Re: [PATCH] x86: Return to kernel without IRET

2014-05-02 Thread Linus Torvalds
On Fri, May 2, 2014 at 4:51 PM, Andy Lutomirski wrote: > On my box, this saves about 100ns on each interrupt and trap that > happens while running in kernel space. This speeds up my kernel_pf > microbenchmark by about 17%. Acked-by: Linus Torvalds Now it just needs lots of testing to make

[PATCH] x86: Return to kernel without IRET

2014-05-02 Thread Andy Lutomirski
On my box, this saves about 100ns on each interrupt and trap that happens while running in kernel space. This speeds up my kernel_pf microbenchmark by about 17%. Signed-off-by: Andy Lutomirski --- Changes from the RFC: - Much better comments - Rewritten to use popq_cfi directly instead of

[PATCH] x86: Return to kernel without IRET

2014-05-02 Thread Andy Lutomirski
On my box, this saves about 100ns on each interrupt and trap that happens while running in kernel space. This speeds up my kernel_pf microbenchmark by about 17%. Signed-off-by: Andy Lutomirski l...@amacapital.net --- Changes from the RFC: - Much better comments - Rewritten to use popq_cfi

Re: [PATCH] x86: Return to kernel without IRET

2014-05-02 Thread Linus Torvalds
On Fri, May 2, 2014 at 4:51 PM, Andy Lutomirski l...@amacapital.net wrote: On my box, this saves about 100ns on each interrupt and trap that happens while running in kernel space. This speeds up my kernel_pf microbenchmark by about 17%. Acked-by: Linus Torvalds torva...@linux-foundation.org