Merge branch 'master' of /repos/git/net-next-2.6

Conflicts: net/bridge/br_device.c net/bridge/br_forward.c Signed-off-by: Patrick McHardy <kaber@trash.net>
2010-05-10 18:39:28 +02:00 · 2010-05-10 18:39:28 +02:00 · 1e4b105712
parent 3b254c54ec 3ee943728f
commit 1e4b105712
744 changed files with 38167 additions and 17720 deletions
--- a/Documentation/RCU/NMI-RCU.txt
+++ b/Documentation/RCU/NMI-RCU.txt
@ -34,7 +34,7 @@ NMI handler.
 		cpu = smp_processor_id();
 		++nmi_count(cpu);

-		if (!rcu_dereference(nmi_callback)(regs, cpu))
+		if (!rcu_dereference_sched(nmi_callback)(regs, cpu))
 			default_do_nmi(regs);

 		nmi_exit();
@ -47,12 +47,13 @@ function pointer.  If this handler returns zero, do_nmi() invokes the
 default_do_nmi() function to handle a machine-specific NMI.  Finally,
 preemption is restored.

-Strictly speaking, rcu_dereference() is not needed, since this code runs
-only on i386, which does not need rcu_dereference() anyway.  However,
-it is a good documentation aid, particularly for anyone attempting to
-do something similar on Alpha.
+In theory, rcu_dereference_sched() is not needed, since this code runs
+only on i386, which in theory does not need rcu_dereference_sched()
+anyway.  However, in practice it is a good documentation aid, particularly
+for anyone attempting to do something similar on Alpha or on systems
+with aggressive optimizing compilers.

-Quick Quiz:  Why might the rcu_dereference() be necessary on Alpha,
+Quick Quiz:  Why might the rcu_dereference_sched() be necessary on Alpha,
 	     given that the code referenced by the pointer is read-only?


@ -99,17 +100,21 @@ invoke irq_enter() and irq_exit() on NMI entry and exit, respectively.

 Answer to Quick Quiz

-	Why might the rcu_dereference() be necessary on Alpha, given
+	Why might the rcu_dereference_sched() be necessary on Alpha, given
 	that the code referenced by the pointer is read-only?

 	Answer: The caller to set_nmi_callback() might well have
-		initialized some data that is to be used by the
-		new NMI handler.  In this case, the rcu_dereference()
-		would be needed, because otherwise a CPU that received
-		an NMI just after the new handler was set might see
-		the pointer to the new NMI handler, but the old
-		pre-initialized version of the handler's data.
+		initialized some data that is to be used by the new NMI
+		handler.  In this case, the rcu_dereference_sched() would
+		be needed, because otherwise a CPU that received an NMI
+		just after the new handler was set might see the pointer
+		to the new NMI handler, but the old pre-initialized
+		version of the handler's data.

-		More important, the rcu_dereference() makes it clear
-		to someone reading the code that the pointer is being
-		protected by RCU.
+		This same sad story can happen on other CPUs when using
+		a compiler with aggressive pointer-value speculation
+		optimizations.
+
+		More important, the rcu_dereference_sched() makes it
+		clear to someone reading the code that the pointer is
+		being protected by RCU-sched.
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@ -260,7 +260,8 @@ over a rather long period of time, but improvements are always welcome!
 	The reason that it is permissible to use RCU list-traversal
 	primitives when the update-side lock is held is that doing so
 	can be quite helpful in reducing code bloat when common code is
-	shared between readers and updaters.
+	shared between readers and updaters.  Additional primitives
+	are provided for this case, as discussed in lockdep.txt.

 10.	Conversely, if you are in an RCU read-side critical section,
 	and you don't hold the appropriate update-side lock, you -must-
@ -344,8 +345,8 @@ over a rather long period of time, but improvements are always welcome!
 	requiring SRCU's read-side deadlock immunity or low read-side
 	realtime latency.

-	Note that, rcu_assign_pointer() and rcu_dereference() relate to
-	SRCU just as they do to other forms of RCU.
+	Note that, rcu_assign_pointer() relates to SRCU just as they do
+	to other forms of RCU.

 15.	The whole point of call_rcu(), synchronize_rcu(), and friends
 	is to wait until all pre-existing readers have finished before
--- a/Documentation/RCU/lockdep.txt
+++ b/Documentation/RCU/lockdep.txt
@ -32,9 +32,20 @@ checking of rcu_dereference() primitives:
 	srcu_dereference(p, sp):
 		Check for SRCU read-side critical section.
 	rcu_dereference_check(p, c):
-		Use explicit check expression "c".
+		Use explicit check expression "c".  This is useful in
+		code that is invoked by both readers and updaters.
 	rcu_dereference_raw(p)
 		Don't check.  (Use sparingly, if at all.)
+	rcu_dereference_protected(p, c):
+		Use explicit check expression "c", and omit all barriers
+		and compiler constraints.  This is useful when the data
+		structure cannot change, for example, in code that is
+		invoked only by updaters.
+	rcu_access_pointer(p):
+		Return the value of the pointer and omit all barriers,
+		but retain the compiler constraints that prevent duplicating
+		or coalescsing.  This is useful when when testing the
+		value of the pointer itself, for example, against NULL.

 The rcu_dereference_check() check expression can be any boolean
 expression, but would normally include one of the rcu_read_lock_held()
@ -59,7 +70,20 @@ In case (1), the pointer is picked up in an RCU-safe manner for vanilla
 RCU read-side critical sections, in case (2) the ->file_lock prevents
 any change from taking place, and finally, in case (3) the current task
 is the only task accessing the file_struct, again preventing any change
-from taking place.
+from taking place.  If the above statement was invoked only from updater
+code, it could instead be written as follows:
+
+	file = rcu_dereference_protected(fdt->fd[fd],
+					 lockdep_is_held(&files->file_lock) ||
+					 atomic_read(&files->count) == 1);
+
+This would verify cases #2 and #3 above, and furthermore lockdep would
+complain if this was used in an RCU read-side critical section unless one
+of these two cases held.  Because rcu_dereference_protected() omits all
+barriers and compiler constraints, it generates better code than do the
+other flavors of rcu_dereference().  On the other hand, it is illegal
+to use rcu_dereference_protected() if either the RCU-protected pointer
+or the RCU-protected data that it points to can change concurrently.

 There are currently only "universal" versions of the rcu_assign_pointer()
 and RCU list-/tree-traversal primitives, which do not (yet) check for
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@ -840,6 +840,12 @@ SRCU:	Initialization/cleanup
 	init_srcu_struct
 	cleanup_srcu_struct

+All:  lockdep-checked RCU-protected pointer access
+
+	rcu_dereference_check
+	rcu_dereference_protected
+	rcu_access_pointer
+
 See the comment headers in the source code (or the docbook generated
 from them) for more information.

--- a/Documentation/input/multi-touch-protocol.txt
+++ b/Documentation/input/multi-touch-protocol.txt
@ -68,6 +68,22 @@ like:
   SYN_MT_REPORT
   SYN_REPORT

+Here is the sequence after lifting one of the fingers:
+
+   ABS_MT_POSITION_X
+   ABS_MT_POSITION_Y
+   SYN_MT_REPORT
+   SYN_REPORT
+
+And here is the sequence after lifting the remaining finger:
+
+   SYN_MT_REPORT
+   SYN_REPORT
+
+If the driver reports one of BTN_TOUCH or ABS_PRESSURE in addition to the
+ABS_MT events, the last SYN_MT_REPORT event may be omitted. Otherwise, the
+last SYN_REPORT will be dropped by the input core, resulting in no
+zero-finger event reaching userland.

 Event Semantics
 ---------------
@ -217,11 +233,6 @@ where examples can be found.
 difference between the contact position and the approaching tool position
 could be used to derive tilt.
 [2] The list can of course be extended.
-[3] The multi-touch X driver is currently in the prototyping stage. At the
-time of writing (April 2009), the MT protocol is not yet merged, and the
-prototype implements finger matching, basic mouse support and two-finger
-scrolling. The project aims at improving the quality of current multi-touch
-functionality available in the Synaptics X driver, and in addition
-implement more advanced gestures.
+[3] Multitouch X driver project: http://bitmath.org/code/multitouch/.
 [4] See the section on event computation.
 [5] See the section on finger tracking.
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@ -320,11 +320,6 @@ and is between 256 and 4096 characters. It is defined in the file
 	amd_iommu=	[HW,X86-84]
 			Pass parameters to the AMD IOMMU driver in the system.
 			Possible values are:
-			isolate - enable device isolation (each device, as far
-			          as possible, will get its own protection
-			          domain) [default]
-			share - put every device behind one IOMMU into the
-				same protection domain
 			fullflush - enable flushing of IO/TLB entries when
 				    they are unmapped. Otherwise they are
 				    flushed before they will be reused, which
--- a/Documentation/networking/x25-iface.txt
+++ b/Documentation/networking/x25-iface.txt
@ -20,23 +20,23 @@ the rest of the skbuff, if any more information does exist.
 Packet Layer to Device Driver
 -----------------------------

-First Byte = 0x00
+First Byte = 0x00 (X25_IFACE_DATA)

 This indicates that the rest of the skbuff contains data to be transmitted
 over the LAPB link. The LAPB link should already exist before any data is
 passed down.

-First Byte = 0x01
+First Byte = 0x01 (X25_IFACE_CONNECT)

 Establish the LAPB link. If the link is already established then the connect
 confirmation message should be returned as soon as possible.

-First Byte = 0x02
+First Byte = 0x02 (X25_IFACE_DISCONNECT)

 Terminate the LAPB link. If it is already disconnected then the disconnect
 confirmation message should be returned as soon as possible.

-First Byte = 0x03
+First Byte = 0x03 (X25_IFACE_PARAMS)

 LAPB parameters. To be defined.

@ -44,22 +44,22 @@ LAPB parameters. To be defined.
 Device Driver to Packet Layer
 -----------------------------

-First Byte = 0x00
+First Byte = 0x00 (X25_IFACE_DATA)

 This indicates that the rest of the skbuff contains data that has been
 received over the LAPB link.

-First Byte = 0x01
+First Byte = 0x01 (X25_IFACE_CONNECT)

 LAPB link has been established. The same message is used for both a LAPB
 link connect_confirmation and a connect_indication.

-First Byte = 0x02
+First Byte = 0x02 (X25_IFACE_DISCONNECT)

 LAPB link has been terminated. This same message is used for both a LAPB
 link disconnect_confirmation and a disconnect_indication.

-First Byte = 0x03
+First Byte = 0x03 (X25_IFACE_PARAMS)

 LAPB parameters. To be defined.

--- a/15
+++ b/15
@ -485,8 +485,8 @@ S:	Maintained
 F:	drivers/input/mouse/bcm5974.c

 APPLE SMC DRIVER
-M:	Nicolas Boichat <nicolas@boichat.ch>
-L:	mactel-linux-devel@lists.sourceforge.net
+M:	Henrik Rydberg <rydberg@euromail.se>
+L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	drivers/hwmon/applesmc.c

@ -971,6 +971,16 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 W:	http://www.mcuos.com
 S:	Maintained

+ARM/U300 MACHINE SUPPORT
+M:	Linus Walleij <linus.walleij@stericsson.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Supported
+F:	arch/arm/mach-u300/
+F:	drivers/i2c/busses/i2c-stu300.c
+F:	drivers/rtc/rtc-coh901331.c
+F:	drivers/watchdog/coh901327_wdt.c
+F:	drivers/dma/coh901318*
+
 ARM/U8500 ARM ARCHITECTURE
 M:	Srinidhi Kasagar <srinidhi.kasagar@stericsson.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@ -3946,6 +3956,7 @@ F:	net/rfkill/
 F:	net/wireless/
 F:	include/net/ieee80211*
 F:	include/linux/wireless.h
+F:	include/linux/iw_handler.h
 F:	drivers/net/wireless/

 NETWORKING DRIVERS
--- a/4
+++ b/4
@ -1,8 +1,8 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 34
-EXTRAVERSION = -rc3
-NAME = Man-Eating Seals of Antiquity
+EXTRAVERSION = -rc5
+NAME = Sheep on Meth

 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@ -172,7 +172,7 @@ not_angel:
 		adr	r0, LC0
 ARM(		ldmia	r0, {r1, r2, r3, r4, r5, r6, r11, ip, sp})
 THUMB(		ldmia	r0, {r1, r2, r3, r4, r5, r6, r11, ip}	)
- THUMB(		ldr	sp, [r0, #28]				)
+ THUMB(		ldr	sp, [r0, #32]				)
 		subs	r0, r0, r1		@ calculate the delta offset

 						@ if delta is zero, we are
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@ -11,7 +11,11 @@

 #define kmap_prot		PAGE_KERNEL

-#define flush_cache_kmaps()	flush_cache_all()
+#define flush_cache_kmaps() \
+	do { \
+		if (cache_is_vivt()) \
+			flush_cache_all(); \
+	} while (0)

 extern pte_t *pkmap_page_table;

@ -21,11 +25,20 @@ 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.
+ */
+#ifdef CONFIG_HIGHMEM
 extern void *kmap(struct page *page);
 extern void kunmap(struct page *page);
 extern void *kmap_atomic(struct page *page, enum km_type type);
 extern void kunmap_atomic(void *kvaddr, enum km_type type);
 extern void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
 extern struct page *kmap_atomic_to_page(const void *ptr);
+#endif

 #endif
--- a/arch/arm/include/asm/kmap_types.h
+++ b/arch/arm/include/asm/kmap_types.h
@ -18,6 +18,7 @@ enum km_type {
 	KM_IRQ1,
 	KM_SOFTIRQ0,
 	KM_SOFTIRQ1,
+	KM_L1_CACHE,
 	KM_L2_CACHE,
 	KM_TYPE_NR
 };
--- a/arch/arm/include/asm/ucontext.h
+++ b/arch/arm/include/asm/ucontext.h
@ -59,23 +59,22 @@ struct iwmmxt_sigframe {
 #endif /* CONFIG_IWMMXT */

 #ifdef CONFIG_VFP
-#if __LINUX_ARM_ARCH__ < 6
-/* For ARM pre-v6, we use fstmiax and fldmiax.  This adds one extra
- * word after the registers, and a word of padding at the end for
- * alignment.  */
 #define VFP_MAGIC		0x56465001
-#define VFP_STORAGE_SIZE	152
-#else
-#define VFP_MAGIC		0x56465002
-#define VFP_STORAGE_SIZE	144
-#endif

 struct vfp_sigframe
 {
 	unsigned long		magic;
 	unsigned long		size;
-	union vfp_state		storage;
-};
+	struct user_vfp		ufp;
+	struct user_vfp_exc	ufp_exc;
+} __attribute__((__aligned__(8)));
+
+/*
+ *  8 byte for magic and size, 264 byte for ufp, 12 bytes for ufp_exc,
+ *  4 bytes padding.
+ */
+#define VFP_STORAGE_SIZE	sizeof(struct vfp_sigframe)
+
 #endif /* CONFIG_VFP */

 /*
@ -91,7 +90,7 @@ struct aux_sigframe {
 #ifdef CONFIG_IWMMXT
 	struct iwmmxt_sigframe	iwmmxt;
 #endif
-#if 0 && defined CONFIG_VFP /* Not yet saved.  */
+#ifdef CONFIG_VFP
 	struct vfp_sigframe	vfp;
 #endif
 	/* Something that isn't a valid magic number for any coprocessor.  */
--- a/arch/arm/include/asm/user.h
+++ b/arch/arm/include/asm/user.h
@ -83,11 +83,21 @@ struct user{

 /*
 * User specific VFP registers. If only VFPv2 is present, registers 16 to 31
- * are ignored by the ptrace system call.
+ * are ignored by the ptrace system call and the signal handler.
 */
 struct user_vfp {
 	unsigned long long fpregs[32];
 	unsigned long fpscr;
 };

+/*
+ * VFP exception registers exposed to user space during signal delivery.
+ * Fields not relavant to the current VFP architecture are ignored.
+ */
+struct user_vfp_exc {
+	unsigned long	fpexc;
+	unsigned long	fpinst;
+	unsigned long	fpinst2;
+};
+
 #endif /* _ARM_USER_H */
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@ -18,6 +18,7 @@
 #include <asm/cacheflush.h>
 #include <asm/ucontext.h>
 #include <asm/unistd.h>
+#include <asm/vfp.h>

 #include "ptrace.h"
 #include "signal.h"
@ -175,6 +176,90 @@ static int restore_iwmmxt_context(struct iwmmxt_sigframe *frame)

 #endif

+#ifdef CONFIG_VFP
+
+static int preserve_vfp_context(struct vfp_sigframe __user *frame)
+{
+	struct thread_info *thread = current_thread_info();
+	struct vfp_hard_struct *h = &thread->vfpstate.hard;
+	const unsigned long magic = VFP_MAGIC;
+	const unsigned long size = VFP_STORAGE_SIZE;
+	int err = 0;
+
+	vfp_sync_hwstate(thread);
+	__put_user_error(magic, &frame->magic, err);
+	__put_user_error(size, &frame->size, err);
+
+	/*
+	 * Copy the floating point registers. There can be unused
+	 * registers see asm/hwcap.h for details.
+	 */
+	err |= __copy_to_user(&frame->ufp.fpregs, &h->fpregs,
+			      sizeof(h->fpregs));
+	/*
+	 * Copy the status and control register.
+	 */
+	__put_user_error(h->fpscr, &frame->ufp.fpscr, err);
+
+	/*
+	 * Copy the exception registers.
+	 */
+	__put_user_error(h->fpexc, &frame->ufp_exc.fpexc, err);
+	__put_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
+	__put_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
+
+	return err ? -EFAULT : 0;
+}
+
+static int restore_vfp_context(struct vfp_sigframe __user *frame)
+{
+	struct thread_info *thread = current_thread_info();
+	struct vfp_hard_struct *h = &thread->vfpstate.hard;
+	unsigned long magic;
+	unsigned long size;
+	unsigned long fpexc;
+	int err = 0;
+
+	__get_user_error(magic, &frame->magic, err);
+	__get_user_error(size, &frame->size, err);
+
+	if (err)
+		return -EFAULT;
+	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
+		return -EINVAL;
+
+	/*
+	 * Copy the floating point registers. There can be unused
+	 * registers see asm/hwcap.h for details.
+	 */
+	err |= __copy_from_user(&h->fpregs, &frame->ufp.fpregs,
+				sizeof(h->fpregs));
+	/*
+	 * Copy the status and control register.
+	 */
+	__get_user_error(h->fpscr, &frame->ufp.fpscr, err);
+
+	/*
+	 * Sanitise and restore the exception registers.
+	 */
+	__get_user_error(fpexc, &frame->ufp_exc.fpexc, err);
+	/* Ensure the VFP is enabled. */
+	fpexc |= FPEXC_EN;
+	/* Ensure FPINST2 is invalid and the exception flag is cleared. */
+	fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
+	h->fpexc = fpexc;
+
+	__get_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
+	__get_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
+
+	if (!err)
+		vfp_flush_hwstate(thread);
+
+	return err ? -EFAULT : 0;
+}
+
+#endif
+
 /*
 * Do a signal return; undo the signal stack.  These are aligned to 64-bit.
 */
@ -233,8 +318,8 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
 		err |= restore_iwmmxt_context(&aux->iwmmxt);
 #endif
 #ifdef CONFIG_VFP
-//	if (err == 0)
-//		err |= vfp_restore_state(&sf->aux.vfp);
+	if (err == 0)
+		err |= restore_vfp_context(&aux->vfp);
 #endif

 	return err;
@ -348,8 +433,8 @@ setup_sigframe(struct sigframe __user *sf, struct pt_regs *regs, sigset_t *set)
 		err |= preserve_iwmmxt_context(&aux->iwmmxt);
 #endif
 #ifdef CONFIG_VFP
-//	if (err == 0)
-//		err |= vfp_save_state(&sf->aux.vfp);
+	if (err == 0)
+		err |= preserve_vfp_context(&aux->vfp);
 #endif
 	__put_user_error(0, &aux->end_magic, err);

