x86/process: Add AVX-512 usage elapsed time to /proc/pid/arch_status

AVX-512 components usage can result in turbo frequency drop. So it's useful
to expose AVX-512 usage elapsed time as a heuristic hint for user space job
schedulers to cluster the AVX-512 using tasks together.

Examples:
$ while [ 1 ]; do cat /proc/tid/arch_status | grep AVX512; sleep 1; done
AVX512_elapsed_ms:      4
AVX512_elapsed_ms:      8
AVX512_elapsed_ms:      4

This means that 4 milliseconds have elapsed since the tsks AVX512 usage was
detected when the task was scheduled out.

$ cat /proc/tid/arch_status | grep AVX512
AVX512_elapsed_ms:      -1

'-1' indicates that no AVX512 usage was recorded for this task.

The time exposed is not necessarily accurate when the arch_status file is
read as the AVX512 usage is only evaluated when a task is scheduled
out. Accurate usage information can be obtained with performance counters.

[ tglx: Massaged changelog ]

Signed-off-by: Aubrey Li <aubrey.li@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: akpm@linux-foundation.org
Cc: peterz@infradead.org
Cc: hpa@zytor.com
Cc: ak@linux.intel.com
Cc: tim.c.chen@linux.intel.com
Cc: dave.hansen@intel.com
Cc: arjan@linux.intel.com
Cc: adobriyan@gmail.com
Cc: aubrey.li@intel.com
Cc: linux-api@vger.kernel.org
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linux API <linux-api@vger.kernel.org>
Link: https://lkml.kernel.org/r/20190606012236.9391-2-aubrey.li@linux.intel.com

2 files changed, 48 insertions, 0 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2bbbd4d1ba31..8a49b4b03f6b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -217,6 +217,7 @@ config X86
 	select USER_STACKTRACE_SUPPORT
 	select VIRT_TO_BUS
 	select X86_FEATURE_NAMES		if PROC_FS
+	select PROC_PID_ARCH_STATUS		if PROC_FS
 
 config INSTRUCTION_DECODER
 	def_bool y
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 3c36dd1784db..591ddde3b3e8 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -8,6 +8,8 @@
 #include <linux/cpu.h>
 #include <linux/mman.h>
 #include <linux/pkeys.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
 
 #include <asm/fpu/api.h>
 #include <asm/fpu/internal.h>
@@ -1240,3 +1242,48 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
 
 	return 0;
 }
+
+#ifdef CONFIG_PROC_PID_ARCH_STATUS
+/*
+ * Report the amount of time elapsed in millisecond since last AVX512
+ * use in the task.
+ */
+static void avx512_status(struct seq_file *m, struct task_struct *task)
+{
+	unsigned long timestamp = READ_ONCE(task->thread.fpu.avx512_timestamp);
+	long delta;
+
+	if (!timestamp) {
+		/*
+		 * Report -1 if no AVX512 usage
+		 */
+		delta = -1;
+	} else {
+		delta = (long)(jiffies - timestamp);
+		/*
+		 * Cap to LONG_MAX if time difference > LONG_MAX
+		 */
+		if (delta < 0)
+			delta = LONG_MAX;
+		delta = jiffies_to_msecs(delta);
+	}
+
+	seq_put_decimal_ll(m, "AVX512_elapsed_ms:\t", delta);
+	seq_putc(m, '\n');
+}
+
+/*
+ * Report architecture specific information
+ */
+int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns,
+			struct pid *pid, struct task_struct *task)
+{
+	/*
+	 * Report AVX512 state if the processor and build option supported.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_AVX512F))
+		avx512_status(m, task);
+
+	return 0;
+}
+#endif /* CONFIG_PROC_PID_ARCH_STATUS */