[RESEND PATCH v4 08/11] perf/cxl: Unfreeze counters after handling an overflow interrupt

The counters run with Freeze on Overflow set, so one overflow freezes every
counter in the block (CXL r4.0 8.2.7.2.1), and a frozen counter "remains
frozen until explicitly unfrozen by software" (8.2.7.1.3, Table 8-183).
cxl_pmu_irq() reads the overflowed counters and clears the overflow status
but never unfreezes, so everything stays frozen until the next pmu_enable()
and events in that window are lost.

Unfreeze after clearing the status, unless the PMU has been disabled in the
meantime - cxl_pmu_disable() freezes the block deliberately. Track the
enabled state and leave it frozen in that case.

Fixes: 5d7107c72796 ("perf: CXL Performance Monitoring Unit driver")
Reported-by: [email protected]
Closes: https://sashiko.dev/#/patchset/[email protected]?part=1
Assisted-by: Claude:claude-opus-4-8
Reviewed-by: Jonathan Cameron <[email protected]>
Signed-off-by: Dave Jiang <[email protected]>
---
 drivers/perf/cxl_pmu.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/perf/cxl_pmu.c b/drivers/perf/cxl_pmu.c
index 448e1da3d59f..a081fcba6991 100644
--- a/drivers/perf/cxl_pmu.c
+++ b/drivers/perf/cxl_pmu.c
@@ -108,6 +108,8 @@ struct cxl_pmu_info {
 	bool filter_hdm;
 	int msi_vec;
 	int irq;
+	/* Set between pmu_enable() and pmu_disable(), read by the IRQ handler */
+	bool enabled;
 };
 
 #define pmu_to_cxl_pmu_info(_pmu) container_of(_pmu, struct cxl_pmu_info, pmu)
@@ -596,6 +598,7 @@ static void cxl_pmu_enable(struct pmu *pmu)
 	void __iomem *base = info->base;
 
 	/* Can assume frozen at this stage */
+	WRITE_ONCE(info->enabled, true);
 	writeq(0, base + CXL_PMU_FREEZE_REG);
 }
 
@@ -604,6 +607,7 @@ static void cxl_pmu_disable(struct pmu *pmu)
 	struct cxl_pmu_info *info = pmu_to_cxl_pmu_info(pmu);
 	void __iomem *base = info->base;
 
+	WRITE_ONCE(info->enabled, false);
 	/*
 	 * Whilst bits above number of counters are RsvdZ
 	 * they are unlikely to be repurposed given
@@ -802,6 +806,21 @@ static irqreturn_t cxl_pmu_irq(int irq, void *data)
 
 	writeq(overflowed, base + CXL_PMU_OVERFLOW_REG);
 
+	/*
+	 * An overflow freezes every counter in the CPMU, so unfreeze once the
+	 * overflowed ones have been read and their status cleared. Otherwise
+	 * they stay frozen until the next pmu_enable() and events are lost.
+	 *
+	 * Not while the PMU is disabled, so as not to undo an intentional freeze.
+	 * The check is advisory, not exclusive: pmu_disable() normally runs on
+	 * info->on_cpu with interrupts off, where the pinned handler cannot
+	 * preempt it. In the one window where it does not - the migration in
+	 * cxl_pmu_offline_cpu() - the counters are legitimately running again,
+	 * so unfreezing is correct there anyway.
+	 */
+	if (READ_ONCE(info->enabled))
+		writeq(0, base + CXL_PMU_FREEZE_REG);
+
 	return IRQ_HANDLED;
 }
 
-- 
2.54.0