Merge tag 'x86_cache_for_v7.4_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 resource control updates from Borislav Petkov:

 - Push down into arch code the rounding of bandwidth control user
   values due to the different ways ARM and x86 report MBA

 - Fix task reporting for the default group for systems which support
   only bandwidth monitoring, aka Haswell vintage computing

 - The usual fixlets and improvements

* tag 'x86_cache_for_v7.4_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  fs/resctrl: Ensure default group reports tasks on monitor-only systems
  x86,fs/resctrl: Add event group descriptions for Intel Diamond Rapids
  x86/resctrl: Update documented unit for the "activity" event
  fs/resctrl: Simplify pseudo_lock_measure_trigger()
  fs/resctrl: Avoid extra call to strlen() in schemata_list_add()
  fs/resctrl: Factor MBA parse-time conversion to be per-arch
  arm_mpam: resctrl: Add pass-through resctrl_arch_preconvert_bw()
  x86,fs/resctrl: Add resctrl_arch_preconvert_bw()

10 files changed, 86 insertions, 26 deletions

diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
index e4b66af55ffb..b52795e03303 100644
--- a/Documentation/filesystems/resctrl.rst
+++ b/Documentation/filesystems/resctrl.rst
@@ -236,12 +236,11 @@ with respect to allocation:
 		user can request.
 
 "bandwidth_gran":
-		The granularity in which the memory bandwidth
-		percentage is allocated. The allocated
-		b/w percentage is rounded off to the next
-		control step available on the hardware. The
-		available bandwidth control steps are:
-		min_bandwidth + N * bandwidth_gran.
+		The approximate granularity in which the memory bandwidth
+		percentage is allocated. The allocated bandwidth percentage is
+		rounded up or down to the closest control step available on the
+		hardware. The available hardware steps are no larger than this
+		value.
 
 "delay_linear":
 		Indicates if the delay scale is linear or
@@ -643,7 +642,7 @@ When monitoring is enabled all MON groups will also contain:
 	during execution of instructions summed across all logical CPUs on a
 	package for the current monitoring group.
 
-	"activity" also reports a floating point value (in Farads).  This provides
+	"activity" also reports a floating point value (in nanofarads).  This provides
 	an estimate of work done independent of the frequency that the CPUs used
 	for execution.
 
@@ -881,8 +880,10 @@ The minimum bandwidth percentage value for each cpu model is predefined
 and can be looked up through "info/MB/min_bandwidth". The bandwidth
 granularity that is allocated is also dependent on the cpu model and can
 be looked up at "info/MB/bandwidth_gran". The available bandwidth
-control steps are: min_bw + N * bw_gran. Intermediate values are rounded
-to the next control step available on the hardware.
+control steps are, approximately, min_bw + N * bw_gran.  The steps may
+appear irregular due to rounding to an exact percentage: bw_gran is the
+maximum interval between the percentage values corresponding to any two
+adjacent steps in the hardware.
 
 The bandwidth throttling is a core specific mechanism on some of Intel
 SKUs. Using a high bandwidth and a low bandwidth setting on two threads
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index e74f1ed54b86..62044489b052 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -16,9 +16,15 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/cpu.h>
+#include <linux/math.h>
 
 #include "internal.h"
 
+u32 resctrl_arch_preconvert_bw(const struct rdt_resource *r, u32 val)
+{
+	return roundup(val, (unsigned long)r->membw.bw_gran);
+}
+
 int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 			    u32 closid, enum resctrl_conf_type t, u32 cfg_val)
 {
diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
index c22c3cf5167d..66cd8c2c7a51 100644
--- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -125,9 +125,43 @@ static struct event_group perf_0x26557651 = {
 	}
 };
 
