seq_printf(m, "%*c", len, ' ');
}
+/*
+ * Proportional Set Size(PSS): my share of RSS.
+ *
+ * PSS of a process is the count of pages it has in memory, where each
+ * page is divided by the number of processes sharing it. So if a
+ * process has 1000 pages all to itself, and 1000 shared with one other
+ * process, its PSS will be 1500.
+ *
+ * To keep (accumulated) division errors low, we adopt a 64bit
+ * fixed-point pss counter to minimize division errors. So (pss >>
+ * PSS_SHIFT) would be the real byte count.
+ *
+ * A shift of 12 before division means (assuming 4K page size):
+ * - 1M 3-user-pages add up to 8KB errors;
+ * - supports mapcount up to 2^24, or 16M;
+ * - supports PSS up to 2^52 bytes, or 4PB.
+ */
+#define PSS_SHIFT 12
+
struct mem_size_stats
{
+ struct vm_area_struct *vma;
unsigned long resident;
unsigned long shared_clean;
unsigned long shared_dirty;
unsigned long private_clean;
unsigned long private_dirty;
unsigned long referenced;
+ u64 pss;
};
-struct pmd_walker {
- struct vm_area_struct *vma;
- void *private;
- void (*action)(struct vm_area_struct *, pmd_t *, unsigned long,
- unsigned long, void *);
-};
-
-static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats *mss)
+static int show_map(struct seq_file *m, void *v)
{
struct proc_maps_private *priv = m->private;
struct task_struct *task = priv->task;
}
seq_putc(m, '\n');
- if (mss)
- seq_printf(m,
- "Size: %8lu kB\n"
- "Rss: %8lu kB\n"
- "Shared_Clean: %8lu kB\n"
- "Shared_Dirty: %8lu kB\n"
- "Private_Clean: %8lu kB\n"
- "Private_Dirty: %8lu kB\n"
- "Referenced: %8lu kB\n",
- (vma->vm_end - vma->vm_start) >> 10,
- mss->resident >> 10,
- mss->shared_clean >> 10,
- mss->shared_dirty >> 10,
- mss->private_clean >> 10,
- mss->private_dirty >> 10,
- mss->referenced >> 10);
-
if (m->count < m->size) /* vma is copied successfully */
m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
return 0;
}
-static int show_map(struct seq_file *m, void *v)
-{
- return show_map_internal(m, v, NULL);
-}
-
-static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
- unsigned long addr, unsigned long end,
- void *private)
+static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+ void *private)
{
struct mem_size_stats *mss = private;
+ struct vm_area_struct *vma = mss->vma;
pte_t *pte, ptent;
spinlock_t *ptl;
struct page *page;
+ int mapcount;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
/* Accumulate the size in pages that have been accessed. */
if (pte_young(ptent) || PageReferenced(page))
mss->referenced += PAGE_SIZE;
- if (page_mapcount(page) >= 2) {
+ mapcount = page_mapcount(page);
+ if (mapcount >= 2) {
if (pte_dirty(ptent))
mss->shared_dirty += PAGE_SIZE;
else
mss->shared_clean += PAGE_SIZE;
+ mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
} else {
if (pte_dirty(ptent))
mss->private_dirty += PAGE_SIZE;
else
mss->private_clean += PAGE_SIZE;
+ mss->pss += (PAGE_SIZE << PSS_SHIFT);
}
}
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
+ return 0;
}
-static void clear_refs_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
- unsigned long addr, unsigned long end,
- void *private)
+static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
+ unsigned long end, void *private)
{
+ struct vm_area_struct *vma = private;
pte_t *pte, ptent;
spinlock_t *ptl;
struct page *page;
}
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
+ return 0;
}
-static inline void walk_pmd_range(struct pmd_walker *walker, pud_t *pud,
- unsigned long addr, unsigned long end)
-{
- pmd_t *pmd;
- unsigned long next;
-
- for (pmd = pmd_offset(pud, addr); addr != end;
- pmd++, addr = next) {
- next = pmd_addr_end(addr, end);
- if (pmd_none_or_clear_bad(pmd))
- continue;
- walker->action(walker->vma, pmd, addr, next, walker->private);
- }
-}
-
-static inline void walk_pud_range(struct pmd_walker *walker, pgd_t *pgd,
- unsigned long addr, unsigned long end)
-{
- pud_t *pud;
- unsigned long next;
-
- for (pud = pud_offset(pgd, addr); addr != end;
- pud++, addr = next) {
- next = pud_addr_end(addr, end);
- if (pud_none_or_clear_bad(pud))
- continue;
- walk_pmd_range(walker, pud, addr, next);
- }
-}
-
-/*
- * walk_page_range - walk the page tables of a VMA with a callback
- * @vma - VMA to walk
- * @action - callback invoked for every bottom-level (PTE) page table
- * @private - private data passed to the callback function
- *
- * Recursively walk the page table for the memory area in a VMA, calling
- * a callback for every bottom-level (PTE) page table.
