| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAP-5=fV+NzS0-dd3a5aaKWCbPQfu2h0isvCWc_R65QgV=9mKOw@mail.gmail.com>
Date: Mon, 9 Feb 2026 14:36:10 -0800
From: Ian Rogers <irogers@...gle.com>
To: Dapeng Mi <dapeng1.mi@...ux.intel.com>
Cc: Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>, Namhyung Kim <namhyung@...nel.org>,
Adrian Hunter <adrian.hunter@...el.com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>, linux-perf-users@...r.kernel.org,
linux-kernel@...r.kernel.org, Zide Chen <zide.chen@...el.com>,
Falcon Thomas <thomas.falcon@...el.com>, Dapeng Mi <dapeng1.mi@...el.com>,
Xudong Hao <xudong.hao@...el.com>
Subject: Re: [Patch v6 2/4] perf regs: Support x86 eGPRs/SSP sampling
On Mon, Feb 9, 2026 at 12:39 AM Dapeng Mi <dapeng1.mi@...ux.intel.com> wrote:
>
> This patch adds support for sampling x86 extended GP registers (R16-R31)
> and the shadow stack pointer (SSP) register.
>
> The original XMM registers space in sample_regs_user/sample_regs_intr is
> reclaimed to represent the eGPRs and SSP when SIMD registers sampling is
> supported with the new SIMD sampling fields in the perf_event_attr
> structure. This necessitates a way to distinguish which register layout
> is used for the sample_regs_user/sample_regs_intr bitmap.
>
> To address this, a new "abi" argument is added to the helpers
> perf_intr_reg_mask(), perf_user_reg_mask(), and perf_reg_name(). When
> "abi & PERF_SAMPLE_REGS_ABI_SIMD" is true, it indicates the eGPRs and SSP
> layout is represented; otherwise, the legacy XMM registers are
> represented.
>
> Signed-off-by: Dapeng Mi <dapeng1.mi@...ux.intel.com>
> ---
> tools/perf/builtin-script.c | 2 +-
> tools/perf/util/evsel.c | 6 +-
> tools/perf/util/parse-regs-options.c | 17 ++-
> .../perf/util/perf-regs-arch/perf_regs_x86.c | 120 +++++++++++++++---
> tools/perf/util/perf_regs.c | 14 +-
> tools/perf/util/perf_regs.h | 10 +-
> .../scripting-engines/trace-event-python.c | 2 +-
> tools/perf/util/session.c | 9 +-
> 8 files changed, 139 insertions(+), 41 deletions(-)
>
> diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
> index 14c6f6c3c4f2..ffe51f895666 100644
> --- a/tools/perf/builtin-script.c
> +++ b/tools/perf/builtin-script.c
> @@ -730,7 +730,7 @@ static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask,
> for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
> u64 val = regs->regs[i++];
> printed += fprintf(fp, "%5s:0x%"PRIx64" ",
> - perf_reg_name(r, e_machine, e_flags),
> + perf_reg_name(r, e_machine, e_flags, regs->abi),
It is tempting for clarity to add the ABI to perf_reg_name as the first patch.
> val);
> }
>
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index f59228c1a39e..b7fb3f936ae3 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -1049,19 +1049,21 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o
> }
>
> if (param->record_mode == CALLCHAIN_DWARF) {
> + int abi;
> +
> if (!function) {
> uint16_t e_machine = evsel__e_machine(evsel, /*e_flags=*/NULL);
>
> evsel__set_sample_bit(evsel, REGS_USER);
> evsel__set_sample_bit(evsel, STACK_USER);
> if (opts->sample_user_regs &&
> - DWARF_MINIMAL_REGS(e_machine) != perf_user_reg_mask(EM_HOST)) {
> + DWARF_MINIMAL_REGS(e_machine) != perf_user_reg_mask(EM_HOST, &abi)) {
> attr->sample_regs_user |= DWARF_MINIMAL_REGS(e_machine);
> pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, "
> "specifying a subset with --user-regs may render DWARF unwinding unreliable, "
> "so the minimal registers set (IP, SP) is explicitly forced.\n");
> } else {
> - attr->sample_regs_user |= perf_user_reg_mask(EM_HOST);
> + attr->sample_regs_user |= perf_user_reg_mask(EM_HOST, &abi);
> }
> attr->sample_stack_user = param->dump_size;
> attr->exclude_callchain_user = 1;
> diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
> index c93c2f0c8105..518327883b18 100644
> --- a/tools/perf/util/parse-regs-options.c
> +++ b/tools/perf/util/parse-regs-options.c
> @@ -10,7 +10,8 @@
> #include "util/perf_regs.h"
> #include "util/parse-regs-options.h"
>
> -static void list_perf_regs(FILE *fp, uint64_t mask)
> +static void
> +list_perf_regs(FILE *fp, uint64_t mask, int abi)
> {
> const char *last_name = NULL;
>
> @@ -21,7 +22,7 @@ static void list_perf_regs(FILE *fp, uint64_t mask)
> if (((1ULL << reg) & mask) == 0)
> continue;
>
> - name = perf_reg_name(reg, EM_HOST, EF_HOST);
> + name = perf_reg_name(reg, EM_HOST, EF_HOST, abi);
> if (name && (!last_name || strcmp(last_name, name)))
> fprintf(fp, "%s%s", reg > 0 ? " " : "", name);
> last_name = name;
> @@ -29,7 +30,8 @@ static void list_perf_regs(FILE *fp, uint64_t mask)
> fputc('\n', fp);
> }
>
> -static uint64_t name_to_perf_reg_mask(const char *to_match, uint64_t mask)
> +static uint64_t
> +name_to_perf_reg_mask(const char *to_match, uint64_t mask, int abi)
> {
> uint64_t reg_mask = 0;
>
> @@ -39,7 +41,7 @@ static uint64_t name_to_perf_reg_mask(const char *to_match, uint64_t mask)
> if (((1ULL << reg) & mask) == 0)
> continue;
>
> - name = perf_reg_name(reg, EM_HOST, EF_HOST);
> + name = perf_reg_name(reg, EM_HOST, EF_HOST, abi);
> if (!name)
> continue;
>
> @@ -56,6 +58,7 @@ __parse_regs(const struct option *opt, const char *str, int unset, bool intr)
> char *s, *os = NULL, *p;
> int ret = -1;
> uint64_t mask;
> + int abi;
>
> if (unset)
> return 0;
> @@ -66,7 +69,7 @@ __parse_regs(const struct option *opt, const char *str, int unset, bool intr)
> if (*mode)
> return -1;
>
> - mask = intr ? perf_intr_reg_mask(EM_HOST) : perf_user_reg_mask(EM_HOST);
> + mask = intr ? perf_intr_reg_mask(EM_HOST, &abi) : perf_user_reg_mask(EM_HOST, &abi);
>
> /* str may be NULL in case no arg is passed to -I */
> if (!str) {
> @@ -87,11 +90,11 @@ __parse_regs(const struct option *opt, const char *str, int unset, bool intr)
> *p = '\0';
>
> if (!strcmp(s, "?")) {
> - list_perf_regs(stderr, mask);
> + list_perf_regs(stderr, mask, abi);
> goto error;
> }
>
> - reg_mask = name_to_perf_reg_mask(s, mask);
> + reg_mask = name_to_perf_reg_mask(s, mask, abi);
> if (reg_mask == 0) {
> ui__warning("Unknown register \"%s\", check man page or run \"perf record %s?\"\n",
> s, intr ? "-I" : "--user-regs=");
> diff --git a/tools/perf/util/perf-regs-arch/perf_regs_x86.c b/tools/perf/util/perf-regs-arch/perf_regs_x86.c
> index b6d20522b4e8..3e9241a11a95 100644
> --- a/tools/perf/util/perf-regs-arch/perf_regs_x86.c
> +++ b/tools/perf/util/perf-regs-arch/perf_regs_x86.c
> @@ -235,26 +235,26 @@ int __perf_sdt_arg_parse_op_x86(char *old_op, char **new_op)
> return SDT_ARG_VALID;
> }
>
> -uint64_t __perf_reg_mask_x86(bool intr)
> +static uint64_t __arch__reg_mask(u64 sample_type, u64 mask, bool has_simd_regs)
> {
> struct perf_event_attr attr = {
> - .type = PERF_TYPE_HARDWARE,
> - .config = PERF_COUNT_HW_CPU_CYCLES,
> - .sample_type = PERF_SAMPLE_REGS_INTR,
> - .sample_regs_intr = PERF_REG_EXTENDED_MASK,
> - .precise_ip = 1,
> - .disabled = 1,
> - .exclude_kernel = 1,
> + .type = PERF_TYPE_HARDWARE,
> + .config = PERF_COUNT_HW_CPU_CYCLES,
> + .sample_type = sample_type,
> + .precise_ip = 1,
> + .disabled = 1,
> + .exclude_kernel = 1,
> + .sample_simd_regs_enabled = has_simd_regs,
> };
> int fd;
> -
> - if (!intr)
> - return PERF_REGS_MASK;
> -
> /*
> * In an unnamed union, init it here to build on older gcc versions
> */
> attr.sample_period = 1;
> + if (sample_type == PERF_SAMPLE_REGS_INTR)
> + attr.sample_regs_intr = mask;
> + else
> + attr.sample_regs_user = mask;
>
> if (perf_pmus__num_core_pmus() > 1) {
> struct perf_pmu *pmu = NULL;
> @@ -276,13 +276,34 @@ uint64_t __perf_reg_mask_x86(bool intr)
> /*group_fd=*/-1, /*flags=*/0);
> if (fd != -1) {
> close(fd);
> - return (PERF_REG_EXTENDED_MASK | PERF_REGS_MASK);
> + return mask;
> + }
> +
> + return 0;
> +}
> +
> +uint64_t __perf_reg_mask_x86(bool intr, int *abi)
> +{
> + u64 sample_type = intr ? PERF_SAMPLE_REGS_INTR : PERF_SAMPLE_REGS_USER;
> + uint64_t mask = PERF_REGS_MASK;
> +
> + *abi = 0;
> + mask |= __arch__reg_mask(sample_type,
> + GENMASK_ULL(PERF_REG_X86_R31, PERF_REG_X86_R16),
> + true);
> + mask |= __arch__reg_mask(sample_type, BIT_ULL(PERF_REG_X86_SSP), true);
> +
> + if (mask != PERF_REGS_MASK) {
> + *abi |= PERF_SAMPLE_REGS_ABI_SIMD;
> + } else {
> + mask |= __arch__reg_mask(sample_type, PERF_REG_EXTENDED_MASK,
> + false);
> }
>
> - return PERF_REGS_MASK;
> + return mask;
> }
>
> -const char *__perf_reg_name_x86(int id)
> +static const char *__arch_reg_gpr_name(int id)
> {
> switch (id) {
> case PERF_REG_X86_AX:
> @@ -333,7 +354,60 @@ const char *__perf_reg_name_x86(int id)
> return "R14";
> case PERF_REG_X86_R15:
> return "R15";
> + default:
> + return NULL;
> + }
> +
> + return NULL;
> +}
>
> +static const char *__arch_reg_egpr_name(int id)
> +{
> + switch (id) {
> + case PERF_REG_X86_R16:
> + return "R16";
> + case PERF_REG_X86_R17:
> + return "R17";
> + case PERF_REG_X86_R18:
> + return "R18";
> + case PERF_REG_X86_R19:
> + return "R19";
> + case PERF_REG_X86_R20:
> + return "R20";
> + case PERF_REG_X86_R21:
> + return "R21";
> + case PERF_REG_X86_R22:
> + return "R22";
> + case PERF_REG_X86_R23:
> + return "R23";
> + case PERF_REG_X86_R24:
