Merge master.kernel.org:/pub/scm/linux/kernel/git/mingo/mutex-2.6

Documentation/DocBook/kernel-locking.tmpl

@@ -222,7 +222,7 @@
    <title>Two Main Types of Kernel Locks: Spinlocks and Semaphores</title>
 
    <para>
-     There are two main types of kernel locks.  The fundamental type
+     There are three main types of kernel locks.  The fundamental type
      is the spinlock 
      (<filename class="headerfile">include/asm/spinlock.h</filename>),
      which is a very simple single-holder lock: if you can't get the 
@@ -230,16 +230,22 @@
      very small and fast, and can be used anywhere.
    </para>
    <para>
-     The second type is a semaphore
+     The second type is a mutex
+     (<filename class="headerfile">include/linux/mutex.h</filename>): it
+     is like a spinlock, but you may block holding a mutex.
+     If you can't lock a mutex, your task will suspend itself, and be woken
+     up when the mutex is released.  This means the CPU can do something
+     else while you are waiting.  There are many cases when you simply
+     can't sleep (see <xref linkend="sleeping-things"/>), and so have to
+     use a spinlock instead.
+   </para>
+   <para>
+     The third type is a semaphore
      (<filename class="headerfile">include/asm/semaphore.h</filename>): it
      can have more than one holder at any time (the number decided at
      initialization time), although it is most commonly used as a
-     single-holder lock (a mutex).  If you can't get a semaphore,
-     your task will put itself on the queue, and be woken up when the
-     semaphore is released.  This means the CPU will do something
-     else while you are waiting, but there are many cases when you
-     simply can't sleep (see <xref linkend="sleeping-things"/>), and so
-     have to use a spinlock instead.
+     single-holder lock (a mutex).  If you can't get a semaphore, your
+     task will be suspended and later on woken up - just like for mutexes.
    </para>
    <para>
      Neither type of lock is recursive: see