- */
-static inline void walk_page_range(struct vm_area_struct *vma,
- void (*action)(struct vm_area_struct *,
- pmd_t *, unsigned long,
- unsigned long, void *),
- void *private)
-{
- unsigned long addr = vma->vm_start;
- unsigned long end = vma->vm_end;
- struct pmd_walker walker = {
- .vma = vma,
- .private = private,
- .action = action,
- };
- pgd_t *pgd;
- unsigned long next;
-
- for (pgd = pgd_offset(vma->vm_mm, addr); addr != end;
- pgd++, addr = next) {
- next = pgd_addr_end(addr, end);
- if (pgd_none_or_clear_bad(pgd))
- continue;
- walk_pud_range(&walker, pgd, addr, next);
- }
-}
+static struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range };
static int show_smap(struct seq_file *m, void *v)
{
struct vm_area_struct *vma = v;
struct mem_size_stats mss;
+ int ret;
memset(&mss, 0, sizeof mss);
+ mss.vma = vma;
if (vma->vm_mm && !is_vm_hugetlb_page(vma))
- walk_page_range(vma, smaps_pte_range, &mss);
- return show_map_internal(m, v, &mss);
+ walk_page_range(vma->vm_mm, vma->vm_start, vma->vm_end,
+ &smaps_walk, &mss);
+
+ ret = show_map(m, v);
+ if (ret)
+ return ret;
+
+ seq_printf(m,
+ "Size: %8lu kB\n"
+ "Rss: %8lu kB\n"
+ "Pss: %8lu kB\n"
+ "Shared_Clean: %8lu kB\n"
+ "Shared_Dirty: %8lu kB\n"
+ "Private_Clean: %8lu kB\n"
+ "Private_Dirty: %8lu kB\n"
+ "Referenced: %8lu kB\n",
+ (vma->vm_end - vma->vm_start) >> 10,
+ mss.resident >> 10,
+ (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
+ mss.shared_clean >> 10,
+ mss.shared_dirty >> 10,
+ mss.private_clean >> 10,
+ mss.private_dirty >> 10,
+ mss.referenced >> 10);
+
+ return ret;
}
-void clear_refs_smap(struct mm_struct *mm)
+static struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range };
+
+static ssize_t clear_refs_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
{
+ struct task_struct *task;
+ char buffer[PROC_NUMBUF], *end;
+ struct mm_struct *mm;
struct vm_area_struct *vma;
- down_read(&mm->mmap_sem);
- for (vma = mm->mmap; vma; vma = vma->vm_next)
- if (vma->vm_mm && !is_vm_hugetlb_page(vma))
- walk_page_range(vma, clear_refs_pte_range, NULL);
- flush_tlb_mm(mm);
- up_read(&mm->mmap_sem);
+ memset(buffer, 0, sizeof(buffer));
+ if (count > sizeof(buffer) - 1)
+ count = sizeof(buffer) - 1;
+ if (copy_from_user(buffer, buf, count))
+ return -EFAULT;
+ if (!simple_strtol(buffer, &end, 0))
+ return -EINVAL;
+ if (*end == '\n')
+ end++;
+ task = get_proc_task(file->f_path.dentry->d_inode);
+ if (!task)
+ return -ESRCH;
+ mm = get_task_mm(task);
+ if (mm) {
+ down_read(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next)
+ if (!is_vm_hugetlb_page(vma))
+ walk_page_range(mm, vma->vm_start, vma->vm_end,
+ &clear_refs_walk, vma);
+ flush_tlb_mm(mm);
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ }
+ put_task_struct(task);
+ if (end - buffer == 0)
+ return -EIO;
+ return end - buffer;
}
+const struct file_operations proc_clear_refs_operations = {
+ .write = clear_refs_write,
+};
+
static void *m_start(struct seq_file *m, loff_t *pos)
{
struct proc_maps_private *priv = m->private;