Merge branch 'x86-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 AVX512 status update from Ingo Molnar:
 "This adds a new ABI that the main scheduler probably doesn't want to
  deal with but HPC job schedulers might want to use: the
  AVX512_elapsed_ms field in the new /proc/<pid>/arch_status task status
  file, which allows the user-space job scheduler to cluster such tasks,
  to avoid turbo frequency drops"

* 'x86-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  Documentation/filesystems/proc.txt: Add arch_status file
  x86/process: Add AVX-512 usage elapsed time to /proc/pid/arch_status
  proc: Add /proc/<pid>/arch_status

6 files changed, 107 insertions, 0 deletions

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
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fbabf59692ff..3b3acb7f1b07 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -220,6 +220,7 @@ 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 7b4c52aa929f..e5cb67d67c03 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>
@@ -1231,3 +1233,48 @@ 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 */
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 255f6754c70d..c40fca98f2b7 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)
@@ -3448,6 +3451,9 @@ 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)