+ box->pmu->type->msr_offset * box->pmu->pmu_idx;
+ reg1->config = event->attr.config1 & SKX_CHA_MSR_PMON_BOX_FILTER_TID;
+ reg1->idx = 0;
+
+ return 0;
+}
+
+static void snr_cha_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE)
+ wrmsrl(reg1->reg, reg1->config);
+
+ wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops snr_uncore_chabox_ops = {
+ .init_box = ivbep_uncore_msr_init_box,
+ .disable_box = snbep_uncore_msr_disable_box,
+ .enable_box = snbep_uncore_msr_enable_box,
+ .disable_event = snbep_uncore_msr_disable_event,
+ .enable_event = snr_cha_enable_event,
+ .read_counter = uncore_msr_read_counter,
+ .hw_config = snr_cha_hw_config,
+};
+
+static struct intel_uncore_type snr_uncore_chabox = {
+ .name = "cha",
+ .num_counters = 4,
+ .num_boxes = 6,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_CHA_MSR_PMON_CTL0,
+ .perf_ctr = SNR_CHA_MSR_PMON_CTR0,
+ .box_ctl = SNR_CHA_MSR_PMON_BOX_CTL,
+ .msr_offset = HSWEP_CBO_MSR_OFFSET,
+ .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SNR_CHA_RAW_EVENT_MASK_EXT,
+ .ops = &snr_uncore_chabox_ops,
+ .format_group = &snr_uncore_chabox_format_group,
+};
+
+static struct attribute *snr_uncore_iio_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh9.attr,
+ &format_attr_ch_mask2.attr,
+ &format_attr_fc_mask2.attr,
+ NULL,
+};
+
+static const struct attribute_group snr_uncore_iio_format_group = {
+ .name = "format",
+ .attrs = snr_uncore_iio_formats_attr,
+};
+
+static struct intel_uncore_type snr_uncore_iio = {
+ .name = "iio",
+ .num_counters = 4,
+ .num_boxes = 5,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_IIO_MSR_PMON_CTL0,
+ .perf_ctr = SNR_IIO_MSR_PMON_CTR0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT,
+ .box_ctl = SNR_IIO_MSR_PMON_BOX_CTL,
+ .msr_offset = SNR_IIO_MSR_OFFSET,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &snr_uncore_iio_format_group,
+};
+
+static struct intel_uncore_type snr_uncore_irp = {
+ .name = "irp",
+ .num_counters = 2,
+ .num_boxes = 5,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_IRP0_MSR_PMON_CTL0,
+ .perf_ctr = SNR_IRP0_MSR_PMON_CTR0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_IRP0_MSR_PMON_BOX_CTL,
+ .msr_offset = SNR_IRP_MSR_OFFSET,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+static struct intel_uncore_type snr_uncore_m2pcie = {
+ .name = "m2pcie",
+ .num_counters = 4,
+ .num_boxes = 5,
+ .perf_ctr_bits = 48,
+ .event_ctl = SNR_M2PCIE_MSR_PMON_CTL0,
+ .perf_ctr = SNR_M2PCIE_MSR_PMON_CTR0,
+ .box_ctl = SNR_M2PCIE_MSR_PMON_BOX_CTL,
+ .msr_offset = SNR_M2PCIE_MSR_OFFSET,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+static int snr_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
+
+ if (ev_sel >= 0xb && ev_sel <= 0xe) {
+ reg1->reg = SNR_PCU_MSR_PMON_BOX_FILTER;
+ reg1->idx = ev_sel - 0xb;
+ reg1->config = event->attr.config1 & (0xff << reg1->idx);
+ }
+ return 0;
+}
+
+static struct intel_uncore_ops snr_uncore_pcu_ops = {
+ IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+ .hw_config = snr_pcu_hw_config,
+ .get_constraint = snbep_pcu_get_constraint,
+ .put_constraint = snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type snr_uncore_pcu = {
+ .name = "pcu",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNR_PCU_MSR_PMON_CTR0,
+ .event_ctl = SNR_PCU_MSR_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_PCU_MSR_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &snr_uncore_pcu_ops,
+ .format_group = &skx_uncore_pcu_format_group,
+};
+
+enum perf_uncore_snr_iio_freerunning_type_id {
+ SNR_IIO_MSR_IOCLK,
+ SNR_IIO_MSR_BW_IN,
+
+ SNR_IIO_FREERUNNING_TYPE_MAX,
+};
+
+static struct freerunning_counters snr_iio_freerunning[] = {
+ [SNR_IIO_MSR_IOCLK] = { 0x1eac, 0x1, 0x10, 1, 48 },
+ [SNR_IIO_MSR_BW_IN] = { 0x1f00, 0x1, 0x10, 8, 48 },
+};
+
+static struct uncore_event_desc snr_uncore_iio_freerunning_events[] = {
+ /* Free-Running IIO CLOCKS Counter */
+ INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"),
+ /* Free-Running IIO BANDWIDTH IN Counters */
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type snr_uncore_iio_free_running = {
+ .name = "iio_free_running",
+ .num_counters = 9,
+ .num_boxes = 5,
+ .num_freerunning_types = SNR_IIO_FREERUNNING_TYPE_MAX,
+ .freerunning = snr_iio_freerunning,
+ .ops = &skx_uncore_iio_freerunning_ops,
+ .event_descs = snr_uncore_iio_freerunning_events,
+ .format_group = &skx_uncore_iio_freerunning_format_group,
+};
+
+static struct intel_uncore_type *snr_msr_uncores[] = {
+ &snr_uncore_ubox,
+ &snr_uncore_chabox,
+ &snr_uncore_iio,
+ &snr_uncore_irp,
+ &snr_uncore_m2pcie,
+ &snr_uncore_pcu,
+ &snr_uncore_iio_free_running,
+ NULL,
+};
+
+void snr_uncore_cpu_init(void)
+{
+ uncore_msr_uncores = snr_msr_uncores;
+}
+
+static void snr_m2m_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ int box_ctl = uncore_pci_box_ctl(box);
+
+ __set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
+ pci_write_config_dword(pdev, box_ctl, IVBEP_PMON_BOX_CTL_INT);
+}
+
+static struct intel_uncore_ops snr_m2m_uncore_pci_ops = {
+ .init_box = snr_m2m_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = snbep_uncore_pci_disable_event,
+ .enable_event = snbep_uncore_pci_enable_event,
+ .read_counter = snbep_uncore_pci_read_counter,
+};
+
+static struct attribute *snr_m2m_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask_ext3.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static const struct attribute_group snr_m2m_uncore_format_group = {
+ .name = "format",
+ .attrs = snr_m2m_uncore_formats_attr,
+};
+
+static struct intel_uncore_type snr_uncore_m2m = {
+ .name = "m2m",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNR_M2M_PCI_PMON_CTR0,
+ .event_ctl = SNR_M2M_PCI_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .event_mask_ext = SNR_M2M_PCI_PMON_UMASK_EXT,
+ .box_ctl = SNR_M2M_PCI_PMON_BOX_CTL,
+ .ops = &snr_m2m_uncore_pci_ops,
+ .format_group = &snr_m2m_uncore_format_group,
+};
+
+static struct intel_uncore_type snr_uncore_pcie3 = {
+ .name = "pcie3",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNR_PCIE3_PCI_PMON_CTR0,
+ .event_ctl = SNR_PCIE3_PCI_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_PCIE3_PCI_PMON_BOX_CTL,
+ .ops = &ivbep_uncore_pci_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+enum {
+ SNR_PCI_UNCORE_M2M,
+ SNR_PCI_UNCORE_PCIE3,
+};
+
+static struct intel_uncore_type *snr_pci_uncores[] = {
+ [SNR_PCI_UNCORE_M2M] = &snr_uncore_m2m,
+ [SNR_PCI_UNCORE_PCIE3] = &snr_uncore_pcie3,
+ NULL,
+};
+
+static const struct pci_device_id snr_uncore_pci_ids[] = {
+ { /* M2M */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 0, SNR_PCI_UNCORE_M2M, 0),
+ },
+ { /* PCIe3 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x334a),
+ .driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 0, SNR_PCI_UNCORE_PCIE3, 0),
+ },
+ { /* end: all zeroes */ }
+};
+
+static struct pci_driver snr_uncore_pci_driver = {
+ .name = "snr_uncore",
+ .id_table = snr_uncore_pci_ids,
+};
+
+int snr_uncore_pci_init(void)
+{
+ /* SNR UBOX DID */
+ int ret = snbep_pci2phy_map_init(0x3460, SKX_CPUNODEID,
+ SKX_GIDNIDMAP, true);
+
+ if (ret)
+ return ret;
+
+ uncore_pci_uncores = snr_pci_uncores;
+ uncore_pci_driver = &snr_uncore_pci_driver;
+ return 0;
+}
+
+static struct pci_dev *snr_uncore_get_mc_dev(int id)
+{
+ struct pci_dev *mc_dev = NULL;
+ int phys_id, pkg;
+
+ while (1) {
+ mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3451, mc_dev);
+ if (!mc_dev)
+ break;
+ phys_id = uncore_pcibus_to_physid(mc_dev->bus);
+ if (phys_id < 0)
+ continue;
+ pkg = topology_phys_to_logical_pkg(phys_id);
+ if (pkg < 0)
+ continue;
+ else if (pkg == id)
+ break;
+ }
+ return mc_dev;
+}
+
+static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = snr_uncore_get_mc_dev(box->dieid);
