14 files changed, 305 insertions, 214 deletions

diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index 28d793390198..70b5bcbc15df 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -2,7 +2,6 @@ perf-$(CONFIG_DWARF_UNWIND) += regs_load.o
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 
 perf-y += arch-tests.o
-perf-y += rdpmc.o
 perf-y += sample-parsing.o
 perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o
 perf-$(CONFIG_X86_64) += bp-modify.o
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index 64fb73d14d2f..04018b8aa85b 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -3,7 +3,6 @@
 #include "tests/tests.h"
 #include "arch-tests.h"
 
-DEFINE_SUITE("x86 rdpmc", rdpmc);
 #ifdef HAVE_AUXTRACE_SUPPORT
 DEFINE_SUITE("x86 instruction decoder - new instructions", insn_x86);
 DEFINE_SUITE("Intel PT packet decoder", intel_pt_pkt_decoder);
@@ -14,7 +13,6 @@ DEFINE_SUITE("x86 bp modify", bp_modify);
 DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing);
 
 struct test_suite *arch_tests[] = {
-	&suite__rdpmc,
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 	&suite__dwarf_unwind,
 #endif
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index cb5b2c6c3b3b..360a082fc928 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -56,7 +56,7 @@ int test__intel_cqm_count_nmi_context(struct test_suite *test __maybe_unused, in
 		return TEST_FAIL;
 	}
 
-	ret = parse_events(evlist, "intel_cqm/llc_occupancy/", NULL);
+	ret = parse_event(evlist, "intel_cqm/llc_occupancy/");
 	if (ret) {
 		pr_debug("parse_events failed, is \"intel_cqm/llc_occupancy/\" available?\n");
 		err = TEST_SKIP;
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
deleted file mode 100644
index 498413ad9c97..000000000000
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ /dev/null
@@ -1,182 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <errno.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <signal.h>
-#include <sys/mman.h>
-#include <sys/types.h>
-#include <sys/wait.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include "perf-sys.h"
-#include "debug.h"
-#include "tests/tests.h"
-#include "cloexec.h"
-#include "event.h"
-#include <internal/lib.h> // page_size
-#include "arch-tests.h"
-
-static u64 rdpmc(unsigned int counter)
-{
-	unsigned int low, high;
-
-	asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter));
-
-	return low | ((u64)high) << 32;
-}
-
-static u64 rdtsc(void)
-{
-	unsigned int low, high;
-
-	asm volatile("rdtsc" : "=a" (low), "=d" (high));
-
-	return low | ((u64)high) << 32;
-}
-
-static u64 mmap_read_self(void *addr)
-{
-	struct perf_event_mmap_page *pc = addr;
-	u32 seq, idx, time_mult = 0, time_shift = 0;
-	u64 count, cyc = 0, time_offset = 0, enabled, running, delta;
-
-	do {
-		seq = pc->lock;
-		barrier();
-
-		enabled = pc->time_enabled;
-		running = pc->time_running;
-
-		if (enabled != running) {
-			cyc = rdtsc();
-			time_mult = pc->time_mult;
-			time_shift = pc->time_shift;
-			time_offset = pc->time_offset;
-		}
-
-		idx = pc->index;
-		count = pc->offset;
-		if (idx)
-			count += rdpmc(idx - 1);
-
-		barrier();
-	} while (pc->lock != seq);
-
-	if (enabled != running) {
-		u64 quot, rem;
-
-		quot = (cyc >> time_shift);
-		rem = cyc & (((u64)1 << time_shift) - 1);
-		delta = time_offset + quot * time_mult +
-			((rem * time_mult) >> time_shift);
-
-		enabled += delta;
-		if (idx)
-			running += delta;
-
-		quot = count / running;
-		rem = count % running;
-		count = quot * enabled + (rem * enabled) / running;
-	}
-
-	return count;
-}
-
-/*
- * If the RDPMC instruction faults then signal this back to the test parent task:
- */
-static void segfault_handler(int sig __maybe_unused,
-			     siginfo_t *info __maybe_unused,
-			     void *uc __maybe_unused)
-{
-	exit(-1);
-}
-
-static int __test__rdpmc(void)
-{
-	volatile int tmp = 0;
-	u64 i, loops = 1000;
-	int n;
-	int fd;
-	void *addr;
-	struct perf_event_attr attr = {
-		.type = PERF_TYPE_HARDWARE,
-		.config = PERF_COUNT_HW_INSTRUCTIONS,
-		.exclude_kernel = 1,
-	};
-	u64 delta_sum = 0;
-        struct sigaction sa;
-	char sbuf[STRERR_BUFSIZE];
-
-	sigfillset(&sa.sa_mask);
-	sa.sa_sigaction = segfault_handler;
-	sa.sa_flags = 0;
-	sigaction(SIGSEGV, &sa, NULL);
-
-	fd = sys_perf_event_open(&attr, 0, -1, -1,
-				 perf_event_open_cloexec_flag());
-	if (fd < 0) {
-		pr_err("Error: sys_perf_event_open() syscall returned "
-		       "with %d (%s)\n", fd,
-		       str_error_r(errno, sbuf, sizeof(sbuf)));
-		return -1;
-	}
-
-	addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
-	if (addr == (void *)(-1)) {
-		pr_err("Error: mmap() syscall returned with (%s)\n",
-		       str_error_r(errno, sbuf, sizeof(sbuf)));
-		goto out_close;
-	}
-
-	for (n = 0; n < 6; n++) {
-		u64 stamp, now, delta;
-
-		stamp = mmap_read_self(addr);
-
-		for (i = 0; i < loops; i++)
-			tmp++;
-
-		now = mmap_read_self(addr);
-		loops *= 10;
-
-		delta = now - stamp;
-		pr_debug("%14d: %14Lu\n", n, (long long)delta);
-
-		delta_sum += delta;
-	}
-
-	munmap(addr, page_size);
-	pr_debug("   ");
-out_close:
-	close(fd);
-
-	if (!delta_sum)
-		return -1;
-
-	return 0;
-}
-
-int test__rdpmc(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
-{
-	int status = 0;
-	int wret = 0;
-	int ret;
-	int pid;
-
-	pid = fork();
-	if (pid < 0)
-		return -1;
-
-	if (!pid) {
-		ret = __test__rdpmc();
-
-		exit(ret);
-	}
-
-	wret = waitpid(pid, &status, 0);
-	if (wret < 0 || status)
-		return -1;
-
-	return 0;
-}
diff --git a/tools/perf/arch/x86/util/cpuid.h b/tools/perf/arch/x86/util/cpuid.h
new file mode 100644
index 000000000000..0a3ae0ace7e9
--- /dev/null
+++ b/tools/perf/arch/x86/util/cpuid.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef PERF_CPUID_H
+#define PERF_CPUID_H 1
+
+
+static inline void
+cpuid(unsigned int op, unsigned int op2, unsigned int *a, unsigned int *b,
+	unsigned int *c, unsigned int *d)
+{
+	/*
+	 * Preserve %ebx/%rbx register by either placing it in %rdi or saving it
+	 * on the stack - x86-64 needs to avoid the stack red zone. In PIC
+	 * compilations %ebx contains the address of the global offset
+	 * table. %rbx is occasionally used to address stack variables in
+	 * presence of dynamic allocas.
+	 */
+	asm(
+#if defined(__x86_64__)
+		"mov %%rbx, %%rdi\n"
+		"cpuid\n"
+		"xchg %%rdi, %%rbx\n"
+#else
+		"pushl %%ebx\n"
+		"cpuid\n"
+		"movl %%ebx, %%edi\n"
+		"popl %%ebx\n"
+#endif
+		: "=a"(*a), "=D"(*b), "=c"(*c), "=d"(*d)
+		: "a"(op), "2"(op2));
+}
+
+void get_cpuid_0(char *vendor, unsigned int *lvl);
+
+#endif
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 68f681ad54c1..cb59ce9b9638 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -3,20 +3,66 @@
 #include "util/pmu.h"
 #include "util/evlist.h"
 #include "util/parse-events.h"
+#include "util/event.h"
+#include "util/pmu-hybrid.h"
 #include "topdown.h"
 
