1 files changed, 465 insertions, 274 deletions

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 83cdc0a61fd6..68f36dc0344f 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "builtin.h"
 
 #include "perf.h"
@@ -87,6 +88,8 @@ enum perf_output_field {
         PERF_OUTPUT_BRSTACKINSN     = 1U << 23,
         PERF_OUTPUT_BRSTACKOFF      = 1U << 24,
         PERF_OUTPUT_SYNTH           = 1U << 25,
+        PERF_OUTPUT_PHYS_ADDR       = 1U << 26,
+        PERF_OUTPUT_UREGS           = 1U << 27,
 };
 
 struct output_option {
@@ -108,6 +111,7 @@ struct output_option {
         {.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
         {.str = "period", .field = PERF_OUTPUT_PERIOD},
         {.str = "iregs", .field = PERF_OUTPUT_IREGS},
+        {.str = "uregs", .field = PERF_OUTPUT_UREGS},
         {.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
         {.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
         {.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
@@ -119,6 +123,7 @@ struct output_option {
         {.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
         {.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
         {.str = "synth", .field = PERF_OUTPUT_SYNTH},
+        {.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
 };
 
 enum {
@@ -175,7 +180,8 @@ static struct {
                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
                               PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
                               PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
-                              PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
+                              PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT |
+                              PERF_OUTPUT_PHYS_ADDR,
 
                 .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
         },
@@ -205,6 +211,51 @@ static struct {
         },
 };
 
+struct perf_evsel_script {
+       char *filename;
+       FILE *fp;
+       u64  samples;
+};
+
+static struct perf_evsel_script *perf_evsel_script__new(struct perf_evsel *evsel,
+                                                        struct perf_data *data)
+{
+        struct perf_evsel_script *es = malloc(sizeof(*es));
+
+        if (es != NULL) {
+                if (asprintf(&es->filename, "%s.%s.dump", data->file.path, perf_evsel__name(evsel)) < 0)
+                        goto out_free;
+                es->fp = fopen(es->filename, "w");
+                if (es->fp == NULL)
+                        goto out_free_filename;
+                es->samples = 0;
+        }
+
+        return es;
+out_free_filename:
+        zfree(&es->filename);
+out_free:
+        free(es);
+        return NULL;
+}
+
+static void perf_evsel_script__delete(struct perf_evsel_script *es)
+{
+        zfree(&es->filename);
+        fclose(es->fp);
+        es->fp = NULL;
+        free(es);
+}
+
+static int perf_evsel_script__fprintf(struct perf_evsel_script *es, FILE *fp)
+{
+        struct stat st;
+
+        fstat(fileno(es->fp), &st);
+        return fprintf(fp, "[ perf script: Wrote %.3f MB %s (%" PRIu64 " samples) ]\n",
+                       st.st_size / 1024.0 / 1024.0, es->filename, es->samples);
+}
+
 static inline int output_type(unsigned int type)
 {
         switch (type) {
@@ -382,6 +433,16 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                                         PERF_OUTPUT_IREGS))
                 return -EINVAL;
 
+        if (PRINT_FIELD(UREGS) &&
+                perf_evsel__check_stype(evsel, PERF_SAMPLE_REGS_USER, "UREGS",
+                                        PERF_OUTPUT_UREGS))
+                return -EINVAL;
+
+        if (PRINT_FIELD(PHYS_ADDR) &&
+                perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
+                                        PERF_OUTPUT_PHYS_ADDR))
+                return -EINVAL;
+
         return 0;
 }
 
@@ -485,51 +546,76 @@ out:
         return 0;
 }
 
-static void print_sample_iregs(struct perf_sample *sample,
-                          struct perf_event_attr *attr)
+static int perf_sample__fprintf_iregs(struct perf_sample *sample,
+                                      struct perf_event_attr *attr, FILE *fp)
 {
         struct regs_dump *regs = &sample->intr_regs;
         uint64_t mask = attr->sample_regs_intr;
         unsigned i = 0, r;
+        int printed = 0;
 
         if (!regs)
-                return;
+                return 0;
+
+        for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
+                u64 val = regs->regs[i++];
+                printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+        }
+
+        return printed;
+}
+
+static int perf_sample__fprintf_uregs(struct perf_sample *sample,
+                                      struct perf_event_attr *attr, FILE *fp)
+{
+        struct regs_dump *regs = &sample->user_regs;
+        uint64_t mask = attr->sample_regs_user;
+        unsigned i = 0, r;
+        int printed = 0;
+
+        if (!regs || !regs->regs)
+                return 0;
+
+        printed += fprintf(fp, " ABI:%" PRIu64 " ", regs->abi);
 
         for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
                 u64 val = regs->regs[i++];
-                printf("%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+                printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
         }
+
+        return printed;
 }
 
-static void print_sample_start(struct perf_sample *sample,
-                               struct thread *thread,
-                               struct perf_evsel *evsel)
+static int perf_sample__fprintf_start(struct perf_sample *sample,
+                                      struct thread *thread,
+                                      struct perf_evsel *evsel, FILE *fp)
 {
         struct perf_event_attr *attr = &evsel->attr;
         unsigned long secs;
         unsigned long long nsecs;
+        int printed = 0;
 
         if (PRINT_FIELD(COMM)) {
                 if (latency_format)
-                        printf("%8.8s ", thread__comm_str(thread));
+                        printed += fprintf(fp, "%8.8s ", thread__comm_str(thread));
                 else if (PRINT_FIELD(IP) && symbol_conf.use_callchain)
-                        printf("%s ", thread__comm_str(thread));
+                        printed += fprintf(fp, "%s ", thread__comm_str(thread));
                 else
-                        printf("%16s ", thread__comm_str(thread));
+                        printed += fprintf(fp, "%16s ", thread__comm_str(thread));
         }
 
         if (PRINT_FIELD(PID) && PRINT_FIELD(TID))
-                printf("%5d/%-5d ", sample->pid, sample->tid);
+                printed += fprintf(fp, "%5d/%-5d ", sample->pid, sample->tid);
         else if (PRINT_FIELD(PID))
-                printf("%5d ", sample->pid);
+                printed += fprintf(fp, "%5d ", sample->pid);
         else if (PRINT_FIELD(TID))
-                printf("%5d ", sample->tid);
+                printed += fprintf(fp, "%5d ", sample->tid);
 
         if (PRINT_FIELD(CPU)) {
                 if (latency_format)
-                        printf("%3d ", sample->cpu);
+                        printed += fprintf(fp, "%3d ", sample->cpu);
                 else
-                        printf("[%03d] ", sample->cpu);
+                        printed += fprintf(fp, "[%03d] ", sample->cpu);
         }
 
         if (PRINT_FIELD(TIME)) {
@@ -538,13 +624,15 @@ static void print_sample_start(struct perf_sample *sample,
                 nsecs -= secs * NSEC_PER_SEC;
 
                 if (nanosecs)
-                        printf("%5lu.%09llu: ", secs, nsecs);
+                        printed += fprintf(fp, "%5lu.%09llu: ", secs, nsecs);
                 else {
                         char sample_time[32];
                         timestamp__scnprintf_usec(sample->time, sample_time, sizeof(sample_time));
-                        printf("%12s: ", sample_time);
+                        printed += fprintf(fp, "%12s: ", sample_time);
                 }
         }
+
+        return printed;
 }
 
 static inline char
@@ -556,16 +644,17 @@ mispred_str(struct branch_entry *br)
         return br->flags.predicted ? 'P' : 'M';
 }
 
-static void print_sample_brstack(struct perf_sample *sample,
-                                 struct thread *thread,
-                                 struct perf_event_attr *attr)
+static int perf_sample__fprintf_brstack(struct perf_sample *sample,
+                                        struct thread *thread,
+                                        struct perf_event_attr *attr, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         struct addr_location alf, alt;
         u64 i, from, to;
+        int printed = 0;
 
         if (!(br && br->nr))
-                return;
+                return 0;
 
         for (i = 0; i < br->nr; i++) {
                 from = br->entries[i].from;
@@ -578,38 +667,41 @@ static void print_sample_brstack(struct perf_sample *sample,
                         thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
                 }
 
-                printf("0x%"PRIx64, from);
+                printed += fprintf(fp, " 0x%"PRIx64, from);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alf.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alf.map, fp);
+                        printed += fprintf(fp, ")");
                 }
 
-                printf("/0x%"PRIx64, to);
+                printed += fprintf(fp, "/0x%"PRIx64, to);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alt.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alt.map, fp);
+                        printed += fprintf(fp, ")");
                 }
 
-                printf("/%c/%c/%c/%d ",
+                printed += fprintf(fp, "/%c/%c/%c/%d ",
                         mispred_str( br->entries + i),
                         br->entries[i].flags.in_tx? 'X' : '-',
                         br->entries[i].flags.abort? 'A' : '-',
                         br->entries[i].flags.cycles);
         }
+
+        return printed;
 }
 
-static void print_sample_brstacksym(struct perf_sample *sample,
-                                    struct thread *thread,
-                                    struct perf_event_attr *attr)
+static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
+                                           struct thread *thread,
+                                           struct perf_event_attr *attr, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         struct addr_location alf, alt;
         u64 i, from, to;
+        int printed = 0;
 
         if (!(br && br->nr))
-                return;
+                return 0;
 
         for (i = 0; i < br->nr; i++) {
 
@@ -626,37 +718,40 @@ static void print_sample_brstacksym(struct perf_sample *sample,
                 if (alt.map)
                         alt.sym = map__find_symbol(alt.map, alt.addr);
 
-                symbol__fprintf_symname_offs(alf.sym, &alf, stdout);
+                printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alf.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alf.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                putchar('/');
-                symbol__fprintf_symname_offs(alt.sym, &alt, stdout);
+                printed += fprintf(fp, "%c", '/');
+                printed += symbol__fprintf_symname_offs(alt.sym, &alt, fp);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alt.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alt.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                printf("/%c/%c/%c/%d ",
+                printed += fprintf(fp, "/%c/%c/%c/%d ",
                         mispred_str( br->entries + i),
                         br->entries[i].flags.in_tx? 'X' : '-',
                         br->entries[i].flags.abort? 'A' : '-',
                         br->entries[i].flags.cycles);
         }
+
+        return printed;
 }
 
-static void print_sample_brstackoff(struct perf_sample *sample,
-                                    struct thread *thread,
-                                    struct perf_event_attr *attr)
+static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
+                                           struct thread *thread,
+                                           struct perf_event_attr *attr, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         struct addr_location alf, alt;
         u64 i, from, to;
+        int printed = 0;
 
         if (!(br && br->nr))
-                return;
+                return 0;
 
         for (i = 0; i < br->nr; i++) {
 
@@ -673,24 +768,26 @@ static void print_sample_brstackoff(struct perf_sample *sample,
                 if (alt.map && !alt.map->dso->adjust_symbols)
                         to = map__map_ip(alt.map, to);
 
-                printf("0x%"PRIx64, from);
+                printed += fprintf(fp, " 0x%"PRIx64, from);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alf.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alf.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                printf("/0x%"PRIx64, to);
+                printed += fprintf(fp, "/0x%"PRIx64, to);
                 if (PRINT_FIELD(DSO)) {
-                        printf("(");
-                        map__fprintf_dsoname(alt.map, stdout);
-                        printf(")");
+                        printed += fprintf(fp, "(");
+                        printed += map__fprintf_dsoname(alt.map, fp);
+                        printed += fprintf(fp, ")");
                 }
-                printf("/%c/%c/%c/%d ",
+                printed += fprintf(fp, "/%c/%c/%c/%d ",
                         mispred_str(br->entries + i),
                         br->entries[i].flags.in_tx ? 'X' : '-',
                         br->entries[i].flags.abort ? 'A' : '-',
                         br->entries[i].flags.cycles);
         }
+
+        return printed;
 }
 #define MAXBB 16384UL
 
