From 68bc30bb9f33fc8d11e3d110d29e06490896a999 Mon Sep 17 00:00:00 2001
From: Aubrey Li <aubrey.li@linux.intel.com>
Date: Thu, 6 Jun 2019 09:22:34 +0800
Subject: [PATCH 1/3] proc: Add /proc/<pid>/arch_status
Exposing architecture specific per process information is useful for
various reasons. An example is the AVX512 usage on x86 which is important
for task placement for power/performance optimizations.
Adding this information to the existing /prcc/pid/status file would be the
obvious choise, but it has been agreed on that a explicit arch_status file
is better in separating the generic and architecture specific information.
[ tglx: Massage changelog ]
Signed-off-by: Aubrey Li <aubrey.li@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Andrew Morton <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: Linux API <linux-api@vger.kernel.org>
Link: https://lkml.kernel.org/r/20190606012236.9391-1-aubrey.li@linux.intel.com
---
fs/proc/Kconfig | 4 ++++
fs/proc/base.c | 6 ++++++
include/linux/proc_fs.h | 9 +++++++++
3 files changed, 19 insertions(+)
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index 62ee41b4bbd0..4c3dcb718961 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -98,3 +98,7 @@ config PROC_CHILDREN
Say Y if you are running any user-space software which takes benefit from
this interface. For example, rkt is such a piece of software.
+
+config PROC_PID_ARCH_STATUS
+ def_bool n
+ depends on PROC_FS
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9c8ca6cd3ce4..ec436c61eece 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3061,6 +3061,9 @@ static const struct pid_entry tgid_base_stuff[] = {
#ifdef CONFIG_STACKLEAK_METRICS
ONE("stack_depth", S_IRUGO, proc_stack_depth),
#endif
+#ifdef CONFIG_PROC_PID_ARCH_STATUS
+ ONE("arch_status", S_IRUGO, proc_pid_arch_status),
+#endif
};
static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
@@ -3449,6 +3452,9 @@ static const struct pid_entry tid_base_stuff[] = {
#ifdef CONFIG_LIVEPATCH
ONE("patch_state", S_IRUSR, proc_pid_patch_state),
#endif
+#ifdef CONFIG_PROC_PID_ARCH_STATUS
+ ONE("arch_status", S_IRUGO, proc_pid_arch_status),
+#endif
};
static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 52a283ba0465..a705aa2d03f9 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -75,6 +75,15 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
void *data);
extern struct pid *tgid_pidfd_to_pid(const struct file *file);
+#ifdef CONFIG_PROC_PID_ARCH_STATUS
+/*
+ * The architecture which selects CONFIG_PROC_PID_ARCH_STATUS must
+ * provide proc_pid_arch_status() definition.
+ */
+int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task);
+#endif /* CONFIG_PROC_PID_ARCH_STATUS */
+
#else /* CONFIG_PROC_FS */
static inline void proc_root_init(void)
From 0c608dad2a771c0a11b6d12148d1a8b975e015d4 Mon Sep 17 00:00:00 2001
From: Aubrey Li <aubrey.li@linux.intel.com>
Date: Thu, 6 Jun 2019 09:22:35 +0800
Subject: [PATCH 2/3] 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
---
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 */
From 711486fd18596315d42cebaac3dba8c408f60a3d Mon Sep 17 00:00:00 2001
From: Aubrey Li <aubrey.li@linux.intel.com>
Date: Thu, 6 Jun 2019 09:22:36 +0800
Subject: [PATCH 3/3] Documentation/filesystems/proc.txt: Add arch_status file
Add documentation for /proc/<pid>/arch_status file and the x86 specific
AVX512_elapsed_ms entry in it.
[ tglx: Massage 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/20190606012236.9391-3-aubrey.li@linux.intel.com
---
Documentation/filesystems/proc.txt | 40 ++++++++++++++++++++++++++++++
1 file changed, 40 insertions(+)
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 66cad5c86171..a226061fa109 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -45,6 +45,7 @@ Table of Contents
3.9 /proc/<pid>/map_files - Information about memory mapped files
3.10 /proc/<pid>/timerslack_ns - Task timerslack value
3.11 /proc/<pid>/patch_state - Livepatch patch operation state
+ 3.12 /proc/<pid>/arch_status - Task architecture specific information
4 Configuring procfs
4.1 Mount options
@@ -1948,6 +1949,45 @@ patched. If the patch is being enabled, then the task has already been
patched. If the patch is being disabled, then the task hasn't been
unpatched yet.
+3.12 /proc/<pid>/arch_status - task architecture specific status
+-------------------------------------------------------------------
+When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the
+architecture specific status of the task.
+
+Example
+-------
+ $ cat /proc/6753/arch_status
+ AVX512_elapsed_ms: 8
+
+Description
+-----------
+
+x86 specific entries:
+---------------------
+ AVX512_elapsed_ms:
+ ------------------
+ If AVX512 is supported on the machine, this entry shows the milliseconds
+ elapsed since the last time AVX512 usage was recorded. The recording
+ happens on a best effort basis when a task is scheduled out. This means
+ that the value depends on two factors:
+
+ 1) The time which the task spent on the CPU without being scheduled
+ out. With CPU isolation and a single runnable task this can take
+ several seconds.
+
+ 2) The time since the task was scheduled out last. Depending on the
+ reason for being scheduled out (time slice exhausted, syscall ...)
+ this can be arbitrary long time.
+
+ As a consequence the value cannot be considered precise and authoritative
+ information. The application which uses this information has to be aware
+ of the overall scenario on the system in order to determine whether a
+ task is a real AVX512 user or not. Precise information can be obtained
+ with performance counters.
+
+ A special value of '-1' indicates that no AVX512 usage was recorded, thus
+ the task is unlikely an AVX512 user, but depends on the workload and the
+ scheduling scenario, it also could be a false negative mentioned above.
------------------------------------------------------------------------------
Configuring procfs