iommu/arm-smmu-v3: Stop pre-zeroing batch commands

Pre-zeroing the batched commands structure is inefficient, as individual
commands are zeroed later in arm_smmu_cmdq_build_cmd(). The size is quite
large and commonly most commands won't even be used:

	struct arm_smmu_cmdq_batch cmds = {};
345c:	52800001 	mov	w1, #0x0                   	// #0
3460:	d2808102 	mov	x2, #0x408                 	// #1032
3464:	910143a0 	add	x0, x29, #0x50
3468:	94000000 	bl	0 <memset>

Stop pre-zeroing the complete structure and only zero the num member.

Signed-off-by: John Garry <john.garry@huawei.com>
Link: https://lore.kernel.org/r/1628696966-88386-1-git-send-email-john.garry@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>

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 283bfad5f28fab380bac067927efae31752920dc..3216e746c28a4fe42e6a765093451948923bb872 100644 (file)
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -955,7 +955,7 @@ static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain,
        size_t i;
        unsigned long flags;
        struct arm_smmu_master *master;
-       struct arm_smmu_cmdq_batch cmds = {};
+       struct arm_smmu_cmdq_batch cmds;
        struct arm_smmu_device *smmu = smmu_domain->smmu;
        struct arm_smmu_cmdq_ent cmd = {
                .opcode = CMDQ_OP_CFGI_CD,
@@ -965,6 +965,8 @@ static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain,
                },
        };
 
+       cmds.num = 0;
+
        spin_lock_irqsave(&smmu_domain->devices_lock, flags);
        list_for_each_entry(master, &smmu_domain->devices, domain_head) {
                for (i = 0; i < master->num_streams; i++) {
@@ -1781,7 +1783,7 @@ int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, int ssid,
        unsigned long flags;
        struct arm_smmu_cmdq_ent cmd;
        struct arm_smmu_master *master;
-       struct arm_smmu_cmdq_batch cmds = {};
+       struct arm_smmu_cmdq_batch cmds;
 
        if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_ATS))
                return 0;
@@ -1805,6 +1807,8 @@ int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, int ssid,
 
        arm_smmu_atc_inv_to_cmd(ssid, iova, size, &cmd);
 
+       cmds.num = 0;
+
        spin_lock_irqsave(&smmu_domain->devices_lock, flags);
        list_for_each_entry(master, &smmu_domain->devices, domain_head) {
                if (!master->ats_enabled)
@@ -1852,7 +1856,7 @@ static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd,
        struct arm_smmu_device *smmu = smmu_domain->smmu;
        unsigned long end = iova + size, num_pages = 0, tg = 0;
        size_t inv_range = granule;
-       struct arm_smmu_cmdq_batch cmds = {};
+       struct arm_smmu_cmdq_batch cmds;
 
        if (!size)
                return;
@@ -1870,6 +1874,8 @@ static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd,
                num_pages = size >> tg;
        }
 
+       cmds.num = 0;
+
        while (iova < end) {
                if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) {
                        /*