mm: Per process reclaim

These day, there are many platforms avaiable in the embedded market
and they are smarter than kernel which has very limited information
about working set so they want to involve memory management more heavily
like android's lowmemory killer and ashmem or recent many lowmemory
notifier.

One of the simple imagine scenario about userspace's intelligence is that
platform can manage tasks as forground and backgroud so it would be
better to reclaim background's task pages for end-user's *responsibility*
although it has frequent referenced pages.

This patch adds new knob "reclaim under proc/<pid>/" so task manager
can reclaim any target process anytime, anywhere. It could give another
method to platform for using memory efficiently.

It can avoid process killing for getting free memory, which was really
terrible experience because I lost my best score of game I had ever
after I switch the phone call while I enjoyed the game.

Reclaim file-backed pages only.
	echo file > /proc/PID/reclaim
Reclaim anonymous pages only.
	echo anon > /proc/PID/reclaim
Reclaim all pages
	echo all > /proc/PID/reclaim

Change-Id: Iabdb7bc2ef3dc4d94e3ea005fbe18f4cd06739ab
Signed-off-by: Minchan Kim <minchan@kernel.org>
Patch-mainline: linux-mm @ 9 May 2013 16:21:24
[vinmenon@codeaurora.org: trivial merge conflict fixes,
and minor tweak of the commit msg]
Signed-off-by: Vinayak Menon <vinmenon@codeaurora.org>

3 files changed, 125 insertions, 0 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 87176c369f87..f5d4bc730c0d 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2972,6 +2972,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("mounts",     S_IRUGO, proc_mounts_operations),
 	REG("mountinfo",  S_IRUGO, proc_mountinfo_operations),
 	REG("mountstats", S_IRUSR, proc_mountstats_operations),
+#ifdef CONFIG_PROCESS_RECLAIM
+	REG("reclaim", S_IWUSR, proc_reclaim_operations),
+#endif
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
 	REG("smaps",      S_IRUGO, proc_pid_smaps_operations),
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index aa2781095bd1..ef2b01533c97 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -209,6 +209,7 @@ struct pde_opener {
 extern const struct inode_operations proc_link_inode_operations;
 
 extern const struct inode_operations proc_pid_link_inode_operations;
+extern const struct file_operations proc_reclaim_operations;
 
 extern void proc_init_inodecache(void);
 extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 67aa7e63a5c1..e003d3d691f7 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/mm_inline.h>
 
 #include <asm/elf.h>
 #include <asm/uaccess.h>
@@ -1429,6 +1430,126 @@ 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 vm_area_struct *vma = walk->private;
+	pte_t *pte, ptent;
+	spinlock_t *ptl;
+	struct page *page;
+	LIST_HEAD(page_list);
+	int isolated;
+
+	split_huge_page_pmd(vma, addr, pmd);
+	if (pmd_trans_unstable(pmd))
+		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++;
+		if (isolated >= SWAP_CLUSTER_MAX)
+			break;
+	}
+	pte_unmap_unlock(pte - 1, ptl);
+	reclaim_pages_from_list(&page_list);
+	if (addr != end)
+		goto cont;
+
+	cond_resched();
+	return 0;
+}
+
+enum reclaim_type {
+	RECLAIM_FILE,
+	RECLAIM_ANON,
+	RECLAIM_ALL,
+	RECLAIM_RANGE,
+};
+
+static ssize_t reclaim_write(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	char buffer[PROC_NUMBUF];
+	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	enum reclaim_type type;
+	char *type_buf;
+
+	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
+		return -EINVAL;
+
+	task = get_proc_task(file->f_path.dentry->d_inode);
+	if (!task)
+		return -ESRCH;
+
+	mm = get_task_mm(task);
+	if (mm) {
+		struct mm_walk reclaim_walk = {
+			.pmd_entry = reclaim_pte_range,
+			.mm = mm,
+		};
+
+		down_read(&mm->mmap_sem);
+		for (vma = mm->mmap; vma; vma = vma->vm_next) {
+			reclaim_walk.private = vma;
+
+			if (is_vm_hugetlb_page(vma))
+				continue;
+
+			if (type == RECLAIM_ANON && vma->vm_file)
+				continue;
+			if (type == RECLAIM_FILE && !vma->vm_file)
+				continue;
+
+			walk_page_range(vma->vm_start, vma->vm_end,
+					&reclaim_walk);
+		}
+		flush_tlb_mm(mm);
+		up_read(&mm->mmap_sem);
+		mmput(mm);
+	}
+	put_task_struct(task);
+
+	return count;
+}
+
+const struct file_operations proc_reclaim_operations = {
+	.write		= reclaim_write,
+	.llseek		= noop_llseek,
+};
+#endif
+
 #ifdef CONFIG_NUMA
 
 struct numa_maps {