[PATCH v12 25/26] x86/resctrl: Introduce the interface to switch between monitor modes

[Babu Moger]

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@xxxxxxx>
---
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@xxxxxxxxx/

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/arch/x86/resctrl.rst     | 25 ++++++++++-
 arch/x86/kernel/cpu/resctrl/internal.h |  2 +
 arch/x86/kernel/cpu/resctrl/monitor.c  | 16 +++++++
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 58 +++++++++++++++++++++++++-
 4 files changed, 99 insertions(+), 2 deletions(-)

diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst
index ad35c38eed34..05f1852ad8e2 100644
--- a/Documentation/arch/x86/resctrl.rst
+++ b/Documentation/arch/x86/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:
 	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_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:
 	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/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 2020a2fe7135..2f3a5d78d153 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -599,6 +599,8 @@ int resctrl_unassign_cntr_event(struct rdt_resource *r, struct rdt_mon_domain *d
 				struct rdtgroup *rdtgrp, enum resctrl_event_id evtid, u32 evt_cfg);
 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);
 
 #ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
 int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 0c6fd5f6ec19..7f2e1fdfa936 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -610,6 +610,17 @@ static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid,
 	}
 }
 
+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);
+}
+
 static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
@@ -1558,6 +1569,11 @@ 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);
+}
+
 /*
  * Allocate a fresh counter and configure the event if not assigned already.
  */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 5d9c4c216522..d10cf1e5b914 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1050,6 +1050,61 @@ static ssize_t resctrl_mbm_assign_on_mkdir_write(struct kernfs_open_file *of,
 	return ret ?: nbytes;
 }
 
+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 = of->kn->parent->priv;
+	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;
+		/*
+		 * 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;
+}
+
 #ifdef CONFIG_PROC_CPU_RESCTRL
 
 /*
@@ -2412,9 +2467,10 @@ 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,
 	},
 	{
-- 
2.34.1