Revision e6da7c9fed111ba1243297ee6eda8e24ae11c384 authored by Eric Sandeen on 23 May 2009, 19:30:12 UTC, committed by Felix Blyakher on 02 June 2009, 03:59:38 UTC
In the case where growing a filesystem would leave the last AG
too small, the fixup code has an overflow in the calculation
of the new size with one fewer ag, because "nagcount" is a 32
bit number.  If the new filesystem has > 2^32 blocks in it
this causes a problem resulting in an EINVAL return from growfs:

 # xfs_io -f -c "truncate 19998630180864" fsfile
 # mkfs.xfs -f -bsize=4096 -dagsize=76288719b,size=3905982455b fsfile
 # mount -o loop fsfile /mnt
 # xfs_growfs /mnt

meta-data=/dev/loop0             isize=256    agcount=52,
agsize=76288719 blks
         =                       sectsz=512   attr=2
data     =                       bsize=4096   blocks=3905982455, imaxpct=5
         =                       sunit=0      swidth=0 blks
naming   =version 2              bsize=4096   ascii-ci=0
log      =internal               bsize=4096   blocks=32768, version=2
         =                       sectsz=512   sunit=0 blks, lazy-count=0
realtime =none                   extsz=4096   blocks=0, rtextents=0
xfs_growfs: XFS_IOC_FSGROWFSDATA xfsctl failed: Invalid argument

Reported-by: richard.ems@cape-horn-eng.com
Signed-off-by: Eric Sandeen <sandeen@sandeen.net>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Felix Blyakher <felixb@sgi.com>
Signed-off-by: Felix Blyakher <felixb@sgi.com>
1 parent 1f23920
Raw File
kernel_lock.c
/*
 * lib/kernel_lock.c
 *
 * This is the traditional BKL - big kernel lock. Largely
 * relegated to obsolescence, but used by various less
 * important (or lazy) subsystems.
 */
#include <linux/smp_lock.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/semaphore.h>

/*
 * The 'big kernel lock'
 *
 * This spinlock is taken and released recursively by lock_kernel()
 * and unlock_kernel().  It is transparently dropped and reacquired
 * 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 (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)
{
	/*
	 * the BKL is not covered by lockdep, so we open-code the
	 * unlocking sequence (and thus avoid the dep-chain ops):
	 */
	_raw_spin_unlock(&kernel_flag);
	preempt_enable();
}

/*
 * 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();
}

EXPORT_SYMBOL(lock_kernel);
EXPORT_SYMBOL(unlock_kernel);

back to top