Skip to contentSkip to conversation

/proc/pid/status: Add support for architecture specific output

PATCH Superseded Aubrey Li 2 participants 11 messages Apr 10, 2019 – Apr 12, 2019

Subsystems (4)

v14 of 16 Superseded Latest is v16 →

lore
Share & tools
lore

Aubrey Li

author
#0 lore raw

PATCH v14 1/3 /proc/pid/status: Add support for architecture specific output

The architecture specific information of the running processes could be useful to the userland. Add support to examine process architecture specific information externally.

Cc Peter Zijlstra <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Tim Chen <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Arjan van de Ven <[email protected]>
Cc Linux API <[email protected]>
Cc Alexey Dobriyan <[email protected]>
Cc Andrew Morton <[email protected]>
---
 fs/proc/array.c         | 5 +++++
 include/linux/proc_fs.h | 2 ++
 2 files changed, 7 insertions(+)
fs/proc/array.c +5 -0
index 2edbb657f859..331592a61718 100644
@@ -401,6 +401,10 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
 	seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+void __weak arch_proc_pid_status(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)
 {
@@ -424,6 +428,7 @@ 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_proc_pid_status(m, task);
 	return 0;
 }
 
include/linux/proc_fs.h +2 -0
index 52a283ba0465..bf4328cb58ed 100644
@@ -74,6 +74,8 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
 						    proc_write_t write,
 						    void *data);
 extern struct pid *tgid_pidfd_to_pid(const struct file *file);
+/* Add support for architecture specific output in /proc/pid/status */
+void arch_proc_pid_status(struct seq_file *m, struct task_struct *task);
 
 #else /* CONFIG_PROC_FS */
 
Signature · 1 line
2.21.0
author
#1 lore raw

PATCH v14 2/3 x86,/proc/pid/status: Add AVX-512 usage elapsed time

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.

Tensorflow example:

$ while [ 1 ]; do cat /proc/tid/status | grep AVX; sleep 1; done
AVX512_elapsed_ms:      4
AVX512_elapsed_ms:      8
AVX512_elapsed_ms:      4

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

Or:

$ cat /proc/tid/status | grep AVX512_elapsed_ms
AVX512_elapsed_ms:      -1

The number '-1' indicates that no AVX512 usage recorded before thus the task 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.

Cc Peter Zijlstra <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Tim Chen <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Arjan van de Ven <[email protected]>
Cc Linux API <[email protected]>
Cc Alexey Dobriyan <[email protected]>
Cc Andrew Morton <[email protected]>
---
 arch/x86/kernel/fpu/xstate.c | 42 ++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)
arch/x86/kernel/fpu/xstate.c +42 -0
index d7432c2b1051..5e55ed9584ab 100644
@@ -7,6 +7,8 @@
 #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>
@@ -1243,3 +1245,43 @@ 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.
+ */
+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
+ */
+void arch_proc_pid_status(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_status(m, task);
+}
Signature · 1 line
2.21.0
author
#2 lore raw

PATCH v14 3/3 Documentation/filesystems/proc.txt: add AVX512_elapsed_ms

In reply to Aubrey Li

Added AVX512_elapsed_ms in /proc/<pid>/status. Report it in Documentation/filesystems/proc.txt

Cc Peter Zijlstra <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Tim Chen <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Arjan van de Ven <[email protected]>
Cc Linux API <[email protected]>
Cc Alexey Dobriyan <[email protected]>
Cc Andrew Morton <[email protected]>
---
 Documentation/filesystems/proc.txt | 29 ++++++++++++++++++++++++++++-
 1 file changed, 28 insertions(+), 1 deletion(-)
Documentation/filesystems/proc.txt +28 -1
index 66cad5c86171..c4a9e48681ad 100644
@@ -207,6 +207,7 @@ read the file /proc/PID/status:
   Speculation_Store_Bypass:       thread vulnerable
   voluntary_ctxt_switches:        0
   nonvoluntary_ctxt_switches:     1
+  AVX512_elapsed_ms:	8
 
 This shows you nearly the same information you would get if you viewed it with
 the ps  command.  In  fact,  ps  uses  the  proc  file  system  to  obtain its
@@ -224,7 +225,7 @@ asynchronous manner and the value may not be very precise. To see a precise
 snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
 It's slow but very precise.
 
