mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-26 06:10:51 +07:00
fb1c8f93d8
This patch (written by me and also containing many suggestions of Arjan van de Ven) does a major cleanup of the spinlock code. It does the following things: - consolidates and enhances the spinlock/rwlock debugging code - simplifies the asm/spinlock.h files - encapsulates the raw spinlock type and moves generic spinlock features (such as ->break_lock) into the generic code. - cleans up the spinlock code hierarchy to get rid of the spaghetti. Most notably there's now only a single variant of the debugging code, located in lib/spinlock_debug.c. (previously we had one SMP debugging variant per architecture, plus a separate generic one for UP builds) Also, i've enhanced the rwlock debugging facility, it will now track write-owners. There is new spinlock-owner/CPU-tracking on SMP builds too. All locks have lockup detection now, which will work for both soft and hard spin/rwlock lockups. The arch-level include files now only contain the minimally necessary subset of the spinlock code - all the rest that can be generalized now lives in the generic headers: include/asm-i386/spinlock_types.h | 16 include/asm-x86_64/spinlock_types.h | 16 I have also split up the various spinlock variants into separate files, making it easier to see which does what. The new layout is: SMP | UP ----------------------------|----------------------------------- asm/spinlock_types_smp.h | linux/spinlock_types_up.h linux/spinlock_types.h | linux/spinlock_types.h asm/spinlock_smp.h | linux/spinlock_up.h linux/spinlock_api_smp.h | linux/spinlock_api_up.h linux/spinlock.h | linux/spinlock.h /* * here's the role of the various spinlock/rwlock related include files: * * on SMP builds: * * asm/spinlock_types.h: contains the raw_spinlock_t/raw_rwlock_t and the * initializers * * linux/spinlock_types.h: * defines the generic type and initializers * * asm/spinlock.h: contains the __raw_spin_*()/etc. lowlevel * implementations, mostly inline assembly code * * (also included on UP-debug builds:) * * linux/spinlock_api_smp.h: * contains the prototypes for the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. * * on UP builds: * * linux/spinlock_type_up.h: * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * * linux/spinlock_types.h: * defines the generic type and initializers * * linux/spinlock_up.h: * contains the __raw_spin_*()/etc. version of UP * builds. (which are NOPs on non-debug, non-preempt * builds) * * (included on UP-non-debug builds:) * * linux/spinlock_api_up.h: * builds the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. */ All SMP and UP architectures are converted by this patch. arm, i386, ia64, ppc, ppc64, s390/s390x, x64 was build-tested via crosscompilers. m32r, mips, sh, sparc, have not been tested yet, but should be mostly fine. From: Grant Grundler <grundler@parisc-linux.org> Booted and lightly tested on a500-44 (64-bit, SMP kernel, dual CPU). Builds 32-bit SMP kernel (not booted or tested). I did not try to build non-SMP kernels. That should be trivial to fix up later if necessary. I converted bit ops atomic_hash lock to raw_spinlock_t. Doing so avoids some ugly nesting of linux/*.h and asm/*.h files. Those particular locks are well tested and contained entirely inside arch specific code. I do NOT expect any new issues to arise with them. If someone does ever need to use debug/metrics with them, then they will need to unravel this hairball between spinlocks, atomic ops, and bit ops that exist only because parisc has exactly one atomic instruction: LDCW (load and clear word). From: "Luck, Tony" <tony.luck@intel.com> ia64 fix Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arjan van de Ven <arjanv@infradead.org> Signed-off-by: Grant Grundler <grundler@parisc-linux.org> Cc: Matthew Wilcox <willy@debian.org> Signed-off-by: Hirokazu Takata <takata@linux-m32r.org> Signed-off-by: Mikael Pettersson <mikpe@csd.uu.se> Signed-off-by: Benoit Boissinot <benoit.boissinot@ens-lyon.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
191 lines
4.2 KiB
C
191 lines
4.2 KiB
C
#ifndef __ASM_SPINLOCK_H
|
|
#define __ASM_SPINLOCK_H
|
|
|
|
#include <asm/atomic.h>
|
|
#include <asm/rwlock.h>
|
|
#include <asm/page.h>
|
|
#include <linux/config.h>
|
|
#include <linux/compiler.h>
|
|
|
|
/*
|
|
* Your basic SMP spinlocks, allowing only a single CPU anywhere
|
|
*
|
|
* Simple spin lock operations. There are two variants, one clears IRQ's
|
|
* on the local processor, one does not.
|
|
*
|
|
* We make no fairness assumptions. They have a cost.
