summaryrefslogtreecommitdiff
path: root/arch/x86/events
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/events')
-rw-r--r--arch/x86/events/amd/core.c1
-rw-r--r--arch/x86/events/amd/power.c2
-rw-r--r--arch/x86/events/amd/uncore.c61
-rw-r--r--arch/x86/events/core.c27
-rw-r--r--arch/x86/events/intel/core.c26
-rw-r--r--arch/x86/events/intel/cstate.c101
-rw-r--r--arch/x86/events/intel/ds.c2
-rw-r--r--arch/x86/events/intel/lbr.c9
-rw-r--r--arch/x86/events/intel/rapl.c58
-rw-r--r--arch/x86/events/intel/uncore.c75
-rw-r--r--arch/x86/events/intel/uncore.h7
-rw-r--r--arch/x86/events/intel/uncore_snb.c159
-rw-r--r--arch/x86/events/intel/uncore_snbep.c12
-rw-r--r--arch/x86/events/msr.c3
14 files changed, 376 insertions, 167 deletions
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 1f22b6bbda68..39eb276d0277 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -250,6 +250,7 @@ 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_CACHE_MISSES] = 0x0964,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
[PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287,
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index abef51320e3a..43b09e9c93a2 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -259,7 +259,7 @@ static int power_cpu_init(unsigned int cpu)
}
static const struct x86_cpu_id cpu_match[] = {
- { .vendor = X86_VENDOR_AMD, .family = 0x15 },
+ X86_MATCH_VENDOR_FAM(AMD, 0x15, NULL),
{},
};
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index a6ea07f2aa84..76400c052b0e 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -180,6 +180,31 @@ static void amd_uncore_del(struct perf_event *event, int flags)
hwc->idx = -1;
}
+/*
+ * Convert logical CPU number to L3 PMC Config ThreadMask format
+ */
+static u64 l3_thread_slice_mask(int cpu)
+{
+ u64 thread_mask, core = topology_core_id(cpu);
+ unsigned int shift, thread = 0;
+
+ if (topology_smt_supported() && !topology_is_primary_thread(cpu))
+ thread = 1;
+
+ if (boot_cpu_data.x86 <= 0x18) {
+ shift = AMD64_L3_THREAD_SHIFT + 2 * (core % 4) + thread;
+ thread_mask = BIT_ULL(shift);
+
+ return AMD64_L3_SLICE_MASK | thread_mask;
+ }
+
+ core = (core << AMD64_L3_COREID_SHIFT) & AMD64_L3_COREID_MASK;
+ shift = AMD64_L3_THREAD_SHIFT + thread;
+ thread_mask = BIT_ULL(shift);
+
+ return AMD64_L3_EN_ALL_SLICES | core | thread_mask;
+}
+
static int amd_uncore_event_init(struct perf_event *event)
{
struct amd_uncore *uncore;
@@ -190,15 +215,12 @@ static int amd_uncore_event_init(struct perf_event *event)
/*
* NB and Last level cache counters (MSRs) are shared across all cores
- * that share the same NB / Last level cache. Interrupts can be directed
- * to a single target core, however, event counts generated by processes
- * running on other cores cannot be masked out. So we do not support
- * sampling and per-thread events.
+ * that share the same NB / Last level cache. On family 16h and below,
+ * Interrupts can be directed to a single target core, however, event
+ * counts generated by processes running on other cores cannot be masked
+ * out. So we do not support sampling and per-thread events via
+ * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts:
*/
- if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
- return -EINVAL;
-
- /* and we do not enable counter overflow interrupts */
hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB;
hwc->idx = -1;
@@ -206,18 +228,11 @@ static int amd_uncore_event_init(struct perf_event *event)
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.
+ * SliceMask and ThreadMask need to be set for certain L3 events.
+ * For other events, the two fields do not affect the count.
*/
- if (l3_mask && is_llc_event(event)) {
- int thread = 2 * (cpu_data(event->cpu).cpu_core_id % 4);
-
- 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;
- }
+ if (l3_mask && is_llc_event(event))
+ hwc->config |= l3_thread_slice_mask(event->cpu);
uncore = event_to_amd_uncore(event);
if (!uncore)
@@ -306,7 +321,7 @@ static struct pmu amd_nb_pmu = {
.start = amd_uncore_start,
.stop = amd_uncore_stop,
.read = amd_uncore_read,
- .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
};
static struct pmu amd_llc_pmu = {
@@ -317,7 +332,7 @@ static struct pmu amd_llc_pmu = {
.start = amd_uncore_start,
.stop = amd_uncore_stop,
.read = amd_uncore_read,
- .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
};
static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
@@ -523,9 +538,9 @@ static int __init amd_uncore_init(void)
if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
return -ENODEV;
- if (boot_cpu_data.x86 == 0x17 || boot_cpu_data.x86 == 0x18) {
+ if (boot_cpu_data.x86 >= 0x17) {
/*
- * For F17h or F18h, the Northbridge counters are
+ * For F17h and above, 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.
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 3bb738f5a472..a619763e96e1 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2490,7 +2490,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
/* 32-bit process in 64-bit kernel. */
unsigned long ss_base, cs_base;
struct stack_frame_ia32 frame;
- const void __user *fp;
+ const struct stack_frame_ia32 __user *fp;
if (!test_thread_flag(TIF_IA32))
return 0;
@@ -2501,18 +2501,12 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
fp = compat_ptr(ss_base + regs->bp);
pagefault_disable();
while (entry->nr < entry->max_stack) {
- unsigned long bytes;
- frame.next_frame = 0;
- frame.return_address = 0;
-
if (!valid_user_frame(fp, sizeof(frame)))
break;
- bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4);
- if (bytes != 0)
+ if (__get_user(frame.next_frame, &fp->next_frame))
break;
- bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4);
- if (bytes != 0)
+ if (__get_user(frame.return_address, &fp->return_address))
break;
perf_callchain_store(entry, cs_base + frame.return_address);
@@ -2533,7 +2527,7 @@ void
perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
struct stack_frame frame;
- const unsigned long __user *fp;
+ const struct stack_frame __user *fp;
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
/* TODO: We don't support guest os callchain now */
@@ -2546,7 +2540,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM))
return;
- fp = (unsigned long __user *)regs->bp;
+ fp = (void __user *)regs->bp;
perf_callchain_store(entry, regs->ip);
@@ -2558,19 +2552,12 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
pagefault_disable();
while (entry->nr < entry->max_stack) {
- unsigned long bytes;
-
- frame.next_frame = NULL;
- frame.return_address = 0;
-
if (!valid_user_frame(fp, sizeof(frame)))
break;
- bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
- if (bytes != 0)
+ if (__get_user(frame.next_frame, &fp->next_frame))
break;
- bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp));
- if (bytes != 0)
+ if (__get_user(frame.return_address, &fp->return_address))
break;
perf_callchain_store(entry, frame.return_address);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 3be51aa06e67..332954cccece 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1945,6 +1945,14 @@ static __initconst const u64 knl_hw_cache_extra_regs
* intel_bts events don't coexist with intel PMU's BTS events because of
* x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
* disabled around intel PMU's event batching etc, only inside the PMI handler.
+ *
+ * Avoid PEBS_ENABLE MSR access in PMIs.
+ * The GLOBAL_CTRL has been disabled. All the counters do not count anymore.
+ * It doesn't matter if the PEBS is enabled or not.
+ * Usually, the PEBS status are not changed in PMIs. It's unnecessary to
+ * access PEBS_ENABLE MSR in disable_all()/enable_all().
+ * However, there are some cases which may change PEBS status, e.g. PMI
+ * throttle. The PEBS_ENABLE should be updated where the status changes.
*/
static void __intel_pmu_disable_all(void)
{
@@ -1954,13 +1962,12 @@ static void __intel_pmu_disable_all(void)
if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
-
- intel_pmu_pebs_disable_all();
}
static void intel_pmu_disable_all(void)
{
__intel_pmu_disable_all();
+ intel_pmu_pebs_disable_all();
intel_pmu_lbr_disable_all();
}
@@ -1968,7 +1975,6 @@ static void __intel_pmu_enable_all(int added, bool pmi)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- intel_pmu_pebs_enable_all();
intel_pmu_lbr_enable_all(pmi);
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
@@ -1986,6 +1992,7 @@ static void __intel_pmu_enable_all(int added, bool pmi)
static void intel_pmu_enable_all(int added)
{
+ intel_pmu_pebs_enable_all();
__intel_pmu_enable_all(added, false);
}
@@ -2374,9 +2381,21 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
* PEBS overflow sets bit 62 in the global status register
*/
if (__test_and_clear_bit(62, (unsigned long *)&status)) {
+ u64 pebs_enabled = cpuc->pebs_enabled;
+
handled++;
x86_pmu.drain_pebs(regs);
status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
+
+ /*
+ * PMI throttle may be triggered, which stops the PEBS event.
+ * Although cpuc->pebs_enabled is updated accordingly, the
+ * MSR_IA32_PEBS_ENABLE is not updated. Because the
+ * cpuc->enabled has been forced to 0 in PMI.
+ * Update the MSR if pebs_enabled is changed.
+ */
+ if (pebs_enabled != cpuc->pebs_enabled)
+ wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
}
/*
@@ -4765,6 +4784,7 @@ __init int intel_pmu_init(void)
break;
case INTEL_FAM6_ATOM_TREMONT_D:
+ case INTEL_FAM6_ATOM_TREMONT:
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index e1daf4151e11..e4aa20c0426f 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -40,17 +40,18 @@
* Model specific counters:
* MSR_CORE_C1_RES: CORE C1 Residency Counter
* perf code: 0x00
- * Available model: SLM,AMT,GLM,CNL
+ * Available model: SLM,AMT,GLM,CNL,TNT
* Scope: Core (each processor core has a MSR)
* MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
* perf code: 0x01
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM,
- * CNL,KBL,CML
+ * CNL,KBL,CML,TNT
* 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,KBL,CML,ICL,TGL
+ * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
+ * TNT
* Scope: Core
* MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
* perf code: 0x03
@@ -60,17 +61,18 @@
* MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter.
* perf code: 0x00
* Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
- * KBL,CML,ICL,TGL
+ * KBL,CML,ICL,TGL,TNT
* 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,KBL,CML,ICL,TGL
+ * GLM,CNL,KBL,CML,ICL,TGL,TNT
* 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,KBL,CML,ICL,TGL
+ * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
+ * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL,
+ * TNT
* Scope: Package (physical package)
* MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
* perf code: 0x03
@@ -87,7 +89,8 @@
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
- * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL
+ * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
+ * TNT
* Scope: Package (physical package)
*
*/
@@ -591,62 +594,60 @@ static const struct cstate_model glm_cstates __initconst = {
};
-#define X86_CSTATES_MODEL(model, states) \
- { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }
-
static const struct x86_cpu_id intel_cstates_match[] __initconst = {
- X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM, nhm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM_EP, nhm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM_EX, nhm_cstates),
-
- X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE, nhm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE_EP, nhm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE_EX, nhm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &nhm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP, &nhm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX, &nhm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_SANDYBRIDGE, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_SANDYBRIDGE_X, snb_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(WESTMERE, &nhm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP, &nhm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX, &nhm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE, snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE_X, snb_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &snb_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &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_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &snb_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_L, hswult_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &snb_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &snb_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &snb_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_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &hswult_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_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, &slm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_D, &slm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT, &slm_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_MATCH_INTEL_FAM6_MODEL(BROADWELL, &snb_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &snb_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &snb_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &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_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &snb_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &snb_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &snb_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_L, cnl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &hswult_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &hswult_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &hswult_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &hswult_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, &cnl_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &knl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &knl_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &glm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &glm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &glm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &glm_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, &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),
+ X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 4b94ae4ae369..dc43cc124e09 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1714,6 +1714,8 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
