From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Nick Terrell <terrelln@fb.com>,
Kan Liang <kan.liang@linux.intel.com>,
Andi Kleen <ak@linux.intel.com>, Leo Yan <leo.yan@linaro.org>,
Song Liu <song@kernel.org>, Sandipan Das <sandipan.das@amd.com>,
James Clark <james.clark@arm.com>,
Anshuman Khandual <anshuman.khandual@arm.com>,
Miguel Ojeda <ojeda@kernel.org>,
Liam Howlett <liam.howlett@oracle.com>,
Yang Jihong <yangjihong1@huawei.com>,
Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
Kajol Jain <kjain@linux.ibm.com>,
K Prateek Nayak <kprateek.nayak@amd.com>,
Sean Christopherson <seanjc@google.com>,
Yanteng Si <siyanteng@loongson.cn>,
Ravi Bangoria <ravi.bangoria@amd.com>,
German Gomez <german.gomez@arm.com>,
Changbin Du <changbin.du@huawei.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Masami Hiramatsu <mhiramat@kernel.org>,
liuwenyu <liuwenyu7@huawei.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org
Subject: [PATCH v3 25/50] perf map: Simplify map_ip/unmap_ip and make map size smaller
Date: Tue, 24 Oct 2023 15:23:28 -0700 [thread overview]
Message-ID: <20231024222353.3024098-26-irogers@google.com> (raw)
In-Reply-To: <20231024222353.3024098-1-irogers@google.com>
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 */
};
```
Signed-off-by: Ian Rogers <irogers@google.com>
---
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,
+ /* 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)
+{
+ 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);
--
2.42.0.758.gaed0368e0e-goog
next prev parent reply other threads:[~2023-10-24 22:26 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-24 22:23 [PATCH v3 00/50] Improvements to memory use Ian Rogers
2023-10-24 22:23 ` [PATCH v3 01/50] perf rwsem: Add debug mode that uses a mutex Ian Rogers
2023-10-24 22:23 ` [PATCH v3 02/50] perf machine: Avoid out of bounds LBR memory read Ian Rogers
2023-10-24 22:23 ` [PATCH v3 03/50] libperf rc_check: Make implicit enabling work for GCC Ian Rogers
2023-10-24 22:23 ` [PATCH v3 04/50] libperf rc_check: Add RC_CHK_EQUAL Ian Rogers
2023-10-24 22:23 ` [PATCH v3 05/50] perf hist: Add missing puts to hist__account_cycles Ian Rogers
2023-10-24 22:23 ` [PATCH v3 06/50] perf threads: Remove unused dead thread list Ian Rogers
2023-10-24 22:23 ` [PATCH v3 07/50] perf offcpu: Add missed btf_free Ian Rogers
2023-10-24 22:23 ` [PATCH v3 08/50] perf callchain: Make display use of branch_type_stat const Ian Rogers
2023-10-24 22:23 ` [PATCH v3 09/50] perf callchain: Make brtype_stat in callchain_list optional Ian Rogers
2023-10-24 22:23 ` [PATCH v3 10/50] perf callchain: Minor layout changes to callchain_list Ian Rogers
2023-10-24 22:23 ` [PATCH v3 11/50] perf mem_info: Add and use map_symbol__exit and addr_map_symbol__exit Ian Rogers
2023-10-24 22:23 ` [PATCH v3 12/50] perf record: Lazy load kernel symbols Ian Rogers
2023-10-25 18:25 ` Namhyung Kim
2023-10-25 18:35 ` Adrian Hunter
2023-10-24 22:23 ` [PATCH v3 13/50] libperf: Lazily allocate mmap event copy Ian Rogers
2023-10-25 2:38 ` Yang Jihong
2023-10-25 3:28 ` Ian Rogers
2023-10-24 22:23 ` [PATCH v3 14/50] perf mmap: Lazily initialize zstd streams Ian Rogers
2023-10-24 22:23 ` [PATCH v3 15/50] perf machine thread: Remove exited threads by default Ian Rogers
2023-10-24 22:23 ` [PATCH v3 16/50] tools api fs: Switch filename__read_str to use io.h Ian Rogers
2023-10-24 22:23 ` [PATCH v3 17/50] tools api fs: Avoid reading whole file for a 1 byte bool Ian Rogers
2023-10-24 22:23 ` [PATCH v3 18/50] tools lib api: Add io_dir an allocation free readdir alternative Ian Rogers
2023-10-25 18:43 ` Namhyung Kim
2023-10-25 22:15 ` Ian Rogers
2023-10-24 22:23 ` [PATCH v3 19/50] perf maps: Switch modules tree walk to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 20/50] perf record: Be lazier in allocating lost samples buffer Ian Rogers
2023-10-25 3:44 ` Yang Jihong
2023-10-25 17:00 ` Ian Rogers