> + return "R24";
> + case PERF_REG_X86_R25:
> + return "R25";
> + case PERF_REG_X86_R26:
> + return "R26";
> + case PERF_REG_X86_R27:
> + return "R27";
> + case PERF_REG_X86_R28:
> + return "R28";
> + case PERF_REG_X86_R29:
> + return "R29";
> + case PERF_REG_X86_R30:
> + return "R30";
> + case PERF_REG_X86_R31:
> + return "R31";
> + case PERF_REG_X86_SSP:
> + return "SSP";
> + default:
> + return NULL;
> + }
> +
> + return NULL;
> +}
> +
> +static const char *__arch_reg_xmm_name(int id)
> +{
> + switch (id) {
> #define XMM(x) \
> case PERF_REG_X86_XMM ## x: \
> case PERF_REG_X86_XMM ## x + 1: \
> @@ -362,6 +436,22 @@ const char *__perf_reg_name_x86(int id)
> return NULL;
> }
>
> +const char *__perf_reg_name_x86(int id, int abi)
> +{
> + const char *name;
> +
> + name = __arch_reg_gpr_name(id);
> + if (name)
> + return name;
> +
> + if (abi & PERF_SAMPLE_REGS_ABI_SIMD)
> + name = __arch_reg_egpr_name(id);
> + else
> + name = __arch_reg_xmm_name(id);
> +
> + return name;
> +}
> +
> uint64_t __perf_reg_ip_x86(void)
> {
> return PERF_REG_X86_IP;
> diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
> index 5b8f34beb24e..bdd2eef13bc3 100644
> --- a/tools/perf/util/perf_regs.c
> +++ b/tools/perf/util/perf_regs.c
> @@ -32,10 +32,11 @@ int perf_sdt_arg_parse_op(uint16_t e_machine, char *old_op, char **new_op)
> return ret;
> }
>
> -uint64_t perf_intr_reg_mask(uint16_t e_machine)
> +uint64_t perf_intr_reg_mask(uint16_t e_machine, int *abi)
I wonder if abi is the right out argument name here. Before the SIMD
change the ABI meant either 32 or 64-bit. So we could imagine if it
were 32-bit then registers R8 to R15 wouldn't be in the mask for x86.
Perhaps just a "bool *" for sample_simd_regs_enabled.
Everything else looks good. Thanks for the weak function clean up,
this code is much more generic and better than before. I know it
wasn't trivial to do, but I appreciate it!
Thanks,
Ian
> {
> uint64_t mask = 0;
>
> + *abi = 0;
> switch (e_machine) {
> case EM_ARM:
> mask = __perf_reg_mask_arm(/*intr=*/true);
> @@ -64,7 +65,7 @@ uint64_t perf_intr_reg_mask(uint16_t e_machine)
> break;
> case EM_386:
> case EM_X86_64:
> - mask = __perf_reg_mask_x86(/*intr=*/true);
> + mask = __perf_reg_mask_x86(/*intr=*/true, abi);
> break;
> default:
> pr_debug("Unknown ELF machine %d, interrupt sampling register mask will be empty.\n",
> @@ -75,10 +76,11 @@ uint64_t perf_intr_reg_mask(uint16_t e_machine)
> return mask;
> }
>
> -uint64_t perf_user_reg_mask(uint16_t e_machine)
> +uint64_t perf_user_reg_mask(uint16_t e_machine, int *abi)
> {
> uint64_t mask = 0;
>
> + *abi = 0;
> switch (e_machine) {
> case EM_ARM:
> mask = __perf_reg_mask_arm(/*intr=*/false);
> @@ -107,7 +109,7 @@ uint64_t perf_user_reg_mask(uint16_t e_machine)
> break;
> case EM_386:
> case EM_X86_64:
> - mask = __perf_reg_mask_x86(/*intr=*/false);
> + mask = __perf_reg_mask_x86(/*intr=*/false, abi);
> break;
> default:
> pr_debug("Unknown ELF machine %d, user sampling register mask will be empty.\n",
> @@ -118,7 +120,7 @@ uint64_t perf_user_reg_mask(uint16_t e_machine)
> return mask;
> }
>
> -const char *perf_reg_name(int id, uint16_t e_machine, uint32_t e_flags)
> +const char *perf_reg_name(int id, uint16_t e_machine, uint32_t e_flags, int abi)
> {
> const char *reg_name = NULL;
>
> @@ -150,7 +152,7 @@ const char *perf_reg_name(int id, uint16_t e_machine, uint32_t e_flags)
> break;
> case EM_386:
> case EM_X86_64:
> - reg_name = __perf_reg_name_x86(id);
> + reg_name = __perf_reg_name_x86(id, abi);
> break;
> default:
> break;
> diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
> index 7c04700bf837..c9501ca8045d 100644
> --- a/tools/perf/util/perf_regs.h
> +++ b/tools/perf/util/perf_regs.h
> @@ -13,10 +13,10 @@ enum {
> };
>
> int perf_sdt_arg_parse_op(uint16_t e_machine, char *old_op, char **new_op);
> -uint64_t perf_intr_reg_mask(uint16_t e_machine);
> -uint64_t perf_user_reg_mask(uint16_t e_machine);
> +uint64_t perf_intr_reg_mask(uint16_t e_machine, int *abi);
> +uint64_t perf_user_reg_mask(uint16_t e_machine, int *abi);
>
> -const char *perf_reg_name(int id, uint16_t e_machine, uint32_t e_flags);
> +const char *perf_reg_name(int id, uint16_t e_machine, uint32_t e_flags, int abi);
> int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
> uint64_t perf_arch_reg_ip(uint16_t e_machine);
> uint64_t perf_arch_reg_sp(uint16_t e_machine);
> @@ -64,8 +64,8 @@ uint64_t __perf_reg_ip_s390(void);
> uint64_t __perf_reg_sp_s390(void);
>
> int __perf_sdt_arg_parse_op_x86(char *old_op, char **new_op);
> -uint64_t __perf_reg_mask_x86(bool intr);
> -const char *__perf_reg_name_x86(int id);
> +uint64_t __perf_reg_mask_x86(bool intr, int *abi);
> +const char *__perf_reg_name_x86(int id, int abi);
> uint64_t __perf_reg_ip_x86(void);
> uint64_t __perf_reg_sp_x86(void);
>
> diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
> index 2b0df7bd9a46..4cc5b96898e6 100644
> --- a/tools/perf/util/scripting-engines/trace-event-python.c
> +++ b/tools/perf/util/scripting-engines/trace-event-python.c
> @@ -733,7 +733,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, uint16_t e_machine,
>
> printed += scnprintf(bf + printed, size - printed,
> "%5s:0x%" PRIx64 " ",
> - perf_reg_name(r, e_machine, e_flags), val);
> + perf_reg_name(r, e_machine, e_flags, regs->abi), val);
> }
> }
>
> diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
> index 4b465abfa36c..7cf7bf86205d 100644
> --- a/tools/perf/util/session.c
> +++ b/tools/perf/util/session.c
> @@ -959,15 +959,16 @@ static void branch_stack__printf(struct perf_sample *sample,
> }
> }
>
> -static void regs_dump__printf(u64 mask, u64 *regs, uint16_t e_machine, uint32_t e_flags)
> +static void regs_dump__printf(u64 mask, struct regs_dump *regs,
> + uint16_t e_machine, uint32_t e_flags)
> {
> unsigned rid, i = 0;
>
> for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) {
> - u64 val = regs[i++];
> + u64 val = regs->regs[i++];
>
> printf(".... %-5s 0x%016" PRIx64 "\n",
> - perf_reg_name(rid, e_machine, e_flags), val);
> + perf_reg_name(rid, e_machine, e_flags, regs->abi), val);
> }
> }
>
> @@ -995,7 +996,7 @@ static void regs__printf(const char *type, struct regs_dump *regs,
> mask,
> regs_dump_abi(regs));
>
> - regs_dump__printf(mask, regs->regs, e_machine, e_flags);
> + regs_dump__printf(mask, regs, e_machine, e_flags);
> }
>
> static void regs_user__printf(struct perf_sample *sample, uint16_t e_machine, uint32_t e_flags)
> --
> 2.34.1
>
Powered by blists - more mailing lists