old = ((s64)(prev_raw_count << shift) >> shift);
local64_add(new - old + count * period, &event->count);
+ local64_set(&hwc->period_left, -new);
+
perf_event_update_userpage(event);
return 0;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 534c76606049..65113b16804a 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -585,6 +585,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
cpuc->lbr_entries[i].reserved = 0;
}
cpuc->lbr_stack.nr = i;
+ cpuc->lbr_stack.hw_idx = tos;
}
/*
@@ -680,6 +681,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
out++;
}
cpuc->lbr_stack.nr = out;
+ cpuc->lbr_stack.hw_idx = tos;
}
void intel_pmu_lbr_read(void)
@@ -1120,6 +1122,13 @@ void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
int i;
cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
+
+ /* Cannot get TOS for large PEBS */
+ if (cpuc->n_pebs == cpuc->n_large_pebs)
+ cpuc->lbr_stack.hw_idx = -1ULL;
+ else
+ cpuc->lbr_stack.hw_idx = intel_pmu_lbr_tos();
+
for (i = 0; i < x86_pmu.lbr_nr; i++) {
u64 info = lbr->lbr[i].info;
struct perf_branch_entry *e = &cpuc->lbr_entries[i];
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 09913121e726..a5dbd25852cb 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -668,9 +668,6 @@ static int __init init_rapl_pmus(void)
return 0;
}
-#define X86_RAPL_MODEL_MATCH(model, init) \
- { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
-
static struct rapl_model model_snb = {
.events = BIT(PERF_RAPL_PP0) |
BIT(PERF_RAPL_PKG) |
@@ -716,36 +713,35 @@ static struct rapl_model model_skl = {
};
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),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE_L, model_skl),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE, model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &model_snb),
+ X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &model_snbep),
+ X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &model_snb),
+ X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &model_snbep),
+ X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &model_hsw),
+ X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &model_hsx),
+ X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &model_hsw),
+ X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &model_hsw),
+ X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &model_hsw),
+ X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &model_hsw),
+ X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &model_hsx),
+ X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &model_hsx),
+ X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &model_knl),
+ X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &model_knl),
+ X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &model_hsx),
+ X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &model_hsw),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &model_hsw),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &model_hsw),
+ X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl),
{},
};
-
MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
static int __init rapl_pmu_init(void)
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 86467f85c383..1ba72c563313 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1392,10 +1392,6 @@ err:
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);
@@ -1470,6 +1466,16 @@ static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
.pci_init = skl_uncore_pci_init,
};
+static const struct intel_uncore_init_fun tgl_uncore_init __initconst = {
+ .cpu_init = icl_uncore_cpu_init,
+ .mmio_init = tgl_uncore_mmio_init,
+};
+
+static const struct intel_uncore_init_fun tgl_l_uncore_init __initconst = {
+ .cpu_init = icl_uncore_cpu_init,
+ .mmio_init = tgl_l_uncore_mmio_init,
+};
+
static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
.cpu_init = snr_uncore_cpu_init,
.pci_init = snr_uncore_pci_init,
@@ -1477,38 +1483,39 @@ static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
};
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),
- X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE, nhm_uncore_init),
- 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, 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_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, 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_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),
+ X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP, &nhm_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &nhm_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(WESTMERE, &nhm_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP, &nhm_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &snb_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &ivb_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &hsw_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &hsw_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &hsw_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &bdw_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &bdw_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &snbep_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX, &nhmex_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX, &nhmex_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &ivbep_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &hswep_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &bdx_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &bdx_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &knl_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &knl_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &skl_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &skl_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &skx_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &skl_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &skl_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI, &icl_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &tgl_l_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &tgl_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init),
{},
};
-
MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match);
static int __init intel_uncore_init(void)
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index bbfdaa720b45..b30429f8a53a 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -154,6 +154,7 @@ struct freerunning_counters {
unsigned int box_offset;
unsigned int num_counters;
unsigned int bits;
+ unsigned *box_offsets;
};
struct pci2phy_map {
@@ -310,7 +311,9 @@ unsigned int uncore_freerunning_counter(struct intel_uncore_box *box,
return pmu->type->freerunning[type].counter_base +
pmu->type->freerunning[type].counter_offset * idx +
- pmu->type->freerunning[type].box_offset * pmu->pmu_idx;
+ (pmu->type->freerunning[type].box_offsets ?
+ pmu->type->freerunning[type].box_offsets[pmu->pmu_idx] :
+ pmu->type->freerunning[type].box_offset * pmu->pmu_idx);
}
static inline
@@ -527,6 +530,8 @@ void snb_uncore_cpu_init(void);
void nhm_uncore_cpu_init(void);
void skl_uncore_cpu_init(void);
void icl_uncore_cpu_init(void);
+void tgl_uncore_mmio_init(void);
+void tgl_l_uncore_mmio_init(void);
int snb_pci2phy_map_init(int devid);
/* uncore_snbep.c */
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index c37cb12d0ef6..3de1065eefc4 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -44,6 +44,11 @@
#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
+#define PCI_DEVICE_ID_INTEL_TGL_U1_IMC 0x9a02
+#define PCI_DEVICE_ID_INTEL_TGL_U2_IMC 0x9a04
+#define PCI_DEVICE_ID_INTEL_TGL_U3_IMC 0x9a12
+#define PCI_DEVICE_ID_INTEL_TGL_U4_IMC 0x9a14
+#define PCI_DEVICE_ID_INTEL_TGL_H_IMC 0x9a36
/* SNB event control */
@@ -1002,3 +1007,157 @@ void nhm_uncore_cpu_init(void)
}
/* end of Nehalem uncore support */
+
+/* Tiger Lake MMIO uncore support */
+
+static const struct pci_device_id tgl_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U1_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U2_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U3_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U4_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_H_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ }
+};
+
+enum perf_tgl_uncore_imc_freerunning_types {
+ TGL_MMIO_UNCORE_IMC_DATA_TOTAL,
+ TGL_MMIO_UNCORE_IMC_DATA_READ,
+ TGL_MMIO_UNCORE_IMC_DATA_WRITE,
+ TGL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX
+};
+
+static struct freerunning_counters tgl_l_uncore_imc_freerunning[] = {
+ [TGL_MMIO_UNCORE_IMC_DATA_TOTAL] = { 0x5040, 0x0, 0x0, 1, 64 },
+ [TGL_MMIO_UNCORE_IMC_DATA_READ] = { 0x5058, 0x0, 0x0, 1, 64 },
+ [TGL_MMIO_UNCORE_IMC_DATA_WRITE] = { 0x50A0, 0x0, 0x0, 1, 64 },
+};
+
+static struct freerunning_counters tgl_uncore_imc_freerunning[] = {
+ [TGL_MMIO_UNCORE_IMC_DATA_TOTAL] = { 0xd840, 0x0, 0x0, 1, 64 },
+ [TGL_MMIO_UNCORE_IMC_DATA_READ] = { 0xd858, 0x0, 0x0, 1, 64 },
+ [TGL_MMIO_UNCORE_IMC_DATA_WRITE] = { 0xd8A0, 0x0, 0x0, 1, 64 },
+};
+
+static struct uncore_event_desc tgl_uncore_imc_events[] = {
+ INTEL_UNCORE_EVENT_DESC(data_total, "event=0xff,umask=0x10"),
+ INTEL_UNCORE_EVENT_DESC(data_total.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(data_total.unit, "MiB"),
+
+ INTEL_UNCORE_EVENT_DESC(data_read, "event=0xff,umask=0x20"),
+ INTEL_UNCORE_EVENT_DESC(data_read.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(data_read.unit, "MiB"),
+
+ INTEL_UNCORE_EVENT_DESC(data_write, "event=0xff,umask=0x30"),
+ INTEL_UNCORE_EVENT_DESC(data_write.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(data_write.unit, "MiB"),
+
+ { /* end: all zeroes */ }
+};
+
+static struct pci_dev *tgl_uncore_get_mc_dev(void)
+{
+ const struct pci_device_id *ids = tgl_uncore_pci_ids;
+ struct pci_dev *mc_dev = NULL;
+
+ while (ids && ids->vendor) {
+ mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, ids->device, NULL);
+ if (mc_dev)
+ return mc_dev;
+ ids++;
+ }
+
+ return mc_dev;
+}
+
+#define TGL_UNCORE_MMIO_IMC_MEM_OFFSET 0x10000
+
+static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = tgl_uncore_get_mc_dev();
+ struct intel_uncore_pmu *pmu = box->pmu;
+ resource_size_t addr;
+ u32 mch_bar;
+
+ if (!pdev) {
+ pr_warn("perf uncore: Cannot find matched IMC device.\n");
