Merge tag 'v3.7' into stable/for-linus-3.8

Linux 3.7

* tag 'v3.7': (833 commits)
  Linux 3.7
  Input: matrix-keymap - provide proper module license
  Revert "revert "Revert "mm: remove __GFP_NO_KSWAPD""" and associated damage
  ipv4: ip_check_defrag must not modify skb before unsharing
  Revert "mm: avoid waking kswapd for THP allocations when compaction is deferred or contended"
  inet_diag: validate port comparison byte code to prevent unsafe reads
  inet_diag: avoid unsafe and nonsensical prefix matches in inet_diag_bc_run()
  inet_diag: validate byte code to prevent oops in inet_diag_bc_run()
  inet_diag: fix oops for IPv4 AF_INET6 TCP SYN-RECV state
  mm: vmscan: fix inappropriate zone congestion clearing
  vfs: fix O_DIRECT read past end of block device
  net: gro: fix possible panic in skb_gro_receive()
  tcp: bug fix Fast Open client retransmission
  tmpfs: fix shared mempolicy leak
  mm: vmscan: do not keep kswapd looping forever due to individual uncompactable zones
  mm: compaction: validate pfn range passed to isolate_freepages_block
  mmc: sh-mmcif: avoid oops on spurious interrupts (second try)
  Revert misapplied "mmc: sh-mmcif: avoid oops on spurious interrupts"
  mmc: sdhci-s3c: fix missing clock for gpio card-detect
  lib/Makefile: Fix oid_registry build dependency
  ...

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Conflicts:
	arch/arm/xen/enlighten.c
	drivers/xen/Makefile

[We need to have the v3.7 base as the 'for-3.8' was based off v3.7-rc3
and there are some patches in v3.7-rc6 that we to have in our branch]

23 files changed, 226 insertions, 94 deletions

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index c760e07..e87b0ca 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -12,6 +12,8 @@
 #include <asm/setup.h>
 #include <asm/desc.h>
 
+#undef memcpy			/* Use memcpy from misc.c */
+
 #include "eboot.h"
 
 static efi_system_table_t *sys_table;
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 2a01744..8c132a6 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -476,6 +476,3 @@ die:
 setup_corrupt:
 	.byte	7
 	.string	"No setup signature found...\n"
-
-	.data
-dummy:	.long	0
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 66e5f0e..79fd8a3 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -12,6 +12,7 @@ header-y += mce.h
 header-y += msr-index.h
 header-y += msr.h
 header-y += mtrr.h
+header-y += perf_regs.h
 header-y += posix_types_32.h
 header-y += posix_types_64.h
 header-y += posix_types_x32.h
@@ -19,8 +20,10 @@ header-y += prctl.h
 header-y += processor-flags.h
 header-y += ptrace-abi.h
 header-y += sigcontext32.h
+header-y += svm.h
 header-y += ucontext.h
 header-y += vm86.h
+header-y += vmx.h
 header-y += vsyscall.h
 
 genhdr-y += unistd_32.h
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 831dbb9..41ab26e 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -399,14 +399,17 @@ static inline void drop_init_fpu(struct task_struct *tsk)
 typedef struct { int preload; } fpu_switch_t;
 
 /*
- * FIXME! We could do a totally lazy restore, but we need to
- * add a per-cpu "this was the task that last touched the FPU
- * on this CPU" variable, and the task needs to have a "I last
- * touched the FPU on this CPU" and check them.
+ * Must be run with preemption disabled: this clears the fpu_owner_task,
+ * on this CPU.
  *
- * We don't do that yet, so "fpu_lazy_restore()" always returns
- * false, but some day..
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
  */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+	per_cpu(fpu_owner_task, cpu) = NULL;
+}
+
 static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
 {
 	return new == this_cpu_read_stable(fpu_owner_task) &&
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index dcfde52..19f16eb 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -205,21 +205,14 @@ static inline bool user_64bit_mode(struct pt_regs *regs)
 }
 #endif
 