+ unsigned int box_ctl = uncore_mmio_box_ctl(box);
+ resource_size_t addr;
+ u32 pci_dword;
+
+ if (!pdev)
+ return;
+
+ pci_read_config_dword(pdev, SNR_IMC_MMIO_BASE_OFFSET, &pci_dword);
+ addr = (pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23;
+
+ pci_read_config_dword(pdev, SNR_IMC_MMIO_MEM0_OFFSET, &pci_dword);
+ addr |= (pci_dword & SNR_IMC_MMIO_MEM0_MASK) << 12;
+
+ addr += box_ctl;
+
+ box->io_addr = ioremap(addr, SNR_IMC_MMIO_SIZE);
+ if (!box->io_addr)
+ return;
+
+ writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr);
+}
+
+static void snr_uncore_mmio_disable_box(struct intel_uncore_box *box)
+{
+ u32 config;
+
+ if (!box->io_addr)
+ return;
+
+ config = readl(box->io_addr);
+ config |= SNBEP_PMON_BOX_CTL_FRZ;
+ writel(config, box->io_addr);
+}
+
+static void snr_uncore_mmio_enable_box(struct intel_uncore_box *box)
+{
+ u32 config;
+
+ if (!box->io_addr)
+ return;
+
+ config = readl(box->io_addr);
+ config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+ writel(config, box->io_addr);
+}
+
+static void snr_uncore_mmio_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!box->io_addr)
+ return;
+
+ writel(hwc->config | SNBEP_PMON_CTL_EN,
+ box->io_addr + hwc->config_base);
+}
+
+static void snr_uncore_mmio_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!box->io_addr)
+ return;
+
+ writel(hwc->config, box->io_addr + hwc->config_base);
+}
+
+static struct intel_uncore_ops snr_uncore_mmio_ops = {
+ .init_box = snr_uncore_mmio_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .disable_box = snr_uncore_mmio_disable_box,
+ .enable_box = snr_uncore_mmio_enable_box,
+ .disable_event = snr_uncore_mmio_disable_event,
+ .enable_event = snr_uncore_mmio_enable_event,
+ .read_counter = uncore_mmio_read_counter,
+};
+
+static struct uncore_event_desc snr_uncore_imc_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x00,umask=0x00"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x0f"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x30"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type snr_uncore_imc = {
+ .name = "imc",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR,
+ .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL,
+ .event_descs = snr_uncore_imc_events,
+ .perf_ctr = SNR_IMC_MMIO_PMON_CTR0,
+ .event_ctl = SNR_IMC_MMIO_PMON_CTL0,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNR_IMC_MMIO_PMON_BOX_CTL,
+ .mmio_offset = SNR_IMC_MMIO_OFFSET,
+ .ops = &snr_uncore_mmio_ops,
+ .format_group = &skx_uncore_format_group,
+};
+
+enum perf_uncore_snr_imc_freerunning_type_id {
+ SNR_IMC_DCLK,
+ SNR_IMC_DDR,
+
+ SNR_IMC_FREERUNNING_TYPE_MAX,
+};
+
+static struct freerunning_counters snr_imc_freerunning[] = {
+ [SNR_IMC_DCLK] = { 0x22b0, 0x0, 0, 1, 48 },
+ [SNR_IMC_DDR] = { 0x2290, 0x8, 0, 2, 48 },
+};
+
+static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = {
+ INTEL_UNCORE_EVENT_DESC(dclk, "event=0xff,umask=0x10"),
+
+ INTEL_UNCORE_EVENT_DESC(read, "event=0xff,umask=0x20"),
+ INTEL_UNCORE_EVENT_DESC(read.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(read.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"),
+ INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"),
+ INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"),
+};
+
+static struct intel_uncore_ops snr_uncore_imc_freerunning_ops = {
+ .init_box = snr_uncore_mmio_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .read_counter = uncore_mmio_read_counter,
+ .hw_config = uncore_freerunning_hw_config,
+};
+
+static struct intel_uncore_type snr_uncore_imc_free_running = {
+ .name = "imc_free_running",
+ .num_counters = 3,
+ .num_boxes = 1,
+ .num_freerunning_types = SNR_IMC_FREERUNNING_TYPE_MAX,
+ .freerunning = snr_imc_freerunning,
+ .ops = &snr_uncore_imc_freerunning_ops,
+ .event_descs = snr_uncore_imc_freerunning_events,
+ .format_group = &skx_uncore_iio_freerunning_format_group,
+};
+
+static struct intel_uncore_type *snr_mmio_uncores[] = {
+ &snr_uncore_imc,
+ &snr_uncore_imc_free_running,
+ NULL,
+};
+
+void snr_uncore_mmio_init(void)
+{
+ uncore_mmio_uncores = snr_mmio_uncores;
+}
+
+/* end of SNR uncore support */
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index b4771a6..6f86650 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -1,7 +1,9 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/perf_event.h>
+#include <linux/sysfs.h>
#include <linux/nospec.h>
#include <asm/intel-family.h>
+#include "probe.h"
enum perf_msr_id {
PERF_MSR_TSC = 0,
@@ -12,32 +14,30 @@
PERF_MSR_PTSC = 5,
PERF_MSR_IRPERF = 6,
PERF_MSR_THERM = 7,
- PERF_MSR_THERM_SNAP = 8,
- PERF_MSR_THERM_UNIT = 9,
PERF_MSR_EVENT_MAX,
};
-static bool test_aperfmperf(int idx)
+static bool test_aperfmperf(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_APERFMPERF);
}
-static bool test_ptsc(int idx)
+static bool test_ptsc(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_PTSC);
}
-static bool test_irperf(int idx)
+static bool test_irperf(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_IRPERF);
}
-static bool test_therm_status(int idx)
+static bool test_therm_status(int idx, void *data)
{
return boot_cpu_has(X86_FEATURE_DTHERM);
}
-static bool test_intel(int idx)
+static bool test_intel(int idx, void *data)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
boot_cpu_data.x86 != 6)
@@ -59,24 +59,24 @@
case INTEL_FAM6_IVYBRIDGE:
case INTEL_FAM6_IVYBRIDGE_X:
- case INTEL_FAM6_HASWELL_CORE:
+ case INTEL_FAM6_HASWELL:
case INTEL_FAM6_HASWELL_X:
- case INTEL_FAM6_HASWELL_ULT:
- case INTEL_FAM6_HASWELL_GT3E:
+ case INTEL_FAM6_HASWELL_L:
+ case INTEL_FAM6_HASWELL_G:
- case INTEL_FAM6_BROADWELL_CORE:
- case INTEL_FAM6_BROADWELL_XEON_D:
- case INTEL_FAM6_BROADWELL_GT3E:
+ case INTEL_FAM6_BROADWELL:
+ case INTEL_FAM6_BROADWELL_D:
+ case INTEL_FAM6_BROADWELL_G:
case INTEL_FAM6_BROADWELL_X:
- case INTEL_FAM6_ATOM_SILVERMONT1:
- case INTEL_FAM6_ATOM_SILVERMONT2:
+ case INTEL_FAM6_ATOM_SILVERMONT:
+ case INTEL_FAM6_ATOM_SILVERMONT_D:
case INTEL_FAM6_ATOM_AIRMONT:
case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_DENVERTON:
+ case INTEL_FAM6_ATOM_GOLDMONT_D:
- case INTEL_FAM6_ATOM_GEMINI_LAKE:
+ case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
case INTEL_FAM6_XEON_PHI_KNL:
case INTEL_FAM6_XEON_PHI_KNM:
@@ -84,11 +84,19 @@
return true;
break;
- case INTEL_FAM6_SKYLAKE_MOBILE:
- case INTEL_FAM6_SKYLAKE_DESKTOP:
+ case INTEL_FAM6_SKYLAKE_L:
+ case INTEL_FAM6_SKYLAKE:
case INTEL_FAM6_SKYLAKE_X:
- case INTEL_FAM6_KABYLAKE_MOBILE:
- case INTEL_FAM6_KABYLAKE_DESKTOP:
+ case INTEL_FAM6_KABYLAKE_L:
+ case INTEL_FAM6_KABYLAKE:
+ case INTEL_FAM6_COMETLAKE_L:
+ case INTEL_FAM6_COMETLAKE:
+ case INTEL_FAM6_ICELAKE_L:
+ case INTEL_FAM6_ICELAKE:
+ case INTEL_FAM6_ICELAKE_X:
+ case INTEL_FAM6_ICELAKE_D:
+ case INTEL_FAM6_TIGERLAKE_L:
+ case INTEL_FAM6_TIGERLAKE:
if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
return true;
break;
@@ -97,37 +105,51 @@
return false;
}
-struct perf_msr {
- u64 msr;
- struct perf_pmu_events_attr *attr;
- bool (*test)(int idx);
+PMU_EVENT_ATTR_STRING(tsc, attr_tsc, "event=0x00" );
+PMU_EVENT_ATTR_STRING(aperf, attr_aperf, "event=0x01" );
+PMU_EVENT_ATTR_STRING(mperf, attr_mperf, "event=0x02" );
+PMU_EVENT_ATTR_STRING(pperf, attr_pperf, "event=0x03" );
+PMU_EVENT_ATTR_STRING(smi, attr_smi, "event=0x04" );
+PMU_EVENT_ATTR_STRING(ptsc, attr_ptsc, "event=0x05" );
+PMU_EVENT_ATTR_STRING(irperf, attr_irperf, "event=0x06" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin, attr_therm, "event=0x07" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, attr_therm_snap, "1" );
+PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, attr_therm_unit, "C" );
+
+static unsigned long msr_mask;
+
+PMU_EVENT_GROUP(events, aperf);
+PMU_EVENT_GROUP(events, mperf);
+PMU_EVENT_GROUP(events, pperf);
