[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <82dfa5e7-286d-777a-b1aa-ebe5144e79db@ans.pl>
Date: Mon, 25 Jan 2021 19:24:56 -0800
From: Krzysztof Olędzki <ole@....pl>
To: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
linux-kernel@...r.kernel.org, Andy Lutomirski <luto@...nel.org>
Cc: stable@...r.kernel.org, Krzysztof Mazur <krzysiek@...lesie.net>,
Borislav Petkov <bp@...e.de>
Subject: Re: [PATCH 5.10 119/199] x86/mmx: Use KFPU_387 for MMX string
operations
Hi,
I think for both 5.4-stable and 5.10-stable we also need
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=e45122893a9870813f9bd7b4add4f613e6f29008
- "x86/fpu: Add kernel_fpu_begin_mask() to selectively initialize state"
Without this, there is no kernel_fpu_begin_mask().
Thanks,
Krzysztof
On 2021-01-25 at 10:39, Greg Kroah-Hartman wrote:
> From: Andy Lutomirski <luto@...nel.org>
>
> commit 67de8dca50c027ca0fa3b62a488ee5035036a0da upstream.
>
> The default kernel_fpu_begin() doesn't work on systems that support XMM but
> haven't yet enabled CR4.OSFXSR. This causes crashes when _mmx_memcpy() is
> called too early because LDMXCSR generates #UD when the aforementioned bit
> is clear.
>
> Fix it by using kernel_fpu_begin_mask(KFPU_387) explicitly.
>
> Fixes: 7ad816762f9b ("x86/fpu: Reset MXCSR to default in kernel_fpu_begin()")
> Reported-by: Krzysztof Mazur <krzysiek@...lesie.net>
> Signed-off-by: Andy Lutomirski <luto@...nel.org>
> Signed-off-by: Borislav Petkov <bp@...e.de>
> Tested-by: Krzysztof Piotr Olędzki <ole@....pl>
> Tested-by: Krzysztof Mazur <krzysiek@...lesie.net>
> Cc: <stable@...r.kernel.org>
> Link: https://lkml.kernel.org/r/e7bf21855fe99e5f3baa27446e32623358f69e8d.1611205691.git.luto@kernel.org
> Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
>
> ---
> arch/x86/lib/mmx_32.c | 20 +++++++++++++++-----
> 1 file changed, 15 insertions(+), 5 deletions(-)
>
> --- a/arch/x86/lib/mmx_32.c
> +++ b/arch/x86/lib/mmx_32.c
> @@ -26,6 +26,16 @@
> #include <asm/fpu/api.h>
> #include <asm/asm.h>
>
> +/*
> + * Use KFPU_387. MMX instructions are not affected by MXCSR,
> + * but both AMD and Intel documentation states that even integer MMX
> + * operations will result in #MF if an exception is pending in FCW.
> + *
> + * EMMS is not needed afterwards because, after calling kernel_fpu_end(),
> + * any subsequent user of the 387 stack will reinitialize it using
> + * KFPU_387.
> + */
> +
> void *_mmx_memcpy(void *to, const void *from, size_t len)
> {
> void *p;
> @@ -37,7 +47,7 @@ void *_mmx_memcpy(void *to, const void *
> p = to;
> i = len >> 6; /* len/64 */
>
> - kernel_fpu_begin();
> + kernel_fpu_begin_mask(KFPU_387);
>
> __asm__ __volatile__ (
> "1: prefetch (%0)\n" /* This set is 28 bytes */
> @@ -127,7 +137,7 @@ static void fast_clear_page(void *page)
> {
> int i;
>
> - kernel_fpu_begin();
> + kernel_fpu_begin_mask(KFPU_387);
>
> __asm__ __volatile__ (
> " pxor %%mm0, %%mm0\n" : :
> @@ -160,7 +170,7 @@ static void fast_copy_page(void *to, voi
> {
> int i;
>
> - kernel_fpu_begin();
> + kernel_fpu_begin_mask(KFPU_387);
>
> /*
> * maybe the prefetch stuff can go before the expensive fnsave...
> @@ -247,7 +257,7 @@ static void fast_clear_page(void *page)
> {
> int i;
>
> - kernel_fpu_begin();
> + kernel_fpu_begin_mask(KFPU_387);
>
> __asm__ __volatile__ (
> " pxor %%mm0, %%mm0\n" : :
> @@ -282,7 +292,7 @@ static void fast_copy_page(void *to, voi
> {
> int i;
>
> - kernel_fpu_begin();
> + kernel_fpu_begin_mask(KFPU_387);
>
> __asm__ __volatile__ (
> "1: prefetch (%0)\n"
>
>
Powered by blists - more mailing lists