Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1722397

[RFC PATCH v2 1/7] x86/paravirt: Add pv_idle_ops to paravirt ops

From Yang Zhang <yang.zhang.wz@gmail.com>
Newsgroups linux.kernel
Subject [RFC PATCH v2 1/7] x86/paravirt: Add pv_idle_ops to paravirt ops
Date 2017-08-29 13:50 +0200
Message-ID <ujNbQ-25K-11@gated-at.bofh.it> (permalink)
References <ujNbP-25K-5@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

So far, pv_idle_ops.poll is the only ops for pv_idle. .poll is called in
idle path which will polling for a while before we enter the real idle
state.

In virtualization, idle path includes several heavy operations
includes timer access(LAPIC timer or TSC deadline timer) which will hurt
performance especially for latency intensive workload like message
passing task. The cost is mainly come from the vmexit which is a
hardware context switch between VM and hypervisor. Our solution is to
poll for a while and do not enter real idle path if we can get the
schedule event during polling.

Poll may cause the CPU waste so we adopt a smart polling mechanism to
reduce the useless poll.

Signed-off-by: Yang Zhang <yang.zhang.wz@gmail.com>
Signed-off-by: Quan Xu <quan.xu0@gmail.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: Alok Kataria <akataria@vmware.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: virtualization@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org
---
 arch/x86/include/asm/paravirt.h       | 5 +++++
 arch/x86/include/asm/paravirt_types.h | 6 ++++++
 arch/x86/kernel/paravirt.c            | 6 ++++++
 3 files changed, 17 insertions(+)

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 9ccac19..6d46760 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -202,6 +202,11 @@ static inline unsigned long long paravirt_read_pmc(int counter)
 
 #define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
 
+static inline void paravirt_idle_poll(void)
+{
+	PVOP_VCALL0(pv_idle_ops.poll);
+}
+
 static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 {
 	PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 9ffc36b..cf45726 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -324,6 +324,10 @@ struct pv_lock_ops {
 	struct paravirt_callee_save vcpu_is_preempted;
 } __no_randomize_layout;
 
+struct pv_idle_ops {
+	void (*poll)(void);
+} __no_randomize_layout;
+
 /* This contains all the paravirt structures: we get a convenient
  * number for each function using the offset which we use to indicate
  * what to patch. */
@@ -334,6 +338,7 @@ struct paravirt_patch_template {
 	struct pv_irq_ops pv_irq_ops;
 	struct pv_mmu_ops pv_mmu_ops;
 	struct pv_lock_ops pv_lock_ops;
+	struct pv_idle_ops pv_idle_ops;
 } __no_randomize_layout;
 
 extern struct pv_info pv_info;
@@ -343,6 +348,7 @@ struct paravirt_patch_template {
 extern struct pv_irq_ops pv_irq_ops;
 extern struct pv_mmu_ops pv_mmu_ops;
 extern struct pv_lock_ops pv_lock_ops;
+extern struct pv_idle_ops pv_idle_ops;
 
 #define PARAVIRT_PATCH(x)					\
 	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index bc0a849..1b5b247 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -128,6 +128,7 @@ static void *get_call_destination(u8 type)
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 		.pv_lock_ops = pv_lock_ops,
 #endif
+		.pv_idle_ops = pv_idle_ops,
 	};
 	return *((void **)&tmpl + type);
 }
@@ -312,6 +313,10 @@ struct pv_time_ops pv_time_ops = {
 	.steal_clock = native_steal_clock,
 };
 
+struct pv_idle_ops pv_idle_ops = {
+	.poll = paravirt_nop,
+};
+
 __visible struct pv_irq_ops pv_irq_ops = {
 	.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
 	.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
@@ -471,3 +476,4 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
 EXPORT_SYMBOL    (pv_mmu_ops);
 EXPORT_SYMBOL_GPL(pv_info);
 EXPORT_SYMBOL    (pv_irq_ops);
+EXPORT_SYMBOL    (pv_idle_ops);
-- 
1.8.3.1

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[RFC PATCH v2 0/7] x86/idle: add halt poll support Yang Zhang <yang.zhang.wz@gmail.com> - 2017-08-29 13:50 +0200
  [RFC PATCH v2 3/7] sched/idle: Add poll before enter real idle path Yang Zhang <yang.zhang.wz@gmail.com> - 2017-08-29 13:50 +0200
    Re: [RFC PATCH v2 3/7] sched/idle: Add poll before enter real idle  path Peter Zijlstra <peterz@infradead.org> - 2017-08-29 14:50 +0200
      Re: [RFC PATCH v2 3/7] sched/idle: Add poll before enter real idle  path Quan Xu <quan.xu0@gmail.com> - 2017-09-01 08:00 +0200
    Re: [RFC PATCH v2 3/7] sched/idle: Add poll before enter real idle  path Borislav Petkov <bp@alien8.de> - 2017-08-29 16:40 +0200
      Re: [RFC PATCH v2 3/7] sched/idle: Add poll before enter real idle  path Quan Xu <quan.xu0@gmail.com> - 2017-09-01 09:00 +0200
  [RFC PATCH v2 1/7] x86/paravirt: Add pv_idle_ops to paravirt ops Yang Zhang <yang.zhang.wz@gmail.com> - 2017-08-29 13:50 +0200
    Re: [RFC PATCH v2 1/7] x86/paravirt: Add pv_idle_ops to paravirt ops Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> - 2017-08-29 16:10 +0200
      Re: [RFC PATCH v2 1/7] x86/paravirt: Add pv_idle_ops to paravirt ops Juergen Gross <jgross@suse.com> - 2017-08-30 09:40 +0200
      Re: [RFC PATCH v2 1/7] x86/paravirt: Add pv_idle_ops to paravirt ops Yang Zhang <yang.zhang.wz@gmail.com> - 2017-09-01 09:00 +0200
  [RFC PATCH v2 5/7] Documentation: Add three sysctls for smart idle poll Yang Zhang <yang.zhang.wz@gmail.com> - 2017-08-29 13:50 +0200
    Re: [RFC PATCH v2 5/7] Documentation: Add three sysctls for smart  idle poll "Luis R. Rodriguez" <mcgrof@kernel.org> - 2017-08-29 19:30 +0200
  [RFC PATCH v2 2/7] KVM guest: register kvm_idle_poll for pv_idle_ops Yang Zhang <yang.zhang.wz@gmail.com> - 2017-08-29 13:50 +0200
  [RFC PATCH v2 4/7] x86/paravirt: Add update in x86/paravirt pv_idle_ops Yang Zhang <yang.zhang.wz@gmail.com> - 2017-08-29 13:50 +0200
  [RFC PATCH v2 7/7] sched/idle: update poll time when wakeup from idle Yang Zhang <yang.zhang.wz@gmail.com> - 2017-08-29 13:50 +0200
    Re: [RFC PATCH v2 7/7] sched/idle: update poll time when wakeup from  idle Peter Zijlstra <peterz@infradead.org> - 2017-08-29 14:50 +0200
      Re: [RFC PATCH v2 7/7] sched/idle: update poll time when wakeup from  idle Yang Zhang <yang.zhang.wz@gmail.com> - 2017-09-01 09:40 +0200
  Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support Alexander Graf <agraf@suse.de> - 2017-08-29 14:00 +0200
    Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support Yang Zhang <yang.zhang.wz@gmail.com> - 2017-09-01 08:30 +0200
  Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support Andi Kleen <andi@firstfloor.org> - 2017-08-29 15:10 +0200
  Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support Wanpeng Li <kernellwp@gmail.com> - 2017-08-29 16:10 +0200
    Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> - 2017-08-29 16:30 +0200
    Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support "Michael S. Tsirkin" <mst@redhat.com> - 2017-08-29 16:40 +0200
    Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support Yang Zhang <yang.zhang.wz@gmail.com> - 2017-09-01 08:40 +0200
      Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support Wanpeng Li <kernellwp@gmail.com> - 2017-09-01 09:00 +0200
    Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support Yang Zhang <yang.zhang.wz@gmail.com> - 2017-09-01 08:50 +0200
      Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support Wanpeng Li <kernellwp@gmail.com> - 2017-09-01 09:00 +0200
        Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support Yang Zhang <yang.zhang.wz@gmail.com> - 2017-09-01 10:00 +0200
  Re: [RFC PATCH v2 0/7] x86/idle: add halt poll support "Michael S. Tsirkin" <mst@redhat.com> - 2017-08-29 17:00 +0200

csiph-web