|
|
*
|
|
* (the type definitions are in asm/spinlock_types.h)
|
|
*/
|
|
|
|
#define __raw_spin_is_locked(x) \
|
|
(*(volatile signed char *)(&(x)->slock) <= 0)
|
|
|
|
#define __raw_spin_lock_string \
|
|
"\n1:\t" \
|
|
"lock ; decb %0\n\t" \
|
|
"jns 3f\n" \
|
|
"2:\t" \
|
|
"rep;nop\n\t" \
|
|
"cmpb $0,%0\n\t" \
|
|
"jle 2b\n\t" \
|
|
"jmp 1b\n" \
|
|
"3:\n\t"
|
|
|
|
#define __raw_spin_lock_string_flags \
|
|
"\n1:\t" \
|
|
"lock ; decb %0\n\t" \
|
|
"jns 4f\n\t" \
|
|
"2:\t" \
|
|
"testl $0x200, %1\n\t" \
|
|
"jz 3f\n\t" \
|
|
"sti\n\t" \
|
|
"3:\t" \
|
|
"rep;nop\n\t" \
|
|
"cmpb $0, %0\n\t" \
|
|
"jle 3b\n\t" \
|
|
"cli\n\t" \
|
|
"jmp 1b\n" \
|
|
"4:\n\t"
|
|
|
|
static inline void __raw_spin_lock(raw_spinlock_t *lock)
|
|
{
|
|
__asm__ __volatile__(
|
|
__raw_spin_lock_string
|
|
:"=m" (lock->slock) : : "memory");
|
|
}
|
|
|
|
static inline void __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
|
|
{
|
|
__asm__ __volatile__(
|
|
__raw_spin_lock_string_flags
|
|
:"=m" (lock->slock) : "r" (flags) : "memory");
|
|
}
|
|
|
|
static inline int __raw_spin_trylock(raw_spinlock_t *lock)
|
|
{
|
|
char oldval;
|
|
__asm__ __volatile__(
|
|
"xchgb %b0,%1"
|
|
:"=q" (oldval), "=m" (lock->slock)
|
|
:"0" (0) : "memory");
|
|
return oldval > 0;
|
|
}
|
|
|
|
/*
|
|
* __raw_spin_unlock based on writing $1 to the low byte.
|
|
* This method works. Despite all the confusion.
|
|
* (except on PPro SMP or if we are using OOSTORE, so we use xchgb there)
|
|
* (PPro errata 66, 92)
|
|
*/
|
|
|
|
#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
|
|
|
|
#define __raw_spin_unlock_string \
|
|
"movb $1,%0" \
|
|
:"=m" (lock->slock) : : "memory"
|
|
|
|
|
|
static inline void __raw_spin_unlock(raw_spinlock_t *lock)
|
|
{
|
|
__asm__ __volatile__(
|
|
__raw_spin_unlock_string
|
|
);
|
|
}
|
|
|
|
#else
|
|
|
|
#define __raw_spin_unlock_string \
|
|
"xchgb %b0, %1" \
|
|
:"=q" (oldval), "=m" (lock->slock) \
|
|
:"0" (oldval) : "memory"
|
|
|
|
static inline void __raw_spin_unlock(raw_spinlock_t *lock)
|
|
{
|
|
char oldval = 1;
|
|
|
|
__asm__ __volatile__(
|
|
__raw_spin_unlock_string
|
|
);
|
|
}
|
|
|
|
#endif
|
|
|
|
#define __raw_spin_unlock_wait(lock) \
|
|
do { while (__raw_spin_is_locked(lock)) cpu_relax(); } while (0)
|
|
|
|
/*
|
|
* 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.
|
|
*
|
|
* On x86, we implement read-write locks as a 32-bit counter
|
|
* with the high bit (sign) being the "contended" bit.
|
|
*
|
|
* The inline assembly is non-obvious. Think about it.
|
|
*
|
|
* Changed to use the same technique as rw semaphores. See
|
|
* semaphore.h for details. -ben
|
|
*
|
|
* the helpers are in arch/i386/kernel/semaphore.c
|
|
*/
|
|
|
|
/**
|
|
* read_can_lock - would read_trylock() succeed?
|
|
* @lock: the rwlock in question.
|
|
*/
|
|
#define __raw_read_can_lock(x) ((int)(x)->lock > 0)
|
|
|
|
/**
|
|
* write_can_lock - would write_trylock() succeed?
|
|
* @lock: the rwlock in question.
|
|
*/
|
|
#define __raw_write_can_lock(x) ((x)->lock == RW_LOCK_BIAS)
|
|
|
|
static inline void __raw_read_lock(raw_rwlock_t *rw)
|
|
{
|
|
__build_read_lock(rw, "__read_lock_failed");
|
|
}
|
|
|
|
static inline void __raw_write_lock(raw_rwlock_t *rw)
|
|
{
|
|
__build_write_lock(rw, "__write_lock_failed");
|
|
}
|
|
|
|
static inline int __raw_read_trylock(raw_rwlock_t *lock)
|
|
{
|
|
atomic_t *count = (atomic_t *)lock;
|
|
atomic_dec(count);
|
|
if (atomic_read(count) >= 0)
|
|
return 1;
|
|
atomic_inc(count);
|
|
return 0;
|
|
}
|
|
|
|
static inline int __raw_write_trylock(raw_rwlock_t *lock)
|
|
{
|
|
atomic_t *count = (atomic_t *)lock;
|
|
if (atomic_sub_and_test(RW_LOCK_BIAS, count))
|
|
return 1;
|
|
atomic_add(RW_LOCK_BIAS, count);
|
|
return 0;
|
|
}
|
|
|
|
static inline void __raw_read_unlock(raw_rwlock_t *rw)
|
|
{
|
|
asm volatile("lock ; incl %0" :"=m" (rw->lock) : : "memory");
|
|
}
|
|
|
|
static inline void __raw_write_unlock(raw_rwlock_t *rw)
|
|
{
|
|
asm volatile("lock ; addl $" RW_LOCK_BIAS_STR ", %0"
|
|
: "=m" (rw->lock) : : "memory");
|
|
}
|
|
|
|
#endif /* __ASM_SPINLOCK_H */
|