aboutsummaryrefslogtreecommitdiff
path: root/samples/bpf/cpustat_kern.c
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2018-02-26 10:37:24 -0500
committerDavid S. Miller <davem@davemloft.net>2018-02-26 10:37:24 -0500
commitba6056a41cb09575a5ffe2fcfa9a0afb1b60eb92 (patch)
treee1858eb29573b86b6a42cbd3d6fbd18aa7b565bf /samples/bpf/cpustat_kern.c
parentf74290fdb363665538743d14c4f00aeacdb68d87 (diff)
parentc53507778998d45543b27266742d04cd384de356 (diff)
downloadlinux-stericsson-ba6056a41cb09575a5ffe2fcfa9a0afb1b60eb92.tar.gz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says: ==================== pull-request: bpf-next 2018-02-26 The following pull-request contains BPF updates for your *net-next* tree. The main changes are: 1) Various improvements for BPF kselftests: i) skip unprivileged tests when kernel.unprivileged_bpf_disabled sysctl knob is set, ii) count the number of skipped tests from unprivileged, iii) when a test case had an unexpected error then print the actual but also the unexpected one for better comparison, from Joe. 2) Add a sample program for collecting CPU state statistics with regards to how long the CPU resides in cstate and pstate levels. Based on cpu_idle and cpu_frequency trace points, from Leo. 3) Various x64 BPF JIT optimizations to further shrink the generated image size in order to make it more icache friendly. When tested on the Cilium generated programs, image size reduced by approx 4-5% in best case mainly due to how LLVM emits unsigned 32 bit constants, from Daniel. 4) Improvements and fixes on the BPF sockmap sample programs: i) fix the sockmap's Makefile to include nlattr.o for libbpf, ii) detach the sock ops programs from the cgroup before exit, from Prashant. 5) Avoid including xdp.h in filter.h by just forward declaring the struct xdp_rxq_info in filter.h, from Jesper. 6) Fix the BPF kselftests Makefile for cgroup_helpers.c by only declaring it a dependency for test_dev_cgroup.c but not every other test case where it is not needed, from Jesper. 7) Adjust rlimit RLIMIT_MEMLOCK for test_tcpbpf_user selftest since the default is insufficient for creating the 'global_map' used in the corresponding BPF program, from Yonghong. 8) Likewise, for the xdp_redirect sample, Tushar ran into the same when invoking xdp_redirect and xdp_monitor at the same time, therefore in order to have the sample generically work bump the limit here, too. Fix from Tushar. 9) Avoid an unnecessary NULL check in BPF_CGROUP_RUN_PROG_INET_SOCK() since sk is always guaranteed to be non-NULL, from Yafang. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'samples/bpf/cpustat_kern.c')
-rw-r--r--samples/bpf/cpustat_kern.c281
1 files changed, 281 insertions, 0 deletions
diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c
new file mode 100644
index 000000000000..68c84da065b1
--- /dev/null
+++ b/samples/bpf/cpustat_kern.c
@@ -0,0 +1,281 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/version.h>
+#include <linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+/*
+ * The CPU number, cstate number and pstate number are based
+ * on 96boards Hikey with octa CA53 CPUs.
+ *
+ * Every CPU have three idle states for cstate:
+ * WFI, CPU_OFF, CLUSTER_OFF
+ *
+ * Every CPU have 5 operating points:
+ * 208MHz, 432MHz, 729MHz, 960MHz, 1200MHz
+ *
+ * This code is based on these assumption and other platforms
+ * need to adjust these definitions.
+ */
+#define MAX_CPU 8
+#define MAX_PSTATE_ENTRIES 5
+#define MAX_CSTATE_ENTRIES 3
+
+static int cpu_opps[] = { 208000, 432000, 729000, 960000, 1200000 };
+
+/*
+ * my_map structure is used to record cstate and pstate index and
+ * timestamp (Idx, Ts), when new event incoming we need to update
+ * combination for new state index and timestamp (Idx`, Ts`).
+ *
+ * Based on (Idx, Ts) and (Idx`, Ts`) we can calculate the time
+ * interval for the previous state: Duration(Idx) = Ts` - Ts.
+ *
+ * Every CPU has one below array for recording state index and
+ * timestamp, and record for cstate and pstate saperately:
+ *
+ * +--------------------------+
+ * | cstate timestamp |
+ * +--------------------------+
+ * | cstate index |
+ * +--------------------------+
+ * | pstate timestamp |
+ * +--------------------------+
+ * | pstate index |
+ * +--------------------------+
+ */
+#define MAP_OFF_CSTATE_TIME 0
+#define MAP_OFF_CSTATE_IDX 1
+#define MAP_OFF_PSTATE_TIME 2
+#define MAP_OFF_PSTATE_IDX 3
+#define MAP_OFF_NUM 4
+
+struct bpf_map_def SEC("maps") my_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u64),
+ .max_entries = MAX_CPU * MAP_OFF_NUM,
+};
+
+/* cstate_duration records duration time for every idle state per CPU */
+struct bpf_map_def SEC("maps") cstate_duration = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u64),
+ .max_entries = MAX_CPU * MAX_CSTATE_ENTRIES,
+};
+
+/* pstate_duration records duration time for every operating point per CPU */
+struct bpf_map_def SEC("maps") pstate_duration = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u64),
+ .max_entries = MAX_CPU * MAX_PSTATE_ENTRIES,
+};
+
+/*
+ * The trace events for cpu_idle and cpu_frequency are taken from:
+ * /sys/kernel/debug/tracing/events/power/cpu_idle/format
+ * /sys/kernel/debug/tracing/events/power/cpu_frequency/format
+ *
+ * These two events have same format, so define one common structure.
