| 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: <20230522113040.2329924-2-kan.liang@linux.intel.com>
Date: Mon, 22 May 2023 04:30:36 -0700
From: kan.liang@...ux.intel.com
To: peterz@...radead.org, mingo@...hat.com, acme@...nel.org,
linux-kernel@...r.kernel.org
Cc: mark.rutland@....com, alexander.shishkin@...ux.intel.com,
jolsa@...nel.org, namhyung@...nel.org, irogers@...gle.com,
adrian.hunter@...el.com, ak@...ux.intel.com, eranian@...gle.com,
alexey.v.bayduraev@...ux.intel.com, tinghao.zhang@...el.com,
Kan Liang <kan.liang@...ux.intel.com>,
Sandipan Das <sandipan.das@....com>,
Ravi Bangoria <ravi.bangoria@....com>,
Athira Rajeev <atrajeev@...ux.vnet.ibm.com>
Subject: [PATCH V2 2/6] perf: Add branch stack extension
From: Kan Liang <kan.liang@...ux.intel.com>
Currently, the extra information of a branch entry is stored in a u64
space. With more and more information added, the space is running out.
For example, the information of occurrences of events will be added for
each branch.
Add an extension space to record the new information for each branch
entry. The space is appended after the struct perf_branch_stack.
Add a bit in struct perf_branch_entry to indicate whether the extra
information is included.
Reviewed-by: Andi Kleen <ak@...ux.intel.com>
Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
Cc: Sandipan Das <sandipan.das@....com>
Cc: Ravi Bangoria <ravi.bangoria@....com>
Cc: Athira Rajeev <atrajeev@...ux.vnet.ibm.com>
---
New patch
- Introduce a generic extension space which can be used to
store the LBR event information for Intel. It can also be used by
other ARCHs for the other purpose.
- Add a new bit in struct perf_branch_entry to indicate whether the
extra information is included.
arch/powerpc/perf/core-book3s.c | 2 +-
arch/x86/events/amd/core.c | 2 +-
arch/x86/events/intel/core.c | 2 +-
arch/x86/events/intel/ds.c | 4 ++--
include/linux/perf_event.h | 18 +++++++++++++++++-
include/uapi/linux/perf_event.h | 4 +++-
kernel/events/core.c | 5 +++++
7 files changed, 30 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 8c1f7def596e..3c14596bbfaf 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2313,7 +2313,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
struct cpu_hw_events *cpuhw;
cpuhw = this_cpu_ptr(&cpu_hw_events);
power_pmu_bhrb_read(event, cpuhw);
- perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack);
+ perf_sample_save_brstack(&data, event, &cpuhw->bhrb_stack, NULL);
}
if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC &&
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index bccea57dee81..facee84aeecb 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -930,7 +930,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
continue;
if (has_branch_stack(event))
- perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
+ perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
if (perf_event_overflow(event, &data, regs))
x86_pmu_stop(event, 0);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ba2a971e6b8a..21566f66bfd8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3048,7 +3048,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
perf_sample_data_init(&data, 0, event->hw.last_period);
if (has_branch_stack(event))
- perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
+ perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
if (perf_event_overflow(event, &data, regs))
x86_pmu_stop(event, 0);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 608e220e46aa..3f16e95e99dd 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1747,7 +1747,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
setup_pebs_time(event, data, pebs->tsc);
if (has_branch_stack(event))
- perf_sample_save_brstack(data, event, &cpuc->lbr_stack);
+ perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
}
static void adaptive_pebs_save_regs(struct pt_regs *regs,
@@ -1904,7 +1904,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
if (has_branch_stack(event)) {
intel_pmu_store_pebs_lbrs(lbr);
- perf_sample_save_brstack(data, event, &cpuc->lbr_stack);
+ perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
}
}
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d5628a7b5eaa..e2e04dc39199 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -126,6 +126,16 @@ struct perf_branch_stack {
struct perf_branch_entry entries[];
};
+/*
+ * The extension space is appended after the struct perf_branch_stack.
+ * It is used to store the extra data of each branch, e.g.,
+ * the occurrences of events since the last branch entry for Intel LBR.
+ */
+struct perf_branch_stack_ext {
+ __u64 nr;
+ __u64 data[];
+};
+
struct task_struct;
/*
@@ -1161,6 +1171,7 @@ struct perf_sample_data {
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
+ struct perf_branch_stack_ext *br_stack_ext;
union perf_sample_weight weight;
union perf_mem_data_src data_src;
u64 txn;
@@ -1237,7 +1248,8 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
static inline void perf_sample_save_brstack(struct perf_sample_data *data,
struct perf_event *event,
- struct perf_branch_stack *brs)
+ struct perf_branch_stack *brs,
+ struct perf_branch_stack_ext *brs_ext)
{
int size = sizeof(u64); /* nr */
@@ -1245,7 +1257,11 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
size += sizeof(u64);
size += brs->nr * sizeof(struct perf_branch_entry);
+ if (brs_ext)
+ size += (1 + brs_ext->nr) * sizeof(u64);
+
data->br_stack = brs;
+ data->br_stack_ext = brs_ext;
data->dyn_size += size;
data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
}
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 37675437b768..1b3b90965b6b 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1410,6 +1410,7 @@ union perf_mem_data_src {
* cycles: cycles from last branch (or 0 if not supported)
* type: branch type
* spec: branch speculation info (or 0 if not supported)
+ * ext: has extension space for extra info (or 0 if not supported)
*/
struct perf_branch_entry {
__u64 from;
@@ -1423,7 +1424,8 @@ struct perf_branch_entry {
spec:2, /* branch speculation info */
new_type:4, /* additional branch type */
priv:3, /* privilege level */
- reserved:31;
+ ext:1, /* has extension */
+ reserved:30;
};
union perf_sample_weight {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 435815d3be3f..dfd6703139a1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7324,6 +7324,11 @@ void perf_output_sample(struct perf_output_handle *handle,
if (branch_sample_hw_index(event))
perf_output_put(handle, data->br_stack->hw_idx);
perf_output_copy(handle, data->br_stack->entries, size);
+ if (data->br_stack_ext) {
+ size = data->br_stack_ext->nr * sizeof(u64);
+ perf_output_put(handle, data->br_stack_ext->nr);
+ perf_output_copy(handle, data->br_stack_ext->data, size);
+ }
} else {
/*
* we always store at least the value of nr
--
2.35.1
Powered by blists - more mailing lists