From mboxrd@z Thu Jan 1 00:00:00 1970 From: jungseoklee85@gmail.com (Jungseok Lee) Date: Tue, 26 May 2015 22:02:46 +0900 Subject: [RFC PATCH 2/2] arm64: Implement vmalloc based thread_info allocator In-Reply-To: References: <1432483340-23157-1-git-send-email-jungseoklee85@gmail.com> <5992243.NYDGjLH37z@wuerfel> Message-ID: To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On May 26, 2015, at 1:47 AM, Catalin Marinas wrote: > On 25 May 2015, at 13:01, Jungseok Lee wrote: > >>> Could the stack size be reduced to 8KB perhaps? >> >> I guess probably not. >> >> A commit, 845ad05e, says that 8KB is not enough to cover SpecWeb benchmark. > > We could go back to 8KB stacks if we implement support for separate IRQ > stack on arm64. It's not too complicated, we would have to use SP0 for (kernel) threads > and SP1 for IRQ handlers. Definitely interesting. It looks like there are two options based on discussion. 1) Reduce the stack size with separate IRQ stack scheme 2) Figure out a generic anti-fragmentation solution Do I miss anything? I am still not sure about the first scheme as reviewing Minchan's findings repeatedly, but I agree that the item should be worked actively. Best Regards Jungseok Lee