v2.4.5.3 -> v2.4.5.4

  - Chris Mason: ReiserFS pre-allocation locking bugfix
  - David Miller: fix bitops users (requires "long" alignment)
  - Andrey Savochkin: file locking failure case SMP lock fix
  - Urban Widmark: smbfs update (avoid unnecessary flushing, make NetApp
  work)
  - Andrew Grover: ACPI update
  - Jeff Garzik: network driver updates
  - Maciej Rozycki: IO-APIC level trigger problem workaround
  - Rusty Russell: ipt_unclean fix
  - Richard Gooch: devfs update

13 files changed, 177 insertions, 162 deletions

diff --git a/include/asm-alpha/delay.h b/include/asm-alpha/delay.h
index ed2e38b81c00..86077c4e03ab 100644
--- a/include/asm-alpha/delay.h
+++ b/include/asm-alpha/delay.h
@@ -1,49 +1,8 @@
 #ifndef __ALPHA_DELAY_H
 #define __ALPHA_DELAY_H
 
-#include <linux/config.h>
-#include <asm/param.h>
-#include <asm/smp.h>
-
-/*
- * Copyright (C) 1993, 2000 Linus Torvalds
- *
- * Delay routines, using a pre-computed "loops_per_jiffy" value.
- */
-
-/*
- * Use only for very small delays (< 1 msec). 
- *
- * The active part of our cycle counter is only 32-bits wide, and
- * we're treating the difference between two marks as signed.  On
- * a 1GHz box, that's about 2 seconds.
- */
-
-extern __inline__ void
-__delay(int loops)
-{
-	int tmp;
-	__asm__ __volatile__(
-		"	rpcc %0\n"
-		"	addl %1,%0,%1\n"
-		"1:	rpcc %0\n"
-		"	subl %1,%0,%0\n"
-		"	bgt %0,1b"
-		: "=&r" (tmp), "=r" (loops) : "1"(loops));
-}
-
-extern __inline__ void
-__udelay(unsigned long usecs, unsigned long lpj)
-{
-	usecs *= (((unsigned long)HZ << 32) / 1000000) * lpj;
-	__delay((long)usecs >> 32);
-}
-
-#ifdef CONFIG_SMP
-#include <linux/sched.h>	/* for smp_processor_id */
-#define udelay(u)  __udelay((u), cpu_data[smp_processor_id()].loops_per_jiffy)
-#else
-#define udelay(u)  __udelay((u), loops_per_jiffy)
-#endif
+extern void __delay(int loops);
+extern void __udelay(unsigned long usecs, unsigned long lpj);
+extern void udelay(unsigned long usecs);
 
 #endif /* defined(__ALPHA_DELAY_H) */
diff --git a/include/asm-i386/hw_irq.h b/include/asm-i386/hw_irq.h
index 0c883af9d6ef..c99045972cf3 100644
--- a/include/asm-i386/hw_irq.h
+++ b/include/asm-i386/hw_irq.h
@@ -13,6 +13,7 @@
  */
 
 #include <linux/config.h>
+#include <asm/atomic.h>
 #include <asm/irq.h>
 
 /*
@@ -83,7 +84,9 @@ extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
 extern void send_IPI(int dest, int vector);
 
 extern unsigned long io_apic_irqs;
-extern volatile unsigned long irq_err_count;
+
+extern atomic_t irq_err_count;
+extern atomic_t irq_mis_count;
 
 extern char _stext, _etext;
 
diff --git a/include/asm-i386/io_apic.h b/include/asm-i386/io_apic.h
index 868f92e0e04f..767e644c8b90 100644
--- a/include/asm-i386/io_apic.h
+++ b/include/asm-i386/io_apic.h
@@ -12,6 +12,8 @@
 
 #ifdef CONFIG_X86_IO_APIC
 
+#define APIC_MISMATCH_DEBUG
+
 #define IO_APIC_BASE(idx) \
 		((volatile int *)__fix_to_virt(FIX_IO_APIC_BASE_0 + idx))
 
diff --git a/include/asm-i386/pci.h b/include/asm-i386/pci.h
index 25eb7da65b6e..3c5f5c01fba6 100644
--- a/include/asm-i386/pci.h
+++ b/include/asm-i386/pci.h
@@ -1,13 +1,19 @@
 #ifndef __i386_PCI_H
 #define __i386_PCI_H
 
+#include <linux/config.h>
+
 #ifdef __KERNEL__
 
 /* Can be used to override the logic in pci_scan_bus for skipping
    already-configured bus numbers - to be used for buggy BIOSes
    or architectures with incomplete PCI setup by the loader */
 
+#ifdef CONFIG_PCI
+extern unsigned int pcibios_assign_all_busses(void);
+#else
 #define pcibios_assign_all_busses()	0
+#endif
 
 extern unsigned long pci_mem_start;
 #define PCIBIOS_MIN_IO		0x1000
diff --git a/include/linux/ibmtr.h b/include/linux/ibmtr.h
index 3e341078b0eb..69fbe085a8d6 100644
--- a/include/linux/ibmtr.h
+++ b/include/linux/ibmtr.h
@@ -1,3 +1,6 @@
+#ifndef __LINUX_IBMTR_H__
+#define __LINUX_IBMTR_H__
+
 /* Definitions for an IBM Token Ring card. */
 /* This file is distributed under the GNU GPL   */
 
@@ -452,3 +455,4 @@ struct srb_set_funct_addr {
 	unsigned char funct_address[4];
 };
 
+#endif /* __LINUX_IBMTR_H__ */
diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h
index bd774e0df9a7..b43c299448df 100644
--- a/include/linux/if_arp.h
+++ b/include/linux/if_arp.h
@@ -79,6 +79,7 @@
 #define ARPHRD_FCFABRIC	787		/* Fibrechannel fabric		*/
 	/* 787->799 reserved for fibrechannel media types */
 #define ARPHRD_IEEE802_TR 800		/* Magic type ident for TR	*/
+#define ARPHRD_IEEE80211 801		/* IEEE 802.11			*/
 
 #define ARPHRD_VOID	  0xFFFF	/* Void type, nothing is known */
 
diff --git a/include/linux/irq.h b/include/linux/irq.h
index de247650398a..3b6af49b3071 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -62,7 +62,4 @@ extern int setup_irq(unsigned int , struct irqaction * );
 extern hw_irq_controller no_irq_type;  /* needed in every arch ? */
 extern void no_action(int cpl, void *dev_id, struct pt_regs *regs);
 
-extern volatile unsigned long irq_err_count;
-
 #endif /* __asm_h */
-
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a54ed37e5645..31ebd2ba14b2 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -40,32 +40,37 @@ extern struct list_head inactive_dirty_list;
  * library, the executable area etc).
  */
 struct vm_area_struct {
-	struct mm_struct * vm_mm;	/* VM area parameters */
-	unsigned long vm_start;
-	unsigned long vm_end;
+	struct mm_struct * vm_mm;	/* The address space we belong to. */
+	unsigned long vm_start;		/* Our start address within vm_mm. */
+	unsigned long vm_end;		/* Our end address within vm_mm. */
 
 	/* linked list of VM areas per task, sorted by address */
 	struct vm_area_struct *vm_next;
 
-	pgprot_t vm_page_prot;
-	unsigned long vm_flags;
+	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
+	unsigned long vm_flags;		/* Flags, listed below. */
 
 	/* AVL tree of VM areas per task, sorted by address */
 	short vm_avl_height;
 	struct vm_area_struct * vm_avl_left;
 	struct vm_area_struct * vm_avl_right;
 
-	/* For areas with an address space and backing store,
+	/*
+	 * For areas with an address space and backing store,
 	 * one of the address_space->i_mmap{,shared} lists,
 	 * for shm areas, the list of attaches, otherwise unused.
 	 */
 	struct vm_area_struct *vm_next_share;
 	struct vm_area_struct **vm_pprev_share;
 
