mm: hugetlb: proc: add HugetlbPages field to /proc/PID/status

Currently there's no easy way to get per-process usage of hugetlb pages,
which is inconvenient because userspace applications which use hugetlb
typically want to control their processes on the basis of how much memory
(including hugetlb) they use.  So this patch simply provides easy access
to the info via /proc/PID/status.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Joern Engel <joern@logfs.org>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 37 insertions, 1 deletions

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index a7d6c06..12ac0e4 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -175,6 +175,7 @@ read the file /proc/PID/status:
   VmLib:      1412 kB
   VmPTE:        20 kb
   VmSwap:        0 kB
+  HugetlbPages:          0 kB
   Threads:        1
   SigQ:   0/28578
   SigPnd: 0000000000000000
@@ -238,6 +239,7 @@ Table 1-2: Contents of the status files (as of 4.1)
  VmPTE                       size of page table entries
  VmPMD                       size of second level page tables
  VmSwap                      size of swap usage (the number of referred swapents)
+ HugetlbPages                size of hugetlb memory portions
  Threads                     number of threads
  SigQ                        number of signals queued/max. number for queue
  SigPnd                      bitmap of pending signals for the thread
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5988b83..288185e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -70,6 +70,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		ptes >> 10,
 		pmds >> 10,
 		swap << (PAGE_SHIFT-10));
+	hugetlb_report_usage(m, mm);
 }
 
 unsigned long task_vsize(struct mm_struct *mm)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 5e35379..685c262 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -483,6 +483,17 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 #define hugepages_supported() (HPAGE_SHIFT != 0)
 #endif
 
+void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm);
+
+static inline void hugetlb_count_add(long l, struct mm_struct *mm)
+{
+	atomic_long_add(l, &mm->hugetlb_usage);
+}
+
+static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
+{
+	atomic_long_sub(l, &mm->hugetlb_usage);
+}
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page(v, a, r) NULL
@@ -519,6 +530,14 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 {
 	return &mm->page_table_lock;
 }
+
+static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m)
+{
+}
+
+static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
+{
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3d6baa7..0a85da2 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -486,6 +486,9 @@ struct mm_struct {
 	/* address of the bounds directory */
 	void __user *bd_addr;
 #endif
+#ifdef CONFIG_HUGETLB_PAGE
+	atomic_long_t hugetlb_usage;
+#endif
 };
 
 static inline void mm_init_cpumask(struct mm_struct *mm)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9cc7734..abfbe8c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2790,6 +2790,12 @@ void hugetlb_show_meminfo(void)
 				1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
 }
 
+void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm)
+{
+	seq_printf(m, "HugetlbPages:\t%8lu kB\n",
+		   atomic_long_read(&mm->hugetlb_usage) << (PAGE_SHIFT - 10));
+}
+
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
@@ -3025,6 +3031,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			get_page(ptepage);
 			page_dup_rmap(ptepage);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
+			hugetlb_count_add(pages_per_huge_page(h), dst);
 		}
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
@@ -3105,6 +3112,7 @@ again:
 		if (huge_pte_dirty(pte))
 			set_page_dirty(page);
 
+		hugetlb_count_sub(pages_per_huge_page(h), mm);
 		page_remove_rmap(page);
 		force_flush = !__tlb_remove_page(tlb, page);
 		if (force_flush) {
@@ -3509,6 +3517,7 @@ retry:
 				&& (vma->vm_flags & VM_SHARED)));
 	set_huge_pte_at(mm, address, ptep, new_pte);
 
+	hugetlb_count_add(pages_per_huge_page(h), mm);
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
 		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page, ptl);
diff --git a/mm/rmap.c b/mm/rmap.c
index f5b5c1f..d40e7ae 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1352,7 +1352,9 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	update_hiwater_rss(mm);
 
 	if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
-		if (!PageHuge(page)) {
+		if (PageHuge(page)) {
+			hugetlb_count_sub(1 << compound_order(page), mm);
+		} else {
 			if (PageAnon(page))
 				dec_mm_counter(mm, MM_ANONPAGES);
 			else