@@ -718,27 +815,26 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
          * but the exit is not. Let the caller patch it up.
          */
         if (kernel != machine__kernel_ip(machine, end)) {
-                printf("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n",
-                                start, end);
+                pr_debug("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n", start, end);
                 return -ENXIO;
         }
 
         memset(&al, 0, sizeof(al));
         if (end - start > MAXBB - MAXINSN) {
                 if (last)
-                        printf("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end);
+                        pr_debug("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end);
                 else
-                        printf("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start);
+                        pr_debug("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start);
                 return 0;
         }
 
         thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al);
         if (!al.map || !al.map->dso) {
-                printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+                pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
                 return 0;
         }
         if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) {
-                printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+                pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
                 return 0;
         }
 
@@ -751,36 +847,35 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
 
         *is64bit = al.map->dso->is_64_bit;
         if (len <= 0)
-                printf("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n",
+                pr_debug("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n",
                         start, end);
         return len;
 }
 
-static void print_jump(uint64_t ip, struct branch_entry *en,
-                       struct perf_insn *x, u8 *inbuf, int len,
-                       int insn)
+static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
+                            struct perf_insn *x, u8 *inbuf, int len,
+                            int insn, FILE *fp)
 {
-        printf("\t%016" PRIx64 "\t%-30s\t#%s%s%s%s",
-               ip,
-               dump_insn(x, ip, inbuf, len, NULL),
-               en->flags.predicted ? " PRED" : "",
-               en->flags.mispred ? " MISPRED" : "",
-               en->flags.in_tx ? " INTX" : "",
-               en->flags.abort ? " ABORT" : "");
+        int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip,
+                              dump_insn(x, ip, inbuf, len, NULL),
+                              en->flags.predicted ? " PRED" : "",
+                              en->flags.mispred ? " MISPRED" : "",
+                              en->flags.in_tx ? " INTX" : "",
+                              en->flags.abort ? " ABORT" : "");
         if (en->flags.cycles) {
-                printf(" %d cycles", en->flags.cycles);
+                printed += fprintf(fp, " %d cycles", en->flags.cycles);
                 if (insn)
-                        printf(" %.2f IPC", (float)insn / en->flags.cycles);
+                        printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles);
         }
-        putchar('\n');
+        return printed + fprintf(fp, "\n");
 }
 
-static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
-                         uint64_t addr, struct symbol **lastsym,
-                         struct perf_event_attr *attr)
+static int ip__fprintf_sym(uint64_t addr, struct thread *thread,
+                           u8 cpumode, int cpu, struct symbol **lastsym,
+                           struct perf_event_attr *attr, FILE *fp)
 {
         struct addr_location al;
-        int off;
+        int off, printed = 0;
 
         memset(&al, 0, sizeof(al));
 
@@ -789,7 +884,7 @@ static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
                 thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
                                       addr, &al);
         if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end)
-                return;
+                return 0;
 
         al.cpu = cpu;
         al.sym = NULL;
@@ -797,37 +892,39 @@ static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
                 al.sym = map__find_symbol(al.map, al.addr);
 
         if (!al.sym)
-                return;
+                return 0;
 
         if (al.addr < al.sym->end)
                 off = al.addr - al.sym->start;
         else
                 off = al.addr - al.map->start - al.sym->start;
-        printf("\t%s", al.sym->name);
+        printed += fprintf(fp, "\t%s", al.sym->name);
         if (off)
-                printf("%+d", off);
-        putchar(':');
+                printed += fprintf(fp, "%+d", off);
+        printed += fprintf(fp, ":");
         if (PRINT_FIELD(SRCLINE))
-                map__fprintf_srcline(al.map, al.addr, "\t", stdout);
-        putchar('\n');
+                printed += map__fprintf_srcline(al.map, al.addr, "\t", fp);
+        printed += fprintf(fp, "\n");
         *lastsym = al.sym;
+
+        return printed;
 }
 
-static void print_sample_brstackinsn(struct perf_sample *sample,
-                                     struct thread *thread,
-                                     struct perf_event_attr *attr,
-                                     struct machine *machine)
+static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
+                                            struct thread *thread,
+                                            struct perf_event_attr *attr,
+                                            struct machine *machine, FILE *fp)
 {
         struct branch_stack *br = sample->branch_stack;
         u64 start, end;
-        int i, insn, len, nr, ilen;
+        int i, insn, len, nr, ilen, printed = 0;
         struct perf_insn x;
         u8 buffer[MAXBB];
         unsigned off;
         struct symbol *lastsym = NULL;
 
         if (!(br && br->nr))
-                return;
+                return 0;
         nr = br->nr;
         if (max_blocks && nr > max_blocks + 1)
                 nr = max_blocks + 1;
@@ -835,17 +932,17 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
         x.thread = thread;
         x.cpu = sample->cpu;
 
-        putchar('\n');
+        printed += fprintf(fp, "%c", '\n');
 
         /* Handle first from jump, of which we don't know the entry. */
         len = grab_bb(buffer, br->entries[nr-1].from,
                         br->entries[nr-1].from,
                         machine, thread, &x.is64bit, &x.cpumode, false);
         if (len > 0) {
-                print_ip_sym(thread, x.cpumode, x.cpu,
-                             br->entries[nr - 1].from, &lastsym, attr);
-                print_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
-                            &x, buffer, len, 0);
+                printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
+                                           x.cpumode, x.cpu, &lastsym, attr, fp);
+                printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
+                                            &x, buffer, len, 0, fp);
         }
 
         /* Print all blocks */
@@ -871,13 +968,13 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
                 for (off = 0;; off += ilen) {
                         uint64_t ip = start + off;
 
-                        print_ip_sym(thread, x.cpumode, x.cpu, ip, &lastsym, attr);
+                        printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
                         if (ip == end) {
-                                print_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn);
+                                printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp);
                                 break;
                         } else {
-                                printf("\t%016" PRIx64 "\t%s\n", ip,
-                                        dump_insn(&x, ip, buffer + off, len - off, &ilen));
+                                printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
+                                                   dump_insn(&x, ip, buffer + off, len - off, &ilen));
                                 if (ilen == 0)
                                         break;
                                 insn++;
@@ -890,9 +987,9 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
          * has not been executed yet.
          */
         if (br->entries[0].from == sample->ip)
-                return;
+                goto out;
         if (br->entries[0].flags.abort)
-                return;
+                goto out;
 
         /*
          * Print final block upto sample
@@ -900,58 +997,61 @@ static void print_sample_brstackinsn(struct perf_sample *sample,
         start = br->entries[0].to;
         end = sample->ip;
         len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true);
-        print_ip_sym(thread, x.cpumode, x.cpu, start, &lastsym, attr);
+        printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
         if (len <= 0) {
                 /* Print at least last IP if basic block did not work */
                 len = grab_bb(buffer, sample->ip, sample->ip,
                               machine, thread, &x.is64bit, &x.cpumode, false);
                 if (len <= 0)
-                        return;
+                        goto out;
 
-                printf("\t%016" PRIx64 "\t%s\n", sample->ip,
+                printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", sample->ip,
                         dump_insn(&x, sample->ip, buffer, len, NULL));
-                return;
+                goto out;
         }
         for (off = 0; off <= end - start; off += ilen) {
-                printf("\t%016" PRIx64 "\t%s\n", start + off,
-                        dump_insn(&x, start + off, buffer + off, len - off, &ilen));
+                printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", start + off,
+                                   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
                 if (ilen == 0)
                         break;
         }
+out:
+        return printed;
 }
 
-static void print_sample_addr(struct perf_sample *sample,
-                          struct thread *thread,
-                          struct perf_event_attr *attr)
+static int perf_sample__fprintf_addr(struct perf_sample *sample,
+                                     struct thread *thread,
+                                     struct perf_event_attr *attr, FILE *fp)
 {
         struct addr_location al;
-
-        printf("%16" PRIx64, sample->addr);
+        int printed = fprintf(fp, "%16" PRIx64, sample->addr);
 
         if (!sample_addr_correlates_sym(attr))
-                return;
+                goto out;
 
         thread__resolve(thread, &al, sample);
 
         if (PRINT_FIELD(SYM)) {
-                printf(" ");
+                printed += fprintf(fp, " ");
                 if (PRINT_FIELD(SYMOFFSET))
-                        symbol__fprintf_symname_offs(al.sym, &al, stdout);
+                        printed += symbol__fprintf_symname_offs(al.sym, &al, fp);
                 else
-                        symbol__fprintf_symname(al.sym, stdout);
+                        printed += symbol__fprintf_symname(al.sym, fp);
         }
 
         if (PRINT_FIELD(DSO)) {
-                printf(" (");
-                map__fprintf_dsoname(al.map, stdout);
-                printf(")");
+                printed += fprintf(fp, " (");
+                printed += map__fprintf_dsoname(al.map, fp);
+                printed += fprintf(fp, ")");
         }
+out:
+        return printed;
 }
 
-static void print_sample_callindent(struct perf_sample *sample,
-                                    struct perf_evsel *evsel,
-                                    struct thread *thread,
-                                    struct addr_location *al)
+static int perf_sample__fprintf_callindent(struct perf_sample *sample,
+                                           struct perf_evsel *evsel,
+                                           struct thread *thread,
+                                           struct addr_location *al, FILE *fp)
 {
         struct perf_event_attr *attr = &evsel->attr;
         size_t depth = thread_stack__depth(thread);
@@ -986,12 +1086,12 @@ static void print_sample_callindent(struct perf_sample *sample,
         }
 
         if (name)
-                len = printf("%*s%s", (int)depth * 4, "", name);
+                len = fprintf(fp, "%*s%s", (int)depth * 4, "", name);
         else if (ip)
-                len = printf("%*s%16" PRIx64, (int)depth * 4, "", ip);
+                len = fprintf(fp, "%*s%16" PRIx64, (int)depth * 4, "", ip);
 
         if (len < 0)
-                return;
+                return len;
 
         /*
          * Try to keep the output length from changing frequently so that the
@@ -1001,39 +1101,46 @@ static void print_sample_callindent(struct perf_sample *sample,
                 spacing = round_up(len + 4, 32);
 
         if (len < spacing)
-                printf("%*s", spacing - len, "");
+                len += fprintf(fp, "%*s", spacing - len, "");
+
+        return len;
 }
 
-static void print_insn(struct perf_sample *sample,
-                       struct perf_event_attr *attr,
-                       struct thread *thread,
-                       struct machine *machine)
+static int perf_sample__fprintf_insn(struct perf_sample *sample,
+                                     struct perf_event_attr *attr,
+                                     struct thread *thread,
+                                     struct machine *machine, FILE *fp)
 {
+        int printed = 0;
+
         if (PRINT_FIELD(INSNLEN))
-                printf(" ilen: %d", sample->insn_len);
+                printed += fprintf(fp, " ilen: %d", sample->insn_len);
         if (PRINT_FIELD(INSN)) {
                 int i;
 
-                printf(" insn:");
+                printed += fprintf(fp, " insn:");
                 for (i = 0; i < sample->insn_len; i++)
-                        printf(" %02x", (unsigned char)sample->insn[i]);
+                        printed += fprintf(fp, " %02x", (unsigned char)sample->insn[i]);
         }
         if (PRINT_FIELD(BRSTACKINSN))
-                print_sample_brstackinsn(sample, thread, attr, machine);
+                printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
+
+        return printed;
 }
 
-static void print_sample_bts(struct perf_sample *sample,
-                             struct perf_evsel *evsel,
-                             struct thread *thread,
-                             struct addr_location *al,
-                             struct machine *machine)
+static int perf_sample__fprintf_bts(struct perf_sample *sample,
+                                    struct perf_evsel *evsel,
+                                    struct thread *thread,
+                                    struct addr_location *al,
+                                    struct machine *machine, FILE *fp)
 {
         struct perf_event_attr *attr = &evsel->attr;
         unsigned int type = output_type(attr->type);
         bool print_srcline_last = false;
+        int printed = 0;
 
         if (PRINT_FIELD(CALLINDENT))
-                print_sample_callindent(sample, evsel, thread, al);
+                printed += perf_sample__fprintf_callindent(sample, evsel, thread, al, fp);
 
         /* print branch_from information */
         if (PRINT_FIELD(IP)) {
@@ -1046,31 +1153,30 @@ static void print_sample_bts(struct perf_sample *sample,
                         cursor = &callchain_cursor;
 
                 if (cursor == NULL) {
-                        putchar(' ');
+                        printed += fprintf(fp, " ");
                         if (print_opts & EVSEL__PRINT_SRCLINE) {
                                 print_srcline_last = true;
                                 print_opts &= ~EVSEL__PRINT_SRCLINE;
                         }
                 } else
-                        putchar('\n');
+                        printed += fprintf(fp, "\n");
 
-                sample__fprintf_sym(sample, al, 0, print_opts, cursor, stdout);
+                printed += sample__fprintf_sym(sample, al, 0, print_opts, cursor, fp);
         }
 
         /* print branch_to information */
         if (PRINT_FIELD(ADDR) ||
             ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
              !output[type].user_set)) {
-                printf(" => ");
-                print_sample_addr(sample, thread, attr);
+                printed += fprintf(fp, " => ");
+                printed += perf_sample__fprintf_addr(sample, thread, attr, fp);
         }
 
         if (print_srcline_last)
-                map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
-
-        print_insn(sample, attr, thread, machine);
+                printed += map__fprintf_srcline(al->map, al->addr, "\n  ", fp);
 
-        printf("\n");
+        printed += perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
+        return printed + fprintf(fp, "\n");
 }
 
 static struct {
@@ -1093,7 +1199,7 @@ static struct {
         {0, NULL}
 };
 
-static void print_sample_flags(u32 flags)
+static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 {
         const char *chars = PERF_IP_FLAG_CHARS;
         const int n = strlen(PERF_IP_FLAG_CHARS);
@@ -1120,9 +1226,9 @@ static void print_sample_flags(u32 flags)
         str[pos] = 0;
 
         if (name)
-                printf("  %-7s%4s ", name, in_tx ? "(x)" : "");
-        else
-                printf("  %-11s ", str);
+                return fprintf(fp, "  %-7s%4s ", name, in_tx ? "(x)" : "");
+
+        return fprintf(fp, "  %-11s ", str);
 }
 
 struct printer_data {
@@ -1131,40 +1237,40 @@ struct printer_data {
         bool is_printable;
 };
 
-static void
-print_sample_bpf_output_printer(enum binary_printer_ops op,
-                                unsigned int val,
-                                void *extra)
+static int sample__fprintf_bpf_output(enum binary_printer_ops op,
+                                      unsigned int val,
+                                      void *extra, FILE *fp)
 {
         unsigned char ch = (unsigned char)val;
         struct printer_data *printer_data = extra;
+        int printed = 0;
 
         switch (op) {
         case BINARY_PRINT_DATA_BEGIN:
-                printf("\n");
+                printed += fprintf(fp, "\n");
                 break;
         case BINARY_PRINT_LINE_BEGIN:
-                printf("%17s", !printer_data->line_no ? "BPF output:" :
+                printed += fprintf(fp, "%17s", !printer_data->line_no ? "BPF output:" :
                                                         "           ");
                 break;
         case BINARY_PRINT_ADDR:
-                printf(" %04x:", val);
+                printed += fprintf(fp, " %04x:", val);
                 break;
         case BINARY_PRINT_NUM_DATA:
-                printf(" %02x", val);
+                printed += fprintf(fp, " %02x", val);
                 break;
         case BINARY_PRINT_NUM_PAD:
-                printf("   ");
+                printed += fprintf(fp, "   ");
                 break;
         case BINARY_PRINT_SEP:
-                printf("  ");
+                printed += fprintf(fp, "  ");
                 break;
         case BINARY_PRINT_CHAR_DATA:
                 if (printer_data->hit_nul && ch)
                         printer_data->is_printable = false;
 
                 if (!isprint(ch)) {
-                        printf("%c", '.');
+                        printed += fprintf(fp, "%c", '.');
 
                         if (!printer_data->is_printable)
                                 break;
@@ -1174,154 +1280,154 @@ print_sample_bpf_output_printer(enum binary_printer_ops op,
                         else
                                 printer_data->is_printable = false;
                 } else {
-                        printf("%c", ch);
+                        printed += fprintf(fp, "%c", ch);
                 }
                 break;
         case BINARY_PRINT_CHAR_PAD:
-                printf(" ");
+                printed += fprintf(fp, " ");
                 break;
         case BINARY_PRINT_LINE_END:
-                printf("\n");
+                printed += fprintf(fp, "\n");
                 printer_data->line_no++;
                 break;
         case BINARY_PRINT_DATA_END:
         default:
                 break;
         }
+
+        return printed;
 }
 
-static void print_sample_bpf_output(struct perf_sample *sample)
+static int perf_sample__fprintf_bpf_output(struct perf_sample *sample, FILE *fp)
 {
         unsigned int nr_bytes = sample->raw_size;
         struct printer_data printer_data = {0, false, true};
-
-        print_binary(sample->raw_data, nr_bytes, 8,
-                     print_sample_bpf_output_printer, &printer_data);
+        int printed = binary__fprintf(sample->raw_data, nr_bytes, 8,
+                                      sample__fprintf_bpf_output, &printer_data, fp);
 
         if (printer_data.is_printable && printer_data.hit_nul)
-                printf("%17s \"%s\"\n", "BPF string:",
-                       (char *)(sample->raw_data));
+                printed += fprintf(fp, "%17s \"%s\"\n", "BPF string:", (char *)(sample->raw_data));
+
+        return printed;
 }
 
-static void print_sample_spacing(int len, int spacing)
+static int perf_sample__fprintf_spacing(int len, int spacing, FILE *fp)
 {
         if (len > 0 && len < spacing)
-                printf("%*s", spacing - len, "");
+                return fprintf(fp, "%*s", spacing - len, "");
+
+        return 0;
 }
 
-static void print_sample_pt_spacing(int len)
+static int perf_sample__fprintf_pt_spacing(int len, FILE *fp)
 {
-        print_sample_spacing(len, 34);
+        return perf_sample__fprintf_spacing(len, 34, fp);
 }
 
-static void print_sample_synth_ptwrite(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_ptwrite(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_ptwrite *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" IP: %u payload: %#" PRIx64 " ",
+        len = fprintf(fp, " IP: %u payload: %#" PRIx64 " ",
                      data->ip, le64_to_cpu(data->payload));
-        print_sample_pt_spacing(len);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_mwait(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_mwait(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_mwait *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" hints: %#x extensions: %#x ",
-                     data->hints, data->extensions);
-        print_sample_pt_spacing(len);
+        len = fprintf(fp, " hints: %#x extensions: %#x ",
+                      data->hints, data->extensions);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_pwre(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_pwre(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_pwre *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" hw: %u cstate: %u sub-cstate: %u ",
-                     data->hw, data->cstate, data->subcstate);
-        print_sample_pt_spacing(len);
+        len = fprintf(fp, " hw: %u cstate: %u sub-cstate: %u ",
+                      data->hw, data->cstate, data->subcstate);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_exstop(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_exstop(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_exstop *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" IP: %u ", data->ip);
-        print_sample_pt_spacing(len);
+        len = fprintf(fp, " IP: %u ", data->ip);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_pwrx(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_pwrx(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_pwrx *data = perf_sample__synth_ptr(sample);
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
-        len = printf(" deepest cstate: %u last cstate: %u wake reason: %#x ",
+        len = fprintf(fp, " deepest cstate: %u last cstate: %u wake reason: %#x ",
                      data->deepest_cstate, data->last_cstate,
                      data->wake_reason);
-        print_sample_pt_spacing(len);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth_cbr(struct perf_sample *sample)
+static int perf_sample__fprintf_synth_cbr(struct perf_sample *sample, FILE *fp)
 {
         struct perf_synth_intel_cbr *data = perf_sample__synth_ptr(sample);
         unsigned int percent, freq;
         int len;
 
         if (perf_sample__bad_synth_size(sample, *data))
-                return;
+                return 0;
 
         freq = (le32_to_cpu(data->freq) + 500) / 1000;
-        len = printf(" cbr: %2u freq: %4u MHz ", data->cbr, freq);
+        len = fprintf(fp, " cbr: %2u freq: %4u MHz ", data->cbr, freq);
         if (data->max_nonturbo) {
                 percent = (5 + (1000 * data->cbr) / data->max_nonturbo) / 10;
-                len += printf("(%3u%%) ", percent);
+                len += fprintf(fp, "(%3u%%) ", percent);
         }
-        print_sample_pt_spacing(len);
+        return len + perf_sample__fprintf_pt_spacing(len, fp);
 }
 
-static void print_sample_synth(struct perf_sample *sample,
-                               struct perf_evsel *evsel)
+static int perf_sample__fprintf_synth(struct perf_sample *sample,
+                                      struct perf_evsel *evsel, FILE *fp)
 {
         switch (evsel->attr.config) {
         case PERF_SYNTH_INTEL_PTWRITE:
-                print_sample_synth_ptwrite(sample);
-                break;
+                return perf_sample__fprintf_synth_ptwrite(sample, fp);
         case PERF_SYNTH_INTEL_MWAIT:
-                print_sample_synth_mwait(sample);
-                break;
+                return perf_sample__fprintf_synth_mwait(sample, fp);
         case PERF_SYNTH_INTEL_PWRE:
-                print_sample_synth_pwre(sample);
-                break;
+                return perf_sample__fprintf_synth_pwre(sample, fp);
         case PERF_SYNTH_INTEL_EXSTOP:
-                print_sample_synth_exstop(sample);
-                break;
+                return perf_sample__fprintf_synth_exstop(sample, fp);
         case PERF_SYNTH_INTEL_PWRX:
-                print_sample_synth_pwrx(sample);
-                break;
+                return perf_sample__fprintf_synth_pwrx(sample, fp);
         case PERF_SYNTH_INTEL_CBR:
-                print_sample_synth_cbr(sample);
-                break;
+                return perf_sample__fprintf_synth_cbr(sample, fp);
         default:
                 break;
         }
+
+        return 0;
 }
 
 struct perf_script {
@@ -1332,6 +1438,7 @@ struct perf_script {
         bool                    show_switch_events;
         bool                    show_namespace_events;
         bool                    allocated;
+        bool                    per_event_dump;
         struct cpu_map          *cpus;
         struct thread_map       *threads;
         int                     name_width;
@@ -1353,7 +1460,7 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
         return max;
 }
 
-static size_t data_src__printf(u64 data_src)
+static int data_src__fprintf(u64 data_src, FILE *fp)
 {
         struct mem_info mi = { .data_src.val = data_src };
         char decode[100];
@@ -1367,7 +1474,7 @@ static size_t data_src__printf(u64 data_src)
         if (maxlen < len)
                 maxlen = len;
 
-        return printf("%-*s", maxlen, out);
+        return fprintf(fp, "%-*s", maxlen, out);
 }
 
 static void process_event(struct perf_script *script,
@@ -1378,14 +1485,18 @@ static void process_event(struct perf_script *script,
         struct thread *thread = al->thread;
         struct perf_event_attr *attr = &evsel->attr;
         unsigned int type = output_type(attr->type);
+        struct perf_evsel_script *es = evsel->priv;
+        FILE *fp = es->fp;
 
         if (output[type].fields == 0)
                 return;
 
-        print_sample_start(sample, thread, evsel);
+        ++es->samples;
+
+        perf_sample__fprintf_start(sample, thread, evsel, fp);
 
         if (PRINT_FIELD(PERIOD))
-                printf("%10" PRIu64 " ", sample->period);
+                fprintf(fp, "%10" PRIu64 " ", sample->period);
 
         if (PRINT_FIELD(EVNAME)) {
                 const char *evname = perf_evsel__name(evsel);
@@ -1393,33 +1504,33 @@ static void process_event(struct perf_script *script,
                 if (!script->name_width)
                         script->name_width = perf_evlist__max_name_len(script->session->evlist);
 
