From: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
To: "H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@elte.hu>
Cc: the arch/x86 maintainers <x86@kernel.org>,
KVM <kvm@vger.kernel.org>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
Peter Zijlstra <peterz@infradead.org>,
Stefano Stabellini <stefano.stabellini@eu.citrix.com>,
LKML <linux-kernel@vger.kernel.org>,
Virtualization <virtualization@lists.linux-foundation.org>,
Andi Kleen <andi@firstfloor.org>, Avi Kivity <avi@redhat.com>,
Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>,
Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>,
Attilio Rao <attilio.rao@citrix.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
Xen Devel <xen-devel@lists.xensource.com>,
Stephan Diestelhorst <stephan.diestelhorst@amd.com>
Subject: [PATCH RFC V6 7/11] x86/pvticketlock: use callee-save for lock_spinning
Date: Wed, 21 Mar 2012 15:51:59 +0530 [thread overview]
Message-ID: <20120321102159.473.94357.sendpatchset@codeblue.in.ibm.com> (raw)
In-Reply-To: <20120321102041.473.61069.sendpatchset@codeblue.in.ibm.com>
From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
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.fitzhardinge@citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.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 0fa4553..4343419 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -753,7 +753,7 @@ 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 005e24d..5e0c138 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 5dce49d..176a554 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)
{
@@ -232,7 +233,7 @@ 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;
}
WARNING: multiple messages have this Message-ID (diff)
From: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
To: "H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@elte.hu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
Peter Zijlstra <peterz@infradead.org>,
the arch/x86 maintainers <x86@kernel.org>,
LKML <linux-kernel@vger.kernel.org>, Avi Kivity <avi@redhat.com>,
Marcelo Tosatti <mtosatti@redhat.com>, KVM <kvm@vger.kernel.org>,
Andi Kleen <andi@firstfloor.org>,
Xen Devel <xen-devel@lists.xensource.com>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
Virtualization <virtualization@lists.linux-foundation.org>,
Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>,
Stephan Diestelhorst <stephan.diestelhorst@amd.com>,
Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>,
Stefano Stabellini <stefano.stabellini@eu.citrix.com>,
Attilio Rao <attilio.rao@citrix.com>
Subject: [PATCH RFC V6 7/11] x86/pvticketlock: use callee-save for lock_spinning
Date: Wed, 21 Mar 2012 15:51:59 +0530 [thread overview]
Message-ID: <20120321102159.473.94357.sendpatchset@codeblue.in.ibm.com> (raw)
In-Reply-To: <20120321102041.473.61069.sendpatchset@codeblue.in.ibm.com>
From: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
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.fitzhardinge@citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.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 0fa4553..4343419 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -753,7 +753,7 @@ 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 005e24d..5e0c138 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 5dce49d..176a554 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)
{
@@ -232,7 +233,7 @@ 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;
}
next prev parent reply other threads:[~2012-03-21 10:21 UTC|newest]
Thread overview: 113+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-03-21 10:20 [PATCH RFC V6 0/11] Paravirtualized ticketlocks Raghavendra K T
2012-03-21 10:20 ` Raghavendra K T
2012-03-21 10:20 ` [PATCH RFC V6 1/11] x86/spinlock: replace pv spinlocks with pv ticketlocks Raghavendra K T
2012-03-21 10:20 ` Raghavendra K T
2012-03-21 13:04 ` Attilio Rao
2012-03-21 13:22 ` Stephan Diestelhorst
2012-03-21 13:22 ` Stephan Diestelhorst
2012-03-21 13:49 ` Attilio Rao
2012-03-21 14:25 ` Stephan Diestelhorst
2012-03-21 14:25 ` Stephan Diestelhorst
2012-03-21 14:33 ` Attilio Rao
2012-03-21 14:33 ` Attilio Rao
2012-03-21 14:49 ` Raghavendra K T
2012-03-21 14:49 ` Raghavendra K T
2012-03-21 13:49 ` Attilio Rao
2012-03-21 13:04 ` Attilio Rao
2012-03-21 10:21 ` [PATCH RFC V6 2/11] x86/ticketlock: don't inline _spin_unlock when using paravirt spinlocks Raghavendra K T
2012-03-21 17:13 ` Linus Torvalds
2012-03-21 17:13 ` Linus Torvalds
2012-03-22 10:06 ` Raghavendra K T
2012-03-22 10:06 ` Raghavendra K T
2012-03-22 10:06 ` Raghavendra K T
2012-03-21 10:21 ` Raghavendra K T
2012-03-21 10:21 ` [PATCH RFC V6 3/11] x86/ticketlock: collapse a layer of functions Raghavendra K T
2012-03-21 10:21 ` Raghavendra K T
2012-03-21 10:21 ` [PATCH RFC V6 4/11] xen: defer spinlock setup until boot CPU setup Raghavendra K T
2012-03-21 10:21 ` Raghavendra K T
2012-03-21 10:21 ` [PATCH RFC V6 5/11] xen/pvticketlock: Xen implementation for PV ticket locks Raghavendra K T
2012-03-21 10:21 ` Raghavendra K T
2012-03-21 10:21 ` [PATCH RFC V6 6/11] xen/pvticketlocks: add xen_nopvspin parameter to disable xen pv ticketlocks Raghavendra K T
2012-03-21 10:21 ` Raghavendra K T
2012-03-21 10:21 ` Raghavendra K T [this message]
2012-03-21 10:21 ` [PATCH RFC V6 7/11] x86/pvticketlock: use callee-save for lock_spinning Raghavendra K T
2012-03-21 10:22 ` [PATCH RFC V6 8/11] x86/pvticketlock: when paravirtualizing ticket locks, increment by 2 Raghavendra K T
2012-03-21 10:22 ` Raghavendra K T
2012-03-21 10:22 ` Raghavendra K T
2012-03-21 10:22 ` [PATCH RFC V6 9/11] x86/ticketlock: add slowpath logic Raghavendra K T
2012-03-21 10:22 ` Raghavendra K T
2012-03-21 10:22 ` [PATCH RFC V6 10/11] xen/pvticketlock: allow interrupts to be enabled while blocking Raghavendra K T
2012-03-21 10:22 ` Raghavendra K T
2012-03-21 10:22 ` [PATCH RFC V6 11/11] xen: enable PV ticketlocks on HVM Xen Raghavendra K T
2012-03-21 10:22 ` Raghavendra K T
2012-03-26 14:25 ` [PATCH RFC V6 0/11] Paravirtualized ticketlocks Avi Kivity
2012-03-26 14:25 ` Avi Kivity
2012-03-27 7:37 ` Raghavendra K T
2012-03-27 7:37 ` Raghavendra K T
2012-03-28 16:09 ` Alan Meadows
2012-03-28 18:21 ` Raghavendra K T
2012-03-28 18:21 ` Raghavendra K T
2012-03-29 9:58 ` Avi Kivity
2012-03-29 9:58 ` Avi Kivity
2012-03-29 18:03 ` Raghavendra K T
2012-03-29 18:03 ` Raghavendra K T
2012-03-30 10:07 ` Raghavendra K T
2012-03-30 10:07 ` Raghavendra K T
2012-04-01 13:18 ` Avi Kivity
2012-04-01 13:18 ` Avi Kivity
2012-04-01 13:48 ` Raghavendra K T
2012-04-01 13:48 ` Raghavendra K T
2012-04-01 13:53 ` Avi Kivity
2012-04-01 13:53 ` Avi Kivity
2012-04-01 13:56 ` Raghavendra K T
2012-04-01 13:56 ` Raghavendra K T
2012-04-02 9:51 ` Raghavendra K T
2012-04-02 9:51 ` Raghavendra K T
2012-04-02 9:51 ` Raghavendra K T
2012-04-02 12:15 ` Raghavendra K T
2012-04-02 12:15 ` Raghavendra K T
2012-04-05 9:01 ` Avi Kivity
2012-04-05 9:01 ` Avi Kivity
2012-04-05 10:40 ` Raghavendra K T
2012-04-05 10:40 ` Raghavendra K T
2012-04-05 8:43 ` Raghavendra K T
2012-04-05 8:43 ` Raghavendra K T
2012-03-28 16:37 ` Alan Meadows
2012-03-30 20:26 ` H. Peter Anvin
2012-03-30 20:26 ` H. Peter Anvin
2012-03-30 22:07 ` Thomas Gleixner
2012-03-30 22:07 ` Thomas Gleixner
2012-03-30 22:18 ` Andi Kleen
2012-03-30 22:18 ` Andi Kleen
2012-03-30 23:04 ` Thomas Gleixner
2012-03-30 23:04 ` Thomas Gleixner
2012-03-31 0:08 ` Andi Kleen
2012-03-31 0:08 ` Andi Kleen
2012-03-31 8:11 ` Ingo Molnar
2012-03-31 8:11 ` Ingo Molnar
2012-03-31 4:07 ` Srivatsa Vaddagiri
2012-03-31 4:07 ` Srivatsa Vaddagiri
2012-03-31 4:09 ` Srivatsa Vaddagiri
2012-03-31 4:09 ` Srivatsa Vaddagiri
2012-04-16 15:44 ` Konrad Rzeszutek Wilk
2012-04-16 15:44 ` Konrad Rzeszutek Wilk
2012-04-16 16:36 ` [Xen-devel] " Ian Campbell
2012-04-16 16:36 ` Ian Campbell
2012-04-16 16:42 ` Jeremy Fitzhardinge
2012-04-16 16:42 ` Jeremy Fitzhardinge
2012-04-17 2:54 ` Srivatsa Vaddagiri
2012-04-17 2:54 ` Srivatsa Vaddagiri
2012-04-01 13:31 ` Avi Kivity
2012-04-01 13:31 ` Avi Kivity
2012-04-02 9:26 ` Thomas Gleixner
2012-04-02 9:26 ` Thomas Gleixner
2012-04-05 9:15 ` Avi Kivity
2012-04-05 9:15 ` Avi Kivity
2012-04-02 4:36 ` [Xen-devel] " Juergen Gross
2012-04-02 4:36 ` Juergen Gross
2012-04-02 9:42 ` Ian Campbell
2012-04-02 9:42 ` Ian Campbell
2012-04-11 1:29 ` Marcelo Tosatti
2012-04-11 1:29 ` Marcelo Tosatti
2012-03-31 0:51 ` Raghavendra K T
2012-03-31 0:51 ` 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=20120321102159.473.94357.sendpatchset@codeblue.in.ibm.com \
--to=raghavendra.kt@linux.vnet.ibm.com \
--cc=andi@firstfloor.org \
--cc=attilio.rao@citrix.com \
--cc=avi@redhat.com \
--cc=hpa@zytor.com \
--cc=jeremy.fitzhardinge@citrix.com \
--cc=konrad.wilk@oracle.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=peterz@infradead.org \
--cc=stefano.stabellini@eu.citrix.com \
--cc=stephan.diestelhorst@amd.com \
--cc=torvalds@linux-foundation.org \
--cc=vatsa@linux.vnet.ibm.com \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.