Hello,
This work is a follow-up of Ian's previous one at
https://lore.kernel.org/all/[email protected]/
Fixing up more symbol ends as introduced in:
https://lore.kernel.org/lkml/[email protected]/
it caused perf annotate to run into memory limits - every symbol holds
all the disassembled code in the annotation, and so making symbols
ends further away dramatically increased memory usage (40MB to >1GB).
Modify the symbol end fixup logic so that special kernel cases aren't
applied in the common case.
v3 changes)
* rename is_kernel to is_kallsyms
* move the logic to generic function
* remove arch-specific functions
Thanks,
Namhyung
Namhyung Kim (3):
perf symbol: Pass is_kallsyms to symbols__fixup_end()
perf symbol: Update symbols__fixup_end()
perf symbol: Remove arch__symbols__fixup_end()
tools/perf/arch/arm64/util/machine.c | 21 ---------------
tools/perf/arch/powerpc/util/Build | 1 -
tools/perf/arch/powerpc/util/machine.c | 25 -----------------
tools/perf/arch/s390/util/machine.c | 16 -----------
tools/perf/util/symbol-elf.c | 2 +-
tools/perf/util/symbol.c | 37 +++++++++++++++++++-------
tools/perf/util/symbol.h | 3 +--
7 files changed, 29 insertions(+), 76 deletions(-)
delete mode 100644 tools/perf/arch/powerpc/util/machine.c
base-commit: 41204da4c16071be9090940b18f566832d46becc
--
2.36.0.rc0.470.gd361397f0d-goog
Now arch-specific functions all do the same thing. When it fixes the
symbol address it needs to check the boundary between the kernel image
and modules. For the last symbol in the previous region, it cannot
know the exact size as it's discarded already. Thus it just uses a
small page size (4096) and rounds it up like the last symbol.
Signed-off-by: Namhyung Kim <[email protected]>
---
tools/perf/util/symbol.c | 29 +++++++++++++++++++++++++----
1 file changed, 25 insertions(+), 4 deletions(-)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 1b85cc1422a9..623094e866fd 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -217,8 +217,8 @@ void symbols__fixup_duplicate(struct rb_root_cached *symbols)
}
}
-void symbols__fixup_end(struct rb_root_cached *symbols,
- bool is_kallsyms __maybe_unused)
+/* Update zero-sized symbols using the address of the next symbol */
+void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms)
{
struct rb_node *nd, *prevnd = rb_first_cached(symbols);
struct symbol *curr, *prev;
@@ -232,8 +232,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols,
prev = curr;
curr = rb_entry(nd, struct symbol, rb_node);
- if (prev->end == prev->start || prev->end != curr->start)
- arch__symbols__fixup_end(prev, curr);
+ /*
+ * On some architecture kernel text segment start is located at
+ * some low memory address, while modules are located at high
+ * memory addresses (or vice versa). The gap between end of
+ * kernel text segment and beginning of first module's text
+ * segment is very big. Therefore do not fill this gap and do
+ * not assign it to the kernel dso map (kallsyms).
+ *
+ * In kallsyms, it determines module symbols using '[' character
+ * like in:
+ * ffffffffc1937000 T hdmi_driver_init [snd_hda_codec_hdmi]
+ */
+ if (prev->end == prev->start) {
+ /* Last kernel/module symbol mapped to end of page */
+ if (is_kallsyms && (!strchr(prev->name, '[') !=
+ !strchr(curr->name, '[')))
+ prev->end = roundup(prev->end + 4096, 4096);
+ else
+ prev->end = curr->start;
+
+ pr_debug4("%s sym:%s end:%#" PRIx64 "\n",
+ __func__, prev->name, prev->end);
+ }
}
/* Last entry */
--
2.36.0.rc0.470.gd361397f0d-goog
Now the generic code can handle kallsyms fixup properly so no need to
keep the arch-functions anymore.
Signed-off-by: Namhyung Kim <[email protected]>
---
tools/perf/arch/arm64/util/machine.c | 21 ---------------------
tools/perf/arch/powerpc/util/Build | 1 -
tools/perf/arch/powerpc/util/machine.c | 25 -------------------------
tools/perf/arch/s390/util/machine.c | 16 ----------------
tools/perf/util/symbol.c | 5 -----
tools/perf/util/symbol.h | 1 -
6 files changed, 69 deletions(-)
delete mode 100644 tools/perf/arch/powerpc/util/machine.c
diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c
index d2ce31e28cd7..41c1596e5207 100644
--- a/tools/perf/arch/arm64/util/machine.c
+++ b/tools/perf/arch/arm64/util/machine.c
@@ -8,27 +8,6 @@
#include "callchain.h"
#include "record.h"
-/* On arm64, kernel text segment starts at high memory address,
- * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory
- * address, like 0xffff 0000 00ax xxxx. When only small amount of
- * memory is used by modules, gap between end of module's text segment
- * and start of kernel text segment may reach 2G.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-
-#define SYMBOL_LIMIT (1 << 12) /* 4K */
-
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
- if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) ||
- (strchr(p->name, '[') == NULL && strchr(c->name, '[')))
- /* Limit range of last symbol in module and kernel */
- p->end += SYMBOL_LIMIT;
- else
- p->end = c->start;
- pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
-
void arch__add_leaf_frame_record_opts(struct record_opts *opts)
{
opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask;
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 8a79c4126e5b..0115f3166568 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,5 +1,4 @@
perf-y += header.o
-perf-y += machine.o
perf-y += kvm-stat.o
perf-y += perf_regs.o
perf-y += mem-events.o
diff --git a/tools/perf/arch/powerpc/util/machine.c b/tools/perf/arch/powerpc/util/machine.c
deleted file mode 100644
index e652a1aa8132..000000000000
--- a/tools/perf/arch/powerpc/util/machine.c