-Table 1-2: Contents of the status files (as of 4.19)
+Table 1-2: Contents of the status files (as of 5.1)
 ..............................................................................
  Field                       Content
  Name                        filename of the executable
@@ -289,6 +290,32 @@ Table 1-2: Contents of the status files (as of 4.19)
  Mems_allowed_list           Same as previous, but in "list format"
  voluntary_ctxt_switches     number of voluntary context switches
  nonvoluntary_ctxt_switches  number of non voluntary context switches
+ AVX512_elapsed_ms           time elapsed since last AVX512 usage recorded
+
+ 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.
+
+  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.
+
 ..............................................................................
 
 Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
Signature · 1 line
2.21.0
#3 lore raw
In reply to Aubrey Li
Quoted 24 lines · Aubrey Li

The architecture specific information of the running processes could be useful to the userland. Add support to examine process architecture specific information externally.

Cc Peter Zijlstra <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Tim Chen <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Arjan van de Ven <[email protected]>
Cc Linux API <[email protected]>
Cc Alexey Dobriyan <[email protected]>
Cc Andrew Morton <[email protected]>
---
 fs/proc/array.c         | 5 +++++
 include/linux/proc_fs.h | 2 ++
 2 files changed, 7 insertions(+)
fs/proc/array.c +0 -0
index 2edbb657f859..331592a61718 100644

fs/proc/array.c static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm) · line 406

Quoted 6 lines
fs/proc/array.c +3 -0
@@ -401,6 +401,10 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
        seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+void __weak arch_proc_pid_status(struct seq_file *m, struct task_struct *task)
+{
+}

This pointlessly bloats other architectures. Do this instead in an appropriate header:

#ifndef arch_proc_pid_status
static inline void arch_proc_pid_status(...)
{
}
#endif

Or add /proc/PID/x86_status, which sounds better in most respects to me.

author
#4 lore raw
Quoted 35 lines · Andy Lutomirski
Quoted 24 lines · Aubrey Li

The architecture specific information of the running processes could be useful to the userland. Add support to examine process architecture specific information externally.

Cc Peter Zijlstra <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Tim Chen <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Arjan van de Ven <[email protected]>
Cc Linux API <[email protected]>
Cc Alexey Dobriyan <[email protected]>
Cc Andrew Morton <[email protected]>
---
 fs/proc/array.c         | 5 +++++
 include/linux/proc_fs.h | 2 ++
 2 files changed, 7 insertions(+)
fs/proc/array.c +0 -0
index 2edbb657f859..331592a61718 100644

fs/proc/array.c static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm) · line 406

Quoted 6 lines
fs/proc/array.c +3 -0
@@ -401,6 +401,10 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
        seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+void __weak arch_proc_pid_status(struct seq_file *m, struct task_struct *task)
+{
+}

This pointlessly bloats other architectures. Do this instead in an appropriate header:

Quoted 6 lines

#ifndef arch_proc_pid_status
static inline void arch_proc_pid_status(...)
{
}
#endif

I saw a bunch of similar weak functions, is it not acceptable?

fs/proc$ grep weak *.c
cpuinfo.c:__weak void arch_freq_prepare_all(void)
meminfo.c:void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) vmcore.c:int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) vmcore.c:void __weak elfcorehdr_free(unsigned long long addr) vmcore.c:ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) vmcore.c:ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) vmcore.c:int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, vmcore.c:ssize_t __weak

Quoted 2 lines

Or add /proc/PID/x86_status, which sounds better in most respects to me.

I didn't figure out how to make /proc/PID/x86_status invisible to other architectures in an appropriate way, do you have any suggestions?

Thanks,
-Aubrey

#5 lore raw
Quoted 46 lines · Aubrey
Quoted 35 lines · Andy Lutomirski
Quoted 24 lines · Aubrey Li

The architecture specific information of the running processes could be useful to the userland. Add support to examine process architecture specific information externally.

Cc Peter Zijlstra <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Tim Chen <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Arjan van de Ven <[email protected]>
Cc Linux API <[email protected]>
Cc Alexey Dobriyan <[email protected]>
Cc Andrew Morton <[email protected]>
---
 fs/proc/array.c         | 5 +++++
 include/linux/proc_fs.h | 2 ++
 2 files changed, 7 insertions(+)
fs/proc/array.c +0 -0
index 2edbb657f859..331592a61718 100644

fs/proc/array.c static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm) · line 406

Quoted 6 lines
fs/proc/array.c +3 -0
@@ -401,6 +401,10 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
        seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+void __weak arch_proc_pid_status(struct seq_file *m, struct task_struct *task)
+{
+}

This pointlessly bloats other architectures. Do this instead in an appropriate header:

Quoted 6 lines

#ifndef arch_proc_pid_status
static inline void arch_proc_pid_status(...)
{
}
#endif

I saw a bunch of similar weak functions, is it not acceptable?

Quoted 9 lines

fs/proc$ grep weak *.c
cpuinfo.c:__weak void arch_freq_prepare_all(void)
meminfo.c:void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) vmcore.c:int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) vmcore.c:void __weak elfcorehdr_free(unsigned long long addr) vmcore.c:ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) vmcore.c:ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) vmcore.c:int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, vmcore.c:ssize_t __weak

I think they're acceptable, but I don't personally like them.

Quoted 6 lines
Quoted 3 lines

Or add /proc/PID/x86_status, which sounds better in most respects to me.

I didn't figure out how to make /proc/PID/x86_status invisible to other architectures in an appropriate way, do you have any suggestions?

#ifdef CONFIG_X86?

author
#6 lore raw
Quoted 57 lines · Andy Lutomirski
Quoted 46 lines · Aubrey
Quoted 35 lines · Andy Lutomirski
Quoted 24 lines · Aubrey Li

The architecture specific information of the running processes could be useful to the userland. Add support to examine process architecture specific information externally.

Cc Peter Zijlstra <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Tim Chen <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Arjan van de Ven <[email protected]>
Cc Linux API <[email protected]>
Cc Alexey Dobriyan <[email protected]>
Cc Andrew Morton <[email protected]>
---
 fs/proc/array.c         | 5 +++++
 include/linux/proc_fs.h | 2 ++
 2 files changed, 7 insertions(+)
fs/proc/array.c +0 -0
index 2edbb657f859..331592a61718 100644

fs/proc/array.c static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm) · line 406

Quoted 6 lines
fs/proc/array.c +3 -0
@@ -401,6 +401,10 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
        seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+void __weak arch_proc_pid_status(struct seq_file *m, struct task_struct *task)
+{
+}

This pointlessly bloats other architectures. Do this instead in an appropriate header:

Quoted 6 lines

#ifndef arch_proc_pid_status
static inline void arch_proc_pid_status(...)
{
}
#endif

I saw a bunch of similar weak functions, is it not acceptable?

Quoted 9 lines

fs/proc$ grep weak *.c
cpuinfo.c:__weak void arch_freq_prepare_all(void)
meminfo.c:void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) vmcore.c:int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) vmcore.c:void __weak elfcorehdr_free(unsigned long long addr) vmcore.c:ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) vmcore.c:ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) vmcore.c:int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, vmcore.c:ssize_t __weak

Quoted 2 lines

I think they're acceptable, but I don't personally like them.

okay, let me try to see if I can refine it in an appropriate way.

Quoted 9 lines
Quoted 6 lines
Quoted 3 lines

Or add /proc/PID/x86_status, which sounds better in most respects to me.

I didn't figure out how to make /proc/PID/x86_status invisible to other architectures in an appropriate way, do you have any suggestions?

#ifdef CONFIG_X86?

I'm not sure if everyone like adding an arch #ifdef in a common file, please allow me to wait a while to see if there are other comments.

Thanks,
-Aubrey

author
#7 lore raw
Quoted 58 lines · Aubrey
Quoted 57 lines · Andy Lutomirski
Quoted 55 lines · Aubrey
Quoted 35 lines · Andy Lutomirski
Quoted 24 lines · Aubrey Li

The architecture specific information of the running processes could be useful to the userland. Add support to examine process architecture specific information externally.

Cc Peter Zijlstra <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Tim Chen <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Arjan van de Ven <[email protected]>
Cc Linux API <[email protected]>
Cc Alexey Dobriyan <[email protected]>
Cc Andrew Morton <[email protected]>
---
 fs/proc/array.c         | 5 +++++
 include/linux/proc_fs.h | 2 ++
 2 files changed, 7 insertions(+)
fs/proc/array.c +0 -0
index 2edbb657f859..331592a61718 100644

fs/proc/array.c static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm) · line 406

Quoted 6 lines
fs/proc/array.c +3 -0
@@ -401,6 +401,10 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
        seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+void __weak arch_proc_pid_status(struct seq_file *m, struct task_struct *task)
+{
+}

This pointlessly bloats other architectures. Do this instead in an appropriate header:

Quoted 6 lines

#ifndef arch_proc_pid_status
static inline void arch_proc_pid_status(...)
{
}
#endif

I saw a bunch of similar weak functions, is it not acceptable?

fs/proc$ grep weak *.c
cpuinfo.c:__weak void arch_freq_prepare_all(void)
meminfo.c:void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) vmcore.c:int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) vmcore.c:void __weak elfcorehdr_free(unsigned long long addr) vmcore.c:ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) vmcore.c:ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) vmcore.c:int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, vmcore.c:ssize_t __weak

Quoted 4 lines
Quoted 2 lines

I think they're acceptable, but I don't personally like them.

okay, let me try to see if I can refine it in an appropriate way.

Hi Andy,

Is this what you want?

Thanks,
-Aubrey

====================================================================

arch/x86/include/asm/processor.h +3 -0
index 2bb3a648fc12..82d77d3aefff 100644
@@ -990,5 +990,8 @@ enum l1tf_mitigations {
 };
 
 extern enum l1tf_mitigations l1tf_mitigation;
+/* Add support for architecture specific output in /proc/pid/status */
+void arch_proc_pid_status(struct seq_file *m, struct task_struct *task);
+#define arch_proc_pid_status arch_proc_pid_status
 
 #endif /* _ASM_X86_PROCESSOR_H */
fs/proc/array.c +6 -0
index 2edbb657f859..fd65a6ba2864 100644
@@ -401,6 +401,11 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
 	seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+/* Add support for architecture specific output in /proc/pid/status */
+#ifndef arch_proc_pid_status
+#define arch_proc_pid_status(m, task)
+#endif
+
 int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
 			struct pid *pid, struct task_struct *task)
 {
@@ -424,6 +429,7 @@ 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_proc_pid_status(m, task);
 	return 0;
 }
 
#8 lore raw
Quoted 103 lines · Aubrey
Quoted 58 lines · Aubrey
Quoted 57 lines · Andy Lutomirski
Quoted 55 lines · Aubrey
Quoted 35 lines · Andy Lutomirski
Quoted 24 lines · Aubrey Li

The architecture specific information of the running processes could be useful to the userland. Add support to examine process architecture specific information externally.

Cc Peter Zijlstra <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Tim Chen <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Arjan van de Ven <[email protected]>
Cc Linux API <[email protected]>
Cc Alexey Dobriyan <[email protected]>
Cc Andrew Morton <[email protected]>
---
 fs/proc/array.c         | 5 +++++
 include/linux/proc_fs.h | 2 ++
 2 files changed, 7 insertions(+)
fs/proc/array.c +0 -0
index 2edbb657f859..331592a61718 100644

fs/proc/array.c static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm) · line 406

Quoted 6 lines
fs/proc/array.c +3 -0
@@ -401,6 +401,10 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
        seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+void __weak arch_proc_pid_status(struct seq_file *m, struct task_struct *task)
+{
+}

This pointlessly bloats other architectures. Do this instead in an appropriate header:

Quoted 6 lines

#ifndef arch_proc_pid_status
static inline void arch_proc_pid_status(...)
{
}
#endif

I saw a bunch of similar weak functions, is it not acceptable?

fs/proc$ grep weak *.c
cpuinfo.c:__weak void arch_freq_prepare_all(void)
meminfo.c:void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) vmcore.c:int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) vmcore.c:void __weak elfcorehdr_free(unsigned long long addr) vmcore.c:ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) vmcore.c:ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) vmcore.c:int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, vmcore.c:ssize_t __weak

Quoted 4 lines
Quoted 2 lines

I think they're acceptable, but I don't personally like them.

okay, let me try to see if I can refine it in an appropriate way.

Hi Andy,

Is this what you want?

