Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (29 commits)
  powerpc/rtas: Fix watchdog driver temperature read functionality
  powerpc/mm: Fix potential access to freed pages when using hugetlbfs
  powerpc/440: Fix warning early debug code
  powerpc/of: Fix usage of dev_set_name() in of_device_alloc()
  powerpc/pasemi: Use raw spinlock in SMP TB sync
  powerpc: Use one common impl. of RTAS timebase sync and use raw spinlock
  powerpc/rtas: Turn rtas lock into a raw spinlock
  powerpc: Add irqtrace support for 32-bit powerpc
  powerpc/BSR: Fix BSR to allow mmap of small BSR on 64k kernel
  powerpc/BSR: add 4096 byte BSR size
  powerpc: Map more memory early on 601 processors
  powerpc/pmac: Fix DMA ops for MacIO devices
  powerpc/mm: Make k(un)map_atomic out of line
  powerpc: Fix mpic alloc warning
  powerpc: Fix output from show_regs
  powerpc/pmac: Fix issues with PowerMac "PowerSurge" SMP
  powerpc/amigaone: Limit ISA I/O range to 4k in the device tree
  powerpc/warp: Platform fix for i2c change
  powerpc: Have git ignore generated files from dtc compile
  powerpc/mpic: Fix mapping of "DCR" based MPIC variants
  ...

33 files changed, 501 insertions, 347 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index bf6cedf..d00131c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -62,7 +62,6 @@ config HAVE_LATENCYTOP_SUPPORT
 
 config TRACE_IRQFLAGS_SUPPORT
 	bool
-	depends on PPC64
 	default y
 
 config LOCKDEP_SUPPORT
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore
index 2f50acd..3d80c3e 100644
--- a/arch/powerpc/boot/.gitignore
+++ b/arch/powerpc/boot/.gitignore
@@ -36,3 +36,13 @@ zImage.pseries
 zconf.h
 zlib.h
 zutil.h
+fdt.c
+fdt.h
+fdt_ro.c
+fdt_rw.c
+fdt_strerror.c
+fdt_sw.c
+fdt_wip.c
+libfdt.h
+libfdt_internal.h
+
diff --git a/arch/powerpc/boot/dts/amigaone.dts b/arch/powerpc/boot/dts/amigaone.dts
index 26549fc..49ac36b 100644
--- a/arch/powerpc/boot/dts/amigaone.dts
+++ b/arch/powerpc/boot/dts/amigaone.dts
@@ -70,8 +70,8 @@
 			devsel-speed = <0x00000001>;
 			min-grant = <0>;
 			max-latency = <0>;
-			/* First 64k for I/O at 0x0 on PCI mapped to 0x0 on ISA. */
-			ranges = <0x00000001 0 0x01000000 0 0x00000000 0x00010000>;
+			/* First 4k for I/O at 0x0 on PCI mapped to 0x0 on ISA. */
+			ranges = <0x00000001 0 0x01000000 0 0x00000000 0x00001000>;
 			interrupt-parent = <&i8259>;
 			#interrupt-cells = <2>;
 			#address-cells = <2>;
diff --git a/arch/powerpc/boot/dts/mpc8569mds.dts b/arch/powerpc/boot/dts/mpc8569mds.dts
index a8dcb01..a680165 100644
--- a/arch/powerpc/boot/dts/mpc8569mds.dts
+++ b/arch/powerpc/boot/dts/mpc8569mds.dts
@@ -253,6 +253,7 @@
 			/* Filled in by U-Boot */
 			clock-frequency = <0>;
 			status = "disabled";
+			sdhci,1-bit-only;
 		};
 
 		crypto@30000 {
diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h
index 2ff79874..7685ffd 100644
--- a/arch/powerpc/include/asm/cpm1.h
+++ b/arch/powerpc/include/asm/cpm1.h
@@ -598,8 +598,6 @@ typedef struct risc_timer_pram {
 #define CICR_IEN		((uint)0x00000080)	/* Int. enable */
 #define CICR_SPS		((uint)0x00000001)	/* SCC Spread */
 
-#define IMAP_ADDR		(get_immrbase())
-
 #define CPM_PIN_INPUT     0
 #define CPM_PIN_OUTPUT    1
 #define CPM_PIN_PRIMARY   0
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 3d9e887..b44aaab 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -309,7 +309,9 @@ static inline void dma_sync_single_for_cpu(struct device *dev,
 	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
-	dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0,
+
+	if (dma_ops->sync_single_range_for_cpu)
+		dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0,
 					   size, direction);
 }
 
@@ -320,7 +322,9 @@ static inline void dma_sync_single_for_device(struct device *dev,
 	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
-	dma_ops->sync_single_range_for_device(dev, dma_handle,
+
+	if (dma_ops->sync_single_range_for_device)
+		dma_ops->sync_single_range_for_device(dev, dma_handle,
 					      0, size, direction);
 }
 
@@ -331,7 +335,9 @@ static inline void dma_sync_sg_for_cpu(struct device *dev,
 	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
-	dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction);
+
+	if (dma_ops->sync_sg_for_cpu)
+		dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction);
 }
 
 static inline void dma_sync_sg_for_device(struct device *dev,
@@ -341,7 +347,9 @@ static inline void dma_sync_sg_for_device(struct device *dev,
 	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
-	dma_ops->sync_sg_for_device(dev, sgl, nents, direction);
+
+	if (dma_ops->sync_sg_for_device)
+		dma_ops->sync_sg_for_device(dev, sgl, nents, direction);
 }
 
 static inline void dma_sync_single_range_for_cpu(struct device *dev,
@@ -351,7 +359,9 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev,
 	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
-	dma_ops->sync_single_range_for_cpu(dev, dma_handle,
+
+	if (dma_ops->sync_single_range_for_cpu)
+		dma_ops->sync_single_range_for_cpu(dev, dma_handle,
 					   offset, size, direction);
 }
 
@@ -362,7 +372,9 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
 	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
 	BUG_ON(!dma_ops);
-	dma_ops->sync_single_range_for_device(dev, dma_handle, offset,
+
+	if (dma_ops->sync_single_range_for_device)
+		dma_ops->sync_single_range_for_device(dev, dma_handle, offset,
 					      size, direction);
 }
 #else /* CONFIG_PPC_NEED_DMA_SYNC_OPS */
diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h
index 684a73f..a74c4ee 100644
--- a/arch/powerpc/include/asm/highmem.h
+++ b/arch/powerpc/include/asm/highmem.h
@@ -22,9 +22,7 @@
 
 #ifdef __KERNEL__
 
-#include <linux/init.h>
 #include <linux/interrupt.h>
-#include <linux/highmem.h>
 #include <asm/kmap_types.h>
 #include <asm/tlbflush.h>
 #include <asm/page.h>
@@ -62,6 +60,9 @@ extern pte_t *pkmap_page_table;
 
 extern void *kmap_high(struct page *page);
 extern void kunmap_high(struct page *page);
+extern void *kmap_atomic_prot(struct page *page, enum km_type type,
+			      pgprot_t prot);
+extern void kunmap_atomic(void *kvaddr, enum km_type type);
 
 static inline void *kmap(struct page *page)
 {
@@ -79,62 +80,11 @@ static inline void kunmap(struct page *page)
 	kunmap_high(page);
 }
 
-/*
- * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap
- * gives a more generic (and caching) interface. But kmap_atomic can
- * be used in IRQ contexts, so in some (very limited) cases we need
- * it.
- */
-static inline void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot)
-{
-	unsigned int idx;
-	unsigned long vaddr;
-
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
-	pagefault_disable();
-	if (!PageHighMem(page))
-		return page_address(page);
-
-	debug_kmap_atomic(type);
-	idx = type + KM_TYPE_NR*smp_processor_id();
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-#ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(!pte_none(*(kmap_pte-idx)));
-#endif
-	__set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot), 1);
-	local_flush_tlb_page(NULL, vaddr);
-
-	return (void*) vaddr;
-}
-
 static inline void *kmap_atomic(struct page *page, enum km_type type)
 {
 	return kmap_atomic_prot(page, type, kmap_prot);
 }
 
-static inline void kunmap_atomic(void *kvaddr, enum km_type type)
-{
-#ifdef CONFIG_DEBUG_HIGHMEM
-	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
-	enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
-
-	if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
-		pagefault_enable();
-		return;
-	}
-
-	BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-
-	/*
-	 * force other mappings to Oops if they'll try to access
-	 * this pte without first remap it
-	 */
-	pte_clear(&init_mm, vaddr, kmap_pte-idx);
-	local_flush_tlb_page(NULL, vaddr);
-#endif
-	pagefault_enable();
-}
-
 static inline struct page *kmap_atomic_to_page(void *ptr)
 {
 	unsigned long idx, vaddr = (unsigned long) ptr;
@@ -148,6 +98,7 @@ static inline struct page *kmap_atomic_to_page(void *ptr)
 	return pte_page(*pte);
 }
 
+
 #define flush_cache_kmaps()	flush_cache_all()
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 867ab8e..8b505ea 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -68,13 +68,13 @@ static inline int irqs_disabled_flags(unsigned long flags)
 
 #if defined(CONFIG_BOOKE)
 #define SET_MSR_EE(x)	mtmsr(x)
-#define local_irq_restore(flags)	__asm__ __volatile__("wrtee %0" : : "r" (flags) : "memory")
+#define raw_local_irq_restore(flags)	__asm__ __volatile__("wrtee %0" : : "r" (flags) : "memory")
 #else
 #define SET_MSR_EE(x)	mtmsr(x)
-#define local_irq_restore(flags)	mtmsr(flags)
+#define raw_local_irq_restore(flags)	mtmsr(flags)
 #endif
 
-static inline void local_irq_disable(void)
+static inline void raw_local_irq_disable(void)
 {
 #ifdef CONFIG_BOOKE
 	__asm__ __volatile__("wrteei 0": : :"memory");
@@ -86,7 +86,7 @@ static inline void local_irq_disable(void)
 #endif
 }
 
-static inline void local_irq_enable(void)
+static inline void raw_local_irq_enable(void)
 {
 #ifdef CONFIG_BOOKE
 	__asm__ __volatile__("wrteei 1": : :"memory");
@@ -98,7 +98,7 @@ static inline void local_irq_enable(void)
 #endif
 }
 
-static inline void local_irq_save_ptr(unsigned long *flags)
+static inline void raw_local_irq_save_ptr(unsigned long *flags)
 {
 	unsigned long msr;
 	msr = mfmsr();
@@ -110,12 +110,12 @@ static inline void local_irq_save_ptr(unsigned long *flags)
 #endif
 }
 
-#define local_save_flags(flags)	((flags) = mfmsr())
-#define local_irq_save(flags)	local_irq_save_ptr(&flags)
-#define irqs_disabled()		((mfmsr() & MSR_EE) == 0)
+#define raw_local_save_flags(flags)	((flags) = mfmsr())
+#define raw_local_irq_save(flags)	raw_local_irq_save_ptr(&flags)
+#define raw_irqs_disabled()		((mfmsr() & MSR_EE) == 0)
+#define raw_irqs_disabled_flags(flags)	(((flags) & MSR_EE) == 0)
 
-#define hard_irq_enable()	local_irq_enable()
-#define hard_irq_disable()	local_irq_disable()
+#define hard_irq_disable()		raw_local_irq_disable()
 
 static inline int irqs_disabled_flags(unsigned long flags)
 {
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index e05d26f..82b7220 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -47,7 +47,8 @@
  * generic accessors and iterators here
  */
 #define __real_pte(e,p) 	((real_pte_t) { \
-	(e), pte_val(*((p) + PTRS_PER_PTE)) })
+			(e), ((e) & _PAGE_COMBO) ? \
+				(pte_val(*((p) + PTRS_PER_PTE))) : 0 })
 #define __rpte_to_hidx(r,index)	((pte_val((r).pte) & _PAGE_COMBO) ? \
         (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf))
 #define __rpte_to_pte(r)	((r).pte)
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 01c1233..168fce7 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -58,7 +58,7 @@ struct rtas_t {
 	unsigned long entry;		/* physical address pointer */
 	unsigned long base;		/* physical address pointer */
 	unsigned long size;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct rtas_args args;
 	struct device_node *dev;	/* virtual address pointer */
 };
@@ -245,5 +245,8 @@ static inline u32 rtas_config_addr(int busno, int devfn, int reg)
 			(devfn << 8) | (reg & 0xff);
 }
 
+extern void __cpuinit rtas_give_timebase(void);
+extern void __cpuinit rtas_take_timebase(void);
+
 #endif /* __KERNEL__ */
 #endif /* _POWERPC_RTAS_H */
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 4dd38f1..3cadba6 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -191,11 +191,49 @@ transfer_to_handler_cont:
 	mflr	r9
 	lwz	r11,0(r9)		/* virtual address of handler */
 	lwz	r9,4(r9)		/* where to go when done */
+#ifdef CONFIG_TRACE_IRQFLAGS
+	lis	r12,reenable_mmu@h
+	ori	r12,r12,reenable_mmu@l
+	mtspr	SPRN_SRR0,r12
+	mtspr	SPRN_SRR1,r10
+	SYNC
+	RFI
+reenable_mmu:				/* re-enable mmu so we can */
+	mfmsr	r10
+	lwz	r12,_MSR(r1)
+	xor	r10,r10,r12
+	andi.	r10,r10,MSR_EE		/* Did EE change? */
+	beq	1f
+
+	/* Save handler and return address into the 2 unused words
+	 * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything
+	 * else can be recovered from the pt_regs except r3 which for
+	 * normal interrupts has been set to pt_regs and for syscalls
+	 * is an argument, so we temporarily use ORIG_GPR3 to save it
+	 */
+	stw	r9,8(r1)
+	stw	r11,12(r1)
+	stw	r3,ORIG_GPR3(r1)
+	bl	trace_hardirqs_off
+	lwz	r0,GPR0(r1)
+	lwz	r3,ORIG_GPR3(r1)
+	lwz	r4,GPR4(r1)
+	lwz	r5,GPR5(r1)
+	lwz	r6,GPR6(r1)
+	lwz	r7,GPR7(r1)
+	lwz	r8,GPR8(r1)
+	lwz	r9,8(r1)
+	lwz	r11,12(r1)
+1:	mtctr	r11
+	mtlr	r9
+	bctr				/* jump to handler */
+#else /* CONFIG_TRACE_IRQFLAGS */
 	mtspr	SPRN_SRR0,r11
 	mtspr	SPRN_SRR1,r10
 	mtlr	r9
 	SYNC
 	RFI				/* jump to handler, enable MMU */
+#endif /* CONFIG_TRACE_IRQFLAGS */
 
 #if defined (CONFIG_6xx) || defined(CONFIG_E500)
 4:	rlwinm	r12,r12,0,~_TLF_NAPPING
@@ -251,6 +289,31 @@ _GLOBAL(DoSyscall)
 #ifdef SHOW_SYSCALLS
 	bl	do_show_syscall
 #endif /* SHOW_SYSCALLS */
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* Return from syscalls can (and generally will) hard enable
+	 * interrupts. You aren't supposed to call a syscall with
+	 * interrupts disabled in the first place. However, to ensure
+	 * that we get it right vs. lockdep if it happens, we force
+	 * that hard enable here with appropriate tracing if we see
+	 * that we have been called with interrupts off
+	 */
+	mfmsr	r11
+	andi.	r12,r11,MSR_EE
+	bne+	1f
+	/* We came in with interrupts disabled, we enable them now */
+	bl	trace_hardirqs_on
+	mfmsr	r11
+	lwz	r0,GPR0(r1)
+	lwz	r3,GPR3(r1)
+	lwz	r4,GPR4(r1)
+	ori	r11,r11,MSR_EE
+	lwz	r5,GPR5(r1)
+	lwz	r6,GPR6(r1)
+	lwz	r7,GPR7(r1)
+	lwz	r8,GPR8(r1)
+	mtmsr	r11
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
 	rlwinm	r10,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
 	lwz	r11,TI_FLAGS(r10)
 	andi.	r11,r11,_TIF_SYSCALL_T_OR_A
@@ -275,6 +338,7 @@ ret_from_syscall:
 	rlwinm	r12,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
 	/* disable interrupts so current_thread_info()->flags can't change */
 	LOAD_MSR_KERNEL(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
+	/* Note: We don't bother telling lockdep about it */
 	SYNC
 	MTMSRD(r10)
 	lwz	r9,TI_FLAGS(r12)
@@ -288,6 +352,19 @@ ret_from_syscall:
 	oris	r11,r11,0x1000	/* Set SO bit in CR */
 	stw	r11,_CCR(r1)
 syscall_exit_cont:
+	lwz	r8,_MSR(r1)
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* If we are going to return from the syscall with interrupts
+	 * off, we trace that here. It shouldn't happen though but we
+	 * want to catch the bugger if it does right ?
+	 */
+	andi.	r10,r8,MSR_EE
+	bne+	1f
+	stw	r3,GPR3(r1)
+	bl      trace_hardirqs_off
+	lwz	r3,GPR3(r1)
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
 #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
 	/* If the process has its own DBCR0 value, load it up.  The internal
 	   debug mode bit tells us that dbcr0 should be loaded. */
@@ -311,7 +388,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	mtlr	r4
 	mtcr	r5
 	lwz	r7,_NIP(r1)
-	lwz	r8,_MSR(r1)
 	FIX_SRR1(r8, r0)
 	lwz	r2,GPR2(r1)
 	lwz	r1,GPR1(r1)
@@ -394,7 +470,9 @@ syscall_exit_work:
 	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
 	beq	ret_from_except
 
-	/* Re-enable interrupts */
+	/* Re-enable interrupts. There is no need to trace that with
+	 * lockdep as we are supposed to have IRQs on at this point
+	 */
 	ori	r10,r10,MSR_EE
 	SYNC
 	MTMSRD(r10)
@@ -705,6 +783,7 @@ ret_from_except:
 	/* Hard-disable interrupts so that current_thread_info()->flags
 	 * can't change between when we test it and when we return
 	 * from the interrupt. */
+	/* Note: We don't bother telling lockdep about it */
 	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
 	SYNC			/* Some chip revs have problems here... */
 	MTMSRD(r10)		/* disable interrupts */
@@ -744,11 +823,24 @@ resume_kernel:
 	beq+	restore
 	andi.	r0,r3,MSR_EE	/* interrupts off? */
 	beq	restore		/* don't schedule if so */
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* Lockdep thinks irqs are enabled, we need to call
+	 * preempt_schedule_irq with IRQs off, so we inform lockdep
+	 * now that we -did- turn them off already
+	 */
+	bl	trace_hardirqs_off
+#endif
 1:	bl	preempt_schedule_irq
 	rlwinm	r9,r1,0,0,(31-THREAD_SHIFT)
 	lwz	r3,TI_FLAGS(r9)
 	andi.	r0,r3,_TIF_NEED_RESCHED
 	bne-	1b
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* And now, to properly rebalance the above, we tell lockdep they
+	 * are being turned back on, which will happen when we return
+	 */
+	bl	trace_hardirqs_on
+#endif
 #else
 resume_kernel:
 #endif /* CONFIG_PREEMPT */
@@ -765,6 +857,28 @@ restore:
 	stw	r6,icache_44x_need_flush@l(r4)
 1:
 #endif  /* CONFIG_44x */
+
+	lwz	r9,_MSR(r1)
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* Lockdep doesn't know about the fact that IRQs are temporarily turned
+	 * off in this assembly code while peeking at TI_FLAGS() and such. However
+	 * we need to inform it if the exception turned interrupts off, and we
+	 * are about to trun them back on.
+	 *
+	 * The problem here sadly is that we don't know whether the exceptions was
+	 * one that turned interrupts off or not. So we always tell lockdep about
+	 * turning them on here when we go back to wherever we came from with EE
+	 * on, even if that may meen some redudant calls being tracked. Maybe later
+	 * we could encode what the exception did somewhere or test the exception
+	 * type in the pt_regs but that sounds overkill
+	 */
+	andi.	r10,r9,MSR_EE
+	beq	1f
+	bl	trace_hardirqs_on
+	lwz	r9,_MSR(r1)
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
+
 	lwz	r0,GPR0(r1)
 	lwz	r2,GPR2(r1)
 	REST_4GPRS(3, r1)
@@ -782,7 +896,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	stwcx.	r0,0,r1			/* to clear the reservation */
 
 #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
-	lwz	r9,_MSR(r1)
 	andi.	r10,r9,MSR_RI		/* check if this exception occurred */
 	beql	nonrecoverable		/* at a bad place (MSR:RI = 0) */
 
@@ -805,7 +918,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	MTMSRD(r10)		/* clear the RI bit */
 	.globl exc_exit_restart
 exc_exit_restart:
-	lwz	r9,_MSR(r1)
 	lwz	r12,_NIP(r1)
 	FIX_SRR1(r9,r10)
 	mtspr	SPRN_SRR0,r12
@@ -1035,11 +1147,18 @@ do_work:			/* r10 contains MSR_KERNEL here */
 	beq	do_user_signal
 
 do_resched:			/* r10 contains MSR_KERNEL here */
+	/* Note: We don't need to inform lockdep that we are enabling
+	 * interrupts here. As far as it knows, they are already enabled
+	 */
 	ori	r10,r10,MSR_EE
 	SYNC
 	MTMSRD(r10)		/* hard-enable interrupts */
 	bl	schedule
 recheck:
+	/* Note: And we don't tell it we are disabling them again
+	 * neither. Those disable/enable cycles used to peek at
+	 * TI_FLAGS aren't advertised.
+	 */
 	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
 	SYNC
 	MTMSRD(r10)		/* disable interrupts */
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 4846946..fc21329 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -1124,9 +1124,8 @@ mmu_off:
 	RFI
 
 /*
- * Use the first pair of BAT registers to map the 1st 16MB
- * of RAM to PAGE_OFFSET.  From this point on we can't safely
- * call OF any more.
+ * On 601, we use 3 BATs to map up to 24M of RAM at _PAGE_OFFSET
+ * (we keep one for debugging) and on others, we use one 256M BAT.
  */
 initial_bats:
 	lis	r11,PAGE_OFFSET@h
@@ -1136,12 +1135,16 @@ initial_bats:
 	bne	4f
 	ori	r11,r11,4		/* set up BAT registers for 601 */
 	li	r8,0x7f			/* valid, block length = 8MB */
-	oris	r9,r11,0x800000@h	/* set up BAT reg for 2nd 8M */
-	oris	r10,r8,0x800000@h	/* set up BAT reg for 2nd 8M */
 	mtspr	SPRN_IBAT0U,r11		/* N.B. 601 has valid bit in */
 	mtspr	SPRN_IBAT0L,r8		/* lower BAT register */
-	mtspr	SPRN_IBAT1U,r9
-	mtspr	SPRN_IBAT1L,r10
+	addis	r11,r11,0x800000@h
+	addis	r8,r8,0x800000@h
+	mtspr	SPRN_IBAT1U,r11
+	mtspr	SPRN_IBAT1L,r8
+	addis	r11,r11,0x800000@h
+	addis	r8,r8,0x800000@h
+	mtspr	SPRN_IBAT2U,r11
+	mtspr	SPRN_IBAT2L,r8
 	isync
 	blr
 
