[PATCH RFC v6 5/5] iommu/arm-smmu-v3: Wire up shared-SID STE ordering and feature gating

[Peng Fan (OSS)]

From: Peng Fan <peng.fan at nxp.com>

For shared SIDs, only the first master to attach writes the STE
(tracked by ste_installed under streams_mutex); subsequent masters
skip the write.  On teardown, skip the ABORT STE write while other
masters still share the SID, and reset ste_installed so the next
domain attach cycle re-writes the STE.

Fault events on shared SIDs cannot be attributed to a specific
master, so arm_smmu_find_master() returns NULL when the stream's
shared_masters list is non-empty.

Disable SVA, IOPF/stall, and vSMMU nesting for shared-SID masters
since all three require unambiguous SID-to-device mapping.  Clear
stall_enabled for both the new master and the existing first master
when sharing is detected in arm_smmu_insert_master(), so the STE
is never programmed with the stall bit.  This prevents
unrecoverable bus lockups since CMD_RESUME cannot be issued without
a unique SID-to-device mapping.

Assisted-by: LLM
Signed-off-by: Peng Fan <peng.fan at nxp.com>
---
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c    |  2 +-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c    |  3 ++
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c        | 60 +++++++++++++++++-----
 3 files changed, 52 insertions(+), 13 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 853276dd54536..cccc42b13d89e 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
@@ -310,7 +310,7 @@ static int arm_vsmmu_vdevice_init(struct iommufd_vdevice *vdev)
 	 * arm_vsmmu_vsid_to_sid() maps a vSID to master->streams[0] alone, so
 	 * more streams would leave the rest stale and none reads out of bounds.
 	 */
-	if (master->num_streams != 1)
+	if (master->num_streams != 1 || !list_empty(&master->shared_masters_elm))
 		return -EOPNOTSUPP;
 	return 0;
 }
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index faeec656da9e7..46d24f8eac830 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -281,6 +281,9 @@ static int arm_smmu_sva_set_dev_pasid(struct iommu_domain *domain,
 	if (!(master->smmu->features & ARM_SMMU_FEAT_SVA))
 		return -EOPNOTSUPP;
 
+	if (!list_empty(&master->shared_masters_elm))
+		return -EOPNOTSUPP;
+
 	/* Prevent arm_smmu_mm_release from being called while we are attaching */
 	if (!mmget_not_zero(domain->mm))
 		return -EINVAL;
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 328d580935b96..d56fe512382dc 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3154,11 +3154,38 @@ arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
 	}
 }
 
+static bool arm_smmu_is_shared_sid(struct arm_smmu_master *master)
+{
+	return !list_empty(&master->shared_masters_elm);
+}
+
+static bool arm_smmu_skip_shared_ste(struct arm_smmu_device *smmu,
+				     u32 sid, bool is_abort)
+{
+	struct arm_smmu_stream *stream;
+
+	lockdep_assert_held(&smmu->streams_mutex);
+
+	stream = arm_smmu_find_stream(smmu, sid);
+	if (!stream || list_empty(&stream->shared_masters))
+		return false;
+
+	if (is_abort) {
+		stream->ste_installed = false;
+		return true;
+	}
+	if (stream->ste_installed)
+		return true;
+	stream->ste_installed = true;
+	return false;
+}
+
 void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master,
 				  const struct arm_smmu_ste *target)
 {
-	int i, j;
+	int i;
 	struct arm_smmu_device *smmu = master->smmu;
+	bool is_abort;
 
 	master->cd_table.in_ste =
 		FIELD_GET(STRTAB_STE_0_CFG, le64_to_cpu(target->data[0])) ==
@@ -3167,18 +3194,23 @@ void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master,
 		FIELD_GET(STRTAB_STE_1_EATS, le64_to_cpu(target->data[1])) ==
 		STRTAB_STE_1_EATS_TRANS;
 
+	is_abort = FIELD_GET(STRTAB_STE_0_CFG, le64_to_cpu(target->data[0])) ==
+		   STRTAB_STE_0_CFG_ABORT;
+
 	for (i = 0; i < master->num_streams; ++i) {
 		u32 sid = master->streams[i]->id;
-		struct arm_smmu_ste *step =
-			arm_smmu_get_step_for_sid(smmu, sid);
+		struct arm_smmu_ste *step;
 
-		/* Bridged PCI devices may end up with duplicated IDs */
-		for (j = 0; j < i; j++)
-			if (master->streams[j]->id == sid)
-				break;
-		if (j < i)
-			continue;
+		if (arm_smmu_is_shared_sid(master)) {
+			mutex_lock(&smmu->streams_mutex);
+			if (arm_smmu_skip_shared_ste(smmu, sid, is_abort)) {
+				mutex_unlock(&smmu->streams_mutex);
+				continue;
+			}
+			mutex_unlock(&smmu->streams_mutex);
+		}
 
+		step = arm_smmu_get_step_for_sid(smmu, sid);
 		arm_smmu_write_ste(master, sid, step, target);
 	}
 }
@@ -3326,8 +3358,7 @@ static int arm_smmu_enable_iopf(struct arm_smmu_master *master,
 	if (!master->stall_enabled)
 		return 0;
 
-	/* We're not keeping track of SIDs in fault events */
-	if (master->num_streams != 1)
+	if (master->num_streams != 1 || arm_smmu_is_shared_sid(master))
 		return -EOPNOTSUPP;
 
 	if (master->iopf_refcount) {
@@ -4360,9 +4391,11 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 				break;
 			}
 
-			if (list_empty(&stream->shared_masters))
+			if (list_empty(&stream->shared_masters)) {
 				list_add_tail(&stream->master->shared_masters_elm,
 					      &stream->shared_masters);
+				stream->master->stall_enabled = false;
+			}
 			list_add_tail(&master->shared_masters_elm,
 				      &stream->shared_masters);
 			master->streams[n++] = stream;
@@ -4522,6 +4555,9 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 	    smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
 		master->stall_enabled = true;
 
+	if (arm_smmu_is_shared_sid(master))
+		master->stall_enabled = false;
+
 	ret = arm_smmu_master_prepare_ats(master);
 	if (ret)
 		goto err_disable_pasid;

-- 
2.34.1