From: Ravi Bangoria <ravi.bangoria@amd.com>
To: Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Ian Rogers <irogers@google.com>,
Dapeng Mi <dapeng1.mi@linux.intel.com>,
James Clark <james.clark@linaro.org>, <x86@kernel.org>,
<linux-perf-users@vger.kernel.org>,
<linux-kernel@vger.kernel.org>,
"Manali Shukla" <manali.shukla@amd.com>,
Santosh Shukla <santosh.shukla@amd.com>,
Ananth Narayan <ananth.narayan@amd.com>,
Sandipan Das <sandipan.das@amd.com>
Subject: [PATCH 08/11] perf/amd/ibs: Enable fetch latency filtering
Date: Fri, 16 Jan 2026 03:34:47 +0000 [thread overview]
Message-ID: <20260116033450.965-9-ravi.bangoria@amd.com> (raw)
In-Reply-To: <20260116033450.965-1-ravi.bangoria@amd.com>
IBS Fetch on future hardware adds fetch latency filtering which
generates interrupt only when FetchLat value exceeds a programmable
threshold.
Hardware allows threshold in 128-cycle increment (i.e. 128, 256, 384
etc.) from 128 to 1920 cycles. Like the existing IBS filters, samples
that fail the latency test are dropped and IBS restarts internally.
Since hardware supports threshold in multiple of 128, add a software
filter on top to support latency threshold with the granularity of 1
cycle in between [128-1920].
Example:
# perf record -e ibs_fetch/fetchlat=128/ -c 10000 -a -- sleep 5
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
---
arch/x86/events/amd/ibs.c | 66 ++++++++++++++++++++++++++++++++++++++-
1 file changed, 65 insertions(+), 1 deletion(-)
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index d8216048be84..b2d21026edae 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -35,6 +35,8 @@ static u32 ibs_caps;
/* attr.config1 */
#define IBS_OP_CONFIG1_LDLAT_MASK (0xFFFULL << 0)
+#define IBS_FETCH_CONFIG1_FETCHLAT_MASK (0x7FFULL << 0)
+
/*
* IBS states:
*
@@ -282,6 +284,14 @@ static bool perf_ibs_ldlat_event(struct perf_ibs *perf_ibs,
(event->attr.config1 & IBS_OP_CONFIG1_LDLAT_MASK);
}
+static bool perf_ibs_fetch_lat_event(struct perf_ibs *perf_ibs,
+ struct perf_event *event)
+{
+ return perf_ibs == &perf_ibs_fetch &&
+ (ibs_caps & IBS_CAPS_FETCHLAT) &&
+ (event->attr.config1 & IBS_FETCH_CONFIG1_FETCHLAT_MASK);
+}
+
static int perf_ibs_init(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
@@ -374,6 +384,17 @@ static int perf_ibs_init(struct perf_event *event)
config |= IBS_OP_L3MISSONLY;
}
+ if (perf_ibs_fetch_lat_event(perf_ibs, event)) {
+ u64 fetchlat = event->attr.config1 & IBS_FETCH_CONFIG1_FETCHLAT_MASK;
+
+ if (fetchlat < 128 || fetchlat > 1920)
+ return -EINVAL;
+ fetchlat >>= 7;
+
+ hwc->extra_reg.reg = perf_ibs->msr2;
+ hwc->extra_reg.config |= fetchlat << 1;
+ }
+
/*
* If we modify hwc->sample_period, we also need to update
* hwc->last_period and hwc->period_left.
@@ -662,6 +683,8 @@ PMU_EVENT_ATTR_STRING(ldlat, ibs_op_ldlat_format, "config1:0-11");
PMU_EVENT_ATTR_STRING(zen4_ibs_extensions, zen4_ibs_extensions, "1");
PMU_EVENT_ATTR_STRING(ldlat, ibs_op_ldlat_cap, "1");
PMU_EVENT_ATTR_STRING(dtlb_pgsize, ibs_op_dtlb_pgsize_cap, "1");
+PMU_EVENT_ATTR_STRING(fetchlat, ibs_fetch_lat_format, "config1:0-10");
+PMU_EVENT_ATTR_STRING(fetchlat, ibs_fetch_lat_cap, "1");
static umode_t
zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int i)
@@ -669,6 +692,12 @@ zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int
return ibs_caps & IBS_CAPS_ZEN4 ? attr->mode : 0;
}
+static umode_t
+ibs_fetch_lat_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ return ibs_caps & IBS_CAPS_FETCHLAT ? attr->mode : 0;
+}
+
static umode_t
ibs_op_ldlat_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
@@ -697,6 +726,16 @@ static struct attribute *zen4_ibs_extensions_attrs[] = {
NULL,
};
+static struct attribute *ibs_fetch_lat_format_attrs[] = {
+ &ibs_fetch_lat_format.attr.attr,
+ NULL,
+};
+
+static struct attribute *ibs_fetch_lat_cap_attrs[] = {
