[PATCH 19/28] x86/intel_rdt/cqm: Add mon_data

[Vikas Shivappa]

Add a mon_data directory for the root rdtgroup and all other rdtgroups.
The directory holds all of the monitored data for all domains and events
of all resources being monitored.

The mon_data itself has a list of directories in the format
mon_<domain_name>_<domain_id>. Each of these subdirectories contain one
file per event in the mode "0444". Reading the file displays a snapshot
of the monitored data for the event the file represents.

For ex, on a 2 socket Broadwell with llc_occupancy being
monitored the mon_data contents look as below:

$ ls /sys/fs/resctrl/p1/mon_data/
mon_L3_00
mon_L3_01

Each domain directory has one file per event:
$ ls /sys/fs/resctrl/p1/mon_data/mon_L3_00/
llc_occupancy

To read current llc_occupancy of ctrl_mon group p1
$ cat /sys/fs/resctrl/p1/mon_data/mon_L3_00/llc_occupancy
33789096

[This patch idea is based on Tony's sample patches to organise data in a
per domain directory and have one file per event (and use the fp->priv to
store mon data bits)]

Signed-off-by: Vikas Shivappa <vikas.shivappa@xxxxxxxxxxxxxxx>
---
 arch/x86/kernel/cpu/intel_rdt.c             |   9 +-
 arch/x86/kernel/cpu/intel_rdt.h             |  29 ++++++
 arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c |  55 ++++++++++-
 arch/x86/kernel/cpu/intel_rdt_monitor.c     |  49 ++++++++++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c    | 145 ++++++++++++++++++++++++++++
 5 files changed, 284 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index cd48ec9..81d1cd3 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -71,6 +71,7 @@
 struct rdt_resource rdt_resources_all[] = {
 	[RDT_RESOURCE_L3] =
 	{
+		.rid			= RDT_RESOURCE_L3,
 		.name			= "L3",
 		.domains		= domain_init(RDT_RESOURCE_L3),
 		.msr_base		= IA32_L3_CBM_BASE,
@@ -87,6 +88,7 @@ struct rdt_resource rdt_resources_all[] = {
 	},
 	[RDT_RESOURCE_L3DATA] =
 	{
+		.rid			= RDT_RESOURCE_L3DATA,
 		.name			= "L3DATA",
 		.domains		= domain_init(RDT_RESOURCE_L3DATA),
 		.msr_base		= IA32_L3_CBM_BASE,
@@ -103,6 +105,7 @@ struct rdt_resource rdt_resources_all[] = {
 	},
 	[RDT_RESOURCE_L3CODE] =
 	{
+		.rid			= RDT_RESOURCE_L3CODE,
 		.name			= "L3CODE",
 		.domains		= domain_init(RDT_RESOURCE_L3CODE),
 		.msr_base		= IA32_L3_CBM_BASE,
@@ -119,6 +122,7 @@ struct rdt_resource rdt_resources_all[] = {
 	},
 	[RDT_RESOURCE_L2] =
 	{
+		.rid			= RDT_RESOURCE_L2,
 		.name			= "L2",
 		.domains		= domain_init(RDT_RESOURCE_L2),
 		.msr_base		= IA32_L2_CBM_BASE,
@@ -135,6 +139,7 @@ struct rdt_resource rdt_resources_all[] = {
 	},
 	[RDT_RESOURCE_MBA] =
 	{
+		.rid			= RDT_RESOURCE_MBA,
 		.name			= "MB",
 		.domains		= domain_init(RDT_RESOURCE_MBA),
 		.msr_base		= IA32_MBA_THRTL_BASE,
@@ -362,8 +367,8 @@ void rdt_ctrl_update(void *arg)
  * caller, return the first domain whose id is bigger than the input id.
  * The domain list is sorted by id in ascending order.
  */
-static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
-					  struct list_head **pos)
+struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
+				   struct list_head **pos)
 {
 	struct rdt_domain *d;
 	struct list_head *l;
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 6f07047..7fcaa5f 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -33,6 +33,27 @@ struct mon_evt {
 	struct list_head	list;
 };
 
+/**
+ * struct mon_data_bits - Monitoring details for each event file
+ * @rid:               Resource id associated with the event file.
+ * @evtid:             Event id associated with the event file
+ * @domid:             The domain to which the event file belongs
+ */
+union mon_data_bits {
+	void *priv;
+	struct {
+		unsigned int rid	: 10;
+		unsigned int evtid	: 8;
+		unsigned int domid	: 14;
+	} u;
+};
+
+struct rmid_read {
+	struct rdtgroup		*rgrp;
+	int			evtid;
+	u64			val;
+};
+
 extern unsigned int intel_cqm_threshold;
 extern bool rdt_alloc_capable;
 extern bool rdt_mon_capable;
@@ -46,11 +67,13 @@ enum rdt_group_type {
 
