iommu/arm-smmu-v3: Fix device crash on kdump kernel

index ef42df4753ec4..cd60b692c3901 100644
@@ -861,6 +861,7 @@ struct arm_smmu_device {
 #define ARM_SMMU_OPT_MSIPOLL		(1 << 2)
 #define ARM_SMMU_OPT_CMDQ_FORCE_SYNC	(1 << 3)
 #define ARM_SMMU_OPT_TEGRA241_CMDQV	(1 << 4)
+#define ARM_SMMU_OPT_KDUMP_ADOPT	(1 << 5)
 	u32				options;
 
 	struct arm_smmu_cmdq		cmdq;

347 lines not on this page · raw message

index fbc0fa6f182c6..27b84688bcc99 100644
@@ -4309,6 +4309,29 @@ static void arm_smmu_remove_master(struct arm_smmu_master *master)
 	kfree(master->build_invs);
 }
 
+static bool arm_smmu_is_attach_deferred(struct device *dev)
+{
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+	struct arm_smmu_device *smmu = master->smmu;
+	int i;
+
+	if (!(smmu->options & ARM_SMMU_OPT_KDUMP_ADOPT))
+		return false;
+
+	for (i = 0; i < master->num_streams; i++) {
+		struct arm_smmu_ste *ste =
+			arm_smmu_get_step_for_sid(smmu, master->streams[i].id);
+		u64 ent0 = le64_to_cpu(ste->data[0]);
+
+		/* Defer only when there might be in-flight DMAs */
+		if ((ent0 & STRTAB_STE_0_V) &&
+		    FIELD_GET(STRTAB_STE_0_CFG, ent0) != STRTAB_STE_0_CFG_ABORT)
+			return true;
+	}
+
+	return false;
+}
+
 static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 {
 	int ret;

@@ -4471,6 +4494,7 @@ static const struct iommu_ops arm_smmu_ops = {
 	.hw_info		= arm_smmu_hw_info,
 	.domain_alloc_sva       = arm_smmu_sva_domain_alloc,
 	.domain_alloc_paging_flags = arm_smmu_domain_alloc_paging_flags,
+	.is_attach_deferred	= arm_smmu_is_attach_deferred,
 	.probe_device		= arm_smmu_probe_device,
 	.release_device		= arm_smmu_release_device,
 	.device_group		= arm_smmu_device_group,

index 27b84688bcc99..17d5e1395e245 100644
@@ -2363,6 +2363,14 @@ 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_NONE;
+
 	do {
 		while (!queue_remove_raw(q, evt)) {
 			arm_smmu_decode_event(smmu, evt, &event);

@@ -2431,6 +2439,14 @@ 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_NONE;
+
 	do {
 		while (!queue_remove_raw(q, evt))
 			arm_smmu_handle_ppr(smmu, evt);

@@ -5055,7 +5071,10 @@ 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,

@@ -5081,7 +5100,7 @@ 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 */

@@ -5191,21 +5210,35 @@ 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,

@@ -5238,9 +5271,6 @@ 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,

index 17d5e1395e245..f9332cf0b28a6 100644
@@ -5150,11 +5150,28 @@ static void arm_smmu_write_strtab(struct arm_smmu_device *smmu)
 static int arm_smmu_device_reset(struct arm_smmu_device *smmu)
 {
 	int ret;
-	u32 reg, enables;
+	u32 reg, enables = 0;
 	struct arm_smmu_cmdq_ent cmd;
 
-	/* Clear CR0 and sync (disables SMMU and queue processing) */
 	reg = readl_relaxed(smmu->base + ARM_SMMU_CR0);
+
+	/*
+	 * In a kdump case (set when CR0_SMMUEN=1 and !GERROR_SFM_ERR), retain
+	 * CR0_SMMUEN to avoid aborting in-flight DMA, and CR0_ATSCHK to carry
+	 * on the ATS-check policy.
+	 *
+	 * According to spec, updating STRTAB_BASE/CR1/CR2 when CR0_SMMUEN=1 is
+	 * CONSTRAINED UNPREDICTABLE. So, skip those register updates and rely
+	 * on the adopted stream table from the crashed kernel.
+	 */
+	if (smmu->options & ARM_SMMU_OPT_KDUMP_ADOPT) {
+		dev_info(smmu->dev,
+			 "kdump: retaining SMMUEN for in-flight DMA\n");
+		enables = reg & (CR0_SMMUEN | CR0_ATSCHK);
+		goto reset_queues;
+	}
+
+	/* Clear CR0 and sync (disables SMMU and queue processing) */
 	if (reg & CR0_SMMUEN) {
 		dev_warn(smmu->dev, "SMMU currently enabled! Resetting...\n");
 		arm_smmu_update_gbpa(smmu, GBPA_ABORT, 0);

