Merge commit 'v2.6.37' into for-2.6.38-incoming

I made a slight mess of Documentation/filesystems/Locking; resolve
conflicts with upstream before fixing it up.

Documentation/accounting/getdelays.c

@@ -516,6 +516,7 @@ int main(int argc, char *argv[])
 			default:
 				fprintf(stderr, "Unknown nla_type %d\n",
 					na->nla_type);
+			case TASKSTATS_TYPE_NULL:
 				break;
 			}
 			na = (struct nlattr *) (GENLMSG_DATA(&msg) + len);

Documentation/filesystems/Locking

@@ -18,7 +18,6 @@ prototypes:
 	char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
 
 locking rules:
-	none have BKL
 		dcache_lock	rename_lock	->d_lock	may block
 d_revalidate:	no		no		no		yes
 d_hash		no		no		no		yes
@@ -42,18 +41,23 @@ ata *);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
 	int (*readlink) (struct dentry *, char __user *,int);
-	int (*follow_link) (struct dentry *, struct nameidata *);
+	void * (*follow_link) (struct dentry *, struct nameidata *);
+	void (*put_link) (struct dentry *, struct nameidata *, void *);
 	void (*truncate) (struct inode *);
 	int (*permission) (struct inode *, int, struct nameidata *);
+	int (*check_acl)(struct inode *, int);
 	int (*setattr) (struct dentry *, struct iattr *);
 	int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *);
 	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
 	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*removexattr) (struct dentry *, const char *);
+	void (*truncate_range)(struct inode *, loff_t, loff_t);
+	long (*fallocate)(struct inode *inode, int mode, loff_t offset, loff_t len);
+	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
 
 locking rules:
-	all may block, none have BKL
+	all may block
 		i_mutex(inode)
 lookup:		yes
 create:		yes
@@ -66,19 +70,24 @@ rmdir:		yes (both)	(see below)
 rename:		yes (all)	(see below)
 readlink:	no
 follow_link:	no
+put_link:	no
 truncate:	yes		(see below)
 setattr:	yes
 permission:	no
+check_acl:	no
 getattr:	no
 setxattr:	yes
 getxattr:	no
 listxattr:	no
 removexattr:	yes
+truncate_range:	yes
+fallocate:	no
+fiemap:		no
 	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
 	cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
 	->truncate() is never called directly - it's a callback, not a
-method. It's called by vmtruncate() - library function normally used by
+method. It's called by vmtruncate() - deprecated library function used by
 ->setattr(). Locking information above applies to that call (i.e. is
 inherited from ->setattr() - vmtruncate() is used when ATTR_SIZE had been
 passed).
@@ -91,7 +100,7 @@ prototypes:
 	struct inode *(*alloc_inode)(struct super_block *sb);
 	void (*destroy_inode)(struct inode *);
 	void (*dirty_inode) (struct inode *);
-	int (*write_inode) (struct inode *, int);
+	int (*write_inode) (struct inode *, struct writeback_control *wbc);
 	int (*drop_inode) (struct inode *);
 	void (*evict_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
@@ -105,10 +114,10 @@ prototypes:
 	int (*show_options)(struct seq_file *, struct vfsmount *);
 	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
+	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
 
 locking rules:
 	All may block [not true, see below]
-	None have BKL
 			s_umount
 alloc_inode:
 destroy_inode:
@@ -127,6 +136,7 @@ umount_begin:		no
 show_options:		no		(namespace_sem)
 quota_read:		no		(see below)
 quota_write:		no		(see below)
+bdev_try_to_free_page:	no		(see below)
 
 ->statfs() has s_umount (shared) when called by ustat(2) (native or
 compat), but that's an accident of bad API; s_umount is used to pin
@@ -139,19 +149,25 @@ be the only ones operating on the quota file by the quota code (via
 dqio_sem) (unless an admin really wants to screw up something and
 writes to quota files with quotas on). For other details about locking
 see also dquot_operations section.
+->bdev_try_to_free_page is called from the ->releasepage handler of
+the block device inode.  See there for more details.
 
 --------------------------- file_system_type ---------------------------
 prototypes:
 	int (*get_sb) (struct file_system_type *, int,
 		       const char *, void *, struct vfsmount *);
+	struct dentry *(*mount) (struct file_system_type *, int,
+		       const char *, void *);
 	void (*kill_sb) (struct super_block *);
 locking rules:
-		may block	BKL
-get_sb		yes		no
-kill_sb		yes		no
+		may block
+get_sb		yes
+mount		yes
+kill_sb		yes
 
 ->get_sb() returns error or 0 with locked superblock attached to the vfsmount
 (exclusive on ->s_umount).
+->mount() returns ERR_PTR or the root dentry.
 ->kill_sb() takes a write-locked superblock, does all shutdown work on it,
 unlocks and drops the reference.
 
@@ -176,27 +192,35 @@ prototypes:
 	void (*freepage)(struct page *);
 	int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
 			loff_t offset, unsigned long nr_segs);
-	int (*launder_page) (struct page *);
+	int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **,
+				unsigned long *);
+	int (*migratepage)(struct address_space *, struct page *, struct page *);
+	int (*launder_page)(struct page *);
+	int (*is_partially_uptodate)(struct page *, read_descriptor_t *, unsigned long);
+	int (*error_remove_page)(struct address_space *, struct page *);
 
 locking rules:
 	All except set_page_dirty and freepage may block
 
-			BKL	PageLocked(page)	i_mutex
-writepage:		no	yes, unlocks (see below)
-readpage:		no	yes, unlocks
-sync_page:		no	maybe
-writepages:		no
-set_page_dirty		no	no
-readpages:		no
-write_begin:		no	locks the page		yes
-write_end:		no	yes, unlocks		yes
-perform_write:		no	n/a			yes
-bmap:			no
-invalidatepage:		no	yes
-releasepage:		no	yes
-freepage:		no	yes
-direct_IO:		no
-launder_page:		no	yes
+			PageLocked(page)	i_mutex
+writepage:		yes, unlocks (see below)
+readpage:		yes, unlocks
+sync_page:		maybe
+writepages:
+set_page_dirty		no
+readpages:
+write_begin:		locks the page		yes
+write_end:		yes, unlocks		yes
+bmap:
+invalidatepage:		yes
+releasepage:		yes
+freepage:		yes
+direct_IO:
+get_xip_mem:					maybe
+migratepage:		yes (both)
+launder_page:		yes
+is_partially_uptodate:	yes
+error_remove_page:	yes
 
 	->write_begin(), ->write_end(), ->sync_page() and ->readpage()
 may be called from the request handler (/dev/loop).
@@ -276,9 +300,8 @@ under spinlock (it cannot block) and is sometimes called with the page
 not locked.
 
 	->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
-filesystems and by the swapper. The latter will eventually go away. All
-instances do not actually need the BKL. Please, keep it that way and don't
-breed new callers.
+filesystems and by the swapper. The latter will eventually go away.  Please,
+keep it that way and don't breed new callers.
 
 	->invalidatepage() is called when the filesystem must attempt to drop
 some or all of the buffers from the page when it is being truncated.  It
@@ -299,47 +322,37 @@ cleaned, or an error value if not. Note that in order to prevent the page
 getting mapped back in and redirtied, it needs to be kept locked
 across the entire operation.
 
-	Note: currently almost all instances of address_space methods are
-using BKL for internal serialization and that's one of the worst sources
-of contention. Normally they are calling library functions (in fs/buffer.c)
-and pass foo_get_block() as a callback (on local block-based filesystems,
-indeed). BKL is not needed for library stuff and is usually taken by
-foo_get_block(). It's an overkill, since block bitmaps can be protected by
-internal fs locking and real critical areas are much smaller than the areas
-filesystems protect now.
-
 ----------------------- file_lock_operations ------------------------------
 prototypes:
-	void (*fl_insert)(struct file_lock *);	/* lock insertion callback */
-	void (*fl_remove)(struct file_lock *);	/* lock removal callback */
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
 	void (*fl_release_private)(struct file_lock *);
 
 
 locking rules:
-			BKL	may block
-fl_insert:		yes	no
-fl_remove:		yes	no
-fl_copy_lock:		yes	no
-fl_release_private:	yes	yes
+			file_lock_lock	may block
+fl_copy_lock:		yes		no
+fl_release_private:	maybe		no
 
 ----------------------- lock_manager_operations ---------------------------
 prototypes:
 	int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
 	void (*fl_notify)(struct file_lock *);  /* unblock callback */
+	int (*fl_grant)(struct file_lock *, struct file_lock *, int);
 	void (*fl_release_private)(struct file_lock *);
 	void (*fl_break)(struct file_lock *); /* break_lease callback */
+	int (*fl_mylease)(struct file_lock *, struct file_lock *);
+	int (*fl_change)(struct file_lock **, int);
 
 locking rules:
-			BKL	may block
-fl_compare_owner:	yes	no
-fl_notify:		yes	no
-fl_release_private:	yes	yes
-fl_break:		yes	no
-
-	Currently only NFSD and NLM provide instances of this class. None of the
-them block. If you have out-of-tree instances - please, show up. Locking
-in that area will change.
+			file_lock_lock	may block
+fl_compare_owner:	yes		no
+fl_notify:		yes		no
+fl_grant:		no		no
+fl_release_private:	maybe		no
+fl_break:		yes		no
+fl_mylease:		yes		no
+fl_change		yes		no
+
 --------------------------- buffer_head -----------------------------------
 prototypes:
 	void (*b_end_io)(struct buffer_head *bh, int uptodate);
@@ -364,17 +377,17 @@ prototypes:
 	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 
 locking rules:
-			BKL	bd_mutex
-open:			no	yes
-release:		no	yes
-ioctl:			no	no
-compat_ioctl:		no	no
-direct_access:		no	no
-media_changed:		no	no
-unlock_native_capacity:	no	no
-revalidate_disk:	no	no
-getgeo:			no	no
-swap_slot_free_notify:	no	no	(see below)
+			bd_mutex
+open:			yes
+release:		yes
+ioctl:			no
+compat_ioctl:		no
+direct_access:		no
+media_changed:		no
+unlock_native_capacity:	no
+revalidate_disk:	no
+getgeo:			no
+swap_slot_free_notify:	no	(see below)
 
 media_changed, unlock_native_capacity and revalidate_disk are called only from
 check_disk_change().
@@ -413,34 +426,21 @@ prototypes:
 	unsigned long (*get_unmapped_area)(struct file *, unsigned long,
 			unsigned long, unsigned long, unsigned long);
 	int (*check_flags)(int);
+	int (*flock) (struct file *, int, struct file_lock *);
+	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *,
+			size_t, unsigned int);
+	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
+			size_t, unsigned int);
+	int (*setlease)(struct file *, long, struct file_lock **);
 };
 
 locking rules:
-	All may block.
-			BKL
-llseek:			no	(see below)
-read:			no
-aio_read:		no
-write:			no
-aio_write:		no
-readdir: 		no
-poll:			no
-unlocked_ioctl:		no
-compat_ioctl:		no
-mmap:			no
-open:			no
-flush:			no
-release:		no
-fsync:			no	(see below)
-aio_fsync:		no
-fasync:			no
-lock:			yes
-readv:			no
-writev:			no
-sendfile:		no
-sendpage:		no
-get_unmapped_area:	no
-check_flags:		no
+	All may block except for ->setlease.
+	No VFS locks held on entry except for ->fsync and ->setlease.
+
+->fsync() has i_mutex on inode.
+
+->setlease has the file_list_lock held and must not sleep.
 
 ->llseek() locking has moved from llseek to the individual llseek
 implementations.  If your fs is not using generic_file_llseek, you
@@ -450,17 +450,10 @@ mutex or just to use i_size_read() instead.
 Note: this does not protect the file->f_pos against concurrent modifications
 since this is something the userspace has to take care about.
 
-Note: ext2_release() was *the* source of contention on fs-intensive
-loads and dropping BKL on ->release() helps to get rid of that (we still
-grab BKL for cases when we close a file that had been opened r/w, but that
-can and should be done using the internal locking with smaller critical areas).
-Current worst offender is ext2_get_block()...
-
-->fasync() is called without BKL protection, and is responsible for
-maintaining the FASYNC bit in filp->f_flags.  Most instances call
-fasync_helper(), which does that maintenance, so it's not normally
-something one needs to worry about.  Return values > 0 will be mapped to
-zero in the VFS layer.
+->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
+Most instances call fasync_helper(), which does that maintenance, so it's
+not normally something one needs to worry about.  Return values > 0 will be
+mapped to zero in the VFS layer.
 
 ->readdir() and ->ioctl() on directories must be changed. Ideally we would
 move ->readdir() to inode_operations and use a separate method for directory
@@ -471,8 +464,6 @@ components. And there are other reasons why the current interface is a mess...
 ->read on directories probably must go away - we should just enforce -EISDIR
 in sys_read() and friends.
 
-->fsync() has i_mutex on inode.
-
 --------------------------- dquot_operations -------------------------------
 prototypes:
 	int (*write_dquot) (struct dquot *);
@@ -507,12 +498,12 @@ prototypes:
 	int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
 
 locking rules:
-		BKL	mmap_sem	PageLocked(page)
-open:		no	yes
-close:		no	yes
-fault:		no	yes		can return with page locked
-page_mkwrite:	no	yes		can return with page locked
-access:		no	yes
+		mmap_sem	PageLocked(page)
+open:		yes
+close:		yes
+fault:		yes		can return with page locked
+page_mkwrite:	yes		can return with page locked
+access:		yes
 
 	->fault() is called when a previously not present pte is about
 to be faulted in. The filesystem must find and return the page associated
@@ -539,6 +530,3 @@ VM_IO | VM_PFNMAP VMAs.
 
 (if you break something or notice that it is broken and do not fix it yourself
 - at least put it here)
-
-ipc/shm.c::shm_delete() - may need BKL.
-->read() and ->write() in many drivers are (probably) missing BKL.

Documentation/kernel-parameters.txt

@@ -1759,7 +1759,7 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nousb		[USB] Disable the USB subsystem
 
-	nowatchdog	[KNL] Disable the lockup detector.
+	nowatchdog	[KNL] Disable the lockup detector (NMI watchdog).
 
 	nowb		[ARM]
 
@@ -2175,11 +2175,6 @@ and is between 256 and 4096 characters. It is defined in the file
 	reset_devices	[KNL] Force drivers to reset the underlying device
 			during initialization.
 
-	resource_alloc_from_bottom
-			Allocate new resources from the beginning of available
-			space, not the end.  If you need to use this, please
-			report a bug.
-
 	resume=		[SWSUSP]
 			Specify the partition device for software suspend
 

Documentation/power/runtime_pm.txt

@@ -379,8 +379,8 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       zero)
 
   bool pm_runtime_suspended(struct device *dev);
-    - return true if the device's runtime PM status is 'suspended', or false
-      otherwise
+    - return true if the device's runtime PM status is 'suspended' and its
+      'power.disable_depth' field is equal to zero, or false otherwise
 
   void pm_runtime_allow(struct device *dev);
     - set the power.runtime_auto flag for the device and decrease its usage

Documentation/scsi/scsi_mid_low_api.txt

@@ -1044,9 +1044,9 @@ Details:
 
 
 /**
- *      queuecommand - queue scsi command, invoke 'done' on completion
+ *      queuecommand - queue scsi command, invoke scp->scsi_done on completion
+ *      @shost: pointer to the scsi host object
  *      @scp: pointer to scsi command object
- *      @done: function pointer to be invoked on completion
  *
  *      Returns 0 on success.
  *
@@ -1074,42 +1074,45 @@ Details:
  *
  *      Other types of errors that are detected immediately may be
  *      flagged by setting scp->result to an appropriate value,
- *      invoking the 'done' callback, and then returning 0 from this
- *      function. If the command is not performed immediately (and the
- *      LLD is starting (or will start) the given command) then this
- *      function should place 0 in scp->result and return 0.
+ *      invoking the scp->scsi_done callback, and then returning 0
+ *      from this function. If the command is not performed
+ *      immediately (and the LLD is starting (or will start) the given
+ *      command) then this function should place 0 in scp->result and
+ *      return 0.
  *
  *      Command ownership.  If the driver returns zero, it owns the
- *      command and must take responsibility for ensuring the 'done'
- *      callback is executed.  Note: the driver may call done before
- *      returning zero, but after it has called done, it may not
- *      return any value other than zero.  If the driver makes a
- *      non-zero return, it must not execute the command's done
- *      callback at any time.
- *
- *      Locks: struct Scsi_Host::host_lock held on entry (with "irqsave")
- *             and is expected to be held on return.
+ *      command and must take responsibility for ensuring the
+ *      scp->scsi_done callback is executed.  Note: the driver may
+ *      call scp->scsi_done before returning zero, but after it has
+ *      called scp->scsi_done, it may not return any value other than
+ *      zero.  If the driver makes a non-zero return, it must not
+ *      execute the command's scsi_done callback at any time.
+ *
+ *      Locks: up to and including 2.6.36, struct Scsi_Host::host_lock
+ *             held on entry (with "irqsave") and is expected to be
+ *             held on return. From 2.6.37 onwards, queuecommand is
+ *             called without any locks held.
  *
  *      Calling context: in interrupt (soft irq) or process context
  *
- *      Notes: This function should be relatively fast. Normally it will
- *      not wait for IO to complete. Hence the 'done' callback is invoked 
- *      (often directly from an interrupt service routine) some time after
- *      this function has returned. In some cases (e.g. pseudo adapter 
- *      drivers that manufacture the response to a SCSI INQUIRY)
- *      the 'done' callback may be invoked before this function returns.
- *      If the 'done' callback is not invoked within a certain period
- *      the SCSI mid level will commence error processing.
- *      If a status of CHECK CONDITION is placed in "result" when the
- *      'done' callback is invoked, then the LLD driver should 
- *      perform autosense and fill in the struct scsi_cmnd::sense_buffer
+ *      Notes: This function should be relatively fast. Normally it
+ *      will not wait for IO to complete. Hence the scp->scsi_done
+ *      callback is invoked (often directly from an interrupt service
+ *      routine) some time after this function has returned. In some
+ *      cases (e.g. pseudo adapter drivers that manufacture the
+ *      response to a SCSI INQUIRY) the scp->scsi_done callback may be
+ *      invoked before this function returns.  If the scp->scsi_done
+ *      callback is not invoked within a certain period the SCSI mid
+ *      level will commence error processing.  If a status of CHECK
+ *      CONDITION is placed in "result" when the scp->scsi_done
+ *      callback is invoked, then the LLD driver should perform
+ *      autosense and fill in the struct scsi_cmnd::sense_buffer
  *      array. The scsi_cmnd::sense_buffer array is zeroed prior to
  *      the mid level queuing a command to an LLD.
  *
  *      Defined in: LLD
  **/
-    int queuecommand(struct scsi_cmnd * scp, 
-                     void (*done)(struct scsi_cmnd *))
+    int queuecommand(struct Scsi_Host *shost, struct scsi_cmnd * scp)
 
 
 /**

Documentation/trace/postprocess/trace-vmscan-postprocess.pl

@@ -373,9 +373,18 @@ EVENT_PROCESS:
 				print "         $regex_lru_isolate/o\n";
 				next;
 			}
+			my $isolate_mode = $1;
 			my $nr_scanned = $4;
 			my $nr_contig_dirty = $7;
-			$perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;
+
+			# To closer match vmstat scanning statistics, only count isolate_both
+			# and isolate_inactive as scanning. isolate_active is rotation
+			# isolate_inactive == 0
+			# isolate_active   == 1
+			# isolate_both     == 2
+			if ($isolate_mode != 1) {
+				$perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;
+			}
 			$perprocesspid{$process_pid}->{HIGH_NR_CONTIG_DIRTY} += $nr_contig_dirty;
 		} elsif ($tracepoint eq "mm_vmscan_lru_shrink_inactive") {
 			$details = $5;

MAINTAINERS

@@ -405,7 +405,7 @@ S:	Supported
 F:	drivers/usb/gadget/amd5536udc.*
 
 AMD GEODE PROCESSOR/CHIPSET SUPPORT
-P:	Jordan Crouse
+P:	Andres Salomon <dilinger@queued.net>
 L:	linux-geode@lists.infradead.org (moderated for non-subscribers)
 W:	http://www.amd.com/us-en/ConnectivitySolutions/TechnicalResources/0,,50_2334_2452_11363,00.html
 S:	Supported
@@ -792,11 +792,14 @@ S:	Maintained
 
 ARM/NOMADIK ARCHITECTURE
 M:	Alessandro Rubini <rubini@unipv.it>
+M:	Linus Walleij <linus.walleij@stericsson.com>
 M:	STEricsson <STEricsson_nomadik_linux@list.st.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-nomadik/
 F:	arch/arm/plat-nomadik/
+F:	drivers/i2c/busses/i2c-nomadik.c
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-stericsson.git
 
 ARM/OPENMOKO NEO FREERUNNER (GTA02) MACHINE SUPPORT
 M:	Nelson Castillo <arhuaco@freaks-unidos.net>
@@ -998,12 +1001,24 @@ F:	drivers/i2c/busses/i2c-stu300.c
 F:	drivers/rtc/rtc-coh901331.c
 F:	drivers/watchdog/coh901327_wdt.c
 F:	drivers/dma/coh901318*
+F:	drivers/mfd/ab3100*
+F:	drivers/rtc/rtc-ab3100.c
+F:	drivers/rtc/rtc-coh901331.c
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-stericsson.git
 
-ARM/U8500 ARM ARCHITECTURE
+ARM/Ux500 ARM ARCHITECTURE
 M:	Srinidhi Kasagar <srinidhi.kasagar@stericsson.com>
+M:	Linus Walleij <linus.walleij@stericsson.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-ux500/
+F:	drivers/dma/ste_dma40*
+F:	drivers/mfd/ab3550*
+F:	drivers/mfd/abx500*
+F:	drivers/mfd/ab8500*
+F:	drivers/mfd/stmpe*
+F:	drivers/rtc/rtc-ab8500.c
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-stericsson.git
 
 ARM/VFP SUPPORT
 M:	Russell King <linux@arm.linux.org.uk>
@@ -4590,7 +4605,7 @@ F:	drivers/pcmcia/
 F:	include/pcmcia/
 
 PCNET32 NETWORK DRIVER
-M:	Don Fry <pcnet32@verizon.net>
+M:	Don Fry <pcnet32@frontier.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/pcnet32.c

Makefile

 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 37
-EXTRAVERSION = -rc6
+EXTRAVERSION =
 NAME = Flesh-Eating Bats with Fangs
 
 # *DOCUMENTATION*

arch/arm/common/it8152.c

@@ -352,3 +352,4 @@ struct pci_bus * __init it8152_pci_scan_bus(int nr, struct pci_sys_data *sys)
 	return pci_scan_bus(nr, &it8152_ops, sys);
 }
 
+EXPORT_SYMBOL(dma_set_coherent_mask);

arch/arm/include/asm/hardware/it8152.h

@@ -76,6 +76,7 @@ extern unsigned long it8152_base_address;
   IT8152_PD_IRQ(0)  Audio controller (ACR)
  */
 #define IT8152_IRQ(x)   (IRQ_BOARD_START + (x))
+#define IT8152_LAST_IRQ	(IRQ_BOARD_START + 40)
 
 /* IRQ-sources in 3 groups - local devices, LPC (serial), and external PCI */
 #define IT8152_LD_IRQ_COUNT     9

arch/arm/include/asm/highmem.h

@@ -25,9 +25,6 @@ extern void *kmap_high(struct page *page);
 extern void *kmap_high_get(struct page *page);
 extern void kunmap_high(struct page *page);
 
-extern void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte);
-extern void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte);
-
 /*
  * The following functions are already defined by <linux/highmem.h>
  * when CONFIG_HIGHMEM is not set.

arch/arm/include/asm/sizes.h

@@ -13,9 +13,6 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-/* DO NOT EDIT!! - this file automatically generated
- *                 from .s file by awk -f s2h.awk
- */
 /*  Size definitions
  *  Copyright (C) ARM Limited 1998. All rights reserved.
  */
@@ -25,6 +22,9 @@
 
 /* handy sizes */
 #define SZ_16				0x00000010
+#define SZ_32				0x00000020
+#define SZ_64				0x00000040
+#define SZ_128				0x00000080
 #define SZ_256				0x00000100
 #define SZ_512				0x00000200
 

arch/arm/include/asm/system.h

@@ -150,6 +150,7 @@ extern unsigned int user_debug;
 #define rmb()		dmb()
 #define wmb()		mb()
 #else
+#include <asm/memory.h>
 #define mb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
 #define rmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
 #define wmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)

arch/arm/kernel/entry-common.S

@@ -29,6 +29,9 @@ ret_fast_syscall:
 	ldr	r1, [tsk, #TI_FLAGS]
 	tst	r1, #_TIF_WORK_MASK
 	bne	fast_work_pending
+#if defined(CONFIG_IRQSOFF_TRACER)
+	asm_trace_hardirqs_on
+#endif
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
@@ -65,6 +68,9 @@ ret_slow_syscall:
 	tst	r1, #_TIF_WORK_MASK
 	bne	work_pending
 no_work_pending:
+#if defined(CONFIG_IRQSOFF_TRACER)
+	asm_trace_hardirqs_on
+#endif
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
 

arch/arm/kernel/smp.c

@@ -310,7 +310,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	 * All kernel threads share the same mm context; grab a
 	 * reference and switch to it.
 	 */
-	atomic_inc(&mm->mm_users);
 	atomic_inc(&mm->mm_count);
 	current->active_mm = mm;
 	cpumask_set_cpu(cpu, mm_cpumask(mm));

arch/arm/mach-at91/Makefile

@@ -65,7 +65,7 @@ obj-$(CONFIG_MACH_AT91SAM9G20EK) += board-sam9g20ek.o
 obj-$(CONFIG_MACH_CPU9G20)	+= board-cpu9krea.o
 obj-$(CONFIG_MACH_STAMP9G20)	+= board-stamp9g20.o
 obj-$(CONFIG_MACH_PORTUXG20)	+= board-stamp9g20.o
-obj-$(CONFIG_MACH_PCONTROL_G20)	+= board-pcontrol-g20.o
+obj-$(CONFIG_MACH_PCONTROL_G20)	+= board-pcontrol-g20.o board-stamp9g20.o
 
 # AT91SAM9260/AT91SAM9G20 board-specific support
 obj-$(CONFIG_MACH_SNAPPER_9260)	+= board-snapper9260.o

arch/arm/mach-at91/board-pcontrol-g20.c

@@ -31,6 +31,7 @@
 
 #include <mach/board.h>
 #include <mach/at91sam9_smc.h>
+#include <mach/stamp9g20.h>
 
 #include "sam9_smc.h"
 #include "generic.h"
@@ -38,11 +39,7 @@
 
 static void __init pcontrol_g20_map_io(void)
 {
-	/* Initialize processor: 18.432 MHz crystal */
-	at91sam9260_initialize(18432000);
-
-	/* DGBU on ttyS0. (Rx, Tx) only TTL -> JTAG connector X7 17,19 ) */
-	at91_register_uart(0, 0, 0);
+	stamp9g20_map_io();
 
 	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS) piggyback  A2 */
 	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS
@@ -54,9 +51,6 @@ static void __init pcontrol_g20_map_io(void)
 
 	/* USART2 on ttyS3. (Rx, Tx)  9bit-Bus  Multidrop-mode  X4 */
 	at91_register_uart(AT91SAM9260_ID_US4, 3, 0);
-
-	/* set serial console to ttyS0 (ie, DBGU) */
-	at91_set_serial_console(0);
 }
 
 
@@ -66,38 +60,6 @@ static void __init init_irq(void)
 }
 
 
-/*
- * NAND flash 512MiB 1,8V 8-bit, sector size 128 KiB
- */
-static struct atmel_nand_data __initdata nand_data = {
-	.ale		= 21,
-	.cle		= 22,
-	.rdy_pin	= AT91_PIN_PC13,
-	.enable_pin	= AT91_PIN_PC14,
-};
-
-/*
- * Bus timings; unit = 7.57ns
- */
-static struct sam9_smc_config __initdata nand_smc_config = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 2,
-	.ncs_write_setup	= 0,
-	.nwe_setup		= 2,
-
-	.ncs_read_pulse		= 4,
-	.nrd_pulse		= 4,
-	.ncs_write_pulse	= 4,
-	.nwe_pulse		= 4,
-
-	.read_cycle		= 7,
-	.write_cycle		= 7,
-
-	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE
-			| AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_DBW_8,
-	.tdf_cycles		= 3,
-};
-
 static struct sam9_smc_config __initdata pcontrol_smc_config[2] = { {
 	.ncs_read_setup		= 16,
 	.nrd_setup		= 18,
@@ -138,14 +100,6 @@ static struct sam9_smc_config __initdata pcontrol_smc_config[2] = { {
 	.tdf_cycles		= 1,
 } };
 
-static void __init add_device_nand(void)
-{
-	/* configure chip-select 3 (NAND) */
-	sam9_smc_configure(3, &nand_smc_config);
-	at91_add_device_nand(&nand_data);
-}
-
-
 static void __init add_device_pcontrol(void)
 {
 	/* configure chip-select 4 (IO compatible to 8051  X4 ) */
@@ -155,23 +109,6 @@ static void __init add_device_pcontrol(void)
 }
 
 
-/*
- * MCI (SD/MMC)
- * det_pin, wp_pin and vcc_pin are not connected
- */
-#if defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_ATMELMCI_MODULE)
-static struct mci_platform_data __initdata mmc_data = {
-	.slot[0] = {
-		.bus_width	= 4,
-	},
-};
-#else
-static struct at91_mmc_data __initdata mmc_data = {
-	.wire4		= 1,
-};
-#endif
-
-
 /*
  * USB Host port
  */
@@ -265,42 +202,13 @@ static struct spi_board_info pcontrol_g20_spi_devices[] = {
 };
 
 
-/*
- * Dallas 1-Wire  DS2431
- */
-static struct w1_gpio_platform_data w1_gpio_pdata = {
-	.pin		= AT91_PIN_PA29,
-	.is_open_drain	= 1,
-};
-
-static struct platform_device w1_device = {
-	.name			= "w1-gpio",
-	.id			= -1,
-	.dev.platform_data	= &w1_gpio_pdata,
-};
-
-static void add_wire1(void)
-{
-	at91_set_GPIO_periph(w1_gpio_pdata.pin, 1);
-	at91_set_multi_drive(w1_gpio_pdata.pin, 1);
-	platform_device_register(&w1_device);
-}
-
-
 static void __init pcontrol_g20_board_init(void)
 {
-	at91_add_device_serial();
-	add_device_nand();
-#if defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_ATMELMCI_MODULE)
-	at91_add_device_mci(0, &mmc_data);
-#else
-	at91_add_device_mmc(0, &mmc_data);
-#endif
+	stamp9g20_board_init();
 	at91_add_device_usbh(&usbh_data);
 	at91_add_device_eth(&macb_data);
 	at91_add_device_i2c(pcontrol_g20_i2c_devices,
 		ARRAY_SIZE(pcontrol_g20_i2c_devices));
-	add_wire1();
 	add_device_pcontrol();
 	at91_add_device_spi(pcontrol_g20_spi_devices,
 		ARRAY_SIZE(pcontrol_g20_spi_devices));

arch/arm/mach-at91/board-stamp9g20.c

@@ -32,7 +32,7 @@
 #include "generic.h"
 
 
-static void __init portuxg20_map_io(void)
+void __init stamp9g20_map_io(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
 	at91sam9260_initialize(18432000);
@@ -40,6 +40,24 @@ static void __init portuxg20_map_io(void)
 	/* DGBU on ttyS0. (Rx & Tx only) */
 	at91_register_uart(0, 0, 0);
 
+	/* set serial console to ttyS0 (ie, DBGU) */
+	at91_set_serial_console(0);
+}
+
+static void __init stamp9g20evb_map_io(void)
+{
+	stamp9g20_map_io();
+
+	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */
+	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS
+						| ATMEL_UART_DTR | ATMEL_UART_DSR
+						| ATMEL_UART_DCD | ATMEL_UART_RI);
+}
+
+static void __init portuxg20_map_io(void)
+{
+	stamp9g20_map_io();
+
 	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */
 	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS
 						| ATMEL_UART_DTR | ATMEL_UART_DSR
@@ -56,26 +74,6 @@ static void __init portuxg20_map_io(void)
 
 	/* USART5 on ttyS6. (Rx, Tx only) */
 	at91_register_uart(AT91SAM9260_ID_US5, 6, 0);
-
-	/* set serial console to ttyS0 (ie, DBGU) */
-	at91_set_serial_console(0);
-}
-
-static void __init stamp9g20_map_io(void)
-{
-	/* Initialize processor: 18.432 MHz crystal */
-	at91sam9260_initialize(18432000);
-
-	/* DGBU on ttyS0. (Rx & Tx only) */
-	at91_register_uart(0, 0, 0);
-
-	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */
-	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS
-						| ATMEL_UART_DTR | ATMEL_UART_DSR
-						| ATMEL_UART_DCD | ATMEL_UART_RI);
-
-	/* set serial console to ttyS0 (ie, DBGU) */
-	at91_set_serial_console(0);
 }
 
 static void __init init_irq(void)
@@ -156,7 +154,7 @@ static struct at91_udc_data __initdata portuxg20_udc_data = {
 	.pullup_pin	= 0,		/* pull-up driven by UDC */
 };
 
-static struct at91_udc_data __initdata stamp9g20_udc_data = {
+static struct at91_udc_data __initdata stamp9g20evb_udc_data = {
 	.vbus_pin	= AT91_PIN_PA22,
 	.pullup_pin	= 0,		/* pull-up driven by UDC */
 };
@@ -190,7 +188,7 @@ static struct gpio_led portuxg20_leds[] = {
 	}
 };
 
-static struct gpio_led stamp9g20_leds[] = {
+static struct gpio_led stamp9g20evb_leds[] = {
 	{
 		.name			= "D8",
 		.gpio			= AT91_PIN_PB18,
@@ -250,7 +248,7 @@ void add_w1(void)
 }
 
 
-static void __init generic_board_init(void)
+void __init stamp9g20_board_init(void)
 {
 	/* Serial */
 	at91_add_device_serial();
@@ -262,34 +260,40 @@ static void __init generic_board_init(void)
 #else
 	at91_add_device_mmc(0, &mmc_data);
 #endif
-	/* USB Host */
-	at91_add_device_usbh(&usbh_data);
-	/* Ethernet */
-	at91_add_device_eth(&macb_data);
-	/* I2C */
-	at91_add_device_i2c(NULL, 0);
 	/* W1 */
 	add_w1();
 }
 
 static void __init portuxg20_board_init(void)
 {
-	generic_board_init();
-	/* SPI */
-	at91_add_device_spi(portuxg20_spi_devices, ARRAY_SIZE(portuxg20_spi_devices));
+	stamp9g20_board_init();
+	/* USB Host */
+	at91_add_device_usbh(&usbh_data);
 	/* USB Device */
 	at91_add_device_udc(&portuxg20_udc_data);
+	/* Ethernet */
+	at91_add_device_eth(&macb_data);
+	/* I2C */
+	at91_add_device_i2c(NULL, 0);
+	/* SPI */
+	at91_add_device_spi(portuxg20_spi_devices, ARRAY_SIZE(portuxg20_spi_devices));
 	/* LEDs */
 	at91_gpio_leds(portuxg20_leds, ARRAY_SIZE(portuxg20_leds));
 }
 
-static void __init stamp9g20_board_init(void)
+static void __init stamp9g20evb_board_init(void)
 {
-	generic_board_init();
+	stamp9g20_board_init();
+	/* USB Host */
+	at91_add_device_usbh(&usbh_data);
 	/* USB Device */
-	at91_add_device_udc(&stamp9g20_udc_data);
+	at91_add_device_udc(&stamp9g20evb_udc_data);
+	/* Ethernet */
+	at91_add_device_eth(&macb_data);
+	/* I2C */
+	at91_add_device_i2c(NULL, 0);
 	/* LEDs */
-	at91_gpio_leds(stamp9g20_leds, ARRAY_SIZE(stamp9g20_leds));
+	at91_gpio_leds(stamp9g20evb_leds, ARRAY_SIZE(stamp9g20evb_leds));
 }
 
 MACHINE_START(PORTUXG20, "taskit PortuxG20")
@@ -305,7 +309,7 @@ MACHINE_START(STAMP9G20, "taskit Stamp9G20")
 	/* Maintainer: taskit GmbH */
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= stamp9g20_map_io,
+	.map_io		= stamp9g20evb_map_io,
 	.init_irq	= init_irq,
-	.init_machine	= stamp9g20_board_init,
+	.init_machine	= stamp9g20evb_board_init,
 MACHINE_END

arch/arm/mach-at91/clock.c

@@ -658,7 +658,7 @@ static void __init at91_upll_usbfs_clock_init(unsigned long main_clock)
 	/* Now set uhpck values */
 	uhpck.parent = &utmi_clk;
 	uhpck.pmc_mask = AT91SAM926x_PMC_UHP;
-	uhpck.rate_hz = utmi_clk.parent->rate_hz;
+	uhpck.rate_hz = utmi_clk.rate_hz;
 	uhpck.rate_hz /= 1 + ((at91_sys_read(AT91_PMC_USB) & AT91_PMC_OHCIUSBDIV) >> 8);
 }
 

arch/arm/mach-at91/include/mach/at91_mci.h

@@ -74,6 +74,8 @@
 #define			AT91_MCI_TRTYP_BLOCK	(0 << 19)
 #define			AT91_MCI_TRTYP_MULTIPLE	(1 << 19)
 #define			AT91_MCI_TRTYP_STREAM	(2 << 19)
+#define			AT91_MCI_TRTYP_SDIO_BYTE	(4 << 19)
+#define			AT91_MCI_TRTYP_SDIO_BLOCK	(5 << 19)
 
 #define AT91_MCI_BLKR		0x18		/* Block Register */
 #define		AT91_MCI_BLKR_BCNT(n)	((0xffff & (n)) << 0)	/* Block count */

arch/arm/mach-at91/include/mach/stamp9g20.h

+#ifndef __MACH_STAMP9G20_H
+#define __MACH_STAMP9G20_H
+
+void stamp9g20_map_io(void);
+void stamp9g20_board_init(void);
+
+#endif

arch/arm/mach-ixp4xx/common-pci.c

@@ -513,4 +513,4 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 
 EXPORT_SYMBOL(ixp4xx_pci_read);
 EXPORT_SYMBOL(ixp4xx_pci_write);
-
+EXPORT_SYMBOL(dma_set_coherent_mask);

arch/arm/mach-pxa/Kconfig

@@ -540,6 +540,7 @@ config MACH_ICONTROL
 config ARCH_PXA_ESERIES
 	bool "PXA based Toshiba e-series PDAs"
 	select PXA25x
+	select FB_W100
 
 config MACH_E330
 	bool "Toshiba e330"

arch/arm/mach-pxa/sleep.S

@@ -353,8 +353,8 @@ resume_turn_on_mmu:
 
 	@ Let us ensure we jump to resume_after_mmu only when the mcr above
 	@ actually took effect.  They call it the "cpwait" operation.
-	mrc	p15, 0, r1, c2, c0, 0		@ queue a dependency on CP15
-	sub	pc, r2, r1, lsr #32		@ jump to virtual addr
+	mrc	p15, 0, r0, c2, c0, 0		@ queue a dependency on CP15
+	sub	pc, r2, r0, lsr #32		@ jump to virtual addr
 	nop
 	nop
 	nop

arch/arm/mach-s3c2412/Kconfig

@@ -28,9 +28,16 @@ config S3C2412_DMA
 
 config S3C2412_PM
 	bool
+	select S3C2412_PM_SLEEP
 	help
 	  Internal config node to apply S3C2412 power management
 
+config S3C2412_PM_SLEEP
+	bool
+	help
+	  Internal config node to apply sleep for S3C2412 power management.
+	  Can be selected by another SoCs with similar sleep procedure.
+
 # Note, the S3C2412 IOtiming support is in plat-s3c24xx
 
 config S3C2412_CPUFREQ

arch/arm/mach-s3c2412/Makefile

@@ -14,7 +14,8 @@ obj-$(CONFIG_CPU_S3C2412)	+= irq.o
 obj-$(CONFIG_CPU_S3C2412)	+= clock.o
 obj-$(CONFIG_CPU_S3C2412)	+= gpio.o
 obj-$(CONFIG_S3C2412_DMA)	+= dma.o
-obj-$(CONFIG_S3C2412_PM)	+= pm.o sleep.o
+obj-$(CONFIG_S3C2412_PM)	+= pm.o
+obj-$(CONFIG_S3C2412_PM_SLEEP)	+= sleep.o
 obj-$(CONFIG_S3C2412_CPUFREQ)	+= cpu-freq.o
 
 # Machine support

arch/arm/mach-s3c2416/Kconfig

@@ -27,6 +27,7 @@ config S3C2416_DMA
 
 config S3C2416_PM
 	bool
+	select S3C2412_PM_SLEEP
 	help
 	  Internal config node to apply S3C2416 power management
 

arch/arm/mach-s5pv210/mach-aquila.c

@@ -378,6 +378,12 @@ static struct max8998_regulator_data aquila_regulators[] = {
 static struct max8998_platform_data aquila_max8998_pdata = {
 	.num_regulators	= ARRAY_SIZE(aquila_regulators),
 	.regulators	= aquila_regulators,
+	.buck1_set1	= S5PV210_GPH0(3),
+	.buck1_set2	= S5PV210_GPH0(4),
+	.buck2_set3	= S5PV210_GPH0(5),
+	.buck1_max_voltage1 = 1200000,
+	.buck1_max_voltage2 = 1200000,
+	.buck2_max_voltage = 1200000,
 };
 #endif
 

arch/arm/mach-s5pv210/mach-goni.c

@@ -518,6 +518,12 @@ static struct max8998_regulator_data goni_regulators[] = {
 static struct max8998_platform_data goni_max8998_pdata = {
 	.num_regulators	= ARRAY_SIZE(goni_regulators),
 	.regulators	= goni_regulators,
+	.buck1_set1	= S5PV210_GPH0(3),
+	.buck1_set2	= S5PV210_GPH0(4),
+	.buck2_set3	= S5PV210_GPH0(5),
+	.buck1_max_voltage1 = 1200000,
+	.buck1_max_voltage2 = 1200000,
+	.buck2_max_voltage = 1200000,
 };
 #endif
 

arch/arm/mach-shmobile/include/mach/entry-macro.S

 /*
+ * Copyright (C) 2010 Magnus Damm
  * Copyright (C) 2008 Renesas Solutions Corp.
  *
  * This program is free software; you can redistribute it and/or modify
@@ -14,24 +15,45 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
-#include <mach/hardware.h>
 #include <mach/irqs.h>
 
+#define INTCA_BASE	0xe6980000
+#define INTFLGA_OFFS	0x00000018 /* accept pending interrupt */
+#define INTEVTA_OFFS	0x00000020 /* vector number of accepted interrupt */
+#define INTLVLA_OFFS	0x00000030 /* priority level of accepted interrupt */
+#define INTLVLB_OFFS	0x00000034 /* previous priority level */
+
 	.macro  disable_fiq
 	.endm
 
 	.macro  get_irqnr_preamble, base, tmp
-	ldr     \base, =INTFLGA
+	ldr     \base, =INTCA_BASE
 	.endm
 
 	.macro  arch_ret_to_user, tmp1, tmp2
 	.endm
 
 	.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
-	ldr     \irqnr, [\base]
+	/* The single INTFLGA read access below results in the following:
+	 *
+	 * 1. INTLVLB is updated with old priority value from INTLVLA
+	 * 2. Highest priority interrupt is accepted
+	 * 3. INTLVLA is updated to contain priority of accepted interrupt
+	 * 4. Accepted interrupt vector is stored in INTFLGA and INTEVTA
+	 */
+	ldr     \irqnr, [\base, #INTFLGA_OFFS]
+
+	/* Restore INTLVLA with the value saved in INTLVLB.
+	 * This is required to support interrupt priorities properly.
+	 */
+	ldrb	\tmp, [\base, #INTLVLB_OFFS]
+	strb    \tmp, [\base, #INTLVLA_OFFS]
+
+	/* Handle invalid vector number case */
 	cmp	\irqnr, #0
 	beq	1000f
-	/* intevt to irq number */
+
+	/* Convert vector to irq number, same as the evt2irq() macro */
 	lsr	\irqnr, \irqnr, #0x5
 	subs	\irqnr, \irqnr, #16
 

arch/arm/mach-shmobile/include/mach/vmalloc.h

@@ -2,6 +2,6 @@
 #define __ASM_MACH_VMALLOC_H
 
 /* Vmalloc at ... - 0xe5ffffff */
-#define VMALLOC_END 0xe6000000
+#define VMALLOC_END 0xe6000000UL
 
 #endif /* __ASM_MACH_VMALLOC_H */

arch/arm/mm/cache-feroceon-l2.c

@@ -13,13 +13,9 @@
  */
 
 #include <linux/init.h>
+#include <linux/highmem.h>
 #include <asm/cacheflush.h>
-#include <asm/kmap_types.h>
-#include <asm/fixmap.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
 #include <plat/cache-feroceon-l2.h>
-#include "mm.h"
 
 /*
  * Low-level cache maintenance operations.
@@ -39,27 +35,30 @@
  * between which we don't want to be preempted.
  */
 
-static inline unsigned long l2_start_va(unsigned long paddr)
+static inline unsigned long l2_get_va(unsigned long paddr)
 {
 #ifdef CONFIG_HIGHMEM
 	/*
-	 * Let's do our own fixmap stuff in a minimal way here.
 	 * Because range ops can't be done on physical addresses,
 	 * we simply install a virtual mapping for it only for the
 	 * TLB lookup to occur, hence no need to flush the untouched
-	 * memory mapping.  This is protected with the disabling of
-	 * interrupts by the caller.
+	 * memory mapping afterwards (note: a cache flush may happen
+	 * in some circumstances depending on the path taken in kunmap_atomic).
 	 */
-	unsigned long idx = KM_L2_CACHE + KM_TYPE_NR * smp_processor_id();
-	unsigned long vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	set_pte_ext(TOP_PTE(vaddr), pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL), 0);
-	local_flush_tlb_kernel_page(vaddr);
-	return vaddr + (paddr & ~PAGE_MASK);
+	void *vaddr = kmap_atomic_pfn(paddr >> PAGE_SHIFT);
+	return (unsigned long)vaddr + (paddr & ~PAGE_MASK);
 #else
 	return __phys_to_virt(paddr);
 #endif
 }
 
+static inline void l2_put_va(unsigned long vaddr)
+{
+#ifdef CONFIG_HIGHMEM
+	kunmap_atomic((void *)vaddr);
+#endif
+}
+
 static inline void l2_clean_pa(unsigned long addr)
 {
 	__asm__("mcr p15, 1, %0, c15, c9, 3" : : "r" (addr));
@@ -76,13 +75,14 @@ static inline void l2_clean_pa_range(unsigned long start, unsigned long end)
 	 */
 	BUG_ON((start ^ end) >> PAGE_SHIFT);
 
-	raw_local_irq_save(flags);
-	va_start = l2_start_va(start);
+	va_start = l2_get_va(start);
 	va_end = va_start + (end - start);
+	raw_local_irq_save(flags);
 	__asm__("mcr p15, 1, %0, c15, c9, 4\n\t"
 		"mcr p15, 1, %1, c15, c9, 5"
 		: : "r" (va_start), "r" (va_end));
 	raw_local_irq_restore(flags);
+	l2_put_va(va_start);
 }
 
 static inline void l2_clean_inv_pa(unsigned long addr)
@@ -106,13 +106,14 @@ static inline void l2_inv_pa_range(unsigned long start, unsigned long end)
 	 */
 	BUG_ON((start ^ end) >> PAGE_SHIFT);
 
-	raw_local_irq_save(flags);
-	va_start = l2_start_va(start);
+	va_start = l2_get_va(start);
 	va_end = va_start + (end - start);
+	raw_local_irq_save(flags);
 	__asm__("mcr p15, 1, %0, c15, c11, 4\n\t"
 		"mcr p15, 1, %1, c15, c11, 5"
 		: : "r" (va_start), "r" (va_end));
 	raw_local_irq_restore(flags);
+	l2_put_va(va_start);
 }
 
 static inline void l2_inv_all(void)

arch/arm/mm/cache-xsc3l2.c

@@ -17,14 +17,10 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 #include <linux/init.h>
+#include <linux/highmem.h>
 #include <asm/system.h>
 #include <asm/cputype.h>
 #include <asm/cacheflush.h>
-#include <asm/kmap_types.h>
-#include <asm/fixmap.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-#include "mm.h"
 
 #define CR_L2	(1 << 26)
 
@@ -71,16 +67,15 @@ static inline void xsc3_l2_inv_all(void)
 	dsb();
 }
 
+static inline void l2_unmap_va(unsigned long va)
+{
 #ifdef CONFIG_HIGHMEM
-#define l2_map_save_flags(x)		raw_local_save_flags(x)
-#define l2_map_restore_flags(x)		raw_local_irq_restore(x)
-#else
-#define l2_map_save_flags(x)		((x) = 0)
-#define l2_map_restore_flags(x)		((void)(x))
+	if (va != -1)
+		kunmap_atomic((void *)va);
 #endif
+}
 
-static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va,
-				      unsigned long flags)
+static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va)
 {
 #ifdef CONFIG_HIGHMEM
 	unsigned long va = prev_va & PAGE_MASK;
@@ -89,17 +84,10 @@ static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va,
 		/*
 		 * Switching to a new page.  Because cache ops are
 		 * using virtual addresses only, we must put a mapping
-		 * in place for it.  We also enable interrupts for a
-		 * short while and disable them again to protect this
-		 * mapping.
+		 * in place for it.
 		 */
-		unsigned long idx;
-		raw_local_irq_restore(flags);
-		idx = KM_L2_CACHE + KM_TYPE_NR * smp_processor_id();
-		va = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-		raw_local_irq_restore(flags | PSR_I_BIT);
-		set_pte_ext(TOP_PTE(va), pfn_pte(pa >> PAGE_SHIFT, PAGE_KERNEL), 0);
-		local_flush_tlb_kernel_page(va);
+		l2_unmap_va(prev_va);
+		va = (unsigned long)kmap_atomic_pfn(pa >> PAGE_SHIFT);
 	}
 	return va + (pa_offset >> (32 - PAGE_SHIFT));
 #else
@@ -109,7 +97,7 @@ static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va,
 
 static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
 {
-	unsigned long vaddr, flags;
+	unsigned long vaddr;
 
 	if (start == 0 && end == -1ul) {
 		xsc3_l2_inv_all();
@@ -117,13 +105,12 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
 	}
 
 	vaddr = -1;  /* to force the first mapping */
-	l2_map_save_flags(flags);
 
 	/*
 	 * Clean and invalidate partial first cache line.
 	 */
 	if (start & (CACHE_LINE_SIZE - 1)) {
-		vaddr = l2_map_va(start & ~(CACHE_LINE_SIZE - 1), vaddr, flags);
+		vaddr = l2_map_va(start & ~(CACHE_LINE_SIZE - 1), vaddr);
 		xsc3_l2_clean_mva(vaddr);
 		xsc3_l2_inv_mva(vaddr);
 		start = (start | (CACHE_LINE_SIZE - 1)) + 1;
@@ -133,7 +120,7 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
 	 * Invalidate all full cache lines between 'start' and 'end'.
 	 */
 	while (start < (end & ~(CACHE_LINE_SIZE - 1))) {
-		vaddr = l2_map_va(start, vaddr, flags);
+		vaddr = l2_map_va(start, vaddr);
 		xsc3_l2_inv_mva(vaddr);
 		start += CACHE_LINE_SIZE;
 	}
@@ -142,31 +129,30 @@ static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
 	 * Clean and invalidate partial last cache line.
 	 */
 	if (start < end) {
-		vaddr = l2_map_va(start, vaddr, flags);
+		vaddr = l2_map_va(start, vaddr);
 		xsc3_l2_clean_mva(vaddr);
 		xsc3_l2_inv_mva(vaddr);
 	}
 
-	l2_map_restore_flags(flags);
+	l2_unmap_va(vaddr);
 
 	dsb();
 }
 
 static void xsc3_l2_clean_range(unsigned long start, unsigned long end)
 {
-	unsigned long vaddr, flags;
+	unsigned long vaddr;
 
 	vaddr = -1;  /* to force the first mapping */
-	l2_map_save_flags(flags);
 
 	start &= ~(CACHE_LINE_SIZE - 1);
 	while (start < end) {
-		vaddr = l2_map_va(start, vaddr, flags);
+		vaddr = l2_map_va(start, vaddr);
 		xsc3_l2_clean_mva(vaddr);
 		start += CACHE_LINE_SIZE;
 	}
 
-	l2_map_restore_flags(flags);
+	l2_unmap_va(vaddr);
 
 	dsb();
 }
@@ -193,7 +179,7 @@ static inline void xsc3_l2_flush_all(void)
 
 static void xsc3_l2_flush_range(unsigned long start, unsigned long end)
 {
-	unsigned long vaddr, flags;
+	unsigned long vaddr;
 
 	if (start == 0 && end == -1ul) {
 		xsc3_l2_flush_all();
@@ -201,17 +187,16 @@ static void xsc3_l2_flush_range(unsigned long start, unsigned long end)
 	}
 
 	vaddr = -1;  /* to force the first mapping */
-	l2_map_save_flags(flags);
 
 	start &= ~(CACHE_LINE_SIZE - 1);
 	while (start < end) {
-		vaddr = l2_map_va(start, vaddr, flags);
+		vaddr = l2_map_va(start, vaddr);
 		xsc3_l2_clean_mva(vaddr);
 		xsc3_l2_inv_mva(vaddr);
 		start += CACHE_LINE_SIZE;
 	}
 
-	l2_map_restore_flags(flags);
+	l2_unmap_va(vaddr);
 
 	dsb();
 }

arch/arm/mm/dma-mapping.c

@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/highmem.h>
 
 #include <asm/memory.h>
 #include <asm/highmem.h>
@@ -480,10 +481,10 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 				op(vaddr, len, dir);
 				kunmap_high(page);
 			} else if (cache_is_vipt()) {
-				pte_t saved_pte;
-				vaddr = kmap_high_l1_vipt(page, &saved_pte);
+				/* unmapped pages might still be cached */
+				vaddr = kmap_atomic(page);
 				op(vaddr + offset, len, dir);
-				kunmap_high_l1_vipt(page, saved_pte);
+				kunmap_atomic(vaddr);
 			}
 		} else {
 			vaddr = page_address(page) + offset;

arch/arm/mm/flush.c

@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
+#include <linux/highmem.h>
 
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
@@ -180,10 +181,10 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
 			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
 			kunmap_high(page);
 		} else if (cache_is_vipt()) {
-			pte_t saved_pte;
-			addr = kmap_high_l1_vipt(page, &saved_pte);
+			/* unmapped pages might still be cached */
+			addr = kmap_atomic(page);
 			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
-			kunmap_high_l1_vipt(page, saved_pte);
+			kunmap_atomic(addr);
 		}
 	}
 

arch/arm/mm/highmem.c

@@ -140,90 +140,3 @@ struct page *kmap_atomic_to_page(const void *ptr)
 	pte = TOP_PTE(vaddr);
 	return pte_page(*pte);
 }
-
-#ifdef CONFIG_CPU_CACHE_VIPT
-
-#include <linux/percpu.h>
-
-/*
- * The VIVT cache of a highmem page is always flushed before the page
- * is unmapped. Hence unmapped highmem pages need no cache maintenance
- * in that case.
- *
- * However unmapped pages may still be cached with a VIPT cache, and
- * it is not possible to perform cache maintenance on them using physical
- * addresses unfortunately.  So we have no choice but to set up a temporary
- * virtual mapping for that purpose.
- *
- * Yet this VIPT cache maintenance may be triggered from DMA support
- * functions which are possibly called from interrupt context. As we don't
- * want to keep interrupt disabled all the time when such maintenance is
- * taking place, we therefore allow for some reentrancy by preserving and
- * restoring the previous fixmap entry before the interrupted context is
- * resumed.  If the reentrancy depth is 0 then there is no need to restore
- * the previous fixmap, and leaving the current one in place allow it to
- * be reused the next time without a TLB flush (common with DMA).
- */
-
-static DEFINE_PER_CPU(int, kmap_high_l1_vipt_depth);
-
-void *kmap_high_l1_vipt(struct page *page, pte_t *saved_pte)
-{
-	unsigned int idx, cpu;
-	int *depth;
-	unsigned long vaddr, flags;
-	pte_t pte, *ptep;
-
-	if (!in_interrupt())
-		preempt_disable();
-
-	cpu = smp_processor_id();
-	depth = &per_cpu(kmap_high_l1_vipt_depth, cpu);
-
-	idx = KM_L1_CACHE + KM_TYPE_NR * cpu;
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	ptep = TOP_PTE(vaddr);
-	pte = mk_pte(page, kmap_prot);
-
-	raw_local_irq_save(flags);
-	(*depth)++;
-	if (pte_val(*ptep) == pte_val(pte)) {
-		*saved_pte = pte;
-	} else {
-		*saved_pte = *ptep;
-		set_pte_ext(ptep, pte, 0);
-		local_flush_tlb_kernel_page(vaddr);
-	}
-	raw_local_irq_restore(flags);
-
-	return (void *)vaddr;
-}
-
-void kunmap_high_l1_vipt(struct page *page, pte_t saved_pte)
-{
-	unsigned int idx, cpu = smp_processor_id();
-	int *depth = &per_cpu(kmap_high_l1_vipt_depth, cpu);
-	unsigned long vaddr, flags;
-	pte_t pte, *ptep;
-
-	idx = KM_L1_CACHE + KM_TYPE_NR * cpu;
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	ptep = TOP_PTE(vaddr);
-	pte = mk_pte(page, kmap_prot);
-
-	BUG_ON(pte_val(*ptep) != pte_val(pte));
-	BUG_ON(*depth <= 0);
-
-	raw_local_irq_save(flags);
-	(*depth)--;
-	if (*depth != 0 && pte_val(pte) != pte_val(saved_pte)) {
-		set_pte_ext(ptep, saved_pte, 0);
-		local_flush_tlb_kernel_page(vaddr);
-	}
-	raw_local_irq_restore(flags);
-
-	if (!in_interrupt())
-		preempt_enable();
-}
-
-#endif  /* CONFIG_CPU_CACHE_VIPT */

arch/arm/plat-s3c24xx/Kconfig

@@ -8,7 +8,7 @@ config PLAT_S3C24XX
 	default y
 	select NO_IOPORT
 	select ARCH_REQUIRE_GPIOLIB
-	select S3C_DEVICE_NAND
+	select S3C_DEV_NAND
 	select S3C_GPIO_CFG_S3C24XX
 	help
 	  Base platform code for any Samsung S3C24XX device

arch/mips/Kconfig

@@ -19,6 +19,8 @@ config MIPS
 	select GENERIC_ATOMIC64 if !64BIT
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
+	select HAVE_GENERIC_HARDIRQS
+	select GENERIC_IRQ_PROBE
 
 menu "Machine selection"
 
@@ -1664,6 +1666,28 @@ config PAGE_SIZE_64KB
 
 endchoice
 
+config FORCE_MAX_ZONEORDER
+	int "Maximum zone order"
+	range 13 64 if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_32KB
+	default "13" if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_32KB
+	range 12 64 if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_16KB
+	default "12" if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_16KB
+	range 11 64
+	default "11"
+	help
+	  The kernel memory allocator divides physically contiguous memory
+	  blocks into "zones", where each zone is a power of two number of
+	  pages.  This option selects the largest power of two that the kernel
+	  keeps in the memory allocator.  If you need to allocate very large
+	  blocks of physically contiguous memory, then you may need to
+	  increase this value.
+
+	  This config option is actually maximum order plus one. For example,
+	  a value of 11 means that the largest free memory block is 2^10 pages.
+
+	  The page size is not necessarily 4KB.  Keep this in mind
+	  when choosing a value for this option.
+
 config BOARD_SCACHE
 	bool
 
@@ -1921,20 +1945,6 @@ config CPU_R4000_WORKAROUNDS
 config CPU_R4400_WORKAROUNDS
 	bool
 
-#
-# Use the generic interrupt handling code in kernel/irq/:
-#
-config GENERIC_HARDIRQS
-	bool
-	default y
-
-config GENERIC_IRQ_PROBE
-	bool
-	default y
-
-config IRQ_PER_CPU
-	bool
-
 #
 # - Highmem only makes sense for the 32-bit kernel.
 # - The current highmem code will only work properly on physically indexed

arch/mips/alchemy/common/platform.c

@@ -27,6 +27,7 @@
 static void alchemy_8250_pm(struct uart_port *port, unsigned int state,
 			    unsigned int old_state)
 {
+#ifdef CONFIG_SERIAL_8250
 	switch (state) {
 	case 0:
 		if ((__raw_readl(port->membase + UART_MOD_CNTRL) & 3) != 3) {
@@ -49,6 +50,7 @@ static void alchemy_8250_pm(struct uart_port *port, unsigned int state,
 		serial8250_do_pm(port, state, old_state);
 		break;
 	}
+#endif
 }
 
 #define PORT(_base, _irq)					\

arch/mips/alchemy/devboards/prom.c

@@ -54,10 +54,9 @@ void __init prom_init(void)
 
 	prom_init_cmdline();
 	memsize_str = prom_getenv("memsize");
-	if (!memsize_str)
+	if (!memsize_str || strict_strtoul(memsize_str, 0, &memsize))
 		memsize = ALCHEMY_BOARD_DEFAULT_MEMSIZE;
-	else
-		strict_strtoul(memsize_str, 0, &memsize);
+
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 

arch/mips/ar7/clock.c

@@ -239,12 +239,12 @@ static void tnetd7300_set_clock(u32 shift, struct tnetd7300_clock *clock,
 	calculate(base_clock, frequency, &prediv, &postdiv, &mul);
 
 	writel(((prediv - 1) << PREDIV_SHIFT) | (postdiv - 1), &clock->ctrl);
-	msleep(1);
+	mdelay(1);
 	writel(4, &clock->pll);
 	while (readl(&clock->pll) & PLL_STATUS)
 		;
 	writel(((mul - 1) << MUL_SHIFT) | (0xff << 3) | 0x0e, &clock->pll);
-	msleep(75);
+	mdelay(75);
 }
 
 static void __init tnetd7300_init_clocks(void)
@@ -456,7 +456,7 @@ void clk_put(struct clk *clk)
 }
 EXPORT_SYMBOL(clk_put);
 
-int __init ar7_init_clocks(void)
+void __init ar7_init_clocks(void)
 {
 	switch (ar7_chip_id()) {
 	case AR7_CHIP_7100:
@@ -472,7 +472,4 @@ int __init ar7_init_clocks(void)
 	}
 	/* adjust vbus clock rate */
 	vbus_clk.rate = bus_clk.rate / 2;
-
-	return 0;
 }
-arch_initcall(ar7_init_clocks);

arch/mips/ar7/time.c

@@ -30,6 +30,9 @@ void __init plat_time_init(void)
 {
 	struct clk *cpu_clk;
 
+	/* Initialize ar7 clocks so the CPU clock frequency is correct */
+	ar7_init_clocks();
+
 	cpu_clk = clk_get(NULL, "cpu");
 	if (IS_ERR(cpu_clk)) {
 		printk(KERN_ERR "unable to get cpu clock\n");

arch/mips/bcm47xx/setup.c

@@ -32,7 +32,6 @@
 #include <asm/reboot.h>
 #include <asm/time.h>
 #include <bcm47xx.h>
-#include <asm/fw/cfe/cfe_api.h>
 #include <asm/mach-bcm47xx/nvram.h>
 
 struct ssb_bus ssb_bcm47xx;
@@ -57,68 +56,112 @@ static void bcm47xx_machine_halt(void)
 		cpu_relax();
 }
 
-static void str2eaddr(char *str, char *dest)
-{
-	int i = 0;
+#define READ_FROM_NVRAM(_outvar, name, buf) \
+	if (nvram_getenv(name, buf, sizeof(buf)) >= 0)\
+		sprom->_outvar = simple_strtoul(buf, NULL, 0);
 