+PMU_EVENT_GROUP(events, smi);
+PMU_EVENT_GROUP(events, ptsc);
+PMU_EVENT_GROUP(events, irperf);
+
+static struct attribute *attrs_therm[] = {
+ &attr_therm.attr.attr,
+ &attr_therm_snap.attr.attr,
+ &attr_therm_unit.attr.attr,
+ NULL,
};
-PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00" );
-PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01" );
-PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02" );
-PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03" );
-PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04" );
-PMU_EVENT_ATTR_STRING(ptsc, evattr_ptsc, "event=0x05" );
-PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06" );
-PMU_EVENT_ATTR_STRING(cpu_thermal_margin, evattr_therm, "event=0x07" );
-PMU_EVENT_ATTR_STRING(cpu_thermal_margin.snapshot, evattr_therm_snap, "1" );
-PMU_EVENT_ATTR_STRING(cpu_thermal_margin.unit, evattr_therm_unit, "C" );
+static struct attribute_group group_therm = {
+ .name = "events",
+ .attrs = attrs_therm,
+};
static struct perf_msr msr[] = {
- [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, },
- [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, },
- [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, },
- [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, },
- [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, },
- [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &evattr_ptsc, test_ptsc, },
- [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &evattr_irperf, test_irperf, },
- [PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &evattr_therm, test_therm_status, },
- [PERF_MSR_THERM_SNAP] = { MSR_IA32_THERM_STATUS, &evattr_therm_snap, test_therm_status, },
- [PERF_MSR_THERM_UNIT] = { MSR_IA32_THERM_STATUS, &evattr_therm_unit, test_therm_status, },
+ [PERF_MSR_TSC] = { .no_check = true, },
+ [PERF_MSR_APERF] = { MSR_IA32_APERF, &group_aperf, test_aperfmperf, },
+ [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &group_mperf, test_aperfmperf, },
+ [PERF_MSR_PPERF] = { MSR_PPERF, &group_pperf, test_intel, },
+ [PERF_MSR_SMI] = { MSR_SMI_COUNT, &group_smi, test_intel, },
+ [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &group_ptsc, test_ptsc, },
+ [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &group_irperf, test_irperf, },
+ [PERF_MSR_THERM] = { MSR_IA32_THERM_STATUS, &group_therm, test_therm_status, },
};
-static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = {
+static struct attribute *events_attrs[] = {
+ &attr_tsc.attr.attr,
NULL,
};
@@ -152,6 +174,17 @@
NULL,
};
+static const struct attribute_group *attr_update[] = {
+ &group_aperf,
+ &group_mperf,
+ &group_pperf,
+ &group_smi,
+ &group_ptsc,
+ &group_irperf,
+ &group_therm,
+ NULL,
+};
+
static int msr_event_init(struct perf_event *event)
{
u64 cfg = event->attr.config;
@@ -160,13 +193,7 @@
return -ENOENT;
/* unsupported modes and filters */
- if (event->attr.exclude_user ||
- event->attr.exclude_kernel ||
- event->attr.exclude_hv ||
- event->attr.exclude_idle ||
- event->attr.exclude_host ||
- event->attr.exclude_guest ||
- event->attr.sample_period) /* no sampling */
+ if (event->attr.sample_period) /* no sampling */
return -EINVAL;
if (cfg >= PERF_MSR_EVENT_MAX)
@@ -174,7 +201,7 @@
cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX);
- if (!msr[cfg].attr)
+ if (!(msr_mask & (1 << cfg)))
return -EINVAL;
event->hw.idx = -1;
@@ -256,33 +283,18 @@
.start = msr_event_start,
.stop = msr_event_stop,
.read = msr_event_update,
- .capabilities = PERF_PMU_CAP_NO_INTERRUPT,
+ .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE,
+ .attr_update = attr_update,
};
static int __init msr_init(void)
{
- int i, j = 0;
-
if (!boot_cpu_has(X86_FEATURE_TSC)) {
pr_cont("no MSR PMU driver.\n");
return 0;
}
- /* Probe the MSRs. */
- for (i = PERF_MSR_TSC + 1; i < PERF_MSR_EVENT_MAX; i++) {
- u64 val;
-
- /* Virt sucks; you cannot tell if a R/O MSR is present :/ */
