[PATCH RFC v6 3/5] iommu/arm-smmu-v3: Support shared SIDs in insert/remove_master

[Peng Fan (OSS)]

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

On SoCs like NXP i.MX95 where the SMMU has a limited number of Stream
IDs (e.g. 6-bit bus = 64 SIDs), multiple DMA-capable devices are
assigned the same Stream ID by hardware design.

When a second master attempts to use a SID that is already claimed,
link the masters together via the stream's shared_masters list instead
of rejecting the probe. The stream object is shared directly between
masters — no duplication.

Sharing is restricted to single-SID masters (num_streams == 1) to keep
the STE lifecycle simple. Multi-SID sharing is explicitly rejected.

On removal, a shared master detaches from the shared_masters list and
ownership transfers to the next sharer if the departing master was the
stream owner. The stream and its RB tree entry are kept alive until
the last master using that SID is removed.

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

Suggested-by: Nicolin Chen <nicolinc at nvidia.com>
Link: https://lore.kernel.org/linux-iommu/Z3r-cBm00tVE4eKe@Asurada-Nvidia/
Assisted-by: LLM
Signed-off-by: Peng Fan <peng.fan at nxp.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 47 +++++++++++++++++++++++++----
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  3 ++
 2 files changed, 44 insertions(+), 6 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 0ea755ea82192..351ccdfa765b4 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2097,6 +2097,8 @@ arm_smmu_find_master(struct arm_smmu_device *smmu, u32 sid)
 	stream = arm_smmu_find_stream(smmu, sid);
 	if (!stream)
 		return NULL;
+	if (!list_empty(&stream->shared_masters))
+		return NULL;
 	return stream->master;
 }
 
@@ -4332,6 +4334,7 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 		kfree(master->streams);
 		return -ENOMEM;
 	}
+	INIT_LIST_HEAD(&master->shared_masters_elm);
 
 	mutex_lock(&smmu->streams_mutex);
 	for (i = 0, n = 0; i < fwspec->num_ids; i++) {
@@ -4348,11 +4351,22 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 			if (stream->master == master)
 				continue;
 
-			dev_warn(master->dev,
-				 "Aliasing StreamID 0x%x (from %s) unsupported, expect DMA to be broken\n",
-				 sid, dev_name(stream->master->dev));
-			ret = -ENODEV;
-			break;
+			if (fwspec->num_ids != 1 ||
+			    stream->master->num_streams != 1) {
+				dev_warn(master->dev,
+					 "Shared StreamID 0x%x not supported for multi-SID masters\n",
+					 sid);
+				ret = -ENODEV;
+				break;
+			}
+
+			if (list_empty(&stream->shared_masters))
+				list_add_tail(&stream->master->shared_masters_elm,
+					      &stream->shared_masters);
+			list_add_tail(&master->shared_masters_elm,
+				      &stream->shared_masters);
+			master->streams[n++] = stream;
+			continue;
 		}
 
 		stream = kzalloc_obj(*stream, GFP_KERNEL);
@@ -4362,6 +4376,7 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 		}
 		stream->id = sid;
 		stream->master = master;
+		INIT_LIST_HEAD(&stream->shared_masters);
 
 		rb_find_add(&stream->node, &smmu->streams,
 			    arm_smmu_streams_cmp_node);
@@ -4370,6 +4385,7 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 	master->num_streams = n;
 
 	if (ret) {
+		list_del_init(&master->shared_masters_elm);
 		arm_smmu_free_master_streams(master);
 		mutex_unlock(&smmu->streams_mutex);
 		kfree(master->streams);
@@ -4388,13 +4404,32 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 
 static void arm_smmu_remove_master(struct arm_smmu_master *master)
 {
+	int i;
 	struct arm_smmu_device *smmu = master->smmu;
 
 	if (!smmu || !master->streams)
 		return;
 
 	mutex_lock(&smmu->streams_mutex);
-	arm_smmu_free_master_streams(master);
+	for (i = 0; i < master->num_streams; i++) {
+		struct arm_smmu_stream *stream = master->streams[i];
+
+		if (!list_empty(&stream->shared_masters)) {
+			struct arm_smmu_master *next;
+
+			list_del_init(&master->shared_masters_elm);
+			next = list_first_entry(&stream->shared_masters,
+						struct arm_smmu_master,
+						shared_masters_elm);
+			if (stream->master == master)
+				stream->master = next;
+			if (list_is_singular(&stream->shared_masters))
+				list_del_init(&next->shared_masters_elm);
+			continue;
+		}
+		rb_erase(&stream->node, &smmu->streams);
+		kfree(stream);
+	}
 	mutex_unlock(&smmu->streams_mutex);
 
 	kfree(master->streams);
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 56ed6ad1dd523..95da4ad354829 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -1020,6 +1020,8 @@ struct arm_smmu_stream {
 	u32				id;
 	struct arm_smmu_master		*master;
 	struct rb_node			node;
+	bool				ste_installed;
+	struct list_head		shared_masters;
 };
 
 struct arm_smmu_vmaster {
@@ -1068,6 +1070,7 @@ struct arm_smmu_master {
 	bool				ste_ats_enabled : 1;
 	bool				stall_enabled;
 	bool				ats_always_on;
+	struct list_head		shared_masters_elm;
 	unsigned int			ssid_bits;
 	unsigned int			iopf_refcount;
 };

-- 
2.34.1