Merge 4.0-rc7 into tty-next

We want the fixes in here as well, also to help out with merge issues.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

8 files changed, 63 insertions, 17 deletions

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 498b6d967138..258990688a5e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -212,11 +212,11 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
 	/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
-	INTEL_EVENT_CONSTRAINT(0x08a3, 0x4),
+	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
 	/* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
-	INTEL_EVENT_CONSTRAINT(0x0ca3, 0x4),
+	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
 	/* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
-	INTEL_EVENT_CONSTRAINT(0x04a3, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf),
 	EVENT_CONSTRAINT_END
 };
 
@@ -1649,11 +1649,11 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event
 	if (c)
 		return c;
 
-	c = intel_pebs_constraints(event);
+	c = intel_shared_regs_constraints(cpuc, event);
 	if (c)
 		return c;
 
-	c = intel_shared_regs_constraints(cpuc, event);
+	c = intel_pebs_constraints(event);
 	if (c)
 		return c;
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1d74d161687c..f0095a76c182 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -364,12 +364,21 @@ system_call_fastpath:
  * Has incomplete stack frame and undefined top of stack.
  */
 ret_from_sys_call:
-	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
-	jnz int_ret_from_sys_call_fixup	/* Go the the slow path */
-
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
+
+	/*
+	 * We must check ti flags with interrupts (or at least preemption)
+	 * off because we must *never* return to userspace without
+	 * processing exit work that is enqueued if we're preempted here.
+	 * In particular, returning to userspace with any of the one-shot
+	 * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
+	 * very bad.
+	 */
+	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jnz int_ret_from_sys_call_fixup	/* Go the the slow path */
+
 	CFI_REMEMBER_STATE
 	/*
 	 * sysretq will re-enable interrupts:
@@ -386,7 +395,7 @@ ret_from_sys_call:
 
 int_ret_from_sys_call_fixup:
 	FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
-	jmp int_ret_from_sys_call
+	jmp int_ret_from_sys_call_irqs_off
 
 	/* Do syscall tracing */
 tracesys:
@@ -432,6 +441,7 @@ tracesys_phase2:
 GLOBAL(int_ret_from_sys_call)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
+int_ret_from_sys_call_irqs_off:
 	movl $_TIF_ALLWORK_MASK,%edi
 	/* edi:	mask to check */
 GLOBAL(int_with_check)
@@ -789,7 +799,21 @@ retint_swapgs:		/* return to user-space */
 	cmpq %r11,(EFLAGS-ARGOFFSET)(%rsp)	/* R11 == RFLAGS */
 	jne opportunistic_sysret_failed
 
-	testq $X86_EFLAGS_RF,%r11		/* sysret can't restore RF */
+	/*
+	 * SYSRET can't restore RF.  SYSRET can restore TF, but unlike IRET,
+	 * restoring TF results in a trap from userspace immediately after
+	 * SYSRET.  This would cause an infinite loop whenever #DB happens
+	 * with register state that satisfies the opportunistic SYSRET
+	 * conditions.  For example, single-stepping this user code:
+	 *
+	 *           movq $stuck_here,%rcx
+	 *           pushfq
+	 *           popq %r11
+	 *   stuck_here:
+	 *
+	 * would never get past 'stuck_here'.
+	 */
+	testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
 	jnz opportunistic_sysret_failed
 
 	/* nothing to check for RSP */
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 7ec1d5f8d283..25ecd56cefa8 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -72,7 +72,7 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] =
 	{ "bx", 8, offsetof(struct pt_regs, bx) },
 	{ "cx", 8, offsetof(struct pt_regs, cx) },
 	{ "dx", 8, offsetof(struct pt_regs, dx) },
-	{ "si", 8, offsetof(struct pt_regs, dx) },
+	{ "si", 8, offsetof(struct pt_regs, si) },
 	{ "di", 8, offsetof(struct pt_regs, di) },
 	{ "bp", 8, offsetof(struct pt_regs, bp) },
 	{ "sp", 8, offsetof(struct pt_regs, sp) },
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index bae6c609888e..86db4bcd7ce5 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -183,6 +183,16 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 		},
 	},
 
+	/* ASRock */
+	{	/* Handle problems with rebooting on ASRock Q1900DC-ITX */
+		.callback = set_pci_reboot,
+		.ident = "ASRock Q1900DC-ITX",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASRock"),
+			DMI_MATCH(DMI_BOARD_NAME, "Q1900DC-ITX"),
+		},
+	},
+
 	/* ASUS */
 	{	/* Handle problems with rebooting on ASUS P4S800 */
 		.callback = set_bios_reboot,
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index b1947e0f3e10..46d4449772bc 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -422,6 +422,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 			struct kvm_ioapic *ioapic, int vector, int trigger_mode)
 {
 	int i;
+	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
 		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
@@ -443,7 +444,8 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 		kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
 		spin_lock(&ioapic->lock);
 
-		if (trigger_mode != IOAPIC_LEVEL_TRIG)
+		if (trigger_mode != IOAPIC_LEVEL_TRIG ||
+		    kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)
 			continue;
 
 		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index bd4e34de24c7..4ee827d7bf36 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -833,8 +833,7 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 
 static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
 {
-	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
-	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
+	if (kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
 		int trigger_mode;
 		if (apic_test_vector(vector, apic->regs + APIC_TMR))
 			trigger_mode = IOAPIC_LEVEL_TRIG;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 10a481b7674d..ae4f6d35d19c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2479,8 +2479,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	if (enable_ept) {
 		/* nested EPT: emulate EPT also to L1 */
 		vmx->nested.nested_vmx_secondary_ctls_high |=
-			SECONDARY_EXEC_ENABLE_EPT |
-			SECONDARY_EXEC_UNRESTRICTED_GUEST;
+			SECONDARY_EXEC_ENABLE_EPT;
 		vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
 			 VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
 			 VMX_EPT_INVEPT_BIT;
@@ -2494,6 +2493,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	} else
 		vmx->nested.nested_vmx_ept_caps = 0;
 
+	if (enable_unrestricted_guest)
+		vmx->nested.nested_vmx_secondary_ctls_high |=
+			SECONDARY_EXEC_UNRESTRICTED_GUEST;
+
 	/* miscellaneous data */
 	rdmsr(MSR_IA32_VMX_MISC,
 		vmx->nested.nested_vmx_misc_low,
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 9f93af56a5fc..b47124d4cd67 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -91,6 +91,12 @@ EXPORT_SYMBOL_GPL(xen_p2m_size);
 unsigned long xen_max_p2m_pfn __read_mostly;
 EXPORT_SYMBOL_GPL(xen_max_p2m_pfn);
 
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
+#define P2M_LIMIT CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
+#else
+#define P2M_LIMIT 0
+#endif
+
 static DEFINE_SPINLOCK(p2m_update_lock);
 
 static unsigned long *p2m_mid_missing_mfn;
@@ -385,9 +391,11 @@ static void __init xen_rebuild_p2m_list(unsigned long *p2m)
 void __init xen_vmalloc_p2m_tree(void)
 {
 	static struct vm_struct vm;
+	unsigned long p2m_limit;
 
+	p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE;
 	vm.flags = VM_ALLOC;
-	vm.size = ALIGN(sizeof(unsigned long) * xen_max_p2m_pfn,
+	vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit),
 			PMD_SIZE * PMDS_PER_MID_PAGE);
 	vm_area_register_early(&vm, PMD_SIZE * PMDS_PER_MID_PAGE);
 	pr_notice("p2m virtual area at %p, size is %lx\n", vm.addr, vm.size);