Merge branch 'x86/urgent' into x86/apic

Bring in the upstream modifications so we can fixup the silent merge
conflict which is introduced by this merge.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

12 files changed, 97 insertions, 45 deletions

diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index 8d4dc97d80ba..35745a733100 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -97,6 +97,7 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
         }
 }
 
+#ifdef HAVE_LIBELF_SUPPORT
 void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
                                            int ntevs)
 {
@@ -118,5 +119,6 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
                 }
         }
 }
+#endif /* HAVE_LIBELF_SUPPORT */
 
 #endif
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index fb51457ba338..a2412e9d883b 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -501,7 +501,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
         struct intel_pt_recording *ptr =
                         container_of(itr, struct intel_pt_recording, itr);
         struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
-        bool have_timing_info;
+        bool have_timing_info, need_immediate = false;
         struct perf_evsel *evsel, *intel_pt_evsel = NULL;
         const struct cpu_map *cpus = evlist->cpus;
         bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
@@ -655,6 +655,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
                                 ptr->have_sched_switch = 3;
                         } else {
                                 opts->record_switch_events = true;
+                                need_immediate = true;
                                 if (cpu_wide)
                                         ptr->have_sched_switch = 3;
                                 else
@@ -700,6 +701,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
                 tracking_evsel->attr.freq = 0;
                 tracking_evsel->attr.sample_period = 1;
 
+                if (need_immediate)
+                        tracking_evsel->immediate = true;
+
                 /* In per-cpu case, always need the time of mmap events etc */
                 if (!cpu_map__empty(cpus)) {
                         perf_evsel__set_sample_bit(tracking_evsel, TIME);
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index d608a2c9e48c..d1ce29be560e 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -88,6 +88,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
         if (mem->operation & MEM_OPERATION_LOAD)
                 perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
 
+        if (mem->operation & MEM_OPERATION_STORE)
+                perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
+
         if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
                 rec_argv[i++] = "-W";
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9c640a8081c7..c859e59dfe3e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -371,14 +371,16 @@ static int perf_session__check_output_opt(struct perf_session *session)
 
         if (!no_callchain) {
                 bool use_callchain = false;
+                bool not_pipe = false;
 
                 evlist__for_each_entry(session->evlist, evsel) {
+                        not_pipe = true;
                         if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
                                 use_callchain = true;
                                 break;
                         }
                 }
-                if (!use_callchain)
+                if (not_pipe && !use_callchain)
                         symbol_conf.use_callchain = false;
         }
 
@@ -1690,8 +1692,13 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
         snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
         scripts_dir = opendir(scripts_path);
-        if (!scripts_dir)
-                return -1;
+        if (!scripts_dir) {
+                fprintf(stdout,
+                        "open(%s) failed.\n"
+                        "Check \"PERF_EXEC_PATH\" env to set scripts dir.\n",
+                        scripts_path);
+                exit(-1);
+        }
 
         for_each_lang(scripts_path, scripts_dir, lang_dirent) {
                 snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d9b80ef881cd..21fd573106ed 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -507,17 +507,17 @@ static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
         u8 op, result, type = (config >>  0) & 0xff;
         const char *err = "unknown-ext-hardware-cache-type";
 
-        if (type > PERF_COUNT_HW_CACHE_MAX)
+        if (type >= PERF_COUNT_HW_CACHE_MAX)
                 goto out_err;
 
         op = (config >>  8) & 0xff;
         err = "unknown-ext-hardware-cache-op";
-        if (op > PERF_COUNT_HW_CACHE_OP_MAX)
+        if (op >= PERF_COUNT_HW_CACHE_OP_MAX)
                 goto out_err;
 
         result = (config >> 16) & 0xff;
         err = "unknown-ext-hardware-cache-result";
-        if (result > PERF_COUNT_HW_CACHE_RESULT_MAX)
+        if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
                 goto out_err;
 
         err = "invalid-cache";
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 9c8f15da86ce..8ff6c6a61291 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -123,8 +123,6 @@ struct intel_pt_decoder {
         bool have_calc_cyc_to_tsc;
         int exec_mode;
         unsigned int insn_bytes;
-        uint64_t sign_bit;
-        uint64_t sign_bits;
         uint64_t period;
         enum intel_pt_period_type period_type;
         uint64_t tot_insn_cnt;
@@ -191,9 +189,6 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
         decoder->data               = params->data;
         decoder->return_compression = params->return_compression;
 
-        decoder->sign_bit           = (uint64_t)1 << 47;
-        decoder->sign_bits          = ~(((uint64_t)1 << 48) - 1);
-
         decoder->period             = params->period;
         decoder->period_type        = params->period_type;
 
@@ -362,21 +357,30 @@ int intel_pt__strerror(int code, char *buf, size_t buflen)
         return 0;
 }
 
-static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
-                                 const struct intel_pt_pkt *packet,
+static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet,
                                  uint64_t last_ip)
 {
         uint64_t ip;
 
         switch (packet->count) {
-        case 2:
+        case 1:
                 ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) |
                      packet->payload;
                 break;
-        case 4:
+        case 2:
                 ip = (last_ip & (uint64_t)0xffffffff00000000ULL) |
                      packet->payload;
                 break;
+        case 3:
+                ip = packet->payload;
+                /* Sign-extend 6-byte ip */
+                if (ip & (uint64_t)0x800000000000ULL)
+                        ip |= (uint64_t)0xffff000000000000ULL;
+                break;
+        case 4:
+                ip = (last_ip & (uint64_t)0xffff000000000000ULL) |
+                     packet->payload;
+                break;
         case 6:
                 ip = packet->payload;
                 break;
@@ -384,16 +388,12 @@ static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
                 return 0;
         }
 
-        if (ip & decoder->sign_bit)
-                return ip | decoder->sign_bits;
-
         return ip;
 }
 
 static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder)
 {
-        decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet,
-                                            decoder->last_ip);
+        decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip);
 }
 
 static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder)
@@ -1657,6 +1657,12 @@ next:
         }
 }
 
+static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder)
+{
+        return decoder->last_ip || decoder->packet.count == 0 ||
+               decoder->packet.count == 3 || decoder->packet.count == 6;
+}
+
 /* Walk PSB+ packets to get in sync. */
 static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 {
@@ -1677,8 +1683,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 
                 case INTEL_PT_FUP:
                         decoder->pge = true;
-                        if (decoder->last_ip || decoder->packet.count == 6 ||
-                            decoder->packet.count == 0) {
+                        if (intel_pt_have_ip(decoder)) {
                                 uint64_t current_ip = decoder->ip;
 
                                 intel_pt_set_ip(decoder);
@@ -1767,8 +1772,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
                 case INTEL_PT_TIP_PGE:
                 case INTEL_PT_TIP:
                         decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
-                        if (decoder->last_ip || decoder->packet.count == 6 ||
-                            decoder->packet.count == 0)
+                        if (intel_pt_have_ip(decoder))
                                 intel_pt_set_ip(decoder);
                         if (decoder->ip)
                                 return 0;
@@ -1776,9 +1780,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 
                 case INTEL_PT_FUP:
                         if (decoder->overflow) {
-                                if (decoder->last_ip ||
-                                    decoder->packet.count == 6 ||
-                                    decoder->packet.count == 0)
+                                if (intel_pt_have_ip(decoder))
                                         intel_pt_set_ip(decoder);
                                 if (decoder->ip)
                                         return 0;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index b1257c816310..4f7b32020487 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -292,36 +292,46 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte,
                            const unsigned char *buf, size_t len,
                            struct intel_pt_pkt *packet)
 {
-        switch (byte >> 5) {
+        int ip_len;
+
+        packet->count = byte >> 5;
+
+        switch (packet->count) {
         case 0:
-                packet->count = 0;
+                ip_len = 0;
                 break;
         case 1:
                 if (len < 3)
                         return INTEL_PT_NEED_MORE_BYTES;
-                packet->count = 2;
+                ip_len = 2;
                 packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
                 break;
         case 2:
                 if (len < 5)
                         return INTEL_PT_NEED_MORE_BYTES;
-                packet->count = 4;
+                ip_len = 4;
                 packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1));
                 break;
         case 3:
-        case 6:
+        case 4:
                 if (len < 7)
                         return INTEL_PT_NEED_MORE_BYTES;
-                packet->count = 6;
+                ip_len = 6;
                 memcpy_le64(&packet->payload, buf + 1, 6);
                 break;
+        case 6:
+                if (len < 9)
+                        return INTEL_PT_NEED_MORE_BYTES;
+                ip_len = 8;
+                packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1));
+                break;
         default:
                 return INTEL_PT_BAD_PACKET;
         }
 
         packet->type = type;
 
-        return packet->count + 1;
+        return ip_len + 1;
 }
 
 static int intel_pt_get_mode(const unsigned char *buf, size_t len,
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 9f3305f6b6d5..95f0884aae02 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -1,3 +1,4 @@
+#include <sys/sysmacros.h>
 #include <sys/types.h>
 #include <stdio.h>
 #include <stdlib.h>
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 9aed9c332da6..9c3b9ed5b3c3 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -133,7 +133,7 @@ int probe_file__open_both(int *kfd, int *ufd, int flag)
 /* Get raw string list of current kprobe_events  or uprobe_events */
 struct strlist *probe_file__get_rawlist(int fd)
 {
-        int ret, idx;
+        int ret, idx, fddup;
         FILE *fp;
         char buf[MAX_CMDLEN];
         char *p;
@@ -143,8 +143,17 @@ struct strlist *probe_file__get_rawlist(int fd)
                 return NULL;
 
         sl = strlist__new(NULL, NULL);
+        if (sl == NULL)
+                return NULL;
+
+        fddup = dup(fd);
+        if (fddup < 0)
+                goto out_free_sl;
+
+        fp = fdopen(fddup, "r");
+        if (!fp)
+                goto out_close_fddup;
 
-        fp = fdopen(dup(fd), "r");
         while (!feof(fp)) {
                 p = fgets(buf, MAX_CMDLEN, fp);
                 if (!p)
@@ -156,13 +165,21 @@ struct strlist *probe_file__get_rawlist(int fd)
                 ret = strlist__add(sl, buf);
                 if (ret < 0) {
                         pr_debug("strlist__add failed (%d)\n", ret);
-                        strlist__delete(sl);
-                        return NULL;
+                        goto out_close_fp;
                 }
         }
         fclose(fp);
 
         return sl;
+
+out_close_fp:
+        fclose(fp);
+        goto out_free_sl;
+out_close_fddup:
+        close(fddup);
+out_free_sl:
+        strlist__delete(sl);
+        return NULL;
 }
 
 static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
@@ -447,12 +464,17 @@ static int probe_cache__load(struct probe_cache *pcache)
 {
         struct probe_cache_entry *entry = NULL;
         char buf[MAX_CMDLEN], *p;
-        int ret = 0;
+        int ret = 0, fddup;
         FILE *fp;
 
-        fp = fdopen(dup(pcache->fd), "r");
-        if (!fp)
+        fddup = dup(pcache->fd);
+        if (fddup < 0)
+                return -errno;
+        fp = fdopen(fddup, "r");
+        if (!fp) {
+                close(fddup);
                 return -EINVAL;
+        }
 
         while (!feof(fp)) {
                 if (!fgets(buf, MAX_CMDLEN, fp))
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a34321e9b44d..a811c13a74d6 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -837,7 +837,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
         sec = syms_ss->symtab;
         shdr = syms_ss->symshdr;
 
-        if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL))
+        if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr,
+                                ".text", NULL))
                 dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
 
         if (runtime_ss->opdsec)
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index cf5e250bc78e..783a53fb7a4e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -66,7 +66,7 @@ static int entry(u64 ip, struct unwind_info *ui)
         if (__report_module(&al, ip, ui))
                 return -1;
 
-        e->ip  = ip;
+        e->ip  = al.addr;
         e->map = al.map;
         e->sym = al.sym;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 97c0f8fc5561..20c2e5743903 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -542,7 +542,7 @@ static int entry(u64 ip, struct thread *thread,
         thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
                                    MAP__FUNCTION, ip, &al);
 
-        e.ip = ip;
+        e.ip = al.addr;
         e.map = al.map;
         e.sym = al.sym;