[PATCH v7 1/4] x86/resctrl: Make input event for MBA Software Controller configurable

[Tony Luck <tony.luck@intel.com>]

The MBA Software Controller(mba_sc) is a feedback loop that uses
measurements of local memory bandwidth to adjust MBA throttling levels
to keep workloads in a resctrl group within a target bandwidth set in
the schemata file.

Users may want to use total memory bandwidth instead of local to handle
workloads that have poor NUMA localization.

Update the once-per-second polling code to pick a chosen event (local
or total memory bandwidth).

Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 include/linux/resctrl.h                |  2 +
 arch/x86/kernel/cpu/resctrl/monitor.c  | 80 ++++++++++++--------------
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  2 +
 3 files changed, 40 insertions(+), 44 deletions(-)

diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index d94abba1c716..ccb0f50dc18c 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -161,6 +161,7 @@ enum membw_throttle_mode {
  * @throttle_mode:	Bandwidth throttling mode when threads request
  *			different memory bandwidths
  * @mba_sc:		True if MBA software controller(mba_sc) is enabled
+ * @mba_mbps_event:	Monitoring event guiding feedback loop when @mba_sc is true
  * @mb_map:		Mapping of memory B/W percentage to memory B/W delay
  */
 struct resctrl_membw {
@@ -170,6 +171,7 @@ struct resctrl_membw {
 	bool				arch_needs_linear;
 	enum membw_throttle_mode	throttle_mode;
 	bool				mba_sc;
+	enum resctrl_event_id		mba_mbps_event;
 	u32				*mb_map;
 };
 
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 851b561850e0..2692ce7f708e 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -663,10 +663,11 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
  */
 static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
-	u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-	struct mbm_state *m = &rr->d->mbm_local[idx];
 	u64 cur_bw, bytes, cur_bytes;
+	struct mbm_state *m;
 
+	m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
+	WARN_ON(!m);
 	cur_bytes = rr->val;
 	bytes = cur_bytes - m->prev_bw_bytes;
 	m->prev_bw_bytes = cur_bytes;
@@ -752,20 +753,22 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 	u32 closid, rmid, cur_msr_val, new_msr_val;
 	struct mbm_state *pmbm_data, *cmbm_data;
 	struct rdt_ctrl_domain *dom_mba;
+	enum resctrl_event_id evt_id;
 	struct rdt_resource *r_mba;
-	u32 cur_bw, user_bw, idx;
 	struct list_head *head;
 	struct rdtgroup *entry;
+	u32 cur_bw, user_bw;
 
-	if (!is_mbm_local_enabled())
+	if (!is_mbm_enabled())
 		return;
 
 	r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+	evt_id = r_mba->membw.mba_mbps_event;
 
 	closid = rgrp->closid;
 	rmid = rgrp->mon.rmid;
-	idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-	pmbm_data = &dom_mbm->mbm_local[idx];
+	pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id);
+	WARN_ON(!pmbm_data);
 
 	dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba);
 	if (!dom_mba) {
@@ -784,7 +787,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 	 */
 	head = &rgrp->mon.crdtgrp_list;
 	list_for_each_entry(entry, head, mon.crdtgrp_list) {
-		cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid];
+		cmbm_data = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id);
+		WARN_ON(!cmbm_data);
 		cur_bw += cmbm_data->prev_bw;
 	}
 
@@ -813,54 +817,42 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
 	resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
 }
 
-static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
-		       u32 closid, u32 rmid)
+static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
+				 u32 closid, u32 rmid, enum resctrl_event_id evtid)
 {
+	struct rdt_resource *rmba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
 	struct rmid_read rr = {0};
 
 	rr.r = r;
 	rr.d = d;
+	rr.evtid = evtid;
+	rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
+	if (IS_ERR(rr.arch_mon_ctx)) {
+		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
+				    PTR_ERR(rr.arch_mon_ctx));
+		return;
+	}
 
+	__mon_event_count(closid, rmid, &rr);
+
+	if (is_mba_sc(NULL) && rr.evtid == rmba->membw.mba_mbps_event)
+		mbm_bw_count(closid, rmid, &rr);
+
+	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
+}
+
+static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
+		       u32 closid, u32 rmid)
+{
 	/*
 	 * This is protected from concurrent reads from user
 	 * as both the user and we hold the global mutex.
 	 */
-	if (is_mbm_total_enabled()) {
-		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
-		rr.val = 0;
-		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
-		if (IS_ERR(rr.arch_mon_ctx)) {
-			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-					    PTR_ERR(rr.arch_mon_ctx));
-			return;
-		}
-
-		__mon_event_count(closid, rmid, &rr);
-
-		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
-	}
-	if (is_mbm_local_enabled()) {
-		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
-		rr.val = 0;
-		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
-		if (IS_ERR(rr.arch_mon_ctx)) {
-			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
-					    PTR_ERR(rr.arch_mon_ctx));
-			return;
-		}
-
-		__mon_event_count(closid, rmid, &rr);
-
-		/*
-		 * Call the MBA software controller only for the
-		 * control groups and when user has enabled
-		 * the software controller explicitly.
-		 */
-		if (is_mba_sc(NULL))
-			mbm_bw_count(closid, rmid, &rr);
+	if (is_mbm_total_enabled())
+		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
 
-		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
-	}
+	if (is_mbm_local_enabled())
+		mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index d7163b764c62..aedb30120d50 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2505,6 +2505,7 @@ static void rdt_disable_ctx(void)
 
 static int rdt_enable_ctx(struct rdt_fs_context *ctx)
 {
+	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
 	int ret = 0;
 
 	if (ctx->enable_cdpl2) {
@@ -2520,6 +2521,7 @@ static int rdt_enable_ctx(struct rdt_fs_context *ctx)
 	}
 
 	if (ctx->enable_mba_mbps) {
+		r->membw.mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID;
 		ret = set_mba_sc(true);
 		if (ret)
 			goto out_cdpl3;
-- 
2.46.1