Merge

Documentation/md.txt

 Tools that manage md devices can be found at
-   http://www.<country>.kernel.org/pub/linux/daemons/raid/....
+   http://www.<country>.kernel.org/pub/linux/utils/raid/....
 
 
 
-You can boot (if you selected boot support in the configuration) with your md 
-device with the following kernel command lines:
+You can boot with your md device with the following kernel command
+lines:
 
 for old raid arrays without persistent superblocks:
   md=<md device no.>,<raid level>,<chunk size factor>,<fault level>,dev0,dev1,...,devn
@@ -33,4 +33,64 @@ dev0-devn: e.g. /dev/hda1,/dev/hdc1,/dev/sda1,/dev/sdb1
 A possible loadlin line (Harald Hoyer <HarryH@Royal.Net>)  looks like this:
 
 e:\loadlin\loadlin e:\zimage root=/dev/md0 md=0,0,4,0,/dev/hdb2,/dev/hdc3 ro
-			    
+
+-------------------------------
+The md driver can support a variety of different superblock formats.
+(It doesn't yet, but it can)
+
+The kernel does *NOT* autodetect which format superblock is being
+used. It must be told.
+
+Superblock format '0' is treated differently to others for legacy
+reasons.
+
+
+General Rules - apply for all superblock formats
+------------------------------------------------
+
+An array is 'created' by writing appropriate superblocks to all
+devices.
+It is 'assembled' by associating each of these devices with an
+particular md virtual device.  Once it is completely assembled, it can
+be accessed.
+
+An array should be created by a user-space tool.  This will write
+superblocks to all devices.  It will usually mark the array as
+'unclean', or with some devices missing so that the kernel md driver
+can create approrpriate redundancy (copying in raid1, parity
+calculation in raid4/5).
+
+When an array is assembled, it is first initialised with the
+SET_ARRAY_INFO ioctl.  This contains, in particular, a major and minor
+version number.  The major version number selects which superblock
+format is to be used.  The minor number might be used to tune handling
+of the format, such as suggesting where on each device to look for the
+superblock.
+
+Then each device is added using the ADD_NEW_DISK ioctl.  This
+provides, in particular, a major and minor number identifying the
+device to add.
+
+The array is started with the RUN_ARRAY ioctl.
+
+Once started, new devices can be added.  They should have an
+appropriate superblock written to them, and then passed be in with
+ADD_NEW_DISK.
+
+Devices that have failed or are not yet active can be detached from an
+array using HOT_REMOVE_DISK.
+
+
+Specific Rules that apply to format-0 super block arrays, and
+       arrays with no superblock (non-presistant).
+-------------------------------------------------------------
+
+An array can be 'created' by describing the array (level, chunksize
+etc) in a SET_ARRAY_INFO ioctl.  This must has major_version==0 and
+raid_disks != 0.
+Then uninitialised devices can be added with ADD_NEW_DISK.  The
+structure passed to ADD_NEW_DISK must specify the state of the device
+and it's role in the array.
+
+One started with RUN_ARRAY, uninitialised spares can be added with
+HOT_ADD_DISK.

arch/i386/kernel/cpu/centaur.c

@@ -248,6 +248,37 @@ static void __init winchip2_protect_mcr(void)
 }
 #endif
 
+static void __init init_c3(struct cpuinfo_x86 *c)
+{
+	u32  lo, hi;
+
+	/* Test for Centaur Extended Feature Flags presence */
+	if (cpuid_eax(0xC0000000) >= 0xC0000001) {
+		/* store Centaur Extended Feature Flags as
+		 * word 5 of the CPU capability bit array
+		 */
+		c->x86_capability[5] = cpuid_edx(0xC0000001);
+	}
+
+	switch (c->x86_model) {
+		case 6 ... 8:		/* Cyrix III family */
+			rdmsr (MSR_VIA_FCR, lo, hi);
+			lo |= (1<<1 | 1<<7);	/* Report CX8 & enable PGE */
+			wrmsr (MSR_VIA_FCR, lo, hi);
+
+			set_bit(X86_FEATURE_CX8, c->x86_capability);
+			set_bit(X86_FEATURE_3DNOW, c->x86_capability);
+
+			/* fall through */
+
+		case 9:	/* Nehemiah */
+		default:
+			get_model_name(c);
+			display_cacheinfo(c);
+			break;
+	}
+}
+
 static void __init init_centaur(struct cpuinfo_x86 *c)
 {
 	enum {
@@ -386,21 +417,7 @@ static void __init init_centaur(struct cpuinfo_x86 *c)
 			break;
 
 		case 6:
-			switch (c->x86_model) {
-				case 6 ... 8:		/* Cyrix III family */
-					rdmsr (MSR_VIA_FCR, lo, hi);
-					lo |= (1<<1 | 1<<7);	/* Report CX8 & enable PGE */
-					wrmsr (MSR_VIA_FCR, lo, hi);
-
-					set_bit(X86_FEATURE_CX8, c->x86_capability);
-					set_bit(X86_FEATURE_3DNOW, c->x86_capability);
-
-				case 9:	/* Nehemiah */
-				default:
-					get_model_name(c);
-					display_cacheinfo(c);
-					break;
-			}
+			init_c3(c);
 			break;
 	}
 }

arch/i386/kernel/cpu/common.c

@@ -211,9 +211,10 @@ void __init generic_identify(struct cpuinfo_x86 * c)
 	
 		/* Intel-defined flags: level 0x00000001 */
 		if ( c->cpuid_level >= 0x00000001 ) {
-			u32 capability;
-			cpuid(0x00000001, &tfms, &junk, &junk, &capability);
+			u32 capability, excap;
+			cpuid(0x00000001, &tfms, &junk, &excap, &capability);
 			c->x86_capability[0] = capability;
+			c->x86_capability[4] = excap;
 			c->x86 = (tfms >> 8) & 15;
 			c->x86_model = (tfms >> 4) & 15;
 			c->x86_mask = tfms & 15;

arch/i386/kernel/cpu/proc.c

@@ -37,7 +37,20 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 
 		/* Other (Linux-defined) */
-		"cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr", NULL, NULL, NULL, NULL,
+		"cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr",
+		NULL, NULL, NULL, NULL,
+		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+
+		/* Intel-defined (#2) */
+		"pni", NULL, NULL, "monitor", "ds_cpl", NULL, NULL, NULL,
+		"tm2", NULL, "cnxt_id", NULL, NULL, NULL, NULL, NULL,
+		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+
+		/* VIA/Cyrix/Centaur-defined */
+		NULL, NULL, "xstore", NULL, NULL, NULL, NULL, NULL,
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,

drivers/base/platform.c

@@ -76,5 +76,6 @@ int __init platform_bus_init(void)
 }
 
 EXPORT_SYMBOL(legacy_bus);
+EXPORT_SYMBOL(platform_bus_type);
 EXPORT_SYMBOL(platform_device_register);
 EXPORT_SYMBOL(platform_device_unregister);

drivers/char/Kconfig

@@ -709,39 +709,20 @@ config NWFLASH
 
 	  If you're not sure, say N.
 
-config INTEL_RNG
-	tristate "Intel i8x0 Random Number Generator support"
+config HW_RANDOM
+	tristate "Intel/AMD/VIA HW Random Number Generator support"
 	depends on (X86 || IA64) && PCI
 	---help---
 	  This driver provides kernel-side support for the Random Number
-	  Generator hardware found on Intel i8xx-based motherboards.
+	  Generator hardware found on Intel i8xx-based motherboards,
+	  AMD 76x-based motherboards, and Via Nehemiah CPUs.
 
-	  Both a character driver, used to read() entropy data, and a timer
-	  function which automatically adds entropy directly into the
-	  kernel pool, are exported by this driver.
+	  Provides a character driver, used to read() entropy data.
 
 	  To compile this driver as a module ( = code which can be inserted in
 	  and removed from the running kernel whenever you want), say M here
 	  and read <file:Documentation/modules.txt>. The module will be called
-	  i810_rng.
-
-	  If unsure, say N.
-
-config AMD_RNG
-	tristate "AMD 768 Random Number Generator support"
-	depends on X86 && PCI
-	---help---
-	  This driver provides kernel-side support for the Random Number
-	  Generator hardware found on AMD 76x based motherboards.
-
-	  Both a character driver, used to read() entropy data, and a timer
-	  function which automatically adds entropy directly into the
-	  kernel pool, are exported by this driver.
-
-	  To compile this driver as a module ( = code which can be inserted in
-	  and removed from the running kernel whenever you want), say M here
-	  and read <file:Documentation/modules.txt>. The module will be called
-	  amd768_rng.
+	  hw_random.
 
 	  If unsure, say N.
 

drivers/char/Makefile

@@ -59,8 +59,7 @@ endif
 obj-$(CONFIG_TOSHIBA) += toshiba.o
 obj-$(CONFIG_I8K) += i8k.o
 obj-$(CONFIG_DS1620) += ds1620.o
-obj-$(CONFIG_INTEL_RNG) += i810_rng.o
-obj-$(CONFIG_AMD_RNG) += amd768_rng.o
+obj-$(CONFIG_HW_RANDOM) += hw_random.o
 obj-$(CONFIG_QIC02_TAPE) += tpqic02.o
 obj-$(CONFIG_FTAPE) += ftape/
 obj-$(CONFIG_H8) += h8.o

drivers/char/amd768_rng.c

-/*
- 	Hardware driver for the AMD 768 Random Number Generator (RNG)
-	(c) Copyright 2001 Red Hat Inc <alan@redhat.com>
- 
- 	derived from
- 
-	Hardware driver for Intel i810 Random Number Generator (RNG)
-	Copyright 2000,2001 Jeff Garzik <jgarzik@pobox.com>
-	Copyright 2000,2001 Philipp Rumpf <prumpf@mandrakesoft.com>
-
-	Please read Documentation/i810_rng.txt for details on use.
-
-	----------------------------------------------------------
-	This software may be used and distributed according to the terms
-        of the GNU General Public License, incorporated herein by reference.
-
- */
-
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/fs.h>
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include <linux/spinlock.h>
-#include <linux/random.h>
-#include <linux/miscdevice.h>
-#include <linux/smp_lock.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-
-#include <asm/io.h>
-#include <asm/uaccess.h>
-
-
-/*
- * core module and version information
- */
-#define RNG_VERSION "0.1.0"
-#define RNG_MODULE_NAME "amd768_rng"
-#define RNG_DRIVER_NAME   RNG_MODULE_NAME " hardware driver " RNG_VERSION
-#define PFX RNG_MODULE_NAME ": "
-
-
-/*
- * debugging macros
- */
-#undef RNG_DEBUG /* define to enable copious debugging info */
-
-#ifdef RNG_DEBUG
-/* note: prints function name for you */
-#define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt, __FUNCTION__ , ## args)
-#else
-#define DPRINTK(fmt, args...)
-#endif
-
-#undef RNG_NDEBUG        /* define to disable lightweight runtime checks */
-#ifdef RNG_NDEBUG
-#define assert(expr)
-#else
-#define assert(expr) \
-        if(!(expr)) {                                   \
-        printk( "Assertion failed! %s,%s,%s,line=%d\n", \
-        #expr,__FILE__,__FUNCTION__,__LINE__);          \
-        }
-#endif
-
-#define RNG_MISCDEV_MINOR		183 /* official */
-
-/*
- * various RNG status variables.  they are globals
- * as we only support a single RNG device
- */
-
-static u32 pmbase;			/* PMxx I/O base */
-static struct semaphore rng_open_sem;	/* Semaphore for serializing rng_open/release */
-
-
-/*
- * inlined helper functions for accessing RNG registers
- */
-
-static inline int rng_data_present (void)
-{
-      	return inl(pmbase+0xF4) & 1;
-}
-
-
-static inline int rng_data_read (void)
-{
-	return inl(pmbase+0xF0);
-}
-
-static int rng_dev_open (struct inode *inode, struct file *filp)
-{
-	if ((filp->f_mode & FMODE_READ) == 0)
-		return -EINVAL;
-	if (filp->f_mode & FMODE_WRITE)
-		return -EINVAL;
-
-	/* wait for device to become free */
-	if (filp->f_flags & O_NONBLOCK) {
-		if (down_trylock (&rng_open_sem))
-			return -EAGAIN;
-	} else {
-		if (down_interruptible (&rng_open_sem))
-			return -ERESTARTSYS;
-	}
-	return 0;
-}
-
-
-static int rng_dev_release (struct inode *inode, struct file *filp)
-{
-	up(&rng_open_sem);
-	return 0;
-}
-
-
-static ssize_t rng_dev_read (struct file *filp, char *buf, size_t size,
-			     loff_t * offp)
-{
-	static spinlock_t rng_lock = SPIN_LOCK_UNLOCKED;
-	int have_data;
-	u32 data = 0;
-	ssize_t ret = 0;
-
-	while (size) {
-		spin_lock(&rng_lock);
-
-		have_data = 0;
-		if (rng_data_present()) {
-			data = rng_data_read();
-			have_data = 4;
-		}
-
-		spin_unlock (&rng_lock);
-
-		while (have_data > 0) {
-			if (put_user((u8)data, buf++)) {
-				ret = ret ? : -EFAULT;
-				break;
-			}
-			size--;
-			ret++;
-			have_data--;
-			data>>=8;
-		}
-
-		if (filp->f_flags & O_NONBLOCK)
-			return ret ? : -EAGAIN;
-
-		if(need_resched())
-		{
-			current->state = TASK_INTERRUPTIBLE;
-			schedule_timeout(1);
-		}
-		else
-			udelay(200);	/* FIXME: We could poll for 250uS ?? */
-
-		if (signal_pending (current))
-			return ret ? : -ERESTARTSYS;
-	}
-	return ret;
-}
-
-
-static struct file_operations rng_chrdev_ops = {
-	.owner		= THIS_MODULE,
-	.open		= rng_dev_open,
-	.release	= rng_dev_release,
-	.read		= rng_dev_read,
-};
-
-
-static struct miscdevice rng_miscdev = {
-	RNG_MISCDEV_MINOR,
-	RNG_MODULE_NAME,
-	&rng_chrdev_ops,
-};
-
-
-/*
- * rng_init_one - look for and attempt to init a single RNG
- */
-static int __init rng_init_one (struct pci_dev *dev)
-{
-	int rc;
-	u8 rnen;
-
-	DPRINTK ("ENTER\n");
-
-	rc = misc_register (&rng_miscdev);
-	if (rc) {
-		printk (KERN_ERR PFX "cannot register misc device\n");
-		DPRINTK ("EXIT, returning %d\n", rc);
-		goto err_out;
-	}
-
-	pci_read_config_dword(dev, 0x58, &pmbase);
-
-	pmbase&=0x0000FF00;
-
-	if(pmbase == 0)
-	{
-		printk (KERN_ERR PFX "power management base not set\n");
-		DPRINTK ("EXIT, returning %d\n", rc);
-		goto err_out_free_miscdev;
-	}
-
-	pci_read_config_byte(dev, 0x40, &rnen);
-	rnen|=(1<<7);	/* RNG on */
-	pci_write_config_byte(dev, 0x40, rnen);
-
-	pci_read_config_byte(dev, 0x41, &rnen);
-	rnen|=(1<<7);	/* PMIO enable */
-	pci_write_config_byte(dev, 0x41, rnen);
-
-	printk(KERN_INFO PFX "AMD768 system management I/O registers at 0x%X.\n", pmbase);
-	DPRINTK ("EXIT, returning 0\n");
-	return 0;
-
-err_out_free_miscdev:
-	misc_deregister (&rng_miscdev);
-err_out:
-	return rc;
-}
-
-
-/*
- * Data for PCI driver interface
- *
- * This data only exists for exporting the supported
- * PCI ids via MODULE_DEVICE_TABLE.  We do not actually
- * register a pci_driver, because someone else might one day
- * want to register another driver on the same PCI id.
- */
-static struct pci_device_id rng_pci_tbl[] __initdata = {
-	{ 0x1022, 0x7443, PCI_ANY_ID, PCI_ANY_ID, },
-	{ 0, },
-};
-MODULE_DEVICE_TABLE (pci, rng_pci_tbl);
-
-
-MODULE_AUTHOR("Alan Cox, Jeff Garzik, Philipp Rumpf, Matt Sottek");
-MODULE_DESCRIPTION("AMD 768 Random Number Generator (RNG) driver");
-MODULE_LICENSE("GPL");
-
-
-/*
- * rng_init - initialize RNG module
- */
-static int __init rng_init (void)
-{
-	int rc;
-	struct pci_dev *pdev;
-
-	DPRINTK ("ENTER\n");
-
-	init_MUTEX (&rng_open_sem);
-
-	pci_for_each_dev(pdev) {
-		if (pci_match_device (rng_pci_tbl, pdev) != NULL)
-			goto match;
-	}
-
-	DPRINTK ("EXIT, returning -ENODEV\n");
-	return -ENODEV;
-
-match:
-	rc = rng_init_one (pdev);
-	if (rc)
-		return rc;
-
-	printk (KERN_INFO RNG_DRIVER_NAME " loaded\n");
-
-	DPRINTK ("EXIT, returning 0\n");
-	return 0;
-}
-
-
-/*
- * rng_init - shutdown RNG module
- */
-static void __exit rng_cleanup (void)
-{
-	DPRINTK ("ENTER\n");
-	misc_deregister (&rng_miscdev);
-	DPRINTK ("EXIT\n");
-}
-
-
-module_init (rng_init);
-module_exit (rng_cleanup);

drivers/i2c/i2c-core.c

@@ -30,6 +30,7 @@
 #include <linux/proc_fs.h>
 #include <linux/i2c.h>
 #include <linux/init.h>
+#include <linux/seq_file.h>
 #include <asm/uaccess.h>
 
 
@@ -326,42 +327,45 @@ int i2c_check_addr(struct i2c_adapter *adapter, int addr)
 int i2c_attach_client(struct i2c_client *client)
 {
 	struct i2c_adapter *adapter = client->adapter;
-	int res =  -EBUSY, i;
+	int i;
 
 	down(&adapter->list);
-	if (__i2c_check_addr(client->adapter,client->addr))
+	if (__i2c_check_addr(client->adapter, client->addr))
 		goto out_unlock_list;
 
-	for (i = 0; i < I2C_CLIENT_MAX; i++)
-		if (NULL == adapter->clients[i])
-			break;
-	if (I2C_CLIENT_MAX == i) {
-		printk(KERN_WARNING 
-		       " i2c-core.o: attach_client(%s) - enlarge I2C_CLIENT_MAX.\n",
-			client->name);
-		res = -ENOMEM;
-		goto out_unlock_list;
+	for (i = 0; i < I2C_CLIENT_MAX; i++) {
+		if (!adapter->clients[i])
+			goto free_slot;
 	}
 
+	printk(KERN_WARNING 
+	       " i2c-core.o: attach_client(%s) - enlarge I2C_CLIENT_MAX.\n",
+	       client->name);
+
+ out_unlock_list:
+	up(&adapter->list);
+	return -EBUSY;
+
+ free_slot:
 	adapter->clients[i] = client;
 	up(&adapter->list);
 	
-	if (adapter->client_register) 
-		if (adapter->client_register(client)) 
-			printk(KERN_DEBUG "i2c-core.o: warning: client_register seems "
+	if (adapter->client_register)  {
+		if (adapter->client_register(client))  {
+			printk(KERN_DEBUG
+			       "i2c-core.o: warning: client_register seems "
 			       "to have failed for client %02x at adapter %s\n",
-			       client->addr,adapter->name);
-	DEB(printk(KERN_DEBUG "i2c-core.o: client [%s] registered to adapter [%s](pos. %d).\n",
-		client->name, adapter->name,i));
+			       client->addr, adapter->name);
+		}
+	}
+
+	DEB(printk(KERN_DEBUG
+		   "i2c-core.o: client [%s] registered to adapter [%s] "
+		   "(pos. %d).\n", client->name, adapter->name, i));
 
-	if(client->flags & I2C_CLIENT_ALLOW_USE)
+	if (client->flags & I2C_CLIENT_ALLOW_USE)
 		client->usage_count = 0;
-	
 	return 0;
-
- out_unlock_list:
-	up(&adapter->list);
-	return res;
 }
 
 
@@ -376,28 +380,30 @@ int i2c_detach_client(struct i2c_client *client)
 	if (adapter->client_unregister)  {
 		res = adapter->client_unregister(client);
 		if (res) {
-			printk(KERN_ERR "i2c-core.o: client_unregister [%s] failed, "
-			       "client not detached",client->name);
-			return res;
+			printk(KERN_ERR
+			       "i2c-core.o: client_unregister [%s] failed, "
+			       "client not detached", client->name);
+			goto out;
 		}
 	}
 
 	down(&adapter->list);
 	for (i = 0; i < I2C_CLIENT_MAX; i++) {
-		if (client == adapter->clients[i])
-			break;
+		if (client == adapter->clients[i]) {
+			adapter->clients[i] = NULL;
+			goto out_unlock;
+		}
 	}
 
-	if (I2C_CLIENT_MAX == i) {
-		printk(KERN_WARNING " i2c-core.o: unregister_client "
-				    "[%s] not found\n",
-			client->name);
-		return -ENODEV;
-	} else
-		adapter->clients[i] = NULL;
-	up(&adapter->list);
+	printk(KERN_WARNING
+	       " i2c-core.o: unregister_client [%s] not found\n",
+	       client->name);
+	res = -ENODEV;
 
-	return 0;
+ out_unlock:
+	up(&adapter->list);
+ out:
+	return res;
 }
 
 static int i2c_inc_use_client(struct i2c_client *client)
@@ -456,45 +462,7 @@ int i2c_release_client(struct i2c_client *client)
 	return 0;
 }
 
-/* ----------------------------------------------------
- * The /proc functions
- * ----------------------------------------------------
- */
-
 #ifdef CONFIG_PROC_FS
-/* This function generates the output for /proc/bus/i2c */
-static int read_bus_i2c(char *buf, char **start, off_t offset,
-			int len, int *eof, void *private)
-{
-	int i;
-	int nr = 0;
-
-	/* Note that it is safe to write a `little' beyond len. Yes, really. */
-	/* Fuck you.  Will convert this to seq_file later.  --hch */
-
-	down(&core_lists);
-	for (i = 0; (i < I2C_ADAP_MAX) && (nr < len); i++) {
-		if (adapters[i]) {
-			nr += sprintf(buf+nr, "i2c-%d\t", i);
-			if (adapters[i]->algo->smbus_xfer) {
-				if (adapters[i]->algo->master_xfer)
-					nr += sprintf(buf+nr,"smbus/i2c");
-				else
-					nr += sprintf(buf+nr,"smbus    ");
-			} else if (adapters[i]->algo->master_xfer)
-				nr += sprintf(buf+nr,"i2c       ");
-			else
-				nr += sprintf(buf+nr,"dummy     ");
-			nr += sprintf(buf+nr,"\t%-32s\t%-32s\n",
-			              adapters[i]->name,
-			              adapters[i]->algo->name);
-		}
-	}
-	up(&core_lists);
-
-	return nr;
-}
-
 /* This function generates the output for /proc/bus/i2c-? */
 static ssize_t i2cproc_bus_read(struct file *file, char *buf,
 				size_t count, loff_t *ppos)
@@ -564,6 +532,50 @@ static struct file_operations i2cproc_operations = {
 	.read		= i2cproc_bus_read,
 };
 
+/* This function generates the output for /proc/bus/i2c */
+static int bus_i2c_show(struct seq_file *s, void *p)
+{
+	int i;
+
+	down(&core_lists);
+	for (i = 0; i < I2C_ADAP_MAX; i++) {
+		struct i2c_adapter *adapter = adapters[i];
+
+		if (!adapter)
+			continue;
+
+		seq_printf(s, "i2c-%d\t", i);
+
+		if (adapter->algo->smbus_xfer) {
+			if (adapter->algo->master_xfer)
+				seq_printf(s, "smbus/i2c");
+			else
+				seq_printf(s, "smbus    ");
+		} else if (adapter->algo->master_xfer)
+			seq_printf(s ,"i2c       ");
+		else
+			seq_printf(s, "dummy     ");
+
+		seq_printf(s, "\t%-32s\t%-32s\n",
+			      adapter->name, adapter->algo->name);
+	}
+	up(&core_lists);
+
+	return 0;
+}
+
+static int bus_i2c_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, bus_i2c_show, NULL);
+}
+
+static struct file_operations bus_i2c_fops = {
+	.open		= bus_i2c_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+ };
+
 static int i2cproc_register(struct i2c_adapter *adap, int bus)
 {
 	struct proc_dir_entry *proc_entry;
@@ -576,7 +588,7 @@ static int i2cproc_register(struct i2c_adapter *adap, int bus)
 		goto fail;
 
 	proc_entry->proc_fops = &i2cproc_operations;
-	proc_entry->owner = THIS_MODULE;
+	proc_entry->owner = adap->owner;
 	adap->inode = proc_entry->low_ino;
 	return 0;
  fail:
@@ -596,15 +608,16 @@ static int __init i2cproc_init(void)
 {
 	struct proc_dir_entry *proc_bus_i2c;
 
-	proc_bus_i2c = create_proc_entry("i2c",0,proc_bus);
-	if (!proc_bus_i2c) {
-		printk(KERN_ERR "i2c-core.o: Could not create /proc/bus/i2c");
-		return -ENOENT;
- 	}
+	proc_bus_i2c = create_proc_entry("i2c", 0, proc_bus);
+	if (!proc_bus_i2c)
+		goto fail;
+	proc_bus_i2c->proc_fops = &bus_i2c_fops;
+ 	proc_bus_i2c->owner = THIS_MODULE;
+ 	return 0;
 
-	proc_bus_i2c->read_proc = &read_bus_i2c;
-	proc_bus_i2c->owner = THIS_MODULE;
-	return 0;
+ fail:
+	printk(KERN_ERR "i2c-core.o: Could not create /proc/bus/i2c");
+	return -ENOENT;
 }
 
 static void __exit i2cproc_cleanup(void)

drivers/i2c/i2c-proc.c

@@ -35,8 +35,6 @@
 #include <linux/i2c-proc.h>
 #include <asm/uaccess.h>
 
-static int i2c_create_name(char **name, const char *prefix,
-			       struct i2c_adapter *adapter, int addr);
 static int i2c_parse_reals(int *nrels, void *buffer, int bufsize,
 			       long *results, int magnitude);
 static int i2c_write_reals(int nrels, void *buffer, size_t *bufsize,
@@ -54,15 +52,6 @@ static struct ctl_table_header *i2c_entries[SENSORS_ENTRY_MAX];
 
 static struct i2c_client *i2c_clients[SENSORS_ENTRY_MAX];
 
-static ctl_table sysctl_table[] = {
-	{CTL_DEV, "dev", NULL, 0, 0555},
-	{0},
-	{DEV_SENSORS, "sensors", NULL, 0, 0555},
-	{0},
-	{0, NULL, NULL, 0, 0555},
-	{0}
-};
-
 static ctl_table i2c_proc_dev_sensors[] = {
 	{SENSORS_CHIPS, "chips", NULL, 0, 0644, NULL, &i2c_proc_chips,
 	 &i2c_sysctl_chips},
@@ -87,36 +76,40 @@ static struct ctl_table_header *i2c_proc_header;
    (for a LM78 chip on the ISA bus at port 0x310), or lm75-i2c-3-4e (for
    a LM75 chip on the third i2c bus at address 0x4e).  
    name is allocated first. */
-static int i2c_create_name(char **name, const char *prefix,
-			struct i2c_adapter *adapter, int addr)
+static char *generate_name(struct i2c_client *client, const char *prefix)
 {
-	char name_buffer[50];
-	int id, i, end;
-	if (i2c_is_isa_adapter(adapter))
+	struct i2c_adapter *adapter = client->adapter;
+	int addr = client->addr;
+	char name_buffer[50], *name;
+
+	if (i2c_is_isa_adapter(adapter)) {
 		sprintf(name_buffer, "%s-isa-%04x", prefix, addr);
-	else if (!adapter->algo->smbus_xfer && !adapter->algo->master_xfer) {
-		/* dummy adapter, generate prefix */
+	} else if (adapter->algo->smbus_xfer || adapter->algo->master_xfer) {
+		int id = i2c_adapter_id(adapter);
+		if (id < 0)
+			return ERR_PTR(-ENOENT);
+		sprintf(name_buffer, "%s-i2c-%d-%02x", prefix, id, addr);
+	} else {	/* dummy adapter, generate prefix */
+		int end, i;
+
 		sprintf(name_buffer, "%s-", prefix);
 		end = strlen(name_buffer);
-		for(i = 0; i < 32; i++) {
-			if(adapter->algo->name[i] == ' ')
+
+		for (i = 0; i < 32; i++) {
+			if (adapter->algo->name[i] == ' ')
 				break;
 			name_buffer[end++] = tolower(adapter->algo->name[i]);
 		}
+
 		name_buffer[end] = 0;
 		sprintf(name_buffer + end, "-%04x", addr);
-	} else {
-		if ((id = i2c_adapter_id(adapter)) < 0)
-			return -ENOENT;
-		sprintf(name_buffer, "%s-i2c-%d-%02x", prefix, id, addr);
-	}
-	*name = kmalloc(strlen(name_buffer) + 1, GFP_KERNEL);
-	if (!*name) {
-		printk (KERN_WARNING "i2c_create_name: not enough memory\n");
-		return -ENOMEM;
 	}
-	strcpy(*name, name_buffer);
-	return 0;
+
+	name = kmalloc(strlen(name_buffer) + 1, GFP_KERNEL);
+	if (unlikely(!name))
+		return ERR_PTR(-ENOMEM);
+	strcpy(name, name_buffer);
+	return name;
 }
 
 /* This rather complex function must be called when you want to add an entry
@@ -127,93 +120,80 @@ static int i2c_create_name(char **name, const char *prefix,
    If any driver wants subdirectories within the newly created directory,
    this function must be updated!  */
 int i2c_register_entry(struct i2c_client *client, const char *prefix,
-			   ctl_table * ctl_template)
+		       struct ctl_table *leaf)
 {
-	int i, res, len, id;
-	ctl_table *new_table, *client_tbl, *tbl;
-	char *name;
-	struct ctl_table_header *new_header;
+	struct { struct ctl_table root[2], dev[2], sensors[2]; } *tbl;
+	struct ctl_table_header *hdr;
+	struct ctl_table *tmp;
+	const char *name;
+	int id;
+
+	name = generate_name(client, prefix);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	for (id = 0; id < SENSORS_ENTRY_MAX; id++) {
+		if (!i2c_entries[id])
+			goto free_slot;
+	}
 
-	if ((res = i2c_create_name(&name, prefix, client->adapter,
-				       client->addr))) return res;
+	goto out_free_name;
 
-	for (id = 0; id < SENSORS_ENTRY_MAX; id++)
-		if (!i2c_entries[id]) {
-			break;
-		}
-	if (id == SENSORS_ENTRY_MAX) {
-		kfree(name);
-		return -ENOMEM;
-	}
+ free_slot:
+	tbl = kmalloc(sizeof(*tbl), GFP_KERNEL);
+	if (unlikely(!tbl))
+		goto out_free_name;
+	memset(tbl, 0, sizeof(*tbl));
 
-	id += 256;
-	
-	len = 0;
-	while (ctl_template[len].procname)
-		len++;
-	if (!(new_table = kmalloc(sizeof(sysctl_table) + sizeof(ctl_table) * (len + 1), 
-				  GFP_KERNEL))) {
-		kfree(name);
-		return -ENOMEM;
-	}
+	for (tmp = leaf; tmp->ctl_name; tmp++)
+		tmp->extra2 = client;
 
-	memcpy(new_table, sysctl_table, sizeof(sysctl_table));
-	tbl = new_table; /* sys/ */
-	tbl = tbl->child = tbl + 2; /* dev/ */
-	tbl = tbl->child = tbl + 2; /* sensors/ */	
-       	client_tbl = tbl->child = tbl + 2; /* XX-chip-YY-ZZ/ */
+	tbl->sensors->ctl_name = id+256;
+	tbl->sensors->procname = name;
+	tbl->sensors->mode = 0555;
+	tbl->sensors->child = leaf;
 
-	client_tbl->procname = name;
-	client_tbl->ctl_name = id;
-	client_tbl->child = client_tbl + 2;
+	tbl->dev->ctl_name = DEV_SENSORS;
+	tbl->dev->procname = "sensors";
+	tbl->dev->mode = 0555;
+	tbl->dev->child = tbl->sensors;
 
-	/* Next the client sysctls. --km */
-	tbl = client_tbl->child;
-	memcpy(tbl, ctl_template, sizeof(ctl_table) * (len+1));
-	for (i = 0; i < len; i++)
-		tbl[i].extra2 = client;
+	tbl->root->ctl_name = CTL_DEV;
+	tbl->root->procname = "dev";
+	tbl->root->mode = 0555;
+	tbl->root->child = tbl->dev;
 
-	if (!(new_header = register_sysctl_table(new_table, 0))) {
-		printk(KERN_ERR "i2c-proc.o: error: sysctl interface not supported by kernel!\n");
-		kfree(new_table);
-		kfree(name);
-		return -EPERM;
-	}
+	hdr = register_sysctl_table(tbl->root, 0);
+	if (unlikely(!hdr))
+		goto out_free_tbl;
 
- 	i2c_entries[id - 256] = new_header;
+	i2c_entries[id] = hdr;
+	i2c_clients[id] = client;
 
-	i2c_clients[id - 256] = client;
+	return (id + 256);	/* XXX(hch) why?? */
 
-#ifdef DEBUG
-	if (!new_header || !new_header->ctl_table ||
-	    !new_header->ctl_table->child ||
-	    !new_header->ctl_table->child->child ||
-	    !new_header->ctl_table->child->child->de ) {
-		printk
-		    (KERN_ERR "i2c-proc.o: NULL pointer when trying to install fill_inode fix!\n");
-		return id;
-	}
-#endif				/* DEBUG */
-	client_tbl->de->owner = client->driver->owner;
-	return id;
+ out_free_tbl:
+	kfree(tbl);
+ out_free_name:
+	kfree(name);
+	return -ENOMEM;
 }
 
 void i2c_deregister_entry(int id)
 {
-	ctl_table *table;
-	char *temp;
+	id -= 256;
 
