1 files changed, 133 insertions, 77 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index e4733feb0..fa95ab2d3 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -14,6 +14,7 @@
 #include <linux/swapops.h>
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
+#include <linux/shmem_fs.h>
 
 #include <asm/elf.h>
 #include <asm/uaccess.h>
@@ -22,9 +23,13 @@
 
 void task_mem(struct seq_file *m, struct mm_struct *mm)
 {
-	unsigned long data, text, lib, swap, ptes, pmds;
+	unsigned long text, lib, swap, ptes, pmds, anon, file, shmem;
 	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
 
+	anon = get_mm_counter(mm, MM_ANONPAGES);
+	file = get_mm_counter(mm, MM_FILEPAGES);
+	shmem = get_mm_counter(mm, MM_SHMEMPAGES);
+
 	/*
 	 * Note: to minimize their overhead, mm maintains hiwater_vm and
 	 * hiwater_rss only when about to *lower* total_vm or rss.  Any
@@ -35,11 +40,10 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	hiwater_vm = total_vm = mm->total_vm;
 	if (hiwater_vm < mm->hiwater_vm)
 		hiwater_vm = mm->hiwater_vm;
-	hiwater_rss = total_rss = get_mm_rss(mm);
+	hiwater_rss = total_rss = anon + file + shmem;
 	if (hiwater_rss < mm->hiwater_rss)
 		hiwater_rss = mm->hiwater_rss;
 
-	data = mm->total_vm - mm->shared_vm - mm->stack_vm;
 	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
 	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
 	swap = get_mm_counter(mm, MM_SWAPENTS);
@@ -52,6 +56,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		"VmPin:\t%8lu kB\n"
 		"VmHWM:\t%8lu kB\n"
 		"VmRSS:\t%8lu kB\n"
+		"RssAnon:\t%8lu kB\n"
+		"RssFile:\t%8lu kB\n"
+		"RssShmem:\t%8lu kB\n"
 		"VmData:\t%8lu kB\n"
 		"VmStk:\t%8lu kB\n"
 		"VmExe:\t%8lu kB\n"
@@ -65,7 +72,10 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		mm->pinned_vm << (PAGE_SHIFT-10),
 		hiwater_rss << (PAGE_SHIFT-10),
 		total_rss << (PAGE_SHIFT-10),
-		data << (PAGE_SHIFT-10),
+		anon << (PAGE_SHIFT-10),
+		file << (PAGE_SHIFT-10),
+		shmem << (PAGE_SHIFT-10),
+		mm->data_vm << (PAGE_SHIFT-10),
 		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
 		ptes >> 10,
 		pmds >> 10,
@@ -82,10 +92,11 @@ unsigned long task_statm(struct mm_struct *mm,
 			 unsigned long *shared, unsigned long *text,
 			 unsigned long *data, unsigned long *resident)
 {
-	*shared = get_mm_counter(mm, MM_FILEPAGES);
+	*shared = get_mm_counter(mm, MM_FILEPAGES) +
+			get_mm_counter(mm, MM_SHMEMPAGES);
 	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
 								>> PAGE_SHIFT;
-	*data = mm->total_vm - mm->shared_vm;
+	*data = mm->data_vm + mm->stack_vm;
 	*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
 	return mm->total_vm;
 }
@@ -248,23 +259,29 @@ static int do_maps_open(struct inode *inode, struct file *file,
 				sizeof(struct proc_maps_private));
 }
 
-static pid_t pid_of_stack(struct proc_maps_private *priv,
-				struct vm_area_struct *vma, bool is_pid)
+/*
+ * Indicate if the VMA is a stack for the given task; for
+ * /proc/PID/maps that is the stack of the main task.
+ */
+static int is_stack(struct proc_maps_private *priv,
+		    struct vm_area_struct *vma, int is_pid)
 {
-	struct inode *inode = priv->inode;
-	struct task_struct *task;
-	pid_t ret = 0;
+	int stack = 0;
 
