linux-kernel - Re: [PATCH 0/4] iommu/arm-smmu-v3: Improve cmdq lock efficiency

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <bd302efa-20d8-e1b3-6a80-db65ab5ad752@huawei.com>
Date:   Thu, 16 Jul 2020 11:56:45 +0100
From:   John Garry <john.garry@...wei.com>
To:     Will Deacon <will@...nel.org>
CC:     <robin.murphy@....com>, <joro@...tes.org>, <trivial@...nel.org>,
        <linux-arm-kernel@...ts.infradead.org>,
        <iommu@...ts.linux-foundation.org>, <linux-kernel@...r.kernel.org>,
        <linuxarm@...wei.com>, <maz@...nel.org>
Subject: Re: [PATCH 0/4] iommu/arm-smmu-v3: Improve cmdq lock efficiency

On 16/07/2020 11:28, Will Deacon wrote:
> On Thu, Jul 16, 2020 at 11:22:33AM +0100, Will Deacon wrote:
>> On Thu, Jul 16, 2020 at 11:19:41AM +0100, Will Deacon wrote:
>>> On Tue, Jun 23, 2020 at 01:28:36AM +0800, John Garry wrote:
>>>> As mentioned in [0], the CPU may consume many cycles processing
>>>> arm_smmu_cmdq_issue_cmdlist(). One issue we find is the cmpxchg() loop to
>>>> get space on the queue takes approx 25% of the cycles for this function.
>>>>
>>>> This series removes that cmpxchg().
>>>
>>> How about something much simpler like the diff below? >>
>> Ah, scratch that, I don't drop the lock if we fail the cas with it held.
>> Let me hack it some more (I have no hardware so I can only build-test this).
> 
> Right, second attempt...

I can try it, but if performance if not as good, then please check mine 
further (patch 4/4 specifically) - performance is really good, IMHO.

Thanks,

> 
> Will
> 
> --->8
> 
> diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
> index f578677a5c41..e6bcddd6ef69 100644
> --- a/drivers/iommu/arm-smmu-v3.c
> +++ b/drivers/iommu/arm-smmu-v3.c
> @@ -560,6 +560,7 @@ struct arm_smmu_cmdq {
>   	atomic_long_t			*valid_map;
>   	atomic_t			owner_prod;
>   	atomic_t			lock;
> +	spinlock_t			slock;
>   };
>   
>   struct arm_smmu_cmdq_batch {
> @@ -1378,7 +1379,7 @@ static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
>   	u64 cmd_sync[CMDQ_ENT_DWORDS];
>   	u32 prod;
>   	unsigned long flags;
> -	bool owner;
> +	bool owner, locked = false;
>   	struct arm_smmu_cmdq *cmdq = &smmu->cmdq;
>   	struct arm_smmu_ll_queue llq = {
>   		.max_n_shift = cmdq->q.llq.max_n_shift,
> @@ -1387,27 +1388,38 @@ static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
>   
>   	/* 1. Allocate some space in the queue */
>   	local_irq_save(flags);
> -	llq.val = READ_ONCE(cmdq->q.llq.val);
>   	do {
>   		u64 old;
> +		llq.val = READ_ONCE(cmdq->q.llq.val);
>   
> -		while (!queue_has_space(&llq, n + sync)) {
> +		if (queue_has_space(&llq, n + sync))
> +			goto try_cas;
> +
> +		if (locked)
> +			spin_unlock(&cmdq->slock);
> +
> +		do {
>   			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);
> -		}
> +		} while (!queue_has_space(&llq, n + sync));
>   
> +try_cas:
>   		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)
> +		if (old != llq.val)
>   			break;
>   
> -		llq.val = old;
> +		if (!locked) {
> +			spin_lock(&cmdq->slock);
> +			locked = true;
> +		}
>   	} while (1);
> +
>   	owner = !(llq.prod & CMDQ_PROD_OWNED_FLAG);
>   	head.prod &= ~CMDQ_PROD_OWNED_FLAG;
>   	llq.prod &= ~CMDQ_PROD_OWNED_FLAG;
> @@ -3192,6 +3204,7 @@ static int arm_smmu_cmdq_init(struct arm_smmu_device *smmu)
>   
>   	atomic_set(&cmdq->owner_prod, 0);
>   	atomic_set(&cmdq->lock, 0);
> +	spin_lock_init(&cmdq->slock);
>   
>   	bitmap = (atomic_long_t *)bitmap_zalloc(nents, GFP_KERNEL);
>   	if (!bitmap) {
> .
>