 /**
  * struct mongroup - store mon group's data in resctrl fs.
+ * @mon_data_kn		kernlfs node for the mon_data directory
  * @parent:			parent rdtgrp
  * @crdtgrp_list:		child rdtgroup node list
  * @rmid:			rmid for this rdtgroup
  */
 struct mongroup {
+	struct kernfs_node	*mon_data_kn;
 	struct rdtgroup		*parent;
 	struct list_head	crdtgrp_list;
 	u32			rmid;
@@ -209,6 +232,7 @@ static inline bool is_llc_occupancy_enabled(void)
 
 /**
  * struct rdt_resource - attributes of an RDT resource
+ * @rid:		The index of the resource
  * @alloc_enabled:	Is allocation enabled on this machine
  * @mon_enabled:		Is monitoring enabled for this feature
  * @alloc_capable:	Is allocation available on this machine
@@ -230,6 +254,7 @@ static inline bool is_llc_occupancy_enabled(void)
  * @fflags:			flags to choose base and info files
  */
 struct rdt_resource {
+	int			rid;
 	bool			alloc_enabled;
 	bool			mon_enabled;
 	bool			alloc_capable;
@@ -323,6 +348,8 @@ enum {
 void rdt_ctrl_update(void *arg);
 struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
 void rdtgroup_kn_unlock(struct kernfs_node *kn);
+struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
+				   struct list_head **pos);
 ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off);
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
@@ -331,5 +358,7 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 int alloc_rmid(void);
 void free_rmid(u32 rmid);
 int rdt_get_mon_l3_config(struct rdt_resource *r);
+void mon_event_count(void *info);
+int rdtgroup_mondata_show(struct seq_file *m, void *arg);
 
 #endif /* _ASM_X86_INTEL_RDT_H */
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 952156c..f44e77d 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -269,7 +269,8 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 {
 	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
-	int closid, ret = 0;
+	int ret = 0;
+	u32 closid;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (rdtgrp) {
@@ -284,3 +285,55 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 	rdtgroup_kn_unlock(of->kn);
 	return ret;
 }
+
+void mon_event_read(struct rmid_read *rr, struct rdt_domain *d,
+		    struct rdtgroup *rdtgrp, int evtid)
+{
+	/*
+	 * setup the parameters to send to the IPI to read the data.
+	 */
+	rr->rgrp = rdtgrp;
+	rr->evtid = evtid;
+	rr->val = 0;
+
+	smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
+}
+
+int rdtgroup_mondata_show(struct seq_file *m, void *arg)
+{
+	struct kernfs_open_file *of = m->private;
+	u32 resid, evtid, domid;
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	union mon_data_bits md;
+	struct rdt_domain *d;
+	struct rmid_read rr;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+
+	md.priv = of->kn->priv;
+	resid = md.u.rid;
+	domid = md.u.domid;
+	evtid = md.u.evtid;
+
+	r = &rdt_resources_all[resid];
+	d = rdt_find_domain(r, domid, NULL);
+	if (!d) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	mon_event_read(&rr, d, rdtgrp, evtid);
+
+	if (rr.val & RMID_VAL_ERROR)
+		seq_puts(m, "Error\n");
+	else if (rr.val & RMID_VAL_UNAVAIL)
+		seq_puts(m, "Unavailable\n");
+	else
+		seq_printf(m, "%llu\n", rr.val * r->mon_scale);
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+	return ret;
+}
diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c
index b6732c5..f8f06f5 100644
--- a/arch/x86/kernel/cpu/intel_rdt_monitor.c
+++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c
@@ -294,6 +294,55 @@ void free_rmid(u32 rmid)
 		list_add_tail(&entry->list, &rmid_free_lru);
 }
 
+static int __mon_event_count(u32 rmid, struct rmid_read *rr)
+{
+	u64 tval;
+
+	tval = __rmid_read(rmid, rr->evtid);
+	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
+		rr->val = tval;
+		return -EINVAL;
+	}
+	switch (rr->evtid) {
+	case QOS_L3_OCCUP_EVENT_ID:
+		rr->val += tval;
+		return 0;
+	default:
+		/*
+		 * Code would never reach here because
+		 * an invalid event id would fail the __rmid_read.
+		 */
+		return -EINVAL;
+	}
+}
+
+/*
+ * This is called via IPI to read the CQM/MBM counters
+ * on a domain.
+ */
+void mon_event_count(void *info)
+{
+	struct rdtgroup *rdtgrp, *entry;
+	struct rmid_read *rr = info;
+	struct list_head *head;
+
+	rdtgrp = rr->rgrp;
+
+	if (__mon_event_count(rdtgrp->mon.rmid, rr))
+		return;
+
+	/*
+	 * For Ctrl groups read data from child monitor groups.
+	 */
+	head = &rdtgrp->mon.crdtgrp_list;
+
+	if (rdtgrp->type == RDTCTRL_GROUP) {
+		list_for_each_entry(entry, head, mon.crdtgrp_list) {
+			if (__mon_event_count(entry->mon.rmid, rr))
+				return;
+		}
+	}
+}
 static int dom_data_init(struct rdt_resource *r)
 {
 	struct rmid_entry *entry = NULL;
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index abc06ea..8f9b54e 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -152,6 +152,11 @@ static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
 	.seq_show		= rdtgroup_seqfile_show,
 };
 