-	if (str == NULL) {
-		memset(dest, 0, 6);
-		return;
+static void bcm47xx_fill_sprom(struct ssb_sprom *sprom)
+{
+	char buf[100];
+	u32 boardflags;
+
+	memset(sprom, 0, sizeof(struct ssb_sprom));
+
+	sprom->revision = 1; /* Fallback: Old hardware does not define this. */
+	READ_FROM_NVRAM(revision, "sromrev", buf);
+	if (nvram_getenv("il0macaddr", buf, sizeof(buf)) >= 0)
+		nvram_parse_macaddr(buf, sprom->il0mac);
+	if (nvram_getenv("et0macaddr", buf, sizeof(buf)) >= 0)
+		nvram_parse_macaddr(buf, sprom->et0mac);
+	if (nvram_getenv("et1macaddr", buf, sizeof(buf)) >= 0)
+		nvram_parse_macaddr(buf, sprom->et1mac);
+	READ_FROM_NVRAM(et0phyaddr, "et0phyaddr", buf);
+	READ_FROM_NVRAM(et1phyaddr, "et1phyaddr", buf);
+	READ_FROM_NVRAM(et0mdcport, "et0mdcport", buf);
+	READ_FROM_NVRAM(et1mdcport, "et1mdcport", buf);
+	READ_FROM_NVRAM(board_rev, "boardrev", buf);
+	READ_FROM_NVRAM(country_code, "ccode", buf);
+	READ_FROM_NVRAM(ant_available_a, "aa5g", buf);
+	READ_FROM_NVRAM(ant_available_bg, "aa2g", buf);
+	READ_FROM_NVRAM(pa0b0, "pa0b0", buf);
+	READ_FROM_NVRAM(pa0b1, "pa0b1", buf);
+	READ_FROM_NVRAM(pa0b2, "pa0b2", buf);
+	READ_FROM_NVRAM(pa1b0, "pa1b0", buf);
+	READ_FROM_NVRAM(pa1b1, "pa1b1", buf);
+	READ_FROM_NVRAM(pa1b2, "pa1b2", buf);
+	READ_FROM_NVRAM(pa1lob0, "pa1lob0", buf);
+	READ_FROM_NVRAM(pa1lob2, "pa1lob1", buf);
+	READ_FROM_NVRAM(pa1lob1, "pa1lob2", buf);
+	READ_FROM_NVRAM(pa1hib0, "pa1hib0", buf);
+	READ_FROM_NVRAM(pa1hib2, "pa1hib1", buf);
+	READ_FROM_NVRAM(pa1hib1, "pa1hib2", buf);
+	READ_FROM_NVRAM(gpio0, "wl0gpio0", buf);
+	READ_FROM_NVRAM(gpio1, "wl0gpio1", buf);
+	READ_FROM_NVRAM(gpio2, "wl0gpio2", buf);
+	READ_FROM_NVRAM(gpio3, "wl0gpio3", buf);
+	READ_FROM_NVRAM(maxpwr_bg, "pa0maxpwr", buf);
+	READ_FROM_NVRAM(maxpwr_al, "pa1lomaxpwr", buf);
+	READ_FROM_NVRAM(maxpwr_a, "pa1maxpwr", buf);
+	READ_FROM_NVRAM(maxpwr_ah, "pa1himaxpwr", buf);
+	READ_FROM_NVRAM(itssi_a, "pa1itssit", buf);
+	READ_FROM_NVRAM(itssi_bg, "pa0itssit", buf);
+	READ_FROM_NVRAM(tri2g, "tri2g", buf);
+	READ_FROM_NVRAM(tri5gl, "tri5gl", buf);
+	READ_FROM_NVRAM(tri5g, "tri5g", buf);
+	READ_FROM_NVRAM(tri5gh, "tri5gh", buf);
+	READ_FROM_NVRAM(rxpo2g, "rxpo2g", buf);
+	READ_FROM_NVRAM(rxpo5g, "rxpo5g", buf);
+	READ_FROM_NVRAM(rssisav2g, "rssisav2g", buf);
+	READ_FROM_NVRAM(rssismc2g, "rssismc2g", buf);
+	READ_FROM_NVRAM(rssismf2g, "rssismf2g", buf);
+	READ_FROM_NVRAM(bxa2g, "bxa2g", buf);
+	READ_FROM_NVRAM(rssisav5g, "rssisav5g", buf);
+	READ_FROM_NVRAM(rssismc5g, "rssismc5g", buf);
+	READ_FROM_NVRAM(rssismf5g, "rssismf5g", buf);
+	READ_FROM_NVRAM(bxa5g, "bxa5g", buf);
+	READ_FROM_NVRAM(cck2gpo, "cck2gpo", buf);
+	READ_FROM_NVRAM(ofdm2gpo, "ofdm2gpo", buf);
+	READ_FROM_NVRAM(ofdm5glpo, "ofdm5glpo", buf);
+	READ_FROM_NVRAM(ofdm5gpo, "ofdm5gpo", buf);
+	READ_FROM_NVRAM(ofdm5ghpo, "ofdm5ghpo", buf);
+
+	if (nvram_getenv("boardflags", buf, sizeof(buf)) >= 0) {
+		boardflags = simple_strtoul(buf, NULL, 0);
+		if (boardflags) {
+			sprom->boardflags_lo = (boardflags & 0x0000FFFFU);
+			sprom->boardflags_hi = (boardflags & 0xFFFF0000U) >> 16;
+		}
 	}
-
-	for (;;) {
-		dest[i++] = (char) simple_strtoul(str, NULL, 16);
-		str += 2;
-		if (!*str++ || i == 6)
-			break;
+	if (nvram_getenv("boardflags2", buf, sizeof(buf)) >= 0) {
+		boardflags = simple_strtoul(buf, NULL, 0);
+		if (boardflags) {
+			sprom->boardflags2_lo = (boardflags & 0x0000FFFFU);
+			sprom->boardflags2_hi = (boardflags & 0xFFFF0000U) >> 16;
+		}
 	}
 }
 
 static int bcm47xx_get_invariants(struct ssb_bus *bus,
 				   struct ssb_init_invariants *iv)
 {
-	char buf[100];
+	char buf[20];
 
 	/* Fill boardinfo structure */
 	memset(&(iv->boardinfo), 0 , sizeof(struct ssb_boardinfo));
 
-	if (cfe_getenv("boardvendor", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("boardvendor", buf, sizeof(buf)) >= 0)
-		iv->boardinfo.type = (u16)simple_strtoul(buf, NULL, 0);
-	if (cfe_getenv("boardtype", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("boardtype", buf, sizeof(buf)) >= 0)
+	if (nvram_getenv("boardvendor", buf, sizeof(buf)) >= 0)
+		iv->boardinfo.vendor = (u16)simple_strtoul(buf, NULL, 0);
+	else
+		iv->boardinfo.vendor = SSB_BOARDVENDOR_BCM;
+	if (nvram_getenv("boardtype", buf, sizeof(buf)) >= 0)
 		iv->boardinfo.type = (u16)simple_strtoul(buf, NULL, 0);
-	if (cfe_getenv("boardrev", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("boardrev", buf, sizeof(buf)) >= 0)
+	if (nvram_getenv("boardrev", buf, sizeof(buf)) >= 0)
 		iv->boardinfo.rev = (u16)simple_strtoul(buf, NULL, 0);
 
-	/* Fill sprom structure */
-	memset(&(iv->sprom), 0, sizeof(struct ssb_sprom));
-	iv->sprom.revision = 3;
-
-	if (cfe_getenv("et0macaddr", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et0macaddr", buf, sizeof(buf)) >= 0)
-		str2eaddr(buf, iv->sprom.et0mac);
+	bcm47xx_fill_sprom(&iv->sprom);
 
-	if (cfe_getenv("et1macaddr", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et1macaddr", buf, sizeof(buf)) >= 0)
-		str2eaddr(buf, iv->sprom.et1mac);
-
-	if (cfe_getenv("et0phyaddr", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et0phyaddr", buf, sizeof(buf)) >= 0)
-		iv->sprom.et0phyaddr = simple_strtoul(buf, NULL, 0);
-
-	if (cfe_getenv("et1phyaddr", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et1phyaddr", buf, sizeof(buf)) >= 0)
-		iv->sprom.et1phyaddr = simple_strtoul(buf, NULL, 0);
-
-	if (cfe_getenv("et0mdcport", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et0mdcport", buf, sizeof(buf)) >= 0)
-		iv->sprom.et0mdcport = simple_strtoul(buf, NULL, 10);
-
-	if (cfe_getenv("et1mdcport", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et1mdcport", buf, sizeof(buf)) >= 0)
-		iv->sprom.et1mdcport = simple_strtoul(buf, NULL, 10);
+	if (nvram_getenv("cardbus", buf, sizeof(buf)) >= 0)
+		iv->has_cardbus_slot = !!simple_strtoul(buf, NULL, 10);
 
 	return 0;
 }
@@ -126,12 +169,28 @@ static int bcm47xx_get_invariants(struct ssb_bus *bus,
 void __init plat_mem_setup(void)
 {
 	int err;
+	char buf[100];
+	struct ssb_mipscore *mcore;
 
 	err = ssb_bus_ssbbus_register(&ssb_bcm47xx, SSB_ENUM_BASE,
 				      bcm47xx_get_invariants);
 	if (err)
 		panic("Failed to initialize SSB bus (err %d)\n", err);
 
+	mcore = &ssb_bcm47xx.mipscore;
+	if (nvram_getenv("kernel_args", buf, sizeof(buf)) >= 0) {
+		if (strstr(buf, "console=ttyS1")) {
+			struct ssb_serial_port port;
+
+			printk(KERN_DEBUG "Swapping serial ports!\n");
+			/* swap serial ports */
+			memcpy(&port, &mcore->serial_ports[0], sizeof(port));
+			memcpy(&mcore->serial_ports[0], &mcore->serial_ports[1],
+			       sizeof(port));
+			memcpy(&mcore->serial_ports[1], &port, sizeof(port));
+		}
+	}
+
 	_machine_restart = bcm47xx_machine_restart;
 	_machine_halt = bcm47xx_machine_halt;
 	pm_power_off = bcm47xx_machine_halt;

arch/mips/include/asm/cpu.h

@@ -111,8 +111,8 @@
  * These are the PRID's for when 23:16 == PRID_COMP_BROADCOM
  */
 
-#define PRID_IMP_BMIPS4KC	0x4000
-#define PRID_IMP_BMIPS32	0x8000
+#define PRID_IMP_BMIPS32_REV4	0x4000
+#define PRID_IMP_BMIPS32_REV8	0x8000
 #define PRID_IMP_BMIPS3300	0x9000
 #define PRID_IMP_BMIPS3300_ALT	0x9100
 #define PRID_IMP_BMIPS3300_BUG	0x0000

arch/mips/include/asm/elf.h

@@ -249,7 +249,8 @@ extern struct mips_abi mips_abi_n32;
 
 #define SET_PERSONALITY(ex)						\
 do {									\
-	set_personality(PER_LINUX);					\
+	if (personality(current->personality) != PER_LINUX)		\
+		set_personality(PER_LINUX);				\
 									\
 	current->thread.abi = &mips_abi;				\
 } while (0)
@@ -296,6 +297,8 @@ do {									\
 
 #define SET_PERSONALITY(ex)						\
 do {									\
+	unsigned int p;							\
+									\
 	clear_thread_flag(TIF_32BIT_REGS);				\
 	clear_thread_flag(TIF_32BIT_ADDR);				\
 									\
@@ -304,7 +307,8 @@ do {									\
 	else								\
 		current->thread.abi = &mips_abi;			\
 									\
-	if (current->personality != PER_LINUX32)			\
+	p = personality(current->personality);				\
+	if (p != PER_LINUX32 && p != PER_LINUX)				\
 		set_personality(PER_LINUX);				\
 } while (0)
 

arch/mips/include/asm/io.h

@@ -329,10 +329,14 @@ static inline void pfx##write##bwlq(type val,				\
 			"dsrl32	%L0, %L0, 0"			"\n\t"	\
 			"dsll32	%M0, %M0, 0"			"\n\t"	\
 			"or	%L0, %L0, %M0"			"\n\t"	\
+			".set	push"				"\n\t"	\
+			".set	noreorder"			"\n\t"	\
+			".set	nomacro"			"\n\t"	\
 			"sd	%L0, %2"			"\n\t"	\
+			".set	pop"				"\n\t"	\
 			".set	mips0"				"\n"	\
 			: "=r" (__tmp)					\
-			: "0" (__val), "m" (*__mem));			\
+			: "0" (__val), "R" (*__mem));			\
 		if (irq)						\
 			local_irq_restore(__flags);			\
 	} else								\
@@ -355,12 +359,16 @@ static inline type pfx##read##bwlq(const volatile void __iomem *mem)	\
 			local_irq_save(__flags);			\
 		__asm__ __volatile__(					\
 			".set	mips3"		"\t\t# __readq"	"\n\t"	\
+			".set	push"				"\n\t"	\
+			".set	noreorder"			"\n\t"	\
+			".set	nomacro"			"\n\t"	\
 			"ld	%L0, %1"			"\n\t"	\
+			".set	pop"				"\n\t"	\
 			"dsra32	%M0, %L0, 0"			"\n\t"	\
 			"sll	%L0, %L0, 0"			"\n\t"	\
 			".set	mips0"				"\n"	\
 			: "=r" (__val)					\
-			: "m" (*__mem));				\
+			: "R" (*__mem));				\
 		if (irq)						\
 			local_irq_restore(__flags);			\
 	} else {							\

arch/mips/include/asm/mach-ar7/ar7.h

@@ -201,7 +201,6 @@ static inline void ar7_device_off(u32 bit)
 }
 
 int __init ar7_gpio_init(void);
-
-int __init ar7_gpio_init(void);
+void __init ar7_init_clocks(void);
 
 #endif /* __AR7_H__ */

arch/mips/include/asm/mach-bcm47xx/nvram.h

@@ -12,6 +12,7 @@
 #define __NVRAM_H
 
 #include <linux/types.h>
+#include <linux/kernel.h>
 
 struct nvram_header {
 	u32 magic;
@@ -36,4 +37,10 @@ struct nvram_header {
 
 extern int nvram_getenv(char *name, char *val, size_t val_len);
 
+static inline void nvram_parse_macaddr(char *buf, u8 *macaddr)
+{
+	sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", &macaddr[0], &macaddr[1],
+	       &macaddr[2], &macaddr[3], &macaddr[4], &macaddr[5]);
+}
+
 #endif

arch/mips/jz4740/board-qi_lb60.c

@@ -5,7 +5,7 @@
  *
  * Copyright (c) 2009 Qi Hardware inc.,
  * Author: Xiangfu Liu <xiangfu@qi-hardware.com>
- * Copyright 2010, Lars-Petrer Clausen <lars@metafoo.de>
+ * Copyright 2010, Lars-Peter Clausen <lars@metafoo.de>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 or later
@@ -235,7 +235,7 @@ static const unsigned int qi_lb60_keypad_rows[] = {
 	QI_LB60_GPIO_KEYIN(3),
 	QI_LB60_GPIO_KEYIN(4),
 	QI_LB60_GPIO_KEYIN(5),
-	QI_LB60_GPIO_KEYIN(7),
+	QI_LB60_GPIO_KEYIN(6),
 	QI_LB60_GPIO_KEYIN8,
 };
 

arch/mips/jz4740/platform.c

@@ -208,7 +208,7 @@ struct platform_device jz4740_i2s_device = {
 
 /* PCM */
 struct platform_device jz4740_pcm_device = {
-	.name		= "jz4740-pcm",
+	.name		= "jz4740-pcm-audio",
 	.id		= -1,
 };
 

arch/mips/jz4740/prom.c

@@ -23,7 +23,7 @@
 #include <asm/bootinfo.h>
 #include <asm/mach-jz4740/base.h>
 
-void jz4740_init_cmdline(int argc, char *argv[])
+static __init void jz4740_init_cmdline(int argc, char *argv[])
 {
 	unsigned int count = COMMAND_LINE_SIZE - 1;
 	int i;

arch/mips/kernel/cevt-r4k.c

@@ -32,7 +32,7 @@ static int mips_next_event(unsigned long delta,
 	cnt = read_c0_count();
 	cnt += delta;
 	write_c0_compare(cnt);
-	res = ((int)(read_c0_count() - cnt) > 0) ? -ETIME : 0;
+	res = ((int)(read_c0_count() - cnt) >= 0) ? -ETIME : 0;
 	return res;
 }
 

arch/mips/kernel/cpu-probe.c

@@ -905,7 +905,8 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	decode_configs(c);
 	switch (c->processor_id & 0xff00) {
-	case PRID_IMP_BMIPS32:
+	case PRID_IMP_BMIPS32_REV4:
+	case PRID_IMP_BMIPS32_REV8:
 		c->cputype = CPU_BMIPS32;
 		__cpu_name[cpu] = "Broadcom BMIPS32";
 		break;
@@ -933,10 +934,6 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 		__cpu_name[cpu] = "Broadcom BMIPS5000";
 		c->options |= MIPS_CPU_ULRI;
 		break;
-	case PRID_IMP_BMIPS4KC:
-		c->cputype = CPU_4KC;
-		__cpu_name[cpu] = "MIPS 4Kc";
-		break;
 	}
 }
 

arch/mips/kernel/linux32.c

@@ -251,14 +251,15 @@ SYSCALL_DEFINE5(n32_msgrcv, int, msqid, u32, msgp, size_t, msgsz,
 
 SYSCALL_DEFINE1(32_personality, unsigned long, personality)
 {
+	unsigned int p = personality & 0xffffffff;
 	int ret;
-	personality &= 0xffffffff;
+
 	if (personality(current->personality) == PER_LINUX32 &&
-	    personality == PER_LINUX)
-		personality = PER_LINUX32;
-	ret = sys_personality(personality);
-	if (ret == PER_LINUX32)
-		ret = PER_LINUX;
+	    personality(p) == PER_LINUX)
+		p = (p & ~PER_MASK) | PER_LINUX32;
+	ret = sys_personality(p);
+	if (ret != -1 && personality(ret) == PER_LINUX32)
+		ret = (ret & ~PER_MASK) | PER_LINUX;
 	return ret;
 }
 

arch/mips/kernel/process.c

@@ -142,7 +142,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	childregs->regs[7] = 0;	/* Clear error flag */
 
 	childregs->regs[2] = 0;	/* Child gets zero as return value */
-	regs->regs[2] = p->pid;
 
 	if (childregs->cp0_status & ST0_CU0) {
 		childregs->regs[28] = (unsigned long) ti;

arch/mips/kernel/prom.c

@@ -100,7 +100,7 @@ void __init device_tree_init(void)
 		return;
 
 	base = virt_to_phys((void *)initial_boot_params);
-	size = initial_boot_params->totalsize;
+	size = be32_to_cpu(initial_boot_params->totalsize);
 
 	/* Before we do anything, lets reserve the dt blob */
 	reserve_mem_mach(base, size);

arch/mips/kernel/smp-mt.c

@@ -153,7 +153,7 @@ static void __cpuinit vsmp_init_secondary(void)
 {
 	extern int gic_present;
 
-	/* This is Malta specific: IPI,performance and timer inetrrupts */
+	/* This is Malta specific: IPI,performance and timer interrupts */
 	if (gic_present)
 		change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 |
 					 STATUSF_IP6 | STATUSF_IP7);

arch/mips/kernel/traps.c

@@ -83,7 +83,8 @@ extern asmlinkage void handle_mcheck(void);
 extern asmlinkage void handle_reserved(void);
 
 extern int fpu_emulator_cop1Handler(struct pt_regs *xcp,
-	struct mips_fpu_struct *ctx, int has_fpu);
+				    struct mips_fpu_struct *ctx, int has_fpu,
+				    void *__user *fault_addr);
 
 void (*board_be_init)(void);
 int (*board_be_handler)(struct pt_regs *regs, int is_fixup);
@@ -661,12 +662,36 @@ asmlinkage void do_ov(struct pt_regs *regs)
 	force_sig_info(SIGFPE, &info, current);
 }
 
+static int process_fpemu_return(int sig, void __user *fault_addr)
+{
+	if (sig == SIGSEGV || sig == SIGBUS) {
+		struct siginfo si = {0};
+		si.si_addr = fault_addr;
+		si.si_signo = sig;
+		if (sig == SIGSEGV) {
+			if (find_vma(current->mm, (unsigned long)fault_addr))
+				si.si_code = SEGV_ACCERR;
+			else
+				si.si_code = SEGV_MAPERR;
+		} else {
+			si.si_code = BUS_ADRERR;
+		}
+		force_sig_info(sig, &si, current);
+		return 1;
+	} else if (sig) {
+		force_sig(sig, current);
+		return 1;
+	} else {
+		return 0;
+	}
+}
+
 /*
  * XXX Delayed fp exceptions when doing a lazy ctx switch XXX
  */
 asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 {
-	siginfo_t info;
+	siginfo_t info = {0};
 
 	if (notify_die(DIE_FP, "FP exception", regs, 0, regs_to_trapnr(regs), SIGFPE)
 	    == NOTIFY_STOP)
@@ -675,6 +700,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 
 	if (fcr31 & FPU_CSR_UNI_X) {
 		int sig;
+		void __user *fault_addr = NULL;
 
 		/*
 		 * Unimplemented operation exception.  If we've got the full
@@ -690,7 +716,8 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 		lose_fpu(1);
 
 		/* Run the emulator */
-		sig = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1);
+		sig = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1,
+					       &fault_addr);
 
 		/*
 		 * We can't allow the emulated instruction to leave any of
@@ -702,8 +729,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 		own_fpu(1);	/* Using the FPU again.  */
 
 		/* If something went wrong, signal */
-		if (sig)
-			force_sig(sig, current);
+		process_fpemu_return(sig, fault_addr);
 
 		return;
 	} else if (fcr31 & FPU_CSR_INV_X)
@@ -996,11 +1022,11 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 
 		if (!raw_cpu_has_fpu) {
 			int sig;
+			void __user *fault_addr = NULL;
 			sig = fpu_emulator_cop1Handler(regs,
-						&current->thread.fpu, 0);
-			if (sig)
-				force_sig(sig, current);
-			else
+						       &current->thread.fpu,
+						       0, &fault_addr);
+			if (!process_fpemu_return(sig, fault_addr))
 				mt_ase_fp_affinity();
 		}
 

arch/mips/kernel/vpe.c

@@ -1092,6 +1092,10 @@ static int vpe_open(struct inode *inode, struct file *filp)
 
 	/* this of-course trashes what was there before... */
 	v->pbuffer = vmalloc(P_SIZE);
+	if (!v->pbuffer) {
+		pr_warning("VPE loader: unable to allocate memory\n");
+		return -ENOMEM;
+	}
 	v->plen = P_SIZE;
 	v->load_addr = NULL;
 	v->len = 0;
@@ -1149,10 +1153,9 @@ static int vpe_release(struct inode *inode, struct file *filp)
 	if (ret < 0)
 		v->shared_ptr = NULL;
 
-	// cleanup any temp buffers
-	if (v->pbuffer)
-		vfree(v->pbuffer);
+	vfree(v->pbuffer);
 	v->plen = 0;
+
 	return ret;
 }
 
@@ -1169,11 +1172,6 @@ static ssize_t vpe_write(struct file *file, const char __user * buffer,
 	if (v == NULL)
 		return -ENODEV;
 
-	if (v->pbuffer == NULL) {
-		printk(KERN_ERR "VPE loader: no buffer for program\n");
-		return -ENOMEM;
-	}
-
 	if ((count + v->len) > v->plen) {
 		printk(KERN_WARNING
 		       "VPE loader: elf size too big. Perhaps strip uneeded symbols\n");

arch/mips/lib/memset.S

@@ -161,16 +161,16 @@ FEXPORT(__bzero)
 
 .Lfwd_fixup:
 	PTR_L		t0, TI_TASK($28)
-	LONG_L		t0, THREAD_BUADDR(t0)
 	andi		a2, 0x3f
+	LONG_L		t0, THREAD_BUADDR(t0)
 	LONG_ADDU	a2, t1
 	jr		ra
 	 LONG_SUBU	a2, t0
 
 .Lpartial_fixup:
 	PTR_L		t0, TI_TASK($28)
-	LONG_L		t0, THREAD_BUADDR(t0)
 	andi		a2, LONGMASK
+	LONG_L		t0, THREAD_BUADDR(t0)
 	LONG_ADDU	a2, t1
 	jr		ra
 	 LONG_SUBU	a2, t0

arch/mips/loongson/common/env.c

@@ -29,9 +29,9 @@ unsigned long memsize, highmemsize;
 
 #define parse_even_earlier(res, option, p)				\
 do {									\
+	int ret;							\
 	if (strncmp(option, (char *)p, strlen(option)) == 0)		\
-			strict_strtol((char *)p + strlen(option"="),	\
-					10, &res);			\
+		ret = strict_strtol((char *)p + strlen(option"="), 10, &res); \
 } while (0)
 
 void __init prom_init_env(void)

arch/mips/math-emu/cp1emu.c

@@ -64,7 +64,7 @@ static int fpu_emu(struct pt_regs *, struct mips_fpu_struct *,
 
 #if __mips >= 4 && __mips != 32
 static int fpux_emu(struct pt_regs *,
-	struct mips_fpu_struct *, mips_instruction);
+	struct mips_fpu_struct *, mips_instruction, void *__user *);
 #endif
 
 /* Further private data for which no space exists in mips_fpu_struct */
@@ -208,16 +208,23 @@ static inline int cop1_64bit(struct pt_regs *xcp)
  * Two instructions if the instruction is in a branch delay slot.
  */
 
-static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
+static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
+		       void *__user *fault_addr)
 {
 	mips_instruction ir;
 	unsigned long emulpc, contpc;
 	unsigned int cond;
 
-	if (get_user(ir, (mips_instruction __user *) xcp->cp0_epc)) {
+	if (!access_ok(VERIFY_READ, xcp->cp0_epc, sizeof(mips_instruction))) {
 		MIPS_FPU_EMU_INC_STATS(errors);
+		*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
 		return SIGBUS;
 	}
+	if (__get_user(ir, (mips_instruction __user *) xcp->cp0_epc)) {
+		MIPS_FPU_EMU_INC_STATS(errors);
+		*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
+		return SIGSEGV;
+	}
 
 	/* XXX NEC Vr54xx bug workaround */
 	if ((xcp->cp0_cause & CAUSEF_BD) && !isBranchInstr(&ir))
@@ -245,10 +252,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 #endif
 			return SIGILL;
 		}
-		if (get_user(ir, (mips_instruction __user *) emulpc)) {
+		if (!access_ok(VERIFY_READ, emulpc, sizeof(mips_instruction))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = (mips_instruction __user *)emulpc;
 			return SIGBUS;
 		}
+		if (__get_user(ir, (mips_instruction __user *) emulpc)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = (mips_instruction __user *)emulpc;
+			return SIGSEGV;
+		}
 		/* __compute_return_epc() will have updated cp0_epc */
 		contpc = xcp->cp0_epc;
 		/* In order not to confuse ptrace() et al, tweak context */
@@ -269,10 +282,17 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 		u64 val;
 
 		MIPS_FPU_EMU_INC_STATS(loads);
-		if (get_user(val, va)) {
+
+		if (!access_ok(VERIFY_READ, va, sizeof(u64))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
 			return SIGBUS;
 		}
+		if (__get_user(val, va)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
+			return SIGSEGV;
+		}
 		DITOREG(val, MIPSInst_RT(ir));
 		break;
 	}
@@ -284,10 +304,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 
 		MIPS_FPU_EMU_INC_STATS(stores);
 		DIFROMREG(val, MIPSInst_RT(ir));
-		if (put_user(val, va)) {
+		if (!access_ok(VERIFY_WRITE, va, sizeof(u64))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
 			return SIGBUS;
 		}
+		if (__put_user(val, va)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
+			return SIGSEGV;
+		}
 		break;
 	}
 
@@ -297,10 +323,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 		u32 val;
 
 		MIPS_FPU_EMU_INC_STATS(loads);
-		if (get_user(val, va)) {
+		if (!access_ok(VERIFY_READ, va, sizeof(u32))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
 			return SIGBUS;
 		}
+		if (__get_user(val, va)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
+			return SIGSEGV;
+		}
 		SITOREG(val, MIPSInst_RT(ir));
 		break;
 	}
@@ -312,10 +344,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 
 		MIPS_FPU_EMU_INC_STATS(stores);
 		SIFROMREG(val, MIPSInst_RT(ir));
-		if (put_user(val, va)) {
+		if (!access_ok(VERIFY_WRITE, va, sizeof(u32))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
 			return SIGBUS;
 		}
+		if (__put_user(val, va)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
+			return SIGSEGV;
+		}
 		break;
 	}
 
@@ -440,11 +478,18 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 				contpc = (xcp->cp0_epc +
 					(MIPSInst_SIMM(ir) << 2));
 
-				if (get_user(ir,
-				    (mips_instruction __user *) xcp->cp0_epc)) {
+				if (!access_ok(VERIFY_READ, xcp->cp0_epc,
+					       sizeof(mips_instruction))) {
 					MIPS_FPU_EMU_INC_STATS(errors);
+					*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
 					return SIGBUS;
 				}
+				if (__get_user(ir,
+				    (mips_instruction __user *) xcp->cp0_epc)) {
+					MIPS_FPU_EMU_INC_STATS(errors);
+					*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
+					return SIGSEGV;
+				}
 
 				switch (MIPSInst_OPCODE(ir)) {
 				case lwc1_op:
@@ -506,9 +551,8 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 
 #if __mips >= 4 && __mips != 32
 	case cop1x_op:{
-		int sig;
-
-		if ((sig = fpux_emu(xcp, ctx, ir)))
+		int sig = fpux_emu(xcp, ctx, ir, fault_addr);
+		if (sig)
 			return sig;
 		break;
 	}
@@ -604,7 +648,7 @@ DEF3OP(nmadd, dp, ieee754dp_mul, ieee754dp_add, ieee754dp_neg);
 DEF3OP(nmsub, dp, ieee754dp_mul, ieee754dp_sub, ieee754dp_neg);
 
 static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
-	mips_instruction ir)
+	mips_instruction ir, void *__user *fault_addr)
 {
 	unsigned rcsr = 0;	/* resulting csr */
 
@@ -624,10 +668,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 				xcp->regs[MIPSInst_FT(ir)]);
 
 			MIPS_FPU_EMU_INC_STATS(loads);
-			if (get_user(val, va)) {
+			if (!access_ok(VERIFY_READ, va, sizeof(u32))) {
 				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
 				return SIGBUS;
 			}
+			if (__get_user(val, va)) {
+				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
+				return SIGSEGV;
+			}
 			SITOREG(val, MIPSInst_FD(ir));
 			break;
 
@@ -638,10 +688,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			MIPS_FPU_EMU_INC_STATS(stores);
 
 			SIFROMREG(val, MIPSInst_FS(ir));
-			if (put_user(val, va)) {
+			if (!access_ok(VERIFY_WRITE, va, sizeof(u32))) {
 				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
 				return SIGBUS;
 			}
+			if (put_user(val, va)) {
+				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
+				return SIGSEGV;
+			}
 			break;
 
 		case madd_s_op:
@@ -701,10 +757,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 				xcp->regs[MIPSInst_FT(ir)]);
 
 			MIPS_FPU_EMU_INC_STATS(loads);
-			if (get_user(val, va)) {
+			if (!access_ok(VERIFY_READ, va, sizeof(u64))) {
 				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
 				return SIGBUS;
 			}
+			if (__get_user(val, va)) {
+				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
+				return SIGSEGV;
+			}
 			DITOREG(val, MIPSInst_FD(ir));
 			break;
 
@@ -714,10 +776,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 
 			MIPS_FPU_EMU_INC_STATS(stores);
 			DIFROMREG(val, MIPSInst_FS(ir));
-			if (put_user(val, va)) {
+			if (!access_ok(VERIFY_WRITE, va, sizeof(u64))) {
 				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
 				return SIGBUS;
 			}
+			if (__put_user(val, va)) {
+				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
+				return SIGSEGV;
+			}
 			break;
 
 		case madd_d_op:
@@ -1242,7 +1310,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 }
 
 int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
-	int has_fpu)
+	int has_fpu, void *__user *fault_addr)
 {
 	unsigned long oldepc, prevepc;
 	mips_instruction insn;
@@ -1252,10 +1320,16 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	do {
 		prevepc = xcp->cp0_epc;
 
-		if (get_user(insn, (mips_instruction __user *) xcp->cp0_epc)) {
+		if (!access_ok(VERIFY_READ, xcp->cp0_epc, sizeof(mips_instruction))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
 			return SIGBUS;
 		}
+		if (__get_user(insn, (mips_instruction __user *) xcp->cp0_epc)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
+			return SIGSEGV;
+		}
 		if (insn == 0)
 			xcp->cp0_epc += 4;	/* skip nops */
 		else {
@@ -1267,7 +1341,7 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			 */
 			/* convert to ieee library modes */
 			ieee754_csr.rm = ieee_rm[ieee754_csr.rm];
-			sig = cop1Emulate(xcp, ctx);
+			sig = cop1Emulate(xcp, ctx, fault_addr);
 			/* revert to mips rounding mode */
 			ieee754_csr.rm = mips_rm[ieee754_csr.rm];
 		}

arch/mips/mm/dma-default.c

@@ -288,7 +288,7 @@ int mips_dma_supported(struct device *dev, u64 mask)
 	return plat_dma_supported(dev, mask);
 }
 
-void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 			 enum dma_data_direction direction)
 {
 	BUG_ON(direction == DMA_NONE);
@@ -298,6 +298,8 @@ void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		__dma_sync((unsigned long)vaddr, size, direction);
 }
 
+EXPORT_SYMBOL(dma_cache_sync);
+
 static struct dma_map_ops mips_default_dma_map_ops = {
 	.alloc_coherent = mips_dma_alloc_coherent,
 	.free_coherent = mips_dma_free_coherent,

arch/mips/mm/sc-mips.c

@@ -68,6 +68,9 @@ static struct bcache_ops mips_sc_ops = {
  */
 static inline int mips_sc_is_activated(struct cpuinfo_mips *c)
 {
+	unsigned int config2 = read_c0_config2();
+	unsigned int tmp;
+
 	/* Check the bypass bit (L2B) */
 	switch (c->cputype) {
 	case CPU_34K:
@@ -83,6 +86,7 @@ static inline int mips_sc_is_activated(struct cpuinfo_mips *c)
 		c->scache.linesz = 2 << tmp;
 	else
 		return 0;
+	return 1;
 }
 
 static inline int __init mips_sc_probe(void)

arch/mips/pmc-sierra/yosemite/py-console.c

@@ -65,11 +65,15 @@ static unsigned char readb_outer_space(unsigned long long phys)
 
 	__asm__ __volatile__ (
 	"	.set	mips3		\n"
+	"	.set	push		\n"
+	"	.set	noreorder	\n"
+	"	.set	nomacro		\n"
 	"	ld	%0, %1		\n"
+	"	.set	pop		\n"
 	"	lbu	%0, (%0)	\n"
 	"	.set	mips0		\n"
 	: "=r" (res)
-	: "m" (vaddr));
+	: "R" (vaddr));
 
 	write_c0_status(sr);
 	ssnop_4();
@@ -89,11 +93,15 @@ static void writeb_outer_space(unsigned long long phys, unsigned char c)
 
