perf machine: Workaround missing maps for x86 PTI entry trampolines

index 6276b340f893..49f58921a968 100644
@@ -3,6 +3,7 @@
 #include "env.h"
 #include "util.h"
 #include <errno.h>
+#include <sys/utsname.h>
 
 struct perf_env perf_env;
 

@@ -87,6 +88,24 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
 	return 0;
 }
 
+static int perf_env__read_arch(struct perf_env *env)
+{
+	struct utsname uts;
+
+	if (env->arch)
+		return 0;
+
+	if (!uname(&uts))
+		env->arch = strdup(uts.machine);
+
+	return env->arch ? 0 : -ENOMEM;
+}
+
+const char *perf_env__raw_arch(struct perf_env *env)
+{
+	return env && !perf_env__read_arch(env) ? env->arch : "unknown";
+}
+
 void cpu_cache_level__free(struct cpu_cache_level *cache)
 {
 	free(cache->type);

index 1eb35b190b34..bd3869913907 100644
@@ -65,4 +65,7 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
 int perf_env__read_cpu_topology_map(struct perf_env *env);
 
 void cpu_cache_level__free(struct cpu_cache_level *cache);
+
+const char *perf_env__raw_arch(struct perf_env *env);
+
 #endif /* __PERF_ENV_H */

index bd5d5b5e2218..2af879693fbe 100644
@@ -2238,6 +2238,15 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 	return 0;
 }
 
+/*
+ * Compares the raw arch string. N.B. see instead perf_env__arch() if a
+ * normalized arch is needed.
+ */
+bool machine__is(struct machine *machine, const char *arch)
+{
+	return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
+}
+
 int machine__get_kernel_start(struct machine *machine)
 {
 	struct map *map = machine__kernel_map(machine);

index d551aa80a59b..fbc5133fb27c 100644
@@ -169,6 +169,8 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
+bool machine__is(struct machine *machine, const char *arch);
+
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 

index 2af879693fbe..af18c3d55642 100644
@@ -2263,7 +2263,12 @@ int machine__get_kernel_start(struct machine *machine)
 	machine->kernel_start = 1ULL << 63;
 	if (map) {
 		err = map__load(map);
-		if (!err)
+		/*
+		 * On x86_64, PTI entry trampolines are less than the
+		 * start of kernel text, but still above 2^63. So leave
+		 * kernel_start = 1ULL << 63 for x86_64.
+		 */
+		if (!err && !machine__is(machine, "x86_64"))
 			machine->kernel_start = map->start;
 	}
 	return err;

index 49f58921a968..b492cb974aa0 100644
@@ -101,11 +101,24 @@ static int perf_env__read_arch(struct perf_env *env)
 	return env->arch ? 0 : -ENOMEM;
 }
 
+static int perf_env__read_nr_cpus_avail(struct perf_env *env)
+{
+	if (env->nr_cpus_avail == 0)
+		env->nr_cpus_avail = cpu__max_present_cpu();
+
+	return env->nr_cpus_avail ? 0 : -ENOENT;
+}
+
 const char *perf_env__raw_arch(struct perf_env *env)
 {
 	return env && !perf_env__read_arch(env) ? env->arch : "unknown";
 }
 
+int perf_env__nr_cpus_avail(struct perf_env *env)
+{
+	return env && !perf_env__read_nr_cpus_avail(env) ? env->nr_cpus_avail : 0;
+}
+
 void cpu_cache_level__free(struct cpu_cache_level *cache)
 {
 	free(cache->type);

index bd3869913907..9aace8452751 100644
@@ -67,5 +67,6 @@ int perf_env__read_cpu_topology_map(struct perf_env *env);
 void cpu_cache_level__free(struct cpu_cache_level *cache);
 
 const char *perf_env__raw_arch(struct perf_env *env);
+int perf_env__nr_cpus_avail(struct perf_env *env);
 
 #endif /* __PERF_ENV_H */

index af18c3d55642..78aa1c5f19ca 100644
@@ -2247,6 +2247,11 @@ bool machine__is(struct machine *machine, const char *arch)
 	return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
 }
 
+int machine__nr_cpus_avail(struct machine *machine)
+{
+	return machine ? perf_env__nr_cpus_avail(machine->env) : 0;
+}
+
 int machine__get_kernel_start(struct machine *machine)
 {
 	struct map *map = machine__kernel_map(machine);

index fbc5133fb27c..245743d9ce63 100644
@@ -170,6 +170,7 @@ static inline bool machine__is_host(struct machine *machine)
 }
 
 bool machine__is(struct machine *machine, const char *arch);
+int machine__nr_cpus_avail(struct machine *machine);
 
