diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-15 10:23:56 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-15 10:23:56 -0700 |
commit | ecc026bff6e8444c6b50dcde192e7acdaf42bf82 (patch) | |
tree | e2a3ac4aab57a84147684cbd0992df9a61c2eca3 /Documentation | |
parent | fa53c4893994da439c6a74a03a13572cf7e1b41a (diff) | |
parent | 14ddde78c787248ada9da2f2d04900548ffcf342 (diff) | |
download | linux-ecc026bff6e8444c6b50dcde192e7acdaf42bf82.tar.bz2 |
Merge branch 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fpu updates from Ingo Molnar:
"The biggest change in terms of impact is the changing of the FPU
context switch model to 'eagerfpu' for all CPU types, via: commit
58122bf1d856: "x86/fpu: Default eagerfpu=on on all CPUs"
This makes all FPU saves and restores synchronous and makes the FPU
code a lot more obvious to read. In the next cycle, if this change is
problem free, we'll remove the old lazy FPU restore code altogether.
This change flushed out some old bugs, which should all be fixed by
now, BYMMV"
* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/fpu: Default eagerfpu=on on all CPUs
x86/fpu: Speed up lazy FPU restores slightly
x86/fpu: Fold fpu_copy() into fpu__copy()
x86/fpu: Fix FNSAVE usage in eagerfpu mode
x86/fpu: Fix math emulation in eager fpu mode
Diffstat (limited to 'Documentation')
0 files changed, 0 insertions, 0 deletions