Preparatory work for MPAM counter assignment:

- Simplify the error handling path when creating monitor group event
   configuration directories
 
 - Make the MBM event filter configurable only on architectures that
   support it and expose this with the respective file modes in the event
   config
 
 - Disallow the MBA software controller on systems where MBM counters are
   assignable, as it requires continuous bandwidth measurement that
   assignable counters do not guarantee
 
 - Replace a compile-time Kconfig option for fixed counter assignment
   with a per-architecture runtime property, and expose whether the
   counter assignment mode is changeable to userspace
 
 - Continue counter allocation across all domains instead of aborting at
   the first failure
 
 - Document that automatic MBM counter assignment is best effort and may
   not assign counters to all domains
 
 - Document the behavior of task ID 0 and idle tasks in the resctrl tasks
   file
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmowEfYACgkQEsHwGGHe
 VUoqpA//SQnC9ehAKVg+tf/V0H5s4sAQimTI3fl9pMYWfduoHCQkdPs/lSWF4Su+
 YNhjr/+nffC1oqSpklG2XEDHYD3HoKnBqSrALX0lmEVPr4MHtAnOAQs/G57Jqp8G
 p1nniOgPqwDltndHYUl2vLX/dFpjIprqPG3lWfjPCFUzrVaOlTPd7Kkv8kSdmZOL
 IYMpMP8IPjA8QfLdGtcqKbtjsNu6gxNs9TS2pXSyy/NuPqaS9CAzsOwj0KNlYPOk
 Hi7KVXc87GAHAUS1LK8+ZjEao/BHtUE8XJlsnTNtPlvwfS7uuOCIrrQyooJS8uT4
 CKv5KbCxZKlRlWNnZLW6IsfYd85N+7gse9n0U2BNlqMor535AEp/X5bka6QO4mLa
 CuN72A8Tkw2bNEcUfOc1akeKNj7bQ9lgz0AESJefmaFNkLmaWJi5mNA/27JFAXBQ
 KfGvPHlKcwt7e8Mj3OaDnhEstf9kVppD2NAL+tl5eGA0mHixyK0WNrDqX1ZjiPkL
 Lf2w5bHA0tTUPtFR/71RqWyHL5N7jjctC6aeVmGDgji7dIkodD8bUFEj/ORY02iS
 oAX7n0E8ccC/E8+jAb8n+zukpbHE4V2ASr+tncLuGVNRuq03YfK5RXIwK0wN6OnM
 dDN1DjaNNMI5pkB48zytDhl1RK6QKVtOqBRBO2TMbQHypnjUMDI=
 =6iVq
 -----END PGP SIGNATURE-----

Merge tag 'x86_cache_for_v7.2_rc1' of gitolite.kernel.org:pub/scm/linux/kernel/git/tip/tip

Pull x86 resource control updates from Borislav Petkov:
 "Preparatory work for MPAM counter assignment:

   - Simplify the error handling path when creating monitor group event
     configuration directories

   - Make the MBM event filter configurable only on architectures that
     support it and expose this with the respective file modes in the
     event config

   - Disallow the MBA software controller on systems where MBM counters
     are assignable, as it requires continuous bandwidth measurement
     that assignable counters do not guarantee

   - Replace a compile-time Kconfig option for fixed counter assignment
     with a per-architecture runtime property, and expose whether the
     counter assignment mode is changeable to userspace

   - Continue counter allocation across all domains instead of aborting
     at the first failure

   - Document that automatic MBM counter assignment is best effort and
     may not assign counters to all domains

   - Document the behavior of task ID 0 and idle tasks in the resctrl
     tasks file"

* tag 'x86_cache_for_v7.2_rc1' of gitolite.kernel.org:pub/scm/linux/kernel/git/tip/tip:
  fs/resctrl: Document tasks file behaviour for task id 0 and idle tasks
  fs/resctrl: Document that automatic counter assignment is best effort
  fs/resctrl: Continue counter allocation after failure
  fs/resctrl: Add monitor property 'mbm_cntr_assign_fixed'
  fs/resctrl: Disallow the software controller when MBM counters are assignable
  x86,fs/resctrl: Create 'event_filter' files read only if they're not configurable
  fs/resctrl: Tidy up the error path in resctrl_mkdir_event_configs()

Documentation/filesystems/resctrl.rst

@@ -427,9 +427,9 @@ with the following files:
 
 	Two MBM events are supported by default: mbm_local_bytes and mbm_total_bytes.
 	Each MBM event's sub-directory contains a file named "event_filter" that is
-	used to view and modify which memory transactions the MBM event is configured
-	with. The file is accessible only when "mbm_event" counter assignment mode is
-	enabled.
+	used to view and (if writable) modify which memory transactions the MBM event
+	is configured with. The file is accessible only when "mbm_event" counter
+	assignment mode is enabled.
 
 	List of memory transaction types supported:
 
@@ -454,9 +454,8 @@ with the following files:
 	  # cat /sys/fs/resctrl/info/L3_MON/event_configs/mbm_local_bytes/event_filter
 	  local_reads,local_non_temporal_writes,local_reads_slow_memory
 
-	Modify the event configuration by writing to the "event_filter" file within
-	the "event_configs" directory. The read/write "event_filter" file contains the
-	configuration of the event that reflects which memory transactions are counted by it.
+	The memory transactions the MBM event is configured with can be changed
+	if "event_filter" is writable.
 
 	For example::
 
@@ -480,6 +479,12 @@ with the following files:
 	"1":
 		Auto assignment is enabled.
 
+	Automatic counter assignment is done with best effort. If auto
+	assignment is enabled but there are not enough available counters then
+	monitor group creation could succeed while one or more events belonging
+	to the group may not have a counter assigned in all domains. Consult
+	mbm_L3_assignments for counter assignment states of the new groups.
+
 	Example::
 
 	  # echo 0 > /sys/fs/resctrl/info/L3_MON/mbm_assign_on_mkdir
@@ -570,6 +575,11 @@ All groups contain the following files:
 	then the task must already belong to the CTRL_MON parent of this
 	group. The task is removed from any previous MON group.
 
+	When writing to this file, a task id of 0 is interpreted as the
+	task id of the currently running task. On reading the file, a task
+	id of 0 will never be shown and there is no representation of the
+	idle tasks. Instead, a CPU's idle task is always considered as a
+	member of the group owning the CPU.
 
 "cpus":
 	Reading this file shows a bitmask of the logical CPUs owned by

arch/x86/kernel/cpu/resctrl/monitor.c

@@ -460,6 +460,7 @@ int __init rdt_get_l3_mon_config(struct rdt_resource *r)
 	    (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL) ||
 	     rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL))) {
 		r->mon.mbm_cntr_assignable = true;
+		r->mon.mbm_cntr_configurable = true;
 		cpuid_count(0x80000020, 5, &eax, &ebx, &ecx, &edx);
 		r->mon.num_mbm_cntrs = (ebx & GENMASK(15, 0)) + 1;
 		hw_res->mbm_cntr_assign_enabled = true;

fs/resctrl/internal.h

@@ -408,6 +408,8 @@ void __check_limbo(struct rdt_l3_mon_domain *d, bool force_free);
 
 void resctrl_file_fflags_init(const char *config, unsigned long fflags);
 
+void resctrl_file_mode_init(const char *config, umode_t mode);
+
 void rdt_staged_configs_clear(void);
 
 bool closid_allocated(unsigned int closid);

fs/resctrl/monitor.c

@@ -1211,9 +1211,10 @@ static int rdtgroup_alloc_assign_cntr(struct rdt_resource *r, struct rdt_l3_mon_
  * NULL; otherwise, assign the counter to the specified domain @d.
  *
  * If all counters in a domain are already in use, rdtgroup_alloc_assign_cntr()
- * will fail. The assignment process will abort at the first failure encountered
- * during domain traversal, which may result in the event being only partially
- * assigned.
+ * will fail. When attempting to assign counters to all domains, carry on trying
+ * to assign counters after a failure since only some domains may have counters
+ * and the goal is to assign counters where possible. If any counter assignment
+ * fails, return the error from the last failing assignment.
  *
  * Return:
  * 0 on success, < 0 on failure.
@@ -1226,9 +1227,11 @@ static int rdtgroup_assign_cntr_event(struct rdt_l3_mon_domain *d, struct rdtgro
 