--- a/arch/arm/mach-at91/Makefile
+++ b/arch/arm/mach-at91/Makefile
@ -16,8 +16,8 @@ obj-$(CONFIG_ARCH_AT91SAM9261)	+= at91sam9261.o at91sam926x_time.o at91sam9261_d
 obj-$(CONFIG_ARCH_AT91SAM9G10)	+= at91sam9261.o at91sam926x_time.o at91sam9261_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT91SAM9263)	+= at91sam9263.o at91sam926x_time.o at91sam9263_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT91SAM9RL)	+= at91sam9rl.o at91sam926x_time.o at91sam9rl_devices.o sam9_smc.o
-obj-$(CONFIG_ARCH_AT91SAM9G20)	+= at91sam9260.o at91sam926x_time.o at91sam9260_devices.o  sam9_smc.o
- obj-$(CONFIG_ARCH_AT91SAM9G45)	+= at91sam9g45.o at91sam926x_time.o at91sam9g45_devices.o sam9_smc.o
+obj-$(CONFIG_ARCH_AT91SAM9G20)	+= at91sam9260.o at91sam926x_time.o at91sam9260_devices.o sam9_smc.o
+obj-$(CONFIG_ARCH_AT91SAM9G45)	+= at91sam9g45.o at91sam926x_time.o at91sam9g45_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT91CAP9)	+= at91cap9.o at91sam926x_time.o at91cap9_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT572D940HF)  += at572d940hf.o at91sam926x_time.o at572d940hf_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT91X40)	+= at91x40.o at91x40_time.o
--- a/arch/arm/mach-at91/pm_slowclock.S
+++ b/arch/arm/mach-at91/pm_slowclock.S
@ -175,8 +175,6 @@ ENTRY(at91_slow_clock)
 	orr	r3, r3, #(1 << 29)		/* bit 29 always set */
 	str	r3, [r1, #(AT91_CKGR_PLLAR - AT91_PMC)]

-	wait_pllalock
-
 	/* Save PLLB setting and disable it */
 	ldr	r3, [r1, #(AT91_CKGR_PLLBR - AT91_PMC)]
 	str	r3, .saved_pllbr
@ -184,8 +182,6 @@ ENTRY(at91_slow_clock)
 	mov	r3, #AT91_PMC_PLLCOUNT
 	str	r3, [r1, #(AT91_CKGR_PLLBR - AT91_PMC)]

-	wait_pllblock
-
 	/* Turn off the main oscillator */
 	ldr	r3, [r1, #(AT91_CKGR_MOR - AT91_PMC)]
 	bic	r3, r3, #AT91_PMC_MOSCEN
@ -205,13 +201,25 @@ ENTRY(at91_slow_clock)
 	ldr	r3, .saved_pllbr
 	str	r3, [r1, #(AT91_CKGR_PLLBR - AT91_PMC)]

+	tst	r3, #(AT91_PMC_MUL &  0xff0000)
+	bne	1f
+	tst	r3, #(AT91_PMC_MUL & ~0xff0000)
+	beq	2f
+1:
 	wait_pllblock
+2:

 	/* Restore PLLA setting */
 	ldr	r3, .saved_pllar
 	str	r3, [r1, #(AT91_CKGR_PLLAR - AT91_PMC)]

+	tst	r3, #(AT91_PMC_MUL &  0xff0000)
+	bne	3f
+	tst	r3, #(AT91_PMC_MUL & ~0xff0000)
+	beq	4f
+3:
 	wait_pllalock
+4:

 #ifdef SLOWDOWN_MASTER_CLOCK
 	/*
--- a/arch/arm/mach-bcmring/dma.c
+++ b/arch/arm/mach-bcmring/dma.c
@ -2221,11 +2221,15 @@ EXPORT_SYMBOL(dma_map_create_descriptor_ring);
 int dma_unmap(DMA_MemMap_t *memMap,	/* Stores state information about the map */
 	      int dirtied	/* non-zero if any of the pages were modified */
    ) {
+
+	int rc = 0;
 	int regionIdx;
 	int segmentIdx;
 	DMA_Region_t *region;
 	DMA_Segment_t *segment;

+	down(&memMap->lock);
+
 	for (regionIdx = 0; regionIdx < memMap->numRegionsUsed; regionIdx++) {
 		region = &memMap->region[regionIdx];

@ -2239,7 +2243,8 @@ int dma_unmap(DMA_MemMap_t *memMap,	/* Stores state information about the map */
 					printk(KERN_ERR
 					       "%s: vmalloc'd pages are not yet supported\n",
 					       __func__);
-					return -EINVAL;
+					rc = -EINVAL;
+					goto out;
 				}

 			case DMA_MEM_TYPE_KMALLOC:
@ -2276,7 +2281,8 @@ int dma_unmap(DMA_MemMap_t *memMap,	/* Stores state information about the map */
 					printk(KERN_ERR
 					       "%s: Unsupported memory type: %d\n",
 					       __func__, region->memType);
-					return -EINVAL;
+					rc = -EINVAL;
+					goto out;
 				}
 			}

@ -2314,9 +2320,10 @@ int dma_unmap(DMA_MemMap_t *memMap,	/* Stores state information about the map */
 	memMap->numRegionsUsed = 0;
 	memMap->inUse = 0;

+out:
 	up(&memMap->lock);

-	return 0;
+	return rc;
 }

 EXPORT_SYMBOL(dma_unmap);
--- a/arch/arm/mach-ep93xx/gpio.c
+++ b/arch/arm/mach-ep93xx/gpio.c
@ -25,7 +25,7 @@
 #include <mach/hardware.h>

 /*************************************************************************
- * GPIO handling for EP93xx
+ * Interrupt handling for EP93xx on-chip GPIOs
 *************************************************************************/
 static unsigned char gpio_int_unmasked[3];
 static unsigned char gpio_int_enabled[3];
@ -40,7 +40,7 @@ static const u8 eoi_register_offset[3]		= { 0x98, 0xb4, 0x54 };
 static const u8 int_en_register_offset[3]	= { 0x9c, 0xb8, 0x58 };
 static const u8 int_debounce_register_offset[3]	= { 0xa8, 0xc4, 0x64 };

-void ep93xx_gpio_update_int_params(unsigned port)
+static void ep93xx_gpio_update_int_params(unsigned port)
 {
 	BUG_ON(port > 2);

@ -56,7 +56,7 @@ void ep93xx_gpio_update_int_params(unsigned port)
 		EP93XX_GPIO_REG(int_en_register_offset[port]));
 }

-void ep93xx_gpio_int_mask(unsigned line)
+static inline void ep93xx_gpio_int_mask(unsigned line)
 {
 	gpio_int_unmasked[line >> 3] &= ~(1 << (line & 7));
 }
--- a/arch/arm/mach-mx3/Kconfig
+++ b/arch/arm/mach-mx3/Kconfig
@ -62,6 +62,15 @@ config MACH_MX31_3DS
 	  Include support for MX31PDK (3DS) platform. This includes specific
 	  configurations for the board and its peripherals.

+config MACH_MX31_3DS_MXC_NAND_USE_BBT
+	bool "Make the MXC NAND driver use the in flash Bad Block Table"
+	depends on MACH_MX31_3DS
+	depends on MTD_NAND_MXC
+	help
+	  Enable this if you want that the MXC NAND driver uses the in flash
+	  Bad Block Table to know what blocks are bad instead of scanning the
+	  entire flash looking for bad block markers.
+
 config MACH_MX31MOBOARD
 	bool "Support mx31moboard platforms (EPFL Mobots group)"
 	select ARCH_MX31
@ -95,6 +104,7 @@ config MACH_PCM043
 config MACH_ARMADILLO5X0
 	bool "Support Atmark Armadillo-500 Development Base Board"
 	select ARCH_MX31
+	select MXC_ULPI if USB_ULPI
 	help
 	  Include support for Atmark Armadillo-500 platform. This includes
 	  specific configurations for the board and its peripherals.
--- a/arch/arm/mach-mx3/clock-imx31.c
+++ b/arch/arm/mach-mx3/clock-imx31.c
@ -468,6 +468,7 @@ static struct clk ahb_clk = {
 	}

 DEFINE_CLOCK(perclk_clk,  0, NULL,          0, NULL, NULL, &ipg_clk);
+DEFINE_CLOCK(ckil_clk,    0, NULL,          0, clk_ckil_get_rate, NULL, NULL);

 DEFINE_CLOCK(sdhc1_clk,   0, MXC_CCM_CGR0,  0, NULL, NULL, &perclk_clk);
 DEFINE_CLOCK(sdhc2_clk,   1, MXC_CCM_CGR0,  2, NULL, NULL, &perclk_clk);
@ -490,7 +491,7 @@ DEFINE_CLOCK(mpeg4_clk,   0, MXC_CCM_CGR1,  0, NULL, NULL, &ahb_clk);
 DEFINE_CLOCK(mstick1_clk, 0, MXC_CCM_CGR1,  2, mstick1_get_rate, NULL, &usb_pll_clk);
 DEFINE_CLOCK(mstick2_clk, 1, MXC_CCM_CGR1,  4, mstick2_get_rate, NULL, &usb_pll_clk);
 DEFINE_CLOCK1(csi_clk,    0, MXC_CCM_CGR1,  6, csi, NULL, &serial_pll_clk);
-DEFINE_CLOCK(rtc_clk,     0, MXC_CCM_CGR1,  8, NULL, NULL, &ipg_clk);
+DEFINE_CLOCK(rtc_clk,     0, MXC_CCM_CGR1,  8, NULL, NULL, &ckil_clk);
 DEFINE_CLOCK(wdog_clk,    0, MXC_CCM_CGR1, 10, NULL, NULL, &ipg_clk);
 DEFINE_CLOCK(pwm_clk,     0, MXC_CCM_CGR1, 12, NULL, NULL, &perclk_clk);
 DEFINE_CLOCK(usb_clk2,    0, MXC_CCM_CGR1, 18, usb_get_rate, NULL, &ahb_clk);
@ -514,7 +515,6 @@ DEFINE_CLOCK(usb_clk1,    0, NULL,          0, usb_get_rate, NULL, &usb_pll_clk)
 DEFINE_CLOCK(nfc_clk,     0, NULL,          0, nfc_get_rate, NULL, &ahb_clk);
 DEFINE_CLOCK(scc_clk,     0, NULL,          0, NULL, NULL, &ipg_clk);
 DEFINE_CLOCK(ipg_clk,     0, NULL,          0, ipg_get_rate, NULL, &ahb_clk);
-DEFINE_CLOCK(ckil_clk,    0, NULL,          0, clk_ckil_get_rate, NULL, NULL);

 #define _REGISTER_CLOCK(d, n, c) \
 	{ \
@ -572,7 +572,6 @@ static struct clk_lookup lookups[] = {
 	_REGISTER_CLOCK(NULL, "iim", iim_clk)
 	_REGISTER_CLOCK(NULL, "mpeg4", mpeg4_clk)
 	_REGISTER_CLOCK(NULL, "mbx", mbx_clk)
-	_REGISTER_CLOCK("mxc_rtc", NULL, ckil_clk)
 };

 int __init mx31_clocks_init(unsigned long fref)
--- a/arch/arm/mach-mx3/devices.c
+++ b/arch/arm/mach-mx3/devices.c
@ -575,11 +575,26 @@ struct platform_device imx_ssi_device1 = {
 	.resource = imx_ssi_resources1,
 };

-static int mx3_devices_init(void)
+static struct resource imx_wdt_resources[] = {
+	{
+		.flags = IORESOURCE_MEM,
+	},
+};
+
+struct platform_device imx_wdt_device0 = {
+	.name           = "imx-wdt",
+	.id             = 0,
+	.num_resources  = ARRAY_SIZE(imx_wdt_resources),
+	.resource       = imx_wdt_resources,
+};
+
+static int __init mx3_devices_init(void)
 {
 	if (cpu_is_mx31()) {
 		mxc_nand_resources[0].start = MX31_NFC_BASE_ADDR;
 		mxc_nand_resources[0].end = MX31_NFC_BASE_ADDR + 0xfff;
+		imx_wdt_resources[0].start = MX31_WDOG_BASE_ADDR;
+		imx_wdt_resources[0].end = MX31_WDOG_BASE_ADDR + 0x3fff;
 		mxc_register_device(&mxc_rnga_device, NULL);
 	}
 	if (cpu_is_mx35()) {
@ -597,6 +612,8 @@ static int mx3_devices_init(void)
 		imx_ssi_resources0[1].end = MX35_INT_SSI1;
 		imx_ssi_resources1[1].start = MX35_INT_SSI2;
 		imx_ssi_resources1[1].end = MX35_INT_SSI2;
+		imx_wdt_resources[0].start = MX35_WDOG_BASE_ADDR;
+		imx_wdt_resources[0].end = MX35_WDOG_BASE_ADDR + 0x3fff;
 	}

 	return 0;
--- a/arch/arm/mach-mx3/devices.h
+++ b/arch/arm/mach-mx3/devices.h
@ -25,4 +25,5 @@ extern struct platform_device mxc_spi_device1;
 extern struct platform_device mxc_spi_device2;
 extern struct platform_device imx_ssi_device0;
 extern struct platform_device imx_ssi_device1;
-
+extern struct platform_device imx_ssi_device1;
+extern struct platform_device imx_wdt_device0;
--- a/arch/arm/mach-mx3/mach-armadillo5x0.c
+++ b/arch/arm/mach-mx3/mach-armadillo5x0.c
@ -36,6 +36,9 @@
 #include <linux/input.h>
 #include <linux/gpio_keys.h>
 #include <linux/i2c.h>
+#include <linux/usb/otg.h>
+#include <linux/usb/ulpi.h>
+#include <linux/delay.h>

 #include <mach/hardware.h>
 #include <asm/mach-types.h>
@ -52,6 +55,8 @@
 #include <mach/ipu.h>
 #include <mach/mx3fb.h>
 #include <mach/mxc_nand.h>
+#include <mach/mxc_ehci.h>
+#include <mach/ulpi.h>

 #include "devices.h"
 #include "crm_regs.h"
@ -103,8 +108,158 @@ static int armadillo5x0_pins[] = {
 	/* I2C2 */
 	MX31_PIN_CSPI2_MOSI__SCL,
 	MX31_PIN_CSPI2_MISO__SDA,
+	/* OTG */
+	MX31_PIN_USBOTG_DATA0__USBOTG_DATA0,
+	MX31_PIN_USBOTG_DATA1__USBOTG_DATA1,
+	MX31_PIN_USBOTG_DATA2__USBOTG_DATA2,
+	MX31_PIN_USBOTG_DATA3__USBOTG_DATA3,
+	MX31_PIN_USBOTG_DATA4__USBOTG_DATA4,
+	MX31_PIN_USBOTG_DATA5__USBOTG_DATA5,
+	MX31_PIN_USBOTG_DATA6__USBOTG_DATA6,
+	MX31_PIN_USBOTG_DATA7__USBOTG_DATA7,
+	MX31_PIN_USBOTG_CLK__USBOTG_CLK,
+	MX31_PIN_USBOTG_DIR__USBOTG_DIR,
+	MX31_PIN_USBOTG_NXT__USBOTG_NXT,
+	MX31_PIN_USBOTG_STP__USBOTG_STP,
+	/* USB host 2 */
+	IOMUX_MODE(MX31_PIN_USBH2_CLK, IOMUX_CONFIG_FUNC),
+	IOMUX_MODE(MX31_PIN_USBH2_DIR, IOMUX_CONFIG_FUNC),
+	IOMUX_MODE(MX31_PIN_USBH2_NXT, IOMUX_CONFIG_FUNC),
+	IOMUX_MODE(MX31_PIN_USBH2_STP, IOMUX_CONFIG_FUNC),
+	IOMUX_MODE(MX31_PIN_USBH2_DATA0, IOMUX_CONFIG_FUNC),
+	IOMUX_MODE(MX31_PIN_USBH2_DATA1, IOMUX_CONFIG_FUNC),
+	IOMUX_MODE(MX31_PIN_STXD3, IOMUX_CONFIG_FUNC),
+	IOMUX_MODE(MX31_PIN_SRXD3, IOMUX_CONFIG_FUNC),
+	IOMUX_MODE(MX31_PIN_SCK3, IOMUX_CONFIG_FUNC),
+	IOMUX_MODE(MX31_PIN_SFS3, IOMUX_CONFIG_FUNC),
+	IOMUX_MODE(MX31_PIN_STXD6, IOMUX_CONFIG_FUNC),
+	IOMUX_MODE(MX31_PIN_SRXD6, IOMUX_CONFIG_FUNC),
 };

+/* USB */
+#if defined(CONFIG_USB_ULPI)
+
+#define OTG_RESET IOMUX_TO_GPIO(MX31_PIN_STXD4)
+#define USBH2_RESET IOMUX_TO_GPIO(MX31_PIN_SCK6)
+#define USBH2_CS IOMUX_TO_GPIO(MX31_PIN_GPIO1_3)
+
+#define USB_PAD_CFG (PAD_CTL_DRV_MAX | PAD_CTL_SRE_FAST | PAD_CTL_HYS_CMOS | \
+			PAD_CTL_ODE_CMOS | PAD_CTL_100K_PU)
+
+static int usbotg_init(struct platform_device *pdev)
+{
+	int err;
+
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_DATA0, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_DATA1, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_DATA2, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_DATA3, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_DATA4, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_DATA5, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_DATA6, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_DATA7, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_CLK, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_DIR, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_NXT, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBOTG_STP, USB_PAD_CFG);
+
+	/* Chip already enabled by hardware */
+	/* OTG phy reset*/
+	err = gpio_request(OTG_RESET, "USB-OTG-RESET");
+	if (err) {
+		pr_err("Failed to request the usb otg reset gpio\n");
+		return err;
+	}
+
+	err = gpio_direction_output(OTG_RESET, 1/*HIGH*/);
+	if (err) {
+		pr_err("Failed to reset the usb otg phy\n");
+		goto otg_free_reset;
+	}
+
+	gpio_set_value(OTG_RESET, 0/*LOW*/);
+	mdelay(5);
+	gpio_set_value(OTG_RESET, 1/*HIGH*/);
+
+	return 0;
+
+otg_free_reset:
+	gpio_free(OTG_RESET);
+	return err;
+}
+
+static int usbh2_init(struct platform_device *pdev)
+{
+	int err;
+
+	mxc_iomux_set_pad(MX31_PIN_USBH2_CLK, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBH2_DIR, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBH2_NXT, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBH2_STP, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBH2_DATA0, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_USBH2_DATA1, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_SRXD6, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_STXD6, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_SFS3, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_SCK3, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_SRXD3, USB_PAD_CFG);
+	mxc_iomux_set_pad(MX31_PIN_STXD3, USB_PAD_CFG);
+
+	mxc_iomux_set_gpr(MUX_PGP_UH2, true);
+
+
+	/* Enable the chip */
+	err = gpio_request(USBH2_CS, "USB-H2-CS");
+	if (err) {
+		pr_err("Failed to request the usb host 2 CS gpio\n");
+		return err;
+	}
+
+	err = gpio_direction_output(USBH2_CS, 0/*Enabled*/);
+	if (err) {
+		pr_err("Failed to drive the usb host 2 CS gpio\n");
+		goto h2_free_cs;
+	}
+
+	/* H2 phy reset*/
+	err = gpio_request(USBH2_RESET, "USB-H2-RESET");
+	if (err) {
+		pr_err("Failed to request the usb host 2 reset gpio\n");
+		goto h2_free_cs;
+	}
+
+	err = gpio_direction_output(USBH2_RESET, 1/*HIGH*/);
+	if (err) {
+		pr_err("Failed to reset the usb host 2 phy\n");
+		goto h2_free_reset;
+	}
+
+	gpio_set_value(USBH2_RESET, 0/*LOW*/);
+	mdelay(5);
+	gpio_set_value(USBH2_RESET, 1/*HIGH*/);
+
+	return 0;
+
+h2_free_reset:
+	gpio_free(USBH2_RESET);
+h2_free_cs:
+	gpio_free(USBH2_CS);
+	return err;
+}
+
+static struct mxc_usbh_platform_data usbotg_pdata = {
+	.init	= usbotg_init,
+	.portsc	= MXC_EHCI_MODE_ULPI | MXC_EHCI_UTMI_8BIT,
+	.flags	= MXC_EHCI_POWER_PINS_ENABLED | MXC_EHCI_INTERFACE_DIFF_UNI,
+};
+
+static struct mxc_usbh_platform_data usbh2_pdata = {
+	.init	= usbh2_init,
+	.portsc	= MXC_EHCI_MODE_ULPI | MXC_EHCI_UTMI_8BIT,
+	.flags	= MXC_EHCI_POWER_PINS_ENABLED | MXC_EHCI_INTERFACE_DIFF_UNI,
+};
+#endif /* CONFIG_USB_ULPI */
+
 /* RTC over I2C*/
 #define ARMADILLO5X0_RTC_GPIO	IOMUX_TO_GPIO(MX31_PIN_SRXD4)

@ -393,6 +548,17 @@ static void __init armadillo5x0_init(void)
 	if (armadillo5x0_i2c_rtc.irq == 0)
 		pr_warning("armadillo5x0_init: failed to get RTC IRQ\n");
 	i2c_register_board_info(1, &armadillo5x0_i2c_rtc, 1);
+
+	/* USB */
+#if defined(CONFIG_USB_ULPI)
+	usbotg_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops,
+			USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT);
+	usbh2_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops,
+			USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT);
+
+	mxc_register_device(&mxc_otg_host, &usbotg_pdata);
+	mxc_register_device(&mxc_usbh2, &usbh2_pdata);
+#endif
 }

 static void __init armadillo5x0_timer_init(void)
--- a/arch/arm/mach-mx3/mach-mx31_3ds.c
+++ b/arch/arm/mach-mx3/mach-mx31_3ds.c
@ -23,6 +23,9 @@
 #include <linux/gpio.h>
 #include <linux/smsc911x.h>
 #include <linux/platform_device.h>
+#include <linux/mfd/mc13783.h>
+#include <linux/spi/spi.h>
+#include <linux/regulator/machine.h>

 #include <mach/hardware.h>
 #include <asm/mach-types.h>
@ -31,26 +34,96 @@
 #include <asm/memory.h>
 #include <asm/mach/map.h>
 #include <mach/common.h>
-#include <mach/board-mx31pdk.h>
+#include <mach/board-mx31_3ds.h>
 #include <mach/imx-uart.h>
 #include <mach/iomux-mx3.h>
+#include <mach/mxc_nand.h>
+#include <mach/spi.h>
 #include "devices.h"

 /*!
- * @file mx31pdk.c
+ * @file mx31_3ds.c
 *
 * @brief This file contains the board-specific initialization routines.
 *
 * @ingroup System
 */

-static int mx31pdk_pins[] = {
+static int mx31_3ds_pins[] = {
 	/* UART1 */
 	MX31_PIN_CTS1__CTS1,
 	MX31_PIN_RTS1__RTS1,
 	MX31_PIN_TXD1__TXD1,
 	MX31_PIN_RXD1__RXD1,
 	IOMUX_MODE(MX31_PIN_GPIO1_1, IOMUX_CONFIG_GPIO),
+	/* SPI 1 */
+	MX31_PIN_CSPI2_SCLK__SCLK,
+	MX31_PIN_CSPI2_MOSI__MOSI,
+	MX31_PIN_CSPI2_MISO__MISO,
+	MX31_PIN_CSPI2_SPI_RDY__SPI_RDY,
+	MX31_PIN_CSPI2_SS0__SS0,
+	MX31_PIN_CSPI2_SS2__SS2, /*CS for MC13783 */
+	/* MC13783 IRQ */
+	IOMUX_MODE(MX31_PIN_GPIO1_3, IOMUX_CONFIG_GPIO),
+};
+
+/* Regulators */
+static struct regulator_init_data pwgtx_init = {
+	.constraints = {
+		.boot_on	= 1,
+		.always_on	= 1,
+	},
+};
+
+static struct mc13783_regulator_init_data mx31_3ds_regulators[] = {
+	{
+		.id = MC13783_REGU_PWGT1SPI, /* Power Gate for ARM core. */
+		.init_data = &pwgtx_init,
+	}, {
+		.id = MC13783_REGU_PWGT2SPI, /* Power Gate for L2 Cache. */
+		.init_data = &pwgtx_init,
+	},
+};
+
+/* MC13783 */
+static struct mc13783_platform_data mc13783_pdata __initdata = {
+	.regulators = mx31_3ds_regulators,
+	.num_regulators = ARRAY_SIZE(mx31_3ds_regulators),
+	.flags  = MC13783_USE_REGULATOR,
+};
+
+/* SPI */
+static int spi1_internal_chipselect[] = {
+	MXC_SPI_CS(0),
+	MXC_SPI_CS(2),
+};
+
+static struct spi_imx_master spi1_pdata = {
+	.chipselect	= spi1_internal_chipselect,
+	.num_chipselect	= ARRAY_SIZE(spi1_internal_chipselect),
+};
+
+static struct spi_board_info mx31_3ds_spi_devs[] __initdata = {
+	{
+		.modalias	= "mc13783",
+		.max_speed_hz	= 1000000,
+		.bus_num	= 1,
+		.chip_select	= 1, /* SS2 */
+		.platform_data	= &mc13783_pdata,
+		.irq		= IOMUX_TO_IRQ(MX31_PIN_GPIO1_3),
+		.mode = SPI_CS_HIGH,
+	},
+};
+
+/*
+ * NAND Flash
+ */
+static struct mxc_nand_platform_data imx31_3ds_nand_flash_pdata = {
+	.width		= 1,
+	.hw_ecc		= 1,
+#ifdef MACH_MX31_3DS_MXC_NAND_USE_BBT
+	.flash_bbt	= 1,
+#endif
 };

 static struct imxuart_platform_data uart_pdata = {
@ -95,7 +168,7 @@ static struct platform_device smsc911x_device = {
 * LEDs, switches, interrupts for Ethernet.
 */

-static void mx31pdk_expio_irq_handler(uint32_t irq, struct irq_desc *desc)
+static void mx31_3ds_expio_irq_handler(uint32_t irq, struct irq_desc *desc)
 {
 	uint32_t imr_val;
 	uint32_t int_valid;
@ -163,7 +236,7 @@ static struct irq_chip expio_irq_chip = {
 	.unmask = expio_unmask_irq,
 };

-static int __init mx31pdk_init_expio(void)
+static int __init mx31_3ds_init_expio(void)
 {
 	int i;
 	int ret;
@ -176,7 +249,7 @@ static int __init mx31pdk_init_expio(void)
 		return -ENODEV;
 	}

-	pr_info("i.MX31PDK Debug board detected, rev = 0x%04X\n",
+	pr_info("i.MX31 3DS Debug board detected, rev = 0x%04X\n",
 		__raw_readw(CPLD_CODE_VER_REG));

 	/*
@ -201,7 +274,7 @@ static int __init mx31pdk_init_expio(void)
 		set_irq_flags(i, IRQF_VALID);
 	}
 	set_irq_type(EXPIO_PARENT_INT, IRQ_TYPE_LEVEL_LOW);
-	set_irq_chained_handler(EXPIO_PARENT_INT, mx31pdk_expio_irq_handler);
+	set_irq_chained_handler(EXPIO_PARENT_INT, mx31_3ds_expio_irq_handler);

 	return 0;
 }
@ -209,7 +282,7 @@ static int __init mx31pdk_init_expio(void)
 /*
 * This structure defines the MX31 memory map.
 */
-static struct map_desc mx31pdk_io_desc[] __initdata = {
+static struct map_desc mx31_3ds_io_desc[] __initdata = {
 	{
 		.virtual = MX31_CS5_BASE_ADDR_VIRT,
 		.pfn = __phys_to_pfn(MX31_CS5_BASE_ADDR),
@ -221,10 +294,10 @@ static struct map_desc mx31pdk_io_desc[] __initdata = {
 /*
 * Set up static virtual mappings.
 */
-static void __init mx31pdk_map_io(void)
+static void __init mx31_3ds_map_io(void)
 {
 	mx31_map_io();
-	iotable_init(mx31pdk_io_desc, ARRAY_SIZE(mx31pdk_io_desc));
+	iotable_init(mx31_3ds_io_desc, ARRAY_SIZE(mx31_3ds_io_desc));
 }

 /*!
@ -232,35 +305,40 @@ static void __init mx31pdk_map_io(void)
 */
 static void __init mxc_board_init(void)
 {
-	mxc_iomux_setup_multiple_pins(mx31pdk_pins, ARRAY_SIZE(mx31pdk_pins),
-				      "mx31pdk");
+	mxc_iomux_setup_multiple_pins(mx31_3ds_pins, ARRAY_SIZE(mx31_3ds_pins),
+				      "mx31_3ds");

 	mxc_register_device(&mxc_uart_device0, &uart_pdata);
+	mxc_register_device(&mxc_nand_device, &imx31_3ds_nand_flash_pdata);

-	if (!mx31pdk_init_expio())
+	mxc_register_device(&mxc_spi_device1, &spi1_pdata);
+	spi_register_board_info(mx31_3ds_spi_devs,
+						ARRAY_SIZE(mx31_3ds_spi_devs));
+
+	if (!mx31_3ds_init_expio())
 		platform_device_register(&smsc911x_device);
 }

-static void __init mx31pdk_timer_init(void)
+static void __init mx31_3ds_timer_init(void)
 {
 	mx31_clocks_init(26000000);
 }

-static struct sys_timer mx31pdk_timer = {
-	.init	= mx31pdk_timer_init,
+static struct sys_timer mx31_3ds_timer = {
+	.init	= mx31_3ds_timer_init,
 };

 /*
 * The following uses standard kernel macros defined in arch.h in order to
- * initialize __mach_desc_MX31PDK data structure.
+ * initialize __mach_desc_MX31_3DS data structure.
 */
 MACHINE_START(MX31_3DS, "Freescale MX31PDK (3DS)")
 	/* Maintainer: Freescale Semiconductor, Inc. */
 	.phys_io	= MX31_AIPS1_BASE_ADDR,
 	.io_pg_offst	= (MX31_AIPS1_BASE_ADDR_VIRT >> 18) & 0xfffc,
 	.boot_params    = MX3x_PHYS_OFFSET + 0x100,
-	.map_io         = mx31pdk_map_io,
+	.map_io         = mx31_3ds_map_io,
 	.init_irq       = mx31_init_irq,
 	.init_machine   = mxc_board_init,
-	.timer          = &mx31pdk_timer,
+	.timer          = &mx31_3ds_timer,
 MACHINE_END
--- a/arch/arm/mach-mx3/mach-pcm037.c
+++ b/arch/arm/mach-mx3/mach-pcm037.c
@ -35,7 +35,6 @@
 #include <linux/can/platform/sja1000.h>
 #include <linux/usb/otg.h>
 #include <linux/usb/ulpi.h>
-#include <linux/fsl_devices.h>
 #include <linux/gfp.h>

 #include <media/soc_camera.h>
--- a/arch/arm/mach-mx3/mx31lite-db.c
+++ b/arch/arm/mach-mx3/mx31lite-db.c
@ -28,7 +28,6 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/gpio.h>
-#include <linux/platform_device.h>
 #include <linux/leds.h>
 #include <linux/platform_device.h>

@ -206,5 +205,6 @@ void __init mx31lite_db_init(void)
 	mxc_register_device(&mxcsdhc_device0, &mmc_pdata);
 	mxc_register_device(&mxc_spi_device0, &spi0_pdata);
 	platform_device_register(&litekit_led_device);
+	mxc_register_device(&imx_wdt_device0, NULL);
 }

--- a/arch/arm/mach-mx5/clock-mx51.c
+++ b/arch/arm/mach-mx5/clock-mx51.c
@ -757,7 +757,7 @@ DEFINE_CLOCK(uart3_ipg_clk, 2, MXC_CCM_CCGR1, MXC_CCM_CCGRx_CG7_OFFSET,

 /* GPT */
 DEFINE_CLOCK(gpt_clk, 0, MXC_CCM_CCGR2, MXC_CCM_CCGRx_CG9_OFFSET,
-	NULL,  NULL, &ipg_perclk, NULL);
+	NULL,  NULL, &ipg_clk, NULL);
 DEFINE_CLOCK(gpt_ipg_clk, 0, MXC_CCM_CCGR2, MXC_CCM_CCGRx_CG10_OFFSET,
 	NULL,  NULL, &ipg_clk, NULL);

--- a/arch/arm/mach-mx5/cpu.c
+++ b/arch/arm/mach-mx5/cpu.c
@ -14,9 +14,62 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/module.h>
 #include <mach/hardware.h>
 #include <asm/io.h>

+static int cpu_silicon_rev = -1;
+
+#define SI_REV 0x48
+
+static void query_silicon_parameter(void)
+{
+	void __iomem *rom = ioremap(MX51_IROM_BASE_ADDR, MX51_IROM_SIZE);
+	u32 rev;
+
+	if (!rom) {
+		cpu_silicon_rev = -EINVAL;
+		return;
+	}
+
+	rev = readl(rom + SI_REV);
+	switch (rev) {
+	case 0x1:
+		cpu_silicon_rev = MX51_CHIP_REV_1_0;
+		break;
+	case 0x2:
+		cpu_silicon_rev = MX51_CHIP_REV_1_1;
+		break;
+	case 0x10:
+		cpu_silicon_rev = MX51_CHIP_REV_2_0;
+		break;
+	case 0x20:
+		cpu_silicon_rev = MX51_CHIP_REV_3_0;
+		break;
+	default:
+		cpu_silicon_rev = 0;
+	}
+
+	iounmap(rom);
+}
+
+/*
+ * Returns:
+ *	the silicon revision of the cpu
+ *	-EINVAL - not a mx51
+ */
+int mx51_revision(void)
+{
+	if (!cpu_is_mx51())
+		return -EINVAL;
+
+	if (cpu_silicon_rev == -1)
+		query_silicon_parameter();
+
+	return cpu_silicon_rev;
+}
+EXPORT_SYMBOL(mx51_revision);
+
 static int __init post_cpu_init(void)
 {
 	unsigned int reg;
--- a/arch/arm/mach-mx5/mm.c
+++ b/arch/arm/mach-mx5/mm.c
@ -34,11 +34,6 @@ static struct map_desc mxc_io_desc[] __initdata = {
 		.pfn = __phys_to_pfn(MX51_DEBUG_BASE_ADDR),
 		.length = MX51_DEBUG_SIZE,
 		.type = MT_DEVICE
-	}, {
-		.virtual = MX51_TZIC_BASE_ADDR_VIRT,
-		.pfn = __phys_to_pfn(MX51_TZIC_BASE_ADDR),
-		.length = MX51_TZIC_SIZE,
-		.type = MT_DEVICE
 	}, {
 		.virtual = MX51_AIPS1_BASE_ADDR_VIRT,
 		.pfn = __phys_to_pfn(MX51_AIPS1_BASE_ADDR),
@ -54,11 +49,6 @@ static struct map_desc mxc_io_desc[] __initdata = {
 		.pfn = __phys_to_pfn(MX51_AIPS2_BASE_ADDR),
 		.length = MX51_AIPS2_SIZE,
 		.type = MT_DEVICE
-	}, {
-		.virtual = MX51_NFC_AXI_BASE_ADDR_VIRT,
-		.pfn = __phys_to_pfn(MX51_NFC_AXI_BASE_ADDR),
-		.length = MX51_NFC_AXI_SIZE,
-		.type = MT_DEVICE
 	},
 };

@ -69,14 +59,6 @@ static struct map_desc mxc_io_desc[] __initdata = {
 */
 void __init mx51_map_io(void)
 {
-	u32 tzic_addr;
-
-	if (mx51_revision() < MX51_CHIP_REV_2_0)
-		tzic_addr = 0x8FFFC000;
-	else
-		tzic_addr = 0xE0003000;
-	mxc_io_desc[2].pfn =  __phys_to_pfn(tzic_addr);
-
 	mxc_set_cpu_type(MXC_CPU_MX51);
 	mxc_iomux_v3_init(MX51_IO_ADDRESS(MX51_IOMUXC_BASE_ADDR));
 	mxc_arch_reset_init(MX51_IO_ADDRESS(MX51_WDOG_BASE_ADDR));
@ -85,5 +67,17 @@ void __init mx51_map_io(void)

 void __init mx51_init_irq(void)
 {
-	tzic_init_irq(MX51_IO_ADDRESS(MX51_TZIC_BASE_ADDR));
+	unsigned long tzic_addr;
+	void __iomem *tzic_virt;
+
+	if (mx51_revision() < MX51_CHIP_REV_2_0)
+		tzic_addr = MX51_TZIC_BASE_ADDR_TO1;
+	else
+		tzic_addr = MX51_TZIC_BASE_ADDR;
+
+	tzic_virt = ioremap(tzic_addr, SZ_16K);
+	if (!tzic_virt)
+		panic("unable to map TZIC interrupt controller\n");
+
+	tzic_init_irq(tzic_virt);
 }
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@ -41,14 +41,7 @@ static void v6_copy_user_highpage_nonaliasing(struct page *to,
 	kfrom = kmap_atomic(from, KM_USER0);
 	kto = kmap_atomic(to, KM_USER1);
 	copy_page(kto, kfrom);
-#ifdef CONFIG_HIGHMEM
-	/*
-	 * kmap_atomic() doesn't set the page virtual address, and
-	 * kunmap_atomic() takes care of cache flushing already.
-	 */
-	if (page_address(to) != NULL)
-#endif
-		__cpuc_flush_dcache_area(kto, PAGE_SIZE);
+	__cpuc_flush_dcache_area(kto, PAGE_SIZE);
 	kunmap_atomic(kto, KM_USER1);
 	kunmap_atomic(kfrom, KM_USER0);
 }
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@ -464,6 +464,11 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 				vaddr += 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);
+				op(vaddr + offset, len, dir);
+				kunmap_high_l1_vipt(page, saved_pte);
 			}
 		} else {
 			vaddr = page_address(page) + offset;
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@ -13,6 +13,7 @@

 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
+#include <asm/highmem.h>
 #include <asm/smp_plat.h>
 #include <asm/system.h>
 #include <asm/tlbflush.h>
@ -152,21 +153,25 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page,

 void __flush_dcache_page(struct address_space *mapping, struct page *page)
 {
-	void *addr = page_address(page);
-
 	/*
 	 * Writeback any data associated with the kernel mapping of this
 	 * page.  This ensures that data in the physical page is mutually
 	 * coherent with the kernels mapping.
 	 */
-#ifdef CONFIG_HIGHMEM
-	/*
-	 * kmap_atomic() doesn't set the page virtual address, and
-	 * kunmap_atomic() takes care of cache flushing already.
-	 */
-	if (addr)
-#endif
-		__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+	if (!PageHighMem(page)) {
+		__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
+	} else {
+		void *addr = kmap_high_get(page);
+		if (addr) {
+			__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);
+			__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+			kunmap_high_l1_vipt(page, saved_pte);
+		}
+	}

 	/*
 	 * If this is a page cache page, and we have an aliasing VIPT cache,
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@ -79,7 +79,8 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
 	unsigned int idx = type + KM_TYPE_NR * smp_processor_id();

 	if (kvaddr >= (void *)FIXADDR_START) {
-		__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
+		if (cache_is_vivt())
+			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
 #ifdef CONFIG_DEBUG_HIGHMEM
 		BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
 		set_pte_ext(TOP_PTE(vaddr), __pte(0), 0);
@ -124,3 +125,87 @@ 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 = 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);
+
+	if (!in_interrupt())
+		preempt_disable();
+
+	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 */
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@ -420,6 +420,10 @@ static void __init build_mem_type_table(void)
 		user_pgprot |= L_PTE_SHARED;
 		kern_pgprot |= L_PTE_SHARED;
 		vecs_pgprot |= L_PTE_SHARED;
+		mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S;
+		mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED;
+		mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
+		mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
 		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
 		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
 #endif
@ -1050,10 +1054,12 @@ void setup_mm_for_reboot(char mode)
 	pgd_t *pgd;
 	int i;

-	if (current->mm && current->mm->pgd)
-		pgd = current->mm->pgd;
-	else
-		pgd = init_mm.pgd;
+	/*
+	 * We need to access to user-mode page tables here. For kernel threads
+	 * we don't have any user-mode mappings so we use the context that we
+	 * "borrowed".
+	 */
+	pgd = current->active_mm->pgd;

 	base_pmdval = PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | PMD_TYPE_SECT;
 	if (cpu_architecture() <= CPU_ARCH_ARMv5TEJ && !cpu_is_xscale())
--- a/arch/arm/plat-mxc/include/mach/board-mx31_3ds.h
+++ b/arch/arm/plat-mxc/include/mach/board-mx31_3ds.h
@ -8,8 +8,8 @@
 * published by the Free Software Foundation.
 */

-#ifndef __ASM_ARCH_MXC_BOARD_MX31PDK_H__
-#define __ASM_ARCH_MXC_BOARD_MX31PDK_H__
+#ifndef __ASM_ARCH_MXC_BOARD_MX31_3DS_H__
+#define __ASM_ARCH_MXC_BOARD_MX31_3DS_H__

 /* Definitions for components on the Debug board */

@ -56,4 +56,4 @@

 #define MXC_MAX_EXP_IO_LINES	16

-#endif /* __ASM_ARCH_MXC_BOARD_MX31PDK_H__ */
+#endif /* __ASM_ARCH_MXC_BOARD_MX31_3DS_H__ */
--- a/arch/arm/plat-mxc/include/mach/mx51.h
+++ b/arch/arm/plat-mxc/include/mach/mx51.h
@ -14,7 +14,7 @@
 * FB100000	70000000	1M	SPBA 0
 * FB000000	73F00000	1M	AIPS 1
 * FB200000	83F00000	1M	AIPS 2
- * FA100000	8FFFC000	16K	TZIC (interrupt controller)
+ *		8FFFC000	16K	TZIC (interrupt controller)
 *         	90000000	256M	CSD0 SDRAM/DDR
 *         	A0000000	256M	CSD1 SDRAM/DDR
 *         	B0000000	128M	CS0 Flash
@ -23,10 +23,16 @@
 *         	C8000000	64M	CS3 Flash
 *         	CC000000	32M	CS4 SRAM
 *         	CE000000	32M	CS5 SRAM
- * F9000000	CFFF0000	64K	NFC (NAND Flash AXI)
+ *		CFFF0000	64K	NFC (NAND Flash AXI)
 *
 */

+/*
+ * IROM
+ */
+#define MX51_IROM_BASE_ADDR		0x0
+#define MX51_IROM_SIZE			SZ_64K
+
 /*
 * IRAM
 */
@ -40,7 +46,6 @@
 * NFC
 */
 #define MX51_NFC_AXI_BASE_ADDR		0xCFFF0000	/* NAND flash AXI */
-#define MX51_NFC_AXI_BASE_ADDR_VIRT	0xF9000000
 #define MX51_NFC_AXI_SIZE		SZ_64K

 /*
@ -49,9 +54,8 @@
 #define MX51_GPU_BASE_ADDR		0x20000000
 #define MX51_GPU2D_BASE_ADDR		0xD0000000

-#define MX51_TZIC_BASE_ADDR		0x8FFFC000
-#define MX51_TZIC_BASE_ADDR_VIRT	0xFA100000
-#define MX51_TZIC_SIZE			SZ_16K
+#define MX51_TZIC_BASE_ADDR_TO1		0x8FFFC000
+#define MX51_TZIC_BASE_ADDR		0xE0000000

 #define MX51_DEBUG_BASE_ADDR		0x60000000
 #define MX51_DEBUG_BASE_ADDR_VIRT	0xFA200000
@ -232,12 +236,10 @@
 #define MX51_IO_ADDRESS(x)					\
 	(void __iomem *)					\
 	(MX51_IS_MODULE(x, IRAM) ? MX51_IRAM_IO_ADDRESS(x) :	\
-	MX51_IS_MODULE(x, TZIC) ? MX51_TZIC_IO_ADDRESS(x) :	\
 	MX51_IS_MODULE(x, DEBUG) ? MX51_DEBUG_IO_ADDRESS(x) :	\
 	MX51_IS_MODULE(x, SPBA0) ? MX51_SPBA0_IO_ADDRESS(x) :	\
 	MX51_IS_MODULE(x, AIPS1) ? MX51_AIPS1_IO_ADDRESS(x) :	\
-	MX51_IS_MODULE(x, AIPS2) ? MX51_AIPS2_IO_ADDRESS(x) :	\
-	MX51_IS_MODULE(x, NFC_AXI) ? MX51_NFC_AXI_IO_ADDRESS(x) : \
+	MX51_IS_MODULE(x, AIPS2) ? MX51_AIPS2_IO_ADDRESS(x) : \
 	0xDEADBEEF)

 /*
@ -246,9 +248,6 @@
 #define MX51_IRAM_IO_ADDRESS(x)  \
 	(((x) - MX51_IRAM_BASE_ADDR) + MX51_IRAM_BASE_ADDR_VIRT)

-#define MX51_TZIC_IO_ADDRESS(x)  \
-	(((x) - MX51_TZIC_BASE_ADDR) + MX51_TZIC_BASE_ADDR_VIRT)
-
 #define MX51_DEBUG_IO_ADDRESS(x)  \
 	(((x) - MX51_DEBUG_BASE_ADDR) + MX51_DEBUG_BASE_ADDR_VIRT)

@ -261,9 +260,6 @@
 #define MX51_AIPS2_IO_ADDRESS(x)  \
 	(((x) - MX51_AIPS2_BASE_ADDR) + MX51_AIPS2_BASE_ADDR_VIRT)

-#define MX51_NFC_AXI_IO_ADDRESS(x) \
-	(((x) - MX51_NFC_AXI_BASE_ADDR) + MX51_NFC_AXI_BASE_ADDR_VIRT)
-
 #define MX51_IS_MEM_DEVICE_NONSHARED(x)		0

 /*
@ -443,12 +439,7 @@

 #if !defined(__ASSEMBLY__) && !defined(__MXC_BOOT_UNCOMPRESS)

-extern unsigned int system_rev;
-
-static inline unsigned int mx51_revision(void)
-{
-	return system_rev;
-}
+extern int mx51_revision(void);
 #endif

 #endif	/*  __ASM_ARCH_MXC_MX51_H__ */
--- a/arch/arm/plat-mxc/include/mach/uncompress.h
+++ b/arch/arm/plat-mxc/include/mach/uncompress.h
@ -66,6 +66,7 @@ static inline void flush(void)
 #define MX2X_UART1_BASE_ADDR	0x1000a000
 #define MX3X_UART1_BASE_ADDR	0x43F90000
 #define MX3X_UART2_BASE_ADDR	0x43F94000
+#define MX51_UART1_BASE_ADDR	0x73fbc000

 static __inline__ void __arch_decomp_setup(unsigned long arch_id)
 {
@ -101,6 +102,9 @@ static __inline__ void __arch_decomp_setup(unsigned long arch_id)
 	case MACH_TYPE_MAGX_ZN5:
 		uart_base = MX3X_UART2_BASE_ADDR;
 		break;
+	case MACH_TYPE_MX51_BABBAGE:
+		uart_base = MX51_UART1_BASE_ADDR;
+		break;
 	default:
 		break;
 	}
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@ -428,26 +428,6 @@ static void vfp_pm_init(void)
 static inline void vfp_pm_init(void) { }
 #endif /* CONFIG_PM */

-/*
- * Synchronise the hardware VFP state of a thread other than current with the
- * saved one. This function is used by the ptrace mechanism.
- */
-#ifdef CONFIG_SMP
-void vfp_sync_hwstate(struct thread_info *thread)
-{
-}
-
-void vfp_flush_hwstate(struct thread_info *thread)
-{
-	/*
-	 * On SMP systems, the VFP state is automatically saved at every
-	 * context switch. We mark the thread VFP state as belonging to a
-	 * non-existent CPU so that the saved one will be reloaded when
-	 * needed.
-	 */
-	thread->vfpstate.hard.cpu = NR_CPUS;
-}
-#else
 void vfp_sync_hwstate(struct thread_info *thread)
 {
 	unsigned int cpu = get_cpu();
@ -490,9 +470,18 @@ void vfp_flush_hwstate(struct thread_info *thread)
 		last_VFP_context[cpu] = NULL;
 	}

+#ifdef CONFIG_SMP
+	/*
+	 * For SMP we still have to take care of the case where the thread
+	 * migrates to another CPU and then back to the original CPU on which
+	 * the last VFP user is still the same thread. Mark the thread VFP
+	 * state as belonging to a non-existent CPU so that the saved one will
+	 * be reloaded in the above case.
+	 */
+	thread->vfpstate.hard.cpu = NR_CPUS;
+#endif
 	put_cpu();
 }
-#endif

 #include <linux/smp.h>

--- a/arch/m68k/include/asm/atomic_mm.h
+++ b/arch/m68k/include/asm/atomic_mm.h
@ -148,14 +148,18 @@ static inline int atomic_xchg(atomic_t *v, int new)
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
 	char c;
-	__asm__ __volatile__("subl %2,%1; seq %0" : "=d" (c), "+m" (*v): "g" (i));
+	__asm__ __volatile__("subl %2,%1; seq %0"
+			     : "=d" (c), "+m" (*v)
+			     : "id" (i));
 	return c != 0;
 }

 static inline int atomic_add_negative(int i, atomic_t *v)
 {
 	char c;
-	__asm__ __volatile__("addl %2,%1; smi %0" : "=d" (c), "+m" (*v): "g" (i));
+	__asm__ __volatile__("addl %2,%1; smi %0"
+			     : "=d" (c), "+m" (*v)
+			     : "id" (i));
 	return c != 0;
 }

--- a/arch/m68k/include/asm/sigcontext.h
+++ b/arch/m68k/include/asm/sigcontext.h
@ -17,13 +17,11 @@ struct sigcontext {
 #ifndef __uClinux__
 # ifdef __mcoldfire__
 	unsigned long  sc_fpregs[2][2];	/* room for two fp registers */
-	unsigned long  sc_fpcntl[3];
-	unsigned char  sc_fpstate[16+6*8];
 # else
 	unsigned long  sc_fpregs[2*3];  /* room for two fp registers */
+# endif
 	unsigned long  sc_fpcntl[3];
 	unsigned char  sc_fpstate[216];
-# endif
 #endif
 };

--- a/arch/mips/alchemy/devboards/db1200/setup.c
+++ b/arch/mips/alchemy/devboards/db1200/setup.c
@ -60,43 +60,6 @@ void __init board_setup(void)
 	wmb();
 }

-/* use the hexleds to count the number of times the cpu has entered
- * wait, the dots to indicate whether the CPU is currently idle or
- * active (dots off = sleeping, dots on = working) for cases where
- * the number doesn't change for a long(er) period of time.
- */
-static void db1200_wait(void)
-{
-	__asm__("	.set	push			\n"
-		"	.set	mips3			\n"
-		"	.set	noreorder		\n"
-		"	cache	0x14, 0(%0)		\n"
-		"	cache	0x14, 32(%0)		\n"
-		"	cache	0x14, 64(%0)		\n"
-		/* dots off: we're about to call wait */
-		"	lui	$26, 0xb980		\n"
-		"	ori	$27, $0, 3		\n"
-		"	sb	$27, 0x18($26)		\n"
-		"	sync				\n"
-		"	nop				\n"
-		"	wait				\n"
-		"	nop				\n"
-		"	nop				\n"
-		"	nop				\n"
-		"	nop				\n"
-		"	nop				\n"
-		/* dots on: there's work to do, increment cntr */
-		"	lui	$26, 0xb980		\n"
-		"	sb	$0, 0x18($26)		\n"
-		"	lui	$26, 0xb9c0		\n"
-		"	lb	$27, 0($26)		\n"
-		"	addiu	$27, $27, 1		\n"
-		"	sb	$27, 0($26)		\n"
-		"	sync				\n"
-		"	.set	pop			\n"
-		: : "r" (db1200_wait));
-}
-
 static int __init db1200_arch_init(void)
 {
 	/* GPIO7 is low-level triggered CPLD cascade */
@ -110,9 +73,6 @@ static int __init db1200_arch_init(void)
 	irq_to_desc(DB1200_SD0_INSERT_INT)->status |= IRQ_NOAUTOEN;
 	irq_to_desc(DB1200_SD0_EJECT_INT)->status |= IRQ_NOAUTOEN;

-	if (cpu_wait)
-		cpu_wait = db1200_wait;
-
 	return 0;
 }
 arch_initcall(db1200_arch_init);
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@ -168,7 +168,7 @@ static struct plat_vlynq_data vlynq_high_data = {
 		.on	= vlynq_on,
 		.off	= vlynq_off,
 	},
-	.reset_bit	= 26,
+	.reset_bit	= 16,
 	.gpio_bit	= 19,
 };

@ -600,6 +600,7 @@ static int __init ar7_register_devices(void)
 	}

 	if (ar7_has_high_cpmac()) {
+		res = fixed_phy_add(PHY_POLL, cpmac_high.id, &fixed_phy_status);
 		if (!res) {
 			cpmac_get_mac(1, cpmac_high_data.dev_addr);

--- a/arch/mips/bcm63xx/boards/board_bcm963xx.c
+++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c
@ -18,6 +18,7 @@
 #include <asm/addrspace.h>
 #include <bcm63xx_board.h>
 #include <bcm63xx_cpu.h>
+#include <bcm63xx_dev_uart.h>
 #include <bcm63xx_regs.h>
 #include <bcm63xx_io.h>
 #include <bcm63xx_dev_pci.h>
@ -40,6 +41,7 @@ static struct board_info __initdata board_96338gw = {
 	.name				= "96338GW",
 	.expected_cpu_id		= 0x6338,

+	.has_uart0			= 1,
 	.has_enet0			= 1,
 	.enet0 = {
 		.force_speed_100	= 1,
@ -82,6 +84,7 @@ static struct board_info __initdata board_96338w = {
 	.name				= "96338W",
 	.expected_cpu_id		= 0x6338,

+	.has_uart0			= 1,
 	.has_enet0			= 1,
 	.enet0 = {
 		.force_speed_100	= 1,
@ -126,6 +129,8 @@ static struct board_info __initdata board_96338w = {
 static struct board_info __initdata board_96345gw2 = {
 	.name				= "96345GW2",
 	.expected_cpu_id		= 0x6345,
+
+	.has_uart0			= 1,
 };
 #endif

@ -137,6 +142,7 @@ static struct board_info __initdata board_96348r = {
 	.name				= "96348R",
 	.expected_cpu_id		= 0x6348,

+	.has_uart0			= 1,
 	.has_enet0			= 1,
 	.has_pci			= 1,

@ -180,6 +186,7 @@ static struct board_info __initdata board_96348gw_10 = {
 	.name				= "96348GW-10",
 	.expected_cpu_id		= 0x6348,

+	.has_uart0			= 1,
 	.has_enet0			= 1,
 	.has_enet1			= 1,
 	.has_pci			= 1,
@ -239,6 +246,7 @@ static struct board_info __initdata board_96348gw_11 = {
 	.name				= "96348GW-11",
 	.expected_cpu_id		= 0x6348,

+	.has_uart0			= 1,
 	.has_enet0			= 1,
 	.has_enet1			= 1,
 	.has_pci			= 1,
@ -292,6 +300,7 @@ static struct board_info __initdata board_96348gw = {
 	.name				= "96348GW",
 	.expected_cpu_id		= 0x6348,

+	.has_uart0			= 1,
 	.has_enet0			= 1,
 	.has_enet1			= 1,
 	.has_pci			= 1,
@ -349,9 +358,10 @@ static struct board_info __initdata board_FAST2404 = {
 	.name				= "F@ST2404",
 	.expected_cpu_id		= 0x6348,

-	.has_enet0			= 1,
-	.has_enet1			= 1,
-	.has_pci			= 1,
+	.has_uart0			= 1,
+        .has_enet0			= 1,
+        .has_enet1			= 1,
+        .has_pci			= 1,

 	.enet0 = {
 		.has_phy		= 1,
@ -368,10 +378,30 @@ static struct board_info __initdata board_FAST2404 = {
 	.has_ehci0			= 1,
 };

+static struct board_info __initdata board_rta1025w_16 = {
+	.name				= "RTA1025W_16",
+	.expected_cpu_id		= 0x6348,
+
+	.has_enet0			= 1,
+	.has_enet1			= 1,
+	.has_pci			= 1,
+
+	.enet0 = {
+		.has_phy		= 1,
+		.use_internal_phy	= 1,
+	},
+	.enet1 = {
+		.force_speed_100	= 1,
+		.force_duplex_full	= 1,
+	},
+};
+
+
 static struct board_info __initdata board_DV201AMR = {
 	.name				= "DV201AMR",
 	.expected_cpu_id		= 0x6348,

+	.has_uart0			= 1,
 	.has_pci			= 1,
 	.has_ohci0			= 1,

@ -391,6 +421,7 @@ static struct board_info __initdata board_96348gw_a = {
 	.name				= "96348GW-A",
 	.expected_cpu_id		= 0x6348,

+	.has_uart0			= 1,
 	.has_enet0			= 1,
 	.has_enet1			= 1,
 	.has_pci			= 1,
@ -416,6 +447,7 @@ static struct board_info __initdata board_96358vw = {
 	.name				= "96358VW",
 	.expected_cpu_id		= 0x6358,

+	.has_uart0			= 1,
 	.has_enet0			= 1,
 	.has_enet1			= 1,
 	.has_pci			= 1,
@ -467,6 +499,7 @@ static struct board_info __initdata board_96358vw2 = {
 	.name				= "96358VW2",
 	.expected_cpu_id		= 0x6358,

+	.has_uart0			= 1,
 	.has_enet0			= 1,
 	.has_enet1			= 1,
 	.has_pci			= 1,
@ -514,6 +547,7 @@ static struct board_info __initdata board_AGPFS0 = {
 	.name                           = "AGPF-S0",
 	.expected_cpu_id                = 0x6358,

+	.has_uart0			= 1,
 	.has_enet0                      = 1,
 	.has_enet1                      = 1,
 	.has_pci                        = 1,
@ -531,6 +565,27 @@ static struct board_info __initdata board_AGPFS0 = {
 	.has_ohci0 = 1,
 	.has_ehci0 = 1,
 };
+
+static struct board_info __initdata board_DWVS0 = {
+	.name				= "DWV-S0",
+	.expected_cpu_id		= 0x6358,
+
+	.has_enet0			= 1,
+	.has_enet1			= 1,
+	.has_pci			= 1,
+
+	.enet0 = {
+		.has_phy		= 1,
+		.use_internal_phy	= 1,
+	},
+
+	.enet1 = {
+		.force_speed_100	= 1,
+		.force_duplex_full	= 1,
+	},
+
+	.has_ohci0			= 1,
+};
 #endif

 /*
@ -552,15 +607,87 @@ static const struct board_info __initdata *bcm963xx_boards[] = {
 	&board_FAST2404,
 	&board_DV201AMR,
 	&board_96348gw_a,
+	&board_rta1025w_16,
 #endif

 #ifdef CONFIG_BCM63XX_CPU_6358
 	&board_96358vw,
 	&board_96358vw2,
 	&board_AGPFS0,
+	&board_DWVS0,
 #endif
 };

+/*
+ * Register a sane SPROMv2 to make the on-board
+ * bcm4318 WLAN work
+ */
+#ifdef CONFIG_SSB_PCIHOST
+static struct ssb_sprom bcm63xx_sprom = {
+	.revision		= 0x02,
+	.board_rev		= 0x17,
+	.country_code		= 0x0,
+	.ant_available_bg 	= 0x3,
+	.pa0b0			= 0x15ae,
+	.pa0b1			= 0xfa85,
+	.pa0b2			= 0xfe8d,
+	.pa1b0			= 0xffff,
+	.pa1b1			= 0xffff,
+	.pa1b2			= 0xffff,
+	.gpio0			= 0xff,
+	.gpio1			= 0xff,
+	.gpio2			= 0xff,
+	.gpio3			= 0xff,
+	.maxpwr_bg		= 0x004c,
+	.itssi_bg		= 0x00,
+	.boardflags_lo		= 0x2848,
+	.boardflags_hi		= 0x0000,
+};
+#endif
+
+/*
+ * return board name for /proc/cpuinfo
+ */
+const char *board_get_name(void)
+{
+	return board.name;
+}
+
+/*
+ * register & return a new board mac address
+ */
+static int board_get_mac_address(u8 *mac)
+{
+	u8 *p;
+	int count;
+
+	if (mac_addr_used >= nvram.mac_addr_count) {
+		printk(KERN_ERR PFX "not enough mac address\n");
+		return -ENODEV;
+	}
+
+	memcpy(mac, nvram.mac_addr_base, ETH_ALEN);
+	p = mac + ETH_ALEN - 1;
+	count = mac_addr_used;
+
+	while (count--) {
+		do {
+			(*p)++;
+			if (*p != 0)
+				break;
+			p--;
+		} while (p != mac);
+	}
+
+	if (p == mac) {
+		printk(KERN_ERR PFX "unable to fetch mac address\n");
+		return -ENODEV;
+	}
+
+	mac_addr_used++;
+	return 0;
+}
+
 /*
 * early init callback, read nvram data from flash and checksum it
 */
@ -659,6 +786,17 @@ void __init board_prom_init(void)
 	}

 	bcm_gpio_writel(val, GPIO_MODE_REG);
+
+	/* Generate MAC address for WLAN and
+	 * register our SPROM */
+#ifdef CONFIG_SSB_PCIHOST
+	if (!board_get_mac_address(bcm63xx_sprom.il0mac)) {
+		memcpy(bcm63xx_sprom.et0mac, bcm63xx_sprom.il0mac, ETH_ALEN);
+		memcpy(bcm63xx_sprom.et1mac, bcm63xx_sprom.il0mac, ETH_ALEN);
+		if (ssb_arch_set_fallback_sprom(&bcm63xx_sprom) < 0)
+			printk(KERN_ERR "failed to register fallback SPROM\n");
+	}
+#endif
 }

