Merge bk://linuxusb.bkbits.net/gregkh-2.6

into home.osdl.org:/home/torvalds/v2.5/linux

drivers/block/scsi_ioctl.c

@@ -150,6 +150,7 @@ static int sg_io(request_queue_t *q, struct block_device *bdev,
 	struct request *rq;
 	struct bio *bio;
 	char sense[SCSI_SENSE_BUFFERSIZE];
+	unsigned char cdb[BLK_MAX_CDB];
 	void *buffer;
 
 	if (hdr->interface_id != 'S')
@@ -166,6 +167,9 @@ static int sg_io(request_queue_t *q, struct block_device *bdev,
 	if (hdr->dxfer_len > (q->max_sectors << 9))
 		return -EIO;
 
+	if (copy_from_user(cdb, hdr->cmdp, hdr->cmd_len))
+		return -EFAULT;
+
 	reading = writing = 0;
 	buffer = NULL;
 	bio = NULL;
@@ -216,12 +220,7 @@ static int sg_io(request_queue_t *q, struct block_device *bdev,
 	 * fill in request structure
 	 */
 	rq->cmd_len = hdr->cmd_len;
-
-	if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len)) {
-		blk_put_request(rq);
-		return -EFAULT;
-	}
-
+	memcpy(rq->cmd, cdb, hdr->cmd_len);
 	if (sizeof(rq->cmd) != hdr->cmd_len)
 		memset(rq->cmd + hdr->cmd_len, 0, sizeof(rq->cmd) - hdr->cmd_len);
 

drivers/md/raid5.c

@@ -40,6 +40,16 @@
 
 #define stripe_hash(conf, sect)	((conf)->stripe_hashtbl[((sect) >> STRIPE_SHIFT) & HASH_MASK])
 
+/* bio's attached to a stripe+device for I/O are linked together in bi_sector
+ * order without overlap.  There may be several bio's per stripe+device, and
+ * a bio could span several devices.
+ * When walking this list for a particular stripe+device, we must never proceed
+ * beyond a bio that extends past this device, as the next bio might no longer
+ * be valid.
+ * This macro is used to determine the 'next' bio in the list, given the sector
+ * of the current stripe+device
+ */
+#define r5_next_bio(bio, sect) ( ( bio->bi_sector + (bio->bi_size>>9) < sect + STRIPE_SECTORS) ? bio->bi_next : NULL)
 /*
  * The following can be used to debug the driver
  */
@@ -613,7 +623,7 @@ static void copy_data(int frombio, struct bio *bio,
 	int i;
 
 	for (;bio && bio->bi_sector < sector+STRIPE_SECTORS;
-		bio = bio->bi_next) {
+	      bio = r5_next_bio(bio, sector) ) {
 		int page_offset;
 		if (bio->bi_sector >= sector)
 			page_offset = (signed)(bio->bi_sector - sector) * 512;
@@ -738,7 +748,11 @@ static void compute_parity(struct stripe_head *sh, int method)
 	for (i = disks; i--;)
 		if (sh->dev[i].written) {
 			sector_t sector = sh->dev[i].sector;
-			copy_data(1, sh->dev[i].written, sh->dev[i].page, sector);
+			struct bio *wbi = sh->dev[i].written;
+			while (wbi && wbi->bi_sector < sector + STRIPE_SECTORS) {
+				copy_data(1, wbi, sh->dev[i].page, sector);
+				wbi = r5_next_bio(wbi, sector);
+			}
 