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index fa983a5..a359cb0 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -76,7 +76,7 @@ struct of_device *of_device_alloc(struct device_node *np,
 	dev->dev.archdata.of_node = np;
 
 	if (bus_id)
-		dev_set_name(&dev->dev, bus_id);
+		dev_set_name(&dev->dev, "%s", bus_id);
 	else
 		of_device_make_bus_id(dev);
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3e7135bb..892a9f2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -528,7 +528,7 @@ void show_regs(struct pt_regs * regs)
 
 	for (i = 0;  i < 32;  i++) {
 		if ((i % REGS_PER_LINE) == 0)
-			printk("\n" KERN_INFO "GPR%02d: ", i);
+			printk("\nGPR%02d: ", i);
 		printk(REG " ", regs->gpr[i]);
 		if (i == LAST_VOLATILE && !FULL_REGS(regs))
 			break;
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index ee4c760..c434823 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -38,9 +38,10 @@
 #include <asm/syscalls.h>
 #include <asm/smp.h>
 #include <asm/atomic.h>
+#include <asm/time.h>
 
 struct rtas_t rtas = {
-	.lock = SPIN_LOCK_UNLOCKED
+	.lock = __RAW_SPIN_LOCK_UNLOCKED
 };
 EXPORT_SYMBOL(rtas);
 
@@ -67,6 +68,28 @@ unsigned long rtas_rmo_buf;
 void (*rtas_flash_term_hook)(int);
 EXPORT_SYMBOL(rtas_flash_term_hook);
 
+/* RTAS use home made raw locking instead of spin_lock_irqsave
+ * because those can be called from within really nasty contexts
+ * such as having the timebase stopped which would lockup with
+ * normal locks and spinlock debugging enabled
+ */
+static unsigned long lock_rtas(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	preempt_disable();
+	__raw_spin_lock_flags(&rtas.lock, flags);
+	return flags;
+}
+
+static void unlock_rtas(unsigned long flags)
+{
+	__raw_spin_unlock(&rtas.lock);
+	local_irq_restore(flags);
+	preempt_enable();
+}
+
 /*
  * call_rtas_display_status and call_rtas_display_status_delay
  * are designed only for very early low-level debugging, which
@@ -79,7 +102,7 @@ static void call_rtas_display_status(char c)
 
 	if (!rtas.base)
 		return;
-	spin_lock_irqsave(&rtas.lock, s);
+	s = lock_rtas();
 
 	args->token = 10;
 	args->nargs = 1;
@@ -89,7 +112,7 @@ static void call_rtas_display_status(char c)
 
 	enter_rtas(__pa(args));
 
-	spin_unlock_irqrestore(&rtas.lock, s);
+	unlock_rtas(s);
 }
 
 static void call_rtas_display_status_delay(char c)
@@ -411,8 +434,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 	if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE)
 		return -1;
 
-	/* Gotta do something different here, use global lock for now... */
-	spin_lock_irqsave(&rtas.lock, s);
+	s = lock_rtas();
 	rtas_args = &rtas.args;
 
 	rtas_args->token = token;
@@ -439,8 +461,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 			outputs[i] = rtas_args->rets[i+1];
 	ret = (nret > 0)? rtas_args->rets[0]: 0;
 
-	/* Gotta do something different here, use global lock for now... */
-	spin_unlock_irqrestore(&rtas.lock, s);
+	unlock_rtas(s);
 
 	if (buff_copy) {
 		log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0);
@@ -837,7 +858,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 
 	buff_copy = get_errorlog_buffer();
 
-	spin_lock_irqsave(&rtas.lock, flags);
+	flags = lock_rtas();
 
 	rtas.args = args;
 	enter_rtas(__pa(&rtas.args));
@@ -848,7 +869,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 	if (args.rets[0] == -1)
 		errbuf = __fetch_rtas_last_error(buff_copy);
 
-	spin_unlock_irqrestore(&rtas.lock, flags);
+	unlock_rtas(flags);
 
 	if (buff_copy) {
 		if (errbuf)
@@ -951,3 +972,33 @@ int __init early_init_dt_scan_rtas(unsigned long node,
 	/* break now */
 	return 1;
 }
+
+static raw_spinlock_t timebase_lock;
+static u64 timebase = 0;
+
+void __cpuinit rtas_give_timebase(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	hard_irq_disable();
+	__raw_spin_lock(&timebase_lock);
+	rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL);
+	timebase = get_tb();
+	__raw_spin_unlock(&timebase_lock);
+
+	while (timebase)
+		barrier();
+	rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL);
+	local_irq_restore(flags);
+}
+
+void __cpuinit rtas_take_timebase(void)
+{
+	while (!timebase)
+		barrier();
+	__raw_spin_lock(&timebase_lock);
+	set_tb(timebase >> 32, timebase & 0xffffffff);
+	timebase = 0;
+	__raw_spin_unlock(&timebase_lock);
+}
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 1d15424..e1e3059 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -119,6 +119,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
  */
 notrace void __init machine_init(unsigned long dt_ptr)
 {
+	lockdep_init();
+
 	/* Enable early debugging if any specified (see udbg.h) */
 	udbg_early_init();
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 65484b2..0b47de0 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -68,7 +68,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 /* SMP operations for this machine */
 struct smp_ops_t *smp_ops;
 
-static volatile unsigned int cpu_callin_map[NR_CPUS];
+/* Can't be static due to PowerMac hackery */
+volatile unsigned int cpu_callin_map[NR_CPUS];
 
 int smt_enabled_at_boot = 1;
 
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 0362a89..acb74a1 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -219,7 +219,7 @@ void udbg_init_pas_realmode(void)
 #ifdef CONFIG_PPC_EARLY_DEBUG_44x
 #include <platforms/44x/44x.h>
 
-static int udbg_44x_as1_flush(void)
+static void udbg_44x_as1_flush(void)
 {
 	if (udbg_comport) {
 		while ((as1_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 2d2192e..3e68363 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -30,3 +30,4 @@ obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage-prot.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
+obj-$(CONFIG_HIGHMEM)		+= highmem.o
diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c
new file mode 100644
index 0000000..c2186c7
--- /dev/null
+++ b/arch/powerpc/mm/highmem.c
@@ -0,0 +1,77 @@
+/*
+ * highmem.c: virtual kernel memory mappings for high memory
+ *
+ * PowerPC version, stolen from the i386 version.
+ *
+ * Used in CONFIG_HIGHMEM systems for memory pages which
+ * are not addressable by direct kernel virtual addresses.
+ *
+ * Copyright (C) 1999 Gerhard Wichert, Siemens AG
+ *		      Gerhard.Wichert@pdb.siemens.de
+ *
+ *
+ * Redesigned the x86 32-bit VM architecture to deal with
+ * up to 16 Terrabyte physical memory. With current x86 CPUs
+ * we now support up to 64 Gigabytes physical RAM.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ *
+ * Reworked for PowerPC by various contributors. Moved from
+ * highmem.h by Benjamin Herrenschmidt (c) 2009 IBM Corp.
+ */
+
+#include <linux/highmem.h>
+#include <linux/module.h>
+
+/*
+ * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap
+ * gives a more generic (and caching) interface. But kmap_atomic can
+ * be used in IRQ contexts, so in some (very limited) cases we need
+ * it.
+ */
+void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot)
+{
+	unsigned int idx;
+	unsigned long vaddr;
+
+	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	pagefault_disable();
+	if (!PageHighMem(page))
+		return page_address(page);
+
+	debug_kmap_atomic(type);
+	idx = type + KM_TYPE_NR*smp_processor_id();
+	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+#ifdef CONFIG_DEBUG_HIGHMEM
+	BUG_ON(!pte_none(*(kmap_pte-idx)));
+#endif
+	__set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot), 1);
+	local_flush_tlb_page(NULL, vaddr);
+
+	return (void*) vaddr;
+}
+EXPORT_SYMBOL(kmap_atomic_prot);
+
+void kunmap_atomic(void *kvaddr, enum km_type type)
+{
+#ifdef CONFIG_DEBUG_HIGHMEM
+	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
+	enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
+
+	if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
+		pagefault_enable();
+		return;
+	}
+
+	BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
+
+	/*
+	 * force other mappings to Oops if they'll try to access
+	 * this pte without first remap it
+	 */
+	pte_clear(&init_mm, vaddr, kmap_pte-idx);
+	local_flush_tlb_page(NULL, vaddr);
+#endif
+	pagefault_enable();
+}
+EXPORT_SYMBOL(kunmap_atomic);
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index 42e09a9..0362c88 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -16,6 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/of_gpio.h>
+#include <linux/of_i2c.h>
 
