kernel.git/arch/x86/kernel/xsave.c, branch linux-2.6.30.y

x86-64: fix FPU corruption with signals and preemption

2009-04-20T21:33:00Z

In 64bit signal delivery path, clear_used_math() was happening before saving the current active FPU state on to the user stack for signal handling. Between clear_used_math() and the state store on to the user stack, potentially we can get a page fault for the user address and can block. Infact, while testing we were hitting the might_fault() in __clear_user() which can do a schedule(). At a later point in time, we will schedule back into this process and resume the save state (using "xsave/fxsave" instruction) which can lead to DNA fault. And as used_math was cleared before, we will reinit the FP state in the DNA fault and continue. This reinit will result in loosing the FPU state of the process. Move clear_used_math() to a point after the FPU state has been stored onto the user stack. This issue is present from a long time (even before the xsave changes and the x86 merge). But it can easily be exposed in 2.6.28.x and 2.6.29.x series because of the __clear_user() in this path, which has an explicit __cond_resched() leading to a context switch with CONFIG_PREEMPT_VOLUNTARY. [ Impact: fix FPU state corruption ] Signed-off-by: Suresh Siddha Cc: [2.6.28.x, 2.6.29.x] Signed-off-by: H. Peter Anvin

x86: add linux kernel support for YMM state

2009-04-12T11:08:56Z

Impact: save/restore Intel-AVX state properly between tasks Intel Advanced Vector Extensions (AVX) introduce 256-bit vector processing capability. More about AVX at http://software.intel.com/sites/avx Add OS support for YMM state management using xsave/xrstor infrastructure to support AVX. Signed-off-by: Suresh Siddha LKML-Reference: <1239402084.27006.8057.camel@localhost.localdomain> Signed-off-by: Ingo Molnar

x86: xsave.c: restore_user_xstate should be static

2008-12-30T21:31:41Z

Impact: cleanup, reduce kernel size a bit, avoid sparse warning Fixes sparse warning: arch/x86/kernel/xsave.c:162:5: warning: symbol 'restore_user_xstate' was not declared. Should it be static? Signed-off-by: Jaswinder Singh Rajput Signed-off-by: H. Peter Anvin

x86: fixing cpuinit/init tangle, xsave_cntxt_init()

2008-11-20T15:43:42Z

Annotate xsave_cntxt_init() as "can be called outside of __init". Signed-off-by: Rakib Mullick Signed-off-by: Ingo Molnar

x86: make variables static

2008-10-22T05:31:28Z

These variables are only used in their source files, so make them static. Signed-off-by: Roel Kluin Signed-off-by: Ingo Molnar

x86, fpu: check __clear_user() return value

2008-10-12T13:17:39Z

fix warning: arch/x86/kernel/xsave.c: In function ‘save_i387_xstate’: arch/x86/kernel/xsave.c:98: warning: ignoring return value of ‘__clear_user’, declared with attribute warn_unused_result check the return value and act on it. We should not be ignoring faults at this point. Signed-off-by: Ingo Molnar

x86: xsave: set FP, SSE bits in the xsave header in the user sigcontext

2008-10-07T21:36:08Z

If a processor implementation discern that a processor state component is in its initialized state, it may modify the corresponding bit in the xsave header.xstate_bv as '0'. State in the memory layout setup by 'xsave' will be consistent with the bit values in the header. During signal handling, legacy applications may change the FP/SSE bits in the sigcontext memory layout without touching the FP/SSE header bits in the xsave header. So always set FP/SSE bits in the xsave header while saving the sigcontext state to the user space. During signal return, this will enable the kernel to capture any changes to the FP/SSE bits by the legacy applications which don't touch xsave headers. xsave aware apps can change the xstate_bv in the xsave header aswell as change any contents in the memory layout. xrestor as part of sigreturn will capture all the changes. Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin

x86: xsave: fix error condition in save_i387_xstate()

2008-10-07T21:36:01Z

Actually return failure on error. Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin

x86: make setup_xstate_init() __init

2008-09-06T17:01:18Z

WARNING: vmlinux.o(.text+0x22453): Section mismatch in reference from the function setup_xstate_init() to the function .init.text:__alloc_bootmem() The function setup_xstate_init() references the function __init __alloc_bootmem(). This is often because setup_xstate_init lacks a __init annotation or the annotation of __alloc_bootmem is wrong. Signed-off-by: Alexey Dobriyan Signed-off-by: Ingo Molnar

x86, xsave: use BUG_ON() instead of BUILD_BUG_ON()

2008-08-14T08:56:07Z

All these structure sizes are runtime determined. So use a runtime bug check. Signed-off-by: Suresh Siddha Signed-off-by: Ingo Molnar