+ &ibs_fetch_lat_cap.attr.attr,
+ NULL,
+};
+
static struct attribute *ibs_op_ldlat_cap_attrs[] = {
&ibs_op_ldlat_cap.attr.attr,
NULL,
@@ -724,6 +763,18 @@ static struct attribute_group group_zen4_ibs_extensions = {
.is_visible = zen4_ibs_extensions_is_visible,
};
+static struct attribute_group group_ibs_fetch_lat_cap = {
+ .name = "caps",
+ .attrs = ibs_fetch_lat_cap_attrs,
+ .is_visible = ibs_fetch_lat_is_visible,
+};
+
+static struct attribute_group group_ibs_fetch_lat_format = {
+ .name = "format",
+ .attrs = ibs_fetch_lat_format_attrs,
+ .is_visible = ibs_fetch_lat_is_visible,
+};
+
static struct attribute_group group_ibs_op_ldlat_cap = {
.name = "caps",
.attrs = ibs_op_ldlat_cap_attrs,
@@ -745,6 +796,8 @@ static const struct attribute_group *fetch_attr_groups[] = {
static const struct attribute_group *fetch_attr_update[] = {
&group_fetch_l3missonly,
&group_zen4_ibs_extensions,
+ &group_ibs_fetch_lat_cap,
+ &group_ibs_fetch_lat_format,
NULL,
};
@@ -1188,7 +1241,8 @@ static int perf_ibs_get_offset_max(struct perf_ibs *perf_ibs,
{
if (event->attr.sample_type & PERF_SAMPLE_RAW ||
perf_ibs_is_mem_sample_type(perf_ibs, event) ||
- perf_ibs_ldlat_event(perf_ibs, event))
+ perf_ibs_ldlat_event(perf_ibs, event) ||
+ perf_ibs_fetch_lat_event(perf_ibs, event))
return perf_ibs->offset_max;
else if (check_rip)
return 3;
@@ -1330,6 +1384,16 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
}
}
+ if (perf_ibs_fetch_lat_event(perf_ibs, event)) {
+ union ibs_fetch_ctl fetch_ctl;
+
+ fetch_ctl.val = ibs_data.regs[ibs_fetch_msr_idx(MSR_AMD64_IBSFETCHCTL)];
+ if (fetch_ctl.fetch_lat < (event->attr.config1 & IBS_FETCH_CONFIG1_FETCHLAT_MASK)) {
+ throttle = perf_event_account_interrupt(event);
+ goto out;
+ }
+ }
+
/*
* Read IbsBrTarget, IbsOpData4, and IbsExtdCtl separately
* depending on their availability.
--
2.43.0
next prev parent reply other threads:[~2026-01-16 3:36 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-16 3:34 [PATCH 00/11] perf/amd/ibs: Fixes + future enhancements Ravi Bangoria
2026-01-16 3:34 ` [PATCH 01/11] perf/amd/ibs: Throttle interrupts with filtered ldlat samples Ravi Bangoria
2026-01-19 7:31 ` Mi, Dapeng
2026-01-19 12:56 ` Ravi Bangoria
2026-01-16 3:34 ` [PATCH 02/11] perf/amd/ibs: Limit ldlat->l3missonly dependency to Zen5 Ravi Bangoria
2026-01-16 3:34 ` [PATCH 03/11] perf/amd/ibs: Preserve PhyAddrVal bit when clearing PhyAddr MSR Ravi Bangoria
2026-01-16 3:34 ` [PATCH 04/11] perf/amd/ibs: Avoid race between event add and NMI Ravi Bangoria
2026-01-16 3:34 ` [PATCH 05/11] perf/amd/ibs: Define macro for ldlat mask Ravi Bangoria
2026-01-19 7:38 ` Mi, Dapeng
2026-01-16 3:34 ` [PATCH 06/11] perf/amd/ibs: Add new MSRs and CPUID bits definitions Ravi Bangoria
2026-01-19 7:39 ` Mi, Dapeng
2026-01-16 3:34 ` [PATCH 07/11] perf/amd/ibs: Support IBS_{FETCH|OP}_CTL2[Dis] to eliminate RMW race Ravi Bangoria
2026-01-19 7:48 ` Mi, Dapeng
2026-01-19 13:00 ` Ravi Bangoria
2026-01-16 3:34 ` Ravi Bangoria [this message]
2026-01-16 3:34 ` [PATCH 09/11] perf/amd/ibs: Enable RIP bit63 hardware filtering Ravi Bangoria
2026-01-16 3:34 ` [PATCH 10/11] perf/amd/ibs: Enable streaming store filter Ravi Bangoria
2026-01-19 7:57 ` Mi, Dapeng
2026-01-19 13:02 ` Ravi Bangoria
2026-01-16 3:34 ` [PATCH 11/11] perf/amd/ibs: Advertise remote socket capability Ravi Bangoria
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260116033450.965-9-ravi.bangoria@amd.com \
--to=ravi.bangoria@amd.com \
--cc=acme@kernel.org \
--cc=ananth.narayan@amd.com \
--cc=dapeng1.mi@linux.intel.com \
--cc=irogers@google.com \
--cc=james.clark@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=manali.shukla@amd.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=sandipan.das@amd.com \
--cc=santosh.shukla@amd.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®