Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-next

Pull sparc updates from David Miller:

 - Rework the sparc32 page tables so that READ_ONCE(*pmd), as done by
   generic code, operates on a word sized element. From Will Deacon.

 - Some scnprintf() conversions, from Chen Zhou.

 - A pin_user_pages() conversion from John Hubbard.

 - Several 32-bit ptrace register handling fixes and such from Al Viro.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-next:
  fix a braino in "sparc32: fix register window handling in genregs32_[gs]et()"
  sparc32: mm: Only call ctor()/dtor() functions for first and last user
  sparc32: mm: Disable SPLIT_PTLOCK_CPUS
  sparc32: mm: Don't try to free page-table pages if ctor() fails
  sparc32: register memory occupied by kernel as memblock.memory
  sparc: remove unused header file nfs_fs.h
  sparc32: fix register window handling in genregs32_[gs]et()
  sparc64: fix misuses of access_process_vm() in genregs32_[sg]et()
  oradax: convert get_user_pages() --> pin_user_pages()
  sparc: use scnprintf() in show_pciobppath_attr() in vio.c
  sparc: use scnprintf() in show_pciobppath_attr() in pci.c
  tty: vcc: Fix error return code in vcc_probe()
  sparc32: mm: Reduce allocation size for PMD and PTE tables
  sparc32: mm: Change pgtable_t type to pte_t * instead of struct page *
  sparc32: mm: Restructure sparc32 MMU page-table layout
  sparc32: mm: Fix argument checking in __srmmu_get_nocache()
  sparc64: Replace zero-length array with flexible-array
  sparc: mm: return true,false in kern_addr_valid()

19 files changed, 219 insertions, 294 deletions

diff --git a/arch/sparc/include/asm/page_32.h b/arch/sparc/include/asm/page_32.h
index 478260002836..fff8861df107 100644
--- a/arch/sparc/include/asm/page_32.h
+++ b/arch/sparc/include/asm/page_32.h
@@ -54,7 +54,7 @@ extern struct sparc_phys_banks sp_banks[SPARC_PHYS_BANKS+1];
  */
 typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long iopte; } iopte_t;
-typedef struct { unsigned long pmdv[16]; } pmd_t;
+typedef struct { unsigned long pmd; } pmd_t;
 typedef struct { unsigned long pgd; } pgd_t;
 typedef struct { unsigned long ctxd; } ctxd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
@@ -62,7 +62,7 @@ typedef struct { unsigned long iopgprot; } iopgprot_t;
 
 #define pte_val(x)	((x).pte)
 #define iopte_val(x)	((x).iopte)
-#define pmd_val(x)      ((x).pmdv[0])
+#define pmd_val(x)      ((x).pmd)
 #define pgd_val(x)	((x).pgd)
 #define ctxd_val(x)	((x).ctxd)
 #define pgprot_val(x)	((x).pgprot)
@@ -82,7 +82,7 @@ typedef struct { unsigned long iopgprot; } iopgprot_t;
  */
 typedef unsigned long pte_t;
 typedef unsigned long iopte_t;
-typedef struct { unsigned long pmdv[16]; } pmd_t;
+typedef unsigned long pmd_t;
 typedef unsigned long pgd_t;
 typedef unsigned long ctxd_t;
 typedef unsigned long pgprot_t;
@@ -90,14 +90,14 @@ typedef unsigned long iopgprot_t;
 
 #define pte_val(x)	(x)
 #define iopte_val(x)	(x)
-#define pmd_val(x)      ((x).pmdv[0])
+#define pmd_val(x)      (x)
 #define pgd_val(x)	(x)
 #define ctxd_val(x)	(x)
 #define pgprot_val(x)	(x)
 #define iopgprot_val(x)	(x)
 
 #define __pte(x)	(x)
-#define __pmd(x)	((pmd_t) { { (x) }, })
+#define __pmd(x)	(x)
 #define __iopte(x)	(x)
 #define __pgd(x)	(x)
 #define __ctxd(x)	(x)
@@ -106,7 +106,7 @@ typedef unsigned long iopgprot_t;
 
 #endif
 
-typedef struct page *pgtable_t;
+typedef pte_t *pgtable_t;
 
 #define TASK_UNMAPPED_BASE	0x50000000
 
diff --git a/arch/sparc/include/asm/pgalloc_32.h b/arch/sparc/include/asm/pgalloc_32.h
index eae0c92ec422..b772384871e9 100644
--- a/arch/sparc/include/asm/pgalloc_32.h
+++ b/arch/sparc/include/asm/pgalloc_32.h
@@ -50,23 +50,24 @@ static inline void free_pmd_fast(pmd_t * pmd)
 #define pmd_free(mm, pmd)		free_pmd_fast(pmd)
 #define __pmd_free_tlb(tlb, pmd, addr)	pmd_free((tlb)->mm, pmd)
 
-void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, struct page *ptep);
-#define pmd_pgtable(pmd) pmd_page(pmd)
+#define pmd_populate(mm, pmd, pte)	pmd_set(pmd, pte)
+#define pmd_pgtable(pmd)		(pgtable_t)__pmd_page(pmd)
 
 void pmd_set(pmd_t *pmdp, pte_t *ptep);
-#define pmd_populate_kernel(MM, PMD, PTE) pmd_set(PMD, PTE)
+#define pmd_populate_kernel		pmd_populate
 
 pgtable_t pte_alloc_one(struct mm_struct *mm);
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 {
-	return srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
+	return srmmu_get_nocache(SRMMU_PTE_TABLE_SIZE,
+				 SRMMU_PTE_TABLE_SIZE);
 }
 
 
 static inline void free_pte_fast(pte_t *pte)
 {
-	srmmu_free_nocache(pte, PTE_SIZE);
+	srmmu_free_nocache(pte, SRMMU_PTE_TABLE_SIZE);
 }
 
