x86/resctrl: Track the closid with the rmid

x86's RMID are independent of the CLOSID. An RMID can be allocated,
used and freed without considering the CLOSID.

MPAM's equivalent feature is PMG, which is not an independent number,
it extends the CLOSID/PARTID space. For MPAM, only PMG-bits worth of
'RMID' can be allocated for a single CLOSID.
i.e. if there is 1 bit of PMG space, then each CLOSID can have two
monitor groups.

To allow resctrl to disambiguate RMID values for different CLOSID,
everything in resctrl that keeps an RMID value needs to know the CLOSID
too. This will always be ignored on x86.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Reviewed-by: Xin Hao <xhao@linux.alibaba.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Tested-by: Peter Newman <peternewman@google.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Link: https://lore.kernel.org/r/20240213184438.16675-6-james.morse@arm.com
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>

1 files changed, 47 insertions, 26 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 3a73db0579d8..3dad4134d2c9 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -24,7 +24,20 @@
 
 #include "internal.h"
 
+/**
+ * struct rmid_entry - dirty tracking for all RMID.
+ * @closid:	The CLOSID for this entry.
+ * @rmid:	The RMID for this entry.
+ * @busy:	The number of domains with cached data using this RMID.
+ * @list:	Member of the rmid_free_lru list when busy == 0.
+ *
+ * Depending on the architecture the correct monitor is accessed using
+ * both @closid and @rmid, or @rmid only.
+ *
+ * Take the rdtgroup_mutex when accessing.
+ */
 struct rmid_entry {
+	u32				closid;
 	u32				rmid;
 	int				busy;
 	struct list_head		list;
@@ -136,7 +149,7 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
 	return val;
 }
 
-static inline struct rmid_entry *__rmid_entry(u32 rmid)
+static inline struct rmid_entry *__rmid_entry(u32 closid, u32 rmid)
 {
 	struct rmid_entry *entry;
 
@@ -190,7 +203,8 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
 }
 
 void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
-			     u32 rmid, enum resctrl_event_id eventid)
+			     u32 unused, u32 rmid,
+			     enum resctrl_event_id eventid)
 {
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct arch_mbm_state *am;
@@ -230,7 +244,8 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
 }
 
 int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
-			   u32 rmid, enum resctrl_event_id eventid, u64 *val)
+			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
+			   u64 *val)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
@@ -285,9 +300,9 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 		if (nrmid >= r->num_rmid)
 			break;
 
-		entry = __rmid_entry(nrmid);
+		entry = __rmid_entry(X86_RESCTRL_EMPTY_CLOSID, nrmid);// temporary
 
-		if (resctrl_arch_rmid_read(r, d, entry->rmid,
+		if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid,
 					   QOS_L3_OCCUP_EVENT_ID, &val)) {
 			rmid_dirty = true;
 		} else {
@@ -342,7 +357,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 	cpu = get_cpu();
 	list_for_each_entry(d, &r->domains, list) {
 		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
-			err = resctrl_arch_rmid_read(r, d, entry->rmid,
+			err = resctrl_arch_rmid_read(r, d, entry->closid,
+						     entry->rmid,
 						     QOS_L3_OCCUP_EVENT_ID,
 						     &val);
 			if (err || val <= resctrl_rmid_realloc_threshold)
@@ -366,7 +382,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-void free_rmid(u32 rmid)
+void free_rmid(u32 closid, u32 rmid)
 {
 	struct rmid_entry *entry;
 
@@ -375,7 +391,7 @@ void free_rmid(u32 rmid)
 
 	lockdep_assert_held(&rdtgroup_mutex);
 
-	entry = __rmid_entry(rmid);
+	entry = __rmid_entry(closid, rmid);
 
 	if (is_llc_occupancy_enabled())
 		add_rmid_to_limbo(entry);
@@ -383,8 +399,8 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid,
-				       enum resctrl_event_id evtid)
+static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid,
+				       u32 rmid, enum resctrl_event_id evtid)
 {
 	switch (evtid) {
 	case QOS_L3_MBM_TOTAL_EVENT_ID:
@@ -396,20 +412,21 @@ static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid,
 	}
 }
 
-static int __mon_event_count(u32 rmid, struct rmid_read *rr)
+static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	struct mbm_state *m;
 	u64 tval = 0;
 
 	if (rr->first) {
-		resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid);
-		m = get_mbm_state(rr->d, rmid, rr->evtid);
+		resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
+		m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
 		if (m)
 			memset(m, 0, sizeof(struct mbm_state));
 		return 0;
 	}
 
-	rr->err = resctrl_arch_rmid_read(rr->r, rr->d, rmid, rr->evtid, &tval);
+	rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, rr->evtid,
+					 &tval);
 	if (rr->err)
 		return rr->err;
 
@@ -421,6 +438,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 /*
  * mbm_bw_count() - Update bw count from values previously read by
  *		    __mon_event_count().
+ * @closid:	The closid used to identify the cached mbm_state.
  * @rmid:	The rmid used to identify the cached mbm_state.
  * @rr:		The struct rmid_read populated by __mon_event_count().
  *
@@ -429,7 +447,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
  * __mon_event_count() is compared with the chunks value from the previous
  * invocation. This must be called once per second to maintain values in MBps.
  */
-static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
+static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	struct mbm_state *m = &rr->d->mbm_local[rmid];
 	u64 cur_bw, bytes, cur_bytes;
@@ -456,7 +474,7 @@ void mon_event_count(void *info)
 
 	rdtgrp = rr->rgrp;
 
-	ret = __mon_event_count(rdtgrp->mon.rmid, rr);
+	ret = __mon_event_count(rdtgrp->closid, rdtgrp->mon.rmid, rr);
 
 	/*
 	 * For Ctrl groups read data from child monitor groups and
@@ -467,7 +485,8 @@ void mon_event_count(void *info)
 
 	if (rdtgrp->type == RDTCTRL_GROUP) {
 		list_for_each_entry(entry, head, mon.crdtgrp_list) {
-			if (__mon_event_count(entry->mon.rmid, rr) == 0)
+			if (__mon_event_count(entry->closid, entry->mon.rmid,
+					      rr) == 0)
 				ret = 0;
 		}
 	}
@@ -578,7 +597,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_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_domain *d, int rmid)
+static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
+		       u32 closid, u32 rmid)
 {
 	struct rmid_read rr;
 
@@ -593,12 +613,12 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 	if (is_mbm_total_enabled()) {
 		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
 		rr.val = 0;
-		__mon_event_count(rmid, &rr);
+		__mon_event_count(closid, rmid, &rr);
 	}
 	if (is_mbm_local_enabled()) {
 		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
 		rr.val = 0;
-		__mon_event_count(rmid, &rr);
+		__mon_event_count(closid, rmid, &rr);
 
 		/*
 		 * Call the MBA software controller only for the
@@ -606,7 +626,7 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 		 * the software controller explicitly.
 		 */
 		if (is_mba_sc(NULL))
-			mbm_bw_count(rmid, &rr);
+			mbm_bw_count(closid, rmid, &rr);
 	}
 }
 
@@ -663,11 +683,11 @@ void mbm_handle_overflow(struct work_struct *work)
 	d = container_of(work, struct rdt_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
-		mbm_update(r, d, prgrp->mon.rmid);
+		mbm_update(r, d, prgrp->closid, prgrp->mon.rmid);
 
 		head = &prgrp->mon.crdtgrp_list;
 		list_for_each_entry(crgrp, head, mon.crdtgrp_list)
-			mbm_update(r, d, crgrp->mon.rmid);
+			mbm_update(r, d, crgrp->closid, crgrp->mon.rmid);
 
 		if (is_mba_sc(NULL))
 			update_mba_bw(prgrp, d);
@@ -710,10 +730,11 @@ static int dom_data_init(struct rdt_resource *r)
 	}
 
 	/*
-	 * RMID 0 is special and is always allocated. It's used for all
-	 * tasks that are not monitored.
+	 * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and
+	 * are always allocated. These are used for the rdtgroup_default
+	 * control group, which will be setup later in rdtgroup_init().
 	 */
-	entry = __rmid_entry(0);
+	entry = __rmid_entry(RESCTRL_RESERVED_CLOSID, RESCTRL_RESERVED_RMID);
 	list_del(&entry->list);
 
 	return 0;