Documentation/mutex-design.txt

+Generic Mutex Subsystem
+
+started by Ingo Molnar <mingo@redhat.com>
+
+  "Why on earth do we need a new mutex subsystem, and what's wrong
+   with semaphores?"
+
+firstly, there's nothing wrong with semaphores. But if the simpler
+mutex semantics are sufficient for your code, then there are a couple
+of advantages of mutexes:
+
+ - 'struct mutex' is smaller on most architectures: .e.g on x86,
+   'struct semaphore' is 20 bytes, 'struct mutex' is 16 bytes.
+   A smaller structure size means less RAM footprint, and better
+   CPU-cache utilization.
+
+ - tighter code. On x86 i get the following .text sizes when
+   switching all mutex-alike semaphores in the kernel to the mutex
+   subsystem:
+
+        text    data     bss     dec     hex filename
+     3280380  868188  396860 4545428  455b94 vmlinux-semaphore
+     3255329  865296  396732 4517357  44eded vmlinux-mutex
+
+   that's 25051 bytes of code saved, or a 0.76% win - off the hottest
+   codepaths of the kernel. (The .data savings are 2892 bytes, or 0.33%)
+   Smaller code means better icache footprint, which is one of the
+   major optimization goals in the Linux kernel currently.
+
+ - the mutex subsystem is slightly faster and has better scalability for
+   contended workloads. On an 8-way x86 system, running a mutex-based
+   kernel and testing creat+unlink+close (of separate, per-task files)
+   in /tmp with 16 parallel tasks, the average number of ops/sec is:
+
+    Semaphores:                        Mutexes:
+
+    $ ./test-mutex V 16 10             $ ./test-mutex V 16 10
+    8 CPUs, running 16 tasks.          8 CPUs, running 16 tasks.
+    checking VFS performance.          checking VFS performance.
+    avg loops/sec:      34713          avg loops/sec:      84153
+    CPU utilization:    63%            CPU utilization:    22%
+
+   i.e. in this workload, the mutex based kernel was 2.4 times faster
+   than the semaphore based kernel, _and_ it also had 2.8 times less CPU
+   utilization. (In terms of 'ops per CPU cycle', the semaphore kernel
+   performed 551 ops/sec per 1% of CPU time used, while the mutex kernel
+   performed 3825 ops/sec per 1% of CPU time used - it was 6.9 times
+   more efficient.)
+
+   the scalability difference is visible even on a 2-way P4 HT box:
+
+    Semaphores:                        Mutexes:
+
+    $ ./test-mutex V 16 10             $ ./test-mutex V 16 10
+    4 CPUs, running 16 tasks.          8 CPUs, running 16 tasks.
+    checking VFS performance.          checking VFS performance.
+    avg loops/sec:      127659         avg loops/sec:      181082
+    CPU utilization:    100%           CPU utilization:    34%
+
+   (the straight performance advantage of mutexes is 41%, the per-cycle
+    efficiency of mutexes is 4.1 times better.)
+
+ - there are no fastpath tradeoffs, the mutex fastpath is just as tight
+   as the semaphore fastpath. On x86, the locking fastpath is 2
+   instructions:
+
+    c0377ccb <mutex_lock>:
+    c0377ccb:       f0 ff 08                lock decl (%eax)
+    c0377cce:       78 0e                   js     c0377cde <.text.lock.mutex>
+    c0377cd0:       c3                      ret
+
+   the unlocking fastpath is equally tight:
+
+    c0377cd1 <mutex_unlock>:
+    c0377cd1:       f0 ff 00                lock incl (%eax)
+    c0377cd4:       7e 0f                   jle    c0377ce5 <.text.lock.mutex+0x7>
+    c0377cd6:       c3                      ret
+
+ - 'struct mutex' semantics are well-defined and are enforced if
+   CONFIG_DEBUG_MUTEXES is turned on. Semaphores on the other hand have
+   virtually no debugging code or instrumentation. The mutex subsystem
+   checks and enforces the following rules:
+
+   * - only one task can hold the mutex at a time
+   * - only the owner can unlock the mutex
+   * - multiple unlocks are not permitted
+   * - recursive locking is not permitted
+   * - a mutex object must be initialized via the API
+   * - a mutex object must not be initialized via memset or copying
+   * - task may not exit with mutex held
+   * - memory areas where held locks reside must not be freed
+   * - held mutexes must not be reinitialized
+   * - mutexes may not be used in irq contexts
+
+   furthermore, there are also convenience features in the debugging
+   code:
+
+   * - uses symbolic names of mutexes, whenever they are printed in debug output
+   * - point-of-acquire tracking, symbolic lookup of function names
+   * - list of all locks held in the system, printout of them
+   * - owner tracking
+   * - detects self-recursing locks and prints out all relevant info
+   * - detects multi-task circular deadlocks and prints out all affected
+   *   locks and tasks (and only those tasks)
+
+Disadvantages
+-------------
+
+The stricter mutex API means you cannot use mutexes the same way you
+can use semaphores: e.g. they cannot be used from an interrupt context,
+nor can they be unlocked from a different context that which acquired
+it. [ I'm not aware of any other (e.g. performance) disadvantages from
+using mutexes at the moment, please let me know if you find any. ]
+
+Implementation of mutexes
+-------------------------
+
+'struct mutex' is the new mutex type, defined in include/linux/mutex.h
+and implemented in kernel/mutex.c. It is a counter-based mutex with a
+spinlock and a wait-list. The counter has 3 states: 1 for "unlocked",
+0 for "locked" and negative numbers (usually -1) for "locked, potential
+waiters queued".
+
+the APIs of 'struct mutex' have been streamlined:
+
+ DEFINE_MUTEX(name);
+
+ mutex_init(mutex);
+
+ void mutex_lock(struct mutex *lock);
+ int  mutex_lock_interruptible(struct mutex *lock);
+ int  mutex_trylock(struct mutex *lock);
+ void mutex_unlock(struct mutex *lock);
+ int  mutex_is_locked(struct mutex *lock);
+

arch/i386/mm/pageattr.c

@@ -222,6 +222,10 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))
 		return;
+	if (!enable)
+		mutex_debug_check_no_locks_freed(page_address(page),
+						 page_address(page+numpages));
+
 	/* the return value is ignored - the calls cannot fail,
 	 * large pages are disabled at boot time.
 	 */

