linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Mathieu Poirier <mathieu.poirier@linaro.org>
To: gregkh@linuxfoundation.org
Cc: linux-arm-kernel@lists.infradead.org
Subject: [PATCH 05/45] coresight: perf: Don't set the truncated flag in snapshot mode
Date: Wed, 19 Jun 2019 11:29:09 -0600	[thread overview]
Message-ID: <20190619172949.4522-6-mathieu.poirier@linaro.org> (raw)
In-Reply-To: <20190619172949.4522-1-mathieu.poirier@linaro.org>

This patch avoids setting the truncated flag when operating in snapshot
mode since the trace buffer is expected to be truncated and discontinuous
from one snapshot to another.  Moreover when the truncated flag is set
the perf core stops enabling the event, waiting for user space to consume
the data.  In snapshot mode this is clearly not what we want since it
results in stale data.

Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Tested-by: Leo Yan <leo.yan@linaro.org>
---
 drivers/hwtracing/coresight/coresight-etb10.c   | 8 +++++++-
 drivers/hwtracing/coresight/coresight-tmc-etf.c | 8 +++++++-
 drivers/hwtracing/coresight/coresight-tmc-etr.c | 8 +++++++-
 3 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c
index 60e753b1768d..516d67cd7759 100644
--- a/drivers/hwtracing/coresight/coresight-etb10.c
+++ b/drivers/hwtracing/coresight/coresight-etb10.c
@@ -512,7 +512,13 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev,
 		lost = true;
 	}
 
-	if (lost)
+	/*
+	 * Don't set the TRUNCATED flag in snapshot mode because 1) the
+	 * captured buffer is expected to be truncated and 2) a full buffer
+	 * prevents the event from being re-enabled by the perf core,
+	 * resulting in stale data being send to user space.
+	 */
+	if (!buf->snapshot && lost)
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 
 	/* finally tell HW where we want to start reading from */
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c
index 31d41e2ad955..bd5f3b57eebd 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etf.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c
@@ -518,7 +518,13 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev,
 		lost = true;
 	}
 
-	if (lost)
+	/*
+	 * Don't set the TRUNCATED flag in snapshot mode because 1) the
+	 * captured buffer is expected to be truncated and 2) a full buffer
+	 * prevents the event from being re-enabled by the perf core,
+	 * resulting in stale data being send to user space.
+	 */
+	if (!buf->snapshot && lost)
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 
 	cur = buf->cur;
diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
index cc8401c76c39..1fc3db8045e1 100644
--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
+++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
@@ -1511,7 +1511,13 @@ tmc_update_etr_buffer(struct coresight_device *csdev,
 
 	lost |= etr_buf->full;
 out:
-	if (lost)
+	/*
+	 * Don't set the TRUNCATED flag in snapshot mode because 1) the
+	 * captured buffer is expected to be truncated and 2) a full buffer
+	 * prevents the event from being re-enabled by the perf core,
+	 * resulting in stale data being send to user space.
+	 */
+	if (!etr_perf->snapshot && lost)
 		perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
 	return size;
 }
-- 
2.17.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  parent reply	other threads:[~2019-06-19 17:31 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-19 17:29 [PATCH 00/45] coresight: next v5.2-rc5 Mathieu Poirier
2019-06-19 17:29 ` [PATCH 01/45] coresight: etb10: Properly set AUX buffer head in snapshot mode Mathieu Poirier
2019-06-19 18:28   ` Greg KH
2019-06-19 17:29 ` [PATCH 02/45] coresight: tmc-etr: " Mathieu Poirier
2019-06-19 17:29 ` [PATCH 03/45] coresight: tmc-etf: " Mathieu Poirier
2019-06-19 17:29 ` [PATCH 04/45] coresight: tmc-etf: Fix snapshot mode update function Mathieu Poirier
2019-06-19 17:29 ` Mathieu Poirier [this message]
2019-06-19 17:29 ` [PATCH 06/45] coresight: funnel: Clean up device book keeping Mathieu Poirier
2019-06-19 17:29 ` [PATCH 07/45] coresight: replicator: Cleanup device tracking Mathieu Poirier
2019-06-19 17:29 ` [PATCH 08/45] coresight: tmc: Clean up device specific data Mathieu Poirier
2019-06-19 17:29 ` [PATCH 09/45] coresight: catu: Cleanup " Mathieu Poirier
2019-06-19 17:29 ` [PATCH 10/45] coresight: tpiu: Clean up " Mathieu Poirier
2019-06-19 17:29 ` [PATCH 11/45] coresight: stm: Cleanup " Mathieu Poirier
2019-06-19 17:29 ` [PATCH 12/45] coresight: etm: Clean up " Mathieu Poirier
2019-06-19 17:29 ` [PATCH 13/45] coresight: etb10: " Mathieu Poirier
2019-06-19 17:29 ` [PATCH 14/45] coresight: Use coresight device names for sinks in PMU attribute Mathieu Poirier
2019-06-19 17:29 ` [PATCH 15/45] coresight: Rename of_coresight to coresight-platform Mathieu Poirier
2019-06-19 17:29 ` [PATCH 16/45] coresight: etm3x: Rearrange cp14 access detection Mathieu Poirier
2019-06-19 17:29 ` [PATCH 17/45] coresight: stm: Rearrange probing the stimulus area Mathieu Poirier
2019-06-19 17:29 ` [PATCH 18/45] coresight: tmc-etr: Rearrange probing default buffer size Mathieu Poirier
2019-06-19 17:29 ` [PATCH 19/45] coresight: platform: Make memory allocation helper generic Mathieu Poirier
2019-06-19 18:31   ` Greg KH
2019-06-19 19:09     ` Mathieu Poirier
2019-06-20  5:35       ` Greg KH
2019-06-19 20:00     ` Mathieu Poirier
2019-06-19 17:29 ` [PATCH 20/45] coresight: Make sure device uses DT for obsolete compatible check Mathieu Poirier
2019-06-19 17:29 ` [PATCH 21/45] coresight: Introduce generic platform data helper Mathieu Poirier
2019-06-19 17:29 ` [PATCH 22/45] coresight: Make device to CPU mapping generic Mathieu Poirier
2019-06-19 17:29 ` [PATCH 23/45] coresight: Remove cpu field from platform data Mathieu Poirier
2019-06-19 17:29 ` [PATCH 24/45] coresight: Remove name from platform description Mathieu Poirier
2019-06-19 17:29 ` [PATCH 25/45] coresight: Cleanup coresight_remove_conns Mathieu Poirier
2019-06-19 17:29 ` [PATCH 26/45] coresight: Reuse platform data structure for connection tracking Mathieu Poirier
2019-06-19 17:29 ` [PATCH 27/45] coresight: Rearrange platform data probing Mathieu Poirier
2019-06-19 17:29 ` [PATCH 28/45] coresight: Add support for releasing platform specific data Mathieu Poirier
2019-06-19 17:29 ` [PATCH 29/45] coresight: platform: Use fwnode handle for device search Mathieu Poirier
2019-06-19 17:29 ` [PATCH 30/45] coresight: Use fwnode handle instead of device names Mathieu Poirier
2019-06-19 17:29 ` [PATCH 31/45] coresight: Use platform agnostic names Mathieu Poirier
2019-06-19 17:29 ` [PATCH 32/45] coresight: stm: ACPI support for parsing stimulus base Mathieu Poirier
2019-06-19 17:29 ` [PATCH 33/45] coresight: Support for ACPI bindings Mathieu Poirier
2019-06-19 17:29 ` [PATCH 34/45] coresight: acpi: Support for AMBA components Mathieu Poirier
2019-06-19 17:29 ` [PATCH 35/45] coresight: acpi: Support for platform devices Mathieu Poirier
2019-06-19 17:29 ` [PATCH 36/45] coresight: Add dummy definition for of_coresight_get_cpu() Mathieu Poirier
2019-06-19 17:29 ` [PATCH 37/45] coresight: tmc-etr: Do not call smp_processor_id() from preemptible Mathieu Poirier
2019-06-19 17:29 ` [PATCH 38/45] coresight: tmc-etr: alloc_perf_buf: Do not call smp_processor_id " Mathieu Poirier
2019-06-19 17:29 ` [PATCH 39/45] coresight: tmc-etf: " Mathieu Poirier
2019-06-19 17:29 ` [PATCH 40/45] coresight: etb10: " Mathieu Poirier
2019-06-19 17:29 ` [PATCH 41/45] coresight: Potential uninitialized variable in probe() Mathieu Poirier
2019-06-19 17:29 ` [PATCH 42/45] coresight: etm3x: Smatch: Fix potential NULL pointer dereference Mathieu Poirier
2019-06-19 17:29 ` [PATCH 43/45] coresight: tmc: " Mathieu Poirier
2019-06-19 17:29 ` [PATCH 44/45] coresight: platform: add OF/APCI dependency Mathieu Poirier
2019-06-19 17:29 ` [PATCH 45/45] coresight: replicator: Add terminate entry for acpi_device_id tables Mathieu Poirier
2019-06-19 18:26   ` Greg KH

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=20190619172949.4522-6-mathieu.poirier@linaro.org \
    --to=mathieu.poirier@linaro.org \
    --cc=gregkh@linuxfoundation.org \
    --cc=linux-arm-kernel@lists.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).