| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1287177279-30876-12-git-send-email-gthelen@google.com>
Date: Fri, 15 Oct 2010 14:14:39 -0700
From: Greg Thelen <gthelen@...gle.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: linux-kernel@...r.kernel.org, linux-mm@...ck.org,
containers@...ts.osdl.org, Andrea Righi <arighi@...eler.com>,
Balbir Singh <balbir@...ux.vnet.ibm.com>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>,
Daisuke Nishimura <nishimura@....nes.nec.co.jp>,
Minchan Kim <minchan.kim@...il.com>,
Ciju Rajan K <ciju@...ux.vnet.ibm.com>,
David Rientjes <rientjes@...gle.com>,
Greg Thelen <gthelen@...gle.com>
Subject: [PATCH v2 11/11] memcg: check memcg dirty limits in page writeback
If the current process is in a non-root memcg, then
global_dirty_limits() will consider the memcg dirty limit.
This allows different cgroups to have distinct dirty limits
which trigger direct and background writeback at different
levels.
Signed-off-by: Andrea Righi <arighi@...eler.com>
Signed-off-by: Greg Thelen <gthelen@...gle.com>
---
mm/page-writeback.c | 89 +++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 73 insertions(+), 16 deletions(-)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index a0bb3e2..9b34f01 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -180,7 +180,7 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
* Returns the numebr of pages that can currently be freed and used
* by the kernel for direct mappings.
*/
-static unsigned long determine_dirtyable_memory(void)
+static unsigned long global_dirtyable_memory(void)
{
unsigned long x;
@@ -192,6 +192,58 @@ static unsigned long determine_dirtyable_memory(void)
return x + 1; /* Ensure that we never return 0 */
}
+static unsigned long dirtyable_memory(void)
+{
+ unsigned long memory;
+ s64 memcg_memory;
+
+ memory = global_dirtyable_memory();
+ if (!mem_cgroup_has_dirty_limit())
+ return memory;
+ memcg_memory = mem_cgroup_page_stat(MEMCG_NR_DIRTYABLE_PAGES);
+ BUG_ON(memcg_memory < 0);
+
+ return min((unsigned long)memcg_memory, memory);
+}
+
+static long reclaimable_pages(void)
+{
+ s64 ret;
+
+ if (!mem_cgroup_has_dirty_limit())
+ return global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS);
+ ret = mem_cgroup_page_stat(MEMCG_NR_RECLAIM_PAGES);
+ BUG_ON(ret < 0);
+
+ return ret;
+}
+
+static long writeback_pages(void)
+{
+ s64 ret;
+
+ if (!mem_cgroup_has_dirty_limit())
+ return global_page_state(NR_WRITEBACK);
+ ret = mem_cgroup_page_stat(MEMCG_NR_WRITEBACK);
+ BUG_ON(ret < 0);
+
+ return ret;
+}
+
+static unsigned long dirty_writeback_pages(void)
+{
+ s64 ret;
+
+ if (!mem_cgroup_has_dirty_limit())
+ return global_page_state(NR_UNSTABLE_NFS) +
+ global_page_state(NR_WRITEBACK);
+ ret = mem_cgroup_page_stat(MEMCG_NR_DIRTY_WRITEBACK_PAGES);
+ BUG_ON(ret < 0);
+
+ return ret;
+}
+
/*
* couple the period to the dirty_ratio:
*
@@ -204,8 +256,8 @@ static int calc_period_shift(void)
if (vm_dirty_bytes)
dirty_total = vm_dirty_bytes / PAGE_SIZE;
else
- dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) /
- 100;
+ dirty_total = (vm_dirty_ratio * global_dirtyable_memory()) /
+ 100;
return 2 + ilog2(dirty_total - 1);
}
@@ -410,18 +462,23 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
{
unsigned long background;
unsigned long dirty;
- unsigned long available_memory = determine_dirtyable_memory();
+ unsigned long available_memory = dirtyable_memory();
struct task_struct *tsk;
+ struct vm_dirty_param dirty_param;
- if (vm_dirty_bytes)
- dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
+ vm_dirty_param(&dirty_param);
+
+ if (dirty_param.dirty_bytes)
+ dirty = DIV_ROUND_UP(dirty_param.dirty_bytes, PAGE_SIZE);
else
- dirty = (vm_dirty_ratio * available_memory) / 100;
+ dirty = (dirty_param.dirty_ratio * available_memory) / 100;
- if (dirty_background_bytes)
- background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
+ if (dirty_param.dirty_background_bytes)
+ background = DIV_ROUND_UP(dirty_param.dirty_background_bytes,
+ PAGE_SIZE);
else
- background = (dirty_background_ratio * available_memory) / 100;
+ background = (dirty_param.dirty_background_ratio *
+ available_memory) / 100;
if (background >= dirty)
background = dirty / 2;
@@ -493,9 +550,8 @@ static void balance_dirty_pages(struct address_space *mapping,
.range_cyclic = 1,
};
- nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
- nr_writeback = global_page_state(NR_WRITEBACK);
+ nr_reclaimable = reclaimable_pages();
+ nr_writeback = writeback_pages();
global_dirty_limits(&background_thresh, &dirty_thresh);
@@ -652,6 +708,7 @@ void throttle_vm_writeout(gfp_t gfp_mask)
{
unsigned long background_thresh;
unsigned long dirty_thresh;
+ unsigned long dirty;
for ( ; ; ) {
global_dirty_limits(&background_thresh, &dirty_thresh);
@@ -662,9 +719,9 @@ void throttle_vm_writeout(gfp_t gfp_mask)
*/
dirty_thresh += dirty_thresh / 10; /* wheeee... */
- if (global_page_state(NR_UNSTABLE_NFS) +
- global_page_state(NR_WRITEBACK) <= dirty_thresh)
- break;
+ dirty = dirty_writeback_pages();
+ if (dirty <= dirty_thresh)
+ break;
congestion_wait(BLK_RW_ASYNC, HZ/10);
/*
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists