[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <aLiH0QxFCP9EpmWn@agluck-desk3>
Date: Wed, 3 Sep 2025 11:24:17 -0700
From: "Luck, Tony" <tony.luck@...el.com>
To: Ilpo Järvinen <ilpo.jarvinen@...ux.intel.com>
CC: Fenghua Yu <fenghuay@...dia.com>, Reinette Chatre
<reinette.chatre@...el.com>, Maciej Wieczor-Retman
<maciej.wieczor-retman@...el.com>, Peter Newman <peternewman@...gle.com>,
James Morse <james.morse@....com>, Babu Moger <babu.moger@....com>, "Drew
Fustini" <dfustini@...libre.com>, Dave Martin <Dave.Martin@....com>, Chen Yu
<yu.c.chen@...el.com>, <x86@...nel.org>, LKML <linux-kernel@...r.kernel.org>,
<patches@...ts.linux.dev>
Subject: Re: [PATCH v9 21/31] x86/resctrl: Read telemetry events
On Mon, Sep 01, 2025 at 12:15:49PM +0300, Ilpo Järvinen wrote:
> > @@ -125,8 +126,14 @@ static bool enable_events(struct event_group *e, struct pmt_feature_group *p)
> > bool usable_events = false;
> >
> > for (int i = 0; i < p->count; i++) {
> > - if (skip_this_region(&p->regions[i], e))
> > + if (skip_this_region(&p->regions[i], e)) {
> > + /*
> > + * Clear addr so that intel_aet_read_event() will
> > + * skip this region.
> > + */
> > + p->regions[i].addr = NULL;
>
> As this is at least semi-hacky, I suggest you move it into own function
> and add a bit longer comment to the function (along the lines what the
> changelog also states why it works).
Agreed. See new mark_telem_region_unusable() in updated patch below.
Also pushed to
git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux.git rdt-aet-v10-wip
-Tony
P.S. In addition to all the extra #include files you suggested, I found
a few others missing. So those are added as needed in the series.
>From 163824a2e10de9f63e20f0bc9f86b8c14f58bfcb Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@...el.com>
Date: Mon, 25 Aug 2025 10:47:06 -0700
Subject: [PATCH 21/31] x86/resctrl: Read telemetry events
Telemetry events are enumerated by the INTEL_PMT_TELEMETRY subsystem.
resctrl enables events with resctrl_enable_mon_event() passing a pointer
to the pmt_event structure for the event within the struct event_group.
The file system stores it in mon_evt::arch_priv.
Mark regions that did not pass the checks in skip_telemetry_region()
so they will not be used by intel_aet_read_event().
Add a check to resctrl_arch_rmid_read() for resource id
RDT_RESOURCE_PERF_PKG and directly call intel_aet_read_event()
passing the enum resctrl_event_id for the event and the arch_priv
pointer that was supplied when the event was enabled.
There may be multiple aggregators tracking each package, so scan all of
them and add up all counters. Aggregators may return an invalid data
indication if they have received no records for a given RMID. Return
success to the user if one or more aggregators provide valid data.
Resctrl now uses readq() so depends on X86_64. Update Kconfig.
Signed-off-by: Tony Luck <tony.luck@...el.com>
---
arch/x86/kernel/cpu/resctrl/internal.h | 7 +++
arch/x86/kernel/cpu/resctrl/intel_aet.c | 65 ++++++++++++++++++++++++-
arch/x86/kernel/cpu/resctrl/monitor.c | 3 ++
arch/x86/Kconfig | 2 +-
4 files changed, 75 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 9ddfbbe5c3cf..8986071dd72a 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -172,9 +172,16 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
#ifdef CONFIG_X86_CPU_RESCTRL_INTEL_AET
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);
#else
static inline bool intel_aet_get_events(void) { return false; }
static inline void __exit intel_aet_exit(void) { }
+static inline int intel_aet_read_event(int domid, int rmid, enum resctrl_event_id evtid,
+ void *arch_priv, u64 *val)
+{
+ return -EINVAL;
+}
#endif
#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 e36b3790733b..170158d40e27 100644
--- a/arch/x86/kernel/cpu/resctrl/intel_aet.c
+++ b/arch/x86/kernel/cpu/resctrl/intel_aet.c
@@ -12,13 +12,17 @@
#define pr_fmt(fmt) "resctrl: " fmt
#include <linux/array_size.h>
+#include <linux/bits.h>
#include <linux/cleanup.h>
#include <linux/compiler_types.h>
+#include <linux/container_of.h>
#include <linux/cpu.h>
#include <linux/err.h>
+#include <linux/errno.h>
#include <linux/init.h>
#include <linux/intel_pmt_features.h>
#include <linux/intel_vsec.h>
+#include <linux/io.h>
#include <linux/overflow.h>
#include <linux/printk.h>
#include <linux/resctrl.h>
@@ -131,13 +135,28 @@ static bool skip_telem_region(struct telemetry_region *tr, struct event_group *e
return false;
}
+/*
+ * Clear the address field of regions that did not pass the checks in
+ * skip_telem_region() so they will not be used by intel_aet_read_event().
+ * This is safe to do because intel_pmt_get_regions_by_feature() allocates
+ * a new pmt_feature_group structure to return to each caller and only makes
+ * use of the pmt_feature_group::kref field when intel_pmt_put_feature_group()
+ * returns the structure.
+ */
+static void mark_telem_region_unusable(struct telemetry_region *tr)
+{
+ tr->addr = NULL;
+}
+
static bool enable_events(struct event_group *e, struct pmt_feature_group *p)
{
bool usable_events = false;
for (int i = 0; i < p->count; i++) {
- if (skip_telem_region(&p->regions[i], e))
+ if (skip_telem_region(&p->regions[i], e)) {
+ mark_telem_region_unusable(&p->regions[i]);
continue;
+ }
usable_events = true;
}
@@ -215,3 +234,47 @@ void __exit intel_aet_exit(void)
(*peg)->pfg = NULL;
}
}
+
+#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). If an aggregator hasn't received any data for a
+ * specific RMID, the MMIO read indicates that data is not valid.
+ * Return success if at least one aggregator has valid data.
+ */
+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 event_group *e;
+ bool valid = false;
+ 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;
+
+ 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 < e->pfg->count; i++) {
+ if (!e->pfg->regions[i].addr)
+ continue;
+ if (e->pfg->regions[i].plat_info.package_id != domid)
+ continue;
+ evtcount = readq(e->pfg->regions[i].addr + idx * sizeof(u64));
+ if (!(evtcount & DATA_VALID))
+ continue;
+ *val += evtcount & DATA_BITS;
+ valid = true;
+ }
+
+ return valid ? 0 : -EINVAL;
+}
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 249569327e4a..0333dd85450b 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 50051fdf4659..a42f749f31cb 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -527,7 +527,7 @@ config X86_CPU_RESCTRL
config X86_CPU_RESCTRL_INTEL_AET
bool "Intel Application Energy Telemetry" if INTEL_PMT_TELEMETRY=y && INTEL_TPMI=y
- depends on X86_CPU_RESCTRL && CPU_SUP_INTEL
+ depends on X86_64 && X86_CPU_RESCTRL && CPU_SUP_INTEL
help
Enable per-RMID telemetry events in resctrl.
--
2.51.0
Powered by blists - more mailing lists