[PATCH 3/3] x86/resctrl: Display cache occupancy of busy RMIDs

[Haifeng Xu]

If llc_occupany is enabled, the RMID may not be freed immediately unless
its llc_occupany is less than the resctrl_rmid_realloc_threshold.

In our production environment, those unused RMIDs get stuck in the limbo
list forever because their llc_occupancy are larger than the threshold.
After turning it up , we can successfully free unused RMIDs and create
new monitor groups. In order to accquire the llc_occupancy of RMIDs in
each rdt domain, we use perf tool to track and filter the log manually.

It's not efficient enough. Therefore, we can add a RFTYPE_TOP_INFO file
'busy_rmids_info' that tells users the llc_occupancy of busy RMIDs. It
can also help to guide users how much the resctrl_rmid_realloc_threshold
should be.

Signed-off-by: Haifeng Xu <haifeng.xu@xxxxxxxxxx>
---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 70 ++++++++++++++++++++++++++
 1 file changed, 70 insertions(+)

diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 1eac0ca97b81..88dadb87f4e1 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -32,6 +32,12 @@
 #include <asm/resctrl.h>
 #include "internal.h"
 
+struct busy_rmids_info {
+	struct rdt_resource *r;
+	struct rdt_domain *d;
+	struct seq_file *seq;
+};
+
 DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
 DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
 DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
@@ -934,6 +940,63 @@ static int rdt_free_rmids_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+void rdt_domain_busy_rmids_show(void *info)
+{
+
+        struct rdt_resource *r;
+        struct rdt_domain *d;
+        struct seq_file *seq;
+        struct busy_rmids_info *rmids_info = info;
+        u32 crmid = 1, nrmid;
+        u64 val;
+        int ret;
+
+        r = rmids_info->r;
+        d = rmids_info->d;
+        seq = rmids_info->seq;
+
+        seq_printf(seq, "domain-%d busy rmids.\n", d->id);
+
+        for (;;) {
+                nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid, crmid);
+                if (nrmid >= r->num_rmid)
+                        break;
+
+                ret = resctrl_arch_rmid_read(r, d, nrmid, QOS_L3_OCCUP_EVENT_ID, &val);
+                switch (ret) {
+                case -EIO:
+                        seq_printf(seq, "I/O Error\n");
+                        return;
+                case -EINVAL:
+                        seq_printf(seq, "Invalid Argument\n");
+                        return;
+                default:
+                        seq_printf(seq, "rmid:%d llc_occupancy:%llu\n", nrmid, val);
+                }
+                crmid = nrmid + 1;
+        }
+}
+
+static int rdt_busy_rmids_info_show(struct kernfs_open_file *of,
+                                    struct seq_file *seq, void *v)
+{
+
+        struct rdt_domain *d;
+        struct rdt_resource *r;
+        struct busy_rmids_info info;
+
+        mutex_lock(&rdtgroup_mutex);
+        r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+        info.r = r;
+        info.seq = seq;
+        list_for_each_entry(d, &r->domains, list) {
+                info.d = d;
+                smp_call_function_any(&d->cpu_mask, rdt_domain_busy_rmids_show, &info, 1);
+        }
+        mutex_unlock(&rdtgroup_mutex);
+        return 0;
+}
+
 static int rdt_num_closids_show(struct kernfs_open_file *of,
 				struct seq_file *seq, void *v)
 {
@@ -1791,6 +1854,13 @@ static struct rftype res_common_files[] = {
 		.seq_show       = rdt_free_rmids_show,
 		.fflags         = RFTYPE_TOP_INFO,
 	},
+	{
+		.name           = "busy_rmids_info",
+		.mode           = 0444,
+		.kf_ops         = &rdtgroup_kf_single_ops,
+		.seq_show       = rdt_busy_rmids_info_show,
+		.fflags         = RFTYPE_TOP_INFO,
+	},
 	{
 		.name		= "num_closids",
 		.mode		= 0444,
-- 
2.25.1