+	/* Function pointers to deal with this struct. */
 	struct vm_operations_struct * vm_ops;
-	unsigned long vm_pgoff;		/* offset in PAGE_SIZE units, *not* PAGE_CACHE_SIZE */
-	struct file * vm_file;
-	unsigned long vm_raend;
+
+	/* Information about our backing store: */
+	unsigned long vm_pgoff;		/* Offset (within vm_file) in PAGE_SIZE
+					   units, *not* PAGE_CACHE_SIZE */
+	struct file * vm_file;		/* File we map to (can be NULL). */
+	unsigned long vm_raend;		/* XXX: put full readahead info here. */
 	void * vm_private_data;		/* was vm_pte (shared mem) */
 };
 
@@ -91,6 +96,7 @@ struct vm_area_struct {
 #define VM_LOCKED	0x00002000
 #define VM_IO           0x00004000	/* Memory mapped I/O or similar */
 
+					/* Used by sys_madvise() */
 #define VM_SEQ_READ	0x00008000	/* App will access data sequentially */
 #define VM_RAND_READ	0x00010000	/* App will not benefit from clustered reads */
 
@@ -125,37 +131,144 @@ struct vm_operations_struct {
 };
 
 /*
+ * Each physical page in the system has a struct page associated with
+ * it to keep track of whatever it is we are using the page for at the
+ * moment. Note that we have no way to track which tasks are using
+ * a page.
+ *
  * Try to keep the most commonly accessed fields in single cache lines
  * here (16 bytes or greater).  This ordering should be particularly
  * beneficial on 32-bit processors.
  *
  * The first line is data used in page cache lookup, the second line
  * is used for linear searches (eg. clock algorithm scans). 
+ *
+ * TODO: make this structure smaller, it could be as small as 32 bytes.
  */
 typedef struct page {
-	struct list_head list;
-	struct address_space *mapping;
-	unsigned long index;
-	struct page *next_hash;
-	atomic_t count;
-	unsigned long flags;	/* atomic flags, some possibly updated asynchronously */
-	struct list_head lru;
-	unsigned long age;
-	wait_queue_head_t wait;
-	struct page **pprev_hash;
-	struct buffer_head * buffers;
-	void *virtual; /* non-NULL if kmapped */
-	struct zone_struct *zone;
+	struct list_head list;		/* ->mapping has some page lists. */
+	struct address_space *mapping;	/* The inode (or ...) we belong to. */
+	unsigned long index;		/* Our offset within mapping. */
+	struct page *next_hash;		/* Next page sharing our hash bucket in
+					   the pagecache hash table. */
+	atomic_t count;			/* Usage count, see below. */
+	unsigned long flags;		/* atomic flags, some possibly
+					   updated asynchronously */
+	struct list_head lru;		/* Pageout list, eg. active_list;
+					   protected by pagemap_lru_lock !! */
+	unsigned long age;		/* Page aging counter. */
+	wait_queue_head_t wait;		/* Page locked?  Stand in line... */
+	struct page **pprev_hash;	/* Complement to *next_hash. */
+	struct buffer_head * buffers;	/* Buffer maps us to a disk block. */
+	void *virtual;			/* Kernel virtual address (NULL if
+					   not kmapped, ie. highmem) */
+	struct zone_struct *zone;	/* Memory zone we are in. */
 } mem_map_t;
 
+/*
+ * Methods to modify the page usage count.
+ *
+ * What counts for a page usage:
+ * - cache mapping   (page->mapping)
+ * - disk mapping    (page->buffers)
+ * - page mapped in a task's page tables, each mapping
+ *   is counted separately
+ *
+ * Also, many kernel routines increase the page count before a critical
+ * routine so they can be sure the page doesn't go away from under them.
+ */
 #define get_page(p)		atomic_inc(&(p)->count)
 #define put_page(p)		__free_page(p)
 #define put_page_testzero(p) 	atomic_dec_and_test(&(p)->count)
 #define page_count(p)		atomic_read(&(p)->count)
 #define set_page_count(p,v) 	atomic_set(&(p)->count, v)
 