+++ /dev/null
@@ -1,25 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <string.h>
-#include <internal/lib.h> // page_size
-#include "debug.h"
-#include "symbol.h"
-
-/* On powerpc kernel text segment start at memory addresses, 0xc000000000000000
- * whereas the modules are located at very high memory addresses,
- * for example 0xc00800000xxxxxxx. The gap between end of kernel text segment
- * and beginning of first module's text segment is very high.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
- if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
- /* Limit the range of last kernel symbol */
- p->end += page_size;
- else
- p->end = c->start;
- pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index 7644a4f6d4a4..98bc3f39d5f3 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -35,19 +35,3 @@ int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
return 0;
}
-
-/* On s390 kernel text segment start is located at very low memory addresses,
- * for example 0x10000. Modules are located at very high memory addresses,
- * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
- * and beginning of first module's text segment is very big.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
- if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
- /* Last kernel symbol mapped to end of page */
- p->end = roundup(p->end, page_size);
- else
- p->end = c->start;
- pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 623094e866fd..f72baf636724 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -101,11 +101,6 @@ static int prefix_underscores_count(const char *str)
return tail - str;
}
-void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
- p->end = c->start;
-}
-
const char * __weak arch__normalize_symbol_name(const char *name)
{
return name;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5fcdd1f94c56..0b893dcc8ea6 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -241,7 +241,6 @@ const char *arch__normalize_symbol_name(const char *name);
#define SYMBOL_A 0
#define SYMBOL_B 1
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
int arch__compare_symbol_names(const char *namea, const char *nameb);
int arch__compare_symbol_names_n(const char *namea, const char *nameb,
unsigned int n);
--
2.36.0.rc0.470.gd361397f0d-goog
On Fri, Apr 15, 2022 at 5:40 PM Namhyung Kim <[email protected]> wrote:
>
> Hello,
>
> This work is a follow-up of Ian's previous one at
> https://lore.kernel.org/all/[email protected]/
>
> Fixing up more symbol ends as introduced in:
> https://lore.kernel.org/lkml/[email protected]/
>
> it caused perf annotate to run into memory limits - every symbol holds
> all the disassembled code in the annotation, and so making symbols
> ends further away dramatically increased memory usage (40MB to >1GB).
>
> Modify the symbol end fixup logic so that special kernel cases aren't
> applied in the common case.
>
> v3 changes)
> * rename is_kernel to is_kallsyms
> * move the logic to generic function
> * remove arch-specific functions
>
> Thanks,
> Namhyung
Thanks Namhyung! The series:
Acked-by: Ian Rogers <[email protected]>
> Namhyung Kim (3):
> perf symbol: Pass is_kallsyms to symbols__fixup_end()
> perf symbol: Update symbols__fixup_end()
> perf symbol: Remove arch__symbols__fixup_end()
>
> tools/perf/arch/arm64/util/machine.c | 21 ---------------
> tools/perf/arch/powerpc/util/Build | 1 -
> tools/perf/arch/powerpc/util/machine.c | 25 -----------------
> tools/perf/arch/s390/util/machine.c | 16 -----------
> tools/perf/util/symbol-elf.c | 2 +-
> tools/perf/util/symbol.c | 37 +++++++++++++++++++-------
> tools/perf/util/symbol.h | 3 +--
> 7 files changed, 29 insertions(+), 76 deletions(-)
> delete mode 100644 tools/perf/arch/powerpc/util/machine.c
>
>
> base-commit: 41204da4c16071be9090940b18f566832d46becc
> --
> 2.36.0.rc0.470.gd361397f0d-goog
>
Em Mon, Apr 25, 2022 at 01:59:03PM -0700, Ian Rogers escreveu:
> On Fri, Apr 15, 2022 at 5:40 PM Namhyung Kim <[email protected]> wrote:
> >
> > Hello,
> >
> > This work is a follow-up of Ian's previous one at
> > https://lore.kernel.org/all/[email protected]/
> >
> > Fixing up more symbol ends as introduced in:
> > https://lore.kernel.org/lkml/[email protected]/
> >
> > it caused perf annotate to run into memory limits - every symbol holds
> > all the disassembled code in the annotation, and so making symbols
> > ends further away dramatically increased memory usage (40MB to >1GB).
> >
> > Modify the symbol end fixup logic so that special kernel cases aren't
> > applied in the common case.
> >
> > v3 changes)
> > * rename is_kernel to is_kallsyms
> > * move the logic to generic function
> > * remove arch-specific functions
> >
> > Thanks,
> > Namhyung
>
> Thanks Namhyung! The series:
>
> Acked-by: Ian Rogers <[email protected]>
Thanks, applied to perf/urgent.
- Arnaldo
> > Namhyung Kim (3):
> > perf symbol: Pass is_kallsyms to symbols__fixup_end()
> > perf symbol: Update symbols__fixup_end()
> > perf symbol: Remove arch__symbols__fixup_end()
> >
> > tools/perf/arch/arm64/util/machine.c | 21 ---------------
> > tools/perf/arch/powerpc/util/Build | 1 -
> > tools/perf/arch/powerpc/util/machine.c | 25 -----------------
> > tools/perf/arch/s390/util/machine.c | 16 -----------
> > tools/perf/util/symbol-elf.c | 2 +-
> > tools/perf/util/symbol.c | 37 +++++++++++++++++++-------
> > tools/perf/util/symbol.h | 3 +--
> > 7 files changed, 29 insertions(+), 76 deletions(-)
> > delete mode 100644 tools/perf/arch/powerpc/util/machine.c
> >
> >
> > base-commit: 41204da4c16071be9090940b18f566832d46becc
> > --
> > 2.36.0.rc0.470.gd361397f0d-goog
> >
--
- Arnaldo