x86/resctrl: Move mbm_overflow_count() into resctrl_arch_rmid_read()

resctrl_arch_rmid_read() is intended as the function that an
architecture agnostic resctrl filesystem driver can use to
read a value in bytes from a counter. Currently the function returns
the MBM values in chunks directly from hardware. When reading a bandwidth
counter, mbm_overflow_count() must be used to correct for any possible
overflow.

mbm_overflow_count() is architecture specific, its behaviour should
be part of resctrl_arch_rmid_read().

Move the mbm_overflow_count() calls into resctrl_arch_rmid_read().
This allows the resctrl filesystems's prev_msr to be removed in
favour of the architecture private version.
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Jamie Iles <quic_jiles@quicinc.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Xin Hao <xhao@linux.alibaba.com>
Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Tested-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20220902154829.30399-18-james.morse@arm.com

arch/x86/kernel/cpu/resctrl/internal.h

@@ -281,7 +281,6 @@ struct rftype {
 /**
  * struct mbm_state - status for each MBM counter in each domain
  * @chunks:	Total data moved (multiply by rdt_group.mon_scale to get bytes)
- * @prev_msr:	Value of IA32_QM_CTR for this RMID last time we read it
  * @prev_bw_chunks: Previous chunks value read for bandwidth calculation
  * @prev_bw:	The most recent bandwidth in MBps
  * @delta_bw:	Difference between the current and previous bandwidth
@@ -289,7 +288,6 @@ struct rftype {
  */
 struct mbm_state {
 	u64	chunks;
-	u64	prev_msr;
 	u64	prev_bw_chunks;
 	u32	prev_bw;
 	u32	delta_bw;

arch/x86/kernel/cpu/resctrl/monitor.c

@@ -167,9 +167,20 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
 		memset(am, 0, sizeof(*am));
 }
 
+static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
+{
+	u64 shift = 64 - width, chunks;
+
+	chunks = (cur_msr << shift) - (prev_msr << shift);
+	return chunks >> shift;
+}
+
 int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 			   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);
+	struct arch_mbm_state *am;
 	u64 msr_val;
 
 	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
@@ -191,7 +202,13 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	if (msr_val & RMID_VAL_UNAVAIL)
 		return -EINVAL;
 
-	*val = msr_val;
+	am = get_arch_mbm_state(hw_dom, rmid, eventid);
+	if (am) {
+		*val = mbm_overflow_count(am->prev_msr, msr_val, hw_res->mbm_width);
+		am->prev_msr = msr_val;
+	} else {
+		*val = msr_val;
+	}
 
 	return 0;
 }
@@ -322,19 +339,10 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
-static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
-{
-	u64 shift = 64 - width, chunks;
-
-	chunks = (cur_msr << shift) - (prev_msr << shift);
-	return chunks >> shift;
-}
-
 static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 {
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
 	struct mbm_state *m;
-	u64 chunks, tval = 0;
+	u64 tval = 0;
 
 	if (rr->first)
 		resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid);
@@ -363,13 +371,10 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
 
 	if (rr->first) {
 		memset(m, 0, sizeof(struct mbm_state));
-		m->prev_msr = tval;
 		return 0;
 	}
 
-	chunks = mbm_overflow_count(m->prev_msr, tval, hw_res->mbm_width);
-	m->chunks += chunks;
-	m->prev_msr = tval;
+	m->chunks += tval;
 
 	rr->val += get_corrected_mbm_count(rmid, m->chunks);