arch/powerpc/platforms/cell/spufs/inode.c

@@ -137,7 +137,7 @@ spufs_delete_inode(struct inode *inode)
 static void spufs_prune_dir(struct dentry *dir)
 {
 	struct dentry *dentry, *tmp;
-	down(&dir->d_inode->i_sem);
+	mutex_lock(&dir->d_inode->i_mutex);
 	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) {
 		spin_lock(&dcache_lock);
 		spin_lock(&dentry->d_lock);
@@ -154,7 +154,7 @@ static void spufs_prune_dir(struct dentry *dir)
 		}
 	}
 	shrink_dcache_parent(dir);
-	up(&dir->d_inode->i_sem);
+	mutex_unlock(&dir->d_inode->i_mutex);
 }
 
 static int spufs_rmdir(struct inode *root, struct dentry *dir_dentry)
@@ -162,15 +162,15 @@ static int spufs_rmdir(struct inode *root, struct dentry *dir_dentry)
 	struct spu_context *ctx;
 
 	/* remove all entries */
-	down(&root->i_sem);
+	mutex_lock(&root->i_mutex);
 	spufs_prune_dir(dir_dentry);
-	up(&root->i_sem);
+	mutex_unlock(&root->i_mutex);
 
 	/* We have to give up the mm_struct */
 	ctx = SPUFS_I(dir_dentry->d_inode)->i_ctx;
 	spu_forget(ctx);
 
-	/* XXX Do we need to hold i_sem here ? */
+	/* XXX Do we need to hold i_mutex here ? */
 	return simple_rmdir(root, dir_dentry);
 }
 
@@ -330,7 +330,7 @@ long spufs_create_thread(struct nameidata *nd,
 out_dput:
 	dput(dentry);
 out_dir:
-	up(&nd->dentry->d_inode->i_sem);
+	mutex_unlock(&nd->dentry->d_inode->i_mutex);
 out:
 	return ret;
 }

drivers/block/loop.c

@@ -215,7 +215,7 @@ static int do_lo_send_aops(struct loop_device *lo, struct bio_vec *bvec,
 	unsigned offset, bv_offs;
 	int len, ret;
 
-	down(&mapping->host->i_sem);
+	mutex_lock(&mapping->host->i_mutex);
 	index = pos >> PAGE_CACHE_SHIFT;
 	offset = pos & ((pgoff_t)PAGE_CACHE_SIZE - 1);
 	bv_offs = bvec->bv_offset;
@@ -278,7 +278,7 @@ static int do_lo_send_aops(struct loop_device *lo, struct bio_vec *bvec,
 	}
 	ret = 0;
 out:
-	up(&mapping->host->i_sem);
+	mutex_unlock(&mapping->host->i_mutex);
 	return ret;
 unlock:
 	unlock_page(page);
@@ -527,12 +527,12 @@ static int loop_make_request(request_queue_t *q, struct bio *old_bio)
 	lo->lo_pending++;
 	loop_add_bio(lo, old_bio);
 	spin_unlock_irq(&lo->lo_lock);
-	up(&lo->lo_bh_mutex);
+	complete(&lo->lo_bh_done);
 	return 0;
 
 out:
 	if (lo->lo_pending == 0)
-		up(&lo->lo_bh_mutex);
+		complete(&lo->lo_bh_done);
 	spin_unlock_irq(&lo->lo_lock);
 	bio_io_error(old_bio, old_bio->bi_size);
 	return 0;
@@ -593,23 +593,20 @@ static int loop_thread(void *data)
 	lo->lo_pending = 1;
 
 	/*
-	 * up sem, we are running
+	 * complete it, we are running
 	 */
-	up(&lo->lo_sem);
+	complete(&lo->lo_done);
 
 	for (;;) {
 		int pending;
 
-		/*
-		 * interruptible just to not contribute to load avg
-		 */
-		if (down_interruptible(&lo->lo_bh_mutex))
+		if (wait_for_completion_interruptible(&lo->lo_bh_done))
 			continue;
 
 		spin_lock_irq(&lo->lo_lock);
 
