mm: add dirty_background_bytes and dirty_bytes sysctls

This change introduces two new sysctls to /proc/sys/vm:
dirty_background_bytes and dirty_bytes.

dirty_background_bytes is the counterpart to dirty_background_ratio and
dirty_bytes is the counterpart to dirty_ratio.

With growing memory capacities of individual machines, it's no longer
sufficient to specify dirty thresholds as a percentage of the amount of
dirtyable memory over the entire system.

dirty_background_bytes and dirty_bytes specify quantities of memory, in
bytes, that represent the dirty limits for the entire system.  If either
of these values is set, its value represents the amount of dirty memory
that is needed to commence either background or direct writeback.

When a `bytes' or `ratio' file is written, its counterpart becomes a
function of the written value.  For example, if dirty_bytes is written to
be 8096, 8K of memory is required to commence direct writeback.
dirty_ratio is then functionally equivalent to 8K / the amount of
dirtyable memory:

	dirtyable_memory = free pages + mapped pages + file cache

	dirty_background_bytes = dirty_background_ratio * dirtyable_memory
		-or-
	dirty_background_ratio = dirty_background_bytes / dirtyable_memory

		AND

	dirty_bytes = dirty_ratio * dirtyable_memory
		-or-
	dirty_ratio = dirty_bytes / dirtyable_memory

Only one of dirty_background_bytes and dirty_background_ratio may be
specified at a time, and only one of dirty_bytes and dirty_ratio may be
specified.  When one sysctl is written, the other appears as 0 when read.

The `bytes' files operate on a page size granularity since dirty limits
are compared with ZVC values, which are in page units.

Prior to this change, the minimum dirty_ratio was 5 as implemented by
get_dirty_limits() although /proc/sys/vm/dirty_ratio would show any user
written value between 0 and 100.  This restriction is maintained, but
dirty_bytes has a lower limit of only one page.

Also prior to this change, the dirty_background_ratio could not equal or
exceed dirty_ratio.  This restriction is maintained in addition to
restricting dirty_background_bytes.  If either background threshold equals
or exceeds that of the dirty threshold, it is implicitly set to half the
dirty threshold.

Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Andrea Righi <righi.andrea@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 22 insertions, 5 deletions

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index ff6d45c7626f..92f6e5bc3c24 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -87,10 +87,6 @@ extern int rcutorture_runnable;
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 /* Constants used for minimum and  maximum */
-#if defined(CONFIG_HIGHMEM) || defined(CONFIG_DETECT_SOFTLOCKUP)
-static int one = 1;
-#endif
-
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 static int sixty = 60;
 static int neg_one = -1;
@@ -101,6 +97,7 @@ static int two = 2;
 #endif
 
 static int zero;
+static int one = 1;
 static int one_hundred = 100;
 
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
@@ -952,12 +949,22 @@ static struct ctl_table vm_table[] = {
 		.data		= &dirty_background_ratio,
 		.maxlen		= sizeof(dirty_background_ratio),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
+		.proc_handler	= &dirty_background_ratio_handler,
 		.strategy	= &sysctl_intvec,
 		.extra1		= &zero,
 		.extra2		= &one_hundred,
 	},
 	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "dirty_background_bytes",
+		.data		= &dirty_background_bytes,
+		.maxlen		= sizeof(dirty_background_bytes),
+		.mode		= 0644,
+		.proc_handler	= &dirty_background_bytes_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &one,
+	},
+	{
 		.ctl_name	= VM_DIRTY_RATIO,
 		.procname	= "dirty_ratio",
 		.data		= &vm_dirty_ratio,
@@ -969,6 +976,16 @@ static struct ctl_table vm_table[] = {
 		.extra2		= &one_hundred,
 	},
 	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "dirty_bytes",
+		.data		= &vm_dirty_bytes,
+		.maxlen		= sizeof(vm_dirty_bytes),
+		.mode		= 0644,
+		.proc_handler	= &dirty_bytes_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &one,
+	},
+	{
 		.procname	= "dirty_writeback_centisecs",
 		.data		= &dirty_writeback_interval,
 		.maxlen		= sizeof(dirty_writeback_interval),