perf libdw: Fix Dwfl discovery with split files

dso__libdw_dwfl() opens the Dwfl with dso__long_name(), the file the
samples came from. When the debug information lives in a separate file,
symbol loading finds it and records it as the dso's symsrc filename, but
the Dwfl still refers to the original file, so libdw has no DWARF to
resolve addresses against.

Open the Dwfl with the symsrc filename when one is known and fall back
to the long name when it isn't.

The symsrc file is found while symbols are loaded, which can happen
after the Dwfl has been created and cached, so drop the cached Dwfl and
the addr2line cache built from it when the symsrc filename is set.  That
teardown can run while another thread is using the cache, so take the
dso lock across both the teardown and the Dwfl accessors, and re-read
dso__symsrc_filename() under the dso lock in libbfd__addr2line() and
cmd__addr2line() to prevent a TOCTOU race with cache invalidation.

Fixes: b7a2b011e9 ("perf powerpc: Unify the skip-callchain-idx libdw with that for addr2line")
Signed-off-by: Ian Rogers <irogers@google.com>
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/arch/powerpc/util/skip-callchain-idx.c

@@ -152,9 +152,10 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr mapped_pc)
 	Dwarf_Addr	end = mapped_pc;
 	bool		signalp;
 
+	mutex_lock(dso__lock(dso));
 	dwfl = dso__libdw_dwfl(dso);
 	if (!dwfl)
-		return -1;
+		goto out;
 
 	mod = dwfl_addrmodule(dwfl, mapped_pc);
 	if (!mod) {
@@ -183,6 +184,7 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr mapped_pc)
 	rc = check_return_reg(ra_regno, frame);
 
 out:
+	mutex_unlock(dso__lock(dso));
 	return rc;
 }
 

tools/perf/util/addr2line.c

@@ -15,6 +15,7 @@
 #include <signal.h>
 #include <stdlib.h>
 #include <string.h>
+#include <unistd.h>
 
 #define MAX_INLINE_NEST 1024
 
@@ -284,7 +285,7 @@ int cmd__addr2line(const char *dso_name, u64 addr,
 		   struct inline_node *node,
 		   struct symbol *sym __maybe_unused)
 {
-	struct child_process *a2l = dso__a2l(dso);
+	struct child_process *a2l;
 	char *record_function = NULL;
 	char *record_filename = NULL;
 	unsigned int record_line_nr = 0;
@@ -296,24 +297,38 @@ int cmd__addr2line(const char *dso_name, u64 addr,
 	ssize_t written;
 	struct io io = { .eof = false };
 	enum cmd_a2l_style cmd_a2l_style;
+	const char *current_dso_name;
+
+	mutex_lock(dso__lock(dso));
+	current_dso_name = dso__symsrc_filename(dso) ?: dso_name;
+	a2l = dso__a2l(dso);
 
 	if (!a2l) {
-		if (!filename__has_section(dso_name, ".debug_line"))
+		if (!filename__has_section(current_dso_name, ".debug_line"))
-			goto out;
+			goto out_unlock;
 
 		dso__set_a2l(dso,
-			     addr2line_subprocess_init(symbol_conf.addr2line_path, dso_name));
+			     addr2line_subprocess_init(symbol_conf.addr2line_path,
+						       current_dso_name));
 		a2l = dso__a2l(dso);
 	}
 
 	if (a2l == NULL) {
 		if (!symbol_conf.addr2line_disable_warn)
 			pr_warning("%s %s: addr2line_subprocess_init failed\n", __func__, dso_name);
-		goto out;
+		goto out_unlock;
 	}
 	cmd_a2l_style = cmd_addr2line_configure(a2l, dso_name);
 	if (cmd_a2l_style == BROKEN)
-		goto out;
+		goto out_unlock;
+
+	/*
+	 * Take ownership of the a2l subprocess so we can safely perform
+	 * blocking IPC without holding the dso lock. If another thread
+	 * resolves a symbol concurrently, it will spawn a new a2l process.
+	 */
+	dso__set_a2l(dso, NULL);
+	mutex_unlock(dso__lock(dso));
 
 	/*
 	 * Send our request and then *deliberately* send something that can't be
@@ -414,12 +429,21 @@ int cmd__addr2line(const char *dso_name, u64 addr,
 	}
 
 out:
+	mutex_lock(dso__lock(dso));
 	free(record_function);
 	free(record_filename);
-	if (io.eof) {
+
-		dso__set_a2l(dso, NULL);
+	current_dso_name = dso__symsrc_filename(dso) ?: dso__long_name(dso);
+	if (!io.eof && dso__a2l(dso) == NULL && current_dso_name &&
+	    !strcmp(current_dso_name, dso_name))
+		dso__set_a2l(dso, a2l);
+	else
 		addr2line_subprocess_cleanup(a2l);
-	}
+	mutex_unlock(dso__lock(dso));
+	return ret;
+
+out_unlock:
+	mutex_unlock(dso__lock(dso));
 	return ret;
 }
 

tools/perf/util/dso.c

@@ -2075,3 +2075,12 @@ struct debuginfo *dso__debuginfo(struct dso *dso)
 	free(name);
 	return dinfo;
 }
+
+void dso__set_symsrc_filename(struct dso *dso, char *val)
+{
+	RC_CHK_ACCESS(dso)->symsrc_filename = val;
+	dso__free_libdw(dso);
+	dso__free_a2l(dso);
+	dso__set_has_srcline(dso, true);
+	dso__set_a2l_fails(dso, 0);
+}

tools/perf/util/dso.h

@@ -735,10 +735,7 @@ static inline const char *dso__symsrc_filename(const struct dso *dso)
 	return RC_CHK_ACCESS(dso)->symsrc_filename;
 }
 
-static inline void dso__set_symsrc_filename(struct dso *dso, char *val)
+void dso__set_symsrc_filename(struct dso *dso, char *val);
-{
-	RC_CHK_ACCESS(dso)->symsrc_filename = val;
-}
 
 static inline void dso__free_symsrc_filename(struct dso *dso)
 {

tools/perf/util/libbfd.c

@@ -226,7 +226,11 @@ int libbfd__addr2line(const char *dso_name, u64 addr,
 		      struct symbol *sym)
 {
 	int ret = 0;
-	struct a2l_data *a2l = dso__a2l(dso);
+	struct a2l_data *a2l;
+
+	mutex_lock(dso__lock(dso));
+	dso_name = dso__symsrc_filename(dso) ?: dso_name;
+	a2l = dso__a2l(dso);
 
 	if (!a2l) {
 		a2l = addr2line_init(dso_name);
@@ -236,7 +240,8 @@ int libbfd__addr2line(const char *dso_name, u64 addr,
 	if (a2l == NULL) {
 		if (!symbol_conf.addr2line_disable_warn)
 			pr_warning("addr2line_init failed for %s\n", dso_name);
-		return 0;
+		ret = -1;
+		goto out;
 	}
 
 	a2l->addr = addr;
@@ -244,14 +249,18 @@ int libbfd__addr2line(const char *dso_name, u64 addr,
 
 	bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
 
-	if (!a2l->found)
+	if (!a2l->found) {
-		return 0;
+		ret = 0;
+		goto out;
+	}
 
 	if (unwind_inlines) {
 		int cnt = 0;
 
-		if (node && inline_list__append_dso_a2l(dso, node, sym))
+		if (node && inline_list__append_dso_a2l(dso, node, sym)) {
-			return 0;
+			ret = 0;
+			goto out;
+		}
 
 		while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
 					     &a2l->funcname, &a2l->line) &&
@@ -261,8 +270,10 @@ int libbfd__addr2line(const char *dso_name, u64 addr,
 				a2l->filename = NULL;
 
 			if (node != NULL) {
-				if (inline_list__append_dso_a2l(dso, node, sym))
+				if (inline_list__append_dso_a2l(dso, node, sym)) {
-					return 0;
+					ret = 0;
+					goto out;
+				}
 				// found at least one inline frame
 				ret = 1;
 			}
@@ -277,6 +288,8 @@ int libbfd__addr2line(const char *dso_name, u64 addr,
 	if (line)
 		*line = a2l->line;
 
