Re: [PATCH] arm64: patching: avoid early page_to_phys()

[Mike Rapoport <rppt@kernel.org>]

On Mon, Dec 02, 2024 at 05:45:11PM +0000, Mark Rutland wrote:
> Looks like I messed up my text editing and left some bonus words...
> 
> On Mon, Dec 02, 2024 at 05:03:59PM +0000, Mark Rutland wrote:
> > When arm64 is configured with CONFIG_DEBUG_VIRTUAL=y, a warning is
> > printed from the patching code because patch_map(), e.g.
> 
> That was meant to say:
> 
> | When arm64 is configured with CONFIG_DEBUG_VIRTUAL=y, a warning is
> | printed from the patching code, e.g.
> 
> [...]
> 
> > For historical reasons, the structure of patch_map() is more complicated
> > than necessary and can be simplified. For kernel image addresses it's
> > sufficient to use __pa_symbol() directly without converting this to a
> > page address and back. Aside from kernel image addresses, all executable
> > code should be allocated from execmem (where all allocations will fall
> > within the vmalloc area), and the vmalloc area), and so there's no need
> > for the fallback case when case when CONFIG_EXECMEM=n.
> 
> That last sentence should have been:
> 
> | Aside from kernel image addresses, all executable code should be
> | allocated from execmem (where all allocations will fall within the
> | vmalloc area), and so there's no need for the fallback case when case
> | when CONFIG_EXECMEM=n.

Still an extra "case when" ;-)
 
> I can spin a v2 with those fixed if necessary.
> 
> Mark.

-- 
Sincerely yours,
Mike.