[PATCH rc v3 4/5] iommu/arm-smmu-v3: Skip EVTQ/PRIQ setup in kdump kernel

[Nicolin Chen]

In kdump cases, the crashed kernel's CDs and page tables can be corrupted,
which could trigger event spamming. Also, we cannot serve page requests.

Skip the EVTQ/PRIQ setup entirely rather than enabling then disabling them.

Skip the IRQ setup and guard their thread functions as well.

Also add some inline comments explaining that.

Fixes: b63b3439b856 ("iommu/arm-smmu-v3: Abort all transactions if SMMU is enabled in kdump kernel")
Cc: stable at vger.kernel.org # v6.12+
Suggested-by: Kevin Tian <kevin.tian at intel.com>
Signed-off-by: Nicolin Chen <nicolinc at nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 66 +++++++++++++++------
 1 file changed, 48 insertions(+), 18 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index b6aade469a6b6..f0ab0b640a3bb 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2269,6 +2269,14 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
 	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
 				      DEFAULT_RATELIMIT_BURST);
 
+	/*
+	 * A combined IRQ might call into this function with the queue disabled.
+	 * E.g. kdump, where stale HW PROD vs SW CONS would drive a bogus drain
+	 * and a CONS write to a disabled queue.
+	 */
+	if (!(readl_relaxed(smmu->base + ARM_SMMU_CR0) & CR0_EVTQEN))
+		return IRQ_HANDLED;
+
 	do {
 		while (!queue_remove_raw(q, evt)) {
 			arm_smmu_decode_event(smmu, evt, &event);
@@ -2337,6 +2345,14 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
 	struct arm_smmu_ll_queue *llq = &q->llq;
 	u64 evt[PRIQ_ENT_DWORDS];
 
+	/*
+	 * A combined IRQ might call into this function with the queue disabled.
+	 * E.g. kdump, where stale HW PROD vs SW CONS would drive a bogus drain
+	 * and a CONS write to a disabled queue.
+	 */
+	if (!(readl_relaxed(smmu->base + ARM_SMMU_CR0) & CR0_PRIQEN))
+		return IRQ_HANDLED;
+
 	do {
 		while (!queue_remove_raw(q, evt))
 			arm_smmu_handle_ppr(smmu, evt);
@@ -4941,7 +4957,10 @@ static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu)
 static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
 {
 	int ret, irq;
-	u32 irqen_flags = IRQ_CTRL_EVTQ_IRQEN | IRQ_CTRL_GERROR_IRQEN;
+	u32 irqen_flags = IRQ_CTRL_GERROR_IRQEN;
+
+	if (!is_kdump_kernel())
+		irqen_flags |= IRQ_CTRL_EVTQ_IRQEN;
 
 	/* Disable IRQs first */
 	ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_IRQ_CTRL,
@@ -4967,7 +4986,7 @@ static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
 	} else
 		arm_smmu_setup_unique_irqs(smmu);
 
-	if (smmu->features & ARM_SMMU_FEAT_PRI)
+	if (!is_kdump_kernel() && (smmu->features & ARM_SMMU_FEAT_PRI))
 		irqen_flags |= IRQ_CTRL_PRIQ_IRQEN;
 
 	/* Enable interrupt generation on the SMMU */
@@ -5118,21 +5137,35 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	cmd.opcode = CMDQ_OP_TLBI_NSNH_ALL;
 	arm_smmu_cmdq_issue_cmd_with_sync(smmu, &cmd);
 
-	/* Event queue */
-	writeq_relaxed(smmu->evtq.q.q_base, smmu->base + ARM_SMMU_EVTQ_BASE);
-	writel_relaxed(smmu->evtq.q.llq.prod, smmu->page1 + ARM_SMMU_EVTQ_PROD);
-	writel_relaxed(smmu->evtq.q.llq.cons, smmu->page1 + ARM_SMMU_EVTQ_CONS);
-
-	enables |= CR0_EVTQEN;
-	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
-				      ARM_SMMU_CR0ACK);
-	if (ret) {
-		dev_err(smmu->dev, "failed to enable event queue\n");
-		return ret;
+	/*
+	 * Event queue
+	 *
+	 * Do not enable in a kdump case, as the crashed kernel's CDs and page
+	 * tables might be corrupted, triggering event spamming.
+	 */
+	if (!is_kdump_kernel()) {
+		writeq_relaxed(smmu->evtq.q.q_base,
+			       smmu->base + ARM_SMMU_EVTQ_BASE);
+		writel_relaxed(smmu->evtq.q.llq.prod,
+			       smmu->page1 + ARM_SMMU_EVTQ_PROD);
+		writel_relaxed(smmu->evtq.q.llq.cons,
+			       smmu->page1 + ARM_SMMU_EVTQ_CONS);
+
+		enables |= CR0_EVTQEN;
+		ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+					      ARM_SMMU_CR0ACK);
+		if (ret) {
+			dev_err(smmu->dev, "failed to enable event queue\n");
+			return ret;
+		}
 	}
 
-	/* PRI queue */
-	if (smmu->features & ARM_SMMU_FEAT_PRI) {
+	/*
+	 * PRI queue
+	 *
+	 * Do not enable in a kdump case, as we cannot serve page requests.
+	 */
+	if (!is_kdump_kernel() && (smmu->features & ARM_SMMU_FEAT_PRI)) {
 		writeq_relaxed(smmu->priq.q.q_base,
 			       smmu->base + ARM_SMMU_PRIQ_BASE);
 		writel_relaxed(smmu->priq.q.llq.prod,
@@ -5165,9 +5198,6 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu)
 		return ret;
 	}
 
-	if (is_kdump_kernel())
-		enables &= ~(CR0_EVTQEN | CR0_PRIQEN);
-
 	/* Enable the SMMU interface */
 	enables |= CR0_SMMUEN;
 	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
-- 
2.43.0