[PATCH v12 5/8] iommu/arm-smmu-v3: Pre-allocate a per-master invalidation array

[Nicolin Chen <nicolinc@nvidia.com>]

When a master is attached from an old domain to a new domain, it needs to
build an invalidation array to delete and add the array entries from/onto
the invalidation arrays of those two domains, passed via the to_merge and
to_unref arguments into arm_smmu_invs_merge/unref() respectively.

Since the master->num_streams might differ across masters, a memory would
have to be allocated when building an to_merge/to_unref array which might
fail with -ENOMEM.

On the other hand, an attachment to arm_smmu_blocked_domain must not fail
so it's the best to avoid any memory allocation in that path.

Pre-allocate a fixed size invalidation array for every master. This array
will be used as a scratch to fill dynamically when building a to_merge or
to_unref invs array. Sort fwspec->ids in an ascending order to fit to the
arm_smmu_invs_merge() function.

Co-developed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  8 ++++
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 41 +++++++++++++++++++--
 2 files changed, 45 insertions(+), 4 deletions(-)

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 ed8820f12ba32..5e0e5055af1eb 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -928,6 +928,14 @@ struct arm_smmu_master {
 	struct arm_smmu_device		*smmu;
 	struct device			*dev;
 	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
+	 * possible build scenarios. It can be used by only one caller at a time
+	 * until the arm_smmu_invs_merge/unref() finishes. Must be locked by the
+	 * iommu_group mutex.
+	 */
+	struct arm_smmu_invs		*build_invs;
 	struct arm_smmu_vmaster		*vmaster; /* use smmu->streams_mutex */
 	/* Locked by the iommu core using the group mutex */
 	struct arm_smmu_ctx_desc_cfg	cd_table;
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 f6a423500ce1f..7d8377f6a6838 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3784,26 +3784,57 @@ static int arm_smmu_init_sid_strtab(struct arm_smmu_device *smmu, u32 sid)
 	return 0;
 }
 
+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;
+
+	return cmp_int(*l, *r);
+}
+
 static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 				  struct arm_smmu_master *master)
 {
 	int i;
 	int ret = 0;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev);
+	bool ats_supported = dev_is_pci(master->dev) &&
+			     pci_ats_supported(to_pci_dev(master->dev));
 
 	master->streams = kzalloc_objs(*master->streams, fwspec->num_ids);
 	if (!master->streams)
 		return -ENOMEM;
 	master->num_streams = fwspec->num_ids;
 
-	mutex_lock(&smmu->streams_mutex);
+	if (!ats_supported) {
+		/* Base case has 1 ASID entry or maximum 2 VMID entries */
+		master->build_invs = arm_smmu_invs_alloc(2);
+	} else {
+		/* ATS case adds num_ids of entries, on top of the base case */
+		master->build_invs = arm_smmu_invs_alloc(2 + fwspec->num_ids);
+	}
+	if (!master->build_invs) {
+		kfree(master->streams);
+		return -ENOMEM;
+	}
+
 	for (i = 0; i < fwspec->num_ids; i++) {
 		struct arm_smmu_stream *new_stream = &master->streams[i];
-		struct rb_node *existing;
-		u32 sid = fwspec->ids[i];
 
-		new_stream->id = sid;
+		new_stream->id = fwspec->ids[i];
 		new_stream->master = master;
+	}
+
+	/* Put the ids into order for sorted to_merge/to_unref arrays */
+	sort_nonatomic(master->streams, master->num_streams,
+		       sizeof(master->streams[0]), arm_smmu_stream_id_cmp,
+		       NULL);
+
+	mutex_lock(&smmu->streams_mutex);
+	for (i = 0; i < fwspec->num_ids; i++) {
+		struct arm_smmu_stream *new_stream = &master->streams[i];
+		struct rb_node *existing;
+		u32 sid = new_stream->id;
 
 		ret = arm_smmu_init_sid_strtab(smmu, sid);
 		if (ret)
@@ -3833,6 +3864,7 @@ static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
 		for (i--; i >= 0; i--)
 			rb_erase(&master->streams[i].node, &smmu->streams);
 		kfree(master->streams);
+		kfree(master->build_invs);
 	}
 	mutex_unlock(&smmu->streams_mutex);
 
@@ -3854,6 +3886,7 @@ static void arm_smmu_remove_master(struct arm_smmu_master *master)
 	mutex_unlock(&smmu->streams_mutex);
 
 	kfree(master->streams);
+	kfree(master->build_invs);
 }
 
 static struct iommu_device *arm_smmu_probe_device(struct device *dev)
-- 
2.43.0