Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Tooling fixes, mostly related to the KASLR fallout, but also other
  fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf buildid-cache: Check relocation when checking for existing kcore
  perf tools: Adjust kallsyms for relocated kernel
  perf tests: No need to set up ref_reloc_sym
  perf symbols: Prevent the use of kcore if the kernel has moved
  perf record: Get ref_reloc_sym from kernel map
  perf machine: Set up ref_reloc_sym in machine__create_kernel_maps()
  perf machine: Add machine__get_kallsyms_filename()
  perf tools: Add kallsyms__get_function_start()
  perf symbols: Fix symbol annotation for relocated kernel
  perf tools: Fix include for non x86 architectures
  perf tools: Fix AAAAARGH64 memory barriers
  perf tools: Demangle kernel and kernel module symbols too
  perf/doc: Remove mention of non-existent set_perf_event_pending() from design.txt

14 files changed, 162 insertions, 63 deletions

diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index cfede86161d8..b22dbb16f877 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -63,11 +63,35 @@ static int build_id_cache__kcore_dir(char *dir, size_t sz)
         return 0;
 }
 
+static bool same_kallsyms_reloc(const char *from_dir, char *to_dir)
+{
+        char from[PATH_MAX];
+        char to[PATH_MAX];
+        const char *name;
+        u64 addr1 = 0, addr2 = 0;
+        int i;
+
+        scnprintf(from, sizeof(from), "%s/kallsyms", from_dir);
+        scnprintf(to, sizeof(to), "%s/kallsyms", to_dir);
+
+        for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+                addr1 = kallsyms__get_function_start(from, name);
+                if (addr1)
+                        break;
+        }
+
+        if (name)
+                addr2 = kallsyms__get_function_start(to, name);
+
+        return addr1 == addr2;
+}
+
 static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
                                           size_t to_dir_sz)
 {
         char from[PATH_MAX];
         char to[PATH_MAX];
+        char to_subdir[PATH_MAX];
         struct dirent *dent;
         int ret = -1;
         DIR *d;
@@ -86,10 +110,11 @@ static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
                         continue;
                 scnprintf(to, sizeof(to), "%s/%s/modules", to_dir,
                           dent->d_name);
-                if (!compare_proc_modules(from, to)) {
-                        scnprintf(to, sizeof(to), "%s/%s", to_dir,
-                                  dent->d_name);
-                        strlcpy(to_dir, to, to_dir_sz);
+                scnprintf(to_subdir, sizeof(to_subdir), "%s/%s",
+                          to_dir, dent->d_name);
+                if (!compare_proc_modules(from, to) &&
+                    same_kallsyms_reloc(from_dir, to_subdir)) {
+                        strlcpy(to_dir, to_subdir, to_dir_sz);
                         ret = 0;
                         break;
                 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3c394bf16fa8..af47531b82ec 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -287,10 +287,7 @@ static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
          * have no _text sometimes.
          */
         err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-                                                 machine, "_text");
-        if (err < 0)
-                err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-                                                         machine, "_stext");
+                                                 machine);
         if (err < 0)
                 pr_err("Couldn't record guest kernel [%d]'s reference"
                        " relocation symbol.\n", machine->pid);
@@ -457,10 +454,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         }
 
         err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-                                                 machine, "_text");
-        if (err < 0)
-                err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-                                                         machine, "_stext");
+                                                 machine);
         if (err < 0)
                 pr_err("Couldn't record kernel reference relocation symbol\n"
                        "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index 67e5d0cace85..63a0e6f04a01 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -454,7 +454,6 @@ So to start with, in order to add HAVE_PERF_EVENTS to your Kconfig, you
 will need at least this:
         - asm/perf_event.h - a basic stub will suffice at first
         - support for atomic64 types (and associated helper functions)
-        - set_perf_event_pending() implemented
 
 If your architecture does have hardware capabilities, you can override the
 weak stub hw_perf_event_init() to register hardware counters.
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 7daa806d9050..e84fa26bc1be 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -100,8 +100,8 @@
 
 #ifdef __aarch64__
 #define mb()            asm volatile("dmb ish" ::: "memory")
-#define wmb()           asm volatile("dmb ishld" ::: "memory")
-#define rmb()           asm volatile("dmb ishst" ::: "memory")
+#define wmb()           asm volatile("dmb ishst" ::: "memory")
+#define rmb()           asm volatile("dmb ishld" ::: "memory")
 #define cpu_relax()     asm volatile("yield" ::: "memory")
 #endif
 
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 2bd13edcbc17..3d9088003a5b 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -26,7 +26,6 @@ int test__vmlinux_matches_kallsyms(void)
         struct map *kallsyms_map, *vmlinux_map;
         struct machine kallsyms, vmlinux;
         enum map_type type = MAP__FUNCTION;
-        struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", };
         u64 mem_start, mem_end;
 
         /*
@@ -70,14 +69,6 @@ int test__vmlinux_matches_kallsyms(void)
          */
         kallsyms_map = machine__kernel_map(&kallsyms, type);
 
-        sym = map__find_symbol_by_name(kallsyms_map, ref_reloc_sym.name, NULL);
-        if (sym == NULL) {
-                pr_debug("dso__find_symbol_by_name ");
-                goto out;
-        }
-
-        ref_reloc_sym.addr = UM(sym->start);
-
         /*
          * Step 5:
          *
@@ -89,7 +80,6 @@ int test__vmlinux_matches_kallsyms(void)
         }
 
         vmlinux_map = machine__kernel_map(&vmlinux, type);
-        map__kmap(vmlinux_map)->ref_reloc_sym = &ref_reloc_sym;
 
         /*
          * Step 6:
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1fc1c2f04772..b0f3ca850e9e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -470,23 +470,32 @@ static int find_symbol_cb(void *arg, const char *name, char type,
         return 1;
 }