linux-arch.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alexey Brodkin <Alexey.Brodkin@synopsys.com>
To: linux-arch@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, Vineet.Gupta1@synopsys.com,
	arc-linux-dev@synopsys.com, arnd@arndb.de, peterz@infradead.org,
	Alexey Brodkin <Alexey.Brodkin@synopsys.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>
Subject: [PATCH v2 1/8] ARC: perf: support RAW events
Date: Wed,  5 Aug 2015 18:13:27 +0300	[thread overview]
Message-ID: <1438787614-14074-2-git-send-email-abrodkin@synopsys.com> (raw)
In-Reply-To: <1438787614-14074-1-git-send-email-abrodkin@synopsys.com>

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@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
---

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

  reply	other threads:[~2015-08-05 15:14 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-08-05 15:13 [PATCH v2 0/8] ARCv2 port to Linux - (C) perf Alexey Brodkin
2015-08-05 15:13 ` Alexey Brodkin [this message]
2015-08-05 15:13 ` [PATCH v2 2/8] ARC: perf: cap the number of counters to hardware max of 32 Alexey Brodkin
2015-08-05 15:13   ` Alexey Brodkin
2015-08-05 15:13 ` [PATCH v2 3/8] ARCv2: perf: implement "event_set_period" for future use with interrupts Alexey Brodkin
2015-08-05 15:13   ` Alexey Brodkin
2015-08-18 17:52   ` Peter Zijlstra
2015-08-18 18:03     ` Alexey Brodkin
2015-08-20 10:46     ` Alexey Brodkin
2015-08-18 17:55   ` Peter Zijlstra
2015-08-20 11:25     ` Alexey Brodkin
2015-08-05 15:13 ` [PATCH v2 4/8] ARCv2: perf: Support sampling events using overflow interrupts Alexey Brodkin
2015-08-05 15:13   ` Alexey Brodkin
2015-08-18 22:12   ` Peter Zijlstra
2015-08-20 11:30     ` Alexey Brodkin
2015-08-05 15:13 ` [PATCH v2 5/8] ARCv2: perf: set usable max period as a half of real max period Alexey Brodkin
2015-08-05 15:13   ` Alexey Brodkin
2015-08-05 15:13 ` [PATCH v2 6/8] ARCv2: perf: implement exclusion of event counting in user or kernel mode Alexey Brodkin
2015-08-05 15:13   ` Alexey Brodkin
2015-08-18 23:37   ` Peter Zijlstra
2015-08-20 11:33     ` Alexey Brodkin
2015-08-05 15:13 ` [PATCH v2 7/8] ARCv2: perf: SMP support Alexey Brodkin
2015-08-05 15:13 ` [PATCH v2 8/8] ARCv2: perf: Finally introduce HS perf unit Alexey Brodkin
2015-08-05 15:13   ` Alexey Brodkin
2015-08-10  8:29 ` [PATCH v2 0/8] ARCv2 port to Linux - (C) perf Alexey Brodkin
2015-08-10  8:29   ` Alexey Brodkin
2015-08-14  7:41 ` [arc-linux-dev] " Vineet Gupta

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1438787614-14074-2-git-send-email-abrodkin@synopsys.com \
    --to=alexey.brodkin@synopsys.com \
    --cc=Vineet.Gupta1@synopsys.com \
    --cc=acme@kernel.org \
    --cc=arc-linux-dev@synopsys.com \
    --cc=arnd@arndb.de \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).