[PATCH v6 2/6] iommu/arm-smmu-v3: Add CS_NONE quirk

[Jason Gunthorpe]

On Mon, Apr 29, 2024 at 09:43:45PM -0700, Nicolin Chen wrote:
> The CMDQV extension in NVIDIA Tegra241 SoC only supports CS_NONE in the
> CS field of CMD_SYNC. Add a quirk flag to accommodate that.
> 
> Signed-off-by: Nicolin Chen <nicolinc at nvidia.com>
> ---
>  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 10 ++++++++--
>  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  4 ++++
>  2 files changed, 12 insertions(+), 2 deletions(-)

This seems fine, other than the misplaced hunk

Reviewed-by: Jason Gunthorpe <jgg at nvidia.com>

But it might be tidier like the below. There is already a function
that is called to build the sync that has the q, just build it
directly there and avoid going through the ent?

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 268da20baa4e9c..fa9cb0f49bf1ee 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -338,18 +338,6 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		cmd[0] |= FIELD_PREP(CMDQ_RESUME_0_RESP, ent->resume.resp);
 		cmd[1] |= FIELD_PREP(CMDQ_RESUME_1_STAG, ent->resume.stag);
 		break;
-	case CMDQ_OP_CMD_SYNC:
-		if (ent->sync.cs_none) {
-			cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_NONE);
-		} else if (ent->sync.msiaddr) {
-			cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_IRQ);
-			cmd[1] |= ent->sync.msiaddr & CMDQ_SYNC_1_MSIADDR_MASK;
-		} else {
-			cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_SEV);
-		}
-		cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSH, ARM_SMMU_SH_ISH);
-		cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIATTR, ARM_SMMU_MEMATTR_OIWB);
-		break;
 	default:
 		return -ENOENT;
 	}
@@ -367,25 +355,30 @@ static struct arm_smmu_cmdq *arm_smmu_get_cmdq(struct arm_smmu_device *smmu,
 }
 
 static void arm_smmu_cmdq_build_sync_cmd(u64 *cmd, struct arm_smmu_device *smmu,
-					 struct arm_smmu_queue *q, u32 prod)
+					 struct arm_smmu_queue *q, u32 prod,
+					 bool msi)
 {
-	struct arm_smmu_cmdq_ent ent = {
-		.opcode = CMDQ_OP_CMD_SYNC,
-	};
+	memset(cmd, 0, 1 << CMDQ_ENT_SZ_SHIFT);
+	cmd[0] = FIELD_PREP(CMDQ_0_OP, CMDQ_OP_CMD_SYNC) |
+		 FIELD_PREP(CMDQ_SYNC_0_MSH, ARM_SMMU_SH_ISH) |
+		 FIELD_PREP(CMDQ_SYNC_0_MSIATTR, ARM_SMMU_MEMATTR_OIWB);
+	if (q->quirks & CMDQ_QUIRK_SYNC_CS_NONE_ONLY) {
+		cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_NONE);
+		return;
+	}
+
+	if (!msi || !(smmu->options & ARM_SMMU_OPT_MSIPOLL)) {
+		cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_SEV);
+		return;
+	}
 
 	/*
 	 * Beware that Hi16xx adds an extra 32 bits of goodness to its MSI
 	 * payload, so the write will zero the entire command on that platform.
 	 */
-	if (smmu->options & ARM_SMMU_OPT_MSIPOLL) {
-		ent.sync.msiaddr = q->base_dma + Q_IDX(&q->llq, prod) *
-				   q->ent_dwords * 8;
-	}
-
-	if (q->quirks & CMDQ_QUIRK_SYNC_CS_NONE_ONLY)
-		ent.sync.cs_none = true;
-
-	arm_smmu_cmdq_build_cmd(cmd, &ent);
+	cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_IRQ);
+	cmd[1] = (q->base_dma + Q_IDX(&q->llq, prod) * q->ent_dwords * 8) &
+		 CMDQ_SYNC_1_MSIADDR_MASK;
 }
 
 void __arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu,
@@ -402,9 +395,6 @@ void __arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu,
 	u64 cmd[CMDQ_ENT_DWORDS];
 	u32 cons = readl_relaxed(q->cons_reg);
 	u32 idx = FIELD_GET(CMDQ_CONS_ERR, cons);
-	struct arm_smmu_cmdq_ent cmd_sync = {
-		.opcode = CMDQ_OP_CMD_SYNC,
-	};
 
 	dev_err(smmu->dev, "CMDQ error (cons 0x%08x): %s\n", cons,
 		idx < ARRAY_SIZE(cerror_str) ?  cerror_str[idx] : "Unknown");
@@ -437,11 +427,8 @@ void __arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu,
 	for (i = 0; i < ARRAY_SIZE(cmd); ++i)
 		dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);
 
-	if (q->quirks & CMDQ_QUIRK_SYNC_CS_NONE_ONLY)
-		cmd_sync.sync.cs_none = true;
-
 	/* Convert the erroneous command into a CMD_SYNC */
-	arm_smmu_cmdq_build_cmd(cmd, &cmd_sync);
+	arm_smmu_cmdq_build_sync_cmd(cmd, smmu, q, 0, false);
 
 	queue_write(Q_ENT(q, cons), cmd, q->ent_dwords);
 }
@@ -812,7 +799,8 @@ static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
 	arm_smmu_cmdq_write_entries(cmdq, cmds, llq.prod, n);
 	if (sync) {
 		prod = queue_inc_prod_n(&llq, n);
-		arm_smmu_cmdq_build_sync_cmd(cmd_sync, smmu, &cmdq->q, prod);
+		arm_smmu_cmdq_build_sync_cmd(cmd_sync, smmu, &cmdq->q, prod,
+					     true);
 		queue_write(Q_ENT(&cmdq->q, prod), cmd_sync, CMDQ_ENT_DWORDS);
 
 		/*
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 9412fa4ff5e045..b1ce1986e61101 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -520,10 +520,6 @@ struct arm_smmu_cmdq_ent {
 		} resume;
 
 		#define CMDQ_OP_CMD_SYNC	0x46
-		struct {
-			u64			msiaddr;
-			bool			cs_none;
-		} sync;
 	};
 };