From: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxxx>
Since balancing mode was added in
bda420b98505 ("numa balancing: migrate on fault among multiple bound nodes"),
it was possible to set this mode but it wouldn't be shown in
/proc/<pid>/numa_maps since there was no support for it in the
mpol_to_str() helper.
Furthermore, because the balancing mode sets the MPOL_F_MORON flag, it
would be displayed as 'default' due a workaround introduced a few years
earlier in
8790c71a18e5 ("mm/mempolicy.c: fix mempolicy printing in numa_maps").
To tidy this up we implement two changes:
First we introduce a new internal flag MPOL_F_KERNEL and with it mark the
kernel's internal default and fallback policies (for tasks and/or VMAs
with no explicit policy set). By doing this we generalise the current
special casing and replace the incorrect 'default' with the correct
'bind'.
Secondly, we add a string representation and corresponding handling for
MPOL_F_NUMA_BALANCING. We do this by adding a sparse mapping array of
flags to names. With the sparseness being the downside, but with the
advantage of generalising and removing the "policy" from flags display.
End result:
$ numactl -b -m 0-1,3 cat /proc/self/numa_maps
555559580000 bind=balancing:0-1,3 file=/usr/bin/cat mapped=3 active=0 N0=3 kernelpagesize_kB=16
...
v2:
* Fully fix by introducing MPOL_F_KERNEL.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@xxxxxxxxxx>
Fixes: bda420b98505 ("numa balancing: migrate on fault among multiple bound nodes")
References: 8790c71a18e5 ("mm/mempolicy.c: fix mempolicy printing in numa_maps")
Cc: Huang Ying <ying.huang@xxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
---
include/uapi/linux/mempolicy.h | 1 +
mm/mempolicy.c | 44 ++++++++++++++++++++++++----------
2 files changed, 32 insertions(+), 13 deletions(-)
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 1f9bb10d1a47..bcf56ce9603b 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -64,6 +64,7 @@ enum {
#define MPOL_F_SHARED (1 << 0) /* identify shared policies */
#define MPOL_F_MOF (1 << 3) /* this policy wants migrate on fault */
#define MPOL_F_MORON (1 << 4) /* Migrate On protnone Reference On Node */
+#define MPOL_F_KERNEL (1 << 5) /* Kernel's internal policy */
/*
* These bit locations are exposed in the vm.zone_reclaim_mode sysctl
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index aec756ae5637..8ecc6d9f100a 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -134,6 +134,7 @@ enum zone_type policy_zone = 0;
static struct mempolicy default_policy = {
.refcnt = ATOMIC_INIT(1), /* never free it */
.mode = MPOL_LOCAL,
+ .flags = MPOL_F_KERNEL,
};
static struct mempolicy preferred_node_policy[MAX_NUMNODES];
@@ -3095,7 +3096,7 @@ void __init numa_policy_init(void)
preferred_node_policy[nid] = (struct mempolicy) {
.refcnt = ATOMIC_INIT(1),
.mode = MPOL_PREFERRED,
- .flags = MPOL_F_MOF | MPOL_F_MORON,
+ .flags = MPOL_F_MOF | MPOL_F_MORON | MPOL_F_KERNEL,
.nodes = nodemask_of_node(nid),
};
}
@@ -3150,6 +3151,12 @@ static const char * const policy_modes[] =
[MPOL_PREFERRED_MANY] = "prefer (many)",
};
+static const char * const policy_flags[] = {
+ [ilog2(MPOL_F_STATIC_NODES)] = "static",
+ [ilog2(MPOL_F_RELATIVE_NODES)] = "relative",
+ [ilog2(MPOL_F_NUMA_BALANCING)] = "balancing",
+};
+
#ifdef CONFIG_TMPFS
/**
* mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option.
@@ -3293,17 +3300,18 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
* @pol: pointer to mempolicy to be formatted
*
* Convert @pol into a string. If @buffer is too short, truncate the string.
- * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the
- * longest flag, "relative", and to display at least a few node ids.
+ * Recommend a @maxlen of at least 42 for the longest mode, "weighted
+ * interleave", the longest flag, "balancing", and to display at least a few
+ * node ids.
*/
void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
{
char *p = buffer;
nodemask_t nodes = NODE_MASK_NONE;
unsigned short mode = MPOL_DEFAULT;
- unsigned short flags = 0;
+ unsigned long flags = 0;
- if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) {
+ if (!(pol->flags & MPOL_F_KERNEL)) {
mode = pol->mode;
flags = pol->flags;
}
@@ -3328,15 +3336,25 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
p += snprintf(p, maxlen, "%s", policy_modes[mode]);
if (flags & MPOL_MODE_FLAGS) {
- p += snprintf(p, buffer + maxlen - p, "=");
+ unsigned int bit, cnt = 0;
- /*
- * Currently, the only defined flags are mutually exclusive
- */
- if (flags & MPOL_F_STATIC_NODES)
- p += snprintf(p, buffer + maxlen - p, "static");
- else if (flags & MPOL_F_RELATIVE_NODES)
- p += snprintf(p, buffer + maxlen - p, "relative");
+ for_each_set_bit(bit, &flags, ARRAY_SIZE(policy_flags)) {
+ if (bit <= ilog2(MPOL_F_KERNEL))
+ continue;
+
+ if (cnt == 0)
+ p += snprintf(p, buffer + maxlen - p, "=");
+ else
+ p += snprintf(p, buffer + maxlen - p, ",");
+
+ if (WARN_ON_ONCE(!policy_flags[bit]))
+ p += snprintf(p, buffer + maxlen - p, "bit%u",
+ bit);
+ else
+ p += snprintf(p, buffer + maxlen - p,
+ policy_flags[bit]);
+ cnt++;
+ }
}
if (!nodes_empty(nodes))
--
2.44.0
