Merge commit 'v2.6.28' into core/core

21 files changed, 78 insertions, 46 deletions

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 6272a395d43c..8f0672d13eb1 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -391,6 +391,7 @@ extern int audit_classify_arch(int arch);
 #ifdef CONFIG_AUDITSYSCALL
 /* These are defined in auditsc.c */
 				/* Public API */
+extern void audit_finish_fork(struct task_struct *child);
 extern int  audit_alloc(struct task_struct *task);
 extern void audit_free(struct task_struct *task);
 extern void audit_syscall_entry(int arch,
@@ -434,7 +435,7 @@ static inline void audit_ptrace(struct task_struct *t)
 
 				/* Private API (for audit.c only) */
 extern unsigned int audit_serial(void);
-extern void auditsc_get_stamp(struct audit_context *ctx,
+extern int auditsc_get_stamp(struct audit_context *ctx,
 			      struct timespec *t, unsigned int *serial);
 extern int  audit_set_loginuid(struct task_struct *task, uid_t loginuid);
 #define audit_get_loginuid(t) ((t)->loginuid)
@@ -504,6 +505,7 @@ static inline int audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
 extern int audit_n_rules;
 extern int audit_signals;
 #else
+#define audit_finish_fork(t)
 #define audit_alloc(t) ({ 0; })
 #define audit_free(t) do { ; } while (0)
 #define audit_syscall_entry(ta,a,b,c,d,e) do { ; } while (0)
@@ -516,7 +518,7 @@ extern int audit_signals;
 #define audit_inode(n,d) do { ; } while (0)
 #define audit_inode_child(d,i,p) do { ; } while (0)
 #define audit_core_dumps(i) do { ; } while (0)
-#define auditsc_get_stamp(c,t,s) do { BUG(); } while (0)
+#define auditsc_get_stamp(c,t,s) (0)
 #define audit_get_loginuid(t) (-1)
 #define audit_get_sessionid(t) (-1)
 #define audit_log_task_context(b) do { ; } while (0)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a135256b272c..031a315c0509 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -662,6 +662,7 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn;
  * default timeout for SG_IO if none specified
  */
 #define BLK_DEFAULT_SG_TIMEOUT	(60 * HZ)
+#define BLK_MIN_SG_TIMEOUT	(7 * HZ)
 
 #ifdef CONFIG_BOUNCE
 extern int init_emergency_isa_pool(void);
@@ -786,6 +787,8 @@ static inline void blk_run_address_space(struct address_space *mapping)
 		blk_run_backing_dev(mapping->backing_dev_info, NULL);
 }
 
+extern void blkdev_dequeue_request(struct request *req);
+
 /*
  * blk_end_request() and friends.
  * __blk_end_request() and end_request() must be called with
@@ -820,11 +823,6 @@ extern void blk_update_request(struct request *rq, int error,
 extern unsigned int blk_rq_bytes(struct request *rq);
 extern unsigned int blk_rq_cur_bytes(struct request *rq);
 
-static inline void blkdev_dequeue_request(struct request *req)
-{
-	elv_dequeue_request(req->q, req);
-}
-
 /*
  * Access functions for manipulating queue properties
  */
@@ -921,6 +919,8 @@ extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter);
 
 #define MAX_SEGMENT_SIZE	65536
 
+#define BLK_SEG_BOUNDARY_MASK	0xFFFFFFFFUL
+
 #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
 
 static inline int queue_hardsect_size(struct request_queue *q)
diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index e9ca210ffa5b..f50785ad4781 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -19,7 +19,7 @@
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 
-#define CAN_VERSION "20071116"
+#define CAN_VERSION "20081130"
 
 /* increment this number each time you change some user-space interface */
 #define CAN_ABI_VERSION "8"
diff --git a/include/linux/compat.h b/include/linux/compat.h
index f061a1ea1b74..e88f3ecf38b4 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -252,12 +252,10 @@ extern int compat_ptrace_request(struct task_struct *child,
 				 compat_long_t request,
 				 compat_ulong_t addr, compat_ulong_t data);
 
-#ifdef __ARCH_WANT_COMPAT_SYS_PTRACE
 extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			       compat_ulong_t addr, compat_ulong_t data);
 asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 				  compat_long_t addr, compat_long_t data);
-#endif	/* __ARCH_WANT_COMPAT_SYS_PTRACE */
 
 /*
  * epoll (fs/eventpoll.c) compat bits follow ...
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0dcdd9458f4b..4a853ef6fd35 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -63,23 +63,24 @@ extern int dir_notify_enable;
 #define MAY_ACCESS 16
 #define MAY_OPEN 32
 