-                printf("%*s: ", script->name_width,
-                       evname ? evname : "[unknown]");
+                fprintf(fp, "%*s: ", script->name_width, evname ?: "[unknown]");
         }
 
         if (print_flags)
-                print_sample_flags(sample->flags);
+                perf_sample__fprintf_flags(sample->flags, fp);
 
         if (is_bts_event(attr)) {
-                print_sample_bts(sample, evsel, thread, al, machine);
+                perf_sample__fprintf_bts(sample, evsel, thread, al, machine, fp);
                 return;
         }
 
-        if (PRINT_FIELD(TRACE))
-                event_format__print(evsel->tp_format, sample->cpu,
-                                    sample->raw_data, sample->raw_size);
+        if (PRINT_FIELD(TRACE)) {
+                event_format__fprintf(evsel->tp_format, sample->cpu,
+                                      sample->raw_data, sample->raw_size, fp);
+        }
 
         if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH))
-                print_sample_synth(sample, evsel);
+                perf_sample__fprintf_synth(sample, evsel, fp);
 
         if (PRINT_FIELD(ADDR))
-                print_sample_addr(sample, thread, attr);
+                perf_sample__fprintf_addr(sample, thread, attr, fp);
 
         if (PRINT_FIELD(DATA_SRC))
-                data_src__printf(sample->data_src);
+                data_src__fprintf(sample->data_src, fp);
 
         if (PRINT_FIELD(WEIGHT))
-                printf("%16" PRIu64, sample->weight);
+                fprintf(fp, "%16" PRIu64, sample->weight);
 
         if (PRINT_FIELD(IP)) {
                 struct callchain_cursor *cursor = NULL;
@@ -1429,24 +1540,30 @@ static void process_event(struct perf_script *script,
                                               sample, NULL, NULL, scripting_max_stack) == 0)
                         cursor = &callchain_cursor;
 
-                putchar(cursor ? '\n' : ' ');
-                sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, stdout);
+                fputc(cursor ? '\n' : ' ', fp);
+                sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, fp);
         }
 
         if (PRINT_FIELD(IREGS))
-                print_sample_iregs(sample, attr);
+                perf_sample__fprintf_iregs(sample, attr, fp);
+
+        if (PRINT_FIELD(UREGS))
+                perf_sample__fprintf_uregs(sample, attr, fp);
 
         if (PRINT_FIELD(BRSTACK))
-                print_sample_brstack(sample, thread, attr);
+                perf_sample__fprintf_brstack(sample, thread, attr, fp);
         else if (PRINT_FIELD(BRSTACKSYM))
-                print_sample_brstacksym(sample, thread, attr);
+                perf_sample__fprintf_brstacksym(sample, thread, attr, fp);
         else if (PRINT_FIELD(BRSTACKOFF))
-                print_sample_brstackoff(sample, thread, attr);
+                perf_sample__fprintf_brstackoff(sample, thread, attr, fp);
 
         if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
-                print_sample_bpf_output(sample);
-        print_insn(sample, attr, thread, machine);
-        printf("\n");
+                perf_sample__fprintf_bpf_output(sample, fp);
+        perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
+
+        if (PRINT_FIELD(PHYS_ADDR))
+                fprintf(fp, "%16" PRIx64, sample->phys_addr);
+        fprintf(fp, "\n");
 }
 
 static struct scripting_ops     *scripting_ops;
@@ -1620,7 +1737,7 @@ static int process_comm_event(struct perf_tool *tool,
                 sample->tid = event->comm.tid;
                 sample->pid = event->comm.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         ret = 0;
 out:
@@ -1655,7 +1772,7 @@ static int process_namespaces_event(struct perf_tool *tool,
                 sample->tid = event->namespaces.tid;
                 sample->pid = event->namespaces.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         ret = 0;
 out:
@@ -1688,7 +1805,7 @@ static int process_fork_event(struct perf_tool *tool,
                 sample->tid = event->fork.tid;
                 sample->pid = event->fork.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
 
@@ -1717,7 +1834,7 @@ static int process_exit_event(struct perf_tool *tool,
                 sample->tid = event->fork.tid;
                 sample->pid = event->fork.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
 
         if (perf_event__process_exit(tool, event, sample, machine) < 0)
@@ -1752,7 +1869,7 @@ static int process_mmap_event(struct perf_tool *tool,
                 sample->tid = event->mmap.tid;
                 sample->pid = event->mmap.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
         return 0;
@@ -1783,7 +1900,7 @@ static int process_mmap2_event(struct perf_tool *tool,
                 sample->tid = event->mmap2.tid;
                 sample->pid = event->mmap2.pid;
         }
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
         return 0;
@@ -1809,7 +1926,7 @@ static int process_switch_event(struct perf_tool *tool,
                 return -1;
         }
 
-        print_sample_start(sample, thread, evsel);
+        perf_sample__fprintf_start(sample, thread, evsel, stdout);
         perf_event__fprintf(event, stdout);
         thread__put(thread);
         return 0;
@@ -1820,6 +1937,65 @@ static void sig_handler(int sig __maybe_unused)
         session_done = 1;
 }
 
+static void perf_script__fclose_per_event_dump(struct perf_script *script)
+{
+        struct perf_evlist *evlist = script->session->evlist;
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(evlist, evsel) {
+                if (!evsel->priv)
+                        break;
+                perf_evsel_script__delete(evsel->priv);
+                evsel->priv = NULL;
+        }
+}
+
+static int perf_script__fopen_per_event_dump(struct perf_script *script)
+{
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(script->session->evlist, evsel) {
+                evsel->priv = perf_evsel_script__new(evsel, script->session->data);
+                if (evsel->priv == NULL)
+                        goto out_err_fclose;
+        }
+
+        return 0;
+
+out_err_fclose:
+        perf_script__fclose_per_event_dump(script);
+        return -1;
+}
+
+static int perf_script__setup_per_event_dump(struct perf_script *script)
+{
+        struct perf_evsel *evsel;
+        static struct perf_evsel_script es_stdout;
+
+        if (script->per_event_dump)
+                return perf_script__fopen_per_event_dump(script);
+
+        es_stdout.fp = stdout;
+
+        evlist__for_each_entry(script->session->evlist, evsel)
+                evsel->priv = &es_stdout;
+
+        return 0;
+}
+
+static void perf_script__exit_per_event_dump_stats(struct perf_script *script)
+{
+        struct perf_evsel *evsel;
+
+        evlist__for_each_entry(script->session->evlist, evsel) {
+                struct perf_evsel_script *es = evsel->priv;
+
+                perf_evsel_script__fprintf(es, stdout);
+                perf_evsel_script__delete(es);
+                evsel->priv = NULL;
+        }
+}
+
 static int __cmd_script(struct perf_script *script)
 {
         int ret;
@@ -1841,8 +2017,16 @@ static int __cmd_script(struct perf_script *script)
         if (script->show_namespace_events)
                 script->tool.namespaces = process_namespaces_event;
 
+        if (perf_script__setup_per_event_dump(script)) {
+                pr_err("Couldn't create the per event dump files\n");
+                return -1;
+        }
+
         ret = perf_session__process_events(script->session);
 
+        if (script->per_event_dump)
+                perf_script__exit_per_event_dump_stats(script);
+
         if (debug_mode)
                 pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
 
@@ -2199,16 +2383,11 @@ static struct script_desc *script_desc__findnew(const char *name)
 
         s = script_desc__new(name);
         if (!s)
-                goto out_delete_desc;
+                return NULL;
 
         script_desc__add(s);
 
         return s;
-
-out_delete_desc:
-        script_desc__delete(s);
-
-        return NULL;
 }
 
 static const char *ends_with(const char *str, const char *suffix)
@@ -2412,14 +2591,16 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
         char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
         DIR *scripts_dir, *lang_dir;
         struct perf_session *session;
-        struct perf_data_file file = {
-                .path = input_name,
-                .mode = PERF_DATA_MODE_READ,
+        struct perf_data data = {
+                .file      = {
+                        .path = input_name,
+                },
+                .mode      = PERF_DATA_MODE_READ,
         };
         char *temp;
         int i = 0;
 
-        session = perf_session__new(&file, false, NULL);
+        session = perf_session__new(&data, false, NULL);
         if (!session)
                 return -1;
 
@@ -2682,6 +2863,7 @@ int cmd_script(int argc, const char **argv)
                         .attr            = process_attr,
                         .event_update   = perf_event__process_event_update,
                         .tracing_data    = perf_event__process_tracing_data,
+                        .feature         = perf_event__process_feature,
                         .build_id        = perf_event__process_build_id,
                         .id_index        = perf_event__process_id_index,
                         .auxtrace_info   = perf_event__process_auxtrace_info,
@@ -2696,7 +2878,7 @@ int cmd_script(int argc, const char **argv)
                         .ordering_requires_timestamps = true,
                 },
         };
-        struct perf_data_file file = {
+        struct perf_data data = {
                 .mode = PERF_DATA_MODE_READ,
         };
         const struct option options[] = {
@@ -2732,8 +2914,8 @@ int cmd_script(int argc, const char **argv)
                      "+field to add and -field to remove."
                      "Valid types: hw,sw,trace,raw,synth. "
                      "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-                     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-                     "bpf-output,callindent,insn,insnlen,brstackinsn,synth",
+                     "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags,"
+                     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
                      parse_output_fields),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                     "system-wide collection from all CPUs"),
@@ -2764,6 +2946,8 @@ int cmd_script(int argc, const char **argv)
                     "Show context switch events (if recorded)"),
         OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events,
                     "Show namespace events (if recorded)"),
+        OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump,
+                    "Dump trace output to files named by the monitored events"),
         OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
         OPT_INTEGER(0, "max-blocks", &max_blocks,
                     "Maximum number of code blocks to dump with brstackinsn"),
@@ -2794,13 +2978,15 @@ int cmd_script(int argc, const char **argv)
                 NULL
         };
 
+        perf_set_singlethreaded();
+
         setup_scripting();
 
         argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
 
-        file.path = input_name;
-        file.force = symbol_conf.force;
+        data.file.path = input_name;
+        data.force     = symbol_conf.force;
 
         if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
                 rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
@@ -2967,15 +3153,18 @@ int cmd_script(int argc, const char **argv)
         if (!script_name)
                 setup_pager();
 
-        session = perf_session__new(&file, false, &script.tool);
+        session = perf_session__new(&data, false, &script.tool);
         if (session == NULL)
                 return -1;
 
         if (header || header_only) {
+                script.tool.show_feat_hdr = SHOW_FEAT_HEADER;
                 perf_session__fprintf_info(session, stdout, show_full_info);
                 if (header_only)
                         goto out_delete;
         }
+        if (show_full_info)
+                script.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO;
 
         if (symbol__init(&session->header.env) < 0)
                 goto out_delete;
@@ -3005,7 +3194,8 @@ int cmd_script(int argc, const char **argv)
                                          machine__resolve_kernel_addr,
                                          &session->machines.host) < 0) {
                 pr_err("%s: failed to set libtraceevent function resolver\n", __func__);
-                return -1;
+                err = -1;
+                goto out_delete;
         }
 
         if (generate_script_lang) {
@@ -3019,7 +3209,7 @@ int cmd_script(int argc, const char **argv)
                         goto out_delete;
                 }
 
-                input = open(file.path, O_RDONLY);      /* input_name */
+                input = open(data.file.path, O_RDONLY); /* input_name */
                 if (input < 0) {
                         err = -errno;
                         perror("failed to open file");
@@ -3065,7 +3255,8 @@ int cmd_script(int argc, const char **argv)
         /* needs to be parsed after looking up reference time */
         if (perf_time__parse_str(&script.ptime, script.time_str) != 0) {
                 pr_err("Invalid time string\n");
-                return -EINVAL;
+                err = -EINVAL;
+                goto out_delete;
         }
 
         err = __cmd_script(&script);