-#define TOPDOWN_L1_EVENTS	"{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}"
-#define TOPDOWN_L2_EVENTS	"{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound,topdown-heavy-ops,topdown-br-mispredict,topdown-fetch-lat,topdown-mem-bound}"
+static int ___evlist__add_default_attrs(struct evlist *evlist,
+					struct perf_event_attr *attrs,
+					size_t nr_attrs)
+{
+	struct perf_cpu_map *cpus;
+	struct evsel *evsel, *n;
+	struct perf_pmu *pmu;
+	LIST_HEAD(head);
+	size_t i = 0;
+
+	for (i = 0; i < nr_attrs; i++)
+		event_attr_init(attrs + i);
+
+	if (!perf_pmu__has_hybrid())
+		return evlist__add_attrs(evlist, attrs, nr_attrs);
+
+	for (i = 0; i < nr_attrs; i++) {
+		if (attrs[i].type == PERF_TYPE_SOFTWARE) {
+			evsel = evsel__new(attrs + i);
+			if (evsel == NULL)
+				goto out_delete_partial_list;
+			list_add_tail(&evsel->core.node, &head);
+			continue;
+		}
+
+		perf_pmu__for_each_hybrid_pmu(pmu) {
+			evsel = evsel__new(attrs + i);
+			if (evsel == NULL)
+				goto out_delete_partial_list;
+			evsel->core.attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+			cpus = perf_cpu_map__get(pmu->cpus);
+			evsel->core.cpus = cpus;
+			evsel->core.own_cpus = perf_cpu_map__get(cpus);
+			evsel->pmu_name = strdup(pmu->name);
+			list_add_tail(&evsel->core.node, &head);
+		}
+	}
+
+	evlist__splice_list_tail(evlist, &head);
+
+	return 0;
+
+out_delete_partial_list:
+	__evlist__for_each_entry_safe(&head, n, evsel)
+		evsel__delete(evsel);
+	return -1;
+}
 
-int arch_evlist__add_default_attrs(struct evlist *evlist)
+int arch_evlist__add_default_attrs(struct evlist *evlist,
+				   struct perf_event_attr *attrs,
+				   size_t nr_attrs)
 {
-	if (!pmu_have_event("cpu", "slots"))
-		return 0;
+	if (nr_attrs)
+		return ___evlist__add_default_attrs(evlist, attrs, nr_attrs);
 
-	if (pmu_have_event("cpu", "topdown-heavy-ops"))
-		return parse_events(evlist, TOPDOWN_L2_EVENTS, NULL);
-	else
-		return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL);
+	return topdown_parse_events(evlist);
 }
 
 struct evsel *arch_evlist__leader(struct list_head *list)
diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index 3501399cef35..ea3972d785d1 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -6,6 +6,10 @@
 #include "util/pmu.h"
 #include "linux/string.h"
 #include "evsel.h"
+#include "util/debug.h"
+
+#define IBS_FETCH_L3MISSONLY   (1ULL << 59)
+#define IBS_OP_L3MISSONLY      (1ULL << 16)
 
 void arch_evsel__set_sample_weight(struct evsel *evsel)
 {
@@ -61,3 +65,71 @@ bool arch_evsel__must_be_in_group(const struct evsel *evsel)
 		(strcasestr(evsel->name, "slots") ||
 		 strcasestr(evsel->name, "topdown"));
 }
+
+int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
+{
+	u64 event = evsel->core.attr.config & PERF_HW_EVENT_MASK;
+	u64 pmu = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT;
+	const char *event_name;
+
+	if (event < PERF_COUNT_HW_MAX && evsel__hw_names[event])
+		event_name = evsel__hw_names[event];
+	else
+		event_name = "unknown-hardware";
+
+	/* The PMU type is not required for the non-hybrid platform. */
+	if (!pmu)
+		return  scnprintf(bf, size, "%s", event_name);
+
+	return scnprintf(bf, size, "%s/%s/",
+			 evsel->pmu_name ? evsel->pmu_name : "cpu",
+			 event_name);
+}
+
+static void ibs_l3miss_warn(void)
+{
+	pr_warning(
+"WARNING: Hw internally resets sampling period when L3 Miss Filtering is enabled\n"
+"and tagged operation does not cause L3 Miss. This causes sampling period skew.\n");
+}
+
+void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr)
+{
+	struct perf_pmu *evsel_pmu, *ibs_fetch_pmu, *ibs_op_pmu;
+	static int warned_once;
+	/* 0: Uninitialized, 1: Yes, -1: No */
+	static int is_amd;
+
+	if (warned_once || is_amd == -1)
+		return;
+
+	if (!is_amd) {
+		struct perf_env *env = evsel__env(evsel);
+
+		if (!perf_env__cpuid(env) || !env->cpuid ||
+		    !strstarts(env->cpuid, "AuthenticAMD")) {
+			is_amd = -1;
+			return;
+		}
+		is_amd = 1;
+	}
+
+	evsel_pmu = evsel__find_pmu(evsel);
+	if (!evsel_pmu)
+		return;
+
+	ibs_fetch_pmu = perf_pmu__find("ibs_fetch");
+	ibs_op_pmu = perf_pmu__find("ibs_op");
+
+	if (ibs_fetch_pmu && ibs_fetch_pmu->type == evsel_pmu->type) {
+		if (attr->config & IBS_FETCH_L3MISSONLY) {
+			ibs_l3miss_warn();
+			warned_once = 1;
+		}
+	} else if (ibs_op_pmu && ibs_op_pmu->type == evsel_pmu->type) {
+		if (attr->config & IBS_OP_L3MISSONLY) {
+			ibs_l3miss_warn();
+			warned_once = 1;
+		}
+	}
+}
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index 578c8c568ffd..a51444a77a5f 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -9,18 +9,17 @@
 
 #include "../../../util/debug.h"
 #include "../../../util/header.h"
+#include "cpuid.h"
 
-static inline void
-cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c,
-      unsigned int *d)
+void get_cpuid_0(char *vendor, unsigned int *lvl)
 {
-	__asm__ __volatile__ (".byte 0x53\n\tcpuid\n\t"
-			      "movl %%ebx, %%esi\n\t.byte 0x5b"
-			: "=a" (*a),
-			"=S" (*b),
-			"=c" (*c),
-			"=d" (*d)
-			: "a" (op));
+	unsigned int b, c, d;
+
+	cpuid(0, 0, lvl, &b, &c, &d);
+	strncpy(&vendor[0], (char *)(&b), 4);
+	strncpy(&vendor[4], (char *)(&d), 4);
+	strncpy(&vendor[8], (char *)(&c), 4);
+	vendor[12] = '\0';
 }
 
 static int
@@ -31,14 +30,10 @@ __get_cpuid(char *buffer, size_t sz, const char *fmt)
 	int nb;
 	char vendor[16];
 
-	cpuid(0, &lvl, &b, &c, &d);
-	strncpy(&vendor[0], (char *)(&b), 4);
-	strncpy(&vendor[4], (char *)(&d), 4);
-	strncpy(&vendor[8], (char *)(&c), 4);
-	vendor[12] = '\0';
+	get_cpuid_0(vendor, &lvl);
 
 	if (lvl >= 1) {
-		cpuid(1, &a, &b, &c, &d);
+		cpuid(1, 0, &a, &b, &c, &d);
 
 		family = (a >> 8) & 0xf;  /* bits 11 - 8 */
 		model  = (a >> 4) & 0xf;  /* Bits  7 - 4 */
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index bcccfbade5c6..439c2956f3e7 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -233,7 +233,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 		struct evsel *tracking_evsel;
 		int err;
 
