[PATCH v2 1/2] x86/resctrl: Fix event counts regression in reused RMIDs

[Peter Newman]

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.

Unlike before, __rmid_read() checks for error bits in the MSR read so
that callers don't need to.

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 | 49 ++++++++++++++++++---------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index efe0c30d3a12..77538abeb72a 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -146,6 +146,30 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
 	return entry;
 }
 
+static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
+{
+	u64 msr_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, msr_val);
+
+	if (msr_val & RMID_VAL_ERROR)
+		return -EIO;
+	if (msr_val & RMID_VAL_UNAVAIL)
+		return -EINVAL;
+
+	*val = msr_val;
+	return 0;
+}
+
 static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
@@ -172,8 +196,12 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
 	struct arch_mbm_state *am;
 
 	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. */
+		__rmid_read(rmid, eventid, &am->prev_msr);
+	}
 }
 
 static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
@@ -191,25 +219,14 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct arch_mbm_state *am;
 	u64 msr_val, chunks;
+	int ret;
 
 	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);
-
-	if (msr_val & RMID_VAL_ERROR)
-		return -EIO;
-	if (msr_val & RMID_VAL_UNAVAIL)
-		return -EINVAL;
+	ret = __rmid_read(rmid, eventid, &msr_val);
+	if (ret)
+		return ret;
 
 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
 	if (am) {

base-commit: 830b3c68c1fb1e9176028d02ef86f3cf76aa2476
-- 
2.39.0.rc1.256.g54fd8350bd-goog