Merge bk://gkernel.bkbits.net/libata-2.5

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

arch/arm/kernel/signal.c

@@ -497,18 +497,21 @@ handle_signal(unsigned long sig, siginfo_t *info, sigset_t *oldset,
 	 */
 	ret |= !valid_user_regs(regs);
 
+	/*
+	 * Block the signal if we were unsuccessful.
+	 */
+	if (ret != 0 || !(ka->sa.sa_flags & SA_NODEFER)) {
+		spin_lock_irq(&tsk->sighand->siglock);
+		sigorsets(&tsk->blocked, &tsk->blocked,
+			  &ka->sa.sa_mask);
+		sigaddset(&tsk->blocked, sig);
+		recalc_sigpending();
+		spin_unlock_irq(&tsk->sighand->siglock);
+	}
+
 	if (ret == 0) {
 		if (ka->sa.sa_flags & SA_ONESHOT)
 			ka->sa.sa_handler = SIG_DFL;
-
-		if (!(ka->sa.sa_flags & SA_NODEFER)) {
-			spin_lock_irq(&tsk->sighand->siglock);
-			sigorsets(&tsk->blocked, &tsk->blocked,
-				  &ka->sa.sa_mask);
-			sigaddset(&tsk->blocked, sig);
-			recalc_sigpending();
-			spin_unlock_irq(&tsk->sighand->siglock);
-		}
 		return;
 	}
 

arch/i386/mach-voyager/voyager_smp.c

@@ -245,8 +245,8 @@ static __u32 cpu_booted_map;
 static cpumask_t smp_commenced_mask = CPU_MASK_NONE;
 
 /* This is for the new dynamic CPU boot code */
-volatile cpumask_t cpu_callin_map = CPU_MASK_NONE;
-volatile cpumask_t cpu_callout_map = CPU_MASK_NONE;
+cpumask_t cpu_callin_map = CPU_MASK_NONE;
+cpumask_t cpu_callout_map = CPU_MASK_NONE;
 
 /* The per processor IRQ masks (these are usually kept in sync) */
 static __u16 vic_irq_mask[NR_CPUS] __cacheline_aligned;

arch/ppc/kernel/vmlinux.lds.S

@@ -47,13 +47,17 @@ SECTIONS
 
   .fixup   : { *(.fixup) }
 
-  __start___ex_table = .;
-  __ex_table : { *(__ex_table) }
-  __stop___ex_table = .;
-
-  __start___bug_table = .;
-  __bug_table : { *(__bug_table) }
-  __stop___bug_table = .;
+	__ex_table : {
+		__start___ex_table = .;
+		*(__ex_table)
+		__stop___ex_table = .;
+	}
+
+	__bug_table : {
+		__start___bug_table = .;
+		*(__bug_table)
+		__stop___bug_table = .;
+	}
 
   /* Read-write section, merged into data segment: */
   . = ALIGN(4096);

arch/x86_64/kernel/entry.S

@@ -219,8 +219,8 @@ tracesys:
 	movq %r10,%rcx	/* fixup for C */
 	call *sys_call_table(,%rax,8)
 	movq %rax,RAX-ARGOFFSET(%rsp)
-	SAVE_REST
-1:	movq %rsp,%rdi
+1:	SAVE_REST
+	movq %rsp,%rdi
 	call syscall_trace
 	RESTORE_TOP_OF_STACK %rbx
 	RESTORE_REST

arch/x86_64/kernel/pci-gart.c

@@ -395,7 +395,7 @@ static int __pci_map_cont(struct scatterlist *sg, int start, int stopat,
 	for (i = start; i < stopat; i++) {
 		struct scatterlist *s = &sg[i];
 		unsigned long start_addr = s->dma_address;
-		BUG_ON(i > 0 && s->offset);
+		BUG_ON(i > start && s->offset);
 		if (i == start) {
 			*sout = *s; 
 			sout->dma_address = iommu_bus_base;
@@ -410,7 +410,6 @@ static int __pci_map_cont(struct scatterlist *sg, int start, int stopat,
 			addr += PAGE_SIZE;
 			iommu_page++;
 	} 
-		BUG_ON(i > 0 && addr % PAGE_SIZE); 
 	} 
 	BUG_ON(iommu_page - iommu_start != pages);	
 	return 0;

arch/x86_64/mm/fault.c

@@ -126,12 +126,6 @@ static int is_prefetch(struct pt_regs *regs, unsigned long addr)
 			break;
 		} 
 	}
-
-#if 1
-	if (prefetch)
-		printk("%s: prefetch caused page fault at %lx/%lx\n", current->comm,
-		       regs->rip, addr);
-#endif
 	return prefetch;
 }
 
@@ -241,6 +235,15 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(in_atomic() || !mm))
 		goto bad_area_nosemaphore;
 
+	/* Work around K8 erratum #100
+	   K8 in compat mode occasionally jumps to illegal addresses >4GB.
+	   We catch this here in the page fault handler because these
+	   addresses are not reachable. Just detect this case and return.
+	   Any code segment in LDT is compatibility mode. */
+	if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) &&
+		(address >> 32))
+		return;
+
  again:
 	down_read(&mm->mmap_sem);
 

drivers/base/class.c

@@ -255,6 +255,7 @@ static decl_subsys(class_obj, &ktype_class_device, &class_hotplug_ops);
 
 void class_device_initialize(struct class_device *class_dev)
 {
+	kobj_set_kset_s(class_dev, class_obj_subsys);
 	kobject_init(&class_dev->kobj);
 	INIT_LIST_HEAD(&class_dev->node);
 }
@@ -277,7 +278,6 @@ int class_device_add(struct class_device *class_dev)
 
