Re: [RFC PATCH] powerpc: Convert ____flush_dcache_icache_phys() to C

From: Christophe Leroy
Date: Thu Aug 22 2019 - 09:43:59 EST

Le 22/08/2019 Ã 02:27, Alastair D'Silva a ÃcritÂ:
On Wed, 2019-08-21 at 22:27 +0200, Christophe Leroy wrote:

Le 20/08/2019 Ã 06:36, Alastair D'Silva a Ãcrit :
On Fri, 2019-08-16 at 15:52 +0000, Christophe Leroy wrote:


Thanks Christophe,

I'm trying a somewhat different approach that requires less
of assembler. Handling of CPU_FTR_COHERENT_ICACHE is outside this
function. The code below is not a patch as my tree is a bit messy,

Can we be 100% sure that GCC won't add any code accessing some
data or stack while the Data MMU is OFF ?



I'm not sure how we would go about making such a guarantee, but I've
tied every variable used to a register and addr is passed in a
register, so there is no stack usage, and every call in there only
operates on it's operands.

The calls to the inline cache helpers (for the PPC32 case) are all
constants, so I can't see a reasonable scenario where there would be a
function call and reordered to after the DR bit is turned off, but I
guess if we want to be paranoid, we could always add an mb() call
before the DR bit is manipulated to prevent the compiler from
reordering across the section where the data MMU is disabled.

Anyway, I think the benefit of converting that function to C is pretty small. flush_dcache_range() and friends were converted to C mainly in order to inline them. But this __flush_dcache_icache_phys() is too big to be worth inlining, yet small and stable enough to remain in assembly for the time being.

So I suggest you keep it aside your series for now, just move PURGE_PREFETCHED_INS inside it directly as it will be the only remaining user of it.