Commit 45c7f7e1 authored by Chris Down's avatar Chris Down Committed by Linus Torvalds

mm, memcg: decouple e{low,min} state mutations from protection checks

mem_cgroup_protected currently is both used to set effective low and min
and return a mem_cgroup_protection based on the result.  As a user, this
can be a little unexpected: it appears to be a simple predicate function,
if not for the big warning in the comment above about the order in which
it must be executed.

This change makes it so that we separate the state mutations from the
actual protection checks, which makes it more obvious where we need to be
careful mutating internal state, and where we are simply checking and
don't need to worry about that.

[mhocko@suse.com - don't check protection on root memcgs]
Suggested-by: default avatarJohannes Weiner <hannes@cmpxchg.org>
Signed-off-by: default avatarChris Down <chris@chrisdown.name>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Acked-by: default avatarJohannes Weiner <hannes@cmpxchg.org>
Acked-by: default avatarMichal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Link: http://lkml.kernel.org/r/ff3f915097fcee9f6d7041c084ef92d16aaeb56a.1594638158.git.chris@chrisdown.nameSigned-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 22f7496f
...@@ -47,12 +47,6 @@ enum memcg_memory_event { ...@@ -47,12 +47,6 @@ enum memcg_memory_event {
MEMCG_NR_MEMORY_EVENTS, MEMCG_NR_MEMORY_EVENTS,
}; };
enum mem_cgroup_protection {
MEMCG_PROT_NONE,
MEMCG_PROT_LOW,
MEMCG_PROT_MIN,
};
struct mem_cgroup_reclaim_cookie { struct mem_cgroup_reclaim_cookie {
pg_data_t *pgdat; pg_data_t *pgdat;
unsigned int generation; unsigned int generation;
...@@ -405,9 +399,37 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, ...@@ -405,9 +399,37 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
READ_ONCE(memcg->memory.elow)); READ_ONCE(memcg->memory.elow));
} }
enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, void mem_cgroup_calculate_protection(struct mem_cgroup *root,
struct mem_cgroup *memcg); struct mem_cgroup *memcg);
static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg)
{
/*
* The root memcg doesn't account charges, and doesn't support
* protection.
*/
return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg);
}
static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
{
if (!mem_cgroup_supports_protection(memcg))
return false;
return READ_ONCE(memcg->memory.elow) >=
page_counter_read(&memcg->memory);
}
static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
{
if (!mem_cgroup_supports_protection(memcg))
return false;
return READ_ONCE(memcg->memory.emin) >=
page_counter_read(&memcg->memory);
}
int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask);
void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge(struct page *page);
...@@ -935,10 +957,19 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, ...@@ -935,10 +957,19 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
return 0; return 0;
} }
static inline enum mem_cgroup_protection mem_cgroup_protected( static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root,
struct mem_cgroup *root, struct mem_cgroup *memcg) struct mem_cgroup *memcg)
{ {
return MEMCG_PROT_NONE; }
static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
{
return false;
}
static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
{
return false;
} }
static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
......
...@@ -6587,21 +6587,15 @@ static unsigned long effective_protection(unsigned long usage, ...@@ -6587,21 +6587,15 @@ static unsigned long effective_protection(unsigned long usage,
* *
* WARNING: This function is not stateless! It can only be used as part * WARNING: This function is not stateless! It can only be used as part
* of a top-down tree iteration, not for isolated queries. * of a top-down tree iteration, not for isolated queries.
*
* Returns one of the following:
* MEMCG_PROT_NONE: cgroup memory is not protected
* MEMCG_PROT_LOW: cgroup memory is protected as long there is
* an unprotected supply of reclaimable memory from other cgroups.
* MEMCG_PROT_MIN: cgroup memory is protected
*/ */
enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, void mem_cgroup_calculate_protection(struct mem_cgroup *root,
struct mem_cgroup *memcg) struct mem_cgroup *memcg)
{ {
unsigned long usage, parent_usage; unsigned long usage, parent_usage;
struct mem_cgroup *parent; struct mem_cgroup *parent;
if (mem_cgroup_disabled()) if (mem_cgroup_disabled())
return MEMCG_PROT_NONE; return;
if (!root) if (!root)
root = root_mem_cgroup; root = root_mem_cgroup;
...@@ -6614,21 +6608,21 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, ...@@ -6614,21 +6608,21 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
* that special casing. * that special casing.
*/ */
if (memcg == root) if (memcg == root)
return MEMCG_PROT_NONE; return;
usage = page_counter_read(&memcg->memory); usage = page_counter_read(&memcg->memory);
if (!usage) if (!usage)
return MEMCG_PROT_NONE; return;
parent = parent_mem_cgroup(memcg); parent = parent_mem_cgroup(memcg);
/* No parent means a non-hierarchical mode on v1 memcg */ /* No parent means a non-hierarchical mode on v1 memcg */
if (!parent) if (!parent)
return MEMCG_PROT_NONE; return;
if (parent == root) { if (parent == root) {
memcg->memory.emin = READ_ONCE(memcg->memory.min); memcg->memory.emin = READ_ONCE(memcg->memory.min);
memcg->memory.elow = READ_ONCE(memcg->memory.low); memcg->memory.elow = READ_ONCE(memcg->memory.low);
goto out; return;
} }
parent_usage = page_counter_read(&parent->memory); parent_usage = page_counter_read(&parent->memory);
...@@ -6642,14 +6636,6 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, ...@@ -6642,14 +6636,6 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
READ_ONCE(memcg->memory.low), READ_ONCE(memcg->memory.low),
READ_ONCE(parent->memory.elow), READ_ONCE(parent->memory.elow),
atomic_long_read(&parent->memory.children_low_usage))); atomic_long_read(&parent->memory.children_low_usage)));
out:
if (usage <= memcg->memory.emin)
return MEMCG_PROT_MIN;
else if (usage <= memcg->memory.elow)
return MEMCG_PROT_LOW;
else
return MEMCG_PROT_NONE;
} }
/** /**
......
...@@ -2620,14 +2620,15 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) ...@@ -2620,14 +2620,15 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
unsigned long reclaimed; unsigned long reclaimed;
unsigned long scanned; unsigned long scanned;
switch (mem_cgroup_protected(target_memcg, memcg)) { mem_cgroup_calculate_protection(target_memcg, memcg);
case MEMCG_PROT_MIN:
if (mem_cgroup_below_min(memcg)) {
/* /*
* Hard protection. * Hard protection.
* If there is no reclaimable memory, OOM. * If there is no reclaimable memory, OOM.
*/ */
continue; continue;
case MEMCG_PROT_LOW: } else if (mem_cgroup_below_low(memcg)) {
/* /*
* Soft protection. * Soft protection.
* Respect the protection only as long as * Respect the protection only as long as
...@@ -2639,16 +2640,6 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) ...@@ -2639,16 +2640,6 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
continue; continue;
} }
memcg_memory_event(memcg, MEMCG_LOW); memcg_memory_event(memcg, MEMCG_LOW);
break;
case MEMCG_PROT_NONE:
/*
* All protection thresholds breached. We may
* still choose to vary the scan pressure
* applied based on by how much the cgroup in
* question has exceeded its protection
* thresholds (see get_scan_count).
*/
break;
} }
reclaimed = sc->nr_reclaimed; reclaimed = sc->nr_reclaimed;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment