Re: [PATCH v1 3/3] powerpc/code-patching: Optimise patch_memcpy() to 4 byte chunks
On Fri, 2024-03-15 at 06:39 +, Christophe Leroy wrote:
>
>
> Le 15/03/2024 à 03:57, Benjamin Gray a écrit :
> > As we are patching instructions, we can assume the length is a
> > multiple
> > of 4 and the destination address is aligned.
> >
> > Atomicity of patching a prefixed instruction is not a concern, as
> > the
> > original implementation doesn't provide it anyway.
>
> This patch looks unnecessary.
>
> copy_to_kernel_nofault() is what you want to use instead.
Yeah, I would drop this patch when using copy_to_kernel_nofault()
>
> >
> > Signed-off-by: Benjamin Gray
> > ---
> > arch/powerpc/lib/code-patching.c | 8
> > 1 file changed, 4 insertions(+), 4 deletions(-)
> >
> > diff --git a/arch/powerpc/lib/code-patching.c
> > b/arch/powerpc/lib/code-patching.c
> > index c6633759b509..ed450a32918c 100644
> > --- a/arch/powerpc/lib/code-patching.c
> > +++ b/arch/powerpc/lib/code-patching.c
> > @@ -394,10 +394,10 @@ static int patch_memset32(u32 *addr, u32 val,
> > size_t count)
> > return -EPERM;
> > }
> >
> > -static int patch_memcpy(void *dst, void *src, size_t len)
> > +static int patch_memcpy32(u32 *dst, u32 *src, size_t count)
> > {
> > - for (void *end = src + len; src < end; dst++, src++)
> > - __put_kernel_nofault(dst, src, u8, failed);
> > + for (u32 *end = src + count; src < end; dst++, src++)
> > + __put_kernel_nofault(dst, src, u32, failed);
> >
> > return 0;
> >
> > @@ -424,7 +424,7 @@ static int __patch_instructions(u32
> > *patch_addr, u32 *code, size_t len, bool rep
> > err = patch_memset32(patch_addr, val, len
> > / 4);
> > }
> > } else {
> > - err = patch_memcpy(patch_addr, code, len);
> > + err = patch_memcpy32(patch_addr, code, len / 4);
> > }
> >
> > smp_wmb(); /* smp write barrier */
Re: [PATCH v1 3/3] powerpc/code-patching: Optimise patch_memcpy() to 4 byte chunks
Le 15/03/2024 à 03:57, Benjamin Gray a écrit :
> As we are patching instructions, we can assume the length is a multiple
> of 4 and the destination address is aligned.
>
> Atomicity of patching a prefixed instruction is not a concern, as the
> original implementation doesn't provide it anyway.
This patch looks unnecessary.
copy_to_kernel_nofault() is what you want to use instead.
>
> Signed-off-by: Benjamin Gray
> ---
> arch/powerpc/lib/code-patching.c | 8
> 1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/arch/powerpc/lib/code-patching.c
> b/arch/powerpc/lib/code-patching.c
> index c6633759b509..ed450a32918c 100644
> --- a/arch/powerpc/lib/code-patching.c
> +++ b/arch/powerpc/lib/code-patching.c
> @@ -394,10 +394,10 @@ static int patch_memset32(u32 *addr, u32 val, size_t
> count)
> return -EPERM;
> }
>
> -static int patch_memcpy(void *dst, void *src, size_t len)
> +static int patch_memcpy32(u32 *dst, u32 *src, size_t count)
> {
> - for (void *end = src + len; src < end; dst++, src++)
> - __put_kernel_nofault(dst, src, u8, failed);
> + for (u32 *end = src + count; src < end; dst++, src++)
> + __put_kernel_nofault(dst, src, u32, failed);
>
> return 0;
>
> @@ -424,7 +424,7 @@ static int __patch_instructions(u32 *patch_addr, u32
> *code, size_t len, bool rep
> err = patch_memset32(patch_addr, val, len / 4);
> }
> } else {
> - err = patch_memcpy(patch_addr, code, len);
> + err = patch_memcpy32(patch_addr, code, len / 4);
> }
>
> smp_wmb(); /* smp write barrier */
[PATCH v1 3/3] powerpc/code-patching: Optimise patch_memcpy() to 4 byte chunks
As we are patching instructions, we can assume the length is a multiple
of 4 and the destination address is aligned.
Atomicity of patching a prefixed instruction is not a concern, as the
original implementation doesn't provide it anyway.
Signed-off-by: Benjamin Gray
---
arch/powerpc/lib/code-patching.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index c6633759b509..ed450a32918c 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -394,10 +394,10 @@ static int patch_memset32(u32 *addr, u32 val, size_t
count)
return -EPERM;
}
-static int patch_memcpy(void *dst, void *src, size_t len)
+static int patch_memcpy32(u32 *dst, u32 *src, size_t count)
{
- for (void *end = src + len; src < end; dst++, src++)
- __put_kernel_nofault(dst, src, u8, failed);
+ for (u32 *end = src + count; src < end; dst++, src++)
+ __put_kernel_nofault(dst, src, u32, failed);
return 0;
@@ -424,7 +424,7 @@ static int __patch_instructions(u32 *patch_addr, u32 *code,
size_t len, bool rep
err = patch_memset32(patch_addr, val, len / 4);
}
} else {
- err = patch_memcpy(patch_addr, code, len);
+ err = patch_memcpy32(patch_addr, code, len / 4);
}
smp_wmb(); /* smp write barrier */
--
2.44.0
