fs/proc/task_mmu.c: add user-space support for resetting mm->hiwater_rss (peak RSS)

Peak resident size of a process can be reset back to the process's
current rss value by writing "5" to /proc/pid/clear_refs.  The driving
use-case for this would be getting the peak RSS value, which can be
retrieved from the VmHWM field in /proc/pid/status, per benchmark
iteration or test scenario.

[akpm@linux-foundation.org: clarify behaviour in documentation]
Signed-off-by: Petr Cermak <petrcermak@chromium.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Primiano Tucci <primiano@chromium.org>
Cc: Petr Cermak <petrcermak@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 23 insertions, 0 deletions

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index cf8fc2f0b34b..0b3448dba9ec 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -489,6 +489,10 @@ To clear the bits for the file mapped pages associated with the process
 To clear the soft-dirty bit
     > echo 4 > /proc/PID/clear_refs
 
+To reset the peak resident set size ("high water mark") to the process's
+current value:
+    > echo 5 > /proc/PID/clear_refs
+
 Any other value written to /proc/PID/clear_refs will have no effect.
 
 The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 0e36c1e49fe3..1359a911d194 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -732,6 +732,7 @@ enum clear_refs_types {
         CLEAR_REFS_ANON,
         CLEAR_REFS_MAPPED,
         CLEAR_REFS_SOFT_DIRTY,
+        CLEAR_REFS_MM_HIWATER_RSS,
         CLEAR_REFS_LAST,
 };
 
@@ -907,6 +908,18 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
                         .mm = mm,
                         .private = &cp,
                 };
+
+                if (type == CLEAR_REFS_MM_HIWATER_RSS) {
+                        /*
+                         * Writing 5 to /proc/pid/clear_refs resets the peak
+                         * resident set size to this mm's current rss value.
+                         */
+                        down_write(&mm->mmap_sem);
+                        reset_mm_hiwater_rss(mm);
+                        up_write(&mm->mmap_sem);
+                        goto out_mm;
+                }
+
                 down_read(&mm->mmap_sem);
                 if (type == CLEAR_REFS_SOFT_DIRTY) {
                         for (vma = mm->mmap; vma; vma = vma->vm_next) {
@@ -928,6 +941,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
                         mmu_notifier_invalidate_range_end(mm, 0, -1);
                 flush_tlb_mm(mm);
                 up_read(&mm->mmap_sem);
+out_mm:
                 mmput(mm);
         }
         put_task_struct(task);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bd52e2f14027..9bee7ec0c31f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1408,6 +1408,11 @@ static inline void update_hiwater_vm(struct mm_struct *mm)
                 mm->hiwater_vm = mm->total_vm;
 }
 
+static inline void reset_mm_hiwater_rss(struct mm_struct *mm)
+{
+        mm->hiwater_rss = get_mm_rss(mm);
+}
+
 static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
                                          struct mm_struct *mm)
 {