-	rcu_read_lock();
-	task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
+	if (is_pid) {
+		stack = vma->vm_start <= vma->vm_mm->start_stack &&
+			vma->vm_end >= vma->vm_mm->start_stack;
+	} else {
+		struct inode *inode = priv->inode;
+		struct task_struct *task;
+
+		rcu_read_lock();
+		task = pid_task(proc_pid(inode), PIDTYPE_PID);
 		if (task)
-			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
+			stack = vma_is_stack_for_task(vma, task);
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
-
-	return ret;
+	return stack;
 }
 
 static void
@@ -281,10 +298,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 	const char *name = NULL;
 
 	if (file) {
-		struct inode *inode;
-
-		file = vma_pr_or_file(vma);
-		inode = file_inode(file);
+		struct inode *inode = file_inode(vma->vm_file);
 		dev = inode->i_sb->s_dev;
 		ino = inode->i_ino;
 		pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
@@ -327,8 +341,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
 	name = arch_vma_name(vma);
 	if (!name) {
-		pid_t tid;
-
 		if (!mm) {
 			name = "[vdso]";
 			goto done;
@@ -340,21 +352,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 			goto done;
 		}
 
-		tid = pid_of_stack(priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack)) {
-				name = "[stack]";
-			} else {
-				/* Thread stack in /proc/PID/maps */
-				seq_pad(m, ' ');
-				seq_printf(m, "[stack:%d]", tid);
-			}
-		}
+		if (is_stack(priv, vma, is_pid))
+			name = "[stack]";
 	}
 
 done:
@@ -454,12 +453,14 @@ struct mem_size_stats {
 	unsigned long private_hugetlb;
 	u64 pss;
 	u64 swap_pss;
+	bool check_shmem_swap;
 };
 
 static void smaps_account(struct mem_size_stats *mss, struct page *page,
-		unsigned long size, bool young, bool dirty)
+		bool compound, bool young, bool dirty)
 {
-	int mapcount;
+	int i, nr = compound ? 1 << compound_order(page) : 1;
+	unsigned long size = nr * PAGE_SIZE;
 
 	if (PageAnon(page))
 		mss->anonymous += size;
@@ -468,26 +469,53 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 	/* Accumulate the size in pages that have been accessed. */
 	if (young || page_is_young(page) || PageReferenced(page))
 		mss->referenced += size;
-	mapcount = page_mapcount(page);
-	if (mapcount >= 2) {
-		u64 pss_delta;
 
-		if (dirty || PageDirty(page))
-			mss->shared_dirty += size;
-		else
-			mss->shared_clean += size;
-		pss_delta = (u64)size << PSS_SHIFT;
-		do_div(pss_delta, mapcount);
-		mss->pss += pss_delta;
-	} else {
+	/*
+	 * page_count(page) == 1 guarantees the page is mapped exactly once.
+	 * If any subpage of the compound page mapped with PTE it would elevate
+	 * page_count().
+	 */
+	if (page_count(page) == 1) {
 		if (dirty || PageDirty(page))
 			mss->private_dirty += size;
 		else
 			mss->private_clean += size;
 		mss->pss += (u64)size << PSS_SHIFT;
+		return;
+	}
+
+	for (i = 0; i < nr; i++, page++) {
+		int mapcount = page_mapcount(page);
+
+		if (mapcount >= 2) {
+			if (dirty || PageDirty(page))
+				mss->shared_dirty += PAGE_SIZE;
+			else
+				mss->shared_clean += PAGE_SIZE;
+			mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
+		} else {
+			if (dirty || PageDirty(page))
+				mss->private_dirty += PAGE_SIZE;
+			else
+				mss->private_clean += PAGE_SIZE;
+			mss->pss += PAGE_SIZE << PSS_SHIFT;
+		}
 	}
 }
 
+#ifdef CONFIG_SHMEM
+static int smaps_pte_hole(unsigned long addr, unsigned long end,
+		struct mm_walk *walk)
+{
+	struct mem_size_stats *mss = walk->private;
+
+	mss->swap += shmem_partial_swap_usage(
+			walk->vma->vm_file->f_mapping, addr, end);
+
+	return 0;
+}
+#endif
+
 static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 		struct mm_walk *walk)
 {
@@ -515,11 +543,25 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 			}
 		} else if (is_migration_entry(swpent))
 			page = migration_entry_to_page(swpent);
+	} else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
+							&& pte_none(*pte))) {
+		page = find_get_entry(vma->vm_file->f_mapping,
+						linear_page_index(vma, addr));
+		if (!page)
+			return;
+
+		if (radix_tree_exceptional_entry(page))
+			mss->swap += PAGE_SIZE;
+		else
+			page_cache_release(page);
+
+		return;
 	}
 
