x86,fs/resctrl: Support binary fixed point event counters

resctrl assumes that all monitor events can be displayed as unsigned decimal
integers.

Hardware architecture counters may provide some telemetry events with greater
precision where the event is not a simple count, but is a measurement of some
sort (e.g. Joules for energy consumed).

Add a new argument to resctrl_enable_mon_event() for architecture code to
inform the file system that the value for a counter is a fixed-point value
with a specific number of binary places.

Only allow architecture to use floating point format on events that the file
system has marked with mon_evt::is_floating_point which reflects the contract
with user space on how the event values are displayed.

Display fixed point values with values rounded to ceil(binary_bits * log10(2))
decimal places. Special case for zero binary bits to print "{value}.0".

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

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

@@ -902,15 +902,15 @@ static __init bool get_rdt_mon_resources(void)
 	bool ret = false;
 
 	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC)) {
-		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false);
+		resctrl_enable_mon_event(QOS_L3_OCCUP_EVENT_ID, false, 0);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) {
-		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false);
+		resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID, false, 0);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) {
-		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false);
+		resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID, false, 0);
 		ret = true;
 	}
 	if (rdt_cpu_has(X86_FEATURE_ABMC))

fs/resctrl/ctrlmondata.c

@@ -17,6 +17,7 @@
 
 #include <linux/cpu.h>
 #include <linux/kernfs.h>
+#include <linux/math.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/tick.h>
@@ -601,6 +602,77 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
 		resctrl_arch_mon_ctx_free(r, evt->evtid, rr->arch_mon_ctx);
 }
 
+/*
+ * Decimal place precision to use for each number of fixed-point
+ * binary bits computed from ceil(binary_bits * log10(2)) except
+ * binary_bits == 0 which will print "value.0"
+ */
+static const unsigned int decplaces[MAX_BINARY_BITS + 1] = {
+	[0]  =  1,
+	[1]  =  1,
+	[2]  =  1,
+	[3]  =  1,
+	[4]  =  2,
+	[5]  =  2,
+	[6]  =  2,
+	[7]  =  3,
+	[8]  =  3,
+	[9]  =  3,
+	[10] =  4,
+	[11] =  4,
+	[12] =  4,
+	[13] =  4,
+	[14] =  5,
+	[15] =  5,
+	[16] =  5,
+	[17] =  6,
+	[18] =  6,
+	[19] =  6,
+	[20] =  7,
+	[21] =  7,
+	[22] =  7,
+	[23] =  7,
+	[24] =  8,
+	[25] =  8,
+	[26] =  8,
+	[27] =  9
+};
+
+static void print_event_value(struct seq_file *m, unsigned int binary_bits, u64 val)
+{
+	unsigned long long frac = 0;
+
+	if (binary_bits) {
+		/* Mask off the integer part of the fixed-point value. */
+		frac = val & GENMASK_ULL(binary_bits - 1, 0);
+
+		/*
+		 * Multiply by 10^{desired decimal places}. The integer part of
+		 * the fixed point value is now almost what is needed.
+		 */
+		frac *= int_pow(10ull, decplaces[binary_bits]);
+
+		/*
+		 * Round to nearest by adding a value that would be a "1" in the
+		 * binary_bits + 1 place.  Integer part of fixed point value is
+		 * now the needed value.
+		 */
+		frac += 1ull << (binary_bits - 1);
+
+		/*
+		 * Extract the integer part of the value. This is the decimal
+		 * representation of the original fixed-point fractional value.
+		 */
+		frac >>= binary_bits;
+	}
+
+	/*
+	 * "frac" is now in the range [0 .. 10^decplaces).  I.e. string
+	 * representation will fit into chosen number of decimal places.
+	 */
+	seq_printf(m, "%llu.%0*llu\n", val >> binary_bits, decplaces[binary_bits], frac);
+}
+
 int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 {
 	struct kernfs_open_file *of = m->private;
@@ -678,6 +750,8 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		seq_puts(m, "Unavailable\n");
 	else if (rr.err == -ENOENT)
 		seq_puts(m, "Unassigned\n");
+	else if (evt->is_floating_point)
+		print_event_value(m, evt->binary_bits, rr.val);
 	else
 		seq_printf(m, "%llu\n", rr.val);
 

fs/resctrl/internal.h

@@ -62,6 +62,9 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
  *			Only valid if @evtid is an MBM event.
  * @configurable:	true if the event is configurable
  * @any_cpu:		true if the event can be read from any CPU
+ * @is_floating_point:	event values are displayed in floating point format
+ * @binary_bits:	number of fixed-point binary bits from architecture,
+ *			only valid if @is_floating_point is true
  * @enabled:		true if the event is enabled
  */
 struct mon_evt {
@@ -71,6 +74,8 @@ struct mon_evt {
 	u32			evt_cfg;
 	bool			configurable;
 	bool			any_cpu;
+	bool			is_floating_point;
+	unsigned int		binary_bits;
 	bool			enabled;
 };
 
@@ -79,6 +84,9 @@ extern struct mon_evt mon_event_all[QOS_NUM_EVENTS];
 #define for_each_mon_event(mevt) for (mevt = &mon_event_all[QOS_FIRST_EVENT];	\
 				      mevt < &mon_event_all[QOS_NUM_EVENTS]; mevt++)
 
+/* Limit for mon_evt::binary_bits */
+#define MAX_BINARY_BITS	27
+
 /**
  * struct mon_data - Monitoring details for each event file.
  * @list:            Member of the global @mon_data_kn_priv_list list.

fs/resctrl/monitor.c

@@ -988,16 +988,22 @@ struct mon_evt mon_event_all[QOS_NUM_EVENTS] = {
 	},
 };
 
-void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu)
+void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu, unsigned int binary_bits)
 {
-	if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS))
+	if (WARN_ON_ONCE(eventid < QOS_FIRST_EVENT || eventid >= QOS_NUM_EVENTS ||
+			 binary_bits > MAX_BINARY_BITS))
 		return;
 	if (mon_event_all[eventid].enabled) {
 		pr_warn("Duplicate enable for event %d\n", eventid);
 		return;
 	}
+	if (binary_bits && !mon_event_all[eventid].is_floating_point) {
+		pr_warn("Event %d may not be floating point\n", eventid);
+		return;
+	}
 
 	mon_event_all[eventid].any_cpu = any_cpu;
+	mon_event_all[eventid].binary_bits = binary_bits;
 	mon_event_all[eventid].enabled = true;
 }
 

include/linux/resctrl.h

@@ -412,7 +412,8 @@ u32 resctrl_arch_get_num_closid(struct rdt_resource *r);
 u32 resctrl_arch_system_num_rmid_idx(void);
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid);
 
-void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu);
+void resctrl_enable_mon_event(enum resctrl_event_id eventid, bool any_cpu,
+			      unsigned int binary_bits);
 
 bool resctrl_is_mon_event_enabled(enum resctrl_event_id eventid);