[PATCH 03/11] cgroup: add memory_cma_accounting mount option

[Eric Chanudet]

Add a cgroup v2 mount option that will be used later in this series to
enable CMA memory accounting under memcg.

The option is made opt-in as it will charge allocations to the cgroup's
overall memory usage, which changes existing expectations.

Signed-off-by: Eric Chanudet <echanude@xxxxxxxxxx>
---
 Documentation/admin-guide/cgroup-v2.rst | 20 ++++++++++++++++++++
 include/linux/cgroup-defs.h             |  5 +++++
 kernel/cgroup/cgroup.c                  | 15 ++++++++++++++-
 3 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index aed195a71cbf..3dfc13f31a0c 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -246,6 +246,26 @@ cgroup v2 currently supports the following mount options.
           will not be tracked by the memory controller (even if cgroup
           v2 is remounted later on).
 
+  memory_cma_accounting
+        Count CMA memory usage towards the cgroup's overall memory usage for
+        the memory controller, and expose per-CMA-area usage counters. This
+        behavior is opt-in, so as to not cause regression on existing setups.
+
+        A few caveats to keep in mind:
+
+        * CMA areas are reserved at boot time, memory is only charged to a
+          cgroup when a CMA allocation is performed on its behalf.
+        * CMA pages allocated while this option is not enabled will not be
+          tracked by the memory controller, even if cgroup v2 is remounted
+          later on with this option. Charges happen at allocation.
+        * CMA allocations are charged both to the cgroup's memory counter
+          (limited by memory.max) and the per-area CMA counter (limited by
+          memory.cma.<area>.max). Hitting either limit can cause an allocation
+          to fail. If CMA usage pushes the cgroup over memory.high or
+          memory.max, the memory controller will attempt to reclaim other
+          memory only. CMA memory charged to the cgroup is not reclaimable.
+          Limits should be sized to accommodate the expected CMA pressure.
+
   pids_localevents
         The option restores v1-like behavior of pids.events:max, that is only
         local (inside cgroup proper) fork failures are counted. Without this
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index de2cd6238c2a..15f3f7110c5b 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -129,6 +129,11 @@ enum {
 	 * Enable legacy local pids.events.
 	 */
 	CGRP_ROOT_PIDS_LOCAL_EVENTS = (1 << 20),
+
+	/*
+	 * Enable cma accounting for the memory controller.
+	 */
+	CGRP_ROOT_MEMORY_CMA_ACCOUNTING = (1 << 21),
 };
 
 /* cftype->flags */
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index b5b461d4418b..12184f85ad10 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1985,6 +1985,7 @@ enum cgroup2_param {
 	Opt_memory_recursiveprot,
 	Opt_memory_hugetlb_accounting,
 	Opt_pids_localevents,
+	Opt_memory_cma_accounting,
 	nr__cgroup2_params
 };
 
@@ -1995,6 +1996,7 @@ static const struct fs_parameter_spec cgroup2_fs_parameters[] = {
 	fsparam_flag("memory_recursiveprot",	Opt_memory_recursiveprot),
 	fsparam_flag("memory_hugetlb_accounting", Opt_memory_hugetlb_accounting),
 	fsparam_flag("pids_localevents",	Opt_pids_localevents),
+	fsparam_flag("memory_cma_accounting",	Opt_memory_cma_accounting),
 	{}
 };
 
@@ -2027,6 +2029,9 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param
 	case Opt_pids_localevents:
 		ctx->flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS;
 		return 0;
+	case Opt_memory_cma_accounting:
+		ctx->flags |= CGRP_ROOT_MEMORY_CMA_ACCOUNTING;
+		return 0;
 	}
 	return -EINVAL;
 }
@@ -2068,6 +2073,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
 			cgrp_dfl_root.flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS;
 		else
 			cgrp_dfl_root.flags &= ~CGRP_ROOT_PIDS_LOCAL_EVENTS;
+
+		if (root_flags & CGRP_ROOT_MEMORY_CMA_ACCOUNTING)
+			cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_CMA_ACCOUNTING;
+		else
+			cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_CMA_ACCOUNTING;
 	}
 }
 
@@ -2085,6 +2095,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
 		seq_puts(seq, ",memory_hugetlb_accounting");
 	if (cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS)
 		seq_puts(seq, ",pids_localevents");
+	if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_CMA_ACCOUNTING)
+		seq_puts(seq, ",memory_cma_accounting");
 	return 0;
 }
 
@@ -7520,7 +7532,8 @@ static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
 			"memory_localevents\n"
 			"memory_recursiveprot\n"
 			"memory_hugetlb_accounting\n"
-			"pids_localevents\n");
+			"pids_localevents\n"
+			"memory_cma_accounting\n");
 }
 static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
 

-- 
2.53.0