Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <1632477717-5254-1-git-send-email-john.garry@huawei.com> <1632477717-5254-2-git-send-email-john.garry@huawei.com>
In-Reply-To: <1632477717-5254-2-git-send-email-john.garry@huawei.com>
From:   Jason Wang <jasowang@redhat.com>
Date:   Mon, 11 Oct 2021 10:06:48 +0800
Message-ID: <CACGkMEt8FcoJ4zMXFZzmrFjm=ynWfr5yLfvSHCckawpa3FvhkA@mail.gmail.com>
Subject: Re: [PATCH 1/5] iova: Move fast alloc size roundup into alloc_iova_fast()
To:     John Garry <john.garry@huawei.com>
Cc:     Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
        mst <mst@redhat.com>, Robin Murphy <robin.murphy@arm.com>,
        Yongji Xie <xieyongji@bytedance.com>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        iommu@lists.linux-foundation.org,
        virtualization <virtualization@lists.linux-foundation.org>,
        linuxarm@huawei.com, thunder.leizhen@huawei.com,
        Lu Baolu <baolu.lu@linux.intel.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Fri, Sep 24, 2021 at 6:07 PM John Garry <john.garry@huawei.com> wrote:
>
> It really is a property of the IOVA rcache code that we need to alloc a
> power-of-2 size, so relocate the functionality to resize into
> alloc_iova_fast(), rather than the callsites.
>
> Signed-off-by: John Garry <john.garry@huawei.com>

Acked-by: Jason Wang <jasowang@redhat.com>

> ---
>  drivers/iommu/dma-iommu.c            | 8 --------
>  drivers/iommu/iova.c                 | 9 +++++++++
>  drivers/vdpa/vdpa_user/iova_domain.c | 8 --------
>  3 files changed, 9 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> index 896bea04c347..a99b3445fef8 100644
> --- a/drivers/iommu/dma-iommu.c
> +++ b/drivers/iommu/dma-iommu.c
> @@ -444,14 +444,6 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
>
>         shift = iova_shift(iovad);
>         iova_len = size >> shift;
> -       /*
> -        * Freeing non-power-of-two-sized allocations back into the IOVA caches
> -        * will come back to bite us badly, so we have to waste a bit of space
> -        * rounding up anything cacheable to make sure that can't happen. The
> -        * order of the unadjusted size will still match upon freeing.
> -        */
> -       if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
> -               iova_len = roundup_pow_of_two(iova_len);
>
>         dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit);
>
> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
> index 9e8bc802ac05..ff567cbc42f7 100644
> --- a/drivers/iommu/iova.c
> +++ b/drivers/iommu/iova.c
> @@ -497,6 +497,15 @@ alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
>         unsigned long iova_pfn;
>         struct iova *new_iova;
>
> +       /*
> +        * Freeing non-power-of-two-sized allocations back into the IOVA caches
> +        * will come back to bite us badly, so we have to waste a bit of space
> +        * rounding up anything cacheable to make sure that can't happen. The
> +        * order of the unadjusted size will still match upon freeing.
> +        */
> +       if (size < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
> +               size = roundup_pow_of_two(size);
> +
>         iova_pfn = iova_rcache_get(iovad, size, limit_pfn + 1);
>         if (iova_pfn)
>                 return iova_pfn;
> diff --git a/drivers/vdpa/vdpa_user/iova_domain.c b/drivers/vdpa/vdpa_user/iova_domain.c
> index 1daae2608860..2b1143f11d8f 100644
> --- a/drivers/vdpa/vdpa_user/iova_domain.c
> +++ b/drivers/vdpa/vdpa_user/iova_domain.c
> @@ -292,14 +292,6 @@ vduse_domain_alloc_iova(struct iova_domain *iovad,
>         unsigned long iova_len = iova_align(iovad, size) >> shift;
>         unsigned long iova_pfn;
>
> -       /*
> -        * Freeing non-power-of-two-sized allocations back into the IOVA caches
> -        * will come back to bite us badly, so we have to waste a bit of space
> -        * rounding up anything cacheable to make sure that can't happen. The
> -        * order of the unadjusted size will still match upon freeing.
> -        */
> -       if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
> -               iova_len = roundup_pow_of_two(iova_len);
>         iova_pfn = alloc_iova_fast(iovad, iova_len, limit >> shift, true);
>
>         return iova_pfn << shift;
> --
> 2.26.2
>