Commit-ID: 0c608dad2a771c0a11b6d12148d1a8b975e015d4
Gitweb: https://git.kernel.org/tip/0c608dad2a771c0a11b6d12148d1a8b975e015d4
Author: Aubrey Li <aubrey.li@xxxxxxxxxxxxxxx>
AuthorDate: Thu, 6 Jun 2019 09:22:35 +0800
Committer: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CommitDate: Wed, 12 Jun 2019 11:42:13 +0200
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@xxxxxxxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: akpm@xxxxxxxxxxxxxxxxxxxx
Cc: peterz@xxxxxxxxxxxxx
Cc: hpa@xxxxxxxxx
Cc: ak@xxxxxxxxxxxxxxx
Cc: tim.c.chen@xxxxxxxxxxxxxxx
Cc: dave.hansen@xxxxxxxxx
Cc: arjan@xxxxxxxxxxxxxxx
Cc: adobriyan@xxxxxxxxx
Cc: aubrey.li@xxxxxxxxx
Cc: linux-api@xxxxxxxxxxxxxxx
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
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>
Cc: Alexey Dobriyan <adobriyan@xxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Linux API <linux-api@xxxxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20190606012236.9391-2-aubrey.li@xxxxxxxxxxxxxxx
---
arch/x86/Kconfig | 1 +
arch/x86/kernel/fpu/xstate.c | 47 ++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 48 insertions(+)
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 */
|