linux-hardening - Re: [RFC v2 1/2] dmapool: Move pool metadata into non-DMA memory

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: <Zz2tzVqql2RMSFN4@infradead.org>
Date: Wed, 20 Nov 2024 01:37:17 -0800
From: Christoph Hellwig <hch@...radead.org>
To: Brian Johannesmeyer <bjohannesmeyer@...il.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
	linux-kernel@...r.kernel.org, linux-hardening@...r.kernel.org,
	Raphael Isemann <teemperor@...il.com>,
	Cristiano Giuffrida <giuffrida@...vu.nl>,
	Herbert Bos <h.j.bos@...nl>, Greg KH <gregkh@...uxfoundation.org>,
	Keith Busch <kbusch@...nel.org>
Subject: Re: [RFC v2 1/2] dmapool: Move pool metadata into non-DMA memory

On Tue, Nov 19, 2024 at 09:55:28PM +0100, Brian Johannesmeyer wrote:

> +	page->blocks_per_page = pool->allocation / pool->size;
> +	page->blocks = kmalloc_array(page->blocks_per_page,
> +				     sizeof(struct dma_block), GFP_KERNEL);

Given that you now need an array of the blocks anyway, it might make
sense to switch from a linked list to a bitmap for tracking free state,
which would be a lot more efficient as you only need a bit per block
as tracking overhead instead of a two pointers and a dma_addr_t.

e.g. do a find_first_zero_bit() to find the ﬀree slot, then calculate
the dma_addr and virt address by simple offseting into the dma_page
ones with bitnr * pool->size.