lkml.org 
[lkml]   [2014]   [Feb]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [PATCH 13/14] perf, x86: enable LBR callstack when recording callchain
From
On Fri, Jan 3, 2014 at 6:48 AM, Yan, Zheng <zheng.z.yan@intel.com> wrote:
> Try enabling the LBR callstack facility if user requests recording
> user space callchain. Also adds a cpu pmu attribute to enable/disable
> this feature. This feature is disabled by default because it may
> contend for the LBR with other events that explicitly require branch
> stack
>
We have discussed this patch before.
I think you need to describe cleary what's going on based on priv levels.

excl_user=0, excl_kernel=0 : user callstack via LBR, kernel via framepointer?
excl_user=0, excl_kernel=1 : user callstack via LBR
excl_user=1, excl_kernel=0 : kernel via framepointer?
excl_user=1, excl_kernel=1 : nothing

This does not come out clear from the code below.

> Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
> ---
> arch/x86/kernel/cpu/perf_event.c | 99 ++++++++++++++++++++++++++++------------
> arch/x86/kernel/cpu/perf_event.h | 7 +++
> 2 files changed, 77 insertions(+), 29 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
> index 1509340..3ea184a 100644
> --- a/arch/x86/kernel/cpu/perf_event.c
> +++ b/arch/x86/kernel/cpu/perf_event.c
> @@ -399,37 +399,49 @@ int x86_pmu_hw_config(struct perf_event *event)
>
> if (event->attr.precise_ip > precise)
> return -EOPNOTSUPP;
> + }
> + /*
> + * check that PEBS LBR correction does not conflict with
> + * whatever the user is asking with attr->branch_sample_type
> + */
> + if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format < 2) {
> + u64 *br_type = &event->attr.branch_sample_type;
> +
> + if (has_branch_stack(event)) {
> + if (!precise_br_compat(event))
> + return -EOPNOTSUPP;
> +
> + /* branch_sample_type is compatible */
> +
> + } else {
> + /*
> + * user did not specify branch_sample_type
> + *
> + * For PEBS fixups, we capture all
> + * the branches at the priv level of the
> + * event.
> + */
> + *br_type = PERF_SAMPLE_BRANCH_ANY;
> +
> + if (!event->attr.exclude_user)
> + *br_type |= PERF_SAMPLE_BRANCH_USER;
> +
> + if (!event->attr.exclude_kernel)
> + *br_type |= PERF_SAMPLE_BRANCH_KERNEL;
> + }
> + } else if ((event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
> + !has_branch_stack(event) &&
> + x86_pmu.attr_lbr_callstack &&
> + !event->attr.exclude_user &&
> + (event->attach_state & PERF_ATTACH_TASK)) {
> /*
> - * check that PEBS LBR correction does not conflict with
> - * whatever the user is asking with attr->branch_sample_type
> + * user did not specify branch_sample_type,
> + * try using the LBR call stack facility to
> + * record call chains of user program.
> */
> - if (event->attr.precise_ip > 1 &&
> - x86_pmu.intel_cap.pebs_format < 2) {
> - u64 *br_type = &event->attr.branch_sample_type;
> -
> - if (has_branch_stack(event)) {
> - if (!precise_br_compat(event))
> - return -EOPNOTSUPP;
> -
> - /* branch_sample_type is compatible */
> -
> - } else {
> - /*
> - * user did not specify branch_sample_type
> - *
> - * For PEBS fixups, we capture all
> - * the branches at the priv level of the
> - * event.
> - */
> - *br_type = PERF_SAMPLE_BRANCH_ANY;
> -
> - if (!event->attr.exclude_user)
> - *br_type |= PERF_SAMPLE_BRANCH_USER;
> -
> - if (!event->attr.exclude_kernel)
> - *br_type |= PERF_SAMPLE_BRANCH_KERNEL;
> - }
> - }
> + event->attr.branch_sample_type =
> + PERF_SAMPLE_BRANCH_USER |
> + PERF_SAMPLE_BRANCH_CALL_STACK;
> }
>
> /*
> @@ -1828,10 +1840,39 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
> return count;
> }
>
> +static ssize_t get_attr_lbr_callstack(struct device *cdev,
> + struct device_attribute *attr, char *buf)
> +{
> + return snprintf(buf, 40, "%d\n", x86_pmu.attr_lbr_callstack);
> +}
> +
> +static ssize_t set_attr_lbr_callstack(struct device *cdev,
> + struct device_attribute *attr,
> + const char *buf, size_t count)
> +{
> + unsigned long val;
> + ssize_t ret;
> +
> + ret = kstrtoul(buf, 0, &val);
> + if (ret)
> + return ret;
> +
> + if (!!val != !!x86_pmu.attr_lbr_callstack) {
> + if (val && !x86_pmu_has_lbr_callstack())
> + return -EOPNOTSUPP;
> + x86_pmu.attr_lbr_callstack = !!val;
> + }
> + return count;
> +}
> +
> static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc);
> +static DEVICE_ATTR(lbr_callstack, S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH,
> + get_attr_lbr_callstack, set_attr_lbr_callstack);
> +
>
> static struct attribute *x86_pmu_attrs[] = {
> &dev_attr_rdpmc.attr,
> + &dev_attr_lbr_callstack.attr,
> NULL,
> };
>
> diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
> index 3ed9629..b45258c 100644
> --- a/arch/x86/kernel/cpu/perf_event.h
> +++ b/arch/x86/kernel/cpu/perf_event.h
> @@ -400,6 +400,7 @@ struct x86_pmu {
> * sysfs attrs
> */
> int attr_rdpmc;
> + int attr_lbr_callstack;
> struct attribute **format_attrs;
> struct attribute **event_attrs;
>
> @@ -504,6 +505,12 @@ static struct perf_pmu_events_attr event_attr_##v = { \
>
> extern struct x86_pmu x86_pmu __read_mostly;
>
> +static inline bool x86_pmu_has_lbr_callstack(void)
> +{
> + return x86_pmu.lbr_sel_map &&
> + x86_pmu.lbr_sel_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] > 0;
> +}
> +
> DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
>
> int x86_perf_event_set_period(struct perf_event *event);
> --
> 1.8.4.2
>


\
 
 \ /
  Last update: 2014-02-06 18:01    [W:0.150 / U:0.716 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site