x86/resctrl: Rename and change the units of resctrl_cqm_threshold

resctrl_cqm_threshold is stored in a hardware specific chunk size,
but exposed to user-space as bytes.

This means the filesystem parts of resctrl need to know how the hardware
counts, to convert the user provided byte value to chunks. The interface
between the architecture's resctrl code and the filesystem ought to
treat everything as bytes.

Change the unit of resctrl_cqm_threshold to bytes. resctrl_arch_rmid_read()
still returns its value in chunks, so this needs converting to bytes.
As all the users have been touched, rename the variable to
resctrl_rmid_realloc_threshold, which describes what the value is for.

Neither r->num_rmid nor hw_res->mon_scale are guaranteed to be a power
of 2, so the existing code introduces a rounding error from resctrl's
theoretical fraction of the cache usage. This behaviour is kept as it
ensures the user visible value matches the value read from hardware
when the rmid will be reallocated.

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/20220902154829.30399-20-james.morse@arm.com

1 files changed, 26 insertions, 17 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 27bb4947a176..e91afe99b763 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -17,7 +17,10 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
+
 #include <asm/cpu_device_id.h>
+#include <asm/resctrl.h>
+
 #include "internal.h"
 
 struct rmid_entry {
@@ -37,8 +40,8 @@ static LIST_HEAD(rmid_free_lru);
  * @rmid_limbo_count     count of currently unused but (potentially)
  *     dirty RMIDs.
  *     This counts RMIDs that no one is currently using but that
- *     may have a occupancy value > intel_cqm_threshold. User can change
- *     the threshold occupancy value.
+ *     may have a occupancy value > resctrl_rmid_realloc_threshold. User can
+ *     change the threshold occupancy value.
  */
 static unsigned int rmid_limbo_count;
 
@@ -59,10 +62,10 @@ bool rdt_mon_capable;
 unsigned int rdt_mon_features;
 
 /*
- * This is the threshold cache occupancy at which we will consider an
+ * This is the threshold cache occupancy in bytes at which we will consider an
  * RMID available for re-allocation.
  */
-unsigned int resctrl_cqm_threshold;
+unsigned int resctrl_rmid_realloc_threshold;
 
 #define CF(cf)	((unsigned long)(1048576 * (cf) + 0.5))
 
@@ -223,14 +226,13 @@ 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;
-	struct rdt_resource *r;
 	u32 crmid = 1, nrmid;
 	bool rmid_dirty;
 	u64 val = 0;
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-
 	/*
 	 * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
 	 * are marked as busy for occupancy < threshold. If the occupancy
@@ -245,10 +247,12 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
 		entry = __rmid_entry(nrmid);
 
 		if (resctrl_arch_rmid_read(r, d, entry->rmid,
-					   QOS_L3_OCCUP_EVENT_ID, &val))
+					   QOS_L3_OCCUP_EVENT_ID, &val)) {
 			rmid_dirty = true;
-		else
-			rmid_dirty = (val >= resctrl_cqm_threshold);
+		} else {
+			val *= hw_res->mon_scale;
+			rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
+		}
 
 		if (force_free || !rmid_dirty) {
 			clear_bit(entry->rmid, d->rmid_busy_llc);
@@ -289,13 +293,12 @@ int alloc_rmid(void)
 
 static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
-	struct rdt_resource *r;
+	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;
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
-
 	entry->busy = 0;
 	cpu = get_cpu();
 	list_for_each_entry(d, &r->domains, list) {
@@ -303,7 +306,8 @@ 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);
-			if (err || val <= resctrl_cqm_threshold)
+			val *= hw_res->mon_scale;
+			if (err || val <= resctrl_rmid_realloc_threshold)
 				continue;
 		}
 
@@ -744,6 +748,7 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
 	unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 	unsigned int cl_size = boot_cpu_data.x86_cache_size;
+	unsigned int threshold;
 	int ret;
 
 	hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
@@ -762,10 +767,14 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
 	 *
 	 * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC.
 	 */
-	resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid;
+	threshold = cl_size * 1024 / r->num_rmid;
 
-	/* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */
-	resctrl_cqm_threshold /= hw_res->mon_scale;
+	/*
+	 * Because num_rmid may not be a power of two, round the value
+	 * to the nearest multiple of hw_res->mon_scale so it matches a
+	 * value the hardware will measure. mon_scale may not be a power of 2.
+	 */
+	resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(threshold);
 
 	ret = dom_data_init(r);
 	if (ret)