teach /proc/$pid/numa_maps about transparent hugepages

[firefly-linux-kernel-4.4.55.git] / fs / proc / task_mmu.c

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index db15935fa7579c18e28f127babbec24348868ee9..5afaa58a863012d83a69763b2e65c9db67fe2ada 100644 (file)
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -536,15 +536,17 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
        char buffer[PROC_NUMBUF];
        struct mm_struct *mm;
        struct vm_area_struct *vma;
-       long type;
+       int type;
+       int rv;
 
        memset(buffer, 0, sizeof(buffer));
        if (count > sizeof(buffer) - 1)
                count = sizeof(buffer) - 1;
        if (copy_from_user(buffer, buf, count))
                return -EFAULT;
-       if (strict_strtol(strstrip(buffer), 10, &type))
-               return -EINVAL;
+       rv = kstrtoint(strstrip(buffer), 10, &type);
+       if (rv < 0)
+               return rv;
        if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
                return -EINVAL;
        task = get_proc_task(file->f_path.dentry->d_inode);
@@ -769,18 +771,12 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
        if (!task)
                goto out;
 
-       mm = mm_for_maps(task);
-       ret = PTR_ERR(mm);
-       if (!mm || IS_ERR(mm))
-               goto out_task;
-
        ret = -EINVAL;
        /* file position must be aligned */
        if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
                goto out_task;
 
        ret = 0;
-
        if (!count)
                goto out_task;
 
@@ -788,7 +784,12 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
        pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
        ret = -ENOMEM;
        if (!pm.buffer)
-               goto out_mm;
+               goto out_task;
+
+       mm = mm_for_maps(task);
+       ret = PTR_ERR(mm);
+       if (!mm || IS_ERR(mm))
+               goto out_free;
 
        pagemap_walk.pmd_entry = pagemap_pte_range;
        pagemap_walk.pte_hole = pagemap_pte_hole;
@@ -831,7 +832,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
                len = min(count, PM_ENTRY_BYTES * pm.pos);
                if (copy_to_user(buf, pm.buffer, len)) {
                        ret = -EFAULT;
-                       goto out_free;
+                       goto out_mm;
                }
                copied += len;
                buf += len;
@@ -841,10 +842,10 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
        if (!ret || ret == PM_END_OF_BUFFER)
                ret = copied;
 
-out_free:
-       kfree(pm.buffer);
 out_mm:
        mmput(mm);
+out_free:
+       kfree(pm.buffer);
 out_task:
        put_task_struct(task);
 out:
@@ -876,30 +877,54 @@ struct numa_maps_private {
        struct numa_maps md;
 };
 
-static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty)
+static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty,
+                       unsigned long nr_pages)
 {
        int count = page_mapcount(page);
 
-       md->pages++;
+       md->pages += nr_pages;
        if (pte_dirty || PageDirty(page))
-               md->dirty++;
+               md->dirty += nr_pages;
 
        if (PageSwapCache(page))
-               md->swapcache++;
+               md->swapcache += nr_pages;
 
        if (PageActive(page) || PageUnevictable(page))
-               md->active++;
+               md->active += nr_pages;
 
        if (PageWriteback(page))
-               md->writeback++;
+               md->writeback += nr_pages;
 
        if (PageAnon(page))
-               md->anon++;
+               md->anon += nr_pages;
 
        if (count > md->mapcount_max)
                md->mapcount_max = count;
 
-       md->node[page_to_nid(page)]++;
+       md->node[page_to_nid(page)] += nr_pages;
+}
+
+static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
+               unsigned long addr)
+{
+       struct page *page;
+       int nid;
+
+       if (!pte_present(pte))
+               return NULL;
+
+       page = vm_normal_page(vma, addr, pte);
+       if (!page)
+               return NULL;
+
+       if (PageReserved(page))
+               return NULL;
+
+       nid = page_to_nid(page);
+       if (!node_isset(nid, node_states[N_HIGH_MEMORY]))
+               return NULL;
+
+       return page;
 }
 
 static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
@@ -911,26 +936,32 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
        pte_t *pte;
 
        md = walk->private;
-       orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
-       do {
-               struct page *page;
-               int nid;
+       spin_lock(&walk->mm->page_table_lock);
+       if (pmd_trans_huge(*pmd)) {
+               if (pmd_trans_splitting(*pmd)) {
+                       spin_unlock(&walk->mm->page_table_lock);
+                       wait_split_huge_page(md->vma->anon_vma, pmd);
+               } else {
+                       pte_t huge_pte = *(pte_t *)pmd;
+                       struct page *page;
 
-               if (!pte_present(*pte))
-                       continue;
+                       page = can_gather_numa_stats(huge_pte, md->vma, addr);
+                       if (page)
+                               gather_stats(page, md, pte_dirty(huge_pte),
+                                               HPAGE_PMD_SIZE/PAGE_SIZE);
+                       spin_unlock(&walk->mm->page_table_lock);
+                       return 0;
+               }
+       } else {
+               spin_unlock(&walk->mm->page_table_lock);
+       }
 
-               page = vm_normal_page(md->vma, addr, *pte);
+       orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+       do {
+               struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
                if (!page)
                        continue;
-
-               if (PageReserved(page))
-                       continue;
-
-               nid = page_to_nid(page);
-               if (!node_isset(nid, node_states[N_HIGH_MEMORY]))
-                       continue;
-
-               gather_stats(page, md, pte_dirty(*pte));
+               gather_stats(page, md, pte_dirty(*pte), 1);
 
        } while (pte++, addr += PAGE_SIZE, addr != end);
        pte_unmap_unlock(orig_pte, ptl);
@@ -951,7 +982,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
                return 0;
 
        md = walk->private;
-       gather_stats(page, md, pte_dirty(*pte));
+       gather_stats(page, md, pte_dirty(*pte), 1);
        return 0;
 }