-	id -= 256;	
 	if (i2c_entries[id]) {
-		table = i2c_entries[id]->ctl_table;
-		unregister_sysctl_table(i2c_entries[id]);
-		/* 2-step kfree needed to keep gcc happy about const points */
-		(const char *) temp = table[4].procname;
-		kfree(temp);
-		kfree(table);
-		i2c_entries[id] = NULL;
-		i2c_clients[id] = NULL;
+		struct ctl_table_header *hdr = i2c_entries[id];
+		struct ctl_table *tbl = hdr->ctl_table;
+
+		unregister_sysctl_table(hdr);
+		kfree(tbl->child->child->procname);
+		kfree(tbl); /* actually the whole anonymous struct */
 	}
+
+	i2c_entries[id] = NULL;
+	i2c_clients[id] = NULL;
 }
 
 static int i2c_proc_chips(ctl_table * ctl, int write, struct file *filp,

drivers/md/linear.c

@@ -203,36 +203,34 @@ static int linear_make_request (request_queue_t *q, struct bio *bio)
 		return 0;
 	}
 	bio->bi_bdev = tmp_dev->rdev->bdev;
-	bio->bi_sector = bio->bi_sector - (tmp_dev->offset << 1);
+	bio->bi_sector = bio->bi_sector - (tmp_dev->offset << 1) + tmp_dev->rdev->data_offset;
 
 	return 1;
 }
 
-static int linear_status (char *page, mddev_t *mddev)
+static void linear_status (struct seq_file *seq, mddev_t *mddev)
 {
-	int sz = 0;
 
 #undef MD_DEBUG
 #ifdef MD_DEBUG
 	int j;
 	linear_conf_t *conf = mddev_to_conf(mddev);
   
-	sz += sprintf(page+sz, "      ");
+	seq_printf(seq, "      ");
 	for (j = 0; j < conf->nr_zones; j++)
 	{
-		sz += sprintf(page+sz, "[%s",
+		seq_printf(seq, "[%s",
 			bdev_partition_name(conf->hash_table[j].dev0->rdev->bdev));
 
 		if (conf->hash_table[j].dev1)
-			sz += sprintf(page+sz, "/%s] ",
+			seq_printf(seq, "/%s] ",
 			  bdev_partition_name(conf->hash_table[j].dev1->rdev->bdev));
 		else
-			sz += sprintf(page+sz, "] ");
+			seq_printf(seq, "] ");
 	}
-	sz += sprintf(page+sz, "\n");
+	seq_printf(seq, "\n");
 #endif
-	sz += sprintf(page+sz, " %dk rounding", mddev->chunk_size/1024);
-	return sz;
+	seq_printf(seq, " %dk rounding", mddev->chunk_size/1024);
 }
 
 

drivers/md/multipath.c

@@ -86,7 +86,6 @@ static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
 {
 	unsigned long flags;
 	mddev_t *mddev = mp_bh->mddev;
-	multipath_conf_t *conf = mddev_to_conf(mddev);
 
 	spin_lock_irqsave(&retry_list_lock, flags);
 	if (multipath_retry_list == NULL)
@@ -95,7 +94,7 @@ static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
 	multipath_retry_tail = &mp_bh->next_mp;
 	mp_bh->next_mp = NULL;
 	spin_unlock_irqrestore(&retry_list_lock, flags);
-	md_wakeup_thread(conf->thread);
+	md_wakeup_thread(mddev->thread);
 }
 
 
@@ -185,19 +184,18 @@ static int multipath_make_request (request_queue_t *q, struct bio * bio)
 	return 0;
 }
 
-static int multipath_status (char *page, mddev_t *mddev)
+static void multipath_status (struct seq_file *seq, mddev_t *mddev)
 {
 	multipath_conf_t *conf = mddev_to_conf(mddev);
-	int sz = 0, i;
+	int i;
 	
-	sz += sprintf (page+sz, " [%d/%d] [", conf->raid_disks,
+	seq_printf (seq, " [%d/%d] [", conf->raid_disks,
 						 conf->working_disks);
 	for (i = 0; i < conf->raid_disks; i++)
-		sz += sprintf (page+sz, "%s",
+		seq_printf (seq, "%s",
 			       conf->multipaths[i].rdev && 
 			       conf->multipaths[i].rdev->in_sync ? "U" : "_");
-	sz += sprintf (page+sz, "]");
-	return sz;
+	seq_printf (seq, "]");
 }
 
 #define LAST_DISK KERN_ALERT \
@@ -334,14 +332,14 @@ static int multipath_remove_disk(mddev_t *mddev, int number)
  *	3.	Performs writes following reads for array syncronising.
  */
 
-static void multipathd (void *data)
+static void multipathd (mddev_t *mddev)
 {
 	struct multipath_bh *mp_bh;
 	struct bio *bio;
 	unsigned long flags;
-	mddev_t *mddev;
 	mdk_rdev_t *rdev;
 
+	md_check_recovery(mddev);
 	for (;;) {
 		spin_lock_irqsave(&retry_list_lock, flags);
 		mp_bh = multipath_retry_list;
@@ -471,10 +469,10 @@ static int multipath_run (mddev_t *mddev)
 	}
 
 	{
-		const char * name = "multipathd";
+		const char * name = "md%d_multipath";
 
-		conf->thread = md_register_thread(multipathd, conf, name);
-		if (!conf->thread) {
+		mddev->thread = md_register_thread(multipathd, mddev, name);
+		if (!mddev->thread) {
 			printk(THREAD_ERROR, mdidx(mddev));
 			goto out_free_conf;
 		}
@@ -513,7 +511,7 @@ static int multipath_stop (mddev_t *mddev)
 {
 	multipath_conf_t *conf = mddev_to_conf(mddev);
 
-	md_unregister_thread(conf->thread);
+	md_unregister_thread(mddev->thread);
 	mempool_destroy(conf->pool);
 	kfree(conf);
 	mddev->private = NULL;

drivers/md/raid0.c

@@ -349,7 +349,7 @@ static int raid0_make_request (request_queue_t *q, struct bio *bio)
 	 * is the only IO operation happening on this bh.
 	 */
 	bio->bi_bdev = tmp_dev->bdev;
-	bio->bi_sector = rsect;
+	bio->bi_sector = rsect + tmp_dev->data_offset;
 
 	/*
 	 * Let the main block layer submit the IO and resolve recursion:
@@ -372,41 +372,40 @@ static int raid0_make_request (request_queue_t *q, struct bio *bio)
 	return 0;
 }
 			   
-static int raid0_status (char *page, mddev_t *mddev)
+static void raid0_status (struct seq_file *seq, mddev_t *mddev)
 {
-	int sz = 0;
 #undef MD_DEBUG
 #ifdef MD_DEBUG
 	int j, k;
 	raid0_conf_t *conf = mddev_to_conf(mddev);
   
-	sz += sprintf(page + sz, "      ");
+	seq_printf(seq, "      ");
 	for (j = 0; j < conf->nr_zones; j++) {
-		sz += sprintf(page + sz, "[z%d",
+		seq_printf(seq, "[z%d",
 				conf->hash_table[j].zone0 - conf->strip_zone);
 		if (conf->hash_table[j].zone1)
-			sz += sprintf(page+sz, "/z%d] ",
+			seq_printf(seq, "/z%d] ",
 				conf->hash_table[j].zone1 - conf->strip_zone);
 		else
-			sz += sprintf(page+sz, "] ");
+			seq_printf(seq, "] ");
 	}
   
-	sz += sprintf(page + sz, "\n");
+	seq_printf(seq, "\n");
   
 	for (j = 0; j < conf->nr_strip_zones; j++) {
-		sz += sprintf(page + sz, "      z%d=[", j);
+		seq_printf(seq, "      z%d=[", j);
 		for (k = 0; k < conf->strip_zone[j].nb_dev; k++)
-			sz += sprintf (page+sz, "%s/", bdev_partition_name(
+			seq_printf (seq, "%s/", bdev_partition_name(
 				conf->strip_zone[j].dev[k]->bdev));
-		sz--;
-		sz += sprintf (page+sz, "] zo=%d do=%d s=%d\n",
+
+		seq_printf (seq, "] zo=%d do=%d s=%d\n",
 				conf->strip_zone[j].zone_offset,
 				conf->strip_zone[j].dev_offset,
 				conf->strip_zone[j].size);
 	}
 #endif
-	sz += sprintf(page + sz, " %dk chunks", mddev->chunk_size/1024);
-	return sz;
+	seq_printf(seq, " %dk chunks", mddev->chunk_size/1024);
+	return;
 }
 
 static mdk_personality_t raid0_personality=

drivers/md/raid1.c

@@ -225,13 +225,12 @@ static void reschedule_retry(r1bio_t *r1_bio)
 {
 	unsigned long flags;
 	mddev_t *mddev = r1_bio->mddev;
-	conf_t *conf = mddev_to_conf(mddev);
 
 	spin_lock_irqsave(&retry_list_lock, flags);
 	list_add(&r1_bio->retry_list, &retry_list_head);
 	spin_unlock_irqrestore(&retry_list_lock, flags);
 
-	md_wakeup_thread(conf->thread);
+	md_wakeup_thread(mddev->thread);
 }
 
 /*
@@ -320,7 +319,7 @@ static int end_request(struct bio *bio, unsigned int bytes_done, int error)
 		 * already.
 		 */
 		if (atomic_dec_and_test(&r1_bio->remaining)) {
-			md_write_end(r1_bio->mddev,conf->thread);
+			md_write_end(r1_bio->mddev);
 			raid_end_bio_io(r1_bio, uptodate);
 		}	
 	}
@@ -494,7 +493,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 			BUG();
 		r1_bio->read_bio = read_bio;
 
-		read_bio->bi_sector = r1_bio->sector;
+		read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset;
 		read_bio->bi_bdev = mirror->rdev->bdev;
 		read_bio->bi_end_io = end_request;
 		read_bio->bi_rw = r1_bio->cmd;
@@ -529,7 +528,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 		mbio = bio_clone(bio, GFP_NOIO);
 		r1_bio->write_bios[i] = mbio;
 
-		mbio->bi_sector	= r1_bio->sector;
+		mbio->bi_sector	= r1_bio->sector + conf->mirrors[i].rdev->data_offset;
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
 		mbio->bi_end_io	= end_request;
 		mbio->bi_rw = r1_bio->cmd;
@@ -542,7 +541,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 		 * If all mirrors are non-operational
 		 * then return an IO error:
 		 */
-		md_write_end(mddev,conf->thread);
+		md_write_end(mddev);
 		raid_end_bio_io(r1_bio, 0);
 		return 0;
 	}
@@ -571,19 +570,18 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	return 0;
 }
 
-static int status(char *page, mddev_t *mddev)
+static void status(struct seq_file *seq, mddev_t *mddev)
 {
 	conf_t *conf = mddev_to_conf(mddev);
-	int sz = 0, i;
+	int i;
 
-	sz += sprintf(page+sz, " [%d/%d] [", conf->raid_disks,
+	seq_printf(seq, " [%d/%d] [", conf->raid_disks,
 						conf->working_disks);
 	for (i = 0; i < conf->raid_disks; i++)
-		sz += sprintf(page+sz, "%s",
+		seq_printf(seq, "%s",
 			      conf->mirrors[i].rdev &&
 			      conf->mirrors[i].rdev->in_sync ? "U" : "_");
-	sz += sprintf (page+sz, "]");
-	return sz;
+	seq_printf(seq, "]");
 }
 
 #define LAST_DISK KERN_ALERT \
@@ -624,10 +622,9 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 		mddev->degraded++;
 		conf->working_disks--;
 		/*
-		 * if recovery was running, stop it now.
+		 * if recovery is running, make sure it aborts.
 		 */
-		if (mddev->recovery_running) 
-			mddev->recovery_running = -EIO;
+		set_bit(MD_RECOVERY_ERR, &mddev->recovery);
 	}
 	rdev->in_sync = 0;
 	rdev->faulty = 1;
@@ -859,7 +856,7 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 		mbio = bio_clone(bio, GFP_NOIO);
 		r1_bio->write_bios[i] = mbio;
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
-		mbio->bi_sector = r1_bio->sector;
+		mbio->bi_sector = r1_bio->sector | conf->mirrors[i].rdev->data_offset;
 		mbio->bi_end_io	= end_sync_write;
 		mbio->bi_rw = WRITE;
 		mbio->bi_private = r1_bio;
@@ -900,17 +897,17 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
  *	3.	Performs writes following reads for array syncronising.
  */
 
-static void raid1d(void *data)
+static void raid1d(mddev_t *mddev)
 {
 	struct list_head *head = &retry_list_head;
 	r1bio_t *r1_bio;
 	struct bio *bio;
 	unsigned long flags;
-	mddev_t *mddev;
-	conf_t *conf = data;
+	conf_t *conf = mddev_to_conf(mddev);
 	mdk_rdev_t *rdev;
 
-	md_handle_safemode(conf->mddev);
+	md_check_recovery(mddev);
+	md_handle_safemode(mddev);
 	
 	for (;;) {
 		spin_lock_irqsave(&retry_list_lock, flags);
@@ -937,7 +934,7 @@ static void raid1d(void *data)
 			printk(REDIRECT_SECTOR,
 				bdev_partition_name(rdev->bdev), (unsigned long long)r1_bio->sector);
 			bio->bi_bdev = rdev->bdev;
-			bio->bi_sector = r1_bio->sector;
+			bio->bi_sector = r1_bio->sector + rdev->data_offset;
 			bio->bi_rw = r1_bio->cmd;
 
 			generic_make_request(bio);
@@ -1048,7 +1045,7 @@ static int sync_request(mddev_t *mddev, sector_t sector_nr, int go_faster)
 
 	read_bio = bio_clone(r1_bio->master_bio, GFP_NOIO);
 
-	read_bio->bi_sector = sector_nr;
+	read_bio->bi_sector = sector_nr + mirror->rdev->data_offset;
 	read_bio->bi_bdev = mirror->rdev->bdev;
 	read_bio->bi_end_io = end_sync_read;
 	read_bio->bi_rw = READ;
@@ -1190,10 +1187,8 @@ static int run(mddev_t *mddev)
 
 
 	{
-		snprintf(conf->thread_name,MD_THREAD_NAME_MAX,"raid1d_md%d",mdidx(mddev));
-
-		conf->thread = md_register_thread(raid1d, conf, conf->thread_name);
-		if (!conf->thread) {
+		mddev->thread = md_register_thread(raid1d, mddev, "md%d_raid1");
+		if (!mddev->thread) {
 			printk(THREAD_ERROR, mdidx(mddev));
 			goto out_free_conf;
 		}
@@ -1219,7 +1214,8 @@ static int stop(mddev_t *mddev)
 {
 	conf_t *conf = mddev_to_conf(mddev);
 
-	md_unregister_thread(conf->thread);
+	md_unregister_thread(mddev->thread);
+	mddev->thread = NULL;
 	if (conf->r1bio_pool)
 		mempool_destroy(conf->r1bio_pool);
 	kfree(conf);

drivers/md/raid5.c

@@ -71,12 +71,12 @@ static inline void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
 				list_add_tail(&sh->lru, &conf->delayed_list);
 			else
 				list_add_tail(&sh->lru, &conf->handle_list);
-			md_wakeup_thread(conf->thread);
+			md_wakeup_thread(conf->mddev->thread);
 		} else {
 			if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
 				atomic_dec(&conf->preread_active_stripes);
 				if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)
-					md_wakeup_thread(conf->thread);
+					md_wakeup_thread(conf->mddev->thread);
 			}
 			list_add_tail(&sh->lru, &conf->inactive_list);
 			atomic_dec(&conf->active_stripes);
@@ -463,10 +463,9 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 			conf->failed_disks++;
 			rdev->in_sync = 0;
 			/*
-			 * if recovery was running, stop it now.
+			 * if recovery was running, make sure it aborts.
 			 */
-			if (mddev->recovery_running) 
-				mddev->recovery_running = -EIO;
+			set_bit(MD_RECOVERY_ERR, &mddev->recovery);
 		}
 		rdev->faulty = 1;
 		printk (KERN_ALERT
@@ -913,7 +912,7 @@ static void handle_stripe(struct stripe_head *sh)
 				struct bio *nextbi = bi->bi_next;
 				clear_bit(BIO_UPTODATE, &bi->bi_flags);
 				if (--bi->bi_phys_segments == 0) {
-					md_write_end(conf->mddev, conf->thread);
+					md_write_end(conf->mddev);
 					bi->bi_next = return_bi;
 					return_bi = bi;
 				}
@@ -970,7 +969,7 @@ static void handle_stripe(struct stripe_head *sh)
 			    while (wbi && wbi->bi_sector < dev->sector + STRIPE_SECTORS) {
 				    wbi2 = wbi->bi_next;
 				    if (--wbi->bi_phys_segments == 0) {
-					    md_write_end(conf->mddev, conf->thread);
+					    md_write_end(conf->mddev);
 					    wbi->bi_next = return_bi;
 					    return_bi = wbi;
 				    }
@@ -1113,7 +1112,7 @@ static void handle_stripe(struct stripe_head *sh)
 			if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
 				atomic_dec(&conf->preread_active_stripes);
 				if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)
-					md_wakeup_thread(conf->thread);
+					md_wakeup_thread(conf->mddev->thread);
 			}
 		}
 	}
@@ -1207,7 +1206,7 @@ static void handle_stripe(struct stripe_head *sh)
 			bi->bi_bdev = rdev->bdev;
 			PRINTK("for %llu schedule op %ld on disc %d\n", (unsigned long long)sh->sector, bi->bi_rw, i);
 			atomic_inc(&sh->count);
-			bi->bi_sector = sh->sector;
+			bi->bi_sector = sh->sector + rdev->data_offset;
 			bi->bi_flags = 1 << BIO_UPTODATE;
 			bi->bi_vcnt = 1;	
 			bi->bi_idx = 0;
@@ -1251,7 +1250,7 @@ static void raid5_unplug_device(void *data)
 
 	if (blk_remove_plug(q))
 		raid5_activate_delayed(conf);
-	md_wakeup_thread(conf->thread);
+	md_wakeup_thread(mddev->thread);
 
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 }
@@ -1304,7 +1303,7 @@ static int make_request (request_queue_t *q, struct bio * bi)
 		int bytes = bi->bi_size;
 
 		if ( bio_data_dir(bi) == WRITE )
-			md_write_end(mddev,conf->thread);
+			md_write_end(mddev);
 		bi->bi_size = 0;
 		bi->bi_end_io(bi, bytes, 0);
 	}
@@ -1356,16 +1355,17 @@ static int sync_request (mddev_t *mddev, sector_t sector_nr, int go_faster)
  * During the scan, completed stripes are saved for us by the interrupt
  * handler, so that they will not have to wait for our next wakeup.
  */
-static void raid5d (void *data)
+static void raid5d (mddev_t *mddev)
 {
 	struct stripe_head *sh;
-	raid5_conf_t *conf = data;
-	mddev_t *mddev = conf->mddev;
+	raid5_conf_t *conf = mddev_to_conf(mddev);
 	int handled;
 
 	PRINTK("+++ raid5d active\n");
 
+	md_check_recovery(mddev);
 	md_handle_safemode(mddev);
+
 	handled = 0;
 	spin_lock_irq(&conf->device_lock);
 	while (1) {
@@ -1486,10 +1486,8 @@ static int run (mddev_t *mddev)
 	}
 
 	{
-		snprintf(conf->thread_name,MD_THREAD_NAME_MAX,"raid5d_md%d",mdidx(mddev));
-
-		conf->thread = md_register_thread(raid5d, conf, conf->thread_name);
-		if (!conf->thread) {
+		mddev->thread = md_register_thread(raid5d, mddev, "md%d_raid5");
+		if (!mddev->thread) {
 			printk(KERN_ERR "raid5: couldn't allocate thread for md%d\n", mdidx(mddev));
 			goto abort;
 		}
@@ -1500,7 +1498,7 @@ static int run (mddev_t *mddev)
 	if (grow_stripes(conf, conf->max_nr_stripes)) {
 		printk(KERN_ERR "raid5: couldn't allocate %dkB for buffers\n", memory);
 		shrink_stripes(conf);
-		md_unregister_thread(conf->thread);
+		md_unregister_thread(mddev->thread);
 		goto abort;
 	} else
 		printk(KERN_INFO "raid5: allocated %dkB for md%d\n", memory, mdidx(mddev));
@@ -1536,7 +1534,8 @@ static int stop (mddev_t *mddev)
 {
 	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
 
-	md_unregister_thread(conf->thread);
+	md_unregister_thread(mddev->thread);
+	mddev->thread = NULL;
 	shrink_stripes(conf);
 	free_pages((unsigned long) conf->stripe_hashtbl, HASH_PAGES_ORDER);
 	kfree(conf);
@@ -1574,29 +1573,26 @@ static void printall (raid5_conf_t *conf)
 		}
 	}
 	spin_unlock_irq(&conf->device_lock);
-
-	PRINTK("--- raid5d inactive\n");
 }
 #endif
 
-static int status (char *page, mddev_t *mddev)
+static void status (struct seq_file *seq, mddev_t *mddev)
 {
 	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
-	int sz = 0, i;
+	int i;
 
-	sz += sprintf (page+sz, " level %d, %dk chunk, algorithm %d", mddev->level, mddev->chunk_size >> 10, mddev->layout);
-	sz += sprintf (page+sz, " [%d/%d] [", conf->raid_disks, conf->working_disks);
+	seq_printf (seq, " level %d, %dk chunk, algorithm %d", mddev->level, mddev->chunk_size >> 10, mddev->layout);
+	seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->working_disks);
 	for (i = 0; i < conf->raid_disks; i++)
-		sz += sprintf (page+sz, "%s",
+		seq_printf (seq, "%s",
 			       conf->disks[i].rdev &&
 			       conf->disks[i].rdev->in_sync ? "U" : "_");
-	sz += sprintf (page+sz, "]");
+	seq_printf (seq, "]");
 #if RAID5_DEBUG
 #define D(x) \
-	sz += sprintf (page+sz, "<"#x":%d>", atomic_read(&conf->x))
+	seq_printf (seq, "<"#x":%d>", atomic_read(&conf->x))
 	printall(conf);
 #endif
-	return sz;
 }
 
 static void print_raid5_conf (raid5_conf_t *conf)

fs/lockd/svclock.c

@@ -305,8 +305,6 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 				(long long)lock->fl.fl_end,
 				wait);
 
-	/* Lock file against concurrent access */
-	down(&file->f_sema);
 
 	/* Get existing block (in case client is busy-waiting) */
 	block = nlmsvc_lookup_block(file, lock, 0);
@@ -314,6 +312,9 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 	lock->fl.fl_flags |= FL_LOCKD;
 
 again:
+	/* Lock file against concurrent access */
+	down(&file->f_sema);
+
 	if (!(conflock = posix_test_lock(&file->f_file, &lock->fl))) {
 		error = posix_lock_file(&file->f_file, &lock->fl);
 
@@ -346,7 +347,10 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 
 	/* If we don't have a block, create and initialize it. Then
 	 * retry because we may have slept in kmalloc. */
+	/* We have to release f_sema as nlmsvc_create_block may try to
+	 * to claim it while doing host garbage collection */
 	if (block == NULL) {
+		up(&file->f_sema);
 		dprintk("lockd: blocking on this lock (allocating).\n");
 		if (!(block = nlmsvc_create_block(rqstp, file, lock, cookie)))
 			return nlm_lck_denied_nolocks;

fs/nfsd/export.c

@@ -294,7 +294,9 @@ int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 
 	/* client */
 	len = qword_get(&mesg, buf, PAGE_SIZE);
-	if (len <= 0) return -EINVAL;
+	err = -EINVAL;
+	if (len <= 0) goto out;
+
 	err = -ENOENT;
 	dom = auth_domain_find(buf);
 	if (!dom)
@@ -473,8 +475,14 @@ exp_get_by_name(svc_client *clp, struct vfsmount *mnt, struct dentry *dentry,
 
 	exp = svc_export_lookup(&key, 0);
 	if (exp != NULL) 
-		if (cache_check(&svc_export_cache, &exp->h, reqp))
+		switch (cache_check(&svc_export_cache, &exp->h, reqp)) {
+		case 0: break;
+		case -EAGAIN:
+			exp = ERR_PTR(-EAGAIN);
+			break;
+		default:
 			exp = NULL;
+		}
 
 	return exp;
 }
@@ -915,7 +923,8 @@ struct flags {
 	{ NFSEXP_UIDMAP, {"uidmap", ""}},
 	{ NFSEXP_KERBEROS, { "kerberos", ""}},
 	{ NFSEXP_SUNSECURE, { "sunsecure", ""}},
-	{ NFSEXP_CROSSMNT, {"nohide", ""}},
+	{ NFSEXP_NOHIDE, {"nohide", ""}},
+	{ NFSEXP_CROSSMNT, {"crossmnt", ""}},
 	{ NFSEXP_NOSUBTREECHECK, {"no_subtree_check", ""}},
 	{ NFSEXP_NOAUTHNLM, {"insecure_locks", ""}},
 #ifdef MSNFS

fs/nfsd/vfs.c

@@ -79,7 +79,7 @@ static struct raparms *		raparm_cache;
  * N.B. After this call _both_ fhp and resfh need an fh_put
  *
  * If the lookup would cross a mountpoint, and the mounted filesystem
- * is exported to the client with NFSEXP_CROSSMNT, then the lookup is
+ * is exported to the client with NFSEXP_NOHIDE, then the lookup is
  * accepted as it stands and the mounted directory is
  * returned. Otherwise the covered directory is returned.
  * NOTE: this mountpoint crossing is not supported properly by all
@@ -115,7 +115,7 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
 			read_lock(&dparent_lock);
 			dentry = dget(dparent->d_parent);
 			read_unlock(&dparent_lock);
-		} else  if (!EX_CROSSMNT(exp))
+		} else  if (!EX_NOHIDE(exp))
 			dentry = dget(dparent); /* .. == . just like at / */
 		else {
 			/* checking mountpoint crossing is very different when stepping up */
@@ -133,6 +133,12 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
 
 			exp2 = exp_parent(exp->ex_client, mnt, dentry,
 					  &rqstp->rq_chandle);
+			if (IS_ERR(exp2)) {
+				err = PTR_ERR(exp2);
+				dput(dentry);
+				mntput(mnt);
+				goto out;
+			}
 			if (!exp2) {
 				dput(dentry);
 				dentry = dget(dparent);
@@ -157,9 +163,19 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
 			struct dentry *mounts = dget(dentry);
 			while (follow_down(&mnt,&mounts)&&d_mountpoint(mounts))
 				;
+
 			exp2 = exp_get_by_name(exp->ex_client, mnt, 
 					       mounts, &rqstp->rq_chandle);
-			if (exp2 && EX_CROSSMNT(exp2)) {
+			if (IS_ERR(exp2)) {
+				err = PTR_ERR(exp2);
+				dput(mounts);
+				dput(dentry);
+				mntput(mnt);
+				goto out;
+			}
+			if (exp2 &&
+			    ((exp->ex_flags & NFSEXP_CROSSMNT)
+			     || EX_NOHIDE(exp2))) {
 				/* successfully crossed mount point */
 				exp_put(exp);
 				exp = exp2;

fs/reiserfs/journal.c

@@ -1310,6 +1310,10 @@ static void free_journal_ram(struct super_block *p_s_sb) {
   if (SB_JOURNAL(p_s_sb)->j_header_bh) {
     brelse(SB_JOURNAL(p_s_sb)->j_header_bh) ;
   }
+  /* j_header_bh is on the journal dev, make sure not to release the journal
+   * dev until we brelse j_header_bh
+   */
+  release_journal_dev(p_s_sb, SB_JOURNAL(p_s_sb));
   vfree(SB_JOURNAL(p_s_sb)) ;
 }
 
@@ -1341,7 +1345,6 @@ static int do_journal_release(struct reiserfs_transaction_handle *th, struct sup
     commit_wq = NULL;
   }
 
-  release_journal_dev( p_s_sb, SB_JOURNAL( p_s_sb ) );
   free_journal_ram(p_s_sb) ;
 
   return 0 ;
@@ -1867,24 +1870,18 @@ static int release_journal_dev( struct super_block *super,
     int result;
     
     result = 0;
-	
 
     if( journal -> j_dev_file != NULL ) {
-	/*
-	 * journal block device was taken via filp_open
-	 */
 	result = filp_close( journal -> j_dev_file, NULL );
 	journal -> j_dev_file = NULL;
 	journal -> j_dev_bd = NULL;
     } else if( journal -> j_dev_bd != NULL ) {
-	/*
-	 * journal block device was taken via bdget and blkdev_get
-	 */
 	result = blkdev_put( journal -> j_dev_bd, BDEV_FS );
 	journal -> j_dev_bd = NULL;
     }
+
     if( result != 0 ) {
-	reiserfs_warning("sh-457: release_journal_dev: Cannot release journal device: %i", result );
+	reiserfs_warning("sh-457: release_journal_dev: Cannot release journal device: %i\n", result );
     }
     return result;
 }
@@ -1895,6 +1892,7 @@ static int journal_init_dev( struct super_block *super,
 {
 	int result;
 	dev_t jdev;
+	int blkdev_mode = FMODE_READ | FMODE_WRITE;
 
 	result = 0;
 
@@ -1902,12 +1900,16 @@ static int journal_init_dev( struct super_block *super,
 	journal -> j_dev_file = NULL;
 	jdev = SB_ONDISK_JOURNAL_DEVICE( super ) ?
 		SB_ONDISK_JOURNAL_DEVICE( super ) : super->s_dev;	
+
+	if (bdev_read_only(super->s_bdev))
+	    blkdev_mode = FMODE_READ;
+
 	/* there is no "jdev" option and journal is on separate device */
 	if( ( !jdev_name || !jdev_name[ 0 ] ) ) {
 		journal -> j_dev_bd = bdget(jdev);
 		if( journal -> j_dev_bd )
 			result = blkdev_get( journal -> j_dev_bd, 
-					     FMODE_READ | FMODE_WRITE, 0, 
+					     blkdev_mode, 0, 
 					     BDEV_FS );
 		else
 			result = -ENOMEM;
@@ -1928,10 +1930,10 @@ static int journal_init_dev( struct super_block *super,
 		jdev_inode = journal -> j_dev_file -> f_dentry -> d_inode;
 		journal -> j_dev_bd = jdev_inode -> i_bdev;
 		if( !S_ISBLK( jdev_inode -> i_mode ) ) {
-			printk( "journal_init_dev: '%s' is not a block device", jdev_name );
+			printk( "journal_init_dev: '%s' is not a block device\n", jdev_name );
 			result = -ENOTBLK;
 		} else if( jdev_inode -> i_bdev == NULL ) {
-			printk( "journal_init_dev: bdev uninitialized for '%s'", jdev_name );
+			printk( "journal_init_dev: bdev uninitialized for '%s'\n", jdev_name );
 			result = -ENOMEM;
 		} else  {
 			/* ok */
@@ -1941,12 +1943,12 @@ static int journal_init_dev( struct super_block *super,
 	} else {
 		result = PTR_ERR( journal -> j_dev_file );
 		journal -> j_dev_file = NULL;
-		printk( "journal_init_dev: Cannot open '%s': %i", jdev_name, result );
+		printk( "journal_init_dev: Cannot open '%s': %i\n", jdev_name, result );
 	}
 	if( result != 0 ) {
 		release_journal_dev( super, journal );
 	}
-	printk( "journal_init_dev: journal device: %s", bdevname(journal->j_dev_bd));
+	printk( "journal_init_dev: journal device: %s\n", bdevname(journal->j_dev_bd));
 	return result;
 }
 
@@ -1960,20 +1962,24 @@ int journal_init(struct super_block *p_s_sb, const char * j_dev_name, int old_fo
     struct reiserfs_journal_header *jh;
     struct reiserfs_journal *journal;
 
-  if (sizeof(struct reiserfs_journal_commit) != 4096 ||
-      sizeof(struct reiserfs_journal_desc) != 4096
-     ) {
-    printk("journal-1249: commit or desc struct not 4096 %Zd %Zd\n", sizeof(struct reiserfs_journal_commit), 
+    if (sizeof(struct reiserfs_journal_commit) != 4096 ||
+      sizeof(struct reiserfs_journal_desc) != 4096) {
+	printk("journal-1249: commit or desc struct not 4096 %Zd %Zd\n", sizeof(struct reiserfs_journal_commit), 
         sizeof(struct reiserfs_journal_desc)) ;
-    return 1 ;
-  }
+	return 1 ;
+    }
 
     journal = SB_JOURNAL(p_s_sb) = vmalloc(sizeof (struct reiserfs_journal)) ;
     if (!journal) {
 	printk("journal-1256: unable to get memory for journal structure\n") ;
-    return 1 ;
-  }
+	return 1 ;
+    }
     memset(journal, 0, sizeof(struct reiserfs_journal)) ;
+    INIT_LIST_HEAD(&SB_JOURNAL(p_s_sb)->j_bitmap_nodes) ;
+    INIT_LIST_HEAD (&SB_JOURNAL(p_s_sb)->j_prealloc_list);
+    reiserfs_allocate_list_bitmaps(p_s_sb, SB_JOURNAL(p_s_sb)->j_list_bitmap, 
+ 				   SB_BMAP_NR(p_s_sb)) ;
+    allocate_bitmap_nodes(p_s_sb) ;
 
     /* reserved for journal area support */
     SB_JOURNAL_1st_RESERVED_BLOCK(p_s_sb) = (old_format ?
@@ -1983,7 +1989,7 @@ int journal_init(struct super_block *p_s_sb, const char * j_dev_name, int old_fo
     
     if( journal_init_dev( p_s_sb, journal, j_dev_name ) != 0 ) {
       printk( "sh-462: unable to initialize jornal device\n");
-      return 1;
+      goto free_and_return;
     }
 
      rs = SB_DISK_SUPER_BLOCK(p_s_sb);
@@ -1993,8 +1999,7 @@ int journal_init(struct super_block *p_s_sb, const char * j_dev_name, int old_fo
 		   SB_ONDISK_JOURNAL_1st_BLOCK(p_s_sb) + SB_ONDISK_JOURNAL_SIZE(p_s_sb));
      if (!bhjh) {
 	 printk("sh-459: unable to read  journal header\n") ;
-	 release_journal_dev(p_s_sb, journal);
-	 return 1 ;
+	 goto free_and_return;
      }
      jh = (struct reiserfs_journal_header *)(bhjh->b_data);
      
