[PATCH] resync docs, dump_csv: support from the Perl version

[Eric Wong <e@80x24.org>]

I somehow forgot about the existence of the perror(3) function :x
---
 Documentation/mwrap.pod |  21 +++-
 README                  |  31 ++++--
 ext/mwrap/httpd.h       | 241 +++++++++++++++++++++-------------------
 ext/mwrap/mwrap_core.h  |  72 +++++++++---
 4 files changed, 222 insertions(+), 143 deletions(-)

diff --git a/Documentation/mwrap.pod b/Documentation/mwrap.pod
index 6832430..a31bc1f 100644
--- a/Documentation/mwrap.pod
+++ b/Documentation/mwrap.pod
@@ -7,8 +7,8 @@ mwrap - run any command under mwrap
   # to trace a long-running program and access it via $DIR/$PID.sock:
   MWRAP=socket_dir:$DIR mwrap COMMAND
 
-  # to trace a short-lived command and dump its output to a log:
-  MWRAP=dump_path:$FILENAME mwrap COMMAND
+  # to trace a short-lived command and dump its output to a CSV:
+  MWRAP=dump_csv:$FILENAME mwrap COMMAND
 
 =head1 DESCRIPTION
 
@@ -46,13 +46,28 @@ This may be changed via POST request (see below).
 
 Default: 0
 
+=item dump_csv:$FILENAME
+
+Dump CSV to the given filename.
+
+This output matches the HTTP server output and includes column headers,
+but is subject to change in future releases.
+
+C<dump_csv> without the C<:> may also be used in conjunction with
+C<dump_fd>, such as C<MWRAP=dump_fd:2,dump_csv>.
+
+As of mwrap 3.0,
+C<$FILENAME> may contain C<%p> where C<%p> is a placeholder for
+the PID being dumped.  No other use of C<%> is accepted, and
+multiple C<%> means all C<%> (including C<%p>) are handled as-is.
+
 =item dump_path:$FILENAME
 
 Dumps the output at exit to a given filename:
 
 	total_bytes	call_count	location
 
-In the future, dumping to a self-describing CSV will be supported.
+Expands C<%p> to the PID in C<$FILENAME> as described for C<dump_csv>
 
 =item dump_fd:$DESCRIPTOR
 
diff --git a/README b/README
index 761f87e..f969c14 100644
--- a/README
+++ b/README
@@ -16,20 +16,24 @@ numeric caller addresses for allocations made without GVL so you
 can get an idea of how much memory usage certain extensions and
 native libraries use.
 
+As of 3.0, it also gives configurable C backtraces of all
+dynamically-linked malloc callsites for any program where backtrace(3)
+works, including programs not linked to Ruby.
+
 It requires the concurrent lock-free hash table from the
 Userspace RCU project: https://liburcu.org/
 
 It does not require recompiling or rebuilding Ruby, but only
 supports Ruby 2.7.0 or later on a few platforms:
 
-* GNU/Linux (only tested --without-jemalloc, mwrap 3.x provides its own)
+* GNU/Linux (only tested --without-jemalloc, mwrap 3.x provides its own malloc)
 
 It may work on FreeBSD, NetBSD, OpenBSD and DragonFly BSD if given
 appropriate build options.
 
 == Install
 
-	# Debian-based systems: apt-get liburcu-dev
+	# Debian-based systems: apt-get install liburcu-dev
 
 	# Install mwrap via RubyGems.org
 	gem install mwrap
@@ -37,13 +41,21 @@ appropriate build options.
 == Usage
 
 mwrap works as an LD_PRELOAD and supplies a mwrap RubyGem executable to
-improve ease-of-use.  You can set dump_path: in the MWRAP environment
-variable to append the results to a log file:
+improve ease-of-use.  You can set `dump_csv:' in the MWRAP environment
+variable to append the results to a CSV file:
+
+	MWRAP=dump_csv:/path/to/log mwrap RUBY_COMMAND
+
+(`dump_csv:' is new in mwrap 3.x, `dump_file:' from earlier versions is
+still supported).
 