-/*
- * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
- * when it traps.  The previous stack will be directly underneath the saved
- * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
- *
- * This is valid only for kernel mode traps.
- */
-static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
-{
 #ifdef CONFIG_X86_32
-	return (unsigned long)(&regs->sp);
+extern unsigned long kernel_stack_pointer(struct pt_regs *regs);
 #else
+static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
 	return regs->sp;
-#endif
 }
+#endif
 
 #define GET_IP(regs) ((regs)->ip)
 #define GET_FP(regs) ((regs)->bp)
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 59c226d..c20d1ce 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -359,18 +359,14 @@ HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
 		return _hypercall4(int, update_va_mapping, va,
 				   new_val.pte, new_val.pte >> 32, flags);
 }
+extern int __must_check xen_event_channel_op_compat(int, void *);
 
 static inline int
 HYPERVISOR_event_channel_op(int cmd, void *arg)
 {
 	int rc = _hypercall2(int, event_channel_op, cmd, arg);
-	if (unlikely(rc == -ENOSYS)) {
-		struct evtchn_op op;
-		op.cmd = cmd;
-		memcpy(&op.u, arg, sizeof(op.u));
-		rc = _hypercall1(int, event_channel_op_compat, &op);
-		memcpy(arg, &op.u, sizeof(op.u));
-	}
+	if (unlikely(rc == -ENOSYS))
+		rc = xen_event_channel_op_compat(cmd, arg);
 	return rc;
 }
 
@@ -386,17 +382,14 @@ HYPERVISOR_console_io(int cmd, int count, char *str)
 	return _hypercall3(int, console_io, cmd, count, str);
 }
 
+extern int __must_check HYPERVISOR_physdev_op_compat(int, void *);
+
 static inline int
 HYPERVISOR_physdev_op(int cmd, void *arg)
 {
 	int rc = _hypercall2(int, physdev_op, cmd, arg);
-	if (unlikely(rc == -ENOSYS)) {
-		struct physdev_op op;
-		op.cmd = cmd;
-		memcpy(&op.u, arg, sizeof(op.u));
-		rc = _hypercall1(int, physdev_op_compat, &op);
-		memcpy(arg, &op.u, sizeof(op.u));
-	}
+	if (unlikely(rc == -ENOSYS))
+		rc = HYPERVISOR_physdev_op_compat(cmd, arg);
 	return rc;
 }
 
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 66d0fff..125f344 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -33,7 +33,6 @@
 #ifndef _ASM_X86_XEN_HYPERVISOR_H
 #define _ASM_X86_XEN_HYPERVISOR_H
 
-/* arch/i386/kernel/setup.c */
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f7e98a2..1b7d165 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -631,6 +631,20 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		}
 	}
 
+	/*
+	 * The way access filter has a performance penalty on some workloads.
+	 * Disable it on the affected CPUs.
+	 */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+		u64 val;
+
+		if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+			val |= 0x1E;
+			wrmsrl_safe(0xc0011021, val);
+		}
+	}
+
 	cpu_detect_cache_sizes(c);
 
 	/* Multi core CPU? */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 698b6ec..1ac581f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -6,7 +6,7 @@
  *
  *  Written by Jacob Shin - AMD, Inc.
  *
- *  Support: borislav.petkov@amd.com
+ *  Maintained by: Borislav Petkov <bp@alien8.de>
  *
  *  April 2006
  *     - added support for AMD Family 0x10 processors
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 5f88abf..4f9a3cb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -285,34 +285,39 @@ void cmci_clear(void)
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
+static long cmci_rediscover_work_func(void *arg)
+{
+	int banks;
+
+	/* Recheck banks in case CPUs don't all have the same */
+	if (cmci_supported(&banks))
+		cmci_discover(banks);
+
+	return 0;
+}
+
 /*
  * After a CPU went down cycle through all the others and rediscover
  * Must run in process context.
  */
 void cmci_rediscover(int dying)
 {
-	int banks;
-	int cpu;
-	cpumask_var_t old;
+	int cpu, banks;
 
 	if (!cmci_supported(&banks))
 		return;
-	if (!alloc_cpumask_var(&old, GFP_KERNEL))
-		return;
-	cpumask_copy(old, &current->cpus_allowed);
 
 	for_each_online_cpu(cpu) {
 		if (cpu == dying)
 			continue;
-		if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
+
+		if (cpu == smp_processor_id()) {
+			cmci_rediscover_work_func(NULL);
 			continue;
-		/* Recheck banks in case CPUs don't all have the same */
-		if (cmci_supported(&banks))
-			cmci_discover(banks);
-	}
+		}
 
-	set_cpus_allowed_ptr(current, old);
-	free_cpumask_var(old);
+		work_on_cpu(cpu, cmci_rediscover_work_func, NULL);
+	}
 }
 
 /*
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b51b2c7..1328fe4 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -995,8 +995,8 @@ END(interrupt)
 	 */
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 common_interrupt:
-	ASM_CLAC
 	XCPT_FRAME
+	ASM_CLAC
 	addq $-0x80,(%rsp)		/* Adjust vector to [-256,-1] range */
 	interrupt do_IRQ
 	/* 0(%rsp): old_rsp-ARGOFFSET */
@@ -1135,8 +1135,8 @@ END(common_interrupt)
  */
 .macro apicinterrupt num sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	pushq_cfi $~(\num)
 .Lcommon_\sym:
 	interrupt \do_sym
@@ -1190,8 +1190,8 @@ apicinterrupt IRQ_WORK_VECTOR \
  */
 .macro zeroentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
 	subq $ORIG_RAX-R15, %rsp
@@ -1208,8 +1208,8 @@ END(\sym)
 
 .macro paranoidzeroentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
 	subq $ORIG_RAX-R15, %rsp
@@ -1227,8 +1227,8 @@ END(\sym)
 #define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8)
 .macro paranoidzeroentry_ist sym do_sym ist
 ENTRY(\sym)
-	ASM_CLAC
 	INTR_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
 	subq $ORIG_RAX-R15, %rsp
@@ -1247,8 +1247,8 @@ END(\sym)
 
 .macro errorentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	XCPT_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	subq $ORIG_RAX-R15, %rsp
 	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
@@ -1266,8 +1266,8 @@ END(\sym)
 	/* error code is on the stack already */
 .macro paranoiderrorentry sym do_sym
 ENTRY(\sym)
-	ASM_CLAC
 	XCPT_FRAME
+	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	subq $ORIG_RAX-R15, %rsp
 	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 957a47a..4dac2f6 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -292,8 +292,8 @@ default_entry:
  *	be using the global pages. 
  *
  *	NOTE! If we are on a 486 we may have no cr4 at all!
- *	Specifically, cr4 exists if and only if CPUID exists,
- *	which in turn exists if and only if EFLAGS.ID exists.
+ *	Specifically, cr4 exists if and only if CPUID exists
+ *	and has flags other than the FPU flag set.
  */
 	movl $X86_EFLAGS_ID,%ecx
 	pushl %ecx
@@ -308,6 +308,11 @@ default_entry:
 	testl %ecx,%eax
 	jz 6f			# No ID flag = no CPUID = no CR4
 
+	movl $1,%eax
+	cpuid
+	andl $~1,%edx		# Ignore CPUID.FPU
+	jz 6f			# No flags or only CPUID.FPU = no CR4
+
 	movl pa(mmu_cr4_features),%eax
 	movl %eax,%cr4
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7720ff5..efdec7c 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -8,8 +8,8 @@
  *  Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
  *
  *  Maintainers:
- *  Andreas Herrmann <andreas.herrmann3@amd.com>
- *  Borislav Petkov <borislav.petkov@amd.com>
+ *  Andreas Herrmann <herrmann.der.user@googlemail.com>
+ *  Borislav Petkov <bp@alien8.de>
  *
  *  This driver allows to upgrade microcode on F10h AMD
  *  CPUs and later.
@@ -190,6 +190,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
 #define F1XH_MPB_MAX_SIZE 2048
 #define F14H_MPB_MAX_SIZE 1824
 #define F15H_MPB_MAX_SIZE 4096
+#define F16H_MPB_MAX_SIZE 3458
 
 	switch (c->x86) {
 	case 0x14:
@@ -198,6 +199,9 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size,
 	case 0x15:
 		max_size = F15H_MPB_MAX_SIZE;
 		break;
+	case 0x16:
+		max_size = F16H_MPB_MAX_SIZE;
+		break;
 	default:
 		max_size = F1XH_MPB_MAX_SIZE;
 		break;
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index b00b33a..974b67e 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/rcupdate.h>
+#include <linux/module.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -166,6 +167,35 @@ static inline bool invalid_selector(u16 value)
 
