Merge tag 'v4.2-rc8' into x86/mm, before applying new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

15 files changed, 241 insertions, 212 deletions

diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 7a4bcc36303d..f9b3a81aefcd 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -15,12 +15,12 @@ generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mutex.h
 generic-y += param.h
 generic-y += percpu.h
 generic-y += poll.h
 generic-y += preempt.h
-generic-y += scatterlist.h
 generic-y += seccomp.h
 generic-y += segment.h
 generic-y += topology.h
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index de65f66ea64e..ec2df4bab302 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -142,6 +142,7 @@ static inline void kunmap(struct page *page)
 
 static inline void *kmap_atomic(struct page *page)
 {
+	preempt_disable();
 	pagefault_disable();
 	return page_address(page);
 }
@@ -150,6 +151,7 @@ static inline void __kunmap_atomic(void *addr)
 {
 	flush_kernel_dcache_page_addr(addr);
 	pagefault_enable();
+	preempt_enable();
 }
 
 #define kmap_atomic_prot(page, prot)	kmap_atomic(page)
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index dbd13354ec41..0a90b965cccb 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -46,8 +46,6 @@ __xchg(unsigned long x, __volatile__ void *ptr, int size)
 #define xchg(ptr, x) \
 	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
 
-#define __HAVE_ARCH_CMPXCHG	1
-
 /* bug catcher for when unsupported size is used - won't link */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h
index d0eae5f2bd87..d8d60a57183f 100644
--- a/arch/parisc/include/asm/dma-mapping.h
+++ b/arch/parisc/include/asm/dma-mapping.h
@@ -2,8 +2,8 @@
 #define _PARISC_DMA_MAPPING_H
 
 #include <linux/mm.h>
+#include <linux/scatterlist.h>
 #include <asm/cacheflush.h>
-#include <asm/scatterlist.h>
 
 /* See Documentation/DMA-API-HOWTO.txt */
 struct hppa_dma_ops {
diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h
index 20df2b04fc09..71889ea72740 100644
--- a/arch/parisc/include/asm/pci.h
+++ b/arch/parisc/include/asm/pci.h
@@ -1,7 +1,7 @@
 #ifndef __ASM_PARISC_PCI_H
 #define __ASM_PARISC_PCI_H
 
-#include <asm/scatterlist.h>
+#include <linux/scatterlist.h>
 
 
 
@@ -196,25 +196,6 @@ static inline void pcibios_register_hba(struct pci_hba_data *x)
 /* export the pci_ DMA API in terms of the dma_ one */
 #include <asm-generic/pci-dma-compat.h>
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_MULTIPLE;
-	*strategy_parameter = cacheline_size;
-}
-#endif
-
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
 	return channel ? 15 : 14;
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index 3a08eae3318f..3edbb9fc91b4 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -72,7 +72,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
+	if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED) {
 		/*
 		 * This is the permanent pmd attached to the pgd;
 		 * cannot free it.
@@ -81,6 +81,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 		 */
 		mm_inc_nr_pmds(mm);
 		return;
+	}
 	free_pages((unsigned long)pmd, PMD_ORDER);
 }
 
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 0a183756d6ec..f93c4a4e6580 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -16,7 +16,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 
-extern spinlock_t pa_dbit_lock;
+extern spinlock_t pa_tlb_lock;
 
 /*
  * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
@@ -33,6 +33,19 @@ extern spinlock_t pa_dbit_lock;
  */
 #define kern_addr_valid(addr)	(1)
 
+/* Purge data and instruction TLB entries.  Must be called holding
+ * the pa_tlb_lock.  The TLB purge instructions are slow on SMP
+ * machines since the purge must be broadcast to all CPUs.
+ */
+
+static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
+{
+	mtsp(mm->context, 1);
+	pdtlb(addr);
+	if (unlikely(split_tlb))
+		pitlb(addr);
+}
+
 /* Certain architectures need to do special things when PTEs
  * within a page table are directly modified.  Thus, the following
  * hook is made available.
@@ -42,15 +55,20 @@ extern spinlock_t pa_dbit_lock;
                 *(pteptr) = (pteval);                           \
         } while(0)
 
-extern void purge_tlb_entries(struct mm_struct *, unsigned long);
+#define pte_inserted(x)						\
+	((pte_val(x) & (_PAGE_PRESENT|_PAGE_ACCESSED))		\
+	 == (_PAGE_PRESENT|_PAGE_ACCESSED))
 
-#define set_pte_at(mm, addr, ptep, pteval)                      \
-	do {                                                    \
+#define set_pte_at(mm, addr, ptep, pteval)			\
+	do {							\
+		pte_t old_pte;					\
 		unsigned long flags;				\
-		spin_lock_irqsave(&pa_dbit_lock, flags);	\
-		set_pte(ptep, pteval);                          \
-		purge_tlb_entries(mm, addr);                    \
-		spin_unlock_irqrestore(&pa_dbit_lock, flags);	\
+		spin_lock_irqsave(&pa_tlb_lock, flags);		\
+		old_pte = *ptep;				\
+		set_pte(ptep, pteval);				\
+		if (pte_inserted(old_pte))			\
+			purge_tlb_entries(mm, addr);		\
+		spin_unlock_irqrestore(&pa_tlb_lock, flags);	\
 	} while (0)
 
 #endif /* !__ASSEMBLY__ */
@@ -268,7 +286,7 @@ extern unsigned long *empty_zero_page;
 
 #define pte_none(x)     (pte_val(x) == 0)
 #define pte_present(x)	(pte_val(x) & _PAGE_PRESENT)
-#define pte_clear(mm,addr,xp)	do { pte_val(*(xp)) = 0; } while (0)
+#define pte_clear(mm, addr, xp)  set_pte_at(mm, addr, xp, __pte(0))
 
 #define pmd_flag(x)	(pmd_val(x) & PxD_FLAG_MASK)
 #define pmd_address(x)	((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
@@ -435,15 +453,15 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned
 	if (!pte_young(*ptep))
 		return 0;
 
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	pte = *ptep;
 	if (!pte_young(pte)) {
-		spin_unlock_irqrestore(&pa_dbit_lock, flags);
+		spin_unlock_irqrestore(&pa_tlb_lock, flags);
 		return 0;
 	}
 	set_pte(ptep, pte_mkold(pte));
 	purge_tlb_entries(vma->vm_mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 	return 1;
 }
 
@@ -453,11 +471,12 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 	pte_t old_pte;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	old_pte = *ptep;
-	pte_clear(mm,addr,ptep);
-	purge_tlb_entries(mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	set_pte(ptep, __pte(0));
+	if (pte_inserted(old_pte))
+		purge_tlb_entries(mm, addr);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 
 	return old_pte;
 }
@@ -465,10 +484,10 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	set_pte(ptep, pte_wrprotect(*ptep));
 	purge_tlb_entries(mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 }
 
 #define pte_same(A,B)	(pte_val(A) == pte_val(B))
diff --git a/arch/parisc/include/asm/tlbflush.h b/arch/parisc/include/asm/tlbflush.h
index 9d086a599fa0..e84b96478193 100644
--- a/arch/parisc/include/asm/tlbflush.h
+++ b/arch/parisc/include/asm/tlbflush.h
@@ -13,6 +13,9 @@
  * active at any one time on the Merced bus.  This tlb purge
  * synchronisation is fairly lightweight and harmless so we activate
  * it on all systems not just the N class.
+
+ * It is also used to ensure PTE updates are atomic and consistent
+ * with the TLB.
  */
 extern spinlock_t pa_tlb_lock;
 
@@ -24,20 +27,24 @@ extern void flush_tlb_all_local(void *);
 
 #define smp_flush_tlb_all()	flush_tlb_all()
 
+int __flush_tlb_range(unsigned long sid,
+	unsigned long start, unsigned long end);
+
+#define flush_tlb_range(vma, start, end) \
+	__flush_tlb_range((vma)->vm_mm->context, start, end)
+
+#define flush_tlb_kernel_range(start, end) \
+	__flush_tlb_range(0, start, end)
+
 /*
  * flush_tlb_mm()
  *
- * XXX This code is NOT valid for HP-UX compatibility processes,
- * (although it will probably work 99% of the time). HP-UX
- * processes are free to play with the space id's and save them
- * over long periods of time, etc. so we have to preserve the
- * space and just flush the entire tlb. We need to check the
- * personality in order to do that, but the personality is not
- * currently being set correctly.
- *
- * Of course, Linux processes could do the same thing, but
- * we don't support that (and the compilers, dynamic linker,
- * etc. do not do that).
+ * The code to switch to a new context is NOT valid for processes
+ * which play with the space id's.  Thus, we have to preserve the
+ * space and just flush the entire tlb.  However, the compilers,
+ * dynamic linker, etc, do not manipulate space id's, so there
+ * could be a significant performance benefit in switching contexts
+ * and not flushing the whole tlb.
  */
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
@@ -45,10 +52,18 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	BUG_ON(mm == &init_mm); /* Should never happen */
 
 #if 1 || defined(CONFIG_SMP)
+	/* Except for very small threads, flushing the whole TLB is
+	 * faster than using __flush_tlb_range.  The pdtlb and pitlb
+	 * instructions are very slow because of the TLB broadcast.
+	 * It might be faster to do local range flushes on all CPUs
+	 * on PA 2.0 systems.
+	 */
 	flush_tlb_all();
 #else
 	/* FIXME: currently broken, causing space id and protection ids
-	 *  to go out of sync, resulting in faults on userspace accesses.
+	 * to go out of sync, resulting in faults on userspace accesses.
+	 * This approach needs further investigation since running many
+	 * small applications (e.g., GCC testsuite) is faster on HP-UX.
 	 */
 	if (mm) {
 		if (mm->context != 0)
@@ -65,22 +80,12 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 {
 	unsigned long flags, sid;
 
-	/* For one page, it's not worth testing the split_tlb variable */
-
-	mb();
 	sid = vma->vm_mm->context;
 	purge_tlb_start(flags);
 	mtsp(sid, 1);
 	pdtlb(addr);
-	pitlb(addr);
+	if (unlikely(split_tlb))
+		pitlb(addr);
 	purge_tlb_end(flags);
 }
-
-void __flush_tlb_range(unsigned long sid,
-	unsigned long start, unsigned long end);
-
-#define flush_tlb_range(vma,start,end) __flush_tlb_range((vma)->vm_mm->context,start,end)
-
-#define flush_tlb_kernel_range(start, end) __flush_tlb_range(0,start,end)
-
 #endif
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index f6448c7c62b5..cda6dbbe9842 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -342,12 +342,15 @@ EXPORT_SYMBOL(flush_data_cache_local);
 EXPORT_SYMBOL(flush_kernel_icache_range_asm);
 
 #define FLUSH_THRESHOLD 0x80000 /* 0.5MB */
-int parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
+static unsigned long parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
+
+#define FLUSH_TLB_THRESHOLD (2*1024*1024) /* 2MB initial TLB threshold */
+static unsigned long parisc_tlb_flush_threshold __read_mostly = FLUSH_TLB_THRESHOLD;
 
 void __init parisc_setup_cache_timing(void)
 {
 	unsigned long rangetime, alltime;
-	unsigned long size;
+	unsigned long size, start;
 
 	alltime = mfctl(16);
 	flush_data_cache();
@@ -364,14 +367,43 @@ void __init parisc_setup_cache_timing(void)
 	/* Racy, but if we see an intermediate value, it's ok too... */
 	parisc_cache_flush_threshold = size * alltime / rangetime;
 
-	parisc_cache_flush_threshold = (parisc_cache_flush_threshold + L1_CACHE_BYTES - 1) &~ (L1_CACHE_BYTES - 1); 
+	parisc_cache_flush_threshold = L1_CACHE_ALIGN(parisc_cache_flush_threshold);
 	if (!parisc_cache_flush_threshold)
 		parisc_cache_flush_threshold = FLUSH_THRESHOLD;
 
 	if (parisc_cache_flush_threshold > cache_info.dc_size)
 		parisc_cache_flush_threshold = cache_info.dc_size;
 
-	printk(KERN_INFO "Setting cache flush threshold to %x (%d CPUs online)\n", parisc_cache_flush_threshold, num_online_cpus());
+	printk(KERN_INFO "Setting cache flush threshold to %lu kB\n",
+		parisc_cache_flush_threshold/1024);
+
+	/* calculate TLB flush threshold */
+
+	alltime = mfctl(16);
+	flush_tlb_all();
+	alltime = mfctl(16) - alltime;
+
+	size = PAGE_SIZE;
+	start = (unsigned long) _text;
+	rangetime = mfctl(16);
+	while (start < (unsigned long) _end) {
+		flush_tlb_kernel_range(start, start + PAGE_SIZE);
+		start += PAGE_SIZE;
+		size += PAGE_SIZE;
+	}
+	rangetime = mfctl(16) - rangetime;
+
+	printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n",
+		alltime, size, rangetime);
+
+	parisc_tlb_flush_threshold = size * alltime / rangetime;
+	parisc_tlb_flush_threshold *= num_online_cpus();
+	parisc_tlb_flush_threshold = PAGE_ALIGN(parisc_tlb_flush_threshold);
+	if (!parisc_tlb_flush_threshold)
+		parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD;
+
+	printk(KERN_INFO "Setting TLB flush threshold to %lu kB\n",
+		parisc_tlb_flush_threshold/1024);
 }
 
 extern void purge_kernel_dcache_page_asm(unsigned long);
@@ -403,48 +435,45 @@ void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
 }
 EXPORT_SYMBOL(copy_user_page);
 