 	if (!d) {
 		list_for_each_entry(d, &r->mon_domains, hdr.list) {
-			ret = rdtgroup_alloc_assign_cntr(r, d, rdtgrp, mevt);
-			if (ret)
-				return ret;
+			int err;
+
+			err = rdtgroup_alloc_assign_cntr(r, d, rdtgrp, mevt);
+			if (err)
+				ret = err;
 		}
 	} else {
 		ret = rdtgroup_alloc_assign_cntr(r, d, rdtgrp, mevt);
@@ -1422,6 +1425,11 @@ ssize_t event_filter_write(struct kernfs_open_file *of, char *buf, size_t nbytes
 		ret = -EINVAL;
 		goto out_unlock;
 	}
+	if (!r->mon.mbm_cntr_configurable) {
+		rdt_last_cmd_puts("event_filter is not configurable\n");
+		ret = -EPERM;
+		goto out_unlock;
+	}
 
 	ret = resctrl_parse_mem_transactions(buf, &evt_cfg);
 	if (!ret && mevt->evt_cfg != evt_cfg) {
@@ -1451,7 +1459,7 @@ int resctrl_mbm_assign_mode_show(struct kernfs_open_file *of,
 		else
 			seq_puts(s, "[default]\n");
 
-		if (!IS_ENABLED(CONFIG_RESCTRL_ASSIGN_FIXED)) {
+		if (!r->mon.mbm_cntr_assign_fixed) {
 			if (enabled)
 				seq_puts(s, "default\n");
 			else
@@ -1502,6 +1510,12 @@ ssize_t resctrl_mbm_assign_mode_write(struct kernfs_open_file *of, char *buf,
 	}
 
 	if (enable != resctrl_arch_mbm_cntr_assign_enabled(r)) {
+		if (r->mon.mbm_cntr_assign_fixed) {
+			ret = -EINVAL;
+			rdt_last_cmd_puts("Counter assignment mode is not configurable\n");
+			goto out_unlock;
+		}
+
 		ret = resctrl_arch_mbm_cntr_assign_set(r, enable);
 		if (ret)
 			goto out_unlock;
@@ -1886,6 +1900,8 @@ int resctrl_l3_mon_resource_init(void)
 		resctrl_file_fflags_init("available_mbm_cntrs",
 					 RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
 		resctrl_file_fflags_init("event_filter", RFTYPE_ASSIGN_CONFIG);
+		if (r->mon.mbm_cntr_configurable)
+			resctrl_file_mode_init("event_filter", 0644);
 		resctrl_file_fflags_init("mbm_assign_on_mkdir", RFTYPE_MON_INFO |
 					 RFTYPE_RES_CACHE);
 		resctrl_file_fflags_init("mbm_L3_assignments", RFTYPE_MON_BASE);

fs/resctrl/rdtgroup.c

@@ -2022,7 +2022,7 @@ static struct rftype res_common_files[] = {
 	},
 	{
 		.name		= "event_filter",
-		.mode		= 0644,
+		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
 		.seq_show	= event_filter_show,
 		.write		= event_filter_write,
@@ -2215,6 +2215,15 @@ void resctrl_file_fflags_init(const char *config, unsigned long fflags)
 		rft->fflags = fflags;
 }
 
