Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1267533 > unrolled thread
| Started by | Andy Lutomirski <luto@kernel.org> |
|---|---|
| First post | 2015-11-12 00:20 +0100 |
| Last post | 2015-11-12 09:20 +0100 |
| Articles | 3 — 2 participants |
Back to article view | Back to linux.kernel
[PATCH v2 0/4] x86 entry stuff, maybe for 4.4 Andy Lutomirski <luto@kernel.org> - 2015-11-12 00:20 +0100
[PATCH v2 4/4] x86/entry/64: Bypass enter_from_user_mode on non-context-tracking boots Andy Lutomirski <luto@kernel.org> - 2015-11-12 00:20 +0100
Re: [PATCH v2 4/4] x86/entry/64: Bypass enter_from_user_mode on non-context-tracking boots Ingo Molnar <mingo@kernel.org> - 2015-11-12 09:20 +0100
| From | Andy Lutomirski <luto@kernel.org> |
|---|---|
| Date | 2015-11-12 00:20 +0100 |
| Subject | [PATCH v2 0/4] x86 entry stuff, maybe for 4.4 |
| Message-ID | <qtMQh-Va-7@gated-at.bofh.it> |
The first patch is a bit ugly, but it fixes a bug that could affect
lockdep. That bug is very minor and may not be observable at all,
but I don't really want to bet on it.
The other three are intended to fix a performance regression in the
entry rework that Frédéric objected to. They're much later than I'd
like to have sent them for 4.4, but they're kind-of sort-of
regression fixes, so maybe they're still okay. They would certainly
need careful review, though.
I don't have a great benchmark for them. The biggest impact is
likely to be to user page fault latency on CONFIG_CONTEXT_TRACKING=y
kernels (i.e. distro kernels) that don't use context tracking
(i.e. most users).
Changes from v1:
- CALL_ENTER_FROM_USER_MODE is now CALL_enter_from_user_mode (Ingo)
- STATIC_JUMP_IF_{TRUE,FALSE} now cannot be (mis-)used on non-jump-label
kernels (Thomas)
- Comments are better (Borislav)
This doesn't really address Thomas' objections to the HAVE_JUMP_LABEL stuff,
but it's more robust now, and maybe that's good enough.
Andy Lutomirski (4):
context_tracking: Switch to new static_branch API
x86/asm: Error out if asm/jump_label.h is included inappropriately
x86/asm: Add asm macros for static keys/jump labels
x86/entry/64: Bypass enter_from_user_mode on non-context-tracking
boots
arch/x86/entry/calling.h | 15 ++++++++
arch/x86/entry/entry_64.S | 8 ++---
arch/x86/include/asm/jump_label.h | 63 ++++++++++++++++++++++++++++++----
include/linux/context_tracking_state.h | 4 +--
kernel/context_tracking.c | 4 +--
5 files changed, 77 insertions(+), 17 deletions(-)
--
2.5.0
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[toc] | [next] | [standalone]
| From | Andy Lutomirski <luto@kernel.org> |
|---|---|
| Date | 2015-11-12 00:20 +0100 |
| Subject | [PATCH v2 4/4] x86/entry/64: Bypass enter_from_user_mode on non-context-tracking boots |
| Message-ID | <qtMQi-Va-21@gated-at.bofh.it> |
| In reply to | #1267533 |
On CONFIG_CONTEXT_TRACKING kernels that have context tracking disabled at runtime (which includes most distro kernels), we still have the overhead of a call to enter_from_user_mode in interrupt and exception entries. If jump labels are available, this uses the jump label infrastructure to skip the call. Signed-off-by: Andy Lutomirski <luto@kernel.org> --- arch/x86/entry/calling.h | 15 +++++++++++++++ arch/x86/entry/entry_64.S | 8 ++------ 2 files changed, 17 insertions(+), 6 deletions(-) diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3c71dd947c7b..e32206e09868 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -1,3 +1,5 @@ +#include <linux/jump_label.h> + /* x86 function call convention, 64-bit: @@ -232,3 +234,16 @@ For 32-bit we have the following conventions - kernel is built with #endif /* CONFIG_X86_64 */ +/* + * This does 'call enter_from_user_mode' unless we can avoid it based on + * kernel config or using the static jump infrastructure. + */ +.macro CALL_enter_from_user_mode +#ifdef CONFIG_CONTEXT_TRACKING +#ifdef HAVE_JUMP_LABEL + STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0 +#endif + call enter_from_user_mode +.Lafter_call_\@: +#endif +.endm diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a55697d19824..9d34d3cfceb6 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -520,9 +520,7 @@ END(irq_entries_start) */ TRACE_IRQS_OFF -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + CALL_enter_from_user_mode 1: /* @@ -1066,9 +1064,7 @@ ENTRY(error_entry) * (which can take locks). */ TRACE_IRQS_OFF -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + CALL_enter_from_user_mode ret .Lerror_entry_done: -- 2.5.0 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[toc] | [prev] | [next] | [standalone]
| From | Ingo Molnar <mingo@kernel.org> |
|---|---|
| Date | 2015-11-12 09:20 +0100 |
| Subject | Re: [PATCH v2 4/4] x86/entry/64: Bypass enter_from_user_mode on non-context-tracking boots |
| Message-ID | <qtVgS-6pI-7@gated-at.bofh.it> |
| In reply to | #1267534 |
* Andy Lutomirski <luto@kernel.org> wrote: > On CONFIG_CONTEXT_TRACKING kernels that have context tracking > disabled at runtime (which includes most distro kernels), we still > have the overhead of a call to enter_from_user_mode in interrupt and > exception entries. > > If jump labels are available, this uses the jump label > infrastructure to skip the call. > > Signed-off-by: Andy Lutomirski <luto@kernel.org> > --- > arch/x86/entry/calling.h | 15 +++++++++++++++ > arch/x86/entry/entry_64.S | 8 ++------ > 2 files changed, 17 insertions(+), 6 deletions(-) > > diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h > index 3c71dd947c7b..e32206e09868 100644 > --- a/arch/x86/entry/calling.h > +++ b/arch/x86/entry/calling.h > @@ -1,3 +1,5 @@ > +#include <linux/jump_label.h> > + > /* > > x86 function call convention, 64-bit: > @@ -232,3 +234,16 @@ For 32-bit we have the following conventions - kernel is built with > > #endif /* CONFIG_X86_64 */ > > +/* > + * This does 'call enter_from_user_mode' unless we can avoid it based on > + * kernel config or using the static jump infrastructure. > + */ > +.macro CALL_enter_from_user_mode > +#ifdef CONFIG_CONTEXT_TRACKING > +#ifdef HAVE_JUMP_LABEL > + STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0 > +#endif > + call enter_from_user_mode > +.Lafter_call_\@: > +#endif > +.endm > diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S > index a55697d19824..9d34d3cfceb6 100644 > --- a/arch/x86/entry/entry_64.S > +++ b/arch/x86/entry/entry_64.S > @@ -520,9 +520,7 @@ END(irq_entries_start) > */ > TRACE_IRQS_OFF > > -#ifdef CONFIG_CONTEXT_TRACKING > - call enter_from_user_mode > -#endif > + CALL_enter_from_user_mode > > 1: > /* > @@ -1066,9 +1064,7 @@ ENTRY(error_entry) > * (which can take locks). > */ > TRACE_IRQS_OFF > -#ifdef CONFIG_CONTEXT_TRACKING > - call enter_from_user_mode > -#endif > + CALL_enter_from_user_mode > ret > > .Lerror_entry_done: > -- > 2.5.0 > hm, this patch does not apply to latest -tip: patching file arch/x86/entry/entry_64.S Hunk #1 FAILED at 520. Hunk #2 FAILED at 1066. 2 out of 2 hunks FAILED -- rejects in file arch/x86/entry/entry_64.S am I missing some dependency, or are they against an older tree? Thanks, Ingo -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[toc] | [prev] | [standalone]
Back to top | Article view | linux.kernel
csiph-web