linux-kernel - [RFC PATCH v2 1/7] x86/paravirt: Add pv_idle

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1504007201-12904-2-git-send-email-yang.zhang.wz@gmail.com>
Date:   Tue, 29 Aug 2017 11:46:35 +0000
From:   Yang Zhang <yang.zhang.wz@...il.com>
To:     linux-kernel@...r.kernel.org
Cc:     kvm@...r.kernel.org, wanpeng.li@...mail.com, mst@...hat.com,
        pbonzini@...hat.com, tglx@...utronix.de, rkrcmar@...hat.com,
        dmatlack@...gle.com, agraf@...e.de, peterz@...radead.org,
        linux-doc@...r.kernel.org, Yang Zhang <yang.zhang.wz@...il.com>,
        Quan Xu <quan.xu0@...il.com>,
        Jeremy Fitzhardinge <jeremy@...p.org>,
        Chris Wright <chrisw@...s-sol.org>,
        Alok Kataria <akataria@...are.com>,
        Rusty Russell <rusty@...tcorp.com.au>,
        Ingo Molnar <mingo@...hat.com>,
        "H. Peter Anvin" <hpa@...or.com>, x86@...nel.org,
        Andy Lutomirski <luto@...nel.org>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Pan Xinhui <xinhui.pan@...ux.vnet.ibm.com>,
        Kees Cook <keescook@...omium.org>,
        virtualization@...ts.linux-foundation.org
Subject: [RFC PATCH v2 1/7] x86/paravirt: Add pv_idle_ops to paravirt ops

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@...il.com>
Signed-off-by: Quan Xu <quan.xu0@...il.com>
Cc: Jeremy Fitzhardinge <jeremy@...p.org>
Cc: Chris Wright <chrisw@...s-sol.org>
Cc: Alok Kataria <akataria@...are.com>
Cc: Rusty Russell <rusty@...tcorp.com.au>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: "H. Peter Anvin" <hpa@...or.com>
Cc: x86@...nel.org
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Andy Lutomirski <luto@...nel.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Cc: Pan Xinhui <xinhui.pan@...ux.vnet.ibm.com>
Cc: Kees Cook <keescook@...omium.org>
Cc: virtualization@...ts.linux-foundation.org
Cc: linux-kernel@...r.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