[PATCH v2 5/6] mm: Support address range reclaim

[Minchan Kim]

This patch adds address range reclaim of a process.
The requirement is following as,

Like webkit1, it uses a address space for handling multi tabs.
IOW, it uses *one* process model so all tabs shares address space
of the process. In such scenario, per-process reclaim is rather
coarse-grained so this patch supports more fine-grained reclaim
for being able to reclaim target address range of the process.
For reclaim target range, you should use following format.

	echo [addr] [size-byte] > /proc/pid/reclaim

addr should be page-aligned.

So now reclaim konb's interface is following as.

echo file > /proc/pid/reclaim
	reclaim file-backed pages only

echo anon > /proc/pid/reclaim
	reclaim anonymous pages only

echo all > /proc/pid/reclaim
	reclaim all pages

echo $((1<<20)) 8192 > /proc/pid/reclaim
	reclaim pages in (0x100000 - 0x102000)

Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
---
 fs/proc/task_mmu.c | 88 ++++++++++++++++++++++++++++++++++++++++++++----------
 mm/internal.h      |  3 ++
 2 files changed, 76 insertions(+), 15 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 79b674e..dff9756 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -12,6 +12,7 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/mm_inline.h>
+#include <linux/ctype.h>
 
 #include <asm/elf.h>
 #include <asm/uaccess.h>
@@ -1239,11 +1240,14 @@ 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];
+	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;
 
 	memset(buffer, 0, sizeof(buffer));
 	if (count > sizeof(buffer) - 1)
@@ -1259,42 +1263,96 @@ static ssize_t reclaim_write(struct file *file, const char __user *buf,
 		type = RECLAIM_ANON;
 	else if (!strcmp(type_buf, "all"))
 		type = RECLAIM_ALL;
+	else if (isdigit(*type_buf))
+		type = RECLAIM_RANGE;
 	else
-		return -EINVAL;
+		goto out_err;
+
+	if (type == RECLAIM_RANGE) {
+		int ret;
+		size_t len;
+		unsigned long len_in;
+		char *token;
+
+		token = strsep(&type_buf, " ");
+		if (!token)
+			goto out_err;
+		ret = kstrtoul(token, 10, &start);
+		if (ret < 0 || (start & ~PAGE_MASK))
+			goto out_err;
+
+		token = strsep(&type_buf, " ");
+		if (!token)
+			goto out_err;
+		ret = kstrtoul(token, 10, &len_in);
+		if (ret < 0)
+			goto out_err;
+
+		len = (len_in + ~PAGE_MASK) & PAGE_MASK;
+		/*
+		 * 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) {
-		struct mm_walk reclaim_walk = {
-			.pmd_entry = reclaim_pte_range,
-			.mm = mm,
-		};
+	if (!mm)
+		goto out;
 
-		down_read(&mm->mmap_sem);
-		for (vma = mm->mmap; vma; vma = vma->vm_next) {
-			reclaim_walk.private = vma;
+	reclaim_walk.mm = mm;
+	reclaim_walk.pmd_entry = reclaim_pte_range;
 
+	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;
+
+			reclaim_walk.private = 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;
 
+			reclaim_walk.private = vma;
 			walk_page_range(vma->vm_start, vma->vm_end,
-					&reclaim_walk);
+				&reclaim_walk);
 		}
-		flush_tlb_mm(mm);
-		up_read(&mm->mmap_sem);
-		mmput(mm);
 	}
-	put_task_struct(task);
 
+	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 = {
diff --git a/mm/internal.h b/mm/internal.h
index 589a29b..1f7ce8f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -85,6 +85,9 @@ static inline void get_page_foll(struct page *page)
 
 extern unsigned long highest_memmap_pfn;
 
+extern int isolate_lru_page(struct page *page);
+extern void putback_lru_page(struct page *page);
+
 /*
  * in mm/rmap.c:
  */
-- 
1.8.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/