 	/* first, register with generic layer. */
 	kobject_set_name(&class_dev->kobj, class_dev->class_id);
-	kobj_set_kset_s(class_dev, class_obj_subsys);
 	if (parent)
 		class_dev->kobj.parent = &parent->subsys.kset.kobj;
 

drivers/block/as-iosched.c

@@ -915,9 +915,10 @@ static void as_completed_request(request_queue_t *q, struct request *rq)
 	if (unlikely(arq->state != AS_RQ_DISPATCHED))
 		return;
 
-	if (ad->changed_batch && ad->nr_dispatched == 1) {
-		WARN_ON(ad->batch_data_dir == arq->is_sync);
+	if (!blk_fs_request(rq))
+		return;
 
+	if (ad->changed_batch && ad->nr_dispatched == 1) {
 		kblockd_schedule_work(&ad->antic_work);
 		ad->changed_batch = 0;
 
@@ -933,7 +934,6 @@ static void as_completed_request(request_queue_t *q, struct request *rq)
 	 * and writeback caches
 	 */
 	if (ad->new_batch && ad->batch_data_dir == arq->is_sync) {
-		WARN_ON(ad->batch_data_dir != REQ_SYNC);
 		update_write_batch(ad);
 		ad->current_batch_expires = jiffies +
 				ad->batch_expire[REQ_SYNC];

drivers/ide/Kconfig

@@ -428,9 +428,10 @@ config BLK_DEV_IDEDMA_PCI
 
 if BLK_DEV_IDEDMA_PCI
 
+# TCQ is disabled for now
 config BLK_DEV_IDE_TCQ
 	bool "ATA tagged command queueing (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	depends on EXPERIMENTAL && n
 	help
 	  Support for tagged command queueing on ATA disk drives. This enables
 	  the IDE layer to have multiple in-flight requests on hardware that

drivers/input/mouse/psmouse-base.c

@@ -36,12 +36,10 @@ MODULE_PARM(psmouse_resetafter, "i");
 MODULE_PARM_DESC(psmouse_resetafter, "Reset Synaptics Touchpad after so many bad packets (0 = never).");
 MODULE_LICENSE("GPL");
 
-#define PSMOUSE_LOGITECH_SMARTSCROLL	1
-
 static int psmouse_noext;
-int psmouse_resolution;
-unsigned int psmouse_rate;
-int psmouse_smartscroll = PSMOUSE_LOGITECH_SMARTSCROLL;
+int psmouse_resolution = 200;
+unsigned int psmouse_rate = 100;
+int psmouse_smartscroll = 1;
 unsigned int psmouse_resetafter;
 
 static char *psmouse_protocols[] = { "None", "PS/2", "PS2++", "PS2T++", "GenPS/2", "ImPS/2", "ImExPS/2", "SynPS/2"};
@@ -466,22 +464,15 @@ static void psmouse_initialize(struct psmouse *psmouse)
 {
 	unsigned char param[2];
 	
-
 /*
- * We set the mouse report rate.
+ * We set the mouse report rate, resolution and scaling.
  */
 
-	if (psmouse_rate)
+	if (!psmouse_noext) {
 		psmouse_set_rate(psmouse);
-
-/*
- * We also set the resolution and scaling.
- */
-
-	if (psmouse_resolution)
 		psmouse_set_resolution(psmouse);
-
-	psmouse_command(psmouse,  NULL, PSMOUSE_CMD_SETSCALE11);
+		psmouse_command(psmouse,  NULL, PSMOUSE_CMD_SETSCALE11);
+	}
 
 /*
  * We set the mouse into streaming mode.

drivers/md/raid1.c

@@ -841,7 +841,7 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 	}
 
 	if (atomic_dec_and_test(&r1_bio->remaining)) {
-		md_done_sync(mddev, r1_bio->master_bio->bi_size >> 9, 0);
+		md_done_sync(mddev, r1_bio->master_bio->bi_size >> 9, 1);
 		put_buf(r1_bio);
 	}
 }

drivers/net/3c509.c

@@ -74,7 +74,9 @@ static int max_interrupt_work = 10;
 
 #include <linux/config.h>
 #include <linux/module.h>
+#ifdef CONFIG_MCA
 #include <linux/mca.h>
+#endif
 #include <linux/isapnp.h>
 #include <linux/string.h>
 #include <linux/interrupt.h>

drivers/pci/quirks.c

@@ -646,7 +646,7 @@ static void __init quirk_disable_pxb(struct pci_dev *pdev)
  
 int interrupt_line_quirk;
 
-static void __init quirk_via_bridge(struct pci_dev *pdev)
+static void __devinit quirk_via_bridge(struct pci_dev *pdev)
 {
 	if(pdev->devfn == 0)
 		interrupt_line_quirk = 1;

drivers/usb/host/ehci-hcd.c

@@ -426,8 +426,11 @@ static int ehci_start (struct usb_hcd *hcd)
 	 */
 	if (HCC_64BIT_ADDR (hcc_params)) {
 		writel (0, &ehci->regs->segment);
+#if 0
+// this is deeply broken on almost all architectures
 		if (!pci_set_dma_mask (ehci->hcd.pdev, 0xffffffffffffffffULL))
 			ehci_info (ehci, "enabled 64bit PCI DMA\n");
+#endif
 	}
 
 	/* help hc dma work well with cachelines */

drivers/usb/net/kaweth.c

@@ -1120,8 +1120,11 @@ static int kaweth_probe(
 
 	usb_set_intfdata(intf, kaweth);
 
+#if 0
+// dma_supported() is deeply broken on almost all architectures
 	if (dma_supported (&intf->dev, 0xffffffffffffffffULL))
 		kaweth->net->features |= NETIF_F_HIGHDMA;
+#endif
 
 	SET_NETDEV_DEV(netdev, &intf->dev);
 	if (register_netdev(netdev) != 0) {

drivers/usb/net/usbnet.c

@@ -2972,9 +2972,12 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 	strcpy (net->name, "usb%d");
 	memcpy (net->dev_addr, node_id, sizeof node_id);
 
+#if 0
+// dma_supported() is deeply broken on almost all architectures
 	// possible with some EHCI controllers
 	if (dma_supported (&udev->dev, 0xffffffffffffffffULL))
 		net->features |= NETIF_F_HIGHDMA;
+#endif
 
 	net->change_mtu = usbnet_change_mtu;
 	net->get_stats = usbnet_get_stats;

drivers/usb/storage/usb.c

@@ -417,10 +417,21 @@ static int usb_stor_control_thread(void * __us)
 		scsi_unlock(host);
 	} /* for (;;) */
 
-	/* notify the exit routine that we're actually exiting now */
-	complete(&(us->notify));
-
-	return 0;
+	/* notify the exit routine that we're actually exiting now 
+	 *
+	 * complete()/wait_for_completion() is similar to up()/down(),
+	 * except that complete() is safe in the case where the structure
+	 * is getting deleted in a parallel mode of execution (i.e. just
+	 * after the down() -- that's necessary for the thread-shutdown
+	 * case.
+	 *
+	 * complete_and_exit() goes even further than this -- it is safe in
+	 * the case that the thread of the caller is going away (not just
+	 * the structure) -- this is necessary for the module-remove case.
+	 * This is important in preemption kernels, which transfer the flow
+	 * of execution immediately upon a complete().
+	 */
+	complete_and_exit(&(us->notify), 0);
 }	
 
 /***********************************************************************

fs/char_dev.c

@@ -434,7 +434,7 @@ void cdev_init(struct cdev *cdev, struct file_operations *fops)
 
 static struct kobject *base_probe(dev_t dev, int *part, void *data)
 {
-	request_module("char-major-%d", MAJOR(dev));
+	request_module("char-major-%d-%d", MAJOR(dev), MINOR(dev));
 	return NULL;
 }
 

fs/cramfs/inode.c

@@ -18,7 +18,6 @@
 #include <linux/string.h>
 #include <linux/blkdev.h>
 #include <linux/cramfs_fs.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <linux/cramfs_fs_sb.h>
 #include <linux/buffer_head.h>
@@ -206,10 +205,10 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb_set_blocksize(sb, PAGE_CACHE_SIZE);
 
 	/* Invalidate the read buffers on mount: think disk change.. */
+	down(&read_mutex);
 	for (i = 0; i < READ_BUFFERS; i++)
 		buffer_blocknr[i] = -1;
 
-	down(&read_mutex);
 	/* Read the first block and get the superblock from it */
 	memcpy(&super, cramfs_read(sb, 0, sizeof(super)), sizeof(super));
 	up(&read_mutex);
@@ -217,7 +216,9 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent)
 	/* Do sanity checks on the superblock */
 	if (super.magic != CRAMFS_MAGIC) {
 		/* check at 512 byte offset */
+		down(&read_mutex);
 		memcpy(&super, cramfs_read(sb, 512, sizeof(super)), sizeof(super));
+		up(&read_mutex);
 		if (super.magic != CRAMFS_MAGIC) {
 			if (!silent)
 				printk(KERN_ERR "cramfs: wrong magic\n");
@@ -288,6 +289,7 @@ static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 {
 	struct inode *inode = filp->f_dentry->d_inode;
 	struct super_block *sb = inode->i_sb;
+	char *buf;
 	unsigned int offset;
 	int copied;
 
@@ -299,18 +301,21 @@ static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	if (offset & 3)
 		return -EINVAL;
 
-	lock_kernel();
+	buf = kmalloc(256, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 
 	copied = 0;
 	while (offset < inode->i_size) {
 		struct cramfs_inode *de;
 		unsigned long nextoffset;
 		char *name;
+		ino_t ino;
+		mode_t mode;
 		int namelen, error;
 
 		down(&read_mutex);
 		de = cramfs_read(sb, OFFSET(inode) + offset, sizeof(*de)+256);
-		up(&read_mutex);
 		name = (char *)(de+1);
 
 		/*
@@ -319,17 +324,21 @@ static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		 * with zeroes.
 		 */
 		namelen = de->namelen << 2;
+		memcpy(buf, name, namelen);
+		ino = CRAMINO(de);
+		mode = de->mode;
+		up(&read_mutex);
 		nextoffset = offset + sizeof(*de) + namelen;
 		for (;;) {
 			if (!namelen) {
-				unlock_kernel();
+				kfree(buf);
 				return -EIO;
 			}
-			if (name[namelen-1])
+			if (buf[namelen-1])
 				break;
 			namelen--;
 		}
-		error = filldir(dirent, name, namelen, offset, CRAMINO(de), de->mode >> 12);
+		error = filldir(dirent, buf, namelen, offset, ino, mode >> 12);
 		if (error)
 			break;
 
@@ -337,7 +346,7 @@ static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		filp->f_pos = offset;
 		copied++;
 	}
-	unlock_kernel();
+	kfree(buf);
 	return 0;
 }
 
@@ -349,16 +358,14 @@ static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, s
 	unsigned int offset = 0;
 	int sorted;
 
-	lock_kernel();
+	down(&read_mutex);
 	sorted = CRAMFS_SB(dir->i_sb)->flags & CRAMFS_FLAG_SORTED_DIRS;
 	while (offset < dir->i_size) {
 		struct cramfs_inode *de;
 		char *name;
 		int namelen, retval;
 
-		down(&read_mutex);
 		de = cramfs_read(dir->i_sb, OFFSET(dir) + offset, sizeof(*de)+256);
-		up(&read_mutex);
 		name = (char *)(de+1);
 
 		/* Try to take advantage of sorted directories */
@@ -374,7 +381,7 @@ static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, s
 
 		for (;;) {
 			if (!namelen) {
-				unlock_kernel();
+				up(&read_mutex);
 				return ERR_PTR(-EIO);
 			}
 			if (name[namelen-1])
@@ -387,15 +394,16 @@ static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, s
 		if (retval > 0)
 			continue;
 		if (!retval) {
-			d_add(dentry, get_cramfs_inode(dir->i_sb, de));
-			unlock_kernel();
+			struct cramfs_inode entry = *de;
+			up(&read_mutex);
+			d_add(dentry, get_cramfs_inode(dir->i_sb, &entry));
 			return NULL;
 		}
 		/* else (retval < 0) */
 		if (sorted)
 			break;
 	}
-	unlock_kernel();
+	up(&read_mutex);
 	d_add(dentry, NULL);
 	return NULL;
 }
@@ -452,6 +460,7 @@ static struct address_space_operations cramfs_aops = {
  * A directory can only readdir
  */
 static struct file_operations cramfs_directory_operations = {
+	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
 	.readdir	= cramfs_readdir,
 };

fs/dquot.c

@@ -128,16 +128,17 @@ static struct quota_format_type *find_quota_format(int id)
 	if (!actqf || !try_module_get(actqf->qf_owner)) {
 		int qm;
 
+		spin_unlock(&dq_list_lock);
+		
 		for (qm = 0; module_names[qm].qm_fmt_id && module_names[qm].qm_fmt_id != id; qm++);
-		if (!module_names[qm].qm_fmt_id || request_module(module_names[qm].qm_mod_name)) {
-			actqf = NULL;
-			goto out;
-		}
+		if (!module_names[qm].qm_fmt_id || request_module(module_names[qm].qm_mod_name))
+			return NULL;
+
+		spin_lock(&dq_list_lock);
 		for (actqf = quota_formats; actqf && actqf->qf_fmt_id != id; actqf = actqf->qf_next);
 		if (actqf && !try_module_get(actqf->qf_owner))
 			actqf = NULL;
 	}
-out:
 	spin_unlock(&dq_list_lock);
 	return actqf;
 }

fs/ext2/balloc.c

@@ -402,6 +402,7 @@ int ext2_new_block(struct inode *inode, unsigned long goal,
 	 * Now search the rest of the groups.  We assume that 
 	 * i and desc correctly point to the last group visited.
 	 */
+retry:
 	for (bit = 0; !group_alloc &&
 			bit < sbi->s_groups_count; bit++) {
 		group_no++;
@@ -425,11 +426,12 @@ int ext2_new_block(struct inode *inode, unsigned long goal,
 	ret_block = grab_block(sb_bgl_lock(sbi, group_no), bitmap_bh->b_data,
 				group_size, 0);
 	if (ret_block < 0) {
-		ext2_error (sb, "ext2_new_block",
-			"Free blocks count corrupted for block group %d",
-				group_no);
+		/*
+		 * Someone else grabbed the last free block in this blockgroup
+		 * before us.  Retry the scan.
+		 */
 		group_alloc = 0;
-		goto io_error;
+		goto retry;
 	}
 
 got_block:

fs/jbd/journal.c

@@ -1729,8 +1729,18 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
 			J_ASSERT_BH(bh, buffer_jbd(bh));
 			J_ASSERT_BH(bh, jh2bh(jh) == bh);
 			BUFFER_TRACE(bh, "remove journal_head");
-			J_ASSERT_BH(bh, !jh->b_frozen_data);
-			J_ASSERT_BH(bh, !jh->b_committed_data);
+			if (jh->b_frozen_data) {
+				printk(KERN_WARNING "%s: freeing "
+						"b_frozen_data\n",
+						__FUNCTION__);
+				kfree(jh->b_frozen_data);
+			}
+			if (jh->b_committed_data) {
+				printk(KERN_WARNING "%s: freeing "
+						"b_committed_data\n",
+						__FUNCTION__);
+				kfree(jh->b_committed_data);
+			}
 			bh->b_private = NULL;
 			jh->b_bh = NULL;	/* debug, really */
 			clear_buffer_jbd(bh);

fs/nfsd/vfs.c

@@ -1368,7 +1368,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 		nfsd_sync_dir(tdentry);
 		nfsd_sync_dir(fdentry);
 	}
-	dput(ndentry);
 
  out_dput_new:
 	dput(ndentry);

include/asm-i386/checksum.h

@@ -83,7 +83,8 @@ static inline unsigned short ip_fast_csum(unsigned char * iph,
 	   are modified, we must also specify them as outputs, or gcc
 	   will assume they contain their original values. */
 	: "=r" (sum), "=r" (iph), "=r" (ihl)
-	: "1" (iph), "2" (ihl));
+	: "1" (iph), "2" (ihl)
+	: "memory");
 	return(sum);
 }
 

include/asm-x86_64/checksum.h

@@ -68,7 +68,8 @@ static inline unsigned short ip_fast_csum(unsigned char *iph, unsigned int ihl)
 	   are modified, we must also specify them as outputs, or gcc
 	   will assume they contain their original values. */
 	: "=r" (sum), "=r" (iph), "=r" (ihl)
-	: "1" (iph), "2" (ihl));
+	: "1" (iph), "2" (ihl)
+	: "memory");
 	return(sum);
 }
 

include/asm-x86_64/desc.h

@@ -118,7 +118,7 @@ static inline void set_tssldt_descriptor(void *ptr, unsigned long tss, unsigned
 	d.base1 = PTR_MIDDLE(tss) & 0xFF; 
 	d.type = type;
 	d.p = 1; 
-	d.limit1 = 0xF;
+	d.limit1 = (size >> 16) & 0xF;
 	d.base2 = (PTR_MIDDLE(tss) >> 8) & 0xFF; 
 	d.base3 = PTR_HIGH(tss); 
 	memcpy(ptr, &d, 16); 

include/linux/sched.h

@@ -574,7 +574,11 @@ extern void do_timer(struct pt_regs *);
 
 extern int FASTCALL(wake_up_state(struct task_struct * tsk, unsigned int state));
 extern int FASTCALL(wake_up_process(struct task_struct * tsk));
-extern int FASTCALL(wake_up_process_kick(struct task_struct * tsk));
+#ifdef CONFIG_SMP
+ extern void FASTCALL(kick_process(struct task_struct * tsk));
+#else
+ static inline void kick_process(struct task_struct *tsk) { }
+#endif
 extern void FASTCALL(wake_up_forked_process(struct task_struct * tsk));
 extern void FASTCALL(sched_exit(task_t * p));
 

include/linux/signal.h

@@ -214,7 +214,7 @@ extern int sigprocmask(int, sigset_t *, sigset_t *);
 struct pt_regs;
 extern int get_signal_to_deliver(siginfo_t *info, struct pt_regs *regs, void *cookie);
 #endif
-#define FOLD_NANO_SLEEP_INTO_CLOCK_NANO_SLEEP
+
 #endif /* __KERNEL__ */
 
 #endif /* _LINUX_SIGNAL_H */

include/linux/times.h

@@ -4,6 +4,7 @@
 #ifdef __KERNEL__
 #include <asm/div64.h>
 #include <asm/types.h>
+#include <asm/param.h>
 
 #if (HZ % USER_HZ)==0
 # define jiffies_to_clock_t(x) ((x) / (HZ / USER_HZ))

kernel/posix-timers.c

@@ -1104,29 +1104,6 @@ long clock_nanosleep_restart(struct restart_block *restart_block);
 extern long do_clock_nanosleep(clockid_t which_clock, int flags,
 			       struct timespec *t);
 
-#ifdef FOLD_NANO_SLEEP_INTO_CLOCK_NANO_SLEEP
-
-asmlinkage long
-sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp)
-{
-	struct timespec t;
-	long ret;
-
-	if (copy_from_user(&t, rqtp, sizeof (t)))
-		return -EFAULT;
-
-	if ((unsigned) t.tv_nsec >= NSEC_PER_SEC || t.tv_sec < 0)
-		return -EINVAL;
-
-	ret = do_clock_nanosleep(CLOCK_REALTIME, 0, &t);
-
-	if (ret == -ERESTART_RESTARTBLOCK && rmtp &&
-					copy_to_user(rmtp, &t, sizeof (t)))
-		return -EFAULT;
-	return ret;
-}
-#endif				// ! FOLD_NANO_SLEEP_INTO_CLOCK_NANO_SLEEP
-
 asmlinkage long
 sys_clock_nanosleep(clockid_t which_clock, int flags,
 		    const struct timespec __user *rqtp,
@@ -1244,7 +1221,7 @@ do_clock_nanosleep(clockid_t which_clock, int flags, struct timespec *tsave)
 	return 0;
 }
 /*
- * This will restart either clock_nanosleep or clock_nanosleep
+ * This will restart clock_nanosleep. Incorrectly, btw.
  */
 long
 clock_nanosleep_restart(struct restart_block *restart_block)

kernel/sched.c

@@ -530,6 +530,15 @@ static inline void resched_task(task_t *p)
 #endif
 }
 
+/**
+ * task_curr - is this task currently executing on a CPU?
+ * @p: the task in question.
+ */
+inline int task_curr(task_t *p)
+{
+	return cpu_curr(task_cpu(p)) == p;
+}
+
 #ifdef CONFIG_SMP
 