 			set_bit(R5_LOCKED, &sh->dev[i].flags);
 			set_bit(R5_UPTODATE, &sh->dev[i].flags);
@@ -791,8 +805,10 @@ static void add_stripe_bio (struct stripe_head *sh, struct bio *bi, int dd_idx,
 		bip = &sh->dev[dd_idx].towrite;
 	else
 		bip = &sh->dev[dd_idx].toread;
-	while (*bip && (*bip)->bi_sector < bi->bi_sector)
+	while (*bip && (*bip)->bi_sector < bi->bi_sector) {
+		BUG_ON((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector);
 		bip = & (*bip)->bi_next;
+	}
 /* FIXME do I need to worry about overlapping bion */
 	if (*bip && bi->bi_next && (*bip) != bi->bi_next)
 		BUG();
@@ -813,7 +829,7 @@ static void add_stripe_bio (struct stripe_head *sh, struct bio *bi, int dd_idx,
 		for (bi=sh->dev[dd_idx].towrite;
 		     sector < sh->dev[dd_idx].sector + STRIPE_SECTORS &&
 			     bi && bi->bi_sector <= sector;
-		     bi = bi->bi_next) {
+		     bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) {
 			if (bi->bi_sector + (bi->bi_size>>9) >= sector)
 				sector = bi->bi_sector + (bi->bi_size>>9);
 		}
@@ -883,7 +899,7 @@ static void handle_stripe(struct stripe_head *sh)
 			spin_unlock_irq(&conf->device_lock);
 			while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) {
 				copy_data(0, rbi, dev->page, dev->sector);
-				rbi2 = rbi->bi_next;
+				rbi2 = r5_next_bio(rbi, dev->sector);
 				spin_lock_irq(&conf->device_lock);
 				if (--rbi->bi_phys_segments == 0) {
 					rbi->bi_next = return_bi;
@@ -928,7 +944,7 @@ static void handle_stripe(struct stripe_head *sh)
 			if (bi) to_write--;
 
 			while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS){
-				struct bio *nextbi = bi->bi_next;
+				struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
 				clear_bit(BIO_UPTODATE, &bi->bi_flags);
 				if (--bi->bi_phys_segments == 0) {
 					md_write_end(conf->mddev);
@@ -941,7 +957,7 @@ static void handle_stripe(struct stripe_head *sh)
 			bi = sh->dev[i].written;
 			sh->dev[i].written = NULL;
 			while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) {
-				struct bio *bi2 = bi->bi_next;
+				struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
 				clear_bit(BIO_UPTODATE, &bi->bi_flags);
 				if (--bi->bi_phys_segments == 0) {
 					md_write_end(conf->mddev);
@@ -957,7 +973,7 @@ static void handle_stripe(struct stripe_head *sh)
 				sh->dev[i].toread = NULL;
 				if (bi) to_read--;
 				while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS){
-					struct bio *nextbi = bi->bi_next;
+					struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
 					clear_bit(BIO_UPTODATE, &bi->bi_flags);
 					if (--bi->bi_phys_segments == 0) {
 						bi->bi_next = return_bi;
@@ -1000,7 +1016,7 @@ static void handle_stripe(struct stripe_head *sh)
 			    wbi = dev->written;
 			    dev->written = NULL;
 			    while (wbi && wbi->bi_sector < dev->sector + STRIPE_SECTORS) {
-				    wbi2 = wbi->bi_next;
+				    wbi2 = r5_next_bio(wbi, dev->sector);
 				    if (--wbi->bi_phys_segments == 0) {
 					    md_write_end(conf->mddev);
 					    wbi->bi_next = return_bi;

fs/hpfs/dir.c

@@ -65,6 +65,8 @@ int hpfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	int c1, c2 = 0;
 	int ret = 0;
 
+	lock_kernel();
+
 	if (hpfs_sb(inode->i_sb)->sb_chk) {
 		if (hpfs_chk_sectors(inode->i_sb, inode->i_ino, 1, "dir_fnode")) {
 			ret = -EFSERROR;

include/linux/blkdev.h

@@ -82,6 +82,8 @@ struct request_list {
 	wait_queue_head_t wait[2];
 };
 
+#define BLK_MAX_CDB	16
+
 /*
  * try to put the fields that are referenced together in the same cacheline
  */
@@ -147,7 +149,7 @@ struct request {
 	 * when request is used as a packet command carrier
 	 */
 	unsigned int cmd_len;
-	unsigned char cmd[16];
+	unsigned char cmd[BLK_MAX_CDB];
 
 	unsigned int data_len;
 	void *data;

include/linux/list.h

@@ -208,6 +208,18 @@ static inline int list_empty(const struct list_head *head)
 	return head->next == head;
 }
 