- if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val))
- msr[i].attr = NULL;
- }
-
- /* List remaining MSRs in the sysfs attrs. */
- for (i = 0; i < PERF_MSR_EVENT_MAX; i++) {
- if (msr[i].attr)
- events_attrs[j++] = &msr[i].attr->attr.attr;
- }
- events_attrs[j] = NULL;
+ msr_mask = perf_msr_probe(msr, PERF_MSR_EVENT_MAX, true, NULL);
perf_pmu_register(&pmu_msr, "msr", -1);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index c5ad9cc..ecacfbf 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -49,28 +49,34 @@
unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
u64 idxmsk64;
};
- u64 code;
- u64 cmask;
- int weight;
- int overlap;
- int flags;
+ u64 code;
+ u64 cmask;
+ int weight;
+ int overlap;
+ int flags;
+ unsigned int size;
};
+
+static inline bool constraint_match(struct event_constraint *c, u64 ecode)
+{
+ return ((ecode & c->cmask) - c->code) <= (u64)c->size;
+}
+
/*
* struct hw_perf_event.flags flags
*/
#define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */
#define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */
#define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */
-#define PERF_X86_EVENT_COMMITTED 0x0008 /* event passed commit_txn */
-#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */
-#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */
-#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */
-#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */
-#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */
-#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */
-#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */
-
+#define PERF_X86_EVENT_PEBS_LD_HSW 0x0008 /* haswell style datala, load */
+#define PERF_X86_EVENT_PEBS_NA_HSW 0x0010 /* haswell style datala, unknown */
+#define PERF_X86_EVENT_EXCL 0x0020 /* HT exclusivity on counter */
+#define PERF_X86_EVENT_DYNAMIC 0x0040 /* dynamic alloc'd constraint */
+#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0080 /* grant rdpmc permission */
+#define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */
+#define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */
+#define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */
+#define PERF_X86_EVENT_PEBS_VIA_PT 0x0800 /* use PT buffer for PEBS */
struct amd_nb {
int nb_id; /* NorthBridge id */
@@ -80,6 +86,11 @@
};
#define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1)
+#define PEBS_PMI_AFTER_EACH_RECORD BIT_ULL(60)
+#define PEBS_OUTPUT_OFFSET 61
+#define PEBS_OUTPUT_MASK (3ull << PEBS_OUTPUT_OFFSET)
+#define PEBS_OUTPUT_PT (1ull << PEBS_OUTPUT_OFFSET)
+#define PEBS_VIA_PT_MASK (PEBS_OUTPUT_PT | PEBS_PMI_AFTER_EACH_RECORD)
/*
* Flags PEBS can handle without an PMI.
@@ -96,25 +107,25 @@
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
PERF_SAMPLE_PERIOD)
-#define PEBS_REGS \
- (PERF_REG_X86_AX | \
- PERF_REG_X86_BX | \
- PERF_REG_X86_CX | \
- PERF_REG_X86_DX | \
- PERF_REG_X86_DI | \
- PERF_REG_X86_SI | \
- PERF_REG_X86_SP | \
- PERF_REG_X86_BP | \
- PERF_REG_X86_IP | \
- PERF_REG_X86_FLAGS | \
- PERF_REG_X86_R8 | \
- PERF_REG_X86_R9 | \
- PERF_REG_X86_R10 | \
- PERF_REG_X86_R11 | \
- PERF_REG_X86_R12 | \
- PERF_REG_X86_R13 | \
- PERF_REG_X86_R14 | \
- PERF_REG_X86_R15)
+#define PEBS_GP_REGS \
+ ((1ULL << PERF_REG_X86_AX) | \
+ (1ULL << PERF_REG_X86_BX) | \
+ (1ULL << PERF_REG_X86_CX) | \
+ (1ULL << PERF_REG_X86_DX) | \
+ (1ULL << PERF_REG_X86_DI) | \
+ (1ULL << PERF_REG_X86_SI) | \
+ (1ULL << PERF_REG_X86_SP) | \
+ (1ULL << PERF_REG_X86_BP) | \
+ (1ULL << PERF_REG_X86_IP) | \
+ (1ULL << PERF_REG_X86_FLAGS) | \
+ (1ULL << PERF_REG_X86_R8) | \
+ (1ULL << PERF_REG_X86_R9) | \
+ (1ULL << PERF_REG_X86_R10) | \
+ (1ULL << PERF_REG_X86_R11) | \
+ (1ULL << PERF_REG_X86_R12) | \
+ (1ULL << PERF_REG_X86_R13) | \
+ (1ULL << PERF_REG_X86_R14) | \
+ (1ULL << PERF_REG_X86_R15))
/*
* Per register state.
