[PATCH v1 4/5] iommu/arm-smmu-v3-iommufd: Convert cache invalidation to the core array loop

[Nicolin Chen]

arm_vsmmu_cache_invalidate() allocated a buffer for the entire user request
array, walked the array converting each of the commands, and issued those
converted commands to the cmdq in CMDQ_BATCH_ENTRIES sized chunks, carrying
the sub-array bookkeeping all on its own.

The iommufd core now iterates the invalidation array and re-invokes the op
with the not-yet-handled sub-array, so the driver only has to proceed with
a single chunk per call.

Instead of a per-array allocation, use a fixed on-stack batch to copy from
the userspace array. If the copy fails due to nonzero padding (VMM violates
the ABI), fail the entire batch.

Convert the whole batch before issuing any of it: a malformed command is a
userspace bug, so the first illegal command fails the batch as a unit,
issuing nothing and leaving array->entry_num at zero, the same way the copy
above bails on nonzero padding. A batch that converts cleanly is issued in
full, so the op returns either a handled count with no error or zero with
an error.

A zero-length array now returns success once the data type gets validated,
matching the documented probe behavior, rather than the -EINVAL that the
full-array copy helper would previously return.

This also fixes two long-standing bugs:
 1) On a conversion failure the old code reported commands that it had
    converted but not yet issued, so user space advanced its consumer
    index past invalidations that never reached the cmdq.
 2) A zero-length array was rejected with -EINVAL, although the uAPI
    documents it as a valid request that only probes the data type.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Nicolin Chen <nicolinc@xxxxxxxxxx>
---
 .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c     | 73 ++++++++++---------
 1 file changed, 39 insertions(+), 34 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
index 393d69783225c..aee58c0be4597 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
@@ -412,49 +412,54 @@ int arm_vsmmu_cache_invalidate(struct iommufd_viommu *viommu,
 			       struct iommu_user_data_array *array)
 {
 	struct arm_vsmmu *vsmmu = container_of(viommu, struct arm_vsmmu, core);
+	struct arm_vsmmu_invalidation_cmd cmds[CMDQ_BATCH_ENTRIES - 1];
 	struct arm_smmu_device *smmu = vsmmu->smmu;
-	struct arm_vsmmu_invalidation_cmd *last;
-	struct arm_vsmmu_invalidation_cmd *cmds;
-	struct arm_vsmmu_invalidation_cmd *cur;
-	struct arm_vsmmu_invalidation_cmd *end;
+	struct iommu_user_data_array batch = {
+		.type = array->type,
+		.uptr = array->uptr,
+		.entry_len = array->entry_len,
+	};
 	int ret;
-
-	cmds = kzalloc_objs(*cmds, array->entry_num);
-	if (!cmds)
-		return -ENOMEM;
-	cur = cmds;
-	end = cmds + array->entry_num;
+	u32 i;
 
 	static_assert(sizeof(*cmds) == 2 * sizeof(u64));
+
+	if (array->type != IOMMU_VIOMMU_INVALIDATE_DATA_ARM_SMMUV3) {
+		array->entry_num = 0;
+		return -EINVAL;
+	}
+
+	/* A zero-length array only probes the type, validated above */
+	if (!array->entry_num)
+		return 0;
+
+	/*
+	 * The core re-invokes this op for the remaining requests, so copy one
+	 * cmdq batch worth of commands into a fixed on-stack buffer rather than
+	 * allocating for the whole array.
+	 */
+	batch.entry_num = min_t(u32, array->entry_num, ARRAY_SIZE(cmds));
 	ret = iommu_copy_struct_from_full_user_array(
-		cmds, sizeof(*cmds), array,
+		cmds, sizeof(*cmds), &batch,
 		IOMMU_VIOMMU_INVALIDATE_DATA_ARM_SMMUV3);
-	if (ret)
-		goto out;
-
-	last = cmds;
-	while (cur != end) {
-		ret = arm_vsmmu_convert_user_cmd(vsmmu, cur);
-		if (ret)
-			goto out;
-
-		/* FIXME work in blocks of CMDQ_BATCH_ENTRIES and copy each block? */
-		cur++;
-		if (cur != end && (cur - last) != CMDQ_BATCH_ENTRIES - 1)
-			continue;
-
-		/* FIXME always uses the main cmdq rather than trying to group by type */
-		ret = arm_smmu_cmdq_issue_cmdlist(smmu, &smmu->cmdq, &last->cmd,
-						  cur - last, true);
+	if (ret) {
+		array->entry_num = 0;
+		return ret;
+	}
+
+	/* Convert the whole batch; a single illegal command fails it all */
+	for (i = 0; i < batch.entry_num; i++) {
+		ret = arm_vsmmu_convert_user_cmd(vsmmu, &cmds[i]);
 		if (ret) {
-			cur--;
-			goto out;
+			array->entry_num = 0;
+			return ret;
 		}
-		last = cur;
 	}
-out:
-	array->entry_num = cur - cmds;
-	kfree(cmds);
+
+	/* FIXME always uses the main cmdq rather than trying to group by type */
+	ret = arm_smmu_cmdq_issue_cmdlist(smmu, &smmu->cmdq, &cmds->cmd,
+					  batch.entry_num, true);
+	array->entry_num = ret ? 0 : batch.entry_num;
 	return ret;
 }
 
-- 
2.43.0