-#define FMODE_READ ((__force fmode_t)1)
-#define FMODE_WRITE ((__force fmode_t)2)
-
-/* Internal kernel extensions */
-#define FMODE_LSEEK	((__force fmode_t)4)
-#define FMODE_PREAD	((__force fmode_t)8)
-#define FMODE_PWRITE	FMODE_PREAD	/* These go hand in hand */
-
-/* File is being opened for execution. Primary users of this flag are
-   distributed filesystems that can use it to achieve correct ETXTBUSY
-   behavior for cross-node execution/opening_for_writing of files */
-#define FMODE_EXEC	((__force fmode_t)16)
-
-#define FMODE_NDELAY	((__force fmode_t)32)
-#define FMODE_EXCL	((__force fmode_t)64)
+/* file is open for reading */
+#define FMODE_READ		((__force fmode_t)1)
+/* file is open for writing */
+#define FMODE_WRITE		((__force fmode_t)2)
+/* file is seekable */
+#define FMODE_LSEEK		((__force fmode_t)4)
+/* file can be accessed using pread/pwrite */
+#define FMODE_PREAD		((__force fmode_t)8)
+#define FMODE_PWRITE		FMODE_PREAD	/* These go hand in hand */
+/* File is opened for execution with sys_execve / sys_uselib */
+#define FMODE_EXEC		((__force fmode_t)16)
+/* File is opened with O_NDELAY (only set for block devices) */
+#define FMODE_NDELAY		((__force fmode_t)32)
+/* File is opened with O_EXCL (only set for block devices) */
+#define FMODE_EXCL		((__force fmode_t)64)
+/* File is opened using open(.., 3, ..) and is writeable only for ioctls
+   (specialy hack for floppy.c) */
 #define FMODE_WRITE_IOCTL	((__force fmode_t)128)
-#define FMODE_NDELAY_NOW	((__force fmode_t)256)
 
 #define RW_MASK		1
 #define RWA_MASK	2
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 703eb53cfa2b..9c5bc6be2b09 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -6,6 +6,7 @@
 #include <linux/ktime.h>
 #include <linux/init.h>
 #include <linux/types.h>
+#include <linux/module.h>
 #include <linux/kallsyms.h>
 
 #ifdef CONFIG_FUNCTION_TRACER
@@ -231,7 +232,7 @@ ftrace_init_module(unsigned long *start, unsigned long *end) { }
 
 struct boot_trace {
 	pid_t			caller;
-	char			func[KSYM_NAME_LEN];
+	char			func[KSYM_SYMBOL_LEN];
 	int			result;
 	unsigned long long	duration;		/* usecs */
 	ktime_t			calltime;
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 7dcbc82f3b7b..13875ce9112a 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -63,12 +63,14 @@ static inline void *kmap_atomic(struct page *page, enum km_type idx)
 #endif /* CONFIG_HIGHMEM */
 
 /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */
+#ifndef clear_user_highpage
 static inline void clear_user_highpage(struct page *page, unsigned long vaddr)
 {
 	void *addr = kmap_atomic(page, KM_USER0);
 	clear_user_page(addr, vaddr, page);
 	kunmap_atomic(addr, KM_USER0);
 }
+#endif
 
 #ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 /**
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 54525be4b5f8..010fb26a1579 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -1296,6 +1296,13 @@ extern int __ide_pci_register_driver(struct pci_driver *driver, struct module *o
 #define ide_pci_register_driver(d) pci_register_driver(d)
 #endif
 
+static inline int ide_pci_is_in_compatibility_mode(struct pci_dev *dev)
+{
+	if ((dev->class >> 8) == PCI_CLASS_STORAGE_IDE && (dev->class & 5) != 5)
+		return 1;
+	return 0;
+}
+
 void ide_pci_setup_ports(struct pci_dev *, const struct ide_port_info *, int,
 			 hw_regs_t *, hw_regs_t **);
 void ide_setup_pci_noise(struct pci_dev *, const struct ide_port_info *);
@@ -1375,6 +1382,7 @@ enum {
 	IDE_HFLAG_IO_32BIT		= (1 << 24),
 	/* unmask IRQs */
 	IDE_HFLAG_UNMASK_IRQS		= (1 << 25),
+	IDE_HFLAG_BROKEN_ALTSTATUS	= (1 << 26),
 	/* serialize ports if DMA is possible (for sl82c105) */
 	IDE_HFLAG_SERIALIZE_DMA		= (1 << 27),
 	/* force host out of "simplex" mode */
diff --git a/include/linux/idr.h b/include/linux/idr.h
index fa035f96f2a3..dd846df8cd32 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -52,13 +52,14 @@ struct idr_layer {
 	unsigned long		 bitmap; /* A zero bit means "space here" */
 	struct idr_layer	*ary[1<<IDR_BITS];
 	int			 count;	 /* When zero, we can release it */
+	int			 layer;	 /* distance from leaf */
 	struct rcu_head		 rcu_head;
 };
 
 struct idr {
 	struct idr_layer *top;
 	struct idr_layer *id_free;
-	int		  layers;
+	int		  layers; /* only valid without concurrent changes */
 	int		  id_free_cnt;
 	spinlock_t	  lock;
 };
diff --git a/include/linux/irq.h b/include/linux/irq.h
index d058c57be02d..3dddfa703ebd 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -63,7 +63,8 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_MOVE_PENDING	0x00200000	/* need to re-target IRQ destination */
 #define IRQ_NO_BALANCING	0x00400000	/* IRQ is excluded from balancing */
 #define IRQ_SPURIOUS_DISABLED	0x00800000	/* IRQ was disabled by the spurious trap */
-#define IRQ_MOVE_PCNTXT	0x01000000	/* IRQ migration from process context */
+#define IRQ_MOVE_PCNTXT		0x01000000	/* IRQ migration from process context */
+#define IRQ_AFFINITY_SET	0x02000000	/* IRQ affinity was set from userspace*/
 
 #ifdef CONFIG_IRQ_PER_CPU
 # define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)
@@ -130,7 +131,7 @@ struct irq_chip {
 
 /**
  * struct irq_desc - interrupt descriptor
- *
+ * @irq:		interrupt number for this descriptor
  * @handle_irq:		highlevel irq-events handler [if NULL, __do_IRQ()]
  * @chip:		low level interrupt hardware access
  * @msi_desc:		MSI descriptor
@@ -149,7 +150,6 @@ struct irq_chip {
  * @cpu:		cpu index useful for balancing
  * @pending_mask:	pending rebalanced interrupts
  * @dir:		/proc/irq/ procfs entry
- * @affinity_entry:	/proc/irq/smp_affinity procfs entry on SMP
  * @name:		flow handler name for /proc/interrupts output
  */
 struct irq_desc {
@@ -210,7 +210,6 @@ extern int setup_irq(unsigned int irq, struct irqaction *new);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 
-void set_pending_irq(unsigned int irq, cpumask_t mask);
 void move_native_irq(int irq);
 void move_masked_irq(int irq);
 
@@ -228,10 +227,6 @@ static inline void move_masked_irq(int irq)
 {
 }
 
-static inline void set_pending_irq(unsigned int irq, cpumask_t mask)
-{
-}
-
 #endif /* CONFIG_GENERIC_PENDING_IRQ */
 
 #else /* CONFIG_SMP */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 59b0f1c807b5..ed3f26eb5df1 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -375,6 +375,7 @@ enum {
 	ATA_HORKAGE_BRIDGE_OK	= (1 << 10),	/* no bridge limits */
 	ATA_HORKAGE_ATAPI_MOD16_DMA = (1 << 11), /* use ATAPI DMA for commands
 						    not multiple of 16 bytes */
+	ATA_HORKAGE_FIRMWARE_WARN = (1 << 12),	/* firwmare update warning */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 2f5f8a5ef2a0..36c82c9e6ea7 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -91,7 +91,7 @@ extern int memory_notify(unsigned long val, void *v);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 #define hotplug_memory_notifier(fn, pri) {			\
-	static struct notifier_block fn##_mem_nb =		\
+	static __meminitdata struct notifier_block fn##_mem_nb =\
 		{ .notifier_call = fn, .priority = pri };	\
 	register_memory_notifier(&fn##_mem_nb);			\
 }
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index bd9977b89490..371086fd946f 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -179,6 +179,7 @@ struct mlx4_caps {
 	int			num_ports;
 	int			vl_cap[MLX4_MAX_PORTS + 1];
 	int			ib_mtu_cap[MLX4_MAX_PORTS + 1];
+	__be32			ib_port_def_cap[MLX4_MAX_PORTS + 1];
 	u64			def_mac[MLX4_MAX_PORTS + 1];
 	int			eth_mtu_cap[MLX4_MAX_PORTS + 1];
 	int			gid_table_len[MLX4_MAX_PORTS + 1];
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9d77b1d7dca8..e26f54952892 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -319,6 +319,7 @@ enum
 {
 	NAPI_STATE_SCHED,	/* Poll is scheduled */
 	NAPI_STATE_DISABLE,	/* Disable pending */
+	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
 };
 
 extern void __napi_schedule(struct napi_struct *n);
@@ -1497,6 +1498,12 @@ static inline void netif_rx_complete(struct net_device *dev,
 {
 	unsigned long flags;
 