-	MWRAP=dump_path:/path/to/log mwrap RUBY_COMMAND
+For long running processes, you can see the AF_UNIX HTTP interface:
 
-	# And to display the locations with the most allocations:
-	sort -k1,1rn </path/to/log | $PAGER
+	MWRAP=socket_dir:/some/dir mwrap COMMAND
+
+And connect via `curl --unix-socket /some/dir/$PID.sock' or
+`mwrap-rproxy(1p)<https://80x24.org/mwrap-perl.git/tree/script/mwrap-rproxy#n44>
+for more info.
 
 You may also `require "mwrap"' in your Ruby code and use
 Mwrap.dump, Mwrap.reset, Mwrap.each, etc.
@@ -53,7 +65,10 @@ effect in tracking malloc use.  However, it is safe to keep
 "require 'mwrap'" in performance-critical deployments,
 as overhead is only incurred when used as an LD_PRELOAD.
 
-The output of the mwrap dump is a text file with 3 columns:
+The output of `dump_csv:' is has self-describing columns and is
+subject to change.  SQLite 3.32+ can load it with: `.import --csv'.
+
+The output of the `dump_file:' output is a text file with 3 columns:
 
 	total_bytes	call_count	location
 
diff --git a/ext/mwrap/httpd.h b/ext/mwrap/httpd.h
index ef4d83c..8a105aa 100644
--- a/ext/mwrap/httpd.h
+++ b/ext/mwrap/httpd.h
@@ -221,7 +221,7 @@ static FILE *fbuf_init(struct mw_fbuf *fb)
 {
 	fb->ptr = NULL;
 	fb->fp = open_memstream(&fb->ptr, &fb->len);
-	if (!fb->fp) fprintf(stderr, "open_memstream: %m\n");
+	if (!fb->fp) perror("open_memstream");
 	return fb->fp;
 }
 
@@ -237,7 +237,7 @@ static int fbuf_close(struct mw_fbuf *fb)
 {
 	int e = ferror(fb->fp) | fclose(fb->fp);
 	fb->fp = NULL;
-	if (e) fprintf(stderr, "ferror|fclose: %m\n");
+	if (e) perror("ferror|fclose");
 	return e;
 }
 
@@ -279,7 +279,7 @@ static enum mw_qev h1_200(struct mw_h1 *h1, struct mw_fbuf *fb, const char *ct)
 	 */
 	off_t clen = ftello(fb->fp);
 	if (clen < 0) {
-		fprintf(stderr, "ftello: %m\n");
+		perror("ftello");
 		fbuf_close(fb);
 		return h1_close(h1);
 	}
@@ -468,7 +468,7 @@ static off_t write_loc_name(FILE *fp, const struct src_loc *l)
 	off_t beg = ftello(fp);
 
 	if (beg < 0) {
-		fprintf(stderr, "ftello: %m\n");
+		perror("ftello");
 		return beg;
 	}
 	if (l->f) {
@@ -498,15 +498,17 @@ static off_t write_loc_name(FILE *fp, const struct src_loc *l)
 	}
 	off_t end = ftello(fp);
 	if (end < 0) {
-		fprintf(stderr, "ftello: %m\n");
+		perror("ftello");
 		return end;
 	}
 	return end - beg;
 }
 
-static struct h1_src_loc *accumulate(unsigned long min, size_t *hslc, FILE *lp)
+static struct h1_src_loc *
+accumulate(struct mw_fbuf *lb, unsigned long min, size_t *hslc)
 {
 	struct mw_fbuf fb;
+	if (!fbuf_init(lb)) return NULL;
 	if (!fbuf_init(&fb)) return NULL;
 	rcu_read_lock();
 	struct cds_lfht *t = CMM_LOAD_SHARED(totals);
@@ -528,18 +530,23 @@ static struct h1_src_loc *accumulate(unsigned long min, size_t *hslc, FILE *lp)
 			HUGE_VAL;
 		hsl.max_life = uatomic_read(&l->max_lifespan);
 		hsl.sl = l;
-		hsl.lname_len = write_loc_name(lp, l);
+		hsl.lname_len = write_loc_name(lb->fp, l);
 		fwrite(&hsl, sizeof(hsl), 1, fb.fp);
 	}
 	rcu_read_unlock();
 
-	struct h1_src_loc *hslv;
-	if (fbuf_close(&fb)) {
-		hslv = NULL;
-	} else {
-		*hslc = fb.len / sizeof(*hslv);
-		mwrap_assert((fb.len % sizeof(*hslv)) == 0);
-		hslv = (struct h1_src_loc *)fb.ptr;
+	if (fbuf_close(&fb) || fbuf_close(lb))
+		return NULL;
+
+	struct h1_src_loc *hslv = (struct h1_src_loc *)fb.ptr;
+	*hslc = fb.len / sizeof(*hslv);
+	mwrap_assert((fb.len % sizeof(*hslv)) == 0);
+	char *n = lb->ptr;
+	for (size_t i = 0; i < *hslc; ++i) {
+		hslv[i].loc_name = n;
+		n += hslv[i].lname_len;
+		if (hslv[i].lname_len < 0)
+			return NULL;
 	}
 	return hslv;
 }
@@ -609,124 +616,128 @@ static enum mw_qev each_at(struct mw_h1 *h1, struct mw_h1req *h1r)
 	return h1_200(h1, &html, TYPE_HTML);
 }
 
-/* /$PID/each/$MIN endpoint */
-static enum mw_qev each_gt(struct mw_h1 *h1, struct mw_h1req *h1r,
-				unsigned long min, bool csv)
-{
-	static const char default_sort[] = "bytes";
-	const char *sort;
-	size_t sort_len = 0;
+typedef int (*cmp_fn)(const void *, const void *);
 
-	if (!csv) {
-		sort = default_sort;
-		sort_len = sizeof(default_sort) - 1;
+static cmp_fn write_csv_header(FILE *fp, const char *sort, size_t sort_len)
+{
+	cmp_fn cmp = NULL;
+	for (size_t i = 0; i < CAA_ARRAY_SIZE(fields); i++) {
+		const char *fn = fields[i].fname;
+		if (i)
+			fputc(',', fp);
+		fputs(fn, fp);
+		if (fields[i].flen == sort_len && !memcmp(fn, sort, sort_len))
+			cmp = fields[i].cmp;
 	}
+	fputc('\n', fp);
+	return cmp;
+}
 
-	if (h1r->qstr && h1r->qlen > 5 && !memcmp(h1r->qstr, "sort=", 5)) {
-		sort = h1r->qstr + 5;
-		sort_len = h1r->qlen - 5;
+static void write_csv_data(FILE *fp, struct h1_src_loc *hslv, size_t hslc)
+{
+	for (size_t i = 0; i < hslc; i++) {
+		struct h1_src_loc *hsl = &hslv[i];
+
+		fprintf(fp, "%zu,%zu,%zu,%zu,%0.3f,%zu,",
+			hsl->bytes, hsl->allocations, hsl->frees,
+			hsl->live, hsl->mean_life, hsl->max_life);
+		write_q_csv(fp, hsl->loc_name, hsl->lname_len);
+		fputc('\n', fp);
 	}
+}
 
-	size_t hslc;
+static void *write_csv(FILE *fp, size_t min, const char *sort, size_t sort_len)
+{
 	AUTO_CLOFREE struct mw_fbuf lb;
-	if (!fbuf_init(&lb)) return h1_close(h1);
-	AUTO_FREE struct h1_src_loc *hslv = accumulate(min, &hslc, lb.fp);
-	if (!hslv)
-		return h1_close(h1);
+	size_t hslc;
+	AUTO_FREE struct h1_src_loc *hslv = accumulate(&lb, min, &hslc);
+	if (!hslv) return NULL;
 
-	if (fbuf_close(&lb))
-		return h1_close(h1);
+	cmp_fn cmp = write_csv_header(fp, sort, sort_len);
+	if (cmp)
+		qsort(hslv, hslc, sizeof(*hslv), cmp);
+	write_csv_data(fp, hslv, hslc);
+	return fp;
+}
 