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);

index 78aa1c5f19ca..968fd0454e6b 100644
@@ -818,6 +818,102 @@ static int machine__get_running_kernel_start(struct machine *machine,
 	return 0;
 }
 
+/* Kernel-space maps for symbols that are outside the main kernel map and module maps */
+struct extra_kernel_map {
+	u64 start;
+	u64 end;
+	u64 pgoff;
+};
+
+static int machine__create_extra_kernel_map(struct machine *machine,
+					    struct dso *kernel,
+					    struct extra_kernel_map *xm)
+{
+	struct kmap *kmap;
+	struct map *map;
+
+	map = map__new2(xm->start, kernel, MAP__FUNCTION);
+	if (!map)
+		return -1;
+
+	map->end   = xm->end;
+	map->pgoff = xm->pgoff;
+
+	kmap = map__kmap(map);
+
+	kmap->kmaps = &machine->kmaps;
+
+	map_groups__insert(&machine->kmaps, map);
+
+	pr_debug2("Added extra kernel map %" PRIx64 "-%" PRIx64 "\n",
+		  map->start, map->end);
+
+	map__put(map);
+
+	return 0;
+}
+
+static u64 find_entry_trampoline(struct dso *dso)
+{
+	/* Duplicates are removed so lookup all aliases */
+	const char *syms[] = {
+		"_entry_trampoline",
+		"__entry_trampoline_start",
+		"entry_SYSCALL_64_trampoline",
+	};
+	struct symbol *sym = dso__first_symbol(dso, MAP__FUNCTION);
+	unsigned int i;
+
+	for (; sym; sym = dso__next_symbol(sym)) {
+		if (sym->binding != STB_GLOBAL)
+			continue;
+		for (i = 0; i < ARRAY_SIZE(syms); i++) {
+			if (!strcmp(sym->name, syms[i]))
+				return sym->start;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * These values can be used for kernels that do not have symbols for the entry
+ * trampolines in kallsyms.
+ */
+#define X86_64_CPU_ENTRY_AREA_PER_CPU	0xfffffe0000000000ULL
+#define X86_64_CPU_ENTRY_AREA_SIZE	0x2c000
+#define X86_64_ENTRY_TRAMPOLINE		0x6000
+
+/* Map x86_64 PTI entry trampolines */
+int machine__map_x86_64_entry_trampolines(struct machine *machine,
+					  struct dso *kernel)
+{
+	u64 pgoff = find_entry_trampoline(kernel);
+	int nr_cpus_avail, cpu;
+
+	if (!pgoff)
+		return 0;
+
+	nr_cpus_avail = machine__nr_cpus_avail(machine);
+
+	/* Add a 1 page map for each CPU's entry trampoline */
+	for (cpu = 0; cpu < nr_cpus_avail; cpu++) {
+		u64 va = X86_64_CPU_ENTRY_AREA_PER_CPU +
+			 cpu * X86_64_CPU_ENTRY_AREA_SIZE +
+			 X86_64_ENTRY_TRAMPOLINE;
+		struct extra_kernel_map xm = {
+			.start = va,
+			.end   = va + page_size,
+			.pgoff = pgoff,
+		};
+
+		if (machine__create_extra_kernel_map(machine, kernel, &xm) < 0)
+			return -1;
+	}
+
+	return 0;
+}
+
 int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
 	int type;

index 245743d9ce63..13041b036a5b 100644
@@ -266,4 +266,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
  */
 char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp);
 
+int machine__map_x86_64_entry_trampolines(struct machine *machine,
+					  struct dso *kernel);
+
 #endif /* __PERF_MACHINE_H */

index ec40e47aa198..3936f69f385c 100644
@@ -1513,20 +1513,22 @@ int dso__load(struct dso *dso, struct map *map)
 		goto out;
 	}
 
+	if (map->groups && map->groups->machine)
+		machine = map->groups->machine;
+	else
+		machine = NULL;
+
 	if (dso->kernel) {
 		if (dso->kernel == DSO_TYPE_KERNEL)
 			ret = dso__load_kernel_sym(dso, map);
 		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 			ret = dso__load_guest_kernel_sym(dso, map);
 
+		if (machine__is(machine, "x86_64"))
+			machine__map_x86_64_entry_trampolines(machine, dso);
 		goto out;
 	}
 
-	if (map->groups && map->groups->machine)
-		machine = map->groups->machine;
-	else
-		machine = NULL;
-
 	dso->adjust_symbols = 0;
 
 	if (perfmap) {

index fcc8984bc329..acad8ba06d77 100644
@@ -527,6 +527,7 @@ static int do_test_code_reading(bool try_kcore)
 	pid = getpid();
 
 	machine = machine__new_host();
+	machine->env = &perf_env;
 
 	ret = machine__create_kernel_maps(machine);
 	if (ret < 0) {