 #include <asm/machdep.h>
 #include <asm/prom.h>
@@ -65,7 +66,6 @@ define_machine(warp) {
 
 static u32 post_info;
 
-/* I am not sure this is the best place for this... */
 static int __init warp_post_info(void)
 {
 	struct device_node *np;
@@ -194,9 +194,9 @@ static int pika_setup_leds(void)
 	return 0;
 }
 
-static void pika_setup_critical_temp(struct i2c_client *client)
+static void pika_setup_critical_temp(struct device_node *np,
+				     struct i2c_client *client)
 {
-	struct device_node *np;
 	int irq, rc;
 
 	/* Do this before enabling critical temp interrupt since we
@@ -208,14 +208,7 @@ static void pika_setup_critical_temp(struct i2c_client *client)
 	i2c_smbus_write_byte_data(client, 2, 65); /* Thigh */
 	i2c_smbus_write_byte_data(client, 3,  0); /* Tlow */
 
-	np = of_find_compatible_node(NULL, NULL, "adi,ad7414");
-	if (np == NULL) {
-		printk(KERN_ERR __FILE__ ": Unable to find ad7414\n");
-		return;
-	}
-
 	irq = irq_of_parse_and_map(np, 0);
-	of_node_put(np);
 	if (irq  == NO_IRQ) {
 		printk(KERN_ERR __FILE__ ": Unable to get ad7414 irq\n");
 		return;
@@ -244,32 +237,24 @@ static inline void pika_dtm_check_fan(void __iomem *fpga)
 
 static int pika_dtm_thread(void __iomem *fpga)
 {
-	struct i2c_adapter *adap;
+	struct device_node *np;
 	struct i2c_client *client;
 
-	/* We loop in case either driver was compiled as a module and
-	 * has not been insmoded yet.
-	 */
-	while (!(adap = i2c_get_adapter(0))) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		schedule_timeout(HZ);
-	}
-
-	while (1) {
-		list_for_each_entry(client, &adap->clients, list)
-			if (client->addr == 0x4a)
-				goto found_it;
+	np = of_find_compatible_node(NULL, NULL, "adi,ad7414");
+	if (np == NULL)
+		return -ENOENT;
 
-		set_current_state(TASK_INTERRUPTIBLE);
-		schedule_timeout(HZ);
+	client = of_find_i2c_device_by_node(np);
+	if (client == NULL) {
+		of_node_put(np);
+		return -ENOENT;
 	}
 
-found_it:
-	pika_setup_critical_temp(client);
+	pika_setup_critical_temp(np, client);
 
-	i2c_put_adapter(adap);
+	of_node_put(np);
 
-	printk(KERN_INFO "PIKA DTM thread running.\n");
+	printk(KERN_INFO "Warp DTM thread running.\n");
 
 	while (!kthread_should_stop()) {
 		int val;
@@ -291,7 +276,6 @@ found_it:
 	return 0;
 }
 
-
 static int __init pika_dtm_start(void)
 {
 	struct task_struct *dtm_thread;
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index 77f90b3..60ed9c0 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -285,6 +285,7 @@ static struct of_device_id mpc85xx_ids[] = {
 	{ .type = "qe", },
 	{ .compatible = "fsl,qe", },
 	{ .compatible = "gianfar", },
+	{ .compatible = "fsl,rapidio-delta", },
 	{},
 };
 
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index cc0b0db..62c592ede6 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -52,20 +52,19 @@ smp_85xx_kick_cpu(int nr)
 
 	pr_debug("smp_85xx_kick_cpu: kick CPU #%d\n", nr);
 
-	local_irq_save(flags);
-
 	np = of_get_cpu_node(nr, NULL);
 	cpu_rel_addr = of_get_property(np, "cpu-release-addr", NULL);
 
 	if (cpu_rel_addr == NULL) {
 		printk(KERN_ERR "No cpu-release-addr for cpu %d\n", nr);
-		local_irq_restore(flags);
 		return;
 	}
 
 	/* Map the spin table */
 	bptr_vaddr = ioremap(*cpu_rel_addr, SIZE_BOOT_ENTRY);
 
+	local_irq_save(flags);
+
 	out_be32(bptr_vaddr + BOOT_ENTRY_PIR, nr);
 	out_be32(bptr_vaddr + BOOT_ENTRY_ADDR_LOWER, __pa(__early_start));
 
@@ -73,10 +72,10 @@ smp_85xx_kick_cpu(int nr)
 	while ((__secondary_hold_acknowledge != nr) && (++n < 1000))
 		mdelay(1);
 
-	iounmap(bptr_vaddr);
-
 	local_irq_restore(flags);
 
+	iounmap(bptr_vaddr);
+
 	pr_debug("waited %d msecs for CPU #%d.\n", n, nr);
 }
 
diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c
index d0e8443..747d8fb 100644
--- a/arch/powerpc/platforms/85xx/socrates.c
+++ b/arch/powerpc/platforms/85xx/socrates.c
@@ -102,10 +102,11 @@ static struct of_device_id __initdata socrates_of_bus_ids[] = {
 	{},
 };
 
-static void __init socrates_init(void)
+static int __init socrates_publish_devices(void)
 {
-	of_platform_bus_probe(NULL, socrates_of_bus_ids, NULL);
+	return of_platform_bus_probe(NULL, socrates_of_bus_ids, NULL);
 }
+machine_device_initcall(socrates, socrates_publish_devices);
 
 /*
  * Called very early, device-tree isn't unflattened
@@ -124,7 +125,6 @@ define_machine(socrates) {
 	.name			= "Socrates",
 	.probe			= socrates_probe,
 	.setup_arch		= socrates_setup_arch,
-	.init			= socrates_init,
 	.init_IRQ		= socrates_pic_init,
 	.get_irq		= mpic_get_irq,
 	.restart		= fsl_rstcr_restart,
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index ee01532..1b42605 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -32,7 +32,6 @@
 
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
-#include <linux/of_platform.h>
 
 /* A few bit definitions needed for fixups on some boards */
 #define MPC85xx_L2CTL_L2E		0x80000000 /* L2 enable */
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index 9046803..bc97fad 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -36,7 +36,6 @@
 #include <asm/prom.h>
 #include <asm/smp.h>
 #include <asm/paca.h>
-#include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/cputable.h>
 #include <asm/firmware.h>
@@ -140,31 +139,6 @@ static void __devinit smp_cell_setup_cpu(int cpu)
 	mtspr(SPRN_DABRX, DABRX_KERNEL | DABRX_USER);
 }
 
-static DEFINE_SPINLOCK(timebase_lock);
-static unsigned long timebase = 0;
-
-static void __devinit cell_give_timebase(void)
-{
-	spin_lock(&timebase_lock);
-	rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL);
-	timebase = get_tb();
-	spin_unlock(&timebase_lock);
-
-	while (timebase)
-		barrier();
-	rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL);
-}
-
-static void __devinit cell_take_timebase(void)
-{
-	while (!timebase)
-		barrier();
-	spin_lock(&timebase_lock);
-	set_tb(timebase >> 32, timebase & 0xffffffff);
-	timebase = 0;
-	spin_unlock(&timebase_lock);
-}
-
 static void __devinit smp_cell_kick_cpu(int nr)
 {
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
@@ -224,8 +198,8 @@ void __init smp_init_cell(void)
 
 	/* Non-lpar has additional take/give timebase */
 	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
-		smp_ops->give_timebase = cell_give_timebase;
-		smp_ops->take_timebase = cell_take_timebase;
+		smp_ops->give_timebase = rtas_give_timebase;
+		smp_ops->take_timebase = rtas_take_timebase;
 	}
 
 	DBG(" <- smp_init_cell()\n");
diff --git a/arch/powerpc/platforms/chrp/smp.c b/arch/powerpc/platforms/chrp/smp.c
index 10a4a4d..02cafec 100644
--- a/arch/powerpc/platforms/chrp/smp.c
+++ b/arch/powerpc/platforms/chrp/smp.c
@@ -26,7 +26,6 @@
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/smp.h>
-#include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/mpic.h>
 #include <asm/rtas.h>
@@ -42,40 +41,12 @@ static void __devinit smp_chrp_setup_cpu(int cpu_nr)
 	mpic_setup_this_cpu();
 }
 
-static DEFINE_SPINLOCK(timebase_lock);
-static unsigned int timebase_upper = 0, timebase_lower = 0;
-
-void __devinit smp_chrp_give_timebase(void)
-{
-	spin_lock(&timebase_lock);
-	rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL);
-	timebase_upper = get_tbu();
-	timebase_lower = get_tbl();
-	spin_unlock(&timebase_lock);
-
-	while (timebase_upper || timebase_lower)
-		barrier();
-	rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL);
-}
-
-void __devinit smp_chrp_take_timebase(void)
-{
-	while (!(timebase_upper || timebase_lower))
-		barrier();
-	spin_lock(&timebase_lock);
-	set_tb(timebase_upper, timebase_lower);
-	timebase_upper = 0;
-	timebase_lower = 0;
-	spin_unlock(&timebase_lock);
-	printk("CPU %i taken timebase\n", smp_processor_id());
-}
-
 /* CHRP with openpic */
 struct smp_ops_t chrp_smp_ops = {
 	.message_pass = smp_mpic_message_pass,
 	.probe = smp_mpic_probe,
 	.kick_cpu = smp_chrp_kick_cpu,
 	.setup_cpu = smp_chrp_setup_cpu,
-	.give_timebase = smp_chrp_give_timebase,
-	.take_timebase = smp_chrp_take_timebase,
+	.give_timebase = rtas_give_timebase,
+	.take_timebase = rtas_take_timebase,
 };
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index 153051e..a461934 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -71,20 +71,25 @@ static void pas_restart(char *cmd)
 }
 
 #ifdef CONFIG_SMP
-static DEFINE_SPINLOCK(timebase_lock);
+static raw_spinlock_t timebase_lock;
 static unsigned long timebase;
 
 static void __devinit pas_give_timebase(void)
 {
-	spin_lock(&timebase_lock);
+	unsigned long flags;
+
+	local_irq_save(flags);
+	hard_irq_disable();
+	__raw_spin_lock(&timebase_lock);
 	mtspr(SPRN_TBCTL, TBCTL_FREEZE);
 	isync();
 	timebase = get_tb();
-	spin_unlock(&timebase_lock);
+	__raw_spin_unlock(&timebase_lock);
 
 	while (timebase)
 		barrier();
 	mtspr(SPRN_TBCTL, TBCTL_RESTART);
+	local_irq_restore(flags);
 }
 
 static void __devinit pas_take_timebase(void)
@@ -92,10 +97,10 @@ static void __devinit pas_take_timebase(void)
 	while (!timebase)
 		smp_rmb();
 
-	spin_lock(&timebase_lock);
+	__raw_spin_lock(&timebase_lock);
 	set_tb(timebase >> 32, timebase & 0xffffffff);
 	timebase = 0;
-	spin_unlock(&timebase_lock);
+	__raw_spin_unlock(&timebase_lock);
 }
 
 struct smp_ops_t pas_smp_ops = {
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 86f69a4..c205226 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -103,11 +103,6 @@ unsigned long smu_cmdbuf_abs;
 EXPORT_SYMBOL(smu_cmdbuf_abs);
 #endif
 
-#ifdef CONFIG_SMP
-extern struct smp_ops_t psurge_smp_ops;
-extern struct smp_ops_t core99_smp_ops;
-#endif /* CONFIG_SMP */
-
 static void pmac_show_cpuinfo(struct seq_file *m)
 {
 	struct device_node *np;
@@ -341,34 +336,6 @@ static void __init pmac_setup_arch(void)
 		ROOT_DEV = DEFAULT_ROOT_DEVICE;
 #endif
 
-#ifdef CONFIG_SMP
-	/* Check for Core99 */
-	ic = of_find_node_by_name(NULL, "uni-n");
-	if (!ic)
-		ic = of_find_node_by_name(NULL, "u3");
-	if (!ic)
-		ic = of_find_node_by_name(NULL, "u4");
-	if (ic) {
-		of_node_put(ic);
-		smp_ops = &core99_smp_ops;
-	}
-#ifdef CONFIG_PPC32
-	else {
-		/*
-		 * We have to set bits in cpu_possible_map here since the
-		 * secondary CPU(s) aren't in the device tree, and
-		 * setup_per_cpu_areas only allocates per-cpu data for
-		 * CPUs in the cpu_possible_map.
-		 */
-		int cpu;
-
-		for (cpu = 1; cpu < 4 && cpu < NR_CPUS; ++cpu)
-			cpu_set(cpu, cpu_possible_map);
-		smp_ops = &psurge_smp_ops;
-	}
-#endif
-#endif /* CONFIG_SMP */
-
 #ifdef CONFIG_ADB
 	if (strstr(cmd_line, "adb_sync")) {
 		extern int __adb_probe_sync;
@@ -512,6 +479,14 @@ static void __init pmac_init_early(void)
 #ifdef CONFIG_PPC64
 	iommu_init_early_dart();
 #endif
+
+	/* SMP Init has to be done early as we need to patch up
+	 * cpu_possible_map before interrupt stacks are allocated
+	 * or kaboom...
+	 */
+#ifdef CONFIG_SMP
+	pmac_setup_smp();
+#endif
 }
 
 static int __init pmac_declare_of_platform_devices(void)
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index cf1dbe7..6d4da7b 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -64,10 +64,11 @@
 extern void __secondary_start_pmac_0(void);
 extern int pmac_pfunc_base_install(void);
 
-#ifdef CONFIG_PPC32
+static void (*pmac_tb_freeze)(int freeze);
+static u64 timebase;
+static int tb_req;
 
-/* Sync flag for HW tb sync */
-static volatile int sec_tb_reset = 0;
+#ifdef CONFIG_PPC32
 
 /*
  * Powersurge (old powermac SMP) support.
@@ -294,6 +295,9 @@ static int __init smp_psurge_probe(void)
 		psurge_quad_init();
 		/* All released cards using this HW design have 4 CPUs */
 		ncpus = 4;
+		/* No sure how timebase sync works on those, let's use SW */
+		smp_ops->give_timebase = smp_generic_give_timebase;
+		smp_ops->take_timebase = smp_generic_take_timebase;
 	} else {
 		iounmap(quad_base);
 		if ((in_8(hhead_base + HHEAD_CONFIG) & 0x02) == 0) {
@@ -308,18 +312,15 @@ static int __init smp_psurge_probe(void)
 	psurge_start = ioremap(PSURGE_START, 4);
 	psurge_pri_intr = ioremap(PSURGE_PRI_INTR, 4);
 
