• Ingo Molnar's avatar
    [PATCH] spinlock consolidation · fb1c8f93
    Ingo Molnar authored
    
    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: default avatarIngo Molnar <mingo@elte.hu>
    Signed-off-by: default avatarArjan van de Ven <arjanv@infradead.org>
    Signed-off-by: default avatarGrant Grundler <grundler@parisc-linux.org>
    Cc: Matthew Wilcox <willy@debian.org>
    Signed-off-by: default avatarHirokazu Takata <takata@linux-m32r.org>
    Signed-off-by: default avatarMikael Pettersson <mikpe@csd.uu.se>
    Signed-off-by: default avatarBenoit Boissinot <benoit.boissinot@ens-lyon.org>
    Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
    Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
    fb1c8f93
kernel_lock.c 4.48 KB
/*
 * lib/kernel_lock.c
 *
 * This is the traditional BKL - big kernel lock. Largely
 * relegated to obsolescense, but used by various less
 * important (or lazy) subsystems.
 */
#include <linux/smp_lock.h>
#include <linux/module.h>
#include <linux/kallsyms.h>

#ifdef CONFIG_PREEMPT_BKL
/*
 * The 'big kernel semaphore'
 *
 * This mutex is taken and released recursively by lock_kernel()
 * and unlock_kernel().  It is transparently dropped and reaquired
 * over schedule().  It is used to protect legacy code that hasn't
 * been migrated to a proper locking design yet.
 *
 * Note: code locked by this semaphore will only be serialized against
 * other code using the same locking facility. The code guarantees that
 * the task remains on the same CPU.
 *
 * Don't use in new code.
 */
static DECLARE_MUTEX(kernel_sem);

/*
 * Re-acquire the kernel semaphore.
 *
 * This function is called with preemption off.
 *
 * We are executing in schedule() so the code must be extremely careful
 * about recursion, both due to the down() and due to the enabling of
 * preemption. schedule() will re-check the preemption flag after
 * reacquiring the semaphore.
 */
int __lockfunc __reacquire_kernel_lock(void)
{
	struct task_struct *task = current;
	int saved_lock_depth = task->lock_depth;

	BUG_ON(saved_lock_depth < 0);

	task->lock_depth = -1;
	preempt_enable_no_resched();

	down(&kernel_sem);

	preempt_disable();
	task->lock_depth = saved_lock_depth;

	return 0;
}

void __lockfunc __release_kernel_lock(void)
{
	up(&kernel_sem);
}

/*
 * Getting the big kernel semaphore.
 */
void __lockfunc lock_kernel(void)
{
	struct task_struct *task = current;
	int depth = task->lock_depth + 1;

	if (likely(!depth))
		/*
		 * No recursion worries - we set up lock_depth _after_
		 */
		down(&kernel_sem);

	task->lock_depth = depth;
}

void __lockfunc unlock_kernel(void)
{
	struct task_struct *task = current;

	BUG_ON(task->lock_depth < 0);

	if (likely(--task->lock_depth < 0))
		up(&kernel_sem);
}

#else

/*
 * The 'big kernel lock'
 *
 * This spinlock is taken and released recursively by lock_kernel()
 * and unlock_kernel().  It is transparently dropped and reaquired
 * over schedule().  It is used to protect legacy code that hasn't
 * been migrated to a proper locking design yet.
 *
 * Don't use in new code.
 */
static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kernel_flag);


/*
 * Acquire/release the underlying lock from the scheduler.
 *
 * This is called with preemption disabled, and should
 * return an error value if it cannot get the lock and
 * TIF_NEED_RESCHED gets set.
 *
 * If it successfully gets the lock, it should increment
 * the preemption count like any spinlock does.
 *
 * (This works on UP too - _raw_spin_trylock will never
 * return false in that case)
 */
int __lockfunc __reacquire_kernel_lock(void)
{
	while (!_raw_spin_trylock(&kernel_flag)) {
		if (test_thread_flag(TIF_NEED_RESCHED))
			return -EAGAIN;
		cpu_relax();
	}
	preempt_disable();
	return 0;
}

void __lockfunc __release_kernel_lock(void)
{
	_raw_spin_unlock(&kernel_flag);
	preempt_enable_no_resched();
}

/*
 * These are the BKL spinlocks - we try to be polite about preemption. 
 * If SMP is not on (ie UP preemption), this all goes away because the
 * _raw_spin_trylock() will always succeed.
 */
#ifdef CONFIG_PREEMPT
static inline void __lock_kernel(void)
{
	preempt_disable();
	if (unlikely(!_raw_spin_trylock(&kernel_flag))) {
		/*
		 * If preemption was disabled even before this
		 * was called, there's nothing we can be polite
		 * about - just spin.
		 */
		if (preempt_count() > 1) {
			_raw_spin_lock(&kernel_flag);
			return;
		}

		/*
		 * Otherwise, let's wait for the kernel lock
		 * with preemption enabled..
		 */
		do {
			preempt_enable();
			while (spin_is_locked(&kernel_flag))
				cpu_relax();
			preempt_disable();
		} while (!_raw_spin_trylock(&kernel_flag));
	}
}

#else

/*
 * Non-preemption case - just get the spinlock
 */
static inline void __lock_kernel(void)
{
	_raw_spin_lock(&kernel_flag);
}
#endif

static inline void __unlock_kernel(void)
{
	spin_unlock(&kernel_flag);
}

/*
 * Getting the big kernel lock.
 *
 * This cannot happen asynchronously, so we only need to
 * worry about other CPU's.
 */
void __lockfunc lock_kernel(void)
{
	int depth = current->lock_depth+1;
	if (likely(!depth))
		__lock_kernel();
	current->lock_depth = depth;
}

void __lockfunc unlock_kernel(void)
{
	BUG_ON(current->lock_depth < 0);
	if (likely(--current->lock_depth < 0))
		__unlock_kernel();
}

#endif

EXPORT_SYMBOL(lock_kernel);
EXPORT_SYMBOL(unlock_kernel);