+	/*
+	 * don't let napi dequeue from the cpu poll list
+	 * just in case its running on a different cpu
+	 */
+	if (unlikely(test_bit(NAPI_STATE_NPSVC, &napi->state)))
+		return;
 	local_irq_save(flags);
 	__netif_rx_complete(dev, napi);
 	local_irq_restore(flags);
diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h
index c19595c89304..29fe9ea1d346 100644
--- a/include/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/linux/netfilter/nfnetlink_conntrack.h
@@ -141,6 +141,7 @@ enum ctattr_protonat {
 #define CTA_PROTONAT_MAX (__CTA_PROTONAT_MAX - 1)
 
 enum ctattr_natseq {
+	CTA_NAT_SEQ_UNSPEC,
 	CTA_NAT_SEQ_CORRECTION_POS,
 	CTA_NAT_SEQ_OFFSET_BEFORE,
 	CTA_NAT_SEQ_OFFSET_AFTER,
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index be41b609c88f..e52ce475d19f 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -251,7 +251,7 @@ struct xt_target_param {
  */
 struct xt_tgchk_param {
 	const char *table;
-	void *entryinfo;
+	const void *entryinfo;
 	const struct xt_target *target;
 	void *targinfo;
 	unsigned int hook_mask;
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index f546ad6fc028..1e6d34bfa094 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -17,7 +17,7 @@ struct page_cgroup {
 	struct list_head lru;		/* per cgroup LRU list */
 };
 
-void __init pgdat_page_cgroup_init(struct pglist_data *pgdat);
+void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat);
 void __init page_cgroup_init(void);
 struct page_cgroup *lookup_page_cgroup(struct page *page);
 
@@ -91,7 +91,7 @@ static inline void unlock_page_cgroup(struct page_cgroup *pc)
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
 struct page_cgroup;
 
-static inline void pgdat_page_cgroup_init(struct pglist_data *pgdat)
+static inline void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
 {
 }
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 644ffbda17ca..55e30d114477 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -630,6 +630,10 @@ struct user_struct {
 	atomic_t inotify_watches; /* How many inotify watches does this user have? */
 	atomic_t inotify_devs;	/* How many inotify devs does this user have opened? */
 #endif
+#ifdef CONFIG_EPOLL
+	atomic_t epoll_devs;	/* The number of epoll descriptors currently open */
+	atomic_t epoll_watches;	/* The number of file descriptors currently watched */
+#endif
 #ifdef CONFIG_POSIX_MQUEUE
 	/* protected by mq_lock	*/
 	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
diff --git a/include/linux/security.h b/include/linux/security.h
index c13f1cec9abb..e3d4ecda2673 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1818,17 +1818,21 @@ static inline int security_settime(struct timespec *ts, struct timezone *tz)
 
 static inline int security_vm_enough_memory(long pages)
 {
+	WARN_ON(current->mm == NULL);
 	return cap_vm_enough_memory(current->mm, pages);
 }
 
-static inline int security_vm_enough_memory_kern(long pages)
+static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages)
 {
-	return cap_vm_enough_memory(current->mm, pages);
+	WARN_ON(mm == NULL);
+	return cap_vm_enough_memory(mm, pages);
 }
 
-static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages)
+static inline int security_vm_enough_memory_kern(long pages)
 {
-	return cap_vm_enough_memory(mm, pages);
+	/* If current->mm is a kernel thread then we will pass NULL,
+	   for this specific case that is fine */
+	return cap_vm_enough_memory(current->mm, pages);
 }
 
 static inline int security_bprm_alloc(struct linux_binprm *bprm)
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 3f9a60043a97..6e7ba16ff454 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -146,6 +146,8 @@ static inline void smp_send_reschedule(int cpu) { }
 })
 #define smp_call_function_mask(mask, func, info, wait) \
 			(up_smp_call_function(func, info))
+#define smp_call_function_many(mask, func, info, wait) \
+			(up_smp_call_function(func, info))
 static inline void init_call_single_data(void)
 {
 }
diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h
index 73a2f4eb1f7a..9b42baed3900 100644
--- a/include/linux/usb/ch9.h
+++ b/include/linux/usb/ch9.h
@@ -158,8 +158,12 @@ struct usb_ctrlrequest {
  * (rarely) accepted by SET_DESCRIPTOR.
  *
  * Note that all multi-byte values here are encoded in little endian
- * byte order "on the wire".  But when exposed through Linux-USB APIs,
- * they've been converted to cpu byte order.
+ * byte order "on the wire".  Within the kernel and when exposed
+ * through the Linux-USB APIs, they are not converted to cpu byte
+ * order; it is the responsibility of the client code to do this.
+ * The single exception is when device and configuration descriptors (but
+ * not other descriptors) are read from usbfs (i.e. /proc/bus/usb/BBB/DDD);
+ * in this case the fields are converted to host endianness by the kernel.
  */
 
 /*