mbox series

[bpf-next,0/2] bpf, x64: optimize JIT's pro/epilogue

Message ID 20200929204653.4325-1-maciej.fijalkowski@intel.com (mailing list archive)
Headers show
Series bpf, x64: optimize JIT's pro/epilogue | expand

Message

Fijalkowski, Maciej Sept. 29, 2020, 8:46 p.m. UTC 
Hi!

This small set can be considered as a followup after recent addition of
support for tailcalls in bpf subprograms and is focused on optimizing
x64 JIT prologue and epilogue sections.

Turns out the popping tail call counter is not needed anymore and %rsp
handling when stack depth is 0 can be skipped.

For longer explanations, please see commit messages.

Thank you,
Maciej


Maciej Fijalkowski (2):
  bpf, x64: drop "pop %rcx" instruction on BPF JIT epilogue
  bpf: x64: do not emit sub/add 0, %rsp when !stack_depth

 arch/x86/net/bpf_jit_comp.c | 35 +++++++++++++++++++++++------------
 1 file changed, 23 insertions(+), 12 deletions(-)

Comments

patchwork-bot+bpf@kernel.org Sept. 30, 2020, midnight UTC | #1 
Hello:

This series was applied to bpf/bpf-next.git (refs/heads/master):

On Tue, 29 Sep 2020 22:46:51 +0200 you wrote:
> Hi!
> 
> This small set can be considered as a followup after recent addition of
> support for tailcalls in bpf subprograms and is focused on optimizing
> x64 JIT prologue and epilogue sections.
> 
> Turns out the popping tail call counter is not needed anymore and %rsp
> handling when stack depth is 0 can be skipped.
> 
> [...]

Here is the summary with links:
  - [bpf-next,1/2] bpf, x64: drop "pop %rcx" instruction on BPF JIT epilogue
    https://git.kernel.org/bpf/bpf-next/c/d207929d97ea
  - [bpf-next,2/2] bpf: x64: do not emit sub/add 0, %rsp when !stack_depth
    https://git.kernel.org/bpf/bpf-next/c/4d0b8c0b46a5

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html