static int arm_smmu_cmdq_issue_cmdlist()

in arm/arm-smmu-v3/arm-smmu-v3.c [734:852]


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 owner;
	struct arm_smmu_cmdq *cmdq = arm_smmu_get_cmdq(smmu);
	struct arm_smmu_ll_queue llq, head;
	int ret = 0;

	llq.max_n_shift = cmdq->q.llq.max_n_shift;

	/* 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);
	head.prod &= ~CMDQ_PROD_OWNED_FLAG;
	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, &cmdq->q, 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();
	arm_smmu_cmdq_set_valid_map(cmdq, llq.prod, head.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;

		/*
		 * c. Wait for any gathered work to be written to the queue.
		 * Note that we read our own entries so that we have the control
		 * dependency required by (d).
		 */
		arm_smmu_cmdq_poll_valid_map(cmdq, llq.prod, prod);

		/*
		 * d. Advance the hardware prod pointer
		 * Control dependency ordering from the entries becoming valid.
		 */
		writel_relaxed(prod, cmdq->q.prod_reg);

		/*
		 * 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 cmdq 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;
}