+/**
+ * list_empty_careful - tests whether a list is
+ * empty _and_ checks that no other CPU might be
+ * in the process of still modifying either member
+ * @head: the list to test.
+ */
+static inline int list_empty_careful(const struct list_head *head)
+{
+	struct list_head *next = head->next;
+	return (next == head) && (next == head->prev);
+}
+
 static inline void __list_splice(struct list_head *list,
 				 struct list_head *head)
 {

kernel/exit.c

@@ -49,9 +49,11 @@ static void __unhash_process(struct task_struct *p)
 
 void release_task(struct task_struct * p)
 {
+	int zap_leader;
 	task_t *leader;
 	struct dentry *proc_dentry;
- 
+
+repeat: 
 	BUG_ON(p->state < TASK_ZOMBIE);
  
 	atomic_dec(&p->user->processes);
@@ -70,10 +72,21 @@ void release_task(struct task_struct * p)
 	 * group, and the leader is zombie, then notify the
 	 * group leader's parent process. (if it wants notification.)
 	 */
+	zap_leader = 0;
 	leader = p->group_leader;
-	if (leader != p && thread_group_empty(leader) &&
-		    leader->state == TASK_ZOMBIE && leader->exit_signal != -1)
+	if (leader != p && thread_group_empty(leader) && leader->state == TASK_ZOMBIE) {
+		BUG_ON(leader->exit_signal == -1);
 		do_notify_parent(leader, leader->exit_signal);
+		/*
+		 * If we were the last child thread and the leader has
+		 * exited already, and the leader's parent ignores SIGCHLD,
+		 * then we are the one who should release the leader.
+		 *
+		 * do_notify_parent() will have marked it self-reaping in
+		 * that case.
+		 */
+		zap_leader = (leader->exit_signal == -1);
+	}
 
 	p->parent->cutime += p->utime + p->cutime;
 	p->parent->cstime += p->stime + p->cstime;
@@ -88,6 +101,10 @@ void release_task(struct task_struct * p)
 	proc_pid_flush(proc_dentry);
 	release_thread(p);
 	put_task_struct(p);
+
+	p = leader;
+	if (unlikely(zap_leader))
+		goto repeat;
 }
 
 /* we are using it only for SMP init */

kernel/fork.c

@@ -125,15 +125,28 @@ void remove_wait_queue(wait_queue_head_t *q, wait_queue_t * wait)
 
 EXPORT_SYMBOL(remove_wait_queue);
 
+
+/*
+ * Note: we use "set_current_state()" _after_ the wait-queue add,
+ * because we need a memory barrier there on SMP, so that any
+ * wake-function that tests for the wait-queue being active
+ * will be guaranteed to see waitqueue addition _or_ subsequent
+ * tests in this thread will see the wakeup having taken place.
+ *
+ * The spin_unlock() itself is semi-permeable and only protects
+ * one way (it only protects stuff inside the critical region and
+ * stops them from bleeding out - it would still allow subsequent
+ * loads to move into the the critical region).
+ */
 void prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state)
 {
 	unsigned long flags;
 
-	__set_current_state(state);
 	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
 	spin_lock_irqsave(&q->lock, flags);
 	if (list_empty(&wait->task_list))
 		__add_wait_queue(q, wait);
+	set_current_state(state);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 
@@ -144,11 +157,11 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
 {
 	unsigned long flags;
 
-	__set_current_state(state);
 	wait->flags |= WQ_FLAG_EXCLUSIVE;
 	spin_lock_irqsave(&q->lock, flags);
 	if (list_empty(&wait->task_list))
 		__add_wait_queue_tail(q, wait);
+	set_current_state(state);
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 
@@ -159,7 +172,20 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 	unsigned long flags;
 
 	__set_current_state(TASK_RUNNING);
-	if (!list_empty(&wait->task_list)) {
+	/*
+	 * We can check for list emptiness outside the lock
+	 * IFF:
+	 *  - we use the "careful" check that verifies both
+	 *    the next and prev pointers, so that there cannot
+	 *    be any half-pending updates in progress on other
+	 *    CPU's that we haven't seen yet (and that might
+	 *    still change the stack area.
+	 * and
+	 *  - all other users take the lock (ie we can only
+	 *    have _one_ other CPU that looks at or modifies
+	 *    the list).
+	 */
+	if (!list_empty_careful(&wait->task_list)) {
 		spin_lock_irqsave(&q->lock, flags);
 		list_del_init(&wait->task_list);
 		spin_unlock_irqrestore(&q->lock, flags);