@@ -206,11 +217,19 @@
u64 pebs_enabled;
int n_pebs;
int n_large_pebs;
+ int n_pebs_via_pt;
+ int pebs_output;
+
+ /* Current super set of events hardware configuration */
+ u64 pebs_data_cfg;
+ u64 active_pebs_data_cfg;
+ int pebs_record_size;
/*
* Intel LBR bits
*/
int lbr_users;
+ int lbr_pebs_users;
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
struct er_account *lbr_sel;
@@ -243,6 +262,11 @@
int excl_thread_id; /* 0 or 1 */
/*
+ * SKL TSX_FORCE_ABORT shadow
+ */
+ u64 tfa_shadow;
+
+ /*
* AMD specific bits
*/
struct amd_nb *amd_nb;
@@ -252,18 +276,29 @@
void *kfree_on_online[X86_PERF_KFREE_MAX];
};
-#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
+#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \
{ .idxmsk64 = (n) }, \
.code = (c), \
+ .size = (e) - (c), \
.cmask = (m), \
.weight = (w), \
.overlap = (o), \
.flags = f, \
}
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \
+ __EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f)
+
#define EVENT_CONSTRAINT(c, n, m) \
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
+/*
+ * The constraint_match() function only works for 'simple' event codes
+ * and not for extended (AMD64_EVENTSEL_EVENT) events codes.
+ */
+#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
+ __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
+
#define INTEL_EXCLEVT_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
0, PERF_X86_EVENT_EXCL)
@@ -299,6 +334,12 @@
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
/*
+ * Constraint on a range of Event codes
+ */
+#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT)
+
+/*
* Constraint on the Event code + UMask + fixed-mask
*
* filter mask to validate fixed counter events.
@@ -343,7 +384,10 @@
/* Event constraint, but match on all event flags too. */
#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
- EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+ EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
+
+#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
/* Check only flags, but allow all event/umask */
#define INTEL_ALL_EVENT_CONSTRAINT(code, n) \
@@ -361,6 +405,11 @@
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \
+ __EVENT_CONSTRAINT_RANGE(code, end, n, \
+ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
__EVENT_CONSTRAINT(code, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
@@ -468,6 +517,9 @@
* values > 32bit.
*/
u64 full_width_write:1;
+ u64 pebs_baseline:1;
+ u64 pebs_metrics_available:1;
+ u64 pebs_output_pt_available:1;
};
u64 capabilities;
};
@@ -560,23 +612,22 @@
struct event_constraint *event_constraints;
struct x86_pmu_quirk *quirks;
int perfctr_second_write;
- bool late_ack;
u64 (*limit_period)(struct perf_event *event, u64 l);
+ /* PMI handler bits */
+ unsigned int late_ack :1,
+ counter_freezing :1;
/*
* sysfs attrs
*/
int attr_rdpmc_broken;
int attr_rdpmc;
struct attribute **format_attrs;
- struct attribute **event_attrs;
- struct attribute **caps_attrs;
ssize_t (*events_sysfs_show)(char *page, u64 config);
- struct attribute **cpu_events;
+ const struct attribute_group **attr_update;
unsigned long attr_freeze_on_smi;
- struct attribute **attrs;
/*
* CPU Hotplug hooks
@@ -599,20 +650,22 @@
/*
* Intel DebugStore bits
*/
- unsigned int bts :1,
- bts_active :1,
- pebs :1,
- pebs_active :1,
- pebs_broken :1,
- pebs_prec_dist :1,
- pebs_no_tlb :1;
+ unsigned int bts :1,
+ bts_active :1,
+ pebs :1,
+ pebs_active :1,
+ pebs_broken :1,
+ pebs_prec_dist :1,
+ pebs_no_tlb :1,
+ pebs_no_isolation :1;
int pebs_record_size;
int pebs_buffer_size;
+ int max_pebs_events;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
- int max_pebs_events;
unsigned long large_pebs_flags;
+ u64 rtm_abort_event;
/*
* Intel LBR
@@ -644,6 +697,13 @@
* Intel host/guest support (KVM)
*/
struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
+
+ /*
+ * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
+ */
+ int (*check_period) (struct perf_event *event, u64 period);
+
+ int (*aux_output_match) (struct perf_event *event);
};
struct x86_perf_task_context {
@@ -674,6 +734,7 @@
#define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */
#define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */
#define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */
+#define PMU_FL_TFA 0x20 /* deal with TSX force abort */