-void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
-{
-	unsigned long flags;
-
-	/* Note: purge_tlb_entries can be called at startup with
-	   no context.  */
-
-	purge_tlb_start(flags);
-	mtsp(mm->context, 1);
-	pdtlb(addr);
-	pitlb(addr);
-	purge_tlb_end(flags);
-}
-EXPORT_SYMBOL(purge_tlb_entries);
-
-void __flush_tlb_range(unsigned long sid, unsigned long start,
-		       unsigned long end)
+/* __flush_tlb_range()
+ *
+ * returns 1 if all TLBs were flushed.
+ */
+int __flush_tlb_range(unsigned long sid, unsigned long start,
+		      unsigned long end)
 {
-	unsigned long npages;
+	unsigned long flags, size;
 
-	npages = ((end - (start & PAGE_MASK)) + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
-	if (npages >= 512)  /* 2MB of space: arbitrary, should be tuned */
+	size = (end - start);
+	if (size >= parisc_tlb_flush_threshold) {
 		flush_tlb_all();
-	else {
-		unsigned long flags;
+		return 1;
+	}
 
+	/* Purge TLB entries for small ranges using the pdtlb and
+	   pitlb instructions.  These instructions execute locally
+	   but cause a purge request to be broadcast to other TLBs.  */
+	if (likely(!split_tlb)) {
+		while (start < end) {
+			purge_tlb_start(flags);
+			mtsp(sid, 1);
+			pdtlb(start);
+			purge_tlb_end(flags);
+			start += PAGE_SIZE;
+		}
+		return 0;
+	}
+
+	/* split TLB case */
+	while (start < end) {
 		purge_tlb_start(flags);
 		mtsp(sid, 1);
-		if (split_tlb) {
-			while (npages--) {
-				pdtlb(start);
-				pitlb(start);
-				start += PAGE_SIZE;
-			}
-		} else {
-			while (npages--) {
-				pdtlb(start);
-				start += PAGE_SIZE;
-			}
-		}
+		pdtlb(start);
+		pitlb(start);
 		purge_tlb_end(flags);
+		start += PAGE_SIZE;
 	}
+	return 0;
 }
 
 static void cacheflush_h_tmp_function(void *dummy)
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 75819617f93b..c5ef4081b01d 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -45,7 +45,7 @@
 	.level 2.0
 #endif
 
-	.import         pa_dbit_lock,data
+	.import		pa_tlb_lock,data
 
 	/* space_to_prot macro creates a prot id from a space id */
 
@@ -420,8 +420,8 @@
 	SHLREG		%r9,PxD_VALUE_SHIFT,\pmd
 	extru		\va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index
 	dep		%r0,31,PAGE_SHIFT,\pmd  /* clear offset */
-	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd
-	LDREG		%r0(\pmd),\pte		/* pmd is now pte */
+	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */
+	LDREG		%r0(\pmd),\pte
 	bb,>=,n		\pte,_PAGE_PRESENT_BIT,\fault
 	.endm
 
@@ -453,57 +453,53 @@
 	L2_ptep		\pgd,\pte,\index,\va,\fault
 	.endm
 
-	/* Acquire pa_dbit_lock lock. */
-	.macro		dbit_lock	spc,tmp,tmp1
+	/* Acquire pa_tlb_lock lock and recheck page is still present. */
+	.macro		tlb_lock	spc,ptp,pte,tmp,tmp1,fault
 #ifdef CONFIG_SMP
 	cmpib,COND(=),n	0,\spc,2f
-	load32		PA(pa_dbit_lock),\tmp
+	load32		PA(pa_tlb_lock),\tmp
 1:	LDCW		0(\tmp),\tmp1
 	cmpib,COND(=)	0,\tmp1,1b
 	nop
+	LDREG		0(\ptp),\pte
+	bb,<,n		\pte,_PAGE_PRESENT_BIT,2f
+	b		\fault
+	stw		 \spc,0(\tmp)
 2:
 #endif
 	.endm
 
-	/* Release pa_dbit_lock lock without reloading lock address. */
-	.macro		dbit_unlock0	spc,tmp
+	/* Release pa_tlb_lock lock without reloading lock address. */
+	.macro		tlb_unlock0	spc,tmp
 #ifdef CONFIG_SMP
 	or,COND(=)	%r0,\spc,%r0
 	stw             \spc,0(\tmp)
 #endif
 	.endm
 
-	/* Release pa_dbit_lock lock. */
-	.macro		dbit_unlock1	spc,tmp
+	/* Release pa_tlb_lock lock. */
+	.macro		tlb_unlock1	spc,tmp
 #ifdef CONFIG_SMP
-	load32		PA(pa_dbit_lock),\tmp
-	dbit_unlock0	\spc,\tmp
+	load32		PA(pa_tlb_lock),\tmp
+	tlb_unlock0	\spc,\tmp
 #endif
 	.endm
 
 	/* Set the _PAGE_ACCESSED bit of the PTE.  Be clever and
 	 * don't needlessly dirty the cache line if it was already set */
-	.macro		update_ptep	spc,ptep,pte,tmp,tmp1
-#ifdef CONFIG_SMP
-	or,COND(=)	%r0,\spc,%r0
-	LDREG		0(\ptep),\pte
-#endif
+	.macro		update_accessed	ptp,pte,tmp,tmp1
 	ldi		_PAGE_ACCESSED,\tmp1
 	or		\tmp1,\pte,\tmp
 	and,COND(<>)	\tmp1,\pte,%r0
-	STREG		\tmp,0(\ptep)
+	STREG		\tmp,0(\ptp)
 	.endm
 
 	/* Set the dirty bit (and accessed bit).  No need to be
 	 * clever, this is only used from the dirty fault */
-	.macro		update_dirty	spc,ptep,pte,tmp
-#ifdef CONFIG_SMP
-	or,COND(=)	%r0,\spc,%r0
-	LDREG		0(\ptep),\pte
-#endif
+	.macro		update_dirty	ptp,pte,tmp
 	ldi		_PAGE_ACCESSED|_PAGE_DIRTY,\tmp
 	or		\tmp,\pte,\pte
-	STREG		\pte,0(\ptep)
+	STREG		\pte,0(\ptp)
 	.endm
 
 	/* bitshift difference between a PFN (based on kernel's PAGE_SIZE)
@@ -1148,14 +1144,14 @@ dtlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,dtlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1174,14 +1170,14 @@ nadtlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,nadtlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1202,20 +1198,20 @@ dtlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	idtlba		pte,(%sr1,va)
 	idtlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1235,21 +1231,20 @@ nadtlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	idtlba		pte,(%sr1,va)
 	idtlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1269,16 +1264,16 @@ dtlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1297,16 +1292,16 @@ nadtlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 	
-        idtlbt          pte,prot
-	dbit_unlock1	spc,t0
+	idtlbt		pte,prot
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1406,14 +1401,14 @@ itlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1430,14 +1425,14 @@ naitlb_miss_20w:
 
 	L3_ptep		ptp,pte,t0,va,naitlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1458,20 +1453,20 @@ itlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	iitlba		pte,(%sr1,va)
 	iitlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1482,20 +1477,20 @@ naitlb_miss_11:
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	iitlba		pte,(%sr1,va)
 	iitlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1516,16 +1511,16 @@ itlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0	
+	f_extend	pte,t1
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1536,16 +1531,16 @@ naitlb_miss_20:
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1568,14 +1563,14 @@ dbit_trap_20w:
 
 	L3_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 		
 	idtlbt          pte,prot
-	dbit_unlock0	spc,t0
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 #else
@@ -1588,8 +1583,8 @@ dbit_trap_11:
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1600,8 +1595,8 @@ dbit_trap_11:
 	idtlbp		prot,(%sr1,va)
 
 	mtsp            t1, %sr1     /* Restore sr1 */
-	dbit_unlock0	spc,t0
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 
@@ -1612,16 +1607,16 @@ dbit_trap_20:
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t1
 	
-        idtlbt          pte,prot
-	dbit_unlock0	spc,t0
+	idtlbt		pte,prot
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 #endif
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index ff834fd67478..b9402c9b3454 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -478,14 +478,16 @@ static void pa11_dma_unmap_single(struct device *dev, dma_addr_t dma_handle, siz
 static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	BUG_ON(direction == DMA_NONE);
 
-	for (i = 0; i < nents; i++, sglist++ ) {
-		unsigned long vaddr = (unsigned long)sg_virt(sglist);
-		sg_dma_address(sglist) = (dma_addr_t) virt_to_phys(vaddr);
-		sg_dma_len(sglist) = sglist->length;
-		flush_kernel_dcache_range(vaddr, sglist->length);
+	for_each_sg(sglist, sg, nents, i) {
+		unsigned long vaddr = (unsigned long)sg_virt(sg);
+
+		sg_dma_address(sg) = (dma_addr_t) virt_to_phys(vaddr);
+		sg_dma_len(sg) = sg->length;
+		flush_kernel_dcache_range(vaddr, sg->length);
 	}
 	return nents;
 }
@@ -493,6 +495,7 @@ static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, int n
 static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	BUG_ON(direction == DMA_NONE);
 
@@ -501,8 +504,8 @@ static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, in
 
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
-	for (i = 0; i < nents; i++, sglist++ )
-		flush_kernel_vmap_range(sg_virt(sglist), sglist->length);
+	for_each_sg(sglist, sg, nents, i)
+		flush_kernel_vmap_range(sg_virt(sg), sg->length);
 	return;
 }
 
@@ -523,21 +526,23 @@ static void pa11_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_h
 static void pa11_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
-	for (i = 0; i < nents; i++, sglist++ )
-		flush_kernel_vmap_range(sg_virt(sglist), sglist->length);
+	for_each_sg(sglist, sg, nents, i)
+		flush_kernel_vmap_range(sg_virt(sg), sg->length);
 }
 
 static void pa11_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
-	for (i = 0; i < nents; i++, sglist++ )
-		flush_kernel_vmap_range(sg_virt(sglist), sglist->length);
+	for_each_sg(sglist, sg, nents, i)
+		flush_kernel_vmap_range(sg_virt(sg), sg->length);
 }
 
 struct hppa_dma_ops pcxl_dma_ops = {
diff --git a/arch/parisc/kernel/pdc_cons.c b/arch/parisc/kernel/pdc_cons.c
index d5cae55195ec..10a5ae9553fd 100644
--- a/arch/parisc/kernel/pdc_cons.c
+++ b/arch/parisc/kernel/pdc_cons.c
@@ -207,8 +207,7 @@ static int __init pdc_console_tty_driver_init(void)
 
 	return 0;
 }
-
-module_init(pdc_console_tty_driver_init);
+device_initcall(pdc_console_tty_driver_init);
 
 static struct tty_driver * pdc_console_device (struct console *c, int *index)
 {
diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c
index ba0c053e25ae..518f4f5f1f43 100644
--- a/arch/parisc/kernel/perf.c
+++ b/arch/parisc/kernel/perf.c
@@ -543,6 +543,7 @@ static int __init perf_init(void)
 
 	return 0;
 }
+device_initcall(perf_init);
 
 /*
  * perf_start_counters(void)
@@ -847,5 +848,3 @@ printk("perf_rdr_write\n");
 	}
 printk("perf_rdr_write done\n");
 }
-
-module_init(perf_init);
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 47ee620d15d2..b99b39f1da02 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -26,9 +26,9 @@
 #include <linux/console.h>
 #include <linux/bug.h>
 #include <linux/ratelimit.h>
+#include <linux/uaccess.h>
 
 #include <asm/assembly.h>
-#include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/traps.h>
@@ -43,10 +43,6 @@
 
 #include "../math-emu/math-emu.h"	/* for handle_fpe() */
 
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
-DEFINE_SPINLOCK(pa_dbit_lock);
-#endif
-
 static void parisc_show_stack(struct task_struct *task, unsigned long *sp,
 	struct pt_regs *regs);
 
@@ -800,7 +796,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 	     * unless pagefault_disable() was called before.
 	     */
 
-	    if (fault_space == 0 && !in_atomic())
+	    if (fault_space == 0 && !faulthandler_disabled())
 	    {
 		pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
 		parisc_terminate("Kernel Fault", regs, code, fault_address);
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index e5120e653240..15503adddf4f 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -15,8 +15,8 @@
 #include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/traps.h>
 
 /* Various important other fields */
@@ -207,7 +207,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 	int fault;
 	unsigned int flags;
 
-	if (in_atomic())
+	if (pagefault_disabled())
 		goto no_context;
 
 	tsk = current;