[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAP-5=fV0=XLLBq6x+hpBSAqBEpQ2H72eyyoS3xEv7CzY1YMFLQ@mail.gmail.com>
Date: Wed, 6 Dec 2023 08:19:58 -0800
From: Ian Rogers <irogers@...gle.com>
To: Arnaldo Carvalho de Melo <acme@...nel.org>
Cc: Namhyung Kim <namhyung@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...nel.org>,
Adrian Hunter <adrian.hunter@...el.com>,
Nick Terrell <terrelln@...com>,
Kan Liang <kan.liang@...ux.intel.com>,
Andi Kleen <ak@...ux.intel.com>,
Kajol Jain <kjain@...ux.ibm.com>,
Athira Rajeev <atrajeev@...ux.vnet.ibm.com>,
Huacai Chen <chenhuacai@...nel.org>,
Masami Hiramatsu <mhiramat@...nel.org>,
Vincent Whitchurch <vincent.whitchurch@...s.com>,
"Steinar H. Gunderson" <sesse@...gle.com>,
Liam Howlett <liam.howlett@...cle.com>,
Miguel Ojeda <ojeda@...nel.org>,
Colin Ian King <colin.i.king@...il.com>,
Dmitrii Dolgov <9erthalion6@...il.com>,
Yang Jihong <yangjihong1@...wei.com>,
Ming Wang <wangming01@...ngson.cn>,
James Clark <james.clark@....com>,
K Prateek Nayak <kprateek.nayak@....com>,
Sean Christopherson <seanjc@...gle.com>,
Leo Yan <leo.yan@...aro.org>,
Ravi Bangoria <ravi.bangoria@....com>,
German Gomez <german.gomez@....com>,
Changbin Du <changbin.du@...wei.com>,
Paolo Bonzini <pbonzini@...hat.com>, Li Dong <lidong@...o.com>,
Sandipan Das <sandipan.das@....com>,
liuwenyu <liuwenyu7@...wei.com>, linux-kernel@...r.kernel.org,
linux-perf-users@...r.kernel.org,
Guilherme Amadio <amadio@...too.org>
Subject: Re: [PATCH v5 12/50] perf map: Simplify map_ip/unmap_ip and make map
size smaller
On Wed, Dec 6, 2023 at 5:49 AM Arnaldo Carvalho de Melo <acme@...nel.org> wrote:
>
> Em Mon, Dec 04, 2023 at 03:39:08PM -0800, Namhyung Kim escreveu:
> > Hi Ian,
> >
> > On Mon, Nov 27, 2023 at 2:09 PM Ian Rogers <irogers@...gle.com> wrote:
> > >
> > > When mapping an IP it is either an identity mapping or a DSO relative
> > > mapping, so a single bit is required in the struct to identify
> > > this. The current code uses function pointers, adding 2 pointers per
> > > map and also pushing the size of a map beyond 1 cache line. Switch to
> > > using a byte to identify the mapping type (as well as priv and
> > > erange_warned), to avoid any masking. Change struct maps's layout to
> > > avoid holes.
> > >
> > > Before:
> > > ```
> > > struct map {
> > > u64 start; /* 0 8 */
> > > u64 end; /* 8 8 */
> > > _Bool erange_warned:1; /* 16: 0 1 */
> > > _Bool priv:1; /* 16: 1 1 */
> > >
> > > /* XXX 6 bits hole, try to pack */
> > > /* XXX 3 bytes hole, try to pack */
> > >
> > > u32 prot; /* 20 4 */
> > > u64 pgoff; /* 24 8 */
> > > u64 reloc; /* 32 8 */
> > > u64 (*map_ip)(const struct map *, u64); /* 40 8 */
> > > u64 (*unmap_ip)(const struct map *, u64); /* 48 8 */
> > > struct dso * dso; /* 56 8 */
> > > /* --- cacheline 1 boundary (64 bytes) --- */
> > > refcount_t refcnt; /* 64 4 */
> > > u32 flags; /* 68 4 */
> > >
> > > /* size: 72, cachelines: 2, members: 12 */
> > > /* sum members: 68, holes: 1, sum holes: 3 */
> > > /* sum bitfield members: 2 bits, bit holes: 1, sum bit holes: 6 bits */
> > > /* last cacheline: 8 bytes */
> > > };
> > > ```
> > >
> > > After:
> > > ```
> > > struct map {
> > > u64 start; /* 0 8 */
> > > u64 end; /* 8 8 */
> > > u64 pgoff; /* 16 8 */
> > > u64 reloc; /* 24 8 */
> > > struct dso * dso; /* 32 8 */
> > > refcount_t refcnt; /* 40 4 */
> > > u32 prot; /* 44 4 */
> > > u32 flags; /* 48 4 */
> > > enum mapping_type mapping_type:8; /* 52: 0 4 */
> > >
> > > /* Bitfield combined with next fields */
> > >
> > > _Bool erange_warned; /* 53 1 */
> > > _Bool priv; /* 54 1 */
> > >
> > > /* size: 56, cachelines: 1, members: 11 */
> > > /* padding: 1 */
> > > /* last cacheline: 56 bytes */
> > > };
> > > ```
> >
> > Thanks for doing this! I really wanted to clean up the map
> > code and to make it more intuitive.
> >
> > >
> > > Signed-off-by: Ian Rogers <irogers@...gle.com>
> >
> > Acked-by: Namhyung Kim <namhyung@...nel.org>
>
> Applied
>
> > A few nitpicks below.
>
> Ian, please consider those for a follow up clarifying patch.
Thanks, I think the variable name should be done. The PIC vs DSO, I
think there is a bit more cognitive load recognizing PIC means an
offset within the DSO than just using DSO. The existing naming used
dso so I think there is some consistency in using it here. I also
think PIC as a term is used to mean the code within an object is PC or
otherwise relative, enabling it to be loaded anywhere. We could have a
static object which isn't position independent but be using DSO
relative offsets for it, in which case PIC would be misleading. But I
think it is a minor issue.
Ian
> - Arnaldo
>
> > > ---
> > > tools/perf/util/machine.c | 3 +-
> > > tools/perf/util/map.c | 20 +--------
> > > tools/perf/util/map.h | 83 +++++++++++++++++++-----------------
> > > tools/perf/util/symbol-elf.c | 6 +--
> > > tools/perf/util/symbol.c | 6 +--
> > > 5 files changed, 50 insertions(+), 68 deletions(-)
> > >
> > > diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
> > > index be3dab9d5253..b6831a1f909d 100644
> > > --- a/tools/perf/util/machine.c
> > > +++ b/tools/perf/util/machine.c
> > > @@ -1360,8 +1360,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
> > > if (machine->vmlinux_map == NULL)
> > > return -ENOMEM;
> > >
> > > - map__set_map_ip(machine->vmlinux_map, identity__map_ip);
> > > - map__set_unmap_ip(machine->vmlinux_map, identity__map_ip);
> > > + map__set_mapping_type(machine->vmlinux_map, MAPPING_TYPE__IDENTITY);
> > > return maps__insert(machine__kernel_maps(machine), machine->vmlinux_map);
> > > }
> > >
> > > diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
> > > index f64b83004421..54c67cb7ecef 100644
> > > --- a/tools/perf/util/map.c
> > > +++ b/tools/perf/util/map.c
> > > @@ -109,8 +109,7 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso)
> > > map__set_pgoff(map, pgoff);
> > > map__set_reloc(map, 0);
> > > map__set_dso(map, dso__get(dso));
> > > - map__set_map_ip(map, map__dso_map_ip);
> > > - map__set_unmap_ip(map, map__dso_unmap_ip);
> > > + map__set_mapping_type(map, MAPPING_TYPE__DSO);
> > > map__set_erange_warned(map, false);
> > > refcount_set(map__refcnt(map), 1);
> > > }
> > > @@ -172,7 +171,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
> > > map__init(result, start, start + len, pgoff, dso);
> > >
> > > if (anon || no_dso) {
> > > - map->map_ip = map->unmap_ip = identity__map_ip;
> > > + map->mapping_type = MAPPING_TYPE__IDENTITY;
> > >
> > > /*
> > > * Set memory without DSO as loaded. All map__find_*
> > > @@ -630,18 +629,3 @@ struct maps *map__kmaps(struct map *map)
> > > }
> > > return kmap->kmaps;
> > > }
> > > -
> > > -u64 map__dso_map_ip(const struct map *map, u64 ip)
> > > -{
> > > - return ip - map__start(map) + map__pgoff(map);
> > > -}
> > > -
> > > -u64 map__dso_unmap_ip(const struct map *map, u64 ip)
> > > -{
> > > - return ip + map__start(map) - map__pgoff(map);
> > > -}
> > > -
> > > -u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip)
> > > -{
> > > - return ip;
> > > -}
> > > diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
> > > index 1b53d53adc86..3a3b7757da5f 100644
> > > --- a/tools/perf/util/map.h
> > > +++ b/tools/perf/util/map.h
> > > @@ -16,23 +16,25 @@ struct dso;
> > > struct maps;
> > > struct machine;
> > >
> > > +enum mapping_type {
> > > + /* map__map_ip/map__unmap_ip are given as offsets in the DSO. */
> > > + MAPPING_TYPE__DSO,
> >
> > I slightly prefer __PIC than __DSO, but won't argue. :)
> >
> > > + /* map__map_ip/map__unmap_ip are just the given ip value. */
> > > + MAPPING_TYPE__IDENTITY,
> > > +};
> > > +
> > > DECLARE_RC_STRUCT(map) {
> > > u64 start;
> > > u64 end;
> > > - bool erange_warned:1;
> > > - bool priv:1;
> > > - u32 prot;
> > > u64 pgoff;
> > > u64 reloc;
> > > -
> > > - /* ip -> dso rip */
> > > - u64 (*map_ip)(const struct map *, u64);
> > > - /* dso rip -> ip */
> > > - u64 (*unmap_ip)(const struct map *, u64);
> > > -
> > > struct dso *dso;
> > > refcount_t refcnt;
> > > + u32 prot;
> > > u32 flags;
> > > + enum mapping_type mapping_type:8;
> > > + bool erange_warned;
> > > + bool priv;
> > > };
> > >
> > > struct kmap;
> > > @@ -41,38 +43,11 @@ struct kmap *__map__kmap(struct map *map);
> > > struct kmap *map__kmap(struct map *map);
> > > struct maps *map__kmaps(struct map *map);
> > >
> > > -/* ip -> dso rip */
> > > -u64 map__dso_map_ip(const struct map *map, u64 ip);
> > > -/* dso rip -> ip */
> > > -u64 map__dso_unmap_ip(const struct map *map, u64 ip);
> > > -/* Returns ip */
> > > -u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip);
> > > -
> > > static inline struct dso *map__dso(const struct map *map)
> > > {
> > > return RC_CHK_ACCESS(map)->dso;
> > > }
> > >
> > > -static inline u64 map__map_ip(const struct map *map, u64 ip)
> > > -{
> > > - return RC_CHK_ACCESS(map)->map_ip(map, ip);
> > > -}
> > > -
> > > -static inline u64 map__unmap_ip(const struct map *map, u64 ip)
> > > -{
> > > - return RC_CHK_ACCESS(map)->unmap_ip(map, ip);
> > > -}
> > > -
> > > -static inline void *map__map_ip_ptr(struct map *map)
> > > -{
> > > - return RC_CHK_ACCESS(map)->map_ip;
> > > -}
> > > -
> > > -static inline void* map__unmap_ip_ptr(struct map *map)
> > > -{
> > > - return RC_CHK_ACCESS(map)->unmap_ip;
> > > -}
> > > -
> > > static inline u64 map__start(const struct map *map)
> > > {
> > > return RC_CHK_ACCESS(map)->start;
> > > @@ -123,6 +98,34 @@ static inline size_t map__size(const struct map *map)
> > > return map__end(map) - map__start(map);
> > > }
> > >
> > > +/* ip -> dso rip */
> > > +static inline u64 map__dso_map_ip(const struct map *map, u64 ip)
> > > +{
> > > + return ip - map__start(map) + map__pgoff(map);
> > > +}
> > > +
> > > +/* dso rip -> ip */
> > > +static inline u64 map__dso_unmap_ip(const struct map *map, u64 ip)
> >
> > I think it's better to use 'rip' consistently in the variable name
> > if possible.
