From mboxrd@z Thu Jan 1 00:00:00 1970 Date: Thu, 12 Sep 2002 08:23:52 -0700 From: Tom Rini To: Benjamin Herrenschmidt Cc: Todd Poynor , linuxppc-dev Subject: Re: consistent_free re-revisited Message-ID: <20020912152352.GE13840@opus.bloom.county> References: <20020912145146.GD13840@opus.bloom.county> <20020912074907.29155@192.168.4.1> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <20020912074907.29155@192.168.4.1> Sender: owner-linuxppc-dev@lists.linuxppc.org List-Id: On Thu, Sep 12, 2002 at 09:49:07AM +0200, Benjamin Herrenschmidt wrote: > >> I tend to hate anything that relies on in_interrupt() as they > >> are other contexts that will have in_interrupt() cleared but still > >> have the same limitations. Typically, anything on the VM path must > >> do either GFP_ATOMIC or GFP_NOIO allocations, wether it's running > >> at interrupt time or not. > > > >The problem is that the atomic pool is limited, iirc. > > Well, ATOMIC can fail, sure, but if you do GFP_KERNEL within a > VM code path, then be prepared for deadlocks. Er, so you're objecting to existing GFP_KERNEL's then? Or is it too early and I need more coffee? :) -- Tom Rini (TR1265) http://gate.crashing.org/~trini/ ** Sent via the linuxppc-dev mail list. See http://lists.linuxppc.org/