Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Reinette Chatre <reinette.chatre@intel.com>
To:     tglx@linutronix.de, fenghua.yu@intel.com, tony.luck@intel.com,
        peterz@infradead.org, mingo@redhat.com, acme@kernel.org
Cc:     gavin.hindman@intel.com, jithu.joseph@intel.com,
        dave.hansen@intel.com, hpa@zytor.com, x86@kernel.org,
        linux-kernel@vger.kernel.org,
        Reinette Chatre <reinette.chatre@intel.com>
Subject: [PATCH V4 4/6] x86/intel_rdt: Create required perf event attributes
Date:   Wed, 12 Sep 2018 12:54:28 -0700
Message-Id: <d4e0a1016e6f4bdcde062c992151ee12c64fd5c1.1536780425.git.reinette.chatre@intel.com>
In-Reply-To: <060c5fa0a1f227e6119841b3b617c3f0cc9d5da1.1536685533.git.reinette.chatre@intel.com>
References: <060c5fa0a1f227e6119841b3b617c3f0cc9d5da1.1536685533.git.reinette.chatre@intel.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

A perf event has many attributes that are maintained in a separate
structure that should be provided when a new perf_event is created.

In preparation for the transition to perf_events the required attribute
structures are created for all the events that may be used in the
measurements. Most attributes for all the events are identical. The
actual configuration, what specifies what needs to be measured, is what
will be different between the events used. This configuration needs to
be done with X86_CONFIG that cannot be used as part of the designated
initializers used here, this will be introduced later.

Although they do look identical at this time the attribute structures
needs to be maintained separately since a perf_event will maintain a
pointer to its unique attributes.

In support of patch testing the new structs are given the unused attribute
until their use in later patches.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
---
V4:
The kbuild test robot reported a build issue that at first seems to be
related to "make ARCH=i386" but was actually a result of the kernel
configuration used not having CONFIG_TRACEPOINTS set.
The consequence was that include/linux/perf_event.h was not being included
via the tracing code (from include/trace/define_trace.h) and we thus encounter
the build failure where struct perf_event_attr is unknown.
Fix this by explicitly including perf_event.h

 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 26 +++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 8ad83eb3fc89..33d7968f152a 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -17,6 +17,7 @@
 #include <linux/debugfs.h>
 #include <linux/kthread.h>
 #include <linux/mman.h>
+#include <linux/perf_event.h>
 #include <linux/pm_qos.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
@@ -915,6 +916,31 @@ static int measure_cycles_lat_fn(void *_plr)
 	return 0;
 }
 
+/*
+ * Create a perf_event_attr for the hit and miss perf events that will
+ * be used during the performance measurement. A perf_event maintains
+ * a pointer to its perf_event_attr so a unique attribute structure is
+ * created for each perf_event.
+ *
+ * The actual configuration of the event is set right before use in order
+ * to use the X86_CONFIG macro.
+ */
+static struct perf_event_attr __attribute__((unused)) perf_miss_attr = {
+	.type		= PERF_TYPE_RAW,
+	.size		= sizeof(struct perf_event_attr),
+	.pinned		= 1,
+	.disabled	= 0,
+	.exclude_user	= 1,
+};
+
+static struct perf_event_attr __attribute__((unused)) perf_hit_attr = {
+	.type		= PERF_TYPE_RAW,
+	.size		= sizeof(struct perf_event_attr),
+	.pinned		= 1,
+	.disabled	= 0,
+	.exclude_user	= 1,
+};
+
 static int measure_cycles_perf_fn(void *_plr)
 {
 	unsigned long long l3_hits = 0, l3_miss = 0;
-- 
2.17.0