Merge delerium.codemonkey.org.uk:/mnt/nfs/sepia/bar/src/kernel/2.6/trees/bk-linus

into delerium.codemonkey.org.uk:/mnt/nfs/sepia/bar/src/kernel/2.6/trees/agpgart

arch/i386/mm/fault.c

@@ -359,7 +359,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code)
 			return;
 
 		tsk->thread.cr2 = address;
-		tsk->thread.error_code = error_code;
+		/* Kernel addresses are always protection faults */
+		tsk->thread.error_code = error_code | (address >= TASK_SIZE);
 		tsk->thread.trap_no = 14;
 		info.si_signo = SIGSEGV;
 		info.si_errno = 0;

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;
@@ -216,7 +220,7 @@ static int sg_io(request_queue_t *q, struct block_device *bdev,
 	 * fill in request structure
 	 */
 	rq->cmd_len = hdr->cmd_len;
-	memcpy(rq->cmd, hdr->cmdp, hdr->cmd_len);
+	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/i2c/busses/i2c-nforce2.c

@@ -147,7 +147,7 @@ static s32 nforce2_access(struct i2c_adapter * adap, u16 addr,
 
 		case I2C_SMBUS_BYTE:
 			if (read_write == I2C_SMBUS_WRITE)
-				outb_p(data->byte, NVIDIA_SMB_DATA);
+				outb_p(command, NVIDIA_SMB_CMD);
 			protocol |= NVIDIA_SMB_PRTCL_BYTE;
 			break;
 

drivers/net/pci-skeleton.c

@@ -864,13 +864,6 @@ static void __devexit netdrv_remove_one (struct pci_dev *pdev)
 
 	pci_release_regions (pdev);
 
-#ifndef NETDRV_NDEBUG
-	/* poison memory before freeing */
-	memset (dev, 0xBC,
-		sizeof (struct net_device) +
-		sizeof (struct netdrv_private));
-#endif /* NETDRV_NDEBUG */
-
 	free_netdev (dev);
 
 	pci_set_drvdata (pdev, NULL);

drivers/net/pcnet32.c

@@ -1766,8 +1766,6 @@ static void __exit pcnet32_cleanup_module(void)
 	next_dev = lp->next;
 	unregister_netdev(pcnet32_dev);
 	release_region(pcnet32_dev->base_addr, PCNET32_TOTAL_SIZE);
-	if (lp->pci_dev)
-	    pci_unregister_driver(&pcnet32_driver);
 	pci_free_consistent(lp->pci_dev, sizeof(*lp), lp, lp->dma_addr);
 	free_netdev(pcnet32_dev);
 	pcnet32_dev = next_dev;

drivers/net/r8169.c

@@ -642,10 +642,6 @@ rtl8169_remove_one(struct pci_dev *pdev)
 	iounmap(tp->mmio_addr);
 	pci_release_regions(pdev);
 
-	// poison memory before freeing 
-	memset(dev, 0xBC,
-	       sizeof (struct net_device) + sizeof (struct rtl8169_private));
-
 	pci_disable_device(pdev);
 	free_netdev(dev);
 	pci_set_drvdata(pdev, NULL);

drivers/net/sis190.c

@@ -703,10 +703,6 @@ SiS190_remove_one(struct pci_dev *pdev)
 	iounmap(tp->mmio_addr);
 	pci_release_regions(pdev);
 
-	// poison memory before freeing 
-	memset(dev, 0xBC,
-	       sizeof (struct net_device) + sizeof (struct sis190_private));
-
 	free_netdev(dev);
 	pci_set_drvdata(pdev, NULL);
 }

drivers/net/wireless/airo.c

@@ -2466,11 +2466,8 @@ static irqreturn_t airo_interrupt ( int irq, void* dev_id, struct pt_regs *regs)
 			OUT4500( apriv, EVACK, EV_MIC );
 #ifdef MICSUPPORT
 			if (test_bit(FLAG_MIC_CAPABLE, &apriv->flags)) {
-				if (down_trylock(&apriv->sem) != 0) {
 				set_bit(JOB_MIC, &apriv->flags);
 				wake_up_interruptible(&apriv->thr_wait);
-				} else
-					micinit (apriv);
 			}
 #endif
 		}

drivers/scsi/ide-scsi.c

@@ -517,6 +517,7 @@ static ide_startstop_t idescsi_issue_pc (ide_drive_t *drive, idescsi_pc_t *pc)
 	pc->current_position=pc->buffer;
 	bcount.all = IDE_MIN(pc->request_transfer, 63 * 1024);		/* Request to transfer the entire buffer at once */
 
+	feature.all = 0;
 	if (drive->using_dma && rq->bio) {
 		if (test_bit(PC_WRITING, &pc->flags))
 			feature.b.dma = !HWIF(drive)->ide_dma_write(drive);

drivers/scsi/libata-core.c

@@ -3224,8 +3224,6 @@ void ata_pci_remove_one (struct pci_dev *pdev)
 		scsi_host_put(ap->host); /* FIXME: check return val */
 	}
 
