From: tip-bot for Thomas Gleixner <tipbot@zytor.com>
To: linux-tip-commits@vger.kernel.org
Cc: peterz@infradead.org, hpa@zytor.com, tglx@linutronix.de,
linux-kernel@vger.kernel.org, rostedt@goodmis.org,
luto@kernel.org, bp@alien8.de, torvalds@linux-foundation.org,
mingo@kernel.org
Subject: [tip:x86/apic] x86/smp: Remove pointless duplicated interrupt code
Date: Tue, 29 Aug 2017 04:09:17 -0700 [thread overview]
Message-ID: <tip-85b77cdd8fbd163d65f340e3f6578c50031af960@git.kernel.org> (raw)
In-Reply-To: <20170828064957.222101344@linutronix.de>
Commit-ID: 85b77cdd8fbd163d65f340e3f6578c50031af960
Gitweb: http://git.kernel.org/tip/85b77cdd8fbd163d65f340e3f6578c50031af960
Author: Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Mon, 28 Aug 2017 08:47:29 +0200
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 29 Aug 2017 11:42:27 +0200
x86/smp: Remove pointless duplicated interrupt code
Two NOP5s are really a good tradeoff vs. the unholy IDT switching mess,
which duplicates code all over the place. The rescheduling interrupt gets
optimized in a later step.
Make the ordering of function call and statistics increment the same as in
other places. Calculate stats first, then do the function call.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20170828064957.222101344@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/include/asm/hw_irq.h | 4 ++--
arch/x86/kernel/smp.c | 43 +++++++------------------------------------
2 files changed, 9 insertions(+), 38 deletions(-)
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 5f042ec..8fb6c22 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -49,8 +49,8 @@ extern asmlinkage void call_function_single_interrupt(void);
#ifdef CONFIG_TRACING
/* Interrupt handlers registered during init_IRQ */
extern void trace_reschedule_interrupt(void);
-extern void trace_call_function_interrupt(void);
-extern void trace_call_function_single_interrupt(void);
+#define trace_call_function_interrupt call_function_interrupt
+#define trace_call_function_single_interrupt call_function_single_interrupt
#define trace_thermal_interrupt thermal_interrupt
#define trace_threshold_interrupt threshold_interrupt
#define trace_deferred_error_interrupt deferred_error_interrupt
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index d798c0d..fb49e10 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -281,57 +281,28 @@ __visible void __irq_entry smp_trace_reschedule_interrupt(struct pt_regs *regs)
*/
ipi_entering_ack_irq();
trace_reschedule_entry(RESCHEDULE_VECTOR);
- __smp_reschedule_interrupt();
+ inc_irq_stat(irq_resched_count);
+ scheduler_ipi();
trace_reschedule_exit(RESCHEDULE_VECTOR);
exiting_irq();
- /*
- * KVM uses this interrupt to force a cpu out of guest mode
- */
-}
-
-static inline void __smp_call_function_interrupt(void)
-{
- generic_smp_call_function_interrupt();
- inc_irq_stat(irq_call_count);
}
__visible void __irq_entry smp_call_function_interrupt(struct pt_regs *regs)
{
ipi_entering_ack_irq();
- __smp_call_function_interrupt();
- exiting_irq();
-}
-
-__visible void __irq_entry
-smp_trace_call_function_interrupt(struct pt_regs *regs)
-{
- ipi_entering_ack_irq();
trace_call_function_entry(CALL_FUNCTION_VECTOR);
- __smp_call_function_interrupt();
- trace_call_function_exit(CALL_FUNCTION_VECTOR);
- exiting_irq();
-}
-
-static inline void __smp_call_function_single_interrupt(void)
-{
- generic_smp_call_function_single_interrupt();
inc_irq_stat(irq_call_count);
-}
-
-__visible void __irq_entry
-smp_call_function_single_interrupt(struct pt_regs *regs)
-{
- ipi_entering_ack_irq();
- __smp_call_function_single_interrupt();
+ generic_smp_call_function_interrupt();
+ trace_call_function_exit(CALL_FUNCTION_VECTOR);
exiting_irq();
}
-__visible void __irq_entry
-smp_trace_call_function_single_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_call_function_single_interrupt(struct pt_regs *r)
{
ipi_entering_ack_irq();
trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
- __smp_call_function_single_interrupt();
+ inc_irq_stat(irq_call_count);
+ generic_smp_call_function_single_interrupt();
trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR);
exiting_irq();
}
next prev parent reply other threads:[~2017-08-29 11:13 UTC|newest]
Thread overview: 95+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-08-28 6:47 [patch V3 00/44] x86: Cleanup IDT code Thomas Gleixner
2017-08-28 6:47 ` [patch V3 01/44] x86/irq: Remove vector_used_by_percpu_irq() Thomas Gleixner
2017-08-29 11:04 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 02/44] x86/irq: Unexport used_vectors Thomas Gleixner
2017-08-29 11:04 ` [tip:x86/apic] x86/irq: Unexport used_vectors[] tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 03/44] x86/irq: Get rid of the first_system_vector bogisity Thomas Gleixner
2017-08-29 11:04 ` [tip:x86/apic] x86/irq: Get rid of the 'first_system_vector' indirection bogosity tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 04/44] x86/irq: Remove duplicated used_vectors definition Thomas Gleixner
2017-08-29 11:05 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 05/44] x86/boot: Move EISA setup to a proper place Thomas Gleixner
2017-08-29 11:05 ` [tip:x86/apic] x86/boot: Move EISA setup to a separate file tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 06/44] x86/tracing: Introduce a static key for exception tracing Thomas Gleixner
2017-08-29 11:06 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 07/44] x86/traps: Simplify pagefault tracing logic Thomas Gleixner
2017-08-29 11:06 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 08/44] x86/apic: Remove the duplicated tracing version of local_timer_interrupt Thomas Gleixner
2017-08-29 11:07 ` [tip:x86/apic] x86/apic: Remove the duplicated tracing version of local_timer_interrupt() tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 09/44] x86/apic: Use this_cpu_ptr in local_timer_interrupt Thomas Gleixner
2017-08-29 11:07 ` [tip:x86/apic] x86/apic: Use this_cpu_ptr() in local_timer_interrupt() tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 10/44] x86/irq: Get rid of duplicated trace_x86_platform_ipi() code Thomas Gleixner
2017-08-29 11:07 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 11/44] x86/apic: Remove the duplicated tracing versions of interrupts Thomas Gleixner
2017-08-29 11:08 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 12/44] x86/irqwork: Get rid of duplicated tracing interrupt code Thomas Gleixner
2017-08-29 11:08 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 13/44] x86/mce: Remove " Thomas Gleixner
2017-08-29 11:08 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 14/44] x86/smp: Remove pointless duplicated " Thomas Gleixner
2017-08-29 11:09 ` tip-bot for Thomas Gleixner [this message]
2017-08-28 6:47 ` [patch V3 15/44] x86/smp: Use static key for reschedule interrupt tracing Thomas Gleixner
2017-08-29 11:09 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 16/44] x86/idt: Remove tracing idt completely Thomas Gleixner
2017-08-29 11:10 ` [tip:x86/apic] x86/idt: Remove the tracing IDT completely tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 17/44] x86/idt: Cleanup the i386 low level entry macros Thomas Gleixner
2017-08-29 11:10 ` [tip:x86/apic] x86/idt: Clean up " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 18/44] x86/tracing: Disentangle pagefault and resched IPI tracing key Thomas Gleixner
2017-08-29 11:10 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 19/44] x86/ipi: Make platform IPI depend on APIC Thomas Gleixner
2017-08-29 11:11 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 20/44] x86/irq_work: Make it " Thomas Gleixner
2017-08-29 11:11 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 21/44] x86/tracing: Build tracepoints only when they are used Thomas Gleixner
2017-08-29 11:12 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 22/44] x86/idt: Unify gate_struct handling for 32/64bit Thomas Gleixner
2017-08-29 11:12 ` [tip:x86/apic] x86/idt: Unify gate_struct handling for 32/64-bit kernels tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 23/44] x86/percpu: Use static initializer for GDT entry Thomas Gleixner
2017-08-29 11:13 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 24/44] x86/fpu: Use bitfield accessors for desc_struct Thomas Gleixner
2017-08-29 11:13 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 25/44] x86: Replace access to desc_struct:a/b fields Thomas Gleixner
2017-08-29 11:13 ` [tip:x86/apic] x86/asm: " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 26/44] x86/gdt: Use bitfields for initialization Thomas Gleixner
2017-08-29 11:14 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 27/44] x86/ldttss: Cleanup 32bit descriptors Thomas Gleixner
2017-08-29 11:14 ` [tip:x86/apic] x86/ldttss: Clean up 32-bit descriptors tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 28/44] x86/idt: Create file for IDT related code Thomas Gleixner
2017-08-29 11:15 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 29/44] x86/idt: Move 32bit idt_descr to C code Thomas Gleixner
2017-08-29 11:15 ` [tip:x86/apic] x86/idt: Move 32-bit " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 30/44] x86/idt: Remove unused set_trap_gate() Thomas Gleixner
2017-08-29 11:16 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 31/44] x86/idt: Consolidate IDT invalidation Thomas Gleixner
2017-08-29 11:16 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 32/44] x86/idt: Move early IDT handler setup to IDT code Thomas Gleixner
2017-08-29 11:16 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 33/44] x86/idt: Move early IDT setup out of 32bit asm Thomas Gleixner
2017-08-29 11:17 ` [tip:x86/apic] x86/idt: Move early IDT setup out of 32-bit asm tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 34/44] x86/idt: Prepare for table based init Thomas Gleixner
2017-08-29 11:17 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 35/44] x86/idt: Switch early trap init to IDT tables Thomas Gleixner
2017-08-29 11:18 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 36/44] x86/idt: Move debug stack init to table based Thomas Gleixner
2017-08-29 11:18 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 37/44] x86/idt: Move ist stack based traps to table init Thomas Gleixner
2017-08-29 11:18 ` [tip:x86/apic] x86/idt: Move IST " tip-bot for Thomas Gleixner
2017-09-01 6:28 ` Andrei Vagin
2017-09-01 8:26 ` [PATCH] x86/idt: Fix the X86_TRAP_BP gate Ingo Molnar
2017-09-01 8:59 ` Thomas Gleixner
2017-09-01 9:09 ` [tip:x86/apic] " tip-bot for Ingo Molnar
2017-09-01 14:39 ` [PATCH] " Andrei Vagin
2017-08-28 6:47 ` [patch V3 38/44] x86/idt: Move regular trap init to tables Thomas Gleixner
2017-08-29 11:19 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 39/44] x86/idt: Move APIC gate initialization " Thomas Gleixner
2017-08-29 11:19 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 40/44] x86/idt: Move interrupt gate initialization to IDT code Thomas Gleixner
2017-08-29 11:20 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 41/44] x86/idt: Remove unused functions/inlines Thomas Gleixner
2017-08-29 11:20 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 42/44] x86/idt: Deinline setup functions Thomas Gleixner
2017-08-29 11:20 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 43/44] x86/idt: Simplify alloc_intr_gate Thomas Gleixner
2017-08-28 14:35 ` KY Srinivasan
2017-08-29 11:21 ` [tip:x86/apic] x86/idt: Simplify alloc_intr_gate() tip-bot for Thomas Gleixner
2017-08-28 6:47 ` [patch V3 44/44] x86/idt: Hide set_intr_gate() Thomas Gleixner
2017-08-29 11:21 ` [tip:x86/apic] " tip-bot for Thomas Gleixner
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=tip-85b77cdd8fbd163d65f340e3f6578c50031af960@git.kernel.org \
--to=tipbot@zytor.com \
--cc=bp@alien8.de \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).