The resctrl file system passes requests to read event monitor files to
the architecture resctrl_arch_rmid_read() to collect values
from hardware counters.

Use the resctrl resource to differentiate between calls to read legacy
L3 events from the new telemetry events (which are attached to
RDT_RESOURCE_PERF_PKG).

There may be multiple aggregators tracking each package, so scan all of
them and add up all counters.

Enable the events marked as readable from any CPU providing an
mon_evt::arch_priv pointer to the struct pmt_event for each
event.

At run time when a user reads an event file the file system code
provides the enum resctrl_event_id for the event and the arch_priv
pointer that was supplied when the event was enabled.

Resctrl now uses readq() so depends on X86_64. Update Kconfig.

Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 arch/x86/kernel/cpu/resctrl/internal.h  |  2 ++
 arch/x86/kernel/cpu/resctrl/intel_aet.c | 46 +++++++++++++++++++++++++
 arch/x86/kernel/cpu/resctrl/monitor.c   |  3 ++
 arch/x86/Kconfig                        |  2 +-
 4 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index e93b15bf6aab..e8d2a754bc0c 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -171,5 +171,7 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 
 bool intel_aet_get_events(void);
 void __exit intel_aet_exit(void);
+int intel_aet_read_event(int domid, int rmid, enum resctrl_event_id evtid,
+			 void *arch_priv, u64 *val);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
index f9b2959693a0..10fd8b04105e 100644
--- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -14,6 +14,7 @@
 #include <linux/cleanup.h>
 #include <linux/cpu.h>
 #include <linux/intel_vsec.h>
+#include <linux/io.h>
 #include <linux/resctrl.h>
 #include <linux/slab.h>
 
@@ -206,6 +207,13 @@ static int configure_events(struct event_group *e, struct pmt_feature_group *p)
 	}
 	e->pkginfo = no_free_ptr(pkginfo);
 
+	for (int i = 0; i < e->num_events; i++) {
+		enum resctrl_event_id eventid;
+
+		eventid = e->evts[i].id;
+		resctrl_enable_mon_event(eventid, true, e->evts[i].bin_bits, &e->evts[i]);
+	}
+
 	return 0;
 }
 
@@ -268,3 +276,41 @@ void __exit intel_aet_exit(void)
 		free_mmio_info((*peg)->pkginfo);
 	}
 }
+
+#define DATA_VALID	BIT_ULL(63)
+#define DATA_BITS	GENMASK_ULL(62, 0)
+
+/*
+ * Read counter for an event on a domain (summing all aggregators
+ * on the domain).
+ */
+int intel_aet_read_event(int domid, int rmid, enum resctrl_event_id eventid,
+			 void *arch_priv, u64 *val)
+{
+	struct pmt_event *pevt = arch_priv;
+	struct mmio_info *mmi;
+	struct event_group *e;
+	u64 evtcount;
+	void *pevt0;
+	int idx;
+
+	pevt0 = pevt - pevt->idx;
+	e = container_of(pevt0, struct event_group, evts);
+	idx = rmid * e->num_events;
+	idx += pevt->idx;
+	mmi = e->pkginfo[domid];
+
+	if (idx * sizeof(u64) + sizeof(u64) > e->mmio_size) {
+		pr_warn_once("MMIO index %d out of range\n", idx);
+		return -EIO;
+	}
+
+	for (int i = 0; i < mmi->num_regions; i++) {
+		evtcount = readq(mmi->addrs[i] + idx * sizeof(u64));
+		if (!(evtcount & DATA_VALID))
+			return -EINVAL;
+		*val += evtcount & DATA_BITS;
+	}
+
+	return 0;
+}
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 185b203f6321..51d7d99336c6 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -232,6 +232,9 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr,
 
 	resctrl_arch_rmid_read_context_check();
 
+	if (r->rid == RDT_RESOURCE_PERF_PKG)
+		return intel_aet_read_event(hdr->id, rmid, eventid, arch_priv, val);
+
 	if (r->rid != RDT_RESOURCE_L3)
 		return -EINVAL;
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8eb68d2230be..a6b6ecbd3877 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -507,7 +507,7 @@ config X86_MPPARSE
 
 config X86_CPU_RESCTRL
 	bool "x86 CPU resource control support"
-	depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)
+	depends on X86_64 && (CPU_SUP_INTEL || CPU_SUP_AMD)
 	depends on MISC_FILESYSTEMS
 	select ARCH_HAS_CPU_RESCTRL
 	select RESCTRL_FS
-- 
2.49.0

Hi Tony,

What does the "core" in the subject refer to?