2023-10-25 19:04 ` Namhyung Kim
2023-10-25 19:00 ` Namhyung Kim
2023-10-24 22:23 ` [PATCH v3 21/50] perf pmu: Switch to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 22/50] perf bpf: Don't synthesize BPF events when disabled Ian Rogers
2023-10-24 22:23 ` [PATCH v3 23/50] perf header: Switch mem topology to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 24/50] perf events: Remove scandir in thread synthesis Ian Rogers
2023-10-24 22:23 ` Ian Rogers [this message]
2023-10-24 22:23 ` [PATCH v3 26/50] perf maps: Move symbol maps functions to maps.c Ian Rogers
2023-10-24 22:23 ` [PATCH v3 27/50] perf thread: Add missing RC_CHK_ACCESS Ian Rogers
2023-10-24 22:23 ` [PATCH v3 28/50] perf maps: Add maps__for_each_map to call a function on each entry Ian Rogers
2023-10-24 22:23 ` [PATCH v3 29/50] perf maps: Add remove maps function to remove a map based on callback Ian Rogers
2023-10-24 22:23 ` [PATCH v3 30/50] perf debug: Expose debug file Ian Rogers
2023-10-24 22:23 ` [PATCH v3 31/50] perf maps: Refactor maps__fixup_overlappings Ian Rogers
2023-10-24 22:23 ` [PATCH v3 32/50] perf maps: Do simple merge if given map doesn't overlap Ian Rogers
2023-10-24 22:23 ` [PATCH v3 33/50] perf maps: Rename clone to copy from Ian Rogers
2023-10-24 22:23 ` [PATCH v3 34/50] perf maps: Add maps__load_first Ian Rogers
2023-10-24 22:23 ` [PATCH v3 35/50] perf maps: Add find next entry to give entry after the given map Ian Rogers
2023-10-24 22:23 ` [PATCH v3 36/50] perf maps: Reduce scope of map_rb_node and maps internals Ian Rogers
2023-10-24 22:23 ` [PATCH v3 37/50] perf maps: Fix up overlaps during fixup_end Ian Rogers
2023-10-24 22:23 ` [PATCH v3 38/50] perf maps: Switch from rbtree to lazily sorted array for addresses Ian Rogers
2023-10-24 22:23 ` [PATCH v3 39/50] perf maps: Get map before returning in maps__find Ian Rogers
2023-10-24 22:23 ` [PATCH v3 40/50] perf maps: Get map before returning in maps__find_by_name Ian Rogers
2023-10-24 22:23 ` [PATCH v3 41/50] perf maps: Get map before returning in maps__find_next_entry Ian Rogers
2023-10-24 22:23 ` [PATCH v3 42/50] perf maps: Hide maps internals Ian Rogers
2023-10-24 22:23 ` [PATCH v3 43/50] perf maps: Locking tidy up of nr_maps Ian Rogers
2023-10-24 22:23 ` [PATCH v3 44/50] perf dso: Reorder variables to save space in struct dso Ian Rogers
2023-10-24 22:23 ` [PATCH v3 45/50] perf report: Sort child tasks by tid Ian Rogers
2023-10-24 22:23 ` [PATCH v3 46/50] perf trace: Ignore thread hashing in summary Ian Rogers
2023-10-24 22:23 ` [PATCH v3 47/50] perf machine: Move fprintf to for_each loop and a callback Ian Rogers
2023-10-24 22:23 ` [PATCH v3 48/50] perf threads: Move threads to its own files Ian Rogers
2023-10-24 22:23 ` [PATCH v3 49/50] perf threads: Switch from rbtree to hashmap Ian Rogers
2023-10-24 22:23 ` [PATCH v3 50/50] perf threads: Reduce table size from 256 to 8 Ian Rogers
2023-10-26 17:11 ` (subset) [PATCH v3 00/50] Improvements to memory use Namhyung Kim
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20231024222353.3024098-26-irogers@google.com \
--to=irogers@google.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=anshuman.khandual@arm.com \
--cc=atrajeev@linux.vnet.ibm.com \
--cc=changbin.du@huawei.com \
--cc=german.gomez@arm.com \
--cc=james.clark@arm.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=kjain@linux.ibm.com \
--cc=kprateek.nayak@amd.com \
--cc=leo.yan@linaro.org \
--cc=liam.howlett@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=liuwenyu7@huawei.com \
--cc=mark.rutland@arm.com \
--cc=mhiramat@kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=ojeda@kernel.org \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=ravi.bangoria@amd.com \
--cc=sandipan.das@amd.com \
--cc=seanjc@google.com \
--cc=siyanteng@loongson.cn \
--cc=song@kernel.org \
--cc=terrelln@fb.com \
--cc=yangjihong1@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox