[PATCH v4 14/24] iommu/arm-smmu-v3: Introduce per-cmdq cmdq_err_handler callback

[Nicolin Chen <nicolinc@nvidia.com>]

A subsequent change will need arm_smmu_cmdq_issue_cmdlist() to co-clear a
pending CMDQ_ERR after a CMD_SYNC poll timeout. And this needs to be done
for both smmu->cmdq and tegra241-cmdq.

Add a cmdq_err_handler and a paired cmdq_err_lock to struct arm_smmu_cmdq.
arm_smmu_gerror_handler() and tegra241_vintf0_handle_error() now take the
per-cmdq cmdq_err_lock when acking CMDQ_ERR.

tegra241_vintf0_handle_error() also checks (gerror ^ gerrorn) inside the
cmdq_err_lock since a concurrent cmdq_err_handler may have already acked
the error. arm_smmu_gerror_handler() already covers this via its existing
early-exit on no-active-bits.

Impl functions and caller will be added in the subsequent change.

Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h    | 12 ++++++++++--
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c    | 18 ++++++++++++++----
 drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c | 15 ++++++++++++---
 3 files changed, 36 insertions(+), 9 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 46f9e292a1cc8..604f7edf54158 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -695,6 +695,10 @@ struct arm_smmu_queue_poll {
 	bool				wfe;
 };
 
+struct arm_smmu_cmdq;
+typedef void (*arm_smmu_cmdq_err_fn)(struct arm_smmu_device *smmu,
+				     struct arm_smmu_cmdq *cmdq);
+
 struct arm_smmu_cmdq {
 	struct arm_smmu_queue		q;
 	atomic_long_t			*valid_map;
@@ -702,6 +706,10 @@ struct arm_smmu_cmdq {
 	atomic_t			lock;
 	unsigned long			*atc_sync_timeouts;
 	bool				(*supports_cmd)(struct arm_smmu_cmd *cmd);
+
+	/* Drain a pending CMDQ_ERR; will hold cmdq_err_lock with irqsave */
+	arm_smmu_cmdq_err_fn		cmdq_err_handler;
+	raw_spinlock_t			cmdq_err_lock;
 };
 
 static inline bool arm_smmu_cmdq_supports_cmd(struct arm_smmu_cmdq *cmdq,
@@ -1163,8 +1171,8 @@ int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
 			    struct arm_smmu_queue *q, void __iomem *page,
 			    unsigned long prod_off, unsigned long cons_off,
 			    size_t dwords, const char *name);
-int arm_smmu_cmdq_init(struct arm_smmu_device *smmu,
-		       struct arm_smmu_cmdq *cmdq);
+int arm_smmu_cmdq_init(struct arm_smmu_device *smmu, struct arm_smmu_cmdq *cmdq,
+		       arm_smmu_cmdq_err_fn cmdq_err_handler);
 
 static inline bool arm_smmu_master_canwbs(struct arm_smmu_master *master)
 {
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 d9fe48989fcd7..fc0757359b783 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2255,13 +2255,18 @@ static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
 {
 	u32 gerror, gerrorn, active;
 	struct arm_smmu_device *smmu = dev;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&smmu->cmdq.cmdq_err_lock, flags);
 
 	gerror = readl_relaxed(smmu->base + ARM_SMMU_GERROR);
 	gerrorn = readl_relaxed(smmu->base + ARM_SMMU_GERRORN);
 
 	active = gerror ^ gerrorn;
-	if (!(active & GERROR_ERR_MASK))
+	if (!(active & GERROR_ERR_MASK)) {
+		raw_spin_unlock_irqrestore(&smmu->cmdq.cmdq_err_lock, flags);
 		return IRQ_NONE; /* No errors pending */
+	}
 
 	dev_warn(smmu->dev,
 		 "unexpected global error reported (0x%08x), this could be serious\n",
@@ -2270,6 +2275,8 @@ static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
 	if (active & GERROR_SFM_ERR) {
 		/* SMMU is being disabled, so other errors don't matter */
 		writel(gerror, smmu->base + ARM_SMMU_GERRORN);
+		/* Release before arm_smmu_device_disable() that sleeps */
+		raw_spin_unlock_irqrestore(&smmu->cmdq.cmdq_err_lock, flags);
 		dev_err(smmu->dev, "device has entered Service Failure Mode!\n");
 		arm_smmu_device_disable(smmu);
 		return IRQ_HANDLED;
@@ -2297,6 +2304,7 @@ static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
 		arm_smmu_cmdq_skip_err(smmu);
 
 	writel(gerror, smmu->base + ARM_SMMU_GERRORN);
+	raw_spin_unlock_irqrestore(&smmu->cmdq.cmdq_err_lock, flags);
 	return IRQ_HANDLED;
 }
 
@@ -4357,13 +4365,15 @@ int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
 	return 0;
 }
 
-int arm_smmu_cmdq_init(struct arm_smmu_device *smmu,
-		       struct arm_smmu_cmdq *cmdq)
+int arm_smmu_cmdq_init(struct arm_smmu_device *smmu, struct arm_smmu_cmdq *cmdq,
+		       arm_smmu_cmdq_err_fn cmdq_err_handler)
 {
 	unsigned int nents = 1 << cmdq->q.llq.max_n_shift;
 
 	atomic_set(&cmdq->owner_prod, 0);
 	atomic_set(&cmdq->lock, 0);
+	raw_spin_lock_init(&cmdq->cmdq_err_lock);
+	cmdq->cmdq_err_handler = cmdq_err_handler;
 
 	cmdq->valid_map = (atomic_long_t *)devm_bitmap_zalloc(smmu->dev, nents,
 							      GFP_KERNEL);
@@ -4389,7 +4399,7 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
 	if (ret)
 		return ret;
 
-	ret = arm_smmu_cmdq_init(smmu, &smmu->cmdq);
+	ret = arm_smmu_cmdq_init(smmu, &smmu->cmdq, NULL);
 	if (ret)
 		return ret;
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
index 67be62a6e7640..fb2f8f68fa344 100644
--- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
+++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
@@ -319,10 +319,19 @@ static void tegra241_vintf0_handle_error(struct tegra241_vintf *vintf)
 		while (map) {
 			unsigned long lidx = __ffs64(map);
 			struct tegra241_vcmdq *vcmdq = vintf->lvcmdqs[lidx];
-			u32 gerror = readl_relaxed(REG_VCMDQ_PAGE0(vcmdq, GERROR));
+			struct arm_smmu_cmdq *cmdq = &vcmdq->cmdq;
+			unsigned long flags;
+			u32 gerror, gerrorn;
 
-			__arm_smmu_cmdq_skip_err(&vintf->cmdqv->smmu, &vcmdq->cmdq);
+			raw_spin_lock_irqsave(&cmdq->cmdq_err_lock, flags);
+			gerror = readl_relaxed(REG_VCMDQ_PAGE0(vcmdq, GERROR));
+			gerrorn = readl_relaxed(REG_VCMDQ_PAGE0(vcmdq, GERRORN));
+
+			if ((gerror ^ gerrorn) & GERROR_CMDQ_ERR)
+				__arm_smmu_cmdq_skip_err(&vintf->cmdqv->smmu,
+							 cmdq);
 			writel(gerror, REG_VCMDQ_PAGE0(vcmdq, GERRORN));
+			raw_spin_unlock_irqrestore(&cmdq->cmdq_err_lock, flags);
 			map &= ~BIT_ULL(lidx);
 		}
 	}
@@ -643,7 +652,7 @@ static int tegra241_vcmdq_alloc_smmu_cmdq(struct tegra241_vcmdq *vcmdq)
 	q->q_base = q->base_dma & VCMDQ_ADDR;
 	q->q_base |= FIELD_PREP(VCMDQ_LOG2SIZE, q->llq.max_n_shift);
 
-	return arm_smmu_cmdq_init(smmu, cmdq);
+	return arm_smmu_cmdq_init(smmu, cmdq, NULL);
 }
 
 /* VINTF Logical VCMDQ Resource Helpers */
-- 
2.43.0