perf: Add generic taken branch sampling support

This patch adds the ability to sample taken branches to the
perf_event interface.

The ability to capture taken branches is very useful for all
sorts of analysis. For instance, basic block profiling, call
counts, statistical call graph.

This new capability requires hardware assist and as such may
not be available on all HW platforms. On Intel x86 it is
implemented on top of the Last Branch Record (LBR) facility.

To enable taken branches sampling, the PERF_SAMPLE_BRANCH_STACK
bit must be set in attr->sample_type.

Sampled taken branches may be filtered by type and/or priv
levels.

The patch adds a new field, called branch_sample_type, to the
perf_event_attr structure. It contains a bitmask of filters
to apply to the sampled taken branches.

Filters may be implemented in HW. If the HW filter does not exist
or is not good enough, some arch may also implement a SW filter.

The following generic filters are currently defined:
- PERF_SAMPLE_USER
  only branches whose targets are at the user level

- PERF_SAMPLE_KERNEL
  only branches whose targets are at the kernel level

- PERF_SAMPLE_HV
  only branches whose targets are at the hypervisor level

- PERF_SAMPLE_ANY
  any type of branches (subject to priv levels filters)

- PERF_SAMPLE_ANY_CALL
  any call branches (may incl. syscall on some arch)

- PERF_SAMPLE_ANY_RET
  any return branches (may incl. syscall returns on some arch)

- PERF_SAMPLE_IND_CALL
  indirect call branches

Obviously filter may be combined. The priv level bits are optional.
If not provided, the priv level of the associated event are used. It
is possible to collect branches at a priv level different from the
associated event. Use of kernel, hv priv levels is subject to permissions
and availability (hv).

The number of taken branch records present in each sample may vary based
on HW, the type of sampled branches, the executed code. Therefore
each sample contains the number of taken branches it contains.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1328826068-11713-2-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 68 insertions, 0 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index e8b32ac75ce3..5820efdf47cd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -118,6 +118,13 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
                        PERF_FLAG_FD_OUTPUT  |\
                        PERF_FLAG_PID_CGROUP)
 
+/*
+ * branch priv levels that need permission checks
+ */
+#define PERF_SAMPLE_BRANCH_PERM_PLM \
+        (PERF_SAMPLE_BRANCH_KERNEL |\
+         PERF_SAMPLE_BRANCH_HV)
+
 enum event_type_t {
         EVENT_FLEXIBLE = 0x1,
         EVENT_PINNED = 0x2,
@@ -3907,6 +3914,24 @@ void perf_output_sample(struct perf_output_handle *handle,
                         }
                 }
         }
+
+        if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+                if (data->br_stack) {
+                        size_t size;
+
+                        size = data->br_stack->nr
+                             * sizeof(struct perf_branch_entry);
+
+                        perf_output_put(handle, data->br_stack->nr);
+                        perf_output_copy(handle, data->br_stack->entries, size);
+                } else {
+                        /*
+                         * we always store at least the value of nr
+                         */
+                        u64 nr = 0;
+                        perf_output_put(handle, nr);
+                }
+        }
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
@@ -3949,6 +3974,15 @@ void perf_prepare_sample(struct perf_event_header *header,
                 WARN_ON_ONCE(size & (sizeof(u64)-1));
                 header->size += size;
         }
+
+        if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+                int size = sizeof(u64); /* nr */
+                if (data->br_stack) {
+                        size += data->br_stack->nr
+                              * sizeof(struct perf_branch_entry);
+                }
+                header->size += size;
+        }
 }
 
 static void perf_event_output(struct perf_event *event,
@@ -5935,6 +5969,40 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
         if (attr->read_format & ~(PERF_FORMAT_MAX-1))
                 return -EINVAL;
 
+        if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) {
+                u64 mask = attr->branch_sample_type;
+
+                /* only using defined bits */
+                if (mask & ~(PERF_SAMPLE_BRANCH_MAX-1))
+                        return -EINVAL;
+
+                /* at least one branch bit must be set */
+                if (!(mask & ~PERF_SAMPLE_BRANCH_PLM_ALL))
+                        return -EINVAL;
+
+                /* kernel level capture: check permissions */
+                if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM)
+                    && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+                        return -EACCES;
+
+                /* propagate priv level, when not set for branch */
+                if (!(mask & PERF_SAMPLE_BRANCH_PLM_ALL)) {
+
+                        /* exclude_kernel checked on syscall entry */
+                        if (!attr->exclude_kernel)
+                                mask |= PERF_SAMPLE_BRANCH_KERNEL;
+
+                        if (!attr->exclude_user)
+                                mask |= PERF_SAMPLE_BRANCH_USER;
+
+                        if (!attr->exclude_hv)
+                                mask |= PERF_SAMPLE_BRANCH_HV;
+                        /*
+                         * adjust user setting (for HW filter setup)
+                         */
+                        attr->branch_sample_type = mask;
+                }
+        }
 out:
         return ret;