lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240918215846.1424282-4-bwicaksono@nvidia.com>
Date: Wed, 18 Sep 2024 21:58:46 +0000
From: Besar Wicaksono <bwicaksono@...dia.com>
To: <suzuki.poulose@....com>, <robin.murphy@....com>,
	<catalin.marinas@....com>, <will@...nel.org>, <mark.rutland@....com>
CC: <linux-arm-kernel@...ts.infradead.org>, <linux-kernel@...r.kernel.org>,
	<linux-tegra@...r.kernel.org>, <treding@...dia.com>, <jonathanh@...dia.com>,
	<vsethi@...dia.com>, <rwiley@...dia.com>, <rknight@...dia.com>, "Besar
 Wicaksono" <bwicaksono@...dia.com>
Subject: [PATCH 3/3] perf: arm_cspmu: nvidia: enable NVLINK-C2C port filtering

Enable NVLINK-C2C port filtering to distinguish traffic from
different GPUs connected to NVLINK-C2C.

Signed-off-by: Besar Wicaksono <bwicaksono@...dia.com>
---
 Documentation/admin-guide/perf/nvidia-pmu.rst | 32 +++++++++++++++++++
 drivers/perf/arm_cspmu/nvidia_cspmu.c         |  7 ++--
 2 files changed, 36 insertions(+), 3 deletions(-)

diff --git a/Documentation/admin-guide/perf/nvidia-pmu.rst b/Documentation/admin-guide/perf/nvidia-pmu.rst
index 2e0d47cfe7ea..6d1d3206b4ad 100644
--- a/Documentation/admin-guide/perf/nvidia-pmu.rst
+++ b/Documentation/admin-guide/perf/nvidia-pmu.rst
@@ -86,6 +86,22 @@ Example usage:
 
    perf stat -a -e nvidia_nvlink_c2c0_pmu_3/event=0x0/
 
+The NVLink-C2C has two ports that can be connected to one GPU (occupying both
+ports) or to two GPUs (one GPU per port). The user can use "port" bitmap
+parameter to select the port(s) to monitor. Each bit represents the port number,
+e.g. "port=0x1" corresponds to port 0 and "port=0x3" is for port 0 and 1. The
+PMU will monitor both ports by default if not specified.
+
+Example for port filtering:
+
+* Count event id 0x0 from the GPU connected with socket 0 on port 0::
+
+   perf stat -a -e nvidia_nvlink_c2c0_pmu_0/event=0x0,port=0x1/
+
+* Count event id 0x0 from the GPUs connected with socket 0 on port 0 and port 1::
+
+   perf stat -a -e nvidia_nvlink_c2c0_pmu_0/event=0x0,port=0x3/
+
 NVLink-C2C1 PMU
 -------------------
 
@@ -116,6 +132,22 @@ Example usage:
 
    perf stat -a -e nvidia_nvlink_c2c1_pmu_3/event=0x0/
 
+The NVLink-C2C has two ports that can be connected to one GPU (occupying both
+ports) or to two GPUs (one GPU per port). The user can use "port" bitmap
+parameter to select the port(s) to monitor. Each bit represents the port number,
+e.g. "port=0x1" corresponds to port 0 and "port=0x3" is for port 0 and 1. The
+PMU will monitor both ports by default if not specified.
+
+Example for port filtering:
+
+* Count event id 0x0 from the GPU connected with socket 0 on port 0::
+
+   perf stat -a -e nvidia_nvlink_c2c1_pmu_0/event=0x0,port=0x1/
+
+* Count event id 0x0 from the GPUs connected with socket 0 on port 0 and port 1::
+
+   perf stat -a -e nvidia_nvlink_c2c1_pmu_0/event=0x0,port=0x3/
+
 CNVLink PMU
 ---------------
 
diff --git a/drivers/perf/arm_cspmu/nvidia_cspmu.c b/drivers/perf/arm_cspmu/nvidia_cspmu.c
index d1cd9975e71a..cd51177347e5 100644
--- a/drivers/perf/arm_cspmu/nvidia_cspmu.c
+++ b/drivers/perf/arm_cspmu/nvidia_cspmu.c
@@ -149,6 +149,7 @@ static struct attribute *pcie_pmu_format_attrs[] = {
 
 static struct attribute *nvlink_c2c_pmu_format_attrs[] = {
 	ARM_CSPMU_FORMAT_EVENT_ATTR,
+	ARM_CSPMU_FORMAT_ATTR(port, "config1:0-1"),
 	NULL,
 };
 
@@ -193,7 +194,7 @@ static u32 nv_cspmu_event_filter(const struct perf_event *event)
 	const struct nv_cspmu_ctx *ctx =
 		to_nv_cspmu_ctx(to_arm_cspmu(event->pmu));
 
-	if (ctx->filter_mask == 0)
+	if (ctx->filter_mask == 0 || event->attr.config1 == 0)
 		return ctx->filter_default_val;
 
 	return event->attr.config1 & ctx->filter_mask;
@@ -229,7 +230,7 @@ static const struct nv_cspmu_match nv_cspmu_match[] = {
 	{
 	  .prodid = 0x104,
 	  .prodid_mask = NV_PRODID_MASK,
-	  .filter_mask = 0x0,
+	  .filter_mask = NV_NVL_C2C_FILTER_ID_MASK,
 	  .filter_default_val = NV_NVL_C2C_FILTER_ID_MASK,
 	  .name_pattern = "nvidia_nvlink_c2c1_pmu_%u",
 	  .name_fmt = NAME_FMT_SOCKET,
@@ -239,7 +240,7 @@ static const struct nv_cspmu_match nv_cspmu_match[] = {
 	{
 	  .prodid = 0x105,
 	  .prodid_mask = NV_PRODID_MASK,
-	  .filter_mask = 0x0,
+	  .filter_mask = NV_NVL_C2C_FILTER_ID_MASK,
 	  .filter_default_val = NV_NVL_C2C_FILTER_ID_MASK,
 	  .name_pattern = "nvidia_nvlink_c2c0_pmu_%u",
 	  .name_fmt = NAME_FMT_SOCKET,
-- 
2.34.1


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