-	char *n = lb.ptr;
-	for (size_t i = 0; i < hslc; ++i) {
-		hslv[i].loc_name = n;
-		n += hslv[i].lname_len;
-		if (hslv[i].lname_len < 0)
-			return h1_close(h1);
+/* /$PID/each/$MIN endpoint */
+static enum mw_qev each_gt(struct mw_h1 *h1, struct mw_h1req *h1r,
+				size_t min, bool csv)
+{
+	static const char default_sort[] = "bytes";
+	const char *sort = csv ? NULL : default_sort;
+	size_t sort_len = csv ? 0 : (sizeof(default_sort) - 1);
+
+	if (h1r->qstr && h1r->qlen > 5 && !memcmp(h1r->qstr, "sort=", 5)) {
+		sort = h1r->qstr + 5;
+		sort_len = h1r->qlen - 5;
 	}
 
 	struct mw_fbuf bdy;
 	FILE *fp = wbuf_init(&bdy);
 	if (!fp) return h1_close(h1);
-
-	if (!csv) {
-		unsigned depth = (unsigned)CMM_LOAD_SHARED(bt_req_depth);
-		fprintf(fp, "<html><head><title>mwrap each &gt;%lu"
-			"</title></head><body><p>mwrap each &gt;%lu "
-			"(change `%lu' in URL to adjust filtering) - "
-			"MWRAP=bt:%u <a href=\"%lu.csv\">.csv</a>",
-			min, min, min, depth, min);
-		show_stats(fp);
-		/* need borders to distinguish multi-level traces */
-		if (depth)
-			FPUTS("<table\nborder=1><tr>", fp);
-		else /* save screen space if only tracing one line */
-			FPUTS("<table><tr>", fp);
+	if (csv) {
+		if (write_csv(fp, min, sort, sort_len))
+			return h1_200(h1, &bdy, TYPE_CSV);
+		return h1_close(h1);
 	}
 
-	int (*cmp)(const void *, const void *) = NULL;
-	if (csv) {
-		for (size_t i = 0; i < CAA_ARRAY_SIZE(fields); i++) {
-			const char *fn = fields[i].fname;
-			if (i)
-				fputc(',', fp);
-			fputs(fn, fp);
-			if (fields[i].flen == sort_len &&
-					!memcmp(fn, sort, sort_len))
-				cmp = fields[i].cmp;
-		}
-		fputc('\n', fp);
-	} else {
-		for (size_t i = 0; i < CAA_ARRAY_SIZE(fields); i++) {
-			const char *fn = fields[i].fname;
-			FPUTS("<th>", fp);
-			if (fields[i].flen == sort_len &&
-					!memcmp(fn, sort, sort_len)) {
-				cmp = fields[i].cmp;
-				fprintf(fp, "<b>%s</b>", fields[i].fname);
-			} else {
-				fprintf(fp, "<a\nhref=\"./%lu?sort=%s\">%s</a>",
-					min, fn, fn);
-			}
-			FPUTS("</th>", fp);
+	size_t hslc;
+	AUTO_CLOFREE struct mw_fbuf lb;
+	AUTO_FREE struct h1_src_loc *hslv = accumulate(&lb, min, &hslc);
+	if (!hslv)
+		return h1_close(h1);
+
+	unsigned depth = (unsigned)CMM_LOAD_SHARED(bt_req_depth);
+	fprintf(fp, "<html><head><title>mwrap each &gt;%lu"
+		"</title></head><body><p>mwrap each &gt;%lu "
+		"(change `%lu' in URL to adjust filtering) - "
+		"MWRAP=bt:%u <a href=\"%lu.csv\">.csv</a>",
+		min, min, min, depth, min);
+	show_stats(fp);
+	/* need borders to distinguish multi-level traces */
+	if (depth)
+		FPUTS("<table\nborder=1><tr>", fp);
+	else /* save screen space if only tracing one line */
+		FPUTS("<table><tr>", fp);
+	cmp_fn cmp = NULL;
+	for (size_t i = 0; i < CAA_ARRAY_SIZE(fields); i++) {
+		const char *fn = fields[i].fname;
+		FPUTS("<th>", fp);
+		if (fields[i].flen == sort_len &&
+				!memcmp(fn, sort, sort_len)) {
+			cmp = fields[i].cmp;
+			fprintf(fp, "<b>%s</b>", fields[i].fname);
+		} else {
+			fprintf(fp, "<a\nhref=\"./%lu?sort=%s\">%s</a>",
+				min, fn, fn);
 		}
+		FPUTS("</th>", fp);
 	}
-	if (!csv)
-		FPUTS("</tr>", fp);
+	FPUTS("</tr>", fp);
 	if (cmp)
 		qsort(hslv, hslc, sizeof(*hslv), cmp);
-	else if (!csv)
+	else
 		FPUTS("<tr><td>sort= not understood</td></tr>", fp);
-	if (csv) {
-		for (size_t i = 0; i < hslc; i++) {
-			struct h1_src_loc *hsl = &hslv[i];
 
