From mboxrd@z Thu Jan 1 00:00:00 1970 From: Conor Dooley Subject: Re: [PATCH 09/21] riscv: dma-mapping: skip invalidation before bidirectional DMA Date: Wed, 29 Mar 2023 21:16:10 +0100 Message-ID: <764e8d2f-ed98-49dc-8fdb-112d59359148@spud> References: <20230327121317.4081816-1-arnd@kernel.org> <20230327121317.4081816-10-arnd@kernel.org> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="2LJh6dsRB07q9YeN" Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1680120980; bh=GQ/BnFe9Q8YTrp9m/Oja+3F+vgOfqDylgmr9jLCscRs=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=P5U564E993rrDoh13ZYMd/KR6rZkNdIdAbkwy4AMMyuaZ2UnsINcIgdKLJGQbZT1R zUAUZnpQCzF0TlpEQXZmdxZiDMl23kcqvk8c8s2jxRsSMekf7FDxCi9gR1oX2Da8hi aag+2sE6WG2TyEHXWa4HzYKbVaDqQKSeZs+SUyrFuRdRhxxhHTm9szdrtMzu032YBF pnLWBxLnUyF1yY234OeM4zx5JvWcQ8+nbW2h2BxGSx1xSG/83/MuR/yVSH7mdi1xg2 0jWbdD9E6OkE4eGUQzkyJv6rP5bdfMAHDI8/GyVgtoddbv/rL55kO33CXzMD08MgAw CkixnBQ6Xb9Yw== Content-Disposition: inline In-Reply-To: <20230327121317.4081816-10-arnd@kernel.org> List-ID: To: Arnd Bergmann Cc: linux-kernel@vger.kernel.org, Arnd Bergmann , Vineet Gupta , Russell King , Neil Armstrong , Linus Walleij , Catalin Marinas , Will Deacon , Guo Ren , Brian Cain , Geert Uytterhoeven , Michal Simek , Thomas Bogendoerfer , Dinh Nguyen , Stafford Horne , Helge Deller , Michael Ellerman , Christophe Leroy , Paul Walmsley , Palmer Dabbelt , Rich --2LJh6dsRB07q9YeN Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Mar 27, 2023 at 02:13:05PM +0200, Arnd Bergmann wrote: > From: Arnd Bergmann >=20 > For a DMA_BIDIRECTIONAL transfer, the caches have to be cleaned > first to let the device see data written by the CPU, and invalidated > after the transfer to let the CPU see data written by the device. >=20 > riscv also invalidates the caches before the transfer, which does > not appear to serve any purpose. Rationale makes sense to me.. Reviewed-by: Conor Dooley Thanks for working on all of this Arnd! --2LJh6dsRB07q9YeN Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- iHUEABYIAB0WIQRh246EGq/8RLhDjO14tDGHoIJi0gUCZCScigAKCRB4tDGHoIJi 0jHpAP47kMhf2uxHoGKhD+jHsEYnFgTHptLnAfIJV6N+QeFoOAD/YxG6hd8qhesW 6Tw9EqBEW/4auX2CLsbK7xE8fP5A9wg= =os1C -----END PGP SIGNATURE----- --2LJh6dsRB07q9YeN--