[PATCH v13 26/27] x86/resctrl: Introduce the interface to switch between monitor modes

[Babu Moger <babu.moger@amd.com>]

Resctrl subsystem can support two monitoring modes, "mbm_cntr_assign" or
"default". In mbm_cntr_assign, 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 interface to switch between mbm_cntr_assign and default modes.

$ cat /sys/fs/resctrl/info/L3_MON/mbm_assign_mode
[mbm_cntr_assign]
default

To enable the "mbm_cntr_assign" monitoring mode:
$ echo "mbm_cntr_assign" > /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

MBM event counters are automatically reset as part of changing the mode.
Clear both architectural and non-architectural event states to prevent
overflow conditions during the next event read.

Signed-off-by: Babu Moger <babu.moger@amd.com>
---
v13: Resolved the conflicts due to FS/ARCH restructure.
     Introduced the new resctrl_init_evt_configuration() to initialize
     the event modes and configuration values.
     Added the call to resctrl_bmec_files_show() hide/show BMEC related
     files.

v12: Fixed the documentation for a consistency.
     Introduced mbm_cntr_free_all() and resctrl_reset_rmid_all() to clear
     counters and non-architectural states when monitor mode is changed.
     https://lore.kernel.org/lkml/b60b4f72-6245-46db-a126-428fb13b6310@intel.com/

v11: Changed the name of the function rdtgroup_mbm_assign_mode_write() to
     resctrl_mbm_assign_mode_write().
     Rewrote the commit message with context.
     Added few more details in resctrl.rst about mbm_cntr_assign mode.
     Re-arranged the text in resctrl.rst file.

v10: The call mbm_cntr_reset() has been moved to earlier patch.
     Minor documentation update.

v9: Fixed extra spaces in user documentation.
    Fixed problem changing the mode to mbm_cntr_assign mode when it is
    not supported. Added extra checks to detect if systems supports it.
    Used the rdtgroup_cntr_id_init to initialize cntr_id.

v8: Reset the internal counters after mbm_cntr_assign mode is changed.
    Renamed rdtgroup_mbm_cntr_reset() to mbm_cntr_reset()
    Updated the documentation to make text generic.

v7: Changed the interface name to mbm_assign_mode.
    Removed the references of ABMC.
    Added the changes to reset global and domain bitmaps.
    Added the changes to reset rmid.

v6: Changed the mode name to mbm_cntr_assign.
    Moved all the FS related code here.
    Added changes to reset mbm_cntr_map and resctrl group counters.

v5: Change log and mode description text correction.

v4: Minor commit text changes. Keep the default to ABMC when supported.
    Fixed comments to reflect changed interface "mbm_mode".

v3: New patch to address the review comments from upstream.
---
 Documentation/filesystems/resctrl.rst | 25 ++++++++++-
 fs/resctrl/internal.h                 |  3 ++
 fs/resctrl/monitor.c                  | 53 +++++++++++++++++++---
 fs/resctrl/rdtgroup.c                 | 65 ++++++++++++++++++++++++++-
 4 files changed, 138 insertions(+), 8 deletions(-)

diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
index d779554a2f91..7c304821ce93 100644
--- a/Documentation/filesystems/resctrl.rst
+++ b/Documentation/filesystems/resctrl.rst
@@ -259,7 +259,10 @@ with the following files:
 
 "mbm_assign_mode":
 	Reports the list of monitoring modes supported. The enclosed brackets
-	indicate which mode is enabled.
+	indicate which mode is enabled. The MBM events (mbm_total_bytes and/or
+	mbm_local_bytes) associated with counters may reset when "mbm_assign_mode"
+	is changed.
+
 	::
 
 	  # cat /sys/fs/resctrl/info/L3_MON/mbm_assign_mode
@@ -275,6 +278,16 @@ with the following files:
 	"num_mbm_cntrs" file. Changing the mode may cause all counters on the
 	resource to reset.
 
+	Moving to mbm_cntr_assign mode require 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
@@ -284,6 +297,16 @@ with the following files:
 	counters. This can result in misleading values or display "Unavailable"
 	if no counter is assigned to the event.
 
+	* To enable "mbm_cntr_assign" monitoring mode:
+	  ::
+
+	    # echo "mbm_cntr_assign" > /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 monitoring counters (total of available and assigned
 	counters) in each domain when the system supports mbm_cntr_assign mode.
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index a6069a5dfd49..d5edb28a8df7 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -404,6 +404,9 @@ int resctrl_unassign_cntr_event(struct rdt_resource *r, struct rdt_mon_domain *d
 				struct rdtgroup *rdtgrp, enum resctrl_event_id evtid);
 int mbm_cntr_get(struct rdt_resource *r, struct rdt_mon_domain *d,
 		 struct rdtgroup *rdtgrp, enum resctrl_event_id evtid);
+void resctrl_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d);
+void mbm_cntr_free_all(struct rdt_resource *r, struct rdt_mon_domain *d);
+void resctrl_init_evt_configuration(struct rdt_resource *r, bool enable);
 
 #ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
 int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index b982540ce4e3..bebe83cf48d5 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -911,16 +911,13 @@ int resctrl_mon_resource_init(void)
 
 	l3_mon_evt_init(r);
 
-	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) {
-		mbm_total_event.mbm_mode = MBM_MODE_BMEC;
+	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID))
 		resctrl_file_fflags_init("mbm_total_bytes_config",
 					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
-	}
-	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID)) {
-		mbm_local_event.mbm_mode = MBM_MODE_BMEC;
+
+	if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID))
 		resctrl_file_fflags_init("mbm_local_bytes_config",
 					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
-	}
 
 	if (resctrl_arch_is_mbm_local_enabled())
 		mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
@@ -938,6 +935,8 @@ int resctrl_mon_resource_init(void)
 		resctrl_file_fflags_init("mbm_L3_assignments", RFTYPE_MON_BASE);
 	}
 
+	resctrl_init_evt_configuration(r, true);
+
 	return 0;
 }
 
@@ -1010,6 +1009,25 @@ static void mbm_cntr_free(struct rdt_mon_domain *d, int cntr_id)
 	memset(&d->cntr_cfg[cntr_id], 0, sizeof(struct mbm_cntr_cfg));
 }
 
+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);
+}
+
+/*
+ * Reset all non-architecture states for all the supported RMIDs.
+ */
+void resctrl_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
+{
+	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
+
+	if (resctrl_arch_is_mbm_total_enabled())
+		memset(d->mbm_total, 0, sizeof(struct mbm_state) * idx_limit);
+
+	if (resctrl_arch_is_mbm_local_enabled())
+		memset(d->mbm_local, 0, sizeof(struct mbm_state) * idx_limit);
+}
+
 /*
  * mbm_get_mon_event() - Return the mon_evt entry for the matching evtid.
  */
@@ -1119,6 +1137,29 @@ static int resctrl_free_config_cntr(struct rdt_resource *r, struct rdt_mon_domai
 	return 0;
 }
 
+/*
+ * Initialize the event modes and configuration values.
+ *
+ * total event is set to count all the supported memory transactions.
+ * local event is set to count all the local memory transactions.
+ */
+void resctrl_init_evt_configuration(struct rdt_resource *r, bool enable)
+{
+	if (resctrl_arch_mbm_cntr_assign_enabled(r)) {
+		mbm_total_event.mbm_mode = MBM_MODE_ASSIGN;
+		mbm_total_event.evt_cfg = MAX_EVT_CONFIG_BITS;
+		mbm_local_event.mbm_mode = MBM_MODE_ASSIGN;
+		mbm_local_event.evt_cfg = READS_TO_LOCAL_MEM |
+					  NON_TEMP_WRITE_TO_LOCAL_MEM |
+					  READS_TO_LOCAL_S_MEM;
+	} else {
+		if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID))
+			mbm_total_event.mbm_mode = MBM_MODE_BMEC;
+		if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID))
+			mbm_local_event.mbm_mode = MBM_MODE_BMEC;
+	}
+}
+
 /*
  * Unassign a hardware counter associated with @evtid from the domain and
  * the group. Unassign the counters from all the domains if @d is NULL else
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index d6bf2a50a105..c76d598e4d23 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -1872,6 +1872,68 @@ static int resctrl_mbm_assign_mode_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+static 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_cntr_assign")) {
+		if (r->mon.mbm_cntr_assignable) {
+			enable = 1;
+		} else {
+			ret = -EINVAL;
+			rdt_last_cmd_puts("mbm_cntr_assign mode is not supported\n");
+			goto write_exit;
+		}
+	} else {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("Unsupported assign mode\n");
+		goto write_exit;
+	}
+
+	if (enable != resctrl_arch_mbm_cntr_assign_enabled(r)) {
+		ret = resctrl_arch_mbm_cntr_assign_set(r, enable);
+		if (ret)
+			goto write_exit;
+
+		/* Initialize event configuration details accordingly */
+		resctrl_init_evt_configuration(r, enable);
+
+		/* Update the visibility of BMEC related files */
+		resctrl_bmec_files_show(r, !enable);
+
+		/*
+		 * 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);
+		}
+	}
+
+write_exit:
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+
+	return ret ?: nbytes;
+}
+
 static int resctrl_num_mbm_cntrs_show(struct kernfs_open_file *of,
 				      struct seq_file *s, void *v)
 {
@@ -2462,9 +2524,10 @@ 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,
 	},
 	{
-- 
2.34.1