@@ -2005,8 +2010,7 @@ int journal_init(struct super_block *p_s_sb, const char * j_dev_name, int old_fo
 		jh->jh_journal.jp_journal_magic, bdevname( SB_JOURNAL(p_s_sb)->j_dev_bd ),
 		sb_jp_journal_magic(rs), reiserfs_bdevname (p_s_sb));
 	 brelse (bhjh);
-	 release_journal_dev(p_s_sb, journal);
-	 return 1 ;
+	 goto free_and_return;
   }
      
   SB_JOURNAL_TRANS_MAX(p_s_sb)      = le32_to_cpu (jh->jh_journal.jp_journal_trans_max);
@@ -2064,7 +2068,6 @@ int journal_init(struct super_block *p_s_sb, const char * j_dev_name, int old_fo
 
   brelse (bhjh);
      
-
   SB_JOURNAL(p_s_sb)->j_list_bitmap_index = 0 ;
   SB_JOURNAL_LIST_INDEX(p_s_sb) = -10000 ; /* make sure flush_old_commits does not try to flush a list while replay is on */
 
@@ -2075,12 +2078,8 @@ int journal_init(struct super_block *p_s_sb, const char * j_dev_name, int old_fo
   memset(SB_JOURNAL(p_s_sb)->j_list_hash_table, 0, JOURNAL_HASH_SIZE * sizeof(struct reiserfs_journal_cnode *)) ;
   memset(journal_writers, 0, sizeof(char *) * 512) ; /* debug code */
 
-  INIT_LIST_HEAD(&SB_JOURNAL(p_s_sb)->j_bitmap_nodes) ;
   INIT_LIST_HEAD(&SB_JOURNAL(p_s_sb)->j_dirty_buffers) ;
   spin_lock_init(&SB_JOURNAL(p_s_sb)->j_dirty_buffers_lock) ;
-  reiserfs_allocate_list_bitmaps(p_s_sb, SB_JOURNAL(p_s_sb)->j_list_bitmap, 
-                                 SB_BMAP_NR(p_s_sb)) ;
-  allocate_bitmap_nodes(p_s_sb) ;
 
   SB_JOURNAL(p_s_sb)->j_start = 0 ;
   SB_JOURNAL(p_s_sb)->j_len = 0 ;
@@ -2107,20 +2106,15 @@ int journal_init(struct super_block *p_s_sb, const char * j_dev_name, int old_fo
   SB_JOURNAL_LIST(p_s_sb)[0].j_list_bitmap = get_list_bitmap(p_s_sb, SB_JOURNAL_LIST(p_s_sb)) ;
   if (!(SB_JOURNAL_LIST(p_s_sb)[0].j_list_bitmap)) {
     reiserfs_warning("journal-2005, get_list_bitmap failed for journal list 0\n") ;
-    release_journal_dev(p_s_sb, journal);
-    return 1 ;
+    goto free_and_return;
   }
   if (journal_read(p_s_sb) < 0) {
     reiserfs_warning("Replay Failure, unable to mount\n") ;
-    free_journal_ram(p_s_sb) ;
-    release_journal_dev(p_s_sb, journal);
-    return 1 ;
+    goto free_and_return;
   }
   SB_JOURNAL_LIST_INDEX(p_s_sb) = 0 ; /* once the read is done, we can set this
                                          where it belongs */
 
-  INIT_LIST_HEAD (&SB_JOURNAL(p_s_sb)->j_prealloc_list);
-
   if (reiserfs_dont_log (p_s_sb))
     return 0;
 
@@ -2129,7 +2123,9 @@ int journal_init(struct super_block *p_s_sb, const char * j_dev_name, int old_fo
     commit_wq = create_workqueue("reiserfs");
 
   return 0 ;
-
+free_and_return:
+  free_journal_ram(p_s_sb);
+  return 1;
 }
 
 /*

include/asm-generic/xor.h

@@ -678,35 +678,35 @@ xor_32regs_p_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 }
 
 static struct xor_block_template xor_block_8regs = {
-	name: "8regs",
-	do_2: xor_8regs_2,
-	do_3: xor_8regs_3,
-	do_4: xor_8regs_4,
-	do_5: xor_8regs_5,
+	.name = "8regs",
+	.do_2 = xor_8regs_2,
+	.do_3 = xor_8regs_3,
+	.do_4 = xor_8regs_4,
+	.do_5 = xor_8regs_5,
 };
 
 static struct xor_block_template xor_block_32regs = {
-	name: "32regs",
-	do_2: xor_32regs_2,
-	do_3: xor_32regs_3,
-	do_4: xor_32regs_4,
-	do_5: xor_32regs_5,
+	.name = "32regs",
+	.do_2 = xor_32regs_2,
+	.do_3 = xor_32regs_3,
+	.do_4 = xor_32regs_4,
+	.do_5 = xor_32regs_5,
 };
 
 static struct xor_block_template xor_block_8regs_p = {
-	name: "8regs_prefetch",
-	do_2: xor_8regs_p_2,
-	do_3: xor_8regs_p_3,
-	do_4: xor_8regs_p_4,
-	do_5: xor_8regs_p_5,
+	.name = "8regs_prefetch",
+	.do_2 = xor_8regs_p_2,
+	.do_3 = xor_8regs_p_3,
+	.do_4 = xor_8regs_p_4,
+	.do_5 = xor_8regs_p_5,
 };
 
 static struct xor_block_template xor_block_32regs_p = {
-	name: "32regs_prefetch",
-	do_2: xor_32regs_p_2,
-	do_3: xor_32regs_p_3,
-	do_4: xor_32regs_p_4,
-	do_5: xor_32regs_p_5,
+	.name = "32regs_prefetch",
+	.do_2 = xor_32regs_p_2,
+	.do_3 = xor_32regs_p_3,
+	.do_4 = xor_32regs_p_4,
+	.do_5 = xor_32regs_p_5,
 };
 
 #define XOR_TRY_TEMPLATES			\

include/asm-i386/cpufeature.h

@@ -9,9 +9,9 @@
 
 #include <linux/bitops.h>
 
-#define NCAPINTS	4	/* Currently we have 4 32-bit words worth of info */
+#define NCAPINTS	6	/* Currently we have 6 32-bit words worth of info */
 
-/* Intel-defined CPU features, CPUID level 0x00000001, word 0 */
+/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
 #define X86_FEATURE_FPU		(0*32+ 0) /* Onboard FPU */
 #define X86_FEATURE_VME		(0*32+ 1) /* Virtual Mode Extensions */
 #define X86_FEATURE_DE		(0*32+ 2) /* Debugging Extensions */
@@ -64,6 +64,11 @@
 #define X86_FEATURE_CYRIX_ARR	(3*32+ 2) /* Cyrix ARRs (= MTRRs) */
 #define X86_FEATURE_CENTAUR_MCR	(3*32+ 3) /* Centaur MCRs (= MTRRs) */
 
+/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
+
+/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
+#define X86_FEATURE_XSTORE	(5*32+ 2) /* on-CPU RNG present (xstore insn) */
+
 
 #define cpu_has(c, bit)		test_bit(bit, (c)->x86_capability)
 #define boot_cpu_has(bit)	test_bit(bit, boot_cpu_data.x86_capability)
@@ -87,6 +92,7 @@
 #define cpu_has_k6_mtrr		boot_cpu_has(X86_FEATURE_K6_MTRR)
 #define cpu_has_cyrix_arr	boot_cpu_has(X86_FEATURE_CYRIX_ARR)
 #define cpu_has_centaur_mcr	boot_cpu_has(X86_FEATURE_CENTAUR_MCR)
+#define cpu_has_xstore		boot_cpu_has(X86_FEATURE_XSTORE)
 
 #endif /* __ASM_I386_CPUFEATURE_H */
 

include/asm-i386/msr.h

@@ -218,6 +218,7 @@
 /* VIA Cyrix defined MSRs*/
 #define MSR_VIA_FCR			0x1107
 #define MSR_VIA_LONGHAUL		0x110a
+#define MSR_VIA_RNG			0x110b
 #define MSR_VIA_BCR2			0x1147
 
 /* Transmeta defined MSRs */

include/asm-i386/xor.h

@@ -25,6 +25,7 @@
 #define XO3(x,y)	"       pxor   8*("#x")(%4), %%mm"#y"   ;\n"
 #define XO4(x,y)	"       pxor   8*("#x")(%5), %%mm"#y"   ;\n"
 
+#include <asm/i387.h>
 
 static void
 xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)

include/linux/bio.h

@@ -239,7 +239,6 @@ extern inline char *bio_kmap_irq(struct bio *bio, unsigned long *flags)
 	 * balancing is a lot nicer this way
 	 */
 	local_save_flags(*flags);
-	local_irq_disable();
 	addr = (unsigned long) kmap_atomic(bio_page(bio), KM_BIO_SRC_IRQ);
 
 	if (addr & ~PAGE_MASK)

include/linux/nfsd/export.h

@@ -35,12 +35,13 @@
 #define NFSEXP_UIDMAP		0x0040
 #define NFSEXP_KERBEROS		0x0080		/* not available */
 #define NFSEXP_SUNSECURE	0x0100
-#define NFSEXP_CROSSMNT		0x0200
+#define NFSEXP_NOHIDE		0x0200
 #define NFSEXP_NOSUBTREECHECK	0x0400
 #define	NFSEXP_NOAUTHNLM	0x0800		/* Don't authenticate NLM requests - just trust */
 #define NFSEXP_MSNFS		0x1000	/* do silly things that MS clients expect */
 #define NFSEXP_FSID		0x2000
-#define NFSEXP_ALLFLAGS		0x3FFF
+#define	NFSEXP_CROSSMNT		0x4000
+#define NFSEXP_ALLFLAGS		0x7FFF
 
 
 #ifdef __KERNEL__
@@ -73,7 +74,7 @@ struct svc_expkey {
 #define EX_SECURE(exp)		(!((exp)->ex_flags & NFSEXP_INSECURE_PORT))
 #define EX_ISSYNC(exp)		(!((exp)->ex_flags & NFSEXP_ASYNC))
 #define EX_RDONLY(exp)		((exp)->ex_flags & NFSEXP_READONLY)
-#define EX_CROSSMNT(exp)	((exp)->ex_flags & NFSEXP_CROSSMNT)
+#define EX_NOHIDE(exp)	((exp)->ex_flags & NFSEXP_NOHIDE)
 #define EX_SUNSECURE(exp)	((exp)->ex_flags & NFSEXP_SUNSECURE)
 #define EX_WGATHER(exp)		((exp)->ex_flags & NFSEXP_GATHERED_WRITES)
 

include/linux/raid/md.h

@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/hdreg.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/smp_lock.h>
 #include <linux/delay.h>
 #include <net/checksum.h>
@@ -68,13 +69,14 @@ extern inline char * bdev_partition_name (struct block_device *bdev)
 }
 extern int register_md_personality (int p_num, mdk_personality_t *p);
 extern int unregister_md_personality (int p_num);
-extern mdk_thread_t * md_register_thread (void (*run) (void *data),
-				void *data, const char *name);
+extern mdk_thread_t * md_register_thread (void (*run) (mddev_t *mddev),
+				mddev_t *mddev, const char *name);
 extern void md_unregister_thread (mdk_thread_t *thread);
 extern void md_wakeup_thread(mdk_thread_t *thread);
+extern void md_check_recovery(mddev_t *mddev);
 extern void md_interrupt_thread (mdk_thread_t *thread);
 extern void md_write_start(mddev_t *mddev);
-extern void md_write_end(mddev_t *mddev, mdk_thread_t *thread);
+extern void md_write_end(mddev_t *mddev);
 extern void md_handle_safemode(mddev_t *mddev);
 extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
 extern void md_sync_acct(mdk_rdev_t *rdev, unsigned long nr_sectors);

include/linux/raid/md_k.h

@@ -155,6 +155,7 @@ struct mdk_rdev_s
 
 	struct page	*sb_page;
 	int		sb_loaded;
+	sector_t	data_offset;	/* start of data in array */
 	sector_t	sb_offset;
 	int		preferred_minor;	/* autorun support */
 