+/*
+ * Link: https://github.com/intel/Intel-PMT/blob/main/xml/DMR/OOBMSM/RMID-ENERGY/dmr_aggregator.xml
+ */
+static struct event_group energy_0x47903099 = {
+	.pfname		= "energy",
+	.guid		= 0x47903099,
+	.num_rmid	= 256,
+	.mmio_size	= XML_MMIO_SIZE(256, 2, 3),
+	.num_events	= 2,
+	.evts		= {
+		EVT(PMT_EVENT_ENERGY, 0, 18),
+		EVT(PMT_EVENT_ACTIVITY, 1, 18),
+	}
+};
+
+/*
+ * Link: https://github.com/intel/Intel-PMT/blob/main/xml/DMR/OOBMSM/RMID-PERF/dmr_aggregator.xml
+ */
+static struct event_group perf_0x1415910a = {
+	.pfname		= "perf",
+	.guid		= 0x1415910a,
+	.num_rmid	= 256,
+	.mmio_size	= XML_MMIO_SIZE(256, 4, 3),
+	.num_events	= 4,
+	.evts		= {
+		EVT(PMT_EVENT_UNHALTED_REF_CYCLES, 0, 0),
+		EVT(PMT_EVENT_UNHALTED_CORE_CYCLES, 1, 0),
+		EVT(PMT_EVENT_INST_RETIRED, 2, 0),
+		EVT(PMT_EVENT_PCNT, 3, 0),
+	}
+};
+
 static struct event_group *known_event_groups[] = {
 	&energy_0x26696143,
+	&energy_0x47903099,
 	&perf_0x26557651,
+	&perf_0x1415910a,
 };
 
 #define for_each_event_group(_peg)						\
diff --git a/drivers/resctrl/mpam_resctrl.c b/drivers/resctrl/mpam_resctrl.c
index 9cec5843e8fa..5468367776e2 100644
--- a/drivers/resctrl/mpam_resctrl.c
+++ b/drivers/resctrl/mpam_resctrl.c
@@ -148,6 +148,11 @@ bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level rid)
 	return mpam_resctrl_controls[rid].cdp_enabled;
 }
 
+u32 resctrl_arch_preconvert_bw(const struct rdt_resource *r, u32 val)
+{
+	return val;
+}
+
 /**
  * resctrl_reset_task_closids() - Reset the PARTID/PMG values for all tasks.
  *
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index 18ec9f564b5a..cafebdff70dc 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -37,8 +37,8 @@ typedef int (ctrlval_parser_t)(struct rdt_parse_data *data,
 /*
  * Check whether MBA bandwidth percentage value is correct. The value is
  * checked against the minimum and max bandwidth values specified by the
- * hardware. The allocated bandwidth percentage is rounded to the next
- * control step available on the hardware.
+ * hardware. The allocated bandwidth percentage is converted as appropriate
+ * for consumption by the specific hardware driver.
  */
 static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r)
 {
@@ -71,7 +71,7 @@ static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r)
 		return false;
 	}
 
-	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
+	*data = resctrl_arch_preconvert_bw(r, bw);
 	return true;
 }
 
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index 73413cb128ea..04e4ea612b7c 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -1041,6 +1041,8 @@ struct mon_evt mon_event_all[QOS_NUM_EVENTS] = {
 	MON_EVENT(PMT_EVENT_AUTO_C6_RES,		"c6_res",		RDT_RESOURCE_PERF_PKG,	false),
 	MON_EVENT(PMT_EVENT_UNHALTED_REF_CYCLES,	"unhalted_ref_cycles",	RDT_RESOURCE_PERF_PKG,	false),
 	MON_EVENT(PMT_EVENT_UOPS_RETIRED,		"uops_retired",		RDT_RESOURCE_PERF_PKG,	false),
+	MON_EVENT(PMT_EVENT_INST_RETIRED,		"inst_retired",		RDT_RESOURCE_PERF_PKG,	false),
+	MON_EVENT(PMT_EVENT_PCNT,			"pcnt",			RDT_RESOURCE_PERF_PKG,	false),
 };
 
 bool resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,
diff --git a/fs/resctrl/pseudo_lock.c b/fs/resctrl/pseudo_lock.c
index dea2b4bf966f..56ab63f19bad 100644
--- a/fs/resctrl/pseudo_lock.c
+++ b/fs/resctrl/pseudo_lock.c
@@ -750,17 +750,10 @@ static ssize_t pseudo_lock_measure_trigger(struct file *file,
 					   size_t count, loff_t *ppos)
 {
 	struct rdtgroup *rdtgrp = file->private_data;
-	size_t buf_size;
-	char buf[32];
 	int ret;
 	int sel;
 
-	buf_size = min(count, (sizeof(buf) - 1));
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
-	ret = kstrtoint(buf, 10, &sel);
+	ret = kstrtoint_from_user(user_buf, count, 10, &sel);
 	if (ret == 0) {
 		if (sel != 1 && sel != 2 && sel != 3)
 			return -EINVAL;
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 5dcbb0a964e8..57ab090072c2 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -685,7 +685,7 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 
 static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
 {
-	return (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) &&
+	return (r->type == RDTCTRL_GROUP &&
 		resctrl_arch_match_closid(t, r->closid));
 }
 
@@ -2858,7 +2858,7 @@ static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type
 {
 	struct resctrl_schema *s;
 	const char *suffix = "";
-	int ret, cl;
+	int cl;
 
 	s = kzalloc_obj(*s);
 	if (!s)
@@ -2882,14 +2882,12 @@ static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type
 		break;
 	}
 
-	ret = snprintf(s->name, sizeof(s->name), "%s%s", r->name, suffix);
-	if (ret >= sizeof(s->name)) {
+	cl = snprintf(s->name, sizeof(s->name), "%s%s", r->name, suffix);
+	if (cl >= sizeof(s->name)) {
 		kfree(s);
 		return -EINVAL;
 	}
 
-	cl = strlen(s->name);
-
 	/*
 	 * If CDP is supported by this resource, but not enabled,
 	 * include the suffix. This ensures the tabular format of the
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index dd09c2ce9a0f..10dfdca7f4bf 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -505,6 +505,25 @@ bool resctrl_arch_mbm_cntr_assign_enabled(struct rdt_resource *r);
  */
 int resctrl_arch_mbm_cntr_assign_set(struct rdt_resource *r, bool enable);
 
+/**
+ * resctrl_arch_preconvert_bw() - Prepare bandwidth control value for arch use.
+ * @r:		Resource whose schema was written.
+ * @val:	Bandwidth control value written to the schemata file by userspace.
+ *
+ * Convert the user provided bandwidth control value to an appropriate form for
+ * consumption by the hardware driver for resource @r. Converted value is stored
+ * in rdt_ctrl_domain::staged_config[] for later consumption by
+ * resctrl_arch_update_domains(). Is not called when MBA software controller is
+ * enabled.
+ *
+ * Architectures for which this pre-conversion hook is not useful should supply
+ * an implementation of this function that just returns @val unmodified.
+ *
+ * Return:
+ * The converted value.
+ */
+u32 resctrl_arch_preconvert_bw(const struct rdt_resource *r, u32 val);
+
 /*
  * Update the ctrl_val and apply this config right now.
  * Must be called on one of the domain's CPUs.
diff --git a/include/linux/resctrl_types.h b/include/linux/resctrl_types.h
index a5f56faa18d2..e2e2cf3d9ff6 100644
--- a/include/linux/resctrl_types.h
+++ b/include/linux/resctrl_types.h
@@ -60,6 +60,8 @@ enum resctrl_event_id {
 	PMT_EVENT_AUTO_C6_RES,
 	PMT_EVENT_UNHALTED_REF_CYCLES,
 	PMT_EVENT_UOPS_RETIRED,
+	PMT_EVENT_INST_RETIRED,
+	PMT_EVENT_PCNT,
 
 	/* Must be the last */
 	QOS_NUM_EVENTS,