mm: Per process reclaim

These day, there are many platforms available 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 background 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: merge conflict fixes]
Signed-off-by: Vinayak Menon <vinmenon@codeaurora.org>

fs/proc/base.c

@@ -3237,6 +3237,9 @@ 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", 0200, 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),

fs/proc/internal.h

@@ -205,6 +205,7 @@ 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 super_operations proc_sops;
+extern const struct file_operations proc_reclaim_operations;
 
 void proc_init_kmemcache(void);
 void set_proc_pid_nlink(void);

fs/proc/task_mmu.c

@@ -19,6 +19,7 @@
 #include <linux/shmem_fs.h>
 #include <linux/uaccess.h>
 #include <linux/pkeys.h>
+#include <linux/mm_inline.h>
 
 #include <asm/elf.h>
 #include <asm/tlb.h>
@@ -1708,6 +1709,124 @@ 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_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_node_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) {
+		const struct mm_walk_ops reclaim_walk_ops = {
+			.pmd_entry = reclaim_pte_range,
+		};
+
+		down_read(&mm->mmap_sem);
+		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;
+
+			walk_page_range(mm, vma->vm_start, vma->vm_end,
+					&reclaim_walk_ops, vma);
+		}
+		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 {

include/linux/rmap.h

@@ -12,6 +12,10 @@
 #include <linux/memcontrol.h>
 #include <linux/highmem.h>
 
+extern int isolate_lru_page(struct page *page);
+extern void putback_lru_page(struct page *page);
+extern unsigned long reclaim_pages_from_list(struct list_head *page_list);
+
 /*
  * The anon_vma heads a list of private "related" vmas, to scan if
  * an anonymous page pointing to this anon_vma needs to be unmapped:

mm/Kconfig

@@ -832,3 +832,17 @@ config OOM_TASK_PRIORITY_ADJ_LIMIT
 	  before considering tasks with a lower oom_score_adj value.
 
 endmenu
+
+config PROCESS_RECLAIM
+	bool "Enable process reclaim"
+	depends on PROC_FS
+	depends on QGKI
+	default y
+	help
+	 It allows to reclaim pages of the process by /proc/pid/reclaim.
+
+	 (echo file > /proc/PID/reclaim) reclaims file-backed pages only.
+	 (echo anon > /proc/PID/reclaim) reclaims anonymous pages only.
+	 (echo all > /proc/PID/reclaim) reclaims all pages.
+
+	 Any other value is ignored.

mm/vmscan.c

@@ -1565,6 +1565,62 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 	return ret;
 }
 
+#ifdef CONFIG_PROCESS_RECLAIM
+static unsigned long shrink_page(struct page *page,
+					struct zone *zone,
+					struct scan_control *sc,
+					enum ttu_flags ttu_flags,
+					bool force_reclaim,
+					struct list_head *ret_pages)
+{
+	int reclaimed;
+	LIST_HEAD(page_list);
+
+	list_add(&page->lru, &page_list);
+
+	reclaimed = shrink_page_list(&page_list, zone->zone_pgdat, sc,
+				ttu_flags, NULL, force_reclaim);
+	if (!reclaimed)
+		list_splice(&page_list, ret_pages);
+
+	return reclaimed;
+}
+
+unsigned long reclaim_pages_from_list(struct list_head *page_list)
+{
+	struct scan_control sc = {
+		.gfp_mask = GFP_KERNEL,
+		.priority = DEF_PRIORITY,
+		.may_writepage = 1,
+		.may_unmap = 1,
+		.may_swap = 1,
+	};
+
+	LIST_HEAD(ret_pages);
+	struct page *page;
+	unsigned long nr_reclaimed = 0;
+
+	while (!list_empty(page_list)) {
+		page = lru_to_page(page_list);
+		list_del(&page->lru);
+
+		ClearPageActive(page);
+		nr_reclaimed += shrink_page(page, page_zone(page), &sc,
+			TTU_IGNORE_ACCESS, true, &ret_pages);
+	}
+
+	while (!list_empty(&ret_pages)) {
+		page = lru_to_page(&ret_pages);
+		list_del(&page->lru);
+		dec_node_page_state(page, NR_ISOLATED_ANON +
+				page_is_file_cache(page));
+		putback_lru_page(page);
+	}
+
+	return nr_reclaimed;
+}
+#endif
+
 /*
  * Attempt to remove the specified page from its LRU.  Only take this page
  * if it is of the appropriate PageActive status.  Pages which are being