+void resctrl_file_mode_init(const char *config, umode_t mode)
+{
+	struct rftype *rft;
+
+	rft = rdtgroup_get_rftype_by_name(config);
+	if (rft)
+		rft->mode = mode;
+}
+
 /**
  * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
  * @r: The resource group with which the file is associated.
@@ -2331,22 +2340,19 @@ static int resctrl_mkdir_event_configs(struct rdt_resource *r, struct kernfs_nod
 			continue;
 
 		kn_subdir2 = kernfs_create_dir(kn_subdir, mevt->name, kn_subdir->mode, mevt);
-		if (IS_ERR(kn_subdir2)) {
-			ret = PTR_ERR(kn_subdir2);
-			goto out;
-		}
+		if (IS_ERR(kn_subdir2))
+			return PTR_ERR(kn_subdir2);
 
 		ret = rdtgroup_kn_set_ugid(kn_subdir2);
 		if (ret)
-			goto out;
+			return ret;
 
 		ret = rdtgroup_add_files(kn_subdir2, RFTYPE_ASSIGN_CONFIG);
 		if (ret)
-			break;
+			return ret;
 	}
 
-out:
-	return ret;
+	return 0;
 }
 
 static int rdtgroup_mkdir_info_resdir(void *priv, char *name,
@@ -2510,10 +2516,13 @@ static void mba_sc_domain_destroy(struct rdt_resource *r,
 }
 
 /*
- * MBA software controller is supported only if
- * MBM is supported and MBA is in linear scale,
- * and the MBM monitor scope is the same as MBA
- * control scope.
+ * The MBA software controller is supported only if MBM is supported and MBA is
+ * in linear scale, and the MBM monitor scope is the same as MBA control scope.
+ *
+ * The software controller cannot be supported when the MBM counters are
+ * assignable.  There is no guarantee that MBM counters are assigned to the
+ * event backing the software controller in all monitoring domains of all
+ * monitoring groups.
  */
 static bool supports_mba_mbps(void)
 {
@@ -2522,7 +2531,8 @@ static bool supports_mba_mbps(void)
 
 	return (resctrl_is_mbm_enabled() &&
 		r->alloc_capable && is_mba_linear() &&
-		r->ctrl_scope == rmbm->mon_scope);
+		r->ctrl_scope == rmbm->mon_scope &&
+		!rmbm->mon.mbm_cntr_assignable);
 }
 
 /*
@@ -2937,7 +2947,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		ctx->enable_cdpl2 = true;
 		return 0;
 	case Opt_mba_mbps:
-		msg = "mba_MBps requires MBM and linear scale MBA at L3 scope";
+		msg = "mba_MBps requires MBM (mbm_event mode not supported) and linear scale MBA at L3 scope";
 		if (!supports_mba_mbps())
 			return invalfc(fc, msg);
 		ctx->enable_mba_mbps = true;

include/linux/resctrl.h

@@ -286,13 +286,15 @@ enum resctrl_schema_fmt {
 
 /**
  * struct resctrl_mon - Monitoring related data of a resctrl resource.
- * @num_rmid:		Number of RMIDs available.
- * @mbm_cfg_mask:	Memory transactions that can be tracked when bandwidth
- *			monitoring events can be configured.
- * @num_mbm_cntrs:	Number of assignable counters.
- * @mbm_cntr_assignable:Is system capable of supporting counter assignment?
- * @mbm_assign_on_mkdir:True if counters should automatically be assigned to MBM
- *			events of monitor groups created via mkdir.
+ * @num_rmid:			Number of RMIDs available.
+ * @mbm_cfg_mask:		Memory transactions that can be tracked when
+ *				bandwidth monitoring events can be configured.
+ * @num_mbm_cntrs:		Number of assignable counters.
+ * @mbm_cntr_assignable:	Is system capable of supporting counter assignment?
+ * @mbm_assign_on_mkdir:	True if counters should automatically be assigned to MBM
+ *				events of monitor groups created via mkdir.
+ * @mbm_cntr_configurable:	True if assignable counters are configurable.
+ * @mbm_cntr_assign_fixed:	True if the counter assignment mode is fixed.
  */
 struct resctrl_mon {
 	u32			num_rmid;
@@ -300,6 +302,8 @@ struct resctrl_mon {
 	int			num_mbm_cntrs;
 	bool			mbm_cntr_assignable;
 	bool			mbm_assign_on_mkdir;
+	bool			mbm_cntr_configurable;
+	bool			mbm_cntr_assign_fixed;
 };
 
 /**