+out:
+	mutex_unlock(dso__lock(dso));
 	return ret;
 }
 

tools/perf/util/libdw.c

@@ -35,7 +35,7 @@ struct Dwfl *dso__libdw_dwfl(struct dso *dso)
 	if (dwfl)
 		return dwfl;
 
-	dso_name = dso__long_name(dso);
+	dso_name = dso__symsrc_filename(dso) ?: dso__long_name(dso);
 	/*
 	 * Initialize Dwfl session.
 	 * We need to open the DSO file to report it to libdw.
@@ -167,32 +167,41 @@ int libdw__addr2line(u64 addr, char **file, unsigned int *line_nr,
 		     struct dso *dso, bool unwind_inlines,
 		     struct inline_node *node, struct symbol *sym)
 {
-	Dwfl *dwfl = dso__libdw_dwfl(dso);
+	Dwfl *dwfl;
 	Dwfl_Module *mod;
 	Dwfl_Line *dwline;
 	Dwarf_Addr bias;
 	const char *src;
 	int lineno = 0;
+	int ret = 0;
 
+	mutex_lock(dso__lock(dso));
+	dwfl = dso__libdw_dwfl(dso);
 	if (!dwfl)
-		return 0;
+		goto out;
 
 	mod = dwfl_addrmodule(dwfl, addr);
-	if (!mod)
+	if (!mod) {
-		return 0;
+		ret = 0;
+		goto out;
+	}
 
 	/*
 	 * Get/ignore the dwarf information. Determine the bias, difference
 	 * between the regular ELF addr2line addresses and those to use with
 	 * libdw.
 	 */
-	if (!dwfl_module_getdwarf(mod, &bias))
+	if (!dwfl_module_getdwarf(mod, &bias)) {
-		return 0;
+		ret = -1;
+		goto out;
+	}
 
 	/* Find source line information for the address. */
 	dwline = dwfl_module_getsrc(mod, addr + bias);
-	if (!dwline)
+	if (!dwline) {
-		return 0;
+		ret = -1;
+		goto out;
+	}
 
 	/* Get line information. */
 	src = dwfl_lineinfo(dwline, /*addr=*/NULL, &lineno, /*col=*/NULL, /*mtime=*/NULL,
@@ -219,7 +228,8 @@ int libdw__addr2line(u64 addr, char **file, unsigned int *line_nr,
 				free(*file);
 				*file = NULL;
 			}
-			return 0;
+			ret = 0;
+			goto out;
 		}
 
 		/* Walk from the parent down to the leaf. */
@@ -235,8 +245,13 @@ int libdw__addr2line(u64 addr, char **file, unsigned int *line_nr,
 				*file = NULL;
 			}
 			inline_node__clear_frames(node);
-			return 0;
+			ret = 0;
+			goto out;
 		}
 	}
-	return 1;
+	ret = 1;
+
+out:
+	mutex_unlock(dso__lock(dso));
+	return ret;
 }

tools/perf/util/srcline.c

@@ -1,40 +1,49 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "srcline.h"
-#include "addr2line.h"
-#include "dso.h"
-#include "callchain.h"
-#include "libbfd.h"
-#include "llvm.h"
-#include "symbol.h"
-#include "libdw.h"
-#include "debug.h"
-#include "util.h"
 
 #include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
+
 #include <linux/string.h>
 #include <linux/zalloc.h>
 
+#include "addr2line.h"
+#include "callchain.h"
+#include "debug.h"
+#include "dso.h"
+#include "libbfd.h"
+#include "libdw.h"
+#include "llvm.h"
+#include "symbol.h"
+#include "util.h"
+
 bool srcline_full_filename;
 
 char *srcline__unknown = (char *)"??:0";
 
-static const char *srcline_dso_name(struct dso *dso)
+static char *srcline_dso_name(struct dso *dso)
 {
 	const char *dso_name;
+	char *ret = NULL;
 
+	mutex_lock(dso__lock(dso));
 	if (dso__symsrc_filename(dso))
 		dso_name = dso__symsrc_filename(dso);
 	else
 		dso_name = dso__long_name(dso);
 
 	if (dso_name[0] == '[')
-		return NULL;
+		goto out;
 
 	if (is_perf_pid_map_name(dso_name))
-		return NULL;
+		goto out;
 
-	return dso_name;
+	ret = strdup(dso_name);
+out:
+	mutex_unlock(dso__lock(dso));
+	return ret;
 }
 
 int inline_list__append(struct symbol *symbol, char *srcline, struct inline_node *node)
@@ -258,7 +267,7 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 	char *file = NULL;
 	unsigned line = 0;
 	char *srcline;
-	const char *dso_name;
+	char *dso_name;
 
 	if (!dso__has_srcline(dso))
 		goto out;
@@ -268,8 +277,11 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 		goto out_err;
 
 	if (!addr2line(dso_name, addr, &file, &line, dso,
-		       unwind_inlines, /*node=*/NULL, sym))
+		       unwind_inlines, /*node=*/NULL, sym)) {
+		free(dso_name);
 		goto out_err;
+	}
+	free(dso_name);
 
 	srcline = srcline_from_fileline(file, line);
 	free(file);
@@ -277,16 +289,20 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 	if (!srcline)
 		goto out_err;
 
+	mutex_lock(dso__lock(dso));
 	dso__set_a2l_fails(dso, 0);
+	mutex_unlock(dso__lock(dso));
 
 	return srcline;
 
 out_err:
+	mutex_lock(dso__lock(dso));
 	dso__set_a2l_fails(dso, dso__a2l_fails(dso) + 1);
 	if (dso__a2l_fails(dso) > A2L_FAIL_LIMIT) {
 		dso__set_has_srcline(dso, false);
 		dso__free_a2l(dso);
 	}
+	mutex_unlock(dso__lock(dso));
 out:
 	if (!show_addr)
 		return (show_sym && sym) ?
@@ -305,7 +321,7 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 char *get_srcline_split(struct dso *dso, u64 addr, unsigned *line)
 {
 	char *file = NULL;
-	const char *dso_name;
+	char *dso_name;
 
 	if (!dso__has_srcline(dso))
 		return NULL;
@@ -315,18 +331,25 @@ char *get_srcline_split(struct dso *dso, u64 addr, unsigned *line)
 		goto out_err;
 
 	if (!addr2line(dso_name, addr, &file, line, dso, /*unwind_inlines=*/true,
-			/*node=*/NULL, /*sym=*/NULL))
+			/*node=*/NULL, /*sym=*/NULL)) {
+		free(dso_name);
 		goto out_err;
+	}
+	free(dso_name);
 
+	mutex_lock(dso__lock(dso));
 	dso__set_a2l_fails(dso, 0);
+	mutex_unlock(dso__lock(dso));
 	return file;
 
 out_err:
+	mutex_lock(dso__lock(dso));
 	dso__set_a2l_fails(dso, dso__a2l_fails(dso) + 1);
 	if (dso__a2l_fails(dso) > A2L_FAIL_LIMIT) {
 		dso__set_has_srcline(dso, false);
 		dso__free_a2l(dso);
 	}
+	mutex_unlock(dso__lock(dso));
 
 	return NULL;
 }
@@ -420,13 +443,16 @@ void srcline__tree_delete(struct rb_root_cached *tree)
 struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
 					    struct symbol *sym)
 {
-	const char *dso_name;
+	char *dso_name;
+	struct inline_node *node;
 
 	dso_name = srcline_dso_name(dso);
 	if (dso_name == NULL)
 		return NULL;
 
