Re: [PATCH 16/19] iommu/amd: Use roundup_pow_two() instead of get_order()

From: Robin Murphy <robin.murphy@arm.com>
To: Jason Gunthorpe <jgg@nvidia.com>,
	Alim Akhtar <alim.akhtar@samsung.com>,
	Alyssa Rosenzweig <alyssa@rosenzweig.io>,
	Albert Ou <aou@eecs.berkeley.edu>,
	asahi@lists.linux.dev, Lu Baolu <baolu.lu@linux.intel.com>,
	David Woodhouse <dwmw2@infradead.org>,
	Heiko Stuebner <heiko@sntech.de>,
	iommu@lists.linux.dev, Jernej Skrabec <jernej.skrabec@gmail.com>,
	Jonathan Hunter <jonathanh@nvidia.com>,
	Joerg Roedel <joro@8bytes.org>,
	Krzysztof Kozlowski <krzk@kernel.org>,
	linux-arm-kernel@lists.infradead.org,
	linux-riscv@lists.infradead.org,
	linux-rockchip@lists.infradead.org,
	linux-samsung-soc@vger.kernel.org, linux-sunxi@lists.linux.dev,
	linux-tegra@vger.kernel.org,
	Marek Szyprowski <m.szyprowski@samsung.com>,
	Hector Martin <marcan@marcan.st>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Samuel Holland <samuel@sholland.org>,
	Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>,
	Sven Peter <sven@svenpeter.dev>,
	Thierry Reding <thierry.reding@gmail.com>,
	Tomasz Jeznach <tjeznach@rivosinc.com>,
	Krishna Reddy <vdumpa@nvidia.com>, Chen-Yu Tsai <wens@csie.org>,
	Will Deacon <will@kernel.org>
Cc: Bagas Sanjaya <bagasdotme@gmail.com>,
	Joerg Roedel <jroedel@suse.de>,
	Pasha Tatashin <pasha.tatashin@soleen.com>,
	patches@lists.linux.dev, David Rientjes <rientjes@google.com>,
	Matthew Wilcox <willy@infradead.org>
Subject: Re: [PATCH 16/19] iommu/amd: Use roundup_pow_two() instead of get_order()
Date: Wed, 5 Feb 2025 16:11:00 +0000	[thread overview]
Message-ID: <f8d73cd3-f85c-49c3-8b37-4eaad0255860@arm.com> (raw)
In-Reply-To: <16-v1-416f64558c7c+2a5-iommu_pages_jgg@nvidia.com>

On 2025-02-04 6:34 pm, Jason Gunthorpe wrote:
>    1 << (get_order(x) + PAGE_SHIFT) ==  roundup_pow_two()

...unless x < 2048, which does seem possible here if last_bdf is 
sufficiently small. Not too significant in the cases where the result is 
only rounded back up again for an allocation or remap anyway, but I do 
wonder about the use of dev_table_size in iommu_set_device_table(), and 
whether this change might break it, or whether it's already wrong for 
that case and this might actually fix it...

Thanks,
Robin.

> Use the shorter version.
> 
> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
> ---
>   drivers/iommu/amd/init.c | 5 +----
>   1 file changed, 1 insertion(+), 4 deletions(-)
> 
> diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
> index f1c5041647173c..7d77929bc63af3 100644
> --- a/drivers/iommu/amd/init.c
> +++ b/drivers/iommu/amd/init.c
> @@ -247,10 +247,7 @@ static void init_translation_status(struct amd_iommu *iommu)
>   
>   static inline unsigned long tbl_size(int entry_size, int last_bdf)
>   {
> -	unsigned shift = PAGE_SHIFT +
> -			 get_order((last_bdf + 1) * entry_size);
> -
> -	return 1UL << shift;
> +	return roundup_pow_of_two((last_bdf + 1) * entry_size);
>   }
>   
>   int amd_iommu_get_num_iommus(void)

_______________________________________________
Linux-rockchip mailing list
Linux-rockchip@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-rockchip