 /*
@@ -568,6 +577,27 @@ void wait_task_inactive(task_t * p)
 	task_rq_unlock(rq, &flags);
 	preempt_enable();
 }
+
+/***
+ * kick_process - kick a running thread to enter/exit the kernel
+ * @p: the to-be-kicked thread
+ *
+ * Cause a process which is running on another CPU to enter
+ * kernel-mode, without any delay. (to get signals handled.)
+ */
+void kick_process(task_t *p)
+{
+	int cpu;
+
+	preempt_disable();
+	cpu = task_cpu(p);
+	if ((cpu != smp_processor_id()) && task_curr(p))
+		smp_send_reschedule(cpu);
+	preempt_enable();
+}
+
+EXPORT_SYMBOL_GPL(kick_process);
+
 #endif
 
 /***
@@ -575,7 +605,6 @@ void wait_task_inactive(task_t * p)
  * @p: the to-be-woken-up thread
  * @state: the mask of task states that can be woken
  * @sync: do a synchronous wakeup?
- * @kick: kick the CPU if the task is already running?
  *
  * Put it on the run-queue if it's not already there. The "current"
  * thread is always on the run-queue (except when the actual
@@ -585,7 +614,7 @@ void wait_task_inactive(task_t * p)
  *
  * returns failure only if the task is already active.
  */
-static int try_to_wake_up(task_t * p, unsigned int state, int sync, int kick)
+static int try_to_wake_up(task_t * p, unsigned int state, int sync)
 {
 	unsigned long flags;
 	int success = 0;
@@ -626,33 +655,22 @@ static int try_to_wake_up(task_t * p, unsigned int state, int sync, int kick)
 			}
 			success = 1;
 		}
-#ifdef CONFIG_SMP
-	       	else
-			if (unlikely(kick) && task_running(rq, p) && (task_cpu(p) != smp_processor_id()))
-				smp_send_reschedule(task_cpu(p));
-#endif
 		p->state = TASK_RUNNING;
 	}
 	task_rq_unlock(rq, &flags);
 
 	return success;
 }
-
 int wake_up_process(task_t * p)
 {
-	return try_to_wake_up(p, TASK_STOPPED | TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0, 0);
+	return try_to_wake_up(p, TASK_STOPPED | TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0);
 }
 
 EXPORT_SYMBOL(wake_up_process);
 
-int wake_up_process_kick(task_t * p)
-{
-	return try_to_wake_up(p, TASK_STOPPED | TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0, 1);
-}
-
 int wake_up_state(task_t *p, unsigned int state)
 {
-	return try_to_wake_up(p, state, 0, 0);
+	return try_to_wake_up(p, state, 0);
 }
 
 /*
@@ -1621,7 +1639,7 @@ EXPORT_SYMBOL(preempt_schedule);
 int default_wake_function(wait_queue_t *curr, unsigned mode, int sync)
 {
 	task_t *p = curr->task;
-	return try_to_wake_up(p, mode, sync, 0);
+	return try_to_wake_up(p, mode, sync);
 }
 
 EXPORT_SYMBOL(default_wake_function);
@@ -1941,15 +1959,6 @@ int task_nice(task_t *p)
 
 EXPORT_SYMBOL(task_nice);
 
-/**
- * task_curr - is this task currently executing on a CPU?
- * @p: the task in question.
- */
-int task_curr(task_t *p)
-{
-	return cpu_curr(task_cpu(p)) == p;
-}
-
 /**
  * idle_cpu - is a given cpu idle currently?
  * @cpu: the processor in question.

kernel/signal.c

@@ -538,8 +538,9 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 inline void signal_wake_up(struct task_struct *t, int resume)
 {
 	unsigned int mask;
+	int woken;
 
-	set_tsk_thread_flag(t,TIF_SIGPENDING);
+	set_tsk_thread_flag(t, TIF_SIGPENDING);
 
 	/*
 	 * If resume is set, we want to wake it up in the TASK_STOPPED case.
@@ -551,10 +552,11 @@ inline void signal_wake_up(struct task_struct *t, int resume)
 	mask = TASK_INTERRUPTIBLE;
 	if (resume)
 		mask |= TASK_STOPPED;
-	if (t->state & mask) {
-		wake_up_process_kick(t);
-		return;
-	}
+	woken = 0;
+	if (t->state & mask)
+		woken = wake_up_state(t, mask);
+	if (!woken)
+		kick_process(t);
 }
 
 /*

kernel/timer.c

@@ -1059,7 +1059,6 @@ asmlinkage long sys_gettid(void)
 {
 	return current->pid;
 }
-#ifndef FOLD_NANO_SLEEP_INTO_CLOCK_NANO_SLEEP
 
 static long nanosleep_restart(struct restart_block *restart)
 {
@@ -1118,7 +1117,6 @@ asmlinkage long sys_nanosleep(struct timespec *rqtp, struct timespec *rmtp)
 	}
 	return ret;
 }
-#endif // ! FOLD_NANO_SLEEP_INTO_CLOCK_NANO_SLEEP
 
 /*
  * sys_sysinfo - fill in sysinfo struct

net/core/flow.c

@@ -19,6 +19,7 @@
 #include <linux/bitops.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
+#include <linux/cpumask.h>
 #include <net/flow.h>
 #include <asm/atomic.h>
 #include <asm/semaphore.h>
@@ -65,7 +66,7 @@ static struct timer_list flow_hash_rnd_timer;
 
 struct flow_flush_info {
 	atomic_t cpuleft;
-	unsigned long cpumap;
+	cpumask_t cpumap;
 	struct completion completion;
 };
 static DEFINE_PER_CPU(struct tasklet_struct, flow_flush_tasklets) = { NULL };
@@ -73,7 +74,7 @@ static DEFINE_PER_CPU(struct tasklet_struct, flow_flush_tasklets) = { NULL };
 #define flow_flush_tasklet(cpu) (&per_cpu(flow_flush_tasklets, cpu))
 
 static DECLARE_MUTEX(flow_cache_cpu_sem);
-static unsigned long flow_cache_cpu_map;
+static cpumask_t flow_cache_cpu_map;
 static unsigned int flow_cache_cpu_count;
 
 static void flow_cache_new_hashrnd(unsigned long arg)
@@ -81,7 +82,7 @@ static void flow_cache_new_hashrnd(unsigned long arg)
 	int i;
 
 	for (i = 0; i < NR_CPUS; i++)
-		if (test_bit(i, &flow_cache_cpu_map))
+		if (cpu_isset(i, flow_cache_cpu_map))
 			flow_hash_rnd_recalc(i) = 1;
 
 	flow_hash_rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD;
@@ -178,7 +179,7 @@ void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir,
 	cpu = smp_processor_id();
 
 	fle = NULL;
-	if (!test_bit(cpu, &flow_cache_cpu_map))
+	if (!cpu_isset(cpu, flow_cache_cpu_map))
 		goto nocache;
 
 	if (flow_hash_rnd_recalc(cpu))
@@ -277,7 +278,7 @@ static void flow_cache_flush_per_cpu(void *data)
 	struct tasklet_struct *tasklet;
 
 	cpu = smp_processor_id();
-	if (!test_bit(cpu, &info->cpumap))
+	if (!cpu_isset(cpu, info->cpumap))
 		return;
 
 	tasklet = flow_flush_tasklet(cpu);
@@ -301,7 +302,7 @@ void flow_cache_flush(void)
 
 	local_bh_disable();
 	smp_call_function(flow_cache_flush_per_cpu, &info, 1, 0);
-	if (test_bit(smp_processor_id(), &info.cpumap))
+	if (cpu_isset(smp_processor_id(), info.cpumap))
 		flow_cache_flush_tasklet((unsigned long)&info);
 	local_bh_enable();
 
@@ -341,7 +342,7 @@ static int __devinit flow_cache_cpu_prepare(int cpu)
 static int __devinit flow_cache_cpu_online(int cpu)
 {
 	down(&flow_cache_cpu_sem);
-	set_bit(cpu, &flow_cache_cpu_map);
+	cpu_set(cpu, flow_cache_cpu_map);
 	flow_cache_cpu_count++;
 	up(&flow_cache_cpu_sem);
 

net/core/link_watch.c

@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/if.h>
+#include <net/sock.h>
 #include <linux/rtnetlink.h>
 #include <linux/jiffies.h>
 #include <linux/spinlock.h>
@@ -91,9 +92,11 @@ static void linkwatch_event(void *dummy)
 	linkwatch_nextevent = jiffies + HZ;
 	clear_bit(LW_RUNNING, &linkwatch_flags);
 
-	rtnl_lock();
+	rtnl_shlock();
+	rtnl_exlock();
 	linkwatch_run_queue();
-	rtnl_unlock();
+	rtnl_exunlock();
+	rtnl_shunlock();
 }
 
 

net/core/skbuff.c

@@ -595,10 +595,10 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 
 	head_copy_len = skb_headroom(skb);
 	head_copy_off = 0;
-	if (newheadroom < head_copy_len) {
-		head_copy_off = head_copy_len - newheadroom;
+	if (newheadroom <= head_copy_len)
 		head_copy_len = newheadroom;
-	}
+	else
+		head_copy_off = newheadroom - head_copy_len;
 
 	/* Copy the linear header and data. */
 	if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,

net/ipv4/netfilter/arpt_mangle.c

@@ -4,8 +4,8 @@
 #include <net/sock.h>
 
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("David S. Miller <davem@redhat.com>");
-MODULE_DESCRIPTION("arptables mangle table");
+MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>");
+MODULE_DESCRIPTION("arptables arp payload mangle target");
 
 static unsigned int
 target(struct sk_buff **pskb, unsigned int hooknum, const struct net_device *in,

net/ipv4/route.c

@@ -89,6 +89,7 @@
 #include <linux/random.h>
 #include <linux/jhash.h>
 #include <linux/rcupdate.h>
+#include <linux/times.h>
 #include <net/protocol.h>
 #include <net/ip.h>
 #include <net/route.h>
@@ -2309,7 +2310,7 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
 	ci.rta_used	= rt->u.dst.__use;
 	ci.rta_clntref	= atomic_read(&rt->u.dst.__refcnt);
 	if (rt->u.dst.expires)
-		ci.rta_expires = rt->u.dst.expires - jiffies;
+		ci.rta_expires = jiffies_to_clock_t(rt->u.dst.expires - jiffies);
 	else
 		ci.rta_expires = 0;
 	ci.rta_error	= rt->u.dst.error;

net/ipv4/tcp_ipv4.c

@@ -61,6 +61,7 @@
 #include <linux/cache.h>
 #include <linux/jhash.h>
 #include <linux/init.h>
+#include <linux/times.h>
 