-/* Page flag bit values */
-#define PG_locked		 0
+/*
+ * Various page->flags bits:
+ *
+ * PG_reserved is set for special pages, which can never be swapped
+ * out. Some of them might not even exist (eg. empty_bad_page)...
+ *
+ * Multiple processes may "see" the same page. E.g. for untouched
+ * mappings of /dev/null, all processes see the same page full of
+ * zeroes, and text pages of executables and shared libraries have
+ * only one copy in memory, at most, normally.
+ *
+ * For the non-reserved pages, page->count denotes a reference count.
+ *   page->count == 0 means the page is free.
+ *   page->count == 1 means the page is used for exactly one purpose
+ *   (e.g. a private data page of one process).
+ *
+ * A page may be used for kmalloc() or anyone else who does a
+ * __get_free_page(). In this case the page->count is at least 1, and
+ * all other fields are unused but should be 0 or NULL. The
+ * management of this page is the responsibility of the one who uses
+ * it.
+ *
+ * The other pages (we may call them "process pages") are completely
+ * managed by the Linux memory manager: I/O, buffers, swapping etc.
+ * The following discussion applies only to them.
+ *
+ * A page may belong to an inode's memory mapping. In this case,
+ * page->mapping is the pointer to the inode, and page->offset is the
+ * file offset of the page (not necessarily a multiple of PAGE_SIZE).
+ *
+ * A page may have buffers allocated to it. In this case,
+ * page->buffers is a circular list of these buffer heads. Else,
+ * page->buffers == NULL.
+ *
+ * For pages belonging to inodes, the page->count is the number of
+ * attaches, plus 1 if buffers are allocated to the page, plus one
+ * for the page cache itself.
+ *
+ * All pages belonging to an inode are in these doubly linked lists:
+ * mapping->clean_pages, mapping->dirty_pages and mapping->locked_pages;
+ * using the page->list list_head. These fields are also used for
+ * freelist managemet (when page->count==0).
+ *
+ * There is also a hash table mapping (inode,offset) to the page
+ * in memory if present. The lists for this hash table use the fields
+ * page->next_hash and page->pprev_hash.
+ *
+ * All process pages can do I/O:
+ * - inode pages may need to be read from disk,
+ * - inode pages which have been modified and are MAP_SHARED may need
+ *   to be written to disk,
+ * - private pages which have been modified may need to be swapped out
+ *   to swap space and (later) to be read back into memory.
+ * During disk I/O, PG_locked is used. This bit is set before I/O
+ * and reset when I/O completes. page->wait is a wait queue of all
+ * tasks waiting for the I/O on this page to complete.
+ * PG_uptodate tells whether the page's contents is valid.
+ * When a read completes, the page becomes uptodate, unless a disk I/O
+ * error happened.
+ *
+ * For choosing which pages to swap out, inode pages carry a
+ * PG_referenced bit, which is set any time the system accesses
+ * that page through the (inode,offset) hash table. This referenced
+ * bit, together with the referenced bit in the page tables, is used
+ * to manipulate page->age and move the page across the active,
+ * inactive_dirty and inactive_clean lists.
+ *
+ * Note that the referenced bit, the page->lru list_head and the
+ * active, inactive_dirty and inactive_clean lists are protected by
+ * the pagemap_lru_lock, and *NOT* by the usual PG_locked bit!
+ *
+ * PG_skip is used on sparc/sparc64 architectures to "skip" certain
+ * parts of the address space.
+ *
+ * PG_error is set to indicate that an I/O error occurred on this page.
+ *
+ * PG_arch_1 is an architecture specific page state bit.  The generic
+ * code guarentees that this bit is cleared for a page when it first
+ * is entered into the page cache.
+ *
+ * PG_highmem pages are not permanently mapped into the kernel virtual
+ * address space, they need to be kmapped separately for doing IO on
+ * the pages. The struct page (these bits with information) are always
+ * mapped into kernel address space...
+ */
+#define PG_locked		 0	/* Page is locked. Don't touch. */
 #define PG_error		 1
 #define PG_referenced		 2
 #define PG_uptodate		 3
@@ -258,81 +371,7 @@ static inline void set_page_dirty(struct page * page)
 #define NOPAGE_SIGBUS	(NULL)
 #define NOPAGE_OOM	((struct page *) (-1))
 
-
-/*
- * Various page->flags bits:
- *
- * PG_reserved is set for a page which must never be accessed (which
- * may not even be present).
- *
- * PG_DMA has been removed, page->zone now tells exactly wether the
- * page is suited to do DMAing into.
- *
- * Multiple processes may "see" the same page. E.g. for untouched
- * mappings of /dev/null, all processes see the same page full of
- * zeroes, and text pages of executables and shared libraries have
- * only one copy in memory, at most, normally.
- *
- * For the non-reserved pages, page->count denotes a reference count.
- *   page->count == 0 means the page is free.
- *   page->count == 1 means the page is used for exactly one purpose
- *   (e.g. a private data page of one process).
- *
- * A page may be used for kmalloc() or anyone else who does a
- * __get_free_page(). In this case the page->count is at least 1, and
- * all other fields are unused but should be 0 or NULL. The
- * management of this page is the responsibility of the one who uses
- * it.
- *
- * The other pages (we may call them "process pages") are completely
- * managed by the Linux memory manager: I/O, buffers, swapping etc.
- * The following discussion applies only to them.
- *
- * A page may belong to an inode's memory mapping. In this case,
- * page->inode is the pointer to the inode, and page->offset is the
- * file offset of the page (not necessarily a multiple of PAGE_SIZE).
- *
- * A page may have buffers allocated to it. In this case,
- * page->buffers is a circular list of these buffer heads. Else,
- * page->buffers == NULL.
- *
- * For pages belonging to inodes, the page->count is the number of
- * attaches, plus 1 if buffers are allocated to the page.
- *
- * All pages belonging to an inode make up a doubly linked list
- * inode->i_pages, using the fields page->next and page->prev. (These
- * fields are also used for freelist management when page->count==0.)
- * There is also a hash table mapping (inode,offset) to the page
- * in memory if present. The lists for this hash table use the fields
- * page->next_hash and page->pprev_hash.
- *
- * All process pages can do I/O:
- * - inode pages may need to be read from disk,
- * - inode pages which have been modified and are MAP_SHARED may need
- *   to be written to disk,
- * - private pages which have been modified may need to be swapped out
- *   to swap space and (later) to be read back into memory.
- * During disk I/O, PG_locked is used. This bit is set before I/O
- * and reset when I/O completes. page->wait is a wait queue of all
- * tasks waiting for the I/O on this page to complete.
- * PG_uptodate tells whether the page's contents is valid.
- * When a read completes, the page becomes uptodate, unless a disk I/O
- * error happened.
- *
- * For choosing which pages to swap out, inode pages carry a
- * PG_referenced bit, which is set any time the system accesses
- * that page through the (inode,offset) hash table.
- *
- * PG_skip is used on sparc/sparc64 architectures to "skip" certain
- * parts of the address space.
- *
- * PG_error is set to indicate that an I/O error occurred on this page.
- *
- * PG_arch_1 is an architecture specific page state bit.  The generic
- * code guarentees that this bit is cleared for a page when it first
- * is entered into the page cache.
- */
-
+/* The array of struct pages */
 extern mem_map_t * mem_map;
 
 /*
@@ -551,11 +590,6 @@ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * m
 
 extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr);
 
-#define buffer_under_min()	(atomic_read(&buffermem_pages) * 100 < \
-				buffer_mem.min_percent * num_physpages)
-#define pgcache_under_min()	(atomic_read(&page_cache_size) * 100 < \
-				page_cache.min_percent * num_physpages)
-
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index a5cb21c2f302..a7cda535d1f9 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1494,13 +1494,18 @@
 #define PCI_DEVICE_ID_INTEL_82801AB_5	0x2425
 #define PCI_DEVICE_ID_INTEL_82801AB_6	0x2426
 #define PCI_DEVICE_ID_INTEL_82801AB_8	0x2428
-#define PCI_DEVICE_ID_INTEL_82820FW_0	0x2440
-#define PCI_DEVICE_ID_INTEL_82820FW_1	0x2442
-#define PCI_DEVICE_ID_INTEL_82820FW_2	0x2443
-#define PCI_DEVICE_ID_INTEL_82820FW_3	0x2444
-#define PCI_DEVICE_ID_INTEL_82820FW_4	0x2449
-#define PCI_DEVICE_ID_INTEL_82820FW_5	0x244b
-#define PCI_DEVICE_ID_INTEL_82820FW_6	0x244e
+#define PCI_DEVICE_ID_INTEL_82801BA_0	0x2440
+#define PCI_DEVICE_ID_INTEL_82801BA_1	0x2442
+#define PCI_DEVICE_ID_INTEL_82801BA_2	0x2443
+#define PCI_DEVICE_ID_INTEL_82801BA_3	0x2444
+#define PCI_DEVICE_ID_INTEL_82801BA_4	0x2445
+#define PCI_DEVICE_ID_INTEL_82801BA_5	0x2446
+#define PCI_DEVICE_ID_INTEL_82801BA_6	0x2448
+#define PCI_DEVICE_ID_INTEL_82801BA_7	0x2449
+#define PCI_DEVICE_ID_INTEL_82801BA_8	0x244a
+#define PCI_DEVICE_ID_INTEL_82801BA_9	0x244b
+#define PCI_DEVICE_ID_INTEL_82801BA_10	0x244c
+#define PCI_DEVICE_ID_INTEL_82801BA_11	0x244e
 #define PCI_DEVICE_ID_INTEL_82810_MC1	0x7120
 #define PCI_DEVICE_ID_INTEL_82810_IG1	0x7121
 #define PCI_DEVICE_ID_INTEL_82810_MC3	0x7122
diff --git a/include/linux/smb_fs.h b/include/linux/smb_fs.h
index 69df503e70ea..716e50ec65f9 100644
--- a/include/linux/smb_fs.h
+++ b/include/linux/smb_fs.h
@@ -93,6 +93,11 @@ smb_kfree(void *obj)
 
 #endif /* DEBUG_SMB_MALLOC */
 
+/*
+ * Flags for the in-memory inode
+ */
+#define SMB_F_LOCALWRITE	0x02	/* file modified locally */
+
 
 /* NT1 protocol capability bits */
 #define SMB_CAP_RAW_MODE         0x0001
diff --git a/include/linux/smb_fs_i.h b/include/linux/smb_fs_i.h
index a2dffed11d0a..d04a4656e50a 100644
--- a/include/linux/smb_fs_i.h
+++ b/include/linux/smb_fs_i.h
@@ -26,6 +26,7 @@ struct smb_inode_info {
 	__u16 attr;		/* Attribute fields, DOS value */
 
 	__u16 access;		/* Access mode */
+	__u16 flags;
 	unsigned long oldmtime;	/* last time refreshed */
 	unsigned long closed;	/* timestamp when closed */
 	unsigned openers;	/* number of fileid users */
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index b204387c5163..2c8024a7128f 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -138,7 +138,7 @@ struct rpc_xprt {
 	struct rpc_wait_queue	reconn;		/* waiting for reconnect */
 	struct rpc_rqst *	free;		/* free slots */
 	struct rpc_rqst		slot[RPC_MAXREQS];
-	unsigned int		sockstate;	/* Socket state */
+	unsigned long		sockstate;	/* Socket state */
 	unsigned char		shutdown   : 1,	/* being shut down */
 				nocong	   : 1,	/* no congestion control */
 				stream     : 1,	/* TCP */
diff --git a/include/net/irda/irdacall.h b/include/net/irda/irdacall.h
deleted file mode 100644
index f7f67ce9292c..000000000000
--- a/include/net/irda/irdacall.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* Separate to keep compilation of protocols.c simpler */
-extern void irda_proto_init(struct net_proto *pro);