-	/*
-	 * This is necessary because OF doesn't know about the
+	/* This is necessary because OF doesn't know about the
 	 * secondary cpu(s), and thus there aren't nodes in the
 	 * device tree for them, and smp_setup_cpu_maps hasn't
-	 * set their bits in cpu_possible_map and cpu_present_map.
+	 * set their bits in cpu_present_map.
 	 */
 	if (ncpus > NR_CPUS)
 		ncpus = NR_CPUS;
-	for (i = 1; i < ncpus ; ++i) {
+	for (i = 1; i < ncpus ; ++i)
 		cpu_set(i, cpu_present_map);
-		set_hard_smp_processor_id(i, i);
-	}
 
 	if (ppc_md.progress) ppc_md.progress("smp_psurge_probe - done", 0x352);
 
@@ -329,8 +330,14 @@ static int __init smp_psurge_probe(void)
 static void __init smp_psurge_kick_cpu(int nr)
 {
 	unsigned long start = __pa(__secondary_start_pmac_0) + nr * 8;
-	unsigned long a;
-	int i;
+	unsigned long a, flags;
+	int i, j;
+
+	/* Defining this here is evil ... but I prefer hiding that
+	 * crap to avoid giving people ideas that they can do the
+	 * same.
+	 */
+	extern volatile unsigned int cpu_callin_map[NR_CPUS];
 
 	/* may need to flush here if secondary bats aren't setup */
 	for (a = KERNELBASE; a < KERNELBASE + 0x800000; a += 32)
@@ -339,47 +346,52 @@ static void __init smp_psurge_kick_cpu(int nr)
 
 	if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu", 0x353);
 
+	/* This is going to freeze the timeebase, we disable interrupts */
+	local_irq_save(flags);
+
 	out_be32(psurge_start, start);
 	mb();
 
 	psurge_set_ipi(nr);
+
 	/*
 	 * We can't use udelay here because the timebase is now frozen.
 	 */
 	for (i = 0; i < 2000; ++i)
-		barrier();
+		asm volatile("nop" : : : "memory");
 	psurge_clr_ipi(nr);
 
-	if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu - done", 0x354);
-}
-
-/*
- * With the dual-cpu powersurge board, the decrementers and timebases
- * of both cpus are frozen after the secondary cpu is started up,
- * until we give the secondary cpu another interrupt.  This routine
- * uses this to get the timebases synchronized.
- *  -- paulus.
- */
-static void __init psurge_dual_sync_tb(int cpu_nr)
-{
-	int t;
-
-	set_dec(tb_ticks_per_jiffy);
-	/* XXX fixme */
-	set_tb(0, 0);
-
-	if (cpu_nr > 0) {
+	/*
+	 * Also, because the timebase is frozen, we must not return to the
+	 * caller which will try to do udelay's etc... Instead, we wait -here-
+	 * for the CPU to callin.
+	 */
+	for (i = 0; i < 100000 && !cpu_callin_map[nr]; ++i) {
+		for (j = 1; j < 10000; j++)
+			asm volatile("nop" : : : "memory");
+		asm volatile("sync" : : : "memory");
+	}
+	if (!cpu_callin_map[nr])
+		goto stuck;
+
+	/* And we do the TB sync here too for standard dual CPU cards */
+	if (psurge_type == PSURGE_DUAL) {
+		while(!tb_req)
+			barrier();
+		tb_req = 0;
+		mb();
+		timebase = get_tb();
+		mb();
+		while (timebase)
+			barrier();
 		mb();
-		sec_tb_reset = 1;
-		return;
 	}
+ stuck:
+	/* now interrupt the secondary, restarting both TBs */
+	if (psurge_type == PSURGE_DUAL)
+		psurge_set_ipi(1);
 
-	/* wait for the secondary to have reset its TB before proceeding */
-	for (t = 10000000; t > 0 && !sec_tb_reset; --t)
-		;
-
-	/* now interrupt the secondary, starting both TBs */
-	psurge_set_ipi(1);
+	if (ppc_md.progress) ppc_md.progress("smp_psurge_kick_cpu - done", 0x354);
 }
 
 static struct irqaction psurge_irqaction = {
@@ -390,36 +402,35 @@ static struct irqaction psurge_irqaction = {
 
 static void __init smp_psurge_setup_cpu(int cpu_nr)
 {
+	if (cpu_nr != 0)
+		return;
 
-	if (cpu_nr == 0) {
-		/* If we failed to start the second CPU, we should still
-		 * send it an IPI to start the timebase & DEC or we might
-		 * have them stuck.
-		 */
-		if (num_online_cpus() < 2) {
-			if (psurge_type == PSURGE_DUAL)
-				psurge_set_ipi(1);
-			return;
-		}
-		/* reset the entry point so if we get another intr we won't
-		 * try to startup again */
-		out_be32(psurge_start, 0x100);
-		if (setup_irq(30, &psurge_irqaction))
-			printk(KERN_ERR "Couldn't get primary IPI interrupt");
-	}
-
-	if (psurge_type == PSURGE_DUAL)
-		psurge_dual_sync_tb(cpu_nr);
+	/* reset the entry point so if we get another intr we won't
+	 * try to startup again */
+	out_be32(psurge_start, 0x100);
+	if (setup_irq(30, &psurge_irqaction))
+		printk(KERN_ERR "Couldn't get primary IPI interrupt");
 }
 
 void __init smp_psurge_take_timebase(void)
 {
-	/* Dummy implementation */
+	if (psurge_type != PSURGE_DUAL)
+		return;
+
+	tb_req = 1;
+	mb();
+	while (!timebase)
+		barrier();
+	mb();
+	set_tb(timebase >> 32, timebase & 0xffffffff);
+	timebase = 0;
+	mb();
+	set_dec(tb_ticks_per_jiffy/2);
 }
 
 void __init smp_psurge_give_timebase(void)
 {
-	/* Dummy implementation */
+	/* Nothing to do here */
 }
 
 /* PowerSurge-style Macs */
@@ -437,9 +448,6 @@ struct smp_ops_t psurge_smp_ops = {
  * Core 99 and later support
  */
 
-static void (*pmac_tb_freeze)(int freeze);
-static u64 timebase;
-static int tb_req;
 
 static void smp_core99_give_timebase(void)
 {
@@ -478,7 +486,6 @@ static void __devinit smp_core99_take_timebase(void)
 	set_tb(timebase >> 32, timebase & 0xffffffff);
 	timebase = 0;
 	mb();
-	set_dec(tb_ticks_per_jiffy/2);
 
 	local_irq_restore(flags);
 }
@@ -920,3 +927,34 @@ struct smp_ops_t core99_smp_ops = {
 # endif
 #endif
 };
+
+void __init pmac_setup_smp(void)
+{
+	struct device_node *np;
+
+	/* Check for Core99 */
+	np = of_find_node_by_name(NULL, "uni-n");
+	if (!np)
+		np = of_find_node_by_name(NULL, "u3");
+	if (!np)
+		np = of_find_node_by_name(NULL, "u4");
+	if (np) {
+		of_node_put(np);
+		smp_ops = &core99_smp_ops;
+	}
+#ifdef CONFIG_PPC32
+	else {
+		/* We have to set bits in cpu_possible_map here since the
+		 * secondary CPU(s) aren't in the device tree. Various
+		 * things won't be initialized for CPUs not in the possible
+		 * map, so we really need to fix it up here.
+		 */
+		int cpu;
+
+		for (cpu = 1; cpu < 4 && cpu < NR_CPUS; ++cpu)
+			cpu_set(cpu, cpu_possible_map);
+		smp_ops = &psurge_smp_ops;
+	}
+#endif /* CONFIG_PPC32 */
+}
+
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 1a231c3..1f8f6cf 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -35,7 +35,6 @@
 #include <asm/prom.h>
 #include <asm/smp.h>
 #include <asm/paca.h>
-#include <asm/time.h>
 #include <asm/machdep.h>
 #include <asm/cputable.h>
 #include <asm/firmware.h>
@@ -118,31 +117,6 @@ static void __devinit smp_xics_setup_cpu(int cpu)
 }
 #endif /* CONFIG_XICS */
 
