Merge remote-tracking branch 'korg/linux-3.0.y' into cm-13.0

Conflicts:
	crypto/algapi.c
	drivers/gpu/drm/i915/i915_debugfs.c
	drivers/gpu/drm/i915/intel_display.c
	drivers/video/fbmem.c
	include/linux/nls.h
	kernel/cgroup.c
	kernel/signal.c
	kernel/timeconst.pl
	net/ipv4/ping.c

Change-Id: I1f532925d1743df74d66bcdd6fc92f05c72ee0dd

23 files changed, 298 insertions, 91 deletions

diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 9e70257..bc31e5e 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -31,6 +31,7 @@ config SPARC
 
 config SPARC32
 	def_bool !64BIT
+	select GENERIC_ATOMIC64
 
 config SPARC64
 	def_bool 64BIT
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 7ae128b..98f223a 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -15,6 +15,8 @@
 
 #ifdef __KERNEL__
 
+#include <asm-generic/atomic64.h>
+
 #include <asm/system.h>
 
 #define ATOMIC_INIT(i)  { (i) }
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 9822628..ba63d08 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -774,6 +774,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 	return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
 }
 
+#include <asm/tlbflush.h>
 #include <asm-generic/pgtable.h>
 
 /* We provide our own get_unmapped_area to cope with VA holes and
diff --git a/arch/sparc/include/asm/signal.h b/arch/sparc/include/asm/signal.h
index e49b828..4929431 100644
--- a/arch/sparc/include/asm/signal.h
+++ b/arch/sparc/include/asm/signal.h
@@ -191,6 +191,7 @@ struct __old_sigaction {
 	unsigned long		sa_flags;
 	void			(*sa_restorer)(void);  /* not used by Linux/SPARC yet */
 };
+#define __ARCH_HAS_SA_RESTORER
 
 typedef struct sigaltstack {
 	void			__user *ss_sp;
diff --git a/arch/sparc/include/asm/system_64.h b/arch/sparc/include/asm/system_64.h
index 10bcabc..f856c7f 100644
--- a/arch/sparc/include/asm/system_64.h
+++ b/arch/sparc/include/asm/system_64.h
@@ -140,8 +140,7 @@ do {						\
 	 * and 2 stores in this critical code path.  -DaveM
 	 */
 #define switch_to(prev, next, last)					\
-do {	flush_tlb_pending();						\
-	save_and_clear_fpu();						\
+do {	save_and_clear_fpu();						\
 	/* If you are tempted to conditionalize the following */	\
 	/* so that ASI is only written if it changes, think again. */	\
 	__asm__ __volatile__("wr %%g0, %0, %%asi"			\
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index 2ef4634..f0d6a97 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -11,24 +11,40 @@
 struct tlb_batch {
 	struct mm_struct *mm;
 	unsigned long tlb_nr;
+	unsigned long active;
 	unsigned long vaddrs[TLB_BATCH_NR];
 };
 
 extern void flush_tsb_kernel_range(unsigned long start, unsigned long end);
 extern void flush_tsb_user(struct tlb_batch *tb);
+extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
 
 /* TLB flush operations. */
 
-extern void flush_tlb_pending(void);
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+				  unsigned long vmaddr)
+{
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+}
+
+#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 
-#define flush_tlb_range(vma,start,end)	\
-	do { (void)(start); flush_tlb_pending(); } while (0)
-#define flush_tlb_page(vma,addr)	flush_tlb_pending()
-#define flush_tlb_mm(mm)		flush_tlb_pending()
+extern void flush_tlb_pending(void);
+extern void arch_enter_lazy_mmu_mode(void);
+extern void arch_leave_lazy_mmu_mode(void);
+#define arch_flush_lazy_mmu_mode()      do {} while (0)
 
 /* Local cpu only.  */
 extern void __flush_tlb_all(void);
-
+extern void __flush_tlb_page(unsigned long context, unsigned long vaddr);
 extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #ifndef CONFIG_SMP
@@ -38,15 +54,24 @@ do {	flush_tsb_kernel_range(start,end); \
 	__flush_tlb_kernel_range(start,end); \
 } while (0)
 
+static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	__flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
+}
+
 #else /* CONFIG_SMP */
 
 extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
 
 #define flush_tlb_kernel_range(start, end) \
 do {	flush_tsb_kernel_range(start,end); \
 	smp_flush_tlb_kernel_range(start, end); \
 } while (0)
 
+#define global_flush_tlb_page(mm, vaddr) \
+	smp_flush_tlb_page(mm, vaddr)
+
 #endif /* ! CONFIG_SMP */
 
 #endif /* _SPARC64_TLBFLUSH_H */
diff --git a/arch/sparc/kernel/asm-offsets.c b/arch/sparc/kernel/asm-offsets.c
index 68f7e11..ce48203 100644
--- a/arch/sparc/kernel/asm-offsets.c
+++ b/arch/sparc/kernel/asm-offsets.c
@@ -34,6 +34,8 @@ int foo(void)
 	DEFINE(AOFF_task_thread, offsetof(struct task_struct, thread));
 	BLANK();
 	DEFINE(AOFF_mm_context, offsetof(struct mm_struct, context));
+	BLANK();
+	DEFINE(VMA_VM_MM,    offsetof(struct vm_area_struct, vm_mm));
 
 	/* DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28); */
 	return 0;
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index f445e98..cfabc3d 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -1177,7 +1177,7 @@ sys_sigreturn:
 	 nop
 
 	call	syscall_trace
-	 nop
+	 mov	1, %o1
 
 1:
 	/* We don't want to muck with user registers like a
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index 79f3103..7c00735 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -25,11 +25,10 @@ kvmap_itlb:
 	 */
 kvmap_itlb_4v:
 
-kvmap_itlb_nonlinear:
 	/* Catch kernel NULL pointer calls.  */
 	sethi		%hi(PAGE_SIZE), %g5
 	cmp		%g4, %g5
-	bleu,pn		%xcc, kvmap_dtlb_longpath
+	blu,pn		%xcc, kvmap_itlb_longpath
 	 nop
 
 	KERN_TSB_LOOKUP_TL1(%g4, %g6, %g5, %g1, %g2, %g3, kvmap_itlb_load)
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 99cb172..e82c18e 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -856,7 +856,7 @@ void smp_tsb_sync(struct mm_struct *mm)
 }
 
 extern unsigned long xcall_flush_tlb_mm;
-extern unsigned long xcall_flush_tlb_pending;
+extern unsigned long xcall_flush_tlb_page;
 extern unsigned long xcall_flush_tlb_kernel_range;
 extern unsigned long xcall_fetch_glob_regs;
 extern unsigned long xcall_receive_signal;
@@ -1070,23 +1070,56 @@ local_flush_and_out:
 	put_cpu();
 }
 
+struct tlb_pending_info {
+	unsigned long ctx;
+	unsigned long nr;
+	unsigned long *vaddrs;
+};
+
+static void tlb_pending_func(void *info)
+{
+	struct tlb_pending_info *t = info;
+
+	__flush_tlb_pending(t->ctx, t->nr, t->vaddrs);
+}
+
 void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs)
 {
 	u32 ctx = CTX_HWBITS(mm->context);
+	struct tlb_pending_info info;
 	int cpu = get_cpu();
 
+	info.ctx = ctx;
+	info.nr = nr;
+	info.vaddrs = vaddrs;
+
 	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
 		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
 	else
-		smp_cross_call_masked(&xcall_flush_tlb_pending,
-				      ctx, nr, (unsigned long) vaddrs,
-				      mm_cpumask(mm));
+		smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
+				       &info, 1);
 
 	__flush_tlb_pending(ctx, nr, vaddrs);
 
 	put_cpu();
 }
 
+void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	unsigned long context = CTX_HWBITS(mm->context);
+	int cpu = get_cpu();
+
+	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
+		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
+	else
+		smp_cross_call_masked(&xcall_flush_tlb_page,
+				      context, vaddr, 0,
+				      mm_cpumask(mm));
+	__flush_tlb_page(context, vaddr);
+
+	put_cpu();
+}
+
 void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
 	start &= PAGE_MASK;
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index 7f5f65d..817187d 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -147,7 +147,7 @@ linux_syscall_trace32:
 	srl	%i4, 0, %o4
 	srl	%i1, 0, %o1
 	srl	%i2, 0, %o2
-	ba,pt	%xcc, 2f
+	ba,pt	%xcc, 5f
 	 srl	%i3, 0, %o3
 
 linux_syscall_trace:
@@ -177,13 +177,13 @@ linux_sparc_syscall32:
 	srl	%i1, 0, %o1				! IEU0	Group
 	ldx	[%g6 + TI_FLAGS], %l0		! Load
 
-	srl	%i5, 0, %o5				! IEU1
+	srl	%i3, 0, %o3				! IEU0
 	srl	%i2, 0, %o2				! IEU0	Group
 	andcc	%l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0
 	bne,pn	%icc, linux_syscall_trace32		! CTI
 	 mov	%i0, %l5				! IEU1
-	call	%l7					! CTI	Group brk forced
-	 srl	%i3, 0, %o3				! IEU0
+5:	call	%l7					! CTI	Group brk forced
+	 srl	%i5, 0, %o5				! IEU1
 	ba,a,pt	%xcc, 3f
 
 	/* Linux native system calls enter here... */
diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S
index da1b781..8fa84a3 100644
--- a/arch/sparc/kernel/trampoline_64.S
+++ b/arch/sparc/kernel/trampoline_64.S
@@ -131,7 +131,6 @@ startup_continue:
 	clr		%l5
 	sethi		%hi(num_kernel_image_mappings), %l6
 	lduw		[%l6 + %lo(num_kernel_image_mappings)], %l6
-	add		%l6, 1, %l6
 
 	mov		15, %l7
 	BRANCH_IF_ANY_CHEETAH(g1,g5,2f)
@@ -224,7 +223,6 @@ niagara_lock_tlb:
 	clr		%l5
 	sethi		%hi(num_kernel_image_mappings), %l6
 	lduw		[%l6 + %lo(num_kernel_image_mappings)], %l6
-	add		%l6, 1, %l6
 
 1:
 	mov		HV_FAST_MMU_MAP_PERM_ADDR, %o5
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index a3fc437..4961516 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -40,7 +40,7 @@ lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
 lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o
 
 obj-y                 += iomap.o
-obj-$(CONFIG_SPARC32) += atomic32.o
+obj-$(CONFIG_SPARC32) += atomic32.o ucmpdi2.o
 obj-y                 += ksyms.o
 obj-$(CONFIG_SPARC64) += PeeCeeI.o
 obj-y                 += usercopy.o
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 1b30bb3..fbb8005 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -131,15 +131,6 @@ EXPORT_SYMBOL(___copy_from_user);
 EXPORT_SYMBOL(___copy_in_user);
 EXPORT_SYMBOL(__clear_user);
 
-/* RW semaphores */
-EXPORT_SYMBOL(__down_read);
-EXPORT_SYMBOL(__down_read_trylock);
-EXPORT_SYMBOL(__down_write);
-EXPORT_SYMBOL(__down_write_trylock);
-EXPORT_SYMBOL(__up_read);
-EXPORT_SYMBOL(__up_write);
-EXPORT_SYMBOL(__downgrade_write);
-
 /* Atomic counter implementation. */
 EXPORT_SYMBOL(atomic_add);
 EXPORT_SYMBOL(atomic_add_ret);
diff --git a/arch/sparc/lib/ucmpdi2.c b/arch/sparc/lib/ucmpdi2.c
new file mode 100644
index 0000000..1e06ed5
--- /dev/null
+++ b/arch/sparc/lib/ucmpdi2.c
@@ -0,0 +1,19 @@
+#include <linux/module.h>
+#include "libgcc.h"
+
+word_type __ucmpdi2(unsigned long long a, unsigned long long b)
+{
+	const DWunion au = {.ll = a};
+	const DWunion bu = {.ll = b};
+
+	if ((unsigned int) au.s.high < (unsigned int) bu.s.high)
+		return 0;
+	else if ((unsigned int) au.s.high > (unsigned int) bu.s.high)
+		return 2;
+	if ((unsigned int) au.s.low < (unsigned int) bu.s.low)
+		return 0;
+	else if ((unsigned int) au.s.low > (unsigned int) bu.s.low)
+		return 2;
+	return 1;
+}
+EXPORT_SYMBOL(__ucmpdi2);
diff --git a/arch/sparc/mm/hypersparc.S b/arch/sparc/mm/hypersparc.S
index 44aad32..969f964 100644
--- a/arch/sparc/mm/hypersparc.S
+++ b/arch/sparc/mm/hypersparc.S
@@ -74,7 +74,7 @@ hypersparc_flush_cache_mm_out:
 
 	/* The things we do for performance... */
 hypersparc_flush_cache_range:
-	ld	[%o0 + 0x0], %o0		/* XXX vma->vm_mm, GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 #ifndef CONFIG_SMP
 	ld	[%o0 + AOFF_mm_context], %g1
 	cmp	%g1, -1
@@ -163,7 +163,7 @@ hypersparc_flush_cache_range_out:
 	 */
 	/* Verified, my ass... */
 hypersparc_flush_cache_page:
-	ld	[%o0 + 0x0], %o0		/* XXX vma->vm_mm, GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 	ld	[%o0 + AOFF_mm_context], %g2
 #ifndef CONFIG_SMP
 	cmp	%g2, -1
@@ -284,7 +284,7 @@ hypersparc_flush_tlb_mm_out:
 	 sta	%g5, [%g1] ASI_M_MMUREGS
 
 hypersparc_flush_tlb_range:
-	ld	[%o0 + 0x00], %o0	/* XXX vma->vm_mm GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 	mov	SRMMU_CTX_REG, %g1
 	ld	[%o0 + AOFF_mm_context], %o3
 	lda	[%g1] ASI_M_MMUREGS, %g5
@@ -307,7 +307,7 @@ hypersparc_flush_tlb_range_out:
 	 sta	%g5, [%g1] ASI_M_MMUREGS
 
 hypersparc_flush_tlb_page:
-	ld	[%o0 + 0x00], %o0	/* XXX vma->vm_mm GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 	mov	SRMMU_CTX_REG, %g1
 	ld	[%o0 + AOFF_mm_context], %o3
 	andn	%o1, (PAGE_SIZE - 1), %o1
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 6ff4d78..b4989f9 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1071,7 +1071,14 @@ static int __init grab_mblocks(struct mdesc_handle *md)
 		m->size = *val;
 		val = mdesc_get_property(md, node,
 					 "address-congruence-offset", NULL);
-		m->offset = *val;
+
+		/* The address-congruence-offset property is optional.
+		 * Explicity zero it be identifty this.
+		 */
+		if (val)
+			m->offset = *val;
+		else
+			m->offset = 0UL;
 
 		numadbg("MBLOCK[%d]: base[%llx] size[%llx] offset[%llx]\n",
 			count - 1, m->base, m->size, m->offset);
diff --git a/arch/sparc/mm/swift.S b/arch/sparc/mm/swift.S
index c801c39..5d2b88d 100644
--- a/arch/sparc/mm/swift.S
+++ b/arch/sparc/mm/swift.S
@@ -105,7 +105,7 @@ swift_flush_cache_mm_out:
 
 	.globl	swift_flush_cache_range
 swift_flush_cache_range:
-	ld	[%o0 + 0x0], %o0		/* XXX vma->vm_mm, GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 	sub	%o2, %o1, %o2
 	sethi	%hi(4096), %o3
 	cmp	%o2, %o3
@@ -116,7 +116,7 @@ swift_flush_cache_range:
 
 	.globl	swift_flush_cache_page
 swift_flush_cache_page:
-	ld	[%o0 + 0x0], %o0		/* XXX vma->vm_mm, GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 70:
 	ld	[%o0 + AOFF_mm_context], %g2
 	cmp	%g2, -1
@@ -219,7 +219,7 @@ swift_flush_sig_insns:
 	.globl	swift_flush_tlb_range
 	.globl	swift_flush_tlb_all
 swift_flush_tlb_range:
-	ld	[%o0 + 0x00], %o0	/* XXX vma->vm_mm GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 swift_flush_tlb_mm:
 	ld	[%o0 + AOFF_mm_context], %g2
 	cmp	%g2, -1
@@ -233,7 +233,7 @@ swift_flush_tlb_all_out:
 