 		/*
-		 * could be upped because of tear-down, not pending work
+		 * could be completed because of tear-down, not pending work
 		 */
 		if (unlikely(!lo->lo_pending)) {
 			spin_unlock_irq(&lo->lo_lock);
@@ -632,7 +629,7 @@ static int loop_thread(void *data)
 			break;
 	}
 
-	up(&lo->lo_sem);
+	complete(&lo->lo_done);
 	return 0;
 }
 
@@ -843,7 +840,7 @@ static int loop_set_fd(struct loop_device *lo, struct file *lo_file,
 	set_blocksize(bdev, lo_blocksize);
 
 	kernel_thread(loop_thread, lo, CLONE_KERNEL);
-	down(&lo->lo_sem);
+	wait_for_completion(&lo->lo_done);
 	return 0;
 
  out_putf:
@@ -909,10 +906,10 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
 	lo->lo_state = Lo_rundown;
 	lo->lo_pending--;
 	if (!lo->lo_pending)
-		up(&lo->lo_bh_mutex);
+		complete(&lo->lo_bh_done);
 	spin_unlock_irq(&lo->lo_lock);
 
-	down(&lo->lo_sem);
+	wait_for_completion(&lo->lo_done);
 
 	lo->lo_backing_file = NULL;
 
@@ -1289,8 +1286,8 @@ static int __init loop_init(void)
 		if (!lo->lo_queue)
 			goto out_mem4;
 		init_MUTEX(&lo->lo_ctl_mutex);
-		init_MUTEX_LOCKED(&lo->lo_sem);
-		init_MUTEX_LOCKED(&lo->lo_bh_mutex);
+		init_completion(&lo->lo_done);
+		init_completion(&lo->lo_bh_done);
 		lo->lo_number = i;
 		spin_lock_init(&lo->lo_lock);
 		disk->major = LOOP_MAJOR;

drivers/block/sx8.c

@@ -27,8 +27,8 @@
 #include <linux/time.h>
 #include <linux/hdreg.h>
 #include <linux/dma-mapping.h>
+#include <linux/completion.h>
 #include <asm/io.h>
-#include <asm/semaphore.h>
 #include <asm/uaccess.h>
 
 #if 0
@@ -303,7 +303,7 @@ struct carm_host {
 
 	struct work_struct		fsm_task;
 
-	struct semaphore		probe_sem;
+	struct completion		probe_comp;
 };
 
 struct carm_response {
@@ -1346,7 +1346,7 @@ static void carm_fsm_task (void *_data)
 	}
 
 	case HST_PROBE_FINISHED:
-		up(&host->probe_sem);
+		complete(&host->probe_comp);
 		break;
 
 	case HST_ERROR:
@@ -1622,7 +1622,7 @@ static int carm_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 	host->flags = pci_dac ? FL_DAC : 0;
 	spin_lock_init(&host->lock);
 	INIT_WORK(&host->fsm_task, carm_fsm_task, host);
-	init_MUTEX_LOCKED(&host->probe_sem);
+	init_completion(&host->probe_comp);
 
 	for (i = 0; i < ARRAY_SIZE(host->req); i++)
 		host->req[i].tag = i;
@@ -1691,8 +1691,8 @@ static int carm_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto err_out_free_irq;
 
-	DPRINTK("waiting for probe_sem\n");
-	down(&host->probe_sem);
+	DPRINTK("waiting for probe_comp\n");
+	wait_for_completion(&host->probe_comp);
 
 	printk(KERN_INFO "%s: pci %s, ports %d, io %lx, irq %u, major %d\n",
 	       host->name, pci_name(pdev), (int) CARM_MAX_PORTS,

drivers/char/mem.c

@@ -741,7 +741,7 @@ static loff_t memory_lseek(struct file * file, loff_t offset, int orig)
 {
 	loff_t ret;
 
