linux-toradex.git/arch/x86/include/asm/xsave.h, branch v3.19.3

x86/fpu/xsaves: Fix improper uses of __ex_table

2015-03-18T13:10:57+00:00

commit 06c8173eb92bbfc03a0fe8bb64315857d0badd06 upstream.

Commit:

  f31a9f7c7169 ("x86/xsaves: Use xsaves/xrstors to save and restore xsave area")

introduced alternative instructions for XSAVES/XRSTORS and commit:

  adb9d526e982 ("x86/xsaves: Add xsaves and xrstors support for booting time")

added support for the XSAVES/XRSTORS instructions at boot time.

Unfortunately both failed to properly protect them against faulting:

The 'xstate_fault' macro will use the closest label named '1'
backward and that ends up in the .altinstr_replacement section
rather than in .text. This means that the kernel will never find
in the __ex_table the .text address where this instruction might
fault, leading to serious problems if userspace manages to
trigger the fault.

Signed-off-by: Quentin Casasnovas 
Signed-off-by: Jamie Iles 
[ Improved the changelog, fixed some whitespace noise. ]
Acked-by: Borislav Petkov 
Acked-by: Linus Torvalds 
Cc: Allan Xavier 
Cc: H. Peter Anvin 
Cc: Thomas Gleixner 
Fixes: adb9d526e982 ("x86/xsaves: Add xsaves and xrstors support for booting time")
Fixes: f31a9f7c7169 ("x86/xsaves: Use xsaves/xrstors to save and restore xsave area")
Signed-off-by: Ingo Molnar 
Signed-off-by: Greg Kroah-Hartman

KVM: x86: Enable Intel AVX-512 for guest

2014-11-03T11:07:30+00:00

Expose Intel AVX-512 feature bits to guest. Also add checks for
xcr0 AVX512 related bits according to spec:
http://download-software.intel.com/sites/default/files/managed/71/2e/319433-017.pdf

Signed-off-by: Chao Peng 
Signed-off-by: Paolo Bonzini

x86, xsave: Add forgotten inline annotation

2014-06-18T22:19:59+00:00

Add a missing inline annotation on a static function, in order to shut
up a bunch of warnings like:

In file included from arch/x86/crypto/camellia_aesni_avx_glue.c:23:0:
./arch/x86/include/asm/xsave.h:73:12: warning: ‘xsave_state_booting’ defined but not used [-Wunused-function]
 static int xsave_state_booting(struct xsave_struct *fx, u64 mask)
            ^
In file included from arch/x86/crypto/camellia_aesni_avx2_glue.c:23:0:
./arch/x86/include/asm/xsave.h:73:12: warning: ‘xsave_state_booting’ defined but not used [-Wunused-function]
 static int xsave_state_booting(struct xsave_struct *fx, u64 mask)
            ^
...

Cc: Fenghua Yu 
Signed-off-by: Borislav Petkov 
Link: http://lkml.kernel.org/r/1403000468-30094-1-git-send-email-bp@alien8.de
Signed-off-by: H. Peter Anvin

x86/xsave: Make it clear that the XSAVE macros use (%edi)/(%rdi)

2014-05-30T15:19:21+00:00

The XSAVE instruction family takes a memory argment.  The macros use
(%edi)/(%rdi) as that memory argument - make that clear to the reader.

Signed-off-by: H. Peter Anvin 
Cc: Fenghua Yu 
Link: http://lkml.kernel.org/r/1401387164-43416-7-git-send-email-fenghua.yu@intel.com

Define kernel API to get address of each state in xsave area

2014-05-29T21:33:09+00:00

In standard form, each state is saved in the xsave area in fixed offset.
But in compacted form, offset of each saved state only can be calculated during
run time because some xstates may not be enabled and saved.

We define kernel API get_xsave_addr() returns address of a given state saved in a xsave area.

It can be called in kernel to get address of each xstate in xsave area in
either standard format or compacted format.

It's useful when kernel wants to directly access each state in xsave area.

Signed-off-by: Fenghua Yu 
Link: http://lkml.kernel.org/r/1401387164-43416-17-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin

x86/xsaves: Add xsaves and xrstors support for booting time

2014-05-29T21:33:02+00:00

Since boot_cpu_data and cpu capabilities are not enabled yet during early
booting time, alternative can not be used in some functions to access xsave
area. Therefore, we define two new functions xrstor_state_booting() and
xsave_state_booting() to access xsave area just during early booting time.

xrstor_state_booting restores xstate from xsave area during early booting time.
xsave_state_booting saves xstate to xsave area during early booting time.

The two functions are similar to xrstor_state and xsave_state respectively.
But the two functions don't use alternatives because alternatives are not
enabled when they are called in such early booting time.

xrstor_state_booting is called only by functions defined as __init. So it's
defined as __init and will be removed from memory after booting time. There
is no extra memory cost caused by this function during running time.

But because xsave_state_booting can be called by run-time function __save_fpu(),
it's not defined as __init and will stay in memory during running time although
it will not be called anymore during running time. It is not ideal to
have this function stay in memory during running time. But it's a pretty small
function and the memory cost will be small. By doing in this way, we can
avoid to change a lot of code to just remove this small function and save a
bit memory for running time.

Signed-off-by: Fenghua Yu 
Link: http://lkml.kernel.org/r/1401387164-43416-13-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin

x86/xsaves: Use xsave/xrstor for saving and restoring user space context

2014-05-29T21:32:57+00:00

We use legacy xsave/xrstor to save and restore standard form of xsave area
in user space context. No xsaveopt or xsaves is used here for two reasons.

First, we don't want to use modified optimization which is implemented in
xsaveopt and xsaves because xrstor/xrstors might track a wrong user space
application.

Secondly, we don't use compacted format of xsave area for backward
compatibility because legacy user space applications only don't understand
the compacted format of the xsave area.

Using standard form of the xsave area may allocate more memory for
user context than compacted form, but preserves compatibility with
legacy applications.  Furthermore, even with holes, the relevant cache
lines don't get touched and thus the performance impact is limited.

Signed-off-by: Fenghua Yu 
Link: http://lkml.kernel.org/r/1401387164-43416-11-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin

x86/xsaves: Use xsaves/xrstors for context switch

2014-05-29T21:31:25+00:00

If xsaves is eanbled, use xsaves/xrstors for context switch to support
compacted format xsave area to occupy less memory and modified optimization
to improve saving performance.

Signed-off-by: Fenghua Yu 
Link: http://lkml.kernel.org/r/1401387164-43416-10-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin

x86/xsaves: Use xsaves/xrstors to save and restore xsave area

2014-05-29T21:31:21+00:00

If xsaves is eanbled, use xsaves/xrstors instrucitons to save and restore
xstate. xsaves and xrstors support compacted format, init optimization,
modified optimization, and supervisor states.

Signed-off-by: Fenghua Yu 
Link: http://lkml.kernel.org/r/1401387164-43416-9-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin

x86/xsaves: Define a macro for handling xsave/xrstor instruction fault

2014-05-29T21:31:18+00:00

Define a macro to handle fault generated by xsave, xsaveopt, xsaves, xrstor,
and xrstors instructions. It is used in functions like xsave_state() etc.

Signed-off-by: Fenghua Yu 
Link: http://lkml.kernel.org/r/1401387164-43416-8-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin