Merge tag 'v4.4.14' into toradex_vf_4.4-nextColibri_VF_LinuxImageV2.6Beta2_20160701

This is the 4.4.14 stable release

27 files changed, 425 insertions, 214 deletions

diff --git a/arch/sparc/include/asm/head_64.h b/arch/sparc/include/asm/head_64.h
index 10e9dabc4c41..f0700cfeedd7 100644
--- a/arch/sparc/include/asm/head_64.h
+++ b/arch/sparc/include/asm/head_64.h
@@ -15,6 +15,10 @@
 
 #define	PTREGS_OFF	(STACK_BIAS + STACKFRAME_SZ)
 
+#define	RTRAP_PSTATE		(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
+#define	RTRAP_PSTATE_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
+#define RTRAP_PSTATE_AG_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
+
 #define __CHEETAH_ID	0x003e0014
 #define __JALAPENO_ID	0x003e0016
 #define __SERRANO_ID	0x003e0022
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 131d36fcd07a..408b715c95a5 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -375,7 +375,7 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
 #define pgprot_noncached pgprot_noncached
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline pte_t pte_mkhuge(pte_t pte)
+static inline unsigned long __pte_huge_mask(void)
 {
 	unsigned long mask;
 
@@ -390,8 +390,19 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	: "=r" (mask)
 	: "i" (_PAGE_SZHUGE_4U), "i" (_PAGE_SZHUGE_4V));
 
-	return __pte(pte_val(pte) | mask);
+	return mask;
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return __pte(pte_val(pte) | __pte_huge_mask());
+}
+
+static inline bool is_hugetlb_pte(pte_t pte)
+{
+	return !!(pte_val(pte) & __pte_huge_mask());
 }
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline pmd_t pmd_mkhuge(pmd_t pmd)
 {
@@ -403,6 +414,11 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 	return __pmd(pte_val(pte));
 }
 #endif
+#else
+static inline bool is_hugetlb_pte(pte_t pte)
+{
+	return false;
+}
 #endif
 
 static inline pte_t pte_mkdirty(pte_t pte)
@@ -865,6 +881,19 @@ static inline unsigned long pud_pfn(pud_t pud)
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm);
 
+static void maybe_tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
+				pte_t *ptep, pte_t orig, int fullmm)
+{
+	/* It is more efficient to let flush_tlb_kernel_range()
+	 * handle init_mm tlb flushes.
+	 *
+	 * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
+	 *             and SUN4V pte layout, so this inline test is fine.
+	 */
+	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
+		tlb_batch_add(mm, vaddr, ptep, orig, fullmm);
+}
+
 #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr,
@@ -881,15 +910,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	pte_t orig = *ptep;
 
 	*ptep = pte;
-
-	/* It is more efficient to let flush_tlb_kernel_range()
-	 * handle init_mm tlb flushes.
-	 *
-	 * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
-	 *             and SUN4V pte layout, so this inline test is fine.
-	 */
-	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
-		tlb_batch_add(mm, addr, ptep, orig, fullmm);
+	maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm);
 }
 
 #define set_pte_at(mm,addr,ptep,pte)	\
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index dea1cfa2122b..a8e192e90700 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -8,6 +8,7 @@
 #define TLB_BATCH_NR	192
 
 struct tlb_batch {
+	bool huge;
 	struct mm_struct *mm;
 	unsigned long tlb_nr;
 	unsigned long active;
@@ -16,7 +17,7 @@ struct tlb_batch {
 
 void flush_tsb_kernel_range(unsigned long start, unsigned long end);
 void flush_tsb_user(struct tlb_batch *tb);
-void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge);
 
 /* TLB flush operations. */
 
diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h
index 71b5a67522ab..781b9f1dbdc2 100644
--- a/arch/sparc/include/asm/ttable.h
+++ b/arch/sparc/include/asm/ttable.h
@@ -589,8 +589,8 @@ user_rtt_fill_64bit:					\
 	 restored;					\
 	nop; nop; nop; nop; nop; nop;			\
 	nop; nop; nop; nop; nop;			\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_dax;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_mna;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;
 
 
@@ -652,8 +652,8 @@ user_rtt_fill_32bit:					\
 	 restored;					\
 	nop; nop; nop; nop; nop;			\
 	nop; nop; nop;					\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
-	ba,a,pt	%xcc, user_rtt_fill_fixup;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_dax;		\
+	ba,a,pt	%xcc, user_rtt_fill_fixup_mna;		\
 	ba,a,pt	%xcc, user_rtt_fill_fixup;
 
 
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 7cf9c6ea3f1f..fdb13327fded 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -21,6 +21,7 @@ CFLAGS_REMOVE_perf_event.o := -pg
 CFLAGS_REMOVE_pcr.o := -pg
 endif
 