 /*
@ -676,49 +814,6 @@ void __init board_setup(void)
 		panic("unexpected CPU for bcm963xx board");
 }

-/*
- * return board name for /proc/cpuinfo
- */
-const char *board_get_name(void)
-{
-	return board.name;
-}
-
-/*
- * register & return a new board mac address
- */
-static int board_get_mac_address(u8 *mac)
-{
-	u8 *p;
-	int count;
-
-	if (mac_addr_used >= nvram.mac_addr_count) {
-		printk(KERN_ERR PFX "not enough mac address\n");
-		return -ENODEV;
-	}
-
-	memcpy(mac, nvram.mac_addr_base, ETH_ALEN);
-	p = mac + ETH_ALEN - 1;
-	count = mac_addr_used;
-
-	while (count--) {
-		do {
-			(*p)++;
-			if (*p != 0)
-				break;
-			p--;
-		} while (p != mac);
-	}
-
-	if (p == mac) {
-		printk(KERN_ERR PFX "unable to fetch mac address\n");
-		return -ENODEV;
-	}
-
-	mac_addr_used++;
-	return 0;
-}
-
 static struct mtd_partition mtd_partitions[] = {
 	{
 		.name		= "cfe",
@ -750,33 +845,6 @@ static struct platform_device mtd_dev = {
 	},
 };

-/*
- * Register a sane SPROMv2 to make the on-board
- * bcm4318 WLAN work
- */
-#ifdef CONFIG_SSB_PCIHOST
-static struct ssb_sprom bcm63xx_sprom = {
-	.revision		= 0x02,
-	.board_rev		= 0x17,
-	.country_code		= 0x0,
-	.ant_available_bg 	= 0x3,
-	.pa0b0			= 0x15ae,
-	.pa0b1			= 0xfa85,
-	.pa0b2			= 0xfe8d,
-	.pa1b0			= 0xffff,
-	.pa1b1			= 0xffff,
-	.pa1b2			= 0xffff,
-	.gpio0			= 0xff,
-	.gpio1			= 0xff,
-	.gpio2			= 0xff,
-	.gpio3			= 0xff,
-	.maxpwr_bg		= 0x004c,
-	.itssi_bg		= 0x00,
-	.boardflags_lo		= 0x2848,
-	.boardflags_hi		= 0x0000,
-};
-#endif
-
 static struct gpio_led_platform_data bcm63xx_led_data;

 static struct platform_device bcm63xx_gpio_leds = {
@ -792,6 +860,12 @@ int __init board_register_devices(void)
 {
 	u32 val;

+	if (board.has_uart0)
+		bcm63xx_uart_register(0);
+
+	if (board.has_uart1)
+		bcm63xx_uart_register(1);
+
 	if (board.has_pccard)
 		bcm63xx_pcmcia_register();

@ -806,17 +880,6 @@ int __init board_register_devices(void)
 	if (board.has_dsp)
 		bcm63xx_dsp_register(&board.dsp);

-	/* Generate MAC address for WLAN and
-	 * register our SPROM */
-#ifdef CONFIG_SSB_PCIHOST
-	if (!board_get_mac_address(bcm63xx_sprom.il0mac)) {
-		memcpy(bcm63xx_sprom.et0mac, bcm63xx_sprom.il0mac, ETH_ALEN);
-		memcpy(bcm63xx_sprom.et1mac, bcm63xx_sprom.il0mac, ETH_ALEN);
-		if (ssb_arch_set_fallback_sprom(&bcm63xx_sprom) < 0)
-			printk(KERN_ERR "failed to register fallback SPROM\n");
-	}
-#endif
-
 	/* read base address of boot chip select (0) */
 	if (BCMCPU_IS_6345())
 		val = 0x1fc00000;
--- a/arch/mips/bcm63xx/cpu.c
+++ b/arch/mips/bcm63xx/cpu.c
@ -36,6 +36,7 @@ static const unsigned long bcm96338_regs_base[] = {
 	[RSET_TIMER]		= BCM_6338_TIMER_BASE,
 	[RSET_WDT]		= BCM_6338_WDT_BASE,
 	[RSET_UART0]		= BCM_6338_UART0_BASE,
+	[RSET_UART1]		= BCM_6338_UART1_BASE,
 	[RSET_GPIO]		= BCM_6338_GPIO_BASE,
 	[RSET_SPI]		= BCM_6338_SPI_BASE,
 	[RSET_OHCI0]		= BCM_6338_OHCI0_BASE,
@ -72,6 +73,7 @@ static const unsigned long bcm96345_regs_base[] = {
 	[RSET_TIMER]		= BCM_6345_TIMER_BASE,
 	[RSET_WDT]		= BCM_6345_WDT_BASE,
 	[RSET_UART0]		= BCM_6345_UART0_BASE,
+	[RSET_UART1]		= BCM_6345_UART1_BASE,
 	[RSET_GPIO]		= BCM_6345_GPIO_BASE,
 	[RSET_SPI]		= BCM_6345_SPI_BASE,
 	[RSET_UDC0]		= BCM_6345_UDC0_BASE,
@ -109,6 +111,7 @@ static const unsigned long bcm96348_regs_base[] = {
 	[RSET_TIMER]		= BCM_6348_TIMER_BASE,
 	[RSET_WDT]		= BCM_6348_WDT_BASE,
 	[RSET_UART0]		= BCM_6348_UART0_BASE,
+	[RSET_UART1]		= BCM_6348_UART1_BASE,
 	[RSET_GPIO]		= BCM_6348_GPIO_BASE,
 	[RSET_SPI]		= BCM_6348_SPI_BASE,
 	[RSET_OHCI0]		= BCM_6348_OHCI0_BASE,
@ -150,6 +153,7 @@ static const unsigned long bcm96358_regs_base[] = {
 	[RSET_TIMER]		= BCM_6358_TIMER_BASE,
 	[RSET_WDT]		= BCM_6358_WDT_BASE,
 	[RSET_UART0]		= BCM_6358_UART0_BASE,
+	[RSET_UART1]		= BCM_6358_UART1_BASE,
 	[RSET_GPIO]		= BCM_6358_GPIO_BASE,
 	[RSET_SPI]		= BCM_6358_SPI_BASE,
 	[RSET_OHCI0]		= BCM_6358_OHCI0_BASE,
@ -170,6 +174,7 @@ static const unsigned long bcm96358_regs_base[] = {
 static const int bcm96358_irqs[] = {
 	[IRQ_TIMER]		= BCM_6358_TIMER_IRQ,
 	[IRQ_UART0]		= BCM_6358_UART0_IRQ,
+	[IRQ_UART1]		= BCM_6358_UART1_IRQ,
 	[IRQ_DSL]		= BCM_6358_DSL_IRQ,
 	[IRQ_ENET0]		= BCM_6358_ENET0_IRQ,
 	[IRQ_ENET1]		= BCM_6358_ENET1_IRQ,
--- a/arch/mips/bcm63xx/dev-uart.c
+++ b/arch/mips/bcm63xx/dev-uart.c
@ -11,31 +11,65 @@
 #include <linux/platform_device.h>
 #include <bcm63xx_cpu.h>

-static struct resource uart_resources[] = {
+static struct resource uart0_resources[] = {
 	{
-		.start		= -1, /* filled at runtime */
-		.end		= -1, /* filled at runtime */
+		/* start & end filled at runtime */
 		.flags		= IORESOURCE_MEM,
 	},
 	{
-		.start		= -1, /* filled at runtime */
+		/* start filled at runtime */
 		.flags		= IORESOURCE_IRQ,
 	},
 };

-static struct platform_device bcm63xx_uart_device = {
-	.name		= "bcm63xx_uart",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(uart_resources),
-	.resource	= uart_resources,
+static struct resource uart1_resources[] = {
+	{
+		/* start & end filled at runtime */
+		.flags		= IORESOURCE_MEM,
+	},
+	{
+		/* start filled at runtime */
+		.flags		= IORESOURCE_IRQ,
+	},
 };

-int __init bcm63xx_uart_register(void)
+static struct platform_device bcm63xx_uart_devices[] = {
+	{
+		.name		= "bcm63xx_uart",
+		.id		= 0,
+		.num_resources	= ARRAY_SIZE(uart0_resources),
+		.resource	= uart0_resources,
+	},
+
+	{
+		.name		= "bcm63xx_uart",
+		.id		= 1,
+		.num_resources	= ARRAY_SIZE(uart1_resources),
+		.resource	= uart1_resources,
+	}
+};
+
+int __init bcm63xx_uart_register(unsigned int id)
 {
-	uart_resources[0].start = bcm63xx_regset_address(RSET_UART0);
-	uart_resources[0].end = uart_resources[0].start;
-	uart_resources[0].end += RSET_UART_SIZE - 1;
-	uart_resources[1].start = bcm63xx_get_irq_number(IRQ_UART0);
-	return platform_device_register(&bcm63xx_uart_device);
+	if (id >= ARRAY_SIZE(bcm63xx_uart_devices))
+		return -ENODEV;
+
+	if (id == 1 && !BCMCPU_IS_6358())
+		return -ENODEV;
+
+	if (id == 0) {
+		uart0_resources[0].start = bcm63xx_regset_address(RSET_UART0);
+		uart0_resources[0].end = uart0_resources[0].start +
+			RSET_UART_SIZE - 1;
+		uart0_resources[1].start = bcm63xx_get_irq_number(IRQ_UART0);
+	}
+
+	if (id == 1) {
+		uart1_resources[0].start = bcm63xx_regset_address(RSET_UART1);
+		uart1_resources[0].end = uart1_resources[0].start +
+			RSET_UART_SIZE - 1;
+		uart1_resources[1].start = bcm63xx_get_irq_number(IRQ_UART1);
+	}
+
+	return platform_device_register(&bcm63xx_uart_devices[id]);
 }
-arch_initcall(bcm63xx_uart_register);
--- a/arch/mips/bcm63xx/gpio.c
+++ b/arch/mips/bcm63xx/gpio.c
@ -125,10 +125,10 @@ static struct gpio_chip bcm63xx_gpio_chip = {

 int __init bcm63xx_gpio_init(void)
 {
+	gpio_out_low = bcm_gpio_readl(GPIO_DATA_LO_REG);
+	gpio_out_high = bcm_gpio_readl(GPIO_DATA_HI_REG);
 	bcm63xx_gpio_chip.ngpio = bcm63xx_gpio_count();
 	pr_info("registering %d GPIOs\n", bcm63xx_gpio_chip.ngpio);

 	return gpiochip_add(&bcm63xx_gpio_chip);
 }
-
-arch_initcall(bcm63xx_gpio_init);
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@ -45,9 +45,6 @@ extern struct plat_smp_ops octeon_smp_ops;
 extern void pci_console_init(const char *arg);
 #endif

-#ifdef CONFIG_CAVIUM_RESERVE32
-extern uint64_t octeon_reserve32_memory;
-#endif
 static unsigned long long MAX_MEMORY = 512ull << 20;

 struct octeon_boot_descriptor *octeon_boot_desc_ptr;
@ -186,54 +183,6 @@ void octeon_check_cpu_bist(void)
 	write_octeon_c0_dcacheerr(0);
 }

-#ifdef CONFIG_CAVIUM_RESERVE32_USE_WIRED_TLB
-/**
- * Called on every core to setup the wired tlb entry needed
- * if CONFIG_CAVIUM_RESERVE32_USE_WIRED_TLB is set.
- *
- */
-static void octeon_hal_setup_per_cpu_reserved32(void *unused)
-{
-	/*
-	 * The config has selected to wire the reserve32 memory for all
-	 * userspace applications. We need to put a wired TLB entry in for each
-	 * 512MB of reserve32 memory. We only handle double 256MB pages here,
-	 * so reserve32 must be multiple of 512MB.
-	 */
-	uint32_t size = CONFIG_CAVIUM_RESERVE32;
-	uint32_t entrylo0 =
-		0x7 | ((octeon_reserve32_memory & ((1ul << 40) - 1)) >> 6);
-	uint32_t entrylo1 = entrylo0 + (256 << 14);
-	uint32_t entryhi = (0x80000000UL - (CONFIG_CAVIUM_RESERVE32 << 20));
-	while (size >= 512) {
-#if 0
-		pr_info("CPU%d: Adding double wired TLB entry for 0x%lx\n",
-			smp_processor_id(), entryhi);
-#endif
-		add_wired_entry(entrylo0, entrylo1, entryhi, PM_256M);
-		entrylo0 += 512 << 14;
-		entrylo1 += 512 << 14;
-		entryhi += 512 << 20;
-		size -= 512;
-	}
-}
-#endif /* CONFIG_CAVIUM_RESERVE32_USE_WIRED_TLB */
-
-/**
- * Called to release the named block which was used to made sure
- * that nobody used the memory for something else during
- * init. Now we'll free it so userspace apps can use this
- * memory region with bootmem_alloc.
- *
- * This function is called only once from prom_free_prom_memory().
- */
-void octeon_hal_setup_reserved32(void)
-{
-#ifdef CONFIG_CAVIUM_RESERVE32_USE_WIRED_TLB
-	on_each_cpu(octeon_hal_setup_per_cpu_reserved32, NULL, 0, 1);
-#endif
-}
-
 /**
 * Reboot Octeon
 *
@ -294,18 +243,6 @@ static void octeon_halt(void)
 	octeon_kill_core(NULL);
 }

-#if 0
-/**
- * Platform time init specifics.
- * Returns
- */
-void __init plat_time_init(void)
-{
-	/* Nothing special here, but we are required to have one */
-}
-
-#endif
-
 /**
 * Handle all the error condition interrupts that might occur.
 *
@ -502,25 +439,13 @@ void __init prom_init(void)
 	 * memory when it is getting memory from the
 	 * bootloader. Later, after the memory allocations are
 	 * complete, the reserve32 will be freed.
-	 */
-#ifdef CONFIG_CAVIUM_RESERVE32_USE_WIRED_TLB
-	if (CONFIG_CAVIUM_RESERVE32 & 0x1ff)
-		pr_err("CAVIUM_RESERVE32 isn't a multiple of 512MB. "
-		       "This is required if CAVIUM_RESERVE32_USE_WIRED_TLB "
-		       "is set\n");
-	else
-		addr = cvmx_bootmem_phy_named_block_alloc(CONFIG_CAVIUM_RESERVE32 << 20,
-							0, 0, 512 << 20,
-							"CAVIUM_RESERVE32", 0);
-#else
-	/*
+	 *
 	 * Allocate memory for RESERVED32 aligned on 2MB boundary. This
 	 * is in case we later use hugetlb entries with it.
 	 */
 	addr = cvmx_bootmem_phy_named_block_alloc(CONFIG_CAVIUM_RESERVE32 << 20,
 						0, 0, 2 << 20,
 						"CAVIUM_RESERVE32", 0);
-#endif
 	if (addr < 0)
 		pr_err("Failed to allocate CAVIUM_RESERVE32 memory area\n");
 	else
@ -817,9 +742,4 @@ void prom_free_prom_memory(void)
 		panic("Unable to request_irq(OCTEON_IRQ_RML)\n");
 	}
 #endif
-
-	/* This call is here so that it is performed after any TLB
-	   initializations. It needs to be after these in case the
-	   CONFIG_CAVIUM_RESERVE32_USE_WIRED_TLB option is set */
-	octeon_hal_setup_reserved32();
 }
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@ -279,14 +279,6 @@ static void octeon_cpu_die(unsigned int cpu)
 	uint32_t avail_coremask;
 	struct cvmx_bootmem_named_block_desc *block_desc;

-#ifdef CONFIG_CAVIUM_OCTEON_WATCHDOG
-	/* Disable the watchdog */
-	cvmx_ciu_wdogx_t ciu_wdog;
-	ciu_wdog.u64 = cvmx_read_csr(CVMX_CIU_WDOGX(cpu));
-	ciu_wdog.s.mode = 0;
-	cvmx_write_csr(CVMX_CIU_WDOGX(cpu), ciu_wdog.u64);
-#endif
-
 	while (per_cpu(cpu_state, cpu) != CPU_DEAD)
 		cpu_relax();

--- a/arch/mips/configs/bigsur_defconfig
+++ b/arch/mips/configs/bigsur_defconfig
--- a/arch/mips/include/asm/abi.h
+++ b/arch/mips/include/asm/abi.h
@ -13,12 +13,14 @@
 #include <asm/siginfo.h>

 struct mips_abi {
-	int (* const setup_frame)(struct k_sigaction * ka,
+	int (* const setup_frame)(void *sig_return, struct k_sigaction *ka,
 	                          struct pt_regs *regs, int signr,
 	                          sigset_t *set);
-	int (* const setup_rt_frame)(struct k_sigaction * ka,
+	const unsigned long	signal_return_offset;
+	int (* const setup_rt_frame)(void *sig_return, struct k_sigaction *ka,
 	                       struct pt_regs *regs, int signr,
 	                       sigset_t *set, siginfo_t *info);
+	const unsigned long	rt_signal_return_offset;
 	const unsigned long	restart;
 };

--- a/arch/mips/include/asm/elf.h
+++ b/arch/mips/include/asm/elf.h
@ -310,6 +310,7 @@ do {									\

 #endif /* CONFIG_64BIT */

+struct pt_regs;
 struct task_struct;

 extern void elf_dump_regs(elf_greg_t *, struct pt_regs *regs);
@ -367,4 +368,8 @@ extern const char *__elf_platform;
 #define ELF_ET_DYN_BASE         (TASK_SIZE / 3 * 2)
 #endif

+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+				       int uses_interp);
 #endif /* _ASM_ELF_H */
--- a/arch/mips/include/asm/fpu_emulator.h
+++ b/arch/mips/include/asm/fpu_emulator.h
@ -41,7 +41,11 @@ struct mips_fpu_emulator_stats {
 DECLARE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats);

 #define MIPS_FPU_EMU_INC_STATS(M)					\
-	cpu_local_wrap(__local_inc(&__get_cpu_var(fpuemustats).M))
+do {									\
+	preempt_disable();						\
+	__local_inc(&__get_cpu_var(fpuemustats).M);			\
+	preempt_enable();						\
+} while (0)

 #else
 #define MIPS_FPU_EMU_INC_STATS(M) do { } while (0)
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_cpu.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_cpu.h
@ -85,6 +85,7 @@ enum bcm63xx_regs_set {
 	RSET_TIMER,
 	RSET_WDT,
 	RSET_UART0,
+	RSET_UART1,
 	RSET_GPIO,
 	RSET_SPI,
 	RSET_UDC0,
@ -123,6 +124,7 @@ enum bcm63xx_regs_set {
 #define BCM_6338_TIMER_BASE		(0xfffe0200)
 #define BCM_6338_WDT_BASE		(0xfffe021c)
 #define BCM_6338_UART0_BASE		(0xfffe0300)
+#define BCM_6338_UART1_BASE		(0xdeadbeef)
 #define BCM_6338_GPIO_BASE		(0xfffe0400)
 #define BCM_6338_SPI_BASE		(0xfffe0c00)
 #define BCM_6338_UDC0_BASE		(0xdeadbeef)
@ -153,6 +155,7 @@ enum bcm63xx_regs_set {
 #define BCM_6345_TIMER_BASE		(0xfffe0200)
 #define BCM_6345_WDT_BASE		(0xfffe021c)
 #define BCM_6345_UART0_BASE		(0xfffe0300)
+#define BCM_6345_UART1_BASE		(0xdeadbeef)
 #define BCM_6345_GPIO_BASE		(0xfffe0400)
 #define BCM_6345_SPI_BASE		(0xdeadbeef)
 #define BCM_6345_UDC0_BASE		(0xdeadbeef)
@ -182,6 +185,7 @@ enum bcm63xx_regs_set {
 #define BCM_6348_TIMER_BASE		(0xfffe0200)
 #define BCM_6348_WDT_BASE		(0xfffe021c)
 #define BCM_6348_UART0_BASE		(0xfffe0300)
+#define BCM_6348_UART1_BASE		(0xdeadbeef)
 #define BCM_6348_GPIO_BASE		(0xfffe0400)
 #define BCM_6348_SPI_BASE		(0xfffe0c00)
 #define BCM_6348_UDC0_BASE		(0xfffe1000)
@ -208,6 +212,7 @@ enum bcm63xx_regs_set {
 #define BCM_6358_TIMER_BASE		(0xfffe0040)
 #define BCM_6358_WDT_BASE		(0xfffe005c)
 #define BCM_6358_UART0_BASE		(0xfffe0100)
+#define BCM_6358_UART1_BASE		(0xfffe0120)
 #define BCM_6358_GPIO_BASE		(0xfffe0080)
 #define BCM_6358_SPI_BASE		(0xdeadbeef)
 #define BCM_6358_UDC0_BASE		(0xfffe0800)
@ -246,6 +251,8 @@ static inline unsigned long bcm63xx_regset_address(enum bcm63xx_regs_set set)
 		return BCM_6338_WDT_BASE;
 	case RSET_UART0:
 		return BCM_6338_UART0_BASE;
+	case RSET_UART1:
+		return BCM_6338_UART1_BASE;
 	case RSET_GPIO:
 		return BCM_6338_GPIO_BASE;
 	case RSET_SPI:
@ -292,6 +299,8 @@ static inline unsigned long bcm63xx_regset_address(enum bcm63xx_regs_set set)
 		return BCM_6345_WDT_BASE;
 	case RSET_UART0:
 		return BCM_6345_UART0_BASE;
+	case RSET_UART1:
+		return BCM_6345_UART1_BASE;
 	case RSET_GPIO:
 		return BCM_6345_GPIO_BASE;
 	case RSET_SPI:
@ -338,6 +347,8 @@ static inline unsigned long bcm63xx_regset_address(enum bcm63xx_regs_set set)
 		return BCM_6348_WDT_BASE;
 	case RSET_UART0:
 		return BCM_6348_UART0_BASE;
+	case RSET_UART1:
+		return BCM_6348_UART1_BASE;
 	case RSET_GPIO:
 		return BCM_6348_GPIO_BASE;
 	case RSET_SPI:
@ -384,6 +395,8 @@ static inline unsigned long bcm63xx_regset_address(enum bcm63xx_regs_set set)
 		return BCM_6358_WDT_BASE;
 	case RSET_UART0:
 		return BCM_6358_UART0_BASE;
+	case RSET_UART1:
+		return BCM_6358_UART1_BASE;
 	case RSET_GPIO:
 		return BCM_6358_GPIO_BASE;
 	case RSET_SPI:
@ -429,6 +442,7 @@ static inline unsigned long bcm63xx_regset_address(enum bcm63xx_regs_set set)
 enum bcm63xx_irq {
 	IRQ_TIMER = 0,
 	IRQ_UART0,
+	IRQ_UART1,
 	IRQ_DSL,
 	IRQ_ENET0,
 	IRQ_ENET1,
@ -510,6 +524,7 @@ enum bcm63xx_irq {
 */
 #define BCM_6358_TIMER_IRQ		(IRQ_INTERNAL_BASE + 0)
 #define BCM_6358_UART0_IRQ		(IRQ_INTERNAL_BASE + 2)
+#define BCM_6358_UART1_IRQ		(IRQ_INTERNAL_BASE + 3)
 #define BCM_6358_OHCI0_IRQ		(IRQ_INTERNAL_BASE + 5)
 #define BCM_6358_ENET1_IRQ		(IRQ_INTERNAL_BASE + 6)
 #define BCM_6358_ENET0_IRQ		(IRQ_INTERNAL_BASE + 8)
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_uart.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_uart.h
@ -0,0 +1,6 @@
+#ifndef BCM63XX_DEV_UART_H_
+#define BCM63XX_DEV_UART_H_
+
+int bcm63xx_uart_register(unsigned int id);
+
+#endif /* BCM63XX_DEV_UART_H_ */
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_gpio.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_gpio.h
@ -10,6 +10,10 @@ static inline unsigned long bcm63xx_gpio_count(void)
 	switch (bcm63xx_get_cpu_id()) {
 	case BCM6358_CPU_ID:
 		return 40;
+	case BCM6338_CPU_ID:
+		return 8;
+	case BCM6345_CPU_ID:
+		return 16;
 	case BCM6348_CPU_ID:
 	default:
 		return 37;
--- a/arch/mips/include/asm/mach-bcm63xx/board_bcm963xx.h
+++ b/arch/mips/include/asm/mach-bcm63xx/board_bcm963xx.h
@ -45,6 +45,8 @@ struct board_info {
 	unsigned int	has_ohci0:1;
 	unsigned int	has_ehci0:1;
 	unsigned int	has_dsp:1;
+	unsigned int	has_uart0:1;
+	unsigned int	has_uart1:1;

 	/* ethernet config */
 	struct bcm63xx_enet_platform_data enet0;
--- a/arch/mips/include/asm/mach-bcm63xx/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-bcm63xx/cpu-feature-overrides.h
@ -24,7 +24,7 @@
 #define cpu_has_smartmips		0
 #define cpu_has_vtag_icache		0

-#if !defined(BCMCPU_RUNTIME_DETECT) && (defined(CONFIG_BCMCPU_IS_6348) || defined(CONFIG_CPU_IS_6338) || defined(CONFIG_CPU_IS_BCM6345))
+#if !defined(BCMCPU_RUNTIME_DETECT) && (defined(CONFIG_BCM63XX_CPU_6348) || defined(CONFIG_BCM63XX_CPU_6345) || defined(CONFIG_BCM63XX_CPU_6338))
 #define cpu_has_dc_aliases		0
 #endif

--- a/arch/mips/include/asm/mach-sibyte/war.h
+++ b/arch/mips/include/asm/mach-sibyte/war.h
@ -16,7 +16,11 @@
 #if defined(CONFIG_SB1_PASS_1_WORKAROUNDS) || \
    defined(CONFIG_SB1_PASS_2_WORKAROUNDS)

-#define BCM1250_M3_WAR	1
+#ifndef __ASSEMBLY__
+extern int sb1250_m3_workaround_needed(void);
+#endif
+
+#define BCM1250_M3_WAR	sb1250_m3_workaround_needed()
 #define SIBYTE_1956_WAR	1

 #else
--- a/arch/mips/include/asm/mmu.h
+++ b/arch/mips/include/asm/mmu.h
@ -1,6 +1,9 @@
 #ifndef __ASM_MMU_H
 #define __ASM_MMU_H

-typedef unsigned long mm_context_t[NR_CPUS];
+typedef struct {
+	unsigned long asid[NR_CPUS];
+	void *vdso;
+} mm_context_t;

 #endif /* __ASM_MMU_H */
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@ -104,7 +104,7 @@ extern unsigned long smtc_asid_mask;

 #endif

-#define cpu_context(cpu, mm)	((mm)->context[cpu])
+#define cpu_context(cpu, mm)	((mm)->context.asid[cpu])
 #define cpu_asid(cpu, mm)	(cpu_context((cpu), (mm)) & ASID_MASK)
 #define asid_cache(cpu)		(cpu_data[cpu].asid_cache)

--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@ -188,8 +188,10 @@ typedef struct { unsigned long pgprot; } pgprot_t;
 #define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
 				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)

-#define UNCAC_ADDR(addr)	((addr) - PAGE_OFFSET + UNCAC_BASE)
-#define CAC_ADDR(addr)		((addr) - UNCAC_BASE + PAGE_OFFSET)
+#define UNCAC_ADDR(addr)	((addr) - PAGE_OFFSET + UNCAC_BASE + 	\
+								PHYS_OFFSET)
+#define CAC_ADDR(addr)		((addr) - UNCAC_BASE + PAGE_OFFSET -	\
+								PHYS_OFFSET)

 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@ -33,13 +33,19 @@ extern void (*cpu_wait)(void);

 extern unsigned int vced_count, vcei_count;

+/*
+ * A special page (the vdso) is mapped into all processes at the very
+ * top of the virtual memory space.
+ */
+#define SPECIAL_PAGES_SIZE PAGE_SIZE
+
 #ifdef CONFIG_32BIT
 /*
 * User space process size: 2GB. This is hardcoded into a few places,
 * so don't change it unless you know what you are doing.
 */
 #define TASK_SIZE	0x7fff8000UL
-#define STACK_TOP	TASK_SIZE
+#define STACK_TOP	((TASK_SIZE & PAGE_MASK) - SPECIAL_PAGES_SIZE)

 /*
 * This decides where the kernel will search for a free chunk of vm
@ -59,7 +65,8 @@ extern unsigned int vced_count, vcei_count;
 #define TASK_SIZE32	0x7fff8000UL
 #define TASK_SIZE	0x10000000000UL
 #define STACK_TOP	\
-      (test_thread_flag(TIF_32BIT_ADDR) ? TASK_SIZE32 : TASK_SIZE)
+	(((test_thread_flag(TIF_32BIT_ADDR) ?				\
+	   TASK_SIZE32 : TASK_SIZE) & PAGE_MASK) - SPECIAL_PAGES_SIZE)

 /*
 * This decides where the kernel will search for a free chunk of vm
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@ -121,6 +121,25 @@
 		.endm
 #else
 		.macro	get_saved_sp	/* Uniprocessor variation */
+#ifdef CONFIG_CPU_LOONGSON2F
+		/*
+		 * Clear BTB (branch target buffer), forbid RAS (return address
+		 * stack) to workaround the Out-of-order Issue in Loongson2F
+		 * via its diagnostic register.
+		 */
+		move	k0, ra
+		jal	1f
+		 nop
+1:		jal	1f
+		 nop
+1:		jal	1f
+		 nop
+1:		jal	1f
+		 nop
+1:		move	ra, k0
+		li	k0, 3
+		mtc0	k0, $22
+#endif /* CONFIG_CPU_LOONGSON2F */
 #if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
 		lui	k1, %hi(kernelsp)
 #else
--- a/arch/mips/include/asm/uasm.h
+++ b/arch/mips/include/asm/uasm.h
@ -84,6 +84,7 @@ Ip_u2s3u1(_lw);
 Ip_u1u2u3(_mfc0);
 Ip_u1u2u3(_mtc0);
 Ip_u2u1u3(_ori);
+Ip_u3u1u2(_or);
 Ip_u2s3u1(_pref);
 Ip_0(_rfe);
 Ip_u2s3u1(_sc);
@ -102,6 +103,7 @@ Ip_0(_tlbwr);
 Ip_u3u1u2(_xor);
 Ip_u2u1u3(_xori);
 Ip_u2u1msbu3(_dins);
+Ip_u1(_syscall);

 /* Handle labels. */
 struct uasm_label {
--- a/arch/mips/include/asm/vdso.h
+++ b/arch/mips/include/asm/vdso.h
@ -0,0 +1,29 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2009 Cavium Networks
+ */
+
+#ifndef __ASM_VDSO_H
+#define __ASM_VDSO_H
+
+#include <linux/types.h>
+
+
+#ifdef CONFIG_32BIT
+struct mips_vdso {
+	u32 signal_trampoline[2];
+	u32 rt_signal_trampoline[2];
+};
+#else  /* !CONFIG_32BIT */
+struct mips_vdso {
+	u32 o32_signal_trampoline[2];
+	u32 o32_rt_signal_trampoline[2];
+	u32 rt_signal_trampoline[2];
+	u32 n32_rt_signal_trampoline[2];
+};
+#endif /* CONFIG_32BIT */
+
+#endif /* __ASM_VDSO_H */
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@ -6,7 +6,7 @@ extra-y		:= head.o init_task.o vmlinux.lds

 obj-y		+= cpu-probe.o branch.o entry.o genex.o irq.o process.o \
 		   ptrace.o reset.o setup.o signal.o syscall.o \
-		   time.o topology.o traps.o unaligned.o watch.o
+		   time.o topology.o traps.o unaligned.o watch.o vdso.o

 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_ftrace.o = -pg
--- a/arch/mips/kernel/cpufreq/loongson2_clock.c
+++ b/arch/mips/kernel/cpufreq/loongson2_clock.c
@ -164,3 +164,7 @@ void loongson2_cpu_wait(void)
 	spin_unlock_irqrestore(&loongson2_wait_lock, flags);
 }
 EXPORT_SYMBOL_GPL(loongson2_cpu_wait);
+
+MODULE_AUTHOR("Yanhua <yanh@lemote.com>");
+MODULE_DESCRIPTION("cpufreq driver for Loongson 2F");
+MODULE_LICENSE("GPL");
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@ -63,8 +63,13 @@ void __noreturn cpu_idle(void)

 			smtc_idle_loop_hook();
 #endif
-			if (cpu_wait)
+
+			if (cpu_wait) {
+				/* Don't trace irqs off for idle */
+				stop_critical_timings();
 				(*cpu_wait)();
+				start_critical_timings();
+			}
 		}
 #ifdef CONFIG_HOTPLUG_CPU
 		if (!cpu_online(cpu) && !cpu_isset(cpu, cpu_callin_map) &&
--- a/arch/mips/kernel/signal-common.h
+++ b/arch/mips/kernel/signal-common.h
@ -26,11 +26,6 @@
 */
 extern void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
 				 size_t frame_size);
-/*
- * install trampoline code to get back from the sig handler
- */
-extern int install_sigtramp(unsigned int __user *tramp, unsigned int syscall);
-
 /* Check and clear pending FPU exceptions in saved CSR */
 extern int fpcsr_pending(unsigned int __user *fpcsr);

--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@ -32,6 +32,7 @@
 #include <asm/ucontext.h>
 #include <asm/cpu-features.h>
 #include <asm/war.h>
+#include <asm/vdso.h>

 #include "signal-common.h"

@ -44,47 +45,20 @@ extern asmlinkage int _restore_fp_context(struct sigcontext __user *sc);
 extern asmlinkage int fpu_emulator_save_context(struct sigcontext __user *sc);
 extern asmlinkage int fpu_emulator_restore_context(struct sigcontext __user *sc);

-/*
- * Horribly complicated - with the bloody RM9000 workarounds enabled
- * the signal trampolines is moving to the end of the structure so we can
- * increase the alignment without breaking software compatibility.
- */
-#if ICACHE_REFILLS_WORKAROUND_WAR == 0
-
 struct sigframe {
 	u32 sf_ass[4];		/* argument save space for o32 */
-	u32 sf_code[2];		/* signal trampoline */
+	u32 sf_pad[2];		/* Was: signal trampoline */
 	struct sigcontext sf_sc;
 	sigset_t sf_mask;
 };

 struct rt_sigframe {
 	u32 rs_ass[4];		/* argument save space for o32 */
-	u32 rs_code[2];		/* signal trampoline */
+	u32 rs_pad[2];		/* Was: signal trampoline */
 	struct siginfo rs_info;
 	struct ucontext rs_uc;
 };

-#else
-
-struct sigframe {
-	u32 sf_ass[4];			/* argument save space for o32 */
-	u32 sf_pad[2];
-	struct sigcontext sf_sc;	/* hw context */
-	sigset_t sf_mask;
-	u32 sf_code[8] ____cacheline_aligned;	/* signal trampoline */
-};
-
-struct rt_sigframe {
-	u32 rs_ass[4];			/* argument save space for o32 */
-	u32 rs_pad[2];
-	struct siginfo rs_info;
-	struct ucontext rs_uc;
-	u32 rs_code[8] ____cacheline_aligned;	/* signal trampoline */
-};
-
-#endif
-
 /*
 * Helper routines
 */
@ -266,32 +240,6 @@ void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
 	return (void __user *)((sp - frame_size) & (ICACHE_REFILLS_WORKAROUND_WAR ? ~(cpu_icache_line_size()-1) : ALMASK));
 }

-int install_sigtramp(unsigned int __user *tramp, unsigned int syscall)
-{
-	int err;
-
-	/*
-	 * Set up the return code ...
-	 *
-	 *         li      v0, __NR__foo_sigreturn
-	 *         syscall
-	 */
-
-	err = __put_user(0x24020000 + syscall, tramp + 0);
-	err |= __put_user(0x0000000c         , tramp + 1);
-	if (ICACHE_REFILLS_WORKAROUND_WAR) {
-		err |= __put_user(0, tramp + 2);
-		err |= __put_user(0, tramp + 3);
-		err |= __put_user(0, tramp + 4);
-		err |= __put_user(0, tramp + 5);
-		err |= __put_user(0, tramp + 6);
-		err |= __put_user(0, tramp + 7);
-	}
-	flush_cache_sigtramp((unsigned long) tramp);
-
-	return err;
-}
-
 /*
 * Atomically swap in the new signal mask, and wait for a signal.
 */
@ -484,8 +432,8 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 }

 #ifdef CONFIG_TRAD_SIGNALS
-static int setup_frame(struct k_sigaction * ka, struct pt_regs *regs,
-	int signr, sigset_t *set)
+static int setup_frame(void *sig_return, struct k_sigaction *ka,
+		       struct pt_regs *regs, int signr, sigset_t *set)
 {
 	struct sigframe __user *frame;
 	int err = 0;
@ -494,8 +442,6 @@ static int setup_frame(struct k_sigaction * ka, struct pt_regs *regs,
 	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
 		goto give_sigsegv;

-	err |= install_sigtramp(frame->sf_code, __NR_sigreturn);
-
 	err |= setup_sigcontext(regs, &frame->sf_sc);
 	err |= __copy_to_user(&frame->sf_mask, set, sizeof(*set));
 	if (err)
@ -515,7 +461,7 @@ static int setup_frame(struct k_sigaction * ka, struct pt_regs *regs,
 	regs->regs[ 5] = 0;
 	regs->regs[ 6] = (unsigned long) &frame->sf_sc;
 	regs->regs[29] = (unsigned long) frame;
-	regs->regs[31] = (unsigned long) frame->sf_code;
+	regs->regs[31] = (unsigned long) sig_return;
 	regs->cp0_epc = regs->regs[25] = (unsigned long) ka->sa.sa_handler;

 	DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n",
@ -529,8 +475,9 @@ static int setup_frame(struct k_sigaction * ka, struct pt_regs *regs,
 }
 #endif

-static int setup_rt_frame(struct k_sigaction * ka, struct pt_regs *regs,
-	int signr, sigset_t *set, siginfo_t *info)
+static int setup_rt_frame(void *sig_return, struct k_sigaction *ka,
+			  struct pt_regs *regs,	int signr, sigset_t *set,
+			  siginfo_t *info)
 {
 	struct rt_sigframe __user *frame;
 	int err = 0;
@ -539,8 +486,6 @@ static int setup_rt_frame(struct k_sigaction * ka, struct pt_regs *regs,
 	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
 		goto give_sigsegv;

-	err |= install_sigtramp(frame->rs_code, __NR_rt_sigreturn);
-
 	/* Create siginfo.  */
 	err |= copy_siginfo_to_user(&frame->rs_info, info);

@ -573,7 +518,7 @@ static int setup_rt_frame(struct k_sigaction * ka, struct pt_regs *regs,
 	regs->regs[ 5] = (unsigned long) &frame->rs_info;
 	regs->regs[ 6] = (unsigned long) &frame->rs_uc;
 	regs->regs[29] = (unsigned long) frame;
-	regs->regs[31] = (unsigned long) frame->rs_code;
+	regs->regs[31] = (unsigned long) sig_return;
 	regs->cp0_epc = regs->regs[25] = (unsigned long) ka->sa.sa_handler;

 	DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n",
@ -590,8 +535,11 @@ static int setup_rt_frame(struct k_sigaction * ka, struct pt_regs *regs,
 struct mips_abi mips_abi = {
 #ifdef CONFIG_TRAD_SIGNALS
 	.setup_frame	= setup_frame,
+	.signal_return_offset = offsetof(struct mips_vdso, signal_trampoline),
 #endif
 	.setup_rt_frame	= setup_rt_frame,
+	.rt_signal_return_offset =
+		offsetof(struct mips_vdso, rt_signal_trampoline),
 	.restart	= __NR_restart_syscall
 };

