Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:

	Documentation/powerpc/booting-without-of.txt
	drivers/atm/Makefile
	drivers/net/fs_enet/fs_enet-main.c
	drivers/pci/pci-acpi.c
	net/8021q/vlan.c
	net/iucv/iucv.c

12 files changed, 1092 insertions, 134 deletions

diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index cd03473f354..a002a381df9 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -6628,15 +6628,18 @@ static void DAC960_DestroyProcEntries(DAC960_Controller_T *Controller)
  * DAC960_gam_ioctl is the ioctl function for performing RAID operations.
 */
 
-static int DAC960_gam_ioctl(struct inode *inode, struct file *file,
-			    unsigned int Request, unsigned long Argument)
+static long DAC960_gam_ioctl(struct file *file, unsigned int Request,
+						unsigned long Argument)
 {
-  int ErrorCode = 0;
+  long ErrorCode = 0;
   if (!capable(CAP_SYS_ADMIN)) return -EACCES;
+
+  lock_kernel();
   switch (Request)
     {
     case DAC960_IOCTL_GET_CONTROLLER_COUNT:
-      return DAC960_ControllerCount;
+      ErrorCode = DAC960_ControllerCount;
+      break;
     case DAC960_IOCTL_GET_CONTROLLER_INFO:
       {
 	DAC960_ControllerInfo_T __user *UserSpaceControllerInfo =
@@ -6644,15 +6647,20 @@ static int DAC960_gam_ioctl(struct inode *inode, struct file *file,
 	DAC960_ControllerInfo_T ControllerInfo;
 	DAC960_Controller_T *Controller;
 	int ControllerNumber;
-	if (UserSpaceControllerInfo == NULL) return -EINVAL;
-	ErrorCode = get_user(ControllerNumber,
+	if (UserSpaceControllerInfo == NULL)
+		ErrorCode = -EINVAL;
+	else ErrorCode = get_user(ControllerNumber,
 			     &UserSpaceControllerInfo->ControllerNumber);
-	if (ErrorCode != 0) return ErrorCode;
+	if (ErrorCode != 0)
+		break;;
+	ErrorCode = -ENXIO;
 	if (ControllerNumber < 0 ||
-	    ControllerNumber > DAC960_ControllerCount - 1)
-	  return -ENXIO;
+	    ControllerNumber > DAC960_ControllerCount - 1) {
+	  break;
+	}
 	Controller = DAC960_Controllers[ControllerNumber];
-	if (Controller == NULL) return -ENXIO;
+	if (Controller == NULL)
+		break;;
 	memset(&ControllerInfo, 0, sizeof(DAC960_ControllerInfo_T));
 	ControllerInfo.ControllerNumber = ControllerNumber;
 	ControllerInfo.FirmwareType = Controller->FirmwareType;
@@ -6665,8 +6673,9 @@ static int DAC960_gam_ioctl(struct inode *inode, struct file *file,
 	ControllerInfo.PCI_Address = Controller->PCI_Address;
 	strcpy(ControllerInfo.ModelName, Controller->ModelName);
 	strcpy(ControllerInfo.FirmwareVersion, Controller->FirmwareVersion);
-	return (copy_to_user(UserSpaceControllerInfo, &ControllerInfo,
+	ErrorCode = (copy_to_user(UserSpaceControllerInfo, &ControllerInfo,
 			     sizeof(DAC960_ControllerInfo_T)) ? -EFAULT : 0);
+	break;
       }
     case DAC960_IOCTL_V1_EXECUTE_COMMAND:
       {
@@ -6684,30 +6693,39 @@ static int DAC960_gam_ioctl(struct inode *inode, struct file *file,
 	int ControllerNumber, DataTransferLength;
 	unsigned char *DataTransferBuffer = NULL;
 	dma_addr_t DataTransferBufferDMA;
-	if (UserSpaceUserCommand == NULL) return -EINVAL;
+	if (UserSpaceUserCommand == NULL) {
+		ErrorCode = -EINVAL;
+		break;
+	}
 	if (copy_from_user(&UserCommand, UserSpaceUserCommand,
 				   sizeof(DAC960_V1_UserCommand_T))) {
 		ErrorCode = -EFAULT;
-		goto Failure1a;
+		break;
 	}
 	ControllerNumber = UserCommand.ControllerNumber;
+    	ErrorCode = -ENXIO;
 	if (ControllerNumber < 0 ||
 	    ControllerNumber > DAC960_ControllerCount - 1)
-	  return -ENXIO;
+	    	break;
 	Controller = DAC960_Controllers[ControllerNumber];
-	if (Controller == NULL) return -ENXIO;
-	if (Controller->FirmwareType != DAC960_V1_Controller) return -EINVAL;
+	if (Controller == NULL)
+		break;
+	ErrorCode = -EINVAL;
+	if (Controller->FirmwareType != DAC960_V1_Controller)
+		break;
 	CommandOpcode = UserCommand.CommandMailbox.Common.CommandOpcode;
 	DataTransferLength = UserCommand.DataTransferLength;
-	if (CommandOpcode & 0x80) return -EINVAL;
+	if (CommandOpcode & 0x80)
+		break;
 	if (CommandOpcode == DAC960_V1_DCDB)
 	  {
 	    if (copy_from_user(&DCDB, UserCommand.DCDB,
 			       sizeof(DAC960_V1_DCDB_T))) {
 		ErrorCode = -EFAULT;
-		goto Failure1a;
+		break;
 	    }
-	    if (DCDB.Channel >= DAC960_V1_MaxChannels) return -EINVAL;
+	    if (DCDB.Channel >= DAC960_V1_MaxChannels)
+	    		break;
 	    if (!((DataTransferLength == 0 &&
 		   DCDB.Direction
 		   == DAC960_V1_DCDB_NoDataTransfer) ||
@@ -6717,38 +6735,37 @@ static int DAC960_gam_ioctl(struct inode *inode, struct file *file,
 		  (DataTransferLength < 0 &&
 		   DCDB.Direction
 		   == DAC960_V1_DCDB_DataTransferSystemToDevice)))
-	      return -EINVAL;
+		   	break;
 	    if (((DCDB.TransferLengthHigh4 << 16) | DCDB.TransferLength)
 		!= abs(DataTransferLength))
-	      return -EINVAL;
+			break;
 	    DCDB_IOBUF = pci_alloc_consistent(Controller->PCIDevice,
 			sizeof(DAC960_V1_DCDB_T), &DCDB_IOBUFDMA);
-	    if (DCDB_IOBUF == NULL)
-			return -ENOMEM;
+	    if (DCDB_IOBUF == NULL) {
+	    		ErrorCode = -ENOMEM;
+			break;
+		}
 	  }
+	ErrorCode = -ENOMEM;
 	if (DataTransferLength > 0)
 	  {
 	    DataTransferBuffer = pci_alloc_consistent(Controller->PCIDevice,
 				DataTransferLength, &DataTransferBufferDMA);
-	    if (DataTransferBuffer == NULL) {
-		ErrorCode = -ENOMEM;
-		goto Failure1;
-	    }
+	    if (DataTransferBuffer == NULL)
+	    	break;
 	    memset(DataTransferBuffer, 0, DataTransferLength);
 	  }
 	else if (DataTransferLength < 0)
 	  {
 	    DataTransferBuffer = pci_alloc_consistent(Controller->PCIDevice,
 				-DataTransferLength, &DataTransferBufferDMA);
-	    if (DataTransferBuffer == NULL) {
-		ErrorCode = -ENOMEM;
-		goto Failure1;
-	    }
+	    if (DataTransferBuffer == NULL)
+	    	break;
 	    if (copy_from_user(DataTransferBuffer,
 			       UserCommand.DataTransferBuffer,
 			       -DataTransferLength)) {
 		ErrorCode = -EFAULT;
-		goto Failure1;
+		break;
 	    }
 	  }
 	if (CommandOpcode == DAC960_V1_DCDB)
@@ -6825,8 +6842,7 @@ static int DAC960_gam_ioctl(struct inode *inode, struct file *file,
 	if (DCDB_IOBUF != NULL)
 	  pci_free_consistent(Controller->PCIDevice, sizeof(DAC960_V1_DCDB_T),
 			DCDB_IOBUF, DCDB_IOBUFDMA);
-      Failure1a:
-	return ErrorCode;
+      	break;
       }
     case DAC960_IOCTL_V2_EXECUTE_COMMAND:
       {
@@ -6844,32 +6860,43 @@ static int DAC960_gam_ioctl(struct inode *inode, struct file *file,
 	dma_addr_t DataTransferBufferDMA;
 	unsigned char *RequestSenseBuffer = NULL;
 	dma_addr_t RequestSenseBufferDMA;
-	if (UserSpaceUserCommand == NULL) return -EINVAL;
+
+	ErrorCode = -EINVAL;
+	if (UserSpaceUserCommand == NULL)
+		break;
 	if (copy_from_user(&UserCommand, UserSpaceUserCommand,
 			   sizeof(DAC960_V2_UserCommand_T))) {
 		ErrorCode = -EFAULT;
-		goto Failure2a;
+		break;
 	}
+	ErrorCode = -ENXIO;
 	ControllerNumber = UserCommand.ControllerNumber;
 	if (ControllerNumber < 0 ||
 	    ControllerNumber > DAC960_ControllerCount - 1)
-	  return -ENXIO;
+	    	break;
 	Controller = DAC960_Controllers[ControllerNumber];
-	if (Controller == NULL) return -ENXIO;
-	if (Controller->FirmwareType != DAC960_V2_Controller) return -EINVAL;
+	if (Controller == NULL)
+		break;
+	if (Controller->FirmwareType != DAC960_V2_Controller){
+		ErrorCode = -EINVAL;
+		break;
+	}
 	DataTransferLength = UserCommand.DataTransferLength;
+    	ErrorCode = -ENOMEM;
 	if (DataTransferLength > 0)
 	  {
 	    DataTransferBuffer = pci_alloc_consistent(Controller->PCIDevice,
 				DataTransferLength, &DataTransferBufferDMA);
-	    if (DataTransferBuffer == NULL) return -ENOMEM;
+	    if (DataTransferBuffer == NULL)
+	    	break;
 	    memset(DataTransferBuffer, 0, DataTransferLength);
 	  }
 	else if (DataTransferLength < 0)
 	  {
 	    DataTransferBuffer = pci_alloc_consistent(Controller->PCIDevice,
 				-DataTransferLength, &DataTransferBufferDMA);
-	    if (DataTransferBuffer == NULL) return -ENOMEM;
+	    if (DataTransferBuffer == NULL)
+	    	break;
 	    if (copy_from_user(DataTransferBuffer,
 			       UserCommand.DataTransferBuffer,
 			       -DataTransferLength)) {
@@ -6979,8 +7006,7 @@ static int DAC960_gam_ioctl(struct inode *inode, struct file *file,
 	if (RequestSenseBuffer != NULL)
 	  pci_free_consistent(Controller->PCIDevice, RequestSenseLength,
 		RequestSenseBuffer, RequestSenseBufferDMA);
-      Failure2a:
-	return ErrorCode;
+        break;
       }
     case DAC960_IOCTL_V2_GET_HEALTH_STATUS:
       {
@@ -6990,21 +7016,33 @@ static int DAC960_gam_ioctl(struct inode *inode, struct file *file,
 	DAC960_V2_HealthStatusBuffer_T HealthStatusBuffer;
 	DAC960_Controller_T *Controller;
 	int ControllerNumber;
-	if (UserSpaceGetHealthStatus == NULL) return -EINVAL;
+	if (UserSpaceGetHealthStatus == NULL) {
+		ErrorCode = -EINVAL;
+		break;
+	}
 	if (copy_from_user(&GetHealthStatus, UserSpaceGetHealthStatus,
-			   sizeof(DAC960_V2_GetHealthStatus_T)))
-		return -EFAULT;
+			   sizeof(DAC960_V2_GetHealthStatus_T))) {
+		ErrorCode = -EFAULT;
+		break;
+	}
+	ErrorCode = -ENXIO;
 	ControllerNumber = GetHealthStatus.ControllerNumber;
 	if (ControllerNumber < 0 ||
 	    ControllerNumber > DAC960_ControllerCount - 1)
-	  return -ENXIO;
+		    break;
 	Controller = DAC960_Controllers[ControllerNumber];
-	if (Controller == NULL) return -ENXIO;
-	if (Controller->FirmwareType != DAC960_V2_Controller) return -EINVAL;
+	if (Controller == NULL)
+		break;
+	if (Controller->FirmwareType != DAC960_V2_Controller) {
+		ErrorCode = -EINVAL;
+		break;
+	}
 	if (copy_from_user(&HealthStatusBuffer,
 			   GetHealthStatus.HealthStatusBuffer,
-			   sizeof(DAC960_V2_HealthStatusBuffer_T)))
-		return -EFAULT;
+			   sizeof(DAC960_V2_HealthStatusBuffer_T))) {
+		ErrorCode = -EFAULT;
+		break;
+	}
 	while (Controller->V2.HealthStatusBuffer->StatusChangeCounter
 	       == HealthStatusBuffer.StatusChangeCounter &&
 	       Controller->V2.HealthStatusBuffer->NextEventSequenceNumber
@@ -7012,21 +7050,28 @@ static int DAC960_gam_ioctl(struct inode *inode, struct file *file,
 	  {
 	    interruptible_sleep_on_timeout(&Controller->HealthStatusWaitQueue,
 					   DAC960_MonitoringTimerInterval);
-	    if (signal_pending(current)) return -EINTR;
+	    if (signal_pending(current)) {
+	    	ErrorCode = -EINTR;
+	    	break;
+	    }
 	  }
 	if (copy_to_user(GetHealthStatus.HealthStatusBuffer,
 			 Controller->V2.HealthStatusBuffer,
 			 sizeof(DAC960_V2_HealthStatusBuffer_T)))
-		return -EFAULT;
-	return 0;
+		ErrorCode = -EFAULT;
+	else
+		ErrorCode =  0;
       }
+      default:
+	ErrorCode = -ENOTTY;
     }
-  return -EINVAL;
+  unlock_kernel();
+  return ErrorCode;
 }
 
 static const struct file_operations DAC960_gam_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= DAC960_gam_ioctl
+	.unlocked_ioctl	= DAC960_gam_ioctl
 };
 
 static struct miscdevice DAC960_gam_dev = {
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 0d1d2133d9b..61ad8d639ba 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -433,4 +433,16 @@ config VIRTIO_BLK
 	  This is the virtual block driver for virtio.  It can be used with
           lguest or QEMU based VMMs (like KVM or Xen).  Say Y or M.
 
+config BLK_DEV_HD
+	bool "Very old hard disk (MFM/RLL/IDE) driver"
+	depends on HAVE_IDE
+	depends on !ARM || ARCH_RPC || ARCH_SHARK || BROKEN
+	help
+	  This is a very old hard disk driver that lacks the enhanced
+	  functionality of the newer ones.
+
+	  It is required for systems with ancient MFM/RLL/ESDI drives.
+
+	  If unsure, say N.
+
 endif # BLK_DEV
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 5e584306be9..204332b2957 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -29,5 +29,6 @@ obj-$(CONFIG_VIRTIO_BLK)	+= virtio_blk.o
 obj-$(CONFIG_VIODASD)		+= viodasd.o
 obj-$(CONFIG_BLK_DEV_SX8)	+= sx8.o
 obj-$(CONFIG_BLK_DEV_UB)	+= ub.o
+obj-$(CONFIG_BLK_DEV_HD)	+= hd.o
 
 obj-$(CONFIG_XEN_BLKDEV_FRONTEND)	+= xen-blkfront.o
diff --git a/drivers/block/aoe/aoechr.c b/drivers/block/aoe/aoechr.c
index e8e60e7a2e7..d1de68a3192 100644
--- a/drivers/block/aoe/aoechr.c
+++ b/drivers/block/aoe/aoechr.c
@@ -7,6 +7,7 @@
 #include <linux/hdreg.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
+#include <linux/smp_lock.h>
 #include "aoe.h"
 
 enum {
@@ -174,12 +175,16 @@ aoechr_open(struct inode *inode, struct file *filp)
 {
 	int n, i;
 
+	lock_kernel();
 	n = iminor(inode);
 	filp->private_data = (void *) (unsigned long) n;
 
 	for (i = 0; i < ARRAY_SIZE(chardevs); ++i)
-		if (chardevs[i].minor == n)
+		if (chardevs[i].minor == n) {
+			unlock_kernel();
 			return 0;
+		}
+	unlock_kernel();
 	return -EINVAL;
 }
 
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 41f818be2f7..2f1746295d0 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1003,7 +1003,7 @@ aoecmd_cfg_rsp(struct sk_buff *skb)
 	 * Enough people have their dip switches set backwards to
 	 * warrant a loud message for this special case.
 	 */
-	aoemajor = be16_to_cpu(get_unaligned(&h->major));
+	aoemajor = get_unaligned_be16(&h->major);
 	if (aoemajor == 0xfff) {
 		printk(KERN_ERR "aoe: Warning: shelf address is all ones.  "
 			"Check shelf dip switches.\n");
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 5f1e1cc6165..d81632cd7d0 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -106,35 +106,34 @@ MODULE_DEVICE_TABLE(pci, cciss_pci_device_id);
 /*  board_id = Subsystem Device ID & Vendor ID
  *  product = Marketing Name for the board
  *  access = Address of the struct of function pointers
- *  nr_cmds = Number of commands supported by controller
  */
 static struct board_type products[] = {
-	{0x40700E11, "Smart Array 5300", &SA5_access, 512},
-	{0x40800E11, "Smart Array 5i", &SA5B_access, 512},
-	{0x40820E11, "Smart Array 532", &SA5B_access, 512},
-	{0x40830E11, "Smart Array 5312", &SA5B_access, 512},
-	{0x409A0E11, "Smart Array 641", &SA5_access, 512},
-	{0x409B0E11, "Smart Array 642", &SA5_access, 512},
-	{0x409C0E11, "Smart Array 6400", &SA5_access, 512},
-	{0x409D0E11, "Smart Array 6400 EM", &SA5_access, 512},
-	{0x40910E11, "Smart Array 6i", &SA5_access, 512},
-	{0x3225103C, "Smart Array P600", &SA5_access, 512},
-	{0x3223103C, "Smart Array P800", &SA5_access, 512},
-	{0x3234103C, "Smart Array P400", &SA5_access, 512},
-	{0x3235103C, "Smart Array P400i", &SA5_access, 512},
-	{0x3211103C, "Smart Array E200i", &SA5_access, 120},
-	{0x3212103C, "Smart Array E200", &SA5_access, 120},
-	{0x3213103C, "Smart Array E200i", &SA5_access, 120},
-	{0x3214103C, "Smart Array E200i", &SA5_access, 120},
-	{0x3215103C, "Smart Array E200i", &SA5_access, 120},
-	{0x3237103C, "Smart Array E500", &SA5_access, 512},
-	{0x323D103C, "Smart Array P700m", &SA5_access, 512},
-	{0x3241103C, "Smart Array P212", &SA5_access, 384},
-	{0x3243103C, "Smart Array P410", &SA5_access, 384},
-	{0x3245103C, "Smart Array P410i", &SA5_access, 384},
-	{0x3247103C, "Smart Array P411", &SA5_access, 384},
-	{0x3249103C, "Smart Array P812", &SA5_access, 384},
-	{0xFFFF103C, "Unknown Smart Array", &SA5_access, 120},
+	{0x40700E11, "Smart Array 5300", &SA5_access},
+	{0x40800E11, "Smart Array 5i", &SA5B_access},
+	{0x40820E11, "Smart Array 532", &SA5B_access},
+	{0x40830E11, "Smart Array 5312", &SA5B_access},
+	{0x409A0E11, "Smart Array 641", &SA5_access},
+	{0x409B0E11, "Smart Array 642", &SA5_access},
+	{0x409C0E11, "Smart Array 6400", &SA5_access},
+	{0x409D0E11, "Smart Array 6400 EM", &SA5_access},
+	{0x40910E11, "Smart Array 6i", &SA5_access},
+	{0x3225103C, "Smart Array P600", &SA5_access},
+	{0x3223103C, "Smart Array P800", &SA5_access},
+	{0x3234103C, "Smart Array P400", &SA5_access},
+	{0x3235103C, "Smart Array P400i", &SA5_access},
+	{0x3211103C, "Smart Array E200i", &SA5_access},
+	{0x3212103C, "Smart Array E200", &SA5_access},
+	{0x3213103C, "Smart Array E200i", &SA5_access},
+	{0x3214103C, "Smart Array E200i", &SA5_access},
+	{0x3215103C, "Smart Array E200i", &SA5_access},
+	{0x3237103C, "Smart Array E500", &SA5_access},
+	{0x323D103C, "Smart Array P700m", &SA5_access},
+	{0x3241103C, "Smart Array P212", &SA5_access},
+	{0x3243103C, "Smart Array P410", &SA5_access},
+	{0x3245103C, "Smart Array P410i", &SA5_access},
+	{0x3247103C, "Smart Array P411", &SA5_access},
+	{0x3249103C, "Smart Array P812", &SA5_access},
+	{0xFFFF103C, "Unknown Smart Array", &SA5_access},
 };
 
 /* How long to wait (in milliseconds) for board to go into simple mode */
@@ -3086,11 +3085,20 @@ static int __devinit cciss_pci_init(ctlr_info_t *c, struct pci_dev *pdev)
 	print_cfg_table(c->cfgtable);
 #endif				/* CCISS_DEBUG */
 
+	/* Some controllers support Zero Memory Raid (ZMR).
+	 * When configured in ZMR mode the number of supported
+	 * commands drops to 64. So instead of just setting an
+	 * arbitrary value we make the driver a little smarter.
+	 * We read the config table to tell us how many commands
+	 * are supported on the controller then subtract 4 to
+	 * leave a little room for ioctl calls.
+	 */
+	c->max_commands = readl(&(c->cfgtable->CmdsOutMax));
 	for (i = 0; i < ARRAY_SIZE(products); i++) {
 		if (board_id == products[i].board_id) {
 			c->product_name = products[i].product_name;
 			c->access = *(products[i].access);
-			c->nr_cmds = products[i].nr_cmds;
+			c->nr_cmds = c->max_commands - 4;
 			break;
 		}
 	}
@@ -3110,7 +3118,7 @@ static int __devinit cciss_pci_init(ctlr_info_t *c, struct pci_dev *pdev)
 		if (subsystem_vendor_id == PCI_VENDOR_ID_HP) {
 			c->product_name = products[i-1].product_name;
 			c->access = *(products[i-1].access);
-			c->nr_cmds = products[i-1].nr_cmds;
+			c->nr_cmds = c->max_commands - 4;
 			printk(KERN_WARNING "cciss: This is an unknown "
 				"Smart Array controller.\n"
 				"cciss: Please update to the latest driver "
@@ -3546,6 +3554,10 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 	for (j = 0; j <= hba[i]->highest_lun; j++)
 		add_disk(hba[i]->gendisk[j]);
 
+	/* we must register the controller even if no disks exist */
+	if (hba[i]->highest_lun == -1)
+		add_disk(hba[i]->gendisk[0]);
+
 	return 1;
 