@@ -206,22 +207,31 @@ struct mddev_s
 
 	char				uuid[16];
 
+	struct mdk_thread_s		*thread;	/* management thread */
 	struct mdk_thread_s		*sync_thread;	/* doing resync or reconstruct */
 	unsigned long			curr_resync;	/* blocks scheduled */
 	unsigned long			resync_mark;	/* a recent timestamp */
 	unsigned long			resync_mark_cnt;/* blocks written at resync_mark */
-	/* recovery_running is 0 for no recovery/resync,
-	 * 1 for active recovery
-	 * 2 for active resync
-	 * -error for an error (e.g. -EINTR)
-	 * it can only be set > 0 under reconfig_sem
+
+	/* recovery/resync flags 
+	 * NEEDED:   we might need to start a resync/recover
+	 * RUNNING:  a thread is running, or about to be started
+	 * SYNC:     actually doing a resync, not a recovery
+	 * ERR:      and IO error was detected - abort the resync/recovery
+	 * INTR:     someone requested a (clean) early abort.
+	 * DONE:     thread is done and is waiting to be reaped
 	 */
-	int				recovery_running;
-	int				recovery_error;	/* error from recovery write */
+#define	MD_RECOVERY_RUNNING	0
+#define	MD_RECOVERY_SYNC	1
+#define	MD_RECOVERY_ERR		2
+#define	MD_RECOVERY_INTR	3
+#define	MD_RECOVERY_DONE	4
+#define	MD_RECOVERY_NEEDED	5
+	unsigned long			recovery;
+
 	int				in_sync;	/* know to not need resync */
 	struct semaphore		reconfig_sem;
 	atomic_t			active;
-	int				spares;
 
 	int				degraded;	/* whether md should consider
 							 * adding a spare
@@ -230,9 +240,11 @@ struct mddev_s
 	atomic_t			recovery_active; /* blocks scheduled, but not written */
 	wait_queue_head_t		recovery_wait;
 	sector_t			recovery_cp;
-	int				safemode;	/* if set, update "clean" superblock
+	unsigned int			safemode;	/* if set, update "clean" superblock
 							 * when no writes pending.
 							 */ 
+	unsigned int			safemode_delay;
+	struct timer_list		safemode_timer;
 	atomic_t			writes_pending; 
 	request_queue_t			queue;	/* for plugging ... */
 
@@ -245,7 +257,7 @@ struct mdk_personality_s
 	int (*make_request)(request_queue_t *q, struct bio *bio);
 	int (*run)(mddev_t *mddev);
 	int (*stop)(mddev_t *mddev);
-	int (*status)(char *page, mddev_t *mddev);
+	void (*status)(struct seq_file *seq, mddev_t *mddev);
 	/* error_handler must set ->faulty and clear ->in_sync
 	 * if appropriate, and should abort recovery if needed 
 	 */
@@ -292,8 +304,8 @@ extern mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr);
 	ITERATE_RDEV_GENERIC(pending_raid_disks,rdev,tmp)
 
 typedef struct mdk_thread_s {
-	void			(*run) (void *data);
-	void			*data;
+	void			(*run) (mddev_t *mddev);
+	mddev_t			*mddev;
 	wait_queue_head_t	wqueue;
 	unsigned long           flags;
 	struct completion	*event;

include/linux/raid/md_p.h

@@ -173,5 +173,58 @@ static inline __u64 md_event(mdp_super_t *sb) {
 	return (ev<<32)| sb->events_lo;
 }
 
+/*
+ * The version-1 superblock :
+ * All numeric fields are little-endian.
+ *
+ * total size: 256 bytes plus 2 per device.
+ *  1K allows 384 devices.
+ */
+struct mdp_superblock_1 {
+	/* constant array information - 128 bytes */
+	__u32	magic;		/* MD_SB_MAGIC: 0xa92b4efc - little endian */
+	__u32	major_version;	/* 1 */
+	__u32	feature_map;	/* 0 for now */
+	__u32	pad0;		/* always set to 0 when writing */
+
+	__u8	set_uuid[16];	/* user-space generated. */
+	char	set_name[32];	/* set and interpreted by user-space */
+
+	__u64	ctime;		/* lo 40 bits are seconds, top 24 are microseconds or 0*/
+	__u32	level;		/* -4 (multipath), -1 (linear), 0,1,4,5 */
+	__u32	layout;		/* only for raid5 currently */
+	__u64	size;		/* used size of component devices, in 512byte sectors */
+
+	__u32	chunksize;	/* in 512byte sectors */
+	__u32	raid_disks;
+	__u8	pad1[128-92];	/* set to 0 when written */
+
+	/* constant this-device information - 64 bytes */
+	__u64	data_offset;	/* sector start of data, often 0 */
+	__u64	data_size;	/* sectors in this device that can be used for data */
+	__u64	super_offset;	/* sector start of this superblock */
+	__u64	recovery_offset;/* sectors before this offset (from data_offset) have been recovered */
+	__u32	dev_number;	/* permanent identifier of this  device - not role in raid */
+	__u32	cnt_corrected_read; /* number of read errors that were corrected by re-writing */
+	__u8	device_uuid[16]; /* user-space setable, ignored by kernel */
+	__u8	pad2[64-56];	/* set to 0 when writing */
+
+	/* array state information - 64 bytes */
+	__u64	utime;		/* 40 bits second, 24 btes microseconds */
+	__u64	events;		/* incremented when superblock updated */
+	__u64	resync_offset;	/* data before this offset (from data_offset) known to be in sync */
+	__u32	sb_csum;	/* checksum upto devs[max_dev] */
+	__u32	max_dev;	/* size of devs[] array to consider */
+	__u8	pad3[64-40];	/* set to 0 when writing */
+
+	/* device state information. Indexed by dev_number.
+	 * 2 bytes per device
+	 * Note there are no per-device state flags. State information is rolled
+	 * into the 'roles' value.  If a device is spare or faulty, then it doesn't
+	 * have a meaningful role.
+	 */
+	__u16	dev_roles[0];	/* role in array, or 0xffff for a spare, or 0xfffe for faulty */
+};
+
 #endif 
 

include/linux/raid/multipath.h

@@ -13,7 +13,6 @@ struct multipath_private_data {
 	struct multipath_info	multipaths[MD_SB_DISKS];
 	int			raid_disks;
 	int			working_disks;
-	mdk_thread_t		*thread;
 	spinlock_t		device_lock;
 
 	mempool_t		*pool;

include/linux/raid/raid1.h

@@ -19,7 +19,6 @@ struct r1_private_data_s {
 	int			working_disks;
 	int			last_used;
 	sector_t		next_seq_sect;
-	mdk_thread_t		*thread;
 	spinlock_t		device_lock;
 
 	/* for use when syncing mirrors: */
@@ -34,7 +33,6 @@ struct r1_private_data_s {
 
 	mempool_t *r1bio_pool;
 	mempool_t *r1buf_pool;
-	char thread_name[MD_THREAD_NAME_MAX];
 };
 
 typedef struct r1_private_data_s conf_t;

include/linux/raid/raid5.h

@@ -203,7 +203,6 @@ struct disk_info {
 struct raid5_private_data {
 	struct stripe_head	**stripe_hashtbl;
 	mddev_t			*mddev;
-	mdk_thread_t		*thread;
 	struct disk_info	disks[MD_SB_DISKS];
 	struct disk_info	*spare;
 	int			chunk_size, level, algorithm;
@@ -226,7 +225,6 @@ struct raid5_private_data {
 							 * waiting for 25% to be free
 							 */        
 	spinlock_t		device_lock;
-	char			thread_name[MD_THREAD_NAME_MAX];
 };
 
 typedef struct raid5_private_data raid5_conf_t;

include/linux/sunrpc/cache.h

@@ -190,6 +190,7 @@ RTN *FNAME ARGS										\
 			else read_unlock(&(DETAIL)->hash_lock);				\
 			if (set)							\
 				cache_fresh(DETAIL, &tmp->MEMBER, item->MEMBER.expiry_time); \
+			if (set==1 && new) cache_fresh(DETAIL, &new->MEMBER, 0);	\
 			if (new) (DETAIL)->cache_put(&new->MEMBER, DETAIL);		\
 			return tmp;							\
 		}									\

net/sunrpc/svcauth_unix.c

@@ -441,9 +441,6 @@ svcauth_unix_accept(struct svc_rqst *rqstp, u32 *authp)
 		return SVC_DENIED;
 	}
 
-	/* Put NULL verifier */
-	svc_putu32(resv, RPC_AUTH_NULL);
-	svc_putu32(resv, 0);
 
 	key.m_class = rqstp->rq_server->sv_program->pg_class;
 	key.m_addr = rqstp->rq_addr.sin_addr;
@@ -470,8 +467,13 @@ svcauth_unix_accept(struct svc_rqst *rqstp, u32 *authp)
 		}
 	else rv = SVC_DROP;
 
-	if (rqstp->rq_client == NULL && rqstp->rq_proc != 0)
+	if (rv  == SVC_OK && rqstp->rq_client == NULL && rqstp->rq_proc != 0)
 		goto badcred;
+
+	/* Put NULL verifier */
+	svc_putu32(resv, RPC_AUTH_NULL);
+	svc_putu32(resv, 0);
+
 	return rv;
 
 badcred:

net/sunrpc/svcsock.c

@@ -577,12 +577,15 @@ svc_udp_recvfrom(struct svc_rqst *rqstp)
 
 	if (skb_is_nonlinear(skb)) {
 		/* we have to copy */
+		local_bh_disable();
 		if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) {
+			local_bh_enable();
 			/* checksum error */
 			skb_free_datagram(svsk->sk_sk, skb);
 			svc_sock_received(svsk);
 			return 0;
 		}
+		local_bh_enable();
 		skb_free_datagram(svsk->sk_sk, skb); 
 	} else {
 		/* we can use it in-place */
@@ -1435,7 +1438,7 @@ static struct cache_deferred_req *
 svc_defer(struct cache_req *req)
 {
 	struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
-	int size = sizeof(struct svc_deferred_req) + (rqstp->rq_arg.head[0].iov_len);
+	int size = sizeof(struct svc_deferred_req) + (rqstp->rq_arg.len);
 	struct svc_deferred_req *dr;
 
 	if (rqstp->rq_arg.page_len)
@@ -1444,6 +1447,7 @@ svc_defer(struct cache_req *req)
 		dr = rqstp->rq_deferred;
 		rqstp->rq_deferred = NULL;
 	} else {
+		int skip  = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len;
 		/* FIXME maybe discard if size too large */
 		dr = kmalloc(size, GFP_KERNEL);
 		if (dr == NULL)
@@ -1452,8 +1456,8 @@ svc_defer(struct cache_req *req)
 		dr->serv = rqstp->rq_server;
 		dr->prot = rqstp->rq_prot;
 		dr->addr = rqstp->rq_addr;
-		dr->argslen = rqstp->rq_arg.head[0].iov_len >> 2;
-		memcpy(dr->args, rqstp->rq_arg.head[0].iov_base, dr->argslen<<2);
+		dr->argslen = rqstp->rq_arg.len >> 2;
+		memcpy(dr->args, rqstp->rq_arg.head[0].iov_base-skip, dr->argslen<<2);
 	}
 	spin_lock(&rqstp->rq_server->sv_lock);
 	rqstp->rq_sock->sk_inuse++;