-	kfree(host_set);
-
 	pci_release_regions(pdev);
 
 	for (i = 0; i < host_set->n_ports; i++) {
@@ -3242,6 +3240,7 @@ void ata_pci_remove_one (struct pci_dev *pdev)
 		}
 	}
 
+	kfree(host_set);
 	pci_disable_device(pdev);
 	pci_set_drvdata(pdev, NULL);
 }

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;

fs/libfs.c

@@ -79,6 +79,7 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin)
 			loff_t n = file->f_pos - 2;
 
 			spin_lock(&dcache_lock);
+			list_del(&cursor->d_child);
 			p = file->f_dentry->d_subdirs.next;
 			while (n && p != &file->f_dentry->d_subdirs) {
 				struct dentry *next;
@@ -87,7 +88,6 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin)
 					n--;
 				p = p->next;
 			}
-			list_del(&cursor->d_child);
 			list_add_tail(&cursor->d_child, p);
 			spin_unlock(&dcache_lock);
 		}

fs/proc/base.c

@@ -1666,10 +1666,14 @@ static int get_tid_list(int index, unsigned int *tids, struct inode *dir)
 
 	index -= 2;
 	read_lock(&tasklist_lock);
-	do {
+	/*
+	 * The starting point task (leader_task) might be an already
+	 * unlinked task, which cannot be used to access the task-list
+	 * via next_thread().
+	 */
+	if (pid_alive(task)) do {
 		int tid = task->pid;
-		if (!pid_alive(task))
-			continue;
+
 		if (--index >= 0)
 			continue;
 		tids[nr_tids] = tid;

include/asm-x86_64/msr.h

@@ -50,9 +50,9 @@
      __asm__ __volatile__ ("rdtsc" : "=a" (low) : : "edx")
 
 #define rdtscll(val) do { \
-     unsigned int a,d; \
-     asm volatile("rdtsc" : "=a" (a), "=d" (d)); \
-     (val) = ((unsigned long)a) | (((unsigned long)d)<<32); \
+     unsigned int __a,__d; \
+     asm volatile("rdtsc" : "=a" (__a), "=d" (__d)); \
+     (val) = ((unsigned long)__a) | (((unsigned long)__d)<<32); \
 } while(0)
 
 #define rdpmc(counter,low,high) \

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)
 {

include/linux/rtnetlink.h

@@ -138,6 +138,7 @@ enum
 #define RTPROT_ZEBRA	11	/* Zebra */
 #define RTPROT_BIRD	12	/* BIRD */
 #define RTPROT_DNROUTED	13	/* DECnet routing daemon */
+#define RTPROT_XORP	14	/* XORP */
 
 /* rtm_scope
 

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);

kernel/sched.c

@@ -646,7 +646,7 @@ static int try_to_wake_up(task_t * p, unsigned int state, int sync)
 				 */
 				p->activated = -1;
 			}
-			if (sync)
+			if (sync && (task_cpu(p) == smp_processor_id()))
 				__activate_task(p, rq);
 			else {
 				activate_task(p, rq);

mm/mmap.c

@@ -19,6 +19,7 @@
 #include <linux/hugetlb.h>
 #include <linux/profile.h>
 #include <linux/module.h>
+#include <linux/mount.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgalloc.h>
@@ -474,9 +475,14 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 	struct rb_node ** rb_link, * rb_parent;
 	unsigned long charged = 0;
 
-	if (file && (!file->f_op || !file->f_op->mmap))
+	if (file) {
+		if (!file->f_op || !file->f_op->mmap)
 			return -ENODEV;
 
+		if ((prot & PROT_EXEC) && (file->f_vfsmnt->mnt_flags & MNT_NOEXEC))
+			return -EPERM;
+	}
+
 	if (!len)
 		return addr;
 

net/bridge/br_netfilter.c

@@ -180,7 +180,7 @@ static int br_nf_pre_routing_finish(struct sk_buff *skb)
 			struct rtable *rt;
 			struct flowi fl = { .nl_u = 
 			{ .ip4_u = { .daddr = iph->daddr, .saddr = 0 ,
-				     .tos = iph->tos} }, .proto = 0};
+				     .tos = RT_TOS(iph->tos)} }, .proto = 0};
 
 			if (!ip_route_output_key(&rt, &fl)) {
 				/* Bridged-and-DNAT'ed traffic doesn't

net/ipv4/netfilter/ip_conntrack_proto_tcp.c

@@ -53,7 +53,7 @@ unsigned long ip_ct_tcp_timeout_syn_sent =      2 MINS;
 unsigned long ip_ct_tcp_timeout_syn_recv =     60 SECS;
 unsigned long ip_ct_tcp_timeout_established =   5 DAYS;
 unsigned long ip_ct_tcp_timeout_fin_wait =      2 MINS;
-unsigned long ip_ct_tcp_timeout_close_wait =    3 DAYS;
+unsigned long ip_ct_tcp_timeout_close_wait =   60 SECS;
 unsigned long ip_ct_tcp_timeout_last_ack =     30 SECS;
 unsigned long ip_ct_tcp_timeout_time_wait =     2 MINS;
 unsigned long ip_ct_tcp_timeout_close =        10 SECS;

net/ipv4/netfilter/ip_conntrack_standalone.c

@@ -201,7 +201,8 @@ static unsigned int ip_refrag(unsigned int hooknum,
 	/* Local packets are never produced too large for their
 	   interface.  We degfragment them at LOCAL_OUT, however,
 	   so we have to refragment them here. */
-	if ((*pskb)->len > dst_pmtu(&rt->u.dst)) {
+	if ((*pskb)->len > dst_pmtu(&rt->u.dst) &&
+	    !skb_shinfo(*pskb)->tso_size) {
 		/* No hook can be after us, so this should be OK. */
 		ip_fragment(*pskb, okfn);
 		return NF_STOLEN;

net/ipv4/tcp_ipv4.c

@@ -2356,6 +2356,7 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
 static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct tcp_iter_state* st = seq->private;
+	st->state = TCP_SEQ_STATE_LISTENING;
 	st->num = 0;
 	return *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
 }

net/ipv6/tcp_ipv6.c

@@ -222,7 +222,7 @@ static __inline__ void __tcp_v6_hash(struct sock *sk)
 		write_lock(lock);
 	}
 
-	sk_add_node(sk, list);
+	__sk_add_node(sk, list);
 	sock_prot_inc_use(sk->sk_prot);
 	write_unlock(lock);
 }

net/ipv6/udp.c

@@ -825,7 +825,7 @@ static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg
 			struct sockaddr_in sin;
 			sin.sin_family = AF_INET;
 			sin.sin_port = sin6 ? sin6->sin6_port : inet->dport;
-			sin.sin_addr.s_addr = daddr->s6_addr[3];
+			sin.sin_addr.s_addr = daddr->s6_addr32[3];
 			msg->msg_name = &sin;
 			msg->msg_namelen = sizeof(sin);
 do_udp_sendmsg:

net/sched/sch_htb.c

@@ -74,7 +74,7 @@
 #define HTB_HYSTERESIS 1/* whether to use mode hysteresis for speedup */
 #define HTB_QLOCK(S) spin_lock_bh(&(S)->dev->queue_lock)
 #define HTB_QUNLOCK(S) spin_unlock_bh(&(S)->dev->queue_lock)
-#define HTB_VER 0x3000d	/* major must be matched with number suplied by TC as version */
+#define HTB_VER 0x3000e	/* major must be matched with number suplied by TC as version */
 
 #if HTB_VER >> 16 != TC_HTB_PROTOVER
 #error "Mismatched sch_htb.c and pkt_sch.h"
@@ -290,6 +290,11 @@ static __inline__ struct htb_class *htb_find(u32 handle, struct Qdisc *sch)
  * then finish and return direct queue.
  */
 #define HTB_DIRECT (struct htb_class*)-1
+static inline u32 htb_classid(struct htb_class *cl)
+{
+	return (cl && cl != HTB_DIRECT) ? cl->classid : TC_H_UNSPEC;
+}
+
 static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct htb_sched *q = (struct htb_sched *)sch->data;
@@ -703,7 +708,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
     sch->q.qlen++;
     sch->stats.packets++; sch->stats.bytes += skb->len;
-    HTB_DBG(1,1,"htb_enq_ok cl=%X skb=%p\n",cl?cl->classid:0,skb);
+    HTB_DBG(1,1,"htb_enq_ok cl=%X skb=%p\n",htb_classid(cl),skb);
     return NET_XMIT_SUCCESS;
 }
 
@@ -731,7 +736,7 @@ static int htb_requeue(struct sk_buff *skb, struct Qdisc *sch)
 	    htb_activate (q,cl);
 
     sch->q.qlen++;
-    HTB_DBG(1,1,"htb_req_ok cl=%X skb=%p\n",cl?cl->classid:0,skb);
+    HTB_DBG(1,1,"htb_req_ok cl=%X skb=%p\n",htb_classid(cl),skb);
     return NET_XMIT_SUCCESS;
 }
 
@@ -1381,11 +1386,16 @@ static void htb_destroy(struct Qdisc* sch)
 #ifdef HTB_RATECM
 	del_timer_sync (&q->rttim);
 #endif
+	/* This line used to be after htb_destroy_class call below
+	   and surprisingly it worked in 2.4. But it must precede it 
+	   because filter need its target class alive to be able to call
+	   unbind_filter on it (without Oops). */
+	htb_destroy_filters(&q->filter_list);
+	
 	while (!list_empty(&q->root)) 
 		htb_destroy_class (sch,list_entry(q->root.next,
 					struct htb_class,sibling));
 
-	htb_destroy_filters(&q->filter_list);
 	__skb_queue_purge(&q->direct_queue);
 }