#define EVENT_VAR(_id) event_attr_##_id
#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
@@ -700,6 +761,7 @@
.event_str_ht = ht, \
}
+struct pmu *x86_get_pmu(void);
extern struct x86_pmu x86_pmu __read_mostly;
static inline bool x86_pmu_has_lbr_callstack(void)
@@ -833,8 +895,6 @@
ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event);
ssize_t intel_event_sysfs_show(char *page, u64 config);
-struct attribute **merge_attr(struct attribute **a, struct attribute **b);
-
ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
@@ -853,9 +913,14 @@
#endif /* CONFIG_CPU_SUP_AMD */
+static inline int is_pebs_pt(struct perf_event *event)
+{
+ return !!(event->hw.flags & PERF_X86_EVENT_PEBS_VIA_PT);
+}
+
#ifdef CONFIG_CPU_SUP_INTEL
-static inline bool intel_pmu_has_bts(struct perf_event *event)
+static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period)
{
struct hw_perf_event *hwc = &event->hw;
unsigned int hw_event, bts_event;
@@ -866,7 +931,14 @@
hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
- return hw_event == bts_event && hwc->sample_period == 1;
+ return hw_event == bts_event && period == 1;
+}
+
+static inline bool intel_pmu_has_bts(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ return intel_pmu_has_bts_period(event, hwc->sample_period);
}
int intel_pmu_save_and_restart(struct perf_event *event);
@@ -875,7 +947,8 @@
x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event);
-struct intel_shared_regs *allocate_shared_regs(int cpu);
+extern int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu);
+extern void intel_cpuc_finish(struct cpu_hw_events *cpuc);
int intel_pmu_init(void);
@@ -919,6 +992,8 @@
extern struct event_constraint intel_skl_pebs_event_constraints[];
+extern struct event_constraint intel_icl_pebs_event_constraints[];
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_add(struct perf_event *event);
@@ -937,6 +1012,8 @@
void intel_pmu_auto_reload_read(struct perf_event *event);
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
+
void intel_ds_init(void);
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
@@ -1011,9 +1088,13 @@
return 0;
}
-static inline struct intel_shared_regs *allocate_shared_regs(int cpu)
+static inline int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
{
- return NULL;
+ return 0;
+}
+
+static inline void intel_cpuc_finish(struct cpu_hw_events *cpuc)
+{
}
static inline int is_ht_workaround_enabled(void)
diff --git a/arch/x86/events/probe.c b/arch/x86/events/probe.c
new file mode 100644
index 0000000..c2ede2f
--- /dev/null
+++ b/arch/x86/events/probe.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/bits.h>
+#include "probe.h"
+
+static umode_t
+not_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return 0;
+}
+
+unsigned long
+perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data)
+{
+ unsigned long avail = 0;
+ unsigned int bit;
+ u64 val;
+
+ if (cnt >= BITS_PER_LONG)
+ return 0;
+
+ for (bit = 0; bit < cnt; bit++) {
+ if (!msr[bit].no_check) {
+ struct attribute_group *grp = msr[bit].grp;
+
+ grp->is_visible = not_visible;
+
+ if (msr[bit].test && !msr[bit].test(bit, data))
+ continue;
+ /* Virt sucks; you cannot tell if a R/O MSR is present :/ */
+ if (rdmsrl_safe(msr[bit].msr, &val))
+ continue;
+ /* Disable zero counters if requested. */
+ if (!zero && !val)
+ continue;
+
+ grp->is_visible = NULL;
+ }
+ avail |= BIT(bit);
+ }
+
+ return avail;
+}
+EXPORT_SYMBOL_GPL(perf_msr_probe);
diff --git a/arch/x86/events/probe.h b/arch/x86/events/probe.h
new file mode 100644
index 0000000..4c8e0af
--- /dev/null
+++ b/arch/x86/events/probe.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARCH_X86_EVENTS_PROBE_H__
+#define __ARCH_X86_EVENTS_PROBE_H__
+#include <linux/sysfs.h>
+
+struct perf_msr {
+ u64 msr;
+ struct attribute_group *grp;
+ bool (*test)(int idx, void *data);
+ bool no_check;
+};
+
+unsigned long
+perf_msr_probe(struct perf_msr *msr, int cnt, bool no_zero, void *data);
+
+#define __PMU_EVENT_GROUP(_name) \
+static struct attribute *attrs_##_name[] = { \
+ &attr_##_name.attr.attr, \
+ NULL, \
+}
+
+#define PMU_EVENT_GROUP(_grp, _name) \
+__PMU_EVENT_GROUP(_name); \
+static struct attribute_group group_##_name = { \
+ .name = #_grp, \
+ .attrs = attrs_##_name, \
+}
+
+#endif /* __ARCH_X86_EVENTS_PROBE_H__ */