-			fprintf(fp, "%zu,%zu,%zu,%zu,%0.3f,%zu,",
-				hsl->bytes, hsl->allocations, hsl->frees,
-				hsl->live, hsl->mean_life, hsl->max_life);
-			write_q_csv(fp, hsl->loc_name, hsl->lname_len);
-			fputc('\n', fp);
-		}
-	} else {
-		for (size_t i = 0; i < hslc; i++) {
-			struct h1_src_loc *hsl = &hslv[i];
+	for (size_t i = 0; i < hslc; i++) {
+		struct h1_src_loc *hsl = &hslv[i];
 
-			fprintf(fp, "<tr><td>%zu</td><td>%zu</td><td>%zu</td>"
-				"<td>%zu</td><td>%0.3f</td><td>%zu</td>",
-				hsl->bytes, hsl->allocations, hsl->frees,
-				hsl->live, hsl->mean_life, hsl->max_life);
-			FPUTS("<td><a\nhref=\"../at/", fp);
+		fprintf(fp, "<tr><td>%zu</td><td>%zu</td><td>%zu</td>"
+			"<td>%zu</td><td>%0.3f</td><td>%zu</td>",
+			hsl->bytes, hsl->allocations, hsl->frees,
+			hsl->live, hsl->mean_life, hsl->max_life);
+		FPUTS("<td><a\nhref=\"../at/", fp);
 
-			write_b64_url(fp, src_loc_hash_tip(hsl->sl),
-					src_loc_hash_len(hsl->sl));
+		write_b64_url(fp, src_loc_hash_tip(hsl->sl),
+				src_loc_hash_len(hsl->sl));
 
-			FPUTS("\">", fp);
-			write_html(fp, hsl->loc_name, hsl->lname_len);
-			FPUTS("</a></td></tr>", fp);
-		}
-		FPUTS("</table></body></html>", fp);
+		FPUTS("\">", fp);
+		write_html(fp, hsl->loc_name, hsl->lname_len);
+		FPUTS("</a></td></tr>", fp);
 	}
-	return h1_200(h1, &bdy, csv ? TYPE_CSV : TYPE_HTML);
+	FPUTS("</table></body></html>", fp);
+	return h1_200(h1, &bdy, TYPE_HTML);
 }
 
 /* /$PID/ root endpoint */
@@ -781,7 +792,7 @@ static enum mw_qev h1_dispatch(struct mw_h1 *h1, struct mw_h1req *h1r)
 		if ((c = PATH_SKIP(h1r, "/each/"))) {
 			errno = 0;
 			char *e;
-			unsigned long min = strtoul(c, &e, 10);
+			size_t min = (size_t)strtoul(c, &e, 10);
 			if (!errno) {
 				if (*e == ' ' || *e == '?')
 					return each_gt(h1, h1r, min, false);
@@ -857,7 +868,7 @@ static enum mw_qev h1_drain_input(struct mw_h1 *h1, struct mw_h1req *h1r,
 				return h1_close(h1);
 			default: /* ENOMEM, ENOBUFS, ... */
 				assert(errno != EBADF);
-				fprintf(stderr, "read: %m\n");
+				perror("read");
 				return h1_close(h1);
 			}
 		}
@@ -990,7 +1001,7 @@ static enum mw_qev h1_event_step(struct mw_h1 *h1, struct mw_h1d *h1d)
 	if (!h1r) {
 		h1r = h1d->shared_h1r = malloc(sizeof(*h1r));
 		if (!h1r) {
-			fprintf(stderr, "h1r malloc: %m\n");
+			perror("h1r malloc");
 			return h1_close(h1);
 		}
 	}
@@ -1034,7 +1045,7 @@ static enum mw_qev h1_event_step(struct mw_h1 *h1, struct mw_h1d *h1d)
 				return h1_close(h1);
 			default: /* ENOMEM, ENOBUFS, ... */
 				assert(errno != EBADF);
-				fprintf(stderr, "read: %m\n");
+				perror("read");
 				return h1_close(h1);
 			}
 		}
@@ -1142,7 +1153,7 @@ static void h1d_unlink(struct mw_h1d *h1d, bool do_close)
 	if (h1d->lfd < 0 || !h1d->pid_len)
 		return;
 	if (getsockname(h1d->lfd, &sa.any, &len) < 0) {
-		fprintf(stderr, "getsockname: %m\n");
+		perror("getsockname");
 		return;
 	}
 	if (do_close) { /* only safe to close if thread isn't running */
@@ -1208,13 +1219,13 @@ static int h1d_init(struct mw_h1d *h1d, const char *menv)
 		return fprintf(stderr, "unlink(%s): %m\n", sa.un.sun_path);
 	h1d->lfd = socket(AF_UNIX, SOCK_STREAM|SOCK_CLOEXEC|SOCK_NONBLOCK, 0);
 	if (h1d->lfd < 0)
-		return fprintf(stderr, "socket: %m\n");
+		return perror("socket"), 1;
 	if (bind(h1d->lfd, &sa.any, (socklen_t)sizeof(sa)) < 0) {
-		fprintf(stderr, "bind: %m\n");
+		perror("bind");
 		goto close_fail;
 	}
 	if (listen(h1d->lfd, 1024) < 0) {
-		fprintf(stderr, "listen: %m\n");
+		perror("listen");
 		goto close_fail;
 	}
 	h1d->alive = 1; /* runs in parent, before pthread_create */
diff --git a/ext/mwrap/mwrap_core.h b/ext/mwrap/mwrap_core.h
index 827ee7b..a84cd6d 100644
--- a/ext/mwrap/mwrap_core.h
+++ b/ext/mwrap/mwrap_core.h
@@ -4,7 +4,9 @@
  * Disclaimer: I don't really know my way around XS or Perl internals well
  */
 #define _LGPL_SOURCE /* allows URCU to inline some stuff */
-#define _GNU_SOURCE
+#ifndef _GNU_SOURCE
+#	define _GNU_SOURCE
+#endif
 #include "mymalloc.h" /* includes dlmalloc_c.h */
 #ifndef MWRAP_PERL
 #	define MWRAP_PERL 0
@@ -19,9 +21,6 @@
 #	define	MWRAP_BT_MAX 32
 #endif
 
-#ifndef _GNU_SOURCE
-#	define _GNU_SOURCE
-#endif
 #include <execinfo.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -389,11 +388,8 @@ static const COP *mwp_curcop(void)
 static const char *mw_perl_src_file_cstr(unsigned *lineno)
 {
 	const COP *cop = mwp_curcop();
-	if (!cop) return NULL;
-	const char *fn = CopFILE(cop);
-	if (!fn) return NULL;
-	*lineno = CopLINE(cop);
-	return fn;
+	*lineno = cop ? CopLINE(cop) : 0;
+	return cop ? CopFILE(cop) : NULL;
 }
 #	define SRC_FILE_CSTR(lineno) mw_perl_src_file_cstr(lineno)
 #endif /* MWRAP_PERL */
@@ -735,6 +731,7 @@ enomem:
 struct dump_arg {
 	FILE *fp;
 	size_t min;
+	bool dump_csv;
 };
 
 char **bt_syms(void * const *addrlist, uint32_t size)
@@ -745,7 +742,7 @@ char **bt_syms(void * const *addrlist, uint32_t size)
 #else /* make FreeBSD look like glibc output: */
 	char **s = backtrace_symbols_fmt(addrlist, size, "%f(%n%D) [%a]");
 #endif
-	if (!s) fprintf(stderr, "backtrace_symbols: %m\n");
+	if (!s) perror("backtrace_symbols");
 	return s;
 }
 
@@ -757,12 +754,16 @@ static void cleanup_free(void *any)
 	free(*p);
 }
 
+static void *write_csv(FILE *, size_t min, const char *sort, size_t sort_len);
 static void *dump_to_file(struct dump_arg *a)
 {
 	struct cds_lfht_iter iter;
 	struct src_loc *l;
 	struct cds_lfht *t;
 
+	if (a->dump_csv)
+		return write_csv(a->fp, a->min, NULL, 0);
+
 	++locating;
 	rcu_read_lock();
 	t = CMM_LOAD_SHARED(totals);
@@ -860,7 +861,7 @@ __attribute__ ((destructor)) static void mwrap_dtor(void)
 {
 	const char *opt = getenv("MWRAP");
 	const char *modes[] = { "a", "a+", "w", "w+", "r+" };
-	struct dump_arg a = { .min = 0 };
+	struct dump_arg a = { .min = 0, .dump_csv = false };
 	size_t i;
 	int dump_fd;
 	char *dump_path;
@@ -873,27 +874,64 @@ __attribute__ ((destructor)) static void mwrap_dtor(void)
 		return;
 
 	++locating;
-	if ((dump_path = strstr(opt, "dump_path:")) &&
-			(dump_path += sizeof("dump_path")) &&
-			*dump_path) {
+
+	/* parse dump_csv:$PATHNAME */
+	if ((dump_path = strstr(opt, "dump_csv:"))) {
+		dump_path += sizeof("dump_csv");
+		if (!*dump_path)
+			dump_path = NULL;
+		else
+			a.dump_csv = true;
+	}
+	if (!dump_path) {
+		/* parse dump_path:$PATHNAME */
+		if ((dump_path = strstr(opt, "dump_path:"))) {
+			dump_path += sizeof("dump_path");
+			if (!*dump_path)
+				dump_path = NULL;
+		}
+	}
+	if (dump_path) {
 		char *end = strchr(dump_path, ',');
 		char buf[PATH_MAX];
+		AUTO_FREE char *pid_path = NULL;
 		if (end) {
 			mwrap_assert((end - dump_path) < (intptr_t)sizeof(buf));
 			end = mempcpy(buf, dump_path, end - dump_path);
 			*end = 0;
 			dump_path = buf;
 		}
+
+		/* %p => PID expansion (Linux core_pattern uses %p, too) */
+		if ((s = strchr(dump_path, '%')) && s[1] == 'p' &&
+				/* don't allow injecting extra formats: */
+				!strchr(s + 2, '%')) {
+			s[1] = 'd'; /* s/%p/%d/ to make asprintf happy */
+			int n = asprintf(&pid_path, dump_path, (int)getpid());
+			if (n < 0)
+				fprintf(stderr,
+					"asprintf failed: %m, dumping to %s\n",
+					dump_path);
+			else
+				dump_path = pid_path;
+		}
 		dump_fd = open(dump_path, O_CLOEXEC|O_WRONLY|O_APPEND|O_CREAT,
 				0666);
 		if (dump_fd < 0) {
 			fprintf(stderr, "open %s failed: %m\n", dump_path);
 			goto out;
 		}
+	} else {
+		s = strstr(opt, "dump_fd:");
+		if (!s)
+			goto out;
+		if (!sscanf(s, "dump_fd:%d", &dump_fd))
+			goto out;
 	}
-	else if (!sscanf(opt, "dump_fd:%d", &dump_fd))
-		goto out;
 
+	/* allow dump_csv standalone for dump_fd */
+	if (!a.dump_csv && strstr(opt, "dump_csv"))
+		a.dump_csv = true;
 	if ((s = strstr(opt, "dump_min:")))
 		sscanf(s, "dump_min:%zu", &a.min);
 
@@ -1019,7 +1057,7 @@ __attribute__((constructor)) static void mwrap_ctor(void)
 		h->real = h;
 		call_rcu(&h->as.dead, free_hdr_rcu);
 	} else
-		fprintf(stderr, "malloc: %m\n");
+		perror("malloc");
 
 	h1d_start();
 	CHECK(int, 0, pthread_sigmask(SIG_SETMASK, &old, NULL));