-	down(&file->f_dentry->d_inode->i_sem);
+	mutex_lock(&file->f_dentry->d_inode->i_mutex);
 	switch (orig) {
 		case 0:
 			file->f_pos = offset;
@@ -756,7 +756,7 @@ static loff_t memory_lseek(struct file * file, loff_t offset, int orig)
 		default:
 			ret = -EINVAL;
 	}
-	up(&file->f_dentry->d_inode->i_sem);
+	mutex_unlock(&file->f_dentry->d_inode->i_mutex);
 	return ret;
 }
 

drivers/char/sysrq.c

@@ -153,6 +153,21 @@ static struct sysrq_key_op sysrq_mountro_op = {
 
 /* END SYNC SYSRQ HANDLERS BLOCK */
 
+#ifdef CONFIG_DEBUG_MUTEXES
+
+static void
+sysrq_handle_showlocks(int key, struct pt_regs *pt_regs, struct tty_struct *tty)
+{
+	mutex_debug_show_all_locks();
+}
+
+static struct sysrq_key_op sysrq_showlocks_op = {
+	.handler	= sysrq_handle_showlocks,
+	.help_msg	= "show-all-locks(D)",
+	.action_msg	= "Show Locks Held",
+};
+
+#endif
 
 /* SHOW SYSRQ HANDLERS BLOCK */
 
@@ -294,7 +309,11 @@ static struct sysrq_key_op *sysrq_key_table[SYSRQ_KEY_TABLE_LENGTH] = {
 #else
 /* c */	NULL,
 #endif
+#ifdef CONFIG_DEBUG_MUTEXES
+/* d */ &sysrq_showlocks_op,
+#else
 /* d */ NULL,
+#endif
 /* e */	&sysrq_term_op,
 /* f */	&sysrq_moom_op,
 /* g */	NULL,

drivers/char/watchdog/cpu5wdt.c

@@ -28,6 +28,7 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/timer.h>
+#include <linux/completion.h>
 #include <linux/jiffies.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
@@ -57,7 +58,7 @@ static int ticks = 10000;
 /* some device data */
 
 static struct {
-	struct semaphore stop;
+	struct completion stop;
 	volatile int running;
 	struct timer_list timer;
 	volatile int queue;
@@ -85,7 +86,7 @@ static void cpu5wdt_trigger(unsigned long unused)
 	}
 	else {
 		/* ticks doesn't matter anyway */
-		up(&cpu5wdt_device.stop);
+		complete(&cpu5wdt_device.stop);
 	}
 
 }
@@ -239,7 +240,7 @@ static int __devinit cpu5wdt_init(void)
 	if ( !val )
 		printk(KERN_INFO PFX "sorry, was my fault\n");
 
-	init_MUTEX_LOCKED(&cpu5wdt_device.stop);
+	init_completion(&cpu5wdt_device.stop);
 	cpu5wdt_device.queue = 0;
 
 	clear_bit(0, &cpu5wdt_device.inuse);
@@ -269,7 +270,7 @@ static void __devexit cpu5wdt_exit(void)
 {
 	if ( cpu5wdt_device.queue ) {
 		cpu5wdt_device.queue = 0;
-		down(&cpu5wdt_device.stop);
+		wait_for_completion(&cpu5wdt_device.stop);
 	}
 
 	misc_deregister(&cpu5wdt_misc);

drivers/ide/ide-probe.c

@@ -655,7 +655,7 @@ static void hwif_release_dev (struct device *dev)
 {
 	ide_hwif_t *hwif = container_of(dev, ide_hwif_t, gendev);
 
-	up(&hwif->gendev_rel_sem);
+	complete(&hwif->gendev_rel_comp);
 }
 
 static void hwif_register (ide_hwif_t *hwif)
@@ -1327,7 +1327,7 @@ static void drive_release_dev (struct device *dev)
 	drive->queue = NULL;
 	spin_unlock_irq(&ide_lock);
 
-	up(&drive->gendev_rel_sem);
+	complete(&drive->gendev_rel_comp);
 }
 
 /*

drivers/ide/ide.c

@@ -222,7 +222,7 @@ static void init_hwif_data(ide_hwif_t *hwif, unsigned int index)
 	hwif->mwdma_mask = 0x80;	/* disable all mwdma */
 	hwif->swdma_mask = 0x80;	/* disable all swdma */
 
-	sema_init(&hwif->gendev_rel_sem, 0);
+	init_completion(&hwif->gendev_rel_comp);
 
 	default_hwif_iops(hwif);
 	default_hwif_transport(hwif);
@@ -245,7 +245,7 @@ static void init_hwif_data(ide_hwif_t *hwif, unsigned int index)
 		drive->is_flash			= 0;
 		drive->vdma			= 0;
 		INIT_LIST_HEAD(&drive->list);
-		sema_init(&drive->gendev_rel_sem, 0);
+		init_completion(&drive->gendev_rel_comp);
 	}
 }
 
@@ -602,7 +602,7 @@ void ide_unregister(unsigned int index)
 		}
 		spin_unlock_irq(&ide_lock);
 		device_unregister(&drive->gendev);
-		down(&drive->gendev_rel_sem);
+		wait_for_completion(&drive->gendev_rel_comp);
 		spin_lock_irq(&ide_lock);
 	}
 	hwif->present = 0;
@@ -662,7 +662,7 @@ void ide_unregister(unsigned int index)
 	/* More messed up locking ... */
 	spin_unlock_irq(&ide_lock);
 	device_unregister(&hwif->gendev);
-	down(&hwif->gendev_rel_sem);
+	wait_for_completion(&hwif->gendev_rel_comp);
 
 	/*
 	 * Remove us from the kernel's knowledge

drivers/isdn/capi/capifs.c

@@ -138,7 +138,7 @@ static struct dentry *get_node(int num)
 {
 	char s[10];
 	struct dentry *root = capifs_root;
-	down(&root->d_inode->i_sem);
+	mutex_lock(&root->d_inode->i_mutex);
 	return lookup_one_len(s, root, sprintf(s, "%d", num));
 }
 
@@ -159,7 +159,7 @@ void capifs_new_ncci(unsigned int number, dev_t device)
 	dentry = get_node(number);
 	if (!IS_ERR(dentry) && !dentry->d_inode)
 		d_instantiate(dentry, inode);
-	up(&capifs_root->d_inode->i_sem);
+	mutex_unlock(&capifs_root->d_inode->i_mutex);
 }
 
 void capifs_free_ncci(unsigned int number)
@@ -175,7 +175,7 @@ void capifs_free_ncci(unsigned int number)
 		}
 		dput(dentry);
 	}
-	up(&capifs_root->d_inode->i_sem);
+	mutex_unlock(&capifs_root->d_inode->i_mutex);
 }
 
 static int __init capifs_init(void)

drivers/md/dm.c

@@ -837,9 +837,9 @@ static void __set_size(struct mapped_device *md, sector_t size)
 {
 	set_capacity(md->disk, size);
 
-	down(&md->suspended_bdev->bd_inode->i_sem);
+	mutex_lock(&md->suspended_bdev->bd_inode->i_mutex);
 	i_size_write(md->suspended_bdev->bd_inode, (loff_t)size << SECTOR_SHIFT);
-	up(&md->suspended_bdev->bd_inode->i_sem);
+	mutex_unlock(&md->suspended_bdev->bd_inode->i_mutex);
 }
 
 static int __bind(struct mapped_device *md, struct dm_table *t)

drivers/md/md.c

@@ -3460,9 +3460,9 @@ static int update_size(mddev_t *mddev, unsigned long size)
 
 		bdev = bdget_disk(mddev->gendisk, 0);
 		if (bdev) {
-			down(&bdev->bd_inode->i_sem);
+			mutex_lock(&bdev->bd_inode->i_mutex);
 			i_size_write(bdev->bd_inode, mddev->array_size << 10);
-			up(&bdev->bd_inode->i_sem);
+			mutex_unlock(&bdev->bd_inode->i_mutex);
 			bdput(bdev);
 		}
 	}
@@ -3486,9 +3486,9 @@ static int update_raid_disks(mddev_t *mddev, int raid_disks)
 
 		bdev = bdget_disk(mddev->gendisk, 0);
 		if (bdev) {
-			down(&bdev->bd_inode->i_sem);
+			mutex_lock(&bdev->bd_inode->i_mutex);
 			i_size_write(bdev->bd_inode, mddev->array_size << 10);
-			up(&bdev->bd_inode->i_sem);
+			mutex_unlock(&bdev->bd_inode->i_mutex);
 			bdput(bdev);
 		}
 	}

drivers/pci/proc.c

@@ -25,7 +25,7 @@ proc_bus_pci_lseek(struct file *file, loff_t off, int whence)
 	loff_t new = -1;
 	struct inode *inode = file->f_dentry->d_inode;
 
-	down(&inode->i_sem);
+	mutex_lock(&inode->i_mutex);
 	switch (whence) {
 	case 0:
 		new = off;
@@ -41,7 +41,7 @@ proc_bus_pci_lseek(struct file *file, loff_t off, int whence)
 		new = -EINVAL;
 	else
 		file->f_pos = new;
-	up(&inode->i_sem);
+	mutex_unlock(&inode->i_mutex);
 	return new;
 }
 

drivers/usb/core/inode.c

@@ -184,13 +184,13 @@ static void update_bus(struct dentry *bus)
 	bus->d_inode->i_gid = busgid;
 	bus->d_inode->i_mode = S_IFDIR | busmode;
 
-	down(&bus->d_inode->i_sem);
+	mutex_lock(&bus->d_inode->i_mutex);
 
 	list_for_each_entry(dev, &bus->d_subdirs, d_u.d_child)
 		if (dev->d_inode)
 			update_dev(dev);
 
-	up(&bus->d_inode->i_sem);
+	mutex_unlock(&bus->d_inode->i_mutex);
 }
 
 static void update_sb(struct super_block *sb)
@@ -201,7 +201,7 @@ static void update_sb(struct super_block *sb)
 	if (!root)
 		return;
 
-	down(&root->d_inode->i_sem);
+	mutex_lock(&root->d_inode->i_mutex);
 
 	list_for_each_entry(bus, &root->d_subdirs, d_u.d_child) {
 		if (bus->d_inode) {
@@ -219,7 +219,7 @@ static void update_sb(struct super_block *sb)
 		}
 	}
 
-	up(&root->d_inode->i_sem);
+	mutex_unlock(&root->d_inode->i_mutex);
 }
 
 static int remount(struct super_block *sb, int *flags, char *data)
@@ -333,10 +333,10 @@ static int usbfs_empty (struct dentry *dentry)
 static int usbfs_unlink (struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode = dentry->d_inode;
-	down(&inode->i_sem);
+	mutex_lock(&inode->i_mutex);
 	dentry->d_inode->i_nlink--;
 	dput(dentry);
-	up(&inode->i_sem);
+	mutex_unlock(&inode->i_mutex);
 	d_delete(dentry);
 	return 0;
 }
@@ -346,7 +346,7 @@ static int usbfs_rmdir(struct inode *dir, struct dentry *dentry)
 	int error = -ENOTEMPTY;
 	struct inode * inode = dentry->d_inode;
 
-	down(&inode->i_sem);
+	mutex_lock(&inode->i_mutex);
 	dentry_unhash(dentry);
 	if (usbfs_empty(dentry)) {
 		dentry->d_inode->i_nlink -= 2;
@@ -355,7 +355,7 @@ static int usbfs_rmdir(struct inode *dir, struct dentry *dentry)
 		dir->i_nlink--;
 		error = 0;
 	}
-	up(&inode->i_sem);
+	mutex_unlock(&inode->i_mutex);
 	if (!error)
 		d_delete(dentry);
 	dput(dentry);
@@ -380,7 +380,7 @@ static loff_t default_file_lseek (struct file *file, loff_t offset, int orig)
 {
 	loff_t retval = -EINVAL;
 
-	down(&file->f_dentry->d_inode->i_sem);
+	mutex_lock(&file->f_dentry->d_inode->i_mutex);
 	switch(orig) {
 	case 0:
 		if (offset > 0) {
@@ -397,7 +397,7 @@ static loff_t default_file_lseek (struct file *file, loff_t offset, int orig)
 	default:
 		break;
 	}
-	up(&file->f_dentry->d_inode->i_sem);
+	mutex_unlock(&file->f_dentry->d_inode->i_mutex);
 	return retval;
 }
 
