mm/page_counter: move calculating protection values to page_counter

It's a lot of math, and there is nothing memcontrol specific about it. 
This makes it easier to use inside of the drm cgroup controller.

[akpm@linux-foundation.org: fix kerneldoc, per Jeff Johnson]
Link: https://lkml.kernel.org/r/20240703112510.36424-1-maarten.lankhorst@linux.intel.com
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 173 insertions, 0 deletions

diff --git a/mm/page_counter.c b/mm/page_counter.c
index db20d6452b71..0153f5bb3161 100644
--- a/mm/page_counter.c
+++ b/mm/page_counter.c
@@ -262,3 +262,176 @@ int page_counter_memparse(const char *buf, const char *max,
 
 	return 0;
 }
+
+
+/*
+ * This function calculates an individual page counter's effective
+ * protection which is derived from its own memory.min/low, its
+ * parent's and siblings' settings, as well as the actual memory
+ * distribution in the tree.
+ *
+ * The following rules apply to the effective protection values:
+ *
+ * 1. At the first level of reclaim, effective protection is equal to
+ *    the declared protection in memory.min and memory.low.
+ *
+ * 2. To enable safe delegation of the protection configuration, at
+ *    subsequent levels the effective protection is capped to the
+ *    parent's effective protection.
+ *
+ * 3. To make complex and dynamic subtrees easier to configure, the
+ *    user is allowed to overcommit the declared protection at a given
+ *    level. If that is the case, the parent's effective protection is
+ *    distributed to the children in proportion to how much protection
+ *    they have declared and how much of it they are utilizing.
+ *
+ *    This makes distribution proportional, but also work-conserving:
+ *    if one counter claims much more protection than it uses memory,
+ *    the unused remainder is available to its siblings.
+ *
+ * 4. Conversely, when the declared protection is undercommitted at a
+ *    given level, the distribution of the larger parental protection
+ *    budget is NOT proportional. A counter's protection from a sibling
+ *    is capped to its own memory.min/low setting.
+ *
+ * 5. However, to allow protecting recursive subtrees from each other
+ *    without having to declare each individual counter's fixed share
+ *    of the ancestor's claim to protection, any unutilized -
+ *    "floating" - protection from up the tree is distributed in
+ *    proportion to each counter's *usage*. This makes the protection
+ *    neutral wrt sibling cgroups and lets them compete freely over
+ *    the shared parental protection budget, but it protects the
+ *    subtree as a whole from neighboring subtrees.
+ *
+ * Note that 4. and 5. are not in conflict: 4. is about protecting
+ * against immediate siblings whereas 5. is about protecting against
+ * neighboring subtrees.
+ */
+static unsigned long effective_protection(unsigned long usage,
+					  unsigned long parent_usage,
+					  unsigned long setting,
+					  unsigned long parent_effective,
+					  unsigned long siblings_protected,
+					  bool recursive_protection)
+{
+	unsigned long protected;
+	unsigned long ep;
+
+	protected = min(usage, setting);
+	/*
+	 * If all cgroups at this level combined claim and use more
+	 * protection than what the parent affords them, distribute
+	 * shares in proportion to utilization.
+	 *
+	 * We are using actual utilization rather than the statically
+	 * claimed protection in order to be work-conserving: claimed
+	 * but unused protection is available to siblings that would
+	 * otherwise get a smaller chunk than what they claimed.
+	 */
+	if (siblings_protected > parent_effective)
+		return protected * parent_effective / siblings_protected;
+
+	/*
+	 * Ok, utilized protection of all children is within what the
+	 * parent affords them, so we know whatever this child claims
+	 * and utilizes is effectively protected.
+	 *
+	 * If there is unprotected usage beyond this value, reclaim
+	 * will apply pressure in proportion to that amount.
+	 *
+	 * If there is unutilized protection, the cgroup will be fully
+	 * shielded from reclaim, but we do return a smaller value for
+	 * protection than what the group could enjoy in theory. This
+	 * is okay. With the overcommit distribution above, effective
+	 * protection is always dependent on how memory is actually
+	 * consumed among the siblings anyway.
+	 */
+	ep = protected;
+
+	/*
+	 * If the children aren't claiming (all of) the protection
+	 * afforded to them by the parent, distribute the remainder in
+	 * proportion to the (unprotected) memory of each cgroup. That
+	 * way, cgroups that aren't explicitly prioritized wrt each
+	 * other compete freely over the allowance, but they are
+	 * collectively protected from neighboring trees.
+	 *
+	 * We're using unprotected memory for the weight so that if
+	 * some cgroups DO claim explicit protection, we don't protect
+	 * the same bytes twice.
+	 *
+	 * Check both usage and parent_usage against the respective
+	 * protected values. One should imply the other, but they
+	 * aren't read atomically - make sure the division is sane.
+	 */
+	if (!recursive_protection)
+		return ep;
+
+	if (parent_effective > siblings_protected &&
+	    parent_usage > siblings_protected &&
+	    usage > protected) {
+		unsigned long unclaimed;
+
+		unclaimed = parent_effective - siblings_protected;
+		unclaimed *= usage - protected;
+		unclaimed /= parent_usage - siblings_protected;
+
+		ep += unclaimed;
+	}
+
+	return ep;
+}
+
+
+/**
+ * page_counter_calculate_protection - check if memory consumption is in the normal range
+ * @root: the top ancestor of the sub-tree being checked
+ * @counter: the page_counter the counter to update
+ * @recursive_protection: Whether to use memory_recursiveprot behavior.
+ *
+ * Calculates elow/emin thresholds for given page_counter.
+ *
+ * WARNING: This function is not stateless! It can only be used as part
+ *          of a top-down tree iteration, not for isolated queries.
+ */
+void page_counter_calculate_protection(struct page_counter *root,
+				       struct page_counter *counter,
+				       bool recursive_protection)
+{
+	unsigned long usage, parent_usage;
+	struct page_counter *parent = counter->parent;
+
+	/*
+	 * Effective values of the reclaim targets are ignored so they
+	 * can be stale. Have a look at mem_cgroup_protection for more
+	 * details.
+	 * TODO: calculation should be more robust so that we do not need
+	 * that special casing.
+	 */
+	if (root == counter)
+		return;
+
+	usage = page_counter_read(counter);
+	if (!usage)
+		return;
+
+	if (parent == root) {
+		counter->emin = READ_ONCE(counter->min);
+		counter->elow = READ_ONCE(counter->low);
+		return;
+	}
+
+	parent_usage = page_counter_read(parent);
+
+	WRITE_ONCE(counter->emin, effective_protection(usage, parent_usage,
+			READ_ONCE(counter->min),
+			READ_ONCE(parent->emin),
+			atomic_long_read(&parent->children_min_usage),
+			recursive_protection));
+
+	WRITE_ONCE(counter->elow, effective_protection(usage, parent_usage,
+			READ_ONCE(counter->low),
+			READ_ONCE(parent->elow),
+			atomic_long_read(&parent->children_low_usage),
+			recursive_protection));
+}