       clean4:
diff --git a/drivers/block/hd.c b/drivers/block/hd.c
new file mode 100644
index 00000000000..682243bf2e4
--- /dev/null
+++ b/drivers/block/hd.c
@@ -0,0 +1,814 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This is the low-level hd interrupt support. It traverses the
+ * request-list, using interrupts to jump between functions. As
+ * all the functions are called within interrupts, we may not
+ * sleep. Special care is recommended.
+ *
+ *  modified by Drew Eckhardt to check nr of hd's from the CMOS.
+ *
+ *  Thanks to Branko Lankester, lankeste@fwi.uva.nl, who found a bug
+ *  in the early extended-partition checks and added DM partitions
+ *
+ *  IRQ-unmask, drive-id, multiple-mode, support for ">16 heads",
+ *  and general streamlining by Mark Lord.
+ *
+ *  Removed 99% of above. Use Mark's ide driver for those options.
+ *  This is now a lightweight ST-506 driver. (Paul Gortmaker)
+ *
+ *  Modified 1995 Russell King for ARM processor.
+ *
+ *  Bugfix: max_sectors must be <= 255 or the wheels tend to come
+ *  off in a hurry once you queue things up - Paul G. 02/2001
+ */
+
+/* Uncomment the following if you want verbose error reports. */
+/* #define VERBOSE_ERRORS */
+
+#include <linux/blkdev.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/interrupt.h>
+#include <linux/timer.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/genhd.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/ioport.h>
+#include <linux/init.h>
+#include <linux/blkpg.h>
+#include <linux/hdreg.h>
+
+#define REALLY_SLOW_IO
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/uaccess.h>
+
+#ifdef __arm__
+#undef  HD_IRQ
+#endif
+#include <asm/irq.h>
+#ifdef __arm__
+#define HD_IRQ IRQ_HARDDISK
+#endif
+
+/* Hd controller regster ports */
+
+#define HD_DATA		0x1f0		/* _CTL when writing */
+#define HD_ERROR	0x1f1		/* see err-bits */
+#define HD_NSECTOR	0x1f2		/* nr of sectors to read/write */
+#define HD_SECTOR	0x1f3		/* starting sector */
+#define HD_LCYL		0x1f4		/* starting cylinder */
+#define HD_HCYL		0x1f5		/* high byte of starting cyl */
+#define HD_CURRENT	0x1f6		/* 101dhhhh , d=drive, hhhh=head */
+#define HD_STATUS	0x1f7		/* see status-bits */
+#define HD_FEATURE	HD_ERROR	/* same io address, read=error, write=feature */
+#define HD_PRECOMP	HD_FEATURE	/* obsolete use of this port - predates IDE */
+#define HD_COMMAND	HD_STATUS	/* same io address, read=status, write=cmd */
+
+#define HD_CMD		0x3f6		/* used for resets */
+#define HD_ALTSTATUS	0x3f6		/* same as HD_STATUS but doesn't clear irq */
+
+/* Bits of HD_STATUS */
+#define ERR_STAT		0x01
+#define INDEX_STAT		0x02
+#define ECC_STAT		0x04	/* Corrected error */
+#define DRQ_STAT		0x08
+#define SEEK_STAT		0x10
+#define SERVICE_STAT		SEEK_STAT
+#define WRERR_STAT		0x20
+#define READY_STAT		0x40
+#define BUSY_STAT		0x80
+
+/* Bits for HD_ERROR */
+#define MARK_ERR		0x01	/* Bad address mark */
+#define TRK0_ERR		0x02	/* couldn't find track 0 */
+#define ABRT_ERR		0x04	/* Command aborted */
+#define MCR_ERR			0x08	/* media change request */
+#define ID_ERR			0x10	/* ID field not found */
+#define MC_ERR			0x20	/* media changed */
+#define ECC_ERR			0x40	/* Uncorrectable ECC error */
+#define BBD_ERR			0x80	/* pre-EIDE meaning:  block marked bad */
+#define ICRC_ERR		0x80	/* new meaning:  CRC error during transfer */
+
+static DEFINE_SPINLOCK(hd_lock);
+static struct request_queue *hd_queue;
+
+#define MAJOR_NR HD_MAJOR
+#define QUEUE (hd_queue)
+#define CURRENT elv_next_request(hd_queue)
+
+#define TIMEOUT_VALUE	(6*HZ)
+#define	HD_DELAY	0
+
+#define MAX_ERRORS     16	/* Max read/write errors/sector */
+#define RESET_FREQ      8	/* Reset controller every 8th retry */
+#define RECAL_FREQ      4	/* Recalibrate every 4th retry */
+#define MAX_HD		2
+
+#define STAT_OK		(READY_STAT|SEEK_STAT)
+#define OK_STATUS(s)	(((s)&(STAT_OK|(BUSY_STAT|WRERR_STAT|ERR_STAT)))==STAT_OK)
+
+static void recal_intr(void);
+static void bad_rw_intr(void);
+
+static int reset;
+static int hd_error;
+
+/*
+ *  This struct defines the HD's and their types.
+ */
+struct hd_i_struct {
+	unsigned int head, sect, cyl, wpcom, lzone, ctl;
+	int unit;
+	int recalibrate;
+	int special_op;
+};
+
+#ifdef HD_TYPE
+static struct hd_i_struct hd_info[] = { HD_TYPE };
+static int NR_HD = ARRAY_SIZE(hd_info);
+#else
+static struct hd_i_struct hd_info[MAX_HD];
+static int NR_HD;
+#endif
+
+static struct gendisk *hd_gendisk[MAX_HD];
+
+static struct timer_list device_timer;
+
+#define TIMEOUT_VALUE (6*HZ)
+
+#define SET_TIMER							\
+	do {								\
+		mod_timer(&device_timer, jiffies + TIMEOUT_VALUE);	\
+	} while (0)
+
+static void (*do_hd)(void) = NULL;
+#define SET_HANDLER(x) \
+if ((do_hd = (x)) != NULL) \
+	SET_TIMER; \
+else \
+	del_timer(&device_timer);
+
+
+#if (HD_DELAY > 0)
+
+#include <asm/i8253.h>
+
+unsigned long last_req;
+
+unsigned long read_timer(void)
+{
+	unsigned long t, flags;
+	int i;
+
+	spin_lock_irqsave(&i8253_lock, flags);
+	t = jiffies * 11932;
+	outb_p(0, 0x43);
+	i = inb_p(0x40);
+	i |= inb(0x40) << 8;
+	spin_unlock_irqrestore(&i8253_lock, flags);
+	return(t - i);
+}
+#endif
+
+static void __init hd_setup(char *str, int *ints)
+{
+	int hdind = 0;
+
+	if (ints[0] != 3)
+		return;
+	if (hd_info[0].head != 0)
+		hdind = 1;
+	hd_info[hdind].head = ints[2];
+	hd_info[hdind].sect = ints[3];
+	hd_info[hdind].cyl = ints[1];
+	hd_info[hdind].wpcom = 0;
+	hd_info[hdind].lzone = ints[1];
+	hd_info[hdind].ctl = (ints[2] > 8 ? 8 : 0);
+	NR_HD = hdind+1;
+}
+
+static void dump_status(const char *msg, unsigned int stat)
+{
+	char *name = "hd?";
+	if (CURRENT)
+		name = CURRENT->rq_disk->disk_name;
+
+#ifdef VERBOSE_ERRORS
+	printk("%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
+	if (stat & BUSY_STAT)	printk("Busy ");
+	if (stat & READY_STAT)	printk("DriveReady ");
+	if (stat & WRERR_STAT)	printk("WriteFault ");
+	if (stat & SEEK_STAT)	printk("SeekComplete ");
+	if (stat & DRQ_STAT)	printk("DataRequest ");
+	if (stat & ECC_STAT)	printk("CorrectedError ");
+	if (stat & INDEX_STAT)	printk("Index ");
+	if (stat & ERR_STAT)	printk("Error ");
+	printk("}\n");
+	if ((stat & ERR_STAT) == 0) {
+		hd_error = 0;
+	} else {
+		hd_error = inb(HD_ERROR);
+		printk("%s: %s: error=0x%02x { ", name, msg, hd_error & 0xff);
+		if (hd_error & BBD_ERR)		printk("BadSector ");
+		if (hd_error & ECC_ERR)		printk("UncorrectableError ");
+		if (hd_error & ID_ERR)		printk("SectorIdNotFound ");
+		if (hd_error & ABRT_ERR)	printk("DriveStatusError ");
+		if (hd_error & TRK0_ERR)	printk("TrackZeroNotFound ");
+		if (hd_error & MARK_ERR)	printk("AddrMarkNotFound ");
+		printk("}");
+		if (hd_error & (BBD_ERR|ECC_ERR|ID_ERR|MARK_ERR)) {
+			printk(", CHS=%d/%d/%d", (inb(HD_HCYL)<<8) + inb(HD_LCYL),
+				inb(HD_CURRENT) & 0xf, inb(HD_SECTOR));
+			if (CURRENT)
+				printk(", sector=%ld", CURRENT->sector);
+		}
+		printk("\n");
+	}
+#else
+	printk("%s: %s: status=0x%02x.\n", name, msg, stat & 0xff);
+	if ((stat & ERR_STAT) == 0) {
+		hd_error = 0;
+	} else {
+		hd_error = inb(HD_ERROR);
+		printk("%s: %s: error=0x%02x.\n", name, msg, hd_error & 0xff);
+	}
+#endif
+}
+
+static void check_status(void)
+{
+	int i = inb_p(HD_STATUS);
+
+	if (!OK_STATUS(i)) {
+		dump_status("check_status", i);
+		bad_rw_intr();
+	}
+}
+
+static int controller_busy(void)
+{
+	int retries = 100000;
+	unsigned char status;
+
+	do {
+		status = inb_p(HD_STATUS);
+	} while ((status & BUSY_STAT) && --retries);
+	return status;
+}
+
+static int status_ok(void)
+{
+	unsigned char status = inb_p(HD_STATUS);
+
+	if (status & BUSY_STAT)
+		return 1;	/* Ancient, but does it make sense??? */
+	if (status & WRERR_STAT)
+		return 0;
+	if (!(status & READY_STAT))
+		return 0;
+	if (!(status & SEEK_STAT))
+		return 0;
+	return 1;
+}
+
+static int controller_ready(unsigned int drive, unsigned int head)
+{
+	int retry = 100;
+
+	do {
+		if (controller_busy() & BUSY_STAT)
+			return 0;
+		outb_p(0xA0 | (drive<<4) | head, HD_CURRENT);
+		if (status_ok())
+			return 1;
+	} while (--retry);
+	return 0;
+}
+
+static void hd_out(struct hd_i_struct *disk,
+		   unsigned int nsect,
+		   unsigned int sect,
+		   unsigned int head,
+		   unsigned int cyl,
+		   unsigned int cmd,
+		   void (*intr_addr)(void))
+{
+	unsigned short port;
+
+#if (HD_DELAY > 0)
+	while (read_timer() - last_req < HD_DELAY)
+		/* nothing */;
+#endif
+	if (reset)
+		return;
+	if (!controller_ready(disk->unit, head)) {
+		reset = 1;
+		return;
+	}
+	SET_HANDLER(intr_addr);
+	outb_p(disk->ctl, HD_CMD);
+	port = HD_DATA;
+	outb_p(disk->wpcom >> 2, ++port);
+	outb_p(nsect, ++port);
+	outb_p(sect, ++port);
+	outb_p(cyl, ++port);
+	outb_p(cyl >> 8, ++port);
+	outb_p(0xA0 | (disk->unit << 4) | head, ++port);
+	outb_p(cmd, ++port);
+}
+
+static void hd_request (void);
+
+static int drive_busy(void)
+{
+	unsigned int i;
+	unsigned char c;
+
+	for (i = 0; i < 500000 ; i++) {
+		c = inb_p(HD_STATUS);
+		if ((c & (BUSY_STAT | READY_STAT | SEEK_STAT)) == STAT_OK)
+			return 0;
+	}
+	dump_status("reset timed out", c);
+	return 1;
+}
+
+static void reset_controller(void)
+{
+	int	i;
+
+	outb_p(4, HD_CMD);
+	for (i = 0; i < 1000; i++) barrier();
+	outb_p(hd_info[0].ctl & 0x0f, HD_CMD);
+	for (i = 0; i < 1000; i++) barrier();
+	if (drive_busy())
+		printk("hd: controller still busy\n");
+	else if ((hd_error = inb(HD_ERROR)) != 1)
+		printk("hd: controller reset failed: %02x\n", hd_error);
+}
+
+static void reset_hd(void)
+{
+	static int i;
+
+repeat:
+	if (reset) {
+		reset = 0;
+		i = -1;
+		reset_controller();
+	} else {
+		check_status();
+		if (reset)
+			goto repeat;
+	}
+	if (++i < NR_HD) {
+		struct hd_i_struct *disk = &hd_info[i];
+		disk->special_op = disk->recalibrate = 1;
+		hd_out(disk, disk->sect, disk->sect, disk->head-1,
+			disk->cyl, WIN_SPECIFY, &reset_hd);
+		if (reset)
+			goto repeat;
+	} else
+		hd_request();
+}
+
+/*
+ * Ok, don't know what to do with the unexpected interrupts: on some machines
+ * doing a reset and a retry seems to result in an eternal loop. Right now I
+ * ignore it, and just set the timeout.
+ *
+ * On laptops (and "green" PCs), an unexpected interrupt occurs whenever the
+ * drive enters "idle", "standby", or "sleep" mode, so if the status looks
+ * "good", we just ignore the interrupt completely.
+ */
+static void unexpected_hd_interrupt(void)
+{
+	unsigned int stat = inb_p(HD_STATUS);
+
+	if (stat & (BUSY_STAT|DRQ_STAT|ECC_STAT|ERR_STAT)) {
+		dump_status("unexpected interrupt", stat);
+		SET_TIMER;
+	}
+}
+
+/*
+ * bad_rw_intr() now tries to be a bit smarter and does things
+ * according to the error returned by the controller.
+ * -Mika Liljeberg (liljeber@cs.Helsinki.FI)
+ */
+static void bad_rw_intr(void)
+{
+	struct request *req = CURRENT;
+	if (req != NULL) {
+		struct hd_i_struct *disk = req->rq_disk->private_data;
+		if (++req->errors >= MAX_ERRORS || (hd_error & BBD_ERR)) {
+			end_request(req, 0);
+			disk->special_op = disk->recalibrate = 1;
+		} else if (req->errors % RESET_FREQ == 0)
+			reset = 1;
+		else if ((hd_error & TRK0_ERR) || req->errors % RECAL_FREQ == 0)
+			disk->special_op = disk->recalibrate = 1;
+		/* Otherwise just retry */
+	}
+}
+
+static inline int wait_DRQ(void)
+{
+	int retries;
+	int stat;
+
+	for (retries = 0; retries < 100000; retries++) {
+		stat = inb_p(HD_STATUS);
+		if (stat & DRQ_STAT)
+			return 0;
+	}
+	dump_status("wait_DRQ", stat);
+	return -1;
+}
+
+static void read_intr(void)
+{
+	struct request *req;
+	int i, retries = 100000;
+
+	do {
+		i = (unsigned) inb_p(HD_STATUS);
+		if (i & BUSY_STAT)
+			continue;
+		if (!OK_STATUS(i))
+			break;
+		if (i & DRQ_STAT)
+			goto ok_to_read;
+	} while (--retries > 0);
+	dump_status("read_intr", i);
+	bad_rw_intr();
+	hd_request();
+	return;
+ok_to_read:
+	req = CURRENT;
+	insw(HD_DATA, req->buffer, 256);
+	req->sector++;
+	req->buffer += 512;
+	req->errors = 0;
+	i = --req->nr_sectors;
+	--req->current_nr_sectors;
+#ifdef DEBUG
+	printk("%s: read: sector %ld, remaining = %ld, buffer=%p\n",
+		req->rq_disk->disk_name, req->sector, req->nr_sectors,
+		req->buffer+512);
+#endif
+	if (req->current_nr_sectors <= 0)
+		end_request(req, 1);
+	if (i > 0) {
+		SET_HANDLER(&read_intr);
+		return;
+	}
+	(void) inb_p(HD_STATUS);
+#if (HD_DELAY > 0)
+	last_req = read_timer();
+#endif
+	if (elv_next_request(QUEUE))
+		hd_request();
+	return;
+}
+
+static void write_intr(void)
+{
+	struct request *req = CURRENT;
+	int i;
+	int retries = 100000;
+
+	do {
+		i = (unsigned) inb_p(HD_STATUS);
+		if (i & BUSY_STAT)
+			continue;
+		if (!OK_STATUS(i))
+			break;
+		if ((req->nr_sectors <= 1) || (i & DRQ_STAT))
+			goto ok_to_write;
+	} while (--retries > 0);
+	dump_status("write_intr", i);
+	bad_rw_intr();
+	hd_request();
+	return;
+ok_to_write:
+	req->sector++;
+	i = --req->nr_sectors;
+	--req->current_nr_sectors;
+	req->buffer += 512;
+	if (!i || (req->bio && req->current_nr_sectors <= 0))
+		end_request(req, 1);
+	if (i > 0) {
+		SET_HANDLER(&write_intr);
+		outsw(HD_DATA, req->buffer, 256);
+		local_irq_enable();
+	} else {
+#if (HD_DELAY > 0)
+		last_req = read_timer();
+#endif
+		hd_request();
+	}
+	return;
+}
+
+static void recal_intr(void)
+{
+	check_status();
+#if (HD_DELAY > 0)
+	last_req = read_timer();
+#endif
+	hd_request();
+}
+
+/*
+ * This is another of the error-routines I don't know what to do with. The
+ * best idea seems to just set reset, and start all over again.
+ */
+static void hd_times_out(unsigned long dummy)
+{
+	char *name;
+
+	do_hd = NULL;
+
+	if (!CURRENT)
+		return;
+
+	disable_irq(HD_IRQ);
+	local_irq_enable();
+	reset = 1;
+	name = CURRENT->rq_disk->disk_name;
+	printk("%s: timeout\n", name);
+	if (++CURRENT->errors >= MAX_ERRORS) {
+#ifdef DEBUG
+		printk("%s: too many errors\n", name);
+#endif
+		end_request(CURRENT, 0);
+	}
+	local_irq_disable();
+	hd_request();
+	enable_irq(HD_IRQ);
+}
+
+static int do_special_op(struct hd_i_struct *disk, struct request *req)
+{
+	if (disk->recalibrate) {
+		disk->recalibrate = 0;
+		hd_out(disk, disk->sect, 0, 0, 0, WIN_RESTORE, &recal_intr);
+		return reset;
+	}
+	if (disk->head > 16) {
+		printk("%s: cannot handle device with more than 16 heads - giving up\n", req->rq_disk->disk_name);
+		end_request(req, 0);
+	}
+	disk->special_op = 0;
+	return 1;
+}
+
+/*
+ * The driver enables interrupts as much as possible.  In order to do this,
+ * (a) the device-interrupt is disabled before entering hd_request(),
+ * and (b) the timeout-interrupt is disabled before the sti().
+ *
+ * Interrupts are still masked (by default) whenever we are exchanging
+ * data/cmds with a drive, because some drives seem to have very poor
+ * tolerance for latency during I/O. The IDE driver has support to unmask
+ * interrupts for non-broken hardware, so use that driver if required.
+ */
+static void hd_request(void)
+{
+	unsigned int block, nsect, sec, track, head, cyl;
+	struct hd_i_struct *disk;
+	struct request *req;
+
+	if (do_hd)
+		return;
+repeat:
+	del_timer(&device_timer);
+	local_irq_enable();
+
+	req = CURRENT;
+	if (!req) {
+		do_hd = NULL;
+		return;
+	}
+
+	if (reset) {
+		local_irq_disable();
+		reset_hd();
+		return;
+	}
+	disk = req->rq_disk->private_data;
+	block = req->sector;
+	nsect = req->nr_sectors;
+	if (block >= get_capacity(req->rq_disk) ||
+	    ((block+nsect) > get_capacity(req->rq_disk))) {
+		printk("%s: bad access: block=%d, count=%d\n",
+			req->rq_disk->disk_name, block, nsect);
+		end_request(req, 0);
+		goto repeat;
+	}
+
+	if (disk->special_op) {
+		if (do_special_op(disk, req))
+			goto repeat;
+		return;
+	}
+	sec   = block % disk->sect + 1;
+	track = block / disk->sect;
+	head  = track % disk->head;
+	cyl   = track / disk->head;
+#ifdef DEBUG
+	printk("%s: %sing: CHS=%d/%d/%d, sectors=%d, buffer=%p\n",
+		req->rq_disk->disk_name,
+		req_data_dir(req) == READ ? "read" : "writ",
+		cyl, head, sec, nsect, req->buffer);
+#endif
+	if (blk_fs_request(req)) {
+		switch (rq_data_dir(req)) {
+		case READ:
+			hd_out(disk, nsect, sec, head, cyl, WIN_READ,
+				&read_intr);
+			if (reset)
+				goto repeat;
+			break;
+		case WRITE:
+			hd_out(disk, nsect, sec, head, cyl, WIN_WRITE,
+				&write_intr);
+			if (reset)
+				goto repeat;
+			if (wait_DRQ()) {
+				bad_rw_intr();
+				goto repeat;
+			}
+			outsw(HD_DATA, req->buffer, 256);
+			break;
+		default:
+			printk("unknown hd-command\n");
+			end_request(req, 0);
+			break;
+		}
+	}
+}
+
+static void do_hd_request(struct request_queue *q)
+{
+	disable_irq(HD_IRQ);
+	hd_request();
+	enable_irq(HD_IRQ);
+}
+
+static int hd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
+{
+	struct hd_i_struct *disk = bdev->bd_disk->private_data;
+
+	geo->heads = disk->head;
+	geo->sectors = disk->sect;
+	geo->cylinders = disk->cyl;
+	return 0;
+}
+
+/*
+ * Releasing a block device means we sync() it, so that it can safely
+ * be forgotten about...
+ */
+
+static irqreturn_t hd_interrupt(int irq, void *dev_id)
+{
+	void (*handler)(void) = do_hd;
+
+	do_hd = NULL;
+	del_timer(&device_timer);
+	if (!handler)
+		handler = unexpected_hd_interrupt;
+	handler();
+	local_irq_enable();
+	return IRQ_HANDLED;
+}
+
+static struct block_device_operations hd_fops = {
+	.getgeo =	hd_getgeo,
+};
+
+/*
+ * This is the hard disk IRQ description. The IRQF_DISABLED in sa_flags
+ * means we run the IRQ-handler with interrupts disabled:  this is bad for
+ * interrupt latency, but anything else has led to problems on some
+ * machines.
+ *
+ * We enable interrupts in some of the routines after making sure it's
+ * safe.
+ */
+
+static int __init hd_init(void)
+{
+	int drive;
+
+	if (register_blkdev(MAJOR_NR, "hd"))
+		return -1;
+
+	hd_queue = blk_init_queue(do_hd_request, &hd_lock);
+	if (!hd_queue) {
+		unregister_blkdev(MAJOR_NR, "hd");
+		return -ENOMEM;
+	}
+
+	blk_queue_max_sectors(hd_queue, 255);
+	init_timer(&device_timer);
+	device_timer.function = hd_times_out;
+	blk_queue_hardsect_size(hd_queue, 512);
+
+	if (!NR_HD) {
+		/*
+		 * We don't know anything about the drive.  This means
+		 * that you *MUST* specify the drive parameters to the
+		 * kernel yourself.
+		 *
+		 * If we were on an i386, we used to read this info from
+		 * the BIOS or CMOS.  This doesn't work all that well,
+		 * since this assumes that this is a primary or secondary
+		 * drive, and if we're using this legacy driver, it's
+		 * probably an auxilliary controller added to recover
+		 * legacy data off an ST-506 drive.  Either way, it's
+		 * definitely safest to have the user explicitly specify
+		 * the information.
+		 */
+		printk("hd: no drives specified - use hd=cyl,head,sectors"
+			" on kernel command line\n");
+		goto out;
+	}
+
+	for (drive = 0 ; drive < NR_HD ; drive++) {
+		struct gendisk *disk = alloc_disk(64);
+		struct hd_i_struct *p = &hd_info[drive];
+		if (!disk)
+			goto Enomem;
+		disk->major = MAJOR_NR;
+		disk->first_minor = drive << 6;
+		disk->fops = &hd_fops;
+		sprintf(disk->disk_name, "hd%c", 'a'+drive);
+		disk->private_data = p;
+		set_capacity(disk, p->head * p->sect * p->cyl);
+		disk->queue = hd_queue;
+		p->unit = drive;
+		hd_gendisk[drive] = disk;
+		printk("%s: %luMB, CHS=%d/%d/%d\n",
+			disk->disk_name, (unsigned long)get_capacity(disk)/2048,
+			p->cyl, p->head, p->sect);
+	}
+
+	if (request_irq(HD_IRQ, hd_interrupt, IRQF_DISABLED, "hd", NULL)) {
+		printk("hd: unable to get IRQ%d for the hard disk driver\n",
+			HD_IRQ);
+		goto out1;
+	}
+	if (!request_region(HD_DATA, 8, "hd")) {
+		printk(KERN_WARNING "hd: port 0x%x busy\n", HD_DATA);
+		goto out2;
+	}
+	if (!request_region(HD_CMD, 1, "hd(cmd)")) {
+		printk(KERN_WARNING "hd: port 0x%x busy\n", HD_CMD);
+		goto out3;
+	}
+
+	/* Let them fly */
+	for (drive = 0; drive < NR_HD; drive++)
+		add_disk(hd_gendisk[drive]);
+
+	return 0;
+
+out3:
+	release_region(HD_DATA, 8);
+out2:
+	free_irq(HD_IRQ, NULL);
+out1:
+	for (drive = 0; drive < NR_HD; drive++)
+		put_disk(hd_gendisk[drive]);
+	NR_HD = 0;
+out:
+	del_timer(&device_timer);
+	unregister_blkdev(MAJOR_NR, "hd");
+	blk_cleanup_queue(hd_queue);
+	return -1;
+Enomem:
+	while (drive--)
+		put_disk(hd_gendisk[drive]);
+	goto out;
+}
+
+static int __init parse_hd_setup(char *line)
+{
+	int ints[6];
+
+	(void) get_options(line, ARRAY_SIZE(ints), ints);
+	hd_setup(NULL, ints);
+
+	return 1;
+}
+__setup("hd=", parse_hd_setup);
+
+late_initcall(hd_init);
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 570f3b70dce..5fdfa7c888c 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -712,19 +712,17 @@ static void do_pd_request(struct request_queue * q)
 static int pd_special_command(struct pd_unit *disk,
 		      enum action (*func)(struct pd_unit *disk))
 {
-	DECLARE_COMPLETION_ONSTACK(wait);
-	struct request rq;
+	struct request *rq;
 	int err = 0;
 
-	blk_rq_init(NULL, &rq);
-	rq.rq_disk = disk->gd;
-	rq.end_io_data = &wait;
-	rq.end_io = blk_end_sync_rq;
-	blk_insert_request(disk->gd->queue, &rq, 0, func);
-	wait_for_completion(&wait);
-	if (rq.errors)
-		err = -EIO;
-	blk_put_request(&rq);
+	rq = blk_get_request(disk->gd->queue, READ, __GFP_WAIT);
+
+	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->special = func;
+
+	err = blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);
+
+	blk_put_request(rq);
 	return err;
 }
 
diff --git a/drivers/block/paride/pg.c b/drivers/block/paride/pg.c
index ab86e23ddc6..9d92636350e 100644
--- a/drivers/block/paride/pg.c
+++ b/drivers/block/paride/pg.c
@@ -162,6 +162,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_SLV, D_DLY};
 #include <linux/pg.h>
 #include <linux/device.h>
 #include <linux/sched.h>	/* current, TASK_* */
+#include <linux/smp_lock.h>
 #include <linux/jiffies.h>
 
 #include <asm/uaccess.h>
@@ -515,12 +516,18 @@ static int pg_open(struct inode *inode, struct file *file)
 {
 	int unit = iminor(inode) & 0x7f;
 	struct pg *dev = &devices[unit];
+	int ret = 0;
 
-	if ((unit >= PG_UNITS) || (!dev->present))
-		return -ENODEV;
+	lock_kernel();
+	if ((unit >= PG_UNITS) || (!dev->present)) {
+		ret = -ENODEV;
+		goto out;
+	}
 
-	if (test_and_set_bit(0, &dev->access))
-		return -EBUSY;
+	if (test_and_set_bit(0, &dev->access)) {
+		ret = -EBUSY;
+		goto out;
+	}
 
 	if (dev->busy) {
 		pg_reset(dev);
@@ -533,12 +540,15 @@ static int pg_open(struct inode *inode, struct file *file)
 	if (dev->bufptr == NULL) {
 		clear_bit(0, &dev->access);
 		printk("%s: buffer allocation failed\n", dev->name);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out;
 	}
 
 	file->private_data = dev;
 
-	return 0;
+out:
+	unlock_kernel();
+	return ret;
 }
 
 static int pg_release(struct inode *inode, struct file *file)
diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c
index 8b9549ab4a4..5c74c3574a5 100644
--- a/drivers/block/paride/pt.c
+++ b/drivers/block/paride/pt.c
@@ -146,6 +146,7 @@ static int (*drives[4])[6] = {&drive0, &drive1, &drive2, &drive3};
 #include <linux/mtio.h>
 #include <linux/device.h>
 #include <linux/sched.h>	/* current, TASK_*, schedule_timeout() */
+#include <linux/smp_lock.h>
 
 #include <asm/uaccess.h>
 
@@ -189,8 +190,7 @@ module_param_array(drive3, int, NULL, 0);
 #define ATAPI_LOG_SENSE		0x4d
 
 static int pt_open(struct inode *inode, struct file *file);
-static int pt_ioctl(struct inode *inode, struct file *file,
-		    unsigned int cmd, unsigned long arg);
+static long pt_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 static int pt_release(struct inode *inode, struct file *file);
 static ssize_t pt_read(struct file *filp, char __user *buf,
 		       size_t count, loff_t * ppos);
@@ -236,7 +236,7 @@ static const struct file_operations pt_fops = {
 	.owner = THIS_MODULE,
 	.read = pt_read,
 	.write = pt_write,
-	.ioctl = pt_ioctl,
+	.unlocked_ioctl = pt_ioctl,
 	.open = pt_open,
 	.release = pt_release,
 };
@@ -650,8 +650,11 @@ static int pt_open(struct inode *inode, struct file *file)
 	struct pt_unit *tape = pt + unit;
 	int err;
 
-	if (unit >= PT_UNITS || (!tape->present))
+	lock_kernel();
+	if (unit >= PT_UNITS || (!tape->present)) {
+		unlock_kernel();
 		return -ENODEV;
+	}
 
 	err = -EBUSY;
 	if (!atomic_dec_and_test(&tape->available))
@@ -678,15 +681,16 @@ static int pt_open(struct inode *inode, struct file *file)
 	}
 
 	file->private_data = tape;
+	unlock_kernel();
 	return 0;
 
 out:
 	atomic_inc(&tape->available);
+	unlock_kernel();
 	return err;
 }
 
-static int pt_ioctl(struct inode *inode, struct file *file,
-	 unsigned int cmd, unsigned long arg)
+static long pt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct pt_unit *tape = file->private_data;
 	struct mtop __user *p = (void __user *)arg;
@@ -700,23 +704,26 @@ static int pt_ioctl(struct inode *inode, struct file *file,
 		switch (mtop.mt_op) {
 
 		case MTREW:
+			lock_kernel();
 			pt_rewind(tape);
+			unlock_kernel();
 			return 0;
 
 		case MTWEOF:
+			lock_kernel();
 			pt_write_fm(tape);
+			unlock_kernel();
 			return 0;
 
 		default:
-			printk("%s: Unimplemented mt_op %d\n", tape->name,
+			/* FIXME: rate limit ?? */
+			printk(KERN_DEBUG "%s: Unimplemented mt_op %d\n", tape->name,
 			       mtop.mt_op);
 			return -EINVAL;
 		}
 
 	default:
-		printk("%s: Unimplemented ioctl 0x%x\n", tape->name, cmd);
-		return -EINVAL;
-
+		return -ENOTTY;
 	}
 }
 
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 3ba1df93e9e..45bee918c46 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -49,6 +49,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/kthread.h>
+#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/spinlock.h>
 #include <linux/file.h>
@@ -2079,7 +2080,6 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
 	unsigned char buf[64];
 	int ret;
 
-	memset(buf, 0, sizeof(buf));
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
 	cgc.sense = &sense;
 	cgc.buflen = pd->mode_offset + 12;
@@ -2126,7 +2126,6 @@ static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
 	unsigned char *cap_buf;
 	int ret, offset;
 
-	memset(buf, 0, sizeof(buf));
 	cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
 	cgc.sense = &sense;
@@ -2633,11 +2632,12 @@ end_io:
 
 
 
-static int pkt_merge_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *bvec)
+static int pkt_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
+			  struct bio_vec *bvec)
 {
 	struct pktcdvd_device *pd = q->queuedata;
-	sector_t zone = ZONE(bio->bi_sector, pd);
-	int used = ((bio->bi_sector - zone) << 9) + bio->bi_size;
+	sector_t zone = ZONE(bmd->bi_sector, pd);
+	int used = ((bmd->bi_sector - zone) << 9) + bmd->bi_size;
 	int remaining = (pd->settings.size << 9) - used;
 	int remaining2;
 
@@ -2645,7 +2645,7 @@ static int pkt_merge_bvec(struct request_queue *q, struct bio *bio, struct bio_v
 	 * A bio <= PAGE_SIZE must be allowed. If it crosses a packet
 	 * boundary, pkt_make_request() will split the bio.
 	 */
-	remaining2 = PAGE_SIZE - bio->bi_size;
+	remaining2 = PAGE_SIZE - bmd->bi_size;
 	remaining = max(remaining, remaining2);
 
 	BUG_ON(remaining < 0);
@@ -2796,9 +2796,14 @@ out_mem:
 	return ret;
 }
 
-static int pkt_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg)
+static long pkt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct pktcdvd_device *pd = inode->i_bdev->bd_disk->private_data;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct pktcdvd_device *pd;
+	long ret;
+
+	lock_kernel();
+	pd = inode->i_bdev->bd_disk->private_data;
 
 	VPRINTK("pkt_ioctl: cmd %x, dev %d:%d\n", cmd, imajor(inode), iminor(inode));
 
@@ -2811,7 +2816,8 @@ static int pkt_ioctl(struct inode *inode, struct file *file, unsigned int cmd, u
 	case CDROM_LAST_WRITTEN:
 	case CDROM_SEND_PACKET:
 	case SCSI_IOCTL_SEND_COMMAND:
-		return blkdev_ioctl(pd->bdev->bd_inode, file, cmd, arg);
+		ret = blkdev_ioctl(pd->bdev->bd_inode, file, cmd, arg);
+		break;
 
 	case CDROMEJECT:
 		/*
@@ -2820,14 +2826,15 @@ static int pkt_ioctl(struct inode *inode, struct file *file, unsigned int cmd, u
 		 */
 		if (pd->refcnt == 1)
 			pkt_lock_door(pd, 0);
-		return blkdev_ioctl(pd->bdev->bd_inode, file, cmd, arg);
+		ret = blkdev_ioctl(pd->bdev->bd_inode, file, cmd, arg);
+		break;
 
 	default:
 		VPRINTK(DRIVER_NAME": Unknown ioctl for %s (%x)\n", pd->name, cmd);
-		return -ENOTTY;
+		ret = -ENOTTY;
 	}
-
-	return 0;
+	unlock_kernel();
+	return ret;
 }
 
 static int pkt_media_changed(struct gendisk *disk)
@@ -2849,7 +2856,7 @@ static struct block_device_operations pktcdvd_ops = {
 	.owner =		THIS_MODULE,
 	.open =			pkt_open,
 	.release =		pkt_close,
-	.ioctl =		pkt_ioctl,
+	.unlocked_ioctl =	pkt_ioctl,
 	.media_changed =	pkt_media_changed,
 };
 
@@ -3014,7 +3021,8 @@ static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd)
 	mutex_unlock(&ctl_mutex);
 }
 
-static int pkt_ctl_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg)
+static long pkt_ctl_ioctl(struct file *file, unsigned int cmd,
+						unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
 	struct pkt_ctrl_command ctrl_cmd;
@@ -3031,16 +3039,22 @@ static int pkt_ctl_ioctl(struct inode *inode, struct file *file, unsigned int cm
 	case PKT_CTRL_CMD_SETUP:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
+		lock_kernel();
 		ret = pkt_setup_dev(new_decode_dev(ctrl_cmd.dev), &pkt_dev);
 		ctrl_cmd.pkt_dev = new_encode_dev(pkt_dev);
+		unlock_kernel();
 		break;
 	case PKT_CTRL_CMD_TEARDOWN:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
+		lock_kernel();
 		ret = pkt_remove_dev(new_decode_dev(ctrl_cmd.pkt_dev));
+		unlock_kernel();
 		break;
 	case PKT_CTRL_CMD_STATUS:
+		lock_kernel();
 		pkt_get_status(&ctrl_cmd);
+		unlock_kernel();
 		break;
 	default:
 		return -ENOTTY;
@@ -3053,7 +3067,7 @@ static int pkt_ctl_ioctl(struct inode *inode, struct file *file, unsigned int cm
 
 
 static const struct file_operations pkt_ctl_fops = {
-	.ioctl	 = pkt_ctl_ioctl,
+	.unlocked_ioctl	 = pkt_ctl_ioctl,
 	.owner	 = THIS_MODULE,
 };
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index f2fff5799dd..9ae05c58423 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -38,6 +38,7 @@
 #include <linux/interrupt.h>
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
+#include <linux/cdrom.h>
 #include <linux/module.h>
 
 #include <xen/xenbus.h>
@@ -153,6 +154,40 @@ static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
 	return 0;
 }
 
+int blkif_ioctl(struct inode *inode, struct file *filep,
+		unsigned command, unsigned long argument)
+{
+	struct blkfront_info *info =
+		inode->i_bdev->bd_disk->private_data;
+	int i;
+
+	dev_dbg(&info->xbdev->dev, "command: 0x%x, argument: 0x%lx\n",
+		command, (long)argument);
+
+	switch (command) {
+	case CDROMMULTISESSION:
+		dev_dbg(&info->xbdev->dev, "FIXME: support multisession CDs later\n");
+		for (i = 0; i < sizeof(struct cdrom_multisession); i++)
+			if (put_user(0, (char __user *)(argument + i)))
+				return -EFAULT;
+		return 0;
+
+	case CDROM_GET_CAPABILITY: {
+		struct gendisk *gd = info->gd;
+		if (gd->flags & GENHD_FL_CD)
+			return 0;
+		return -EINVAL;
+	}
+
+	default:
+		/*printk(KERN_ALERT "ioctl %08x not supported by Xen blkdev\n",
+		  command);*/
+		return -EINVAL; /* same return as native Linux */
+	}
+
+	return 0;
+}
+
 /*
  * blkif_queue_request
  *
@@ -324,6 +359,9 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
 	/* Make sure buffer addresses are sector-aligned. */
 	blk_queue_dma_alignment(rq, 511);
 
+	/* Make sure we don't use bounce buffers. */
+	blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
+
 	gd->queue = rq;
 
 	return 0;
@@ -546,7 +584,7 @@ static int setup_blkring(struct xenbus_device *dev,
 
 	info->ring_ref = GRANT_INVALID_REF;
 
-	sring = (struct blkif_sring *)__get_free_page(GFP_KERNEL);
+	sring = (struct blkif_sring *)__get_free_page(GFP_NOIO | __GFP_HIGH);
 	if (!sring) {
 		xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
 		return -ENOMEM;
@@ -703,7 +741,8 @@ static int blkif_recover(struct blkfront_info *info)
 	int j;
 
 	/* Stage 1: Make a safe copy of the shadow state. */
-	copy = kmalloc(sizeof(info->shadow), GFP_KERNEL);
+	copy = kmalloc(sizeof(info->shadow),
+		       GFP_NOIO | __GFP_REPEAT | __GFP_HIGH);
 	if (!copy)
 		return -ENOMEM;
 	memcpy(copy, info->shadow, sizeof(info->shadow));
@@ -959,7 +998,7 @@ static int blkif_release(struct inode *inode, struct file *filep)
 		struct xenbus_device *dev = info->xbdev;
 		enum xenbus_state state = xenbus_read_driver_state(dev->otherend);
 
-		if (state == XenbusStateClosing)
+		if (state == XenbusStateClosing && info->is_ready)
 			blkfront_closing(dev);
 	}
 	return 0;
@@ -971,6 +1010,7 @@ static struct block_device_operations xlvbd_block_fops =
 	.open = blkif_open,
 	.release = blkif_release,
 	.getgeo = blkif_getgeo,
+	.ioctl = blkif_ioctl,
 };
 
 
@@ -1006,7 +1046,7 @@ static int __init xlblk_init(void)
 module_init(xlblk_init);
 
 
-static void xlblk_exit(void)
+static void __exit xlblk_exit(void)
 {
 	return xenbus_unregister_driver(&blkfront);
 }