@ -599,6 +547,8 @@ static int handle_signal(unsigned long sig, siginfo_t *info,
 	struct k_sigaction *ka, sigset_t *oldset, struct pt_regs *regs)
 {
 	int ret;
+	struct mips_abi *abi = current->thread.abi;
+	void *vdso = current->mm->context.vdso;

 	switch(regs->regs[0]) {
 	case ERESTART_RESTARTBLOCK:
@ -619,9 +569,11 @@ static int handle_signal(unsigned long sig, siginfo_t *info,
 	regs->regs[0] = 0;		/* Don't deal with this again.  */

 	if (sig_uses_siginfo(ka))
-		ret = current->thread.abi->setup_rt_frame(ka, regs, sig, oldset, info);
+		ret = abi->setup_rt_frame(vdso + abi->rt_signal_return_offset,
+					  ka, regs, sig, oldset, info);
 	else
-		ret = current->thread.abi->setup_frame(ka, regs, sig, oldset);
+		ret = abi->setup_frame(vdso + abi->signal_return_offset,
+				       ka, regs, sig, oldset);

 	spin_lock_irq(&current->sighand->siglock);
 	sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@ -32,6 +32,7 @@
 #include <asm/system.h>
 #include <asm/fpu.h>
 #include <asm/war.h>
+#include <asm/vdso.h>

 #include "signal-common.h"

@ -47,8 +48,6 @@ extern asmlinkage int fpu_emulator_restore_context32(struct sigcontext32 __user
 /*
 * Including <asm/unistd.h> would give use the 64-bit syscall numbers ...
 */
-#define __NR_O32_sigreturn		4119
-#define __NR_O32_rt_sigreturn		4193
 #define __NR_O32_restart_syscall        4253

 /* 32-bit compatibility types */
@ -77,47 +76,20 @@ struct ucontext32 {
 	compat_sigset_t     uc_sigmask;   /* mask last for extensibility */
 };

-/*
- * Horribly complicated - with the bloody RM9000 workarounds enabled
- * the signal trampolines is moving to the end of the structure so we can
- * increase the alignment without breaking software compatibility.
- */
-#if ICACHE_REFILLS_WORKAROUND_WAR == 0
-
 struct sigframe32 {
 	u32 sf_ass[4];		/* argument save space for o32 */
-	u32 sf_code[2];		/* signal trampoline */
+	u32 sf_pad[2];		/* Was: signal trampoline */
 	struct sigcontext32 sf_sc;
 	compat_sigset_t sf_mask;
 };

 struct rt_sigframe32 {
 	u32 rs_ass[4];			/* argument save space for o32 */
-	u32 rs_code[2];			/* signal trampoline */
+	u32 rs_pad[2];			/* Was: signal trampoline */
 	compat_siginfo_t rs_info;
 	struct ucontext32 rs_uc;
 };

-#else  /* ICACHE_REFILLS_WORKAROUND_WAR */
-
-struct sigframe32 {
-	u32 sf_ass[4];			/* argument save space for o32 */
-	u32 sf_pad[2];
-	struct sigcontext32 sf_sc;	/* hw context */
-	compat_sigset_t sf_mask;
-	u32 sf_code[8] ____cacheline_aligned;	/* signal trampoline */
-};
-
-struct rt_sigframe32 {
-	u32 rs_ass[4];			/* argument save space for o32 */
-	u32 rs_pad[2];
-	compat_siginfo_t rs_info;
-	struct ucontext32 rs_uc;
-	u32 rs_code[8] __attribute__((aligned(32)));	/* signal trampoline */
-};
-
-#endif	/* !ICACHE_REFILLS_WORKAROUND_WAR */
-
 /*
 * sigcontext handlers
 */
@ -598,8 +570,8 @@ asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	force_sig(SIGSEGV, current);
 }

-static int setup_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
-	int signr, sigset_t *set)
+static int setup_frame_32(void *sig_return, struct k_sigaction *ka,
+			  struct pt_regs *regs, int signr, sigset_t *set)
 {
 	struct sigframe32 __user *frame;
 	int err = 0;
@ -608,8 +580,6 @@ static int setup_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
 	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
 		goto give_sigsegv;

-	err |= install_sigtramp(frame->sf_code, __NR_O32_sigreturn);
-
 	err |= setup_sigcontext32(regs, &frame->sf_sc);
 	err |= __copy_conv_sigset_to_user(&frame->sf_mask, set);

@ -630,7 +600,7 @@ static int setup_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
 	regs->regs[ 5] = 0;
 	regs->regs[ 6] = (unsigned long) &frame->sf_sc;
 	regs->regs[29] = (unsigned long) frame;
-	regs->regs[31] = (unsigned long) frame->sf_code;
+	regs->regs[31] = (unsigned long) sig_return;
 	regs->cp0_epc = regs->regs[25] = (unsigned long) ka->sa.sa_handler;

 	DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n",
@ -644,8 +614,9 @@ static int setup_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
 	return -EFAULT;
 }

-static int setup_rt_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
-	int signr, sigset_t *set, siginfo_t *info)
+static int setup_rt_frame_32(void *sig_return, struct k_sigaction *ka,
+			     struct pt_regs *regs, int signr, sigset_t *set,
+			     siginfo_t *info)
 {
 	struct rt_sigframe32 __user *frame;
 	int err = 0;
@ -655,8 +626,6 @@ static int setup_rt_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
 	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
 		goto give_sigsegv;

-	err |= install_sigtramp(frame->rs_code, __NR_O32_rt_sigreturn);
-
 	/* Convert (siginfo_t -> compat_siginfo_t) and copy to user. */
 	err |= copy_siginfo_to_user32(&frame->rs_info, info);

@ -690,7 +659,7 @@ static int setup_rt_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
 	regs->regs[ 5] = (unsigned long) &frame->rs_info;
 	regs->regs[ 6] = (unsigned long) &frame->rs_uc;
 	regs->regs[29] = (unsigned long) frame;
-	regs->regs[31] = (unsigned long) frame->rs_code;
+	regs->regs[31] = (unsigned long) sig_return;
 	regs->cp0_epc = regs->regs[25] = (unsigned long) ka->sa.sa_handler;

 	DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n",
@ -709,7 +678,11 @@ static int setup_rt_frame_32(struct k_sigaction * ka, struct pt_regs *regs,
 */
 struct mips_abi mips_abi_32 = {
 	.setup_frame	= setup_frame_32,
+	.signal_return_offset =
+		offsetof(struct mips_vdso, o32_signal_trampoline),
 	.setup_rt_frame	= setup_rt_frame_32,
+	.rt_signal_return_offset =
+		offsetof(struct mips_vdso, o32_rt_signal_trampoline),
 	.restart	= __NR_O32_restart_syscall
 };

--- a/arch/mips/kernel/signal_n32.c
+++ b/arch/mips/kernel/signal_n32.c
@ -39,13 +39,13 @@
 #include <asm/fpu.h>
 #include <asm/cpu-features.h>
 #include <asm/war.h>
+#include <asm/vdso.h>

 #include "signal-common.h"

 /*
 * Including <asm/unistd.h> would give use the 64-bit syscall numbers ...
 */
-#define __NR_N32_rt_sigreturn		6211
 #define __NR_N32_restart_syscall	6214

 extern int setup_sigcontext(struct pt_regs *, struct sigcontext __user *);
@ -67,27 +67,13 @@ struct ucontextn32 {
 	compat_sigset_t     uc_sigmask;   /* mask last for extensibility */
 };

-#if ICACHE_REFILLS_WORKAROUND_WAR == 0
-
 struct rt_sigframe_n32 {
 	u32 rs_ass[4];			/* argument save space for o32 */
-	u32 rs_code[2];			/* signal trampoline */
+	u32 rs_pad[2];			/* Was: signal trampoline */
 	struct compat_siginfo rs_info;
 	struct ucontextn32 rs_uc;
 };

-#else  /* ICACHE_REFILLS_WORKAROUND_WAR */
-
-struct rt_sigframe_n32 {
-	u32 rs_ass[4];			/* argument save space for o32 */
-	u32 rs_pad[2];
-	struct compat_siginfo rs_info;
-	struct ucontextn32 rs_uc;
-	u32 rs_code[8] ____cacheline_aligned;		/* signal trampoline */
-};
-
-#endif	/* !ICACHE_REFILLS_WORKAROUND_WAR */
-
 extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat);

 asmlinkage int sysn32_rt_sigsuspend(nabi_no_regargs struct pt_regs regs)
@ -173,7 +159,7 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	force_sig(SIGSEGV, current);
 }

-static int setup_rt_frame_n32(struct k_sigaction * ka,
+static int setup_rt_frame_n32(void *sig_return, struct k_sigaction *ka,
 	struct pt_regs *regs, int signr, sigset_t *set, siginfo_t *info)
 {
 	struct rt_sigframe_n32 __user *frame;
@ -184,8 +170,6 @@ static int setup_rt_frame_n32(struct k_sigaction * ka,
 	if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
 		goto give_sigsegv;

-	install_sigtramp(frame->rs_code, __NR_N32_rt_sigreturn);
-
 	/* Create siginfo.  */
 	err |= copy_siginfo_to_user32(&frame->rs_info, info);

@ -219,7 +203,7 @@ static int setup_rt_frame_n32(struct k_sigaction * ka,
 	regs->regs[ 5] = (unsigned long) &frame->rs_info;
 	regs->regs[ 6] = (unsigned long) &frame->rs_uc;
 	regs->regs[29] = (unsigned long) frame;
-	regs->regs[31] = (unsigned long) frame->rs_code;
+	regs->regs[31] = (unsigned long) sig_return;
 	regs->cp0_epc = regs->regs[25] = (unsigned long) ka->sa.sa_handler;

 	DEBUGP("SIG deliver (%s:%d): sp=0x%p pc=0x%lx ra=0x%lx\n",
@ -235,5 +219,7 @@ static int setup_rt_frame_n32(struct k_sigaction * ka,

 struct mips_abi mips_abi_n32 = {
 	.setup_rt_frame	= setup_rt_frame_n32,
+	.rt_signal_return_offset =
+		offsetof(struct mips_vdso, n32_rt_signal_trampoline),
 	.restart	= __NR_N32_restart_syscall
 };
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@ -182,7 +182,7 @@ static int vpemask[2][8] = {
 	{0, 0, 0, 0, 0, 0, 0, 1}
 };
 int tcnoprog[NR_CPUS];
-static atomic_t idle_hook_initialized = {0};
+static atomic_t idle_hook_initialized = ATOMIC_INIT(0);
 static int clock_hang_reported[NR_CPUS];

 #endif /* CONFIG_SMTC_IDLE_HOOK_DEBUG */
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@ -79,7 +79,11 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	int do_color_align;
 	unsigned long task_size;

-	task_size = STACK_TOP;
+#ifdef CONFIG_32BIT
+	task_size = TASK_SIZE;
+#else /* Must be CONFIG_64BIT*/
+	task_size = test_thread_flag(TIF_32BIT_ADDR) ? TASK_SIZE32 : TASK_SIZE;
+#endif

 	if (len > task_size)
 		return -ENOMEM;
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@ -1599,7 +1599,7 @@ void __init trap_init(void)
 		ebase = (unsigned long)
 			__alloc_bootmem(size, 1 << fls(size), 0);
 	} else {
-		ebase = CAC_BASE;
+		ebase = CKSEG0;
 		if (cpu_has_mips_r2)
 			ebase += (read_c0_ebase() & 0x3ffff000);
 	}
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@ -0,0 +1,112 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2009, 2010 Cavium Networks, Inc.
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/binfmts.h>
+#include <linux/elf.h>
+#include <linux/vmalloc.h>
+#include <linux/unistd.h>
+
+#include <asm/vdso.h>
+#include <asm/uasm.h>
+
+/*
+ * Including <asm/unistd.h> would give use the 64-bit syscall numbers ...
+ */
+#define __NR_O32_sigreturn		4119
+#define __NR_O32_rt_sigreturn		4193
+#define __NR_N32_rt_sigreturn		6211
+
+static struct page *vdso_page;
+
+static void __init install_trampoline(u32 *tramp, unsigned int sigreturn)
+{
+	uasm_i_addiu(&tramp, 2, 0, sigreturn);	/* li v0, sigreturn */
+	uasm_i_syscall(&tramp, 0);
+}
+
+static int __init init_vdso(void)
+{
+	struct mips_vdso *vdso;
+
+	vdso_page = alloc_page(GFP_KERNEL);
+	if (!vdso_page)
+		panic("Cannot allocate vdso");
+
+	vdso = vmap(&vdso_page, 1, 0, PAGE_KERNEL);
+	if (!vdso)
+		panic("Cannot map vdso");
+	clear_page(vdso);
+
+	install_trampoline(vdso->rt_signal_trampoline, __NR_rt_sigreturn);
+#ifdef CONFIG_32BIT
+	install_trampoline(vdso->signal_trampoline, __NR_sigreturn);
+#else
+	install_trampoline(vdso->n32_rt_signal_trampoline,
+			   __NR_N32_rt_sigreturn);
+	install_trampoline(vdso->o32_signal_trampoline, __NR_O32_sigreturn);
+	install_trampoline(vdso->o32_rt_signal_trampoline,
+			   __NR_O32_rt_sigreturn);
+#endif
+
+	vunmap(vdso);
+
+	pr_notice("init_vdso successfull\n");
+
+	return 0;
+}
+device_initcall(init_vdso);
+
+static unsigned long vdso_addr(unsigned long start)
+{
+	return STACK_TOP;
+}
+
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	int ret;
+	unsigned long addr;
+	struct mm_struct *mm = current->mm;
+
+	down_write(&mm->mmap_sem);
+
+	addr = vdso_addr(mm->start_stack);
+
+	addr = get_unmapped_area(NULL, addr, PAGE_SIZE, 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = addr;
+		goto up_fail;
+	}
+
+	ret = install_special_mapping(mm, addr, PAGE_SIZE,
+				      VM_READ|VM_EXEC|
+				      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+				      VM_ALWAYSDUMP,
+				      &vdso_page);
+
+	if (ret)
+		goto up_fail;
+
+	mm->context.vdso = (void *)addr;
+
+up_fail:
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
+		return "[vdso]";
+	return NULL;
+}
--- a/arch/mips/lib/delay.c
+++ b/arch/mips/lib/delay.c
@ -41,7 +41,7 @@ EXPORT_SYMBOL(__delay);

 void __udelay(unsigned long us)
 {
-	unsigned int lpj = current_cpu_data.udelay_val;
+	unsigned int lpj = raw_current_cpu_data.udelay_val;

 	__delay((us * 0x000010c7ull * HZ * lpj) >> 32);
 }
@ -49,7 +49,7 @@ EXPORT_SYMBOL(__udelay);

 void __ndelay(unsigned long ns)
 {
-	unsigned int lpj = current_cpu_data.udelay_val;
+	unsigned int lpj = raw_current_cpu_data.udelay_val;

 	__delay((ns * 0x00000005ull * HZ * lpj) >> 32);
 }
--- a/arch/mips/lib/libgcc.h
+++ b/arch/mips/lib/libgcc.h
@ -17,8 +17,7 @@ struct DWstruct {
 #error I feel sick.
 #endif

-typedef union
-{
+typedef union {
 	struct DWstruct s;
 	long long ll;
 } DWunion;
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@ -133,7 +133,7 @@ void __update_cache(struct vm_area_struct *vma, unsigned long address,
 }

 unsigned long _page_cachable_default;
-EXPORT_SYMBOL_GPL(_page_cachable_default);
+EXPORT_SYMBOL(_page_cachable_default);

 static inline void setup_protection_map(void)
 {
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@ -788,10 +788,15 @@ static void __cpuinit build_r4000_tlb_refill_handler(void)
 	 * create the plain linear handler
 	 */
 	if (bcm1250_m3_war()) {
-		UASM_i_MFC0(&p, K0, C0_BADVADDR);
-		UASM_i_MFC0(&p, K1, C0_ENTRYHI);
+		unsigned int segbits = 44;
+
+		uasm_i_dmfc0(&p, K0, C0_BADVADDR);
+		uasm_i_dmfc0(&p, K1, C0_ENTRYHI);
 		uasm_i_xor(&p, K0, K0, K1);
-		UASM_i_SRL(&p, K0, K0, PAGE_SHIFT + 1);
+		uasm_i_dsrl32(&p, K1, K0, 62 - 32);
+		uasm_i_dsrl(&p, K0, K0, 12 + 1);
+		uasm_i_dsll32(&p, K0, K0, 64 + 12 + 1 - segbits - 32);
+		uasm_i_or(&p, K0, K0, K1);
 		uasm_il_bnez(&p, &r, K0, label_leave);
 		/* No need for uasm_i_nop */
 	}
@ -1312,10 +1317,15 @@ static void __cpuinit build_r4000_tlb_load_handler(void)
 	memset(relocs, 0, sizeof(relocs));

 	if (bcm1250_m3_war()) {
-		UASM_i_MFC0(&p, K0, C0_BADVADDR);
-		UASM_i_MFC0(&p, K1, C0_ENTRYHI);
+		unsigned int segbits = 44;
+
+		uasm_i_dmfc0(&p, K0, C0_BADVADDR);
+		uasm_i_dmfc0(&p, K1, C0_ENTRYHI);
 		uasm_i_xor(&p, K0, K0, K1);
-		UASM_i_SRL(&p, K0, K0, PAGE_SHIFT + 1);
+		uasm_i_dsrl32(&p, K1, K0, 62 - 32);
+		uasm_i_dsrl(&p, K0, K0, 12 + 1);
+		uasm_i_dsll32(&p, K0, K0, 64 + 12 + 1 - segbits - 32);
+		uasm_i_or(&p, K0, K0, K1);
 		uasm_il_bnez(&p, &r, K0, label_leave);
 		/* No need for uasm_i_nop */
 	}
--- a/arch/mips/mm/uasm.c
+++ b/arch/mips/mm/uasm.c
@ -31,7 +31,8 @@ enum fields {
 	BIMM = 0x040,
 	JIMM = 0x080,
 	FUNC = 0x100,
-	SET = 0x200
+	SET = 0x200,
+	SCIMM = 0x400
 };

 #define OP_MASK		0x3f
@ -52,6 +53,8 @@ enum fields {
 #define FUNC_SH		0
 #define SET_MASK	0x7
 #define SET_SH		0
+#define SCIMM_MASK	0xfffff
+#define SCIMM_SH	6

 enum opcode {
 	insn_invalid,
@ -61,10 +64,10 @@ enum opcode {
 	insn_dmtc0, insn_dsll, insn_dsll32, insn_dsra, insn_dsrl,
 	insn_dsrl32, insn_drotr, insn_dsubu, insn_eret, insn_j, insn_jal,
 	insn_jr, insn_ld, insn_ll, insn_lld, insn_lui, insn_lw, insn_mfc0,
-	insn_mtc0, insn_ori, insn_pref, insn_rfe, insn_sc, insn_scd,
+	insn_mtc0, insn_or, insn_ori, insn_pref, insn_rfe, insn_sc, insn_scd,
 	insn_sd, insn_sll, insn_sra, insn_srl, insn_rotr, insn_subu, insn_sw,
 	insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_xor, insn_xori,
-	insn_dins
+	insn_dins, insn_syscall
 };

 struct insn {
@ -117,6 +120,7 @@ static struct insn insn_table[] __cpuinitdata = {
 	{ insn_lw,  M(lw_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_mfc0,  M(cop0_op, mfc_op, 0, 0, 0, 0),  RT | RD | SET},
 	{ insn_mtc0,  M(cop0_op, mtc_op, 0, 0, 0, 0),  RT | RD | SET},
+	{ insn_or,  M(spec_op, 0, 0, 0, 0, or_op),  RS | RT | RD },
 	{ insn_ori,  M(ori_op, 0, 0, 0, 0, 0),  RS | RT | UIMM },
 	{ insn_pref,  M(pref_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_rfe,  M(cop0_op, cop_op, 0, 0, 0, rfe_op),  0 },
@ -136,6 +140,7 @@ static struct insn insn_table[] __cpuinitdata = {
 	{ insn_xor,  M(spec_op, 0, 0, 0, 0, xor_op),  RS | RT | RD },
 	{ insn_xori,  M(xori_op, 0, 0, 0, 0, 0),  RS | RT | UIMM },
 	{ insn_dins, M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE },
+	{ insn_syscall, M(spec_op, 0, 0, 0, 0, syscall_op), SCIMM},
 	{ insn_invalid, 0, 0 }
 };

@ -208,6 +213,14 @@ static inline __cpuinit u32 build_jimm(u32 arg)
 	return (arg >> 2) & JIMM_MASK;
 }

+static inline __cpuinit u32 build_scimm(u32 arg)
+{
+	if (arg & ~SCIMM_MASK)
+		printk(KERN_WARNING "Micro-assembler field overflow\n");
+
+	return (arg & SCIMM_MASK) << SCIMM_SH;
+}
+
 static inline __cpuinit u32 build_func(u32 arg)
 {
 	if (arg & ~FUNC_MASK)
@ -266,6 +279,8 @@ static void __cpuinit build_insn(u32 **buf, enum opcode opc, ...)
 		op |= build_func(va_arg(ap, u32));
 	if (ip->fields & SET)
 		op |= build_set(va_arg(ap, u32));
+	if (ip->fields & SCIMM)
+		op |= build_scimm(va_arg(ap, u32));
 	va_end(ap);

 	**buf = op;
@ -373,6 +388,7 @@ I_u2s3u1(_lw)
 I_u1u2u3(_mfc0)
 I_u1u2u3(_mtc0)
 I_u2u1u3(_ori)
+I_u3u1u2(_or)
 I_u2s3u1(_pref)
 I_0(_rfe)
 I_u2s3u1(_sc)
@ -391,6 +407,7 @@ I_0(_tlbwr)
 I_u3u1u2(_xor)
 I_u2u1u3(_xori)
 I_u2u1msbu3(_dins);
+I_u1(_syscall);

 /* Handle labels. */
 void __cpuinit uasm_build_label(struct uasm_label **lab, u32 *addr, int lid)
--- a/arch/mips/pci/ops-loongson2.c
+++ b/arch/mips/pci/ops-loongson2.c
@ -180,15 +180,21 @@ struct pci_ops loongson_pci_ops = {
 };

 #ifdef CONFIG_CS5536
+DEFINE_RAW_SPINLOCK(msr_lock);
+
 void _rdmsr(u32 msr, u32 *hi, u32 *lo)
 {
 	struct pci_bus bus = {
 		.number = PCI_BUS_CS5536
 	};
 	u32 devfn = PCI_DEVFN(PCI_IDSEL_CS5536, 0);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&msr_lock, flags);
 	loongson_pcibios_write(&bus, devfn, PCI_MSR_ADDR, 4, msr);
 	loongson_pcibios_read(&bus, devfn, PCI_MSR_DATA_LO, 4, lo);
 	loongson_pcibios_read(&bus, devfn, PCI_MSR_DATA_HI, 4, hi);
+	raw_spin_unlock_irqrestore(&msr_lock, flags);
 }
 EXPORT_SYMBOL(_rdmsr);

@ -198,9 +204,13 @@ void _wrmsr(u32 msr, u32 hi, u32 lo)
 		.number = PCI_BUS_CS5536
 	};
 	u32 devfn = PCI_DEVFN(PCI_IDSEL_CS5536, 0);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&msr_lock, flags);
 	loongson_pcibios_write(&bus, devfn, PCI_MSR_ADDR, 4, msr);
 	loongson_pcibios_write(&bus, devfn, PCI_MSR_DATA_LO, 4, lo);
 	loongson_pcibios_write(&bus, devfn, PCI_MSR_DATA_HI, 4, hi);
+	raw_spin_unlock_irqrestore(&msr_lock, flags);
 }
 EXPORT_SYMBOL(_wrmsr);
 #endif
--- a/arch/mips/sibyte/sb1250/setup.c
+++ b/arch/mips/sibyte/sb1250/setup.c
@ -87,6 +87,21 @@ static int __init setup_bcm1250(void)
 	return ret;
 }

+int sb1250_m3_workaround_needed(void)
+{
+	switch (soc_type) {
+	case K_SYS_SOC_TYPE_BCM1250:
+	case K_SYS_SOC_TYPE_BCM1250_ALT:
+	case K_SYS_SOC_TYPE_BCM1250_ALT2:
+	case K_SYS_SOC_TYPE_BCM1125:
+	case K_SYS_SOC_TYPE_BCM1125H:
+		return soc_pass < K_SYS_REVISION_BCM1250_C0;
+
+	default:
+		return 0;
+	}
+}
+
 static int __init setup_bcm112x(void)
 {
 	int ret = 0;
--- a/arch/mips/sibyte/swarm/platform.c
+++ b/arch/mips/sibyte/swarm/platform.c
@ -83,3 +83,57 @@ static int __init swarm_pata_init(void)
 device_initcall(swarm_pata_init);

 #endif /* defined(CONFIG_SIBYTE_SWARM) || defined(CONFIG_SIBYTE_LITTLESUR) */
+
+#define sb1250_dev_struct(num) \
+	static struct resource sb1250_res##num = {		\
+		.name = "SB1250 MAC " __stringify(num),		\
+		.flags = IORESOURCE_MEM,		\
+		.start = A_MAC_CHANNEL_BASE(num),	\
+		.end = A_MAC_CHANNEL_BASE(num + 1) -1,	\
+	};\
+	static struct platform_device sb1250_dev##num = {	\
+		.name = "sb1250-mac",			\
+	.id = num,					\
+	.resource = &sb1250_res##num,			\
+	.num_resources = 1,				\
+	}
+
+sb1250_dev_struct(0);
+sb1250_dev_struct(1);
+sb1250_dev_struct(2);
+sb1250_dev_struct(3);
+
+static struct platform_device *sb1250_devs[] __initdata = {
+	&sb1250_dev0,
+	&sb1250_dev1,
+	&sb1250_dev2,
+	&sb1250_dev3,
+};
+
+static int __init sb1250_device_init(void)
+{
+	int ret;
+
+	/* Set the number of available units based on the SOC type.  */
+	switch (soc_type) {
+	case K_SYS_SOC_TYPE_BCM1250:
+	case K_SYS_SOC_TYPE_BCM1250_ALT:
+		ret = platform_add_devices(sb1250_devs, 3);
+		break;
+	case K_SYS_SOC_TYPE_BCM1120:
+	case K_SYS_SOC_TYPE_BCM1125:
+	case K_SYS_SOC_TYPE_BCM1125H:
+	case K_SYS_SOC_TYPE_BCM1250_ALT2:       /* Hybrid */
+		ret = platform_add_devices(sb1250_devs, 2);
+		break;
+	case K_SYS_SOC_TYPE_BCM1x55:
+	case K_SYS_SOC_TYPE_BCM1x80:
+		ret = platform_add_devices(sb1250_devs, 4);
+		break;
+	default:
+		ret = -ENODEV;
+		break;
+	}
+	return ret;
+}
+device_initcall(sb1250_device_init);
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@ -37,6 +37,9 @@ config SPARC64
 	def_bool 64BIT
 	select ARCH_SUPPORTS_MSI
 	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_GRAPH_FP_TEST
+	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
 	select HAVE_LMB
--- a/arch/sparc/Kconfig.debug
+++ b/arch/sparc/Kconfig.debug
@ -19,13 +19,10 @@ config DEBUG_DCFLUSH
 	bool "D-cache flush debugging"
 	depends on SPARC64 && DEBUG_KERNEL

-config STACK_DEBUG
-	bool "Stack Overflow Detection Support"
-
 config MCOUNT
 	bool
 	depends on SPARC64
-	depends on STACK_DEBUG || FUNCTION_TRACER
+	depends on FUNCTION_TRACER
 	default y

 config FRAME_POINTER
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@ -17,7 +17,7 @@ typedef struct {
 	unsigned int	__nmi_count;
 	unsigned long	clock_tick;	/* %tick's per second */
 	unsigned long	__pad;
-	unsigned int	__pad1;
+	unsigned int	irq0_irqs;
 	unsigned int	__pad2;

 	/* Dcache line 2, rarely used */
--- a/arch/sparc/include/asm/irqflags_64.h
+++ b/arch/sparc/include/asm/irqflags_64.h
@ -76,9 +76,26 @@ static inline int raw_irqs_disabled(void)
 */
 static inline unsigned long __raw_local_irq_save(void)
 {
-	unsigned long flags = __raw_local_save_flags();
+	unsigned long flags, tmp;

-	raw_local_irq_disable();
+	/* Disable interrupts to PIL_NORMAL_MAX unless we already
+	 * are using PIL_NMI, in which case PIL_NMI is retained.
+	 *
+	 * The only values we ever program into the %pil are 0,
+	 * PIL_NORMAL_MAX and PIL_NMI.
+	 *
+	 * Since PIL_NMI is the largest %pil value and all bits are
+	 * set in it (0xf), it doesn't matter what PIL_NORMAL_MAX
+	 * actually is.
+	 */
+	__asm__ __volatile__(
+		"rdpr	%%pil, %0\n\t"
+		"or	%0, %2, %1\n\t"
+		"wrpr	%1, 0x0, %%pil"
+		: "=r" (flags), "=r" (tmp)
+		: "i" (PIL_NORMAL_MAX)
+		: "memory"
+	);

 	return flags;
 }
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@ -111,7 +111,7 @@ struct thread_info {
 #define THREAD_SHIFT PAGE_SHIFT
 #endif /* PAGE_SHIFT == 13 */

-#define PREEMPT_ACTIVE		0x4000000
+#define PREEMPT_ACTIVE		0x10000000

 /*
 * macros/functions for gaining access to the thread information structure
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@ -13,6 +13,14 @@ extra-y     += init_task.o
 CPPFLAGS_vmlinux.lds := -Usparc -m$(BITS)
 extra-y              += vmlinux.lds

+ifdef CONFIG_FUNCTION_TRACER
+# Do not profile debug and lowlevel utilities
+CFLAGS_REMOVE_ftrace.o := -pg
+CFLAGS_REMOVE_time_$(BITS).o := -pg
+CFLAGS_REMOVE_perf_event.o := -pg
+CFLAGS_REMOVE_pcr.o := -pg
+endif
+
 obj-$(CONFIG_SPARC32)   += entry.o wof.o wuf.o
 obj-$(CONFIG_SPARC32)   += etrap_32.o
 obj-$(CONFIG_SPARC32)   += rtrap_32.o
@ -85,7 +93,7 @@ obj-$(CONFIG_KGDB)        += kgdb_$(BITS).o


 obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
-CFLAGS_REMOVE_ftrace.o := -pg
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o

 obj-$(CONFIG_EARLYFB) += btext.o
 obj-$(CONFIG_STACKTRACE)     += stacktrace.o
--- a/arch/sparc/kernel/ftrace.c
+++ b/arch/sparc/kernel/ftrace.c
@ -13,7 +13,7 @@ static const u32 ftrace_nop = 0x01000000;

 static u32 ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
-	static u32 call;
+	u32 call;
 	s32 off;

 	off = ((s32)addr - (s32)ip);
@ -91,3 +91,61 @@ int __init ftrace_dyn_arch_init(void *data)
 	return 0;
 }
 #endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	unsigned long ip = (unsigned long)(&ftrace_graph_call);
+	u32 old, new;
+
+	old = *(u32 *) &ftrace_graph_call;
+	new = ftrace_call_replace(ip, (unsigned long) &ftrace_graph_caller);
+	return ftrace_modify_code(ip, old, new);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	unsigned long ip = (unsigned long)(&ftrace_graph_call);
+	u32 old, new;
+
+	old = *(u32 *) &ftrace_graph_call;
+	new = ftrace_call_replace(ip, (unsigned long) &ftrace_stub);
+
+	return ftrace_modify_code(ip, old, new);
+}
+
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+unsigned long prepare_ftrace_return(unsigned long parent,
+				    unsigned long self_addr,
+				    unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long) &return_to_handler;
+	struct ftrace_graph_ent trace;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return parent + 8UL;
+
+	if (ftrace_push_return_trace(parent, self_addr, &trace.depth,
+				     frame_pointer) == -EBUSY)
+		return parent + 8UL;
+
+	trace.func = self_addr;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
+		current->curr_ret_stack--;
+		return parent + 8UL;
+	}
+
+	return return_hooker;
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@ -20,7 +20,9 @@
 #include <linux/delay.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/ftrace.h>
 #include <linux/irq.h>
+#include <linux/kmemleak.h>

 #include <asm/ptrace.h>
 #include <asm/processor.h>
@ -45,6 +47,7 @@

 #include "entry.h"
 #include "cpumap.h"
+#include "kstack.h"

 #define NUM_IVECS	(IMAP_INR + 1)

@ -647,6 +650,14 @@ unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino)
 	bucket = kzalloc(sizeof(struct ino_bucket), GFP_ATOMIC);
 	if (unlikely(!bucket))
 		return 0;
+
+	/* The only reference we store to the IRQ bucket is
+	 * by physical address which kmemleak can't see, tell
+	 * it that this object explicitly is not a leak and
+	 * should be scanned.
+	 */
+	kmemleak_not_leak(bucket);
+
 	__flush_dcache_range((unsigned long) bucket,
 			     ((unsigned long) bucket +
 			      sizeof(struct ino_bucket)));
@ -703,25 +714,7 @@ void ack_bad_irq(unsigned int virt_irq)
 void *hardirq_stack[NR_CPUS];
 void *softirq_stack[NR_CPUS];

-static __attribute__((always_inline)) void *set_hardirq_stack(void)
-{
-	void *orig_sp, *sp = hardirq_stack[smp_processor_id()];
-
-	__asm__ __volatile__("mov %%sp, %0" : "=r" (orig_sp));
-	if (orig_sp < sp ||
-	    orig_sp > (sp + THREAD_SIZE)) {
-		sp += THREAD_SIZE - 192 - STACK_BIAS;
-		__asm__ __volatile__("mov %0, %%sp" : : "r" (sp));
-	}
-
-	return orig_sp;
-}
-static __attribute__((always_inline)) void restore_hardirq_stack(void *orig_sp)
-{
-	__asm__ __volatile__("mov %0, %%sp" : : "r" (orig_sp));
-}
-
-void handler_irq(int irq, struct pt_regs *regs)
+void __irq_entry handler_irq(int irq, struct pt_regs *regs)
 {
 	unsigned long pstate, bucket_pa;
 	struct pt_regs *old_regs;
--- a/arch/sparc/kernel/kgdb_64.c
+++ b/arch/sparc/kernel/kgdb_64.c
@ -5,6 +5,7 @@

 #include <linux/kgdb.h>
 #include <linux/kdebug.h>
+#include <linux/ftrace.h>

 #include <asm/kdebug.h>
 #include <asm/ptrace.h>
@ -108,7 +109,7 @@ void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 }

 #ifdef CONFIG_SMP
-void smp_kgdb_capture_client(int irq, struct pt_regs *regs)
+void __irq_entry smp_kgdb_capture_client(int irq, struct pt_regs *regs)
 {
 	unsigned long flags;

--- a/arch/sparc/kernel/kstack.h
+++ b/arch/sparc/kernel/kstack.h
@ -61,4 +61,23 @@ static inline bool kstack_is_trap_frame(struct thread_info *tp, struct pt_regs *

 }

+static inline __attribute__((always_inline)) void *set_hardirq_stack(void)
+{
+	void *orig_sp, *sp = hardirq_stack[smp_processor_id()];
+
+	__asm__ __volatile__("mov %%sp, %0" : "=r" (orig_sp));
+	if (orig_sp < sp ||
+	    orig_sp > (sp + THREAD_SIZE)) {
+		sp += THREAD_SIZE - 192 - STACK_BIAS;
+		__asm__ __volatile__("mov %0, %%sp" : : "r" (sp));
+	}
+
+	return orig_sp;
+}
+
+static inline __attribute__((always_inline)) void restore_hardirq_stack(void *orig_sp)
+{
+	__asm__ __volatile__("mov %0, %%sp" : : "r" (orig_sp));
+}
+
 #endif /* _KSTACK_H */
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@ -23,6 +23,8 @@
 #include <asm/ptrace.h>
 #include <asm/pcr.h>

+#include "kstack.h"
+
 /* We don't have a real NMI on sparc64, but we can fake one
 * up using profiling counter overflow interrupts and interrupt
 * levels.
@ -92,7 +94,7 @@ static void die_nmi(const char *str, struct pt_regs *regs, int do_panic)
 notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
 {
 	unsigned int sum, touched = 0;
-	int cpu = smp_processor_id();
+	void *orig_sp;

 	clear_softint(1 << irq);

@ -100,13 +102,15 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)

 	nmi_enter();

+	orig_sp = set_hardirq_stack();
+
 	if (notify_die(DIE_NMI, "nmi", regs, 0,
 		       pt_regs_trap_type(regs), SIGINT) == NOTIFY_STOP)
 		touched = 1;
 	else
 		pcr_ops->write(PCR_PIC_PRIV);

-	sum = kstat_irqs_cpu(0, cpu);
+	sum = local_cpu_data().irq0_irqs;
 	if (__get_cpu_var(nmi_touch)) {
 		__get_cpu_var(nmi_touch) = 0;
 		touched = 1;
@ -125,6 +129,8 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
 		pcr_ops->write(pcr_enable);
 	}

+	restore_hardirq_stack(orig_sp);
+
 	nmi_exit();
 }

--- a/arch/sparc/kernel/pci_common.c
+++ b/arch/sparc/kernel/pci_common.c
@ -371,14 +371,19 @@ static void pci_register_iommu_region(struct pci_pbm_info *pbm)
 		struct resource *rp = kzalloc(sizeof(*rp), GFP_KERNEL);

 		if (!rp) {
-			prom_printf("Cannot allocate IOMMU resource.\n");
-			prom_halt();
+			pr_info("%s: Cannot allocate IOMMU resource.\n",
+				pbm->name);
+			return;
 		}
 		rp->name = "IOMMU";
 		rp->start = pbm->mem_space.start + (unsigned long) vdma[0];
 		rp->end = rp->start + (unsigned long) vdma[1] - 1UL;
 		rp->flags = IORESOURCE_BUSY;
-		request_resource(&pbm->mem_space, rp);
+		if (request_resource(&pbm->mem_space, rp)) {
+			pr_info("%s: Unable to request IOMMU resource.\n",
+				pbm->name);
+			kfree(rp);
+		}
 	}
 }

--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@ -8,6 +8,7 @@
 #include <linux/irq.h>

 #include <linux/perf_event.h>
+#include <linux/ftrace.h>

 #include <asm/pil.h>
 #include <asm/pcr.h>
@ -34,7 +35,7 @@ unsigned int picl_shift;
 * Therefore in such situations we defer the work by signalling
 * a lower level cpu IRQ.
 */
-void deferred_pcr_work_irq(int irq, struct pt_regs *regs)
+void __irq_entry deferred_pcr_work_irq(int irq, struct pt_regs *regs)
 {
 	struct pt_regs *old_regs;

--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@ -130,7 +130,17 @@ rtrap_xcall:
 		 nop
 		call			trace_hardirqs_on
 		 nop
-		wrpr			%l4, %pil
+		/* Do not actually set the %pil here.  We will do that
+		 * below after we clear PSTATE_IE in the %pstate register.
+		 * If we re-enable interrupts here, we can recurse down
+		 * the hardirq stack potentially endlessly, causing a
+		 * stack overflow.
+		 *
+		 * It is tempting to put this test and trace_hardirqs_on
+		 * call at the 'rt_continue' label, but that will not work
+		 * as that path hits unconditionally and we do not want to
+		 * execute this in NMI return paths, for example.
+		 */
 #endif
 rtrap_no_irq_enable:
 		andcc			%l1, TSTATE_PRIV, %l3
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@ -22,6 +22,7 @@
 #include <linux/profile.h>
 #include <linux/bootmem.h>
 #include <linux/vmalloc.h>
+#include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/slab.h>

@ -823,13 +824,13 @@ void arch_send_call_function_single_ipi(int cpu)
 		      &cpumask_of_cpu(cpu));
 }

-void smp_call_function_client(int irq, struct pt_regs *regs)
+void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
 	generic_smp_call_function_interrupt();
 }

-void smp_call_function_single_client(int irq, struct pt_regs *regs)
+void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
 	generic_smp_call_function_single_interrupt();
@ -965,7 +966,7 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
 	put_cpu();
 }

-void smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
+void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
 {
 	struct mm_struct *mm;
 	unsigned long flags;
@ -1149,7 +1150,7 @@ void smp_release(void)
 */
 extern void prom_world(int);

-void smp_penguin_jailcell(int irq, struct pt_regs *regs)
+void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);

@ -1365,7 +1366,7 @@ void smp_send_reschedule(int cpu)
 		      &cpumask_of_cpu(cpu));
 }

-void smp_receive_signal_client(int irq, struct pt_regs *regs)
+void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs)
 {
 	clear_softint(1 << irq);
 }
--- a/Show More
+++ b/Show More