fs/resctrl: Introduce the interface to switch between monitor modes

Resctrl subsystem can support two monitoring modes, "mbm_event" or "default".
In mbm_event mode, monitoring event can only accumulate data while it is
backed by a hardware counter. In "default" mode, resctrl assumes there is
a hardware counter for each event within every CTRL_MON and MON group.

Introduce mbm_assign_mode resctrl file to switch between mbm_event and default
modes.

Example:
To list the MBM monitor modes supported:
  $ cat /sys/fs/resctrl/info/L3_MON/mbm_assign_mode
  [mbm_event]
  default

To enable the "mbm_event" counter assignment mode:
  $ echo "mbm_event" > /sys/fs/resctrl/info/L3_MON/mbm_assign_mode

To enable the "default" monitoring mode:
  $ echo "default" > /sys/fs/resctrl/info/L3_MON/mbm_assign_mode

Reset MBM event counters automatically as part of changing the mode.  Clear
both architectural and non-architectural event states to prevent overflow
conditions during the next event read. Clear assignable counter configuration
on all the domains. Also, enable auto assignment when switching to "mbm_event"
mode.

Signed-off-by: Babu Moger <babu.moger@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/cover.1757108044.git.babu.moger@amd.com

4 files changed, 131 insertions, 4 deletions

diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
index f60f6a96cb6b..006d23af66e1 100644
--- a/Documentation/filesystems/resctrl.rst
+++ b/Documentation/filesystems/resctrl.rst
@@ -259,7 +259,8 @@ with the following files:
 
 "mbm_assign_mode":
 	The supported counter assignment modes. The enclosed brackets indicate which mode
-	is enabled.
+	is enabled. The MBM events associated with counters may reset when "mbm_assign_mode"
+	is changed.
 	::
 
 	  # cat /sys/fs/resctrl/info/L3_MON/mbm_assign_mode
@@ -279,6 +280,15 @@ with the following files:
 	of counters available is described in the "num_mbm_cntrs" file. Changing the
 	mode may cause all counters on the resource to reset.
 
+	Moving to mbm_event counter assignment mode requires users to assign the counters
+	to the events. Otherwise, the MBM event counters will return 'Unassigned' when read.
+
+	The mode is beneficial for AMD platforms that support more CTRL_MON
+	and MON groups than available hardware counters. By default, this
+	feature is enabled on AMD platforms with the ABMC (Assignable Bandwidth
+	Monitoring Counters) capability, ensuring counters remain assigned even
+	when the corresponding RMID is not actively used by any processor.
+
 	"default":
 
 	In default mode, resctrl assumes there is a hardware counter for each
@@ -288,6 +298,16 @@ with the following files:
 	result in misleading values or display "Unavailable" if no counter is assigned
 	to the event.
 
+	* To enable "mbm_event" counter assignment mode:
+	  ::
+
+	    # echo "mbm_event" > /sys/fs/resctrl/info/L3_MON/mbm_assign_mode
+
+	* To enable "default" monitoring mode:
+	  ::
+
+	    # echo "default" > /sys/fs/resctrl/info/L3_MON/mbm_assign_mode
+
 "num_mbm_cntrs":
 	The maximum number of counters (total of available and assigned counters) in
 	each domain when the system supports mbm_event mode.
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index c69b1da80d3f..cf1fd82dc5a9 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -396,6 +396,12 @@ void *rdt_kn_parent_priv(struct kernfs_node *kn);
 
 int resctrl_mbm_assign_mode_show(struct kernfs_open_file *of, struct seq_file *s, void *v);
 
+ssize_t resctrl_mbm_assign_mode_write(struct kernfs_open_file *of, char *buf,
+				      size_t nbytes, loff_t off);
+
+void resctrl_bmec_files_show(struct rdt_resource *r, struct kernfs_node *l3_mon_kn,
+			     bool show);
+
 int resctrl_num_mbm_cntrs_show(struct kernfs_open_file *of, struct seq_file *s, void *v);
 
 int resctrl_available_mbm_cntrs_show(struct kernfs_open_file *of, struct seq_file *s,
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index f388dbcdbdcd..50c24460d992 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -1079,6 +1079,33 @@ out_unlock:
 }
 
 /*
+ * mbm_cntr_free_all() - Clear all the counter ID configuration details in the
+ *			 domain @d. Called when mbm_assign_mode is changed.
+ */
+static void mbm_cntr_free_all(struct rdt_resource *r, struct rdt_mon_domain *d)
+{
+	memset(d->cntr_cfg, 0, sizeof(*d->cntr_cfg) * r->mon.num_mbm_cntrs);
+}
+
+/*
+ * resctrl_reset_rmid_all() - Reset all non-architecture states for all the
+ *			      supported RMIDs.
+ */
+static void resctrl_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
+{
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
+	enum resctrl_event_id evt;
+	int idx;
+
+	for_each_mbm_event_id(evt) {
+		if (!resctrl_is_mon_event_enabled(evt))
+			continue;
+		idx = MBM_STATE_IDX(evt);
+		memset(d->mbm_states[idx], 0, sizeof(*d->mbm_states[0]) * idx_limit);
+	}
+}
+
+/*
  * rdtgroup_assign_cntr() - Assign/unassign the counter ID for the event, RMID
  * pair in the domain.
  *
@@ -1388,6 +1415,79 @@ int resctrl_mbm_assign_mode_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+ssize_t resctrl_mbm_assign_mode_write(struct kernfs_open_file *of, char *buf,
+				      size_t nbytes, loff_t off)
+{
+	struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
+	struct rdt_mon_domain *d;
+	int ret = 0;
+	bool enable;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+
+	buf[nbytes - 1] = '\0';
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	rdt_last_cmd_clear();
+
+	if (!strcmp(buf, "default")) {
+		enable = 0;
+	} else if (!strcmp(buf, "mbm_event")) {
+		if (r->mon.mbm_cntr_assignable) {
+			enable = 1;
+		} else {
+			ret = -EINVAL;
+			rdt_last_cmd_puts("mbm_event mode is not supported\n");
+			goto out_unlock;
+		}
+	} else {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("Unsupported assign mode\n");
+		goto out_unlock;
+	}
+
+	if (enable != resctrl_arch_mbm_cntr_assign_enabled(r)) {
+		ret = resctrl_arch_mbm_cntr_assign_set(r, enable);
+		if (ret)
+			goto out_unlock;
+
+		/* Update the visibility of BMEC related files */
+		resctrl_bmec_files_show(r, NULL, !enable);
+
+		/*
+		 * Initialize the default memory transaction values for
+		 * total and local events.
+		 */
+		if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
+			mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask;
+		if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
+			mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask &
+									   (READS_TO_LOCAL_MEM |
+									    READS_TO_LOCAL_S_MEM |
+									    NON_TEMP_WRITE_TO_LOCAL_MEM);
+		/* Enable auto assignment when switching to "mbm_event" mode */
+		if (enable)
+			r->mon.mbm_assign_on_mkdir = true;
+		/*
+		 * Reset all the non-achitectural RMID state and assignable counters.
+		 */
+		list_for_each_entry(d, &r->mon_domains, hdr.list) {
+			mbm_cntr_free_all(r, d);
+			resctrl_reset_rmid_all(r, d);
+		}
+	}
+
+out_unlock:
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+
+	return ret ?: nbytes;
+}
+
 int resctrl_num_mbm_cntrs_show(struct kernfs_open_file *of,
 			       struct seq_file *s, void *v)
 {
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 0c404a159d45..0320360cd7a6 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -1807,8 +1807,8 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
  * Don't treat kernfs_find_and_get failure as an error, since this function may
  * be called regardless of whether BMEC is supported or the event is enabled.
  */
-static void resctrl_bmec_files_show(struct rdt_resource *r, struct kernfs_node *l3_mon_kn,
-				    bool show)
+void resctrl_bmec_files_show(struct rdt_resource *r, struct kernfs_node *l3_mon_kn,
+			     bool show)
 {
 	struct kernfs_node *kn_config, *mon_kn = NULL;
 	char name[32];
@@ -1985,9 +1985,10 @@ static struct rftype res_common_files[] = {
 	},
 	{
 		.name		= "mbm_assign_mode",
-		.mode		= 0444,
+		.mode		= 0644,
 		.kf_ops		= &rdtgroup_kf_single_ops,
 		.seq_show	= resctrl_mbm_assign_mode_show,
+		.write		= resctrl_mbm_assign_mode_write,
 		.fflags		= RFTYPE_MON_INFO | RFTYPE_RES_CACHE,
 	},
 	{