x86/resctrl: Make resctrl_arch_rmid_read() return values in bytes

resctrl_arch_rmid_read() returns a value in chunks, as read from the
hardware. This needs scaling to bytes by mon_scale, as provided by
the architecture code.

Now that resctrl_arch_rmid_read() performs the overflow and corrections
itself, it may as well return a value in bytes directly. This allows
the accesses to the architecture specific 'hw' structure to be removed.

Move the mon_scale conversion into resctrl_arch_rmid_read().
mbm_bw_count() is updated to calculate bandwidth from bytes.

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/20220902154829.30399-22-james.morse@arm.com

Author: James Morse

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

@@ -549,7 +549,6 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
-	struct rdt_hw_resource *hw_res;
 	u32 resid, evtid, domid;
 	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
@@ -569,8 +568,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	domid = md.u.domid;
 	evtid = md.u.evtid;
 
-	hw_res = &rdt_resources_all[resid];
-	r = &hw_res->r_resctrl;
+	r = &rdt_resources_all[resid].r_resctrl;
 	d = rdt_find_domain(r, domid, NULL);
 	if (IS_ERR_OR_NULL(d)) {
 		ret = -ENOENT;
@@ -584,7 +582,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	else if (rr.err == -EINVAL)
 		seq_puts(m, "Unavailable\n");
 	else
-		seq_printf(m, "%llu\n", rr.val * hw_res->mon_scale);
+		seq_printf(m, "%llu\n", rr.val);
 
 out:
 	rdtgroup_kn_unlock(of->kn);

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

@@ -279,13 +279,13 @@ struct rftype {
 
 /**
  * struct mbm_state - status for each MBM counter in each domain
- * @prev_bw_chunks: Previous chunks value read for bandwidth calculation
+ * @prev_bw_bytes: Previous bytes value read for bandwidth calculation
  * @prev_bw:	The most recent bandwidth in MBps
  * @delta_bw:	Difference between the current and previous bandwidth
  * @delta_comp:	Indicates whether to compute the delta_bw
  */
 struct mbm_state {
-	u64	prev_bw_chunks;
+	u64	prev_bw_bytes;
 	u32	prev_bw;
 	u32	delta_bw;
 	bool	delta_comp;

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

@@ -16,6 +16,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <linux/slab.h>
 
 #include <asm/cpu_device_id.h>
@@ -189,7 +190,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	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;
+	u64 msr_val, chunks;
 
 	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
 		return -EINVAL;
@@ -214,12 +215,14 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	if (am) {
 		am->chunks += mbm_overflow_count(am->prev_msr, msr_val,
 						 hw_res->mbm_width);
-		*val = get_corrected_mbm_count(rmid, am->chunks);
+		chunks = get_corrected_mbm_count(rmid, am->chunks);
 		am->prev_msr = msr_val;
 	} else {
-		*val = msr_val;
+		chunks = msr_val;
 	}
 
+	*val = chunks * hw_res->mon_scale;
+
 	return 0;
 }
 
@@ -232,7 +235,6 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 void __check_limbo(struct rdt_domain *d, bool force_free)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	struct rmid_entry *entry;
 	u32 crmid = 1, nrmid;
 	bool rmid_dirty;
@@ -255,7 +257,6 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 					   QOS_L3_OCCUP_EVENT_ID, &val)) {
 			rmid_dirty = true;
 		} else {
-			val *= hw_res->mon_scale;
 			rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
 		}
 
@@ -299,7 +300,6 @@ int alloc_rmid(void)
 static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	struct rdt_domain *d;
 	int cpu, err;
 	u64 val = 0;
@@ -311,7 +311,6 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 			err = resctrl_arch_rmid_read(r, d, entry->rmid,
 						     QOS_L3_OCCUP_EVENT_ID,
 						     &val);
-			val *= hw_res->mon_scale;
 			if (err || val <= resctrl_rmid_realloc_threshold)
 				continue;
 		}
@@ -403,15 +402,14 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr)
  */
 static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 {
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
 	struct mbm_state *m = &rr->d->mbm_local[rmid];
-	u64 cur_bw, chunks, cur_chunks;
+	u64 cur_bw, bytes, cur_bytes;
 
-	cur_chunks = rr->val;
-	chunks = cur_chunks - m->prev_bw_chunks;
-	m->prev_bw_chunks = cur_chunks;
+	cur_bytes = rr->val;
+	bytes = cur_bytes - m->prev_bw_bytes;
+	m->prev_bw_bytes = cur_bytes;
 
-	cur_bw = (chunks * hw_res->mon_scale) >> 20;
+	cur_bw = bytes / SZ_1M;
 
 	if (m->delta_comp)
 		m->delta_bw = abs(cur_bw - m->prev_bw);

include/linux/resctrl.h

@@ -227,7 +227,7 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
  * @d:			domain that the counter should be read from.
  * @rmid:		rmid of the counter to read.
  * @eventid:		eventid to read, e.g. L3 occupancy.
- * @val:		result of the counter read in chunks.
+ * @val:		result of the counter read in bytes.
  *
  * Call from process context on a CPU that belongs to domain @d.
  *