-		err = parse_events(evlist, "dummy:u", NULL);
+		err = parse_event(evlist, "dummy:u");
 		if (err)
 			return err;
 
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 06c2cdfd8f2f..13933020a79e 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -426,7 +426,7 @@ static int intel_pt_track_switches(struct evlist *evlist)
 	if (!evlist__can_select_event(evlist, sched_switch))
 		return -EPERM;
 
-	err = parse_events(evlist, sched_switch, NULL);
+	err = parse_event(evlist, sched_switch);
 	if (err) {
 		pr_debug2("%s: failed to parse %s, error %d\n",
 			  __func__, sched_switch, err);
diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c
index 792cd75ade33..404de795ec0b 100644
--- a/tools/perf/arch/x86/util/iostat.c
+++ b/tools/perf/arch/x86/util/iostat.c
@@ -316,7 +316,7 @@ static int iostat_event_group(struct evlist *evl,
 		sprintf(iostat_cmd, iostat_cmd_template,
 			list->rps[idx]->pmu_idx, list->rps[idx]->pmu_idx,
 			list->rps[idx]->pmu_idx, list->rps[idx]->pmu_idx);
-		ret = parse_events(evl, iostat_cmd, NULL);
+		ret = parse_event(evl, iostat_cmd);
 		if (ret)
 			goto err;
 	}
diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
index f81a7cfe4d63..54810f9acd6f 100644
--- a/tools/perf/arch/x86/util/topdown.c
+++ b/tools/perf/arch/x86/util/topdown.c
@@ -3,9 +3,17 @@
 #include "api/fs/fs.h"
 #include "util/pmu.h"
 #include "util/topdown.h"
+#include "util/evlist.h"
+#include "util/debug.h"
+#include "util/pmu-hybrid.h"
 #include "topdown.h"
 #include "evsel.h"
 
+#define TOPDOWN_L1_EVENTS       "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}"
+#define TOPDOWN_L1_EVENTS_CORE  "{slots,cpu_core/topdown-retiring/,cpu_core/topdown-bad-spec/,cpu_core/topdown-fe-bound/,cpu_core/topdown-be-bound/}"
+#define TOPDOWN_L2_EVENTS       "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound,topdown-heavy-ops,topdown-br-mispredict,topdown-fetch-lat,topdown-mem-bound}"
+#define TOPDOWN_L2_EVENTS_CORE  "{slots,cpu_core/topdown-retiring/,cpu_core/topdown-bad-spec/,cpu_core/topdown-fe-bound/,cpu_core/topdown-be-bound/,cpu_core/topdown-heavy-ops/,cpu_core/topdown-br-mispredict/,cpu_core/topdown-fetch-lat/,cpu_core/topdown-mem-bound/}"
+
 /* Check whether there is a PMU which supports the perf metrics. */
 bool topdown_sys_has_perf_metrics(void)
 {
@@ -73,3 +81,46 @@ bool arch_topdown_sample_read(struct evsel *leader)
 
 	return false;
 }
+
+const char *arch_get_topdown_pmu_name(struct evlist *evlist, bool warn)
+{
+	const char *pmu_name;
+
+	if (!perf_pmu__has_hybrid())
+		return "cpu";
+
+	if (!evlist->hybrid_pmu_name) {
+		if (warn)
+			pr_warning("WARNING: default to use cpu_core topdown events\n");
+		evlist->hybrid_pmu_name = perf_pmu__hybrid_type_to_pmu("core");
+	}
+
+	pmu_name = evlist->hybrid_pmu_name;
+
+	return pmu_name;
+}
+
+int topdown_parse_events(struct evlist *evlist)
+{
+	const char *topdown_events;
+	const char *pmu_name;
+
+	if (!topdown_sys_has_perf_metrics())
+		return 0;
+
+	pmu_name = arch_get_topdown_pmu_name(evlist, false);
+
+	if (pmu_have_event(pmu_name, "topdown-heavy-ops")) {
+		if (!strcmp(pmu_name, "cpu_core"))
+			topdown_events = TOPDOWN_L2_EVENTS_CORE;
+		else
+			topdown_events = TOPDOWN_L2_EVENTS;
+	} else {
+		if (!strcmp(pmu_name, "cpu_core"))
+			topdown_events = TOPDOWN_L1_EVENTS_CORE;
+		else
+			topdown_events = TOPDOWN_L1_EVENTS;
+	}
+
+	return parse_event(evlist, topdown_events);
+}
diff --git a/tools/perf/arch/x86/util/topdown.h b/tools/perf/arch/x86/util/topdown.h
index 46bf9273e572..7eb81f042838 100644
--- a/tools/perf/arch/x86/util/topdown.h
+++ b/tools/perf/arch/x86/util/topdown.h
@@ -3,5 +3,6 @@
 #define _TOPDOWN_H 1
 
 bool topdown_sys_has_perf_metrics(void);
+int topdown_parse_events(struct evlist *evlist);
 
 #endif
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 559365f8fe52..eb2b5195bd02 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -1,7 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
+#include <math.h>
+#include <string.h>
 
+#include "../../../util/debug.h"
 #include "../../../util/tsc.h"
+#include "cpuid.h"
 
 u64 rdtsc(void)
 {
@@ -11,3 +15,76 @@ u64 rdtsc(void)
 
 	return low | ((u64)high) << 32;
 }
+
+/*
+ * Derive the TSC frequency in Hz from the /proc/cpuinfo, for example:
+ * ...
+ * model name      : Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz
+ * ...
+ * will return 3000000000.
+ */
+static double cpuinfo_tsc_freq(void)
+{
+	double result = 0;
+	FILE *cpuinfo;
+	char *line = NULL;
+	size_t len = 0;
+
+	cpuinfo = fopen("/proc/cpuinfo", "r");
+	if (!cpuinfo) {
+		pr_err("Failed to read /proc/cpuinfo for TSC frequency");
+		return NAN;
+	}
+	while (getline(&line, &len, cpuinfo) > 0) {
+		if (!strncmp(line, "model name", 10)) {
+			char *pos = strstr(line + 11, " @ ");
+
+			if (pos && sscanf(pos, " @ %lfGHz", &result) == 1) {
+				result *= 1000000000;
+				goto out;
+			}
+		}
+	}
+out:
+	if (fpclassify(result) == FP_ZERO)
+		pr_err("Failed to find TSC frequency in /proc/cpuinfo");
+
+	free(line);
+	fclose(cpuinfo);
+	return result;
+}
+
+double arch_get_tsc_freq(void)
+{
+	unsigned int a, b, c, d, lvl;
+	static bool cached;
+	static double tsc;
+	char vendor[16];
+
+	if (cached)
+		return tsc;
+
+	cached = true;
+	get_cpuid_0(vendor, &lvl);
+	if (!strstr(vendor, "Intel"))
+		return 0;
+
+	/*
+	 * Don't support Time Stamp Counter and
+	 * Nominal Core Crystal Clock Information Leaf.
+	 */
+	if (lvl < 0x15) {
+		tsc = cpuinfo_tsc_freq();
+		return tsc;
+	}
+
+	cpuid(0x15, 0, &a, &b, &c, &d);
+	/* TSC frequency is not enumerated */
+	if (!a || !b || !c) {
+		tsc = cpuinfo_tsc_freq();
+		return tsc;
+	}
+
+	tsc = (double)c * (double)b / (double)a;
+	return tsc;
+}