Thanks,
-Aubrey

====================================================================

arch/x86/include/asm/processor.h +3 -0
index 2bb3a648fc12..82d77d3aefff 100644
@@ -990,5 +990,8 @@ enum l1tf_mitigations {
 };
 
 extern enum l1tf_mitigations l1tf_mitigation;
+/* Add support for architecture specific output in /proc/pid/status */
+void arch_proc_pid_status(struct seq_file *m, struct task_struct *task);
+#define arch_proc_pid_status arch_proc_pid_status
 
 #endif /* _ASM_X86_PROCESSOR_H */
fs/proc/array.c +5 -0
index 2edbb657f859..fd65a6ba2864 100644
@@ -401,6 +401,11 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
        seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+/* Add support for architecture specific output in /proc/pid/status */
+#ifndef arch_proc_pid_status
+#define arch_proc_pid_status(m, task)
+#endif
+
 int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
                        struct pid *pid, struct task_struct *task)
 {

fs/proc/array.c int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, · line 435

Quoted 7 lines
fs/proc/array.c +1 -0
@@ -424,6 +429,7 @@ 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_proc_pid_status(m, task);
        return 0;
 }
 

Yes. But I still think it would be nicer to separate the arch stuff into its own file. Others might reasonably disagree with me.

author
#9 lore raw
Quoted 106 lines · Andy Lutomirski
Quoted 105 lines · Aubrey
Quoted 58 lines · Aubrey
Quoted 57 lines · Andy Lutomirski
Quoted 55 lines · Aubrey
Quoted 35 lines · Andy Lutomirski
Quoted 24 lines · Aubrey Li

The architecture specific information of the running processes could be useful to the userland. Add support to examine process architecture specific information externally.

Cc Peter Zijlstra <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Tim Chen <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Arjan van de Ven <[email protected]>
Cc Linux API <[email protected]>
Cc Alexey Dobriyan <[email protected]>
Cc Andrew Morton <[email protected]>
---
 fs/proc/array.c         | 5 +++++
 include/linux/proc_fs.h | 2 ++
 2 files changed, 7 insertions(+)
fs/proc/array.c +0 -0
index 2edbb657f859..331592a61718 100644

fs/proc/array.c static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm) · line 406

Quoted 6 lines
fs/proc/array.c +3 -0
@@ -401,6 +401,10 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
        seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+void __weak arch_proc_pid_status(struct seq_file *m, struct task_struct *task)
+{
+}

This pointlessly bloats other architectures. Do this instead in an appropriate header:

Quoted 6 lines

#ifndef arch_proc_pid_status
static inline void arch_proc_pid_status(...)
{
}
#endif

I saw a bunch of similar weak functions, is it not acceptable?

fs/proc$ grep weak *.c
cpuinfo.c:__weak void arch_freq_prepare_all(void)
meminfo.c:void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) vmcore.c:int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) vmcore.c:void __weak elfcorehdr_free(unsigned long long addr) vmcore.c:ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) vmcore.c:ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) vmcore.c:int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, vmcore.c:ssize_t __weak

Quoted 4 lines
Quoted 2 lines

I think they're acceptable, but I don't personally like them.

okay, let me try to see if I can refine it in an appropriate way.

Hi Andy,

Is this what you want?

Thanks,
-Aubrey

====================================================================

arch/x86/include/asm/processor.h +3 -0
index 2bb3a648fc12..82d77d3aefff 100644
@@ -990,5 +990,8 @@ enum l1tf_mitigations {
 };
 
 extern enum l1tf_mitigations l1tf_mitigation;
+/* Add support for architecture specific output in /proc/pid/status */
+void arch_proc_pid_status(struct seq_file *m, struct task_struct *task);
+#define arch_proc_pid_status arch_proc_pid_status
 
 #endif /* _ASM_X86_PROCESSOR_H */
fs/proc/array.c +5 -0
index 2edbb657f859..fd65a6ba2864 100644
@@ -401,6 +401,11 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
        seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+/* Add support for architecture specific output in /proc/pid/status */
+#ifndef arch_proc_pid_status
+#define arch_proc_pid_status(m, task)
+#endif
+
 int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
                        struct pid *pid, struct task_struct *task)
 {
@@ -424,6 +429,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
        task_cpus_allowed(m, task);
        cpuset_task_status_allowed(m, task);
Quoted 9 lines

fs/proc/array.c int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, · line 435

Quoted 5 lines
fs/proc/array.c +1 -0
        task_context_switch_counts(m, task);
+       arch_proc_pid_status(m, task);
        return 0;
 }
 

Yes. But I still think it would be nicer to separate the arch stuff into its own file. Others might reasonably disagree with me.

