[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH] arm: fix TB alignment check
From: |
Peter Maydell |
Subject: |
Re: [Qemu-devel] [PATCH] arm: fix TB alignment check |
Date: |
Thu, 23 Oct 2014 17:25:22 +0100 |
On 23 October 2014 17:15, Richard Henderson <address@hidden> wrote:
> [1] Why 32 when the maximum insn size is more like 15 bytes, I don't know.
> But
> it likely doesn't matter since I'd expect such large TB's to fill up the
> opcode
> buffer first. There would have to be a lot of nops on that page.
Do we actually correctly GPF if the guest hands us an instruction
with a huge long set of prefix bytes? I can't see anything obviously
in the code that catches this case...
-- PMM