 	__asm__ __volatile__ (
 	"	.set	mips3		\n"
+	"	.set	push		\n"
+	"	.set	noreorder	\n"
+	"	.set	nomacro		\n"
 	"	ld	%0, %1		\n"
+	"	.set	pop		\n"
 	"	sb	%2, (%0)	\n"
 	"	.set	mips0		\n"
 	: "=&r" (tmp)
-	: "m" (vaddr), "r" (c));
+	: "R" (vaddr), "r" (c));
 
 	write_c0_status(sr);
 	ssnop_4();

arch/mips/sibyte/swarm/setup.c

@@ -82,7 +82,7 @@ int swarm_be_handler(struct pt_regs *regs, int is_fixup)
 enum swarm_rtc_type {
 	RTC_NONE,
 	RTC_XICOR,
-	RTC_M4LT81
+	RTC_M41T81,
 };
 
 enum swarm_rtc_type swarm_rtc_type;
@@ -96,7 +96,7 @@ void read_persistent_clock(struct timespec *ts)
 		sec = xicor_get_time();
 		break;
 
-	case RTC_M4LT81:
+	case RTC_M41T81:
 		sec = m41t81_get_time();
 		break;
 
@@ -115,7 +115,7 @@ int rtc_mips_set_time(unsigned long sec)
 	case RTC_XICOR:
 		return xicor_set_time(sec);
 
-	case RTC_M4LT81:
+	case RTC_M41T81:
 		return m41t81_set_time(sec);
 
 	case RTC_NONE:
@@ -141,7 +141,7 @@ void __init plat_mem_setup(void)
 	if (xicor_probe())
 		swarm_rtc_type = RTC_XICOR;
 	if (m41t81_probe())
-		swarm_rtc_type = RTC_M4LT81;
+		swarm_rtc_type = RTC_M41T81;
 
 #ifdef CONFIG_VT
 	screen_info = (struct screen_info) {

arch/mn10300/kernel/irq.c

@@ -459,7 +459,7 @@ void migrate_irqs(void)
 			tmp = CROSS_GxICR(irq, new);
 
 			x &= GxICR_LEVEL | GxICR_ENABLE;
-			if (GxICR(irq) & GxICR_REQUEST) {
+			if (GxICR(irq) & GxICR_REQUEST)
 				x |= GxICR_REQUEST | GxICR_DETECT;
 			CROSS_GxICR(irq, new) = x;
 			tmp = CROSS_GxICR(irq, new);

arch/mn10300/kernel/time.c

@@ -40,21 +40,17 @@ unsigned long long sched_clock(void)
 		unsigned long long ll;
 		unsigned l[2];
 	} tsc64, result;
-	unsigned long tsc, tmp;
+	unsigned long tmp;
 	unsigned product[3]; /* 96-bit intermediate value */
 
 	/* cnt32_to_63() is not safe with preemption */
 	preempt_disable();
 
-	/* read the TSC value
-	 */
-	tsc = get_cycles();
-
-	/* expand to 64-bits.
+	/* expand the tsc to 64-bits.
 	 * - sched_clock() must be called once a minute or better or the
 	 *   following will go horribly wrong - see cnt32_to_63()
 	 */
-	tsc64.ll = cnt32_to_63(tsc) & 0x7fffffffffffffffULL;
+	tsc64.ll = cnt32_to_63(get_cycles()) & 0x7fffffffffffffffULL;
 
 	preempt_enable();
 

arch/powerpc/platforms/52xx/mpc52xx_gpt.c

@@ -63,6 +63,7 @@
 #include <linux/of_gpio.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/fs.h>
 #include <linux/watchdog.h>
 #include <linux/miscdevice.h>
 #include <linux/uaccess.h>

arch/sh/boards/mach-se/7206/irq.c

@@ -140,7 +140,7 @@ void __init init_se7206_IRQ(void)
 	make_se7206_irq(IRQ1_IRQ); /* ATA */
 	make_se7206_irq(IRQ3_IRQ); /* SLOT / PCM */
 
-	__raw_writew(__raw_readw(INTC_ICR1) | 0x000b, INTC_ICR); /* ICR1 */
+	__raw_writew(__raw_readw(INTC_ICR1) | 0x000b, INTC_ICR1); /* ICR1 */
 
 	/* FPGA System register setup*/
 	__raw_writew(0x0000,INTSTS0); /* Clear INTSTS0 */

arch/sh/kernel/cpu/sh2a/clock-sh7201.c

@@ -34,7 +34,7 @@ static const int pfc_divisors[]={1,2,3,4,6,8,12};
 
 static void master_clk_init(struct clk *clk)
 {
-	return 10000000 * PLL2 * pll1rate[(__raw_readw(FREQCR) >> 8) & 0x0007];
+	clk->rate = 10000000 * PLL2 * pll1rate[(__raw_readw(FREQCR) >> 8) & 0x0007];
 }
 
 static struct clk_ops sh7201_master_clk_ops = {

arch/sh/kernel/cpu/sh4/clock-sh4-202.c

@@ -81,8 +81,7 @@ static void shoc_clk_init(struct clk *clk)
 	for (i = 0; i < ARRAY_SIZE(frqcr3_divisors); i++) {
 		int divisor = frqcr3_divisors[i];
 
-		if (clk->ops->set_rate(clk, clk->parent->rate /
-						divisor, 0) == 0)
+		if (clk->ops->set_rate(clk, clk->parent->rate / divisor) == 0)
 			break;
 	}
 

arch/tile/include/asm/signal.h

@@ -25,7 +25,7 @@
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 struct pt_regs;
-int restore_sigcontext(struct pt_regs *, struct sigcontext __user *, long *);
+int restore_sigcontext(struct pt_regs *, struct sigcontext __user *);
 int setup_sigcontext(struct sigcontext __user *, struct pt_regs *);
 void do_signal(struct pt_regs *regs);
 #endif

arch/tile/kernel/compat_signal.c

@@ -290,12 +290,12 @@ long compat_sys_sigaltstack(const struct compat_sigaltstack __user *uss_ptr,
 	return ret;
 }
 
+/* The assembly shim for this function arranges to ignore the return value. */
 long compat_sys_rt_sigreturn(struct pt_regs *regs)
 {
 	struct compat_rt_sigframe __user *frame =
 		(struct compat_rt_sigframe __user *) compat_ptr(regs->sp);
 	sigset_t set;
-	long r0;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
@@ -308,13 +308,13 @@ long compat_sys_rt_sigreturn(struct pt_regs *regs)
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
 
-	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &r0))
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
 		goto badframe;
 
 	if (compat_sys_sigaltstack(&frame->uc.uc_stack, NULL, regs) != 0)
 		goto badframe;
 
-	return r0;
+	return 0;
 
 badframe:
 	force_sig(SIGSEGV, current);

arch/tile/kernel/intvec_32.S

@@ -1342,8 +1342,8 @@ handle_syscall:
 	lw      r20, r20
 
 	/* Jump to syscall handler. */
-	jalr    r20; .Lhandle_syscall_link:
-	FEEDBACK_REENTER(handle_syscall)
+	jalr    r20
+.Lhandle_syscall_link: /* value of "lr" after "jalr r20" above */
 
 	/*
 	 * Write our r0 onto the stack so it gets restored instead
@@ -1352,6 +1352,9 @@ handle_syscall:
 	PTREGS_PTR(r29, PTREGS_OFFSET_REG(0))
 	sw      r29, r0
 
+.Lsyscall_sigreturn_skip:
+	FEEDBACK_REENTER(handle_syscall)
+
 	/* Do syscall trace again, if requested. */
 	lw	r30, r31
 	andi    r30, r30, _TIF_SYSCALL_TRACE
@@ -1536,9 +1539,24 @@ STD_ENTRY_LOCAL(bad_intr)
 	};                                              \
 	STD_ENDPROC(_##x)
 
+/*
+ * Special-case sigreturn to not write r0 to the stack on return.
+ * This is technically more efficient, but it also avoids difficulties
+ * in the 64-bit OS when handling 32-bit compat code, since we must not
+ * sign-extend r0 for the sigreturn return-value case.
+ */
+#define PTREGS_SYSCALL_SIGRETURN(x, reg)                \
+	STD_ENTRY(_##x);                                \
+	addli   lr, lr, .Lsyscall_sigreturn_skip - .Lhandle_syscall_link; \
+	{                                               \
+	 PTREGS_PTR(reg, PTREGS_OFFSET_BASE);           \
+	 j      x                                       \
+	};                                              \
+	STD_ENDPROC(_##x)
+
 PTREGS_SYSCALL(sys_execve, r3)
 PTREGS_SYSCALL(sys_sigaltstack, r2)
-PTREGS_SYSCALL(sys_rt_sigreturn, r0)
+PTREGS_SYSCALL_SIGRETURN(sys_rt_sigreturn, r0)
 PTREGS_SYSCALL(sys_cmpxchg_badaddr, r1)
 
 /* Save additional callee-saves to pt_regs, put address in r4 and jump. */

arch/tile/kernel/process.c

@@ -211,6 +211,13 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	childregs->regs[0] = 0;         /* return value is zero */
 	childregs->sp = sp;  /* override with new user stack pointer */
 
+	/*
+	 * If CLONE_SETTLS is set, set "tp" in the new task to "r4",
+	 * which is passed in as arg #5 to sys_clone().
+	 */
+	if (clone_flags & CLONE_SETTLS)
+		childregs->tp = regs->regs[4];
+
 	/*
 	 * Copy the callee-saved registers from the passed pt_regs struct
 	 * into the context-switch callee-saved registers area.
@@ -539,6 +546,7 @@ struct task_struct *__sched _switch_to(struct task_struct *prev,
 	return __switch_to(prev, next, next_current_ksp0(next));
 }
 
+/* Note there is an implicit fifth argument if (clone_flags & CLONE_SETTLS). */
 SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		void __user *, parent_tidptr, void __user *, child_tidptr,
 		struct pt_regs *, regs)

arch/tile/kernel/signal.c

@@ -52,7 +52,7 @@ SYSCALL_DEFINE3(sigaltstack, const stack_t __user *, uss,
  */
 
 int restore_sigcontext(struct pt_regs *regs,
-		       struct sigcontext __user *sc, long *pr0)
+		       struct sigcontext __user *sc)
 {
 	int err = 0;
 	int i;
@@ -75,17 +75,15 @@ int restore_sigcontext(struct pt_regs *regs,
 
 	regs->faultnum = INT_SWINT_1_SIGRETURN;
 
-	err |= __get_user(*pr0, &sc->gregs[0]);
 	return err;
 }
 
-/* sigreturn() returns long since it restores r0 in the interrupted code. */
+/* The assembly shim for this function arranges to ignore the return value. */
 SYSCALL_DEFINE1(rt_sigreturn, struct pt_regs *, regs)
 {
 	struct rt_sigframe __user *frame =
 		(struct rt_sigframe __user *)(regs->sp);
 	sigset_t set;
-	long r0;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
@@ -98,13 +96,13 @@ SYSCALL_DEFINE1(rt_sigreturn, struct pt_regs *, regs)
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
 
-	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &r0))
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
 		goto badframe;
 
 	if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT)
 		goto badframe;
 
-	return r0;
+	return 0;
 
 badframe:
 	force_sig(SIGSEGV, current);

arch/x86/boot/compressed/misc.c

@@ -355,7 +355,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	if (heap > 0x3fffffffffffUL)
 		error("Destination address too large");
 #else
-	if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff))
+	if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff))
 		error("Destination address too large");
 #endif
 #ifndef CONFIG_RELOCATABLE

arch/x86/include/asm/e820.h

@@ -72,6 +72,9 @@ struct e820map {
 #define BIOS_BEGIN		0x000a0000
 #define BIOS_END		0x00100000
 
+#define BIOS_ROM_BASE		0xffe00000
+#define BIOS_ROM_END		0xffffffff
+
 #ifdef __KERNEL__
 /* see comment in arch/x86/kernel/e820.c */
 extern struct e820map e820;

arch/x86/include/asm/kvm_host.h

@@ -79,7 +79,7 @@
 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
-#define KVM_MAX_CPUID_ENTRIES 40
+#define KVM_MAX_CPUID_ENTRIES 80
 #define KVM_NR_FIXED_MTRR_REGION 88
 #define KVM_NR_VAR_MTRR 8
 

arch/x86/kernel/Makefile

@@ -45,6 +45,7 @@ obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
 obj-y			+= tsc.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
+obj-y			+= resource.o
 
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y				+= process.o

arch/x86/kernel/apic/apic.c

@@ -1389,6 +1389,14 @@ void __cpuinit end_local_APIC_setup(void)
 
 	setup_apic_nmi_watchdog(NULL);
 	apic_pm_activate();
+
+	/*
+	 * Now that local APIC setup is completed for BP, configure the fault
+	 * handling for interrupt remapping.
+	 */
+	if (!smp_processor_id() && intr_remapping_enabled)
+		enable_drhd_fault_handling();
+
 }
 
 #ifdef CONFIG_X86_X2APIC

arch/x86/kernel/apic/io_apic.c

@@ -2430,13 +2430,12 @@ static void ack_apic_level(struct irq_data *data)
 {
 	struct irq_cfg *cfg = data->chip_data;
 	int i, do_unmask_irq = 0, irq = data->irq;
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long v;
 
 	irq_complete_move(cfg);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	/* If we are moving the irq we need to mask it */
-	if (unlikely(desc->status & IRQ_MOVE_PENDING)) {
+	if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
 		do_unmask_irq = 1;
 		mask_ioapic(cfg);
 	}
@@ -3413,6 +3412,7 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	msg.data |= MSI_DATA_VECTOR(cfg->vector);
 	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+	msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
 
 	dmar_msi_write(irq, &msg);
 

arch/x86/kernel/apic/probe_64.c

@@ -79,13 +79,6 @@ void __init default_setup_apic_routing(void)
 		/* need to update phys_pkg_id */
 		apic->phys_pkg_id = apicid_phys_pkg_id;
 	}
-
-	/*
-	 * Now that apic routing model is selected, configure the
-	 * fault handling for intr remapping.
-	 */
-	if (intr_remapping_enabled)
-		enable_drhd_fault_handling();
 }
 
 /* Same for both flat and physical. */

arch/x86/kernel/head_32.S

@@ -60,16 +60,18 @@
 #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
 #endif
 
+/* Number of possible pages in the lowmem region */
+LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT)
+	
 /* Enough space to fit pagetables for the low memory linear map */
-MAPPING_BEYOND_END = \
-	PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT
+MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
 
 /*
  * Worst-case size of the kernel mapping we need to make:
- * the worst-case size of the kernel itself, plus the extra we need
- * to map for the linear map.
+ * a relocatable kernel can live anywhere in lowmem, so we need to be able
+ * to map all of lowmem.
  */
-KERNEL_PAGES = (KERNEL_IMAGE_SIZE + MAPPING_BEYOND_END)>>PAGE_SHIFT
+KERNEL_PAGES = LOWMEM_PAGES
 
 INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm
 RESERVE_BRK(pagetables, INIT_MAP_SIZE)
@@ -620,13 +622,13 @@ ENTRY(initial_code)
 __PAGE_ALIGNED_BSS
 	.align PAGE_SIZE_asm
 #ifdef CONFIG_X86_PAE
-initial_pg_pmd:
+ENTRY(initial_pg_pmd)
 	.fill 1024*KPMDS,4,0
 #else
 ENTRY(initial_page_table)
 	.fill 1024,4,0
 #endif
-initial_pg_fixmap:
+ENTRY(initial_pg_fixmap)
 	.fill 1024,4,0
 ENTRY(empty_zero_page)
 	.fill 4096,1,0

arch/x86/kernel/hpet.c

@@ -27,6 +27,9 @@
 #define HPET_DEV_FSB_CAP		0x1000
 #define HPET_DEV_PERI_CAP		0x2000
 
+#define HPET_MIN_CYCLES			128
+#define HPET_MIN_PROG_DELTA		(HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
+
 #define EVT_TO_HPET_DEV(evt) container_of(evt, struct hpet_dev, evt)
 
 /*
@@ -299,8 +302,9 @@ static void hpet_legacy_clockevent_register(void)
 	/* Calculate the min / max delta */
 	hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
 							   &hpet_clockevent);
-	/* 5 usec minimum reprogramming delta. */
-	hpet_clockevent.min_delta_ns = 5000;
+	/* Setup minimum reprogramming delta. */
+	hpet_clockevent.min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA,
+							   &hpet_clockevent);
 
 	/*
 	 * Start hpet with the boot cpu mask and make it
@@ -393,22 +397,24 @@ static int hpet_next_event(unsigned long delta,
 	 * the wraparound into account) nor a simple count down event
 	 * mode. Further the write to the comparator register is
 	 * delayed internally up to two HPET clock cycles in certain
-	 * chipsets (ATI, ICH9,10). We worked around that by reading
-	 * back the compare register, but that required another
-	 * workaround for ICH9,10 chips where the first readout after
-	 * write can return the old stale value. We already have a
-	 * minimum delta of 5us enforced, but a NMI or SMI hitting
+	 * chipsets (ATI, ICH9,10). Some newer AMD chipsets have even
+	 * longer delays. We worked around that by reading back the
+	 * compare register, but that required another workaround for
+	 * ICH9,10 chips where the first readout after write can
+	 * return the old stale value. We already had a minimum
+	 * programming delta of 5us enforced, but a NMI or SMI hitting
 	 * between the counter readout and the comparator write can
 	 * move us behind that point easily. Now instead of reading
 	 * the compare register back several times, we make the ETIME
 	 * decision based on the following: Return ETIME if the
-	 * counter value after the write is less than 8 HPET cycles
+	 * counter value after the write is less than HPET_MIN_CYCLES
 	 * away from the event or if the counter is already ahead of
-	 * the event.
+	 * the event. The minimum programming delta for the generic
+	 * clockevents code is set to 1.5 * HPET_MIN_CYCLES.
 	 */
 	res = (s32)(cnt - hpet_readl(HPET_COUNTER));
 
-	return res < 8 ? -ETIME : 0;
+	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
 
 static void hpet_legacy_set_mode(enum clock_event_mode mode,

arch/x86/kernel/microcode_intel.c

@@ -364,8 +364,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 
 		/* For performance reasons, reuse mc area when possible */
 		if (!mc || mc_size > curr_mc_size) {
-			if (mc)
-				vfree(mc);
+			vfree(mc);
 			mc = vmalloc(mc_size);
 			if (!mc)
 				break;
@@ -374,13 +373,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 
 		if (get_ucode_data(mc, ucode_ptr, mc_size) ||
 		    microcode_sanity_check(mc) < 0) {
-			vfree(mc);
 			break;
 		}
 
 		if (get_matching_microcode(&uci->cpu_sig, mc, new_rev)) {
-			if (new_mc)
-				vfree(new_mc);
+			vfree(new_mc);
 			new_rev = mc_header.rev;
 			new_mc  = mc;
 			mc = NULL;	/* trigger new vmalloc */
@@ -390,12 +387,10 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 		leftover  -= mc_size;
 	}
 
-	if (mc)
-		vfree(mc);
+	vfree(mc);
 
 	if (leftover) {
-		if (new_mc)
-			vfree(new_mc);
+		vfree(new_mc);
 		state = UCODE_ERROR;
 		goto out;
 	}
@@ -405,8 +400,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 		goto out;
 	}
 
-	if (uci->mc)
-		vfree(uci->mc);
+	vfree(uci->mc);
 	uci->mc = (struct microcode_intel *)new_mc;
 
 	pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",

arch/x86/kernel/resource.c

+#include <linux/ioport.h>
+#include <asm/e820.h>
+
+static void resource_clip(struct resource *res, resource_size_t start,
+			  resource_size_t end)
+{
+	resource_size_t low = 0, high = 0;
+
+	if (res->end < start || res->start > end)
+		return;		/* no conflict */
+
+	if (res->start < start)
+		low = start - res->start;
+
+	if (res->end > end)
+		high = res->end - end;
+
+	/* Keep the area above or below the conflict, whichever is larger */
+	if (low > high)
+		res->end = start - 1;
+	else
+		res->start = end + 1;
+}
+
+static void remove_e820_regions(struct resource *avail)
+{
+	int i;
+	struct e820entry *entry;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		entry = &e820.map[i];
+
+		resource_clip(avail, entry->addr,
+			      entry->addr + entry->size - 1);
+	}
+}
+
+void arch_remove_reservations(struct resource *avail)
+{
+	/* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+	if (avail->flags & IORESOURCE_MEM) {
+		if (avail->start < BIOS_END)
+			avail->start = BIOS_END;
+		resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
+
+		remove_e820_regions(avail);
+	}
+}

arch/x86/kernel/setup.c

@@ -501,7 +501,18 @@ static inline unsigned long long get_total_mem(void)
 	return total << PAGE_SHIFT;
 }
 
-#define DEFAULT_BZIMAGE_ADDR_MAX 0x37FFFFFF
+/*
+ * Keep the crash kernel below this limit.  On 32 bits earlier kernels
+ * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * On 64 bits, kexec-tools currently limits us to 896 MiB; increase this
+ * limit once kexec-tools are fixed.
+ */
+#ifdef CONFIG_X86_32
+# define CRASH_KERNEL_ADDR_MAX	(512 << 20)
+#else
+# define CRASH_KERNEL_ADDR_MAX	(896 << 20)
+#endif
+
 static void __init reserve_crashkernel(void)
 {
 	unsigned long long total_mem;
@@ -520,10 +531,10 @@ static void __init reserve_crashkernel(void)
 		const unsigned long long alignment = 16<<20;	/* 16M */
 
 		/*
-		 *  kexec want bzImage is below DEFAULT_BZIMAGE_ADDR_MAX
+		 *  kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
 		 */
 		crash_base = memblock_find_in_range(alignment,
-			       DEFAULT_BZIMAGE_ADDR_MAX, crash_size, alignment);
+			       CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
 
 		if (crash_base == MEMBLOCK_ERROR) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
@@ -769,7 +780,6 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_init.oem.arch_setup();
 
-	resource_alloc_from_bottom = 0;
 	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
 	setup_memory_map();
 	parse_setup_data();

arch/x86/kernel/xsave.c

@@ -394,7 +394,8 @@ static void __init setup_xstate_init(void)
 	 * Setup init_xstate_buf to represent the init state of
 	 * all the features managed by the xsave
 	 */
-	init_xstate_buf = alloc_bootmem(xstate_size);
+	init_xstate_buf = alloc_bootmem_align(xstate_size,
+					      __alignof__(struct xsave_struct));
 	init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT;
 
 	clts();

arch/x86/kvm/i8259.c

@@ -575,6 +575,8 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm)
 	s->pics[1].elcr_mask = 0xde;
 	s->pics[0].pics_state = s;
 	s->pics[1].pics_state = s;
+	s->pics[0].isr_ack = 0xff;
+	s->pics[1].isr_ack = 0xff;
 
 	/*
 	 * Initialize PIO device

arch/x86/kvm/mmu.c

@@ -2394,7 +2394,8 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 			ASSERT(!VALID_PAGE(root));
 			spin_lock(&vcpu->kvm->mmu_lock);
 			kvm_mmu_free_some_pages(vcpu);
-			sp = kvm_mmu_get_page(vcpu, i << 30, i << 30,
+			sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
+					      i << 30,
 					      PT32_ROOT_LEVEL, 1, ACC_ALL,
 					      NULL);
 			root = __pa(sp->spt);

arch/x86/kvm/svm.c

@@ -3494,6 +3494,10 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
 	switch (func) {
+	case 0x00000001:
+		/* Mask out xsave bit as long as it is not supported by SVM */
+		entry->ecx &= ~(bit(X86_FEATURE_XSAVE));
+		break;
 	case 0x80000001:
 		if (nested)
 			entry->ecx |= (1 << 2); /* Set SVM bit */

arch/x86/kvm/vmx.c

@@ -4227,11 +4227,6 @@ static int vmx_get_lpage_level(void)
 		return PT_PDPE_LEVEL;
 }
 
-static inline u32 bit(int bitno)
-{
-	return 1 << (bitno & 31);
-}
-
 static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;

arch/x86/kvm/x86.c

@@ -155,11 +155,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 u64 __read_mostly host_xcr0;
 
-static inline u32 bit(int bitno)
-{
-	return 1 << (bitno & 31);
-}
-
 static void kvm_on_user_return(struct user_return_notifier *urn)
 {
 	unsigned slot;
@@ -4569,9 +4564,11 @@ static void kvm_timer_init(void)
 #ifdef CONFIG_CPU_FREQ
 		struct cpufreq_policy policy;
 		memset(&policy, 0, sizeof(policy));
-		cpufreq_get_policy(&policy, get_cpu());
+		cpu = get_cpu();
+		cpufreq_get_policy(&policy, cpu);
 		if (policy.cpuinfo.max_freq)
 			max_tsc_khz = policy.cpuinfo.max_freq;
+		put_cpu();
 #endif
 		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
 					  CPUFREQ_TRANSITION_NOTIFIER);
@@ -5522,6 +5519,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
 	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
+	if (sregs->cr4 & X86_CR4_OSXSAVE)
+		update_cpuid(vcpu);
 	if (!is_long_mode(vcpu) && is_pae(vcpu)) {
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3);
 		mmu_reset_needed = 1;

arch/x86/kvm/x86.h

@@ -70,6 +70,11 @@ static inline int is_paging(struct kvm_vcpu *vcpu)
 	return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
 }
 
+static inline u32 bit(int bitno)
+{
+	return 1 << (bitno & 31);
+}
+
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
 int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq);

arch/x86/lguest/boot.c

@@ -531,7 +531,10 @@ static void lguest_write_cr3(unsigned long cr3)
 {
 	lguest_data.pgdir = cr3;
 	lazy_hcall1(LHCALL_NEW_PGTABLE, cr3);
-	cr3_changed = true;
+
+	/* These two page tables are simple, linear, and used during boot */
+	if (cr3 != __pa(swapper_pg_dir) && cr3 != __pa(initial_page_table))
+		cr3_changed = true;
 }
 
 static unsigned long lguest_read_cr3(void)
@@ -703,9 +706,9 @@ static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval)
  * to forget all of them.  Fortunately, this is very rare.
  *
  * ... except in early boot when the kernel sets up the initial pagetables,
- * which makes booting astonishingly slow: 1.83 seconds!  So we don't even tell
- * the Host anything changed until we've done the first page table switch,
- * which brings boot back to 0.25 seconds.
+ * which makes booting astonishingly slow: 48 seconds!  So we don't even tell
+ * the Host anything changed until we've done the first real page table switch,
+ * which brings boot back to 4.3 seconds.
  */
 static void lguest_set_pte(pte_t *ptep, pte_t pteval)
 {
@@ -1002,7 +1005,7 @@ static void lguest_time_init(void)
 	clockevents_register_device(&lguest_clockevent);
 
 	/* Finally, we unblock the timer interrupt. */
-	enable_lguest_irq(0);
+	clear_bit(0, lguest_data.blocked_interrupts);
 }
 
 /*
@@ -1349,9 +1352,6 @@ __init void lguest_init(void)
 	 */
 	switch_to_new_gdt(0);
 
-	/* We actually boot with all memory mapped, but let's say 128MB. */
-	max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT;
-
 	/*
 	 * The Host<->Guest Switcher lives at the top of our address space, and
 	 * the Host told us how big it is when we made LGUEST_INIT hypercall:

arch/x86/lguest/i386_head.S

@@ -4,6 +4,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/processor-flags.h>
+#include <asm/pgtable.h>
 
 /*G:020
  * Our story starts with the kernel booting into startup_32 in
@@ -37,9 +38,113 @@ ENTRY(lguest_entry)
 	/* Set up the initial stack so we can run C code. */
 	movl $(init_thread_union+THREAD_SIZE),%esp
 
+	call init_pagetables
+
 	/* Jumps are relative: we're running __PAGE_OFFSET too low. */
 	jmp lguest_init+__PAGE_OFFSET
 
+/*
+ * Initialize page tables.  This creates a PDE and a set of page
+ * tables, which are located immediately beyond __brk_base.  The variable
+ * _brk_end is set up to point to the first "safe" location.
+ * Mappings are created both at virtual address 0 (identity mapping)
+ * and PAGE_OFFSET for up to _end.
+ *
+ * FIXME: This code is taken verbatim from arch/x86/kernel/head_32.S: they
+ * don't have a stack at this point, so we can't just use call and ret.
+ */
+init_pagetables:
+#if PTRS_PER_PMD > 1
+#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)
+#else
+#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
+#endif
+#define pa(X) ((X) - __PAGE_OFFSET)
+
+/* Enough space to fit pagetables for the low memory linear map */
+MAPPING_BEYOND_END = \
+	PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT
+#ifdef CONFIG_X86_PAE
+
+	/*
+	 * In PAE mode initial_page_table is statically defined to contain
+	 * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3
+	 * entries). The identity mapping is handled by pointing two PGD entries
+	 * to the first kernel PMD.
+	 *
+	 * Note the upper half of each PMD or PTE are always zero at this stage.
+	 */
+
+#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
+
+	xorl %ebx,%ebx				/* %ebx is kept at zero */
+
+	movl $pa(__brk_base), %edi
+	movl $pa(initial_pg_pmd), %edx
+	movl $PTE_IDENT_ATTR, %eax
+10:
+	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PMD entry */
+	movl %ecx,(%edx)			/* Store PMD entry */
+						/* Upper half already zero */
+	addl $8,%edx
+	movl $512,%ecx
+11:
+	stosl
+	xchgl %eax,%ebx
+	stosl
+	xchgl %eax,%ebx
+	addl $0x1000,%eax
+	loop 11b
+
+	/*
+	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
+	 */
+	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
+	cmpl %ebp,%eax
+	jb 10b
+1:
+	addl $__PAGE_OFFSET, %edi
+	movl %edi, pa(_brk_end)
+	shrl $12, %eax
+	movl %eax, pa(max_pfn_mapped)
+
+	/* Do early initialization of the fixmap area */
+	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+	movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8)
+#else	/* Not PAE */
+
+page_pde_offset = (__PAGE_OFFSET >> 20);
+
+	movl $pa(__brk_base), %edi
+	movl $pa(initial_page_table), %edx
+	movl $PTE_IDENT_ATTR, %eax
+10:
+	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PDE entry */
+	movl %ecx,(%edx)			/* Store identity PDE entry */
+	movl %ecx,page_pde_offset(%edx)		/* Store kernel PDE entry */
+	addl $4,%edx
+	movl $1024, %ecx
+11:
+	stosl
+	addl $0x1000,%eax
+	loop 11b
+	/*
+	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
+	 */
+	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
+	cmpl %ebp,%eax
+	jb 10b
+	addl $__PAGE_OFFSET, %edi
+	movl %edi, pa(_brk_end)
+	shrl $12, %eax
+	movl %eax, pa(max_pfn_mapped)
+
+	/* Do early initialization of the fixmap area */
+	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+	movl %eax,pa(initial_page_table+0xffc)
+#endif
+	ret
+
 /*G:055
  * We create a macro which puts the assembler code between lgstart_ and lgend_
  * markers.  These templates are put in the .text section: they can't be

arch/x86/oprofile/op_model_amd.c

@@ -630,21 +630,29 @@ static int __init_ibs_nmi(void)
 	return 0;
 }
 
-/* initialize the APIC for the IBS interrupts if available */
+/*
+ * check and reserve APIC extended interrupt LVT offset for IBS if
+ * available
+ *
+ * init_ibs() preforms implicitly cpu-local operations, so pin this
+ * thread to its current CPU
+ */
+
 static void init_ibs(void)
 {
-	ibs_caps = get_ibs_caps();
+	preempt_disable();
 
+	ibs_caps = get_ibs_caps();
 	if (!ibs_caps)
-		return;
+		goto out;
 
-	if (__init_ibs_nmi()) {
+	if (__init_ibs_nmi() < 0)
 		ibs_caps = 0;
-		return;
-	}
+	else
+		printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
 
-	printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n",
-	       (unsigned)ibs_caps);
+out:
+	preempt_enable();
 }
 
 static int (*create_arch_files)(struct super_block *sb, struct dentry *root);

arch/x86/pci/i386.c

@@ -65,21 +65,13 @@ pcibios_align_resource(void *data, const struct resource *res,
 			resource_size_t size, resource_size_t align)
 {
 	struct pci_dev *dev = data;
-	resource_size_t start = round_down(res->end - size + 1, align);
+	resource_size_t start = res->start;
 
 	if (res->flags & IORESOURCE_IO) {
-
-		/*
-		 * If we're avoiding ISA aliases, the largest contiguous I/O
-		 * port space is 256 bytes.  Clearing bits 9 and 10 preserves
-		 * all 256-byte and smaller alignments, so the result will
-		 * still be correctly aligned.
-		 */
-		if (!skip_isa_ioresource_align(dev))
-			start &= ~0x300;
-	} else if (res->flags & IORESOURCE_MEM) {
-		if (start < BIOS_END)
-			start = res->end;	/* fail; no space */
+		if (skip_isa_ioresource_align(dev))
+			return start;
+		if (start & 0x300)
+			start = (start + 0x3ff) & ~0x3ff;
 	}
 	return start;
 }