Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1268265
| From | Andy Lutomirski <luto@kernel.org> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | [PATCH v3 5/5] x86/entry/64: Bypass enter_from_user_mode on non-context-tracking boots |
| Date | 2015-11-12 22:00 +0100 |
| Message-ID | <qu78l-5oc-1@gated-at.bofh.it> (permalink) |
| References | <qu78l-5oc-3@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
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/
Back to linux.kernel | Previous | Next — Next in thread | Find similar | Unroll thread
[PATCH v3 5/5] x86/entry/64: Bypass enter_from_user_mode on non-context-tracking boots Andy Lutomirski <luto@kernel.org> - 2015-11-12 22:00 +0100 Re: [PATCH v3 5/5] x86/entry/64: Bypass enter_from_user_mode on non-context-tracking boots Thomas Gleixner <tglx@linutronix.de> - 2015-11-13 15:30 +0100 Re: [PATCH v3 5/5] x86/entry/64: Bypass enter_from_user_mode on non-context-tracking boots Frederic Weisbecker <fweisbec@gmail.com> - 2015-11-13 16:30 +0100
csiph-web