[PATCH v7 2/3] proc: add AVX-512 usage elapsed time to /proc/pid/status

[Aubrey Li]

AVX-512 components use could cause core turbo frequency drop. So
it's useful to expose AVX-512 usage elapsed time as a heuristic hint
for the user space job scheduler to cluster the AVX-512 using tasks
together.

Example:
$ cat /proc/pid/status | grep AVX512_elapsed_ms
AVX512_elapsed_ms:      1020

The number '1020' denotes 1020 millisecond elapsed since last time
context switch the off-CPU task using AVX-512 components, thus the
task could cause core frequency drop.

Or:
$ cat /proc/pid/status | grep AVX512_elapsed_ms
AVX512_elapsed_ms:      -1

The number '-1' indicates the task didn't use AVX-512 components
before thus unlikely has frequency drop issue.

User space tools may want to further check by:

$ perf stat --pid <pid> -e core_power.lvl2_turbo_license -- sleep 1

 Performance counter stats for process id '3558':

     3,251,565,961      core_power.lvl2_turbo_license

       1.004031387 seconds time elapsed

Non-zero counter value confirms that the task causes frequency drop.

Signed-off-by: Aubrey Li <aubrey.li@xxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx>
---
 arch/x86/kernel/fpu/xstate.c | 38 ++++++++++++++++++++++++++++++++++++
 fs/proc/array.c              |  5 +++++
 2 files changed, 43 insertions(+)

diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 87a57b7642d3..c361de2bfb28 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -7,6 +7,7 @@
 #include <linux/cpu.h>
 #include <linux/mman.h>
 #include <linux/pkeys.h>
+#include <linux/seq_file.h>
 
 #include <asm/fpu/api.h>
 #include <asm/fpu/internal.h>
@@ -1245,3 +1246,40 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
 
 	return 0;
 }
+
+/*
+ * Report the amount of time elapsed in millisecond since last AVX512
+ * use in the task.
+ */
+void avx512_state(struct seq_file *m, struct task_struct *task)
+{
+	unsigned long timestamp = task->thread.fpu.avx512_timestamp;
+	long delta;
+
+	if (!timestamp)
+		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 CPU specific thread state
+ */
+void arch_task_state(struct seq_file *m, struct task_struct *task)
+{
+	/*
+	 * Report AVX512 state if the processor and build option supported.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_AVX512F))
+		avx512_state(m, task);
+}
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 0ceb3b6b37e7..dd88c2219f08 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -392,6 +392,10 @@ static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm)
 	seq_putc(m, '\n');
 }
 
+void __weak arch_task_state(struct seq_file *m, struct task_struct *task)
+{
+}
+
 int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
 			struct pid *pid, struct task_struct *task)
 {
@@ -414,6 +418,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
 	task_cpus_allowed(m, task);
 	cpuset_task_status_allowed(m, task);
 	task_context_switch_counts(m, task);
+	arch_task_state(m, task);
 	return 0;
 }
 
-- 
2.17.1