 	.globl	swift_flush_tlb_page
 swift_flush_tlb_page:
-	ld	[%o0 + 0x00], %o0	/* XXX vma->vm_mm GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 	mov	SRMMU_CTX_REG, %g1
 	ld	[%o0 + AOFF_mm_context], %o3
 	andn	%o1, (PAGE_SIZE - 1), %o1
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index b1f279c..072f553 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, tlb_batch);
 void flush_tlb_pending(void)
 {
 	struct tlb_batch *tb = &get_cpu_var(tlb_batch);
+	struct mm_struct *mm = tb->mm;
 
-	if (tb->tlb_nr) {
-		flush_tsb_user(tb);
+	if (!tb->tlb_nr)
+		goto out;
 
-		if (CTX_VALID(tb->mm->context)) {
+	flush_tsb_user(tb);
+
+	if (CTX_VALID(mm->context)) {
+		if (tb->tlb_nr == 1) {
+			global_flush_tlb_page(mm, tb->vaddrs[0]);
+		} else {
 #ifdef CONFIG_SMP
 			smp_flush_tlb_pending(tb->mm, tb->tlb_nr,
 					      &tb->vaddrs[0]);
@@ -37,12 +43,30 @@ void flush_tlb_pending(void)
 					    tb->tlb_nr, &tb->vaddrs[0]);
 #endif
 		}
-		tb->tlb_nr = 0;
 	}
 
+	tb->tlb_nr = 0;
+
+out:
 	put_cpu_var(tlb_batch);
 }
 
+void arch_enter_lazy_mmu_mode(void)
+{
+	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+	tb->active = 1;
+}
+
+void arch_leave_lazy_mmu_mode(void)
+{
+	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+	if (tb->tlb_nr)
+		flush_tlb_pending();
+	tb->active = 0;
+}
+
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm)
 {
@@ -90,6 +114,12 @@ no_cache_flush:
 		nr = 0;
 	}
 
+	if (!tb->active) {
+		flush_tsb_user_page(mm, vaddr);
+		global_flush_tlb_page(mm, vaddr);
+		goto out;
+	}
+
 	if (nr == 0)
 		tb->mm = mm;
 
@@ -98,5 +128,6 @@ no_cache_flush:
 	if (nr >= TLB_BATCH_NR)
 		flush_tlb_pending();
 
+out:
 	put_cpu_var(tlb_batch);
 }
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index a5f51b2..cb16ff3 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -8,11 +8,10 @@
 #include <linux/slab.h>
 #include <asm/system.h>
 #include <asm/page.h>
-#include <asm/tlbflush.h>
-#include <asm/tlb.h>
-#include <asm/mmu_context.h>
 #include <asm/pgtable.h>
+#include <asm/mmu_context.h>
 #include <asm/tsb.h>
+#include <asm/tlb.h>
 #include <asm/oplib.h>
 
 extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
@@ -47,23 +46,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
 	}
 }
 
-static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
-			    unsigned long tsb, unsigned long nentries)
+static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v,
+				  unsigned long hash_shift,
+				  unsigned long nentries)
 {
-	unsigned long i;
+	unsigned long tag, ent, hash;
 
-	for (i = 0; i < tb->tlb_nr; i++) {
-		unsigned long v = tb->vaddrs[i];
-		unsigned long tag, ent, hash;
+	v &= ~0x1UL;
+	hash = tsb_hash(v, hash_shift, nentries);
+	ent = tsb + (hash * sizeof(struct tsb));
+	tag = (v >> 22UL);
 
-		v &= ~0x1UL;
+	tsb_flush(ent, tag);
+}
 
-		hash = tsb_hash(v, hash_shift, nentries);
-		ent = tsb + (hash * sizeof(struct tsb));
-		tag = (v >> 22UL);
+static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
+			    unsigned long tsb, unsigned long nentries)
+{
+	unsigned long i;
 
-		tsb_flush(ent, tag);
-	}
+	for (i = 0; i < tb->tlb_nr; i++)
+		__flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries);
 }
 
 void flush_tsb_user(struct tlb_batch *tb)
@@ -91,6 +94,30 @@ void flush_tsb_user(struct tlb_batch *tb)
 	spin_unlock_irqrestore(&mm->context.lock, flags);
 }
 
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	unsigned long nentries, base, flags;
+
+	spin_lock_irqsave(&mm->context.lock, flags);
+
+	base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+	nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+	if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+		base = __pa(base);
+	__flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
+
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+		base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
+		nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
+		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+			base = __pa(base);
+		__flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries);
+	}
+#endif
+	spin_unlock_irqrestore(&mm->context.lock, flags);
+}
+
 #if defined(CONFIG_SPARC64_PAGE_SIZE_8KB)
 #define HV_PGSZ_IDX_BASE	HV_PGSZ_IDX_8K
 #define HV_PGSZ_MASK_BASE	HV_PGSZ_MASK_8K
diff --git a/arch/sparc/mm/tsunami.S b/arch/sparc/mm/tsunami.S
index 4e55e8f..bf10a34 100644
--- a/arch/sparc/mm/tsunami.S
+++ b/arch/sparc/mm/tsunami.S
@@ -24,7 +24,7 @@
 	/* Sliiick... */
 tsunami_flush_cache_page:
 tsunami_flush_cache_range:
-	ld	[%o0 + 0x0], %o0	/* XXX vma->vm_mm, GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 tsunami_flush_cache_mm:
 	ld	[%o0 + AOFF_mm_context], %g2
 	cmp	%g2, -1
@@ -46,7 +46,7 @@ tsunami_flush_sig_insns:
 
 	/* More slick stuff... */
 tsunami_flush_tlb_range:
-	ld	[%o0 + 0x00], %o0	/* XXX vma->vm_mm GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 tsunami_flush_tlb_mm:
 	ld	[%o0 + AOFF_mm_context], %g2
 	cmp	%g2, -1
@@ -65,7 +65,7 @@ tsunami_flush_tlb_out:
 
 	/* This one can be done in a fine grained manner... */
 tsunami_flush_tlb_page:
-	ld	[%o0 + 0x00], %o0	/* XXX vma->vm_mm GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 	mov	SRMMU_CTX_REG, %g1
 	ld	[%o0 + AOFF_mm_context], %o3
 	andn	%o1, (PAGE_SIZE - 1), %o1
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index 874162a..dd10caa 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -53,6 +53,33 @@ __flush_tlb_mm:		/* 18 insns */
 	nop
 
 	.align		32
+	.globl		__flush_tlb_page
+__flush_tlb_page:	/* 22 insns */
+	/* %o0 = context, %o1 = vaddr */
+	rdpr		%pstate, %g7
+	andn		%g7, PSTATE_IE, %g2
+	wrpr		%g2, %pstate
+	mov		SECONDARY_CONTEXT, %o4
+	ldxa		[%o4] ASI_DMMU, %g2
+	stxa		%o0, [%o4] ASI_DMMU
+	andcc		%o1, 1, %g0
+	andn		%o1, 1, %o3
+	be,pn		%icc, 1f
+	 or		%o3, 0x10, %o3
+	stxa		%g0, [%o3] ASI_IMMU_DEMAP
+1:	stxa		%g0, [%o3] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g2, [%o4] ASI_DMMU
+	sethi		%hi(KERNBASE), %o4
+	flush		%o4
+	retl
+	 wrpr		%g7, 0x0, %pstate
+	nop
+	nop
+	nop
+	nop
+
+	.align		32
 	.globl		__flush_tlb_pending
 __flush_tlb_pending:	/* 26 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
@@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */
 	retl
 	 wrpr		%g7, 0x0, %pstate
 
+__cheetah_flush_tlb_page:	/* 22 insns */
+	/* %o0 = context, %o1 = vaddr */
+	rdpr		%pstate, %g7
+	andn		%g7, PSTATE_IE, %g2
+	wrpr		%g2, 0x0, %pstate
+	wrpr		%g0, 1, %tl
+	mov		PRIMARY_CONTEXT, %o4
+	ldxa		[%o4] ASI_DMMU, %g2
+	srlx		%g2, CTX_PGSZ1_NUC_SHIFT, %o3
+	sllx		%o3, CTX_PGSZ1_NUC_SHIFT, %o3
+	or		%o0, %o3, %o0	/* Preserve nucleus page size fields */
+	stxa		%o0, [%o4] ASI_DMMU
+	andcc		%o1, 1, %g0
+	be,pn		%icc, 1f
+	 andn		%o1, 1, %o3
+	stxa		%g0, [%o3] ASI_IMMU_DEMAP
+1:	stxa		%g0, [%o3] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g2, [%o4] ASI_DMMU
+	sethi		%hi(KERNBASE), %o4
+	flush		%o4
+	wrpr		%g0, 0, %tl
+	retl
+	 wrpr		%g7, 0x0, %pstate
+
 __cheetah_flush_tlb_pending:	/* 27 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	rdpr		%pstate, %g7
@@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns */
 	retl
 	 nop
 
+__hypervisor_flush_tlb_page: /* 11 insns */
+	/* %o0 = context, %o1 = vaddr */
+	mov		%o0, %g2
+	mov		%o1, %o0              /* ARG0: vaddr + IMMU-bit */
+	mov		%g2, %o1	      /* ARG1: mmu context */
+	mov		HV_MMU_ALL, %o2	      /* ARG2: flags */
+	srlx		%o0, PAGE_SHIFT, %o0
+	sllx		%o0, PAGE_SHIFT, %o0
+	ta		HV_MMU_UNMAP_ADDR_TRAP
+	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
+	retl
+	 nop
+
 __hypervisor_flush_tlb_pending: /* 16 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	sllx		%o1, 3, %g1
@@ -339,6 +405,13 @@ cheetah_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		19, %o2
 
+	sethi		%hi(__flush_tlb_page), %o0
+	or		%o0, %lo(__flush_tlb_page), %o0
+	sethi		%hi(__cheetah_flush_tlb_page), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_page), %o1
+	call		tlb_patch_one
+	 mov		22, %o2
+
 	sethi		%hi(__flush_tlb_pending), %o0
 	or		%o0, %lo(__flush_tlb_pending), %o0
 	sethi		%hi(__cheetah_flush_tlb_pending), %o1
@@ -397,10 +470,9 @@ xcall_flush_tlb_mm:	/* 21 insns */
 	nop
 	nop
 
-	.globl		xcall_flush_tlb_pending
-xcall_flush_tlb_pending:	/* 21 insns */
-	/* %g5=context, %g1=nr, %g7=vaddrs[] */
-	sllx		%g1, 3, %g1
+	.globl		xcall_flush_tlb_page
+xcall_flush_tlb_page:	/* 17 insns */
+	/* %g5=context, %g1=vaddr */
 	mov		PRIMARY_CONTEXT, %g4
 	ldxa		[%g4] ASI_DMMU, %g2
 	srlx		%g2, CTX_PGSZ1_NUC_SHIFT, %g4
@@ -408,20 +480,16 @@ xcall_flush_tlb_pending:	/* 21 insns */
 	or		%g5, %g4, %g5
 	mov		PRIMARY_CONTEXT, %g4
 	stxa		%g5, [%g4] ASI_DMMU
-1:	sub		%g1, (1 << 3), %g1
-	ldx		[%g7 + %g1], %g5
-	andcc		%g5, 0x1, %g0
+	andcc		%g1, 0x1, %g0
 	be,pn		%icc, 2f
-
-	 andn		%g5, 0x1, %g5
+	 andn		%g1, 0x1, %g5
 	stxa		%g0, [%g5] ASI_IMMU_DEMAP
 2:	stxa		%g0, [%g5] ASI_DMMU_DEMAP
 	membar		#Sync
-	brnz,pt		%g1, 1b
-	 nop
 	stxa		%g2, [%g4] ASI_DMMU
 	retry
 	nop
+	nop
 
 	.globl		xcall_flush_tlb_kernel_range
 xcall_flush_tlb_kernel_range:	/* 25 insns */
@@ -596,15 +664,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
 	membar		#Sync
 	retry
 
-	.globl		__hypervisor_xcall_flush_tlb_pending
-__hypervisor_xcall_flush_tlb_pending: /* 21 insns */
-	/* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */
-	sllx		%g1, 3, %g1
+	.globl		__hypervisor_xcall_flush_tlb_page
+__hypervisor_xcall_flush_tlb_page: /* 17 insns */
+	/* %g5=ctx, %g1=vaddr */
 	mov		%o0, %g2
 	mov		%o1, %g3
 	mov		%o2, %g4
-1:	sub		%g1, (1 << 3), %g1
-	ldx		[%g7 + %g1], %o0	/* ARG0: virtual address */
+	mov		%g1, %o0	        /* ARG0: virtual address */
 	mov		%g5, %o1		/* ARG1: mmu context */
 	mov		HV_MMU_ALL, %o2		/* ARG2: flags */
 	srlx		%o0, PAGE_SHIFT, %o0
@@ -613,8 +679,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */
 	mov		HV_MMU_UNMAP_ADDR_TRAP, %g6
 	brnz,a,pn	%o0, __hypervisor_tlb_xcall_error
 	 mov		%o0, %g5
-	brnz,pt		%g1, 1b
-	 nop
 	mov		%g2, %o0
 	mov		%g3, %o1
 	mov		%g4, %o2
@@ -697,6 +761,13 @@ hypervisor_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		10, %o2
 
+	sethi		%hi(__flush_tlb_page), %o0
+	or		%o0, %lo(__flush_tlb_page), %o0
+	sethi		%hi(__hypervisor_flush_tlb_page), %o1
+	or		%o1, %lo(__hypervisor_flush_tlb_page), %o1
+	call		tlb_patch_one
+	 mov		11, %o2
+
 	sethi		%hi(__flush_tlb_pending), %o0
 	or		%o0, %lo(__flush_tlb_pending), %o0
 	sethi		%hi(__hypervisor_flush_tlb_pending), %o1
@@ -728,12 +799,12 @@ hypervisor_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		21, %o2
 
-	sethi		%hi(xcall_flush_tlb_pending), %o0
-	or		%o0, %lo(xcall_flush_tlb_pending), %o0
-	sethi		%hi(__hypervisor_xcall_flush_tlb_pending), %o1
-	or		%o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1
+	sethi		%hi(xcall_flush_tlb_page), %o0
+	or		%o0, %lo(xcall_flush_tlb_page), %o0
+	sethi		%hi(__hypervisor_xcall_flush_tlb_page), %o1
+	or		%o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1
 	call		tlb_patch_one
-	 mov		21, %o2
+	 mov		17, %o2
 
 	sethi		%hi(xcall_flush_tlb_kernel_range), %o0
 	or		%o0, %lo(xcall_flush_tlb_kernel_range), %o0
diff --git a/arch/sparc/mm/viking.S b/arch/sparc/mm/viking.S
index 6dfcc13..a516372 100644
--- a/arch/sparc/mm/viking.S
+++ b/arch/sparc/mm/viking.S
@@ -109,7 +109,7 @@ viking_mxcc_flush_page:
 viking_flush_cache_page:
 viking_flush_cache_range:
 #ifndef CONFIG_SMP
-	ld	[%o0 + 0x0], %o0		/* XXX vma->vm_mm, GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 #endif
 viking_flush_cache_mm:
 #ifndef CONFIG_SMP
@@ -149,7 +149,7 @@ viking_flush_tlb_mm:
 #endif
 
 viking_flush_tlb_range:
-	ld	[%o0 + 0x00], %o0	/* XXX vma->vm_mm GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 	mov	SRMMU_CTX_REG, %g1
 	ld	[%o0 + AOFF_mm_context], %o3
 	lda	[%g1] ASI_M_MMUREGS, %g5
@@ -174,7 +174,7 @@ viking_flush_tlb_range:
 #endif
 
 viking_flush_tlb_page:
-	ld	[%o0 + 0x00], %o0	/* XXX vma->vm_mm GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 	mov	SRMMU_CTX_REG, %g1
 	ld	[%o0 + AOFF_mm_context], %o3
 	lda	[%g1] ASI_M_MMUREGS, %g5
@@ -240,7 +240,7 @@ sun4dsmp_flush_tlb_range:
 	tst	%g5
 	bne	3f
 	 mov	SRMMU_CTX_REG, %g1
-	ld	[%o0 + 0x00], %o0	/* XXX vma->vm_mm GROSS XXX */
+	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
@@ -266,7 +266,7 @@ sun4dsmp_flush_tlb_page:
 	tst	%g5
 	bne	2f
 	 mov	SRMMU_CTX_REG, %g1
-	ld	[%o0 + 0x00], %o0	/* XXX vma->vm_mm GROSS XXX */
+	ld	[%o0 + VMA_VM_MM], %o0
 	ld	[%o0 + AOFF_mm_context], %o3
 	lda	[%g1] ASI_M_MMUREGS, %g5
 	and	%o1, PAGE_MASK, %o1