[PATCH] x86/resctrl: Fix event counts regression in reused RMIDs
From: Peter Newman
Date: Wed Dec 07 2022 - 06:29:39 EST
When creating a new monitoring group, the RMID allocated for it may have
been used by a group which was previously removed. In this case, the
hardware counters will have non-zero values which should be deducted
from what is reported in the new group's counts.
resctrl_arch_reset_rmid() initializes the prev_msr value for counters to
0, causing the initial count to be charged to the new group. Resurrect
__rmid_read() and use it to initialize prev_msr correctly.
Fixes: 1d81d15db39c ("x86/resctrl: Move mbm_overflow_count() into resctrl_arch_rmid_read()")
Signed-off-by: Peter Newman <peternewman@xxxxxxxxxx>
---
arch/x86/kernel/cpu/resctrl/monitor.c | 39 ++++++++++++++++++---------
1 file changed, 27 insertions(+), 12 deletions(-)
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index efe0c30d3a12..404dd9c472c7 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -146,6 +146,24 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
return entry;
}
+static u64 __rmid_read(u32 rmid, enum resctrl_event_id eventid)
+{
+ u64 val;
+
+ /*
+ * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
+ * with a valid event code for supported resource type and the bits
+ * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
+ * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
+ * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
+ * are error bits.
+ */
+ wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+ rdmsrl(MSR_IA32_QM_CTR, val);
+
+ return val;
+}
+
static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
u32 rmid,
enum resctrl_event_id eventid)
@@ -170,10 +188,17 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
{
struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
struct arch_mbm_state *am;
+ uint64_t val;
am = get_arch_mbm_state(hw_dom, rmid, eventid);
- if (am)
+ if (am) {
memset(am, 0, sizeof(*am));
+
+ /* Record any initial, non-zero count value. */
+ val = __rmid_read(rmid, eventid);
+ if (!(val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)))
+ am->prev_msr = val;
+ }
}
static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
@@ -195,17 +220,7 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
return -EINVAL;
- /*
- * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
- * with a valid event code for supported resource type and the bits
- * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
- * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
- * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
- * are error bits.
- */
- wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
- rdmsrl(MSR_IA32_QM_CTR, msr_val);
-
+ msr_val = __rmid_read(rmid, eventid);
if (msr_val & RMID_VAL_ERROR)
return -EIO;
if (msr_val & RMID_VAL_UNAVAIL)
base-commit: 76dcd734eca23168cb008912c0f69ff408905235
--
2.39.0.rc0.267.gcb52ba06e7-goog