There is an existing arm_smmu_cmdq_build_sync_cmd() so the driver should
call it at all places other than going through arm_smmu_cmdq_build_cmd()
separately. This helps the following patch that adds a CS_NONE option.

Note that this changes the type of CMD_SYNC in __arm_smmu_cmdq_skip_err,
in ARM_SMMU_OPT_MSIPOLL=true case, from previously a non-MSI one to now
an MSI one that is proven to still work using a hacking test:
  nvme: Adding to iommu group 10
  nvme: --------hacking-----------
  arm-smmu-v3: unexpected global error reported (0x00000001),
               this could be serious
  arm-smmu-v3: CMDQ error (cons 0x01000022): Illegal command
  arm-smmu-v3: skipping command in error state:
  arm-smmu-v3:  0x0000000000000000
  arm-smmu-v3:  0x0000000000000000
  nvme: -------recovered----------
  nvme nvme0: 72/0/0 default/read/poll queues
   nvme0n1: p1 p2

Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 36 ++++++++-------------
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  3 --
 2 files changed, 13 insertions(+), 26 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 f409ead589ff..f481d7be3d4e 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -329,16 +329,6 @@ 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.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;
 	}
@@ -354,20 +344,23 @@ 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_cmdq_ent ent = {
-		.opcode = CMDQ_OP_CMD_SYNC,
-	};
+	cmd[1] = 0;
+	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 (!(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;
-	}
-
-	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;
 }
 
 static void __arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu,
@@ -384,9 +377,6 @@ static 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");
@@ -420,7 +410,7 @@ static void __arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu,
 		dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);
 
 	/* 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, cons);
 
 	queue_write(Q_ENT(q, cons), cmd, q->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 c1454e9758c4..6c5739f6b90f 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -518,9 +518,6 @@ struct arm_smmu_cmdq_ent {
 		} resume;
 
 		#define CMDQ_OP_CMD_SYNC	0x46
-		struct {
-			u64			msiaddr;
-		} sync;
 	};
 };
 
-- 
2.43.0

On Tue, Aug 06, 2024 at 07:11:47PM -0700, Nicolin Chen wrote:
> There is an existing arm_smmu_cmdq_build_sync_cmd() so the driver should
> call it at all places other than going through arm_smmu_cmdq_build_cmd()
> separately. This helps the following patch that adds a CS_NONE option.
> 
> Note that this changes the type of CMD_SYNC in __arm_smmu_cmdq_skip_err,
> in ARM_SMMU_OPT_MSIPOLL=true case, from previously a non-MSI one to now
> an MSI one that is proven to still work using a hacking test:
>   nvme: Adding to iommu group 10
>   nvme: --------hacking-----------
>   arm-smmu-v3: unexpected global error reported (0x00000001),
>                this could be serious
>   arm-smmu-v3: CMDQ error (cons 0x01000022): Illegal command
>   arm-smmu-v3: skipping command in error state:
>   arm-smmu-v3:  0x0000000000000000
>   arm-smmu-v3:  0x0000000000000000
>   nvme: -------recovered----------
>   nvme nvme0: 72/0/0 default/read/poll queues
>    nvme0n1: p1 p2

Hmm, I'm still a little wary of this. The only reason we emit a CMD_SYNC
in __arm_smmu_cmdq_skip_err() is because the SMMU doesn't have a NOP
command. So I'd really like the SYNC to have as little functionality
as possible in this case.

I think we could either propapate the 'cs' field down to
arm_smmu_cmdq_build_cmd() or just open-code the command-creation in
__arm_smmu_cmdq_skip_err().

Will

On Fri, Aug 16, 2024 at 02:53:31PM +0100, Will Deacon wrote:
> On Tue, Aug 06, 2024 at 07:11:47PM -0700, Nicolin Chen wrote:
> > There is an existing arm_smmu_cmdq_build_sync_cmd() so the driver should
> > call it at all places other than going through arm_smmu_cmdq_build_cmd()
> > separately. This helps the following patch that adds a CS_NONE option.
> >
> > Note that this changes the type of CMD_SYNC in __arm_smmu_cmdq_skip_err,
> > in ARM_SMMU_OPT_MSIPOLL=true case, from previously a non-MSI one to now
> > an MSI one that is proven to still work using a hacking test:
> >   nvme: Adding to iommu group 10
> >   nvme: --------hacking-----------
> >   arm-smmu-v3: unexpected global error reported (0x00000001),
> >                this could be serious
> >   arm-smmu-v3: CMDQ error (cons 0x01000022): Illegal command
> >   arm-smmu-v3: skipping command in error state:
> >   arm-smmu-v3:  0x0000000000000000
> >   arm-smmu-v3:  0x0000000000000000
> >   nvme: -------recovered----------
> >   nvme nvme0: 72/0/0 default/read/poll queues
> >    nvme0n1: p1 p2
> 
> Hmm, I'm still a little wary of this. The only reason we emit a CMD_SYNC
> in __arm_smmu_cmdq_skip_err() is because the SMMU doesn't have a NOP
> command. So I'd really like the SYNC to have as little functionality
> as possible in this case.
> 
> I think we could either propapate the 'cs' field down to
> arm_smmu_cmdq_build_cmd() or just open-code the command-creation in
> __arm_smmu_cmdq_skip_err().

OK. Let's go with your approach then:
+       if (arm_smmu_cmdq_needs_busy_polling(smmu, cmdq))
+               u64p_replace_bits(cmd, CMDQ_SYNC_0_CS_NONE, CMDQ_SYNC_0_CS);

Thanks
Nicolin