| 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: <CABPqkBRzwsmzaGFKK9+zOed8HK=Q9T9++hMHW+tSKh4EF0cKjg@mail.gmail.com>
Date: Wed, 24 Oct 2012 10:57:01 +0200
From: Stephane Eranian <eranian@...gle.com>
To: "Yan, Zheng" <zheng.z.yan@...el.com>
Cc: LKML <linux-kernel@...r.kernel.org>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
"ak@...ux.intel.com" <ak@...ux.intel.com>
Subject: Re: [PATCH V2 6/7] perf, x86: Use LBR call stack to get user callchain
On Wed, Oct 24, 2012 at 7:59 AM, Yan, Zheng <zheng.z.yan@...el.com> wrote:
> From: "Yan, Zheng" <zheng.z.yan@...el.com>
>
> Try enabling the LBR call stack feature if event request recording
> callchain. Try utilizing the LBR call stack to get user callchain
> in case of there is no frame pointer.
>
> Signed-off-by: Yan, Zheng <zheng.z.yan@...el.com>
> ---
> arch/x86/kernel/cpu/perf_event.c | 126 +++++++++++++++++++++--------
> arch/x86/kernel/cpu/perf_event.h | 7 ++
> arch/x86/kernel/cpu/perf_event_intel.c | 20 ++---
> arch/x86/kernel/cpu/perf_event_intel_lbr.c | 3 +
> include/linux/perf_event.h | 6 ++
> kernel/events/core.c | 11 ++-
> 6 files changed, 124 insertions(+), 49 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
> index 8ae8044..3bf2100 100644
> --- a/arch/x86/kernel/cpu/perf_event.c
> +++ b/arch/x86/kernel/cpu/perf_event.c
> @@ -398,35 +398,46 @@ 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;
> - }
> + }
> + /*
> + * 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) {
> + if (!has_branch_stack(event) && x86_pmu.attr_lbr_callstack) {
> + /*
> + * user did not specify branch_sample_type,
> + * try using the LBR call stack facility to
> + * record call chains in the user space.
> + */
> + event->attr.branch_sample_type =
> + PERF_SAMPLE_BRANCH_USER |
> + PERF_SAMPLE_BRANCH_CALL_STACK;
You are forcing user level here, but how do you know the user wanted
ONLY user level
callchains?
> }
> }
>
> @@ -1663,12 +1674,35 @@ 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 = simple_strtoul(buf, NULL, 0);
> +
> + if (x86_pmu.attr_lbr_callstack != !!val) {
> + 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_INT_ATTR(print_spurious_pmi, 0644, print_spurious_pmi);
> +static DEVICE_ATTR(lbr_callstack, S_IRUSR | S_IWUSR,
> + get_attr_lbr_callstack, set_attr_lbr_callstack);
>
> static struct attribute *x86_pmu_attrs[] = {
> &dev_attr_rdpmc.attr,
> &dev_attr_print_spurious_pmi.attr.attr,
> + &dev_attr_lbr_callstack.attr,
> NULL,
> };
>
Yes, you definitively want that level of control given you do things
under the cover.
> @@ -1795,12 +1829,29 @@ static unsigned long get_segment_base(unsigned int segment)
> return get_desc_base(desc + idx);
> }
>
> +static inline void
> +perf_callchain_lbr_callstack(struct perf_callchain_entry *entry,
> + struct perf_sample_data *data)
> +{
> + struct perf_branch_stack *br_stack = data->br_stack;
> +
> + if (br_stack && br_stack->user_callstack &&
> + x86_pmu.attr_lbr_callstack) {
> + int i = 0;
> + while (i < br_stack->nr && entry->nr < PERF_MAX_STACK_DEPTH) {
> + perf_callchain_store(entry, br_stack->entries[i].from);
> + i++;
> + }
> + }
> +}
> +
> #ifdef CONFIG_COMPAT
>
> #include <asm/compat.h>
>
> static inline int
> -perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
> +perf_callchain_user32(struct perf_callchain_entry *entry,
> + struct pt_regs *regs, struct perf_sample_data *data)
> {
> /* 32-bit process in 64-bit kernel. */
> unsigned long ss_base, cs_base;
> @@ -1829,11 +1880,16 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
> perf_callchain_store(entry, cs_base + frame.return_address);
> fp = compat_ptr(ss_base + frame.next_frame);
> }
> +
> + if (fp == compat_ptr(regs->bp))
> + perf_callchain_lbr_callstack(entry, data);
> +
> return 1;
> }
> #else
> static inline int
> -perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
> +perf_callchain_user32(struct perf_callchain_entry *entry,
> + struct pt_regs *regs, struct perf_sample_data *data)
> {
> return 0;
> }
> @@ -1863,12 +1919,12 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
> if (!current->mm)
> return;
>
> - if (perf_callchain_user32(regs, entry))
> + if (perf_callchain_user32(entry, regs, data))
> return;
>
> while (entry->nr < PERF_MAX_STACK_DEPTH) {
> unsigned long bytes;
> - frame.next_frame = NULL;
> + frame.next_frame = NULL;
> frame.return_address = 0;
>
> bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
> @@ -1881,6 +1937,10 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
> perf_callchain_store(entry, frame.return_address);
> fp = frame.next_frame;
> }
> +
> + /* try LBR callstack if there is no frame pointer */
> + if (fp == (void __user *)regs->bp)
> + perf_callchain_lbr_callstack(entry, data);
> }
>
> /*
> diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
> index bff282c..df7218a 100644
> --- a/arch/x86/kernel/cpu/perf_event.h
> +++ b/arch/x86/kernel/cpu/perf_event.h
> @@ -357,6 +357,7 @@ struct x86_pmu {
> * sysfs attrs
> */
> int attr_rdpmc;
> + int attr_lbr_callstack;
> struct attribute **format_attrs;
> struct attribute **events_attrs;
>
> @@ -444,6 +445,12 @@ do { \
>
> 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] > 0;
> +}
> +
> DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
>
> int x86_perf_event_set_period(struct perf_event *event);
> diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
> index dc2282d..57cc6ba 100644
> --- a/arch/x86/kernel/cpu/perf_event_intel.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel.c
> @@ -832,15 +832,10 @@ static __initconst const u64 atom_hw_cache_event_ids
> },
> };
>
> -static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
> +static inline bool intel_pmu_needs_lbr_callstack(struct perf_event *event)
> {
> - /* user explicitly requested branch sampling */
> - if (has_branch_stack(event))
> - return true;
> -
> - /* implicit branch sampling to correct PEBS skid */
> - if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 &&
> - x86_pmu.intel_cap.pebs_format < 2)
> + if ((event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
> + (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK))
> return true;
>
> return false;
> @@ -1004,7 +999,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
> * must disable before any actual event
> * because any event may be combined with LBR
> */
> - if (intel_pmu_needs_lbr_smpl(event))
> + if (needs_branch_stack(event))
> intel_pmu_lbr_disable(event);
>
> if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
> @@ -1065,7 +1060,7 @@ static void intel_pmu_enable_event(struct perf_event *event)
> * must enabled before any actual event
> * because any event may be combined with LBR
> */
> - if (intel_pmu_needs_lbr_smpl(event))
> + if (needs_branch_stack(event))
> intel_pmu_lbr_enable(event);
>
> if (event->attr.exclude_host)
> @@ -1202,7 +1197,8 @@ again:
>
> perf_sample_data_init(&data, 0, event->hw.last_period);
>
> - if (has_branch_stack(event))
> + if (has_branch_stack(event) ||
> + (event->ctx->task && intel_pmu_needs_lbr_callstack(event)))
> data.br_stack = &cpuc->lbr_stack;
>
> if (perf_event_overflow(event, &data, regs))
> @@ -1526,7 +1522,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
> if (event->attr.precise_ip && x86_pmu.pebs_aliases)
> x86_pmu.pebs_aliases(event);
>
> - if (intel_pmu_needs_lbr_smpl(event)) {
> + if (needs_branch_stack(event)) {
> ret = intel_pmu_setup_lbr_filter(event);
> if (ret)
> return ret;
> diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
> index c423830..4879904 100644
> --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
> @@ -691,6 +691,8 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
> int i, j, type;
> bool compress = false;
>
> + cpuc->lbr_stack.user_callstack = branch_user_callstack(br_sel);
> +
> /* if sampling all branches, then nothing to filter */
> if ((br_sel & X86_BR_ALL) == X86_BR_ALL)
> return;
> @@ -843,6 +845,7 @@ void intel_pmu_lbr_init_hsw(void)
>
> x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
> x86_pmu.lbr_sel_map = hsw_lbr_sel_map;
> + x86_pmu.attr_lbr_callstack = 1;
>
> pr_cont("16-deep LBR, ");
> }
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index 803b511..693dfec 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -98,6 +98,7 @@ struct perf_branch_entry {
> * recent branch.
> */
> struct perf_branch_stack {
> + unsigned user_callstack:1;
> __u64 nr;
> struct perf_branch_entry entries[0];
> };
> @@ -757,6 +758,11 @@ static inline bool has_branch_stack(struct perf_event *event)
> return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
> }
>
> +static inline bool needs_branch_stack(struct perf_event *event)
> +{
> + return event->attr.branch_sample_type != 0;
> +}
> +
> extern int perf_output_begin(struct perf_output_handle *handle,
> struct perf_event *event, unsigned int size);
> extern void perf_output_end(struct perf_output_handle *handle);
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index b914039..7236122 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -899,7 +899,7 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
> if (is_cgroup_event(event))
> ctx->nr_cgroups++;
>
> - if (has_branch_stack(event))
> + if (needs_branch_stack(event))
> ctx->nr_branch_stack++;
>
> list_add_rcu(&event->event_entry, &ctx->event_list);
> @@ -1047,7 +1047,7 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
> cpuctx->cgrp = NULL;
> }
>
> - if (has_branch_stack(event)) {
> + if (needs_branch_stack(event)) {
> if (ctx->is_active)
> __get_cpu_var(perf_branch_stack_events)--;
> ctx->nr_branch_stack--;
> @@ -2914,7 +2914,7 @@ static void free_event(struct perf_event *event)
> static_key_slow_dec_deferred(&perf_sched_events);
> }
>
> - if (has_branch_stack(event))
> + if (needs_branch_stack(event))
> static_key_slow_dec_deferred(&perf_sched_events);
> }
>
> @@ -6234,6 +6234,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
> if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
> goto done;
>
> + if (!has_branch_stack(event))
> + event->attr.branch_sample_type = 0;
> +
> pmu = perf_init_event(event);
>
> done:
> @@ -6266,7 +6269,7 @@ done:
> return ERR_PTR(err);
> }
> }
> - if (has_branch_stack(event))
> + if (needs_branch_stack(event))
> static_key_slow_inc(&perf_sched_events.key);
> }
>
> --
> 1.7.11.7
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists