[PATCH v2 1/2] iommu/arm-smmu-v3: Calculate max commands per batch

[John Garry]

Calculate the batch size limit such that all CPUs in the system cannot
issue so many commands as to fill the command queue.

Signed-off-by: John Garry <john.garry@xxxxxxxxxx>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 46 +++++++++++++++++++--
 1 file changed, 42 insertions(+), 4 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 7196207be7ea..a705fa3e18ea 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -532,6 +532,7 @@ struct arm_smmu_ll_queue {
 		u8			__pad[SMP_CACHE_BYTES];
 	} ____cacheline_aligned_in_smp;
 	u32				max_n_shift;
+	u32				max_cmd_per_batch;
 };
 
 struct arm_smmu_queue {
@@ -1515,7 +1516,10 @@ static void arm_smmu_cmdq_batch_add(struct arm_smmu_device *smmu,
 				    struct arm_smmu_cmdq_batch *cmds,
 				    struct arm_smmu_cmdq_ent *cmd)
 {
-	if (cmds->num == CMDQ_BATCH_ENTRIES) {
+	struct arm_smmu_cmdq *q = &smmu->cmdq;
+	struct arm_smmu_ll_queue *llq = &q->q.llq;
+
+	if (cmds->num == llq->max_cmd_per_batch) {
 		arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, false);
 		cmds->num = 0;
 	}
@@ -3177,6 +3181,41 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
 	return 0;
 }
 
+static int arm_smmu_init_cmd_queue(struct arm_smmu_device *smmu,
+				   struct arm_smmu_queue *q,
+				   unsigned long prod_off,
+				   unsigned long cons_off,
+				   size_t dwords)
+{
+	u32 cpus = num_possible_cpus(), entries_for_prod;
+	int ret;
+
+	ret = arm_smmu_init_one_queue(smmu, q, prod_off, cons_off, dwords,
+				      "cmdq");
+	if (ret)
+		return ret;
+
+	entries_for_prod = 1 << q->llq.max_n_shift;
+
+	/*
+	 * We need at least 2 commands in a batch (1 x CMD_SYNC and 1 x
+	 * whatever else).
+	 */
+	if (entries_for_prod < 2 * cpus) {
+		dev_err(smmu->dev, "command queue size too small, suggest reduce #CPUs\n");
+		return -ENXIO;
+	}
+
+	/*
+	 * When finding max_cmd_per_batch, deduct 1 entry per batch to take
+	 * account of a CMD_SYNC being issued also.
+	 */
+	q->llq.max_cmd_per_batch = min((entries_for_prod / cpus) - 1,
+				       (u32)CMDQ_BATCH_ENTRIES);
+
+	return 0;
+}
+
 static void arm_smmu_cmdq_free_bitmap(void *data)
 {
 	unsigned long *bitmap = data;
@@ -3210,9 +3249,8 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
 	int ret;
 
 	/* cmdq */
-	ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
-				      ARM_SMMU_CMDQ_CONS, CMDQ_ENT_DWORDS,
-				      "cmdq");
+	ret = arm_smmu_init_cmd_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
+				      ARM_SMMU_CMDQ_CONS, CMDQ_ENT_DWORDS);
 	if (ret)
 		return ret;
 
-- 
2.26.2