+ */
+struct cpu_args {
+ u64 pad;
+ u32 state;
+ u32 cpu_id;
+};
+
+/* calculate pstate index, returns MAX_PSTATE_ENTRIES for failure */
+static u32 find_cpu_pstate_idx(u32 frequency)
+{
+ u32 i;
+
+ for (i = 0; i < sizeof(cpu_opps) / sizeof(u32); i++) {
+ if (frequency == cpu_opps[i])
+ return i;
+ }
+
+ return i;
+}
+
+SEC("tracepoint/power/cpu_idle")
+int bpf_prog1(struct cpu_args *ctx)
+{
+ u64 *cts, *pts, *cstate, *pstate, prev_state, cur_ts, delta;
+ u32 key, cpu, pstate_idx;
+ u64 *val;
+
+ if (ctx->cpu_id > MAX_CPU)
+ return 0;
+
+ cpu = ctx->cpu_id;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_TIME;
+ cts = bpf_map_lookup_elem(&my_map, &key);
+ if (!cts)
+ return 0;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX;
+ cstate = bpf_map_lookup_elem(&my_map, &key);
+ if (!cstate)
+ return 0;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME;
+ pts = bpf_map_lookup_elem(&my_map, &key);
+ if (!pts)
+ return 0;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX;
+ pstate = bpf_map_lookup_elem(&my_map, &key);
+ if (!pstate)
+ return 0;
+
+ prev_state = *cstate;
+ *cstate = ctx->state;
+
+ if (!*cts) {
+ *cts = bpf_ktime_get_ns();
+ return 0;
+ }
+
+ cur_ts = bpf_ktime_get_ns();
+ delta = cur_ts - *cts;
+ *cts = cur_ts;
+
+ /*
+ * When state doesn't equal to (u32)-1, the cpu will enter
+ * one idle state; for this case we need to record interval
+ * for the pstate.
+ *
+ * OPP2
+ * +---------------------+
+ * OPP1 | |
+ * ---------+ |
+ * | Idle state
+ * +---------------
+ *
+ * |<- pstate duration ->|
+ * ^ ^
+ * pts cur_ts
+ */
+ if (ctx->state != (u32)-1) {
+
+ /* record pstate after have first cpu_frequency event */
+ if (!*pts)
+ return 0;
+
+ delta = cur_ts - *pts;
+
+ pstate_idx = find_cpu_pstate_idx(*pstate);
+ if (pstate_idx >= MAX_PSTATE_ENTRIES)
+ return 0;
+
+ key = cpu * MAX_PSTATE_ENTRIES + pstate_idx;
+ val = bpf_map_lookup_elem(&pstate_duration, &key);
+ if (val)
+ __sync_fetch_and_add((long *)val, delta);
+
+ /*
+ * When state equal to (u32)-1, the cpu just exits from one
+ * specific idle state; for this case we need to record
+ * interval for the pstate.
+ *
+ * OPP2
+ * -----------+
+ * | OPP1
+ * | +-----------
+ * | Idle state |
+ * +---------------------+
+ *
+ * |<- cstate duration ->|
+ * ^ ^
+ * cts cur_ts
+ */
+ } else {
+
+ key = cpu * MAX_CSTATE_ENTRIES + prev_state;
+ val = bpf_map_lookup_elem(&cstate_duration, &key);
+ if (val)
+ __sync_fetch_and_add((long *)val, delta);
+ }
+
+ /* Update timestamp for pstate as new start time */
+ if (*pts)
+ *pts = cur_ts;
+
+ return 0;
+}
+
+SEC("tracepoint/power/cpu_frequency")
+int bpf_prog2(struct cpu_args *ctx)
+{
+ u64 *pts, *cstate, *pstate, prev_state, cur_ts, delta;
+ u32 key, cpu, pstate_idx;
+ u64 *val;
+
+ cpu = ctx->cpu_id;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME;
+ pts = bpf_map_lookup_elem(&my_map, &key);
+ if (!pts)
+ return 0;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX;
+ pstate = bpf_map_lookup_elem(&my_map, &key);
+ if (!pstate)
+ return 0;
+
+ key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX;
+ cstate = bpf_map_lookup_elem(&my_map, &key);
+ if (!cstate)
+ return 0;
+
+ prev_state = *pstate;
+ *pstate = ctx->state;
+
+ if (!*pts) {
+ *pts = bpf_ktime_get_ns();
+ return 0;
+ }
+
+ cur_ts = bpf_ktime_get_ns();
+ delta = cur_ts - *pts;
+ *pts = cur_ts;
+
+ /* When CPU is in idle, bail out to skip pstate statistics */
+ if (*cstate != (u32)(-1))
+ return 0;
+
+ /*
+ * The cpu changes to another different OPP (in below diagram
+ * change frequency from OPP3 to OPP1), need recording interval
+ * for previous frequency OPP3 and update timestamp as start
+ * time for new frequency OPP1.
+ *
+ * OPP3
+ * +---------------------+
+ * OPP2 | |
+ * ---------+ |
+ * | OPP1
+ * +---------------
+ *
+ * |<- pstate duration ->|
+ * ^ ^
+ * pts cur_ts
+ */
+ pstate_idx = find_cpu_pstate_idx(*pstate);
+ if (pstate_idx >= MAX_PSTATE_ENTRIES)
+ return 0;
+
+ key = cpu * MAX_PSTATE_ENTRIES + pstate_idx;
+ val = bpf_map_lookup_elem(&pstate_duration, &key);
+ if (val)
+ __sync_fetch_and_add((long *)val, delta);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;