> >
> > Thanks,
> > Namhyung
> >
> >
> > > +{
> > > + return ip + map__start(map) - map__pgoff(map);
> > > +}
> > > +
> > > +static inline u64 map__map_ip(const struct map *map, u64 ip)
> > > +{
> > > + if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
> > > + return map__dso_map_ip(map, ip);
> > > + else
> > > + return ip;
> > > +}
> > > +
> > > +static inline u64 map__unmap_ip(const struct map *map, u64 ip)
> > > +{
> > > + if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO)
> > > + return map__dso_unmap_ip(map, ip);
> > > + else
> > > + return ip;
> > > +}
> > > +
> > > /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
> > > u64 map__rip_2objdump(struct map *map, u64 rip);
> > >
> > > @@ -294,13 +297,13 @@ static inline void map__set_dso(struct map *map, struct dso *dso)
> > > RC_CHK_ACCESS(map)->dso = dso;
> > > }
> > >
> > > -static inline void map__set_map_ip(struct map *map, u64 (*map_ip)(const struct map *map, u64 ip))
> > > +static inline void map__set_mapping_type(struct map *map, enum mapping_type type)
> > > {
> > > - RC_CHK_ACCESS(map)->map_ip = map_ip;
> > > + RC_CHK_ACCESS(map)->mapping_type = type;
> > > }
> > >
> > > -static inline void map__set_unmap_ip(struct map *map, u64 (*unmap_ip)(const struct map *map, u64 rip))
> > > +static inline enum mapping_type map__mapping_type(struct map *map)
> > > {
> > > - RC_CHK_ACCESS(map)->unmap_ip = unmap_ip;
> > > + return RC_CHK_ACCESS(map)->mapping_type;
> > > }
> > > #endif /* __PERF_MAP_H */
> > > diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
> > > index 9e7eeaf616b8..4b934ed3bfd1 100644
> > > --- a/tools/perf/util/symbol-elf.c
> > > +++ b/tools/perf/util/symbol-elf.c
> > > @@ -1392,8 +1392,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
> > > map__set_start(map, shdr->sh_addr + ref_reloc(kmap));
> > > map__set_end(map, map__start(map) + shdr->sh_size);
> > > map__set_pgoff(map, shdr->sh_offset);
> > > - map__set_map_ip(map, map__dso_map_ip);
> > > - map__set_unmap_ip(map, map__dso_unmap_ip);
> > > + map__set_mapping_type(map, MAPPING_TYPE__DSO);
> > > /* Ensure maps are correctly ordered */
> > > if (kmaps) {
> > > int err;
> > > @@ -1455,8 +1454,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
> > > map__set_end(curr_map, map__start(curr_map) + shdr->sh_size);
> > > map__set_pgoff(curr_map, shdr->sh_offset);
> > > } else {
> > > - map__set_map_ip(curr_map, identity__map_ip);
> > > - map__set_unmap_ip(curr_map, identity__map_ip);
> > > + map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY);
> > > }
> > > curr_dso->symtab_type = dso->symtab_type;
> > > if (maps__insert(kmaps, curr_map))
> > > diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
> > > index 82cc74b9358e..314c0263bf3c 100644
> > > --- a/tools/perf/util/symbol.c
> > > +++ b/tools/perf/util/symbol.c
> > > @@ -956,8 +956,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta,
> > > return -1;
> > > }
> > >
> > > - map__set_map_ip(curr_map, identity__map_ip);
> > > - map__set_unmap_ip(curr_map, identity__map_ip);
> > > + map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY);
> > > if (maps__insert(kmaps, curr_map)) {
> > > dso__put(ndso);
> > > return -1;
> > > @@ -1475,8 +1474,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
> > > map__set_start(map, map__start(new_map));
> > > map__set_end(map, map__end(new_map));
> > > map__set_pgoff(map, map__pgoff(new_map));
> > > - map__set_map_ip(map, map__map_ip_ptr(new_map));
> > > - map__set_unmap_ip(map, map__unmap_ip_ptr(new_map));
> > > + map__set_mapping_type(map, map__mapping_type(new_map));
> > > /* Ensure maps are correctly ordered */
> > > map_ref = map__get(map);
> > > maps__remove(kmaps, map_ref);
> > > --
> > > 2.43.0.rc1.413.gea7ed67945-goog
> > >
>
> --
>
> - Arnaldo
Powered by blists - more mailing lists