+ return;
+ }
+
+ pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET, &mch_bar);
+ /* MCHBAR is disabled */
+ if (!(mch_bar & BIT(0))) {
+ pr_warn("perf uncore: MCHBAR is disabled. Failed to map IMC free-running counters.\n");
+ return;
+ }
+ mch_bar &= ~BIT(0);
+ addr = (resource_size_t)(mch_bar + TGL_UNCORE_MMIO_IMC_MEM_OFFSET * pmu->pmu_idx);
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET + 4, &mch_bar);
+ addr |= ((resource_size_t)mch_bar << 32);
+#endif
+
+ box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+}
+
+static struct intel_uncore_ops tgl_uncore_imc_freerunning_ops = {
+ .init_box = tgl_uncore_imc_freerunning_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .read_counter = uncore_mmio_read_counter,
+ .hw_config = uncore_freerunning_hw_config,
+};
+
+static struct attribute *tgl_uncore_imc_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ NULL
+};
+
+static const struct attribute_group tgl_uncore_imc_format_group = {
+ .name = "format",
+ .attrs = tgl_uncore_imc_formats_attr,
+};
+
+static struct intel_uncore_type tgl_uncore_imc_free_running = {
+ .name = "imc_free_running",
+ .num_counters = 3,
+ .num_boxes = 2,
+ .num_freerunning_types = TGL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+ .freerunning = tgl_uncore_imc_freerunning,
+ .ops = &tgl_uncore_imc_freerunning_ops,
+ .event_descs = tgl_uncore_imc_events,
+ .format_group = &tgl_uncore_imc_format_group,
+};
+
+static struct intel_uncore_type *tgl_mmio_uncores[] = {
+ &tgl_uncore_imc_free_running,
+ NULL
+};
+
+void tgl_l_uncore_mmio_init(void)
+{
+ tgl_uncore_imc_free_running.freerunning = tgl_l_uncore_imc_freerunning;
+ uncore_mmio_uncores = tgl_mmio_uncores;
+}
+
+void tgl_uncore_mmio_init(void)
+{
+ uncore_mmio_uncores = tgl_mmio_uncores;
+}
+
+/* end of Tiger Lake MMIO uncore support */
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index ad20220af303..01023f0d935b 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -4380,10 +4380,10 @@ static struct pci_dev *snr_uncore_get_mc_dev(int id)
return mc_dev;
}
-static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
+static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box,
+ unsigned int box_ctl, int mem_offset)
{
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;
@@ -4393,7 +4393,7 @@ static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
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);
+ pci_read_config_dword(pdev, mem_offset, &pci_dword);
addr |= (pci_dword & SNR_IMC_MMIO_MEM0_MASK) << 12;
addr += box_ctl;
@@ -4405,6 +4405,12 @@ static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr);
}
+static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
+{
+ __snr_uncore_mmio_init_box(box, uncore_mmio_box_ctl(box),
+ SNR_IMC_MMIO_MEM0_OFFSET);
+}
+
static void snr_uncore_mmio_disable_box(struct intel_uncore_box *box)
{
u32 config;
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 6f86650b3f77..a949f6f55991 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -75,8 +75,9 @@ static bool test_intel(int idx, void *data)
case INTEL_FAM6_ATOM_GOLDMONT:
case INTEL_FAM6_ATOM_GOLDMONT_D:
-
case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ case INTEL_FAM6_ATOM_TREMONT_D:
+ case INTEL_FAM6_ATOM_TREMONT:
case INTEL_FAM6_XEON_PHI_KNL:
case INTEL_FAM6_XEON_PHI_KNM:
generated by cgit v1.2.3 (git 2.39.0) at 2024-10-03 19:28:48 +0300