Merge branch 'master' into upstream

arch/frv/Kconfig

@@ -29,6 +29,10 @@ config GENERIC_HARDIRQS
 	bool
 	default n
 
+config GENERIC_TIME
+	bool
+	default y
+
 config TIME_LOW_RES
 	bool
 	default y

arch/frv/kernel/time.c

@@ -32,8 +32,6 @@
 
 #define TICK_SIZE (tick_nsec / 1000)
 
-extern unsigned long wall_jiffies;
-
 unsigned long __nongprelbss __clkin_clock_speed_HZ;
 unsigned long __nongprelbss __ext_bus_clock_speed_HZ;
 unsigned long __nongprelbss __res_bus_clock_speed_HZ;
@@ -144,85 +142,6 @@ void time_init(void)
 	time_divisor_init();
 }
 
-/*
- * This version of gettimeofday has near microsecond resolution.
- */
-void do_gettimeofday(struct timeval *tv)
-{
-	unsigned long seq;
-	unsigned long usec, sec;
-	unsigned long max_ntp_tick;
-
-	do {
-		unsigned long lost;
-
-		seq = read_seqbegin(&xtime_lock);
-
-		usec = 0;
-		lost = jiffies - wall_jiffies;
-
-		/*
-		 * If time_adjust is negative then NTP is slowing the clock
-		 * so make sure not to go into next possible interval.
-		 * Better to lose some accuracy than have time go backwards..
-		 */
-		if (unlikely(time_adjust < 0)) {
-			max_ntp_tick = (USEC_PER_SEC / HZ) - tickadj;
-			usec = min(usec, max_ntp_tick);
-
-			if (lost)
-				usec += lost * max_ntp_tick;
-		}
-		else if (unlikely(lost))
-			usec += lost * (USEC_PER_SEC / HZ);
-
-		sec = xtime.tv_sec;
-		usec += (xtime.tv_nsec / 1000);
-	} while (read_seqretry(&xtime_lock, seq));
-
-	while (usec >= 1000000) {
-		usec -= 1000000;
-		sec++;
-	}
-
-	tv->tv_sec = sec;
-	tv->tv_usec = usec;
-}
-
-EXPORT_SYMBOL(do_gettimeofday);
-
-int do_settimeofday(struct timespec *tv)
-{
-	time_t wtm_sec, sec = tv->tv_sec;
-	long wtm_nsec, nsec = tv->tv_nsec;
-
-	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
-		return -EINVAL;
-
-	write_seqlock_irq(&xtime_lock);
-	/*
-	 * This is revolting. We need to set "xtime" correctly. However, the
-	 * value in this location is the value at the most recent update of
-	 * wall time.  Discover what correction gettimeofday() would have
-	 * made, and then undo it!
-	 */
-	nsec -= 0 * NSEC_PER_USEC;
-	nsec -= (jiffies - wall_jiffies) * TICK_NSEC;
-
-	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
-	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
-
-	set_normalized_timespec(&xtime, sec, nsec);
-	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
-
-	ntp_clear();
-	write_sequnlock_irq(&xtime_lock);
-	clock_was_set();
-	return 0;
-}
-
-EXPORT_SYMBOL(do_settimeofday);
-
 /*
  * Scheduler clock - returns current time in nanosec units.
  */

arch/ia64/kernel/entry.S

@@ -1605,8 +1605,8 @@ sys_call_table:
 	data8 sys_ni_syscall			// 1295 reserved for ppoll
 	data8 sys_unshare
 	data8 sys_splice
-	data8 sys_set_robust_list
+	data8 sys_ni_syscall			// reserved for set_robust_list
-	data8 sys_get_robust_list
+	data8 sys_ni_syscall			// reserved for get_robust_list
 	data8 sys_sync_file_range		// 1300
 	data8 sys_tee
 	data8 sys_vmsplice

arch/ia64/kernel/head.S

@@ -197,6 +197,11 @@ start_ap:
 	;;
 	srlz.i
 	;;
+ {
+	flushrs				// must be first insn in group
+	srlz.i
+ }
+	;;
 	/*
 	 * Save the region registers, predicate before they get clobbered
 	 */

arch/ia64/kernel/perfmon.c

@@ -4936,13 +4936,15 @@ abort_locked:
 	if (likely(ctx)) {
 		DPRINT(("context unlocked\n"));
 		UNPROTECT_CTX(ctx, flags);
-		fput(file);
 	}
 
 	/* copy argument back to user, if needed */
 	if (call_made && PFM_CMD_RW_ARG(cmd) && copy_to_user(arg, args_k, base_sz*count)) ret = -EFAULT;
 
 error_args:
+	if (file)
+		fput(file);
+
 	kfree(args_k);
 
 	DPRINT(("cmd=%s ret=%ld\n", PFM_CMD_NAME(cmd), ret));

arch/ia64/kernel/sys_ia64.c

@@ -163,10 +163,25 @@ sys_pipe (void)
 	return retval;
 }
 
+int ia64_mmap_check(unsigned long addr, unsigned long len,
+		unsigned long flags)
+{
+	unsigned long roff;
+
+	/*
+	 * Don't permit mappings into unmapped space, the virtual page table
+	 * of a region, or across a region boundary.  Note: RGN_MAP_LIMIT is
+	 * equal to 2^n-PAGE_SIZE (for some integer n <= 61) and len > 0.
+	 */
+	roff = REGION_OFFSET(addr);
+	if ((len > RGN_MAP_LIMIT) || (roff > (RGN_MAP_LIMIT - len)))
+		return -EINVAL;
+	return 0;
+}
+
 static inline unsigned long
 do_mmap2 (unsigned long addr, unsigned long len, int prot, int flags, int fd, unsigned long pgoff)
 {
-	unsigned long roff;
 	struct file *file = NULL;
 
 	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
@@ -188,17 +203,6 @@ do_mmap2 (unsigned long addr, unsigned long len, int prot, int flags, int fd, un
 		goto out;
 	}
 
-	/*
-	 * Don't permit mappings into unmapped space, the virtual page table of a region,
-	 * or across a region boundary.  Note: RGN_MAP_LIMIT is equal to 2^n-PAGE_SIZE
-	 * (for some integer n <= 61) and len > 0.
-	 */
-	roff = REGION_OFFSET(addr);
-	if ((len > RGN_MAP_LIMIT) || (roff > (RGN_MAP_LIMIT - len))) {
-		addr = -EINVAL;
-		goto out;
-	}
-
 	down_write(&current->mm->mmap_sem);
 	addr = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
 	up_write(&current->mm->mmap_sem);

arch/ia64/sn/kernel/setup.c

@@ -565,7 +565,7 @@ static void __init sn_init_pdas(char **cmdline_p)
  * Also sets up a few fields in the nodepda.  Also known as
  * platform_cpu_init() by the ia64 machvec code.
  */
-void __init sn_cpu_init(void)
+void __cpuinit sn_cpu_init(void)
 {
 	int cpuid;
 	int cpuphyid;

arch/sparc/kernel/sys_sparc.c

@@ -219,6 +219,21 @@ out:
 	return err;
 }
 
+int sparc_mmap_check(unsigned long addr, unsigned long len, unsigned long flags)
+{
+	if (ARCH_SUN4C_SUN4 &&
+	    (len > 0x20000000 ||
+	     ((flags & MAP_FIXED) &&
+	      addr < 0xe0000000 && addr + len > 0x20000000)))
+		return -EINVAL;
+
+	/* See asm-sparc/uaccess.h */
+	if (len > TASK_SIZE - PAGE_SIZE || addr + len > TASK_SIZE - PAGE_SIZE)
+		return -EINVAL;
+
+	return 0;
+}
+
 /* Linux version of mmap */
 static unsigned long do_mmap2(unsigned long addr, unsigned long len,
 	unsigned long prot, unsigned long flags, unsigned long fd,
@@ -233,25 +248,13 @@ static unsigned long do_mmap2(unsigned long addr, unsigned long len,
 			goto out;
 	}
 
-	retval = -EINVAL;
 	len = PAGE_ALIGN(len);
-	if (ARCH_SUN4C_SUN4 &&
-	    (len > 0x20000000 ||
-	     ((flags & MAP_FIXED) &&
-	      addr < 0xe0000000 && addr + len > 0x20000000)))
-		goto out_putf;
-
-	/* See asm-sparc/uaccess.h */
-	if (len > TASK_SIZE - PAGE_SIZE || addr + len > TASK_SIZE - PAGE_SIZE)
-		goto out_putf;
-
 	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
 
 	down_write(&current->mm->mmap_sem);
 	retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
 	up_write(&current->mm->mmap_sem);
 
-out_putf:
 	if (file)
 		fput(file);
 out:

arch/sparc64/kernel/sys_sparc.c

@@ -548,6 +548,26 @@ asmlinkage long sparc64_personality(unsigned long personality)
 	return ret;
 }
 
+int sparc64_mmap_check(unsigned long addr, unsigned long len,
+		unsigned long flags)
+{
+	if (test_thread_flag(TIF_32BIT)) {
+		if (len >= STACK_TOP32)
+			return -EINVAL;
+
+		if ((flags & MAP_FIXED) && addr > STACK_TOP32 - len)
+			return -EINVAL;
+	} else {
+		if (len >= VA_EXCLUDE_START)
+			return -EINVAL;
+
+		if ((flags & MAP_FIXED) && invalid_64bit_range(addr, len))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 /* Linux version of mmap */
 asmlinkage unsigned long sys_mmap(unsigned long addr, unsigned long len,
 	unsigned long prot, unsigned long flags, unsigned long fd,
@@ -563,27 +583,11 @@ asmlinkage unsigned long sys_mmap(unsigned long addr, unsigned long len,
 	}
 	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
 	len = PAGE_ALIGN(len);
-	retval = -EINVAL;
-
-	if (test_thread_flag(TIF_32BIT)) {
-		if (len >= STACK_TOP32)
-			goto out_putf;
-
-		if ((flags & MAP_FIXED) && addr > STACK_TOP32 - len)
-			goto out_putf;
-	} else {
-		if (len >= VA_EXCLUDE_START)
-			goto out_putf;
-
-		if ((flags & MAP_FIXED) && invalid_64bit_range(addr, len))
-			goto out_putf;
-	}
 
 	down_write(&current->mm->mmap_sem);
 	retval = do_mmap(file, addr, len, prot, flags, off);
 	up_write(&current->mm->mmap_sem);
 
-out_putf:
 	if (file)
 		fput(file);
 out:

drivers/ide/ide-proc.c

@@ -376,6 +376,8 @@ static int proc_ide_read_media
 				break;
 		case ide_floppy:media = "floppy\n";
 				break;
+		case ide_optical:media = "optical\n";
+				break;
 		default:	media = "UNKNOWN\n";
 				break;
 	}

drivers/ide/pci/sis5513.c

@@ -86,6 +86,8 @@ static const struct {
 	u8 chipset_family;
 	u8 flags;
 } SiSHostChipInfo[] = {
+	{ "SiS968",	PCI_DEVICE_ID_SI_968,	ATA_133  },
+	{ "SiS966",	PCI_DEVICE_ID_SI_966,	ATA_133  },
 	{ "SiS965",	PCI_DEVICE_ID_SI_965,	ATA_133  },
 	{ "SiS745",	PCI_DEVICE_ID_SI_745,	ATA_100  },
 	{ "SiS735",	PCI_DEVICE_ID_SI_735,	ATA_100  },

fs/ext3/inode.c

@@ -1009,11 +1009,14 @@ struct buffer_head *ext3_getblk(handle_t *handle, struct inode *inode,
 	buffer_trace_init(&dummy.b_history);
 	err = ext3_get_blocks_handle(handle, inode, block, 1,
 					&dummy, create, 1);
-	if (err == 1) {
+	/*
+	 * ext3_get_blocks_handle() returns number of blocks
+	 * mapped. 0 in case of a HOLE.
+	 */
+	if (err > 0) {
+		if (err > 1)
+			WARN_ON(1);
 		err = 0;
-	} else if (err >= 0) {
-		WARN_ON(1);
-		err = -EIO;
 	}
 	*errp = err;
 	if (!err && buffer_mapped(&dummy)) {

fs/nfs/direct.c

@@ -100,25 +100,6 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
 	return atomic_dec_and_test(&dreq->io_count);
 }
 
-/*
- * "size" is never larger than rsize or wsize.
- */
-static inline int nfs_direct_count_pages(unsigned long user_addr, size_t size)
-{
-	int page_count;
-
-	page_count = (user_addr + size + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	page_count -= user_addr >> PAGE_SHIFT;
-	BUG_ON(page_count < 0);
-
-	return page_count;
-}
-
-static inline unsigned int nfs_max_pages(unsigned int size)
-{
-	return (size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-}
-
 /**
  * nfs_direct_IO - NFS address space operation for direct I/O
  * @rw: direction (read or write)
@@ -276,28 +257,24 @@ static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, unsigned lo
 	struct nfs_open_context *ctx = dreq->ctx;
 	struct inode *inode = ctx->dentry->d_inode;
 	size_t rsize = NFS_SERVER(inode)->rsize;
-	unsigned int rpages = nfs_max_pages(rsize);
 	unsigned int pgbase;
 	int result;
 	ssize_t started = 0;
 
 	get_dreq(dreq);
 
-	pgbase = user_addr & ~PAGE_MASK;
 	do {
 		struct nfs_read_data *data;
 		size_t bytes;
 
+		pgbase = user_addr & ~PAGE_MASK;
+		bytes = min(rsize,count);
+
 		result = -ENOMEM;
-		data = nfs_readdata_alloc(rpages);
+		data = nfs_readdata_alloc(pgbase + bytes);
 		if (unlikely(!data))
 			break;
 
-		bytes = rsize;
-		if (count < rsize)
-			bytes = count;
-
-		data->npages = nfs_direct_count_pages(user_addr, bytes);
 		down_read(&current->mm->mmap_sem);
 		result = get_user_pages(current, current->mm, user_addr,
 					data->npages, 1, 0, data->pagevec, NULL);
@@ -344,8 +321,10 @@ static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, unsigned lo
 		started += bytes;
 		user_addr += bytes;
 		pos += bytes;
+		/* FIXME: Remove this unnecessary math from final patch */
 		pgbase += bytes;
 		pgbase &= ~PAGE_MASK;
+		BUG_ON(pgbase != (user_addr & ~PAGE_MASK));
 
 		count -= bytes;
 	} while (count != 0);
@@ -524,7 +503,7 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode
 
 static void nfs_alloc_commit_data(struct nfs_direct_req *dreq)
 {
-	dreq->commit_data = nfs_commit_alloc(0);
+	dreq->commit_data = nfs_commit_alloc();
 	if (dreq->commit_data != NULL)
 		dreq->commit_data->req = (struct nfs_page *) dreq;
 }
@@ -605,28 +584,24 @@ static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, unsigned l
 	struct nfs_open_context *ctx = dreq->ctx;
 	struct inode *inode = ctx->dentry->d_inode;
 	size_t wsize = NFS_SERVER(inode)->wsize;
-	unsigned int wpages = nfs_max_pages(wsize);
 	unsigned int pgbase;
 	int result;
 	ssize_t started = 0;
 
 	get_dreq(dreq);
 
-	pgbase = user_addr & ~PAGE_MASK;
 	do {
 		struct nfs_write_data *data;
 		size_t bytes;
 
+		pgbase = user_addr & ~PAGE_MASK;
+		bytes = min(wsize,count);
+
 		result = -ENOMEM;
-		data = nfs_writedata_alloc(wpages);
+		data = nfs_writedata_alloc(pgbase + bytes);
 		if (unlikely(!data))
 			break;
 
-		bytes = wsize;
-		if (count < wsize)
-			bytes = count;
-
-		data->npages = nfs_direct_count_pages(user_addr, bytes);
 		down_read(&current->mm->mmap_sem);
 		result = get_user_pages(current, current->mm, user_addr,
 					data->npages, 0, 0, data->pagevec, NULL);
@@ -676,8 +651,11 @@ static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, unsigned l
 		started += bytes;
 		user_addr += bytes;
 		pos += bytes;
+
+		/* FIXME: Remove this useless math from the final patch */
 		pgbase += bytes;
 		pgbase &= ~PAGE_MASK;
+		BUG_ON(pgbase != (user_addr & ~PAGE_MASK));
 
 		count -= bytes;
 	} while (count != 0);

fs/nfs/read.c

@@ -43,13 +43,15 @@ static mempool_t *nfs_rdata_mempool;
 
 #define MIN_POOL_READ	(32)
 
-struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
+struct nfs_read_data *nfs_readdata_alloc(size_t len)
 {
+	unsigned int pagecount = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	struct nfs_read_data *p = mempool_alloc(nfs_rdata_mempool, SLAB_NOFS);
 
 	if (p) {
 		memset(p, 0, sizeof(*p));
 		INIT_LIST_HEAD(&p->pages);
+		p->npages = pagecount;
 		if (pagecount <= ARRAY_SIZE(p->page_array))
 			p->pagevec = p->page_array;
 		else {
@@ -140,7 +142,7 @@ static int nfs_readpage_sync(struct nfs_open_context *ctx, struct inode *inode,
 	int		result;
 	struct nfs_read_data *rdata;
 
-	rdata = nfs_readdata_alloc(1);
+	rdata = nfs_readdata_alloc(count);
 	if (!rdata)
 		return -ENOMEM;
 
@@ -336,25 +338,25 @@ static int nfs_pagein_multi(struct list_head *head, struct inode *inode)
 	struct nfs_page *req = nfs_list_entry(head->next);
 	struct page *page = req->wb_page;
 	struct nfs_read_data *data;
-	unsigned int rsize = NFS_SERVER(inode)->rsize;
+	size_t rsize = NFS_SERVER(inode)->rsize, nbytes;
-	unsigned int nbytes, offset;
+	unsigned int offset;
 	int requests = 0;
 	LIST_HEAD(list);
 
 	nfs_list_remove_request(req);
 
 	nbytes = req->wb_bytes;
-	for(;;) {
+	do {
-		data = nfs_readdata_alloc(1);
+		size_t len = min(nbytes,rsize);
+
+		data = nfs_readdata_alloc(len);
 		if (!data)
 			goto out_bad;
 		INIT_LIST_HEAD(&data->pages);
 		list_add(&data->pages, &list);
 		requests++;
-		if (nbytes <= rsize)
+		nbytes -= len;
-			break;
+	} while(nbytes != 0);
-		nbytes -= rsize;
-	}
 	atomic_set(&req->wb_complete, requests);
 
 	ClearPageError(page);
@@ -402,7 +404,7 @@ static int nfs_pagein_one(struct list_head *head, struct inode *inode)
 	if (NFS_SERVER(inode)->rsize < PAGE_CACHE_SIZE)
 		return nfs_pagein_multi(head, inode);
 
-	data = nfs_readdata_alloc(NFS_SERVER(inode)->rpages);
+	data = nfs_readdata_alloc(NFS_SERVER(inode)->rsize);
 	if (!data)
 		goto out_bad;
 

fs/nfs/write.c

@@ -90,22 +90,13 @@ static mempool_t *nfs_commit_mempool;
 
 static DECLARE_WAIT_QUEUE_HEAD(nfs_write_congestion);
 
-struct nfs_write_data *nfs_commit_alloc(unsigned int pagecount)
+struct nfs_write_data *nfs_commit_alloc(void)
 {
 	struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, SLAB_NOFS);
 
 	if (p) {
 		memset(p, 0, sizeof(*p));
 		INIT_LIST_HEAD(&p->pages);
-		if (pagecount <= ARRAY_SIZE(p->page_array))
-			p->pagevec = p->page_array;
-		else {
-			p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS);
-			if (!p->pagevec) {
-				mempool_free(p, nfs_commit_mempool);
-				p = NULL;
-			}
-		}
 	}
 	return p;
 }
@@ -117,13 +108,15 @@ void nfs_commit_free(struct nfs_write_data *p)
 	mempool_free(p, nfs_commit_mempool);
 }
 
-struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
+struct nfs_write_data *nfs_writedata_alloc(size_t len)
 {
+	unsigned int pagecount = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, SLAB_NOFS);
 
 	if (p) {
 		memset(p, 0, sizeof(*p));
 		INIT_LIST_HEAD(&p->pages);
+		p->npages = pagecount;
 		if (pagecount <= ARRAY_SIZE(p->page_array))
 			p->pagevec = p->page_array;
 		else {
@@ -208,7 +201,7 @@ static int nfs_writepage_sync(struct nfs_open_context *ctx, struct inode *inode,
 	int		result, written = 0;
 	struct nfs_write_data *wdata;
 
-	wdata = nfs_writedata_alloc(1);
+	wdata = nfs_writedata_alloc(wsize);
 	if (!wdata)
 		return -ENOMEM;
 
@@ -999,24 +992,24 @@ static int nfs_flush_multi(struct inode *inode, struct list_head *head, int how)
 	struct nfs_page *req = nfs_list_entry(head->next);
 	struct page *page = req->wb_page;
 	struct nfs_write_data *data;
-	unsigned int wsize = NFS_SERVER(inode)->wsize;
+	size_t wsize = NFS_SERVER(inode)->wsize, nbytes;
-	unsigned int nbytes, offset;
+	unsigned int offset;
 	int requests = 0;
 	LIST_HEAD(list);
 
 	nfs_list_remove_request(req);
 
 	nbytes = req->wb_bytes;
-	for (;;) {
+	do {
-		data = nfs_writedata_alloc(1);
+		size_t len = min(nbytes, wsize);
+
+		data = nfs_writedata_alloc(len);
 		if (!data)
 			goto out_bad;
 		list_add(&data->pages, &list);
 		requests++;
-		if (nbytes <= wsize)
+		nbytes -= len;
-			break;
+	} while (nbytes != 0);
-		nbytes -= wsize;
-	}
 	atomic_set(&req->wb_complete, requests);
 
 	ClearPageError(page);
@@ -1070,7 +1063,7 @@ static int nfs_flush_one(struct inode *inode, struct list_head *head, int how)
 	struct nfs_write_data	*data;
 	unsigned int		count;
 
-	data = nfs_writedata_alloc(NFS_SERVER(inode)->wpages);
+	data = nfs_writedata_alloc(NFS_SERVER(inode)->wsize);
 	if (!data)
 		goto out_bad;
 
@@ -1378,7 +1371,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how)
 	struct nfs_write_data	*data;
 	struct nfs_page         *req;
 
-	data = nfs_commit_alloc(NFS_SERVER(inode)->wpages);
+	data = nfs_commit_alloc();
 
 	if (!data)
 		goto out_bad;

fs/super.c

@@ -49,6 +49,7 @@ DEFINE_SPINLOCK(sb_lock);
 
 /**
  *	alloc_super	-	create new superblock
+ *	@type:	filesystem type superblock should belong to
  *
  *	Allocates and initializes a new &struct super_block.  alloc_super()
  *	returns a pointer new superblock or %NULL if allocation had failed.

include/asm-i386/Kbuild

@@ -1,5 +1,5 @@
 include include/asm-generic/Kbuild.asm
 
-header-y += boot.h cpufeature.h debugreg.h ldt.h setup.h ucontext.h
+header-y += boot.h debugreg.h ldt.h setup.h ucontext.h
 
 unifdef-y += mtrr.h vm86.h

include/asm-ia64/mman.h

@@ -22,4 +22,12 @@
 #define MCL_CURRENT	1		/* lock all current mappings */
 #define MCL_FUTURE	2		/* lock all future mappings */
 
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+#define arch_mmap_check	ia64_mmap_check
+int ia64_mmap_check(unsigned long addr, unsigned long len,
+		unsigned long flags);
+#endif
+#endif
+
 #endif /* _ASM_IA64_MMAN_H */

include/asm-ia64/unistd.h

@@ -286,8 +286,7 @@
 /* 1294, 1295 reserved for pselect/ppoll */
 #define __NR_unshare			1296
 #define __NR_splice			1297
-#define __NR_set_robust_list		1298
+/* 1298, 1299 reserved for set_robust_list/get_robust_list */
-#define __NR_get_robust_list		1299
 #define __NR_sync_file_range		1300
 #define __NR_tee			1301
 #define __NR_vmsplice			1302

include/asm-sh/page.h

@@ -104,7 +104,7 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 
 /* PFN start number, because of __MEMORY_START */
 #define PFN_START		(__MEMORY_START >> PAGE_SHIFT)
-#define ARCH_PFN_OFFSET		(FPN_START)
+#define ARCH_PFN_OFFSET		(PFN_START)
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 #define pfn_valid(pfn)		(((pfn) - PFN_START) < max_mapnr)
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)

include/asm-sparc/mman.h

@@ -35,4 +35,12 @@
 
 #define MADV_FREE	0x5		/* (Solaris) contents can be freed */
 
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+#define arch_mmap_check	sparc_mmap_check
+int sparc_mmap_check(unsigned long addr, unsigned long len,
+		unsigned long flags);
+#endif
+#endif
+
 #endif /* __SPARC_MMAN_H__ */

include/asm-sparc64/mman.h

@@ -35,4 +35,12 @@
 
 #define MADV_FREE	0x5		/* (Solaris) contents can be freed */
 
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+#define arch_mmap_check	sparc64_mmap_check
+int sparc64_mmap_check(unsigned long addr, unsigned long len,
+		unsigned long flags);
+#endif
+#endif
+
 #endif /* __SPARC64_MMAN_H__ */

include/linux/atmdev.h

@@ -7,7 +7,6 @@
 #define LINUX_ATMDEV_H
 
 
-#include <linux/device.h>
 #include <linux/atmapi.h>
 #include <linux/atm.h>
 #include <linux/atmioc.h>
@@ -210,6 +209,7 @@ struct atm_cirange {
 
 #ifdef __KERNEL__
 
+#include <linux/device.h>
 #include <linux/wait.h> /* wait_queue_head_t */
 #include <linux/time.h> /* struct timeval */
 #include <linux/net.h>

include/linux/hrtimer.h

@@ -80,6 +80,7 @@ struct hrtimer_sleeper {
  * @get_softirq_time:	function to retrieve the current time from the softirq
  * @curr_timer:		the timer which is executing a callback right now
  * @softirq_time:	the time when running the hrtimer queue in the softirq
+ * @lock_key:		the lock_class_key for use with lockdep
  */
 struct hrtimer_base {
 	clockid_t		index;

include/linux/ktime.h

@@ -56,7 +56,8 @@ typedef union {
 #endif
 } ktime_t;
 
-#define KTIME_MAX			(~((u64)1 << 63))
+#define KTIME_MAX			((s64)~((u64)1 << 63))
+#define KTIME_SEC_MAX			(KTIME_MAX / NSEC_PER_SEC)
 
 /*
  * ktime_t definitions when using the 64-bit scalar representation:
@@ -73,6 +74,10 @@ typedef union {
  */
 static inline ktime_t ktime_set(const long secs, const unsigned long nsecs)
 {
+#if (BITS_PER_LONG == 64)
+	if (unlikely(secs >= KTIME_SEC_MAX))
+		return (ktime_t){ .tv64 = KTIME_MAX };
+#endif
 	return (ktime_t) { .tv64 = (s64)secs * NSEC_PER_SEC + (s64)nsecs };
 }
 

include/linux/nfs_fs.h

@@ -427,7 +427,7 @@ extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *);
 extern void nfs_writedata_release(void *);
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
-struct nfs_write_data *nfs_commit_alloc(unsigned int pagecount);
+struct nfs_write_data *nfs_commit_alloc(void);
 void nfs_commit_free(struct nfs_write_data *p);
 #endif
 
@@ -478,7 +478,7 @@ static inline int nfs_wb_page(struct inode *inode, struct page* page)
 /*
  * Allocate nfs_write_data structures
  */
-extern struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount);
+extern struct nfs_write_data *nfs_writedata_alloc(size_t len);
 
 /*
  * linux/fs/nfs/read.c
@@ -492,7 +492,7 @@ extern void nfs_readdata_release(void *data);
 /*
  * Allocate nfs_read_data structures
  */
-extern struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount);
+extern struct nfs_read_data *nfs_readdata_alloc(size_t len);
 
 /*
  * linux/fs/nfs3proc.c

include/linux/nfs_xdr.h

@@ -729,7 +729,7 @@ struct nfs_read_data {
 	struct list_head	pages;	/* Coalesced read requests */
 	struct nfs_page		*req;	/* multi ops per nfs_page */
 	struct page		**pagevec;
-	unsigned int		npages;	/* active pages in pagevec */
+	unsigned int		npages;	/* Max length of pagevec */
 	struct nfs_readargs args;
 	struct nfs_readres  res;
 #ifdef CONFIG_NFS_V4
@@ -748,7 +748,7 @@ struct nfs_write_data {
 	struct list_head	pages;		/* Coalesced requests we wish to flush */
 	struct nfs_page		*req;		/* multi ops per nfs_page */
 	struct page		**pagevec;
-	unsigned int		npages;		/* active pages in pagevec */
+	unsigned int		npages;		/* Max length of pagevec */
 	struct nfs_writeargs	args;		/* argument struct */
 	struct nfs_writeres	res;		/* result struct */
 #ifdef CONFIG_NFS_V4

include/linux/pci_ids.h

@@ -648,6 +648,8 @@
 #define PCI_DEVICE_ID_SI_962		0x0962
 #define PCI_DEVICE_ID_SI_963		0x0963
 #define PCI_DEVICE_ID_SI_965		0x0965
+#define PCI_DEVICE_ID_SI_966		0x0966
+#define PCI_DEVICE_ID_SI_968		0x0968
 #define PCI_DEVICE_ID_SI_5511		0x5511
 #define PCI_DEVICE_ID_SI_5513		0x5513
 #define PCI_DEVICE_ID_SI_5517		0x5517

kernel/futex.c

@@ -1120,9 +1120,10 @@ static int futex_wait(u32 __user *uaddr, u32 val, unsigned long time)
  * if there are waiters then it will block, it does PI, etc. (Due to
  * races the kernel might see a 0 value of the futex too.)
  */
-static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
+static int futex_lock_pi(u32 __user *uaddr, int detect, unsigned long sec,
-			    struct hrtimer_sleeper *to)
+			 long nsec, int trylock)
 {
+	struct hrtimer_sleeper timeout, *to = NULL;
 	struct task_struct *curr = current;
 	struct futex_hash_bucket *hb;
 	u32 uval, newval, curval;
@@ -1132,6 +1133,13 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
 	if (refill_pi_state_cache())
 		return -ENOMEM;
 
+	if (sec != MAX_SCHEDULE_TIMEOUT) {
+		to = &timeout;
+		hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_ABS);
+		hrtimer_init_sleeper(to, current);
+		to->timer.expires = ktime_set(sec, nsec);
+	}
+
 	q.pi_state = NULL;
  retry:
 	down_read(&curr->mm->mmap_sem);
@@ -1307,7 +1315,7 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
 	if (!detect && ret == -EDEADLK && 0)
 		force_sig(SIGKILL, current);
 
-	return ret;
+	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
  out_unlock_release_sem:
 	queue_unlock(&q, hb);
@@ -1341,76 +1349,6 @@ static int do_futex_lock_pi(u32 __user *uaddr, int detect, int trylock,
 	return ret;
 }
 
-/*
- * Restart handler
- */
-static long futex_lock_pi_restart(struct restart_block *restart)
-{
-	struct hrtimer_sleeper timeout, *to = NULL;
-	int ret;
-
-	restart->fn = do_no_restart_syscall;
-
-	if (restart->arg2 || restart->arg3) {
-		to = &timeout;
-		hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_ABS);
-		hrtimer_init_sleeper(to, current);
-		to->timer.expires.tv64 = ((u64)restart->arg1 << 32) |
-			(u64) restart->arg0;
-	}
-
-	pr_debug("lock_pi restart: %p, %d (%d)\n",
-		 (u32 __user *)restart->arg0, current->pid);
-
-	ret = do_futex_lock_pi((u32 __user *)restart->arg0, restart->arg1,
-			       0, to);
-
-	if (ret != -EINTR)
-		return ret;
-
-	restart->fn = futex_lock_pi_restart;
-
-	/* The other values are filled in */
-	return -ERESTART_RESTARTBLOCK;
-}
-
-/*
- * Called from the syscall entry below.
- */
-static int futex_lock_pi(u32 __user *uaddr, int detect, unsigned long sec,
-			 long nsec, int trylock)
-{
-	struct hrtimer_sleeper timeout, *to = NULL;
-	struct restart_block *restart;
-	int ret;
-
-	if (sec != MAX_SCHEDULE_TIMEOUT) {
-		to = &timeout;
-		hrtimer_init(&to->timer, CLOCK_REALTIME, HRTIMER_ABS);
-		hrtimer_init_sleeper(to, current);
-		to->timer.expires = ktime_set(sec, nsec);
-	}
-
-	ret = do_futex_lock_pi(uaddr, detect, trylock, to);
-
-	if (ret != -EINTR)
-		return ret;
-
-	pr_debug("lock_pi interrupted: %p, %d (%d)\n", uaddr, current->pid);
-
-	restart = &current_thread_info()->restart_block;
-	restart->fn = futex_lock_pi_restart;
-	restart->arg0 = (unsigned long) uaddr;
-	restart->arg1 = detect;
-	if (to) {
-		restart->arg2 = to->timer.expires.tv64 & 0xFFFFFFFF;
-		restart->arg3 = to->timer.expires.tv64 >> 32;
-	} else
-		restart->arg2 = restart->arg3 = 0;
-
-	return -ERESTART_RESTARTBLOCK;
-}
-
 /*
  * Userspace attempted a TID -> 0 atomic transition, and failed.
  * This is the in-kernel slowpath: we look up the PI state (if any),

kernel/panic.c

@@ -173,7 +173,7 @@ const char *print_tainted(void)
 
 void add_taint(unsigned flag)
 {
-	debug_locks_off(); /* can't trust the integrity of the kernel anymore */
+	debug_locks = 0; /* can't trust the integrity of the kernel anymore */
 	tainted |= flag;
 }
 EXPORT_SYMBOL(add_taint);

kernel/power/Kconfig

@@ -56,7 +56,7 @@ config PM_TRACE
 
 config SOFTWARE_SUSPEND
 	bool "Software Suspend"
-	depends on PM && SWAP && (X86 && (!SMP || SUSPEND_SMP)) || ((FRV || PPC32) && !SMP)
+	depends on PM && SWAP && ((X86 && (!SMP || SUSPEND_SMP) && !X86_PAE) || ((FRV || PPC32) && !SMP))
 	---help---
 	  Enable the possibility of suspending the machine.
 	  It doesn't need ACPI or APM.
@@ -78,6 +78,10 @@ config SOFTWARE_SUSPEND
 
 	  For more information take a look at <file:Documentation/power/swsusp.txt>.
 
+	  (For now, swsusp is incompatible with PAE aka HIGHMEM_64G on i386.
+	  we need identity mapping for resume to work, and that is trivial
+	  to get with 4MB pages, but less than trivial on PAE).
+
 config PM_STD_PARTITION
 	string "Default resume partition"
 	depends on SOFTWARE_SUSPEND

kernel/spinlock.c

@@ -72,7 +72,7 @@ EXPORT_SYMBOL(_write_trylock);
  * not re-enabled during lock-acquire (which the preempt-spin-ops do):
  */
 #if !defined(CONFIG_PREEMPT) || !defined(CONFIG_SMP) || \
-	defined(CONFIG_PROVE_LOCKING)
+	defined(CONFIG_DEBUG_LOCK_ALLOC)
 
 void __lockfunc _read_lock(rwlock_t *lock)
 {

mm/mmap.c

@@ -30,6 +30,10 @@
 #include <asm/cacheflush.h>
 #include <asm/tlb.h>
 
+#ifndef arch_mmap_check
+#define arch_mmap_check(addr, len, flags)	(0)
+#endif
+
 static void unmap_region(struct mm_struct *mm,
 		struct vm_area_struct *vma, struct vm_area_struct *prev,
 		unsigned long start, unsigned long end);
@@ -913,6 +917,10 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 	if (!len)
 		return -EINVAL;
 
+	error = arch_mmap_check(addr, len, flags);
+	if (error)
+		return error;
+
 	/* Careful about overflows.. */
 	len = PAGE_ALIGN(len);
 	if (!len || len > TASK_SIZE)
@@ -1859,6 +1867,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
 	unsigned long flags;
 	struct rb_node ** rb_link, * rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
+	int error;
 
 	len = PAGE_ALIGN(len);
 	if (!len)
@@ -1867,6 +1876,12 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
 	if ((addr + len) > TASK_SIZE || (addr + len) < addr)
 		return -EINVAL;
 
+	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
+
+	error = arch_mmap_check(addr, len, flags);
+	if (error)
+		return error;
+
 	/*
 	 * mlock MCL_FUTURE?
 	 */
@@ -1907,8 +1922,6 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
 	if (security_vm_enough_memory(len >> PAGE_SHIFT))
 		return -ENOMEM;
 
-	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
-
 	/* Can we just expand an old private anonymous mapping? */
 	if (vma_merge(mm, prev, addr, addr + len, flags,
 					NULL, NULL, pgoff, NULL))

mm/truncate.c

@@ -68,10 +68,10 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
 		return 0;
 
 	write_lock_irq(&mapping->tree_lock);
-	if (PageDirty(page)) {
+	if (PageDirty(page))
-		write_unlock_irq(&mapping->tree_lock);
+		goto failed;
-		return 0;
+	if (page_count(page) != 2)	/* caller's ref + pagecache ref */
-	}
+		goto failed;
 
 	BUG_ON(PagePrivate(page));
 	__remove_from_page_cache(page);
@@ -79,6 +79,9 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
 	ClearPageUptodate(page);
 	page_cache_release(page);	/* pagecache ref */
 	return 1;
+failed:
+	write_unlock_irq(&mapping->tree_lock);
+	return 0;
 }
 
 /**