mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2025-08-18 01:27:40 +00:00
dc6d2bc2d8
The struct dump_regs contains 512 bytes of cache_regs, meaning the two values in perf_sample contribute 1088 bytes of its total 1384 bytes size. Initializing this much memory has a cost reported by Tavian Barnes <tavianator@tavianator.com> as about 2.5% when running `perf script --itrace=i0`: https://lore.kernel.org/lkml/d841b97b3ad2ca8bcab07e4293375fb7c32dfce7.1736618095.git.tavianator@tavianator.com/ Adrian Hunter <adrian.hunter@intel.com> replied that the zero initialization was necessary and couldn't simply be removed. This patch aims to strike a middle ground of still zeroing the perf_sample, but removing 79% of its size by make user_regs and intr_regs optional pointers to zalloc-ed memory. To support the allocation accessors are created for user_regs and intr_regs. To support correct cleanup perf_sample__init and perf_sample__exit functions are created and added throughout the code base. Signed-off-by: Ian Rogers <irogers@google.com> Link: https://lore.kernel.org/r/20250113194345.1537821-1-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
55 lines
1.4 KiB
C
55 lines
1.4 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <elfutils/libdwfl.h>
|
|
#include "perf_regs.h"
|
|
#include "../../../util/unwind-libdw.h"
|
|
#include "../../../util/perf_regs.h"
|
|
#include "util/sample.h"
|
|
|
|
bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
|
|
{
|
|
struct unwind_info *ui = arg;
|
|
struct regs_dump *user_regs = perf_sample__user_regs(ui->sample);
|
|
Dwarf_Word dwarf_regs[17];
|
|
unsigned nregs;
|
|
|
|
#define REG(r) ({ \
|
|
Dwarf_Word val = 0; \
|
|
perf_reg_value(&val, user_regs, PERF_REG_X86_##r); \
|
|
val; \
|
|
})
|
|
|
|
if (user_regs->abi == PERF_SAMPLE_REGS_ABI_32) {
|
|
dwarf_regs[0] = REG(AX);
|
|
dwarf_regs[1] = REG(CX);
|
|
dwarf_regs[2] = REG(DX);
|
|
dwarf_regs[3] = REG(BX);
|
|
dwarf_regs[4] = REG(SP);
|
|
dwarf_regs[5] = REG(BP);
|
|
dwarf_regs[6] = REG(SI);
|
|
dwarf_regs[7] = REG(DI);
|
|
dwarf_regs[8] = REG(IP);
|
|
nregs = 9;
|
|
} else {
|
|
dwarf_regs[0] = REG(AX);
|
|
dwarf_regs[1] = REG(DX);
|
|
dwarf_regs[2] = REG(CX);
|
|
dwarf_regs[3] = REG(BX);
|
|
dwarf_regs[4] = REG(SI);
|
|
dwarf_regs[5] = REG(DI);
|
|
dwarf_regs[6] = REG(BP);
|
|
dwarf_regs[7] = REG(SP);
|
|
dwarf_regs[8] = REG(R8);
|
|
dwarf_regs[9] = REG(R9);
|
|
dwarf_regs[10] = REG(R10);
|
|
dwarf_regs[11] = REG(R11);
|
|
dwarf_regs[12] = REG(R12);
|
|
dwarf_regs[13] = REG(R13);
|
|
dwarf_regs[14] = REG(R14);
|
|
dwarf_regs[15] = REG(R15);
|
|
dwarf_regs[16] = REG(IP);
|
|
nregs = 17;
|
|
}
|
|
|
|
return dwfl_thread_state_registers(thread, 0, nregs, dwarf_regs);
|
|
}
|