[PATCH v2 1/8] ARC: perf: support RAW events

From: Alexey Brodkin
Date: Wed Aug 05 2015 - 11:14:09 EST


To run perf against raw event user may issue following command:
-------------->-------------
# perf stat -e r6372756e ls -la /proc > /dev/null

Performance counter stats for 'ls -la /proc':

7336905 r6372756e

0.085494733 seconds time elapsed
-------------->-------------

"-e rXXX" is indication of raw event to count.
XXX is 64-bit ASCII value.
0x6372756e = crun (in ASCII)

Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Signed-off-by: Alexey Brodkin <abrodkin@xxxxxxxxxxxx>
---

Compared to v1:
[1] Swapping of event names moved to probe routine so now we're closer to
real raw event in terms of accepting exactly what user entered.
[2] Added comment in sources that explains logic for swapping etc.
[3] Cosmetics

arch/arc/include/asm/perf_event.h | 3 ++
arch/arc/kernel/perf_event.c | 78 +++++++++++++++++++++++++++++++++------
2 files changed, 69 insertions(+), 12 deletions(-)

diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 2b8880e..ea43477 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -15,6 +15,9 @@
/* real maximum varies per CPU, this is the maximum supported by the driver */
#define ARC_PMU_MAX_HWEVENTS 64

+/* Max number of countable events that CPU may have */
+#define ARC_PERF_MAX_EVENTS 256
+
#define ARC_REG_CC_BUILD 0xF6
#define ARC_REG_CC_INDEX 0x240
#define ARC_REG_CC_NAME0 0x241
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 1287388..ae4a921 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -22,8 +22,10 @@ struct arc_pmu {
struct pmu pmu;
int counter_size; /* in bits */
int n_counters;
+ int n_events;
unsigned long used_mask[BITS_TO_LONGS(ARC_PMU_MAX_HWEVENTS)];
int ev_hw_idx[PERF_COUNT_ARC_HW_MAX];
+ u64 raw_events[ARC_PERF_MAX_EVENTS];
};

struct arc_callchain_trace {
@@ -136,6 +138,18 @@ static int arc_pmu_cache_event(u64 config)
return ret;
}

+static int arc_pmu_raw_event(u64 config)
+{
+ int i;
+
+ for (i = 0; i < arc_pmu->n_events; i++) {
+ if (config == arc_pmu->raw_events[i])
+ return i;
+ }
+
+ return -ENOENT;
+}
+
/* initializes hw_perf_event structure if event is supported */
static int arc_pmu_event_init(struct perf_event *event)
{
@@ -159,6 +173,14 @@ static int arc_pmu_event_init(struct perf_event *event)
return ret;
hwc->config = arc_pmu->ev_hw_idx[ret];
return 0;
+
+ case PERF_TYPE_RAW:
+ ret = arc_pmu_raw_event(event->attr.config);
+ if (ret < 0)
+ return ret;
+ hwc->config |= ret;
+ return 0;
+
default:
return -ENOENT;
}
@@ -270,15 +292,15 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
struct arc_reg_cc_build cc_bcr;
int i, j;

- union cc_name {
- struct {
- uint32_t word0, word1;
- char sentinel;
- } indiv;
- char str[9];
+ struct cc_name {
+ union {
+ uint32_t word[2];
+ u64 dword;
+ char str[8];
+ } u;
+ char sentinel[8];
} cc_name;

-
READ_BCR(ARC_REG_PCT_BUILD, pct_bcr);
if (!pct_bcr.v) {
pr_err("This core does not have performance counters!\n");
@@ -288,6 +310,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)

READ_BCR(ARC_REG_CC_BUILD, cc_bcr);
BUG_ON(!cc_bcr.v); /* Counters exist but No countable conditions ? */
+ BUG_ON(cc_bcr.c > ARC_PERF_MAX_EVENTS);

arc_pmu = devm_kzalloc(&pdev->dev, sizeof(struct arc_pmu), GFP_KERNEL);
if (!arc_pmu)
@@ -299,23 +322,54 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
pr_info("ARC perf\t: %d counters (%d bits), %d countable conditions\n",
arc_pmu->n_counters, arc_pmu->counter_size, cc_bcr.c);

- cc_name.str[8] = 0;
+ arc_pmu->n_events = cc_bcr.c;
+
for (i = 0; i < PERF_COUNT_ARC_HW_MAX; i++)
arc_pmu->ev_hw_idx[i] = -1;

+ cc_name.sentinel[0] = '\0';
+
/* loop thru all available h/w condition indexes */
for (j = 0; j < cc_bcr.c; j++) {
+ u64 name;
+
write_aux_reg(ARC_REG_CC_INDEX, j);
- cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0);
- cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1);
+ cc_name.u.word[0] = read_aux_reg(ARC_REG_CC_NAME0);
+ cc_name.u.word[1] = read_aux_reg(ARC_REG_CC_NAME1);
+
+ /*
+ * condition name caching for raw events
+ *
+ * In PCT register CC_NAME{0,1} event name string[] is saved
+ * from LSB side:
+ * e.g. cycles corresponds to "crun" and is saved as 0x6e757263
+ * n u r c
+ * However in perf cmdline they are specified in human order as
+ * r6372756e
+ *
+ * Thus save a 64bit swapped value for quick cross check at the
+ * time of raw event request, which will give in example above:
+ * __swab64(0x000000006e757263) = 0x6372756e00000000.
+ * And then to finally have 0x6372756e, trim the trailing zeroes
+ */
+ name = __swab64(cc_name.u.dword);
+
+ /* Trim leading zeroes */
+ for (i = 0; i < sizeof(u64); i++)
+ if (!(name & 0xFF))
+ name = name >> 8;
+ else
+ break;
+
+ arc_pmu->raw_events[j] = name;

/* See if it has been mapped to a perf event_id */
for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {
if (arc_pmu_ev_hw_map[i] &&
- !strcmp(arc_pmu_ev_hw_map[i], cc_name.str) &&
+ !strcmp(arc_pmu_ev_hw_map[i], cc_name.u.str) &&
strlen(arc_pmu_ev_hw_map[i])) {
pr_debug("mapping perf event %2d to h/w event \'%8s\' (idx %d)\n",
- i, cc_name.str, j);
+ i, cc_name.u.str, j);
arc_pmu->ev_hw_idx[i] = j;
}
}
--
2.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/