 	if (!page)
 		return;
-	smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte));
+
+	smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte));
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -535,8 +577,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 	if (IS_ERR_OR_NULL(page))
 		return;
 	mss->anonymous_thp += HPAGE_PMD_SIZE;
-	smaps_account(mss, page, HPAGE_PMD_SIZE,
-			pmd_young(*pmd), pmd_dirty(*pmd));
+	smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
 }
 #else
 static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
@@ -552,7 +593,8 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	ptl = pmd_trans_huge_lock(pmd, vma);
+	if (ptl) {
 		smaps_pmd_entry(pmd, addr, walk);
 		spin_unlock(ptl);
 		return 0;
@@ -674,6 +716,31 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 	};
 
 	memset(&mss, 0, sizeof mss);
+
+#ifdef CONFIG_SHMEM
+	if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
+		/*
+		 * For shared or readonly shmem mappings we know that all
+		 * swapped out pages belong to the shmem object, and we can
+		 * obtain the swap value much more efficiently. For private
+		 * writable mappings, we might have COW pages that are
+		 * not affected by the parent swapped out pages of the shmem
+		 * object, so we have to distinguish them during the page walk.
+		 * Unless we know that the shmem object (or the part mapped by
+		 * our VMA) has no swapped out pages at all.
+		 */
+		unsigned long shmem_swapped = shmem_swap_usage(vma);
+
+		if (!shmem_swapped || (vma->vm_flags & VM_SHARED) ||
+					!(vma->vm_flags & VM_WRITE)) {
+			mss.swap = shmem_swapped;
+		} else {
+			mss.check_shmem_swap = true;
+			smaps_walk.pte_hole = smaps_pte_hole;
+		}
+	}
+#endif
+
 	/* mmap_sem is held in m_start */
 	walk_page_vma(vma, &smaps_walk);
 
@@ -820,9 +887,6 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 	pmd = pmd_wrprotect(pmd);
 	pmd = pmd_clear_soft_dirty(pmd);
 
-	if (vma->vm_flags & VM_SOFTDIRTY)
-		vma->vm_flags &= ~VM_SOFTDIRTY;
-
 	set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
 }
 #else
@@ -841,7 +905,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	spinlock_t *ptl;
 	struct page *page;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	ptl = pmd_trans_huge_lock(pmd, vma);
+	if (ptl) {
 		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
 			clear_soft_dirty_pmd(vma, addr, pmd);
 			goto out;
@@ -1115,7 +1180,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 	int err = 0;
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (pmd_trans_huge_lock(pmdp, vma, &ptl) == 1) {
+	ptl = pmd_trans_huge_lock(pmdp, vma);
+	if (ptl) {
 		u64 flags = 0, frame = 0;
 		pmd_t pmd = *pmdp;
 
@@ -1447,7 +1513,8 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	pte_t *orig_pte;
 	pte_t *pte;
 
-	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+	ptl = pmd_trans_huge_lock(pmd, vma);
+	if (ptl) {
 		pte_t huge_pte = *(pte_t *)pmd;
 		struct page *page;
 
@@ -1509,7 +1576,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
 	struct vm_area_struct *vma = v;
 	struct numa_maps *md = &numa_priv->md;
-	struct file *file = vma_pr_or_file(vma);
+	struct file *file = vma->vm_file;
 	struct mm_struct *mm = vma->vm_mm;
 	struct mm_walk walk = {
 		.hugetlb_entry = gather_hugetlb_stats,
@@ -1542,19 +1609,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 		seq_file_path(m, file, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_puts(m, " heap");
-	} else {
-		pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack))
-				seq_puts(m, " stack");
-			else
-				seq_printf(m, " stack:%d", tid);
-		}
+	} else if (is_stack(proc_priv, vma, is_pid)) {
+		seq_puts(m, " stack");
 	}
 
 	if (is_vm_hugetlb_page(vma))