Athira Rajeev <atraj...@linux.vnet.ibm.com> writes:
> From: Anju T Sudhakar <a...@linux.vnet.ibm.com>
>
> Add extended regs to sample_reg_mask in the tool side to use
> with `-I?` option. Perf tools side uses extended mask to display
> the platform supported register names (with -I? option) to the user
> and also send this mask to the kernel to capture the extended registers
> in each sample. Hence decide the mask value based on the processor
> version.
>
> Signed-off-by: Anju T Sudhakar <a...@linux.vnet.ibm.com>
> [Decide extended mask at run time based on platform]
> Signed-off-by: Athira Rajeev <atraj...@linux.vnet.ibm.com>
> Reviewed-by: Madhavan Srinivasan <ma...@linux.vnet.ibm.com>
Will need an ack from perf tools folks, who are not on Cc by the looks.
> diff --git a/tools/arch/powerpc/include/uapi/asm/perf_regs.h
> b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
> index f599064..485b1d5 100644
> --- a/tools/arch/powerpc/include/uapi/asm/perf_regs.h
> +++ b/tools/arch/powerpc/include/uapi/asm/perf_regs.h
> @@ -48,6 +48,18 @@ enum perf_event_powerpc_regs {
> PERF_REG_POWERPC_DSISR,
> PERF_REG_POWERPC_SIER,
> PERF_REG_POWERPC_MMCRA,
> - PERF_REG_POWERPC_MAX,
> + /* Extended registers */
> + PERF_REG_POWERPC_MMCR0,
> + PERF_REG_POWERPC_MMCR1,
> + PERF_REG_POWERPC_MMCR2,
> + /* Max regs without the extended regs */
> + PERF_REG_POWERPC_MAX = PERF_REG_POWERPC_MMCRA + 1,
I don't really understand this idea of a max that's not the max.
> };
> +
> +#define PERF_REG_PMU_MASK ((1ULL << PERF_REG_POWERPC_MAX) - 1)
> +
> +/* PERF_REG_EXTENDED_MASK value for CPU_FTR_ARCH_300 */
> +#define PERF_REG_PMU_MASK_300 (((1ULL << (PERF_REG_POWERPC_MMCR2 + 1)) -
> 1) \
> + - PERF_REG_PMU_MASK)
> +
> #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */
> diff --git a/tools/perf/arch/powerpc/include/perf_regs.h
> b/tools/perf/arch/powerpc/include/perf_regs.h
> index e18a355..46ed00d 100644
> --- a/tools/perf/arch/powerpc/include/perf_regs.h
> +++ b/tools/perf/arch/powerpc/include/perf_regs.h
> @@ -64,7 +64,10 @@
> [PERF_REG_POWERPC_DAR] = "dar",
> [PERF_REG_POWERPC_DSISR] = "dsisr",
> [PERF_REG_POWERPC_SIER] = "sier",
> - [PERF_REG_POWERPC_MMCRA] = "mmcra"
> + [PERF_REG_POWERPC_MMCRA] = "mmcra",
> + [PERF_REG_POWERPC_MMCR0] = "mmcr0",
> + [PERF_REG_POWERPC_MMCR1] = "mmcr1",
> + [PERF_REG_POWERPC_MMCR2] = "mmcr2",
> };
>
> static inline const char *perf_reg_name(int id)
> diff --git a/tools/perf/arch/powerpc/util/perf_regs.c
> b/tools/perf/arch/powerpc/util/perf_regs.c
> index 0a52429..9179230 100644
> --- a/tools/perf/arch/powerpc/util/perf_regs.c
> +++ b/tools/perf/arch/powerpc/util/perf_regs.c
> @@ -6,9 +6,14 @@
>
> #include "../../../util/perf_regs.h"
> #include "../../../util/debug.h"
> +#include "../../../util/event.h"
> +#include "../../../util/header.h"
> +#include "../../../perf-sys.h"
>
> #include <linux/kernel.h>
>
> +#define PVR_POWER9 0x004E
> +
> const struct sample_reg sample_reg_masks[] = {
> SMPL_REG(r0, PERF_REG_POWERPC_R0),
> SMPL_REG(r1, PERF_REG_POWERPC_R1),
> @@ -55,6 +60,9 @@
> SMPL_REG(dsisr, PERF_REG_POWERPC_DSISR),
> SMPL_REG(sier, PERF_REG_POWERPC_SIER),
> SMPL_REG(mmcra, PERF_REG_POWERPC_MMCRA),
> + SMPL_REG(mmcr0, PERF_REG_POWERPC_MMCR0),
> + SMPL_REG(mmcr1, PERF_REG_POWERPC_MMCR1),
> + SMPL_REG(mmcr2, PERF_REG_POWERPC_MMCR2),
> SMPL_REG_END
> };
>
> @@ -163,3 +171,50 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
>
> return SDT_ARG_VALID;
> }
> +
> +uint64_t arch__intr_reg_mask(void)
> +{
> + struct perf_event_attr attr = {
> + .type = PERF_TYPE_HARDWARE,
> + .config = PERF_COUNT_HW_CPU_CYCLES,
> + .sample_type = PERF_SAMPLE_REGS_INTR,
> + .precise_ip = 1,
> + .disabled = 1,
> + .exclude_kernel = 1,
> + };
> + int fd, ret;
> + char buffer[64];
> + u32 version;
> + u64 extended_mask = 0;
> +
> + /* Get the PVR value to set the extended
> + * mask specific to platform
Comment format is wrong, and punctuation please.
> + */
> + get_cpuid(buffer, sizeof(buffer));
> + ret = sscanf(buffer, "%u,", &version);
This is powerpc specific code, why not just use mfspr(SPRN_PVR), rather
than redirecting via printf/sscanf.
> +
> + if (ret != 1) {
> + pr_debug("Failed to get the processor version, unable to output
> extended registers\n");
> + return PERF_REGS_MASK;
> + }
> +
> + if (version == PVR_POWER9)
> + extended_mask = PERF_REG_PMU_MASK_300;
> + else
> + return PERF_REGS_MASK;
> +
> + attr.sample_regs_intr = extended_mask;
> + attr.sample_period = 1;
> + event_attr_init(&attr);
> +
> + /*
> + * check if the pmu supports perf extended regs, before
> + * returning the register mask to sample.
> + */
> + fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
> + if (fd != -1) {
> + close(fd);
> + return (extended_mask | PERF_REGS_MASK);
> + }
> + return PERF_REGS_MASK;
I think this would read a bit better like:
mask = PERF_REGS_MASK;
if (version == PVR_POWER9)
extended_mask = PERF_REG_PMU_MASK_300;
else
return mask;
attr.sample_regs_intr = extended_mask;
attr.sample_period = 1;
event_attr_init(&attr);
/*
* check if the pmu supports perf extended regs, before
* returning the register mask to sample.
*/
fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
if (fd != -1) {
close(fd);
mask |= extended_mask;
}
return mask;
cheers
