From: Herbert Xu Subject: Re: [PATCH] crypto: allow to assign gfp_t for __crypto_alloc_tfm Date: Wed, 20 May 2015 23:42:05 +0800 Message-ID: <20150520154205.GA13539@gondor.apana.org.au> References: <20150519063211.GA28347@gondor.apana.org.au> <20150519065812.GA40012@jaegeuk-mac02.hsd1.ca.comcast.net> <20150519065929.GA28610@gondor.apana.org.au> <20150519071317.GB40012@jaegeuk-mac02.hsd1.ca.comcast.net> <20150519071521.GA28862@gondor.apana.org.au> <20150519141430.GD20421@thunk.org> <20150519142755.GB32663@gondor.apana.org.au> <20150520072118.GN8928@secunet.com> <20150520145901.GI2871@thunk.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Theodore Ts'o , Steffen Klassert , Jaegeuk Kim , "David S. Miller" , "linux-crypto@vger.kernel.org" , linux-ext4@vger.kernel.org, "linux-kernel@vger.kernel.org" , linux-f2fs-devel@lists.sourceforge.net, ecryptfs@vger.kernel.org, "linux-arm-kernel@lists.infradead.org" To: Ard Biesheuvel Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org On Wed, May 20, 2015 at 05:30:14PM +0200, Ard Biesheuvel wrote: > > However, it's quite a can of worms you're opening here. Speed is > easily quantified, and it may even be feasible to introduce some kind > of boottime benchmark to select the fastest implementation available > (like already exists for xor and raid6, for instance). > @Herbert: was something like this ever proposed? And would you > consider merging it if it were implemented adequately? Up until now static priorities have been sufficient in selecting the best implementation. However, if you can show us a case where a given implementation is slower on one host but faster on another then sure we can add a run-time test and priority adjustment for it. Cheers, -- Email: Herbert Xu Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt