Linux-libre 4.6.3-gnupck-4.6.3-gnu

32 files changed, 417 insertions, 201 deletions

diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ef9119f74..4d9375814 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -733,8 +733,8 @@ static int vfp_set(struct task_struct *target,
 	if (ret)
 		return ret;
 
-	vfp_flush_hwstate(thread);
 	thread->vfpstate.hard = new_vfp;
+	vfp_flush_hwstate(thread);
 
 	return 0;
 }
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 24ed037f0..83d48a599 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -160,14 +160,14 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define STACK_RND_MASK			(0x3ffff >> (PAGE_SHIFT - 12))
 #endif
 
-#ifdef CONFIG_COMPAT
-
 #ifdef __AARCH64EB__
 #define COMPAT_ELF_PLATFORM		("v8b")
 #else
 #define COMPAT_ELF_PLATFORM		("v8l")
 #endif
 
+#ifdef CONFIG_COMPAT
+
 #define COMPAT_ELF_ET_DYN_BASE		(2 * TASK_SIZE_32 / 3)
 
 /* AArch32 registers. */
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index f0c3fb7ec..2d2d7cb04 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -22,6 +22,8 @@
 
 #include <linux/bitops.h>
 #include <linux/bug.h>
+#include <linux/compat.h>
+#include <linux/elf.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/personality.h>
@@ -104,6 +106,7 @@ static const char *const compat_hwcap2_str[] = {
 static int c_show(struct seq_file *m, void *v)
 {
 	int i, j;
+	bool compat = personality(current->personality) == PER_LINUX32;
 
 	for_each_online_cpu(i) {
 		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
@@ -115,6 +118,9 @@ static int c_show(struct seq_file *m, void *v)
 		 * "processor".  Give glibc what it expects.
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
+		if (compat)
+			seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
+				   MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);
 
 		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
 			   loops_per_jiffy / (500000UL/HZ),
@@ -127,7 +133,7 @@ static int c_show(struct seq_file *m, void *v)
 		 * software which does already (at least for 32-bit).
 		 */
 		seq_puts(m, "Features\t:");
-		if (personality(current->personality) == PER_LINUX32) {
+		if (compat) {
 #ifdef CONFIG_COMPAT
 			for (j = 0; compat_hwcap_str[j]; j++)
 				if (compat_elf_hwcap & (1 << j))
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index fff7cd42b..3129df9d3 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -190,12 +190,11 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 			if (!(vcpu->arch.vgic_cpu.live_lrs & (1UL << i)))
 				continue;
 
-			if (cpu_if->vgic_elrsr & (1 << i)) {
+			if (cpu_if->vgic_elrsr & (1 << i))
 				cpu_if->vgic_lr[i] &= ~ICH_LR_STATE;
-				continue;
-			}
+			else
+				cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
 
-			cpu_if->vgic_lr[i] = __gic_v3_get_lr(i);
 			__gic_v3_set_lr(0, i);
 		}
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 3ae4a28c4..10b79e9e8 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -109,7 +109,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	 * PTE_RDONLY is cleared by default in the asm below, so set it in
 	 * back if necessary (read-only or clean PTE).
 	 */
-	if (!pte_write(entry) || !dirty)
+	if (!pte_write(entry) || !pte_sw_dirty(entry))
 		pte_val(entry) |= PTE_RDONLY;
 
 	/*
diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c
index d7c0acb35..8d49614d6 100644
--- a/arch/parisc/kernel/unaligned.c
+++ b/arch/parisc/kernel/unaligned.c
@@ -666,7 +666,7 @@ void handle_unaligned(struct pt_regs *regs)
 		break;
 	}
 
-	if (modify && R1(regs->iir))
+	if (ret == 0 && modify && R1(regs->iir))
 		regs->gr[R1(regs->iir)] = newbase;
 
 
@@ -677,6 +677,14 @@ void handle_unaligned(struct pt_regs *regs)
 
 	if (ret)
 	{
+		/*
+		 * The unaligned handler failed.
+		 * If we were called by __get_user() or __put_user() jump
+		 * to it's exception fixup handler instead of crashing.
+		 */
+		if (!user_mode(regs) && fixup_exception(regs))
+			return;
+
 		printk(KERN_CRIT "Unaligned handler failed, ret = %d\n", ret);
 		die_if_kernel("Unaligned data reference", regs, 28);
 
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index f5f4c66bb..166d86317 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -715,7 +715,7 @@
 #define   MMCR0_FCWAIT	0x00000002UL /* freeze counter in WAIT state */
 #define   MMCR0_FCHV	0x00000001UL /* freeze conditions in hypervisor mode */
 #define SPRN_MMCR1	798
-#define SPRN_MMCR2	769
+#define SPRN_MMCR2	785
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
 #define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
@@ -752,13 +752,13 @@
 #define SPRN_PMC6	792
 #define SPRN_PMC7	793
 #define SPRN_PMC8	794
-#define SPRN_SIAR	780
-#define SPRN_SDAR	781
 #define SPRN_SIER	784
 #define   SIER_SIPR		0x2000000	/* Sampled MSR_PR */
 #define   SIER_SIHV		0x1000000	/* Sampled MSR_HV */
 #define   SIER_SIAR_VALID	0x0400000	/* SIAR contents valid */
 #define   SIER_SDAR_VALID	0x0200000	/* SDAR contents valid */
+#define SPRN_SIAR	796
+#define SPRN_SDAR	797
 #define SPRN_TACR	888
 #define SPRN_TCSCR	889
 #define SPRN_CSIGR	890
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index da5192590..ccd2037c7 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -656,6 +656,7 @@ unsigned char ibm_architecture_vec[] = {
 	W(0xffff0000), W(0x003e0000),	/* POWER6 */
 	W(0xffff0000), W(0x003f0000),	/* POWER7 */
 	W(0xffff0000), W(0x004b0000),	/* POWER8E */
+	W(0xffff0000), W(0x004c0000),   /* POWER8NVL */
 	W(0xffff0000), W(0x004d0000),	/* POWER8 */
 	W(0xffffffff), W(0x0f000004),	/* all 2.07-compliant */
 	W(0xffffffff), W(0x0f000003),	/* all 2.06-compliant */
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 7635b1c6b..f4acba25f 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -159,6 +159,19 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = {
 	},
 };
 
+/*
+ * 'R' and 'C' update notes:
+ *  - Under pHyp or KVM, the updatepp path will not set C, thus it *will*
+ *     create writeable HPTEs without C set, because the hcall H_PROTECT
+ *     that we use in that case will not update C
+ *  - The above is however not a problem, because we also don't do that
+ *     fancy "no flush" variant of eviction and we use H_REMOVE which will
+ *     do the right thing and thus we don't have the race I described earlier
+ *
+ *    - Under bare metal,  we do have the race, so we need R and C set
+ *    - We make sure R is always set and never lost
+ *    - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping
+ */
 unsigned long htab_convert_pte_flags(unsigned long pteflags)
 {
 	unsigned long rflags = 0;
@@ -180,9 +193,14 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
 			rflags |= 0x1;
 	}
 	/*
-	 * Always add "C" bit for perf. Memory coherence is always enabled
+	 * We can't allow hardware to update hpte bits. Hence always
+	 * set 'R' bit and set 'C' if it is a write fault
+	 * Memory coherence is always enabled
 	 */
-	rflags |=  HPTE_R_C | HPTE_R_M;
+	rflags |=  HPTE_R_R | HPTE_R_M;
+
+	if (pteflags & _PAGE_DIRTY)
+		rflags |= HPTE_R_C;
 	/*
 	 * Add in WIG bits
 	 */
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index ac3ffd97e..405baaf96 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -615,29 +615,50 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
 {
 	int config_addr;
 	int ret;
+	/* Waiting 0.2s maximum before skipping configuration */
+	int max_wait = 200;
 
 	/* Figure out the PE address */
 	config_addr = pe->config_addr;
 	if (pe->addr)
 		config_addr = pe->addr;
 
-	/* Use new configure-pe function, if supported */
-	if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
-		ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
-				config_addr, BUID_HI(pe->phb->buid),
-				BUID_LO(pe->phb->buid));
-	} else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
-		ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
-				config_addr, BUID_HI(pe->phb->buid),
-				BUID_LO(pe->phb->buid));
-	} else {
-		return -EFAULT;
-	}
+	while (max_wait > 0) {
+		/* Use new configure-pe function, if supported */
+		if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
+			ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
+					config_addr, BUID_HI(pe->phb->buid),
+					BUID_LO(pe->phb->buid));
+		} else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
+			ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
+					config_addr, BUID_HI(pe->phb->buid),
+					BUID_LO(pe->phb->buid));
+		} else {
+			return -EFAULT;
+		}
 
-	if (ret)
-		pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
-			__func__, pe->phb->global_number, pe->addr, ret);
+		if (!ret)
+			return ret;
+
+		/*
+		 * If RTAS returns a delay value that's above 100ms, cut it
+		 * down to 100ms in case firmware made a mistake.  For more
+		 * on how these delay values work see rtas_busy_delay_time
+		 */
+		if (ret > RTAS_EXTENDED_DELAY_MIN+2 &&
+		    ret <= RTAS_EXTENDED_DELAY_MAX)
+			ret = RTAS_EXTENDED_DELAY_MIN+2;
+
+		max_wait -= rtas_busy_delay_time(ret);
+
+		if (max_wait < 0)
+			break;
+
+		rtas_busy_delay(ret);
+	}
 
+	pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n",
+		__func__, pe->phb->global_number, pe->addr, ret);
 	return ret;
 }
 
diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h
index f010c93a8..fda605dbc 100644
--- a/arch/s390/net/bpf_jit.h
+++ b/arch/s390/net/bpf_jit.h
@@ -37,7 +37,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  *	      |		      |     |
  *	      +---------------+     |
  *	      | 8 byte skbp   |     |
- * R15+170 -> +---------------+     |
+ * R15+176 -> +---------------+     |
  *	      | 8 byte hlen   |     |
  * R15+168 -> +---------------+     |
  *	      | 4 byte align  |     |
@@ -58,7 +58,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
 #define STK_OFF		(STK_SPACE - STK_160_UNUSED)
 #define STK_OFF_TMP	160	/* Offset of tmp buffer on stack */
 #define STK_OFF_HLEN	168	/* Offset of SKB header length on stack */
-#define STK_OFF_SKBP	170	/* Offset of SKB pointer on stack */
+#define STK_OFF_SKBP	176	/* Offset of SKB pointer on stack */
 
 #define STK_OFF_R6	(160 - 11 * 8)	/* Offset of r6 on stack */
 #define STK_OFF_TCCNT	(160 - 12 * 8)	/* Offset of tail_call_cnt on stack */
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 3c0bfc1f2..2662fcc67 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -45,7 +45,7 @@ struct bpf_jit {
 	int labels[1];		/* Labels for local jumps */
 };
 
-#define BPF_SIZE_MAX	0x7ffff	/* Max size for program (20 bit signed displ) */
+#define BPF_SIZE_MAX	0xffff	/* Max size for program (16 bit branches) */
 
 #define SEEN_SKB	1	/* skb access */
 #define SEEN_MEM	2	/* use mem[] for temporary storage */
@@ -446,7 +446,7 @@ static void bpf_jit_prologue(struct bpf_jit *jit)
 		emit_load_skb_data_hlen(jit);
 	if (jit->seen & SEEN_SKB_CHANGE)
 		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
-		EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15,
+		EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
 			      STK_OFF_SKBP);
 }
 
diff --git a/arch/sparc/include/asm/head_64.h b/arch/sparc/include/asm/head_64.h
index 10e9dabc4..f0700cfee 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 f089cfa24..5a189bf3c 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)
@@ -858,6 +874,19 @@ 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,
@@ -874,15 +903,7 @@ 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 dea1cfa21..a8e192e90 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 71b5a6752..781b9f1db 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 7cf9c6ea3..fdb13327f 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/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index d08bdaffd..216948ca4 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 3c25241fa..ebd0bfe25 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 int 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 52aa5e4ce..c3c12efe0 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 39aaec173..5ee930c48 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -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 0f6eebe71..e5fe8cef9 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 387834a9c..36aadcbea 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/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S
new file mode 100644
index 000000000..5604a2b05
--- /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/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 4977800e9..ba52e6466 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 09e838801..14bb0d5ed 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;
@@ -2836,9 +2824,10 @@ 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;
@@ -2857,9 +2846,12 @@ 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 9df2190c0..f81cd9736 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 a06576683..a0604a493 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)
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 88d0ae205..8a121991e 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -27,8 +27,7 @@
 static int max_ypos = 25, max_xpos = 80;
 static int current_ypos = 25, current_xpos;
 
-static void early_vga_write(struct console *con, const char *str, unsigned n,
-                            unsigned int loglevel)
+static void early_vga_write(struct console *con, const char *str, unsigned n)
 {
 	char c;
 	int  i, k, j;
@@ -119,8 +118,7 @@ static int early_serial_putc(unsigned char ch)
 	return timeout ? 0 : -1;
 }
 
-static void early_serial_write(struct console *con, const char *s, unsigned n,
-                               unsigned int loglevel)
+static void early_serial_write(struct console *con, const char *s, unsigned n)
 {
 	while (*s && n-- > 0) {
 		if (*s == '\n')
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 06cbe2586..87bd6b6bf 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -95,6 +95,12 @@ static inline void cond_local_irq_disable(struct pt_regs *regs)
 		local_irq_disable();
 }
 
+/*
+ * In IST context, we explicitly disable preemption.  This serves two
+ * purposes: it makes it much less likely that we would accidentally
+ * schedule in IST context and it will force a warning if we somehow
+ * manage to schedule by accident.
+ */
 void ist_enter(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
@@ -109,13 +115,7 @@ void ist_enter(struct pt_regs *regs)
 		rcu_nmi_enter();
 	}
 
-	/*
-	 * We are atomic because we're on the IST stack; or we're on
-	 * x86_32, in which case we still shouldn't schedule; or we're
-	 * on x86_64 and entered from user mode, in which case we're
-	 * still atomic unless ist_begin_non_atomic is called.
-	 */
-	preempt_count_add(HARDIRQ_OFFSET);
+	preempt_disable();
 
 	/* This code is a bit fragile.  Test it. */
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
@@ -123,7 +123,7 @@ void ist_enter(struct pt_regs *regs)
 
 void ist_exit(struct pt_regs *regs)
 {
-	preempt_count_sub(HARDIRQ_OFFSET);
+	preempt_enable_no_resched();
 
 	if (!user_mode(regs))
 		rcu_nmi_exit();
@@ -154,7 +154,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
 	BUG_ON((unsigned long)(current_top_of_stack() -
 			       current_stack_pointer()) >= THREAD_SIZE);
 
-	preempt_count_sub(HARDIRQ_OFFSET);
+	preempt_enable_no_resched();
 }
 
 /**
@@ -164,7 +164,7 @@ void ist_begin_non_atomic(struct pt_regs *regs)
  */
 void ist_end_non_atomic(void)
 {
-	preempt_count_add(HARDIRQ_OFFSET);
+	preempt_disable();
 }
 
 static nokprobe_inline int
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9b7798c7b..6b9701bab 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3032,6 +3032,11 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 	if (dbgregs->flags)
 		return -EINVAL;
 
+	if (dbgregs->dr6 & ~0xffffffffull)
+		return -EINVAL;
+	if (dbgregs->dr7 & ~0xffffffffull)
+		return -EINVAL;
+
 	memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
 	kvm_update_dr0123(vcpu);
 	vcpu->arch.dr6 = dbgregs->dr6;
diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
index 5eb772c0d..524142117 100644
--- a/arch/x86/platform/efi/early_printk.c
+++ b/arch/x86/platform/efi/early_printk.c
@@ -124,8 +124,7 @@ static void early_efi_write_char(u32 *dst, unsigned char c, unsigned int h)
 }
 
 static void
-early_efi_write(struct console *con, const char *str, unsigned int num,
-		unsigned int loglevel)
+early_efi_write(struct console *con, const char *str, unsigned int num)
 {
 	struct screen_info *si;
 	unsigned int len;