+static struct kernfs_ops kf_mondata_ops = {
+	.atomic_write_len	= PAGE_SIZE,
+	.seq_show		= rdtgroup_mondata_show,
+};
+
 static bool is_cpu_list(struct kernfs_open_file *of)
 {
 	struct rftype *rft = of->kn->priv;
@@ -1218,6 +1223,140 @@ static void rdt_kill_sb(struct super_block *sb)
 	.kill_sb = rdt_kill_sb,
 };
 
+static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
+		       void *priv)
+{
+	struct kernfs_node *kn;
+	int ret = 0;
+
+	kn = __kernfs_create_file(parent_kn, name, 0444, 0,
+				  &kf_mondata_ops, priv, NULL, NULL);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret) {
+		kernfs_remove(kn);
+		return ret;
+	}
+
+	return ret;
+}
+
+static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
+				struct rdt_domain *d,
+				struct rdt_resource *r, struct rdtgroup *prgrp)
+{
+	union mon_data_bits priv;
+	struct kernfs_node *kn;
+	struct mon_evt *mevt;
+	char name[32];
+	int ret;
+
+	sprintf(name, "mon_%s_%02d", r->name, d->id);
+	/* create the directory */
+	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
+
+	/*
+	 * This extra ref will be put in kernfs_remove() and guarantees
+	 * that kn is always accessible.
+	 */
+	kernfs_get(kn);
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret)
+		goto out_destroy;
+
+	if (WARN_ON(list_empty(&r->evt_list))) {
+		ret = -EPERM;
+		goto out_destroy;
+	}
+
+	priv.u.rid = r->rid;
+	priv.u.domid = d->id;
+	list_for_each_entry(mevt, &r->evt_list, list) {
+		priv.u.evtid = mevt->evtid;
+		ret = mon_addfile(kn, mevt->name, priv.priv);
+		if (ret)
+			goto out_destroy;
+	}
+	kernfs_activate(kn);
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn);
+	return ret;
+}
+
+static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
+				       struct rdt_resource *r,
+				       struct rdtgroup *prgrp)
+{
+	struct rdt_domain *dom;
+	int ret;
+
+	list_for_each_entry(dom, &r->domains, list) {
+		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * This creates a directory mon_data which contains the monitored data.
+ *
+ * mon_data has one directory for each domain whic are named
+ * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data
+ * with L3 domain looks as below:
+ * ./mon_data:
+ * mon_L3_00
+ * mon_L3_01
+ * mon_L3_02
+ * ...
+ *
+ * Each domain directory has one file per event:
+ * ./mon_L3_00/:
+ * llc_occupancy
+ *
+ */
+static int mkdir_mondata_all(struct kernfs_node *parent_kn,
+			     struct rdtgroup *prgrp,
+			     struct kernfs_node **dest_kn)
+{
+	struct rdt_resource *r;
+	struct kernfs_node *kn;
+	int ret;
+
+	/*
+	 * Create the mon_data directory first.
+	 */
+	ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn);
+	if (ret)
+		return ret;
+
+	if (dest_kn)
+		*dest_kn = kn;
+
+	/*
+	 * Create the subdirectories for each domain. Note that all events
+	 * in a domain like L3 are grouped into a resource whose domain is L3
+	 */
+	for_each_mon_enabled_rdt_resource(r) {
+		ret = mkdir_mondata_subdir_alldom(kn, r, prgrp);
+		if (ret)
+			goto out_destroy;
+	}
+
+	return 0;
+
+out_destroy:
+	kernfs_remove(kn);
+	return ret;
+}
+
 static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 			     struct kernfs_node *prgrp_kn,
 			     const char *name, umode_t mode,
@@ -1276,6 +1415,10 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 		if (ret < 0)
 			goto out_destroy;
 		rdtgrp->mon.rmid = ret;
+
+		ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
+		if (ret)
+			goto out_idfree;
 	}
 	kernfs_activate(kn);
 
@@ -1284,6 +1427,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	 */
 	return 0;
 
+out_idfree:
+	free_rmid(rdtgrp->mon.rmid);
 out_destroy:
 	kernfs_remove(rdtgrp->kn);
 out_free_rgrp:
-- 
1.9.1