AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-25 20:55:29 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
a7b9f671f2
linux_dsm_epyc7002/arch/powerpc/include/asm/spinlock.h
Michael Ellerman 51d7d5205d powerpc: Add smp_mb() to arch_spin_is_locked() 
The kernel defines the function spin_is_locked(), which can be used to
check if a spinlock is currently locked.

Using spin_is_locked() on a lock you don't hold is obviously racy. That
is, even though you may observe that the lock is unlocked, it may become
locked at any time.

There is (at least) one exception to that, which is if two locks are
used as a pair, and the holder of each checks the status of the other
before doing any update.

Assuming *A and *B are two locks, and *COUNTER is a shared non-atomic
value:

The first CPU does:

	spin_lock(*A)

	if spin_is_locked(*B)
		# nothing
	else
		smp_mb()
		LOAD r = *COUNTER
		r++
		STORE *COUNTER = r

	spin_unlock(*A)

And the second CPU does:

	spin_lock(*B)

	if spin_is_locked(*A)
		# nothing
	else
		smp_mb()
		LOAD r = *COUNTER
		r++
		STORE *COUNTER = r

	spin_unlock(*B)

Although this is a strange locking construct, it should work.

It seems to be understood, but not documented, that spin_is_locked() is
not a memory barrier, so in the examples above and below the caller
inserts its own memory barrier before acting on the result of
spin_is_locked().

For now we assume spin_is_locked() is implemented as below, and we break
it out in our examples:

	bool spin_is_locked(*LOCK) {
		LOAD l = *LOCK
		return l.locked
	}

Our intuition is that there should be no problem even if the two code
sequences run simultaneously such as:

	CPU 0			CPU 1
	==================================================
	spin_lock(*A)		spin_lock(*B)
	LOAD b = *B		LOAD a = *A
	if b.locked # true	if a.locked # true
	# nothing		# nothing
	spin_unlock(*A)		spin_unlock(*B)

If one CPU gets the lock before the other then it will do the update and
the other CPU will back off:

	CPU 0			CPU 1
	==================================================
	spin_lock(*A)
	LOAD b = *B
				spin_lock(*B)
	if b.locked # false	LOAD a = *A
	else			if a.locked # true
	smp_mb()		# nothing
	LOAD r1 = *COUNTER	spin_unlock(*B)
	r1++
	STORE *COUNTER = r1
	spin_unlock(*A)

However in reality spin_lock() itself is not indivisible. On powerpc we
implement it as a load-and-reserve and store-conditional.

Ignoring the retry logic for the lost reservation case, it boils down to:
	spin_lock(*LOCK) {
		LOAD l = *LOCK
		l.locked = true
		STORE *LOCK = l
		ACQUIRE_BARRIER
	}

The ACQUIRE_BARRIER is required to give spin_lock() ACQUIRE semantics as
defined in memory-barriers.txt:

     This acts as a one-way permeable barrier.  It guarantees that all
     memory operations after the ACQUIRE operation will appear to happen
     after the ACQUIRE operation with respect to the other components of
     the system.

On modern powerpc systems we use lwsync for ACQUIRE_BARRIER. lwsync is
also know as "lightweight sync", or "sync 1".

As described in Power ISA v2.07 section B.2.1.1, in this scenario the
lwsync is not the barrier itself. It instead causes the LOAD of *LOCK to
act as the barrier, preventing any loads or stores in the locked region
from occurring prior to the load of *LOCK.

Whether this behaviour is in accordance with the definition of ACQUIRE
semantics in memory-barriers.txt is open to discussion, we may switch to
a different barrier in future.

What this means in practice is that the following can occur:

	CPU 0			CPU 1
	==================================================
	LOAD a = *A 		LOAD b = *B
	a.locked = true		b.locked = true
	LOAD b = *B		LOAD a = *A
	STORE *A = a		STORE *B = b
	if b.locked # false	if a.locked # false
	else			else
	smp_mb()		smp_mb()
	LOAD r1 = *COUNTER	LOAD r2 = *COUNTER
	r1++			r2++
	STORE *COUNTER = r1
				STORE *COUNTER = r2	# Lost update
	spin_unlock(*A)		spin_unlock(*B)

That is, the load of *B can occur prior to the store that makes *A
visibly locked. And similarly for CPU 1. The result is both CPUs hold
their lock and believe the other lock is unlocked.

The easiest fix for this is to add a full memory barrier to the start of
spin_is_locked(), so adding to our previous definition would give us:

	bool spin_is_locked(*LOCK) {
		smp_mb()
		LOAD l = *LOCK
		return l.locked
	}

The new barrier orders the store to the lock we are locking vs the load
of the other lock:

	CPU 0			CPU 1
	==================================================
	LOAD a = *A 		LOAD b = *B
	a.locked = true		b.locked = true
	STORE *A = a		STORE *B = b
	smp_mb()		smp_mb()
	LOAD b = *B		LOAD a = *A
	if b.locked # true	if a.locked # true
	# nothing		# nothing
	spin_unlock(*A)		spin_unlock(*B)

Although the above example is theoretical, there is code similar to this
example in sem_lock() in ipc/sem.c. This commit in addition to the next
commit appears to be a fix for crashes we are seeing in that code where
we believe this race happens in practice.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-08-13 15:13:26 +10:00

315 lines
7.2 KiB
C
Raw Blame History

#ifndef __ASM_SPINLOCK_H
#define __ASM_SPINLOCK_H
#ifdef __KERNEL__
/*
* Simple spin lock operations.
*
* Copyright (C) 2001-2004 Paul Mackerras <paulus@au.ibm.com>, IBM
* Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
* Copyright (C) 2002 Dave Engebretsen <engebret@us.ibm.com>, IBM
* Rework to support virtual processors
*
* Type of int is used as a full 64b word is not necessary.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* (the type definitions are in asm/spinlock_types.h)
*/
#include <linux/irqflags.h>
#ifdef CONFIG_PPC64
#include <asm/paca.h>
#include <asm/hvcall.h>
#endif
#include <asm/asm-compat.h>
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */
#ifdef CONFIG_PPC64
/* use 0x800000yy when locked, where yy == CPU number */
#ifdef __BIG_ENDIAN__
#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token))
#else
#define LOCK_TOKEN (*(u32 *)(&get_paca()->paca_index))
#endif
#else
#define LOCK_TOKEN 1
#endif
#if defined(CONFIG_PPC64) && defined(CONFIG_SMP)
#define CLEAR_IO_SYNC (get_paca()->io_sync = 0)
#define SYNC_IO do { \
if (unlikely(get_paca()->io_sync)) { \
mb(); \
get_paca()->io_sync = 0; \
} \
} while (0)
#else
#define CLEAR_IO_SYNC
#define SYNC_IO
#endif
static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
{
return lock.slock == 0;
}
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
smp_mb();
return !arch_spin_value_unlocked(*lock);
}
/*
* This returns the old value in the lock, so we succeeded
* in getting the lock if the return value is 0.
*/
static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock)
{
unsigned long tmp, token;
token = LOCK_TOKEN;
__asm__ __volatile__(
"1: " PPC_LWARX(%0,0,%2,1) "\n\
cmpwi 0,%0,0\n\
bne- 2f\n\
stwcx. %1,0,%2\n\
bne- 1b\n"
PPC_ACQUIRE_BARRIER
"2:"
: "=&r" (tmp)
: "r" (token), "r" (&lock->slock)
: "cr0", "memory");
return tmp;
}
static inline int arch_spin_trylock(arch_spinlock_t *lock)
{
CLEAR_IO_SYNC;
return __arch_spin_trylock(lock) == 0;
}
/*
* On a system with shared processors (that is, where a physical
* processor is multiplexed between several virtual processors),
* there is no point spinning on a lock if the holder of the lock
* isn't currently scheduled on a physical processor. Instead
* we detect this situation and ask the hypervisor to give the
* rest of our timeslice to the lock holder.
*
* So that we can tell which virtual processor is holding a lock,
* we put 0x80000000 | smp_processor_id() in the lock when it is
* held. Conveniently, we have a word in the paca that holds this
* value.
*/
#if defined(CONFIG_PPC_SPLPAR)
/* We only yield to the hypervisor if we are in shared processor mode */
#define SHARED_PROCESSOR (lppaca_shared_proc(local_paca->lppaca_ptr))
extern void __spin_yield(arch_spinlock_t *lock);
extern void __rw_yield(arch_rwlock_t *lock);
#else /* SPLPAR */
#define __spin_yield(x) barrier()
#define __rw_yield(x) barrier()
#define SHARED_PROCESSOR 0
#endif
static inline void arch_spin_lock(arch_spinlock_t *lock)
{
CLEAR_IO_SYNC;
while (1) {
if (likely(__arch_spin_trylock(lock) == 0))
break;
do {
HMT_low();
if (SHARED_PROCESSOR)
__spin_yield(lock);
} while (unlikely(lock->slock != 0));
HMT_medium();
}
}
static inline
void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
{
unsigned long flags_dis;
CLEAR_IO_SYNC;
while (1) {
if (likely(__arch_spin_trylock(lock) == 0))
break;
local_save_flags(flags_dis);
local_irq_restore(flags);
do {
HMT_low();
if (SHARED_PROCESSOR)
__spin_yield(lock);
} while (unlikely(lock->slock != 0));
HMT_medium();
local_irq_restore(flags_dis);
}
}
static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
SYNC_IO;
__asm__ __volatile__("# arch_spin_unlock\n\t"
PPC_RELEASE_BARRIER: : :"memory");
lock->slock = 0;
}
#ifdef CONFIG_PPC64
extern void arch_spin_unlock_wait(arch_spinlock_t *lock);
#else
#define arch_spin_unlock_wait(lock) \
do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
#endif
/*
* Read-write spinlocks, allowing multiple readers
* but only one writer.
*
* NOTE! it is quite common to have readers in interrupts
* but no interrupt writers. For those circumstances we
* can "mix" irq-safe locks - any writer needs to get a
* irq-safe write-lock, but readers can get non-irqsafe
* read-locks.
*/
#define arch_read_can_lock(rw) ((rw)->lock >= 0)
#define arch_write_can_lock(rw) (!(rw)->lock)
#ifdef CONFIG_PPC64
#define __DO_SIGN_EXTEND "extsw %0,%0\n"
#define WRLOCK_TOKEN LOCK_TOKEN /* it's negative */
#else
#define __DO_SIGN_EXTEND
#define WRLOCK_TOKEN (-1)
#endif
/*
* This returns the old value in the lock + 1,
* so we got a read lock if the return value is > 0.
*/
static inline long __arch_read_trylock(arch_rwlock_t *rw)
{
long tmp;
__asm__ __volatile__(
"1: " PPC_LWARX(%0,0,%1,1) "\n"
__DO_SIGN_EXTEND
" addic. %0,%0,1\n\
ble- 2f\n"
PPC405_ERR77(0,%1)
" stwcx. %0,0,%1\n\
bne- 1b\n"
PPC_ACQUIRE_BARRIER
"2:" : "=&r" (tmp)
: "r" (&rw->lock)
: "cr0", "xer", "memory");
return tmp;
}
/*
* This returns the old value in the lock,
* so we got the write lock if the return value is 0.
*/
static inline long __arch_write_trylock(arch_rwlock_t *rw)
{
long tmp, token;
token = WRLOCK_TOKEN;
__asm__ __volatile__(
"1: " PPC_LWARX(%0,0,%2,1) "\n\
cmpwi 0,%0,0\n\
bne- 2f\n"
PPC405_ERR77(0,%1)
" stwcx. %1,0,%2\n\
bne- 1b\n"
PPC_ACQUIRE_BARRIER
"2:" : "=&r" (tmp)
: "r" (token), "r" (&rw->lock)
: "cr0", "memory");
return tmp;
}
static inline void arch_read_lock(arch_rwlock_t *rw)
{
while (1) {
if (likely(__arch_read_trylock(rw) > 0))
break;
do {
HMT_low();
if (SHARED_PROCESSOR)
__rw_yield(rw);
} while (unlikely(rw->lock < 0));
HMT_medium();
}
}
static inline void arch_write_lock(arch_rwlock_t *rw)
{
while (1) {
if (likely(__arch_write_trylock(rw) == 0))
break;
do {
HMT_low();
if (SHARED_PROCESSOR)
__rw_yield(rw);
} while (unlikely(rw->lock != 0));
HMT_medium();
}
}
static inline int arch_read_trylock(arch_rwlock_t *rw)
{
return __arch_read_trylock(rw) > 0;
}
static inline int arch_write_trylock(arch_rwlock_t *rw)
{
return __arch_write_trylock(rw) == 0;
}
static inline void arch_read_unlock(arch_rwlock_t *rw)
{
long tmp;
__asm__ __volatile__(
"# read_unlock\n\t"
PPC_RELEASE_BARRIER
"1: lwarx %0,0,%1\n\
addic %0,%0,-1\n"
PPC405_ERR77(0,%1)
" stwcx. %0,0,%1\n\
bne- 1b"
: "=&r"(tmp)
: "r"(&rw->lock)
: "cr0", "xer", "memory");
}
static inline void arch_write_unlock(arch_rwlock_t *rw)
{
__asm__ __volatile__("# write_unlock\n\t"
PPC_RELEASE_BARRIER: : :"memory");
rw->lock = 0;
}
#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
#define arch_spin_relax(lock) __spin_yield(lock)
#define arch_read_relax(lock) __rw_yield(lock)
#define arch_write_relax(lock) __rw_yield(lock)
#endif /* __KERNEL__ */
#endif /* __ASM_SPINLOCK_H */
Reference in New Issue View Git Blame Copy Permalink