xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
To: gleb@redhat.com, mingo@redhat.com, jeremy@goop.org,
	x86@kernel.org, konrad.wilk@oracle.com, hpa@zytor.com,
	pbonzini@redhat.com
Cc: gregkh@suse.de, kvm@vger.kernel.org, linux-doc@vger.kernel.org,
	peterz@infradead.org, drjones@redhat.com,
	virtualization@lists.linux-foundation.org, andi@firstfloor.org,
	xen-devel@lists.xensource.com,
	Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>,
	habanero@linux.vnet.ibm.com, riel@redhat.com,
	stefano.stabellini@eu.citrix.com, ouyang@cs.pitt.edu,
	avi.kivity@gmail.com, tglx@linutronix.de, chegu_vinod@hp.com,
	linux-kernel@vger.kernel.org, srivatsa.vaddagiri@gmail.com,
	attilio.rao@citrix.com, torvalds@linux-foundation.org
Subject: [PATCH RFC V11 7/18] x86/pvticketlock: Use callee-save for lock_spinning
Date: Mon, 22 Jul 2013 11:48:09 +0530	[thread overview]
Message-ID: <20130722061809.24737.51002.sendpatchset@codeblue> (raw)
In-Reply-To: <20130722061631.24737.75508.sendpatchset@codeblue>

x86/pvticketlock: Use callee-save for lock_spinning

From: Jeremy Fitzhardinge <jeremy@goop.org>

Although the lock_spinning calls in the spinlock code are on the
uncommon path, their presence can cause the compiler to generate many
more register save/restores in the function pre/postamble, which is in
the fast path.  To avoid this, convert it to using the pvops callee-save
calling convention, which defers all the save/restores until the actual
function is called, keeping the fastpath clean.

Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Attilio Rao <attilio.rao@citrix.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
---
 arch/x86/include/asm/paravirt.h       |    2 +-
 arch/x86/include/asm/paravirt_types.h |    2 +-
 arch/x86/kernel/paravirt-spinlocks.c  |    2 +-
 arch/x86/xen/spinlock.c               |    3 ++-
 4 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 040e72d..7131e12c 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -715,7 +715,7 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
 							__ticket_t ticket)
 {
-	PVOP_VCALL2(pv_lock_ops.lock_spinning, lock, ticket);
+	PVOP_VCALLEE2(pv_lock_ops.lock_spinning, lock, ticket);
 }
 
 static __always_inline void ____ticket_unlock_kick(struct arch_spinlock *lock,
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index d5deb6d..350d017 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -330,7 +330,7 @@ struct arch_spinlock;
 #include <asm/spinlock_types.h>
 
 struct pv_lock_ops {
-	void (*lock_spinning)(struct arch_spinlock *lock, __ticket_t ticket);
+	struct paravirt_callee_save lock_spinning;
 	void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
 };
 
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index c2e010e..4251c1d 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -9,7 +9,7 @@
 
 struct pv_lock_ops pv_lock_ops = {
 #ifdef CONFIG_SMP
-	.lock_spinning = paravirt_nop,
+	.lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
 	.unlock_kick = paravirt_nop,
 #endif
 };
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index ec9183b..b41872b 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -173,6 +173,7 @@ out:
 	local_irq_restore(flags);
 	spin_time_accum_blocked(start);
 }
+PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning);
 
 static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
 {
@@ -260,7 +261,7 @@ void __init xen_init_spinlocks(void)
 		return;
 	}
 
-	pv_lock_ops.lock_spinning = xen_lock_spinning;
+	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
 	pv_lock_ops.unlock_kick = xen_unlock_kick;
 }

  parent reply	other threads:[~2013-07-22  6:18 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-07-22  6:16 [PATCH RFC V11 0/18] Paravirtualized ticket spinlocks Raghavendra K T
2013-07-22  6:16 ` [PATCH RFC V11 1/18] x86/spinlock: Replace pv spinlocks with pv ticketlocks Raghavendra K T
2013-07-22  6:17 ` [PATCH RFC V11 2/18] x86/ticketlock: Don't inline _spin_unlock when using paravirt spinlocks Raghavendra K T
2013-07-22  6:17 ` [PATCH RFC V11 3/18] x86/ticketlock: Collapse a layer of functions Raghavendra K T
2013-07-22  6:17 ` [PATCH RFC V11 4/18] xen: Defer spinlock setup until boot CPU setup Raghavendra K T
2013-07-22  6:17 ` [PATCH RFC V11 5/18] xen/pvticketlock: Xen implementation for PV ticket locks Raghavendra K T
2013-07-22  6:17 ` [PATCH RFC V11 6/18] xen/pvticketlocks: Add xen_nopvspin parameter to disable xen pv ticketlocks Raghavendra K T
2013-07-22  6:18 ` Raghavendra K T [this message]
2013-07-22  6:18 ` [PATCH RFC V11 8/18] x86/pvticketlock: When paravirtualizing ticket locks, increment by 2 Raghavendra K T
2013-07-22  6:18 ` [PATCH RFC V11 9/18] jump_label: Split out rate limiting from jump_label.h Raghavendra K T
2013-07-22  6:18 ` [PATCH RFC V11 10/18] x86/ticketlock: Add slowpath logic Raghavendra K T
2013-07-22  6:19 ` [PATCH RFC V11 11/18] xen/pvticketlock: Allow interrupts to be enabled while blocking Raghavendra K T
2013-07-22  6:19 ` [PATCH RFC V11 12/18] kvm hypervisor : Add a hypercall to KVM hypervisor to support pv-ticketlocks Raghavendra K T
2013-07-22  6:19 ` [PATCH RFC V11 13/18] kvm : Fold pv_unhalt flag into GET_MP_STATE ioctl to aid migration Raghavendra K T
2013-07-22  6:20 ` [PATCH RFC V11 14/18] kvm guest : Add configuration support to enable debug information for KVM Guests Raghavendra K T
2013-07-22  6:20 ` [PATCH RFC V11 15/18] kvm : Paravirtual ticketlocks support for linux guests running on KVM hypervisor Raghavendra K T
2013-07-23 15:07   ` Gleb Natapov
2013-07-24  9:24     ` [PATCH RESEND " Raghavendra K T
2013-07-24  9:45     ` [PATCH " Raghavendra K T
2013-07-24 10:39       ` Gleb Natapov
2013-07-24 12:00         ` Raghavendra K T
2013-07-24 12:06           ` Gleb Natapov
2013-07-24 12:36             ` Raghavendra K T
2013-07-25  9:17               ` Raghavendra K T
2013-07-25  9:15                 ` Gleb Natapov
2013-07-25  9:38                   ` Raghavendra K T
2013-07-30 16:43                     ` Raghavendra K T
2013-07-31  6:24                       ` Gleb Natapov
2013-08-01  7:38                         ` Raghavendra K T
2013-08-01  7:45                           ` Gleb Natapov
2013-08-01  9:04                             ` Raghavendra K T
2013-08-02  3:22                               ` Raghavendra K T
2013-08-02  9:23                                 ` Ingo Molnar
2013-08-02  9:44                                   ` Raghavendra K T
2013-08-02  9:25                           ` Ingo Molnar
2013-08-02  9:54                             ` Gleb Natapov
2013-08-02 10:57                               ` Raghavendra K T
2013-08-05  9:46                               ` Ingo Molnar
2013-08-05 10:42                                 ` Raghavendra K T
     [not found]                                 ` <20130805095901.GL2258@redhat.com>
2013-08-05 13:52                                   ` Ingo Molnar
2013-08-05 14:05                                     ` Paolo Bonzini
2013-08-05 14:39                                       ` Raghavendra K T
2013-08-05 14:45                                         ` Paolo Bonzini
2013-08-05 15:37                                 ` Konrad Rzeszutek Wilk
2013-07-22  6:20 ` [PATCH RFC V11 16/18] kvm hypervisor : Simplify kvm_for_each_vcpu with kvm_irq_delivery_to_apic Raghavendra K T
2013-07-22  6:20 ` [PATCH RFC V11 17/18] Documentation/kvm : Add documentation on Hypercalls and features used for PV spinlock Raghavendra K T
2013-07-22  6:20 ` [PATCH RFC V11 18/18] kvm hypervisor: Add directed yield in vcpu block path Raghavendra K T
2013-07-22 19:36 ` [PATCH RFC V11 0/18] Paravirtualized ticket spinlocks Konrad Rzeszutek Wilk
2013-07-23  2:50   ` Raghavendra K T
2013-08-05 22:50 ` H. Peter Anvin
2013-08-06  2:50   ` Raghavendra K T

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=20130722061809.24737.51002.sendpatchset@codeblue \
    --to=raghavendra.kt@linux.vnet.ibm.com \
    --cc=andi@firstfloor.org \
    --cc=attilio.rao@citrix.com \
    --cc=avi.kivity@gmail.com \
    --cc=chegu_vinod@hp.com \
    --cc=drjones@redhat.com \
    --cc=gleb@redhat.com \
    --cc=gregkh@suse.de \
    --cc=habanero@linux.vnet.ibm.com \
    --cc=hpa@zytor.com \
    --cc=jeremy@goop.org \
    --cc=konrad.wilk@oracle.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=ouyang@cs.pitt.edu \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=riel@redhat.com \
    --cc=srivatsa.vaddagiri@gmail.com \
    --cc=stefano.stabellini@eu.citrix.com \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=x86@kernel.org \
    --cc=xen-devel@lists.xensource.com \
    /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).