 #define FLAG_MASK		FLAG_MASK_32
 
+/*
+ * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
+ * when it traps.  The previous stack will be directly underneath the saved
+ * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
+ *
+ * Now, if the stack is empty, '&regs->sp' is out of range. In this
+ * case we try to take the previous stack. To always return a non-null
+ * stack pointer we fall back to regs as stack if no previous stack
+ * exists.
+ *
+ * This is valid only for kernel mode traps.
+ */
+unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1);
+	unsigned long sp = (unsigned long)&regs->sp;
+	struct thread_info *tinfo;
+
+	if (context == (sp & ~(THREAD_SIZE - 1)))
+		return sp;
+
+	tinfo = (struct thread_info *)context;
+	if (tinfo->previous_esp)
+		return tinfo->previous_esp;
+
+	return (unsigned long)regs;
+}
+EXPORT_SYMBOL_GPL(kernel_stack_pointer);
+
 static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
 {
 	BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
@@ -1511,6 +1541,13 @@ void syscall_trace_leave(struct pt_regs *regs)
 {
 	bool step;
 
+	/*
+	 * We may come here right after calling schedule_user()
+	 * or do_notify_resume(), in which case we can be in RCU
+	 * user mode.
+	 */
+	rcu_user_exit();
+
 	audit_syscall_exit(regs);
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c80a33b..f3e2ec8 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -68,6 +68,8 @@
 #include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
@@ -818,6 +820,9 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 
 	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
 
+	/* the FPU context is blank, nobody can own it */
+	__cpu_disable_lazy_restore(cpu);
+
 	err = do_boot_cpu(apicid, cpu, tidle);
 	if (err) {
 		pr_debug("do_boot_cpu failed %d\n", err);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index a10e460..58fc514 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -24,6 +24,9 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
 
+	if (!static_cpu_has(X86_FEATURE_XSAVE))
+		return 0;
+
 	best = kvm_find_cpuid_entry(vcpu, 1, 0);
 	return best && (best->ecx & bit(X86_FEATURE_XSAVE));
 }
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 39171cb..bba39bf 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -426,8 +426,7 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 			_ASM_EXTABLE(1b, 3b)				\
 			: "=m" ((ctxt)->eflags), "=&r" (_tmp),		\
 			  "+a" (*rax), "+d" (*rdx), "+qm"(_ex)		\
-			: "i" (EFLAGS_MASK), "m" ((ctxt)->src.val),	\
-			  "a" (*rax), "d" (*rdx));			\
+			: "i" (EFLAGS_MASK), "m" ((ctxt)->src.val));	\
 	} while (0)
 
 /* instruction has only one source operand, destination is implicit (e.g. mul, div, imul, idiv) */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ad6b1dd..f858159 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6549,19 +6549,22 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
 	/* Exposing INVPCID only when PCID is exposed */
 	best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
 	if (vmx_invpcid_supported() &&
 	    best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
 	    guest_cpuid_has_pcid(vcpu)) {
+		exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
 		exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
 		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
 			     exec_control);
 	} else {
-		exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
-		vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
-			     exec_control);
+		if (cpu_has_secondary_exec_ctrls()) {
+			exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+			exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
+			vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
+				     exec_control);
+		}
 		if (best)
 			best->ebx &= ~bit(X86_FEATURE_INVPCID);
 	}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1eefebe..4f76417 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3779,7 +3779,7 @@ static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
 {
 	struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0];
 
-	memcpy(vcpu->run->mmio.data, frag->data, frag->len);
+	memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len));
 	return X86EMUL_CONTINUE;
 }
 
@@ -3832,18 +3832,11 @@ mmio:
 	bytes -= handled;
 	val += handled;
 