-static DEFINE_SPINLOCK(timebase_lock);
-static unsigned long timebase = 0;
-
-static void __devinit pSeries_give_timebase(void)
-{
-	spin_lock(&timebase_lock);
-	rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL);
-	timebase = get_tb();
-	spin_unlock(&timebase_lock);
-
-	while (timebase)
-		barrier();
-	rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL);
-}
-
-static void __devinit pSeries_take_timebase(void)
-{
-	while (!timebase)
-		barrier();
-	spin_lock(&timebase_lock);
-	set_tb(timebase >> 32, timebase & 0xffffffff);
-	timebase = 0;
-	spin_unlock(&timebase_lock);
-}
-
 static void __devinit smp_pSeries_kick_cpu(int nr)
 {
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
@@ -209,8 +183,8 @@ static void __init smp_init_pseries(void)
 
 	/* Non-lpar has additional take/give timebase */
 	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
-		smp_ops->give_timebase = pSeries_give_timebase;
-		smp_ops->take_timebase = pSeries_take_timebase;
+		smp_ops->give_timebase = rtas_give_timebase;
+		smp_ops->take_timebase = rtas_take_timebase;
 	}
 
 	pr_debug(" <- smp_init_pSeries()\n");
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 9c3af50..d46de1f 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -279,28 +279,29 @@ static void _mpic_map_mmio(struct mpic *mpic, phys_addr_t phys_addr,
 }
 
 #ifdef CONFIG_PPC_DCR
-static void _mpic_map_dcr(struct mpic *mpic, struct mpic_reg_bank *rb,
+static void _mpic_map_dcr(struct mpic *mpic, struct device_node *node,
+			  struct mpic_reg_bank *rb,
 			  unsigned int offset, unsigned int size)
 {
 	const u32 *dbasep;
 
-	dbasep = of_get_property(mpic->irqhost->of_node, "dcr-reg", NULL);
+	dbasep = of_get_property(node, "dcr-reg", NULL);
 
-	rb->dhost = dcr_map(mpic->irqhost->of_node, *dbasep + offset, size);
+	rb->dhost = dcr_map(node, *dbasep + offset, size);
 	BUG_ON(!DCR_MAP_OK(rb->dhost));
 }
 
-static inline void mpic_map(struct mpic *mpic, phys_addr_t phys_addr,
-			    struct mpic_reg_bank *rb, unsigned int offset,
-			    unsigned int size)
+static inline void mpic_map(struct mpic *mpic, struct device_node *node,
+			    phys_addr_t phys_addr, struct mpic_reg_bank *rb,
+			    unsigned int offset, unsigned int size)
 {
 	if (mpic->flags & MPIC_USES_DCR)
-		_mpic_map_dcr(mpic, rb, offset, size);
+		_mpic_map_dcr(mpic, node, rb, offset, size);
 	else
 		_mpic_map_mmio(mpic, phys_addr, rb, offset, size);
 }
 #else /* CONFIG_PPC_DCR */
-#define mpic_map(m,p,b,o,s)	_mpic_map_mmio(m,p,b,o,s)
+#define mpic_map(m,n,p,b,o,s)	_mpic_map_mmio(m,p,b,o,s)
 #endif /* !CONFIG_PPC_DCR */
 
 
@@ -1052,11 +1053,10 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	int		intvec_top;
 	u64		paddr = phys_addr;
 
-	mpic = alloc_bootmem(sizeof(struct mpic));
+	mpic = kzalloc(sizeof(struct mpic), GFP_KERNEL);
 	if (mpic == NULL)
 		return NULL;
-	
-	memset(mpic, 0, sizeof(struct mpic));
+
 	mpic->name = name;
 
 	mpic->hc_irq = mpic_irq_chip;
@@ -1152,8 +1152,8 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	}
 
 	/* Map the global registers */
-	mpic_map(mpic, paddr, &mpic->gregs, MPIC_INFO(GREG_BASE), 0x1000);
-	mpic_map(mpic, paddr, &mpic->tmregs, MPIC_INFO(TIMER_BASE), 0x1000);
+	mpic_map(mpic, node, paddr, &mpic->gregs, MPIC_INFO(GREG_BASE), 0x1000);
+	mpic_map(mpic, node, paddr, &mpic->tmregs, MPIC_INFO(TIMER_BASE), 0x1000);
 
 	/* Reset */
 	if (flags & MPIC_WANTS_RESET) {
@@ -1194,7 +1194,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 
 	/* Map the per-CPU registers */
 	for (i = 0; i < mpic->num_cpus; i++) {
-		mpic_map(mpic, paddr, &mpic->cpuregs[i],
+		mpic_map(mpic, node, paddr, &mpic->cpuregs[i],
 			 MPIC_INFO(CPU_BASE) + i * MPIC_INFO(CPU_STRIDE),
 			 0x1000);
 	}
@@ -1202,7 +1202,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	/* Initialize main ISU if none provided */
 	if (mpic->isu_size == 0) {
 		mpic->isu_size = mpic->num_sources;
-		mpic_map(mpic, paddr, &mpic->isus[0],
+		mpic_map(mpic, node, paddr, &mpic->isus[0],
 			 MPIC_INFO(IRQ_BASE), MPIC_INFO(IRQ_STRIDE) * mpic->isu_size);
 	}
 	mpic->isu_shift = 1 + __ilog2(mpic->isu_size - 1);
@@ -1256,8 +1256,10 @@ void __init mpic_assign_isu(struct mpic *mpic, unsigned int isu_num,
 
 	BUG_ON(isu_num >= MPIC_MAX_ISU);
 
-	mpic_map(mpic, paddr, &mpic->isus[isu_num], 0,
+	mpic_map(mpic, mpic->irqhost->of_node,
+		 paddr, &mpic->isus[isu_num], 0,
 		 MPIC_INFO(IRQ_STRIDE) * mpic->isu_size);
+
 	if ((isu_first + mpic->isu_size) > mpic->num_sources)
 		mpic->num_sources = isu_first + mpic->isu_size;
 }
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index b28b0e5..237e365 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -112,6 +112,7 @@ int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol, u32 cmd_input)
 {
 	unsigned long flags;
 	u8 mcn_shift = 0, dev_shift = 0;
+	u32 ret;
 
 	spin_lock_irqsave(&qe_lock, flags);
 	if (cmd == QE_RESET) {
@@ -139,11 +140,13 @@ int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol, u32 cmd_input)
 	}
 
 	/* wait for the QE_CR_FLG to clear */
-	while(in_be32(&qe_immr->cp.cecr) & QE_CR_FLG)
-		cpu_relax();
+	ret = spin_event_timeout((in_be32(&qe_immr->cp.cecr) & QE_CR_FLG) == 0,
+			   100, 0);
+	/* On timeout (e.g. failure), the expression will be false (ret == 0),
+	   otherwise it will be true (ret == 1). */
 	spin_unlock_irqrestore(&qe_lock, flags);
 
-	return 0;
+	return ret == 1;
 }
 EXPORT_SYMBOL(qe_issue_cmd);