+obj-$(CONFIG_SPARC64)   += urtt_fill.o
 obj-$(CONFIG_SPARC32)   += entry.o wof.o wuf.o
 obj-$(CONFIG_SPARC32)   += etrap_32.o
 obj-$(CONFIG_SPARC32)   += rtrap_32.o
diff --git a/arch/sparc/kernel/cherrs.S b/arch/sparc/kernel/cherrs.S
index 4ee1ad420862..655628def68e 100644
--- a/arch/sparc/kernel/cherrs.S
+++ b/arch/sparc/kernel/cherrs.S
@@ -214,8 +214,7 @@ do_dcpe_tl1_nonfatal:	/* Ok we may use interrupt globals safely. */
 	subcc		%g1, %g2, %g1		! Next cacheline
 	bge,pt		%icc, 1b
 	 nop
-	ba,pt		%xcc, dcpe_icpe_tl1_common
-	 nop
+	ba,a,pt		%xcc, dcpe_icpe_tl1_common
 
 do_dcpe_tl1_fatal:
 	sethi		%hi(1f), %g7
@@ -224,8 +223,7 @@ do_dcpe_tl1_fatal:
 	mov		0x2, %o0
 	call		cheetah_plus_parity_error
 	 add		%sp, PTREGS_OFF, %o1
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_dcpe_tl1,.-do_dcpe_tl1
 
 	.globl		do_icpe_tl1
@@ -259,8 +257,7 @@ do_icpe_tl1_nonfatal:	/* Ok we may use interrupt globals safely. */
 	subcc		%g1, %g2, %g1
 	bge,pt		%icc, 1b
 	 nop
-	ba,pt		%xcc, dcpe_icpe_tl1_common
-	 nop
+	ba,a,pt		%xcc, dcpe_icpe_tl1_common
 
 do_icpe_tl1_fatal:
 	sethi		%hi(1f), %g7
@@ -269,8 +266,7 @@ do_icpe_tl1_fatal:
 	mov		0x3, %o0
 	call		cheetah_plus_parity_error
 	 add		%sp, PTREGS_OFF, %o1
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_icpe_tl1,.-do_icpe_tl1
 	
 	.type		dcpe_icpe_tl1_common,#function
@@ -456,7 +452,7 @@ __cheetah_log_error:
 	 cmp		%g2, 0x63
 	be		c_cee
 	 nop
-	ba,pt		%xcc, c_deferred
+	ba,a,pt		%xcc, c_deferred
 	.size		__cheetah_log_error,.-__cheetah_log_error
 
 	/* Cheetah FECC trap handling, we get here from tl{0,1}_fecc
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index 33c02b15f478..a83707c83be8 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -948,7 +948,24 @@ linux_syscall_trace:
 	cmp	%o0, 0
 	bne	3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ld	[%sp + STACKFRAME_SZ + PT_G1], %g1
+	sethi	%hi(sys_call_table), %l7
+	ld	[%sp + STACKFRAME_SZ + PT_I0], %i0
+	or	%l7, %lo(sys_call_table), %l7
+	ld	[%sp + STACKFRAME_SZ + PT_I1], %i1
+	ld	[%sp + STACKFRAME_SZ + PT_I2], %i2
+	ld	[%sp + STACKFRAME_SZ + PT_I3], %i3
+	ld	[%sp + STACKFRAME_SZ + PT_I4], %i4
+	ld	[%sp + STACKFRAME_SZ + PT_I5], %i5
+	cmp	%g1, NR_syscalls
+	bgeu	3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	mov	%i0, %o0
+	ld	[%l7 + %l4], %l7
 	mov	%i1, %o1
 	mov	%i2, %o2
 	mov	%i3, %o3
diff --git a/arch/sparc/kernel/fpu_traps.S b/arch/sparc/kernel/fpu_traps.S
index a6864826a4bd..336d2750fe78 100644
--- a/arch/sparc/kernel/fpu_traps.S
+++ b/arch/sparc/kernel/fpu_traps.S
@@ -100,8 +100,8 @@ do_fpdis:
 	fmuld		%f0, %f2, %f26
 	faddd		%f0, %f2, %f28
 	fmuld		%f0, %f2, %f30
-	b,pt		%xcc, fpdis_exit
-	 nop
+	ba,a,pt		%xcc, fpdis_exit
+
 2:	andcc		%g5, FPRS_DU, %g0
 	bne,pt		%icc, 3f
 	 fzero		%f32
@@ -144,8 +144,8 @@ do_fpdis:
 	fmuld		%f32, %f34, %f58
 	faddd		%f32, %f34, %f60
 	fmuld		%f32, %f34, %f62
-	ba,pt		%xcc, fpdis_exit
-	 nop
+	ba,a,pt		%xcc, fpdis_exit
+
 3:	mov		SECONDARY_CONTEXT, %g3
 	add		%g6, TI_FPREGS, %g1
 
@@ -197,8 +197,7 @@ fpdis_exit2:
 fp_other_bounce:
 	call		do_fpother
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		fp_other_bounce,.-fp_other_bounce
 
 	.align		32
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index f2d30cab5b3f..51faf92ace00 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -461,9 +461,8 @@ sun4v_chip_type:
 	subcc	%g3, 1, %g3
 	bne,pt	%xcc, 41b
 	add	%g1, 1, %g1
-	mov	SUN4V_CHIP_SPARC64X, %g4
 	ba,pt	%xcc, 5f
-	nop
+	 mov	SUN4V_CHIP_SPARC64X, %g4
 
 49:
 	mov	SUN4V_CHIP_UNKNOWN, %g4
@@ -548,8 +547,7 @@ sun4u_init:
 	stxa		%g0, [%g7] ASI_DMMU
 	membar	#Sync
 
-	ba,pt		%xcc, sun4u_continue
-	 nop
+	ba,a,pt		%xcc, sun4u_continue
 
 sun4v_init:
 	/* Set ctx 0 */
@@ -560,14 +558,12 @@ sun4v_init:
 	mov		SECONDARY_CONTEXT, %g7
 	stxa		%g0, [%g7] ASI_MMU
 	membar		#Sync
-	ba,pt		%xcc, niagara_tlb_fixup
-	 nop
+	ba,a,pt		%xcc, niagara_tlb_fixup
 
 sun4u_continue:
 	BRANCH_IF_ANY_CHEETAH(g1, g7, cheetah_tlb_fixup)
 
-	ba,pt	%xcc, spitfire_tlb_fixup
-	 nop
+	ba,a,pt	%xcc, spitfire_tlb_fixup
 
 niagara_tlb_fixup:
 	mov	3, %g2		/* Set TLB type to hypervisor. */
@@ -639,8 +635,7 @@ niagara_patch:
 	call	hypervisor_patch_cachetlbops
 	 nop
 
-	ba,pt	%xcc, tlb_fixup_done
-	 nop
+	ba,a,pt	%xcc, tlb_fixup_done
 
 cheetah_tlb_fixup:
 	mov	2, %g2		/* Set TLB type to cheetah+. */
@@ -659,8 +654,7 @@ cheetah_tlb_fixup:
 	call	cheetah_patch_cachetlbops
 	 nop
 
-	ba,pt	%xcc, tlb_fixup_done
-	 nop
+	ba,a,pt	%xcc, tlb_fixup_done
 
 spitfire_tlb_fixup:
 	/* Set TLB type to spitfire. */
@@ -782,8 +776,7 @@ setup_trap_table:
 	call	%o1
 	 add	%sp, (2047 + 128), %o0
 
-	ba,pt	%xcc, 2f
-	 nop
+	ba,a,pt	%xcc, 2f
 
 1:	sethi	%hi(sparc64_ttable_tl0), %o0
 	set	prom_set_trap_table_name, %g2
@@ -822,8 +815,7 @@ setup_trap_table:
 
 	BRANCH_IF_ANY_CHEETAH(o2, o3, 1f)
 
-	ba,pt	%xcc, 2f
-	 nop
+	ba,a,pt	%xcc, 2f
 
 	/* Disable STICK_INT interrupts. */
 1:
diff --git a/arch/sparc/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S
index 753b4f031bfb..34b4933900bf 100644
--- a/arch/sparc/kernel/misctrap.S
+++ b/arch/sparc/kernel/misctrap.S
@@ -18,8 +18,7 @@ __do_privact:
 109:	or		%g7, %lo(109b), %g7
 	call		do_privact
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__do_privact,.-__do_privact
 
 	.type		do_mna,#function
@@ -46,8 +45,7 @@ do_mna:
 	mov		%l5, %o2
 	call		mem_address_unaligned
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_mna,.-do_mna
 
 	.type		do_lddfmna,#function
@@ -65,8 +63,7 @@ do_lddfmna:
 	mov		%l5, %o2
 	call		handle_lddfmna
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_lddfmna,.-do_lddfmna
 
 	.type		do_stdfmna,#function
@@ -84,8 +81,7 @@ do_stdfmna:
 	mov		%l5, %o2
 	call		handle_stdfmna
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		do_stdfmna,.-do_stdfmna
 
 	.type		breakpoint_trap,#function
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index badf0951d73c..9f9614df9e1e 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -994,6 +994,23 @@ void pcibios_set_master(struct pci_dev *dev)
 	/* No special bus mastering setup handling */
 }
 
+#ifdef CONFIG_PCI_IOV
+int pcibios_add_device(struct pci_dev *dev)
+{
+	struct pci_dev *pdev;
+
+	/* Add sriov arch specific initialization here.
+	 * Copy dev_archdata from PF to VF
+	 */
+	if (dev->is_virtfn) {
+		pdev = dev->physfn;
+		memcpy(&dev->dev.archdata, &pdev->dev.archdata,
+		       sizeof(struct dev_archdata));
+	}
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 static int __init pcibios_init(void)
 {
 	pci_dfl_cache_line_size = 64 >> 2;
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index d08bdaffdbfc..216948ca4382 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -14,10 +14,6 @@
 #include <asm/visasm.h>
 #include <asm/processor.h>
 
-#define		RTRAP_PSTATE		(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
-#define		RTRAP_PSTATE_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
-#define		RTRAP_PSTATE_AG_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
-
 #ifdef CONFIG_CONTEXT_TRACKING
 # define SCHEDULE_USER schedule_user
 #else
@@ -242,52 +238,17 @@ rt_continue:	ldx			[%sp + PTREGS_OFF + PT_V9_G1], %g1
 		 wrpr			%g1, %cwp
 		ba,a,pt			%xcc, user_rtt_fill_64bit
 
-user_rtt_fill_fixup:
-		rdpr	%cwp, %g1
-		add	%g1, 1, %g1
-		wrpr	%g1, 0x0, %cwp
-
-		rdpr	%wstate, %g2
-		sll	%g2, 3, %g2
-		wrpr	%g2, 0x0, %wstate
-
-		/* We know %canrestore and %otherwin are both zero.  */
-
-		sethi	%hi(sparc64_kern_pri_context), %g2
-		ldx	[%g2 + %lo(sparc64_kern_pri_context)], %g2
-		mov	PRIMARY_CONTEXT, %g1
-
-661:		stxa	%g2, [%g1] ASI_DMMU
-		.section .sun4v_1insn_patch, "ax"
-		.word	661b
-		stxa	%g2, [%g1] ASI_MMU
-		.previous
-
-		sethi	%hi(KERNBASE), %g1
-		flush	%g1
+user_rtt_fill_fixup_dax:
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 mov	1, %g3
 
-		or	%g4, FAULT_CODE_WINFIXUP, %g4
-		stb	%g4, [%g6 + TI_FAULT_CODE]
-		stx	%g5, [%g6 + TI_FAULT_ADDR]
+user_rtt_fill_fixup_mna:
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 mov	2, %g3
 
-		mov	%g6, %l1
-		wrpr	%g0, 0x0, %tl
-
-661:		nop
-		.section		.sun4v_1insn_patch, "ax"
-		.word			661b
-		SET_GL(0)
-		.previous
-
-		wrpr	%g0, RTRAP_PSTATE, %pstate
-
-		mov	%l1, %g6
-		ldx	[%g6 + TI_TASK], %g4
-		LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
-		call	do_sparc64_fault
-		 add	%sp, PTREGS_OFF, %o0
-		ba,pt	%xcc, rtrap
-		 nop
+user_rtt_fill_fixup:
+		ba,pt	%xcc, user_rtt_fill_fixup_common
+		 clr	%g3
 
 user_rtt_pre_restore:
 		add			%g1, 1, %g1
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 4eed773a7735..77655f0f0fc7 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -138,12 +138,24 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 	return 0;
 }
 
+/* Checks if the fp is valid.  We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+	if ((((unsigned long) fp) & 15) ||
+	    ((unsigned long)fp) > 0x100000000ULL - fplen)
+		return true;
+	return false;
+}
+
 void do_sigreturn32(struct pt_regs *regs)
 {
 	struct signal_frame32 __user *sf;
 	compat_uptr_t fpu_save;
 	compat_uptr_t rwin_save;
-	unsigned int psr;
+	unsigned int psr, ufp;
 	unsigned pc, npc;
 	sigset_t set;
 	compat_sigset_t seta;
@@ -158,11 +170,16 @@ void do_sigreturn32(struct pt_regs *regs)
 	sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 3))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
+		goto segv;
+
+	if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
 		goto segv;
 
-	if (get_user(pc, &sf->info.si_regs.pc) ||
+	if (__get_user(pc, &sf->info.si_regs.pc) ||
 	    __get_user(npc, &sf->info.si_regs.npc))
 		goto segv;
 
@@ -227,7 +244,7 @@ segv:
 asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 {
 	struct rt_signal_frame32 __user *sf;
-	unsigned int psr, pc, npc;
+	unsigned int psr, pc, npc, ufp;
 	compat_uptr_t fpu_save;
 	compat_uptr_t rwin_save;
 	sigset_t set;
@@ -242,11 +259,16 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 	sf = (struct rt_signal_frame32 __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 3))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv;
 
-	if (get_user(pc, &sf->regs.pc) || 
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
+		goto segv;
+
+	if (__get_user(pc, &sf->regs.pc) ||
 	    __get_user(npc, &sf->regs.npc))
 		goto segv;
 
@@ -307,14 +329,6 @@ segv:
 	force_sig(SIGSEGV, current);
 }
 
-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp, int fplen)
-{
-	if ((((unsigned long) fp) & 7) || ((unsigned long)fp) > 0x100000000ULL - fplen)
-		return 1;
-	return 0;
-}
-
 static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp;
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 52aa5e4ce5e7..c3c12efe0bc0 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -60,10 +60,22 @@ struct rt_signal_frame {
 #define SF_ALIGNEDSZ  (((sizeof(struct signal_frame) + 7) & (~7)))
 #define RT_ALIGNEDSZ  (((sizeof(struct rt_signal_frame) + 7) & (~7)))
 
+/* Checks if the fp is valid.  We always build signal frames which are
+ * 16-byte aligned, therefore we can always enforce that the restore
+ * frame has that property as well.
+ */
+static inline bool invalid_frame_pointer(void __user *fp, int fplen)
+{
+	if ((((unsigned long) fp) & 15) || !__access_ok((unsigned long)fp, fplen))
+		return true;
+
+	return false;
+}
+
 asmlinkage void do_sigreturn(struct pt_regs *regs)
 {
+	unsigned long up_psr, pc, npc, ufp;
 	struct signal_frame __user *sf;
-	unsigned long up_psr, pc, npc;
 	sigset_t set;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
@@ -77,10 +89,13 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
+	if (!invalid_frame_pointer(sf, sizeof(*sf)))
+		goto segv_and_exit;
+
+	if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
 		goto segv_and_exit;
 
-	if (((unsigned long) sf) & 3)
+	if (ufp & 0x7)
 		goto segv_and_exit;
 
 	err = __get_user(pc,  &sf->info.si_regs.pc);
@@ -127,7 +142,7 @@ segv_and_exit:
 asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 {
 	struct rt_signal_frame __user *sf;
-	unsigned int psr, pc, npc;
+	unsigned int psr, pc, npc, ufp;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
 	sigset_t set;
@@ -135,8 +150,13 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 
 	synchronize_user_stack();
 	sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP];
-	if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) ||
-	    (((unsigned long) sf) & 0x03))
+	if (!invalid_frame_pointer(sf, sizeof(*sf)))
+		goto segv;
+
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
+		goto segv;
+
+	if (ufp & 0x7)
 		goto segv;
 
 	err = __get_user(pc, &sf->regs.pc);
@@ -178,15 +198,6 @@ segv:
 	force_sig(SIGSEGV, current);
 }
 
-/* Checks if the fp is valid */
-static inline int invalid_frame_pointer(void __user *fp, int fplen)
-{
-	if ((((unsigned long) fp) & 7) || !__access_ok((unsigned long)fp, fplen))
-		return 1;
-
-	return 0;
-}
-
 static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp = regs->u_regs[UREG_FP];
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index d88beff47bab..5ee930c48f4c 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs)
 	unsigned char fenab;
 	int err;
 
-	flush_user_windows();
+	synchronize_user_stack();
 	if (get_thread_wsaved()					||
 	    (((unsigned long)ucp) & (sizeof(unsigned long)-1))	||
 	    (!__access_ok(ucp, sizeof(*ucp))))
@@ -234,6 +234,17 @@ do_sigsegv:
 	goto out;
 }
 
+/* Checks if the fp is valid.  We always build rt signal frames which
+ * are 16-byte aligned, therefore we can always enforce that the
+ * restore frame has that property as well.
+ */
+static bool invalid_frame_pointer(void __user *fp)
+{
+	if (((unsigned long) fp) & 15)
+		return true;
+	return false;
+}
+
 struct rt_signal_frame {
 	struct sparc_stackf	ss;
 	siginfo_t		info;
@@ -246,8 +257,8 @@ struct rt_signal_frame {
 
 void do_rt_sigreturn(struct pt_regs *regs)
 {
+	unsigned long tpc, tnpc, tstate, ufp;
 	struct rt_signal_frame __user *sf;
-	unsigned long tpc, tnpc, tstate;
 	__siginfo_fpu_t __user *fpu_save;
 	__siginfo_rwin_t __user *rwin_save;
 	sigset_t set;
@@ -261,10 +272,16 @@ void do_rt_sigreturn(struct pt_regs *regs)
 		(regs->u_regs [UREG_FP] + STACK_BIAS);
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (((unsigned long) sf) & 3)
+	if (invalid_frame_pointer(sf))
+		goto segv;
+
+	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
 		goto segv;
 
-	err = get_user(tpc, &sf->regs.tpc);
+	if ((ufp + STACK_BIAS) & 0x7)
+		goto segv;
+
+	err = __get_user(tpc, &sf->regs.tpc);
 	err |= __get_user(tnpc, &sf->regs.tnpc);
 	if (test_thread_flag(TIF_32BIT)) {
 		tpc &= 0xffffffff;
@@ -308,14 +325,6 @@ segv:
 	force_sig(SIGSEGV, current);
 }
 
-/* Checks if the fp is valid */
-static int invalid_frame_pointer(void __user *fp)
-{
-	if (((unsigned long) fp) & 15)
-		return 1;
-	return 0;
-}
-
 static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize)
 {
 	unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS;
diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c
index 0f6eebe71e6c..e5fe8cef9a69 100644
--- a/arch/sparc/kernel/sigutil_32.c
+++ b/arch/sparc/kernel/sigutil_32.c
@@ -48,6 +48,10 @@ int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 {
 	int err;
+
+	if (((unsigned long) fpu) & 3)
+		return -EFAULT;
+
 #ifdef CONFIG_SMP
 	if (test_tsk_thread_flag(current, TIF_USEDFPU))
 		regs->psr &= ~PSR_EF;
@@ -97,7 +101,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
 	struct thread_info *t = current_thread_info();
 	int i, wsaved, err;
 
-	__get_user(wsaved, &rp->wsaved);
+	if (((unsigned long) rp) & 3)
+		return -EFAULT;
+
+	get_user(wsaved, &rp->wsaved);
 	if (wsaved > NSWINS)
 		return -EFAULT;
 
diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c
index 387834a9c56a..36aadcbeac69 100644
--- a/arch/sparc/kernel/sigutil_64.c
+++ b/arch/sparc/kernel/sigutil_64.c
@@ -37,7 +37,10 @@ int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu)
 	unsigned long fprs;
 	int err;
 
-	err = __get_user(fprs, &fpu->si_fprs);
+	if (((unsigned long) fpu) & 7)
+		return -EFAULT;
+
+	err = get_user(fprs, &fpu->si_fprs);
 	fprs_write(0);
 	regs->tstate &= ~TSTATE_PEF;
 	if (fprs & FPRS_DL)
@@ -72,7 +75,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp)
 	struct thread_info *t = current_thread_info();
 	int i, wsaved, err;
 
-	__get_user(wsaved, &rp->wsaved);
+	if (((unsigned long) rp) & 7)
+		return -EFAULT;
+
+	get_user(wsaved, &rp->wsaved);
 	if (wsaved > NSWINS)
 		return -EFAULT;
 
diff --git a/arch/sparc/kernel/spiterrs.S b/arch/sparc/kernel/spiterrs.S
index c357e40ffd01..4a73009f66a5 100644
--- a/arch/sparc/kernel/spiterrs.S
+++ b/arch/sparc/kernel/spiterrs.S
@@ -85,8 +85,7 @@ __spitfire_cee_trap_continue:
 	ba,pt		%xcc, etraptl1
 	 rd		%pc, %g7
 
-	ba,pt		%xcc, 2f
-	 nop
+	ba,a,pt		%xcc, 2f
 
 1:	ba,pt		%xcc, etrap_irq
 	 rd		%pc, %g7
@@ -100,8 +99,7 @@ __spitfire_cee_trap_continue:
 	mov		%l5, %o2
 	call		spitfire_access_error
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_access_error,.-__spitfire_access_error
 
 	/* This is the trap handler entry point for ECC correctable
@@ -179,8 +177,7 @@ __spitfire_data_access_exception_tl1:
 	mov		%l5, %o2
 	call		spitfire_data_access_exception_tl1
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_data_access_exception_tl1,.-__spitfire_data_access_exception_tl1
 
 	.type		__spitfire_data_access_exception,#function
@@ -200,8 +197,7 @@ __spitfire_data_access_exception:
 	mov		%l5, %o2
 	call		spitfire_data_access_exception
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_data_access_exception,.-__spitfire_data_access_exception
 
 	.type		__spitfire_insn_access_exception_tl1,#function
@@ -220,8 +216,7 @@ __spitfire_insn_access_exception_tl1:
 	mov		%l5, %o2
 	call		spitfire_insn_access_exception_tl1
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_insn_access_exception_tl1,.-__spitfire_insn_access_exception_tl1
 
 	.type		__spitfire_insn_access_exception,#function
@@ -240,6 +235,5 @@ __spitfire_insn_access_exception:
 	mov		%l5, %o2
 	call		spitfire_insn_access_exception
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 	.size		__spitfire_insn_access_exception,.-__spitfire_insn_access_exception
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index bb0008927598..c4a1b5c40e4e 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -158,7 +158,25 @@ linux_syscall_trace32:
 	 add	%sp, PTREGS_OFF, %o0
 	brnz,pn	%o0, 3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ldx	[%sp + PTREGS_OFF + PT_V9_G1], %g1
+	sethi	%hi(sys_call_table32), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I0], %i0
+	or	%l7, %lo(sys_call_table32), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I1], %i1
+	ldx	[%sp + PTREGS_OFF + PT_V9_I2], %i2
+	ldx	[%sp + PTREGS_OFF + PT_V9_I3], %i3
+	ldx	[%sp + PTREGS_OFF + PT_V9_I4], %i4
+	ldx	[%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+	cmp	%g1, NR_syscalls
+	bgeu,pn	%xcc, 3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	srl	%i0, 0, %o0
+	lduw	[%l7 + %l4], %l7
 	srl	%i4, 0, %o4
 	srl	%i1, 0, %o1
 	srl	%i2, 0, %o2
@@ -170,7 +188,25 @@ linux_syscall_trace:
 	 add	%sp, PTREGS_OFF, %o0
 	brnz,pn	%o0, 3f
 	 mov	-ENOSYS, %o0
+
+	/* Syscall tracing can modify the registers.  */
+	ldx	[%sp + PTREGS_OFF + PT_V9_G1], %g1
+	sethi	%hi(sys_call_table64), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I0], %i0
+	or	%l7, %lo(sys_call_table64), %l7
+	ldx	[%sp + PTREGS_OFF + PT_V9_I1], %i1
+	ldx	[%sp + PTREGS_OFF + PT_V9_I2], %i2
+	ldx	[%sp + PTREGS_OFF + PT_V9_I3], %i3
+	ldx	[%sp + PTREGS_OFF + PT_V9_I4], %i4
+	ldx	[%sp + PTREGS_OFF + PT_V9_I5], %i5
+
+	cmp	%g1, NR_syscalls
+	bgeu,pn	%xcc, 3f
+	 mov	-ENOSYS, %o0
+
+	sll	%g1, 2, %l4
 	mov	%i0, %o0
+	lduw	[%l7 + %l4], %l7
 	mov	%i1, %o1
 	mov	%i2, %o2
 	mov	%i3, %o3
diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S
new file mode 100644
index 000000000000..5604a2b051d4
--- /dev/null
+++ b/arch/sparc/kernel/urtt_fill.S
@@ -0,0 +1,98 @@
+#include <asm/thread_info.h>
+#include <asm/trap_block.h>
+#include <asm/spitfire.h>
+#include <asm/ptrace.h>
+#include <asm/head.h>
+
+		.text
+		.align	8
+		.globl	user_rtt_fill_fixup_common
+user_rtt_fill_fixup_common:
+		rdpr	%cwp, %g1
+		add	%g1, 1, %g1
+		wrpr	%g1, 0x0, %cwp
+
+		rdpr	%wstate, %g2
+		sll	%g2, 3, %g2
+		wrpr	%g2, 0x0, %wstate
+
+		/* We know %canrestore and %otherwin are both zero.  */
+
+		sethi	%hi(sparc64_kern_pri_context), %g2
+		ldx	[%g2 + %lo(sparc64_kern_pri_context)], %g2
+		mov	PRIMARY_CONTEXT, %g1
+
+661:		stxa	%g2, [%g1] ASI_DMMU
+		.section .sun4v_1insn_patch, "ax"
+		.word	661b
+		stxa	%g2, [%g1] ASI_MMU
+		.previous
+
+		sethi	%hi(KERNBASE), %g1
+		flush	%g1
+
+		mov	%g4, %l4
+		mov	%g5, %l5
+		brnz,pn	%g3, 1f
+		 mov	%g3, %l3
+
+		or	%g4, FAULT_CODE_WINFIXUP, %g4
+		stb	%g4, [%g6 + TI_FAULT_CODE]
+		stx	%g5, [%g6 + TI_FAULT_ADDR]
+1:
+		mov	%g6, %l1
+		wrpr	%g0, 0x0, %tl
+
+661:		nop
+		.section		.sun4v_1insn_patch, "ax"
+		.word			661b
+		SET_GL(0)
+		.previous
+
+		wrpr	%g0, RTRAP_PSTATE, %pstate
+
+		mov	%l1, %g6
+		ldx	[%g6 + TI_TASK], %g4
+		LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3)
+
+		brnz,pn	%l3, 1f
+		 nop
+
+		call	do_sparc64_fault
+		 add	%sp, PTREGS_OFF, %o0
+		ba,pt	%xcc, rtrap
+		 nop
+
+1:		cmp	%g3, 2
+		bne,pn	%xcc, 2f
+		 nop
+
+		sethi	%hi(tlb_type), %g1
+		lduw	[%g1 + %lo(tlb_type)], %g1
+		cmp	%g1, 3
+		bne,pt	%icc, 1f
+		 add	%sp, PTREGS_OFF, %o0
+		mov	%l4, %o2
+		call	sun4v_do_mna
+		 mov	%l5, %o1
+		ba,a,pt	%xcc, rtrap
+1:		mov	%l4, %o1
+		mov	%l5, %o2
+		call	mem_address_unaligned
+		 nop
+		ba,a,pt	%xcc, rtrap
+
+2:		sethi	%hi(tlb_type), %g1
+		mov	%l4, %o1
+		lduw	[%g1 + %lo(tlb_type)], %g1
+		mov	%l5, %o2
+		cmp	%g1, 3
+		bne,pt	%icc, 1f
+		 add	%sp, PTREGS_OFF, %o0
+		call	sun4v_data_access_exception
+		 nop
+		ba,a,pt	%xcc, rtrap
+
+1:		call	spitfire_data_access_exception
+		 nop
+		ba,a,pt	%xcc, rtrap
diff --git a/arch/sparc/kernel/utrap.S b/arch/sparc/kernel/utrap.S
index b7f0f3f3a909..c731e8023d3e 100644
--- a/arch/sparc/kernel/utrap.S
+++ b/arch/sparc/kernel/utrap.S
@@ -11,8 +11,7 @@ utrap_trap:		/* %g3=handler,%g4=level */
 	mov		%l4, %o1
         call		bad_trap
 	 add		%sp, PTREGS_OFF, %o0
-	ba,pt		%xcc, rtrap
-	 nop
+	ba,a,pt		%xcc, rtrap
 
 invoke_utrap:
 	sllx		%g3, 3, %g3
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index f1a2f688b28a..4a41d412dd3d 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -33,6 +33,10 @@ ENTRY(_start)
 jiffies = jiffies_64;
 #endif
 
+#ifdef CONFIG_SPARC64
+ASSERT((swapper_tsb == 0x0000000000408000), "Error: sparc64 early assembler too large")
+#endif
+
 SECTIONS
 {
 #ifdef CONFIG_SPARC64
diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S
index 1e67ce958369..855019a8590e 100644
--- a/arch/sparc/kernel/winfixup.S
+++ b/arch/sparc/kernel/winfixup.S
@@ -32,8 +32,7 @@ fill_fixup:
 	 rd	%pc, %g7
 	call	do_sparc64_fault
 	 add	%sp, PTREGS_OFF, %o0
-	ba,pt	%xcc, rtrap
-	 nop
+	ba,a,pt	%xcc, rtrap
 
 	/* Be very careful about usage of the trap globals here.
 	 * You cannot touch %g5 as that has the fault information.
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 131eaf4ad7f5..364d093f46c6 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -176,17 +176,31 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
 	int i;
+	pte_t orig[2];
+	unsigned long nptes;
 
 	if (!pte_present(*ptep) && pte_present(entry))
 		mm->context.huge_pte_count++;
 
 	addr &= HPAGE_MASK;
-	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
-		set_pte_at(mm, addr, ptep, entry);
+
+	nptes = 1 << HUGETLB_PAGE_ORDER;
+	orig[0] = *ptep;
+	orig[1] = *(ptep + nptes / 2);
+	for (i = 0; i < nptes; i++) {
+		*ptep = entry;
 		ptep++;
 		addr += PAGE_SIZE;
 		pte_val(entry) += PAGE_SIZE;
 	}
+
+	/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, orig[1], 0);
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, orig[0], 0);
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
@@ -194,19 +208,28 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 {
 	pte_t entry;
 	int i;
+	unsigned long nptes;
 
 	entry = *ptep;
 	if (pte_present(entry))
 		mm->context.huge_pte_count--;
 
 	addr &= HPAGE_MASK;
-
-	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
-		pte_clear(mm, addr, ptep);
+	nptes = 1 << HUGETLB_PAGE_ORDER;
+	for (i = 0; i < nptes; i++) {
+		*ptep = __pte(0UL);
 		addr += PAGE_SIZE;
 		ptep++;
 	}
 
+	/* Issue TLB flush at REAL_HPAGE_SIZE boundaries */
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
+	addr -= REAL_HPAGE_SIZE;
+	ptep -= nptes / 2;
+	maybe_tlb_batch_add(mm, addr, ptep, entry, 0);
+
 	return entry;
 }
 
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3025bd57f7ab..3c4b8975fa76 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -324,18 +324,6 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde
 	tsb_insert(tsb, tag, tte);
 }
 