On 6/26/25 9:49 AM, Tony Luck wrote:
> The resctrl file system passes requests to read event monitor files to
> the architecture resctrl_arch_rmid_read() to collect values
> from hardware counters.
> 
> Use the resctrl resource to differentiate between calls to read legacy
> L3 events from the new telemetry events (which are attached to
> RDT_RESOURCE_PERF_PKG).
> 
> There may be multiple aggregators tracking each package, so scan all of
> them and add up all counters.
> 
> Enable the events marked as readable from any CPU providing an
> mon_evt::arch_priv pointer to the struct pmt_event for each
> event.
> 
> At run time when a user reads an event file the file system code
> provides the enum resctrl_event_id for the event and the arch_priv
> pointer that was supplied when the event was enabled.
> 
> Resctrl now uses readq() so depends on X86_64. Update Kconfig.
> 
> Signed-off-by: Tony Luck <tony.luck@intel.com>
> ---
>  arch/x86/kernel/cpu/resctrl/internal.h  |  2 ++
>  arch/x86/kernel/cpu/resctrl/intel_aet.c | 46 +++++++++++++++++++++++++
>  arch/x86/kernel/cpu/resctrl/monitor.c   |  3 ++
>  arch/x86/Kconfig                        |  2 +-
>  4 files changed, 52 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
> index e93b15bf6aab..e8d2a754bc0c 100644
> --- a/arch/x86/kernel/cpu/resctrl/internal.h
> +++ b/arch/x86/kernel/cpu/resctrl/internal.h
> @@ -171,5 +171,7 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
>  
>  bool intel_aet_get_events(void);
>  void __exit intel_aet_exit(void);
> +int intel_aet_read_event(int domid, int rmid, enum resctrl_event_id evtid,
> +			 void *arch_priv, u64 *val);
>  
>  #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
> diff --git a/arch/x86/kernel/cpu/resctrl/intel_aet.c b/arch/x86/kernel/cpu/resctrl/intel_aet.c
> index f9b2959693a0..10fd8b04105e 100644
> --- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
> +++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
> @@ -14,6 +14,7 @@
>  #include <linux/cleanup.h>
>  #include <linux/cpu.h>
>  #include <linux/intel_vsec.h>
> +#include <linux/io.h>
>  #include <linux/resctrl.h>
>  #include <linux/slab.h>
>  
> @@ -206,6 +207,13 @@ static int configure_events(struct event_group *e, struct pmt_feature_group *p)
>  	}
>  	e->pkginfo = no_free_ptr(pkginfo);
>  
> +	for (int i = 0; i < e->num_events; i++) {
> +		enum resctrl_event_id eventid;
> +
> +		eventid = e->evts[i].id;
> +		resctrl_enable_mon_event(eventid, true, e->evts[i].bin_bits, &e->evts[i]);
> +	}
> +
>  	return 0;
>  }
>  
> @@ -268,3 +276,41 @@ void __exit intel_aet_exit(void)
>  		free_mmio_info((*peg)->pkginfo);
>  	}
>  }
> +
> +#define DATA_VALID	BIT_ULL(63)
> +#define DATA_BITS	GENMASK_ULL(62, 0)
> +
> +/*
> + * Read counter for an event on a domain (summing all aggregators
> + * on the domain).
> + */
> +int intel_aet_read_event(int domid, int rmid, enum resctrl_event_id eventid,
> +			 void *arch_priv, u64 *val)
> +{
> +	struct pmt_event *pevt = arch_priv;
> +	struct mmio_info *mmi;
> +	struct event_group *e;
> +	u64 evtcount;
> +	void *pevt0;

Should this be a struct pmt_event *?

> +	int idx;
> +
> +	pevt0 = pevt - pevt->idx;
> +	e = container_of(pevt0, struct event_group, evts);
> +	idx = rmid * e->num_events;
> +	idx += pevt->idx;
> +	mmi = e->pkginfo[domid];
> +
> +	if (idx * sizeof(u64) + sizeof(u64) > e->mmio_size) {
> +		pr_warn_once("MMIO index %d out of range\n", idx);
> +		return -EIO;
> +	}
> +
> +	for (int i = 0; i < mmi->num_regions; i++) {
> +		evtcount = readq(mmi->addrs[i] + idx * sizeof(u64));
> +		if (!(evtcount & DATA_VALID))
> +			return -EINVAL;
> +		*val += evtcount & DATA_BITS;
> +	}
> +
> +	return 0;
> +}
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index 185b203f6321..51d7d99336c6 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -232,6 +232,9 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain_hdr *hdr,
>  
>  	resctrl_arch_rmid_read_context_check();
>  
> +	if (r->rid == RDT_RESOURCE_PERF_PKG)
> +		return intel_aet_read_event(hdr->id, rmid, eventid, arch_priv, val);
> +
>  	if (r->rid != RDT_RESOURCE_L3)
>  		return -EINVAL;
>  

This part looks good to me. I expect Kconfig part to look different next time.

Reinette

On Wed, Jul 09, 2025 at 08:48:47AM -0700, Reinette Chatre wrote:
> Hi Tony,
> 
> What does the "core" in the subject refer to?

The events are collected by each core. But since resctrl reports the
aggregated per-package values this is confusing. I'll drop "core" from
the Subject line.

[snip]

> > +/*
> > + * Read counter for an event on a domain (summing all aggregators
> > + * on the domain).
> > + */
> > +int intel_aet_read_event(int domid, int rmid, enum resctrl_event_id eventid,
> > +			 void *arch_priv, u64 *val)
> > +{
> > +	struct pmt_event *pevt = arch_priv;
> > +	struct mmio_info *mmi;
> > +	struct event_group *e;
> > +	u64 evtcount;
> > +	void *pevt0;
> 
> Should this be a struct pmt_event *?

I thought that too. But container_of() gets confused about types (I
think because the evts[] element is a flex array.

With "struct pmt_event *pevt0;" the compiler complains:

arch/x86/kernel/cpu/resctrl/intel_aet.c: In function ‘intel_aet_read_event’:
./include/linux/build_bug.h:78:41: error: static assertion failed: "pointer type mismatch in container_of()"
   78 | #define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
      |                                         ^~~~~~~~~~~~~~
./include/linux/build_bug.h:77:34: note: in expansion of macro ‘__static_assert’
   77 | #define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
      |                                  ^~~~~~~~~~~~~~~
./include/linux/container_of.h:20:9: note: in expansion of macro ‘static_assert’
   20 |         static_assert(__same_type(*(ptr), ((type *)0)->member) ||       \
      |         ^~~~~~~~~~~~~
arch/x86/kernel/cpu/resctrl/intel_aet.c:311:13: note: in expansion of macro ‘container_of’
  311 |         e = container_of(pevt0, struct event_group, evts);
      |             ^~~~~~~~~~~~

Making it void * is the "get of of jail free" case in container_of()
with the test " || __same_type(*(ptr), void)"

If there is a better way to do this, let me know.

-Tony

Hi Tony,

On 7/9/25 2:57 PM, Luck, Tony wrote:
> On Wed, Jul 09, 2025 at 08:48:47AM -0700, Reinette Chatre wrote:
>> Hi Tony,
>>
>> What does the "core" in the subject refer to?
> 
> The events are collected by each core. But since resctrl reports the
> aggregated per-package values this is confusing. I'll drop "core" from
> the Subject line.
> 
> [snip]
> 
>>> +/*
>>> + * Read counter for an event on a domain (summing all aggregators
>>> + * on the domain).
>>> + */
>>> +int intel_aet_read_event(int domid, int rmid, enum resctrl_event_id eventid,
>>> +			 void *arch_priv, u64 *val)
>>> +{
>>> +	struct pmt_event *pevt = arch_priv;
>>> +	struct mmio_info *mmi;
>>> +	struct event_group *e;
>>> +	u64 evtcount;
>>> +	void *pevt0;
>>
>> Should this be a struct pmt_event *?
> 
> I thought that too. But container_of() gets confused about types (I
> think because the evts[] element is a flex array.
> 
> With "struct pmt_event *pevt0;" the compiler complains:
> 
> arch/x86/kernel/cpu/resctrl/intel_aet.c: In function ‘intel_aet_read_event’:
> ./include/linux/build_bug.h:78:41: error: static assertion failed: "pointer type mismatch in container_of()"
>    78 | #define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
>       |                                         ^~~~~~~~~~~~~~
> ./include/linux/build_bug.h:77:34: note: in expansion of macro ‘__static_assert’
>    77 | #define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
>       |                                  ^~~~~~~~~~~~~~~
> ./include/linux/container_of.h:20:9: note: in expansion of macro ‘static_assert’
>    20 |         static_assert(__same_type(*(ptr), ((type *)0)->member) ||       \
>       |         ^~~~~~~~~~~~~
> arch/x86/kernel/cpu/resctrl/intel_aet.c:311:13: note: in expansion of macro ‘container_of’
>   311 |         e = container_of(pevt0, struct event_group, evts);
>       |             ^~~~~~~~~~~~
> 
> Making it void * is the "get of of jail free" case in container_of()
> with the test " || __same_type(*(ptr), void)"
> 
> If there is a better way to do this, let me know.

Thanks for investigating. I did not consider this.

Reinette