-	return addr2inlines(dso_name, addr, dso, sym);
+	node = addr2inlines(dso_name, addr, dso, sym);
+	free(dso_name);
+	return node;
 }
 
 void inline_node__clear_frames(struct inline_node *node)

tools/perf/util/unwind-libdw.c

@@ -42,8 +42,10 @@ static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata,
 	const struct dso *dso = *userdata;
 
 	assert(dso);
+	mutex_lock(dso__lock((struct dso *)dso));
 	if (dso__symsrc_filename(dso) && strcmp(file_name, dso__symsrc_filename(dso)))
 		*debuginfo_file_name = strdup(dso__symsrc_filename(dso));
+	mutex_unlock(dso__lock((struct dso *)dso));
 	return -1;
 }
 

tools/perf/util/unwind-libunwind.c

@@ -1,20 +1,28 @@
 // SPDX-License-Identifier: GPL-2.0
+#include "unwind.h"
+
+#include <inttypes.h>
+#include <limits.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <elf.h>
+#include <fcntl.h>
+#include <gelf.h>
+#include <unistd.h>
+
+#include <dwarf-regs.h>
+
 #include "callchain.h"
 #include "debug.h"
 #include "dso.h"
 #include "env.h"
+#include "libunwind-arch/libunwind-arch.h"
 #include "map.h"
 #include "perf_regs.h"
 #include "session.h"
 #include "symbol.h"
 #include "thread.h"
-#include "unwind.h"
-#include "libunwind-arch/libunwind-arch.h"
-#include <dwarf-regs.h>
-#include <elf.h>
-#include <fcntl.h>
-#include <gelf.h>
-#include <inttypes.h>
 
 #define DW_EH_PE_FORMAT_MASK	0x0f	/* format of the encoded value */
 #define DW_EH_PE_APPL_MASK	0x70	/* how the value is to be applied */
@@ -293,10 +301,19 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 		}
 
 		if (ofs <= 0) {
-			fd = open(dso__symsrc_filename(dso), O_RDONLY);
+			char *alloc_name;
-			if (fd >= 0) {
+
-				ofs = elf_section_offset(fd, ".debug_frame");
+			mutex_lock(dso__lock(dso));
-				close(fd);
+			alloc_name = dso__symsrc_filename(dso) ?
+					strdup(dso__symsrc_filename(dso)) : NULL;
+			mutex_unlock(dso__lock(dso));
+			if (alloc_name) {
+				fd = open(alloc_name, O_RDONLY);
+				if (fd >= 0) {
+					ofs = elf_section_offset(fd, ".debug_frame");
+					close(fd);
+				}
+				free(alloc_name);
 			}
 		}
 
@@ -321,6 +338,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 				}
 			}
 			if (ofs > 0) {
+				mutex_lock(dso__lock(dso));
 				if (dso__symsrc_filename(dso) != NULL) {
 					pr_warning(
 						"%s: overwrite symsrc(%s,%s)\n",
@@ -330,6 +348,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 					dso__free_symsrc_filename(dso);
 				}
 				dso__set_symsrc_filename(dso, debuglink);
+				mutex_unlock(dso__lock(dso));
 			} else {
 				free(debuglink);
 			}
@@ -429,12 +448,23 @@ int __libunwind__find_proc_info(void *as, uint64_t ip, void *pi, int need_unwind
 			dso__data_put_fd(dso);
 		}
 
-		symfile = dso__symsrc_filename(dso) ?: dso__name(dso);
+		mutex_lock(dso__lock(dso));
+		symfile = dso__symsrc_filename(dso) ?
+				strdup(dso__symsrc_filename(dso)) :
+				strdup(dso__name(dso));
+		mutex_unlock(dso__lock(dso));
 
-		if (libunwind_arch__dwarf_find_debug_frame(ui->e_machine, /*found=*/0, &di, ip,
+		if (symfile) {
-							   base, symfile, start, map__end(map))) {
+			if (libunwind_arch__dwarf_find_debug_frame(ui->e_machine,
-			ret = libunwind_arch__dwarf_search_unwind_table(ui->e_machine, as, ip, &di, pi,
+								   /*found=*/0, &di, ip,
-									need_unwind_info, arg);
+								   base, symfile, start,
+								   map__end(map))) {
+				ret = libunwind_arch__dwarf_search_unwind_table(ui->e_machine, as,
+										ip, &di, pi,
+										need_unwind_info,
+										arg);
+			}
+			free((char *)symfile);
 		}
 	}
 	map__put(map);