All of lore.kernel.org
 help / color / mirror / Atom feed
From: Will Deacon <will.deacon@arm.com>
To: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org, ard.biesheuvel@linaro.org,
	catalin.marinas@arm.com, rml@tech9.net, tglx@linutronix.de,
	peterz@infradead.org, schwidefsky@de.ibm.com,
	Will Deacon <will.deacon@arm.com>
Subject: [PATCH 0/2] arm64: Only call into preempt_schedule() if need_resched()
Date: Tue, 27 Nov 2018 19:45:00 +0000	[thread overview]
Message-ID: <1543347902-21170-1-git-send-email-will.deacon@arm.com> (raw)

Hi all,

This pair of patches improves our preempt_enable() implementation slightly
on arm64 by making the resulting call to preempt_schedule() conditional
on need_resched(), which is tracked in bit 32 of the preempt count. The
logic is inverted so that we can detect the preempt count going to zero
and need_resched being set with a single CBZ instruction.

Consequently, our preempt_enable() code (including prologue/epilogue)
goes from:

  40:   a9bf7bfd        stp     x29, x30, [sp, #-16]!
  44:   910003fd        mov     x29, sp
  48:   d5384101        mrs     x1, sp_el0
  4c:   b9401020        ldr     w0, [x1, #16]
  50:   51000400        sub     w0, w0, #0x1
  54:   b9001020        str     w0, [x1, #16]
  58:   350000a0        cbnz    w0, 6c
  5c:   f9400020        ldr     x0, [x1]
  60:   721f001f        tst     w0, #0x2
  64:   54000040        b.eq    6c // b.none
  68:   94000000        bl      0 <preempt_schedule>
  6c:   a8c17bfd        ldp     x29, x30, [sp], #16
  70:   d65f03c0        ret

to:

  40:   a9bf7bfd        stp     x29, x30, [sp, #-16]!
  44:   910003fd        mov     x29, sp
  48:   d5384101        mrs     x1, sp_el0
  4c:   f9400820        ldr     x0, [x1, #16]
  50:   d1000400        sub     x0, x0, #0x1
  54:   b9001020        str     w0, [x1, #16]
  58:   b4000060        cbz     x0, 64 <will+0x24>
  5c:   a8c17bfd        ldp     x29, x30, [sp], #16
  60:   d65f03c0        ret
  64:   94000000        bl      0 <preempt_schedule>
  68:   a8c17bfd        ldp     x29, x30, [sp], #16
  6c:   d65f03c0        ret

Will

--->8

Will Deacon (2):
  preempt: Move PREEMPT_NEED_RESCHED definition into arch code
  arm64: preempt: Provide our own implementation of asm/preempt.h

 arch/arm64/include/asm/Kbuild        |  1 -
 arch/arm64/include/asm/preempt.h     | 78 ++++++++++++++++++++++++++++++++++++
 arch/arm64/include/asm/thread_info.h | 13 +++++-
 arch/s390/include/asm/preempt.h      |  2 +
 arch/x86/include/asm/preempt.h       |  3 ++
 include/linux/preempt.h              |  3 --
 6 files changed, 95 insertions(+), 5 deletions(-)
 create mode 100644 arch/arm64/include/asm/preempt.h

-- 
2.1.4


WARNING: multiple messages have this Message-ID (diff)
From: will.deacon@arm.com (Will Deacon)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH 0/2] arm64: Only call into preempt_schedule() if need_resched()
Date: Tue, 27 Nov 2018 19:45:00 +0000	[thread overview]
Message-ID: <1543347902-21170-1-git-send-email-will.deacon@arm.com> (raw)

Hi all,

This pair of patches improves our preempt_enable() implementation slightly
on arm64 by making the resulting call to preempt_schedule() conditional
on need_resched(), which is tracked in bit 32 of the preempt count. The
logic is inverted so that we can detect the preempt count going to zero
and need_resched being set with a single CBZ instruction.

Consequently, our preempt_enable() code (including prologue/epilogue)
goes from:

  40:   a9bf7bfd        stp     x29, x30, [sp, #-16]!
  44:   910003fd        mov     x29, sp
  48:   d5384101        mrs     x1, sp_el0
  4c:   b9401020        ldr     w0, [x1, #16]
  50:   51000400        sub     w0, w0, #0x1
  54:   b9001020        str     w0, [x1, #16]
  58:   350000a0        cbnz    w0, 6c
  5c:   f9400020        ldr     x0, [x1]
  60:   721f001f        tst     w0, #0x2
  64:   54000040        b.eq    6c // b.none
  68:   94000000        bl      0 <preempt_schedule>
  6c:   a8c17bfd        ldp     x29, x30, [sp], #16
  70:   d65f03c0        ret

to:

  40:   a9bf7bfd        stp     x29, x30, [sp, #-16]!
  44:   910003fd        mov     x29, sp
  48:   d5384101        mrs     x1, sp_el0
  4c:   f9400820        ldr     x0, [x1, #16]
  50:   d1000400        sub     x0, x0, #0x1
  54:   b9001020        str     w0, [x1, #16]
  58:   b4000060        cbz     x0, 64 <will+0x24>
  5c:   a8c17bfd        ldp     x29, x30, [sp], #16
  60:   d65f03c0        ret
  64:   94000000        bl      0 <preempt_schedule>
  68:   a8c17bfd        ldp     x29, x30, [sp], #16
  6c:   d65f03c0        ret

Will

--->8

Will Deacon (2):
  preempt: Move PREEMPT_NEED_RESCHED definition into arch code
  arm64: preempt: Provide our own implementation of asm/preempt.h

 arch/arm64/include/asm/Kbuild        |  1 -
 arch/arm64/include/asm/preempt.h     | 78 ++++++++++++++++++++++++++++++++++++
 arch/arm64/include/asm/thread_info.h | 13 +++++-
 arch/s390/include/asm/preempt.h      |  2 +
 arch/x86/include/asm/preempt.h       |  3 ++
 include/linux/preempt.h              |  3 --
 6 files changed, 95 insertions(+), 5 deletions(-)
 create mode 100644 arch/arm64/include/asm/preempt.h

-- 
2.1.4

             reply	other threads:[~2018-11-27 19:44 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-27 19:45 Will Deacon [this message]
2018-11-27 19:45 ` [PATCH 0/2] arm64: Only call into preempt_schedule() if need_resched() Will Deacon
2018-11-27 19:45 ` [PATCH 1/2] preempt: Move PREEMPT_NEED_RESCHED definition into arch code Will Deacon
2018-11-27 19:45   ` Will Deacon
2018-11-27 19:45 ` [PATCH 2/2] arm64: preempt: Provide our own implementation of asm/preempt.h Will Deacon
2018-11-27 19:45   ` Will Deacon
2018-11-28 15:35   ` Ard Biesheuvel
2018-11-28 15:35     ` Ard Biesheuvel
2018-11-28 16:40     ` Peter Zijlstra
2018-11-28 16:40       ` Peter Zijlstra
2018-11-28 16:45       ` Ard Biesheuvel
2018-11-28 16:45         ` Ard Biesheuvel
2018-11-28  8:56 ` [PATCH 0/2] arm64: Only call into preempt_schedule() if need_resched() Peter Zijlstra
2018-11-28  8:56   ` Peter Zijlstra
2018-11-28  9:01   ` Peter Zijlstra
2018-11-28  9:01     ` Peter Zijlstra
2018-11-28 12:04     ` Will Deacon
2018-11-28 12:04       ` Will Deacon

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1543347902-21170-1-git-send-email-will.deacon@arm.com \
    --to=will.deacon@arm.com \
    --cc=ard.biesheuvel@linaro.org \
    --cc=catalin.marinas@arm.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=rml@tech9.net \
    --cc=schwidefsky@de.ibm.com \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.