[PATCH v3] iommu/arm-smmu-v3: permit users to disable MSI polling

[Barry Song]

Polling by MSI isn't necessarily faster than polling by SEV. Tests on
hi1620 show hns3 100G NIC network throughput can improve from 25G to
27G if we disable MSI polling while running 16 netperf threads sending
UDP packets in size 32KB.
This patch provides a command line option so that users can decide to
use MSI polling or not based on their tests.

Signed-off-by: Barry Song <song.bao.hua at hisilicon.com>
---
 -v3:
  * rebase on top of linux-next as arm-smmu-v3.c has moved;
  * provide a command line option

 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 18 ++++++++++++++----
 1 file changed, 14 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..89d3cb391fef 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -418,6 +418,11 @@ module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
 MODULE_PARM_DESC(disable_bypass,
 	"Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU.");
 
+static bool disable_msipolling;
+module_param_named(disable_msipolling, disable_msipolling, bool, S_IRUGO);
+MODULE_PARM_DESC(disable_msipolling,
+	"Disable MSI-based polling for CMD_SYNC completion.");
+
 enum pri_resp {
 	PRI_RESP_DENY = 0,
 	PRI_RESP_FAIL = 1,
@@ -980,6 +985,13 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 	return 0;
 }
 
+static bool arm_smmu_use_msipolling(struct arm_smmu_device *smmu)
+{
+	return !disable_msipolling &&
+	       smmu->features & ARM_SMMU_FEAT_COHERENCY &&
+	       smmu->features & ARM_SMMU_FEAT_MSI;
+}
+
 static void arm_smmu_cmdq_build_sync_cmd(u64 *cmd, struct arm_smmu_device *smmu,
 					 u32 prod)
 {
@@ -992,8 +1004,7 @@ static void arm_smmu_cmdq_build_sync_cmd(u64 *cmd, struct arm_smmu_device *smmu,
 	 * Beware that Hi16xx adds an extra 32 bits of goodness to its MSI
 	 * payload, so the write will zero the entire command on that platform.
 	 */
-	if (smmu->features & ARM_SMMU_FEAT_MSI &&
-	    smmu->features & ARM_SMMU_FEAT_COHERENCY) {
+	if (arm_smmu_use_msipolling(smmu)) {
 		ent.sync.msiaddr = q->base_dma + Q_IDX(&q->llq, prod) *
 				   q->ent_dwords * 8;
 	}
@@ -1332,8 +1343,7 @@ static int __arm_smmu_cmdq_poll_until_consumed(struct arm_smmu_device *smmu,
 static int arm_smmu_cmdq_poll_until_sync(struct arm_smmu_device *smmu,
 					 struct arm_smmu_ll_queue *llq)
 {
-	if (smmu->features & ARM_SMMU_FEAT_MSI &&
-	    smmu->features & ARM_SMMU_FEAT_COHERENCY)
+	if (arm_smmu_use_msipolling(smmu))
 		return __arm_smmu_cmdq_poll_until_msi(smmu, llq);
 
 	return __arm_smmu_cmdq_poll_until_consumed(smmu, llq);
-- 
2.27.0