x86/resctrl: Add energy/perf choices to rdt boot option

Legacy resctrl features are enumerated by X86_FEATURE_* flags. These may be
overridden by quirks to disable features in the case of errata.  Users can use
kernel command line options to either disable a feature, or to force enable
a feature that was disabled by a quirk.

A different approach is needed for hardware features that do not have an
X86_FEATURE_* flag.

Update parsing of the "rdt=" boot parameter to call the telemetry driver
directly to handle new "perf" and "energy" options that controls activation of
telemetry monitoring of the named type. By itself a "perf" or "energy" option
controls the forced enabling or disabling (with ! prefix) of all event groups
of the named type. A ":guid" suffix allows for fine grained control per event
group.

  [ bp: s/intel_aet_option/intel_handle_aet_option/g ]

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lore.kernel.org/20251217172121.12030-1-tony.luck@intel.com

Author: aegl

Documentation/admin-guide/kernel-parameters.txt

@@ -6325,9 +6325,14 @@ Kernel parameters
 	rdt=		[HW,X86,RDT]
 			Turn on/off individual RDT features. List is:
 			cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
-			mba, smba, bmec, abmc, sdciae.
+			mba, smba, bmec, abmc, sdciae, energy[:guid],
+			perf[:guid].
 			E.g. to turn on cmt and turn off mba use:
 				rdt=cmt,!mba
+			To turn off all energy telemetry monitoring and ensure that
+			perf telemetry monitoring associated with guid 0x12345
+			is enabled use:
+				rdt=!energy,perf:0x12345
 
 	reboot=		[KNL]
 			Format (x86 or x86_64):

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

@@ -814,6 +814,8 @@ static int __init set_rdt_options(char *str)
 		force_off = *tok == '!';
 		if (force_off)
 			tok++;
+		if (intel_handle_aet_option(force_off, tok))
+			continue;
 		for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) {
 			if (strcmp(tok, o->name) == 0) {
 				if (force_off)

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

@@ -52,12 +52,17 @@ struct pmt_event {
 /**
  * struct event_group - Events with the same feature type ("energy" or "perf") and GUID.
  * @pfname:		PMT feature name ("energy" or "perf") of this event group.
+ *			Used by boot rdt= option.
  * @pfg:		Points to the aggregated telemetry space information
  *			returned by the intel_pmt_get_regions_by_feature()
  *			call to the INTEL_PMT_TELEMETRY driver that contains
  *			data for all telemetry regions of type @pfname.
  *			Valid if the system supports the event group,
  *			NULL otherwise.
+ * @force_off:		True when "rdt" command line or architecture code disables
+ *			this event group.
+ * @force_on:		True when "rdt" command line overrides disable of this
+ *			event group.
  * @guid:		Unique number per XML description file.
  * @mmio_size:		Number of bytes of MMIO registers for this group.
  * @num_events:		Number of events in this group.
@@ -67,6 +72,7 @@ struct event_group {
 	/* Data fields for additional structures to manage this group. */
 	const char			*pfname;
 	struct pmt_feature_group	*pfg;
+	bool				force_off, force_on;
 
 	/* Remaining fields initialized from XML file. */
 	u32				guid;
@@ -121,6 +127,35 @@ static struct event_group *known_event_groups[] = {
 	     _peg < &known_event_groups[ARRAY_SIZE(known_event_groups)];	\
 	     _peg++)
 
+bool intel_handle_aet_option(bool force_off, char *tok)
+{
+	struct event_group **peg;
+	bool ret = false;
+	u32 guid = 0;
+	char *name;
+
+	if (!tok)
+		return false;
+
+	name = strsep(&tok, ":");
+	if (tok && kstrtou32(tok, 16, &guid))
+		return false;
+
+	for_each_event_group(peg) {
+		if (strcmp(name, (*peg)->pfname))
+			continue;
+		if (guid && (*peg)->guid != guid)
+			continue;
+		if (force_off)
+			(*peg)->force_off = true;
+		else
+			(*peg)->force_on = true;
+		ret = true;
+	}
+
+	return ret;
+}
+
 static bool skip_telem_region(struct telemetry_region *tr, struct event_group *e)
 {
 	if (tr->guid != e->guid)
@@ -168,6 +203,9 @@ static bool enable_events(struct event_group *e, struct pmt_feature_group *p)
 	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_PERF_PKG].r_resctrl;
 	int skipped_events = 0;
 
+	if (e->force_off)
+		return false;
+
 	if (!group_has_usable_regions(e, p))
 		return false;
 

arch/x86/kernel/cpu/resctrl/internal.h

@@ -236,6 +236,7 @@ void __exit intel_aet_exit(void);
 int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64 *val);
 void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r,
 				struct list_head *add_pos);
+bool intel_handle_aet_option(bool force_off, char *tok);
 #else
 static inline bool intel_aet_get_events(void) { return false; }
 static inline void __exit intel_aet_exit(void) { }
@@ -246,6 +247,7 @@ static inline int intel_aet_read_event(int domid, u32 rmid, void *arch_priv, u64
 
 static inline void intel_aet_mon_domain_setup(int cpu, int id, struct rdt_resource *r,
 					      struct list_head *add_pos) { }
+static inline bool intel_handle_aet_option(bool force_off, char *tok) { return false; }
 #endif
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */