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 1/18] x86/spinlock: Replace pv spinlocks with pv ticketlocks
Date: Mon, 22 Jul 2013 11:46:48 +0530 [thread overview]
Message-ID: <20130722061648.24737.6034.sendpatchset@codeblue> (raw)
In-Reply-To: <20130722061631.24737.75508.sendpatchset@codeblue>
x86/spinlock: Replace pv spinlocks with pv ticketlocks
From: Jeremy Fitzhardinge <jeremy@goop.org>
Rather than outright replacing the entire spinlock implementation in
order to paravirtualize it, keep the ticket lock implementation but add
a couple of pvops hooks on the slow patch (long spin on lock, unlocking
a contended lock).
Ticket locks have a number of nice properties, but they also have some
surprising behaviours in virtual environments. They enforce a strict
FIFO ordering on cpus trying to take a lock; however, if the hypervisor
scheduler does not schedule the cpus in the correct order, the system can
waste a huge amount of time spinning until the next cpu can take the lock.
(See Thomas Friebel's talk "Prevent Guests from Spinning Around"
http://www.xen.org/files/xensummitboston08/LHP.pdf for more details.)
To address this, we add two hooks:
- __ticket_spin_lock which is called after the cpu has been
spinning on the lock for a significant number of iterations but has
failed to take the lock (presumably because the cpu holding the lock
has been descheduled). The lock_spinning pvop is expected to block
the cpu until it has been kicked by the current lock holder.
- __ticket_spin_unlock, which on releasing a contended lock
(there are more cpus with tail tickets), it looks to see if the next
cpu is blocked and wakes it if so.
When compiled with CONFIG_PARAVIRT_SPINLOCKS disabled, a set of stub
functions causes all the extra code to go away.
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>
[ Raghavendra: Changed SPIN_THRESHOLD ]
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
---
arch/x86/include/asm/paravirt.h | 32 ++++----------------
arch/x86/include/asm/paravirt_types.h | 10 ++----
arch/x86/include/asm/spinlock.h | 53 +++++++++++++++++++++++++++------
arch/x86/include/asm/spinlock_types.h | 4 --
arch/x86/kernel/paravirt-spinlocks.c | 15 +--------
arch/x86/xen/spinlock.c | 8 ++++-
6 files changed, 61 insertions(+), 61 deletions(-)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index cfdc9ee..040e72d 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -712,36 +712,16 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
-static inline int arch_spin_is_locked(struct arch_spinlock *lock)
+static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
+ __ticket_t ticket)
{
- return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock);
+ PVOP_VCALL2(pv_lock_ops.lock_spinning, lock, ticket);
}
-static inline int arch_spin_is_contended(struct arch_spinlock *lock)
+static __always_inline void ____ticket_unlock_kick(struct arch_spinlock *lock,
+ __ticket_t ticket)
{
- return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
-}
-#define arch_spin_is_contended arch_spin_is_contended
-
-static __always_inline void arch_spin_lock(struct arch_spinlock *lock)
-{
- PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
-}
-
-static __always_inline void arch_spin_lock_flags(struct arch_spinlock *lock,
- unsigned long flags)
-{
- PVOP_VCALL2(pv_lock_ops.spin_lock_flags, lock, flags);
-}
-
-static __always_inline int arch_spin_trylock(struct arch_spinlock *lock)
-{
- return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
-}
-
-static __always_inline void arch_spin_unlock(struct arch_spinlock *lock)
-{
- PVOP_VCALL1(pv_lock_ops.spin_unlock, lock);
+ PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket);
}
#endif
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0db1fca..d5deb6d 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -327,13 +327,11 @@ struct pv_mmu_ops {
};
struct arch_spinlock;
+#include <asm/spinlock_types.h>
+
struct pv_lock_ops {
- int (*spin_is_locked)(struct arch_spinlock *lock);
- int (*spin_is_contended)(struct arch_spinlock *lock);
- void (*spin_lock)(struct arch_spinlock *lock);
- void (*spin_lock_flags)(struct arch_spinlock *lock, unsigned long flags);
- int (*spin_trylock)(struct arch_spinlock *lock);
- void (*spin_unlock)(struct arch_spinlock *lock);
+ void (*lock_spinning)(struct arch_spinlock *lock, __ticket_t ticket);
+ void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
};
/* This contains all the paravirt structures: we get a convenient
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 33692ea..4d54244 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -34,6 +34,35 @@
# define UNLOCK_LOCK_PREFIX
#endif
+/* How long a lock should spin before we consider blocking */
+#define SPIN_THRESHOLD (1 << 15)
+
+#ifndef CONFIG_PARAVIRT_SPINLOCKS
+
+static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
+ __ticket_t ticket)
+{
+}
+
+static __always_inline void ____ticket_unlock_kick(struct arch_spinlock *lock,
+ __ticket_t ticket)
+{
+}
+
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+
+/*
+ * If a spinlock has someone waiting on it, then kick the appropriate
+ * waiting cpu.
+ */
+static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock,
+ __ticket_t next)
+{
+ if (unlikely(lock->tickets.tail != next))
+ ____ticket_unlock_kick(lock, next);
+}
+
/*
* Ticket locks are conceptually two parts, one indicating the current head of
* the queue, and the other indicating the current tail. The lock is acquired
@@ -47,19 +76,24 @@
* in the high part, because a wide xadd increment of the low part would carry
* up and contaminate the high part.
*/
-static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
+static __always_inline void __ticket_spin_lock(struct arch_spinlock *lock)
{
register struct __raw_tickets inc = { .tail = 1 };
inc = xadd(&lock->tickets, inc);
for (;;) {
- if (inc.head == inc.tail)
- break;
- cpu_relax();
- inc.head = ACCESS_ONCE(lock->tickets.head);
+ unsigned count = SPIN_THRESHOLD;
+
+ do {
+ if (inc.head == inc.tail)
+ goto out;
+ cpu_relax();
+ inc.head = ACCESS_ONCE(lock->tickets.head);
+ } while (--count);
+ __ticket_lock_spinning(lock, inc.tail);
}
- barrier(); /* make sure nothing creeps before the lock is taken */
+out: barrier(); /* make sure nothing creeps before the lock is taken */
}
static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
@@ -78,7 +112,10 @@ static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
{
+ __ticket_t next = lock->tickets.head + 1;
+
__add(&lock->tickets.head, 1, UNLOCK_LOCK_PREFIX);
+ __ticket_unlock_kick(lock, next);
}
static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
@@ -95,8 +132,6 @@ static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
return (__ticket_t)(tmp.tail - tmp.head) > 1;
}
-#ifndef CONFIG_PARAVIRT_SPINLOCKS
-
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
return __ticket_spin_is_locked(lock);
@@ -129,8 +164,6 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
arch_spin_lock(lock);
}
-#endif /* CONFIG_PARAVIRT_SPINLOCKS */
-
static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
{
while (arch_spin_is_locked(lock))
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index ad0ad07..83fd3c7 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -1,10 +1,6 @@
#ifndef _ASM_X86_SPINLOCK_TYPES_H
#define _ASM_X86_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
#include <linux/types.h>
#if (CONFIG_NR_CPUS < 256)
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 676b8c7..c2e010e 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -7,21 +7,10 @@
#include <asm/paravirt.h>
-static inline void
-default_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
-{
- arch_spin_lock(lock);
-}
-
struct pv_lock_ops pv_lock_ops = {
#ifdef CONFIG_SMP
- .spin_is_locked = __ticket_spin_is_locked,
- .spin_is_contended = __ticket_spin_is_contended,
-
- .spin_lock = __ticket_spin_lock,
- .spin_lock_flags = default_spin_lock_flags,
- .spin_trylock = __ticket_spin_trylock,
- .spin_unlock = __ticket_spin_unlock,
+ .lock_spinning = paravirt_nop,
+ .unlock_kick = paravirt_nop,
#endif
};
EXPORT_SYMBOL(pv_lock_ops);
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index a40f850..0454bcb 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -139,6 +139,9 @@ struct xen_spinlock {
xen_spinners_t spinners; /* count of waiting cpus */
};
+static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
+
+#if 0
static int xen_spin_is_locked(struct arch_spinlock *lock)
{
struct xen_spinlock *xl = (struct xen_spinlock *)lock;
@@ -167,7 +170,6 @@ static int xen_spin_trylock(struct arch_spinlock *lock)
}
static DEFINE_PER_CPU(char *, irq_name);
-static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
static DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners);
/*
@@ -354,6 +356,7 @@ static void xen_spin_unlock(struct arch_spinlock *lock)
if (unlikely(xl->spinners))
xen_spin_unlock_slow(xl);
}
+#endif
static irqreturn_t dummy_handler(int irq, void *dev_id)
{
@@ -418,13 +421,14 @@ void __init xen_init_spinlocks(void)
return;
BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t));
-
+#if 0
pv_lock_ops.spin_is_locked = xen_spin_is_locked;
pv_lock_ops.spin_is_contended = xen_spin_is_contended;
pv_lock_ops.spin_lock = xen_spin_lock;
pv_lock_ops.spin_lock_flags = xen_spin_lock_flags;
pv_lock_ops.spin_trylock = xen_spin_trylock;
pv_lock_ops.spin_unlock = xen_spin_unlock;
+#endif
}
#ifdef CONFIG_XEN_DEBUG_FS
next prev parent reply other threads:[~2013-07-22 6:16 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 ` Raghavendra K T [this message]
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 ` [PATCH RFC V11 7/18] x86/pvticketlock: Use callee-save for lock_spinning Raghavendra K T
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=20130722061648.24737.6034.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).