[PATCH v17 23/33] fs/resctrl: Support counter read/reset with mbm_event assignment mode

[Babu Moger <babu.moger@amd.com>]

When "mbm_event" counter assignment mode is enabled, the architecture
requires a counter ID to read the event data.

Introduce an is_mbm_cntr field in struct rmid_read to indicate whether
counter assignment mode is in use.

Update the logic to call resctrl_arch_cntr_read() and
resctrl_arch_reset_cntr() when the assignment mode is active. Report
'Unassigned' in case the user attempts to read an event without assigning
a hardware counter.

Suggested-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
---
v17: Updated the changelog.
     Removed duplicate resctrl_arch_mbm_cntr_assign_enabled() check.
     mbm_cntr_get() need not be static anymore.

v16: Squashed two patches here.
     https://lore.kernel.org/lkml/df215f02db88cad714755cd5275f20cf0ee4ae26.1752013061.git.babu.moger@amd.com/
     https://lore.kernel.org/lkml/296c435e9bf63fc5031114cced00fbb4837ad327.1752013061.git.babu.moger@amd.com/
     Changed is_cntr field in struct rmid_read to is_mbm_cntr.
     Fixed the memory leak with arch_mon_ctx.
     Updated the resctrl.rst user doc.
     Updated the changelog.
     Report Unassigned only if none of the events in CTRL_MON and MON are assigned.

v15: New patch to add is_cntr in rmid_read as discussed in
     https://lore.kernel.org/lkml/b4b14670-9cb0-4f65-abd5-39db996e8da9@intel.com/
---
 Documentation/filesystems/resctrl.rst |  6 ++++
 fs/resctrl/ctrlmondata.c              | 22 ++++++++++---
 fs/resctrl/internal.h                 |  3 ++
 fs/resctrl/monitor.c                  | 47 ++++++++++++++++++++-------
 4 files changed, 62 insertions(+), 16 deletions(-)

diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
index 446736dbd97f..4c24c5f3f4c1 100644
--- a/Documentation/filesystems/resctrl.rst
+++ b/Documentation/filesystems/resctrl.rst
@@ -434,6 +434,12 @@ When monitoring is enabled all MON groups will also contain:
 	for the L3 cache they occupy). These are named "mon_sub_L3_YY"
 	where "YY" is the node number.
 
+	When the 'mbm_event' counter assignment mode is enabled, reading
+	an MBM event of a MON group returns 'Unassigned' if no hardware
+	counter is assigned to it. For CTRL_MON groups, 'Unassigned' is
+	returned if the MBM event does not have an assigned counter in the
+	CTRL_MON group nor in any of its associated MON groups.
+
 "mon_hw_id":
 	Available only with debug option. The identifier used by hardware
 	for the monitor group. On x86 this is the RMID.
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index ad7ffc6acf13..31787ce6ec91 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -563,10 +563,15 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	rr->r = r;
 	rr->d = d;
 	rr->first = first;
-	rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
-	if (IS_ERR(rr->arch_mon_ctx)) {
-		rr->err = -EINVAL;
-		return;
+	if (resctrl_arch_mbm_cntr_assign_enabled(r) &&
+	    resctrl_is_mbm_event(evtid)) {
+		rr->is_mbm_cntr = true;
+	} else {
+		rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
+		if (IS_ERR(rr->arch_mon_ctx)) {
+			rr->err = -EINVAL;
+			return;
+		}
 	}
 
 	cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU);
@@ -582,7 +587,8 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 	else
 		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
 
-	resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
+	if (rr->arch_mon_ctx)
+		resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
 }
 
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
@@ -653,10 +659,16 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 checkresult:
 
+	/*
+	 * -ENOENT is a special case, set only when "mbm_event" counter assignment
+	 * mode is enabled and no counter has been assigned.
+	 */
 	if (rr.err == -EIO)
 		seq_puts(m, "Error\n");
 	else if (rr.err == -EINVAL)
 		seq_puts(m, "Unavailable\n");
+	else if (rr.err == -ENOENT)
+		seq_puts(m, "Unassigned\n");
 	else
 		seq_printf(m, "%llu\n", rr.val);
 
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index c11f2751acf5..88e1a800417d 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -110,6 +110,8 @@ struct mon_data {
  *	   domains in @r sharing L3 @ci.id
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
+ * @is_mbm_cntr: true if "mbm_event" counter assignment mode is enabled and it
+ *	   is an MBM event.
  * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains.
  * @err:   Error encountered when reading counter.
  * @val:   Returned value of event counter. If @rgrp is a parent resource group,
@@ -124,6 +126,7 @@ struct rmid_read {
 	struct rdt_mon_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
+	bool			is_mbm_cntr;
 	unsigned int		ci_id;
 	int			err;
 	u64			val;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 85187273d562..0a9d257e27a2 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -419,13 +419,25 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	u32 closid = rdtgrp->closid;
 	u32 rmid = rdtgrp->mon.rmid;
 	struct rdt_mon_domain *d;
+	int cntr_id = -ENOENT;
 	struct cacheinfo *ci;
 	struct mbm_state *m;
 	int err, ret;
 	u64 tval = 0;
 
+	if (rr->is_mbm_cntr) {
+		cntr_id = mbm_cntr_get(rr->r, rr->d, rdtgrp, rr->evtid);
+		if (cntr_id < 0) {
+			rr->err = -ENOENT;
+			return -EINVAL;
+		}
+	}
+
 	if (rr->first) {
-		resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
+		if (rr->is_mbm_cntr)
+			resctrl_arch_reset_cntr(rr->r, rr->d, closid, rmid, cntr_id, rr->evtid);
+		else
+			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));
@@ -436,8 +448,12 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 		/* Reading a single domain, must be on a CPU in that domain. */
 		if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask))
 			return -EINVAL;
-		rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
-						 rr->evtid, &tval, rr->arch_mon_ctx);
+		if (rr->is_mbm_cntr)
+			rr->err = resctrl_arch_cntr_read(rr->r, rr->d, closid, rmid, cntr_id,
+							 rr->evtid, &tval);
+		else
+			rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
+							 rr->evtid, &tval, rr->arch_mon_ctx);
 		if (rr->err)
 			return rr->err;
 
@@ -462,8 +478,12 @@ static int __mon_event_count(struct rdtgroup *rdtgrp, struct rmid_read *rr)
 	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
 		if (d->ci_id != rr->ci_id)
 			continue;
-		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
-					     rr->evtid, &tval, rr->arch_mon_ctx);
+		if (rr->is_mbm_cntr)
+			err = resctrl_arch_cntr_read(rr->r, d, closid, rmid, cntr_id,
+						     rr->evtid, &tval);
+		else
+			err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
+						     rr->evtid, &tval, rr->arch_mon_ctx);
 		if (!err) {
 			rr->val += tval;
 			ret = 0;
@@ -670,11 +690,15 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *
 	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;
+	if (resctrl_arch_mbm_cntr_assign_enabled(r)) {
+		rr.is_mbm_cntr = true;
+	} else {
+		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(rdtgrp, &rr);
@@ -686,7 +710,8 @@ static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *
 	if (is_mba_sc(NULL))
 		mbm_bw_count(rdtgrp, &rr);
 
-	resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
+	if (rr.arch_mon_ctx)
+		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,
-- 
2.34.1