[PATCH] vmscan: protect mapped executable pages

Rik van Riel riel at redhat.com
Wed May 6 15:53:37 UTC 2009


This is a follow-up patch by Wu Fengguang to my earlier patch to protect
the active file list.  This provides aggressive protection of mapped
executable pages and should really help desktop performance.


Date: Sun, 3 May 2009 11:15:39 +0800
From: Wu Fengguang <fengguang.wu at intel.com>
To: Andrew Morton <akpm at linux-foundation.org>
Cc: Rik van Riel <riel at redhat.com>, elladan at eskimo.com, peterz at infradead.org,        linux-kernel at vger.kernel.org, tytso at mit.edu,        kosaki.motohiro at jp.fujitsu.com, linux-mm at kvack.org
Subject: Re: [PATCH] vmscan: evict use-once pages first (v2)


Commit 7e9cd484204f(vmscan: fix pagecache reclaim referenced bit check)
tries to address scalability problem when every page get mapped and
referenced, so that logic(which lowed the priority of mapped pages)
could be enabled only on conditions like (priority < DEF_PRIORITY).

Or preferably we can explicitly protect the mapped executables,
as illustrated by this patch (a quick prototype).

Thanks,
Fengguang
---
 include/linux/pagemap.h |    1 +
 mm/mmap.c               |    2 ++
 mm/nommu.c              |    2 ++
 mm/vmscan.c             |   37 +++++++++++++++++++++++++++++++++++--
 4 files changed, 40 insertions(+), 2 deletions(-)

--- linux.orig/include/linux/pagemap.h
+++ linux/include/linux/pagemap.h
@@ -25,6 +25,7 @@ enum mapping_flags {
 #ifdef CONFIG_UNEVICTABLE_LRU
 	AS_UNEVICTABLE	= __GFP_BITS_SHIFT + 3,	/* e.g., ramdisk, SHM_LOCK */
 #endif
+	AS_EXEC		= __GFP_BITS_SHIFT + 4,	/* mapped PROT_EXEC somewhere */
 };
 
 static inline void mapping_set_error(struct address_space *mapping, int error)
--- linux.orig/mm/mmap.c
+++ linux/mm/mmap.c
@@ -1198,6 +1198,8 @@ munmap_back:
 			goto unmap_and_free_vma;
 		if (vm_flags & VM_EXECUTABLE)
 			added_exe_file_vma(mm);
+		if (vm_flags & VM_EXEC)
+			set_bit(AS_EXEC, &file->f_mapping->flags);
 	} else if (vm_flags & VM_SHARED) {
 		error = shmem_zero_setup(vma);
 		if (error)
--- linux.orig/mm/vmscan.c
+++ linux/mm/vmscan.c
@@ -1220,6 +1220,7 @@ static void shrink_active_list(unsigned 
 	int pgdeactivate = 0;
 	unsigned long pgscanned;
 	LIST_HEAD(l_hold);	/* The pages which were snipped off */
+	LIST_HEAD(l_active);
 	LIST_HEAD(l_inactive);
 	struct page *page;
 	struct pagevec pvec;
@@ -1259,8 +1260,15 @@ static void shrink_active_list(unsigned 
 
 		/* page_referenced clears PageReferenced */
 		if (page_mapping_inuse(page) &&
-		    page_referenced(page, 0, sc->mem_cgroup))
+		    page_referenced(page, 0, sc->mem_cgroup)) {
+			struct address_space *mapping = page_mapping(page);
+
 			pgmoved++;
+			if (mapping && test_bit(AS_EXEC, &mapping->flags)) {
+				list_add(&page->lru, &l_active);
+				continue;
+			}
+		}
 
 		list_add(&page->lru, &l_inactive);
 	}
@@ -1269,7 +1277,6 @@ static void shrink_active_list(unsigned 
 	 * Move the pages to the [file or anon] inactive list.
 	 */
 	pagevec_init(&pvec, 1);
-	lru = LRU_BASE + file * LRU_FILE;
 
 	spin_lock_irq(&zone->lru_lock);
 	/*
@@ -1281,6 +1288,7 @@ static void shrink_active_list(unsigned 
 	reclaim_stat->recent_rotated[!!file] += pgmoved;
 
 	pgmoved = 0;
+	lru = LRU_BASE + file * LRU_FILE;
 	while (!list_empty(&l_inactive)) {
 		page = lru_to_page(&l_inactive);
 		prefetchw_prev_lru_page(page, &l_inactive, flags);
@@ -1305,6 +1313,31 @@ static void shrink_active_list(unsigned 
 	}
 	__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
 	pgdeactivate += pgmoved;
+
+	pgmoved = 0;
+	lru = LRU_ACTIVE + file * LRU_FILE;
+	while (!list_empty(&l_active)) {
+		page = lru_to_page(&l_active);
+		prefetchw_prev_lru_page(page, &l_active, flags);
+		VM_BUG_ON(PageLRU(page));
+		SetPageLRU(page);
+		VM_BUG_ON(!PageActive(page));
+
+		list_move(&page->lru, &zone->lru[lru].list);
+		mem_cgroup_add_lru_list(page, lru);
+		pgmoved++;
+		if (!pagevec_add(&pvec, page)) {
+			__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
+			pgmoved = 0;
+			spin_unlock_irq(&zone->lru_lock);
+			if (buffer_heads_over_limit)
+				pagevec_strip(&pvec);
+			__pagevec_release(&pvec);
+			spin_lock_irq(&zone->lru_lock);
+		}
+	}
+	__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
+
 	__count_zone_vm_events(PGREFILL, zone, pgscanned);
 	__count_vm_events(PGDEACTIVATE, pgdeactivate);
 	spin_unlock_irq(&zone->lru_lock);
--- linux.orig/mm/nommu.c
+++ linux/mm/nommu.c
@@ -1220,6 +1220,8 @@ unsigned long do_mmap_pgoff(struct file 
 			added_exe_file_vma(current->mm);
 			vma->vm_mm = current->mm;
 		}
+		if (vm_flags & VM_EXEC)
+			set_bit(AS_EXEC, &file->f_mapping->flags);
 	}
 
 	down_write(&nommu_region_sem);


-- 
All Rights Reversed




More information about the kernel mailing list