mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Will Deacon <will@kernel.org>
To: Jacob Pan <jacob.pan@linux.microsoft.com>
Cc: linux-kernel@vger.kernel.org,
	"iommu@lists.linux.dev" <iommu@lists.linux.dev>,
	Joerg Roedel <joro@8bytes.org>,
	Mostafa Saleh <smostafa@google.com>,
	Jason Gunthorpe <jgg@nvidia.com>,
	Robin Murphy <robin.murphy@arm.com>,
	Nicolin Chen <nicolinc@nvidia.com>,
	Zhang Yu <zhangyu1@linux.microsoft.com>,
	Jean Philippe-Brucker <jean-philippe@linaro.org>,
	Alexander Grest <Alexander.Grest@microsoft.com>
Subject: Re: [PATCH v4 2/2] iommu/arm-smmu-v3: Improve CMDQ lock fairness and efficiency
Date: Tue, 25 Nov 2025 17:18:57 +0000	[thread overview]
Message-ID: <aSXlAT00HVCGBaNY@willie-the-truck> (raw)
In-Reply-To: <20251114171718.42215-3-jacob.pan@linux.microsoft.com>

On Fri, Nov 14, 2025 at 09:17:18AM -0800, Jacob Pan wrote:
> @@ -521,9 +527,14 @@ static bool arm_smmu_cmdq_shared_tryunlock(struct arm_smmu_cmdq *cmdq)
>  	__ret;								\
>  })
>  
> +/*
> + * Only clear the sign bit when releasing the exclusive lock this will
> + * allow any shared_lock() waiters to proceed without the possibility
> + * of entering the exclusive lock in a tight loop.
> + */
>  #define arm_smmu_cmdq_exclusive_unlock_irqrestore(cmdq, flags)		\
>  ({									\
> -	atomic_set_release(&cmdq->lock, 0);				\
> +	atomic_fetch_and_release(~INT_MIN, &cmdq->lock);		\

nit: you can use atomic_fetch_andnot_release(INT_MIN)

That aside, doesn't this introduce a new fairness issue in that a steady
stream of shared lockers will starve somebody trying to take the lock
in exclusive state?

Will

  reply	other threads:[~2025-11-25 17:19 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-14 17:17 [PATCH v4 0/2] SMMU v3 CMDQ fix and improvement Jacob Pan
2025-11-14 17:17 ` [PATCH v4 1/2] iommu/arm-smmu-v3: Fix CMDQ timeout warning Jacob Pan
2025-11-14 18:29   ` Nicolin Chen
2025-11-25 17:19   ` Will Deacon
2025-11-30 23:06     ` Jacob Pan
2025-12-01 19:57       ` Robin Murphy
2025-12-01 21:49         ` Jacob Pan
2025-12-01 17:42     ` Jacob Pan
2025-11-14 17:17 ` [PATCH v4 2/2] iommu/arm-smmu-v3: Improve CMDQ lock fairness and efficiency Jacob Pan
2025-11-25 17:18   ` Will Deacon [this message]
2025-11-30 22:52     ` Jacob Pan
2025-12-10  3:11       ` Will Deacon
2025-11-20 17:10 ` [PATCH v4 0/2] SMMU v3 CMDQ fix and improvement Jacob Pan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=aSXlAT00HVCGBaNY@willie-the-truck \
    --to=will@kernel.org \
    --cc=Alexander.Grest@microsoft.com \
    --cc=iommu@lists.linux.dev \
    --cc=jacob.pan@linux.microsoft.com \
    --cc=jean-philippe@linaro.org \
    --cc=jgg@nvidia.com \
    --cc=joro@8bytes.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nicolinc@nvidia.com \
    --cc=robin.murphy@arm.com \
    --cc=smostafa@google.com \
    --cc=zhangyu1@linux.microsoft.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®