-	while (bytes) {
-		unsigned now = min(bytes, 8U);
-
-		frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
-		frag->gpa = gpa;
-		frag->data = val;
-		frag->len = now;
-
-		gpa += now;
-		val += now;
-		bytes -= now;
-	}
+	WARN_ON(vcpu->mmio_nr_fragments >= KVM_MAX_MMIO_FRAGMENTS);
+	frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
+	frag->gpa = gpa;
+	frag->data = val;
+	frag->len = bytes;
 	return X86EMUL_CONTINUE;
 }
 
@@ -3890,7 +3883,7 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
 	vcpu->mmio_needed = 1;
 	vcpu->mmio_cur_fragment = 0;
 
-	vcpu->run->mmio.len = vcpu->mmio_fragments[0].len;
+	vcpu->run->mmio.len = min(8u, vcpu->mmio_fragments[0].len);
 	vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write;
 	vcpu->run->exit_reason = KVM_EXIT_MMIO;
 	vcpu->run->mmio.phys_addr = gpa;
@@ -5522,28 +5515,44 @@ static int complete_emulated_pio(struct kvm_vcpu *vcpu)
  *
  * read:
  *   for each fragment
- *     write gpa, len
- *     exit
- *     copy data
+ *     for each mmio piece in the fragment
+ *       write gpa, len
+ *       exit
+ *       copy data
  *   execute insn
  *
  * write:
  *   for each fragment
- *      write gpa, len
- *      copy data
- *      exit
+ *     for each mmio piece in the fragment
+ *       write gpa, len
+ *       copy data
+ *       exit
  */
 static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 	struct kvm_mmio_fragment *frag;
+	unsigned len;
 
 	BUG_ON(!vcpu->mmio_needed);
 
 	/* Complete previous fragment */
-	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++];
+	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment];
+	len = min(8u, frag->len);
 	if (!vcpu->mmio_is_write)
-		memcpy(frag->data, run->mmio.data, frag->len);
+		memcpy(frag->data, run->mmio.data, len);
+
+	if (frag->len <= 8) {
+		/* Switch to the next fragment. */
+		frag++;
+		vcpu->mmio_cur_fragment++;
+	} else {
+		/* Go forward to the next mmio piece. */
+		frag->data += len;
+		frag->gpa += len;
+		frag->len -= len;
+	}
+
 	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
 		if (vcpu->mmio_is_write)
@@ -5551,13 +5560,12 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 		vcpu->mmio_read_completed = 1;
 		return complete_emulated_io(vcpu);
 	}
-	/* Initiate next fragment */
-	++frag;
+
 	run->exit_reason = KVM_EXIT_MMIO;
 	run->mmio.phys_addr = frag->gpa;
 	if (vcpu->mmio_is_write)
-		memcpy(run->mmio.data, frag->data, frag->len);
-	run->mmio.len = frag->len;
+		memcpy(run->mmio.data, frag->data, min(8u, frag->len));
+	run->mmio.len = min(8u, frag->len);
 	run->mmio.is_write = vcpu->mmio_is_write;
 	vcpu->arch.complete_userspace_io = complete_emulated_mmio;
 	return 0;
@@ -5773,6 +5781,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 
+	if (!guest_cpuid_has_xsave(vcpu) && (sregs->cr4 & X86_CR4_OSXSAVE))
+		return -EINVAL;
+
 	dt.size = sregs->idt.limit;
 	dt.address = sregs->idt.base;
 	kvm_x86_ops->set_idt(vcpu, &dt);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 0777f04..60f926c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -197,7 +197,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	}
 
 	if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1
-					|| vmflag == VM_HUGETLB) {
+					|| vmflag & VM_HUGETLB) {
 		local_flush_tlb();
 		goto flush_all;
 	}
diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c
index 41bd2a2..b914e20 100644
--- a/arch/x86/pci/ce4100.c
+++ b/arch/x86/pci/ce4100.c
@@ -115,6 +115,16 @@ static void sata_revid_read(struct sim_dev_reg *reg, u32 *value)
 	reg_read(reg, value);
 }
 
+static void reg_noirq_read(struct sim_dev_reg *reg, u32 *value)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&pci_config_lock, flags);
+	/* force interrupt pin value to 0 */
+	*value = reg->sim_reg.value & 0xfff00ff;
+	raw_spin_unlock_irqrestore(&pci_config_lock, flags);
+}
+
 static struct sim_dev_reg bus1_fixups[] = {
 	DEFINE_REG(2, 0, 0x10, (16*MB), reg_init, reg_read, reg_write)
 	DEFINE_REG(2, 0, 0x14, (256), reg_init, reg_read, reg_write)
@@ -144,6 +154,7 @@ static struct sim_dev_reg bus1_fixups[] = {
 	DEFINE_REG(11, 5, 0x10, (64*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(11, 6, 0x10, (256), reg_init, reg_read, reg_write)
 	DEFINE_REG(11, 7, 0x10, (64*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(11, 7, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
 	DEFINE_REG(12, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(12, 0, 0x14, (256), reg_init, reg_read, reg_write)
 	DEFINE_REG(12, 1, 0x10, (1024), reg_init, reg_read, reg_write)
@@ -161,8 +172,10 @@ static struct sim_dev_reg bus1_fixups[] = {
 	DEFINE_REG(16, 0, 0x10, (64*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(16, 0, 0x14, (64*MB), reg_init, reg_read, reg_write)
 	DEFINE_REG(16, 0, 0x18, (64*MB), reg_init, reg_read, reg_write)
+	DEFINE_REG(16, 0, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
 	DEFINE_REG(17, 0, 0x10, (128*KB), reg_init, reg_read, reg_write)
 	DEFINE_REG(18, 0, 0x10, (1*KB), reg_init, reg_read, reg_write)
+	DEFINE_REG(18, 0, 0x3c, 256, reg_init, reg_noirq_read, reg_write)
 };
 
 static void __init init_sim_regs(void)
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index 4c61b52..92525cb 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -21,12 +21,25 @@
 #include <asm/i8259.h>
 #include <asm/io.h>
 #include <asm/io_apic.h>
+#include <asm/emergency-restart.h>
 
 static int ce4100_i8042_detect(void)
 {
 	return 0;
 }
 
+/*
+ * The CE4100 platform has an internal 8051 Microcontroller which is
+ * responsible for signaling to the external Power Management Unit the
+ * intention to reset, reboot or power off the system. This 8051 device has
+ * its command register mapped at I/O port 0xcf9 and the value 0x4 is used
+ * to power off the system.
+ */
+static void ce4100_power_off(void)
+{
+	outb(0x4, 0xcf9);
+}
+
 #ifdef CONFIG_SERIAL_8250
 
 static unsigned int mem_serial_in(struct uart_port *p, int offset)
@@ -139,8 +152,19 @@ void __init x86_ce4100_early_setup(void)
 	x86_init.mpparse.find_smp_config = x86_init_noop;
 	x86_init.pci.init = ce4100_pci_init;
 
+	/*
+	 * By default, the reboot method is ACPI which is supported by the
+	 * CE4100 bootloader CEFDK using FADT.ResetReg Address and ResetValue
+	 * the bootloader will however issue a system power off instead of
+	 * reboot. By using BOOT_KBD we ensure proper system reboot as
+	 * expected.
+	 */
+	reboot_type = BOOT_KBD;
+
 #ifdef CONFIG_X86_IO_APIC
 	x86_init.pci.init_irq = sdv_pci_init;
 	x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck;
 #endif
+
+	pm_power_off = ce4100_power_off;
 }
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index fd8393f..01de35c 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1288,6 +1288,25 @@ unsigned long xen_read_cr2_direct(void)
 	return this_cpu_read(xen_vcpu_info.arch.cr2);
 }
 
+void xen_flush_tlb_all(void)
+{
+	struct mmuext_op *op;
+	struct multicall_space mcs;
+
+	trace_xen_mmu_flush_tlb_all(0);
+
+	preempt_disable();
+
+	mcs = xen_mc_entry(sizeof(*op));
+
+	op = mcs.args;
+	op->cmd = MMUEXT_TLB_FLUSH_ALL;
+	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	preempt_enable();
+}
 static void xen_flush_tlb(void)
 {
 	struct mmuext_op *op;
@@ -2520,7 +2539,7 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 	err = 0;
 out:
 
-	flush_tlb_all();
+	xen_flush_tlb_all();
 
 	return err;
 }