-#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline bool is_hugetlb_pte(pte_t pte)
-{
-	if ((tlb_type == hypervisor &&
-	     (pte_val(pte) & _PAGE_SZALL_4V) == _PAGE_SZHUGE_4V) ||
-	    (tlb_type != hypervisor &&
-	     (pte_val(pte) & _PAGE_SZALL_4U) == _PAGE_SZHUGE_4U))
-		return true;
-	return false;
-}
-#endif
-
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 {
 	struct mm_struct *mm;
@@ -1267,13 +1255,6 @@ static int __init numa_parse_mdesc(void)
 	int i, j, err, count;
 	u64 node;
 
-	/* Some sane defaults for numa latency values */
-	for (i = 0; i < MAX_NUMNODES; i++) {
-		for (j = 0; j < MAX_NUMNODES; j++)
-			numa_latency[i][j] = (i == j) ?
-				LOCAL_DISTANCE : REMOTE_DISTANCE;
-	}
-
 	node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
 	if (node == MDESC_NODE_NULL) {
 		mdesc_release(md);
@@ -1369,10 +1350,18 @@ static int __init numa_parse_sun4u(void)
 
 static int __init bootmem_init_numa(void)
 {
+	int i, j;
 	int err = -1;
 
 	numadbg("bootmem_init_numa()\n");
 
+	/* Some sane defaults for numa latency values */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		for (j = 0; j < MAX_NUMNODES; j++)
+			numa_latency[i][j] = (i == j) ?
+				LOCAL_DISTANCE : REMOTE_DISTANCE;
+	}
+
 	if (numa_enabled) {
 		if (tlb_type == hypervisor)
 			err = numa_parse_mdesc();
@@ -2832,9 +2821,10 @@ void hugetlb_setup(struct pt_regs *regs)
 	 * the Data-TLB for huge pages.
 	 */
 	if (tlb_type == cheetah_plus) {
+		bool need_context_reload = false;
 		unsigned long ctx;
 
-		spin_lock(&ctx_alloc_lock);
+		spin_lock_irq(&ctx_alloc_lock);
 		ctx = mm->context.sparc64_ctx_val;
 		ctx &= ~CTX_PGSZ_MASK;
 		ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
@@ -2853,9 +2843,12 @@ void hugetlb_setup(struct pt_regs *regs)
 			 * also executing in this address space.
 			 */
 			mm->context.sparc64_ctx_val = ctx;
-			on_each_cpu(context_reload, mm, 0);
+			need_context_reload = true;
 		}
-		spin_unlock(&ctx_alloc_lock);
+		spin_unlock_irq(&ctx_alloc_lock);
+
+		if (need_context_reload)
+			on_each_cpu(context_reload, mm, 0);
 	}
 }
 #endif
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 9df2190c097e..f81cd9736700 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -67,7 +67,7 @@ void arch_leave_lazy_mmu_mode(void)
 }
 
 static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
-			      bool exec)
+			      bool exec, bool huge)
 {
 	struct tlb_batch *tb = &get_cpu_var(tlb_batch);
 	unsigned long nr;
@@ -84,13 +84,21 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 	}
 
 	if (!tb->active) {
-		flush_tsb_user_page(mm, vaddr);
+		flush_tsb_user_page(mm, vaddr, huge);
 		global_flush_tlb_page(mm, vaddr);
 		goto out;
 	}
 
-	if (nr == 0)
+	if (nr == 0) {
 		tb->mm = mm;
+		tb->huge = huge;
+	}
+
+	if (tb->huge != huge) {
+		flush_tlb_pending();
+		tb->huge = huge;
+		nr = 0;
+	}
 
 	tb->vaddrs[nr] = vaddr;
 	tb->tlb_nr = ++nr;
@@ -104,6 +112,8 @@ out:
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm)
 {
+	bool huge = is_hugetlb_pte(orig);
+
 	if (tlb_type != hypervisor &&
 	    pte_dirty(orig)) {
 		unsigned long paddr, pfn = pte_pfn(orig);
@@ -129,7 +139,7 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 
 no_cache_flush:
 	if (!fullmm)
-		tlb_batch_add_one(mm, vaddr, pte_exec(orig));
+		tlb_batch_add_one(mm, vaddr, pte_exec(orig), huge);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -145,7 +155,7 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
 		if (pte_val(*pte) & _PAGE_VALID) {
 			bool exec = pte_exec(*pte);
 
-			tlb_batch_add_one(mm, vaddr, exec);
+			tlb_batch_add_one(mm, vaddr, exec, false);
 		}
 		pte++;
 		vaddr += PAGE_SIZE;
@@ -185,8 +195,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			pte_t orig_pte = __pte(pmd_val(orig));
 			bool exec = pte_exec(orig_pte);
 
-			tlb_batch_add_one(mm, addr, exec);
-			tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec);
+			tlb_batch_add_one(mm, addr, exec, true);
+			tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
+					true);
 		} else {
 			tlb_batch_pmd_scan(mm, addr, orig);
 		}
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index a06576683c38..a0604a493a36 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -76,14 +76,15 @@ void flush_tsb_user(struct tlb_batch *tb)
 
 	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(tb, PAGE_SHIFT, base, nentries);
-
+	if (!tb->huge) {
+		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(tb, PAGE_SHIFT, base, nentries);
+	}
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+	if (tb->huge && 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)
@@ -94,20 +95,21 @@ 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)
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge)
 {
 	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 (!huge) {
+		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) {
+	if (huge && 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)