Re: [RFC PATCH v2 18/19] iommu/arm-smmu-v3: Reduce contention during command-queue insertion

[John Garry <john.garry@huawei.com>]

> +static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
> +				       u64 *cmds, int n, bool sync)
> +{
> +	u64 cmd_sync[CMDQ_ENT_DWORDS];
> +	u32 prod;
>  	unsigned long flags;
> -	bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
> -	struct arm_smmu_cmdq_ent ent = { .opcode = CMDQ_OP_CMD_SYNC };
> -	int ret;
> +	bool owner;
> +	struct arm_smmu_cmdq *cmdq = &smmu->cmdq;
> +	struct arm_smmu_ll_queue llq = {
> +		.max_n_shift = cmdq->q.llq.max_n_shift,
> +	}, head = llq;
> +	int ret = 0;
>
> -	arm_smmu_cmdq_build_cmd(cmd, &ent);
> +	/* 1. Allocate some space in the queue */
> +	local_irq_save(flags);
> +	llq.val = READ_ONCE(cmdq->q.llq.val);
> +	do {
> +		u64 old;
> +
> +		while (!queue_has_space(&llq, n + sync)) {
> +			local_irq_restore(flags);
> +			if (arm_smmu_cmdq_poll_until_not_full(smmu, &llq))
> +				dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
> +			local_irq_save(flags);
> +		}
> +
> +		head.cons = llq.cons;
> +		head.prod = queue_inc_prod_n(&llq, n + sync) |
> +					     CMDQ_PROD_OWNED_FLAG;
> +
> +		old = cmpxchg_relaxed(&cmdq->q.llq.val, llq.val, head.val);
> +		if (old == llq.val)
> +			break;
> +
> +		llq.val = old;
> +	} while (1);
> +	owner = !(llq.prod & CMDQ_PROD_OWNED_FLAG);
> +
> +	/*
> +	 * 2. Write our commands into the queue
> +	 * Dependency ordering from the cmpxchg() loop above.
> +	 */
> +	arm_smmu_cmdq_write_entries(cmdq, cmds, llq.prod, n);
> +	if (sync) {
> +		prod = queue_inc_prod_n(&llq, n);
> +		arm_smmu_cmdq_build_sync_cmd(cmd_sync, smmu, prod);
> +		queue_write(Q_ENT(&cmdq->q, prod), cmd_sync, CMDQ_ENT_DWORDS);
> +
> +		/*
> +		 * In order to determine completion of our CMD_SYNC, we must
> +		 * ensure that the queue can't wrap twice without us noticing.
> +		 * We achieve that by taking the cmdq lock as shared before
> +		 * marking our slot as valid.
> +		 */
> +		arm_smmu_cmdq_shared_lock(cmdq);
> +	}
> +
> +	/* 3. Mark our slots as valid, ensuring commands are visible first */
> +	dma_wmb();
> +	prod = queue_inc_prod_n(&llq, n + sync);
> +	arm_smmu_cmdq_set_valid_map(cmdq, llq.prod, prod);
> +
> +	/* 4. If we are the owner, take control of the SMMU hardware */
> +	if (owner) {
> +		/* a. Wait for previous owner to finish */
> +		atomic_cond_read_relaxed(&cmdq->owner_prod, VAL == llq.prod);
> +
> +		/* b. Stop gathering work by clearing the owned flag */
> +		prod = atomic_fetch_andnot_relaxed(CMDQ_PROD_OWNED_FLAG,
> +						   &cmdq->q.llq.atomic.prod);
> +		prod &= ~CMDQ_PROD_OWNED_FLAG;
> +		head.prod &= ~CMDQ_PROD_OWNED_FLAG;
> +


Hi Will,

Could it be a minor optimisation to advance the HW producer pointer at 
this stage for the owner only? We know that its entries are written, and 
it should be first in the new batch of commands (right?), so we could 
advance the pointer to at least get the HW started.

Cheers,

> +		/* c. Wait for any gathered work to be written to the queue */
> +		arm_smmu_cmdq_poll_valid_map(cmdq, head.prod, prod);
> +
> +		/*
> +		 * d. Advance the hardware prod pointer
> +		 * Control dependency ordering from the entries becoming valid.
> +		 */
> +		writel_relaxed(prod, cmdq->q.prod_reg);
>
> -	spin_lock_irqsave(&smmu->cmdq.lock, flags);
> -	arm_smmu_cmdq_insert_cmd(smmu, cmd);
> -	ret = queue_poll_cons(&smmu->cmdq.q, true, wfe);
> -	spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
> +		/*
> +		 * e. Tell the next owner we're done
> +		 * Make sure we've updated the hardware first, so that we don't
> +		 * race to update prod and potentially move it backwards.
> +		 */
> +		atomic_set_release(&cmdq->owner_prod, prod);
> +	}
>
> +	/* 5. If we are inserting a CMD_SYNC, we must wait for it to complete */
> +	if (sync) {
> +		llq.prod = queue_inc_prod_n(&llq, n);
> +		ret = arm_smmu_cmdq_poll_until_sync(smmu, &llq);
> +		if (ret) {
> +			dev_err_ratelimited(smmu->dev,
> +					    "CMD_SYNC timeout at 0x%08x [hwprod 0x%08x, hwcons 0x%08x]\n",
> +					    llq.prod,
> +					    readl_relaxed(cmdq->q.prod_reg),
> +					    readl_relaxed(cmdq->q.cons_reg));
> +		}
> +
> +		/*
> +		 * Try to unlock the cmq lock. This will fail if we're the last
> +		 * reader, in which case we can safely update cmdq->q.llq.cons
> +		 */
> +		if (!arm_smmu_cmdq_shared_tryunlock(cmdq)) {
> +			WRITE_ONCE(cmdq->q.llq.cons, llq.cons);
> +			arm_smmu_cmdq_shared_unlock(cmdq);
> +		}
> +	}
> +
> +	local_irq_restore(flags);
>  	return ret;
>  }
>

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu