Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts were simply overlapping changes.  In the net/ipv4/route.c
case the code had simply moved around a little bit and the same fix
was made in both 'net' and 'net-next'.

In the net/sched/sch_generic.c case a fix in 'net' happened at
the same time that a new argument was added to qdisc_hash_add().

Signed-off-by: David S. Miller <davem@davemloft.net>

69 files changed, 563 insertions, 367 deletions

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 0b961093ca5c..6d76e528ab8f 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1290,7 +1290,7 @@ SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p)
 	/* copy relevant bits of struct timex. */
 	if (copy_from_user(&txc, txc_p, offsetof(struct timex32, time)) ||
 	    copy_from_user(&txc.tick, &txc_p->tick, sizeof(struct timex32) - 
-			   offsetof(struct timex32, time)))
+			   offsetof(struct timex32, tick)))
 	  return -EFAULT;
 
 	ret = do_adjtimex(&txc);	
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 96dba7cd8be7..314eb6abe1ff 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -1124,6 +1124,9 @@ static void cpu_hyp_reinit(void)
 		if (__hyp_get_vectors() == hyp_default_vectors)
 			cpu_init_hyp_mode(NULL);
 	}
+
+	if (vgic_present)
+		kvm_vgic_init_cpu_hardware();
 }
 
 static void cpu_hyp_reset(void)
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 962616fd4ddd..582a972371cf 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -292,11 +292,18 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 	phys_addr_t addr = start, end = start + size;
 	phys_addr_t next;
 
+	assert_spin_locked(&kvm->mmu_lock);
 	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
 	do {
 		next = stage2_pgd_addr_end(addr, end);
 		if (!stage2_pgd_none(*pgd))
 			unmap_stage2_puds(kvm, pgd, addr, next);
+		/*
+		 * If the range is too large, release the kvm->mmu_lock
+		 * to prevent starvation and lockup detector warnings.
+		 */
+		if (next != end)
+			cond_resched_lock(&kvm->mmu_lock);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -803,6 +810,7 @@ void stage2_unmap_vm(struct kvm *kvm)
 	int idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
+	down_read(&current->mm->mmap_sem);
 	spin_lock(&kvm->mmu_lock);
 
 	slots = kvm_memslots(kvm);
@@ -810,6 +818,7 @@ void stage2_unmap_vm(struct kvm *kvm)
 		stage2_unmap_memslot(kvm, memslot);
 
 	spin_unlock(&kvm->mmu_lock);
+	up_read(&current->mm->mmap_sem);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -829,7 +838,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
 	if (kvm->arch.pgd == NULL)
 		return;
 
+	spin_lock(&kvm->mmu_lock);
 	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+	spin_unlock(&kvm->mmu_lock);
+
 	/* Free the HW pgd, one page at a time */
 	free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE);
 	kvm->arch.pgd = NULL;
@@ -1801,6 +1813,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	    (KVM_PHYS_SIZE >> PAGE_SHIFT))
 		return -EFAULT;
 
+	down_read(&current->mm->mmap_sem);
 	/*
 	 * A memory region could potentially cover multiple VMAs, and any holes
 	 * between them, so iterate over all of them to find out if we can map
@@ -1844,8 +1857,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 			pa += vm_start - vma->vm_start;
 
 			/* IO region dirty page logging not allowed */
-			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES)
-				return -EINVAL;
+			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+				ret = -EINVAL;
+				goto out;
+			}
 
 			ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
 						    vm_end - vm_start,
@@ -1857,7 +1872,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	} while (hva < reg_end);
 
 	if (change == KVM_MR_FLAGS_ONLY)
-		return ret;
+		goto out;
 
 	spin_lock(&kvm->mmu_lock);
 	if (ret)
@@ -1865,6 +1880,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	else
 		stage2_flush_memslot(kvm, memslot);
 	spin_unlock(&kvm->mmu_lock);
+out:
+	up_read(&current->mm->mmap_sem);
 	return ret;
 }
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 63eabb06f9f1..475811f5383a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -935,13 +935,31 @@ static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_add
 	__arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
 }
 
+/*
+ * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
+ * that the intention is to allow exporting memory allocated via the
+ * coherent DMA APIs through the dma_buf API, which only accepts a
+ * scattertable.  This presents a couple of problems:
+ * 1. Not all memory allocated via the coherent DMA APIs is backed by
+ *    a struct page
+ * 2. Passing coherent DMA memory into the streaming APIs is not allowed
+ *    as we will try to flush the memory through a different alias to that
+ *    actually being used (and the flushes are redundant.)
+ */
 int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 		 void *cpu_addr, dma_addr_t handle, size_t size,
 		 unsigned long attrs)
 {
-	struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
+	unsigned long pfn = dma_to_pfn(dev, handle);
+	struct page *page;
 	int ret;
 
+	/* If the PFN is not valid, we do not have a struct page */
+	if (!pfn_valid(pfn))
+		return -ENXIO;
+
+	page = pfn_to_page(pfn);
+
 	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
 	if (unlikely(ret))
 		return ret;
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 3b5c7aaf9c76..33a45bd96860 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -303,7 +303,10 @@ static inline void set_vbar(unsigned long val)
  */
 static inline bool security_extensions_enabled(void)
 {
-	return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+	/* Check CPUID Identification Scheme before ID_PFR1 read */
+	if ((read_cpuid_id() & 0x000f0000) == 0x000f0000)
+		return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+	return 0;
 }
 
 static unsigned long __init setup_vectors_base(void)
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index b6dc9d838a9a..ad1f4e6a9e33 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -266,11 +266,20 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 #endif
 
 	if (p) {
-		if (cur) {
+		if (!p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
+			/*
+			 * Probe hit but conditional execution check failed,
+			 * so just skip the instruction and continue as if
+			 * nothing had happened.
+			 * In this case, we can skip recursing check too.
+			 */
+			singlestep_skip(p, regs);
+		} else if (cur) {
 			/* Kprobe is pending, so we're recursing. */
 			switch (kcb->kprobe_status) {
 			case KPROBE_HIT_ACTIVE:
 			case KPROBE_HIT_SSDONE:
+			case KPROBE_HIT_SS:
 				/* A pre- or post-handler probe got us here. */
 				kprobes_inc_nmissed_count(p);
 				save_previous_kprobe(kcb);
@@ -279,11 +288,16 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				singlestep(p, regs, kcb);
 				restore_previous_kprobe(kcb);
 				break;
+			case KPROBE_REENTER:
+				/* A nested probe was hit in FIQ, it is a BUG */
+				pr_warn("Unrecoverable kprobe detected at %p.\n",
+					p->addr);
+				/* fall through */
 			default:
 				/* impossible cases */
 				BUG();
 			}
-		} else if (p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
+		} else {
 			/* Probe hit and conditional execution check ok. */
 			set_current_kprobe(p);
 			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
@@ -304,13 +318,6 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				}
 				reset_current_kprobe();
 			}
-		} else {
-			/*
-			 * Probe hit but conditional execution check failed,
-			 * so just skip the instruction and continue as if
-			 * nothing had happened.
-			 */
-			singlestep_skip(p, regs);
 		}
 	} else if (cur) {
 		/* We probably hit a jprobe.  Call its break handler. */
@@ -434,6 +441,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	struct hlist_node *tmp;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+	kprobe_opcode_t *correct_ret_addr = NULL;
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
@@ -456,14 +464,34 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			/* another task is sharing our hash bucket */
 			continue;
 
+		orig_ret_address = (unsigned long)ri->ret_addr;
+
+		if (orig_ret_address != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+	correct_ret_addr = ri->ret_addr;
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+
+		orig_ret_address = (unsigned long)ri->ret_addr;
 		if (ri->rp && ri->rp->handler) {
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
 			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
 			__this_cpu_write(current_kprobe, NULL);
 		}
 
-		orig_ret_address = (unsigned long)ri->ret_addr;
 		recycle_rp_inst(ri, &empty_rp);
 
 		if (orig_ret_address != trampoline_address)
@@ -475,7 +503,6 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			break;
 	}
 
-	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	kretprobe_hash_unlock(current, &flags);
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c
index c893726aa52d..1c98a87786ca 100644
--- a/arch/arm/probes/kprobes/test-core.c
+++ b/arch/arm/probes/kprobes/test-core.c
@@ -977,7 +977,10 @@ static void coverage_end(void)
 void __naked __kprobes_test_case_start(void)
 {
 	__asm__ __volatile__ (
-		"stmdb	sp!, {r4-r11}				\n\t"
+		"mov	r2, sp					\n\t"
+		"bic	r3, r2, #7				\n\t"
+		"mov	sp, r3					\n\t"
+		"stmdb	sp!, {r2-r11}				\n\t"
 		"sub	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
 		"bic	r0, lr, #1  @ r0 = inline data		\n\t"
 		"mov	r1, sp					\n\t"
@@ -997,7 +1000,8 @@ void __naked __kprobes_test_case_end_32(void)
 		"movne	pc, r0					\n\t"
 		"mov	r0, r4					\n\t"
 		"add	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
-		"ldmia	sp!, {r4-r11}				\n\t"
+		"ldmia	sp!, {r2-r11}				\n\t"
+		"mov	sp, r2					\n\t"
 		"mov	pc, r0					\n\t"
 	);
 }
@@ -1013,7 +1017,8 @@ void __naked __kprobes_test_case_end_16(void)
 		"bxne	r0					\n\t"
 		"mov	r0, r4					\n\t"
 		"add	sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
-		"ldmia	sp!, {r4-r11}				\n\t"
+		"ldmia	sp!, {r2-r11}				\n\t"
+		"mov	sp, r2					\n\t"
 		"bx	r0					\n\t"
 	);
 }
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 4bf899fb451b..1b35b8bddbfb 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -42,7 +42,20 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
-static const char *fault_name(unsigned int esr);
+struct fault_info {
+	int	(*fn)(unsigned long addr, unsigned int esr,
+		      struct pt_regs *regs);
+	int	sig;
+	int	code;
+	const char *name;
+};
+
+static const struct fault_info fault_info[];
+
+static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
+{
+	return fault_info + (esr & 63);
+}
 
 #ifdef CONFIG_KPROBES
 static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
@@ -197,10 +210,12 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 			    struct pt_regs *regs)
 {
 	struct siginfo si;
+	const struct fault_info *inf;
 
 	if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
+		inf = esr_to_fault_info(esr);
 		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
-			tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
+			tsk->comm, task_pid_nr(tsk), inf->name, sig,
 			addr, esr);
 		show_pte(tsk->mm, addr);
 		show_regs(regs);
@@ -219,14 +234,16 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 {
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->active_mm;
+	const struct fault_info *inf;
 
 	/*
 	 * If we are in kernel mode at this point, we have no context to
 	 * handle this fault with.
 	 */
-	if (user_mode(regs))
-		__do_user_fault(tsk, addr, esr, SIGSEGV, SEGV_MAPERR, regs);
-	else
+	if (user_mode(regs)) {
+		inf = esr_to_fault_info(esr);
+		__do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs);
+	} else
 		__do_kernel_fault(mm, addr, esr, regs);
 }
 
@@ -488,12 +505,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 	return 1;
 }
 
-static const struct fault_info {
-	int	(*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
-	int	sig;
-	int	code;
-	const char *name;
-} fault_info[] = {
+static const struct fault_info fault_info[] = {
 	{ do_bad,		SIGBUS,  0,		"ttbr address size fault"	},
 	{ do_bad,		SIGBUS,  0,		"level 1 address size fault"	},
 	{ do_bad,		SIGBUS,  0,		"level 2 address size fault"	},
@@ -560,19 +572,13 @@ static const struct fault_info {
 	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
 };
 
-static const char *fault_name(unsigned int esr)
-{
-	const struct fault_info *inf = fault_info + (esr & 63);
-	return inf->name;
-}
-
 /*
  * Dispatch a data abort to the relevant handler.
  */
 asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
 					 struct pt_regs *regs)
 {
-	const struct fault_info *inf = fault_info + (esr & 63);
+	const struct fault_info *inf = esr_to_fault_info(esr);
 	struct siginfo info;
 
 	if (!inf->fn(addr, esr, regs))
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index e25584d72396..7514a000e361 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -294,10 +294,6 @@ static __init int setup_hugepagesz(char *opt)
 		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
 	} else if (ps == PUD_SIZE) {
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
-	} else if (ps == (PAGE_SIZE * CONT_PTES)) {
-		hugetlb_add_hstate(CONT_PTE_SHIFT);
-	} else if (ps == (PMD_SIZE * CONT_PMDS)) {
-		hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
 	} else {
 		hugetlb_bad_size();
 		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
@@ -306,13 +302,3 @@ static __init int setup_hugepagesz(char *opt)
 	return 1;
 }
 __setup("hugepagesz=", setup_hugepagesz);
-
-#ifdef CONFIG_ARM64_64K_PAGES
-static __init int add_default_hugepagesz(void)
-{
-	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
-		hugetlb_add_hstate(CONT_PTE_SHIFT);
-	return 0;
-}
-arch_initcall(add_default_hugepagesz);
-#endif
diff --git a/arch/ia64/include/asm/asm-prototypes.h b/arch/ia64/include/asm/asm-prototypes.h
new file mode 100644
index 000000000000..a2c139808cfe
--- /dev/null
+++ b/arch/ia64/include/asm/asm-prototypes.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_IA64_ASM_PROTOTYPES_H
+#define _ASM_IA64_ASM_PROTOTYPES_H
+
+#include <asm/cacheflush.h>
+#include <asm/checksum.h>
+#include <asm/esi.h>
+#include <asm/ftrace.h>
+#include <asm/page.h>
+#include <asm/pal.h>
+#include <asm/string.h>
+#include <asm/uaccess.h>
+#include <asm/unwind.h>
+#include <asm/xor.h>
+
+extern const char ia64_ivt[];
+
+signed int __divsi3(signed int, unsigned int);
+signed int __modsi3(signed int, unsigned int);
+
+signed long long __divdi3(signed long long, unsigned long long);
+signed long long __moddi3(signed long long, unsigned long long);
+
+unsigned int __udivsi3(unsigned int, unsigned int);
+unsigned int __umodsi3(unsigned int, unsigned int);
+
+unsigned long long __udivdi3(unsigned long long, unsigned long long);
+unsigned long long __umoddi3(unsigned long long, unsigned long long);
+
+#endif /* _ASM_IA64_ASM_PROTOTYPES_H */
diff --git a/arch/ia64/lib/Makefile b/arch/ia64/lib/Makefile
index 1f3d3877618f..0a40b14407b1 100644
--- a/arch/ia64/lib/Makefile
+++ b/arch/ia64/lib/Makefile
@@ -24,25 +24,25 @@ AFLAGS___modsi3.o	=	     -DMODULO
 AFLAGS___umodsi3.o	= -DUNSIGNED -DMODULO
 
 $(obj)/__divdi3.o: $(src)/idiv64.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__udivdi3.o: $(src)/idiv64.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__moddi3.o: $(src)/idiv64.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__umoddi3.o: $(src)/idiv64.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__divsi3.o: $(src)/idiv32.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__udivsi3.o: $(src)/idiv32.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__modsi3.o: $(src)/idiv32.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
 
 $(obj)/__umodsi3.o: $(src)/idiv32.S FORCE
-	$(call if_changed_dep,as_o_S)
+	$(call if_changed_rule,as_o_S)
diff --git a/arch/metag/include/asm/uaccess.h b/arch/metag/include/asm/uaccess.h
index 273e61225c27..07238b39638c 100644
--- a/arch/metag/include/asm/uaccess.h
+++ b/arch/metag/include/asm/uaccess.h
@@ -197,20 +197,21 @@ extern long __must_check strnlen_user(const char __user *src, long count);
 
 #define strlen_user(str) strnlen_user(str, 32767)
 
-extern unsigned long __must_check __copy_user_zeroing(void *to,
-						      const void __user *from,
-						      unsigned long n);
+extern unsigned long raw_copy_from_user(void *to, const void __user *from,
+					unsigned long n);
 
 static inline unsigned long
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
+	unsigned long res = n;
 	if (likely(access_ok(VERIFY_READ, from, n)))
-		return __copy_user_zeroing(to, from, n);
-	memset(to, 0, n);
-	return n;
+		res = raw_copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }
 
-#define __copy_from_user(to, from, n) __copy_user_zeroing(to, from, n)
+#define __copy_from_user(to, from, n) raw_copy_from_user(to, from, n)
 #define __copy_from_user_inatomic __copy_from_user
 
 extern unsigned long __must_check __copy_user(void __user *to,
diff --git a/arch/metag/lib/usercopy.c b/arch/metag/lib/usercopy.c
index b3ebfe9c8e88..2792fc621088 100644
--- a/arch/metag/lib/usercopy.c
+++ b/arch/metag/lib/usercopy.c
@@ -29,7 +29,6 @@
 		COPY						 \
 		"1:\n"						 \
 		"	.section .fixup,\"ax\"\n"		 \
-		"	MOV D1Ar1,#0\n"				 \
 		FIXUP						 \
 		"	MOVT    D1Ar1,#HI(1b)\n"		 \
 		"	JUMP    D1Ar1,#LO(1b)\n"		 \
@@ -260,27 +259,31 @@
 		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
 		"22:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
-		"SUB	%3, %3, #32\n"					\
 		"23:\n"							\
-		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
+		"SUB	%3, %3, #32\n"					\
 		"24:\n"							\
+		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
+		"25:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"26:\n"							\
 		"SUB	%3, %3, #32\n"					\
 		"DCACHE	[%1+#-64], D0Ar6\n"				\
 		"BR	$Lloop"id"\n"					\
 									\
 		"MOV	RAPF, %1\n"					\
-		"25:\n"							\
+		"27:\n"							\
 		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"26:\n"							\
+		"28:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"29:\n"							\
 		"SUB	%3, %3, #32\n"					\
-		"27:\n"							\
+		"30:\n"							\
 		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"28:\n"							\
+		"31:\n"							\
 		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"32:\n"							\
 		"SUB	%0, %0, #8\n"					\
-		"29:\n"							\
+		"33:\n"							\
 		"SETL	[%0++], D0.7, D1.7\n"				\
 		"SUB	%3, %3, #32\n"					\
 		"1:"							\
@@ -312,11 +315,15 @@
 		"	.long 26b,3b\n"					\
 		"	.long 27b,3b\n"					\
 		"	.long 28b,3b\n"					\
-		"	.long 29b,4b\n"					\
+		"	.long 29b,3b\n"					\
+		"	.long 30b,3b\n"					\
+		"	.long 31b,3b\n"					\
+		"	.long 32b,3b\n"					\
+		"	.long 33b,4b\n"					\
 		"	.previous\n"					\
 		: "=r" (to), "=r" (from), "=r" (ret), "=d" (n)		\
 		: "0" (to), "1" (from), "2" (ret), "3" (n)		\
-		: "D1Ar1", "D0Ar2", "memory")
+		: "D1Ar1", "D0Ar2", "cc", "memory")
 
 /*	rewind 'to' and 'from'  pointers when a fault occurs
  *
@@ -342,7 +349,7 @@
 #define __asm_copy_to_user_64bit_rapf_loop(to,	from, ret, n, id)\
 	__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id,		\
 		"LSR	D0Ar2, D0Ar2, #8\n"				\
-		"AND	D0Ar2, D0Ar2, #0x7\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x7\n"				\
 		"ADDZ	D0Ar2, D0Ar2, #4\n"				\
 		"SUB	D0Ar2, D0Ar2, #1\n"				\
 		"MOV	D1Ar1, #4\n"					\
@@ -403,47 +410,55 @@
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
 		"22:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
-		"SUB	%3, %3, #16\n"					\
 		"23:\n"							\
-		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"24:\n"							\
-		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
 		"SUB	%3, %3, #16\n"					\
-		"25:\n"							\
+		"24:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"26:\n"							\
+		"25:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"26:\n"							\
 		"SUB	%3, %3, #16\n"					\
 		"27:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
 		"28:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"29:\n"							\
+		"SUB	%3, %3, #16\n"					\
+		"30:\n"							\
+		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
+		"31:\n"							\
+		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"32:\n"							\
 		"SUB	%3, %3, #16\n"					\
 		"DCACHE	[%1+#-64], D0Ar6\n"				\
 		"BR	$Lloop"id"\n"					\
 									\
 		"MOV	RAPF, %1\n"					\
-		"29:\n"							\
+		"33:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"30:\n"							\
+		"34:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"35:\n"							\
 		"SUB	%3, %3, #16\n"					\
-		"31:\n"							\
+		"36:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"32:\n"							\
+		"37:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"38:\n"							\
 		"SUB	%3, %3, #16\n"					\
-		"33:\n"							\
+		"39:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"34:\n"							\
+		"40:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"41:\n"							\
 		"SUB	%3, %3, #16\n"					\
-		"35:\n"							\
+		"42:\n"							\
 		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
-		"36:\n"							\
+		"43:\n"							\
 		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
+		"44:\n"							\
 		"SUB	%0, %0, #4\n"					\
-		"37:\n"							\
+		"45:\n"							\
 		"SETD	[%0++], D0.7\n"					\
 		"SUB	%3, %3, #16\n"					\
 		"1:"							\
@@ -483,11 +498,19 @@
 		"	.long 34b,3b\n"					\
 		"	.long 35b,3b\n"					\
 		"	.long 36b,3b\n"					\
-		"	.long 37b,4b\n"					\
+		"	.long 37b,3b\n"					\
+		"	.long 38b,3b\n"					\
+		"	.long 39b,3b\n"					\
+		"	.long 40b,3b\n"					\
+		"	.long 41b,3b\n"					\
+		"	.long 42b,3b\n"					\
+		"	.long 43b,3b\n"					\
+		"	.long 44b,3b\n"					\
+		"	.long 45b,4b\n"					\
 		"	.previous\n"					\
 		: "=r" (to), "=r" (from), "=r" (ret), "=d" (n)		\
 		: "0" (to), "1" (from), "2" (ret), "3" (n)		\
-		: "D1Ar1", "D0Ar2", "memory")
+		: "D1Ar1", "D0Ar2", "cc", "memory")
 
 /*	rewind 'to' and 'from'  pointers when a fault occurs
  *
@@ -513,7 +536,7 @@
 #define __asm_copy_to_user_32bit_rapf_loop(to, from, ret, n, id)\
 	__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id,		\
 		"LSR	D0Ar2, D0Ar2, #8\n"				\
-		"AND	D0Ar2, D0Ar2, #0x7\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x7\n"				\
 		"ADDZ	D0Ar2, D0Ar2, #4\n"				\
 		"SUB	D0Ar2, D0Ar2, #1\n"				\
 		"MOV	D1Ar1, #4\n"					\
@@ -538,23 +561,31 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 	if ((unsigned long) src & 1) {
 		__asm_copy_to_user_1(dst, src, retn);
 		n--;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 1) {
 		/* Worst case - byte copy */
 		while (n > 0) {
 			__asm_copy_to_user_1(dst, src, retn);
 			n--;
+			if (retn)
+				return retn + n;
 		}
 	}
 	if (((unsigned long) src & 2) && n >= 2) {
 		__asm_copy_to_user_2(dst, src, retn);
 		n -= 2;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 2) {
 		/* Second worst case - word copy */
 		while (n >= 2) {
 			__asm_copy_to_user_2(dst, src, retn);
 			n -= 2;
+			if (retn)
+				return retn + n;
 		}
 	}
 
@@ -569,6 +600,8 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 		while (n >= 8) {
 			__asm_copy_to_user_8x64(dst, src, retn);
 			n -= 8;
+			if (retn)
+				return retn + n;
 		}
 	}
 	if (n >= RAPF_MIN_BUF_SIZE) {
@@ -581,6 +614,8 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 		while (n >= 8) {
 			__asm_copy_to_user_8x64(dst, src, retn);
 			n -= 8;
+			if (retn)
+				return retn + n;
 		}
 	}
 #endif
@@ -588,11 +623,15 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 	while (n >= 16) {
 		__asm_copy_to_user_16(dst, src, retn);
 		n -= 16;
+		if (retn)
+			return retn + n;
 	}
 
 	while (n >= 4) {
 		__asm_copy_to_user_4(dst, src, retn);
 		n -= 4;
+		if (retn)
+			return retn + n;
 	}
 
 	switch (n) {
@@ -609,6 +648,10 @@ unsigned long __copy_user(void __user *pdst, const void *psrc,
 		break;
 	}
 
+	/*
+	 * If we get here, retn correctly reflects the number of failing
+	 * bytes.
+	 */
 	return retn;
 }
 EXPORT_SYMBOL(__copy_user);
@@ -617,16 +660,14 @@ EXPORT_SYMBOL(__copy_user);
 	__asm_copy_user_cont(to, from, ret,	\
 		"	GETB D1Ar1,[%1++]\n"	\
 		"2:	SETB [%0++],D1Ar1\n",	\
-		"3:	ADD  %2,%2,#1\n"	\
-		"	SETB [%0++],D1Ar1\n",	\
+		"3:	ADD  %2,%2,#1\n",	\
 		"	.long 2b,3b\n")
 
 #define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
 	__asm_copy_user_cont(to, from, ret,		\
 		"	GETW D1Ar1,[%1++]\n"		\
 		"2:	SETW [%0++],D1Ar1\n" COPY,	\
-		"3:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
+		"3:	ADD  %2,%2,#2\n" FIXUP,		\
 		"	.long 2b,3b\n" TENTRY)
 
 #define __asm_copy_from_user_2(to, from, ret) \
@@ -636,145 +677,26 @@ EXPORT_SYMBOL(__copy_user);
 	__asm_copy_from_user_2x_cont(to, from, ret,	\
 		"	GETB D1Ar1,[%1++]\n"		\
 		"4:	SETB [%0++],D1Ar1\n",		\
-		"5:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
+		"5:	ADD  %2,%2,#1\n",		\
 		"	.long 4b,5b\n")
 
 #define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
 	__asm_copy_user_cont(to, from, ret,		\
 		"	GETD D1Ar1,[%1++]\n"		\
 		"2:	SETD [%0++],D1Ar1\n" COPY,	\
-		"3:	ADD  %2,%2,#4\n"		\
-		"	SETD [%0++],D1Ar1\n" FIXUP,	\
+		"3:	ADD  %2,%2,#4\n" FIXUP,		\
 		"	.long 2b,3b\n" TENTRY)
 
 #define __asm_copy_from_user_4(to, from, ret) \
 	__asm_copy_from_user_4x_cont(to, from, ret, "", "", "")
 
-#define __asm_copy_from_user_5(to, from, ret) \
-	__asm_copy_from_user_4x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"4:	SETB [%0++],D1Ar1\n",		\
-		"5:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 4b,5b\n")
-
-#define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_4x_cont(to, from, ret,	\
-		"	GETW D1Ar1,[%1++]\n"		\
-		"4:	SETW [%0++],D1Ar1\n" COPY,	\
-		"5:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_6(to, from, ret) \
-	__asm_copy_from_user_6x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_7(to, from, ret) \
-	__asm_copy_from_user_6x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"6:	SETB [%0++],D1Ar1\n",		\
-		"7:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 6b,7b\n")
-
-#define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_4x_cont(to, from, ret,	\
-		"	GETD D1Ar1,[%1++]\n"		\
-		"4:	SETD [%0++],D1Ar1\n" COPY,	\
-		"5:	ADD  %2,%2,#4\n"			\
-		"	SETD [%0++],D1Ar1\n" FIXUP,		\
-		"	.long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_8(to, from, ret) \
-	__asm_copy_from_user_8x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_9(to, from, ret) \
-	__asm_copy_from_user_8x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"6:	SETB [%0++],D1Ar1\n",		\
-		"7:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 6b,7b\n")
-
-#define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_8x_cont(to, from, ret,	\
-		"	GETW D1Ar1,[%1++]\n"		\
-		"6:	SETW [%0++],D1Ar1\n" COPY,	\
-		"7:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_10(to, from, ret) \
-	__asm_copy_from_user_10x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_11(to, from, ret)		\
-	__asm_copy_from_user_10x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"8:	SETB [%0++],D1Ar1\n",		\
-		"9:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 8b,9b\n")
-
-#define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_8x_cont(to, from, ret,	\
-		"	GETD D1Ar1,[%1++]\n"		\
-		"6:	SETD [%0++],D1Ar1\n" COPY,	\
-		"7:	ADD  %2,%2,#4\n"		\
-		"	SETD [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_12(to, from, ret) \
-	__asm_copy_from_user_12x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_13(to, from, ret) \
-	__asm_copy_from_user_12x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"8:	SETB [%0++],D1Ar1\n",		\
-		"9:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 8b,9b\n")
-
-#define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_12x_cont(to, from, ret,	\
-		"	GETW D1Ar1,[%1++]\n"		\
-		"8:	SETW [%0++],D1Ar1\n" COPY,	\
-		"9:	ADD  %2,%2,#2\n"		\
-		"	SETW [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_14(to, from, ret) \
-	__asm_copy_from_user_14x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_15(to, from, ret) \
-	__asm_copy_from_user_14x_cont(to, from, ret,	\
-		"	GETB D1Ar1,[%1++]\n"		\
-		"10:	SETB [%0++],D1Ar1\n",		\
-		"11:	ADD  %2,%2,#1\n"		\
-		"	SETB [%0++],D1Ar1\n",		\
-		"	.long 10b,11b\n")
-
-#define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
-	__asm_copy_from_user_12x_cont(to, from, ret,	\
-		"	GETD D1Ar1,[%1++]\n"		\
-		"8:	SETD [%0++],D1Ar1\n" COPY,	\
-		"9:	ADD  %2,%2,#4\n"		\
-		"	SETD [%0++],D1Ar1\n" FIXUP,	\
-		"	.long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_16(to, from, ret) \
-	__asm_copy_from_user_16x_cont(to, from, ret, "", "", "")
-
 #define __asm_copy_from_user_8x64(to, from, ret) \
 	asm volatile (				\
 		"	GETL D0Ar2,D1Ar1,[%1++]\n"	\
 		"2:	SETL [%0++],D0Ar2,D1Ar1\n"	\
 		"1:\n"					\
 		"	.section .fixup,\"ax\"\n"	\
-		"	MOV D1Ar1,#0\n"			\
-		"	MOV D0Ar2,#0\n"			\
 		"3:	ADD  %2,%2,#8\n"		\
-		"	SETL [%0++],D0Ar2,D1Ar1\n"	\
 		"	MOVT    D0Ar2,#HI(1b)\n"	\
 		"	JUMP    D0Ar2,#LO(1b)\n"	\
 		"	.previous\n"			\
@@ -789,36 +711,57 @@ EXPORT_SYMBOL(__copy_user);
  *
  *	Rationale:
  *		A fault occurs while reading from user buffer, which is the
- *		source. Since the fault is at a single address, we only
- *		need to rewind by 8 bytes.
+ *		source.
  *		Since we don't write to kernel buffer until we read first,
  *		the kernel buffer is at the right state and needn't be
- *		corrected.
+ *		corrected, but the source must be rewound to the beginning of
+ *		the block, which is LSM_STEP*8 bytes.
+ *		LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ *		and stored in D0Ar2
+ *
+ *		NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ *			LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ *			a fault happens at the 4th write, LSM_STEP will be 0
+ *			instead of 4. The code copes with that.
  */
 #define __asm_copy_from_user_64bit_rapf_loop(to, from, ret, n, id)	\
 	__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id,		\
-		"SUB	%1, %1, #8\n")
+		"LSR	D0Ar2, D0Ar2, #5\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x38\n"				\
+		"ADDZ	D0Ar2, D0Ar2, #32\n"				\
+		"SUB	%1, %1, D0Ar2\n")
 
 /*	rewind 'from' pointer when a fault occurs
  *
  *	Rationale:
  *		A fault occurs while reading from user buffer, which is the
- *		source. Since the fault is at a single address, we only
- *		need to rewind by 4 bytes.
+ *		source.
  *		Since we don't write to kernel buffer until we read first,
  *		the kernel buffer is at the right state and needn't be
- *		corrected.
+ *		corrected, but the source must be rewound to the beginning of
+ *		the block, which is LSM_STEP*4 bytes.
+ *		LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ *		and stored in D0Ar2
+ *
+ *		NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ *			LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ *			a fault happens at the 4th write, LSM_STEP will be 0
+ *			instead of 4. The code copes with that.
  */
 #define __asm_copy_from_user_32bit_rapf_loop(to, from, ret, n, id)	\
 	__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id,		\
-		"SUB	%1, %1, #4\n")
+		"LSR	D0Ar2, D0Ar2, #6\n"				\
+		"ANDS	D0Ar2, D0Ar2, #0x1c\n"				\
+		"ADDZ	D0Ar2, D0Ar2, #16\n"				\
+		"SUB	%1, %1, D0Ar2\n")
 
 
-/* Copy from user to kernel, zeroing the bytes that were inaccessible in
-   userland.  The return-value is the number of bytes that were
-   inaccessible.  */
-unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
-				  unsigned long n)
+/*
+ * Copy from user to kernel. The return-value is the number of bytes that were
+ * inaccessible.
+ */
+unsigned long raw_copy_from_user(void *pdst, const void __user *psrc,
+				 unsigned long n)
 {
 	register char *dst asm ("A0.2") = pdst;
 	register const char __user *src asm ("A1.2") = psrc;
@@ -830,6 +773,8 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 	if ((unsigned long) src & 1) {
 		__asm_copy_from_user_1(dst, src, retn);
 		n--;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 1) {
 		/* Worst case - byte copy */
@@ -837,12 +782,14 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_1(dst, src, retn);
 			n--;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 	if (((unsigned long) src & 2) && n >= 2) {
 		__asm_copy_from_user_2(dst, src, retn);
 		n -= 2;
+		if (retn)
+			return retn + n;
 	}
 	if ((unsigned long) dst & 2) {
 		/* Second worst case - word copy */
@@ -850,16 +797,10 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_2(dst, src, retn);
 			n -= 2;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 
-	/* We only need one check after the unalignment-adjustments,
-	   because if both adjustments were done, either both or
-	   neither reference had an exception.  */
-	if (retn != 0)
-		goto copy_exception_bytes;
-
 #ifdef USE_RAPF
 	/* 64 bit copy loop */
 	if (!(((unsigned long) src | (unsigned long) dst) & 7)) {
@@ -872,7 +813,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_8x64(dst, src, retn);
 			n -= 8;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 
@@ -888,7 +829,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 			__asm_copy_from_user_8x64(dst, src, retn);
 			n -= 8;
 			if (retn)
-				goto copy_exception_bytes;
+				return retn + n;
 		}
 	}
 #endif
@@ -898,7 +839,7 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 		n -= 4;
 
 		if (retn)
-			goto copy_exception_bytes;
+			return retn + n;
 	}
 
 	/* If we get here, there were no memory read faults.  */
@@ -924,21 +865,8 @@ unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
 	/* If we get here, retn correctly reflects the number of failing
 	   bytes.  */
 	return retn;
-
- copy_exception_bytes:
-	/* We already have "retn" bytes cleared, and need to clear the
-	   remaining "n" bytes.  A non-optimized simple byte-for-byte in-line
-	   memset is preferred here, since this isn't speed-critical code and
-	   we'd rather have this a leaf-function than calling memset.  */
-	{
-		char *endp;
-		for (endp = dst + n; dst < endp; dst++)
-			*dst = 0;
-	}
-
-	return retn + n;
 }
-EXPORT_SYMBOL(__copy_user_zeroing);
+EXPORT_SYMBOL(raw_copy_from_user);
 
 #define __asm_clear_8x64(to, ret) \
 	asm volatile (					\
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a008a9f03072..e0bb576410bb 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1531,7 +1531,7 @@ config CPU_MIPS64_R6
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_MSA
 	select GENERIC_CSUM
-	select MIPS_O32_FP64_SUPPORT if MIPS32_O32
+	select MIPS_O32_FP64_SUPPORT if 32BIT || MIPS32_O32
 	select HAVE_KVM
 	help
 	  Choose this option to build a kernel for release 6 or later of the
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index f94455f964ec..a2813fe381cf 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -21,6 +21,7 @@
 #include <asm/cpu-features.h>
 #include <asm/fpu_emulator.h>
 #include <asm/hazards.h>
+#include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <asm/current.h>
 #include <asm/msa.h>
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index 956db6e201d1..ddd1c918103b 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -18,9 +18,24 @@
 #include <irq.h>
 
 #define IRQ_STACK_SIZE			THREAD_SIZE
+#define IRQ_STACK_START			(IRQ_STACK_SIZE - sizeof(unsigned long))
 
 extern void *irq_stack[NR_CPUS];
 
+/*
+ * The highest address on the IRQ stack contains a dummy frame put down in
+ * genex.S (handle_int & except_vec_vi_handler) which is structured as follows:
+ *
+ *   top ------------
+ *       | task sp  | <- irq_stack[cpu] + IRQ_STACK_START
+ *       ------------
+ *       |          | <- First frame of IRQ context
+ *       ------------
+ *
+ * task sp holds a copy of the task stack pointer where the struct pt_regs
+ * from exception entry can be found.
+ */
+
 static inline bool on_irq_stack(int cpu, unsigned long sp)
 {
 	unsigned long low = (unsigned long)irq_stack[cpu];
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index f485afe51514..a8df44d60607 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -127,7 +127,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 		"	andi	%[ticket], %[ticket], 0xffff		\n"
 		"	bne	%[ticket], %[my_ticket], 4f		\n"
 		"	 subu	%[ticket], %[my_ticket], %[ticket]	\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		"	.subsection 2					\n"
 		"4:	andi	%[ticket], %[ticket], 0xffff		\n"
 		"	sll	%[ticket], 5				\n"
@@ -202,7 +202,7 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
 		"	sc	%[ticket], %[ticket_ptr]		\n"
 		"	beqz	%[ticket], 1b				\n"
 		"	 li	%[ticket], 1				\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		"	.subsection 2					\n"
 		"3:	b	2b					\n"
 		"	 li	%[ticket], 0				\n"
@@ -382,7 +382,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 		"	.set	reorder					\n"
 		__WEAK_LLSC_MB
 		"	li	%2, 1					\n"
-		"2:							\n"
+		"2:	.insn						\n"
 		: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
 		: GCC_OFF_SMALL_ASM() (rw->lock)
 		: "memory");
@@ -422,7 +422,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 			"	lui	%1, 0x8000			\n"
 			"	sc	%1, %0				\n"
 			"	li	%2, 1				\n"
-			"2:						\n"
+			"2:	.insn					\n"
 			: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp),
 			  "=&r" (ret)
 			: GCC_OFF_SMALL_ASM() (rw->lock)
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index 3e940dbe0262..78faf4292e90 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -386,17 +386,18 @@
 #define __NR_pkey_mprotect		(__NR_Linux + 363)
 #define __NR_pkey_alloc			(__NR_Linux + 364)
 #define __NR_pkey_free			(__NR_Linux + 365)
+#define __NR_statx			(__NR_Linux + 366)
 
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		365
+#define __NR_Linux_syscalls		366
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		365
+#define __NR_O32_Linux_syscalls		366
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -730,16 +731,17 @@
 #define __NR_pkey_mprotect		(__NR_Linux + 323)
 #define __NR_pkey_alloc			(__NR_Linux + 324)
 #define __NR_pkey_free			(__NR_Linux + 325)
+#define __NR_statx			(__NR_Linux + 326)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		325
+#define __NR_Linux_syscalls		326
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		325
+#define __NR_64_Linux_syscalls		326
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1077,15 +1079,16 @@
 #define __NR_pkey_mprotect		(__NR_Linux + 327)
 #define __NR_pkey_alloc			(__NR_Linux + 328)
 #define __NR_pkey_free			(__NR_Linux + 329)
+#define __NR_statx			(__NR_Linux + 330)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		329
+#define __NR_Linux_syscalls		330
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		329
+#define __NR_N32_Linux_syscalls		330
 
 #endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index bb5c5d34ba81..a670c0c11875 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -102,6 +102,7 @@ void output_thread_info_defines(void)
 	DEFINE(_THREAD_SIZE, THREAD_SIZE);
 	DEFINE(_THREAD_MASK, THREAD_MASK);
 	DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
+	DEFINE(_IRQ_STACK_START, IRQ_STACK_START);
 	BLANK();
 }
 
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 59476a607add..a00e87b0256d 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -361,7 +361,7 @@ LEAF(mips_cps_get_bootcfg)
 	END(mips_cps_get_bootcfg)
 
 LEAF(mips_cps_boot_vpes)
-	PTR_L	ta2, COREBOOTCFG_VPEMASK(a0)
+	lw	ta2, COREBOOTCFG_VPEMASK(a0)
 	PTR_L	ta3, COREBOOTCFG_VPECONFIG(a0)
 
 #if defined(CONFIG_CPU_MIPSR6)
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 07718bb5fc9d..12422fd4af23 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -1824,7 +1824,7 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 		}
 
 		decode_configs(c);
-		c->options |= MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
+		c->options |= MIPS_CPU_FTLB | MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
 		c->writecombine = _CACHE_UNCACHED_ACCELERATED;
 		break;
 	default:
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index 7ec9612cb007..ae810da4d499 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -215,9 +215,11 @@ NESTED(handle_int, PT_SIZE, sp)
 	beq	t0, t1, 2f
 
 	/* Switch to IRQ stack */
-	li	t1, _IRQ_STACK_SIZE
+	li	t1, _IRQ_STACK_START
 	PTR_ADD sp, t0, t1
 
+	/* Save task's sp on IRQ stack so that unwinding can follow it */
+	LONG_S	s1, 0(sp)
 2:
 	jal	plat_irq_dispatch
 
@@ -325,9 +327,11 @@ NESTED(except_vec_vi_handler, 0, sp)
 	beq	t0, t1, 2f
 
 	/* Switch to IRQ stack */
-	li	t1, _IRQ_STACK_SIZE
+	li	t1, _IRQ_STACK_START
 	PTR_ADD sp, t0, t1
 
+	/* Save task's sp on IRQ stack so that unwinding can follow it */
+	LONG_S	s1, 0(sp)
 2:
 	jalr	v0
 
@@ -519,7 +523,7 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	BUILD_HANDLER reserved reserved sti verbose	/* others */
 
 	.align	5
-	LEAF(handle_ri_rdhwr_vivt)
+	LEAF(handle_ri_rdhwr_tlbp)
 	.set	push
 	.set	noat
 	.set	noreorder
@@ -538,7 +542,7 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	.set	pop
 	bltz	k1, handle_ri	/* slow path */
 	/* fall thru */
-	END(handle_ri_rdhwr_vivt)
+	END(handle_ri_rdhwr_tlbp)
 
 	LEAF(handle_ri_rdhwr)
 	.set	push
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index fb6b6b650719..b68e10fc453d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -488,31 +488,52 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
 					      unsigned long pc,
 					      unsigned long *ra)
 {
+	unsigned long low, high, irq_stack_high;
 	struct mips_frame_info info;
 	unsigned long size, ofs;
+	struct pt_regs *regs;
 	int leaf;
-	extern void ret_from_irq(void);
-	extern void ret_from_exception(void);
 
 	if (!stack_page)
 		return 0;
 
 	/*
-	 * If we reached the bottom of interrupt context,
-	 * return saved pc in pt_regs.
+	 * IRQ stacks start at IRQ_STACK_START
+	 * task stacks at THREAD_SIZE - 32
 	 */
-	if (pc == (unsigned long)ret_from_irq ||
-	    pc == (unsigned long)ret_from_exception) {
-		struct pt_regs *regs;
-		if (*sp >= stack_page &&
-		    *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) {
-			regs = (struct pt_regs *)*sp;
-			pc = regs->cp0_epc;
-			if (!user_mode(regs) && __kernel_text_address(pc)) {
-				*sp = regs->regs[29];
-				*ra = regs->regs[31];
-				return pc;
-			}
+	low = stack_page;
+	if (!preemptible() && on_irq_stack(raw_smp_processor_id(), *sp)) {
+		high = stack_page + IRQ_STACK_START;
+		irq_stack_high = high;
+	} else {
+		high = stack_page + THREAD_SIZE - 32;
+		irq_stack_high = 0;
+	}
+
+	/*
+	 * If we reached the top of the interrupt stack, start unwinding
+	 * the interrupted task stack.
+	 */
+	if (unlikely(*sp == irq_stack_high)) {
+		unsigned long task_sp = *(unsigned long *)*sp;
+
+		/*
+		 * Check that the pointer saved in the IRQ stack head points to
+		 * something within the stack of the current task
+		 */
+		if (!object_is_on_stack((void *)task_sp))
+			return 0;
+
+		/*
+		 * Follow pointer to tasks kernel stack frame where interrupted
+		 * state was saved.
+		 */
+		regs = (struct pt_regs *)task_sp;
+		pc = regs->cp0_epc;
+		if (!user_mode(regs) && __kernel_text_address(pc)) {
+			*sp = regs->regs[29];
+			*ra = regs->regs[31];
+			return pc;
 		}
 		return 0;
 	}
@@ -533,8 +554,7 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page,
 	if (leaf < 0)
 		return 0;
 
-	if (*sp < stack_page ||
-	    *sp + info.frame_size > stack_page + THREAD_SIZE - 32)
+	if (*sp < low || *sp + info.frame_size > high)
 		return 0;
 
 	if (leaf)
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index c29d397eee86..80ed68b2c95e 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -600,3 +600,4 @@ EXPORT(sys_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 4365 */
+	PTR	sys_statx
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 0687f96ee912..49765b44aa9b 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -438,4 +438,5 @@ EXPORT(sys_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 5325 */
+	PTR	sys_statx
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 0331ba39a065..90bad2d1b2d3 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -433,4 +433,5 @@ EXPORT(sysn32_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free
+	PTR	sys_statx			/* 6330 */
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 5a47042dd25f..2dd70bd104e1 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -588,4 +588,5 @@ EXPORT(sys32_call_table)
 	PTR	sys_pkey_mprotect
 	PTR	sys_pkey_alloc
 	PTR	sys_pkey_free			/* 4365 */
+	PTR	sys_statx
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index c7d17cfb32f6..b49e7bf9f950 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -83,7 +83,7 @@ extern asmlinkage void handle_dbe(void);
 extern asmlinkage void handle_sys(void);
 extern asmlinkage void handle_bp(void);
 extern asmlinkage void handle_ri(void);
-extern asmlinkage void handle_ri_rdhwr_vivt(void);
+extern asmlinkage void handle_ri_rdhwr_tlbp(void);
 extern asmlinkage void handle_ri_rdhwr(void);
 extern asmlinkage void handle_cpu(void);
 extern asmlinkage void handle_ov(void);
@@ -2408,9 +2408,18 @@ void __init trap_init(void)
 
 	set_except_vector(EXCCODE_SYS, handle_sys);
 	set_except_vector(EXCCODE_BP, handle_bp);
-	set_except_vector(EXCCODE_RI, rdhwr_noopt ? handle_ri :
-			  (cpu_has_vtag_icache ?
-			   handle_ri_rdhwr_vivt : handle_ri_rdhwr));
+
+	if (rdhwr_noopt)
+		set_except_vector(EXCCODE_RI, handle_ri);
+	else {
+		if (cpu_has_vtag_icache)
+			set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+		else if (current_cpu_type() == CPU_LOONGSON3)
+			set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+		else
+			set_except_vector(EXCCODE_RI, handle_ri_rdhwr);
+	}
+
 	set_except_vector(EXCCODE_CPU, handle_cpu);
 	set_except_vector(EXCCODE_OV, handle_ov);
 	set_except_vector(EXCCODE_TR, handle_tr);
diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c
index 3c3aa05891dd..95bec460b651 100644
--- a/arch/mips/lantiq/xway/sysctrl.c
+++ b/arch/mips/lantiq/xway/sysctrl.c
@@ -467,7 +467,7 @@ void __init ltq_soc_init(void)
 
 		if (!np_xbar)
 			panic("Failed to load xbar nodes from devicetree");
-		if (of_address_to_resource(np_pmu, 0, &res_xbar))
+		if (of_address_to_resource(np_xbar, 0, &res_xbar))
 			panic("Failed to get xbar resources");
 		if (!request_mem_region(res_xbar.start, resource_size(&res_xbar),
 			res_xbar.name))
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index e7f798d55fbc..3fe99cb271a9 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1562,6 +1562,7 @@ static void probe_vcache(void)
 	vcache_size = c->vcache.sets * c->vcache.ways * c->vcache.linesz;
 
 	c->vcache.waybit = 0;
+	c->vcache.waysize = vcache_size / c->vcache.ways;
 
 	pr_info("Unified victim cache %ldkB %s, linesize %d bytes.\n",
 		vcache_size >> 10, way_string[c->vcache.ways], c->vcache.linesz);
@@ -1664,6 +1665,7 @@ static void __init loongson3_sc_init(void)
 	/* Loongson-3 has 4 cores, 1MB scache for each. scaches are shared */
 	scache_size *= 4;
 	c->scache.waybit = 0;
+	c->scache.waysize = scache_size / c->scache.ways;
 	pr_info("Unified secondary cache %ldkB %s, linesize %d bytes.\n",
 	       scache_size >> 10, way_string[c->scache.ways], c->scache.linesz);
 	if (scache_size)
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 9bfee8988eaf..4f642e07c2b1 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -760,7 +760,8 @@ static void build_huge_update_entries(u32 **p, unsigned int pte,
 static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r,
 				    struct uasm_label **l,
 				    unsigned int pte,
-				    unsigned int ptr)
+				    unsigned int ptr,
+				    unsigned int flush)
 {
 #ifdef CONFIG_SMP
 	UASM_i_SC(p, pte, 0, ptr);
@@ -769,6 +770,22 @@ static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r,
 #else
 	UASM_i_SW(p, pte, 0, ptr);
 #endif
+	if (cpu_has_ftlb && flush) {
+		BUG_ON(!cpu_has_tlbinv);
+
+		UASM_i_MFC0(p, ptr, C0_ENTRYHI);
+		uasm_i_ori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+		UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+		build_tlb_write_entry(p, l, r, tlb_indexed);
+
+		uasm_i_xori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+		UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+		build_huge_update_entries(p, pte, ptr);
+		build_huge_tlb_write_entry(p, l, r, pte, tlb_random, 0);
+
+		return;
+	}
+
 	build_huge_update_entries(p, pte, ptr);
 	build_huge_tlb_write_entry(p, l, r, pte, tlb_indexed, 0);
 }
@@ -2199,7 +2216,7 @@ static void build_r4000_tlb_load_handler(void)
 		uasm_l_tlbl_goaround2(&l, p);
 	}
 	uasm_i_ori(&p, wr.r1, wr.r1, (_PAGE_ACCESSED | _PAGE_VALID));
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
 #endif
 
 	uasm_l_nopage_tlbl(&l, p);
@@ -2254,7 +2271,7 @@ static void build_r4000_tlb_store_handler(void)
 	build_tlb_probe_entry(&p);
 	uasm_i_ori(&p, wr.r1, wr.r1,
 		   _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
 #endif
 
 	uasm_l_nopage_tlbs(&l, p);
@@ -2310,7 +2327,7 @@ static void build_r4000_tlb_modify_handler(void)
 	build_tlb_probe_entry(&p);
 	uasm_i_ori(&p, wr.r1, wr.r1,
 		   _PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
-	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+	build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 0);
 #endif
 
 	uasm_l_nopage_tlbm(&l, p);
diff --git a/arch/mips/ralink/rt3883.c b/arch/mips/ralink/rt3883.c
index c4ffd43d3996..48ce701557a4 100644
--- a/arch/mips/ralink/rt3883.c
+++ b/arch/mips/ralink/rt3883.c
@@ -35,7 +35,7 @@ static struct rt2880_pmx_func uartlite_func[] = { FUNC("uartlite", 0, 15, 2) };
 static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
 static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
 static struct rt2880_pmx_func lna_a_func[] = { FUNC("lna a", 0, 32, 3) };
-static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna a", 0, 35, 3) };
+static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna g", 0, 35, 3) };
 static struct rt2880_pmx_func pci_func[] = {
 	FUNC("pci-dev", 0, 40, 32),
 	FUNC("pci-host2", 1, 40, 32),
@@ -43,7 +43,7 @@ static struct rt2880_pmx_func pci_func[] = {
 	FUNC("pci-fnc", 3, 40, 32)
 };
 static struct rt2880_pmx_func ge1_func[] = { FUNC("ge1", 0, 72, 12) };
-static struct rt2880_pmx_func ge2_func[] = { FUNC("ge1", 0, 84, 12) };
+static struct rt2880_pmx_func ge2_func[] = { FUNC("ge2", 0, 84, 12) };
 
 static struct rt2880_pmx_group rt3883_pinmux_data[] = {
 	GRP("i2c", i2c_func, 1, RT3883_GPIO_MODE_I2C),
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
index 411994551afc..f058e0c3e4d4 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -33,10 +33,13 @@ static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len)
 	}
 
 	if (len & ~VMX_ALIGN_MASK) {
+		preempt_disable();
 		pagefault_disable();
 		enable_kernel_altivec();
 		crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+		disable_kernel_altivec();
 		pagefault_enable();
+		preempt_enable();
 	}
 
 	tail = len & VMX_ALIGN_MASK;
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index cbc7c42cdb74..ec7a8b099dd9 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -807,14 +807,25 @@ int fix_alignment(struct pt_regs *regs)
 	nb = aligninfo[instr].len;
 	flags = aligninfo[instr].flags;
 
-	/* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
-	if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
-		nb = 8;
-		flags = LD+SW;
-	} else if (IS_XFORM(instruction) &&
-		   ((instruction >> 1) & 0x3ff) == 660) {
-		nb = 8;
-		flags = ST+SW;
+	/*
+	 * Handle some cases which give overlaps in the DSISR values.
+	 */
+	if (IS_XFORM(instruction)) {
+		switch (get_xop(instruction)) {
+		case 532:	/* ldbrx */
+			nb = 8;
+			flags = LD+SW;
+			break;
+		case 660:	/* stdbrx */
+			nb = 8;
+			flags = ST+SW;
+			break;
+		case 20:	/* lwarx */
+		case 84:	/* ldarx */
+		case 116:	/* lharx */
+		case 276:	/* lqarx */
+			return 0;	/* not emulated ever */
+		}
 	}
 
 	/* Byteswap little endian loads and stores */
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index ae179cb1bb3c..c119044cad0d 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -67,7 +67,7 @@ PPC64_CACHES:
  *   flush all bytes from start through stop-1 inclusive
  */
 
-_GLOBAL(flush_icache_range)
+_GLOBAL_TOC(flush_icache_range)
 BEGIN_FTR_SECTION
 	PURGE_PREFETCHED_INS
 	blr
@@ -120,7 +120,7 @@ EXPORT_SYMBOL(flush_icache_range)
  *
  *    flush all bytes from start to stop-1 inclusive
  */
-_GLOBAL(flush_dcache_range)
+_GLOBAL_TOC(flush_dcache_range)
 
 /*
  * Flush the data cache to memory 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 9cfaa8b69b5f..f997154dfc41 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -236,6 +236,15 @@ static void cpu_ready_for_interrupts(void)
 		mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
 	}
 
+	/*
+	 * Fixup HFSCR:TM based on CPU features. The bit is set by our
+	 * early asm init because at that point we haven't updated our
+	 * CPU features from firmware and device-tree. Here we have,
+	 * so let's do it.
+	 */
+	if (cpu_has_feature(CPU_FTR_HVMODE) && !cpu_has_feature(CPU_FTR_TM_COMP))
+		mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM);
+
 	/* Set IR and DR in PACA MSR */
 	get_paca()->kernel_msr = MSR_KERNEL;
 }
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 8c68145ba1bd..710e491206ed 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1487,6 +1487,10 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
 	/* start new resize */
 
 	resize = kzalloc(sizeof(*resize), GFP_KERNEL);
+	if (!resize) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	resize->order = shift;
 	resize->kvm = kvm;
 	INIT_WORK(&resize->work, resize_hpt_prepare_work);
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index cc332608e656..65bb8f33b399 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -638,6 +638,10 @@ static void native_flush_hash_range(unsigned long number, int local)
 	unsigned long psize = batch->psize;
 	int ssize = batch->ssize;
 	int i;
+	unsigned int use_local;
+
+	use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) &&
+		mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use();
 
 	local_irq_save(flags);
 
@@ -667,8 +671,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 		} pte_iterate_hashed_end();
 	}
 
-	if (mmu_has_feature(MMU_FTR_TLBIEL) &&
-	    mmu_psize_defs[psize].tlbiel && local) {
+	if (use_local) {
 		asm volatile("ptesync":::"memory");
 		for (i = 0; i < number; i++) {
 			vpn = batch->vpn[i];
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index d55c829a5944..ddbffb715b40 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -168,8 +168,7 @@ union page_table_entry {
 		unsigned long z  : 1; /* Zero Bit */
 		unsigned long i  : 1; /* Page-Invalid Bit */
 		unsigned long p  : 1; /* DAT-Protection Bit */
-		unsigned long co : 1; /* Change-Recording Override */
-		unsigned long	 : 8;
+		unsigned long	 : 9;
 	};
 };
 
@@ -745,8 +744,6 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva,
 		return PGM_PAGE_TRANSLATION;
 	if (pte.z)
 		return PGM_TRANSLATION_SPEC;
-	if (pte.co && !edat1)
-		return PGM_TRANSLATION_SPEC;
 	dat_protection |= pte.p;
 	raddr.pfra = pte.pfra;
 real_address:
@@ -1182,7 +1179,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
 		rc = gmap_read_table(sg->parent, pgt + vaddr.px * 8, &pte.val);
 	if (!rc && pte.i)
 		rc = PGM_PAGE_TRANSLATION;
-	if (!rc && (pte.z || (pte.co && sg->edat_level < 1)))
+	if (!rc && pte.z)
 		rc = PGM_TRANSLATION_SPEC;
 shadow_page:
 	pte.p |= dat_protection;
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index f294dd42fc7d..5961b2d8398a 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -17,6 +17,7 @@
 
 #define HPAGE_SHIFT		23
 #define REAL_HPAGE_SHIFT	22
+#define HPAGE_2GB_SHIFT		31
 #define HPAGE_256MB_SHIFT	28
 #define HPAGE_64K_SHIFT		16
 #define REAL_HPAGE_SIZE		(_AC(1,UL) << REAL_HPAGE_SHIFT)
@@ -27,7 +28,7 @@
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 #define REAL_HPAGE_PER_HPAGE	(_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
-#define HUGE_MAX_HSTATE		3
+#define HUGE_MAX_HSTATE		4
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 8a598528ec1f..6fbd931f0570 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -679,26 +679,27 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 	return pte_pfn(pte);
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline unsigned long pmd_dirty(pmd_t pmd)
+#define __HAVE_ARCH_PMD_WRITE
+static inline unsigned long pmd_write(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_dirty(pte);
+	return pte_write(pte);
 }
 
-static inline unsigned long pmd_young(pmd_t pmd)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long pmd_dirty(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_young(pte);
+	return pte_dirty(pte);
 }
 
-static inline unsigned long pmd_write(pmd_t pmd)
+static inline unsigned long pmd_young(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
 
-	return pte_write(pte);
+	return pte_young(pte);
 }
 
 static inline unsigned long pmd_trans_huge(pmd_t pmd)
diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index 365d4cb267b4..dd27159819eb 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/arch/sparc/include/asm/processor_32.h
@@ -18,12 +18,6 @@
 #include <asm/signal.h>
 #include <asm/page.h>
 
-/*
- * The sparc has no problems with write protection
- */
-#define wp_works_ok 1
-#define wp_works_ok__is_a_macro /* for versions in ksyms.c */
-
 /* Whee, this is STACK_TOP + PAGE_SIZE and the lowest kernel address too...
  * That one page is used to protect kernel from intruders, so that
  * we can make our access_ok test faster
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index 6448cfc8292f..b58ee9018433 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/arch/sparc/include/asm/processor_64.h
@@ -18,10 +18,6 @@
 #include <asm/ptrace.h>
 #include <asm/page.h>
 
-/* The sparc has no problems with write protection */
-#define wp_works_ok 1
-#define wp_works_ok__is_a_macro /* for versions in ksyms.c */
-
 /*
  * User lives in his very own context, and cannot reference us. Note
  * that TASK_SIZE is a misnomer, it really gives maximum user virtual
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 6aa3da152c20..44101196d02b 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -96,6 +96,7 @@ sparc64_boot:
 	andn	%g1, PSTATE_AM, %g1
 	wrpr	%g1, 0x0, %pstate
 	ba,a,pt	%xcc, 1f
+	 nop
 
 	.globl	prom_finddev_name, prom_chosen_path, prom_root_node
 	.globl	prom_getprop_name, prom_mmu_name, prom_peer_name
@@ -613,6 +614,7 @@ niagara_tlb_fixup:
 	 nop
 
 	ba,a,pt	%xcc, 80f
+	 nop
 niagara4_patch:
 	call	niagara4_patch_copyops
 	 nop
@@ -622,6 +624,7 @@ niagara4_patch:
 	 nop
 
 	ba,a,pt	%xcc, 80f
+	 nop
 
 niagara2_patch:
 	call	niagara2_patch_copyops
@@ -632,6 +635,7 @@ niagara2_patch:
 	 nop
 
 	ba,a,pt	%xcc, 80f
+	 nop
 
 niagara_patch:
 	call	niagara_patch_copyops
diff --git a/arch/sparc/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S
index 34b4933900bf..9276d2f0dd86 100644
--- a/arch/sparc/kernel/misctrap.S
+++ b/arch/sparc/kernel/misctrap.S
@@ -82,6 +82,7 @@ do_stdfmna:
 	call		handle_stdfmna
 	 add		%sp, PTREGS_OFF, %o0
 	ba,a,pt		%xcc, rtrap
+	 nop
 	.size		do_stdfmna,.-do_stdfmna
 
 	.type		breakpoint_trap,#function
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 216948ca4382..709a82ebd294 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -237,6 +237,7 @@ rt_continue:	ldx			[%sp + PTREGS_OFF + PT_V9_G1], %g1
 		bne,pt			%xcc, user_rtt_fill_32bit
 		 wrpr			%g1, %cwp
 		ba,a,pt			%xcc, user_rtt_fill_64bit
+		 nop
 
 user_rtt_fill_fixup_dax:
 		ba,pt	%xcc, user_rtt_fill_fixup_common
diff --git a/arch/sparc/kernel/spiterrs.S b/arch/sparc/kernel/spiterrs.S
index 4a73009f66a5..d7e540842809 100644
--- a/arch/sparc/kernel/spiterrs.S
+++ b/arch/sparc/kernel/spiterrs.S
@@ -86,6 +86,7 @@ __spitfire_cee_trap_continue:
 	 rd		%pc, %g7
 
 	ba,a,pt		%xcc, 2f
+	 nop
 
 1:	ba,pt		%xcc, etrap_irq
 	 rd		%pc, %g7
diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S
index 6179e19bc9b9..c19f352f46c7 100644
--- a/arch/sparc/kernel/sun4v_tlb_miss.S
+++ b/arch/sparc/kernel/sun4v_tlb_miss.S
@@ -352,6 +352,7 @@ sun4v_mna:
 	call	sun4v_do_mna
 	 add	%sp, PTREGS_OFF, %o0
 	ba,a,pt	%xcc, rtrap
+	 nop
 
 	/* Privileged Action.  */
 sun4v_privact:
diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S
index 5604a2b051d4..364af3250646 100644
--- a/arch/sparc/kernel/urtt_fill.S
+++ b/arch/sparc/kernel/urtt_fill.S
@@ -92,6 +92,7 @@ user_rtt_fill_fixup_common:
 		call	sun4v_data_access_exception
 		 nop
 		ba,a,pt	%xcc, rtrap
+		 nop
 
 1:		call	spitfire_data_access_exception
 		 nop
diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S
index 855019a8590e..1ee173cc3c39 100644
--- a/arch/sparc/kernel/winfixup.S
+++ b/arch/sparc/kernel/winfixup.S
@@ -152,6 +152,8 @@ fill_fixup_dax:
 	call	sun4v_data_access_exception
 	 nop
 	ba,a,pt	%xcc, rtrap
+	 nop
 1:	call	spitfire_data_access_exception
 	 nop
 	ba,a,pt	%xcc, rtrap
+	 nop
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index c629dbd121b6..64dcd6cdb606 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -326,11 +326,13 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	blu		170f
 	 nop
 	ba,a,pt		%xcc, 180f
+	 nop
 
 4:	/* 32 <= low bits < 48 */
 	blu		150f
 	 nop
 	ba,a,pt		%xcc, 160f
+	 nop
 5:	/* 0 < low bits < 32 */
 	blu,a		6f
 	 cmp		%g2, 8
@@ -338,6 +340,7 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	blu		130f
 	 nop
 	ba,a,pt		%xcc, 140f
+	 nop
 6:	/* 0 < low bits < 16 */
 	bgeu		120f
 	 nop
@@ -475,6 +478,7 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	brz,pt		%o2, 85f
 	 sub		%o0, %o1, GLOBAL_SPARE
 	ba,a,pt		%XCC, 90f
+	 nop
 
 	.align		64
 75: /* 16 < len <= 64 */
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 75bb93b1437f..78ea962edcbe 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -530,4 +530,5 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	bne,pt		%icc, 1b
 	 EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1)
 	ba,a,pt		%icc, .Lexit
+	 nop
 	.size		FUNC_NAME, .-FUNC_NAME
diff --git a/arch/sparc/lib/NG4memset.S b/arch/sparc/lib/NG4memset.S
index 41da4bdd95cb..7c0c81f18837 100644
--- a/arch/sparc/lib/NG4memset.S
+++ b/arch/sparc/lib/NG4memset.S
@@ -102,4 +102,5 @@ NG4bzero:
 	bne,pt		%icc, 1b
 	 add		%o0, 0x30, %o0
 	ba,a,pt		%icc, .Lpostloop
+	 nop
 	.size		NG4bzero,.-NG4bzero
diff --git a/arch/sparc/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S
index d88c4ed50a00..cd654a719b27 100644
--- a/arch/sparc/lib/NGmemcpy.S
+++ b/arch/sparc/lib/NGmemcpy.S
@@ -394,6 +394,7 @@ FUNC_NAME:	/* %i0=dst, %i1=src, %i2=len */
 	brz,pt		%i2, 85f
 	 sub		%o0, %i1, %i3
 	ba,a,pt		%XCC, 90f
+	 nop
 
 	.align		64
 70: /* 16 < len <= 64 */
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 323bc6b6e3ad..ee5273ad918d 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -143,6 +143,10 @@ static pte_t sun4v_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
 	pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V;
 
 	switch (shift) {
+	case HPAGE_2GB_SHIFT:
+		hugepage_size = _PAGE_SZ2GB_4V;
+		pte_val(entry) |= _PAGE_PMD_HUGE;
+		break;
 	case HPAGE_256MB_SHIFT:
 		hugepage_size = _PAGE_SZ256MB_4V;
 		pte_val(entry) |= _PAGE_PMD_HUGE;
@@ -183,6 +187,9 @@ static unsigned int sun4v_huge_tte_to_shift(pte_t entry)
 	unsigned int shift;
 
 	switch (tte_szbits) {
+	case _PAGE_SZ2GB_4V:
+		shift = HPAGE_2GB_SHIFT;
+		break;
 	case _PAGE_SZ256MB_4V:
 		shift = HPAGE_256MB_SHIFT;
 		break;
@@ -261,7 +268,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		if (!pmd)
 			return NULL;
 
-		if (sz == PMD_SHIFT)
+		if (sz >= PMD_SIZE)
 			pte = (pte_t *)pmd;
 		else
 			pte = pte_alloc_map(mm, pmd, addr);
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index ccd455328989..0cda653ae007 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -337,6 +337,10 @@ static int __init setup_hugepagesz(char *string)
 	hugepage_shift = ilog2(hugepage_size);
 
 	switch (hugepage_shift) {
+	case HPAGE_2GB_SHIFT:
+		hv_pgsz_mask = HV_PGSZ_MASK_2GB;
+		hv_pgsz_idx = HV_PGSZ_IDX_2GB;
+		break;
 	case HPAGE_256MB_SHIFT:
 		hv_pgsz_mask = HV_PGSZ_MASK_256MB;
 		hv_pgsz_idx = HV_PGSZ_IDX_256MB;
@@ -1563,7 +1567,7 @@ bool kern_addr_valid(unsigned long addr)
 	if ((long)addr < 0L) {
 		unsigned long pa = __pa(addr);
 
-		if ((addr >> max_phys_bits) != 0UL)
+		if ((pa >> max_phys_bits) != 0UL)
 			return false;
 
 		return pfn_valid(pa >> PAGE_SHIFT);
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index def82f6d626f..8e76ebba2986 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -54,6 +54,7 @@
 enum mbus_module srmmu_modtype;
 static unsigned int hwbug_bitmask;
 int vac_cache_size;
+EXPORT_SYMBOL(vac_cache_size);
 int vac_line_size;
 
 extern struct resource sparc_iomap;
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index afda3bbf7854..ee8066c3d96c 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -154,7 +154,7 @@ 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, false);
+			tlb_batch_add_one(mm, vaddr, exec, PAGE_SHIFT);
 		}
 		pte++;
 		vaddr += PAGE_SIZE;
@@ -209,9 +209,9 @@ 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, true);
+			tlb_batch_add_one(mm, addr, exec, REAL_HPAGE_SHIFT);
 			tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
-					true);
+					  REAL_HPAGE_SHIFT);
 		} else {
 			tlb_batch_pmd_scan(mm, addr, orig);
 		}
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 0a04811f06b7..bedf08b22a47 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -122,7 +122,7 @@ void flush_tsb_user(struct tlb_batch *tb)
 
 	spin_lock_irqsave(&mm->context.lock, flags);
 
-	if (tb->hugepage_shift < HPAGE_SHIFT) {
+	if (tb->hugepage_shift < REAL_HPAGE_SHIFT) {
 		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)
@@ -155,7 +155,7 @@ void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr,
 
 	spin_lock_irqsave(&mm->context.lock, flags);
 
-	if (hugepage_shift < HPAGE_SHIFT) {
+	if (hugepage_shift < REAL_HPAGE_SHIFT) {
 		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)
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 7853b53959cd..3f9d1a83891a 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -30,8 +30,10 @@ static int __init vdso32_setup(char *s)
 {
 	vdso32_enabled = simple_strtoul(s, NULL, 0);
 
-	if (vdso32_enabled > 1)
+	if (vdso32_enabled > 1) {
 		pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+		vdso32_enabled = 0;
+	}
 
 	return 1;
 }
@@ -62,13 +64,18 @@ subsys_initcall(sysenter_setup);
 /* Register vsyscall32 into the ABI table */
 #include <linux/sysctl.h>
 
+static const int zero;
+static const int one = 1;
+
 static struct ctl_table abi_table2[] = {
 	{
 		.procname	= "vsyscall32",
 		.data		= &vdso32_enabled,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= (int *)&zero,
+		.extra2		= (int *)&one,
 	},
 	{}
 };
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 81b321ace8e0..f924629836a8 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -507,6 +507,9 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
 		cpuc->lbr_entries[i].mispred	= 0;
 		cpuc->lbr_entries[i].predicted	= 0;
+		cpuc->lbr_entries[i].in_tx	= 0;
+		cpuc->lbr_entries[i].abort	= 0;
+		cpuc->lbr_entries[i].cycles	= 0;
 		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 9d49c18b5ea9..3762536619f8 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -287,7 +287,7 @@ struct task_struct;
 
 #define	ARCH_DLINFO_IA32						\
 do {									\
-	if (vdso32_enabled) {						\
+	if (VDSO_CURRENT_BASE) {					\
 		NEW_AUX_ENT(AT_SYSINFO,	VDSO_ENTRY);			\
 		NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE);	\
 	}								\
diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_schemata.c
index f369cb8db0d5..badd2b31a560 100644
--- a/arch/x86/kernel/cpu/intel_rdt_schemata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_schemata.c
@@ -200,11 +200,11 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	}
 
 out:
-	rdtgroup_kn_unlock(of->kn);
 	for_each_enabled_rdt_resource(r) {
 		kfree(r->tmp_cbms);
 		r->tmp_cbms = NULL;
 	}
+	rdtgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
 }
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 396c042e9d0e..cc30a74e4adb 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -846,7 +846,7 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
 		       task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
 		       me->comm, me->pid, where, frame,
 		       regs->ip, regs->sp, regs->orig_ax);
-		print_vma_addr(" in ", regs->ip);
+		print_vma_addr(KERN_CONT " in ", regs->ip);
 		pr_cont("\n");
 	}
 
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index ec1f756f9dc9..71beb28600d4 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -151,8 +151,8 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from,
 
 				if (from->si_signo == SIGSEGV) {
 					if (from->si_code == SEGV_BNDERR) {
-						compat_uptr_t lower = (unsigned long)&to->si_lower;
-						compat_uptr_t upper = (unsigned long)&to->si_upper;
+						compat_uptr_t lower = (unsigned long)from->si_lower;
+						compat_uptr_t upper = (unsigned long)from->si_upper;
 						put_user_ex(lower, &to->si_lower);
 						put_user_ex(upper, &to->si_upper);
 					}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 948443e115c1..4e496379a871 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -255,7 +255,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 		pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx",
 			tsk->comm, tsk->pid, str,
 			regs->ip, regs->sp, error_code);
-		print_vma_addr(" in ", regs->ip);
+		print_vma_addr(KERN_CONT " in ", regs->ip);
 		pr_cont("\n");
 	}
 
@@ -519,7 +519,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
 		pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx",
 			tsk->comm, task_pid_nr(tsk),
 			regs->ip, regs->sp, error_code);
-		print_vma_addr(" in ", regs->ip);
+		print_vma_addr(KERN_CONT " in ", regs->ip);
 		pr_cont("\n");
 	}
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2ee00dbbbd51..259e9b28ccf8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8198,6 +8198,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
 	case EXIT_REASON_PREEMPTION_TIMER:
 		return false;
+	case EXIT_REASON_PML_FULL:
+		/* We don't expose PML support to L1. */
+		return false;
 	default:
 		return true;
 	}
@@ -10267,6 +10270,18 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	}
 
+	if (enable_pml) {
+		/*
+		 * Conceptually we want to copy the PML address and index from
+		 * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
+		 * since we always flush the log on each vmexit, this happens
+		 * to be equivalent to simply resetting the fields in vmcs02.
+		 */
+		ASSERT(vmx->pml_pg);
+		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+	}
+
 	if (nested_cpu_has_ept(vmcs12)) {
 		kvm_mmu_unload(vcpu);
 		nested_ept_init_mmu_context(vcpu);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 22af912d66d2..889e7619a091 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -643,21 +643,40 @@ void __init init_mem_mapping(void)
  * devmem_is_allowed() checks to see if /dev/mem access to a certain address
  * is valid. The argument is a physical page number.
  *
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains BIOS code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
+ * On x86, access has to be given to the first megabyte of RAM because that
+ * area traditionally contains BIOS code and data regions used by X, dosemu,
+ * and similar apps. Since they map the entire memory range, the whole range
+ * must be allowed (for mapping), but any areas that would otherwise be
+ * disallowed are flagged as being "zero filled" instead of rejected.
+ * Access has to be given to non-kernel-ram areas as well, these contain the
+ * PCI mmio resources as well as potential bios/acpi data regions.
  */
 int devmem_is_allowed(unsigned long pagenr)
 {
-	if (pagenr < 256)
-		return 1;
-	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+	if (page_is_ram(pagenr)) {
+		/*
+		 * For disallowed memory regions in the low 1MB range,
+		 * request that the page be shown as all zeros.
+		 */
+		if (pagenr < 256)
+			return 2;
+
+		return 0;
+	}
+
+	/*
+	 * This must follow RAM test, since System RAM is considered a
+	 * restricted resource under CONFIG_STRICT_IOMEM.
+	 */
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) {
+		/* Low 1MB bypasses iomem restrictions. */
+		if (pagenr < 256)
+			return 1;
+
 		return 0;
-	if (!page_is_ram(pagenr))
-		return 1;
-	return 0;
+	}
+
+	return 1;
 }
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 30031d5293c4..cdfe8c628959 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -201,6 +201,10 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
 		return;
 	}
 
+	/* No need to reserve regions that will never be freed. */
+	if (md.attribute & EFI_MEMORY_RUNTIME)
+		return;
+
 	size += addr % EFI_PAGE_SIZE;
 	size = round_up(size, EFI_PAGE_SIZE);
 	addr = round_down(addr, EFI_PAGE_SIZE);