 #include <net/icmp.h>
 #include <net/tcp.h>
@@ -2490,7 +2491,7 @@ static void get_openreq4(struct sock *sk, struct open_request *req,
 		TCP_SYN_RECV,
 		0, 0, /* could print option size, but that is af dependent. */
 		1,    /* timers active (only the expire timer) */
-		ttd,
+		jiffies_to_clock_t(ttd),
 		req->retrans,
 		uid,
 		0,  /* non standard timer */
@@ -2528,7 +2529,8 @@ static void get_tcp4_sock(struct sock *sp, char *tmpbuf, int i)
 			"%08X %5d %8d %lu %d %p %u %u %u %u %d",
 		i, src, srcp, dest, destp, sp->sk_state,
 		tp->write_seq - tp->snd_una, tp->rcv_nxt - tp->copied_seq,
-		timer_active, timer_expires - jiffies,
+		timer_active,
+		jiffies_to_clock_t(timer_expires - jiffies),
 		tp->retransmits,
 		sock_i_uid(sp),
 		tp->probes_out,
@@ -2556,7 +2558,7 @@ static void get_timewait4_sock(struct tcp_tw_bucket *tw, char *tmpbuf, int i)
 	sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
 		" %02X %08X:%08X %02X:%08X %08X %5d %8d %d %d %p",
 		i, src, srcp, dest, destp, tw->tw_substate, 0, 0,
-		3, ttd, 0, 0, 0, 0,
+		3, jiffies_to_clock_t(ttd), 0, 0, 0, 0,
 		atomic_read(&tw->tw_refcnt), tw);
 }
 

net/ipv6/addrconf.c

@@ -571,15 +571,6 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 
 	ifp->dead = 1;
 
-#ifdef CONFIG_IPV6_PRIVACY
-	spin_lock_bh(&ifp->lock);
-	if (ifp->ifpub) {
-		__in6_ifa_put(ifp->ifpub);
-		ifp->ifpub = NULL;
-	}
-	spin_unlock_bh(&ifp->lock);
-#endif
-
 	write_lock_bh(&addrconf_hash_lock);
 	for (ifap = &inet6_addr_lst[hash]; (ifa=*ifap) != NULL;
 	     ifap = &ifa->lst_next) {
@@ -600,7 +591,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 			if (ifa == ifp) {
 				*ifap = ifa->tmp_next;
 				if (ifp->ifpub) {
-					__in6_ifa_put(ifp->ifpub);
+					in6_ifa_put(ifp->ifpub);
 					ifp->ifpub = NULL;
 				}
 				__in6_ifa_put(ifp);

net/ipv6/route.c

@@ -27,6 +27,7 @@
 #include <linux/config.h>
 #include <linux/errno.h>
 #include <linux/types.h>
+#include <linux/times.h>
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/net.h>
@@ -717,7 +718,7 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_rtattr)
 		return -ENOMEM;
 
 	rt->u.dst.obsolete = -1;
-	rt->rt6i_expires = rtmsg->rtmsg_info;
+	rt->rt6i_expires = clock_t_to_jiffies(rtmsg->rtmsg_info);
 	if (nlh && (r = NLMSG_DATA(nlh))) {
 		rt->rt6i_protocol = r->rtm_protocol;
 	} else {
@@ -1535,7 +1536,7 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt,
 	RTA_PUT(skb, RTA_PRIORITY, 4, &rt->rt6i_metric);
 	ci.rta_lastuse = jiffies - rt->u.dst.lastuse;
 	if (rt->rt6i_expires)
-		ci.rta_expires = rt->rt6i_expires - jiffies;
+		ci.rta_expires = jiffies_to_clock_t(rt->rt6i_expires - jiffies);
 	else
 		ci.rta_expires = 0;
 	ci.rta_used = rt->u.dst.__use;

net/ipv6/tcp_ipv6.c

@@ -39,6 +39,7 @@
 #include <linux/init.h>
 #include <linux/jhash.h>
 #include <linux/ipsec.h>
+#include <linux/times.h>
 
 #include <linux/ipv6.h>
 #include <linux/icmpv6.h>
@@ -1941,7 +1942,7 @@ static void get_openreq6(struct seq_file *seq,
 		   TCP_SYN_RECV,
 		   0,0, /* could print option size, but that is af dependent. */
 		   1,   /* timers active (only the expire timer) */  
-		   ttd, 
+		   jiffies_to_clock_t(ttd), 
 		   req->retrans,
 		   uid,
 		   0,  /* non standard timer */  
@@ -1987,7 +1988,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
 		   sp->sk_state, 
 		   tp->write_seq-tp->snd_una, tp->rcv_nxt-tp->copied_seq,
-		   timer_active, timer_expires-jiffies,
+		   timer_active,
+		   jiffies_to_clock_t(timer_expires - jiffies),
 		   tp->retransmits,
 		   sock_i_uid(sp),
 		   tp->probes_out,
@@ -2022,7 +2024,7 @@ static void get_timewait6_sock(struct seq_file *seq,
 		   dest->s6_addr32[0], dest->s6_addr32[1],
 		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
 		   tw->tw_substate, 0, 0,
-		   3, ttd, 0, 0, 0, 0,
+		   3, jiffies_to_clock_t(ttd), 0, 0, 0, 0,
 		   atomic_read(&tw->tw_refcnt), tw);
 }