@@ -5184,12 +5201,36 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	/* Stream table */
 	arm_smmu_write_strtab(smmu);
 
+reset_queues:
+	if (smmu->options & ARM_SMMU_OPT_KDUMP_ADOPT) {
+		/* Disable queues since arm_smmu_device_disable() was skipped */
+		ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+					      ARM_SMMU_CR0ACK);
+		if (ret) {
+			dev_err(smmu->dev, "failed to disable queues\n");
+			return ret;
+		}
+	}
+
+	/*
+	 * GERROR bits are latched. Read after queue disabling so that unhandled
+	 * errors would be visible. Ack everything prior to re-enabling the CMDQ
+	 * as a stale CMDQ_ERR would halt the CMDQ and new command will timeout.
+	 */
+	if (is_kdump_kernel()) {
+		u32 gerror = readl_relaxed(smmu->base + ARM_SMMU_GERROR);
+		u32 gerrorn = readl_relaxed(smmu->base + ARM_SMMU_GERRORN);
+
+		if ((gerror ^ gerrorn) & GERROR_ERR_MASK)
+			writel(gerror, smmu->base + ARM_SMMU_GERRORN);
+	}
+
 	/* Command queue */
 	writeq_relaxed(smmu->cmdq.q.q_base, smmu->base + ARM_SMMU_CMDQ_BASE);
 	writel_relaxed(smmu->cmdq.q.llq.prod, smmu->base + ARM_SMMU_CMDQ_PROD);
 	writel_relaxed(smmu->cmdq.q.llq.cons, smmu->base + ARM_SMMU_CMDQ_CONS);
 
-	enables = CR0_CMDQEN;
+	enables |= CR0_CMDQEN;
 	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
 				      ARM_SMMU_CR0ACK);
 	if (ret) {

index f9332cf0b28a6..18e0d97cec401 100644
@@ -5402,6 +5402,36 @@ static void arm_smmu_get_httu(struct arm_smmu_device *smmu, u32 reg)
 			  hw_features, fw_features);
 }
 
+static void arm_smmu_device_hw_probe_kdump(struct arm_smmu_device *smmu)
+{
+	u32 gerror, gerrorn, active;
+
+	/*
+	 * If SMMU is already active in kdump case, there could be in-flight DMA
+	 * from devices initiated by the crashed kernel.
+	 */
+	if (!(readl_relaxed(smmu->base + ARM_SMMU_CR0) & CR0_SMMUEN))
+		return;
+
+	/* For now, only support a coherent SMMU that works with MEMREMAP_WB */
+	if (!(smmu->features & ARM_SMMU_FEAT_COHERENCY)) {
+		dev_warn(smmu->dev,
+			 "kdump: non-coherent SMMU can't adopt stream table\n");
+		return;
+	}
+
+	gerror = readl_relaxed(smmu->base + ARM_SMMU_GERROR);
+	gerrorn = readl_relaxed(smmu->base + ARM_SMMU_GERRORN);
+	active = gerror ^ gerrorn;
+	if (active & GERROR_SFM_ERR) {
+		dev_warn(smmu->dev,
+			 "kdump: SMMU in Service Failure Mode, must reset\n");
+		return;
+	}
+
+	smmu->options |= ARM_SMMU_OPT_KDUMP_ADOPT;
+}
+
 static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 {
 	u32 reg;

@@ -5616,6 +5646,10 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 
 	dev_info(smmu->dev, "oas %lu-bit (features 0x%08x)\n",
 		 smmu->oas, smmu->features);
+
+	if (is_kdump_kernel())
+		arm_smmu_device_hw_probe_kdump(smmu);
+
 	return 0;
 }