 #define pte_free_kernel(mm, pte)	free_pte_fast(pte)
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 0de659ae0ba4..c5625b2aa331 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -11,6 +11,16 @@
 
 #include <linux/const.h>
 
+#define PMD_SHIFT		18
+#define PMD_SIZE        	(1UL << PMD_SHIFT)
+#define PMD_MASK        	(~(PMD_SIZE-1))
+#define PMD_ALIGN(__addr) 	(((__addr) + ~PMD_MASK) & PMD_MASK)
+
+#define PGDIR_SHIFT     	24
+#define PGDIR_SIZE      	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK      	(~(PGDIR_SIZE-1))
+#define PGDIR_ALIGN(__addr) 	(((__addr) + ~PGDIR_MASK) & PGDIR_MASK)
+
 #ifndef __ASSEMBLY__
 #include <asm-generic/pgtable-nopud.h>
 
@@ -34,17 +44,10 @@ unsigned long __init bootmem_init(unsigned long *pages_avail);
 #define pmd_ERROR(e)   __builtin_trap()
 #define pgd_ERROR(e)   __builtin_trap()
 
-#define PMD_SHIFT		22
-#define PMD_SIZE        	(1UL << PMD_SHIFT)
-#define PMD_MASK        	(~(PMD_SIZE-1))
-#define PMD_ALIGN(__addr) 	(((__addr) + ~PMD_MASK) & PMD_MASK)
-#define PGDIR_SHIFT     	SRMMU_PGDIR_SHIFT
-#define PGDIR_SIZE      	SRMMU_PGDIR_SIZE
-#define PGDIR_MASK      	SRMMU_PGDIR_MASK
-#define PTRS_PER_PTE    	1024
-#define PTRS_PER_PMD    	SRMMU_PTRS_PER_PMD
-#define PTRS_PER_PGD    	SRMMU_PTRS_PER_PGD
-#define USER_PTRS_PER_PGD	PAGE_OFFSET / SRMMU_PGDIR_SIZE
+#define PTRS_PER_PTE    	64
+#define PTRS_PER_PMD    	64
+#define PTRS_PER_PGD    	256
+#define USER_PTRS_PER_PGD	PAGE_OFFSET / PGDIR_SIZE
 #define FIRST_USER_ADDRESS	0UL
 #define PTE_SIZE		(PTRS_PER_PTE*4)
 
@@ -132,6 +135,17 @@ static inline struct page *pmd_page(pmd_t pmd)
 	return pfn_to_page((pmd_val(pmd) & SRMMU_PTD_PMASK) >> (PAGE_SHIFT-4));
 }
 
+static inline unsigned long __pmd_page(pmd_t pmd)
+{
+	unsigned long v;
+
+	if (srmmu_device_memory(pmd_val(pmd)))
+		BUG();
+
+	v = pmd_val(pmd) & SRMMU_PTD_PMASK;
+	return (unsigned long)__nocache_va(v << 4);
+}
+
 static inline unsigned long pud_page_vaddr(pud_t pud)
 {
 	if (srmmu_device_memory(pud_val(pud))) {
@@ -179,9 +193,7 @@ static inline int pmd_none(pmd_t pmd)
 
 static inline void pmd_clear(pmd_t *pmdp)
 {
-	int i;
-	for (i = 0; i < PTRS_PER_PTE/SRMMU_REAL_PTRS_PER_PTE; i++)
-		set_pte((pte_t *)&pmdp->pmdv[i], __pte(0));
+	set_pte((pte_t *)&pmd_val(*pmdp), __pte(0));
 }
 
 static inline int pud_none(pud_t pud)
diff --git a/arch/sparc/include/asm/pgtsrmmu.h b/arch/sparc/include/asm/pgtsrmmu.h
index 32a508897501..7708d015712b 100644
--- a/arch/sparc/include/asm/pgtsrmmu.h
+++ b/arch/sparc/include/asm/pgtsrmmu.h
@@ -17,39 +17,9 @@
 /* Number of contexts is implementation-dependent; 64k is the most we support */
 #define SRMMU_MAX_CONTEXTS	65536
 
-/* PMD_SHIFT determines the size of the area a second-level page table entry can map */
-#define SRMMU_REAL_PMD_SHIFT		18
-#define SRMMU_REAL_PMD_SIZE		(1UL << SRMMU_REAL_PMD_SHIFT)
-#define SRMMU_REAL_PMD_MASK		(~(SRMMU_REAL_PMD_SIZE-1))
-#define SRMMU_REAL_PMD_ALIGN(__addr)	(((__addr)+SRMMU_REAL_PMD_SIZE-1)&SRMMU_REAL_PMD_MASK)
-
-/* PGDIR_SHIFT determines what a third-level page table entry can map */
-#define SRMMU_PGDIR_SHIFT       24
-#define SRMMU_PGDIR_SIZE        (1UL << SRMMU_PGDIR_SHIFT)
-#define SRMMU_PGDIR_MASK        (~(SRMMU_PGDIR_SIZE-1))
-#define SRMMU_PGDIR_ALIGN(addr) (((addr)+SRMMU_PGDIR_SIZE-1)&SRMMU_PGDIR_MASK)
-
-#define SRMMU_REAL_PTRS_PER_PTE	64
-#define SRMMU_REAL_PTRS_PER_PMD	64
-#define SRMMU_PTRS_PER_PGD	256
-
-#define SRMMU_REAL_PTE_TABLE_SIZE	(SRMMU_REAL_PTRS_PER_PTE*4)
-#define SRMMU_PMD_TABLE_SIZE		(SRMMU_REAL_PTRS_PER_PMD*4)
-#define SRMMU_PGD_TABLE_SIZE		(SRMMU_PTRS_PER_PGD*4)
-
-/*
- * To support pagetables in highmem, Linux introduces APIs which
- * return struct page* and generally manipulate page tables when
- * they are not mapped into kernel space. Our hardware page tables
- * are smaller than pages. We lump hardware tabes into big, page sized
- * software tables.
- *
- * PMD_SHIFT determines the size of the area a second-level page table entry
- * can map, and our pmd_t is 16 times larger than normal.  The values which
- * were once defined here are now generic for 4c and srmmu, so they're
- * found in pgtable.h.
- */
-#define SRMMU_PTRS_PER_PMD	4
+#define SRMMU_PTE_TABLE_SIZE		(PTRS_PER_PTE*4)
+#define SRMMU_PMD_TABLE_SIZE		(PTRS_PER_PMD*4)
+#define SRMMU_PGD_TABLE_SIZE		(PTRS_PER_PGD*4)
 
 /* Definition of the values in the ET field of PTD's and PTE's */
 #define SRMMU_ET_MASK         0x3
diff --git a/arch/sparc/include/asm/viking.h b/arch/sparc/include/asm/viking.h
index 0bbefd184221..08ffc605035f 100644
--- a/arch/sparc/include/asm/viking.h
+++ b/arch/sparc/include/asm/viking.h
@@ -10,6 +10,7 @@
 
 #include <asm/asi.h>
 #include <asm/mxcc.h>
+#include <asm/pgtable.h>
 #include <asm/pgtsrmmu.h>
 
 /* Bits in the SRMMU control register for GNU/Viking modules.
@@ -227,7 +228,7 @@ static inline unsigned long viking_hwprobe(unsigned long vaddr)
 			     : "=r" (val)
 			     : "r" (vaddr | 0x200), "i" (ASI_M_FLUSH_PROBE));
 	if ((val & SRMMU_ET_MASK) == SRMMU_ET_PTE) {
-		vaddr &= ~SRMMU_PGDIR_MASK;
+		vaddr &= ~PGDIR_MASK;
 		vaddr >>= PAGE_SHIFT;
 		return val | (vaddr << 8);
 	}
@@ -237,7 +238,7 @@ static inline unsigned long viking_hwprobe(unsigned long vaddr)
 			     : "=r" (val)
 			     : "r" (vaddr | 0x100), "i" (ASI_M_FLUSH_PROBE));
 	if ((val & SRMMU_ET_MASK) == SRMMU_ET_PTE) {
-		vaddr &= ~SRMMU_REAL_PMD_MASK;
+		vaddr &= ~PMD_MASK;
 		vaddr >>= PAGE_SHIFT;
 		return val | (vaddr << 8);
 	}
diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c
index 1cb62bfeaa1f..f07ea88a83af 100644
--- a/arch/sparc/kernel/cpumap.c
+++ b/arch/sparc/kernel/cpumap.c
@@ -50,7 +50,7 @@ struct cpuinfo_tree {
 
 	/* Offsets into nodes[] for each level of the tree */
 	struct cpuinfo_level level[CPUINFO_LVL_MAX];
-	struct cpuinfo_node  nodes[0];
+	struct cpuinfo_node  nodes[];
 };
 
 
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 75232cbd58bf..522e5b51050c 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -87,7 +87,7 @@ struct ds_reg_req {
 	__u64			handle;
 	__u16			major;
 	__u16			minor;
-	char			svc_id[0];
+	char			svc_id[];
 };
 
 struct ds_reg_ack {
@@ -701,12 +701,12 @@ struct ds_var_hdr {
 
 struct ds_var_set_msg {
 	struct ds_var_hdr		hdr;
-	char				name_and_value[0];
+	char				name_and_value[];
 };
 
 struct ds_var_delete_msg {
 	struct ds_var_hdr		hdr;
-	char				name[0];
+	char				name[];
 };
 
 struct ds_var_resp {
@@ -989,7 +989,7 @@ struct ds_queue_entry {
 	struct ds_info			*dp;
 	int				req_len;
 	int				__pad;
-	u64				req[0];
+	u64				req[];
 };
 
 static void process_ds_work(void)
diff --git a/arch/sparc/kernel/head_32.S b/arch/sparc/kernel/head_32.S
index e55f2c075165..be30c8d4cc73 100644
--- a/arch/sparc/kernel/head_32.S
+++ b/arch/sparc/kernel/head_32.S
@@ -24,7 +24,7 @@
 #include <asm/winmacro.h>
 #include <asm/thread_info.h>	/* TI_UWINMASK */
 #include <asm/errno.h>
-#include <asm/pgtsrmmu.h>	/* SRMMU_PGDIR_SHIFT */
+#include <asm/pgtable.h>	/* PGDIR_SHIFT */
 #include <asm/export.h>
 
 	.data
@@ -273,7 +273,7 @@ not_a_sun4:
 		lda	[%o1] ASI_M_BYPASS, %o2		! This is the 0x0 16MB pgd
 
 		/* Calculate to KERNBASE entry. */
-		add	%o1, KERNBASE >> (SRMMU_PGDIR_SHIFT - 2), %o3
+		add	%o1, KERNBASE >> (PGDIR_SHIFT - 2), %o3
 
 		/* Poke the entry into the calculated address. */
 		sta	%o2, [%o3] ASI_M_BYPASS
@@ -317,7 +317,7 @@ srmmu_not_viking:
 		sll	%g1, 0x8, %g1			! make phys addr for l1 tbl
 
 		lda	[%g1] ASI_M_BYPASS, %g2		! get level1 entry for 0x0
-		add	%g1, KERNBASE >> (SRMMU_PGDIR_SHIFT - 2), %g3
+		add	%g1, KERNBASE >> (PGDIR_SHIFT - 2), %g3
 		sta	%g2, [%g3] ASI_M_BYPASS		! place at KERNBASE entry
 		b	go_to_highmem
 		 nop					! wheee....
@@ -341,7 +341,7 @@ leon_remap:
 		sll	%g1, 0x8, %g1			! make phys addr for l1 tbl
 
 		lda	[%g1] ASI_M_BYPASS, %g2		! get level1 entry for 0x0
-		add	%g1, KERNBASE >> (SRMMU_PGDIR_SHIFT - 2), %g3
+		add	%g1, KERNBASE >> (PGDIR_SHIFT - 2), %g3
 		sta	%g2, [%g3] ASI_M_BYPASS		! place at KERNBASE entry
 		b	go_to_highmem
 		 nop					! wheee....
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 5ed43828e078..a41ad562ed4e 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -593,7 +593,7 @@ show_pciobppath_attr(struct device * dev, struct device_attribute * attr, char *
 	pdev = to_pci_dev(dev);
 	dp = pdev->dev.of_node;
 
-	return snprintf (buf, PAGE_SIZE, "%pOF\n", dp);
+	return scnprintf(buf, PAGE_SIZE, "%pOF\n", dp);
 }
 
 static DEVICE_ATTR(obppath, S_IRUSR | S_IRGRP | S_IROTH, show_pciobppath_attr, NULL);
diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c
index 16b50afe7b52..646dd58169ec 100644
--- a/arch/sparc/kernel/ptrace_32.c
+++ b/arch/sparc/kernel/ptrace_32.c
@@ -46,82 +46,79 @@ enum sparc_regset {
 	REGSET_FP,
 };
 
+static int regwindow32_get(struct task_struct *target,
+			   const struct pt_regs *regs,
+			   u32 *uregs)
+{
+	unsigned long reg_window = regs->u_regs[UREG_I6];
+	int size = 16 * sizeof(u32);
+
+	if (target == current) {
+		if (copy_from_user(uregs, (void __user *)reg_window, size))
+			return -EFAULT;
+	} else {
+		if (access_process_vm(target, reg_window, uregs, size,
+				      FOLL_FORCE) != size)
+			return -EFAULT;
+	}
+	return 0;
+}
+
+static int regwindow32_set(struct task_struct *target,
+			   const struct pt_regs *regs,
+			   u32 *uregs)
+{
+	unsigned long reg_window = regs->u_regs[UREG_I6];
+	int size = 16 * sizeof(u32);
+
+	if (target == current) {
+		if (copy_to_user((void __user *)reg_window, uregs, size))
+			return -EFAULT;
+	} else {
+		if (access_process_vm(target, reg_window, uregs, size,
+				      FOLL_FORCE | FOLL_WRITE) != size)
+			return -EFAULT;
+	}
+	return 0;
+}
+
 static int genregs32_get(struct task_struct *target,
 			 const struct user_regset *regset,
 			 unsigned int pos, unsigned int count,
 			 void *kbuf, void __user *ubuf)
 {
 	const struct pt_regs *regs = target->thread.kregs;
-	unsigned long __user *reg_window;
-	unsigned long *k = kbuf;
-	unsigned long __user *u = ubuf;
-	unsigned long reg;
+	u32 uregs[16];
+	int ret;
 
 	if (target == current)
 		flush_user_windows();
 
-	pos /= sizeof(reg);
-	count /= sizeof(reg);
-
-	if (kbuf) {
-		for (; count > 0 && pos < 16; count--)
-			*k++ = regs->u_regs[pos++];
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (get_user(*k++, &reg_window[pos++]))
-				return -EFAULT;
-		}
-	} else {
-		for (; count > 0 && pos < 16; count--) {
-			if (put_user(regs->u_regs[pos++], u++))
-				return -EFAULT;
-		}
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (get_user(reg, &reg_window[pos++]) ||
-			    put_user(reg, u++))
-				return -EFAULT;
-		}
-	}
-	while (count > 0) {
-		switch (pos) {
-		case 32: /* PSR */
-			reg = regs->psr;
-			break;
-		case 33: /* PC */
-			reg = regs->pc;
-			break;
-		case 34: /* NPC */
-			reg = regs->npc;
-			break;
-		case 35: /* Y */
-			reg = regs->y;
-			break;
-		case 36: /* WIM */
-		case 37: /* TBR */
-			reg = 0;
-			break;
-		default:
-			goto finish;
-		}
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  regs->u_regs,
+				  0, 16 * sizeof(u32));
+	if (ret || !count)
+		return ret;
 
-		if (kbuf)
-			*k++ = reg;
-		else if (put_user(reg, u++))
+	if (pos < 32 * sizeof(u32)) {
+		if (regwindow32_get(target, regs, uregs))
 			return -EFAULT;
-		pos++;
-		count--;
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+					  uregs,
+					  16 * sizeof(u32), 32 * sizeof(u32));
+		if (ret || !count)
+			return ret;
 	}
-finish:
-	pos *= sizeof(reg);
-	count *= sizeof(reg);
 
-	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
-					38 * sizeof(reg), -1);
+	uregs[0] = regs->psr;
+	uregs[1] = regs->pc;
+	uregs[2] = regs->npc;
+	uregs[3] = regs->y;
+	uregs[4] = 0;	/* WIM */
+	uregs[5] = 0;	/* TBR */
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  uregs,
+				  32 * sizeof(u32), 38 * sizeof(u32));
 }
 
 static int genregs32_set(struct task_struct *target,
@@ -130,82 +127,58 @@ static int genregs32_set(struct task_struct *target,
 			 const void *kbuf, const void __user *ubuf)
 {
 	struct pt_regs *regs = target->thread.kregs;
-	unsigned long __user *reg_window;
-	const unsigned long *k = kbuf;
-	const unsigned long __user *u = ubuf;
-	unsigned long reg;
+	u32 uregs[16];
+	u32 psr;
+	int ret;
 
 	if (target == current)
 		flush_user_windows();
 
-	pos /= sizeof(reg);
-	count /= sizeof(reg);
-
-	if (kbuf) {
-		for (; count > 0 && pos < 16; count--)
-			regs->u_regs[pos++] = *k++;
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (put_user(*k++, &reg_window[pos++]))
-				return -EFAULT;
-		}
-	} else {
-		for (; count > 0 && pos < 16; count--) {
-			if (get_user(reg, u++))
-				return -EFAULT;
-			regs->u_regs[pos++] = reg;
-		}
-
-		reg_window = (unsigned long __user *) regs->u_regs[UREG_I6];
-		reg_window -= 16;
-		for (; count > 0 && pos < 32; count--) {
-			if (get_user(reg, u++) ||
-			    put_user(reg, &reg_window[pos++]))
-				return -EFAULT;
-		}
-	}
-	while (count > 0) {
-		unsigned long psr;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 regs->u_regs,
+				 0, 16 * sizeof(u32));
+	if (ret || !count)
+		return ret;
 
-		if (kbuf)
-			reg = *k++;
-		else if (get_user(reg, u++))
+	if (pos < 32 * sizeof(u32)) {
+		if (regwindow32_get(target, regs, uregs))
 			return -EFAULT;
-
-		switch (pos) {
-		case 32: /* PSR */
-			psr = regs->psr;
-			psr &= ~(PSR_ICC | PSR_SYSCALL);
-			psr |= (reg & (PSR_ICC | PSR_SYSCALL));
-			regs->psr = psr;
-			break;
-		case 33: /* PC */
-			regs->pc = reg;
-			break;
-		case 34: /* NPC */
-			regs->npc = reg;
-			break;
-		case 35: /* Y */
-			regs->y = reg;
-			break;
-		case 36: /* WIM */
-		case 37: /* TBR */
-			break;
-		default:
-			goto finish;
-		}
-
-		pos++;
-		count--;
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 uregs,
+					 16 * sizeof(u32), 32 * sizeof(u32));
+		if (ret)
+			return ret;
+		if (regwindow32_set(target, regs, uregs))
+			return -EFAULT;
+		if (!count)
+			return 0;
 	}
-finish:
-	pos *= sizeof(reg);
-	count *= sizeof(reg);
-
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &psr,
+				 32 * sizeof(u32), 33 * sizeof(u32));
+	if (ret)
+		return ret;
+	regs->psr = (regs->psr & ~(PSR_ICC | PSR_SYSCALL)) |
+		    (psr & (PSR_ICC | PSR_SYSCALL));
+	if (!count)
+		return 0;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->pc,
+				 33 * sizeof(u32), 34 * sizeof(u32));
+	if (ret || !count)
+		return ret;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->npc,
+				 34 * sizeof(u32), 35 * sizeof(u32));
+	if (ret || !count)
+		return ret;
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs->y,
+				 35 * sizeof(u32), 36 * sizeof(u32));
+	if (ret || !count)
+		return ret;
 	return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
-					 38 * sizeof(reg), -1);
+					 36 * sizeof(u32), 38 * sizeof(u32));
 }
 
 static int fpregs32_get(struct task_struct *target,
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index c9d41a96468f..3f5930bfab06 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -572,19 +572,13 @@ static int genregs32_get(struct task_struct *target,
 			for (; count > 0 && pos < 32; count--) {
 				if (access_process_vm(target,
 						      (unsigned long)
-						      &reg_window[pos],
+						      &reg_window[pos++],
 						      &reg, sizeof(reg),
 						      FOLL_FORCE)
 				    != sizeof(reg))
 					return -EFAULT;
-				if (access_process_vm(target,
-						      (unsigned long) u,
-						      &reg, sizeof(reg),
-						      FOLL_FORCE | FOLL_WRITE)
-				    != sizeof(reg))
+				if (put_user(reg, u++))
 					return -EFAULT;
-				pos++;
-				u++;
 			}
 		}
 	}
@@ -684,12 +678,7 @@ static int genregs32_set(struct task_struct *target,
 			}
 		} else {
 			for (; count > 0 && pos < 32; count--) {
-				if (access_process_vm(target,
-						      (unsigned long)
-						      u,
-						      &reg, sizeof(reg),
-						      FOLL_FORCE)
-				    != sizeof(reg))
+				if (get_user(reg, u++))
 					return -EFAULT;
 				if (access_process_vm(target,
 						      (unsigned long)
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index b5da3bfdc225..f84a02ab6bf9 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
@@ -22,7 +22,6 @@
 #include <linux/msg.h>
 #include <linux/shm.h>
 #include <linux/uio.h>
-#include <linux/nfs_fs.h>
 #include <linux/quota.h>
 #include <linux/poll.h>
 #include <linux/personality.h>
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index c7cad9b7bba7..4f57056ed463 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -193,7 +193,7 @@ show_pciobppath_attr(struct device *dev, struct device_attribute *attr,
 	vdev = to_vio_dev(dev);
 	dp = vdev->dp;
 
-	return snprintf (buf, PAGE_SIZE, "%pOF\n", dp);
+	return scnprintf(buf, PAGE_SIZE, "%pOF\n", dp);
 }
 
 static DEVICE_ATTR(obppath, S_IRUSR | S_IRGRP | S_IROTH,
diff --git a/arch/sparc/mm/hypersparc.S b/arch/sparc/mm/hypersparc.S
index 66885a8dc50a..6c2521e85a42 100644
--- a/arch/sparc/mm/hypersparc.S
+++ b/arch/sparc/mm/hypersparc.S
@@ -10,6 +10,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/asi.h>
 #include <asm/page.h>
+#include <asm/pgtable.h>
 #include <asm/pgtsrmmu.h>
 #include <linux/init.h>
 
@@ -293,7 +294,7 @@ hypersparc_flush_tlb_range:
 	cmp	%o3, -1
 	be	hypersparc_flush_tlb_range_out
 #endif
-	 sethi	%hi(~((1 << SRMMU_PGDIR_SHIFT) - 1)), %o4
+	 sethi	%hi(~((1 << PGDIR_SHIFT) - 1)), %o4
 	sta	%o3, [%g1] ASI_M_MMUREGS
 	and	%o1, %o4, %o1
 	add	%o1, 0x200, %o1
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 5774529ceb43..2ef6826a6ca6 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1649,29 +1649,29 @@ bool kern_addr_valid(unsigned long addr)
 
 	pgd = pgd_offset_k(addr);
 	if (pgd_none(*pgd))
-		return 0;
+		return false;
 
 	p4d = p4d_offset(pgd, addr);
 	if (p4d_none(*p4d))
-		return 0;
+		return false;
 
 	pud = pud_offset(p4d, addr);
 	if (pud_none(*pud))
-		return 0;
+		return false;
 
 	if (pud_large(*pud))
 		return pfn_valid(pud_pfn(*pud));
 
 	pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd))
-		return 0;
+		return false;
 
 	if (pmd_large(*pmd))
 		return pfn_valid(pmd_pfn(*pmd));
 
 	pte = pte_offset_kernel(pmd, addr);
 	if (pte_none(*pte))
-		return 0;
+		return false;
 
 	return pfn_valid(pte_pfn(*pte));
 }
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index 7c2278dd308d..989da22ba8e9 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -136,26 +136,8 @@ static void msi_set_sync(void)
 
 void pmd_set(pmd_t *pmdp, pte_t *ptep)
 {
-	unsigned long ptp;	/* Physical address, shifted right by 4 */
-	int i;
-
-	ptp = __nocache_pa(ptep) >> 4;
-	for (i = 0; i < PTRS_PER_PTE/SRMMU_REAL_PTRS_PER_PTE; i++) {
-		set_pte((pte_t *)&pmdp->pmdv[i], __pte(SRMMU_ET_PTD | ptp));
-		ptp += (SRMMU_REAL_PTRS_PER_PTE * sizeof(pte_t) >> 4);
-	}
-}
-
-void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, struct page *ptep)
-{
-	unsigned long ptp;	/* Physical address, shifted right by 4 */
-	int i;
-
-	ptp = page_to_pfn(ptep) << (PAGE_SHIFT-4);	/* watch for overflow */
-	for (i = 0; i < PTRS_PER_PTE/SRMMU_REAL_PTRS_PER_PTE; i++) {
-		set_pte((pte_t *)&pmdp->pmdv[i], __pte(SRMMU_ET_PTD | ptp));
-		ptp += (SRMMU_REAL_PTRS_PER_PTE * sizeof(pte_t) >> 4);
-	}
+	unsigned long ptp = __nocache_pa(ptep) >> 4;
+	set_pte((pte_t *)&pmd_val(*pmdp), __pte(SRMMU_ET_PTD | ptp));
 }
 
 /* Find an entry in the third-level page table.. */
@@ -163,7 +145,7 @@ pte_t *pte_offset_kernel(pmd_t *dir, unsigned long address)
 {
 	void *pte;
 
-	pte = __nocache_va((dir->pmdv[0] & SRMMU_PTD_PMASK) << 4);
+	pte = __nocache_va((pmd_val(*dir) & SRMMU_PTD_PMASK) << 4);
 	return (pte_t *) pte +
 	    ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1));
 }
@@ -175,18 +157,18 @@ pte_t *pte_offset_kernel(pmd_t *dir, unsigned long address)
  */
 static void *__srmmu_get_nocache(int size, int align)
 {
-	int offset;
+	int offset, minsz = 1 << SRMMU_NOCACHE_BITMAP_SHIFT;
 	unsigned long addr;
 
-	if (size < SRMMU_NOCACHE_BITMAP_SHIFT) {
+	if (size < minsz) {
 		printk(KERN_ERR "Size 0x%x too small for nocache request\n",
 		       size);
-		size = SRMMU_NOCACHE_BITMAP_SHIFT;
+		size = minsz;
 	}
-	if (size & (SRMMU_NOCACHE_BITMAP_SHIFT - 1)) {
-		printk(KERN_ERR "Size 0x%x unaligned int nocache request\n",
+	if (size & (minsz - 1)) {
+		printk(KERN_ERR "Size 0x%x unaligned in nocache request\n",
 		       size);
-		size += SRMMU_NOCACHE_BITMAP_SHIFT - 1;
+		size += minsz - 1;
 	}
 	BUG_ON(align > SRMMU_NOCACHE_ALIGN_MAX);
 
@@ -376,31 +358,33 @@ pgd_t *get_pgd_fast(void)
  */
 pgtable_t pte_alloc_one(struct mm_struct *mm)
 {
-	unsigned long pte;
+	pte_t *ptep;
 	struct page *page;
 
-	if ((pte = (unsigned long)pte_alloc_one_kernel(mm)) == 0)
-		return NULL;
-	page = pfn_to_page(__nocache_pa(pte) >> PAGE_SHIFT);
-	if (!pgtable_pte_page_ctor(page)) {
-		__free_page(page);
+	if ((ptep = pte_alloc_one_kernel(mm)) == 0)
 		return NULL;
+	page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT);
+	spin_lock(&mm->page_table_lock);
+	if (page_ref_inc_return(page) == 2 && !pgtable_pte_page_ctor(page)) {
+		page_ref_dec(page);
+		ptep = NULL;
 	}
-	return page;
+	spin_unlock(&mm->page_table_lock);
+
+	return ptep;
 }
 
-void pte_free(struct mm_struct *mm, pgtable_t pte)
+void pte_free(struct mm_struct *mm, pgtable_t ptep)
 {
-	unsigned long p;
+	struct page *page;
 
-	pgtable_pte_page_dtor(pte);
-	p = (unsigned long)page_address(pte);	/* Cached address (for test) */
-	if (p == 0)
-		BUG();
-	p = page_to_pfn(pte) << PAGE_SHIFT;	/* Physical address */
+	page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT);
+	spin_lock(&mm->page_table_lock);
+	if (page_ref_dec_return(page) == 1)
+		pgtable_pte_page_dtor(page);
+	spin_unlock(&mm->page_table_lock);
 
-	/* free non cached virtual address*/
-	srmmu_free_nocache(__nocache_va(p), PTE_SIZE);
+	srmmu_free_nocache(ptep, SRMMU_PTE_TABLE_SIZE);
 }
 
 /* context handling - a dynamically sized pool is used */
@@ -822,13 +806,13 @@ static void __init srmmu_inherit_prom_mappings(unsigned long start,
 		what = 0;
 		addr = start - PAGE_SIZE;
 
-		if (!(start & ~(SRMMU_REAL_PMD_MASK))) {
-			if (srmmu_probe(addr + SRMMU_REAL_PMD_SIZE) == probed)
+		if (!(start & ~(PMD_MASK))) {
+			if (srmmu_probe(addr + PMD_SIZE) == probed)
 				what = 1;
 		}
 
-		if (!(start & ~(SRMMU_PGDIR_MASK))) {
-			if (srmmu_probe(addr + SRMMU_PGDIR_SIZE) == probed)
+		if (!(start & ~(PGDIR_MASK))) {
+			if (srmmu_probe(addr + PGDIR_SIZE) == probed)
 				what = 2;
 		}
 
@@ -837,7 +821,7 @@ static void __init srmmu_inherit_prom_mappings(unsigned long start,
 		pudp = pud_offset(p4dp, start);
 		if (what == 2) {
 			*(pgd_t *)__nocache_fix(pgdp) = __pgd(probed);
-			start += SRMMU_PGDIR_SIZE;
+			start += PGDIR_SIZE;
 			continue;
 		}
 		if (pud_none(*(pud_t *)__nocache_fix(pudp))) {
@@ -849,6 +833,11 @@ static void __init srmmu_inherit_prom_mappings(unsigned long start,
 			pud_set(__nocache_fix(pudp), pmdp);
 		}
 		pmdp = pmd_offset(__nocache_fix(pgdp), start);
+		if (what == 1) {
+			*(pmd_t *)__nocache_fix(pmdp) = __pmd(probed);
+			start += PMD_SIZE;
+			continue;
+		}
 		if (srmmu_pmd_none(*(pmd_t *)__nocache_fix(pmdp))) {
 			ptep = __srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
 			if (ptep == NULL)
@@ -856,19 +845,6 @@ static void __init srmmu_inherit_prom_mappings(unsigned long start,
 			memset(__nocache_fix(ptep), 0, PTE_SIZE);
 			pmd_set(__nocache_fix(pmdp), ptep);
 		}
-		if (what == 1) {
-			/* We bend the rule where all 16 PTPs in a pmd_t point
-			 * inside the same PTE page, and we leak a perfectly
-			 * good hardware PTE piece. Alternatives seem worse.
-			 */
-			unsigned int x;	/* Index of HW PMD in soft cluster */
-			unsigned long *val;
-			x = (start >> PMD_SHIFT) & 15;
-			val = &pmdp->pmdv[x];
-			*(unsigned long *)__nocache_fix(val) = probed;
-			start += SRMMU_REAL_PMD_SIZE;
-			continue;
-		}
 		ptep = pte_offset_kernel(__nocache_fix(pmdp), start);
 		*(pte_t *)__nocache_fix(ptep) = __pte(probed);
 		start += PAGE_SIZE;
@@ -890,9 +866,9 @@ static void __init do_large_mapping(unsigned long vaddr, unsigned long phys_base
 /* Map sp_bank entry SP_ENTRY, starting at virtual address VBASE. */
 static unsigned long __init map_spbank(unsigned long vbase, int sp_entry)
 {
-	unsigned long pstart = (sp_banks[sp_entry].base_addr & SRMMU_PGDIR_MASK);
-	unsigned long vstart = (vbase & SRMMU_PGDIR_MASK);
-	unsigned long vend = SRMMU_PGDIR_ALIGN(vbase + sp_banks[sp_entry].num_bytes);
+	unsigned long pstart = (sp_banks[sp_entry].base_addr & PGDIR_MASK);
+	unsigned long vstart = (vbase & PGDIR_MASK);
+	unsigned long vend = PGDIR_ALIGN(vbase + sp_banks[sp_entry].num_bytes);
 	/* Map "low" memory only */
 	const unsigned long min_vaddr = PAGE_OFFSET;
 	const unsigned long max_vaddr = PAGE_OFFSET + SRMMU_MAXMEM;
@@ -905,7 +881,7 @@ static unsigned long __init map_spbank(unsigned long vbase, int sp_entry)
 
 	while (vstart < vend) {
 		do_large_mapping(vstart, pstart);
-		vstart += SRMMU_PGDIR_SIZE; pstart += SRMMU_PGDIR_SIZE;
+		vstart += PGDIR_SIZE; pstart += PGDIR_SIZE;
 	}
 	return vstart;
 }
diff --git a/arch/sparc/mm/viking.S b/arch/sparc/mm/viking.S
index adaef6e7b8cf..48f062de7a7f 100644
--- a/arch/sparc/mm/viking.S
+++ b/arch/sparc/mm/viking.S
@@ -13,6 +13,7 @@
 #include <asm/asi.h>
 #include <asm/mxcc.h>
 #include <asm/page.h>
+#include <asm/pgtable.h>
 #include <asm/pgtsrmmu.h>
 #include <asm/viking.h>
 
@@ -157,7 +158,7 @@ viking_flush_tlb_range:
 	cmp	%o3, -1
 	be	2f
 #endif
-	sethi	%hi(~((1 << SRMMU_PGDIR_SHIFT) - 1)), %o4
+	sethi	%hi(~((1 << PGDIR_SHIFT) - 1)), %o4
 	sta	%o3, [%g1] ASI_M_MMUREGS
 	and	%o1, %o4, %o1
 	add	%o1, 0x200, %o1
@@ -243,7 +244,7 @@ sun4dsmp_flush_tlb_range:
 	ld	[%o0 + VMA_VM_MM], %o0
 	ld	[%o0 + AOFF_mm_context], %o3
 	lda	[%g1] ASI_M_MMUREGS, %g5
-	sethi	%hi(~((1 << SRMMU_PGDIR_SHIFT) - 1)), %o4
+	sethi	%hi(~((1 << PGDIR_SHIFT) - 1)), %o4
 	sta	%o3, [%g1] ASI_M_MMUREGS
 	and	%o1, %o4, %o1
 	add	%o1, 0x200, %o1
diff --git a/drivers/sbus/char/oradax.c b/drivers/sbus/char/oradax.c
index 8af216287a84..21b7cb6e7e70 100644
--- a/drivers/sbus/char/oradax.c
+++ b/drivers/sbus/char/oradax.c
@@ -410,9 +410,7 @@ static void dax_unlock_pages(struct dax_ctx *ctx, int ccb_index, int nelem)
 
 			if (p) {
 				dax_dbg("freeing page %p", p);
-				if (j == OUT)
-					set_page_dirty(p);
-				put_page(p);
+				unpin_user_pages_dirty_lock(&p, 1, j == OUT);
 				ctx->pages[i][j] = NULL;
 			}
 		}
@@ -425,13 +423,13 @@ static int dax_lock_page(void *va, struct page **p)
 
 	dax_dbg("uva %p", va);
 
-	ret = get_user_pages_fast((unsigned long)va, 1, FOLL_WRITE, p);
+	ret = pin_user_pages_fast((unsigned long)va, 1, FOLL_WRITE, p);
 	if (ret == 1) {
 		dax_dbg("locked page %p, for VA %p", *p, va);
 		return 0;
 	}
 
-	dax_dbg("get_user_pages failed, va=%p, ret=%d", va, ret);
+	dax_dbg("pin_user_pages failed, va=%p, ret=%d", va, ret);
 	return -1;
 }
 
diff --git a/mm/Kconfig b/mm/Kconfig
index cffc276fa19c..f2104cc0d35c 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -193,6 +193,9 @@ config MEMORY_HOTREMOVE
 # Default to 4 for wider testing, though 8 might be more appropriate.
 # ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
 # PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
+# SPARC32 allocates multiple pte tables within a single page, and therefore
+# a per-page lock leads to problems when multiple tables need to be locked
+# at the same time (e.g. copy_page_range()).
 # DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
 #
 config SPLIT_PTLOCK_CPUS
@@ -200,6 +203,7 @@ config SPLIT_PTLOCK_CPUS
 	default "999999" if !MMU
 	default "999999" if ARM && !CPU_CACHE_VIPT
 	default "999999" if PARISC && !PA20
+	default "999999" if SPARC32
 	default "4"
 
 config ARCH_ENABLE_SPLIT_PMD_PTLOCK