perf unwind-libdw: Don't discard loaded ELF/DWARF after every unwind

The unwind-libdw dwfl has ELF binaries associated with mmap
addresses. Experimenting with using the per dso dwfl it is required to
alter the address to be 0 based variant. Unfortunately libdwfl doesn't
allow a single unwind and then an update to the return address to be 0
based as there are assertions that registers aren't updated once an
unwind has started, etc.

As removing the dwfl didn't prove possible, an alternative is to just
not discard the dwfl when the unwind ends. The dwfl is valid for a
process unless a dso is loaded at the same address as a previous
one. So keep the dwfl with the maps, invalidate it if a map is removed
(in case a new map replaces it) and recycle the dwfl in the unwinding
code. A wrinkly in the implementation of this is that the attached
thread argument is remembered by the dwfl and so it needs to be a
pointer to memory that also persists with the dwfl (struct
dwfl_ui_thread_info in the code).

Recording 10 seconds of system wide data with --call-graph=dwarf and
then processing with perf report shows a total runtime improvement
from 41.583s to 2.279s (an 18x speedup).

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Aditya Bodkhe <aditya.b1@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.ibm.com>
Cc: Chun-Tse Shao <ctshao@google.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Haibo Xu <haibo1.xu@intel.com>
Cc: Howard Chu <howardchu95@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Krzysztof Łopatowski <krzysztof.m.lopatowski@gmail.com>
Cc: Leo Yan <leo.yan@linux.dev>
Cc: Mark Wielaard <mark@klomp.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergei Trofimovich <slyich@gmail.com>
Cc: Shimin Guo <shimin.guo@skydio.com>
Cc: Stephen Brennan <stephen.s.brennan@oracle.com>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
index c321d4f4d84669abfab5e5ff54b2d3c53be1a3d7..8ccc46d515b637fef396333293a61eb894738983 100644 (file)
--- a/tools/perf/util/maps.c
+++ b/tools/perf/util/maps.c
@@ -10,6 +10,7 @@
 #include "thread.h"
 #include "ui/ui.h"
 #include "unwind.h"
+#include "unwind-libdw.h"
 #include <internal/rc_check.h>
 
 /*
@@ -39,6 +40,9 @@ DECLARE_RC_STRUCT(maps) {
 #ifdef HAVE_LIBUNWIND_SUPPORT
        void            *addr_space;
        const struct unwind_libunwind_ops *unwind_libunwind_ops;
+#endif
+#ifdef HAVE_LIBDW_SUPPORT
+       void            *libdw_addr_space_dwfl;
 #endif
        refcount_t       refcnt;
        /**
@@ -203,6 +207,17 @@ void maps__set_unwind_libunwind_ops(struct maps *maps, const struct unwind_libun
        RC_CHK_ACCESS(maps)->unwind_libunwind_ops = ops;
 }
 #endif
+#ifdef HAVE_LIBDW_SUPPORT
+void *maps__libdw_addr_space_dwfl(const struct maps *maps)
+{
+       return RC_CHK_ACCESS(maps)->libdw_addr_space_dwfl;
+}
+
+void maps__set_libdw_addr_space_dwfl(struct maps *maps, void *dwfl)
+{
+       RC_CHK_ACCESS(maps)->libdw_addr_space_dwfl = dwfl;
+}
+#endif
 
 static struct rw_semaphore *maps__lock(struct maps *maps)
 {
@@ -218,6 +233,9 @@ static void maps__init(struct maps *maps, struct machine *machine)
 #ifdef HAVE_LIBUNWIND_SUPPORT
        RC_CHK_ACCESS(maps)->addr_space = NULL;
        RC_CHK_ACCESS(maps)->unwind_libunwind_ops = NULL;
+#endif
+#ifdef HAVE_LIBDW_SUPPORT
+       RC_CHK_ACCESS(maps)->libdw_addr_space_dwfl = NULL;
 #endif
        refcount_set(maps__refcnt(maps), 1);
        RC_CHK_ACCESS(maps)->nr_maps = 0;
@@ -240,6 +258,9 @@ static void maps__exit(struct maps *maps)
        zfree(&maps_by_address);
        zfree(&maps_by_name);
        unwind__finish_access(maps);
+#ifdef HAVE_LIBDW_SUPPORT
+       libdw__invalidate_dwfl(maps, maps__libdw_addr_space_dwfl(maps));
+#endif
 }
 
 struct maps *maps__new(struct machine *machine)
@@ -549,6 +570,9 @@ void maps__remove(struct maps *maps, struct map *map)
        __maps__remove(maps, map);
        check_invariants(maps);
        up_write(maps__lock(maps));
+#ifdef HAVE_LIBDW_SUPPORT
+       libdw__invalidate_dwfl(maps, maps__libdw_addr_space_dwfl(maps));
+#endif
 }
 
 bool maps__empty(struct maps *maps)
@@ -604,18 +628,26 @@ int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data)
 void maps__remove_maps(struct maps *maps, bool (*cb)(struct map *map, void *data), void *data)
 {
        struct map **maps_by_address;
+       bool removed = false;
 
        down_write(maps__lock(maps));
 
        maps_by_address = maps__maps_by_address(maps);
        for (unsigned int i = 0; i < maps__nr_maps(maps);) {
-               if (cb(maps_by_address[i], data))
+               if (cb(maps_by_address[i], data)) {
                        __maps__remove(maps, maps_by_address[i]);
-               else
+                       removed = true;
+               } else {
                        i++;
+               }
        }
        check_invariants(maps);
        up_write(maps__lock(maps));
+       if (removed) {
+#ifdef HAVE_LIBDW_SUPPORT
+               libdw__invalidate_dwfl(maps, maps__libdw_addr_space_dwfl(maps));
+#endif
+       }
 }
 
 struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)

diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h
index d9aa62ed968ac43d16b67279b512c9393c8b219b..20c52084ba9e63473b220fcda683842e8f942fb2 100644 (file)
--- a/tools/perf/util/maps.h
+++ b/tools/perf/util/maps.h
@@ -52,6 +52,10 @@ void maps__set_addr_space(struct maps *maps, void *addr_space);
 const struct unwind_libunwind_ops *maps__unwind_libunwind_ops(const struct maps *maps);
 void maps__set_unwind_libunwind_ops(struct maps *maps, const struct unwind_libunwind_ops *ops);
 #endif
+#ifdef HAVE_LIBDW_SUPPORT
+void *maps__libdw_addr_space_dwfl(const struct maps *maps);
+void maps__set_libdw_addr_space_dwfl(struct maps *maps, void *dwfl);
+#endif
 
 size_t maps__fprintf(struct maps *maps, FILE *fp);
 

diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index e0321043af885d6d24549a2817eff53427832331..c1646ef5f9717f0308e0aa8e594b5c4a6057744d 100644 (file)
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -20,6 +20,17 @@
 #include "callchain.h"
 #include "util/env.h"
 
+/*
+ * The dwfl thread argument passed to functions like memory_read. Memory has to
+ * be allocated to persist of multiple uses of the dwfl.
+ */
+struct dwfl_ui_thread_info {
+       /* Back link to the dwfl. */
+       Dwfl *dwfl;
+       /* The current unwind info, only 1 is supported. */
+       struct unwind_info *ui;
+};
+
 static char *debuginfo_path;
 
 static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata,
@@ -35,6 +46,19 @@ static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata,
        return -1;
 }
 
+void libdw__invalidate_dwfl(struct maps *maps, void *arg)
+{
+       struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+
+       if (!dwfl_ui_ti)
+               return;
+
+       assert(dwfl_ui_ti->ui == NULL);
+       maps__set_libdw_addr_space_dwfl(maps, NULL);
+       dwfl_end(dwfl_ui_ti->dwfl);
+       free(dwfl_ui_ti);
+}
+
 static const Dwfl_Callbacks offline_callbacks = {
        .find_debuginfo         = __find_debuginfo,
        .debuginfo_path         = &debuginfo_path,
@@ -187,7 +211,8 @@ out_fail:
 static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *result,
                        void *arg)
 {
-       struct unwind_info *ui = arg;
+       struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+       struct unwind_info *ui = dwfl_ui_ti->ui;
        uint16_t e_machine = thread__e_machine(ui->thread, ui->machine);
        struct stack_dump *stack = &ui->sample->user_stack;
        u64 start, end;
@@ -228,7 +253,8 @@ static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *
 
 static bool libdw_set_initial_registers(Dwfl_Thread *thread, void *arg)
 {
-       struct unwind_info *ui = arg;
+       struct dwfl_ui_thread_info *dwfl_ui_ti = arg;
+       struct unwind_info *ui = dwfl_ui_ti->ui;
        struct regs_dump *user_regs = perf_sample__user_regs(ui->sample);
        Dwarf_Word *dwarf_regs;
        int max_dwarf_reg = 0;
@@ -320,33 +346,50 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
                        int max_stack,
                        bool best_effort)
 {
-       struct machine *machine = maps__machine(thread__maps(thread));
+       struct maps *maps = thread__maps(thread);
+       struct machine *machine = maps__machine(maps);
        uint16_t e_machine = thread__e_machine(thread, machine);
-       struct unwind_info *ui, ui_buf = {
-               .sample         = data,
-               .thread         = thread,
-               .machine        = machine,
-               .cb             = cb,
-               .arg            = arg,
-               .max_stack      = max_stack,
-               .e_machine      = e_machine,
-               .best_effort    = best_effort
-       };
+       struct dwfl_ui_thread_info *dwfl_ui_ti;
+       static struct unwind_info *ui;
+       Dwfl *dwfl;
        Dwarf_Word ip;
        int err = -EINVAL, i;
 
        if (!data->user_regs || !data->user_regs->regs)
                return -EINVAL;
 
-       ui = zalloc(sizeof(ui_buf) + sizeof(ui_buf.entries[0]) * max_stack);
+       ui = zalloc(sizeof(*ui) + sizeof(ui->entries[0]) * max_stack);
        if (!ui)
                return -ENOMEM;
 
-       *ui = ui_buf;
+       *ui = (struct unwind_info){
+               .sample         = data,
+               .thread         = thread,
+               .machine        = machine,
+               .cb             = cb,
+               .arg            = arg,
+               .max_stack      = max_stack,
+               .e_machine      = e_machine,
+               .best_effort    = best_effort
+       };
 
-       ui->dwfl = dwfl_begin(&offline_callbacks);
-       if (!ui->dwfl)
-               goto out;
+       dwfl_ui_ti = maps__libdw_addr_space_dwfl(maps);
+       if (dwfl_ui_ti) {
+               dwfl = dwfl_ui_ti->dwfl;
+       } else {
+               dwfl_ui_ti = zalloc(sizeof(*dwfl_ui_ti));
+               dwfl = dwfl_begin(&offline_callbacks);
+               if (!dwfl)
+                       goto out;
+
+               dwfl_ui_ti->dwfl = dwfl;
+               maps__set_libdw_addr_space_dwfl(maps, dwfl_ui_ti);
+       }
+       assert(dwfl_ui_ti->ui == NULL);
+       assert(dwfl_ui_ti->dwfl == dwfl);
+       assert(dwfl_ui_ti == maps__libdw_addr_space_dwfl(maps));
+       dwfl_ui_ti->ui = ui;
+       ui->dwfl = dwfl;
 
        err = perf_reg_value(&ip, data->user_regs, perf_arch_reg_ip(e_machine));
        if (err)
@@ -356,11 +399,12 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
        if (err)
                goto out;
 
-       err = !dwfl_attach_state(ui->dwfl, /*elf=*/NULL, thread__tid(thread), &callbacks, ui);
-       if (err)
-               goto out;
+       dwfl_attach_state(dwfl, /*elf=*/NULL, thread__tid(thread), &callbacks,
+                         /* Dwfl thread function argument*/dwfl_ui_ti);
+       // Ignore thread already attached error.
 
-       err = dwfl_getthread_frames(ui->dwfl, thread__tid(thread), frame_callback, ui);
+       err = dwfl_getthread_frames(dwfl, thread__tid(thread), frame_callback,
+                                   /* Dwfl frame function argument*/ui);
 
        if (err && ui->max_stack != max_stack)
                err = 0;
@@ -384,7 +428,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
        for (i = 0; i < ui->idx; i++)
                map_symbol__exit(&ui->entries[i].ms);
 
-       dwfl_end(ui->dwfl);
+       dwfl_ui_ti->ui = NULL;
        free(ui);
        return 0;
 }

diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 9c5b5fcaaae8741204b565f6832d6c00dbaa928f..3dec0ab8bd50ecfdf2b3b34fde7580d3dffd1b63 100644 (file)
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -2,15 +2,17 @@
 #ifndef __PERF_UNWIND_LIBDW_H
 #define __PERF_UNWIND_LIBDW_H
 
-#include <elfutils/libdwfl.h>
+#include <stdint.h>
 #include "unwind.h"
 
 struct machine;
 struct perf_sample;
 struct thread;
 
+#ifdef HAVE_LIBDW_SUPPORT
+
 struct unwind_info {
-       Dwfl                    *dwfl;
+       void                    *dwfl;
        struct perf_sample      *sample;
        struct machine          *machine;
        struct thread           *thread;
@@ -23,4 +25,7 @@ struct unwind_info {
        struct unwind_entry     entries[];
 };
 
+void libdw__invalidate_dwfl(struct maps *maps, void *dwfl);
+#endif
+
 #endif /* __PERF_UNWIND_LIBDW_H */