1 files changed, 366 insertions, 57 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index fc8dca4a7b19..c3faa39c0ce1 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -14,6 +14,8 @@
 #include <linux/swapops.h>
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
+#include <linux/mm_inline.h>
+#include <linux/ctype.h>
 
 #include <asm/elf.h>
 #include <asm/uaccess.h>
@@ -288,6 +290,7 @@ static int proc_map_release(struct inode *inode, struct file *file)
 	if (priv->mm)
 		mmdrop(priv->mm);
 
+	kfree(priv->rollup);
 	return seq_release_private(inode, file);
 }
 
@@ -314,6 +317,23 @@ static int is_stack(struct proc_maps_private *priv,
 		vma->vm_end >= vma->vm_mm->start_stack;
 }
 
+static void show_vma_header_prefix(struct seq_file *m,
+				   unsigned long start, unsigned long end,
+				   vm_flags_t flags, unsigned long long pgoff,
+				   dev_t dev, unsigned long ino)
+{
+	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
+	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
+		   start,
+		   end,
+		   flags & VM_READ ? 'r' : '-',
+		   flags & VM_WRITE ? 'w' : '-',
+		   flags & VM_EXEC ? 'x' : '-',
+		   flags & VM_MAYSHARE ? 's' : 'p',
+		   pgoff,
+		   MAJOR(dev), MINOR(dev), ino);
+}
+
 static void
 show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 {
@@ -337,17 +357,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 	/* We don't show the stack guard page in /proc/maps */
 	start = vma->vm_start;
 	end = vma->vm_end;
-
-	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
-	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
-			start,
-			end,
-			flags & VM_READ ? 'r' : '-',
-			flags & VM_WRITE ? 'w' : '-',
-			flags & VM_EXEC ? 'x' : '-',
-			flags & VM_MAYSHARE ? 's' : 'p',
-			pgoff,
-			MAJOR(dev), MINOR(dev), ino);
+	show_vma_header_prefix(m, start, end, flags, pgoff, dev, ino);
 
 	/*
 	 * Print the dentry name for named mappings, and a
@@ -382,7 +392,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 			name = "[stack]";
 			goto done;
 		}
-
 		if (vma_get_anon_name(vma)) {
 			seq_pad(m, ' ');
 			seq_print_vma_name(m, vma);
@@ -473,6 +482,7 @@ const struct file_operations proc_tid_maps_operations = {
 
 #ifdef CONFIG_PROC_PAGE_MONITOR
 struct mem_size_stats {
+	bool first;
 	unsigned long resident;
 	unsigned long shared_clean;
 	unsigned long shared_dirty;
@@ -484,7 +494,9 @@ struct mem_size_stats {
 	unsigned long swap;
 	unsigned long shared_hugetlb;
 	unsigned long private_hugetlb;
+	unsigned long first_vma_start;
 	u64 pss;
+	u64 pss_locked;
 	u64 swap_pss;
 };
 
@@ -694,69 +706,105 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 
 static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
+	struct proc_maps_private *priv = m->private;
 	struct vm_area_struct *vma = v;
-	struct mem_size_stats mss;
+	struct mem_size_stats mss_stack;
+	struct mem_size_stats *mss;
 	struct mm_walk smaps_walk = {
 		.pmd_entry = smaps_pte_range,
 #ifdef CONFIG_HUGETLB_PAGE
 		.hugetlb_entry = smaps_hugetlb_range,
 #endif
 		.mm = vma->vm_mm,
-		.private = &mss,
 	};
+	int ret = 0;
+	bool rollup_mode;
+	bool last_vma;
+
+	if (priv->rollup) {
+		rollup_mode = true;
+		mss = priv->rollup;
+		if (mss->first) {
+			mss->first_vma_start = vma->vm_start;
+			mss->first = false;
+		}
+		last_vma = !m_next_vma(priv, vma);
+	} else {
+		rollup_mode = false;
+		memset(&mss_stack, 0, sizeof(mss_stack));
+		mss = &mss_stack;
+	}
+
+	smaps_walk.private = mss;
 
-	memset(&mss, 0, sizeof mss);
 	/* mmap_sem is held in m_start */
 	walk_page_vma(vma, &smaps_walk);
+	if (vma->vm_flags & VM_LOCKED)
+		mss->pss_locked += mss->pss;
+
+	if (!rollup_mode) {
+		show_map_vma(m, vma, is_pid);
+	} else if (last_vma) {
+		show_vma_header_prefix(
+			m, mss->first_vma_start, vma->vm_end, 0, 0, 0, 0);
+		seq_pad(m, ' ');
+		seq_puts(m, "[rollup]\n");
+	} else {
+		ret = SEQ_SKIP;
+	}
 
-	show_map_vma(m, vma, is_pid);
-
-	if (vma_get_anon_name(vma)) {
+	if (!rollup_mode && vma_get_anon_name(vma)) {
 		seq_puts(m, "Name:           ");
 		seq_print_vma_name(m, vma);
 		seq_putc(m, '\n');
 	}
 
-	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"
-		   "Anonymous:      %8lu kB\n"
-		   "AnonHugePages:  %8lu kB\n"
-		   "Shared_Hugetlb: %8lu kB\n"
-		   "Private_Hugetlb: %7lu kB\n"
-		   "Swap:           %8lu kB\n"
-		   "SwapPss:        %8lu kB\n"
-		   "KernelPageSize: %8lu kB\n"
-		   "MMUPageSize:    %8lu kB\n"
-		   "Locked:         %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,
-		   mss.anonymous >> 10,
-		   mss.anonymous_thp >> 10,
-		   mss.shared_hugetlb >> 10,
-		   mss.private_hugetlb >> 10,
-		   mss.swap >> 10,
-		   (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)),
-		   vma_kernel_pagesize(vma) >> 10,
-		   vma_mmu_pagesize(vma) >> 10,
-		   (vma->vm_flags & VM_LOCKED) ?
-			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
-
-	show_smap_vma_flags(m, vma);
+	if (!rollup_mode)
+		seq_printf(m,
+			   "Size:           %8lu kB\n"
+			   "KernelPageSize: %8lu kB\n"
+			   "MMUPageSize:    %8lu kB\n",
+			   (vma->vm_end - vma->vm_start) >> 10,
+			   vma_kernel_pagesize(vma) >> 10,
+			   vma_mmu_pagesize(vma) >> 10);
+
+
+	if (!rollup_mode || last_vma)
+		seq_printf(m,
+			   "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"
+			   "Anonymous:      %8lu kB\n"
+			   "AnonHugePages:  %8lu kB\n"
+			   "Shared_Hugetlb: %8lu kB\n"
+			   "Private_Hugetlb: %7lu kB\n"
+			   "Swap:           %8lu kB\n"
+			   "SwapPss:        %8lu kB\n"
+			   "Locked:         %8lu kB\n",
+			   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,
+			   mss->anonymous >> 10,
+			   mss->anonymous_thp >> 10,
+			   mss->shared_hugetlb >> 10,
+			   mss->private_hugetlb >> 10,
+			   mss->swap >> 10,
+			   (unsigned long)(mss->swap_pss >> (10 + PSS_SHIFT)),
+			   (unsigned long)(mss->pss >> (10 + PSS_SHIFT)));
+
+	if (!rollup_mode) {
+		show_smap_vma_flags(m, vma);
+	}
 	m_cache_vma(m, vma);
-	return 0;
+	return ret;
 }
 
 static int show_pid_smap(struct seq_file *m, void *v)
@@ -788,6 +836,25 @@ static int pid_smaps_open(struct inode *inode, struct file *file)
 	return do_maps_open(inode, file, &proc_pid_smaps_op);
 }
 
+static int pid_smaps_rollup_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq;
+	struct proc_maps_private *priv;
+	int ret = do_maps_open(inode, file, &proc_pid_smaps_op);
+
+	if (ret < 0)
+		return ret;
+	seq = file->private_data;
+	priv = seq->private;
+	priv->rollup = kzalloc(sizeof(*priv->rollup), GFP_KERNEL);
+	if (!priv->rollup) {
+		proc_map_release(inode, file);
+		return -ENOMEM;
+	}
+	priv->rollup->first = true;
+	return 0;
+}
+
 static int tid_smaps_open(struct inode *inode, struct file *file)
 {
 	return do_maps_open(inode, file, &proc_tid_smaps_op);
@@ -800,6 +867,13 @@ const struct file_operations proc_pid_smaps_operations = {
 	.release	= proc_map_release,
 };
 
+const struct file_operations proc_pid_smaps_rollup_operations = {
+	.open		= pid_smaps_rollup_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= proc_map_release,
+};
+
 const struct file_operations proc_tid_smaps_operations = {
 	.open		= tid_smaps_open,
 	.read		= seq_read,
@@ -1433,6 +1507,241 @@ const struct file_operations proc_pagemap_operations = {
 };
 #endif /* CONFIG_PROC_PAGE_MONITOR */
 
+#ifdef CONFIG_PROCESS_RECLAIM
+static int reclaim_pte_range(pmd_t *pmd, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
+{
+	struct reclaim_param *rp = walk->private;
+	struct vm_area_struct *vma = rp->vma;
+	pte_t *pte, ptent;
+	spinlock_t *ptl;
+	struct page *page;
+	LIST_HEAD(page_list);
+	int isolated;
+	int reclaimed;
+
+	split_huge_page_pmd(vma, addr, pmd);
+	if (pmd_trans_unstable(pmd) || !rp->nr_to_reclaim)
+		return 0;
+cont:
+	isolated = 0;
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	for (; addr != end; pte++, addr += PAGE_SIZE) {
+		ptent = *pte;
+		if (!pte_present(ptent))
+			continue;
+
+		page = vm_normal_page(vma, addr, ptent);
+		if (!page)
+			continue;
+
+		if (isolate_lru_page(page))
+			continue;
+
+		list_add(&page->lru, &page_list);
+		inc_zone_page_state(page, NR_ISOLATED_ANON +
+				page_is_file_cache(page));
+		isolated++;
+		rp->nr_scanned++;
+		if ((isolated >= SWAP_CLUSTER_MAX) || !rp->nr_to_reclaim)
+			break;
+	}
+	pte_unmap_unlock(pte - 1, ptl);
+	reclaimed = reclaim_pages_from_list(&page_list, vma);
+	rp->nr_reclaimed += reclaimed;
+	rp->nr_to_reclaim -= reclaimed;
+	if (rp->nr_to_reclaim < 0)
+		rp->nr_to_reclaim = 0;
+
+	if (rp->nr_to_reclaim && (addr != end))
+		goto cont;
+
+	cond_resched();
+	return 0;
+}
+
+enum reclaim_type {
+	RECLAIM_FILE,
+	RECLAIM_ANON,
+	RECLAIM_ALL,
+	RECLAIM_RANGE,
+};
+
+struct reclaim_param reclaim_task_anon(struct task_struct *task,
+		int nr_to_reclaim)
+{
+	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	struct mm_walk reclaim_walk = {};
+	struct reclaim_param rp;
+
+	rp.nr_reclaimed = 0;
+	rp.nr_scanned = 0;
+	get_task_struct(task);
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out;
+
+	reclaim_walk.mm = mm;
+	reclaim_walk.pmd_entry = reclaim_pte_range;
+
+	rp.nr_to_reclaim = nr_to_reclaim;
+	reclaim_walk.private = &rp;
+
+	down_read(&mm->mmap_sem);
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		if (is_vm_hugetlb_page(vma))
+			continue;
+
+		if (vma->vm_file)
+			continue;
+
+		if (vma->vm_flags & VM_LOCKED)
+			continue;
+
+		if (!rp.nr_to_reclaim)
+			break;
+
+		rp.vma = vma;
+		walk_page_range(vma->vm_start, vma->vm_end,
+			&reclaim_walk);
+	}
+
+	flush_tlb_mm(mm);
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+out:
+	put_task_struct(task);
+	return rp;
+}
+
+static ssize_t reclaim_write(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	char buffer[200];
+	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	enum reclaim_type type;
+	char *type_buf;
+	struct mm_walk reclaim_walk = {};
+	unsigned long start = 0;
+	unsigned long end = 0;
+	struct reclaim_param rp;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+
+	if (copy_from_user(buffer, buf, count))
+		return -EFAULT;
+
+	type_buf = strstrip(buffer);
+	if (!strcmp(type_buf, "file"))
+		type = RECLAIM_FILE;
+	else if (!strcmp(type_buf, "anon"))
+		type = RECLAIM_ANON;
+	else if (!strcmp(type_buf, "all"))
+		type = RECLAIM_ALL;
+	else if (isdigit(*type_buf))
+		type = RECLAIM_RANGE;
+	else
+		goto out_err;
+
+	if (type == RECLAIM_RANGE) {
+		char *token;
+		unsigned long long len, len_in, tmp;
+		token = strsep(&type_buf, " ");
+		if (!token)
+			goto out_err;
+		tmp = memparse(token, &token);
+		if (tmp & ~PAGE_MASK || tmp > ULONG_MAX)
+			goto out_err;
+		start = tmp;
+
+		token = strsep(&type_buf, " ");
+		if (!token)
+			goto out_err;
+		len_in = memparse(token, &token);
+		len = (len_in + ~PAGE_MASK) & PAGE_MASK;
+		if (len > ULONG_MAX)
+			goto out_err;
+		/*
+		 * Check to see whether len was rounded up from small -ve
+		 * to zero.
+		 */
+		if (len_in && !len)
+			goto out_err;
+
+		end = start + len;
+		if (end < start)
+			goto out_err;
+	}
+
+	task = get_proc_task(file->f_path.dentry->d_inode);
+	if (!task)
+		return -ESRCH;
+
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out;
+
+	reclaim_walk.mm = mm;
+	reclaim_walk.pmd_entry = reclaim_pte_range;
+
+	rp.nr_to_reclaim = ~0;
+	rp.nr_reclaimed = 0;
+	reclaim_walk.private = &rp;
+
+	down_read(&mm->mmap_sem);
+	if (type == RECLAIM_RANGE) {
+		vma = find_vma(mm, start);
+		while (vma) {
+			if (vma->vm_start > end)
+				break;
+			if (is_vm_hugetlb_page(vma))
+				continue;
+
+			rp.vma = vma;
+			walk_page_range(max(vma->vm_start, start),
+					min(vma->vm_end, end),
+					&reclaim_walk);
+			vma = vma->vm_next;
+		}
+	} else {
+		for (vma = mm->mmap; vma; vma = vma->vm_next) {
+			if (is_vm_hugetlb_page(vma))
+				continue;
+
+			if (type == RECLAIM_ANON && vma->vm_file)
+				continue;
+
+			if (type == RECLAIM_FILE && !vma->vm_file)
+				continue;
+
+			rp.vma = vma;
+			walk_page_range(vma->vm_start, vma->vm_end,
+				&reclaim_walk);
+		}
+	}
+
+	flush_tlb_mm(mm);
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+out:
+	put_task_struct(task);
+	return count;
+
+out_err:
+	return -EINVAL;
+}
+
+const struct file_operations proc_reclaim_operations = {
+	.write		= reclaim_write,
+	.llseek		= noop_llseek,
+};
+#endif
+
 #ifdef CONFIG_NUMA
 
 struct numa_maps {