[PATCH v10 08/17] x86/resctrl: Enforce system RMID limit on AET event groups

[Tony Luck]

AET (Application Energy Telemetry) event groups each support a specific
number of RMIDs. But that number may be lower than the number supported
by the system. Especially true on systems with SNC (Sub-NUMA Cluster)
enabled as that reduces the number of supported RMIDs.

Fix get_rdt_mon_resources() to return true when any monitor resource is
possibly enabled. Call intel_aet_init() to adjust the event_group::num_rmid
values to not exceed the system supported maximum.

Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---
v10:
	New patch

 arch/x86/kernel/cpu/resctrl/internal.h  |  4 +++-
 arch/x86/kernel/cpu/resctrl/core.c      |  8 +++++---
 arch/x86/kernel/cpu/resctrl/intel_aet.c | 17 +++++++++++++----
 arch/x86/kernel/cpu/resctrl/monitor.c   |  4 +---
 4 files changed, 22 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index e3cfa0c10e92..8e4f0bb91785 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -224,7 +224,7 @@ union l3_qos_abmc_cfg {
 
 void rdt_ctrl_update(void *arg);
 
-int rdt_get_l3_mon_config(struct rdt_resource *r);
+void rdt_get_l3_mon_config(struct rdt_resource *r);
 
 bool rdt_cpu_has(int flag);
 
@@ -235,6 +235,7 @@ void resctrl_arch_mbm_cntr_assign_set_one(struct rdt_resource *r);
 
 #ifdef CONFIG_X86_CPU_RESCTRL_INTEL_AET
 bool intel_aet_get_events(void);
+void __init intel_aet_init(void);
 void __exit intel_aet_exit(void);
 int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val);
 void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r,
@@ -242,6 +243,7 @@ void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r,
 bool intel_handle_aet_option(bool force_off, char *tok);
 #else
 static inline bool intel_aet_get_events(void) { return false; }
+static inline void intel_aet_init(void) { }
 static inline void __exit intel_aet_exit(void) { }
 static inline int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val)
 {
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 092764cf693f..2c938b97b147 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -1019,10 +1019,10 @@ static __init bool get_rdt_mon_resources(void)
 	if (rdt_cpu_has(X86_FEATURE_ABMC))
 		ret = true;
 
-	if (!ret)
-		return false;
+	if (ret)
+		rdt_get_l3_mon_config(r);
 
-	return !rdt_get_l3_mon_config(r);
+	return boot_cpu_data.x86_cache_max_rmid > 0;
 }
 
 static __init void __check_quirks_intel(void)
@@ -1169,6 +1169,8 @@ static int __init resctrl_arch_late_init(void)
 	if (!get_rdt_resources())
 		return -ENODEV;
 
+	intel_aet_init();
+
 	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
 				  "x86/resctrl/cat:online:",
 				  resctrl_arch_online_cpu,
diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
index 4ad6ad78e93e..e6cc57206381 100644
--- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -65,10 +65,10 @@ struct pmt_event {
  * @force_on:		True when "rdt" command line overrides disable of this
  *			event group.
  * @guid:		Unique number per XML description file.
- * @num_rmid:		Number of RMIDs supported by this group. May be
- *			adjusted downwards if enumeration from
- *			intel_pmt_get_regions_by_feature() indicates fewer
- *			RMIDs can be tracked simultaneously.
+ * @num_rmid:		Number of RMIDs supported by this group. May be adjusted
+ *			downwards if the system supports fewer RMIDs or
+ *			enumeration from intel_pmt_get_regions_by_feature()
+ *			indicates fewer RMIDs can be tracked simultaneously.
  * @mmio_size:		Number of bytes of MMIO registers for this group.
  * @num_events:		Number of events in this group.
  * @evts:		Array of event descriptors.
@@ -325,6 +325,15 @@ bool intel_aet_get_events(void)
 	return ret;
 }
 
+void __init intel_aet_init(void)
+{
+	u32 max_rmid = resctrl_arch_system_max_rmid_idx();
+	struct event_group **peg;
+
+	for_each_event_group(peg)
+		(*peg)->num_rmid = min(max_rmid, (*peg)->num_rmid);
+}
+
 void __exit intel_aet_exit(void)
 {
 	struct event_group **peg;
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 1fea893f2cc1..f40f5dd1440c 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -407,7 +407,7 @@ static __init int snc_get_config(void)
 	return ret;
 }
 
-int __init rdt_get_l3_mon_config(struct rdt_resource *r)
+void __init rdt_get_l3_mon_config(struct rdt_resource *r)
 {
 	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
@@ -466,8 +466,6 @@ int __init rdt_get_l3_mon_config(struct rdt_resource *r)
 	}
 
 	r->mon_capable = true;
-
-	return 0;
 }
 
 void __init intel_rdt_mbm_apply_quirk(void)
-- 
2.55.0