@@ -480,7 +480,7 @@ static int fs_create_by_name (const char *name, mode_t mode,
 	}
 
 	*dentry = NULL;
-	down(&parent->d_inode->i_sem);
+	mutex_lock(&parent->d_inode->i_mutex);
 	*dentry = lookup_one_len(name, parent, strlen(name));
 	if (!IS_ERR(dentry)) {
 		if ((mode & S_IFMT) == S_IFDIR)
@@ -489,7 +489,7 @@ static int fs_create_by_name (const char *name, mode_t mode,
 			error = usbfs_create (parent->d_inode, *dentry, mode);
 	} else
 		error = PTR_ERR(dentry);
-	up(&parent->d_inode->i_sem);
+	mutex_unlock(&parent->d_inode->i_mutex);
 
 	return error;
 }
@@ -528,7 +528,7 @@ static void fs_remove_file (struct dentry *dentry)
 	if (!parent || !parent->d_inode)
 		return;
 
-	down(&parent->d_inode->i_sem);
+	mutex_lock(&parent->d_inode->i_mutex);
 	if (usbfs_positive(dentry)) {
 		if (dentry->d_inode) {
 			if (S_ISDIR(dentry->d_inode->i_mode))
@@ -538,7 +538,7 @@ static void fs_remove_file (struct dentry *dentry)
 		dput(dentry);
 		}
 	}
-	up(&parent->d_inode->i_sem);
+	mutex_unlock(&parent->d_inode->i_mutex);
 }
 
 /* --------------------------------------------------------------------- */

drivers/usb/gadget/file_storage.c

@@ -1891,7 +1891,7 @@ static int fsync_sub(struct lun *curlun)
 		return -EINVAL;
 
 	inode = filp->f_dentry->d_inode;
-	down(&inode->i_sem);
+	mutex_lock(&inode->i_mutex);
 	current->flags |= PF_SYNCWRITE;
 	rc = filemap_fdatawrite(inode->i_mapping);
 	err = filp->f_op->fsync(filp, filp->f_dentry, 1);
@@ -1901,7 +1901,7 @@ static int fsync_sub(struct lun *curlun)
 	if (!rc)
 		rc = err;
 	current->flags &= ~PF_SYNCWRITE;
-	up(&inode->i_sem);
+	mutex_unlock(&inode->i_mutex);
 	VLDBG(curlun, "fdatasync -> %d\n", rc);
 	return rc;
 }

drivers/usb/gadget/inode.c

@@ -1562,10 +1562,10 @@ restart:
 		spin_unlock_irq (&dev->lock);
 
 		/* break link to dcache */
-		down (&parent->i_sem);
+		mutex_lock (&parent->i_mutex);
 		d_delete (dentry);
 		dput (dentry);
-		up (&parent->i_sem);
+		mutex_unlock (&parent->i_mutex);
 
 		/* fds may still be open */
 		goto restart;

fs/affs/inode.c

@@ -244,10 +244,10 @@ affs_put_inode(struct inode *inode)
 	pr_debug("AFFS: put_inode(ino=%lu, nlink=%u)\n", inode->i_ino, inode->i_nlink);
 	affs_free_prealloc(inode);
 	if (atomic_read(&inode->i_count) == 1) {
-		down(&inode->i_sem);
+		mutex_lock(&inode->i_mutex);
 		if (inode->i_size != AFFS_I(inode)->mmu_private)
 			affs_truncate(inode);
-		up(&inode->i_sem);
+		mutex_unlock(&inode->i_mutex);
 	}
 }
 

fs/autofs/root.c

@@ -229,9 +229,9 @@ static struct dentry *autofs_root_lookup(struct inode *dir, struct dentry *dentr
 	dentry->d_flags |= DCACHE_AUTOFS_PENDING;
 	d_add(dentry, NULL);
 
-	up(&dir->i_sem);
+	mutex_unlock(&dir->i_mutex);
 	autofs_revalidate(dentry, nd);
-	down(&dir->i_sem);
+	mutex_lock(&dir->i_mutex);
 
 	/*
 	 * If we are still pending, check if we had to handle