I like arch_status, I proposed but no other arch shows interesting in it.

I think the problem is similar for x86_status, it does not make sense for those x86 platform without AVX512 to have an empty arch file. I personally don't like [arch]_status because the code may become unclean if more arches added in future.

Maybe it's too early to have a separated arch staff file for now.

Thanks,
-Aubrey

author
#10 lore raw
Quoted 116 lines · Aubrey
Quoted 106 lines · Andy Lutomirski
Quoted 105 lines · Aubrey
Quoted 58 lines · Aubrey
Quoted 57 lines · Andy Lutomirski
Quoted 55 lines · Aubrey
Quoted 35 lines · Andy Lutomirski
Quoted 24 lines · Aubrey Li

The architecture specific information of the running processes could be useful to the userland. Add support to examine process architecture specific information externally.

Cc Peter Zijlstra <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Tim Chen <[email protected]>
Cc Dave Hansen <[email protected]>
Cc Arjan van de Ven <[email protected]>
Cc Linux API <[email protected]>
Cc Alexey Dobriyan <[email protected]>
Cc Andrew Morton <[email protected]>
---
 fs/proc/array.c         | 5 +++++
 include/linux/proc_fs.h | 2 ++
 2 files changed, 7 insertions(+)
fs/proc/array.c +0 -0
index 2edbb657f859..331592a61718 100644

fs/proc/array.c static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm) · line 406

Quoted 6 lines
fs/proc/array.c +3 -0
@@ -401,6 +401,10 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
        seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+void __weak arch_proc_pid_status(struct seq_file *m, struct task_struct *task)
+{
+}

This pointlessly bloats other architectures. Do this instead in an appropriate header:

Quoted 6 lines

#ifndef arch_proc_pid_status
static inline void arch_proc_pid_status(...)
{
}
#endif

I saw a bunch of similar weak functions, is it not acceptable?

fs/proc$ grep weak *.c
cpuinfo.c:__weak void arch_freq_prepare_all(void)
meminfo.c:void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) vmcore.c:int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size) vmcore.c:void __weak elfcorehdr_free(unsigned long long addr) vmcore.c:ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) vmcore.c:ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) vmcore.c:int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma, vmcore.c:ssize_t __weak

Quoted 4 lines
Quoted 2 lines

I think they're acceptable, but I don't personally like them.

okay, let me try to see if I can refine it in an appropriate way.

Hi Andy,

Is this what you want?

Thanks,
-Aubrey

====================================================================

arch/x86/include/asm/processor.h +3 -0
index 2bb3a648fc12..82d77d3aefff 100644
@@ -990,5 +990,8 @@ enum l1tf_mitigations {
 };
 
 extern enum l1tf_mitigations l1tf_mitigation;
+/* Add support for architecture specific output in /proc/pid/status */
+void arch_proc_pid_status(struct seq_file *m, struct task_struct *task);
+#define arch_proc_pid_status arch_proc_pid_status
 
 #endif /* _ASM_X86_PROCESSOR_H */
fs/proc/array.c +5 -0
index 2edbb657f859..fd65a6ba2864 100644
@@ -401,6 +401,11 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm)
        seq_printf(m, "THP_enabled:\t%d\n", thp_enabled);
 }
 
+/* Add support for architecture specific output in /proc/pid/status */
+#ifndef arch_proc_pid_status
+#define arch_proc_pid_status(m, task)
+#endif
+
 int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
                        struct pid *pid, struct task_struct *task)
 {
@@ -424,6 +429,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
        task_cpus_allowed(m, task);
        cpuset_task_status_allowed(m, task);
Quoted 9 lines

fs/proc/array.c int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, · line 435

Quoted 5 lines
fs/proc/array.c +1 -0
        task_context_switch_counts(m, task);
+       arch_proc_pid_status(m, task);
        return 0;
 }
 

Yes. But I still think it would be nicer to separate the arch stuff into its own file. Others might reasonably disagree with me.

Quoted 8 lines

I like arch_status, I proposed but no other arch shows interesting in it.

I think the problem is similar for x86_status, it does not make sense for those x86 platform without AVX512 to have an empty arch file. I personally don't like [arch]_status because the code may become unclean if more arches added in future.

Maybe it's too early to have a separated arch staff file for now.

Hi Andy,

Is it acceptable to you if I make the above change and post v15?

Thanks,
-Aubrey