summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/traps.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-02-21 19:25:45 +0100
committerH. Peter Anvin <hpa@linux.intel.com>2012-02-21 23:12:46 +0100
commit8546c008924d5fd1724fa698eaa92b414bafd50d (patch)
treefe2d3f50b350c884201c57ca6c331dd867c5d1e8 /arch/x86/kernel/traps.c
parenti387: export 'fpu_owner_task' per-cpu variable (diff)
downloadlinux-8546c008924d5fd1724fa698eaa92b414bafd50d.tar.xz
linux-8546c008924d5fd1724fa698eaa92b414bafd50d.zip
i387: Uninline the generic FP helpers that we expose to kernel modules
Instead of exporting the very low-level internals of the FPU state save/restore code (ie things like 'fpu_owner_task'), we should export the higher-level interfaces. Inlining these things is pointless anyway: sure, sometimes the end result is small, but while 'stts()' can result in just three x86 instructions, those are not cheap instructions (writing %cr0 is a serializing instruction and a very slow one at that). So the overhead of a function call is not noticeable, and we really don't want random modules mucking about with our internal state save logic anyway. So this unexports 'fpu_owner_task', and instead uninlines and exports the actual functions that modules can use: fpu_kernel_begin/end() and unlazy_fpu(). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1202211339590.5354@i5.linux-foundation.org Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Diffstat (limited to 'arch/x86/kernel/traps.c')
0 files changed, 0 insertions, 0 deletions