[PATCH RFC v5 2/6] iommu/arm-smmu-v3: Allocate streams individually

["Peng Fan (OSS)" <peng.fan@oss.nxp.com>]

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

Change master->streams from an embedded array of struct arm_smmu_stream
to an array of pointers, with each stream individually allocated.

Prepare for shared-SID support where multiple masters will point to the
same stream object. With embedded structs, sharing requires duplicating
stream state and manually keeping fields like ste_installed in sync.
With individually allocated streams, a sharing master can simply point to
the existing stream.

The sort comparator is updated to dereference the pointer indirection.

No functional change.

Suggested-by: Nicolin Chen <nicolinc@nvidia.com>
Link: https://lore.kernel.org/linux-iommu/arG6hmng3NddGEHm@nvidia.com/
Assisted-by: LLM
Signed-off-by: Peng Fan <peng.fan@nxp.com>
---
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c    |  2 +-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c        | 52 ++++++++++++++--------
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h        |  2 +-
 drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c     |  2 +-
 4 files changed, 37 insertions(+), 21 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 ab1078a97d801..0934a6bbd3e08 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
@@ -294,7 +294,7 @@ static int arm_vsmmu_vsid_to_sid(struct arm_vsmmu *vsmmu, u32 vsid, u32 *sid)
 
 	/* At this moment, iommufd only supports PCI device that has one SID */
 	if (sid)
-		*sid = master->streams[0].id;
+		*sid = master->streams[0]->id;
 unlock:
 	xa_unlock(&vsmmu->core.vdevs);
 	return ret;
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 dba6c2942af8f..9d34eac196a65 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -972,7 +972,7 @@ static void arm_smmu_page_response(struct device *dev, struct iopf_fault *unused
 	}
 
 	arm_smmu_cmdq_issue_cmd(master->smmu,
-				arm_smmu_make_cmd_resume(master->streams[0].id,
+				arm_smmu_make_cmd_resume(master->streams[0]->id,
 							 resp->grpid,
 							 resume_resp));
 	/*
@@ -1504,7 +1504,7 @@ static void arm_smmu_sync_cd(struct arm_smmu_master *master,
 	for (i = 0; i < master->num_streams; i++)
 		arm_smmu_cmdq_batch_add_cmd(
 			smmu, &cmds,
-			arm_smmu_make_cmd_cfgi_cd(master->streams[i].id, ssid,
+			arm_smmu_make_cmd_cfgi_cd(master->streams[i]->id, ssid,
 						  leaf));
 
 	arm_smmu_cmdq_batch_submit(smmu, &cmds);
@@ -2431,7 +2431,7 @@ static int arm_smmu_atc_inv_master(struct arm_smmu_master *master,
 	for (i = 0; i < master->num_streams; i++)
 		arm_smmu_cmdq_batch_add_cmd(
 			master->smmu, &cmds,
-			arm_smmu_make_cmd_atc_inv_all(master->streams[i].id,
+			arm_smmu_make_cmd_atc_inv_all(master->streams[i]->id,
 						      ssid));
 
 	return arm_smmu_cmdq_batch_submit(master->smmu, &cmds);
@@ -2978,13 +2978,13 @@ void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master,
 		STRTAB_STE_1_EATS_TRANS;
 
 	for (i = 0; i < master->num_streams; ++i) {
-		u32 sid = master->streams[i].id;
+		u32 sid = master->streams[i]->id;
 		struct arm_smmu_ste *step =
 			arm_smmu_get_step_for_sid(smmu, sid);
 
 		/* Bridged PCI devices may end up with duplicated IDs */
 		for (j = 0; j < i; j++)
-			if (master->streams[j].id == sid)
+			if (master->streams[j]->id == sid)
 				break;
 		if (j < i)
 			continue;
@@ -3276,7 +3276,7 @@ arm_smmu_master_build_invs(struct arm_smmu_master *master, bool ats_enabled,
 		 */
 		if (!arm_smmu_master_build_inv(
 			    master, nesting ? INV_TYPE_ATS_FULL : INV_TYPE_ATS,
-			    master->streams[i].id, ssid, 0))
+			    master->streams[i]->id, ssid, 0))
 			return NULL;
 	}
 
@@ -4078,10 +4078,10 @@ static int arm_smmu_init_sid_strtab(struct arm_smmu_device *smmu, u32 sid)
 
 static int arm_smmu_stream_id_cmp(const void *_l, const void *_r)
 {
-	const typeof_member(struct arm_smmu_stream, id) *l = _l;
-	const typeof_member(struct arm_smmu_stream, id) *r = _r;
+	const struct arm_smmu_stream * const *l = _l;
+	const struct arm_smmu_stream * const *r = _r;
 
-	return cmp_int(*l, *r);
+	return cmp_int((*l)->id, (*r)->id);
 }
 
 static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
@@ -4111,10 +4111,16 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 	}
 
 	for (i = 0; i < fwspec->num_ids; i++) {
-		struct arm_smmu_stream *new_stream = &master->streams[i];
+		struct arm_smmu_stream *new_stream;
 
+		new_stream = kzalloc_obj(*new_stream, GFP_KERNEL);
+		if (!new_stream) {
+			ret = -ENOMEM;
+			goto out_free_streams;
+		}
 		new_stream->id = fwspec->ids[i];
 		new_stream->master = master;
+		master->streams[i] = new_stream;
 	}
 
 	/* Put the ids into order for sorted to_merge/to_unref arrays */
@@ -4127,11 +4133,11 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 	 * which sort_nonatomic() invalidates by relocating the entries.
 	 */
 	for (i = 0; i < fwspec->num_ids; i++)
-		RB_CLEAR_NODE(&master->streams[i].node);
+		RB_CLEAR_NODE(&master->streams[i]->node);
 
 	mutex_lock(&smmu->streams_mutex);
 	for (i = 0; i < fwspec->num_ids; i++) {
-		struct arm_smmu_stream *new_stream = &master->streams[i];
+		struct arm_smmu_stream *new_stream = master->streams[i];
 		struct rb_node *existing;
 		u32 sid = new_stream->id;
 
@@ -4161,14 +4167,21 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 
 	if (ret) {
 		for (i--; i >= 0; i--)
-			if (!RB_EMPTY_NODE(&master->streams[i].node))
-				rb_erase(&master->streams[i].node,
+			if (!RB_EMPTY_NODE(&master->streams[i]->node))
+				rb_erase(&master->streams[i]->node,
 					 &smmu->streams);
-		kfree(master->streams);
-		kfree(master->build_invs);
+		mutex_unlock(&smmu->streams_mutex);
+		goto out_free_streams;
 	}
 	mutex_unlock(&smmu->streams_mutex);
 
+	return 0;
+
+out_free_streams:
+	for (i = 0; i < master->num_streams; i++)
+		kfree(master->streams[i]);
+	kfree(master->streams);
+	kfree(master->build_invs);
 	return ret;
 }
 
@@ -4183,10 +4196,13 @@ static void arm_smmu_remove_master(struct arm_smmu_master *master)
 
 	mutex_lock(&smmu->streams_mutex);
 	for (i = 0; i < fwspec->num_ids; i++)
-		if (!RB_EMPTY_NODE(&master->streams[i].node))
-			rb_erase(&master->streams[i].node, &smmu->streams);
+		if (!RB_EMPTY_NODE(&master->streams[i]->node))
+			rb_erase(&master->streams[i]->node, &smmu->streams);
 	mutex_unlock(&smmu->streams_mutex);
 
+	for (i = 0; i < master->num_streams; i++)
+		kfree(master->streams[i]);
+
 	kfree(master->streams);
 	kfree(master->build_invs);
 }
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 dd2fee2f560e6..ba430078cbce9 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -1000,7 +1000,7 @@ struct arm_smmu_event {
 struct arm_smmu_master {
 	struct arm_smmu_device		*smmu;
 	struct device			*dev;
-	struct arm_smmu_stream		*streams;
+	struct arm_smmu_stream		**streams;
 	/*
 	 * Scratch memory for a to_merge or to_unref array to build a per-domain
 	 * invalidation array. It'll be pre-allocated with enough enries for all
diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
index 6644075c1431e..bc62a3d5a63f9 100644
--- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
+++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
@@ -1257,7 +1257,7 @@ static int tegra241_vintf_init_vsid(struct iommufd_vdevice *vdev)
 	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
 	struct tegra241_vintf *vintf = viommu_to_vintf(vdev->viommu);
 	struct tegra241_vintf_sid *vsid = vdev_to_vsid(vdev);
-	struct arm_smmu_stream *stream = &master->streams[0];
+	struct arm_smmu_stream *stream = master->streams[0];
 	u64 virt_sid = vdev->virt_id;
 	int sidx;
 

-- 
2.34.1